USB: Push scatter gather lists down to host controller drivers.

This is the original patch I created before David Vrabel posted a better
patch (http://marc.info/?l=linux-usb&m=123377477209109&w=2) that does
basically the same thing.  This patch will get replaced with his
(modified) patch later.

Allow USB device drivers that use usb_sg_init() and usb_sg_wait() to push
bulk endpoint scatter gather lists down to the host controller drivers.
This allows host controller drivers to more efficiently enqueue these
transfers, and allows the xHCI host controller to better take advantage of
USB 3.0 "bursts" for bulk endpoints.

This patch currently only enables scatter gather lists for bulk endpoints.
Other endpoint types that use the usb_sg_* functions will not have their
scatter gather lists pushed down to the host controller.  For periodic
endpoints, we want each scatterlist entry to be a separate transfer.
Eventually, HCDs could parse these scatter-gather lists for periodic
endpoints also.  For now, we use the old code and call usb_submit_urb()
for each scatterlist entry.

The caller of usb_sg_init() can request that all bytes in the scatter
gather list be transferred by passing in a length of zero.  Handle that
request for a bulk endpoint under xHCI by walking the scatter gather list
and calculating the length.  We could let the HCD handle a zero length in
this case, but I'm not sure if the core layers in between will get
confused by this.

Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

3 files changed, 95 insertions, 49 deletions

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index b2da4753b12..1609623ec82 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1239,7 +1239,8 @@ static int map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
 
 	/* Map the URB's buffers for DMA access.
 	 * Lower level HCD code should use *_dma exclusively,
-	 * unless it uses pio or talks to another transport.
+	 * unless it uses pio or talks to another transport,
+	 * or uses the provided scatter gather list for bulk.
 	 */
 	if (is_root_hub(urb->dev))
 		return 0;
diff --git a/drivers/usb/core/message.c b/drivers/usb/core/message.c
index 3a2e69ec2f2..2bed83caacb 100644
--- a/drivers/usb/core/message.c
+++ b/drivers/usb/core/message.c
@@ -365,6 +365,7 @@ int usb_sg_init(struct usb_sg_request *io, struct usb_device *dev,
 	int i;
 	int urb_flags;
 	int dma;
+	int use_sg;
 
 	if (!io || !dev || !sg
 			|| usb_pipecontrol(pipe)
@@ -392,7 +393,19 @@ int usb_sg_init(struct usb_sg_request *io, struct usb_device *dev,
 	if (io->entries <= 0)
 		return io->entries;
 
-	io->urbs = kmalloc(io->entries * sizeof *io->urbs, mem_flags);
+	/* If we're running on an xHCI host controller, queue the whole scatter
+	 * gather list with one call to urb_enqueue().  This is only for bulk,
+	 * as that endpoint type does not care how the data gets broken up
+	 * across frames.
+	 */
+	if (usb_pipebulk(pipe) &&
+			bus_to_hcd(dev->bus)->driver->flags & HCD_USB3) {
+		io->urbs = kmalloc(sizeof *io->urbs, mem_flags);
+		use_sg = true;
+	} else {
+		io->urbs = kmalloc(io->entries * sizeof *io->urbs, mem_flags);
+		use_sg = false;
+	}
 	if (!io->urbs)
 		goto nomem;
 
@@ -402,62 +415,92 @@ int usb_sg_init(struct usb_sg_request *io, struct usb_device *dev,
 	if (usb_pipein(pipe))
 		urb_flags |= URB_SHORT_NOT_OK;
 
-	for_each_sg(sg, sg, io->entries, i) {
-		unsigned len;
-
-		io->urbs[i] = usb_alloc_urb(0, mem_flags);
-		if (!io->urbs[i]) {
-			io->entries = i;
+	if (use_sg) {
+		io->urbs[0] = usb_alloc_urb(0, mem_flags);
+		if (!io->urbs[0]) {
+			io->entries = 0;
 			goto nomem;
 		}
 
-		io->urbs[i]->dev = NULL;
-		io->urbs[i]->pipe = pipe;
-		io->urbs[i]->interval = period;
-		io->urbs[i]->transfer_flags = urb_flags;
-
-		io->urbs[i]->complete = sg_complete;
-		io->urbs[i]->context = io;
-
-		/*
-		 * Some systems need to revert to PIO when DMA is temporarily
-		 * unavailable.  For their sakes, both transfer_buffer and
-		 * transfer_dma are set when possible.  However this can only
-		 * work on systems without:
-		 *
-		 *  - HIGHMEM, since DMA buffers located in high memory are
-		 *    not directly addressable by the CPU for PIO;
-		 *
-		 *  - IOMMU, since dma_map_sg() is allowed to use an IOMMU to
-		 *    make virtually discontiguous buffers be "dma-contiguous"
-		 *    so that PIO and DMA need diferent numbers of URBs.
-		 *
-		 * So when HIGHMEM or IOMMU are in use, transfer_buffer is NULL
-		 * to prevent stale pointers and to help spot bugs.
-		 */
-		if (dma) {
-			io->urbs[i]->transfer_dma = sg_dma_address(sg);
-			len = sg_dma_len(sg);
+		io->urbs[0]->dev = NULL;
+		io->urbs[0]->pipe = pipe;
+		io->urbs[0]->interval = period;
+		io->urbs[0]->transfer_flags = urb_flags;
+
+		io->urbs[0]->complete = sg_complete;
+		io->urbs[0]->context = io;
+		/* A length of zero means transfer the whole sg list */
+		io->urbs[0]->transfer_buffer_length = length;
+		if (length == 0) {
+			for_each_sg(sg, sg, io->entries, i) {
+				io->urbs[0]->transfer_buffer_length +=
+					sg_dma_len(sg);
+			}
+		}
+		io->urbs[0]->sg = io;
+		io->urbs[0]->num_sgs = io->entries;
+		io->entries = 1;
+	} else {
+		for_each_sg(sg, sg, io->entries, i) {
+			unsigned len;
+
+			io->urbs[i] = usb_alloc_urb(0, mem_flags);
+			if (!io->urbs[i]) {
+				io->entries = i;
+				goto nomem;
+			}
+
+			io->urbs[i]->dev = NULL;
+			io->urbs[i]->pipe = pipe;
+			io->urbs[i]->interval = period;
+			io->urbs[i]->transfer_flags = urb_flags;
+
+			io->urbs[i]->complete = sg_complete;
+			io->urbs[i]->context = io;
+
+			/*
+			 * Some systems need to revert to PIO when DMA is
+			 * temporarily unavailable.  For their sakes, both
+			 * transfer_buffer and transfer_dma are set when
+			 * possible.  However this can only work on systems
+			 * without:
+			 *
+			 *  - HIGHMEM, since DMA buffers located in high memory
+			 *    are not directly addressable by the CPU for PIO;
+			 *
+			 *  - IOMMU, since dma_map_sg() is allowed to use an
+			 *    IOMMU to make virtually discontiguous buffers be
+			 *    "dma-contiguous" so that PIO and DMA need diferent
+			 *    numbers of URBs.
+			 *
+			 * So when HIGHMEM or IOMMU are in use, transfer_buffer
+			 * is NULL to prevent stale pointers and to help spot
+			 * bugs.
+			 */
+			if (dma) {
+				io->urbs[i]->transfer_dma = sg_dma_address(sg);
+				len = sg_dma_len(sg);
 #if defined(CONFIG_HIGHMEM) || defined(CONFIG_GART_IOMMU)
-			io->urbs[i]->transfer_buffer = NULL;
+				io->urbs[i]->transfer_buffer = NULL;
 #else
-			io->urbs[i]->transfer_buffer = sg_virt(sg);
+				io->urbs[i]->transfer_buffer = sg_virt(sg);
 #endif
-		} else {
-			/* hc may use _only_ transfer_buffer */
-			io->urbs[i]->transfer_buffer = sg_virt(sg);
-			len = sg->length;
-		}
+			} else {
+				/* hc may use _only_ transfer_buffer */
+				io->urbs[i]->transfer_buffer = sg_virt(sg);
+				len = sg->length;
+			}
 
-		if (length) {
-			len = min_t(unsigned, len, length);
-			length -= len;
-			if (length == 0)
-				io->entries = i + 1;
+			if (length) {
+				len = min_t(unsigned, len, length);
+				length -= len;
+				if (length == 0)
+					io->entries = i + 1;
+			}
+			io->urbs[i]->transfer_buffer_length = len;
 		}
-		io->urbs[i]->transfer_buffer_length = len;
+		io->urbs[--i]->transfer_flags &= ~URB_NO_INTERRUPT;
 	}
-	io->urbs[--i]->transfer_flags &= ~URB_NO_INTERRUPT;
 
 	/* transaction state */
 	io->count = io->entries;
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 13bced521b8..0a1819a6497 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1198,6 +1198,8 @@ struct urb {
 	unsigned int transfer_flags;	/* (in) URB_SHORT_NOT_OK | ...*/
 	void *transfer_buffer;		/* (in) associated data buffer */
 	dma_addr_t transfer_dma;	/* (in) dma addr for transfer_buffer */
+	struct usb_sg_request *sg;	/* (in) scatter gather buffer list */
+	int num_sgs;			/* (in) number of entries in the sg list */
 	u32 transfer_buffer_length;	/* (in) data buffer length */
 	u32 actual_length;		/* (return) actual transfer length */
 	unsigned char *setup_packet;	/* (in) setup packet (control only) */