android_kernel_xiaomi_sm8350/kernel/fork.c
Michael Bestas ffe9ce5b43
Merge tag 'ASB-2023-12-05_11-5.4' of https://android.googlesource.com/kernel/common into android13-5.4-lahaina
https://source.android.com/docs/security/bulletin/2023-12-01

* tag 'ASB-2023-12-05_11-5.4' of https://android.googlesource.com/kernel/common:
  ANDROID: ABI: Update allowed list for QCOM
  BACKPORT: ALSA: compress: Allow pause and resume during draining
  UPSTREAM: netfilter: nf_tables: pass context to nft_set_destroy()
  UPSTREAM: netfilter: nf_tables: don't skip expired elements during walk
  ANDROID: GKI: db845c: Update symbols list and ABI on rpmsg_register_device_override
  ANDROID: Use GKI Dr. No OWNERS file
  ANDROID: Remove android/OWNERs file
  FROMGIT: Input: uinput - allow injecting event times
  ANDROID: fix up rpmsg_device ABI break
  ANDROID: fix up platform_device ABI break
  UPSTREAM: rpmsg: Fix possible refcount leak in rpmsg_register_device_override()
  UPSTREAM: rpmsg: glink: Release driver_override
  BACKPORT: rpmsg: Fix calling device_lock() on non-initialized device
  BACKPORT: rpmsg: Fix kfree() of static memory on setting driver_override
  UPSTREAM: rpmsg: Constify local variable in field store macro
  UPSTREAM: driver: platform: Add helper for safer setting of driver_override
  BACKPORT: firmware_loader: Abort all upcoming firmware load request once reboot triggered
  UPSTREAM: firmware_loader: Refactor kill_pending_fw_fallback_reqs()
  Revert "perf: Disallow mis-matched inherited group reads"
  Revert "xfrm: fix a data-race in xfrm_gen_index()"
  Revert "Bluetooth: hci_core: Fix build warnings"
  Revert "xfrm: interface: use DEV_STATS_INC()"
  Revert "netfilter: conntrack: allow sctp hearbeat after connection re-use"
  Revert "netfilter: conntrack: don't refresh sctp entries in closed state"
  Revert "netfilter: handle the connecting collision properly in nf_conntrack_proto_sctp"
  Reapply "netfilter: conntrack: don't refresh sctp entries in closed state"
  Reapply "netfilter: conntrack: allow sctp hearbeat after connection re-use"
  Linux 5.4.259
  xfrm6: fix inet6_dev refcount underflow problem
  Bluetooth: hci_sock: Correctly bounds check and pad HCI_MON_NEW_INDEX name
  Bluetooth: hci_sock: fix slab oob read in create_monitor_event
  phy: mapphone-mdm6600: Fix pinctrl_pm handling for sleep pins
  phy: mapphone-mdm6600: Fix runtime PM for remove
  phy: mapphone-mdm6600: Fix runtime disable on probe
  ASoC: pxa: fix a memory leak in probe()
  gpio: vf610: set value before the direction to avoid a glitch
  s390/pci: fix iommu bitmap allocation
  perf: Disallow mis-matched inherited group reads
  USB: serial: option: add Fibocom to DELL custom modem FM101R-GL
  USB: serial: option: add entry for Sierra EM9191 with new firmware
  USB: serial: option: add Telit LE910C4-WWX 0x1035 composition
  ACPI: irq: Fix incorrect return value in acpi_register_gsi()
  Revert "pinctrl: avoid unsafe code pattern in find_pinctrl()"
  mmc: core: Capture correct oemid-bits for eMMC cards
  mmc: core: sdio: hold retuning if sdio in 1-bit mode
  mtd: physmap-core: Restore map_rom fallback
  mtd: spinand: micron: correct bitmask for ecc status
  mtd: rawnand: qcom: Unmap the right resource upon probe failure
  Bluetooth: hci_event: Fix using memcmp when comparing keys
  HID: multitouch: Add required quirk for Synaptics 0xcd7e device
  btrfs: fix some -Wmaybe-uninitialized warnings in ioctl.c
  drm: panel-orientation-quirks: Add quirk for One Mix 2S
  sky2: Make sure there is at least one frag_addr available
  regulator/core: Revert "fix kobject release warning and memory leak in regulator_register()"
  wifi: cfg80211: avoid leaking stack data into trace
  wifi: mac80211: allow transmitting EAPOL frames with tainted key
  Bluetooth: hci_core: Fix build warnings
  Bluetooth: Avoid redundant authentication
  HID: holtek: fix slab-out-of-bounds Write in holtek_kbd_input_event
  tracing: relax trace_event_eval_update() execution with cond_resched()
  ata: libata-eh: Fix compilation warning in ata_eh_link_report()
  gpio: timberdale: Fix potential deadlock on &tgpio->lock
  overlayfs: set ctime when setting mtime and atime
  i2c: mux: Avoid potential false error message in i2c_mux_add_adapter
  btrfs: initialize start_slot in btrfs_log_prealloc_extents
  btrfs: return -EUCLEAN for delayed tree ref with a ref count not equals to 1
  ARM: dts: ti: omap: Fix noisy serial with overrun-throttle-ms for mapphone
  ACPI: resource: Skip IRQ override on ASUS ExpertBook B1402CBA
  ACPI: resource: Skip IRQ override on ASUS ExpertBook B1502CBA
  ACPI: resource: Skip IRQ override on Asus Expertbook B2402CBA
  ACPI: resource: Add Asus ExpertBook B2502 to Asus quirks
  ACPI: resource: Skip IRQ override on Asus Vivobook S5602ZA
  ACPI: resource: Add ASUS model S5402ZA to quirks
  ACPI: resource: Skip IRQ override on Asus Vivobook K3402ZA/K3502ZA
  ACPI: resources: Add DMI-based legacy IRQ override quirk
  ACPI: Drop acpi_dev_irqresource_disabled()
  resource: Add irqresource_disabled()
  net: pktgen: Fix interface flags printing
  netfilter: nft_set_rbtree: .deactivate fails if element has expired
  neighbor: tracing: Move pin6 inside CONFIG_IPV6=y section
  net/sched: sch_hfsc: upgrade 'rt' to 'sc' when it becomes a inner curve
  i40e: prevent crash on probe if hw registers have invalid values
  net: usb: smsc95xx: Fix an error code in smsc95xx_reset()
  ipv4: fib: annotate races around nh->nh_saddr_genid and nh->nh_saddr
  tun: prevent negative ifindex
  tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a single skb
  tcp: fix excessive TLP and RACK timeouts from HZ rounding
  net: rfkill: gpio: prevent value glitch during probe
  net: ipv6: fix return value check in esp_remove_trailer
  net: ipv4: fix return value check in esp_remove_trailer
  xfrm: interface: use DEV_STATS_INC()
  xfrm: fix a data-race in xfrm_gen_index()
  qed: fix LL2 RX buffer allocation
  netfilter: nft_payload: fix wrong mac header matching
  KVM: x86: Mask LVTPC when handling a PMI
  regmap: fix NULL deref on lookup
  nfc: nci: fix possible NULL pointer dereference in send_acknowledge()
  ice: fix over-shifted variable
  Bluetooth: avoid memcmp() out of bounds warning
  Bluetooth: hci_event: Fix coding style
  Bluetooth: vhci: Fix race when opening vhci device
  Bluetooth: Fix a refcnt underflow problem for hci_conn
  Bluetooth: Reject connection with the device which has same BD_ADDR
  Bluetooth: hci_event: Ignore NULL link key
  usb: hub: Guard against accesses to uninitialized BOS descriptors
  Documentation: sysctl: align cells in second content column
  dev_forward_skb: do not scrub skb mark within the same name space
  ravb: Fix use-after-free issue in ravb_tx_timeout_work()
  powerpc/64e: Fix wrong test in __ptep_test_and_clear_young()
  powerpc/8xx: Fix pte_access_permitted() for PAGE_NONE
  dmaengine: mediatek: Fix deadlock caused by synchronize_irq()
  x86/cpu: Fix AMD erratum #1485 on Zen4-based CPUs
  usb: gadget: ncm: Handle decoding of multiple NTB's in unwrap call
  usb: gadget: udc-xilinx: replace memcpy with memcpy_toio
  pinctrl: avoid unsafe code pattern in find_pinctrl()
  cgroup: Remove duplicates in cgroup v1 tasks file
  Input: xpad - add PXN V900 support
  Input: psmouse - fix fast_reconnect function for PS/2 mode
  Input: powermate - fix use-after-free in powermate_config_complete
  ceph: fix incorrect revoked caps assert in ceph_fill_file_size()
  libceph: use kernel_connect()
  mcb: remove is_added flag from mcb_device struct
  iio: pressure: ms5611: ms5611_prom_is_valid false negative bug
  iio: pressure: dps310: Adjust Timeout Settings
  iio: pressure: bmp280: Fix NULL pointer exception
  usb: musb: Modify the "HWVers" register address
  usb: musb: Get the musb_qh poniter after musb_giveback
  usb: dwc3: Soft reset phy on probe for host
  net: usb: dm9601: fix uninitialized variable use in dm9601_mdio_read
  usb: xhci: xhci-ring: Use sysdev for mapping bounce buffer
  dmaengine: stm32-mdma: abort resume if no ongoing transfer
  workqueue: Override implicit ordered attribute in workqueue_apply_unbound_cpumask()
  nfc: nci: assert requested protocol is valid
  net: nfc: fix races in nfc_llcp_sock_get() and nfc_llcp_sock_get_sn()
  ixgbe: fix crash with empty VF macvlan list
  drm/vmwgfx: fix typo of sizeof argument
  xen-netback: use default TX queue size for vifs
  mlxsw: fix mlxsw_sp2_nve_vxlan_learning_set() return type
  ieee802154: ca8210: Fix a potential UAF in ca8210_probe
  ravb: Fix up dma_free_coherent() call in ravb_remove()
  drm/msm/dsi: skip the wait for video mode done if not applicable
  drm: etvnaviv: fix bad backport leading to warning
  net: prevent address rewrite in kernel_bind()
  quota: Fix slow quotaoff
  HID: logitech-hidpp: Fix kernel crash on receiver USB disconnect
  pwm: hibvt: Explicitly set .polarity in .get_state()
  lib/test_meminit: fix off-by-one error in test_pages()
  RDMA/cxgb4: Check skb value for failure to allocate
  Reapply "ANDROID: Revert "tracing/ring-buffer: Have polling block on watermark""
  Revert "ring-buffer: Update "shortest_full" in polling"
  Revert "ANDROID: Revert "tracing/ring-buffer: Have polling block on watermark""
  Revert "net: bridge: use DEV_STATS_INC()"
  FROMLIST: lib/test_meminit: fix off-by-one error in test_pages()
  Linux 5.4.258
  xen/events: replace evtchn_rwlock with RCU
  ima: rework CONFIG_IMA dependency block
  NFS: Fix a race in __nfs_list_for_each_server()
  parisc: Restore __ldcw_align for PA-RISC 2.0 processors
  RDMA/mlx5: Fix NULL string error
  RDMA/siw: Fix connection failure handling
  RDMA/uverbs: Fix typo of sizeof argument
  RDMA/cma: Fix truncation compilation warning in make_cma_ports
  gpio: pxa: disable pinctrl calls for MMP_GPIO
  gpio: aspeed: fix the GPIO number passed to pinctrl_gpio_set_config()
  IB/mlx4: Fix the size of a buffer in add_port_entries()
  RDMA/core: Require admin capabilities to set system parameters
  cpupower: add Makefile dependencies for install targets
  sctp: update hb timer immediately after users change hb_interval
  sctp: update transport state when processing a dupcook packet
  tcp: fix delayed ACKs for MSS boundary condition
  tcp: fix quick-ack counting to count actual ACKs of new data
  net: stmmac: dwmac-stm32: fix resume on STM32 MCU
  netfilter: handle the connecting collision properly in nf_conntrack_proto_sctp
  net: nfc: llcp: Add lock when modifying device list
  net: usb: smsc75xx: Fix uninit-value access in __smsc75xx_read_reg
  net: dsa: mv88e6xxx: Avoid EEPROM timeout when EEPROM is absent
  ipv4, ipv6: Fix handling of transhdrlen in __ip{,6}_append_data()
  net: fix possible store tearing in neigh_periodic_work()
  modpost: add missing else to the "of" check
  NFSv4: Fix a nfs4_state_manager() race
  NFS: Add a helper nfs_client_for_each_server()
  NFS4: Trace state recovery operation
  wifi: mt76: mt76x02: fix MT76x0 external LNA gain handling
  wifi: mwifiex: Fix tlv_buf_left calculation
  scsi: target: core: Fix deadlock due to recursive locking
  drivers/net: process the result of hdlc_open() and add call of hdlc_close() in uhdlc_close()
  qed/red_ll2: Fix undefined behavior bug in struct qed_ll2_info
  ima: Finish deprecation of IMA_TRUSTED_KEYRING Kconfig
  wifi: mwifiex: Fix oob check condition in mwifiex_process_rx_packet
  regmap: rbtree: Fix wrong register marked as in-cache when creating new node
  wifi: iwlwifi: dbg_ini: fix structure packing
  ubi: Refuse attaching if mtd's erasesize is 0
  net: prevent rewrite of msg_name in sock_sendmsg()
  net: replace calls to sock->ops->connect() with kernel_connect()
  fs: binfmt_elf_efpic: fix personality for ELF-FDPIC
  scsi: zfcp: Fix a double put in zfcp_port_enqueue()
  ata: libata-sata: increase PMP SRST timeout to 10s
  Revert "PCI: qcom: Disable write access to read only registers for IP v2.3.3"
  ata: libata-core: Do not register PM operations for SAS ports
  rbd: take header_rwsem in rbd_dev_refresh() only when updating
  ata: libata-core: Fix port and device removal
  rbd: decouple parent info read-in from updating rbd_dev
  ata: libata-core: Fix ata_port_request_pm() locking
  rbd: decouple header read-in from updating rbd_dev->header
  rbd: move rbd_dev_refresh() definition
  ring-buffer: Update "shortest_full" in polling
  i2c: i801: unregister tco_pdev in i801_probe() error path
  net: thunderbolt: Fix TCPv6 GSO checksum calculation
  ata: libata-scsi: ignore reserved bits for REPORT SUPPORTED OPERATION CODES
  btrfs: properly report 0 avail for very full file systems
  ALSA: hda: Disable power save for solving pop issue on Lenovo ThinkCentre M70q
  nilfs2: fix potential use after free in nilfs_gccache_submit_read_data()
  serial: 8250_port: Check IRQ data before use
  Smack:- Use overlay inode label in smack_inode_copy_up()
  smack: Retrieve transmuting information in smack_inode_getsecurity()
  smack: Record transmuting in smk_transmuted
  i40e: fix return of uninitialized aq_ret in i40e_set_vsi_promisc
  i40e: always propagate error value in i40e_set_vsi_promisc()
  ring-buffer: Avoid softlockup in ring_buffer_resize()
  selftests/ftrace: Correctly enable event in instance-event.tc
  i40e: improve locking of mac_filter_hash
  watchdog: iTCO_wdt: Set NO_REBOOT if the watchdog is not already running
  watchdog: iTCO_wdt: No need to stop the timer in probe
  nvme-pci: do not set the NUMA node of device if it has none
  fbdev/sh7760fb: Depend on FB=y
  ncsi: Propagate carrier gain/loss events to the NCSI controller
  powerpc/watchpoints: Annotate atomic context in more places
  bpf: Clarify error expectations from bpf_clone_redirect
  spi: nxp-fspi: reset the FLSHxCR1 registers
  ata: libata-eh: do not clear ATA_PFLAG_EH_PENDING in ata_eh_reset()
  parisc: irq: Make irq_stack_union static to avoid sparse warning
  parisc: drivers: Fix sparse warning
  parisc: iosapic.c: Fix sparse warnings
  parisc: sba: Fix compile warning wrt list of SBA devices
  gpio: pmic-eic-sprd: Add can_sleep flag for PMIC EIC chip
  xtensa: boot/lib: fix function prototypes
  xtensa: boot: don't add include-dirs
  xtensa: iss/network: make functions static
  xtensa: add default definition for XCHAL_HAVE_DIV32
  bus: ti-sysc: Fix SYSC_QUIRK_SWSUP_SIDLE_ACT handling for uart wake-up
  ARM: dts: ti: omap: motorola-mapphone: Fix abe_clkctrl warning on boot
  clk: tegra: fix error return case for recalc_rate
  scsi: qla2xxx: Fix deletion race condition
  MIPS: Alchemy: only build mmc support helpers if au1xmmc is enabled
  scsi: qla2xxx: Fix update_fcport for current_topology
  ata: libata: disallow dev-initiated LPM transitions to unsupported states
  Input: i8042 - add quirk for TUXEDO Gemini 17 Gen1/Clevo PD70PN
  drm/amd/display: prevent potential division by zero errors
  i2c: mux: demux-pinctrl: check the return value of devm_kstrdup()
  drm/amd/display: Fix LFC multiplier changing erratically
  gpio: tb10x: Fix an error handling path in tb10x_gpio_probe()
  drm/amd/display: Reinstate LFC optimization
  netfilter: ipset: Fix race between IPSET_CMD_CREATE and IPSET_CMD_SWAP
  net: rds: Fix possible NULL-pointer dereference
  team: fix null-ptr-deref when team device type is changed
  net: bridge: use DEV_STATS_INC()
  net: hns3: add 5ms delay before clear firmware reset irq source
  dccp: fix dccp_v4_err()/dccp_v6_err() again
  powerpc/perf/hv-24x7: Update domain value check
  ipv4: fix null-deref in ipv4_link_failure
  i40e: Fix VF VLAN offloading when port VLAN is configured
  i40e: Fix warning message and call stack during rmmod i40e driver
  i40e: Remove scheduling while atomic possibility
  i40e: Fix for persistent lldp support
  ASoC: imx-audmix: Fix return error with devm_clk_get()
  selftests: tls: swap the TX and RX sockets in some tests
  ASoC: meson: spdifin: start hw on dai probe
  selftests/tls: Add {} to avoid static checker warning
  ext4: do not let fstrim block system suspend
  bpf: Avoid deadlock when using queue and stack maps from NMI
  ext4: move setting of trimmed bit into ext4_try_to_trim_range()
  netfilter: nf_tables: disallow element removal on anonymous sets
  ext4: replace the traditional ternary conditional operator with with max()/min()
  ext4: mark group as trimmed only if it was fully scanned
  ext4: change s_last_trim_minblks type to unsigned long
  ext4: scope ret locally in ext4_try_to_trim_range()
  ext4: add new helper interface ext4_try_to_trim_range()
  ext4: remove the 'group' parameter of ext4_trim_extent
  ata: libahci: clear pending interrupt status
  tracing: Increase trace array ref count on enable and filter files
  SUNRPC: Mark the cred for revalidation if the server rejects it
  NFS/pNFS: Report EINVAL errors from connect() to the server
  Revert "drm/panel: simple: Add missing connector type and pixel format for AUO T215HVN01"
  Revert "usb: typec: bus: verify partner exists in typec_altmode_attention"
  Revert "fs/nls: make load_nls() take a const parameter"
  Revert "ip_tunnels: use DEV_STATS_INC()"
  Linux 5.4.257
  net/sched: Retire rsvp classifier
  drm/amdgpu: fix amdgpu_cs_p1_user_fence
  mtd: rawnand: brcmnand: Fix ECC level field setting for v7.2 controller
  ext4: fix rec_len verify error
  scsi: megaraid_sas: Fix deadlock on firmware crashdump
  i2c: aspeed: Reset the i2c controller when timeout occurs
  tracefs: Add missing lockdown check to tracefs_create_dir()
  nfsd: fix change_info in NFSv4 RENAME replies
  tracing: Have option files inc the trace array ref count
  tracing: Have current_trace inc the trace array ref count
  btrfs: fix lockdep splat and potential deadlock after failure running delayed items
  attr: block mode changes of symlinks
  md/raid1: fix error: ISO C90 forbids mixed declarations
  selftests: tracing: Fix to unmount tracefs for recovering environment
  btrfs: compare the correct fsid/metadata_uuid in btrfs_validate_super
  btrfs: add a helper to read the superblock metadata_uuid
  btrfs: move btrfs_pinned_by_swapfile prototype into volumes.h
  perf tools: Add an option to build without libbfd
  perf jevents: Make build dependency on test JSONs
  tools features: Add feature test to check if libbfd has buildid support
  kobject: Add sanity check for kset->kobj.ktype in kset_register()
  media: pci: ipu3-cio2: Initialise timing struct to avoid a compiler warning
  serial: cpm_uart: Avoid suspicious locking
  scsi: target: iscsi: Fix buffer overflow in lio_target_nacl_info_show()
  usb: gadget: fsl_qe_udc: validate endpoint index for ch9 udc
  media: pci: cx23885: replace BUG with error return
  media: tuners: qt1010: replace BUG_ON with a regular error
  media: az6007: Fix null-ptr-deref in az6007_i2c_xfer()
  media: anysee: fix null-ptr-deref in anysee_master_xfer
  media: af9005: Fix null-ptr-deref in af9005_i2c_xfer
  media: dw2102: Fix null-ptr-deref in dw2102_i2c_transfer()
  media: dvb-usb-v2: af9035: Fix null-ptr-deref in af9035_i2c_master_xfer
  powerpc/pseries: fix possible memory leak in ibmebus_bus_init()
  jfs: fix invalid free of JFS_IP(ipimap)->i_imap in diUnmount
  fs/jfs: prevent double-free in dbUnmount() after failed jfs_remount()
  ext2: fix datatype of block number in ext2_xattr_set2()
  md: raid1: fix potential OOB in raid1_remove_disk()
  bus: ti-sysc: Configure uart quirks for k3 SoC
  drm/exynos: fix a possible null-pointer dereference due to data race in exynos_drm_crtc_atomic_disable()
  wifi: mac80211_hwsim: drop short frames
  alx: fix OOB-read compiler warning
  mmc: sdhci-esdhc-imx: improve ESDHC_FLAG_ERR010450
  tpm_tis: Resend command to recover from data transfer errors
  crypto: lib/mpi - avoid null pointer deref in mpi_cmp_ui()
  wifi: mwifiex: fix fortify warning
  wifi: ath9k: fix printk specifier
  devlink: remove reload failed checks in params get/set callbacks
  hw_breakpoint: fix single-stepping when using bpf_overflow_handler
  perf/smmuv3: Enable HiSilicon Erratum 162001900 quirk for HIP08/09
  ACPI: video: Add backlight=native DMI quirk for Lenovo Ideapad Z470
  kernel/fork: beware of __put_task_struct() calling context
  ACPICA: Add AML_NO_OPERAND_RESOLVE flag to Timer
  locks: fix KASAN: use-after-free in trace_event_raw_event_filelock_lock
  btrfs: output extra debug info if we failed to find an inline backref
  autofs: fix memory leak of waitqueues in autofs_catatonic_mode
  parisc: Drop loops_per_jiffy from per_cpu struct
  drm/amd/display: Fix a bug when searching for insert_above_mpcc
  kcm: Fix error handling for SOCK_DGRAM in kcm_sendmsg().
  ixgbe: fix timestamp configuration code
  net/tls: do not free tls_rec on async operation in bpf_exec_tx_verdict()
  platform/mellanox: mlxbf-tmfifo: Drop jumbo frames
  mlxbf-tmfifo: sparse tags for config access
  platform/mellanox: mlxbf-tmfifo: Drop the Rx packet if no more descriptors
  kcm: Fix memory leak in error path of kcm_sendmsg()
  r8152: check budget for r8152_poll()
  net: ethernet: mtk_eth_soc: fix possible NULL pointer dereference in mtk_hwlro_get_fdir_all()
  net: ethernet: mvpp2_main: fix possible OOB write in mvpp2_ethtool_get_rxnfc()
  net: ipv4: fix one memleak in __inet_del_ifa()
  clk: imx8mm: Move 1443X/1416X PLL clock structure to common place
  ARM: dts: BCM5301X: Extend RAM to full 256MB for Linksys EA6500 V2
  usb: typec: bus: verify partner exists in typec_altmode_attention
  usb: typec: tcpm: Refactor tcpm_handle_vdm_request
  usb: typec: tcpm: Refactor tcpm_handle_vdm_request payload handling
  perf tools: Handle old data in PERF_RECORD_ATTR
  perf hists browser: Fix hierarchy mode header
  mtd: rawnand: brcmnand: Fix potential false time out warning
  mtd: rawnand: brcmnand: Fix potential out-of-bounds access in oob write
  mtd: rawnand: brcmnand: Fix crash during the panic_write
  btrfs: use the correct superblock to compare fsid in btrfs_validate_super
  btrfs: don't start transaction when joining with TRANS_JOIN_NOSTART
  fuse: nlookup missing decrement in fuse_direntplus_link
  ata: pata_ftide010: Add missing MODULE_DESCRIPTION
  ata: sata_gemini: Add missing MODULE_DESCRIPTION
  sh: boards: Fix CEU buffer size passed to dma_declare_coherent_memory()
  net: hns3: fix the port information display when sfp is absent
  netfilter: nfnetlink_osf: avoid OOB read
  ip_tunnels: use DEV_STATS_INC()
  idr: fix param name in idr_alloc_cyclic() doc
  s390/zcrypt: don't leak memory if dev_set_name() fails
  igb: Change IGB_MIN to allow set rx/tx value between 64 and 80
  igbvf: Change IGBVF_MIN to allow set rx/tx value between 64 and 80
  igc: Change IGC_MIN to allow set rx/tx value between 64 and 80
  kcm: Destroy mutex in kcm_exit_net()
  net: sched: sch_qfq: Fix UAF in qfq_dequeue()
  af_unix: Fix data race around sk->sk_err.
  af_unix: Fix data-races around sk->sk_shutdown.
  af_unix: Fix data-race around unix_tot_inflight.
  af_unix: Fix data-races around user->unix_inflight.
  net: ipv6/addrconf: avoid integer underflow in ipv6_create_tempaddr
  veth: Fixing transmit return status for dropped packets
  igb: disable virtualization features on 82580
  net: read sk->sk_family once in sk_mc_loop()
  ipv4: annotate data-races around fi->fib_dead
  sctp: annotate data-races around sk->sk_wmem_queued
  pwm: lpc32xx: Remove handling of PWM channels
  watchdog: intel-mid_wdt: add MODULE_ALIAS() to allow auto-load
  perf top: Don't pass an ERR_PTR() directly to perf_session__delete()
  x86/virt: Drop unnecessary check on extended CPUID level in cpu_has_svm()
  perf annotate bpf: Don't enclose non-debug code with an assert()
  kconfig: fix possible buffer overflow
  NFSv4/pnfs: minor fix for cleanup path in nfs4_get_device_info
  soc: qcom: qmi_encdec: Restrict string length in decode
  clk: qcom: gcc-mdm9615: use proper parent for pll0_vote clock
  parisc: led: Reduce CPU overhead for disk & lan LED computation
  parisc: led: Fix LAN receive and transmit LEDs
  lib/test_meminit: allocate pages up to order MAX_ORDER
  drm/ast: Fix DRAM init on AST2200
  fbdev/ep93xx-fb: Do not assign to struct fb_info.dev
  scsi: qla2xxx: Remove unsupported ql2xenabledif option
  scsi: qla2xxx: Turn off noisy message log
  scsi: qla2xxx: Fix erroneous link up failure
  scsi: qla2xxx: fix inconsistent TMF timeout
  net/ipv6: SKB symmetric hash should incorporate transport ports
  drm: fix double free for gbo in drm_gem_vram_init and drm_gem_vram_create
  udf: initialize newblock to 0
  usb: typec: tcpci: clear the fault status bit
  serial: sc16is7xx: fix broken port 0 uart init
  sc16is7xx: Set iobase to device index
  cpufreq: brcmstb-avs-cpufreq: Fix -Warray-bounds bug
  crypto: stm32 - fix loop iterating through scatterlist for DMA
  s390/ipl: add missing secure/has_secure file to ipl type 'unknown'
  pstore/ram: Check start of empty przs during init
  fsverity: skip PKCS#7 parser when keyring is empty
  net: handle ARPHRD_PPP in dev_is_mac_header_xmit()
  X.509: if signature is unsupported skip validation
  dccp: Fix out of bounds access in DCCP error handler
  dlm: fix plock lookup when using multiple lockspaces
  parisc: Fix /proc/cpuinfo output for lscpu
  procfs: block chmod on /proc/thread-self/comm
  Revert "PCI: Mark NVIDIA T4 GPUs to avoid bus reset"
  ntb: Fix calculation ntb_transport_tx_free_entry()
  ntb: Clean up tx tail index on link down
  ntb: Drop packets when qp link is down
  media: dvb: symbol fixup for dvb_attach()
  xtensa: PMU: fix base address for the newer hardware
  backlight/lv5207lp: Compare against struct fb_info.device
  backlight/bd6107: Compare against struct fb_info.device
  backlight/gpio_backlight: Compare against struct fb_info.device
  ARM: OMAP2+: Fix -Warray-bounds warning in _pwrdm_state_switch()
  ipmi_si: fix a memleak in try_smi_init()
  ALSA: pcm: Fix missing fixup call in compat hw_refine ioctl
  PM / devfreq: Fix leak in devfreq_dev_release()
  igb: set max size RX buffer when store bad packet is enabled
  skbuff: skb_segment, Call zero copy functions before using skbuff frags
  netfilter: xt_sctp: validate the flag_info count
  netfilter: xt_u32: validate user space input
  netfilter: ipset: add the missing IP_SET_HASH_WITH_NET0 macro for ip_set_hash_netportnet.c
  igmp: limit igmpv3_newpack() packet size to IP_MAX_MTU
  virtio_ring: fix avail_wrap_counter in virtqueue_add_packed
  cpufreq: Fix the race condition while updating the transition_task of policy
  dmaengine: ste_dma40: Add missing IRQ check in d40_probe
  um: Fix hostaudio build errors
  mtd: rawnand: fsmc: handle clk prepare error in fsmc_nand_resume()
  rpmsg: glink: Add check for kstrdup
  phy/rockchip: inno-hdmi: do not power on rk3328 post pll on reg write
  phy/rockchip: inno-hdmi: round fractal pixclock in rk3328 recalc_rate
  phy/rockchip: inno-hdmi: use correct vco_div_5 macro on rk3328
  tracing: Fix race issue between cpu buffer write and swap
  x86/speculation: Mark all Skylake CPUs as vulnerable to GDS
  HID: multitouch: Correct devm device reference for hidinput input_dev name
  HID: logitech-dj: Fix error handling in logi_dj_recv_switch_to_dj_mode()
  RDMA/siw: Correct wrong debug message
  RDMA/siw: Balance the reference of cep->kref in the error path
  Revert "IB/isert: Fix incorrect release of isert connection"
  amba: bus: fix refcount leak
  serial: tegra: handle clk prepare error in tegra_uart_hw_init()
  scsi: fcoe: Fix potential deadlock on &fip->ctlr_lock
  scsi: core: Use 32-bit hostnum in scsi_host_lookup()
  media: ov2680: Fix regulators being left enabled on ov2680_power_on() errors
  media: ov2680: Fix vflip / hflip set functions
  media: ov2680: Fix ov2680_bayer_order()
  media: ov2680: Remove auto-gain and auto-exposure controls
  media: i2c: ov2680: Set V4L2_CTRL_FLAG_MODIFY_LAYOUT on flips
  media: ov5640: Enable MIPI interface in ov5640_set_power_mipi()
  media: i2c: ov5640: Configure HVP lines in s_power callback
  USB: gadget: f_mass_storage: Fix unused variable warning
  media: go7007: Remove redundant if statement
  iommu/vt-d: Fix to flush cache of PASID directory table
  IB/uverbs: Fix an potential error pointer dereference
  driver core: test_async: fix an error code
  dma-buf/sync_file: Fix docs syntax
  coresight: tmc: Explicit type conversions to prevent integer overflow
  scsi: qedf: Do not touch __user pointer in qedf_dbg_fp_int_cmd_read() directly
  scsi: qedf: Do not touch __user pointer in qedf_dbg_debug_cmd_read() directly
  scsi: qedf: Do not touch __user pointer in qedf_dbg_stop_io_on_error_cmd_read() directly
  x86/APM: drop the duplicate APM_MINOR_DEV macro
  serial: sprd: Fix DMA buffer leak issue
  serial: sprd: Assign sprd_port after initialized to avoid wrong access
  serial: sprd: remove redundant sprd_port cleanup
  serial: sprd: getting port index via serial aliases only
  scsi: qla4xxx: Add length check when parsing nlattrs
  scsi: be2iscsi: Add length check when parsing nlattrs
  scsi: iscsi: Add strlen() check in iscsi_if_set{_host}_param()
  usb: phy: mxs: fix getting wrong state with mxs_phy_is_otg_host()
  media: mediatek: vcodec: Return NULL if no vdec_fb is found
  media: cx24120: Add retval check for cx24120_message_send()
  media: dvb-usb: m920x: Fix a potential memory leak in m920x_i2c_xfer()
  media: dib7000p: Fix potential division by zero
  drivers: usb: smsusb: fix error handling code in smsusb_init_device
  media: v4l2-core: Fix a potential resource leak in v4l2_fwnode_parse_link()
  media: v4l2-fwnode: simplify v4l2_fwnode_parse_link
  media: v4l2-fwnode: fix v4l2_fwnode_parse_link handling
  NFS: Guard against READDIR loop when entry names exceed MAXNAMELEN
  NFSD: da_addr_body field missing in some GETDEVICEINFO replies
  fs: lockd: avoid possible wrong NULL parameter
  jfs: validate max amount of blocks before allocation.
  powerpc/iommu: Fix notifiers being shared by PCI and VIO buses
  nfs/blocklayout: Use the passed in gfp flags
  wifi: ath10k: Use RMW accessors for changing LNKCTL
  drm/radeon: Use RMW accessors for changing LNKCTL
  drm/radeon: Prefer pcie_capability_read_word()
  drm/radeon: Replace numbers with PCI_EXP_LNKCTL2 definitions
  drm/radeon: Correct Transmit Margin masks
  drm/amdgpu: Use RMW accessors for changing LNKCTL
  drm/amdgpu: Prefer pcie_capability_read_word()
  drm/amdgpu: Replace numbers with PCI_EXP_LNKCTL2 definitions
  drm/amdgpu: Correct Transmit Margin masks
  PCI: Add #defines for Enter Compliance, Transmit Margin
  powerpc/fadump: reset dump area size if fadump memory reserve fails
  clk: imx: composite-8m: fix clock pauses when set_rate would be a no-op
  PCI/ASPM: Use RMW accessors for changing LNKCTL
  PCI: pciehp: Use RMW accessors for changing LNKCTL
  PCI: Mark NVIDIA T4 GPUs to avoid bus reset
  clk: sunxi-ng: Modify mismatched function name
  drivers: clk: keystone: Fix parameter judgment in _of_pll_clk_init()
  ipmi:ssif: Fix a memory leak when scanning for an adapter
  ipmi:ssif: Add check for kstrdup
  ALSA: ac97: Fix possible error value of *rac97
  of: unittest: Fix overlay type in apply/revert check
  drm/mediatek: Fix potential memory leak if vmap() fail
  audit: fix possible soft lockup in __audit_inode_child()
  smackfs: Prevent underflow in smk_set_cipso()
  drm/msm/mdp5: Don't leak some plane state
  ima: Remove deprecated IMA_TRUSTED_KEYRING Kconfig
  drm/panel: simple: Add missing connector type and pixel format for AUO T215HVN01
  drm/armada: Fix off-by-one error in armada_overlay_get_property()
  of: unittest: fix null pointer dereferencing in of_unittest_find_node_by_name()
  drm/tegra: dpaux: Fix incorrect return value of platform_get_irq
  drm/tegra: Remove superfluous error messages around platform_get_irq()
  md/md-bitmap: hold 'reconfig_mutex' in backlog_store()
  md/bitmap: don't set max_write_behind if there is no write mostly device
  drm/amdgpu: Update min() to min_t() in 'amdgpu_info_ioctl'
  arm64: dts: qcom: sdm845: Add missing RPMh power domain to GCC
  ARM: dts: BCM53573: Fix Ethernet info for Luxul devices
  drm: adv7511: Fix low refresh rate register for ADV7533/5
  ARM: dts: samsung: s5pv210-smdkv210: correct ethernet reg addresses (split)
  ARM: dts: s5pv210: add dummy 5V regulator for backlight on SMDKv210
  ARM: dts: s5pv210: correct ethernet unit address in SMDKV210
  ARM: dts: s5pv210: use defines for IRQ flags in SMDKV210
  ARM: dts: s5pv210: add RTC 32 KHz clock in SMDKV210
  ARM: dts: samsung: s3c6410-mini6410: correct ethernet reg addresses (split)
  ARM: dts: s3c64xx: align pinctrl with dtschema
  ARM: dts: s3c6410: align node SROM bus node name with dtschema in Mini6410
  ARM: dts: s3c6410: move fixed clocks under root node in Mini6410
  drm/etnaviv: fix dumping of active MMU context
  ARM: dts: BCM53573: Use updated "spi-gpio" binding properties
  ARM: dts: BCM53573: Add cells sizes to PCIe node
  ARM: dts: BCM53573: Drop nonexistent "default-off" LED trigger
  drm/amdgpu: avoid integer overflow warning in amdgpu_device_resize_fb_bar()
  quota: fix dqput() to follow the guarantees dquot_srcu should provide
  quota: add new helper dquot_active()
  quota: rename dquot_active() to inode_quota_active()
  quota: factor out dquot_write_dquot()
  quota: avoid increasing DQST_LOOKUPS when iterating over dirty/inuse list
  drm/bridge: tc358764: Fix debug print parameter order
  netrom: Deny concurrent connect().
  net/sched: sch_hfsc: Ensure inner classes have fsc curve
  mlxsw: i2c: Limit single transaction buffer size
  mlxsw: i2c: Fix chunk size setting in output mailbox buffer
  net: arcnet: Do not call kfree_skb() under local_irq_disable()
  wifi: ath9k: use IS_ERR() with debugfs_create_dir()
  wifi: mwifiex: avoid possible NULL skb pointer dereference
  wifi: ath9k: protect WMI command response buffer replacement with a lock
  wifi: ath9k: fix races between ath9k_wmi_cmd and ath9k_wmi_ctrl_rx
  wifi: mwifiex: Fix missed return in oob checks failed path
  wifi: mwifiex: fix memory leak in mwifiex_histogram_read()
  fs: ocfs2: namei: check return value of ocfs2_add_entry()
  lwt: Check LWTUNNEL_XMIT_CONTINUE strictly
  lwt: Fix return values of BPF xmit ops
  hwrng: iproc-rng200 - Implement suspend and resume calls
  hwrng: iproc-rng200 - use semicolons rather than commas to separate statements
  crypto: caam - fix unchecked return value error
  Bluetooth: nokia: fix value check in nokia_bluetooth_serdev_probe()
  crypto: stm32 - Properly handle pm_runtime_get failing
  wifi: mwifiex: fix error recovery in PCIE buffer descriptor management
  mwifiex: switch from 'pci_' to 'dma_' API
  wifi: mwifiex: Fix OOB and integer underflow when rx packets
  can: gs_usb: gs_usb_receive_bulk_callback(): count RX overflow errors also in case of OOM
  spi: tegra20-sflash: fix to check return value of platform_get_irq() in tegra_sflash_probe()
  regmap: rbtree: Use alloc_flags for memory allocations
  tcp: tcp_enter_quickack_mode() should be static
  bpf: Clear the probe_addr for uprobe
  cpufreq: powernow-k8: Use related_cpus instead of cpus in driver.exit()
  perf/imx_ddr: don't enable counter0 if none of 4 counters are used
  x86/decompressor: Don't rely on upper 32 bits of GPRs being preserved
  x86/boot: Annotate local functions
  x86/asm: Make more symbols local
  OPP: Fix passing 0 to PTR_ERR in _opp_attach_genpd()
  tmpfs: verify {g,u}id mount options correctly
  fs: Fix error checking for d_hash_and_lookup()
  new helper: lookup_positive_unlocked()
  eventfd: prevent underflow for eventfd semaphores
  eventfd: Export eventfd_ctx_do_read()
  reiserfs: Check the return value from __getblk()
  Revert "net: macsec: preserve ingress frame ordering"
  udf: Handle error when adding extent to a file
  udf: Check consistency of Space Bitmap Descriptor
  powerpc/32s: Fix assembler warning about r0
  net: Avoid address overwrite in kernel_connect
  platform/mellanox: Fix mlxbf-tmfifo not handling all virtio CONSOLE notifications
  ALSA: seq: oss: Fix racy open/close of MIDI devices
  scsi: storvsc: Always set no_report_opcodes
  cifs: add a warning when the in-flight count goes negative
  sctp: handle invalid error codes without calling BUG()
  bnx2x: fix page fault following EEH recovery
  netlabel: fix shift wrapping bug in netlbl_catmap_setlong()
  scsi: qedi: Fix potential deadlock on &qedi_percpu->p_work_lock
  idmaengine: make FSL_EDMA and INTEL_IDMA64 depends on HAS_IOMEM
  net: usb: qmi_wwan: add Quectel EM05GV2
  clk: fixed-mmio: make COMMON_CLK_FIXED_MMIO depend on HAS_IOMEM
  security: keys: perform capable check only on privileged operations
  platform/x86: huawei-wmi: Silence ambient light sensor
  platform/x86: intel: hid: Always call BTNL ACPI method
  ASoC: atmel: Fix the 8K sample parameter in I2SC master
  ASoc: codecs: ES8316: Fix DMIC config
  fs/nls: make load_nls() take a const parameter
  s390/dasd: fix hanging device after request requeue
  s390/dasd: use correct number of retries for ERP requests
  m68k: Fix invalid .section syntax
  vxlan: generalize vxlan_parse_gpe_hdr and remove unused args
  ethernet: atheros: fix return value check in atl1c_tso_csum()
  ASoC: da7219: Check for failure reading AAD IRQ events
  ASoC: da7219: Flush pending AAD IRQ when suspending
  9p: virtio: make sure 'offs' is initialized in zc_request
  pinctrl: amd: Don't show `Invalid config param` errors
  nilfs2: fix WARNING in mark_buffer_dirty due to discarded buffer reuse
  nilfs2: fix general protection fault in nilfs_lookup_dirty_data_buffers()
  fsi: master-ast-cf: Add MODULE_FIRMWARE macro
  firmware: stratix10-svc: Fix an NULL vs IS_ERR() bug in probe
  serial: sc16is7xx: fix bug when first setting GPIO direction
  Bluetooth: btsdio: fix use after free bug in btsdio_remove due to race condition
  staging: rtl8712: fix race condition
  HID: wacom: remove the battery when the EKR is off
  USB: serial: option: add FOXCONN T99W368/T99W373 product
  USB: serial: option: add Quectel EM05G variant (0x030e)
  modules: only allow symbol_get of EXPORT_SYMBOL_GPL modules
  rtc: ds1685: use EXPORT_SYMBOL_GPL for ds1685_rtc_poweroff
  net: enetc: use EXPORT_SYMBOL_GPL for enetc_phc_index
  mmc: au1xmmc: force non-modular build and remove symbol_get usage
  ARM: pxa: remove use of symbol_get()
  erofs: ensure that the post-EOF tails are all zeroed
  Linux 5.4.256
  Revert "MIPS: Alchemy: fix dbdma2"
  powerpc/pmac/smp: Drop unnecessary volatile qualifier
  powerpc/pmac/smp: Avoid unused-variable warnings
  Revert "drm/display/dp: Fix the DP DSC Receiver cap size"
  Revert "macsec: Fix traffic counters/statistics"
  Revert "macsec: use DEV_STATS_INC()"
  ANDROID: GKI: add back pm_runtime_get_if_in_use()
  Revert "interconnect: Add helpers for enabling/disabling a path"
  Revert "interconnect: Do not skip aggregation for disabled paths"
  Revert "ALSA: pcm: Set per-card upper limit of PCM buffer allocations"
  Revert "ALSA: pcm: Use SG-buffer only when direct DMA is available"
  Revert "ALSA: pcm: Fix potential data race at PCM memory allocation helpers"
  Revert "ALSA: pcm: Fix build error on m68k and others"
  Revert "Revert "ALSA: pcm: Use SG-buffer only when direct DMA is available""
  Revert "ALSA: pcm: Check for null pointer of pointer substream before dereferencing it"
  Linux 5.4.255
  dma-buf/sw_sync: Avoid recursive lock during fence signal
  pinctrl: renesas: rza2: Add lock around pinctrl_generic{{add,remove}_group,{add,remove}_function}
  clk: Fix undefined reference to `clk_rate_exclusive_{get,put}'
  scsi: core: raid_class: Remove raid_component_add()
  scsi: snic: Fix double free in snic_tgt_create()
  irqchip/mips-gic: Don't touch vl_map if a local interrupt is not routable
  Documentation/sysctl: document page_lock_unfairness
  ALSA: pcm: Check for null pointer of pointer substream before dereferencing it
  interconnect: Do not skip aggregation for disabled paths
  Revert "ALSA: pcm: Use SG-buffer only when direct DMA is available"
  ALSA: pcm: Fix build error on m68k and others
  rtnetlink: Reject negative ifindexes in RTM_NEWLINK
  mm: allow a controlled amount of unfairness in the page lock
  x86/fpu: Set X86_FEATURE_OSXSAVE feature after enabling OSXSAVE in CR4
  drm/display/dp: Fix the DP DSC Receiver cap size
  PCI: acpiphp: Use pci_assign_unassigned_bridge_resources() only for non-root bus
  media: vcodec: Fix potential array out-of-bounds in encoder queue_setup
  radix tree: remove unused variable
  lib/clz_ctz.c: Fix __clzdi2() and __ctzdi2() for 32-bit kernels
  batman-adv: Hold rtnl lock during MTU update via netlink
  batman-adv: Fix batadv_v_ogm_aggr_send memory leak
  batman-adv: Fix TT global entry leak when client roamed back
  batman-adv: Do not get eth header before batadv_check_management_packet
  batman-adv: Don't increase MTU when set by user
  batman-adv: Trigger events for auto adjusted MTU
  nfsd: Fix race to FREE_STATEID and cl_revoked
  clk: Fix slab-out-of-bounds error in devm_clk_release()
  NFSv4: Fix dropped lock for racing OPEN and delegation return
  ibmveth: Use dcbf rather than dcbfl
  bonding: fix macvlan over alb bond support
  net: remove bond_slave_has_mac_rcu()
  net/sched: fix a qdisc modification with ambiguous command request
  igb: Avoid starting unnecessary workqueues
  net: validate veth and vxcan peer ifindexes
  net: bcmgenet: Fix return value check for fixed_phy_register()
  net: bgmac: Fix return value check for fixed_phy_register()
  ipvlan: Fix a reference count leak warning in ipvlan_ns_exit()
  dccp: annotate data-races in dccp_poll()
  sock: annotate data-races around prot->memory_pressure
  octeontx2-af: SDP: fix receive link config
  tracing: Fix memleak due to race between current_tracer and trace
  drm/amd/display: check TG is non-null before checking if enabled
  drm/amd/display: do not wait for mpc idle if tg is disabled
  ASoC: fsl_sai: Disable bit clock with transmitter
  ASoC: fsl_sai: Add new added registers and new bit definition
  ASoC: fsl_sai: Refine enable/disable TE/RE sequence in trigger()
  regmap: Account for register length in SMBus I/O limits
  ALSA: pcm: Fix potential data race at PCM memory allocation helpers
  ALSA: pcm: Use SG-buffer only when direct DMA is available
  ALSA: pcm: Set per-card upper limit of PCM buffer allocations
  dm integrity: reduce vmalloc space footprint on 32-bit architectures
  dm integrity: increase RECALC_SECTORS to improve recalculate speed
  fbdev: fix potential OOB read in fast_imageblit()
  fbdev: Fix sys_imageblit() for arbitrary image widths
  fbdev: Improve performance of sys_imageblit()
  MIPS: cpu-features: Use boot_cpu_type for CPU type based features
  MIPS: cpu-features: Enable octeon_cache by cpu_type
  fs: dlm: fix mismatch of plock results from userspace
  fs: dlm: use dlm_plock_info for do_unlock_close
  fs: dlm: change plock interrupted message to debug again
  fs: dlm: add pid to debug log
  dlm: replace usage of found with dedicated list iterator variable
  dlm: improve plock logging if interrupted
  PCI: acpiphp: Reassign resources on bridge if necessary
  net: phy: broadcom: stub c45 read/write for 54810
  mmc: f-sdh30: fix order of function calls in sdhci_f_sdh30_remove
  net: xfrm: Amend XFRMA_SEC_CTX nla_policy structure
  net: fix the RTO timer retransmitting skb every 1ms if linear option is enabled
  virtio-net: set queues after driver_ok
  af_unix: Fix null-ptr-deref in unix_stream_sendpage().
  netfilter: set default timeout to 3 secs for sctp shutdown send and recv state
  mmc: block: Fix in_flight[issue_type] value error
  mmc: wbsd: fix double mmc_free_host() in wbsd_init()
  cifs: Release folio lock on fscache read hit.
  ALSA: usb-audio: Add support for Mythware XA001AU capture and playback interfaces.
  serial: 8250: Fix oops for port->pm on uart_change_pm()
  ASoC: meson: axg-tdm-formatter: fix channel slot allocation
  ASoC: rt5665: add missed regulator_bulk_disable
  ARM: dts: imx: Set default tuning step for imx6sx usdhc
  ARM: dts: imx: Set default tuning step for imx7d usdhc
  ARM: dts: imx: Adjust dma-apbh node name
  ARM: dts: imx7s: Drop dma-apb interrupt-names
  bus: ti-sysc: Flush posted write on enable before reset
  bus: ti-sysc: Improve reset to work with modules with no sysconfig
  net: do not allow gso_size to be set to GSO_BY_FRAGS
  sock: Fix misuse of sk_under_memory_pressure()
  net: dsa: mv88e6xxx: Wait for EEPROM done before HW reset
  i40e: fix misleading debug logs
  team: Fix incorrect deletion of ETH_P_8021AD protocol vid from slaves
  netfilter: nft_dynset: disallow object maps
  ipvs: fix racy memcpy in proc_do_sync_threshold
  selftests: mirror_gre_changes: Tighten up the TTL test match
  xfrm: add NULL check in xfrm_update_ae_params
  ip_vti: fix potential slab-use-after-free in decode_session6
  ip6_vti: fix slab-use-after-free in decode_session6
  xfrm: fix slab-use-after-free in decode_session6
  xfrm: interface: rename xfrm_interface.c to xfrm_interface_core.c
  net: af_key: fix sadb_x_filter validation
  net: xfrm: Fix xfrm_address_filter OOB read
  btrfs: fix BUG_ON condition in btrfs_cancel_balance
  tty: serial: fsl_lpuart: Clear the error flags by writing 1 for lpuart32 platforms
  powerpc/rtas_flash: allow user copy to flash block cache objects
  fbdev: mmp: fix value check in mmphw_probe()
  i2c: bcm-iproc: Fix bcm_iproc_i2c_isr deadlock issue
  virtio-mmio: don't break lifecycle of vm_dev
  virtio-mmio: Use to_virtio_mmio_device() to simply code
  virtio-mmio: convert to devm_platform_ioremap_resource
  nfsd: Remove incorrect check in nfsd4_validate_stateid
  nfsd4: kill warnings on testing stateids with mismatched clientids
  net/ncsi: Fix gma flag setting after response
  tracing/probes: Fix to update dynamic data counter if fetcharg uses it
  tracing/probes: Have process_fetch_insn() take a void * instead of pt_regs
  leds: trigger: netdev: Recheck NETDEV_LED_MODE_LINKUP on dev rename
  mmc: sunxi: fix deferred probing
  mmc: bcm2835: fix deferred probing
  USB: dwc3: qcom: fix NULL-deref on suspend
  usb: dwc3: qcom: Add helper functions to enable,disable wake irqs
  interconnect: Add helpers for enabling/disabling a path
  interconnect: Move internal structs into a separate file
  irqchip/mips-gic: Use raw spinlock for gic_lock
  irqchip/mips-gic: Get rid of the reliance on irq_cpu_online()
  ALSA: hda: Fix unhandled register update during auto-suspend period
  PM: runtime: Add pm_runtime_get_if_active()
  PM-runtime: add tracepoints for usage_count changes
  iommu/amd: Fix "Guest Virtual APIC Table Root Pointer" configuration in IRTE
  iio: addac: stx104: Fix race condition when converting analog-to-digital
  iio: addac: stx104: Fix race condition for stx104_write_raw()
  iio: stx104: Move to addac subdirectory
  iio: adc: stx104: Implement and utilize register structures
  iio: adc: stx104: Utilize iomap interface
  iio: add addac subdirectory
  IMA: allow/fix UML builds
  powerpc/kasan: Disable KCOV in KASAN code
  ALSA: hda: fix a possible null-pointer dereference due to data race in snd_hdac_regmap_sync()
  ALSA: hda/realtek: Add quirks for Unis H3C Desktop B760 & Q760
  drm/amdgpu: Fix potential fence use-after-free v2
  Bluetooth: L2CAP: Fix use-after-free
  pcmcia: rsrc_nonstatic: Fix memory leak in nonstatic_release_resource_db()
  gfs2: Fix possible data races in gfs2_show_options()
  usb: chipidea: imx: don't request QoS for imx8ulp
  media: platform: mediatek: vpu: fix NULL ptr dereference
  media: v4l2-mem2mem: add lock to protect parameter num_rdy
  FS: JFS: Check for read-only mounted filesystem in txBegin
  FS: JFS: Fix null-ptr-deref Read in txBegin
  MIPS: dec: prom: Address -Warray-bounds warning
  fs: jfs: Fix UBSAN: array-index-out-of-bounds in dbAllocDmapLev
  udf: Fix uninitialized array access for some pathnames
  ovl: check type and offset of struct vfsmount in ovl_entry
  HID: add quirk for 03f0:464a HP Elite Presenter Mouse
  quota: fix warning in dqgrab()
  quota: Properly disable quotas when add_dquot_ref() fails
  ALSA: emu10k1: roll up loops in DSP setup code for Audigy
  drm/radeon: Fix integer overflow in radeon_cs_parser_init
  macsec: use DEV_STATS_INC()
  macsec: Fix traffic counters/statistics
  selftests: forwarding: tc_flower: Relax success criterion
  mmc: sdhci-f-sdh30: Replace with sdhci_pltfm
  mmc: sdhci_f_sdh30: convert to devm_platform_ioremap_resource

 Conflicts:
	drivers/devfreq/devfreq.c
	drivers/mmc/core/block.c
	drivers/rpmsg/qcom_glink_native.c
	include/net/tcp.h

Change-Id: Ic33d13451796752e101ed9f9bdb8c80a580af8b5
2023-12-11 20:22:05 +02:00

3060 lines
73 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/kernel/fork.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
/*
* 'fork.c' contains the help-routines for the 'fork' system call
* (see also entry.S and others).
* Fork is rather simple, once you get the hang of it, but the memory
* management can be a bitch. See 'mm/memory.c': 'copy_page_range()'
*/
#include <linux/anon_inodes.h>
#include <linux/slab.h>
#include <linux/sched/autogroup.h>
#include <linux/sched/mm.h>
#include <linux/sched/coredump.h>
#include <linux/sched/user.h>
#include <linux/sched/numa_balancing.h>
#include <linux/sched/stat.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/sched/cputime.h>
#include <linux/seq_file.h>
#include <linux/rtmutex.h>
#include <linux/init.h>
#include <linux/unistd.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/completion.h>
#include <linux/personality.h>
#include <linux/mempolicy.h>
#include <linux/sem.h>
#include <linux/file.h>
#include <linux/fdtable.h>
#include <linux/iocontext.h>
#include <linux/key.h>
#include <linux/binfmts.h>
#include <linux/mman.h>
#include <linux/mmu_notifier.h>
#include <linux/hmm.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/vmacache.h>
#include <linux/nsproxy.h>
#include <linux/capability.h>
#include <linux/cpu.h>
#include <linux/cgroup.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
#include <linux/seccomp.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
#include <linux/jiffies.h>
#include <linux/futex.h>
#include <linux/compat.h>
#include <linux/kthread.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/rcupdate.h>
#include <linux/ptrace.h>
#include <linux/mount.h>
#include <linux/audit.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
#include <linux/proc_fs.h>
#include <linux/profile.h>
#include <linux/rmap.h>
#include <linux/ksm.h>
#include <linux/acct.h>
#include <linux/userfaultfd_k.h>
#include <linux/tsacct_kern.h>
#include <linux/cn_proc.h>
#include <linux/freezer.h>
#include <linux/delayacct.h>
#include <linux/taskstats_kern.h>
#include <linux/random.h>
#include <linux/tty.h>
#include <linux/blkdev.h>
#include <linux/fs_struct.h>
#include <linux/magic.h>
#include <linux/perf_event.h>
#include <linux/posix-timers.h>
#include <linux/user-return-notifier.h>
#include <linux/oom.h>
#include <linux/khugepaged.h>
#include <linux/signalfd.h>
#include <linux/uprobes.h>
#include <linux/aio.h>
#include <linux/compiler.h>
#include <linux/sysctl.h>
#include <linux/kcov.h>
#include <linux/livepatch.h>
#include <linux/thread_info.h>
#include <linux/cpufreq_times.h>
#include <linux/stackleak.h>
#include <linux/scs.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <linux/uaccess.h>
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <trace/events/sched.h>
#define CREATE_TRACE_POINTS
#include <trace/events/task.h>
/*
* Minimum number of threads to boot the kernel
*/
#define MIN_THREADS 20
/*
* Maximum number of threads
*/
#define MAX_THREADS FUTEX_TID_MASK
/*
* Protected counters by write_lock_irq(&tasklist_lock)
*/
unsigned long total_forks; /* Handle normal Linux uptimes. */
int nr_threads; /* The idle threads do not count.. */
static int max_threads; /* tunable limit on nr_threads */
#define NAMED_ARRAY_INDEX(x) [x] = __stringify(x)
static const char * const resident_page_types[] = {
NAMED_ARRAY_INDEX(MM_FILEPAGES),
NAMED_ARRAY_INDEX(MM_ANONPAGES),
NAMED_ARRAY_INDEX(MM_SWAPENTS),
NAMED_ARRAY_INDEX(MM_SHMEMPAGES),
#ifdef CONFIG_MM_STAT_UNRECLAIMABLE_PAGES
NAMED_ARRAY_INDEX(MM_UNRECLAIMABLE),
#endif
};
DEFINE_PER_CPU(unsigned long, process_counts) = 0;
__cacheline_aligned DEFINE_RWLOCK(tasklist_lock); /* outer */
#ifdef CONFIG_PROVE_RCU
int lockdep_tasklist_lock_is_held(void)
{
return lockdep_is_held(&tasklist_lock);
}
EXPORT_SYMBOL_GPL(lockdep_tasklist_lock_is_held);
#endif /* #ifdef CONFIG_PROVE_RCU */
int nr_processes(void)
{
int cpu;
int total = 0;
for_each_possible_cpu(cpu)
total += per_cpu(process_counts, cpu);
return total;
}
void __weak arch_release_task_struct(struct task_struct *tsk)
{
}
#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
static struct kmem_cache *task_struct_cachep;
static inline struct task_struct *alloc_task_struct_node(int node)
{
return kmem_cache_alloc_node(task_struct_cachep, GFP_KERNEL, node);
}
static inline void free_task_struct(struct task_struct *tsk)
{
kmem_cache_free(task_struct_cachep, tsk);
}
#endif
#ifndef CONFIG_ARCH_THREAD_STACK_ALLOCATOR
/*
* Allocate pages if THREAD_SIZE is >= PAGE_SIZE, otherwise use a
* kmemcache based allocator.
*/
# if THREAD_SIZE >= PAGE_SIZE || defined(CONFIG_VMAP_STACK)
#ifdef CONFIG_VMAP_STACK
/*
* vmalloc() is a bit slow, and calling vfree() enough times will force a TLB
* flush. Try to minimize the number of calls by caching stacks.
*/
#define NR_CACHED_STACKS 2
static DEFINE_PER_CPU(struct vm_struct *, cached_stacks[NR_CACHED_STACKS]);
static int free_vm_stack_cache(unsigned int cpu)
{
struct vm_struct **cached_vm_stacks = per_cpu_ptr(cached_stacks, cpu);
int i;
for (i = 0; i < NR_CACHED_STACKS; i++) {
struct vm_struct *vm_stack = cached_vm_stacks[i];
if (!vm_stack)
continue;
vfree(vm_stack->addr);
cached_vm_stacks[i] = NULL;
}
return 0;
}
#endif
static unsigned long *alloc_thread_stack_node(struct task_struct *tsk, int node)
{
#ifdef CONFIG_VMAP_STACK
void *stack;
int i;
for (i = 0; i < NR_CACHED_STACKS; i++) {
struct vm_struct *s;
s = this_cpu_xchg(cached_stacks[i], NULL);
if (!s)
continue;
/* Clear stale pointers from reused stack. */
memset(s->addr, 0, THREAD_SIZE);
tsk->stack_vm_area = s;
tsk->stack = s->addr;
return s->addr;
}
/*
* Allocated stacks are cached and later reused by new threads,
* so memcg accounting is performed manually on assigning/releasing
* stacks to tasks. Drop __GFP_ACCOUNT.
*/
stack = __vmalloc_node_range(THREAD_SIZE, THREAD_ALIGN,
VMALLOC_START, VMALLOC_END,
THREADINFO_GFP & ~__GFP_ACCOUNT,
PAGE_KERNEL,
0, node, __builtin_return_address(0));
/*
* We can't call find_vm_area() in interrupt context, and
* free_thread_stack() can be called in interrupt context,
* so cache the vm_struct.
*/
if (stack) {
tsk->stack_vm_area = find_vm_area(stack);
tsk->stack = stack;
}
return stack;
#else
struct page *page = alloc_pages_node(node, THREADINFO_GFP,
THREAD_SIZE_ORDER);
if (likely(page)) {
tsk->stack = page_address(page);
return tsk->stack;
}
return NULL;
#endif
}
static inline void free_thread_stack(struct task_struct *tsk)
{
#ifdef CONFIG_VMAP_STACK
struct vm_struct *vm = task_stack_vm_area(tsk);
if (vm) {
int i;
for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
mod_memcg_page_state(vm->pages[i],
MEMCG_KERNEL_STACK_KB,
-(int)(PAGE_SIZE / 1024));
memcg_kmem_uncharge(vm->pages[i], 0);
}
for (i = 0; i < NR_CACHED_STACKS; i++) {
if (this_cpu_cmpxchg(cached_stacks[i],
NULL, tsk->stack_vm_area) != NULL)
continue;
return;
}
vfree_atomic(tsk->stack);
return;
}
#endif
__free_pages(virt_to_page(tsk->stack), THREAD_SIZE_ORDER);
}
# else
static struct kmem_cache *thread_stack_cache;
static unsigned long *alloc_thread_stack_node(struct task_struct *tsk,
int node)
{
unsigned long *stack;
stack = kmem_cache_alloc_node(thread_stack_cache, THREADINFO_GFP, node);
tsk->stack = stack;
return stack;
}
static void free_thread_stack(struct task_struct *tsk)
{
kmem_cache_free(thread_stack_cache, tsk->stack);
}
void thread_stack_cache_init(void)
{
thread_stack_cache = kmem_cache_create_usercopy("thread_stack",
THREAD_SIZE, THREAD_SIZE, 0, 0,
THREAD_SIZE, NULL);
BUG_ON(thread_stack_cache == NULL);
}
# endif
#endif
/* SLAB cache for signal_struct structures (tsk->signal) */
static struct kmem_cache *signal_cachep;
/* SLAB cache for sighand_struct structures (tsk->sighand) */
struct kmem_cache *sighand_cachep;
/* SLAB cache for files_struct structures (tsk->files) */
struct kmem_cache *files_cachep;
/* SLAB cache for fs_struct structures (tsk->fs) */
struct kmem_cache *fs_cachep;
/* SLAB cache for vm_area_struct structures */
static struct kmem_cache *vm_area_cachep;
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
{
struct vm_area_struct *vma;
vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
if (vma)
vma_init(vma, mm);
return vma;
}
struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
{
struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
if (new) {
*new = *orig;
INIT_VMA(new);
}
return new;
}
void vm_area_free(struct vm_area_struct *vma)
{
kmem_cache_free(vm_area_cachep, vma);
}
static void account_kernel_stack(struct task_struct *tsk, int account)
{
void *stack = task_stack_page(tsk);
struct vm_struct *vm = task_stack_vm_area(tsk);
BUILD_BUG_ON(IS_ENABLED(CONFIG_VMAP_STACK) && PAGE_SIZE % 1024 != 0);
if (vm) {
int i;
BUG_ON(vm->nr_pages != THREAD_SIZE / PAGE_SIZE);
for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
mod_zone_page_state(page_zone(vm->pages[i]),
NR_KERNEL_STACK_KB,
PAGE_SIZE / 1024 * account);
}
} else {
/*
* All stack pages are in the same zone and belong to the
* same memcg.
*/
struct page *first_page = virt_to_page(stack);
mod_zone_page_state(page_zone(first_page), NR_KERNEL_STACK_KB,
THREAD_SIZE / 1024 * account);
mod_memcg_obj_state(stack, MEMCG_KERNEL_STACK_KB,
account * (THREAD_SIZE / 1024));
}
}
static int memcg_charge_kernel_stack(struct task_struct *tsk)
{
#ifdef CONFIG_VMAP_STACK
struct vm_struct *vm = task_stack_vm_area(tsk);
int ret;
if (vm) {
int i;
for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) {
/*
* If memcg_kmem_charge() fails, page->mem_cgroup
* pointer is NULL, and both memcg_kmem_uncharge()
* and mod_memcg_page_state() in free_thread_stack()
* will ignore this page. So it's safe.
*/
ret = memcg_kmem_charge(vm->pages[i], GFP_KERNEL, 0);
if (ret)
return ret;
mod_memcg_page_state(vm->pages[i],
MEMCG_KERNEL_STACK_KB,
PAGE_SIZE / 1024);
}
}
#endif
return 0;
}
static void release_task_stack(struct task_struct *tsk)
{
if (WARN_ON(tsk->state != TASK_DEAD))
return; /* Better to leak the stack than to free prematurely */
account_kernel_stack(tsk, -1);
free_thread_stack(tsk);
tsk->stack = NULL;
#ifdef CONFIG_VMAP_STACK
tsk->stack_vm_area = NULL;
#endif
}
#ifdef CONFIG_THREAD_INFO_IN_TASK
void put_task_stack(struct task_struct *tsk)
{
if (refcount_dec_and_test(&tsk->stack_refcount))
release_task_stack(tsk);
}
#endif
void free_task(struct task_struct *tsk)
{
cpufreq_task_times_exit(tsk);
scs_release(tsk);
#ifndef CONFIG_THREAD_INFO_IN_TASK
/*
* The task is finally done with both the stack and thread_info,
* so free both.
*/
release_task_stack(tsk);
#else
/*
* If the task had a separate stack allocation, it should be gone
* by now.
*/
WARN_ON_ONCE(refcount_read(&tsk->stack_refcount) != 0);
#endif
rt_mutex_debug_task_free(tsk);
ftrace_graph_exit_task(tsk);
put_seccomp_filter(tsk);
arch_release_task_struct(tsk);
if (tsk->flags & PF_KTHREAD)
free_kthread_struct(tsk);
free_task_struct(tsk);
}
EXPORT_SYMBOL(free_task);
#ifdef CONFIG_MMU
static __latent_entropy int dup_mmap(struct mm_struct *mm,
struct mm_struct *oldmm)
{
struct vm_area_struct *mpnt, *tmp, *prev, **pprev, *last = NULL;
struct rb_node **rb_link, *rb_parent;
int retval;
unsigned long charge;
LIST_HEAD(uf);
uprobe_start_dup_mmap();
if (down_write_killable(&oldmm->mmap_sem)) {
retval = -EINTR;
goto fail_uprobe_end;
}
flush_cache_dup_mm(oldmm);
uprobe_dup_mmap(oldmm, mm);
/*
* Not linked in yet - no deadlock potential:
*/
down_write_nested(&mm->mmap_sem, SINGLE_DEPTH_NESTING);
/* No ordering required: file already has been exposed. */
RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
mm->total_vm = oldmm->total_vm;
mm->data_vm = oldmm->data_vm;
mm->exec_vm = oldmm->exec_vm;
mm->stack_vm = oldmm->stack_vm;
rb_link = &mm->mm_rb.rb_node;
rb_parent = NULL;
pprev = &mm->mmap;
retval = ksm_fork(mm, oldmm);
if (retval)
goto out;
retval = khugepaged_fork(mm, oldmm);
if (retval)
goto out;
prev = NULL;
for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
struct file *file;
if (mpnt->vm_flags & VM_DONTCOPY) {
vm_stat_account(mm, mpnt->vm_flags, -vma_pages(mpnt));
continue;
}
charge = 0;
/*
* Don't duplicate many vmas if we've been oom-killed (for
* example)
*/
if (fatal_signal_pending(current)) {
retval = -EINTR;
goto out;
}
if (mpnt->vm_flags & VM_ACCOUNT) {
unsigned long len = vma_pages(mpnt);
if (security_vm_enough_memory_mm(oldmm, len)) /* sic */
goto fail_nomem;
charge = len;
}
tmp = vm_area_dup(mpnt);
if (!tmp)
goto fail_nomem;
retval = vma_dup_policy(mpnt, tmp);
if (retval)
goto fail_nomem_policy;
tmp->vm_mm = mm;
retval = dup_userfaultfd(tmp, &uf);
if (retval)
goto fail_nomem_anon_vma_fork;
if (tmp->vm_flags & VM_WIPEONFORK) {
/* VM_WIPEONFORK gets a clean slate in the child. */
tmp->anon_vma = NULL;
if (anon_vma_prepare(tmp))
goto fail_nomem_anon_vma_fork;
} else if (anon_vma_fork(tmp, mpnt))
goto fail_nomem_anon_vma_fork;
tmp->vm_flags &= ~(VM_LOCKED | VM_LOCKONFAULT);
tmp->vm_next = tmp->vm_prev = NULL;
file = tmp->vm_file;
if (file) {
struct inode *inode = file_inode(file);
struct address_space *mapping = file->f_mapping;
get_file(file);
if (tmp->vm_flags & VM_DENYWRITE)
atomic_dec(&inode->i_writecount);
i_mmap_lock_write(mapping);
if (tmp->vm_flags & VM_SHARED)
atomic_inc(&mapping->i_mmap_writable);
flush_dcache_mmap_lock(mapping);
/* insert tmp into the share list, just after mpnt */
vma_interval_tree_insert_after(tmp, mpnt,
&mapping->i_mmap);
flush_dcache_mmap_unlock(mapping);
i_mmap_unlock_write(mapping);
}
/*
* Clear hugetlb-related page reserves for children. This only
* affects MAP_PRIVATE mappings. Faults generated by the child
* are not guaranteed to succeed, even if read-only
*/
if (is_vm_hugetlb_page(tmp))
reset_vma_resv_huge_pages(tmp);
/*
* Link in the new vma and copy the page table entries.
*/
*pprev = tmp;
pprev = &tmp->vm_next;
tmp->vm_prev = prev;
prev = tmp;
__vma_link_rb(mm, tmp, rb_link, rb_parent);
rb_link = &tmp->vm_rb.rb_right;
rb_parent = &tmp->vm_rb;
mm->map_count++;
if (!(tmp->vm_flags & VM_WIPEONFORK)) {
if (IS_ENABLED(CONFIG_SPECULATIVE_PAGE_FAULT)) {
/*
* Mark this VMA as changing to prevent the
* speculative page fault hanlder to process
* it until the TLB are flushed below.
*/
last = mpnt;
vm_write_begin(mpnt);
}
retval = copy_page_range(mm, oldmm, mpnt);
}
if (tmp->vm_ops && tmp->vm_ops->open)
tmp->vm_ops->open(tmp);
if (retval)
goto out;
}
/* a new mm has just been created */
retval = arch_dup_mmap(oldmm, mm);
out:
up_write(&mm->mmap_sem);
flush_tlb_mm(oldmm);
if (IS_ENABLED(CONFIG_SPECULATIVE_PAGE_FAULT)) {
/*
* Since the TLB has been flush, we can safely unmark the
* copied VMAs and allows the speculative page fault handler to
* process them again.
* Walk back the VMA list from the last marked VMA.
*/
for (; last; last = last->vm_prev) {
if (last->vm_flags & VM_DONTCOPY)
continue;
if (!(last->vm_flags & VM_WIPEONFORK))
vm_write_end(last);
}
}
up_write(&oldmm->mmap_sem);
dup_userfaultfd_complete(&uf);
fail_uprobe_end:
uprobe_end_dup_mmap();
return retval;
fail_nomem_anon_vma_fork:
mpol_put(vma_policy(tmp));
fail_nomem_policy:
vm_area_free(tmp);
fail_nomem:
retval = -ENOMEM;
vm_unacct_memory(charge);
goto out;
}
static inline int mm_alloc_pgd(struct mm_struct *mm)
{
mm->pgd = pgd_alloc(mm);
if (unlikely(!mm->pgd))
return -ENOMEM;
return 0;
}
static inline void mm_free_pgd(struct mm_struct *mm)
{
pgd_free(mm, mm->pgd);
}
#else
static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
{
down_write(&oldmm->mmap_sem);
RCU_INIT_POINTER(mm->exe_file, get_mm_exe_file(oldmm));
up_write(&oldmm->mmap_sem);
return 0;
}
#define mm_alloc_pgd(mm) (0)
#define mm_free_pgd(mm)
#endif /* CONFIG_MMU */
static void check_mm(struct mm_struct *mm)
{
int i;
BUILD_BUG_ON_MSG(ARRAY_SIZE(resident_page_types) != NR_MM_COUNTERS,
"Please make sure 'struct resident_page_types[]' is updated as well");
for (i = 0; i < NR_MM_COUNTERS; i++) {
long x;
#ifdef CONFIG_MM_STAT_UNRECLAIMABLE_PAGES
/* MM_UNRECLAIMABLE could be freed later in exit_files */
if (i == MM_UNRECLAIMABLE)
continue;
#endif
x = atomic_long_read(&mm->rss_stat.count[i]);
if (unlikely(x))
pr_alert("BUG: Bad rss-counter state mm:%p type:%s val:%ld\n",
mm, resident_page_types[i], x);
}
if (mm_pgtables_bytes(mm))
pr_alert("BUG: non-zero pgtables_bytes on freeing mm: %ld\n",
mm_pgtables_bytes(mm));
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
VM_BUG_ON_MM(mm->pmd_huge_pte, mm);
#endif
}
#define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL))
#define free_mm(mm) (kmem_cache_free(mm_cachep, (mm)))
/*
* Called when the last reference to the mm
* is dropped: either by a lazy thread or by
* mmput. Free the page directory and the mm.
*/
void __mmdrop(struct mm_struct *mm)
{
BUG_ON(mm == &init_mm);
WARN_ON_ONCE(mm == current->mm);
WARN_ON_ONCE(mm == current->active_mm);
mm_free_pgd(mm);
destroy_context(mm);
mmu_notifier_mm_destroy(mm);
check_mm(mm);
put_user_ns(mm->user_ns);
free_mm(mm);
}
EXPORT_SYMBOL_GPL(__mmdrop);
static void mmdrop_async_fn(struct work_struct *work)
{
struct mm_struct *mm;
mm = container_of(work, struct mm_struct, async_put_work);
__mmdrop(mm);
}
static void mmdrop_async(struct mm_struct *mm)
{
if (unlikely(atomic_dec_and_test(&mm->mm_count))) {
INIT_WORK(&mm->async_put_work, mmdrop_async_fn);
schedule_work(&mm->async_put_work);
}
}
static inline void free_signal_struct(struct signal_struct *sig)
{
taskstats_tgid_free(sig);
sched_autogroup_exit(sig);
/*
* __mmdrop is not safe to call from softirq context on x86 due to
* pgd_dtor so postpone it to the async context
*/
if (sig->oom_mm)
mmdrop_async(sig->oom_mm);
kmem_cache_free(signal_cachep, sig);
}
static inline void put_signal_struct(struct signal_struct *sig)
{
if (refcount_dec_and_test(&sig->sigcnt))
free_signal_struct(sig);
}
void __put_task_struct(struct task_struct *tsk)
{
WARN_ON(!tsk->exit_state);
WARN_ON(refcount_read(&tsk->usage));
WARN_ON(tsk == current);
cgroup_free(tsk);
task_numa_free(tsk, true);
security_task_free(tsk);
exit_creds(tsk);
delayacct_tsk_free(tsk);
put_signal_struct(tsk->signal);
if (!profile_handoff_task(tsk))
free_task(tsk);
}
EXPORT_SYMBOL_GPL(__put_task_struct);
void __put_task_struct_rcu_cb(struct rcu_head *rhp)
{
struct task_struct *task = container_of(rhp, struct task_struct, rcu);
__put_task_struct(task);
}
EXPORT_SYMBOL_GPL(__put_task_struct_rcu_cb);
void __init __weak arch_task_cache_init(void) { }
/*
* set_max_threads
*/
static void set_max_threads(unsigned int max_threads_suggested)
{
u64 threads;
unsigned long nr_pages = totalram_pages();
/*
* The number of threads shall be limited such that the thread
* structures may only consume a small part of the available memory.
*/
if (fls64(nr_pages) + fls64(PAGE_SIZE) > 64)
threads = MAX_THREADS;
else
threads = div64_u64((u64) nr_pages * (u64) PAGE_SIZE,
(u64) THREAD_SIZE * 8UL);
if (threads > max_threads_suggested)
threads = max_threads_suggested;
max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS);
}
#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
/* Initialized by the architecture: */
int arch_task_struct_size __read_mostly;
#endif
#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
static void task_struct_whitelist(unsigned long *offset, unsigned long *size)
{
/* Fetch thread_struct whitelist for the architecture. */
arch_thread_struct_whitelist(offset, size);
/*
* Handle zero-sized whitelist or empty thread_struct, otherwise
* adjust offset to position of thread_struct in task_struct.
*/
if (unlikely(*size == 0))
*offset = 0;
else
*offset += offsetof(struct task_struct, thread);
}
#endif /* CONFIG_ARCH_TASK_STRUCT_ALLOCATOR */
void __init fork_init(void)
{
int i;
#ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
#ifndef ARCH_MIN_TASKALIGN
#define ARCH_MIN_TASKALIGN 0
#endif
int align = max_t(int, L1_CACHE_BYTES, ARCH_MIN_TASKALIGN);
unsigned long useroffset, usersize;
/* create a slab on which task_structs can be allocated */
task_struct_whitelist(&useroffset, &usersize);
task_struct_cachep = kmem_cache_create_usercopy("task_struct",
arch_task_struct_size, align,
SLAB_PANIC|SLAB_ACCOUNT,
useroffset, usersize, NULL);
#endif
/* do the arch specific task caches init */
arch_task_cache_init();
set_max_threads(MAX_THREADS);
init_task.signal->rlim[RLIMIT_NPROC].rlim_cur = max_threads/2;
init_task.signal->rlim[RLIMIT_NPROC].rlim_max = max_threads/2;
init_task.signal->rlim[RLIMIT_SIGPENDING] =
init_task.signal->rlim[RLIMIT_NPROC];
for (i = 0; i < UCOUNT_COUNTS; i++) {
init_user_ns.ucount_max[i] = max_threads/2;
}
#ifdef CONFIG_VMAP_STACK
cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
NULL, free_vm_stack_cache);
#endif
scs_init();
lockdep_init_task(&init_task);
uprobes_init();
}
int __weak arch_dup_task_struct(struct task_struct *dst,
struct task_struct *src)
{
*dst = *src;
return 0;
}
void set_task_stack_end_magic(struct task_struct *tsk)
{
unsigned long *stackend;
stackend = end_of_stack(tsk);
*stackend = STACK_END_MAGIC; /* for overflow detection */
}
static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
{
struct task_struct *tsk;
unsigned long *stack;
struct vm_struct *stack_vm_area __maybe_unused;
int err;
if (node == NUMA_NO_NODE)
node = tsk_fork_get_node(orig);
tsk = alloc_task_struct_node(node);
if (!tsk)
return NULL;
stack = alloc_thread_stack_node(tsk, node);
if (!stack)
goto free_tsk;
if (memcg_charge_kernel_stack(tsk))
goto free_stack;
stack_vm_area = task_stack_vm_area(tsk);
err = arch_dup_task_struct(tsk, orig);
/*
* arch_dup_task_struct() clobbers the stack-related fields. Make
* sure they're properly initialized before using any stack-related
* functions again.
*/
tsk->stack = stack;
#ifdef CONFIG_VMAP_STACK
tsk->stack_vm_area = stack_vm_area;
#endif
#ifdef CONFIG_THREAD_INFO_IN_TASK
refcount_set(&tsk->stack_refcount, 1);
#endif
if (err)
goto free_stack;
err = scs_prepare(tsk, node);
if (err)
goto free_stack;
#ifdef CONFIG_SECCOMP
/*
* We must handle setting up seccomp filters once we're under
* the sighand lock in case orig has changed between now and
* then. Until then, filter must be NULL to avoid messing up
* the usage counts on the error path calling free_task.
*/
tsk->seccomp.filter = NULL;
#endif
setup_thread_stack(tsk, orig);
clear_user_return_notifier(tsk);
clear_tsk_need_resched(tsk);
set_task_stack_end_magic(tsk);
#ifdef CONFIG_STACKPROTECTOR
tsk->stack_canary = get_random_canary();
#endif
if (orig->cpus_ptr == &orig->cpus_mask)
tsk->cpus_ptr = &tsk->cpus_mask;
/*
* One for the user space visible state that goes away when reaped.
* One for the scheduler.
*/
refcount_set(&tsk->rcu_users, 2);
/* One for the rcu users */
refcount_set(&tsk->usage, 1);
#ifdef CONFIG_BLK_DEV_IO_TRACE
tsk->btrace_seq = 0;
#endif
tsk->splice_pipe = NULL;
tsk->task_frag.page = NULL;
tsk->wake_q.next = NULL;
account_kernel_stack(tsk, 1);
kcov_task_init(tsk);
#ifdef CONFIG_FAULT_INJECTION
tsk->fail_nth = 0;
#endif
#ifdef CONFIG_BLK_CGROUP
tsk->throttle_queue = NULL;
tsk->use_memdelay = 0;
#endif
#ifdef CONFIG_MEMCG
tsk->active_memcg = NULL;
#endif
return tsk;
free_stack:
free_thread_stack(tsk);
free_tsk:
free_task_struct(tsk);
return NULL;
}
__cacheline_aligned_in_smp DEFINE_SPINLOCK(mmlist_lock);
static unsigned long default_dump_filter = MMF_DUMP_FILTER_DEFAULT;
static int __init coredump_filter_setup(char *s)
{
default_dump_filter =
(simple_strtoul(s, NULL, 0) << MMF_DUMP_FILTER_SHIFT) &
MMF_DUMP_FILTER_MASK;
return 1;
}
__setup("coredump_filter=", coredump_filter_setup);
#include <linux/init_task.h>
static void mm_init_aio(struct mm_struct *mm)
{
#ifdef CONFIG_AIO
spin_lock_init(&mm->ioctx_lock);
mm->ioctx_table = NULL;
#endif
}
static __always_inline void mm_clear_owner(struct mm_struct *mm,
struct task_struct *p)
{
#ifdef CONFIG_MEMCG
if (mm->owner == p)
WRITE_ONCE(mm->owner, NULL);
#endif
}
static void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
{
#ifdef CONFIG_MEMCG
mm->owner = p;
#endif
}
static void mm_init_uprobes_state(struct mm_struct *mm)
{
#ifdef CONFIG_UPROBES
mm->uprobes_state.xol_area = NULL;
#endif
}
static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
struct user_namespace *user_ns)
{
mm->mmap = NULL;
mm->mm_rb = RB_ROOT;
mm->vmacache_seqnum = 0;
#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
rwlock_init(&mm->mm_rb_lock);
#endif
atomic_set(&mm->mm_users, 1);
atomic_set(&mm->mm_count, 1);
init_rwsem(&mm->mmap_sem);
INIT_LIST_HEAD(&mm->mmlist);
mm->core_state = NULL;
mm_pgtables_bytes_init(mm);
mm->map_count = 0;
mm->locked_vm = 0;
atomic64_set(&mm->pinned_vm, 0);
memset(&mm->rss_stat, 0, sizeof(mm->rss_stat));
spin_lock_init(&mm->page_table_lock);
spin_lock_init(&mm->arg_lock);
mm_init_cpumask(mm);
mm_init_aio(mm);
mm_init_owner(mm, p);
RCU_INIT_POINTER(mm->exe_file, NULL);
mmu_notifier_mm_init(mm);
init_tlb_flush_pending(mm);
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
mm->pmd_huge_pte = NULL;
#endif
mm_init_uprobes_state(mm);
hugetlb_count_init(mm);
if (current->mm) {
mm->flags = current->mm->flags & MMF_INIT_MASK;
mm->def_flags = current->mm->def_flags & VM_INIT_DEF_MASK;
} else {
mm->flags = default_dump_filter;
mm->def_flags = 0;
}
if (mm_alloc_pgd(mm))
goto fail_nopgd;
if (init_new_context(p, mm))
goto fail_nocontext;
mm->user_ns = get_user_ns(user_ns);
return mm;
fail_nocontext:
mm_free_pgd(mm);
fail_nopgd:
free_mm(mm);
return NULL;
}
/*
* Allocate and initialize an mm_struct.
*/
struct mm_struct *mm_alloc(void)
{
struct mm_struct *mm;
mm = allocate_mm();
if (!mm)
return NULL;
memset(mm, 0, sizeof(*mm));
return mm_init(mm, current, current_user_ns());
}
static inline void __mmput(struct mm_struct *mm)
{
VM_BUG_ON(atomic_read(&mm->mm_users));
uprobe_clear_state(mm);
exit_aio(mm);
ksm_exit(mm);
khugepaged_exit(mm); /* must run before exit_mmap */
exit_mmap(mm);
mm_put_huge_zero_page(mm);
set_mm_exe_file(mm, NULL);
if (!list_empty(&mm->mmlist)) {
spin_lock(&mmlist_lock);
list_del(&mm->mmlist);
spin_unlock(&mmlist_lock);
}
if (mm->binfmt)
module_put(mm->binfmt->module);
mmdrop(mm);
}
/*
* Decrement the use count and release all resources for an mm.
*/
void mmput(struct mm_struct *mm)
{
might_sleep();
if (atomic_dec_and_test(&mm->mm_users))
__mmput(mm);
}
EXPORT_SYMBOL_GPL(mmput);
#ifdef CONFIG_MMU
static void mmput_async_fn(struct work_struct *work)
{
struct mm_struct *mm = container_of(work, struct mm_struct,
async_put_work);
__mmput(mm);
}
void mmput_async(struct mm_struct *mm)
{
if (atomic_dec_and_test(&mm->mm_users)) {
INIT_WORK(&mm->async_put_work, mmput_async_fn);
schedule_work(&mm->async_put_work);
}
}
#endif
/**
* set_mm_exe_file - change a reference to the mm's executable file
*
* This changes mm's executable file (shown as symlink /proc/[pid]/exe).
*
* Main users are mmput() and sys_execve(). Callers prevent concurrent
* invocations: in mmput() nobody alive left, in execve task is single
* threaded. sys_prctl(PR_SET_MM_MAP/EXE_FILE) also needs to set the
* mm->exe_file, but does so without using set_mm_exe_file() in order
* to do avoid the need for any locks.
*/
void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file)
{
struct file *old_exe_file;
/*
* It is safe to dereference the exe_file without RCU as
* this function is only called if nobody else can access
* this mm -- see comment above for justification.
*/
old_exe_file = rcu_dereference_raw(mm->exe_file);
if (new_exe_file)
get_file(new_exe_file);
rcu_assign_pointer(mm->exe_file, new_exe_file);
if (old_exe_file)
fput(old_exe_file);
}
/**
* get_mm_exe_file - acquire a reference to the mm's executable file
*
* Returns %NULL if mm has no associated executable file.
* User must release file via fput().
*/
struct file *get_mm_exe_file(struct mm_struct *mm)
{
struct file *exe_file;
rcu_read_lock();
exe_file = rcu_dereference(mm->exe_file);
if (exe_file && !get_file_rcu(exe_file))
exe_file = NULL;
rcu_read_unlock();
return exe_file;
}
EXPORT_SYMBOL(get_mm_exe_file);
/**
* get_task_exe_file - acquire a reference to the task's executable file
*
* Returns %NULL if task's mm (if any) has no associated executable file or
* this is a kernel thread with borrowed mm (see the comment above get_task_mm).
* User must release file via fput().
*/
struct file *get_task_exe_file(struct task_struct *task)
{
struct file *exe_file = NULL;
struct mm_struct *mm;
task_lock(task);
mm = task->mm;
if (mm) {
if (!(task->flags & PF_KTHREAD))
exe_file = get_mm_exe_file(mm);
}
task_unlock(task);
return exe_file;
}
EXPORT_SYMBOL(get_task_exe_file);
/**
* get_task_mm - acquire a reference to the task's mm
*
* Returns %NULL if the task has no mm. Checks PF_KTHREAD (meaning
* this kernel workthread has transiently adopted a user mm with use_mm,
* to do its AIO) is not set and if so returns a reference to it, after
* bumping up the use count. User must release the mm via mmput()
* after use. Typically used by /proc and ptrace.
*/
struct mm_struct *get_task_mm(struct task_struct *task)
{
struct mm_struct *mm;
task_lock(task);
mm = task->mm;
if (mm) {
if (task->flags & PF_KTHREAD)
mm = NULL;
else
mmget(mm);
}
task_unlock(task);
return mm;
}
EXPORT_SYMBOL_GPL(get_task_mm);
struct mm_struct *mm_access(struct task_struct *task, unsigned int mode)
{
struct mm_struct *mm;
int err;
err = mutex_lock_killable(&task->signal->cred_guard_mutex);
if (err)
return ERR_PTR(err);
mm = get_task_mm(task);
if (mm && mm != current->mm &&
!ptrace_may_access(task, mode)) {
mmput(mm);
mm = ERR_PTR(-EACCES);
}
mutex_unlock(&task->signal->cred_guard_mutex);
return mm;
}
static void complete_vfork_done(struct task_struct *tsk)
{
struct completion *vfork;
task_lock(tsk);
vfork = tsk->vfork_done;
if (likely(vfork)) {
tsk->vfork_done = NULL;
complete(vfork);
}
task_unlock(tsk);
}
static int wait_for_vfork_done(struct task_struct *child,
struct completion *vfork)
{
int killed;
freezer_do_not_count();
cgroup_enter_frozen();
killed = wait_for_completion_killable(vfork);
cgroup_leave_frozen(false);
freezer_count();
if (killed) {
task_lock(child);
child->vfork_done = NULL;
task_unlock(child);
}
put_task_struct(child);
return killed;
}
/* Please note the differences between mmput and mm_release.
* mmput is called whenever we stop holding onto a mm_struct,
* error success whatever.
*
* mm_release is called after a mm_struct has been removed
* from the current process.
*
* This difference is important for error handling, when we
* only half set up a mm_struct for a new process and need to restore
* the old one. Because we mmput the new mm_struct before
* restoring the old one. . .
* Eric Biederman 10 January 1998
*/
static void mm_release(struct task_struct *tsk, struct mm_struct *mm)
{
uprobe_free_utask(tsk);
/* Get rid of any cached register state */
deactivate_mm(tsk, mm);
/*
* Signal userspace if we're not exiting with a core dump
* because we want to leave the value intact for debugging
* purposes.
*/
if (tsk->clear_child_tid) {
if (!(tsk->signal->flags & SIGNAL_GROUP_COREDUMP) &&
atomic_read(&mm->mm_users) > 1) {
/*
* We don't check the error code - if userspace has
* not set up a proper pointer then tough luck.
*/
put_user(0, tsk->clear_child_tid);
do_futex(tsk->clear_child_tid, FUTEX_WAKE,
1, NULL, NULL, 0, 0);
}
tsk->clear_child_tid = NULL;
}
/*
* All done, finally we can wake up parent and return this mm to him.
* Also kthread_stop() uses this completion for synchronization.
*/
if (tsk->vfork_done)
complete_vfork_done(tsk);
}
void exit_mm_release(struct task_struct *tsk, struct mm_struct *mm)
{
futex_exit_release(tsk);
mm_release(tsk, mm);
}
void exec_mm_release(struct task_struct *tsk, struct mm_struct *mm)
{
futex_exec_release(tsk);
mm_release(tsk, mm);
}
/**
* dup_mm() - duplicates an existing mm structure
* @tsk: the task_struct with which the new mm will be associated.
* @oldmm: the mm to duplicate.
*
* Allocates a new mm structure and duplicates the provided @oldmm structure
* content into it.
*
* Return: the duplicated mm or NULL on failure.
*/
static struct mm_struct *dup_mm(struct task_struct *tsk,
struct mm_struct *oldmm)
{
struct mm_struct *mm;
int err;
mm = allocate_mm();
if (!mm)
goto fail_nomem;
memcpy(mm, oldmm, sizeof(*mm));
if (!mm_init(mm, tsk, mm->user_ns))
goto fail_nomem;
err = dup_mmap(mm, oldmm);
if (err)
goto free_pt;
mm->hiwater_rss = get_mm_rss(mm);
mm->hiwater_vm = mm->total_vm;
if (mm->binfmt && !try_module_get(mm->binfmt->module))
goto free_pt;
return mm;
free_pt:
/* don't put binfmt in mmput, we haven't got module yet */
mm->binfmt = NULL;
mm_init_owner(mm, NULL);
mmput(mm);
fail_nomem:
return NULL;
}
static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
{
struct mm_struct *mm, *oldmm;
int retval;
tsk->min_flt = tsk->maj_flt = 0;
tsk->nvcsw = tsk->nivcsw = 0;
#ifdef CONFIG_DETECT_HUNG_TASK
tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw;
tsk->last_switch_time = 0;
#endif
tsk->mm = NULL;
tsk->active_mm = NULL;
/*
* Are we cloning a kernel thread?
*
* We need to steal a active VM for that..
*/
oldmm = current->mm;
if (!oldmm)
return 0;
/* initialize the new vmacache entries */
vmacache_flush(tsk);
if (clone_flags & CLONE_VM) {
mmget(oldmm);
mm = oldmm;
goto good_mm;
}
retval = -ENOMEM;
mm = dup_mm(tsk, current->mm);
if (!mm)
goto fail_nomem;
good_mm:
tsk->mm = mm;
tsk->active_mm = mm;
return 0;
fail_nomem:
return retval;
}
static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
{
struct fs_struct *fs = current->fs;
if (clone_flags & CLONE_FS) {
/* tsk->fs is already what we want */
spin_lock(&fs->lock);
if (fs->in_exec) {
spin_unlock(&fs->lock);
return -EAGAIN;
}
fs->users++;
spin_unlock(&fs->lock);
return 0;
}
tsk->fs = copy_fs_struct(fs);
if (!tsk->fs)
return -ENOMEM;
return 0;
}
static int copy_files(unsigned long clone_flags, struct task_struct *tsk)
{
struct files_struct *oldf, *newf;
int error = 0;
/*
* A background process may not have any files ...
*/
oldf = current->files;
if (!oldf)
goto out;
if (clone_flags & CLONE_FILES) {
atomic_inc(&oldf->count);
goto out;
}
newf = dup_fd(oldf, &error);
if (!newf)
goto out;
tsk->files = newf;
error = 0;
out:
return error;
}
static int copy_io(unsigned long clone_flags, struct task_struct *tsk)
{
#ifdef CONFIG_BLOCK
struct io_context *ioc = current->io_context;
struct io_context *new_ioc;
if (!ioc)
return 0;
/*
* Share io context with parent, if CLONE_IO is set
*/
if (clone_flags & CLONE_IO) {
ioc_task_link(ioc);
tsk->io_context = ioc;
} else if (ioprio_valid(ioc->ioprio)) {
new_ioc = get_task_io_context(tsk, GFP_KERNEL, NUMA_NO_NODE);
if (unlikely(!new_ioc))
return -ENOMEM;
new_ioc->ioprio = ioc->ioprio;
put_io_context(new_ioc);
}
#endif
return 0;
}
static int copy_sighand(unsigned long clone_flags, struct task_struct *tsk)
{
struct sighand_struct *sig;
if (clone_flags & CLONE_SIGHAND) {
refcount_inc(&current->sighand->count);
return 0;
}
sig = kmem_cache_alloc(sighand_cachep, GFP_KERNEL);
rcu_assign_pointer(tsk->sighand, sig);
if (!sig)
return -ENOMEM;
refcount_set(&sig->count, 1);
spin_lock_irq(&current->sighand->siglock);
memcpy(sig->action, current->sighand->action, sizeof(sig->action));
spin_unlock_irq(&current->sighand->siglock);
return 0;
}
void __cleanup_sighand(struct sighand_struct *sighand)
{
if (refcount_dec_and_test(&sighand->count)) {
signalfd_cleanup(sighand);
/*
* sighand_cachep is SLAB_TYPESAFE_BY_RCU so we can free it
* without an RCU grace period, see __lock_task_sighand().
*/
kmem_cache_free(sighand_cachep, sighand);
}
}
/*
* Initialize POSIX timer handling for a thread group.
*/
static void posix_cpu_timers_init_group(struct signal_struct *sig)
{
struct posix_cputimers *pct = &sig->posix_cputimers;
unsigned long cpu_limit;
cpu_limit = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur);
posix_cputimers_group_init(pct, cpu_limit);
}
static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
{
struct signal_struct *sig;
if (clone_flags & CLONE_THREAD)
return 0;
sig = kmem_cache_zalloc(signal_cachep, GFP_KERNEL);
tsk->signal = sig;
if (!sig)
return -ENOMEM;
sig->nr_threads = 1;
atomic_set(&sig->live, 1);
refcount_set(&sig->sigcnt, 1);
/* list_add(thread_node, thread_head) without INIT_LIST_HEAD() */
sig->thread_head = (struct list_head)LIST_HEAD_INIT(tsk->thread_node);
tsk->thread_node = (struct list_head)LIST_HEAD_INIT(sig->thread_head);
init_waitqueue_head(&sig->wait_chldexit);
sig->curr_target = tsk;
init_sigpending(&sig->shared_pending);
INIT_HLIST_HEAD(&sig->multiprocess);
seqlock_init(&sig->stats_lock);
prev_cputime_init(&sig->prev_cputime);
#ifdef CONFIG_POSIX_TIMERS
INIT_LIST_HEAD(&sig->posix_timers);
hrtimer_init(&sig->real_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
sig->real_timer.function = it_real_fn;
#endif
task_lock(current->group_leader);
memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
task_unlock(current->group_leader);
posix_cpu_timers_init_group(sig);
tty_audit_fork(sig);
sched_autogroup_fork(sig);
sig->oom_score_adj = current->signal->oom_score_adj;
sig->oom_score_adj_min = current->signal->oom_score_adj_min;
mutex_init(&sig->cred_guard_mutex);
return 0;
}
static void copy_seccomp(struct task_struct *p)
{
#ifdef CONFIG_SECCOMP
/*
* Must be called with sighand->lock held, which is common to
* all threads in the group. Holding cred_guard_mutex is not
* needed because this new task is not yet running and cannot
* be racing exec.
*/
assert_spin_locked(&current->sighand->siglock);
/* Ref-count the new filter user, and assign it. */
get_seccomp_filter(current);
p->seccomp = current->seccomp;
/*
* Explicitly enable no_new_privs here in case it got set
* between the task_struct being duplicated and holding the
* sighand lock. The seccomp state and nnp must be in sync.
*/
if (task_no_new_privs(current))
task_set_no_new_privs(p);
/*
* If the parent gained a seccomp mode after copying thread
* flags and between before we held the sighand lock, we have
* to manually enable the seccomp thread flag here.
*/
if (p->seccomp.mode != SECCOMP_MODE_DISABLED)
set_tsk_thread_flag(p, TIF_SECCOMP);
#endif
}
SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
{
current->clear_child_tid = tidptr;
return task_pid_vnr(current);
}
static void rt_mutex_init_task(struct task_struct *p)
{
raw_spin_lock_init(&p->pi_lock);
#ifdef CONFIG_RT_MUTEXES
p->pi_waiters = RB_ROOT_CACHED;
p->pi_top_task = NULL;
p->pi_blocked_on = NULL;
#endif
}
static inline void init_task_pid_links(struct task_struct *task)
{
enum pid_type type;
for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) {
INIT_HLIST_NODE(&task->pid_links[type]);
}
}
static inline void
init_task_pid(struct task_struct *task, enum pid_type type, struct pid *pid)
{
if (type == PIDTYPE_PID)
task->thread_pid = pid;
else
task->signal->pids[type] = pid;
}
static inline void rcu_copy_process(struct task_struct *p)
{
#ifdef CONFIG_PREEMPT_RCU
p->rcu_read_lock_nesting = 0;
p->rcu_read_unlock_special.s = 0;
p->rcu_blocked_node = NULL;
INIT_LIST_HEAD(&p->rcu_node_entry);
#endif /* #ifdef CONFIG_PREEMPT_RCU */
#ifdef CONFIG_TASKS_RCU
p->rcu_tasks_holdout = false;
INIT_LIST_HEAD(&p->rcu_tasks_holdout_list);
p->rcu_tasks_idle_cpu = -1;
#endif /* #ifdef CONFIG_TASKS_RCU */
}
struct pid *pidfd_pid(const struct file *file)
{
if (file->f_op == &pidfd_fops)
return file->private_data;
return ERR_PTR(-EBADF);
}
static int pidfd_release(struct inode *inode, struct file *file)
{
struct pid *pid = file->private_data;
file->private_data = NULL;
put_pid(pid);
return 0;
}
#ifdef CONFIG_PROC_FS
static void pidfd_show_fdinfo(struct seq_file *m, struct file *f)
{
struct pid_namespace *ns = proc_pid_ns(file_inode(m->file));
struct pid *pid = f->private_data;
seq_put_decimal_ull(m, "Pid:\t", pid_nr_ns(pid, ns));
seq_putc(m, '\n');
}
#endif
/*
* Poll support for process exit notification.
*/
static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
{
struct task_struct *task;
struct pid *pid = file->private_data;
__poll_t poll_flags = 0;
poll_wait(file, &pid->wait_pidfd, pts);
rcu_read_lock();
task = pid_task(pid, PIDTYPE_PID);
/*
* Inform pollers only when the whole thread group exits.
* If the thread group leader exits before all other threads in the
* group, then poll(2) should block, similar to the wait(2) family.
*/
if (!task || (task->exit_state && thread_group_empty(task)))
poll_flags = EPOLLIN | EPOLLRDNORM;
rcu_read_unlock();
return poll_flags;
}
const struct file_operations pidfd_fops = {
.release = pidfd_release,
.poll = pidfd_poll,
#ifdef CONFIG_PROC_FS
.show_fdinfo = pidfd_show_fdinfo,
#endif
};
static void __delayed_free_task(struct rcu_head *rhp)
{
struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
free_task(tsk);
}
static __always_inline void delayed_free_task(struct task_struct *tsk)
{
if (IS_ENABLED(CONFIG_MEMCG))
call_rcu(&tsk->rcu, __delayed_free_task);
else
free_task(tsk);
}
static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk)
{
/* Skip if kernel thread */
if (!tsk->mm)
return;
/* Skip if spawning a thread or using vfork */
if ((clone_flags & (CLONE_VM | CLONE_THREAD | CLONE_VFORK)) != CLONE_VM)
return;
/* We need to synchronize with __set_oom_adj */
mutex_lock(&oom_adj_mutex);
set_bit(MMF_MULTIPROCESS, &tsk->mm->flags);
/* Update the values in case they were changed after copy_signal */
tsk->signal->oom_score_adj = current->signal->oom_score_adj;
tsk->signal->oom_score_adj_min = current->signal->oom_score_adj_min;
mutex_unlock(&oom_adj_mutex);
}
/*
* This creates a new process as a copy of the old one,
* but does not actually start it yet.
*
* It copies the registers, and all the appropriate
* parts of the process environment (as per the clone
* flags). The actual kick-off is left to the caller.
*/
static __latent_entropy struct task_struct *copy_process(
struct pid *pid,
int trace,
int node,
struct kernel_clone_args *args)
{
int pidfd = -1, retval;
struct task_struct *p;
struct multiprocess_signals delayed;
struct file *pidfile = NULL;
u64 clone_flags = args->flags;
/*
* Don't allow sharing the root directory with processes in a different
* namespace
*/
if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS))
return ERR_PTR(-EINVAL);
if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS))
return ERR_PTR(-EINVAL);
/*
* Thread groups must share signals as well, and detached threads
* can only be started up within the thread group.
*/
if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND))
return ERR_PTR(-EINVAL);
/*
* Shared signal handlers imply shared VM. By way of the above,
* thread groups also imply shared VM. Blocking this case allows
* for various simplifications in other code.
*/
if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM))
return ERR_PTR(-EINVAL);
/*
* Siblings of global init remain as zombies on exit since they are
* not reaped by their parent (swapper). To solve this and to avoid
* multi-rooted process trees, prevent global and container-inits
* from creating siblings.
*/
if ((clone_flags & CLONE_PARENT) &&
current->signal->flags & SIGNAL_UNKILLABLE)
return ERR_PTR(-EINVAL);
/*
* If the new process will be in a different pid or user namespace
* do not allow it to share a thread group with the forking task.
*/
if (clone_flags & CLONE_THREAD) {
if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) ||
(task_active_pid_ns(current) !=
current->nsproxy->pid_ns_for_children))
return ERR_PTR(-EINVAL);
}
if (clone_flags & CLONE_PIDFD) {
/*
* - CLONE_DETACHED is blocked so that we can potentially
* reuse it later for CLONE_PIDFD.
* - CLONE_THREAD is blocked until someone really needs it.
*/
if (clone_flags & (CLONE_DETACHED | CLONE_THREAD))
return ERR_PTR(-EINVAL);
}
/*
* Force any signals received before this point to be delivered
* before the fork happens. Collect up signals sent to multiple
* processes that happen during the fork and delay them so that
* they appear to happen after the fork.
*/
sigemptyset(&delayed.signal);
INIT_HLIST_NODE(&delayed.node);
spin_lock_irq(&current->sighand->siglock);
if (!(clone_flags & CLONE_THREAD))
hlist_add_head(&delayed.node, &current->signal->multiprocess);
recalc_sigpending();
spin_unlock_irq(&current->sighand->siglock);
retval = -ERESTARTNOINTR;
if (signal_pending(current))
goto fork_out;
retval = -ENOMEM;
p = dup_task_struct(current, node);
if (!p)
goto fork_out;
cpufreq_task_times_init(p);
/*
* This _must_ happen before we call free_task(), i.e. before we jump
* to any of the bad_fork_* labels. This is to avoid freeing
* p->set_child_tid which is (ab)used as a kthread's data pointer for
* kernel threads (PF_KTHREAD).
*/
p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL;
/*
* Clear TID on mm_release()?
*/
p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL;
ftrace_graph_init_task(p);
rt_mutex_init_task(p);
#ifdef CONFIG_PROVE_LOCKING
DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled);
DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);
#endif
retval = -EAGAIN;
if (atomic_read(&p->real_cred->user->processes) >=
task_rlimit(p, RLIMIT_NPROC)) {
if (p->real_cred->user != INIT_USER &&
!capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
goto bad_fork_free;
}
current->flags &= ~PF_NPROC_EXCEEDED;
retval = copy_creds(p, clone_flags);
if (retval < 0)
goto bad_fork_free;
/*
* If multiple threads are within copy_process(), then this check
* triggers too late. This doesn't hurt, the check is only there
* to stop root fork bombs.
*/
retval = -EAGAIN;
if (nr_threads >= max_threads)
goto bad_fork_cleanup_count;
delayacct_tsk_init(p); /* Must remain after dup_task_struct() */
p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE);
p->flags |= PF_FORKNOEXEC;
INIT_LIST_HEAD(&p->children);
INIT_LIST_HEAD(&p->sibling);
rcu_copy_process(p);
p->vfork_done = NULL;
spin_lock_init(&p->alloc_lock);
init_sigpending(&p->pending);
p->utime = p->stime = p->gtime = 0;
#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
p->utimescaled = p->stimescaled = 0;
#endif
prev_cputime_init(&p->prev_cputime);
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
seqcount_init(&p->vtime.seqcount);
p->vtime.starttime = 0;
p->vtime.state = VTIME_INACTIVE;
#endif
#if defined(SPLIT_RSS_COUNTING)
memset(&p->rss_stat, 0, sizeof(p->rss_stat));
#endif
p->default_timer_slack_ns = current->timer_slack_ns;
#ifdef CONFIG_PSI
p->psi_flags = 0;
#endif
task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
posix_cputimers_init(&p->posix_cputimers);
p->io_context = NULL;
audit_set_context(p, NULL);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
if (IS_ERR(p->mempolicy)) {
retval = PTR_ERR(p->mempolicy);
p->mempolicy = NULL;
goto bad_fork_cleanup_threadgroup_lock;
}
#endif
#ifdef CONFIG_CPUSETS
p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
seqcount_init(&p->mems_allowed_seq);
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
p->irq_events = 0;
p->hardirqs_enabled = 0;
p->hardirq_enable_ip = 0;
p->hardirq_enable_event = 0;
p->hardirq_disable_ip = _THIS_IP_;
p->hardirq_disable_event = 0;
p->softirqs_enabled = 1;
p->softirq_enable_ip = _THIS_IP_;
p->softirq_enable_event = 0;
p->softirq_disable_ip = 0;
p->softirq_disable_event = 0;
p->hardirq_context = 0;
p->softirq_context = 0;
#endif
p->pagefault_disabled = 0;
#ifdef CONFIG_LOCKDEP
lockdep_init_task(p);
#endif
#ifdef CONFIG_DEBUG_MUTEXES
p->blocked_on = NULL; /* not blocked yet */
#endif
#ifdef CONFIG_BCACHE
p->sequential_io = 0;
p->sequential_io_avg = 0;
#endif
/* Perform scheduler related setup. Assign this task to a CPU. */
retval = sched_fork(clone_flags, p);
if (retval)
goto bad_fork_cleanup_policy;
retval = perf_event_init_task(p);
if (retval)
goto bad_fork_cleanup_policy;
retval = audit_alloc(p);
if (retval)
goto bad_fork_cleanup_perf;
/* copy all the process information */
shm_init_task(p);
retval = security_task_alloc(p, clone_flags);
if (retval)
goto bad_fork_cleanup_audit;
retval = copy_semundo(clone_flags, p);
if (retval)
goto bad_fork_cleanup_security;
retval = copy_files(clone_flags, p);
if (retval)
goto bad_fork_cleanup_semundo;
retval = copy_fs(clone_flags, p);
if (retval)
goto bad_fork_cleanup_files;
retval = copy_sighand(clone_flags, p);
if (retval)
goto bad_fork_cleanup_fs;
retval = copy_signal(clone_flags, p);
if (retval)
goto bad_fork_cleanup_sighand;
retval = copy_mm(clone_flags, p);
if (retval)
goto bad_fork_cleanup_signal;
retval = copy_namespaces(clone_flags, p);
if (retval)
goto bad_fork_cleanup_mm;
retval = copy_io(clone_flags, p);
if (retval)
goto bad_fork_cleanup_namespaces;
retval = copy_thread_tls(clone_flags, args->stack, args->stack_size, p,
args->tls);
if (retval)
goto bad_fork_cleanup_io;
stackleak_task_init(p);
if (pid != &init_struct_pid) {
pid = alloc_pid(p->nsproxy->pid_ns_for_children);
if (IS_ERR(pid)) {
retval = PTR_ERR(pid);
goto bad_fork_cleanup_thread;
}
}
/*
* This has to happen after we've potentially unshared the file
* descriptor table (so that the pidfd doesn't leak into the child
* if the fd table isn't shared).
*/
if (clone_flags & CLONE_PIDFD) {
retval = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
if (retval < 0)
goto bad_fork_free_pid;
pidfd = retval;
pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
O_RDWR | O_CLOEXEC);
if (IS_ERR(pidfile)) {
put_unused_fd(pidfd);
retval = PTR_ERR(pidfile);
goto bad_fork_free_pid;
}
get_pid(pid); /* held by pidfile now */
retval = put_user(pidfd, args->pidfd);
if (retval)
goto bad_fork_put_pidfd;
}
#ifdef CONFIG_BLOCK
p->plug = NULL;
#endif
futex_init_task(p);
/*
* sigaltstack should be cleared when sharing the same VM
*/
if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM)
sas_ss_reset(p);
/*
* Syscall tracing and stepping should be turned off in the
* child regardless of CLONE_PTRACE.
*/
user_disable_single_step(p);
clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE);
#ifdef TIF_SYSCALL_EMU
clear_tsk_thread_flag(p, TIF_SYSCALL_EMU);
#endif
clear_tsk_latency_tracing(p);
/* ok, now we should be set up.. */
p->pid = pid_nr(pid);
if (clone_flags & CLONE_THREAD) {
p->group_leader = current->group_leader;
p->tgid = current->tgid;
} else {
p->group_leader = p;
p->tgid = p->pid;
}
p->nr_dirtied = 0;
p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10);
p->dirty_paused_when = 0;
p->pdeath_signal = 0;
INIT_LIST_HEAD(&p->thread_group);
p->task_works = NULL;
cgroup_threadgroup_change_begin(current);
/*
* Ensure that the cgroup subsystem policies allow the new process to be
* forked. It should be noted the the new process's css_set can be changed
* between here and cgroup_post_fork() if an organisation operation is in
* progress.
*/
retval = cgroup_can_fork(p);
if (retval)
goto bad_fork_cgroup_threadgroup_change_end;
/*
* From this point on we must avoid any synchronous user-space
* communication until we take the tasklist-lock. In particular, we do
* not want user-space to be able to predict the process start-time by
* stalling fork(2) after we recorded the start_time but before it is
* visible to the system.
*/
p->start_time = ktime_get_ns();
p->real_start_time = ktime_get_boottime_ns();
/*
* Make it visible to the rest of the system, but dont wake it up yet.
* Need tasklist lock for parent etc handling!
*/
write_lock_irq(&tasklist_lock);
/* CLONE_PARENT re-uses the old parent */
if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) {
p->real_parent = current->real_parent;
p->parent_exec_id = current->parent_exec_id;
if (clone_flags & CLONE_THREAD)
p->exit_signal = -1;
else
p->exit_signal = current->group_leader->exit_signal;
} else {
p->real_parent = current;
p->parent_exec_id = current->self_exec_id;
p->exit_signal = args->exit_signal;
}
klp_copy_process(p);
spin_lock(&current->sighand->siglock);
/*
* Copy seccomp details explicitly here, in case they were changed
* before holding sighand lock.
*/
copy_seccomp(p);
rseq_fork(p, clone_flags);
/* Don't start children in a dying pid namespace */
if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) {
retval = -ENOMEM;
goto bad_fork_cancel_cgroup;
}
/* Let kill terminate clone/fork in the middle */
if (fatal_signal_pending(current)) {
retval = -EINTR;
goto bad_fork_cancel_cgroup;
}
init_task_pid_links(p);
if (likely(p->pid)) {
ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
init_task_pid(p, PIDTYPE_PID, pid);
if (thread_group_leader(p)) {
init_task_pid(p, PIDTYPE_TGID, pid);
init_task_pid(p, PIDTYPE_PGID, task_pgrp(current));
init_task_pid(p, PIDTYPE_SID, task_session(current));
if (is_child_reaper(pid)) {
ns_of_pid(pid)->child_reaper = p;
p->signal->flags |= SIGNAL_UNKILLABLE;
}
p->signal->shared_pending.signal = delayed.signal;
p->signal->tty = tty_kref_get(current->signal->tty);
/*
* Inherit has_child_subreaper flag under the same
* tasklist_lock with adding child to the process tree
* for propagate_has_child_subreaper optimization.
*/
p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper ||
p->real_parent->signal->is_child_subreaper;
list_add_tail(&p->sibling, &p->real_parent->children);
list_add_tail_rcu(&p->tasks, &init_task.tasks);
attach_pid(p, PIDTYPE_TGID);
attach_pid(p, PIDTYPE_PGID);
attach_pid(p, PIDTYPE_SID);
__this_cpu_inc(process_counts);
} else {
current->signal->nr_threads++;
atomic_inc(&current->signal->live);
refcount_inc(&current->signal->sigcnt);
task_join_group_stop(p);
list_add_tail_rcu(&p->thread_group,
&p->group_leader->thread_group);
list_add_tail_rcu(&p->thread_node,
&p->signal->thread_head);
}
attach_pid(p, PIDTYPE_PID);
nr_threads++;
}
total_forks++;
hlist_del_init(&delayed.node);
spin_unlock(&current->sighand->siglock);
syscall_tracepoint_update(p);
write_unlock_irq(&tasklist_lock);
if (pidfile)
fd_install(pidfd, pidfile);
proc_fork_connector(p);
cgroup_post_fork(p);
cgroup_threadgroup_change_end(current);
perf_event_fork(p);
trace_task_newtask(p, clone_flags);
uprobe_copy_process(p, clone_flags);
copy_oom_score_adj(clone_flags, p);
return p;
bad_fork_cancel_cgroup:
spin_unlock(&current->sighand->siglock);
write_unlock_irq(&tasklist_lock);
cgroup_cancel_fork(p);
bad_fork_cgroup_threadgroup_change_end:
cgroup_threadgroup_change_end(current);
bad_fork_put_pidfd:
if (clone_flags & CLONE_PIDFD) {
fput(pidfile);
put_unused_fd(pidfd);
}
bad_fork_free_pid:
if (pid != &init_struct_pid)
free_pid(pid);
bad_fork_cleanup_thread:
exit_thread(p);
bad_fork_cleanup_io:
if (p->io_context)
exit_io_context(p);
bad_fork_cleanup_namespaces:
exit_task_namespaces(p);
bad_fork_cleanup_mm:
if (p->mm) {
mm_clear_owner(p->mm, p);
mmput(p->mm);
}
bad_fork_cleanup_signal:
if (!(clone_flags & CLONE_THREAD))
free_signal_struct(p->signal);
bad_fork_cleanup_sighand:
__cleanup_sighand(p->sighand);
bad_fork_cleanup_fs:
exit_fs(p); /* blocking */
bad_fork_cleanup_files:
exit_files(p); /* blocking */
bad_fork_cleanup_semundo:
exit_sem(p);
bad_fork_cleanup_security:
security_task_free(p);
bad_fork_cleanup_audit:
audit_free(p);
bad_fork_cleanup_perf:
perf_event_free_task(p);
bad_fork_cleanup_policy:
lockdep_free_task(p);
free_task_load_ptrs(p);
#ifdef CONFIG_NUMA
mpol_put(p->mempolicy);
bad_fork_cleanup_threadgroup_lock:
#endif
delayacct_tsk_free(p);
bad_fork_cleanup_count:
atomic_dec(&p->cred->user->processes);
exit_creds(p);
bad_fork_free:
p->state = TASK_DEAD;
put_task_stack(p);
delayed_free_task(p);
fork_out:
spin_lock_irq(&current->sighand->siglock);
hlist_del_init(&delayed.node);
spin_unlock_irq(&current->sighand->siglock);
return ERR_PTR(retval);
}
static inline void init_idle_pids(struct task_struct *idle)
{
enum pid_type type;
for (type = PIDTYPE_PID; type < PIDTYPE_MAX; ++type) {
INIT_HLIST_NODE(&idle->pid_links[type]); /* not really needed */
init_task_pid(idle, type, &init_struct_pid);
}
}
struct task_struct *fork_idle(int cpu)
{
struct task_struct *task;
struct kernel_clone_args args = {
.flags = CLONE_VM,
};
task = copy_process(&init_struct_pid, 0, cpu_to_node(cpu), &args);
if (!IS_ERR(task)) {
init_idle_pids(task);
init_idle(task, cpu);
}
return task;
}
/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*
* args->exit_signal is expected to be checked for sanity by the caller.
*/
long _do_fork(struct kernel_clone_args *args)
{
u64 clone_flags = args->flags;
struct completion vfork;
struct pid *pid;
struct task_struct *p;
int trace = 0;
long nr;
/*
* Determine whether and which event to report to ptracer. When
* called from kernel_thread or CLONE_UNTRACED is explicitly
* requested, no event is reported; otherwise, report if the event
* for the type of forking is enabled.
*/
if (!(clone_flags & CLONE_UNTRACED)) {
if (clone_flags & CLONE_VFORK)
trace = PTRACE_EVENT_VFORK;
else if (args->exit_signal != SIGCHLD)
trace = PTRACE_EVENT_CLONE;
else
trace = PTRACE_EVENT_FORK;
if (likely(!ptrace_event_enabled(current, trace)))
trace = 0;
}
p = copy_process(NULL, trace, NUMA_NO_NODE, args);
add_latent_entropy();
if (IS_ERR(p))
return PTR_ERR(p);
cpufreq_task_times_alloc(p);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
trace_sched_process_fork(current, p);
pid = get_task_pid(p, PIDTYPE_PID);
nr = pid_vnr(pid);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, args->parent_tid);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
get_task_struct(p);
}
wake_up_new_task(p);
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
ptrace_event_pid(trace, pid);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
ptrace_event_pid(PTRACE_EVENT_VFORK_DONE, pid);
}
put_pid(pid);
return nr;
}
bool legacy_clone_args_valid(const struct kernel_clone_args *kargs)
{
/* clone(CLONE_PIDFD) uses parent_tidptr to return a pidfd */
if ((kargs->flags & CLONE_PIDFD) &&
(kargs->flags & CLONE_PARENT_SETTID))
return false;
return true;
}
#ifndef CONFIG_HAVE_COPY_THREAD_TLS
/* For compatibility with architectures that call do_fork directly rather than
* using the syscall entry points below. */
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct kernel_clone_args args = {
.flags = (lower_32_bits(clone_flags) & ~CSIGNAL),
.pidfd = parent_tidptr,
.child_tid = child_tidptr,
.parent_tid = parent_tidptr,
.exit_signal = (lower_32_bits(clone_flags) & CSIGNAL),
.stack = stack_start,
.stack_size = stack_size,
};
if (!legacy_clone_args_valid(&args))
return -EINVAL;
return _do_fork(&args);
}
#endif
/*
* Create a kernel thread.
*/
pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
{
struct kernel_clone_args args = {
.flags = ((lower_32_bits(flags) | CLONE_VM |
CLONE_UNTRACED) & ~CSIGNAL),
.exit_signal = (lower_32_bits(flags) & CSIGNAL),
.stack = (unsigned long)fn,
.stack_size = (unsigned long)arg,
};
return _do_fork(&args);
}
#ifdef __ARCH_WANT_SYS_FORK
SYSCALL_DEFINE0(fork)
{
#ifdef CONFIG_MMU
struct kernel_clone_args args = {
.exit_signal = SIGCHLD,
};
return _do_fork(&args);
#else
/* can not support in nommu mode */
return -EINVAL;
#endif
}
#endif
#ifdef __ARCH_WANT_SYS_VFORK
SYSCALL_DEFINE0(vfork)
{
struct kernel_clone_args args = {
.flags = CLONE_VFORK | CLONE_VM,
.exit_signal = SIGCHLD,
};
return _do_fork(&args);
}
#endif
#ifdef __ARCH_WANT_SYS_CLONE
#ifdef CONFIG_CLONE_BACKWARDS
SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
int __user *, parent_tidptr,
unsigned long, tls,
int __user *, child_tidptr)
#elif defined(CONFIG_CLONE_BACKWARDS2)
SYSCALL_DEFINE5(clone, unsigned long, newsp, unsigned long, clone_flags,
int __user *, parent_tidptr,
int __user *, child_tidptr,
unsigned long, tls)
#elif defined(CONFIG_CLONE_BACKWARDS3)
SYSCALL_DEFINE6(clone, unsigned long, clone_flags, unsigned long, newsp,
int, stack_size,
int __user *, parent_tidptr,
int __user *, child_tidptr,
unsigned long, tls)
#else
SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
int __user *, parent_tidptr,
int __user *, child_tidptr,
unsigned long, tls)
#endif
{
struct kernel_clone_args args = {
.flags = (lower_32_bits(clone_flags) & ~CSIGNAL),
.pidfd = parent_tidptr,
.child_tid = child_tidptr,
.parent_tid = parent_tidptr,
.exit_signal = (lower_32_bits(clone_flags) & CSIGNAL),
.stack = newsp,
.tls = tls,
};
if (!legacy_clone_args_valid(&args))
return -EINVAL;
return _do_fork(&args);
}
#endif
#ifdef __ARCH_WANT_SYS_CLONE3
/*
* copy_thread implementations handle CLONE_SETTLS by reading the TLS value from
* the registers containing the syscall arguments for clone. This doesn't work
* with clone3 since the TLS value is passed in clone_args instead.
*/
#ifndef CONFIG_HAVE_COPY_THREAD_TLS
#error clone3 requires copy_thread_tls support in arch
#endif
noinline static int copy_clone_args_from_user(struct kernel_clone_args *kargs,
struct clone_args __user *uargs,
size_t usize)
{
int err;
struct clone_args args;
if (unlikely(usize > PAGE_SIZE))
return -E2BIG;
if (unlikely(usize < CLONE_ARGS_SIZE_VER0))
return -EINVAL;
err = copy_struct_from_user(&args, sizeof(args), uargs, usize);
if (err)
return err;
/*
* Verify that higher 32bits of exit_signal are unset and that
* it is a valid signal
*/
if (unlikely((args.exit_signal & ~((u64)CSIGNAL)) ||
!valid_signal(args.exit_signal)))
return -EINVAL;
*kargs = (struct kernel_clone_args){
.flags = args.flags,
.pidfd = u64_to_user_ptr(args.pidfd),
.child_tid = u64_to_user_ptr(args.child_tid),
.parent_tid = u64_to_user_ptr(args.parent_tid),
.exit_signal = args.exit_signal,
.stack = args.stack,
.stack_size = args.stack_size,
.tls = args.tls,
};
return 0;
}
/**
* clone3_stack_valid - check and prepare stack
* @kargs: kernel clone args
*
* Verify that the stack arguments userspace gave us are sane.
* In addition, set the stack direction for userspace since it's easy for us to
* determine.
*/
static inline bool clone3_stack_valid(struct kernel_clone_args *kargs)
{
if (kargs->stack == 0) {
if (kargs->stack_size > 0)
return false;
} else {
if (kargs->stack_size == 0)
return false;
if (!access_ok((void __user *)kargs->stack, kargs->stack_size))
return false;
#if !defined(CONFIG_STACK_GROWSUP) && !defined(CONFIG_IA64)
kargs->stack += kargs->stack_size;
#endif
}
return true;
}
static bool clone3_args_valid(struct kernel_clone_args *kargs)
{
/*
* All lower bits of the flag word are taken.
* Verify that no other unknown flags are passed along.
*/
if (kargs->flags & ~CLONE_LEGACY_FLAGS)
return false;
/*
* - make the CLONE_DETACHED bit reuseable for clone3
* - make the CSIGNAL bits reuseable for clone3
*/
if (kargs->flags & (CLONE_DETACHED | CSIGNAL))
return false;
if ((kargs->flags & (CLONE_THREAD | CLONE_PARENT)) &&
kargs->exit_signal)
return false;
if (!clone3_stack_valid(kargs))
return false;
return true;
}
/**
* clone3 - create a new process with specific properties
* @uargs: argument structure
* @size: size of @uargs
*
* clone3() is the extensible successor to clone()/clone2().
* It takes a struct as argument that is versioned by its size.
*
* Return: On success, a positive PID for the child process.
* On error, a negative errno number.
*/
SYSCALL_DEFINE2(clone3, struct clone_args __user *, uargs, size_t, size)
{
int err;
struct kernel_clone_args kargs;
err = copy_clone_args_from_user(&kargs, uargs, size);
if (err)
return err;
if (!clone3_args_valid(&kargs))
return -EINVAL;
return _do_fork(&kargs);
}
#endif
void walk_process_tree(struct task_struct *top, proc_visitor visitor, void *data)
{
struct task_struct *leader, *parent, *child;
int res;
read_lock(&tasklist_lock);
leader = top = top->group_leader;
down:
for_each_thread(leader, parent) {
list_for_each_entry(child, &parent->children, sibling) {
res = visitor(child, data);
if (res) {
if (res < 0)
goto out;
leader = child;
goto down;
}
up:
;
}
}
if (leader != top) {
child = leader;
parent = child->real_parent;
leader = parent->group_leader;
goto up;
}
out:
read_unlock(&tasklist_lock);
}
#ifndef ARCH_MIN_MMSTRUCT_ALIGN
#define ARCH_MIN_MMSTRUCT_ALIGN 0
#endif
static void sighand_ctor(void *data)
{
struct sighand_struct *sighand = data;
spin_lock_init(&sighand->siglock);
init_waitqueue_head(&sighand->signalfd_wqh);
}
void __init mm_cache_init(void)
{
unsigned int mm_size;
/*
* The mm_cpumask is located at the end of mm_struct, and is
* dynamically sized based on the maximum CPU number this system
* can have, taking hotplug into account (nr_cpu_ids).
*/
mm_size = sizeof(struct mm_struct) + cpumask_size();
mm_cachep = kmem_cache_create_usercopy("mm_struct",
mm_size, ARCH_MIN_MMSTRUCT_ALIGN,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
offsetof(struct mm_struct, saved_auxv),
sizeof_field(struct mm_struct, saved_auxv),
NULL);
}
void __init proc_caches_init(void)
{
sighand_cachep = kmem_cache_create("sighand_cache",
sizeof(struct sighand_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
SLAB_ACCOUNT, sighand_ctor);
signal_cachep = kmem_cache_create("signal_cache",
sizeof(struct signal_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
NULL);
files_cachep = kmem_cache_create("files_cache",
sizeof(struct files_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
NULL);
fs_cachep = kmem_cache_create("fs_cache",
sizeof(struct fs_struct), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
NULL);
vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT);
mmap_init();
nsproxy_cache_init();
}
/*
* Check constraints on flags passed to the unshare system call.
*/
static int check_unshare_flags(unsigned long unshare_flags)
{
if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND|
CLONE_VM|CLONE_FILES|CLONE_SYSVSEM|
CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET|
CLONE_NEWUSER|CLONE_NEWPID|CLONE_NEWCGROUP))
return -EINVAL;
/*
* Not implemented, but pretend it works if there is nothing
* to unshare. Note that unsharing the address space or the
* signal handlers also need to unshare the signal queues (aka
* CLONE_THREAD).
*/
if (unshare_flags & (CLONE_THREAD | CLONE_SIGHAND | CLONE_VM)) {
if (!thread_group_empty(current))
return -EINVAL;
}
if (unshare_flags & (CLONE_SIGHAND | CLONE_VM)) {
if (refcount_read(&current->sighand->count) > 1)
return -EINVAL;
}
if (unshare_flags & CLONE_VM) {
if (!current_is_single_threaded())
return -EINVAL;
}
return 0;
}
/*
* Unshare the filesystem structure if it is being shared
*/
static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
{
struct fs_struct *fs = current->fs;
if (!(unshare_flags & CLONE_FS) || !fs)
return 0;
/* don't need lock here; in the worst case we'll do useless copy */
if (fs->users == 1)
return 0;
*new_fsp = copy_fs_struct(fs);
if (!*new_fsp)
return -ENOMEM;
return 0;
}
/*
* Unshare file descriptor table if it is being shared
*/
static int unshare_fd(unsigned long unshare_flags, struct files_struct **new_fdp)
{
struct files_struct *fd = current->files;
int error = 0;
if ((unshare_flags & CLONE_FILES) &&
(fd && atomic_read(&fd->count) > 1)) {
*new_fdp = dup_fd(fd, &error);
if (!*new_fdp)
return error;
}
return 0;
}
/*
* unshare allows a process to 'unshare' part of the process
* context which was originally shared using clone. copy_*
* functions used by do_fork() cannot be used here directly
* because they modify an inactive task_struct that is being
* constructed. Here we are modifying the current, active,
* task_struct.
*/
int ksys_unshare(unsigned long unshare_flags)
{
struct fs_struct *fs, *new_fs = NULL;
struct files_struct *fd, *new_fd = NULL;
struct cred *new_cred = NULL;
struct nsproxy *new_nsproxy = NULL;
int do_sysvsem = 0;
int err;
/*
* If unsharing a user namespace must also unshare the thread group
* and unshare the filesystem root and working directories.
*/
if (unshare_flags & CLONE_NEWUSER)
unshare_flags |= CLONE_THREAD | CLONE_FS;
/*
* If unsharing vm, must also unshare signal handlers.
*/
if (unshare_flags & CLONE_VM)
unshare_flags |= CLONE_SIGHAND;
/*
* If unsharing a signal handlers, must also unshare the signal queues.
*/
if (unshare_flags & CLONE_SIGHAND)
unshare_flags |= CLONE_THREAD;
/*
* If unsharing namespace, must also unshare filesystem information.
*/
if (unshare_flags & CLONE_NEWNS)
unshare_flags |= CLONE_FS;
err = check_unshare_flags(unshare_flags);
if (err)
goto bad_unshare_out;
/*
* CLONE_NEWIPC must also detach from the undolist: after switching
* to a new ipc namespace, the semaphore arrays from the old
* namespace are unreachable.
*/
if (unshare_flags & (CLONE_NEWIPC|CLONE_SYSVSEM))
do_sysvsem = 1;
err = unshare_fs(unshare_flags, &new_fs);
if (err)
goto bad_unshare_out;
err = unshare_fd(unshare_flags, &new_fd);
if (err)
goto bad_unshare_cleanup_fs;
err = unshare_userns(unshare_flags, &new_cred);
if (err)
goto bad_unshare_cleanup_fd;
err = unshare_nsproxy_namespaces(unshare_flags, &new_nsproxy,
new_cred, new_fs);
if (err)
goto bad_unshare_cleanup_cred;
if (new_fs || new_fd || do_sysvsem || new_cred || new_nsproxy) {
if (do_sysvsem) {
/*
* CLONE_SYSVSEM is equivalent to sys_exit().
*/
exit_sem(current);
}
if (unshare_flags & CLONE_NEWIPC) {
/* Orphan segments in old ns (see sem above). */
exit_shm(current);
shm_init_task(current);
}
if (new_nsproxy)
switch_task_namespaces(current, new_nsproxy);
task_lock(current);
if (new_fs) {
fs = current->fs;
spin_lock(&fs->lock);
current->fs = new_fs;
if (--fs->users)
new_fs = NULL;
else
new_fs = fs;
spin_unlock(&fs->lock);
}
if (new_fd) {
fd = current->files;
current->files = new_fd;
new_fd = fd;
}
task_unlock(current);
if (new_cred) {
/* Install the new user namespace */
commit_creds(new_cred);
new_cred = NULL;
}
}
perf_event_namespaces(current);
bad_unshare_cleanup_cred:
if (new_cred)
put_cred(new_cred);
bad_unshare_cleanup_fd:
if (new_fd)
put_files_struct(new_fd);
bad_unshare_cleanup_fs:
if (new_fs)
free_fs_struct(new_fs);
bad_unshare_out:
return err;
}
SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
{
return ksys_unshare(unshare_flags);
}
/*
* Helper to unshare the files of the current task.
* We don't want to expose copy_files internals to
* the exec layer of the kernel.
*/
int unshare_files(struct files_struct **displaced)
{
struct task_struct *task = current;
struct files_struct *copy = NULL;
int error;
error = unshare_fd(CLONE_FILES, &copy);
if (error || !copy) {
*displaced = NULL;
return error;
}
*displaced = task->files;
task_lock(task);
task->files = copy;
task_unlock(task);
return 0;
}
int sysctl_max_threads(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table t;
int ret;
int threads = max_threads;
int min = 1;
int max = MAX_THREADS;
t = *table;
t.data = &threads;
t.extra1 = &min;
t.extra2 = &max;
ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
if (ret || !write)
return ret;
max_threads = threads;
return 0;
}