* tmp-917a9:
ARM/vdso: Mark the vDSO code read-only after init
x86/vdso: Mark the vDSO code read-only after init
lkdtm: Verify that '__ro_after_init' works correctly
arch: Introduce post-init read-only memory
x86/mm: Always enable CONFIG_DEBUG_RODATA and remove the Kconfig option
mm/init: Add 'rodata=off' boot cmdline parameter to disable read-only kernel mappings
asm-generic: Consolidate mark_rodata_ro()
Linux 4.4.6
ld-version: Fix awk regex compile failure
target: Drop incorrect ABORT_TASK put for completed commands
block: don't optimize for non-cloned bio in bio_get_last_bvec()
MIPS: smp.c: Fix uninitialised temp_foreign_map
MIPS: Fix build error when SMP is used without GIC
ovl: fix getcwd() failure after unsuccessful rmdir
ovl: copy new uid/gid into overlayfs runtime inode
userfaultfd: don't block on the last VM updates at exit time
powerpc/powernv: Fix OPAL_CONSOLE_FLUSH prototype and usages
powerpc/powernv: Add a kmsg_dumper that flushes console output on panic
powerpc: Fix dedotify for binutils >= 2.26
Revert "drm/radeon/pm: adjust display configuration after powerstate"
drm/radeon: Fix error handling in radeon_flip_work_func.
drm/amdgpu: Fix error handling in amdgpu_flip_work_func.
Revert "drm/radeon: call hpd_irq_event on resume"
x86/mm: Fix slow_virt_to_phys() for X86_PAE again
gpu: ipu-v3: Do not bail out on missing optional port nodes
mac80211: Fix Public Action frame RX in AP mode
mac80211: check PN correctly for GCMP-encrypted fragmented MPDUs
mac80211: minstrel_ht: fix a logic error in RTS/CTS handling
mac80211: minstrel_ht: set default tx aggregation timeout to 0
mac80211: fix use of uninitialised values in RX aggregation
mac80211: minstrel: Change expected throughput unit back to Kbps
iwlwifi: mvm: inc pending frames counter also when txing non-sta
can: gs_usb: fixed disconnect bug by removing erroneous use of kfree()
cfg80211/wext: fix message ordering
wext: fix message delay/ordering
ovl: fix working on distributed fs as lower layer
ovl: ignore lower entries when checking purity of non-directory entries
ASoC: wm8958: Fix enum ctl accesses in a wrong type
ASoC: wm8994: Fix enum ctl accesses in a wrong type
ASoC: samsung: Use IRQ safe spin lock calls
ASoC: dapm: Fix ctl value accesses in a wrong type
ncpfs: fix a braino in OOM handling in ncp_fill_cache()
jffs2: reduce the breakage on recovery from halfway failed rename()
dmaengine: at_xdmac: fix residue computation
tracing: Fix check for cpu online when event is disabled
s390/dasd: fix diag 0x250 inline assembly
s390/mm: four page table levels vs. fork
KVM: MMU: fix reserved bit check for ept=0/CR0.WP=0/CR4.SMEP=1/EFER.NX=0
KVM: MMU: fix ept=0/pte.u=1/pte.w=0/CR0.WP=0/CR4.SMEP=1/EFER.NX=0 combo
KVM: PPC: Book3S HV: Sanitize special-purpose register values on guest exit
KVM: s390: correct fprs on SIGP (STOP AND) STORE STATUS
KVM: VMX: disable PEBS before a guest entry
kvm: cap halt polling at exactly halt_poll_ns
PCI: Allow a NULL "parent" pointer in pci_bus_assign_domain_nr()
ARM: OMAP2+: hwmod: Introduce ti,no-idle dt property
ARM: dts: dra7: do not gate cpsw clock due to errata i877
ARM: mvebu: fix overlap of Crypto SRAM with PCIe memory window
arm64: account for sparsemem section alignment when choosing vmemmap offset
Linux 4.4.5
drm/amdgpu: fix topaz/tonga gmc assignment in 4.4 stable
modules: fix longstanding /proc/kallsyms vs module insertion race.
drm/i915: refine qemu south bridge detection
drm/i915: more virtual south bridge detection
block: get the 1st and last bvec via helpers
block: check virt boundary in bio_will_gap()
drm/amdgpu: Use drm_calloc_large for VM page_tables array
thermal: cpu_cooling: fix out of bounds access in time_in_idle
i2c: brcmstb: allocate correct amount of memory for regmap
ubi: Fix out of bounds write in volume update code
cxl: Fix PSL timebase synchronization detection
MIPS: traps: Fix SIGFPE information leak from `do_ov' and `do_trap_or_bp'
MIPS: scache: Fix scache init with invalid line size.
USB: serial: option: add support for Quectel UC20
USB: serial: option: add support for Telit LE922 PID 0x1045
USB: qcserial: add Sierra Wireless EM74xx device ID
USB: qcserial: add Dell Wireless 5809e Gobi 4G HSPA+ (rev3)
USB: cp210x: Add ID for Parrot NMEA GPS Flight Recorder
usb: chipidea: otg: change workqueue ci_otg as freezable
ALSA: timer: Fix broken compat timer user status ioctl
ALSA: hdspm: Fix zero-division
ALSA: hdsp: Fix wrong boolean ctl value accesses
ALSA: hdspm: Fix wrong boolean ctl value accesses
ALSA: seq: oss: Don't drain at closing a client
ALSA: pcm: Fix ioctls for X32 ABI
ALSA: timer: Fix ioctls for X32 ABI
ALSA: rawmidi: Fix ioctls X32 ABI
ALSA: hda - Fix mic issues on Acer Aspire E1-472
ALSA: ctl: Fix ioctls for X32 ABI
ALSA: usb-audio: Add a quirk for Plantronics DA45
adv7604: fix tx 5v detect regression
dmaengine: pxa_dma: fix cyclic transfers
Fix directory hardlinks from deleted directories
jffs2: Fix page lock / f->sem deadlock
Revert "jffs2: Fix lock acquisition order bug in jffs2_write_begin"
Btrfs: fix loading of orphan roots leading to BUG_ON
pata-rb532-cf: get rid of the irq_to_gpio() call
tracing: Do not have 'comm' filter override event 'comm' field
ata: ahci: don't mark HotPlugCapable Ports as external/removable
PM / sleep / x86: Fix crash on graph trace through x86 suspend
arm64: vmemmap: use virtual projection of linear region
Adding Intel Lewisburg device IDs for SATA
writeback: flush inode cgroup wb switches instead of pinning super_block
block: bio: introduce helpers to get the 1st and last bvec
libata: Align ata_device's id on a cacheline
libata: fix HDIO_GET_32BIT ioctl
drm/amdgpu: return from atombios_dp_get_dpcd only when error
drm/amdgpu/gfx8: specify which engine to wait before vm flush
drm/amdgpu: apply gfx_v8 fixes to gfx_v7 as well
drm/amdgpu/pm: update current crtc info after setting the powerstate
drm/radeon/pm: update current crtc info after setting the powerstate
drm/ast: Fix incorrect register check for DRAM width
target: Fix WRITE_SAME/DISCARD conversion to linux 512b sectors
iommu/vt-d: Use BUS_NOTIFY_REMOVED_DEVICE in hotplug path
iommu/amd: Fix boot warning when device 00:00.0 is not iommu covered
iommu/amd: Apply workaround for ATS write permission check
arm/arm64: KVM: Fix ioctl error handling
KVM: x86: fix root cause for missed hardware breakpoints
vfio: fix ioctl error handling
Fix cifs_uniqueid_to_ino_t() function for s390x
CIFS: Fix SMB2+ interim response processing for read requests
cifs: fix out-of-bounds access in lease parsing
fbcon: set a default value to blink interval
kvm: x86: Update tsc multiplier on change.
mips/kvm: fix ioctl error handling
parisc: Fix ptrace syscall number and return value modification
PCI: keystone: Fix MSI code that retrieves struct pcie_port pointer
block: Initialize max_dev_sectors to 0
drm/amdgpu: mask out WC from BO on unsupported arches
btrfs: async-thread: Fix a use-after-free error for trace
btrfs: Fix no_space in write and rm loop
Btrfs: fix deadlock running delayed iputs at transaction commit time
drivers: sh: Restore legacy clock domain on SuperH platforms
use ->d_seq to get coherency between ->d_inode and ->d_flags
Linux 4.4.4
iwlwifi: mvm: don't allow sched scans without matches to be started
iwlwifi: update and fix 7265 series PCI IDs
iwlwifi: pcie: properly configure the debug buffer size for 8000
iwlwifi: dvm: fix WoWLAN
security: let security modules use PTRACE_MODE_* with bitmasks
IB/cma: Fix RDMA port validation for iWarp
x86/irq: Plug vector cleanup race
x86/irq: Call irq_force_move_complete with irq descriptor
x86/irq: Remove outgoing CPU from vector cleanup mask
x86/irq: Remove the cpumask allocation from send_cleanup_vector()
x86/irq: Clear move_in_progress before sending cleanup IPI
x86/irq: Remove offline cpus from vector cleanup
x86/irq: Get rid of code duplication
x86/irq: Copy vectormask instead of an AND operation
x86/irq: Check vector allocation early
x86/irq: Reorganize the search in assign_irq_vector
x86/irq: Reorganize the return path in assign_irq_vector
x86/irq: Do not use apic_chip_data.old_domain as temporary buffer
x86/irq: Validate that irq descriptor is still active
x86/irq: Fix a race in x86_vector_free_irqs()
x86/irq: Call chip->irq_set_affinity in proper context
x86/entry/compat: Add missing CLAC to entry_INT80_32
x86/mpx: Fix off-by-one comparison with nr_registers
hpfs: don't truncate the file when delete fails
do_last(): ELOOP failure exit should be done after leaving RCU mode
should_follow_link(): validate ->d_seq after having decided to follow
xen/pcifront: Fix mysterious crashes when NUMA locality information was extracted.
xen/pciback: Save the number of MSI-X entries to be copied later.
xen/pciback: Check PF instead of VF for PCI_COMMAND_MEMORY
xen/scsiback: correct frontend counting
xen/arm: correctly handle DMA mapping of compound pages
ARM: at91/dt: fix typo in sama5d2 pinmux descriptions
ARM: OMAP2+: Fix onenand initialization to avoid filesystem corruption
do_last(): don't let a bogus return value from ->open() et.al. to confuse us
kernel/resource.c: fix muxed resource handling in __request_region()
sunrpc/cache: fix off-by-one in qword_get()
tracing: Fix showing function event in available_events
powerpc/eeh: Fix partial hotplug criterion
KVM: x86: MMU: fix ubsan index-out-of-range warning
KVM: x86: fix conversion of addresses to linear in 32-bit protected mode
KVM: x86: fix missed hardware breakpoints
KVM: arm/arm64: vgic: Ensure bitmaps are long enough
KVM: async_pf: do not warn on page allocation failures
of/irq: Fix msi-map calculation for nonzero rid-base
NFSv4: Fix a dentry leak on alias use
nfs: fix nfs_size_to_loff_t
block: fix use-after-free in dio_bio_complete
bio: return EINTR if copying to user space got interrupted
i2c: i801: Adding Intel Lewisburg support for iTCO
phy: core: fix wrong err handle for phy_power_on
writeback: keep superblock pinned during cgroup writeback association switches
cgroup: make sure a parent css isn't offlined before its children
cpuset: make mm migration asynchronous
PCI/AER: Flush workqueue on device remove to avoid use-after-free
ARCv2: SMP: Emulate IPI to self using software triggered interrupt
ARCv2: STAR 9000950267: Handle return from intr to Delay Slot #2
libata: fix sff host state machine locking while polling
qla2xxx: Fix stale pointer access.
spi: atmel: fix gpio chip-select in case of non-DT platform
target: Fix race with SCF_SEND_DELAYED_TAS handling
target: Fix remote-port TMR ABORT + se_cmd fabric stop
target: Fix TAS handling for multi-session se_node_acls
target: Fix LUN_RESET active TMR descriptor handling
target: Fix LUN_RESET active I/O handling for ACK_KREF
ALSA: hda - Fixing background noise on Dell Inspiron 3162
ALSA: hda - Apply clock gate workaround to Skylake, too
Revert "workqueue: make sure delayed work run in local cpu"
workqueue: handle NUMA_NO_NODE for unbound pool_workqueue lookup
mac80211: Requeue work after scan complete for all VIF types.
rfkill: fix rfkill_fop_read wait_event usage
tick/nohz: Set the correct expiry when switching to nohz/lowres mode
perf stat: Do not clean event's private stats
cdc-acm:exclude Samsung phone 04e8:685d
Revert "Staging: panel: usleep_range is preferred over udelay"
Staging: speakup: Fix getting port information
sd: Optimal I/O size is in bytes, not sectors
libceph: don't spam dmesg with stray reply warnings
libceph: use the right footer size when skipping a message
libceph: don't bail early from try_read() when skipping a message
libceph: fix ceph_msg_revoke()
seccomp: always propagate NO_NEW_PRIVS on tsync
cpufreq: Fix NULL reference crash while accessing policy->governor_data
cpufreq: pxa2xx: fix pxa_cpufreq_change_voltage prototype
hwmon: (ads1015) Handle negative conversion values correctly
hwmon: (gpio-fan) Remove un-necessary speed_index lookup for thermal hook
hwmon: (dell-smm) Blacklist Dell Studio XPS 8000
Thermal: do thermal zone update after a cooling device registered
Thermal: handle thermal zone device properly during system sleep
Thermal: initialize thermal zone device correctly
IB/mlx5: Expose correct maximum number of CQE capacity
IB/qib: Support creating qps with GFP_NOIO flag
IB/qib: fix mcast detach when qp not attached
IB/cm: Fix a recently introduced deadlock
dmaengine: dw: disable BLOCK IRQs for non-cyclic xfer
dmaengine: at_xdmac: fix resume for cyclic transfers
dmaengine: dw: fix cyclic transfer callbacks
dmaengine: dw: fix cyclic transfer setup
nfit: fix multi-interface dimm handling, acpi6.1 compatibility
ACPI / PCI / hotplug: unlock in error path in acpiphp_enable_slot()
ACPI: Revert "ACPI / video: Add Dell Inspiron 5737 to the blacklist"
ACPI / video: Add disable_backlight_sysfs_if quirk for the Toshiba Satellite R830
ACPI / video: Add disable_backlight_sysfs_if quirk for the Toshiba Portege R700
lib: sw842: select crc32
uapi: update install list after nvme.h rename
ideapad-laptop: Add Lenovo Yoga 700 to no_hw_rfkill dmi list
ideapad-laptop: Add Lenovo ideapad Y700-17ISK to no_hw_rfkill dmi list
toshiba_acpi: Fix blank screen at boot if transflective backlight is supported
make sure that freeing shmem fast symlinks is RCU-delayed
drm/radeon/pm: adjust display configuration after powerstate
drm/radeon: Don't hang in radeon_flip_work_func on disabled crtc. (v2)
drm: Fix treatment of drm_vblank_offdelay in drm_vblank_on() (v2)
drm: Fix drm_vblank_pre/post_modeset regression from Linux 4.4
drm: Prevent vblank counter bumps > 1 with active vblank clients. (v2)
drm: No-Op redundant calls to drm_vblank_off() (v2)
drm/radeon: use post-decrement in error handling
drm/qxl: use kmalloc_array to alloc reloc_info in qxl_process_single_command
drm/i915: fix error path in intel_setup_gmbus()
drm/i915/dsi: don't pass arbitrary data to sideband
drm/i915/dsi: defend gpio table against out of bounds access
drm/i915/skl: Don't skip mst encoders in skl_ddi_pll_select()
drm/i915: Don't reject primary plane windowing with color keying enabled on SKL+
drm/i915/dp: fall back to 18 bpp when sink capability is unknown
drm/i915: Make sure DC writes are coherent on flush.
drm/i915: Init power domains early in driver load
drm/i915: intel_hpd_init(): Fix suspend/resume reprobing
drm/i915: Restore inhibiting the load of the default context
drm: fix missing reference counting decrease
drm/radeon: hold reference to fences in radeon_sa_bo_new
drm/radeon: mask out WC from BO on unsupported arches
drm: add helper to check for wc memory support
drm/radeon: fix DP audio support for APU with DCE4.1 display engine
drm/radeon: Add a common function for DFS handling
drm/radeon: cleaned up VCO output settings for DP audio
drm/radeon: properly byte swap vce firmware setup
drm/radeon: clean up fujitsu quirks
drm/radeon: Fix "slow" audio over DP on DCE8+
drm/radeon: call hpd_irq_event on resume
drm/radeon: Fix off-by-one errors in radeon_vm_bo_set_addr
drm/dp/mst: deallocate payload on port destruction
drm/dp/mst: Reverse order of MST enable and clearing VC payload table.
drm/dp/mst: move GUID storage from mgr, port to only mst branch
drm/dp/mst: Calculate MST PBN with 31.32 fixed point
drm: Add drm_fixp_from_fraction and drm_fixp2int_ceil
drm/dp/mst: fix in RAD element access
drm/dp/mst: fix in MSTB RAD initialization
drm/dp/mst: always send reply for UP request
drm/dp/mst: process broadcast messages correctly
drm/nouveau: platform: Fix deferred probe
drm/nouveau/disp/dp: ensure sink is powered up before attempting link training
drm/nouveau/display: Enable vblank irqs after display engine is on again.
drm/nouveau/kms: take mode_config mutex in connector hotplug path
drm/amdgpu/pm: adjust display configuration after powerstate
drm/amdgpu: Don't hang in amdgpu_flip_work_func on disabled crtc.
drm/amdgpu: use post-decrement in error handling
drm/amdgpu: fix issue with overlapping userptrs
drm/amdgpu: hold reference to fences in amdgpu_sa_bo_new (v2)
drm/amdgpu: remove unnecessary forward declaration
drm/amdgpu: fix s4 resume
drm/amdgpu: remove exp hardware support from iceland
drm/amdgpu: don't load MEC2 on topaz
drm/amdgpu: drop topaz support from gmc8 module
drm/amdgpu: pull topaz gmc bits into gmc_v7
drm/amdgpu: The VI specific EXE bit should only apply to GMC v8.0 above
drm/amdgpu: iceland use CI based MC IP
drm/amdgpu: move gmc7 support out of CIK dependency
drm/amdgpu: no need to load MC firmware on fiji
drm/amdgpu: fix amdgpu_bo_pin_restricted VRAM placing v2
drm/amdgpu: fix tonga smu resume
drm/amdgpu: fix lost sync_to if scheduler is enabled.
drm/amdgpu: call hpd_irq_event on resume
drm/amdgpu: Fix off-by-one errors in amdgpu_vm_bo_map
drm/vmwgfx: respect 'nomodeset'
drm/vmwgfx: Fix a width / pitch mismatch on framebuffer updates
drm/vmwgfx: Fix an incorrect lock check
virtio_pci: fix use after free on release
virtio_balloon: fix race between migration and ballooning
virtio_balloon: fix race by fill and leak
regulator: mt6311: MT6311_REGULATOR needs to select REGMAP_I2C
regulator: axp20x: Fix GPIO LDO enable value for AXP22x
clk: exynos: use irqsave version of spin_lock to avoid deadlock with irqs
cxl: use correct operator when writing pcie config space values
sparc64: fix incorrect sign extension in sys_sparc64_personality
EDAC, mc_sysfs: Fix freeing bus' name
EDAC: Robustify workqueues destruction
MIPS: Fix buffer overflow in syscall_get_arguments()
MIPS: Fix some missing CONFIG_CPU_MIPSR6 #ifdefs
MIPS: hpet: Choose a safe value for the ETIME check
MIPS: Loongson-3: Fix SMP_ASK_C0COUNT IPI handler
Revert "MIPS: Fix PAGE_MASK definition"
cputime: Prevent 32bit overflow in time[val|spec]_to_cputime()
time: Avoid signed overflow in timekeeping_get_ns()
Bluetooth: 6lowpan: Fix handling of uncompressed IPv6 packets
Bluetooth: 6lowpan: Fix kernel NULL pointer dereferences
Bluetooth: Fix incorrect removing of IRKs
Bluetooth: Add support of Toshiba Broadcom based devices
Bluetooth: Use continuous scanning when creating LE connections
Drivers: hv: vmbus: Fix a Host signaling bug
tools: hv: vss: fix the write()'s argument: error -> vss_msg
mmc: sdhci: Allow override of get_cd() called from sdhci_request()
mmc: sdhci: Allow override of mmc host operations
mmc: sdhci-pci: Fix card detect race for Intel BXT/APL
mmc: pxamci: fix again read-only gpio detection polarity
mmc: sdhci-acpi: Fix card detect race for Intel BXT/APL
mmc: mmci: fix an ages old detection error
mmc: core: Enable tuning according to the actual timing
mmc: sdhci: Fix sdhci_runtime_pm_bus_on/off()
mmc: mmc: Fix incorrect use of driver strength switching HS200 and HS400
mmc: sdio: Fix invalid vdd in voltage switch power cycle
mmc: sdhci: Fix DMA descriptor with zero data length
mmc: sdhci-pci: Do not default to 33 Ohm driver strength for Intel SPT
mmc: usdhi6rol0: handle NULL data in timeout
clockevents/tcb_clksrc: Prevent disabling an already disabled clock
posix-clock: Fix return code on the poll method's error path
irqchip/gic-v3-its: Fix double ICC_EOIR write for LPI in EOImode==1
irqchip/atmel-aic: Fix wrong bit operation for IRQ priority
irqchip/mxs: Add missing set_handle_irq()
irqchip/omap-intc: Add support for spurious irq handling
coresight: checking for NULL string in coresight_name_match()
dm: fix dm_rq_target_io leak on faults with .request_fn DM w/ blk-mq paths
dm snapshot: fix hung bios when copy error occurs
dm space map metadata: remove unused variable in brb_pop()
tda1004x: only update the frontend properties if locked
vb2: fix a regression in poll() behavior for output,streams
gspca: ov534/topro: prevent a division by 0
si2157: return -EINVAL if firmware blob is too big
media: dvb-core: Don't force CAN_INVERSION_AUTO in oneshot mode
rc: sunxi-cir: Initialize the spinlock properly
namei: ->d_inode of a pinned dentry is stable only for positives
mei: validate request value in client notify request ioctl
mei: fix fasync return value on error
rtlwifi: rtl8723be: Fix module parameter initialization
rtlwifi: rtl8188ee: Fix module parameter initialization
rtlwifi: rtl8192se: Fix module parameter initialization
rtlwifi: rtl8723ae: Fix initialization of module parameters
rtlwifi: rtl8192de: Fix incorrect module parameter descriptions
rtlwifi: rtl8192ce: Fix handling of module parameters
rtlwifi: rtl8192cu: Add missing parameter setup
rtlwifi: rtl_pci: Fix kernel panic
locks: fix unlock when fcntl_setlk races with a close
um: link with -lpthread
uml: fix hostfs mknod()
uml: flush stdout before forking
s390/fpu: signals vs. floating point control register
s390/compat: correct restore of high gprs on signal return
s390/dasd: fix performance drop
s390/dasd: fix refcount for PAV reassignment
s390/dasd: prevent incorrect length error under z/VM after PAV changes
s390: fix normalization bug in exception table sorting
btrfs: initialize the seq counter in struct btrfs_device
Btrfs: Initialize btrfs_root->highest_objectid when loading tree root and subvolume roots
Btrfs: fix transaction handle leak on failure to create hard link
Btrfs: fix number of transaction units required to create symlink
Btrfs: send, don't BUG_ON() when an empty symlink is found
btrfs: statfs: report zero available if metadata are exhausted
Btrfs: igrab inode in writepage
Btrfs: add missing brelse when superblock checksum fails
KVM: s390: fix memory overwrites when vx is disabled
s390/kvm: remove dependency on struct save_area definition
clocksource/drivers/vt8500: Increase the minimum delta
genirq: Validate action before dereferencing it in handle_irq_event_percpu()
mm: numa: quickly fail allocations for NUMA balancing on full nodes
mm: thp: fix SMP race condition between THP page fault and MADV_DONTNEED
ocfs2: unlock inode if deleting inode from orphan fails
drm/i915: shut up gen8+ SDE irq dmesg noise
iw_cxgb3: Fix incorrectly returning error on success
spi: omap2-mcspi: Prevent duplicate gpio_request
drivers: android: correct the size of struct binder_uintptr_t for BC_DEAD_BINDER_DONE
USB: option: add "4G LTE usb-modem U901"
USB: option: add support for SIM7100E
USB: cp210x: add IDs for GE B650V3 and B850V3 boards
usb: dwc3: Fix assignment of EP transfer resources
can: ems_usb: Fix possible tx overflow
dm thin: fix race condition when destroying thin pool workqueue
bcache: Change refill_dirty() to always scan entire disk if necessary
bcache: prevent crash on changing writeback_running
bcache: allows use of register in udev to avoid "device_busy" error.
bcache: unregister reboot notifier if bcache fails to unregister device
bcache: fix a leak in bch_cached_dev_run()
bcache: clear BCACHE_DEV_UNLINK_DONE flag when attaching a backing device
bcache: Add a cond_resched() call to gc
bcache: fix a livelock when we cause a huge number of cache misses
lib/ucs2_string: Correct ucs2 -> utf8 conversion
efi: Add pstore variables to the deletion whitelist
efi: Make efivarfs entries immutable by default
efi: Make our variable validation list include the guid
efi: Do variable name validation tests in utf8
efi: Use ucs2_as_utf8 in efivarfs instead of open coding a bad version
lib/ucs2_string: Add ucs2 -> utf8 helper functions
ARM: 8457/1: psci-smp is built only for SMP
drm/gma500: Use correct unref in the gem bo create function
devm_memremap: Fix error value when memremap failed
KVM: s390: fix guest fprs memory leak
arm64: errata: Add -mpc-relative-literal-loads to build flags
ARM: debug-ll: fix BCM63xx entry for multiplatform
ext4: fix bh->b_state corruption
sctp: Fix port hash table size computation
unix_diag: fix incorrect sign extension in unix_lookup_by_ino
tipc: unlock in error path
rtnl: RTM_GETNETCONF: fix wrong return value
IFF_NO_QUEUE: Fix for drivers not calling ether_setup()
tcp/dccp: fix another race at listener dismantle
route: check and remove route cache when we get route
net_sched fix: reclassification needs to consider ether protocol changes
pppoe: fix reference counting in PPPoE proxy
l2tp: Fix error creating L2TP tunnels
net/mlx4_en: Avoid changing dev->features directly in run-time
net/mlx4_en: Choose time-stamping shift value according to HW frequency
net/mlx4_en: Count HW buffer overrun only once
qmi_wwan: add "4G LTE usb-modem U901"
tcp: md5: release request socket instead of listener
tipc: fix premature addition of node to lookup table
af_unix: Guard against other == sk in unix_dgram_sendmsg
af_unix: Don't set err in unix_stream_read_generic unless there was an error
ipv4: fix memory leaks in ip_cmsg_send() callers
bonding: Fix ARP monitor validation
bpf: fix branch offset adjustment on backjumps after patching ctx expansion
flow_dissector: Fix unaligned access in __skb_flow_dissector when used by eth_get_headlen
net: Copy inner L3 and L4 headers as unaligned on GRE TEB
sctp: translate network order to host order when users get a hmacid
enic: increment devcmd2 result ring in case of timeout
tg3: Fix for tg3 transmit queue 0 timed out when too many gso_segs
net:Add sysctl_max_skb_frags
tcp: do not drop syn_recv on all icmp reports
unix: correctly track in-flight fds in sending process user_struct
ipv6: fix a lockdep splat
ipv6: addrconf: Fix recursive spin lock call
ipv6/udp: use sticky pktinfo egress ifindex on connect()
ipv6: enforce flowi6_oif usage in ip6_dst_lookup_tail()
tcp: beware of alignments in tcp_get_info()
switchdev: Require RTNL mutex to be held when sending FDB notifications
inet: frag: Always orphan skbs inside ip_defrag()
tipc: fix connection abort during subscription cancel
net: dsa: fix mv88e6xxx switches
sctp: allow setting SCTP_SACK_IMMEDIATELY by the application
pptp: fix illegal memory access caused by multiple bind()s
af_unix: fix struct pid memory leak
tcp: fix NULL deref in tcp_v4_send_ack()
lwt: fix rx checksum setting for lwt devices tunneling over ipv6
tunnels: Allow IPv6 UDP checksums to be correctly controlled.
net: dp83640: Fix tx timestamp overflow handling.
gro: Make GRO aware of lightweight tunnels.
af_iucv: Validate socket address length in iucv_sock_bind()
Conflicts:
arch/arm64/Makefile
arch/arm64/include/asm/cacheflush.h
drivers/mmc/host/sdhci.c
drivers/usb/dwc3/ep0.c
drivers/usb/dwc3/gadget.c
kernel/module.c
sound/core/pcm_compat.c
CRs-Fixed: 1010239
Signed-off-by: Runmin Wang <runminw@codeaurora.org>
Change-Id: I41a28636fc9ad91f9d979b191784609476294cdf
[ Upstream commit 9cf7490360bf2c46a16b7525f899e4970c5fc144 ]
Petr Novopashenniy reported that ICMP redirects on SYN_RECV sockets
were leading to RST.
This is of course incorrect.
A specific list of ICMP messages should be able to drop a SYN_RECV.
For instance, a REDIRECT on SYN_RECV shall be ignored, as we do
not hold a dst per SYN_RECV pseudo request.
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=111751
Fixes: 079096f103 ("tcp/dccp: install syn_recv requests into ehash table")
Reported-by: Petr Novopashenniy <pety@rusnet.ru>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This implements SOCK_DESTROY for TCP sockets. It causes all
blocking calls on the socket to fail fast with ECONNABORTED and
causes a protocol close of the socket. It informs the other end
of the connection by sending a RST, i.e., initiating a TCP ABORT
as per RFC 793. ECONNABORTED was chosen for consistency with
FreeBSD.
[cherry-pick of net-next c1e64e298b8cad309091b95d8436a0255c84f54a]
Change-Id: I728a01ef03f2ccfb9016a3f3051ef00975980e49
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The default initial rwnd is hardcoded to 10.
Now we allow it to be controlled via
/proc/sys/net/ipv4/tcp_default_init_rwnd
which limits the values from 3 to 100
This is somewhat needed because ipv6 routes are
autoconfigured by the kernel.
See "An Argument for Increasing TCP's Initial Congestion Window"
in https://developers.google.com/speed/articles/tcp_initcwnd_paper.pdf
Change-Id: I386b2a9d62de0ebe05c1ebe1b4bd91b314af5c54
Signed-off-by: JP Abgrall <jpa@google.com>
Conflicts:
net/ipv4/sysctl_net_ipv4.c
net/ipv4/tcp_input.c
Introduce a new socket ioctl, SIOCKILLADDR, that nukes all sockets
bound to the same local address. This is useful in situations with
dynamic IPs, to kill stuck connections.
Signed-off-by: Brian Swetland <swetland@google.com>
net: fix tcp_v4_nuke_addr
Signed-off-by: Dima Zavin <dima@android.com>
net: ipv4: Fix a spinlock recursion bug in tcp_v4_nuke.
We can't hold the lock while calling to tcp_done(), so we drop
it before calling. We then have to start at the top of the chain again.
Signed-off-by: Dima Zavin <dima@android.com>
net: ipv4: Fix race in tcp_v4_nuke_addr().
To fix a recursive deadlock in 2.6.29, we stopped holding the hash table lock
across tcp_done() calls. This fixed the deadlock, but introduced a race where
the socket could die or change state.
Fix: Before unlocking the hash table, we grab a reference to the socket. We
can then unlock the hash table without risk of the socket going away. We then
lock the socket, which is safe because it is pinned. We can then call
tcp_done() without recursive deadlock and without race. Upon return, we unlock
the socket and then unpin it, killing it.
Change-Id: Idcdae072b48238b01bdbc8823b60310f1976e045
Signed-off-by: Robert Love <rlove@google.com>
Acked-by: Dima Zavin <dima@android.com>
ipv4: disable bottom halves around call to tcp_done().
Signed-off-by: Robert Love <rlove@google.com>
Signed-off-by: Colin Cross <ccross@android.com>
ipv4: Move sk_error_report inside bh_lock_sock in tcp_v4_nuke_addr
When sk_error_report is called, it wakes up the user-space thread, which then
calls tcp_close. When the tcp_close is interrupted by the tcp_v4_nuke_addr
ioctl thread running tcp_done, it leaks 392 bytes and triggers a WARN_ON.
This patch moves the call to sk_error_report inside the bh_lock_sock, which
matches the locking used in tcp_v4_err.
Signed-off-by: Colin Cross <ccross@android.com>
Multiple cpus can process duplicates of incoming ACK messages
matching a SYN_RECV request socket. This is a rare event under
normal operations, but definitely can happen.
Only one must win the race, otherwise corruption would occur.
To fix this without adding new atomic ops, we use logic in
inet_ehash_nolisten() to detect the request was present in the same
ehash bucket where we try to insert the new child.
If request socket was not found, we have to undo the child creation.
This actually removes a spin_lock()/spin_unlock() pair in
reqsk_queue_unlink() for the fast path.
Fixes: e994b2f0fb ("tcp: do not lock listener to process SYN packets")
Fixes: 079096f103 ("tcp/dccp: install syn_recv requests into ehash table")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch implements the second half of RACK that uses the the most
recent transmit time among all delivered packets to detect losses.
tcp_rack_mark_lost() is called upon receiving a dubious ACK.
It then checks if an not-yet-sacked packet was sent at least
"reo_wnd" prior to the sent time of the most recently delivered.
If so the packet is deemed lost.
The "reo_wnd" reordering window starts with 1msec for fast loss
detection and changes to min-RTT/4 when reordering is observed.
We found 1msec accommodates well on tiny degree of reordering
(<3 pkts) on faster links. We use min-RTT instead of SRTT because
reordering is more of a path property but SRTT can be inflated by
self-inflicated congestion. The factor of 4 is borrowed from the
delayed early retransmit and seems to work reasonably well.
Since RACK is still experimental, it is now used as a supplemental
loss detection on top of existing algorithms. It is only effective
after the fast recovery starts or after the timeout occurs. The
fast recovery is still triggered by FACK and/or dupack threshold
instead of RACK.
We introduce a new sysctl net.ipv4.tcp_recovery for future
experiments of loss recoveries. For now RACK can be disabled by
setting it to 0.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch is the first half of the RACK loss recovery.
RACK loss recovery uses the notion of time instead
of packet sequence (FACK) or counts (dupthresh). It's inspired by the
previous FACK heuristic in tcp_mark_lost_retrans(): when a limited
transmit (new data packet) is sacked, then current retransmitted
sequence below the newly sacked sequence must been lost,
since at least one round trip time has elapsed.
But it has several limitations:
1) can't detect tail drops since it depends on limited transmit
2) is disabled upon reordering (assumes no reordering)
3) only enabled in fast recovery ut not timeout recovery
RACK (Recently ACK) addresses these limitations with the notion
of time instead: a packet P1 is lost if a later packet P2 is s/acked,
as at least one round trip has passed.
Since RACK cares about the time sequence instead of the data sequence
of packets, it can detect tail drops when later retransmission is
s/acked while FACK or dupthresh can't. For reordering RACK uses a
dynamically adjusted reordering window ("reo_wnd") to reduce false
positives on ever (small) degree of reordering.
This patch implements tcp_advanced_rack() which tracks the
most recent transmission time among the packets that have been
delivered (ACKed or SACKed) in tp->rack.mstamp. This timestamp
is the key to determine which packet has been lost.
Consider an example that the sender sends six packets:
T1: P1 (lost)
T2: P2
T3: P3
T4: P4
T100: sack of P2. rack.mstamp = T2
T101: retransmit P1
T102: sack of P2,P3,P4. rack.mstamp = T4
T205: ACK of P4 since the hole is repaired. rack.mstamp = T101
We need to be careful about spurious retransmission because it may
falsely advance tp->rack.mstamp by an RTT or an RTO, causing RACK
to falsely mark all packets lost, just like a spurious timeout.
We identify spurious retransmission by the ACK's TS echo value.
If TS option is not applicable but the retransmission is acknowledged
less than min-RTT ago, it is likely to be spurious. We refrain from
using the transmission time of these spurious retransmissions.
The second half is implemented in the next patch that marks packet
lost using RACK timestamp.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Kathleen Nichols' algorithm for tracking the minimum RTT of a
data stream over some measurement window. It uses constant space
and constant time per update. Yet it almost always delivers
the same minimum as an implementation that has to keep all
the data in the window. The measurement window is tunable via
sysctl.net.ipv4.tcp_min_rtt_wlen with a default value of 5 minutes.
The algorithm keeps track of the best, 2nd best & 3rd best min
values, maintaining an invariant that the measurement time of
the n'th best >= n-1'th best. It also makes sure that the three
values are widely separated in the time window since that bounds
the worse case error when that data is monotonically increasing
over the window.
Upon getting a new min, we can forget everything earlier because
it has no value - the new min is less than everything else in the
window by definition and it's the most recent. So we restart fresh
on every new min and overwrites the 2nd & 3rd choices. The same
property holds for the 2nd & 3rd best.
Therefore we have to maintain two invariants to maximize the
information in the samples, one on values (1st.v <= 2nd.v <=
3rd.v) and the other on times (now-win <=1st.t <= 2nd.t <= 3rd.t <=
now). These invariants determine the structure of the code
The RTT input to the windowed filter is the minimum RTT measured
from ACK or SACK, or as the last resort from TCP timestamps.
The accessor tcp_min_rtt() returns the minimum RTT seen in the
window. ~0U indicates it is not available. The minimum is 1usec
even if the true RTT is below that.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
At the time of commit fff3269907 ("tcp: reflect SYN queue_mapping into
SYNACK packets") we had little ways to cope with SYN floods.
We no longer need to reflect incoming skb queue mappings, and instead
can pick a TX queue based on cpu cooking the SYNACK, with normal XPS
affinities.
Note that all SYNACK retransmits were picking TX queue 0, this no longer
is a win given that SYNACK rtx are now distributed on all cpus.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If a listen backlog is very big (to avoid syncookies), then
the listener sk->sk_wmem_alloc is the main source of false
sharing, as we need to touch it twice per SYNACK re-transmit
and TX completion.
(One SYN packet takes listener lock once, but up to 6 SYNACK
are generated)
By attaching the skb to the request socket, we remove this
source of contention.
Tested:
listen(fd, 10485760); // single listener (no SO_REUSEPORT)
16 RX/TX queue NIC
Sustain a SYNFLOOD attack of ~320,000 SYN per second,
Sending ~1,400,000 SYNACK per second.
Perf profiles now show listener spinlock being next bottleneck.
20.29% [kernel] [k] queued_spin_lock_slowpath
10.06% [kernel] [k] __inet_lookup_established
5.12% [kernel] [k] reqsk_timer_handler
3.22% [kernel] [k] get_next_timer_interrupt
3.00% [kernel] [k] tcp_make_synack
2.77% [kernel] [k] ipt_do_table
2.70% [kernel] [k] run_timer_softirq
2.50% [kernel] [k] ip_finish_output
2.04% [kernel] [k] cascade
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In this patch, we insert request sockets into TCP/DCCP
regular ehash table (where ESTABLISHED and TIMEWAIT sockets
are) instead of using the per listener hash table.
ACK packets find SYN_RECV pseudo sockets without having
to find and lock the listener.
In nominal conditions, this halves pressure on listener lock.
Note that this will allow for SO_REUSEPORT refinements,
so that we can select a listener using cpu/numa affinities instead
of the prior 'consistent hash', since only SYN packets will
apply this selection logic.
We will shrink listen_sock in the following patch to ease
code review.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Ying Cai <ycai@google.com>
Cc: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When request sockets are no longer in a per listener hash table
but on regular TCP ehash, we need to access listener uid
through req->rsk_listener
get_openreq6() also gets a const for its request socket argument.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
These functions do not change the listener socket.
Goal is to make sure tcp_conn_request() is not messing with
listener in a racy way.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Some common IPv4/IPv6 code can be factorized.
Also constify cookie_init_sequence() socket argument.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We'll soon no longer hold listener socket lock, these
functions do not modify the socket in any way.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Factorize code to get tcp header from skb. It makes no sense
to duplicate code in callers.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Once we realize tcp_rcv_synsent_state_process() does not use
its 'len' argument and we get rid of it, then it becomes clear
this argument is no longer used in tcp_rcv_state_process()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We found that a TCP Fast Open passive connection was vulnerable
to reorders, as the exchange might look like
[1] C -> S S <FO ...> <request>
[2] S -> C S. ack request <options>
[3] S -> C . <answer>
packets [2] and [3] can be generated at almost the same time.
If C receives the 3rd packet before the 2nd, it will drop it as
the socket is in SYN_SENT state and expects a SYNACK.
S will have to retransmit the answer.
Current OOO avoidance in linux is defeated because SYNACK
packets are attached to the LISTEN socket, while DATA packets
are attached to the children. They might be sent by different cpus,
and different TX queues might be selected.
It turns out that for TFO, we created a child, which is a
full blown socket in TCP_SYN_RECV state, and we simply can attach
the SYNACK packet to this socket.
This means that at the time tcp_sendmsg() pushes DATA packet,
skb->ooo_okay will be set iff the SYNACK packet had been sent
and TX completed.
This removes the reorder source at the host level.
We also removed the export of tcp_try_fastopen(), as it is no
longer called from IPv6.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is done to make sure we do not change listener socket
while sending SYNACK packets while socket lock is not held.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This documents fact that listener lock might not be held
at the time SYNACK are sent.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
listener socket is not locked when tcp_make_synack() is called.
We better make sure no field is written.
There is one exception : Since SYNACK packets are attached to the listener
at this moment (or SYN_RECV child in case of Fast Open),
sock_wmalloc() needs to update sk->sk_wmem_alloc, but this is done using
atomic operations so this is safe.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
When TCP new listener is done, these functions will be called
without socket lock being held. Make sure they don't change
anything.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Soon, listener socket wont be locked when tcp_openreq_init_rwin()
is called. We need to read socket fields once, as their value
could change under us.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Soon, listener socket spinlock will no longer be held,
add const arguments to tcp_v[46]_init_req() to make clear these
functions can not mess socket fields.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently SYN/ACK RTT is measured in jiffies. For LAN the SYN/ACK
RTT is often measured as 0ms or sometimes 1ms, which would affect
RTT estimation and min RTT samping used by some congestion control.
This patch improves SYN/ACK RTT to be usec resolution if platform
supports it. While the timestamping of SYN/ACK is done in request
sock, the RTT measurement is carefully arranged to avoid storing
another u64 timestamp in tcp_sock.
For regular handshake w/o SYNACK retransmission, the RTT is sampled
right after the child socket is created and right before the request
sock is released (tcp_check_req() in tcp_minisocks.c)
For Fast Open the child socket is already created when SYN/ACK was
sent, the RTT is sampled in tcp_rcv_state_process() after processing
the final ACK an right before the request socket is released.
If the SYN/ACK was retransmistted or SYN-cookie was used, we rely
on TCP timestamps to measure the RTT. The sample is taken at the
same place in tcp_rcv_state_process() after the timestamp values
are validated in tcp_validate_incoming(). Note that we do not store
TS echo value in request_sock for SYN-cookies, because the value
is already stored in tp->rx_opt used by tcp_ack_update_rtt().
One side benefit is that the RTT measurement now happens before
initializing congestion control (of the passive side). Therefore
the congestion control can use the SYN/ACK RTT.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Currently, the following case doesn't use DCTCP, even if it should:
A responder has f.e. Cubic as system wide default, but for a specific
route to the initiating host, DCTCP is being set in RTAX_CC_ALGO. The
initiating host then uses DCTCP as congestion control, but since the
initiator sets ECT(0), tcp_ecn_create_request() doesn't set ecn_ok,
and we have to fall back to Reno after 3WHS completes.
We were thinking on how to solve this in a minimal, non-intrusive
way without bloating tcp_ecn_create_request() needlessly: lets cache
the CA ecn option flag in RTAX_FEATURES. In other words, when ECT(0)
is set on the SYN packet, set ecn_ok=1 iff route RTAX_FEATURES
contains the unexposed (internal-only) DST_FEATURE_ECN_CA. This allows
to only do a single metric feature lookup inside tcp_ecn_create_request().
Joint work with Florian Westphal.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
When TCP pacing was added back in linux-3.12, we chose
to apply a fixed ratio of 200 % against current rate,
to allow probing for optimal throughput even during
slow start phase, where cwnd can be doubled every other gRTT.
At Google, we found it was better applying a different ratio
while in Congestion Avoidance phase.
This ratio was set to 120 %.
We've used the normal tcp_in_slow_start() helper for a while,
then tuned the condition to select the conservative ratio
as soon as cwnd >= ssthresh/2 :
- After cwnd reduction, it is safer to ramp up more slowly,
as we approach optimal cwnd.
- Initial ramp up (ssthresh == INFINITY) still allows doubling
cwnd every other RTT.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
slow start after idle might reduce cwnd, but we perform this
after first packet was cooked and sent.
With TSO/GSO, it means that we might send a full TSO packet
even if cwnd should have been reduced to IW10.
Moving the SSAI check in skb_entail() makes sense, because
we slightly reduce number of times this check is done,
especially for large send() and TCP Small queue callbacks from
softirq context.
As Neal pointed out, we also need to perform the check
if/when receive window opens.
Tested:
Following packetdrill test demonstrates the problem
// Test of slow start after idle
`sysctl -q net.ipv4.tcp_slow_start_after_idle=1`
0.000 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
+0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
+0 bind(3, ..., ...) = 0
+0 listen(3, 1) = 0
+0 < S 0:0(0) win 65535 <mss 1000,sackOK,nop,nop,nop,wscale 7>
+0 > S. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 6>
+.100 < . 1:1(0) ack 1 win 511
+0 accept(3, ..., ...) = 4
+0 setsockopt(4, SOL_SOCKET, SO_SNDBUF, [200000], 4) = 0
+0 write(4, ..., 26000) = 26000
+0 > . 1:5001(5000) ack 1
+0 > . 5001:10001(5000) ack 1
+0 %{ assert tcpi_snd_cwnd == 10 }%
+.100 < . 1:1(0) ack 10001 win 511
+0 %{ assert tcpi_snd_cwnd == 20, tcpi_snd_cwnd }%
+0 > . 10001:20001(10000) ack 1
+0 > P. 20001:26001(6000) ack 1
+.100 < . 1:1(0) ack 26001 win 511
+0 %{ assert tcpi_snd_cwnd == 36, tcpi_snd_cwnd }%
+4 write(4, ..., 20000) = 20000
// If slow start after idle works properly, we should send 5 MSS here (cwnd/2)
+0 > . 26001:31001(5000) ack 1
+0 %{ assert tcpi_snd_cwnd == 10, tcpi_snd_cwnd }%
+0 > . 31001:36001(5000) ack 1
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In the original design slow start is only used to raise cwnd
when cwnd is stricly below ssthresh. It makes little sense
to slow start when cwnd == ssthresh: especially
when hystart has set ssthresh in the initial ramp, or after
recovery when cwnd resets to ssthresh. Not doing so will
also help reduce the buffer bloat slightly.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Add a helper to test the slow start condition in various congestion
control modules and other places. This is to prepare a slight improvement
in policy as to exactly when to slow start.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In commit cd7d8498c9 ("tcp: change tcp_skb_pcount() location") we stored
gso_segs in a temporary cache hot location.
This patch does the same for gso_size.
This allows to save 2 cache line misses in tcp xmit path for
the last packet that is considered but not sent because of
various conditions (cwnd, tso defer, receiver window, TSQ...)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
IPv4 and IPv6 share same implementation of get_cookie_sock(),
and there is no point inlining it.
We add tcp_ prefix to the common helper name and export it.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This work as a follow-up of commit f7b3bec6f5 ("net: allow setting ecn
via routing table") and adds RFC3168 section 6.1.1.1. fallback for outgoing
ECN connections. In other words, this work adds a retry with a non-ECN
setup SYN packet, as suggested from the RFC on the first timeout:
[...] A host that receives no reply to an ECN-setup SYN within the
normal SYN retransmission timeout interval MAY resend the SYN and
any subsequent SYN retransmissions with CWR and ECE cleared. [...]
Schematic client-side view when assuming the server is in tcp_ecn=2 mode,
that is, Linux default since 2009 via commit 255cac91c3 ("tcp: extend
ECN sysctl to allow server-side only ECN"):
1) Normal ECN-capable path:
SYN ECE CWR ----->
<----- SYN ACK ECE
ACK ----->
2) Path with broken middlebox, when client has fallback:
SYN ECE CWR ----X crappy middlebox drops packet
(timeout, rtx)
SYN ----->
<----- SYN ACK
ACK ----->
In case we would not have the fallback implemented, the middlebox drop
point would basically end up as:
SYN ECE CWR ----X crappy middlebox drops packet
(timeout, rtx)
SYN ECE CWR ----X crappy middlebox drops packet
(timeout, rtx)
SYN ECE CWR ----X crappy middlebox drops packet
(timeout, rtx)
In any case, it's rather a smaller percentage of sites where there would
occur such additional setup latency: it was found in end of 2014 that ~56%
of IPv4 and 65% of IPv6 servers of Alexa 1 million list would negotiate
ECN (aka tcp_ecn=2 default), 0.42% of these webservers will fail to connect
when trying to negotiate with ECN (tcp_ecn=1) due to timeouts, which the
fallback would mitigate with a slight latency trade-off. Recent related
paper on this topic:
Brian Trammell, Mirja Kühlewind, Damiano Boppart, Iain Learmonth,
Gorry Fairhurst, and Richard Scheffenegger:
"Enabling Internet-Wide Deployment of Explicit Congestion Notification."
Proc. PAM 2015, New York.
http://ecn.ethz.ch/ecn-pam15.pdf
Thus, when net.ipv4.tcp_ecn=1 is being set, the patch will perform RFC3168,
section 6.1.1.1. fallback on timeout. For users explicitly not wanting this
which can be in DC use case, we add a net.ipv4.tcp_ecn_fallback knob that
allows for disabling the fallback.
tp->ecn_flags are not being cleared in tcp_ecn_clear_syn() on output, but
rather we let tcp_ecn_rcv_synack() take that over on input path in case a
SYN ACK ECE was delayed. Thus a spurious SYN retransmission will not prevent
ECN being negotiated eventually in that case.
Reference: https://www.ietf.org/proceedings/92/slides/slides-92-iccrg-1.pdf
Reference: https://www.ietf.org/proceedings/89/slides/slides-89-tsvarea-1.pdf
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Mirja Kühlewind <mirja.kuehlewind@tik.ee.ethz.ch>
Signed-off-by: Brian Trammell <trammell@tik.ee.ethz.ch>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Dave That <dave.taht@gmail.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduce an optimized version of sk_under_memory_pressure()
for TCP. Our intent is to use it in fast paths.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We plan to use sk_forced_wmem_schedule() in input path as well,
so make it non static and rename it.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Now we allow storing more request socks per listener, we might
hit syncookie mode less often and hit following bug in our stack :
When we send a burst of syncookies, then exit this mode,
tcp_synq_no_recent_overflow() can return false if the ACK packets coming
from clients are coming three seconds after the end of syncookie
episode.
This is a way too strong requirement and conflicts with rest of
syncookie code which allows ACK to be aged up to 2 minutes.
Perfectly valid ACK packets are dropped just because clients might be
in a crowded wifi environment or on another planet.
So let's fix this, and also change tcp_synq_overflow() to not
dirty a cache line for every syncookie we send, as we are under attack.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Florian Westphal <fw@strlen.de>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diagnosing problems related to Window Probes has been hard because
we lack a counter.
TCPWinProbe counts the number of ACK packets a sender has to send
at regular intervals to make sure a reverse ACK packet opening back
a window had not been lost.
TCPKeepAlive counts the number of ACK packets sent to keep TCP
flows alive (SO_KEEPALIVE)
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Nandita Dukkipati <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With the advent of small rto timers in datacenter TCP,
(ip route ... rto_min x), the following can happen :
1) Qdisc is full, transmit fails.
TCP sets a timer based on icsk_rto to retry the transmit, without
exponential backoff.
With low icsk_rto, and lot of sockets, all cpus are servicing timer
interrupts like crazy.
Intent of the code was to retry with a timer between 200 (TCP_RTO_MIN)
and 500ms (TCP_RESOURCE_PROBE_INTERVAL)
2) Receivers can send zero windows if they don't drain their receive queue.
TCP sends zero window probes, based on icsk_rto current value, with
exponential backoff.
With /proc/sys/net/ipv4/tcp_retries2 being 15 (or even smaller in
some cases), sender can abort in less than one or two minutes !
If receiver stops the sender, it obviously doesn't care of very tight
rto. Probability of dropping the ACK reopening the window is not
worth the risk.
Lets change the base timer to be at least 200ms (TCP_RTO_MIN) for these
events (but not normal RTO based retransmits)
A followup patch adds a new SNMP counter, as it would have helped a lot
diagnosing this issue.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We would like that optional info provided by Congestion Control
modules using netlink can also be read using getsockopt()
This patch changes get_info() to put this information in a buffer,
instead of skb, like tcp_get_info(), so that following patch
can reuse this common infrastructure.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch tracks total number of bytes acked for a TCP socket.
This is the sum of all changes done to tp->snd_una, and allows
for precise tracking of delivered data.
RFC4898 named this : tcpEStatsAppHCThruOctetsAcked
This is a 64bit field, and can be fetched both from TCP_INFO
getsockopt() if one has a handle on a TCP socket, or from inet_diag
netlink facility (iproute2/ss patch will follow)
Note that tp->bytes_acked was placed near tp->snd_una for
best data locality and minimal performance impact.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Cc: Matt Mathis <mattmathis@google.com>
Cc: Eric Salo <salo@google.com>
Cc: Martin Lau <kafai@fb.com>
Cc: Chris Rapier <rapier@psc.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>
Two different problems are fixed here :
1) inet_sk_diag_fill() might be called without socket lock held.
icsk->icsk_ca_ops can change under us and module be unloaded.
-> Access to freed memory.
Fix this using rcu_read_lock() to prevent module unload.
2) Some TCP Congestion Control modules provide information
but again this is not safe against icsk->icsk_ca_ops
change and nla_put() errors were ignored. Some sockets
could not get the additional info if skb was almost full.
Fix this by returning a status from get_info() handlers and
using rcu protection as well.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fast Open has been using an experimental option with a magic number
(RFC6994). This patch makes the client by default use the RFC7413
option (34) to get and send Fast Open cookies. This patch makes
the client solicit cookies from a given server first with the
RFC7413 option. If that fails to elicit a cookie, then it tries
the RFC6994 experimental option. If that also fails, it uses the
RFC7413 option on all subsequent connect attempts. If the server
returns a Fast Open cookie then the client caches the form of the
option that successfully elicited a cookie, and uses that form on
later connects when it presents that cookie.
The idea is to gradually obsolete the use of experimental options as
the servers and clients upgrade, while keeping the interoperability
meanwhile.
Signed-off-by: Daniel Lee <Longinus00@gmail.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Fast Open has been using the experimental option with a magic number
(RFC6994) to request and grant Fast Open cookies. This patch enables
the server to support the official IANA option 34 in RFC7413 in
addition.
The change has passed all existing Fast Open tests with both
old and new options at Google.
Signed-off-by: Daniel Lee <Longinus00@gmail.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After commit 1fb6f159fd ("tcp: add tcp_conn_request"),
tcp_syn_flood_action() is no longer used from IPv6.
We can make it static, by moving it above tcp_conn_request()
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Octavian Purdila <octavian.purdila@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
With request socks convergence, we no longer need
different lookup methods. A request socket can
use generic lookup function.
Add const qualifier to 2nd tcp_v[46]_md5_lookup() parameter.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Since request and established sockets now have same base,
there is no need to pass two pointers to tcp_v4_md5_hash_skb()
or tcp_v6_md5_hash_skb()
Also add a const qualifier to their struct tcp_md5sig_key argument.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
tcp_v4_err() can restrict lookups to ehash table, and not to listeners.
Note this patch creates the infrastructure, but this means that ICMP
messages for request sockets are ignored until complete conversion.
New tcp_req_err() helper is exported so that we can use it in IPv6
in following patch.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
It is not needed, and req->sk_listener points to the listener anyway.
request_sock argument can be const.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
