Linux-USB Archive on lore.kernel.org
 help / color / Atom feed
From: Tejas Joglekar <Tejas.Joglekar@synopsys.com>
To: Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Tejas Joglekar <Tejas.Joglekar@synopsys.com>,
	linux-usb@vger.kernel.org,
	Mathias Nyman <mathias.nyman@intel.com>
Cc: John Youn <John.Youn@synopsys.com>
Subject: [PATCH v5 2/3] usb: xhci: Use temporary buffer to consolidate SG
Date: Fri, 16 Oct 2020 18:35:19 +0530
Message-ID: <a4cb87733fe1e82a1a3f2b8998add6af7d363fe4.1602853270.git.joglekar@synopsys.com> (raw)
In-Reply-To: <cover.1602853270.git.joglekar@synopsys.com>

The Synopsys xHC has an internal TRB cache of size TRB_CACHE_SIZE for
each endpoint. The default value for TRB_CACHE_SIZE is 16 for SS and 8
for HS. The controller loads and updates the TRB cache from the transfer
ring in system memory whenever the driver issues a start transfer or
update transfer command.

For chained TRBs, the Synopsys xHC requires that the total amount of
bytes for all TRBs loaded in the TRB cache be greater than or equal to 1
MPS. Or the chain ends within the TRB cache (with a last TRB).

If this requirement is not met, the controller will not be able to send
or receive a packet and it will hang causing a driver timeout and error.

This can be a problem if a class driver queues SG requests with many
small-buffer entries. The XHCI driver will create a chained TRB for each
entry which may trigger this issue.

This patch adds logic to the XHCI driver to detect and prevent this from
happening.

For every (TRB_CACHE_SIZE - 2), we check the total buffer size of
the SG list and if the last window of (TRB_CACHE_SIZE - 2) SG list length
and we don't make up at least 1 MPS, we create a temporary buffer to
consolidate full SG list into the buffer.

We check at (TRB_CACHE_SIZE - 2) window because it is possible that there
would be a link and/or event data TRB that take up to 2 of the cache
entries.

We discovered this issue with devices on other platforms but have not
yet come across any device that triggers this on Linux. But it could be
a real problem now or in the future. All it takes is N number of small
chained TRBs. And other instances of the Synopsys IP may have smaller
values for the TRB_CACHE_SIZE which would exacerbate the problem.

Signed-off-by: Tejas Joglekar <joglekar@synopsys.com>
---
 drivers/usb/host/xhci-ring.c |   2 +-
 drivers/usb/host/xhci.c      | 137 ++++++++++++++++++++++++++++++++++-
 drivers/usb/host/xhci.h      |   4 +
 3 files changed, 141 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 167dae117f73..6d4dae5e5f21 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -3325,7 +3325,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 
 	full_len = urb->transfer_buffer_length;
 	/* If we have scatter/gather list, we use it. */
-	if (urb->num_sgs) {
+	if (urb->num_sgs && !(urb->transfer_flags & URB_DMA_MAP_SINGLE)) {
 		num_sgs = urb->num_mapped_sgs;
 		sg = urb->sg;
 		addr = (u64) sg_dma_address(sg);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 482fe8c5e3b4..8c6089a4a6a4 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -1259,6 +1259,116 @@ EXPORT_SYMBOL_GPL(xhci_resume);
 
 /*-------------------------------------------------------------------------*/
 
+static int xhci_map_temp_buffer(struct usb_hcd *hcd, struct urb *urb)
+{
+	void *temp;
+	int ret = 0;
+	unsigned int len;
+	unsigned int buf_len;
+	enum dma_data_direction dir;
+	struct xhci_hcd *xhci;
+
+	xhci = hcd_to_xhci(hcd);
+	dir = usb_urb_dir_in(urb) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+	buf_len = urb->transfer_buffer_length;
+
+	temp = kzalloc_node(buf_len, GFP_ATOMIC,
+			    dev_to_node(hcd->self.sysdev));
+
+	if (usb_urb_dir_out(urb))
+		len = sg_pcopy_to_buffer(urb->sg, urb->num_sgs,
+					 temp, buf_len, 0);
+
+	urb->transfer_buffer = temp;
+	urb->transfer_dma = dma_map_single(hcd->self.sysdev,
+					   urb->transfer_buffer,
+					   urb->transfer_buffer_length,
+					   dir);
+
+	if (dma_mapping_error(hcd->self.sysdev,
+			      urb->transfer_dma)) {
+		ret = -EAGAIN;
+		kfree(temp);
+	} else {
+		urb->transfer_flags |= URB_DMA_MAP_SINGLE;
+	}
+
+	return ret;
+}
+
+static bool xhci_urb_temp_buffer_required(struct usb_hcd *hcd,
+					  struct urb *urb)
+{
+	bool ret = false;
+	unsigned int i;
+	unsigned int len = 0;
+	unsigned int buf_len;
+	unsigned int trb_size;
+	unsigned int max_pkt;
+	struct scatterlist *sg;
+	struct scatterlist *tail_sg;
+
+	sg = urb->sg;
+	tail_sg = urb->sg;
+	buf_len = urb->transfer_buffer_length;
+	max_pkt = usb_endpoint_maxp(&urb->ep->desc);
+
+	if (!urb->num_sgs)
+		return ret;
+
+	if (urb->dev->speed >= USB_SPEED_SUPER)
+		trb_size = TRB_CACHE_SIZE_SS;
+	else
+		trb_size = TRB_CACHE_SIZE_HS;
+
+	if (urb->transfer_buffer_length != 0 &&
+	    !(urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP)) {
+		for_each_sg(urb->sg, sg, urb->num_sgs, i) {
+			len = len + sg->length;
+			if (i > trb_size - 2) {
+				len = len - tail_sg->length;
+				if (len < max_pkt) {
+					ret = true;
+					break;
+				}
+
+				tail_sg = sg_next(tail_sg);
+			}
+		}
+	}
+	return ret;
+}
+
+static void xhci_unmap_temp_buf(struct usb_hcd *hcd, struct urb *urb)
+{
+	struct scatterlist *sg;
+	unsigned int len;
+	unsigned int buf_len;
+	enum dma_data_direction dir;
+
+	dir = usb_urb_dir_in(urb) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+
+	sg = urb->sg;
+	buf_len = urb->transfer_buffer_length;
+
+	if (IS_ENABLED(CONFIG_HAS_DMA) &&
+	    (urb->transfer_flags & URB_DMA_MAP_SINGLE))
+		dma_unmap_single(hcd->self.sysdev,
+				 urb->transfer_dma,
+				 urb->transfer_buffer_length,
+				 dir);
+
+	if (usb_urb_dir_in(urb))
+		len = sg_pcopy_from_buffer(urb->sg, urb->num_sgs,
+					   urb->transfer_buffer,
+					   buf_len,
+					   0);
+
+	urb->transfer_flags &= ~URB_DMA_MAP_SINGLE;
+	kfree(urb->transfer_buffer);
+	urb->transfer_buffer = NULL;
+}
+
 /*
  * Bypass the DMA mapping if URB is suitable for Immediate Transfer (IDT),
  * we'll copy the actual data into the TRB address register. This is limited to
@@ -1268,13 +1378,37 @@ EXPORT_SYMBOL_GPL(xhci_resume);
 static int xhci_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
 				gfp_t mem_flags)
 {
+	struct xhci_hcd *xhci;
+
+	xhci = hcd_to_xhci(hcd);
+
 	if (xhci_urb_suitable_for_idt(urb))
 		return 0;
 
+	if (xhci->quirks & XHCI_SG_TRB_CACHE_SIZE_QUIRK) {
+		if (xhci_urb_temp_buffer_required(hcd, urb))
+			return xhci_map_temp_buffer(hcd, urb);
+	}
 	return usb_hcd_map_urb_for_dma(hcd, urb, mem_flags);
 }
 
-/*
+static void xhci_unmap_urb_for_dma(struct usb_hcd *hcd, struct urb *urb)
+{
+	struct xhci_hcd *xhci;
+	bool unmap_temp_buf = false;
+
+	xhci = hcd_to_xhci(hcd);
+
+	if (urb->num_sgs && (urb->transfer_flags & URB_DMA_MAP_SINGLE))
+		unmap_temp_buf = true;
+
+	if ((xhci->quirks & XHCI_SG_TRB_CACHE_SIZE_QUIRK) && unmap_temp_buf)
+		xhci_unmap_temp_buf(hcd, urb);
+	else
+		usb_hcd_unmap_urb_for_dma(hcd, urb);
+}
+
+/**
  * xhci_get_endpoint_index - Used for passing endpoint bitmasks between the core and
  * HCDs.  Find the index for an endpoint given its descriptor.  Use the return
  * value to right shift 1 for the bitmask.
@@ -5326,6 +5460,7 @@ static const struct hc_driver xhci_hc_driver = {
 	 * managing i/o requests and associated device resources
 	 */
 	.map_urb_for_dma =      xhci_map_urb_for_dma,
+	.unmap_urb_for_dma =    xhci_unmap_urb_for_dma,
 	.urb_enqueue =		xhci_urb_enqueue,
 	.urb_dequeue =		xhci_urb_dequeue,
 	.alloc_dev =		xhci_alloc_dev,
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index f8e453a2674d..f69504f91b5e 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1330,6 +1330,10 @@ enum xhci_setup_dev {
 #define TRB_SIA			(1<<31)
 #define TRB_FRAME_ID(p)		(((p) & 0x7ff) << 20)
 
+/* TRB cache size for xHC with TRB cache */
+#define TRB_CACHE_SIZE_HS	8
+#define TRB_CACHE_SIZE_SS	16
+
 struct xhci_generic_trb {
 	__le32 field[4];
 };
-- 
2.28.0


  parent reply index

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-16 13:04 [PATCH v5 0/3] Add logic to consolidate TRBs for Synopsys xHC Tejas Joglekar
2020-10-16 13:04 ` [PATCH v5 1/3] usb: xhci: Set quirk for XHCI_SG_TRB_CACHE_SIZE_QUIRK Tejas Joglekar
2020-10-16 13:05 ` Tejas Joglekar [this message]
2020-10-16 13:05 ` [PATCH v5 3/3] usb: dwc3: Pass quirk as platform data Tejas Joglekar
2020-10-27 18:28 ` [PATCH v5 0/3] Add logic to consolidate TRBs for Synopsys xHC Tejas Joglekar
     [not found]   ` <09737ac8-66a0-564c-2f1c-60a92ec716b5@linux.intel.com>
2020-10-28 15:20     ` Tejas Joglekar
2020-11-06 16:06       ` Tejas Joglekar
2020-11-12  2:31         ` Tejas Joglekar
2020-11-17 17:16           ` Tejas Joglekar
2020-11-18 14:09             ` Mathias Nyman
2020-11-19  1:19               ` Tejas Joglekar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=a4cb87733fe1e82a1a3f2b8998add6af7d363fe4.1602853270.git.joglekar@synopsys.com \
    --to=tejas.joglekar@synopsys.com \
    --cc=John.Youn@synopsys.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=linux-usb@vger.kernel.org \
    --cc=mathias.nyman@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

Linux-USB Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-usb/0 linux-usb/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-usb linux-usb/ https://lore.kernel.org/linux-usb \
		linux-usb@vger.kernel.org
	public-inbox-index linux-usb

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-usb


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git