Files
Wilson Sung 4accad7636 Merge android-4.14-stable (4.14.302) into android-msm-pixel-4.14-tm-lts
Merge 4.14.302 into android-4.14-stable
Linux 4.14.302
    net: mvneta: Fix an out of bounds check
  * ipv6: avoid use-after-free in ip6_fragment()
      net/ipv6/ip6_output.c
    net: plip: don't call kfree_skb/dev_kfree_skb() under spin_lock_irq()
    xen/netback: fix build warning
    ethernet: aeroflex: fix potential skb leak in greth_init_rings()
    tipc: Fix potential OOB in tipc_link_proto_rcv()
    net: hisilicon: Fix potential use-after-free in hix5hd2_rx()
    net: hisilicon: Fix potential use-after-free in hisi_femac_rx()
    net: stmmac: fix "snps,axi-config" node property parsing
    NFC: nci: Bounds check struct nfc_target arrays
    net: mvneta: Prevent out of bounds read in mvneta_config_rss()
    net: encx24j600: Fix invalid logic in reading of MISTAT register
    net: encx24j600: Add parentheses to fix precedence
    mac802154: fix missing INIT_LIST_HEAD in ieee802154_if_add()
    Bluetooth: 6LoWPAN: add missing hci_dev_put() in get_l2cap_conn()
    igb: Allocate MSI-X vector when testing
    e1000e: Fix TX dispatch condition
    gpio: amd8111: Fix PCI device reference count leak
    ca8210: Fix crash by zero initializing data
    ieee802154: cc2520: Fix error return code in cc2520_hw_init()
  * HID: core: fix shift-out-of-bounds in hid_report_raw_event
      drivers/hid/hid-core.c
    HID: hid-lg4ff: Add check for empty lbuf
    KVM: s390: vsie: Fix the initialization of the epoch extension (epdx) field
  * memcg: fix possible use-after-free in memcg_write_event_control()
      include/linux/cgroup.h
      kernel/cgroup/cgroup-internal.h
  * media: v4l2-dv-timings.c: fix too strict blanking sanity checks
      drivers/media/v4l2-core/v4l2-dv-timings.c
    rcutorture: Automatically create initrd directory
    xen/netback: don't call kfree_skb() with interrupts disabled
    xen/netback: do some code cleanup
    xen/netback: Ensure protocol headers don't fall in the non-linear area
    net: usb: qmi_wwan: add u-blox 0x1342 composition
    regulator: twl6030: fix get status of twl6032 regulators
  * ASoC: soc-pcm: Add NULL check in BE reparenting
      sound/soc/soc-pcm.c
    ALSA: seq: Fix function prototype mismatch in snd_seq_expand_var_event
    ARM: dts: rockchip: disable arm_global_timer on rk3066 and rk3188
    ARM: 9266/1: mm: fix no-MMU ZERO_PAGE() implementation
    ARM: 9251/1: perf: Fix stacktraces for tracepoint events in THUMB2 kernels
    ARM: dts: rockchip: fix ir-receiver node names
    arm: dts: rockchip: fix node name for hym8563 rtc
    Merge 4.14.301 into android-4.14-stable
Linux 4.14.301
    Revert "x86/speculation: Change FILL_RETURN_BUFFER to work with objtool"
    x86/nospec: Fix i386 RSB stuffing
    ipc/sem: Fix dangling sem_array access in semtimedop race
  * v4l2: don't fall back to follow_pfn() if pin_user_pages_fast() fails
      mm/frame_vector.c
  * proc: proc_skip_spaces() shouldn't think it is working on C strings
      kernel/sysctl.c
  * proc: avoid integer type confusion in get_proc_long
      kernel/sysctl.c
  * mmc: sdhci: Fix voltage switch delay
      drivers/mmc/host/sdhci.c
  * mmc: sdhci: use FIELD_GET for preset value bit masks
      drivers/mmc/host/sdhci.c
    x86/ioremap: Fix page aligned size calculation in __ioremap_caller()
  * Bluetooth: L2CAP: Fix accepting connection request for invalid SPSM
      net/bluetooth/l2cap_core.c
    x86/pm: Add enumeration check before spec MSRs save/restore setup
    x86/tsx: Add a feature bit for TSX control MSR support
    nvme: restrict management ioctls to admin
  * tcp/udp: Fix memory leak in ipv6_renew_options().
      net/ipv6/ipv6_sockglue.c
    iommu/vt-d: Fix PCI device refcount leak in dmar_dev_scope_init()
    pinctrl: single: Fix potential division by zero
  * ASoC: ops: Fix bounds check for _sx controls
      sound/soc/soc-ops.c
    efi: random: Properly limit the size of the random seed
  * arm64: errata: Fix KVM Spectre-v2 mitigation selection for Cortex-A57/A72
      arch/arm64/kernel/cpu_errata.c
  * arm64: Fix panic() when Spectre-v2 causes Spectre-BHB to re-allocate KVM vectors
      arch/arm64/kernel/cpu_errata.c
    x86/bugs: Make sure MSR_SPEC_CTRL is updated properly upon resume from S3
    nilfs2: fix NULL pointer dereference in nilfs_palloc_commit_free_entry()
    tools/vm/slabinfo-gnuplot: use "grep -E" instead of "egrep"
    btrfs: qgroup: fix sleep from invalid context bug in btrfs_qgroup_inherit()
  * perf: Add sample_flags to indicate the PMU-filled sample data
      include/linux/perf_event.h
      kernel/events/core.c
    hwmon: (coretemp) fix pci device refcount leak in nv1a_ram_new()
    hwmon: (coretemp) Check for null before removing sysfs attrs
    net: ethernet: renesas: ravb: Fix promiscuous mode after system resumed
  * packet: do not set TP_STATUS_CSUM_VALID on CHECKSUM_COMPLETE
      net/packet/af_packet.c
    net: hsr: Fix potential use-after-free
    dsa: lan9303: Correct stat name
    net/9p: Fix a potential socket leak in p9_socket_open
    net: net_netdev: Fix error handling in ntb_netdev_init_module()
  * net: phy: fix null-ptr-deref while probe() failed
      drivers/net/phy/phy_device.c
    qlcnic: fix sleep-in-atomic-context bugs caused by msleep
    can: cc770: cc770_isa_probe(): add missing free_cc770dev()
    can: sja1000_isa: sja1000_isa_probe(): add missing free_sja1000dev()
    net/mlx5: Fix uninitialized variable bug in outlen_write()
  * of: property: decrement node refcount in of_fwnode_get_reference_args()
      drivers/of/property.c
    hwmon: (ibmpex) Fix possible UAF when ibmpex_register_bmc() fails
    hwmon: (i5500_temp) fix missing pci_disable_device()
  * iio: light: rpr0521: add missing Kconfig dependencies
      drivers/iio/light/Kconfig
    iio: health: afe4404: Fix oob read in afe4404_[read|write]_raw
    iio: health: afe4403: Fix oob read in afe4403_read_raw
    drm/amdgpu: always register an MMU notifier for userptr
    net: usb: qmi_wwan: add Telit 0x103a composition
  * tcp: configurable source port perturb table size
      net/ipv4/Kconfig
      net/ipv4/inet_hashtables.c
    platform/x86: hp-wmi: Ignore Smart Experience App event
    platform/x86: acer-wmi: Enable SW_TABLET_MODE on Switch V 10 (SW5-017)
    platform/x86: asus-wmi: add missing pci_dev_put() in asus_wmi_set_xusb2pr()
    xen/platform-pci: add missing free_irq() in error path
    serial: 8250: 8250_omap: Avoid RS485 RTS glitch on ->set_termios()
    Input: synaptics - switch touchpad on HP Laptop 15-da3001TU to RMI mode
    nilfs2: fix nilfs_sufile_mark_dirty() not set segment usage as dirty
  * kconfig: display recursive dependency resolution hint just once
      scripts/kconfig/symbol.c
    iio: core: Fix entry not deleted when iio_register_sw_trigger_type() fails
    iio: light: apds9960: fix wrong register for gesture gain
    arm64: dts: rockchip: lower rk3399-puma-haikou SD controller clock frequency
    nios2: add FORCE for vmlinuz.gz
    s390/crashdump: fix TOD programmable field size
    net: thunderx: Fix the ACPI memory leak
    nfc: st-nci: fix memory leaks in EVT_TRANSACTION
    nfc: st-nci: fix incorrect validating logic in EVT_TRANSACTION
    s390/dasd: fix no record found for raw_track_access
  * dccp/tcp: Reset saddr on failure after inet6?_hash_connect().
      net/ipv4/tcp_ipv4.c
      net/ipv6/tcp_ipv6.c
    NFC: nci: fix memory leak in nci_rx_data_packet()
  * xfrm: Fix ignored return value in xfrm6_init()
      net/ipv6/xfrm6_policy.c
    net/qla3xxx: fix potential memleak in ql3xxx_send()
    net/mlx4: Check retval of mlx4_bitmap_init
    ARM: mxs: fix memory leak in mxs_machine_init()
    9p/fd: fix issue of list_del corruption in p9_fd_cancel()
    net: pch_gbe: fix potential memleak in pch_gbe_tx_queue()
    nfc/nci: fix race with opening and closing
    ARM: dts: at91: sam9g20ek: enable udc vbus gpio pinctrl
    bus: sunxi-rsb: Support atomic transfers
    ARM: dts: am335x-pcm-953: Define fixed regulators in root node
  * af_key: Fix send_acquire race with pfkey_register
      net/key/af_key.c
    MIPS: pic32: treat port as signed integer
    spi: stm32: fix stm32_spi_prepare_mbr() that halves spi clk for every run
    wifi: mac80211: Fix ack frame idr leak when mesh has no route
  * audit: fix undefined behavior in bit shift for AUDIT_BIT
      include/uapi/linux/audit.h
    wifi: mac80211_hwsim: fix debugfs attribute ps with rc table support
    Merge 4.14.300 into android-4.14-stable
Linux 4.14.300
    ntfs: check overflow when iterating ATTR_RECORDs
    ntfs: fix out-of-bounds read in ntfs_attr_find()
    ntfs: fix use-after-free in ntfs_attr_find()
  * mm: fs: initialize fsdata passed to write_begin/write_end interface
      fs/buffer.c
      fs/namei.c
      mm/filemap.c
    9p/trans_fd: always use O_NONBLOCK read/write
    gfs2: Switch from strlcpy to strscpy
    gfs2: Check sb_bsize_shift after reading superblock
    9p: trans_fd/p9_conn_cancel: drop client lock earlier
    kcm: close race conditions on sk_receive_queue
  * bpf, test_run: Fix alignment problem in bpf_prog_test_run_skb()
      net/bpf/test_run.c
    kcm: avoid potential race in kcm_tx_work
    tcp: cdg: allow tcp_cdg_release() to be called multiple times
    macvlan: enforce a consistent minimal mtu
    serial: 8250: Flush DMA Rx on RLSI
    nilfs2: fix use-after-free bug of ns_writer on remount
    misc/vmw_vmci: fix an infoleak in vmci_host_do_receive_datagram()
    mmc: sdhci-pci: Fix possible memory leak caused by missing pci_dev_put()
    mmc: core: properly select voltage range without power cycle
    serial: 8250_lpss: Configure DMA also w/o DMA filter
    serial: 8250: Fall back to non-DMA Rx if IIR_RDI occurs
  * dm ioctl: fix misbehavior if list_versions races with module loading
      drivers/md/dm-ioctl.c
    iio: pressure: ms5611: changed hardcoded SPI speed to value limited
    iio: trigger: sysfs: fix possible memory leak in iio_sysfs_trig_init()
    iio: adc: at91_adc: fix possible memory leak in at91_adc_allocate_trigger()
    usb: chipidea: fix deadlock in ci_otg_del_timer
  * usb: add NO_LPM quirk for Realforce 87U Keyboard
      drivers/usb/core/quirks.c
    USB: serial: option: add Fibocom FM160 0x0111 composition
    USB: serial: option: add u-blox LARA-L6 modem
    USB: serial: option: add u-blox LARA-R6 00B modem
    USB: serial: option: remove old LARA-R6 PID
    USB: serial: option: add Sierra Wireless EM9191
  * ALSA: usb-audio: Drop snd_BUG_ON() from snd_usbmidi_output_open()
      sound/usb/midi.c
  * ring_buffer: Do not deactivate non-existant pages
      kernel/trace/ring_buffer.c
    ftrace: Fix null pointer dereference in ftrace_add_mod()
    ftrace: Optimize the allocation for mcount entries
    ftrace: Fix the possible incorrect kernel message
    cifs: Fix wrong return value checking when GETFLAGS
    net/x25: Fix skb leak in x25_lapb_receive_frame()
    drbd: use after free in drbd_create_device()
    xen/pcpu: fix possible memory leak in register_pcpu()
    net: caif: fix double disconnect client in chnl_net_open()
    mISDN: fix misuse of put_device() in mISDN_register_device()
    mISDN: fix possible memory leak in mISDN_dsp_element_register()
    net: bgmac: Drop free_netdev() from bgmac_enet_remove()
  * pinctrl: devicetree: fix null pointer dereferencing in pinctrl_dt_to_map
      drivers/pinctrl/devicetree.c
    parport_pc: Avoid FIFO port location truncation
    block: sed-opal: kmalloc the cmd/resp buffers
  * ASoC: soc-utils: Remove __exit for snd_soc_util_exit()
      sound/soc/soc-utils.c
    tty: n_gsm: fix sleep-in-atomic-context bug in gsm_control_send
    serial: 8250: omap: Flush PM QOS work on remove
    serial: 8250_omap: remove wait loop from Errata i202 workaround
  * ASoC: core: Fix use-after-free in snd_soc_exit()
      sound/soc/soc-core.c
  * Bluetooth: L2CAP: Fix l2cap_global_chan_by_psm
      net/bluetooth/l2cap_core.c
    drm/imx: imx-tve: Fix return type of imx_tve_connector_mode_valid
    selftests/futex: fix build for clang
    x86/cpu: Restore AMD's DE_CFG MSR after resume
    dmaengine: at_hdmac: Check return code of dma_async_device_register
    dmaengine: at_hdmac: Fix impossible condition
    dmaengine: at_hdmac: Don't allow CPU to reorder channel enable
    dmaengine: at_hdmac: Fix completion of unissued descriptor in case of errors
    dmaengine: at_hdmac: Don't start transactions at tx_submit level
    dmaengine: at_hdmac: Fix at_lli struct definition
  * cert host tools: Stop complaining about deprecated OpenSSL functions
      scripts/extract-cert.c
    udf: Fix a slab-out-of-bounds write bug in udf_find_entry()
    btrfs: selftests: fix wrong error check in btrfs_free_dummy_root()
    platform/x86: hp_wmi: Fix rfkill causing soft blocked wifi
    drm/i915/dmabuf: fix sg_table handling in map_dma_buf
    nilfs2: fix deadlock in nilfs_count_free_blocks()
  * ALSA: usb-audio: Add quirk entry for M-Audio Micro
      sound/usb/quirks-table.h
    ALSA: hda: fix potential memleak in 'add_widget_node'
    arm64: efi: Fix handling of misaligned runtime regions and drop warning
    net: macvlan: fix memory leaks of macvlan_common_newlink
    net: mv643xx_eth: disable napi when init rxq or txq failed in mv643xx_eth_open()
    ethernet: s2io: disable napi when start nic failed in s2io_card_up()
    net: cxgb3_main: disable napi when bind qsets failed in cxgb_up()
    drivers: net: xgene: disable napi when register irq failed in xgene_enet_open()
    dmaengine: mv_xor_v2: Fix a resource leak in mv_xor_v2_remove()
    tipc: fix the msg->req tlv len check in tipc_nl_compat_name_table_dump_header
  * ipv6: addrlabel: fix infoleak when sending struct ifaddrlblmsg to network
      net/ipv6/addrlabel.c
    drm/vc4: Fix missing platform_unregister_drivers() call in vc4_drm_register()
    hamradio: fix issue of dev reference count leakage in bpq_device_event()
    net: lapbether: fix issue of dev reference count leakage in lapbeth_device_event()
  * capabilities: fix undefined behavior in bit shift for CAP_TO_MASK
      include/uapi/linux/capability.h
    net: fman: Unregister ethernet device on removal
    bnxt_en: fix potentially incorrect return value for ndo_rx_flow_steer
  * net: gso: fix panic on frag_list with mixed head alloc types
      net/core/skbuff.c
    HID: hyperv: fix possible memory leak in mousevsc_probe()

Bug: 263916797
Change-Id: I51192457a574c0d06884b644b950753a4953c2bb
Signed-off-by: JohnnLee <johnnlee@google.com>
2023-01-10 06:35:51 +00:00

881 lines
27 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_CGROUP_H
#define _LINUX_CGROUP_H
/*
* cgroup interface
*
* Copyright (C) 2003 BULL SA
* Copyright (C) 2004-2006 Silicon Graphics, Inc.
*
*/
#include <linux/sched.h>
#include <linux/cpumask.h>
#include <linux/nodemask.h>
#include <linux/rculist.h>
#include <linux/cgroupstats.h>
#include <linux/fs.h>
#include <linux/seq_file.h>
#include <linux/kernfs.h>
#include <linux/jump_label.h>
#include <linux/types.h>
#include <linux/ns_common.h>
#include <linux/nsproxy.h>
#include <linux/user_namespace.h>
#include <linux/refcount.h>
#include <linux/cgroup-defs.h>
#ifdef CONFIG_CGROUPS
/*
* All weight knobs on the default hierarhcy should use the following min,
* default and max values. The default value is the logarithmic center of
* MIN and MAX and allows 100x to be expressed in both directions.
*/
#define CGROUP_WEIGHT_MIN 1
#define CGROUP_WEIGHT_DFL 100
#define CGROUP_WEIGHT_MAX 10000
/* walk only threadgroup leaders */
#define CSS_TASK_ITER_PROCS (1U << 0)
/* walk all threaded css_sets in the domain */
#define CSS_TASK_ITER_THREADED (1U << 1)
/* internal flags */
#define CSS_TASK_ITER_SKIPPED (1U << 16)
/* a css_task_iter should be treated as an opaque object */
struct css_task_iter {
struct cgroup_subsys *ss;
unsigned int flags;
struct list_head *cset_pos;
struct list_head *cset_head;
struct list_head *tcset_pos;
struct list_head *tcset_head;
struct list_head *task_pos;
struct list_head *tasks_head;
struct list_head *mg_tasks_head;
struct list_head *dying_tasks_head;
struct list_head *cur_tasks_head;
struct css_set *cur_cset;
struct css_set *cur_dcset;
struct task_struct *cur_task;
struct list_head iters_node; /* css_set->task_iters */
};
extern struct file_system_type cgroup_fs_type;
extern struct cgroup_root cgrp_dfl_root;
extern struct css_set init_css_set;
#define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
#include <linux/cgroup_subsys.h>
#undef SUBSYS
#define SUBSYS(_x) \
extern struct static_key_true _x ## _cgrp_subsys_enabled_key; \
extern struct static_key_true _x ## _cgrp_subsys_on_dfl_key;
#include <linux/cgroup_subsys.h>
#undef SUBSYS
/**
* cgroup_subsys_enabled - fast test on whether a subsys is enabled
* @ss: subsystem in question
*/
#define cgroup_subsys_enabled(ss) \
static_branch_likely(&ss ## _enabled_key)
/**
* cgroup_subsys_on_dfl - fast test on whether a subsys is on default hierarchy
* @ss: subsystem in question
*/
#define cgroup_subsys_on_dfl(ss) \
static_branch_likely(&ss ## _on_dfl_key)
bool css_has_online_children(struct cgroup_subsys_state *css);
struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss);
struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup,
struct cgroup_subsys *ss);
struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry,
struct cgroup_subsys *ss);
struct cgroup *cgroup_get_from_path(const char *path);
struct cgroup *cgroup_get_from_fd(int fd);
int cgroup_attach_task_all(struct task_struct *from, struct task_struct *);
int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
int cgroup_rm_cftypes(struct cftype *cfts);
void cgroup_file_notify(struct cgroup_file *cfile);
int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry);
int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *tsk);
void cgroup_fork(struct task_struct *p);
extern int cgroup_can_fork(struct task_struct *p);
extern void cgroup_cancel_fork(struct task_struct *p);
extern void cgroup_post_fork(struct task_struct *p);
void cgroup_exit(struct task_struct *p);
void cgroup_release(struct task_struct *p);
void cgroup_free(struct task_struct *p);
int cgroup_init_early(void);
int cgroup_init(void);
/*
* Iteration helpers and macros.
*/
struct cgroup_subsys_state *css_next_child(struct cgroup_subsys_state *pos,
struct cgroup_subsys_state *parent);
struct cgroup_subsys_state *css_next_descendant_pre(struct cgroup_subsys_state *pos,
struct cgroup_subsys_state *css);
struct cgroup_subsys_state *css_rightmost_descendant(struct cgroup_subsys_state *pos);
struct cgroup_subsys_state *css_next_descendant_post(struct cgroup_subsys_state *pos,
struct cgroup_subsys_state *css);
struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset,
struct cgroup_subsys_state **dst_cssp);
struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset,
struct cgroup_subsys_state **dst_cssp);
void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags,
struct css_task_iter *it);
struct task_struct *css_task_iter_next(struct css_task_iter *it);
void css_task_iter_end(struct css_task_iter *it);
/**
* css_for_each_child - iterate through children of a css
* @pos: the css * to use as the loop cursor
* @parent: css whose children to walk
*
* Walk @parent's children. Must be called under rcu_read_lock().
*
* If a subsystem synchronizes ->css_online() and the start of iteration, a
* css which finished ->css_online() is guaranteed to be visible in the
* future iterations and will stay visible until the last reference is put.
* A css which hasn't finished ->css_online() or already finished
* ->css_offline() may show up during traversal. It's each subsystem's
* responsibility to synchronize against on/offlining.
*
* It is allowed to temporarily drop RCU read lock during iteration. The
* caller is responsible for ensuring that @pos remains accessible until
* the start of the next iteration by, for example, bumping the css refcnt.
*/
#define css_for_each_child(pos, parent) \
for ((pos) = css_next_child(NULL, (parent)); (pos); \
(pos) = css_next_child((pos), (parent)))
/**
* css_for_each_descendant_pre - pre-order walk of a css's descendants
* @pos: the css * to use as the loop cursor
* @root: css whose descendants to walk
*
* Walk @root's descendants. @root is included in the iteration and the
* first node to be visited. Must be called under rcu_read_lock().
*
* If a subsystem synchronizes ->css_online() and the start of iteration, a
* css which finished ->css_online() is guaranteed to be visible in the
* future iterations and will stay visible until the last reference is put.
* A css which hasn't finished ->css_online() or already finished
* ->css_offline() may show up during traversal. It's each subsystem's
* responsibility to synchronize against on/offlining.
*
* For example, the following guarantees that a descendant can't escape
* state updates of its ancestors.
*
* my_online(@css)
* {
* Lock @css's parent and @css;
* Inherit state from the parent;
* Unlock both.
* }
*
* my_update_state(@css)
* {
* css_for_each_descendant_pre(@pos, @css) {
* Lock @pos;
* if (@pos == @css)
* Update @css's state;
* else
* Verify @pos is alive and inherit state from its parent;
* Unlock @pos;
* }
* }
*
* As long as the inheriting step, including checking the parent state, is
* enclosed inside @pos locking, double-locking the parent isn't necessary
* while inheriting. The state update to the parent is guaranteed to be
* visible by walking order and, as long as inheriting operations to the
* same @pos are atomic to each other, multiple updates racing each other
* still result in the correct state. It's guaranateed that at least one
* inheritance happens for any css after the latest update to its parent.
*
* If checking parent's state requires locking the parent, each inheriting
* iteration should lock and unlock both @pos->parent and @pos.
*
* Alternatively, a subsystem may choose to use a single global lock to
* synchronize ->css_online() and ->css_offline() against tree-walking
* operations.
*
* It is allowed to temporarily drop RCU read lock during iteration. The
* caller is responsible for ensuring that @pos remains accessible until
* the start of the next iteration by, for example, bumping the css refcnt.
*/
#define css_for_each_descendant_pre(pos, css) \
for ((pos) = css_next_descendant_pre(NULL, (css)); (pos); \
(pos) = css_next_descendant_pre((pos), (css)))
/**
* css_for_each_descendant_post - post-order walk of a css's descendants
* @pos: the css * to use as the loop cursor
* @css: css whose descendants to walk
*
* Similar to css_for_each_descendant_pre() but performs post-order
* traversal instead. @root is included in the iteration and the last
* node to be visited.
*
* If a subsystem synchronizes ->css_online() and the start of iteration, a
* css which finished ->css_online() is guaranteed to be visible in the
* future iterations and will stay visible until the last reference is put.
* A css which hasn't finished ->css_online() or already finished
* ->css_offline() may show up during traversal. It's each subsystem's
* responsibility to synchronize against on/offlining.
*
* Note that the walk visibility guarantee example described in pre-order
* walk doesn't apply the same to post-order walks.
*/
#define css_for_each_descendant_post(pos, css) \
for ((pos) = css_next_descendant_post(NULL, (css)); (pos); \
(pos) = css_next_descendant_post((pos), (css)))
/**
* cgroup_taskset_for_each - iterate cgroup_taskset
* @task: the loop cursor
* @dst_css: the destination css
* @tset: taskset to iterate
*
* @tset may contain multiple tasks and they may belong to multiple
* processes.
*
* On the v2 hierarchy, there may be tasks from multiple processes and they
* may not share the source or destination csses.
*
* On traditional hierarchies, when there are multiple tasks in @tset, if a
* task of a process is in @tset, all tasks of the process are in @tset.
* Also, all are guaranteed to share the same source and destination csses.
*
* Iteration is not in any specific order.
*/
#define cgroup_taskset_for_each(task, dst_css, tset) \
for ((task) = cgroup_taskset_first((tset), &(dst_css)); \
(task); \
(task) = cgroup_taskset_next((tset), &(dst_css)))
/**
* cgroup_taskset_for_each_leader - iterate group leaders in a cgroup_taskset
* @leader: the loop cursor
* @dst_css: the destination css
* @tset: taskset to iterate
*
* Iterate threadgroup leaders of @tset. For single-task migrations, @tset
* may not contain any.
*/
#define cgroup_taskset_for_each_leader(leader, dst_css, tset) \
for ((leader) = cgroup_taskset_first((tset), &(dst_css)); \
(leader); \
(leader) = cgroup_taskset_next((tset), &(dst_css))) \
if ((leader) != (leader)->group_leader) \
; \
else
/*
* Inline functions.
*/
/**
* css_get - obtain a reference on the specified css
* @css: target css
*
* The caller must already have a reference.
*/
static inline void css_get(struct cgroup_subsys_state *css)
{
if (!(css->flags & CSS_NO_REF))
percpu_ref_get(&css->refcnt);
}
/**
* css_get_many - obtain references on the specified css
* @css: target css
* @n: number of references to get
*
* The caller must already have a reference.
*/
static inline void css_get_many(struct cgroup_subsys_state *css, unsigned int n)
{
if (!(css->flags & CSS_NO_REF))
percpu_ref_get_many(&css->refcnt, n);
}
/**
* css_tryget - try to obtain a reference on the specified css
* @css: target css
*
* Obtain a reference on @css unless it already has reached zero and is
* being released. This function doesn't care whether @css is on or
* offline. The caller naturally needs to ensure that @css is accessible
* but doesn't have to be holding a reference on it - IOW, RCU protected
* access is good enough for this function. Returns %true if a reference
* count was successfully obtained; %false otherwise.
*/
static inline bool css_tryget(struct cgroup_subsys_state *css)
{
if (!(css->flags & CSS_NO_REF))
return percpu_ref_tryget(&css->refcnt);
return true;
}
/**
* css_tryget_online - try to obtain a reference on the specified css if online
* @css: target css
*
* Obtain a reference on @css if it's online. The caller naturally needs
* to ensure that @css is accessible but doesn't have to be holding a
* reference on it - IOW, RCU protected access is good enough for this
* function. Returns %true if a reference count was successfully obtained;
* %false otherwise.
*/
static inline bool css_tryget_online(struct cgroup_subsys_state *css)
{
if (!(css->flags & CSS_NO_REF))
return percpu_ref_tryget_live(&css->refcnt);
return true;
}
/**
* css_is_dying - test whether the specified css is dying
* @css: target css
*
* Test whether @css is in the process of offlining or already offline. In
* most cases, ->css_online() and ->css_offline() callbacks should be
* enough; however, the actual offline operations are RCU delayed and this
* test returns %true also when @css is scheduled to be offlined.
*
* This is useful, for example, when the use case requires synchronous
* behavior with respect to cgroup removal. cgroup removal schedules css
* offlining but the css can seem alive while the operation is being
* delayed. If the delay affects user visible semantics, this test can be
* used to resolve the situation.
*/
static inline bool css_is_dying(struct cgroup_subsys_state *css)
{
return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt);
}
/**
* css_put - put a css reference
* @css: target css
*
* Put a reference obtained via css_get() and css_tryget_online().
*/
static inline void css_put(struct cgroup_subsys_state *css)
{
if (!(css->flags & CSS_NO_REF))
percpu_ref_put(&css->refcnt);
}
/**
* css_put_many - put css references
* @css: target css
* @n: number of references to put
*
* Put references obtained via css_get() and css_tryget_online().
*/
static inline void css_put_many(struct cgroup_subsys_state *css, unsigned int n)
{
if (!(css->flags & CSS_NO_REF))
percpu_ref_put_many(&css->refcnt, n);
}
static inline void cgroup_get(struct cgroup *cgrp)
{
css_get(&cgrp->self);
}
static inline bool cgroup_tryget(struct cgroup *cgrp)
{
return css_tryget(&cgrp->self);
}
static inline void cgroup_put(struct cgroup *cgrp)
{
css_put(&cgrp->self);
}
/**
* task_css_set_check - obtain a task's css_set with extra access conditions
* @task: the task to obtain css_set for
* @__c: extra condition expression to be passed to rcu_dereference_check()
*
* A task's css_set is RCU protected, initialized and exited while holding
* task_lock(), and can only be modified while holding both cgroup_mutex
* and task_lock() while the task is alive. This macro verifies that the
* caller is inside proper critical section and returns @task's css_set.
*
* The caller can also specify additional allowed conditions via @__c, such
* as locks used during the cgroup_subsys::attach() methods.
*/
#ifdef CONFIG_PROVE_RCU
extern struct mutex cgroup_mutex;
extern spinlock_t css_set_lock;
#define task_css_set_check(task, __c) \
rcu_dereference_check((task)->cgroups, \
lockdep_is_held(&cgroup_mutex) || \
lockdep_is_held(&css_set_lock) || \
((task)->flags & PF_EXITING) || (__c))
#else
#define task_css_set_check(task, __c) \
rcu_dereference((task)->cgroups)
#endif
/**
* task_css_check - obtain css for (task, subsys) w/ extra access conds
* @task: the target task
* @subsys_id: the target subsystem ID
* @__c: extra condition expression to be passed to rcu_dereference_check()
*
* Return the cgroup_subsys_state for the (@task, @subsys_id) pair. The
* synchronization rules are the same as task_css_set_check().
*/
#define task_css_check(task, subsys_id, __c) \
task_css_set_check((task), (__c))->subsys[(subsys_id)]
/**
* task_css_set - obtain a task's css_set
* @task: the task to obtain css_set for
*
* See task_css_set_check().
*/
static inline struct css_set *task_css_set(struct task_struct *task)
{
return task_css_set_check(task, false);
}
/**
* task_css - obtain css for (task, subsys)
* @task: the target task
* @subsys_id: the target subsystem ID
*
* See task_css_check().
*/
static inline struct cgroup_subsys_state *task_css(struct task_struct *task,
int subsys_id)
{
return task_css_check(task, subsys_id, false);
}
/**
* task_get_css - find and get the css for (task, subsys)
* @task: the target task
* @subsys_id: the target subsystem ID
*
* Find the css for the (@task, @subsys_id) combination, increment a
* reference on and return it. This function is guaranteed to return a
* valid css. The returned css may already have been offlined.
*/
static inline struct cgroup_subsys_state *
task_get_css(struct task_struct *task, int subsys_id)
{
struct cgroup_subsys_state *css;
rcu_read_lock();
while (true) {
css = task_css(task, subsys_id);
/*
* Can't use css_tryget_online() here. A task which has
* PF_EXITING set may stay associated with an offline css.
* If such task calls this function, css_tryget_online()
* will keep failing.
*/
if (likely(css_tryget(css)))
break;
cpu_relax();
}
rcu_read_unlock();
return css;
}
/**
* task_css_is_root - test whether a task belongs to the root css
* @task: the target task
* @subsys_id: the target subsystem ID
*
* Test whether @task belongs to the root css on the specified subsystem.
* May be invoked in any context.
*/
static inline bool task_css_is_root(struct task_struct *task, int subsys_id)
{
return task_css_check(task, subsys_id, true) ==
init_css_set.subsys[subsys_id];
}
static inline struct cgroup *task_cgroup(struct task_struct *task,
int subsys_id)
{
return task_css(task, subsys_id)->cgroup;
}
static inline struct cgroup *task_dfl_cgroup(struct task_struct *task)
{
return task_css_set(task)->dfl_cgrp;
}
static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
{
struct cgroup_subsys_state *parent_css = cgrp->self.parent;
if (parent_css)
return container_of(parent_css, struct cgroup, self);
return NULL;
}
/**
* cgroup_is_descendant - test ancestry
* @cgrp: the cgroup to be tested
* @ancestor: possible ancestor of @cgrp
*
* Test whether @cgrp is a descendant of @ancestor. It also returns %true
* if @cgrp == @ancestor. This function is safe to call as long as @cgrp
* and @ancestor are accessible.
*/
static inline bool cgroup_is_descendant(struct cgroup *cgrp,
struct cgroup *ancestor)
{
if (cgrp->root != ancestor->root || cgrp->level < ancestor->level)
return false;
return cgrp->ancestor_ids[ancestor->level] == ancestor->id;
}
/**
* cgroup_ancestor - find ancestor of cgroup
* @cgrp: cgroup to find ancestor of
* @ancestor_level: level of ancestor to find starting from root
*
* Find ancestor of cgroup at specified level starting from root if it exists
* and return pointer to it. Return NULL if @cgrp doesn't have ancestor at
* @ancestor_level.
*
* This function is safe to call as long as @cgrp is accessible.
*/
static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp,
int ancestor_level)
{
if (cgrp->level < ancestor_level)
return NULL;
while (cgrp && cgrp->level > ancestor_level)
cgrp = cgroup_parent(cgrp);
return cgrp;
}
/**
* task_under_cgroup_hierarchy - test task's membership of cgroup ancestry
* @task: the task to be tested
* @ancestor: possible ancestor of @task's cgroup
*
* Tests whether @task's default cgroup hierarchy is a descendant of @ancestor.
* It follows all the same rules as cgroup_is_descendant, and only applies
* to the default hierarchy.
*/
static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
struct cgroup *ancestor)
{
struct css_set *cset = task_css_set(task);
return cgroup_is_descendant(cset->dfl_cgrp, ancestor);
}
/* no synchronization, the result can only be used as a hint */
static inline bool cgroup_is_populated(struct cgroup *cgrp)
{
return cgrp->nr_populated_csets + cgrp->nr_populated_domain_children +
cgrp->nr_populated_threaded_children;
}
/* returns ino associated with a cgroup */
static inline ino_t cgroup_ino(struct cgroup *cgrp)
{
return cgrp->kn->id.ino;
}
/* cft/css accessors for cftype->write() operation */
static inline struct cftype *of_cft(struct kernfs_open_file *of)
{
return of->kn->priv;
}
struct cgroup_subsys_state *of_css(struct kernfs_open_file *of);
/* cft/css accessors for cftype->seq_*() operations */
static inline struct cftype *seq_cft(struct seq_file *seq)
{
return of_cft(seq->private);
}
static inline struct cgroup_subsys_state *seq_css(struct seq_file *seq)
{
return of_css(seq->private);
}
/*
* Name / path handling functions. All are thin wrappers around the kernfs
* counterparts and can be called under any context.
*/
static inline int cgroup_name(struct cgroup *cgrp, char *buf, size_t buflen)
{
return kernfs_name(cgrp->kn, buf, buflen);
}
static inline int cgroup_path(struct cgroup *cgrp, char *buf, size_t buflen)
{
return kernfs_path(cgrp->kn, buf, buflen);
}
static inline void pr_cont_cgroup_name(struct cgroup *cgrp)
{
pr_cont_kernfs_name(cgrp->kn);
}
static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
{
pr_cont_kernfs_path(cgrp->kn);
}
static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
{
return &cgrp->psi;
}
bool cgroup_psi_enabled(void);
static inline void cgroup_init_kthreadd(void)
{
/*
* kthreadd is inherited by all kthreads, keep it in the root so
* that the new kthreads are guaranteed to stay in the root until
* initialization is finished.
*/
current->no_cgroup_migration = 1;
}
static inline void cgroup_kthread_ready(void)
{
/*
* This kthread finished initialization. The creator should have
* set PF_NO_SETAFFINITY if this kthread should stay in the root.
*/
current->no_cgroup_migration = 0;
}
static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp)
{
return &cgrp->kn->id;
}
void cgroup_path_from_kernfs_id(const union kernfs_node_id *id,
char *buf, size_t buflen);
#else /* !CONFIG_CGROUPS */
struct cgroup_subsys_state;
struct cgroup;
static inline void css_put(struct cgroup_subsys_state *css) {}
static inline int cgroup_attach_task_all(struct task_struct *from,
struct task_struct *t) { return 0; }
static inline int cgroupstats_build(struct cgroupstats *stats,
struct dentry *dentry) { return -EINVAL; }
static inline void cgroup_fork(struct task_struct *p) {}
static inline int cgroup_can_fork(struct task_struct *p) { return 0; }
static inline void cgroup_cancel_fork(struct task_struct *p) {}
static inline void cgroup_post_fork(struct task_struct *p) {}
static inline void cgroup_exit(struct task_struct *p) {}
static inline void cgroup_release(struct task_struct *p) {}
static inline void cgroup_free(struct task_struct *p) {}
static inline int cgroup_init_early(void) { return 0; }
static inline int cgroup_init(void) { return 0; }
static inline void cgroup_init_kthreadd(void) {}
static inline void cgroup_kthread_ready(void) {}
static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp)
{
return NULL;
}
static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
{
return NULL;
}
static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
{
return NULL;
}
static inline bool cgroup_psi_enabled(void)
{
return false;
}
static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
struct cgroup *ancestor)
{
return true;
}
static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id,
char *buf, size_t buflen) {}
#endif /* !CONFIG_CGROUPS */
/*
* sock->sk_cgrp_data handling. For more info, see sock_cgroup_data
* definition in cgroup-defs.h.
*/
#ifdef CONFIG_SOCK_CGROUP_DATA
#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
extern spinlock_t cgroup_sk_update_lock;
#endif
void cgroup_sk_alloc_disable(void);
void cgroup_sk_alloc(struct sock_cgroup_data *skcd);
void cgroup_sk_clone(struct sock_cgroup_data *skcd);
void cgroup_sk_free(struct sock_cgroup_data *skcd);
static inline struct cgroup *sock_cgroup_ptr(struct sock_cgroup_data *skcd)
{
#if defined(CONFIG_CGROUP_NET_PRIO) || defined(CONFIG_CGROUP_NET_CLASSID)
unsigned long v;
/*
* @skcd->val is 64bit but the following is safe on 32bit too as we
* just need the lower ulong to be written and read atomically.
*/
v = READ_ONCE(skcd->val);
if (v & 3)
return &cgrp_dfl_root.cgrp;
return (struct cgroup *)(unsigned long)v ?: &cgrp_dfl_root.cgrp;
#else
return (struct cgroup *)(unsigned long)skcd->val;
#endif
}
#else /* CONFIG_CGROUP_DATA */
static inline void cgroup_sk_alloc(struct sock_cgroup_data *skcd) {}
static inline void cgroup_sk_clone(struct sock_cgroup_data *skcd) {}
static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
#endif /* CONFIG_CGROUP_DATA */
struct cgroup_namespace {
refcount_t count;
struct ns_common ns;
struct user_namespace *user_ns;
struct ucounts *ucounts;
struct css_set *root_cset;
};
extern struct cgroup_namespace init_cgroup_ns;
#ifdef CONFIG_CGROUPS
void free_cgroup_ns(struct cgroup_namespace *ns);
struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
struct user_namespace *user_ns,
struct cgroup_namespace *old_ns);
int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
struct cgroup_namespace *ns);
#else /* !CONFIG_CGROUPS */
static inline void free_cgroup_ns(struct cgroup_namespace *ns) { }
static inline struct cgroup_namespace *
copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns,
struct cgroup_namespace *old_ns)
{
return old_ns;
}
#endif /* !CONFIG_CGROUPS */
static inline void get_cgroup_ns(struct cgroup_namespace *ns)
{
if (ns)
refcount_inc(&ns->count);
}
static inline void put_cgroup_ns(struct cgroup_namespace *ns)
{
if (ns && refcount_dec_and_test(&ns->count))
free_cgroup_ns(ns);
}
#ifdef CONFIG_CGROUPS
void cgroup_enter_frozen(void);
void cgroup_leave_frozen(bool always_leave);
void cgroup_update_frozen(struct cgroup *cgrp);
void cgroup_freeze(struct cgroup *cgrp, bool freeze);
void cgroup_freezer_migrate_task(struct task_struct *task, struct cgroup *src,
struct cgroup *dst);
void cgroup_freezer_frozen_exit(struct task_struct *task);
static inline bool cgroup_task_freeze(struct task_struct *task)
{
bool ret;
if (task->flags & PF_KTHREAD)
return false;
rcu_read_lock();
ret = test_bit(CGRP_FREEZE, &task_dfl_cgroup(task)->flags);
rcu_read_unlock();
return ret;
}
static inline bool cgroup_task_frozen(struct task_struct *task)
{
return task->frozen;
}
#else /* !CONFIG_CGROUPS */
static inline void cgroup_enter_frozen(void) { }
static inline void cgroup_leave_frozen(bool always_leave) { }
static inline bool cgroup_task_freeze(struct task_struct *task)
{
return false;
}
static inline bool cgroup_task_frozen(struct task_struct *task)
{
return false;
}
#endif /* !CONFIG_CGROUPS */
#endif /* _LINUX_CGROUP_H */