mirror of
https://github.com/team-infusion-developers/android_kernel_samsung_msm8976.git
synced 2024-09-21 20:04:01 +00:00
8b08aa9e75
-----BEGIN PGP SIGNATURE----- Version: GnuPG v2 iQIcBAABCAAGBQJUyuGRAAoJEDjbvchgkmk+7EwQALYPOeh+AManQFB1MQvFuOgZ /4ulpjhGXw/RPTKHMeyHo8vRfUhMOx8UPF62uql+g1l9b/Zt2bs6qXu4QcxRRsQc trSTUpi+U14y1hkgqOVOcFYP2ZaTjNEBQgLJ4eGn46CliLqme+rfoyRYm2GXzcR4 6cbSAr3mufdFIpi9/8Dn62Gv0aws5lIv3qkHJXznyuux3tisPT5y6Ux2KJoivPn/ SqADtRpwo+7lTjl15fE++9AqNsGMorV6toT2OO/7nXP+824psInKLmREAT2qC99b BG61vcYdxOuHtzmwrvCf1jSRjxhvZT0j2xhBr/vCKcxy08AT0vDv68zrV1r6TIuu U7/CKXtFBY95cjfnkTLJuswBSuIA/+sQHV6DaddH0V8fcZ6rQMLrblQ9ZcFFFkmT 2SG6lmlXqZvcEKYGMnL/Dcow1rkRhB5stiGgTkYxjiRSRpzAHISRJ/GGpsT+rRqK HpBs5p9JshvRl7RWKwAu+DNGaEK1X/WYxc4/jw6dZFWX7lEWSMIPlr9zXgZCZ39y V6lV1VVlT9/CSs1swKHUyhHHehlFsnIlQ6Fkiycr/KkuqBLs92Hyb7WhpVa819yX osXdxSm6J54skiOLKYpBWHpnY09Tc+p28VEfMpErTExgp2oE8F34K7kdhoQPQb97 2mHiXNa+J4CLUNQ+sRmw =HDBo -----END PGP SIGNATURE----- Merge commit 'v3.10.67' into msm-3.10 This merge brings us up to date with upstream kernel.org tag v3.10.67. It also contains changes to allow forbidden warnings introduced in the commit 'core, nfqueue, openvswitch: Orphan frags in skb_zerocopy and handle errors'. Once upstream has corrected these warnings, the changes to scripts/gcc-wrapper.py, in this commit, can be reverted. * commit 'v3.10.67' (915 commits) Linux 3.10.67 md/raid5: fetch_block must fetch all the blocks handle_stripe_dirtying wants. ext4: fix warning in ext4_da_update_reserve_space() quota: provide interface for readding allocated space into reserved space crypto: add missing crypto module aliases crypto: include crypto- module prefix in template crypto: prefix module autoloading with "crypto-" drbd: merge_bvec_fn: properly remap bvm->bi_bdev Revert "swiotlb-xen: pass dev_addr to swiotlb_tbl_unmap_single" ipvs: uninitialized data with IP_VS_IPV6 KEYS: close race between key lookup and freeing sata_dwc_460ex: fix resource leak on error path x86/asm/traps: Disable tracing and kprobes in fixup_bad_iret and sync_regs x86, tls: Interpret an all-zero struct user_desc as "no segment" x86, tls, ldt: Stop checking lm in LDT_empty x86/tsc: Change Fast TSC calibration failed from error to info x86, hyperv: Mark the Hyper-V clocksource as being continuous clocksource: exynos_mct: Fix bitmask regression for exynos4_mct_write can: dev: fix crtlmode_supported check bus: mvebu-mbus: fix support of MBus window 13 ARM: dts: imx25: Fix PWM "per" clocks time: adjtimex: Validate the ADJ_FREQUENCY values time: settimeofday: Validate the values of tv from user dm cache: share cache-metadata object across inactive and active DM tables ipr: wait for aborted command responses drm/i915: Fix mutex->owner inspection race under DEBUG_MUTEXES scripts/recordmcount.pl: There is no -m32 gcc option on Super-H anymore ALSA: usb-audio: Add mic volume fix quirk for Logitech Webcam C210 libata: prevent HSM state change race between ISR and PIO pinctrl: Fix two deadlocks gpio: sysfs: fix gpio device-attribute leak gpio: sysfs: fix gpio-chip device-attribute leak Linux 3.10.66 s390/3215: fix tty output containing tabs s390/3215: fix hanging console issue fsnotify: next_i is freed during fsnotify_unmount_inodes. netfilter: ipset: small potential read beyond the end of buffer mmc: sdhci: Fix sleep in atomic after inserting SD card LOCKD: Fix a race when initialising nlmsvc_timeout x86, um: actually mark system call tables readonly um: Skip futex_atomic_cmpxchg_inatomic() test decompress_bunzip2: off by one in get_next_block() ARM: shmobile: sh73a0 legacy: Set .control_parent for all irqpin instances ARM: omap5/dra7xx: Fix frequency typos ARM: clk-imx6q: fix video divider for rev T0 1.0 ARM: imx6q: drop unnecessary semicolon ARM: dts: imx25: Fix the SPI1 clocks Input: I8042 - add Acer Aspire 7738 to the nomux list Input: i8042 - reset keyboard to fix Elantech touchpad detection can: kvaser_usb: Don't send a RESET_CHIP for non-existing channels can: kvaser_usb: Reset all URB tx contexts upon channel close can: kvaser_usb: Don't free packets when tight on URBs USB: keyspan: fix null-deref at probe USB: cp210x: add IDs for CEL USB sticks and MeshWorks devices USB: cp210x: fix ID for production CEL MeshConnect USB Stick usb: dwc3: gadget: Stop TRB preparation after limit is reached usb: dwc3: gadget: Fix TRB preparation during SG OHCI: add a quirk for ULi M5237 blocking on reset gpiolib: of: Correct error handling in of_get_named_gpiod_flags NFSv4.1: Fix client id trunking on Linux ftrace/jprobes/x86: Fix conflict between jprobes and function graph tracing vfio-pci: Fix the check on pci device type in vfio_pci_probe() uvcvideo: Fix destruction order in uvc_delete() smiapp: Take mutex during PLL update in sensor initialisation af9005: fix kernel panic on init if compiled without IR smiapp-pll: Correct clock debug prints video/logo: prevent use of logos after they have been freed storvsc: ring buffer failures may result in I/O freeze iscsi-target: Fail connection on short sendmsg writes hp_accel: Add support for HP ZBook 15 cfg80211: Fix 160 MHz channels with 80+80 and 160 MHz drivers ARC: [nsimosci] move peripherals to match model to FPGA drm/i915: Force the CS stall for invalidate flushes drm/i915: Invalidate media caches on gen7 drm/radeon: properly filter DP1.2 4k modes on non-DP1.2 hw drm/radeon: check the right ring in radeon_evict_flags() drm/vmwgfx: Fix fence event code enic: fix rx skb checksum alx: fix alx_poll() tcp: Do not apply TSO segment limit to non-TSO packets tg3: tg3_disable_ints using uninitialized mailbox value to disable interrupts netlink: Don't reorder loads/stores before marking mmap netlink frame as available netlink: Always copy on mmap TX. Linux 3.10.65 mm: Don't count the stack guard page towards RLIMIT_STACK mm: propagate error from stack expansion even for guard page mm, vmscan: prevent kswapd livelock due to pfmemalloc-throttled process being killed perf session: Do not fail on processing out of order event perf: Fix events installation during moving group perf/x86/intel/uncore: Make sure only uncore events are collected Btrfs: don't delay inode ref updates during log replay ARM: mvebu: disable I/O coherency on non-SMP situations on Armada 370/375/38x/XP scripts/kernel-doc: don't eat struct members with __aligned nilfs2: fix the nilfs_iget() vs. nilfs_new_inode() races nfsd4: fix xdr4 inclusion of escaped char fs: nfsd: Fix signedness bug in compare_blob serial: samsung: wait for transfer completion before clock disable writeback: fix a subtle race condition in I_DIRTY clearing cdc-acm: memory leak in error case genhd: check for int overflow in disk_expand_part_tbl() USB: cdc-acm: check for valid interfaces ALSA: hda - Fix wrong gpio_dir & gpio_mask hint setups for IDT/STAC codecs ALSA: hda - using uninitialized data ALSA: usb-audio: extend KEF X300A FU 10 tweak to Arcam rPAC driver core: Fix unbalanced device reference in drivers_probe x86, vdso: Use asm volatile in __getcpu x86_64, vdso: Fix the vdso address randomization algorithm HID: Add a new id 0x501a for Genius MousePen i608X HID: add battery quirk for USB_DEVICE_ID_APPLE_ALU_WIRELESS_2011_ISO keyboard HID: roccat: potential out of bounds in pyra_sysfs_write_settings() HID: i2c-hid: prevent buffer overflow in early IRQ HID: i2c-hid: fix race condition reading reports iommu/vt-d: Fix an off-by-one bug in __domain_mapping() UBI: Fix double free after do_sync_erase() UBI: Fix invalid vfree() pstore-ram: Allow optional mapping with pgprot_noncached pstore-ram: Fix hangs by using write-combine mappings PCI: Restore detection of read-only BARs ASoC: dwc: Ensure FIFOs are flushed to prevent channel swap ASoC: max98090: Fix ill-defined sidetone route ASoC: sigmadsp: Refuse to load firmware files with a non-supported version ath5k: fix hardware queue index assignment swiotlb-xen: pass dev_addr to swiotlb_tbl_unmap_single can: peak_usb: fix memset() usage can: peak_usb: fix cleanup sequence order in case of error during init ath9k: fix BE/BK queue order ath9k_hw: fix hardware queue allocation ocfs2: fix journal commit deadlock Linux 3.10.64 Btrfs: fix fs corruption on transaction abort if device supports discard Btrfs: do not move em to modified list when unpinning eCryptfs: Remove buggy and unnecessary write in file name decode routine eCryptfs: Force RO mount when encrypted view is enabled udf: Verify symlink size before loading it exit: pidns: alloc_pid() leaks pid_namespace if child_reaper is exiting ncpfs: return proper error from NCP_IOC_SETROOT ioctl crypto: af_alg - fix backlog handling userns: Unbreak the unprivileged remount tests userns: Allow setting gid_maps without privilege when setgroups is disabled userns: Add a knob to disable setgroups on a per user namespace basis userns: Rename id_map_mutex to userns_state_mutex userns: Only allow the creator of the userns unprivileged mappings userns: Check euid no fsuid when establishing an unprivileged uid mapping userns: Don't allow unprivileged creation of gid mappings userns: Don't allow setgroups until a gid mapping has been setablished userns: Document what the invariant required for safe unprivileged mappings. groups: Consolidate the setgroups permission checks umount: Disallow unprivileged mount force mnt: Update unprivileged remount test mnt: Implicitly add MNT_NODEV on remount when it was implicitly added by mount mac80211: free management frame keys when removing station mac80211: fix multicast LED blinking and counter KEYS: Fix stale key registration at error path isofs: Fix unchecked printing of ER records x86/tls: Don't validate lm in set_thread_area() after all dm space map metadata: fix sm_bootstrap_get_nr_blocks() dm bufio: fix memleak when using a dm_buffer's inline bio nfs41: fix nfs4_proc_layoutget error handling megaraid_sas: corrected return of wait_event from abort frame path mmc: block: add newline to sysfs display of force_ro mfd: tc6393xb: Fail ohci suspend if full state restore is required md/bitmap: always wait for writes on unplug. x86, kvm: Clear paravirt_enabled on KVM guests for espfix32's benefit x86_64, switch_to(): Load TLS descriptors before switching DS and ES x86/tls: Disallow unusual TLS segments x86/tls: Validate TLS entries to protect espfix isofs: Fix infinite looping over CE entries Linux 3.10.63 ALSA: usb-audio: Don't resubmit pending URBs at MIDI error recovery powerpc: 32 bit getcpu VDSO function uses 64 bit instructions ARM: sched_clock: Load cycle count after epoch stabilizes igb: bring link up when PHY is powered up ext2: Fix oops in ext2_get_block() called from ext2_quota_write() nEPT: Nested INVEPT net: sctp: use MAX_HEADER for headroom reserve in output path net: mvneta: fix Tx interrupt delay rtnetlink: release net refcnt on error in do_setlink() net/mlx4_core: Limit count field to 24 bits in qp_alloc_res tg3: fix ring init when there are more TX than RX channels ipv6: gre: fix wrong skb->protocol in WCCP sata_fsl: fix error handling of irq_of_parse_and_map ahci: disable MSI on SAMSUNG 0xa800 SSD AHCI: Add DeviceIDs for Sunrise Point-LP SATA controller media: smiapp: Only some selection targets are settable drm/i915: Unlock panel even when LVDS is disabled drm/radeon: kernel panic in drm_calc_vbltimestamp_from_scanoutpos with 3.18.0-rc6 i2c: davinci: generate STP always when NACK is received i2c: omap: fix i207 errata handling i2c: omap: fix NACK and Arbitration Lost irq handling xen-netfront: Remove BUGs on paged skb data which crosses a page boundary mm: fix swapoff hang after page migration and fork mm: frontswap: invalidate expired data on a dup-store failure Linux 3.10.62 nfsd: Fix ACL null pointer deref powerpc/powernv: Honor the generic "no_64bit_msi" flag bnx2fc: do not add shared skbs to the fcoe_rx_list nfsd4: fix leak of inode reference on delegation failure nfsd: Fix slot wake up race in the nfsv4.1 callback code rt2x00: do not align payload on modern H/W can: dev: avoid calling kfree_skb() from interrupt context spi: dw: Fix dynamic speed change. iser-target: Handle DEVICE_REMOVAL event on network portal listener correctly target: Don't call TFO->write_pending if data_length == 0 srp-target: Retry when QP creation fails with ENOMEM Input: xpad - use proper endpoint type ARM: 8222/1: mvebu: enable strex backoff delay ARM: 8216/1: xscale: correct auxiliary register in suspend/resume ALSA: usb-audio: Add ctrl message delay quirk for Marantz/Denon devices can: esd_usb2: fix memory leak on disconnect USB: xhci: don't start a halted endpoint before its new dequeue is set usb-quirks: Add reset-resume quirk for MS Wireless Laser Mouse 6000 usb: serial: ftdi_sio: add PIDs for Matrix Orbital products USB: serial: cp210x: add IDs for CEL MeshConnect USB Stick USB: keyspan: fix tty line-status reporting USB: keyspan: fix overrun-error reporting USB: ssu100: fix overrun-error reporting iio: Fix IIO_EVENT_CODE_EXTRACT_DIR bit mask powerpc/pseries: Fix endiannes issue in RTAS call from xmon powerpc/pseries: Honor the generic "no_64bit_msi" flag of/base: Fix PowerPC address parsing hack ASoC: wm_adsp: Avoid attempt to free buffers that might still be in use ASoC: sgtl5000: Fix SMALL_POP bit definition PCI/MSI: Add device flag indicating that 64-bit MSIs don't work ipx: fix locking regression in ipx_sendmsg and ipx_recvmsg pptp: fix stack info leak in pptp_getname() qmi_wwan: Add support for HP lt4112 LTE/HSPA+ Gobi 4G Modem ieee802154: fix error handling in ieee802154fake_probe() ipv4: Fix incorrect error code when adding an unreachable route inetdevice: fixed signed integer overflow sparc64: Fix constraints on swab helpers. uprobes, x86: Fix _TIF_UPROBE vs _TIF_NOTIFY_RESUME x86, mm: Set NX across entire PMD at boot x86: Require exact match for 'noxsave' command line option x86_64, traps: Rework bad_iret x86_64, traps: Stop using IST for #SS x86_64, traps: Fix the espfix64 #DF fixup and rewrite it in C MIPS: Loongson: Make platform serial setup always built-in. MIPS: oprofile: Fix backtrace on 64-bit kernel Linux 3.10.61 mm: memcg: handle non-error OOM situations more gracefully mm: memcg: do not trap chargers with full callstack on OOM mm: memcg: rework and document OOM waiting and wakeup mm: memcg: enable memcg OOM killer only for user faults x86: finish user fault error path with fatal signal arch: mm: pass userspace fault flag to generic fault handler arch: mm: do not invoke OOM killer on kernel fault OOM arch: mm: remove obsolete init OOM protection mm: invoke oom-killer from remaining unconverted page fault handlers net: sctp: fix skb_over_panic when receiving malformed ASCONF chunks net: sctp: fix panic on duplicate ASCONF chunks net: sctp: fix remote memory pressure from excessive queueing KVM: x86: Don't report guest userspace emulation error to userspace SCSI: hpsa: fix a race in cmd_free/scsi_done net/mlx4_en: Fix BlueFlame race ARM: Correct BUG() assembly to ensure it is endian-agnostic perf/x86/intel: Use proper dTLB-load-misses event on IvyBridge mei: bus: fix possible boundaries violation perf: Handle compat ioctl MIPS: Fix forgotten preempt_enable() when CPU has inclusive pcaches dell-wmi: Fix access out of memory ARM: probes: fix instruction fetch order with <asm/opcodes.h> br: fix use of ->rx_handler_data in code executed on non-rx_handler path netfilter: nf_nat: fix oops on netns removal netfilter: xt_bpf: add mising opaque struct sk_filter definition netfilter: nf_log: release skbuff on nlmsg put failure netfilter: nfnetlink_log: fix maximum packet length logged to userspace netfilter: nf_log: account for size of NLMSG_DONE attribute ipc: always handle a new value of auto_msgmni clocksource: Remove "weak" from clocksource_default_clock() declaration kgdb: Remove "weak" from kgdb_arch_pc() declaration media: ttusb-dec: buffer overflow in ioctl NFSv4: Fix races between nfs_remove_bad_delegation() and delegation return nfs: Fix use of uninitialized variable in nfs_getattr() NFS: Don't try to reclaim delegation open state if recovery failed NFSv4: Ensure that we remove NFSv4.0 delegations when state has expired Input: alps - allow up to 2 invalid packets without resetting device Input: alps - ignore potential bare packets when device is out of sync dm raid: ensure superblock's size matches device's logical block size dm btree: fix a recursion depth bug in btree walking code block: Fix computation of merged request priority parisc: Use compat layer for msgctl, shmat, shmctl and semtimedop syscalls scsi: only re-lock door after EH on devices that were reset nfs: fix pnfs direct write memory leak firewire: cdev: prevent kernel stack leaking into ioctl arguments arm64: __clear_user: handle exceptions on strb ARM: 8198/1: make kuser helpers depend on MMU drm/radeon: add missing crtc unlock when setting up the MC mac80211: fix use-after-free in defragmentation macvtap: Fix csum_start when VLAN tags are present iwlwifi: configure the LTR libceph: do not crash on large auth tickets xtensa: re-wire umount syscall to sys_oldumount ALSA: usb-audio: Fix memory leak in FTU quirk ahci: disable MSI instead of NCQ on Samsung pci-e SSDs on macbooks ahci: Add Device IDs for Intel Sunrise Point PCH audit: keep inode pinned x86, x32, audit: Fix x32's AUDIT_ARCH wrt audit sparc32: Implement xchg and atomic_xchg using ATOMIC_HASH locks sparc64: Do irq_{enter,exit}() around generic_smp_call_function*(). sparc64: Fix crashes in schizo_pcierr_intr_other(). sunvdc: don't call VD_OP_GET_VTOC vio: fix reuse of vio_dring slot sunvdc: limit each sg segment to a page sunvdc: compute vdisk geometry from capacity sunvdc: add cdrom and v1.1 protocol support net: sctp: fix memory leak in auth key management net: sctp: fix NULL pointer dereference in af->from_addr_param on malformed packet gre6: Move the setting of dev->iflink into the ndo_init functions. ip6_tunnel: Use ip6_tnl_dev_init as the ndo_init function. Linux 3.10.60 libceph: ceph-msgr workqueue needs a resque worker Btrfs: fix kfree on list_head in btrfs_lookup_csums_range error cleanup of: Fix overflow bug in string property parsing functions sysfs: driver core: Fix glue dir race condition by gdp_mutex i2c: at91: don't account as iowait acer-wmi: Add acpi_backlight=video quirk for the Acer KAV80 rbd: Fix error recovery in rbd_obj_read_sync() drm/radeon: remove invalid pci id usb: gadget: udc: core: fix kernel oops with soft-connect usb: gadget: function: acm: make f_acm pass USB20CV Chapter9 usb: dwc3: gadget: fix set_halt() bug with pending transfers crypto: algif - avoid excessive use of socket buffer in skcipher mm: Remove false WARN_ON from pagecache_isize_extended() x86, apic: Handle a bad TSC more gracefully posix-timers: Fix stack info leak in timer_create() mac80211: fix typo in starting baserate for rts_cts_rate_idx PM / Sleep: fix recovery during resuming from hibernation tty: Fix high cpu load if tty is unreleaseable quota: Properly return errors from dquot_writeback_dquots() ext3: Don't check quota format when there are no quota files nfsd4: fix crash on unknown operation number cpc925_edac: Report UE events properly e7xxx_edac: Report CE events properly i3200_edac: Report CE events properly i82860_edac: Report CE events properly scsi: Fix error handling in SCSI_IOCTL_SEND_COMMAND lib/bitmap.c: fix undefined shift in __bitmap_shift_{left|right}() cgroup/kmemleak: add kmemleak_free() for cgroup deallocations. usb: Do not allow usb_alloc_streams on unconfigured devices USB: opticon: fix non-atomic allocation in write path usb-storage: handle a skipped data phase spi: pxa2xx: toggle clocks on suspend if not disabled by runtime PM spi: pl022: Fix incorrect dma_unmap_sg usb: dwc3: gadget: Properly initialize LINK TRB wireless: rt2x00: add new rt2800usb device USB: option: add Haier CE81B CDMA modem usb: option: add support for Telit LE910 USB: cdc-acm: only raise DTR on transitions from B0 USB: cdc-acm: add device id for GW Instek AFG-2225 usb: serial: ftdi_sio: add "bricked" FTDI device PID usb: serial: ftdi_sio: add Awinda Station and Dongle products USB: serial: cp210x: add Silicon Labs 358x VID and PID serial: Fix divide-by-zero fault in uart_get_divisor() staging:iio:ade7758: Remove "raw" from channel name staging:iio:ade7758: Fix check if channels are enabled in prenable staging:iio:ade7758: Fix NULL pointer deref when enabling buffer staging:iio:ad5933: Drop "raw" from channel names staging:iio:ad5933: Fix NULL pointer deref when enabling buffer OOM, PM: OOM killed task shouldn't escape PM suspend freezer: Do not freeze tasks killed by OOM killer ext4: fix oops when loading block bitmap failed cpufreq: intel_pstate: Fix setting max_perf_pct in performance policy ext4: fix overflow when updating superblock backups after resize ext4: check s_chksum_driver when looking for bg csum presence ext4: fix reservation overflow in ext4_da_write_begin ext4: add ext4_iget_normal() which is to be used for dir tree lookups ext4: grab missed write_count for EXT4_IOC_SWAP_BOOT ext4: don't check quota format when there are no quota files ext4: check EA value offset when loading jbd2: free bh when descriptor block checksum fails MIPS: tlbex: Properly fix HUGE TLB Refill exception handler target: Fix APTPL metadata handling for dynamic MappedLUNs target: Fix queue full status NULL pointer for SCF_TRANSPORT_TASK_SENSE qla_target: don't delete changed nacls ARC: Update order of registers in KGDB to match GDB 7.5 ARC: [nsimosci] Allow "headless" models to boot KVM: x86: Emulator fixes for eip canonical checks on near branches KVM: x86: Fix wrong masking on relative jump/call kvm: x86: don't kill guest on unknown exit reason KVM: x86: Check non-canonical addresses upon WRMSR KVM: x86: Improve thread safety in pit KVM: x86: Prevent host from panicking on shared MSR writes. kvm: fix excessive pages un-pinning in kvm_iommu_map error path. media: tda7432: Fix setting TDA7432_MUTE bit for TDA7432_RF register media: ds3000: fix LNB supply voltage on Tevii S480 on initialization media: em28xx-v4l: give back all active video buffers to the vb2 core properly on streaming stop media: v4l2-common: fix overflow in v4l_bound_align_image() drm/nouveau/bios: memset dcb struct to zero before parsing drm/tilcdc: Fix the error path in tilcdc_load() drm/ast: Fix HW cursor image Input: i8042 - quirks for Fujitsu Lifebook A544 and Lifebook AH544 Input: i8042 - add noloop quirk for Asus X750LN framebuffer: fix border color modules, lock around setting of MODULE_STATE_UNFORMED dm log userspace: fix memory leak in dm_ulog_tfr_init failure path block: fix alignment_offset math that assumes io_min is a power-of-2 drbd: compute the end before rb_insert_augmented() dm bufio: update last_accessed when relinking a buffer virtio_pci: fix virtio spec compliance on restore selinux: fix inode security list corruption pstore: Fix duplicate {console,ftrace}-efi entries mfd: rtsx_pcr: Fix MSI enable error handling mnt: Prevent pivot_root from creating a loop in the mount tree UBI: add missing kmem_cache_free() in process_pool_aeb error path random: add and use memzero_explicit() for clearing data crypto: more robust crypto_memneq fix misuses of f_count() in ppp and netlink kill wbuf_queued/wbuf_dwork_lock ALSA: pcm: Zero-clear reserved fields of PCM status ioctl in compat mode evm: check xattr value length and type in evm_inode_setxattr() x86, pageattr: Prevent overflow in slow_virt_to_phys() for X86_PAE x86_64, entry: Fix out of bounds read on sysenter x86_64, entry: Filter RFLAGS.NT on entry from userspace x86, flags: Rename X86_EFLAGS_BIT1 to X86_EFLAGS_FIXED x86, fpu: shift drop_init_fpu() from save_xstate_sig() to handle_signal() x86, fpu: __restore_xstate_sig()->math_state_restore() needs preempt_disable() x86: Reject x32 executables if x32 ABI not supported vfs: fix data corruption when blocksize < pagesize for mmaped data UBIFS: fix free log space calculation UBIFS: fix a race condition UBIFS: remove mst_mutex fs: Fix theoretical division by 0 in super_cache_scan(). fs: make cont_expand_zero interruptible mmc: rtsx_pci_sdmmc: fix incorrect last byte in R2 response libata-sff: Fix controllers with no ctl port pata_serverworks: disable 64-KB DMA transfers on Broadcom OSB4 IDE Controller Revert "percpu: free percpu allocation info for uniprocessor system" lockd: Try to reconnect if statd has moved drivers/net: macvtap and tun depend on INET ipv4: dst_entry leak in ip_send_unicast_reply() ax88179_178a: fix bonding failure ipv4: fix nexthop attlen check in fib_nh_match tracing/syscalls: Ignore numbers outside NR_syscalls' range Linux 3.10.59 ecryptfs: avoid to access NULL pointer when write metadata in xattr ARM: at91/PMC: don't forget to write PMC_PCDR register to disable clocks ALSA: usb-audio: Add support for Steinberg UR22 USB interface ALSA: emu10k1: Fix deadlock in synth voice lookup ALSA: pcm: use the same dma mmap codepath both for arm and arm64 arm64: compat: fix compat types affecting struct compat_elf_prpsinfo spi: dw-mid: terminate ongoing transfers at exit kernel: add support for gcc 5 fanotify: enable close-on-exec on events' fd when requested in fanotify_init() mm: clear __GFP_FS when PF_MEMALLOC_NOIO is set Bluetooth: Fix issue with USB suspend in btusb driver Bluetooth: Fix HCI H5 corrupted ack value rt2800: correct BBP1_TX_POWER_CTRL mask PCI: Generate uppercase hex for modalias interface class PCI: Increase IBM ipr SAS Crocodile BARs to at least system page size iwlwifi: Add missing PCI IDs for the 7260 series NFSv4.1: Fix an NFSv4.1 state renewal regression NFSv4: fix open/lock state recovery error handling NFSv4: Fix lock recovery when CREATE_SESSION/SETCLIENTID_CONFIRM fails lzo: check for length overrun in variable length encoding. Revert "lzo: properly check for overruns" Documentation: lzo: document part of the encoding m68k: Disable/restore interrupts in hwreg_present()/hwreg_write() Drivers: hv: vmbus: Fix a bug in vmbus_open() Drivers: hv: vmbus: Cleanup vmbus_establish_gpadl() Drivers: hv: vmbus: Cleanup vmbus_teardown_gpadl() Drivers: hv: vmbus: Cleanup vmbus_post_msg() firmware_class: make sure fw requests contain a name qla2xxx: Use correct offset to req-q-out for reserve calculation mptfusion: enable no_write_same for vmware scsi disks be2iscsi: check ip buffer before copying regmap: fix NULL pointer dereference in _regmap_write/read regmap: debugfs: fix possbile NULL pointer dereference spi: dw-mid: check that DMA was inited before exit spi: dw-mid: respect 8 bit mode x86/intel/quark: Switch off CR4.PGE so TLB flush uses CR3 instead kvm: don't take vcpu mutex for obviously invalid vcpu ioctls KVM: s390: unintended fallthrough for external call kvm: x86: fix stale mmio cache bug fs: Add a missing permission check to do_umount Btrfs: fix race in WAIT_SYNC ioctl Btrfs: fix build_backref_tree issue with multiple shared blocks Btrfs: try not to ENOSPC on log replay Linux 3.10.58 USB: cp210x: add support for Seluxit USB dongle USB: serial: cp210x: added Ketra N1 wireless interface support USB: Add device quirk for ASUS T100 Base Station keyboard ipv6: reallocate addrconf router for ipv6 address when lo device up tcp: fixing TLP's FIN recovery sctp: handle association restarts when the socket is closed. ip6_gre: fix flowi6_proto value in xmit path hyperv: Fix a bug in netvsc_start_xmit() tg3: Allow for recieve of full-size 8021AD frames tg3: Work around HW/FW limitations with vlan encapsulated frames l2tp: fix race while getting PMTU on PPP pseudo-wire openvswitch: fix panic with multiple vlan headers packet: handle too big packets for PACKET_V3 tcp: fix tcp_release_cb() to dispatch via address family for mtu_reduced() sit: Fix ipip6_tunnel_lookup device matching criteria myri10ge: check for DMA mapping errors Linux 3.10.57 cpufreq: ondemand: Change the calculation of target frequency cpufreq: Fix wrong time unit conversion nl80211: clear skb cb before passing to netlink drbd: fix regression 'out of mem, failed to invoke fence-peer helper' jiffies: Fix timeval conversion to jiffies md/raid5: disable 'DISCARD' by default due to safety concerns. media: vb2: fix VBI/poll regression mm: numa: Do not mark PTEs pte_numa when splitting huge pages mm, thp: move invariant bug check out of loop in __split_huge_page_map ring-buffer: Fix infinite spin in reading buffer init/Kconfig: Fix HAVE_FUTEX_CMPXCHG to not break up the EXPERT menu perf: fix perf bug in fork() udf: Avoid infinite loop when processing indirect ICBs Linux 3.10.56 vm_is_stack: use for_each_thread() rather then buggy while_each_thread() oom_kill: add rcu_read_lock() into find_lock_task_mm() oom_kill: has_intersects_mems_allowed() needs rcu_read_lock() oom_kill: change oom_kill.c to use for_each_thread() introduce for_each_thread() to replace the buggy while_each_thread() kernel/fork.c:copy_process(): unify CLONE_THREAD-or-thread_group_leader code arm: multi_v7_defconfig: Enable Zynq UART driver ext2: Fix fs corruption in ext2_get_xip_mem() serial: 8250_dma: check the result of TX buffer mapping ARM: 7748/1: oabi: handle faults when loading swi instruction from userspace netfilter: nf_conntrack: avoid large timeout for mid-stream pickup PM / sleep: Use valid_state() for platform-dependent sleep states only PM / sleep: Add state field to pm_states[] entries ipvs: fix ipv6 hook registration for local replies ipvs: Maintain all DSCP and ECN bits for ipv6 tun forwarding ipvs: avoid netns exit crash on ip_vs_conn_drop_conntrack md/raid1: fix_read_error should act on all non-faulty devices. media: cx18: fix kernel oops with tda8290 tuner Fix nasty 32-bit overflow bug in buffer i/o code. perf kmem: Make it work again on non NUMA machines perf: Fix a race condition in perf_remove_from_context() alarmtimer: Lock k_itimer during timer callback alarmtimer: Do not signal SIGEV_NONE timers parisc: Only use -mfast-indirect-calls option for 32-bit kernel builds powerpc/perf: Fix ABIv2 kernel backtraces sched: Fix unreleased llc_shared_mask bit during CPU hotplug ocfs2/dlm: do not get resource spinlock if lockres is new nilfs2: fix data loss with mmap() fs/notify: don't show f_handle if exportfs_encode_inode_fh failed fsnotify/fdinfo: use named constants instead of hardcoded values kcmp: fix standard comparison bug Revert "mac80211: disable uAPSD if all ACs are under ACM" usb: dwc3: core: fix ordering for PHY suspend usb: dwc3: core: fix order of PM runtime calls usb: host: xhci: fix compliance mode workaround genhd: fix leftover might_sleep() in blk_free_devt() lockd: fix rpcbind crash on lockd startup failure rtlwifi: rtl8192cu: Add new ID percpu: perform tlb flush after pcpu_map_pages() failure percpu: fix pcpu_alloc_pages() failure path percpu: free percpu allocation info for uniprocessor system ata_piix: Add Device IDs for Intel 9 Series PCH Input: i8042 - add nomux quirk for Avatar AVIU-145A6 Input: i8042 - add Fujitsu U574 to no_timeout dmi table Input: atkbd - do not try 'deactivate' keyboard on any LG laptops Input: elantech - fix detection of touchpad on ASUS s301l Input: synaptics - add support for ForcePads Input: serport - add compat handling for SPIOCSTYPE ioctl dm crypt: fix access beyond the end of allocated space block: Fix dev_t minor allocation lifetime workqueue: apply __WQ_ORDERED to create_singlethread_workqueue() Revert "iwlwifi: dvm: don't enable CTS to self" SCSI: libiscsi: fix potential buffer overrun in __iscsi_conn_send_pdu NFC: microread: Potential overflows in microread_target_discovered() iscsi-target: Fix memory corruption in iscsit_logout_post_handler_diffcid iscsi-target: avoid NULL pointer in iscsi_copy_param_list failure Target/iser: Don't put isert_conn inside disconnected handler Target/iser: Get isert_conn reference once got to connected_handler iio:inkern: fix overwritten -EPROBE_DEFER in of_iio_channel_get_by_name iio:magnetometer: bugfix magnetometers gain values iio: adc: ad_sigma_delta: Fix indio_dev->trig assignment iio: st_sensors: Fix indio_dev->trig assignment iio: meter: ade7758: Fix indio_dev->trig assignment iio: inv_mpu6050: Fix indio_dev->trig assignment iio: gyro: itg3200: Fix indio_dev->trig assignment iio:trigger: modify return value for iio_trigger_get CIFS: Fix SMB2 readdir error handling CIFS: Fix directory rename error ASoC: davinci-mcasp: Correct rx format unit configuration shmem: fix nlink for rename overwrite directory x86 early_ioremap: Increase FIX_BTMAPS_SLOTS to 8 KVM: x86: handle idiv overflow at kvm_write_tsc regmap: Fix handling of volatile registers for format_write() chips ACPICA: Update to GPIO region handler interface. MIPS: mcount: Adjust stack pointer for static trace in MIPS32 MIPS: ZBOOT: add missing <linux/string.h> include ARM: 8165/1: alignment: don't break misaligned NEON load/store ARM: 7897/1: kexec: Use the right ISA for relocate_new_kernel ARM: 8133/1: use irq_set_affinity with force=false when migrating irqs ARM: 8128/1: abort: don't clear the exclusive monitors NFSv4: Fix another bug in the close/open_downgrade code NFSv4: nfs4_state_manager() vs. nfs_server_remove_lists() usb:hub set hub->change_bits when over-current happens usb: dwc3: omap: fix ordering for runtime pm calls USB: EHCI: unlink QHs even after the controller has stopped USB: storage: Add quirks for Entrega/Xircom USB to SCSI converters USB: storage: Add quirk for Ariston Technologies iConnect USB to SCSI adapter USB: storage: Add quirk for Adaptec USBConnect 2000 USB-to-SCSI Adapter storage: Add single-LUN quirk for Jaz USB Adapter usb: hub: take hub->hdev reference when processing from eventlist xhci: fix oops when xhci resumes from hibernate with hw lpm capable devices xhci: Fix null pointer dereference if xhci initialization fails USB: zte_ev: fix removed PIDs USB: ftdi_sio: add support for NOVITUS Bono E thermal printer USB: sierra: add 1199:68AA device ID USB: sierra: avoid CDC class functions on "68A3" devices USB: zte_ev: remove duplicate Qualcom PID USB: zte_ev: remove duplicate Gobi PID Revert "USB: option,zte_ev: move most ZTE CDMA devices to zte_ev" USB: option: add VIA Telecom CDS7 chipset device id USB: option: reduce interrupt-urb logging verbosity USB: serial: fix potential heap buffer overflow USB: sisusb: add device id for Magic Control USB video USB: serial: fix potential stack buffer overflow USB: serial: pl2303: add device id for ztek device xtensa: fix a6 and a7 handling in fast_syscall_xtensa xtensa: fix TLBTEMP_BASE_2 region handling in fast_second_level_miss xtensa: fix access to THREAD_RA/THREAD_SP/THREAD_DS xtensa: fix address checks in dma_{alloc,free}_coherent xtensa: replace IOCTL code definitions with constants drm/radeon: add connector quirk for fujitsu board drm/vmwgfx: Fix a potential infinite spin waiting for fifo idle drm/ast: AST2000 cannot be detected correctly drm/i915: Wait for vblank before enabling the TV encoder drm/i915: Remove bogus __init annotation from DMI callbacks HID: logitech-dj: prevent false errors to be shown HID: magicmouse: sanity check report size in raw_event() callback HID: picolcd: sanity check report size in raw_event() callback cfq-iosched: Fix wrong children_weight calculation ALSA: pcm: fix fifo_size frame calculation ALSA: hda - Fix invalid pin powermap without jack detection ALSA: hda - Fix COEF setups for ALC1150 codec ALSA: core: fix buffer overflow in snd_info_get_line() arm64: ptrace: fix compat hardware watchpoint reporting trace: Fix epoll hang when we race with new entries i2c: at91: Fix a race condition during signal handling in at91_do_twi_xfer. i2c: at91: add bound checking on SMBus block length bytes arm64: flush TLS registers during exec ibmveth: Fix endian issues with rx_no_buffer statistic ahci: add pcid for Marvel 0x9182 controller ahci: Add Device IDs for Intel 9 Series PCH pata_scc: propagate return value of scc_wait_after_reset drm/i915: read HEAD register back in init_ring_common() to enforce ordering drm/radeon: load the lm63 driver for an lm64 thermal chip. drm/ttm: Choose a pool to shrink correctly in ttm_dma_pool_shrink_scan(). drm/ttm: Fix possible division by 0 in ttm_dma_pool_shrink_scan(). drm/tilcdc: fix double kfree drm/tilcdc: fix release order on exit drm/tilcdc: panel: fix leak when unloading the module drm/tilcdc: tfp410: fix dangling sysfs connector node drm/tilcdc: slave: fix dangling sysfs connector node drm/tilcdc: panel: fix dangling sysfs connector node carl9170: fix sending URBs with wrong type when using full-speed Linux 3.10.55 libceph: gracefully handle large reply messages from the mon libceph: rename ceph_msg::front_max to front_alloc_len tpm: Provide a generic means to override the chip returned timeouts vfs: fix bad hashing of dentries dcache.c: get rid of pointless macros IB/srp: Fix deadlock between host removal and multipathd blkcg: don't call into policy draining if root_blkg is already gone mtd: nand: omap: Fix 1-bit Hamming code scheme, omap_calculate_ecc() mtd/ftl: fix the double free of the buffers allocated in build_maps() CIFS: Fix wrong restart readdir for SMB1 CIFS: Fix wrong filename length for SMB2 CIFS: Fix wrong directory attributes after rename CIFS: Possible null ptr deref in SMB2_tcon CIFS: Fix async reading on reconnects CIFS: Fix STATUS_CANNOT_DELETE error mapping for SMB2 libceph: do not hard code max auth ticket len libceph: add process_one_ticket() helper libceph: set last_piece in ceph_msg_data_pages_cursor_init() correctly md/raid1,raid10: always abort recover on write error. xfs: don't zero partial page cache pages during O_DIRECT writes xfs: don't zero partial page cache pages during O_DIRECT writes xfs: don't dirty buffers beyond EOF xfs: quotacheck leaves dquot buffers without verifiers RDMA/iwcm: Use a default listen backlog if needed md/raid10: Fix memory leak when raid10 reshape completes. md/raid10: fix memory leak when reshaping a RAID10. md/raid6: avoid data corruption during recovery of double-degraded RAID6 Bluetooth: Avoid use of session socket after the session gets freed Bluetooth: never linger on process exit mnt: Add tests for unprivileged remount cases that have found to be faulty mnt: Change the default remount atime from relatime to the existing value mnt: Correct permission checks in do_remount mnt: Move the test for MNT_LOCK_READONLY from change_mount_flags into do_remount mnt: Only change user settable mount flags in remount ring-buffer: Up rb_iter_peek() loop count to 3 ring-buffer: Always reset iterator to reader page ACPI / cpuidle: fix deadlock between cpuidle_lock and cpu_hotplug.lock ACPI: Run fixed event device notifications in process context ACPICA: Utilities: Fix memory leak in acpi_ut_copy_iobject_to_iobject bfa: Fix undefined bit shift on big-endian architectures with 32-bit DMA address ASoC: pxa-ssp: drop SNDRV_PCM_FMTBIT_S24_LE ASoC: max98090: Fix missing free_irq ASoC: samsung: Correct I2S DAI suspend/resume ops ASoC: wm_adsp: Add missing MODULE_LICENSE ASoC: pcm: fix dpcm_path_put in dpcm runtime update openrisc: Rework signal handling MIPS: Fix accessing to per-cpu data when flushing the cache MIPS: OCTEON: make get_system_type() thread-safe MIPS: asm: thread_info: Add _TIF_SECCOMP flag MIPS: Cleanup flags in syscall flags handlers. MIPS: asm/reg.h: Make 32- and 64-bit definitions available at the same time MIPS: Remove BUG_ON(!is_fpu_owner()) in do_ade() MIPS: tlbex: Fix a missing statement for HUGETLB MIPS: Prevent user from setting FCSR cause bits MIPS: GIC: Prevent array overrun drivers: scsi: storvsc: Correctly handle TEST_UNIT_READY failure Drivers: scsi: storvsc: Implement a eh_timed_out handler powerpc/pseries: Failure on removing device node powerpc/mm: Use read barrier when creating real_pte powerpc/mm/numa: Fix break placement regulator: arizona-ldo1: remove bypass functionality mfd: omap-usb-host: Fix improper mask use. kernel/smp.c:on_each_cpu_cond(): fix warning in fallback path CAPABILITIES: remove undefined caps from all processes tpm: missing tpm_chip_put in tpm_get_random() firmware: Do not use WARN_ON(!spin_is_locked()) spi: omap2-mcspi: Configure hardware when slave driver changes mode spi: orion: fix incorrect handling of cell-index DT property iommu/amd: Fix cleanup_domain for mass device removal media: media-device: Remove duplicated memset() in media_enum_entities() media: au0828: Only alt setting logic when needed media: xc4000: Fix get_frequency() media: xc5000: Fix get_frequency() Linux 3.10.54 USB: fix build error with CONFIG_PM_RUNTIME disabled NFSv4: Fix problems with close in the presence of a delegation NFSv3: Fix another acl regression svcrdma: Select NFSv4.1 backchannel transport based on forward channel NFSD: Decrease nfsd_users in nfsd_startup_generic fail usb: hub: Prevent hub autosuspend if usbcore.autosuspend is -1 USB: whiteheat: Added bounds checking for bulk command response USB: ftdi_sio: Added PID for new ekey device USB: ftdi_sio: add Basic Micro ATOM Nano USB2Serial PID ARM: OMAP2+: hwmod: Rearm wake-up interrupts for DT when MUSB is idled usb: xhci: amd chipset also needs short TX quirk xhci: Treat not finding the event_seg on COMP_STOP the same as COMP_STOP_INVAL Staging: speakup: Update __speakup_paste_selection() tty (ab)usage to match vt jbd2: fix infinite loop when recovering corrupt journal blocks mei: nfc: fix memory leak in error path mei: reset client state on queued connect request Btrfs: fix csum tree corruption, duplicate and outdated checksums hpsa: fix bad -ENOMEM return value in hpsa_big_passthru_ioctl x86/efi: Enforce CONFIG_RELOCATABLE for EFI boot stub x86_64/vsyscall: Fix warn_bad_vsyscall log output x86: don't exclude low BIOS area when allocating address space for non-PCI cards drm/radeon: add additional SI pci ids ext4: fix BUG_ON in mb_free_blocks() kvm: iommu: fix the third parameter of kvm_iommu_put_pages (CVE-2014-3601) Revert "KVM: x86: Increase the number of fixed MTRR regs to 10" KVM: nVMX: fix "acknowledge interrupt on exit" when APICv is in use KVM: x86: always exit on EOIs for interrupts listed in the IOAPIC redir table KVM: x86: Inter-privilege level ret emulation is not implemeneted crypto: ux500 - make interrupt mode plausible serial: core: Preserve termios c_cflag for console resume ext4: fix ext4_discard_allocated_blocks() if we can't allocate the pa struct drivers/i2c/busses: use correct type for dma_map/unmap hwmon: (dme1737) Prevent overflow problem when writing large limits hwmon: (ads1015) Fix out-of-bounds array access hwmon: (lm85) Fix various errors on attribute writes hwmon: (ads1015) Fix off-by-one for valid channel index checking hwmon: (gpio-fan) Prevent overflow problem when writing large limits hwmon: (lm78) Fix overflow problems seen when writing large temperature limits hwmon: (sis5595) Prevent overflow problem when writing large limits drm: omapdrm: fix compiler errors ARM: OMAP3: Fix choice of omap3_restore_es function in OMAP34XX rev3.1.2 case. mei: start disconnect request timer consistently ALSA: hda/realtek - Avoid setting wrong COEF on ALC269 & co ALSA: hda/ca0132 - Don't try loading firmware at resume when already failed ALSA: virtuoso: add Xonar Essence STX II support ALSA: hda - fix an external mic jack problem on a HP machine USB: Fix persist resume of some SS USB devices USB: ehci-pci: USB host controller support for Intel Quark X1000 USB: serial: ftdi_sio: Add support for new Xsens devices USB: serial: ftdi_sio: Annotate the current Xsens PID assignments USB: OHCI: don't lose track of EDs when a controller dies isofs: Fix unbounded recursion when processing relocated directories HID: fix a couple of off-by-ones HID: logitech: perform bounds checking on device_id early enough stable_kernel_rules: Add pointer to netdev-FAQ for network patches Linux 3.10.53 arch/sparc/math-emu/math_32.c: drop stray break operator sparc64: ldc_connect() should not return EINVAL when handshake is in progress. sunsab: Fix detection of BREAK on sunsab serial console bbc-i2c: Fix BBC I2C envctrl on SunBlade 2000 sparc64: Guard against flushing openfirmware mappings. sparc64: Do not insert non-valid PTEs into the TSB hash table. sparc64: Add membar to Niagara2 memcpy code. sparc64: Fix huge TSB mapping on pre-UltraSPARC-III cpus. sparc64: Don't bark so loudly about 32-bit tasks generating 64-bit fault addresses. sparc64: Fix top-level fault handling bugs. sparc64: Handle 32-bit tasks properly in compute_effective_address(). sparc64: Make itc_sync_lock raw sparc64: Fix argument sign extension for compat_sys_futex(). sctp: fix possible seqlock seadlock in sctp_packet_transmit() iovec: make sure the caller actually wants anything in memcpy_fromiovecend net: Correctly set segment mac_len in skb_segment(). macvlan: Initialize vlan_features to turn on offload support. net: sctp: inherit auth_capable on INIT collisions tcp: Fix integer-overflow in TCP vegas tcp: Fix integer-overflows in TCP veno net: sendmsg: fix NULL pointer dereference ip: make IP identifiers less predictable inetpeer: get rid of ip_id_count bnx2x: fix crash during TSO tunneling Linux 3.10.52 x86/espfix/xen: Fix allocation of pages for paravirt page tables lib/btree.c: fix leak of whole btree nodes net/l2tp: don't fall back on UDP [get|set]sockopt net: mvneta: replace Tx timer with a real interrupt net: mvneta: add missing bit descriptions for interrupt masks and causes net: mvneta: do not schedule in mvneta_tx_timeout net: mvneta: use per_cpu stats to fix an SMP lock up net: mvneta: increase the 64-bit rx/tx stats out of the hot path Revert "mac80211: move "bufferable MMPDU" check to fix AP mode scan" staging: vt6655: Fix Warning on boot handle_irq_event_percpu. x86_64/entry/xen: Do not invoke espfix64 on Xen x86, espfix: Make it possible to disable 16-bit support x86, espfix: Make espfix64 a Kconfig option, fix UML x86, espfix: Fix broken header guard x86, espfix: Move espfix definitions into a separate header file x86-64, espfix: Don't leak bits 31:16 of %esp returning to 16-bit stack Revert "x86-64, modify_ldt: Make support for 16-bit segments a runtime option" timer: Fix lock inversion between hrtimer_bases.lock and scheduler locks printk: rename printk_sched to printk_deferred iio: buffer: Fix demux table creation staging: vt6655: Fix disassociated messages every 10 seconds mm, thp: do not allow thp faults to avoid cpuset restrictions scsi: handle flush errors properly rapidio/tsi721_dma: fix failure to obtain transaction descriptor cfg80211: fix mic_failure tracing ARM: 8115/1: LPAE: reduce damage caused by idmap to virtual memory layout crypto: af_alg - properly label AF_ALG socket Linux 3.10.51 core, nfqueue, openvswitch: Orphan frags in skb_zerocopy and handle errors x86/efi: Include a .bss section within the PE/COFF headers s390/ptrace: fix PSW mask check Fix gcc-4.9.0 miscompilation of load_balance() in scheduler mm: hugetlb: fix copy_hugetlb_page_range() x86_32, entry: Store badsys error code in %eax hwmon: (smsc47m192) Fix temperature limit and vrm write operations parisc: Remove SA_RESTORER define coredump: fix the setting of PF_DUMPCORE Input: fix defuzzing logic slab_common: fix the check for duplicate slab names slab_common: Do not check for duplicate slab names tracing: Fix wraparound problems in "uptime" trace clock blkcg: don't call into policy draining if root_blkg is already gone ahci: add support for the Promise FastTrak TX8660 SATA HBA (ahci mode) libata: introduce ata_host->n_tags to avoid oops on SAS controllers libata: support the ata host which implements a queue depth less than 32 block: don't assume last put of shared tags is for the host block: provide compat ioctl for BLKZEROOUT media: tda10071: force modulation to QPSK on DVB-S media: hdpvr: fix two audio bugs Linux 3.10.50 ARC: Implement ptrace(PTRACE_GET_THREAD_AREA) sched: Fix possible divide by zero in avg_atom() calculation locking/mutex: Disable optimistic spinning on some architectures PM / sleep: Fix request_firmware() error at resume dm cache metadata: do not allow the data block size to change dm thin metadata: do not allow the data block size to change alarmtimer: Fix bug where relative alarm timers were treated as absolute drm/radeon: avoid leaking edid data drm/qxl: return IRQ_NONE if it was not our irq drm/radeon: set default bl level to something reasonable irqchip: gic: Fix core ID calculation when topology is read from DT irqchip: gic: Add support for cortex a7 compatible string ring-buffer: Fix polling on trace_pipe mwifiex: fix Tx timeout issue perf/x86/intel: ignore CondChgd bit to avoid false NMI handling ipv4: fix buffer overflow in ip_options_compile() dns_resolver: Null-terminate the right string dns_resolver: assure that dns_query() result is null-terminated sunvnet: clean up objects created in vnet_new() on vnet_exit() net: pppoe: use correct channel MTU when using Multilink PPP net: sctp: fix information leaks in ulpevent layer tipc: clear 'next'-pointer of message fragments before reassembly be2net: set EQ DB clear-intr bit in be_open() netlink: Fix handling of error from netlink_dump(). net: mvneta: Fix big endian issue in mvneta_txq_desc_csum() net: mvneta: fix operation in 10 Mbit/s mode appletalk: Fix socket referencing in skb tcp: fix false undo corner cases igmp: fix the problem when mc leave group net: qmi_wwan: add two Sierra Wireless/Netgear devices net: qmi_wwan: Add ID for Telewell TW-LTE 4G v2 ipv4: icmp: Fix pMTU handling for rare case tcp: Fix divide by zero when pushing during tcp-repair bnx2x: fix possible panic under memory stress net: fix sparse warning in sk_dst_set() ipv4: irq safe sk_dst_[re]set() and ipv4_sk_update_pmtu() fix ipv4: fix dst race in sk_dst_get() 8021q: fix a potential memory leak net: sctp: check proc_dointvec result in proc_sctp_do_auth tcp: fix tcp_match_skb_to_sack() for unaligned SACK at end of an skb ip_tunnel: fix ip_tunnel_lookup shmem: fix splicing from a hole while it's punched shmem: fix faulting into a hole, not taking i_mutex shmem: fix faulting into a hole while it's punched iwlwifi: dvm: don't enable CTS to self igb: do a reset on SR-IOV re-init if device is down hwmon: (adt7470) Fix writes to temperature limit registers hwmon: (da9052) Don't use dash in the name attribute hwmon: (da9055) Don't use dash in the name attribute tracing: Add ftrace_trace_stack into __trace_puts/__trace_bputs tracing: Fix graph tracer with stack tracer on other archs fuse: handle large user and group ID Bluetooth: Ignore H5 non-link packets in non-active state Drivers: hv: util: Fix a bug in the KVP code media: gspca_pac7302: Add new usb-id for Genius i-Look 317 usb: Check if port status is equal to RxDetect Signed-off-by: Ian Maund <imaund@codeaurora.org>
3944 lines
111 KiB
C
3944 lines
111 KiB
C
/*
|
|
* linux/mm/vmscan.c
|
|
*
|
|
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
|
|
*
|
|
* Swap reorganised 29.12.95, Stephen Tweedie.
|
|
* kswapd added: 7.1.96 sct
|
|
* Removed kswapd_ctl limits, and swap out as many pages as needed
|
|
* to bring the system back to freepages.high: 2.4.97, Rik van Riel.
|
|
* Zone aware kswapd started 02/00, Kanoj Sarcar (kanoj@sgi.com).
|
|
* Multiqueue VM started 5.8.00, Rik van Riel.
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/module.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/init.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/vmpressure.h>
|
|
#include <linux/vmstat.h>
|
|
#include <linux/file.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/buffer_head.h> /* for try_to_release_page(),
|
|
buffer_heads_over_limit */
|
|
#include <linux/mm_inline.h>
|
|
#include <linux/backing-dev.h>
|
|
#include <linux/rmap.h>
|
|
#include <linux/topology.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/cpuset.h>
|
|
#include <linux/compaction.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/rwsem.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/kthread.h>
|
|
#include <linux/freezer.h>
|
|
#include <linux/memcontrol.h>
|
|
#include <linux/delayacct.h>
|
|
#include <linux/sysctl.h>
|
|
#include <linux/oom.h>
|
|
#include <linux/prefetch.h>
|
|
#include <linux/debugfs.h>
|
|
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/div64.h>
|
|
|
|
#include <linux/swapops.h>
|
|
#include <linux/balloon_compaction.h>
|
|
|
|
#include "internal.h"
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/vmscan.h>
|
|
|
|
struct scan_control {
|
|
/* Incremented by the number of inactive pages that were scanned */
|
|
unsigned long nr_scanned;
|
|
|
|
/* Number of pages freed so far during a call to shrink_zones() */
|
|
unsigned long nr_reclaimed;
|
|
|
|
/* How many pages shrink_list() should reclaim */
|
|
unsigned long nr_to_reclaim;
|
|
|
|
unsigned long hibernation_mode;
|
|
|
|
/* This context's GFP mask */
|
|
gfp_t gfp_mask;
|
|
|
|
int may_writepage;
|
|
|
|
/* Can mapped pages be reclaimed? */
|
|
int may_unmap;
|
|
|
|
/* Can pages be swapped as part of reclaim? */
|
|
int may_swap;
|
|
|
|
int order;
|
|
|
|
/* Scan (total_size >> priority) pages at once */
|
|
int priority;
|
|
|
|
/*
|
|
* The memory cgroup that hit its limit and as a result is the
|
|
* primary target of this reclaim invocation.
|
|
*/
|
|
struct mem_cgroup *target_mem_cgroup;
|
|
|
|
/*
|
|
* Nodemask of nodes allowed by the caller. If NULL, all nodes
|
|
* are scanned.
|
|
*/
|
|
nodemask_t *nodemask;
|
|
|
|
/*
|
|
* Reclaim pages from a vma. If the page is shared by other tasks
|
|
* it is zapped from a vma without reclaim so it ends up remaining
|
|
* on memory until last task zap it.
|
|
*/
|
|
struct vm_area_struct *target_vma;
|
|
};
|
|
|
|
#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
|
|
|
|
#ifdef ARCH_HAS_PREFETCH
|
|
#define prefetch_prev_lru_page(_page, _base, _field) \
|
|
do { \
|
|
if ((_page)->lru.prev != _base) { \
|
|
struct page *prev; \
|
|
\
|
|
prev = lru_to_page(&(_page->lru)); \
|
|
prefetch(&prev->_field); \
|
|
} \
|
|
} while (0)
|
|
#else
|
|
#define prefetch_prev_lru_page(_page, _base, _field) do { } while (0)
|
|
#endif
|
|
|
|
#ifdef ARCH_HAS_PREFETCHW
|
|
#define prefetchw_prev_lru_page(_page, _base, _field) \
|
|
do { \
|
|
if ((_page)->lru.prev != _base) { \
|
|
struct page *prev; \
|
|
\
|
|
prev = lru_to_page(&(_page->lru)); \
|
|
prefetchw(&prev->_field); \
|
|
} \
|
|
} while (0)
|
|
#else
|
|
#define prefetchw_prev_lru_page(_page, _base, _field) do { } while (0)
|
|
#endif
|
|
|
|
/*
|
|
* From 0 .. 100. Higher means more swappy.
|
|
*/
|
|
int vm_swappiness = 60;
|
|
unsigned long vm_total_pages; /* The total number of pages which the VM controls */
|
|
|
|
#ifdef CONFIG_KSWAPD_CPU_AFFINITY_MASK
|
|
char *kswapd_cpu_mask = CONFIG_KSWAPD_CPU_AFFINITY_MASK;
|
|
#else
|
|
char *kswapd_cpu_mask = NULL;
|
|
#endif
|
|
|
|
static LIST_HEAD(shrinker_list);
|
|
static DECLARE_RWSEM(shrinker_rwsem);
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
static bool global_reclaim(struct scan_control *sc)
|
|
{
|
|
return !sc->target_mem_cgroup;
|
|
}
|
|
#else
|
|
static bool global_reclaim(struct scan_control *sc)
|
|
{
|
|
return true;
|
|
}
|
|
#endif
|
|
|
|
static unsigned long zone_reclaimable_pages(struct zone *zone)
|
|
{
|
|
int nr;
|
|
|
|
nr = zone_page_state(zone, NR_ACTIVE_FILE) +
|
|
zone_page_state(zone, NR_INACTIVE_FILE);
|
|
|
|
if (get_nr_swap_pages() > 0)
|
|
nr += zone_page_state(zone, NR_ACTIVE_ANON) +
|
|
zone_page_state(zone, NR_INACTIVE_ANON);
|
|
|
|
return nr;
|
|
}
|
|
|
|
bool zone_reclaimable(struct zone *zone)
|
|
{
|
|
return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
|
|
}
|
|
|
|
static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
|
|
{
|
|
if (!mem_cgroup_disabled())
|
|
return mem_cgroup_get_lru_size(lruvec, lru);
|
|
|
|
return zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru);
|
|
}
|
|
|
|
struct dentry *debug_file;
|
|
|
|
static int debug_shrinker_show(struct seq_file *s, void *unused)
|
|
{
|
|
struct shrinker *shrinker;
|
|
struct shrink_control sc;
|
|
|
|
sc.gfp_mask = -1;
|
|
sc.nr_to_scan = 0;
|
|
|
|
down_read(&shrinker_rwsem);
|
|
list_for_each_entry(shrinker, &shrinker_list, list) {
|
|
int num_objs;
|
|
|
|
num_objs = shrinker->shrink(shrinker, &sc);
|
|
seq_printf(s, "%pf %d\n", shrinker->shrink, num_objs);
|
|
}
|
|
up_read(&shrinker_rwsem);
|
|
return 0;
|
|
}
|
|
|
|
static int debug_shrinker_open(struct inode *inode, struct file *file)
|
|
{
|
|
return single_open(file, debug_shrinker_show, inode->i_private);
|
|
}
|
|
|
|
static const struct file_operations debug_shrinker_fops = {
|
|
.open = debug_shrinker_open,
|
|
.read = seq_read,
|
|
.llseek = seq_lseek,
|
|
.release = single_release,
|
|
};
|
|
|
|
/*
|
|
* Add a shrinker callback to be called from the vm
|
|
*/
|
|
void register_shrinker(struct shrinker *shrinker)
|
|
{
|
|
atomic_long_set(&shrinker->nr_in_batch, 0);
|
|
down_write(&shrinker_rwsem);
|
|
list_add_tail(&shrinker->list, &shrinker_list);
|
|
up_write(&shrinker_rwsem);
|
|
}
|
|
EXPORT_SYMBOL(register_shrinker);
|
|
|
|
static int __init add_shrinker_debug(void)
|
|
{
|
|
debugfs_create_file("shrinker", 0644, NULL, NULL,
|
|
&debug_shrinker_fops);
|
|
return 0;
|
|
}
|
|
|
|
late_initcall(add_shrinker_debug);
|
|
|
|
/*
|
|
* Remove one
|
|
*/
|
|
void unregister_shrinker(struct shrinker *shrinker)
|
|
{
|
|
down_write(&shrinker_rwsem);
|
|
list_del(&shrinker->list);
|
|
up_write(&shrinker_rwsem);
|
|
}
|
|
EXPORT_SYMBOL(unregister_shrinker);
|
|
|
|
static inline int do_shrinker_shrink(struct shrinker *shrinker,
|
|
struct shrink_control *sc,
|
|
unsigned long nr_to_scan)
|
|
{
|
|
sc->nr_to_scan = nr_to_scan;
|
|
return (*shrinker->shrink)(shrinker, sc);
|
|
}
|
|
|
|
#define SHRINK_BATCH 128
|
|
/*
|
|
* Call the shrink functions to age shrinkable caches
|
|
*
|
|
* Here we assume it costs one seek to replace a lru page and that it also
|
|
* takes a seek to recreate a cache object. With this in mind we age equal
|
|
* percentages of the lru and ageable caches. This should balance the seeks
|
|
* generated by these structures.
|
|
*
|
|
* If the vm encountered mapped pages on the LRU it increase the pressure on
|
|
* slab to avoid swapping.
|
|
*
|
|
* We do weird things to avoid (scanned*seeks*entries) overflowing 32 bits.
|
|
*
|
|
* `lru_pages' represents the number of on-LRU pages in all the zones which
|
|
* are eligible for the caller's allocation attempt. It is used for balancing
|
|
* slab reclaim versus page reclaim.
|
|
*
|
|
* Returns the number of slab objects which we shrunk.
|
|
*/
|
|
unsigned long shrink_slab(struct shrink_control *shrink,
|
|
unsigned long nr_pages_scanned,
|
|
unsigned long lru_pages)
|
|
{
|
|
struct shrinker *shrinker;
|
|
unsigned long ret = 0;
|
|
|
|
if (nr_pages_scanned == 0)
|
|
nr_pages_scanned = SWAP_CLUSTER_MAX;
|
|
|
|
if (!down_read_trylock(&shrinker_rwsem)) {
|
|
/* Assume we'll be able to shrink next time */
|
|
ret = 1;
|
|
goto out;
|
|
}
|
|
|
|
list_for_each_entry(shrinker, &shrinker_list, list) {
|
|
unsigned long long delta;
|
|
long total_scan;
|
|
long max_pass;
|
|
int shrink_ret = 0;
|
|
long nr;
|
|
long new_nr;
|
|
long batch_size = shrinker->batch ? shrinker->batch
|
|
: SHRINK_BATCH;
|
|
long min_cache_size = batch_size;
|
|
|
|
if (current_is_kswapd())
|
|
min_cache_size = 0;
|
|
|
|
max_pass = do_shrinker_shrink(shrinker, shrink, 0);
|
|
if (max_pass <= 0)
|
|
continue;
|
|
|
|
/*
|
|
* copy the current shrinker scan count into a local variable
|
|
* and zero it so that other concurrent shrinker invocations
|
|
* don't also do this scanning work.
|
|
*/
|
|
nr = atomic_long_xchg(&shrinker->nr_in_batch, 0);
|
|
|
|
total_scan = nr;
|
|
delta = (4 * nr_pages_scanned) / shrinker->seeks;
|
|
delta *= max_pass;
|
|
do_div(delta, lru_pages + 1);
|
|
total_scan += delta;
|
|
if (total_scan < 0) {
|
|
printk(KERN_ERR "shrink_slab: %pF negative objects to "
|
|
"delete nr=%ld\n",
|
|
shrinker->shrink, total_scan);
|
|
total_scan = max_pass;
|
|
}
|
|
|
|
/*
|
|
* We need to avoid excessive windup on filesystem shrinkers
|
|
* due to large numbers of GFP_NOFS allocations causing the
|
|
* shrinkers to return -1 all the time. This results in a large
|
|
* nr being built up so when a shrink that can do some work
|
|
* comes along it empties the entire cache due to nr >>>
|
|
* max_pass. This is bad for sustaining a working set in
|
|
* memory.
|
|
*
|
|
* Hence only allow the shrinker to scan the entire cache when
|
|
* a large delta change is calculated directly.
|
|
*/
|
|
if (delta < max_pass / 4)
|
|
total_scan = min(total_scan, max_pass / 2);
|
|
|
|
/*
|
|
* Avoid risking looping forever due to too large nr value:
|
|
* never try to free more than twice the estimate number of
|
|
* freeable entries.
|
|
*/
|
|
if (total_scan > max_pass * 2)
|
|
total_scan = max_pass * 2;
|
|
|
|
trace_mm_shrink_slab_start(shrinker, shrink, nr,
|
|
nr_pages_scanned, lru_pages,
|
|
max_pass, delta, total_scan);
|
|
|
|
while (total_scan > min_cache_size) {
|
|
int nr_before;
|
|
|
|
if (total_scan < batch_size)
|
|
batch_size = total_scan;
|
|
|
|
nr_before = do_shrinker_shrink(shrinker, shrink, 0);
|
|
shrink_ret = do_shrinker_shrink(shrinker, shrink,
|
|
batch_size);
|
|
if (shrink_ret == -1)
|
|
break;
|
|
if (shrink_ret < nr_before)
|
|
ret += nr_before - shrink_ret;
|
|
count_vm_events(SLABS_SCANNED, batch_size);
|
|
total_scan -= batch_size;
|
|
|
|
cond_resched();
|
|
}
|
|
|
|
/*
|
|
* move the unused scan count back into the shrinker in a
|
|
* manner that handles concurrent updates. If we exhausted the
|
|
* scan, there is no need to do an update.
|
|
*/
|
|
if (total_scan > 0)
|
|
new_nr = atomic_long_add_return(total_scan,
|
|
&shrinker->nr_in_batch);
|
|
else
|
|
new_nr = atomic_long_read(&shrinker->nr_in_batch);
|
|
|
|
trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
|
|
}
|
|
up_read(&shrinker_rwsem);
|
|
out:
|
|
cond_resched();
|
|
return ret;
|
|
}
|
|
|
|
static inline int is_page_cache_freeable(struct page *page)
|
|
{
|
|
/*
|
|
* A freeable page cache page is referenced only by the caller
|
|
* that isolated the page, the page cache radix tree and
|
|
* optional buffer heads at page->private.
|
|
*/
|
|
return page_count(page) - page_has_private(page) == 2;
|
|
}
|
|
|
|
static int may_write_to_queue(struct backing_dev_info *bdi,
|
|
struct scan_control *sc)
|
|
{
|
|
if (current->flags & PF_SWAPWRITE)
|
|
return 1;
|
|
if (!bdi_write_congested(bdi))
|
|
return 1;
|
|
if (bdi == current->backing_dev_info)
|
|
return 1;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* We detected a synchronous write error writing a page out. Probably
|
|
* -ENOSPC. We need to propagate that into the address_space for a subsequent
|
|
* fsync(), msync() or close().
|
|
*
|
|
* The tricky part is that after writepage we cannot touch the mapping: nothing
|
|
* prevents it from being freed up. But we have a ref on the page and once
|
|
* that page is locked, the mapping is pinned.
|
|
*
|
|
* We're allowed to run sleeping lock_page() here because we know the caller has
|
|
* __GFP_FS.
|
|
*/
|
|
static void handle_write_error(struct address_space *mapping,
|
|
struct page *page, int error)
|
|
{
|
|
lock_page(page);
|
|
if (page_mapping(page) == mapping)
|
|
mapping_set_error(mapping, error);
|
|
unlock_page(page);
|
|
}
|
|
|
|
/* possible outcome of pageout() */
|
|
typedef enum {
|
|
/* failed to write page out, page is locked */
|
|
PAGE_KEEP,
|
|
/* move page to the active list, page is locked */
|
|
PAGE_ACTIVATE,
|
|
/* page has been sent to the disk successfully, page is unlocked */
|
|
PAGE_SUCCESS,
|
|
/* page is clean and locked */
|
|
PAGE_CLEAN,
|
|
} pageout_t;
|
|
|
|
/*
|
|
* pageout is called by shrink_page_list() for each dirty page.
|
|
* Calls ->writepage().
|
|
*/
|
|
static pageout_t pageout(struct page *page, struct address_space *mapping,
|
|
struct scan_control *sc)
|
|
{
|
|
/*
|
|
* If the page is dirty, only perform writeback if that write
|
|
* will be non-blocking. To prevent this allocation from being
|
|
* stalled by pagecache activity. But note that there may be
|
|
* stalls if we need to run get_block(). We could test
|
|
* PagePrivate for that.
|
|
*
|
|
* If this process is currently in __generic_file_aio_write() against
|
|
* this page's queue, we can perform writeback even if that
|
|
* will block.
|
|
*
|
|
* If the page is swapcache, write it back even if that would
|
|
* block, for some throttling. This happens by accident, because
|
|
* swap_backing_dev_info is bust: it doesn't reflect the
|
|
* congestion state of the swapdevs. Easy to fix, if needed.
|
|
*/
|
|
if (!is_page_cache_freeable(page))
|
|
return PAGE_KEEP;
|
|
if (!mapping) {
|
|
/*
|
|
* Some data journaling orphaned pages can have
|
|
* page->mapping == NULL while being dirty with clean buffers.
|
|
*/
|
|
if (page_has_private(page)) {
|
|
if (try_to_free_buffers(page)) {
|
|
ClearPageDirty(page);
|
|
printk("%s: orphaned page\n", __func__);
|
|
return PAGE_CLEAN;
|
|
}
|
|
}
|
|
return PAGE_KEEP;
|
|
}
|
|
if (mapping->a_ops->writepage == NULL)
|
|
return PAGE_ACTIVATE;
|
|
if (!may_write_to_queue(mapping->backing_dev_info, sc))
|
|
return PAGE_KEEP;
|
|
|
|
if (clear_page_dirty_for_io(page)) {
|
|
int res;
|
|
struct writeback_control wbc = {
|
|
.sync_mode = WB_SYNC_NONE,
|
|
.nr_to_write = SWAP_CLUSTER_MAX,
|
|
.range_start = 0,
|
|
.range_end = LLONG_MAX,
|
|
.for_reclaim = 1,
|
|
};
|
|
|
|
SetPageReclaim(page);
|
|
res = mapping->a_ops->writepage(page, &wbc);
|
|
if (res < 0)
|
|
handle_write_error(mapping, page, res);
|
|
if (res == AOP_WRITEPAGE_ACTIVATE) {
|
|
ClearPageReclaim(page);
|
|
return PAGE_ACTIVATE;
|
|
}
|
|
|
|
if (!PageWriteback(page)) {
|
|
/* synchronous write or broken a_ops? */
|
|
ClearPageReclaim(page);
|
|
if (PageError(page) && PageSwapCache(page)) {
|
|
ClearPageError(page);
|
|
/*
|
|
* We lock the page here because it is required
|
|
* to free the swp space later in
|
|
* shrink_page_list. But the page may be
|
|
* unclocked by functions like
|
|
* handle_write_error.
|
|
*/
|
|
__set_page_locked(page);
|
|
return PAGE_ACTIVATE;
|
|
}
|
|
}
|
|
trace_mm_vmscan_writepage(page, trace_reclaim_flags(page));
|
|
inc_zone_page_state(page, NR_VMSCAN_WRITE);
|
|
return PAGE_SUCCESS;
|
|
}
|
|
|
|
return PAGE_CLEAN;
|
|
}
|
|
|
|
/*
|
|
* Same as remove_mapping, but if the page is removed from the mapping, it
|
|
* gets returned with a refcount of 0.
|
|
*/
|
|
static int __remove_mapping(struct address_space *mapping, struct page *page)
|
|
{
|
|
BUG_ON(!PageLocked(page));
|
|
BUG_ON(mapping != page_mapping(page));
|
|
|
|
spin_lock_irq(&mapping->tree_lock);
|
|
/*
|
|
* The non racy check for a busy page.
|
|
*
|
|
* Must be careful with the order of the tests. When someone has
|
|
* a ref to the page, it may be possible that they dirty it then
|
|
* drop the reference. So if PageDirty is tested before page_count
|
|
* here, then the following race may occur:
|
|
*
|
|
* get_user_pages(&page);
|
|
* [user mapping goes away]
|
|
* write_to(page);
|
|
* !PageDirty(page) [good]
|
|
* SetPageDirty(page);
|
|
* put_page(page);
|
|
* !page_count(page) [good, discard it]
|
|
*
|
|
* [oops, our write_to data is lost]
|
|
*
|
|
* Reversing the order of the tests ensures such a situation cannot
|
|
* escape unnoticed. The smp_rmb is needed to ensure the page->flags
|
|
* load is not satisfied before that of page->_count.
|
|
*
|
|
* Note that if SetPageDirty is always performed via set_page_dirty,
|
|
* and thus under tree_lock, then this ordering is not required.
|
|
*/
|
|
if (!page_freeze_refs(page, 2))
|
|
goto cannot_free;
|
|
/* note: atomic_cmpxchg in page_freeze_refs provides the smp_rmb */
|
|
if (unlikely(PageDirty(page))) {
|
|
page_unfreeze_refs(page, 2);
|
|
goto cannot_free;
|
|
}
|
|
|
|
if (PageSwapCache(page)) {
|
|
swp_entry_t swap = { .val = page_private(page) };
|
|
__delete_from_swap_cache(page);
|
|
spin_unlock_irq(&mapping->tree_lock);
|
|
swapcache_free(swap, page);
|
|
} else {
|
|
void (*freepage)(struct page *);
|
|
|
|
freepage = mapping->a_ops->freepage;
|
|
|
|
__delete_from_page_cache(page);
|
|
spin_unlock_irq(&mapping->tree_lock);
|
|
mem_cgroup_uncharge_cache_page(page);
|
|
|
|
if (freepage != NULL)
|
|
freepage(page);
|
|
}
|
|
|
|
return 1;
|
|
|
|
cannot_free:
|
|
spin_unlock_irq(&mapping->tree_lock);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Attempt to detach a locked page from its ->mapping. If it is dirty or if
|
|
* someone else has a ref on the page, abort and return 0. If it was
|
|
* successfully detached, return 1. Assumes the caller has a single ref on
|
|
* this page.
|
|
*/
|
|
int remove_mapping(struct address_space *mapping, struct page *page)
|
|
{
|
|
if (__remove_mapping(mapping, page)) {
|
|
/*
|
|
* Unfreezing the refcount with 1 rather than 2 effectively
|
|
* drops the pagecache ref for us without requiring another
|
|
* atomic operation.
|
|
*/
|
|
page_unfreeze_refs(page, 1);
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* putback_lru_page - put previously isolated page onto appropriate LRU list
|
|
* @page: page to be put back to appropriate lru list
|
|
*
|
|
* Add previously isolated @page to appropriate LRU list.
|
|
* Page may still be unevictable for other reasons.
|
|
*
|
|
* lru_lock must not be held, interrupts must be enabled.
|
|
*/
|
|
void putback_lru_page(struct page *page)
|
|
{
|
|
int lru;
|
|
int active = !!TestClearPageActive(page);
|
|
int was_unevictable = PageUnevictable(page);
|
|
|
|
VM_BUG_ON(PageLRU(page));
|
|
|
|
redo:
|
|
ClearPageUnevictable(page);
|
|
|
|
if (page_evictable(page)) {
|
|
/*
|
|
* For evictable pages, we can use the cache.
|
|
* In event of a race, worst case is we end up with an
|
|
* unevictable page on [in]active list.
|
|
* We know how to handle that.
|
|
*/
|
|
lru = active + page_lru_base_type(page);
|
|
lru_cache_add_lru(page, lru);
|
|
} else {
|
|
/*
|
|
* Put unevictable pages directly on zone's unevictable
|
|
* list.
|
|
*/
|
|
lru = LRU_UNEVICTABLE;
|
|
add_page_to_unevictable_list(page);
|
|
/*
|
|
* When racing with an mlock or AS_UNEVICTABLE clearing
|
|
* (page is unlocked) make sure that if the other thread
|
|
* does not observe our setting of PG_lru and fails
|
|
* isolation/check_move_unevictable_pages,
|
|
* we see PG_mlocked/AS_UNEVICTABLE cleared below and move
|
|
* the page back to the evictable list.
|
|
*
|
|
* The other side is TestClearPageMlocked() or shmem_lock().
|
|
*/
|
|
smp_mb();
|
|
}
|
|
|
|
/*
|
|
* page's status can change while we move it among lru. If an evictable
|
|
* page is on unevictable list, it never be freed. To avoid that,
|
|
* check after we added it to the list, again.
|
|
*/
|
|
if (lru == LRU_UNEVICTABLE && page_evictable(page)) {
|
|
if (!isolate_lru_page(page)) {
|
|
put_page(page);
|
|
goto redo;
|
|
}
|
|
/* This means someone else dropped this page from LRU
|
|
* So, it will be freed or putback to LRU again. There is
|
|
* nothing to do here.
|
|
*/
|
|
}
|
|
|
|
if (was_unevictable && lru != LRU_UNEVICTABLE)
|
|
count_vm_event(UNEVICTABLE_PGRESCUED);
|
|
else if (!was_unevictable && lru == LRU_UNEVICTABLE)
|
|
count_vm_event(UNEVICTABLE_PGCULLED);
|
|
|
|
put_page(page); /* drop ref from isolate */
|
|
}
|
|
|
|
enum page_references {
|
|
PAGEREF_RECLAIM,
|
|
PAGEREF_RECLAIM_CLEAN,
|
|
PAGEREF_KEEP,
|
|
PAGEREF_ACTIVATE,
|
|
};
|
|
|
|
static enum page_references page_check_references(struct page *page,
|
|
struct scan_control *sc)
|
|
{
|
|
int referenced_ptes, referenced_page;
|
|
unsigned long vm_flags;
|
|
|
|
referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup,
|
|
&vm_flags);
|
|
referenced_page = TestClearPageReferenced(page);
|
|
|
|
/*
|
|
* Mlock lost the isolation race with us. Let try_to_unmap()
|
|
* move the page to the unevictable list.
|
|
*/
|
|
if (vm_flags & VM_LOCKED)
|
|
return PAGEREF_RECLAIM;
|
|
|
|
if (referenced_ptes) {
|
|
if (PageSwapBacked(page))
|
|
return PAGEREF_ACTIVATE;
|
|
/*
|
|
* All mapped pages start out with page table
|
|
* references from the instantiating fault, so we need
|
|
* to look twice if a mapped file page is used more
|
|
* than once.
|
|
*
|
|
* Mark it and spare it for another trip around the
|
|
* inactive list. Another page table reference will
|
|
* lead to its activation.
|
|
*
|
|
* Note: the mark is set for activated pages as well
|
|
* so that recently deactivated but used pages are
|
|
* quickly recovered.
|
|
*/
|
|
SetPageReferenced(page);
|
|
|
|
if (referenced_page || referenced_ptes > 1)
|
|
return PAGEREF_ACTIVATE;
|
|
|
|
/*
|
|
* Activate file-backed executable pages after first usage.
|
|
*/
|
|
if (vm_flags & VM_EXEC)
|
|
return PAGEREF_ACTIVATE;
|
|
|
|
return PAGEREF_KEEP;
|
|
}
|
|
|
|
/* Reclaim if clean, defer dirty pages to writeback */
|
|
if (referenced_page && !PageSwapBacked(page))
|
|
return PAGEREF_RECLAIM_CLEAN;
|
|
|
|
return PAGEREF_RECLAIM;
|
|
}
|
|
|
|
/* Check if a page is dirty or under writeback */
|
|
static void page_check_dirty_writeback(struct page *page,
|
|
bool *dirty, bool *writeback)
|
|
{
|
|
struct address_space *mapping;
|
|
|
|
/*
|
|
* Anonymous pages are not handled by flushers and must be written
|
|
* from reclaim context. Do not stall reclaim based on them
|
|
*/
|
|
if (!page_is_file_cache(page)) {
|
|
*dirty = false;
|
|
*writeback = false;
|
|
return;
|
|
}
|
|
|
|
/* By default assume that the page flags are accurate */
|
|
*dirty = PageDirty(page);
|
|
*writeback = PageWriteback(page);
|
|
|
|
/* Verify dirty/writeback state if the filesystem supports it */
|
|
if (!page_has_private(page))
|
|
return;
|
|
|
|
mapping = page_mapping(page);
|
|
if (mapping && mapping->a_ops->is_dirty_writeback)
|
|
mapping->a_ops->is_dirty_writeback(page, dirty, writeback);
|
|
}
|
|
|
|
/*
|
|
* shrink_page_list() returns the number of reclaimed pages
|
|
*/
|
|
static unsigned long shrink_page_list(struct list_head *page_list,
|
|
struct zone *zone,
|
|
struct scan_control *sc,
|
|
enum ttu_flags ttu_flags,
|
|
unsigned long *ret_nr_dirty,
|
|
unsigned long *ret_nr_unqueued_dirty,
|
|
unsigned long *ret_nr_congested,
|
|
unsigned long *ret_nr_writeback,
|
|
unsigned long *ret_nr_immediate,
|
|
bool force_reclaim)
|
|
{
|
|
LIST_HEAD(ret_pages);
|
|
LIST_HEAD(free_pages);
|
|
int pgactivate = 0;
|
|
unsigned long nr_unqueued_dirty = 0;
|
|
unsigned long nr_dirty = 0;
|
|
unsigned long nr_congested = 0;
|
|
unsigned long nr_reclaimed = 0;
|
|
unsigned long nr_writeback = 0;
|
|
unsigned long nr_immediate = 0;
|
|
|
|
cond_resched();
|
|
|
|
mem_cgroup_uncharge_start();
|
|
while (!list_empty(page_list)) {
|
|
struct address_space *mapping;
|
|
struct page *page;
|
|
int may_enter_fs;
|
|
enum page_references references = PAGEREF_RECLAIM;
|
|
bool dirty, writeback;
|
|
|
|
cond_resched();
|
|
|
|
page = lru_to_page(page_list);
|
|
list_del(&page->lru);
|
|
|
|
if (!trylock_page(page))
|
|
goto keep;
|
|
|
|
VM_BUG_ON(PageActive(page));
|
|
if (zone)
|
|
VM_BUG_ON(page_zone(page) != zone);
|
|
|
|
sc->nr_scanned++;
|
|
|
|
if (unlikely(!page_evictable(page)))
|
|
goto cull_mlocked;
|
|
|
|
if (!sc->may_unmap && page_mapped(page))
|
|
goto keep_locked;
|
|
|
|
/* Double the slab pressure for mapped and swapcache pages */
|
|
if (page_mapped(page) || PageSwapCache(page))
|
|
sc->nr_scanned++;
|
|
|
|
may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
|
|
(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
|
|
|
|
/*
|
|
* The number of dirty pages determines if a zone is marked
|
|
* reclaim_congested which affects wait_iff_congested. kswapd
|
|
* will stall and start writing pages if the tail of the LRU
|
|
* is all dirty unqueued pages.
|
|
*/
|
|
page_check_dirty_writeback(page, &dirty, &writeback);
|
|
if (dirty || writeback)
|
|
nr_dirty++;
|
|
|
|
if (dirty && !writeback)
|
|
nr_unqueued_dirty++;
|
|
|
|
/*
|
|
* Treat this page as congested if the underlying BDI is or if
|
|
* pages are cycling through the LRU so quickly that the
|
|
* pages marked for immediate reclaim are making it to the
|
|
* end of the LRU a second time.
|
|
*/
|
|
mapping = page_mapping(page);
|
|
if ((mapping && bdi_write_congested(mapping->backing_dev_info)) ||
|
|
(writeback && PageReclaim(page)))
|
|
nr_congested++;
|
|
|
|
/*
|
|
* If a page at the tail of the LRU is under writeback, there
|
|
* are three cases to consider.
|
|
*
|
|
* 1) If reclaim is encountering an excessive number of pages
|
|
* under writeback and this page is both under writeback and
|
|
* PageReclaim then it indicates that pages are being queued
|
|
* for IO but are being recycled through the LRU before the
|
|
* IO can complete. Waiting on the page itself risks an
|
|
* indefinite stall if it is impossible to writeback the
|
|
* page due to IO error or disconnected storage so instead
|
|
* note that the LRU is being scanned too quickly and the
|
|
* caller can stall after page list has been processed.
|
|
*
|
|
* 2) Global reclaim encounters a page, memcg encounters a
|
|
* page that is not marked for immediate reclaim or
|
|
* the caller does not have __GFP_IO. In this case mark
|
|
* the page for immediate reclaim and continue scanning.
|
|
*
|
|
* __GFP_IO is checked because a loop driver thread might
|
|
* enter reclaim, and deadlock if it waits on a page for
|
|
* which it is needed to do the write (loop masks off
|
|
* __GFP_IO|__GFP_FS for this reason); but more thought
|
|
* would probably show more reasons.
|
|
*
|
|
* Don't require __GFP_FS, since we're not going into the
|
|
* FS, just waiting on its writeback completion. Worryingly,
|
|
* ext4 gfs2 and xfs allocate pages with
|
|
* grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so testing
|
|
* may_enter_fs here is liable to OOM on them.
|
|
*
|
|
* 3) memcg encounters a page that is not already marked
|
|
* PageReclaim. memcg does not have any dirty pages
|
|
* throttling so we could easily OOM just because too many
|
|
* pages are in writeback and there is nothing else to
|
|
* reclaim. Wait for the writeback to complete.
|
|
*/
|
|
if (PageWriteback(page)) {
|
|
/* Case 1 above */
|
|
if (current_is_kswapd() &&
|
|
PageReclaim(page) &&
|
|
zone_is_reclaim_writeback(zone)) {
|
|
nr_immediate++;
|
|
goto keep_locked;
|
|
|
|
/* Case 2 above */
|
|
} else if (global_reclaim(sc) ||
|
|
!PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) {
|
|
/*
|
|
* This is slightly racy - end_page_writeback()
|
|
* might have just cleared PageReclaim, then
|
|
* setting PageReclaim here end up interpreted
|
|
* as PageReadahead - but that does not matter
|
|
* enough to care. What we do want is for this
|
|
* page to have PageReclaim set next time memcg
|
|
* reclaim reaches the tests above, so it will
|
|
* then wait_on_page_writeback() to avoid OOM;
|
|
* and it's also appropriate in global reclaim.
|
|
*/
|
|
SetPageReclaim(page);
|
|
nr_writeback++;
|
|
|
|
goto keep_locked;
|
|
|
|
/* Case 3 above */
|
|
} else {
|
|
wait_on_page_writeback(page);
|
|
}
|
|
}
|
|
|
|
if (!force_reclaim)
|
|
references = page_check_references(page, sc);
|
|
|
|
switch (references) {
|
|
case PAGEREF_ACTIVATE:
|
|
goto activate_locked;
|
|
case PAGEREF_KEEP:
|
|
goto keep_locked;
|
|
case PAGEREF_RECLAIM:
|
|
case PAGEREF_RECLAIM_CLEAN:
|
|
; /* try to reclaim the page below */
|
|
}
|
|
|
|
/*
|
|
* Anonymous process memory has backing store?
|
|
* Try to allocate it some swap space here.
|
|
*/
|
|
if (PageAnon(page) && !PageSwapCache(page)) {
|
|
if (!(sc->gfp_mask & __GFP_IO))
|
|
goto keep_locked;
|
|
if (!add_to_swap(page, page_list))
|
|
goto activate_locked;
|
|
may_enter_fs = 1;
|
|
|
|
/* Adding to swap updated mapping */
|
|
mapping = page_mapping(page);
|
|
}
|
|
|
|
/*
|
|
* The page is mapped into the page tables of one or more
|
|
* processes. Try to unmap it here.
|
|
*/
|
|
if (page_mapped(page) && mapping) {
|
|
switch (try_to_unmap(page,
|
|
ttu_flags, sc->target_vma)) {
|
|
case SWAP_FAIL:
|
|
goto activate_locked;
|
|
case SWAP_AGAIN:
|
|
goto keep_locked;
|
|
case SWAP_MLOCK:
|
|
goto cull_mlocked;
|
|
case SWAP_SUCCESS:
|
|
; /* try to free the page below */
|
|
}
|
|
}
|
|
|
|
if (PageDirty(page)) {
|
|
/*
|
|
* Only kswapd can writeback filesystem pages to
|
|
* avoid risk of stack overflow but only writeback
|
|
* if many dirty pages have been encountered.
|
|
*/
|
|
if (page_is_file_cache(page) &&
|
|
(!current_is_kswapd() ||
|
|
(zone && !zone_is_reclaim_dirty(zone)))) {
|
|
/*
|
|
* Immediately reclaim when written back.
|
|
* Similar in principal to deactivate_page()
|
|
* except we already have the page isolated
|
|
* and know it's dirty
|
|
*/
|
|
inc_zone_page_state(page, NR_VMSCAN_IMMEDIATE);
|
|
SetPageReclaim(page);
|
|
|
|
goto keep_locked;
|
|
}
|
|
|
|
if (references == PAGEREF_RECLAIM_CLEAN)
|
|
goto keep_locked;
|
|
if (!may_enter_fs)
|
|
goto keep_locked;
|
|
if (!sc->may_writepage)
|
|
goto keep_locked;
|
|
|
|
/* Page is dirty, try to write it out here */
|
|
switch (pageout(page, mapping, sc)) {
|
|
case PAGE_KEEP:
|
|
goto keep_locked;
|
|
case PAGE_ACTIVATE:
|
|
goto activate_locked;
|
|
case PAGE_SUCCESS:
|
|
if (PageWriteback(page))
|
|
goto keep;
|
|
if (PageDirty(page))
|
|
goto keep;
|
|
|
|
/*
|
|
* A synchronous write - probably a ramdisk. Go
|
|
* ahead and try to reclaim the page.
|
|
*/
|
|
if (!trylock_page(page))
|
|
goto keep;
|
|
if (PageDirty(page) || PageWriteback(page))
|
|
goto keep_locked;
|
|
mapping = page_mapping(page);
|
|
case PAGE_CLEAN:
|
|
; /* try to free the page below */
|
|
}
|
|
}
|
|
|
|
/*
|
|
* If the page has buffers, try to free the buffer mappings
|
|
* associated with this page. If we succeed we try to free
|
|
* the page as well.
|
|
*
|
|
* We do this even if the page is PageDirty().
|
|
* try_to_release_page() does not perform I/O, but it is
|
|
* possible for a page to have PageDirty set, but it is actually
|
|
* clean (all its buffers are clean). This happens if the
|
|
* buffers were written out directly, with submit_bh(). ext3
|
|
* will do this, as well as the blockdev mapping.
|
|
* try_to_release_page() will discover that cleanness and will
|
|
* drop the buffers and mark the page clean - it can be freed.
|
|
*
|
|
* Rarely, pages can have buffers and no ->mapping. These are
|
|
* the pages which were not successfully invalidated in
|
|
* truncate_complete_page(). We try to drop those buffers here
|
|
* and if that worked, and the page is no longer mapped into
|
|
* process address space (page_count == 1) it can be freed.
|
|
* Otherwise, leave the page on the LRU so it is swappable.
|
|
*/
|
|
if (page_has_private(page)) {
|
|
if (!try_to_release_page(page, sc->gfp_mask))
|
|
goto activate_locked;
|
|
if (!mapping && page_count(page) == 1) {
|
|
unlock_page(page);
|
|
if (put_page_testzero(page))
|
|
goto free_it;
|
|
else {
|
|
/*
|
|
* rare race with speculative reference.
|
|
* the speculative reference will free
|
|
* this page shortly, so we may
|
|
* increment nr_reclaimed here (and
|
|
* leave it off the LRU).
|
|
*/
|
|
nr_reclaimed++;
|
|
continue;
|
|
}
|
|
}
|
|
}
|
|
|
|
if (!mapping || !__remove_mapping(mapping, page))
|
|
goto keep_locked;
|
|
|
|
/*
|
|
* At this point, we have no other references and there is
|
|
* no way to pick any more up (removed from LRU, removed
|
|
* from pagecache). Can use non-atomic bitops now (and
|
|
* we obviously don't have to worry about waking up a process
|
|
* waiting on the page lock, because there are no references.
|
|
*/
|
|
__clear_page_locked(page);
|
|
free_it:
|
|
nr_reclaimed++;
|
|
|
|
/*
|
|
* Is there need to periodically free_page_list? It would
|
|
* appear not as the counts should be low
|
|
*/
|
|
list_add(&page->lru, &free_pages);
|
|
/*
|
|
* If pagelist are from multiple zones, we should decrease
|
|
* NR_ISOLATED_ANON + x on freed pages in here.
|
|
*/
|
|
if (!zone)
|
|
dec_zone_page_state(page, NR_ISOLATED_ANON +
|
|
page_is_file_cache(page));
|
|
continue;
|
|
|
|
cull_mlocked:
|
|
if (PageSwapCache(page))
|
|
try_to_free_swap(page);
|
|
unlock_page(page);
|
|
putback_lru_page(page);
|
|
continue;
|
|
|
|
activate_locked:
|
|
/* Not a candidate for swapping, so reclaim swap space. */
|
|
if (PageSwapCache(page) && vm_swap_full(page_swap_info(page)))
|
|
try_to_free_swap(page);
|
|
VM_BUG_ON(PageActive(page));
|
|
SetPageActive(page);
|
|
pgactivate++;
|
|
keep_locked:
|
|
unlock_page(page);
|
|
keep:
|
|
list_add(&page->lru, &ret_pages);
|
|
VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
|
|
}
|
|
|
|
free_hot_cold_page_list(&free_pages, 1);
|
|
|
|
list_splice(&ret_pages, page_list);
|
|
count_vm_events(PGACTIVATE, pgactivate);
|
|
mem_cgroup_uncharge_end();
|
|
*ret_nr_dirty += nr_dirty;
|
|
*ret_nr_congested += nr_congested;
|
|
*ret_nr_unqueued_dirty += nr_unqueued_dirty;
|
|
*ret_nr_writeback += nr_writeback;
|
|
*ret_nr_immediate += nr_immediate;
|
|
return nr_reclaimed;
|
|
}
|
|
|
|
unsigned long reclaim_clean_pages_from_list(struct zone *zone,
|
|
struct list_head *page_list)
|
|
{
|
|
struct scan_control sc = {
|
|
.gfp_mask = GFP_KERNEL,
|
|
.priority = DEF_PRIORITY,
|
|
.may_unmap = 1,
|
|
/* Doesn't allow to write out dirty page */
|
|
.may_writepage = 0,
|
|
};
|
|
unsigned long ret, dummy1, dummy2, dummy3, dummy4, dummy5;
|
|
struct page *page, *next;
|
|
LIST_HEAD(clean_pages);
|
|
|
|
list_for_each_entry_safe(page, next, page_list, lru) {
|
|
if (page_is_file_cache(page) && !PageDirty(page) &&
|
|
!isolated_balloon_page(page)) {
|
|
ClearPageActive(page);
|
|
list_move(&page->lru, &clean_pages);
|
|
}
|
|
}
|
|
|
|
ret = shrink_page_list(&clean_pages, zone, &sc,
|
|
TTU_UNMAP|TTU_IGNORE_ACCESS,
|
|
&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
|
|
list_splice(&clean_pages, page_list);
|
|
__mod_zone_page_state(zone, NR_ISOLATED_FILE, -ret);
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_PROCESS_RECLAIM
|
|
unsigned long reclaim_pages_from_list(struct list_head *page_list,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
struct scan_control sc = {
|
|
.gfp_mask = GFP_KERNEL,
|
|
.priority = DEF_PRIORITY,
|
|
.may_writepage = 1,
|
|
.may_unmap = 1,
|
|
.may_swap = 1,
|
|
.target_vma = vma,
|
|
};
|
|
|
|
unsigned long nr_reclaimed;
|
|
struct page *page;
|
|
unsigned long dummy1, dummy2, dummy3, dummy4, dummy5;
|
|
|
|
list_for_each_entry(page, page_list, lru)
|
|
ClearPageActive(page);
|
|
|
|
nr_reclaimed = shrink_page_list(page_list, NULL, &sc,
|
|
TTU_UNMAP|TTU_IGNORE_ACCESS,
|
|
&dummy1, &dummy2, &dummy3, &dummy4, &dummy5, true);
|
|
|
|
while (!list_empty(page_list)) {
|
|
page = lru_to_page(page_list);
|
|
list_del(&page->lru);
|
|
dec_zone_page_state(page, NR_ISOLATED_ANON +
|
|
page_is_file_cache(page));
|
|
putback_lru_page(page);
|
|
}
|
|
|
|
return nr_reclaimed;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Attempt to remove the specified page from its LRU. Only take this page
|
|
* if it is of the appropriate PageActive status. Pages which are being
|
|
* freed elsewhere are also ignored.
|
|
*
|
|
* page: page to consider
|
|
* mode: one of the LRU isolation modes defined above
|
|
*
|
|
* returns 0 on success, -ve errno on failure.
|
|
*/
|
|
int __isolate_lru_page(struct page *page, isolate_mode_t mode)
|
|
{
|
|
int ret = -EINVAL;
|
|
|
|
/* Only take pages on the LRU. */
|
|
if (!PageLRU(page))
|
|
return ret;
|
|
|
|
/* Compaction should not handle unevictable pages but CMA can do so */
|
|
if (PageUnevictable(page) && !(mode & ISOLATE_UNEVICTABLE))
|
|
return ret;
|
|
|
|
ret = -EBUSY;
|
|
|
|
/*
|
|
* To minimise LRU disruption, the caller can indicate that it only
|
|
* wants to isolate pages it will be able to operate on without
|
|
* blocking - clean pages for the most part.
|
|
*
|
|
* ISOLATE_CLEAN means that only clean pages should be isolated. This
|
|
* is used by reclaim when it is cannot write to backing storage
|
|
*
|
|
* ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages
|
|
* that it is possible to migrate without blocking
|
|
*/
|
|
if (mode & (ISOLATE_CLEAN|ISOLATE_ASYNC_MIGRATE)) {
|
|
/* All the caller can do on PageWriteback is block */
|
|
if (PageWriteback(page))
|
|
return ret;
|
|
|
|
if (PageDirty(page)) {
|
|
struct address_space *mapping;
|
|
|
|
/* ISOLATE_CLEAN means only clean pages */
|
|
if (mode & ISOLATE_CLEAN)
|
|
return ret;
|
|
|
|
/*
|
|
* Only pages without mappings or that have a
|
|
* ->migratepage callback are possible to migrate
|
|
* without blocking
|
|
*/
|
|
mapping = page_mapping(page);
|
|
if (mapping && !mapping->a_ops->migratepage)
|
|
return ret;
|
|
}
|
|
}
|
|
|
|
if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
|
|
return ret;
|
|
|
|
if (likely(get_page_unless_zero(page))) {
|
|
/*
|
|
* Be careful not to clear PageLRU until after we're
|
|
* sure the page is not being freed elsewhere -- the
|
|
* page release code relies on it.
|
|
*/
|
|
ClearPageLRU(page);
|
|
ret = 0;
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* zone->lru_lock is heavily contended. Some of the functions that
|
|
* shrink the lists perform better by taking out a batch of pages
|
|
* and working on them outside the LRU lock.
|
|
*
|
|
* For pagecache intensive workloads, this function is the hottest
|
|
* spot in the kernel (apart from copy_*_user functions).
|
|
*
|
|
* Appropriate locks must be held before calling this function.
|
|
*
|
|
* @nr_to_scan: The number of pages to look through on the list.
|
|
* @lruvec: The LRU vector to pull pages from.
|
|
* @dst: The temp list to put pages on to.
|
|
* @nr_scanned: The number of pages that were scanned.
|
|
* @sc: The scan_control struct for this reclaim session
|
|
* @mode: One of the LRU isolation modes
|
|
* @lru: LRU list id for isolating
|
|
*
|
|
* returns how many pages were moved onto *@dst.
|
|
*/
|
|
static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
|
|
struct lruvec *lruvec, struct list_head *dst,
|
|
unsigned long *nr_scanned, struct scan_control *sc,
|
|
isolate_mode_t mode, enum lru_list lru)
|
|
{
|
|
struct list_head *src = &lruvec->lists[lru];
|
|
unsigned long nr_taken = 0;
|
|
unsigned long scan;
|
|
|
|
for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
|
|
struct page *page;
|
|
int nr_pages;
|
|
|
|
page = lru_to_page(src);
|
|
prefetchw_prev_lru_page(page, src, flags);
|
|
|
|
VM_BUG_ON(!PageLRU(page));
|
|
|
|
switch (__isolate_lru_page(page, mode)) {
|
|
case 0:
|
|
nr_pages = hpage_nr_pages(page);
|
|
mem_cgroup_update_lru_size(lruvec, lru, -nr_pages);
|
|
list_move(&page->lru, dst);
|
|
nr_taken += nr_pages;
|
|
break;
|
|
|
|
case -EBUSY:
|
|
/* else it is being freed elsewhere */
|
|
list_move(&page->lru, src);
|
|
continue;
|
|
|
|
default:
|
|
BUG();
|
|
}
|
|
}
|
|
|
|
*nr_scanned = scan;
|
|
trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan,
|
|
nr_taken, mode, is_file_lru(lru));
|
|
return nr_taken;
|
|
}
|
|
|
|
/**
|
|
* isolate_lru_page - tries to isolate a page from its LRU list
|
|
* @page: page to isolate from its LRU list
|
|
*
|
|
* Isolates a @page from an LRU list, clears PageLRU and adjusts the
|
|
* vmstat statistic corresponding to whatever LRU list the page was on.
|
|
*
|
|
* Returns 0 if the page was removed from an LRU list.
|
|
* Returns -EBUSY if the page was not on an LRU list.
|
|
*
|
|
* The returned page will have PageLRU() cleared. If it was found on
|
|
* the active list, it will have PageActive set. If it was found on
|
|
* the unevictable list, it will have the PageUnevictable bit set. That flag
|
|
* may need to be cleared by the caller before letting the page go.
|
|
*
|
|
* The vmstat statistic corresponding to the list on which the page was
|
|
* found will be decremented.
|
|
*
|
|
* Restrictions:
|
|
* (1) Must be called with an elevated refcount on the page. This is a
|
|
* fundamentnal difference from isolate_lru_pages (which is called
|
|
* without a stable reference).
|
|
* (2) the lru_lock must not be held.
|
|
* (3) interrupts must be enabled.
|
|
*/
|
|
int isolate_lru_page(struct page *page)
|
|
{
|
|
int ret = -EBUSY;
|
|
|
|
VM_BUG_ON(!page_count(page));
|
|
|
|
if (PageLRU(page)) {
|
|
struct zone *zone = page_zone(page);
|
|
struct lruvec *lruvec;
|
|
|
|
spin_lock_irq(&zone->lru_lock);
|
|
lruvec = mem_cgroup_page_lruvec(page, zone);
|
|
if (PageLRU(page)) {
|
|
int lru = page_lru(page);
|
|
get_page(page);
|
|
ClearPageLRU(page);
|
|
del_page_from_lru_list(page, lruvec, lru);
|
|
ret = 0;
|
|
}
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
static int __too_many_isolated(struct zone *zone, int file,
|
|
struct scan_control *sc, int safe)
|
|
{
|
|
unsigned long inactive, isolated;
|
|
|
|
if (file) {
|
|
if (safe) {
|
|
inactive = zone_page_state_snapshot(zone,
|
|
NR_INACTIVE_FILE);
|
|
isolated = zone_page_state_snapshot(zone,
|
|
NR_ISOLATED_FILE);
|
|
} else {
|
|
inactive = zone_page_state(zone, NR_INACTIVE_FILE);
|
|
isolated = zone_page_state(zone, NR_ISOLATED_FILE);
|
|
}
|
|
} else {
|
|
if (safe) {
|
|
inactive = zone_page_state_snapshot(zone,
|
|
NR_INACTIVE_ANON);
|
|
isolated = zone_page_state_snapshot(zone,
|
|
NR_ISOLATED_ANON);
|
|
} else {
|
|
inactive = zone_page_state(zone, NR_INACTIVE_ANON);
|
|
isolated = zone_page_state(zone, NR_ISOLATED_ANON);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they
|
|
* won't get blocked by normal direct-reclaimers, forming a circular
|
|
* deadlock.
|
|
*/
|
|
if ((sc->gfp_mask & GFP_IOFS) == GFP_IOFS)
|
|
inactive >>= 3;
|
|
|
|
return isolated > inactive;
|
|
}
|
|
|
|
/*
|
|
* A direct reclaimer may isolate SWAP_CLUSTER_MAX pages from the LRU list and
|
|
* then get resheduled. When there are massive number of tasks doing page
|
|
* allocation, such sleeping direct reclaimers may keep piling up on each CPU,
|
|
* the LRU list will go small and be scanned faster than necessary, leading to
|
|
* unnecessary swapping, thrashing and OOM.
|
|
*/
|
|
static int too_many_isolated(struct zone *zone, int file,
|
|
struct scan_control *sc, int safe)
|
|
{
|
|
if (current_is_kswapd())
|
|
return 0;
|
|
|
|
if (!global_reclaim(sc))
|
|
return 0;
|
|
|
|
if (unlikely(__too_many_isolated(zone, file, sc, 0))) {
|
|
if (safe)
|
|
return __too_many_isolated(zone, file, sc, safe);
|
|
else
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static noinline_for_stack void
|
|
putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
|
|
{
|
|
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
|
|
struct zone *zone = lruvec_zone(lruvec);
|
|
LIST_HEAD(pages_to_free);
|
|
|
|
/*
|
|
* Put back any unfreeable pages.
|
|
*/
|
|
while (!list_empty(page_list)) {
|
|
struct page *page = lru_to_page(page_list);
|
|
int lru;
|
|
|
|
VM_BUG_ON(PageLRU(page));
|
|
list_del(&page->lru);
|
|
if (unlikely(!page_evictable(page))) {
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
putback_lru_page(page);
|
|
spin_lock_irq(&zone->lru_lock);
|
|
continue;
|
|
}
|
|
|
|
lruvec = mem_cgroup_page_lruvec(page, zone);
|
|
|
|
SetPageLRU(page);
|
|
lru = page_lru(page);
|
|
add_page_to_lru_list(page, lruvec, lru);
|
|
|
|
if (is_active_lru(lru)) {
|
|
int file = is_file_lru(lru);
|
|
int numpages = hpage_nr_pages(page);
|
|
reclaim_stat->recent_rotated[file] += numpages;
|
|
}
|
|
if (put_page_testzero(page)) {
|
|
__ClearPageLRU(page);
|
|
__ClearPageActive(page);
|
|
del_page_from_lru_list(page, lruvec, lru);
|
|
|
|
if (unlikely(PageCompound(page))) {
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
(*get_compound_page_dtor(page))(page);
|
|
spin_lock_irq(&zone->lru_lock);
|
|
} else
|
|
list_add(&page->lru, &pages_to_free);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* To save our caller's stack, now use input list for pages to free.
|
|
*/
|
|
list_splice(&pages_to_free, page_list);
|
|
}
|
|
|
|
/*
|
|
* shrink_inactive_list() is a helper for shrink_zone(). It returns the number
|
|
* of reclaimed pages
|
|
*/
|
|
static noinline_for_stack unsigned long
|
|
shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
|
|
struct scan_control *sc, enum lru_list lru)
|
|
{
|
|
LIST_HEAD(page_list);
|
|
unsigned long nr_scanned;
|
|
unsigned long nr_reclaimed = 0;
|
|
unsigned long nr_taken;
|
|
unsigned long nr_dirty = 0;
|
|
unsigned long nr_congested = 0;
|
|
unsigned long nr_unqueued_dirty = 0;
|
|
unsigned long nr_writeback = 0;
|
|
unsigned long nr_immediate = 0;
|
|
isolate_mode_t isolate_mode = 0;
|
|
int file = is_file_lru(lru);
|
|
int safe = 0;
|
|
struct zone *zone = lruvec_zone(lruvec);
|
|
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
|
|
|
|
while (unlikely(too_many_isolated(zone, file, sc, safe))) {
|
|
congestion_wait(BLK_RW_ASYNC, HZ/10);
|
|
|
|
/* We are about to die and free our memory. Return now. */
|
|
if (fatal_signal_pending(current))
|
|
return SWAP_CLUSTER_MAX;
|
|
|
|
safe = 1;
|
|
}
|
|
|
|
lru_add_drain();
|
|
|
|
if (!sc->may_unmap)
|
|
isolate_mode |= ISOLATE_UNMAPPED;
|
|
if (!sc->may_writepage)
|
|
isolate_mode |= ISOLATE_CLEAN;
|
|
|
|
spin_lock_irq(&zone->lru_lock);
|
|
|
|
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &page_list,
|
|
&nr_scanned, sc, isolate_mode, lru);
|
|
|
|
__mod_zone_page_state(zone, NR_LRU_BASE + lru, -nr_taken);
|
|
__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
|
|
|
|
if (global_reclaim(sc)) {
|
|
zone->pages_scanned += nr_scanned;
|
|
if (current_is_kswapd())
|
|
__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scanned);
|
|
else
|
|
__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned);
|
|
}
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
|
|
if (nr_taken == 0)
|
|
return 0;
|
|
|
|
nr_reclaimed = shrink_page_list(&page_list, zone, sc, TTU_UNMAP,
|
|
&nr_dirty, &nr_unqueued_dirty, &nr_congested,
|
|
&nr_writeback, &nr_immediate,
|
|
false);
|
|
|
|
spin_lock_irq(&zone->lru_lock);
|
|
|
|
reclaim_stat->recent_scanned[file] += nr_taken;
|
|
|
|
if (global_reclaim(sc)) {
|
|
if (current_is_kswapd())
|
|
__count_zone_vm_events(PGSTEAL_KSWAPD, zone,
|
|
nr_reclaimed);
|
|
else
|
|
__count_zone_vm_events(PGSTEAL_DIRECT, zone,
|
|
nr_reclaimed);
|
|
}
|
|
|
|
putback_inactive_pages(lruvec, &page_list);
|
|
|
|
__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
|
|
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
|
|
free_hot_cold_page_list(&page_list, 1);
|
|
|
|
/*
|
|
* If reclaim is isolating dirty pages under writeback, it implies
|
|
* that the long-lived page allocation rate is exceeding the page
|
|
* laundering rate. Either the global limits are not being effective
|
|
* at throttling processes due to the page distribution throughout
|
|
* zones or there is heavy usage of a slow backing device. The
|
|
* only option is to throttle from reclaim context which is not ideal
|
|
* as there is no guarantee the dirtying process is throttled in the
|
|
* same way balance_dirty_pages() manages.
|
|
*
|
|
* Once a zone is flagged ZONE_WRITEBACK, kswapd will count the number
|
|
* of pages under pages flagged for immediate reclaim and stall if any
|
|
* are encountered in the nr_immediate check below.
|
|
*/
|
|
if (nr_writeback && nr_writeback == nr_taken)
|
|
zone_set_flag(zone, ZONE_WRITEBACK);
|
|
|
|
/*
|
|
* memcg will stall in page writeback so only consider forcibly
|
|
* stalling for global reclaim
|
|
*/
|
|
if (global_reclaim(sc)) {
|
|
/*
|
|
* Tag a zone as congested if all the dirty pages scanned were
|
|
* backed by a congested BDI and wait_iff_congested will stall.
|
|
*/
|
|
if (nr_dirty && nr_dirty == nr_congested)
|
|
zone_set_flag(zone, ZONE_CONGESTED);
|
|
|
|
/*
|
|
* If dirty pages are scanned that are not queued for IO, it
|
|
* implies that flushers are not keeping up. In this case, flag
|
|
* the zone ZONE_TAIL_LRU_DIRTY and kswapd will start writing
|
|
* pages from reclaim context.
|
|
*/
|
|
if (nr_unqueued_dirty == nr_taken)
|
|
zone_set_flag(zone, ZONE_TAIL_LRU_DIRTY);
|
|
|
|
/*
|
|
* If kswapd scans pages marked marked for immediate
|
|
* reclaim and under writeback (nr_immediate), it implies
|
|
* that pages are cycling through the LRU faster than
|
|
* they are written so also forcibly stall.
|
|
*/
|
|
if (nr_immediate)
|
|
congestion_wait(BLK_RW_ASYNC, HZ/10);
|
|
}
|
|
|
|
/*
|
|
* Stall direct reclaim for IO completions if underlying BDIs or zone
|
|
* is congested. Allow kswapd to continue until it starts encountering
|
|
* unqueued dirty pages or cycling through the LRU too quickly.
|
|
*/
|
|
if (!sc->hibernation_mode && !current_is_kswapd())
|
|
wait_iff_congested(zone, BLK_RW_ASYNC, HZ/10);
|
|
|
|
trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id,
|
|
zone_idx(zone),
|
|
nr_scanned, nr_reclaimed,
|
|
sc->priority,
|
|
trace_shrink_flags(file));
|
|
return nr_reclaimed;
|
|
}
|
|
|
|
/*
|
|
* This moves pages from the active list to the inactive list.
|
|
*
|
|
* We move them the other way if the page is referenced by one or more
|
|
* processes, from rmap.
|
|
*
|
|
* If the pages are mostly unmapped, the processing is fast and it is
|
|
* appropriate to hold zone->lru_lock across the whole operation. But if
|
|
* the pages are mapped, the processing is slow (page_referenced()) so we
|
|
* should drop zone->lru_lock around each page. It's impossible to balance
|
|
* this, so instead we remove the pages from the LRU while processing them.
|
|
* It is safe to rely on PG_active against the non-LRU pages in here because
|
|
* nobody will play with that bit on a non-LRU page.
|
|
*
|
|
* The downside is that we have to touch page->_count against each page.
|
|
* But we had to alter page->flags anyway.
|
|
*/
|
|
|
|
static void move_active_pages_to_lru(struct lruvec *lruvec,
|
|
struct list_head *list,
|
|
struct list_head *pages_to_free,
|
|
enum lru_list lru)
|
|
{
|
|
struct zone *zone = lruvec_zone(lruvec);
|
|
unsigned long pgmoved = 0;
|
|
struct page *page;
|
|
int nr_pages;
|
|
|
|
while (!list_empty(list)) {
|
|
page = lru_to_page(list);
|
|
lruvec = mem_cgroup_page_lruvec(page, zone);
|
|
|
|
VM_BUG_ON(PageLRU(page));
|
|
SetPageLRU(page);
|
|
|
|
nr_pages = hpage_nr_pages(page);
|
|
mem_cgroup_update_lru_size(lruvec, lru, nr_pages);
|
|
list_move(&page->lru, &lruvec->lists[lru]);
|
|
pgmoved += nr_pages;
|
|
|
|
if (put_page_testzero(page)) {
|
|
__ClearPageLRU(page);
|
|
__ClearPageActive(page);
|
|
del_page_from_lru_list(page, lruvec, lru);
|
|
|
|
if (unlikely(PageCompound(page))) {
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
(*get_compound_page_dtor(page))(page);
|
|
spin_lock_irq(&zone->lru_lock);
|
|
} else
|
|
list_add(&page->lru, pages_to_free);
|
|
}
|
|
}
|
|
__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
|
|
if (!is_active_lru(lru))
|
|
__count_vm_events(PGDEACTIVATE, pgmoved);
|
|
}
|
|
|
|
static void shrink_active_list(unsigned long nr_to_scan,
|
|
struct lruvec *lruvec,
|
|
struct scan_control *sc,
|
|
enum lru_list lru)
|
|
{
|
|
unsigned long nr_taken;
|
|
unsigned long nr_scanned;
|
|
unsigned long vm_flags;
|
|
LIST_HEAD(l_hold); /* The pages which were snipped off */
|
|
LIST_HEAD(l_active);
|
|
LIST_HEAD(l_inactive);
|
|
struct page *page;
|
|
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
|
|
unsigned long nr_rotated = 0;
|
|
isolate_mode_t isolate_mode = 0;
|
|
int file = is_file_lru(lru);
|
|
struct zone *zone = lruvec_zone(lruvec);
|
|
|
|
lru_add_drain();
|
|
|
|
if (!sc->may_unmap)
|
|
isolate_mode |= ISOLATE_UNMAPPED;
|
|
if (!sc->may_writepage)
|
|
isolate_mode |= ISOLATE_CLEAN;
|
|
|
|
spin_lock_irq(&zone->lru_lock);
|
|
|
|
nr_taken = isolate_lru_pages(nr_to_scan, lruvec, &l_hold,
|
|
&nr_scanned, sc, isolate_mode, lru);
|
|
if (global_reclaim(sc))
|
|
zone->pages_scanned += nr_scanned;
|
|
|
|
reclaim_stat->recent_scanned[file] += nr_taken;
|
|
|
|
__count_zone_vm_events(PGREFILL, zone, nr_scanned);
|
|
__mod_zone_page_state(zone, NR_LRU_BASE + lru, -nr_taken);
|
|
__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
|
|
while (!list_empty(&l_hold)) {
|
|
cond_resched();
|
|
page = lru_to_page(&l_hold);
|
|
list_del(&page->lru);
|
|
|
|
if (unlikely(!page_evictable(page))) {
|
|
putback_lru_page(page);
|
|
continue;
|
|
}
|
|
|
|
if (unlikely(buffer_heads_over_limit)) {
|
|
if (page_has_private(page) && trylock_page(page)) {
|
|
if (page_has_private(page))
|
|
try_to_release_page(page, 0);
|
|
unlock_page(page);
|
|
}
|
|
}
|
|
|
|
if (page_referenced(page, 0, sc->target_mem_cgroup,
|
|
&vm_flags)) {
|
|
nr_rotated += hpage_nr_pages(page);
|
|
/*
|
|
* Identify referenced, file-backed active pages and
|
|
* give them one more trip around the active list. So
|
|
* that executable code get better chances to stay in
|
|
* memory under moderate memory pressure. Anon pages
|
|
* are not likely to be evicted by use-once streaming
|
|
* IO, plus JVM can create lots of anon VM_EXEC pages,
|
|
* so we ignore them here.
|
|
*/
|
|
if ((vm_flags & VM_EXEC) && page_is_file_cache(page)) {
|
|
list_add(&page->lru, &l_active);
|
|
continue;
|
|
}
|
|
}
|
|
|
|
ClearPageActive(page); /* we are de-activating */
|
|
list_add(&page->lru, &l_inactive);
|
|
}
|
|
|
|
/*
|
|
* Move pages back to the lru list.
|
|
*/
|
|
spin_lock_irq(&zone->lru_lock);
|
|
/*
|
|
* Count referenced pages from currently used mappings as rotated,
|
|
* even though only some of them are actually re-activated. This
|
|
* helps balance scan pressure between file and anonymous pages in
|
|
* get_scan_ratio.
|
|
*/
|
|
reclaim_stat->recent_rotated[file] += nr_rotated;
|
|
|
|
move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
|
|
move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
|
|
__mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
|
|
free_hot_cold_page_list(&l_hold, 1);
|
|
}
|
|
|
|
#ifdef CONFIG_SWAP
|
|
static int inactive_anon_is_low_global(struct zone *zone)
|
|
{
|
|
unsigned long active, inactive;
|
|
|
|
active = zone_page_state(zone, NR_ACTIVE_ANON);
|
|
inactive = zone_page_state(zone, NR_INACTIVE_ANON);
|
|
|
|
if (inactive * zone->inactive_ratio < active)
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* inactive_anon_is_low - check if anonymous pages need to be deactivated
|
|
* @lruvec: LRU vector to check
|
|
*
|
|
* Returns true if the zone does not have enough inactive anon pages,
|
|
* meaning some active anon pages need to be deactivated.
|
|
*/
|
|
static int inactive_anon_is_low(struct lruvec *lruvec)
|
|
{
|
|
/*
|
|
* If we don't have swap space, anonymous page deactivation
|
|
* is pointless.
|
|
*/
|
|
if (!total_swap_pages)
|
|
return 0;
|
|
|
|
if (!mem_cgroup_disabled())
|
|
return mem_cgroup_inactive_anon_is_low(lruvec);
|
|
|
|
return inactive_anon_is_low_global(lruvec_zone(lruvec));
|
|
}
|
|
#else
|
|
static inline int inactive_anon_is_low(struct lruvec *lruvec)
|
|
{
|
|
return 0;
|
|
}
|
|
#endif
|
|
|
|
/**
|
|
* inactive_file_is_low - check if file pages need to be deactivated
|
|
* @lruvec: LRU vector to check
|
|
*
|
|
* When the system is doing streaming IO, memory pressure here
|
|
* ensures that active file pages get deactivated, until more
|
|
* than half of the file pages are on the inactive list.
|
|
*
|
|
* Once we get to that situation, protect the system's working
|
|
* set from being evicted by disabling active file page aging.
|
|
*
|
|
* This uses a different ratio than the anonymous pages, because
|
|
* the page cache uses a use-once replacement algorithm.
|
|
*/
|
|
static int inactive_file_is_low(struct lruvec *lruvec)
|
|
{
|
|
unsigned long inactive;
|
|
unsigned long active;
|
|
|
|
inactive = get_lru_size(lruvec, LRU_INACTIVE_FILE);
|
|
active = get_lru_size(lruvec, LRU_ACTIVE_FILE);
|
|
|
|
return active > inactive;
|
|
}
|
|
|
|
static int inactive_list_is_low(struct lruvec *lruvec, enum lru_list lru)
|
|
{
|
|
if (is_file_lru(lru))
|
|
return inactive_file_is_low(lruvec);
|
|
else
|
|
return inactive_anon_is_low(lruvec);
|
|
}
|
|
|
|
static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
|
|
struct lruvec *lruvec, struct scan_control *sc)
|
|
{
|
|
if (is_active_lru(lru)) {
|
|
if (inactive_list_is_low(lruvec, lru))
|
|
shrink_active_list(nr_to_scan, lruvec, sc, lru);
|
|
return 0;
|
|
}
|
|
|
|
return shrink_inactive_list(nr_to_scan, lruvec, sc, lru);
|
|
}
|
|
|
|
static int vmscan_swappiness(struct scan_control *sc)
|
|
{
|
|
if (global_reclaim(sc))
|
|
return vm_swappiness;
|
|
return mem_cgroup_swappiness(sc->target_mem_cgroup);
|
|
}
|
|
|
|
enum scan_balance {
|
|
SCAN_EQUAL,
|
|
SCAN_FRACT,
|
|
SCAN_ANON,
|
|
SCAN_FILE,
|
|
};
|
|
|
|
/*
|
|
* Determine how aggressively the anon and file LRU lists should be
|
|
* scanned. The relative value of each set of LRU lists is determined
|
|
* by looking at the fraction of the pages scanned we did rotate back
|
|
* onto the active list instead of evict.
|
|
*
|
|
* nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan
|
|
* nr[2] = file inactive pages to scan; nr[3] = file active pages to scan
|
|
*/
|
|
static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
|
|
unsigned long *nr)
|
|
{
|
|
struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
|
|
u64 fraction[2];
|
|
u64 denominator = 0; /* gcc */
|
|
struct zone *zone = lruvec_zone(lruvec);
|
|
unsigned long anon_prio, file_prio;
|
|
enum scan_balance scan_balance;
|
|
unsigned long anon, file, free;
|
|
bool force_scan = false;
|
|
unsigned long ap, fp;
|
|
enum lru_list lru;
|
|
|
|
/*
|
|
* If the zone or memcg is small, nr[l] can be 0. This
|
|
* results in no scanning on this priority and a potential
|
|
* priority drop. Global direct reclaim can go to the next
|
|
* zone and tends to have no problems. Global kswapd is for
|
|
* zone balancing and it needs to scan a minimum amount. When
|
|
* reclaiming for a memcg, a priority drop can cause high
|
|
* latencies, so it's better to scan a minimum amount there as
|
|
* well.
|
|
*/
|
|
if (current_is_kswapd() && !zone_reclaimable(zone))
|
|
force_scan = true;
|
|
if (!global_reclaim(sc))
|
|
force_scan = true;
|
|
|
|
/* If we have no swap space, do not bother scanning anon pages. */
|
|
if (!sc->may_swap || (get_nr_swap_pages() <= 0)) {
|
|
scan_balance = SCAN_FILE;
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* Global reclaim will swap to prevent OOM even with no
|
|
* swappiness, but memcg users want to use this knob to
|
|
* disable swapping for individual groups completely when
|
|
* using the memory controller's swap limit feature would be
|
|
* too expensive.
|
|
*/
|
|
if (!global_reclaim(sc) && !vmscan_swappiness(sc)) {
|
|
scan_balance = SCAN_FILE;
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* Do not apply any pressure balancing cleverness when the
|
|
* system is close to OOM, scan both anon and file equally
|
|
* (unless the swappiness setting disagrees with swapping).
|
|
*/
|
|
if (!sc->priority && vmscan_swappiness(sc)) {
|
|
scan_balance = SCAN_EQUAL;
|
|
goto out;
|
|
}
|
|
|
|
anon = get_lru_size(lruvec, LRU_ACTIVE_ANON) +
|
|
get_lru_size(lruvec, LRU_INACTIVE_ANON);
|
|
file = get_lru_size(lruvec, LRU_ACTIVE_FILE) +
|
|
get_lru_size(lruvec, LRU_INACTIVE_FILE);
|
|
|
|
/*
|
|
* If it's foreseeable that reclaiming the file cache won't be
|
|
* enough to get the zone back into a desirable shape, we have
|
|
* to swap. Better start now and leave the - probably heavily
|
|
* thrashing - remaining file pages alone.
|
|
*/
|
|
if (global_reclaim(sc)) {
|
|
free = zone_page_state(zone, NR_FREE_PAGES);
|
|
if (unlikely(file + free <= high_wmark_pages(zone))) {
|
|
scan_balance = SCAN_ANON;
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* There is enough inactive page cache, do not reclaim
|
|
* anything from the anonymous working set right now.
|
|
*/
|
|
if (!IS_ENABLED(CONFIG_BALANCE_ANON_FILE_RECLAIM) &&
|
|
!inactive_file_is_low(lruvec)) {
|
|
scan_balance = SCAN_FILE;
|
|
goto out;
|
|
}
|
|
|
|
scan_balance = SCAN_FRACT;
|
|
|
|
/*
|
|
* With swappiness at 100, anonymous and file have the same priority.
|
|
* This scanning priority is essentially the inverse of IO cost.
|
|
*/
|
|
anon_prio = vmscan_swappiness(sc);
|
|
file_prio = 200 - anon_prio;
|
|
|
|
/*
|
|
* OK, so we have swap space and a fair amount of page cache
|
|
* pages. We use the recently rotated / recently scanned
|
|
* ratios to determine how valuable each cache is.
|
|
*
|
|
* Because workloads change over time (and to avoid overflow)
|
|
* we keep these statistics as a floating average, which ends
|
|
* up weighing recent references more than old ones.
|
|
*
|
|
* anon in [0], file in [1]
|
|
*/
|
|
spin_lock_irq(&zone->lru_lock);
|
|
if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
|
|
reclaim_stat->recent_scanned[0] /= 2;
|
|
reclaim_stat->recent_rotated[0] /= 2;
|
|
}
|
|
|
|
if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) {
|
|
reclaim_stat->recent_scanned[1] /= 2;
|
|
reclaim_stat->recent_rotated[1] /= 2;
|
|
}
|
|
|
|
/*
|
|
* The amount of pressure on anon vs file pages is inversely
|
|
* proportional to the fraction of recently scanned pages on
|
|
* each list that were recently referenced and in active use.
|
|
*/
|
|
ap = anon_prio * (reclaim_stat->recent_scanned[0] + 1);
|
|
ap /= reclaim_stat->recent_rotated[0] + 1;
|
|
|
|
fp = file_prio * (reclaim_stat->recent_scanned[1] + 1);
|
|
fp /= reclaim_stat->recent_rotated[1] + 1;
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
|
|
fraction[0] = ap;
|
|
fraction[1] = fp;
|
|
denominator = ap + fp + 1;
|
|
out:
|
|
for_each_evictable_lru(lru) {
|
|
int file = is_file_lru(lru);
|
|
unsigned long size;
|
|
unsigned long scan;
|
|
|
|
size = get_lru_size(lruvec, lru);
|
|
scan = size >> sc->priority;
|
|
|
|
if (!scan && force_scan)
|
|
scan = min(size, SWAP_CLUSTER_MAX);
|
|
|
|
switch (scan_balance) {
|
|
case SCAN_EQUAL:
|
|
/* Scan lists relative to size */
|
|
break;
|
|
case SCAN_FRACT:
|
|
/*
|
|
* Scan types proportional to swappiness and
|
|
* their relative recent reclaim efficiency.
|
|
*/
|
|
scan = div64_u64(scan * fraction[file], denominator);
|
|
break;
|
|
case SCAN_FILE:
|
|
case SCAN_ANON:
|
|
/* Scan one type exclusively */
|
|
if ((scan_balance == SCAN_FILE) != file)
|
|
scan = 0;
|
|
break;
|
|
default:
|
|
/* Look ma, no brain */
|
|
BUG();
|
|
}
|
|
nr[lru] = scan;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
|
|
*/
|
|
static void shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc)
|
|
{
|
|
unsigned long nr[NR_LRU_LISTS];
|
|
unsigned long targets[NR_LRU_LISTS];
|
|
unsigned long nr_to_scan;
|
|
enum lru_list lru;
|
|
unsigned long nr_reclaimed = 0;
|
|
unsigned long nr_to_reclaim = sc->nr_to_reclaim;
|
|
struct blk_plug plug;
|
|
bool scan_adjusted;
|
|
|
|
get_scan_count(lruvec, sc, nr);
|
|
|
|
/* Record the original scan target for proportional adjustments later */
|
|
memcpy(targets, nr, sizeof(nr));
|
|
|
|
/*
|
|
* Global reclaiming within direct reclaim at DEF_PRIORITY is a normal
|
|
* event that can occur when there is little memory pressure e.g.
|
|
* multiple streaming readers/writers. Hence, we do not abort scanning
|
|
* when the requested number of pages are reclaimed when scanning at
|
|
* DEF_PRIORITY on the assumption that the fact we are direct
|
|
* reclaiming implies that kswapd is not keeping up and it is best to
|
|
* do a batch of work at once. For memcg reclaim one check is made to
|
|
* abort proportional reclaim if either the file or anon lru has already
|
|
* dropped to zero at the first pass.
|
|
*/
|
|
scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() &&
|
|
sc->priority == DEF_PRIORITY);
|
|
|
|
blk_start_plug(&plug);
|
|
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
|
|
nr[LRU_INACTIVE_FILE]) {
|
|
unsigned long nr_anon, nr_file, percentage;
|
|
unsigned long nr_scanned;
|
|
|
|
for_each_evictable_lru(lru) {
|
|
if (nr[lru]) {
|
|
nr_to_scan = min(nr[lru], SWAP_CLUSTER_MAX);
|
|
nr[lru] -= nr_to_scan;
|
|
|
|
nr_reclaimed += shrink_list(lru, nr_to_scan,
|
|
lruvec, sc);
|
|
}
|
|
}
|
|
|
|
if (nr_reclaimed < nr_to_reclaim || scan_adjusted)
|
|
continue;
|
|
|
|
/*
|
|
* For kswapd and memcg, reclaim at least the number of pages
|
|
* requested. Ensure that the anon and file LRUs are scanned
|
|
* proportionally what was requested by get_scan_count(). We
|
|
* stop reclaiming one LRU and reduce the amount scanning
|
|
* proportional to the original scan target.
|
|
*/
|
|
nr_file = nr[LRU_INACTIVE_FILE] + nr[LRU_ACTIVE_FILE];
|
|
nr_anon = nr[LRU_INACTIVE_ANON] + nr[LRU_ACTIVE_ANON];
|
|
|
|
/*
|
|
* It's just vindictive to attack the larger once the smaller
|
|
* has gone to zero. And given the way we stop scanning the
|
|
* smaller below, this makes sure that we only make one nudge
|
|
* towards proportionality once we've got nr_to_reclaim.
|
|
*/
|
|
if (!nr_file || !nr_anon)
|
|
break;
|
|
|
|
if (nr_file > nr_anon) {
|
|
unsigned long scan_target = targets[LRU_INACTIVE_ANON] +
|
|
targets[LRU_ACTIVE_ANON] + 1;
|
|
lru = LRU_BASE;
|
|
percentage = nr_anon * 100 / scan_target;
|
|
} else {
|
|
unsigned long scan_target = targets[LRU_INACTIVE_FILE] +
|
|
targets[LRU_ACTIVE_FILE] + 1;
|
|
lru = LRU_FILE;
|
|
percentage = nr_file * 100 / scan_target;
|
|
}
|
|
|
|
/* Stop scanning the smaller of the LRU */
|
|
nr[lru] = 0;
|
|
nr[lru + LRU_ACTIVE] = 0;
|
|
|
|
/*
|
|
* Recalculate the other LRU scan count based on its original
|
|
* scan target and the percentage scanning already complete
|
|
*/
|
|
lru = (lru == LRU_FILE) ? LRU_BASE : LRU_FILE;
|
|
nr_scanned = targets[lru] - nr[lru];
|
|
nr[lru] = targets[lru] * (100 - percentage) / 100;
|
|
nr[lru] -= min(nr[lru], nr_scanned);
|
|
|
|
lru += LRU_ACTIVE;
|
|
nr_scanned = targets[lru] - nr[lru];
|
|
nr[lru] = targets[lru] * (100 - percentage) / 100;
|
|
nr[lru] -= min(nr[lru], nr_scanned);
|
|
|
|
scan_adjusted = true;
|
|
}
|
|
blk_finish_plug(&plug);
|
|
sc->nr_reclaimed += nr_reclaimed;
|
|
|
|
/*
|
|
* Even if we did not try to evict anon pages at all, we want to
|
|
* rebalance the anon lru active/inactive ratio.
|
|
*/
|
|
if (inactive_anon_is_low(lruvec))
|
|
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
|
|
sc, LRU_ACTIVE_ANON);
|
|
|
|
throttle_vm_writeout(sc->gfp_mask);
|
|
}
|
|
|
|
/* Use reclaim/compaction for costly allocs or under memory pressure */
|
|
static bool in_reclaim_compaction(struct scan_control *sc)
|
|
{
|
|
if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
|
|
(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
|
|
sc->priority < DEF_PRIORITY - 2))
|
|
return true;
|
|
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* Reclaim/compaction is used for high-order allocation requests. It reclaims
|
|
* order-0 pages before compacting the zone. should_continue_reclaim() returns
|
|
* true if more pages should be reclaimed such that when the page allocator
|
|
* calls try_to_compact_zone() that it will have enough free pages to succeed.
|
|
* It will give up earlier than that if there is difficulty reclaiming pages.
|
|
*/
|
|
static inline bool should_continue_reclaim(struct zone *zone,
|
|
unsigned long nr_reclaimed,
|
|
unsigned long nr_scanned,
|
|
struct scan_control *sc)
|
|
{
|
|
unsigned long pages_for_compaction;
|
|
unsigned long inactive_lru_pages;
|
|
|
|
/* If not in reclaim/compaction mode, stop */
|
|
if (!in_reclaim_compaction(sc))
|
|
return false;
|
|
|
|
/* Consider stopping depending on scan and reclaim activity */
|
|
if (sc->gfp_mask & __GFP_REPEAT) {
|
|
/*
|
|
* For __GFP_REPEAT allocations, stop reclaiming if the
|
|
* full LRU list has been scanned and we are still failing
|
|
* to reclaim pages. This full LRU scan is potentially
|
|
* expensive but a __GFP_REPEAT caller really wants to succeed
|
|
*/
|
|
if (!nr_reclaimed && !nr_scanned)
|
|
return false;
|
|
} else {
|
|
/*
|
|
* For non-__GFP_REPEAT allocations which can presumably
|
|
* fail without consequence, stop if we failed to reclaim
|
|
* any pages from the last SWAP_CLUSTER_MAX number of
|
|
* pages that were scanned. This will return to the
|
|
* caller faster at the risk reclaim/compaction and
|
|
* the resulting allocation attempt fails
|
|
*/
|
|
if (!nr_reclaimed)
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* If we have not reclaimed enough pages for compaction and the
|
|
* inactive lists are large enough, continue reclaiming
|
|
*/
|
|
pages_for_compaction = (2UL << sc->order);
|
|
inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE);
|
|
if (get_nr_swap_pages() > 0)
|
|
inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON);
|
|
if (sc->nr_reclaimed < pages_for_compaction &&
|
|
inactive_lru_pages > pages_for_compaction)
|
|
return true;
|
|
|
|
/* If compaction would go ahead or the allocation would succeed, stop */
|
|
switch (compaction_suitable(zone, sc->order)) {
|
|
case COMPACT_PARTIAL:
|
|
case COMPACT_CONTINUE:
|
|
return false;
|
|
default:
|
|
return true;
|
|
}
|
|
}
|
|
|
|
static void shrink_zone(struct zone *zone, struct scan_control *sc)
|
|
{
|
|
unsigned long nr_reclaimed, nr_scanned;
|
|
|
|
do {
|
|
struct mem_cgroup *root = sc->target_mem_cgroup;
|
|
struct mem_cgroup_reclaim_cookie reclaim = {
|
|
.zone = zone,
|
|
.priority = sc->priority,
|
|
};
|
|
struct mem_cgroup *memcg;
|
|
|
|
nr_reclaimed = sc->nr_reclaimed;
|
|
nr_scanned = sc->nr_scanned;
|
|
|
|
memcg = mem_cgroup_iter(root, NULL, &reclaim);
|
|
do {
|
|
struct lruvec *lruvec;
|
|
|
|
lruvec = mem_cgroup_zone_lruvec(zone, memcg);
|
|
|
|
shrink_lruvec(lruvec, sc);
|
|
|
|
/*
|
|
* Direct reclaim and kswapd have to scan all memory
|
|
* cgroups to fulfill the overall scan target for the
|
|
* zone.
|
|
*
|
|
* Limit reclaim, on the other hand, only cares about
|
|
* nr_to_reclaim pages to be reclaimed and it will
|
|
* retry with decreasing priority if one round over the
|
|
* whole hierarchy is not sufficient.
|
|
*/
|
|
if (!global_reclaim(sc) &&
|
|
sc->nr_reclaimed >= sc->nr_to_reclaim) {
|
|
mem_cgroup_iter_break(root, memcg);
|
|
break;
|
|
}
|
|
memcg = mem_cgroup_iter(root, memcg, &reclaim);
|
|
} while (memcg);
|
|
|
|
vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
|
|
sc->nr_scanned - nr_scanned,
|
|
sc->nr_reclaimed - nr_reclaimed);
|
|
|
|
} while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
|
|
sc->nr_scanned - nr_scanned, sc));
|
|
}
|
|
|
|
/* Returns true if compaction should go ahead for a high-order request */
|
|
static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
|
|
{
|
|
unsigned long balance_gap, watermark;
|
|
bool watermark_ok;
|
|
|
|
/* Do not consider compaction for orders reclaim is meant to satisfy */
|
|
if (sc->order <= PAGE_ALLOC_COSTLY_ORDER)
|
|
return false;
|
|
|
|
/*
|
|
* Compaction takes time to run and there are potentially other
|
|
* callers using the pages just freed. Continue reclaiming until
|
|
* there is a buffer of free pages available to give compaction
|
|
* a reasonable chance of completing and allocating the page
|
|
*/
|
|
balance_gap = min(low_wmark_pages(zone),
|
|
(zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
|
|
KSWAPD_ZONE_BALANCE_GAP_RATIO);
|
|
watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order);
|
|
watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0);
|
|
|
|
/*
|
|
* If compaction is deferred, reclaim up to a point where
|
|
* compaction will have a chance of success when re-enabled
|
|
*/
|
|
if (compaction_deferred(zone, sc->order))
|
|
return watermark_ok;
|
|
|
|
/* If compaction is not ready to start, keep reclaiming */
|
|
if (!compaction_suitable(zone, sc->order))
|
|
return false;
|
|
|
|
return watermark_ok;
|
|
}
|
|
|
|
/*
|
|
* This is the direct reclaim path, for page-allocating processes. We only
|
|
* try to reclaim pages from zones which will satisfy the caller's allocation
|
|
* request.
|
|
*
|
|
* We reclaim from a zone even if that zone is over high_wmark_pages(zone).
|
|
* Because:
|
|
* a) The caller may be trying to free *extra* pages to satisfy a higher-order
|
|
* allocation or
|
|
* b) The target zone may be at high_wmark_pages(zone) but the lower zones
|
|
* must go *over* high_wmark_pages(zone) to satisfy the `incremental min'
|
|
* zone defense algorithm.
|
|
*
|
|
* If a zone is deemed to be full of pinned pages then just give it a light
|
|
* scan then give up on it.
|
|
*
|
|
* This function returns true if a zone is being reclaimed for a costly
|
|
* high-order allocation and compaction is ready to begin. This indicates to
|
|
* the caller that it should consider retrying the allocation instead of
|
|
* further reclaim.
|
|
*/
|
|
static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
|
|
{
|
|
struct zoneref *z;
|
|
struct zone *zone;
|
|
unsigned long nr_soft_reclaimed;
|
|
unsigned long nr_soft_scanned;
|
|
bool aborted_reclaim = false;
|
|
|
|
/*
|
|
* If the number of buffer_heads in the machine exceeds the maximum
|
|
* allowed level, force direct reclaim to scan the highmem zone as
|
|
* highmem pages could be pinning lowmem pages storing buffer_heads
|
|
*/
|
|
if (buffer_heads_over_limit)
|
|
sc->gfp_mask |= __GFP_HIGHMEM;
|
|
|
|
for_each_zone_zonelist_nodemask(zone, z, zonelist,
|
|
gfp_zone(sc->gfp_mask), sc->nodemask) {
|
|
if (!populated_zone(zone))
|
|
continue;
|
|
/*
|
|
* Take care memory controller reclaiming has small influence
|
|
* to global LRU.
|
|
*/
|
|
if (global_reclaim(sc)) {
|
|
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
|
|
continue;
|
|
if (sc->priority != DEF_PRIORITY &&
|
|
!zone_reclaimable(zone))
|
|
continue; /* Let kswapd poll it */
|
|
if (IS_ENABLED(CONFIG_COMPACTION)) {
|
|
/*
|
|
* If we already have plenty of memory free for
|
|
* compaction in this zone, don't free any more.
|
|
* Even though compaction is invoked for any
|
|
* non-zero order, only frequent costly order
|
|
* reclamation is disruptive enough to become a
|
|
* noticeable problem, like transparent huge
|
|
* page allocations.
|
|
*/
|
|
if (compaction_ready(zone, sc)) {
|
|
aborted_reclaim = true;
|
|
continue;
|
|
}
|
|
}
|
|
/*
|
|
* This steals pages from memory cgroups over softlimit
|
|
* and returns the number of reclaimed pages and
|
|
* scanned pages. This works for global memory pressure
|
|
* and balancing, not for a memcg's limit.
|
|
*/
|
|
nr_soft_scanned = 0;
|
|
nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
|
|
sc->order, sc->gfp_mask,
|
|
&nr_soft_scanned);
|
|
sc->nr_reclaimed += nr_soft_reclaimed;
|
|
sc->nr_scanned += nr_soft_scanned;
|
|
/* need some check for avoid more shrink_zone() */
|
|
}
|
|
|
|
shrink_zone(zone, sc);
|
|
}
|
|
|
|
return aborted_reclaim;
|
|
}
|
|
|
|
/* All zones in zonelist are unreclaimable? */
|
|
static bool all_unreclaimable(struct zonelist *zonelist,
|
|
struct scan_control *sc)
|
|
{
|
|
struct zoneref *z;
|
|
struct zone *zone;
|
|
|
|
for_each_zone_zonelist_nodemask(zone, z, zonelist,
|
|
gfp_zone(sc->gfp_mask), sc->nodemask) {
|
|
if (!populated_zone(zone))
|
|
continue;
|
|
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
|
|
continue;
|
|
if (zone_reclaimable(zone))
|
|
return false;
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
/*
|
|
* This is the main entry point to direct page reclaim.
|
|
*
|
|
* If a full scan of the inactive list fails to free enough memory then we
|
|
* are "out of memory" and something needs to be killed.
|
|
*
|
|
* If the caller is !__GFP_FS then the probability of a failure is reasonably
|
|
* high - the zone may be full of dirty or under-writeback pages, which this
|
|
* caller can't do much about. We kick the writeback threads and take explicit
|
|
* naps in the hope that some of these pages can be written. But if the
|
|
* allocating task holds filesystem locks which prevent writeout this might not
|
|
* work, and the allocation attempt will fail.
|
|
*
|
|
* returns: 0, if no pages reclaimed
|
|
* else, the number of pages reclaimed
|
|
*/
|
|
static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
|
|
struct scan_control *sc,
|
|
struct shrink_control *shrink)
|
|
{
|
|
unsigned long total_scanned = 0;
|
|
struct reclaim_state *reclaim_state = current->reclaim_state;
|
|
struct zoneref *z;
|
|
struct zone *zone;
|
|
unsigned long writeback_threshold;
|
|
bool aborted_reclaim;
|
|
|
|
delayacct_freepages_start();
|
|
|
|
if (global_reclaim(sc))
|
|
count_vm_event(ALLOCSTALL);
|
|
|
|
do {
|
|
vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup,
|
|
sc->priority);
|
|
sc->nr_scanned = 0;
|
|
aborted_reclaim = shrink_zones(zonelist, sc);
|
|
|
|
/*
|
|
* Don't shrink slabs when reclaiming memory from over limit
|
|
* cgroups but do shrink slab at least once when aborting
|
|
* reclaim for compaction to avoid unevenly scanning file/anon
|
|
* LRU pages over slab pages.
|
|
*/
|
|
if (global_reclaim(sc)) {
|
|
unsigned long lru_pages = 0;
|
|
for_each_zone_zonelist(zone, z, zonelist,
|
|
gfp_zone(sc->gfp_mask)) {
|
|
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
|
|
continue;
|
|
|
|
lru_pages += zone_reclaimable_pages(zone);
|
|
}
|
|
|
|
shrink_slab(shrink, sc->nr_scanned, lru_pages);
|
|
if (reclaim_state) {
|
|
sc->nr_reclaimed += reclaim_state->reclaimed_slab;
|
|
reclaim_state->reclaimed_slab = 0;
|
|
}
|
|
}
|
|
total_scanned += sc->nr_scanned;
|
|
if (sc->nr_reclaimed >= sc->nr_to_reclaim)
|
|
goto out;
|
|
|
|
/*
|
|
* If we're getting trouble reclaiming, start doing
|
|
* writepage even in laptop mode.
|
|
*/
|
|
if (sc->priority < DEF_PRIORITY - 2)
|
|
sc->may_writepage = 1;
|
|
|
|
/*
|
|
* Try to write back as many pages as we just scanned. This
|
|
* tends to cause slow streaming writers to write data to the
|
|
* disk smoothly, at the dirtying rate, which is nice. But
|
|
* that's undesirable in laptop mode, where we *want* lumpy
|
|
* writeout. So in laptop mode, write out the whole world.
|
|
*/
|
|
writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2;
|
|
if (total_scanned > writeback_threshold) {
|
|
wakeup_flusher_threads(laptop_mode ? 0 : total_scanned,
|
|
WB_REASON_TRY_TO_FREE_PAGES);
|
|
sc->may_writepage = 1;
|
|
}
|
|
} while (--sc->priority >= 0 && !aborted_reclaim);
|
|
|
|
out:
|
|
delayacct_freepages_end();
|
|
|
|
if (sc->nr_reclaimed)
|
|
return sc->nr_reclaimed;
|
|
|
|
/*
|
|
* As hibernation is going on, kswapd is freezed so that it can't mark
|
|
* the zone into all_unreclaimable. Thus bypassing all_unreclaimable
|
|
* check.
|
|
*/
|
|
if (oom_killer_disabled)
|
|
return 0;
|
|
|
|
/* Aborted reclaim to try compaction? don't OOM, then */
|
|
if (aborted_reclaim)
|
|
return 1;
|
|
|
|
/* top priority shrink_zones still had more to do? don't OOM, then */
|
|
if (global_reclaim(sc) && !all_unreclaimable(zonelist, sc))
|
|
return 1;
|
|
|
|
return 0;
|
|
}
|
|
|
|
static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
|
|
{
|
|
struct zone *zone;
|
|
unsigned long pfmemalloc_reserve = 0;
|
|
unsigned long free_pages = 0;
|
|
int i;
|
|
bool wmark_ok;
|
|
|
|
for (i = 0; i <= ZONE_NORMAL; i++) {
|
|
zone = &pgdat->node_zones[i];
|
|
if (!populated_zone(zone))
|
|
continue;
|
|
|
|
pfmemalloc_reserve += min_wmark_pages(zone);
|
|
free_pages += zone_page_state(zone, NR_FREE_PAGES);
|
|
}
|
|
|
|
/* If there are no reserves (unexpected config) then do not throttle */
|
|
if (!pfmemalloc_reserve)
|
|
return true;
|
|
|
|
wmark_ok = free_pages > pfmemalloc_reserve / 2;
|
|
|
|
/* kswapd must be awake if processes are being throttled */
|
|
if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
|
|
pgdat->classzone_idx = min(pgdat->classzone_idx,
|
|
(enum zone_type)ZONE_NORMAL);
|
|
wake_up_interruptible(&pgdat->kswapd_wait);
|
|
}
|
|
|
|
return wmark_ok;
|
|
}
|
|
|
|
/*
|
|
* Throttle direct reclaimers if backing storage is backed by the network
|
|
* and the PFMEMALLOC reserve for the preferred node is getting dangerously
|
|
* depleted. kswapd will continue to make progress and wake the processes
|
|
* when the low watermark is reached.
|
|
*
|
|
* Returns true if a fatal signal was delivered during throttling. If this
|
|
* happens, the page allocator should not consider triggering the OOM killer.
|
|
*/
|
|
static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist,
|
|
nodemask_t *nodemask)
|
|
{
|
|
struct zoneref *z;
|
|
struct zone *zone;
|
|
pg_data_t *pgdat = NULL;
|
|
|
|
/*
|
|
* Kernel threads should not be throttled as they may be indirectly
|
|
* responsible for cleaning pages necessary for reclaim to make forward
|
|
* progress. kjournald for example may enter direct reclaim while
|
|
* committing a transaction where throttling it could forcing other
|
|
* processes to block on log_wait_commit().
|
|
*/
|
|
if (current->flags & PF_KTHREAD)
|
|
goto out;
|
|
|
|
/*
|
|
* If a fatal signal is pending, this process should not throttle.
|
|
* It should return quickly so it can exit and free its memory
|
|
*/
|
|
if (fatal_signal_pending(current))
|
|
goto out;
|
|
|
|
/*
|
|
* Check if the pfmemalloc reserves are ok by finding the first node
|
|
* with a usable ZONE_NORMAL or lower zone. The expectation is that
|
|
* GFP_KERNEL will be required for allocating network buffers when
|
|
* swapping over the network so ZONE_HIGHMEM is unusable.
|
|
*
|
|
* Throttling is based on the first usable node and throttled processes
|
|
* wait on a queue until kswapd makes progress and wakes them. There
|
|
* is an affinity then between processes waking up and where reclaim
|
|
* progress has been made assuming the process wakes on the same node.
|
|
* More importantly, processes running on remote nodes will not compete
|
|
* for remote pfmemalloc reserves and processes on different nodes
|
|
* should make reasonable progress.
|
|
*/
|
|
for_each_zone_zonelist_nodemask(zone, z, zonelist,
|
|
gfp_mask, nodemask) {
|
|
if (zone_idx(zone) > ZONE_NORMAL)
|
|
continue;
|
|
|
|
/* Throttle based on the first usable node */
|
|
pgdat = zone->zone_pgdat;
|
|
if (pfmemalloc_watermark_ok(pgdat))
|
|
goto out;
|
|
break;
|
|
}
|
|
|
|
/* If no zone was usable by the allocation flags then do not throttle */
|
|
if (!pgdat)
|
|
goto out;
|
|
|
|
/* Account for the throttling */
|
|
count_vm_event(PGSCAN_DIRECT_THROTTLE);
|
|
|
|
/*
|
|
* If the caller cannot enter the filesystem, it's possible that it
|
|
* is due to the caller holding an FS lock or performing a journal
|
|
* transaction in the case of a filesystem like ext[3|4]. In this case,
|
|
* it is not safe to block on pfmemalloc_wait as kswapd could be
|
|
* blocked waiting on the same lock. Instead, throttle for up to a
|
|
* second before continuing.
|
|
*/
|
|
if (!(gfp_mask & __GFP_FS)) {
|
|
wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
|
|
pfmemalloc_watermark_ok(pgdat), HZ);
|
|
|
|
goto check_pending;
|
|
}
|
|
|
|
/* Throttle until kswapd wakes the process */
|
|
wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
|
|
pfmemalloc_watermark_ok(pgdat));
|
|
|
|
check_pending:
|
|
if (fatal_signal_pending(current))
|
|
return true;
|
|
|
|
out:
|
|
return false;
|
|
}
|
|
|
|
unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
|
|
gfp_t gfp_mask, nodemask_t *nodemask)
|
|
{
|
|
unsigned long nr_reclaimed;
|
|
struct scan_control sc = {
|
|
.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
|
|
.may_writepage = !laptop_mode,
|
|
.nr_to_reclaim = SWAP_CLUSTER_MAX,
|
|
.may_unmap = 1,
|
|
.may_swap = 1,
|
|
.order = order,
|
|
.priority = DEF_PRIORITY,
|
|
.target_mem_cgroup = NULL,
|
|
.nodemask = nodemask,
|
|
};
|
|
struct shrink_control shrink = {
|
|
.gfp_mask = sc.gfp_mask,
|
|
};
|
|
|
|
/*
|
|
* Do not enter reclaim if fatal signal was delivered while throttled.
|
|
* 1 is returned so that the page allocator does not OOM kill at this
|
|
* point.
|
|
*/
|
|
if (throttle_direct_reclaim(gfp_mask, zonelist, nodemask))
|
|
return 1;
|
|
|
|
trace_mm_vmscan_direct_reclaim_begin(order,
|
|
sc.may_writepage,
|
|
gfp_mask);
|
|
|
|
nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
|
|
|
|
trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
|
|
|
|
return nr_reclaimed;
|
|
}
|
|
|
|
#ifdef CONFIG_MEMCG
|
|
|
|
unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg,
|
|
gfp_t gfp_mask, bool noswap,
|
|
struct zone *zone,
|
|
unsigned long *nr_scanned)
|
|
{
|
|
struct scan_control sc = {
|
|
.nr_scanned = 0,
|
|
.nr_to_reclaim = SWAP_CLUSTER_MAX,
|
|
.may_writepage = !laptop_mode,
|
|
.may_unmap = 1,
|
|
.may_swap = !noswap,
|
|
.order = 0,
|
|
.priority = 0,
|
|
.target_mem_cgroup = memcg,
|
|
};
|
|
struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
|
|
|
|
sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
|
|
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
|
|
|
|
trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
|
|
sc.may_writepage,
|
|
sc.gfp_mask);
|
|
|
|
/*
|
|
* NOTE: Although we can get the priority field, using it
|
|
* here is not a good idea, since it limits the pages we can scan.
|
|
* if we don't reclaim here, the shrink_zone from balance_pgdat
|
|
* will pick up pages from other mem cgroup's as well. We hack
|
|
* the priority and make it zero.
|
|
*/
|
|
shrink_lruvec(lruvec, &sc);
|
|
|
|
trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
|
|
|
|
*nr_scanned = sc.nr_scanned;
|
|
return sc.nr_reclaimed;
|
|
}
|
|
|
|
unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
|
|
gfp_t gfp_mask,
|
|
bool noswap)
|
|
{
|
|
struct zonelist *zonelist;
|
|
unsigned long nr_reclaimed;
|
|
int nid;
|
|
struct scan_control sc = {
|
|
.may_writepage = !laptop_mode,
|
|
.may_unmap = 1,
|
|
.may_swap = !noswap,
|
|
.nr_to_reclaim = SWAP_CLUSTER_MAX,
|
|
.order = 0,
|
|
.priority = DEF_PRIORITY,
|
|
.target_mem_cgroup = memcg,
|
|
.nodemask = NULL, /* we don't care the placement */
|
|
.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
|
|
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK),
|
|
};
|
|
struct shrink_control shrink = {
|
|
.gfp_mask = sc.gfp_mask,
|
|
};
|
|
|
|
/*
|
|
* Unlike direct reclaim via alloc_pages(), memcg's reclaim doesn't
|
|
* take care of from where we get pages. So the node where we start the
|
|
* scan does not need to be the current node.
|
|
*/
|
|
nid = mem_cgroup_select_victim_node(memcg);
|
|
|
|
zonelist = NODE_DATA(nid)->node_zonelists;
|
|
|
|
trace_mm_vmscan_memcg_reclaim_begin(0,
|
|
sc.may_writepage,
|
|
sc.gfp_mask);
|
|
|
|
nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
|
|
|
|
trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
|
|
|
|
return nr_reclaimed;
|
|
}
|
|
#endif
|
|
|
|
static void age_active_anon(struct zone *zone, struct scan_control *sc)
|
|
{
|
|
struct mem_cgroup *memcg;
|
|
|
|
if (!total_swap_pages)
|
|
return;
|
|
|
|
memcg = mem_cgroup_iter(NULL, NULL, NULL);
|
|
do {
|
|
struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg);
|
|
|
|
if (inactive_anon_is_low(lruvec))
|
|
shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
|
|
sc, LRU_ACTIVE_ANON);
|
|
|
|
memcg = mem_cgroup_iter(NULL, memcg, NULL);
|
|
} while (memcg);
|
|
}
|
|
|
|
static bool zone_balanced(struct zone *zone, int order,
|
|
unsigned long balance_gap, int classzone_idx)
|
|
{
|
|
if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone) +
|
|
balance_gap, classzone_idx, 0))
|
|
return false;
|
|
|
|
if (IS_ENABLED(CONFIG_COMPACTION) && order &&
|
|
!compaction_suitable(zone, order))
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
/*
|
|
* pgdat_balanced() is used when checking if a node is balanced.
|
|
*
|
|
* For order-0, all zones must be balanced!
|
|
*
|
|
* For high-order allocations only zones that meet watermarks and are in a
|
|
* zone allowed by the callers classzone_idx are added to balanced_pages. The
|
|
* total of balanced pages must be at least 25% of the zones allowed by
|
|
* classzone_idx for the node to be considered balanced. Forcing all zones to
|
|
* be balanced for high orders can cause excessive reclaim when there are
|
|
* imbalanced zones.
|
|
* The choice of 25% is due to
|
|
* o a 16M DMA zone that is balanced will not balance a zone on any
|
|
* reasonable sized machine
|
|
* o On all other machines, the top zone must be at least a reasonable
|
|
* percentage of the middle zones. For example, on 32-bit x86, highmem
|
|
* would need to be at least 256M for it to be balance a whole node.
|
|
* Similarly, on x86-64 the Normal zone would need to be at least 1G
|
|
* to balance a node on its own. These seemed like reasonable ratios.
|
|
*/
|
|
static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
|
|
{
|
|
unsigned long managed_pages = 0;
|
|
unsigned long balanced_pages = 0;
|
|
int i;
|
|
|
|
/* Check the watermark levels */
|
|
for (i = 0; i <= classzone_idx; i++) {
|
|
struct zone *zone = pgdat->node_zones + i;
|
|
|
|
if (!populated_zone(zone))
|
|
continue;
|
|
|
|
managed_pages += zone->managed_pages;
|
|
|
|
/*
|
|
* A special case here:
|
|
*
|
|
* balance_pgdat() skips over all_unreclaimable after
|
|
* DEF_PRIORITY. Effectively, it considers them balanced so
|
|
* they must be considered balanced here as well!
|
|
*/
|
|
if (!zone_reclaimable(zone)) {
|
|
balanced_pages += zone->managed_pages;
|
|
continue;
|
|
}
|
|
|
|
if (zone_balanced(zone, order, 0, i))
|
|
balanced_pages += zone->managed_pages;
|
|
else if (!order)
|
|
return false;
|
|
}
|
|
|
|
if (order)
|
|
return balanced_pages >= (managed_pages >> 2);
|
|
else
|
|
return true;
|
|
}
|
|
|
|
/*
|
|
* Prepare kswapd for sleeping. This verifies that there are no processes
|
|
* waiting in throttle_direct_reclaim() and that watermarks have been met.
|
|
*
|
|
* Returns true if kswapd is ready to sleep
|
|
*/
|
|
static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining,
|
|
int classzone_idx)
|
|
{
|
|
/* If a direct reclaimer woke kswapd within HZ/10, it's premature */
|
|
if (remaining)
|
|
return false;
|
|
|
|
/*
|
|
* The throttled processes are normally woken up in balance_pgdat() as
|
|
* soon as pfmemalloc_watermark_ok() is true. But there is a potential
|
|
* race between when kswapd checks the watermarks and a process gets
|
|
* throttled. There is also a potential race if processes get
|
|
* throttled, kswapd wakes, a large process exits thereby balancing the
|
|
* zones, which causes kswapd to exit balance_pgdat() before reaching
|
|
* the wake up checks. If kswapd is going to sleep, no process should
|
|
* be sleeping on pfmemalloc_wait, so wake them now if necessary. If
|
|
* the wake up is premature, processes will wake kswapd and get
|
|
* throttled again. The difference from wake ups in balance_pgdat() is
|
|
* that here we are under prepare_to_wait().
|
|
*/
|
|
if (waitqueue_active(&pgdat->pfmemalloc_wait))
|
|
wake_up_all(&pgdat->pfmemalloc_wait);
|
|
|
|
return pgdat_balanced(pgdat, order, classzone_idx);
|
|
}
|
|
|
|
/*
|
|
* kswapd shrinks the zone by the number of pages required to reach
|
|
* the high watermark.
|
|
*
|
|
* Returns true if kswapd scanned at least the requested number of pages to
|
|
* reclaim or if the lack of progress was due to pages under writeback.
|
|
* This is used to determine if the scanning priority needs to be raised.
|
|
*/
|
|
static bool kswapd_shrink_zone(struct zone *zone,
|
|
int classzone_idx,
|
|
struct scan_control *sc,
|
|
unsigned long lru_pages,
|
|
unsigned long *nr_attempted)
|
|
{
|
|
unsigned long nr_slab;
|
|
int testorder = sc->order;
|
|
unsigned long balance_gap;
|
|
struct reclaim_state *reclaim_state = current->reclaim_state;
|
|
struct shrink_control shrink = {
|
|
.gfp_mask = sc->gfp_mask,
|
|
};
|
|
bool lowmem_pressure;
|
|
|
|
/* Reclaim above the high watermark. */
|
|
sc->nr_to_reclaim = max(SWAP_CLUSTER_MAX, high_wmark_pages(zone));
|
|
|
|
/*
|
|
* Kswapd reclaims only single pages with compaction enabled. Trying
|
|
* too hard to reclaim until contiguous free pages have become
|
|
* available can hurt performance by evicting too much useful data
|
|
* from memory. Do not reclaim more than needed for compaction.
|
|
*/
|
|
if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
|
|
compaction_suitable(zone, sc->order) !=
|
|
COMPACT_SKIPPED)
|
|
testorder = 0;
|
|
|
|
/*
|
|
* We put equal pressure on every zone, unless one zone has way too
|
|
* many pages free already. The "too many pages" is defined as the
|
|
* high wmark plus a "gap" where the gap is either the low
|
|
* watermark or 1% of the zone, whichever is smaller.
|
|
*/
|
|
balance_gap = min(low_wmark_pages(zone),
|
|
(zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
|
|
KSWAPD_ZONE_BALANCE_GAP_RATIO);
|
|
|
|
/*
|
|
* If there is no low memory pressure or the zone is balanced then no
|
|
* reclaim is necessary
|
|
*/
|
|
lowmem_pressure = (buffer_heads_over_limit && is_highmem(zone));
|
|
if (!lowmem_pressure && zone_balanced(zone, testorder,
|
|
balance_gap, classzone_idx))
|
|
return true;
|
|
|
|
shrink_zone(zone, sc);
|
|
|
|
reclaim_state->reclaimed_slab = 0;
|
|
nr_slab = shrink_slab(&shrink, sc->nr_scanned, lru_pages);
|
|
sc->nr_reclaimed += reclaim_state->reclaimed_slab;
|
|
|
|
/* Account for the number of pages attempted to reclaim */
|
|
*nr_attempted += sc->nr_to_reclaim;
|
|
|
|
zone_clear_flag(zone, ZONE_WRITEBACK);
|
|
|
|
/*
|
|
* If a zone reaches its high watermark, consider it to be no longer
|
|
* congested. It's possible there are dirty pages backed by congested
|
|
* BDIs but as pressure is relieved, speculatively avoid congestion
|
|
* waits.
|
|
*/
|
|
if (zone_reclaimable(zone) &&
|
|
zone_balanced(zone, testorder, 0, classzone_idx)) {
|
|
zone_clear_flag(zone, ZONE_CONGESTED);
|
|
zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY);
|
|
}
|
|
|
|
return sc->nr_scanned >= sc->nr_to_reclaim;
|
|
}
|
|
|
|
/*
|
|
* For kswapd, balance_pgdat() will work across all this node's zones until
|
|
* they are all at high_wmark_pages(zone).
|
|
*
|
|
* Returns the final order kswapd was reclaiming at
|
|
*
|
|
* There is special handling here for zones which are full of pinned pages.
|
|
* This can happen if the pages are all mlocked, or if they are all used by
|
|
* device drivers (say, ZONE_DMA). Or if they are all in use by hugetlb.
|
|
* What we do is to detect the case where all pages in the zone have been
|
|
* scanned twice and there has been zero successful reclaim. Mark the zone as
|
|
* dead and from now on, only perform a short scan. Basically we're polling
|
|
* the zone for when the problem goes away.
|
|
*
|
|
* kswapd scans the zones in the highmem->normal->dma direction. It skips
|
|
* zones which have free_pages > high_wmark_pages(zone), but once a zone is
|
|
* found to have free_pages <= high_wmark_pages(zone), we scan that zone and the
|
|
* lower zones regardless of the number of free pages in the lower zones. This
|
|
* interoperates with the page allocator fallback scheme to ensure that aging
|
|
* of pages is balanced across the zones.
|
|
*/
|
|
static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
|
|
int *classzone_idx)
|
|
{
|
|
int i;
|
|
int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */
|
|
unsigned long nr_soft_reclaimed;
|
|
unsigned long nr_soft_scanned;
|
|
struct scan_control sc = {
|
|
.gfp_mask = GFP_KERNEL,
|
|
.priority = DEF_PRIORITY,
|
|
.may_unmap = 1,
|
|
.may_swap = 1,
|
|
.may_writepage = !laptop_mode,
|
|
.order = order,
|
|
.target_mem_cgroup = NULL,
|
|
};
|
|
count_vm_event(PAGEOUTRUN);
|
|
|
|
do {
|
|
unsigned long lru_pages = 0;
|
|
unsigned long nr_attempted = 0;
|
|
bool raise_priority = true;
|
|
bool pgdat_needs_compaction = (order > 0);
|
|
|
|
sc.nr_reclaimed = 0;
|
|
|
|
/*
|
|
* Scan in the highmem->dma direction for the highest
|
|
* zone which needs scanning
|
|
*/
|
|
for (i = pgdat->nr_zones - 1; i >= 0; i--) {
|
|
struct zone *zone = pgdat->node_zones + i;
|
|
|
|
if (!populated_zone(zone))
|
|
continue;
|
|
|
|
if (sc.priority != DEF_PRIORITY &&
|
|
!zone_reclaimable(zone))
|
|
continue;
|
|
|
|
/*
|
|
* Do some background aging of the anon list, to give
|
|
* pages a chance to be referenced before reclaiming.
|
|
*/
|
|
age_active_anon(zone, &sc);
|
|
|
|
/*
|
|
* If the number of buffer_heads in the machine
|
|
* exceeds the maximum allowed level and this node
|
|
* has a highmem zone, force kswapd to reclaim from
|
|
* it to relieve lowmem pressure.
|
|
*/
|
|
if (buffer_heads_over_limit && is_highmem_idx(i)) {
|
|
end_zone = i;
|
|
break;
|
|
}
|
|
|
|
if (!zone_balanced(zone, order, 0, 0)) {
|
|
end_zone = i;
|
|
break;
|
|
} else {
|
|
/*
|
|
* If balanced, clear the dirty and congested
|
|
* flags
|
|
*/
|
|
zone_clear_flag(zone, ZONE_CONGESTED);
|
|
zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY);
|
|
}
|
|
}
|
|
|
|
if (i < 0)
|
|
goto out;
|
|
|
|
for (i = 0; i <= end_zone; i++) {
|
|
struct zone *zone = pgdat->node_zones + i;
|
|
|
|
if (!populated_zone(zone))
|
|
continue;
|
|
|
|
lru_pages += zone_reclaimable_pages(zone);
|
|
|
|
/*
|
|
* If any zone is currently balanced then kswapd will
|
|
* not call compaction as it is expected that the
|
|
* necessary pages are already available.
|
|
*/
|
|
if (pgdat_needs_compaction &&
|
|
zone_watermark_ok(zone, order,
|
|
low_wmark_pages(zone),
|
|
*classzone_idx, 0))
|
|
pgdat_needs_compaction = false;
|
|
}
|
|
|
|
/*
|
|
* If we're getting trouble reclaiming, start doing writepage
|
|
* even in laptop mode.
|
|
*/
|
|
if (sc.priority < DEF_PRIORITY - 2)
|
|
sc.may_writepage = 1;
|
|
|
|
/*
|
|
* Now scan the zone in the dma->highmem direction, stopping
|
|
* at the last zone which needs scanning.
|
|
*
|
|
* We do this because the page allocator works in the opposite
|
|
* direction. This prevents the page allocator from allocating
|
|
* pages behind kswapd's direction of progress, which would
|
|
* cause too much scanning of the lower zones.
|
|
*/
|
|
for (i = 0; i <= end_zone; i++) {
|
|
struct zone *zone = pgdat->node_zones + i;
|
|
|
|
if (!populated_zone(zone))
|
|
continue;
|
|
|
|
if (sc.priority != DEF_PRIORITY &&
|
|
!zone_reclaimable(zone))
|
|
continue;
|
|
|
|
sc.nr_scanned = 0;
|
|
|
|
nr_soft_scanned = 0;
|
|
/*
|
|
* Call soft limit reclaim before calling shrink_zone.
|
|
*/
|
|
nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
|
|
order, sc.gfp_mask,
|
|
&nr_soft_scanned);
|
|
sc.nr_reclaimed += nr_soft_reclaimed;
|
|
|
|
/*
|
|
* There should be no need to raise the scanning
|
|
* priority if enough pages are already being scanned
|
|
* that that high watermark would be met at 100%
|
|
* efficiency.
|
|
*/
|
|
if (kswapd_shrink_zone(zone, end_zone, &sc,
|
|
lru_pages, &nr_attempted))
|
|
raise_priority = false;
|
|
}
|
|
|
|
/*
|
|
* If the low watermark is met there is no need for processes
|
|
* to be throttled on pfmemalloc_wait as they should not be
|
|
* able to safely make forward progress. Wake them
|
|
*/
|
|
if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
|
|
pfmemalloc_watermark_ok(pgdat))
|
|
wake_up(&pgdat->pfmemalloc_wait);
|
|
|
|
/*
|
|
* Fragmentation may mean that the system cannot be rebalanced
|
|
* for high-order allocations in all zones. If twice the
|
|
* allocation size has been reclaimed and the zones are still
|
|
* not balanced then recheck the watermarks at order-0 to
|
|
* prevent kswapd reclaiming excessively. Assume that a
|
|
* process requested a high-order can direct reclaim/compact.
|
|
*/
|
|
if (order && sc.nr_reclaimed >= 2UL << order)
|
|
order = sc.order = 0;
|
|
|
|
/* Check if kswapd should be suspending */
|
|
if (try_to_freeze() || kthread_should_stop())
|
|
break;
|
|
|
|
/*
|
|
* Compact if necessary and kswapd is reclaiming at least the
|
|
* high watermark number of pages as requsted
|
|
*/
|
|
if (pgdat_needs_compaction && sc.nr_reclaimed > nr_attempted)
|
|
compact_pgdat(pgdat, order);
|
|
|
|
/*
|
|
* Raise priority if scanning rate is too low or there was no
|
|
* progress in reclaiming pages
|
|
*/
|
|
if (raise_priority || !sc.nr_reclaimed)
|
|
sc.priority--;
|
|
} while (sc.priority >= 1 &&
|
|
!pgdat_balanced(pgdat, order, *classzone_idx));
|
|
|
|
out:
|
|
/*
|
|
* Return the order we were reclaiming at so prepare_kswapd_sleep()
|
|
* makes a decision on the order we were last reclaiming at. However,
|
|
* if another caller entered the allocator slow path while kswapd
|
|
* was awake, order will remain at the higher level
|
|
*/
|
|
*classzone_idx = end_zone;
|
|
return order;
|
|
}
|
|
|
|
static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
|
|
{
|
|
long remaining = 0;
|
|
DEFINE_WAIT(wait);
|
|
|
|
if (freezing(current) || kthread_should_stop())
|
|
return;
|
|
|
|
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
|
|
|
|
/* Try to sleep for a short interval */
|
|
if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) {
|
|
remaining = schedule_timeout(HZ/10);
|
|
finish_wait(&pgdat->kswapd_wait, &wait);
|
|
prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
|
|
}
|
|
|
|
/*
|
|
* After a short sleep, check if it was a premature sleep. If not, then
|
|
* go fully to sleep until explicitly woken up.
|
|
*/
|
|
if (prepare_kswapd_sleep(pgdat, order, remaining, classzone_idx)) {
|
|
trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
|
|
|
|
/*
|
|
* vmstat counters are not perfectly accurate and the estimated
|
|
* value for counters such as NR_FREE_PAGES can deviate from the
|
|
* true value by nr_online_cpus * threshold. To avoid the zone
|
|
* watermarks being breached while under pressure, we reduce the
|
|
* per-cpu vmstat threshold while kswapd is awake and restore
|
|
* them before going back to sleep.
|
|
*/
|
|
set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
|
|
|
|
/*
|
|
* Compaction records what page blocks it recently failed to
|
|
* isolate pages from and skips them in the future scanning.
|
|
* When kswapd is going to sleep, it is reasonable to assume
|
|
* that pages and compaction may succeed so reset the cache.
|
|
*/
|
|
reset_isolation_suitable(pgdat);
|
|
|
|
if (!kthread_should_stop())
|
|
schedule();
|
|
|
|
set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
|
|
} else {
|
|
if (remaining)
|
|
count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
|
|
else
|
|
count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
|
|
}
|
|
finish_wait(&pgdat->kswapd_wait, &wait);
|
|
}
|
|
|
|
/*
|
|
* The background pageout daemon, started as a kernel thread
|
|
* from the init process.
|
|
*
|
|
* This basically trickles out pages so that we have _some_
|
|
* free memory available even if there is no other activity
|
|
* that frees anything up. This is needed for things like routing
|
|
* etc, where we otherwise might have all activity going on in
|
|
* asynchronous contexts that cannot page things out.
|
|
*
|
|
* If there are applications that are active memory-allocators
|
|
* (most normal use), this basically shouldn't matter.
|
|
*/
|
|
static int kswapd(void *p)
|
|
{
|
|
unsigned long order, new_order;
|
|
unsigned balanced_order;
|
|
int classzone_idx, new_classzone_idx;
|
|
int balanced_classzone_idx;
|
|
pg_data_t *pgdat = (pg_data_t*)p;
|
|
struct task_struct *tsk = current;
|
|
|
|
struct reclaim_state reclaim_state = {
|
|
.reclaimed_slab = 0,
|
|
};
|
|
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
|
|
|
|
lockdep_set_current_reclaim_state(GFP_KERNEL);
|
|
|
|
if (kswapd_cpu_mask == NULL && !cpumask_empty(cpumask))
|
|
set_cpus_allowed_ptr(tsk, cpumask);
|
|
current->reclaim_state = &reclaim_state;
|
|
|
|
/*
|
|
* Tell the memory management that we're a "memory allocator",
|
|
* and that if we need more memory we should get access to it
|
|
* regardless (see "__alloc_pages()"). "kswapd" should
|
|
* never get caught in the normal page freeing logic.
|
|
*
|
|
* (Kswapd normally doesn't need memory anyway, but sometimes
|
|
* you need a small amount of memory in order to be able to
|
|
* page out something else, and this flag essentially protects
|
|
* us from recursively trying to free more memory as we're
|
|
* trying to free the first piece of memory in the first place).
|
|
*/
|
|
tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
|
|
set_freezable();
|
|
|
|
order = new_order = 0;
|
|
balanced_order = 0;
|
|
classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
|
|
balanced_classzone_idx = classzone_idx;
|
|
for ( ; ; ) {
|
|
bool ret;
|
|
|
|
/*
|
|
* If the last balance_pgdat was unsuccessful it's unlikely a
|
|
* new request of a similar or harder type will succeed soon
|
|
* so consider going to sleep on the basis we reclaimed at
|
|
*/
|
|
if (balanced_classzone_idx >= new_classzone_idx &&
|
|
balanced_order == new_order) {
|
|
new_order = pgdat->kswapd_max_order;
|
|
new_classzone_idx = pgdat->classzone_idx;
|
|
pgdat->kswapd_max_order = 0;
|
|
pgdat->classzone_idx = pgdat->nr_zones - 1;
|
|
}
|
|
|
|
if (order < new_order || classzone_idx > new_classzone_idx) {
|
|
/*
|
|
* Don't sleep if someone wants a larger 'order'
|
|
* allocation or has tigher zone constraints
|
|
*/
|
|
order = new_order;
|
|
classzone_idx = new_classzone_idx;
|
|
} else {
|
|
kswapd_try_to_sleep(pgdat, balanced_order,
|
|
balanced_classzone_idx);
|
|
order = pgdat->kswapd_max_order;
|
|
classzone_idx = pgdat->classzone_idx;
|
|
new_order = order;
|
|
new_classzone_idx = classzone_idx;
|
|
pgdat->kswapd_max_order = 0;
|
|
pgdat->classzone_idx = pgdat->nr_zones - 1;
|
|
}
|
|
|
|
ret = try_to_freeze();
|
|
if (kthread_should_stop())
|
|
break;
|
|
|
|
/*
|
|
* We can speed up thawing tasks if we don't call balance_pgdat
|
|
* after returning from the refrigerator
|
|
*/
|
|
if (!ret) {
|
|
trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
|
|
balanced_classzone_idx = classzone_idx;
|
|
balanced_order = balance_pgdat(pgdat, order,
|
|
&balanced_classzone_idx);
|
|
}
|
|
}
|
|
|
|
tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
|
|
current->reclaim_state = NULL;
|
|
lockdep_clear_current_reclaim_state();
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* A zone is low on free memory, so wake its kswapd task to service it.
|
|
*/
|
|
void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
|
|
{
|
|
pg_data_t *pgdat;
|
|
|
|
if (!populated_zone(zone))
|
|
return;
|
|
|
|
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
|
|
return;
|
|
pgdat = zone->zone_pgdat;
|
|
if (pgdat->kswapd_max_order < order) {
|
|
pgdat->kswapd_max_order = order;
|
|
pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
|
|
}
|
|
if (!waitqueue_active(&pgdat->kswapd_wait))
|
|
return;
|
|
if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0))
|
|
return;
|
|
|
|
trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
|
|
wake_up_interruptible(&pgdat->kswapd_wait);
|
|
}
|
|
|
|
#ifdef CONFIG_HIBERNATION
|
|
/*
|
|
* Try to free `nr_to_reclaim' of memory, system-wide, and return the number of
|
|
* freed pages.
|
|
*
|
|
* Rather than trying to age LRUs the aim is to preserve the overall
|
|
* LRU order by reclaiming preferentially
|
|
* inactive > active > active referenced > active mapped
|
|
*/
|
|
unsigned long shrink_all_memory(unsigned long nr_to_reclaim)
|
|
{
|
|
struct reclaim_state reclaim_state;
|
|
struct scan_control sc = {
|
|
.gfp_mask = GFP_HIGHUSER_MOVABLE,
|
|
.may_swap = 1,
|
|
.may_unmap = 1,
|
|
.may_writepage = 1,
|
|
.nr_to_reclaim = nr_to_reclaim,
|
|
.hibernation_mode = 1,
|
|
.order = 0,
|
|
.priority = DEF_PRIORITY,
|
|
};
|
|
struct shrink_control shrink = {
|
|
.gfp_mask = sc.gfp_mask,
|
|
};
|
|
struct zonelist *zonelist = node_zonelist(numa_node_id(), sc.gfp_mask);
|
|
struct task_struct *p = current;
|
|
unsigned long nr_reclaimed;
|
|
|
|
p->flags |= PF_MEMALLOC;
|
|
lockdep_set_current_reclaim_state(sc.gfp_mask);
|
|
reclaim_state.reclaimed_slab = 0;
|
|
p->reclaim_state = &reclaim_state;
|
|
|
|
nr_reclaimed = do_try_to_free_pages(zonelist, &sc, &shrink);
|
|
|
|
p->reclaim_state = NULL;
|
|
lockdep_clear_current_reclaim_state();
|
|
p->flags &= ~PF_MEMALLOC;
|
|
|
|
return nr_reclaimed;
|
|
}
|
|
#endif /* CONFIG_HIBERNATION */
|
|
|
|
/* It's optimal to keep kswapds on the same CPUs as their memory, but
|
|
not required for correctness. So if the last cpu in a node goes
|
|
away, we get changed to run anywhere: as the first one comes back,
|
|
restore their cpu bindings. */
|
|
static int cpu_callback(struct notifier_block *nfb, unsigned long action,
|
|
void *hcpu)
|
|
{
|
|
int nid;
|
|
|
|
if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
|
|
for_each_node_state(nid, N_MEMORY) {
|
|
pg_data_t *pgdat = NODE_DATA(nid);
|
|
const struct cpumask *mask;
|
|
|
|
mask = cpumask_of_node(pgdat->node_id);
|
|
|
|
if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
|
|
/* One of our CPUs online: restore mask */
|
|
set_cpus_allowed_ptr(pgdat->kswapd, mask);
|
|
}
|
|
}
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
static int set_kswapd_cpu_mask(pg_data_t *pgdat)
|
|
{
|
|
int ret = 0;
|
|
cpumask_t tmask;
|
|
|
|
if (!kswapd_cpu_mask)
|
|
return 0;
|
|
|
|
cpus_clear(tmask);
|
|
ret = cpumask_parse(kswapd_cpu_mask, &tmask);
|
|
if (ret)
|
|
return ret;
|
|
|
|
return set_cpus_allowed_ptr(pgdat->kswapd, &tmask);
|
|
}
|
|
|
|
/*
|
|
* This kswapd start function will be called by init and node-hot-add.
|
|
* On node-hot-add, kswapd will moved to proper cpus if cpus are hot-added.
|
|
*/
|
|
int kswapd_run(int nid)
|
|
{
|
|
pg_data_t *pgdat = NODE_DATA(nid);
|
|
int ret = 0;
|
|
|
|
if (pgdat->kswapd)
|
|
return 0;
|
|
|
|
pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
|
|
if (IS_ERR(pgdat->kswapd)) {
|
|
/* failure at boot is fatal */
|
|
BUG_ON(system_state == SYSTEM_BOOTING);
|
|
pr_err("Failed to start kswapd on node %d\n", nid);
|
|
ret = PTR_ERR(pgdat->kswapd);
|
|
pgdat->kswapd = NULL;
|
|
} else if (kswapd_cpu_mask) {
|
|
if (set_kswapd_cpu_mask(pgdat))
|
|
pr_warn("error setting kswapd cpu affinity mask\n");
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Called by memory hotplug when all memory in a node is offlined. Caller must
|
|
* hold lock_memory_hotplug().
|
|
*/
|
|
void kswapd_stop(int nid)
|
|
{
|
|
struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
|
|
|
|
if (kswapd) {
|
|
kthread_stop(kswapd);
|
|
NODE_DATA(nid)->kswapd = NULL;
|
|
}
|
|
}
|
|
|
|
static int __init kswapd_init(void)
|
|
{
|
|
int nid;
|
|
|
|
swap_setup();
|
|
for_each_node_state(nid, N_MEMORY)
|
|
kswapd_run(nid);
|
|
if (kswapd_cpu_mask == NULL)
|
|
hotcpu_notifier(cpu_callback, 0);
|
|
return 0;
|
|
}
|
|
|
|
module_init(kswapd_init)
|
|
|
|
#ifdef CONFIG_NUMA
|
|
/*
|
|
* Zone reclaim mode
|
|
*
|
|
* If non-zero call zone_reclaim when the number of free pages falls below
|
|
* the watermarks.
|
|
*/
|
|
int zone_reclaim_mode __read_mostly;
|
|
|
|
#define RECLAIM_OFF 0
|
|
#define RECLAIM_ZONE (1<<0) /* Run shrink_inactive_list on the zone */
|
|
#define RECLAIM_WRITE (1<<1) /* Writeout pages during reclaim */
|
|
#define RECLAIM_SWAP (1<<2) /* Swap pages out during reclaim */
|
|
|
|
/*
|
|
* Priority for ZONE_RECLAIM. This determines the fraction of pages
|
|
* of a node considered for each zone_reclaim. 4 scans 1/16th of
|
|
* a zone.
|
|
*/
|
|
#define ZONE_RECLAIM_PRIORITY 4
|
|
|
|
/*
|
|
* Percentage of pages in a zone that must be unmapped for zone_reclaim to
|
|
* occur.
|
|
*/
|
|
int sysctl_min_unmapped_ratio = 1;
|
|
|
|
/*
|
|
* If the number of slab pages in a zone grows beyond this percentage then
|
|
* slab reclaim needs to occur.
|
|
*/
|
|
int sysctl_min_slab_ratio = 5;
|
|
|
|
static inline unsigned long zone_unmapped_file_pages(struct zone *zone)
|
|
{
|
|
unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED);
|
|
unsigned long file_lru = zone_page_state(zone, NR_INACTIVE_FILE) +
|
|
zone_page_state(zone, NR_ACTIVE_FILE);
|
|
|
|
/*
|
|
* It's possible for there to be more file mapped pages than
|
|
* accounted for by the pages on the file LRU lists because
|
|
* tmpfs pages accounted for as ANON can also be FILE_MAPPED
|
|
*/
|
|
return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0;
|
|
}
|
|
|
|
/* Work out how many page cache pages we can reclaim in this reclaim_mode */
|
|
static long zone_pagecache_reclaimable(struct zone *zone)
|
|
{
|
|
long nr_pagecache_reclaimable;
|
|
long delta = 0;
|
|
|
|
/*
|
|
* If RECLAIM_SWAP is set, then all file pages are considered
|
|
* potentially reclaimable. Otherwise, we have to worry about
|
|
* pages like swapcache and zone_unmapped_file_pages() provides
|
|
* a better estimate
|
|
*/
|
|
if (zone_reclaim_mode & RECLAIM_SWAP)
|
|
nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES);
|
|
else
|
|
nr_pagecache_reclaimable = zone_unmapped_file_pages(zone);
|
|
|
|
/* If we can't clean pages, remove dirty pages from consideration */
|
|
if (!(zone_reclaim_mode & RECLAIM_WRITE))
|
|
delta += zone_page_state(zone, NR_FILE_DIRTY);
|
|
|
|
/* Watch for any possible underflows due to delta */
|
|
if (unlikely(delta > nr_pagecache_reclaimable))
|
|
delta = nr_pagecache_reclaimable;
|
|
|
|
return nr_pagecache_reclaimable - delta;
|
|
}
|
|
|
|
/*
|
|
* Try to free up some pages from this zone through reclaim.
|
|
*/
|
|
static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
|
|
{
|
|
/* Minimum pages needed in order to stay on node */
|
|
const unsigned long nr_pages = 1 << order;
|
|
struct task_struct *p = current;
|
|
struct reclaim_state reclaim_state;
|
|
struct scan_control sc = {
|
|
.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
|
|
.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
|
|
.may_swap = 1,
|
|
.nr_to_reclaim = max(nr_pages, SWAP_CLUSTER_MAX),
|
|
.gfp_mask = (gfp_mask = memalloc_noio_flags(gfp_mask)),
|
|
.order = order,
|
|
.priority = ZONE_RECLAIM_PRIORITY,
|
|
};
|
|
struct shrink_control shrink = {
|
|
.gfp_mask = sc.gfp_mask,
|
|
};
|
|
unsigned long nr_slab_pages0, nr_slab_pages1;
|
|
|
|
cond_resched();
|
|
/*
|
|
* We need to be able to allocate from the reserves for RECLAIM_SWAP
|
|
* and we also need to be able to write out pages for RECLAIM_WRITE
|
|
* and RECLAIM_SWAP.
|
|
*/
|
|
p->flags |= PF_MEMALLOC | PF_SWAPWRITE;
|
|
lockdep_set_current_reclaim_state(gfp_mask);
|
|
reclaim_state.reclaimed_slab = 0;
|
|
p->reclaim_state = &reclaim_state;
|
|
|
|
if (zone_pagecache_reclaimable(zone) > zone->min_unmapped_pages) {
|
|
/*
|
|
* Free memory by calling shrink zone with increasing
|
|
* priorities until we have enough memory freed.
|
|
*/
|
|
do {
|
|
shrink_zone(zone, &sc);
|
|
} while (sc.nr_reclaimed < nr_pages && --sc.priority >= 0);
|
|
}
|
|
|
|
nr_slab_pages0 = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
|
|
if (nr_slab_pages0 > zone->min_slab_pages) {
|
|
/*
|
|
* shrink_slab() does not currently allow us to determine how
|
|
* many pages were freed in this zone. So we take the current
|
|
* number of slab pages and shake the slab until it is reduced
|
|
* by the same nr_pages that we used for reclaiming unmapped
|
|
* pages.
|
|
*
|
|
* Note that shrink_slab will free memory on all zones and may
|
|
* take a long time.
|
|
*/
|
|
for (;;) {
|
|
unsigned long lru_pages = zone_reclaimable_pages(zone);
|
|
|
|
/* No reclaimable slab or very low memory pressure */
|
|
if (!shrink_slab(&shrink, sc.nr_scanned, lru_pages))
|
|
break;
|
|
|
|
/* Freed enough memory */
|
|
nr_slab_pages1 = zone_page_state(zone,
|
|
NR_SLAB_RECLAIMABLE);
|
|
if (nr_slab_pages1 + nr_pages <= nr_slab_pages0)
|
|
break;
|
|
}
|
|
|
|
/*
|
|
* Update nr_reclaimed by the number of slab pages we
|
|
* reclaimed from this zone.
|
|
*/
|
|
nr_slab_pages1 = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
|
|
if (nr_slab_pages1 < nr_slab_pages0)
|
|
sc.nr_reclaimed += nr_slab_pages0 - nr_slab_pages1;
|
|
}
|
|
|
|
p->reclaim_state = NULL;
|
|
current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
|
|
lockdep_clear_current_reclaim_state();
|
|
return sc.nr_reclaimed >= nr_pages;
|
|
}
|
|
|
|
int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
|
|
{
|
|
int node_id;
|
|
int ret;
|
|
|
|
/*
|
|
* Zone reclaim reclaims unmapped file backed pages and
|
|
* slab pages if we are over the defined limits.
|
|
*
|
|
* A small portion of unmapped file backed pages is needed for
|
|
* file I/O otherwise pages read by file I/O will be immediately
|
|
* thrown out if the zone is overallocated. So we do not reclaim
|
|
* if less than a specified percentage of the zone is used by
|
|
* unmapped file backed pages.
|
|
*/
|
|
if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages &&
|
|
zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
|
|
return ZONE_RECLAIM_FULL;
|
|
|
|
if (!zone_reclaimable(zone))
|
|
return ZONE_RECLAIM_FULL;
|
|
|
|
/*
|
|
* Do not scan if the allocation should not be delayed.
|
|
*/
|
|
if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC))
|
|
return ZONE_RECLAIM_NOSCAN;
|
|
|
|
/*
|
|
* Only run zone reclaim on the local zone or on zones that do not
|
|
* have associated processors. This will favor the local processor
|
|
* over remote processors and spread off node memory allocations
|
|
* as wide as possible.
|
|
*/
|
|
node_id = zone_to_nid(zone);
|
|
if (node_state(node_id, N_CPU) && node_id != numa_node_id())
|
|
return ZONE_RECLAIM_NOSCAN;
|
|
|
|
if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED))
|
|
return ZONE_RECLAIM_NOSCAN;
|
|
|
|
ret = __zone_reclaim(zone, gfp_mask, order);
|
|
zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);
|
|
|
|
if (!ret)
|
|
count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
|
|
|
|
return ret;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* page_evictable - test whether a page is evictable
|
|
* @page: the page to test
|
|
*
|
|
* Test whether page is evictable--i.e., should be placed on active/inactive
|
|
* lists vs unevictable list.
|
|
*
|
|
* Reasons page might not be evictable:
|
|
* (1) page's mapping marked unevictable
|
|
* (2) page is part of an mlocked VMA
|
|
*
|
|
*/
|
|
int page_evictable(struct page *page)
|
|
{
|
|
return !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
|
|
}
|
|
|
|
#ifdef CONFIG_SHMEM
|
|
/**
|
|
* check_move_unevictable_pages - check pages for evictability and move to appropriate zone lru list
|
|
* @pages: array of pages to check
|
|
* @nr_pages: number of pages to check
|
|
*
|
|
* Checks pages for evictability and moves them to the appropriate lru list.
|
|
*
|
|
* This function is only used for SysV IPC SHM_UNLOCK.
|
|
*/
|
|
void check_move_unevictable_pages(struct page **pages, int nr_pages)
|
|
{
|
|
struct lruvec *lruvec;
|
|
struct zone *zone = NULL;
|
|
int pgscanned = 0;
|
|
int pgrescued = 0;
|
|
int i;
|
|
|
|
for (i = 0; i < nr_pages; i++) {
|
|
struct page *page = pages[i];
|
|
struct zone *pagezone;
|
|
|
|
pgscanned++;
|
|
pagezone = page_zone(page);
|
|
if (pagezone != zone) {
|
|
if (zone)
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
zone = pagezone;
|
|
spin_lock_irq(&zone->lru_lock);
|
|
}
|
|
lruvec = mem_cgroup_page_lruvec(page, zone);
|
|
|
|
if (!PageLRU(page) || !PageUnevictable(page))
|
|
continue;
|
|
|
|
if (page_evictable(page)) {
|
|
enum lru_list lru = page_lru_base_type(page);
|
|
|
|
VM_BUG_ON(PageActive(page));
|
|
ClearPageUnevictable(page);
|
|
del_page_from_lru_list(page, lruvec, LRU_UNEVICTABLE);
|
|
add_page_to_lru_list(page, lruvec, lru);
|
|
pgrescued++;
|
|
}
|
|
}
|
|
|
|
if (zone) {
|
|
__count_vm_events(UNEVICTABLE_PGRESCUED, pgrescued);
|
|
__count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
|
|
spin_unlock_irq(&zone->lru_lock);
|
|
}
|
|
}
|
|
#endif /* CONFIG_SHMEM */
|
|
|
|
static void warn_scan_unevictable_pages(void)
|
|
{
|
|
printk_once(KERN_WARNING
|
|
"%s: The scan_unevictable_pages sysctl/node-interface has been "
|
|
"disabled for lack of a legitimate use case. If you have "
|
|
"one, please send an email to linux-mm@kvack.org.\n",
|
|
current->comm);
|
|
}
|
|
|
|
/*
|
|
* scan_unevictable_pages [vm] sysctl handler. On demand re-scan of
|
|
* all nodes' unevictable lists for evictable pages
|
|
*/
|
|
unsigned long scan_unevictable_pages;
|
|
|
|
int scan_unevictable_handler(struct ctl_table *table, int write,
|
|
void __user *buffer,
|
|
size_t *length, loff_t *ppos)
|
|
{
|
|
warn_scan_unevictable_pages();
|
|
proc_doulongvec_minmax(table, write, buffer, length, ppos);
|
|
scan_unevictable_pages = 0;
|
|
return 0;
|
|
}
|
|
|
|
#ifdef CONFIG_NUMA
|
|
/*
|
|
* per node 'scan_unevictable_pages' attribute. On demand re-scan of
|
|
* a specified node's per zone unevictable lists for evictable pages.
|
|
*/
|
|
|
|
static ssize_t read_scan_unevictable_node(struct device *dev,
|
|
struct device_attribute *attr,
|
|
char *buf)
|
|
{
|
|
warn_scan_unevictable_pages();
|
|
return sprintf(buf, "0\n"); /* always zero; should fit... */
|
|
}
|
|
|
|
static ssize_t write_scan_unevictable_node(struct device *dev,
|
|
struct device_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
warn_scan_unevictable_pages();
|
|
return 1;
|
|
}
|
|
|
|
|
|
static DEVICE_ATTR(scan_unevictable_pages, S_IRUGO | S_IWUSR,
|
|
read_scan_unevictable_node,
|
|
write_scan_unevictable_node);
|
|
|
|
int scan_unevictable_register_node(struct node *node)
|
|
{
|
|
return device_create_file(&node->dev, &dev_attr_scan_unevictable_pages);
|
|
}
|
|
|
|
void scan_unevictable_unregister_node(struct node *node)
|
|
{
|
|
device_remove_file(&node->dev, &dev_attr_scan_unevictable_pages);
|
|
}
|
|
#endif
|