-----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmUBaBUACgkQONu9yGCS aT6OkBAArqBSUyCYQJrhoUlFYBnBqF7BLSkj0GwINGSUOlt5ilJ3kZwH9ftjvpWp ZtO0Rp/1yH2H5PpcsaLljPl055Sf30e0oCkz6vX16vy17NGnzI4rJi55+nRZbFRH tBMhMjblgIJoTiTPEQPSGghENok+QzJ9Imffo4/Wru3w5ytkBnGcPPXreHJw+8V5 Pjhzg5tcjhz23rk2wzVtR4VfEqWaHQaapv49rKB1Yls578WYn4QXl4jgUyB7rCo7 9vBB7xy77H1hr9m8ifB/9v1ToV/vw6L1xGPWWWbhsSikFAMBoq34SCsq+6RdeURo 43CCcFsx1s5acM7NQWvxkoV5Hgl8Hc3WgFsx5eVBlNd+vS6ezkgdYuGmN76t+dF/ hZ7XGEoEFuoz9NKQC/5rKjdBd2p/IQYx6vf8EpK0IxFPD4h+DY9pn0FvwuAmxAcA M41xLYGbXX5l/QJR016B1AYiB3DqVxRRRyQT0yNip+PDAh2N06MOJ84KgMSR9lg7 jyeFKZM2vQ619RopMIspuHTWxNiMw7x94aUhBnY1oD+fDzaRn+VNL8po6QYHLK8U QTDhrWplTbTuGIF72h+1IyX1aUj6ozoCewl9Y9ry1u9jBb7LZoupVd0s1dwqORIk 2OSo74pDu5F2BT+4hEcCpDRcYvWlfKbZWBunRrMqvHN8BON0Mks= =aFyS -----END PGP SIGNATURE----- Merge 6.1.53 into android14-6.1-lts Changes in 6.1.53 Revert "bridge: Add extack warning when enabling STP in netns." Partially revert "drm/amd/display: Fix possible underflow for displays with large vblank" scsi: ufs: Try harder to change the power mode Revert "Revert drm/amd/display: Enable Freesync Video Mode by default" ARM: dts: imx: Set default tuning step for imx7d usdhc ALSA: hda/realtek: Enable 4 amplifiers instead of 2 on a HP platform powerpc/boot: Disable power10 features after BOOTAFLAGS assignment media: uapi: HEVC: Add num_delta_pocs_of_ref_rps_idx field Revert "MIPS: unhide PATA_PLATFORM" phy: qcom-snps-femto-v2: use qcom_snps_hsphy_suspend/resume error code media: amphion: use dev_err_probe media: pulse8-cec: handle possible ping error media: pci: cx23885: fix error handling for cx23885 ATSC boards 9p: virtio: fix unlikely null pointer deref in handle_rerror 9p: virtio: make sure 'offs' is initialized in zc_request ksmbd: fix out of bounds in smb3_decrypt_req() ksmbd: validate session id and tree id in compound request ksmbd: no response from compound read ksmbd: fix out of bounds in init_smb2_rsp_hdr() ASoC: da7219: Flush pending AAD IRQ when suspending ASoC: da7219: Check for failure reading AAD IRQ events ASoC: nau8821: Add DMI quirk mechanism for active-high jack-detect ethernet: atheros: fix return value check in atl1c_tso_csum() m68k: Fix invalid .section syntax s390/dasd: use correct number of retries for ERP requests s390/dasd: fix hanging device after request requeue fs/nls: make load_nls() take a const parameter ASoC: rt5682-sdw: fix for JD event handling in ClockStop Mode0 ASoc: codecs: ES8316: Fix DMIC config ASoC: rt711: fix for JD event handling in ClockStop Mode0 ASoC: rt711-sdca: fix for JD event handling in ClockStop Mode0 ASoC: atmel: Fix the 8K sample parameter in I2SC master ALSA: usb-audio: Add quirk for Microsoft Modern Wireless Headset platform/x86: intel: hid: Always call BTNL ACPI method platform/x86/intel/hid: Add HP Dragonfly G2 to VGBS DMI quirks platform/x86: think-lmi: Use kfree_sensitive instead of kfree platform/x86: asus-wmi: Fix setting RGB mode on some TUF laptops platform/x86: huawei-wmi: Silence ambient light sensor drm/amd/smu: use AverageGfxclkFrequency* to replace previous GFX Curr Clock drm/amd/display: Guard DCN31 PHYD32CLK logic against chip family drm/amd/display: Exit idle optimizations before attempt to access PHY ovl: Always reevaluate the file signature for IMA ata: pata_arasan_cf: Use dev_err_probe() instead dev_err() in data_xfer() ALSA: usb-audio: Update for native DSD support quirks staging: fbtft: ili9341: use macro FBTFT_REGISTER_SPI_DRIVER security: keys: perform capable check only on privileged operations kprobes: Prohibit probing on CFI preamble symbol clk: fixed-mmio: make COMMON_CLK_FIXED_MMIO depend on HAS_IOMEM vmbus_testing: fix wrong python syntax for integer value comparison Revert "wifi: ath6k: silence false positive -Wno-dangling-pointer warning on GCC 12" net: dsa: microchip: KSZ9477 register regmap alignment to 32 bit boundaries net: annotate data-races around sk->sk_{rcv|snd}timeo net: usb: qmi_wwan: add Quectel EM05GV2 wifi: brcmfmac: Fix field-spanning write in brcmf_scan_params_v2_to_v1() powerpc/powermac: Use early_* IO variants in via_calibrate_decr() idmaengine: make FSL_EDMA and INTEL_IDMA64 depends on HAS_IOMEM platform/x86/amd/pmf: Fix unsigned comparison with less than zero scsi: lpfc: Remove reftag check in DIF paths scsi: qedi: Fix potential deadlock on &qedi_percpu->p_work_lock net: hns3: restore user pause configure when disable autoneg drm/amdgpu: Match against exact bootloader status wifi: cfg80211: remove links only on AP wifi: mac80211: Use active_links instead of valid_links in Tx netlabel: fix shift wrapping bug in netlbl_catmap_setlong() bnx2x: fix page fault following EEH recovery cifs: fix sockaddr comparison in iface_cmp cifs: fix max_credits implementation sctp: handle invalid error codes without calling BUG() scsi: aacraid: Reply queue mapping to CPUs based on IRQ affinity scsi: storvsc: Always set no_report_opcodes scsi: lpfc: Fix incorrect big endian type assignment in bsg loopback path LoongArch: Let pmd_present() return true when splitting pmd LoongArch: Fix the write_fcsr() macro ALSA: seq: oss: Fix racy open/close of MIDI devices net: sfp: handle 100G/25G active optical cables in sfp_parse_support tracing: Introduce pipe_cpumask to avoid race on trace_pipes platform/mellanox: Fix mlxbf-tmfifo not handling all virtio CONSOLE notifications of: property: Simplify of_link_to_phandle() cpufreq: intel_pstate: set stale CPU frequency to minimum crypto: rsa-pkcs1pad - Use helper to set reqsize tpm: Enable hwrng only for Pluton on AMD CPUs KVM: x86/mmu: Use kstrtobool() instead of strtobool() KVM: x86/mmu: Add "never" option to allow sticky disabling of nx_huge_pages net: Avoid address overwrite in kernel_connect drm/amd/display: ensure async flips are only accepted for fast updates udf: Check consistency of Space Bitmap Descriptor udf: Handle error when adding extent to a file Input: i8042 - add quirk for TUXEDO Gemini 17 Gen1/Clevo PD70PN Revert "PCI: tegra194: Enable support for 256 Byte payload" Revert "net: macsec: preserve ingress frame ordering" tools lib subcmd: Add install target tools lib subcmd: Make install_headers clearer tools lib subcmd: Add dependency test to install_headers tools/resolve_btfids: Use pkg-config to locate libelf tools/resolve_btfids: Install subcmd headers tools/resolve_btfids: Alter how HOSTCC is forced tools/resolve_btfids: Compile resolve_btfids as host program tools/resolve_btfids: Tidy HOST_OVERRIDES tools/resolve_btfids: Pass HOSTCFLAGS as EXTRA_CFLAGS to prepare targets tools/resolve_btfids: Fix setting HOSTCFLAGS reiserfs: Check the return value from __getblk() eventfd: prevent underflow for eventfd semaphores fs: Fix error checking for d_hash_and_lookup() iomap: Remove large folio handling in iomap_invalidate_folio() tmpfs: verify {g,u}id mount options correctly selftests/harness: Actually report SKIP for signal tests vfs, security: Fix automount superblock LSM init problem, preventing NFS sb sharing ARM: ptrace: Restore syscall restart tracing ARM: ptrace: Restore syscall skipping for tracers refscale: Fix uninitalized use of wait_queue_head_t OPP: Fix passing 0 to PTR_ERR in _opp_attach_genpd() selftests/resctrl: Add resctrl.h into build deps selftests/resctrl: Don't leak buffer in fill_cache() selftests/resctrl: Unmount resctrl FS if child fails to run benchmark selftests/resctrl: Close perf value read fd on errors arm64/ptrace: Clean up error handling path in sve_set_common() sched/psi: Select KERNFS as needed x86/decompressor: Don't rely on upper 32 bits of GPRs being preserved arm64/sme: Don't use streaming mode to probe the maximum SME VL arm64/fpsimd: Only provide the length to cpufeature for xCR registers sched/rt: Fix sysctl_sched_rr_timeslice intial value perf/imx_ddr: don't enable counter0 if none of 4 counters are used selftests/futex: Order calls to futex_lock_pi s390/pkey: fix/harmonize internal keyblob headers s390/pkey: fix PKEY_TYPE_EP11_AES handling in PKEY_GENSECK2 IOCTL s390/pkey: fix PKEY_TYPE_EP11_AES handling for sysfs attributes s390/paes: fix PKEY_TYPE_EP11_AES handling for secure keyblobs irqchip/loongson-eiointc: Fix return value checking of eiointc_index ACPI: x86: s2idle: Post-increment variables when getting constraints ACPI: x86: s2idle: Fix a logic error parsing AMD constraints table thermal/of: Fix potential uninitialized value access cpufreq: amd-pstate-ut: Remove module parameter access cpufreq: amd-pstate-ut: Fix kernel panic when loading the driver x86/efistub: Fix PCI ROM preservation in mixed mode cpufreq: powernow-k8: Use related_cpus instead of cpus in driver.exit() selftests/bpf: Fix bpf_nf failure upon test rerun bpftool: use a local copy of perf_event to fix accessing :: Bpf_cookie bpftool: Define a local bpf_perf_link to fix accessing its fields bpftool: Use a local copy of BPF_LINK_TYPE_PERF_EVENT in pid_iter.bpf.c bpftool: Use a local bpf_perf_event_value to fix accessing its fields libbpf: Fix realloc API handling in zero-sized edge cases bpf: Clear the probe_addr for uprobe bpf: Fix an error in verifying a field in a union crypto: qat - change value of default idle filter tcp: tcp_enter_quickack_mode() should be static hwrng: nomadik - keep clock enabled while hwrng is registered hwrng: pic32 - use devm_clk_get_enabled regmap: rbtree: Use alloc_flags for memory allocations wifi: rtw89: debug: Fix error handling in rtw89_debug_priv_btc_manual_set() wifi: mt76: mt7921: fix non-PSC channel scan fail udp: re-score reuseport groups when connected sockets are present bpf: reject unhashed sockets in bpf_sk_assign wifi: mt76: testmode: add nla_policy for MT76_TM_ATTR_TX_LENGTH spi: tegra20-sflash: fix to check return value of platform_get_irq() in tegra_sflash_probe() can: gs_usb: gs_usb_receive_bulk_callback(): count RX overflow errors also in case of OOM wifi: mt76: mt7915: fix power-limits while chan_switch wifi: mwifiex: Fix OOB and integer underflow when rx packets wifi: mwifiex: fix error recovery in PCIE buffer descriptor management selftests/bpf: fix static assert compilation issue for test_cls_*.c kbuild: rust_is_available: remove -v option kbuild: rust_is_available: fix version check when CC has multiple arguments kbuild: rust_is_available: add check for `bindgen` invocation kbuild: rust_is_available: fix confusion when a version appears in the path crypto: stm32 - Properly handle pm_runtime_get failing crypto: api - Use work queue in crypto_destroy_instance Bluetooth: nokia: fix value check in nokia_bluetooth_serdev_probe() Bluetooth: Fix potential use-after-free when clear keys Bluetooth: hci_sync: Don't double print name in add/remove adv_monitor Bluetooth: hci_sync: Avoid use-after-free in dbg for hci_add_adv_monitor() net: tcp: fix unexcepted socket die when snd_wnd is 0 selftests/bpf: Fix repeat option when kfunc_call verification fails selftests/bpf: Clean up fmod_ret in bench_rename test script net-memcg: Fix scope of sockmem pressure indicators ice: ice_aq_check_events: fix off-by-one check when filling buffer crypto: caam - fix unchecked return value error hwrng: iproc-rng200 - Implement suspend and resume calls lwt: Fix return values of BPF xmit ops lwt: Check LWTUNNEL_XMIT_CONTINUE strictly fs: ocfs2: namei: check return value of ocfs2_add_entry() net: annotate data-races around sk->sk_lingertime wifi: mwifiex: fix memory leak in mwifiex_histogram_read() wifi: mwifiex: Fix missed return in oob checks failed path ARM: dts: Add .dts files missing from the build samples/bpf: fix bio latency check with tracepoint samples/bpf: fix broken map lookup probe wifi: ath9k: fix races between ath9k_wmi_cmd and ath9k_wmi_ctrl_rx wifi: ath9k: protect WMI command response buffer replacement with a lock wifi: nl80211/cfg80211: add forgotten nla_policy for BSS color attribute mac80211: make ieee80211_tx_info padding explicit wifi: mwifiex: avoid possible NULL skb pointer dereference Bluetooth: btusb: Do not call kfree_skb() under spin_lock_irqsave() arm64: mm: use ptep_clear() instead of pte_clear() in clear_flush() wifi: ath9k: use IS_ERR() with debugfs_create_dir() ice: avoid executing commands on other ports when driving sync net: arcnet: Do not call kfree_skb() under local_irq_disable() mlxsw: i2c: Fix chunk size setting in output mailbox buffer mlxsw: i2c: Limit single transaction buffer size mlxsw: core_hwmon: Adjust module label names based on MTCAP sensor counter hwmon: (tmp513) Fix the channel number in tmp51x_is_visible() octeontx2-pf: Refactor schedular queue alloc/free calls octeontx2-pf: Fix PFC TX scheduler free cteonxt2-pf: Fix backpressure config for multiple PFC priorities to work simultaneously sfc: Check firmware supports Ethernet PTP filter net/sched: sch_hfsc: Ensure inner classes have fsc curve netrom: Deny concurrent connect(). drm/bridge: tc358764: Fix debug print parameter order ASoC: cs43130: Fix numerator/denominator mixup quota: factor out dquot_write_dquot() quota: rename dquot_active() to inode_quota_active() quota: add new helper dquot_active() quota: fix dqput() to follow the guarantees dquot_srcu should provide drm/amd/display: Do not set drr on pipe commit drm/hyperv: Fix a compilation issue because of not including screen_info.h ASoC: stac9766: fix build errors with REGMAP_AC97 soc: qcom: ocmem: Add OCMEM hardware version print soc: qcom: ocmem: Fix NUM_PORTS & NUM_MACROS macros arm64: dts: qcom: sm6350: Fix ZAP region arm64: dts: qcom: sm8250: correct dynamic power coefficients arm64: dts: qcom: msm8916-l8150: correct light sensor VDDIO supply arm64: dts: qcom: sm8250-edo: Add gpio line names for TLMM arm64: dts: qcom: sm8250-edo: Add GPIO line names for PMIC GPIOs arm64: dts: qcom: sm8250-edo: Rectify gpio-keys arm64: dts: qcom: sc8280xp-crd: Correct vreg_misc_3p3 GPIO arm64: dts: qcom: sc8280xp: Add missing SCM interconnect arm64: dts: qcom: msm8996: Add missing interrupt to the USB2 controller arm64: dts: qcom: sdm845-tama: Set serial indices and stdout-path arm64: dts: qcom: sm8350: Fix CPU idle state residency times arm64: dts: qcom: sm8350: Add missing LMH interrupts to cpufreq arm64: dts: qcom: sm8350: Use proper CPU compatibles arm64: dts: qcom: pm8350: fix thermal zone name arm64: dts: qcom: pm8350b: fix thermal zone name arm64: dts: qcom: pmr735b: fix thermal zone name arm64: dts: qcom: pmk8350: fix ADC-TM compatible string arm64: dts: qcom: sm8250: Mark PCIe hosts as DMA coherent ARM: dts: stm32: Rename mdio0 to mdio ARM: dts: stm32: YAML validation fails for Argon Boards ARM: dts: stm32: adopt generic iio bindings for adc channels on emstamp-argon ARM: dts: stm32: Add missing detach mailbox for emtrion emSBC-Argon ARM: dts: stm32: YAML validation fails for Odyssey Boards ARM: dts: stm32: Add missing detach mailbox for Odyssey SoM ARM: dts: stm32: Update to generic ADC channel binding on DHSOM systems ARM: dts: stm32: Add missing detach mailbox for DHCOM SoM firmware: ti_sci: Use system_state to determine polling drm/amdgpu: avoid integer overflow warning in amdgpu_device_resize_fb_bar() ARM: dts: BCM53573: Drop nonexistent #usb-cells ARM: dts: BCM53573: Add cells sizes to PCIe node ARM: dts: BCM53573: Use updated "spi-gpio" binding properties arm64: tegra: Fix HSUART for Jetson AGX Orin arm64: dts: qcom: sm8250-sony-xperia: correct GPIO keys wakeup again arm64: dts: qcom: pm6150l: Add missing short interrupt arm64: dts: qcom: pm660l: Add missing short interrupt arm64: dts: qcom: pmi8994: Add missing OVP interrupt arm64: tegra: Fix HSUART for Smaug drm/etnaviv: fix dumping of active MMU context block: cleanup queue_wc_store block: don't allow enabling a cache on devices that don't support it x86/mm: Fix PAT bit missing from page protection modify mask drm/bridge: anx7625: Use common macros for DP power sequencing commands drm/bridge: anx7625: Use common macros for HDCP capabilities ARM: dts: samsung: s3c6410-mini6410: correct ethernet reg addresses (split) ARM: dts: s5pv210: add dummy 5V regulator for backlight on SMDKv210 ARM: dts: samsung: s5pv210-smdkv210: correct ethernet reg addresses (split) drm: adv7511: Fix low refresh rate register for ADV7533/5 ARM: dts: BCM53573: Fix Ethernet info for Luxul devices arm64: dts: qcom: sdm845: Add missing RPMh power domain to GCC arm64: dts: qcom: sdm845: Fix the min frequency of "ice_core_clk" arm64: dts: qcom: msm8996-gemini: fix touchscreen VIO supply drm/amdgpu: Update min() to min_t() in 'amdgpu_info_ioctl' md: Factor out is_md_suspended helper md: Change active_io to percpu md: restore 'noio_flag' for the last mddev_resume() md/raid10: factor out dereference_rdev_and_rrdev() md/raid10: use dereference_rdev_and_rrdev() to get devices md/md-bitmap: remove unnecessary local variable in backlog_store() md/md-bitmap: hold 'reconfig_mutex' in backlog_store() drm/msm: Update dev core dump to not print backwards drm/tegra: dpaux: Fix incorrect return value of platform_get_irq of: unittest: fix null pointer dereferencing in of_unittest_find_node_by_name() arm64: dts: qcom: sm8150: Fix the I2C7 interrupt ARM: dts: BCM53573: Fix Tenda AC9 switch CPU port drm/armada: Fix off-by-one error in armada_overlay_get_property() drm/repaper: Reduce temporary buffer size in repaper_fb_dirty() drm/panel: simple: Add missing connector type and pixel format for AUO T215HVN01 ima: Remove deprecated IMA_TRUSTED_KEYRING Kconfig drm: xlnx: zynqmp_dpsub: Add missing check for dma_set_mask soc: qcom: smem: Fix incompatible types in comparison drm/msm/mdp5: Don't leak some plane state firmware: meson_sm: fix to avoid potential NULL pointer dereference drm/msm/dpu: fix the irq index in dpu_encoder_phys_wb_wait_for_commit_done smackfs: Prevent underflow in smk_set_cipso() drm/amd/pm: fix variable dereferenced issue in amdgpu_device_attr_create() drm/msm/a2xx: Call adreno_gpu_init() earlier audit: fix possible soft lockup in __audit_inode_child() block/mq-deadline: use correct way to throttling write requests io_uring: fix drain stalls by invalid SQE drm/mediatek: dp: Add missing error checks in mtk_dp_parse_capabilities bus: ti-sysc: Fix build warning for 64-bit build drm/mediatek: Remove freeing not dynamic allocated memory ARM: dts: qcom: ipq4019: correct SDHCI XO clock drm/mediatek: Fix potential memory leak if vmap() fail arm64: dts: qcom: apq8016-sbc: Fix ov5640 regulator supply names arm64: dts: qcom: msm8998: Drop bus clock reference from MMSS SMMU arm64: dts: qcom: msm8998: Add missing power domain to MMSS SMMU arm64: dts: qcom: msm8996: Fix dsi1 interrupts arm64: dts: qcom: sc8280xp-x13s: Unreserve NC pins bus: ti-sysc: Fix cast to enum warning md/raid5-cache: fix a deadlock in r5l_exit_log() md/raid5-cache: fix null-ptr-deref for r5l_flush_stripe_to_raid() firmware: cs_dsp: Fix new control name check md: add error_handlers for raid0 and linear md/raid0: Factor out helper for mapping and submitting a bio md/raid0: Fix performance regression for large sequential writes md: raid0: account for split bio in iostat accounting ASoC: SOF: amd: clear dsp to host interrupt status of: overlay: Call of_changeset_init() early of: unittest: Fix overlay type in apply/revert check ALSA: ac97: Fix possible error value of *rac97 ipmi:ssif: Add check for kstrdup ipmi:ssif: Fix a memory leak when scanning for an adapter clk: qcom: gpucc-sm6350: Introduce index-based clk lookup clk: qcom: gpucc-sm6350: Fix clock source names clk: qcom: gcc-sc8280xp: Add EMAC GDSCs clk: qcom: gcc-sc8280xp: Add missing GDSC flags dt-bindings: clock: qcom,gcc-sc8280xp: Add missing GDSCs clk: qcom: gcc-sc8280xp: Add missing GDSCs clk: rockchip: rk3568: Fix PLL rate setting for 78.75MHz PCI: apple: Initialize pcie->nvecs before use PCI: qcom-ep: Switch MHI bus master clock off during L1SS drivers: clk: keystone: Fix parameter judgment in _of_pll_clk_init() PCI/DOE: Fix destroy_work_on_stack() race clk: sunxi-ng: Modify mismatched function name clk: qcom: gcc-sc7180: Fix up gcc_sdcc2_apps_clk_src EDAC/igen6: Fix the issue of no error events ext4: correct grp validation in ext4_mb_good_group ext4: avoid potential data overflow in next_linear_group clk: qcom: gcc-sm8250: Fix gcc_sdcc2_apps_clk_src kvm/vfio: Prepare for accepting vfio device fd kvm/vfio: ensure kvg instance stays around in kvm_vfio_group_add() clk: qcom: reset: Use the correct type of sleep/delay based on length clk: qcom: gcc-sm6350: Fix gcc_sdcc2_apps_clk_src PCI: microchip: Correct the DED and SEC interrupt bit offsets PCI: Mark NVIDIA T4 GPUs to avoid bus reset pinctrl: mcp23s08: check return value of devm_kasprintf() PCI: Allow drivers to request exclusive config regions PCI: Add locking to RMW PCI Express Capability Register accessors PCI: pciehp: Use RMW accessors for changing LNKCTL PCI/ASPM: Use RMW accessors for changing LNKCTL clk: qcom: gcc-sm8450: Use floor ops for SDCC RCGs clk: imx: pllv4: Fix SPLL2 MULT range clk: imx: imx8ulp: update SPLL2 type clk: imx8mp: fix sai4 clock clk: imx: composite-8m: fix clock pauses when set_rate would be a no-op powerpc/radix: Move some functions into #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE vfio/type1: fix cap_migration information leak nvdimm: Fix memleak of pmu attr_groups in unregister_nvdimm_pmu() nvdimm: Fix dereference after free in register_nvdimm_pmu() powerpc/fadump: reset dump area size if fadump memory reserve fails powerpc/perf: Convert fsl_emb notifier to state machine callbacks drm/amdgpu: Use RMW accessors for changing LNKCTL drm/radeon: Use RMW accessors for changing LNKCTL net/mlx5: Use RMW accessors for changing LNKCTL wifi: ath11k: Use RMW accessors for changing LNKCTL wifi: ath10k: Use RMW accessors for changing LNKCTL NFSv4.2: Rework scratch handling for READ_PLUS NFSv4.2: Fix READ_PLUS smatch warnings NFSv4.2: Fix up READ_PLUS alignment NFSv4.2: Fix READ_PLUS size calculations powerpc: Don't include lppaca.h in paca.h powerpc/pseries: Rework lppaca_shared_proc() to avoid DEBUG_PREEMPT nfs/blocklayout: Use the passed in gfp flags powerpc/pseries: Fix hcall tracepoints with JUMP_LABEL=n powerpc/mpc5xxx: Add missing fwnode_handle_put() powerpc/iommu: Fix notifiers being shared by PCI and VIO buses ext4: fix unttached inode after power cut with orphan file feature enabled jfs: validate max amount of blocks before allocation. fs: lockd: avoid possible wrong NULL parameter NFSD: da_addr_body field missing in some GETDEVICEINFO replies NFS: Guard against READDIR loop when entry names exceed MAXNAMELEN NFSv4.2: fix handling of COPY ERR_OFFLOAD_NO_REQ pNFS: Fix assignment of xprtdata.cred cgroup/cpuset: Inherit parent's load balance state in v2 RDMA/qedr: Remove a duplicate assignment in irdma_query_ah() media: ov5640: fix low resolution image abnormal issue media: ad5820: Drop unsupported ad5823 from i2c_ and of_device_id tables media: i2c: tvp5150: check return value of devm_kasprintf() media: v4l2-core: Fix a potential resource leak in v4l2_fwnode_parse_link() iommu/amd/iommu_v2: Fix pasid_state refcount dec hit 0 warning on pasid unbind iommu: rockchip: Fix directory table address encoding drivers: usb: smsusb: fix error handling code in smsusb_init_device media: dib7000p: Fix potential division by zero media: dvb-usb: m920x: Fix a potential memory leak in m920x_i2c_xfer() media: cx24120: Add retval check for cx24120_message_send() RDMA/siw: Fabricate a GID on tun and loopback devices scsi: hisi_sas: Fix warnings detected by sparse scsi: hisi_sas: Fix normally completed I/O analysed as failed dt-bindings: extcon: maxim,max77843: restrict connector properties media: amphion: reinit vpu if reqbufs output 0 media: amphion: add helper function to get id name media: mtk-jpeg: Fix use after free bug due to uncanceled work media: rkvdec: increase max supported height for H.264 media: amphion: fix CHECKED_RETURN issues reported by coverity media: amphion: fix REVERSE_INULL issues reported by coverity media: amphion: fix UNINIT issues reported by coverity media: amphion: fix UNUSED_VALUE issue reported by coverity media: amphion: ensure the bitops don't cross boundaries media: mediatek: vcodec: Return NULL if no vdec_fb is found media: mediatek: vcodec: fix potential double free media: mediatek: vcodec: fix resource leaks in vdec_msg_queue_init() usb: phy: mxs: fix getting wrong state with mxs_phy_is_otg_host() scsi: RDMA/srp: Fix residual handling scsi: iscsi: Rename iscsi_set_param() to iscsi_if_set_param() scsi: iscsi: Add length check for nlattr payload scsi: iscsi: Add strlen() check in iscsi_if_set{_host}_param() scsi: be2iscsi: Add length check when parsing nlattrs scsi: qla4xxx: Add length check when parsing nlattrs iio: accel: adxl313: Fix adxl313_i2c_id[] table serial: sprd: Assign sprd_port after initialized to avoid wrong access serial: sprd: Fix DMA buffer leak issue x86/APM: drop the duplicate APM_MINOR_DEV macro RDMA/rxe: Split rxe_run_task() into two subroutines RDMA/rxe: Fix incomplete state save in rxe_requester scsi: qedf: Do not touch __user pointer in qedf_dbg_stop_io_on_error_cmd_read() directly scsi: qedf: Do not touch __user pointer in qedf_dbg_debug_cmd_read() directly scsi: qedf: Do not touch __user pointer in qedf_dbg_fp_int_cmd_read() directly RDMA/irdma: Replace one-element array with flexible-array member coresight: tmc: Explicit type conversions to prevent integer overflow interconnect: qcom: qcm2290: Enable sync state dma-buf/sync_file: Fix docs syntax driver core: test_async: fix an error code driver core: Call dma_cleanup() on the test_remove path kernfs: add stub helper for kernfs_generic_poll() extcon: cht_wc: add POWER_SUPPLY dependency iommu/mediatek: Remove unused "mapping" member from mtk_iommu_data iommu/mediatek: Fix two IOMMU share pagetable issue iommu/sprd: Add missing force_aperture RDMA/hns: Fix port active speed RDMA/hns: Fix incorrect post-send with direct wqe of wr-list RDMA/hns: Fix inaccurate error label name in init instance RDMA/hns: Fix CQ and QP cache affinity IB/uverbs: Fix an potential error pointer dereference fsi: aspeed: Reset master errors after CFAM reset iommu/qcom: Disable and reset context bank before programming iommu/vt-d: Fix to flush cache of PASID directory table platform/x86: dell-sysman: Fix reference leak media: cec: core: add adap_nb_transmit_canceled() callback media: cec: core: add adap_unconfigured() callback media: go7007: Remove redundant if statement media: venus: hfi_venus: Only consider sys_idle_indicator on V1 docs: ABI: fix spelling/grammar in SBEFIFO timeout interface USB: gadget: core: Add missing kerneldoc for vbus_work USB: gadget: f_mass_storage: Fix unused variable warning drivers: base: Free devm resources when unregistering a device HID: input: Support devices sending Eraser without Invert media: ov5640: Enable MIPI interface in ov5640_set_power_mipi() media: ov5640: Fix initial RESETB state and annotate timings media: i2c: ov2680: Set V4L2_CTRL_FLAG_MODIFY_LAYOUT on flips media: ov2680: Remove auto-gain and auto-exposure controls media: ov2680: Fix ov2680_bayer_order() media: ov2680: Fix vflip / hflip set functions media: ov2680: Remove VIDEO_V4L2_SUBDEV_API ifdef-s media: ov2680: Don't take the lock for try_fmt calls media: ov2680: Add ov2680_fill_format() helper function media: ov2680: Fix ov2680_set_fmt() which == V4L2_SUBDEV_FORMAT_TRY not working media: ov2680: Fix regulators being left enabled on ov2680_power_on() errors media: i2c: rdacm21: Fix uninitialized value f2fs: fix to avoid mmap vs set_compress_option case f2fs: judge whether discard_unit is section only when have CONFIG_BLK_DEV_ZONED f2fs: Only lfs mode is allowed with zoned block device feature Revert "f2fs: fix to do sanity check on extent cache correctly" cgroup:namespace: Remove unused cgroup_namespaces_init() coresight: trbe: Fix TRBE potential sleep in atomic context RDMA/irdma: Prevent zero-length STAG registration scsi: core: Use 32-bit hostnum in scsi_host_lookup() scsi: fcoe: Fix potential deadlock on &fip->ctlr_lock interconnect: qcom: sm8450: Enable sync_state interconnect: qcom: bcm-voter: Improve enable_mask handling interconnect: qcom: bcm-voter: Use enable_maks for keepalive voting serial: tegra: handle clk prepare error in tegra_uart_hw_init() amba: bus: fix refcount leak Revert "IB/isert: Fix incorrect release of isert connection" RDMA/siw: Balance the reference of cep->kref in the error path RDMA/siw: Correct wrong debug message RDMA/efa: Fix wrong resources deallocation order HID: logitech-dj: Fix error handling in logi_dj_recv_switch_to_dj_mode() HID: uclogic: Correct devm device reference for hidinput input_dev name HID: multitouch: Correct devm device reference for hidinput input_dev name platform/x86/amd/pmf: Fix a missing cleanup path tick/rcu: Fix false positive "softirq work is pending" messages x86/speculation: Mark all Skylake CPUs as vulnerable to GDS tracing: Remove extra space at the end of hwlat_detector/mode tracing: Fix race issue between cpu buffer write and swap mtd: rawnand: brcmnand: Fix mtd oobsize dmaengine: idxd: Modify the dependence of attribute pasid_enabled phy/rockchip: inno-hdmi: use correct vco_div_5 macro on rk3328 phy/rockchip: inno-hdmi: round fractal pixclock in rk3328 recalc_rate phy/rockchip: inno-hdmi: do not power on rk3328 post pll on reg write rpmsg: glink: Add check for kstrdup leds: pwm: Fix error code in led_pwm_create_fwnode() leds: multicolor: Use rounded division when calculating color components leds: Fix BUG_ON check for LED_COLOR_ID_MULTI that is always false leds: trigger: tty: Do not use LED_ON/OFF constants, use led_blink_set_oneshot instead mtd: spi-nor: Check bus width while setting QE bit mtd: rawnand: fsmc: handle clk prepare error in fsmc_nand_resume() um: Fix hostaudio build errors dmaengine: ste_dma40: Add missing IRQ check in d40_probe Drivers: hv: vmbus: Don't dereference ACPI root object handle cpufreq: Fix the race condition while updating the transition_task of policy virtio_ring: fix avail_wrap_counter in virtqueue_add_packed igmp: limit igmpv3_newpack() packet size to IP_MAX_MTU netfilter: ipset: add the missing IP_SET_HASH_WITH_NET0 macro for ip_set_hash_netportnet.c netfilter: nft_exthdr: Fix non-linear header modification netfilter: xt_u32: validate user space input netfilter: xt_sctp: validate the flag_info count skbuff: skb_segment, Call zero copy functions before using skbuff frags igb: set max size RX buffer when store bad packet is enabled PM / devfreq: Fix leak in devfreq_dev_release() ALSA: pcm: Fix missing fixup call in compat hw_refine ioctl rcu: dump vmalloc memory info safely printk: ringbuffer: Fix truncating buffer size min_t cast scsi: core: Fix the scsi_set_resid() documentation mm/vmalloc: add a safer version of find_vm_area() for debug cpu/hotplug: Prevent self deadlock on CPU hot-unplug media: i2c: ccs: Check rules is non-NULL media: i2c: Add a camera sensor top level menu PCI: rockchip: Use 64-bit mask on MSI 64-bit PCI address ipmi_si: fix a memleak in try_smi_init() ARM: OMAP2+: Fix -Warray-bounds warning in _pwrdm_state_switch() XArray: Do not return sibling entries from xa_load() io_uring: break iopolling on signal backlight/gpio_backlight: Compare against struct fb_info.device backlight/bd6107: Compare against struct fb_info.device backlight/lv5207lp: Compare against struct fb_info.device drm/amd/display: register edp_backlight_control() for DCN301 xtensa: PMU: fix base address for the newer hardware LoongArch: mm: Add p?d_leaf() definitions i3c: master: svc: fix probe failure when no i3c device exist arm64: csum: Fix OoB access in IP checksum code for negative lengths ALSA: hda/cirrus: Fix broken audio on hardware with two CS42L42 codecs. media: dvb: symbol fixup for dvb_attach() media: venus: hfi_venus: Write to VIDC_CTRL_INIT after unmasking interrupts Revert "scsi: qla2xxx: Fix buffer overrun" scsi: mpt3sas: Perform additional retries if doorbell read returns 0 PCI: Free released resource after coalescing PCI: hv: Fix a crash in hv_pci_restore_msi_msg() during hibernation PCI/PM: Only read PCI_PM_CTRL register when available ntb: Drop packets when qp link is down ntb: Clean up tx tail index on link down ntb: Fix calculation ntb_transport_tx_free_entry() Revert "PCI: Mark NVIDIA T4 GPUs to avoid bus reset" block: don't add or resize partition on the disk with GENHD_FL_NO_PART procfs: block chmod on /proc/thread-self/comm parisc: Fix /proc/cpuinfo output for lscpu drm/amd/display: Add smu write msg id fail retry process bpf: Fix issue in verifying allow_ptr_leaks dlm: fix plock lookup when using multiple lockspaces dccp: Fix out of bounds access in DCCP error handler x86/sev: Make enc_dec_hypercall() accept a size instead of npages r8169: fix ASPM-related issues on a number of systems with NIC version from RTL8168h X.509: if signature is unsupported skip validation net: handle ARPHRD_PPP in dev_is_mac_header_xmit() fsverity: skip PKCS#7 parser when keyring is empty x86/MCE: Always save CS register on AMD Zen IF Poison errors platform/chrome: chromeos_acpi: print hex string for ACPI_TYPE_BUFFER mmc: renesas_sdhi: register irqs before registering controller pstore/ram: Check start of empty przs during init arm64: sdei: abort running SDEI handlers during crash s390/dcssblk: fix kernel crash with list_add corruption s390/ipl: add missing secure/has_secure file to ipl type 'unknown' s390/dasd: fix string length handling crypto: stm32 - fix loop iterating through scatterlist for DMA cpufreq: brcmstb-avs-cpufreq: Fix -Warray-bounds bug of: property: fw_devlink: Add a devlink for panel followers usb: typec: tcpm: set initial svdm version based on pd revision usb: typec: bus: verify partner exists in typec_altmode_attention USB: core: Unite old scheme and new scheme descriptor reads USB: core: Change usb_get_device_descriptor() API USB: core: Fix race by not overwriting udev->descriptor in hub_port_init() USB: core: Fix oversight in SuperSpeed initialization x86/sgx: Break up long non-preemptible delays in sgx_vepc_release() perf/x86/uncore: Correct the number of CHAs on EMR serial: sc16is7xx: remove obsolete out_thread label serial: sc16is7xx: fix regression with GPIO configuration tracing: Zero the pipe cpumask on alloc to avoid spurious -EBUSY Revert "drm/amd/display: Do not set drr on pipe commit" md: Free resources in __md_stop NFSv4.2: Fix a potential double free with READ_PLUS NFSv4.2: Rework scratch handling for READ_PLUS (again) md: fix regression for null-ptr-deference in __md_stop() clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro treewide: Fix probing of devices in DT overlays clk: Avoid invalid function names in CLK_OF_DECLARE() udf: initialize newblock to 0 Linux 6.1.53 Change-Id: I6f5858bce0f20963ae42515eac36ac14cb686f24 Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
1622 lines
40 KiB
C
1622 lines
40 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
|
|
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
|
|
* Copyright(C) 2006-2007 Timesys Corp., Thomas Gleixner
|
|
*
|
|
* No idle tick implementation for low and high resolution timers
|
|
*
|
|
* Started by: Thomas Gleixner and Ingo Molnar
|
|
*/
|
|
#include <linux/cpu.h>
|
|
#include <linux/err.h>
|
|
#include <linux/hrtimer.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/nmi.h>
|
|
#include <linux/profile.h>
|
|
#include <linux/sched/signal.h>
|
|
#include <linux/sched/clock.h>
|
|
#include <linux/sched/stat.h>
|
|
#include <linux/sched/nohz.h>
|
|
#include <linux/sched/loadavg.h>
|
|
#include <linux/module.h>
|
|
#include <linux/irq_work.h>
|
|
#include <linux/posix-timers.h>
|
|
#include <linux/context_tracking.h>
|
|
#include <linux/mm.h>
|
|
#include <trace/hooks/sched.h>
|
|
|
|
#include <asm/irq_regs.h>
|
|
|
|
#include "tick-internal.h"
|
|
|
|
#include <trace/events/timer.h>
|
|
|
|
/*
|
|
* Per-CPU nohz control structure
|
|
*/
|
|
static DEFINE_PER_CPU(struct tick_sched, tick_cpu_sched);
|
|
|
|
struct tick_sched *tick_get_tick_sched(int cpu)
|
|
{
|
|
return &per_cpu(tick_cpu_sched, cpu);
|
|
}
|
|
|
|
#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS)
|
|
/*
|
|
* The time, when the last jiffy update happened. Write access must hold
|
|
* jiffies_lock and jiffies_seq. tick_nohz_next_event() needs to get a
|
|
* consistent view of jiffies and last_jiffies_update.
|
|
*/
|
|
static ktime_t last_jiffies_update;
|
|
|
|
/*
|
|
* Must be called with interrupts disabled !
|
|
*/
|
|
static void tick_do_update_jiffies64(ktime_t now)
|
|
{
|
|
unsigned long ticks = 1;
|
|
ktime_t delta, nextp;
|
|
|
|
/*
|
|
* 64bit can do a quick check without holding jiffies lock and
|
|
* without looking at the sequence count. The smp_load_acquire()
|
|
* pairs with the update done later in this function.
|
|
*
|
|
* 32bit cannot do that because the store of tick_next_period
|
|
* consists of two 32bit stores and the first store could move it
|
|
* to a random point in the future.
|
|
*/
|
|
if (IS_ENABLED(CONFIG_64BIT)) {
|
|
if (ktime_before(now, smp_load_acquire(&tick_next_period)))
|
|
return;
|
|
} else {
|
|
unsigned int seq;
|
|
|
|
/*
|
|
* Avoid contention on jiffies_lock and protect the quick
|
|
* check with the sequence count.
|
|
*/
|
|
do {
|
|
seq = read_seqcount_begin(&jiffies_seq);
|
|
nextp = tick_next_period;
|
|
} while (read_seqcount_retry(&jiffies_seq, seq));
|
|
|
|
if (ktime_before(now, nextp))
|
|
return;
|
|
}
|
|
|
|
/* Quick check failed, i.e. update is required. */
|
|
raw_spin_lock(&jiffies_lock);
|
|
/*
|
|
* Reevaluate with the lock held. Another CPU might have done the
|
|
* update already.
|
|
*/
|
|
if (ktime_before(now, tick_next_period)) {
|
|
raw_spin_unlock(&jiffies_lock);
|
|
return;
|
|
}
|
|
|
|
write_seqcount_begin(&jiffies_seq);
|
|
|
|
delta = ktime_sub(now, tick_next_period);
|
|
if (unlikely(delta >= TICK_NSEC)) {
|
|
/* Slow path for long idle sleep times */
|
|
s64 incr = TICK_NSEC;
|
|
|
|
ticks += ktime_divns(delta, incr);
|
|
|
|
last_jiffies_update = ktime_add_ns(last_jiffies_update,
|
|
incr * ticks);
|
|
} else {
|
|
last_jiffies_update = ktime_add_ns(last_jiffies_update,
|
|
TICK_NSEC);
|
|
}
|
|
|
|
/* Advance jiffies to complete the jiffies_seq protected job */
|
|
jiffies_64 += ticks;
|
|
|
|
/*
|
|
* Keep the tick_next_period variable up to date.
|
|
*/
|
|
nextp = ktime_add_ns(last_jiffies_update, TICK_NSEC);
|
|
|
|
if (IS_ENABLED(CONFIG_64BIT)) {
|
|
/*
|
|
* Pairs with smp_load_acquire() in the lockless quick
|
|
* check above and ensures that the update to jiffies_64 is
|
|
* not reordered vs. the store to tick_next_period, neither
|
|
* by the compiler nor by the CPU.
|
|
*/
|
|
smp_store_release(&tick_next_period, nextp);
|
|
} else {
|
|
/*
|
|
* A plain store is good enough on 32bit as the quick check
|
|
* above is protected by the sequence count.
|
|
*/
|
|
tick_next_period = nextp;
|
|
}
|
|
|
|
/*
|
|
* Release the sequence count. calc_global_load() below is not
|
|
* protected by it, but jiffies_lock needs to be held to prevent
|
|
* concurrent invocations.
|
|
*/
|
|
write_seqcount_end(&jiffies_seq);
|
|
|
|
calc_global_load();
|
|
|
|
raw_spin_unlock(&jiffies_lock);
|
|
update_wall_time();
|
|
}
|
|
|
|
/*
|
|
* Initialize and return retrieve the jiffies update.
|
|
*/
|
|
static ktime_t tick_init_jiffy_update(void)
|
|
{
|
|
ktime_t period;
|
|
|
|
raw_spin_lock(&jiffies_lock);
|
|
write_seqcount_begin(&jiffies_seq);
|
|
/* Did we start the jiffies update yet ? */
|
|
if (last_jiffies_update == 0) {
|
|
u32 rem;
|
|
|
|
/*
|
|
* Ensure that the tick is aligned to a multiple of
|
|
* TICK_NSEC.
|
|
*/
|
|
div_u64_rem(tick_next_period, TICK_NSEC, &rem);
|
|
if (rem)
|
|
tick_next_period += TICK_NSEC - rem;
|
|
|
|
last_jiffies_update = tick_next_period;
|
|
}
|
|
period = last_jiffies_update;
|
|
write_seqcount_end(&jiffies_seq);
|
|
raw_spin_unlock(&jiffies_lock);
|
|
return period;
|
|
}
|
|
|
|
#define MAX_STALLED_JIFFIES 5
|
|
|
|
static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
|
|
{
|
|
int cpu = smp_processor_id();
|
|
|
|
#ifdef CONFIG_NO_HZ_COMMON
|
|
/*
|
|
* Check if the do_timer duty was dropped. We don't care about
|
|
* concurrency: This happens only when the CPU in charge went
|
|
* into a long sleep. If two CPUs happen to assign themselves to
|
|
* this duty, then the jiffies update is still serialized by
|
|
* jiffies_lock.
|
|
*
|
|
* If nohz_full is enabled, this should not happen because the
|
|
* tick_do_timer_cpu never relinquishes.
|
|
*/
|
|
if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) {
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
WARN_ON_ONCE(tick_nohz_full_running);
|
|
#endif
|
|
tick_do_timer_cpu = cpu;
|
|
}
|
|
#endif
|
|
|
|
/* Check, if the jiffies need an update */
|
|
if (tick_do_timer_cpu == cpu) {
|
|
tick_do_update_jiffies64(now);
|
|
trace_android_vh_jiffies_update(NULL);
|
|
}
|
|
|
|
/*
|
|
* If jiffies update stalled for too long (timekeeper in stop_machine()
|
|
* or VMEXIT'ed for several msecs), force an update.
|
|
*/
|
|
if (ts->last_tick_jiffies != jiffies) {
|
|
ts->stalled_jiffies = 0;
|
|
ts->last_tick_jiffies = READ_ONCE(jiffies);
|
|
} else {
|
|
if (++ts->stalled_jiffies == MAX_STALLED_JIFFIES) {
|
|
tick_do_update_jiffies64(now);
|
|
ts->stalled_jiffies = 0;
|
|
ts->last_tick_jiffies = READ_ONCE(jiffies);
|
|
}
|
|
}
|
|
|
|
if (ts->inidle)
|
|
ts->got_idle_tick = 1;
|
|
}
|
|
|
|
static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
|
|
{
|
|
#ifdef CONFIG_NO_HZ_COMMON
|
|
/*
|
|
* When we are idle and the tick is stopped, we have to touch
|
|
* the watchdog as we might not schedule for a really long
|
|
* time. This happens on complete idle SMP systems while
|
|
* waiting on the login prompt. We also increment the "start of
|
|
* idle" jiffy stamp so the idle accounting adjustment we do
|
|
* when we go busy again does not account too much ticks.
|
|
*/
|
|
if (ts->tick_stopped) {
|
|
touch_softlockup_watchdog_sched();
|
|
if (is_idle_task(current))
|
|
ts->idle_jiffies++;
|
|
/*
|
|
* In case the current tick fired too early past its expected
|
|
* expiration, make sure we don't bypass the next clock reprogramming
|
|
* to the same deadline.
|
|
*/
|
|
ts->next_tick = 0;
|
|
}
|
|
#endif
|
|
update_process_times(user_mode(regs));
|
|
profile_tick(CPU_PROFILING);
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
cpumask_var_t tick_nohz_full_mask;
|
|
EXPORT_SYMBOL_GPL(tick_nohz_full_mask);
|
|
bool tick_nohz_full_running;
|
|
EXPORT_SYMBOL_GPL(tick_nohz_full_running);
|
|
static atomic_t tick_dep_mask;
|
|
|
|
static bool check_tick_dependency(atomic_t *dep)
|
|
{
|
|
int val = atomic_read(dep);
|
|
|
|
if (val & TICK_DEP_MASK_POSIX_TIMER) {
|
|
trace_tick_stop(0, TICK_DEP_MASK_POSIX_TIMER);
|
|
return true;
|
|
}
|
|
|
|
if (val & TICK_DEP_MASK_PERF_EVENTS) {
|
|
trace_tick_stop(0, TICK_DEP_MASK_PERF_EVENTS);
|
|
return true;
|
|
}
|
|
|
|
if (val & TICK_DEP_MASK_SCHED) {
|
|
trace_tick_stop(0, TICK_DEP_MASK_SCHED);
|
|
return true;
|
|
}
|
|
|
|
if (val & TICK_DEP_MASK_CLOCK_UNSTABLE) {
|
|
trace_tick_stop(0, TICK_DEP_MASK_CLOCK_UNSTABLE);
|
|
return true;
|
|
}
|
|
|
|
if (val & TICK_DEP_MASK_RCU) {
|
|
trace_tick_stop(0, TICK_DEP_MASK_RCU);
|
|
return true;
|
|
}
|
|
|
|
if (val & TICK_DEP_MASK_RCU_EXP) {
|
|
trace_tick_stop(0, TICK_DEP_MASK_RCU_EXP);
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
static bool can_stop_full_tick(int cpu, struct tick_sched *ts)
|
|
{
|
|
lockdep_assert_irqs_disabled();
|
|
|
|
if (unlikely(!cpu_online(cpu)))
|
|
return false;
|
|
|
|
if (check_tick_dependency(&tick_dep_mask))
|
|
return false;
|
|
|
|
if (check_tick_dependency(&ts->tick_dep_mask))
|
|
return false;
|
|
|
|
if (check_tick_dependency(¤t->tick_dep_mask))
|
|
return false;
|
|
|
|
if (check_tick_dependency(¤t->signal->tick_dep_mask))
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
static void nohz_full_kick_func(struct irq_work *work)
|
|
{
|
|
/* Empty, the tick restart happens on tick_nohz_irq_exit() */
|
|
}
|
|
|
|
static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) =
|
|
IRQ_WORK_INIT_HARD(nohz_full_kick_func);
|
|
|
|
/*
|
|
* Kick this CPU if it's full dynticks in order to force it to
|
|
* re-evaluate its dependency on the tick and restart it if necessary.
|
|
* This kick, unlike tick_nohz_full_kick_cpu() and tick_nohz_full_kick_all(),
|
|
* is NMI safe.
|
|
*/
|
|
static void tick_nohz_full_kick(void)
|
|
{
|
|
if (!tick_nohz_full_cpu(smp_processor_id()))
|
|
return;
|
|
|
|
irq_work_queue(this_cpu_ptr(&nohz_full_kick_work));
|
|
}
|
|
|
|
/*
|
|
* Kick the CPU if it's full dynticks in order to force it to
|
|
* re-evaluate its dependency on the tick and restart it if necessary.
|
|
*/
|
|
void tick_nohz_full_kick_cpu(int cpu)
|
|
{
|
|
if (!tick_nohz_full_cpu(cpu))
|
|
return;
|
|
|
|
irq_work_queue_on(&per_cpu(nohz_full_kick_work, cpu), cpu);
|
|
}
|
|
|
|
static void tick_nohz_kick_task(struct task_struct *tsk)
|
|
{
|
|
int cpu;
|
|
|
|
/*
|
|
* If the task is not running, run_posix_cpu_timers()
|
|
* has nothing to elapse, IPI can then be spared.
|
|
*
|
|
* activate_task() STORE p->tick_dep_mask
|
|
* STORE p->on_rq
|
|
* __schedule() (switch to task 'p') smp_mb() (atomic_fetch_or())
|
|
* LOCK rq->lock LOAD p->on_rq
|
|
* smp_mb__after_spin_lock()
|
|
* tick_nohz_task_switch()
|
|
* LOAD p->tick_dep_mask
|
|
*/
|
|
if (!sched_task_on_rq(tsk))
|
|
return;
|
|
|
|
/*
|
|
* If the task concurrently migrates to another CPU,
|
|
* we guarantee it sees the new tick dependency upon
|
|
* schedule.
|
|
*
|
|
* set_task_cpu(p, cpu);
|
|
* STORE p->cpu = @cpu
|
|
* __schedule() (switch to task 'p')
|
|
* LOCK rq->lock
|
|
* smp_mb__after_spin_lock() STORE p->tick_dep_mask
|
|
* tick_nohz_task_switch() smp_mb() (atomic_fetch_or())
|
|
* LOAD p->tick_dep_mask LOAD p->cpu
|
|
*/
|
|
cpu = task_cpu(tsk);
|
|
|
|
preempt_disable();
|
|
if (cpu_online(cpu))
|
|
tick_nohz_full_kick_cpu(cpu);
|
|
preempt_enable();
|
|
}
|
|
|
|
/*
|
|
* Kick all full dynticks CPUs in order to force these to re-evaluate
|
|
* their dependency on the tick and restart it if necessary.
|
|
*/
|
|
static void tick_nohz_full_kick_all(void)
|
|
{
|
|
int cpu;
|
|
|
|
if (!tick_nohz_full_running)
|
|
return;
|
|
|
|
preempt_disable();
|
|
for_each_cpu_and(cpu, tick_nohz_full_mask, cpu_online_mask)
|
|
tick_nohz_full_kick_cpu(cpu);
|
|
preempt_enable();
|
|
}
|
|
|
|
static void tick_nohz_dep_set_all(atomic_t *dep,
|
|
enum tick_dep_bits bit)
|
|
{
|
|
int prev;
|
|
|
|
prev = atomic_fetch_or(BIT(bit), dep);
|
|
if (!prev)
|
|
tick_nohz_full_kick_all();
|
|
}
|
|
|
|
/*
|
|
* Set a global tick dependency. Used by perf events that rely on freq and
|
|
* by unstable clock.
|
|
*/
|
|
void tick_nohz_dep_set(enum tick_dep_bits bit)
|
|
{
|
|
tick_nohz_dep_set_all(&tick_dep_mask, bit);
|
|
}
|
|
|
|
void tick_nohz_dep_clear(enum tick_dep_bits bit)
|
|
{
|
|
atomic_andnot(BIT(bit), &tick_dep_mask);
|
|
}
|
|
|
|
/*
|
|
* Set per-CPU tick dependency. Used by scheduler and perf events in order to
|
|
* manage events throttling.
|
|
*/
|
|
void tick_nohz_dep_set_cpu(int cpu, enum tick_dep_bits bit)
|
|
{
|
|
int prev;
|
|
struct tick_sched *ts;
|
|
|
|
ts = per_cpu_ptr(&tick_cpu_sched, cpu);
|
|
|
|
prev = atomic_fetch_or(BIT(bit), &ts->tick_dep_mask);
|
|
if (!prev) {
|
|
preempt_disable();
|
|
/* Perf needs local kick that is NMI safe */
|
|
if (cpu == smp_processor_id()) {
|
|
tick_nohz_full_kick();
|
|
} else {
|
|
/* Remote irq work not NMI-safe */
|
|
if (!WARN_ON_ONCE(in_nmi()))
|
|
tick_nohz_full_kick_cpu(cpu);
|
|
}
|
|
preempt_enable();
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(tick_nohz_dep_set_cpu);
|
|
|
|
void tick_nohz_dep_clear_cpu(int cpu, enum tick_dep_bits bit)
|
|
{
|
|
struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu);
|
|
|
|
atomic_andnot(BIT(bit), &ts->tick_dep_mask);
|
|
}
|
|
EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cpu);
|
|
|
|
/*
|
|
* Set a per-task tick dependency. RCU need this. Also posix CPU timers
|
|
* in order to elapse per task timers.
|
|
*/
|
|
void tick_nohz_dep_set_task(struct task_struct *tsk, enum tick_dep_bits bit)
|
|
{
|
|
if (!atomic_fetch_or(BIT(bit), &tsk->tick_dep_mask))
|
|
tick_nohz_kick_task(tsk);
|
|
}
|
|
EXPORT_SYMBOL_GPL(tick_nohz_dep_set_task);
|
|
|
|
void tick_nohz_dep_clear_task(struct task_struct *tsk, enum tick_dep_bits bit)
|
|
{
|
|
atomic_andnot(BIT(bit), &tsk->tick_dep_mask);
|
|
}
|
|
EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_task);
|
|
|
|
/*
|
|
* Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse
|
|
* per process timers.
|
|
*/
|
|
void tick_nohz_dep_set_signal(struct task_struct *tsk,
|
|
enum tick_dep_bits bit)
|
|
{
|
|
int prev;
|
|
struct signal_struct *sig = tsk->signal;
|
|
|
|
prev = atomic_fetch_or(BIT(bit), &sig->tick_dep_mask);
|
|
if (!prev) {
|
|
struct task_struct *t;
|
|
|
|
lockdep_assert_held(&tsk->sighand->siglock);
|
|
__for_each_thread(sig, t)
|
|
tick_nohz_kick_task(t);
|
|
}
|
|
}
|
|
|
|
void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit)
|
|
{
|
|
atomic_andnot(BIT(bit), &sig->tick_dep_mask);
|
|
}
|
|
|
|
/*
|
|
* Re-evaluate the need for the tick as we switch the current task.
|
|
* It might need the tick due to per task/process properties:
|
|
* perf events, posix CPU timers, ...
|
|
*/
|
|
void __tick_nohz_task_switch(void)
|
|
{
|
|
struct tick_sched *ts;
|
|
|
|
if (!tick_nohz_full_cpu(smp_processor_id()))
|
|
return;
|
|
|
|
ts = this_cpu_ptr(&tick_cpu_sched);
|
|
|
|
if (ts->tick_stopped) {
|
|
if (atomic_read(¤t->tick_dep_mask) ||
|
|
atomic_read(¤t->signal->tick_dep_mask))
|
|
tick_nohz_full_kick();
|
|
}
|
|
}
|
|
|
|
/* Get the boot-time nohz CPU list from the kernel parameters. */
|
|
void __init tick_nohz_full_setup(cpumask_var_t cpumask)
|
|
{
|
|
alloc_bootmem_cpumask_var(&tick_nohz_full_mask);
|
|
cpumask_copy(tick_nohz_full_mask, cpumask);
|
|
tick_nohz_full_running = true;
|
|
}
|
|
|
|
bool tick_nohz_cpu_hotpluggable(unsigned int cpu)
|
|
{
|
|
/*
|
|
* The tick_do_timer_cpu CPU handles housekeeping duty (unbound
|
|
* timers, workqueues, timekeeping, ...) on behalf of full dynticks
|
|
* CPUs. It must remain online when nohz full is enabled.
|
|
*/
|
|
if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
|
|
return false;
|
|
return true;
|
|
}
|
|
|
|
static int tick_nohz_cpu_down(unsigned int cpu)
|
|
{
|
|
return tick_nohz_cpu_hotpluggable(cpu) ? 0 : -EBUSY;
|
|
}
|
|
|
|
void __init tick_nohz_init(void)
|
|
{
|
|
int cpu, ret;
|
|
|
|
if (!tick_nohz_full_running)
|
|
return;
|
|
|
|
/*
|
|
* Full dynticks uses irq work to drive the tick rescheduling on safe
|
|
* locking contexts. But then we need irq work to raise its own
|
|
* interrupts to avoid circular dependency on the tick
|
|
*/
|
|
if (!arch_irq_work_has_interrupt()) {
|
|
pr_warn("NO_HZ: Can't run full dynticks because arch doesn't support irq work self-IPIs\n");
|
|
cpumask_clear(tick_nohz_full_mask);
|
|
tick_nohz_full_running = false;
|
|
return;
|
|
}
|
|
|
|
if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) &&
|
|
!IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) {
|
|
cpu = smp_processor_id();
|
|
|
|
if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) {
|
|
pr_warn("NO_HZ: Clearing %d from nohz_full range "
|
|
"for timekeeping\n", cpu);
|
|
cpumask_clear_cpu(cpu, tick_nohz_full_mask);
|
|
}
|
|
}
|
|
|
|
for_each_cpu(cpu, tick_nohz_full_mask)
|
|
ct_cpu_track_user(cpu);
|
|
|
|
ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
|
|
"kernel/nohz:predown", NULL,
|
|
tick_nohz_cpu_down);
|
|
WARN_ON(ret < 0);
|
|
pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n",
|
|
cpumask_pr_args(tick_nohz_full_mask));
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* NOHZ - aka dynamic tick functionality
|
|
*/
|
|
#ifdef CONFIG_NO_HZ_COMMON
|
|
/*
|
|
* NO HZ enabled ?
|
|
*/
|
|
bool tick_nohz_enabled __read_mostly = true;
|
|
unsigned long tick_nohz_active __read_mostly;
|
|
/*
|
|
* Enable / Disable tickless mode
|
|
*/
|
|
static int __init setup_tick_nohz(char *str)
|
|
{
|
|
return (kstrtobool(str, &tick_nohz_enabled) == 0);
|
|
}
|
|
|
|
__setup("nohz=", setup_tick_nohz);
|
|
|
|
bool tick_nohz_tick_stopped(void)
|
|
{
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
|
|
return ts->tick_stopped;
|
|
}
|
|
|
|
bool tick_nohz_tick_stopped_cpu(int cpu)
|
|
{
|
|
struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu);
|
|
|
|
return ts->tick_stopped;
|
|
}
|
|
|
|
/**
|
|
* tick_nohz_update_jiffies - update jiffies when idle was interrupted
|
|
*
|
|
* Called from interrupt entry when the CPU was idle
|
|
*
|
|
* In case the sched_tick was stopped on this CPU, we have to check if jiffies
|
|
* must be updated. Otherwise an interrupt handler could use a stale jiffy
|
|
* value. We do this unconditionally on any CPU, as we don't know whether the
|
|
* CPU, which has the update task assigned is in a long sleep.
|
|
*/
|
|
static void tick_nohz_update_jiffies(ktime_t now)
|
|
{
|
|
unsigned long flags;
|
|
|
|
__this_cpu_write(tick_cpu_sched.idle_waketime, now);
|
|
|
|
local_irq_save(flags);
|
|
tick_do_update_jiffies64(now);
|
|
local_irq_restore(flags);
|
|
|
|
touch_softlockup_watchdog_sched();
|
|
}
|
|
|
|
/*
|
|
* Updates the per-CPU time idle statistics counters
|
|
*/
|
|
static void
|
|
update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_update_time)
|
|
{
|
|
ktime_t delta;
|
|
|
|
if (ts->idle_active) {
|
|
delta = ktime_sub(now, ts->idle_entrytime);
|
|
if (nr_iowait_cpu(cpu) > 0)
|
|
ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
|
|
else
|
|
ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
|
|
ts->idle_entrytime = now;
|
|
}
|
|
|
|
if (last_update_time)
|
|
*last_update_time = ktime_to_us(now);
|
|
|
|
}
|
|
|
|
static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
|
|
{
|
|
update_ts_time_stats(smp_processor_id(), ts, now, NULL);
|
|
ts->idle_active = 0;
|
|
|
|
sched_clock_idle_wakeup_event();
|
|
}
|
|
|
|
static void tick_nohz_start_idle(struct tick_sched *ts)
|
|
{
|
|
ts->idle_entrytime = ktime_get();
|
|
ts->idle_active = 1;
|
|
sched_clock_idle_sleep_event();
|
|
}
|
|
|
|
/**
|
|
* get_cpu_idle_time_us - get the total idle time of a CPU
|
|
* @cpu: CPU number to query
|
|
* @last_update_time: variable to store update time in. Do not update
|
|
* counters if NULL.
|
|
*
|
|
* Return the cumulative idle time (since boot) for a given
|
|
* CPU, in microseconds.
|
|
*
|
|
* This time is measured via accounting rather than sampling,
|
|
* and is as accurate as ktime_get() is.
|
|
*
|
|
* This function returns -1 if NOHZ is not enabled.
|
|
*/
|
|
u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
|
|
{
|
|
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
|
|
ktime_t now, idle;
|
|
|
|
if (!tick_nohz_active)
|
|
return -1;
|
|
|
|
now = ktime_get();
|
|
if (last_update_time) {
|
|
update_ts_time_stats(cpu, ts, now, last_update_time);
|
|
idle = ts->idle_sleeptime;
|
|
} else {
|
|
if (ts->idle_active && !nr_iowait_cpu(cpu)) {
|
|
ktime_t delta = ktime_sub(now, ts->idle_entrytime);
|
|
|
|
idle = ktime_add(ts->idle_sleeptime, delta);
|
|
} else {
|
|
idle = ts->idle_sleeptime;
|
|
}
|
|
}
|
|
|
|
return ktime_to_us(idle);
|
|
|
|
}
|
|
EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
|
|
|
|
/**
|
|
* get_cpu_iowait_time_us - get the total iowait time of a CPU
|
|
* @cpu: CPU number to query
|
|
* @last_update_time: variable to store update time in. Do not update
|
|
* counters if NULL.
|
|
*
|
|
* Return the cumulative iowait time (since boot) for a given
|
|
* CPU, in microseconds.
|
|
*
|
|
* This time is measured via accounting rather than sampling,
|
|
* and is as accurate as ktime_get() is.
|
|
*
|
|
* This function returns -1 if NOHZ is not enabled.
|
|
*/
|
|
u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
|
|
{
|
|
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
|
|
ktime_t now, iowait;
|
|
|
|
if (!tick_nohz_active)
|
|
return -1;
|
|
|
|
now = ktime_get();
|
|
if (last_update_time) {
|
|
update_ts_time_stats(cpu, ts, now, last_update_time);
|
|
iowait = ts->iowait_sleeptime;
|
|
} else {
|
|
if (ts->idle_active && nr_iowait_cpu(cpu) > 0) {
|
|
ktime_t delta = ktime_sub(now, ts->idle_entrytime);
|
|
|
|
iowait = ktime_add(ts->iowait_sleeptime, delta);
|
|
} else {
|
|
iowait = ts->iowait_sleeptime;
|
|
}
|
|
}
|
|
|
|
return ktime_to_us(iowait);
|
|
}
|
|
EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
|
|
|
|
static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
|
|
{
|
|
hrtimer_cancel(&ts->sched_timer);
|
|
hrtimer_set_expires(&ts->sched_timer, ts->last_tick);
|
|
|
|
/* Forward the time to expire in the future */
|
|
hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
|
|
|
|
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
|
|
hrtimer_start_expires(&ts->sched_timer,
|
|
HRTIMER_MODE_ABS_PINNED_HARD);
|
|
} else {
|
|
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
|
|
}
|
|
|
|
/*
|
|
* Reset to make sure next tick stop doesn't get fooled by past
|
|
* cached clock deadline.
|
|
*/
|
|
ts->next_tick = 0;
|
|
}
|
|
|
|
static inline bool local_timer_softirq_pending(void)
|
|
{
|
|
return local_softirq_pending() & BIT(TIMER_SOFTIRQ);
|
|
}
|
|
|
|
static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
|
|
{
|
|
u64 basemono, next_tick, delta, expires;
|
|
unsigned long basejiff;
|
|
unsigned int seq;
|
|
|
|
/* Read jiffies and the time when jiffies were updated last */
|
|
do {
|
|
seq = read_seqcount_begin(&jiffies_seq);
|
|
basemono = last_jiffies_update;
|
|
basejiff = jiffies;
|
|
} while (read_seqcount_retry(&jiffies_seq, seq));
|
|
ts->last_jiffies = basejiff;
|
|
ts->timer_expires_base = basemono;
|
|
|
|
/*
|
|
* Keep the periodic tick, when RCU, architecture or irq_work
|
|
* requests it.
|
|
* Aside of that check whether the local timer softirq is
|
|
* pending. If so its a bad idea to call get_next_timer_interrupt()
|
|
* because there is an already expired timer, so it will request
|
|
* immediate expiry, which rearms the hardware timer with a
|
|
* minimal delta which brings us back to this place
|
|
* immediately. Lather, rinse and repeat...
|
|
*/
|
|
if (rcu_needs_cpu() || arch_needs_cpu() ||
|
|
irq_work_needs_cpu() || local_timer_softirq_pending()) {
|
|
next_tick = basemono + TICK_NSEC;
|
|
} else {
|
|
/*
|
|
* Get the next pending timer. If high resolution
|
|
* timers are enabled this only takes the timer wheel
|
|
* timers into account. If high resolution timers are
|
|
* disabled this also looks at the next expiring
|
|
* hrtimer.
|
|
*/
|
|
next_tick = get_next_timer_interrupt(basejiff, basemono);
|
|
ts->next_timer = next_tick;
|
|
}
|
|
|
|
/*
|
|
* If the tick is due in the next period, keep it ticking or
|
|
* force prod the timer.
|
|
*/
|
|
delta = next_tick - basemono;
|
|
if (delta <= (u64)TICK_NSEC) {
|
|
/*
|
|
* Tell the timer code that the base is not idle, i.e. undo
|
|
* the effect of get_next_timer_interrupt():
|
|
*/
|
|
timer_clear_idle();
|
|
/*
|
|
* We've not stopped the tick yet, and there's a timer in the
|
|
* next period, so no point in stopping it either, bail.
|
|
*/
|
|
if (!ts->tick_stopped) {
|
|
ts->timer_expires = 0;
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* If this CPU is the one which had the do_timer() duty last, we limit
|
|
* the sleep time to the timekeeping max_deferment value.
|
|
* Otherwise we can sleep as long as we want.
|
|
*/
|
|
delta = timekeeping_max_deferment();
|
|
if (cpu != tick_do_timer_cpu &&
|
|
(tick_do_timer_cpu != TICK_DO_TIMER_NONE || !ts->do_timer_last))
|
|
delta = KTIME_MAX;
|
|
|
|
/* Calculate the next expiry time */
|
|
if (delta < (KTIME_MAX - basemono))
|
|
expires = basemono + delta;
|
|
else
|
|
expires = KTIME_MAX;
|
|
|
|
ts->timer_expires = min_t(u64, expires, next_tick);
|
|
|
|
out:
|
|
return ts->timer_expires;
|
|
}
|
|
|
|
static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
|
|
{
|
|
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
|
|
u64 basemono = ts->timer_expires_base;
|
|
u64 expires = ts->timer_expires;
|
|
ktime_t tick = expires;
|
|
|
|
/* Make sure we won't be trying to stop it twice in a row. */
|
|
ts->timer_expires_base = 0;
|
|
|
|
/*
|
|
* If this CPU is the one which updates jiffies, then give up
|
|
* the assignment and let it be taken by the CPU which runs
|
|
* the tick timer next, which might be this CPU as well. If we
|
|
* don't drop this here the jiffies might be stale and
|
|
* do_timer() never invoked. Keep track of the fact that it
|
|
* was the one which had the do_timer() duty last.
|
|
*/
|
|
if (cpu == tick_do_timer_cpu) {
|
|
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
|
|
ts->do_timer_last = 1;
|
|
} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
|
|
ts->do_timer_last = 0;
|
|
}
|
|
|
|
/* Skip reprogram of event if its not changed */
|
|
if (ts->tick_stopped && (expires == ts->next_tick)) {
|
|
/* Sanity check: make sure clockevent is actually programmed */
|
|
if (tick == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer))
|
|
return;
|
|
|
|
WARN_ON_ONCE(1);
|
|
printk_once("basemono: %llu ts->next_tick: %llu dev->next_event: %llu timer->active: %d timer->expires: %llu\n",
|
|
basemono, ts->next_tick, dev->next_event,
|
|
hrtimer_active(&ts->sched_timer), hrtimer_get_expires(&ts->sched_timer));
|
|
}
|
|
|
|
/*
|
|
* nohz_stop_sched_tick can be called several times before
|
|
* the nohz_restart_sched_tick is called. This happens when
|
|
* interrupts arrive which do not cause a reschedule. In the
|
|
* first call we save the current tick time, so we can restart
|
|
* the scheduler tick in nohz_restart_sched_tick.
|
|
*/
|
|
if (!ts->tick_stopped) {
|
|
calc_load_nohz_start();
|
|
quiet_vmstat();
|
|
|
|
ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
|
|
ts->tick_stopped = 1;
|
|
trace_tick_stop(1, TICK_DEP_MASK_NONE);
|
|
}
|
|
|
|
ts->next_tick = tick;
|
|
|
|
/*
|
|
* If the expiration time == KTIME_MAX, then we simply stop
|
|
* the tick timer.
|
|
*/
|
|
if (unlikely(expires == KTIME_MAX)) {
|
|
if (ts->nohz_mode == NOHZ_MODE_HIGHRES)
|
|
hrtimer_cancel(&ts->sched_timer);
|
|
else
|
|
tick_program_event(KTIME_MAX, 1);
|
|
return;
|
|
}
|
|
|
|
if (ts->nohz_mode == NOHZ_MODE_HIGHRES) {
|
|
hrtimer_start(&ts->sched_timer, tick,
|
|
HRTIMER_MODE_ABS_PINNED_HARD);
|
|
} else {
|
|
hrtimer_set_expires(&ts->sched_timer, tick);
|
|
tick_program_event(tick, 1);
|
|
}
|
|
}
|
|
|
|
static void tick_nohz_retain_tick(struct tick_sched *ts)
|
|
{
|
|
ts->timer_expires_base = 0;
|
|
}
|
|
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
static void tick_nohz_stop_sched_tick(struct tick_sched *ts, int cpu)
|
|
{
|
|
if (tick_nohz_next_event(ts, cpu))
|
|
tick_nohz_stop_tick(ts, cpu);
|
|
else
|
|
tick_nohz_retain_tick(ts);
|
|
}
|
|
#endif /* CONFIG_NO_HZ_FULL */
|
|
|
|
static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
|
|
{
|
|
/* Update jiffies first */
|
|
tick_do_update_jiffies64(now);
|
|
|
|
/*
|
|
* Clear the timer idle flag, so we avoid IPIs on remote queueing and
|
|
* the clock forward checks in the enqueue path:
|
|
*/
|
|
timer_clear_idle();
|
|
|
|
calc_load_nohz_stop();
|
|
touch_softlockup_watchdog_sched();
|
|
/*
|
|
* Cancel the scheduled timer and restore the tick
|
|
*/
|
|
ts->tick_stopped = 0;
|
|
tick_nohz_restart(ts, now);
|
|
}
|
|
|
|
static void __tick_nohz_full_update_tick(struct tick_sched *ts,
|
|
ktime_t now)
|
|
{
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
int cpu = smp_processor_id();
|
|
|
|
if (can_stop_full_tick(cpu, ts))
|
|
tick_nohz_stop_sched_tick(ts, cpu);
|
|
else if (ts->tick_stopped)
|
|
tick_nohz_restart_sched_tick(ts, now);
|
|
#endif
|
|
}
|
|
|
|
static void tick_nohz_full_update_tick(struct tick_sched *ts)
|
|
{
|
|
if (!tick_nohz_full_cpu(smp_processor_id()))
|
|
return;
|
|
|
|
if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
|
|
return;
|
|
|
|
__tick_nohz_full_update_tick(ts, ktime_get());
|
|
}
|
|
|
|
/*
|
|
* A pending softirq outside an IRQ (or softirq disabled section) context
|
|
* should be waiting for ksoftirqd to handle it. Therefore we shouldn't
|
|
* reach here due to the need_resched() early check in can_stop_idle_tick().
|
|
*
|
|
* However if we are between CPUHP_AP_SMPBOOT_THREADS and CPU_TEARDOWN_CPU on the
|
|
* cpu_down() process, softirqs can still be raised while ksoftirqd is parked,
|
|
* triggering the below since wakep_softirqd() is ignored.
|
|
*
|
|
*/
|
|
static bool report_idle_softirq(void)
|
|
{
|
|
static int ratelimit;
|
|
unsigned int pending = local_softirq_pending();
|
|
|
|
if (likely(!pending))
|
|
return false;
|
|
|
|
/* Some softirqs claim to be safe against hotplug and ksoftirqd parking */
|
|
if (!cpu_active(smp_processor_id())) {
|
|
pending &= ~SOFTIRQ_HOTPLUG_SAFE_MASK;
|
|
if (!pending)
|
|
return false;
|
|
}
|
|
|
|
if (ratelimit >= 10)
|
|
return false;
|
|
|
|
/* On RT, softirqs handling may be waiting on some lock */
|
|
if (local_bh_blocked())
|
|
return false;
|
|
|
|
pr_warn("NOHZ tick-stop error: local softirq work is pending, handler #%02x!!!\n",
|
|
pending);
|
|
ratelimit++;
|
|
|
|
return true;
|
|
}
|
|
|
|
static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
|
|
{
|
|
/*
|
|
* If this CPU is offline and it is the one which updates
|
|
* jiffies, then give up the assignment and let it be taken by
|
|
* the CPU which runs the tick timer next. If we don't drop
|
|
* this here the jiffies might be stale and do_timer() never
|
|
* invoked.
|
|
*/
|
|
if (unlikely(!cpu_online(cpu))) {
|
|
if (cpu == tick_do_timer_cpu)
|
|
tick_do_timer_cpu = TICK_DO_TIMER_NONE;
|
|
/*
|
|
* Make sure the CPU doesn't get fooled by obsolete tick
|
|
* deadline if it comes back online later.
|
|
*/
|
|
ts->next_tick = 0;
|
|
return false;
|
|
}
|
|
|
|
if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
|
|
return false;
|
|
|
|
if (need_resched())
|
|
return false;
|
|
|
|
if (unlikely(report_idle_softirq()))
|
|
return false;
|
|
|
|
if (tick_nohz_full_enabled()) {
|
|
/*
|
|
* Keep the tick alive to guarantee timekeeping progression
|
|
* if there are full dynticks CPUs around
|
|
*/
|
|
if (tick_do_timer_cpu == cpu)
|
|
return false;
|
|
|
|
/* Should not happen for nohz-full */
|
|
if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
|
|
return false;
|
|
}
|
|
|
|
return true;
|
|
}
|
|
|
|
static void __tick_nohz_idle_stop_tick(struct tick_sched *ts)
|
|
{
|
|
ktime_t expires;
|
|
int cpu = smp_processor_id();
|
|
|
|
/*
|
|
* If tick_nohz_get_sleep_length() ran tick_nohz_next_event(), the
|
|
* tick timer expiration time is known already.
|
|
*/
|
|
if (ts->timer_expires_base)
|
|
expires = ts->timer_expires;
|
|
else if (can_stop_idle_tick(cpu, ts))
|
|
expires = tick_nohz_next_event(ts, cpu);
|
|
else
|
|
return;
|
|
|
|
ts->idle_calls++;
|
|
|
|
if (expires > 0LL) {
|
|
int was_stopped = ts->tick_stopped;
|
|
|
|
tick_nohz_stop_tick(ts, cpu);
|
|
|
|
ts->idle_sleeps++;
|
|
ts->idle_expires = expires;
|
|
|
|
if (!was_stopped && ts->tick_stopped) {
|
|
ts->idle_jiffies = ts->last_jiffies;
|
|
nohz_balance_enter_idle(cpu);
|
|
}
|
|
} else {
|
|
tick_nohz_retain_tick(ts);
|
|
}
|
|
}
|
|
|
|
/**
|
|
* tick_nohz_idle_stop_tick - stop the idle tick from the idle task
|
|
*
|
|
* When the next event is more than a tick into the future, stop the idle tick
|
|
*/
|
|
void tick_nohz_idle_stop_tick(void)
|
|
{
|
|
__tick_nohz_idle_stop_tick(this_cpu_ptr(&tick_cpu_sched));
|
|
}
|
|
|
|
void tick_nohz_idle_retain_tick(void)
|
|
{
|
|
tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched));
|
|
/*
|
|
* Undo the effect of get_next_timer_interrupt() called from
|
|
* tick_nohz_next_event().
|
|
*/
|
|
timer_clear_idle();
|
|
}
|
|
|
|
/**
|
|
* tick_nohz_idle_enter - prepare for entering idle on the current CPU
|
|
*
|
|
* Called when we start the idle loop.
|
|
*/
|
|
void tick_nohz_idle_enter(void)
|
|
{
|
|
struct tick_sched *ts;
|
|
|
|
lockdep_assert_irqs_enabled();
|
|
|
|
local_irq_disable();
|
|
|
|
ts = this_cpu_ptr(&tick_cpu_sched);
|
|
|
|
WARN_ON_ONCE(ts->timer_expires_base);
|
|
|
|
ts->inidle = 1;
|
|
tick_nohz_start_idle(ts);
|
|
|
|
local_irq_enable();
|
|
}
|
|
|
|
/**
|
|
* tick_nohz_irq_exit - update next tick event from interrupt exit
|
|
*
|
|
* When an interrupt fires while we are idle and it doesn't cause
|
|
* a reschedule, it may still add, modify or delete a timer, enqueue
|
|
* an RCU callback, etc...
|
|
* So we need to re-calculate and reprogram the next tick event.
|
|
*/
|
|
void tick_nohz_irq_exit(void)
|
|
{
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
|
|
if (ts->inidle)
|
|
tick_nohz_start_idle(ts);
|
|
else
|
|
tick_nohz_full_update_tick(ts);
|
|
}
|
|
|
|
/**
|
|
* tick_nohz_idle_got_tick - Check whether or not the tick handler has run
|
|
*/
|
|
bool tick_nohz_idle_got_tick(void)
|
|
{
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
|
|
if (ts->got_idle_tick) {
|
|
ts->got_idle_tick = 0;
|
|
return true;
|
|
}
|
|
return false;
|
|
}
|
|
|
|
/**
|
|
* tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer
|
|
* or the tick, whatever that expires first. Note that, if the tick has been
|
|
* stopped, it returns the next hrtimer.
|
|
*
|
|
* Called from power state control code with interrupts disabled
|
|
*/
|
|
ktime_t tick_nohz_get_next_hrtimer(void)
|
|
{
|
|
return __this_cpu_read(tick_cpu_device.evtdev)->next_event;
|
|
}
|
|
|
|
/**
|
|
* tick_nohz_get_sleep_length - return the expected length of the current sleep
|
|
* @delta_next: duration until the next event if the tick cannot be stopped
|
|
*
|
|
* Called from power state control code with interrupts disabled.
|
|
*
|
|
* The return value of this function and/or the value returned by it through the
|
|
* @delta_next pointer can be negative which must be taken into account by its
|
|
* callers.
|
|
*/
|
|
ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next)
|
|
{
|
|
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
int cpu = smp_processor_id();
|
|
/*
|
|
* The idle entry time is expected to be a sufficient approximation of
|
|
* the current time at this point.
|
|
*/
|
|
ktime_t now = ts->idle_entrytime;
|
|
ktime_t next_event;
|
|
|
|
WARN_ON_ONCE(!ts->inidle);
|
|
|
|
*delta_next = ktime_sub(dev->next_event, now);
|
|
|
|
if (!can_stop_idle_tick(cpu, ts))
|
|
return *delta_next;
|
|
|
|
next_event = tick_nohz_next_event(ts, cpu);
|
|
if (!next_event)
|
|
return *delta_next;
|
|
|
|
/*
|
|
* If the next highres timer to expire is earlier than next_event, the
|
|
* idle governor needs to know that.
|
|
*/
|
|
next_event = min_t(u64, next_event,
|
|
hrtimer_next_event_without(&ts->sched_timer));
|
|
|
|
return ktime_sub(next_event, now);
|
|
}
|
|
EXPORT_SYMBOL_GPL(tick_nohz_get_sleep_length);
|
|
|
|
/**
|
|
* tick_nohz_get_idle_calls_cpu - return the current idle calls counter value
|
|
* for a particular CPU.
|
|
*
|
|
* Called from the schedutil frequency scaling governor in scheduler context.
|
|
*/
|
|
unsigned long tick_nohz_get_idle_calls_cpu(int cpu)
|
|
{
|
|
struct tick_sched *ts = tick_get_tick_sched(cpu);
|
|
|
|
return ts->idle_calls;
|
|
}
|
|
EXPORT_SYMBOL_GPL(tick_nohz_get_idle_calls_cpu);
|
|
|
|
/**
|
|
* tick_nohz_get_idle_calls - return the current idle calls counter value
|
|
*
|
|
* Called from the schedutil frequency scaling governor in scheduler context.
|
|
*/
|
|
unsigned long tick_nohz_get_idle_calls(void)
|
|
{
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
|
|
return ts->idle_calls;
|
|
}
|
|
|
|
static void tick_nohz_account_idle_time(struct tick_sched *ts,
|
|
ktime_t now)
|
|
{
|
|
unsigned long ticks;
|
|
|
|
ts->idle_exittime = now;
|
|
|
|
if (vtime_accounting_enabled_this_cpu())
|
|
return;
|
|
/*
|
|
* We stopped the tick in idle. Update process times would miss the
|
|
* time we slept as update_process_times does only a 1 tick
|
|
* accounting. Enforce that this is accounted to idle !
|
|
*/
|
|
ticks = jiffies - ts->idle_jiffies;
|
|
/*
|
|
* We might be one off. Do not randomly account a huge number of ticks!
|
|
*/
|
|
if (ticks && ticks < LONG_MAX)
|
|
account_idle_ticks(ticks);
|
|
}
|
|
|
|
void tick_nohz_idle_restart_tick(void)
|
|
{
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
|
|
if (ts->tick_stopped) {
|
|
ktime_t now = ktime_get();
|
|
tick_nohz_restart_sched_tick(ts, now);
|
|
tick_nohz_account_idle_time(ts, now);
|
|
}
|
|
}
|
|
|
|
static void tick_nohz_idle_update_tick(struct tick_sched *ts, ktime_t now)
|
|
{
|
|
if (tick_nohz_full_cpu(smp_processor_id()))
|
|
__tick_nohz_full_update_tick(ts, now);
|
|
else
|
|
tick_nohz_restart_sched_tick(ts, now);
|
|
|
|
tick_nohz_account_idle_time(ts, now);
|
|
}
|
|
|
|
/**
|
|
* tick_nohz_idle_exit - restart the idle tick from the idle task
|
|
*
|
|
* Restart the idle tick when the CPU is woken up from idle
|
|
* This also exit the RCU extended quiescent state. The CPU
|
|
* can use RCU again after this function is called.
|
|
*/
|
|
void tick_nohz_idle_exit(void)
|
|
{
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
bool idle_active, tick_stopped;
|
|
ktime_t now;
|
|
|
|
local_irq_disable();
|
|
|
|
WARN_ON_ONCE(!ts->inidle);
|
|
WARN_ON_ONCE(ts->timer_expires_base);
|
|
|
|
ts->inidle = 0;
|
|
idle_active = ts->idle_active;
|
|
tick_stopped = ts->tick_stopped;
|
|
|
|
if (idle_active || tick_stopped)
|
|
now = ktime_get();
|
|
|
|
if (idle_active)
|
|
tick_nohz_stop_idle(ts, now);
|
|
|
|
if (tick_stopped)
|
|
tick_nohz_idle_update_tick(ts, now);
|
|
|
|
local_irq_enable();
|
|
}
|
|
|
|
/*
|
|
* The nohz low res interrupt handler
|
|
*/
|
|
static void tick_nohz_handler(struct clock_event_device *dev)
|
|
{
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
struct pt_regs *regs = get_irq_regs();
|
|
ktime_t now = ktime_get();
|
|
|
|
dev->next_event = KTIME_MAX;
|
|
|
|
tick_sched_do_timer(ts, now);
|
|
tick_sched_handle(ts, regs);
|
|
|
|
if (unlikely(ts->tick_stopped)) {
|
|
/*
|
|
* The clockevent device is not reprogrammed, so change the
|
|
* clock event device to ONESHOT_STOPPED to avoid spurious
|
|
* interrupts on devices which might not be truly one shot.
|
|
*/
|
|
tick_program_event(KTIME_MAX, 1);
|
|
return;
|
|
}
|
|
|
|
hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
|
|
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
|
|
}
|
|
|
|
static inline void tick_nohz_activate(struct tick_sched *ts, int mode)
|
|
{
|
|
if (!tick_nohz_enabled)
|
|
return;
|
|
ts->nohz_mode = mode;
|
|
/* One update is enough */
|
|
if (!test_and_set_bit(0, &tick_nohz_active))
|
|
timers_update_nohz();
|
|
}
|
|
|
|
/**
|
|
* tick_nohz_switch_to_nohz - switch to nohz mode
|
|
*/
|
|
static void tick_nohz_switch_to_nohz(void)
|
|
{
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
ktime_t next;
|
|
|
|
if (!tick_nohz_enabled)
|
|
return;
|
|
|
|
if (tick_switch_to_oneshot(tick_nohz_handler))
|
|
return;
|
|
|
|
/*
|
|
* Recycle the hrtimer in ts, so we can share the
|
|
* hrtimer_forward with the highres code.
|
|
*/
|
|
hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
|
|
/* Get the next period */
|
|
next = tick_init_jiffy_update();
|
|
|
|
hrtimer_set_expires(&ts->sched_timer, next);
|
|
hrtimer_forward_now(&ts->sched_timer, TICK_NSEC);
|
|
tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1);
|
|
tick_nohz_activate(ts, NOHZ_MODE_LOWRES);
|
|
}
|
|
|
|
static inline void tick_nohz_irq_enter(void)
|
|
{
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
ktime_t now;
|
|
|
|
if (!ts->idle_active && !ts->tick_stopped)
|
|
return;
|
|
now = ktime_get();
|
|
if (ts->idle_active)
|
|
tick_nohz_stop_idle(ts, now);
|
|
/*
|
|
* If all CPUs are idle. We may need to update a stale jiffies value.
|
|
* Note nohz_full is a special case: a timekeeper is guaranteed to stay
|
|
* alive but it might be busy looping with interrupts disabled in some
|
|
* rare case (typically stop machine). So we must make sure we have a
|
|
* last resort.
|
|
*/
|
|
if (ts->tick_stopped)
|
|
tick_nohz_update_jiffies(now);
|
|
}
|
|
|
|
#else
|
|
|
|
static inline void tick_nohz_switch_to_nohz(void) { }
|
|
static inline void tick_nohz_irq_enter(void) { }
|
|
static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { }
|
|
|
|
#endif /* CONFIG_NO_HZ_COMMON */
|
|
|
|
/*
|
|
* Called from irq_enter to notify about the possible interruption of idle()
|
|
*/
|
|
void tick_irq_enter(void)
|
|
{
|
|
tick_check_oneshot_broadcast_this_cpu();
|
|
tick_nohz_irq_enter();
|
|
}
|
|
|
|
/*
|
|
* High resolution timer specific code
|
|
*/
|
|
#ifdef CONFIG_HIGH_RES_TIMERS
|
|
/*
|
|
* We rearm the timer until we get disabled by the idle code.
|
|
* Called with interrupts disabled.
|
|
*/
|
|
static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
|
|
{
|
|
struct tick_sched *ts =
|
|
container_of(timer, struct tick_sched, sched_timer);
|
|
struct pt_regs *regs = get_irq_regs();
|
|
ktime_t now = ktime_get();
|
|
|
|
tick_sched_do_timer(ts, now);
|
|
|
|
/*
|
|
* Do not call, when we are not in irq context and have
|
|
* no valid regs pointer
|
|
*/
|
|
if (regs)
|
|
tick_sched_handle(ts, regs);
|
|
else
|
|
ts->next_tick = 0;
|
|
|
|
/* No need to reprogram if we are in idle or full dynticks mode */
|
|
if (unlikely(ts->tick_stopped))
|
|
return HRTIMER_NORESTART;
|
|
|
|
hrtimer_forward(timer, now, TICK_NSEC);
|
|
|
|
return HRTIMER_RESTART;
|
|
}
|
|
|
|
static int sched_skew_tick;
|
|
|
|
static int __init skew_tick(char *str)
|
|
{
|
|
get_option(&str, &sched_skew_tick);
|
|
|
|
return 0;
|
|
}
|
|
early_param("skew_tick", skew_tick);
|
|
|
|
/**
|
|
* tick_setup_sched_timer - setup the tick emulation timer
|
|
*/
|
|
void tick_setup_sched_timer(void)
|
|
{
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
ktime_t now = ktime_get();
|
|
|
|
/*
|
|
* Emulate tick processing via per-CPU hrtimers:
|
|
*/
|
|
hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD);
|
|
ts->sched_timer.function = tick_sched_timer;
|
|
|
|
/* Get the next period (per-CPU) */
|
|
hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
|
|
|
|
/* Offset the tick to avert jiffies_lock contention. */
|
|
if (sched_skew_tick) {
|
|
u64 offset = TICK_NSEC >> 1;
|
|
do_div(offset, num_possible_cpus());
|
|
offset *= smp_processor_id();
|
|
hrtimer_add_expires_ns(&ts->sched_timer, offset);
|
|
}
|
|
|
|
hrtimer_forward(&ts->sched_timer, now, TICK_NSEC);
|
|
hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD);
|
|
tick_nohz_activate(ts, NOHZ_MODE_HIGHRES);
|
|
}
|
|
#endif /* HIGH_RES_TIMERS */
|
|
|
|
#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
|
|
void tick_cancel_sched_timer(int cpu)
|
|
{
|
|
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
|
|
|
|
# ifdef CONFIG_HIGH_RES_TIMERS
|
|
if (ts->sched_timer.base)
|
|
hrtimer_cancel(&ts->sched_timer);
|
|
# endif
|
|
|
|
memset(ts, 0, sizeof(*ts));
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Async notification about clocksource changes
|
|
*/
|
|
void tick_clock_notify(void)
|
|
{
|
|
int cpu;
|
|
|
|
for_each_possible_cpu(cpu)
|
|
set_bit(0, &per_cpu(tick_cpu_sched, cpu).check_clocks);
|
|
}
|
|
|
|
/*
|
|
* Async notification about clock event changes
|
|
*/
|
|
void tick_oneshot_notify(void)
|
|
{
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
|
|
set_bit(0, &ts->check_clocks);
|
|
}
|
|
|
|
/*
|
|
* Check, if a change happened, which makes oneshot possible.
|
|
*
|
|
* Called cyclic from the hrtimer softirq (driven by the timer
|
|
* softirq) allow_nohz signals, that we can switch into low-res nohz
|
|
* mode, because high resolution timers are disabled (either compile
|
|
* or runtime). Called with interrupts disabled.
|
|
*/
|
|
int tick_check_oneshot_change(int allow_nohz)
|
|
{
|
|
struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched);
|
|
|
|
if (!test_and_clear_bit(0, &ts->check_clocks))
|
|
return 0;
|
|
|
|
if (ts->nohz_mode != NOHZ_MODE_INACTIVE)
|
|
return 0;
|
|
|
|
if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available())
|
|
return 0;
|
|
|
|
if (!allow_nohz)
|
|
return 1;
|
|
|
|
tick_nohz_switch_to_nohz();
|
|
return 0;
|
|
}
|