linux_dsm_epyc7002/drivers/usb/host/ehci-octeon.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

199 lines
4.2 KiB
C

/*
* EHCI HCD glue for Cavium Octeon II SOCs.
*
* Loosely based on ehci-au1xxx.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.
*
* Copyright (C) 2010 Cavium Networks
*
*/
#include <linux/platform_device.h>
#include <asm/octeon/octeon.h>
#include <asm/octeon/cvmx-uctlx-defs.h>
#define OCTEON_EHCI_HCD_NAME "octeon-ehci"
/* Common clock init code. */
void octeon2_usb_clocks_start(void);
void octeon2_usb_clocks_stop(void);
static void ehci_octeon_start(void)
{
union cvmx_uctlx_ehci_ctl ehci_ctl;
octeon2_usb_clocks_start();
ehci_ctl.u64 = cvmx_read_csr(CVMX_UCTLX_EHCI_CTL(0));
/* Use 64-bit addressing. */
ehci_ctl.s.ehci_64b_addr_en = 1;
ehci_ctl.s.l2c_addr_msb = 0;
ehci_ctl.s.l2c_buff_emod = 1; /* Byte swapped. */
ehci_ctl.s.l2c_desc_emod = 1; /* Byte swapped. */
cvmx_write_csr(CVMX_UCTLX_EHCI_CTL(0), ehci_ctl.u64);
}
static void ehci_octeon_stop(void)
{
octeon2_usb_clocks_stop();
}
static const struct hc_driver ehci_octeon_hc_driver = {
.description = hcd_name,
.product_desc = "Octeon 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 = ehci_setup,
.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,
.bus_suspend = ehci_bus_suspend,
.bus_resume = ehci_bus_resume,
.relinquish_port = ehci_relinquish_port,
.port_handed_over = ehci_port_handed_over,
.clear_tt_buffer_complete = ehci_clear_tt_buffer_complete,
};
static u64 ehci_octeon_dma_mask = DMA_BIT_MASK(64);
static int ehci_octeon_drv_probe(struct platform_device *pdev)
{
struct usb_hcd *hcd;
struct ehci_hcd *ehci;
struct resource *res_mem;
int irq;
int ret;
if (usb_disabled())
return -ENODEV;
irq = platform_get_irq(pdev, 0);
if (irq < 0) {
dev_err(&pdev->dev, "No irq assigned\n");
return -ENODEV;
}
res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
if (res_mem == NULL) {
dev_err(&pdev->dev, "No register space assigned\n");
return -ENODEV;
}
/*
* We can DMA from anywhere. But the descriptors must be in
* the lower 4GB.
*/
pdev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
pdev->dev.dma_mask = &ehci_octeon_dma_mask;
hcd = usb_create_hcd(&ehci_octeon_hc_driver, &pdev->dev, "octeon");
if (!hcd)
return -ENOMEM;
hcd->rsrc_start = res_mem->start;
hcd->rsrc_len = resource_size(res_mem);
if (!request_mem_region(hcd->rsrc_start, hcd->rsrc_len,
OCTEON_EHCI_HCD_NAME)) {
dev_err(&pdev->dev, "request_mem_region failed\n");
ret = -EBUSY;
goto err1;
}
hcd->regs = ioremap(hcd->rsrc_start, hcd->rsrc_len);
if (!hcd->regs) {
dev_err(&pdev->dev, "ioremap failed\n");
ret = -ENOMEM;
goto err2;
}
ehci_octeon_start();
ehci = hcd_to_ehci(hcd);
/* Octeon EHCI matches CPU endianness. */
#ifdef __BIG_ENDIAN
ehci->big_endian_mmio = 1;
#endif
ehci->caps = hcd->regs;
ret = usb_add_hcd(hcd, irq, IRQF_SHARED);
if (ret) {
dev_dbg(&pdev->dev, "failed to add hcd with err %d\n", ret);
goto err3;
}
platform_set_drvdata(pdev, hcd);
return 0;
err3:
ehci_octeon_stop();
iounmap(hcd->regs);
err2:
release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
err1:
usb_put_hcd(hcd);
return ret;
}
static int ehci_octeon_drv_remove(struct platform_device *pdev)
{
struct usb_hcd *hcd = platform_get_drvdata(pdev);
usb_remove_hcd(hcd);
ehci_octeon_stop();
iounmap(hcd->regs);
release_mem_region(hcd->rsrc_start, hcd->rsrc_len);
usb_put_hcd(hcd);
return 0;
}
static struct platform_driver ehci_octeon_driver = {
.probe = ehci_octeon_drv_probe,
.remove = ehci_octeon_drv_remove,
.shutdown = usb_hcd_platform_shutdown,
.driver = {
.name = OCTEON_EHCI_HCD_NAME,
.owner = THIS_MODULE,
}
};
MODULE_ALIAS("platform:" OCTEON_EHCI_HCD_NAME);