diff options
author | Ming Lei <ming.lei@canonical.com> | 2011-08-31 00:03:13 +0800 |
---|---|---|
committer | Andrey Konovalov <andrey.konovalov@linaro.org> | 2013-01-11 20:29:28 +0400 |
commit | b70295cf051e6d3e0cd697c9cdf8ab91586ca66f (patch) | |
tree | 2056a6c8cbc43314157bd3e53c0c8d9b793d0b3d /drivers | |
parent | 9931faca02c604c22335f5a935a501bb2ace6e20 (diff) |
usb: ehci: make HC see up-to-date qh/qtd descriptor ASAP
This patch introduces the helper of ehci_sync_mem to flush
qtd/qh into memory immediately on some ARM, so that HC can
see the up-to-date qtd/qh descriptor asap.
This patch fixs one performance bug on ARM Cortex A9 dual core
platform, which has been reported on quite a few ARM machines
(OMAP4, Tegra 2, snowball...), see details from link of
https://bugs.launchpad.net/bugs/709245.
The patch has been tested ok on OMAP4 panda A1 board, and the
performance of 'dd' over usb mass storage can be increased from
4~5MB/sec to 14~16MB/sec after applying this patch.
Cc: Russell King <linux@arm.linux.org.uk>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Diffstat (limited to 'drivers')
-rw-r--r-- | drivers/usb/host/ehci-q.c | 18 | ||||
-rw-r--r-- | drivers/usb/host/ehci.h | 17 |
2 files changed, 35 insertions, 0 deletions
diff --git a/drivers/usb/host/ehci-q.c b/drivers/usb/host/ehci-q.c index 3d989028c836..7842997e06a3 100644 --- a/drivers/usb/host/ehci-q.c +++ b/drivers/usb/host/ehci-q.c @@ -1012,6 +1012,12 @@ static void qh_link_async (struct ehci_hcd *ehci, struct ehci_qh *qh) head->qh_next.qh = qh; head->hw->hw_next = dma; + /* + * flush qh descriptor into memory immediately, + * see comments in qh_append_tds. + */ + ehci_sync_mem(); + qh->xacterrs = 0; qh->qh_state = QH_STATE_LINKED; /* qtd completions reported later by interrupt */ @@ -1100,6 +1106,18 @@ static struct ehci_qh *qh_append_tds ( wmb (); dummy->hw_token = token; + /* + * Writing to dma coherent buffer on ARM may + * be delayed to reach memory, so HC may not see + * hw_token of dummy qtd in time, which can cause + * the qtd transaction to be executed very late, + * and degrade performance a lot. ehci_sync_mem + * is added to flush 'token' immediatelly into + * memory, so that ehci can execute the transaction + * ASAP. + */ + ehci_sync_mem(); + urb->hcpriv = qh; } } diff --git a/drivers/usb/host/ehci.h b/drivers/usb/host/ehci.h index 9dadc7118d68..53e4b49ca735 100644 --- a/drivers/usb/host/ehci.h +++ b/drivers/usb/host/ehci.h @@ -758,6 +758,23 @@ static inline u32 hc32_to_cpup (const struct ehci_hcd *ehci, const __hc32 *x) #endif +/* + * Writing to dma coherent memory on ARM may be delayed via L2 + * writing buffer, so introduce the helper which can flush L2 writing + * buffer into memory immediately, especially used to flush ehci + * descriptor to memory. + */ +#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE +static inline void ehci_sync_mem() +{ + mb(); +} +#else +static inline void ehci_sync_mem() +{ +} +#endif + /*-------------------------------------------------------------------------*/ #define ehci_dbg(ehci, fmt, args...) \ |