Merge tag 'firewire-updates-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394

Pull firewire updates from Takashi Sakamoto:

 - Refactor page allocation dedicated to 1394 OHCI IR/IT/AR DMA contexts

   Although 1394 OHCI specification does not impose any restriction on
   the memory size dedicated to these DMA contexts, 1394 OHCI PCI driver
   allocates pages for convenience when mapping them into either kernel
   space or userspace VMA. The driver previously used dma_alloc_pages()
   for both page allocation and mapping creation, even though this
   kernel API is rarely used. Following discussions questioning the
   page-oriented kernel API in the DMA layer, the driver has been
   refactored to avoid using this API. In addition, the use of private
   members in the allocated pages has been removed following
   long-standing concern.

 - Allocate variable-sized buffer for isochronous context header

   1394 OHCI PCI driver previously allocated a single page for
   isochronous context header. As a result, the buffer size for the
   header was fixed to PAGE_SIZE, which imposed a limitation on IEC
   61883-1/6 packet streaming engine. Consequently, the ALSA PCM devices
   provided by drivers for audio and music units in IEEE 1394 bus were
   constrained in the maximum size of buffer period (64 ms in most
   cases). This limitation is resolved by dynamically allocating the
   header buffer with an arbitrary size.

* tag 'firewire-updates-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/ieee1394/linux1394:
  ALSA: firewire: remove PCM buffer size constraint from isoc context header
  firewire: core: add fw_iso_context_create() variant with header storage size
  firewire: core: provide isoc header buffer size outside card driver
  firewire: ohci: allocate isoc context header by kvmalloc()
  firewire: core: add flags member for isochronous context structure
  firewire: ohci: use cleanup helper for isoc context header allocation
  firewire: ohci: code refactoring to use union for isoc multiple channel state
  firewire: ohci: refactor isoc single-channel state using a union
  firewire: core: add function variants for isochronous context creation
  firewire: ohci: fix index of pages for dma address to 1394 OHCI IT context
  firewire: ohci: stop using page private to store DMA mapping address
  firewire: ohci: split page allocation from dma mapping
  firewire: ohci: use MAX macro to guarantee minimum count of pages for AR contexts
  firewire: core: stop using page private to store DMA mapping address
  firewire: core: use common kernel API to allocate and release a batch of pages
  firewire: core: code refactoring with cleanup function for isoc pages
  firewire: core: use mutex instead of spinlock for client isochronous context
  firewire: core: move private function declaration from public header to internal header

Author: torvalds

drivers/firewire/core-card.c

@@ -704,8 +704,8 @@ static int dummy_enable_phys_dma(struct fw_card *card,
 	return -ENODEV;
 }
 
-static struct fw_iso_context *dummy_allocate_iso_context(struct fw_card *card,
-				int type, int channel, size_t header_size)
+static struct fw_iso_context *dummy_allocate_iso_context(struct fw_card *card, int type,
+		int channel, size_t header_size, size_t header_storage_size)
 {
 	return ERR_PTR(-ENODEV);
 }

drivers/firewire/core-cdev.c

@@ -63,10 +63,10 @@ struct client {
 	u64 bus_reset_closure;
 
 	struct fw_iso_context *iso_context;
+	struct mutex iso_context_mutex;
 	u64 iso_closure;
 	struct fw_iso_buffer buffer;
 	unsigned long vm_start;
-	bool buffer_is_mapped;
 
 	struct list_head phy_receiver_link;
 	u64 phy_receiver_closure;
@@ -306,6 +306,7 @@ static int fw_device_op_open(struct inode *inode, struct file *file)
 	INIT_LIST_HEAD(&client->phy_receiver_link);
 	INIT_LIST_HEAD(&client->link);
 	kref_init(&client->kref);
+	mutex_init(&client->iso_context_mutex);
 
 	file->private_data = client;
 
@@ -1025,25 +1026,10 @@ static enum dma_data_direction iso_dma_direction(struct fw_iso_context *context)
 			return DMA_FROM_DEVICE;
 }
 
-static struct fw_iso_context *fw_iso_mc_context_create(struct fw_card *card,
-						fw_iso_mc_callback_t callback,
-						void *callback_data)
-{
-	struct fw_iso_context *ctx;
-
-	ctx = fw_iso_context_create(card, FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL,
-				    0, 0, 0, NULL, callback_data);
-	if (!IS_ERR(ctx))
-		ctx->callback.mc = callback;
-
-	return ctx;
-}
-
 static int ioctl_create_iso_context(struct client *client, union ioctl_arg *arg)
 {
 	struct fw_cdev_create_iso_context *a = &arg->create_iso_context;
 	struct fw_iso_context *context;
-	union fw_iso_callback cb;
 	int ret;
 
 	BUILD_BUG_ON(FW_CDEV_ISO_CONTEXT_TRANSMIT != FW_ISO_CONTEXT_TRANSMIT ||
@@ -1055,59 +1041,52 @@ static int ioctl_create_iso_context(struct client *client, union ioctl_arg *arg)
 	case FW_ISO_CONTEXT_TRANSMIT:
 		if (a->speed > SCODE_3200 || a->channel > 63)
 			return -EINVAL;
-
-		cb.sc = iso_callback;
 		break;
 
 	case FW_ISO_CONTEXT_RECEIVE:
 		if (a->header_size < 4 || (a->header_size & 3) ||
 		    a->channel > 63)
 			return -EINVAL;
-
-		cb.sc = iso_callback;
 		break;
 
 	case FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL:
-		cb.mc = iso_mc_callback;
 		break;
 
 	default:
 		return -EINVAL;
 	}
 
 	if (a->type == FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL)
-		context = fw_iso_mc_context_create(client->device->card, cb.mc,
-						   client);
+		context = fw_iso_mc_context_create(client->device->card, iso_mc_callback, client);
 	else
-		context = fw_iso_context_create(client->device->card, a->type,
-						a->channel, a->speed,
-						a->header_size, cb.sc, client);
+		context = fw_iso_context_create(client->device->card, a->type, a->channel, a->speed,
+						a->header_size, iso_callback, client);
 	if (IS_ERR(context))
 		return PTR_ERR(context);
 	if (client->version < FW_CDEV_VERSION_AUTO_FLUSH_ISO_OVERFLOW)
-		context->drop_overflow_headers = true;
+		context->flags |= FW_ISO_CONTEXT_FLAG_DROP_OVERFLOW_HEADERS;
 
 	// We only support one context at this time.
-	guard(spinlock_irq)(&client->lock);
-
-	if (client->iso_context != NULL) {
-		fw_iso_context_destroy(context);
-
-		return -EBUSY;
-	}
-	if (!client->buffer_is_mapped) {
-		ret = fw_iso_buffer_map_dma(&client->buffer,
-					    client->device->card,
-					    iso_dma_direction(context));
-		if (ret < 0) {
+	scoped_guard(mutex, &client->iso_context_mutex) {
+		if (client->iso_context != NULL) {
 			fw_iso_context_destroy(context);
 
-			return ret;
+			return -EBUSY;
+		}
+		// The DMA mapping operation is available if the buffer is already allocated by
+		// mmap(2) system call. If not, it is delegated to the system call.
+		if (client->buffer.pages && !client->buffer.dma_addrs) {
+			ret = fw_iso_buffer_map_dma(&client->buffer, client->device->card,
+						    iso_dma_direction(context));
+			if (ret < 0) {
+				fw_iso_context_destroy(context);
+
+				return ret;
+			}
 		}
-		client->buffer_is_mapped = true;
+		client->iso_closure = a->closure;
+		client->iso_context = context;
 	}
-	client->iso_closure = a->closure;
-	client->iso_context = context;
 
 	a->handle = 0;
 
@@ -1826,13 +1805,14 @@ static int fw_device_op_mmap(struct file *file, struct vm_area_struct *vma)
 	if (ret < 0)
 		return ret;
 
-	scoped_guard(spinlock_irq, &client->lock) {
+	scoped_guard(mutex, &client->iso_context_mutex) {
+		// The direction of DMA can be determined if the isochronous context is already
+		// allocated. If not, the DMA mapping operation is postponed after the allocation.
 		if (client->iso_context) {
 			ret = fw_iso_buffer_map_dma(&client->buffer, client->device->card,
 						    iso_dma_direction(client->iso_context));
 			if (ret < 0)
 				goto fail;
-			client->buffer_is_mapped = true;
 		}
 	}
 
@@ -1879,6 +1859,7 @@ static int fw_device_op_release(struct inode *inode, struct file *file)
 
 	if (client->iso_context)
 		fw_iso_context_destroy(client->iso_context);
+	mutex_destroy(&client->iso_context_mutex);
 
 	if (client->buffer.pages)
 		fw_iso_buffer_destroy(&client->buffer, client->device->card);

drivers/firewire/core-iso.c

@@ -30,48 +30,57 @@
 
 int fw_iso_buffer_alloc(struct fw_iso_buffer *buffer, int page_count)
 {
-	int i;
+	struct page **page_array __free(kfree) = kcalloc(page_count, sizeof(page_array[0]), GFP_KERNEL);
 
-	buffer->page_count = 0;
-	buffer->page_count_mapped = 0;
-	buffer->pages = kmalloc_array(page_count, sizeof(buffer->pages[0]),
-				      GFP_KERNEL);
-	if (buffer->pages == NULL)
+	if (!page_array)
 		return -ENOMEM;
 
-	for (i = 0; i < page_count; i++) {
-		buffer->pages[i] = alloc_page(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO);
-		if (buffer->pages[i] == NULL)
-			break;
-	}
-	buffer->page_count = i;
-	if (i < page_count) {
-		fw_iso_buffer_destroy(buffer, NULL);
+	// Retrieve noncontiguous pages. The descriptors for 1394 OHCI isochronous DMA contexts
+	// have a set of address and length per each, while the reason to use pages is the
+	// convenience to map them into virtual address space of user process.
+	unsigned long nr_populated = alloc_pages_bulk(GFP_KERNEL | GFP_DMA32 | __GFP_ZERO,
+						      page_count, page_array);
+	if (nr_populated != page_count) {
+		// Assuming the above call fills page_array sequentially from the beginning.
+		release_pages(page_array, nr_populated);
 		return -ENOMEM;
 	}
 
+	buffer->page_count = page_count;
+	buffer->pages = no_free_ptr(page_array);
+
 	return 0;
 }
 
 int fw_iso_buffer_map_dma(struct fw_iso_buffer *buffer, struct fw_card *card,
 			  enum dma_data_direction direction)
 {
-	dma_addr_t address;
+	dma_addr_t *dma_addrs __free(kfree) = kcalloc(buffer->page_count, sizeof(dma_addrs[0]),
+						      GFP_KERNEL);
 	int i;
 
-	buffer->direction = direction;
+	if (!dma_addrs)
+		return -ENOMEM;
 
+	// Retrieve DMA mapping addresses for the pages. They are not contiguous. Maintain the cache
+	// coherency for the pages by hand.
 	for (i = 0; i < buffer->page_count; i++) {
-		address = dma_map_page(card->device, buffer->pages[i],
-				       0, PAGE_SIZE, direction);
-		if (dma_mapping_error(card->device, address))
+		// The dma_map_phys() with a physical address per page is available here, instead.
+		dma_addr_t dma_addr = dma_map_page(card->device, buffer->pages[i], 0, PAGE_SIZE,
+						   direction);
+		if (dma_mapping_error(card->device, dma_addr))
 			break;
 
-		set_page_private(buffer->pages[i], address);
+		dma_addrs[i] = dma_addr;
 	}
-	buffer->page_count_mapped = i;
-	if (i < buffer->page_count)
+	if (i < buffer->page_count) {
+		while (i-- > 0)
+			dma_unmap_page(card->device, dma_addrs[i], PAGE_SIZE, buffer->direction);
 		return -ENOMEM;
+	}
+
+	buffer->direction = direction;
+	buffer->dma_addrs = no_free_ptr(dma_addrs);
 
 	return 0;
 }
@@ -96,58 +105,57 @@ EXPORT_SYMBOL(fw_iso_buffer_init);
 void fw_iso_buffer_destroy(struct fw_iso_buffer *buffer,
 			   struct fw_card *card)
 {
-	int i;
-	dma_addr_t address;
+	if (buffer->dma_addrs) {
+		for (int i = 0; i < buffer->page_count; ++i) {
+			dma_addr_t dma_addr = buffer->dma_addrs[i];
+			dma_unmap_page(card->device, dma_addr, PAGE_SIZE, buffer->direction);
+		}
+		kfree(buffer->dma_addrs);
+		buffer->dma_addrs = NULL;
+	}
 
-	for (i = 0; i < buffer->page_count_mapped; i++) {
-		address = page_private(buffer->pages[i]);
-		dma_unmap_page(card->device, address,
-			       PAGE_SIZE, buffer->direction);
+	if (buffer->pages) {
+		release_pages(buffer->pages, buffer->page_count);
+		kfree(buffer->pages);
+		buffer->pages = NULL;
 	}
-	for (i = 0; i < buffer->page_count; i++)
-		__free_page(buffer->pages[i]);
 
-	kfree(buffer->pages);
-	buffer->pages = NULL;
 	buffer->page_count = 0;
-	buffer->page_count_mapped = 0;
 }
 EXPORT_SYMBOL(fw_iso_buffer_destroy);
 
 /* Convert DMA address to offset into virtually contiguous buffer. */
 size_t fw_iso_buffer_lookup(struct fw_iso_buffer *buffer, dma_addr_t completed)
 {
-	size_t i;
-	dma_addr_t address;
-	ssize_t offset;
-
-	for (i = 0; i < buffer->page_count; i++) {
-		address = page_private(buffer->pages[i]);
-		offset = (ssize_t)completed - (ssize_t)address;
+	for (int i = 0; i < buffer->page_count; i++) {
+		dma_addr_t dma_addr = buffer->dma_addrs[i];
+		ssize_t offset = (ssize_t)completed - (ssize_t)dma_addr;
 		if (offset > 0 && offset <= PAGE_SIZE)
 			return (i << PAGE_SHIFT) + offset;
 	}
 
 	return 0;
 }
 
-struct fw_iso_context *fw_iso_context_create(struct fw_card *card,
-		int type, int channel, int speed, size_t header_size,
-		fw_iso_callback_t callback, void *callback_data)
+struct fw_iso_context *__fw_iso_context_create(struct fw_card *card, int type, int channel,
+		int speed, size_t header_size, size_t header_storage_size,
+		union fw_iso_callback callback, void *callback_data)
 {
 	struct fw_iso_context *ctx;
 
-	ctx = card->driver->allocate_iso_context(card,
-						 type, channel, header_size);
+	ctx = card->driver->allocate_iso_context(card, type, channel, header_size,
+						 header_storage_size);
 	if (IS_ERR(ctx))
 		return ctx;
 
 	ctx->card = card;
 	ctx->type = type;
 	ctx->channel = channel;
 	ctx->speed = speed;
+	ctx->flags = 0;
 	ctx->header_size = header_size;
-	ctx->callback.sc = callback;
+	ctx->header_storage_size = header_storage_size;
+	ctx->callback = callback;
 	ctx->callback_data = callback_data;
 
 	trace_isoc_outbound_allocate(ctx, channel, speed);
@@ -156,7 +164,7 @@ struct fw_iso_context *fw_iso_context_create(struct fw_card *card,
 
 	return ctx;
 }
-EXPORT_SYMBOL(fw_iso_context_create);
+EXPORT_SYMBOL(__fw_iso_context_create);
 
 void fw_iso_context_destroy(struct fw_iso_context *ctx)
 {

drivers/firewire/core.h

@@ -100,8 +100,8 @@ struct fw_card_driver {
 	void (*write_csr)(struct fw_card *card, int csr_offset, u32 value);
 
 	struct fw_iso_context *
-	(*allocate_iso_context)(struct fw_card *card,
-				int type, int channel, size_t header_size);
+	(*allocate_iso_context)(struct fw_card *card, int type, int channel, size_t header_size,
+				size_t header_storage_size);
 	void (*free_iso_context)(struct fw_iso_context *ctx);
 
 	int (*start_iso)(struct fw_iso_context *ctx,
@@ -166,12 +166,22 @@ void fw_node_event(struct fw_card *card, struct fw_node *node, int event);
 int fw_iso_buffer_alloc(struct fw_iso_buffer *buffer, int page_count);
 int fw_iso_buffer_map_dma(struct fw_iso_buffer *buffer, struct fw_card *card,
 			  enum dma_data_direction direction);
+size_t fw_iso_buffer_lookup(struct fw_iso_buffer *buffer, dma_addr_t completed);
 
 static inline void fw_iso_context_init_work(struct fw_iso_context *ctx, work_func_t func)
 {
 	INIT_WORK(&ctx->work, func);
 }
 
+static inline struct fw_iso_context *fw_iso_mc_context_create(struct fw_card *card,
+		fw_iso_mc_callback_t callback, void *callback_data)
+{
+	union fw_iso_callback cb = { .mc = callback };
+
+	return __fw_iso_context_create(card, FW_ISO_CONTEXT_RECEIVE_MULTICHANNEL, 0, 0, 0, 0, cb,
+				       callback_data);
+}
+
 
 /* -topology */