linux/drivers/usb/host/ehci-sh.c
Ming Lei 428aac8a81 USB: EHCI: support running URB giveback in tasklet context
All 4 transfer types can work well on EHCI HCD after switching to run
URB giveback in tasklet context, so mark all HCD drivers to support
it.

Also we don't need to release ehci->lock during URB giveback any more.

>From below test results on 3 machines(2 ARM and one x86), time
consumed by EHCI interrupt handler droped much without performance
loss.

1 test description
1.1 mass storage performance test:
- run below command 10 times and compute the average performance

    dd if=/dev/sdN iflag=direct of=/dev/null bs=200M count=1

- two usb mass storage device:
A: sandisk extreme USB 3.0 16G(used in test case 1 & case 2)
B: kingston DataTraveler G2 4GB(only used in test case 2)

1.2 uvc function test:
- run one simple capture program in the below link

   http://kernel.ubuntu.com/~ming/up/capture.c

- capture format 640*480 and results in High Bandwidth mode on the
uvc device: Z-Star 0x0ac8/0x3450

- on T410(x86) laptop, also use guvcview to watch video capture/playback

1.3 about test2 and test4
- both two devices involved are tested concurrently by above test items

1.4 how to compute irq time(the time consumed by ehci_irq)
- use trace points of irq:irq_handler_entry and irq:irq_handler_exit

1.5 kernel
3.10.0-rc3-next-20130528

1.6 test machines
Pandaboard A1: ARM CortexA9 dural core
Arndale board: ARM CortexA15 dural core
T410: i5 CPU 2.67GHz quad core

2 test result
2.1 test case1: single mass storage device performance test
--------------------------------------------------------------------
		upstream 		| patched
		perf(MB/s)+irq time(us)	| perf(MB/s)+irq time(us)
--------------------------------------------------------------------
Pandaboard A1:  25.280(avg:145,max:772)	| 25.540(avg:14, max:75)
Arndale board:  29.700(avg:33, max:129)	| 29.700(avg:10,  max:50)
T410: 		34.430(avg:17, max:154*)| 34.660(avg:12, max:155)
---------------------------------------------------------------------

2.2 test case2: two mass storage devices' performance test
--------------------------------------------------------------------
		upstream 			| patched
		perf(MB/s)+irq time(us)		| perf(MB/s)+irq time(us)
--------------------------------------------------------------------
Pandaboard A1:  15.840/15.580(avg:158,max:1216)	| 16.500/16.160(avg:15,max:139)
Arndale board:  17.370/16.220(avg:33 max:234)	| 17.480/16.200(avg:11, max:91)
T410: 		21.180/19.820(avg:18 max:160)	| 21.220/19.880(avg:11, max:149)
---------------------------------------------------------------------

2.3 test case3: one uvc streaming test
- uvc device works well(on x86, luvcview can be used too and has
same result with uvc capture)
--------------------------------------------------------------------
		upstream 		| patched
		irq time(us)		| irq time(us)
--------------------------------------------------------------------
Pandaboard A1:  (avg:445, max:873)	| (avg:33, max:44)
Arndale board:  (avg:316, max:630)	| (avg:20, max:27)
T410: 		(avg:39,  max:107)	| (avg:10, max:65)
---------------------------------------------------------------------

2.4 test case4: one uvc streaming plus one mass storage device test
--------------------------------------------------------------------
		upstream 		| patched
		perf(MB/s)+irq time(us)	| perf(MB/s)+irq time(us)
--------------------------------------------------------------------
Pandaboard A1:  20.340(avg:259,max:1704)| 20.390(avg:24, max:101)
Arndale board:  23.460(avg:124,max:726)	| 23.370(avg:15, max:52)
T410: 		28.520(avg:27, max:169)	| 28.630(avg:13, max:160)
---------------------------------------------------------------------

2.5 test case5: read single mass storage device with small transfer
- run below command 10 times and compute the average speed

 dd if=/dev/sdN iflag=direct of=/dev/null bs=4K count=4000

1), test device A:
--------------------------------------------------------------------
		upstream 		| patched
		perf(MB/s)+irq time(us)	| perf(MB/s)+irq time(us)
--------------------------------------------------------------------
Pandaboard A1:  6.5(avg:21, max:64)	| 6.5(avg:10, max:24)
Arndale board:  8.13(avg:12, max:23)	| 8.06(avg:7,  max:17)
T410: 		6.66(avg:13, max:131)   | 6.84(avg:11, max:149)
---------------------------------------------------------------------

2), test device B:
--------------------------------------------------------------------
		upstream 		| patched
		perf(MB/s)+irq time(us)	| perf(MB/s)+irq time(us)
--------------------------------------------------------------------
Pandaboard A1:  5.5(avg:21,max:43)	| 5.49(avg:10, max:24)
Arndale board:  5.9(avg:12, max:22)	| 5.9(avg:7, max:17)
T410: 		5.48(avg:13, max:155)	| 5.48(avg:7, max:140)
---------------------------------------------------------------------

* On T410, sometimes read ehci status register in ehci_irq takes more
than 100us, and the problem has been reported on the link:

	http://marc.info/?t=137065867300001&r=1&w=2

Acked-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2013-08-12 11:43:49 -07:00

206 lines
4.3 KiB
C

/*
* SuperH EHCI host controller driver
*
* Copyright (C) 2010 Paul Mundt
*
* Based on ohci-sh.c and ehci-atmel.c.
*
* This file is subject to the terms and conditions of the GNU General Public
* License. See the file "COPYING" in the main directory of this archive
* for more details.
*/
#include <linux/platform_device.h>
#include <linux/clk.h>
#include <linux/platform_data/ehci-sh.h>
struct ehci_sh_priv {
struct clk *iclk, *fclk;
struct usb_hcd *hcd;
};
static int ehci_sh_reset(struct usb_hcd *hcd)
{
struct ehci_hcd *ehci = hcd_to_ehci(hcd);
ehci->caps = hcd->regs;
return ehci_setup(hcd);
}
static const struct hc_driver ehci_sh_hc_driver = {
.description = hcd_name,
.product_desc = "SuperH EHCI",
.hcd_priv_size = sizeof(struct ehci_hcd),
/*
* generic hardware linkage
*/
.irq = ehci_irq,
.flags = HCD_USB2 | HCD_MEMORY | HCD_BH,
/*
* basic lifecycle operations
*/
.reset = ehci_sh_reset,
.start = ehci_run,
.stop = ehci_stop,
.shutdown = ehci_shutdown,
/*
* managing i/o requests and associated device resources
*/
.urb_enqueue = ehci_urb_enqueue,
.urb_dequeue = ehci_urb_dequeue,
.endpoint_disable = ehci_endpoint_disable,
.endpoint_reset = ehci_endpoint_reset,
/*
* scheduling support
*/
.get_frame_number = ehci_get_frame,
/*
* root hub support
*/
.hub_status_data = ehci_hub_status_data,
.hub_control = ehci_hub_control,
#ifdef CONFIG_PM
.bus_suspend = ehci_bus_suspend,
.bus_resume = ehci_bus_resume,
#endif
.relinquish_port = ehci_relinquish_port,
.port_handed_over = ehci_port_handed_over,
.clear_tt_buffer_complete = ehci_clear_tt_buffer_complete,
};
static int ehci_hcd_sh_probe(struct platform_device *pdev)
{
struct resource *res;
struct ehci_sh_priv *priv;
struct ehci_sh_platdata *pdata;
struct usb_hcd *hcd;
int irq, ret;
if (usb_disabled())
return -ENODEV;
res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (!res) {
dev_err(&pdev->dev,
"Found HC with no register addr. Check %s setup!\n",
dev_name(&pdev->dev));
ret = -ENODEV;
goto fail_create_hcd;
}
irq = platform_get_irq(pdev, 0);
if (irq <= 0) {
dev_err(&pdev->dev,
"Found HC with no IRQ. Check %s setup!\n",
dev_name(&pdev->dev));
ret = -ENODEV;
goto fail_create_hcd;
}
pdata = dev_get_platdata(&pdev->dev);
/* initialize hcd */
hcd = usb_create_hcd(&ehci_sh_hc_driver, &pdev->dev,
dev_name(&pdev->dev));
if (!hcd) {
ret = -ENOMEM;
goto fail_create_hcd;
}
hcd->rsrc_start = res->start;
hcd->rsrc_len = resource_size(res);
hcd->regs = devm_ioremap_resource(&pdev->dev, res);
if (IS_ERR(hcd->regs)) {
ret = PTR_ERR(hcd->regs);
goto fail_request_resource;
}
priv = devm_kzalloc(&pdev->dev, sizeof(struct ehci_sh_priv),
GFP_KERNEL);
if (!priv) {
dev_dbg(&pdev->dev, "error allocating priv data\n");
ret = -ENOMEM;
goto fail_request_resource;
}
/* These are optional, we don't care if they fail */
priv->fclk = devm_clk_get(&pdev->dev, "usb_fck");
if (IS_ERR(priv->fclk))
priv->fclk = NULL;
priv->iclk = devm_clk_get(&pdev->dev, "usb_ick");
if (IS_ERR(priv->iclk))
priv->iclk = NULL;
clk_enable(priv->fclk);
clk_enable(priv->iclk);
if (pdata && pdata->phy_init)
pdata->phy_init();
ret = usb_add_hcd(hcd, irq, IRQF_SHARED);
if (ret != 0) {
dev_err(&pdev->dev, "Failed to add hcd");
goto fail_add_hcd;
}
priv->hcd = hcd;
platform_set_drvdata(pdev, priv);
return ret;
fail_add_hcd:
clk_disable(priv->iclk);
clk_disable(priv->fclk);
fail_request_resource:
usb_put_hcd(hcd);
fail_create_hcd:
dev_err(&pdev->dev, "init %s fail, %d\n", dev_name(&pdev->dev), ret);
return ret;
}
static int ehci_hcd_sh_remove(struct platform_device *pdev)
{
struct ehci_sh_priv *priv = platform_get_drvdata(pdev);
struct usb_hcd *hcd = priv->hcd;
usb_remove_hcd(hcd);
usb_put_hcd(hcd);
clk_disable(priv->fclk);
clk_disable(priv->iclk);
return 0;
}
static void ehci_hcd_sh_shutdown(struct platform_device *pdev)
{
struct ehci_sh_priv *priv = platform_get_drvdata(pdev);
struct usb_hcd *hcd = priv->hcd;
if (hcd->driver->shutdown)
hcd->driver->shutdown(hcd);
}
static struct platform_driver ehci_hcd_sh_driver = {
.probe = ehci_hcd_sh_probe,
.remove = ehci_hcd_sh_remove,
.shutdown = ehci_hcd_sh_shutdown,
.driver = {
.name = "sh_ehci",
.owner = THIS_MODULE,
},
};
MODULE_ALIAS("platform:sh_ehci");