- 07 Apr, 2016 4 commits
-
-
Sunil Goutham authored
BugLink: http://bugs.launchpad.net/bugs/1567091 Counting rx packets for every CQE_RX in CQ irq handler is incorrect. Synchronization is missing when multiple queues are receiving packets simultaneously. Like transmit packet stats use HW stats here. Also removed unused 'cqe_type' parameter in nicvf_rcv_pkt_handler(). Signed-off-by:
Sunil Goutham <sgoutham@cavium.com> Signed-off-by:
David S. Miller <davem@davemloft.net> (cherry picked from commit ad2ecebd) Signed-off-by:
dann frazier <dann.frazier@canonical.com> Signed-off-by:
Tim Gardner <tim.gardner@canonical.com>
-
Sunil Goutham authored
BugLink: http://bugs.launchpad.net/bugs/1567091 For secondary Qsets 'hw_tso' is not getting set as probe() returns much earlier. Fixed it by moving silicon revision check. Signed-off-by:
-
Sunil Goutham authored
BugLink: http://bugs.launchpad.net/bugs/1567091 When a interface is assigned morethan 8 queues and the logical interface is toggled i.e down & up, additional queues or qsets are not initialized as secondary qset count is being set to zero while tearing down. Signed-off-by:
-
Tim Gardner authored
Ignore: yes Signed-off-by:
-
- 06 Apr, 2016 36 commits
-
-
Tim Gardner authored
Signed-off-by: -
Mika Kuoppala authored
BugLink: http://bugs.launchpad.net/bugs/1564759 Experiments with heaven 4.0 benchmark and skylake gt3e (rev 0xa) suggest that WaForceContextSaveRestoreNonCoherent is needed for all revs. Extending this to all revs cures a gpu hang with rev 0xa when running heaven4.0 gpu benchmark. We have been here before, with problems enabling gt4e and extending up to revision F0 instead of false claims of bspec of E0 only. See commit <e238659d> ("drm/i915/skl: Default to noncoherent access up to F0"). In retrospect we should have covered this with this big blanket back then already, as E0 vs F0 discrepancy was suspicious enough. Previously the WaForceEnableNonCoherent has been tied to context non-coherence, atleast in relevant hsds. So keep this tie and extended this alongside. Cc: Abdiel Janulgue <abdiel.janulgue@linux.intel.com> Cc: Ben Widawsky <benjamin.widawsky@intel.com> Cc: Timo Aaltonen <tjaalton@ubuntu.com> Cc: stable@vger.kernel.org Reported-by:
Mike Lothian <mike@fireburn.co.uk> References: https://bugs.freedesktop.org/show_bug.cgi?id=93491Signed-off-by:
Mika Kuoppala <mika.kuoppala@intel.com> (pulled from stable@ list) Signed-off-by:
Timo Aaltonen <timo.aaltonen@canonical.com> Signed-off-by:
-
Mika Kuoppala authored
BugLink: http://bugs.launchpad.net/bugs/1564759 For all gt3 and gt4 skylake variants, extend the usage of WaRsDisableCoarsePowerGating for all revisions. Without this gt3 and gt4 skylakes up to atleast rev 0xa can gpu hang or system hang. Cc: Abdiel Janulgue <abdiel.janulgue@linux.intel.com> Cc: Ben Widawsky <benjamin.widawsky@intel.com> Cc: Timo Aaltonen <tjaalton@ubuntu.com> Cc: <stable@vger.kernel.org> Reported-by:
Mikael Djurfeldt <mikael@djurfeldt.com> References: https://bugs.freedesktop.org/show_bug.cgi?id=94161Signed-off-by:
-
Timo Aaltonen authored
It was mistakenly enabled, the option should be left disabled and instead enable KBL/BXT via the driver once they have been properly tested. Signed-off-by:
-
Tim Gardner authored
BugLink: http://bugs.launchpad.net/bugs/1566283Signed-off-by:
-
Vikas Shivappa authored
BugLink: http://bugs.launchpad.net/bugs/1397880 This patch adds a per package timer which periodically updates the memory bandwidth counters for the events that are currently active. Current patch has a periodic timer every 1s since the SDM guarantees that the counter will not overflow in 1s but this time can be definitely improved by calibrating on the system. The overflow is really a function of the max memory b/w that the socket can support, max counter value and scaling factor. Signed-off-by:
Vikas Shivappa <vikas.shivappa@linux.intel.com> Signed-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by:
Tony Luck <tony.luck@intel.com> Acked-by:
Thomas Gleixner <tglx@linutronix.de> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Matt Fleming <matt@codeblueprint.co.uk> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Vince Weaver <vincent.weaver@maine.edu> Cc: fenghua.yu@intel.com Cc: h.peter.anvin@intel.com Cc: ravi.v.shankar@intel.com Cc: vikas.shivappa@intel.com Link: http://lkml.kernel.org/r/013b756c5006b1c4ca411f3ecf43ed52f19fbf87.1457723885.git.tony.luck@intel.comSigned-off-by:
Ingo Molnar <mingo@kernel.org> (cherry picked from commit e7ee3e8c) Signed-off-by:
-
Vikas Shivappa authored
BugLink: http://bugs.launchpad.net/bugs/1397880 RMID could be allocated or deallocated as part of RMID recycling. When an RMID is allocated for MBM event, the MBM counter needs to be initialized because next time we read the counter we need the previous value to account for total bytes that went to the memory controller. Similarly, when RMID is deallocated we need to update the ->count variable. Signed-off-by:
-
Tony Luck authored
BugLink: http://bugs.launchpad.net/bugs/1397880 Includes all the core infrastructure to measure the total_bytes and bandwidth. We have per socket counters for both total system wide L3 external bytes and local socket memory-controller bytes. The OS does MSR writes to MSR_IA32_QM_EVTSEL and MSR_IA32_QM_CTR to read the counters and uses the IA32_PQR_ASSOC_MSR to associate the RMID with the task. The tasks have a common RMID for CQM (cache quality of service monitoring) and MBM. Hence most of the scheduling code is reused from CQM. Signed-off-by:
-
Vikas Shivappa authored
BugLink: http://bugs.launchpad.net/bugs/1397880 The MBM init patch enumerates the Intel MBM (Memory b/w monitoring) and initializes the perf events and datastructures for monitoring the memory b/w. Its based on original patch series by Tony Luck and Kanaka Juvva. Memory bandwidth monitoring (MBM) provides OS/VMM a way to monitor bandwidth from one level of cache to another. The current patches support L3 external bandwidth monitoring. It supports both 'local bandwidth' and 'total bandwidth' monitoring for the socket. Local bandwidth measures the amount of data sent through the memory controller on the socket and total b/w measures the total system bandwidth. Extending the cache quality of service monitoring (CQM) we add two more events to the perf infrastructure: intel_cqm_llc/local_bytes - bytes sent through local socket memory controller intel_cqm_llc/total_bytes - total L3 external bytes sent The tasks are associated with a Resouce Monitoring ID (RMID) just like in CQM and OS uses a MSR write to indicate the RMID of the task during scheduling. Signed-off-by:
-
Thomas Gleixner authored
BugLink: http://bugs.launchpad.net/bugs/1397880 For per package oriented services we must be able to rely on the number of CPU packages to be within bounds. Create a tracking facility, which - calculates the number of possible packages depending on nr_cpu_ids after boot - makes sure that the package id is within the number of possible packages. If the apic id is outside we map it to a logical package id if there is enough space available. Provide interfaces for drivers to query the mapping and do translations from physcial to logical ids. Signed-off-by:
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
BugLink: http://bugs.launchpad.net/bugs/1397880 Pull timer updates from Thomas Gleixner: "The timer department delivers this time: - Support for cross clock domain timestamps in the core code plus a first user. That allows more precise timestamping for PTP and later for audio and other peripherals. The ptp/e1000e patches have been acked by the relevant maintainers and are carried in the timer tree to avoid merge ordering issues. - Support for unregistering the current clocksource watchdog. That lifts a limitation for switching clocksources which has been there from day 1 - The usual pile of fixes and updates to the core and the drivers. Nothing outstanding and exciting" * 'timers-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits) time/timekeeping: Work around false positive GCC warning e1000e: Adds hardware supported cross timestamp on e1000e nic ptp: Add PTP_SYS_OFFSET_PRECISE for driver crosstimestamping x86/tsc: Always Running Timer (ART) correlated clocksource hrtimer: Revert CLOCK_MONOTONIC_RAW support time: Add history to cross timestamp interface supporting slower devices time: Add driver cross timestamp interface for higher precision time synchronization time: Remove duplicated code in ktime_get_raw_and_real() time: Add timekeeping snapshot code capturing system time and counter time: Add cycles to nanoseconds translation jiffies: Use CLOCKSOURCE_MASK instead of constant clocksource: Introduce clocksource_freq2mult() clockevents/drivers/exynos_mct: Implement ->set_state_oneshot_stopped() clockevents/drivers/arm_global_timer: Implement ->set_state_oneshot_stopped() clockevents/drivers/arm_arch_timer: Implement ->set_state_oneshot_stopped() clocksource/drivers/arm_global_timer: Register delay timer clocksource/drivers/lpc32xx: Support timer-based ARM delay clocksource/drivers/lpc32xx: Support periodic mode clocksource/drivers/lpc32xx: Don't use the prescaler counter for clockevents clocksource/drivers/rockchip: Add err handle for rk_timer_init ... (cherry picked from commit 8a284c06) Signed-off-by:
-
Borislav Petkov authored
BugLink: http://bugs.launchpad.net/bugs/1397880 Move them to a separate header and have the following dependency: x86/cpufeatures.h <- x86/processor.h <- x86/cpufeature.h This makes it easier to use the header in asm code and not include the whole cpufeature.h and add guards for asm. Suggested-by:
H. Peter Anvin <hpa@zytor.com> Signed-off-by:
Borislav Petkov <bp@suse.de> Cc: Andy Lutomirski <luto@amacapital.net> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1453842730-28463-5-git-send-email-bp@alien8.deSigned-off-by:
-
Vikas Shivappa authored
BugLink: http://bugs.launchpad.net/bugs/1397880 Fixes the hotcpu notifier leak and other global variable memory leaks during CQM (cache quality of service monitoring) initialization. Signed-off-by:
-
Vikas Shivappa authored
BugLink: http://bugs.launchpad.net/bugs/1397880 Currently CQM (cache quality of service monitoring) is grouping all events belonging to same PID to use one RMID. However its not counting all of these different events. Hence we end up with a count of zero for all events other than the group leader. The patch tries to address the issue by keeping a flag in the perf_event.hw which has other CQM related fields. The field is updated at event creation and during grouping. Signed-off-by:
-
Pavel Tikhomirov authored
BugLink: http://bugs.launchpad.net/bugs/1566505 We probably need to fix superblock leak in patch (v4 "fs: Add user namesapace member to struct super_block"): Imagine posible code path in sget_userns: we iterate through type->fs_supers and do not find suitable sb, we drop sb_lock to allocate s and go to retry. After we dropped sb_lock some other task from different userns takes sb_lock, it is already in retry stage and has s allocated, so it puts its s in type->fs_supers list. So in retry we will find these sb in list and check it has a different userns, and finally we will return without freeing s. Signed-off-by:
Pavel Tikhomirov <ptikhomirov@virtuozzo.com> Acked-by:
Seth Forshee <seth.forshee@canonical.com> Signed-off-by:
-
Seth Forshee authored
BugLink: http://bugs.launchpad.net/bugs/1566505 Currently a new mount of an existing hierarchy always reuses the original super block, even when the new mount is in a cgroup namespace. This sometimes conflicts with the user namespace mount support, which requires a new mount of an existing super block to be in the same user namespace as the original mount. When mounting from non-init cgroup and user namespaces sget() will fail. To fix this we can pass a pointer to the cgroup ns to kernfs when mounting, causing kernfs_test_super() to no longer match super blocks from different cgroup namespaces. However we do wish to continue sharing the cgroup_root between mounts of the same heirarchy. The cgroup_root's lifetime is governed by the reference count of its cgrp member, but this is a percpu reference count and is not well suited to this new situation. Instead a new reference count is added to the cgroup_root structure to track the number of super blocks sharing that root, and this refcnt is used to determine when to put the cgroup reference. Signed-off-by:
-
Seth Forshee authored
BugLink: http://bugs.launchpad.net/bugs/1566505 These are required mount options, thus there is no need to initialize the values in struct fuse_mount_data. Signed-off-by:
-
Seth Forshee authored
BugLink: http://bugs.launchpad.net/bugs/1566505 In a userns mount some on-disk inodes may have ids which do not map into s_user_ns, in which case the in-kernel inodes are owned by invalid users. The superblock owner should be able to change attributes of these inodes but cannot. However it is unsafe to grant the superblock owner privileged access to all inodes in the superblock since proc, sysfs, etc. use DAC to protect files which may not belong to s_user_ns. The problem is restricted to only inodes where the owner or group is an invalid user. We can work around this by allowing users with CAP_CHOWN in s_user_ns to change an invalid owner or group id, so long as the other id is either invalid or mappable in s_user_ns. After changing ownership the user will be privileged towards the inode and thus able to change other attributes. As an precaution, checks for invalid ids are added to the proc and kernfs setattr interfaces. These filesystems are not expected to have inodes with invalid ids, but if it does happen any setattr operations will return -EPERM. Signed-off-by:
-
Seth Forshee authored
BugLink: http://bugs.launchpad.net/bugs/1566505 This ensures that quotas that aren't valid on disk never make it into the hash table. inodes with ids which don't map into s_user_ns will now have no quota enforcement. Signed-off-by:
-
Catalin Marinas authored
BugLink: http://bugs.launchpad.net/bugs/1566518 The set_pte_at() function must update the hardware PTE_RDONLY bit depending on the state of the PTE_WRITE and PTE_DIRTY bits of the given entry value. However, it currently only performs this for pte_valid() entries, ignoring PTE_PROT_NONE. The side-effect is that PROT_NONE mappings would not have the PTE_RDONLY bit set. Without CONFIG_ARM64_HW_AFDBM, this is not an issue since such PROT_NONE pages are not accessible anyway. With commit 2f4b829c ("arm64: Add support for hardware updates of the access and dirty pte bits"), the ptep_set_wrprotect() function was re-written to cope with automatic hardware updates of the dirty state. As an optimisation, only PTE_RDONLY is checked to assess the "dirty" status. Since set_pte_at() does not set this bit for PROT_NONE mappings, such pages may be considered "dirty" as a result of ptep_set_wrprotect(). This patch updates the pte_valid() check to pte_present() in set_pte_at(). It also adds PTE_PROT_NONE to the swap entry bits comment. Fixes: 2f4b829c ("arm64: Add support for hardware updates of the access and dirty pte bits") Signed-off-by:
Catalin Marinas <catalin.marinas@arm.com> Reported-by:
Ganapatrao Kulkarni <gkulkarni@caviumnetworks.com> Tested-by:
Ganapatrao Kulkarni <gkulkarni@cavium.com> Cc: <stable@vger.kernel.org> (cherry picked from commit fdc69e7d) Signed-off-by:
-
Catalin Marinas authored
BugLink: http://bugs.launchpad.net/bugs/1566518 Currently, set_pte_at() only checks the software PTE_WRITE bit for user mappings when it sets or clears the hardware PTE_RDONLY accordingly. The kernel ptes are written directly without any modification, relying solely on the protection bits in macros like PAGE_KERNEL. However, modifying kernel pte attributes via pte_wrprotect() would be ignored by set_pte_at(). Since pte_wrprotect() does not set PTE_RDONLY (it only clears PTE_WRITE), the new permission is not taken into account. This patch changes set_pte_at() to adjust the read-only permission for kernel ptes as well. As a side effect, existing PROT_* definitions used for kernel ioremap*() need to include PTE_DIRTY | PTE_WRITE. (additionally, white space fix for PTE_KERNEL_ROX) Acked-by:
Andrey Ryabinin <aryabinin@virtuozzo.com> Tested-by:
Ard Biesheuvel <ard.biesheuvel@linaro.org> Signed-off-by:
Will Deacon <will.deacon@arm.com> (cherry picked from commit ac15bd63) Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 https://git.kernel.org/cgit/linux/kernel/git/gregkh/usb.git/commit/?h=usb-linus&id=59b9023c356c54e5f468029fa504461d04c0f02b commit b37d83a6 ("usb: Parse the new USB 3.1 SuperSpeedPlus Isoc endpoint companion descriptor") caused a regression in 4.6-rc1 and fails to parse SuperSpeed endpoint companion descriptors. The new SuperSpeedPlus Isoc endpoint companion parsing code incorrectly decreased the the remaining buffer size before comparing the size with the expected length of the descriptor. This lead to possible failure in reading the SuperSpeed endpoint companion descriptor of the last endpoint, displaying a message like: "No SuperSpeed endpoint companion for config 1 interface 0 altsetting 0 ep 129: using minimum values" Fix it by decreasing the size after comparing it. Also finish all the SS endpoint companion parsing before calling SSP isoc endpoint parsing function. Fixes: b37d83a6Signed-off-by:
Mathias Nyman <mathias.nyman@linux.intel.com> Signed-off-by:
Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 The transfer burst count (TBC) field in the Isoc TRB does not fit the new larger burst count available for USB 3.1 SSP Isoc tranfers. xhci 1.1 solved this by reusing the TD size field for transfer burst count. The Mult field was outgrown as well. xhci 1.1 controllers can calculate Mult itself and is not set if the new layout is used. xhci 1.1 controllers that support the new Isoc TRB format expose a Extended TBC Capability (ETC). To take the new format into use the xhci host controller driver needs to set a Extended TBC Enable (ETE) bit. Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 Clean up xhci_queue_isoc_tx() and helpers to prepare them for USB 3.1 and xhci 1.1 isoc TRB changes. Only functional change is adding xhci version 1.1 to the BEI flag check toghether with xhci version 1.0. Both versions behave the same. Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 SuperSpeedPlus doubled the number of transactions per service interval the isoc endpoints supports. To support this, xhci 1.1 added Large ESIT Capability (LEC), which takes into use new bits in the endpoint context to fit the parameters. If xhci supports LEC, and the device has a SuperSpeedPlus Isoc companion descriptor then take into use the high bits of max esit payload, and skip calculating the Mult field as it wouldn't fit. LEC capable host will calculate the Mult based on other paramenters. Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 xhci_endpoint_init() and helper functions were a bit messy. Adding the higher bandwidth SuperSpeedPlus Isoc support on top of it would make it even harder to read. No functional changes. Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 USB 3.1 devices that support precision time measurement have an additional PTM cabaility descriptor as part of the full BOS descriptor Look for this descriptor while parsing the BOS descriptor, and store it in struct usb_hub_bos if it exists. Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 USB 3.1 devices can return a new SuperSpeedPlus isoc endpoint companion descriptor for a isochronous endpoint that requires more than 48K bytes per Service Interval. The new descriptor immediately follows the old USB 3.0 SuperSpeed Endpoint Companion and will provide a new BytesPerInterval value. It is parsed and stored in struct usb_host_endpoint with the other endpoint related descriptors, and should be used by USB3.1 capable hosts to reserve bus time in the schedule. Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 USB3.1 specifies a SuperSpeedPlus Isoc endpoint companion descriptor which is returned as part of the devices complete configuration descriptor. It contains number of bytes per service interval which is needed when reserving bus time in the schedule for transfers over 48K bytes per service interval. If bmAttributes bit 7 is set in the old SuperSpeed Endpoint Companion descriptor, it will be ollowed by the new SuperSpeedPlus Isoc Endpoint Companion descriptor. Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 The speed field of the input slot context should represent the speed the device is working at. Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 If a xhci controller does not provide a protocol speed ID (PSI) table, a default one should be used instead. Add the default values to the SuperSpeedPlus device capability. Overwrite the default ones if a PSI table exists. See xHCI 1.1 sectio 7.2.2.1.1 for more info Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 In most cases the devices with the speed set to USB_SPEED_SUPER_PLUS are handled like regular SuperSpeed devices. Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 usb 3.1 extend the hub get-port-status request by adding different request types. the new request types return 4 additional bytes called extended port status, these bytes are returned after the regular portstatus and portchange values. The extended port status contains a speed ID for the currently used sublink speed. A table of supported Speed IDs with details about the link is provided by the hub in the device descriptor BOS SuperSpeedPlus device capability Sublink Speed Attributes. Support this new request. Ask for the extended port status after port reset if hub supports USB 3.1. If link is running at SuperSpeedPlus set the device speed to USB_SPEED_SUPER_PLUS Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623Signed-off-by:
-
Mathias Nyman authored
BugLink: http://bugs.launchpad.net/bugs/1519623 The same way as SuperSpeed devices show "5000" as device speed we wan't to show "10000" as the default speed for SuperSpeedPlus devices in sysfs. Signed-off-by:
-
