Files
Greg Kroah-Hartman 2d76dea417 Merge 4.19.323 into android-4.19-stable
Changes in 4.19.323
	staging: iio: frequency: ad9833: Get frequency value statically
	staging: iio: frequency: ad9833: Load clock using clock framework
	staging: iio: frequency: ad9834: Validate frequency parameter value
	usbnet: ipheth: fix carrier detection in modes 1 and 4
	net: ethernet: use ip_hdrlen() instead of bit shift
	net: phy: vitesse: repair vsc73xx autonegotiation
	scripts: kconfig: merge_config: config files: add a trailing newline
	arm64: dts: rockchip: override BIOS_DISABLE signal via GPIO hog on RK3399 Puma
	net/mlx5: Update the list of the PCI supported devices
	net: ftgmac100: Enable TX interrupt to avoid TX timeout
	net: dpaa: Pad packets to ETH_ZLEN
	soundwire: stream: Revert "soundwire: stream: fix programming slave ports for non-continous port maps"
	selftests/vm: remove call to ksft_set_plan()
	selftests/kcmp: remove call to ksft_set_plan()
	ASoC: allow module autoloading for table db1200_pids
	pinctrl: at91: make it work with current gpiolib
	microblaze: don't treat zero reserved memory regions as error
	net: ftgmac100: Ensure tx descriptor updates are visible
	wifi: iwlwifi: mvm: fix iwl_mvm_max_scan_ie_fw_cmd_room()
	wifi: iwlwifi: mvm: don't wait for tx queues if firmware is dead
	ASoC: tda7419: fix module autoloading
	spi: bcm63xx: Enable module autoloading
	x86/hyperv: Set X86_FEATURE_TSC_KNOWN_FREQ when Hyper-V provides frequency
	ocfs2: add bounds checking to ocfs2_xattr_find_entry()
	ocfs2: strict bound check before memcmp in ocfs2_xattr_find_entry()
	gpio: prevent potential speculation leaks in gpio_device_get_desc()
	USB: serial: pl2303: add device id for Macrosilicon MS3020
	ACPI: PMIC: Remove unneeded check in tps68470_pmic_opregion_probe()
	wifi: ath9k: fix parameter check in ath9k_init_debug()
	wifi: ath9k: Remove error checks when creating debugfs entries
	netfilter: nf_tables: elements with timeout below CONFIG_HZ never expire
	wifi: cfg80211: fix UBSAN noise in cfg80211_wext_siwscan()
	wifi: cfg80211: fix two more possible UBSAN-detected off-by-one errors
	wifi: mac80211: use two-phase skb reclamation in ieee80211_do_stop()
	can: bcm: Clear bo->bcm_proc_read after remove_proc_entry().
	Bluetooth: btusb: Fix not handling ZPL/short-transfer
	block, bfq: fix possible UAF for bfqq->bic with merge chain
	block, bfq: choose the last bfqq from merge chain in bfq_setup_cooperator()
	block, bfq: don't break merge chain in bfq_split_bfqq()
	spi: ppc4xx: handle irq_of_parse_and_map() errors
	spi: ppc4xx: Avoid returning 0 when failed to parse and map IRQ
	ARM: versatile: fix OF node leak in CPUs prepare
	reset: berlin: fix OF node leak in probe() error path
	clocksource/drivers/qcom: Add missing iounmap() on errors in msm_dt_timer_init()
	hwmon: (max16065) Fix overflows seen when writing limits
	mtd: slram: insert break after errors in parsing the map
	hwmon: (ntc_thermistor) fix module autoloading
	power: supply: max17042_battery: Fix SOC threshold calc w/ no current sense
	fbdev: hpfb: Fix an error handling path in hpfb_dio_probe()
	drm/stm: Fix an error handling path in stm_drm_platform_probe()
	drm/amd: fix typo
	drm/amdgpu: Replace one-element array with flexible-array member
	drm/amdgpu: properly handle vbios fake edid sizing
	drm/radeon: Replace one-element array with flexible-array member
	drm/radeon: properly handle vbios fake edid sizing
	drm/rockchip: vop: Allow 4096px width scaling
	drm/radeon/evergreen_cs: fix int overflow errors in cs track offsets
	jfs: fix out-of-bounds in dbNextAG() and diAlloc()
	drm/msm/a5xx: properly clear preemption records on resume
	drm/msm/a5xx: fix races in preemption evaluation stage
	ipmi: docs: don't advertise deprecated sysfs entries
	drm/msm: fix %s null argument error
	xen: use correct end address of kernel for conflict checking
	xen/swiotlb: simplify range_straddles_page_boundary()
	xen/swiotlb: add alignment check for dma buffers
	selftests/bpf: Fix error compiling test_lru_map.c
	xz: cleanup CRC32 edits from 2018
	kthread: add kthread_work tracepoints
	kthread: fix task state in kthread worker if being frozen
	jbd2: introduce/export functions jbd2_journal_submit|finish_inode_data_buffers()
	ext4: clear EXT4_GROUP_INFO_WAS_TRIMMED_BIT even mount with discard
	smackfs: Use rcu_assign_pointer() to ensure safe assignment in smk_set_cipso
	ext4: avoid negative min_clusters in find_group_orlov()
	ext4: return error on ext4_find_inline_entry
	ext4: avoid OOB when system.data xattr changes underneath the filesystem
	nilfs2: fix potential null-ptr-deref in nilfs_btree_insert()
	nilfs2: determine empty node blocks as corrupted
	nilfs2: fix potential oob read in nilfs_btree_check_delete()
	perf sched timehist: Fix missing free of session in perf_sched__timehist()
	perf sched timehist: Fixed timestamp error when unable to confirm event sched_in time
	perf time-utils: Fix 32-bit nsec parsing
	clk: rockchip: Set parent rate for DCLK_VOP clock on RK3228
	drivers: media: dvb-frontends/rtl2832: fix an out-of-bounds write error
	drivers: media: dvb-frontends/rtl2830: fix an out-of-bounds write error
	PCI: xilinx-nwl: Fix register misspelling
	RDMA/iwcm: Fix WARNING:at_kernel/workqueue.c:#check_flush_dependency
	pinctrl: single: fix missing error code in pcs_probe()
	clk: ti: dra7-atl: Fix leak of of_nodes
	pinctrl: mvebu: Fix devinit_dove_pinctrl_probe function
	RDMA/cxgb4: Added NULL check for lookup_atid
	ntb: intel: Fix the NULL vs IS_ERR() bug for debugfs_create_dir()
	nfsd: call cache_put if xdr_reserve_space returns NULL
	f2fs: enhance to update i_mode and acl atomically in f2fs_setattr()
	f2fs: fix typo
	f2fs: fix to update i_ctime in __f2fs_setxattr()
	f2fs: remove unneeded check condition in __f2fs_setxattr()
	f2fs: reduce expensive checkpoint trigger frequency
	coresight: tmc: sg: Do not leak sg_table
	netfilter: nf_reject_ipv6: fix nf_reject_ip6_tcphdr_put()
	net: seeq: Fix use after free vulnerability in ether3 Driver Due to Race Condition
	tcp: introduce tcp_skb_timestamp_us() helper
	tcp: check skb is non-NULL in tcp_rto_delta_us()
	net: qrtr: Update packets cloning when broadcasting
	netfilter: ctnetlink: compile ctnetlink_label_size with CONFIG_NF_CONNTRACK_EVENTS
	crypto: aead,cipher - zeroize key buffer after use
	Remove *.orig pattern from .gitignore
	soc: versatile: integrator: fix OF node leak in probe() error path
	USB: appledisplay: close race between probe and completion handler
	USB: misc: cypress_cy7c63: check for short transfer
	firmware_loader: Block path traversal
	tty: rp2: Fix reset with non forgiving PCIe host bridges
	drbd: Fix atomicity violation in drbd_uuid_set_bm()
	drbd: Add NULL check for net_conf to prevent dereference in state validation
	ACPI: sysfs: validate return type of _STR method
	f2fs: prevent possible int overflow in dir_block_index()
	f2fs: avoid potential int overflow in sanity_check_area_boundary()
	vfs: fix race between evice_inodes() and find_inode()&iput()
	fs: Fix file_set_fowner LSM hook inconsistencies
	nfs: fix memory leak in error path of nfs4_do_reclaim
	PCI: xilinx-nwl: Use irq_data_get_irq_chip_data()
	PCI: xilinx-nwl: Fix off-by-one in INTx IRQ handler
	soc: versatile: realview: fix memory leak during device remove
	soc: versatile: realview: fix soc_dev leak during device remove
	usb: yurex: Replace snprintf() with the safer scnprintf() variant
	USB: misc: yurex: fix race between read and write
	pps: remove usage of the deprecated ida_simple_xx() API
	pps: add an error check in parport_attach
	i2c: aspeed: Update the stop sw state when the bus recovery occurs
	i2c: isch: Add missed 'else'
	usb: yurex: Fix inconsistent locking bug in yurex_read()
	mailbox: rockchip: fix a typo in module autoloading
	mailbox: bcm2835: Fix timeout during suspend mode
	ceph: remove the incorrect Fw reference check when dirtying pages
	netfilter: uapi: NFTA_FLOWTABLE_HOOK is NLA_NESTED
	netfilter: nf_tables: prevent nf_skb_duplicated corruption
	r8152: Factor out OOB link list waits
	net: ethernet: lantiq_etop: fix memory disclosure
	net: avoid potential underflow in qdisc_pkt_len_init() with UFO
	net: add more sanity checks to qdisc_pkt_len_init()
	ipv4: ip_gre: Fix drops of small packets in ipgre_xmit
	sctp: set sk_state back to CLOSED if autobind fails in sctp_listen_start
	ALSA: hda/generic: Unconditionally prefer preferred_dacs pairs
	ALSA: hda/conexant: Fix conflicting quirk for System76 Pangolin
	f2fs: Require FMODE_WRITE for atomic write ioctls
	wifi: ath9k: fix possible integer overflow in ath9k_get_et_stats()
	wifi: ath9k_htc: Use __skb_set_length() for resetting urb before resubmit
	net: hisilicon: hip04: fix OF node leak in probe()
	net: hisilicon: hns_dsaf_mac: fix OF node leak in hns_mac_get_info()
	net: hisilicon: hns_mdio: fix OF node leak in probe()
	ACPICA: Fix memory leak if acpi_ps_get_next_namepath() fails
	ACPICA: Fix memory leak if acpi_ps_get_next_field() fails
	ACPI: EC: Do not release locks during operation region accesses
	ACPICA: check null return of ACPI_ALLOCATE_ZEROED() in acpi_db_convert_to_package()
	tipc: guard against string buffer overrun
	net: mvpp2: Increase size of queue_name buffer
	ipv4: Check !in_dev earlier for ioctl(SIOCSIFADDR).
	ipv4: Mask upper DSCP bits and ECN bits in NETLINK_FIB_LOOKUP family
	tcp: avoid reusing FIN_WAIT2 when trying to find port in connect() process
	ACPICA: iasl: handle empty connection_node
	wifi: mwifiex: Fix memcpy() field-spanning write warning in mwifiex_cmd_802_11_scan_ext()
	signal: Replace BUG_ON()s
	ALSA: asihpi: Fix potential OOB array access
	ALSA: hdsp: Break infinite MIDI input flush loop
	fbdev: pxafb: Fix possible use after free in pxafb_task()
	power: reset: brcmstb: Do not go into infinite loop if reset fails
	ata: sata_sil: Rename sil_blacklist to sil_quirks
	jfs: UBSAN: shift-out-of-bounds in dbFindBits
	jfs: Fix uaf in dbFreeBits
	jfs: check if leafidx greater than num leaves per dmap tree
	jfs: Fix uninit-value access of new_ea in ea_buffer
	drm/amd/display: Check stream before comparing them
	drm/amd/display: Fix index out of bounds in degamma hardware format translation
	drm/printer: Allow NULL data in devcoredump printer
	scsi: aacraid: Rearrange order of struct aac_srb_unit
	drm/radeon/r100: Handle unknown family in r100_cp_init_microcode()
	of/irq: Refer to actual buffer size in of_irq_parse_one()
	ext4: ext4_search_dir should return a proper error
	ext4: fix i_data_sem unlock order in ext4_ind_migrate()
	spi: s3c64xx: fix timeout counters in flush_fifo
	selftests: breakpoints: use remaining time to check if suspend succeed
	selftests: vDSO: fix vDSO symbols lookup for powerpc64
	i2c: xiic: Wait for TX empty to avoid missed TX NAKs
	spi: bcm63xx: Fix module autoloading
	perf/core: Fix small negative period being ignored
	parisc: Fix itlb miss handler for 64-bit programs
	ALSA: core: add isascii() check to card ID generator
	ext4: no need to continue when the number of entries is 1
	ext4: propagate errors from ext4_find_extent() in ext4_insert_range()
	ext4: fix incorrect tid assumption in __jbd2_log_wait_for_space()
	ext4: aovid use-after-free in ext4_ext_insert_extent()
	ext4: fix double brelse() the buffer of the extents path
	ext4: fix incorrect tid assumption in ext4_wait_for_tail_page_commit()
	parisc: Fix 64-bit userspace syscall path
	of/irq: Support #msi-cells=<0> in of_msi_get_domain
	jbd2: stop waiting for space when jbd2_cleanup_journal_tail() returns error
	ocfs2: fix the la space leak when unmounting an ocfs2 volume
	ocfs2: fix uninit-value in ocfs2_get_block()
	ocfs2: reserve space for inline xattr before attaching reflink tree
	ocfs2: cancel dqi_sync_work before freeing oinfo
	ocfs2: remove unreasonable unlock in ocfs2_read_blocks
	ocfs2: fix null-ptr-deref when journal load failed.
	ocfs2: fix possible null-ptr-deref in ocfs2_set_buffer_uptodate
	riscv: define ILLEGAL_POINTER_VALUE for 64bit
	aoe: fix the potential use-after-free problem in more places
	clk: rockchip: fix error for unknown clocks
	media: uapi/linux/cec.h: cec_msg_set_reply_to: zero flags
	media: venus: fix use after free bug in venus_remove due to race condition
	iio: magnetometer: ak8975: Fix reading for ak099xx sensors
	tomoyo: fallback to realpath if symlink's pathname does not exist
	Input: adp5589-keys - fix adp5589_gpio_get_value()
	btrfs: wait for fixup workers before stopping cleaner kthread during umount
	gpio: davinci: fix lazy disable
	ext4: avoid ext4_error()'s caused by ENOMEM in the truncate path
	ext4: fix slab-use-after-free in ext4_split_extent_at()
	ext4: update orig_path in ext4_find_extent()
	arm64: Add Cortex-715 CPU part definition
	arm64: cputype: Add Neoverse-N3 definitions
	arm64: errata: Expand speculative SSBS workaround once more
	uprobes: fix kernel info leak via "[uprobes]" vma
	nfsd: use ktime_get_seconds() for timestamps
	nfsd: fix delegation_blocked() to block correctly for at least 30 seconds
	rtc: at91sam9: drop platform_data support
	rtc: at91sam9: fix OF node leak in probe() error path
	ACPI: battery: Simplify battery hook locking
	ACPI: battery: Fix possible crash when unregistering a battery hook
	ext4: fix inode tree inconsistency caused by ENOMEM
	net: ethernet: cortina: Drop TSO support
	tracing: Remove precision vsnprintf() check from print event
	drm: Move drm_mode_setcrtc() local re-init to failure path
	drm/crtc: fix uninitialized variable use even harder
	virtio_console: fix misc probe bugs
	Input: synaptics-rmi4 - fix UAF of IRQ domain on driver removal
	bpf: Check percpu map value size first
	s390/facility: Disable compile time optimization for decompressor code
	s390/mm: Add cond_resched() to cmm_alloc/free_pages()
	ext4: nested locking for xattr inode
	s390/cpum_sf: Remove WARN_ON_ONCE statements
	ktest.pl: Avoid false positives with grub2 skip regex
	clk: bcm: bcm53573: fix OF node leak in init
	i2c: i801: Use a different adapter-name for IDF adapters
	PCI: Mark Creative Labs EMU20k2 INTx masking as broken
	media: videobuf2-core: clear memory related fields in __vb2_plane_dmabuf_put()
	usb: chipidea: udc: enable suspend interrupt after usb reset
	tools/iio: Add memory allocation failure check for trigger_name
	driver core: bus: Return -EIO instead of 0 when show/store invalid bus attribute
	fbdev: sisfb: Fix strbuf array overflow
	NFS: Remove print_overflow_msg()
	SUNRPC: Fix integer overflow in decode_rc_list()
	tcp: fix tcp_enter_recovery() to zero retrans_stamp when it's safe
	netfilter: br_netfilter: fix panic with metadata_dst skb
	Bluetooth: RFCOMM: FIX possible deadlock in rfcomm_sk_state_change
	gpio: aspeed: Add the flush write to ensure the write complete.
	clk: Add (devm_)clk_get_optional() functions
	clk: generalize devm_clk_get() a bit
	clk: Provide new devm_clk helpers for prepared and enabled clocks
	gpio: aspeed: Use devm_clk api to manage clock source
	igb: Do not bring the device up after non-fatal error
	net: ibm: emac: mal: fix wrong goto
	ppp: fix ppp_async_encode() illegal access
	net: ipv6: ensure we call ipv6_mc_down() at most once
	CDC-NCM: avoid overflow in sanity checking
	HID: plantronics: Workaround for an unexcepted opposite volume key
	Revert "usb: yurex: Replace snprintf() with the safer scnprintf() variant"
	usb: xhci: Fix problem with xhci resume from suspend
	usb: storage: ignore bogus device raised by JieLi BR21 USB sound chip
	net: Fix an unsafe loop on the list
	posix-clock: Fix missing timespec64 check in pc_clock_settime()
	arm64: probes: Remove broken LDR (literal) uprobe support
	arm64: probes: Fix simulate_ldr*_literal()
	PCI: Add function 0 DMA alias quirk for Glenfly Arise chip
	fat: fix uninitialized variable
	KVM: Fix a data race on last_boosted_vcpu in kvm_vcpu_on_spin()
	net: dsa: mv88e6xxx: Fix out-of-bound access
	s390/sclp_vt220: Convert newlines to CRLF instead of LFCR
	KVM: s390: Change virtual to physical address access in diag 0x258 handler
	x86/cpufeatures: Define X86_FEATURE_AMD_IBPB_RET
	drm/vmwgfx: Handle surface check failure correctly
	iio: dac: stm32-dac-core: add missing select REGMAP_MMIO in Kconfig
	iio: adc: ti-ads8688: add missing select IIO_(TRIGGERED_)BUFFER in Kconfig
	iio: hid-sensors: Fix an error handling path in _hid_sensor_set_report_latency()
	iio: light: opt3001: add missing full-scale range value
	Bluetooth: Remove debugfs directory on module init failure
	Bluetooth: btusb: Fix regression with fake CSR controllers 0a12:0001
	xhci: Fix incorrect stream context type macro
	USB: serial: option: add support for Quectel EG916Q-GL
	USB: serial: option: add Telit FN920C04 MBIM compositions
	parport: Proper fix for array out-of-bounds access
	x86/apic: Always explicitly disarm TSC-deadline timer
	nilfs2: propagate directory read errors from nilfs_find_entry()
	clk: Fix pointer casting to prevent oops in devm_clk_release()
	clk: Fix slab-out-of-bounds error in devm_clk_release()
	RDMA/bnxt_re: Fix incorrect AVID type in WQE structure
	RDMA/cxgb4: Fix RDMA_CM_EVENT_UNREACHABLE error for iWARP
	RDMA/bnxt_re: Return more meaningful error
	drm/msm/dsi: fix 32-bit signed integer extension in pclk_rate calculation
	macsec: don't increment counters for an unrelated SA
	net: ethernet: aeroflex: fix potential memory leak in greth_start_xmit_gbit()
	net: systemport: fix potential memory leak in bcm_sysport_xmit()
	usb: typec: altmode should keep reference to parent
	Bluetooth: bnep: fix wild-memory-access in proto_unregister
	arm64:uprobe fix the uprobe SWBP_INSN in big-endian
	arm64: probes: Fix uprobes for big-endian kernels
	KVM: s390: gaccess: Refactor gpa and length calculation
	KVM: s390: gaccess: Refactor access address range check
	KVM: s390: gaccess: Cleanup access to guest pages
	KVM: s390: gaccess: Check if guest address is in memslot
	udf: fix uninit-value use in udf_get_fileshortad
	jfs: Fix sanity check in dbMount
	net/sun3_82586: fix potential memory leak in sun3_82586_send_packet()
	be2net: fix potential memory leak in be_xmit()
	net: usb: usbnet: fix name regression
	posix-clock: posix-clock: Fix unbalanced locking in pc_clock_settime()
	ALSA: hda/realtek: Update default depop procedure
	drm/amd: Guard against bad data for ATIF ACPI method
	ACPI: button: Add DMI quirk for Samsung Galaxy Book2 to fix initial lid detection issue
	nilfs2: fix kernel bug due to missing clearing of buffer delay flag
	hv_netvsc: Fix VF namespace also in synthetic NIC NETDEV_REGISTER event
	selinux: improve error checking in sel_write_load()
	arm64/uprobes: change the uprobe_opcode_t typedef to fix the sparse warning
	xfrm: validate new SA's prefixlen using SA family when sel.family is unset
	usb: dwc3: remove generic PHY calibrate() calls
	usb: dwc3: Add splitdisable quirk for Hisilicon Kirin Soc
	usb: dwc3: core: Stop processing of pending events if controller is halted
	cgroup: Fix potential overflow issue when checking max_depth
	wifi: mac80211: skip non-uploaded keys in ieee80211_iter_keys
	gtp: simplify error handling code in 'gtp_encap_enable()'
	gtp: allow -1 to be specified as file description from userspace
	net/sched: stop qdisc_tree_reduce_backlog on TC_H_ROOT
	bpf: Fix out-of-bounds write in trie_get_next_key()
	net: support ip generic csum processing in skb_csum_hwoffload_help
	net: skip offload for NETIF_F_IPV6_CSUM if ipv6 header contains extension
	netfilter: nft_payload: sanitize offset and length before calling skb_checksum()
	firmware: arm_sdei: Fix the input parameter of cpuhp_remove_state()
	net: amd: mvme147: Fix probe banner message
	misc: sgi-gru: Don't disable preemption in GRU driver
	usbip: tools: Fix detach_port() invalid port error path
	usb: phy: Fix API devm_usb_put_phy() can not release the phy
	xhci: Fix Link TRB DMA in command ring stopped completion event
	Revert "driver core: Fix uevent_show() vs driver detach race"
	wifi: mac80211: do not pass a stopped vif to the driver in .get_txpower
	wifi: ath10k: Fix memory leak in management tx
	wifi: iwlegacy: Clear stale interrupts before resuming device
	nilfs2: fix potential deadlock with newly created symlinks
	ocfs2: pass u64 to ocfs2_truncate_inline maybe overflow
	nilfs2: fix kernel bug due to missing clearing of checked flag
	mm: shmem: fix data-race in shmem_getattr()
	vt: prevent kernel-infoleak in con_font_get()
	Linux 4.19.323

Change-Id: I2348f834187153067ab46b3b48b8fe7da9cee1f1
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
2024-11-09 11:24:17 +00:00

1315 lines
36 KiB
C

/* Kernel thread helper functions.
* Copyright (C) 2004 IBM Corporation, Rusty Russell.
*
* Creation is done via kthreadd, so that we get a clean environment
* even if we're invoked from userspace (think modprobe, hotplug cpu,
* etc.).
*/
#include <uapi/linux/sched/types.h>
#include <linux/sched.h>
#include <linux/sched/task.h>
#include <linux/kthread.h>
#include <linux/completion.h>
#include <linux/err.h>
#include <linux/cgroup.h>
#include <linux/cpuset.h>
#include <linux/unistd.h>
#include <linux/file.h>
#include <linux/export.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <linux/freezer.h>
#include <linux/ptrace.h>
#include <linux/uaccess.h>
#include <trace/events/sched.h>
static DEFINE_SPINLOCK(kthread_create_lock);
static LIST_HEAD(kthread_create_list);
struct task_struct *kthreadd_task;
struct kthread_create_info
{
/* Information passed to kthread() from kthreadd. */
int (*threadfn)(void *data);
void *data;
int node;
/* Result passed back to kthread_create() from kthreadd. */
struct task_struct *result;
struct completion *done;
struct list_head list;
};
struct kthread {
unsigned long flags;
unsigned int cpu;
void *data;
struct completion parked;
struct completion exited;
#ifdef CONFIG_BLK_CGROUP
struct cgroup_subsys_state *blkcg_css;
#endif
};
enum KTHREAD_BITS {
KTHREAD_IS_PER_CPU = 0,
KTHREAD_SHOULD_STOP,
KTHREAD_SHOULD_PARK,
};
static inline void set_kthread_struct(void *kthread)
{
/*
* We abuse ->set_child_tid to avoid the new member and because it
* can't be wrongly copied by copy_process(). We also rely on fact
* that the caller can't exec, so PF_KTHREAD can't be cleared.
*/
current->set_child_tid = (__force void __user *)kthread;
}
static inline struct kthread *to_kthread(struct task_struct *k)
{
WARN_ON(!(k->flags & PF_KTHREAD));
return (__force void *)k->set_child_tid;
}
void free_kthread_struct(struct task_struct *k)
{
struct kthread *kthread;
/*
* Can be NULL if this kthread was created by kernel_thread()
* or if kmalloc() in kthread() failed.
*/
kthread = to_kthread(k);
#ifdef CONFIG_BLK_CGROUP
WARN_ON_ONCE(kthread && kthread->blkcg_css);
#endif
kfree(kthread);
}
/**
* kthread_should_stop - should this kthread return now?
*
* When someone calls kthread_stop() on your kthread, it will be woken
* and this will return true. You should then return, and your return
* value will be passed through to kthread_stop().
*/
bool kthread_should_stop(void)
{
return test_bit(KTHREAD_SHOULD_STOP, &to_kthread(current)->flags);
}
EXPORT_SYMBOL(kthread_should_stop);
/**
* kthread_should_park - should this kthread park now?
*
* When someone calls kthread_park() on your kthread, it will be woken
* and this will return true. You should then do the necessary
* cleanup and call kthread_parkme()
*
* Similar to kthread_should_stop(), but this keeps the thread alive
* and in a park position. kthread_unpark() "restarts" the thread and
* calls the thread function again.
*/
bool kthread_should_park(void)
{
return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags);
}
EXPORT_SYMBOL_GPL(kthread_should_park);
/**
* kthread_freezable_should_stop - should this freezable kthread return now?
* @was_frozen: optional out parameter, indicates whether %current was frozen
*
* kthread_should_stop() for freezable kthreads, which will enter
* refrigerator if necessary. This function is safe from kthread_stop() /
* freezer deadlock and freezable kthreads should use this function instead
* of calling try_to_freeze() directly.
*/
bool kthread_freezable_should_stop(bool *was_frozen)
{
bool frozen = false;
might_sleep();
if (unlikely(freezing(current)))
frozen = __refrigerator(true);
if (was_frozen)
*was_frozen = frozen;
return kthread_should_stop();
}
EXPORT_SYMBOL_GPL(kthread_freezable_should_stop);
/**
* kthread_data - return data value specified on kthread creation
* @task: kthread task in question
*
* Return the data value specified when kthread @task was created.
* The caller is responsible for ensuring the validity of @task when
* calling this function.
*/
void *kthread_data(struct task_struct *task)
{
return to_kthread(task)->data;
}
/**
* kthread_probe_data - speculative version of kthread_data()
* @task: possible kthread task in question
*
* @task could be a kthread task. Return the data value specified when it
* was created if accessible. If @task isn't a kthread task or its data is
* inaccessible for any reason, %NULL is returned. This function requires
* that @task itself is safe to dereference.
*/
void *kthread_probe_data(struct task_struct *task)
{
struct kthread *kthread = to_kthread(task);
void *data = NULL;
probe_kernel_read(&data, &kthread->data, sizeof(data));
return data;
}
static void __kthread_parkme(struct kthread *self)
{
for (;;) {
/*
* TASK_PARKED is a special state; we must serialize against
* possible pending wakeups to avoid store-store collisions on
* task->state.
*
* Such a collision might possibly result in the task state
* changin from TASK_PARKED and us failing the
* wait_task_inactive() in kthread_park().
*/
set_special_state(TASK_PARKED);
if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
break;
/*
* Thread is going to call schedule(), do not preempt it,
* or the caller of kthread_park() may spend more time in
* wait_task_inactive().
*/
preempt_disable();
complete(&self->parked);
schedule_preempt_disabled();
preempt_enable();
}
__set_current_state(TASK_RUNNING);
}
void kthread_parkme(void)
{
__kthread_parkme(to_kthread(current));
}
EXPORT_SYMBOL_GPL(kthread_parkme);
static int kthread(void *_create)
{
/* Copy data: it's on kthread's stack */
struct kthread_create_info *create = _create;
int (*threadfn)(void *data) = create->threadfn;
void *data = create->data;
struct completion *done;
struct kthread *self;
int ret;
self = kzalloc(sizeof(*self), GFP_KERNEL);
set_kthread_struct(self);
/* If user was SIGKILLed, I release the structure. */
done = xchg(&create->done, NULL);
if (!done) {
kfree(create);
do_exit(-EINTR);
}
if (!self) {
create->result = ERR_PTR(-ENOMEM);
complete(done);
do_exit(-ENOMEM);
}
self->data = data;
init_completion(&self->exited);
init_completion(&self->parked);
current->vfork_done = &self->exited;
/* OK, tell user we're spawned, wait for stop or wakeup */
__set_current_state(TASK_UNINTERRUPTIBLE);
create->result = current;
/*
* Thread is going to call schedule(), do not preempt it,
* or the creator may spend more time in wait_task_inactive().
*/
preempt_disable();
complete(done);
schedule_preempt_disabled();
preempt_enable();
ret = -EINTR;
if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) {
cgroup_kthread_ready();
__kthread_parkme(self);
ret = threadfn(data);
}
do_exit(ret);
}
/* called from do_fork() to get node information for about to be created task */
int tsk_fork_get_node(struct task_struct *tsk)
{
#ifdef CONFIG_NUMA
if (tsk == kthreadd_task)
return tsk->pref_node_fork;
#endif
return NUMA_NO_NODE;
}
static void create_kthread(struct kthread_create_info *create)
{
int pid;
#ifdef CONFIG_NUMA
current->pref_node_fork = create->node;
#endif
/* We want our own signal handler (we take no signals by default). */
pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD);
if (pid < 0) {
/* If user was SIGKILLed, I release the structure. */
struct completion *done = xchg(&create->done, NULL);
if (!done) {
kfree(create);
return;
}
create->result = ERR_PTR(pid);
complete(done);
}
}
static __printf(4, 0)
struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
void *data, int node,
const char namefmt[],
va_list args)
{
DECLARE_COMPLETION_ONSTACK(done);
struct task_struct *task;
struct kthread_create_info *create = kmalloc(sizeof(*create),
GFP_KERNEL);
if (!create)
return ERR_PTR(-ENOMEM);
create->threadfn = threadfn;
create->data = data;
create->node = node;
create->done = &done;
spin_lock(&kthread_create_lock);
list_add_tail(&create->list, &kthread_create_list);
spin_unlock(&kthread_create_lock);
wake_up_process(kthreadd_task);
/*
* Wait for completion in killable state, for I might be chosen by
* the OOM killer while kthreadd is trying to allocate memory for
* new kernel thread.
*/
if (unlikely(wait_for_completion_killable(&done))) {
/*
* If I was SIGKILLed before kthreadd (or new kernel thread)
* calls complete(), leave the cleanup of this structure to
* that thread.
*/
if (xchg(&create->done, NULL))
return ERR_PTR(-EINTR);
/*
* kthreadd (or new kernel thread) will call complete()
* shortly.
*/
wait_for_completion(&done);
}
task = create->result;
if (!IS_ERR(task)) {
static const struct sched_param param = { .sched_priority = 0 };
char name[TASK_COMM_LEN];
/*
* task is already visible to other tasks, so updating
* COMM must be protected.
*/
vsnprintf(name, sizeof(name), namefmt, args);
set_task_comm(task, name);
/*
* root may have changed our (kthreadd's) priority or CPU mask.
* The kernel thread should not inherit these properties.
*/
sched_setscheduler_nocheck(task, SCHED_NORMAL, &param);
set_cpus_allowed_ptr(task, cpu_all_mask);
}
kfree(create);
return task;
}
/**
* kthread_create_on_node - create a kthread.
* @threadfn: the function to run until signal_pending(current).
* @data: data ptr for @threadfn.
* @node: task and thread structures for the thread are allocated on this node
* @namefmt: printf-style name for the thread.
*
* Description: This helper function creates and names a kernel
* thread. The thread will be stopped: use wake_up_process() to start
* it. See also kthread_run(). The new thread has SCHED_NORMAL policy and
* is affine to all CPUs.
*
* If thread is going to be bound on a particular cpu, give its node
* in @node, to get NUMA affinity for kthread stack, or else give NUMA_NO_NODE.
* When woken, the thread will run @threadfn() with @data as its
* argument. @threadfn() can either call do_exit() directly if it is a
* standalone thread for which no one will call kthread_stop(), or
* return when 'kthread_should_stop()' is true (which means
* kthread_stop() has been called). The return value should be zero
* or a negative error number; it will be passed to kthread_stop().
*
* Returns a task_struct or ERR_PTR(-ENOMEM) or ERR_PTR(-EINTR).
*/
struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
void *data, int node,
const char namefmt[],
...)
{
struct task_struct *task;
va_list args;
va_start(args, namefmt);
task = __kthread_create_on_node(threadfn, data, node, namefmt, args);
va_end(args);
return task;
}
EXPORT_SYMBOL(kthread_create_on_node);
static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, long state)
{
unsigned long flags;
if (!wait_task_inactive(p, state)) {
WARN_ON(1);
return;
}
/* It's safe because the task is inactive. */
raw_spin_lock_irqsave(&p->pi_lock, flags);
do_set_cpus_allowed(p, mask);
p->flags |= PF_NO_SETAFFINITY;
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
}
static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state)
{
__kthread_bind_mask(p, cpumask_of(cpu), state);
}
void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask)
{
__kthread_bind_mask(p, mask, TASK_UNINTERRUPTIBLE);
}
/**
* kthread_bind - bind a just-created kthread to a cpu.
* @p: thread created by kthread_create().
* @cpu: cpu (might not be online, must be possible) for @k to run on.
*
* Description: This function is equivalent to set_cpus_allowed(),
* except that @cpu doesn't need to be online, and the thread must be
* stopped (i.e., just returned from kthread_create()).
*/
void kthread_bind(struct task_struct *p, unsigned int cpu)
{
__kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE);
}
EXPORT_SYMBOL(kthread_bind);
/**
* kthread_create_on_cpu - Create a cpu bound kthread
* @threadfn: the function to run until signal_pending(current).
* @data: data ptr for @threadfn.
* @cpu: The cpu on which the thread should be bound,
* @namefmt: printf-style name for the thread. Format is restricted
* to "name.*%u". Code fills in cpu number.
*
* Description: This helper function creates and names a kernel thread
* The thread will be woken and put into park mode.
*/
struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data),
void *data, unsigned int cpu,
const char *namefmt)
{
struct task_struct *p;
p = kthread_create_on_node(threadfn, data, cpu_to_node(cpu), namefmt,
cpu);
if (IS_ERR(p))
return p;
kthread_bind(p, cpu);
/* CPU hotplug need to bind once again when unparking the thread. */
to_kthread(p)->cpu = cpu;
return p;
}
void kthread_set_per_cpu(struct task_struct *k, int cpu)
{
struct kthread *kthread = to_kthread(k);
if (!kthread)
return;
WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY));
if (cpu < 0) {
clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
return;
}
kthread->cpu = cpu;
set_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
}
bool kthread_is_per_cpu(struct task_struct *k)
{
struct kthread *kthread = to_kthread(k);
if (!kthread)
return false;
return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags);
}
/**
* kthread_unpark - unpark a thread created by kthread_create().
* @k: thread created by kthread_create().
*
* Sets kthread_should_park() for @k to return false, wakes it, and
* waits for it to return. If the thread is marked percpu then its
* bound to the cpu again.
*/
void kthread_unpark(struct task_struct *k)
{
struct kthread *kthread = to_kthread(k);
/*
* Newly created kthread was parked when the CPU was offline.
* The binding was lost and we need to set it again.
*/
if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
__kthread_bind(k, kthread->cpu, TASK_PARKED);
clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
/*
* __kthread_parkme() will either see !SHOULD_PARK or get the wakeup.
*/
wake_up_state(k, TASK_PARKED);
}
EXPORT_SYMBOL_GPL(kthread_unpark);
/**
* kthread_park - park a thread created by kthread_create().
* @k: thread created by kthread_create().
*
* Sets kthread_should_park() for @k to return true, wakes it, and
* waits for it to return. This can also be called after kthread_create()
* instead of calling wake_up_process(): the thread will park without
* calling threadfn().
*
* Returns 0 if the thread is parked, -ENOSYS if the thread exited.
* If called by the kthread itself just the park bit is set.
*/
int kthread_park(struct task_struct *k)
{
struct kthread *kthread = to_kthread(k);
if (WARN_ON(k->flags & PF_EXITING))
return -ENOSYS;
if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)))
return -EBUSY;
set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
if (k != current) {
wake_up_process(k);
/*
* Wait for __kthread_parkme() to complete(), this means we
* _will_ have TASK_PARKED and are about to call schedule().
*/
wait_for_completion(&kthread->parked);
/*
* Now wait for that schedule() to complete and the task to
* get scheduled out.
*/
WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED));
}
return 0;
}
EXPORT_SYMBOL_GPL(kthread_park);
/**
* kthread_stop - stop a thread created by kthread_create().
* @k: thread created by kthread_create().
*
* Sets kthread_should_stop() for @k to return true, wakes it, and
* waits for it to exit. This can also be called after kthread_create()
* instead of calling wake_up_process(): the thread will exit without
* calling threadfn().
*
* If threadfn() may call do_exit() itself, the caller must ensure
* task_struct can't go away.
*
* Returns the result of threadfn(), or %-EINTR if wake_up_process()
* was never called.
*/
int kthread_stop(struct task_struct *k)
{
struct kthread *kthread;
int ret;
trace_sched_kthread_stop(k);
get_task_struct(k);
kthread = to_kthread(k);
set_bit(KTHREAD_SHOULD_STOP, &kthread->flags);
kthread_unpark(k);
wake_up_process(k);
wait_for_completion(&kthread->exited);
ret = k->exit_code;
put_task_struct(k);
trace_sched_kthread_stop_ret(ret);
return ret;
}
EXPORT_SYMBOL(kthread_stop);
int kthreadd(void *unused)
{
struct task_struct *tsk = current;
/* Setup a clean context for our children to inherit. */
set_task_comm(tsk, "kthreadd");
ignore_signals(tsk);
set_cpus_allowed_ptr(tsk, cpu_all_mask);
set_mems_allowed(node_states[N_MEMORY]);
current->flags |= PF_NOFREEZE;
cgroup_init_kthreadd();
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
if (list_empty(&kthread_create_list))
schedule();
__set_current_state(TASK_RUNNING);
spin_lock(&kthread_create_lock);
while (!list_empty(&kthread_create_list)) {
struct kthread_create_info *create;
create = list_entry(kthread_create_list.next,
struct kthread_create_info, list);
list_del_init(&create->list);
spin_unlock(&kthread_create_lock);
create_kthread(create);
spin_lock(&kthread_create_lock);
}
spin_unlock(&kthread_create_lock);
}
return 0;
}
void __kthread_init_worker(struct kthread_worker *worker,
const char *name,
struct lock_class_key *key)
{
memset(worker, 0, sizeof(struct kthread_worker));
spin_lock_init(&worker->lock);
lockdep_set_class_and_name(&worker->lock, key, name);
INIT_LIST_HEAD(&worker->work_list);
INIT_LIST_HEAD(&worker->delayed_work_list);
}
EXPORT_SYMBOL_GPL(__kthread_init_worker);
/**
* kthread_worker_fn - kthread function to process kthread_worker
* @worker_ptr: pointer to initialized kthread_worker
*
* This function implements the main cycle of kthread worker. It processes
* work_list until it is stopped with kthread_stop(). It sleeps when the queue
* is empty.
*
* The works are not allowed to keep any locks, disable preemption or interrupts
* when they finish. There is defined a safe point for freezing when one work
* finishes and before a new one is started.
*
* Also the works must not be handled by more than one worker at the same time,
* see also kthread_queue_work().
*/
int kthread_worker_fn(void *worker_ptr)
{
struct kthread_worker *worker = worker_ptr;
struct kthread_work *work;
/*
* FIXME: Update the check and remove the assignment when all kthread
* worker users are created using kthread_create_worker*() functions.
*/
WARN_ON(worker->task && worker->task != current);
worker->task = current;
if (worker->flags & KTW_FREEZABLE)
set_freezable();
repeat:
set_current_state(TASK_INTERRUPTIBLE); /* mb paired w/ kthread_stop */
if (kthread_should_stop()) {
__set_current_state(TASK_RUNNING);
spin_lock_irq(&worker->lock);
worker->task = NULL;
spin_unlock_irq(&worker->lock);
return 0;
}
work = NULL;
spin_lock_irq(&worker->lock);
if (!list_empty(&worker->work_list)) {
work = list_first_entry(&worker->work_list,
struct kthread_work, node);
list_del_init(&work->node);
}
worker->current_work = work;
spin_unlock_irq(&worker->lock);
if (work) {
kthread_work_func_t func = work->func;
__set_current_state(TASK_RUNNING);
trace_sched_kthread_work_execute_start(work);
work->func(work);
/*
* Avoid dereferencing work after this point. The trace
* event only cares about the address.
*/
trace_sched_kthread_work_execute_end(work, func);
} else if (!freezing(current)) {
schedule();
} else {
/*
* Handle the case where the current remains
* TASK_INTERRUPTIBLE. try_to_freeze() expects
* the current to be TASK_RUNNING.
*/
__set_current_state(TASK_RUNNING);
}
try_to_freeze();
cond_resched();
goto repeat;
}
EXPORT_SYMBOL_GPL(kthread_worker_fn);
static __printf(3, 0) struct kthread_worker *
__kthread_create_worker(int cpu, unsigned int flags,
const char namefmt[], va_list args)
{
struct kthread_worker *worker;
struct task_struct *task;
int node = -1;
worker = kzalloc(sizeof(*worker), GFP_KERNEL);
if (!worker)
return ERR_PTR(-ENOMEM);
kthread_init_worker(worker);
if (cpu >= 0)
node = cpu_to_node(cpu);
task = __kthread_create_on_node(kthread_worker_fn, worker,
node, namefmt, args);
if (IS_ERR(task))
goto fail_task;
if (cpu >= 0)
kthread_bind(task, cpu);
worker->flags = flags;
worker->task = task;
wake_up_process(task);
return worker;
fail_task:
kfree(worker);
return ERR_CAST(task);
}
/**
* kthread_create_worker - create a kthread worker
* @flags: flags modifying the default behavior of the worker
* @namefmt: printf-style name for the kthread worker (task).
*
* Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM)
* when the needed structures could not get allocated, and ERR_PTR(-EINTR)
* when the worker was SIGKILLed.
*/
struct kthread_worker *
kthread_create_worker(unsigned int flags, const char namefmt[], ...)
{
struct kthread_worker *worker;
va_list args;
va_start(args, namefmt);
worker = __kthread_create_worker(-1, flags, namefmt, args);
va_end(args);
return worker;
}
EXPORT_SYMBOL(kthread_create_worker);
/**
* kthread_create_worker_on_cpu - create a kthread worker and bind it
* it to a given CPU and the associated NUMA node.
* @cpu: CPU number
* @flags: flags modifying the default behavior of the worker
* @namefmt: printf-style name for the kthread worker (task).
*
* Use a valid CPU number if you want to bind the kthread worker
* to the given CPU and the associated NUMA node.
*
* A good practice is to add the cpu number also into the worker name.
* For example, use kthread_create_worker_on_cpu(cpu, "helper/%d", cpu).
*
* Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM)
* when the needed structures could not get allocated, and ERR_PTR(-EINTR)
* when the worker was SIGKILLed.
*/
struct kthread_worker *
kthread_create_worker_on_cpu(int cpu, unsigned int flags,
const char namefmt[], ...)
{
struct kthread_worker *worker;
va_list args;
va_start(args, namefmt);
worker = __kthread_create_worker(cpu, flags, namefmt, args);
va_end(args);
return worker;
}
EXPORT_SYMBOL(kthread_create_worker_on_cpu);
/*
* Returns true when the work could not be queued at the moment.
* It happens when it is already pending in a worker list
* or when it is being cancelled.
*/
static inline bool queuing_blocked(struct kthread_worker *worker,
struct kthread_work *work)
{
lockdep_assert_held(&worker->lock);
return !list_empty(&work->node) || work->canceling;
}
static void kthread_insert_work_sanity_check(struct kthread_worker *worker,
struct kthread_work *work)
{
lockdep_assert_held(&worker->lock);
WARN_ON_ONCE(!list_empty(&work->node));
/* Do not use a work with >1 worker, see kthread_queue_work() */
WARN_ON_ONCE(work->worker && work->worker != worker);
}
/* insert @work before @pos in @worker */
static void kthread_insert_work(struct kthread_worker *worker,
struct kthread_work *work,
struct list_head *pos)
{
kthread_insert_work_sanity_check(worker, work);
trace_sched_kthread_work_queue_work(worker, work);
list_add_tail(&work->node, pos);
work->worker = worker;
if (!worker->current_work && likely(worker->task))
wake_up_process(worker->task);
}
/**
* kthread_queue_work - queue a kthread_work
* @worker: target kthread_worker
* @work: kthread_work to queue
*
* Queue @work to work processor @task for async execution. @task
* must have been created with kthread_worker_create(). Returns %true
* if @work was successfully queued, %false if it was already pending.
*
* Reinitialize the work if it needs to be used by another worker.
* For example, when the worker was stopped and started again.
*/
bool kthread_queue_work(struct kthread_worker *worker,
struct kthread_work *work)
{
bool ret = false;
unsigned long flags;
spin_lock_irqsave(&worker->lock, flags);
if (!queuing_blocked(worker, work)) {
kthread_insert_work(worker, work, &worker->work_list);
ret = true;
}
spin_unlock_irqrestore(&worker->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(kthread_queue_work);
/**
* kthread_delayed_work_timer_fn - callback that queues the associated kthread
* delayed work when the timer expires.
* @t: pointer to the expired timer
*
* The format of the function is defined by struct timer_list.
* It should have been called from irqsafe timer with irq already off.
*/
void kthread_delayed_work_timer_fn(struct timer_list *t)
{
struct kthread_delayed_work *dwork = from_timer(dwork, t, timer);
struct kthread_work *work = &dwork->work;
struct kthread_worker *worker = work->worker;
/*
* This might happen when a pending work is reinitialized.
* It means that it is used a wrong way.
*/
if (WARN_ON_ONCE(!worker))
return;
spin_lock(&worker->lock);
/* Work must not be used with >1 worker, see kthread_queue_work(). */
WARN_ON_ONCE(work->worker != worker);
/* Move the work from worker->delayed_work_list. */
WARN_ON_ONCE(list_empty(&work->node));
list_del_init(&work->node);
if (!work->canceling)
kthread_insert_work(worker, work, &worker->work_list);
spin_unlock(&worker->lock);
}
EXPORT_SYMBOL(kthread_delayed_work_timer_fn);
void __kthread_queue_delayed_work(struct kthread_worker *worker,
struct kthread_delayed_work *dwork,
unsigned long delay)
{
struct timer_list *timer = &dwork->timer;
struct kthread_work *work = &dwork->work;
WARN_ON_ONCE(timer->function != kthread_delayed_work_timer_fn);
/*
* If @delay is 0, queue @dwork->work immediately. This is for
* both optimization and correctness. The earliest @timer can
* expire is on the closest next tick and delayed_work users depend
* on that there's no such delay when @delay is 0.
*/
if (!delay) {
kthread_insert_work(worker, work, &worker->work_list);
return;
}
/* Be paranoid and try to detect possible races already now. */
kthread_insert_work_sanity_check(worker, work);
list_add(&work->node, &worker->delayed_work_list);
work->worker = worker;
timer->expires = jiffies + delay;
add_timer(timer);
}
/**
* kthread_queue_delayed_work - queue the associated kthread work
* after a delay.
* @worker: target kthread_worker
* @dwork: kthread_delayed_work to queue
* @delay: number of jiffies to wait before queuing
*
* If the work has not been pending it starts a timer that will queue
* the work after the given @delay. If @delay is zero, it queues the
* work immediately.
*
* Return: %false if the @work has already been pending. It means that
* either the timer was running or the work was queued. It returns %true
* otherwise.
*/
bool kthread_queue_delayed_work(struct kthread_worker *worker,
struct kthread_delayed_work *dwork,
unsigned long delay)
{
struct kthread_work *work = &dwork->work;
unsigned long flags;
bool ret = false;
spin_lock_irqsave(&worker->lock, flags);
if (!queuing_blocked(worker, work)) {
__kthread_queue_delayed_work(worker, dwork, delay);
ret = true;
}
spin_unlock_irqrestore(&worker->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(kthread_queue_delayed_work);
struct kthread_flush_work {
struct kthread_work work;
struct completion done;
};
static void kthread_flush_work_fn(struct kthread_work *work)
{
struct kthread_flush_work *fwork =
container_of(work, struct kthread_flush_work, work);
complete(&fwork->done);
}
/**
* kthread_flush_work - flush a kthread_work
* @work: work to flush
*
* If @work is queued or executing, wait for it to finish execution.
*/
void kthread_flush_work(struct kthread_work *work)
{
struct kthread_flush_work fwork = {
KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn),
COMPLETION_INITIALIZER_ONSTACK(fwork.done),
};
struct kthread_worker *worker;
bool noop = false;
worker = work->worker;
if (!worker)
return;
spin_lock_irq(&worker->lock);
/* Work must not be used with >1 worker, see kthread_queue_work(). */
WARN_ON_ONCE(work->worker != worker);
if (!list_empty(&work->node))
kthread_insert_work(worker, &fwork.work, work->node.next);
else if (worker->current_work == work)
kthread_insert_work(worker, &fwork.work,
worker->work_list.next);
else
noop = true;
spin_unlock_irq(&worker->lock);
if (!noop)
wait_for_completion(&fwork.done);
}
EXPORT_SYMBOL_GPL(kthread_flush_work);
/*
* Make sure that the timer is neither set nor running and could
* not manipulate the work list_head any longer.
*
* The function is called under worker->lock. The lock is temporary
* released but the timer can't be set again in the meantime.
*/
static void kthread_cancel_delayed_work_timer(struct kthread_work *work,
unsigned long *flags)
{
struct kthread_delayed_work *dwork =
container_of(work, struct kthread_delayed_work, work);
struct kthread_worker *worker = work->worker;
/*
* del_timer_sync() must be called to make sure that the timer
* callback is not running. The lock must be temporary released
* to avoid a deadlock with the callback. In the meantime,
* any queuing is blocked by setting the canceling counter.
*/
work->canceling++;
spin_unlock_irqrestore(&worker->lock, *flags);
del_timer_sync(&dwork->timer);
spin_lock_irqsave(&worker->lock, *flags);
work->canceling--;
}
/*
* This function removes the work from the worker queue.
*
* It is called under worker->lock. The caller must make sure that
* the timer used by delayed work is not running, e.g. by calling
* kthread_cancel_delayed_work_timer().
*
* The work might still be in use when this function finishes. See the
* current_work proceed by the worker.
*
* Return: %true if @work was pending and successfully canceled,
* %false if @work was not pending
*/
static bool __kthread_cancel_work(struct kthread_work *work)
{
/*
* Try to remove the work from a worker list. It might either
* be from worker->work_list or from worker->delayed_work_list.
*/
if (!list_empty(&work->node)) {
list_del_init(&work->node);
return true;
}
return false;
}
/**
* kthread_mod_delayed_work - modify delay of or queue a kthread delayed work
* @worker: kthread worker to use
* @dwork: kthread delayed work to queue
* @delay: number of jiffies to wait before queuing
*
* If @dwork is idle, equivalent to kthread_queue_delayed_work(). Otherwise,
* modify @dwork's timer so that it expires after @delay. If @delay is zero,
* @work is guaranteed to be queued immediately.
*
* Return: %true if @dwork was pending and its timer was modified,
* %false otherwise.
*
* A special case is when the work is being canceled in parallel.
* It might be caused either by the real kthread_cancel_delayed_work_sync()
* or yet another kthread_mod_delayed_work() call. We let the other command
* win and return %false here. The caller is supposed to synchronize these
* operations a reasonable way.
*
* This function is safe to call from any context including IRQ handler.
* See __kthread_cancel_work() and kthread_delayed_work_timer_fn()
* for details.
*/
bool kthread_mod_delayed_work(struct kthread_worker *worker,
struct kthread_delayed_work *dwork,
unsigned long delay)
{
struct kthread_work *work = &dwork->work;
unsigned long flags;
int ret = false;
spin_lock_irqsave(&worker->lock, flags);
/* Do not bother with canceling when never queued. */
if (!work->worker)
goto fast_queue;
/* Work must not be used with >1 worker, see kthread_queue_work() */
WARN_ON_ONCE(work->worker != worker);
/*
* Temporary cancel the work but do not fight with another command
* that is canceling the work as well.
*
* It is a bit tricky because of possible races with another
* mod_delayed_work() and cancel_delayed_work() callers.
*
* The timer must be canceled first because worker->lock is released
* when doing so. But the work can be removed from the queue (list)
* only when it can be queued again so that the return value can
* be used for reference counting.
*/
kthread_cancel_delayed_work_timer(work, &flags);
if (work->canceling)
goto out;
ret = __kthread_cancel_work(work);
fast_queue:
__kthread_queue_delayed_work(worker, dwork, delay);
out:
spin_unlock_irqrestore(&worker->lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(kthread_mod_delayed_work);
static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork)
{
struct kthread_worker *worker = work->worker;
unsigned long flags;
int ret = false;
if (!worker)
goto out;
spin_lock_irqsave(&worker->lock, flags);
/* Work must not be used with >1 worker, see kthread_queue_work(). */
WARN_ON_ONCE(work->worker != worker);
if (is_dwork)
kthread_cancel_delayed_work_timer(work, &flags);
ret = __kthread_cancel_work(work);
if (worker->current_work != work)
goto out_fast;
/*
* The work is in progress and we need to wait with the lock released.
* In the meantime, block any queuing by setting the canceling counter.
*/
work->canceling++;
spin_unlock_irqrestore(&worker->lock, flags);
kthread_flush_work(work);
spin_lock_irqsave(&worker->lock, flags);
work->canceling--;
out_fast:
spin_unlock_irqrestore(&worker->lock, flags);
out:
return ret;
}
/**
* kthread_cancel_work_sync - cancel a kthread work and wait for it to finish
* @work: the kthread work to cancel
*
* Cancel @work and wait for its execution to finish. This function
* can be used even if the work re-queues itself. On return from this
* function, @work is guaranteed to be not pending or executing on any CPU.
*
* kthread_cancel_work_sync(&delayed_work->work) must not be used for
* delayed_work's. Use kthread_cancel_delayed_work_sync() instead.
*
* The caller must ensure that the worker on which @work was last
* queued can't be destroyed before this function returns.
*
* Return: %true if @work was pending, %false otherwise.
*/
bool kthread_cancel_work_sync(struct kthread_work *work)
{
return __kthread_cancel_work_sync(work, false);
}
EXPORT_SYMBOL_GPL(kthread_cancel_work_sync);
/**
* kthread_cancel_delayed_work_sync - cancel a kthread delayed work and
* wait for it to finish.
* @dwork: the kthread delayed work to cancel
*
* This is kthread_cancel_work_sync() for delayed works.
*
* Return: %true if @dwork was pending, %false otherwise.
*/
bool kthread_cancel_delayed_work_sync(struct kthread_delayed_work *dwork)
{
return __kthread_cancel_work_sync(&dwork->work, true);
}
EXPORT_SYMBOL_GPL(kthread_cancel_delayed_work_sync);
/**
* kthread_flush_worker - flush all current works on a kthread_worker
* @worker: worker to flush
*
* Wait until all currently executing or pending works on @worker are
* finished.
*/
void kthread_flush_worker(struct kthread_worker *worker)
{
struct kthread_flush_work fwork = {
KTHREAD_WORK_INIT(fwork.work, kthread_flush_work_fn),
COMPLETION_INITIALIZER_ONSTACK(fwork.done),
};
kthread_queue_work(worker, &fwork.work);
wait_for_completion(&fwork.done);
}
EXPORT_SYMBOL_GPL(kthread_flush_worker);
/**
* kthread_destroy_worker - destroy a kthread worker
* @worker: worker to be destroyed
*
* Flush and destroy @worker. The simple flush is enough because the kthread
* worker API is used only in trivial scenarios. There are no multi-step state
* machines needed.
*/
void kthread_destroy_worker(struct kthread_worker *worker)
{
struct task_struct *task;
task = worker->task;
if (WARN_ON(!task))
return;
kthread_flush_worker(worker);
kthread_stop(task);
WARN_ON(!list_empty(&worker->work_list));
kfree(worker);
}
EXPORT_SYMBOL(kthread_destroy_worker);
#ifdef CONFIG_BLK_CGROUP
/**
* kthread_associate_blkcg - associate blkcg to current kthread
* @css: the cgroup info
*
* Current thread must be a kthread. The thread is running jobs on behalf of
* other threads. In some cases, we expect the jobs attach cgroup info of
* original threads instead of that of current thread. This function stores
* original thread's cgroup info in current kthread context for later
* retrieval.
*/
void kthread_associate_blkcg(struct cgroup_subsys_state *css)
{
struct kthread *kthread;
if (!(current->flags & PF_KTHREAD))
return;
kthread = to_kthread(current);
if (!kthread)
return;
if (kthread->blkcg_css) {
css_put(kthread->blkcg_css);
kthread->blkcg_css = NULL;
}
if (css) {
css_get(css);
kthread->blkcg_css = css;
}
}
EXPORT_SYMBOL(kthread_associate_blkcg);
/**
* kthread_blkcg - get associated blkcg css of current kthread
*
* Current thread must be a kthread.
*/
struct cgroup_subsys_state *kthread_blkcg(void)
{
struct kthread *kthread;
if (current->flags & PF_KTHREAD) {
kthread = to_kthread(current);
if (kthread)
return kthread->blkcg_css;
}
return NULL;
}
EXPORT_SYMBOL(kthread_blkcg);
#endif