-----BEGIN PGP SIGNATURE-----
iQIzBAABCAAdFiEEZH8oZUiU471FcZm+ONu9yGCSaT4FAmSb+ZMACgkQONu9yGCS
aT7qORAAmbYIAtIdWp+3wAM8g9TihQAeknz6f7Q8sxUB1EkZKJ9TgnFdR1IPPcBI
BWMUNutyUtHY90XTlZbVM04P070FafWjyT23+sdNG+pZGv+sOJkTHO6NgvkFlt0m
doOq9ojOe6hXS5oqK+8grfbwBG0VDUv7HHuUKsGBLhlDAHP58sVqtkrpiK2EiJpx
WGIR1t7gPd7jIxsnWTSurdjGfrAUw3SmE07K6sjwGgHsc2Mvd5vluQ+ljnmlz2qd
3WMyHymIhNP69/HY5Zz6sqCNGJ0eglp6IP8VPw9a7eGDu1UNp2Gu+P5ZB4FR7ABg
Rbsvrkr/08S9on0OSFiYJ11sfbzdIb4AfGdSHnUpeuqBp5ak1JS5jE6eSiy9YZU/
V9wDFdlDDwwORCWTMJzcTvhtlzWI+BkKq0bZEiYSxeCZ6m5RKi0i6X/lOPFt/ihA
PfEHGZVZ12atEEnYm5iich8Frqyp3nOYJKR972/zeKkkcWoYslFA6KuA3PA3eV7S
rdbz3hK6T3kZTe7FUvmghdi1lGgIKYy8IOiqY9tbMHWa3YQ7k5ZA2BZOiCEri0RF
tfzT1wI4DknbEXv5fs5PQ8c8eYMXaFKxdZ4+ndfB7f/jPn6IEK2xb5VtbnLe/NIE
qeRtanzccoKh8P7CmnwWqQ4CaqVeZTFrQ3jiadptSbpTnt3qzlM=
=oSd/
-----END PGP SIGNATURE-----
Merge 6.1.36 into android14-6.1-lts
Changes in 6.1.36
drm/amd/display: Use dc_update_planes_and_stream
drm/amd/display: Add wrapper to call planes and stream update
drm/amd/display: fix the system hang while disable PSR
tty: serial: fsl_lpuart: make rx_watermark configurable for different platforms
tty: serial: fsl_lpuart: reduce RX watermark to 0 on LS1028A
ata: libata-scsi: Avoid deadlock on rescan after device resume
mm: Fix copy_from_user_nofault().
tpm, tpm_tis: Claim locality in interrupt handler
tpm_crb: Add support for CRB devices based on Pluton
ksmbd: validate command payload size
ksmbd: fix out-of-bound read in smb2_write
ksmbd: validate session id and tree id in the compound request
tick/common: Align tick period during sched_timer setup
selftests: mptcp: remove duplicated entries in usage
selftests: mptcp: join: fix ShellCheck warnings
selftests: mptcp: lib: skip if missing symbol
selftests: mptcp: connect: skip transp tests if not supported
selftests: mptcp: connect: skip disconnect tests if not supported
selftests: mptcp: pm nl: remove hardcoded default limits
selftests: mptcp: pm nl: skip fullmesh flag checks if not supported
selftests: mptcp: sockopt: relax expected returned size
selftests: mptcp: sockopt: skip getsockopt checks if not supported
selftests: mptcp: userspace pm: skip if 'ip' tool is unavailable
selftests: mptcp: userspace pm: skip if not supported
selftests: mptcp: lib: skip if not below kernel version
selftests: mptcp: join: use 'iptables-legacy' if available
selftests: mptcp: join: helpers to skip tests
selftests: mptcp: join: skip check if MIB counter not supported
selftests: mptcp: join: support local endpoint being tracked or not
selftests: mptcp: join: skip Fastclose tests if not supported
selftests: mptcp: join: support RM_ADDR for used endpoints or not
selftests: mptcp: join: skip implicit tests if not supported
selftests: mptcp: join: skip backup if set flag on ID not supported
selftests: mptcp: join: skip fullmesh flag tests if not supported
selftests: mptcp: join: skip MPC backups tests if not supported
selftests/mount_setattr: fix redefine struct mount_attr build error
selftests: mptcp: diag: skip listen tests if not supported
selftests: mptcp: sockopt: skip TCP_INQ checks if not supported
selftests: mptcp: join: skip test if iptables/tc cmds fail
selftests: mptcp: join: skip userspace PM tests if not supported
selftests: mptcp: join: skip fail tests if not supported
selftests: mptcp: join: fix "userspace pm add & remove address"
writeback: fix dereferencing NULL mapping->host on writeback_page_template
scripts: fix the gfp flags header path in gfp-translate
nilfs2: fix buffer corruption due to concurrent device reads
ACPI: sleep: Avoid breaking S3 wakeup due to might_sleep()
KVM: Avoid illegal stage2 mapping on invalid memory slot
Drivers: hv: vmbus: Call hv_synic_free() if hv_synic_alloc() fails
Drivers: hv: vmbus: Fix vmbus_wait_for_unload() to scan present CPUs
PCI: hv: Fix a race condition bug in hv_pci_query_relations()
Revert "PCI: hv: Fix a timing issue which causes kdump to fail occasionally"
PCI: hv: Remove the useless hv_pcichild_state from struct hv_pci_dev
PCI: hv: Fix a race condition in hv_irq_unmask() that can cause panic
PCI: hv: Add a per-bus mutex state_lock
io_uring/net: clear msg_controllen on partial sendmsg retry
io_uring/net: disable partial retries for recvmsg with cmsg
mptcp: handle correctly disconnect() failures
mptcp: fix possible divide by zero in recvmsg()
mptcp: fix possible list corruption on passive MPJ
mptcp: consolidate fallback and non fallback state machine
cgroup: Do not corrupt task iteration when rebinding subsystem
cgroup,freezer: hold cpu_hotplug_lock before freezer_mutex in freezer_css_{online,offline}()
mmc: litex_mmc: set PROBE_PREFER_ASYNCHRONOUS
mmc: sdhci-msm: Disable broken 64-bit DMA on MSM8916
mmc: meson-gx: remove redundant mmc_request_done() call from irq context
mmc: mmci: stm32: fix max busy timeout calculation
mmc: sdhci-spear: fix deferred probing
mmc: bcm2835: fix deferred probing
mmc: sunxi: fix deferred probing
bpf: ensure main program has an extable
wifi: iwlwifi: pcie: Handle SO-F device for PCI id 0x7AF0
spi: spi-geni-qcom: correctly handle -EPROBE_DEFER from dma_request_chan()
regulator: pca9450: Fix LDO3OUT and LDO4OUT MASK
regmap: spi-avmm: Fix regmap_bus max_raw_write
arm64: dts: rockchip: Fix rk356x PCIe register and range mappings
io_uring/poll: serialize poll linked timer start with poll removal
nilfs2: prevent general protection fault in nilfs_clear_dirty_page()
x86/mm: Avoid using set_pgd() outside of real PGD pages
memfd: check for non-NULL file_seals in memfd_create() syscall
mmc: meson-gx: fix deferred probing
ieee802154: hwsim: Fix possible memory leaks
xfrm: Treat already-verified secpath entries as optional
xfrm: interface: rename xfrm_interface.c to xfrm_interface_core.c
xfrm: Ensure policies always checked on XFRM-I input path
KVM: arm64: PMU: Restore the host's PMUSERENR_EL0
bpf: track immediate values written to stack by BPF_ST instruction
bpf: Fix verifier id tracking of scalars on spill
xfrm: fix inbound ipv4/udp/esp packets to UDPv6 dualstack sockets
bpf: Fix a bpf_jit_dump issue for x86_64 with sysctl bpf_jit_enable.
selftests: net: tls: check if FIPS mode is enabled
selftests: net: vrf-xfrm-tests: change authentication and encryption algos
selftests: net: fcnal-test: check if FIPS mode is enabled
xfrm: Linearize the skb after offloading if needed.
net/mlx5: DR, Fix wrong action data allocation in decap action
sfc: use budget for TX completions
net: qca_spi: Avoid high load if QCA7000 is not available
mmc: mtk-sd: fix deferred probing
mmc: mvsdio: fix deferred probing
mmc: omap: fix deferred probing
mmc: omap_hsmmc: fix deferred probing
mmc: owl: fix deferred probing
mmc: sdhci-acpi: fix deferred probing
mmc: sh_mmcif: fix deferred probing
mmc: usdhi60rol0: fix deferred probing
ipvs: align inner_mac_header for encapsulation
net: dsa: mt7530: fix trapping frames on non-MT7621 SoC MT7530 switch
net: dsa: mt7530: fix handling of BPDUs on MT7530 switch
net: dsa: mt7530: fix handling of LLDP frames
be2net: Extend xmit workaround to BE3 chip
netfilter: nf_tables: fix chain binding transaction logic
netfilter: nf_tables: add NFT_TRANS_PREPARE_ERROR to deal with bound set/chain
netfilter: nf_tables: drop map element references from preparation phase
netfilter: nft_set_pipapo: .walk does not deal with generations
netfilter: nf_tables: disallow element updates of bound anonymous sets
netfilter: nf_tables: reject unbound anonymous set before commit phase
netfilter: nf_tables: reject unbound chain set before commit phase
netfilter: nf_tables: disallow updates of anonymous sets
netfilter: nfnetlink_osf: fix module autoload
Revert "net: phy: dp83867: perform soft reset and retain established link"
bpf/btf: Accept function names that contain dots
bpf: Force kprobe multi expected_attach_type for kprobe_multi link
io_uring/net: use the correct msghdr union member in io_sendmsg_copy_hdr
selftests: forwarding: Fix race condition in mirror installation
platform/x86/amd/pmf: Register notify handler only if SPS is enabled
sch_netem: acquire qdisc lock in netem_change()
revert "net: align SO_RCVMARK required privileges with SO_MARK"
arm64: dts: rockchip: Enable GPU on SOQuartz CM4
arm64: dts: rockchip: fix nEXTRST on SOQuartz
gpiolib: Fix GPIO chip IRQ initialization restriction
gpio: sifive: add missing check for platform_get_irq
gpiolib: Fix irq_domain resource tracking for gpiochip_irqchip_add_domain()
scsi: target: iscsi: Prevent login threads from racing between each other
HID: wacom: Add error check to wacom_parse_and_register()
arm64: Add missing Set/Way CMO encodings
smb3: missing null check in SMB2_change_notify
media: cec: core: disable adapter in cec_devnode_unregister
media: cec: core: don't set last_initiator if tx in progress
nfcsim.c: Fix error checking for debugfs_create_dir
btrfs: fix an uninitialized variable warning in btrfs_log_inode
usb: gadget: udc: fix NULL dereference in remove()
nvme: double KA polling frequency to avoid KATO with TBKAS on
nvme: check IO start time when deciding to defer KA
nvme: improve handling of long keep alives
Input: soc_button_array - add invalid acpi_index DMI quirk handling
arm64: dts: qcom: sc7280-idp: drop incorrect dai-cells from WCD938x SDW
arm64: dts: qcom: sc7280-qcard: drop incorrect dai-cells from WCD938x SDW
s390/cio: unregister device when the only path is gone
spi: lpspi: disable lpspi module irq in DMA mode
ASoC: codecs: wcd938x-sdw: do not set can_multi_write flag
ASoC: simple-card: Add missing of_node_put() in case of error
soundwire: dmi-quirks: add new mapping for HP Spectre x360
soundwire: qcom: add proper error paths in qcom_swrm_startup()
ASoC: nau8824: Add quirk to active-high jack-detect
ASoC: amd: yc: Add Thinkpad Neo14 to quirks list for acp6x
gfs2: Don't get stuck writing page onto itself under direct I/O
s390/purgatory: disable branch profiling
ASoC: fsl_sai: Enable BCI bit if SAI works on synchronous mode with BYP asserted
ALSA: hda/realtek: Add "Intel Reference board" and "NUC 13" SSID in the ALC256
i2c: mchp-pci1xxxx: Avoid cast to incompatible function type
ARM: dts: Fix erroneous ADS touchscreen polarities
null_blk: Fix: memory release when memory_backed=1
drm/exynos: vidi: fix a wrong error return
drm/exynos: fix race condition UAF in exynos_g2d_exec_ioctl
drm/radeon: fix race condition UAF in radeon_gem_set_domain_ioctl
vhost_vdpa: tell vqs about the negotiated
vhost_net: revert upend_idx only on retriable error
KVM: arm64: Restore GICv2-on-GICv3 functionality
x86/apic: Fix kernel panic when booting with intremap=off and x2apic_phys
i2c: imx-lpi2c: fix type char overflow issue when calculating the clock cycle
smb: move client and server files to common directory fs/smb
Linux 6.1.36
Note, this "merges away" commit:
679354bea0 ("KVM: arm64: Restore GICv2-on-GICv3 functionality")
because of the merge conflicts were too complex to resolve. If this is
needed in the android tree it should be brought back as an individual
change in the future.
Change-Id: Iafee89e3fb40c8bd631e6cc22eaaf7453b82f727
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
580 lines
15 KiB
C
580 lines
15 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* This file contains the base functions to manage periodic tick
|
|
* related events.
|
|
*
|
|
* Copyright(C) 2005-2006, Thomas Gleixner <tglx@linutronix.de>
|
|
* Copyright(C) 2005-2007, Red Hat, Inc., Ingo Molnar
|
|
* Copyright(C) 2006-2007, Timesys Corp., Thomas Gleixner
|
|
*/
|
|
#include <linux/cpu.h>
|
|
#include <linux/err.h>
|
|
#include <linux/hrtimer.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/nmi.h>
|
|
#include <linux/percpu.h>
|
|
#include <linux/profile.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/module.h>
|
|
#include <trace/events/power.h>
|
|
#include <trace/hooks/sched.h>
|
|
|
|
#include <asm/irq_regs.h>
|
|
|
|
#include "tick-internal.h"
|
|
|
|
/*
|
|
* Tick devices
|
|
*/
|
|
DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
|
|
/*
|
|
* Tick next event: keeps track of the tick time. It's updated by the
|
|
* CPU which handles the tick and protected by jiffies_lock. There is
|
|
* no requirement to write hold the jiffies seqcount for it.
|
|
*/
|
|
ktime_t tick_next_period;
|
|
|
|
/*
|
|
* tick_do_timer_cpu is a timer core internal variable which holds the CPU NR
|
|
* which is responsible for calling do_timer(), i.e. the timekeeping stuff. This
|
|
* variable has two functions:
|
|
*
|
|
* 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the
|
|
* timekeeping lock all at once. Only the CPU which is assigned to do the
|
|
* update is handling it.
|
|
*
|
|
* 2) Hand off the duty in the NOHZ idle case by setting the value to
|
|
* TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks
|
|
* at it will take over and keep the time keeping alive. The handover
|
|
* procedure also covers cpu hotplug.
|
|
*/
|
|
int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
/*
|
|
* tick_do_timer_boot_cpu indicates the boot CPU temporarily owns
|
|
* tick_do_timer_cpu and it should be taken over by an eligible secondary
|
|
* when one comes online.
|
|
*/
|
|
static int tick_do_timer_boot_cpu __read_mostly = -1;
|
|
#endif
|
|
|
|
/*
|
|
* Debugging: see timer_list.c
|
|
*/
|
|
struct tick_device *tick_get_device(int cpu)
|
|
{
|
|
return &per_cpu(tick_cpu_device, cpu);
|
|
}
|
|
|
|
/**
|
|
* tick_is_oneshot_available - check for a oneshot capable event device
|
|
*/
|
|
int tick_is_oneshot_available(void)
|
|
{
|
|
struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev);
|
|
|
|
if (!dev || !(dev->features & CLOCK_EVT_FEAT_ONESHOT))
|
|
return 0;
|
|
if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
|
|
return 1;
|
|
return tick_broadcast_oneshot_available();
|
|
}
|
|
|
|
/*
|
|
* Periodic tick
|
|
*/
|
|
static void tick_periodic(int cpu)
|
|
{
|
|
if (tick_do_timer_cpu == cpu) {
|
|
raw_spin_lock(&jiffies_lock);
|
|
write_seqcount_begin(&jiffies_seq);
|
|
|
|
/* Keep track of the next tick event */
|
|
tick_next_period = ktime_add_ns(tick_next_period, TICK_NSEC);
|
|
|
|
do_timer(1);
|
|
write_seqcount_end(&jiffies_seq);
|
|
raw_spin_unlock(&jiffies_lock);
|
|
update_wall_time();
|
|
trace_android_vh_jiffies_update(NULL);
|
|
}
|
|
|
|
update_process_times(user_mode(get_irq_regs()));
|
|
profile_tick(CPU_PROFILING);
|
|
}
|
|
|
|
/*
|
|
* Event handler for periodic ticks
|
|
*/
|
|
void tick_handle_periodic(struct clock_event_device *dev)
|
|
{
|
|
int cpu = smp_processor_id();
|
|
ktime_t next = dev->next_event;
|
|
|
|
tick_periodic(cpu);
|
|
|
|
#if defined(CONFIG_HIGH_RES_TIMERS) || defined(CONFIG_NO_HZ_COMMON)
|
|
/*
|
|
* The cpu might have transitioned to HIGHRES or NOHZ mode via
|
|
* update_process_times() -> run_local_timers() ->
|
|
* hrtimer_run_queues().
|
|
*/
|
|
if (dev->event_handler != tick_handle_periodic)
|
|
return;
|
|
#endif
|
|
|
|
if (!clockevent_state_oneshot(dev))
|
|
return;
|
|
for (;;) {
|
|
/*
|
|
* Setup the next period for devices, which do not have
|
|
* periodic mode:
|
|
*/
|
|
next = ktime_add_ns(next, TICK_NSEC);
|
|
|
|
if (!clockevents_program_event(dev, next, false))
|
|
return;
|
|
/*
|
|
* Have to be careful here. If we're in oneshot mode,
|
|
* before we call tick_periodic() in a loop, we need
|
|
* to be sure we're using a real hardware clocksource.
|
|
* Otherwise we could get trapped in an infinite
|
|
* loop, as the tick_periodic() increments jiffies,
|
|
* which then will increment time, possibly causing
|
|
* the loop to trigger again and again.
|
|
*/
|
|
if (timekeeping_valid_for_hres())
|
|
tick_periodic(cpu);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Setup the device for a periodic tick
|
|
*/
|
|
void tick_setup_periodic(struct clock_event_device *dev, int broadcast)
|
|
{
|
|
tick_set_periodic_handler(dev, broadcast);
|
|
|
|
/* Broadcast setup ? */
|
|
if (!tick_device_is_functional(dev))
|
|
return;
|
|
|
|
if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
|
|
!tick_broadcast_oneshot_active()) {
|
|
clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC);
|
|
} else {
|
|
unsigned int seq;
|
|
ktime_t next;
|
|
|
|
do {
|
|
seq = read_seqcount_begin(&jiffies_seq);
|
|
next = tick_next_period;
|
|
} while (read_seqcount_retry(&jiffies_seq, seq));
|
|
|
|
clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
|
|
|
|
for (;;) {
|
|
if (!clockevents_program_event(dev, next, false))
|
|
return;
|
|
next = ktime_add_ns(next, TICK_NSEC);
|
|
}
|
|
}
|
|
}
|
|
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
static void giveup_do_timer(void *info)
|
|
{
|
|
int cpu = *(unsigned int *)info;
|
|
|
|
WARN_ON(tick_do_timer_cpu != smp_processor_id());
|
|
|
|
tick_do_timer_cpu = cpu;
|
|
}
|
|
|
|
static void tick_take_do_timer_from_boot(void)
|
|
{
|
|
int cpu = smp_processor_id();
|
|
int from = tick_do_timer_boot_cpu;
|
|
|
|
if (from >= 0 && from != cpu)
|
|
smp_call_function_single(from, giveup_do_timer, &cpu, 1);
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Setup the tick device
|
|
*/
|
|
static void tick_setup_device(struct tick_device *td,
|
|
struct clock_event_device *newdev, int cpu,
|
|
const struct cpumask *cpumask)
|
|
{
|
|
void (*handler)(struct clock_event_device *) = NULL;
|
|
ktime_t next_event = 0;
|
|
|
|
/*
|
|
* First device setup ?
|
|
*/
|
|
if (!td->evtdev) {
|
|
/*
|
|
* If no cpu took the do_timer update, assign it to
|
|
* this cpu:
|
|
*/
|
|
if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
|
|
tick_do_timer_cpu = cpu;
|
|
tick_next_period = ktime_get();
|
|
#ifdef CONFIG_NO_HZ_FULL
|
|
/*
|
|
* The boot CPU may be nohz_full, in which case set
|
|
* tick_do_timer_boot_cpu so the first housekeeping
|
|
* secondary that comes up will take do_timer from
|
|
* us.
|
|
*/
|
|
if (tick_nohz_full_cpu(cpu))
|
|
tick_do_timer_boot_cpu = cpu;
|
|
|
|
} else if (tick_do_timer_boot_cpu != -1 &&
|
|
!tick_nohz_full_cpu(cpu)) {
|
|
tick_take_do_timer_from_boot();
|
|
tick_do_timer_boot_cpu = -1;
|
|
WARN_ON(tick_do_timer_cpu != cpu);
|
|
#endif
|
|
}
|
|
|
|
/*
|
|
* Startup in periodic mode first.
|
|
*/
|
|
td->mode = TICKDEV_MODE_PERIODIC;
|
|
} else {
|
|
handler = td->evtdev->event_handler;
|
|
next_event = td->evtdev->next_event;
|
|
td->evtdev->event_handler = clockevents_handle_noop;
|
|
}
|
|
|
|
td->evtdev = newdev;
|
|
|
|
/*
|
|
* When the device is not per cpu, pin the interrupt to the
|
|
* current cpu:
|
|
*/
|
|
if (!cpumask_equal(newdev->cpumask, cpumask))
|
|
irq_set_affinity(newdev->irq, cpumask);
|
|
|
|
/*
|
|
* When global broadcasting is active, check if the current
|
|
* device is registered as a placeholder for broadcast mode.
|
|
* This allows us to handle this x86 misfeature in a generic
|
|
* way. This function also returns !=0 when we keep the
|
|
* current active broadcast state for this CPU.
|
|
*/
|
|
if (tick_device_uses_broadcast(newdev, cpu))
|
|
return;
|
|
|
|
if (td->mode == TICKDEV_MODE_PERIODIC)
|
|
tick_setup_periodic(newdev, 0);
|
|
else
|
|
tick_setup_oneshot(newdev, handler, next_event);
|
|
}
|
|
|
|
void tick_install_replacement(struct clock_event_device *newdev)
|
|
{
|
|
struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
|
|
int cpu = smp_processor_id();
|
|
|
|
clockevents_exchange_device(td->evtdev, newdev);
|
|
tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
|
|
if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
|
|
tick_oneshot_notify();
|
|
}
|
|
|
|
static bool tick_check_percpu(struct clock_event_device *curdev,
|
|
struct clock_event_device *newdev, int cpu)
|
|
{
|
|
if (!cpumask_test_cpu(cpu, newdev->cpumask))
|
|
return false;
|
|
if (cpumask_equal(newdev->cpumask, cpumask_of(cpu)))
|
|
return true;
|
|
/* Check if irq affinity can be set */
|
|
if (newdev->irq >= 0 && !irq_can_set_affinity(newdev->irq))
|
|
return false;
|
|
/* Prefer an existing cpu local device */
|
|
if (curdev && cpumask_equal(curdev->cpumask, cpumask_of(cpu)))
|
|
return false;
|
|
return true;
|
|
}
|
|
|
|
static bool tick_check_preferred(struct clock_event_device *curdev,
|
|
struct clock_event_device *newdev)
|
|
{
|
|
/* Prefer oneshot capable device */
|
|
if (!(newdev->features & CLOCK_EVT_FEAT_ONESHOT)) {
|
|
if (curdev && (curdev->features & CLOCK_EVT_FEAT_ONESHOT))
|
|
return false;
|
|
if (tick_oneshot_mode_active())
|
|
return false;
|
|
}
|
|
|
|
/*
|
|
* Use the higher rated one, but prefer a CPU local device with a lower
|
|
* rating than a non-CPU local device
|
|
*/
|
|
return !curdev ||
|
|
newdev->rating > curdev->rating ||
|
|
!cpumask_equal(curdev->cpumask, newdev->cpumask);
|
|
}
|
|
|
|
/*
|
|
* Check whether the new device is a better fit than curdev. curdev
|
|
* can be NULL !
|
|
*/
|
|
bool tick_check_replacement(struct clock_event_device *curdev,
|
|
struct clock_event_device *newdev)
|
|
{
|
|
if (!tick_check_percpu(curdev, newdev, smp_processor_id()))
|
|
return false;
|
|
|
|
return tick_check_preferred(curdev, newdev);
|
|
}
|
|
|
|
/*
|
|
* Check, if the new registered device should be used. Called with
|
|
* clockevents_lock held and interrupts disabled.
|
|
*/
|
|
void tick_check_new_device(struct clock_event_device *newdev)
|
|
{
|
|
struct clock_event_device *curdev;
|
|
struct tick_device *td;
|
|
int cpu;
|
|
|
|
cpu = smp_processor_id();
|
|
td = &per_cpu(tick_cpu_device, cpu);
|
|
curdev = td->evtdev;
|
|
|
|
if (!tick_check_replacement(curdev, newdev))
|
|
goto out_bc;
|
|
|
|
if (!try_module_get(newdev->owner))
|
|
return;
|
|
|
|
/*
|
|
* Replace the eventually existing device by the new
|
|
* device. If the current device is the broadcast device, do
|
|
* not give it back to the clockevents layer !
|
|
*/
|
|
if (tick_is_broadcast_device(curdev)) {
|
|
clockevents_shutdown(curdev);
|
|
curdev = NULL;
|
|
}
|
|
clockevents_exchange_device(curdev, newdev);
|
|
tick_setup_device(td, newdev, cpu, cpumask_of(cpu));
|
|
if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
|
|
tick_oneshot_notify();
|
|
return;
|
|
|
|
out_bc:
|
|
/*
|
|
* Can the new device be used as a broadcast device ?
|
|
*/
|
|
tick_install_broadcast_device(newdev, cpu);
|
|
}
|
|
|
|
/**
|
|
* tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode
|
|
* @state: The target state (enter/exit)
|
|
*
|
|
* The system enters/leaves a state, where affected devices might stop
|
|
* Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
|
|
*
|
|
* Called with interrupts disabled, so clockevents_lock is not
|
|
* required here because the local clock event device cannot go away
|
|
* under us.
|
|
*/
|
|
int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
|
|
{
|
|
struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
|
|
|
|
if (!(td->evtdev->features & CLOCK_EVT_FEAT_C3STOP))
|
|
return 0;
|
|
|
|
return __tick_broadcast_oneshot_control(state);
|
|
}
|
|
EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control);
|
|
|
|
#ifdef CONFIG_HOTPLUG_CPU
|
|
/*
|
|
* Transfer the do_timer job away from a dying cpu.
|
|
*
|
|
* Called with interrupts disabled. No locking required. If
|
|
* tick_do_timer_cpu is owned by this cpu, nothing can change it.
|
|
*/
|
|
void tick_handover_do_timer(void)
|
|
{
|
|
if (tick_do_timer_cpu == smp_processor_id())
|
|
tick_do_timer_cpu = cpumask_first(cpu_online_mask);
|
|
}
|
|
|
|
/*
|
|
* Shutdown an event device on a given cpu:
|
|
*
|
|
* This is called on a life CPU, when a CPU is dead. So we cannot
|
|
* access the hardware device itself.
|
|
* We just set the mode and remove it from the lists.
|
|
*/
|
|
void tick_shutdown(unsigned int cpu)
|
|
{
|
|
struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
|
|
struct clock_event_device *dev = td->evtdev;
|
|
|
|
td->mode = TICKDEV_MODE_PERIODIC;
|
|
if (dev) {
|
|
/*
|
|
* Prevent that the clock events layer tries to call
|
|
* the set mode function!
|
|
*/
|
|
clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
|
|
clockevents_exchange_device(dev, NULL);
|
|
dev->event_handler = clockevents_handle_noop;
|
|
td->evtdev = NULL;
|
|
}
|
|
}
|
|
#endif
|
|
|
|
/**
|
|
* tick_suspend_local - Suspend the local tick device
|
|
*
|
|
* Called from the local cpu for freeze with interrupts disabled.
|
|
*
|
|
* No locks required. Nothing can change the per cpu device.
|
|
*/
|
|
void tick_suspend_local(void)
|
|
{
|
|
struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
|
|
|
|
clockevents_shutdown(td->evtdev);
|
|
}
|
|
|
|
/**
|
|
* tick_resume_local - Resume the local tick device
|
|
*
|
|
* Called from the local CPU for unfreeze or XEN resume magic.
|
|
*
|
|
* No locks required. Nothing can change the per cpu device.
|
|
*/
|
|
void tick_resume_local(void)
|
|
{
|
|
struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
|
|
bool broadcast = tick_resume_check_broadcast();
|
|
|
|
clockevents_tick_resume(td->evtdev);
|
|
if (!broadcast) {
|
|
if (td->mode == TICKDEV_MODE_PERIODIC)
|
|
tick_setup_periodic(td->evtdev, 0);
|
|
else
|
|
tick_resume_oneshot();
|
|
}
|
|
|
|
/*
|
|
* Ensure that hrtimers are up to date and the clockevents device
|
|
* is reprogrammed correctly when high resolution timers are
|
|
* enabled.
|
|
*/
|
|
hrtimers_resume_local();
|
|
}
|
|
|
|
/**
|
|
* tick_suspend - Suspend the tick and the broadcast device
|
|
*
|
|
* Called from syscore_suspend() via timekeeping_suspend with only one
|
|
* CPU online and interrupts disabled or from tick_unfreeze() under
|
|
* tick_freeze_lock.
|
|
*
|
|
* No locks required. Nothing can change the per cpu device.
|
|
*/
|
|
void tick_suspend(void)
|
|
{
|
|
tick_suspend_local();
|
|
tick_suspend_broadcast();
|
|
}
|
|
|
|
/**
|
|
* tick_resume - Resume the tick and the broadcast device
|
|
*
|
|
* Called from syscore_resume() via timekeeping_resume with only one
|
|
* CPU online and interrupts disabled.
|
|
*
|
|
* No locks required. Nothing can change the per cpu device.
|
|
*/
|
|
void tick_resume(void)
|
|
{
|
|
tick_resume_broadcast();
|
|
tick_resume_local();
|
|
}
|
|
|
|
#ifdef CONFIG_SUSPEND
|
|
static DEFINE_RAW_SPINLOCK(tick_freeze_lock);
|
|
static unsigned int tick_freeze_depth;
|
|
|
|
/**
|
|
* tick_freeze - Suspend the local tick and (possibly) timekeeping.
|
|
*
|
|
* Check if this is the last online CPU executing the function and if so,
|
|
* suspend timekeeping. Otherwise suspend the local tick.
|
|
*
|
|
* Call with interrupts disabled. Must be balanced with %tick_unfreeze().
|
|
* Interrupts must not be enabled before the subsequent %tick_unfreeze().
|
|
*/
|
|
void tick_freeze(void)
|
|
{
|
|
raw_spin_lock(&tick_freeze_lock);
|
|
|
|
tick_freeze_depth++;
|
|
if (tick_freeze_depth == num_online_cpus()) {
|
|
trace_suspend_resume(TPS("timekeeping_freeze"),
|
|
smp_processor_id(), true);
|
|
system_state = SYSTEM_SUSPEND;
|
|
sched_clock_suspend();
|
|
timekeeping_suspend();
|
|
} else {
|
|
tick_suspend_local();
|
|
}
|
|
|
|
raw_spin_unlock(&tick_freeze_lock);
|
|
}
|
|
|
|
/**
|
|
* tick_unfreeze - Resume the local tick and (possibly) timekeeping.
|
|
*
|
|
* Check if this is the first CPU executing the function and if so, resume
|
|
* timekeeping. Otherwise resume the local tick.
|
|
*
|
|
* Call with interrupts disabled. Must be balanced with %tick_freeze().
|
|
* Interrupts must not be enabled after the preceding %tick_freeze().
|
|
*/
|
|
void tick_unfreeze(void)
|
|
{
|
|
raw_spin_lock(&tick_freeze_lock);
|
|
|
|
if (tick_freeze_depth == num_online_cpus()) {
|
|
timekeeping_resume();
|
|
sched_clock_resume();
|
|
system_state = SYSTEM_RUNNING;
|
|
trace_suspend_resume(TPS("timekeeping_freeze"),
|
|
smp_processor_id(), false);
|
|
} else {
|
|
touch_softlockup_watchdog();
|
|
tick_resume_local();
|
|
}
|
|
|
|
tick_freeze_depth--;
|
|
|
|
raw_spin_unlock(&tick_freeze_lock);
|
|
}
|
|
#endif /* CONFIG_SUSPEND */
|
|
|
|
/**
|
|
* tick_init - initialize the tick control
|
|
*/
|
|
void __init tick_init(void)
|
|
{
|
|
tick_broadcast_init();
|
|
tick_nohz_init();
|
|
}
|