07ce88e9de
-----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAl/sVdwACgkQONu9yGCS aT581g/+KZ4lFcY/lAEY6/n6RjFenerl5O2a4tqO+j7eivOA8aNOzXQpvwcPXFKZ uCCwab3shrp0MdOJ4Ub1qLF5rZoJ/QvLNkI+8GVRztnchkWHwNlYbheZqHRows9E LM5w/+SUh+I7wymfjsjxr8ohSOxkvygNL9PLLTkuQMwbs/jjdizmcgqeYo54Plih IdtHrp/ZjxKMOu+fkp1dpTy2RUfbxxWS4RnVjSI+g3s8vaxWh90jMCwLP3fyUwpX a8eNCFkIV0lBCj+dYF+ry5x7wGd9mvCVAG70DmRkHd4nyc1WGnp+yz3lQlQnIzeq Hc7k3ts3FXmXBSRTzkqM9pmaOuyrKwqu3DoiplXxHgjeJYegP9k0jh33eohXmc/u qSz9XB3FhBxy7uRf8tqGLKiUsARnQUYfqzR8qgGFndvWRpIBr9egSzDKVNSF5uWu bPt3UQpM8O714NcnB2PGs4OUPqxSikT3BrnfurZOzEddkSveXfkItYnt3mc300bx MSHYY/iuLpsBeDd0U6POgf5J5RigmOWvayZrMkPSxlnm7v9diefpKo7xB7+l3AqD DZ5BSZMNtgKHwzck6d3RXX+GCILreL16Lj299NM1SJPm+j5SEkna7luikgi2pqrk r2cD31L9JHiq36L3uP5u30JoxEG6+W2Px+dqc+uyB3RXHJzRwy4= =TKv4 -----END PGP SIGNATURE----- Merge 4.19.164 into android-4.19-stable Changes in 4.19.164 Kbuild: do not emit debug info for assembly with LLVM_IAS=1 x86/lib: Change .weak to SYM_FUNC_START_WEAK for arch/x86/lib/mem*_64.S spi: bcm2835aux: Fix use-after-free on unbind spi: bcm2835aux: Restore err assignment in bcm2835aux_spi_probe iwlwifi: pcie: limit memory read spin time arm64: dts: rockchip: Assign a fixed index to mmc devices on rk3399 boards. iwlwifi: mvm: fix kernel panic in case of assert during CSA powerpc: Drop -me200 addition to build flags ARC: stack unwinding: don't assume non-current task is sleeping scsi: ufs: Make sure clk scaling happens only when HBA is runtime ACTIVE irqchip/gic-v3-its: Unconditionally save/restore the ITS state on suspend soc: fsl: dpio: Get the cpumask through cpumask_of(cpu) platform/x86: thinkpad_acpi: Do not report SW_TABLET_MODE on Yoga 11e platform/x86: thinkpad_acpi: Add BAT1 is primary battery quirk for Thinkpad Yoga 11e 4th gen platform/x86: acer-wmi: add automatic keyboard background light toggle key as KEY_LIGHTS_TOGGLE platform/x86: intel-vbtn: Support for tablet mode on HP Pavilion 13 x360 PC Input: cm109 - do not stomp on control URB Input: i8042 - add Acer laptops to the i8042 reset list pinctrl: amd: remove debounce filter setting in IRQ type setting mmc: block: Fixup condition for CMD13 polling for RPMB requests kbuild: avoid static_assert for genksyms scsi: be2iscsi: Revert "Fix a theoretical leak in beiscsi_create_eqs()" x86/mm/mem_encrypt: Fix definition of PMD_FLAGS_DEC_WP x86/membarrier: Get rid of a dubious optimization x86/apic/vector: Fix ordering in vector assignment compiler.h: fix barrier_data() on clang PCI: qcom: Add missing reset for ipq806x mac80211: mesh: fix mesh_pathtbl_init() error path net: stmmac: free tx skb buffer in stmmac_resume() tcp: select sane initial rcvq_space.space for big MSS tcp: fix cwnd-limited bug for TSO deferral where we send nothing net/mlx4_en: Avoid scheduling restart task if it is already running lan743x: fix for potential NULL pointer dereference with bare card net/mlx4_en: Handle TX error CQE net: stmmac: delete the eee_ctrl_timer after napi disabled net: stmmac: dwmac-meson8b: fix mask definition of the m250_sel mux net: bridge: vlan: fix error return code in __vlan_add() ktest.pl: If size of log is too big to email, email error message USB: dummy-hcd: Fix uninitialized array use in init() USB: add RESET_RESUME quirk for Snapscan 1212 ALSA: usb-audio: Fix potential out-of-bounds shift ALSA: usb-audio: Fix control 'access overflow' errors from chmap xhci: Give USB2 ports time to enter U3 in bus suspend USB: UAS: introduce a quirk to set no_write_same USB: sisusbvga: Make console support depend on BROKEN ALSA: pcm: oss: Fix potential out-of-bounds shift serial: 8250_omap: Avoid FIFO corruption caused by MDR1 access drm/xen-front: Fix misused IS_ERR_OR_NULL checks drm: fix drm_dp_mst_port refcount leaks in drm_dp_mst_allocate_vcpi arm64: lse: fix LSE atomics with LLVM's integrated assembler arm64: lse: Fix LSE atomics with LLVM arm64: Change .weak to SYM_FUNC_START_WEAK_PI for arch/arm64/lib/mem*.S x86/resctrl: Remove unused struct mbm_state::chunks_bw x86/resctrl: Fix incorrect local bandwidth when mba_sc is enabled pinctrl: merrifield: Set default bias in case no particular value given pinctrl: baytrail: Avoid clearing debounce value when turning it off ARM: dts: sun8i: v3s: fix GIC node memory range gpio: mvebu: fix potential user-after-free on probe scsi: bnx2i: Requires MMU xsk: Fix xsk_poll()'s return type can: softing: softing_netdev_open(): fix error handling clk: renesas: r9a06g032: Drop __packed for portability block: factor out requeue handling from dispatch code netfilter: x_tables: Switch synchronization to RCU gpio: eic-sprd: break loop when getting NULL device resource selftests/bpf/test_offload.py: Reset ethtool features after failed setting RDMA/cm: Fix an attempt to use non-valid pointer when cleaning timewait ixgbe: avoid premature Rx buffer reuse drm/tegra: replace idr_init() by idr_init_base() kernel/cpu: add arch override for clear_tasks_mm_cpumask() mm handling drm/tegra: sor: Disable clocks on error in tegra_sor_init() arm64: syscall: exit userspace before unmasking exceptions vxlan: Add needed_headroom for lower device vxlan: Copy needed_tailroom from lowerdev scsi: mpt3sas: Increase IOCInit request timeout to 30s dm table: Remove BUG_ON(in_interrupt()) soc/tegra: fuse: Fix index bug in get_process_id USB: serial: option: add interface-number sanity check to flag handling USB: gadget: f_acm: add support for SuperSpeed Plus USB: gadget: f_midi: setup SuperSpeed Plus descriptors usb: gadget: f_fs: Re-use SS descriptors for SuperSpeedPlus USB: gadget: f_rndis: fix bitrate for SuperSpeed and above usb: chipidea: ci_hdrc_imx: Pass DISABLE_DEVICE_STREAMING flag to imx6ul ARM: dts: exynos: fix roles of USB 3.0 ports on Odroid XU ARM: dts: exynos: fix USB 3.0 VBUS control and over-current pins on Exynos5410 ARM: dts: exynos: fix USB 3.0 pins supply being turned off on Odroid XU coresight: tmc-etr: Check if page is valid before dma_map_page() scsi: megaraid_sas: Check user-provided offsets HID: i2c-hid: add Vero K147 to descriptor override serial_core: Check for port state when tty is in error state Bluetooth: Fix slab-out-of-bounds read in hci_le_direct_adv_report_evt() quota: Sanity-check quota file headers on load media: msi2500: assign SPI bus number dynamically crypto: af_alg - avoid undefined behavior accessing salg_name md: fix a warning caused by a race between concurrent md_ioctl()s perf cs-etm: Change tuple from traceID-CPU# to traceID-metadata perf cs-etm: Move definition of 'traceid_list' global variable from header file drm/gma500: fix double free of gma_connector drm/tve200: Fix handling of platform_get_irq() error soc: renesas: rmobile-sysc: Fix some leaks in rmobile_init_pm_domains() soc: mediatek: Check if power domains can be powered on at boot time soc: qcom: geni: More properly switch to DMA mode RDMA/bnxt_re: Set queue pair state when being queried selinux: fix error initialization in inode_doinit_with_dentry() ARM: dts: aspeed: s2600wf: Fix VGA memory region location RDMA/rxe: Compute PSN windows correctly x86/mm/ident_map: Check for errors from ident_pud_init() ARM: p2v: fix handling of LPAE translation in BE mode x86/apic: Fix x2apic enablement without interrupt remapping sched/deadline: Fix sched_dl_global_validate() sched: Reenable interrupts in do_sched_yield() crypto: talitos - Endianess in current_desc_hdr() crypto: talitos - Fix return type of current_desc_hdr() crypto: inside-secure - Fix sizeof() mismatch powerpc/64: Set up a kernel stack for secondaries before cpu_restore() spi: img-spfi: fix reference leak in img_spfi_resume drm/msm/dsi_pll_10nm: restore VCO rate during restore_state ASoC: pcm: DRAIN support reactivation selinux: fix inode_doinit_with_dentry() LABEL_INVALID error handling arm64: dts: exynos: Include common syscon restart/poweroff for Exynos7 arm64: dts: exynos: Correct psci compatible used on Exynos7 Bluetooth: Fix null pointer dereference in hci_event_packet() Bluetooth: hci_h5: fix memory leak in h5_close spi: spi-ti-qspi: fix reference leak in ti_qspi_setup spi: tegra20-slink: fix reference leak in slink ops of tegra20 spi: tegra20-sflash: fix reference leak in tegra_sflash_resume spi: tegra114: fix reference leak in tegra spi ops spi: bcm63xx-hsspi: fix missing clk_disable_unprepare() on error in bcm63xx_hsspi_resume mwifiex: fix mwifiex_shutdown_sw() causing sw reset failure ASoC: wm8998: Fix PM disable depth imbalance on error ASoC: arizona: Fix a wrong free in wm8997_probe RDMa/mthca: Work around -Wenum-conversion warning MIPS: BCM47XX: fix kconfig dependency bug for BCM47XX_BCMA crypto: qat - fix status check in qat_hal_put_rel_rd_xfer() staging: greybus: codecs: Fix reference counter leak in error handling staging: gasket: interrupt: fix the missed eventfd_ctx_put() in gasket_interrupt.c media: tm6000: Fix sizeof() mismatches media: mtk-vcodec: add missing put_device() call in mtk_vcodec_release_dec_pm() ASoC: meson: fix COMPILE_TEST error scsi: core: Fix VPD LUN ID designator priorities media: solo6x10: fix missing snd_card_free in error handling case video: fbdev: atmel_lcdfb: fix return error code in atmel_lcdfb_of_init() drm/omap: dmm_tiler: fix return error code in omap_dmm_probe() Input: ads7846 - fix race that causes missing releases Input: ads7846 - fix integer overflow on Rt calculation Input: ads7846 - fix unaligned access on 7845 usb/max3421: fix return error code in max3421_probe() spi: mxs: fix reference leak in mxs_spi_probe powerpc/feature: Fix CPU_FTRS_ALWAYS by removing CPU_FTRS_GENERIC_32 crypto: crypto4xx - Replace bitwise OR with logical OR in crypto4xx_build_pd crypto: omap-aes - Fix PM disable depth imbalance in omap_aes_probe spi: fix resource leak for drivers without .remove callback soc: ti: knav_qmss: fix reference leak in knav_queue_probe soc: ti: Fix reference imbalance in knav_dma_probe drivers: soc: ti: knav_qmss_queue: Fix error return code in knav_queue_probe Input: omap4-keypad - fix runtime PM error handling RDMA/cxgb4: Validate the number of CQEs memstick: fix a double-free bug in memstick_check ARM: dts: at91: sama5d4_xplained: add pincontrol for USB Host ARM: dts: at91: sama5d3_xplained: add pincontrol for USB Host orinoco: Move context allocation after processing the skb cw1200: fix missing destroy_workqueue() on error in cw1200_init_common dmaengine: mv_xor_v2: Fix error return code in mv_xor_v2_probe() media: siano: fix memory leak of debugfs members in smsdvb_hotplug platform/x86: mlx-platform: Remove PSU EEPROM from default platform configuration platform/x86: mlx-platform: Remove PSU EEPROM from MSN274x platform configuration samples: bpf: Fix lwt_len_hist reusing previous BPF map mips: cdmm: fix use-after-free in mips_cdmm_bus_discover media: max2175: fix max2175_set_csm_mode() error code slimbus: qcom-ngd-ctrl: Avoid sending power requests without QMI HSI: omap_ssi: Don't jump to free ID in ssi_add_controller() ARM: dts: Remove non-existent i2c1 from 98dx3236 arm64: dts: rockchip: Set dr_mode to "host" for OTG on rk3328-roc-cc power: supply: axp288_charger: Fix HP Pavilion x2 10 DMI matching power: supply: bq24190_charger: fix reference leak genirq/irqdomain: Don't try to free an interrupt that has no mapping PCI: Bounds-check command-line resource alignment requests PCI: Fix overflow in command-line resource alignment requests PCI: iproc: Fix out-of-bound array accesses arm64: dts: meson: fix spi-max-frequency on Khadas VIM2 ARM: dts: at91: at91sam9rl: fix ADC triggers platform/x86: dell-smbios-base: Fix error return code in dell_smbios_init ath10k: Fix the parsing error in service available event ath10k: Fix an error handling path ath10k: Release some resources in an error handling path NFSv4.2: condition READDIR's mask for security label based on LSM state SUNRPC: xprt_load_transport() needs to support the netid "rdma6" lockd: don't use interval-based rebinding over TCP NFS: switch nfsiod to be an UNBOUND workqueue. vfio-pci: Use io_remap_pfn_range() for PCI IO memory media: saa7146: fix array overflow in vidioc_s_audio() clocksource/drivers/cadence_ttc: Fix memory leak in ttc_setup_clockevent() ARM: dts: at91: sama5d2: map securam as device pinctrl: falcon: add missing put_device() call in pinctrl_falcon_probe() arm64: dts: rockchip: Fix UART pull-ups on rk3328 memstick: r592: Fix error return in r592_probe() net/mlx5: Properly convey driver version to firmware ASoC: jz4740-i2s: add missed checks for clk_get() dm ioctl: fix error return code in target_message clocksource/drivers/arm_arch_timer: Correct fault programming of CNTKCTL_EL1.EVNTI cpufreq: highbank: Add missing MODULE_DEVICE_TABLE cpufreq: mediatek: Add missing MODULE_DEVICE_TABLE cpufreq: st: Add missing MODULE_DEVICE_TABLE cpufreq: loongson1: Add missing MODULE_ALIAS cpufreq: scpi: Add missing MODULE_ALIAS scsi: qedi: Fix missing destroy_workqueue() on error in __qedi_probe scsi: pm80xx: Fix error return in pm8001_pci_probe() seq_buf: Avoid type mismatch for seq_buf_init scsi: fnic: Fix error return code in fnic_probe() platform/x86: mlx-platform: Fix item counter assignment for MSN2700, MSN24xx systems powerpc/pseries/hibernation: drop pseries_suspend_begin() from suspend ops powerpc/pseries/hibernation: remove redundant cacheinfo update usb: ehci-omap: Fix PM disable depth umbalance in ehci_hcd_omap_probe usb: oxu210hp-hcd: Fix memory leak in oxu_create speakup: fix uninitialized flush_lock nfsd: Fix message level for normal termination nfs_common: need lock during iterate through the list x86/kprobes: Restore BTF if the single-stepping is cancelled bus: fsl-mc: fix error return code in fsl_mc_object_allocate() clk: tegra: Fix duplicated SE clock entry extcon: max77693: Fix modalias string mac80211: don't set set TDLS STA bandwidth wider than possible ASoC: wm_adsp: remove "ctl" from list on error in wm_adsp_create_control() irqchip/alpine-msi: Fix freeing of interrupts on allocation error path watchdog: sirfsoc: Add missing dependency on HAS_IOMEM watchdog: sprd: remove watchdog disable from resume fail path watchdog: sprd: check busy bit before new loading rather than after that watchdog: Fix potential dereferencing of null pointer um: Monitor error events in IRQ controller um: tty: Fix handling of close in tty lines um: chan_xterm: Fix fd leak nfc: s3fwrn5: Release the nfc firmware powerpc/ps3: use dma_mapping_error() checkpatch: fix unescaped left brace net: bcmgenet: Fix a resource leak in an error handling path in the probe functin net: allwinner: Fix some resources leak in the error handling path of the probe and in the remove function net: korina: fix return value libnvdimm/label: Return -ENXIO for no slot in __blk_label_update watchdog: qcom: Avoid context switch in restart handler watchdog: coh901327: add COMMON_CLK dependency clk: ti: Fix memleak in ti_fapll_synth_setup pwm: zx: Add missing cleanup in error path pwm: lp3943: Dynamically allocate PWM chip base perf record: Fix memory leak when using '--user-regs=?' to list registers qlcnic: Fix error code in probe clk: s2mps11: Fix a resource leak in error handling paths in the probe function clk: sunxi-ng: Make sure divider tables have sentinel kconfig: fix return value of do_error_if() ARM: sunxi: Add machine match for the Allwinner V3 SoC cfg80211: initialize rekey_data fix namespaced fscaps when !CONFIG_SECURITY lwt: Disable BH too in run_lwt_bpf() Input: cros_ec_keyb - send 'scancodes' in addition to key events Input: goodix - add upside-down quirk for Teclast X98 Pro tablet media: gspca: Fix memory leak in probe media: sunxi-cir: ensure IR is handled when it is continuous media: netup_unidvb: Don't leak SPI master in probe error path media: ipu3-cio2: Remove traces of returned buffers media: ipu3-cio2: Return actual subdev format media: ipu3-cio2: Serialise access to pad format media: ipu3-cio2: Validate mbus format in setting subdev format media: ipu3-cio2: Make the field on subdev format V4L2_FIELD_NONE Input: cyapa_gen6 - fix out-of-bounds stack access ALSA: hda/ca0132 - Change Input Source enum strings. PM: ACPI: PCI: Drop acpi_pm_set_bridge_wakeup() Revert "ACPI / resources: Use AE_CTRL_TERMINATE to terminate resources walks" ACPI: PNP: compare the string length in the matching_id() ALSA: hda: Fix regressions on clear and reconfig sysfs ALSA: hda/realtek - Enable headset mic of ASUS X430UN with ALC256 ALSA: hda/realtek - Enable headset mic of ASUS Q524UQK with ALC255 ALSA: pcm: oss: Fix a few more UBSAN fixes ALSA: hda/realtek: Add quirk for MSI-GP73 ALSA: hda/realtek: Apply jack fixup for Quanta NL3 ALSA: usb-audio: Add VID to support native DSD reproduction on FiiO devices ALSA: usb-audio: Disable sample read check if firmware doesn't give back s390/smp: perform initial CPU reset also for SMT siblings s390/kexec_file: fix diag308 subcode when loading crash kernel s390/dasd: fix hanging device offline processing s390/dasd: prevent inconsistent LCU device data s390/dasd: fix list corruption of pavgroup group list s390/dasd: fix list corruption of lcu list staging: comedi: mf6x4: Fix AI end-of-conversion detection powerpc/perf: Exclude kernel samples while counting events in user space. crypto: ecdh - avoid unaligned accesses in ecdh_set_secret() EDAC/amd64: Fix PCI component registration USB: serial: mos7720: fix parallel-port state restore USB: serial: digi_acceleport: fix write-wakeup deadlocks USB: serial: keyspan_pda: fix dropped unthrottle interrupts USB: serial: keyspan_pda: fix write deadlock USB: serial: keyspan_pda: fix stalled writes USB: serial: keyspan_pda: fix write-wakeup use-after-free USB: serial: keyspan_pda: fix tx-unthrottle use-after-free USB: serial: keyspan_pda: fix write unthrottling ext4: fix a memory leak of ext4_free_data ext4: fix deadlock with fs freezing and EA inodes KVM: arm64: Introduce handling of AArch32 TTBCR2 traps ARM: dts: pandaboard: fix pinmux for gpio user button of Pandaboard ES ARM: dts: at91: sama5d2: fix CAN message ram offset and size powerpc: Fix incorrect stw{, ux, u, x} instructions in __set_pte_at powerpc/rtas: Fix typo of ibm,open-errinjct in RTAS filter powerpc/xmon: Change printk() to pr_cont() powerpc/powernv/memtrace: Don't leak kernel memory to user space powerpc/powernv/memtrace: Fix crashing the kernel when enabling concurrently ima: Don't modify file descriptor mode on the fly ceph: fix race in concurrent __ceph_remove_cap invocations SMB3: avoid confusing warning message on mount to Azure SMB3.1.1: do not log warning message if server doesn't populate salt ubifs: wbuf: Don't leak kernel memory to flash jffs2: Fix GC exit abnormally jfs: Fix array index bounds check in dbAdjTree drm/dp_aux_dev: check aux_dev before use in drm_dp_aux_dev_get_by_minor() spi: spi-sh: Fix use-after-free on unbind spi: davinci: Fix use-after-free on unbind spi: pic32: Don't leak DMA channels in probe error path spi: rb4xx: Don't leak SPI master in probe error path spi: sc18is602: Don't leak SPI master in probe error path spi: st-ssc4: Fix unbalanced pm_runtime_disable() in probe error path spi: mt7621: fix missing clk_disable_unprepare() on error in mt7621_spi_probe soc: qcom: smp2p: Safely acquire spinlock without IRQs mtd: spinand: Fix OOB read mtd: parser: cmdline: Fix parsing of part-names with colons mtd: rawnand: qcom: Fix DMA sync on FLASH_STATUS register read scsi: lpfc: Fix invalid sleeping context in lpfc_sli4_nvmet_alloc() scsi: lpfc: Re-fix use after free in lpfc_rq_buf_free() iio: buffer: Fix demux update iio: adc: rockchip_saradc: fix missing clk_disable_unprepare() on error in rockchip_saradc_resume iio:light:rpr0521: Fix timestamp alignment and prevent data leak. iio:light:st_uvis25: Fix timestamp alignment and prevent data leak. iio:pressure:mpl3115: Force alignment of buffer iio:imu:bmi160: Fix too large a buffer. md/cluster: block reshape with remote resync job md/cluster: fix deadlock when node is doing resync job pinctrl: sunxi: Always call chained_irq_{enter, exit} in sunxi_pinctrl_irq_handler clk: mvebu: a3700: fix the XTAL MODE pin to MPP1_9 xen-blkback: set ring->xenblkd to NULL after kthread_stop() xen/xenbus: Allow watches discard events before queueing xen/xenbus: Add 'will_handle' callback support in xenbus_watch_path() xen/xenbus/xen_bus_type: Support will_handle watch callback xen/xenbus: Count pending messages for each watch xenbus/xenbus_backend: Disallow pending watch messages libnvdimm/namespace: Fix reaping of invalidated block-window-namespace labels platform/x86: intel-vbtn: Allow switch events on Acer Switch Alpha 12 PCI: Fix pci_slot_release() NULL pointer dereference platform/x86: mlx-platform: remove an unused variable Linux 4.19.164 Signed-off-by: Greg Kroah-Hartman <gregkh@google.com> Change-Id: I8e2d24b45393ee2360186893d4e578e20156c7f1
2360 lines
56 KiB
C
2360 lines
56 KiB
C
/* CPU control.
|
|
* (C) 2001, 2002, 2003, 2004 Rusty Russell
|
|
*
|
|
* This code is licenced under the GPL.
|
|
*/
|
|
#include <linux/sched/mm.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/init.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/sched/signal.h>
|
|
#include <linux/sched/hotplug.h>
|
|
#include <linux/sched/task.h>
|
|
#include <linux/sched/smt.h>
|
|
#include <linux/unistd.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/oom.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/export.h>
|
|
#include <linux/bug.h>
|
|
#include <linux/kthread.h>
|
|
#include <linux/stop_machine.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/suspend.h>
|
|
#include <linux/lockdep.h>
|
|
#include <linux/tick.h>
|
|
#include <linux/irq.h>
|
|
#include <linux/nmi.h>
|
|
#include <linux/smpboot.h>
|
|
#include <linux/relay.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/percpu-rwsem.h>
|
|
|
|
#include <trace/events/power.h>
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/cpuhp.h>
|
|
|
|
#include "smpboot.h"
|
|
|
|
/**
|
|
* cpuhp_cpu_state - Per cpu hotplug state storage
|
|
* @state: The current cpu state
|
|
* @target: The target state
|
|
* @thread: Pointer to the hotplug thread
|
|
* @should_run: Thread should execute
|
|
* @rollback: Perform a rollback
|
|
* @single: Single callback invocation
|
|
* @bringup: Single callback bringup or teardown selector
|
|
* @cb_state: The state for a single callback (install/uninstall)
|
|
* @result: Result of the operation
|
|
* @done_up: Signal completion to the issuer of the task for cpu-up
|
|
* @done_down: Signal completion to the issuer of the task for cpu-down
|
|
*/
|
|
struct cpuhp_cpu_state {
|
|
enum cpuhp_state state;
|
|
enum cpuhp_state target;
|
|
enum cpuhp_state fail;
|
|
#ifdef CONFIG_SMP
|
|
struct task_struct *thread;
|
|
bool should_run;
|
|
bool rollback;
|
|
bool single;
|
|
bool bringup;
|
|
bool booted_once;
|
|
struct hlist_node *node;
|
|
struct hlist_node *last;
|
|
enum cpuhp_state cb_state;
|
|
int result;
|
|
struct completion done_up;
|
|
struct completion done_down;
|
|
#endif
|
|
};
|
|
|
|
static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = {
|
|
.fail = CPUHP_INVALID,
|
|
};
|
|
|
|
#if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP)
|
|
static struct lockdep_map cpuhp_state_up_map =
|
|
STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map);
|
|
static struct lockdep_map cpuhp_state_down_map =
|
|
STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map);
|
|
|
|
|
|
static inline void cpuhp_lock_acquire(bool bringup)
|
|
{
|
|
lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
|
|
}
|
|
|
|
static inline void cpuhp_lock_release(bool bringup)
|
|
{
|
|
lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
|
|
}
|
|
#else
|
|
|
|
static inline void cpuhp_lock_acquire(bool bringup) { }
|
|
static inline void cpuhp_lock_release(bool bringup) { }
|
|
|
|
#endif
|
|
|
|
/**
|
|
* cpuhp_step - Hotplug state machine step
|
|
* @name: Name of the step
|
|
* @startup: Startup function of the step
|
|
* @teardown: Teardown function of the step
|
|
* @cant_stop: Bringup/teardown can't be stopped at this step
|
|
*/
|
|
struct cpuhp_step {
|
|
const char *name;
|
|
union {
|
|
int (*single)(unsigned int cpu);
|
|
int (*multi)(unsigned int cpu,
|
|
struct hlist_node *node);
|
|
} startup;
|
|
union {
|
|
int (*single)(unsigned int cpu);
|
|
int (*multi)(unsigned int cpu,
|
|
struct hlist_node *node);
|
|
} teardown;
|
|
struct hlist_head list;
|
|
bool cant_stop;
|
|
bool multi_instance;
|
|
};
|
|
|
|
static DEFINE_MUTEX(cpuhp_state_mutex);
|
|
static struct cpuhp_step cpuhp_hp_states[];
|
|
|
|
static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
|
|
{
|
|
return cpuhp_hp_states + state;
|
|
}
|
|
|
|
/**
|
|
* cpuhp_invoke_callback _ Invoke the callbacks for a given state
|
|
* @cpu: The cpu for which the callback should be invoked
|
|
* @state: The state to do callbacks for
|
|
* @bringup: True if the bringup callback should be invoked
|
|
* @node: For multi-instance, do a single entry callback for install/remove
|
|
* @lastp: For multi-instance rollback, remember how far we got
|
|
*
|
|
* Called from cpu hotplug and from the state register machinery.
|
|
*/
|
|
static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state,
|
|
bool bringup, struct hlist_node *node,
|
|
struct hlist_node **lastp)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
struct cpuhp_step *step = cpuhp_get_step(state);
|
|
int (*cbm)(unsigned int cpu, struct hlist_node *node);
|
|
int (*cb)(unsigned int cpu);
|
|
int ret, cnt;
|
|
|
|
if (st->fail == state) {
|
|
st->fail = CPUHP_INVALID;
|
|
|
|
if (!(bringup ? step->startup.single : step->teardown.single))
|
|
return 0;
|
|
|
|
return -EAGAIN;
|
|
}
|
|
|
|
if (!step->multi_instance) {
|
|
WARN_ON_ONCE(lastp && *lastp);
|
|
cb = bringup ? step->startup.single : step->teardown.single;
|
|
if (!cb)
|
|
return 0;
|
|
trace_cpuhp_enter(cpu, st->target, state, cb);
|
|
ret = cb(cpu);
|
|
trace_cpuhp_exit(cpu, st->state, state, ret);
|
|
return ret;
|
|
}
|
|
cbm = bringup ? step->startup.multi : step->teardown.multi;
|
|
if (!cbm)
|
|
return 0;
|
|
|
|
/* Single invocation for instance add/remove */
|
|
if (node) {
|
|
WARN_ON_ONCE(lastp && *lastp);
|
|
trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
|
|
ret = cbm(cpu, node);
|
|
trace_cpuhp_exit(cpu, st->state, state, ret);
|
|
return ret;
|
|
}
|
|
|
|
/* State transition. Invoke on all instances */
|
|
cnt = 0;
|
|
hlist_for_each(node, &step->list) {
|
|
if (lastp && node == *lastp)
|
|
break;
|
|
|
|
trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
|
|
ret = cbm(cpu, node);
|
|
trace_cpuhp_exit(cpu, st->state, state, ret);
|
|
if (ret) {
|
|
if (!lastp)
|
|
goto err;
|
|
|
|
*lastp = node;
|
|
return ret;
|
|
}
|
|
cnt++;
|
|
}
|
|
if (lastp)
|
|
*lastp = NULL;
|
|
return 0;
|
|
err:
|
|
/* Rollback the instances if one failed */
|
|
cbm = !bringup ? step->startup.multi : step->teardown.multi;
|
|
if (!cbm)
|
|
return ret;
|
|
|
|
hlist_for_each(node, &step->list) {
|
|
if (!cnt--)
|
|
break;
|
|
|
|
trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
|
|
ret = cbm(cpu, node);
|
|
trace_cpuhp_exit(cpu, st->state, state, ret);
|
|
/*
|
|
* Rollback must not fail,
|
|
*/
|
|
WARN_ON_ONCE(ret);
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
static bool cpuhp_is_ap_state(enum cpuhp_state state)
|
|
{
|
|
/*
|
|
* The extra check for CPUHP_TEARDOWN_CPU is only for documentation
|
|
* purposes as that state is handled explicitly in cpu_down.
|
|
*/
|
|
return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU;
|
|
}
|
|
|
|
static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
|
|
{
|
|
struct completion *done = bringup ? &st->done_up : &st->done_down;
|
|
wait_for_completion(done);
|
|
}
|
|
|
|
static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
|
|
{
|
|
struct completion *done = bringup ? &st->done_up : &st->done_down;
|
|
complete(done);
|
|
}
|
|
|
|
/*
|
|
* The former STARTING/DYING states, ran with IRQs disabled and must not fail.
|
|
*/
|
|
static bool cpuhp_is_atomic_state(enum cpuhp_state state)
|
|
{
|
|
return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE;
|
|
}
|
|
|
|
/* Serializes the updates to cpu_online_mask, cpu_present_mask */
|
|
static DEFINE_MUTEX(cpu_add_remove_lock);
|
|
bool cpuhp_tasks_frozen;
|
|
EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);
|
|
|
|
/*
|
|
* The following two APIs (cpu_maps_update_begin/done) must be used when
|
|
* attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
|
|
*/
|
|
void cpu_maps_update_begin(void)
|
|
{
|
|
mutex_lock(&cpu_add_remove_lock);
|
|
}
|
|
|
|
void cpu_maps_update_done(void)
|
|
{
|
|
mutex_unlock(&cpu_add_remove_lock);
|
|
}
|
|
|
|
/*
|
|
* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
|
|
* Should always be manipulated under cpu_add_remove_lock
|
|
*/
|
|
static int cpu_hotplug_disabled;
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock);
|
|
|
|
void cpus_read_lock(void)
|
|
{
|
|
percpu_down_read(&cpu_hotplug_lock);
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpus_read_lock);
|
|
|
|
int cpus_read_trylock(void)
|
|
{
|
|
return percpu_down_read_trylock(&cpu_hotplug_lock);
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpus_read_trylock);
|
|
|
|
void cpus_read_unlock(void)
|
|
{
|
|
percpu_up_read(&cpu_hotplug_lock);
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpus_read_unlock);
|
|
|
|
void cpus_write_lock(void)
|
|
{
|
|
percpu_down_write(&cpu_hotplug_lock);
|
|
}
|
|
|
|
void cpus_write_unlock(void)
|
|
{
|
|
percpu_up_write(&cpu_hotplug_lock);
|
|
}
|
|
|
|
void lockdep_assert_cpus_held(void)
|
|
{
|
|
/*
|
|
* We can't have hotplug operations before userspace starts running,
|
|
* and some init codepaths will knowingly not take the hotplug lock.
|
|
* This is all valid, so mute lockdep until it makes sense to report
|
|
* unheld locks.
|
|
*/
|
|
if (system_state < SYSTEM_RUNNING)
|
|
return;
|
|
|
|
percpu_rwsem_assert_held(&cpu_hotplug_lock);
|
|
}
|
|
|
|
/*
|
|
* Wait for currently running CPU hotplug operations to complete (if any) and
|
|
* disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects
|
|
* the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the
|
|
* hotplug path before performing hotplug operations. So acquiring that lock
|
|
* guarantees mutual exclusion from any currently running hotplug operations.
|
|
*/
|
|
void cpu_hotplug_disable(void)
|
|
{
|
|
cpu_maps_update_begin();
|
|
cpu_hotplug_disabled++;
|
|
cpu_maps_update_done();
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_hotplug_disable);
|
|
|
|
static void __cpu_hotplug_enable(void)
|
|
{
|
|
if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n"))
|
|
return;
|
|
cpu_hotplug_disabled--;
|
|
}
|
|
|
|
void cpu_hotplug_enable(void)
|
|
{
|
|
cpu_maps_update_begin();
|
|
__cpu_hotplug_enable();
|
|
cpu_maps_update_done();
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
|
|
#endif /* CONFIG_HOTPLUG_CPU */
|
|
|
|
/*
|
|
* Architectures that need SMT-specific errata handling during SMT hotplug
|
|
* should override this.
|
|
*/
|
|
void __weak arch_smt_update(void) { }
|
|
|
|
#ifdef CONFIG_HOTPLUG_SMT
|
|
enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
|
|
|
|
void __init cpu_smt_disable(bool force)
|
|
{
|
|
if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
|
|
cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
|
|
return;
|
|
|
|
if (force) {
|
|
pr_info("SMT: Force disabled\n");
|
|
cpu_smt_control = CPU_SMT_FORCE_DISABLED;
|
|
} else {
|
|
pr_info("SMT: disabled\n");
|
|
cpu_smt_control = CPU_SMT_DISABLED;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* The decision whether SMT is supported can only be done after the full
|
|
* CPU identification. Called from architecture code.
|
|
*/
|
|
void __init cpu_smt_check_topology(void)
|
|
{
|
|
if (!topology_smt_supported())
|
|
cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
|
|
}
|
|
|
|
static int __init smt_cmdline_disable(char *str)
|
|
{
|
|
cpu_smt_disable(str && !strcmp(str, "force"));
|
|
return 0;
|
|
}
|
|
early_param("nosmt", smt_cmdline_disable);
|
|
|
|
static inline bool cpu_smt_allowed(unsigned int cpu)
|
|
{
|
|
if (cpu_smt_control == CPU_SMT_ENABLED)
|
|
return true;
|
|
|
|
if (topology_is_primary_thread(cpu))
|
|
return true;
|
|
|
|
/*
|
|
* On x86 it's required to boot all logical CPUs at least once so
|
|
* that the init code can get a chance to set CR4.MCE on each
|
|
* CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
|
|
* core will shutdown the machine.
|
|
*/
|
|
return !per_cpu(cpuhp_state, cpu).booted_once;
|
|
}
|
|
#else
|
|
static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
|
|
#endif
|
|
|
|
static inline enum cpuhp_state
|
|
cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
|
|
{
|
|
enum cpuhp_state prev_state = st->state;
|
|
|
|
st->rollback = false;
|
|
st->last = NULL;
|
|
|
|
st->target = target;
|
|
st->single = false;
|
|
st->bringup = st->state < target;
|
|
|
|
return prev_state;
|
|
}
|
|
|
|
static inline void
|
|
cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state)
|
|
{
|
|
st->rollback = true;
|
|
|
|
/*
|
|
* If we have st->last we need to undo partial multi_instance of this
|
|
* state first. Otherwise start undo at the previous state.
|
|
*/
|
|
if (!st->last) {
|
|
if (st->bringup)
|
|
st->state--;
|
|
else
|
|
st->state++;
|
|
}
|
|
|
|
st->target = prev_state;
|
|
st->bringup = !st->bringup;
|
|
}
|
|
|
|
/* Regular hotplug invocation of the AP hotplug thread */
|
|
static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st)
|
|
{
|
|
if (!st->single && st->state == st->target)
|
|
return;
|
|
|
|
st->result = 0;
|
|
/*
|
|
* Make sure the above stores are visible before should_run becomes
|
|
* true. Paired with the mb() above in cpuhp_thread_fun()
|
|
*/
|
|
smp_mb();
|
|
st->should_run = true;
|
|
wake_up_process(st->thread);
|
|
wait_for_ap_thread(st, st->bringup);
|
|
}
|
|
|
|
static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target)
|
|
{
|
|
enum cpuhp_state prev_state;
|
|
int ret;
|
|
|
|
prev_state = cpuhp_set_state(st, target);
|
|
__cpuhp_kick_ap(st);
|
|
if ((ret = st->result)) {
|
|
cpuhp_reset_state(st, prev_state);
|
|
__cpuhp_kick_ap(st);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int bringup_wait_for_ap(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
|
|
/* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */
|
|
wait_for_ap_thread(st, true);
|
|
if (WARN_ON_ONCE((!cpu_online(cpu))))
|
|
return -ECANCELED;
|
|
|
|
/* Unpark the hotplug thread of the target cpu */
|
|
kthread_unpark(st->thread);
|
|
|
|
/*
|
|
* SMT soft disabling on X86 requires to bring the CPU out of the
|
|
* BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The
|
|
* CPU marked itself as booted_once in cpu_notify_starting() so the
|
|
* cpu_smt_allowed() check will now return false if this is not the
|
|
* primary sibling.
|
|
*/
|
|
if (!cpu_smt_allowed(cpu))
|
|
return -ECANCELED;
|
|
|
|
if (st->target <= CPUHP_AP_ONLINE_IDLE)
|
|
return 0;
|
|
|
|
return cpuhp_kick_ap(st, st->target);
|
|
}
|
|
|
|
static int bringup_cpu(unsigned int cpu)
|
|
{
|
|
struct task_struct *idle = idle_thread_get(cpu);
|
|
int ret;
|
|
|
|
/*
|
|
* Some architectures have to walk the irq descriptors to
|
|
* setup the vector space for the cpu which comes online.
|
|
* Prevent irq alloc/free across the bringup.
|
|
*/
|
|
irq_lock_sparse();
|
|
|
|
/* Arch-specific enabling code. */
|
|
ret = __cpu_up(cpu, idle);
|
|
irq_unlock_sparse();
|
|
if (ret)
|
|
return ret;
|
|
return bringup_wait_for_ap(cpu);
|
|
}
|
|
|
|
static int finish_cpu(unsigned int cpu)
|
|
{
|
|
struct task_struct *idle = idle_thread_get(cpu);
|
|
struct mm_struct *mm = idle->active_mm;
|
|
|
|
/*
|
|
* idle_task_exit() will have switched to &init_mm, now
|
|
* clean up any remaining active_mm state.
|
|
*/
|
|
if (mm != &init_mm)
|
|
idle->active_mm = &init_mm;
|
|
mmdrop(mm);
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Hotplug state machine related functions
|
|
*/
|
|
|
|
static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st)
|
|
{
|
|
for (st->state--; st->state > st->target; st->state--)
|
|
cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
|
|
}
|
|
|
|
static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st)
|
|
{
|
|
if (IS_ENABLED(CONFIG_HOTPLUG_CPU))
|
|
return true;
|
|
/*
|
|
* When CPU hotplug is disabled, then taking the CPU down is not
|
|
* possible because takedown_cpu() and the architecture and
|
|
* subsystem specific mechanisms are not available. So the CPU
|
|
* which would be completely unplugged again needs to stay around
|
|
* in the current state.
|
|
*/
|
|
return st->state <= CPUHP_BRINGUP_CPU;
|
|
}
|
|
|
|
static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
|
|
enum cpuhp_state target)
|
|
{
|
|
enum cpuhp_state prev_state = st->state;
|
|
int ret = 0;
|
|
|
|
while (st->state < target) {
|
|
st->state++;
|
|
ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
|
|
if (ret) {
|
|
if (can_rollback_cpu(st)) {
|
|
st->target = prev_state;
|
|
undo_cpu_up(cpu, st);
|
|
}
|
|
break;
|
|
}
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* The cpu hotplug threads manage the bringup and teardown of the cpus
|
|
*/
|
|
static void cpuhp_create(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
|
|
init_completion(&st->done_up);
|
|
init_completion(&st->done_down);
|
|
}
|
|
|
|
static int cpuhp_should_run(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
|
|
|
|
return st->should_run;
|
|
}
|
|
|
|
/*
|
|
* Execute teardown/startup callbacks on the plugged cpu. Also used to invoke
|
|
* callbacks when a state gets [un]installed at runtime.
|
|
*
|
|
* Each invocation of this function by the smpboot thread does a single AP
|
|
* state callback.
|
|
*
|
|
* It has 3 modes of operation:
|
|
* - single: runs st->cb_state
|
|
* - up: runs ++st->state, while st->state < st->target
|
|
* - down: runs st->state--, while st->state > st->target
|
|
*
|
|
* When complete or on error, should_run is cleared and the completion is fired.
|
|
*/
|
|
static void cpuhp_thread_fun(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
|
|
bool bringup = st->bringup;
|
|
enum cpuhp_state state;
|
|
|
|
if (WARN_ON_ONCE(!st->should_run))
|
|
return;
|
|
|
|
/*
|
|
* ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures
|
|
* that if we see ->should_run we also see the rest of the state.
|
|
*/
|
|
smp_mb();
|
|
|
|
cpuhp_lock_acquire(bringup);
|
|
|
|
if (st->single) {
|
|
state = st->cb_state;
|
|
st->should_run = false;
|
|
} else {
|
|
if (bringup) {
|
|
st->state++;
|
|
state = st->state;
|
|
st->should_run = (st->state < st->target);
|
|
WARN_ON_ONCE(st->state > st->target);
|
|
} else {
|
|
state = st->state;
|
|
st->state--;
|
|
st->should_run = (st->state > st->target);
|
|
WARN_ON_ONCE(st->state < st->target);
|
|
}
|
|
}
|
|
|
|
WARN_ON_ONCE(!cpuhp_is_ap_state(state));
|
|
|
|
if (cpuhp_is_atomic_state(state)) {
|
|
local_irq_disable();
|
|
st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last);
|
|
local_irq_enable();
|
|
|
|
/*
|
|
* STARTING/DYING must not fail!
|
|
*/
|
|
WARN_ON_ONCE(st->result);
|
|
} else {
|
|
st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last);
|
|
}
|
|
|
|
if (st->result) {
|
|
/*
|
|
* If we fail on a rollback, we're up a creek without no
|
|
* paddle, no way forward, no way back. We loose, thanks for
|
|
* playing.
|
|
*/
|
|
WARN_ON_ONCE(st->rollback);
|
|
st->should_run = false;
|
|
}
|
|
|
|
cpuhp_lock_release(bringup);
|
|
|
|
if (!st->should_run)
|
|
complete_ap_thread(st, bringup);
|
|
}
|
|
|
|
/* Invoke a single callback on a remote cpu */
|
|
static int
|
|
cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup,
|
|
struct hlist_node *node)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int ret;
|
|
|
|
if (!cpu_online(cpu))
|
|
return 0;
|
|
|
|
cpuhp_lock_acquire(false);
|
|
cpuhp_lock_release(false);
|
|
|
|
cpuhp_lock_acquire(true);
|
|
cpuhp_lock_release(true);
|
|
|
|
/*
|
|
* If we are up and running, use the hotplug thread. For early calls
|
|
* we invoke the thread function directly.
|
|
*/
|
|
if (!st->thread)
|
|
return cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
|
|
|
|
st->rollback = false;
|
|
st->last = NULL;
|
|
|
|
st->node = node;
|
|
st->bringup = bringup;
|
|
st->cb_state = state;
|
|
st->single = true;
|
|
|
|
__cpuhp_kick_ap(st);
|
|
|
|
/*
|
|
* If we failed and did a partial, do a rollback.
|
|
*/
|
|
if ((ret = st->result) && st->last) {
|
|
st->rollback = true;
|
|
st->bringup = !bringup;
|
|
|
|
__cpuhp_kick_ap(st);
|
|
}
|
|
|
|
/*
|
|
* Clean up the leftovers so the next hotplug operation wont use stale
|
|
* data.
|
|
*/
|
|
st->node = st->last = NULL;
|
|
return ret;
|
|
}
|
|
|
|
static int cpuhp_kick_ap_work(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
enum cpuhp_state prev_state = st->state;
|
|
int ret;
|
|
|
|
cpuhp_lock_acquire(false);
|
|
cpuhp_lock_release(false);
|
|
|
|
cpuhp_lock_acquire(true);
|
|
cpuhp_lock_release(true);
|
|
|
|
trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work);
|
|
ret = cpuhp_kick_ap(st, st->target);
|
|
trace_cpuhp_exit(cpu, st->state, prev_state, ret);
|
|
|
|
return ret;
|
|
}
|
|
|
|
static struct smp_hotplug_thread cpuhp_threads = {
|
|
.store = &cpuhp_state.thread,
|
|
.create = &cpuhp_create,
|
|
.thread_should_run = cpuhp_should_run,
|
|
.thread_fn = cpuhp_thread_fun,
|
|
.thread_comm = "cpuhp/%u",
|
|
.selfparking = true,
|
|
};
|
|
|
|
void __init cpuhp_threads_init(void)
|
|
{
|
|
BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads));
|
|
kthread_unpark(this_cpu_read(cpuhp_state.thread));
|
|
}
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
#ifndef arch_clear_mm_cpumask_cpu
|
|
#define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm))
|
|
#endif
|
|
|
|
/**
|
|
* clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
|
|
* @cpu: a CPU id
|
|
*
|
|
* This function walks all processes, finds a valid mm struct for each one and
|
|
* then clears a corresponding bit in mm's cpumask. While this all sounds
|
|
* trivial, there are various non-obvious corner cases, which this function
|
|
* tries to solve in a safe manner.
|
|
*
|
|
* Also note that the function uses a somewhat relaxed locking scheme, so it may
|
|
* be called only for an already offlined CPU.
|
|
*/
|
|
void clear_tasks_mm_cpumask(int cpu)
|
|
{
|
|
struct task_struct *p;
|
|
|
|
/*
|
|
* This function is called after the cpu is taken down and marked
|
|
* offline, so its not like new tasks will ever get this cpu set in
|
|
* their mm mask. -- Peter Zijlstra
|
|
* Thus, we may use rcu_read_lock() here, instead of grabbing
|
|
* full-fledged tasklist_lock.
|
|
*/
|
|
WARN_ON(cpu_online(cpu));
|
|
rcu_read_lock();
|
|
for_each_process(p) {
|
|
struct task_struct *t;
|
|
|
|
/*
|
|
* Main thread might exit, but other threads may still have
|
|
* a valid mm. Find one.
|
|
*/
|
|
t = find_lock_task_mm(p);
|
|
if (!t)
|
|
continue;
|
|
arch_clear_mm_cpumask_cpu(cpu, t->mm);
|
|
task_unlock(t);
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
/* Take this CPU down. */
|
|
static int take_cpu_down(void *_param)
|
|
{
|
|
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
|
|
enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE);
|
|
int err, cpu = smp_processor_id();
|
|
int ret;
|
|
|
|
/* Ensure this CPU doesn't handle any more interrupts. */
|
|
err = __cpu_disable();
|
|
if (err < 0)
|
|
return err;
|
|
|
|
/*
|
|
* We get here while we are in CPUHP_TEARDOWN_CPU state and we must not
|
|
* do this step again.
|
|
*/
|
|
WARN_ON(st->state != CPUHP_TEARDOWN_CPU);
|
|
st->state--;
|
|
/* Invoke the former CPU_DYING callbacks */
|
|
for (; st->state > target; st->state--) {
|
|
ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
|
|
/*
|
|
* DYING must not fail!
|
|
*/
|
|
WARN_ON_ONCE(ret);
|
|
}
|
|
|
|
/* Give up timekeeping duties */
|
|
tick_handover_do_timer();
|
|
/* Park the stopper thread */
|
|
stop_machine_park(cpu);
|
|
return 0;
|
|
}
|
|
|
|
static int takedown_cpu(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int err;
|
|
|
|
/* Park the smpboot threads */
|
|
kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);
|
|
|
|
/*
|
|
* Prevent irq alloc/free while the dying cpu reorganizes the
|
|
* interrupt affinities.
|
|
*/
|
|
irq_lock_sparse();
|
|
|
|
/*
|
|
* So now all preempt/rcu users must observe !cpu_active().
|
|
*/
|
|
err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu));
|
|
if (err) {
|
|
/* CPU refused to die */
|
|
irq_unlock_sparse();
|
|
/* Unpark the hotplug thread so we can rollback there */
|
|
kthread_unpark(per_cpu_ptr(&cpuhp_state, cpu)->thread);
|
|
return err;
|
|
}
|
|
BUG_ON(cpu_online(cpu));
|
|
|
|
/*
|
|
* The teardown callback for CPUHP_AP_SCHED_STARTING will have removed
|
|
* all runnable tasks from the CPU, there's only the idle task left now
|
|
* that the migration thread is done doing the stop_machine thing.
|
|
*
|
|
* Wait for the stop thread to go away.
|
|
*/
|
|
wait_for_ap_thread(st, false);
|
|
BUG_ON(st->state != CPUHP_AP_IDLE_DEAD);
|
|
|
|
/* Interrupts are moved away from the dying cpu, reenable alloc/free */
|
|
irq_unlock_sparse();
|
|
|
|
hotplug_cpu__broadcast_tick_pull(cpu);
|
|
/* This actually kills the CPU. */
|
|
__cpu_die(cpu);
|
|
|
|
tick_cleanup_dead_cpu(cpu);
|
|
rcutree_migrate_callbacks(cpu);
|
|
return 0;
|
|
}
|
|
|
|
static void cpuhp_complete_idle_dead(void *arg)
|
|
{
|
|
struct cpuhp_cpu_state *st = arg;
|
|
|
|
complete_ap_thread(st, false);
|
|
}
|
|
|
|
void cpuhp_report_idle_dead(void)
|
|
{
|
|
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
|
|
|
|
BUG_ON(st->state != CPUHP_AP_OFFLINE);
|
|
rcu_report_dead(smp_processor_id());
|
|
st->state = CPUHP_AP_IDLE_DEAD;
|
|
/*
|
|
* We cannot call complete after rcu_report_dead() so we delegate it
|
|
* to an online cpu.
|
|
*/
|
|
smp_call_function_single(cpumask_first(cpu_online_mask),
|
|
cpuhp_complete_idle_dead, st, 0);
|
|
}
|
|
|
|
static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st)
|
|
{
|
|
for (st->state++; st->state < st->target; st->state++)
|
|
cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
|
|
}
|
|
|
|
static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
|
|
enum cpuhp_state target)
|
|
{
|
|
enum cpuhp_state prev_state = st->state;
|
|
int ret = 0;
|
|
|
|
for (; st->state > target; st->state--) {
|
|
ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
|
|
if (ret) {
|
|
st->target = prev_state;
|
|
if (st->state < prev_state)
|
|
undo_cpu_down(cpu, st);
|
|
break;
|
|
}
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
/* Requires cpu_add_remove_lock to be held */
|
|
static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
|
|
enum cpuhp_state target)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int prev_state, ret = 0;
|
|
|
|
if (num_online_cpus() == 1)
|
|
return -EBUSY;
|
|
|
|
if (!cpu_present(cpu))
|
|
return -EINVAL;
|
|
|
|
cpus_write_lock();
|
|
|
|
cpuhp_tasks_frozen = tasks_frozen;
|
|
|
|
prev_state = cpuhp_set_state(st, target);
|
|
/*
|
|
* If the current CPU state is in the range of the AP hotplug thread,
|
|
* then we need to kick the thread.
|
|
*/
|
|
if (st->state > CPUHP_TEARDOWN_CPU) {
|
|
st->target = max((int)target, CPUHP_TEARDOWN_CPU);
|
|
ret = cpuhp_kick_ap_work(cpu);
|
|
/*
|
|
* The AP side has done the error rollback already. Just
|
|
* return the error code..
|
|
*/
|
|
if (ret)
|
|
goto out;
|
|
|
|
/*
|
|
* We might have stopped still in the range of the AP hotplug
|
|
* thread. Nothing to do anymore.
|
|
*/
|
|
if (st->state > CPUHP_TEARDOWN_CPU)
|
|
goto out;
|
|
|
|
st->target = target;
|
|
}
|
|
/*
|
|
* The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need
|
|
* to do the further cleanups.
|
|
*/
|
|
ret = cpuhp_down_callbacks(cpu, st, target);
|
|
if (ret && st->state == CPUHP_TEARDOWN_CPU && st->state < prev_state) {
|
|
cpuhp_reset_state(st, prev_state);
|
|
__cpuhp_kick_ap(st);
|
|
}
|
|
|
|
out:
|
|
cpus_write_unlock();
|
|
/*
|
|
* Do post unplug cleanup. This is still protected against
|
|
* concurrent CPU hotplug via cpu_add_remove_lock.
|
|
*/
|
|
lockup_detector_cleanup();
|
|
arch_smt_update();
|
|
return ret;
|
|
}
|
|
|
|
static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
|
|
{
|
|
if (cpu_hotplug_disabled)
|
|
return -EBUSY;
|
|
return _cpu_down(cpu, 0, target);
|
|
}
|
|
|
|
static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
|
|
{
|
|
int err;
|
|
|
|
cpu_maps_update_begin();
|
|
err = cpu_down_maps_locked(cpu, target);
|
|
cpu_maps_update_done();
|
|
return err;
|
|
}
|
|
|
|
int cpu_down(unsigned int cpu)
|
|
{
|
|
return do_cpu_down(cpu, CPUHP_OFFLINE);
|
|
}
|
|
EXPORT_SYMBOL(cpu_down);
|
|
|
|
#else
|
|
#define takedown_cpu NULL
|
|
#endif /*CONFIG_HOTPLUG_CPU*/
|
|
|
|
/**
|
|
* notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU
|
|
* @cpu: cpu that just started
|
|
*
|
|
* It must be called by the arch code on the new cpu, before the new cpu
|
|
* enables interrupts and before the "boot" cpu returns from __cpu_up().
|
|
*/
|
|
void notify_cpu_starting(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
|
|
int ret;
|
|
|
|
rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
|
|
st->booted_once = true;
|
|
while (st->state < target) {
|
|
st->state++;
|
|
ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
|
|
/*
|
|
* STARTING must not fail!
|
|
*/
|
|
WARN_ON_ONCE(ret);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Called from the idle task. Wake up the controlling task which brings the
|
|
* hotplug thread of the upcoming CPU up and then delegates the rest of the
|
|
* online bringup to the hotplug thread.
|
|
*/
|
|
void cpuhp_online_idle(enum cpuhp_state state)
|
|
{
|
|
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
|
|
|
|
/* Happens for the boot cpu */
|
|
if (state != CPUHP_AP_ONLINE_IDLE)
|
|
return;
|
|
|
|
/*
|
|
* Unpart the stopper thread before we start the idle loop (and start
|
|
* scheduling); this ensures the stopper task is always available.
|
|
*/
|
|
stop_machine_unpark(smp_processor_id());
|
|
|
|
st->state = CPUHP_AP_ONLINE_IDLE;
|
|
complete_ap_thread(st, true);
|
|
}
|
|
|
|
/* Requires cpu_add_remove_lock to be held */
|
|
static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
struct task_struct *idle;
|
|
int ret = 0;
|
|
|
|
cpus_write_lock();
|
|
|
|
if (!cpu_present(cpu)) {
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* The caller of do_cpu_up might have raced with another
|
|
* caller. Ignore it for now.
|
|
*/
|
|
if (st->state >= target)
|
|
goto out;
|
|
|
|
if (st->state == CPUHP_OFFLINE) {
|
|
/* Let it fail before we try to bring the cpu up */
|
|
idle = idle_thread_get(cpu);
|
|
if (IS_ERR(idle)) {
|
|
ret = PTR_ERR(idle);
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
cpuhp_tasks_frozen = tasks_frozen;
|
|
|
|
cpuhp_set_state(st, target);
|
|
/*
|
|
* If the current CPU state is in the range of the AP hotplug thread,
|
|
* then we need to kick the thread once more.
|
|
*/
|
|
if (st->state > CPUHP_BRINGUP_CPU) {
|
|
ret = cpuhp_kick_ap_work(cpu);
|
|
/*
|
|
* The AP side has done the error rollback already. Just
|
|
* return the error code..
|
|
*/
|
|
if (ret)
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* Try to reach the target state. We max out on the BP at
|
|
* CPUHP_BRINGUP_CPU. After that the AP hotplug thread is
|
|
* responsible for bringing it up to the target state.
|
|
*/
|
|
target = min((int)target, CPUHP_BRINGUP_CPU);
|
|
ret = cpuhp_up_callbacks(cpu, st, target);
|
|
out:
|
|
cpus_write_unlock();
|
|
arch_smt_update();
|
|
return ret;
|
|
}
|
|
|
|
static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
|
|
{
|
|
int err = 0;
|
|
|
|
if (!cpu_possible(cpu)) {
|
|
pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n",
|
|
cpu);
|
|
#if defined(CONFIG_IA64)
|
|
pr_err("please check additional_cpus= boot parameter\n");
|
|
#endif
|
|
return -EINVAL;
|
|
}
|
|
|
|
err = try_online_node(cpu_to_node(cpu));
|
|
if (err)
|
|
return err;
|
|
|
|
cpu_maps_update_begin();
|
|
|
|
if (cpu_hotplug_disabled) {
|
|
err = -EBUSY;
|
|
goto out;
|
|
}
|
|
if (!cpu_smt_allowed(cpu)) {
|
|
err = -EPERM;
|
|
goto out;
|
|
}
|
|
|
|
err = _cpu_up(cpu, 0, target);
|
|
out:
|
|
cpu_maps_update_done();
|
|
return err;
|
|
}
|
|
|
|
int cpu_up(unsigned int cpu)
|
|
{
|
|
return do_cpu_up(cpu, CPUHP_ONLINE);
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_up);
|
|
|
|
#ifdef CONFIG_PM_SLEEP_SMP
|
|
static cpumask_var_t frozen_cpus;
|
|
|
|
int freeze_secondary_cpus(int primary)
|
|
{
|
|
int cpu, error = 0;
|
|
|
|
cpu_maps_update_begin();
|
|
if (!cpu_online(primary))
|
|
primary = cpumask_first(cpu_online_mask);
|
|
/*
|
|
* We take down all of the non-boot CPUs in one shot to avoid races
|
|
* with the userspace trying to use the CPU hotplug at the same time
|
|
*/
|
|
cpumask_clear(frozen_cpus);
|
|
|
|
pr_info("Disabling non-boot CPUs ...\n");
|
|
for_each_online_cpu(cpu) {
|
|
if (cpu == primary)
|
|
continue;
|
|
trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
|
|
error = _cpu_down(cpu, 1, CPUHP_OFFLINE);
|
|
trace_suspend_resume(TPS("CPU_OFF"), cpu, false);
|
|
if (!error)
|
|
cpumask_set_cpu(cpu, frozen_cpus);
|
|
else {
|
|
pr_err("Error taking CPU%d down: %d\n", cpu, error);
|
|
break;
|
|
}
|
|
}
|
|
|
|
if (!error)
|
|
BUG_ON(num_online_cpus() > 1);
|
|
else
|
|
pr_err("Non-boot CPUs are not disabled\n");
|
|
|
|
/*
|
|
* Make sure the CPUs won't be enabled by someone else. We need to do
|
|
* this even in case of failure as all disable_nonboot_cpus() users are
|
|
* supposed to do enable_nonboot_cpus() on the failure path.
|
|
*/
|
|
cpu_hotplug_disabled++;
|
|
|
|
cpu_maps_update_done();
|
|
return error;
|
|
}
|
|
|
|
void __weak arch_enable_nonboot_cpus_begin(void)
|
|
{
|
|
}
|
|
|
|
void __weak arch_enable_nonboot_cpus_end(void)
|
|
{
|
|
}
|
|
|
|
void enable_nonboot_cpus(void)
|
|
{
|
|
int cpu, error;
|
|
struct device *cpu_device;
|
|
|
|
/* Allow everyone to use the CPU hotplug again */
|
|
cpu_maps_update_begin();
|
|
__cpu_hotplug_enable();
|
|
if (cpumask_empty(frozen_cpus))
|
|
goto out;
|
|
|
|
pr_info("Enabling non-boot CPUs ...\n");
|
|
|
|
arch_enable_nonboot_cpus_begin();
|
|
|
|
for_each_cpu(cpu, frozen_cpus) {
|
|
trace_suspend_resume(TPS("CPU_ON"), cpu, true);
|
|
error = _cpu_up(cpu, 1, CPUHP_ONLINE);
|
|
trace_suspend_resume(TPS("CPU_ON"), cpu, false);
|
|
if (!error) {
|
|
pr_info("CPU%d is up\n", cpu);
|
|
cpu_device = get_cpu_device(cpu);
|
|
if (!cpu_device)
|
|
pr_err("%s: failed to get cpu%d device\n",
|
|
__func__, cpu);
|
|
else
|
|
kobject_uevent(&cpu_device->kobj, KOBJ_ONLINE);
|
|
continue;
|
|
}
|
|
pr_warn("Error taking CPU%d up: %d\n", cpu, error);
|
|
}
|
|
|
|
arch_enable_nonboot_cpus_end();
|
|
|
|
cpumask_clear(frozen_cpus);
|
|
out:
|
|
cpu_maps_update_done();
|
|
}
|
|
|
|
static int __init alloc_frozen_cpus(void)
|
|
{
|
|
if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO))
|
|
return -ENOMEM;
|
|
return 0;
|
|
}
|
|
core_initcall(alloc_frozen_cpus);
|
|
|
|
/*
|
|
* When callbacks for CPU hotplug notifications are being executed, we must
|
|
* ensure that the state of the system with respect to the tasks being frozen
|
|
* or not, as reported by the notification, remains unchanged *throughout the
|
|
* duration* of the execution of the callbacks.
|
|
* Hence we need to prevent the freezer from racing with regular CPU hotplug.
|
|
*
|
|
* This synchronization is implemented by mutually excluding regular CPU
|
|
* hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/
|
|
* Hibernate notifications.
|
|
*/
|
|
static int
|
|
cpu_hotplug_pm_callback(struct notifier_block *nb,
|
|
unsigned long action, void *ptr)
|
|
{
|
|
switch (action) {
|
|
|
|
case PM_SUSPEND_PREPARE:
|
|
case PM_HIBERNATION_PREPARE:
|
|
cpu_hotplug_disable();
|
|
break;
|
|
|
|
case PM_POST_SUSPEND:
|
|
case PM_POST_HIBERNATION:
|
|
cpu_hotplug_enable();
|
|
break;
|
|
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
|
|
static int __init cpu_hotplug_pm_sync_init(void)
|
|
{
|
|
/*
|
|
* cpu_hotplug_pm_callback has higher priority than x86
|
|
* bsp_pm_callback which depends on cpu_hotplug_pm_callback
|
|
* to disable cpu hotplug to avoid cpu hotplug race.
|
|
*/
|
|
pm_notifier(cpu_hotplug_pm_callback, 0);
|
|
return 0;
|
|
}
|
|
core_initcall(cpu_hotplug_pm_sync_init);
|
|
|
|
#endif /* CONFIG_PM_SLEEP_SMP */
|
|
|
|
int __boot_cpu_id;
|
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
/* Boot processor state steps */
|
|
static struct cpuhp_step cpuhp_hp_states[] = {
|
|
[CPUHP_OFFLINE] = {
|
|
.name = "offline",
|
|
.startup.single = NULL,
|
|
.teardown.single = NULL,
|
|
},
|
|
#ifdef CONFIG_SMP
|
|
[CPUHP_CREATE_THREADS]= {
|
|
.name = "threads:prepare",
|
|
.startup.single = smpboot_create_threads,
|
|
.teardown.single = NULL,
|
|
.cant_stop = true,
|
|
},
|
|
[CPUHP_PERF_PREPARE] = {
|
|
.name = "perf:prepare",
|
|
.startup.single = perf_event_init_cpu,
|
|
.teardown.single = perf_event_exit_cpu,
|
|
},
|
|
[CPUHP_WORKQUEUE_PREP] = {
|
|
.name = "workqueue:prepare",
|
|
.startup.single = workqueue_prepare_cpu,
|
|
.teardown.single = NULL,
|
|
},
|
|
[CPUHP_HRTIMERS_PREPARE] = {
|
|
.name = "hrtimers:prepare",
|
|
.startup.single = hrtimers_prepare_cpu,
|
|
.teardown.single = hrtimers_dead_cpu,
|
|
},
|
|
[CPUHP_SMPCFD_PREPARE] = {
|
|
.name = "smpcfd:prepare",
|
|
.startup.single = smpcfd_prepare_cpu,
|
|
.teardown.single = smpcfd_dead_cpu,
|
|
},
|
|
[CPUHP_RELAY_PREPARE] = {
|
|
.name = "relay:prepare",
|
|
.startup.single = relay_prepare_cpu,
|
|
.teardown.single = NULL,
|
|
},
|
|
[CPUHP_SLAB_PREPARE] = {
|
|
.name = "slab:prepare",
|
|
.startup.single = slab_prepare_cpu,
|
|
.teardown.single = slab_dead_cpu,
|
|
},
|
|
[CPUHP_RCUTREE_PREP] = {
|
|
.name = "RCU/tree:prepare",
|
|
.startup.single = rcutree_prepare_cpu,
|
|
.teardown.single = rcutree_dead_cpu,
|
|
},
|
|
/*
|
|
* On the tear-down path, timers_dead_cpu() must be invoked
|
|
* before blk_mq_queue_reinit_notify() from notify_dead(),
|
|
* otherwise a RCU stall occurs.
|
|
*/
|
|
[CPUHP_TIMERS_PREPARE] = {
|
|
.name = "timers:prepare",
|
|
.startup.single = timers_prepare_cpu,
|
|
.teardown.single = timers_dead_cpu,
|
|
},
|
|
/* Kicks the plugged cpu into life */
|
|
[CPUHP_BRINGUP_CPU] = {
|
|
.name = "cpu:bringup",
|
|
.startup.single = bringup_cpu,
|
|
.teardown.single = finish_cpu,
|
|
.cant_stop = true,
|
|
},
|
|
/* Final state before CPU kills itself */
|
|
[CPUHP_AP_IDLE_DEAD] = {
|
|
.name = "idle:dead",
|
|
},
|
|
/*
|
|
* Last state before CPU enters the idle loop to die. Transient state
|
|
* for synchronization.
|
|
*/
|
|
[CPUHP_AP_OFFLINE] = {
|
|
.name = "ap:offline",
|
|
.cant_stop = true,
|
|
},
|
|
/* First state is scheduler control. Interrupts are disabled */
|
|
[CPUHP_AP_SCHED_STARTING] = {
|
|
.name = "sched:starting",
|
|
.startup.single = sched_cpu_starting,
|
|
.teardown.single = sched_cpu_dying,
|
|
},
|
|
[CPUHP_AP_RCUTREE_DYING] = {
|
|
.name = "RCU/tree:dying",
|
|
.startup.single = NULL,
|
|
.teardown.single = rcutree_dying_cpu,
|
|
},
|
|
[CPUHP_AP_SMPCFD_DYING] = {
|
|
.name = "smpcfd:dying",
|
|
.startup.single = NULL,
|
|
.teardown.single = smpcfd_dying_cpu,
|
|
},
|
|
/* Entry state on starting. Interrupts enabled from here on. Transient
|
|
* state for synchronsization */
|
|
[CPUHP_AP_ONLINE] = {
|
|
.name = "ap:online",
|
|
},
|
|
/*
|
|
* Handled on controll processor until the plugged processor manages
|
|
* this itself.
|
|
*/
|
|
[CPUHP_TEARDOWN_CPU] = {
|
|
.name = "cpu:teardown",
|
|
.startup.single = NULL,
|
|
.teardown.single = takedown_cpu,
|
|
.cant_stop = true,
|
|
},
|
|
/* Handle smpboot threads park/unpark */
|
|
[CPUHP_AP_SMPBOOT_THREADS] = {
|
|
.name = "smpboot/threads:online",
|
|
.startup.single = smpboot_unpark_threads,
|
|
.teardown.single = smpboot_park_threads,
|
|
},
|
|
[CPUHP_AP_IRQ_AFFINITY_ONLINE] = {
|
|
.name = "irq/affinity:online",
|
|
.startup.single = irq_affinity_online_cpu,
|
|
.teardown.single = NULL,
|
|
},
|
|
[CPUHP_AP_PERF_ONLINE] = {
|
|
.name = "perf:online",
|
|
.startup.single = perf_event_init_cpu,
|
|
.teardown.single = perf_event_exit_cpu,
|
|
},
|
|
[CPUHP_AP_WATCHDOG_ONLINE] = {
|
|
.name = "lockup_detector:online",
|
|
.startup.single = lockup_detector_online_cpu,
|
|
.teardown.single = lockup_detector_offline_cpu,
|
|
},
|
|
[CPUHP_AP_WORKQUEUE_ONLINE] = {
|
|
.name = "workqueue:online",
|
|
.startup.single = workqueue_online_cpu,
|
|
.teardown.single = workqueue_offline_cpu,
|
|
},
|
|
[CPUHP_AP_RCUTREE_ONLINE] = {
|
|
.name = "RCU/tree:online",
|
|
.startup.single = rcutree_online_cpu,
|
|
.teardown.single = rcutree_offline_cpu,
|
|
},
|
|
#endif
|
|
/*
|
|
* The dynamically registered state space is here
|
|
*/
|
|
|
|
#ifdef CONFIG_SMP
|
|
/* Last state is scheduler control setting the cpu active */
|
|
[CPUHP_AP_ACTIVE] = {
|
|
.name = "sched:active",
|
|
.startup.single = sched_cpu_activate,
|
|
.teardown.single = sched_cpu_deactivate,
|
|
},
|
|
#endif
|
|
|
|
/* CPU is fully up and running. */
|
|
[CPUHP_ONLINE] = {
|
|
.name = "online",
|
|
.startup.single = NULL,
|
|
.teardown.single = NULL,
|
|
},
|
|
};
|
|
|
|
/* Sanity check for callbacks */
|
|
static int cpuhp_cb_check(enum cpuhp_state state)
|
|
{
|
|
if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE)
|
|
return -EINVAL;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Returns a free for dynamic slot assignment of the Online state. The states
|
|
* are protected by the cpuhp_slot_states mutex and an empty slot is identified
|
|
* by having no name assigned.
|
|
*/
|
|
static int cpuhp_reserve_state(enum cpuhp_state state)
|
|
{
|
|
enum cpuhp_state i, end;
|
|
struct cpuhp_step *step;
|
|
|
|
switch (state) {
|
|
case CPUHP_AP_ONLINE_DYN:
|
|
step = cpuhp_hp_states + CPUHP_AP_ONLINE_DYN;
|
|
end = CPUHP_AP_ONLINE_DYN_END;
|
|
break;
|
|
case CPUHP_BP_PREPARE_DYN:
|
|
step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN;
|
|
end = CPUHP_BP_PREPARE_DYN_END;
|
|
break;
|
|
default:
|
|
return -EINVAL;
|
|
}
|
|
|
|
for (i = state; i <= end; i++, step++) {
|
|
if (!step->name)
|
|
return i;
|
|
}
|
|
WARN(1, "No more dynamic states available for CPU hotplug\n");
|
|
return -ENOSPC;
|
|
}
|
|
|
|
static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name,
|
|
int (*startup)(unsigned int cpu),
|
|
int (*teardown)(unsigned int cpu),
|
|
bool multi_instance)
|
|
{
|
|
/* (Un)Install the callbacks for further cpu hotplug operations */
|
|
struct cpuhp_step *sp;
|
|
int ret = 0;
|
|
|
|
/*
|
|
* If name is NULL, then the state gets removed.
|
|
*
|
|
* CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on
|
|
* the first allocation from these dynamic ranges, so the removal
|
|
* would trigger a new allocation and clear the wrong (already
|
|
* empty) state, leaving the callbacks of the to be cleared state
|
|
* dangling, which causes wreckage on the next hotplug operation.
|
|
*/
|
|
if (name && (state == CPUHP_AP_ONLINE_DYN ||
|
|
state == CPUHP_BP_PREPARE_DYN)) {
|
|
ret = cpuhp_reserve_state(state);
|
|
if (ret < 0)
|
|
return ret;
|
|
state = ret;
|
|
}
|
|
sp = cpuhp_get_step(state);
|
|
if (name && sp->name)
|
|
return -EBUSY;
|
|
|
|
sp->startup.single = startup;
|
|
sp->teardown.single = teardown;
|
|
sp->name = name;
|
|
sp->multi_instance = multi_instance;
|
|
INIT_HLIST_HEAD(&sp->list);
|
|
return ret;
|
|
}
|
|
|
|
static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
|
|
{
|
|
return cpuhp_get_step(state)->teardown.single;
|
|
}
|
|
|
|
/*
|
|
* Call the startup/teardown function for a step either on the AP or
|
|
* on the current CPU.
|
|
*/
|
|
static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup,
|
|
struct hlist_node *node)
|
|
{
|
|
struct cpuhp_step *sp = cpuhp_get_step(state);
|
|
int ret;
|
|
|
|
/*
|
|
* If there's nothing to do, we done.
|
|
* Relies on the union for multi_instance.
|
|
*/
|
|
if ((bringup && !sp->startup.single) ||
|
|
(!bringup && !sp->teardown.single))
|
|
return 0;
|
|
/*
|
|
* The non AP bound callbacks can fail on bringup. On teardown
|
|
* e.g. module removal we crash for now.
|
|
*/
|
|
#ifdef CONFIG_SMP
|
|
if (cpuhp_is_ap_state(state))
|
|
ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node);
|
|
else
|
|
ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
|
|
#else
|
|
ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
|
|
#endif
|
|
BUG_ON(ret && !bringup);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Called from __cpuhp_setup_state on a recoverable failure.
|
|
*
|
|
* Note: The teardown callbacks for rollback are not allowed to fail!
|
|
*/
|
|
static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
|
|
struct hlist_node *node)
|
|
{
|
|
int cpu;
|
|
|
|
/* Roll back the already executed steps on the other cpus */
|
|
for_each_present_cpu(cpu) {
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int cpustate = st->state;
|
|
|
|
if (cpu >= failedcpu)
|
|
break;
|
|
|
|
/* Did we invoke the startup call on that cpu ? */
|
|
if (cpustate >= state)
|
|
cpuhp_issue_call(cpu, state, false, node);
|
|
}
|
|
}
|
|
|
|
int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state,
|
|
struct hlist_node *node,
|
|
bool invoke)
|
|
{
|
|
struct cpuhp_step *sp;
|
|
int cpu;
|
|
int ret;
|
|
|
|
lockdep_assert_cpus_held();
|
|
|
|
sp = cpuhp_get_step(state);
|
|
if (sp->multi_instance == false)
|
|
return -EINVAL;
|
|
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
|
|
if (!invoke || !sp->startup.multi)
|
|
goto add_node;
|
|
|
|
/*
|
|
* Try to call the startup callback for each present cpu
|
|
* depending on the hotplug state of the cpu.
|
|
*/
|
|
for_each_present_cpu(cpu) {
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int cpustate = st->state;
|
|
|
|
if (cpustate < state)
|
|
continue;
|
|
|
|
ret = cpuhp_issue_call(cpu, state, true, node);
|
|
if (ret) {
|
|
if (sp->teardown.multi)
|
|
cpuhp_rollback_install(cpu, state, node);
|
|
goto unlock;
|
|
}
|
|
}
|
|
add_node:
|
|
ret = 0;
|
|
hlist_add_head(node, &sp->list);
|
|
unlock:
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
return ret;
|
|
}
|
|
|
|
int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
|
|
bool invoke)
|
|
{
|
|
int ret;
|
|
|
|
cpus_read_lock();
|
|
ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke);
|
|
cpus_read_unlock();
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
|
|
|
|
/**
|
|
* __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state
|
|
* @state: The state to setup
|
|
* @invoke: If true, the startup function is invoked for cpus where
|
|
* cpu state >= @state
|
|
* @startup: startup callback function
|
|
* @teardown: teardown callback function
|
|
* @multi_instance: State is set up for multiple instances which get
|
|
* added afterwards.
|
|
*
|
|
* The caller needs to hold cpus read locked while calling this function.
|
|
* Returns:
|
|
* On success:
|
|
* Positive state number if @state is CPUHP_AP_ONLINE_DYN
|
|
* 0 for all other states
|
|
* On failure: proper (negative) error code
|
|
*/
|
|
int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state,
|
|
const char *name, bool invoke,
|
|
int (*startup)(unsigned int cpu),
|
|
int (*teardown)(unsigned int cpu),
|
|
bool multi_instance)
|
|
{
|
|
int cpu, ret = 0;
|
|
bool dynstate;
|
|
|
|
lockdep_assert_cpus_held();
|
|
|
|
if (cpuhp_cb_check(state) || !name)
|
|
return -EINVAL;
|
|
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
|
|
ret = cpuhp_store_callbacks(state, name, startup, teardown,
|
|
multi_instance);
|
|
|
|
dynstate = state == CPUHP_AP_ONLINE_DYN;
|
|
if (ret > 0 && dynstate) {
|
|
state = ret;
|
|
ret = 0;
|
|
}
|
|
|
|
if (ret || !invoke || !startup)
|
|
goto out;
|
|
|
|
/*
|
|
* Try to call the startup callback for each present cpu
|
|
* depending on the hotplug state of the cpu.
|
|
*/
|
|
for_each_present_cpu(cpu) {
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int cpustate = st->state;
|
|
|
|
if (cpustate < state)
|
|
continue;
|
|
|
|
ret = cpuhp_issue_call(cpu, state, true, NULL);
|
|
if (ret) {
|
|
if (teardown)
|
|
cpuhp_rollback_install(cpu, state, NULL);
|
|
cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
|
|
goto out;
|
|
}
|
|
}
|
|
out:
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
/*
|
|
* If the requested state is CPUHP_AP_ONLINE_DYN, return the
|
|
* dynamically allocated state in case of success.
|
|
*/
|
|
if (!ret && dynstate)
|
|
return state;
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked);
|
|
|
|
int __cpuhp_setup_state(enum cpuhp_state state,
|
|
const char *name, bool invoke,
|
|
int (*startup)(unsigned int cpu),
|
|
int (*teardown)(unsigned int cpu),
|
|
bool multi_instance)
|
|
{
|
|
int ret;
|
|
|
|
cpus_read_lock();
|
|
ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup,
|
|
teardown, multi_instance);
|
|
cpus_read_unlock();
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(__cpuhp_setup_state);
|
|
|
|
int __cpuhp_state_remove_instance(enum cpuhp_state state,
|
|
struct hlist_node *node, bool invoke)
|
|
{
|
|
struct cpuhp_step *sp = cpuhp_get_step(state);
|
|
int cpu;
|
|
|
|
BUG_ON(cpuhp_cb_check(state));
|
|
|
|
if (!sp->multi_instance)
|
|
return -EINVAL;
|
|
|
|
cpus_read_lock();
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
|
|
if (!invoke || !cpuhp_get_teardown_cb(state))
|
|
goto remove;
|
|
/*
|
|
* Call the teardown callback for each present cpu depending
|
|
* on the hotplug state of the cpu. This function is not
|
|
* allowed to fail currently!
|
|
*/
|
|
for_each_present_cpu(cpu) {
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int cpustate = st->state;
|
|
|
|
if (cpustate >= state)
|
|
cpuhp_issue_call(cpu, state, false, node);
|
|
}
|
|
|
|
remove:
|
|
hlist_del(node);
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
cpus_read_unlock();
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance);
|
|
|
|
/**
|
|
* __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state
|
|
* @state: The state to remove
|
|
* @invoke: If true, the teardown function is invoked for cpus where
|
|
* cpu state >= @state
|
|
*
|
|
* The caller needs to hold cpus read locked while calling this function.
|
|
* The teardown callback is currently not allowed to fail. Think
|
|
* about module removal!
|
|
*/
|
|
void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke)
|
|
{
|
|
struct cpuhp_step *sp = cpuhp_get_step(state);
|
|
int cpu;
|
|
|
|
BUG_ON(cpuhp_cb_check(state));
|
|
|
|
lockdep_assert_cpus_held();
|
|
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
if (sp->multi_instance) {
|
|
WARN(!hlist_empty(&sp->list),
|
|
"Error: Removing state %d which has instances left.\n",
|
|
state);
|
|
goto remove;
|
|
}
|
|
|
|
if (!invoke || !cpuhp_get_teardown_cb(state))
|
|
goto remove;
|
|
|
|
/*
|
|
* Call the teardown callback for each present cpu depending
|
|
* on the hotplug state of the cpu. This function is not
|
|
* allowed to fail currently!
|
|
*/
|
|
for_each_present_cpu(cpu) {
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int cpustate = st->state;
|
|
|
|
if (cpustate >= state)
|
|
cpuhp_issue_call(cpu, state, false, NULL);
|
|
}
|
|
remove:
|
|
cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
}
|
|
EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked);
|
|
|
|
void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
|
|
{
|
|
cpus_read_lock();
|
|
__cpuhp_remove_state_cpuslocked(state, invoke);
|
|
cpus_read_unlock();
|
|
}
|
|
EXPORT_SYMBOL(__cpuhp_remove_state);
|
|
|
|
#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
|
|
static ssize_t show_cpuhp_state(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
|
|
|
|
return sprintf(buf, "%d\n", st->state);
|
|
}
|
|
static DEVICE_ATTR(state, 0444, show_cpuhp_state, NULL);
|
|
|
|
static ssize_t write_cpuhp_target(struct device *dev,
|
|
struct device_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
|
|
struct cpuhp_step *sp;
|
|
int target, ret;
|
|
|
|
ret = kstrtoint(buf, 10, &target);
|
|
if (ret)
|
|
return ret;
|
|
|
|
#ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL
|
|
if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE)
|
|
return -EINVAL;
|
|
#else
|
|
if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE)
|
|
return -EINVAL;
|
|
#endif
|
|
|
|
ret = lock_device_hotplug_sysfs();
|
|
if (ret)
|
|
return ret;
|
|
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
sp = cpuhp_get_step(target);
|
|
ret = !sp->name || sp->cant_stop ? -EINVAL : 0;
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
if (ret)
|
|
goto out;
|
|
|
|
if (st->state < target)
|
|
ret = do_cpu_up(dev->id, target);
|
|
else
|
|
ret = do_cpu_down(dev->id, target);
|
|
out:
|
|
unlock_device_hotplug();
|
|
return ret ? ret : count;
|
|
}
|
|
|
|
static ssize_t show_cpuhp_target(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
|
|
|
|
return sprintf(buf, "%d\n", st->target);
|
|
}
|
|
static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target);
|
|
|
|
|
|
static ssize_t write_cpuhp_fail(struct device *dev,
|
|
struct device_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
|
|
struct cpuhp_step *sp;
|
|
int fail, ret;
|
|
|
|
ret = kstrtoint(buf, 10, &fail);
|
|
if (ret)
|
|
return ret;
|
|
|
|
if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE)
|
|
return -EINVAL;
|
|
|
|
/*
|
|
* Cannot fail STARTING/DYING callbacks.
|
|
*/
|
|
if (cpuhp_is_atomic_state(fail))
|
|
return -EINVAL;
|
|
|
|
/*
|
|
* Cannot fail anything that doesn't have callbacks.
|
|
*/
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
sp = cpuhp_get_step(fail);
|
|
if (!sp->startup.single && !sp->teardown.single)
|
|
ret = -EINVAL;
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
if (ret)
|
|
return ret;
|
|
|
|
st->fail = fail;
|
|
|
|
return count;
|
|
}
|
|
|
|
static ssize_t show_cpuhp_fail(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
|
|
|
|
return sprintf(buf, "%d\n", st->fail);
|
|
}
|
|
|
|
static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail);
|
|
|
|
static struct attribute *cpuhp_cpu_attrs[] = {
|
|
&dev_attr_state.attr,
|
|
&dev_attr_target.attr,
|
|
&dev_attr_fail.attr,
|
|
NULL
|
|
};
|
|
|
|
static const struct attribute_group cpuhp_cpu_attr_group = {
|
|
.attrs = cpuhp_cpu_attrs,
|
|
.name = "hotplug",
|
|
NULL
|
|
};
|
|
|
|
static ssize_t show_cpuhp_states(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
ssize_t cur, res = 0;
|
|
int i;
|
|
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) {
|
|
struct cpuhp_step *sp = cpuhp_get_step(i);
|
|
|
|
if (sp->name) {
|
|
cur = sprintf(buf, "%3d: %s\n", i, sp->name);
|
|
buf += cur;
|
|
res += cur;
|
|
}
|
|
}
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
return res;
|
|
}
|
|
static DEVICE_ATTR(states, 0444, show_cpuhp_states, NULL);
|
|
|
|
static struct attribute *cpuhp_cpu_root_attrs[] = {
|
|
&dev_attr_states.attr,
|
|
NULL
|
|
};
|
|
|
|
static const struct attribute_group cpuhp_cpu_root_attr_group = {
|
|
.attrs = cpuhp_cpu_root_attrs,
|
|
.name = "hotplug",
|
|
NULL
|
|
};
|
|
|
|
#ifdef CONFIG_HOTPLUG_SMT
|
|
|
|
static const char *smt_states[] = {
|
|
[CPU_SMT_ENABLED] = "on",
|
|
[CPU_SMT_DISABLED] = "off",
|
|
[CPU_SMT_FORCE_DISABLED] = "forceoff",
|
|
[CPU_SMT_NOT_SUPPORTED] = "notsupported",
|
|
};
|
|
|
|
static ssize_t
|
|
show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
|
|
{
|
|
return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]);
|
|
}
|
|
|
|
static void cpuhp_offline_cpu_device(unsigned int cpu)
|
|
{
|
|
struct device *dev = get_cpu_device(cpu);
|
|
|
|
dev->offline = true;
|
|
/* Tell user space about the state change */
|
|
kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
|
|
}
|
|
|
|
static void cpuhp_online_cpu_device(unsigned int cpu)
|
|
{
|
|
struct device *dev = get_cpu_device(cpu);
|
|
|
|
dev->offline = false;
|
|
/* Tell user space about the state change */
|
|
kobject_uevent(&dev->kobj, KOBJ_ONLINE);
|
|
}
|
|
|
|
int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
|
|
{
|
|
int cpu, ret = 0;
|
|
|
|
cpu_maps_update_begin();
|
|
for_each_online_cpu(cpu) {
|
|
if (topology_is_primary_thread(cpu))
|
|
continue;
|
|
ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
|
|
if (ret)
|
|
break;
|
|
/*
|
|
* As this needs to hold the cpu maps lock it's impossible
|
|
* to call device_offline() because that ends up calling
|
|
* cpu_down() which takes cpu maps lock. cpu maps lock
|
|
* needs to be held as this might race against in kernel
|
|
* abusers of the hotplug machinery (thermal management).
|
|
*
|
|
* So nothing would update device:offline state. That would
|
|
* leave the sysfs entry stale and prevent onlining after
|
|
* smt control has been changed to 'off' again. This is
|
|
* called under the sysfs hotplug lock, so it is properly
|
|
* serialized against the regular offline usage.
|
|
*/
|
|
cpuhp_offline_cpu_device(cpu);
|
|
}
|
|
if (!ret)
|
|
cpu_smt_control = ctrlval;
|
|
cpu_maps_update_done();
|
|
return ret;
|
|
}
|
|
|
|
int cpuhp_smt_enable(void)
|
|
{
|
|
int cpu, ret = 0;
|
|
|
|
cpu_maps_update_begin();
|
|
cpu_smt_control = CPU_SMT_ENABLED;
|
|
for_each_present_cpu(cpu) {
|
|
/* Skip online CPUs and CPUs on offline nodes */
|
|
if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
|
|
continue;
|
|
ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
|
|
if (ret)
|
|
break;
|
|
/* See comment in cpuhp_smt_disable() */
|
|
cpuhp_online_cpu_device(cpu);
|
|
}
|
|
cpu_maps_update_done();
|
|
return ret;
|
|
}
|
|
|
|
static ssize_t
|
|
store_smt_control(struct device *dev, struct device_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
int ctrlval, ret;
|
|
|
|
if (sysfs_streq(buf, "on"))
|
|
ctrlval = CPU_SMT_ENABLED;
|
|
else if (sysfs_streq(buf, "off"))
|
|
ctrlval = CPU_SMT_DISABLED;
|
|
else if (sysfs_streq(buf, "forceoff"))
|
|
ctrlval = CPU_SMT_FORCE_DISABLED;
|
|
else
|
|
return -EINVAL;
|
|
|
|
if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
|
|
return -EPERM;
|
|
|
|
if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
|
|
return -ENODEV;
|
|
|
|
ret = lock_device_hotplug_sysfs();
|
|
if (ret)
|
|
return ret;
|
|
|
|
if (ctrlval != cpu_smt_control) {
|
|
switch (ctrlval) {
|
|
case CPU_SMT_ENABLED:
|
|
ret = cpuhp_smt_enable();
|
|
break;
|
|
case CPU_SMT_DISABLED:
|
|
case CPU_SMT_FORCE_DISABLED:
|
|
ret = cpuhp_smt_disable(ctrlval);
|
|
break;
|
|
}
|
|
}
|
|
|
|
unlock_device_hotplug();
|
|
return ret ? ret : count;
|
|
}
|
|
static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control);
|
|
|
|
static ssize_t
|
|
show_smt_active(struct device *dev, struct device_attribute *attr, char *buf)
|
|
{
|
|
bool active = topology_max_smt_threads() > 1;
|
|
|
|
return snprintf(buf, PAGE_SIZE - 2, "%d\n", active);
|
|
}
|
|
static DEVICE_ATTR(active, 0444, show_smt_active, NULL);
|
|
|
|
static struct attribute *cpuhp_smt_attrs[] = {
|
|
&dev_attr_control.attr,
|
|
&dev_attr_active.attr,
|
|
NULL
|
|
};
|
|
|
|
static const struct attribute_group cpuhp_smt_attr_group = {
|
|
.attrs = cpuhp_smt_attrs,
|
|
.name = "smt",
|
|
NULL
|
|
};
|
|
|
|
static int __init cpu_smt_state_init(void)
|
|
{
|
|
return sysfs_create_group(&cpu_subsys.dev_root->kobj,
|
|
&cpuhp_smt_attr_group);
|
|
}
|
|
|
|
#else
|
|
static inline int cpu_smt_state_init(void) { return 0; }
|
|
#endif
|
|
|
|
static int __init cpuhp_sysfs_init(void)
|
|
{
|
|
int cpu, ret;
|
|
|
|
ret = cpu_smt_state_init();
|
|
if (ret)
|
|
return ret;
|
|
|
|
ret = sysfs_create_group(&cpu_subsys.dev_root->kobj,
|
|
&cpuhp_cpu_root_attr_group);
|
|
if (ret)
|
|
return ret;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
struct device *dev = get_cpu_device(cpu);
|
|
|
|
if (!dev)
|
|
continue;
|
|
ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group);
|
|
if (ret)
|
|
return ret;
|
|
}
|
|
return 0;
|
|
}
|
|
device_initcall(cpuhp_sysfs_init);
|
|
#endif
|
|
|
|
/*
|
|
* cpu_bit_bitmap[] is a special, "compressed" data structure that
|
|
* represents all NR_CPUS bits binary values of 1<<nr.
|
|
*
|
|
* It is used by cpumask_of() to get a constant address to a CPU
|
|
* mask value that has a single bit set only.
|
|
*/
|
|
|
|
/* cpu_bit_bitmap[0] is empty - so we can back into it */
|
|
#define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x))
|
|
#define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)
|
|
#define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)
|
|
#define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)
|
|
|
|
const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
|
|
|
|
MASK_DECLARE_8(0), MASK_DECLARE_8(8),
|
|
MASK_DECLARE_8(16), MASK_DECLARE_8(24),
|
|
#if BITS_PER_LONG > 32
|
|
MASK_DECLARE_8(32), MASK_DECLARE_8(40),
|
|
MASK_DECLARE_8(48), MASK_DECLARE_8(56),
|
|
#endif
|
|
};
|
|
EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
|
|
|
|
const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
|
|
EXPORT_SYMBOL(cpu_all_bits);
|
|
|
|
#ifdef CONFIG_INIT_ALL_POSSIBLE
|
|
struct cpumask __cpu_possible_mask __read_mostly
|
|
= {CPU_BITS_ALL};
|
|
#else
|
|
struct cpumask __cpu_possible_mask __read_mostly;
|
|
#endif
|
|
EXPORT_SYMBOL(__cpu_possible_mask);
|
|
|
|
struct cpumask __cpu_online_mask __read_mostly;
|
|
EXPORT_SYMBOL(__cpu_online_mask);
|
|
|
|
struct cpumask __cpu_present_mask __read_mostly;
|
|
EXPORT_SYMBOL(__cpu_present_mask);
|
|
|
|
struct cpumask __cpu_active_mask __read_mostly;
|
|
EXPORT_SYMBOL(__cpu_active_mask);
|
|
|
|
struct cpumask __cpu_isolated_mask __read_mostly;
|
|
EXPORT_SYMBOL(__cpu_isolated_mask);
|
|
|
|
void init_cpu_present(const struct cpumask *src)
|
|
{
|
|
cpumask_copy(&__cpu_present_mask, src);
|
|
}
|
|
|
|
void init_cpu_possible(const struct cpumask *src)
|
|
{
|
|
cpumask_copy(&__cpu_possible_mask, src);
|
|
}
|
|
|
|
void init_cpu_online(const struct cpumask *src)
|
|
{
|
|
cpumask_copy(&__cpu_online_mask, src);
|
|
}
|
|
|
|
/*
|
|
* Activate the first processor.
|
|
*/
|
|
void __init boot_cpu_init(void)
|
|
{
|
|
int cpu = smp_processor_id();
|
|
|
|
/* Mark the boot cpu "present", "online" etc for SMP and UP case */
|
|
set_cpu_online(cpu, true);
|
|
set_cpu_active(cpu, true);
|
|
set_cpu_present(cpu, true);
|
|
set_cpu_possible(cpu, true);
|
|
|
|
#ifdef CONFIG_SMP
|
|
__boot_cpu_id = cpu;
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* Must be called _AFTER_ setting up the per_cpu areas
|
|
*/
|
|
void __init boot_cpu_hotplug_init(void)
|
|
{
|
|
#ifdef CONFIG_SMP
|
|
this_cpu_write(cpuhp_state.booted_once, true);
|
|
#endif
|
|
this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
|
|
}
|
|
|
|
/*
|
|
* These are used for a global "mitigations=" cmdline option for toggling
|
|
* optional CPU mitigations.
|
|
*/
|
|
enum cpu_mitigations {
|
|
CPU_MITIGATIONS_OFF,
|
|
CPU_MITIGATIONS_AUTO,
|
|
CPU_MITIGATIONS_AUTO_NOSMT,
|
|
};
|
|
|
|
static enum cpu_mitigations cpu_mitigations __ro_after_init =
|
|
CPU_MITIGATIONS_AUTO;
|
|
|
|
static int __init mitigations_parse_cmdline(char *arg)
|
|
{
|
|
if (!strcmp(arg, "off"))
|
|
cpu_mitigations = CPU_MITIGATIONS_OFF;
|
|
else if (!strcmp(arg, "auto"))
|
|
cpu_mitigations = CPU_MITIGATIONS_AUTO;
|
|
else if (!strcmp(arg, "auto,nosmt"))
|
|
cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT;
|
|
else
|
|
pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n",
|
|
arg);
|
|
|
|
return 0;
|
|
}
|
|
early_param("mitigations", mitigations_parse_cmdline);
|
|
|
|
/* mitigations=off */
|
|
bool cpu_mitigations_off(void)
|
|
{
|
|
return cpu_mitigations == CPU_MITIGATIONS_OFF;
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_mitigations_off);
|
|
|
|
/* mitigations=auto,nosmt */
|
|
bool cpu_mitigations_auto_nosmt(void)
|
|
{
|
|
return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt);
|