- 12 Feb, 2019 40 commits
-
-
Lorenzo Bianconi authored
commit 0c60c490 upstream. In order to make propagation time estimation faster, use current sample as ewma output value during 'late ack' tracking Tested-by:
Koen Vandeputte <koen.vandeputte@ncentric.com> Signed-off-by:
Lorenzo Bianconi <lorenzo.bianconi@redhat.com> Signed-off-by:
Kalle Valo <kvalo@codeaurora.org> Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-
Peter Zijlstra authored
commit 602cae04 upstream. intel_pmu_cpu_prepare() allocated memory for ->shared_regs among other members of struct cpu_hw_events. This memory is released in intel_pmu_cpu_dying() which is wrong. The counterpart of the intel_pmu_cpu_prepare() callback is x86_pmu_dead_cpu(). Otherwise if the CPU fails on the UP path between CPUHP_PERF_X86_PREPARE and CPUHP_AP_PERF_X86_STARTING then it won't release the memory but allocate new memory on the next attempt to online the CPU (leaking the old memory). Also, if the CPU down path fails between CPUHP_AP_PERF_X86_STARTING and CPUHP_PERF_X86_PREPARE then the CPU will go back online but never allocate the memory that was released in x86_pmu_dying_cpu(). Make the memory allocation/free symmetrical in regard to the CPU hotplug notifier by moving the deallocation to intel_pmu_cpu_dead(). This started in commit: a7e3ed1e ("perf: Add support for supplementary event registers"). In principle the bug was introduced in v2.6.39 (!), but it will almost certainly not backport cleanly across the big CPU hotplug rewrite between v4.7-v4.15... [ bigeasy: Added patch description. ] [ mingo: Added backporting guidance. ] Reported-by:
He Zhe <zhe.he@windriver.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> # With developer hat on Signed-off-by:
Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> # With maintainer hat on Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: acme@kernel.org Cc: bp@alien8.de Cc: hpa@zytor.com Cc: jolsa@kernel.org Cc: kan.liang@linux.intel.com Cc: namhyung@kernel.org Cc: <stable@vger.kernel.org> Fixes: a7e3ed1e ("perf: Add support for supplementary event registers"). Link: https://lkml.kernel.org/r/20181219165350.6s3jvyxbibpvlhtq@linutronix.deSigned-off-by:
Ingo Molnar <mingo@kernel.org> [ He Zhe: Fixes conflict caused by missing disable_counter_freeze which is introduced since v4.20 af3bdb99. ] Signed-off-by:
-
Mike Marciniszyn authored
commit 09ce351d upstream. Fix potential memory corruption and panic in loopback for IB_WR_SEND variants. The code blindly assumes the posted length will fit in the fetched rwqe, which is not a valid assumption. Fix by adding a limit test, and triggering the appropriate send completion and putting the QP in an error state. This mimics the handling for non-loopback QPs. Fixes: 15703461 ("IB/{hfi1, qib, rdmavt}: Move ruc_loopback to rdmavt") Cc: <stable@vger.kernel.org> #v4.20+ Reviewed-by:
Michael J. Ruhl <michael.j.ruhl@intel.com> Signed-off-by:
Mike Marciniszyn <mike.marciniszyn@intel.com> Signed-off-by:
Dennis Dalessandro <dennis.dalessandro@intel.com> Signed-off-by:
Jason Gunthorpe <jgg@mellanox.com> Signed-off-by:
-
Huacai Chen authored
commit 3a34c986 upstream. Commit 448a5a55 ("drivers: base: cacheinfo: use OF property_read_u32 instead of get_property,read_number") makes cache size and number_of_sets be 0 if DT doesn't provide there values. I think this is unreasonable so make them keep the old values, which is the same as old kernels. Fixes: 448a5a55 ("drivers: base: cacheinfo: use OF property_read_u32 instead of get_property,read_number") Cc: stable@vger.kernel.org Signed-off-by:
Huacai Chen <chenhc@lemote.com> Reviewed-by:
Sudeep Holla <sudeep.holla@arm.com> Signed-off-by:
-
Chris Brandt authored
commit 4d95987a upstream. Since IRQs might be muxed on some parts, we need to pay attention when we are freeing them. Otherwise we get the ugly WARNING "Trying to free already-free IRQ 20". Fixes: 628c534a ("serial: sh-sci: Improve support for separate TEI and DRI interrupts") Cc: stable <stable@vger.kernel.org> Signed-off-by:
Chris Brandt <chris.brandt@renesas.com> Signed-off-by:
-
Andy Shevchenko authored
commit 824d17c5 upstream. As has been reported the National Instruments serial cards have broken PCI class. The commit 7d8905d0 ("serial: 8250_pci: Enable device after we check black list") made the PCI class check mandatory for the case when device is listed in a quirk list. Make PCI class test non fatal to allow broken card be enumerated. Fixes: 7d8905d0 ("serial: 8250_pci: Enable device after we check black list") Cc: stable <stable@vger.kernel.org> Reported-by:
Guan Yung Tseng <guan.yung.tseng@ni.com> Tested-by:
KHUENY.Gerhard <Gerhard.KHUENY@bachmann.info> Signed-off-by:
Andy Shevchenko <andriy.shevchenko@linux.intel.com> Signed-off-by:
-
Greg Kroah-Hartman authored
commit fedb5760 upstream. There still is a race window after the commit b027e229 ("tty: fix data race between tty_init_dev and flush of buf"), and we encountered this crash issue if receive_buf call comes before tty initialization completes in tty_open and tty->driver_data may be NULL. CPU0 CPU1 ---- ---- tty_open tty_init_dev tty_ldisc_unlock schedule flush_to_ldisc receive_buf tty_port_default_receive_buf tty_ldisc_receive_buf n_tty_receive_buf_common __receive_buf uart_flush_chars uart_start /*tty->driver_data is NULL*/ tty->ops->open /*init tty->driver_data*/ it can be fixed by extending ldisc semaphore lock in tty_init_dev to driver_data initialized completely after tty->ops->open(), but this will lead to get lock on one function and unlock in some other function, and hard to maintain, so fix this race only by checking tty->driver_data when receiving, and return if tty->driver_data is NULL, and n_tty_receive_buf_common maybe calls uart_unthrottle, so add the same check. Because the tty layer knows nothing about the driver associated with the device, the tty layer can not do anything here, it is up to the tty driver itself to check for this type of race. Fix up the serial driver to correctly check to see if it is finished binding with the device when being called, and if not, abort the tty calls. [Description and problem report and testing from Li RongQing, I rewrote the patch to be in the serial layer, not in the tty core - gregkh] Reported-by:
Li RongQing <lirongqing@baidu.com> Tested-by:
Wang Li <wangli39@baidu.com> Signed-off-by:
Zhang Yu <zhangyu31@baidu.com> Signed-off-by:
-
Gustavo A. R. Silva authored
commit 489338a7 upstream. Notice that the use of the bitwise OR operator '|' always leads to true in this particular case, which seems a bit suspicious due to the context in which this expression is being used. Fix this by using bitwise AND operator '&' instead. This bug was detected with the help of Coccinelle. Signed-off-by:
Gustavo A. R. Silva <gustavo@embeddedor.com> Acked-by:
Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: stable@vger.kernel.org Fixes: 6a6cd11d ("perf test: Add test for the sched tracepoint format fields") Link: http://lkml.kernel.org/r/20190122233439.GA5868@embeddedorSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by:
-
Mark Rutland authored
commit 9dff0aa9 upstream. The perf tool uses /proc/sys/kernel/perf_event_mlock_kb to determine how large its ringbuffer mmap should be. This can be configured to arbitrary values, which can be larger than the maximum possible allocation from kmalloc. When this is configured to a suitably large value (e.g. thanks to the perf fuzzer), attempting to use perf record triggers a WARN_ON_ONCE() in __alloc_pages_nodemask(): WARNING: CPU: 2 PID: 5666 at mm/page_alloc.c:4511 __alloc_pages_nodemask+0x3f8/0xbc8 Let's avoid this by checking that the requested allocation is possible before calling kzalloc. Reported-by:
Julien Thierry <julien.thierry@arm.com> Signed-off-by:
Mark Rutland <mark.rutland@arm.com> Signed-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by:
-
Tony Luck authored
commit d28af26f upstream. Internal injection testing crashed with a console log that said: mce: [Hardware Error]: CPU 7: Machine Check Exception: f Bank 0: bd80000000100134 This caused a lot of head scratching because the MCACOD (bits 15:0) of that status is a signature from an L1 data cache error. But Linux says that it found it in "Bank 0", which on this model CPU only reports L1 instruction cache errors. The answer was that Linux doesn't initialize "m->bank" in the case that it finds a fatal error in the mce_no_way_out() pre-scan of banks. If this was a local machine check, then this partially initialized struct mce is being passed to mce_panic(). Fix is simple: just initialize m->bank in the case of a fatal error. Fixes: 40c36e27 ("x86/mce: Fix incorrect "Machine check from unknown source" message") Signed-off-by:
Tony Luck <tony.luck@intel.com> Signed-off-by:
Borislav Petkov <bp@suse.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vishal Verma <vishal.l.verma@intel.com> Cc: x86-ml <x86@kernel.org> Cc: stable@vger.kernel.org # v4.18 Note pre-v5.0 arch/x86/kernel/cpu/mce/core.c was called arch/x86/kernel/cpu/mcheck/mce.c Link: https://lkml.kernel.org/r/20190201003341.10638-1-tony.luck@intel.comSigned-off-by:
-
Kan Liang authored
commit 9e63a789 upstream. Some PCI uncore PMUs cannot be registered on an 8-socket system (HPE Superdome Flex). To understand which Socket the PCI uncore PMUs belongs to, perf retrieves the local Node ID of the uncore device from CPUNODEID(0xC0) of the PCI configuration space, and the mapping between Socket ID and Node ID from GIDNIDMAP(0xD4). The Socket ID can be calculated accordingly. The local Node ID is only available at bit 2:0, but current code doesn't mask it. If a BIOS doesn't clear the rest of the bits, an incorrect Node ID will be fetched. Filter the Node ID by adding a mask. Reported-by:
Song Liu <songliubraving@fb.com> Tested-by:
Kan Liang <kan.liang@linux.intel.com> Signed-off-by:
-
Josh Poimboeuf authored
commit b284909a upstream. With the following commit: 73d5e2b4 ("cpu/hotplug: detect SMT disabled by BIOS") ... the hotplug code attempted to detect when SMT was disabled by BIOS, in which case it reported SMT as permanently disabled. However, that code broke a virt hotplug scenario, where the guest is booted with only primary CPU threads, and a sibling is brought online later. The problem is that there doesn't seem to be a way to reliably distinguish between the HW "SMT disabled by BIOS" case and the virt "sibling not yet brought online" case. So the above-mentioned commit was a bit misguided, as it permanently disabled SMT for both cases, preventing future virt sibling hotplugs. Going back and reviewing the original problems which were attempted to be solved by that commit, when SMT was disabled in BIOS: 1) /sys/devices/system/cpu/smt/control showed "on" instead of "notsupported"; and 2) vmx_vm_init() was incorrectly showing the L1TF_MSG_SMT warning. I'd propose that we instead consider #1 above to not actually be a problem. Because, at least in the virt case, it's possible that SMT wasn't disabled by BIOS and a sibling thread could be brought online later. So it makes sense to just always default the smt control to "on" to allow for that possibility (assuming cpuid indicates that the CPU supports SMT). The real problem is #2, which has a simple fix: change vmx_vm_init() to query the actual current SMT state -- i.e., whether any siblings are currently online -- instead of looking at the SMT "control" sysfs value. So fix it by: a) reverting the original "fix" and its followup fix: 73d5e2b4 ("cpu/hotplug: detect SMT disabled by BIOS") bc2d8d26 ("cpu/hotplug: Fix SMT supported evaluation") and b) changing vmx_vm_init() to query the actual current SMT state -- instead of the sysfs control value -- to determine whether the L1TF warning is needed. This also requires the 'sched_smt_present' variable to exported, instead of 'cpu_smt_control'. Fixes: 73d5e2b4 ("cpu/hotplug: detect SMT disabled by BIOS") Reported-by:
Igor Mammedov <imammedo@redhat.com> Signed-off-by:
Josh Poimboeuf <jpoimboe@redhat.com> Signed-off-by:
Thomas Gleixner <tglx@linutronix.de> Cc: Joe Mario <jmario@redhat.com> Cc: Jiri Kosina <jikos@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: kvm@vger.kernel.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/e3a85d585da28cc333ecbc1e78ee9216e6da9396.1548794349.git.jpoimboe@redhat.comSigned-off-by:
-
Peter Shier authored
commit ecec7688 upstream. Bugzilla: 1671904 There are multiple code paths where an hrtimer may have been started to emulate an L1 VMX preemption timer that can result in a call to free_nested without an intervening L2 exit where the hrtimer is normally cancelled. Unconditionally cancel in free_nested to cover all cases. Embargoed until Feb 7th 2019. Signed-off-by:
Peter Shier <pshier@google.com> Reported-by:
Jim Mattson <jmattson@google.com> Reviewed-by:
Felix Wilhelm <fwilhelm@google.com> Cc: stable@kernel.org Message-Id: <20181011184646.154065-1-pshier@google.com> Signed-off-by:
Paolo Bonzini <pbonzini@redhat.com> Signed-off-by:
-
Jann Horn authored
commit cfa39381 upstream. kvm_ioctl_create_device() does the following: 1. creates a device that holds a reference to the VM object (with a borrowed reference, the VM's refcount has not been bumped yet) 2. initializes the device 3. transfers the reference to the device to the caller's file descriptor table 4. calls kvm_get_kvm() to turn the borrowed reference to the VM into a real reference The ownership transfer in step 3 must not happen before the reference to the VM becomes a proper, non-borrowed reference, which only happens in step 4. After step 3, an attacker can close the file descriptor and drop the borrowed reference, which can cause the refcount of the kvm object to drop to zero. This means that we need to grab a reference for the device before anon_inode_getfd(), otherwise the VM can disappear from under us. Fixes: 852b6d57 ("kvm: add device control API") Cc: stable@kernel.org Signed-off-by:
Jann Horn <jannh@google.com> Signed-off-by:
-
Paolo Bonzini authored
commit 353c0956 upstream. Bugzilla: 1671930 Emulation of certain instructions (VMXON, VMCLEAR, VMPTRLD, VMWRITE with memory operand, INVEPT, INVVPID) can incorrectly inject a page fault when passed an operand that points to an MMIO address. The page fault will use uninitialized kernel stack memory as the CR2 and error code. The right behavior would be to abort the VM with a KVM_EXIT_INTERNAL_ERROR exit to userspace; however, it is not an easy fix, so for now just ensure that the error code and CR2 are zero. Embargoed until Feb 7th 2019. Reported-by:
-
James Bottomley authored
commit 42caa0ed upstream. The aic94xx driver is currently failing to load with errors like sysfs: cannot create duplicate filename '/devices/pci0000:00/0000:00:03.0/0000:02:00.3/0000:07:02.0/revision' Because the PCI code had recently added a file named 'revision' to every PCI device. Fix this by renaming the aic94xx revision file to aic_revision. This is safe to do for us because as far as I can tell, there's nothing in userspace relying on the current aic94xx revision file so it can be renamed without breaking anything. Fixes: 702ed3be (PCI: Create revision file in sysfs) Cc: stable@vger.kernel.org Signed-off-by:
James Bottomley <James.Bottomley@HansenPartnership.com> Signed-off-by:
Martin K. Petersen <martin.petersen@oracle.com> Signed-off-by:
-
Vaibhav Jain authored
commit bb61b843 upstream. Presently when an error is encountered during probe of the cxlflash adapter, a deadlock is seen with cpu thread stuck inside cxlflash_remove(). Below is the trace of the deadlock as logged by khungtaskd: cxlflash 0006:00:00.0: cxlflash_probe: init_afu failed rc=-16 INFO: task kworker/80:1:890 blocked for more than 120 seconds. Not tainted 5.0.0-rc4-capi2-kexec+ #2 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. kworker/80:1 D 0 890 2 0x00000808 Workqueue: events work_for_cpu_fn Call Trace: 0x4d72136320 (unreliable) __switch_to+0x2cc/0x460 __schedule+0x2bc/0xac0 schedule+0x40/0xb0 cxlflash_remove+0xec/0x640 [cxlflash] cxlflash_probe+0x370/0x8f0 [cxlflash] local_pci_probe+0x6c/0x140 work_for_cpu_fn+0x38/0x60 process_one_work+0x260/0x530 worker_thread+0x280/0x5d0 kthread+0x1a8/0x1b0 ret_from_kernel_thread+0x5c/0x80 INFO: task systemd-udevd:5160 blocked for more than 120 seconds. The deadlock occurs as cxlflash_remove() is called from cxlflash_probe() without setting 'cxlflash_cfg->state' to STATE_PROBED and the probe thread starts to wait on 'cxlflash_cfg->reset_waitq'. Since the device was never successfully probed the 'cxlflash_cfg->state' never changes from STATE_PROBING hence the deadlock occurs. We fix this deadlock by setting the variable 'cxlflash_cfg->state' to STATE_PROBED in case an error occurs during cxlflash_probe() and just before calling cxlflash_remove(). Cc: stable@vger.kernel.org Fixes: c21e0bbf("cxlflash: Base support for IBM CXL Flash Adapter") Signed-off-by:
Vaibhav Jain <vaibhav@linux.ibm.com> Signed-off-by:
-
Johan Hovold authored
commit a1960e0f upstream. The send_xchar() and tiocmset() tty operations are optional. Add the missing sanity checks to prevent user-space triggerable NULL-pointer dereferences. Fixes: 6b9ad1c7 ("staging: speakup: add send_xchar, tiocmset and input functionality for tty") Cc: stable <stable@vger.kernel.org> # 4.13 Cc: Okash Khawaja <okash.khawaja@gmail.com> Cc: Samuel Thibault <samuel.thibault@ens-lyon.org> Signed-off-by:
Johan Hovold <johan@kernel.org> Reviewed-by:
Samuel Thibault <samuel.thibault@ens-lyon.org> Signed-off-by:
-
Paul Elder authored
commit c418fd6c upstream. Handling short packets (length < max packet size) in the Inventra DMA engine in the MUSB driver causes the MUSB DMA controller to hang. An example of a problem that is caused by this problem is when streaming video out of a UVC gadget, only the first video frame is transferred. For short packets (mode-0 or mode-1 DMA), MUSB_TXCSR_TXPKTRDY must be set manually by the driver. This was previously done in musb_g_tx (musb_gadget.c), but incorrectly (all csr flags were cleared, and only MUSB_TXCSR_MODE and MUSB_TXCSR_TXPKTRDY were set). Fixing that problem allows some requests to be transferred correctly, but multiple requests were often put together in one USB packet, and caused problems if the packet size was not a multiple of 4. Instead, set MUSB_TXCSR_TXPKTRDY in dma_controller_irq (musbhsdma.c), just like host mode transfers. This topic was originally tackled by Nicolas Boichat [0] [1] and is discussed further at [2] as part of his GSoC project [3]. [0] https://groups.google.com/forum/?hl=en#!topic/beagleboard-gsoc/k8Azwfp75CU [1] https://gitorious.org/beagleboard-usbsniffer/beagleboard-usbsniffer-kernel/commit/b0be3b6cc195ba732189b04f1d43ec843c3e54c9?p=beagleboard-usbsniffer:beagleboard-usbsniffer-kernel.git;a=patch;h=b0be3b6cc195ba732189b04f1d43ec843c3e54c9 [2] http://beagleboard-usbsniffer.blogspot.com/2010/07/musb-isochronous-transfers-fixed.html [3] http://elinux.org/BeagleBoard/GSoC/USBSniffer Fixes: 550a7375 ("USB: Add MUSB and TUSB support") Signed-off-by:
Paul Elder <paul.elder@ideasonboard.com> Signed-off-by:
Bin Liu <b-liu@ti.com> Cc: stable <stable@vger.kernel.org> Signed-off-by:
-
Gustavo A. R. Silva authored
commit 07c69f11 upstream. (!x & y) strikes again. Fix bitwise and boolean operations by enclosing the expression: intcsr & (1 << NET2272_PCI_IRQ) in parentheses, before applying the boolean operator '!'. Notice that this code has been there since 2011. So, it would be helpful if someone can double-check this. This issue was detected with the help of Coccinelle. Fixes: ceb80363 ("USB: net2272: driver for PLX NET2272 USB device controller") Cc: stable@vger.kernel.org Signed-off-by:
Felipe Balbi <felipe.balbi@linux.intel.com> Signed-off-by:
-
Tejas Joglekar authored
commit 1e19cdc8 upstream. For OUT endpoints, zero-length transfers require MaxPacketSize buffer as per the DWC_usb3 programming guide 3.30a section 4.2.3.3. This patch fixes this by explicitly checking zero length transfer to correctly pad up to MaxPacketSize. Fixes: c6267a51 ("usb: dwc3: gadget: align transfers to wMaxPacketSize") Cc: stable@vger.kernel.org Signed-off-by:
Tejas Joglekar <joglekar@synopsys.com> Signed-off-by:
-
Bin Liu authored
commit a53469a6 upstream. power off the phy should be done before populate the phy. Otherwise, am335x_init() could be called by the phy owner to power on the phy first, then am335x_phy_probe() turns off the phy again without the caller knowing it. Fixes: 2fc711d7 ("usb: phy: am335x: Enable USB remote wakeup using PHY wakeup") Cc: stable@vger.kernel.org # v3.18+ Signed-off-by:
-
Marc Zyngier authored
commit 9791ec7d upstream. On systems or VMs where multiple devices share a single DevID (because they sit behind a PCI bridge, or because the HW is broken in funky ways), we reuse the save its_device structure in order to reflect this. It turns out that there is a distinct lack of locking when looking up the its_device, and two device being probed concurrently can result in double allocations. That's obviously not nice. A solution for this is to have a per-ITS mutex that serializes device allocation. A similar issue exists on the freeing side, which can run concurrently with the allocation. On top of now taking the appropriate lock, we also make sure that a shared device is never freed, as we have no way to currently track the life cycle of such object. Reported-by:
Zheng Xiang <zhengxiang9@huawei.com> Tested-by:
Marc Zyngier <marc.zyngier@arm.com> Signed-off-by:
-
Thomas Gleixner authored
commit 1a1fb985 upstream. commit 56222b21 ("futex: Drop hb->lock before enqueueing on the rtmutex") changed the locking rules in the futex code so that the hash bucket lock is not longer held while the waiter is enqueued into the rtmutex wait list. This made the lock and the unlock path symmetric, but unfortunately the possible early exit from __rt_mutex_proxy_start() due to a detected deadlock was not updated accordingly. That allows a concurrent unlocker to observe inconsitent state which triggers the warning in the unlock path. futex_lock_pi() futex_unlock_pi() lock(hb->lock) queue(hb_waiter) lock(hb->lock) lock(rtmutex->wait_lock) unlock(hb->lock) // acquired hb->lock hb_waiter = futex_top_waiter() lock(rtmutex->wait_lock) __rt_mutex_proxy_start() ---> fail remove(rtmutex_waiter); ---> returns -EDEADLOCK unlock(rtmutex->wait_lock) // acquired wait_lock wake_futex_pi() rt_mutex_next_owner() --> returns NULL --> WARN lock(hb->lock) unqueue(hb_waiter) The problem is caused by the remove(rtmutex_waiter) in the failure case of __rt_mutex_proxy_start() as this lets the unlocker observe a waiter in the hash bucket but no waiter on the rtmutex, i.e. inconsistent state. The original commit handles this correctly for the other early return cases (timeout, signal) by delaying the removal of the rtmutex waiter until the returning task reacquired the hash bucket lock. Treat the failure case of __rt_mutex_proxy_start() in the same way and let the existing cleanup code handle the eventual handover of the rtmutex gracefully. The regular rt_mutex_proxy_start() gains the rtmutex waiter removal for the failure case, so that the other callsites are still operating correctly. Add proper comments to the code so all these details are fully documented. Thanks to Peter for helping with the analysis and writing the really valuable code comments. Fixes: 56222b21 ("futex: Drop hb->lock before enqueueing on the rtmutex") Reported-by:
Heiko Carstens <heiko.carstens@de.ibm.com> Co-developed-by:
-
Leonid Iziumtsev authored
commit 341198ed upstream. Once the "ld_queue" list is not empty, next descriptor will migrate into "ld_active" list. The "desc" variable will be overwritten during that transition. And later the dmaengine_desc_get_callback_invoke() will use it as an argument. As result we invoke wrong callback. That behaviour was in place since: commit fcaaba6c ("dmaengine: imx-dma: fix callback path in tasklet"). But after commit 4cd13c21 ("softirq: Let ksoftirqd do its job") things got worse, since possible delay between tasklet_schedule() from DMA irq handler and actual tasklet function execution got bigger. And that gave more time for new DMA request to be submitted and to be put into "ld_queue" list. It has been noticed that DMA issue is causing problems for "mxc-mmc" driver. While stressing the system with heavy network traffic and writing/reading to/from sd card simultaneously the timeout may happen: 10013000.sdhci: mxcmci_watchdog: read time out (status = 0x30004900) That often lead to file system corruption. Signed-off-by:
Leonid Iziumtsev <leonid.iziumtsev@gmail.com> Signed-off-by:
Vinod Koul <vkoul@kernel.org> Cc: stable@vger.kernel.org Signed-off-by:
-
Lukas Wunner authored
commit 9e528c79 upstream. There are multiple issues with bcm2835_dma_abort() (which is called on termination of a transaction): * The algorithm to abort the transaction first pauses the channel by clearing the ACTIVE flag in the CS register, then waits for the PAUSED flag to clear. Page 49 of the spec documents the latter as follows: "Indicates if the DMA is currently paused and not transferring data. This will occur if the active bit has been cleared [...]" https://www.raspberrypi.org/app/uploads/2012/02/BCM2835-ARM-Peripherals.pdf So the function is entering an infinite loop because it is waiting for PAUSED to clear which is always set due to the function having cleared the ACTIVE flag. The only thing that's saving it from itself is the upper bound of 10000 loop iterations. The code comment says that the intention is to "wait for any current AXI transfer to complete", so the author probably wanted to check the WAITING_FOR_OUTSTANDING_WRITES flag instead. Amend the function accordingly. * The CS register is only read at the beginning of the function. It needs to be read again after pausing the channel and before checking for outstanding writes, otherwise writes which were issued between the register read at the beginning of the function and pausing the channel may not be waited for. * The function seeks to abort the transfer by writing 0 to the NEXTCONBK register and setting the ABORT and ACTIVE flags. Thereby, the 0 in NEXTCONBK is sought to be loaded into the CONBLK_AD register. However experimentation has shown this approach to not work: The CONBLK_AD register remains the same as before and the CS register contains 0x00000030 (PAUSED | DREQ_STOPS_DMA). In other words, the control block is not aborted but merely paused and it will be resumed once the next DMA transaction is started. That is absolutely not the desired behavior. A simpler approach is to set the channel's RESET flag instead. This reliably zeroes the NEXTCONBK as well as the CS register. It requires less code and only a single MMIO write. This is also what popular user space DMA drivers do, e.g.: https://github.com/metachris/RPIO/blob/master/source/c_pwm/pwm.c Note that the spec is contradictory whether the NEXTCONBK register is writeable at all. On the one hand, page 41 claims: "The value loaded into the NEXTCONBK register can be overwritten so that the linked list of Control Block data structures can be dynamically altered. However it is only safe to do this when the DMA is paused." On the other hand, page 40 specifies: "Only three registers in each channel's register set are directly writeable (CS, CONBLK_AD and DEBUG). The other registers (TI, SOURCE_AD, DEST_AD, TXFR_LEN, STRIDE & NEXTCONBK), are automatically loaded from a Control Block data structure held in external memory." Fixes: 96286b57 ("dmaengine: Add support for BCM2835") Signed-off-by:
Lukas Wunner <lukas@wunner.de> Cc: stable@vger.kernel.org # v3.14+ Cc: Frank Pavlic <f.pavlic@kunbus.de> Cc: Martin Sperl <kernel@martin.sperl.org> Cc: Florian Meier <florian.meier@koalo.de> Cc: Clive Messer <clive.m.messer@gmail.com> Cc: Matthias Reichl <hias@horus.com> Tested-by:
Stefan Wahren <stefan.wahren@i2se.com> Acked-by:
Florian Kauer <florian.kauer@koalo.de> Signed-off-by:
-
Lukas Wunner authored
commit f7da7782 upstream. If IRQ handlers are threaded (either because CONFIG_PREEMPT_RT_BASE is enabled or "threadirqs" was passed on the command line) and if system load is sufficiently high that wakeup latency of IRQ threads degrades, SPI DMA transactions on the BCM2835 occasionally break like this: ks8851 spi0.0: SPI transfer timed out bcm2835-dma 3f007000.dma: DMA transfer could not be terminated ks8851 spi0.0 eth2: ks8851_rdfifo: spi_sync() failed The root cause is an assumption made by the DMA driver which is documented in a code comment in bcm2835_dma_terminate_all(): /* * Stop DMA activity: we assume the callback will not be called * after bcm_dma_abort() returns (even if it does, it will see * c->desc is NULL and exit.) */ That assumption falls apart if the IRQ handler bcm2835_dma_callback() is threaded: A client may terminate a descriptor and issue a new one before the IRQ handler had a chance to run. In fact the IRQ handler may miss an *arbitrary* number of descriptors. The result is the following race condition: 1. A descriptor finishes, its interrupt is deferred to the IRQ thread. 2. A client calls dma_terminate_async() which sets channel->desc = NULL. 3. The client issues a new descriptor. Because channel->desc is NULL, bcm2835_dma_issue_pending() immediately starts the descriptor. 4. Finally the IRQ thread runs and writes BCM2835_DMA_INT to the CS register to acknowledge the interrupt. This clears the ACTIVE flag, so the newly issued descriptor is paused in the middle of the transaction. Because channel->desc is not NULL, the IRQ thread finalizes the descriptor and tries to start the next one. I see two possible solutions: The first is to call synchronize_irq() in bcm2835_dma_issue_pending() to wait until the IRQ thread has finished before issuing a new descriptor. The downside of this approach is unnecessary latency if clients desire rapidly terminating and re-issuing descriptors and don't have any use for an IRQ callback. (The SPI TX DMA channel is a case in point.) A better alternative is to make the IRQ thread recognize that it has missed descriptors and avoid finalizing the newly issued descriptor. So first of all, set the ACTIVE flag when acknowledging the interrupt. This keeps a newly issued descriptor running. If the descriptor was finished, the channel remains idle despite the ACTIVE flag being set. However the ACTIVE flag can then no longer be used to check whether the channel is idle, so instead check whether the register containing the current control block address is zero and finalize the current descriptor only if so. That way, there is no impact on latency and throughput if the client doesn't care for the interrupt: Only minimal additional overhead is introduced for non-cyclic descriptors as one further MMIO read is necessary per interrupt to check for idleness of the channel. Cyclic descriptors are sped up slightly by removing one MMIO write per interrupt. Fixes: 96286b57 ("dmaengine: Add support for BCM2835") Signed-off-by:
-
Vladis Dronov authored
commit 13054abb upstream. Ring buffer implementation in hid_debug_event() and hid_debug_events_read() is strange allowing lost or corrupted data. After commit 717adfda ("HID: debug: check length before copy_to_user()") it is possible to enter an infinite loop in hid_debug_events_read() by providing 0 as count, this locks up a system. Fix this by rewriting the ring buffer implementation with kfifo and simplify the code. This fixes CVE-2019-3819. v2: fix an execution logic and add a comment v3: use __set_current_state() instead of set_current_state() Link: https://bugzilla.redhat.com/show_bug.cgi?id=1669187 Cc: stable@vger.kernel.org # v4.18+ Fixes: cd667ce2 ("HID: use debugfs for events/reports dumping") Fixes: 717adfda ("HID: debug: check length before copy_to_user()") Signed-off-by:
Vladis Dronov <vdronov@redhat.com> Reviewed-by:
Oleg Nesterov <oleg@redhat.com> Signed-off-by:
Benjamin Tissoires <benjamin.tissoires@redhat.com> Signed-off-by:
-
Miklos Szeredi authored
commit 97e1532e upstream. Dereferencing req->page_descs[0] will Oops if req->max_pages is zero. Reported-by: syzbot+c1e36d30ee3416289cc0@syzkaller.appspotmail.com Tested-by: syzbot+c1e36d30ee3416289cc0@syzkaller.appspotmail.com Fixes: b2430d75 ("fuse: add per-page descriptor <offset, length> to fuse_req") Cc: <stable@vger.kernel.org> # v3.9 Signed-off-by:
Miklos Szeredi <mszeredi@redhat.com> Signed-off-by:
-
Miklos Szeredi authored
commit a2ebba82 upstream. NR_WRITEBACK_TEMP is accounted on the temporary page in the request, not the page cache page. Fixes: 8b284dc4 ("fuse: writepages: handle same page rewrites") Cc: <stable@vger.kernel.org> # v3.13 Signed-off-by:
-
Jann Horn authored
commit 9509941e upstream. Some of the pipe_buf_release() handlers seem to assume that the pipe is locked - in particular, anon_pipe_buf_release() accesses pipe->tmp_page without taking any extra locks. From a glance through the callers of pipe_buf_release(), it looks like FUSE is the only one that calls pipe_buf_release() without having the pipe locked. This bug should only lead to a memory leak, nothing terrible. Fixes: dd3bb14f ("fuse: support splice() writing to fuse device") Cc: stable@vger.kernel.org Signed-off-by:
-
Jeremy Soller authored
commit 89e3a568 upstream. On the System76 Darter Pro (darp5), there is a headset microphone input attached to 0x1a that does not have a jack detect. In order to get it working, the pin configuration needs to be set correctly, and the ALC269_FIXUP_HEADSET_MODE_NO_HP_MIC fixup needs to be applied. This is similar to the MIC_NO_PRESENCE fixups for some Dell laptops, except we have a separate microphone jack that is already configured correctly. Signed-off-by:
Jeremy Soller <jeremy@system76.com> Cc: <stable@vger.kernel.org> Signed-off-by:
Takashi Iwai <tiwai@suse.de> Signed-off-by:
-
Takashi Iwai authored
commit 35a39f98 upstream. Replace the open-codes in many places with a new common helper for performing the same thing: referring to the primary headphone pin. This eventually fixes the potentially missing headphone pin on some weird devices, too. Cc: <stable@vger.kernel.org> Signed-off-by:
-
Kailang Yang authored
commit d561aa0a upstream. When auto_mute = no or spec->suppress_auto_mute = 1, cfg->hp_pins will lose value. Add this patch to find hp_pins value. I add fixed for ALC282 ALC225 ALC256 ALC294 and alc_default_init() alc_default_shutup(). Signed-off-by:
Kailang Yang <kailang@realtek.com> Cc: <stable@vger.kernel.org> Signed-off-by:
-
Takashi Iwai authored
commit 305a0ade upstream. In the current code, the codec registration may happen both at the codec bind time and the end of the controller probe time. In a rare occasion, they race with each other, leading to Oops due to the still uninitialized card device. This patch introduces a simple flag to prevent the codec registration at the codec bind time as long as the controller probe is going on. The controller probe invokes snd_card_register() that does the whole registration task, and we don't need to register each piece beforehand. Cc: <stable@vger.kernel.org> Signed-off-by:
-
Udo Eberhardt authored
commit 3bff2407 upstream. This patch adds the T+A VID to the generic check in order to enable native DSD support for T+A devices. This works with the new T+A USB DAC model SD3100HV and will also work with future devices which support the XMOS/Thesycon style DSD format. Signed-off-by:
Udo Eberhardt <udo.eberhardt@thesycon.de> Cc: <stable@vger.kernel.org> Signed-off-by:
-
Charles Keepax authored
commit 4f2ab5e1 upstream. It is normal user behaviour to start, stop, then start a stream again without closing it. Currently this works for compressed playback streams but not capture ones. The states on a compressed capture stream go directly from OPEN to PREPARED, unlike a playback stream which moves to SETUP and waits for a write of data before moving to PREPARED. Currently however, when a stop is sent the state is set to SETUP for both types of streams. This leaves a capture stream in the situation where a new start can't be sent as that requires the state to be PREPARED and a new set_params can't be sent as that requires the state to be OPEN. The only option being to close the stream, and then reopen. Correct this issues by allowing snd_compr_drain_notify to set the state depending on the stream direction, as we already do in set_params. Fixes: 49bb6402 ("ALSA: compress_core: Add support for capture streams") Signed-off-by:
Charles Keepax <ckeepax@opensource.cirrus.com> Cc: <stable@vger.kernel.org> Signed-off-by:
-
Brian Foster authored
commit aa6ee4ab upstream. The cached writeback mapping is EOF trimmed to try and avoid races between post-eof block management and writeback that result in sending cached data to a stale location. The cached mapping is currently trimmed on the validation check, which leaves a race window between the time the mapping is cached and when it is trimmed against the current inode size. For example, if a new mapping is cached by delalloc conversion on a blocksize == page size fs, we could cycle various locks, perform memory allocations, etc. in the writeback codepath before the associated mapping is eventually trimmed to i_size. This leaves enough time for a post-eof truncate and file append before the cached mapping is trimmed. The former event essentially invalidates a range of the cached mapping and the latter bumps the inode size such the trim on the next writepage event won't trim all of the invalid blocks. fstest generic/464 reproduces this scenario occasionally and causes a lost writeback and stale delalloc blocks warning on inode inactivation. To work around this problem, trim the cached writeback mapping as soon as it is cached in addition to on subsequent validation checks. This is a minor tweak to tighten the race window as much as possible until a proper invalidation mechanism is available. Fixes: 40214d12 ("xfs: trim writepage mapping to within eof") Cc: <stable@vger.kernel.org> # v4.14+ Signed-off-by:
Brian Foster <bfoster@redhat.com> Reviewed-by:
Allison Henderson <allison.henderson@oracle.com> Reviewed-by:
Christoph Hellwig <hch@lst.de> Reviewed-by:
Darrick J. Wong <darrick.wong@oracle.com> Signed-off-by:
-
Raed Salem authored
[ Upstream commit 82eaa1fa ] At Innova IPsec TX offload data path a special software parser metadata is used to pass some packet attributes to the hardware, this metadata is passed using the Ethernet control segment of a WQE (a HW descriptor) header. The cited commit might nullify this header, hence the metadata is lost, this caused a significant performance drop during hw offloading operation. Fix by restoring the metadata at the Ethernet control segment in case it was nullified. Fixes: 37fdffb2 ("net/mlx5: WQ, fixes for fragmented WQ buffers API") Signed-off-by:
Raed Salem <raeds@mellanox.com> Reviewed-by:
Tariq Toukan <tariqt@mellanox.com> Signed-off-by:
Saeed Mahameed <saeedm@mellanox.com> Signed-off-by:
-
Toshiaki Makita authored
[ Upstream commit 546f2897 ] Previously virtnet_xdp_xmit() did not account for device tx counters, which caused confusions. To be consistent with SKBs, account them on freeing xdp_frames. Reported-by:
David Ahern <dsahern@gmail.com> Signed-off-by:
Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp> Acked-by:
Michael S. Tsirkin <mst@redhat.com> Signed-off-by:
David S. Miller <davem@davemloft.net> Signed-off-by:
-
