Files
kernel_xiaomi_sm8250/drivers/cpuidle/cpuidle.c
Michael Bestas 9cd6ae99b7 Merge tag 'ASB-2023-11-05_4.19-stable' of https://android.googlesource.com/kernel/common into android13-4.19-kona
https://source.android.com/docs/security/bulletin/2023-11-01

* tag 'ASB-2023-11-05_4.19-stable' of https://android.googlesource.com/kernel/common:
  Reapply "perf: Disallow mis-matched inherited group reads"
  Revert "perf: Disallow mis-matched inherited group reads"
  Revert "xfrm: fix a data-race in xfrm_gen_index()"
  Revert "Bluetooth: hci_core: Fix build warnings"
  Revert "xfrm: interface: use DEV_STATS_INC()"
  Linux 4.19.297
  xfrm6: fix inet6_dev refcount underflow problem
  Bluetooth: hci_sock: Correctly bounds check and pad HCI_MON_NEW_INDEX name
  Bluetooth: hci_sock: fix slab oob read in create_monitor_event
  phy: mapphone-mdm6600: Fix runtime PM for remove
  ASoC: pxa: fix a memory leak in probe()
  gpio: vf610: set value before the direction to avoid a glitch
  s390/pci: fix iommu bitmap allocation
  perf: Disallow mis-matched inherited group reads
  USB: serial: option: add Fibocom to DELL custom modem FM101R-GL
  USB: serial: option: add entry for Sierra EM9191 with new firmware
  USB: serial: option: add Telit LE910C4-WWX 0x1035 composition
  ACPI: irq: Fix incorrect return value in acpi_register_gsi()
  Revert "pinctrl: avoid unsafe code pattern in find_pinctrl()"
  mmc: core: Capture correct oemid-bits for eMMC cards
  mtd: spinand: micron: correct bitmask for ecc status
  mtd: rawnand: qcom: Unmap the right resource upon probe failure
  Bluetooth: hci_event: Fix using memcmp when comparing keys
  btrfs: fix some -Wmaybe-uninitialized warnings in ioctl.c
  drm: panel-orientation-quirks: Add quirk for One Mix 2S
  sky2: Make sure there is at least one frag_addr available
  wifi: cfg80211: avoid leaking stack data into trace
  wifi: mac80211: allow transmitting EAPOL frames with tainted key
  Bluetooth: hci_core: Fix build warnings
  Bluetooth: Avoid redundant authentication
  HID: holtek: fix slab-out-of-bounds Write in holtek_kbd_input_event
  tracing: relax trace_event_eval_update() execution with cond_resched()
  ata: libata-eh: Fix compilation warning in ata_eh_link_report()
  gpio: timberdale: Fix potential deadlock on &tgpio->lock
  overlayfs: set ctime when setting mtime and atime
  i2c: mux: Avoid potential false error message in i2c_mux_add_adapter
  btrfs: initialize start_slot in btrfs_log_prealloc_extents
  btrfs: return -EUCLEAN for delayed tree ref with a ref count not equals to 1
  ARM: dts: ti: omap: Fix noisy serial with overrun-throttle-ms for mapphone
  libceph: use kernel_connect()
  libceph: fix unaligned accesses in ceph_entity_addr handling
  net: pktgen: Fix interface flags printing
  netfilter: nft_set_rbtree: .deactivate fails if element has expired
  net/sched: sch_hfsc: upgrade 'rt' to 'sc' when it becomes a inner curve
  i40e: prevent crash on probe if hw registers have invalid values
  net: usb: smsc95xx: Fix an error code in smsc95xx_reset()
  tcp: tsq: relax tcp_small_queue_check() when rtx queue contains a single skb
  tcp: fix excessive TLP and RACK timeouts from HZ rounding
  net: rfkill: gpio: prevent value glitch during probe
  net: ipv6: fix return value check in esp_remove_trailer
  net: ipv4: fix return value check in esp_remove_trailer
  xfrm: interface: use DEV_STATS_INC()
  xfrm: fix a data-race in xfrm_gen_index()
  netfilter: nft_payload: fix wrong mac header matching
  KVM: x86: Mask LVTPC when handling a PMI
  regmap: fix NULL deref on lookup
  nfc: nci: fix possible NULL pointer dereference in send_acknowledge()
  Bluetooth: avoid memcmp() out of bounds warning
  Bluetooth: hci_event: Fix coding style
  Bluetooth: vhci: Fix race when opening vhci device
  Bluetooth: Fix a refcnt underflow problem for hci_conn
  Bluetooth: Reject connection with the device which has same BD_ADDR
  Bluetooth: hci_event: Ignore NULL link key
  usb: hub: Guard against accesses to uninitialized BOS descriptors
  dev_forward_skb: do not scrub skb mark within the same name space
  x86/alternatives: Disable KASAN in apply_alternatives()
  powerpc/64e: Fix wrong test in __ptep_test_and_clear_young()
  usb: gadget: ncm: Handle decoding of multiple NTB's in unwrap call
  usb: gadget: udc-xilinx: replace memcpy with memcpy_toio
  x86/cpu: Fix AMD erratum #1485 on Zen4-based CPUs
  pinctrl: avoid unsafe code pattern in find_pinctrl()
  cgroup: Remove duplicates in cgroup v1 tasks file
  Input: xpad - add PXN V900 support
  Input: psmouse - fix fast_reconnect function for PS/2 mode
  Input: powermate - fix use-after-free in powermate_config_complete
  ceph: fix incorrect revoked caps assert in ceph_fill_file_size()
  mcb: remove is_added flag from mcb_device struct
  iio: pressure: ms5611: ms5611_prom_is_valid false negative bug
  iio: pressure: bmp280: Fix NULL pointer exception
  usb: musb: Modify the "HWVers" register address
  usb: musb: Get the musb_qh poniter after musb_giveback
  usb: dwc3: Soft reset phy on probe for host
  net: usb: dm9601: fix uninitialized variable use in dm9601_mdio_read
  usb: xhci: xhci-ring: Use sysdev for mapping bounce buffer
  dmaengine: stm32-mdma: abort resume if no ongoing transfer
  sched,idle,rcu: Push rcu_idle deeper into the idle path
  workqueue: Override implicit ordered attribute in workqueue_apply_unbound_cpumask()
  nfc: nci: assert requested protocol is valid
  net: nfc: fix races in nfc_llcp_sock_get() and nfc_llcp_sock_get_sn()
  ixgbe: fix crash with empty VF macvlan list
  drm/vmwgfx: fix typo of sizeof argument
  xen-netback: use default TX queue size for vifs
  ieee802154: ca8210: Fix a potential UAF in ca8210_probe
  drm/msm/dsi: skip the wait for video mode done if not applicable
  drm: etvnaviv: fix bad backport leading to warning
  net: prevent address rewrite in kernel_bind()
  quota: Fix slow quotaoff
  HID: logitech-hidpp: Fix kernel crash on receiver USB disconnect
  RDMA/cxgb4: Check skb value for failure to allocate
  net: prevent rewrite of msg_name in sock_sendmsg()
  net: fix kernel-doc warnings for socket.c
  net: use indirect calls helpers at the socket layer
  indirect call wrappers: helpers to speed-up indirect calls of builtin
  Revert "net: add atomic_long_t to net_device_stats fields"
  Revert "net: Fix unwanted sign extension in netdev_stats_to_stats64()"
  Revert "net: bridge: use DEV_STATS_INC()"
  Linux 4.19.296
  xen/events: replace evtchn_rwlock with RCU
  rtnetlink: Reject negative ifindexes in RTM_NEWLINK
  Revert "rtnetlink: Reject negative ifindexes in RTM_NEWLINK"
  dccp: fix dccp_v4_err()/dccp_v6_err() again
  parisc: Restore __ldcw_align for PA-RISC 2.0 processors
  RDMA/mlx5: Fix NULL string error
  RDMA/cma: Fix truncation compilation warning in make_cma_ports
  gpio: pxa: disable pinctrl calls for MMP_GPIO
  gpio: aspeed: fix the GPIO number passed to pinctrl_gpio_set_config()
  IB/mlx4: Fix the size of a buffer in add_port_entries()
  cpupower: add Makefile dependencies for install targets
  sctp: update hb timer immediately after users change hb_interval
  sctp: update transport state when processing a dupcook packet
  tcp: fix delayed ACKs for MSS boundary condition
  tcp: fix quick-ack counting to count actual ACKs of new data
  net: stmmac: dwmac-stm32: fix resume on STM32 MCU
  net: usb: smsc75xx: Fix uninit-value access in __smsc75xx_read_reg
  ipv4, ipv6: Fix handling of transhdrlen in __ip{,6}_append_data()
  modpost: add missing else to the "of" check
  scsi: target: core: Fix deadlock due to recursive locking
  regmap: rbtree: Fix wrong register marked as in-cache when creating new node
  drivers/net: process the result of hdlc_open() and add call of hdlc_close() in uhdlc_close()
  wifi: mwifiex: Fix oob check condition in mwifiex_process_rx_packet
  ubi: Refuse attaching if mtd's erasesize is 0
  net: replace calls to sock->ops->connect() with kernel_connect()
  wifi: mwifiex: Fix tlv_buf_left calculation
  qed/red_ll2: Fix undefined behavior bug in struct qed_ll2_info
  scsi: zfcp: Fix a double put in zfcp_port_enqueue()
  Revert "PCI: qcom: Disable write access to read only registers for IP v2.3.3"
  media: dvb: symbol fixup for dvb_attach() - again
  Revert "drivers core: Use sysfs_emit and sysfs_emit_at for show(device *...) functions"
  ata: libata: disallow dev-initiated LPM transitions to unsupported states
  ext4: fix rec_len verify error
  fs: binfmt_elf_efpic: fix personality for ELF-FDPIC
  ata: libata-sata: increase PMP SRST timeout to 10s
  ata: libata-core: Do not register PM operations for SAS ports
  ata: libata-core: Fix port and device removal
  ata: libata-core: Fix ata_port_request_pm() locking
  net: thunderbolt: Fix TCPv6 GSO checksum calculation
  btrfs: properly report 0 avail for very full file systems
  i2c: i801: unregister tco_pdev in i801_probe() error path
  ata: libata-scsi: ignore reserved bits for REPORT SUPPORTED OPERATION CODES
  ALSA: hda: Disable power save for solving pop issue on Lenovo ThinkCentre M70q
  nilfs2: fix potential use after free in nilfs_gccache_submit_read_data()
  serial: 8250_port: Check IRQ data before use
  smack: Record transmuting in smk_transmuted
  smack: Retrieve transmuting information in smack_inode_getsecurity()
  Smack:- Use overlay inode label in smack_inode_copy_up()
  scsi: megaraid_sas: Enable msix_load_balance for Invader and later controllers
  net: Fix unwanted sign extension in netdev_stats_to_stats64()
  watchdog: iTCO_wdt: Set NO_REBOOT if the watchdog is not already running
  watchdog: iTCO_wdt: No need to stop the timer in probe
  nvme-pci: do not set the NUMA node of device if it has none
  fbdev/sh7760fb: Depend on FB=y
  bpf: Clarify error expectations from bpf_clone_redirect
  ata: libata-eh: do not clear ATA_PFLAG_EH_PENDING in ata_eh_reset()
  ring-buffer: Avoid softlockup in ring_buffer_resize()
  selftests/ftrace: Correctly enable event in instance-event.tc
  parisc: irq: Make irq_stack_union static to avoid sparse warning
  parisc: drivers: Fix sparse warning
  parisc: iosapic.c: Fix sparse warnings
  parisc: sba: Fix compile warning wrt list of SBA devices
  gpio: pmic-eic-sprd: Add can_sleep flag for PMIC EIC chip
  ARM: dts: ti: omap: motorola-mapphone: Fix abe_clkctrl warning on boot
  clk: tegra: fix error return case for recalc_rate
  MIPS: Alchemy: only build mmc support helpers if au1xmmc is enabled
  ext4: do not let fstrim block system suspend
  ext4: move setting of trimmed bit into ext4_try_to_trim_range()
  ext4: replace the traditional ternary conditional operator with with max()/min()
  ext4: mark group as trimmed only if it was fully scanned
  ext4: change s_last_trim_minblks type to unsigned long
  ext4: scope ret locally in ext4_try_to_trim_range()
  ext4: add new helper interface ext4_try_to_trim_range()
  ext4: remove the 'group' parameter of ext4_trim_extent
  scsi: megaraid_sas: Fix deadlock on firmware crashdump
  scsi: megaraid_sas: Load balance completions across all MSI-X
  scsi: qla2xxx: Remove unsupported ql2xenabledif option
  scsi: qla2xxx: Add protection mask module parameters
  Input: i8042 - add quirk for TUXEDO Gemini 17 Gen1/Clevo PD70PN
  i2c: mux: demux-pinctrl: check the return value of devm_kstrdup()
  gpio: tb10x: Fix an error handling path in tb10x_gpio_probe()
  team: fix null-ptr-deref when team device type is changed
  net: bridge: use DEV_STATS_INC()
  net: add atomic_long_t to net_device_stats fields
  net: hns3: add 5ms delay before clear firmware reset irq source
  powerpc/perf/hv-24x7: Update domain value check
  ipv4: fix null-deref in ipv4_link_failure
  selftests: tls: swap the TX and RX sockets in some tests
  selftests/tls: Add {} to avoid static checker warning
  netfilter: nf_tables: disallow element removal on anonymous sets
  ata: libahci: clear pending interrupt status
  ata: ahci: Drop pointless VPRINTK() calls and convert the remaining ones
  NFS/pNFS: Report EINVAL errors from connect() to the server
  ANDROID: ALSA: jack: Revert mismerge done in v4.19.291

 Conflicts:
	include/net/tcp.h
	kernel/events/core.c
	kernel/sched/idle.c

Change-Id: I141cc494dcfda5fbd11f8bd2f7166bf3bf157084
2023-11-09 14:55:01 +02:00

733 lines
17 KiB
C

/*
* cpuidle.c - core cpuidle infrastructure
*
* (C) 2006-2007 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
* Shaohua Li <shaohua.li@intel.com>
* Adam Belay <abelay@novell.com>
*
* This code is licenced under the GPL.
*/
#include <linux/clockchips.h>
#include <linux/kernel.h>
#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/sched/clock.h>
#include <linux/sched/idle.h>
#include <linux/notifier.h>
#include <linux/pm_qos.h>
#include <linux/cpu.h>
#include <linux/cpuidle.h>
#include <linux/ktime.h>
#include <linux/hrtimer.h>
#include <linux/module.h>
#include <linux/suspend.h>
#include <linux/tick.h>
#include <trace/events/power.h>
#include "cpuidle.h"
DEFINE_PER_CPU(struct cpuidle_device *, cpuidle_devices);
DEFINE_PER_CPU(struct cpuidle_device, cpuidle_dev);
EXPORT_SYMBOL_GPL(cpuidle_dev);
DEFINE_MUTEX(cpuidle_lock);
LIST_HEAD(cpuidle_detected_devices);
static int enabled_devices;
static int off __read_mostly;
static int initialized __read_mostly;
int cpuidle_disabled(void)
{
return off;
}
void disable_cpuidle(void)
{
off = 1;
}
bool cpuidle_not_available(struct cpuidle_driver *drv,
struct cpuidle_device *dev)
{
return off || !initialized || !drv || !dev || !dev->enabled;
}
/**
* cpuidle_play_dead - cpu off-lining
*
* Returns in case of an error or no driver
*/
int cpuidle_play_dead(void)
{
struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
int i;
if (!drv)
return -ENODEV;
/* Find lowest-power state that supports long-term idle */
for (i = drv->state_count - 1; i >= 0; i--)
if (drv->states[i].enter_dead)
return drv->states[i].enter_dead(dev, i);
return -ENODEV;
}
static int find_deepest_state(struct cpuidle_driver *drv,
struct cpuidle_device *dev,
unsigned int max_latency,
unsigned int forbidden_flags,
bool s2idle)
{
unsigned int latency_req = 0;
int i, ret = 0;
for (i = 1; i < drv->state_count; i++) {
struct cpuidle_state *s = &drv->states[i];
struct cpuidle_state_usage *su = &dev->states_usage[i];
if (s->disabled || su->disable || s->exit_latency <= latency_req
|| s->exit_latency > max_latency
|| (s->flags & forbidden_flags)
|| (s2idle && !s->enter_s2idle))
continue;
latency_req = s->exit_latency;
ret = i;
}
return ret;
}
/**
* cpuidle_use_deepest_state - Set/clear governor override flag.
* @enable: New value of the flag.
*
* Set/unset the current CPU to use the deepest idle state (override governors
* going forward if set).
*/
void cpuidle_use_deepest_state(bool enable)
{
struct cpuidle_device *dev;
preempt_disable();
dev = cpuidle_get_device();
if (dev)
dev->use_deepest_state = enable;
preempt_enable();
}
/**
* cpuidle_find_deepest_state - Find the deepest available idle state.
* @drv: cpuidle driver for the given CPU.
* @dev: cpuidle device for the given CPU.
*/
int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
struct cpuidle_device *dev)
{
return find_deepest_state(drv, dev, UINT_MAX, 0, false);
}
#ifdef CONFIG_SUSPEND
static void enter_s2idle_proper(struct cpuidle_driver *drv,
struct cpuidle_device *dev, int index)
{
ktime_t time_start, time_end;
time_start = ns_to_ktime(local_clock());
/*
* trace_suspend_resume() called by tick_freeze() for the last CPU
* executing it contains RCU usage regarded as invalid in the idle
* context, so tell RCU about that.
*/
tick_freeze();
/*
* The state used here cannot be a "coupled" one, because the "coupled"
* cpuidle mechanism enables interrupts and doing that with timekeeping
* suspended is generally unsafe.
*/
stop_critical_timings();
rcu_idle_enter();
drv->states[index].enter_s2idle(dev, drv, index);
if (WARN_ON_ONCE(!irqs_disabled()))
local_irq_disable();
/*
* timekeeping_resume() that will be called by tick_unfreeze() for the
* first CPU executing it calls functions containing RCU read-side
* critical sections, so tell RCU about that.
*/
rcu_idle_exit();
tick_unfreeze();
start_critical_timings();
time_end = ns_to_ktime(local_clock());
dev->states_usage[index].s2idle_time += ktime_us_delta(time_end, time_start);
dev->states_usage[index].s2idle_usage++;
}
/**
* cpuidle_enter_s2idle - Enter an idle state suitable for suspend-to-idle.
* @drv: cpuidle driver for the given CPU.
* @dev: cpuidle device for the given CPU.
*
* If there are states with the ->enter_s2idle callback, find the deepest of
* them and enter it with frozen tick.
*/
int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev)
{
int index;
/*
* Find the deepest state with ->enter_s2idle present, which guarantees
* that interrupts won't be enabled when it exits and allows the tick to
* be frozen safely.
*/
index = find_deepest_state(drv, dev, UINT_MAX, 0, true);
if (index > 0)
enter_s2idle_proper(drv, dev, index);
return index;
}
#endif /* CONFIG_SUSPEND */
/**
* cpuidle_enter_state - enter the state and update stats
* @dev: cpuidle device for this cpu
* @drv: cpuidle driver for this cpu
* @index: index into the states table in @drv of the state to enter
*/
int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
int index)
{
int entered_state;
struct cpuidle_state *target_state = &drv->states[index];
bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP);
ktime_t time_start, time_end;
s64 diff;
/*
* Tell the time framework to switch to a broadcast timer because our
* local timer will be shut down. If a local timer is used from another
* CPU as a broadcast timer, this call may fail if it is not available.
*/
if (broadcast && tick_broadcast_enter()) {
index = find_deepest_state(drv, dev, target_state->exit_latency,
CPUIDLE_FLAG_TIMER_STOP, false);
if (index < 0) {
default_idle_call();
return -EBUSY;
}
target_state = &drv->states[index];
broadcast = false;
}
/* Take note of the planned idle state. */
sched_idle_set_state(target_state, index);
trace_cpu_idle(index, dev->cpu);
time_start = ns_to_ktime(local_clock());
stop_critical_timings();
rcu_idle_enter();
entered_state = target_state->enter(dev, drv, index);
rcu_idle_exit();
start_critical_timings();
sched_clock_idle_wakeup_event();
time_end = ns_to_ktime(local_clock());
trace_cpu_idle(PWR_EVENT_EXIT, dev->cpu);
/* The cpu is no longer idle or about to enter idle. */
sched_idle_set_state(NULL, -1);
if (broadcast) {
if (WARN_ON_ONCE(!irqs_disabled()))
local_irq_disable();
tick_broadcast_exit();
}
if (!cpuidle_state_is_coupled(drv, index))
local_irq_enable();
diff = ktime_us_delta(time_end, time_start);
if (diff > INT_MAX)
diff = INT_MAX;
dev->last_residency = (int) diff;
if (entered_state >= 0) {
/* Update cpuidle counters */
/* This can be moved to within driver enter routine
* but that results in multiple copies of same code.
*/
dev->states_usage[entered_state].time += dev->last_residency;
dev->states_usage[entered_state].usage++;
} else {
dev->last_residency = 0;
}
return entered_state;
}
/**
* cpuidle_select - ask the cpuidle framework to choose an idle state
*
* @drv: the cpuidle driver
* @dev: the cpuidle device
* @stop_tick: indication on whether or not to stop the tick
*
* Returns the index of the idle state. The return value must not be negative.
*
* The memory location pointed to by @stop_tick is expected to be written the
* 'false' boolean value if the scheduler tick should not be stopped before
* entering the returned state.
*/
int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
bool *stop_tick)
{
return cpuidle_curr_governor->select(drv, dev, stop_tick);
}
/**
* cpuidle_enter - enter into the specified idle state
*
* @drv: the cpuidle driver tied with the cpu
* @dev: the cpuidle device
* @index: the index in the idle state table
*
* Returns the index in the idle state, < 0 in case of error.
* The error code depends on the backend driver
*/
int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev,
int index)
{
if (cpuidle_state_is_coupled(drv, index))
return cpuidle_enter_state_coupled(dev, drv, index);
return cpuidle_enter_state(dev, drv, index);
}
/**
* cpuidle_reflect - tell the underlying governor what was the state
* we were in
*
* @dev : the cpuidle device
* @index: the index in the idle state table
*
*/
void cpuidle_reflect(struct cpuidle_device *dev, int index)
{
if (cpuidle_curr_governor->reflect && index >= 0)
cpuidle_curr_governor->reflect(dev, index);
}
/**
* cpuidle_install_idle_handler - installs the cpuidle idle loop handler
*/
void cpuidle_install_idle_handler(void)
{
if (enabled_devices) {
/* Make sure all changes finished before we switch to new idle */
smp_wmb();
initialized = 1;
}
}
/**
* cpuidle_uninstall_idle_handler - uninstalls the cpuidle idle loop handler
*/
void cpuidle_uninstall_idle_handler(void)
{
if (enabled_devices) {
initialized = 0;
wake_up_all_idle_cpus();
}
/*
* Make sure external observers (such as the scheduler)
* are done looking at pointed idle states.
*/
synchronize_rcu();
}
/**
* cpuidle_pause_and_lock - temporarily disables CPUIDLE
*/
void cpuidle_pause_and_lock(void)
{
mutex_lock(&cpuidle_lock);
cpuidle_uninstall_idle_handler();
}
EXPORT_SYMBOL_GPL(cpuidle_pause_and_lock);
/**
* cpuidle_resume_and_unlock - resumes CPUIDLE operation
*/
void cpuidle_resume_and_unlock(void)
{
cpuidle_install_idle_handler();
mutex_unlock(&cpuidle_lock);
}
EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock);
/* Currently used in suspend/resume path to suspend cpuidle */
void cpuidle_pause(void)
{
mutex_lock(&cpuidle_lock);
cpuidle_uninstall_idle_handler();
mutex_unlock(&cpuidle_lock);
}
/* Currently used in suspend/resume path to resume cpuidle */
void cpuidle_resume(void)
{
mutex_lock(&cpuidle_lock);
cpuidle_install_idle_handler();
mutex_unlock(&cpuidle_lock);
}
/**
* cpuidle_enable_device - enables idle PM for a CPU
* @dev: the CPU
*
* This function must be called between cpuidle_pause_and_lock and
* cpuidle_resume_and_unlock when used externally.
*/
int cpuidle_enable_device(struct cpuidle_device *dev)
{
int ret;
struct cpuidle_driver *drv;
if (!dev)
return -EINVAL;
if (dev->enabled)
return 0;
if (!cpuidle_curr_governor)
return -EIO;
drv = cpuidle_get_cpu_driver(dev);
if (!drv)
return -EIO;
if (!dev->registered)
return -EINVAL;
ret = cpuidle_add_device_sysfs(dev);
if (ret)
return ret;
if (cpuidle_curr_governor->enable) {
ret = cpuidle_curr_governor->enable(drv, dev);
if (ret)
goto fail_sysfs;
}
smp_wmb();
dev->enabled = 1;
enabled_devices++;
return 0;
fail_sysfs:
cpuidle_remove_device_sysfs(dev);
return ret;
}
EXPORT_SYMBOL_GPL(cpuidle_enable_device);
/**
* cpuidle_disable_device - disables idle PM for a CPU
* @dev: the CPU
*
* This function must be called between cpuidle_pause_and_lock and
* cpuidle_resume_and_unlock when used externally.
*/
void cpuidle_disable_device(struct cpuidle_device *dev)
{
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
if (!dev || !dev->enabled)
return;
if (!drv || !cpuidle_curr_governor)
return;
dev->enabled = 0;
if (cpuidle_curr_governor->disable)
cpuidle_curr_governor->disable(drv, dev);
cpuidle_remove_device_sysfs(dev);
enabled_devices--;
}
EXPORT_SYMBOL_GPL(cpuidle_disable_device);
static void __cpuidle_unregister_device(struct cpuidle_device *dev)
{
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
list_del(&dev->device_list);
per_cpu(cpuidle_devices, dev->cpu) = NULL;
module_put(drv->owner);
dev->registered = 0;
}
static void __cpuidle_device_init(struct cpuidle_device *dev)
{
memset(dev->states_usage, 0, sizeof(dev->states_usage));
dev->last_residency = 0;
}
/**
* __cpuidle_register_device - internal register function called before register
* and enable routines
* @dev: the cpu
*
* cpuidle_lock mutex must be held before this is called
*/
static int __cpuidle_register_device(struct cpuidle_device *dev)
{
int ret;
struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
if (!try_module_get(drv->owner))
return -EINVAL;
per_cpu(cpuidle_devices, dev->cpu) = dev;
list_add(&dev->device_list, &cpuidle_detected_devices);
ret = cpuidle_coupled_register_device(dev);
if (ret)
__cpuidle_unregister_device(dev);
else
dev->registered = 1;
return ret;
}
/**
* cpuidle_register_device - registers a CPU's idle PM feature
* @dev: the cpu
*/
int cpuidle_register_device(struct cpuidle_device *dev)
{
int ret = -EBUSY;
if (!dev)
return -EINVAL;
mutex_lock(&cpuidle_lock);
if (dev->registered)
goto out_unlock;
__cpuidle_device_init(dev);
ret = __cpuidle_register_device(dev);
if (ret)
goto out_unlock;
ret = cpuidle_add_sysfs(dev);
if (ret)
goto out_unregister;
ret = cpuidle_enable_device(dev);
if (ret)
goto out_sysfs;
cpuidle_install_idle_handler();
out_unlock:
mutex_unlock(&cpuidle_lock);
return ret;
out_sysfs:
cpuidle_remove_sysfs(dev);
out_unregister:
__cpuidle_unregister_device(dev);
goto out_unlock;
}
EXPORT_SYMBOL_GPL(cpuidle_register_device);
/**
* cpuidle_unregister_device - unregisters a CPU's idle PM feature
* @dev: the cpu
*/
void cpuidle_unregister_device(struct cpuidle_device *dev)
{
if (!dev || dev->registered == 0)
return;
cpuidle_pause_and_lock();
cpuidle_disable_device(dev);
cpuidle_remove_sysfs(dev);
__cpuidle_unregister_device(dev);
cpuidle_coupled_unregister_device(dev);
cpuidle_resume_and_unlock();
}
EXPORT_SYMBOL_GPL(cpuidle_unregister_device);
/**
* cpuidle_unregister: unregister a driver and the devices. This function
* can be used only if the driver has been previously registered through
* the cpuidle_register function.
*
* @drv: a valid pointer to a struct cpuidle_driver
*/
void cpuidle_unregister(struct cpuidle_driver *drv)
{
int cpu;
struct cpuidle_device *device;
for_each_cpu(cpu, drv->cpumask) {
device = &per_cpu(cpuidle_dev, cpu);
cpuidle_unregister_device(device);
}
cpuidle_unregister_driver(drv);
}
EXPORT_SYMBOL_GPL(cpuidle_unregister);
/**
* cpuidle_register: registers the driver and the cpu devices with the
* coupled_cpus passed as parameter. This function is used for all common
* initialization pattern there are in the arch specific drivers. The
* devices is globally defined in this file.
*
* @drv : a valid pointer to a struct cpuidle_driver
* @coupled_cpus: a cpumask for the coupled states
*
* Returns 0 on success, < 0 otherwise
*/
int cpuidle_register(struct cpuidle_driver *drv,
const struct cpumask *const coupled_cpus)
{
int ret, cpu;
struct cpuidle_device *device;
ret = cpuidle_register_driver(drv);
if (ret) {
pr_err("failed to register cpuidle driver\n");
return ret;
}
for_each_cpu(cpu, drv->cpumask) {
device = &per_cpu(cpuidle_dev, cpu);
device->cpu = cpu;
#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
/*
* On multiplatform for ARM, the coupled idle states could be
* enabled in the kernel even if the cpuidle driver does not
* use it. Note, coupled_cpus is a struct copy.
*/
if (coupled_cpus)
device->coupled_cpus = *coupled_cpus;
#endif
ret = cpuidle_register_device(device);
if (!ret)
continue;
pr_err("Failed to register cpuidle device for cpu%d\n", cpu);
cpuidle_unregister(drv);
break;
}
return ret;
}
EXPORT_SYMBOL_GPL(cpuidle_register);
#ifdef CONFIG_SMP
static void wake_up_idle_cpus(void *v)
{
int cpu;
struct cpumask cpus;
preempt_disable();
if (v) {
cpumask_andnot(&cpus, v, cpu_isolated_mask);
cpumask_and(&cpus, &cpus, cpu_online_mask);
} else
cpumask_andnot(&cpus, cpu_online_mask, cpu_isolated_mask);
for_each_cpu(cpu, &cpus) {
if (cpu == smp_processor_id())
continue;
wake_up_if_idle(cpu);
}
preempt_enable();
}
/*
* This function gets called when a part of the kernel has a new latency
* requirement. This means we need to get only those processors out of their
* C-state for which qos requirement is changed, and then recalculate a new
* suitable C-state. Just do a cross-cpu IPI; that wakes them all right up.
*/
static int cpuidle_latency_notify(struct notifier_block *b,
unsigned long l, void *v)
{
wake_up_idle_cpus(v);
return NOTIFY_OK;
}
static struct notifier_block cpuidle_latency_notifier = {
.notifier_call = cpuidle_latency_notify,
};
static inline void latency_notifier_init(struct notifier_block *n)
{
pm_qos_add_notifier(PM_QOS_CPU_DMA_LATENCY, n);
}
#else /* CONFIG_SMP */
#define latency_notifier_init(x) do { } while (0)
#endif /* CONFIG_SMP */
/**
* cpuidle_init - core initializer
*/
static int __init cpuidle_init(void)
{
int ret;
if (cpuidle_disabled())
return -ENODEV;
ret = cpuidle_add_interface(cpu_subsys.dev_root);
if (ret)
return ret;
latency_notifier_init(&cpuidle_latency_notifier);
return 0;
}
module_param(off, int, 0444);
core_initcall(cpuidle_init);