usb: host: Fix excessive alignment restriction for local memory allocations

The PAGE_SHIFT alignment restriction to devm_gen_pool_create() quickly
exhaust local memory because most allocations are much smaller than
PAGE_SIZE. This causes USB device failures such as

usb 1-2.1: reset full-speed USB device number 4 using sm501-usb
sd 1:0:0:0: [sda] tag#0 UNKNOWN(0x2003) Result: hostbyte=0x03 driverbyte=0x00
sd 1:0:0:0: [sda] tag#0 CDB: opcode=0x28 28 00 00 00 08 7c 00 00 f0 00
print_req_error: I/O error, dev sda, sector 2172 flags 80700

when trying to boot from the SM501 USB controller on SH4 with QEMU.

Align allocations as required but not necessarily much more than that.
The HCCA, TD and ED structures align with 256, 32 and 16 byte memory
boundaries, as specified by the Open HCI[1]. The min_alloc_order argument
to devm_gen_pool_create is now somewhat arbitrarily set to 4 (16 bytes).
Perhaps it could be somewhat lower for general buffer allocations.

Reference:

[1] "Open Host Controller Interface Specification for USB",
release 1.0a, Compaq, Microsoft, National Semiconductor, 1999,
pp. 16, 19, 33.

Reported-by: Guenter Roeck <[e-mail]>
Signed-off-by: Fredrik Noring <[e-mail]>
Tested-by: Guenter Roeck <[e-mail]>
Signed-off-by: Christoph Hellwig <[e-mail]>

drivers/usb/core/hcd.c

···
 	int err;
 	void *local_mem;
 
-	hcd->localmem_pool = devm_gen_pool_create(hcd->self.sysdev, PAGE_SHIFT,
+	hcd->localmem_pool = devm_gen_pool_create(hcd->self.sysdev, 4,
 						  dev_to_node(hcd->self.sysdev),
 						  dev_name(hcd->self.sysdev));
 	if (IS_ERR(hcd->localmem_pool))

drivers/usb/host/ohci-hcd.c

···
 	ohci->prev_frame_no = IO_WATCHDOG_OFF;
 
 	if (hcd->localmem_pool)
-		ohci->hcca = gen_pool_dma_alloc(hcd->localmem_pool,
+		ohci->hcca = gen_pool_dma_alloc_align(hcd->localmem_pool,
 						sizeof(*ohci->hcca),
-						&ohci->hcca_dma);
+						&ohci->hcca_dma, 256);
 	else
 		ohci->hcca = dma_alloc_coherent(hcd->self.controller,
 						sizeof(*ohci->hcca),

drivers/usb/host/ohci-mem.c

···
 	struct usb_hcd	*hcd = ohci_to_hcd(hc);
 
 	if (hcd->localmem_pool)
-		td = gen_pool_dma_zalloc(hcd->localmem_pool, sizeof(*td), &dma);
+		td = gen_pool_dma_zalloc_align(hcd->localmem_pool,
+				sizeof(*td), &dma, 32);
 	else
 		td = dma_pool_zalloc(hc->td_cache, mem_flags, &dma);
 	if (td) {
···
 	struct usb_hcd	*hcd = ohci_to_hcd(hc);
 
 	if (hcd->localmem_pool)
-		ed = gen_pool_dma_zalloc(hcd->localmem_pool, sizeof(*ed), &dma);
+		ed = gen_pool_dma_zalloc_align(hcd->localmem_pool,
+				sizeof(*ed), &dma, 16);
 	else
 		ed = dma_pool_zalloc(hc->ed_cache, mem_flags, &dma);
 	if (ed) {