kernel/linux.git/drivers/usb/chipidea, branch v6.12.80

usb: chipidea: udc: fix DMA and SG cleanup in _ep_nuke()

2026-03-04T12:21:24+00:00

[ Upstream commit cea2a1257a3b5ea3e769a445b34af13e6aa5a123 ] The ChipIdea UDC driver can encounter "not page aligned sg buffer" errors when a USB device is reconnected after being disconnected during an active transfer. This occurs because _ep_nuke() returns requests to the gadget layer without properly unmapping DMA buffers or cleaning up scatter-gather bounce buffers. Root cause: When a disconnect happens during a multi-segment DMA transfer, the request's num_mapped_sgs field and sgt.sgl pointer remain set with stale values. The request is returned to the gadget driver with status -ESHUTDOWN but still has active DMA state. If the gadget driver reuses this request on reconnect without reinitializing it, the stale DMA state causes _hardware_enqueue() to skip DMA mapping (seeing non-zero num_mapped_sgs) and attempt to use freed/invalid DMA addresses, leading to alignment errors and potential memory corruption. The normal completion path via _hardware_dequeue() properly calls usb_gadget_unmap_request_by_dev() and sglist_do_debounce() before returning the request. The _ep_nuke() path must do the same cleanup to ensure requests are returned in a clean, reusable state. Fix: Add DMA unmapping and bounce buffer cleanup to _ep_nuke() to mirror the cleanup sequence in _hardware_dequeue(): - Call usb_gadget_unmap_request_by_dev() if num_mapped_sgs is set - Call sglist_do_debounce() with copy=false if bounce buffer exists This ensures that when requests are returned due to endpoint shutdown, they don't retain stale DMA mappings. The 'false' parameter to sglist_do_debounce() prevents copying data back (appropriate for shutdown path where transfer was aborted). Signed-off-by: Mario Peter Reviewed-by: Xu Yang Acked-by: Peter Chen Link: https://patch.msgid.link/20260108165902.795354-1-mario.peter@leica-geosystems.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin

usb: chipidea: udc: disconnect/reconnect from host when do suspend/resume

2025-07-10T14:05:11+00:00

commit 31a6afbe86e8e9deba9ab53876ec49eafc7fd901 upstream. Shawn and John reported a hang issue during system suspend as below: - USB gadget is enabled as Ethernet - There is data transfer over USB Ethernet (scp a big file between host and device) - Device is going in/out suspend (echo mem > /sys/power/state) The root cause is the USB device controller is suspended but the USB bus is still active which caused the USB host continues to transfer data with device and the device continues to queue USB requests (in this case, a delayed TCP ACK packet trigger the issue) after controller is suspended, however the USB controller clock is already gated off. Then if udc driver access registers after that point, the system will hang. The correct way to avoid such issue is to disconnect device from host when the USB bus is not at suspend state. Then the host will receive disconnect event and stop data transfer in time. To continue make USB gadget device work after system resume, this will reconnect device automatically. To make usb wakeup work if USB bus is already at suspend state, this will keep connection for it only when USB device controller has enabled wakeup capability. Reported-by: Shawn Guo Reported-by: John Ernberg Closes: https://lore.kernel.org/linux-usb/aEZxmlHmjeWcXiF3@dragon/ Tested-by: John Ernberg # iMX8QXP Fixes: 235ffc17d014 ("usb: chipidea: udc: add suspend/resume support for device controller") Cc: stable Reviewed-by: Jun Li Signed-off-by: Xu Yang Acked-by: Peter Chen Link: https://lore.kernel.org/r/20250614124914.207540-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman

usb: chipidea: ci_hdrc_imx: implement usb_phy_init() error handling

2025-05-02T05:59:12+00:00

commit 8c531e0a8c2d82509ad97c6d3a1e6217c7ed136d upstream. usb_phy_init() may return an error code if e.g. its implementation fails to prepare/enable some clocks. And properly rollback on probe error path by calling the counterpart usb_phy_shutdown(). Found by Linux Verification Center (linuxtesting.org). Fixes: be9cae2479f4 ("usb: chipidea: imx: Fix ULPI on imx53") Cc: stable Signed-off-by: Fedor Pchelkin Acked-by: Peter Chen Link: https://lore.kernel.org/r/20250316102658.490340-4-pchelkin@ispras.ru Signed-off-by: Greg Kroah-Hartman

usb: chipidea: ci_hdrc_imx: fix call balance of regulator routines

2025-05-02T05:59:12+00:00

commit 8cab0e9a3f3e8d700179e0d6141643d54a267fd5 upstream. Upon encountering errors during the HSIC pinctrl handling section the regulator should be disabled. Use devm_add_action_or_reset() to let the regulator-disabling routine be handled by device resource management stack. Found by Linux Verification Center (linuxtesting.org). Fixes: 4d6141288c33 ("usb: chipidea: imx: pinctrl for HSIC is optional") Cc: stable Signed-off-by: Fedor Pchelkin Acked-by: Peter Chen Link: https://lore.kernel.org/r/20250316102658.490340-3-pchelkin@ispras.ru Signed-off-by: Greg Kroah-Hartman

usb: chipidea: ci_hdrc_imx: fix usbmisc handling

2025-05-02T05:59:12+00:00

commit 4e28f79e3dffa52d327b46d1a78dac16efb5810b upstream. usbmisc is an optional device property so it is totally valid for the corresponding data->usbmisc_data to have a NULL value. Check that before dereferencing the pointer. Found by Linux Verification Center (linuxtesting.org) with Svace static analysis tool. Fixes: 74adad500346 ("usb: chipidea: ci_hdrc_imx: decrement device's refcount in .remove() and in the error path of .probe()") Cc: stable Signed-off-by: Fedor Pchelkin Acked-by: Peter Chen Link: https://lore.kernel.org/r/20250316102658.490340-2-pchelkin@ispras.ru Signed-off-by: Greg Kroah-Hartman

usb: chipidea: ci_hdrc_imx: decrement device's refcount in .remove() and in the error path of .probe()

2025-01-17T12:40:54+00:00

commit 74adad500346fb07d69af2c79acbff4adb061134 upstream. Current implementation of ci_hdrc_imx_driver does not decrement the refcount of the device obtained in usbmisc_get_init_data(). Add a put_device() call in .remove() and in .probe() before returning an error. This bug was found by an experimental static analysis tool that I am developing. Cc: stable Fixes: f40017e0f332 ("chipidea: usbmisc_imx: Add USB support for VF610 SoCs") Signed-off-by: Joe Hattori Acked-by: Peter Chen Link: https://lore.kernel.org/r/20241216015539.352579-1-joe@pf.is.s.u-tokyo.ac.jp Signed-off-by: Greg Kroah-Hartman

usb: chipidea: udc: handle USB Error Interrupt if IOC not set

2024-12-14T19:04:07+00:00

[ Upstream commit 548f48b66c0c5d4b9795a55f304b7298cde2a025 ] As per USBSTS register description about UEI: When completion of a USB transaction results in an error condition, this bit is set by the Host/Device Controller. This bit is set along with the USBINT bit, if the TD on which the error interrupt occurred also had its interrupt on complete (IOC) bit set. UI is set only when IOC set. Add checking UEI to fix miss call isr_tr_complete_handler() when IOC have not set and transfer error happen. Acked-by: Peter Chen Signed-off-by: Xu Yang Link: https://lore.kernel.org/r/20240926022906.473319-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin

usb: chipidea: udc: create bounce buffer for problem sglist entries if possible

2024-12-14T19:04:07+00:00

[ Upstream commit edfcc455c85ccc5855f0c329ca5a2d85cc9fc6c6 ] The chipidea controller doesn't fully support sglist, such as it can not transfer data spanned more dTDs to form a bus packet, so it can only work on very limited cases. The limitations as below: 1. the end address of the first sg buffer must be 4KB aligned. 2. the start and end address of the middle sg buffer must be 4KB aligned. 3. the start address of the first sg buffer must be 4KB aligned. However, not all the use cases violate these limitations. To make the controller compatible with most of the cases, this will try to bounce the problem sglist entries which can be found by sglist_get_invalid_entry(). Then a bounced line buffer (the size will roundup to page size) will be allocated to replace the remaining problem sg entries. The data will be copied between problem sg entries and bounce buffer according to the transfer direction. The bounce buffer will be freed when the request completed. Acked-by: Peter Chen Signed-off-by: Xu Yang Link: https://lore.kernel.org/r/20240923081203.2851768-3-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin

usb: chipidea: udc: limit usb request length to max 16KB

2024-12-14T19:04:07+00:00

[ Upstream commit ca8d18aa7b0f22d66a3ca9a90d8f73431b8eca89 ] To let the device controller work properly on short packet limitations, one usb request should only correspond to one dTD. Then every dTD will set IOC. In theory, each dTD support up to 20KB data transfer if the offset is 0. Due to we cannot predetermine the offset, this will limit the usb request length to max 16KB. This should be fine since most of the user transfer data based on this size policy. Signed-off-by: Xu Yang Acked-by: Peter Chen Link: https://lore.kernel.org/r/20240923081203.2851768-2-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin

usb: chipidea: add CI_HDRC_HAS_SHORT_PKT_LIMIT flag

2024-12-14T19:04:07+00:00

[ Upstream commit ec841b8d73cff37f8960e209017efe1eb2fb21f2 ] Currently, the imx deivice controller has below limitations: 1. can't generate short packet interrupt if IOC not set in dTD. So if one request span more than one dTDs and only the last dTD set IOC, the usb request will pending there if no more data comes. 2. the controller can't accurately deliver data to differtent usb requests in some cases due to short packet. For example: one usb request span 3 dTDs, then if the controller received a short packet the next packet will go to 2nd dTD of current request rather than the first dTD of next request. 3. can't build a bus packet use multiple dTDs. For example: controller needs to send one packet of 512 bytes use dTD1 (200 bytes) + dTD2 (312 bytes), actually the host side will see 200 bytes short packet. Based on these limits, add CI_HDRC_HAS_SHORT_PKT_LIMIT flag and use it on imx platforms. Signed-off-by: Xu Yang Acked-by: Peter Chen Link: https://lore.kernel.org/r/20240923081203.2851768-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin