From: Ming Lei Date: Wed, 3 Jul 2013 14:53:11 +0000 (+0800) Subject: USB: EHCI: support running URB giveback in tasklet context X-Git-Tag: upstream/snapshot3+hdmi~4476^2~113 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=428aac8a81058e2303677a8fbf26670229e51d3a;p=platform%2Fadaptation%2Frenesas_rcar%2Frenesas_kernel.git 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 Signed-off-by: Ming Lei Signed-off-by: Greg Kroah-Hartman --- diff --git a/drivers/usb/host/ehci-fsl.c b/drivers/usb/host/ehci-fsl.c index 45eee6e..e44f442 100644 --- a/drivers/usb/host/ehci-fsl.c +++ b/drivers/usb/host/ehci-fsl.c @@ -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 diff --git a/drivers/usb/host/ehci-grlib.c b/drivers/usb/host/ehci-grlib.c index 83ab51a..b52a66c 100644 --- a/drivers/usb/host/ehci-grlib.c +++ b/drivers/usb/host/ehci-grlib.c @@ -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 diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 7ad9ef8..73c7299 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -1166,7 +1166,7 @@ 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 diff --git a/drivers/usb/host/ehci-mv.c b/drivers/usb/host/ehci-mv.c index 35cdbd8..417c10d 100644 --- a/drivers/usb/host/ehci-mv.c +++ b/drivers/usb/host/ehci-mv.c @@ -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 diff --git a/drivers/usb/host/ehci-octeon.c b/drivers/usb/host/ehci-octeon.c index 45cc001..ab0397e 100644 --- a/drivers/usb/host/ehci-octeon.c +++ b/drivers/usb/host/ehci-octeon.c @@ -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 diff --git a/drivers/usb/host/ehci-pmcmsp.c b/drivers/usb/host/ehci-pmcmsp.c index 601e208..893b707 100644 --- a/drivers/usb/host/ehci-pmcmsp.c +++ b/drivers/usb/host/ehci-pmcmsp.c @@ -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 diff --git a/drivers/usb/host/ehci-ppc-of.c b/drivers/usb/host/ehci-ppc-of.c index 932293f..6cc5567 100644 --- a/drivers/usb/host/ehci-ppc-of.c +++ b/drivers/usb/host/ehci-ppc-of.c @@ -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 diff --git a/drivers/usb/host/ehci-ps3.c b/drivers/usb/host/ehci-ps3.c index fd98377..8188542 100644 --- a/drivers/usb/host/ehci-ps3.c +++ b/drivers/usb/host/ehci-ps3.c @@ -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, diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c index d34b399..b637a65 100644 --- a/drivers/usb/host/ehci-q.c +++ b/drivers/usb/host/ehci-q.c @@ -254,8 +254,6 @@ static int qtd_copy_status ( static void ehci_urb_done(struct ehci_hcd *ehci, struct urb *urb, int status) -__releases(ehci->lock) -__acquires(ehci->lock) { if (usb_pipetype(urb->pipe) == PIPE_INTERRUPT) { /* ... update hc-wide periodic stats */ @@ -281,11 +279,8 @@ __acquires(ehci->lock) urb->actual_length, urb->transfer_buffer_length); #endif - /* complete() can reenter this HCD */ usb_hcd_unlink_urb_from_ep(ehci_to_hcd(ehci), urb); - spin_unlock (&ehci->lock); usb_hcd_giveback_urb(ehci_to_hcd(ehci), urb, status); - spin_lock (&ehci->lock); } static int qh_schedule (struct ehci_hcd *ehci, struct ehci_qh *qh); diff --git a/drivers/usb/host/ehci-sead3.c b/drivers/usb/host/ehci-sead3.c index b2de52d..8a73449 100644 --- a/drivers/usb/host/ehci-sead3.c +++ b/drivers/usb/host/ehci-sead3.c @@ -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 diff --git a/drivers/usb/host/ehci-sh.c b/drivers/usb/host/ehci-sh.c index 93e59a1..dc899eb 100644 --- a/drivers/usb/host/ehci-sh.c +++ b/drivers/usb/host/ehci-sh.c @@ -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 diff --git a/drivers/usb/host/ehci-tilegx.c b/drivers/usb/host/ehci-tilegx.c index cca4be9..67026ff 100644 --- a/drivers/usb/host/ehci-tilegx.c +++ b/drivers/usb/host/ehci-tilegx.c @@ -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. diff --git a/drivers/usb/host/ehci-w90x900.c b/drivers/usb/host/ehci-w90x900.c index 59e0e24..1c370df 100644 --- a/drivers/usb/host/ehci-w90x900.c +++ b/drivers/usb/host/ehci-w90x900.c @@ -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 diff --git a/drivers/usb/host/ehci-xilinx-of.c b/drivers/usb/host/ehci-xilinx-of.c index eba962e..95979f9 100644 --- a/drivers/usb/host/ehci-xilinx-of.c +++ b/drivers/usb/host/ehci-xilinx-of.c @@ -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