Hi Jonathan,
Here's the final-er version of the IIO DMABUF patchset.
This v9 fixes the few issues reported by the kernel bot.
This was based on next-20240308.
Changelog:
- [3/6]:
- Select DMA_SHARED_BUFFER in Kconfig
- Remove useless forward declaration of 'iio_dma_fence'
- Import DMA-BUF namespace
- Add missing __user tag to iio_buffer_detach_dmabuf() argument
Cheers,
-Paul
Paul Cercueil (6):
dmaengine: Add API function dmaengine_prep_peripheral_dma_vec()
dmaengine: dma-axi-dmac: Implement device_prep_peripheral_dma_vec
iio: core: Add new DMABUF interface infrastructure
iio: buffer-dma: Enable support for DMABUFs
iio: buffer-dmaengine: Support new DMABUF based userspace API
Documentation: iio: Document high-speed DMABUF based API
Documentation/iio/iio_dmabuf_api.rst | 54 ++
Documentation/iio/index.rst | 1 +
drivers/dma/dma-axi-dmac.c | 40 ++
drivers/iio/Kconfig | 1 +
drivers/iio/buffer/industrialio-buffer-dma.c | 181 ++++++-
.../buffer/industrialio-buffer-dmaengine.c | 59 ++-
drivers/iio/industrialio-buffer.c | 462 ++++++++++++++++++
include/linux/dmaengine.h | 27 +
include/linux/iio/buffer-dma.h | 31 ++
include/linux/iio/buffer_impl.h | 30 ++
include/uapi/linux/iio/buffer.h | 22 +
11 files changed, 891 insertions(+), 17 deletions(-)
create mode 100644 Documentation/iio/iio_dmabuf_api.rst
--
2.43.0
This function can be used to initiate a scatter-gather DMA transfer,
where the address and size of each segment is located in one entry of
the dma_vec array.
The major difference with dmaengine_prep_slave_sg() is that it supports
specifying the lengths of each DMA transfer; as trying to override the
length of the transfer with dmaengine_prep_slave_sg() is a very tedious
process. The introduction of a new API function is also justified by the
fact that scatterlists are on their way out.
Note that dmaengine_prep_interleaved_dma() is not helpful either in that
case, as it assumes that the address of each segment will be higher than
the one of the previous segment, which we just cannot guarantee in case
of a scatter-gather transfer.
Signed-off-by: Paul Cercueil <[email protected]>
Signed-off-by: Nuno Sa <[email protected]>
---
v3: New patch
v5: Replace with function dmaengine_prep_slave_dma_vec(), and struct
'dma_vec'.
Note that at some point we will need to support cyclic transfers
using dmaengine_prep_slave_dma_vec(). Maybe with a new "flags"
parameter to the function?
v7:
- Renamed *device_prep_slave_dma_vec() -> device_prep_peripheral_dma_vec();
- Added a new flag parameter to the function as agreed between Paul
and Vinod. I renamed the first parameter to prep_flags as it's supposed to
be used (I think) with enum dma_ctrl_flags. I'm not really sure how that API
can grow but I was thinking in just having a bool cyclic parameter (as the
first intention of the flags is to support cyclic transfers) but ended up
"respecting" the previously agreed approach.
---
include/linux/dmaengine.h | 27 +++++++++++++++++++++++++++
1 file changed, 27 insertions(+)
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 752dbde4cec1..856df8cd9a4e 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -160,6 +160,16 @@ struct dma_interleaved_template {
struct data_chunk sgl[];
};
+/**
+ * struct dma_vec - DMA vector
+ * @addr: Bus address of the start of the vector
+ * @len: Length in bytes of the DMA vector
+ */
+struct dma_vec {
+ dma_addr_t addr;
+ size_t len;
+};
+
/**
* enum dma_ctrl_flags - DMA flags to augment operation preparation,
* control completion, and communicate status.
@@ -910,6 +920,10 @@ struct dma_device {
struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)(
struct dma_chan *chan, unsigned long flags);
+ struct dma_async_tx_descriptor *(*device_prep_peripheral_dma_vec)(
+ struct dma_chan *chan, const struct dma_vec *vecs,
+ size_t nents, enum dma_transfer_direction direction,
+ unsigned long prep_flags, 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,
@@ -973,6 +987,19 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single(
dir, flags, NULL);
}
+static inline struct dma_async_tx_descriptor *dmaengine_prep_peripheral_dma_vec(
+ struct dma_chan *chan, const struct dma_vec *vecs, size_t nents,
+ enum dma_transfer_direction dir, unsigned long prep_flags,
+ unsigned long flags)
+{
+ if (!chan || !chan->device || !chan->device->device_prep_peripheral_dma_vec)
+ return NULL;
+
+ return chan->device->device_prep_peripheral_dma_vec(chan, vecs, nents,
+ dir, prep_flags,
+ flags);
+}
+
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)
--
2.43.0
Add implementation of the .device_prep_peripheral_dma_vec() callback.
Signed-off-by: Paul Cercueil <[email protected]>
Signed-off-by: Nuno Sa <[email protected]>
---
v3: New patch
v5: Implement .device_prep_slave_dma_vec() instead of v3's
.device_prep_slave_dma_array().
v6: Use new prototype for axi_dmac_alloc_desc() as it changed upstream.
v7: Adapted patch for the changes made in patch 1.
---
drivers/dma/dma-axi-dmac.c | 40 ++++++++++++++++++++++++++++++++++++++
1 file changed, 40 insertions(+)
diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 4e339c04fc1e..d03cbf1d28e8 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -620,6 +620,45 @@ static struct axi_dmac_sg *axi_dmac_fill_linear_sg(struct axi_dmac_chan *chan,
return sg;
}
+static struct dma_async_tx_descriptor *
+axi_dmac_prep_peripheral_dma_vec(struct dma_chan *c, const struct dma_vec *vecs,
+ size_t nb, enum dma_transfer_direction direction,
+ unsigned long prep_flags, unsigned long flags)
+{
+ struct axi_dmac_chan *chan = to_axi_dmac_chan(c);
+ struct axi_dmac_desc *desc;
+ unsigned int num_sgs = 0;
+ struct axi_dmac_sg *dsg;
+ size_t i;
+
+ if (direction != chan->direction)
+ return NULL;
+
+ for (i = 0; i < nb; i++)
+ num_sgs += DIV_ROUND_UP(vecs[i].len, chan->max_length);
+
+ desc = axi_dmac_alloc_desc(chan, num_sgs);
+ if (!desc)
+ return NULL;
+
+ dsg = desc->sg;
+
+ for (i = 0; i < nb; i++) {
+ if (!axi_dmac_check_addr(chan, vecs[i].addr) ||
+ !axi_dmac_check_len(chan, vecs[i].len)) {
+ kfree(desc);
+ return NULL;
+ }
+
+ dsg = axi_dmac_fill_linear_sg(chan, direction, vecs[i].addr, 1,
+ vecs[i].len, dsg);
+ }
+
+ desc->cyclic = false;
+
+ return vchan_tx_prep(&chan->vchan, &desc->vdesc, prep_flags);
+}
+
static struct dma_async_tx_descriptor *axi_dmac_prep_slave_sg(
struct dma_chan *c, struct scatterlist *sgl,
unsigned int sg_len, enum dma_transfer_direction direction,
@@ -1055,6 +1094,7 @@ static int axi_dmac_probe(struct platform_device *pdev)
dma_dev->device_tx_status = dma_cookie_status;
dma_dev->device_issue_pending = axi_dmac_issue_pending;
dma_dev->device_prep_slave_sg = axi_dmac_prep_slave_sg;
+ dma_dev->device_prep_peripheral_dma_vec = axi_dmac_prep_peripheral_dma_vec;
dma_dev->device_prep_dma_cyclic = axi_dmac_prep_dma_cyclic;
dma_dev->device_prep_interleaved_dma = axi_dmac_prep_interleaved;
dma_dev->device_terminate_all = axi_dmac_terminate_all;
--
2.43.0
Add the necessary infrastructure to the IIO core to support a new
optional DMABUF based interface.
With this new interface, DMABUF objects (externally created) can be
attached to a IIO buffer, and subsequently used for data transfer.
A userspace application can then use this interface to share DMABUF
objects between several interfaces, allowing it to transfer data in a
zero-copy fashion, for instance between IIO and the USB stack.
The userspace application can also memory-map the DMABUF objects, and
access the sample data directly. The advantage of doing this vs. the
read() interface is that it avoids an extra copy of the data between the
kernel and userspace. This is particularly userful for high-speed
devices which produce several megabytes or even gigabytes of data per
second.
As part of the interface, 3 new IOCTLs have been added:
IIO_BUFFER_DMABUF_ATTACH_IOCTL(int fd):
Attach the DMABUF object identified by the given file descriptor to the
buffer.
IIO_BUFFER_DMABUF_DETACH_IOCTL(int fd):
Detach the DMABUF object identified by the given file descriptor from
the buffer. Note that closing the IIO buffer's file descriptor will
automatically detach all previously attached DMABUF objects.
IIO_BUFFER_DMABUF_ENQUEUE_IOCTL(struct iio_dmabuf *):
Request a data transfer to/from the given DMABUF object. Its file
descriptor, as well as the transfer size and flags are provided in the
"iio_dmabuf" structure.
These three IOCTLs have to be performed on the IIO buffer's file
descriptor, obtained using the IIO_BUFFER_GET_FD_IOCTL() ioctl.
Signed-off-by: Paul Cercueil <[email protected]>
Signed-off-by: Nuno Sa <[email protected]>
---
v2: Only allow the new IOCTLs on the buffer FD created with
IIO_BUFFER_GET_FD_IOCTL().
v3: - Get rid of the old IOCTLs. The IIO subsystem does not create or
manage DMABUFs anymore, and only attaches/detaches externally
created DMABUFs.
- Add IIO_BUFFER_DMABUF_CYCLIC to the supported flags.
v5: - Use dev_err() instead of pr_err()
- Inline to_iio_dma_fence()
- Add comment to explain why we unref twice when detaching dmabuf
- Remove TODO comment. It is actually safe to free the file's
private data even when transfers are still pending because it
won't be accessed.
- Fix documentation of new fields in struct iio_buffer_access_funcs
- iio_dma_resv_lock() does not need to be exported, make it static
v6: - Remove dead code in iio_dma_resv_lock()
- Fix non-block actually blocking
- Cache dma_buf_attachment instead of mapping/unmapping it for every
transfer
- Return -EINVAL instead of IIO_IOCTL_UNHANDLED for unknown ioctl
- Make .block_enqueue() callback take a dma_fence pointer, which
will be passed to iio_buffer_signal_dmabuf_done() instead of the
dma_buf_attachment; and remove the backpointer from the priv
structure to the dma_fence.
- Use dma_fence_begin/end_signalling in the dma_fence critical
sections
- Unref dma_fence and dma_buf_attachment in worker, because they
might try to lock the dma_resv, which would deadlock.
- Add buffer ops to lock/unlock the queue. This is motivated by the
fact that once the dma_fence has been installed, we cannot lock
anything anymore - so the queue must be locked before the
dma_fence is installed.
- Use 'long retl' variable to handle the return value of
dma_resv_wait_timeout()
- Protect dmabufs list access with a mutex
- Rework iio_buffer_find_attachment() to use the internal dmabufs
list, instead of messing with dmabufs private data.
- Add an atomically-increasing sequence number for fences
v8 - Fix swapped fence direction
- Simplify fence wait mechanism
- Remove "Buffer closed with active transfers" print, as it was dead
code
- Un-export iio_buffer_dmabuf_{get,put}. They are not used anywhere
else so they can even be static.
- Prevent attaching already-attached DMABUFs
v9: - Select DMA_SHARED_BUFFER in Kconfig
- Remove useless forward declaration of 'iio_dma_fence'
- Import DMA-BUF namespace
- Add missing __user tag to iio_buffer_detach_dmabuf() argument
---
drivers/iio/Kconfig | 1 +
drivers/iio/industrialio-buffer.c | 462 ++++++++++++++++++++++++++++++
include/linux/iio/buffer_impl.h | 30 ++
include/uapi/linux/iio/buffer.h | 22 ++
4 files changed, 515 insertions(+)
diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig
index 9c351ffc7bed..661127aed2f9 100644
--- a/drivers/iio/Kconfig
+++ b/drivers/iio/Kconfig
@@ -14,6 +14,7 @@ if IIO
config IIO_BUFFER
bool "Enable buffer support within IIO"
+ select DMA_SHARED_BUFFER
help
Provide core support for various buffer based data
acquisition methods.
diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
index b581a7e80566..a987654f82fc 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -9,14 +9,19 @@
* - Better memory allocation techniques?
* - Alternative access techniques?
*/
+#include <linux/atomic.h>
#include <linux/anon_inodes.h>
#include <linux/kernel.h>
#include <linux/export.h>
#include <linux/device.h>
+#include <linux/dma-buf.h>
+#include <linux/dma-fence.h>
+#include <linux/dma-resv.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/cdev.h>
#include <linux/slab.h>
+#include <linux/mm.h>
#include <linux/poll.h>
#include <linux/sched/signal.h>
@@ -28,6 +33,32 @@
#include <linux/iio/buffer.h>
#include <linux/iio/buffer_impl.h>
+#define DMABUF_ENQUEUE_TIMEOUT_MS 5000
+
+MODULE_IMPORT_NS(DMA_BUF);
+
+struct iio_dmabuf_priv {
+ struct list_head entry;
+ struct kref ref;
+
+ struct iio_buffer *buffer;
+ struct iio_dma_buffer_block *block;
+
+ u64 context;
+ spinlock_t lock;
+
+ struct dma_buf_attachment *attach;
+ struct sg_table *sgt;
+ enum dma_data_direction dir;
+ atomic_t seqno;
+};
+
+struct iio_dma_fence {
+ struct dma_fence base;
+ struct iio_dmabuf_priv *priv;
+ struct work_struct work;
+};
+
static const char * const iio_endian_prefix[] = {
[IIO_BE] = "be",
[IIO_LE] = "le",
@@ -332,6 +363,8 @@ void iio_buffer_init(struct iio_buffer *buffer)
{
INIT_LIST_HEAD(&buffer->demux_list);
INIT_LIST_HEAD(&buffer->buffer_list);
+ INIT_LIST_HEAD(&buffer->dmabufs);
+ mutex_init(&buffer->dmabufs_mutex);
init_waitqueue_head(&buffer->pollq);
kref_init(&buffer->ref);
if (!buffer->watermark)
@@ -1519,14 +1552,57 @@ static void iio_buffer_unregister_legacy_sysfs_groups(struct iio_dev *indio_dev)
kfree(iio_dev_opaque->legacy_scan_el_group.attrs);
}
+static void iio_buffer_dmabuf_release(struct kref *ref)
+{
+ struct iio_dmabuf_priv *priv = container_of(ref, struct iio_dmabuf_priv, ref);
+ struct dma_buf_attachment *attach = priv->attach;
+ struct iio_buffer *buffer = priv->buffer;
+ struct dma_buf *dmabuf = attach->dmabuf;
+
+ dma_resv_lock(dmabuf->resv, NULL);
+ dma_buf_unmap_attachment(attach, priv->sgt, priv->dir);
+ dma_resv_unlock(dmabuf->resv);
+
+ buffer->access->detach_dmabuf(buffer, priv->block);
+
+ dma_buf_detach(attach->dmabuf, attach);
+ dma_buf_put(dmabuf);
+ kfree(priv);
+}
+
+static void iio_buffer_dmabuf_get(struct dma_buf_attachment *attach)
+{
+ struct iio_dmabuf_priv *priv = attach->importer_priv;
+
+ kref_get(&priv->ref);
+}
+
+static void iio_buffer_dmabuf_put(struct dma_buf_attachment *attach)
+{
+ struct iio_dmabuf_priv *priv = attach->importer_priv;
+
+ kref_put(&priv->ref, iio_buffer_dmabuf_release);
+}
+
static int iio_buffer_chrdev_release(struct inode *inode, struct file *filep)
{
struct iio_dev_buffer_pair *ib = filep->private_data;
struct iio_dev *indio_dev = ib->indio_dev;
struct iio_buffer *buffer = ib->buffer;
+ struct iio_dmabuf_priv *priv, *tmp;
wake_up(&buffer->pollq);
+ mutex_lock(&buffer->dmabufs_mutex);
+
+ /* Close all attached DMABUFs */
+ list_for_each_entry_safe(priv, tmp, &buffer->dmabufs, entry) {
+ list_del_init(&priv->entry);
+ iio_buffer_dmabuf_put(priv->attach);
+ }
+
+ mutex_unlock(&buffer->dmabufs_mutex);
+
kfree(ib);
clear_bit(IIO_BUSY_BIT_POS, &buffer->flags);
iio_device_put(indio_dev);
@@ -1534,11 +1610,396 @@ static int iio_buffer_chrdev_release(struct inode *inode, struct file *filep)
return 0;
}
+static int iio_dma_resv_lock(struct dma_buf *dmabuf, bool nonblock)
+{
+ if (!nonblock)
+ return dma_resv_lock_interruptible(dmabuf->resv, NULL);
+
+ if (!dma_resv_trylock(dmabuf->resv))
+ return -EBUSY;
+
+ return 0;
+}
+
+static struct dma_buf_attachment *
+iio_buffer_find_attachment(struct iio_dev_buffer_pair *ib,
+ struct dma_buf *dmabuf, bool nonblock)
+{
+ struct device *dev = ib->indio_dev->dev.parent;
+ struct iio_buffer *buffer = ib->buffer;
+ struct dma_buf_attachment *attach = NULL;
+ struct iio_dmabuf_priv *priv;
+
+ mutex_lock(&buffer->dmabufs_mutex);
+
+ list_for_each_entry(priv, &buffer->dmabufs, entry) {
+ if (priv->attach->dev == dev
+ && priv->attach->dmabuf == dmabuf) {
+ attach = priv->attach;
+ break;
+ }
+ }
+
+ if (attach)
+ iio_buffer_dmabuf_get(attach);
+
+ mutex_unlock(&buffer->dmabufs_mutex);
+
+ return attach ?: ERR_PTR(-EPERM);
+}
+
+static int iio_buffer_attach_dmabuf(struct iio_dev_buffer_pair *ib,
+ int __user *user_fd, bool nonblock)
+{
+ struct iio_dev *indio_dev = ib->indio_dev;
+ struct iio_buffer *buffer = ib->buffer;
+ struct dma_buf_attachment *attach;
+ struct iio_dmabuf_priv *priv, *each;
+ struct dma_buf *dmabuf;
+ int err, fd;
+
+ if (!buffer->access->attach_dmabuf
+ || !buffer->access->detach_dmabuf
+ || !buffer->access->enqueue_dmabuf)
+ return -EPERM;
+
+ if (copy_from_user(&fd, user_fd, sizeof(fd)))
+ return -EFAULT;
+
+ priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ spin_lock_init(&priv->lock);
+ priv->context = dma_fence_context_alloc(1);
+
+ dmabuf = dma_buf_get(fd);
+ if (IS_ERR(dmabuf)) {
+ err = PTR_ERR(dmabuf);
+ goto err_free_priv;
+ }
+
+ attach = dma_buf_attach(dmabuf, indio_dev->dev.parent);
+ if (IS_ERR(attach)) {
+ err = PTR_ERR(attach);
+ goto err_dmabuf_put;
+ }
+
+ err = iio_dma_resv_lock(dmabuf, nonblock);
+ if (err)
+ goto err_dmabuf_detach;
+
+ priv->dir = buffer->direction == IIO_BUFFER_DIRECTION_IN
+ ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+
+ priv->sgt = dma_buf_map_attachment(attach, priv->dir);
+ if (IS_ERR(priv->sgt)) {
+ err = PTR_ERR(priv->sgt);
+ dev_err(&indio_dev->dev, "Unable to map attachment: %d\n", err);
+ goto err_resv_unlock;
+ }
+
+ kref_init(&priv->ref);
+ priv->buffer = buffer;
+ priv->attach = attach;
+ attach->importer_priv = priv;
+
+ priv->block = buffer->access->attach_dmabuf(buffer, attach);
+ if (IS_ERR(priv->block)) {
+ err = PTR_ERR(priv->block);
+ goto err_dmabuf_unmap_attachment;
+ }
+
+ dma_resv_unlock(dmabuf->resv);
+
+ mutex_lock(&buffer->dmabufs_mutex);
+
+ /*
+ * Check whether we already have an attachment for this driver/DMABUF
+ * combo. If we do, refuse to attach.
+ */
+ list_for_each_entry(each, &buffer->dmabufs, entry) {
+ if (each->attach->dev == indio_dev->dev.parent
+ && each->attach->dmabuf == dmabuf) {
+ /*
+ * We unlocked the reservation object, so going through
+ * the cleanup code would mean re-locking it first.
+ * At this stage it is simpler to free the attachment
+ * using iio_buffer_dma_put().
+ */
+ mutex_unlock(&buffer->dmabufs_mutex);
+ iio_buffer_dmabuf_put(attach);
+ return -EBUSY;
+ }
+ }
+
+ /* Otherwise, add the new attachment to our dmabufs list. */
+ list_add(&priv->entry, &buffer->dmabufs);
+ mutex_unlock(&buffer->dmabufs_mutex);
+
+ return 0;
+
+err_dmabuf_unmap_attachment:
+ dma_buf_unmap_attachment(attach, priv->sgt, priv->dir);
+err_resv_unlock:
+ dma_resv_unlock(dmabuf->resv);
+err_dmabuf_detach:
+ dma_buf_detach(dmabuf, attach);
+err_dmabuf_put:
+ dma_buf_put(dmabuf);
+err_free_priv:
+ kfree(priv);
+
+ return err;
+}
+
+static int iio_buffer_detach_dmabuf(struct iio_dev_buffer_pair *ib,
+ int __user *user_req, bool nonblock)
+{
+ struct iio_buffer *buffer = ib->buffer;
+ struct iio_dev *indio_dev = ib->indio_dev;
+ struct iio_dmabuf_priv *priv;
+ struct dma_buf *dmabuf;
+ int dmabuf_fd, ret = -EPERM;
+
+ if (copy_from_user(&dmabuf_fd, user_req, sizeof(dmabuf_fd)))
+ return -EFAULT;
+
+ dmabuf = dma_buf_get(dmabuf_fd);
+ if (IS_ERR(dmabuf))
+ return PTR_ERR(dmabuf);
+
+ mutex_lock(&buffer->dmabufs_mutex);
+
+ list_for_each_entry(priv, &buffer->dmabufs, entry) {
+ if (priv->attach->dev == indio_dev->dev.parent
+ && priv->attach->dmabuf == dmabuf) {
+ list_del(&priv->entry);
+
+ /* Unref the reference from iio_buffer_attach_dmabuf() */
+ iio_buffer_dmabuf_put(priv->attach);
+ ret = 0;
+ break;
+ }
+ }
+
+ mutex_unlock(&buffer->dmabufs_mutex);
+ dma_buf_put(dmabuf);
+
+ return ret;
+}
+
+static const char *
+iio_buffer_dma_fence_get_driver_name(struct dma_fence *fence)
+{
+ return "iio";
+}
+
+static void iio_buffer_dma_fence_release(struct dma_fence *fence)
+{
+ struct iio_dma_fence *iio_fence =
+ container_of(fence, struct iio_dma_fence, base);
+
+ kfree(iio_fence);
+}
+
+static const struct dma_fence_ops iio_buffer_dma_fence_ops = {
+ .get_driver_name = iio_buffer_dma_fence_get_driver_name,
+ .get_timeline_name = iio_buffer_dma_fence_get_driver_name,
+ .release = iio_buffer_dma_fence_release,
+};
+
+static int iio_buffer_enqueue_dmabuf(struct iio_dev_buffer_pair *ib,
+ struct iio_dmabuf __user *iio_dmabuf_req,
+ bool nonblock)
+{
+ struct iio_buffer *buffer = ib->buffer;
+ struct iio_dmabuf iio_dmabuf;
+ struct dma_buf_attachment *attach;
+ struct iio_dmabuf_priv *priv;
+ struct iio_dma_fence *fence;
+ struct dma_buf *dmabuf;
+ unsigned long timeout;
+ bool cookie, cyclic, dma_to_ram;
+ long retl;
+ u32 seqno;
+ int ret;
+
+ if (copy_from_user(&iio_dmabuf, iio_dmabuf_req, sizeof(iio_dmabuf)))
+ return -EFAULT;
+
+ if (iio_dmabuf.flags & ~IIO_BUFFER_DMABUF_SUPPORTED_FLAGS)
+ return -EINVAL;
+
+ cyclic = iio_dmabuf.flags & IIO_BUFFER_DMABUF_CYCLIC;
+
+ /* Cyclic flag is only supported on output buffers */
+ if (cyclic && buffer->direction != IIO_BUFFER_DIRECTION_OUT)
+ return -EINVAL;
+
+ dmabuf = dma_buf_get(iio_dmabuf.fd);
+ if (IS_ERR(dmabuf))
+ return PTR_ERR(dmabuf);
+
+ if (!iio_dmabuf.bytes_used || iio_dmabuf.bytes_used > dmabuf->size) {
+ ret = -EINVAL;
+ goto err_dmabuf_put;
+ }
+
+ attach = iio_buffer_find_attachment(ib, dmabuf, nonblock);
+ if (IS_ERR(attach)) {
+ ret = PTR_ERR(attach);
+ goto err_dmabuf_put;
+ }
+
+ priv = attach->importer_priv;
+
+ fence = kmalloc(sizeof(*fence), GFP_KERNEL);
+ if (!fence) {
+ ret = -ENOMEM;
+ goto err_attachment_put;
+ }
+
+ fence->priv = priv;
+
+ seqno = atomic_add_return(1, &priv->seqno);
+
+ /*
+ * The transfers are guaranteed to be processed in the order they are
+ * enqueued, so we can use a simple incrementing sequence number for
+ * the dma_fence.
+ */
+ dma_fence_init(&fence->base, &iio_buffer_dma_fence_ops,
+ &priv->lock, priv->context, seqno);
+
+ ret = iio_dma_resv_lock(dmabuf, nonblock);
+ if (ret)
+ goto err_fence_put;
+
+ timeout = nonblock ? 0 : msecs_to_jiffies(DMABUF_ENQUEUE_TIMEOUT_MS);
+ dma_to_ram = buffer->direction == IIO_BUFFER_DIRECTION_IN;
+
+ /* Make sure we don't have writers */
+ retl = dma_resv_wait_timeout(dmabuf->resv,
+ dma_resv_usage_rw(dma_to_ram),
+ true, timeout);
+ if (retl == 0)
+ retl = -EBUSY;
+ if (retl < 0) {
+ ret = (int)retl;
+ goto err_resv_unlock;
+ }
+
+ if (buffer->access->lock_queue)
+ buffer->access->lock_queue(buffer);
+
+ ret = dma_resv_reserve_fences(dmabuf->resv, 1);
+ if (ret)
+ goto err_queue_unlock;
+
+ dma_resv_add_fence(dmabuf->resv, &fence->base,
+ dma_to_ram ? DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ);
+ dma_resv_unlock(dmabuf->resv);
+
+ cookie = dma_fence_begin_signalling();
+
+ ret = buffer->access->enqueue_dmabuf(buffer, priv->block, &fence->base,
+ priv->sgt, iio_dmabuf.bytes_used,
+ cyclic);
+ if (ret) {
+ /*
+ * DMABUF enqueue failed, but we already added the fence.
+ * Signal the error through the fence completion mechanism.
+ */
+ iio_buffer_signal_dmabuf_done(&fence->base, ret);
+ }
+
+ if (buffer->access->unlock_queue)
+ buffer->access->unlock_queue(buffer);
+
+ dma_fence_end_signalling(cookie);
+ dma_buf_put(dmabuf);
+
+ return ret;
+
+err_queue_unlock:
+ if (buffer->access->unlock_queue)
+ buffer->access->unlock_queue(buffer);
+err_resv_unlock:
+ dma_resv_unlock(dmabuf->resv);
+err_fence_put:
+ dma_fence_put(&fence->base);
+err_attachment_put:
+ iio_buffer_dmabuf_put(attach);
+err_dmabuf_put:
+ dma_buf_put(dmabuf);
+
+ return ret;
+}
+
+static void iio_buffer_cleanup(struct work_struct *work)
+{
+ struct iio_dma_fence *fence =
+ container_of(work, struct iio_dma_fence, work);
+ struct iio_dmabuf_priv *priv = fence->priv;
+ struct dma_buf_attachment *attach = priv->attach;
+
+ dma_fence_put(&fence->base);
+ iio_buffer_dmabuf_put(attach);
+}
+
+void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int ret)
+{
+ struct iio_dma_fence *iio_fence =
+ container_of(fence, struct iio_dma_fence, base);
+ bool cookie = dma_fence_begin_signalling();
+
+ /*
+ * Get a reference to the fence, so that it's not freed as soon as
+ * it's signaled.
+ */
+ dma_fence_get(fence);
+
+ fence->error = ret;
+ dma_fence_signal(fence);
+ dma_fence_end_signalling(cookie);
+
+ /*
+ * The fence will be unref'd in iio_buffer_cleanup.
+ * It can't be done here, as the unref functions might try to lock the
+ * resv object, which can deadlock.
+ */
+ INIT_WORK(&iio_fence->work, iio_buffer_cleanup);
+ schedule_work(&iio_fence->work);
+}
+EXPORT_SYMBOL_GPL(iio_buffer_signal_dmabuf_done);
+
+static long iio_buffer_chrdev_ioctl(struct file *filp,
+ unsigned int cmd, unsigned long arg)
+{
+ struct iio_dev_buffer_pair *ib = filp->private_data;
+ void __user *_arg = (void __user *)arg;
+ bool nonblock = filp->f_flags & O_NONBLOCK;
+
+ switch (cmd) {
+ case IIO_BUFFER_DMABUF_ATTACH_IOCTL:
+ return iio_buffer_attach_dmabuf(ib, _arg, nonblock);
+ case IIO_BUFFER_DMABUF_DETACH_IOCTL:
+ return iio_buffer_detach_dmabuf(ib, _arg, nonblock);
+ case IIO_BUFFER_DMABUF_ENQUEUE_IOCTL:
+ return iio_buffer_enqueue_dmabuf(ib, _arg, nonblock);
+ default:
+ return -EINVAL;
+ }
+}
+
static const struct file_operations iio_buffer_chrdev_fileops = {
.owner = THIS_MODULE,
.llseek = noop_llseek,
.read = iio_buffer_read,
.write = iio_buffer_write,
+ .unlocked_ioctl = iio_buffer_chrdev_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.poll = iio_buffer_poll,
.release = iio_buffer_chrdev_release,
};
@@ -1953,6 +2414,7 @@ static void iio_buffer_release(struct kref *ref)
{
struct iio_buffer *buffer = container_of(ref, struct iio_buffer, ref);
+ mutex_destroy(&buffer->dmabufs_mutex);
buffer->access->release(buffer);
}
diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h
index 89c3fd7c29ca..1a221c1d7736 100644
--- a/include/linux/iio/buffer_impl.h
+++ b/include/linux/iio/buffer_impl.h
@@ -9,8 +9,12 @@
#include <uapi/linux/iio/buffer.h>
#include <linux/iio/buffer.h>
+struct dma_buf_attachment;
+struct dma_fence;
struct iio_dev;
+struct iio_dma_buffer_block;
struct iio_buffer;
+struct sg_table;
/**
* INDIO_BUFFER_FLAG_FIXED_WATERMARK - Watermark level of the buffer can not be
@@ -39,6 +43,13 @@ struct iio_buffer;
* device stops sampling. Calles are balanced with @enable.
* @release: called when the last reference to the buffer is dropped,
* should free all resources allocated by the buffer.
+ * @attach_dmabuf: called from userspace via ioctl to attach one external
+ * DMABUF.
+ * @detach_dmabuf: called from userspace via ioctl to detach one previously
+ * attached DMABUF.
+ * @enqueue_dmabuf: called from userspace via ioctl to queue this DMABUF
+ * object to this buffer. Requires a valid DMABUF fd, that
+ * was previouly attached to this buffer.
* @modes: Supported operating modes by this buffer type
* @flags: A bitmask combination of INDIO_BUFFER_FLAG_*
*
@@ -68,6 +79,17 @@ struct iio_buffer_access_funcs {
void (*release)(struct iio_buffer *buffer);
+ struct iio_dma_buffer_block * (*attach_dmabuf)(struct iio_buffer *buffer,
+ struct dma_buf_attachment *attach);
+ void (*detach_dmabuf)(struct iio_buffer *buffer,
+ struct iio_dma_buffer_block *block);
+ int (*enqueue_dmabuf)(struct iio_buffer *buffer,
+ struct iio_dma_buffer_block *block,
+ struct dma_fence *fence, struct sg_table *sgt,
+ size_t size, bool cyclic);
+ void (*lock_queue)(struct iio_buffer *buffer);
+ void (*unlock_queue)(struct iio_buffer *buffer);
+
unsigned int modes;
unsigned int flags;
};
@@ -136,6 +158,12 @@ struct iio_buffer {
/* @ref: Reference count of the buffer. */
struct kref ref;
+
+ /* @dmabufs: List of DMABUF attachments */
+ struct list_head dmabufs; /* P: dmabufs_mutex */
+
+ /* @dmabufs_mutex: Protects dmabufs */
+ struct mutex dmabufs_mutex;
};
/**
@@ -159,6 +187,8 @@ void iio_buffer_init(struct iio_buffer *buffer);
struct iio_buffer *iio_buffer_get(struct iio_buffer *buffer);
void iio_buffer_put(struct iio_buffer *buffer);
+void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int ret);
+
#else /* CONFIG_IIO_BUFFER */
static inline void iio_buffer_get(struct iio_buffer *buffer) {}
diff --git a/include/uapi/linux/iio/buffer.h b/include/uapi/linux/iio/buffer.h
index 13939032b3f6..c666aa95e532 100644
--- a/include/uapi/linux/iio/buffer.h
+++ b/include/uapi/linux/iio/buffer.h
@@ -5,6 +5,28 @@
#ifndef _UAPI_IIO_BUFFER_H_
#define _UAPI_IIO_BUFFER_H_
+#include <linux/types.h>
+
+/* Flags for iio_dmabuf.flags */
+#define IIO_BUFFER_DMABUF_CYCLIC (1 << 0)
+#define IIO_BUFFER_DMABUF_SUPPORTED_FLAGS 0x00000001
+
+/**
+ * struct iio_dmabuf - Descriptor for a single IIO DMABUF object
+ * @fd: file descriptor of the DMABUF object
+ * @flags: one or more IIO_BUFFER_DMABUF_* flags
+ * @bytes_used: number of bytes used in this DMABUF for the data transfer.
+ * Should generally be set to the DMABUF's size.
+ */
+struct iio_dmabuf {
+ __u32 fd;
+ __u32 flags;
+ __u64 bytes_used;
+};
+
#define IIO_BUFFER_GET_FD_IOCTL _IOWR('i', 0x91, int)
+#define IIO_BUFFER_DMABUF_ATTACH_IOCTL _IOW('i', 0x92, int)
+#define IIO_BUFFER_DMABUF_DETACH_IOCTL _IOW('i', 0x93, int)
+#define IIO_BUFFER_DMABUF_ENQUEUE_IOCTL _IOW('i', 0x94, struct iio_dmabuf)
#endif /* _UAPI_IIO_BUFFER_H_ */
--
2.43.0
Use the functions provided by the buffer-dma core to implement the
DMABUF userspace API in the buffer-dmaengine IIO buffer implementation.
Since we want to be able to transfer an arbitrary number of bytes and
not necesarily the full DMABUF, the associated scatterlist is converted
to an array of DMA addresses + lengths, which is then passed to
dmaengine_prep_slave_dma_array().
Signed-off-by: Paul Cercueil <[email protected]>
Signed-off-by: Nuno Sa <[email protected]>
---
v3: Use the new dmaengine_prep_slave_dma_array(), and adapt the code to
work with the new functions introduced in industrialio-buffer-dma.c.
v5: - Use the new dmaengine_prep_slave_dma_vec().
- Restrict to input buffers, since output buffers are not yet
supported by IIO buffers.
v6: - Populate .lock_queue / .unlock_queue callbacks
- Switch to atomic memory allocations in .submit_queue, because of
the dma_fence critical section
- Make sure that the size of the scatterlist is enough
v7: Adapted patch for the changes made in patch 1.
---
.../buffer/industrialio-buffer-dmaengine.c | 59 +++++++++++++++++--
1 file changed, 53 insertions(+), 6 deletions(-)
diff --git a/drivers/iio/buffer/industrialio-buffer-dmaengine.c b/drivers/iio/buffer/industrialio-buffer-dmaengine.c
index a18c1da292af..3b7b649f0a89 100644
--- a/drivers/iio/buffer/industrialio-buffer-dmaengine.c
+++ b/drivers/iio/buffer/industrialio-buffer-dmaengine.c
@@ -64,15 +64,55 @@ static int iio_dmaengine_buffer_submit_block(struct iio_dma_buffer_queue *queue,
struct dmaengine_buffer *dmaengine_buffer =
iio_buffer_to_dmaengine_buffer(&queue->buffer);
struct dma_async_tx_descriptor *desc;
+ struct scatterlist *sgl;
+ struct dma_vec *vecs;
dma_cookie_t cookie;
+ size_t len_total;
+ size_t max_size;
+ unsigned int i;
+ int nents;
- block->bytes_used = min(block->size, dmaengine_buffer->max_size);
- block->bytes_used = round_down(block->bytes_used,
- dmaengine_buffer->align);
+ if (queue->buffer.direction != IIO_BUFFER_DIRECTION_IN) {
+ /* We do not yet support output buffers. */
+ return -EINVAL;
+ }
- desc = dmaengine_prep_slave_single(dmaengine_buffer->chan,
- block->phys_addr, block->bytes_used, DMA_DEV_TO_MEM,
- DMA_PREP_INTERRUPT);
+ if (block->sg_table) {
+ sgl = block->sg_table->sgl;
+ nents = sg_nents_for_len(sgl, block->bytes_used);
+ if (nents < 0)
+ return nents;
+
+ vecs = kmalloc_array(nents, sizeof(*vecs), GFP_ATOMIC);
+ if (!vecs)
+ return -ENOMEM;
+
+ len_total = block->bytes_used;
+
+ for (i = 0; i < nents; i++) {
+ vecs[i].addr = sg_dma_address(sgl);
+ vecs[i].len = min(sg_dma_len(sgl), len_total);
+ len_total -= vecs[i].len;
+
+ sgl = sg_next(sgl);
+ }
+
+ desc = dmaengine_prep_peripheral_dma_vec(dmaengine_buffer->chan,
+ vecs, nents,
+ DMA_DEV_TO_MEM,
+ DMA_PREP_INTERRUPT, 0);
+ kfree(vecs);
+ } else {
+ max_size = min(block->size, dmaengine_buffer->max_size);
+ max_size = round_down(max_size, dmaengine_buffer->align);
+ block->bytes_used = max_size;
+
+ desc = dmaengine_prep_slave_single(dmaengine_buffer->chan,
+ block->phys_addr,
+ block->bytes_used,
+ DMA_DEV_TO_MEM,
+ DMA_PREP_INTERRUPT);
+ }
if (!desc)
return -ENOMEM;
@@ -120,6 +160,13 @@ static const struct iio_buffer_access_funcs iio_dmaengine_buffer_ops = {
.data_available = iio_dma_buffer_data_available,
.release = iio_dmaengine_buffer_release,
+ .enqueue_dmabuf = iio_dma_buffer_enqueue_dmabuf,
+ .attach_dmabuf = iio_dma_buffer_attach_dmabuf,
+ .detach_dmabuf = iio_dma_buffer_detach_dmabuf,
+
+ .lock_queue = iio_dma_buffer_lock_queue,
+ .unlock_queue = iio_dma_buffer_unlock_queue,
+
.modes = INDIO_BUFFER_HARDWARE,
.flags = INDIO_BUFFER_FLAG_FIXED_WATERMARK,
};
--
2.43.0
Implement iio_dma_buffer_attach_dmabuf(), iio_dma_buffer_detach_dmabuf()
and iio_dma_buffer_transfer_dmabuf(), which can then be used by the IIO
DMA buffer implementations.
Signed-off-by: Paul Cercueil <[email protected]>
Signed-off-by: Nuno Sa <[email protected]>
---
v3: Update code to provide the functions that will be used as callbacks
for the new IOCTLs.
v6: - Update iio_dma_buffer_enqueue_dmabuf() to take a dma_fence pointer
- Pass that dma_fence pointer along to
iio_buffer_signal_dmabuf_done()
- Add iio_dma_buffer_lock_queue() / iio_dma_buffer_unlock_queue()
- Do not lock the queue in iio_dma_buffer_enqueue_dmabuf().
The caller will ensure that it has been locked already.
- Replace "int += bool;" by "if (bool) int++;"
- Use dma_fence_begin/end_signalling in the dma_fence critical
sections
- Use one "num_dmabufs" fields instead of one "num_blocks" and one
"num_fileio_blocks". Make it an atomic_t, which makes it possible
to decrement it atomically in iio_buffer_block_release() without
having to lock the queue mutex; and in turn, it means that we
don't need to use iio_buffer_block_put_atomic() everywhere to
avoid locking the queue mutex twice.
- Use cleanup.h guard(mutex) when possible
- Explicitely list all states in the switch in
iio_dma_can_enqueue_block()
- Rename iio_dma_buffer_fileio_mode() to
iio_dma_buffer_can_use_fileio(), and add a comment explaining why
it cannot race vs. DMABUF.
---
drivers/iio/buffer/industrialio-buffer-dma.c | 181 +++++++++++++++++--
include/linux/iio/buffer-dma.h | 31 ++++
2 files changed, 201 insertions(+), 11 deletions(-)
diff --git a/drivers/iio/buffer/industrialio-buffer-dma.c b/drivers/iio/buffer/industrialio-buffer-dma.c
index 5610ba67925e..c0f539af98f9 100644
--- a/drivers/iio/buffer/industrialio-buffer-dma.c
+++ b/drivers/iio/buffer/industrialio-buffer-dma.c
@@ -4,6 +4,8 @@
* Author: Lars-Peter Clausen <[email protected]>
*/
+#include <linux/atomic.h>
+#include <linux/cleanup.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/module.h>
@@ -14,6 +16,8 @@
#include <linux/poll.h>
#include <linux/iio/buffer_impl.h>
#include <linux/iio/buffer-dma.h>
+#include <linux/dma-buf.h>
+#include <linux/dma-fence.h>
#include <linux/dma-mapping.h>
#include <linux/sizes.h>
@@ -94,13 +98,18 @@ static void iio_buffer_block_release(struct kref *kref)
{
struct iio_dma_buffer_block *block = container_of(kref,
struct iio_dma_buffer_block, kref);
+ struct iio_dma_buffer_queue *queue = block->queue;
- WARN_ON(block->state != IIO_BLOCK_STATE_DEAD);
+ WARN_ON(block->fileio && block->state != IIO_BLOCK_STATE_DEAD);
- dma_free_coherent(block->queue->dev, PAGE_ALIGN(block->size),
- block->vaddr, block->phys_addr);
+ if (block->fileio) {
+ dma_free_coherent(queue->dev, PAGE_ALIGN(block->size),
+ block->vaddr, block->phys_addr);
+ } else {
+ atomic_dec(&queue->num_dmabufs);
+ }
- iio_buffer_put(&block->queue->buffer);
+ iio_buffer_put(&queue->buffer);
kfree(block);
}
@@ -163,7 +172,7 @@ static struct iio_dma_buffer_queue *iio_buffer_to_queue(struct iio_buffer *buf)
}
static struct iio_dma_buffer_block *iio_dma_buffer_alloc_block(
- struct iio_dma_buffer_queue *queue, size_t size)
+ struct iio_dma_buffer_queue *queue, size_t size, bool fileio)
{
struct iio_dma_buffer_block *block;
@@ -171,13 +180,16 @@ static struct iio_dma_buffer_block *iio_dma_buffer_alloc_block(
if (!block)
return NULL;
- block->vaddr = dma_alloc_coherent(queue->dev, PAGE_ALIGN(size),
- &block->phys_addr, GFP_KERNEL);
- if (!block->vaddr) {
- kfree(block);
- return NULL;
+ if (fileio) {
+ block->vaddr = dma_alloc_coherent(queue->dev, PAGE_ALIGN(size),
+ &block->phys_addr, GFP_KERNEL);
+ if (!block->vaddr) {
+ kfree(block);
+ return NULL;
+ }
}
+ block->fileio = fileio;
block->size = size;
block->state = IIO_BLOCK_STATE_DONE;
block->queue = queue;
@@ -186,6 +198,9 @@ static struct iio_dma_buffer_block *iio_dma_buffer_alloc_block(
iio_buffer_get(&queue->buffer);
+ if (!fileio)
+ atomic_inc(&queue->num_dmabufs);
+
return block;
}
@@ -206,13 +221,21 @@ void iio_dma_buffer_block_done(struct iio_dma_buffer_block *block)
{
struct iio_dma_buffer_queue *queue = block->queue;
unsigned long flags;
+ bool cookie;
+
+ cookie = dma_fence_begin_signalling();
spin_lock_irqsave(&queue->list_lock, flags);
_iio_dma_buffer_block_done(block);
spin_unlock_irqrestore(&queue->list_lock, flags);
+ if (!block->fileio)
+ iio_buffer_signal_dmabuf_done(block->fence, 0);
+
iio_buffer_block_put_atomic(block);
wake_up_interruptible_poll(&queue->buffer.pollq, EPOLLIN | EPOLLRDNORM);
+
+ dma_fence_end_signalling(cookie);
}
EXPORT_SYMBOL_GPL(iio_dma_buffer_block_done);
@@ -231,17 +254,27 @@ void iio_dma_buffer_block_list_abort(struct iio_dma_buffer_queue *queue,
{
struct iio_dma_buffer_block *block, *_block;
unsigned long flags;
+ bool cookie;
+
+ cookie = dma_fence_begin_signalling();
spin_lock_irqsave(&queue->list_lock, flags);
list_for_each_entry_safe(block, _block, list, head) {
list_del(&block->head);
block->bytes_used = 0;
_iio_dma_buffer_block_done(block);
+
+ if (!block->fileio)
+ iio_buffer_signal_dmabuf_done(block->fence, -EINTR);
iio_buffer_block_put_atomic(block);
}
spin_unlock_irqrestore(&queue->list_lock, flags);
+ if (queue->fileio.enabled)
+ queue->fileio.enabled = false;
+
wake_up_interruptible_poll(&queue->buffer.pollq, EPOLLIN | EPOLLRDNORM);
+ dma_fence_end_signalling(cookie);
}
EXPORT_SYMBOL_GPL(iio_dma_buffer_block_list_abort);
@@ -261,6 +294,16 @@ static bool iio_dma_block_reusable(struct iio_dma_buffer_block *block)
}
}
+static bool iio_dma_buffer_can_use_fileio(struct iio_dma_buffer_queue *queue)
+{
+ /*
+ * Note that queue->num_dmabufs cannot increase while the queue is
+ * locked, it can only decrease, so it does not race against
+ * iio_dma_buffer_alloc_block().
+ */
+ return queue->fileio.enabled || !atomic_read(&queue->num_dmabufs);
+}
+
/**
* iio_dma_buffer_request_update() - DMA buffer request_update callback
* @buffer: The buffer which to request an update
@@ -287,6 +330,12 @@ int iio_dma_buffer_request_update(struct iio_buffer *buffer)
mutex_lock(&queue->lock);
+ queue->fileio.enabled = iio_dma_buffer_can_use_fileio(queue);
+
+ /* If DMABUFs were created, disable fileio interface */
+ if (!queue->fileio.enabled)
+ goto out_unlock;
+
/* Allocations are page aligned */
if (PAGE_ALIGN(queue->fileio.block_size) == PAGE_ALIGN(size))
try_reuse = true;
@@ -327,7 +376,7 @@ int iio_dma_buffer_request_update(struct iio_buffer *buffer)
}
if (!block) {
- block = iio_dma_buffer_alloc_block(queue, size);
+ block = iio_dma_buffer_alloc_block(queue, size, true);
if (!block) {
ret = -ENOMEM;
goto out_unlock;
@@ -384,8 +433,12 @@ static void iio_dma_buffer_submit_block(struct iio_dma_buffer_queue *queue,
block->state = IIO_BLOCK_STATE_ACTIVE;
iio_buffer_block_get(block);
+
ret = queue->ops->submit(queue, block);
if (ret) {
+ if (!block->fileio)
+ iio_buffer_signal_dmabuf_done(block->fence, ret);
+
/*
* This is a bit of a problem and there is not much we can do
* other then wait for the buffer to be disabled and re-enabled
@@ -588,6 +641,112 @@ size_t iio_dma_buffer_data_available(struct iio_buffer *buf)
}
EXPORT_SYMBOL_GPL(iio_dma_buffer_data_available);
+struct iio_dma_buffer_block *
+iio_dma_buffer_attach_dmabuf(struct iio_buffer *buffer,
+ struct dma_buf_attachment *attach)
+{
+ struct iio_dma_buffer_queue *queue = iio_buffer_to_queue(buffer);
+ struct iio_dma_buffer_block *block;
+
+ guard(mutex)(&queue->lock);
+
+ /*
+ * If the buffer is enabled and in fileio mode new blocks can't be
+ * allocated.
+ */
+ if (queue->fileio.enabled)
+ return ERR_PTR(-EBUSY);
+
+ block = iio_dma_buffer_alloc_block(queue, attach->dmabuf->size, false);
+ if (!block)
+ return ERR_PTR(-ENOMEM);
+
+ block->attach = attach;
+
+ /* Free memory that might be in use for fileio mode */
+ iio_dma_buffer_fileio_free(queue);
+
+ return block;
+}
+EXPORT_SYMBOL_GPL(iio_dma_buffer_attach_dmabuf);
+
+void iio_dma_buffer_detach_dmabuf(struct iio_buffer *buffer,
+ struct iio_dma_buffer_block *block)
+{
+ block->state = IIO_BLOCK_STATE_DEAD;
+ iio_buffer_block_put_atomic(block);
+}
+EXPORT_SYMBOL_GPL(iio_dma_buffer_detach_dmabuf);
+
+static int iio_dma_can_enqueue_block(struct iio_dma_buffer_block *block)
+{
+ struct iio_dma_buffer_queue *queue = block->queue;
+
+ /* If in fileio mode buffers can't be enqueued. */
+ if (queue->fileio.enabled)
+ return -EBUSY;
+
+ switch (block->state) {
+ case IIO_BLOCK_STATE_QUEUED:
+ return -EPERM;
+ case IIO_BLOCK_STATE_ACTIVE:
+ case IIO_BLOCK_STATE_DEAD:
+ return -EBUSY;
+ case IIO_BLOCK_STATE_DONE:
+ break;
+ }
+
+ return 0;
+}
+
+int iio_dma_buffer_enqueue_dmabuf(struct iio_buffer *buffer,
+ struct iio_dma_buffer_block *block,
+ struct dma_fence *fence,
+ struct sg_table *sgt,
+ size_t size, bool cyclic)
+{
+ struct iio_dma_buffer_queue *queue = iio_buffer_to_queue(buffer);
+ bool cookie;
+ int ret;
+
+ WARN_ON(!mutex_is_locked(&queue->lock));
+
+ cookie = dma_fence_begin_signalling();
+
+ ret = iio_dma_can_enqueue_block(block);
+ if (ret < 0)
+ goto out_end_signalling;
+
+ block->bytes_used = size;
+ block->cyclic = cyclic;
+ block->sg_table = sgt;
+ block->fence = fence;
+
+ iio_dma_buffer_enqueue(queue, block);
+
+out_end_signalling:
+ dma_fence_end_signalling(cookie);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(iio_dma_buffer_enqueue_dmabuf);
+
+void iio_dma_buffer_lock_queue(struct iio_buffer *buffer)
+{
+ struct iio_dma_buffer_queue *queue = iio_buffer_to_queue(buffer);
+
+ mutex_lock(&queue->lock);
+}
+EXPORT_SYMBOL_GPL(iio_dma_buffer_lock_queue);
+
+void iio_dma_buffer_unlock_queue(struct iio_buffer *buffer)
+{
+ struct iio_dma_buffer_queue *queue = iio_buffer_to_queue(buffer);
+
+ mutex_unlock(&queue->lock);
+}
+EXPORT_SYMBOL_GPL(iio_dma_buffer_unlock_queue);
+
/**
* iio_dma_buffer_set_bytes_per_datum() - DMA buffer set_bytes_per_datum callback
* @buffer: Buffer to set the bytes-per-datum for
diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h
index 18d3702fa95d..b62ff2a3f554 100644
--- a/include/linux/iio/buffer-dma.h
+++ b/include/linux/iio/buffer-dma.h
@@ -7,6 +7,7 @@
#ifndef __INDUSTRIALIO_DMA_BUFFER_H__
#define __INDUSTRIALIO_DMA_BUFFER_H__
+#include <linux/atomic.h>
#include <linux/list.h>
#include <linux/kref.h>
#include <linux/spinlock.h>
@@ -16,6 +17,9 @@
struct iio_dma_buffer_queue;
struct iio_dma_buffer_ops;
struct device;
+struct dma_buf_attachment;
+struct dma_fence;
+struct sg_table;
/**
* enum iio_block_state - State of a struct iio_dma_buffer_block
@@ -41,6 +45,8 @@ enum iio_block_state {
* @queue: Parent DMA buffer queue
* @kref: kref used to manage the lifetime of block
* @state: Current state of the block
+ * @cyclic: True if this is a cyclic buffer
+ * @fileio: True if this buffer is used for fileio mode
*/
struct iio_dma_buffer_block {
/* May only be accessed by the owner of the block */
@@ -63,6 +69,14 @@ struct iio_dma_buffer_block {
* queue->list_lock if the block is not owned by the core.
*/
enum iio_block_state state;
+
+ bool cyclic;
+ bool fileio;
+
+ struct dma_buf_attachment *attach;
+ struct sg_table *sg_table;
+
+ struct dma_fence *fence;
};
/**
@@ -72,6 +86,7 @@ struct iio_dma_buffer_block {
* @pos: Read offset in the active block
* @block_size: Size of each block
* @next_dequeue: index of next block that will be dequeued
+ * @enabled: Whether the buffer is operating in fileio mode
*/
struct iio_dma_buffer_queue_fileio {
struct iio_dma_buffer_block *blocks[2];
@@ -80,6 +95,7 @@ struct iio_dma_buffer_queue_fileio {
size_t block_size;
unsigned int next_dequeue;
+ bool enabled;
};
/**
@@ -95,6 +111,7 @@ struct iio_dma_buffer_queue_fileio {
* the DMA controller
* @incoming: List of buffers on the incoming queue
* @active: Whether the buffer is currently active
+ * @num_dmabufs: Total number of DMABUFs attached to this queue
* @fileio: FileIO state
*/
struct iio_dma_buffer_queue {
@@ -107,6 +124,7 @@ struct iio_dma_buffer_queue {
struct list_head incoming;
bool active;
+ atomic_t num_dmabufs;
struct iio_dma_buffer_queue_fileio fileio;
};
@@ -142,4 +160,17 @@ int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue,
void iio_dma_buffer_exit(struct iio_dma_buffer_queue *queue);
void iio_dma_buffer_release(struct iio_dma_buffer_queue *queue);
+struct iio_dma_buffer_block *
+iio_dma_buffer_attach_dmabuf(struct iio_buffer *buffer,
+ struct dma_buf_attachment *attach);
+void iio_dma_buffer_detach_dmabuf(struct iio_buffer *buffer,
+ struct iio_dma_buffer_block *block);
+int iio_dma_buffer_enqueue_dmabuf(struct iio_buffer *buffer,
+ struct iio_dma_buffer_block *block,
+ struct dma_fence *fence,
+ struct sg_table *sgt,
+ size_t size, bool cyclic);
+void iio_dma_buffer_lock_queue(struct iio_buffer *buffer);
+void iio_dma_buffer_unlock_queue(struct iio_buffer *buffer);
+
#endif
--
2.43.0
Document the new DMABUF based API.
Signed-off-by: Paul Cercueil <[email protected]>
Signed-off-by: Nuno Sa <[email protected]>
---
v2: - Explicitly state that the new interface is optional and is
not implemented by all drivers.
- The IOCTLs can now only be called on the buffer FD returned by
IIO_BUFFER_GET_FD_IOCTL.
- Move the page up a bit in the index since it is core stuff and not
driver-specific.
v3: Update the documentation to reflect the new API.
v5: Use description lists for the documentation of the three new IOCTLs
instead of abusing subsections.
v8: Renamed dmabuf_api.rst -> iio_dmabuf_api.rst, and updated index.rst
whose format changed in iio/togreg.
---
Documentation/iio/iio_dmabuf_api.rst | 54 ++++++++++++++++++++++++++++
Documentation/iio/index.rst | 1 +
2 files changed, 55 insertions(+)
create mode 100644 Documentation/iio/iio_dmabuf_api.rst
diff --git a/Documentation/iio/iio_dmabuf_api.rst b/Documentation/iio/iio_dmabuf_api.rst
new file mode 100644
index 000000000000..1cd6cd51a582
--- /dev/null
+++ b/Documentation/iio/iio_dmabuf_api.rst
@@ -0,0 +1,54 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===================================
+High-speed DMABUF interface for IIO
+===================================
+
+1. Overview
+===========
+
+The Industrial I/O subsystem supports access to buffers through a
+file-based interface, with read() and write() access calls through the
+IIO device's dev node.
+
+It additionally supports a DMABUF based interface, where the userspace
+can attach DMABUF objects (externally created) to a IIO buffer, and
+subsequently use them for data transfers.
+
+A userspace application can then use this interface to share DMABUF
+objects between several interfaces, allowing it to transfer data in a
+zero-copy fashion, for instance between IIO and the USB stack.
+
+The userspace application can also memory-map the DMABUF objects, and
+access the sample data directly. The advantage of doing this vs. the
+read() interface is that it avoids an extra copy of the data between the
+kernel and userspace. This is particularly useful for high-speed devices
+which produce several megabytes or even gigabytes of data per second.
+It does however increase the userspace-kernelspace synchronization
+overhead, as the DMA_BUF_SYNC_START and DMA_BUF_SYNC_END IOCTLs have to
+be used for data integrity.
+
+2. User API
+===========
+
+As part of this interface, three new IOCTLs have been added. These three
+IOCTLs have to be performed on the IIO buffer's file descriptor,
+obtained using the IIO_BUFFER_GET_FD_IOCTL() ioctl.
+
+ ``IIO_BUFFER_DMABUF_ATTACH_IOCTL(int)``
+ Attach the DMABUF object, identified by its file descriptor, to the
+ IIO buffer. Returns zero on success, and a negative errno value on
+ error.
+
+ ``IIO_BUFFER_DMABUF_DETACH_IOCTL(int)``
+ Detach the given DMABUF object, identified by its file descriptor,
+ from the IIO buffer. Returns zero on success, and a negative errno
+ value on error.
+
+ Note that closing the IIO buffer's file descriptor will
+ automatically detach all previously attached DMABUF objects.
+
+ ``IIO_BUFFER_DMABUF_ENQUEUE_IOCTL(struct iio_dmabuf *iio_dmabuf)``
+ Enqueue a previously attached DMABUF object to the buffer queue.
+ Enqueued DMABUFs will be read from (if output buffer) or written to
+ (if input buffer) as long as the buffer is enabled.
diff --git a/Documentation/iio/index.rst b/Documentation/iio/index.rst
index 30b09eefe75e..feb50b61aac0 100644
--- a/Documentation/iio/index.rst
+++ b/Documentation/iio/index.rst
@@ -9,6 +9,7 @@ Industrial I/O
iio_configfs
iio_devbuf
+ iio_dmabuf_api
Industrial I/O Kernel Drivers
=============================
--
2.43.0
On Sun, 10 Mar 2024 13:48:29 +0100
Paul Cercueil <[email protected]> wrote:
> Hi Jonathan,
>
> Here's the final-er version of the IIO DMABUF patchset.
>
> This v9 fixes the few issues reported by the kernel bot.
>
> This was based on next-20240308.
>
> Changelog:
>
> - [3/6]:
> - Select DMA_SHARED_BUFFER in Kconfig
> - Remove useless forward declaration of 'iio_dma_fence'
> - Import DMA-BUF namespace
> - Add missing __user tag to iio_buffer_detach_dmabuf() argument
Merge window is coming to an end, and whilst we obviously have
plenty of time left in this cycle, I would like to get this queued
up fairly early so any issues can shake out and the various series
that will build on this can progress.
Hopefully Paul has addressed all remaining comments.
So I'm looking for RB or Ack for DMABUF and dmaengine parts from
respective reviewers/maintainers.
Thanks
Jonathan
>
> Cheers,
> -Paul
>
> Paul Cercueil (6):
> dmaengine: Add API function dmaengine_prep_peripheral_dma_vec()
> dmaengine: dma-axi-dmac: Implement device_prep_peripheral_dma_vec
> iio: core: Add new DMABUF interface infrastructure
> iio: buffer-dma: Enable support for DMABUFs
> iio: buffer-dmaengine: Support new DMABUF based userspace API
> Documentation: iio: Document high-speed DMABUF based API
>
> Documentation/iio/iio_dmabuf_api.rst | 54 ++
> Documentation/iio/index.rst | 1 +
> drivers/dma/dma-axi-dmac.c | 40 ++
> drivers/iio/Kconfig | 1 +
> drivers/iio/buffer/industrialio-buffer-dma.c | 181 ++++++-
> .../buffer/industrialio-buffer-dmaengine.c | 59 ++-
> drivers/iio/industrialio-buffer.c | 462 ++++++++++++++++++
> include/linux/dmaengine.h | 27 +
> include/linux/iio/buffer-dma.h | 31 ++
> include/linux/iio/buffer_impl.h | 30 ++
> include/uapi/linux/iio/buffer.h | 22 +
> 11 files changed, 891 insertions(+), 17 deletions(-)
> create mode 100644 Documentation/iio/iio_dmabuf_api.rst
>
On 3/10/24 7:48 AM, Paul Cercueil wrote:
> Add the necessary infrastructure to the IIO core to support a new
> optional DMABUF based interface.
>
> With this new interface, DMABUF objects (externally created) can be
> attached to a IIO buffer, and subsequently used for data transfer.
>
> A userspace application can then use this interface to share DMABUF
> objects between several interfaces, allowing it to transfer data in a
> zero-copy fashion, for instance between IIO and the USB stack.
>
> The userspace application can also memory-map the DMABUF objects, and
> access the sample data directly. The advantage of doing this vs. the
> read() interface is that it avoids an extra copy of the data between the
> kernel and userspace. This is particularly userful for high-speed
> devices which produce several megabytes or even gigabytes of data per
> second.
>
> As part of the interface, 3 new IOCTLs have been added:
>
> IIO_BUFFER_DMABUF_ATTACH_IOCTL(int fd):
> Attach the DMABUF object identified by the given file descriptor to the
> buffer.
>
> IIO_BUFFER_DMABUF_DETACH_IOCTL(int fd):
> Detach the DMABUF object identified by the given file descriptor from
> the buffer. Note that closing the IIO buffer's file descriptor will
> automatically detach all previously attached DMABUF objects.
>
> IIO_BUFFER_DMABUF_ENQUEUE_IOCTL(struct iio_dmabuf *):
> Request a data transfer to/from the given DMABUF object. Its file
> descriptor, as well as the transfer size and flags are provided in the
> "iio_dmabuf" structure.
>
> These three IOCTLs have to be performed on the IIO buffer's file
> descriptor, obtained using the IIO_BUFFER_GET_FD_IOCTL() ioctl.
>
> Signed-off-by: Paul Cercueil <[email protected]>
> Signed-off-by: Nuno Sa <[email protected]>
>
> ---
> v2: Only allow the new IOCTLs on the buffer FD created with
> IIO_BUFFER_GET_FD_IOCTL().
>
> v3: - Get rid of the old IOCTLs. The IIO subsystem does not create or
> manage DMABUFs anymore, and only attaches/detaches externally
> created DMABUFs.
> - Add IIO_BUFFER_DMABUF_CYCLIC to the supported flags.
>
> v5: - Use dev_err() instead of pr_err()
> - Inline to_iio_dma_fence()
> - Add comment to explain why we unref twice when detaching dmabuf
> - Remove TODO comment. It is actually safe to free the file's
> private data even when transfers are still pending because it
> won't be accessed.
> - Fix documentation of new fields in struct iio_buffer_access_funcs
> - iio_dma_resv_lock() does not need to be exported, make it static
>
> v6: - Remove dead code in iio_dma_resv_lock()
> - Fix non-block actually blocking
> - Cache dma_buf_attachment instead of mapping/unmapping it for every
> transfer
> - Return -EINVAL instead of IIO_IOCTL_UNHANDLED for unknown ioctl
> - Make .block_enqueue() callback take a dma_fence pointer, which
> will be passed to iio_buffer_signal_dmabuf_done() instead of the
> dma_buf_attachment; and remove the backpointer from the priv
> structure to the dma_fence.
> - Use dma_fence_begin/end_signalling in the dma_fence critical
> sections
> - Unref dma_fence and dma_buf_attachment in worker, because they
> might try to lock the dma_resv, which would deadlock.
> - Add buffer ops to lock/unlock the queue. This is motivated by the
> fact that once the dma_fence has been installed, we cannot lock
> anything anymore - so the queue must be locked before the
> dma_fence is installed.
> - Use 'long retl' variable to handle the return value of
> dma_resv_wait_timeout()
> - Protect dmabufs list access with a mutex
> - Rework iio_buffer_find_attachment() to use the internal dmabufs
> list, instead of messing with dmabufs private data.
> - Add an atomically-increasing sequence number for fences
>
> v8 - Fix swapped fence direction
> - Simplify fence wait mechanism
> - Remove "Buffer closed with active transfers" print, as it was dead
> code
> - Un-export iio_buffer_dmabuf_{get,put}. They are not used anywhere
> else so they can even be static.
> - Prevent attaching already-attached DMABUFs
>
> v9: - Select DMA_SHARED_BUFFER in Kconfig
> - Remove useless forward declaration of 'iio_dma_fence'
> - Import DMA-BUF namespace
> - Add missing __user tag to iio_buffer_detach_dmabuf() argument
> ---
> drivers/iio/Kconfig | 1 +
> drivers/iio/industrialio-buffer.c | 462 ++++++++++++++++++++++++++++++
> include/linux/iio/buffer_impl.h | 30 ++
> include/uapi/linux/iio/buffer.h | 22 ++
> 4 files changed, 515 insertions(+)
>
> diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig
> index 9c351ffc7bed..661127aed2f9 100644
> --- a/drivers/iio/Kconfig
> +++ b/drivers/iio/Kconfig
> @@ -14,6 +14,7 @@ if IIO
>
> config IIO_BUFFER
> bool "Enable buffer support within IIO"
> + select DMA_SHARED_BUFFER
> help
> Provide core support for various buffer based data
> acquisition methods.
> diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c
> index b581a7e80566..a987654f82fc 100644
> --- a/drivers/iio/industrialio-buffer.c
> +++ b/drivers/iio/industrialio-buffer.c
> @@ -9,14 +9,19 @@
> * - Better memory allocation techniques?
> * - Alternative access techniques?
> */
> +#include <linux/atomic.h>
> #include <linux/anon_inodes.h>
> #include <linux/kernel.h>
> #include <linux/export.h>
> #include <linux/device.h>
> +#include <linux/dma-buf.h>
> +#include <linux/dma-fence.h>
> +#include <linux/dma-resv.h>
> #include <linux/file.h>
> #include <linux/fs.h>
> #include <linux/cdev.h>
> #include <linux/slab.h>
> +#include <linux/mm.h>
> #include <linux/poll.h>
> #include <linux/sched/signal.h>
>
> @@ -28,6 +33,32 @@
> #include <linux/iio/buffer.h>
> #include <linux/iio/buffer_impl.h>
>
> +#define DMABUF_ENQUEUE_TIMEOUT_MS 5000
> +
> +MODULE_IMPORT_NS(DMA_BUF);
> +
> +struct iio_dmabuf_priv {
> + struct list_head entry;
> + struct kref ref;
> +
> + struct iio_buffer *buffer;
> + struct iio_dma_buffer_block *block;
> +
> + u64 context;
> + spinlock_t lock;
> +
> + struct dma_buf_attachment *attach;
> + struct sg_table *sgt;
> + enum dma_data_direction dir;
> + atomic_t seqno;
> +};
> +
> +struct iio_dma_fence {
> + struct dma_fence base;
> + struct iio_dmabuf_priv *priv;
> + struct work_struct work;
> +};
> +
> static const char * const iio_endian_prefix[] = {
> [IIO_BE] = "be",
> [IIO_LE] = "le",
> @@ -332,6 +363,8 @@ void iio_buffer_init(struct iio_buffer *buffer)
> {
> INIT_LIST_HEAD(&buffer->demux_list);
> INIT_LIST_HEAD(&buffer->buffer_list);
> + INIT_LIST_HEAD(&buffer->dmabufs);
> + mutex_init(&buffer->dmabufs_mutex);
> init_waitqueue_head(&buffer->pollq);
> kref_init(&buffer->ref);
> if (!buffer->watermark)
> @@ -1519,14 +1552,57 @@ static void iio_buffer_unregister_legacy_sysfs_groups(struct iio_dev *indio_dev)
> kfree(iio_dev_opaque->legacy_scan_el_group.attrs);
> }
>
> +static void iio_buffer_dmabuf_release(struct kref *ref)
> +{
> + struct iio_dmabuf_priv *priv = container_of(ref, struct iio_dmabuf_priv, ref);
> + struct dma_buf_attachment *attach = priv->attach;
> + struct iio_buffer *buffer = priv->buffer;
> + struct dma_buf *dmabuf = attach->dmabuf;
> +
> + dma_resv_lock(dmabuf->resv, NULL);
> + dma_buf_unmap_attachment(attach, priv->sgt, priv->dir);
> + dma_resv_unlock(dmabuf->resv);
> +
> + buffer->access->detach_dmabuf(buffer, priv->block);
> +
> + dma_buf_detach(attach->dmabuf, attach);
> + dma_buf_put(dmabuf);
> + kfree(priv);
> +}
> +
> +static void iio_buffer_dmabuf_get(struct dma_buf_attachment *attach)
> +{
> + struct iio_dmabuf_priv *priv = attach->importer_priv;
> +
> + kref_get(&priv->ref);
> +}
> +
> +static void iio_buffer_dmabuf_put(struct dma_buf_attachment *attach)
> +{
> + struct iio_dmabuf_priv *priv = attach->importer_priv;
> +
> + kref_put(&priv->ref, iio_buffer_dmabuf_release);
> +}
> +
> static int iio_buffer_chrdev_release(struct inode *inode, struct file *filep)
> {
> struct iio_dev_buffer_pair *ib = filep->private_data;
> struct iio_dev *indio_dev = ib->indio_dev;
> struct iio_buffer *buffer = ib->buffer;
> + struct iio_dmabuf_priv *priv, *tmp;
>
> wake_up(&buffer->pollq);
>
> + mutex_lock(&buffer->dmabufs_mutex);
> +
> + /* Close all attached DMABUFs */
> + list_for_each_entry_safe(priv, tmp, &buffer->dmabufs, entry) {
> + list_del_init(&priv->entry);
> + iio_buffer_dmabuf_put(priv->attach);
> + }
> +
> + mutex_unlock(&buffer->dmabufs_mutex);
> +
> kfree(ib);
> clear_bit(IIO_BUSY_BIT_POS, &buffer->flags);
> iio_device_put(indio_dev);
> @@ -1534,11 +1610,396 @@ static int iio_buffer_chrdev_release(struct inode *inode, struct file *filep)
> return 0;
> }
>
> +static int iio_dma_resv_lock(struct dma_buf *dmabuf, bool nonblock)
> +{
> + if (!nonblock)
> + return dma_resv_lock_interruptible(dmabuf->resv, NULL);
> +
> + if (!dma_resv_trylock(dmabuf->resv))
> + return -EBUSY;
> +
> + return 0;
> +}
> +
> +static struct dma_buf_attachment *
> +iio_buffer_find_attachment(struct iio_dev_buffer_pair *ib,
> + struct dma_buf *dmabuf, bool nonblock)
> +{
> + struct device *dev = ib->indio_dev->dev.parent;
> + struct iio_buffer *buffer = ib->buffer;
> + struct dma_buf_attachment *attach = NULL;
> + struct iio_dmabuf_priv *priv;
> +
> + mutex_lock(&buffer->dmabufs_mutex);
> +
> + list_for_each_entry(priv, &buffer->dmabufs, entry) {
> + if (priv->attach->dev == dev
> + && priv->attach->dmabuf == dmabuf) {
> + attach = priv->attach;
> + break;
> + }
> + }
> +
> + if (attach)
> + iio_buffer_dmabuf_get(attach);
> +
> + mutex_unlock(&buffer->dmabufs_mutex);
> +
> + return attach ?: ERR_PTR(-EPERM);
> +}
> +
> +static int iio_buffer_attach_dmabuf(struct iio_dev_buffer_pair *ib,
> + int __user *user_fd, bool nonblock)
> +{
> + struct iio_dev *indio_dev = ib->indio_dev;
> + struct iio_buffer *buffer = ib->buffer;
> + struct dma_buf_attachment *attach;
> + struct iio_dmabuf_priv *priv, *each;
> + struct dma_buf *dmabuf;
> + int err, fd;
> +
> + if (!buffer->access->attach_dmabuf
> + || !buffer->access->detach_dmabuf
> + || !buffer->access->enqueue_dmabuf)
> + return -EPERM;
> +
> + if (copy_from_user(&fd, user_fd, sizeof(fd)))
> + return -EFAULT;
> +
> + priv = kzalloc(sizeof(*priv), GFP_KERNEL);
> + if (!priv)
> + return -ENOMEM;
> +
> + spin_lock_init(&priv->lock);
> + priv->context = dma_fence_context_alloc(1);
> +
> + dmabuf = dma_buf_get(fd);
> + if (IS_ERR(dmabuf)) {
> + err = PTR_ERR(dmabuf);
> + goto err_free_priv;
> + }
> +
> + attach = dma_buf_attach(dmabuf, indio_dev->dev.parent);
> + if (IS_ERR(attach)) {
> + err = PTR_ERR(attach);
> + goto err_dmabuf_put;
> + }
> +
> + err = iio_dma_resv_lock(dmabuf, nonblock);
> + if (err)
> + goto err_dmabuf_detach;
> +
> + priv->dir = buffer->direction == IIO_BUFFER_DIRECTION_IN
> + ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
> +
> + priv->sgt = dma_buf_map_attachment(attach, priv->dir);
Part of the fundamental design of DMABUF is the ability for all
users of a buffer to attach to the buffer before any user maps that
buffer. This allows an exporter to do constraint solving based
on all the attached buffers at map time to select the best backing
memory.
I know none of the exporters do that right now, probably due to
most of the importers doing what you do here: attach then immediately
map. This prevents the split between attach and map from being useful.
I'd recommend only doing the dma_buf_map_attachment() later when you
use the buffer, maybe part of enqueue_dmabuf() step below. Then unmap()
it after you are done with it, not only when detaching.
As this change will not affect the UAPI (which only deals with
"attach" ioctl), then this comment should not be seen as a blocker
for taking this series. We should be able to make this change later,
but just something to think about.
Andrew
> + if (IS_ERR(priv->sgt)) {
> + err = PTR_ERR(priv->sgt);
> + dev_err(&indio_dev->dev, "Unable to map attachment: %d\n", err);
> + goto err_resv_unlock;
> + }
> +
> + kref_init(&priv->ref);
> + priv->buffer = buffer;
> + priv->attach = attach;
> + attach->importer_priv = priv;
> +
> + priv->block = buffer->access->attach_dmabuf(buffer, attach);
> + if (IS_ERR(priv->block)) {
> + err = PTR_ERR(priv->block);
> + goto err_dmabuf_unmap_attachment;
> + }
> +
> + dma_resv_unlock(dmabuf->resv);
> +
> + mutex_lock(&buffer->dmabufs_mutex);
> +
> + /*
> + * Check whether we already have an attachment for this driver/DMABUF
> + * combo. If we do, refuse to attach.
> + */
> + list_for_each_entry(each, &buffer->dmabufs, entry) {
> + if (each->attach->dev == indio_dev->dev.parent
> + && each->attach->dmabuf == dmabuf) {
> + /*
> + * We unlocked the reservation object, so going through
> + * the cleanup code would mean re-locking it first.
> + * At this stage it is simpler to free the attachment
> + * using iio_buffer_dma_put().
> + */
> + mutex_unlock(&buffer->dmabufs_mutex);
> + iio_buffer_dmabuf_put(attach);
> + return -EBUSY;
> + }
> + }
> +
> + /* Otherwise, add the new attachment to our dmabufs list. */
> + list_add(&priv->entry, &buffer->dmabufs);
> + mutex_unlock(&buffer->dmabufs_mutex);
> +
> + return 0;
> +
> +err_dmabuf_unmap_attachment:
> + dma_buf_unmap_attachment(attach, priv->sgt, priv->dir);
> +err_resv_unlock:
> + dma_resv_unlock(dmabuf->resv);
> +err_dmabuf_detach:
> + dma_buf_detach(dmabuf, attach);
> +err_dmabuf_put:
> + dma_buf_put(dmabuf);
> +err_free_priv:
> + kfree(priv);
> +
> + return err;
> +}
> +
> +static int iio_buffer_detach_dmabuf(struct iio_dev_buffer_pair *ib,
> + int __user *user_req, bool nonblock)
> +{
> + struct iio_buffer *buffer = ib->buffer;
> + struct iio_dev *indio_dev = ib->indio_dev;
> + struct iio_dmabuf_priv *priv;
> + struct dma_buf *dmabuf;
> + int dmabuf_fd, ret = -EPERM;
> +
> + if (copy_from_user(&dmabuf_fd, user_req, sizeof(dmabuf_fd)))
> + return -EFAULT;
> +
> + dmabuf = dma_buf_get(dmabuf_fd);
> + if (IS_ERR(dmabuf))
> + return PTR_ERR(dmabuf);
> +
> + mutex_lock(&buffer->dmabufs_mutex);
> +
> + list_for_each_entry(priv, &buffer->dmabufs, entry) {
> + if (priv->attach->dev == indio_dev->dev.parent
> + && priv->attach->dmabuf == dmabuf) {
> + list_del(&priv->entry);
> +
> + /* Unref the reference from iio_buffer_attach_dmabuf() */
> + iio_buffer_dmabuf_put(priv->attach);
> + ret = 0;
> + break;
> + }
> + }
> +
> + mutex_unlock(&buffer->dmabufs_mutex);
> + dma_buf_put(dmabuf);
> +
> + return ret;
> +}
> +
> +static const char *
> +iio_buffer_dma_fence_get_driver_name(struct dma_fence *fence)
> +{
> + return "iio";
> +}
> +
> +static void iio_buffer_dma_fence_release(struct dma_fence *fence)
> +{
> + struct iio_dma_fence *iio_fence =
> + container_of(fence, struct iio_dma_fence, base);
> +
> + kfree(iio_fence);
> +}
> +
> +static const struct dma_fence_ops iio_buffer_dma_fence_ops = {
> + .get_driver_name = iio_buffer_dma_fence_get_driver_name,
> + .get_timeline_name = iio_buffer_dma_fence_get_driver_name,
> + .release = iio_buffer_dma_fence_release,
> +};
> +
> +static int iio_buffer_enqueue_dmabuf(struct iio_dev_buffer_pair *ib,
> + struct iio_dmabuf __user *iio_dmabuf_req,
> + bool nonblock)
> +{
> + struct iio_buffer *buffer = ib->buffer;
> + struct iio_dmabuf iio_dmabuf;
> + struct dma_buf_attachment *attach;
> + struct iio_dmabuf_priv *priv;
> + struct iio_dma_fence *fence;
> + struct dma_buf *dmabuf;
> + unsigned long timeout;
> + bool cookie, cyclic, dma_to_ram;
> + long retl;
> + u32 seqno;
> + int ret;
> +
> + if (copy_from_user(&iio_dmabuf, iio_dmabuf_req, sizeof(iio_dmabuf)))
> + return -EFAULT;
> +
> + if (iio_dmabuf.flags & ~IIO_BUFFER_DMABUF_SUPPORTED_FLAGS)
> + return -EINVAL;
> +
> + cyclic = iio_dmabuf.flags & IIO_BUFFER_DMABUF_CYCLIC;
> +
> + /* Cyclic flag is only supported on output buffers */
> + if (cyclic && buffer->direction != IIO_BUFFER_DIRECTION_OUT)
> + return -EINVAL;
> +
> + dmabuf = dma_buf_get(iio_dmabuf.fd);
> + if (IS_ERR(dmabuf))
> + return PTR_ERR(dmabuf);
> +
> + if (!iio_dmabuf.bytes_used || iio_dmabuf.bytes_used > dmabuf->size) {
> + ret = -EINVAL;
> + goto err_dmabuf_put;
> + }
> +
> + attach = iio_buffer_find_attachment(ib, dmabuf, nonblock);
> + if (IS_ERR(attach)) {
> + ret = PTR_ERR(attach);
> + goto err_dmabuf_put;
> + }
> +
> + priv = attach->importer_priv;
> +
> + fence = kmalloc(sizeof(*fence), GFP_KERNEL);
> + if (!fence) {
> + ret = -ENOMEM;
> + goto err_attachment_put;
> + }
> +
> + fence->priv = priv;
> +
> + seqno = atomic_add_return(1, &priv->seqno);
> +
> + /*
> + * The transfers are guaranteed to be processed in the order they are
> + * enqueued, so we can use a simple incrementing sequence number for
> + * the dma_fence.
> + */
> + dma_fence_init(&fence->base, &iio_buffer_dma_fence_ops,
> + &priv->lock, priv->context, seqno);
> +
> + ret = iio_dma_resv_lock(dmabuf, nonblock);
> + if (ret)
> + goto err_fence_put;
> +
> + timeout = nonblock ? 0 : msecs_to_jiffies(DMABUF_ENQUEUE_TIMEOUT_MS);
> + dma_to_ram = buffer->direction == IIO_BUFFER_DIRECTION_IN;
> +
> + /* Make sure we don't have writers */
> + retl = dma_resv_wait_timeout(dmabuf->resv,
> + dma_resv_usage_rw(dma_to_ram),
> + true, timeout);
> + if (retl == 0)
> + retl = -EBUSY;
> + if (retl < 0) {
> + ret = (int)retl;
> + goto err_resv_unlock;
> + }
> +
> + if (buffer->access->lock_queue)
> + buffer->access->lock_queue(buffer);
> +
> + ret = dma_resv_reserve_fences(dmabuf->resv, 1);
> + if (ret)
> + goto err_queue_unlock;
> +
> + dma_resv_add_fence(dmabuf->resv, &fence->base,
> + dma_to_ram ? DMA_RESV_USAGE_WRITE : DMA_RESV_USAGE_READ);
> + dma_resv_unlock(dmabuf->resv);
> +
> + cookie = dma_fence_begin_signalling();
> +
> + ret = buffer->access->enqueue_dmabuf(buffer, priv->block, &fence->base,
> + priv->sgt, iio_dmabuf.bytes_used,
> + cyclic);
> + if (ret) {
> + /*
> + * DMABUF enqueue failed, but we already added the fence.
> + * Signal the error through the fence completion mechanism.
> + */
> + iio_buffer_signal_dmabuf_done(&fence->base, ret);
> + }
> +
> + if (buffer->access->unlock_queue)
> + buffer->access->unlock_queue(buffer);
> +
> + dma_fence_end_signalling(cookie);
> + dma_buf_put(dmabuf);
> +
> + return ret;
> +
> +err_queue_unlock:
> + if (buffer->access->unlock_queue)
> + buffer->access->unlock_queue(buffer);
> +err_resv_unlock:
> + dma_resv_unlock(dmabuf->resv);
> +err_fence_put:
> + dma_fence_put(&fence->base);
> +err_attachment_put:
> + iio_buffer_dmabuf_put(attach);
> +err_dmabuf_put:
> + dma_buf_put(dmabuf);
> +
> + return ret;
> +}
> +
> +static void iio_buffer_cleanup(struct work_struct *work)
> +{
> + struct iio_dma_fence *fence =
> + container_of(work, struct iio_dma_fence, work);
> + struct iio_dmabuf_priv *priv = fence->priv;
> + struct dma_buf_attachment *attach = priv->attach;
> +
> + dma_fence_put(&fence->base);
> + iio_buffer_dmabuf_put(attach);
> +}
> +
> +void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int ret)
> +{
> + struct iio_dma_fence *iio_fence =
> + container_of(fence, struct iio_dma_fence, base);
> + bool cookie = dma_fence_begin_signalling();
> +
> + /*
> + * Get a reference to the fence, so that it's not freed as soon as
> + * it's signaled.
> + */
> + dma_fence_get(fence);
> +
> + fence->error = ret;
> + dma_fence_signal(fence);
> + dma_fence_end_signalling(cookie);
> +
> + /*
> + * The fence will be unref'd in iio_buffer_cleanup.
> + * It can't be done here, as the unref functions might try to lock the
> + * resv object, which can deadlock.
> + */
> + INIT_WORK(&iio_fence->work, iio_buffer_cleanup);
> + schedule_work(&iio_fence->work);
> +}
> +EXPORT_SYMBOL_GPL(iio_buffer_signal_dmabuf_done);
> +
> +static long iio_buffer_chrdev_ioctl(struct file *filp,
> + unsigned int cmd, unsigned long arg)
> +{
> + struct iio_dev_buffer_pair *ib = filp->private_data;
> + void __user *_arg = (void __user *)arg;
> + bool nonblock = filp->f_flags & O_NONBLOCK;
> +
> + switch (cmd) {
> + case IIO_BUFFER_DMABUF_ATTACH_IOCTL:
> + return iio_buffer_attach_dmabuf(ib, _arg, nonblock);
> + case IIO_BUFFER_DMABUF_DETACH_IOCTL:
> + return iio_buffer_detach_dmabuf(ib, _arg, nonblock);
> + case IIO_BUFFER_DMABUF_ENQUEUE_IOCTL:
> + return iio_buffer_enqueue_dmabuf(ib, _arg, nonblock);
> + default:
> + return -EINVAL;
> + }
> +}
> +
> static const struct file_operations iio_buffer_chrdev_fileops = {
> .owner = THIS_MODULE,
> .llseek = noop_llseek,
> .read = iio_buffer_read,
> .write = iio_buffer_write,
> + .unlocked_ioctl = iio_buffer_chrdev_ioctl,
> + .compat_ioctl = compat_ptr_ioctl,
> .poll = iio_buffer_poll,
> .release = iio_buffer_chrdev_release,
> };
> @@ -1953,6 +2414,7 @@ static void iio_buffer_release(struct kref *ref)
> {
> struct iio_buffer *buffer = container_of(ref, struct iio_buffer, ref);
>
> + mutex_destroy(&buffer->dmabufs_mutex);
> buffer->access->release(buffer);
> }
>
> diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h
> index 89c3fd7c29ca..1a221c1d7736 100644
> --- a/include/linux/iio/buffer_impl.h
> +++ b/include/linux/iio/buffer_impl.h
> @@ -9,8 +9,12 @@
> #include <uapi/linux/iio/buffer.h>
> #include <linux/iio/buffer.h>
>
> +struct dma_buf_attachment;
> +struct dma_fence;
> struct iio_dev;
> +struct iio_dma_buffer_block;
> struct iio_buffer;
> +struct sg_table;
>
> /**
> * INDIO_BUFFER_FLAG_FIXED_WATERMARK - Watermark level of the buffer can not be
> @@ -39,6 +43,13 @@ struct iio_buffer;
> * device stops sampling. Calles are balanced with @enable.
> * @release: called when the last reference to the buffer is dropped,
> * should free all resources allocated by the buffer.
> + * @attach_dmabuf: called from userspace via ioctl to attach one external
> + * DMABUF.
> + * @detach_dmabuf: called from userspace via ioctl to detach one previously
> + * attached DMABUF.
> + * @enqueue_dmabuf: called from userspace via ioctl to queue this DMABUF
> + * object to this buffer. Requires a valid DMABUF fd, that
> + * was previouly attached to this buffer.
> * @modes: Supported operating modes by this buffer type
> * @flags: A bitmask combination of INDIO_BUFFER_FLAG_*
> *
> @@ -68,6 +79,17 @@ struct iio_buffer_access_funcs {
>
> void (*release)(struct iio_buffer *buffer);
>
> + struct iio_dma_buffer_block * (*attach_dmabuf)(struct iio_buffer *buffer,
> + struct dma_buf_attachment *attach);
> + void (*detach_dmabuf)(struct iio_buffer *buffer,
> + struct iio_dma_buffer_block *block);
> + int (*enqueue_dmabuf)(struct iio_buffer *buffer,
> + struct iio_dma_buffer_block *block,
> + struct dma_fence *fence, struct sg_table *sgt,
> + size_t size, bool cyclic);
> + void (*lock_queue)(struct iio_buffer *buffer);
> + void (*unlock_queue)(struct iio_buffer *buffer);
> +
> unsigned int modes;
> unsigned int flags;
> };
> @@ -136,6 +158,12 @@ struct iio_buffer {
>
> /* @ref: Reference count of the buffer. */
> struct kref ref;
> +
> + /* @dmabufs: List of DMABUF attachments */
> + struct list_head dmabufs; /* P: dmabufs_mutex */
> +
> + /* @dmabufs_mutex: Protects dmabufs */
> + struct mutex dmabufs_mutex;
> };
>
> /**
> @@ -159,6 +187,8 @@ void iio_buffer_init(struct iio_buffer *buffer);
> struct iio_buffer *iio_buffer_get(struct iio_buffer *buffer);
> void iio_buffer_put(struct iio_buffer *buffer);
>
> +void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int ret);
> +
> #else /* CONFIG_IIO_BUFFER */
>
> static inline void iio_buffer_get(struct iio_buffer *buffer) {}
> diff --git a/include/uapi/linux/iio/buffer.h b/include/uapi/linux/iio/buffer.h
> index 13939032b3f6..c666aa95e532 100644
> --- a/include/uapi/linux/iio/buffer.h
> +++ b/include/uapi/linux/iio/buffer.h
> @@ -5,6 +5,28 @@
> #ifndef _UAPI_IIO_BUFFER_H_
> #define _UAPI_IIO_BUFFER_H_
>
> +#include <linux/types.h>
> +
> +/* Flags for iio_dmabuf.flags */
> +#define IIO_BUFFER_DMABUF_CYCLIC (1 << 0)
> +#define IIO_BUFFER_DMABUF_SUPPORTED_FLAGS 0x00000001
> +
> +/**
> + * struct iio_dmabuf - Descriptor for a single IIO DMABUF object
> + * @fd: file descriptor of the DMABUF object
> + * @flags: one or more IIO_BUFFER_DMABUF_* flags
> + * @bytes_used: number of bytes used in this DMABUF for the data transfer.
> + * Should generally be set to the DMABUF's size.
> + */
> +struct iio_dmabuf {
> + __u32 fd;
> + __u32 flags;
> + __u64 bytes_used;
> +};
> +
> #define IIO_BUFFER_GET_FD_IOCTL _IOWR('i', 0x91, int)
> +#define IIO_BUFFER_DMABUF_ATTACH_IOCTL _IOW('i', 0x92, int)
> +#define IIO_BUFFER_DMABUF_DETACH_IOCTL _IOW('i', 0x93, int)
> +#define IIO_BUFFER_DMABUF_ENQUEUE_IOCTL _IOW('i', 0x94, struct iio_dmabuf)
>
> #endif /* _UAPI_IIO_BUFFER_H_ */
Hi Andrew,
Le mercredi 27 mars 2024 à 12:21 -0500, Andrew Davis a écrit :
> On 3/10/24 7:48 AM, Paul Cercueil wrote:
> > Add the necessary infrastructure to the IIO core to support a new
> > optional DMABUF based interface.
> >
> > With this new interface, DMABUF objects (externally created) can be
> > attached to a IIO buffer, and subsequently used for data transfer.
> >
> > A userspace application can then use this interface to share DMABUF
> > objects between several interfaces, allowing it to transfer data in
> > a
> > zero-copy fashion, for instance between IIO and the USB stack.
> >
> > The userspace application can also memory-map the DMABUF objects,
> > and
> > access the sample data directly. The advantage of doing this vs.
> > the
> > read() interface is that it avoids an extra copy of the data
> > between the
> > kernel and userspace. This is particularly userful for high-speed
> > devices which produce several megabytes or even gigabytes of data
> > per
> > second.
> >
> > As part of the interface, 3 new IOCTLs have been added:
> >
> > IIO_BUFFER_DMABUF_ATTACH_IOCTL(int fd):
> > Attach the DMABUF object identified by the given file descriptor
> > to the
> > buffer.
> >
> > IIO_BUFFER_DMABUF_DETACH_IOCTL(int fd):
> > Detach the DMABUF object identified by the given file descriptor
> > from
> > the buffer. Note that closing the IIO buffer's file descriptor
> > will
> > automatically detach all previously attached DMABUF objects.
> >
> > IIO_BUFFER_DMABUF_ENQUEUE_IOCTL(struct iio_dmabuf *):
> > Request a data transfer to/from the given DMABUF object. Its file
> > descriptor, as well as the transfer size and flags are provided
> > in the
> > "iio_dmabuf" structure.
> >
> > These three IOCTLs have to be performed on the IIO buffer's file
> > descriptor, obtained using the IIO_BUFFER_GET_FD_IOCTL() ioctl.
> >
> > Signed-off-by: Paul Cercueil <[email protected]>
> > Signed-off-by: Nuno Sa <[email protected]>
> >
> > ---
> > v2: Only allow the new IOCTLs on the buffer FD created with
> > IIO_BUFFER_GET_FD_IOCTL().
> >
> > v3: - Get rid of the old IOCTLs. The IIO subsystem does not create
> > or
> > manage DMABUFs anymore, and only attaches/detaches externally
> > created DMABUFs.
> > - Add IIO_BUFFER_DMABUF_CYCLIC to the supported flags.
> >
> > v5: - Use dev_err() instead of pr_err()
> > - Inline to_iio_dma_fence()
> > - Add comment to explain why we unref twice when detaching
> > dmabuf
> > - Remove TODO comment. It is actually safe to free the file's
> > private data even when transfers are still pending because
> > it
> > won't be accessed.
> > - Fix documentation of new fields in struct
> > iio_buffer_access_funcs
> > - iio_dma_resv_lock() does not need to be exported, make it
> > static
> >
> > v6: - Remove dead code in iio_dma_resv_lock()
> > - Fix non-block actually blocking
> > - Cache dma_buf_attachment instead of mapping/unmapping it for
> > every
> > transfer
> > - Return -EINVAL instead of IIO_IOCTL_UNHANDLED for unknown
> > ioctl
> > - Make .block_enqueue() callback take a dma_fence pointer,
> > which
> > will be passed to iio_buffer_signal_dmabuf_done() instead of
> > the
> > dma_buf_attachment; and remove the backpointer from the priv
> > structure to the dma_fence.
> > - Use dma_fence_begin/end_signalling in the dma_fence critical
> > sections
> > - Unref dma_fence and dma_buf_attachment in worker, because
> > they
> > might try to lock the dma_resv, which would deadlock.
> > - Add buffer ops to lock/unlock the queue. This is motivated
> > by the
> > fact that once the dma_fence has been installed, we cannot
> > lock
> > anything anymore - so the queue must be locked before the
> > dma_fence is installed.
> > - Use 'long retl' variable to handle the return value of
> > dma_resv_wait_timeout()
> > - Protect dmabufs list access with a mutex
> > - Rework iio_buffer_find_attachment() to use the internal
> > dmabufs
> > list, instead of messing with dmabufs private data.
> > - Add an atomically-increasing sequence number for fences
> >
> > v8 - Fix swapped fence direction
> > - Simplify fence wait mechanism
> > - Remove "Buffer closed with active transfers" print, as it
> > was dead
> > code
> > - Un-export iio_buffer_dmabuf_{get,put}. They are not used
> > anywhere
> > else so they can even be static.
> > - Prevent attaching already-attached DMABUFs
> >
> > v9: - Select DMA_SHARED_BUFFER in Kconfig
> > - Remove useless forward declaration of 'iio_dma_fence'
> > - Import DMA-BUF namespace
> > - Add missing __user tag to iio_buffer_detach_dmabuf()
> > argument
> > ---
> > drivers/iio/Kconfig | 1 +
> > drivers/iio/industrialio-buffer.c | 462
> > ++++++++++++++++++++++++++++++
> > include/linux/iio/buffer_impl.h | 30 ++
> > include/uapi/linux/iio/buffer.h | 22 ++
> > 4 files changed, 515 insertions(+)
> >
> > diff --git a/drivers/iio/Kconfig b/drivers/iio/Kconfig
> > index 9c351ffc7bed..661127aed2f9 100644
> > --- a/drivers/iio/Kconfig
> > +++ b/drivers/iio/Kconfig
> > @@ -14,6 +14,7 @@ if IIO
> >
> > config IIO_BUFFER
> > bool "Enable buffer support within IIO"
> > + select DMA_SHARED_BUFFER
> > help
> > Provide core support for various buffer based data
> > acquisition methods.
> > diff --git a/drivers/iio/industrialio-buffer.c
> > b/drivers/iio/industrialio-buffer.c
> > index b581a7e80566..a987654f82fc 100644
> > --- a/drivers/iio/industrialio-buffer.c
> > +++ b/drivers/iio/industrialio-buffer.c
> > @@ -9,14 +9,19 @@
> > * - Better memory allocation techniques?
> > * - Alternative access techniques?
> > */
> > +#include <linux/atomic.h>
> > #include <linux/anon_inodes.h>
> > #include <linux/kernel.h>
> > #include <linux/export.h>
> > #include <linux/device.h>
> > +#include <linux/dma-buf.h>
> > +#include <linux/dma-fence.h>
> > +#include <linux/dma-resv.h>
> > #include <linux/file.h>
> > #include <linux/fs.h>
> > #include <linux/cdev.h>
> > #include <linux/slab.h>
> > +#include <linux/mm.h>
> > #include <linux/poll.h>
> > #include <linux/sched/signal.h>
> >
> > @@ -28,6 +33,32 @@
> > #include <linux/iio/buffer.h>
> > #include <linux/iio/buffer_impl.h>
> >
> > +#define DMABUF_ENQUEUE_TIMEOUT_MS 5000
> > +
> > +MODULE_IMPORT_NS(DMA_BUF);
> > +
> > +struct iio_dmabuf_priv {
> > + struct list_head entry;
> > + struct kref ref;
> > +
> > + struct iio_buffer *buffer;
> > + struct iio_dma_buffer_block *block;
> > +
> > + u64 context;
> > + spinlock_t lock;
> > +
> > + struct dma_buf_attachment *attach;
> > + struct sg_table *sgt;
> > + enum dma_data_direction dir;
> > + atomic_t seqno;
> > +};
> > +
> > +struct iio_dma_fence {
> > + struct dma_fence base;
> > + struct iio_dmabuf_priv *priv;
> > + struct work_struct work;
> > +};
> > +
> > static const char * const iio_endian_prefix[] = {
> > [IIO_BE] = "be",
> > [IIO_LE] = "le",
> > @@ -332,6 +363,8 @@ void iio_buffer_init(struct iio_buffer *buffer)
> > {
> > INIT_LIST_HEAD(&buffer->demux_list);
> > INIT_LIST_HEAD(&buffer->buffer_list);
> > + INIT_LIST_HEAD(&buffer->dmabufs);
> > + mutex_init(&buffer->dmabufs_mutex);
> > init_waitqueue_head(&buffer->pollq);
> > kref_init(&buffer->ref);
> > if (!buffer->watermark)
> > @@ -1519,14 +1552,57 @@ static void
> > iio_buffer_unregister_legacy_sysfs_groups(struct iio_dev
> > *indio_dev)
> > kfree(iio_dev_opaque->legacy_scan_el_group.attrs);
> > }
> >
> > +static void iio_buffer_dmabuf_release(struct kref *ref)
> > +{
> > + struct iio_dmabuf_priv *priv = container_of(ref, struct
> > iio_dmabuf_priv, ref);
> > + struct dma_buf_attachment *attach = priv->attach;
> > + struct iio_buffer *buffer = priv->buffer;
> > + struct dma_buf *dmabuf = attach->dmabuf;
> > +
> > + dma_resv_lock(dmabuf->resv, NULL);
> > + dma_buf_unmap_attachment(attach, priv->sgt, priv->dir);
> > + dma_resv_unlock(dmabuf->resv);
> > +
> > + buffer->access->detach_dmabuf(buffer, priv->block);
> > +
> > + dma_buf_detach(attach->dmabuf, attach);
> > + dma_buf_put(dmabuf);
> > + kfree(priv);
> > +}
> > +
> > +static void iio_buffer_dmabuf_get(struct dma_buf_attachment
> > *attach)
> > +{
> > + struct iio_dmabuf_priv *priv = attach->importer_priv;
> > +
> > + kref_get(&priv->ref);
> > +}
> > +
> > +static void iio_buffer_dmabuf_put(struct dma_buf_attachment
> > *attach)
> > +{
> > + struct iio_dmabuf_priv *priv = attach->importer_priv;
> > +
> > + kref_put(&priv->ref, iio_buffer_dmabuf_release);
> > +}
> > +
> > static int iio_buffer_chrdev_release(struct inode *inode, struct
> > file *filep)
> > {
> > struct iio_dev_buffer_pair *ib = filep->private_data;
> > struct iio_dev *indio_dev = ib->indio_dev;
> > struct iio_buffer *buffer = ib->buffer;
> > + struct iio_dmabuf_priv *priv, *tmp;
> >
> > wake_up(&buffer->pollq);
> >
> > + mutex_lock(&buffer->dmabufs_mutex);
> > +
> > + /* Close all attached DMABUFs */
> > + list_for_each_entry_safe(priv, tmp, &buffer->dmabufs,
> > entry) {
> > + list_del_init(&priv->entry);
> > + iio_buffer_dmabuf_put(priv->attach);
> > + }
> > +
> > + mutex_unlock(&buffer->dmabufs_mutex);
> > +
> > kfree(ib);
> > clear_bit(IIO_BUSY_BIT_POS, &buffer->flags);
> > iio_device_put(indio_dev);
> > @@ -1534,11 +1610,396 @@ static int
> > iio_buffer_chrdev_release(struct inode *inode, struct file *filep)
> > return 0;
> > }
> >
> > +static int iio_dma_resv_lock(struct dma_buf *dmabuf, bool
> > nonblock)
> > +{
> > + if (!nonblock)
> > + return dma_resv_lock_interruptible(dmabuf->resv,
> > NULL);
> > +
> > + if (!dma_resv_trylock(dmabuf->resv))
> > + return -EBUSY;
> > +
> > + return 0;
> > +}
> > +
> > +static struct dma_buf_attachment *
> > +iio_buffer_find_attachment(struct iio_dev_buffer_pair *ib,
> > + struct dma_buf *dmabuf, bool nonblock)
> > +{
> > + struct device *dev = ib->indio_dev->dev.parent;
> > + struct iio_buffer *buffer = ib->buffer;
> > + struct dma_buf_attachment *attach = NULL;
> > + struct iio_dmabuf_priv *priv;
> > +
> > + mutex_lock(&buffer->dmabufs_mutex);
> > +
> > + list_for_each_entry(priv, &buffer->dmabufs, entry) {
> > + if (priv->attach->dev == dev
> > + && priv->attach->dmabuf == dmabuf) {
> > + attach = priv->attach;
> > + break;
> > + }
> > + }
> > +
> > + if (attach)
> > + iio_buffer_dmabuf_get(attach);
> > +
> > + mutex_unlock(&buffer->dmabufs_mutex);
> > +
> > + return attach ?: ERR_PTR(-EPERM);
> > +}
> > +
> > +static int iio_buffer_attach_dmabuf(struct iio_dev_buffer_pair
> > *ib,
> > + int __user *user_fd, bool
> > nonblock)
> > +{
> > + struct iio_dev *indio_dev = ib->indio_dev;
> > + struct iio_buffer *buffer = ib->buffer;
> > + struct dma_buf_attachment *attach;
> > + struct iio_dmabuf_priv *priv, *each;
> > + struct dma_buf *dmabuf;
> > + int err, fd;
> > +
> > + if (!buffer->access->attach_dmabuf
> > + || !buffer->access->detach_dmabuf
> > + || !buffer->access->enqueue_dmabuf)
> > + return -EPERM;
> > +
> > + if (copy_from_user(&fd, user_fd, sizeof(fd)))
> > + return -EFAULT;
> > +
> > + priv = kzalloc(sizeof(*priv), GFP_KERNEL);
> > + if (!priv)
> > + return -ENOMEM;
> > +
> > + spin_lock_init(&priv->lock);
> > + priv->context = dma_fence_context_alloc(1);
> > +
> > + dmabuf = dma_buf_get(fd);
> > + if (IS_ERR(dmabuf)) {
> > + err = PTR_ERR(dmabuf);
> > + goto err_free_priv;
> > + }
> > +
> > + attach = dma_buf_attach(dmabuf, indio_dev->dev.parent);
> > + if (IS_ERR(attach)) {
> > + err = PTR_ERR(attach);
> > + goto err_dmabuf_put;
> > + }
> > +
> > + err = iio_dma_resv_lock(dmabuf, nonblock);
> > + if (err)
> > + goto err_dmabuf_detach;
> > +
> > + priv->dir = buffer->direction == IIO_BUFFER_DIRECTION_IN
> > + ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
> > +
> > + priv->sgt = dma_buf_map_attachment(attach, priv->dir);
>
> Part of the fundamental design of DMABUF is the ability for all
> users of a buffer to attach to the buffer before any user maps that
> buffer. This allows an exporter to do constraint solving based
> on all the attached buffers at map time to select the best backing
> memory.
>
> I know none of the exporters do that right now, probably due to
> most of the importers doing what you do here: attach then immediately
> map. This prevents the split between attach and map from being
> useful.
>
> I'd recommend only doing the dma_buf_map_attachment() later when you
> use the buffer, maybe part of enqueue_dmabuf() step below. Then
> unmap()
> it after you are done with it, not only when detaching.
>
> As this change will not affect the UAPI (which only deals with
> "attach" ioctl), then this comment should not be seen as a blocker
> for taking this series. We should be able to make this change later,
> but just something to think about.
Both the dma-heap implementations and udmabuf will sync/flush the CPU
cache in their map/unmap callbacks (as they call dma_{un}map_sgtable()
with attrs == 0). In my case not only it is unnecessary, it also
destroys performance, especially with big DMABUFs backed by small pages
as they'll be sync'd one by one.
For that reason (as well as convenience) I'm caching the attachment.
> Andrew
Cheers,
-Paul
>
> > + if (IS_ERR(priv->sgt)) {
> > + err = PTR_ERR(priv->sgt);
> > + dev_err(&indio_dev->dev, "Unable to map
> > attachment: %d\n", err);
> > + goto err_resv_unlock;
> > + }
> > +
> > + kref_init(&priv->ref);
> > + priv->buffer = buffer;
> > + priv->attach = attach;
> > + attach->importer_priv = priv;
> > +
> > + priv->block = buffer->access->attach_dmabuf(buffer,
> > attach);
> > + if (IS_ERR(priv->block)) {
> > + err = PTR_ERR(priv->block);
> > + goto err_dmabuf_unmap_attachment;
> > + }
> > +
> > + dma_resv_unlock(dmabuf->resv);
> > +
> > + mutex_lock(&buffer->dmabufs_mutex);
> > +
> > + /*
> > + * Check whether we already have an attachment for this
> > driver/DMABUF
> > + * combo. If we do, refuse to attach.
> > + */
> > + list_for_each_entry(each, &buffer->dmabufs, entry) {
> > + if (each->attach->dev == indio_dev->dev.parent
> > + && each->attach->dmabuf == dmabuf) {
> > + /*
> > + * We unlocked the reservation object, so
> > going through
> > + * the cleanup code would mean re-locking
> > it first.
> > + * At this stage it is simpler to free the
> > attachment
> > + * using iio_buffer_dma_put().
> > + */
> > + mutex_unlock(&buffer->dmabufs_mutex);
> > + iio_buffer_dmabuf_put(attach);
> > + return -EBUSY;
> > + }
> > + }
> > +
> > + /* Otherwise, add the new attachment to our dmabufs list.
> > */
> > + list_add(&priv->entry, &buffer->dmabufs);
> > + mutex_unlock(&buffer->dmabufs_mutex);
> > +
> > + return 0;
> > +
> > +err_dmabuf_unmap_attachment:
> > + dma_buf_unmap_attachment(attach, priv->sgt, priv->dir);
> > +err_resv_unlock:
> > + dma_resv_unlock(dmabuf->resv);
> > +err_dmabuf_detach:
> > + dma_buf_detach(dmabuf, attach);
> > +err_dmabuf_put:
> > + dma_buf_put(dmabuf);
> > +err_free_priv:
> > + kfree(priv);
> > +
> > + return err;
> > +}
> > +
> > +static int iio_buffer_detach_dmabuf(struct iio_dev_buffer_pair
> > *ib,
> > + int __user *user_req, bool
> > nonblock)
> > +{
> > + struct iio_buffer *buffer = ib->buffer;
> > + struct iio_dev *indio_dev = ib->indio_dev;
> > + struct iio_dmabuf_priv *priv;
> > + struct dma_buf *dmabuf;
> > + int dmabuf_fd, ret = -EPERM;
> > +
> > + if (copy_from_user(&dmabuf_fd, user_req,
> > sizeof(dmabuf_fd)))
> > + return -EFAULT;
> > +
> > + dmabuf = dma_buf_get(dmabuf_fd);
> > + if (IS_ERR(dmabuf))
> > + return PTR_ERR(dmabuf);
> > +
> > + mutex_lock(&buffer->dmabufs_mutex);
> > +
> > + list_for_each_entry(priv, &buffer->dmabufs, entry) {
> > + if (priv->attach->dev == indio_dev->dev.parent
> > + && priv->attach->dmabuf == dmabuf) {
> > + list_del(&priv->entry);
> > +
> > + /* Unref the reference from
> > iio_buffer_attach_dmabuf() */
> > + iio_buffer_dmabuf_put(priv->attach);
> > + ret = 0;
> > + break;
> > + }
> > + }
> > +
> > + mutex_unlock(&buffer->dmabufs_mutex);
> > + dma_buf_put(dmabuf);
> > +
> > + return ret;
> > +}
> > +
> > +static const char *
> > +iio_buffer_dma_fence_get_driver_name(struct dma_fence *fence)
> > +{
> > + return "iio";
> > +}
> > +
> > +static void iio_buffer_dma_fence_release(struct dma_fence *fence)
> > +{
> > + struct iio_dma_fence *iio_fence =
> > + container_of(fence, struct iio_dma_fence, base);
> > +
> > + kfree(iio_fence);
> > +}
> > +
> > +static const struct dma_fence_ops iio_buffer_dma_fence_ops = {
> > + .get_driver_name =
> > iio_buffer_dma_fence_get_driver_name,
> > + .get_timeline_name =
> > iio_buffer_dma_fence_get_driver_name,
> > + .release = iio_buffer_dma_fence_release,
> > +};
> > +
> > +static int iio_buffer_enqueue_dmabuf(struct iio_dev_buffer_pair
> > *ib,
> > + struct iio_dmabuf __user
> > *iio_dmabuf_req,
> > + bool nonblock)
> > +{
> > + struct iio_buffer *buffer = ib->buffer;
> > + struct iio_dmabuf iio_dmabuf;
> > + struct dma_buf_attachment *attach;
> > + struct iio_dmabuf_priv *priv;
> > + struct iio_dma_fence *fence;
> > + struct dma_buf *dmabuf;
> > + unsigned long timeout;
> > + bool cookie, cyclic, dma_to_ram;
> > + long retl;
> > + u32 seqno;
> > + int ret;
> > +
> > + if (copy_from_user(&iio_dmabuf, iio_dmabuf_req,
> > sizeof(iio_dmabuf)))
> > + return -EFAULT;
> > +
> > + if (iio_dmabuf.flags & ~IIO_BUFFER_DMABUF_SUPPORTED_FLAGS)
> > + return -EINVAL;
> > +
> > + cyclic = iio_dmabuf.flags & IIO_BUFFER_DMABUF_CYCLIC;
> > +
> > + /* Cyclic flag is only supported on output buffers */
> > + if (cyclic && buffer->direction !=
> > IIO_BUFFER_DIRECTION_OUT)
> > + return -EINVAL;
> > +
> > + dmabuf = dma_buf_get(iio_dmabuf.fd);
> > + if (IS_ERR(dmabuf))
> > + return PTR_ERR(dmabuf);
> > +
> > + if (!iio_dmabuf.bytes_used || iio_dmabuf.bytes_used >
> > dmabuf->size) {
> > + ret = -EINVAL;
> > + goto err_dmabuf_put;
> > + }
> > +
> > + attach = iio_buffer_find_attachment(ib, dmabuf, nonblock);
> > + if (IS_ERR(attach)) {
> > + ret = PTR_ERR(attach);
> > + goto err_dmabuf_put;
> > + }
> > +
> > + priv = attach->importer_priv;
> > +
> > + fence = kmalloc(sizeof(*fence), GFP_KERNEL);
> > + if (!fence) {
> > + ret = -ENOMEM;
> > + goto err_attachment_put;
> > + }
> > +
> > + fence->priv = priv;
> > +
> > + seqno = atomic_add_return(1, &priv->seqno);
> > +
> > + /*
> > + * The transfers are guaranteed to be processed in the
> > order they are
> > + * enqueued, so we can use a simple incrementing sequence
> > number for
> > + * the dma_fence.
> > + */
> > + dma_fence_init(&fence->base, &iio_buffer_dma_fence_ops,
> > + &priv->lock, priv->context, seqno);
> > +
> > + ret = iio_dma_resv_lock(dmabuf, nonblock);
> > + if (ret)
> > + goto err_fence_put;
> > +
> > + timeout = nonblock ? 0 :
> > msecs_to_jiffies(DMABUF_ENQUEUE_TIMEOUT_MS);
> > + dma_to_ram = buffer->direction == IIO_BUFFER_DIRECTION_IN;
> > +
> > + /* Make sure we don't have writers */
> > + retl = dma_resv_wait_timeout(dmabuf->resv,
> > +
> > dma_resv_usage_rw(dma_to_ram),
> > + true, timeout);
> > + if (retl == 0)
> > + retl = -EBUSY;
> > + if (retl < 0) {
> > + ret = (int)retl;
> > + goto err_resv_unlock;
> > + }
> > +
> > + if (buffer->access->lock_queue)
> > + buffer->access->lock_queue(buffer);
> > +
> > + ret = dma_resv_reserve_fences(dmabuf->resv, 1);
> > + if (ret)
> > + goto err_queue_unlock;
> > +
> > + dma_resv_add_fence(dmabuf->resv, &fence->base,
> > + dma_to_ram ? DMA_RESV_USAGE_WRITE :
> > DMA_RESV_USAGE_READ);
> > + dma_resv_unlock(dmabuf->resv);
> > +
> > + cookie = dma_fence_begin_signalling();
> > +
> > + ret = buffer->access->enqueue_dmabuf(buffer, priv->block,
> > &fence->base,
> > + priv->sgt,
> > iio_dmabuf.bytes_used,
> > + cyclic);
> > + if (ret) {
> > + /*
> > + * DMABUF enqueue failed, but we already added the
> > fence.
> > + * Signal the error through the fence completion
> > mechanism.
> > + */
> > + iio_buffer_signal_dmabuf_done(&fence->base, ret);
> > + }
> > +
> > + if (buffer->access->unlock_queue)
> > + buffer->access->unlock_queue(buffer);
> > +
> > + dma_fence_end_signalling(cookie);
> > + dma_buf_put(dmabuf);
> > +
> > + return ret;
> > +
> > +err_queue_unlock:
> > + if (buffer->access->unlock_queue)
> > + buffer->access->unlock_queue(buffer);
> > +err_resv_unlock:
> > + dma_resv_unlock(dmabuf->resv);
> > +err_fence_put:
> > + dma_fence_put(&fence->base);
> > +err_attachment_put:
> > + iio_buffer_dmabuf_put(attach);
> > +err_dmabuf_put:
> > + dma_buf_put(dmabuf);
> > +
> > + return ret;
> > +}
> > +
> > +static void iio_buffer_cleanup(struct work_struct *work)
> > +{
> > + struct iio_dma_fence *fence =
> > + container_of(work, struct iio_dma_fence, work);
> > + struct iio_dmabuf_priv *priv = fence->priv;
> > + struct dma_buf_attachment *attach = priv->attach;
> > +
> > + dma_fence_put(&fence->base);
> > + iio_buffer_dmabuf_put(attach);
> > +}
> > +
> > +void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int
> > ret)
> > +{
> > + struct iio_dma_fence *iio_fence =
> > + container_of(fence, struct iio_dma_fence, base);
> > + bool cookie = dma_fence_begin_signalling();
> > +
> > + /*
> > + * Get a reference to the fence, so that it's not freed as
> > soon as
> > + * it's signaled.
> > + */
> > + dma_fence_get(fence);
> > +
> > + fence->error = ret;
> > + dma_fence_signal(fence);
> > + dma_fence_end_signalling(cookie);
> > +
> > + /*
> > + * The fence will be unref'd in iio_buffer_cleanup.
> > + * It can't be done here, as the unref functions might try
> > to lock the
> > + * resv object, which can deadlock.
> > + */
> > + INIT_WORK(&iio_fence->work, iio_buffer_cleanup);
> > + schedule_work(&iio_fence->work);
> > +}
> > +EXPORT_SYMBOL_GPL(iio_buffer_signal_dmabuf_done);
> > +
> > +static long iio_buffer_chrdev_ioctl(struct file *filp,
> > + unsigned int cmd, unsigned
> > long arg)
> > +{
> > + struct iio_dev_buffer_pair *ib = filp->private_data;
> > + void __user *_arg = (void __user *)arg;
> > + bool nonblock = filp->f_flags & O_NONBLOCK;
> > +
> > + switch (cmd) {
> > + case IIO_BUFFER_DMABUF_ATTACH_IOCTL:
> > + return iio_buffer_attach_dmabuf(ib, _arg,
> > nonblock);
> > + case IIO_BUFFER_DMABUF_DETACH_IOCTL:
> > + return iio_buffer_detach_dmabuf(ib, _arg,
> > nonblock);
> > + case IIO_BUFFER_DMABUF_ENQUEUE_IOCTL:
> > + return iio_buffer_enqueue_dmabuf(ib, _arg,
> > nonblock);
> > + default:
> > + return -EINVAL;
> > + }
> > +}
> > +
> > static const struct file_operations iio_buffer_chrdev_fileops = {
> > .owner = THIS_MODULE,
> > .llseek = noop_llseek,
> > .read = iio_buffer_read,
> > .write = iio_buffer_write,
> > + .unlocked_ioctl = iio_buffer_chrdev_ioctl,
> > + .compat_ioctl = compat_ptr_ioctl,
> > .poll = iio_buffer_poll,
> > .release = iio_buffer_chrdev_release,
> > };
> > @@ -1953,6 +2414,7 @@ static void iio_buffer_release(struct kref
> > *ref)
> > {
> > struct iio_buffer *buffer = container_of(ref, struct
> > iio_buffer, ref);
> >
> > + mutex_destroy(&buffer->dmabufs_mutex);
> > buffer->access->release(buffer);
> > }
> >
> > diff --git a/include/linux/iio/buffer_impl.h
> > b/include/linux/iio/buffer_impl.h
> > index 89c3fd7c29ca..1a221c1d7736 100644
> > --- a/include/linux/iio/buffer_impl.h
> > +++ b/include/linux/iio/buffer_impl.h
> > @@ -9,8 +9,12 @@
> > #include <uapi/linux/iio/buffer.h>
> > #include <linux/iio/buffer.h>
> >
> > +struct dma_buf_attachment;
> > +struct dma_fence;
> > struct iio_dev;
> > +struct iio_dma_buffer_block;
> > struct iio_buffer;
> > +struct sg_table;
> >
> > /**
> > * INDIO_BUFFER_FLAG_FIXED_WATERMARK - Watermark level of the
> > buffer can not be
> > @@ -39,6 +43,13 @@ struct iio_buffer;
> > * device stops sampling. Calles are
> > balanced with @enable.
> > * @release: called when the last reference to the
> > buffer is dropped,
> > * should free all resources allocated by the
> > buffer.
> > + * @attach_dmabuf: called from userspace via ioctl to attach
> > one external
> > + * DMABUF.
> > + * @detach_dmabuf: called from userspace via ioctl to detach
> > one previously
> > + * attached DMABUF.
> > + * @enqueue_dmabuf: called from userspace via ioctl to queue
> > this DMABUF
> > + * object to this buffer. Requires a valid
> > DMABUF fd, that
> > + * was previouly attached to this buffer.
> > * @modes: Supported operating modes by this buffer
> > type
> > * @flags: A bitmask combination of
> > INDIO_BUFFER_FLAG_*
> > *
> > @@ -68,6 +79,17 @@ struct iio_buffer_access_funcs {
> >
> > void (*release)(struct iio_buffer *buffer);
> >
> > + struct iio_dma_buffer_block * (*attach_dmabuf)(struct
> > iio_buffer *buffer,
> > + struct
> > dma_buf_attachment *attach);
> > + void (*detach_dmabuf)(struct iio_buffer *buffer,
> > + struct iio_dma_buffer_block *block);
> > + int (*enqueue_dmabuf)(struct iio_buffer *buffer,
> > + struct iio_dma_buffer_block *block,
> > + struct dma_fence *fence, struct
> > sg_table *sgt,
> > + size_t size, bool cyclic);
> > + void (*lock_queue)(struct iio_buffer *buffer);
> > + void (*unlock_queue)(struct iio_buffer *buffer);
> > +
> > unsigned int modes;
> > unsigned int flags;
> > };
> > @@ -136,6 +158,12 @@ struct iio_buffer {
> >
> > /* @ref: Reference count of the buffer. */
> > struct kref ref;
> > +
> > + /* @dmabufs: List of DMABUF attachments */
> > + struct list_head dmabufs; /* P: dmabufs_mutex */
> > +
> > + /* @dmabufs_mutex: Protects dmabufs */
> > + struct mutex dmabufs_mutex;
> > };
> >
> > /**
> > @@ -159,6 +187,8 @@ void iio_buffer_init(struct iio_buffer
> > *buffer);
> > struct iio_buffer *iio_buffer_get(struct iio_buffer *buffer);
> > void iio_buffer_put(struct iio_buffer *buffer);
> >
> > +void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int
> > ret);
> > +
> > #else /* CONFIG_IIO_BUFFER */
> >
> > static inline void iio_buffer_get(struct iio_buffer *buffer) {}
> > diff --git a/include/uapi/linux/iio/buffer.h
> > b/include/uapi/linux/iio/buffer.h
> > index 13939032b3f6..c666aa95e532 100644
> > --- a/include/uapi/linux/iio/buffer.h
> > +++ b/include/uapi/linux/iio/buffer.h
> > @@ -5,6 +5,28 @@
> > #ifndef _UAPI_IIO_BUFFER_H_
> > #define _UAPI_IIO_BUFFER_H_
> >
> > +#include <linux/types.h>
> > +
> > +/* Flags for iio_dmabuf.flags */
> > +#define IIO_BUFFER_DMABUF_CYCLIC (1 << 0)
> > +#define IIO_BUFFER_DMABUF_SUPPORTED_FLAGS 0x00000001
> > +
> > +/**
> > + * struct iio_dmabuf - Descriptor for a single IIO DMABUF object
> > + * @fd: file descriptor of the DMABUF object
> > + * @flags: one or more IIO_BUFFER_DMABUF_* flags
> > + * @bytes_used: number of bytes used in this DMABUF for
> > the data transfer.
> > + * Should generally be set to the DMABUF's size.
> > + */
> > +struct iio_dmabuf {
> > + __u32 fd;
> > + __u32 flags;
> > + __u64 bytes_used;
> > +};
> > +
> > #define IIO_BUFFER_GET_FD_IOCTL _IOWR('i',
> > 0x91, int)
> > +#define IIO_BUFFER_DMABUF_ATTACH_IOCTL _IOW('i', 0x92,
> > int)
> > +#define IIO_BUFFER_DMABUF_DETACH_IOCTL _IOW('i', 0x93,
> > int)
> > +#define IIO_BUFFER_DMABUF_ENQUEUE_IOCTL _IOW('i',
> > 0x94, struct iio_dmabuf)
> >
> > #endif /* _UAPI_IIO_BUFFER_H_ */
On 10-03-24, 13:48, Paul Cercueil wrote:
> This function can be used to initiate a scatter-gather DMA transfer,
> where the address and size of each segment is located in one entry of
> the dma_vec array.
>
> The major difference with dmaengine_prep_slave_sg() is that it supports
> specifying the lengths of each DMA transfer; as trying to override the
> length of the transfer with dmaengine_prep_slave_sg() is a very tedious
> process. The introduction of a new API function is also justified by the
> fact that scatterlists are on their way out.
>
> Note that dmaengine_prep_interleaved_dma() is not helpful either in that
> case, as it assumes that the address of each segment will be higher than
> the one of the previous segment, which we just cannot guarantee in case
> of a scatter-gather transfer.
>
> Signed-off-by: Paul Cercueil <[email protected]>
> Signed-off-by: Nuno Sa <[email protected]>
>
> ---
> v3: New patch
>
> v5: Replace with function dmaengine_prep_slave_dma_vec(), and struct
> 'dma_vec'.
> Note that at some point we will need to support cyclic transfers
> using dmaengine_prep_slave_dma_vec(). Maybe with a new "flags"
> parameter to the function?
>
> v7:
> - Renamed *device_prep_slave_dma_vec() -> device_prep_peripheral_dma_vec();
> - Added a new flag parameter to the function as agreed between Paul
> and Vinod. I renamed the first parameter to prep_flags as it's supposed to
> be used (I think) with enum dma_ctrl_flags. I'm not really sure how that API
> can grow but I was thinking in just having a bool cyclic parameter (as the
> first intention of the flags is to support cyclic transfers) but ended up
> "respecting" the previously agreed approach.
> ---
> include/linux/dmaengine.h | 27 +++++++++++++++++++++++++++
> 1 file changed, 27 insertions(+)
>
> diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
> index 752dbde4cec1..856df8cd9a4e 100644
> --- a/include/linux/dmaengine.h
> +++ b/include/linux/dmaengine.h
> @@ -160,6 +160,16 @@ struct dma_interleaved_template {
> struct data_chunk sgl[];
> };
>
> +/**
> + * struct dma_vec - DMA vector
> + * @addr: Bus address of the start of the vector
> + * @len: Length in bytes of the DMA vector
> + */
> +struct dma_vec {
> + dma_addr_t addr;
> + size_t len;
> +};
> +
> /**
> * enum dma_ctrl_flags - DMA flags to augment operation preparation,
> * control completion, and communicate status.
> @@ -910,6 +920,10 @@ struct dma_device {
> struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)(
> struct dma_chan *chan, unsigned long flags);
>
> + struct dma_async_tx_descriptor *(*device_prep_peripheral_dma_vec)(
> + struct dma_chan *chan, const struct dma_vec *vecs,
> + size_t nents, enum dma_transfer_direction direction,
> + unsigned long prep_flags, 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,
> @@ -973,6 +987,19 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single(
> dir, flags, NULL);
> }
>
> +static inline struct dma_async_tx_descriptor *dmaengine_prep_peripheral_dma_vec(
> + struct dma_chan *chan, const struct dma_vec *vecs, size_t nents,
> + enum dma_transfer_direction dir, unsigned long prep_flags,
> + unsigned long flags)
> +{
> + if (!chan || !chan->device || !chan->device->device_prep_peripheral_dma_vec)
> + return NULL;
> +
> + return chan->device->device_prep_peripheral_dma_vec(chan, vecs, nents,
> + dir, prep_flags,
> + flags);
> +}
API looks good to me, thanks
Few nits though:
- Can we add kernel-doc for this new API please
- Also update the documentation adding this new api
- Lastly, we seem to have two flags, I know you have added a comment but
I dont seem to recall the discussion (looked at old threads for clue
as well), can you please remind me why we need both? And in your case,
what is the intended usage of these flags, i would prefer single
clean one...
--
~Vinod
Hi Vinod,
Le jeudi 28 mars 2024 à 11:53 +0530, Vinod Koul a écrit :
> On 10-03-24, 13:48, Paul Cercueil wrote:
> > This function can be used to initiate a scatter-gather DMA
> > transfer,
> > where the address and size of each segment is located in one entry
> > of
> > the dma_vec array.
> >
> > The major difference with dmaengine_prep_slave_sg() is that it
> > supports
> > specifying the lengths of each DMA transfer; as trying to override
> > the
> > length of the transfer with dmaengine_prep_slave_sg() is a very
> > tedious
> > process. The introduction of a new API function is also justified
> > by the
> > fact that scatterlists are on their way out.
> >
> > Note that dmaengine_prep_interleaved_dma() is not helpful either in
> > that
> > case, as it assumes that the address of each segment will be higher
> > than
> > the one of the previous segment, which we just cannot guarantee in
> > case
> > of a scatter-gather transfer.
> >
> > Signed-off-by: Paul Cercueil <[email protected]>
> > Signed-off-by: Nuno Sa <[email protected]>
> >
> > ---
> > v3: New patch
> >
> > v5: Replace with function dmaengine_prep_slave_dma_vec(), and
> > struct
> > 'dma_vec'.
> > Note that at some point we will need to support cyclic
> > transfers
> > using dmaengine_prep_slave_dma_vec(). Maybe with a new "flags"
> > parameter to the function?
> >
> > v7:
> > - Renamed *device_prep_slave_dma_vec() ->
> > device_prep_peripheral_dma_vec();
> > - Added a new flag parameter to the function as agreed between
> > Paul
> > and Vinod. I renamed the first parameter to prep_flags as it's
> > supposed to
> > be used (I think) with enum dma_ctrl_flags. I'm not really sure
> > how that API
> > can grow but I was thinking in just having a bool cyclic
> > parameter (as the
> > first intention of the flags is to support cyclic transfers)
> > but ended up
> > "respecting" the previously agreed approach.
> > ---
> > include/linux/dmaengine.h | 27 +++++++++++++++++++++++++++
> > 1 file changed, 27 insertions(+)
> >
> > diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
> > index 752dbde4cec1..856df8cd9a4e 100644
> > --- a/include/linux/dmaengine.h
> > +++ b/include/linux/dmaengine.h
> > @@ -160,6 +160,16 @@ struct dma_interleaved_template {
> > struct data_chunk sgl[];
> > };
> >
> > +/**
> > + * struct dma_vec - DMA vector
> > + * @addr: Bus address of the start of the vector
> > + * @len: Length in bytes of the DMA vector
> > + */
> > +struct dma_vec {
> > + dma_addr_t addr;
> > + size_t len;
> > +};
> > +
> > /**
> > * enum dma_ctrl_flags - DMA flags to augment operation
> > preparation,
> > * control completion, and communicate status.
> > @@ -910,6 +920,10 @@ struct dma_device {
> > struct dma_async_tx_descriptor
> > *(*device_prep_dma_interrupt)(
> > struct dma_chan *chan, unsigned long flags);
> >
> > + struct dma_async_tx_descriptor
> > *(*device_prep_peripheral_dma_vec)(
> > + struct dma_chan *chan, const struct dma_vec *vecs,
> > + size_t nents, enum dma_transfer_direction
> > direction,
> > + unsigned long prep_flags, 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,
> > @@ -973,6 +987,19 @@ static inline struct dma_async_tx_descriptor
> > *dmaengine_prep_slave_single(
> > dir, flags,
> > NULL);
> > }
> >
> > +static inline struct dma_async_tx_descriptor
> > *dmaengine_prep_peripheral_dma_vec(
> > + struct dma_chan *chan, const struct dma_vec *vecs, size_t
> > nents,
> > + enum dma_transfer_direction dir, unsigned long prep_flags,
> > + unsigned long flags)
> > +{
> > + if (!chan || !chan->device || !chan->device-
> > >device_prep_peripheral_dma_vec)
> > + return NULL;
> > +
> > + return chan->device->device_prep_peripheral_dma_vec(chan,
> > vecs, nents,
> > + dir,
> > prep_flags,
> > +
> > flags);
> > +}
>
> API looks good to me, thanks
> Few nits though:
> - Can we add kernel-doc for this new API please
> - Also update the documentation adding this new api
> - Lastly, we seem to have two flags, I know you have added a comment
> but
> I dont seem to recall the discussion (looked at old threads for
> clue
> as well), can you please remind me why we need both? And in your
> case,
> what is the intended usage of these flags, i would prefer single
> clean one...
>
The "prep_flags" is a mask of "enum dma_ctrl_flags".
The second "flags" was supposed to be specific to this function, and
was to future-proof the API as we eventually want to have a "cyclic"
flag, which would emulate a cyclic transfer by linking the SG hardware
descriptors accordingly.
However - I think we can already do that with DMA_PREP_REPEAT and
DMA_PREP_LOAD_EOT, right? So we can probably drop the second "flags".
Cheers,
-Paul
On 02-04-24, 13:31, Paul Cercueil wrote:
> Hi Vinod,
>
> Le jeudi 28 mars 2024 ? 11:53 +0530, Vinod Koul a ?crit?:
> > On 10-03-24, 13:48, Paul Cercueil wrote:
> > > This function can be used to initiate a scatter-gather DMA
> > > transfer,
> > > where the address and size of each segment is located in one entry
> > > of
> > > the dma_vec array.
> > >
> > > The major difference with dmaengine_prep_slave_sg() is that it
> > > supports
> > > specifying the lengths of each DMA transfer; as trying to override
> > > the
> > > length of the transfer with dmaengine_prep_slave_sg() is a very
> > > tedious
> > > process. The introduction of a new API function is also justified
> > > by the
> > > fact that scatterlists are on their way out.
> > >
> > > Note that dmaengine_prep_interleaved_dma() is not helpful either in
> > > that
> > > case, as it assumes that the address of each segment will be higher
> > > than
> > > the one of the previous segment, which we just cannot guarantee in
> > > case
> > > of a scatter-gather transfer.
> > >
> > > Signed-off-by: Paul Cercueil <[email protected]>
> > > Signed-off-by: Nuno Sa <[email protected]>
> > >
> > > ---
> > > v3: New patch
> > >
> > > v5: Replace with function dmaengine_prep_slave_dma_vec(), and
> > > struct
> > > ??? 'dma_vec'.
> > > ??? Note that at some point we will need to support cyclic
> > > transfers
> > > ??? using dmaengine_prep_slave_dma_vec(). Maybe with a new "flags"
> > > ??? parameter to the function?
> > >
> > > v7:
> > > ? - Renamed *device_prep_slave_dma_vec() ->
> > > device_prep_peripheral_dma_vec();
> > > ? - Added a new flag parameter to the function as agreed between
> > > Paul
> > > ??? and Vinod. I renamed the first parameter to prep_flags as it's
> > > supposed to
> > > ??? be used (I think) with enum dma_ctrl_flags. I'm not really sure
> > > how that API
> > > ??? can grow but I was thinking in just having a bool cyclic
> > > parameter (as the
> > > ??? first intention of the flags is to support cyclic transfers)
> > > but ended up
> > > ??? "respecting" the previously agreed approach.
> > > ---
> > > ?include/linux/dmaengine.h | 27 +++++++++++++++++++++++++++
> > > ?1 file changed, 27 insertions(+)
> > >
> > > diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
> > > index 752dbde4cec1..856df8cd9a4e 100644
> > > --- a/include/linux/dmaengine.h
> > > +++ b/include/linux/dmaengine.h
> > > @@ -160,6 +160,16 @@ struct dma_interleaved_template {
> > > ? struct data_chunk sgl[];
> > > ?};
> > > ?
> > > +/**
> > > + * struct dma_vec - DMA vector
> > > + * @addr: Bus address of the start of the vector
> > > + * @len: Length in bytes of the DMA vector
> > > + */
> > > +struct dma_vec {
> > > + dma_addr_t addr;
> > > + size_t len;
> > > +};
> > > +
> > > ?/**
> > > ? * enum dma_ctrl_flags - DMA flags to augment operation
> > > preparation,
> > > ? *? control completion, and communicate status.
> > > @@ -910,6 +920,10 @@ struct dma_device {
> > > ? struct dma_async_tx_descriptor
> > > *(*device_prep_dma_interrupt)(
> > > ? struct dma_chan *chan, unsigned long flags);
> > > ?
> > > + struct dma_async_tx_descriptor
> > > *(*device_prep_peripheral_dma_vec)(
> > > + struct dma_chan *chan, const struct dma_vec *vecs,
> > > + size_t nents, enum dma_transfer_direction
> > > direction,
> > > + unsigned long prep_flags, 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,
> > > @@ -973,6 +987,19 @@ static inline struct dma_async_tx_descriptor
> > > *dmaengine_prep_slave_single(
> > > ? ? dir, flags,
> > > NULL);
> > > ?}
> > > ?
> > > +static inline struct dma_async_tx_descriptor
> > > *dmaengine_prep_peripheral_dma_vec(
> > > + struct dma_chan *chan, const struct dma_vec *vecs, size_t
> > > nents,
> > > + enum dma_transfer_direction dir, unsigned long prep_flags,
> > > + unsigned long flags)
> > > +{
> > > + if (!chan || !chan->device || !chan->device-
> > > >device_prep_peripheral_dma_vec)
> > > + return NULL;
> > > +
> > > + return chan->device->device_prep_peripheral_dma_vec(chan,
> > > vecs, nents,
> > > + ??? dir,
> > > prep_flags,
> > > + ???
> > > flags);
> > > +}
> >
> > API looks good to me, thanks
> > Few nits though:
> > - Can we add kernel-doc for this new API please
> > - Also update the documentation adding this new api
> > - Lastly, we seem to have two flags, I know you have added a comment
> > but
> > ? I dont seem to recall the discussion (looked at old threads for
> > clue
> > ? as well), can you please remind me why we need both? And in your
> > case,
> > ? what is the intended usage of these flags, i would prefer single
> > ? clean one...
> >
>
> The "prep_flags" is a mask of "enum dma_ctrl_flags".
>
> The second "flags" was supposed to be specific to this function, and
> was to future-proof the API as we eventually want to have a "cyclic"
> flag, which would emulate a cyclic transfer by linking the SG hardware
> descriptors accordingly.
>
> However - I think we can already do that with DMA_PREP_REPEAT and
> DMA_PREP_LOAD_EOT, right? So we can probably drop the second "flags".
Yeah that could be done, we should add Documentation to clarify this
--
~Vinod