From: Tom Rini trini@ti.com
The USB spec says that 32 bytes is the minimum required alignment. However on some platforms we have a larger minimum requirement for cache coherency. In those cases, use that value rather than the USB spec minimum. We add a cpp check to <usb.h> to define USB_DMA_MINALIGN and make use of it in ehci-hcd.c and musb_core.h. We cannot use MAX() here as we are not allowed to have tests inside of align(...).
Signed-off-by: Tom Rini trini@ti.com [marek.vasut]: introduce some crazy macro voodoo Signed-off-by: Marek Vasut marex@denx.de [ilya.yanok]: moved external buffer fixes to separate patch, we use {ALLOC,DEFINE}_ALIGN_BUFFER macros with alignment of USB_DMA_MINALIGN for qh_list, qh and qtd structures to make sure they are proper aligned for both controller and cache operations. Signed-off-by: Ilya Yanok ilya.yanok@cogentembedded.com --- Changes from V2: - qh struct made non-static
drivers/usb/host/ehci-hcd.c | 61 ++++++++++++++++++++++-------------------- drivers/usb/musb/musb_core.h | 2 +- include/usb.h | 10 +++++++ 3 files changed, 43 insertions(+), 30 deletions(-)
diff --git a/drivers/usb/host/ehci-hcd.c b/drivers/usb/host/ehci-hcd.c index 3be2a77..2b46662 100644 --- a/drivers/usb/host/ehci-hcd.c +++ b/drivers/usb/host/ehci-hcd.c @@ -34,7 +34,10 @@ struct ehci_hccr *hccr; /* R/O registers, not need for volatile */ volatile struct ehci_hcor *hcor;
static uint16_t portreset; -static struct QH qh_list __attribute__((aligned(32))); +DEFINE_ALIGN_BUFFER(struct QH, qh_list, 1, USB_DMA_MINALIGN); + +#define ALIGN_END_ADDR(type, ptr, size) \ + ((uint32_t)(ptr) + roundup((size) * sizeof(type), USB_DMA_MINALIGN))
static struct descriptor { struct usb_hub_descriptor hub; @@ -207,8 +210,8 @@ static int ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer, int length, struct devrequest *req) { - static struct QH qh __attribute__((aligned(32))); - static struct qTD qtd[3] __attribute__((aligned (32))); + ALLOC_ALIGN_BUFFER(struct QH, qh, 1, USB_DMA_MINALIGN); + ALLOC_ALIGN_BUFFER(struct qTD, qtd, 3, USB_DMA_MINALIGN); int qtd_counter = 0;
volatile struct qTD *vtd; @@ -229,8 +232,8 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer, le16_to_cpu(req->value), le16_to_cpu(req->value), le16_to_cpu(req->index));
- memset(&qh, 0, sizeof(struct QH)); - memset(qtd, 0, sizeof(qtd)); + memset(qh, 0, sizeof(struct QH)); + memset(qtd, 0, 3 * sizeof(*qtd));
toggle = usb_gettoggle(dev, usb_pipeendpoint(pipe), usb_pipeout(pipe));
@@ -244,7 +247,7 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer, * qh_overlay.qt_next ...... 13-10 H * - qh_overlay.qt_altnext */ - qh.qh_link = cpu_to_hc32((uint32_t)&qh_list | QH_LINK_TYPE_QH); + qh->qh_link = cpu_to_hc32((uint32_t)qh_list | QH_LINK_TYPE_QH); c = (usb_pipespeed(pipe) != USB_SPEED_HIGH && usb_pipeendpoint(pipe) == 0) ? 1 : 0; endpt = (8 << 28) | @@ -255,14 +258,14 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer, (usb_pipespeed(pipe) << 12) | (usb_pipeendpoint(pipe) << 8) | (0 << 7) | (usb_pipedevice(pipe) << 0); - qh.qh_endpt1 = cpu_to_hc32(endpt); + qh->qh_endpt1 = cpu_to_hc32(endpt); endpt = (1 << 30) | (dev->portnr << 23) | (dev->parent->devnum << 16) | (0 << 8) | (0 << 0); - qh.qh_endpt2 = cpu_to_hc32(endpt); - qh.qh_overlay.qt_next = cpu_to_hc32(QT_NEXT_TERMINATE); + qh->qh_endpt2 = cpu_to_hc32(endpt); + qh->qh_overlay.qt_next = cpu_to_hc32(QT_NEXT_TERMINATE);
- tdp = &qh.qh_overlay.qt_next; + tdp = &qh->qh_overlay.qt_next;
if (req != NULL) { /* @@ -340,16 +343,16 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer, tdp = &qtd[qtd_counter++].qt_next; }
- qh_list.qh_link = cpu_to_hc32((uint32_t)&qh | QH_LINK_TYPE_QH); + qh_list->qh_link = cpu_to_hc32((uint32_t)qh | QH_LINK_TYPE_QH);
/* Flush dcache */ - flush_dcache_range((uint32_t)&qh_list, - (uint32_t)&qh_list + sizeof(struct QH)); - flush_dcache_range((uint32_t)&qh, (uint32_t)&qh + sizeof(struct QH)); - flush_dcache_range((uint32_t)qtd, (uint32_t)qtd + sizeof(qtd)); + flush_dcache_range((uint32_t)qh_list, + ALIGN_END_ADDR(struct QH, qh_list, 1)); + flush_dcache_range((uint32_t)qh, ALIGN_END_ADDR(struct QH, qh, 1)); + flush_dcache_range((uint32_t)qtd, ALIGN_END_ADDR(struct qTD, qtd, 3));
/* Set async. queue head pointer. */ - ehci_writel(&hcor->or_asynclistaddr, (uint32_t)&qh_list); + ehci_writel(&hcor->or_asynclistaddr, (uint32_t)qh_list);
usbsts = ehci_readl(&hcor->or_usbsts); ehci_writel(&hcor->or_usbsts, (usbsts & 0x3f)); @@ -372,12 +375,12 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer, timeout = USB_TIMEOUT_MS(pipe); do { /* Invalidate dcache */ - invalidate_dcache_range((uint32_t)&qh_list, - (uint32_t)&qh_list + sizeof(struct QH)); - invalidate_dcache_range((uint32_t)&qh, - (uint32_t)&qh + sizeof(struct QH)); + invalidate_dcache_range((uint32_t)qh_list, + ALIGN_END_ADDR(struct QH, qh_list, 1)); + invalidate_dcache_range((uint32_t)qh, + ALIGN_END_ADDR(struct QH, qh, 1)); invalidate_dcache_range((uint32_t)qtd, - (uint32_t)qtd + sizeof(qtd)); + ALIGN_END_ADDR(struct qTD, qtd, 3));
token = hc32_to_cpu(vtd->qt_token); if (!(token & 0x80)) @@ -406,7 +409,7 @@ ehci_submit_async(struct usb_device *dev, unsigned long pipe, void *buffer, goto fail; }
- token = hc32_to_cpu(qh.qh_overlay.qt_token); + token = hc32_to_cpu(qh->qh_overlay.qt_token); if (!(token & 0x80)) { debug("TOKEN=%#x\n", token); switch (token & 0xfc) { @@ -734,13 +737,13 @@ int usb_lowlevel_init(void) #endif
/* Set head of reclaim list */ - memset(&qh_list, 0, sizeof(qh_list)); - qh_list.qh_link = cpu_to_hc32((uint32_t)&qh_list | QH_LINK_TYPE_QH); - qh_list.qh_endpt1 = cpu_to_hc32((1 << 15) | (USB_SPEED_HIGH << 12)); - qh_list.qh_curtd = cpu_to_hc32(QT_NEXT_TERMINATE); - qh_list.qh_overlay.qt_next = cpu_to_hc32(QT_NEXT_TERMINATE); - qh_list.qh_overlay.qt_altnext = cpu_to_hc32(QT_NEXT_TERMINATE); - qh_list.qh_overlay.qt_token = cpu_to_hc32(0x40); + memset(qh_list, 0, sizeof(*qh_list)); + qh_list->qh_link = cpu_to_hc32((uint32_t)qh_list | QH_LINK_TYPE_QH); + qh_list->qh_endpt1 = cpu_to_hc32((1 << 15) | (USB_SPEED_HIGH << 12)); + qh_list->qh_curtd = cpu_to_hc32(QT_NEXT_TERMINATE); + qh_list->qh_overlay.qt_next = cpu_to_hc32(QT_NEXT_TERMINATE); + qh_list->qh_overlay.qt_altnext = cpu_to_hc32(QT_NEXT_TERMINATE); + qh_list->qh_overlay.qt_token = cpu_to_hc32(0x40);
reg = ehci_readl(&hccr->cr_hcsparams); descriptor.hub.bNbrPorts = HCS_N_PORTS(reg); diff --git a/drivers/usb/musb/musb_core.h b/drivers/usb/musb/musb_core.h index a8adcce..e914369 100644 --- a/drivers/usb/musb/musb_core.h +++ b/drivers/usb/musb/musb_core.h @@ -145,7 +145,7 @@ struct musb_regs { struct musb_epN_regs epN; } ep[16];
-} __attribute__((packed, aligned(32))); +} __attribute__((packed, aligned(USB_DMA_MINALIGN))); #endif
/* diff --git a/include/usb.h b/include/usb.h index 6da91e7..ba3d169 100644 --- a/include/usb.h +++ b/include/usb.h @@ -29,6 +29,16 @@ #include <usb_defs.h> #include <usbdescriptors.h>
+/* + * The EHCI spec says that we must align to at least 32 bytes. However, + * some platforms require larger alignment. + */ +#if ARCH_DMA_MINALIGN > 32 +#define USB_DMA_MINALIGN ARCH_DMA_MINALIGN +#else +#define USB_DMA_MINALIGN 32 +#endif + /* Everything is aribtrary */ #define USB_ALTSETTINGALLOC 4 #define USB_MAXALTSETTING 128 /* Hard limit */