Evolution-X-Devices/kernel_google_msm-4.14
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
udc
kernel_google_msm-4.14/kernel/cpu.c
Lucas Wei fa61e2931e Merge android-4.14-stable (4.14.285) into android-msm-pixel-4.14-tm-lts 
Merge 4.14.285 into android-4.14-stable
  * UPSTREAM: lib/vsprintf: Hash printed address for netdev bits fallback
      lib/vsprintf.c
  * UPSTREAM: lib/vsprintf: Prepare for more general use of ptr_to_id()
      lib/vsprintf.c
  * UPSTREAM: lib/vsprintf: Make ptr argument conts in ptr_to_id()
      lib/vsprintf.c
  * UPSTREAM: vsprintf: Replace memory barrier with static_key for random_ptr_key update
      lib/vsprintf.c
    UPSTREAM: lib/test_printf.c: accept "ptrval" as valid result for plain 'p' tests
  * UPSTREAM: lib/vsprintf: Do not handle %pO[^F] as %px
      lib/vsprintf.c
  * BACKPORT: l2tp: fix race in pppol2tp_release with session object destroy
      net/l2tp/l2tp_ppp.c
  * BACKPORT: l2tp: don't use inet_shutdown on ppp session destroy
      net/l2tp/l2tp_ppp.c
Linux 4.14.285
  * tcp: drop the hash_32() part from the index calculation
      net/ipv4/inet_hashtables.c
  * tcp: increase source port perturb table to 2^16
      net/ipv4/inet_hashtables.c
  * tcp: dynamically allocate the perturb table used by source ports
      net/ipv4/inet_hashtables.c
  * tcp: add small random increments to the source port
      net/ipv4/inet_hashtables.c
  * tcp: use different parts of the port_offset for index and offset
      net/ipv4/inet_hashtables.c
  * tcp: add some entropy in __inet_hash_connect()
      net/ipv4/inet_hashtables.c
    xprtrdma: fix incorrect header size calculations
  * usb: gadget: u_ether: fix regression in setting fixed MAC address
      drivers/usb/gadget/function/u_ether.c
    s390/mm: use non-quiescing sske for KVM switch to keyed guest
  * l2tp: fix race in pppol2tp_release with session object destroy
      net/l2tp/l2tp_ppp.c
  * l2tp: don't use inet_shutdown on ppp session destroy
      net/l2tp/l2tp_ppp.c
    virtio-pci: Remove wrong address verification in vp_del_vqs()
  * ext4: add reserved GDT blocks check
      fs/ext4/resize.c
  * ext4: make variable "count" signed
      fs/ext4/namei.c
  * ext4: fix bug_on ext4_mb_use_inode_pa
      fs/ext4/mballoc.c
    serial: 8250: Store to lsr_save_flags after lsr read
    usb: gadget: lpc32xx_udc: Fix refcount leak in lpc32xx_udc_probe
    usb: dwc2: Fix memory leak in dwc2_hcd_init
    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/realview: Fix refcount leak in realview_gic_of_init
    certs/blacklist_hashes.c: fix const confusion in certs blacklist
    arm64: ftrace: fix branch range checks
    net: bgmac: Fix an erroneous kfree() in bgmac_remove()
    misc: atmel-ssc: Fix IRQ check in ssc_probe
    tty: goldfish: Fix free_irq() on remove
    i40e: Fix call trace in setup_tx_descriptors
    pNFS: Don't keep retrying if the server replied NFS4ERR_LAYOUTUNAVAILABLE
  * random: credit cpu and bootloader seeds by default
      drivers/char/Kconfig
    net: ethernet: mtk_eth_soc: fix misuse of mem alloc interface netdev[napi]_alloc_frag
  * ipv6: Fix signed integer overflow in l2tp_ip6_sendmsg
      net/l2tp/l2tp_ip6.c
    nfc: nfcmrvl: Fix memory leak in nfcmrvl_play_deferred
    virtio-mmio: fix missing put_device() when vm_cmdline_parent registration failed
    scsi: pmcraid: Fix missing resource cleanup in error case
    scsi: ipr: Fix missing/incorrect resource cleanup in error case
    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
      drivers/char/random.c
  * random: mark bootloader randomness code as __init
      drivers/char/random.c
      include/linux/random.h
  * random: avoid checking crng_ready() twice in random_init()
      drivers/char/random.c
  * crypto: drbg - make reseeding from get_random_bytes() synchronous
      crypto/drbg.c
      drivers/char/random.c
      include/crypto/drbg.h
  * crypto: drbg - always try to free Jitter RNG instance
      crypto/drbg.c
  * crypto: drbg - move dynamic ->reseed_threshold adjustments to __drbg_seed()
      crypto/drbg.c
  * crypto: drbg - track whether DRBG was seeded with !rng_is_initialized()
      crypto/drbg.c
      include/crypto/drbg.h
  * crypto: drbg - prepare for more fine-grained tracking of seeding state
      crypto/drbg.c
      include/crypto/drbg.h
  * crypto: drbg - always seeded with SP800-90B compliant noise source
      crypto/drbg.c
      include/crypto/drbg.h
  * crypto: drbg - add FIPS 140-2 CTRNG for noise source
      crypto/drbg.c
      include/crypto/drbg.h
  * Revert "random: use static branch for crng_ready()"
      drivers/char/random.c
  * random: check for signals after page of pool writes
      drivers/char/random.c
  * random: wire up fops->splice_{read,write}_iter()
      drivers/char/random.c
  * random: convert to using fops->write_iter()
      drivers/char/random.c
  * random: move randomize_page() into mm where it belongs
      drivers/char/random.c
      include/linux/mm.h
      include/linux/random.h
      mm/util.c
  * random: move initialization functions out of hot pages
      drivers/char/random.c
  * random: use proper return types on get_random_{int,long}_wait()
      drivers/char/random.c
      include/linux/random.h
  * random: remove extern from functions in header
      include/linux/random.h
  * random: use static branch for crng_ready()
      drivers/char/random.c
  * random: credit architectural init the exact amount
      drivers/char/random.c
  * random: handle latent entropy and command line from random_init()
      drivers/char/random.c
      include/linux/random.h
      init/main.c
  * random: use proper jiffies comparison macro
      drivers/char/random.c
  * random: remove ratelimiting for in-kernel unseeded randomness
      drivers/char/random.c
      lib/Kconfig.debug
  * random: avoid initializing twice in credit race
      drivers/char/random.c
  * random: use symbolic constants for crng_init states
      drivers/char/random.c
  * siphash: use one source of truth for siphash permutations
      drivers/char/random.c
      include/linux/prandom.h
      include/linux/siphash.h
      lib/siphash.c
  * random: help compiler out with fast_mix() by using simpler arguments
      drivers/char/random.c
  * random: do not use input pool from hard IRQs
      drivers/char/random.c
  * random: order timer entropy functions below interrupt functions
      drivers/char/random.c
  * random: do not pretend to handle premature next security model
      drivers/char/random.c
  * random: do not use batches when !crng_ready()
      drivers/char/random.c
  * random: insist on random_get_entropy() existing in order to simplify
      drivers/char/random.c
    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()
      include/linux/timex.h
      kernel/time/timekeeping.c
    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()
      init/main.c
    random: fix sysctl documentation nits
  * random: document crng_fast_key_erasure() destination possibility
      drivers/char/random.c
  * random: make random_get_entropy() return an unsigned long
      drivers/char/random.c
      include/linux/timex.h
  * random: check for signals every PAGE_SIZE chunk of /dev/[u]random
      drivers/char/random.c
  * random: check for signal_pending() outside of need_resched() check
      drivers/char/random.c
  * random: do not allow user to keep crng key around on stack
      drivers/char/random.c
  * random: do not split fast init input in add_hwgenerator_randomness()
      drivers/char/random.c
  * random: mix build-time latent entropy into pool at init
      drivers/char/random.c
  * random: re-add removed comment about get_random_{u32,u64} reseeding
      drivers/char/random.c
  * random: treat bootloader trust toggle the same way as cpu trust toggle
      drivers/char/Kconfig
      drivers/char/random.c
  * random: skip fast_init if hwrng provides large chunk of entropy
      drivers/char/random.c
  * random: check for signal and try earlier when generating entropy
      drivers/char/random.c
  * random: reseed more often immediately after booting
      drivers/char/random.c
  * random: make consistent usage of crng_ready()
      drivers/char/random.c
  * random: use SipHash as interrupt entropy accumulator
      drivers/char/random.c
  * random: replace custom notifier chain with standard one
      crypto/drbg.c
      drivers/char/random.c
      include/crypto/drbg.h
      include/linux/random.h
      lib/random32.c
  * random: don't let 644 read-only sysctls be written to
      drivers/char/random.c
  * random: give sysctl_random_min_urandom_seed a more sensible value
      drivers/char/random.c
  * random: do crng pre-init loading in worker rather than irq
      drivers/char/random.c
  * random: unify cycles_t and jiffies usage and types
      drivers/char/random.c
  * random: cleanup UUID handling
      drivers/char/random.c
  * random: only wake up writers after zap if threshold was passed
      drivers/char/random.c
  * random: round-robin registers as ulong, not u32
      drivers/char/random.c
  * random: clear fast pool, crng, and batches in cpuhp bring up
      drivers/char/random.c
      include/linux/cpuhotplug.h
      include/linux/random.h
      kernel/cpu.c
  * random: pull add_hwgenerator_randomness() declaration into random.h
      drivers/char/hw_random/core.c
      include/linux/hw_random.h
      include/linux/random.h
  * random: check for crng_init == 0 in add_device_randomness()
      drivers/char/random.c
  * random: unify early init crng load accounting
      drivers/char/random.c
  * random: do not take pool spinlock at boot
      drivers/char/random.c
  * random: defer fast pool mixing to worker
      drivers/char/random.c
  * random: rewrite header introductory comment
      drivers/char/random.c
  * random: group sysctl functions
      drivers/char/random.c
  * random: group userspace read/write functions
      drivers/char/random.c
  * random: group entropy collection functions
      drivers/char/random.c
  * random: group entropy extraction functions
      drivers/char/random.c
  * random: group initialization wait functions
      drivers/char/random.c
  * random: remove whitespace and reorder includes
      drivers/char/random.c
  * random: remove useless header comment
      include/linux/random.h
  * random: introduce drain_entropy() helper to declutter crng_reseed()
      drivers/char/random.c
  * random: deobfuscate irq u32/u64 contributions
      drivers/char/random.c
  * random: add proper SPDX header
      drivers/char/random.c
  * random: remove unused tracepoints
      drivers/char/random.c
      lib/random32.c
  * random: remove ifdef'd out interrupt bench
      drivers/char/random.c
  * random: tie batched entropy generation to base_crng generation
      drivers/char/random.c
  * random: zero buffer after reading entropy from userspace
      drivers/char/random.c
  * random: remove outdated INT_MAX >> 6 check in urandom_read()
      drivers/char/random.c
  * random: use hash function for crng_slow_load()
      drivers/char/random.c
      include/linux/hw_random.h
      include/linux/random.h
  * random: absorb fast pool into input pool after fast load
      drivers/char/random.c
  * random: do not xor RDRAND when writing into /dev/random
      drivers/char/random.c
  * random: ensure early RDSEED goes through mixer on init
      drivers/char/random.c
  * random: inline leaves of rand_initialize()
      drivers/char/random.c
  * random: use RDSEED instead of RDRAND in entropy extraction
      drivers/char/random.c
  * random: fix locking in crng_fast_load()
      drivers/char/random.c
  * random: remove batched entropy locking
      drivers/char/random.c
  * random: remove use_input_pool parameter from crng_reseed()
      drivers/char/random.c
  * random: make credit_entropy_bits() always safe
      drivers/char/random.c
  * random: always wake up entropy writers after extraction
      drivers/char/random.c
  * random: use linear min-entropy accumulation crediting
      drivers/char/random.c
  * random: simplify entropy debiting
      drivers/char/random.c
  * random: use computational hash for entropy extraction
      drivers/char/random.c
  * random: only call crng_finalize_init() for primary_crng
      drivers/char/random.c
  * random: access primary_pool directly rather than through pointer
      drivers/char/random.c
  * random: continually use hwgenerator randomness
      drivers/char/random.c
  * random: simplify arithmetic function flow in account()
      drivers/char/random.c
  * random: access input_pool_data directly rather than through pointer
      drivers/char/random.c
  * random: cleanup fractional entropy shift constants
      drivers/char/random.c
  * random: prepend remaining pool constants with POOL_
      drivers/char/random.c
  * random: de-duplicate INPUT_POOL constants
      drivers/char/random.c
  * random: remove unused OUTPUT_POOL constants
      drivers/char/random.c
  * random: rather than entropy_store abstraction, use global
      drivers/char/random.c
  * random: try to actively add entropy rather than passively wait for it
      drivers/char/random.c
  * random: remove unused extract_entropy() reserved argument
      drivers/char/random.c
  * random: remove incomplete last_data logic
      drivers/char/random.c
  * random: cleanup integer types
      drivers/char/random.c
  * crypto: chacha20 - Fix chacha20_block() keystream alignment (again)
      drivers/char/random.c
  * random: cleanup poolinfo abstraction
      drivers/char/random.c
  * random: fix typo in comments
      drivers/char/random.c
  * random: don't reset crng_init_cnt on urandom_read()
      drivers/char/random.c
  * random: avoid superfluous call to RDRAND in CRNG extraction
      drivers/char/random.c
  * random: early initialization of ChaCha constants
      drivers/char/random.c
  * random: initialize ChaCha20 constants with correct endianness
      drivers/char/random.c
  * random: use IS_ENABLED(CONFIG_NUMA) instead of ifdefs
      drivers/char/random.c
  * random: harmonize "crng init done" messages
      drivers/char/random.c
  * random: mix bootloader randomness into pool
      drivers/char/random.c
  * random: do not re-init if crng_reseed completes before primary init
      drivers/char/random.c
  * random: do not sign extend bytes for rotation when mixing
      drivers/char/random.c
  * random: use BLAKE2s instead of SHA1 in extraction
      drivers/char/random.c
  * random: remove unused irq_flags argument from add_interrupt_randomness()
      drivers/char/random.c
      include/linux/random.h
      kernel/irq/handle.c
  * random: document add_hwgenerator_randomness() with other input functions
      drivers/char/random.c
  * crypto: blake2s - adjust include guard naming
      include/crypto/blake2s.h
      include/crypto/internal/blake2s.h
  * crypto: blake2s - include <linux/bug.h> instead of <asm/bug.h>
      include/crypto/blake2s.h
    MAINTAINERS: co-maintain random.c
  * random: remove dead code left over from blocking pool
      drivers/char/random.c
  * random: avoid arch_get_random_seed_long() when collecting IRQ randomness
      drivers/char/random.c
  * random: add arch_get_random_*long_early()
      drivers/char/random.c
      include/linux/random.h
    powerpc: Use bool in archrandom.h
  * linux/random.h: Mark CONFIG_ARCH_RANDOM functions __must_check
      include/linux/random.h
  * linux/random.h: Use false with bool
      include/linux/random.h
  * linux/random.h: Remove arch_has_random, arch_has_random_seed
      include/linux/random.h
    s390: 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
      drivers/char/random.c
  * random: split primary/secondary crng init paths
      drivers/char/random.c
  * random: remove some dead code of poolinfo
      drivers/char/random.c
  * random: fix typo in add_timer_randomness()
      drivers/char/random.c
  * random: Add and use pr_fmt()
      drivers/char/random.c
  * random: convert to ENTROPY_BITS for better code readability
      drivers/char/random.c
  * random: remove unnecessary unlikely()
      drivers/char/random.c
  * random: remove kernel.random.read_wakeup_threshold
      drivers/char/random.c
  * random: delete code to pull data into pools
      drivers/char/random.c
  * random: remove the blocking pool
      drivers/char/random.c
  * random: fix crash on multiple early calls to add_bootloader_randomness()
      drivers/char/random.c
  * char/random: silence a lockdep splat with printk()
      drivers/char/random.c
  * random: make /dev/random be almost like /dev/urandom
      drivers/char/random.c
  * random: ignore GRND_RANDOM in getentropy(2)
      drivers/char/random.c
      include/uapi/linux/random.h
  * random: add GRND_INSECURE to return best-effort non-cryptographic bytes
      drivers/char/random.c
      include/uapi/linux/random.h
  * random: Add a urandom_read_nowait() for random APIs that don't warn
      drivers/char/random.c
  * random: Don't wake crng_init_wait when crng_init == 1
      drivers/char/random.c
  * lib/crypto: sha1: re-roll loops to reduce code size
      lib/sha1.c
  * lib/crypto: blake2s: move hmac construction into wireguard
      include/crypto/blake2s.h
      lib/crypto/blake2s.c
  * crypto: blake2s - generic C library implementation and selftest
      include/crypto/blake2s.h
      include/crypto/internal/blake2s.h
      lib/Makefile
      lib/crypto/Makefile
      lib/crypto/blake2s-generic.c
      lib/crypto/blake2s.c
  * crypto: Deduplicate le32_to_cpu_array() and cpu_to_le32_array()
      crypto/md4.c
      crypto/md5.c
      include/linux/byteorder/generic.h
  * Revert "hwrng: core - Freeze khwrng thread during suspend"
      drivers/char/random.c
  * char/random: Add a newline at the end of the file
      drivers/char/random.c
  * random: Use wait_event_freezable() in add_hwgenerator_randomness()
      drivers/char/random.c
  * fdt: add support for rng-seed
      drivers/char/Kconfig
      drivers/char/random.c
      drivers/of/fdt.c
      include/linux/random.h
  * random: Support freezable kthreads in add_hwgenerator_randomness()
      drivers/char/random.c
  * random: fix soft lockup when trying to read from an uninitialized blocking pool
      drivers/char/random.c
  * latent_entropy: avoid build error when plugin cflags are not set
      include/linux/random.h
  * random: document get_random_int() family
      drivers/char/random.c
  * random: move rand_initialize() earlier
      drivers/char/random.c
      include/linux/random.h
      init/main.c
  * random: only read from /dev/random after its pool has received 128 bits
      drivers/char/random.c
  * drivers/char/random.c: make primary_crng static
      drivers/char/random.c
  * drivers/char/random.c: remove unused stuct poolinfo::poolbits
      drivers/char/random.c
  * drivers/char/random.c: constify poolinfo_table
      drivers/char/random.c
  * random: make CPU trust a boot parameter
      drivers/char/Kconfig
      drivers/char/random.c
  * random: Make crng state queryable
      drivers/char/random.c
      include/linux/random.h
  * random: remove preempt disabled region
      drivers/char/random.c
  * random: add a config option to trust the CPU's hwrng
      drivers/char/Kconfig
      drivers/char/random.c
  * random: Return nbytes filled from hw RNG
      drivers/char/random.c
      include/linux/random.h
  * random: Fix whitespace pre random-bytes work
      drivers/char/random.c
  * drivers/char/random.c: remove unused dont_count_entropy
      drivers/char/random.c
  * random: optimize add_interrupt_randomness
      drivers/char/random.c
  * random: always fill buffer in get_random_bytes_wait
      include/linux/random.h
  * crypto: chacha20 - Fix keystream alignment for chacha20_block()
      drivers/char/random.c
    9p: missing chunk of "fs/9p: Don't update file type when updating file attributes"
  * UPSTREAM: ext4: verify dir block before splitting it
      fs/ext4/namei.c
  * UPSTREAM: ext4: fix use-after-free in ext4_rename_dir_prepare
      fs/ext4/namei.c
  * BACKPORT: ext4: Only advertise encrypted_casefold when encryption and unicode are enabled
      fs/ext4/sysfs.c
  * BACKPORT: ext4: fix no-key deletion for encrypt+casefold
      fs/ext4/namei.c
  * BACKPORT: ext4: optimize match for casefolded encrypted dirs
      fs/ext4/ext4.h
      fs/ext4/namei.c
  * BACKPORT: ext4: handle casefolding with encryption
      fs/ext4/dir.c
      fs/ext4/ext4.h
      fs/ext4/hash.c
      fs/ext4/inline.c
      fs/ext4/namei.c
      fs/ext4/super.c
      fs/ext4/sysfs.c
  * Revert "ANDROID: ext4: Handle casefolding with encryption"
      fs/ext4/dir.c
      fs/ext4/ext4.h
      fs/ext4/hash.c
      fs/ext4/ialloc.c
      fs/ext4/inline.c
      fs/ext4/namei.c
      fs/ext4/super.c
  * Revert "ANDROID: ext4: Optimize match for casefolded encrypted dirs"
      fs/ext4/ext4.h
      fs/ext4/namei.c
    Merge 4.14.284 into android-4.14-stable
  * Revert "ext4: fix use-after-free in ext4_rename_dir_prepare"
      fs/ext4/namei.c
  * Revert "ext4: verify dir block before splitting it"
      fs/ext4/namei.c
Linux 4.14.284
    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
      drivers/base/cpu.c
      include/linux/cpu.h
    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()
      include/linux/cpu.h
    x86/cpu: Add Elkhart Lake to Intel family
    Merge 4.14.283 into android-4.14-stable
Linux 4.14.283
  * tcp: fix tcp_mtup_probe_success vs wrong snd_cwnd
      net/ipv4/tcp_input.c
    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
    md/raid0: Ignore RAID0 layout if the second zone has only one device
    powerpc/32: Fix overread/overwrite of thread_struct via ptrace
    Input: bcm5974 - set missing URB_NO_TRANSFER_DMA_MAP urb flag
    ixgbe: fix unexpected VLAN Rx in promisc mode on VF
    ixgbe: fix bcast packets Rx on VF after promisc removal
    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
      include/linux/nodemask.h
      lib/nodemask.c
    nbd: fix io hung while disconnecting device
    nbd: fix race between nbd_alloc_config() and module removal
    nbd: call genl_unregister_family() first in nbd_cleanup()
  * modpost: fix undefined behavior of is_arm_mapping_symbol()
      scripts/mod/modpost.c
    drm/radeon: fix a possible null pointer dereference
  * Revert "net: af_key: add check for pfkey_broadcast in function pfkey_process"
      net/key/af_key.c
    md: protect md_unregister_thread from reentrancy
  * kernfs: Separate kernfs_pr_cont_buf and rename_lock.
      fs/kernfs/dir.c
    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
  * extcon: Modify extcon device to be created after driver data is set
      drivers/extcon/extcon.c
    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/core/hcd-pci.c
    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()
    drm: imx: fix compiler warning with gcc-12
    net: altera: Fix refcount leak in altera_tse_mdio_create
    net: ipv6: unexport __init-annotated seg6_hmac_init()
  * net: xfrm: unexport __init-annotated xfrm4_protocol_init()
      net/ipv4/xfrm4_protocol.c
  * net: mdio: unexport __init-annotated mdio_bus_init()
      drivers/net/phy/mdio_bus.c
    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
    xprtrdma: treat all calls not a bcall when bc_serv is NULL
    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
      kernel/trace/trace.c
  * tracing: Fix sleeping function called from invalid context on RT kernel
      kernel/trace/trace.c
    mips: cpc: Fix refcount leak in mips_cpc_default_phys_base
    perf c2c: Fix sorting in percent_rmt_hitm_cmp()
  * tcp: tcp_rtx_synack() can be called from process context
      net/ipv4/tcp_output.c
    ubi: ubi_create_volume: Fix use-after-free when volume creation failed
    jffs2: fix memory leak in jffs2_do_fill_super
  * modpost: fix removing numeric suffixes
      scripts/mod/modpost.c
    net: dsa: mv88e6xxx: Fix refcount leak in mv88e6xxx_mdios_register
    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()
    soc: rockchip: Fix refcount leak in rockchip_grf_init
    coresight: cpu-debug: Replace mutex with mutex_trylock on panic notifier
    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()
    tty: goldfish: Use tty_port_destroy() to destroy port
    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
    phy: qcom-qmp: fix reset-controller leak on probe errors
    dt-bindings: gpio: altera: correct interrupt-cells
    docs/conf.py: Cope with removal of language=None in Sphinx 5.0.0
    phy: qcom-qmp: fix struct clk leak on probe errors
    arm64: dts: qcom: ipq8074: fix the sleep clock frequency
    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
      sound/soc/codecs/rt5514.c
    rtl818x: Prevent using not initialized queues
    hugetlb: fix huge_pmd_unshare address update
  * nodemask.h: fix compilation error with GCC12
      include/linux/nodemask.h
    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/nouveau/clk: Fix an incorrect NULL check on list iterator
    drm/amdgpu/cs: make commands with 0 chunks illegal behaviour.
  * scsi: ufs: qcom: Add a readl() to make sure ref_clk gets enabled
      drivers/scsi/ufs/ufs-qcom.c
    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: avoid cycles in directory h-tree
      fs/ext4/namei.c
  * ext4: verify dir block before splitting it
      fs/ext4/namei.c
  * ext4: fix bug_on in ext4_writepages
      fs/ext4/inline.c
  * ext4: fix use-after-free in ext4_rename_dir_prepare
      fs/ext4/namei.c
  * fs-writeback: writeback_sb_inodes：Recalculate 'wrote' according skipped pages
      fs/fs-writeback.c
    iwlwifi: mvm: fix assert 1F04 upon reconfig
    wifi: mac80211: fix use-after-free in chanctx code
    perf jevents: Fix event syntax error caused by ExtSel
    perf c2c: Use stdio interface if slang is not supported
    iommu/amd: Increase timeout waiting for GA log enablement
    video: fbdev: clcdfb: Fix refcount leak in clcdfb_of_vram_setup
    iommu/mediatek: Add list_del in mtk_iommu_remove
  * mailbox: forward the hrtimer if not queued and under a lock
      drivers/mailbox/mailbox.c
      include/linux/mailbox_controller.h
    powerpc/fsl_rio: Fix refcount leak in fsl_rio_setup
    powerpc/perf: Fix the threshold compare group constraint for power9
    Input: sparcspkr - fix refcount leak in bbc_beep_probe
  * tty: fix deadlock caused by calling printk() under tty_port->lock
      drivers/tty/tty_buffer.c
    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
    pinctrl: mvebu: Fix irq_of_parse_and_map() return value
    scsi: fcoe: Fix Wstringop-overflow warnings in fcoe_wwn_from_mac()
    mfd: ipaq-micro: Fix error check return value of platform_get_irq()
    ARM: dts: bcm2835-rpi-b: Fix GPIO line names
    ARM: dts: bcm2835-rpi-zero-w: Fix GPIO line name for Wifi/BT
    soc: qcom: smsm: Fix missing of_node_put() in smsm_parse_ipc
  * soc: qcom: smp2p: Fix missing of_node_put() in smp2p_parse_ipc
      drivers/soc/qcom/smp2p.c
    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()
      net/sctp/input.c
    m68k: math-emu: Fix dependencies of math emulation support
  * Bluetooth: fix dangling sco_conn and use-after-free in sco_sock_timeout
      net/bluetooth/sco.c
    media: pvrusb2: fix array-index-out-of-bounds in pvr2_i2c_core_init
    media: exynos4-is: Change clk_disable to clk_disable_unprepare
    media: st-delta: Fix PM disable depth imbalance in delta_probe
    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
      drivers/media/usb/uvc/uvc_v4l2.c
  * drm/msm: return an error pointer in msm_gem_prime_get_sg_table()
      drivers/gpu/drm/msm/msm_gem_prime.c
    x86/mm: Cleanup the control_va_addr_alignment() __setup handler
    irqchip/aspeed-i2c-ic: Fix irq_of_parse_and_map() return value
    x86: Fix return value of __setup handlers
    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()
  * fsnotify: fix wrong lockdep annotations
      fs/notify/mark.c
  * inotify: show inotify mask flags in proc fdinfo
      fs/notify/fdinfo.c
      fs/notify/inotify/inotify.h
      fs/notify/inotify/inotify_user.c
    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
  * efi: Add missing prototype for efi_capsule_setup_info
      include/linux/efi.h
    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 missing of_node_put in mt2701_wm8960_machine_probe
    ASoC: mediatek: Fix error handling in mt8173_max98090_dev_probe
    ath9k: fix ar9003_get_eepmisc
  * drm: fix EDID struct for old ARM OABI format
      include/drm/drm_edid.h
    RDMA/hfi1: Prevent panic when SDMA is disabled
  * macintosh/via-pmu: Fix build failure when CONFIG_INPUT is disabled
      drivers/macintosh/Kconfig
      drivers/macintosh/Makefile
    powerpc/xics: fix refcount leak in icp_opal_init()
  * tracing: incorrect isolate_mote_t cast in mm_vmscan_lru_isolate
      include/trace/events/vmscan.h
  * PCI: Avoid pci_dev_lock() AB/BA deadlock with sriov_numvfs_store()
      drivers/pci/pci.c
    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()
      fs/fat/fatent.c
    ARM: OMAP1: clock: Fix UART rate reporting algorithm
    fs: jfs: fix possible NULL pointer dereference in dbFree()
    ARM: dts: ox820: align interrupt controller node name with dtschema
  * eth: tg3: silence the GCC 12 array-bounds warning
      drivers/net/ethernet/broadcom/Makefile
    rxrpc: Return an error to sendmsg if call failed
    media: exynos4-is: Fix compile warning
  * net: phy: micrel: Allow probing without .driver_data
      drivers/net/phy/micrel.c
    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
    rtlwifi: Use pr_warn instead of WARN_ONCE
    ipmi:ssif: Check for NULL msg when handling events and messages
    dma-debug: change allocation mode from GFP_NOWAIT to GFP_ATIOMIC
    s390/preempt: disable __preempt_count_add() optimization for PROFILE_ALL_BRANCHES
  * ASoC: dapm: Don't fold register value changes into notifications
      sound/soc/soc-dapm.c
  * ipv6: Don't send rs packets to the interface of ARPHRD_TUNNEL
      net/ipv6/addrconf.c
    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
    media: pci: cx23885: Fix the error handling in cx23885_initdev()
    media: venus: hfi: avoid null dereference in deinit
    ath9k: fix QCA9561 PA bias level
    drm/amd/pm: fix double free in si_parse_power_table()
  * ALSA: jack: Access input_dev under mutex
      include/sound/jack.h
      sound/core/jack.c
    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: repair super block num_devices automatically
    btrfs: add "0x" prefix for unsupported optional features
  * ptrace: Reimplement PTRACE_KILL by always sending SIGKILL
      kernel/ptrace.c
  * ptrace/xtensa: Replace PT_SINGLESTEP with TIF_SINGLESTEP
      include/linux/ptrace.h
  * USB: new quirk for Dell Gen 2 devices
      drivers/usb/core/quirks.c
    USB: serial: option: add Quectel BG95 modem
    binfmt_flat: do not stop relocating GOT entries prematurely on riscv
  * BACKPORT: psi: Fix uaf issue when psi trigger is destroyed while being polled
      include/linux/psi.h
      include/linux/psi_types.h
      kernel/cgroup/cgroup.c
      kernel/sched/psi.c
  * FROMGIT: Revert "net: af_key: add check for pfkey_broadcast in function pfkey_process"
      net/key/af_key.c
    ANDROID: android-verity: Prevent double-freeing metadata
    Merge 4.14.282 into android-4.14-stable
Linux 4.14.282
  * bpf: Enlarge offset check value to INT_MAX in bpf_skb_{load,store}_bytes
      net/core/filter.c
    NFSD: Fix possible sleep during nfsd4_release_lockowner()
    docs: submitting-patches: Fix crossref to 'The canonical patch format'
    tpm: ibmvtpm: Correct the return value in tpm_ibmvtpm_probe()
  * dm verity: set DM_TARGET_IMMUTABLE feature flag
      drivers/md/dm-verity-target.c
  * dm stats: add cond_resched when looping over entries
      drivers/md/dm-stats.c
  * dm crypt: make printing of the key constant-time
      drivers/md/dm-crypt.c
    dm integrity: fix error code in dm_integrity_ctr()
  * zsmalloc: fix races between asynchronous zspage free and page migration
      mm/zsmalloc.c
  * netfilter: conntrack: re-fetch conntrack after insertion
      include/net/netfilter/nf_conntrack_core.h
  * exec: Force single empty string when argv is empty
      fs/exec.c
  * block-map: add __GFP_ZERO flag for alloc_page in function bio_copy_kern
      block/bio.c
    drm/i915: Fix -Wstringop-overflow warning in call to intel_read_wm_latency()
  * assoc_array: Fix BUG_ON during garbage collect
      lib/assoc_array.c
    drivers: i2c: thunderx: Allow driver to work with ACPI defined TWSI controllers
    net: ftgmac100: Disable hardware checksum on AST2600
  * net: af_key: check encryption module availability consistency
      net/key/af_key.c
    ACPI: sysfs: Fix BERT error region memory mapping
    ACPI: sysfs: Make sparse happy about address space in use
  * secure_seq: use the 64 bits of the siphash for port offset calculation
      include/net/inet_hashtables.h
      include/net/secure_seq.h
      net/core/secure_seq.c
      net/ipv4/inet_hashtables.c
      net/ipv6/inet6_hashtables.c
  * tcp: change source port randomizarion at connect() time
      net/ipv4/inet_hashtables.c
    staging: rtl8723bs: prevent ->Ssid overflow in rtw_wx_set_scan()
    x86/pci/xen: Disable PCI/MSI[-X] masking for XEN_HVM guests

Bug: 237729727
Change-Id: I47053f037f09ce3b44fb4ca21dd80f8b6371d3aa
Signed-off-by: Lucas Wei <lucaswei@google.com>
2022-07-25 15:26:14 +08:00

2534 lines
62 KiB
C
Raw Permalink Blame History

/* 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/signal.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/task.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/nmi.h>
#include <linux/smpboot.h>
#include <linux/relay.h>
#include <linux/slab.h>
#include <linux/percpu-rwsem.h>
#include <uapi/linux/sched/types.h>
#include <linux/highmem.h>
#include <linux/cpuset.h>
#include <linux/random.h>
#include <trace/events/power.h>
#define CREATE_TRACE_POINTS
#include <trace/events/cpuhp.h>
#include <linux/sched/clock.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_up: Signal completion to the issuer of the task for cpu-up
* @done_down: Signal completion to the issuer of the task for cpu-down
*/
struct cpuhp_cpu_state {
enum cpuhp_state state;
enum cpuhp_state target;
enum cpuhp_state fail;
#ifdef CONFIG_SMP
struct task_struct *thread;
bool should_run;
bool rollback;
bool single;
bool bringup;
bool booted_once;
struct hlist_node *node;
struct hlist_node *last;
enum cpuhp_state cb_state;
int result;
struct completion done_up;
struct completion done_down;
#endif
};
static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = {
.fail = CPUHP_INVALID,
};
#if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP)
static struct lockdep_map cpuhp_state_up_map =
STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map);
static struct lockdep_map cpuhp_state_down_map =
STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map);
static void inline cpuhp_lock_acquire(bool bringup)
{
lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
}
static void inline cpuhp_lock_release(bool bringup)
{
lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
}
#else
static void inline cpuhp_lock_acquire(bool bringup) { }
static void inline cpuhp_lock_release(bool bringup) { }
#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
* @state: The state to do callbacks for
* @bringup: True if the bringup callback should be invoked
* @node: For multi-instance, do a single entry callback for install/remove
* @lastp: For multi-instance rollback, remember how far we got
*
* 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 hlist_node **lastp)
{
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 (st->fail == state) {
st->fail = CPUHP_INVALID;
if (!(bringup ? step->startup.single : step->teardown.single))
return 0;
return -EAGAIN;
}
if (!step->multi_instance) {
WARN_ON_ONCE(lastp && *lastp);
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) {
WARN_ON_ONCE(lastp && *lastp);
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) {
if (lastp && node == *lastp)
break;
trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
ret = cbm(cpu, node);
trace_cpuhp_exit(cpu, st->state, state, ret);
if (ret) {
if (!lastp)
goto err;
*lastp = node;
return ret;
}
cnt++;
}
if (lastp)
*lastp = NULL;
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;
trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
ret = cbm(cpu, node);
trace_cpuhp_exit(cpu, st->state, state, ret);
/*
* Rollback must not fail,
*/
WARN_ON_ONCE(ret);
}
return ret;
}
#ifdef CONFIG_SMP
static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
{
struct completion *done = bringup ? &st->done_up : &st->done_down;
wait_for_completion(done);
}
static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup)
{
struct completion *done = bringup ? &st->done_up : &st->done_down;
complete(done);
}
/*
* The former STARTING/DYING states, ran with IRQs disabled and must not fail.
*/
static bool cpuhp_is_atomic_state(enum cpuhp_state state)
{
return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE;
}
/* 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.
*/
void cpu_maps_update_begin(void)
{
mutex_lock(&cpu_add_remove_lock);
}
void cpu_maps_update_done(void)
{
mutex_unlock(&cpu_add_remove_lock);
}
/*
* 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
DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock);
void cpus_read_lock(void)
{
percpu_down_read(&cpu_hotplug_lock);
}
EXPORT_SYMBOL_GPL(cpus_read_lock);
void cpus_read_unlock(void)
{
percpu_up_read(&cpu_hotplug_lock);
}
EXPORT_SYMBOL_GPL(cpus_read_unlock);
void cpus_write_lock(void)
{
percpu_down_write(&cpu_hotplug_lock);
}
void cpus_write_unlock(void)
{
percpu_up_write(&cpu_hotplug_lock);
}
void lockdep_assert_cpus_held(void)
{
/*
* We can't have hotplug operations before userspace starts running,
* and some init codepaths will knowingly not take the hotplug lock.
* This is all valid, so mute lockdep until it makes sense to report
* unheld locks.
*/
if (system_state < SYSTEM_RUNNING)
return;
percpu_rwsem_assert_held(&cpu_hotplug_lock);
}
/*
* 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;
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.
*/
void __init cpu_smt_check_topology(void)
{
if (!topology_smt_supported())
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 (cpu_smt_control == CPU_SMT_ENABLED)
return true;
if (topology_is_primary_thread(cpu))
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
static inline enum cpuhp_state
cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
{
enum cpuhp_state prev_state = st->state;
st->rollback = false;
st->last = NULL;
st->target = target;
st->single = false;
st->bringup = st->state < target;
return prev_state;
}
static inline void
cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state)
{
st->rollback = true;
/*
* If we have st->last we need to undo partial multi_instance of this
* state first. Otherwise start undo at the previous state.
*/
if (!st->last) {
if (st->bringup)
st->state--;
else
st->state++;
}
st->target = prev_state;
st->bringup = !st->bringup;
}
/* Regular hotplug invocation of the AP hotplug thread */
static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st)
{
if (!st->single && st->state == st->target)
return;
st->result = 0;
/*
* 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_ap_thread(st, st->bringup);
}
static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target)
{
enum cpuhp_state prev_state;
int ret;
prev_state = cpuhp_set_state(st, target);
__cpuhp_kick_ap(st);
if ((ret = st->result)) {
cpuhp_reset_state(st, prev_state);
__cpuhp_kick_ap(st);
}
return ret;
}
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_ap_thread(st, true);
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;
if (st->target <= CPUHP_AP_ONLINE_IDLE)
return 0;
return cpuhp_kick_ap(st, st->target);
}
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)
return ret;
return bringup_wait_for_ap(cpu);
}
/*
* Hotplug state machine related functions
*/
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, 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, 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_up);
init_completion(&st->done_down);
}
static int cpuhp_should_run(unsigned int cpu)
{
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
return st->should_run;
}
/*
* Execute teardown/startup callbacks on the plugged cpu. Also used to invoke
* callbacks when a state gets [un]installed at runtime.
*
* Each invocation of this function by the smpboot thread does a single AP
* state callback.
*
* It has 3 modes of operation:
* - single: runs st->cb_state
* - up: runs ++st->state, while st->state < st->target
* - down: runs st->state--, while st->state > st->target
*
* When complete or on error, should_run is cleared and the completion is fired.
*/
static void cpuhp_thread_fun(unsigned int cpu)
{
struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state);
bool bringup = st->bringup;
enum cpuhp_state state;
if (WARN_ON_ONCE(!st->should_run))
return;
/*
* ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures
* that if we see ->should_run we also see the rest of the state.
*/
smp_mb();
cpuhp_lock_acquire(bringup);
if (st->single) {
state = st->cb_state;
st->should_run = false;
} else {
if (bringup) {
st->state++;
state = st->state;
st->should_run = (st->state < st->target);
WARN_ON_ONCE(st->state > st->target);
} else {
state = st->state;
st->state--;
st->should_run = (st->state > st->target);
WARN_ON_ONCE(st->state < st->target);
}
}
WARN_ON_ONCE(!cpuhp_is_ap_state(state));
if (st->rollback) {
struct cpuhp_step *step = cpuhp_get_step(state);
if (step->skip_onerr)
goto next;
}
if (cpuhp_is_atomic_state(state)) {
local_irq_disable();
st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last);
local_irq_enable();
/*
* STARTING/DYING must not fail!
*/
WARN_ON_ONCE(st->result);
} else {
st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last);
}
if (st->result) {
/*
* If we fail on a rollback, we're up a creek without no
* paddle, no way forward, no way back. We loose, thanks for
* playing.
*/
WARN_ON_ONCE(st->rollback);
st->should_run = false;
}
next:
cpuhp_lock_release(bringup);
if (!st->should_run)
complete_ap_thread(st, bringup);
}
/* 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);
int ret;
if (!cpu_online(cpu))
return 0;
cpuhp_lock_acquire(false);
cpuhp_lock_release(false);
cpuhp_lock_acquire(true);
cpuhp_lock_release(true);
/*
* 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, NULL);
st->rollback = false;
st->last = NULL;
st->node = node;
st->bringup = bringup;
st->cb_state = state;
st->single = true;
__cpuhp_kick_ap(st);
/*
* If we failed and did a partial, do a rollback.
*/
if ((ret = st->result) && st->last) {
st->rollback = true;
st->bringup = !bringup;
__cpuhp_kick_ap(st);
}
/*
* Clean up the leftovers so the next hotplug operation wont use stale
* data.
*/
st->node = st->last = NULL;
return ret;
}
static int cpuhp_kick_ap_work(unsigned int cpu)
{
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
enum cpuhp_state prev_state = st->state;
int ret;
cpuhp_lock_acquire(false);
cpuhp_lock_release(false);
cpuhp_lock_acquire(true);
cpuhp_lock_release(true);
trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work);
ret = cpuhp_kick_ap(st, st->target);
trace_cpuhp_exit(cpu, st->state, prev_state, ret);
return ret;
}
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));
}
/*
*
* Serialize hotplug trainwrecks outside of the cpu_hotplug_lock
* protected region.
*
* The operation is still serialized against concurrent CPU hotplug via
* cpu_add_remove_lock, i.e. CPU map protection. But it is _not_
* serialized against other hotplug related activity like adding or
* removing of state callbacks and state instances, which invoke either the
* startup or the teardown callback of the affected state.
*
* This is required for subsystems which are unfixable vs. CPU hotplug and
* evade lock inversion problems by scheduling work which has to be
* completed _before_ cpu_up()/_cpu_down() returns.
*
* Don't even think about adding anything to this for any new code or even
* drivers. It's only purpose is to keep existing lock order trainwrecks
* working.
*
* For cpu_down() there might be valid reasons to finish cleanups which are
* not required to be done under cpu_hotplug_lock, but that's a different
* story and would be not invoked via this.
*/
static void cpu_up_down_serialize_trainwrecks(bool tasks_frozen)
{
/*
* cpusets delegate hotplug operations to a worker to "solve" the
* lock order problems. Wait for the worker, but only if tasks are
* _not_ frozen (suspend, hibernate) as that would wait forever.
*
* The wait is required because otherwise the hotplug operation
* returns with inconsistent state, which could even be observed in
* user space when a new CPU is brought up. The CPU plug uevent
* would be delivered and user space reacting on it would fail to
* move tasks to the newly plugged CPU up to the point where the
* work has finished because up to that point the newly plugged CPU
* is not assignable in cpusets/cgroups. On unplug that's not
* necessarily a visible issue, but it is still inconsistent state,
* which is the real problem which needs to be "fixed". This can't
* prevent the transient state between scheduling the work and
* returning from waiting for it.
*/
if (!tasks_frozen)
cpuset_wait_for_hotplug();
}
#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();
}
/* 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();
int ret;
/* 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--) {
ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL);
/*
* DYING must not fail!
*/
WARN_ON_ONCE(ret);
}
/* 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_cpuslocked(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_ap_thread(st, false);
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);
rcutree_migrate_callbacks(cpu);
return 0;
}
static void cpuhp_complete_idle_dead(void *arg)
{
struct cpuhp_cpu_state *st = arg;
complete_ap_thread(st, false);
}
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);
}
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, 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, NULL);
BUG_ON(ret && st->state < CPUHP_AP_IDLE_DEAD);
if (ret) {
st->target = prev_state;
if (st->state < prev_state)
undo_cpu_down(cpu, st);
break;
}
}
return ret;
}
/* 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;
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;
cpus_write_lock();
if (trace_cpuhp_latency_enabled())
start_time = sched_clock();
cpuhp_tasks_frozen = tasks_frozen;
prev_state = cpuhp_set_state(st, 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) {
st->target = max((int)target, 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;
st->target = target;
}
/*
* 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) {
cpuhp_reset_state(st, prev_state);
__cpuhp_kick_ap(st);
}
out:
trace_cpuhp_latency(cpu, 0, start_time, ret);
cpus_write_unlock();
/*
* Do post unplug cleanup. This is still protected against
* concurrent CPU hotplug via cpu_add_remove_lock.
*/
lockup_detector_cleanup();
arch_smt_update();
cpu_up_down_serialize_trainwrecks(tasks_frozen);
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;
/*
* When cpusets are enabled, the rebuilding of the scheduling
* domains is deferred to a workqueue context. Make sure
* that the work is completed before proceeding to the next
* hotplug. Otherwise scheduler observes an inconsistent
* view of online and offline CPUs in the root domain. If
* the online CPUs are still stuck in the offline (default)
* domain, those CPUs would not be visible when scheduling
* happens on from other CPUs in the root domain.
*/
cpuset_wait_for_hotplug();
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);
#else
#define takedown_cpu NULL
#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);
int ret;
rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
st->booted_once = true;
while (st->state < target) {
st->state++;
ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
/*
* STARTING must not fail!
*/
WARN_ON_ONCE(ret);
}
}
/*
* 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_ap_thread(st, true);
}
/* 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;
cpus_write_lock();
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;
cpuhp_set_state(st, 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);
cpus_write_unlock();
arch_smt_update();
cpu_up_down_serialize_trainwrecks(tasks_frozen);
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, &param);
return err;
}
static int switch_to_fair_policy(void)
{
struct sched_param param = { .sched_priority = 0 };
return sched_setscheduler_nocheck(current, SCHED_NORMAL, &param);
}
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;
}
cpuset_wait_for_hotplug();
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;
if (pm_wakeup_pending()) {
pr_info("Wakeup pending. Abort CPU freeze\n");
error = -EBUSY;
break;
}
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 */
int __boot_cpu_id;
#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,
},
/*
* 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_IRQ_AFFINITY_ONLINE] = {
.name = "irq/affinity:online",
.startup.single = irq_affinity_online_cpu,
.teardown.single = NULL,
},
[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,
},
#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;
}
/*
* 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, end;
struct cpuhp_step *step;
switch (state) {
case CPUHP_AP_ONLINE_DYN:
step = cpuhp_ap_states + CPUHP_AP_ONLINE_DYN;
end = CPUHP_AP_ONLINE_DYN_END;
break;
case CPUHP_BP_PREPARE_DYN:
step = cpuhp_bp_states + CPUHP_BP_PREPARE_DYN;
end = CPUHP_BP_PREPARE_DYN_END;
break;
default:
return -EINVAL;
}
for (i = state; i <= end; i++, step++) {
if (!step->name)
return i;
}
WARN(1, "No more dynamic states available for CPU hotplug\n");
return -ENOSPC;
}
static int 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;
int ret = 0;
/*
* If name is NULL, then the state gets removed.
*
* CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on
* the first allocation from these dynamic ranges, so the removal
* would trigger a new allocation and clear the wrong (already
* empty) state, leaving the callbacks of the to be cleared state
* dangling, which causes wreckage on the next hotplug operation.
*/
if (name && (state == CPUHP_AP_ONLINE_DYN ||
state == CPUHP_BP_PREPARE_DYN)) {
ret = cpuhp_reserve_state(state);
if (ret < 0)
return ret;
state = ret;
}
sp = cpuhp_get_step(state);
if (name && sp->name)
return -EBUSY;
sp->startup.single = startup;
sp->teardown.single = teardown;
sp->name = name;
sp->multi_instance = multi_instance;
INIT_HLIST_HEAD(&sp->list);
return ret;
}
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 there's nothing to do, we done.
* Relies on the union for multi_instance.
*/
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, NULL);
#else
ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL);
#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);
}
}
int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state,
struct hlist_node *node,
bool invoke)
{
struct cpuhp_step *sp;
int cpu;
int ret;
lockdep_assert_cpus_held();
sp = cpuhp_get_step(state);
if (sp->multi_instance == false)
return -EINVAL;
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 unlock;
}
}
add_node:
ret = 0;
hlist_add_head(node, &sp->list);
unlock:
mutex_unlock(&cpuhp_state_mutex);
return ret;
}
int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
bool invoke)
{
int ret;
cpus_read_lock();
ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke);
cpus_read_unlock();
return ret;
}
EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
/**
* __cpuhp_setup_state_cpuslocked - 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
* @multi_instance: State is set up for multiple instances which get
* added afterwards.
*
* The caller needs to hold cpus read locked while calling this function.
* Returns:
* On success:
* Positive state number if @state is CPUHP_AP_ONLINE_DYN
* 0 for all other states
* On failure: proper (negative) error code
*/
int __cpuhp_setup_state_cpuslocked(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;
bool dynstate;
lockdep_assert_cpus_held();
if (cpuhp_cb_check(state) || !name)
return -EINVAL;
mutex_lock(&cpuhp_state_mutex);
ret = cpuhp_store_callbacks(state, name, startup, teardown,
multi_instance);
dynstate = state == CPUHP_AP_ONLINE_DYN;
if (ret > 0 && dynstate) {
state = ret;
ret = 0;
}
if (ret || !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);
/*
* If the requested state is CPUHP_AP_ONLINE_DYN, return the
* dynamically allocated state in case of success.
*/
if (!ret && dynstate)
return state;
return ret;
}
EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked);
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 ret;
cpus_read_lock();
ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup,
teardown, multi_instance);
cpus_read_unlock();
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;
cpus_read_lock();
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);
cpus_read_unlock();
return 0;
}
EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance);
/**
* __cpuhp_remove_state_cpuslocked - 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 caller needs to hold cpus read locked while calling this function.
* The teardown callback is currently not allowed to fail. Think
* about module removal!
*/
void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke)
{
struct cpuhp_step *sp = cpuhp_get_step(state);
int cpu;
BUG_ON(cpuhp_cb_check(state));
lockdep_assert_cpus_held();
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);
}
EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked);
void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
{
cpus_read_lock();
__cpuhp_remove_state_cpuslocked(state, invoke);
cpus_read_unlock();
}
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 ssize_t write_cpuhp_fail(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 fail, ret;
ret = kstrtoint(buf, 10, &fail);
if (ret)
return ret;
if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE)
return -EINVAL;
/*
* Cannot fail STARTING/DYING callbacks.
*/
if (cpuhp_is_atomic_state(fail))
return -EINVAL;
/*
* Cannot fail anything that doesn't have callbacks.
*/
mutex_lock(&cpuhp_state_mutex);
sp = cpuhp_get_step(fail);
if (!sp->startup.single && !sp->teardown.single)
ret = -EINVAL;
mutex_unlock(&cpuhp_state_mutex);
if (ret)
return ret;
st->fail = fail;
return count;
}
static ssize_t show_cpuhp_fail(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->fail);
}
static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail);
static struct attribute *cpuhp_cpu_attrs[] = {
&dev_attr_state.attr,
&dev_attr_target.attr,
&dev_attr_fail.attr,
NULL
};
static const 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 const 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);
unsigned int __cpu_psci_id[NR_CPUS];
EXPORT_SYMBOL(__cpu_psci_id);
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);
#ifdef CONFIG_SMP
__boot_cpu_id = cpu;
#endif
set_cpu_psci_function_id(cpu, 0);
}
/*
* 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);
Reference in New Issue View Git Blame Copy Permalink