* common/android-4.9-q:
Linux 4.9.321
swiotlb: skip swiotlb_bounce when orig_addr is zero
kexec_file: drop weak attribute from arch_kexec_apply_relocations[_add]
fdt: Update CRC check for rng-seed
xen: unexport __init-annotated xen_xlate_map_ballooned_pages()
drm: remove drm_fb_helper_modinit
powerpc/pseries: wire up rng during setup_arch()
modpost: fix section mismatch check for exported init/exit sections
ARM: cns3xxx: Fix refcount leak in cns3xxx_init
ARM: Fix refcount leak in axxia_boot_secondary
ARM: exynos: Fix refcount leak in exynos_map_pmu
ARM: dts: imx6qdl: correct PU regulator ramp delay
powerpc: Enable execve syscall exit tracepoint
xtensa: Fix refcount leak bug in time.c
xtensa: xtfpga: Fix refcount leak bug in setup
iio: trigger: sysfs: fix use-after-free on remove
iio: accel: mma8452: ignore the return value of reset operation
iio:accel:bma180: rearrange iio trigger get and register
usb: chipidea: udc: check request status before setting device address
iio: adc: vf610: fix conversion mode sysfs node name
igb: Make DMA faster when CPU is active on the PCIe link
MIPS: Remove repetitive increase irq_err_count
x86/xen: Remove undefined behavior in setup_features()
bonding: ARP monitor spams NETDEV_NOTIFY_PEERS notifiers
USB: serial: option: add Telit LE910Cx 0x1250 composition
random: quiet urandom warning ratelimit suppression message
dm era: commit metadata in postsuspend after worker stops
ata: libata: add qc->flags in ata_qc_complete_template tracepoint
random: schedule mix_interrupt_randomness() less often
vt: drop old FONT ioctls
BACKPORT: l2tp: fix race in pppol2tp_release with session object destroy
BACKPORT: l2tp: don't use inet_shutdown on ppp session destroy
Linux 4.9.320
tcp: drop the hash_32() part from the index calculation
tcp: increase source port perturb table to 2^16
tcp: dynamically allocate the perturb table used by source ports
tcp: add small random increments to the source port
tcp: use different parts of the port_offset for index and offset
secure_seq: use the 64 bits of the siphash for port offset calculation
tcp: add some entropy in __inet_hash_connect()
tcp: change source port randomizarion at connect() time
fuse: fix pipe buffer lifetime for direct_io
Reinstate some of "swiotlb: rework "fix info leak with DMA_FROM_DEVICE""
swiotlb: fix info leak with DMA_FROM_DEVICE
xprtrdma: fix incorrect header size calculations
s390/mm: use non-quiescing sske for KVM switch to keyed guest
l2tp: fix race in pppol2tp_release with session object destroy
l2tp: don't use inet_shutdown on ppp session destroy
ext4: add reserved GDT blocks check
ext4: make variable "count" signed
ext4: fix bug_on ext4_mb_use_inode_pa
serial: 8250: Store to lsr_save_flags after lsr read
usb: gadget: lpc32xx_udc: Fix refcount leak in lpc32xx_udc_probe
USB: serial: io_ti: add Agilent E5805A support
USB: serial: option: add support for Cinterion MV31 with new baseline
comedi: vmk80xx: fix expression for tx buffer size
irqchip/gic-v3: Iterate over possible CPUs by for_each_possible_cpu()
irqchip/gic/realview: Fix refcount leak in realview_gic_of_init
misc: atmel-ssc: Fix IRQ check in ssc_probe
pNFS: Don't keep retrying if the server replied NFS4ERR_LAYOUTUNAVAILABLE
random: credit cpu and bootloader seeds by default
net: ethernet: mtk_eth_soc: fix misuse of mem alloc interface netdev[napi]_alloc_frag
ipv6: Fix signed integer overflow in l2tp_ip6_sendmsg
nfc: nfcmrvl: Fix memory leak in nfcmrvl_play_deferred
virtio-mmio: fix missing put_device() when vm_cmdline_parent registration failed
scsi: lpfc: Fix port stuck in bypassed state after LIP in PT2PT topology
scsi: vmw_pvscsi: Expand vcpuHint to 16 bits
ASoC: wm8962: Fix suspend while playing music
ata: libata-core: fix NULL pointer deref in ata_host_alloc_pinfo()
ASoC: cs42l56: Correct typo in minimum level for SX volume controls
ASoC: cs42l52: Correct TLV for Bypass Volume
ASoC: cs53l30: Correct number of volume levels on SX controls
ASoC: cs42l52: Fix TLV scales for mixer controls
random: account for arch randomness in bits
random: mark bootloader randomness code as __init
random: avoid checking crng_ready() twice in random_init()
crypto: drbg - make reseeding from get_random_bytes() synchronous
crypto: drbg - always try to free Jitter RNG instance
crypto: drbg - move dynamic ->reseed_threshold adjustments to __drbg_seed()
crypto: drbg - track whether DRBG was seeded with !rng_is_initialized()
crypto: drbg - prepare for more fine-grained tracking of seeding state
crypto: drbg - always seeded with SP800-90B compliant noise source
crypto: drbg - add FIPS 140-2 CTRNG for noise source
Revert "random: use static branch for crng_ready()"
random: check for signals after page of pool writes
random: wire up fops->splice_{read,write}_iter()
random: convert to using fops->write_iter()
random: move randomize_page() into mm where it belongs
random: move initialization functions out of hot pages
random: use proper return types on get_random_{int,long}_wait()
random: remove extern from functions in header
random: use static branch for crng_ready()
random: credit architectural init the exact amount
random: handle latent entropy and command line from random_init()
random: use proper jiffies comparison macro
random: remove ratelimiting for in-kernel unseeded randomness
random: avoid initializing twice in credit race
random: use symbolic constants for crng_init states
siphash: use one source of truth for siphash permutations
random: help compiler out with fast_mix() by using simpler arguments
random: do not use input pool from hard IRQs
random: order timer entropy functions below interrupt functions
random: do not pretend to handle premature next security model
random: do not use batches when !crng_ready()
random: insist on random_get_entropy() existing in order to simplify
uapi: rename ext2_swab() to swab() and share globally in swab.h
xtensa: use fallback for random_get_entropy() instead of zero
sparc: use fallback for random_get_entropy() instead of zero
um: use fallback for random_get_entropy() instead of zero
x86/tsc: Use fallback for random_get_entropy() instead of zero
nios2: use fallback for random_get_entropy() instead of zero
arm: use fallback for random_get_entropy() instead of zero
mips: use fallback for random_get_entropy() instead of just c0 random
m68k: use fallback for random_get_entropy() instead of zero
timekeeping: Add raw clock fallback for random_get_entropy()
powerpc: define get_cycles macro for arch-override
alpha: define get_cycles macro for arch-override
parisc: define get_cycles macro for arch-override
s390: define get_cycles macro for arch-override
ia64: define get_cycles macro for arch-override
init: call time_init() before rand_initialize()
random: fix sysctl documentation nits
random: document crng_fast_key_erasure() destination possibility
random: make random_get_entropy() return an unsigned long
random: check for signals every PAGE_SIZE chunk of /dev/[u]random
random: check for signal_pending() outside of need_resched() check
random: do not allow user to keep crng key around on stack
random: do not split fast init input in add_hwgenerator_randomness()
random: mix build-time latent entropy into pool at init
random: re-add removed comment about get_random_{u32,u64} reseeding
random: treat bootloader trust toggle the same way as cpu trust toggle
random: skip fast_init if hwrng provides large chunk of entropy
random: check for signal and try earlier when generating entropy
random: reseed more often immediately after booting
random: make consistent usage of crng_ready()
random: use SipHash as interrupt entropy accumulator
random: replace custom notifier chain with standard one
random: don't let 644 read-only sysctls be written to
random: give sysctl_random_min_urandom_seed a more sensible value
random: do crng pre-init loading in worker rather than irq
random: unify cycles_t and jiffies usage and types
random: cleanup UUID handling
random: only wake up writers after zap if threshold was passed
random: round-robin registers as ulong, not u32
random: clear fast pool, crng, and batches in cpuhp bring up
random: pull add_hwgenerator_randomness() declaration into random.h
hwrng: remember rng chosen by user
hwrng: use rng source with best quality
hwrng: core - remove unused PFX macro
hwrng: core - Move hwrng miscdev minor number to include/linux/miscdevice.h
hwrng: core - Rewrite the header
hwrng: core - rewrite better comparison to NULL
hwrng: core - do not use multiple blank lines
random: check for crng_init == 0 in add_device_randomness()
random: unify early init crng load accounting
random: do not take pool spinlock at boot
random: defer fast pool mixing to worker
workqueue: make workqueue available early during boot
random: rewrite header introductory comment
random: group sysctl functions
random: group userspace read/write functions
random: group entropy collection functions
random: group entropy extraction functions
random: group initialization wait functions
random: remove whitespace and reorder includes
random: remove useless header comment
random: introduce drain_entropy() helper to declutter crng_reseed()
random: deobfuscate irq u32/u64 contributions
random: add proper SPDX header
random: remove unused tracepoints
random: remove ifdef'd out interrupt bench
random: tie batched entropy generation to base_crng generation
random: zero buffer after reading entropy from userspace
random: remove outdated INT_MAX >> 6 check in urandom_read()
random: use hash function for crng_slow_load()
random: absorb fast pool into input pool after fast load
random: do not xor RDRAND when writing into /dev/random
random: ensure early RDSEED goes through mixer on init
random: inline leaves of rand_initialize()
random: use RDSEED instead of RDRAND in entropy extraction
random: fix locking in crng_fast_load()
random: remove batched entropy locking
random: remove use_input_pool parameter from crng_reseed()
random: make credit_entropy_bits() always safe
random: always wake up entropy writers after extraction
random: use linear min-entropy accumulation crediting
random: simplify entropy debiting
random: use computational hash for entropy extraction
random: only call crng_finalize_init() for primary_crng
random: access primary_pool directly rather than through pointer
random: continually use hwgenerator randomness
random: simplify arithmetic function flow in account()
random: access input_pool_data directly rather than through pointer
random: cleanup fractional entropy shift constants
random: prepend remaining pool constants with POOL_
random: de-duplicate INPUT_POOL constants
random: remove unused OUTPUT_POOL constants
random: rather than entropy_store abstraction, use global
random: try to actively add entropy rather than passively wait for it
random: remove unused extract_entropy() reserved argument
random: remove incomplete last_data logic
random: cleanup integer types
crypto: chacha20 - Fix chacha20_block() keystream alignment (again)
random: cleanup poolinfo abstraction
random: fix typo in comments
random: don't reset crng_init_cnt on urandom_read()
random: avoid superfluous call to RDRAND in CRNG extraction
random: early initialization of ChaCha constants
random: initialize ChaCha20 constants with correct endianness
random: use IS_ENABLED(CONFIG_NUMA) instead of ifdefs
random: harmonize "crng init done" messages
random: mix bootloader randomness into pool
random: do not re-init if crng_reseed completes before primary init
random: do not sign extend bytes for rotation when mixing
random: use BLAKE2s instead of SHA1 in extraction
random: remove unused irq_flags argument from add_interrupt_randomness()
random: document add_hwgenerator_randomness() with other input functions
crypto: blake2s - adjust include guard naming
crypto: blake2s - include <linux/bug.h> instead of <asm/bug.h>
MAINTAINERS: co-maintain random.c
random: remove dead code left over from blocking pool
random: avoid arch_get_random_seed_long() when collecting IRQ randomness
random: add arch_get_random_*long_early()
powerpc: Use bool in archrandom.h
linux/random.h: Mark CONFIG_ARCH_RANDOM functions __must_check
linux/random.h: Use false with bool
linux/random.h: Remove arch_has_random, arch_has_random_seed
powerpc: Remove arch_has_random, arch_has_random_seed
x86: Remove arch_has_random, arch_has_random_seed
random: avoid warnings for !CONFIG_NUMA builds
random: split primary/secondary crng init paths
random: remove some dead code of poolinfo
random: fix typo in add_timer_randomness()
random: Add and use pr_fmt()
random: convert to ENTROPY_BITS for better code readability
random: remove unnecessary unlikely()
random: remove kernel.random.read_wakeup_threshold
random: delete code to pull data into pools
random: remove the blocking pool
random: fix crash on multiple early calls to add_bootloader_randomness()
random: make /dev/random be almost like /dev/urandom
random: ignore GRND_RANDOM in getentropy(2)
random: add GRND_INSECURE to return best-effort non-cryptographic bytes
random: Add a urandom_read_nowait() for random APIs that don't warn
random: Don't wake crng_init_wait when crng_init == 1
lib/crypto: sha1: re-roll loops to reduce code size
lib/crypto: blake2s: move hmac construction into wireguard
crypto: blake2s - generic C library implementation and selftest
crypto: Deduplicate le32_to_cpu_array() and cpu_to_le32_array()
Revert "hwrng: core - Freeze khwrng thread during suspend"
char/random: Add a newline at the end of the file
random: Use wait_event_freezable() in add_hwgenerator_randomness()
fdt: add support for rng-seed
random: Support freezable kthreads in add_hwgenerator_randomness()
random: fix soft lockup when trying to read from an uninitialized blocking pool
latent_entropy: avoid build error when plugin cflags are not set
random: document get_random_int() family
random: move rand_initialize() earlier
random: only read from /dev/random after its pool has received 128 bits
drivers/char/random.c: make primary_crng static
drivers/char/random.c: remove unused stuct poolinfo::poolbits
drivers/char/random.c: constify poolinfo_table
random: make CPU trust a boot parameter
random: Make crng state queryable
random: remove preempt disabled region
random: add a config option to trust the CPU's hwrng
random: Return nbytes filled from hw RNG
random: Fix whitespace pre random-bytes work
drivers/char/random.c: remove unused dont_count_entropy
random: optimize add_interrupt_randomness
random: always fill buffer in get_random_bytes_wait
crypto: chacha20 - Fix keystream alignment for chacha20_block()
random: fix data race on crng_node_pool
random: always use batched entropy for get_random_u{32,64}
Revert "char/random: silence a lockdep splat with printk()"
char/random: silence a lockdep splat with printk()
random: add a spinlock_t to struct batched_entropy
random: rate limit unseeded randomness warnings
random: fix possible sleeping allocation from irq context
random: set up the NUMA crng instances after the CRNG is fully initialized
random: use a different mixing algorithm for add_device_randomness()
random: fix warning message on ia64 and parisc
random: reorder READ_ONCE() in get_random_uXX
random: suppress spammy warnings about unseeded randomness
random: do not ignore early device randomness
random: warn when kernel uses unseeded randomness
random: add get_random_{bytes,u32,u64,int,long,once}_wait family
random: add wait_for_random_bytes() API
random: silence compiler warnings and fix race
random: invalidate batched entropy after crng init
random: move random_min_urandom_seed into CONFIG_SYSCTL ifdef block
random: convert get_random_int/long into get_random_u32/u64
random: fix comment for unused random_min_urandom_seed
random: remove variable limit
random: remove stale urandom_init_wait
random: remove stale maybe_reseed_primary_crng
9p: missing chunk of "fs/9p: Don't update file type when updating file attributes"
Linux 4.9.319
x86/speculation/mmio: Print SMT warning
KVM: x86/speculation: Disable Fill buffer clear within guests
x86/speculation/mmio: Reuse SRBDS mitigation for SBDS
x86/speculation/srbds: Update SRBDS mitigation selection
x86/speculation/mmio: Add sysfs reporting for Processor MMIO Stale Data
x86/speculation/mmio: Enable CPU Fill buffer clearing on idle
x86/bugs: Group MDS, TAA & Processor MMIO Stale Data mitigations
x86/speculation/mmio: Add mitigation for Processor MMIO Stale Data
x86/speculation: Add a common function for MD_CLEAR mitigation update
x86/speculation/mmio: Enumerate Processor MMIO Stale Data bug
Documentation: Add documentation for Processor MMIO Stale Data
x86/cpu: Add another Alder Lake CPU to the Intel family
x86/cpu: Add Lakefield, Alder Lake and Rocket Lake models to the to Intel CPU family
x86/cpu: Add Comet Lake to the Intel CPU models header
x86/CPU: Add more Icelake model numbers
x86/CPU: Add Icelake model number
x86/cpu: Add Cannonlake to Intel family
x86/cpu: Add Jasper Lake to Intel family
cpu/speculation: Add prototype for cpu_show_srbds()
x86/cpu: Add Elkhart Lake to Intel family
ANDROID: arch: fix backported syscall numbers
Linux 4.9.318
tcp: fix tcp_mtup_probe_success vs wrong snd_cwnd
PCI: qcom: Fix unbalanced PHY init on probe errors
mtd: cfi_cmdset_0002: Use chip_ready() for write on S29GL064N
mtd: cfi_cmdset_0002: Move and rename chip_check/chip_ready/chip_good_for_write
powerpc/32: Fix overread/overwrite of thread_struct via ptrace
Input: bcm5974 - set missing URB_NO_TRANSFER_DMA_MAP urb flag
nfc: st21nfca: fix memory leaks in EVT_TRANSACTION handling
nfc: st21nfca: fix incorrect validating logic in EVT_TRANSACTION
ata: libata-transport: fix {dma|pio|xfer}_mode sysfs files
cifs: return errors during session setup during reconnects
ALSA: hda/conexant - Fix loopback issue with CX20632
vringh: Fix loop descriptors check in the indirect cases
nodemask: Fix return values to be unsigned
modpost: fix undefined behavior of is_arm_mapping_symbol()
drm/radeon: fix a possible null pointer dereference
Revert "net: af_key: add check for pfkey_broadcast in function pfkey_process"
md: protect md_unregister_thread from reentrancy
serial: msm_serial: disable interrupts in __msm_console_write()
staging: rtl8712: fix uninit-value in r871xu_drv_init()
clocksource/drivers/sp804: Avoid error on multiple instances
misc: rtsx: set NULL intfdata when probe fails
usb: dwc2: gadget: don't reset gadget's driver->bus
USB: hcd-pci: Fully suspend across freeze/thaw cycle
drivers: usb: host: Fix deadlock in oxu_bus_suspend()
drivers: tty: serial: Fix deadlock in sa1100_set_termios()
USB: host: isp116x: check return value after calling platform_get_resource()
drivers: staging: rtl8192e: Fix deadlock in rtllib_beacons_stop()
tty: Fix a possible resource leak in icom_probe
tty: synclink_gt: Fix null-pointer-dereference in slgt_clean()
lkdtm/usercopy: Expand size of "out of frame" object
iio: dummy: iio_simple_dummy: check the return value of kstrdup()
net: altera: Fix refcount leak in altera_tse_mdio_create
net: xfrm: unexport __init-annotated xfrm4_protocol_init()
SUNRPC: Fix the calculation of xdr->end in xdr_get_next_encode_buffer()
net/mlx4_en: Fix wrong return value on ioctl EEPROM query failure
ata: pata_octeon_cf: Fix refcount leak in octeon_cf_probe
net: fix nla_strcmp to handle more then one trailing null character
video: fbdev: pxa3xx-gcu: release the resources correctly in pxa3xx_gcu_probe/remove()
m68knommu: fix undefined reference to `_init_sp'
m68knommu: set ZERO_PAGE() to the allocated zeroed page
i2c: cadence: Increase timeout per message if necessary
tracing: Avoid adding tracer option before update_tracer_options
tcp: tcp_rtx_synack() can be called from process context
jffs2: fix memory leak in jffs2_do_fill_super
modpost: fix removing numeric suffixes
net: ethernet: mtk_eth_soc: out of bounds read in mtk_hwlro_get_fdir_entry()
clocksource/drivers/oxnas-rps: Fix irq_of_parse_and_map() return value
firmware: dmi-sysfs: Fix memory leak in dmi_sysfs_register_handle
serial: st-asc: Sanitize CSIZE and correct PARENB for CS7
serial: sh-sci: Don't allow CS5-6
serial: txx9: Don't allow CS5-6
serial: digicolor-usart: Don't allow CS5-6
serial: meson: acquire port->lock in startup()
rtc: mt6397: check return value after calling platform_get_resource()
rpmsg: qcom_smd: Fix irq_of_parse_and_map() return value
pwm: lp3943: Fix duty calculation in case period was clamped
USB: storage: karma: fix rio_karma_init return
usb: usbip: add missing device lock on tweak configuration cmd
usb: usbip: fix a refcount leak in stub_probe()
staging: greybus: codecs: fix type confusion of list iterator variable
pcmcia: db1xxx_ss: restrict to MIPS_DB1XXX boards
netfilter: nf_tables: disallow non-stateful expression in sets earlier
MIPS: IP27: Remove incorrect `cpu_has_fpu' override
RDMA/rxe: Generate a completion for unsupported/invalid opcode
dt-bindings: gpio: altera: correct interrupt-cells
docs/conf.py: Cope with removal of language=None in Sphinx 5.0.0
gma500: fix an incorrect NULL check on list iterator
carl9170: tx: fix an incorrect use of list iterator
ASoC: rt5514: Fix event generation for "DSP Voice Wake Up" control
rtl818x: Prevent using not initialized queues
hugetlb: fix huge_pmd_unshare address update
nodemask.h: fix compilation error with GCC12
iommu/msm: Fix an incorrect NULL check on list iterator
um: Fix out-of-bounds read in LDT setup
um: chan_user: Fix winch_tramp() return value
mac80211: upgrade passive scan to active scan on DFS channels after beacon rx
irqchip: irq-xtensa-mx: fix initial IRQ affinity
irqchip/armada-370-xp: Do not touch Performance Counter Overflow on A375, A38x, A39x
RDMA/hfi1: Fix potential integer multiplication overflow errors
md: fix an incorrect NULL check in md_reload_sb
md: fix an incorrect NULL check in does_sb_need_changing
drm/bridge: analogix_dp: Grab runtime PM reference for DP-AUX
drm/amdgpu/cs: make commands with 0 chunks illegal behaviour.
scsi: ufs: qcom: Add a readl() to make sure ref_clk gets enabled
scsi: dc395x: Fix a missing check on list iterator
ocfs2: dlmfs: fix error handling of user_dlm_destroy_lock
dlm: fix missing lkb refcount handling
dlm: fix plock invalid read
ext4: verify dir block before splitting it
ext4: fix bug_on in ext4_writepages
ext4: fix use-after-free in ext4_rename_dir_prepare
fs-writeback: writeback_sb_inodes:Recalculate 'wrote' according skipped pages
iwlwifi: mvm: fix assert 1F04 upon reconfig
wifi: mac80211: fix use-after-free in chanctx code
iommu/amd: Increase timeout waiting for GA log enablement
video: fbdev: clcdfb: Fix refcount leak in clcdfb_of_vram_setup
Input: sparcspkr - fix refcount leak in bbc_beep_probe
tty: fix deadlock caused by calling printk() under tty_port->lock
powerpc/4xx/cpm: Fix return value of __setup() handler
powerpc/idle: Fix return value of __setup() handler
powerpc/8xx: export 'cpm_setbrg' for modules
drivers/base/node.c: fix compaction sysfs file leak
scsi: fcoe: Fix Wstringop-overflow warnings in fcoe_wwn_from_mac()
mfd: ipaq-micro: Fix error check return value of platform_get_irq()
soc: qcom: smsm: Fix missing of_node_put() in smsm_parse_ipc
soc: qcom: smp2p: Fix missing of_node_put() in smp2p_parse_ipc
rxrpc: Don't try to resend the request if we're receiving the reply
rxrpc: Fix listen() setting the bar too high for the prealloc rings
ASoC: wm2000: fix missing clk_disable_unprepare() on error in wm2000_anc_transition()
sctp: read sk->sk_bound_dev_if once in sctp_rcv()
m68k: math-emu: Fix dependencies of math emulation support
Bluetooth: fix dangling sco_conn and use-after-free in sco_sock_timeout
media: pvrusb2: fix array-index-out-of-bounds in pvr2_i2c_core_init
media: exynos4-is: Change clk_disable to clk_disable_unprepare
regulator: pfuze100: Fix refcount leak in pfuze_parse_regulators_dt
ASoC: mxs-saif: Fix refcount leak in mxs_saif_probe
media: uvcvideo: Fix missing check to determine if element is found in list
drm/msm: return an error pointer in msm_gem_prime_get_sg_table()
x86/mm: Cleanup the control_va_addr_alignment() __setup handler
drm/rockchip: vop: fix possible null-ptr-deref in vop_bind()
drm/msm/hdmi: check return value after calling platform_get_resource_byname()
drm/msm/dsi: fix error checks and return values for DSI xmit functions
x86/pm: Fix false positive kmemleak report in msr_build_context()
inotify: show inotify mask flags in proc fdinfo
ath9k_htc: fix potential out of bounds access with invalid rxstatus->rs_keyix
spi: img-spfi: Fix pm_runtime_get_sync() error checking
HID: hid-led: fix maximum brightness for Dream Cheeky
NFC: NULL out the dev->rfkill to prevent UAF
spi: spi-ti-qspi: Fix return value handling of wait_for_completion_timeout
drm/mediatek: Fix mtk_cec_mask()
x86/delay: Fix the wrong asm constraint in delay_loop()
ASoC: mediatek: Fix error handling in mt8173_max98090_dev_probe
drm: fix EDID struct for old ARM OABI format
macintosh/via-pmu: Fix build failure when CONFIG_INPUT is disabled
powerpc/xics: fix refcount leak in icp_opal_init()
PCI: Avoid pci_dev_lock() AB/BA deadlock with sriov_numvfs_store()
ARM: hisi: Add missing of_node_put after of_find_compatible_node
ARM: dts: exynos: add atmel,24c128 fallback to Samsung EEPROM
ARM: versatile: Add missing of_node_put in dcscb_init
fat: add ratelimit to fat*_ent_bread()
ARM: OMAP1: clock: Fix UART rate reporting algorithm
fs: jfs: fix possible NULL pointer dereference in dbFree()
eth: tg3: silence the GCC 12 array-bounds warning
rxrpc: Return an error to sendmsg if call failed
media: exynos4-is: Fix compile warning
ASoC: rt5645: Fix errorenous cleanup order
nvme-pci: fix a NULL pointer dereference in nvme_alloc_admin_tags
openrisc: start CPU timer early in boot
ipmi:ssif: Check for NULL msg when handling events and messages
dma-debug: change allocation mode from GFP_NOWAIT to GFP_ATIOMIC
ASoC: dapm: Don't fold register value changes into notifications
ipv6: Don't send rs packets to the interface of ARPHRD_TUNNEL
drm/amd/pm: fix the compile warning
scsi: megaraid: Fix error check return value of register_chrdev()
media: cx25821: Fix the warning when removing the module
ath9k: fix QCA9561 PA bias level
drm/amd/pm: fix double free in si_parse_power_table()
ALSA: jack: Access input_dev under mutex
ACPICA: Avoid cache flush inside virtual machines
ipw2x00: Fix potential NULL dereference in libipw_xmit()
b43: Fix assigning negative value to unsigned variable
b43legacy: Fix assigning negative value to unsigned variable
mwifiex: add mutex lock for call in mwifiex_dfs_chan_sw_work_queue
drm/virtio: fix NULL pointer dereference in virtio_gpu_conn_get_modes
btrfs: add "0x" prefix for unsupported optional features
ptrace: Reimplement PTRACE_KILL by always sending SIGKILL
ptrace/xtensa: Replace PT_SINGLESTEP with TIF_SINGLESTEP
USB: new quirk for Dell Gen 2 devices
BACKPORT: psi: Fix uaf issue when psi trigger is destroyed while being polled
Conflicts:
arch/arm/include/asm/unistd.h
arch/arm/kernel/calls.S
drivers/char/Kconfig
drivers/char/random.c
fs/fat/fatent.c
include/linux/random.h
init/main.c
kernel/cpu.c
lib/Makefile
Change-Id: I43d99223205dec1f47e87016818be23514a62cba
2395 lines
59 KiB
C
2395 lines
59 KiB
C
/* CPU control.
|
|
* (C) 2001, 2002, 2003, 2004 Rusty Russell
|
|
*
|
|
* This code is licenced under the GPL.
|
|
*/
|
|
#include <linux/proc_fs.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/init.h>
|
|
#include <linux/notifier.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/sched/smt.h>
|
|
#include <linux/unistd.h>
|
|
#include <linux/cpu.h>
|
|
#include <linux/oom.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/export.h>
|
|
#include <linux/bug.h>
|
|
#include <linux/kthread.h>
|
|
#include <linux/stop_machine.h>
|
|
#include <linux/mutex.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/suspend.h>
|
|
#include <linux/lockdep.h>
|
|
#include <linux/tick.h>
|
|
#include <linux/irq.h>
|
|
#include <linux/smpboot.h>
|
|
#include <linux/relay.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/random.h>
|
|
#include <linux/highmem.h>
|
|
|
|
#include <trace/events/power.h>
|
|
#define CREATE_TRACE_POINTS
|
|
#include <trace/events/cpuhp.h>
|
|
|
|
#include "smpboot.h"
|
|
|
|
/**
|
|
* cpuhp_cpu_state - Per cpu hotplug state storage
|
|
* @state: The current cpu state
|
|
* @target: The target state
|
|
* @thread: Pointer to the hotplug thread
|
|
* @should_run: Thread should execute
|
|
* @rollback: Perform a rollback
|
|
* @single: Single callback invocation
|
|
* @bringup: Single callback bringup or teardown selector
|
|
* @cb_state: The state for a single callback (install/uninstall)
|
|
* @result: Result of the operation
|
|
* @done: Signal completion to the issuer of the task
|
|
*/
|
|
struct cpuhp_cpu_state {
|
|
enum cpuhp_state state;
|
|
enum cpuhp_state target;
|
|
#ifdef CONFIG_SMP
|
|
struct task_struct *thread;
|
|
bool should_run;
|
|
bool rollback;
|
|
bool single;
|
|
bool bringup;
|
|
bool booted_once;
|
|
struct hlist_node *node;
|
|
enum cpuhp_state cb_state;
|
|
int result;
|
|
struct completion done;
|
|
#endif
|
|
};
|
|
|
|
static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state);
|
|
|
|
#if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP)
|
|
static struct lock_class_key cpuhp_state_key;
|
|
static struct lockdep_map cpuhp_state_lock_map =
|
|
STATIC_LOCKDEP_MAP_INIT("cpuhp_state", &cpuhp_state_key);
|
|
#endif
|
|
|
|
/**
|
|
* cpuhp_step - Hotplug state machine step
|
|
* @name: Name of the step
|
|
* @startup: Startup function of the step
|
|
* @teardown: Teardown function of the step
|
|
* @skip_onerr: Do not invoke the functions on error rollback
|
|
* Will go away once the notifiers are gone
|
|
* @cant_stop: Bringup/teardown can't be stopped at this step
|
|
*/
|
|
struct cpuhp_step {
|
|
const char *name;
|
|
union {
|
|
int (*single)(unsigned int cpu);
|
|
int (*multi)(unsigned int cpu,
|
|
struct hlist_node *node);
|
|
} startup;
|
|
union {
|
|
int (*single)(unsigned int cpu);
|
|
int (*multi)(unsigned int cpu,
|
|
struct hlist_node *node);
|
|
} teardown;
|
|
struct hlist_head list;
|
|
bool skip_onerr;
|
|
bool cant_stop;
|
|
bool multi_instance;
|
|
};
|
|
|
|
static DEFINE_MUTEX(cpuhp_state_mutex);
|
|
static struct cpuhp_step cpuhp_bp_states[];
|
|
static struct cpuhp_step cpuhp_ap_states[];
|
|
|
|
static bool cpuhp_is_ap_state(enum cpuhp_state state)
|
|
{
|
|
/*
|
|
* The extra check for CPUHP_TEARDOWN_CPU is only for documentation
|
|
* purposes as that state is handled explicitly in cpu_down.
|
|
*/
|
|
return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU;
|
|
}
|
|
|
|
static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
|
|
{
|
|
struct cpuhp_step *sp;
|
|
|
|
sp = cpuhp_is_ap_state(state) ? cpuhp_ap_states : cpuhp_bp_states;
|
|
return sp + state;
|
|
}
|
|
|
|
/**
|
|
* cpuhp_invoke_callback _ Invoke the callbacks for a given state
|
|
* @cpu: The cpu for which the callback should be invoked
|
|
* @step: The step in the state machine
|
|
* @bringup: True if the bringup callback should be invoked
|
|
*
|
|
* Called from cpu hotplug and from the state register machinery.
|
|
*/
|
|
static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state,
|
|
bool bringup, struct hlist_node *node)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
struct cpuhp_step *step = cpuhp_get_step(state);
|
|
int (*cbm)(unsigned int cpu, struct hlist_node *node);
|
|
int (*cb)(unsigned int cpu);
|
|
int ret, cnt;
|
|
|
|
if (!step->multi_instance) {
|
|
cb = bringup ? step->startup.single : step->teardown.single;
|
|
if (!cb)
|
|
return 0;
|
|
trace_cpuhp_enter(cpu, st->target, state, cb);
|
|
ret = cb(cpu);
|
|
trace_cpuhp_exit(cpu, st->state, state, ret);
|
|
return ret;
|
|
}
|
|
cbm = bringup ? step->startup.multi : step->teardown.multi;
|
|
if (!cbm)
|
|
return 0;
|
|
|
|
/* Single invocation for instance add/remove */
|
|
if (node) {
|
|
trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
|
|
ret = cbm(cpu, node);
|
|
trace_cpuhp_exit(cpu, st->state, state, ret);
|
|
return ret;
|
|
}
|
|
|
|
/* State transition. Invoke on all instances */
|
|
cnt = 0;
|
|
hlist_for_each(node, &step->list) {
|
|
trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
|
|
ret = cbm(cpu, node);
|
|
trace_cpuhp_exit(cpu, st->state, state, ret);
|
|
if (ret)
|
|
goto err;
|
|
cnt++;
|
|
}
|
|
return 0;
|
|
err:
|
|
/* Rollback the instances if one failed */
|
|
cbm = !bringup ? step->startup.multi : step->teardown.multi;
|
|
if (!cbm)
|
|
return ret;
|
|
|
|
hlist_for_each(node, &step->list) {
|
|
if (!cnt--)
|
|
break;
|
|
cbm(cpu, node);
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
/* Serializes the updates to cpu_online_mask, cpu_present_mask */
|
|
static DEFINE_MUTEX(cpu_add_remove_lock);
|
|
bool cpuhp_tasks_frozen;
|
|
EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen);
|
|
|
|
/*
|
|
* The following two APIs (cpu_maps_update_begin/done) must be used when
|
|
* attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
|
|
* The APIs cpu_notifier_register_begin/done() must be used to protect CPU
|
|
* hotplug callback (un)registration performed using __register_cpu_notifier()
|
|
* or __unregister_cpu_notifier().
|
|
*/
|
|
void cpu_maps_update_begin(void)
|
|
{
|
|
mutex_lock(&cpu_add_remove_lock);
|
|
}
|
|
EXPORT_SYMBOL(cpu_notifier_register_begin);
|
|
|
|
void cpu_maps_update_done(void)
|
|
{
|
|
mutex_unlock(&cpu_add_remove_lock);
|
|
}
|
|
EXPORT_SYMBOL(cpu_notifier_register_done);
|
|
|
|
static RAW_NOTIFIER_HEAD(cpu_chain);
|
|
|
|
/* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
|
|
* Should always be manipulated under cpu_add_remove_lock
|
|
*/
|
|
static int cpu_hotplug_disabled;
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
static struct {
|
|
struct task_struct *active_writer;
|
|
/* wait queue to wake up the active_writer */
|
|
wait_queue_head_t wq;
|
|
/* verifies that no writer will get active while readers are active */
|
|
struct mutex lock;
|
|
/*
|
|
* Also blocks the new readers during
|
|
* an ongoing cpu hotplug operation.
|
|
*/
|
|
atomic_t refcount;
|
|
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
struct lockdep_map dep_map;
|
|
#endif
|
|
} cpu_hotplug = {
|
|
.active_writer = NULL,
|
|
.wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
|
|
.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
|
|
#ifdef CONFIG_DEBUG_LOCK_ALLOC
|
|
.dep_map = STATIC_LOCKDEP_MAP_INIT("cpu_hotplug.dep_map", &cpu_hotplug.dep_map),
|
|
#endif
|
|
};
|
|
|
|
/* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */
|
|
#define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map)
|
|
#define cpuhp_lock_acquire_tryread() \
|
|
lock_map_acquire_tryread(&cpu_hotplug.dep_map)
|
|
#define cpuhp_lock_acquire() lock_map_acquire(&cpu_hotplug.dep_map)
|
|
#define cpuhp_lock_release() lock_map_release(&cpu_hotplug.dep_map)
|
|
|
|
void cpu_hotplug_mutex_held(void)
|
|
{
|
|
lockdep_assert_held(&cpu_hotplug.lock);
|
|
}
|
|
EXPORT_SYMBOL(cpu_hotplug_mutex_held);
|
|
|
|
void get_online_cpus(void)
|
|
{
|
|
might_sleep();
|
|
if (cpu_hotplug.active_writer == current)
|
|
return;
|
|
cpuhp_lock_acquire_read();
|
|
mutex_lock(&cpu_hotplug.lock);
|
|
atomic_inc(&cpu_hotplug.refcount);
|
|
mutex_unlock(&cpu_hotplug.lock);
|
|
}
|
|
EXPORT_SYMBOL_GPL(get_online_cpus);
|
|
|
|
void put_online_cpus(void)
|
|
{
|
|
int refcount;
|
|
|
|
if (cpu_hotplug.active_writer == current)
|
|
return;
|
|
|
|
refcount = atomic_dec_return(&cpu_hotplug.refcount);
|
|
if (WARN_ON(refcount < 0)) /* try to fix things up */
|
|
atomic_inc(&cpu_hotplug.refcount);
|
|
|
|
if (refcount <= 0 && waitqueue_active(&cpu_hotplug.wq))
|
|
wake_up(&cpu_hotplug.wq);
|
|
|
|
cpuhp_lock_release();
|
|
|
|
}
|
|
EXPORT_SYMBOL_GPL(put_online_cpus);
|
|
|
|
/*
|
|
* This ensures that the hotplug operation can begin only when the
|
|
* refcount goes to zero.
|
|
*
|
|
* Note that during a cpu-hotplug operation, the new readers, if any,
|
|
* will be blocked by the cpu_hotplug.lock
|
|
*
|
|
* Since cpu_hotplug_begin() is always called after invoking
|
|
* cpu_maps_update_begin(), we can be sure that only one writer is active.
|
|
*
|
|
* Note that theoretically, there is a possibility of a livelock:
|
|
* - Refcount goes to zero, last reader wakes up the sleeping
|
|
* writer.
|
|
* - Last reader unlocks the cpu_hotplug.lock.
|
|
* - A new reader arrives at this moment, bumps up the refcount.
|
|
* - The writer acquires the cpu_hotplug.lock finds the refcount
|
|
* non zero and goes to sleep again.
|
|
*
|
|
* However, this is very difficult to achieve in practice since
|
|
* get_online_cpus() not an api which is called all that often.
|
|
*
|
|
*/
|
|
void cpu_hotplug_begin(void)
|
|
{
|
|
DEFINE_WAIT(wait);
|
|
|
|
cpu_hotplug.active_writer = current;
|
|
cpuhp_lock_acquire();
|
|
|
|
for (;;) {
|
|
mutex_lock(&cpu_hotplug.lock);
|
|
prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE);
|
|
if (likely(!atomic_read(&cpu_hotplug.refcount)))
|
|
break;
|
|
mutex_unlock(&cpu_hotplug.lock);
|
|
schedule();
|
|
}
|
|
finish_wait(&cpu_hotplug.wq, &wait);
|
|
}
|
|
|
|
void cpu_hotplug_done(void)
|
|
{
|
|
cpu_hotplug.active_writer = NULL;
|
|
mutex_unlock(&cpu_hotplug.lock);
|
|
cpuhp_lock_release();
|
|
}
|
|
|
|
/*
|
|
* Wait for currently running CPU hotplug operations to complete (if any) and
|
|
* disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects
|
|
* the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the
|
|
* hotplug path before performing hotplug operations. So acquiring that lock
|
|
* guarantees mutual exclusion from any currently running hotplug operations.
|
|
*/
|
|
void cpu_hotplug_disable(void)
|
|
{
|
|
cpu_maps_update_begin();
|
|
cpu_hotplug_disabled++;
|
|
cpu_maps_update_done();
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_hotplug_disable);
|
|
|
|
static void __cpu_hotplug_enable(void)
|
|
{
|
|
if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n"))
|
|
return;
|
|
cpu_hotplug_disabled--;
|
|
}
|
|
|
|
void cpu_hotplug_enable(void)
|
|
{
|
|
cpu_maps_update_begin();
|
|
__cpu_hotplug_enable();
|
|
cpu_maps_update_done();
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
|
|
#endif /* CONFIG_HOTPLUG_CPU */
|
|
|
|
/*
|
|
* Architectures that need SMT-specific errata handling during SMT hotplug
|
|
* should override this.
|
|
*/
|
|
void __weak arch_smt_update(void) { }
|
|
|
|
#ifdef CONFIG_HOTPLUG_SMT
|
|
enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
|
|
EXPORT_SYMBOL_GPL(cpu_smt_control);
|
|
|
|
static bool cpu_smt_available __read_mostly;
|
|
|
|
void __init cpu_smt_disable(bool force)
|
|
{
|
|
if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
|
|
cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
|
|
return;
|
|
|
|
if (force) {
|
|
pr_info("SMT: Force disabled\n");
|
|
cpu_smt_control = CPU_SMT_FORCE_DISABLED;
|
|
} else {
|
|
pr_info("SMT: disabled\n");
|
|
cpu_smt_control = CPU_SMT_DISABLED;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* The decision whether SMT is supported can only be done after the full
|
|
* CPU identification. Called from architecture code before non boot CPUs
|
|
* are brought up.
|
|
*/
|
|
void __init cpu_smt_check_topology_early(void)
|
|
{
|
|
if (!topology_smt_supported())
|
|
cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
|
|
}
|
|
|
|
/*
|
|
* If SMT was disabled by BIOS, detect it here, after the CPUs have been
|
|
* brought online. This ensures the smt/l1tf sysfs entries are consistent
|
|
* with reality. cpu_smt_available is set to true during the bringup of non
|
|
* boot CPUs when a SMT sibling is detected. Note, this may overwrite
|
|
* cpu_smt_control's previous setting.
|
|
*/
|
|
void __init cpu_smt_check_topology(void)
|
|
{
|
|
if (!cpu_smt_available)
|
|
cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
|
|
}
|
|
|
|
static int __init smt_cmdline_disable(char *str)
|
|
{
|
|
cpu_smt_disable(str && !strcmp(str, "force"));
|
|
return 0;
|
|
}
|
|
early_param("nosmt", smt_cmdline_disable);
|
|
|
|
static inline bool cpu_smt_allowed(unsigned int cpu)
|
|
{
|
|
if (topology_is_primary_thread(cpu))
|
|
return true;
|
|
|
|
/*
|
|
* If the CPU is not a 'primary' thread and the booted_once bit is
|
|
* set then the processor has SMT support. Store this information
|
|
* for the late check of SMT support in cpu_smt_check_topology().
|
|
*/
|
|
if (per_cpu(cpuhp_state, cpu).booted_once)
|
|
cpu_smt_available = true;
|
|
|
|
if (cpu_smt_control == CPU_SMT_ENABLED)
|
|
return true;
|
|
|
|
/*
|
|
* On x86 it's required to boot all logical CPUs at least once so
|
|
* that the init code can get a chance to set CR4.MCE on each
|
|
* CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
|
|
* core will shutdown the machine.
|
|
*/
|
|
return !per_cpu(cpuhp_state, cpu).booted_once;
|
|
}
|
|
#else
|
|
static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
|
|
#endif
|
|
|
|
/* Need to know about CPUs going up/down? */
|
|
int register_cpu_notifier(struct notifier_block *nb)
|
|
{
|
|
int ret;
|
|
cpu_maps_update_begin();
|
|
ret = raw_notifier_chain_register(&cpu_chain, nb);
|
|
cpu_maps_update_done();
|
|
return ret;
|
|
}
|
|
|
|
int __register_cpu_notifier(struct notifier_block *nb)
|
|
{
|
|
return raw_notifier_chain_register(&cpu_chain, nb);
|
|
}
|
|
|
|
static int __cpu_notify(unsigned long val, unsigned int cpu, int nr_to_call,
|
|
int *nr_calls)
|
|
{
|
|
unsigned long mod = cpuhp_tasks_frozen ? CPU_TASKS_FROZEN : 0;
|
|
void *hcpu = (void *)(long)cpu;
|
|
|
|
int ret;
|
|
|
|
ret = __raw_notifier_call_chain(&cpu_chain, val | mod, hcpu, nr_to_call,
|
|
nr_calls);
|
|
|
|
return notifier_to_errno(ret);
|
|
}
|
|
|
|
static int cpu_notify(unsigned long val, unsigned int cpu)
|
|
{
|
|
return __cpu_notify(val, cpu, -1, NULL);
|
|
}
|
|
|
|
static void cpu_notify_nofail(unsigned long val, unsigned int cpu)
|
|
{
|
|
BUG_ON(cpu_notify(val, cpu));
|
|
}
|
|
|
|
/* Notifier wrappers for transitioning to state machine */
|
|
static int notify_prepare(unsigned int cpu)
|
|
{
|
|
int nr_calls = 0;
|
|
int ret;
|
|
|
|
ret = __cpu_notify(CPU_UP_PREPARE, cpu, -1, &nr_calls);
|
|
if (ret) {
|
|
nr_calls--;
|
|
printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",
|
|
__func__, cpu);
|
|
__cpu_notify(CPU_UP_CANCELED, cpu, nr_calls, NULL);
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
static int notify_online(unsigned int cpu)
|
|
{
|
|
cpu_notify(CPU_ONLINE, cpu);
|
|
return 0;
|
|
}
|
|
static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st);
|
|
|
|
static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st);
|
|
|
|
static int bringup_wait_for_ap(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
|
|
/* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */
|
|
wait_for_completion(&st->done);
|
|
if (WARN_ON_ONCE((!cpu_online(cpu))))
|
|
return -ECANCELED;
|
|
|
|
/* Unpark the hotplug thread of the target cpu */
|
|
kthread_unpark(st->thread);
|
|
|
|
/*
|
|
* SMT soft disabling on X86 requires to bring the CPU out of the
|
|
* BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The
|
|
* CPU marked itself as booted_once in cpu_notify_starting() so the
|
|
* cpu_smt_allowed() check will now return false if this is not the
|
|
* primary sibling.
|
|
*/
|
|
if (!cpu_smt_allowed(cpu))
|
|
return -ECANCELED;
|
|
|
|
/* Should we go further up ? */
|
|
if (st->target > CPUHP_AP_ONLINE_IDLE) {
|
|
__cpuhp_kick_ap_work(st);
|
|
wait_for_completion(&st->done);
|
|
}
|
|
return st->result;
|
|
}
|
|
|
|
static int bringup_cpu(unsigned int cpu)
|
|
{
|
|
struct task_struct *idle = idle_thread_get(cpu);
|
|
int ret;
|
|
|
|
/*
|
|
* Some architectures have to walk the irq descriptors to
|
|
* setup the vector space for the cpu which comes online.
|
|
* Prevent irq alloc/free across the bringup.
|
|
*/
|
|
irq_lock_sparse();
|
|
|
|
/* Arch-specific enabling code. */
|
|
ret = __cpu_up(cpu, idle);
|
|
irq_unlock_sparse();
|
|
if (ret) {
|
|
cpu_notify(CPU_UP_CANCELED, cpu);
|
|
return ret;
|
|
}
|
|
return bringup_wait_for_ap(cpu);
|
|
}
|
|
|
|
/*
|
|
* Hotplug state machine related functions
|
|
*/
|
|
static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st)
|
|
{
|
|
for (st->state++; st->state < st->target; st->state++) {
|
|
struct cpuhp_step *step = cpuhp_get_step(st->state);
|
|
|
|
if (!step->skip_onerr)
|
|
cpuhp_invoke_callback(cpu, st->state, true, NULL);
|
|
}
|
|
}
|
|
|
|
static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
|
|
enum cpuhp_state target)
|
|
{
|
|
enum cpuhp_state prev_state = st->state;
|
|
int ret = 0;
|
|
|
|
for (; st->state > target; st->state--) {
|
|
ret = cpuhp_invoke_callback(cpu, st->state, false, NULL);
|
|
BUG_ON(ret && st->state < CPUHP_AP_IDLE_DEAD);
|
|
if (ret) {
|
|
st->target = prev_state;
|
|
undo_cpu_down(cpu, st);
|
|
break;
|
|
}
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st)
|
|
{
|
|
for (st->state--; st->state > st->target; st->state--) {
|
|
struct cpuhp_step *step = cpuhp_get_step(st->state);
|
|
|
|
if (!step->skip_onerr)
|
|
cpuhp_invoke_callback(cpu, st->state, false, NULL);
|
|
}
|
|
}
|
|
|
|
static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st)
|
|
{
|
|
if (IS_ENABLED(CONFIG_HOTPLUG_CPU))
|
|
return true;
|
|
/*
|
|
* When CPU hotplug is disabled, then taking the CPU down is not
|
|
* possible because takedown_cpu() and the architecture and
|
|
* subsystem specific mechanisms are not available. So the CPU
|
|
* which would be completely unplugged again needs to stay around
|
|
* in the current state.
|
|
*/
|
|
return st->state <= CPUHP_BRINGUP_CPU;
|
|
}
|
|
|
|
static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
|
|
enum cpuhp_state target)
|
|
{
|
|
enum cpuhp_state prev_state = st->state;
|
|
int ret = 0;
|
|
|
|
while (st->state < target) {
|
|
st->state++;
|
|
ret = cpuhp_invoke_callback(cpu, st->state, true, NULL);
|
|
if (ret) {
|
|
if (can_rollback_cpu(st)) {
|
|
st->target = prev_state;
|
|
undo_cpu_up(cpu, st);
|
|
}
|
|
break;
|
|
}
|
|
}
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* The cpu hotplug threads manage the bringup and teardown of the cpus
|
|
*/
|
|
static void cpuhp_create(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
|
|
init_completion(&st->done);
|
|
}
|
|
|
|
static int cpuhp_should_run(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
|
|
|
|
return st->should_run;
|
|
}
|
|
|
|
/* Execute the teardown callbacks. Used to be CPU_DOWN_PREPARE */
|
|
static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st)
|
|
{
|
|
enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU);
|
|
|
|
return cpuhp_down_callbacks(cpu, st, target);
|
|
}
|
|
|
|
/* Execute the online startup callbacks. Used to be CPU_ONLINE */
|
|
static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st)
|
|
{
|
|
return cpuhp_up_callbacks(cpu, st, st->target);
|
|
}
|
|
|
|
/*
|
|
* Execute teardown/startup callbacks on the plugged cpu. Also used to invoke
|
|
* callbacks when a state gets [un]installed at runtime.
|
|
*/
|
|
static void cpuhp_thread_fun(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
|
|
int ret = 0;
|
|
|
|
/*
|
|
* Paired with the mb() in cpuhp_kick_ap_work and
|
|
* cpuhp_invoke_ap_callback, so the work set is consistent visible.
|
|
*/
|
|
smp_mb();
|
|
if (!st->should_run)
|
|
return;
|
|
|
|
st->should_run = false;
|
|
|
|
lock_map_acquire(&cpuhp_state_lock_map);
|
|
/* Single callback invocation for [un]install ? */
|
|
if (st->single) {
|
|
if (st->cb_state < CPUHP_AP_ONLINE) {
|
|
local_irq_disable();
|
|
ret = cpuhp_invoke_callback(cpu, st->cb_state,
|
|
st->bringup, st->node);
|
|
local_irq_enable();
|
|
} else {
|
|
ret = cpuhp_invoke_callback(cpu, st->cb_state,
|
|
st->bringup, st->node);
|
|
}
|
|
} else if (st->rollback) {
|
|
BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
|
|
|
|
undo_cpu_down(cpu, st);
|
|
/*
|
|
* This is a momentary workaround to keep the notifier users
|
|
* happy. Will go away once we got rid of the notifiers.
|
|
*/
|
|
cpu_notify_nofail(CPU_DOWN_FAILED, cpu);
|
|
st->rollback = false;
|
|
} else {
|
|
/* Cannot happen .... */
|
|
BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
|
|
|
|
/* Regular hotplug work */
|
|
if (st->state < st->target)
|
|
ret = cpuhp_ap_online(cpu, st);
|
|
else if (st->state > st->target)
|
|
ret = cpuhp_ap_offline(cpu, st);
|
|
}
|
|
lock_map_release(&cpuhp_state_lock_map);
|
|
st->result = ret;
|
|
complete(&st->done);
|
|
}
|
|
|
|
/* Invoke a single callback on a remote cpu */
|
|
static int
|
|
cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup,
|
|
struct hlist_node *node)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
|
|
if (!cpu_online(cpu))
|
|
return 0;
|
|
|
|
lock_map_acquire(&cpuhp_state_lock_map);
|
|
lock_map_release(&cpuhp_state_lock_map);
|
|
|
|
/*
|
|
* If we are up and running, use the hotplug thread. For early calls
|
|
* we invoke the thread function directly.
|
|
*/
|
|
if (!st->thread)
|
|
return cpuhp_invoke_callback(cpu, state, bringup, node);
|
|
|
|
st->cb_state = state;
|
|
st->single = true;
|
|
st->bringup = bringup;
|
|
st->node = node;
|
|
|
|
/*
|
|
* Make sure the above stores are visible before should_run becomes
|
|
* true. Paired with the mb() above in cpuhp_thread_fun()
|
|
*/
|
|
smp_mb();
|
|
st->should_run = true;
|
|
wake_up_process(st->thread);
|
|
wait_for_completion(&st->done);
|
|
return st->result;
|
|
}
|
|
|
|
/* Regular hotplug invocation of the AP hotplug thread */
|
|
static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st)
|
|
{
|
|
st->result = 0;
|
|
st->single = false;
|
|
/*
|
|
* Make sure the above stores are visible before should_run becomes
|
|
* true. Paired with the mb() above in cpuhp_thread_fun()
|
|
*/
|
|
smp_mb();
|
|
st->should_run = true;
|
|
wake_up_process(st->thread);
|
|
}
|
|
|
|
static int cpuhp_kick_ap_work(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
enum cpuhp_state state = st->state;
|
|
|
|
trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work);
|
|
lock_map_acquire(&cpuhp_state_lock_map);
|
|
lock_map_release(&cpuhp_state_lock_map);
|
|
__cpuhp_kick_ap_work(st);
|
|
wait_for_completion(&st->done);
|
|
trace_cpuhp_exit(cpu, st->state, state, st->result);
|
|
return st->result;
|
|
}
|
|
|
|
static struct smp_hotplug_thread cpuhp_threads = {
|
|
.store = &cpuhp_state.thread,
|
|
.create = &cpuhp_create,
|
|
.thread_should_run = cpuhp_should_run,
|
|
.thread_fn = cpuhp_thread_fun,
|
|
.thread_comm = "cpuhp/%u",
|
|
.selfparking = true,
|
|
};
|
|
|
|
void __init cpuhp_threads_init(void)
|
|
{
|
|
BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads));
|
|
kthread_unpark(this_cpu_read(cpuhp_state.thread));
|
|
}
|
|
|
|
EXPORT_SYMBOL(register_cpu_notifier);
|
|
EXPORT_SYMBOL(__register_cpu_notifier);
|
|
void unregister_cpu_notifier(struct notifier_block *nb)
|
|
{
|
|
cpu_maps_update_begin();
|
|
raw_notifier_chain_unregister(&cpu_chain, nb);
|
|
cpu_maps_update_done();
|
|
}
|
|
EXPORT_SYMBOL(unregister_cpu_notifier);
|
|
|
|
void __unregister_cpu_notifier(struct notifier_block *nb)
|
|
{
|
|
raw_notifier_chain_unregister(&cpu_chain, nb);
|
|
}
|
|
EXPORT_SYMBOL(__unregister_cpu_notifier);
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
#ifndef arch_clear_mm_cpumask_cpu
|
|
#define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm))
|
|
#endif
|
|
|
|
/**
|
|
* clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
|
|
* @cpu: a CPU id
|
|
*
|
|
* This function walks all processes, finds a valid mm struct for each one and
|
|
* then clears a corresponding bit in mm's cpumask. While this all sounds
|
|
* trivial, there are various non-obvious corner cases, which this function
|
|
* tries to solve in a safe manner.
|
|
*
|
|
* Also note that the function uses a somewhat relaxed locking scheme, so it may
|
|
* be called only for an already offlined CPU.
|
|
*/
|
|
void clear_tasks_mm_cpumask(int cpu)
|
|
{
|
|
struct task_struct *p;
|
|
|
|
/*
|
|
* This function is called after the cpu is taken down and marked
|
|
* offline, so its not like new tasks will ever get this cpu set in
|
|
* their mm mask. -- Peter Zijlstra
|
|
* Thus, we may use rcu_read_lock() here, instead of grabbing
|
|
* full-fledged tasklist_lock.
|
|
*/
|
|
WARN_ON(cpu_online(cpu));
|
|
rcu_read_lock();
|
|
for_each_process(p) {
|
|
struct task_struct *t;
|
|
|
|
/*
|
|
* Main thread might exit, but other threads may still have
|
|
* a valid mm. Find one.
|
|
*/
|
|
t = find_lock_task_mm(p);
|
|
if (!t)
|
|
continue;
|
|
arch_clear_mm_cpumask_cpu(cpu, t->mm);
|
|
task_unlock(t);
|
|
}
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
static inline void check_for_tasks(int dead_cpu)
|
|
{
|
|
struct task_struct *g, *p;
|
|
|
|
read_lock(&tasklist_lock);
|
|
for_each_process_thread(g, p) {
|
|
if (!p->on_rq)
|
|
continue;
|
|
/*
|
|
* We do the check with unlocked task_rq(p)->lock.
|
|
* Order the reading to do not warn about a task,
|
|
* which was running on this cpu in the past, and
|
|
* it's just been woken on another cpu.
|
|
*/
|
|
rmb();
|
|
if (task_cpu(p) != dead_cpu)
|
|
continue;
|
|
|
|
pr_warn("Task %s (pid=%d) is on cpu %d (state=%ld, flags=%x)\n",
|
|
p->comm, task_pid_nr(p), dead_cpu, p->state, p->flags);
|
|
}
|
|
read_unlock(&tasklist_lock);
|
|
}
|
|
|
|
static int notify_down_prepare(unsigned int cpu)
|
|
{
|
|
int err, nr_calls = 0;
|
|
|
|
err = __cpu_notify(CPU_DOWN_PREPARE, cpu, -1, &nr_calls);
|
|
if (err) {
|
|
nr_calls--;
|
|
__cpu_notify(CPU_DOWN_FAILED, cpu, nr_calls, NULL);
|
|
pr_warn("%s: attempt to take down CPU %u failed\n",
|
|
__func__, cpu);
|
|
}
|
|
return err;
|
|
}
|
|
|
|
/* Take this CPU down. */
|
|
static int take_cpu_down(void *_param)
|
|
{
|
|
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
|
|
enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE);
|
|
int err, cpu = smp_processor_id();
|
|
|
|
/* Ensure this CPU doesn't handle any more interrupts. */
|
|
err = __cpu_disable();
|
|
if (err < 0)
|
|
return err;
|
|
|
|
/*
|
|
* We get here while we are in CPUHP_TEARDOWN_CPU state and we must not
|
|
* do this step again.
|
|
*/
|
|
WARN_ON(st->state != CPUHP_TEARDOWN_CPU);
|
|
st->state--;
|
|
/* Invoke the former CPU_DYING callbacks */
|
|
for (; st->state > target; st->state--)
|
|
cpuhp_invoke_callback(cpu, st->state, false, NULL);
|
|
|
|
/* Give up timekeeping duties */
|
|
tick_handover_do_timer();
|
|
/* Park the stopper thread */
|
|
stop_machine_park(cpu);
|
|
return 0;
|
|
}
|
|
|
|
static int takedown_cpu(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int err;
|
|
|
|
/* Park the smpboot threads */
|
|
kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);
|
|
|
|
/*
|
|
* Prevent irq alloc/free while the dying cpu reorganizes the
|
|
* interrupt affinities.
|
|
*/
|
|
irq_lock_sparse();
|
|
|
|
/*
|
|
* So now all preempt/rcu users must observe !cpu_active().
|
|
*/
|
|
err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu));
|
|
if (err) {
|
|
/* CPU refused to die */
|
|
irq_unlock_sparse();
|
|
/* Unpark the hotplug thread so we can rollback there */
|
|
kthread_unpark(per_cpu_ptr(&cpuhp_state, cpu)->thread);
|
|
return err;
|
|
}
|
|
BUG_ON(cpu_online(cpu));
|
|
|
|
/*
|
|
* The CPUHP_AP_SCHED_MIGRATE_DYING callback will have removed all
|
|
* runnable tasks from the cpu, there's only the idle task left now
|
|
* that the migration thread is done doing the stop_machine thing.
|
|
*
|
|
* Wait for the stop thread to go away.
|
|
*/
|
|
wait_for_completion(&st->done);
|
|
BUG_ON(st->state != CPUHP_AP_IDLE_DEAD);
|
|
|
|
/* Interrupts are moved away from the dying cpu, reenable alloc/free */
|
|
irq_unlock_sparse();
|
|
|
|
hotplug_cpu__broadcast_tick_pull(cpu);
|
|
/* This actually kills the CPU. */
|
|
__cpu_die(cpu);
|
|
|
|
tick_cleanup_dead_cpu(cpu);
|
|
return 0;
|
|
}
|
|
|
|
static int notify_dead(unsigned int cpu)
|
|
{
|
|
cpu_notify_nofail(CPU_DEAD, cpu);
|
|
check_for_tasks(cpu);
|
|
return 0;
|
|
}
|
|
|
|
static void cpuhp_complete_idle_dead(void *arg)
|
|
{
|
|
struct cpuhp_cpu_state *st = arg;
|
|
|
|
complete(&st->done);
|
|
}
|
|
|
|
void cpuhp_report_idle_dead(void)
|
|
{
|
|
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
|
|
|
|
BUG_ON(st->state != CPUHP_AP_OFFLINE);
|
|
rcu_report_dead(smp_processor_id());
|
|
st->state = CPUHP_AP_IDLE_DEAD;
|
|
/*
|
|
* We cannot call complete after rcu_report_dead() so we delegate it
|
|
* to an online cpu.
|
|
*/
|
|
smp_call_function_single(cpumask_first(cpu_online_mask),
|
|
cpuhp_complete_idle_dead, st, 0);
|
|
}
|
|
|
|
#else
|
|
#define notify_down_prepare NULL
|
|
#define takedown_cpu NULL
|
|
#define notify_dead NULL
|
|
#endif
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
|
|
/* Requires cpu_add_remove_lock to be held */
|
|
static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
|
|
enum cpuhp_state target)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int prev_state, ret = 0;
|
|
bool hasdied = false;
|
|
u64 start_time = 0;
|
|
|
|
if (num_online_cpus() == 1)
|
|
return -EBUSY;
|
|
|
|
if (!cpu_present(cpu))
|
|
return -EINVAL;
|
|
|
|
if (!tasks_frozen && !cpu_isolated(cpu) && num_online_uniso_cpus() == 1)
|
|
return -EBUSY;
|
|
|
|
cpu_hotplug_begin();
|
|
if (trace_cpuhp_latency_enabled())
|
|
start_time = sched_clock();
|
|
|
|
cpuhp_tasks_frozen = tasks_frozen;
|
|
|
|
prev_state = st->state;
|
|
st->target = target;
|
|
/*
|
|
* If the current CPU state is in the range of the AP hotplug thread,
|
|
* then we need to kick the thread.
|
|
*/
|
|
if (st->state > CPUHP_TEARDOWN_CPU) {
|
|
ret = cpuhp_kick_ap_work(cpu);
|
|
/*
|
|
* The AP side has done the error rollback already. Just
|
|
* return the error code..
|
|
*/
|
|
if (ret)
|
|
goto out;
|
|
|
|
/*
|
|
* We might have stopped still in the range of the AP hotplug
|
|
* thread. Nothing to do anymore.
|
|
*/
|
|
if (st->state > CPUHP_TEARDOWN_CPU)
|
|
goto out;
|
|
}
|
|
/*
|
|
* The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need
|
|
* to do the further cleanups.
|
|
*/
|
|
ret = cpuhp_down_callbacks(cpu, st, target);
|
|
if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) {
|
|
st->target = prev_state;
|
|
st->rollback = true;
|
|
cpuhp_kick_ap_work(cpu);
|
|
}
|
|
|
|
hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
|
|
out:
|
|
trace_cpuhp_latency(cpu, 0, start_time, ret);
|
|
cpu_hotplug_done();
|
|
/* This post dead nonsense must die */
|
|
if (!ret && hasdied)
|
|
cpu_notify_nofail(CPU_POST_DEAD, cpu);
|
|
arch_smt_update();
|
|
return ret;
|
|
}
|
|
|
|
static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
|
|
{
|
|
if (cpu_hotplug_disabled)
|
|
return -EBUSY;
|
|
return _cpu_down(cpu, 0, target);
|
|
}
|
|
|
|
static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
|
|
{
|
|
int err;
|
|
|
|
cpu_maps_update_begin();
|
|
err = cpu_down_maps_locked(cpu, target);
|
|
cpu_maps_update_done();
|
|
return err;
|
|
}
|
|
int cpu_down(unsigned int cpu)
|
|
{
|
|
return do_cpu_down(cpu, CPUHP_OFFLINE);
|
|
}
|
|
EXPORT_SYMBOL(cpu_down);
|
|
#endif /*CONFIG_HOTPLUG_CPU*/
|
|
|
|
/**
|
|
* notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU
|
|
* @cpu: cpu that just started
|
|
*
|
|
* It must be called by the arch code on the new cpu, before the new cpu
|
|
* enables interrupts and before the "boot" cpu returns from __cpu_up().
|
|
*/
|
|
void notify_cpu_starting(unsigned int cpu)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE);
|
|
|
|
rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
|
|
st->booted_once = true;
|
|
while (st->state < target) {
|
|
st->state++;
|
|
cpuhp_invoke_callback(cpu, st->state, true, NULL);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Called from the idle task. Wake up the controlling task which brings the
|
|
* hotplug thread of the upcoming CPU up and then delegates the rest of the
|
|
* online bringup to the hotplug thread.
|
|
*/
|
|
void cpuhp_online_idle(enum cpuhp_state state)
|
|
{
|
|
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
|
|
|
|
/* Happens for the boot cpu */
|
|
if (state != CPUHP_AP_ONLINE_IDLE)
|
|
return;
|
|
|
|
/*
|
|
* Unpart the stopper thread before we start the idle loop (and start
|
|
* scheduling); this ensures the stopper task is always available.
|
|
*/
|
|
stop_machine_unpark(smp_processor_id());
|
|
|
|
st->state = CPUHP_AP_ONLINE_IDLE;
|
|
complete(&st->done);
|
|
}
|
|
|
|
/* Requires cpu_add_remove_lock to be held */
|
|
static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
struct task_struct *idle;
|
|
int ret = 0;
|
|
u64 start_time = 0;
|
|
|
|
cpu_hotplug_begin();
|
|
if (trace_cpuhp_latency_enabled())
|
|
start_time = sched_clock();
|
|
|
|
if (!cpu_present(cpu)) {
|
|
ret = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* The caller of do_cpu_up might have raced with another
|
|
* caller. Ignore it for now.
|
|
*/
|
|
if (st->state >= target)
|
|
goto out;
|
|
|
|
if (st->state == CPUHP_OFFLINE) {
|
|
/* Let it fail before we try to bring the cpu up */
|
|
idle = idle_thread_get(cpu);
|
|
if (IS_ERR(idle)) {
|
|
ret = PTR_ERR(idle);
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
cpuhp_tasks_frozen = tasks_frozen;
|
|
|
|
st->target = target;
|
|
/*
|
|
* If the current CPU state is in the range of the AP hotplug thread,
|
|
* then we need to kick the thread once more.
|
|
*/
|
|
if (st->state > CPUHP_BRINGUP_CPU) {
|
|
ret = cpuhp_kick_ap_work(cpu);
|
|
/*
|
|
* The AP side has done the error rollback already. Just
|
|
* return the error code..
|
|
*/
|
|
if (ret)
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* Try to reach the target state. We max out on the BP at
|
|
* CPUHP_BRINGUP_CPU. After that the AP hotplug thread is
|
|
* responsible for bringing it up to the target state.
|
|
*/
|
|
target = min((int)target, CPUHP_BRINGUP_CPU);
|
|
ret = cpuhp_up_callbacks(cpu, st, target);
|
|
out:
|
|
trace_cpuhp_latency(cpu, 1, start_time, ret);
|
|
cpu_hotplug_done();
|
|
arch_smt_update();
|
|
return ret;
|
|
}
|
|
|
|
static int switch_to_rt_policy(void)
|
|
{
|
|
struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
|
|
unsigned int policy = current->policy;
|
|
int err;
|
|
|
|
/* Nobody should be attempting hotplug from these policy contexts. */
|
|
if (policy == SCHED_BATCH || policy == SCHED_IDLE ||
|
|
policy == SCHED_DEADLINE)
|
|
return -EPERM;
|
|
|
|
if (policy == SCHED_FIFO || policy == SCHED_RR)
|
|
return 1;
|
|
|
|
/* Only SCHED_NORMAL left. */
|
|
err = sched_setscheduler_nocheck(current, SCHED_FIFO, ¶m);
|
|
return err;
|
|
|
|
}
|
|
|
|
static int switch_to_fair_policy(void)
|
|
{
|
|
struct sched_param param = { .sched_priority = 0 };
|
|
|
|
return sched_setscheduler_nocheck(current, SCHED_NORMAL, ¶m);
|
|
}
|
|
|
|
static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
|
|
{
|
|
int err = 0;
|
|
int switch_err = 0;
|
|
|
|
if (!cpu_possible(cpu)) {
|
|
pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n",
|
|
cpu);
|
|
#if defined(CONFIG_IA64)
|
|
pr_err("please check additional_cpus= boot parameter\n");
|
|
#endif
|
|
return -EINVAL;
|
|
}
|
|
|
|
switch_err = switch_to_rt_policy();
|
|
if (switch_err < 0)
|
|
return switch_err;
|
|
|
|
err = try_online_node(cpu_to_node(cpu));
|
|
if (err)
|
|
return err;
|
|
|
|
cpu_maps_update_begin();
|
|
|
|
if (cpu_hotplug_disabled) {
|
|
err = -EBUSY;
|
|
goto out;
|
|
}
|
|
if (!cpu_smt_allowed(cpu)) {
|
|
err = -EPERM;
|
|
goto out;
|
|
}
|
|
|
|
err = _cpu_up(cpu, 0, target);
|
|
out:
|
|
cpu_maps_update_done();
|
|
|
|
if (!switch_err) {
|
|
switch_err = switch_to_fair_policy();
|
|
if (switch_err)
|
|
pr_err("Hotplug policy switch err=%d Task %s pid=%d\n",
|
|
switch_err, current->comm, current->pid);
|
|
}
|
|
|
|
return err;
|
|
}
|
|
|
|
int cpu_up(unsigned int cpu)
|
|
{
|
|
return do_cpu_up(cpu, CPUHP_ONLINE);
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_up);
|
|
|
|
#ifdef CONFIG_PM_SLEEP_SMP
|
|
static cpumask_var_t frozen_cpus;
|
|
|
|
int freeze_secondary_cpus(int primary)
|
|
{
|
|
int cpu, error = 0;
|
|
|
|
cpu_maps_update_begin();
|
|
if (!cpu_online(primary))
|
|
primary = cpumask_first(cpu_online_mask);
|
|
/*
|
|
* We take down all of the non-boot CPUs in one shot to avoid races
|
|
* with the userspace trying to use the CPU hotplug at the same time
|
|
*/
|
|
cpumask_clear(frozen_cpus);
|
|
|
|
pr_info("Disabling non-boot CPUs ...\n");
|
|
for_each_online_cpu(cpu) {
|
|
if (cpu == primary)
|
|
continue;
|
|
trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
|
|
error = _cpu_down(cpu, 1, CPUHP_OFFLINE);
|
|
trace_suspend_resume(TPS("CPU_OFF"), cpu, false);
|
|
if (!error)
|
|
cpumask_set_cpu(cpu, frozen_cpus);
|
|
else {
|
|
pr_err("Error taking CPU%d down: %d\n", cpu, error);
|
|
break;
|
|
}
|
|
}
|
|
|
|
if (!error)
|
|
BUG_ON(num_online_cpus() > 1);
|
|
else
|
|
pr_err("Non-boot CPUs are not disabled\n");
|
|
|
|
/*
|
|
* Make sure the CPUs won't be enabled by someone else. We need to do
|
|
* this even in case of failure as all disable_nonboot_cpus() users are
|
|
* supposed to do enable_nonboot_cpus() on the failure path.
|
|
*/
|
|
cpu_hotplug_disabled++;
|
|
|
|
cpu_maps_update_done();
|
|
return error;
|
|
}
|
|
|
|
void __weak arch_enable_nonboot_cpus_begin(void)
|
|
{
|
|
}
|
|
|
|
void __weak arch_enable_nonboot_cpus_end(void)
|
|
{
|
|
}
|
|
|
|
void enable_nonboot_cpus(void)
|
|
{
|
|
int cpu, error;
|
|
struct device *cpu_device;
|
|
|
|
/* Allow everyone to use the CPU hotplug again */
|
|
cpu_maps_update_begin();
|
|
__cpu_hotplug_enable();
|
|
if (cpumask_empty(frozen_cpus))
|
|
goto out;
|
|
|
|
pr_info("Enabling non-boot CPUs ...\n");
|
|
|
|
arch_enable_nonboot_cpus_begin();
|
|
|
|
for_each_cpu(cpu, frozen_cpus) {
|
|
trace_suspend_resume(TPS("CPU_ON"), cpu, true);
|
|
error = _cpu_up(cpu, 1, CPUHP_ONLINE);
|
|
trace_suspend_resume(TPS("CPU_ON"), cpu, false);
|
|
if (!error) {
|
|
pr_info("CPU%d is up\n", cpu);
|
|
cpu_device = get_cpu_device(cpu);
|
|
if (!cpu_device)
|
|
pr_err("%s: failed to get cpu%d device\n",
|
|
__func__, cpu);
|
|
else
|
|
kobject_uevent(&cpu_device->kobj, KOBJ_ONLINE);
|
|
continue;
|
|
}
|
|
pr_warn("Error taking CPU%d up: %d\n", cpu, error);
|
|
}
|
|
|
|
arch_enable_nonboot_cpus_end();
|
|
|
|
cpumask_clear(frozen_cpus);
|
|
out:
|
|
cpu_maps_update_done();
|
|
}
|
|
|
|
static int __init alloc_frozen_cpus(void)
|
|
{
|
|
if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO))
|
|
return -ENOMEM;
|
|
return 0;
|
|
}
|
|
core_initcall(alloc_frozen_cpus);
|
|
|
|
/*
|
|
* When callbacks for CPU hotplug notifications are being executed, we must
|
|
* ensure that the state of the system with respect to the tasks being frozen
|
|
* or not, as reported by the notification, remains unchanged *throughout the
|
|
* duration* of the execution of the callbacks.
|
|
* Hence we need to prevent the freezer from racing with regular CPU hotplug.
|
|
*
|
|
* This synchronization is implemented by mutually excluding regular CPU
|
|
* hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/
|
|
* Hibernate notifications.
|
|
*/
|
|
static int
|
|
cpu_hotplug_pm_callback(struct notifier_block *nb,
|
|
unsigned long action, void *ptr)
|
|
{
|
|
switch (action) {
|
|
|
|
case PM_SUSPEND_PREPARE:
|
|
case PM_HIBERNATION_PREPARE:
|
|
cpu_hotplug_disable();
|
|
break;
|
|
|
|
case PM_POST_SUSPEND:
|
|
case PM_POST_HIBERNATION:
|
|
cpu_hotplug_enable();
|
|
break;
|
|
|
|
default:
|
|
return NOTIFY_DONE;
|
|
}
|
|
|
|
return NOTIFY_OK;
|
|
}
|
|
|
|
|
|
static int __init cpu_hotplug_pm_sync_init(void)
|
|
{
|
|
/*
|
|
* cpu_hotplug_pm_callback has higher priority than x86
|
|
* bsp_pm_callback which depends on cpu_hotplug_pm_callback
|
|
* to disable cpu hotplug to avoid cpu hotplug race.
|
|
*/
|
|
pm_notifier(cpu_hotplug_pm_callback, 0);
|
|
return 0;
|
|
}
|
|
core_initcall(cpu_hotplug_pm_sync_init);
|
|
|
|
#endif /* CONFIG_PM_SLEEP_SMP */
|
|
|
|
#endif /* CONFIG_SMP */
|
|
|
|
/* Boot processor state steps */
|
|
static struct cpuhp_step cpuhp_bp_states[] = {
|
|
[CPUHP_OFFLINE] = {
|
|
.name = "offline",
|
|
.startup.single = NULL,
|
|
.teardown.single = NULL,
|
|
},
|
|
#ifdef CONFIG_SMP
|
|
[CPUHP_CREATE_THREADS]= {
|
|
.name = "threads:prepare",
|
|
.startup.single = smpboot_create_threads,
|
|
.teardown.single = NULL,
|
|
.cant_stop = true,
|
|
},
|
|
[CPUHP_PERF_PREPARE] = {
|
|
.name = "perf:prepare",
|
|
.startup.single = perf_event_init_cpu,
|
|
.teardown.single = perf_event_exit_cpu,
|
|
},
|
|
[CPUHP_RANDOM_PREPARE] = {
|
|
.name = "random:prepare",
|
|
.startup.single = random_prepare_cpu,
|
|
.teardown.single = NULL,
|
|
},
|
|
[CPUHP_WORKQUEUE_PREP] = {
|
|
.name = "workqueue:prepare",
|
|
.startup.single = workqueue_prepare_cpu,
|
|
.teardown.single = NULL,
|
|
},
|
|
[CPUHP_HRTIMERS_PREPARE] = {
|
|
.name = "hrtimers:prepare",
|
|
.startup.single = hrtimers_prepare_cpu,
|
|
.teardown.single = hrtimers_dead_cpu,
|
|
},
|
|
[CPUHP_SMPCFD_PREPARE] = {
|
|
.name = "smpcfd:prepare",
|
|
.startup.single = smpcfd_prepare_cpu,
|
|
.teardown.single = smpcfd_dead_cpu,
|
|
},
|
|
[CPUHP_RELAY_PREPARE] = {
|
|
.name = "relay:prepare",
|
|
.startup.single = relay_prepare_cpu,
|
|
.teardown.single = NULL,
|
|
},
|
|
[CPUHP_SLAB_PREPARE] = {
|
|
.name = "slab:prepare",
|
|
.startup.single = slab_prepare_cpu,
|
|
.teardown.single = slab_dead_cpu,
|
|
},
|
|
[CPUHP_RCUTREE_PREP] = {
|
|
.name = "RCU/tree:prepare",
|
|
.startup.single = rcutree_prepare_cpu,
|
|
.teardown.single = rcutree_dead_cpu,
|
|
},
|
|
/*
|
|
* Preparatory and dead notifiers. Will be replaced once the notifiers
|
|
* are converted to states.
|
|
*/
|
|
[CPUHP_NOTIFY_PREPARE] = {
|
|
.name = "notify:prepare",
|
|
.startup.single = notify_prepare,
|
|
.teardown.single = notify_dead,
|
|
.cant_stop = true,
|
|
},
|
|
/*
|
|
* On the tear-down path, timers_dead_cpu() must be invoked
|
|
* before blk_mq_queue_reinit_notify() from notify_dead(),
|
|
* otherwise a RCU stall occurs.
|
|
*/
|
|
[CPUHP_TIMERS_PREPARE] = {
|
|
.name = "timers:dead",
|
|
.startup.single = timers_prepare_cpu,
|
|
.teardown.single = timers_dead_cpu,
|
|
},
|
|
/* Kicks the plugged cpu into life */
|
|
[CPUHP_BRINGUP_CPU] = {
|
|
.name = "cpu:bringup",
|
|
.startup.single = bringup_cpu,
|
|
.teardown.single = NULL,
|
|
.cant_stop = true,
|
|
},
|
|
/*
|
|
* Handled on controll processor until the plugged processor manages
|
|
* this itself.
|
|
*/
|
|
[CPUHP_TEARDOWN_CPU] = {
|
|
.name = "cpu:teardown",
|
|
.startup.single = NULL,
|
|
.teardown.single = takedown_cpu,
|
|
.cant_stop = true,
|
|
},
|
|
#else
|
|
[CPUHP_BRINGUP_CPU] = { },
|
|
#endif
|
|
};
|
|
|
|
/* Application processor state steps */
|
|
static struct cpuhp_step cpuhp_ap_states[] = {
|
|
#ifdef CONFIG_SMP
|
|
/* Final state before CPU kills itself */
|
|
[CPUHP_AP_IDLE_DEAD] = {
|
|
.name = "idle:dead",
|
|
},
|
|
/*
|
|
* Last state before CPU enters the idle loop to die. Transient state
|
|
* for synchronization.
|
|
*/
|
|
[CPUHP_AP_OFFLINE] = {
|
|
.name = "ap:offline",
|
|
.cant_stop = true,
|
|
},
|
|
/* First state is scheduler control. Interrupts are disabled */
|
|
[CPUHP_AP_SCHED_STARTING] = {
|
|
.name = "sched:starting",
|
|
.startup.single = sched_cpu_starting,
|
|
.teardown.single = sched_cpu_dying,
|
|
},
|
|
[CPUHP_AP_RCUTREE_DYING] = {
|
|
.name = "RCU/tree:dying",
|
|
.startup.single = NULL,
|
|
.teardown.single = rcutree_dying_cpu,
|
|
},
|
|
[CPUHP_AP_KMAP_DYING] = {
|
|
.name = "KMAP:dying",
|
|
.startup.single = NULL,
|
|
.teardown.single = kmap_remove_unused_cpu,
|
|
},
|
|
[CPUHP_AP_SMPCFD_DYING] = {
|
|
.name = "smpcfd:dying",
|
|
.startup.single = NULL,
|
|
.teardown.single = smpcfd_dying_cpu,
|
|
},
|
|
/* Entry state on starting. Interrupts enabled from here on. Transient
|
|
* state for synchronsization */
|
|
[CPUHP_AP_ONLINE] = {
|
|
.name = "ap:online",
|
|
},
|
|
/* Handle smpboot threads park/unpark */
|
|
[CPUHP_AP_SMPBOOT_THREADS] = {
|
|
.name = "smpboot/threads:online",
|
|
.startup.single = smpboot_unpark_threads,
|
|
.teardown.single = smpboot_park_threads,
|
|
},
|
|
[CPUHP_AP_PERF_ONLINE] = {
|
|
.name = "perf:online",
|
|
.startup.single = perf_event_restart_events,
|
|
.teardown.single = perf_event_exit_cpu,
|
|
},
|
|
[CPUHP_AP_WORKQUEUE_ONLINE] = {
|
|
.name = "workqueue:online",
|
|
.startup.single = workqueue_online_cpu,
|
|
.teardown.single = workqueue_offline_cpu,
|
|
},
|
|
[CPUHP_AP_RANDOM_ONLINE] = {
|
|
.name = "random:online",
|
|
.startup.single = random_online_cpu,
|
|
.teardown.single = NULL,
|
|
},
|
|
[CPUHP_AP_RCUTREE_ONLINE] = {
|
|
.name = "RCU/tree:online",
|
|
.startup.single = rcutree_online_cpu,
|
|
.teardown.single = rcutree_offline_cpu,
|
|
},
|
|
|
|
/*
|
|
* Online/down_prepare notifiers. Will be removed once the notifiers
|
|
* are converted to states.
|
|
*/
|
|
[CPUHP_AP_NOTIFY_ONLINE] = {
|
|
.name = "notify:online",
|
|
.startup.single = notify_online,
|
|
.teardown.single = notify_down_prepare,
|
|
},
|
|
#endif
|
|
/*
|
|
* The dynamically registered state space is here
|
|
*/
|
|
|
|
#ifdef CONFIG_SMP
|
|
/* Last state is scheduler control setting the cpu active */
|
|
[CPUHP_AP_ACTIVE] = {
|
|
.name = "sched:active",
|
|
.startup.single = sched_cpu_activate,
|
|
.teardown.single = sched_cpu_deactivate,
|
|
},
|
|
#endif
|
|
|
|
/* CPU is fully up and running. */
|
|
[CPUHP_ONLINE] = {
|
|
.name = "online",
|
|
.startup.single = NULL,
|
|
.teardown.single = NULL,
|
|
},
|
|
};
|
|
|
|
/* Sanity check for callbacks */
|
|
static int cpuhp_cb_check(enum cpuhp_state state)
|
|
{
|
|
if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE)
|
|
return -EINVAL;
|
|
return 0;
|
|
}
|
|
|
|
static void cpuhp_store_callbacks(enum cpuhp_state state,
|
|
const char *name,
|
|
int (*startup)(unsigned int cpu),
|
|
int (*teardown)(unsigned int cpu),
|
|
bool multi_instance)
|
|
{
|
|
/* (Un)Install the callbacks for further cpu hotplug operations */
|
|
struct cpuhp_step *sp;
|
|
|
|
sp = cpuhp_get_step(state);
|
|
sp->startup.single = startup;
|
|
sp->teardown.single = teardown;
|
|
sp->name = name;
|
|
sp->multi_instance = multi_instance;
|
|
INIT_HLIST_HEAD(&sp->list);
|
|
}
|
|
|
|
static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
|
|
{
|
|
return cpuhp_get_step(state)->teardown.single;
|
|
}
|
|
|
|
/*
|
|
* Call the startup/teardown function for a step either on the AP or
|
|
* on the current CPU.
|
|
*/
|
|
static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup,
|
|
struct hlist_node *node)
|
|
{
|
|
struct cpuhp_step *sp = cpuhp_get_step(state);
|
|
int ret;
|
|
|
|
if ((bringup && !sp->startup.single) ||
|
|
(!bringup && !sp->teardown.single))
|
|
return 0;
|
|
/*
|
|
* The non AP bound callbacks can fail on bringup. On teardown
|
|
* e.g. module removal we crash for now.
|
|
*/
|
|
#ifdef CONFIG_SMP
|
|
if (cpuhp_is_ap_state(state))
|
|
ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node);
|
|
else
|
|
ret = cpuhp_invoke_callback(cpu, state, bringup, node);
|
|
#else
|
|
ret = cpuhp_invoke_callback(cpu, state, bringup, node);
|
|
#endif
|
|
BUG_ON(ret && !bringup);
|
|
return ret;
|
|
}
|
|
|
|
/*
|
|
* Called from __cpuhp_setup_state on a recoverable failure.
|
|
*
|
|
* Note: The teardown callbacks for rollback are not allowed to fail!
|
|
*/
|
|
static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
|
|
struct hlist_node *node)
|
|
{
|
|
int cpu;
|
|
|
|
/* Roll back the already executed steps on the other cpus */
|
|
for_each_present_cpu(cpu) {
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int cpustate = st->state;
|
|
|
|
if (cpu >= failedcpu)
|
|
break;
|
|
|
|
/* Did we invoke the startup call on that cpu ? */
|
|
if (cpustate >= state)
|
|
cpuhp_issue_call(cpu, state, false, node);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Returns a free for dynamic slot assignment of the Online state. The states
|
|
* are protected by the cpuhp_slot_states mutex and an empty slot is identified
|
|
* by having no name assigned.
|
|
*/
|
|
static int cpuhp_reserve_state(enum cpuhp_state state)
|
|
{
|
|
enum cpuhp_state i;
|
|
|
|
for (i = CPUHP_AP_ONLINE_DYN; i <= CPUHP_AP_ONLINE_DYN_END; i++) {
|
|
if (cpuhp_ap_states[i].name)
|
|
continue;
|
|
|
|
cpuhp_ap_states[i].name = "Reserved";
|
|
return i;
|
|
}
|
|
WARN(1, "No more dynamic states available for CPU hotplug\n");
|
|
return -ENOSPC;
|
|
}
|
|
|
|
int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
|
|
bool invoke)
|
|
{
|
|
struct cpuhp_step *sp;
|
|
int cpu;
|
|
int ret;
|
|
|
|
sp = cpuhp_get_step(state);
|
|
if (sp->multi_instance == false)
|
|
return -EINVAL;
|
|
|
|
get_online_cpus();
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
|
|
if (!invoke || !sp->startup.multi)
|
|
goto add_node;
|
|
|
|
/*
|
|
* Try to call the startup callback for each present cpu
|
|
* depending on the hotplug state of the cpu.
|
|
*/
|
|
for_each_present_cpu(cpu) {
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int cpustate = st->state;
|
|
|
|
if (cpustate < state)
|
|
continue;
|
|
|
|
ret = cpuhp_issue_call(cpu, state, true, node);
|
|
if (ret) {
|
|
if (sp->teardown.multi)
|
|
cpuhp_rollback_install(cpu, state, node);
|
|
goto err;
|
|
}
|
|
}
|
|
add_node:
|
|
ret = 0;
|
|
hlist_add_head(node, &sp->list);
|
|
|
|
err:
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
put_online_cpus();
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
|
|
|
|
/**
|
|
* __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
|
|
* @state: The state to setup
|
|
* @invoke: If true, the startup function is invoked for cpus where
|
|
* cpu state >= @state
|
|
* @startup: startup callback function
|
|
* @teardown: teardown callback function
|
|
*
|
|
* Returns 0 if successful, otherwise a proper error code
|
|
*/
|
|
int __cpuhp_setup_state(enum cpuhp_state state,
|
|
const char *name, bool invoke,
|
|
int (*startup)(unsigned int cpu),
|
|
int (*teardown)(unsigned int cpu),
|
|
bool multi_instance)
|
|
{
|
|
int cpu, ret = 0;
|
|
int dyn_state = 0;
|
|
|
|
if (cpuhp_cb_check(state) || !name)
|
|
return -EINVAL;
|
|
|
|
get_online_cpus();
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
|
|
/* currently assignments for the ONLINE state are possible */
|
|
if (state == CPUHP_AP_ONLINE_DYN) {
|
|
dyn_state = 1;
|
|
ret = cpuhp_reserve_state(state);
|
|
if (ret < 0)
|
|
goto out;
|
|
state = ret;
|
|
}
|
|
|
|
cpuhp_store_callbacks(state, name, startup, teardown, multi_instance);
|
|
|
|
if (!invoke || !startup)
|
|
goto out;
|
|
|
|
/*
|
|
* Try to call the startup callback for each present cpu
|
|
* depending on the hotplug state of the cpu.
|
|
*/
|
|
for_each_present_cpu(cpu) {
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int cpustate = st->state;
|
|
|
|
if (cpustate < state)
|
|
continue;
|
|
|
|
ret = cpuhp_issue_call(cpu, state, true, NULL);
|
|
if (ret) {
|
|
if (teardown)
|
|
cpuhp_rollback_install(cpu, state, NULL);
|
|
cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
|
|
goto out;
|
|
}
|
|
}
|
|
out:
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
|
|
put_online_cpus();
|
|
if (!ret && dyn_state)
|
|
return state;
|
|
return ret;
|
|
}
|
|
EXPORT_SYMBOL(__cpuhp_setup_state);
|
|
|
|
int __cpuhp_state_remove_instance(enum cpuhp_state state,
|
|
struct hlist_node *node, bool invoke)
|
|
{
|
|
struct cpuhp_step *sp = cpuhp_get_step(state);
|
|
int cpu;
|
|
|
|
BUG_ON(cpuhp_cb_check(state));
|
|
|
|
if (!sp->multi_instance)
|
|
return -EINVAL;
|
|
|
|
get_online_cpus();
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
|
|
if (!invoke || !cpuhp_get_teardown_cb(state))
|
|
goto remove;
|
|
/*
|
|
* Call the teardown callback for each present cpu depending
|
|
* on the hotplug state of the cpu. This function is not
|
|
* allowed to fail currently!
|
|
*/
|
|
for_each_present_cpu(cpu) {
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int cpustate = st->state;
|
|
|
|
if (cpustate >= state)
|
|
cpuhp_issue_call(cpu, state, false, node);
|
|
}
|
|
|
|
remove:
|
|
hlist_del(node);
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
put_online_cpus();
|
|
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance);
|
|
/**
|
|
* __cpuhp_remove_state - Remove the callbacks for an hotplug machine state
|
|
* @state: The state to remove
|
|
* @invoke: If true, the teardown function is invoked for cpus where
|
|
* cpu state >= @state
|
|
*
|
|
* The teardown callback is currently not allowed to fail. Think
|
|
* about module removal!
|
|
*/
|
|
void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
|
|
{
|
|
struct cpuhp_step *sp = cpuhp_get_step(state);
|
|
int cpu;
|
|
|
|
BUG_ON(cpuhp_cb_check(state));
|
|
|
|
get_online_cpus();
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
|
|
if (sp->multi_instance) {
|
|
WARN(!hlist_empty(&sp->list),
|
|
"Error: Removing state %d which has instances left.\n",
|
|
state);
|
|
goto remove;
|
|
}
|
|
|
|
if (!invoke || !cpuhp_get_teardown_cb(state))
|
|
goto remove;
|
|
|
|
/*
|
|
* Call the teardown callback for each present cpu depending
|
|
* on the hotplug state of the cpu. This function is not
|
|
* allowed to fail currently!
|
|
*/
|
|
for_each_present_cpu(cpu) {
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
|
|
int cpustate = st->state;
|
|
|
|
if (cpustate >= state)
|
|
cpuhp_issue_call(cpu, state, false, NULL);
|
|
}
|
|
remove:
|
|
cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
put_online_cpus();
|
|
}
|
|
EXPORT_SYMBOL(__cpuhp_remove_state);
|
|
|
|
#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
|
|
static ssize_t show_cpuhp_state(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
|
|
|
|
return sprintf(buf, "%d\n", st->state);
|
|
}
|
|
static DEVICE_ATTR(state, 0444, show_cpuhp_state, NULL);
|
|
|
|
static ssize_t write_cpuhp_target(struct device *dev,
|
|
struct device_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
|
|
struct cpuhp_step *sp;
|
|
int target, ret;
|
|
|
|
ret = kstrtoint(buf, 10, &target);
|
|
if (ret)
|
|
return ret;
|
|
|
|
#ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL
|
|
if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE)
|
|
return -EINVAL;
|
|
#else
|
|
if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE)
|
|
return -EINVAL;
|
|
#endif
|
|
|
|
ret = lock_device_hotplug_sysfs();
|
|
if (ret)
|
|
return ret;
|
|
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
sp = cpuhp_get_step(target);
|
|
ret = !sp->name || sp->cant_stop ? -EINVAL : 0;
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
if (ret)
|
|
goto out;
|
|
|
|
if (st->state < target)
|
|
ret = do_cpu_up(dev->id, target);
|
|
else
|
|
ret = do_cpu_down(dev->id, target);
|
|
out:
|
|
unlock_device_hotplug();
|
|
return ret ? ret : count;
|
|
}
|
|
|
|
static ssize_t show_cpuhp_target(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id);
|
|
|
|
return sprintf(buf, "%d\n", st->target);
|
|
}
|
|
static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target);
|
|
|
|
static struct attribute *cpuhp_cpu_attrs[] = {
|
|
&dev_attr_state.attr,
|
|
&dev_attr_target.attr,
|
|
NULL
|
|
};
|
|
|
|
static struct attribute_group cpuhp_cpu_attr_group = {
|
|
.attrs = cpuhp_cpu_attrs,
|
|
.name = "hotplug",
|
|
NULL
|
|
};
|
|
|
|
static ssize_t show_cpuhp_states(struct device *dev,
|
|
struct device_attribute *attr, char *buf)
|
|
{
|
|
ssize_t cur, res = 0;
|
|
int i;
|
|
|
|
mutex_lock(&cpuhp_state_mutex);
|
|
for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) {
|
|
struct cpuhp_step *sp = cpuhp_get_step(i);
|
|
|
|
if (sp->name) {
|
|
cur = sprintf(buf, "%3d: %s\n", i, sp->name);
|
|
buf += cur;
|
|
res += cur;
|
|
}
|
|
}
|
|
mutex_unlock(&cpuhp_state_mutex);
|
|
return res;
|
|
}
|
|
static DEVICE_ATTR(states, 0444, show_cpuhp_states, NULL);
|
|
|
|
static struct attribute *cpuhp_cpu_root_attrs[] = {
|
|
&dev_attr_states.attr,
|
|
NULL
|
|
};
|
|
|
|
static struct attribute_group cpuhp_cpu_root_attr_group = {
|
|
.attrs = cpuhp_cpu_root_attrs,
|
|
.name = "hotplug",
|
|
NULL
|
|
};
|
|
|
|
#ifdef CONFIG_HOTPLUG_SMT
|
|
|
|
static const char *smt_states[] = {
|
|
[CPU_SMT_ENABLED] = "on",
|
|
[CPU_SMT_DISABLED] = "off",
|
|
[CPU_SMT_FORCE_DISABLED] = "forceoff",
|
|
[CPU_SMT_NOT_SUPPORTED] = "notsupported",
|
|
};
|
|
|
|
static ssize_t
|
|
show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
|
|
{
|
|
return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]);
|
|
}
|
|
|
|
static void cpuhp_offline_cpu_device(unsigned int cpu)
|
|
{
|
|
struct device *dev = get_cpu_device(cpu);
|
|
|
|
dev->offline = true;
|
|
/* Tell user space about the state change */
|
|
kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
|
|
}
|
|
|
|
static void cpuhp_online_cpu_device(unsigned int cpu)
|
|
{
|
|
struct device *dev = get_cpu_device(cpu);
|
|
|
|
dev->offline = false;
|
|
/* Tell user space about the state change */
|
|
kobject_uevent(&dev->kobj, KOBJ_ONLINE);
|
|
}
|
|
|
|
int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
|
|
{
|
|
int cpu, ret = 0;
|
|
|
|
cpu_maps_update_begin();
|
|
for_each_online_cpu(cpu) {
|
|
if (topology_is_primary_thread(cpu))
|
|
continue;
|
|
ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
|
|
if (ret)
|
|
break;
|
|
/*
|
|
* As this needs to hold the cpu maps lock it's impossible
|
|
* to call device_offline() because that ends up calling
|
|
* cpu_down() which takes cpu maps lock. cpu maps lock
|
|
* needs to be held as this might race against in kernel
|
|
* abusers of the hotplug machinery (thermal management).
|
|
*
|
|
* So nothing would update device:offline state. That would
|
|
* leave the sysfs entry stale and prevent onlining after
|
|
* smt control has been changed to 'off' again. This is
|
|
* called under the sysfs hotplug lock, so it is properly
|
|
* serialized against the regular offline usage.
|
|
*/
|
|
cpuhp_offline_cpu_device(cpu);
|
|
}
|
|
if (!ret)
|
|
cpu_smt_control = ctrlval;
|
|
cpu_maps_update_done();
|
|
return ret;
|
|
}
|
|
|
|
int cpuhp_smt_enable(void)
|
|
{
|
|
int cpu, ret = 0;
|
|
|
|
cpu_maps_update_begin();
|
|
cpu_smt_control = CPU_SMT_ENABLED;
|
|
for_each_present_cpu(cpu) {
|
|
/* Skip online CPUs and CPUs on offline nodes */
|
|
if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
|
|
continue;
|
|
ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
|
|
if (ret)
|
|
break;
|
|
/* See comment in cpuhp_smt_disable() */
|
|
cpuhp_online_cpu_device(cpu);
|
|
}
|
|
cpu_maps_update_done();
|
|
return ret;
|
|
}
|
|
|
|
static ssize_t
|
|
store_smt_control(struct device *dev, struct device_attribute *attr,
|
|
const char *buf, size_t count)
|
|
{
|
|
int ctrlval, ret;
|
|
|
|
if (sysfs_streq(buf, "on"))
|
|
ctrlval = CPU_SMT_ENABLED;
|
|
else if (sysfs_streq(buf, "off"))
|
|
ctrlval = CPU_SMT_DISABLED;
|
|
else if (sysfs_streq(buf, "forceoff"))
|
|
ctrlval = CPU_SMT_FORCE_DISABLED;
|
|
else
|
|
return -EINVAL;
|
|
|
|
if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
|
|
return -EPERM;
|
|
|
|
if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
|
|
return -ENODEV;
|
|
|
|
ret = lock_device_hotplug_sysfs();
|
|
if (ret)
|
|
return ret;
|
|
|
|
if (ctrlval != cpu_smt_control) {
|
|
switch (ctrlval) {
|
|
case CPU_SMT_ENABLED:
|
|
ret = cpuhp_smt_enable();
|
|
break;
|
|
case CPU_SMT_DISABLED:
|
|
case CPU_SMT_FORCE_DISABLED:
|
|
ret = cpuhp_smt_disable(ctrlval);
|
|
break;
|
|
}
|
|
}
|
|
|
|
unlock_device_hotplug();
|
|
return ret ? ret : count;
|
|
}
|
|
static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control);
|
|
|
|
static ssize_t
|
|
show_smt_active(struct device *dev, struct device_attribute *attr, char *buf)
|
|
{
|
|
bool active = topology_max_smt_threads() > 1;
|
|
|
|
return snprintf(buf, PAGE_SIZE - 2, "%d\n", active);
|
|
}
|
|
static DEVICE_ATTR(active, 0444, show_smt_active, NULL);
|
|
|
|
static struct attribute *cpuhp_smt_attrs[] = {
|
|
&dev_attr_control.attr,
|
|
&dev_attr_active.attr,
|
|
NULL
|
|
};
|
|
|
|
static const struct attribute_group cpuhp_smt_attr_group = {
|
|
.attrs = cpuhp_smt_attrs,
|
|
.name = "smt",
|
|
NULL
|
|
};
|
|
|
|
static int __init cpu_smt_state_init(void)
|
|
{
|
|
return sysfs_create_group(&cpu_subsys.dev_root->kobj,
|
|
&cpuhp_smt_attr_group);
|
|
}
|
|
|
|
#else
|
|
static inline int cpu_smt_state_init(void) { return 0; }
|
|
#endif
|
|
|
|
static int __init cpuhp_sysfs_init(void)
|
|
{
|
|
int cpu, ret;
|
|
|
|
ret = cpu_smt_state_init();
|
|
if (ret)
|
|
return ret;
|
|
|
|
ret = sysfs_create_group(&cpu_subsys.dev_root->kobj,
|
|
&cpuhp_cpu_root_attr_group);
|
|
if (ret)
|
|
return ret;
|
|
|
|
for_each_possible_cpu(cpu) {
|
|
struct device *dev = get_cpu_device(cpu);
|
|
|
|
if (!dev)
|
|
continue;
|
|
ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group);
|
|
if (ret)
|
|
return ret;
|
|
}
|
|
return 0;
|
|
}
|
|
device_initcall(cpuhp_sysfs_init);
|
|
#endif
|
|
|
|
/*
|
|
* cpu_bit_bitmap[] is a special, "compressed" data structure that
|
|
* represents all NR_CPUS bits binary values of 1<<nr.
|
|
*
|
|
* It is used by cpumask_of() to get a constant address to a CPU
|
|
* mask value that has a single bit set only.
|
|
*/
|
|
|
|
/* cpu_bit_bitmap[0] is empty - so we can back into it */
|
|
#define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x))
|
|
#define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)
|
|
#define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)
|
|
#define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)
|
|
|
|
const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
|
|
|
|
MASK_DECLARE_8(0), MASK_DECLARE_8(8),
|
|
MASK_DECLARE_8(16), MASK_DECLARE_8(24),
|
|
#if BITS_PER_LONG > 32
|
|
MASK_DECLARE_8(32), MASK_DECLARE_8(40),
|
|
MASK_DECLARE_8(48), MASK_DECLARE_8(56),
|
|
#endif
|
|
};
|
|
EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
|
|
|
|
const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
|
|
EXPORT_SYMBOL(cpu_all_bits);
|
|
|
|
#ifdef CONFIG_INIT_ALL_POSSIBLE
|
|
struct cpumask __cpu_possible_mask __read_mostly
|
|
= {CPU_BITS_ALL};
|
|
#else
|
|
struct cpumask __cpu_possible_mask __read_mostly;
|
|
#endif
|
|
EXPORT_SYMBOL(__cpu_possible_mask);
|
|
|
|
struct cpumask __cpu_online_mask __read_mostly;
|
|
EXPORT_SYMBOL(__cpu_online_mask);
|
|
|
|
struct cpumask __cpu_present_mask __read_mostly;
|
|
EXPORT_SYMBOL(__cpu_present_mask);
|
|
|
|
struct cpumask __cpu_active_mask __read_mostly;
|
|
EXPORT_SYMBOL(__cpu_active_mask);
|
|
|
|
struct cpumask __cpu_isolated_mask __read_mostly;
|
|
EXPORT_SYMBOL(__cpu_isolated_mask);
|
|
|
|
void init_cpu_present(const struct cpumask *src)
|
|
{
|
|
cpumask_copy(&__cpu_present_mask, src);
|
|
}
|
|
|
|
void init_cpu_possible(const struct cpumask *src)
|
|
{
|
|
cpumask_copy(&__cpu_possible_mask, src);
|
|
}
|
|
|
|
void init_cpu_online(const struct cpumask *src)
|
|
{
|
|
cpumask_copy(&__cpu_online_mask, src);
|
|
}
|
|
|
|
void init_cpu_isolated(const struct cpumask *src)
|
|
{
|
|
cpumask_copy(&__cpu_isolated_mask, src);
|
|
}
|
|
|
|
/*
|
|
* Activate the first processor.
|
|
*/
|
|
void __init boot_cpu_init(void)
|
|
{
|
|
int cpu = smp_processor_id();
|
|
|
|
/* Mark the boot cpu "present", "online" etc for SMP and UP case */
|
|
set_cpu_online(cpu, true);
|
|
set_cpu_active(cpu, true);
|
|
set_cpu_present(cpu, true);
|
|
set_cpu_possible(cpu, true);
|
|
}
|
|
|
|
/*
|
|
* Must be called _AFTER_ setting up the per_cpu areas
|
|
*/
|
|
void __init boot_cpu_hotplug_init(void)
|
|
{
|
|
#ifdef CONFIG_SMP
|
|
this_cpu_write(cpuhp_state.booted_once, true);
|
|
#endif
|
|
this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
|
|
}
|
|
|
|
/*
|
|
* These are used for a global "mitigations=" cmdline option for toggling
|
|
* optional CPU mitigations.
|
|
*/
|
|
enum cpu_mitigations {
|
|
CPU_MITIGATIONS_OFF,
|
|
CPU_MITIGATIONS_AUTO,
|
|
CPU_MITIGATIONS_AUTO_NOSMT,
|
|
};
|
|
|
|
static enum cpu_mitigations cpu_mitigations __ro_after_init =
|
|
CPU_MITIGATIONS_AUTO;
|
|
|
|
static int __init mitigations_parse_cmdline(char *arg)
|
|
{
|
|
if (!strcmp(arg, "off"))
|
|
cpu_mitigations = CPU_MITIGATIONS_OFF;
|
|
else if (!strcmp(arg, "auto"))
|
|
cpu_mitigations = CPU_MITIGATIONS_AUTO;
|
|
else if (!strcmp(arg, "auto,nosmt"))
|
|
cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT;
|
|
else
|
|
pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n",
|
|
arg);
|
|
|
|
return 0;
|
|
}
|
|
early_param("mitigations", mitigations_parse_cmdline);
|
|
|
|
/* mitigations=off */
|
|
bool cpu_mitigations_off(void)
|
|
{
|
|
return cpu_mitigations == CPU_MITIGATIONS_OFF;
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_mitigations_off);
|
|
|
|
/* mitigations=auto,nosmt */
|
|
bool cpu_mitigations_auto_nosmt(void)
|
|
{
|
|
return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT;
|
|
}
|
|
EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt);
|
|
|
|
static ATOMIC_NOTIFIER_HEAD(idle_notifier);
|
|
|
|
void idle_notifier_register(struct notifier_block *n)
|
|
{
|
|
atomic_notifier_chain_register(&idle_notifier, n);
|
|
}
|
|
EXPORT_SYMBOL_GPL(idle_notifier_register);
|
|
|
|
void idle_notifier_unregister(struct notifier_block *n)
|
|
{
|
|
atomic_notifier_chain_unregister(&idle_notifier, n);
|
|
}
|
|
EXPORT_SYMBOL_GPL(idle_notifier_unregister);
|
|
|
|
void idle_notifier_call_chain(unsigned long val)
|
|
{
|
|
atomic_notifier_call_chain(&idle_notifier, val, NULL);
|
|
}
|
|
EXPORT_SYMBOL_GPL(idle_notifier_call_chain);
|