usb: xhci: Enable the TRB overfetch quirk on VIA VL805

commit c133ec0e5717868c9967fa3df92a55e537b1aead upstream.

Raspberry Pi is a major user of those chips and they discovered a bug -
when the end of a transfer ring segment is reached, up to four TRBs can
be prefetched from the next page even if the segment ends with link TRB
and on page boundary (the chip claims to support standard 4KB pages).

It also appears that if the prefetched TRBs belong to a different ring
whose doorbell is later rung, they may be used without refreshing from
system RAM and the endpoint will stay idle if their cycle bit is stale.

Other users complain about IOMMU faults on x86 systems, unsurprisingly.

Deal with it by using existing quirk which allocates a dummy page after
each transfer ring segment. This was seen to resolve both problems. RPi
came up with a more efficient solution, shortening each segment by four
TRBs, but it complicated the driver and they ditched it for this quirk.

Also rename the quirk and add VL805 device ID macro.

Signed-off-by: Michal Pecio <michal.pecio@gmail.com>
Link: https://github.com/raspberrypi/linux/issues/4685
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=215906
CC: stable@vger.kernel.org
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250225095927.2512358-2-mathias.nyman@linux.intel.com
[ Michal: merge conflict with white space and an unrelated quirk ]
Signed-off-by: Michal Pecio <michal.pecio@gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

3 files changed, 9 insertions, 5 deletions

diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 8740bd443f13..5b0e00978322 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -2494,7 +2494,8 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	 * and our use of dma addresses in the trb_address_map radix tree needs
 	 * TRB_SEGMENT_SIZE alignment, so we pick the greater alignment need.
 	 */
-	if (xhci->quirks & XHCI_ZHAOXIN_TRB_FETCH)
+	if (xhci->quirks & XHCI_TRB_OVERFETCH)
+		/* Buggy HC prefetches beyond segment bounds - allocate dummy space at the end */
 		xhci->segment_pool = dma_pool_create("xHCI ring segments", dev,
 				TRB_SEGMENT_SIZE * 2, TRB_SEGMENT_SIZE * 2, xhci->page_size * 2);
 	else
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index f716c848285f..2be84d5e9261 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -37,6 +37,8 @@
 #define PCI_DEVICE_ID_EJ168		0x7023
 #define PCI_DEVICE_ID_EJ188		0x7052
 
+#define PCI_DEVICE_ID_VIA_VL805				0x3483
+
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI		0x8c31
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI		0x9c31
 #define PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_XHCI	0x9cb1
@@ -296,8 +298,9 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 			pdev->device == 0x3432)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
 
-	if (pdev->vendor == PCI_VENDOR_ID_VIA && pdev->device == 0x3483) {
+	if (pdev->vendor == PCI_VENDOR_ID_VIA && pdev->device == PCI_DEVICE_ID_VIA_VL805) {
 		xhci->quirks |= XHCI_LPM_SUPPORT;
+		xhci->quirks |= XHCI_TRB_OVERFETCH;
 		xhci->quirks |= XHCI_EP_CTX_BROKEN_DCS;
 	}
 
@@ -347,11 +350,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 
 		if (pdev->device == 0x9202) {
 			xhci->quirks |= XHCI_RESET_ON_RESUME;
-			xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH;
+			xhci->quirks |= XHCI_TRB_OVERFETCH;
 		}
 
 		if (pdev->device == 0x9203)
-			xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH;
+			xhci->quirks |= XHCI_TRB_OVERFETCH;
 	}
 
 	/* xHC spec requires PCI devices to support D3hot and D3cold */
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index efce7f40dd94..2d2e9c59add6 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1902,7 +1902,7 @@ struct xhci_hcd {
 #define XHCI_EP_CTX_BROKEN_DCS	BIT_ULL(42)
 #define XHCI_SUSPEND_RESUME_CLKS	BIT_ULL(43)
 #define XHCI_RESET_TO_DEFAULT	BIT_ULL(44)
-#define XHCI_ZHAOXIN_TRB_FETCH	BIT_ULL(45)
+#define XHCI_TRB_OVERFETCH	BIT_ULL(45)
 #define XHCI_ZHAOXIN_HOST	BIT_ULL(46)
 
 	unsigned int		num_active_eps;