Re: [PATCH V3 4/4] dma: add Qualcomm Technologies HIDMA channel driver

[Andy Shevchenko]

On Sun, Nov 8, 2015 at 6:53 AM, Sinan Kaya <okaya@xxxxxxxxxxxxxx> wrote:
> This patch adds support for hidma engine. The driver
> consists of two logical blocks. The DMA engine interface
> and the low-level interface. The hardware only supports
> memcpy/memset and this driver only support memcpy
> interface. HW and driver doesn't support slave interface.

Make lines a bit longer.

> +/*
> + * Qualcomm Technologies HIDMA DMA engine interface
> + *
> + * Copyright (c) 2015, The Linux Foundation. All rights reserved.
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 and
> + * only version 2 as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
> + * GNU General Public License for more details.
> + */
> +
> +/*
> + * Copyright (C) Freescale Semicondutor, Inc. 2007, 2008.
> + * Copyright (C) Semihalf 2009
> + * Copyright (C) Ilya Yanok, Emcraft Systems 2010
> + * Copyright (C) Alexander Popov, Promcontroller 2014
> + *
> + * Written by Piotr Ziecik <kosmo@xxxxxxxxxxxx>. Hardware description
> + * (defines, structures and comments) was taken from MPC5121 DMA driver
> + * written by Hongjun Chen <hong-jun.chen@xxxxxxxxxxxxx>.
> + *
> + * Approved as OSADL project by a majority of OSADL members and funded
> + * by OSADL membership fees in 2009;  for details see www.osadl.org.
> + *
> + * 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.
> + */
> +
> +/* Linux Foundation elects GPLv2 license only. */
> +
> +#include <linux/dmaengine.h>
> +#include <linux/dma-mapping.h>
> +#include <linux/err.h>
> +#include <linux/init.h>
> +#include <linux/interrupt.h>
> +#include <linux/list.h>
> +#include <linux/module.h>
> +#include <linux/platform_device.h>
> +#include <linux/slab.h>
> +#include <linux/spinlock.h>
> +#include <linux/of_dma.h>
> +#include <linux/property.h>
> +#include <linux/delay.h>
> +#include <linux/highmem.h>
> +#include <linux/io.h>
> +#include <linux/sched.h>
> +#include <linux/wait.h>
> +#include <linux/acpi.h>
> +#include <linux/irq.h>
> +#include <linux/atomic.h>
> +#include <linux/pm_runtime.h>
> +
> +#include "../dmaengine.h"
> +#include "hidma.h"
> +
> +/*
> + * Default idle time is 2 seconds. This parameter can
> + * be overridden by changing the following
> + * /sys/bus/platform/devices/QCOM8061:<xy>/power/autosuspend_delay_ms
> + * during kernel boot.
> + */
> +#define AUTOSUSPEND_TIMEOUT            2000
> +#define ERR_INFO_SW                    0xFF
> +#define ERR_CODE_UNEXPECTED_TERMINATE  0x0
> +
> +static inline
> +struct hidma_dev *to_hidma_dev(struct dma_device *dmadev)
> +{
> +       return container_of(dmadev, struct hidma_dev, ddev);
> +}
> +
> +static inline
> +struct hidma_dev *to_hidma_dev_from_lldev(struct hidma_lldev **_lldevp)
> +{
> +       return container_of(_lldevp, struct hidma_dev, lldev);
> +}
> +
> +static inline
> +struct hidma_chan *to_hidma_chan(struct dma_chan *dmach)
> +{
> +       return container_of(dmach, struct hidma_chan, chan);
> +}
> +
> +static inline struct hidma_desc *
> +to_hidma_desc(struct dma_async_tx_descriptor *t)
> +{
> +       return container_of(t, struct hidma_desc, desc);
> +}
> +
> +static void hidma_free(struct hidma_dev *dmadev)
> +{
> +       dev_dbg(dmadev->ddev.dev, "free dmadev\n");
> +       INIT_LIST_HEAD(&dmadev->ddev.channels);
> +}
> +
> +static unsigned int nr_desc_prm;
> +module_param(nr_desc_prm, uint, 0644);
> +MODULE_PARM_DESC(nr_desc_prm,
> +                "number of descriptors (default: 0)");
> +
> +#define MAX_HIDMA_CHANNELS     64
> +static int event_channel_idx[MAX_HIDMA_CHANNELS] = {
> +       [0 ... (MAX_HIDMA_CHANNELS - 1)] = -1};
> +static unsigned int num_event_channel_idx;
> +module_param_array_named(event_channel_idx, event_channel_idx, int,
> +                       &num_event_channel_idx, 0644);
> +MODULE_PARM_DESC(event_channel_idx,
> +               "event channel index array for the notifications");
> +static atomic_t channel_ref_count;
> +
> +/* process completed descriptors */
> +static void hidma_process_completed(struct hidma_dev *mdma)
> +{
> +       dma_cookie_t last_cookie = 0;
> +       struct hidma_chan *mchan;
> +       struct hidma_desc *mdesc;
> +       struct dma_async_tx_descriptor *desc;
> +       unsigned long irqflags;
> +       struct list_head list;
> +       struct dma_chan *dmach = NULL;

Redundant assignment.

> +
> +       list_for_each_entry(dmach, &mdma->ddev.channels,
> +                       device_node) {
> +               mchan = to_hidma_chan(dmach);
> +               INIT_LIST_HEAD(&list);
> +
> +               /* Get all completed descriptors */
> +               spin_lock_irqsave(&mchan->lock, irqflags);
> +               list_splice_tail_init(&mchan->completed, &list);
> +               spin_unlock_irqrestore(&mchan->lock, irqflags);
> +
> +               /* Execute callbacks and run dependencies */
> +               list_for_each_entry(mdesc, &list, node) {
> +                       desc = &mdesc->desc;
> +
> +                       spin_lock_irqsave(&mchan->lock, irqflags);
> +                       dma_cookie_complete(desc);
> +                       spin_unlock_irqrestore(&mchan->lock, irqflags);
> +
> +                       if (desc->callback &&
> +                               (hidma_ll_status(mdma->lldev, mdesc->tre_ch)
> +                               == DMA_COMPLETE))
> +                               desc->callback(desc->callback_param);
> +
> +                       last_cookie = desc->cookie;
> +                       dma_run_dependencies(desc);
> +               }
> +
> +               /* Free descriptors */
> +               spin_lock_irqsave(&mchan->lock, irqflags);
> +               list_splice_tail_init(&list, &mchan->free);
> +               spin_unlock_irqrestore(&mchan->lock, irqflags);
> +       }
> +}
> +
> +/*
> + * Called once for each submitted descriptor.
> + * PM is locked once for each descriptor that is currently
> + * in execution.
> + */
> +static void hidma_callback(void *data)
> +{
> +       struct hidma_desc *mdesc = data;
> +       struct hidma_chan *mchan = to_hidma_chan(mdesc->desc.chan);
> +       unsigned long irqflags;
> +       struct dma_device *ddev = mchan->chan.device;
> +       struct hidma_dev *dmadev = to_hidma_dev(ddev);
> +       bool queued = false;
> +
> +       dev_dbg(dmadev->ddev.dev, "callback: data:0x%p\n", data);
> +
> +       spin_lock_irqsave(&mchan->lock, irqflags);
> +
> +       if (mdesc->node.next) {
> +               /* Delete from the active list, add to completed list */
> +               list_move_tail(&mdesc->node, &mchan->completed);
> +               queued = true;
> +       }
> +       spin_unlock_irqrestore(&mchan->lock, irqflags);
> +
> +       hidma_process_completed(dmadev);
> +
> +       if (queued) {
> +               pm_runtime_mark_last_busy(dmadev->ddev.dev);
> +               pm_runtime_put_autosuspend(dmadev->ddev.dev);
> +       }
> +}
> +
> +static int hidma_chan_init(struct hidma_dev *dmadev, u32 dma_sig)
> +{
> +       struct hidma_chan *mchan;
> +       struct dma_device *ddev;
> +
> +       mchan = devm_kzalloc(dmadev->ddev.dev, sizeof(*mchan), GFP_KERNEL);
> +       if (!mchan)
> +               return -ENOMEM;
> +
> +       ddev = &dmadev->ddev;
> +       mchan->dma_sig = dma_sig;
> +       mchan->dmadev = dmadev;
> +       mchan->chan.device = ddev;
> +       dma_cookie_init(&mchan->chan);
> +
> +       INIT_LIST_HEAD(&mchan->free);
> +       INIT_LIST_HEAD(&mchan->prepared);
> +       INIT_LIST_HEAD(&mchan->active);
> +       INIT_LIST_HEAD(&mchan->completed);
> +
> +       spin_lock_init(&mchan->lock);
> +       list_add_tail(&mchan->chan.device_node, &ddev->channels);
> +       dmadev->ddev.chancnt++;
> +       return 0;
> +}
> +
> +static void hidma_issue_pending(struct dma_chan *dmach)
> +{
> +       struct hidma_chan *mchan = to_hidma_chan(dmach);
> +       struct hidma_dev *dmadev = mchan->dmadev;
> +
> +       /* PM will be released in hidma_callback function. */
> +       pm_runtime_get_sync(dmadev->ddev.dev);
> +       hidma_ll_start(dmadev->lldev);
> +}
> +
> +static enum dma_status hidma_tx_status(struct dma_chan *dmach,
> +                                       dma_cookie_t cookie,
> +                                       struct dma_tx_state *txstate)
> +{
> +       enum dma_status ret;
> +       struct hidma_chan *mchan = to_hidma_chan(dmach);
> +
> +       if (mchan->paused)
> +               ret = DMA_PAUSED;
> +       else
> +               ret = dma_cookie_status(dmach, cookie, txstate);
> +
> +       return ret;
> +}
> +
> +/*
> + * Submit descriptor to hardware.
> + * Lock the PM for each descriptor we are sending.
> + */
> +static dma_cookie_t hidma_tx_submit(struct dma_async_tx_descriptor *txd)
> +{
> +       struct hidma_chan *mchan = to_hidma_chan(txd->chan);
> +       struct hidma_dev *dmadev = mchan->dmadev;
> +       struct hidma_desc *mdesc;
> +       unsigned long irqflags;
> +       dma_cookie_t cookie;
> +
> +       if (!hidma_ll_isenabled(dmadev->lldev))
> +               return -ENODEV;
> +
> +       mdesc = container_of(txd, struct hidma_desc, desc);
> +       spin_lock_irqsave(&mchan->lock, irqflags);
> +
> +       /* Move descriptor to active */
> +       list_move_tail(&mdesc->node, &mchan->active);
> +
> +       /* Update cookie */
> +       cookie = dma_cookie_assign(txd);
> +
> +       hidma_ll_queue_request(dmadev->lldev, mdesc->tre_ch);
> +       spin_unlock_irqrestore(&mchan->lock, irqflags);
> +
> +       return cookie;
> +}
> +
> +static int hidma_alloc_chan_resources(struct dma_chan *dmach)
> +{
> +       struct hidma_chan *mchan = to_hidma_chan(dmach);
> +       struct hidma_dev *dmadev = mchan->dmadev;
> +       int rc = 0;
> +       struct hidma_desc *mdesc, *tmp;
> +       unsigned long irqflags;
> +       LIST_HEAD(descs);
> +       u32 i;
> +
> +       if (mchan->allocated)
> +               return 0;
> +
> +       /* Alloc descriptors for this channel */
> +       for (i = 0; i < dmadev->nr_descriptors; i++) {
> +               mdesc = kzalloc(sizeof(struct hidma_desc), GFP_KERNEL);
> +               if (!mdesc) {
> +                       rc = -ENOMEM;
> +                       break;
> +               }
> +               dma_async_tx_descriptor_init(&mdesc->desc, dmach);
> +               mdesc->desc.flags = DMA_CTRL_ACK;
> +               mdesc->desc.tx_submit = hidma_tx_submit;
> +
> +               rc = hidma_ll_request(dmadev->lldev,
> +                               mchan->dma_sig, "DMA engine", hidma_callback,
> +                               mdesc, &mdesc->tre_ch);
> +               if (rc) {
> +                       dev_err(dmach->device->dev,
> +                               "channel alloc failed at %u\n", i);
> +                       kfree(mdesc);
> +                       break;
> +               }
> +               list_add_tail(&mdesc->node, &descs);
> +       }
> +
> +       if (rc) {
> +               /* return the allocated descriptors */
> +               list_for_each_entry_safe(mdesc, tmp, &descs, node) {
> +                       hidma_ll_free(dmadev->lldev, mdesc->tre_ch);
> +                       kfree(mdesc);
> +               }
> +               return rc;
> +       }
> +
> +       spin_lock_irqsave(&mchan->lock, irqflags);
> +       list_splice_tail_init(&descs, &mchan->free);
> +       mchan->allocated = true;
> +       spin_unlock_irqrestore(&mchan->lock, irqflags);
> +       dev_dbg(dmadev->ddev.dev,
> +               "allocated channel for %u\n", mchan->dma_sig);
> +       return 1;
> +}
> +
> +static void hidma_free_chan_resources(struct dma_chan *dmach)
> +{
> +       struct hidma_chan *mchan = to_hidma_chan(dmach);
> +       struct hidma_dev *mdma = mchan->dmadev;
> +       struct hidma_desc *mdesc, *tmp;
> +       unsigned long irqflags;
> +       LIST_HEAD(descs);
> +
> +       if (!list_empty(&mchan->prepared) ||
> +               !list_empty(&mchan->active) ||
> +               !list_empty(&mchan->completed)) {
> +               /*
> +                * We have unfinished requests waiting.
> +                * Terminate the request from the hardware.
> +                */
> +               hidma_cleanup_pending_tre(mdma->lldev, ERR_INFO_SW,
> +                               ERR_CODE_UNEXPECTED_TERMINATE);
> +
> +               /* Give enough time for completions to be called. */
> +               msleep(100);
> +       }
> +
> +       spin_lock_irqsave(&mchan->lock, irqflags);
> +       /* Channel must be idle */
> +       WARN_ON(!list_empty(&mchan->prepared));
> +       WARN_ON(!list_empty(&mchan->active));
> +       WARN_ON(!list_empty(&mchan->completed));
> +
> +       /* Move data */
> +       list_splice_tail_init(&mchan->free, &descs);
> +
> +       /* Free descriptors */
> +       list_for_each_entry_safe(mdesc, tmp, &descs, node) {
> +               hidma_ll_free(mdma->lldev, mdesc->tre_ch);
> +               list_del(&mdesc->node);
> +               kfree(mdesc);
> +       }
> +
> +       mchan->allocated = 0;
> +       spin_unlock_irqrestore(&mchan->lock, irqflags);
> +       dev_dbg(mdma->ddev.dev, "freed channel for %u\n", mchan->dma_sig);
> +}
> +
> +
> +static struct dma_async_tx_descriptor *
> +hidma_prep_dma_memcpy(struct dma_chan *dmach, dma_addr_t dma_dest,
> +                       dma_addr_t dma_src, size_t len, unsigned long flags)
> +{
> +       struct hidma_chan *mchan = to_hidma_chan(dmach);
> +       struct hidma_desc *mdesc = NULL;
> +       struct hidma_dev *mdma = mchan->dmadev;
> +       unsigned long irqflags;
> +
> +       dev_dbg(mdma->ddev.dev,
> +               "memcpy: chan:%p dest:%pad src:%pad len:%zu\n", mchan,
> +               &dma_dest, &dma_src, len);
> +
> +       /* Get free descriptor */
> +       spin_lock_irqsave(&mchan->lock, irqflags);
> +       if (!list_empty(&mchan->free)) {
> +               mdesc = list_first_entry(&mchan->free, struct hidma_desc,
> +                                       node);
> +               list_del(&mdesc->node);
> +       }
> +       spin_unlock_irqrestore(&mchan->lock, irqflags);
> +
> +       if (!mdesc)
> +               return NULL;
> +
> +       hidma_ll_set_transfer_params(mdma->lldev, mdesc->tre_ch,
> +                       dma_src, dma_dest, len, flags);
> +
> +       /* Place descriptor in prepared list */
> +       spin_lock_irqsave(&mchan->lock, irqflags);
> +       list_add_tail(&mdesc->node, &mchan->prepared);
> +       spin_unlock_irqrestore(&mchan->lock, irqflags);
> +
> +       return &mdesc->desc;
> +}
> +
> +static int hidma_terminate_all(struct dma_chan *chan)
> +{
> +       struct hidma_dev *dmadev;
> +       LIST_HEAD(head);
> +       unsigned long irqflags;
> +       LIST_HEAD(list);
> +       struct hidma_desc *tmp, *mdesc = NULL;
> +       int rc;
> +       struct hidma_chan *mchan;
> +
> +       mchan = to_hidma_chan(chan);
> +       dmadev = to_hidma_dev(mchan->chan.device);
> +       dev_dbg(dmadev->ddev.dev, "terminateall: chan:0x%p\n", mchan);
> +
> +       pm_runtime_get_sync(dmadev->ddev.dev);
> +       /* give completed requests a chance to finish */
> +       hidma_process_completed(dmadev);
> +
> +       spin_lock_irqsave(&mchan->lock, irqflags);
> +       list_splice_init(&mchan->active, &list);
> +       list_splice_init(&mchan->prepared, &list);
> +       list_splice_init(&mchan->completed, &list);
> +       spin_unlock_irqrestore(&mchan->lock, irqflags);
> +
> +       /* this suspends the existing transfer */
> +       rc = hidma_ll_pause(dmadev->lldev);
> +       if (rc) {
> +               dev_err(dmadev->ddev.dev, "channel did not pause\n");
> +               goto out;
> +       }
> +
> +       /* return all user requests */
> +       list_for_each_entry_safe(mdesc, tmp, &list, node) {
> +               struct dma_async_tx_descriptor  *txd = &mdesc->desc;
> +               dma_async_tx_callback callback = mdesc->desc.callback;
> +               void *param = mdesc->desc.callback_param;
> +               enum dma_status status;
> +
> +               dma_descriptor_unmap(txd);
> +
> +               status = hidma_ll_status(dmadev->lldev, mdesc->tre_ch);
> +               /*
> +                * The API requires that no submissions are done from a
> +                * callback, so we don't need to drop the lock here
> +                */
> +               if (callback && (status == DMA_COMPLETE))
> +                       callback(param);
> +
> +               dma_run_dependencies(txd);
> +
> +               /* move myself to free_list */
> +               list_move(&mdesc->node, &mchan->free);
> +       }
> +
> +       /* reinitialize the hardware */
> +       rc = hidma_ll_setup(dmadev->lldev);
> +
> +out:
> +       pm_runtime_mark_last_busy(dmadev->ddev.dev);
> +       pm_runtime_put_autosuspend(dmadev->ddev.dev);
> +       return rc;
> +}
> +
> +static int hidma_pause(struct dma_chan *chan)
> +{
> +       struct hidma_chan *mchan;
> +       struct hidma_dev *dmadev;
> +
> +       mchan = to_hidma_chan(chan);
> +       dmadev = to_hidma_dev(mchan->chan.device);
> +       dev_dbg(dmadev->ddev.dev, "pause: chan:0x%p\n", mchan);
> +
> +       if (!mchan->paused) {
> +               pm_runtime_get_sync(dmadev->ddev.dev);
> +               if (hidma_ll_pause(dmadev->lldev))
> +                       dev_warn(dmadev->ddev.dev, "channel did not stop\n");
> +               mchan->paused = true;
> +               pm_runtime_mark_last_busy(dmadev->ddev.dev);
> +               pm_runtime_put_autosuspend(dmadev->ddev.dev);
> +       }
> +       return 0;
> +}
> +
> +static int hidma_resume(struct dma_chan *chan)
> +{
> +       struct hidma_chan *mchan;
> +       struct hidma_dev *dmadev;
> +       int rc = 0;
> +
> +       mchan = to_hidma_chan(chan);
> +       dmadev = to_hidma_dev(mchan->chan.device);
> +       dev_dbg(dmadev->ddev.dev, "resume: chan:0x%p\n", mchan);
> +
> +       if (mchan->paused) {
> +               pm_runtime_get_sync(dmadev->ddev.dev);
> +               rc = hidma_ll_resume(dmadev->lldev);
> +               if (!rc)
> +                       mchan->paused = false;
> +               else
> +                       dev_err(dmadev->ddev.dev,
> +                                       "failed to resume the channel");
> +               pm_runtime_mark_last_busy(dmadev->ddev.dev);
> +               pm_runtime_put_autosuspend(dmadev->ddev.dev);
> +       }
> +       return rc;
> +}
> +
> +static irqreturn_t hidma_chirq_handler(int chirq, void *arg)
> +{
> +       struct hidma_lldev **lldev_ptr = arg;
> +       irqreturn_t ret;
> +       struct hidma_dev *dmadev = to_hidma_dev_from_lldev(lldev_ptr);
> +
> +       /*
> +        * All interrupts are request driven.
> +        * HW doesn't send an interrupt by itself.
> +        */
> +       pm_runtime_get_sync(dmadev->ddev.dev);
> +       ret = hidma_ll_inthandler(chirq, *lldev_ptr);
> +       pm_runtime_mark_last_busy(dmadev->ddev.dev);
> +       pm_runtime_put_autosuspend(dmadev->ddev.dev);
> +       return ret;
> +}
> +
> +static int hidma_probe(struct platform_device *pdev)
> +{
> +       struct hidma_dev *dmadev;
> +       int rc = 0;
> +       struct resource *trca_resource;
> +       struct resource *evca_resource;
> +       int chirq;
> +       int current_channel_index = atomic_read(&channel_ref_count);
> +       void *evca;
> +       void *trca;
> +
> +       pm_runtime_set_autosuspend_delay(&pdev->dev, AUTOSUSPEND_TIMEOUT);
> +       pm_runtime_use_autosuspend(&pdev->dev);
> +       pm_runtime_set_active(&pdev->dev);
> +       pm_runtime_enable(&pdev->dev);
> +
> +       trca_resource = platform_get_resource(pdev, IORESOURCE_MEM, 0);

> +       if (!trca_resource) {
> +               rc = -ENODEV;
> +               goto bailout;
> +       }

Why did you ignore my comment about this block?
Remove that condition entirely.

> +
> +       trca = devm_ioremap_resource(&pdev->dev, trca_resource);
> +       if (IS_ERR(trca)) {
> +               rc = -ENOMEM;
> +               goto bailout;
> +       }
> +
> +       evca_resource = platform_get_resource(pdev, IORESOURCE_MEM, 1);
> +       if (!evca_resource) {
> +               rc = -ENODEV;
> +               goto bailout;
> +       }

Ditto.

> +
> +       evca = devm_ioremap_resource(&pdev->dev, evca_resource);
> +       if (IS_ERR(evca)) {
> +               rc = -ENOMEM;
> +               goto bailout;
> +       }
> +
> +       /*
> +        * This driver only handles the channel IRQs.
> +        * Common IRQ is handled by the management driver.
> +        */
> +       chirq = platform_get_irq(pdev, 0);
> +       if (chirq < 0) {
> +               rc = -ENODEV;
> +               goto bailout;
> +       }
> +
> +       dmadev = devm_kzalloc(&pdev->dev, sizeof(*dmadev), GFP_KERNEL);
> +       if (!dmadev) {
> +               rc = -ENOMEM;
> +               goto bailout;
> +       }
> +
> +       INIT_LIST_HEAD(&dmadev->ddev.channels);
> +       spin_lock_init(&dmadev->lock);
> +       dmadev->ddev.dev = &pdev->dev;
> +       pm_runtime_get_sync(dmadev->ddev.dev);
> +
> +       dma_cap_set(DMA_MEMCPY, dmadev->ddev.cap_mask);
> +       if (WARN_ON(!pdev->dev.dma_mask)) {
> +               rc = -ENXIO;
> +               goto dmafree;
> +       }
> +
> +       dmadev->dev_evca = evca;
> +       dmadev->evca_resource = evca_resource;
> +       dmadev->dev_trca = trca;
> +       dmadev->trca_resource = trca_resource;
> +       dmadev->ddev.device_prep_dma_memcpy = hidma_prep_dma_memcpy;
> +       dmadev->ddev.device_alloc_chan_resources =
> +               hidma_alloc_chan_resources;
> +       dmadev->ddev.device_free_chan_resources = hidma_free_chan_resources;
> +       dmadev->ddev.device_tx_status = hidma_tx_status;
> +       dmadev->ddev.device_issue_pending = hidma_issue_pending;
> +       dmadev->ddev.device_pause = hidma_pause;
> +       dmadev->ddev.device_resume = hidma_resume;
> +       dmadev->ddev.device_terminate_all = hidma_terminate_all;
> +       dmadev->ddev.copy_align = 8;
> +
> +       device_property_read_u32(&pdev->dev, "desc-count",
> +                               &dmadev->nr_descriptors);
> +
> +       if (!dmadev->nr_descriptors && nr_desc_prm)
> +               dmadev->nr_descriptors = nr_desc_prm;
> +
> +       if (!dmadev->nr_descriptors)
> +               goto dmafree;
> +
> +       if (current_channel_index > MAX_HIDMA_CHANNELS)
> +               goto dmafree;
> +
> +       dmadev->evridx = -1;
> +       device_property_read_u32(&pdev->dev, "event-channel", &dmadev->evridx);
> +
> +       /* kernel command line override for the guest machine */
> +       if (event_channel_idx[current_channel_index] != -1)
> +               dmadev->evridx = event_channel_idx[current_channel_index];
> +
> +       if (dmadev->evridx == -1)
> +               goto dmafree;
> +
> +       /* Set DMA mask to 64 bits. */
> +       rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
> +       if (rc) {
> +               dev_warn(&pdev->dev, "unable to set coherent mask to 64");
> +               rc = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
> +               if (rc)
> +                       goto dmafree;
> +       }
> +
> +       dmadev->lldev = hidma_ll_init(dmadev->ddev.dev,
> +                               dmadev->nr_descriptors, dmadev->dev_trca,
> +                               dmadev->dev_evca, dmadev->evridx);
> +       if (!dmadev->lldev) {
> +               rc = -EPROBE_DEFER;
> +               goto dmafree;
> +       }
> +
> +       rc = devm_request_irq(&pdev->dev, chirq, hidma_chirq_handler, 0,
> +                             "qcom-hidma", &dmadev->lldev);
> +       if (rc)
> +               goto uninit;
> +
> +       INIT_LIST_HEAD(&dmadev->ddev.channels);
> +       rc = hidma_chan_init(dmadev, 0);
> +       if (rc)
> +               goto uninit;
> +
> +       rc = dma_selftest_memcpy(&dmadev->ddev);
> +       if (rc)
> +               goto uninit;
> +
> +       rc = dma_async_device_register(&dmadev->ddev);
> +       if (rc)
> +               goto uninit;
> +
> +       hidma_debug_init(dmadev);
> +       dev_info(&pdev->dev, "HI-DMA engine driver registration complete\n");
> +       platform_set_drvdata(pdev, dmadev);
> +       pm_runtime_mark_last_busy(dmadev->ddev.dev);
> +       pm_runtime_put_autosuspend(dmadev->ddev.dev);
> +       atomic_inc(&channel_ref_count);
> +       return 0;
> +
> +uninit:
> +       hidma_debug_uninit(dmadev);
> +       hidma_ll_uninit(dmadev->lldev);
> +dmafree:
> +       if (dmadev)
> +               hidma_free(dmadev);
> +bailout:
> +       pm_runtime_disable(&pdev->dev);
> +       pm_runtime_put_sync_suspend(&pdev->dev);

Are you sure this is appropriate sequence?

I think

pm_runtime_put();
pm_runtime_disable();

will do the job.

> +       return rc;
> +}
> +
> +static int hidma_remove(struct platform_device *pdev)
> +{
> +       struct hidma_dev *dmadev = platform_get_drvdata(pdev);
> +
> +       dev_dbg(&pdev->dev, "removing\n");

Useless message.

> +       pm_runtime_get_sync(dmadev->ddev.dev);
> +
> +       dma_async_device_unregister(&dmadev->ddev);
> +       hidma_debug_uninit(dmadev);
> +       hidma_ll_uninit(dmadev->lldev);
> +       hidma_free(dmadev);
> +
> +       dev_info(&pdev->dev, "HI-DMA engine removed\n");
> +       pm_runtime_put_sync_suspend(&pdev->dev);
> +       pm_runtime_disable(&pdev->dev);
> +
> +       return 0;
> +}
> +
> +#if IS_ENABLED(CONFIG_ACPI)
> +static const struct acpi_device_id hidma_acpi_ids[] = {
> +       {"QCOM8061"},
> +       {},
> +};
> +#endif
> +
> +static const struct of_device_id hidma_match[] = {
> +       { .compatible = "qcom,hidma-1.0", },
> +       {},
> +};
> +MODULE_DEVICE_TABLE(of, hidma_match);
> +
> +static struct platform_driver hidma_driver = {
> +       .probe = hidma_probe,
> +       .remove = hidma_remove,
> +       .driver = {
> +               .name = "hidma",
> +               .of_match_table = hidma_match,
> +               .acpi_match_table = ACPI_PTR(hidma_acpi_ids),
> +       },
> +};
> +module_platform_driver(hidma_driver);
> +MODULE_LICENSE("GPL v2");
> diff --git a/drivers/dma/qcom/hidma.h b/drivers/dma/qcom/hidma.h
> new file mode 100644
> index 0000000..195d6b5
> --- /dev/null
> +++ b/drivers/dma/qcom/hidma.h
> @@ -0,0 +1,157 @@
> +/*
> + * Qualcomm Technologies HIDMA data structures
> + *
> + * Copyright (c) 2014, The Linux Foundation. All rights reserved.
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 and
> + * only version 2 as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
> + * GNU General Public License for more details.
> + */
> +
> +#ifndef QCOM_HIDMA_H
> +#define QCOM_HIDMA_H
> +
> +#include <linux/kfifo.h>
> +#include <linux/interrupt.h>
> +#include <linux/dmaengine.h>
> +
> +#define TRE_SIZE                       32 /* each TRE is 32 bytes  */
> +#define TRE_CFG_IDX                    0
> +#define TRE_LEN_IDX                    1
> +#define TRE_SRC_LOW_IDX                2
> +#define TRE_SRC_HI_IDX                 3
> +#define TRE_DEST_LOW_IDX               4
> +#define TRE_DEST_HI_IDX                5
> +
> +struct hidma_tx_status {
> +       u8 err_info;                    /* error record in this transfer    */
> +       u8 err_code;                    /* completion code                  */
> +};
> +
> +struct hidma_tre {
> +       atomic_t allocated;             /* if this channel is allocated     */
> +       bool queued;                    /* flag whether this is pending     */
> +       u16 status;                     /* status                           */
> +       u32 chidx;                      /* index of the tre         */
> +       u32 dma_sig;                    /* signature of the tre     */
> +       const char *dev_name;           /* name of the device               */
> +       void (*callback)(void *data);   /* requester callback               */
> +       void *data;                     /* Data associated with this channel*/
> +       struct hidma_lldev *lldev;      /* lldma device pointer             */
> +       u32 tre_local[TRE_SIZE / sizeof(u32) + 1]; /* TRE local copy        */
> +       u32 tre_index;                  /* the offset where this was written*/
> +       u32 int_flags;                  /* interrupt flags*/
> +};
> +
> +struct hidma_lldev {
> +       bool initialized;               /* initialized flag               */
> +       u8 trch_state;                  /* trch_state of the device       */
> +       u8 evch_state;                  /* evch_state of the device       */
> +       u8 evridx;                      /* event channel to notify        */
> +       u32 nr_tres;                    /* max number of configs          */
> +       spinlock_t lock;                /* reentrancy                     */
> +       struct hidma_tre *trepool;      /* trepool of user configs */
> +       struct device *dev;             /* device                         */
> +       void __iomem *trca;             /* Transfer Channel address       */
> +       void __iomem *evca;             /* Event Channel address          */
> +       struct hidma_tre
> +               **pending_tre_list;     /* Pointers to pending TREs       */
> +       struct hidma_tx_status
> +               *tx_status_list;        /* Pointers to pending TREs status*/
> +       s32 pending_tre_count;          /* Number of TREs pending         */
> +
> +       void *tre_ring;         /* TRE ring                       */
> +       dma_addr_t tre_ring_handle;     /* TRE ring to be shared with HW  */
> +       u32 tre_ring_size;              /* Byte size of the ring          */
> +       u32 tre_processed_off;          /* last processed TRE              */
> +
> +       void *evre_ring;                /* EVRE ring                       */
> +       dma_addr_t evre_ring_handle;    /* EVRE ring to be shared with HW  */
> +       u32 evre_ring_size;             /* Byte size of the ring          */
> +       u32 evre_processed_off; /* last processed EVRE             */
> +
> +       u32 tre_write_offset;           /* TRE write location              */
> +       struct tasklet_struct task;     /* task delivering notifications   */
> +       DECLARE_KFIFO_PTR(handoff_fifo,
> +               struct hidma_tre *);    /* pending TREs FIFO              */
> +};
> +
> +struct hidma_desc {
> +       struct dma_async_tx_descriptor  desc;
> +       /* link list node for this channel*/
> +       struct list_head                node;
> +       u32                             tre_ch;
> +};
> +
> +struct hidma_chan {
> +       bool                            paused;
> +       bool                            allocated;
> +       char                            dbg_name[16];
> +       u32                             dma_sig;
> +
> +       /*
> +        * active descriptor on this channel
> +        * It is used by the DMA complete notification to
> +        * locate the descriptor that initiated the transfer.
> +        */
> +       struct dentry                   *debugfs;
> +       struct dentry                   *stats;
> +       struct hidma_dev                *dmadev;
> +
> +       struct dma_chan                 chan;
> +       struct list_head                free;
> +       struct list_head                prepared;
> +       struct list_head                active;
> +       struct list_head                completed;
> +
> +       /* Lock for this structure */
> +       spinlock_t                      lock;
> +};
> +
> +struct hidma_dev {
> +       int                             evridx;
> +       u32                             nr_descriptors;
> +
> +       struct hidma_lldev              *lldev;
> +       void                            __iomem *dev_trca;
> +       struct resource                 *trca_resource;
> +       void                            __iomem *dev_evca;
> +       struct resource                 *evca_resource;
> +
> +       /* used to protect the pending channel list*/
> +       spinlock_t                      lock;
> +       struct dma_device               ddev;
> +
> +       struct dentry                   *debugfs;
> +       struct dentry                   *stats;
> +};
> +
> +int hidma_ll_request(struct hidma_lldev *llhndl, u32 dev_id,
> +                       const char *dev_name,
> +                       void (*callback)(void *data), void *data, u32 *tre_ch);
> +
> +void hidma_ll_free(struct hidma_lldev *llhndl, u32 tre_ch);
> +enum dma_status hidma_ll_status(struct hidma_lldev *llhndl, u32 tre_ch);
> +bool hidma_ll_isenabled(struct hidma_lldev *llhndl);
> +int hidma_ll_queue_request(struct hidma_lldev *llhndl, u32 tre_ch);
> +int hidma_ll_start(struct hidma_lldev *llhndl);
> +int hidma_ll_pause(struct hidma_lldev *llhndl);
> +int hidma_ll_resume(struct hidma_lldev *llhndl);
> +void hidma_ll_set_transfer_params(struct hidma_lldev *llhndl, u32 tre_ch,
> +       dma_addr_t src, dma_addr_t dest, u32 len, u32 flags);
> +int hidma_ll_setup(struct hidma_lldev *lldev);
> +struct hidma_lldev *hidma_ll_init(struct device *dev, u32 max_channels,
> +                       void __iomem *trca, void __iomem *evca,
> +                       u8 evridx);
> +int hidma_ll_uninit(struct hidma_lldev *llhndl);
> +irqreturn_t hidma_ll_inthandler(int irq, void *arg);
> +void hidma_cleanup_pending_tre(struct hidma_lldev *llhndl, u8 err_info,
> +                               u8 err_code);
> +int hidma_debug_init(struct hidma_dev *dmadev);
> +void hidma_debug_uninit(struct hidma_dev *dmadev);
> +#endif
> diff --git a/drivers/dma/qcom/hidma_dbg.c b/drivers/dma/qcom/hidma_dbg.c
> new file mode 100644
> index 0000000..e0e6711
> --- /dev/null
> +++ b/drivers/dma/qcom/hidma_dbg.c
> @@ -0,0 +1,225 @@
> +/*
> + * Qualcomm Technologies HIDMA debug file
> + *
> + * Copyright (c) 2015, The Linux Foundation. All rights reserved.
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 and
> + * only version 2 as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
> + * GNU General Public License for more details.
> + */
> +
> +#include <linux/debugfs.h>
> +#include <linux/device.h>
> +#include <linux/list.h>
> +#include <linux/pm_runtime.h>
> +
> +#include "hidma.h"
> +
> +void hidma_ll_chstats(struct seq_file *s, void *llhndl, u32 tre_ch)
> +{
> +       struct hidma_lldev *lldev = llhndl;
> +       struct hidma_tre *tre;
> +       u32 length;
> +       dma_addr_t src_start;
> +       dma_addr_t dest_start;
> +       u32 *tre_local;
> +
> +       if (tre_ch >= lldev->nr_tres) {
> +               dev_err(lldev->dev, "invalid TRE number in chstats:%d",
> +                       tre_ch);
> +               return;
> +       }
> +       tre = &lldev->trepool[tre_ch];
> +       seq_printf(s, "------Channel %d -----\n", tre_ch);
> +       seq_printf(s, "allocated=%d\n", atomic_read(&tre->allocated));
> +       seq_printf(s, "queued=0x%x\n", tre->queued);
> +       seq_printf(s, "err_info=0x%x\n",
> +                  lldev->tx_status_list[tre->chidx].err_info);
> +       seq_printf(s, "err_code=0x%x\n",
> +                  lldev->tx_status_list[tre->chidx].err_code);
> +       seq_printf(s, "status=0x%x\n", tre->status);
> +       seq_printf(s, "chidx=0x%x\n", tre->chidx);
> +       seq_printf(s, "dma_sig=0x%x\n", tre->dma_sig);
> +       seq_printf(s, "dev_name=%s\n", tre->dev_name);
> +       seq_printf(s, "callback=%p\n", tre->callback);
> +       seq_printf(s, "data=%p\n", tre->data);
> +       seq_printf(s, "tre_index=0x%x\n", tre->tre_index);
> +
> +       tre_local = &tre->tre_local[0];
> +       src_start = tre_local[TRE_SRC_LOW_IDX];
> +       src_start = ((u64)(tre_local[TRE_SRC_HI_IDX]) << 32) + src_start;
> +       dest_start = tre_local[TRE_DEST_LOW_IDX];
> +       dest_start += ((u64)(tre_local[TRE_DEST_HI_IDX]) << 32);
> +       length = tre_local[TRE_LEN_IDX];
> +
> +       seq_printf(s, "src=%pap\n", &src_start);
> +       seq_printf(s, "dest=%pap\n", &dest_start);
> +       seq_printf(s, "length=0x%x\n", length);
> +}
> +
> +void hidma_ll_devstats(struct seq_file *s, void *llhndl)
> +{
> +       struct hidma_lldev *lldev = llhndl;
> +
> +       seq_puts(s, "------Device -----\n");
> +       seq_printf(s, "lldev init=0x%x\n", lldev->initialized);
> +       seq_printf(s, "trch_state=0x%x\n", lldev->trch_state);
> +       seq_printf(s, "evch_state=0x%x\n", lldev->evch_state);
> +       seq_printf(s, "evridx=0x%x\n", lldev->evridx);
> +       seq_printf(s, "nr_tres=0x%x\n", lldev->nr_tres);
> +       seq_printf(s, "trca=%p\n", lldev->trca);
> +       seq_printf(s, "tre_ring=%p\n", lldev->tre_ring);
> +       seq_printf(s, "tre_ring_handle=%pap\n", &lldev->tre_ring_handle);
> +       seq_printf(s, "tre_ring_size=0x%x\n", lldev->tre_ring_size);
> +       seq_printf(s, "tre_processed_off=0x%x\n", lldev->tre_processed_off);
> +       seq_printf(s, "pending_tre_count=%d\n", lldev->pending_tre_count);
> +       seq_printf(s, "evca=%p\n", lldev->evca);
> +       seq_printf(s, "evre_ring=%p\n", lldev->evre_ring);
> +       seq_printf(s, "evre_ring_handle=%pap\n", &lldev->evre_ring_handle);
> +       seq_printf(s, "evre_ring_size=0x%x\n", lldev->evre_ring_size);
> +       seq_printf(s, "evre_processed_off=0x%x\n", lldev->evre_processed_off);
> +       seq_printf(s, "tre_write_offset=0x%x\n", lldev->tre_write_offset);
> +}
> +
> +/**
> + * hidma_chan_stats: display HIDMA channel statistics
> + *
> + * Display the statistics for the current HIDMA virtual channel device.
> + */
> +static int hidma_chan_stats(struct seq_file *s, void *unused)
> +{
> +       struct hidma_chan *mchan = s->private;
> +       struct hidma_desc *mdesc;
> +       struct hidma_dev *dmadev = mchan->dmadev;
> +
> +       pm_runtime_get_sync(dmadev->ddev.dev);
> +       seq_printf(s, "paused=%u\n", mchan->paused);
> +       seq_printf(s, "dma_sig=%u\n", mchan->dma_sig);
> +       seq_puts(s, "prepared\n");
> +       list_for_each_entry(mdesc, &mchan->prepared, node)
> +               hidma_ll_chstats(s, mchan->dmadev->lldev, mdesc->tre_ch);
> +
> +       seq_puts(s, "active\n");
> +               list_for_each_entry(mdesc, &mchan->active, node)
> +                       hidma_ll_chstats(s, mchan->dmadev->lldev,
> +                               mdesc->tre_ch);
> +
> +       seq_puts(s, "completed\n");
> +               list_for_each_entry(mdesc, &mchan->completed, node)
> +                       hidma_ll_chstats(s, mchan->dmadev->lldev,
> +                               mdesc->tre_ch);
> +
> +       hidma_ll_devstats(s, mchan->dmadev->lldev);
> +       pm_runtime_mark_last_busy(dmadev->ddev.dev);
> +       pm_runtime_put_autosuspend(dmadev->ddev.dev);
> +       return 0;
> +}
> +
> +/**
> + * hidma_dma_info: display HIDMA device info
> + *
> + * Display the info for the current HIDMA device.
> + */
> +static int hidma_dma_info(struct seq_file *s, void *unused)
> +{
> +       struct hidma_dev *dmadev = s->private;
> +       resource_size_t sz;
> +
> +       seq_printf(s, "nr_descriptors=%d\n", dmadev->nr_descriptors);
> +       seq_printf(s, "dev_trca=%p\n", &dmadev->dev_trca);
> +       seq_printf(s, "dev_trca_phys=%pa\n",
> +               &dmadev->trca_resource->start);
> +       sz = resource_size(dmadev->trca_resource);
> +       seq_printf(s, "dev_trca_size=%pa\n", &sz);
> +       seq_printf(s, "dev_evca=%p\n", &dmadev->dev_evca);
> +       seq_printf(s, "dev_evca_phys=%pa\n",
> +               &dmadev->evca_resource->start);
> +       sz = resource_size(dmadev->evca_resource);
> +       seq_printf(s, "dev_evca_size=%pa\n", &sz);
> +       return 0;
> +}
> +
> +static int hidma_chan_stats_open(struct inode *inode, struct file *file)
> +{
> +       return single_open(file, hidma_chan_stats, inode->i_private);
> +}
> +
> +static int hidma_dma_info_open(struct inode *inode, struct file *file)
> +{
> +       return single_open(file, hidma_dma_info, inode->i_private);
> +}
> +
> +static const struct file_operations hidma_chan_fops = {
> +       .open = hidma_chan_stats_open,
> +       .read = seq_read,
> +       .llseek = seq_lseek,
> +       .release = single_release,
> +};
> +
> +static const struct file_operations hidma_dma_fops = {
> +       .open = hidma_dma_info_open,
> +       .read = seq_read,
> +       .llseek = seq_lseek,
> +       .release = single_release,
> +};
> +
> +void hidma_debug_uninit(struct hidma_dev *dmadev)
> +{
> +       debugfs_remove_recursive(dmadev->debugfs);
> +       debugfs_remove_recursive(dmadev->stats);
> +}
> +
> +int hidma_debug_init(struct hidma_dev *dmadev)
> +{
> +       int rc = 0;
> +       int chidx = 0;
> +       struct list_head *position = NULL;
> +
> +       dmadev->debugfs = debugfs_create_dir(dev_name(dmadev->ddev.dev),
> +                                               NULL);
> +       if (!dmadev->debugfs) {
> +               rc = -ENODEV;
> +               return rc;
> +       }
> +
> +       /* walk through the virtual channel list */
> +       list_for_each(position, &dmadev->ddev.channels) {
> +               struct hidma_chan *chan;
> +
> +               chan = list_entry(position, struct hidma_chan,
> +                               chan.device_node);
> +               sprintf(chan->dbg_name, "chan%d", chidx);
> +               chan->debugfs = debugfs_create_dir(chan->dbg_name,
> +                                               dmadev->debugfs);
> +               if (!chan->debugfs) {
> +                       rc = -ENOMEM;
> +                       goto cleanup;
> +               }
> +               chan->stats = debugfs_create_file("stats", S_IRUGO,
> +                               chan->debugfs, chan,
> +                               &hidma_chan_fops);
> +               if (!chan->stats) {
> +                       rc = -ENOMEM;
> +                       goto cleanup;
> +               }
> +               chidx++;
> +       }
> +
> +       dmadev->stats = debugfs_create_file("stats", S_IRUGO,
> +                       dmadev->debugfs, dmadev,
> +                       &hidma_dma_fops);
> +       if (!dmadev->stats) {
> +               rc = -ENOMEM;
> +               goto cleanup;
> +       }
> +
> +       return 0;
> +cleanup:
> +       hidma_debug_uninit(dmadev);
> +       return rc;
> +}
> diff --git a/drivers/dma/qcom/hidma_ll.c b/drivers/dma/qcom/hidma_ll.c
> new file mode 100644
> index 0000000..f5c0b8b
> --- /dev/null
> +++ b/drivers/dma/qcom/hidma_ll.c
> @@ -0,0 +1,944 @@
> +/*
> + * Qualcomm Technologies HIDMA DMA engine low level code
> + *
> + * Copyright (c) 2015, The Linux Foundation. All rights reserved.
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License version 2 and
> + * only version 2 as published by the Free Software Foundation.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
> + * GNU General Public License for more details.
> + */
> +
> +#include <linux/dmaengine.h>
> +#include <linux/slab.h>
> +#include <linux/interrupt.h>
> +#include <linux/mm.h>
> +#include <linux/highmem.h>
> +#include <linux/dma-mapping.h>
> +#include <linux/delay.h>
> +#include <linux/atomic.h>
> +#include <linux/iopoll.h>
> +#include <linux/kfifo.h>
> +
> +#include "hidma.h"
> +
> +#define EVRE_SIZE                      16 /* each EVRE is 16 bytes */
> +
> +#define TRCA_CTRLSTS_OFFSET            0x0
> +#define TRCA_RING_LOW_OFFSET           0x8
> +#define TRCA_RING_HIGH_OFFSET          0xC
> +#define TRCA_RING_LEN_OFFSET           0x10
> +#define TRCA_READ_PTR_OFFSET           0x18
> +#define TRCA_WRITE_PTR_OFFSET          0x20
> +#define TRCA_DOORBELL_OFFSET           0x400
> +
> +#define EVCA_CTRLSTS_OFFSET            0x0
> +#define EVCA_INTCTRL_OFFSET            0x4
> +#define EVCA_RING_LOW_OFFSET           0x8
> +#define EVCA_RING_HIGH_OFFSET          0xC
> +#define EVCA_RING_LEN_OFFSET           0x10
> +#define EVCA_READ_PTR_OFFSET           0x18
> +#define EVCA_WRITE_PTR_OFFSET          0x20
> +#define EVCA_DOORBELL_OFFSET           0x400
> +
> +#define EVCA_IRQ_STAT_OFFSET           0x100
> +#define EVCA_IRQ_CLR_OFFSET            0x108
> +#define EVCA_IRQ_EN_OFFSET             0x110
> +
> +#define EVRE_CFG_IDX                   0
> +#define EVRE_LEN_IDX                   1
> +#define EVRE_DEST_LOW_IDX              2
> +#define EVRE_DEST_HI_IDX               3
> +
> +#define EVRE_ERRINFO_BIT_POS           24
> +#define EVRE_CODE_BIT_POS              28
> +
> +#define EVRE_ERRINFO_MASK              0xF
> +#define EVRE_CODE_MASK                 0xF
> +
> +#define CH_CONTROL_MASK                0xFF
> +#define CH_STATE_MASK                  0xFF
> +#define CH_STATE_BIT_POS               0x8
> +
> +#define MAKE64(high, low) (((u64)(high) << 32) | (low))
> +
> +#define IRQ_EV_CH_EOB_IRQ_BIT_POS      0
> +#define IRQ_EV_CH_WR_RESP_BIT_POS      1
> +#define IRQ_TR_CH_TRE_RD_RSP_ER_BIT_POS 9
> +#define IRQ_TR_CH_DATA_RD_ER_BIT_POS   10
> +#define IRQ_TR_CH_DATA_WR_ER_BIT_POS   11
> +#define IRQ_TR_CH_INVALID_TRE_BIT_POS  14
> +
> +#define        ENABLE_IRQS (BIT(IRQ_EV_CH_EOB_IRQ_BIT_POS) | \
> +               BIT(IRQ_EV_CH_WR_RESP_BIT_POS) | \
> +               BIT(IRQ_TR_CH_TRE_RD_RSP_ER_BIT_POS) |   \
> +               BIT(IRQ_TR_CH_DATA_RD_ER_BIT_POS) |              \
> +               BIT(IRQ_TR_CH_DATA_WR_ER_BIT_POS) |              \
> +               BIT(IRQ_TR_CH_INVALID_TRE_BIT_POS))
> +
> +enum ch_command {
> +       CH_DISABLE = 0,
> +       CH_ENABLE = 1,
> +       CH_SUSPEND = 2,
> +       CH_RESET = 9,
> +};
> +
> +enum ch_state {
> +       CH_DISABLED = 0,
> +       CH_ENABLED = 1,
> +       CH_RUNNING = 2,
> +       CH_SUSPENDED = 3,
> +       CH_STOPPED = 4,
> +       CH_ERROR = 5,
> +       CH_IN_RESET = 9,
> +};
> +
> +enum tre_type {
> +       TRE_MEMCPY = 3,
> +       TRE_MEMSET = 4,
> +};
> +
> +enum evre_type {
> +       EVRE_DMA_COMPLETE = 0x23,
> +       EVRE_IMM_DATA = 0x24,
> +};
> +
> +enum err_code {
> +       EVRE_STATUS_COMPLETE = 1,
> +       EVRE_STATUS_ERROR = 4,
> +};
> +
> +void hidma_ll_free(struct hidma_lldev *lldev, u32 tre_ch)
> +{
> +       struct hidma_tre *tre;
> +
> +       if (tre_ch >= lldev->nr_tres) {
> +               dev_err(lldev->dev, "invalid TRE number in free:%d", tre_ch);
> +               return;
> +       }
> +
> +       tre = &lldev->trepool[tre_ch];
> +       if (atomic_read(&tre->allocated) != true) {
> +               dev_err(lldev->dev, "trying to free an unused TRE:%d",
> +                       tre_ch);
> +               return;
> +       }
> +
> +       atomic_set(&tre->allocated, 0);
> +       dev_dbg(lldev->dev, "free_dma: allocated:%d tre_ch:%d\n",
> +               atomic_read(&tre->allocated), tre_ch);
> +}
> +
> +int hidma_ll_request(struct hidma_lldev *lldev, u32 dma_sig,
> +                       const char *dev_name,
> +                       void (*callback)(void *data), void *data, u32 *tre_ch)
> +{
> +       u32 i;
> +       struct hidma_tre *tre = NULL;
> +       u32 *tre_local;
> +
> +       if (!tre_ch || !lldev)
> +               return -EINVAL;
> +
> +       /* need to have at least one empty spot in the queue */
> +       for (i = 0; i < lldev->nr_tres - 1; i++) {
> +               if (atomic_add_unless(&lldev->trepool[i].allocated, 1, 1))
> +                       break;
> +       }
> +
> +       if (i == (lldev->nr_tres - 1))
> +               return -ENOMEM;
> +
> +       tre = &lldev->trepool[i];
> +       tre->dma_sig = dma_sig;
> +       tre->dev_name = dev_name;
> +       tre->callback = callback;
> +       tre->data = data;
> +       tre->chidx = i;
> +       tre->status = 0;
> +       tre->queued = 0;
> +       lldev->tx_status_list[i].err_code = 0;
> +       tre->lldev = lldev;
> +       tre_local = &tre->tre_local[0];
> +       tre_local[TRE_CFG_IDX] = TRE_MEMCPY;
> +       tre_local[TRE_CFG_IDX] |= ((lldev->evridx & 0xFF) << 8);
> +       tre_local[TRE_CFG_IDX] |= BIT(16);      /* set IEOB */
> +       *tre_ch = i;
> +       if (callback)
> +               callback(data);
> +       return 0;
> +}
> +
> +/*
> + * Multiple TREs may be queued and waiting in the
> + * pending queue.
> + */
> +static void hidma_ll_tre_complete(unsigned long arg)
> +{
> +       struct hidma_lldev *lldev = (struct hidma_lldev *)arg;
> +       struct hidma_tre *tre;
> +
> +       while (kfifo_out(&lldev->handoff_fifo, &tre, 1)) {
> +               /* call the user if it has been read by the hardware*/
> +               if (tre->callback)
> +                       tre->callback(tre->data);
> +       }
> +}
> +
> +/*
> + * Called to handle the interrupt for the channel.
> + * Return a positive number if TRE or EVRE were consumed on this run.
> + * Return a positive number if there are pending TREs or EVREs.
> + * Return 0 if there is nothing to consume or no pending TREs/EVREs found.
> + */
> +static int hidma_handle_tre_completion(struct hidma_lldev *lldev)
> +{
> +       struct hidma_tre *tre;
> +       u32 evre_write_off;
> +       u32 evre_ring_size = lldev->evre_ring_size;
> +       u32 tre_ring_size = lldev->tre_ring_size;
> +       u32 num_completed = 0, tre_iterator, evre_iterator;
> +       unsigned long flags;
> +
> +       evre_write_off = readl_relaxed(lldev->evca + EVCA_WRITE_PTR_OFFSET);
> +       tre_iterator = lldev->tre_processed_off;
> +       evre_iterator = lldev->evre_processed_off;
> +
> +       if ((evre_write_off > evre_ring_size) ||
> +               ((evre_write_off % EVRE_SIZE) != 0)) {
> +               dev_err(lldev->dev, "HW reports invalid EVRE write offset\n");
> +               return 0;
> +       }
> +
> +       /*
> +        * By the time control reaches here the number of EVREs and TREs
> +        * may not match. Only consume the ones that hardware told us.
> +        */
> +       while ((evre_iterator != evre_write_off)) {
> +               u32 *current_evre = lldev->evre_ring + evre_iterator;
> +               u32 cfg;
> +               u8 err_info;
> +
> +               spin_lock_irqsave(&lldev->lock, flags);
> +               tre = lldev->pending_tre_list[tre_iterator / TRE_SIZE];
> +               if (!tre) {
> +                       spin_unlock_irqrestore(&lldev->lock, flags);
> +                       dev_warn(lldev->dev,
> +                               "tre_index [%d] and tre out of sync\n",
> +                               tre_iterator / TRE_SIZE);
> +                       tre_iterator += TRE_SIZE;
> +                       if (tre_iterator >= tre_ring_size)
> +                               tre_iterator -= tre_ring_size;
> +                       evre_iterator += EVRE_SIZE;
> +                       if (evre_iterator >= evre_ring_size)
> +                               evre_iterator -= evre_ring_size;
> +
> +                       continue;
> +               }
> +               lldev->pending_tre_list[tre->tre_index] = NULL;
> +
> +               /*
> +                * Keep track of pending TREs that SW is expecting to receive
> +                * from HW. We got one now. Decrement our counter.
> +                */
> +               lldev->pending_tre_count--;
> +               if (lldev->pending_tre_count < 0) {
> +                       dev_warn(lldev->dev,
> +                               "tre count mismatch on completion");
> +                       lldev->pending_tre_count = 0;
> +               }
> +
> +               spin_unlock_irqrestore(&lldev->lock, flags);
> +
> +               cfg = current_evre[EVRE_CFG_IDX];
> +               err_info = (cfg >> EVRE_ERRINFO_BIT_POS);
> +               err_info = err_info & EVRE_ERRINFO_MASK;
> +               lldev->tx_status_list[tre->chidx].err_info = err_info;
> +               lldev->tx_status_list[tre->chidx].err_code =
> +                       (cfg >> EVRE_CODE_BIT_POS) & EVRE_CODE_MASK;
> +               tre->queued = 0;
> +
> +               kfifo_put(&lldev->handoff_fifo, tre);
> +               tasklet_schedule(&lldev->task);
> +
> +               tre_iterator += TRE_SIZE;
> +               if (tre_iterator >= tre_ring_size)
> +                       tre_iterator -= tre_ring_size;
> +               evre_iterator += EVRE_SIZE;
> +               if (evre_iterator >= evre_ring_size)
> +                       evre_iterator -= evre_ring_size;
> +
> +               /*
> +                * Read the new event descriptor written by the HW.
> +                * As we are processing the delivered events, other events
> +                * get queued to the SW for processing.
> +                */
> +               evre_write_off =
> +                       readl_relaxed(lldev->evca + EVCA_WRITE_PTR_OFFSET);
> +               num_completed++;
> +       }
> +
> +       if (num_completed) {
> +               u32 evre_read_off = (lldev->evre_processed_off +
> +                               EVRE_SIZE * num_completed);
> +               u32 tre_read_off = (lldev->tre_processed_off +
> +                               TRE_SIZE * num_completed);
> +
> +               evre_read_off = evre_read_off % evre_ring_size;
> +               tre_read_off = tre_read_off % tre_ring_size;
> +
> +               writel(evre_read_off, lldev->evca + EVCA_DOORBELL_OFFSET);
> +
> +               /* record the last processed tre offset */
> +               lldev->tre_processed_off = tre_read_off;
> +               lldev->evre_processed_off = evre_read_off;
> +       }
> +
> +       return num_completed;
> +}
> +
> +void hidma_cleanup_pending_tre(struct hidma_lldev *lldev, u8 err_info,
> +                               u8 err_code)
> +{
> +       u32 tre_iterator;
> +       struct hidma_tre *tre;
> +       u32 tre_ring_size = lldev->tre_ring_size;
> +       int num_completed = 0;
> +       u32 tre_read_off;
> +       unsigned long flags;
> +
> +       tre_iterator = lldev->tre_processed_off;
> +       while (lldev->pending_tre_count) {
> +               int tre_index = tre_iterator / TRE_SIZE;
> +
> +               spin_lock_irqsave(&lldev->lock, flags);
> +               tre = lldev->pending_tre_list[tre_index];
> +               if (!tre) {
> +                       spin_unlock_irqrestore(&lldev->lock, flags);
> +                       tre_iterator += TRE_SIZE;
> +                       if (tre_iterator >= tre_ring_size)
> +                               tre_iterator -= tre_ring_size;
> +                       continue;
> +               }
> +               lldev->pending_tre_list[tre_index] = NULL;
> +               lldev->pending_tre_count--;
> +               if (lldev->pending_tre_count < 0) {
> +                       dev_warn(lldev->dev,
> +                               "tre count mismatch on completion");
> +                       lldev->pending_tre_count = 0;
> +               }
> +               spin_unlock_irqrestore(&lldev->lock, flags);
> +
> +               lldev->tx_status_list[tre->chidx].err_info = err_info;
> +               lldev->tx_status_list[tre->chidx].err_code = err_code;
> +               tre->queued = 0;
> +
> +               kfifo_put(&lldev->handoff_fifo, tre);
> +               tasklet_schedule(&lldev->task);
> +
> +               tre_iterator += TRE_SIZE;
> +               if (tre_iterator >= tre_ring_size)
> +                       tre_iterator -= tre_ring_size;
> +
> +               num_completed++;
> +       }
> +       tre_read_off = (lldev->tre_processed_off +
> +                       TRE_SIZE * num_completed);
> +
> +       tre_read_off = tre_read_off % tre_ring_size;
> +
> +       /* record the last processed tre offset */
> +       lldev->tre_processed_off = tre_read_off;
> +}
> +
> +static int hidma_ll_reset(struct hidma_lldev *lldev)
> +{
> +       u32 val;
> +       int ret;
> +
> +       val = readl(lldev->trca + TRCA_CTRLSTS_OFFSET);
> +       val = val & ~(CH_CONTROL_MASK << 16);
> +       val = val | (CH_RESET << 16);
> +       writel(val, lldev->trca + TRCA_CTRLSTS_OFFSET);
> +
> +       /*
> +        * Delay 10ms after reset to allow DMA logic to quiesce.
> +        * Do a polled read up to 1ms and 10ms maximum.
> +        */
> +       ret = readl_poll_timeout(lldev->trca + TRCA_CTRLSTS_OFFSET, val,
> +               (((val >> CH_STATE_BIT_POS) & CH_STATE_MASK) == CH_DISABLED),
> +               1000, 10000);
> +       if (ret) {
> +               dev_err(lldev->dev,
> +                       "transfer channel did not reset\n");
> +               return ret;
> +       }
> +
> +       val = readl(lldev->evca + EVCA_CTRLSTS_OFFSET);
> +       val = val & ~(CH_CONTROL_MASK << 16);
> +       val = val | (CH_RESET << 16);
> +       writel(val, lldev->evca + EVCA_CTRLSTS_OFFSET);
> +
> +       /*
> +        * Delay 10ms after reset to allow DMA logic to quiesce.
> +        * Do a polled read up to 1ms and 10ms maximum.
> +        */
> +       ret = readl_poll_timeout(lldev->evca + EVCA_CTRLSTS_OFFSET, val,
> +               (((val >> CH_STATE_BIT_POS) & CH_STATE_MASK) == CH_DISABLED),
> +               1000, 10000);
> +       if (ret)
> +               return ret;
> +
> +       lldev->trch_state = CH_DISABLED;
> +       lldev->evch_state = CH_DISABLED;
> +       return 0;
> +}
> +
> +static void hidma_ll_enable_irq(struct hidma_lldev *lldev, u32 irq_bits)
> +{
> +       writel(irq_bits, lldev->evca + EVCA_IRQ_EN_OFFSET);
> +       dev_dbg(lldev->dev, "enableirq\n");
> +}
> +
> +/*
> + * The interrupt handler for HIDMA will try to consume as many pending
> + * EVRE from the event queue as possible. Each EVRE has an associated
> + * TRE that holds the user interface parameters. EVRE reports the
> + * result of the transaction. Hardware guarantees ordering between EVREs
> + * and TREs. We use last processed offset to figure out which TRE is
> + * associated with which EVRE. If two TREs are consumed by HW, the EVREs
> + * are in order in the event ring.
> + *
> + * This handler will do a one pass for consuming EVREs. Other EVREs may
> + * be delivered while we are working. It will try to consume incoming
> + * EVREs one more time and return.
> + *
> + * For unprocessed EVREs, hardware will trigger another interrupt until
> + * all the interrupt bits are cleared.
> + *
> + * Hardware guarantees that by the time interrupt is observed, all data
> + * transactions in flight are delivered to their respective places and
> + * are visible to the CPU.
> + *
> + * On demand paging for IOMMU is only supported for PCIe via PRI
> + * (Page Request Interface) not for HIDMA. All other hardware instances
> + * including HIDMA work on pinned DMA addresses.
> + *
> + * HIDMA is not aware of IOMMU presence since it follows the DMA API. All
> + * IOMMU latency will be built into the data movement time. By the time
> + * interrupt happens, IOMMU lookups + data movement has already taken place.
> + *
> + * While the first read in a typical PCI endpoint ISR flushes all outstanding
> + * requests traditionally to the destination, this concept does not apply
> + * here for this HW.
> + */
> +static void hidma_ll_int_handler_internal(struct hidma_lldev *lldev)
> +{
> +       u32 status;
> +       u32 enable;
> +       u32 cause;
> +       int repeat = 2;
> +       unsigned long timeout;
> +
> +       /*
> +        * Fine tuned for this HW...
> +        *
> +        * This ISR has been designed for this particular hardware. Relaxed read
> +        * and write accessors are used for performance reasons due to interrupt
> +        * delivery guarantees. Do not copy this code blindly and expect
> +        * that to work.
> +        */
> +       status = readl_relaxed(lldev->evca + EVCA_IRQ_STAT_OFFSET);
> +       enable = readl_relaxed(lldev->evca + EVCA_IRQ_EN_OFFSET);
> +       cause = status & enable;
> +
> +       if ((cause & (BIT(IRQ_TR_CH_INVALID_TRE_BIT_POS))) ||
> +                       (cause & BIT(IRQ_TR_CH_TRE_RD_RSP_ER_BIT_POS)) ||
> +                       (cause & BIT(IRQ_EV_CH_WR_RESP_BIT_POS)) ||
> +                       (cause & BIT(IRQ_TR_CH_DATA_RD_ER_BIT_POS)) ||
> +                       (cause & BIT(IRQ_TR_CH_DATA_WR_ER_BIT_POS))) {
> +               u8 err_code = EVRE_STATUS_ERROR;
> +               u8 err_info = 0xFF;
> +
> +               /* Clear out pending interrupts */
> +               writel(cause, lldev->evca + EVCA_IRQ_CLR_OFFSET);
> +
> +               dev_err(lldev->dev,
> +                       "error 0x%x, resetting...\n", cause);
> +
> +               hidma_cleanup_pending_tre(lldev, err_info, err_code);
> +
> +               /* reset the channel for recovery */
> +               if (hidma_ll_setup(lldev)) {
> +                       dev_err(lldev->dev,
> +                               "channel reinitialize failed after error\n");
> +                       return;
> +               }
> +               hidma_ll_enable_irq(lldev, ENABLE_IRQS);
> +               return;
> +       }
> +
> +       /*
> +        * Try to consume as many EVREs as possible.
> +        * skip this loop if the interrupt is spurious.
> +        */
> +       while (cause && repeat) {
> +               unsigned long start = jiffies;
> +
> +               /* This timeout should be sufficent for core to finish */
> +               timeout = start + msecs_to_jiffies(500);
> +
> +               while (lldev->pending_tre_count) {
> +                       hidma_handle_tre_completion(lldev);
> +                       if (time_is_before_jiffies(timeout)) {
> +                               dev_warn(lldev->dev,
> +                                       "ISR timeout %lx-%lx from %lx [%d]\n",
> +                                       jiffies, timeout, start,
> +                                       lldev->pending_tre_count);
> +                               break;
> +                       }
> +               }
> +
> +               /* We consumed TREs or there are pending TREs or EVREs. */
> +               writel_relaxed(cause, lldev->evca + EVCA_IRQ_CLR_OFFSET);
> +
> +               /*
> +                * Another interrupt might have arrived while we are
> +                * processing this one. Read the new cause.
> +                */
> +               status = readl_relaxed(lldev->evca + EVCA_IRQ_STAT_OFFSET);
> +               enable = readl_relaxed(lldev->evca + EVCA_IRQ_EN_OFFSET);
> +               cause = status & enable;
> +
> +               repeat--;
> +       }
> +}
> +
> +
> +static int hidma_ll_enable(struct hidma_lldev *lldev)
> +{
> +       u32 val;
> +       int ret;
> +
> +       val = readl(lldev->evca + EVCA_CTRLSTS_OFFSET);
> +       val &= ~(CH_CONTROL_MASK << 16);
> +       val |= (CH_ENABLE << 16);
> +       writel(val, lldev->evca + EVCA_CTRLSTS_OFFSET);
> +
> +       ret = readl_poll_timeout(lldev->evca + EVCA_CTRLSTS_OFFSET, val,
> +               ((((val >> CH_STATE_BIT_POS) & CH_STATE_MASK) == CH_ENABLED) ||
> +               (((val >> CH_STATE_BIT_POS) & CH_STATE_MASK) == CH_RUNNING)),
> +               1000, 10000);
> +       if (ret) {
> +               dev_err(lldev->dev,
> +                       "event channel did not get enabled\n");
> +               return ret;
> +       }
> +
> +       val = readl(lldev->trca + TRCA_CTRLSTS_OFFSET);
> +       val = val & ~(CH_CONTROL_MASK << 16);
> +       val = val | (CH_ENABLE << 16);
> +       writel(val, lldev->trca + TRCA_CTRLSTS_OFFSET);
> +
> +       ret = readl_poll_timeout(lldev->trca + TRCA_CTRLSTS_OFFSET, val,
> +               ((((val >> CH_STATE_BIT_POS) & CH_STATE_MASK) == CH_ENABLED) ||
> +               (((val >> CH_STATE_BIT_POS) & CH_STATE_MASK) == CH_RUNNING)),
> +               1000, 10000);
> +       if (ret) {
> +               dev_err(lldev->dev,
> +                       "transfer channel did not get enabled\n");
> +               return ret;
> +       }
> +
> +       lldev->trch_state = CH_ENABLED;
> +       lldev->evch_state = CH_ENABLED;
> +
> +       return 0;
> +}
> +
> +int hidma_ll_resume(struct hidma_lldev *lldev)
> +{
> +       return hidma_ll_enable(lldev);
> +}
> +
> +static int hidma_ll_hw_start(struct hidma_lldev *lldev)
> +{
> +       int rc = 0;
> +       unsigned long irqflags;
> +
> +       spin_lock_irqsave(&lldev->lock, irqflags);
> +       writel(lldev->tre_write_offset, lldev->trca + TRCA_DOORBELL_OFFSET);
> +       spin_unlock_irqrestore(&lldev->lock, irqflags);
> +
> +       return rc;
> +}
> +
> +bool hidma_ll_isenabled(struct hidma_lldev *lldev)
> +{
> +       u32 val;
> +
> +       val = readl(lldev->trca + TRCA_CTRLSTS_OFFSET);
> +       lldev->trch_state = (val >> CH_STATE_BIT_POS) & CH_STATE_MASK;
> +       val = readl(lldev->evca + EVCA_CTRLSTS_OFFSET);
> +       lldev->evch_state = (val >> CH_STATE_BIT_POS) & CH_STATE_MASK;
> +
> +       /* both channels have to be enabled before calling this function*/
> +       if (((lldev->trch_state == CH_ENABLED) ||
> +               (lldev->trch_state == CH_RUNNING)) &&
> +               ((lldev->evch_state == CH_ENABLED) ||
> +                       (lldev->evch_state == CH_RUNNING)))
> +               return true;
> +
> +       dev_dbg(lldev->dev, "channels are not enabled or are in error state");
> +       return false;
> +}
> +
> +int hidma_ll_queue_request(struct hidma_lldev *lldev, u32 tre_ch)
> +{
> +       struct hidma_tre *tre;
> +       int rc = 0;
> +       unsigned long flags;
> +
> +       tre = &lldev->trepool[tre_ch];
> +
> +       /* copy the TRE into its location in the TRE ring */
> +       spin_lock_irqsave(&lldev->lock, flags);
> +       tre->tre_index = lldev->tre_write_offset / TRE_SIZE;
> +       lldev->pending_tre_list[tre->tre_index] = tre;
> +       memcpy(lldev->tre_ring + lldev->tre_write_offset, &tre->tre_local[0],
> +               TRE_SIZE);
> +       lldev->tx_status_list[tre->chidx].err_code = 0;
> +       lldev->tx_status_list[tre->chidx].err_info = 0;
> +       tre->queued = 1;
> +       lldev->pending_tre_count++;
> +       lldev->tre_write_offset = (lldev->tre_write_offset + TRE_SIZE)
> +                               % lldev->tre_ring_size;
> +       spin_unlock_irqrestore(&lldev->lock, flags);
> +       return rc;
> +}
> +
> +int hidma_ll_start(struct hidma_lldev *lldev)
> +{
> +       return hidma_ll_hw_start(lldev);
> +}
> +
> +/*
> + * Note that even though we stop this channel
> + * if there is a pending transaction in flight
> + * it will complete and follow the callback.
> + * This request will prevent further requests
> + * to be made.
> + */
> +int hidma_ll_pause(struct hidma_lldev *lldev)
> +{
> +       u32 val;
> +       int ret;
> +
> +       val = readl(lldev->evca + EVCA_CTRLSTS_OFFSET);
> +       lldev->evch_state = (val >> CH_STATE_BIT_POS) & CH_STATE_MASK;
> +       val = readl(lldev->trca + TRCA_CTRLSTS_OFFSET);
> +       lldev->trch_state = (val >> CH_STATE_BIT_POS) & CH_STATE_MASK;
> +
> +       /* already suspended by this OS */
> +       if ((lldev->trch_state == CH_SUSPENDED) ||
> +               (lldev->evch_state == CH_SUSPENDED))
> +               return 0;
> +
> +       /* already stopped by the manager */
> +       if ((lldev->trch_state == CH_STOPPED) ||
> +               (lldev->evch_state == CH_STOPPED))
> +               return 0;
> +
> +       val = readl(lldev->trca + TRCA_CTRLSTS_OFFSET);
> +       val = val & ~(CH_CONTROL_MASK << 16);
> +       val = val | (CH_SUSPEND << 16);
> +       writel(val, lldev->trca + TRCA_CTRLSTS_OFFSET);
> +
> +       /*
> +        * Start the wait right after the suspend is confirmed.
> +        * Do a polled read up to 1ms and 10ms maximum.
> +        */
> +       ret = readl_poll_timeout(lldev->trca + TRCA_CTRLSTS_OFFSET, val,
> +               (((val >> CH_STATE_BIT_POS) & CH_STATE_MASK) == CH_SUSPENDED),
> +               1000, 10000);
> +       if (ret)
> +               return ret;
> +
> +       val = readl(lldev->evca + EVCA_CTRLSTS_OFFSET);
> +       val = val & ~(CH_CONTROL_MASK << 16);
> +       val = val | (CH_SUSPEND << 16);
> +       writel(val, lldev->evca + EVCA_CTRLSTS_OFFSET);
> +
> +       /*
> +        * Start the wait right after the suspend is confirmed
> +        * Delay up to 10ms after reset to allow DMA logic to quiesce.
> +        */
> +       ret = readl_poll_timeout(lldev->evca + EVCA_CTRLSTS_OFFSET, val,
> +               (((val >> CH_STATE_BIT_POS) & CH_STATE_MASK) == CH_SUSPENDED),
> +               1000, 10000);
> +       if (ret)
> +               return ret;
> +
> +       lldev->trch_state = CH_SUSPENDED;
> +       lldev->evch_state = CH_SUSPENDED;
> +       dev_dbg(lldev->dev, "stop\n");
> +
> +       return 0;
> +}
> +
> +void hidma_ll_set_transfer_params(struct hidma_lldev *lldev, u32 tre_ch,
> +       dma_addr_t src, dma_addr_t dest, u32 len, u32 flags)
> +{
> +       struct hidma_tre *tre;
> +       u32 *tre_local;
> +
> +       if (tre_ch >= lldev->nr_tres) {
> +               dev_err(lldev->dev,
> +                       "invalid TRE number in transfer params:%d", tre_ch);
> +               return;
> +       }
> +
> +       tre = &lldev->trepool[tre_ch];
> +       if (atomic_read(&tre->allocated) != true) {
> +               dev_err(lldev->dev,
> +                       "trying to set params on an unused TRE:%d", tre_ch);
> +               return;
> +       }
> +
> +       tre_local = &tre->tre_local[0];
> +       tre_local[TRE_LEN_IDX] = len;
> +       tre_local[TRE_SRC_LOW_IDX] = lower_32_bits(src);
> +       tre_local[TRE_SRC_HI_IDX] = upper_32_bits(src);
> +       tre_local[TRE_DEST_LOW_IDX] = lower_32_bits(dest);
> +       tre_local[TRE_DEST_HI_IDX] = upper_32_bits(dest);
> +       tre->int_flags = flags;
> +
> +       dev_dbg(lldev->dev, "transferparams: tre_ch:%d %pap->%pap len:%u\n",
> +               tre_ch, &src, &dest, len);
> +}
> +
> +/*
> + * Called during initialization and after an error condition
> + * to restore hardware state.
> + */
> +int hidma_ll_setup(struct hidma_lldev *lldev)
> +{
> +       int rc;
> +       u64 addr;
> +       u32 val;
> +       u32 nr_tres = lldev->nr_tres;
> +
> +       lldev->pending_tre_count = 0;
> +       lldev->tre_processed_off = 0;
> +       lldev->evre_processed_off = 0;
> +       lldev->tre_write_offset = 0;
> +
> +       /* disable interrupts */
> +       hidma_ll_enable_irq(lldev, 0);
> +
> +       /* clear all pending interrupts */
> +       val = readl(lldev->evca + EVCA_IRQ_STAT_OFFSET);
> +       writel(val, lldev->evca + EVCA_IRQ_CLR_OFFSET);
> +
> +       rc = hidma_ll_reset(lldev);
> +       if (rc)
> +               return rc;
> +
> +       /*
> +        * Clear all pending interrupts again.
> +        * Otherwise, we observe reset complete interrupts.
> +        */
> +       val = readl(lldev->evca + EVCA_IRQ_STAT_OFFSET);
> +       writel(val, lldev->evca + EVCA_IRQ_CLR_OFFSET);
> +
> +       /* disable interrupts again after reset */
> +       hidma_ll_enable_irq(lldev, 0);
> +
> +       addr = lldev->tre_ring_handle;
> +       writel(lower_32_bits(addr), lldev->trca + TRCA_RING_LOW_OFFSET);
> +       writel(upper_32_bits(addr), lldev->trca + TRCA_RING_HIGH_OFFSET);
> +       writel(lldev->tre_ring_size, lldev->trca + TRCA_RING_LEN_OFFSET);
> +
> +       addr = lldev->evre_ring_handle;
> +       writel(lower_32_bits(addr), lldev->evca + EVCA_RING_LOW_OFFSET);
> +       writel(upper_32_bits(addr), lldev->evca + EVCA_RING_HIGH_OFFSET);
> +       writel(EVRE_SIZE * nr_tres, lldev->evca + EVCA_RING_LEN_OFFSET);
> +
> +       /* support IRQ only for now */
> +       val = readl(lldev->evca + EVCA_INTCTRL_OFFSET);
> +       val = val & ~(0xF);
> +       val = val | 0x1;
> +       writel(val, lldev->evca + EVCA_INTCTRL_OFFSET);
> +
> +       /* clear all pending interrupts and enable them*/
> +       writel(ENABLE_IRQS, lldev->evca + EVCA_IRQ_CLR_OFFSET);
> +       hidma_ll_enable_irq(lldev, ENABLE_IRQS);
> +
> +       rc = hidma_ll_enable(lldev);
> +       if (rc)
> +               return rc;
> +
> +       return rc;
> +}
> +
> +struct hidma_lldev *hidma_ll_init(struct device *dev, u32 nr_tres,
> +                       void __iomem *trca, void __iomem *evca,
> +                       u8 evridx)
> +{
> +       u32 required_bytes;
> +       struct hidma_lldev *lldev;
> +       int rc;
> +
> +       if (!trca || !evca || !dev || !nr_tres)
> +               return NULL;
> +
> +       /* need at least four TREs */
> +       if (nr_tres < 4)
> +               return NULL;
> +
> +       /* need an extra space */
> +       nr_tres += 1;
> +
> +       lldev = devm_kzalloc(dev, sizeof(struct hidma_lldev), GFP_KERNEL);
> +       if (!lldev)
> +               return NULL;
> +
> +       lldev->evca = evca;
> +       lldev->trca = trca;
> +       lldev->dev = dev;
> +       required_bytes = sizeof(struct hidma_tre) * nr_tres;
> +       lldev->trepool = devm_kzalloc(lldev->dev, required_bytes, GFP_KERNEL);
> +       if (!lldev->trepool)
> +               return NULL;
> +
> +       required_bytes = sizeof(lldev->pending_tre_list[0]) * nr_tres;
> +       lldev->pending_tre_list = devm_kzalloc(dev, required_bytes,
> +                                       GFP_KERNEL);
> +       if (!lldev->pending_tre_list)
> +               return NULL;
> +
> +       required_bytes = sizeof(lldev->tx_status_list[0]) * nr_tres;
> +       lldev->tx_status_list = devm_kzalloc(dev, required_bytes, GFP_KERNEL);
> +       if (!lldev->tx_status_list)
> +               return NULL;
> +
> +       lldev->tre_ring = dmam_alloc_coherent(dev, (TRE_SIZE + 1) * nr_tres,
> +                                       &lldev->tre_ring_handle, GFP_KERNEL);
> +       if (!lldev->tre_ring)
> +               return NULL;
> +
> +       memset(lldev->tre_ring, 0, (TRE_SIZE + 1) * nr_tres);
> +       lldev->tre_ring_size = TRE_SIZE * nr_tres;
> +       lldev->nr_tres = nr_tres;
> +
> +       /* the TRE ring has to be TRE_SIZE aligned */
> +       if (!IS_ALIGNED(lldev->tre_ring_handle, TRE_SIZE)) {
> +               u8  tre_ring_shift;
> +
> +               tre_ring_shift = lldev->tre_ring_handle % TRE_SIZE;
> +               tre_ring_shift = TRE_SIZE - tre_ring_shift;
> +               lldev->tre_ring_handle += tre_ring_shift;
> +               lldev->tre_ring += tre_ring_shift;
> +       }
> +
> +       lldev->evre_ring = dmam_alloc_coherent(dev, (EVRE_SIZE + 1) * nr_tres,
> +                                       &lldev->evre_ring_handle, GFP_KERNEL);
> +       if (!lldev->evre_ring)
> +               return NULL;
> +
> +       memset(lldev->evre_ring, 0, (EVRE_SIZE + 1) * nr_tres);
> +       lldev->evre_ring_size = EVRE_SIZE * nr_tres;
> +
> +       /* the EVRE ring has to be EVRE_SIZE aligned */
> +       if (!IS_ALIGNED(lldev->evre_ring_handle, EVRE_SIZE)) {
> +               u8  evre_ring_shift;
> +
> +               evre_ring_shift = lldev->evre_ring_handle % EVRE_SIZE;
> +               evre_ring_shift = EVRE_SIZE - evre_ring_shift;
> +               lldev->evre_ring_handle += evre_ring_shift;
> +               lldev->evre_ring += evre_ring_shift;
> +       }
> +       lldev->nr_tres = nr_tres;
> +       lldev->evridx = evridx;
> +
> +       rc = kfifo_alloc(&lldev->handoff_fifo,
> +               nr_tres * sizeof(struct hidma_tre *), GFP_KERNEL);
> +       if (rc)
> +               return NULL;
> +
> +       rc = hidma_ll_setup(lldev);
> +       if (rc)
> +               return NULL;
> +
> +       spin_lock_init(&lldev->lock);
> +       tasklet_init(&lldev->task, hidma_ll_tre_complete,
> +                       (unsigned long)lldev);
> +       lldev->initialized = 1;
> +       hidma_ll_enable_irq(lldev, ENABLE_IRQS);
> +       return lldev;
> +}
> +
> +int hidma_ll_uninit(struct hidma_lldev *lldev)
> +{
> +       int rc = 0;
> +       u32 val;
> +
> +       if (!lldev)
> +               return -ENODEV;
> +
> +       if (lldev->initialized) {
> +               u32 required_bytes;
> +
> +               lldev->initialized = 0;
> +
> +               required_bytes = sizeof(struct hidma_tre) * lldev->nr_tres;
> +               tasklet_kill(&lldev->task);
> +               memset(lldev->trepool, 0, required_bytes);
> +               lldev->trepool = NULL;
> +               lldev->pending_tre_count = 0;
> +               lldev->tre_write_offset = 0;
> +
> +               rc = hidma_ll_reset(lldev);
> +
> +               /*
> +                * Clear all pending interrupts again.
> +                * Otherwise, we observe reset complete interrupts.
> +                */
> +               val = readl(lldev->evca + EVCA_IRQ_STAT_OFFSET);
> +               writel(val, lldev->evca + EVCA_IRQ_CLR_OFFSET);
> +               hidma_ll_enable_irq(lldev, 0);
> +       }
> +       return rc;
> +}
> +
> +irqreturn_t hidma_ll_inthandler(int chirq, void *arg)
> +{
> +       struct hidma_lldev *lldev = arg;
> +
> +       hidma_ll_int_handler_internal(lldev);
> +       return IRQ_HANDLED;
> +}
> +
> +enum dma_status hidma_ll_status(struct hidma_lldev *lldev, u32 tre_ch)
> +{
> +       enum dma_status ret = DMA_ERROR;
> +       unsigned long flags;
> +       u8 err_code;
> +
> +       spin_lock_irqsave(&lldev->lock, flags);
> +       err_code = lldev->tx_status_list[tre_ch].err_code;
> +
> +       if (err_code & EVRE_STATUS_COMPLETE)
> +               ret = DMA_COMPLETE;
> +       else if (err_code & EVRE_STATUS_ERROR)
> +               ret = DMA_ERROR;
> +       else
> +               ret = DMA_IN_PROGRESS;
> +       spin_unlock_irqrestore(&lldev->lock, flags);
> +
> +       return ret;
> +}
> --
> Qualcomm Technologies, Inc. on behalf of Qualcomm Innovation Center, Inc.
> Qualcomm Innovation Center, Inc. is a member of Code Aurora Forum, a Linux Foundation Collaborative Project
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/



-- 
With Best Regards,
Andy Shevchenko
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/