kernel/linux.git/drivers/staging/gpib, branch v6.18.21

gpib: Fix memory leak in ni_usb_init()

2026-02-26T22:59:33+00:00

[ Upstream commit b89921eed8cf2d97250bac4be38dbcfbf048b586 ] In ni_usb_init(), if ni_usb_setup_init() fails, the function returns -EFAULT without freeing the allocated writes buffer, leading to a memory leak. Additionally, ni_usb_setup_init() returns 0 on failure, which causes ni_usb_init() to return -EFAULT, an inappropriate error code for this situation. Fix the leak by freeing writes in the error path. Modify ni_usb_setup_init() to return -EINVAL on failure and propagate this error code in ni_usb_init(). Fixes: 4e127de14fa7 ("staging: gpib: Add National Instruments USB GPIB driver") Suggested-by: Greg KH Suggested-by: Dave Penkler Co-developed-by: Jianhao Xu Signed-off-by: Jianhao Xu Signed-off-by: Zilin Guan Link: https://patch.msgid.link/20251230034546.929452-1-zilin@seu.edu.cn Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin

gpib: Fix error code in ni_usb_write_registers()

2026-02-26T22:59:33+00:00

[ Upstream commit 484e62252212c5b5fc62eaee5e4977143cb159c6 ] If ni_usb_receive_bulk_msg() succeeds but without reading 16 bytes, then the error code needs to be set. The current code returns success. Fixes: 4e127de14fa7 ("staging: gpib: Add National Instruments USB GPIB driver") Signed-off-by: Dan Carpenter Link: https://patch.msgid.link/aSlMpbE4IrQuBGFS@stanley.mountain Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin

gpib: Fix error code in ibonline()

2026-02-26T22:59:33+00:00

[ Upstream commit 96118565d24e7691e423d73be224b3a3fffc4680 ] This accidentally returns 1 on error, but it should return negative error codes. Fixes: 9dde4559e939 ("staging: gpib: Add GPIB common core driver") Signed-off-by: Dan Carpenter Link: https://patch.msgid.link/aSlMnaT1M104NJb2@stanley.mountain Signed-off-by: Greg Kroah-Hartman Signed-off-by: Sasha Levin

staging: gpib: Fix device reference leak in fmh_gpib driver

2025-10-13T08:55:03+00:00

The fmh_gpib driver contains a device reference count leak in fmh_gpib_attach_impl() where driver_find_device() increases the reference count of the device by get_device() when matching but this reference is not properly decreased. Add put_device() in fmh_gpib_detach(), which ensures that the reference count of the device is correctly managed. Found by code review. Cc: stable Fixes: 8e4841a0888c ("staging: gpib: Add Frank Mori Hess FPGA PCI GPIB driver") Signed-off-by: Ma Ke Reviewed-by: Dan Carpenter Signed-off-by: Greg Kroah-Hartman

staging: gpib: Return -EINTR on device clear

2025-10-13T08:54:44+00:00

When the ATN (Attention) line is asserted during a read we get a NIUSB_ATN_STATE_ERROR during a read. For the controller to send a device clear it asserts ATN. Normally this is an error but in the case of a device clear it should be regarded as an interrupt. Return -EINTR when the Device Clear Active State (DCAS) is entered else signal an error with dev_dbg with status instead of just dev_err. Signed-off-by: Dave Penkler Cc: stable Signed-off-by: Greg Kroah-Hartman

staging: gpib: Fix sending clear and trigger events

2025-10-13T08:54:39+00:00

This driver was not sending device clear or trigger events when the board entered the DCAS or DTAS state respectively in device mode. DCAS is the Device Clear Active State which is entered on receiving a selective device clear message (SDC) or universal device clear message (DCL) from the controller in charge. DTAS is the Device Trigger Active State which is entered on receiving a group execute trigger (GET) message from the controller. In order for an application, implementing a particular device, to detect when one of these states is entered the driver needs to send the appropriate event. Send the appropriate gpib_event when DCAS or DTAS is set in the reported status word. This sets the DCAS or DTAS bits in the board's status word which can be monitored by the application. Fixes: 4e127de14fa7 ("staging: gpib: Add National Instruments USB GPIB driver") Cc: stable Tested-by: Dave Penkler Signed-off-by: Dave Penkler Signed-off-by: Greg Kroah-Hartman

staging: gpib: Fix no EOI on 1 and 2 byte writes

2025-10-13T08:53:52+00:00

EOI (End Or Identify) is a hardware line on the GPIB bus that can be asserted with the last byte of a message to indicate the end of the transfer to the receiving device. In this driver, a write with send_eoi true is done in 3 parts: Send first byte directly Send remaining but 1 bytes using the fifo Send the last byte directly with EOI asserted The first byte in a write is always sent by writing to the tms9914 chip directly to setup for the subsequent fifo transfer. We were not checking for a 1 byte write with send_eoi true resulting in EOI not being asserted. Since the fifo transfer was not executed (fifotransfersize == 0) the retval in the test after the fifo transfer code was still 1 from the preceding direct write. This caused it to return without executing the final direct write which would have sent an unsollicited extra byte. For a 2 byte message the first byte was sent directly. But since the fifo transfer was not executed (fifotransfersize == 1) and the retval in the test after the fifo transfer code was still 1 from the preceding first byte write it returned before the final direct byte write with send_eoi true. The second byte was then sent as a separate 1 byte write to complete the 2 byte write count again without EOI being asserted as above. Only send the first byte directly if more than 1 byte is to be transferred with send_eoi true. Also check for retval < 0 for the error return in case the fifo code is not used (1 or 2 byte message with send_eoi true). Fixes: 09a4655ee1eb ("staging: gpib: Add HP/Agilent/Keysight 8235xx PCI GPIB driver") Cc: stable Tested-by: Dave Penkler Signed-off-by: Dave Penkler Signed-off-by: Greg Kroah-Hartman

staging: gpib: use int type to store negative error codes

2025-09-06T13:55:35+00:00

The "ret" variable is used to store the return from bb_write() returns either zero on success or negative error codes on failure. Storing the error codes in size_t which is an unsigned long, doesn't cause an issue at runtime but it's ugly as pants. Change "ret" from size_t to int type. No effect on runtime. Signed-off-by: Qianfeng Rong Reviewed-by: Dan Carpenter Link: https://lore.kernel.org/r/20250826123208.300145-1-rongqianfeng@vivo.com Signed-off-by: Greg Kroah-Hartman

staging: gpib: tnt4882: Remove redundant header files

2025-09-06T13:54:23+00:00

The header file is already included on line 12, outside of the #ifdef CONFIG_GPIB_PCMCIA block. It does not need to be included again inside the #ifdef CONFIG_GPIB_PCMCIA block. Signed-off-by: Liao Yuanhong Link: https://lore.kernel.org/r/20250819131203.152724-1-liaoyuanhong@vivo.com Signed-off-by: Greg Kroah-Hartman

staging: gpib: tidy-up comments

2025-08-19T10:58:19+00:00

Improve comment readability: - "//comment" -> "// comment" - Align comments vertically in columns - Enforce consistency between "// comments" and "/* comments */" Signed-off-by: Luke Yang Link: https://lore.kernel.org/r/aJ4ykOs_MmjnQdPa@luyang-thinkpadp1gen7.toromso.csb Signed-off-by: Greg Kroah-Hartman