@@ -669,7 +669,7 @@ static const struct hc_driver ehci_fsl_hc_driver = {
* generic hardware linkage
*/
.irq = ehci_irq,
- .flags = HCD_USB2 | HCD_MEMORY,
+ .flags = HCD_USB2 | HCD_MEMORY | HCD_BH,
/*
* basic lifecycle operations
@@ -43,7 +43,7 @@ static const struct hc_driver ehci_grlib_hc_driver = {
* generic hardware linkage
*/
.irq = ehci_irq,
- .flags = HCD_MEMORY | HCD_USB2,
+ .flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
/*
* basic lifecycle operations
@@ -1174,7 +1174,7 @@ static const struct hc_driver ehci_hc_driver = {
* generic hardware linkage
*/
.irq = ehci_irq,
- .flags = HCD_MEMORY | HCD_USB2,
+ .flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
/*
* basic lifecycle operations
@@ -96,7 +96,7 @@ static const struct hc_driver mv_ehci_hc_driver = {
* generic hardware linkage
*/
.irq = ehci_irq,
- .flags = HCD_MEMORY | HCD_USB2,
+ .flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
/*
* basic lifecycle operations
@@ -51,7 +51,7 @@ static const struct hc_driver ehci_octeon_hc_driver = {
* generic hardware linkage
*/
.irq = ehci_irq,
- .flags = HCD_MEMORY | HCD_USB2,
+ .flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
/*
* basic lifecycle operations
@@ -286,7 +286,7 @@ static const struct hc_driver ehci_msp_hc_driver = {
#else
.irq = ehci_irq,
#endif
- .flags = HCD_MEMORY | HCD_USB2,
+ .flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
/*
* basic lifecycle operations
@@ -28,7 +28,7 @@ static const struct hc_driver ehci_ppc_of_hc_driver = {
* generic hardware linkage
*/
.irq = ehci_irq,
- .flags = HCD_MEMORY | HCD_USB2,
+ .flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
/*
* basic lifecycle operations
@@ -71,7 +71,7 @@ static const struct hc_driver ps3_ehci_hc_driver = {
.product_desc = "PS3 EHCI Host Controller",
.hcd_priv_size = sizeof(struct ehci_hcd),
.irq = ehci_irq,
- .flags = HCD_MEMORY | HCD_USB2,
+ .flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
.reset = ps3_ehci_hc_reset,
.start = ehci_run,
.stop = ehci_stop,
@@ -55,7 +55,7 @@ const struct hc_driver ehci_sead3_hc_driver = {
* generic hardware linkage
*/
.irq = ehci_irq,
- .flags = HCD_MEMORY | HCD_USB2,
+ .flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
/*
* basic lifecycle operations
@@ -36,7 +36,7 @@ static const struct hc_driver ehci_sh_hc_driver = {
* generic hardware linkage
*/
.irq = ehci_irq,
- .flags = HCD_USB2 | HCD_MEMORY,
+ .flags = HCD_USB2 | HCD_MEMORY | HCD_BH,
/*
* basic lifecycle operations
@@ -377,7 +377,7 @@ static const struct hc_driver tegra_ehci_hc_driver = {
.description = hcd_name,
.product_desc = "Tegra EHCI Host Controller",
.hcd_priv_size = sizeof(struct ehci_hcd),
- .flags = HCD_USB2 | HCD_MEMORY,
+ .flags = HCD_USB2 | HCD_MEMORY | HCD_BH,
/* standard ehci functions */
.irq = ehci_irq,
@@ -61,7 +61,7 @@ static const struct hc_driver ehci_tilegx_hc_driver = {
* Generic hardware linkage.
*/
.irq = ehci_irq,
- .flags = HCD_MEMORY | HCD_USB2,
+ .flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
/*
* Basic lifecycle operations.
@@ -108,7 +108,7 @@ static const struct hc_driver ehci_w90x900_hc_driver = {
* generic hardware linkage
*/
.irq = ehci_irq,
- .flags = HCD_USB2|HCD_MEMORY,
+ .flags = HCD_USB2|HCD_MEMORY|HCD_BH,
/*
* basic lifecycle operations
@@ -79,7 +79,7 @@ static const struct hc_driver ehci_xilinx_of_hc_driver = {
* generic hardware linkage
*/
.irq = ehci_irq,
- .flags = HCD_MEMORY | HCD_USB2,
+ .flags = HCD_MEMORY | HCD_USB2 | HCD_BH,
/*
* basic lifecycle operations
Both 4 transfers can work well on EHCI HCD after switching to run URB giveback in tasklet context, so mark all HCD drivers to support it. 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) --------------------------------------------------------------------- * 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 Cc: Alan Stern <stern@rowland.harvard.edu> Signed-off-by: Ming Lei <ming.lei@canonical.com> --- drivers/usb/host/ehci-fsl.c | 2 +- drivers/usb/host/ehci-grlib.c | 2 +- drivers/usb/host/ehci-hcd.c | 2 +- drivers/usb/host/ehci-mv.c | 2 +- drivers/usb/host/ehci-octeon.c | 2 +- drivers/usb/host/ehci-pmcmsp.c | 2 +- drivers/usb/host/ehci-ppc-of.c | 2 +- drivers/usb/host/ehci-ps3.c | 2 +- drivers/usb/host/ehci-sead3.c | 2 +- drivers/usb/host/ehci-sh.c | 2 +- drivers/usb/host/ehci-tegra.c | 2 +- drivers/usb/host/ehci-tilegx.c | 2 +- drivers/usb/host/ehci-w90x900.c | 2 +- drivers/usb/host/ehci-xilinx-of.c | 2 +- 14 files changed, 14 insertions(+), 14 deletions(-)