dma: import dmaengine from Linux From Linux 5.2. Signed-off-by: Barret Rhoden <brho@cs.berkeley.edu>
diff --git a/kern/drivers/dma/dmaengine.c b/kern/drivers/dma/dmaengine.c new file mode 100644 index 0000000..3a11b10 --- /dev/null +++ b/kern/drivers/dma/dmaengine.c
@@ -0,0 +1,1383 @@ +/* + * Copyright(c) 2004 - 2006 Intel Corporation. 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 as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + * 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. + */ + +/* + * This code implements the DMA subsystem. It provides a HW-neutral interface + * for other kernel code to use asynchronous memory copy capabilities, + * if present, and allows different HW DMA drivers to register as providing + * this capability. + * + * Due to the fact we are accelerating what is already a relatively fast + * operation, the code goes to great lengths to avoid additional overhead, + * such as locking. + * + * LOCKING: + * + * The subsystem keeps a global list of dma_device structs it is protected by a + * mutex, dma_list_mutex. + * + * A subsystem can get access to a channel by calling dmaengine_get() followed + * by dma_find_channel(), or if it has need for an exclusive channel it can call + * dma_request_channel(). Once a channel is allocated a reference is taken + * against its corresponding driver to disable removal. + * + * 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. + * + * See Documentation/driver-api/dmaengine for more details + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/platform_device.h> +#include <linux/dma-mapping.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/mm.h> +#include <linux/device.h> +#include <linux/dmaengine.h> +#include <linux/hardirq.h> +#include <linux/spinlock.h> +#include <linux/percpu.h> +#include <linux/rcupdate.h> +#include <linux/mutex.h> +#include <linux/jiffies.h> +#include <linux/rculist.h> +#include <linux/idr.h> +#include <linux/slab.h> +#include <linux/acpi.h> +#include <linux/acpi_dma.h> +#include <linux/of_dma.h> +#include <linux/mempool.h> +#include <linux/numa.h> + +static DEFINE_MUTEX(dma_list_mutex); +static DEFINE_IDA(dma_ida); +static LIST_HEAD(dma_device_list); +static long dmaengine_ref_count; + +/* --- sysfs implementation --- */ + +/** + * dev_to_dma_chan - convert a device pointer to the its sysfs container object + * @dev - device node + * + * Must be called under dma_list_mutex + */ +static struct dma_chan *dev_to_dma_chan(struct device *dev) +{ + struct dma_chan_dev *chan_dev; + + chan_dev = container_of(dev, typeof(*chan_dev), device); + return chan_dev->chan; +} + +static ssize_t memcpy_count_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct dma_chan *chan; + unsigned long count = 0; + int i; + int err; + + mutex_lock(&dma_list_mutex); + chan = dev_to_dma_chan(dev); + if (chan) { + for_each_possible_cpu(i) + count += per_cpu_ptr(chan->local, i)->memcpy_count; + err = sprintf(buf, "%lu\n", count); + } else + err = -ENODEV; + mutex_unlock(&dma_list_mutex); + + return err; +} +static DEVICE_ATTR_RO(memcpy_count); + +static ssize_t bytes_transferred_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct dma_chan *chan; + unsigned long count = 0; + int i; + int err; + + mutex_lock(&dma_list_mutex); + chan = dev_to_dma_chan(dev); + if (chan) { + for_each_possible_cpu(i) + count += per_cpu_ptr(chan->local, i)->bytes_transferred; + err = sprintf(buf, "%lu\n", count); + } else + err = -ENODEV; + mutex_unlock(&dma_list_mutex); + + return err; +} +static DEVICE_ATTR_RO(bytes_transferred); + +static ssize_t in_use_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct dma_chan *chan; + int err; + + mutex_lock(&dma_list_mutex); + chan = dev_to_dma_chan(dev); + if (chan) + err = sprintf(buf, "%d\n", chan->client_count); + else + err = -ENODEV; + mutex_unlock(&dma_list_mutex); + + return err; +} +static DEVICE_ATTR_RO(in_use); + +static struct attribute *dma_dev_attrs[] = { + &dev_attr_memcpy_count.attr, + &dev_attr_bytes_transferred.attr, + &dev_attr_in_use.attr, + NULL, +}; +ATTRIBUTE_GROUPS(dma_dev); + +static void chan_dev_release(struct device *dev) +{ + struct dma_chan_dev *chan_dev; + + chan_dev = container_of(dev, typeof(*chan_dev), device); + if (atomic_dec_and_test(chan_dev->idr_ref)) { + ida_free(&dma_ida, chan_dev->dev_id); + kfree(chan_dev->idr_ref); + } + kfree(chan_dev); +} + +static struct class dma_devclass = { + .name = "dma", + .dev_groups = dma_dev_groups, + .dev_release = chan_dev_release, +}; + +/* --- client and device registration --- */ + +#define dma_device_satisfies_mask(device, mask) \ + __dma_device_satisfies_mask((device), &(mask)) +static int +__dma_device_satisfies_mask(struct dma_device *device, + const dma_cap_mask_t *want) +{ + dma_cap_mask_t has; + + bitmap_and(has.bits, want->bits, device->cap_mask.bits, + DMA_TX_TYPE_END); + return bitmap_equal(want->bits, has.bits, DMA_TX_TYPE_END); +} + +static struct module *dma_chan_to_owner(struct dma_chan *chan) +{ + return chan->device->dev->driver->owner; +} + +/** + * balance_ref_count - catch up the channel reference count + * @chan - channel to balance ->client_count versus dmaengine_ref_count + * + * balance_ref_count must be called under dma_list_mutex + */ +static void balance_ref_count(struct dma_chan *chan) +{ + struct module *owner = dma_chan_to_owner(chan); + + while (chan->client_count < dmaengine_ref_count) { + __module_get(owner); + chan->client_count++; + } +} + +/** + * dma_chan_get - try to grab a dma channel's parent driver module + * @chan - channel to grab + * + * Must be called under dma_list_mutex + */ +static int dma_chan_get(struct dma_chan *chan) +{ + struct module *owner = dma_chan_to_owner(chan); + int ret; + + /* The channel is already in use, update client count */ + if (chan->client_count) { + __module_get(owner); + goto out; + } + + if (!try_module_get(owner)) + return -ENODEV; + + /* allocate upon first client reference */ + if (chan->device->device_alloc_chan_resources) { + ret = chan->device->device_alloc_chan_resources(chan); + if (ret < 0) + goto err_out; + } + + if (!dma_has_cap(DMA_PRIVATE, chan->device->cap_mask)) + balance_ref_count(chan); + +out: + chan->client_count++; + return 0; + +err_out: + module_put(owner); + return ret; +} + +/** + * dma_chan_put - drop a reference to a dma channel's parent driver module + * @chan - channel to release + * + * Must be called under dma_list_mutex + */ +static void dma_chan_put(struct dma_chan *chan) +{ + /* This channel is not in use, bail out */ + if (!chan->client_count) + return; + + chan->client_count--; + module_put(dma_chan_to_owner(chan)); + + /* This channel is not in use anymore, free it */ + if (!chan->client_count && chan->device->device_free_chan_resources) { + /* Make sure all operations have completed */ + dmaengine_synchronize(chan); + chan->device->device_free_chan_resources(chan); + } + + /* If the channel is used via a DMA request router, free the mapping */ + if (chan->router && chan->router->route_free) { + chan->router->route_free(chan->router->dev, chan->route_data); + chan->router = NULL; + chan->route_data = NULL; + } +} + +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)) { + dev_err(chan->device->dev, "%s: timeout!\n", __func__); + return DMA_ERROR; + } + if (status != DMA_IN_PROGRESS) + break; + cpu_relax(); + } while (1); + + return status; +} +EXPORT_SYMBOL(dma_sync_wait); + +/** + * dma_cap_mask_all - enable iteration over all operation types + */ +static dma_cap_mask_t dma_cap_mask_all; + +/** + * dma_chan_tbl_ent - tracks channel allocations per core/operation + * @chan - associated channel for this entry + */ +struct dma_chan_tbl_ent { + struct dma_chan *chan; +}; + +/** + * channel_table - percpu lookup table for memory-to-memory offload providers + */ +static struct dma_chan_tbl_ent __percpu *channel_table[DMA_TX_TYPE_END]; + +static int __init dma_channel_table_init(void) +{ + enum dma_transaction_type cap; + int err = 0; + + bitmap_fill(dma_cap_mask_all.bits, DMA_TX_TYPE_END); + + /* 'interrupt', 'private', and 'slave' are channel capabilities, + * but are not associated with an operation so they do not need + * an entry in the channel_table + */ + clear_bit(DMA_INTERRUPT, dma_cap_mask_all.bits); + clear_bit(DMA_PRIVATE, dma_cap_mask_all.bits); + clear_bit(DMA_SLAVE, dma_cap_mask_all.bits); + + for_each_dma_cap_mask(cap, dma_cap_mask_all) { + channel_table[cap] = alloc_percpu(struct dma_chan_tbl_ent); + if (!channel_table[cap]) { + err = -ENOMEM; + break; + } + } + + if (err) { + pr_err("initialization failure\n"); + for_each_dma_cap_mask(cap, dma_cap_mask_all) + free_percpu(channel_table[cap]); + } + + return err; +} +arch_initcall(dma_channel_table_init); + +/** + * dma_find_channel - find a channel to carry out the operation + * @tx_type: transaction type + */ +struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type) +{ + return this_cpu_read(channel_table[tx_type]->chan); +} +EXPORT_SYMBOL(dma_find_channel); + +/** + * dma_issue_pending_all - flush all pending operations across all channels + */ +void dma_issue_pending_all(void) +{ + struct dma_device *device; + struct dma_chan *chan; + + rcu_read_lock(); + list_for_each_entry_rcu(device, &dma_device_list, global_node) { + if (dma_has_cap(DMA_PRIVATE, device->cap_mask)) + continue; + list_for_each_entry(chan, &device->channels, device_node) + if (chan->client_count) + device->device_issue_pending(chan); + } + rcu_read_unlock(); +} +EXPORT_SYMBOL(dma_issue_pending_all); + +/** + * dma_chan_is_local - returns true if the channel is in the same numa-node as the cpu + */ +static bool dma_chan_is_local(struct dma_chan *chan, int cpu) +{ + int node = dev_to_node(chan->device->dev); + return node == NUMA_NO_NODE || + cpumask_test_cpu(cpu, cpumask_of_node(node)); +} + +/** + * min_chan - returns the channel with min count and in the same numa-node as the cpu + * @cap: capability to match + * @cpu: cpu index which the channel should be close to + * + * If some channels are close to the given cpu, the one with the lowest + * reference count is returned. Otherwise, cpu is ignored and only the + * reference count is taken into account. + * Must be called under dma_list_mutex. + */ +static struct dma_chan *min_chan(enum dma_transaction_type cap, int cpu) +{ + struct dma_device *device; + struct dma_chan *chan; + struct dma_chan *min = NULL; + struct dma_chan *localmin = NULL; + + list_for_each_entry(device, &dma_device_list, global_node) { + if (!dma_has_cap(cap, device->cap_mask) || + dma_has_cap(DMA_PRIVATE, device->cap_mask)) + continue; + list_for_each_entry(chan, &device->channels, device_node) { + if (!chan->client_count) + continue; + if (!min || chan->table_count < min->table_count) + min = chan; + + if (dma_chan_is_local(chan, cpu)) + if (!localmin || + chan->table_count < localmin->table_count) + localmin = chan; + } + } + + chan = localmin ? localmin : min; + + if (chan) + chan->table_count++; + + return chan; +} + +/** + * dma_channel_rebalance - redistribute the available channels + * + * Optimize for cpu isolation (each cpu gets a dedicated channel for an + * operation type) in the SMP case, and operation isolation (avoid + * multi-tasking channels) in the non-SMP case. Must be called under + * dma_list_mutex. + */ +static void dma_channel_rebalance(void) +{ + struct dma_chan *chan; + struct dma_device *device; + int cpu; + int cap; + + /* undo the last distribution */ + for_each_dma_cap_mask(cap, dma_cap_mask_all) + for_each_possible_cpu(cpu) + per_cpu_ptr(channel_table[cap], cpu)->chan = NULL; + + list_for_each_entry(device, &dma_device_list, global_node) { + if (dma_has_cap(DMA_PRIVATE, device->cap_mask)) + continue; + list_for_each_entry(chan, &device->channels, device_node) + chan->table_count = 0; + } + + /* don't populate the channel_table if no clients are available */ + if (!dmaengine_ref_count) + return; + + /* redistribute available channels */ + for_each_dma_cap_mask(cap, dma_cap_mask_all) + for_each_online_cpu(cpu) { + chan = min_chan(cap, cpu); + per_cpu_ptr(channel_table[cap], cpu)->chan = chan; + } +} + +int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps) +{ + struct dma_device *device; + + if (!chan || !caps) + return -EINVAL; + + device = chan->device; + + /* check if the channel supports slave transactions */ + if (!(test_bit(DMA_SLAVE, device->cap_mask.bits) || + test_bit(DMA_CYCLIC, device->cap_mask.bits))) + return -ENXIO; + + /* + * Check whether it reports it uses the generic slave + * capabilities, if not, that means it doesn't support any + * kind of slave capabilities reporting. + */ + if (!device->directions) + return -ENXIO; + + caps->src_addr_widths = device->src_addr_widths; + caps->dst_addr_widths = device->dst_addr_widths; + caps->directions = device->directions; + caps->max_burst = device->max_burst; + caps->residue_granularity = device->residue_granularity; + caps->descriptor_reuse = device->descriptor_reuse; + caps->cmd_pause = !!device->device_pause; + caps->cmd_resume = !!device->device_resume; + caps->cmd_terminate = !!device->device_terminate_all; + + return 0; +} +EXPORT_SYMBOL_GPL(dma_get_slave_caps); + +static struct dma_chan *private_candidate(const dma_cap_mask_t *mask, + struct dma_device *dev, + dma_filter_fn fn, void *fn_param) +{ + struct dma_chan *chan; + + if (mask && !__dma_device_satisfies_mask(dev, mask)) { + dev_dbg(dev->dev, "%s: wrong capabilities\n", __func__); + return NULL; + } + /* devices with multiple channels need special handling as we need to + * ensure that all channels are either private or public. + */ + if (dev->chancnt > 1 && !dma_has_cap(DMA_PRIVATE, dev->cap_mask)) + list_for_each_entry(chan, &dev->channels, device_node) { + /* some channels are already publicly allocated */ + if (chan->client_count) + return NULL; + } + + list_for_each_entry(chan, &dev->channels, device_node) { + if (chan->client_count) { + dev_dbg(dev->dev, "%s: %s busy\n", + __func__, dma_chan_name(chan)); + continue; + } + if (fn && !fn(chan, fn_param)) { + dev_dbg(dev->dev, "%s: %s filter said false\n", + __func__, dma_chan_name(chan)); + continue; + } + return chan; + } + + return NULL; +} + +static struct dma_chan *find_candidate(struct dma_device *device, + const dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param) +{ + struct dma_chan *chan = private_candidate(mask, device, fn, fn_param); + int err; + + if (chan) { + /* Found a suitable channel, try to grab, prep, and return it. + * We first set DMA_PRIVATE to disable balance_ref_count as this + * channel will not be published in the general-purpose + * allocator + */ + dma_cap_set(DMA_PRIVATE, device->cap_mask); + device->privatecnt++; + err = dma_chan_get(chan); + + if (err) { + if (err == -ENODEV) { + dev_dbg(device->dev, "%s: %s module removed\n", + __func__, dma_chan_name(chan)); + list_del_rcu(&device->global_node); + } else + dev_dbg(device->dev, + "%s: failed to get %s: (%d)\n", + __func__, dma_chan_name(chan), err); + + if (--device->privatecnt == 0) + dma_cap_clear(DMA_PRIVATE, device->cap_mask); + + chan = ERR_PTR(err); + } + } + + return chan ? chan : ERR_PTR(-EPROBE_DEFER); +} + +/** + * dma_get_slave_channel - try to get specific channel exclusively + * @chan: target channel + */ +struct dma_chan *dma_get_slave_channel(struct dma_chan *chan) +{ + int err = -EBUSY; + + /* lock against __dma_request_channel */ + mutex_lock(&dma_list_mutex); + + if (chan->client_count == 0) { + struct dma_device *device = chan->device; + + dma_cap_set(DMA_PRIVATE, device->cap_mask); + device->privatecnt++; + err = dma_chan_get(chan); + if (err) { + dev_dbg(chan->device->dev, + "%s: failed to get %s: (%d)\n", + __func__, dma_chan_name(chan), err); + chan = NULL; + if (--device->privatecnt == 0) + dma_cap_clear(DMA_PRIVATE, device->cap_mask); + } + } else + chan = NULL; + + mutex_unlock(&dma_list_mutex); + + + return chan; +} +EXPORT_SYMBOL_GPL(dma_get_slave_channel); + +struct dma_chan *dma_get_any_slave_channel(struct dma_device *device) +{ + dma_cap_mask_t mask; + struct dma_chan *chan; + + dma_cap_zero(mask); + dma_cap_set(DMA_SLAVE, mask); + + /* lock against __dma_request_channel */ + mutex_lock(&dma_list_mutex); + + chan = find_candidate(device, &mask, NULL, NULL); + + mutex_unlock(&dma_list_mutex); + + return IS_ERR(chan) ? NULL : chan; +} +EXPORT_SYMBOL_GPL(dma_get_any_slave_channel); + +/** + * __dma_request_channel - try to allocate an exclusive channel + * @mask: capabilities that the channel must satisfy + * @fn: optional callback to disposition available channels + * @fn_param: opaque parameter to pass to dma_filter_fn + * + * Returns pointer to appropriate DMA channel on success or NULL. + */ +struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param) +{ + struct dma_device *device, *_d; + struct dma_chan *chan = NULL; + + /* Find a channel */ + mutex_lock(&dma_list_mutex); + list_for_each_entry_safe(device, _d, &dma_device_list, global_node) { + chan = find_candidate(device, mask, fn, fn_param); + if (!IS_ERR(chan)) + break; + + chan = NULL; + } + mutex_unlock(&dma_list_mutex); + + pr_debug("%s: %s (%s)\n", + __func__, + chan ? "success" : "fail", + chan ? dma_chan_name(chan) : NULL); + + return chan; +} +EXPORT_SYMBOL_GPL(__dma_request_channel); + +static const struct dma_slave_map *dma_filter_match(struct dma_device *device, + const char *name, + struct device *dev) +{ + int i; + + if (!device->filter.mapcnt) + return NULL; + + for (i = 0; i < device->filter.mapcnt; i++) { + const struct dma_slave_map *map = &device->filter.map[i]; + + if (!strcmp(map->devname, dev_name(dev)) && + !strcmp(map->slave, name)) + return map; + } + + return NULL; +} + +/** + * dma_request_chan - try to allocate an exclusive slave channel + * @dev: pointer to client device structure + * @name: slave channel name + * + * Returns pointer to appropriate DMA channel on success or an error pointer. + */ +struct dma_chan *dma_request_chan(struct device *dev, const char *name) +{ + struct dma_device *d, *_d; + struct dma_chan *chan = NULL; + + /* If device-tree is present get slave info from here */ + if (dev->of_node) + chan = of_dma_request_slave_channel(dev->of_node, name); + + /* If device was enumerated by ACPI get slave info from here */ + if (has_acpi_companion(dev) && !chan) + chan = acpi_dma_request_slave_chan_by_name(dev, name); + + if (chan) { + /* Valid channel found or requester need to be deferred */ + if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER) + return chan; + } + + /* Try to find the channel via the DMA filter map(s) */ + mutex_lock(&dma_list_mutex); + list_for_each_entry_safe(d, _d, &dma_device_list, global_node) { + dma_cap_mask_t mask; + const struct dma_slave_map *map = dma_filter_match(d, name, dev); + + if (!map) + continue; + + dma_cap_zero(mask); + dma_cap_set(DMA_SLAVE, mask); + + chan = find_candidate(d, &mask, d->filter.fn, map->param); + if (!IS_ERR(chan)) + break; + } + mutex_unlock(&dma_list_mutex); + + return chan ? chan : ERR_PTR(-EPROBE_DEFER); +} +EXPORT_SYMBOL_GPL(dma_request_chan); + +/** + * dma_request_slave_channel - try to allocate an exclusive slave channel + * @dev: pointer to client device structure + * @name: slave channel name + * + * Returns pointer to appropriate DMA channel on success or NULL. + */ +struct dma_chan *dma_request_slave_channel(struct device *dev, + const char *name) +{ + struct dma_chan *ch = dma_request_chan(dev, name); + if (IS_ERR(ch)) + return NULL; + + return ch; +} +EXPORT_SYMBOL_GPL(dma_request_slave_channel); + +/** + * dma_request_chan_by_mask - allocate a channel satisfying certain capabilities + * @mask: capabilities that the channel must satisfy + * + * Returns pointer to appropriate DMA channel on success or an error pointer. + */ +struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask) +{ + struct dma_chan *chan; + + if (!mask) + return ERR_PTR(-ENODEV); + + chan = __dma_request_channel(mask, NULL, NULL); + if (!chan) { + mutex_lock(&dma_list_mutex); + if (list_empty(&dma_device_list)) + chan = ERR_PTR(-EPROBE_DEFER); + else + chan = ERR_PTR(-ENODEV); + mutex_unlock(&dma_list_mutex); + } + + return chan; +} +EXPORT_SYMBOL_GPL(dma_request_chan_by_mask); + +void dma_release_channel(struct dma_chan *chan) +{ + mutex_lock(&dma_list_mutex); + WARN_ONCE(chan->client_count != 1, + "chan reference count %d != 1\n", chan->client_count); + dma_chan_put(chan); + /* drop PRIVATE cap enabled by __dma_request_channel() */ + if (--chan->device->privatecnt == 0) + dma_cap_clear(DMA_PRIVATE, chan->device->cap_mask); + mutex_unlock(&dma_list_mutex); +} +EXPORT_SYMBOL_GPL(dma_release_channel); + +/** + * dmaengine_get - register interest in dma_channels + */ +void dmaengine_get(void) +{ + struct dma_device *device, *_d; + struct dma_chan *chan; + int err; + + mutex_lock(&dma_list_mutex); + dmaengine_ref_count++; + + /* try to grab channels */ + list_for_each_entry_safe(device, _d, &dma_device_list, global_node) { + if (dma_has_cap(DMA_PRIVATE, device->cap_mask)) + continue; + list_for_each_entry(chan, &device->channels, device_node) { + err = dma_chan_get(chan); + if (err == -ENODEV) { + /* module removed before we could use it */ + list_del_rcu(&device->global_node); + break; + } else if (err) + dev_dbg(chan->device->dev, + "%s: failed to get %s: (%d)\n", + __func__, dma_chan_name(chan), err); + } + } + + /* if this is the first reference and there were channels + * waiting we need to rebalance to get those channels + * incorporated into the channel table + */ + if (dmaengine_ref_count == 1) + dma_channel_rebalance(); + mutex_unlock(&dma_list_mutex); +} +EXPORT_SYMBOL(dmaengine_get); + +/** + * dmaengine_put - let dma drivers be removed when ref_count == 0 + */ +void dmaengine_put(void) +{ + struct dma_device *device; + struct dma_chan *chan; + + mutex_lock(&dma_list_mutex); + dmaengine_ref_count--; + BUG_ON(dmaengine_ref_count < 0); + /* drop channel references */ + list_for_each_entry(device, &dma_device_list, global_node) { + if (dma_has_cap(DMA_PRIVATE, device->cap_mask)) + continue; + list_for_each_entry(chan, &device->channels, device_node) + dma_chan_put(chan); + } + mutex_unlock(&dma_list_mutex); +} +EXPORT_SYMBOL(dmaengine_put); + +static bool device_has_all_tx_types(struct dma_device *device) +{ + /* A device that satisfies this test has channels that will never cause + * an async_tx channel switch event as all possible operation types can + * be handled. + */ + #ifdef CONFIG_ASYNC_TX_DMA + if (!dma_has_cap(DMA_INTERRUPT, device->cap_mask)) + return false; + #endif + + #if IS_ENABLED(CONFIG_ASYNC_MEMCPY) + if (!dma_has_cap(DMA_MEMCPY, device->cap_mask)) + return false; + #endif + + #if IS_ENABLED(CONFIG_ASYNC_XOR) + if (!dma_has_cap(DMA_XOR, device->cap_mask)) + return false; + + #ifndef CONFIG_ASYNC_TX_DISABLE_XOR_VAL_DMA + if (!dma_has_cap(DMA_XOR_VAL, device->cap_mask)) + return false; + #endif + #endif + + #if IS_ENABLED(CONFIG_ASYNC_PQ) + if (!dma_has_cap(DMA_PQ, device->cap_mask)) + return false; + + #ifndef CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA + if (!dma_has_cap(DMA_PQ_VAL, device->cap_mask)) + return false; + #endif + #endif + + return true; +} + +static int get_dma_id(struct dma_device *device) +{ + int rc = ida_alloc(&dma_ida, GFP_KERNEL); + + if (rc < 0) + return rc; + device->dev_id = rc; + return 0; +} + +/** + * dma_async_device_register - registers DMA devices found + * @device: &dma_device + */ +int dma_async_device_register(struct dma_device *device) +{ + int chancnt = 0, rc; + struct dma_chan* chan; + atomic_t *idr_ref; + + if (!device) + return -ENODEV; + + /* validate device routines */ + if (!device->dev) { + pr_err("DMAdevice must have dev\n"); + return -EIO; + } + + if (dma_has_cap(DMA_MEMCPY, device->cap_mask) && !device->device_prep_dma_memcpy) { + dev_err(device->dev, + "Device claims capability %s, but op is not defined\n", + "DMA_MEMCPY"); + return -EIO; + } + + if (dma_has_cap(DMA_XOR, device->cap_mask) && !device->device_prep_dma_xor) { + dev_err(device->dev, + "Device claims capability %s, but op is not defined\n", + "DMA_XOR"); + return -EIO; + } + + if (dma_has_cap(DMA_XOR_VAL, device->cap_mask) && !device->device_prep_dma_xor_val) { + dev_err(device->dev, + "Device claims capability %s, but op is not defined\n", + "DMA_XOR_VAL"); + return -EIO; + } + + if (dma_has_cap(DMA_PQ, device->cap_mask) && !device->device_prep_dma_pq) { + dev_err(device->dev, + "Device claims capability %s, but op is not defined\n", + "DMA_PQ"); + return -EIO; + } + + if (dma_has_cap(DMA_PQ_VAL, device->cap_mask) && !device->device_prep_dma_pq_val) { + dev_err(device->dev, + "Device claims capability %s, but op is not defined\n", + "DMA_PQ_VAL"); + return -EIO; + } + + if (dma_has_cap(DMA_MEMSET, device->cap_mask) && !device->device_prep_dma_memset) { + dev_err(device->dev, + "Device claims capability %s, but op is not defined\n", + "DMA_MEMSET"); + return -EIO; + } + + if (dma_has_cap(DMA_INTERRUPT, device->cap_mask) && !device->device_prep_dma_interrupt) { + dev_err(device->dev, + "Device claims capability %s, but op is not defined\n", + "DMA_INTERRUPT"); + return -EIO; + } + + if (dma_has_cap(DMA_CYCLIC, device->cap_mask) && !device->device_prep_dma_cyclic) { + dev_err(device->dev, + "Device claims capability %s, but op is not defined\n", + "DMA_CYCLIC"); + return -EIO; + } + + if (dma_has_cap(DMA_INTERLEAVE, device->cap_mask) && !device->device_prep_interleaved_dma) { + dev_err(device->dev, + "Device claims capability %s, but op is not defined\n", + "DMA_INTERLEAVE"); + return -EIO; + } + + + if (!device->device_tx_status) { + dev_err(device->dev, "Device tx_status is not defined\n"); + return -EIO; + } + + + if (!device->device_issue_pending) { + dev_err(device->dev, "Device issue_pending is not defined\n"); + return -EIO; + } + + /* note: this only matters in the + * CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH=n case + */ + if (device_has_all_tx_types(device)) + dma_cap_set(DMA_ASYNC_TX, device->cap_mask); + + idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL); + if (!idr_ref) + return -ENOMEM; + rc = get_dma_id(device); + if (rc != 0) { + kfree(idr_ref); + return rc; + } + + atomic_set(idr_ref, 0); + + /* represent channels in sysfs. Probably want devs too */ + list_for_each_entry(chan, &device->channels, device_node) { + rc = -ENOMEM; + chan->local = alloc_percpu(typeof(*chan->local)); + if (chan->local == NULL) + goto err_out; + chan->dev = kzalloc(sizeof(*chan->dev), GFP_KERNEL); + if (chan->dev == NULL) { + free_percpu(chan->local); + chan->local = NULL; + goto err_out; + } + + chan->chan_id = chancnt++; + chan->dev->device.class = &dma_devclass; + chan->dev->device.parent = device->dev; + chan->dev->chan = chan; + chan->dev->idr_ref = idr_ref; + chan->dev->dev_id = device->dev_id; + atomic_inc(idr_ref); + dev_set_name(&chan->dev->device, "dma%dchan%d", + device->dev_id, chan->chan_id); + + rc = device_register(&chan->dev->device); + if (rc) { + free_percpu(chan->local); + chan->local = NULL; + kfree(chan->dev); + atomic_dec(idr_ref); + goto err_out; + } + chan->client_count = 0; + } + + if (!chancnt) { + dev_err(device->dev, "%s: device has no channels!\n", __func__); + rc = -ENODEV; + goto err_out; + } + + device->chancnt = chancnt; + + mutex_lock(&dma_list_mutex); + /* take references on public channels */ + if (dmaengine_ref_count && !dma_has_cap(DMA_PRIVATE, device->cap_mask)) + list_for_each_entry(chan, &device->channels, device_node) { + /* if clients are already waiting for channels we need + * to take references on their behalf + */ + if (dma_chan_get(chan) == -ENODEV) { + /* note we can only get here for the first + * channel as the remaining channels are + * guaranteed to get a reference + */ + rc = -ENODEV; + mutex_unlock(&dma_list_mutex); + goto err_out; + } + } + list_add_tail_rcu(&device->global_node, &dma_device_list); + if (dma_has_cap(DMA_PRIVATE, device->cap_mask)) + device->privatecnt++; /* Always private */ + dma_channel_rebalance(); + mutex_unlock(&dma_list_mutex); + + return 0; + +err_out: + /* if we never registered a channel just release the idr */ + if (atomic_read(idr_ref) == 0) { + ida_free(&dma_ida, device->dev_id); + kfree(idr_ref); + return rc; + } + + list_for_each_entry(chan, &device->channels, device_node) { + if (chan->local == NULL) + continue; + mutex_lock(&dma_list_mutex); + chan->dev->chan = NULL; + mutex_unlock(&dma_list_mutex); + device_unregister(&chan->dev->device); + free_percpu(chan->local); + } + return rc; +} +EXPORT_SYMBOL(dma_async_device_register); + +/** + * dma_async_device_unregister - unregister a DMA device + * @device: &dma_device + * + * This routine is called by dma driver exit routines, dmaengine holds module + * references to prevent it being called while channels are in use. + */ +void dma_async_device_unregister(struct dma_device *device) +{ + struct dma_chan *chan; + + mutex_lock(&dma_list_mutex); + list_del_rcu(&device->global_node); + dma_channel_rebalance(); + mutex_unlock(&dma_list_mutex); + + list_for_each_entry(chan, &device->channels, device_node) { + WARN_ONCE(chan->client_count, + "%s called while %d clients hold a reference\n", + __func__, chan->client_count); + mutex_lock(&dma_list_mutex); + chan->dev->chan = NULL; + mutex_unlock(&dma_list_mutex); + device_unregister(&chan->dev->device); + free_percpu(chan->local); + } +} +EXPORT_SYMBOL(dma_async_device_unregister); + +static void dmam_device_release(struct device *dev, void *res) +{ + struct dma_device *device; + + device = *(struct dma_device **)res; + dma_async_device_unregister(device); +} + +/** + * dmaenginem_async_device_register - registers DMA devices found + * @device: &dma_device + * + * The operation is managed and will be undone on driver detach. + */ +int dmaenginem_async_device_register(struct dma_device *device) +{ + void *p; + int ret; + + p = devres_alloc(dmam_device_release, sizeof(void *), GFP_KERNEL); + if (!p) + return -ENOMEM; + + ret = dma_async_device_register(device); + if (!ret) { + *(struct dma_device **)p = device; + devres_add(device->dev, p); + } else { + devres_free(p); + } + + return ret; +} +EXPORT_SYMBOL(dmaenginem_async_device_register); + +struct dmaengine_unmap_pool { + struct kmem_cache *cache; + const char *name; + mempool_t *pool; + size_t size; +}; + +#define __UNMAP_POOL(x) { .size = x, .name = "dmaengine-unmap-" __stringify(x) } +static struct dmaengine_unmap_pool unmap_pool[] = { + __UNMAP_POOL(2), + #if IS_ENABLED(CONFIG_DMA_ENGINE_RAID) + __UNMAP_POOL(16), + __UNMAP_POOL(128), + __UNMAP_POOL(256), + #endif +}; + +static struct dmaengine_unmap_pool *__get_unmap_pool(int nr) +{ + int order = get_count_order(nr); + + switch (order) { + case 0 ... 1: + return &unmap_pool[0]; +#if IS_ENABLED(CONFIG_DMA_ENGINE_RAID) + case 2 ... 4: + return &unmap_pool[1]; + case 5 ... 7: + return &unmap_pool[2]; + case 8: + return &unmap_pool[3]; +#endif + default: + BUG(); + return NULL; + } +} + +static void dmaengine_unmap(struct kref *kref) +{ + struct dmaengine_unmap_data *unmap = container_of(kref, typeof(*unmap), kref); + struct device *dev = unmap->dev; + int cnt, i; + + cnt = unmap->to_cnt; + for (i = 0; i < cnt; i++) + dma_unmap_page(dev, unmap->addr[i], unmap->len, + DMA_TO_DEVICE); + cnt += unmap->from_cnt; + for (; i < cnt; i++) + dma_unmap_page(dev, unmap->addr[i], unmap->len, + DMA_FROM_DEVICE); + cnt += unmap->bidi_cnt; + for (; i < cnt; i++) { + if (unmap->addr[i] == 0) + continue; + dma_unmap_page(dev, unmap->addr[i], unmap->len, + DMA_BIDIRECTIONAL); + } + cnt = unmap->map_cnt; + mempool_free(unmap, __get_unmap_pool(cnt)->pool); +} + +void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap) +{ + if (unmap) + kref_put(&unmap->kref, dmaengine_unmap); +} +EXPORT_SYMBOL_GPL(dmaengine_unmap_put); + +static void dmaengine_destroy_unmap_pool(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(unmap_pool); i++) { + struct dmaengine_unmap_pool *p = &unmap_pool[i]; + + mempool_destroy(p->pool); + p->pool = NULL; + kmem_cache_destroy(p->cache); + p->cache = NULL; + } +} + +static int __init dmaengine_init_unmap_pool(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(unmap_pool); i++) { + struct dmaengine_unmap_pool *p = &unmap_pool[i]; + size_t size; + + size = sizeof(struct dmaengine_unmap_data) + + sizeof(dma_addr_t) * p->size; + + p->cache = kmem_cache_create(p->name, size, 0, + SLAB_HWCACHE_ALIGN, NULL); + if (!p->cache) + break; + p->pool = mempool_create_slab_pool(1, p->cache); + if (!p->pool) + break; + } + + if (i == ARRAY_SIZE(unmap_pool)) + return 0; + + dmaengine_destroy_unmap_pool(); + return -ENOMEM; +} + +struct dmaengine_unmap_data * +dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags) +{ + struct dmaengine_unmap_data *unmap; + + unmap = mempool_alloc(__get_unmap_pool(nr)->pool, flags); + if (!unmap) + return NULL; + + memset(unmap, 0, sizeof(*unmap)); + kref_init(&unmap->kref); + unmap->dev = dev; + unmap->map_cnt = nr; + + return unmap; +} +EXPORT_SYMBOL(dmaengine_get_unmap_data); + +void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx, + struct dma_chan *chan) +{ + tx->chan = chan; + #ifdef CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH + spin_lock_init(&tx->lock); + #endif +} +EXPORT_SYMBOL(dma_async_tx_descriptor_init); + +/* dma_wait_for_async_tx - spin wait for a transaction to complete + * @tx: in-flight transaction to wait on + */ +enum dma_status +dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) +{ + unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000); + + if (!tx) + return DMA_COMPLETE; + + while (tx->cookie == -EBUSY) { + if (time_after_eq(jiffies, dma_sync_wait_timeout)) { + dev_err(tx->chan->device->dev, + "%s timeout waiting for descriptor submission\n", + __func__); + return DMA_ERROR; + } + cpu_relax(); + } + return dma_sync_wait(tx->chan, tx->cookie); +} +EXPORT_SYMBOL_GPL(dma_wait_for_async_tx); + +/* dma_run_dependencies - helper routine for dma drivers to process + * (start) dependent operations on their target channel + * @tx: transaction with dependencies + */ +void dma_run_dependencies(struct dma_async_tx_descriptor *tx) +{ + struct dma_async_tx_descriptor *dep = txd_next(tx); + struct dma_async_tx_descriptor *dep_next; + struct dma_chan *chan; + + if (!dep) + return; + + /* we'll submit tx->next now, so clear the link */ + txd_clear_next(tx); + chan = dep->chan; + + /* keep submitting up until a channel switch is detected + * in that case we will be called again as a result of + * processing the interrupt from async_tx_channel_switch + */ + for (; dep; dep = dep_next) { + txd_lock(dep); + txd_clear_parent(dep); + dep_next = txd_next(dep); + if (dep_next && dep_next->chan == chan) + txd_clear_next(dep); /* ->next will be submitted */ + else + dep_next = NULL; /* submit current dep and terminate */ + txd_unlock(dep); + + dep->tx_submit(dep); + } + + chan->device->device_issue_pending(chan); +} +EXPORT_SYMBOL_GPL(dma_run_dependencies); + +static int __init dma_bus_init(void) +{ + int err = dmaengine_init_unmap_pool(); + + if (err) + return err; + return class_register(&dma_devclass); +} +arch_initcall(dma_bus_init); + +
diff --git a/kern/drivers/dma/dmaengine.h b/kern/drivers/dma/dmaengine.h new file mode 100644 index 0000000..501c0b0 --- /dev/null +++ b/kern/drivers/dma/dmaengine.h
@@ -0,0 +1,174 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * The contents of this file are private to DMA engine drivers, and is not + * part of the API to be used by DMA engine users. + */ +#ifndef DMAENGINE_H +#define DMAENGINE_H + +#include <linux/bug.h> +#include <linux/dmaengine.h> + +/** + * dma_cookie_init - initialize the cookies for a DMA channel + * @chan: dma channel to initialize + */ +static inline void dma_cookie_init(struct dma_chan *chan) +{ + chan->cookie = DMA_MIN_COOKIE; + chan->completed_cookie = DMA_MIN_COOKIE; +} + +/** + * dma_cookie_assign - assign a DMA engine cookie to the descriptor + * @tx: descriptor needing cookie + * + * Assign a unique non-zero per-channel cookie to the descriptor. + * Note: caller is expected to hold a lock to prevent concurrency. + */ +static inline dma_cookie_t dma_cookie_assign(struct dma_async_tx_descriptor *tx) +{ + struct dma_chan *chan = tx->chan; + dma_cookie_t cookie; + + cookie = chan->cookie + 1; + if (cookie < DMA_MIN_COOKIE) + cookie = DMA_MIN_COOKIE; + tx->cookie = chan->cookie = cookie; + + return cookie; +} + +/** + * dma_cookie_complete - complete a descriptor + * @tx: descriptor to complete + * + * Mark this descriptor complete by updating the channels completed + * cookie marker. Zero the descriptors cookie to prevent accidental + * repeated completions. + * + * Note: caller is expected to hold a lock to prevent concurrency. + */ +static inline void dma_cookie_complete(struct dma_async_tx_descriptor *tx) +{ + BUG_ON(tx->cookie < DMA_MIN_COOKIE); + tx->chan->completed_cookie = tx->cookie; + tx->cookie = 0; +} + +/** + * dma_cookie_status - report cookie status + * @chan: dma channel + * @cookie: cookie we are interested in + * @state: dma_tx_state structure to return last/used cookies + * + * Report the status of the cookie, filling in the state structure if + * non-NULL. No locking is required. + */ +static inline enum dma_status dma_cookie_status(struct dma_chan *chan, + dma_cookie_t cookie, struct dma_tx_state *state) +{ + dma_cookie_t used, complete; + + used = chan->cookie; + complete = chan->completed_cookie; + barrier(); + if (state) { + state->last = complete; + state->used = used; + state->residue = 0; + } + return dma_async_is_complete(cookie, complete, used); +} + +static inline void dma_set_residue(struct dma_tx_state *state, u32 residue) +{ + if (state) + state->residue = residue; +} + +struct dmaengine_desc_callback { + dma_async_tx_callback callback; + dma_async_tx_callback_result callback_result; + void *callback_param; +}; + +/** + * dmaengine_desc_get_callback - get the passed in callback function + * @tx: tx descriptor + * @cb: temp struct to hold the callback info + * + * Fill the passed in cb struct with what's available in the passed in + * tx descriptor struct + * No locking is required. + */ +static inline void +dmaengine_desc_get_callback(struct dma_async_tx_descriptor *tx, + struct dmaengine_desc_callback *cb) +{ + cb->callback = tx->callback; + cb->callback_result = tx->callback_result; + cb->callback_param = tx->callback_param; +} + +/** + * dmaengine_desc_callback_invoke - call the callback function in cb struct + * @cb: temp struct that is holding the callback info + * @result: transaction result + * + * Call the callback function provided in the cb struct with the parameter + * in the cb struct. + * Locking is dependent on the driver. + */ +static inline void +dmaengine_desc_callback_invoke(struct dmaengine_desc_callback *cb, + const struct dmaengine_result *result) +{ + struct dmaengine_result dummy_result = { + .result = DMA_TRANS_NOERROR, + .residue = 0 + }; + + if (cb->callback_result) { + if (!result) + result = &dummy_result; + cb->callback_result(cb->callback_param, result); + } else if (cb->callback) { + cb->callback(cb->callback_param); + } +} + +/** + * dmaengine_desc_get_callback_invoke - get the callback in tx descriptor and + * then immediately call the callback. + * @tx: dma async tx descriptor + * @result: transaction result + * + * Call dmaengine_desc_get_callback() and dmaengine_desc_callback_invoke() + * in a single function since no work is necessary in between for the driver. + * Locking is dependent on the driver. + */ +static inline void +dmaengine_desc_get_callback_invoke(struct dma_async_tx_descriptor *tx, + const struct dmaengine_result *result) +{ + struct dmaengine_desc_callback cb; + + dmaengine_desc_get_callback(tx, &cb); + dmaengine_desc_callback_invoke(&cb, result); +} + +/** + * dmaengine_desc_callback_valid - verify the callback is valid in cb + * @cb: callback info struct + * + * Return a bool that verifies whether callback in cb is valid or not. + * No locking is required. + */ +static inline bool +dmaengine_desc_callback_valid(struct dmaengine_desc_callback *cb) +{ + return (cb->callback) ? true : false; +} + +#endif
diff --git a/kern/include/linux/dmaengine.h b/kern/include/linux/dmaengine.h new file mode 100644 index 0000000..d49ec5c --- /dev/null +++ b/kern/include/linux/dmaengine.h
@@ -0,0 +1,1434 @@ +/* + * Copyright(c) 2004 - 2006 Intel Corporation. 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 as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + * 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. + */ +#ifndef LINUX_DMAENGINE_H +#define LINUX_DMAENGINE_H + +#include <linux/device.h> +#include <linux/err.h> +#include <linux/uio.h> +#include <linux/bug.h> +#include <linux/scatterlist.h> +#include <linux/bitmap.h> +#include <linux/types.h> +#include <asm/page.h> + +/** + * typedef dma_cookie_t - an opaque DMA cookie + * + * if dma_cookie_t is >0 it's a DMA request cookie, <0 it's an error code + */ +typedef s32 dma_cookie_t; +#define DMA_MIN_COOKIE 1 + +static inline int dma_submit_error(dma_cookie_t cookie) +{ + return cookie < 0 ? cookie : 0; +} + +/** + * enum dma_status - DMA transaction status + * @DMA_COMPLETE: transaction completed + * @DMA_IN_PROGRESS: transaction not yet processed + * @DMA_PAUSED: transaction is paused + * @DMA_ERROR: transaction failed + */ +enum dma_status { + DMA_COMPLETE, + DMA_IN_PROGRESS, + DMA_PAUSED, + DMA_ERROR, +}; + +/** + * enum dma_transaction_type - DMA transaction types/indexes + * + * Note: The DMA_ASYNC_TX capability is not to be set by drivers. It is + * automatically set as dma devices are registered. + */ +enum dma_transaction_type { + DMA_MEMCPY, + DMA_XOR, + DMA_PQ, + DMA_XOR_VAL, + DMA_PQ_VAL, + DMA_MEMSET, + DMA_MEMSET_SG, + DMA_INTERRUPT, + DMA_PRIVATE, + DMA_ASYNC_TX, + DMA_SLAVE, + DMA_CYCLIC, + DMA_INTERLEAVE, +/* last transaction type for creation of the capabilities mask */ + DMA_TX_TYPE_END, +}; + +/** + * enum dma_transfer_direction - dma transfer mode and direction indicator + * @DMA_MEM_TO_MEM: Async/Memcpy mode + * @DMA_MEM_TO_DEV: Slave mode & From Memory to Device + * @DMA_DEV_TO_MEM: Slave mode & From Device to Memory + * @DMA_DEV_TO_DEV: Slave mode & From Device to Device + */ +enum dma_transfer_direction { + DMA_MEM_TO_MEM, + DMA_MEM_TO_DEV, + DMA_DEV_TO_MEM, + DMA_DEV_TO_DEV, + DMA_TRANS_NONE, +}; + +/** + * Interleaved Transfer Request + * ---------------------------- + * A chunk is collection of contiguous bytes to be transfered. + * The gap(in bytes) between two chunks is called inter-chunk-gap(ICG). + * ICGs may or maynot change between chunks. + * A FRAME is the smallest series of contiguous {chunk,icg} pairs, + * that when repeated an integral number of times, specifies the transfer. + * A transfer template is specification of a Frame, the number of times + * it is to be repeated and other per-transfer attributes. + * + * Practically, a client driver would have ready a template for each + * type of transfer it is going to need during its lifetime and + * set only 'src_start' and 'dst_start' before submitting the requests. + * + * + * | Frame-1 | Frame-2 | ~ | Frame-'numf' | + * |====....==.===...=...|====....==.===...=...| ~ |====....==.===...=...| + * + * == Chunk size + * ... ICG + */ + +/** + * struct data_chunk - Element of scatter-gather list that makes a frame. + * @size: Number of bytes to read from source. + * size_dst := fn(op, size_src), so doesn't mean much for destination. + * @icg: Number of bytes to jump after last src/dst address of this + * chunk and before first src/dst address for next chunk. + * Ignored for dst(assumed 0), if dst_inc is true and dst_sgl is false. + * Ignored for src(assumed 0), if src_inc is true and src_sgl is false. + * @dst_icg: Number of bytes to jump after last dst address of this + * chunk and before the first dst address for next chunk. + * Ignored if dst_inc is true and dst_sgl is false. + * @src_icg: Number of bytes to jump after last src address of this + * chunk and before the first src address for next chunk. + * Ignored if src_inc is true and src_sgl is false. + */ +struct data_chunk { + size_t size; + size_t icg; + size_t dst_icg; + size_t src_icg; +}; + +/** + * struct dma_interleaved_template - Template to convey DMAC the transfer pattern + * and attributes. + * @src_start: Bus address of source for the first chunk. + * @dst_start: Bus address of destination for the first chunk. + * @dir: Specifies the type of Source and Destination. + * @src_inc: If the source address increments after reading from it. + * @dst_inc: If the destination address increments after writing to it. + * @src_sgl: If the 'icg' of sgl[] applies to Source (scattered read). + * Otherwise, source is read contiguously (icg ignored). + * Ignored if src_inc is false. + * @dst_sgl: If the 'icg' of sgl[] applies to Destination (scattered write). + * Otherwise, destination is filled contiguously (icg ignored). + * Ignored if dst_inc is false. + * @numf: Number of frames in this template. + * @frame_size: Number of chunks in a frame i.e, size of sgl[]. + * @sgl: Array of {chunk,icg} pairs that make up a frame. + */ +struct dma_interleaved_template { + dma_addr_t src_start; + dma_addr_t dst_start; + enum dma_transfer_direction dir; + bool src_inc; + bool dst_inc; + bool src_sgl; + bool dst_sgl; + size_t numf; + size_t frame_size; + struct data_chunk sgl[0]; +}; + +/** + * enum dma_ctrl_flags - DMA flags to augment operation preparation, + * control completion, and communicate status. + * @DMA_PREP_INTERRUPT - trigger an interrupt (callback) upon completion of + * this transaction + * @DMA_CTRL_ACK - if clear, the descriptor cannot be reused until the client + * acknowledges receipt, i.e. has has a chance to establish any dependency + * chains + * @DMA_PREP_PQ_DISABLE_P - prevent generation of P while generating Q + * @DMA_PREP_PQ_DISABLE_Q - prevent generation of Q while generating P + * @DMA_PREP_CONTINUE - indicate to a driver that it is reusing buffers as + * sources that were the result of a previous operation, in the case of a PQ + * operation it continues the calculation with new sources + * @DMA_PREP_FENCE - tell the driver that subsequent operations depend + * on the result of this operation + * @DMA_CTRL_REUSE: client can reuse the descriptor and submit again till + * cleared or freed + * @DMA_PREP_CMD: tell the driver that the data passed to DMA API is command + * data and the descriptor should be in different format from normal + * data descriptors. + */ +enum dma_ctrl_flags { + DMA_PREP_INTERRUPT = (1 << 0), + DMA_CTRL_ACK = (1 << 1), + DMA_PREP_PQ_DISABLE_P = (1 << 2), + DMA_PREP_PQ_DISABLE_Q = (1 << 3), + DMA_PREP_CONTINUE = (1 << 4), + DMA_PREP_FENCE = (1 << 5), + DMA_CTRL_REUSE = (1 << 6), + DMA_PREP_CMD = (1 << 7), +}; + +/** + * enum sum_check_bits - bit position of pq_check_flags + */ +enum sum_check_bits { + SUM_CHECK_P = 0, + SUM_CHECK_Q = 1, +}; + +/** + * enum pq_check_flags - result of async_{xor,pq}_zero_sum operations + * @SUM_CHECK_P_RESULT - 1 if xor zero sum error, 0 otherwise + * @SUM_CHECK_Q_RESULT - 1 if reed-solomon zero sum error, 0 otherwise + */ +enum sum_check_flags { + SUM_CHECK_P_RESULT = (1 << SUM_CHECK_P), + SUM_CHECK_Q_RESULT = (1 << SUM_CHECK_Q), +}; + + +/** + * dma_cap_mask_t - capabilities bitmap modeled after cpumask_t. + * See linux/cpumask.h + */ +typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t; + +/** + * struct dma_chan_percpu - the per-CPU part of struct dma_chan + * @memcpy_count: transaction counter + * @bytes_transferred: byte counter + */ + +struct dma_chan_percpu { + /* stats */ + unsigned long memcpy_count; + unsigned long bytes_transferred; +}; + +/** + * struct dma_router - DMA router structure + * @dev: pointer to the DMA router device + * @route_free: function to be called when the route can be disconnected + */ +struct dma_router { + struct device *dev; + void (*route_free)(struct device *dev, void *route_data); +}; + +/** + * struct dma_chan - devices supply DMA channels, clients use them + * @device: ptr to the dma device who supplies this channel, always !%NULL + * @cookie: last cookie value returned to client + * @completed_cookie: last completed cookie for this channel + * @chan_id: channel ID for sysfs + * @dev: class device for sysfs + * @device_node: used to add this to the device chan list + * @local: per-cpu pointer to a struct dma_chan_percpu + * @client_count: how many clients are using this channel + * @table_count: number of appearances in the mem-to-mem allocation table + * @router: pointer to the DMA router structure + * @route_data: channel specific data for the router + * @private: private data for certain client-channel associations + */ +struct dma_chan { + struct dma_device *device; + dma_cookie_t cookie; + dma_cookie_t completed_cookie; + + /* sysfs */ + int chan_id; + struct dma_chan_dev *dev; + + struct list_head device_node; + struct dma_chan_percpu __percpu *local; + int client_count; + int table_count; + + /* DMA router */ + struct dma_router *router; + void *route_data; + + void *private; +}; + +/** + * struct dma_chan_dev - relate sysfs device node to backing channel device + * @chan: driver channel device + * @device: sysfs device + * @dev_id: parent dma_device dev_id + * @idr_ref: reference count to gate release of dma_device dev_id + */ +struct dma_chan_dev { + struct dma_chan *chan; + struct device device; + int dev_id; + atomic_t *idr_ref; +}; + +/** + * enum dma_slave_buswidth - defines bus width of the DMA slave + * device, source or target buses + */ +enum dma_slave_buswidth { + DMA_SLAVE_BUSWIDTH_UNDEFINED = 0, + DMA_SLAVE_BUSWIDTH_1_BYTE = 1, + DMA_SLAVE_BUSWIDTH_2_BYTES = 2, + DMA_SLAVE_BUSWIDTH_3_BYTES = 3, + DMA_SLAVE_BUSWIDTH_4_BYTES = 4, + DMA_SLAVE_BUSWIDTH_8_BYTES = 8, + DMA_SLAVE_BUSWIDTH_16_BYTES = 16, + DMA_SLAVE_BUSWIDTH_32_BYTES = 32, + DMA_SLAVE_BUSWIDTH_64_BYTES = 64, +}; + +/** + * struct dma_slave_config - dma slave channel runtime config + * @direction: whether the data shall go in or out on this slave + * channel, right now. DMA_MEM_TO_DEV and DMA_DEV_TO_MEM are + * legal values. DEPRECATED, drivers should use the direction argument + * to the device_prep_slave_sg and device_prep_dma_cyclic functions or + * the dir field in the dma_interleaved_template structure. + * @src_addr: this is the physical address where DMA slave data + * should be read (RX), if the source is memory this argument is + * ignored. + * @dst_addr: this is the physical address where DMA slave data + * should be written (TX), if the source is memory this argument + * is ignored. + * @src_addr_width: this is the width in bytes of the source (RX) + * register where DMA data shall be read. If the source + * is memory this may be ignored depending on architecture. + * Legal values: 1, 2, 3, 4, 8, 16, 32, 64. + * @dst_addr_width: same as src_addr_width but for destination + * target (TX) mutatis mutandis. + * @src_maxburst: the maximum number of words (note: words, as in + * units of the src_addr_width member, not bytes) that can be sent + * in one burst to the device. Typically something like half the + * FIFO depth on I/O peripherals so you don't overflow it. This + * may or may not be applicable on memory sources. + * @dst_maxburst: same as src_maxburst but for destination target + * mutatis mutandis. + * @src_port_window_size: The length of the register area in words the data need + * to be accessed on the device side. It is only used for devices which is using + * an area instead of a single register to receive the data. Typically the DMA + * loops in this area in order to transfer the data. + * @dst_port_window_size: same as src_port_window_size but for the destination + * port. + * @device_fc: Flow Controller Settings. Only valid for slave channels. Fill + * with 'true' if peripheral should be flow controller. Direction will be + * selected at Runtime. + * @slave_id: Slave requester id. Only valid for slave channels. The dma + * slave peripheral will have unique id as dma requester which need to be + * pass as slave config. + * + * This struct is passed in as configuration data to a DMA engine + * in order to set up a certain channel for DMA transport at runtime. + * The DMA device/engine has to provide support for an additional + * callback in the dma_device structure, device_config and this struct + * will then be passed in as an argument to the function. + * + * The rationale for adding configuration information to this struct is as + * follows: if it is likely that more than one DMA slave controllers in + * the world will support the configuration option, then make it generic. + * If not: if it is fixed so that it be sent in static from the platform + * data, then prefer to do that. + */ +struct dma_slave_config { + enum dma_transfer_direction direction; + phys_addr_t src_addr; + phys_addr_t dst_addr; + enum dma_slave_buswidth src_addr_width; + enum dma_slave_buswidth dst_addr_width; + u32 src_maxburst; + u32 dst_maxburst; + u32 src_port_window_size; + u32 dst_port_window_size; + bool device_fc; + unsigned int slave_id; +}; + +/** + * enum dma_residue_granularity - Granularity of the reported transfer residue + * @DMA_RESIDUE_GRANULARITY_DESCRIPTOR: Residue reporting is not support. The + * DMA channel is only able to tell whether a descriptor has been completed or + * not, which means residue reporting is not supported by this channel. The + * residue field of the dma_tx_state field will always be 0. + * @DMA_RESIDUE_GRANULARITY_SEGMENT: Residue is updated after each successfully + * completed segment of the transfer (For cyclic transfers this is after each + * period). This is typically implemented by having the hardware generate an + * interrupt after each transferred segment and then the drivers updates the + * outstanding residue by the size of the segment. Another possibility is if + * the hardware supports scatter-gather and the segment descriptor has a field + * which gets set after the segment has been completed. The driver then counts + * the number of segments without the flag set to compute the residue. + * @DMA_RESIDUE_GRANULARITY_BURST: Residue is updated after each transferred + * burst. This is typically only supported if the hardware has a progress + * register of some sort (E.g. a register with the current read/write address + * or a register with the amount of bursts/beats/bytes that have been + * transferred or still need to be transferred). + */ +enum dma_residue_granularity { + DMA_RESIDUE_GRANULARITY_DESCRIPTOR = 0, + DMA_RESIDUE_GRANULARITY_SEGMENT = 1, + DMA_RESIDUE_GRANULARITY_BURST = 2, +}; + +/** + * struct dma_slave_caps - expose capabilities of a slave channel only + * @src_addr_widths: bit mask of src addr widths the channel supports. + * Width is specified in bytes, e.g. for a channel supporting + * a width of 4 the mask should have BIT(4) set. + * @dst_addr_widths: bit mask of dst addr widths the channel supports + * @directions: bit mask of slave directions the channel supports. + * Since the enum dma_transfer_direction is not defined as bit flag for + * each type, the dma controller should set BIT(<TYPE>) and same + * should be checked by controller as well + * @max_burst: max burst capability per-transfer + * @cmd_pause: true, if pause is supported (i.e. for reading residue or + * for resume later) + * @cmd_resume: true, if resume is supported + * @cmd_terminate: true, if terminate cmd is supported + * @residue_granularity: granularity of the reported transfer residue + * @descriptor_reuse: if a descriptor can be reused by client and + * resubmitted multiple times + */ +struct dma_slave_caps { + u32 src_addr_widths; + u32 dst_addr_widths; + u32 directions; + u32 max_burst; + bool cmd_pause; + bool cmd_resume; + bool cmd_terminate; + enum dma_residue_granularity residue_granularity; + bool descriptor_reuse; +}; + +static inline const char *dma_chan_name(struct dma_chan *chan) +{ + return dev_name(&chan->dev->device); +} + +void dma_chan_cleanup(struct kref *kref); + +/** + * typedef dma_filter_fn - callback filter for dma_request_channel + * @chan: channel to be reviewed + * @filter_param: opaque parameter passed through dma_request_channel + * + * When this optional parameter is specified in a call to dma_request_channel a + * suitable channel is passed to this routine for further dispositioning before + * being returned. Where 'suitable' indicates a non-busy channel that + * satisfies the given capability mask. It returns 'true' to indicate that the + * channel is suitable. + */ +typedef bool (*dma_filter_fn)(struct dma_chan *chan, void *filter_param); + +typedef void (*dma_async_tx_callback)(void *dma_async_param); + +enum dmaengine_tx_result { + DMA_TRANS_NOERROR = 0, /* SUCCESS */ + DMA_TRANS_READ_FAILED, /* Source DMA read failed */ + DMA_TRANS_WRITE_FAILED, /* Destination DMA write failed */ + DMA_TRANS_ABORTED, /* Op never submitted / aborted */ +}; + +struct dmaengine_result { + enum dmaengine_tx_result result; + u32 residue; +}; + +typedef void (*dma_async_tx_callback_result)(void *dma_async_param, + const struct dmaengine_result *result); + +struct dmaengine_unmap_data { +#if IS_ENABLED(CONFIG_DMA_ENGINE_RAID) + u16 map_cnt; +#else + u8 map_cnt; +#endif + u8 to_cnt; + u8 from_cnt; + u8 bidi_cnt; + struct device *dev; + struct kref kref; + size_t len; + dma_addr_t addr[0]; +}; + +/** + * struct dma_async_tx_descriptor - async transaction descriptor + * ---dma generic offload fields--- + * @cookie: tracking cookie for this transaction, set to -EBUSY if + * this tx is sitting on a dependency list + * @flags: flags to augment operation preparation, control completion, and + * communicate status + * @phys: physical address of the descriptor + * @chan: target channel for this operation + * @tx_submit: accept the descriptor, assign ordered cookie and mark the + * descriptor pending. To be pushed on .issue_pending() call + * @callback: routine to call after this operation is complete + * @callback_param: general parameter to pass to the callback routine + * ---async_tx api specific fields--- + * @next: at completion submit this descriptor + * @parent: pointer to the next level up in the dependency chain + * @lock: protect the parent and next pointers + */ +struct dma_async_tx_descriptor { + dma_cookie_t cookie; + enum dma_ctrl_flags flags; /* not a 'long' to pack with cookie */ + dma_addr_t phys; + struct dma_chan *chan; + dma_cookie_t (*tx_submit)(struct dma_async_tx_descriptor *tx); + int (*desc_free)(struct dma_async_tx_descriptor *tx); + dma_async_tx_callback callback; + dma_async_tx_callback_result callback_result; + void *callback_param; + struct dmaengine_unmap_data *unmap; +#ifdef CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH + struct dma_async_tx_descriptor *next; + struct dma_async_tx_descriptor *parent; + spinlock_t lock; +#endif +}; + +#ifdef CONFIG_DMA_ENGINE +static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx, + struct dmaengine_unmap_data *unmap) +{ + kref_get(&unmap->kref); + tx->unmap = unmap; +} + +struct dmaengine_unmap_data * +dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags); +void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap); +#else +static inline void dma_set_unmap(struct dma_async_tx_descriptor *tx, + struct dmaengine_unmap_data *unmap) +{ +} +static inline struct dmaengine_unmap_data * +dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags) +{ + return NULL; +} +static inline void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap) +{ +} +#endif + +static inline void dma_descriptor_unmap(struct dma_async_tx_descriptor *tx) +{ + if (tx->unmap) { + dmaengine_unmap_put(tx->unmap); + tx->unmap = NULL; + } +} + +#ifndef CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH +static inline void txd_lock(struct dma_async_tx_descriptor *txd) +{ +} +static inline void txd_unlock(struct dma_async_tx_descriptor *txd) +{ +} +static inline void txd_chain(struct dma_async_tx_descriptor *txd, struct dma_async_tx_descriptor *next) +{ + BUG(); +} +static inline void txd_clear_parent(struct dma_async_tx_descriptor *txd) +{ +} +static inline void txd_clear_next(struct dma_async_tx_descriptor *txd) +{ +} +static inline struct dma_async_tx_descriptor *txd_next(struct dma_async_tx_descriptor *txd) +{ + return NULL; +} +static inline struct dma_async_tx_descriptor *txd_parent(struct dma_async_tx_descriptor *txd) +{ + return NULL; +} + +#else +static inline void txd_lock(struct dma_async_tx_descriptor *txd) +{ + spin_lock_bh(&txd->lock); +} +static inline void txd_unlock(struct dma_async_tx_descriptor *txd) +{ + spin_unlock_bh(&txd->lock); +} +static inline void txd_chain(struct dma_async_tx_descriptor *txd, struct dma_async_tx_descriptor *next) +{ + txd->next = next; + next->parent = txd; +} +static inline void txd_clear_parent(struct dma_async_tx_descriptor *txd) +{ + txd->parent = NULL; +} +static inline void txd_clear_next(struct dma_async_tx_descriptor *txd) +{ + txd->next = NULL; +} +static inline struct dma_async_tx_descriptor *txd_parent(struct dma_async_tx_descriptor *txd) +{ + return txd->parent; +} +static inline struct dma_async_tx_descriptor *txd_next(struct dma_async_tx_descriptor *txd) +{ + return txd->next; +} +#endif + +/** + * struct dma_tx_state - filled in to report the status of + * a transfer. + * @last: last completed DMA cookie + * @used: last issued DMA cookie (i.e. the one in progress) + * @residue: the remaining number of bytes left to transmit + * on the selected transfer for states DMA_IN_PROGRESS and + * DMA_PAUSED if this is implemented in the driver, else 0 + */ +struct dma_tx_state { + dma_cookie_t last; + dma_cookie_t used; + u32 residue; +}; + +/** + * enum dmaengine_alignment - defines alignment of the DMA async tx + * buffers + */ +enum dmaengine_alignment { + DMAENGINE_ALIGN_1_BYTE = 0, + DMAENGINE_ALIGN_2_BYTES = 1, + DMAENGINE_ALIGN_4_BYTES = 2, + DMAENGINE_ALIGN_8_BYTES = 3, + DMAENGINE_ALIGN_16_BYTES = 4, + DMAENGINE_ALIGN_32_BYTES = 5, + DMAENGINE_ALIGN_64_BYTES = 6, +}; + +/** + * struct dma_slave_map - associates slave device and it's slave channel with + * parameter to be used by a filter function + * @devname: name of the device + * @slave: slave channel name + * @param: opaque parameter to pass to struct dma_filter.fn + */ +struct dma_slave_map { + const char *devname; + const char *slave; + void *param; +}; + +/** + * struct dma_filter - information for slave device/channel to filter_fn/param + * mapping + * @fn: filter function callback + * @mapcnt: number of slave device/channel in the map + * @map: array of channel to filter mapping data + */ +struct dma_filter { + dma_filter_fn fn; + int mapcnt; + const struct dma_slave_map *map; +}; + +/** + * struct dma_device - info on the entity supplying DMA services + * @chancnt: how many DMA channels are supported + * @privatecnt: how many DMA channels are requested by dma_request_channel + * @channels: the list of struct dma_chan + * @global_node: list_head for global dma_device_list + * @filter: information for device/slave to filter function/param mapping + * @cap_mask: one or more dma_capability flags + * @max_xor: maximum number of xor sources, 0 if no capability + * @max_pq: maximum number of PQ sources and PQ-continue capability + * @copy_align: alignment shift for memcpy operations + * @xor_align: alignment shift for xor operations + * @pq_align: alignment shift for pq operations + * @fill_align: alignment shift for memset operations + * @dev_id: unique device ID + * @dev: struct device reference for dma mapping api + * @src_addr_widths: bit mask of src addr widths the device supports + * Width is specified in bytes, e.g. for a device supporting + * a width of 4 the mask should have BIT(4) set. + * @dst_addr_widths: bit mask of dst addr widths the device supports + * @directions: bit mask of slave directions the device supports. + * Since the enum dma_transfer_direction is not defined as bit flag for + * each type, the dma controller should set BIT(<TYPE>) and same + * should be checked by controller as well + * @max_burst: max burst capability per-transfer + * @residue_granularity: granularity of the transfer residue reported + * by tx_status + * @device_alloc_chan_resources: allocate resources and return the + * number of allocated descriptors + * @device_free_chan_resources: release DMA channel's resources + * @device_prep_dma_memcpy: prepares a memcpy operation + * @device_prep_dma_xor: prepares a xor operation + * @device_prep_dma_xor_val: prepares a xor validation operation + * @device_prep_dma_pq: prepares a pq operation + * @device_prep_dma_pq_val: prepares a pqzero_sum operation + * @device_prep_dma_memset: prepares a memset operation + * @device_prep_dma_memset_sg: prepares a memset operation over a scatter list + * @device_prep_dma_interrupt: prepares an end of chain interrupt operation + * @device_prep_slave_sg: prepares a slave dma operation + * @device_prep_dma_cyclic: prepare a cyclic dma operation suitable for audio. + * The function takes a buffer of size buf_len. The callback function will + * be called after period_len bytes have been transferred. + * @device_prep_interleaved_dma: Transfer expression in a generic way. + * @device_prep_dma_imm_data: DMA's 8 byte immediate data to the dst address + * @device_config: Pushes a new configuration to a channel, return 0 or an error + * code + * @device_pause: Pauses any transfer happening on a channel. Returns + * 0 or an error code + * @device_resume: Resumes any transfer on a channel previously + * paused. Returns 0 or an error code + * @device_terminate_all: Aborts all transfers on a channel. Returns 0 + * or an error code + * @device_synchronize: Synchronizes the termination of a transfers to the + * current context. + * @device_tx_status: poll for transaction completion, the optional + * txstate parameter can be supplied with a pointer to get a + * struct with auxiliary transfer status information, otherwise the call + * will just return a simple status code + * @device_issue_pending: push pending transactions to hardware + * @descriptor_reuse: a submitted transfer can be resubmitted after completion + */ +struct dma_device { + + unsigned int chancnt; + unsigned int privatecnt; + struct list_head channels; + struct list_head global_node; + struct dma_filter filter; + dma_cap_mask_t cap_mask; + unsigned short max_xor; + unsigned short max_pq; + enum dmaengine_alignment copy_align; + enum dmaengine_alignment xor_align; + enum dmaengine_alignment pq_align; + enum dmaengine_alignment fill_align; + #define DMA_HAS_PQ_CONTINUE (1 << 15) + + int dev_id; + struct device *dev; + + u32 src_addr_widths; + u32 dst_addr_widths; + u32 directions; + u32 max_burst; + bool descriptor_reuse; + enum dma_residue_granularity residue_granularity; + + int (*device_alloc_chan_resources)(struct dma_chan *chan); + void (*device_free_chan_resources)(struct dma_chan *chan); + + struct dma_async_tx_descriptor *(*device_prep_dma_memcpy)( + struct dma_chan *chan, dma_addr_t dst, dma_addr_t src, + size_t len, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_xor)( + struct dma_chan *chan, dma_addr_t dst, dma_addr_t *src, + unsigned int src_cnt, size_t len, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_xor_val)( + struct dma_chan *chan, dma_addr_t *src, unsigned int src_cnt, + size_t len, enum sum_check_flags *result, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_pq)( + struct dma_chan *chan, dma_addr_t *dst, dma_addr_t *src, + unsigned int src_cnt, const unsigned char *scf, + size_t len, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_pq_val)( + struct dma_chan *chan, dma_addr_t *pq, dma_addr_t *src, + unsigned int src_cnt, const unsigned char *scf, size_t len, + enum sum_check_flags *pqres, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_memset)( + struct dma_chan *chan, dma_addr_t dest, int value, size_t len, + unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_memset_sg)( + struct dma_chan *chan, struct scatterlist *sg, + unsigned int nents, int value, unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)( + struct dma_chan *chan, unsigned long flags); + + struct dma_async_tx_descriptor *(*device_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 dma_async_tx_descriptor *(*device_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 dma_async_tx_descriptor *(*device_prep_interleaved_dma)( + struct dma_chan *chan, struct dma_interleaved_template *xt, + unsigned long flags); + struct dma_async_tx_descriptor *(*device_prep_dma_imm_data)( + struct dma_chan *chan, dma_addr_t dst, u64 data, + unsigned long flags); + + int (*device_config)(struct dma_chan *chan, + struct dma_slave_config *config); + int (*device_pause)(struct dma_chan *chan); + int (*device_resume)(struct dma_chan *chan); + int (*device_terminate_all)(struct dma_chan *chan); + void (*device_synchronize)(struct dma_chan *chan); + + enum dma_status (*device_tx_status)(struct dma_chan *chan, + dma_cookie_t cookie, + struct dma_tx_state *txstate); + void (*device_issue_pending)(struct dma_chan *chan); +}; + +static inline int dmaengine_slave_config(struct dma_chan *chan, + struct dma_slave_config *config) +{ + if (chan->device->device_config) + return chan->device->device_config(chan, config); + + return -ENOSYS; +} + +static inline bool is_slave_direction(enum dma_transfer_direction direction) +{ + return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM); +} + +static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single( + struct dma_chan *chan, dma_addr_t buf, size_t len, + enum dma_transfer_direction dir, unsigned long flags) +{ + struct scatterlist sg; + sg_init_table(&sg, 1); + sg_dma_address(&sg) = buf; + sg_dma_len(&sg) = len; + + if (!chan || !chan->device || !chan->device->device_prep_slave_sg) + return NULL; + + return chan->device->device_prep_slave_sg(chan, &sg, 1, + dir, flags, NULL); +} + +static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_sg( + struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, + enum dma_transfer_direction dir, unsigned long flags) +{ + if (!chan || !chan->device || !chan->device->device_prep_slave_sg) + return NULL; + + return chan->device->device_prep_slave_sg(chan, sgl, sg_len, + dir, flags, NULL); +} + +#ifdef CONFIG_RAPIDIO_DMA_ENGINE +struct rio_dma_ext; +static inline struct dma_async_tx_descriptor *dmaengine_prep_rio_sg( + struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len, + enum dma_transfer_direction dir, unsigned long flags, + struct rio_dma_ext *rio_ext) +{ + if (!chan || !chan->device || !chan->device->device_prep_slave_sg) + return NULL; + + return chan->device->device_prep_slave_sg(chan, sgl, sg_len, + dir, flags, rio_ext); +} +#endif + +static inline struct dma_async_tx_descriptor *dmaengine_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) +{ + if (!chan || !chan->device || !chan->device->device_prep_dma_cyclic) + return NULL; + + return chan->device->device_prep_dma_cyclic(chan, buf_addr, buf_len, + period_len, dir, flags); +} + +static inline struct dma_async_tx_descriptor *dmaengine_prep_interleaved_dma( + struct dma_chan *chan, struct dma_interleaved_template *xt, + unsigned long flags) +{ + if (!chan || !chan->device || !chan->device->device_prep_interleaved_dma) + return NULL; + + return chan->device->device_prep_interleaved_dma(chan, xt, flags); +} + +static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memset( + struct dma_chan *chan, dma_addr_t dest, int value, size_t len, + unsigned long flags) +{ + if (!chan || !chan->device || !chan->device->device_prep_dma_memset) + return NULL; + + return chan->device->device_prep_dma_memset(chan, dest, value, + len, flags); +} + +static inline struct dma_async_tx_descriptor *dmaengine_prep_dma_memcpy( + struct dma_chan *chan, dma_addr_t dest, dma_addr_t src, + size_t len, unsigned long flags) +{ + if (!chan || !chan->device || !chan->device->device_prep_dma_memcpy) + return NULL; + + return chan->device->device_prep_dma_memcpy(chan, dest, src, + len, flags); +} + +/** + * dmaengine_terminate_all() - Terminate all active DMA transfers + * @chan: The channel for which to terminate the transfers + * + * This function is DEPRECATED use either dmaengine_terminate_sync() or + * dmaengine_terminate_async() instead. + */ +static inline int dmaengine_terminate_all(struct dma_chan *chan) +{ + if (chan->device->device_terminate_all) + return chan->device->device_terminate_all(chan); + + return -ENOSYS; +} + +/** + * dmaengine_terminate_async() - Terminate all active DMA transfers + * @chan: The channel for which to terminate the transfers + * + * Calling this function will terminate all active and pending descriptors + * that have previously been submitted to the channel. It is not guaranteed + * though that the transfer for the active descriptor has stopped when the + * function returns. Furthermore it is possible the complete callback of a + * submitted transfer is still running when this function returns. + * + * dmaengine_synchronize() needs to be called before it is safe to free + * any memory that is accessed by previously submitted descriptors or before + * freeing any resources accessed from within the completion callback of any + * perviously submitted descriptors. + * + * This function can be called from atomic context as well as from within a + * complete callback of a descriptor submitted on the same channel. + * + * If none of the two conditions above apply consider using + * dmaengine_terminate_sync() instead. + */ +static inline int dmaengine_terminate_async(struct dma_chan *chan) +{ + if (chan->device->device_terminate_all) + return chan->device->device_terminate_all(chan); + + return -EINVAL; +} + +/** + * dmaengine_synchronize() - Synchronize DMA channel termination + * @chan: The channel to synchronize + * + * Synchronizes to the DMA channel termination to the current context. When this + * function returns it is guaranteed that all transfers for previously issued + * descriptors have stopped and and it is safe to free the memory assoicated + * with them. Furthermore it is guaranteed that all complete callback functions + * for a previously submitted descriptor have finished running and it is safe to + * free resources accessed from within the complete callbacks. + * + * The behavior of this function is undefined if dma_async_issue_pending() has + * been called between dmaengine_terminate_async() and this function. + * + * This function must only be called from non-atomic context and must not be + * called from within a complete callback of a descriptor submitted on the same + * channel. + */ +static inline void dmaengine_synchronize(struct dma_chan *chan) +{ + might_sleep(); + + if (chan->device->device_synchronize) + chan->device->device_synchronize(chan); +} + +/** + * dmaengine_terminate_sync() - Terminate all active DMA transfers + * @chan: The channel for which to terminate the transfers + * + * Calling this function will terminate all active and pending transfers + * that have previously been submitted to the channel. It is similar to + * dmaengine_terminate_async() but guarantees that the DMA transfer has actually + * stopped and that all complete callbacks have finished running when the + * function returns. + * + * This function must only be called from non-atomic context and must not be + * called from within a complete callback of a descriptor submitted on the same + * channel. + */ +static inline int dmaengine_terminate_sync(struct dma_chan *chan) +{ + int ret; + + ret = dmaengine_terminate_async(chan); + if (ret) + return ret; + + dmaengine_synchronize(chan); + + return 0; +} + +static inline int dmaengine_pause(struct dma_chan *chan) +{ + if (chan->device->device_pause) + return chan->device->device_pause(chan); + + return -ENOSYS; +} + +static inline int dmaengine_resume(struct dma_chan *chan) +{ + if (chan->device->device_resume) + return chan->device->device_resume(chan); + + return -ENOSYS; +} + +static inline enum dma_status dmaengine_tx_status(struct dma_chan *chan, + dma_cookie_t cookie, struct dma_tx_state *state) +{ + return chan->device->device_tx_status(chan, cookie, state); +} + +static inline dma_cookie_t dmaengine_submit(struct dma_async_tx_descriptor *desc) +{ + return desc->tx_submit(desc); +} + +static inline bool dmaengine_check_align(enum dmaengine_alignment align, + size_t off1, size_t off2, size_t len) +{ + size_t mask; + + if (!align) + return true; + mask = (1 << align) - 1; + if (mask & (off1 | off2 | len)) + return false; + return true; +} + +static inline bool is_dma_copy_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->copy_align, off1, off2, len); +} + +static inline bool is_dma_xor_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->xor_align, off1, off2, len); +} + +static inline bool is_dma_pq_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->pq_align, off1, off2, len); +} + +static inline bool is_dma_fill_aligned(struct dma_device *dev, size_t off1, + size_t off2, size_t len) +{ + return dmaengine_check_align(dev->fill_align, off1, off2, len); +} + +static inline void +dma_set_maxpq(struct dma_device *dma, int maxpq, int has_pq_continue) +{ + dma->max_pq = maxpq; + if (has_pq_continue) + dma->max_pq |= DMA_HAS_PQ_CONTINUE; +} + +static inline bool dmaf_continue(enum dma_ctrl_flags flags) +{ + return (flags & DMA_PREP_CONTINUE) == DMA_PREP_CONTINUE; +} + +static inline bool dmaf_p_disabled_continue(enum dma_ctrl_flags flags) +{ + enum dma_ctrl_flags mask = DMA_PREP_CONTINUE | DMA_PREP_PQ_DISABLE_P; + + return (flags & mask) == mask; +} + +static inline bool dma_dev_has_pq_continue(struct dma_device *dma) +{ + return (dma->max_pq & DMA_HAS_PQ_CONTINUE) == DMA_HAS_PQ_CONTINUE; +} + +static inline unsigned short dma_dev_to_maxpq(struct dma_device *dma) +{ + return dma->max_pq & ~DMA_HAS_PQ_CONTINUE; +} + +/* dma_maxpq - reduce maxpq in the face of continued operations + * @dma - dma device with PQ capability + * @flags - to check if DMA_PREP_CONTINUE and DMA_PREP_PQ_DISABLE_P are set + * + * When an engine does not support native continuation we need 3 extra + * source slots to reuse P and Q with the following coefficients: + * 1/ {00} * P : remove P from Q', but use it as a source for P' + * 2/ {01} * Q : use Q to continue Q' calculation + * 3/ {00} * Q : subtract Q from P' to cancel (2) + * + * In the case where P is disabled we only need 1 extra source: + * 1/ {01} * Q : use Q to continue Q' calculation + */ +static inline int dma_maxpq(struct dma_device *dma, enum dma_ctrl_flags flags) +{ + if (dma_dev_has_pq_continue(dma) || !dmaf_continue(flags)) + return dma_dev_to_maxpq(dma); + else if (dmaf_p_disabled_continue(flags)) + return dma_dev_to_maxpq(dma) - 1; + else if (dmaf_continue(flags)) + return dma_dev_to_maxpq(dma) - 3; + BUG(); +} + +static inline size_t dmaengine_get_icg(bool inc, bool sgl, size_t icg, + size_t dir_icg) +{ + if (inc) { + if (dir_icg) + return dir_icg; + else if (sgl) + return icg; + } + + return 0; +} + +static inline size_t dmaengine_get_dst_icg(struct dma_interleaved_template *xt, + struct data_chunk *chunk) +{ + return dmaengine_get_icg(xt->dst_inc, xt->dst_sgl, + chunk->icg, chunk->dst_icg); +} + +static inline size_t dmaengine_get_src_icg(struct dma_interleaved_template *xt, + struct data_chunk *chunk) +{ + return dmaengine_get_icg(xt->src_inc, xt->src_sgl, + chunk->icg, chunk->src_icg); +} + +/* --- public DMA engine API --- */ + +#ifdef CONFIG_DMA_ENGINE +void dmaengine_get(void); +void dmaengine_put(void); +#else +static inline void dmaengine_get(void) +{ +} +static inline void dmaengine_put(void) +{ +} +#endif + +#ifdef CONFIG_ASYNC_TX_DMA +#define async_dmaengine_get() dmaengine_get() +#define async_dmaengine_put() dmaengine_put() +#ifndef CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH +#define async_dma_find_channel(type) dma_find_channel(DMA_ASYNC_TX) +#else +#define async_dma_find_channel(type) dma_find_channel(type) +#endif /* CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH */ +#else +static inline void async_dmaengine_get(void) +{ +} +static inline void async_dmaengine_put(void) +{ +} +static inline struct dma_chan * +async_dma_find_channel(enum dma_transaction_type type) +{ + return NULL; +} +#endif /* CONFIG_ASYNC_TX_DMA */ +void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx, + struct dma_chan *chan); + +static inline void async_tx_ack(struct dma_async_tx_descriptor *tx) +{ + tx->flags |= DMA_CTRL_ACK; +} + +static inline void async_tx_clear_ack(struct dma_async_tx_descriptor *tx) +{ + tx->flags &= ~DMA_CTRL_ACK; +} + +static inline bool async_tx_test_ack(struct dma_async_tx_descriptor *tx) +{ + return (tx->flags & DMA_CTRL_ACK) == DMA_CTRL_ACK; +} + +#define dma_cap_set(tx, mask) __dma_cap_set((tx), &(mask)) +static inline void +__dma_cap_set(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp) +{ + set_bit(tx_type, dstp->bits); +} + +#define dma_cap_clear(tx, mask) __dma_cap_clear((tx), &(mask)) +static inline void +__dma_cap_clear(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp) +{ + clear_bit(tx_type, dstp->bits); +} + +#define dma_cap_zero(mask) __dma_cap_zero(&(mask)) +static inline void __dma_cap_zero(dma_cap_mask_t *dstp) +{ + bitmap_zero(dstp->bits, DMA_TX_TYPE_END); +} + +#define dma_has_cap(tx, mask) __dma_has_cap((tx), &(mask)) +static inline int +__dma_has_cap(enum dma_transaction_type tx_type, dma_cap_mask_t *srcp) +{ + return test_bit(tx_type, srcp->bits); +} + +#define for_each_dma_cap_mask(cap, mask) \ + for_each_set_bit(cap, mask.bits, DMA_TX_TYPE_END) + +/** + * dma_async_issue_pending - flush pending transactions to HW + * @chan: target DMA channel + * + * This allows drivers to push copies to HW in batches, + * reducing MMIO writes where possible. + */ +static inline void dma_async_issue_pending(struct dma_chan *chan) +{ + chan->device->device_issue_pending(chan); +} + +/** + * dma_async_is_tx_complete - poll for transaction completion + * @chan: DMA channel + * @cookie: transaction identifier to check status of + * @last: returns last completed cookie, can be NULL + * @used: returns last issued cookie, can be NULL + * + * If @last and @used are passed in, upon return they reflect the driver + * internal state and can be used with dma_async_is_complete() to check + * the status of multiple cookies without re-checking hardware state. + */ +static inline enum dma_status dma_async_is_tx_complete(struct dma_chan *chan, + dma_cookie_t cookie, dma_cookie_t *last, dma_cookie_t *used) +{ + struct dma_tx_state state; + enum dma_status status; + + status = chan->device->device_tx_status(chan, cookie, &state); + if (last) + *last = state.last; + if (used) + *used = state.used; + return status; +} + +/** + * dma_async_is_complete - test a cookie against chan state + * @cookie: transaction identifier to test status of + * @last_complete: last know completed transaction + * @last_used: last cookie value handed out + * + * dma_async_is_complete() is used in dma_async_is_tx_complete() + * the test logic is separated for lightweight testing of multiple cookies + */ +static inline enum dma_status dma_async_is_complete(dma_cookie_t cookie, + dma_cookie_t last_complete, dma_cookie_t last_used) +{ + if (last_complete <= last_used) { + if ((cookie <= last_complete) || (cookie > last_used)) + return DMA_COMPLETE; + } else { + if ((cookie <= last_complete) && (cookie > last_used)) + return DMA_COMPLETE; + } + return DMA_IN_PROGRESS; +} + +static inline void +dma_set_tx_state(struct dma_tx_state *st, dma_cookie_t last, dma_cookie_t used, u32 residue) +{ + if (st) { + st->last = last; + st->used = used; + st->residue = residue; + } +} + +#ifdef CONFIG_DMA_ENGINE +struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type); +enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie); +enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx); +void dma_issue_pending_all(void); +struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param); +struct dma_chan *dma_request_slave_channel(struct device *dev, const char *name); + +struct dma_chan *dma_request_chan(struct device *dev, const char *name); +struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask); + +void dma_release_channel(struct dma_chan *chan); +int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps); +#else +static inline struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type) +{ + return NULL; +} +static inline enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie) +{ + return DMA_COMPLETE; +} +static inline enum dma_status dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx) +{ + return DMA_COMPLETE; +} +static inline void dma_issue_pending_all(void) +{ +} +static inline struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param) +{ + return NULL; +} +static inline struct dma_chan *dma_request_slave_channel(struct device *dev, + const char *name) +{ + return NULL; +} +static inline struct dma_chan *dma_request_chan(struct device *dev, + const char *name) +{ + return ERR_PTR(-ENODEV); +} +static inline struct dma_chan *dma_request_chan_by_mask( + const dma_cap_mask_t *mask) +{ + return ERR_PTR(-ENODEV); +} +static inline void dma_release_channel(struct dma_chan *chan) +{ +} +static inline int dma_get_slave_caps(struct dma_chan *chan, + struct dma_slave_caps *caps) +{ + return -ENXIO; +} +#endif + +#define dma_request_slave_channel_reason(dev, name) dma_request_chan(dev, name) + +static inline int dmaengine_desc_set_reuse(struct dma_async_tx_descriptor *tx) +{ + struct dma_slave_caps caps; + + dma_get_slave_caps(tx->chan, &caps); + + if (caps.descriptor_reuse) { + tx->flags |= DMA_CTRL_REUSE; + return 0; + } else { + return -EPERM; + } +} + +static inline void dmaengine_desc_clear_reuse(struct dma_async_tx_descriptor *tx) +{ + tx->flags &= ~DMA_CTRL_REUSE; +} + +static inline bool dmaengine_desc_test_reuse(struct dma_async_tx_descriptor *tx) +{ + return (tx->flags & DMA_CTRL_REUSE) == DMA_CTRL_REUSE; +} + +static inline int dmaengine_desc_free(struct dma_async_tx_descriptor *desc) +{ + /* this is supported for reusable desc, so check that */ + if (dmaengine_desc_test_reuse(desc)) + return desc->desc_free(desc); + else + return -EPERM; +} + +/* --- DMA device --- */ + +int dma_async_device_register(struct dma_device *device); +int dmaenginem_async_device_register(struct dma_device *device); +void dma_async_device_unregister(struct dma_device *device); +void dma_run_dependencies(struct dma_async_tx_descriptor *tx); +struct dma_chan *dma_get_slave_channel(struct dma_chan *chan); +struct dma_chan *dma_get_any_slave_channel(struct dma_device *device); +#define dma_request_channel(mask, x, y) __dma_request_channel(&(mask), x, y) +#define dma_request_slave_channel_compat(mask, x, y, dev, name) \ + __dma_request_slave_channel_compat(&(mask), x, y, dev, name) + +static inline struct dma_chan +*__dma_request_slave_channel_compat(const dma_cap_mask_t *mask, + dma_filter_fn fn, void *fn_param, + struct device *dev, const char *name) +{ + struct dma_chan *chan; + + chan = dma_request_slave_channel(dev, name); + if (chan) + return chan; + + if (!fn || !fn_param) + return NULL; + + return __dma_request_channel(mask, fn, fn_param); +} +#endif /* DMAENGINE_H */