usb: fsl_udc_core: Fix scheduling while atomic dump message

When loading g_ether gadget, there is below message:

Backtrace:
[<80012248>] (dump_backtrace+0x0/0x10c) from [<803cb42c>] (dump_stack+0x18/0x1c)
r7:00000000 r6:80512000 r5:8052bef8 r4:80513f30
[<803cb414>] (dump_stack+0x0/0x1c) from [<8000feb4>] (show_regs+0x44/0x50)
[<8000fe70>] (show_regs+0x0/0x50) from [<8004c840>] (__schedule_bug+0x68/0x84)
r5:8052bef8 r4:80513f30
[<8004c7d8>] (__schedule_bug+0x0/0x84) from [<803cd0e4>] (__schedule+0x4b0/0x528)
r5:8052bef8 r4:809aad00
[<803ccc34>] (__schedule+0x0/0x528) from [<803cd214>] (_cond_resched+0x44/0x58)
[<803cd1d0>] (_cond_resched+0x0/0x58) from [<800a9488>] (dma_pool_alloc+0x184/0x250)
 r5:9f9b4000 r4:9fb4fb80
 [<800a9304>] (dma_pool_alloc+0x0/0x250) from [<802a8ad8>] (fsl_req_to_dtd+0xac/0x180)
[<802a8a2c>] (fsl_req_to_dtd+0x0/0x180) from [<802a8ce4>] (fsl_ep_queue+0x138/0x274)
[<802a8bac>] (fsl_ep_queue+0x0/0x274) from [<7f004328>] (composite_setup+0x2d4/0xfac [g_ether])
[<7f004054>] (composite_setup+0x0/0xfac [g_ether]) from [<802a9bb4>] (fsl_udc_irq+0x8dc/0xd38)
[<802a92d8>] (fsl_udc_irq+0x0/0xd38) from [<800704f8>] (handle_irq_event_percpu+0x54/0x188)
[<800704a4>] (handle_irq_event_percpu+0x0/0x188) from [<80070674>] (handle_irq_event+0x48/0x68)
[<8007062c>] (handle_irq_event+0x0/0x68) from [<800738ec>] (handle_level_irq+0xb4/0x138)
 r5:80514f94 r4:80514f40
 [<80073838>] (handle_level_irq+0x0/0x138) from [<8006ffa4>] (generic_handle_irq+0x38/0x44)
 r7:00000012 r6:80510b1c r5:80529860 r4:80512000
 [<8006ff6c>] (generic_handle_irq+0x0/0x44) from [<8000f4c4>] (handle_IRQ+0x54/0xb4)
[<8000f470>] (handle_IRQ+0x0/0xb4) from [<800085b8>] (tzic_handle_irq+0x64/0x94)
 r9:412fc085 r8:00000000 r7:80513f30 r6:00000001 r5:00000000
 r4:00000000
 [<80008554>] (tzic_handle_irq+0x0/0x94) from [<8000e680>] (__irq_svc+0x40/0x60)

The reason of above dump message is calling dma_poll_alloc with can-schedule
mem_flags at atomic context.

To fix this problem, below changes are made:
- fsl_req_to_dtd doesn't need to be protected by spin_lock_irqsave,
as struct usb_request can be access at process context. Move lock
to beginning of hardware visit (fsl_queue_td).
- Change the memory flag which using to allocate dTD descriptor buffer,
the memory flag can be from gadget layer.

It is tested at i.mx51 bbg board with g_mass_storage, g_ether, g_serial.

Cc: stable@vger.kernel.org
Signed-off-by: NPeter Chen <peter.chen@freescale.com>
Acked-by: NLi Yang <leoli@freescale.com>
Signed-off-by: NFelipe Balbi <balbi@ti.com>

drivers/usb/gadget/fsl_udc_core.c

@@ -769,7 +769,7 @@ static void fsl_queue_td(struct fsl_ep *ep, struct fsl_req *req)
  * @is_last: return flag if it is the last dTD of the request
  * return: pointer to the built dTD */
 static struct ep_td_struct *fsl_build_dtd(struct fsl_req *req, unsigned *length,
-		dma_addr_t *dma, int *is_last)
+		dma_addr_t *dma, int *is_last, gfp_t gfp_flags)
 {
 	u32 swap_temp;
 	struct ep_td_struct *dtd;
@@ -778,7 +778,7 @@ static struct ep_td_struct *fsl_build_dtd(struct fsl_req *req, unsigned *length,
 	*length = min(req->req.length - req->req.actual,
 			(unsigned)EP_MAX_LENGTH_TRANSFER);
 
-	dtd = dma_pool_alloc(udc_controller->td_pool, GFP_KERNEL, dma);
+	dtd = dma_pool_alloc(udc_controller->td_pool, gfp_flags, dma);
 	if (dtd == NULL)
 		return dtd;
 
@@ -828,7 +828,7 @@ static struct ep_td_struct *fsl_build_dtd(struct fsl_req *req, unsigned *length,
 }
 
 /* Generate dtd chain for a request */
-static int fsl_req_to_dtd(struct fsl_req *req)
+static int fsl_req_to_dtd(struct fsl_req *req, gfp_t gfp_flags)
 {
 	unsigned	count;
 	int		is_last;
@@ -837,7 +837,7 @@ static int fsl_req_to_dtd(struct fsl_req *req)
 	dma_addr_t dma;
 
 	do {
-		dtd = fsl_build_dtd(req, &count, &dma, &is_last);
+		dtd = fsl_build_dtd(req, &count, &dma, &is_last, gfp_flags);
 		if (dtd == NULL)
 			return -ENOMEM;
 
@@ -911,13 +911,11 @@ fsl_ep_queue(struct usb_ep *_ep, struct usb_request *_req, gfp_t gfp_flags)
 	req->req.actual = 0;
 	req->dtd_count = 0;
 
-	spin_lock_irqsave(&udc->lock, flags);
-
 	/* build dtds and push them to device queue */
-	if (!fsl_req_to_dtd(req)) {
+	if (!fsl_req_to_dtd(req, gfp_flags)) {
+		spin_lock_irqsave(&udc->lock, flags);
 		fsl_queue_td(ep, req);
 	} else {
-		spin_unlock_irqrestore(&udc->lock, flags);
 		return -ENOMEM;
 	}
 
@@ -1296,7 +1294,7 @@ static int ep0_prime_status(struct fsl_udc *udc, int direction)
 			ep_is_in(ep) ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 	req->mapped = 1;
 
-	if (fsl_req_to_dtd(req) == 0)
+	if (fsl_req_to_dtd(req, GFP_ATOMIC) == 0)
 		fsl_queue_td(ep, req);
 	else
 		return -ENOMEM;
@@ -1380,7 +1378,7 @@ static void ch9getstatus(struct fsl_udc *udc, u8 request_type, u16 value,
 	req->mapped = 1;
 
 	/* prime the data phase */
-	if ((fsl_req_to_dtd(req) == 0))
+	if ((fsl_req_to_dtd(req, GFP_ATOMIC) == 0))
 		fsl_queue_td(ep, req);
 	else			/* no mem */
 		goto stall;