linux/drivers/usb/host/ehci-mv.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

338 lines
7.5 KiB
C

/*
* Copyright (C) 2011 Marvell International Ltd. All rights reserved.
* Author: Chao Xie <chao.xie@marvell.com>
* Neil Zhang <zhangwm@marvell.com>
*
* This program is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
* Free Software Foundation; either version 2 of the License, or (at your
* option) any later version.
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/clk.h>
#include <linux/err.h>
#include <linux/usb/otg.h>
#include <linux/platform_data/mv_usb.h>
#define CAPLENGTH_MASK (0xff)
struct ehci_hcd_mv {
struct usb_hcd *hcd;
/* Which mode does this ehci running OTG/Host ? */
int mode;
void __iomem *phy_regs;
void __iomem *cap_regs;
void __iomem *op_regs;
struct usb_phy *otg;
struct mv_usb_platform_data *pdata;
struct clk *clk;
};
static void ehci_clock_enable(struct ehci_hcd_mv *ehci_mv)
{
clk_prepare_enable(ehci_mv->clk);
}
static void ehci_clock_disable(struct ehci_hcd_mv *ehci_mv)
{
clk_disable_unprepare(ehci_mv->clk);
}
static int mv_ehci_enable(struct ehci_hcd_mv *ehci_mv)
{
int retval;
ehci_clock_enable(ehci_mv);
if (ehci_mv->pdata->phy_init) {
retval = ehci_mv->pdata->phy_init(ehci_mv->phy_regs);
if (retval)
return retval;
}
return 0;
}
static void mv_ehci_disable(struct ehci_hcd_mv *ehci_mv)
{
if (ehci_mv->pdata->phy_deinit)
ehci_mv->pdata->phy_deinit(ehci_mv->phy_regs);
ehci_clock_disable(ehci_mv);
}
static int mv_ehci_reset(struct usb_hcd *hcd)
{
struct device *dev = hcd->self.controller;
struct ehci_hcd_mv *ehci_mv = dev_get_drvdata(dev);
int retval;
if (ehci_mv == NULL) {
dev_err(dev, "Can not find private ehci data\n");
return -ENODEV;
}
hcd->has_tt = 1;
retval = ehci_setup(hcd);
if (retval)
dev_err(dev, "ehci_setup failed %d\n", retval);
return retval;
}
static const struct hc_driver mv_ehci_hc_driver = {
.description = hcd_name,
.product_desc = "Marvell EHCI",
.hcd_priv_size = sizeof(struct ehci_hcd),
/*
* generic hardware linkage
*/
.irq = ehci_irq,
.flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
/*
* basic lifecycle operations
*/
.reset = mv_ehci_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,
.clear_tt_buffer_complete = ehci_clear_tt_buffer_complete,
/*
* scheduling support
*/
.get_frame_number = ehci_get_frame,
/*
* root hub support
*/
.hub_status_data = ehci_hub_status_data,
.hub_control = ehci_hub_control,
.bus_suspend = ehci_bus_suspend,
.bus_resume = ehci_bus_resume,
};
static int mv_ehci_probe(struct platform_device *pdev)
{
struct mv_usb_platform_data *pdata = dev_get_platdata(&pdev->dev);
struct usb_hcd *hcd;
struct ehci_hcd *ehci;
struct ehci_hcd_mv *ehci_mv;
struct resource *r;
int retval = -ENODEV;
u32 offset;
if (!pdata) {
dev_err(&pdev->dev, "missing platform_data\n");
return -ENODEV;
}
if (usb_disabled())
return -ENODEV;
hcd = usb_create_hcd(&mv_ehci_hc_driver, &pdev->dev, "mv ehci");
if (!hcd)
return -ENOMEM;
ehci_mv = devm_kzalloc(&pdev->dev, sizeof(*ehci_mv), GFP_KERNEL);
if (ehci_mv == NULL) {
dev_err(&pdev->dev, "cannot allocate ehci_hcd_mv\n");
retval = -ENOMEM;
goto err_put_hcd;
}
platform_set_drvdata(pdev, ehci_mv);
ehci_mv->pdata = pdata;
ehci_mv->hcd = hcd;
ehci_mv->clk = devm_clk_get(&pdev->dev, NULL);
if (IS_ERR(ehci_mv->clk)) {
dev_err(&pdev->dev, "error getting clock\n");
retval = PTR_ERR(ehci_mv->clk);
goto err_put_hcd;
}
r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "phyregs");
if (r == NULL) {
dev_err(&pdev->dev, "no phy I/O memory resource defined\n");
retval = -ENODEV;
goto err_put_hcd;
}
ehci_mv->phy_regs = devm_ioremap(&pdev->dev, r->start,
resource_size(r));
if (ehci_mv->phy_regs == 0) {
dev_err(&pdev->dev, "failed to map phy I/O memory\n");
retval = -EFAULT;
goto err_put_hcd;
}
r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "capregs");
if (!r) {
dev_err(&pdev->dev, "no I/O memory resource defined\n");
retval = -ENODEV;
goto err_put_hcd;
}
ehci_mv->cap_regs = devm_ioremap(&pdev->dev, r->start,
resource_size(r));
if (ehci_mv->cap_regs == NULL) {
dev_err(&pdev->dev, "failed to map I/O memory\n");
retval = -EFAULT;
goto err_put_hcd;
}
retval = mv_ehci_enable(ehci_mv);
if (retval) {
dev_err(&pdev->dev, "init phy error %d\n", retval);
goto err_put_hcd;
}
offset = readl(ehci_mv->cap_regs) & CAPLENGTH_MASK;
ehci_mv->op_regs =
(void __iomem *) ((unsigned long) ehci_mv->cap_regs + offset);
hcd->rsrc_start = r->start;
hcd->rsrc_len = resource_size(r);
hcd->regs = ehci_mv->op_regs;
hcd->irq = platform_get_irq(pdev, 0);
if (!hcd->irq) {
dev_err(&pdev->dev, "Cannot get irq.");
retval = -ENODEV;
goto err_disable_clk;
}
ehci = hcd_to_ehci(hcd);
ehci->caps = (struct ehci_caps *) ehci_mv->cap_regs;
ehci_mv->mode = pdata->mode;
if (ehci_mv->mode == MV_USB_MODE_OTG) {
ehci_mv->otg = devm_usb_get_phy(&pdev->dev, USB_PHY_TYPE_USB2);
if (IS_ERR(ehci_mv->otg)) {
retval = PTR_ERR(ehci_mv->otg);
if (retval == -ENXIO)
dev_info(&pdev->dev, "MV_USB_MODE_OTG "
"must have CONFIG_USB_PHY enabled\n");
else
dev_err(&pdev->dev,
"unable to find transceiver\n");
goto err_disable_clk;
}
retval = otg_set_host(ehci_mv->otg->otg, &hcd->self);
if (retval < 0) {
dev_err(&pdev->dev,
"unable to register with transceiver\n");
retval = -ENODEV;
goto err_disable_clk;
}
/* otg will enable clock before use as host */
mv_ehci_disable(ehci_mv);
} else {
if (pdata->set_vbus)
pdata->set_vbus(1);
retval = usb_add_hcd(hcd, hcd->irq, IRQF_SHARED);
if (retval) {
dev_err(&pdev->dev,
"failed to add hcd with err %d\n", retval);
goto err_set_vbus;
}
}
if (pdata->private_init)
pdata->private_init(ehci_mv->op_regs, ehci_mv->phy_regs);
dev_info(&pdev->dev,
"successful find EHCI device with regs 0x%p irq %d"
" working in %s mode\n", hcd->regs, hcd->irq,
ehci_mv->mode == MV_USB_MODE_OTG ? "OTG" : "Host");
return 0;
err_set_vbus:
if (pdata->set_vbus)
pdata->set_vbus(0);
err_disable_clk:
mv_ehci_disable(ehci_mv);
err_put_hcd:
usb_put_hcd(hcd);
return retval;
}
static int mv_ehci_remove(struct platform_device *pdev)
{
struct ehci_hcd_mv *ehci_mv = platform_get_drvdata(pdev);
struct usb_hcd *hcd = ehci_mv->hcd;
if (hcd->rh_registered)
usb_remove_hcd(hcd);
if (!IS_ERR_OR_NULL(ehci_mv->otg))
otg_set_host(ehci_mv->otg->otg, NULL);
if (ehci_mv->mode == MV_USB_MODE_HOST) {
if (ehci_mv->pdata->set_vbus)
ehci_mv->pdata->set_vbus(0);
mv_ehci_disable(ehci_mv);
}
usb_put_hcd(hcd);
return 0;
}
MODULE_ALIAS("mv-ehci");
static const struct platform_device_id ehci_id_table[] = {
{"pxa-u2oehci", PXA_U2OEHCI},
{"pxa-sph", PXA_SPH},
{"mmp3-hsic", MMP3_HSIC},
{"mmp3-fsic", MMP3_FSIC},
{},
};
static void mv_ehci_shutdown(struct platform_device *pdev)
{
struct ehci_hcd_mv *ehci_mv = platform_get_drvdata(pdev);
struct usb_hcd *hcd = ehci_mv->hcd;
if (!hcd->rh_registered)
return;
if (hcd->driver->shutdown)
hcd->driver->shutdown(hcd);
}
static struct platform_driver ehci_mv_driver = {
.probe = mv_ehci_probe,
.remove = mv_ehci_remove,
.shutdown = mv_ehci_shutdown,
.driver = {
.name = "mv-ehci",
.bus = &platform_bus_type,
},
.id_table = ehci_id_table,
};