mirror of
https://github.com/BobTheBlinker/android_kernel_motorola_sm6375.git
synced 2026-10-06 03:45:24 -04:00
-----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAl91u0cACgkQONu9yGCS aT7KmhAAvuW3edfAfzD/F5h4vHaa9rMRmtvp2/FwefBoE4LEi3F6p2gBrUZMA3ds DNQ8Nheafeqd63wFkfE//TXYR0rYTxTxa0jTrhtuJCUZ4+anRyG00fEbHPOxvMnJ aPwQQVNOfCaUAvRbFdQ4RbuIm5chhX8Bml0ZtqvsAAFJ9XkCh1UPF0VHtSrS7PRL lRMBlamLgZqU72naaJaFY2nMp+pvMFPZrzkR7tpv0Z1bqxuJp6L2n/EmcHpmTOJy Ze+Wvt1wKk8Ep5Vql5ekXt5lEiInjacwsJZXbb5HfHO++Y+1b+ABt1kSjJx+R3/q 2Qdztq+9Eoj0N1A4gXdVFoZHqKihhbD49k8YqX4qO5ujTzqgnNyHGSEXyIKvaU6z b3b12IvjbcMhM1zm3qvFfrVbbQI3kJf66zSi9NAwsZHlsvxRzslALR8I7mila4r5 fVOyfGoZxFs44FNW9JG7I85/isAxgg0ogYraMZbk8gmhTtb1ZaN+r7kJeXuTpzOg UBAIDYPclMyZeny6tn1/qFuzNGYQQ0R9kxFcTC21Cf2zNLWHNfwCL1vE3Ob+ROIS IHcsce6IqWQKGlD8UPjkZiXTLfqCAVi51PsGTVrnidXfa1IBOuvDsVqlghPsjHSD 30N4VB++9Gbw7LFEP4e33cOZLBLjDEdYd4VuoQFYywDZ3cy6xXo= =OoZD -----END PGP SIGNATURE----- Merge 5.4.69 into android11-5.4-lts Changes in 5.4.69 kernel/sysctl-test: Add null pointer test for sysctl.c:proc_dointvec() scsi: lpfc: Fix pt2pt discovery on SLI3 HBAs scsi: mpt3sas: Free diag buffer without any status check selinux: allow labeling before policy is loaded media: mc-device.c: fix memleak in media_device_register_entity drm/amd/display: Do not double-buffer DTO adjustments drm/amdkfd: Fix race in gfx10 context restore handler dma-fence: Serialise signal enabling (dma_fence_enable_sw_signaling) scsi: qla2xxx: Add error handling for PLOGI ELS passthrough ath10k: fix array out-of-bounds access ath10k: fix memory leak for tpc_stats_final PCI/IOV: Serialize sysfs sriov_numvfs reads vs writes mm: fix double page fault on arm64 if PTE_AF is cleared scsi: aacraid: fix illegal IO beyond last LBA m68k: q40: Fix info-leak in rtc_ioctl xfs: fix inode fork extent count overflow gma/gma500: fix a memory disclosure bug due to uninitialized bytes ASoC: kirkwood: fix IRQ error handling soundwire: intel/cadence: fix startup sequence media: smiapp: Fix error handling at NVM reading drm/amd/display: Free gamma after calculating legacy transfer function xfs: properly serialise fallocate against AIO+DIO leds: mlxreg: Fix possible buffer overflow dm table: do not allow request-based DM to stack on partitions PM / devfreq: tegra30: Fix integer overflow on CPU's freq max out scsi: fnic: fix use after free scsi: lpfc: Fix kernel crash at lpfc_nvme_info_show during remote port bounce powerpc/64s: Always disable branch profiling for prom_init.o net: silence data-races on sk_backlog.tail dax: Fix alloc_dax_region() compile warning iomap: Fix overflow in iomap_page_mkwrite f2fs: avoid kernel panic on corruption test clk/ti/adpll: allocate room for terminating null drm/amdgpu/powerplay: fix AVFS handling with custom powerplay table ice: Fix to change Rx/Tx ring descriptor size via ethtool with DCBx mtd: cfi_cmdset_0002: don't free cfi->cfiq in error path of cfi_amdstd_setup() mfd: mfd-core: Protect against NULL call-back function pointer drm/amdgpu/powerplay/smu7: fix AVFS handling with custom powerplay table tpm_crb: fix fTPM on AMD Zen+ CPUs tracing: Verify if trace array exists before destroying it. tracing: Adding NULL checks for trace_array descriptor pointer bcache: fix a lost wake-up problem caused by mca_cannibalize_lock dmaengine: mediatek: hsdma_probe: fixed a memory leak when devm_request_irq fails x86/kdump: Always reserve the low 1M when the crashkernel option is specified RDMA/qedr: Fix potential use after free RDMA/i40iw: Fix potential use after free PCI: Avoid double hpmemsize MMIO window assignment fix dget_parent() fastpath race xfs: fix attr leaf header freemap.size underflow RDMA/iw_cgxb4: Fix an error handling path in 'c4iw_connect()' ubi: Fix producing anchor PEBs mmc: core: Fix size overflow for mmc partitions gfs2: clean up iopen glock mess in gfs2_create_inode scsi: pm80xx: Cleanup command when a reset times out mt76: do not use devm API for led classdev mt76: add missing locking around ampdu action debugfs: Fix !DEBUG_FS debugfs_create_automount SUNRPC: Capture completion of all RPC tasks CIFS: Use common error handling code in smb2_ioctl_query_info() CIFS: Properly process SMB3 lease breaks f2fs: stop GC when the victim becomes fully valid ASoC: max98090: remove msleep in PLL unlocked workaround xtensa: fix system_call interaction with ptrace s390: avoid misusing CALL_ON_STACK for task stack setup xfs: fix realtime file data space leak drm/amdgpu: fix calltrace during kmd unload(v3) arm64: insn: consistently handle exit text selftests/bpf: De-flake test_tcpbpf kernel/notifier.c: intercept duplicate registrations to avoid infinite loops kernel/sys.c: avoid copying possible padding bytes in copy_to_user KVM: arm/arm64: vgic: Fix potential double free dist->spis in __kvm_vgic_destroy() module: Remove accidental change of module_enable_x() xfs: fix log reservation overflows when allocating large rt extents ALSA: hda: enable regmap internal locking tipc: fix link overflow issue at socket shutdown vcc_seq_next should increase position index neigh_stat_seq_next() should increase position index rt_cpu_seq_next should increase position index ipv6_route_seq_next should increase position index drm/mcde: Handle pending vblank while disabling display seqlock: Require WRITE_ONCE surrounding raw_seqcount_barrier drm/scheduler: Avoid accessing freed bad job. media: ti-vpe: cal: Restrict DMA to avoid memory corruption opp: Replace list_kref with a local counter scsi: qla2xxx: Fix stuck session in GNL scsi: lpfc: Fix incomplete NVME discovery when target sctp: move trace_sctp_probe_path into sctp_outq_sack ACPI: EC: Reference count query handlers under lock scsi: ufs: Make ufshcd_add_command_trace() easier to read scsi: ufs: Fix a race condition in the tracing code drm/amd/display: Initialize DSC PPS variables to 0 i2c: tegra: Prevent interrupt triggering after transfer timeout btrfs: tree-checker: Check leaf chunk item size dmaengine: zynqmp_dma: fix burst length configuration s390/cpum_sf: Use kzalloc and minor changes nfsd: Fix a soft lockup race in nfsd_file_mark_find_or_create() powerpc/eeh: Only dump stack once if an MMIO loop is detected Bluetooth: btrtl: Use kvmalloc for FW allocations tracing: Set kernel_stack's caller size properly ARM: 8948/1: Prevent OOB access in stacktrace ar5523: Add USB ID of SMCWUSBT-G2 wireless adapter ceph: ensure we have a new cap before continuing in fill_inode selftests/ftrace: fix glob selftest tools/power/x86/intel_pstate_tracer: changes for python 3 compatibility Bluetooth: Fix refcount use-after-free issue mm/swapfile.c: swap_next should increase position index mm: pagewalk: fix termination condition in walk_pte_range() Bluetooth: prefetch channel before killing sock KVM: fix overflow of zero page refcount with ksm running ALSA: hda: Clear RIRB status before reading WP skbuff: fix a data race in skb_queue_len() nfsd: Fix a perf warning drm/amd/display: fix workaround for incorrect double buffer register for DLG ADL and TTU audit: CONFIG_CHANGE don't log internal bookkeeping as an event selinux: sel_avc_get_stat_idx should increase position index scsi: lpfc: Fix RQ buffer leakage when no IOCBs available scsi: lpfc: Fix release of hwq to clear the eq relationship scsi: lpfc: Fix coverity errors in fmdi attribute handling drm/omap: fix possible object reference leak locking/lockdep: Decrement IRQ context counters when removing lock chain clk: stratix10: use do_div() for 64-bit calculation crypto: chelsio - This fixes the kernel panic which occurs during a libkcapi test mt76: clear skb pointers from rx aggregation reorder buffer during cleanup mt76: fix handling full tx queues in mt76_dma_tx_queue_skb_raw ALSA: usb-audio: Don't create a mixer element with bogus volume range perf test: Fix test trace+probe_vfs_getname.sh on s390 RDMA/rxe: Fix configuration of atomic queue pair attributes KVM: x86: fix incorrect comparison in trace event KVM: nVMX: Hold KVM's srcu lock when syncing vmcs12->shadow dmaengine: stm32-mdma: use vchan_terminate_vdesc() in .terminate_all media: staging/imx: Missing assignment in imx_media_capture_device_register() x86/pkeys: Add check for pkey "overflow" bpf: Remove recursion prevention from rcu free callback dmaengine: stm32-dma: use vchan_terminate_vdesc() in .terminate_all dmaengine: tegra-apb: Prevent race conditions on channel's freeing soundwire: bus: disable pm_runtime in sdw_slave_delete drm/amd/display: dal_ddc_i2c_payloads_create can fail causing panic drm/omap: dss: Cleanup DSS ports on initialisation failure iavf: use tc_cls_can_offload_and_chain0() instead of chain check firmware: arm_sdei: Use cpus_read_lock() to avoid races with cpuhp random: fix data races at timer_rand_state bus: hisi_lpc: Fixup IO ports addresses to avoid use-after-free in host removal ASoC: SOF: ipc: check ipc return value before data copy media: go7007: Fix URB type for interrupt handling Bluetooth: guard against controllers sending zero'd events timekeeping: Prevent 32bit truncation in scale64_check_overflow() powerpc/book3s64: Fix error handling in mm_iommu_do_alloc() drm/amd/display: fix image corruption with ODM 2:1 DSC 2 slice ext4: fix a data race at inode->i_disksize perf jevents: Fix leak of mapfile memory mm: avoid data corruption on CoW fault into PFN-mapped VMA drm/amdgpu: increase atombios cmd timeout ARM: OMAP2+: Handle errors for cpu_pm drm/amd/display: Stop if retimer is not available clk: imx: Fix division by zero warning on pfdv2 cpu-topology: Fix the potential data corruption s390/irq: replace setup_irq() by request_irq() perf cs-etm: Swap packets for instruction samples perf cs-etm: Correct synthesizing instruction samples ath10k: use kzalloc to read for ath10k_sdio_hif_diag_read scsi: aacraid: Disabling TM path and only processing IOP reset Bluetooth: L2CAP: handle l2cap config request during open state media: tda10071: fix unsigned sign extension overflow tty: sifive: Finish transmission before changing the clock xfs: don't ever return a stale pointer from __xfs_dir3_free_read xfs: mark dir corrupt when lookup-by-hash fails ext4: mark block bitmap corrupted when found instead of BUGON tpm: ibmvtpm: Wait for buffer to be set before proceeding rtc: sa1100: fix possible race condition rtc: ds1374: fix possible race condition nfsd: Don't add locks to closed or closing open stateids RDMA/cm: Remove a race freeing timewait_info intel_th: Disallow multi mode on devices where it's broken KVM: PPC: Book3S HV: Treat TM-related invalid form instructions on P9 like the valid ones drm/msm: fix leaks if initialization fails drm/msm/a5xx: Always set an OPP supported hardware value tracing: Use address-of operator on section symbols thermal: rcar_thermal: Handle probe error gracefully KVM: LAPIC: Mark hrtimer for period or oneshot mode to expire in hard interrupt context perf parse-events: Fix 3 use after frees found with clang ASAN btrfs: do not init a reloc root if we aren't relocating btrfs: free the reloc_control in a consistent way r8169: improve RTL8168b FIFO overflow workaround serial: 8250_port: Don't service RX FIFO if throttled serial: 8250_omap: Fix sleeping function called from invalid context during probe serial: 8250: 8250_omap: Terminate DMA before pushing data on RX timeout perf cpumap: Fix snprintf overflow check net: axienet: Convert DMA error handler to a work queue net: axienet: Propagate failure of DMA descriptor setup cpufreq: powernv: Fix frame-size-overflow in powernv_cpufreq_work_fn tools: gpio-hammer: Avoid potential overflow in main exec: Add exec_update_mutex to replace cred_guard_mutex exec: Fix a deadlock in strace selftests/ptrace: add test cases for dead-locks kernel/kcmp.c: Use new infrastructure to fix deadlocks in execve proc: Use new infrastructure to fix deadlocks in execve proc: io_accounting: Use new infrastructure to fix deadlocks in execve perf: Use new infrastructure to fix deadlocks in execve nvme-multipath: do not reset on unknown status nvme: Fix ctrl use-after-free during sysfs deletion nvme: Fix controller creation races with teardown flow brcmfmac: Fix double freeing in the fmac usb data path xfs: prohibit fs freezing when using empty transactions RDMA/rxe: Set sys_image_guid to be aligned with HW IB devices IB/iser: Always check sig MR before putting it to the free pool scsi: hpsa: correct race condition in offload enabled SUNRPC: Fix a potential buffer overflow in 'svc_print_xprts()' svcrdma: Fix leak of transport addresses netfilter: nf_tables: silence a RCU-list warning in nft_table_lookup() PCI: Use ioremap(), not phys_to_virt() for platform ROM ubifs: ubifs_jnl_write_inode: Fix a memory leak bug ubifs: ubifs_add_orphan: Fix a memory leak bug ubifs: Fix out-of-bounds memory access caused by abnormal value of node_len ALSA: usb-audio: Fix case when USB MIDI interface has more than one extra endpoint descriptor PCI: pciehp: Fix MSI interrupt race NFS: Fix races nfs_page_group_destroy() vs nfs_destroy_unlinked_subrequests() drm/amdgpu/vcn2.0: stall DPG when WPTR/RPTR reset powerpc/perf: Implement a global lock to avoid races between trace, core and thread imc events. mm/kmemleak.c: use address-of operator on section symbols mm/filemap.c: clear page error before actual read mm/swapfile: fix data races in try_to_unuse() mm/vmscan.c: fix data races using kswapd_classzone_idx SUNRPC: Don't start a timer on an already queued rpc task nvmet-rdma: fix double free of rdma queue workqueue: Remove the warning in wq_worker_sleeping() drm/amdgpu/sriov add amdgpu_amdkfd_pre_reset in gpu reset mm/mmap.c: initialize align_offset explicitly for vm_unmapped_area ALSA: hda: Skip controller resume if not needed scsi: qedi: Fix termination timeouts in session logout serial: uartps: Wait for tx_empty in console setup btrfs: fix setting last_trans for reloc roots KVM: Remove CREATE_IRQCHIP/SET_PIT2 race perf stat: Force error in fallback on :k events bdev: Reduce time holding bd_mutex in sync in blkdev_close() drivers: char: tlclk.c: Avoid data race between init and interrupt handler KVM: arm64: vgic-v3: Retire all pending LPIs on vcpu destroy KVM: arm64: vgic-its: Fix memory leak on the error path of vgic_add_lpi() net: openvswitch: use u64 for meter bucket scsi: aacraid: Fix error handling paths in aac_probe_one() staging:r8188eu: avoid skb_clone for amsdu to msdu conversion sparc64: vcc: Fix error return code in vcc_probe() arm64: cpufeature: Relax checks for AArch32 support at EL[0-2] sched/fair: Eliminate bandwidth race between throttling and distribution dpaa2-eth: fix error return code in setup_dpni() dt-bindings: sound: wm8994: Correct required supplies based on actual implementaion devlink: Fix reporter's recovery condition atm: fix a memory leak of vcc->user_back media: venus: vdec: Init registered list unconditionally perf mem2node: Avoid double free related to realloc mm/slub: fix incorrect interpretation of s->offset i2c: tegra: Restore pinmux on system resume power: supply: max17040: Correct voltage reading phy: samsung: s5pv210-usb2: Add delay after reset Bluetooth: Handle Inquiry Cancel error after Inquiry Complete USB: EHCI: ehci-mv: fix error handling in mv_ehci_probe() KVM: x86: handle wrap around 32-bit address space tipc: fix memory leak in service subscripting tty: serial: samsung: Correct clock selection logic ALSA: hda: Fix potential race in unsol event handler drm/exynos: dsi: Remove bridge node reference in error handling path in probe function ipmi:bt-bmc: Fix error handling and status check powerpc/traps: Make unrecoverable NMIs die instead of panic svcrdma: Fix backchannel return code fuse: don't check refcount after stealing page fuse: update attr_version counter on fuse_notify_inval_inode() USB: EHCI: ehci-mv: fix less than zero comparison of an unsigned int coresight: etm4x: Fix use-after-free of per-cpu etm drvdata arm64: acpi: Make apei_claim_sea() synchronise with APEI's irq work scsi: cxlflash: Fix error return code in cxlflash_probe() arm64/cpufeature: Drop TraceFilt feature exposure from ID_DFR0 register drm/amdkfd: fix restore worker race condition e1000: Do not perform reset in reset_task if we are already down drm/nouveau/debugfs: fix runtime pm imbalance on error drm/nouveau: fix runtime pm imbalance on error drm/nouveau/dispnv50: fix runtime pm imbalance on error printk: handle blank console arguments passed in. usb: dwc3: Increase timeout for CmdAct cleared by device controller btrfs: don't force read-only after error in drop snapshot btrfs: fix double __endio_write_update_ordered in direct I/O gpio: rcar: Fix runtime PM imbalance on error vfio/pci: fix memory leaks of eventfd ctx KVM: PPC: Book3S HV: Close race with page faults around memslot flushes perf evsel: Fix 2 memory leaks perf trace: Fix the selection for architectures to generate the errno name tables perf stat: Fix duration_time value for higher intervals perf util: Fix memory leak of prefix_if_not_in perf metricgroup: Free metric_events on error perf kcore_copy: Fix module map when there are no modules loaded PCI: tegra194: Fix runtime PM imbalance on error ASoC: img-i2s-out: Fix runtime PM imbalance on error wlcore: fix runtime pm imbalance in wl1271_tx_work wlcore: fix runtime pm imbalance in wlcore_regdomain_config mtd: rawnand: gpmi: Fix runtime PM imbalance on error mtd: rawnand: omap_elm: Fix runtime PM imbalance on error PCI: tegra: Fix runtime PM imbalance on error ceph: fix potential race in ceph_check_caps mm/swap_state: fix a data race in swapin_nr_pages mm: memcontrol: fix stat-corrupting race in charge moving rapidio: avoid data race between file operation callbacks and mport_cdev_add(). mtd: parser: cmdline: Support MTD names containing one or more colons x86/speculation/mds: Mark mds_user_clear_cpu_buffers() __always_inline NFS: nfs_xdr_status should record the procedure name vfio/pci: Clear error and request eventfd ctx after releasing cifs: Fix double add page to memcg when cifs_readpages nvme: fix possible deadlock when I/O is blocked mac80211: skip mpath lookup also for control port tx scsi: libfc: Handling of extra kref scsi: libfc: Skip additional kref updating work event selftests/x86/syscall_nt: Clear weird flags after each test vfio/pci: fix racy on error and request eventfd ctx btrfs: qgroup: fix data leak caused by race between writeback and truncate perf tests: Fix test 68 zstd compression for s390 scsi: qla2xxx: Retry PLOGI on FC-NVMe PRLI failure ubi: fastmap: Free unused fastmap anchor peb during detach mt76: fix LED link time failure opp: Increase parsed_static_opps in _of_add_opp_table_v1() perf parse-events: Use strcmp() to compare the PMU name ALSA: hda: Always use jackpoll helper for jack update after resume ALSA: hda: Workaround for spurious wakeups on some Intel platforms net: openvswitch: use div_u64() for 64-by-32 divisions nvme: explicitly update mpath disk capacity on revalidation device_cgroup: Fix RCU list debugging warning ASoC: pcm3168a: ignore 0 Hz settings ASoC: wm8994: Skip setting of the WM8994_MICBIAS register for WM1811 ASoC: wm8994: Ensure the device is resumed in wm89xx_mic_detect functions ASoC: Intel: bytcr_rt5640: Add quirk for MPMAN Converter9 2-in-1 RISC-V: Take text_mutex in ftrace_init_nop() i2c: aspeed: Mask IRQ status to relevant bits s390/init: add missing __init annotations lockdep: fix order in trace_hardirqs_off_caller() EDAC/ghes: Check whether the driver is on the safe list correctly drm/amdkfd: fix a memory leak issue drm/amd/display: update nv1x stutter latencies drm/amdgpu/dc: Require primary plane to be enabled whenever the CRTC is i2c: core: Call i2c_acpi_install_space_handler() before i2c_acpi_register_devices() objtool: Fix noreturn detection for ignored functions ieee802154: fix one possible memleak in ca8210_dev_com_init ieee802154/adf7242: check status of adf7242_read_reg clocksource/drivers/h8300_timer8: Fix wrong return value in h8300_8timer_init() mwifiex: Increase AES key storage size to 256 bits batman-adv: bla: fix type misuse for backbone_gw hash indexing atm: eni: fix the missed pci_disable_device() for eni_init_one() batman-adv: mcast/TT: fix wrongly dropped or rerouted packets netfilter: conntrack: nf_conncount_init is failing with IPv6 disabled mac802154: tx: fix use-after-free bpf: Fix clobbering of r2 in bpf_gen_ld_abs drm/vc4/vc4_hdmi: fill ASoC card owner net: qed: Disable aRFS for NPAR and 100G net: qede: Disable aRFS for NPAR and 100G net: qed: RDMA personality shouldn't fail VF load drm/sun4i: sun8i-csc: Secondary CSC register correction batman-adv: Add missing include for in_interrupt() nvme-tcp: fix kconfig dependency warning when !CRYPTO batman-adv: mcast: fix duplicate mcast packets in BLA backbone from LAN batman-adv: mcast: fix duplicate mcast packets in BLA backbone from mesh batman-adv: mcast: fix duplicate mcast packets from BLA backbone to mesh bpf: Fix a rcu warning for bpffs map pretty-print lib80211: fix unmet direct dependendices config warning when !CRYPTO ALSA: asihpi: fix iounmap in error handler regmap: fix page selection for noinc reads regmap: fix page selection for noinc writes MIPS: Add the missing 'CPU_1074K' into __get_cpu_type() regulator: axp20x: fix LDO2/4 description KVM: x86: Reset MMU context if guest toggles CR4.SMAP or CR4.PKE KVM: SVM: Add a dedicated INVD intercept routine mm: validate pmd after splitting arch/x86/lib/usercopy_64.c: fix __copy_user_flushcache() cache writeback x86/ioapic: Unbreak check_timer() scsi: lpfc: Fix initial FLOGI failure due to BBSCN not supported ALSA: usb-audio: Add delay quirk for H570e USB headsets ALSA: hda/realtek - Couldn't detect Mic if booting with headset plugged ALSA: hda/realtek: Enable front panel headset LED on Lenovo ThinkStation P520 lib/string.c: implement stpcpy tracing: fix double free s390/dasd: Fix zero write for FBA devices kprobes: Fix to check probe enabled before disarm_kprobe_ftrace() kprobes: tracing/kprobes: Fix to kill kprobes on initmem after boot btrfs: fix overflow when copying corrupt csums for a message dmabuf: fix NULL pointer dereference in dma_buf_release() mm, THP, swap: fix allocating cluster for swapfile by mistake mm/gup: fix gup_fast with dynamic page table folding s390/zcrypt: Fix ZCRYPT_PERDEV_REQCNT ioctl KVM: arm64: Assume write fault on S1PTW permission fault on instruction fetch dm: fix bio splitting and its bio completion order for regular IO kprobes: Fix compiler warning for !CONFIG_KPROBES_ON_FTRACE ata: define AC_ERR_OK ata: make qc_prep return ata_completion_errors ata: sata_mv, avoid trigerrable BUG_ON Linux 5.4.69 Signed-off-by: Greg Kroah-Hartman <gregkh@google.com> Change-Id: I2a26b4f6fd89b641fa80e339ee72089da51a1415
1229 lines
30 KiB
C
1229 lines
30 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/*
|
|
* linux/init/main.c
|
|
*
|
|
* Copyright (C) 1991, 1992 Linus Torvalds
|
|
*
|
|
* GK 2/5/95 - Changed to support mounting root fs via NFS
|
|
* Added initrd & change_root: Werner Almesberger & Hans Lermen, Feb '96
|
|
* Moan early if gcc is old, avoiding bogus kernels - Paul Gortmaker, May '96
|
|
* Simplified starting of init: Michael A. Griffith <grif@acm.org>
|
|
*/
|
|
|
|
#define DEBUG /* Enable initcall_debug */
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/extable.h>
|
|
#include <linux/module.h>
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/binfmts.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/stackprotector.h>
|
|
#include <linux/string.h>
|
|
#include <linux/ctype.h>
|
|
#include <linux/delay.h>
|
|
#include <linux/ioport.h>
|
|
#include <linux/init.h>
|
|
#include <linux/initrd.h>
|
|
#include <linux/memblock.h>
|
|
#include <linux/acpi.h>
|
|
#include <linux/console.h>
|
|
#include <linux/nmi.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/kmod.h>
|
|
#include <linux/kprobes.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/start_kernel.h>
|
|
#include <linux/security.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/profile.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/moduleparam.h>
|
|
#include <linux/kallsyms.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/cpuset.h>
|
|
#include <linux/cgroup.h>
|
|
#include <linux/efi.h>
|
|
#include <linux/tick.h>
|
|
#include <linux/sched/isolation.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/taskstats_kern.h>
|
|
#include <linux/delayacct.h>
|
|
#include <linux/unistd.h>
|
|
#include <linux/utsname.h>
|
|
#include <linux/rmap.h>
|
|
#include <linux/mempolicy.h>
|
|
#include <linux/key.h>
|
|
#include <linux/buffer_head.h>
|
|
#include <linux/page_ext.h>
|
|
#include <linux/debug_locks.h>
|
|
#include <linux/debugobjects.h>
|
|
#include <linux/lockdep.h>
|
|
#include <linux/kmemleak.h>
|
|
#include <linux/pid_namespace.h>
|
|
#include <linux/device.h>
|
|
#include <linux/kthread.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/sched/init.h>
|
|
#include <linux/signal.h>
|
|
#include <linux/idr.h>
|
|
#include <linux/kgdb.h>
|
|
#include <linux/ftrace.h>
|
|
#include <linux/async.h>
|
|
#include <linux/sfi.h>
|
|
#include <linux/shmem_fs.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/perf_event.h>
|
|
#include <linux/ptrace.h>
|
|
#include <linux/pti.h>
|
|
#include <linux/blkdev.h>
|
|
#include <linux/elevator.h>
|
|
#include <linux/sched/clock.h>
|
|
#include <linux/sched/task.h>
|
|
#include <linux/sched/task_stack.h>
|
|
#include <linux/context_tracking.h>
|
|
#include <linux/random.h>
|
|
#include <linux/list.h>
|
|
#include <linux/integrity.h>
|
|
#include <linux/proc_ns.h>
|
|
#include <linux/io.h>
|
|
#include <linux/cache.h>
|
|
#include <linux/rodata_test.h>
|
|
#include <linux/jump_label.h>
|
|
#include <linux/mem_encrypt.h>
|
|
|
|
#include <asm/io.h>
|
|
#include <asm/bugs.h>
|
|
#include <asm/setup.h>
|
|
#include <asm/sections.h>
|
|
#include <asm/cacheflush.h>
|
|
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/initcall.h>
|
|
|
|
static int kernel_init(void *);
|
|
|
|
extern void init_IRQ(void);
|
|
extern void radix_tree_init(void);
|
|
|
|
/*
|
|
* Debug helper: via this flag we know that we are in 'early bootup code'
|
|
* where only the boot processor is running with IRQ disabled. This means
|
|
* two things - IRQ must not be enabled before the flag is cleared and some
|
|
* operations which are not allowed with IRQ disabled are allowed while the
|
|
* flag is set.
|
|
*/
|
|
bool early_boot_irqs_disabled __read_mostly;
|
|
|
|
enum system_states system_state __read_mostly;
|
|
EXPORT_SYMBOL(system_state);
|
|
|
|
/*
|
|
* Boot command-line arguments
|
|
*/
|
|
#define MAX_INIT_ARGS CONFIG_INIT_ENV_ARG_LIMIT
|
|
#define MAX_INIT_ENVS CONFIG_INIT_ENV_ARG_LIMIT
|
|
|
|
extern void time_init(void);
|
|
/* Default late time init is NULL. archs can override this later. */
|
|
void (*__initdata late_time_init)(void);
|
|
|
|
/* Untouched command line saved by arch-specific code. */
|
|
char __initdata boot_command_line[COMMAND_LINE_SIZE];
|
|
/* Untouched saved command line (eg. for /proc) */
|
|
char *saved_command_line;
|
|
/* Command line for parameter parsing */
|
|
static char *static_command_line;
|
|
/* Command line for per-initcall parameter parsing */
|
|
static char *initcall_command_line;
|
|
|
|
static char *execute_command;
|
|
static char *ramdisk_execute_command;
|
|
|
|
/*
|
|
* Used to generate warnings if static_key manipulation functions are used
|
|
* before jump_label_init is called.
|
|
*/
|
|
bool static_key_initialized __read_mostly;
|
|
EXPORT_SYMBOL_GPL(static_key_initialized);
|
|
|
|
/*
|
|
* If set, this is an indication to the drivers that reset the underlying
|
|
* device before going ahead with the initialization otherwise driver might
|
|
* rely on the BIOS and skip the reset operation.
|
|
*
|
|
* This is useful if kernel is booting in an unreliable environment.
|
|
* For ex. kdump situation where previous kernel has crashed, BIOS has been
|
|
* skipped and devices will be in unknown state.
|
|
*/
|
|
unsigned int reset_devices;
|
|
EXPORT_SYMBOL(reset_devices);
|
|
|
|
static int __init set_reset_devices(char *str)
|
|
{
|
|
reset_devices = 1;
|
|
return 1;
|
|
}
|
|
|
|
__setup("reset_devices", set_reset_devices);
|
|
|
|
static const char *argv_init[MAX_INIT_ARGS+2] = { "init", NULL, };
|
|
const char *envp_init[MAX_INIT_ENVS+2] = { "HOME=/", "TERM=linux", NULL, };
|
|
static const char *panic_later, *panic_param;
|
|
|
|
extern const struct obs_kernel_param __setup_start[], __setup_end[];
|
|
|
|
static bool __init obsolete_checksetup(char *line)
|
|
{
|
|
const struct obs_kernel_param *p;
|
|
bool had_early_param = false;
|
|
|
|
p = __setup_start;
|
|
do {
|
|
int n = strlen(p->str);
|
|
if (parameqn(line, p->str, n)) {
|
|
if (p->early) {
|
|
/* Already done in parse_early_param?
|
|
* (Needs exact match on param part).
|
|
* Keep iterating, as we can have early
|
|
* params and __setups of same names 8( */
|
|
if (line[n] == '\0' || line[n] == '=')
|
|
had_early_param = true;
|
|
} else if (!p->setup_func) {
|
|
pr_warn("Parameter %s is obsolete, ignored\n",
|
|
p->str);
|
|
return true;
|
|
} else if (p->setup_func(line + n))
|
|
return true;
|
|
}
|
|
p++;
|
|
} while (p < __setup_end);
|
|
|
|
return had_early_param;
|
|
}
|
|
|
|
/*
|
|
* This should be approx 2 Bo*oMips to start (note initial shift), and will
|
|
* still work even if initially too large, it will just take slightly longer
|
|
*/
|
|
unsigned long loops_per_jiffy = (1<<12);
|
|
EXPORT_SYMBOL(loops_per_jiffy);
|
|
|
|
static int __init debug_kernel(char *str)
|
|
{
|
|
console_loglevel = CONSOLE_LOGLEVEL_DEBUG;
|
|
return 0;
|
|
}
|
|
|
|
static int __init quiet_kernel(char *str)
|
|
{
|
|
console_loglevel = CONSOLE_LOGLEVEL_QUIET;
|
|
return 0;
|
|
}
|
|
|
|
early_param("debug", debug_kernel);
|
|
early_param("quiet", quiet_kernel);
|
|
|
|
static int __init loglevel(char *str)
|
|
{
|
|
int newlevel;
|
|
|
|
/*
|
|
* Only update loglevel value when a correct setting was passed,
|
|
* to prevent blind crashes (when loglevel being set to 0) that
|
|
* are quite hard to debug
|
|
*/
|
|
if (get_option(&str, &newlevel)) {
|
|
console_loglevel = newlevel;
|
|
return 0;
|
|
}
|
|
|
|
return -EINVAL;
|
|
}
|
|
|
|
early_param("loglevel", loglevel);
|
|
|
|
/* Change NUL term back to "=", to make "param" the whole string. */
|
|
static int __init repair_env_string(char *param, char *val,
|
|
const char *unused, void *arg)
|
|
{
|
|
if (val) {
|
|
/* param=val or param="val"? */
|
|
if (val == param+strlen(param)+1)
|
|
val[-1] = '=';
|
|
else if (val == param+strlen(param)+2) {
|
|
val[-2] = '=';
|
|
memmove(val-1, val, strlen(val)+1);
|
|
val--;
|
|
} else
|
|
BUG();
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* Anything after -- gets handed straight to init. */
|
|
static int __init set_init_arg(char *param, char *val,
|
|
const char *unused, void *arg)
|
|
{
|
|
unsigned int i;
|
|
|
|
if (panic_later)
|
|
return 0;
|
|
|
|
repair_env_string(param, val, unused, NULL);
|
|
|
|
for (i = 0; argv_init[i]; i++) {
|
|
if (i == MAX_INIT_ARGS) {
|
|
panic_later = "init";
|
|
panic_param = param;
|
|
return 0;
|
|
}
|
|
}
|
|
argv_init[i] = param;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Unknown boot options get handed to init, unless they look like
|
|
* unused parameters (modprobe will find them in /proc/cmdline).
|
|
*/
|
|
static int __init unknown_bootoption(char *param, char *val,
|
|
const char *unused, void *arg)
|
|
{
|
|
repair_env_string(param, val, unused, NULL);
|
|
|
|
/* Handle obsolete-style parameters */
|
|
if (obsolete_checksetup(param))
|
|
return 0;
|
|
|
|
/* Unused module parameter. */
|
|
if (strchr(param, '.') && (!val || strchr(param, '.') < val))
|
|
return 0;
|
|
|
|
if (panic_later)
|
|
return 0;
|
|
|
|
if (val) {
|
|
/* Environment option */
|
|
unsigned int i;
|
|
for (i = 0; envp_init[i]; i++) {
|
|
if (i == MAX_INIT_ENVS) {
|
|
panic_later = "env";
|
|
panic_param = param;
|
|
}
|
|
if (!strncmp(param, envp_init[i], val - param))
|
|
break;
|
|
}
|
|
envp_init[i] = param;
|
|
} else {
|
|
/* Command line option */
|
|
unsigned int i;
|
|
for (i = 0; argv_init[i]; i++) {
|
|
if (i == MAX_INIT_ARGS) {
|
|
panic_later = "init";
|
|
panic_param = param;
|
|
}
|
|
}
|
|
argv_init[i] = param;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static int __init init_setup(char *str)
|
|
{
|
|
unsigned int i;
|
|
|
|
execute_command = str;
|
|
/*
|
|
* In case LILO is going to boot us with default command line,
|
|
* it prepends "auto" before the whole cmdline which makes
|
|
* the shell think it should execute a script with such name.
|
|
* So we ignore all arguments entered _before_ init=... [MJ]
|
|
*/
|
|
for (i = 1; i < MAX_INIT_ARGS; i++)
|
|
argv_init[i] = NULL;
|
|
return 1;
|
|
}
|
|
__setup("init=", init_setup);
|
|
|
|
static int __init rdinit_setup(char *str)
|
|
{
|
|
unsigned int i;
|
|
|
|
ramdisk_execute_command = str;
|
|
/* See "auto" comment in init_setup */
|
|
for (i = 1; i < MAX_INIT_ARGS; i++)
|
|
argv_init[i] = NULL;
|
|
return 1;
|
|
}
|
|
__setup("rdinit=", rdinit_setup);
|
|
|
|
#ifndef CONFIG_SMP
|
|
static const unsigned int setup_max_cpus = NR_CPUS;
|
|
static inline void setup_nr_cpu_ids(void) { }
|
|
static inline void smp_prepare_cpus(unsigned int maxcpus) { }
|
|
#endif
|
|
|
|
/*
|
|
* We need to store the untouched command line for future reference.
|
|
* We also need to store the touched command line since the parameter
|
|
* parsing is performed in place, and we should allow a component to
|
|
* store reference of name/value for future reference.
|
|
*/
|
|
static void __init setup_command_line(char *command_line)
|
|
{
|
|
size_t len = strlen(boot_command_line) + 1;
|
|
|
|
saved_command_line = memblock_alloc(len, SMP_CACHE_BYTES);
|
|
if (!saved_command_line)
|
|
panic("%s: Failed to allocate %zu bytes\n", __func__, len);
|
|
|
|
initcall_command_line = memblock_alloc(len, SMP_CACHE_BYTES);
|
|
if (!initcall_command_line)
|
|
panic("%s: Failed to allocate %zu bytes\n", __func__, len);
|
|
|
|
static_command_line = memblock_alloc(len, SMP_CACHE_BYTES);
|
|
if (!static_command_line)
|
|
panic("%s: Failed to allocate %zu bytes\n", __func__, len);
|
|
|
|
strcpy(saved_command_line, boot_command_line);
|
|
strcpy(static_command_line, command_line);
|
|
}
|
|
|
|
/*
|
|
* We need to finalize in a non-__init function or else race conditions
|
|
* between the root thread and the init thread may cause start_kernel to
|
|
* be reaped by free_initmem before the root thread has proceeded to
|
|
* cpu_idle.
|
|
*
|
|
* gcc-3.4 accidentally inlines this function, so use noinline.
|
|
*/
|
|
|
|
static __initdata DECLARE_COMPLETION(kthreadd_done);
|
|
|
|
noinline void __ref rest_init(void)
|
|
{
|
|
struct task_struct *tsk;
|
|
int pid;
|
|
|
|
rcu_scheduler_starting();
|
|
/*
|
|
* We need to spawn init first so that it obtains pid 1, however
|
|
* the init task will end up wanting to create kthreads, which, if
|
|
* we schedule it before we create kthreadd, will OOPS.
|
|
*/
|
|
pid = kernel_thread(kernel_init, NULL, CLONE_FS);
|
|
/*
|
|
* Pin init on the boot CPU. Task migration is not properly working
|
|
* until sched_init_smp() has been run. It will set the allowed
|
|
* CPUs for init to the non isolated CPUs.
|
|
*/
|
|
rcu_read_lock();
|
|
tsk = find_task_by_pid_ns(pid, &init_pid_ns);
|
|
set_cpus_allowed_ptr(tsk, cpumask_of(smp_processor_id()));
|
|
rcu_read_unlock();
|
|
|
|
numa_default_policy();
|
|
pid = kernel_thread(kthreadd, NULL, CLONE_FS | CLONE_FILES);
|
|
rcu_read_lock();
|
|
kthreadd_task = find_task_by_pid_ns(pid, &init_pid_ns);
|
|
rcu_read_unlock();
|
|
|
|
/*
|
|
* Enable might_sleep() and smp_processor_id() checks.
|
|
* They cannot be enabled earlier because with CONFIG_PREEMPTION=y
|
|
* kernel_thread() would trigger might_sleep() splats. With
|
|
* CONFIG_PREEMPT_VOLUNTARY=y the init task might have scheduled
|
|
* already, but it's stuck on the kthreadd_done completion.
|
|
*/
|
|
system_state = SYSTEM_SCHEDULING;
|
|
|
|
complete(&kthreadd_done);
|
|
|
|
/*
|
|
* The boot idle thread must execute schedule()
|
|
* at least once to get things moving:
|
|
*/
|
|
schedule_preempt_disabled();
|
|
/* Call into cpu_idle with preempt disabled */
|
|
cpu_startup_entry(CPUHP_ONLINE);
|
|
}
|
|
|
|
/* Check for early params. */
|
|
static int __init do_early_param(char *param, char *val,
|
|
const char *unused, void *arg)
|
|
{
|
|
const struct obs_kernel_param *p;
|
|
|
|
for (p = __setup_start; p < __setup_end; p++) {
|
|
if ((p->early && parameq(param, p->str)) ||
|
|
(strcmp(param, "console") == 0 &&
|
|
strcmp(p->str, "earlycon") == 0)
|
|
) {
|
|
if (p->setup_func(val) != 0)
|
|
pr_warn("Malformed early option '%s'\n", param);
|
|
}
|
|
}
|
|
/* We accept everything at this stage. */
|
|
return 0;
|
|
}
|
|
|
|
void __init parse_early_options(char *cmdline)
|
|
{
|
|
parse_args("early options", cmdline, NULL, 0, 0, 0, NULL,
|
|
do_early_param);
|
|
}
|
|
|
|
/* Arch code calls this early on, or if not, just before other parsing. */
|
|
void __init parse_early_param(void)
|
|
{
|
|
static int done __initdata;
|
|
static char tmp_cmdline[COMMAND_LINE_SIZE] __initdata;
|
|
|
|
if (done)
|
|
return;
|
|
|
|
/* All fall through to do_early_param. */
|
|
strlcpy(tmp_cmdline, boot_command_line, COMMAND_LINE_SIZE);
|
|
parse_early_options(tmp_cmdline);
|
|
done = 1;
|
|
}
|
|
|
|
void __init __weak arch_post_acpi_subsys_init(void) { }
|
|
|
|
void __init __weak smp_setup_processor_id(void)
|
|
{
|
|
}
|
|
|
|
# if THREAD_SIZE >= PAGE_SIZE
|
|
void __init __weak thread_stack_cache_init(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
void __init __weak mem_encrypt_init(void) { }
|
|
|
|
void __init __weak poking_init(void) { }
|
|
|
|
void __init __weak pgtable_cache_init(void) { }
|
|
|
|
bool initcall_debug;
|
|
core_param(initcall_debug, initcall_debug, bool, 0644);
|
|
|
|
#ifdef TRACEPOINTS_ENABLED
|
|
static void __init initcall_debug_enable(void);
|
|
#else
|
|
static inline void initcall_debug_enable(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
/* Report memory auto-initialization states for this boot. */
|
|
static void __init report_meminit(void)
|
|
{
|
|
const char *stack;
|
|
|
|
if (IS_ENABLED(CONFIG_INIT_STACK_ALL_PATTERN))
|
|
stack = "all(pattern)";
|
|
else if (IS_ENABLED(CONFIG_INIT_STACK_ALL_ZERO))
|
|
stack = "all(zero)";
|
|
else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL))
|
|
stack = "byref_all(zero)";
|
|
else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF))
|
|
stack = "byref(zero)";
|
|
else if (IS_ENABLED(CONFIG_GCC_PLUGIN_STRUCTLEAK_USER))
|
|
stack = "__user(zero)";
|
|
else
|
|
stack = "off";
|
|
|
|
pr_info("mem auto-init: stack:%s, heap alloc:%s, heap free:%s\n",
|
|
stack, want_init_on_alloc(GFP_KERNEL) ? "on" : "off",
|
|
want_init_on_free() ? "on" : "off");
|
|
if (want_init_on_free())
|
|
pr_info("mem auto-init: clearing system memory may take some time...\n");
|
|
}
|
|
|
|
/*
|
|
* Set up kernel memory allocators
|
|
*/
|
|
static void __init mm_init(void)
|
|
{
|
|
/*
|
|
* page_ext requires contiguous pages,
|
|
* bigger than MAX_ORDER unless SPARSEMEM.
|
|
*/
|
|
page_ext_init_flatmem();
|
|
init_debug_pagealloc();
|
|
report_meminit();
|
|
mem_init();
|
|
kmem_cache_init();
|
|
kmemleak_init();
|
|
pgtable_init();
|
|
debug_objects_mem_init();
|
|
vmalloc_init();
|
|
ioremap_huge_init();
|
|
/* Should be run before the first non-init thread is created */
|
|
init_espfix_bsp();
|
|
/* Should be run after espfix64 is set up. */
|
|
pti_init();
|
|
}
|
|
|
|
void __init __weak arch_call_rest_init(void)
|
|
{
|
|
rest_init();
|
|
}
|
|
|
|
asmlinkage __visible void __init start_kernel(void)
|
|
{
|
|
char *command_line;
|
|
char *after_dashes;
|
|
|
|
set_task_stack_end_magic(&init_task);
|
|
smp_setup_processor_id();
|
|
debug_objects_early_init();
|
|
|
|
cgroup_init_early();
|
|
|
|
local_irq_disable();
|
|
early_boot_irqs_disabled = true;
|
|
|
|
/*
|
|
* Interrupts are still disabled. Do necessary setups, then
|
|
* enable them.
|
|
*/
|
|
boot_cpu_init();
|
|
page_address_init();
|
|
pr_notice("%s", linux_banner);
|
|
early_security_init();
|
|
setup_arch(&command_line);
|
|
setup_command_line(command_line);
|
|
setup_nr_cpu_ids();
|
|
setup_per_cpu_areas();
|
|
smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */
|
|
boot_cpu_hotplug_init();
|
|
|
|
build_all_zonelists(NULL);
|
|
page_alloc_init();
|
|
|
|
pr_notice("Kernel command line: %s\n", boot_command_line);
|
|
/* parameters may set static keys */
|
|
jump_label_init();
|
|
parse_early_param();
|
|
after_dashes = parse_args("Booting kernel",
|
|
static_command_line, __start___param,
|
|
__stop___param - __start___param,
|
|
-1, -1, NULL, &unknown_bootoption);
|
|
if (!IS_ERR_OR_NULL(after_dashes))
|
|
parse_args("Setting init args", after_dashes, NULL, 0, -1, -1,
|
|
NULL, set_init_arg);
|
|
|
|
/*
|
|
* These use large bootmem allocations and must precede
|
|
* kmem_cache_init()
|
|
*/
|
|
setup_log_buf(0);
|
|
vfs_caches_init_early();
|
|
sort_main_extable();
|
|
trap_init();
|
|
mm_init();
|
|
|
|
ftrace_init();
|
|
|
|
/* trace_printk can be enabled here */
|
|
early_trace_init();
|
|
|
|
/*
|
|
* Set up the scheduler prior starting any interrupts (such as the
|
|
* timer interrupt). Full topology setup happens at smp_init()
|
|
* time - but meanwhile we still have a functioning scheduler.
|
|
*/
|
|
sched_init();
|
|
/*
|
|
* Disable preemption - early bootup scheduling is extremely
|
|
* fragile until we cpu_idle() for the first time.
|
|
*/
|
|
preempt_disable();
|
|
if (WARN(!irqs_disabled(),
|
|
"Interrupts were enabled *very* early, fixing it\n"))
|
|
local_irq_disable();
|
|
radix_tree_init();
|
|
|
|
/*
|
|
* Set up housekeeping before setting up workqueues to allow the unbound
|
|
* workqueue to take non-housekeeping into account.
|
|
*/
|
|
housekeeping_init();
|
|
|
|
/*
|
|
* Allow workqueue creation and work item queueing/cancelling
|
|
* early. Work item execution depends on kthreads and starts after
|
|
* workqueue_init().
|
|
*/
|
|
workqueue_init_early();
|
|
|
|
rcu_init();
|
|
|
|
/* Trace events are available after this */
|
|
trace_init();
|
|
|
|
if (initcall_debug)
|
|
initcall_debug_enable();
|
|
|
|
context_tracking_init();
|
|
/* init some links before init_ISA_irqs() */
|
|
early_irq_init();
|
|
init_IRQ();
|
|
tick_init();
|
|
rcu_init_nohz();
|
|
init_timers();
|
|
hrtimers_init();
|
|
softirq_init();
|
|
timekeeping_init();
|
|
|
|
/*
|
|
* For best initial stack canary entropy, prepare it after:
|
|
* - setup_arch() for any UEFI RNG entropy and boot cmdline access
|
|
* - timekeeping_init() for ktime entropy used in rand_initialize()
|
|
* - rand_initialize() to get any arch-specific entropy like RDRAND
|
|
* - add_latent_entropy() to get any latent entropy
|
|
* - adding command line entropy
|
|
*/
|
|
rand_initialize();
|
|
add_latent_entropy();
|
|
add_device_randomness(command_line, strlen(command_line));
|
|
boot_init_stack_canary();
|
|
|
|
time_init();
|
|
perf_event_init();
|
|
profile_init();
|
|
call_function_init();
|
|
WARN(!irqs_disabled(), "Interrupts were enabled early\n");
|
|
|
|
early_boot_irqs_disabled = false;
|
|
local_irq_enable();
|
|
|
|
kmem_cache_init_late();
|
|
|
|
/*
|
|
* HACK ALERT! This is early. We're enabling the console before
|
|
* we've done PCI setups etc, and console_init() must be aware of
|
|
* this. But we do want output early, in case something goes wrong.
|
|
*/
|
|
console_init();
|
|
if (panic_later)
|
|
panic("Too many boot %s vars at `%s'", panic_later,
|
|
panic_param);
|
|
|
|
lockdep_init();
|
|
|
|
/*
|
|
* Need to run this when irqs are enabled, because it wants
|
|
* to self-test [hard/soft]-irqs on/off lock inversion bugs
|
|
* too:
|
|
*/
|
|
locking_selftest();
|
|
|
|
/*
|
|
* This needs to be called before any devices perform DMA
|
|
* operations that might use the SWIOTLB bounce buffers. It will
|
|
* mark the bounce buffers as decrypted so that their usage will
|
|
* not cause "plain-text" data to be decrypted when accessed.
|
|
*/
|
|
mem_encrypt_init();
|
|
|
|
#ifdef CONFIG_BLK_DEV_INITRD
|
|
if (initrd_start && !initrd_below_start_ok &&
|
|
page_to_pfn(virt_to_page((void *)initrd_start)) < min_low_pfn) {
|
|
pr_crit("initrd overwritten (0x%08lx < 0x%08lx) - disabling it.\n",
|
|
page_to_pfn(virt_to_page((void *)initrd_start)),
|
|
min_low_pfn);
|
|
initrd_start = 0;
|
|
}
|
|
#endif
|
|
setup_per_cpu_pageset();
|
|
numa_policy_init();
|
|
acpi_early_init();
|
|
if (late_time_init)
|
|
late_time_init();
|
|
sched_clock_init();
|
|
calibrate_delay();
|
|
pid_idr_init();
|
|
anon_vma_init();
|
|
#ifdef CONFIG_X86
|
|
if (efi_enabled(EFI_RUNTIME_SERVICES))
|
|
efi_enter_virtual_mode();
|
|
#endif
|
|
thread_stack_cache_init();
|
|
cred_init();
|
|
fork_init();
|
|
proc_caches_init();
|
|
uts_ns_init();
|
|
buffer_init();
|
|
key_init();
|
|
security_init();
|
|
dbg_late_init();
|
|
vfs_caches_init();
|
|
pagecache_init();
|
|
signals_init();
|
|
seq_file_init();
|
|
proc_root_init();
|
|
nsfs_init();
|
|
cpuset_init();
|
|
cgroup_init();
|
|
taskstats_init_early();
|
|
delayacct_init();
|
|
|
|
poking_init();
|
|
check_bugs();
|
|
|
|
acpi_subsystem_init();
|
|
arch_post_acpi_subsys_init();
|
|
sfi_init_late();
|
|
|
|
/* Do the rest non-__init'ed, we're now alive */
|
|
arch_call_rest_init();
|
|
|
|
prevent_tail_call_optimization();
|
|
}
|
|
|
|
/* Call all constructor functions linked into the kernel. */
|
|
static void __init do_ctors(void)
|
|
{
|
|
#ifdef CONFIG_CONSTRUCTORS
|
|
ctor_fn_t *fn = (ctor_fn_t *) __ctors_start;
|
|
|
|
for (; fn < (ctor_fn_t *) __ctors_end; fn++)
|
|
(*fn)();
|
|
#endif
|
|
}
|
|
|
|
#ifdef CONFIG_KALLSYMS
|
|
struct blacklist_entry {
|
|
struct list_head next;
|
|
char *buf;
|
|
};
|
|
|
|
static __initdata_or_module LIST_HEAD(blacklisted_initcalls);
|
|
|
|
static int __init initcall_blacklist(char *str)
|
|
{
|
|
char *str_entry;
|
|
struct blacklist_entry *entry;
|
|
|
|
/* str argument is a comma-separated list of functions */
|
|
do {
|
|
str_entry = strsep(&str, ",");
|
|
if (str_entry) {
|
|
pr_debug("blacklisting initcall %s\n", str_entry);
|
|
entry = memblock_alloc(sizeof(*entry),
|
|
SMP_CACHE_BYTES);
|
|
if (!entry)
|
|
panic("%s: Failed to allocate %zu bytes\n",
|
|
__func__, sizeof(*entry));
|
|
entry->buf = memblock_alloc(strlen(str_entry) + 1,
|
|
SMP_CACHE_BYTES);
|
|
if (!entry->buf)
|
|
panic("%s: Failed to allocate %zu bytes\n",
|
|
__func__, strlen(str_entry) + 1);
|
|
strcpy(entry->buf, str_entry);
|
|
list_add(&entry->next, &blacklisted_initcalls);
|
|
}
|
|
} while (str_entry);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static bool __init_or_module initcall_blacklisted(initcall_t fn)
|
|
{
|
|
struct blacklist_entry *entry;
|
|
char fn_name[KSYM_SYMBOL_LEN];
|
|
unsigned long addr;
|
|
|
|
if (list_empty(&blacklisted_initcalls))
|
|
return false;
|
|
|
|
addr = (unsigned long) dereference_function_descriptor(fn);
|
|
sprint_symbol_no_offset(fn_name, addr);
|
|
|
|
/*
|
|
* fn will be "function_name [module_name]" where [module_name] is not
|
|
* displayed for built-in init functions. Strip off the [module_name].
|
|
*/
|
|
strreplace(fn_name, ' ', '\0');
|
|
|
|
list_for_each_entry(entry, &blacklisted_initcalls, next) {
|
|
if (!strcmp(fn_name, entry->buf)) {
|
|
pr_debug("initcall %s blacklisted\n", fn_name);
|
|
return true;
|
|
}
|
|
}
|
|
|
|
return false;
|
|
}
|
|
#else
|
|
static int __init initcall_blacklist(char *str)
|
|
{
|
|
pr_warn("initcall_blacklist requires CONFIG_KALLSYMS\n");
|
|
return 0;
|
|
}
|
|
|
|
static bool __init_or_module initcall_blacklisted(initcall_t fn)
|
|
{
|
|
return false;
|
|
}
|
|
#endif
|
|
__setup("initcall_blacklist=", initcall_blacklist);
|
|
|
|
static __init_or_module void
|
|
trace_initcall_start_cb(void *data, initcall_t fn)
|
|
{
|
|
ktime_t *calltime = (ktime_t *)data;
|
|
|
|
printk(KERN_DEBUG "calling %pS @ %i\n", fn, task_pid_nr(current));
|
|
*calltime = ktime_get();
|
|
}
|
|
|
|
static __init_or_module void
|
|
trace_initcall_finish_cb(void *data, initcall_t fn, int ret)
|
|
{
|
|
ktime_t *calltime = (ktime_t *)data;
|
|
ktime_t delta, rettime;
|
|
unsigned long long duration;
|
|
|
|
rettime = ktime_get();
|
|
delta = ktime_sub(rettime, *calltime);
|
|
duration = (unsigned long long) ktime_to_ns(delta) >> 10;
|
|
printk(KERN_DEBUG "initcall %pS returned %d after %lld usecs\n",
|
|
fn, ret, duration);
|
|
}
|
|
|
|
static ktime_t initcall_calltime;
|
|
|
|
#ifdef TRACEPOINTS_ENABLED
|
|
static void __init initcall_debug_enable(void)
|
|
{
|
|
int ret;
|
|
|
|
ret = register_trace_initcall_start(trace_initcall_start_cb,
|
|
&initcall_calltime);
|
|
ret |= register_trace_initcall_finish(trace_initcall_finish_cb,
|
|
&initcall_calltime);
|
|
WARN(ret, "Failed to register initcall tracepoints\n");
|
|
}
|
|
# define do_trace_initcall_start trace_initcall_start
|
|
# define do_trace_initcall_finish trace_initcall_finish
|
|
#else
|
|
static inline void do_trace_initcall_start(initcall_t fn)
|
|
{
|
|
if (!initcall_debug)
|
|
return;
|
|
trace_initcall_start_cb(&initcall_calltime, fn);
|
|
}
|
|
static inline void do_trace_initcall_finish(initcall_t fn, int ret)
|
|
{
|
|
if (!initcall_debug)
|
|
return;
|
|
trace_initcall_finish_cb(&initcall_calltime, fn, ret);
|
|
}
|
|
#endif /* !TRACEPOINTS_ENABLED */
|
|
|
|
int __init_or_module do_one_initcall(initcall_t fn)
|
|
{
|
|
int count = preempt_count();
|
|
char msgbuf[64];
|
|
int ret;
|
|
|
|
if (initcall_blacklisted(fn))
|
|
return -EPERM;
|
|
|
|
do_trace_initcall_start(fn);
|
|
ret = fn();
|
|
do_trace_initcall_finish(fn, ret);
|
|
|
|
msgbuf[0] = 0;
|
|
|
|
if (preempt_count() != count) {
|
|
sprintf(msgbuf, "preemption imbalance ");
|
|
preempt_count_set(count);
|
|
}
|
|
if (irqs_disabled()) {
|
|
strlcat(msgbuf, "disabled interrupts ", sizeof(msgbuf));
|
|
local_irq_enable();
|
|
}
|
|
WARN(msgbuf[0], "initcall %pS returned with %s\n", fn, msgbuf);
|
|
|
|
add_latent_entropy();
|
|
return ret;
|
|
}
|
|
|
|
|
|
extern initcall_entry_t __initcall_start[];
|
|
extern initcall_entry_t __initcall0_start[];
|
|
extern initcall_entry_t __initcall1_start[];
|
|
extern initcall_entry_t __initcall2_start[];
|
|
extern initcall_entry_t __initcall3_start[];
|
|
extern initcall_entry_t __initcall4_start[];
|
|
extern initcall_entry_t __initcall5_start[];
|
|
extern initcall_entry_t __initcall6_start[];
|
|
extern initcall_entry_t __initcall7_start[];
|
|
extern initcall_entry_t __initcall_end[];
|
|
|
|
static initcall_entry_t *initcall_levels[] __initdata = {
|
|
__initcall0_start,
|
|
__initcall1_start,
|
|
__initcall2_start,
|
|
__initcall3_start,
|
|
__initcall4_start,
|
|
__initcall5_start,
|
|
__initcall6_start,
|
|
__initcall7_start,
|
|
__initcall_end,
|
|
};
|
|
|
|
/* Keep these in sync with initcalls in include/linux/init.h */
|
|
static const char *initcall_level_names[] __initdata = {
|
|
"pure",
|
|
"core",
|
|
"postcore",
|
|
"arch",
|
|
"subsys",
|
|
"fs",
|
|
"device",
|
|
"late",
|
|
};
|
|
|
|
static void __init do_initcall_level(int level)
|
|
{
|
|
initcall_entry_t *fn;
|
|
|
|
strcpy(initcall_command_line, saved_command_line);
|
|
parse_args(initcall_level_names[level],
|
|
initcall_command_line, __start___param,
|
|
__stop___param - __start___param,
|
|
level, level,
|
|
NULL, &repair_env_string);
|
|
|
|
trace_initcall_level(initcall_level_names[level]);
|
|
for (fn = initcall_levels[level]; fn < initcall_levels[level+1]; fn++)
|
|
do_one_initcall(initcall_from_entry(fn));
|
|
}
|
|
|
|
static void __init do_initcalls(void)
|
|
{
|
|
int level;
|
|
|
|
for (level = 0; level < ARRAY_SIZE(initcall_levels) - 1; level++)
|
|
do_initcall_level(level);
|
|
}
|
|
|
|
/*
|
|
* Ok, the machine is now initialized. None of the devices
|
|
* have been touched yet, but the CPU subsystem is up and
|
|
* running, and memory and process management works.
|
|
*
|
|
* Now we can finally start doing some real work..
|
|
*/
|
|
static void __init do_basic_setup(void)
|
|
{
|
|
cpuset_init_smp();
|
|
driver_init();
|
|
init_irq_proc();
|
|
do_ctors();
|
|
usermodehelper_enable();
|
|
do_initcalls();
|
|
}
|
|
|
|
static void __init do_pre_smp_initcalls(void)
|
|
{
|
|
initcall_entry_t *fn;
|
|
|
|
trace_initcall_level("early");
|
|
for (fn = __initcall_start; fn < __initcall0_start; fn++)
|
|
do_one_initcall(initcall_from_entry(fn));
|
|
}
|
|
|
|
static int run_init_process(const char *init_filename)
|
|
{
|
|
argv_init[0] = init_filename;
|
|
pr_info("Run %s as init process\n", init_filename);
|
|
return do_execve(getname_kernel(init_filename),
|
|
(const char __user *const __user *)argv_init,
|
|
(const char __user *const __user *)envp_init);
|
|
}
|
|
|
|
static int try_to_run_init_process(const char *init_filename)
|
|
{
|
|
int ret;
|
|
|
|
ret = run_init_process(init_filename);
|
|
|
|
if (ret && ret != -ENOENT) {
|
|
pr_err("Starting init: %s exists but couldn't execute it (error %d)\n",
|
|
init_filename, ret);
|
|
}
|
|
|
|
return ret;
|
|
}
|
|
|
|
static noinline void __init kernel_init_freeable(void);
|
|
|
|
#if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX)
|
|
bool rodata_enabled __ro_after_init = true;
|
|
static int __init set_debug_rodata(char *str)
|
|
{
|
|
return strtobool(str, &rodata_enabled);
|
|
}
|
|
__setup("rodata=", set_debug_rodata);
|
|
#endif
|
|
|
|
#ifdef CONFIG_STRICT_KERNEL_RWX
|
|
static void mark_readonly(void)
|
|
{
|
|
if (rodata_enabled) {
|
|
/*
|
|
* load_module() results in W+X mappings, which are cleaned
|
|
* up with call_rcu(). Let's make sure that queued work is
|
|
* flushed so that we don't hit false positives looking for
|
|
* insecure pages which are W+X.
|
|
*/
|
|
rcu_barrier();
|
|
mark_rodata_ro();
|
|
rodata_test();
|
|
} else
|
|
pr_info("Kernel memory protection disabled.\n");
|
|
}
|
|
#else
|
|
static inline void mark_readonly(void)
|
|
{
|
|
pr_warn("This architecture does not have kernel memory protection.\n");
|
|
}
|
|
#endif
|
|
|
|
void __weak free_initmem(void)
|
|
{
|
|
free_initmem_default(POISON_FREE_INITMEM);
|
|
}
|
|
|
|
static int __ref kernel_init(void *unused)
|
|
{
|
|
int ret;
|
|
|
|
kernel_init_freeable();
|
|
/* need to finish all async __init code before freeing the memory */
|
|
async_synchronize_full();
|
|
kprobe_free_init_mem();
|
|
ftrace_free_init_mem();
|
|
free_initmem();
|
|
mark_readonly();
|
|
|
|
/*
|
|
* Kernel mappings are now finalized - update the userspace page-table
|
|
* to finalize PTI.
|
|
*/
|
|
pti_finalize();
|
|
|
|
system_state = SYSTEM_RUNNING;
|
|
numa_default_policy();
|
|
|
|
rcu_end_inkernel_boot();
|
|
|
|
if (ramdisk_execute_command) {
|
|
ret = run_init_process(ramdisk_execute_command);
|
|
if (!ret)
|
|
return 0;
|
|
pr_err("Failed to execute %s (error %d)\n",
|
|
ramdisk_execute_command, ret);
|
|
}
|
|
|
|
/*
|
|
* We try each of these until one succeeds.
|
|
*
|
|
* The Bourne shell can be used instead of init if we are
|
|
* trying to recover a really broken machine.
|
|
*/
|
|
if (execute_command) {
|
|
ret = run_init_process(execute_command);
|
|
if (!ret)
|
|
return 0;
|
|
panic("Requested init %s failed (error %d).",
|
|
execute_command, ret);
|
|
}
|
|
if (!try_to_run_init_process("/sbin/init") ||
|
|
!try_to_run_init_process("/etc/init") ||
|
|
!try_to_run_init_process("/bin/init") ||
|
|
!try_to_run_init_process("/bin/sh"))
|
|
return 0;
|
|
|
|
panic("No working init found. Try passing init= option to kernel. "
|
|
"See Linux Documentation/admin-guide/init.rst for guidance.");
|
|
}
|
|
|
|
static noinline void __init kernel_init_freeable(void)
|
|
{
|
|
/*
|
|
* Wait until kthreadd is all set-up.
|
|
*/
|
|
wait_for_completion(&kthreadd_done);
|
|
|
|
/* Now the scheduler is fully set up and can do blocking allocations */
|
|
gfp_allowed_mask = __GFP_BITS_MASK;
|
|
|
|
/*
|
|
* init can allocate pages on any node
|
|
*/
|
|
set_mems_allowed(node_states[N_MEMORY]);
|
|
|
|
cad_pid = task_pid(current);
|
|
|
|
smp_prepare_cpus(setup_max_cpus);
|
|
|
|
workqueue_init();
|
|
|
|
init_mm_internals();
|
|
|
|
do_pre_smp_initcalls();
|
|
lockup_detector_init();
|
|
|
|
smp_init();
|
|
sched_init_smp();
|
|
|
|
page_alloc_init_late();
|
|
/* Initialize page ext after all struct pages are initialized. */
|
|
page_ext_init();
|
|
|
|
do_basic_setup();
|
|
|
|
/* Open the /dev/console on the rootfs, this should never fail */
|
|
if (ksys_open((const char __user *) "/dev/console", O_RDWR, 0) < 0)
|
|
pr_err("Warning: unable to open an initial console.\n");
|
|
|
|
(void) ksys_dup(0);
|
|
(void) ksys_dup(0);
|
|
/*
|
|
* check if there is an early userspace init. If yes, let it do all
|
|
* the work
|
|
*/
|
|
|
|
if (!ramdisk_execute_command)
|
|
ramdisk_execute_command = "/init";
|
|
|
|
if (ksys_access((const char __user *)
|
|
ramdisk_execute_command, 0) != 0) {
|
|
ramdisk_execute_command = NULL;
|
|
prepare_namespace();
|
|
}
|
|
|
|
/*
|
|
* Ok, we have completed the initial bootup, and
|
|
* we're essentially up and running. Get rid of the
|
|
* initmem segments and start the user-mode stuff..
|
|
*
|
|
* rootfs is available now, try loading the public keys
|
|
* and default modules
|
|
*/
|
|
|
|
integrity_load_keys();
|
|
}
|