android_kernel_asus_sm8350/kernel/cpu.c
Greg Kroah-Hartman a9372c6b57 This is the 5.4.33 stable release
-----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAl6ZbdIACgkQONu9yGCS
 aT5Jqw/7BZ639nTAAmz809yOF1JBhvBptRg9tBKYAfw62DzfZe5s9IZA6znIt0f0
 nlluLvnhHlDSpgycHNkFry5AkiCUpRQW6NY681xITm918w3BxsKX2pfCawojIOSw
 YBaTWoWqNFQQWlC18L1CWJmIvIktSCHXBMTVDpnvRv7sw5A4Oe/zarzVDNb0A6OJ
 ThaR7LAKJrUEDDLuCOuB/IrYCOpOzg2SkViFmlo4wmmhvCSi8PXvf3royrSFXxM/
 Y1bs67Hu/uqeHl8Y2RaMZpXf1aW9F31sooca4GD+UnVoWppjIOKRyuGLTrXKv7pw
 /goIzlE8wfJz5K0iQ4UcbXwwdY81L9UlMdVsmIWHHgxMjSp1J5mfQ5TLUC/VK3UO
 Ll9tCYBwH4FjzxNRJq7if8TDAfgPzyhw4BMchgXZWzW1oasl51T2uEye3KgFXQSb
 u6TwCx4KGS0w/Q81SKis83Pb0unHGanJOSCZxI1B44raf0ruCBpTYUc713pfegWT
 46YtwoorAK8N+GpFQA1tsTJvVclqCF5bHVE19TMvXV4UX/VTPtbIAUE7vnvcxcqO
 uh0b9Jfmd6Fcgh7VZQCH7CUYnsyJmGqj2kycB1p+T8UB6H+PCeuQBZBl8sJnf8oj
 d5NIzB7WWXBQuEG5XuPtxg6+ARMPEIpd2exEVn9ZOv5qhesBo04=
 =pjAq
 -----END PGP SIGNATURE-----

Merge 5.4.33 into android-5.4-stable

Changes in 5.4.33
	ARM: dts: sun8i-a83t-tbs-a711: HM5065 doesn't like such a high voltage
	bus: sunxi-rsb: Return correct data when mixing 16-bit and 8-bit reads
	ARM: dts: Fix dm814x Ethernet by changing to use rgmii-id mode
	bpf: Fix deadlock with rq_lock in bpf_send_signal()
	iwlwifi: mvm: Fix rate scale NSS configuration
	Input: tm2-touchkey - add support for Coreriver TC360 variant
	soc: fsl: dpio: register dpio irq handlers after dpio create
	rxrpc: Abstract out the calculation of whether there's Tx space
	rxrpc: Fix call interruptibility handling
	net: stmmac: platform: Fix misleading interrupt error msg
	net: vxge: fix wrong __VA_ARGS__ usage
	hinic: fix a bug of waitting for IO stopped
	hinic: fix the bug of clearing event queue
	hinic: fix out-of-order excution in arm cpu
	hinic: fix wrong para of wait_for_completion_timeout
	hinic: fix wrong value of MIN_SKB_LEN
	selftests/net: add definition for SOL_DCCP to fix compilation errors for old libc
	cxgb4/ptp: pass the sign of offset delta in FW CMD
	drm/scheduler: fix rare NULL ptr race
	cfg80211: Do not warn on same channel at the end of CSA
	qlcnic: Fix bad kzalloc null test
	i2c: st: fix missing struct parameter description
	i2c: pca-platform: Use platform_irq_get_optional
	media: rc: add keymap for Videostrong KII Pro
	cpufreq: imx6q: Fixes unwanted cpu overclocking on i.MX6ULL
	staging: wilc1000: avoid double unlocking of 'wilc->hif_cs' mutex
	media: venus: hfi_parser: Ignore HEVC encoding for V1
	firmware: arm_sdei: fix double-lock on hibernate with shared events
	null_blk: Fix the null_add_dev() error path
	null_blk: Handle null_add_dev() failures properly
	null_blk: fix spurious IO errors after failed past-wp access
	media: imx: imx7_mipi_csis: Power off the source when stopping streaming
	media: imx: imx7-media-csi: Fix video field handling
	xhci: bail out early if driver can't accress host in resume
	ACPI: EC: Do not clear boot_ec_is_ecdt in acpi_ec_add()
	x86: Don't let pgprot_modify() change the page encryption bit
	dma-mapping: Fix dma_pgprot() for unencrypted coherent pages
	block: keep bdi->io_pages in sync with max_sectors_kb for stacked devices
	debugfs: Check module state before warning in {full/open}_proxy_open()
	irqchip/versatile-fpga: Handle chained IRQs properly
	time/sched_clock: Expire timer in hardirq context
	media: allegro: fix type of gop_length in channel_create message
	sched: Avoid scale real weight down to zero
	selftests/x86/ptrace_syscall_32: Fix no-vDSO segfault
	PCI/switchtec: Fix init_completion race condition with poll_wait()
	block, bfq: move forward the getting of an extra ref in bfq_bfqq_move
	media: i2c: video-i2c: fix build errors due to 'imply hwmon'
	libata: Remove extra scsi_host_put() in ata_scsi_add_hosts()
	pstore/platform: fix potential mem leak if pstore_init_fs failed
	gfs2: Do log_flush in gfs2_ail_empty_gl even if ail list is empty
	gfs2: Don't demote a glock until its revokes are written
	cpufreq: imx6q: fix error handling
	x86/boot: Use unsigned comparison for addresses
	efi/x86: Ignore the memory attributes table on i386
	genirq/irqdomain: Check pointer in irq_domain_alloc_irqs_hierarchy()
	block: Fix use-after-free issue accessing struct io_cq
	media: i2c: ov5695: Fix power on and off sequences
	usb: dwc3: core: add support for disabling SS instances in park mode
	irqchip/gic-v4: Provide irq_retrigger to avoid circular locking dependency
	md: check arrays is suspended in mddev_detach before call quiesce operations
	firmware: fix a double abort case with fw_load_sysfs_fallback
	spi: spi-fsl-dspi: Replace interruptible wait queue with a simple completion
	locking/lockdep: Avoid recursion in lockdep_count_{for,back}ward_deps()
	block, bfq: fix use-after-free in bfq_idle_slice_timer_body
	btrfs: qgroup: ensure qgroup_rescan_running is only set when the worker is at least queued
	btrfs: remove a BUG_ON() from merge_reloc_roots()
	btrfs: restart relocate_tree_blocks properly
	btrfs: track reloc roots based on their commit root bytenr
	ASoC: fix regwmask
	ASoC: dapm: connect virtual mux with default value
	ASoC: dpcm: allow start or stop during pause for backend
	ASoC: topology: use name_prefix for new kcontrol
	usb: gadget: f_fs: Fix use after free issue as part of queue failure
	usb: gadget: composite: Inform controller driver of self-powered
	ALSA: usb-audio: Add mixer workaround for TRX40 and co
	ALSA: hda: Add driver blacklist
	ALSA: hda: Fix potential access overflow in beep helper
	ALSA: ice1724: Fix invalid access for enumerated ctl items
	ALSA: pcm: oss: Fix regression by buffer overflow fix
	ALSA: hda/realtek: Enable mute LED on an HP system
	ALSA: hda/realtek - a fake key event is triggered by running shutup
	ALSA: doc: Document PC Beep Hidden Register on Realtek ALC256
	ALSA: hda/realtek - Set principled PC Beep configuration for ALC256
	ALSA: hda/realtek - Remove now-unnecessary XPS 13 headphone noise fixups
	ALSA: hda/realtek - Add quirk for Lenovo Carbon X1 8th gen
	ALSA: hda/realtek - Add quirk for MSI GL63
	media: venus: firmware: Ignore secure call error on first resume
	media: hantro: Read be32 words starting at every fourth byte
	media: ti-vpe: cal: fix disable_irqs to only the intended target
	media: ti-vpe: cal: fix a kernel oops when unloading module
	seccomp: Add missing compat_ioctl for notify
	acpi/x86: ignore unspecified bit positions in the ACPI global lock field
	ACPICA: Allow acpi_any_gpe_status_set() to skip one GPE
	ACPI: PM: s2idle: Refine active GPEs check
	thermal: devfreq_cooling: inline all stubs for CONFIG_DEVFREQ_THERMAL=n
	nvmet-tcp: fix maxh2cdata icresp parameter
	nvme-fc: Revert "add module to ops template to allow module references"
	efi/x86: Add TPM related EFI tables to unencrypted mapping checks
	PCI: pciehp: Fix indefinite wait on sysfs requests
	PCI/ASPM: Clear the correct bits when enabling L1 substates
	PCI: Add boot interrupt quirk mechanism for Xeon chipsets
	PCI: qcom: Fix the fixup of PCI_VENDOR_ID_QCOM
	PCI: endpoint: Fix for concurrent memory allocation in OB address region
	sched/fair: Fix enqueue_task_fair warning
	tpm: Don't make log failures fatal
	tpm: tpm1_bios_measurements_next should increase position index
	tpm: tpm2_bios_measurements_next should increase position index
	KEYS: reaching the keys quotas correctly
	cpu/hotplug: Ignore pm_wakeup_pending() for disable_nonboot_cpus()
	genirq/debugfs: Add missing sanity checks to interrupt injection
	irqchip/versatile-fpga: Apply clear-mask earlier
	io_uring: remove bogus RLIMIT_NOFILE check in file registration
	pstore: pstore_ftrace_seq_next should increase position index
	MIPS/tlbex: Fix LDDIR usage in setup_pw() for Loongson-3
	MIPS: OCTEON: irq: Fix potential NULL pointer dereference
	PM / Domains: Allow no domain-idle-states DT property in genpd when parsing
	PM: sleep: wakeup: Skip wakeup_source_sysfs_remove() if device is not there
	ath9k: Handle txpower changes even when TPC is disabled
	signal: Extend exec_id to 64bits
	x86/tsc_msr: Use named struct initializers
	x86/tsc_msr: Fix MSR_FSB_FREQ mask for Cherry Trail devices
	x86/tsc_msr: Make MSR derived TSC frequency more accurate
	x86/entry/32: Add missing ASM_CLAC to general_protection entry
	platform/x86: asus-wmi: Support laptops where the first battery is named BATT
	KVM: nVMX: Properly handle userspace interrupt window request
	KVM: s390: vsie: Fix region 1 ASCE sanity shadow address checks
	KVM: s390: vsie: Fix delivery of addressing exceptions
	KVM: x86: Allocate new rmap and large page tracking when moving memslot
	KVM: VMX: Always VMCLEAR in-use VMCSes during crash with kexec support
	KVM: x86: Gracefully handle __vmalloc() failure during VM allocation
	KVM: VMX: Add a trampoline to fix VMREAD error handling
	KVM: VMX: fix crash cleanup when KVM wasn't used
	smb3: fix performance regression with setting mtime
	CIFS: Fix bug which the return value by asynchronous read is error
	mtd: spinand: Stop using spinand->oobbuf for buffering bad block markers
	mtd: spinand: Do not erase the block before writing a bad block marker
	btrfs: Don't submit any btree write bio if the fs has errors
	Btrfs: fix crash during unmount due to race with delayed inode workers
	btrfs: reloc: clean dirty subvols if we fail to start a transaction
	btrfs: set update the uuid generation as soon as possible
	btrfs: drop block from cache on error in relocation
	btrfs: fix missing file extent item for hole after ranged fsync
	btrfs: unset reloc control if we fail to recover
	btrfs: fix missing semaphore unlock in btrfs_sync_file
	btrfs: use nofs allocations for running delayed items
	remoteproc: qcom_q6v5_mss: Don't reassign mpss region on shutdown
	remoteproc: qcom_q6v5_mss: Reload the mba region on coredump
	remoteproc: Fix NULL pointer dereference in rproc_virtio_notify
	crypto: rng - Fix a refcounting bug in crypto_rng_reset()
	crypto: mxs-dcp - fix scatterlist linearization for hash
	erofs: correct the remaining shrink objects
	io_uring: honor original task RLIMIT_FSIZE
	mmc: sdhci-of-esdhc: fix esdhc_reset() for different controller versions
	powerpc/pseries: Drop pointless static qualifier in vpa_debugfs_init()
	tools: gpio: Fix out-of-tree build regression
	net: qualcomm: rmnet: Allow configuration updates to existing devices
	arm64: dts: allwinner: h6: Fix PMU compatible
	sched/core: Remove duplicate assignment in sched_tick_remote()
	arm64: dts: allwinner: h5: Fix PMU compatible
	mm, memcg: do not high throttle allocators based on wraparound
	dm writecache: add cond_resched to avoid CPU hangs
	dm integrity: fix a crash with unusually large tag size
	dm verity fec: fix memory leak in verity_fec_dtr
	dm clone: Add overflow check for number of regions
	dm clone metadata: Fix return type of dm_clone_nr_of_hydrated_regions()
	XArray: Fix xas_pause for large multi-index entries
	xarray: Fix early termination of xas_for_each_marked
	crypto: caam/qi2 - fix chacha20 data size error
	crypto: caam - update xts sector size for large input length
	crypto: ccree - protect against empty or NULL scatterlists
	crypto: ccree - only try to map auth tag if needed
	crypto: ccree - dec auth tag size from cryptlen map
	scsi: zfcp: fix missing erp_lock in port recovery trigger for point-to-point
	scsi: ufs: fix Auto-Hibern8 error detection
	scsi: lpfc: Fix lpfc_io_buf resource leak in lpfc_get_scsi_buf_s4 error path
	ARM: dts: exynos: Fix polarity of the LCD SPI bus on UniversalC210 board
	arm64: dts: ti: k3-am65: Add clocks to dwc3 nodes
	arm64: armv8_deprecated: Fix undef_hook mask for thumb setend
	selftests: vm: drop dependencies on page flags from mlock2 tests
	selftests/vm: fix map_hugetlb length used for testing read and write
	selftests/powerpc: Add tlbie_test in .gitignore
	vfio: platform: Switch to platform_get_irq_optional()
	drm/i915/gem: Flush all the reloc_gpu batch
	drm/etnaviv: rework perfmon query infrastructure
	drm: Remove PageReserved manipulation from drm_pci_alloc
	drm/amdgpu/powerplay: using the FCLK DPM table to set the MCLK
	drm/amdgpu: unify fw_write_wait for new gfx9 asics
	powerpc/pseries: Avoid NULL pointer dereference when drmem is unavailable
	nfsd: fsnotify on rmdir under nfsd/clients/
	NFS: Fix use-after-free issues in nfs_pageio_add_request()
	NFS: Fix a page leak in nfs_destroy_unlinked_subrequests()
	ext4: fix a data race at inode->i_blocks
	fs/filesystems.c: downgrade user-reachable WARN_ONCE() to pr_warn_once()
	ocfs2: no need try to truncate file beyond i_size
	perf tools: Support Python 3.8+ in Makefile
	s390/diag: fix display of diagnose call statistics
	Input: i8042 - add Acer Aspire 5738z to nomux list
	ftrace/kprobe: Show the maxactive number on kprobe_events
	clk: ingenic/jz4770: Exit with error if CGU init failed
	clk: ingenic/TCU: Fix round_rate returning error
	kmod: make request_module() return an error when autoloading is disabled
	cpufreq: powernv: Fix use-after-free
	hfsplus: fix crash and filesystem corruption when deleting files
	libata: Return correct status in sata_pmp_eh_recover_pm() when ATA_DFLAG_DETACH is set
	ipmi: fix hung processes in __get_guid()
	xen/blkfront: fix memory allocation flags in blkfront_setup_indirect()
	powerpc/64/tm: Don't let userspace set regs->trap via sigreturn
	powerpc/fsl_booke: Avoid creating duplicate tlb1 entry
	powerpc/hash64/devmap: Use H_PAGE_THP_HUGE when setting up huge devmap PTE entries
	powerpc/xive: Use XIVE_BAD_IRQ instead of zero to catch non configured IPIs
	powerpc/64: Setup a paca before parsing device tree etc.
	powerpc/xive: Fix xmon support on the PowerNV platform
	powerpc/kprobes: Ignore traps that happened in real mode
	powerpc/64: Prevent stack protection in early boot
	scsi: mpt3sas: Fix kernel panic observed on soft HBA unplug
	powerpc: Make setjmp/longjmp signature standard
	arm64: Always force a branch protection mode when the compiler has one
	dm zoned: remove duplicate nr_rnd_zones increase in dmz_init_zone()
	dm clone: replace spin_lock_irqsave with spin_lock_irq
	dm clone: Fix handling of partial region discards
	dm clone: Add missing casts to prevent overflows and data corruption
	scsi: lpfc: Add registration for CPU Offline/Online events
	scsi: lpfc: Fix Fabric hostname registration if system hostname changes
	scsi: lpfc: Fix configuration of BB credit recovery in service parameters
	scsi: lpfc: Fix broken Credit Recovery after driver load
	Revert "drm/dp_mst: Remove VCPI while disabling topology mgr"
	drm/dp_mst: Fix clearing payload state on topology disable
	drm/amdgpu: fix gfx hang during suspend with video playback (v2)
	drm/i915/icl+: Don't enable DDI IO power on a TypeC port in TBT mode
	powerpc/kasan: Fix kasan_remap_early_shadow_ro()
	mmc: sdhci: Convert sdhci_set_timeout_irq() to non-static
	mmc: sdhci: Refactor sdhci_set_timeout()
	bpf: Fix tnum constraints for 32-bit comparisons
	mfd: dln2: Fix sanity checking for endpoints
	efi/x86: Fix the deletion of variables in mixed mode
	ASoC: stm32: sai: Add missing cleanup
	scsi: lpfc: fix inlining of lpfc_sli4_cleanup_poll_list()
	Linux 5.4.33

Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
Change-Id: I6c37e2c64801a572781c46fc5883bcc74e6a7a1a
2020-04-17 11:26:58 +02:00

2431 lines
58 KiB
C

/* CPU control.
* (C) 2001, 2002, 2003, 2004 Rusty Russell
*
* This code is licenced under the GPL.
*/
#include <linux/proc_fs.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/sched/signal.h>
#include <linux/sched/hotplug.h>
#include <linux/sched/isolation.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 <trace/events/power.h>
#define CREATE_TRACE_POINTS
#include <trace/events/cpuhp.h>
#include "smpboot.h"
/**
* cpuhp_cpu_state - Per cpu hotplug state storage
* @state: The current cpu state
* @target: The target state
* @thread: Pointer to the hotplug thread
* @should_run: Thread should execute
* @rollback: Perform a rollback
* @single: Single callback invocation
* @bringup: Single callback bringup or teardown selector
* @cb_state: The state for a single callback (install/uninstall)
* @result: Result of the operation
* @done_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;
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,
};
#ifdef CONFIG_SMP
cpumask_t cpus_booted_once_mask;
#endif
#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 inline void cpuhp_lock_acquire(bool bringup)
{
lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
}
static inline void cpuhp_lock_release(bool bringup)
{
lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map);
}
#else
static inline void cpuhp_lock_acquire(bool bringup) { }
static inline void 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
* @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 cant_stop;
bool multi_instance;
};
static DEFINE_MUTEX(cpuhp_state_mutex);
static struct cpuhp_step cpuhp_hp_states[];
static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
{
return cpuhp_hp_states + 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 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 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);
int cpus_read_trylock(void)
{
return percpu_down_read_trylock(&cpu_hotplug_lock);
}
EXPORT_SYMBOL_GPL(cpus_read_trylock);
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);
}
static void lockdep_acquire_cpus_lock(void)
{
rwsem_acquire(&cpu_hotplug_lock.rw_sem.dep_map, 0, 0, _THIS_IP_);
}
static void lockdep_release_cpus_lock(void)
{
rwsem_release(&cpu_hotplug_lock.rw_sem.dep_map, 1, _THIS_IP_);
}
/*
* 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);
#else
static void lockdep_acquire_cpus_lock(void)
{
}
static void lockdep_release_cpus_lock(void)
{
}
#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_possible())
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 !cpumask_test_cpu(cpu, &cpus_booted_once_mask);
}
/* Returns true if SMT is not supported of forcefully (irreversibly) disabled */
bool cpu_smt_possible(void)
{
return cpu_smt_control != CPU_SMT_FORCE_DISABLED &&
cpu_smt_control != CPU_SMT_NOT_SUPPORTED;
}
EXPORT_SYMBOL_GPL(cpu_smt_possible);
#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 notify_cpu_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--)
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();
/*
* The BP holds the hotplug lock, but we're now running on the AP,
* ensure that anybody asserting the lock is held, will actually find
* it so.
*/
lockdep_acquire_cpus_lock();
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 (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;
}
cpuhp_lock_release(bringup);
lockdep_release_cpus_lock();
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));
}
#ifdef CONFIG_HOTPLUG_CPU
/**
* 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;
cpumask_clear_cpu(cpu, mm_cpumask(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();
/* Remove CPU from timer broadcasting */
tick_offline_cpu(cpu);
/* 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 teardown callback for CPUHP_AP_SCHED_STARTING 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++)
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);
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;
if (num_online_cpus() == 1)
return -EBUSY;
if (!cpu_present(cpu))
return -EINVAL;
cpus_write_lock();
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:
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();
return ret;
}
static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
{
if (cpu_hotplug_disabled)
return -EBUSY;
return _cpu_down(cpu, 0, target);
}
static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
{
int err;
cpu_maps_update_begin();
err = cpu_down_maps_locked(cpu, target);
cpu_maps_update_done();
return err;
}
int cpu_down(unsigned int cpu)
{
return do_cpu_down(cpu, CPUHP_OFFLINE);
}
EXPORT_SYMBOL(cpu_down);
#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. */
cpumask_set_cpu(cpu, &cpus_booted_once_mask);
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;
cpus_write_lock();
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:
cpus_write_unlock();
arch_smt_update();
return ret;
}
static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
{
int 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;
}
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();
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, bool suspend)
{
int cpu, error = 0;
cpu_maps_update_begin();
if (primary == -1) {
primary = cpumask_first(cpu_online_mask);
if (!housekeeping_cpu(primary, HK_FLAG_TIMER))
primary = housekeeping_any_cpu(HK_FLAG_TIMER);
} else {
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 (suspend && 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_hp_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_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:prepare",
.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,
},
/* 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_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",
},
/*
* 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,
},
/* 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_init_cpu,
.teardown.single = perf_event_exit_cpu,
},
[CPUHP_AP_WATCHDOG_ONLINE] = {
.name = "lockup_detector:online",
.startup.single = lockup_detector_online_cpu,
.teardown.single = lockup_detector_offline_cpu,
},
[CPUHP_AP_WORKQUEUE_ONLINE] = {
.name = "workqueue:online",
.startup.single = workqueue_online_cpu,
.teardown.single = workqueue_offline_cpu,
},
[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_hp_states + CPUHP_AP_ONLINE_DYN;
end = CPUHP_AP_ONLINE_DYN_END;
break;
case CPUHP_BP_PREPARE_DYN:
step = cpuhp_hp_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);
#ifdef CONFIG_HOTPLUG_SMT
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;
}
#endif
#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 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;
}
#else /* !CONFIG_HOTPLUG_SMT */
static ssize_t
__store_smt_control(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
return -ENODEV;
}
#endif /* 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",
[CPU_SMT_NOT_IMPLEMENTED] = "notimplemented",
};
static ssize_t
show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
{
const char *state = smt_states[cpu_smt_control];
return snprintf(buf, PAGE_SIZE - 2, "%s\n", state);
}
static ssize_t
store_smt_control(struct device *dev, struct device_attribute *attr,
const char *buf, size_t count)
{
return __store_smt_control(dev, attr, buf, 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)
{
return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_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_sysfs_init(void)
{
return sysfs_create_group(&cpu_subsys.dev_root->kobj,
&cpuhp_smt_attr_group);
}
static int __init cpuhp_sysfs_init(void)
{
int cpu, ret;
ret = cpu_smt_sysfs_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 /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */
/*
* 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);
atomic_t __num_online_cpus __read_mostly;
EXPORT_SYMBOL(__num_online_cpus);
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 set_cpu_online(unsigned int cpu, bool online)
{
/*
* atomic_inc/dec() is required to handle the horrid abuse of this
* function by the reboot and kexec code which invoke it from
* IPI/NMI broadcasts when shutting down CPUs. Invocation from
* regular CPU hotplug is properly serialized.
*
* Note, that the fact that __num_online_cpus is of type atomic_t
* does not protect readers which are not serialized against
* concurrent hotplug operations.
*/
if (online) {
if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask))
atomic_inc(&__num_online_cpus);
} else {
if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask))
atomic_dec(&__num_online_cpus);
}
}
/*
* 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
}
/*
* Must be called _AFTER_ setting up the per_cpu areas
*/
void __init boot_cpu_hotplug_init(void)
{
#ifdef CONFIG_SMP
cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask);
#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);