--- /dev/null
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * NVIDIA Tegra Video decoder driver
+ *
+ * Copyright (C) 2016-2019 GRATE-DRIVER project
+ */
+
+#include <linux/dma-buf.h>
+#include <linux/iova.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/workqueue.h>
+
+#include "vde.h"
+
+struct tegra_vde_cache_entry {
+ enum dma_data_direction dma_dir;
+ struct dma_buf_attachment *a;
+ struct delayed_work dwork;
+ struct tegra_vde *vde;
+ struct list_head list;
+ struct sg_table *sgt;
+ struct iova *iova;
+ unsigned int refcnt;
+};
+
+static void tegra_vde_release_entry(struct tegra_vde_cache_entry *entry)
+{
+ struct dma_buf *dmabuf = entry->a->dmabuf;
+
+ WARN_ON_ONCE(entry->refcnt);
+
+ if (entry->vde->domain)
+ tegra_vde_iommu_unmap(entry->vde, entry->iova);
+
+ dma_buf_unmap_attachment(entry->a, entry->sgt, entry->dma_dir);
+ dma_buf_detach(dmabuf, entry->a);
+ dma_buf_put(dmabuf);
+
+ list_del(&entry->list);
+ kfree(entry);
+}
+
+static void tegra_vde_delayed_unmap(struct work_struct *work)
+{
+ struct tegra_vde_cache_entry *entry;
+ struct tegra_vde *vde;
+
+ entry = container_of(work, struct tegra_vde_cache_entry,
+ dwork.work);
+ vde = entry->vde;
+
+ mutex_lock(&vde->map_lock);
+ tegra_vde_release_entry(entry);
+ mutex_unlock(&vde->map_lock);
+}
+
+int tegra_vde_dmabuf_cache_map(struct tegra_vde *vde,
+ struct dma_buf *dmabuf,
+ enum dma_data_direction dma_dir,
+ struct dma_buf_attachment **ap,
+ dma_addr_t *addrp)
+{
+ struct device *dev = vde->miscdev.parent;
+ struct dma_buf_attachment *attachment;
+ struct tegra_vde_cache_entry *entry;
+ struct sg_table *sgt;
+ struct iova *iova;
+ int err;
+
+ mutex_lock(&vde->map_lock);
+
+ list_for_each_entry(entry, &vde->map_list, list) {
+ if (entry->a->dmabuf != dmabuf)
+ continue;
+
+ if (!cancel_delayed_work(&entry->dwork))
+ continue;
+
+ if (entry->dma_dir != dma_dir)
+ entry->dma_dir = DMA_BIDIRECTIONAL;
+
+ dma_buf_put(dmabuf);
+
+ if (vde->domain)
+ *addrp = iova_dma_addr(&vde->iova, entry->iova);
+ else
+ *addrp = sg_dma_address(entry->sgt->sgl);
+
+ goto ref;
+ }
+
+ attachment = dma_buf_attach(dmabuf, dev);
+ if (IS_ERR(attachment)) {
+ dev_err(dev, "Failed to attach dmabuf\n");
+ err = PTR_ERR(attachment);
+ goto err_unlock;
+ }
+
+ sgt = dma_buf_map_attachment(attachment, dma_dir);
+ if (IS_ERR(sgt)) {
+ dev_err(dev, "Failed to get dmabufs sg_table\n");
+ err = PTR_ERR(sgt);
+ goto err_detach;
+ }
+
+ if (!vde->domain && sgt->nents > 1) {
+ dev_err(dev, "Sparse DMA region is unsupported, please enable IOMMU\n");
+ err = -EINVAL;
+ goto err_unmap;
+ }
+
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry) {
+ err = -ENOMEM;
+ goto err_unmap;
+ }
+
+ if (vde->domain) {
+ err = tegra_vde_iommu_map(vde, sgt, &iova, dmabuf->size);
+ if (err)
+ goto err_free;
+
+ *addrp = iova_dma_addr(&vde->iova, iova);
+ } else {
+ *addrp = sg_dma_address(sgt->sgl);
+ iova = NULL;
+ }
+
+ INIT_DELAYED_WORK(&entry->dwork, tegra_vde_delayed_unmap);
+ list_add(&entry->list, &vde->map_list);
+
+ entry->dma_dir = dma_dir;
+ entry->iova = iova;
+ entry->vde = vde;
+ entry->sgt = sgt;
+ entry->a = attachment;
+ref:
+ entry->refcnt++;
+
+ *ap = entry->a;
+
+ mutex_unlock(&vde->map_lock);
+
+ return 0;
+
+err_free:
+ kfree(entry);
+err_unmap:
+ dma_buf_unmap_attachment(attachment, sgt, dma_dir);
+err_detach:
+ dma_buf_detach(dmabuf, attachment);
+err_unlock:
+ mutex_unlock(&vde->map_lock);
+
+ return err;
+}
+
+void tegra_vde_dmabuf_cache_unmap(struct tegra_vde *vde,
+ struct dma_buf_attachment *a,
+ bool release)
+{
+ struct tegra_vde_cache_entry *entry;
+
+ mutex_lock(&vde->map_lock);
+
+ list_for_each_entry(entry, &vde->map_list, list) {
+ if (entry->a != a)
+ continue;
+
+ WARN_ON_ONCE(!entry->refcnt);
+
+ if (--entry->refcnt == 0) {
+ if (release)
+ tegra_vde_release_entry(entry);
+ else
+ schedule_delayed_work(&entry->dwork, 5 * HZ);
+ }
+ break;
+ }
+
+ mutex_unlock(&vde->map_lock);
+}
+
+void tegra_vde_dmabuf_cache_unmap_sync(struct tegra_vde *vde)
+{
+ struct tegra_vde_cache_entry *entry, *tmp;
+
+ mutex_lock(&vde->map_lock);
+
+ list_for_each_entry_safe(entry, tmp, &vde->map_list, list) {
+ if (entry->refcnt)
+ continue;
+
+ if (!cancel_delayed_work(&entry->dwork))
+ continue;
+
+ tegra_vde_release_entry(entry);
+ }
+
+ mutex_unlock(&vde->map_lock);
+}
+
+void tegra_vde_dmabuf_cache_unmap_all(struct tegra_vde *vde)
+{
+ struct tegra_vde_cache_entry *entry, *tmp;
+
+ mutex_lock(&vde->map_lock);
+
+ while (!list_empty(&vde->map_list)) {
+ list_for_each_entry_safe(entry, tmp, &vde->map_list, list) {
+ if (!cancel_delayed_work(&entry->dwork))
+ continue;
+
+ tegra_vde_release_entry(entry);
+ }
+
+ mutex_unlock(&vde->map_lock);
+ schedule();
+ mutex_lock(&vde->map_lock);
+ }
+
+ mutex_unlock(&vde->map_lock);
+}
#include <linux/genalloc.h>
#include <linux/interrupt.h>
#include <linux/iopoll.h>
+#include <linux/list.h>
#include <linux/miscdevice.h>
#include <linux/module.h>
#include <linux/of_device.h>
#define BSE_DMA_BUSY BIT(23)
struct video_frame {
- struct iova *y_iova;
- struct iova *cb_iova;
- struct iova *cr_iova;
- struct iova *aux_iova;
struct dma_buf_attachment *y_dmabuf_attachment;
struct dma_buf_attachment *cb_dmabuf_attachment;
struct dma_buf_attachment *cr_dmabuf_attachment;
struct dma_buf_attachment *aux_dmabuf_attachment;
- struct sg_table *y_sgt;
- struct sg_table *cb_sgt;
- struct sg_table *cr_sgt;
- struct sg_table *aux_sgt;
dma_addr_t y_addr;
dma_addr_t cb_addr;
dma_addr_t cr_addr;
vde->sxe, 0x00);
}
-static void tegra_vde_detach_and_put_dmabuf(struct tegra_vde *vde,
- enum dma_data_direction dma_dir,
- struct dma_buf_attachment *a,
- struct sg_table *sgt,
- struct iova *iova)
-{
- struct dma_buf *dmabuf = a->dmabuf;
-
- if (vde->domain)
- tegra_vde_iommu_unmap(vde, iova);
-
- dma_buf_unmap_attachment(a, sgt, dma_dir);
- dma_buf_detach(dmabuf, a);
- dma_buf_put(dmabuf);
-}
-
static int tegra_vde_attach_dmabuf(struct tegra_vde *vde,
int fd,
unsigned long offset,
size_t align_size,
struct dma_buf_attachment **a,
dma_addr_t *addrp,
- struct sg_table **s,
- struct iova **iovap,
size_t *size,
enum dma_data_direction dma_dir)
{
struct device *dev = vde->miscdev.parent;
- struct dma_buf_attachment *attachment;
struct dma_buf *dmabuf;
- struct sg_table *sgt;
int err;
dmabuf = dma_buf_get(fd);
return -EINVAL;
}
- attachment = dma_buf_attach(dmabuf, dev);
- if (IS_ERR(attachment)) {
- dev_err(dev, "Failed to attach dmabuf\n");
- err = PTR_ERR(attachment);
+ err = tegra_vde_dmabuf_cache_map(vde, dmabuf, dma_dir, a, addrp);
+ if (err)
goto err_put;
- }
-
- sgt = dma_buf_map_attachment(attachment, dma_dir);
- if (IS_ERR(sgt)) {
- dev_err(dev, "Failed to get dmabufs sg_table\n");
- err = PTR_ERR(sgt);
- goto err_detach;
- }
-
- if (!vde->domain && sgt->nents > 1) {
- dev_err(dev, "Sparse DMA region is unsupported, please enable IOMMU\n");
- err = -EINVAL;
- goto err_unmap;
- }
-
- if (vde->domain) {
- err = tegra_vde_iommu_map(vde, sgt, iovap, addrp, dmabuf->size);
- if (err) {
- dev_err(dev, "IOMMU mapping failed: %d\n", err);
- goto err_unmap;
- }
- } else {
- *addrp = sg_dma_address(sgt->sgl);
- }
*addrp = *addrp + offset;
- *a = attachment;
- *s = sgt;
if (size)
*size = dmabuf->size - offset;
return 0;
-err_unmap:
- dma_buf_unmap_attachment(attachment, sgt, dma_dir);
-err_detach:
- dma_buf_detach(dmabuf, attachment);
err_put:
dma_buf_put(dmabuf);
src->y_offset, lsize, SZ_256,
&frame->y_dmabuf_attachment,
&frame->y_addr,
- &frame->y_sgt,
- &frame->y_iova,
NULL, dma_dir);
if (err)
return err;
src->cb_offset, csize, SZ_256,
&frame->cb_dmabuf_attachment,
&frame->cb_addr,
- &frame->cb_sgt,
- &frame->cb_iova,
NULL, dma_dir);
if (err)
goto err_release_y;
src->cr_offset, csize, SZ_256,
&frame->cr_dmabuf_attachment,
&frame->cr_addr,
- &frame->cr_sgt,
- &frame->cr_iova,
NULL, dma_dir);
if (err)
goto err_release_cb;
src->aux_offset, csize, SZ_256,
&frame->aux_dmabuf_attachment,
&frame->aux_addr,
- &frame->aux_sgt,
- &frame->aux_iova,
NULL, dma_dir);
if (err)
goto err_release_cr;
return 0;
err_release_cr:
- tegra_vde_detach_and_put_dmabuf(vde, dma_dir,
- frame->cr_dmabuf_attachment,
- frame->cr_sgt,
- frame->cr_iova);
+ tegra_vde_dmabuf_cache_unmap(vde, frame->cr_dmabuf_attachment, true);
err_release_cb:
- tegra_vde_detach_and_put_dmabuf(vde, dma_dir,
- frame->cb_dmabuf_attachment,
- frame->cb_sgt,
- frame->cb_iova);
+ tegra_vde_dmabuf_cache_unmap(vde, frame->cb_dmabuf_attachment, true);
err_release_y:
- tegra_vde_detach_and_put_dmabuf(vde, dma_dir,
- frame->y_dmabuf_attachment,
- frame->y_sgt,
- frame->y_iova);
+ tegra_vde_dmabuf_cache_unmap(vde, frame->y_dmabuf_attachment, true);
return err;
}
static void tegra_vde_release_frame_dmabufs(struct tegra_vde *vde,
struct video_frame *frame,
enum dma_data_direction dma_dir,
- bool baseline_profile)
+ bool baseline_profile,
+ bool release)
{
if (!baseline_profile)
- tegra_vde_detach_and_put_dmabuf(vde, dma_dir,
- frame->aux_dmabuf_attachment,
- frame->aux_sgt,
- frame->aux_iova);
-
- tegra_vde_detach_and_put_dmabuf(vde, dma_dir,
- frame->cr_dmabuf_attachment,
- frame->cr_sgt,
- frame->cr_iova);
-
- tegra_vde_detach_and_put_dmabuf(vde, dma_dir,
- frame->cb_dmabuf_attachment,
- frame->cb_sgt,
- frame->cb_iova);
-
- tegra_vde_detach_and_put_dmabuf(vde, dma_dir,
- frame->y_dmabuf_attachment,
- frame->y_sgt,
- frame->y_iova);
+ tegra_vde_dmabuf_cache_unmap(vde, frame->aux_dmabuf_attachment,
+ release);
+
+ tegra_vde_dmabuf_cache_unmap(vde, frame->cr_dmabuf_attachment, release);
+ tegra_vde_dmabuf_cache_unmap(vde, frame->cb_dmabuf_attachment, release);
+ tegra_vde_dmabuf_cache_unmap(vde, frame->y_dmabuf_attachment, release);
}
static int tegra_vde_validate_frame(struct device *dev,
struct tegra_vde_h264_frame __user *frames_user;
struct video_frame *dpb_frames;
struct dma_buf_attachment *bitstream_data_dmabuf_attachment;
- struct sg_table *bitstream_sgt;
- struct iova *bitstream_iova;
enum dma_data_direction dma_dir;
dma_addr_t bitstream_data_addr;
dma_addr_t bsev_ptr;
SZ_16K, SZ_16K,
&bitstream_data_dmabuf_attachment,
&bitstream_data_addr,
- &bitstream_sgt,
- &bitstream_iova,
&bitstream_data_size,
DMA_TO_DEVICE);
if (ret)
dma_dir = (i == 0) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
tegra_vde_release_frame_dmabufs(vde, &dpb_frames[i], dma_dir,
- ctx.baseline_profile);
+ ctx.baseline_profile, ret != 0);
}
free_dpb_frames:
kfree(frames);
release_bitstream_dmabuf:
- tegra_vde_detach_and_put_dmabuf(vde, DMA_TO_DEVICE,
- bitstream_data_dmabuf_attachment,
- bitstream_sgt,
- bitstream_iova);
+ tegra_vde_dmabuf_cache_unmap(vde, bitstream_data_dmabuf_attachment,
+ ret != 0);
return ret;
}
return -ENOTTY;
}
+static int tegra_vde_release_file(struct inode *inode, struct file *filp)
+{
+ struct miscdevice *miscdev = filp->private_data;
+ struct tegra_vde *vde = container_of(miscdev, struct tegra_vde,
+ miscdev);
+
+ tegra_vde_dmabuf_cache_unmap_sync(vde);
+
+ return 0;
+}
+
static const struct file_operations tegra_vde_fops = {
.owner = THIS_MODULE,
.unlocked_ioctl = tegra_vde_unlocked_ioctl,
+ .release = tegra_vde_release_file,
};
static irqreturn_t tegra_vde_isr(int irq, void *data)
return -ENOMEM;
}
+ INIT_LIST_HEAD(&vde->map_list);
+ mutex_init(&vde->map_lock);
mutex_init(&vde->lock);
init_completion(&vde->decode_completion);
misc_deregister(&vde->miscdev);
+ tegra_vde_dmabuf_cache_unmap_all(vde);
tegra_vde_iommu_deinit(vde);
gen_pool_free(vde->iram_pool, (unsigned long)vde->iram,