- 13 Oct, 2014 40 commits
-
-
Nathan Lynch authored
commit fbfb872f upstream. The TPIDRURO and TPIDRURW registers need to be flushed during exec; otherwise TLS information is potentially leaked. TPIDRURO in particular needs careful treatment. Since flush_thread basically needs the same code used to set the TLS in arm_syscall, pull that into a common set_tls helper in tls.h and use it in both places. Similarly, TEEHBR needs to be cleared during exec as well. Clearing its save slot in thread_info isn't right as there is no guarantee that a thread switch will occur before the new program runs. Just setting the register directly is sufficient. Signed-off-by:
Nathan Lynch <nathan_lynch@mentor.com> Acked-by:
Will Deacon <will.deacon@arm.com> Signed-off-by:
Russell King <rmk+kernel@arm.linux.org.uk> Signed-off-by:
Jiri Slaby <jslaby@suse.cz>
-
Sudeep Holla authored
commit a040803a upstream. Since commit 1dbfa187 ("ARM: irq migration: force migration off CPU going down") the ARM interrupt migration code on cpu offline calls irqchip.irq_set_affinity() with the argument force=true. At the point of this change the argument had no effect because it was not used by any interrupt chip driver and there was no semantics defined. This changed with commit 01f8fa4f ("genirq: Allow forcing cpu affinity of interrupts") which made the force argument useful to route interrupts to not yet online cpus without checking the target cpu against the cpu online mask. The following commit ffde1de6 ("irqchip: gic: Support forced affinity setting") implemented this for the GIC interrupt controller. As a consequence the ARM cpu offline irq migration fails if CPU0 is offlined, because CPU0 is still set in the affinity mask and the validataion against cpu online mask is skipped to the force argument being true. The following first_cpu(mask) selection always selects CPU0 as the target. Solve the issue by calling irq_set_affinity() with force=false from the CPU offline irq migration code so the GIC driver validates the affinity mask against CPU online mask and therefore removes CPU0 from the possible target candidates. Tested on TC2 hotpluging CPU0 in and out. Without this patch the system locks up as the IRQs are not migrated away from CPU0. Signed-off-by:
Sudeep Holla <sudeep.holla@arm.com> Acked-by:
Thomas Gleixner <tglx@linutronix.de> Acked-by:
Mark Rutland <mark.rutland@arm.com> Signed-off-by:
-
Mark Rutland authored
commit 85868313 upstream. The ARMv6 and ARMv7 early abort handlers clear the exclusive monitors upon entry to the kernel, but this is redundant: - We clear the monitors on every exception return since commit 200b812d ("Clear the exclusive monitor when returning from an exception"), so this is not necessary to ensure the monitors are cleared before returning from a fault handler. - Any dummy STREX will target a temporary scratch area in memory, and may succeed or fail without corrupting useful data. Its status value will not be used. - Any other STREX in the kernel must be preceded by an LDREX, which will initialise the monitors consistently and will not depend on the earlier state of the monitors. Therefore we have no reason to care about the initial state of the exclusive monitors when a data abort is taken, and clearing the monitors prior to exception return (as we already do) is sufficient. This patch removes the redundant clearing of the exclusive monitors from the early abort handlers. Signed-off-by:
-
Jorge A. Ventura authored
commit 3d0763c0 upstream. The spi hangs waiting the completion of omap2_mcspi_rx_callback. Signed-off-by:
Jorge A. Ventura <jorge.araujo.ventura@gmail.com> Signed-off-by:
Mark Brown <broonie@linaro.org> Signed-off-by:
-
Trond Myklebust authored
commit cd9288ff upstream. James Drew reports another bug whereby the NFS client is now sending an OPEN_DOWNGRADE in a situation where it should really have sent a CLOSE: the client is opening the file for O_RDWR, but then trying to do a downgrade to O_RDONLY, which is not allowed by the NFSv4 spec. Reported-by:
James Drews <drews@engr.wisc.edu> Link: http://lkml.kernel.org/r/541AD7E5.8020409@engr.wisc.edu Fixes: aee7af35 (NFSv4: Fix problems with close in the presence...) Signed-off-by:
Trond Myklebust <trond.myklebust@primarydata.com> Signed-off-by:
-
Steve Dickson authored
commit 080af20c upstream. There is a race between nfs4_state_manager() and nfs_server_remove_lists() that happens during a nfsv3 mount. The v3 mount notices there is already a supper block so nfs_server_remove_lists() called which uses the nfs_client_lock spin lock to synchronize access to the client list. At the same time nfs4_state_manager() is running through the client list looking for work to do, using the same lock. When nfs4_state_manager() wins the race to the list, a v3 client pointer is found and not ignored properly which causes the panic. Moving some protocol checks before the state checking avoids the panic. Signed-off-by:
Steve Dickson <steved@redhat.com> Signed-off-by:
-
Olav Haugan authored
commit 1fc870c7 upstream. Stage-1 context banks do not have the SMMU_CBn_TCR[SL0] field since it is only applicable to stage-2 context banks. This patch ensures that we don't set the reserved TCR bits for stage-1 translations. Signed-off-by:
Olav Haugan <ohaugan@codeaurora.org> Signed-off-by:
-
Lee, Chun-Yi authored
commit 9389f46e upstream. The value64 parameter is an u64 point that used to transfer the value for write to CMOS, or used to return the value that's read from CMOS. The value64 is an u64 point, so don't need get address again. It causes acpi_cmos_rtc_space_handler always return 0 to reader and didn't write expected value to CMOS. Signed-off-by:
Lee, Chun-Yi <jlee@suse.com> Signed-off-by:
Rafael J. Wysocki <rafael.j.wysocki@intel.com> Signed-off-by:
-
Felipe Balbi authored
commit 81a60b7f upstream. we don't to gate clocks until our children are done with their remove path. Fixes: af310e96 (usb: dwc3: omap: use runtime API's to enable clocks) Signed-off-by:
Felipe Balbi <balbi@ti.com> Signed-off-by:
-
Alan Stern authored
commit 7312b5dd upstream. Old code in ehci-hcd tries to expedite disabling endpoints after the controller has stopped, by destroying the endpoint's associated QH without first unlinking the QH. This was necessary back when the driver wasn't so careful about keeping track of the controller's state. But now we are careful about it, and the driver knows that when the controller isn't running, no unlinking delay is needed. Furthermore, skipping the unlink step will trigger a BUG() in qh_destroy() when the preceding QH is released, because the link pointer will be non-NULL. Removing the lines that skip the unlinking step and go directly to QH_STATE_IDLE fixes the problem. Signed-off-by:
Alan Stern <stern@rowland.harvard.edu> Reported-by:
Joe Lawrence <joe.lawrence@stratus.com> Tested-by:
-
Mark authored
commit c80b4495 upstream. This patch adds quirks for Entrega Technologies (later Xircom PortGear) USB- SCSI converters. They use Shuttle Technology EUSB-01/EUSB-S1 chips. The US_FL_SCM_MULT_TARG quirk is needed to allow multiple devices on the SCSI chain to be accessed. Without it only the (single) device with SCSI ID 0 can be used. The standalone converter sold by Entrega had model number U1-SC25. Xircom acquired Entrega and re-branded the product line PortGear. The PortGear USB to SCSI Converter (model PGSCSI) is internally identical to the Entrega product, but later models may use a different USB ID. The Entrega-branded units have USB ID 1645:0007, as does my Xircom PGSCSI, but the Windows and Macintosh drivers also support 085A:0028. Entrega also sold the "Mac USB Dock", which provides two USB ports, a Mac (8-pin mini-DIN) serial port and a SCSI port. It appears to the computer as a four-port hub, USB-serial, and USB-SCSI converters. The USB-SCSI part may have initially used the same ID as the standalone U1-SC25 (1645:0007), but later production used 085A:0026. My Xircom PortGear PGSCSI has bcdDevice=0x0100. Units with bcdDevice=0x0133 probably also exist. This patch adds quirks for 1645:0007, 085A:0026 and 085A:0028. The Windows driver INF file also mentions 085A:0032 "PortStation SCSI Module", but I couldn't find any mention of that actually existing in the wild; perhaps it was cancelled before release? Signed-off-by:
Mark Knibbs <markk@clara.co.uk> Signed-off-by:
-
Mark authored
commit b6a3ed67 upstream. Hi, The Ariston Technologies iConnect 025 and iConnect 050 (also known as e.g. iSCSI-50) are SCSI-USB converters which use Shuttle Technology/SCM Microsystems chips. Only the connectors differ; both have the same USB ID. The US_FL_SCM_MULT_TARG quirk is required to use SCSI devices with ID other than 0. I don't have one of these, but based on the other entries for Shuttle/ SCM-based converters this patch is very likely correct. I used 0x0000 and 0x9999 for bcdDeviceMin and bcdDeviceMax because I'm not sure which bcdDevice value the products use. Signed-off-by:
-
Mark authored
commit 67d365a5 upstream. The Adaptec USBConnect 2000 is another SCSI-USB converter which uses Shuttle Technology/SCM Microsystems chips. The US_FL_SCM_MULT_TARG quirk is required to use SCSI devices with ID other than 0. I don't have a USBConnect 2000, but based on the other entries for Shuttle/ SCM-based converters this patch is very likely correct. I used 0x0000 and 0x9999 for bcdDeviceMin and bcdDeviceMax because I'm not sure which bcdDevice value the product uses. Signed-off-by:
-
Mark authored
commit c66f1c62 upstream. The Iomega Jaz USB Adapter is a SCSI-USB converter cable. The hardware seems to be identical to e.g. the Microtech XpressSCSI, using a Shuttle/ SCM chip set. However its firmware restricts it to only work with Jaz drives. On connecting the cable a message like this appears four times in the log: reset full speed USB device number 4 using uhci_hcd That's non-fatal but the US_FL_SINGLE_LUN quirk fixes it. Signed-off-by:
-
Joe Lawrence authored
commit c605f3cd upstream. During surprise device hotplug removal tests, it was observed that hub_events may try to call usb_lock_device on a device that has already been freed. Protect the usb_device by taking out a reference (under the hub_event_lock) when hub_events pulls it off the list, returning the reference after hub_events is finished using it. Signed-off-by:
-
Mathias Nyman authored
commit 96044694 upstream. Resuming from hibernate (S4) will restart and re-initialize xHC. The device contexts are freed and will be re-allocated later during device reset. Usb core will disable link pm in device resume before device reset, which will try to change the max exit latency, accessing the device contexts before they are re-allocated. There is no need to zero (disable) the max exit latency when disabling hw lpm for a freshly re-initialized xHC. So check that device context exists before doing anything. The max exit latency will be set again after device reset when usb core enables the link pm. Reported-by:
Imre Deak <imre.deak@intel.com> Tested-by:
Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by:
-
Mathias Nyman authored
commit c207e7c5 upstream. If xhci initialization fails before the roothub bandwidth domains (xhci->rh_bw[i]) are allocated it will oops when trying to access rh_bw members in xhci_mem_cleanup(). Reported-by:
Manuel Reimer <manuel.reimer@gmx.de> Signed-off-by:
-
Felipe Balbi authored
commit 96908589 upstream. Commit 71c731a2 (usb: host: xhci: Fix Compliance Mode on SN65LVP3502CP Hardware) implemented a workaround for a known issue with Texas Instruments' USB 3.0 redriver IC but it left a condition where any xHCI host would be taken out of reset if port was placed in compliance mode and there was no device connected to the port. That condition would trigger a fake connection to a non-existent device so that usbcore would trigger a warm reset of the port, thus taking the link out of reset. This has the side-effect of preventing any xHCI host connected to a Linux machine from starting and running the USB 3.0 Electrical Compliance Suite because the port will mysteriously taken out of compliance mode and, thus, xHCI won't step through the necessary compliance patterns for link validation. This patch fixes the issue by just adding a missing check for XHCI_COMP_MODE_QUIRK inside xhci_hub_report_usb3_link_state() when PORT_CAS isn't set. This patch should be backported to all kernels containing commit 71c731a2. Fixes: 71c731a2 (usb: host: xhci: Fix Compliance Mode on SN65LVP3502CP Hardware) Cc: Alexis R. Cortes <alexis.cortes@ti.com> Signed-off-by:
-
Thomas Pugliese authored
commit 675f0ab2 upstream. Make sure the uwb_dev->bce entry is set before calling uwb_dev_add in uwbd_dev_onair so that usermode will only see the device after it is properly initialized. This fixes a kernel panic that can occur if usermode tries to access the IEs sysfs attribute of a UWB device before the driver has had a chance to set the beacon cache entry. Signed-off-by:
Thomas Pugliese <thomas.pugliese@gmail.com> Signed-off-by:
-
Johan Hovold authored
commit ee444609 upstream. Add device id for NOVITUS Bono E thermal printer. Reported-by:
Emanuel Koczwara <poczta@emanuelkoczwara.pl> Signed-off-by:
Johan Hovold <johan@kernel.org> Signed-off-by:
-
Taylor Braun-Jones authored
commit 9c491c37 upstream. Signed-off-by:
Taylor Braun-Jones <taylor.braun-jones@ge.com> Cc: Johan Hovold <johan@kernel.org> Signed-off-by:
-
Ivan T. Ivanov authored
commit 233c7daf upstream. Initialize USB PHY after every Link controller reset Cc: Tim Bird <tbird20d@gmail.com> Signed-off-by:
Peter Chen <peter.chen@freescale.com> Signed-off-by:
Ivan T. Ivanov <iivanov@mm-sol.com> Signed-off-by:
-
Ivan T. Ivanov authored
commit ea290056 upstream. PHY drivers keep track of the current state of the hardware, so don't change PHY settings under it. Cc: Tim Bird <tbird20d@gmail.com> Signed-off-by:
-
Thierry Reding authored
commit 9ce9ec95 upstream. The PHY configuration is stored in an opaque "config" field, but when allocating the structure, its proper size needs to be known. In the case of UTMI, the proper structure is tegra_utmip_config of which a local variable already exists, so we can use that to obtain the size from. Fixes the following warning from the sparse checker: drivers/usb/phy/phy-tegra-usb.c:882:17: warning: expression using sizeof(void) Fixes: 81d5dfe6 (usb: phy: tegra: Read UTMIP parameters from device tree) Signed-off-by:
Thierry Reding <treding@nvidia.com> Signed-off-by:
-
Bjørn Mork authored
commit 5b3da692 upstream. This VID:PID is used for some Direct IP devices behaving identical to the already supported 0F3D:68AA devices. Reported-by:
Lars Melin <larsm17@gmail.com> Signed-off-by:
Bjørn Mork <bjorn@mork.no> Signed-off-by:
-
Bjørn Mork authored
commit 049255f5 upstream. Sierra Wireless Direct IP devices using the 68A3 product ID can be configured for modes including a CDC ECM class function. The known example uses interface numbers 12 and 13 for the ECM control and data interfaces respectively, consistent with CDC MBIM function interface numbering on other Sierra devices. It seems cleaner to restrict this driver to the ff/ff/ff vendor specific interfaces rather than increasing the already long interface number blacklist. This should be more future proof if Sierra adds more class functions using interface numbers not yet in the blacklist. Signed-off-by:
-
Johan Hovold authored
commit 754eb21c upstream. Remove dublicate Qualcom PID 0x3197 which is already handled by the moto-modem driver since commit 6986a978 ("USB: add new moto_modem driver for some Morotola phones"). Fixes: 799ee924 ("USB: serial: add zte_ev.c driver") Signed-off-by:
-
Johan Hovold authored
commit 95be5739 upstream. Remove dublicate Gobi PID 0x9008 which is already handled by the qcserial driver since commit f05932c0 ("USB: qcserial: Add extra device IDs"). Fixes: 799ee924 ("USB: serial: add zte_ev.c driver") Signed-off-by:
-
Johan Hovold authored
commit 63a901c0 upstream. This reverts commit 73228a05 ("USB: option,zte_ev: move most ZTE CDMA devices to zte_ev"). Move the IDs of the devices that were previously driven by the option driver back to that driver. As several users have reported, the zte_ev driver is causing random disconnects as well as reconnect failures. A closer analysis of the zte_ev setup code reveals that it consists of standard CDC requests (SET/GET_LINE_CODING and SET_CONTROL_LINE_STATE) but unfortunately fails to get some of those right. In particular, as reported by Liu Lei, it fails to lower DTR/RTS on close. It also appears that the control requests lack the interface argument. Note that the zte_ev driver is based on code (once) distributed by ZTE that still appears to originally have been reverse-engineered and bolted onto the generic driver. Since line control is already handled properly by the option driver, and the SET/GET_LINE_CODING requests appears to be redundant (amounts to a SET 9600 8N1), this is a first step in ultimately removing the redundant zte_ev driver. Note that AC2726 had already been moved back to option, and that some IDs were in the device table of both drivers prior to the commit being reverted. Reported-by:
Lei Liu <liu.lei78@zte.com.cn> Signed-off-by:
-
Brennan Ashton authored
commit d7730273 upstream. This VIA Telecom baseband processor is used is used by by u-blox in both the FW2770 and FW2760 products and may be used in others as well. This patch has been tested on both of these modem versions. Signed-off-by:
Brennan Ashton <bashton@brennanashton.com> Signed-off-by:
-
Johan Hovold authored
commit f0e4cba2 upstream. Do not log normal interrupt-urb shutdowns as errors. The option driver has always been logging any nonzero interrupt-urb status as an error, including when the urb is killed during normal operation. Commit 9096f1fb ("USB: usb_wwan: fix potential NULL-deref at resume") moved the interrupt urb submission from port probe and release to open and close, thus potentially increasing the number of these false-positive error messages dramatically. Reported-by:
Ed Butler <ressy66@ausics.net> Tested-by:
-
Johan Hovold authored
commit 5654699f upstream. Make sure to verify the number of ports requested by subdriver to avoid writing beyond the end of fixed-size array in interface data. The current usb-serial implementation is limited to eight ports per interface but failed to verify that the number of ports requested by a subdriver (which could have been determined from device descriptors) did not exceed this limit. Signed-off-by:
-
Stephen Hemminger authored
commit 5b6b80ae upstream. I have a j5 create (JUA210) USB 2 video device and adding it device id to SIS USB video gets it to work. Signed-off-by:
Stephen Hemminger <stephen@networkplumber.org> Signed-off-by:
-
Johan Hovold authored
commit d979e9f9 upstream. Make sure to verify the maximum number of endpoints per type to avoid writing beyond the end of a stack-allocated array. The current usb-serial implementation is limited to eight ports per interface but failed to verify that the number of endpoints of a certain type reported by a device did not exceed this limit. Signed-off-by:
-
Greg KH authored
commit 91fcb1ce upstream. This adds a new device id to the pl2303 driver for the ZTEK device. Reported-by:
Mike Chu <Mike-Chu@prolific.com.tw> Signed-off-by:
-
Max Filippov authored
commit d1b6ba82 upstream. Remove restoring a6 on some return paths and instead modify and restore it in a single place, using symbolic name. Correctly restore a7 from PT_AREG7 in case of illegal a6 value. Signed-off-by:
Max Filippov <jcmvbkbc@gmail.com> Signed-off-by:
-
Max Filippov authored
commit 7128039f upstream. Current definition of TLBTEMP_BASE_2 is always 32K above the TLBTEMP_BASE_1, whereas fast_second_level_miss handler for the TLBTEMP region analyzes virtual address bit (PAGE_SHIFT + DCACHE_ALIAS_ORDER) to determine TLBTEMP region where the fault happened. The size of the TLBTEMP region is also checked incorrectly: not 64K, but twice data cache way size (whicht may as well be less than the instruction cache way size). Fix TLBTEMP_BASE_2 to be TLBTEMP_BASE_1 + data cache way size. Provide TLBTEMP_SIZE that is a greater of doubled data cache way size or the instruction cache way size, and use it to determine if the second level TLB miss occured in the TLBTEMP region. Practical occurence of page faults in the TLBTEMP area is extremely rare, this code can be tested by deletion of all w[di]tlb instructions in the tlbtemp_mapping region. Signed-off-by:
-
Max Filippov authored
commit 52247123 upstream. With SMP and a lot of debug options enabled task_struct::thread gets out of reach of s32i/l32i instructions with base pointing at task_struct, breaking build with the following messages: arch/xtensa/kernel/entry.S: Assembler messages: arch/xtensa/kernel/entry.S:1002: Error: operand 3 of 'l32i.n' has invalid value '1048' arch/xtensa/kernel/entry.S:1831: Error: operand 3 of 's32i.n' has invalid value '1040' arch/xtensa/kernel/entry.S:1832: Error: operand 3 of 's32i.n' has invalid value '1044' Change base to point to task_struct::thread in such cases. Don't use a10 in _switch_to to save/restore prev pointer as a2 is not clobbered. Signed-off-by:
-
Alan Douglas authored
commit 1ca49463 upstream. Virtual address is translated to the XCHAL_KSEG_CACHED region in the dma_free_coherent, but is checked to be in the 0...XCHAL_KSEG_SIZE range. Change check for end of the range from 'addr >= X' to 'addr > X - 1' to handle the case of X == 0. Replace 'if (C) BUG();' construct with 'BUG_ON(C);'. Signed-off-by:
Alan Douglas <adouglas@cadence.com> Signed-off-by:
-
Max Filippov authored
commit f61bf8e7 upstream. This fixes userspace code that builds on other architectures but fails on xtensa due to references to structures that other architectures don't refer to. E.g. this fixes the following issue with python-2.7.8: python-2.7.8/Modules/termios.c:861:25: error: invalid application of 'sizeof' to incomplete type 'struct serial_multiport_struct' {"TIOCSERGETMULTI", TIOCSERGETMULTI}, python-2.7.8/Modules/termios.c:870:25: error: invalid application of 'sizeof' to incomplete type 'struct serial_multiport_struct' {"TIOCSERSETMULTI", TIOCSERSETMULTI}, python-2.7.8/Modules/termios.c:900:24: error: invalid application of 'sizeof' to incomplete type 'struct tty_struct' {"TIOCTTYGSTRUCT", TIOCTTYGSTRUCT}, Signed-off-by:
-
