c547c8c45b
https://source.android.com/security/bulletin/2022-02-01 CVE-2021-39685 CVE-2021-39686 * tag 'ASB-2022-02-05_4.19-stable' of https://github.com/aosp-mirror/kernel_common: ANDROID: incremental-fs: remove index and incomplete dir on umount Revert "ASoC: dpcm: prevent snd_soc_dpcm use after free" Revert "ANDROID: android-4.19-stable build canary test." ANDROID: android-4.19-stable build canary test. Linux 4.19.227 drm/vmwgfx: Fix stale file descriptors on failed usercopy select: Fix indefinitely sleeping task in poll_schedule_timeout() net: bridge: clear bridge's private skb space on xmit drm/i915: Flush TLBs before releasing backing store Linux 4.19.226 fuse: fix live lock in fuse_iget() fuse: fix bad inode mips,s390,sh,sparc: gup: Work around the "COW can break either way" issue mtd: nand: bbt: Fix corner case in bad block table handling lib82596: Fix IRQ check in sni_82596_probe scripts/dtc: dtx_diff: remove broken example from help text bcmgenet: add WOL IRQ check net_sched: restore "mpu xxx" handling dmaengine: at_xdmac: Fix at_xdmac_lld struct definition dmaengine: at_xdmac: Fix lld view setting dmaengine: at_xdmac: Print debug message after realeasing the lock dmaengine: at_xdmac: Don't start transactions at tx_submit level libcxgb: Don't accidentally set RTO_ONLINK in cxgb_find_route() netns: add schedule point in ops_exit_list() rtc: pxa: fix null pointer dereference net: axienet: fix number of TX ring slots for available check net: axienet: Wait for PhyRstCmplt after core reset af_unix: annote lockless accesses to unix_tot_inflight & gc_in_progress parisc: pdc_stable: Fix memory leak in pdcs_register_pathentries net/fsl: xgmac_mdio: Fix incorrect iounmap when removing module powerpc/fsl/dts: Enable WA for erratum A-009885 on fman3l MDIO buses powerpc/cell: Fix clang -Wimplicit-fallthrough warning dmaengine: stm32-mdma: fix STM32_MDMA_CTBR_TSEL_MASK RDMA/rxe: Fix a typo in opcode name RDMA/hns: Modify the mapping attribute of doorbell to device Documentation: refer to config RANDOMIZE_BASE for kernel address-space randomization media: rcar-csi2: Optimize the selection PHTW register firmware: Update Kconfig help text for Google firmware ARM: dts: Fix vcsi regulator to be always-on for droid4 to prevent hangs drm/radeon: fix error handling in radeon_driver_open_kms regulator: core: Let boot-on regulators be powered off ASoC: dpcm: prevent snd_soc_dpcm use after free crypto: stm32/crc32 - Fix kernel BUG triggered in probe() ext4: don't use the orphan list when migrating an inode ext4: Fix BUG_ON in ext4_bread when write quota data ext4: set csum seed in tmp inode while migrating to extents ext4: make sure quota gets properly shutdown on error ext4: make sure to reset inode lockdep class when quota enabling fails drm/etnaviv: limit submit sizes s390/mm: fix 2KB pgtable release race iwlwifi: mvm: Increase the scan timeout guard to 30 seconds cputime, cpuacct: Include guest time in user time in cpuacct.stat serial: Fix incorrect rs485 polarity on uart open ubifs: Error path in ubifs_remount_rw() seems to wrongly free write buffers rpmsg: core: Clean up resources on announce_create failure. power: bq25890: Enable continuous conversion for ADC at charging ASoC: mediatek: mt8173: fix device_node leak scsi: sr: Don't use GFP_DMA MIPS: Octeon: Fix build errors using clang i2c: designware-pci: Fix to change data types of hcnt and lcnt parameters MIPS: OCTEON: add put_device() after of_find_device_by_node() powerpc: handle kdump appropriately with crash_kexec_post_notifiers option ALSA: seq: Set upper limit of processed events w1: Misuse of get_user()/put_user() reported by sparse i2c: mpc: Correct I2C reset procedure powerpc/smp: Move setup_profiling_timer() under CONFIG_PROFILING i2c: i801: Don't silently correct invalid transfer size powerpc/watchdog: Fix missed watchdog reset due to memory ordering race powerpc/btext: add missing of_node_put powerpc/cell: add missing of_node_put powerpc/powernv: add missing of_node_put powerpc/6xx: add missing of_node_put parisc: Avoid calling faulthandler_disabled() twice serial: core: Keep mctrl register state and cached copy in sync serial: pl010: Drop CR register reset on set_termios regulator: qcom_smd: Align probe function with rpmh-regulator net: gemini: allow any RGMII interface mode net: phy: marvell: configure RGMII delays for 88E1118 dm space map common: add bounds check to sm_ll_lookup_bitmap() dm btree: add a defensive bounds check to insert_at() mac80211: allow non-standard VHT MCS-10/11 net: mdio: Demote probed message to debug print btrfs: remove BUG_ON(!eie) in find_parent_nodes btrfs: remove BUG_ON() in find_parent_nodes() ACPI: battery: Add the ThinkPad "Not Charging" quirk drm/amdgpu: fixup bad vram size on gmc v8 ACPICA: Hardware: Do not flush CPU cache when entering S4 and S5 ACPICA: Executer: Fix the REFCLASS_REFOF case in acpi_ex_opcode_1A_0T_1R() ACPICA: Utilities: Avoid deleting the same object twice in a row ACPICA: actypes.h: Expand the ACPI_ACCESS_ definitions jffs2: GC deadlock reading a page that is used in jffs2_write_begin() um: registers: Rename function names to avoid conflicts and build problems iwlwifi: mvm: Fix calculation of frame length iwlwifi: remove module loading failure message iwlwifi: fix leaks/bad data after failed firmware load ath9k: Fix out-of-bound memcpy in ath9k_hif_usb_rx_stream usb: hub: Add delay for SuperSpeed hub resume to let links transit to U0 arm64: tegra: Adjust length of CCPLEX cluster MMIO region audit: ensure userspace is penalized the same as the kernel when under pressure mmc: core: Fixup storing of OCR for MMC_QUIRK_NONSTD_SDIO media: saa7146: hexium_gemini: Fix a NULL pointer dereference in hexium_attach() media: igorplugusb: receiver overflow should be reported HID: quirks: Allow inverting the absolute X/Y values bpf: Do not WARN in bpf_warn_invalid_xdp_action() net: bonding: debug: avoid printing debug logs when bond is not notifying peers x86/mce: Mark mce_read_aux() noinstr x86/mce: Mark mce_end() noinstr x86/mce: Mark mce_panic() noinstr net-sysfs: update the queue counts in the unregistration path ath10k: Fix tx hanging iwlwifi: mvm: synchronize with FW after multicast commands media: m920x: don't use stack on USB reads media: saa7146: hexium_orion: Fix a NULL pointer dereference in hexium_attach() media: uvcvideo: Increase UVC_CTRL_CONTROL_TIMEOUT to 5 seconds. floppy: Add max size check for user space request usb: uhci: add aspeed ast2600 uhci support rsi: Fix out-of-bounds read in rsi_read_pkt() mwifiex: Fix skb_over_panic in mwifiex_usb_recv() HSI: core: Fix return freed object in hsi_new_client gpiolib: acpi: Do not set the IRQ type if the IRQ is already in use drm/bridge: megachips: Ensure both bridges are probed before registration mlxsw: pci: Add shutdown method in PCI driver media: b2c2: Add missing check in flexcop_pci_isr: HID: apple: Do not reset quirks when the Fn key is not found usb: gadget: f_fs: Use stream_open() for endpoint files drm/nouveau/pmu/gm200-: avoid touching PMU outside of DEVINIT/PREOS/ACR ar5523: Fix null-ptr-deref with unexpected WDCMSG_TARGET_START reply fs: dlm: filter user dlm messages for kernel locks Bluetooth: Fix debugfs entry leak in hci_register_dev() RDMA/cxgb4: Set queue pair state when being queried mips: bcm63xx: add support for clk_set_parent() mips: lantiq: add support for clk_set_parent() misc: lattice-ecp3-config: Fix task hung when firmware load failed ASoC: samsung: idma: Check of ioremap return value ASoC: mediatek: Check for error clk pointer iommu/iova: Fix race between FQ timeout and teardown dmaengine: pxa/mmp: stop referencing config->slave_id ASoC: rt5663: Handle device_property_read_u32_array error codes RDMA/core: Let ib_find_gid() continue search even after empty entry scsi: ufs: Fix race conditions related to driver data iommu/io-pgtable-arm: Fix table descriptor paddr formatting char/mwave: Adjust io port register size ALSA: oss: fix compile error when OSS_DEBUG is enabled ASoC: uniphier: drop selecting non-existing SND_SOC_UNIPHIER_AIO_DMA powerpc/prom_init: Fix improper check of prom_getprop() RDMA/hns: Validate the pkey index ALSA: hda: Add missing rwsem around snd_ctl_remove() calls ALSA: PCM: Add missing rwsem around snd_ctl_remove() calls ALSA: jack: Add missing rwsem around snd_ctl_remove() calls ext4: avoid trim error on fs with small groups net: mcs7830: handle usb read errors properly pcmcia: fix setting of kthread task states can: xilinx_can: xcan_probe(): check for error irq can: softing: softing_startstop(): fix set but not used variable warning tpm: add request_locality before write TPM_INT_ENABLE spi: spi-meson-spifc: Add missing pm_runtime_disable() in meson_spifc_probe Bluetooth: hci_bcm: Check for error irq fsl/fman: Check for null pointer after calling devm_ioremap staging: greybus: audio: Check null pointer ppp: ensure minimum packet size in ppp_write() netfilter: ipt_CLUSTERIP: fix refcount leak in clusterip_tg_check() pcmcia: rsrc_nonstatic: Fix a NULL pointer dereference in nonstatic_find_mem_region() pcmcia: rsrc_nonstatic: Fix a NULL pointer dereference in __nonstatic_find_io_region() x86/mce/inject: Avoid out-of-bounds write when setting flags mmc: meson-mx-sdio: add IRQ check ARM: dts: armada-38x: Add generic compatible to UART nodes usb: ftdi-elan: fix memory leak on device disconnect xfrm: state and policy should fail if XFRMA_IF_ID 0 xfrm: interface with if_id 0 should return error drm/msm/dpu: fix safe status debugfs file media: coda/imx-vdoa: Handle dma_set_coherent_mask error codes media: msi001: fix possible null-ptr-deref in msi001_probe() media: dw2102: Fix use after free crypto: stm32/cryp - fix double pm exit xfrm: fix a small bug in xfrm_sa_len() sched/rt: Try to restart rt period timer when rt runtime exceeded media: si2157: Fix "warm" tuner state detection media: saa7146: mxb: Fix a NULL pointer dereference in mxb_attach() media: dib8000: Fix a memleak in dib8000_init() floppy: Fix hang in watchdog when disk is ejected serial: amba-pl011: do not request memory region twice tty: serial: uartlite: allow 64 bit address drm/radeon/radeon_kms: Fix a NULL pointer dereference in radeon_driver_open_kms() drm/amdgpu: Fix a NULL pointer dereference in amdgpu_connector_lcd_native_mode() arm64: dts: qcom: msm8916: fix MMC controller aliases netfilter: bridge: add support for pppoe filtering media: mtk-vcodec: call v4l2_m2m_ctx_release first when file is released media: si470x-i2c: fix possible memory leak in si470x_i2c_probe() media: rcar-csi2: Correct the selection of hsfreqrange tty: serial: atmel: Call dma_async_issue_pending() tty: serial: atmel: Check return code of dmaengine_submit() crypto: qce - fix uaf on qce_ahash_register_one media: dmxdev: fix UAF when dvb_register_device() fails tee: fix put order in teedev_close_context() Bluetooth: stop proccessing malicious adv data arm64: dts: meson-gxbb-wetek: fix missing GPIO binding media: em28xx: fix memory leak in em28xx_init_dev media: videobuf2: Fix the size printk format wcn36xx: Release DMA channel descriptor allocations wcn36xx: Indicate beacon not connection loss on MISSED_BEACON_IND clk: bcm-2835: Remove rounding up the dividers clk: bcm-2835: Pick the closest clock rate Bluetooth: cmtp: fix possible panic when cmtp_init_sockets() fails drm/panel: innolux-p079zca: Delete panel on attach() failure shmem: fix a race between shmem_unused_huge_shrink and shmem_evict_inode PCI: Add function 1 DMA alias quirk for Marvell 88SE9125 SATA controller lkdtm: Fix content of section containing lkdtm_rodata_do_nothing() can: softing_cs: softingcs_probe(): fix memleak on registration failure media: stk1160: fix control-message timeouts media: pvrusb2: fix control-message timeouts media: redrat3: fix control-message timeouts media: dib0700: fix undefined behavior in tuner shutdown media: s2255: fix control-message timeouts media: cpia2: fix control-message timeouts media: em28xx: fix control-message timeouts media: mceusb: fix control-message timeouts media: flexcop-usb: fix control-message timeouts rtc: cmos: take rtc_lock while reading from CMOS x86/gpu: Reserve stolen memory for first integrated Intel GPU mtd: rawnand: gpmi: Remove explicit default gpmi clock setting for i.MX6 nfc: llcp: fix NULL error pointer dereference on sendmsg() after failed bind() f2fs: fix to do sanity check in is_alive() HID: wacom: Avoid using stale array indicies to read contact count HID: wacom: Ignore the confidence flag when a touch is removed HID: wacom: Reset expected and received contact counts at the same time HID: uhid: Fix worker destroying device without any protection ALSA: hda/realtek - Fix silent output on Gigabyte X570 Aorus Master after reboot from Windows firmware: qemu_fw_cfg: fix kobject leak in probe error path firmware: qemu_fw_cfg: fix NULL-pointer deref on duplicate entries firmware: qemu_fw_cfg: fix sysfs information leak rtlwifi: rtl8192cu: Fix WARNING when calling local_irq_restore() with interrupts enabled media: uvcvideo: fix division by zero at stream start KVM: s390: Clarify SIGP orders versus STOP/RESTART orangefs: Fix the size of a memory allocation in orangefs_bufmap_alloc() kbuild: Add $(KBUILD_HOSTLDFLAGS) to 'has_libelf' test drm/i915: Avoid bitwise vs logical OR warning in snb_wm_latency_quirk() staging: wlan-ng: Avoid bitwise vs logical OR warning in hfa384x_usb_throttlefn() random: fix data race on crng init time random: fix data race on crng_node_pool can: gs_usb: gs_can_start_xmit(): zero-initialize hf->{flags,reserved} can: gs_usb: fix use of uninitialized variable, detach device on reception of invalid USB data mfd: intel-lpss: Fix too early PM enablement in the ACPI ->probe() veth: Do not record rx queue hint in veth_xmit can: bcm: switch timer to HRTIMER_MODE_SOFT and remove hrtimer_tasklet USB: Fix "slab-out-of-bounds Write" bug in usb_hcd_poll_rh_status USB: core: Fix bug in resuming hub's handling of wakeup requests Bluetooth: bfusb: fix division by zero in send path ANDROID: incremental-fs: fix mount_fs issue ANDROID: Add allowed symbols requried from Qualcomm drivers UPSTREAM: drivers core: Use sysfs_emit and sysfs_emit_at for show(device *...) functions UPSTREAM: x86/pci: Fix the function type for check_reserved_t Linux 4.19.225 mISDN: change function names to avoid conflicts net: udp: fix alignment problem in udp4_seq_show() ip6_vti: initialize __ip6_tnl_parm struct in vti6_siocdevprivate scsi: libiscsi: Fix UAF in iscsi_conn_get_param()/iscsi_conn_teardown() usb: mtu3: fix interval value for intr and isoc ipv6: Do cleanup if attribute validation fails in multipath route ipv6: Continue processing multipath route even if gateway attribute is invalid phonet: refcount leak in pep_sock_accep rndis_host: support Hytera digital radios power: reset: ltc2952: Fix use of floating point literals xfs: map unwritten blocks in XFS_IOC_{ALLOC,FREE}SP just like fallocate sch_qfq: prevent shift-out-of-bounds in qfq_init_qdisc ipv6: Check attribute length for RTA_GATEWAY when deleting multipath route ipv6: Check attribute length for RTA_GATEWAY in multipath route i40e: Fix incorrect netdev's real number of RX/TX queues i40e: fix use-after-free in i40e_sync_filters_subtask() mac80211: initialize variable have_higher_than_11mbit RDMA/core: Don't infoleak GRH fields ieee802154: atusb: fix uninit value in atusb_set_extended_addr tracing: Tag trace_percpu_buffer as a percpu pointer tracing: Fix check for trace_percpu_buffer validity in get_trace_buf() Change-Id: If855472ff18be9e734ef3f4d9f84adbd8c8c3883 Signed-off-by: UtsavBalar1231 <utsavbalar1231@gmail.com> Conflicts: drivers/media/dvb-core/dmxdev.c
920 lines
23 KiB
C
920 lines
23 KiB
C
/*
|
|
* Simple CPU accounting cgroup controller
|
|
*/
|
|
#include <linux/cpufreq_times.h>
|
|
#include "sched.h"
|
|
#include "walt.h"
|
|
|
|
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
|
|
|
|
/*
|
|
* There are no locks covering percpu hardirq/softirq time.
|
|
* They are only modified in vtime_account, on corresponding CPU
|
|
* with interrupts disabled. So, writes are safe.
|
|
* They are read and saved off onto struct rq in update_rq_clock().
|
|
* This may result in other CPU reading this CPU's irq time and can
|
|
* race with irq/vtime_account on this CPU. We would either get old
|
|
* or new value with a side effect of accounting a slice of irq time to wrong
|
|
* task when irq is in progress while we read rq->clock. That is a worthy
|
|
* compromise in place of having locks on each irq in account_system_time.
|
|
*/
|
|
DEFINE_PER_CPU(struct irqtime, cpu_irqtime);
|
|
|
|
static int sched_clock_irqtime;
|
|
|
|
void enable_sched_clock_irqtime(void)
|
|
{
|
|
sched_clock_irqtime = 1;
|
|
}
|
|
|
|
void disable_sched_clock_irqtime(void)
|
|
{
|
|
sched_clock_irqtime = 0;
|
|
}
|
|
|
|
static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
|
|
enum cpu_usage_stat idx)
|
|
{
|
|
u64 *cpustat = kcpustat_this_cpu->cpustat;
|
|
|
|
u64_stats_update_begin(&irqtime->sync);
|
|
cpustat[idx] += delta;
|
|
irqtime->total += delta;
|
|
irqtime->tick_delta += delta;
|
|
u64_stats_update_end(&irqtime->sync);
|
|
}
|
|
|
|
/*
|
|
* Called before incrementing preempt_count on {soft,}irq_enter
|
|
* and before decrementing preempt_count on {soft,}irq_exit.
|
|
*/
|
|
void irqtime_account_irq(struct task_struct *curr)
|
|
{
|
|
struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
|
|
s64 delta;
|
|
int cpu;
|
|
#ifdef CONFIG_SCHED_WALT
|
|
u64 wallclock;
|
|
bool account = true;
|
|
#endif
|
|
|
|
if (!sched_clock_irqtime)
|
|
return;
|
|
|
|
cpu = smp_processor_id();
|
|
#ifdef CONFIG_SCHED_WALT
|
|
wallclock = sched_clock_cpu(cpu);
|
|
#endif
|
|
delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
|
|
irqtime->irq_start_time += delta;
|
|
|
|
/*
|
|
* We do not account for softirq time from ksoftirqd here.
|
|
* We want to continue accounting softirq time to ksoftirqd thread
|
|
* in that case, so as not to confuse scheduler with a special task
|
|
* that do not consume any time, but still wants to run.
|
|
*/
|
|
if (hardirq_count())
|
|
irqtime_account_delta(irqtime, delta, CPUTIME_IRQ);
|
|
else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
|
|
irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
|
|
#ifdef CONFIG_SCHED_WALT
|
|
else
|
|
account = false;
|
|
|
|
if (account)
|
|
sched_account_irqtime(cpu, curr, delta, wallclock);
|
|
else if (curr != this_cpu_ksoftirqd())
|
|
sched_account_irqstart(cpu, curr, wallclock);
|
|
#endif
|
|
}
|
|
EXPORT_SYMBOL_GPL(irqtime_account_irq);
|
|
|
|
static u64 irqtime_tick_accounted(u64 maxtime)
|
|
{
|
|
struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
|
|
u64 delta;
|
|
|
|
delta = min(irqtime->tick_delta, maxtime);
|
|
irqtime->tick_delta -= delta;
|
|
|
|
return delta;
|
|
}
|
|
|
|
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
|
|
|
|
#define sched_clock_irqtime (0)
|
|
|
|
static u64 irqtime_tick_accounted(u64 dummy)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */
|
|
|
|
static inline void task_group_account_field(struct task_struct *p, int index,
|
|
u64 tmp)
|
|
{
|
|
/*
|
|
* Since all updates are sure to touch the root cgroup, we
|
|
* get ourselves ahead and touch it first. If the root cgroup
|
|
* is the only cgroup, then nothing else should be necessary.
|
|
*
|
|
*/
|
|
__this_cpu_add(kernel_cpustat.cpustat[index], tmp);
|
|
|
|
cgroup_account_cputime_field(p, index, tmp);
|
|
}
|
|
|
|
/*
|
|
* Account user CPU time to a process.
|
|
* @p: the process that the CPU time gets accounted to
|
|
* @cputime: the CPU time spent in user space since the last update
|
|
*/
|
|
void account_user_time(struct task_struct *p, u64 cputime)
|
|
{
|
|
int index;
|
|
|
|
/* Add user time to process. */
|
|
p->utime += cputime;
|
|
account_group_user_time(p, cputime);
|
|
|
|
index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
|
|
|
|
/* Add user time to cpustat. */
|
|
task_group_account_field(p, index, cputime);
|
|
|
|
/* Account for user time used */
|
|
acct_account_cputime(p);
|
|
|
|
/* Account power usage for user time */
|
|
cpufreq_acct_update_power(p, cputime);
|
|
}
|
|
|
|
/*
|
|
* Account guest CPU time to a process.
|
|
* @p: the process that the CPU time gets accounted to
|
|
* @cputime: the CPU time spent in virtual machine since the last update
|
|
*/
|
|
void account_guest_time(struct task_struct *p, u64 cputime)
|
|
{
|
|
u64 *cpustat = kcpustat_this_cpu->cpustat;
|
|
|
|
/* Add guest time to process. */
|
|
p->utime += cputime;
|
|
account_group_user_time(p, cputime);
|
|
p->gtime += cputime;
|
|
|
|
/* Add guest time to cpustat. */
|
|
if (task_nice(p) > 0) {
|
|
task_group_account_field(p, CPUTIME_NICE, cputime);
|
|
cpustat[CPUTIME_GUEST_NICE] += cputime;
|
|
} else {
|
|
task_group_account_field(p, CPUTIME_USER, cputime);
|
|
cpustat[CPUTIME_GUEST] += cputime;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Account system CPU time to a process and desired cpustat field
|
|
* @p: the process that the CPU time gets accounted to
|
|
* @cputime: the CPU time spent in kernel space since the last update
|
|
* @index: pointer to cpustat field that has to be updated
|
|
*/
|
|
void account_system_index_time(struct task_struct *p,
|
|
u64 cputime, enum cpu_usage_stat index)
|
|
{
|
|
/* Add system time to process. */
|
|
p->stime += cputime;
|
|
account_group_system_time(p, cputime);
|
|
|
|
/* Add system time to cpustat. */
|
|
task_group_account_field(p, index, cputime);
|
|
|
|
/* Account for system time used */
|
|
acct_account_cputime(p);
|
|
|
|
/* Account power usage for system time */
|
|
cpufreq_acct_update_power(p, cputime);
|
|
}
|
|
|
|
/*
|
|
* Account system CPU time to a process.
|
|
* @p: the process that the CPU time gets accounted to
|
|
* @hardirq_offset: the offset to subtract from hardirq_count()
|
|
* @cputime: the CPU time spent in kernel space since the last update
|
|
*/
|
|
void account_system_time(struct task_struct *p, int hardirq_offset, u64 cputime)
|
|
{
|
|
int index;
|
|
|
|
if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
|
|
account_guest_time(p, cputime);
|
|
return;
|
|
}
|
|
|
|
if (hardirq_count() - hardirq_offset)
|
|
index = CPUTIME_IRQ;
|
|
else if (in_serving_softirq())
|
|
index = CPUTIME_SOFTIRQ;
|
|
else
|
|
index = CPUTIME_SYSTEM;
|
|
|
|
account_system_index_time(p, cputime, index);
|
|
}
|
|
|
|
/*
|
|
* Account for involuntary wait time.
|
|
* @cputime: the CPU time spent in involuntary wait
|
|
*/
|
|
void account_steal_time(u64 cputime)
|
|
{
|
|
u64 *cpustat = kcpustat_this_cpu->cpustat;
|
|
|
|
cpustat[CPUTIME_STEAL] += cputime;
|
|
}
|
|
|
|
/*
|
|
* Account for idle time.
|
|
* @cputime: the CPU time spent in idle wait
|
|
*/
|
|
void account_idle_time(u64 cputime)
|
|
{
|
|
u64 *cpustat = kcpustat_this_cpu->cpustat;
|
|
struct rq *rq = this_rq();
|
|
|
|
if (atomic_read(&rq->nr_iowait) > 0)
|
|
cpustat[CPUTIME_IOWAIT] += cputime;
|
|
else
|
|
cpustat[CPUTIME_IDLE] += cputime;
|
|
}
|
|
|
|
/*
|
|
* When a guest is interrupted for a longer amount of time, missed clock
|
|
* ticks are not redelivered later. Due to that, this function may on
|
|
* occasion account more time than the calling functions think elapsed.
|
|
*/
|
|
static __always_inline u64 steal_account_process_time(u64 maxtime)
|
|
{
|
|
#ifdef CONFIG_PARAVIRT
|
|
if (static_key_false(¶virt_steal_enabled)) {
|
|
u64 steal;
|
|
|
|
steal = paravirt_steal_clock(smp_processor_id());
|
|
steal -= this_rq()->prev_steal_time;
|
|
steal = min(steal, maxtime);
|
|
account_steal_time(steal);
|
|
this_rq()->prev_steal_time += steal;
|
|
|
|
return steal;
|
|
}
|
|
#endif
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Account how much elapsed time was spent in steal, irq, or softirq time.
|
|
*/
|
|
static inline u64 account_other_time(u64 max)
|
|
{
|
|
u64 accounted;
|
|
|
|
lockdep_assert_irqs_disabled();
|
|
|
|
accounted = steal_account_process_time(max);
|
|
|
|
if (accounted < max)
|
|
accounted += irqtime_tick_accounted(max - accounted);
|
|
|
|
return accounted;
|
|
}
|
|
|
|
#ifdef CONFIG_64BIT
|
|
static inline u64 read_sum_exec_runtime(struct task_struct *t)
|
|
{
|
|
return t->se.sum_exec_runtime;
|
|
}
|
|
#else
|
|
static u64 read_sum_exec_runtime(struct task_struct *t)
|
|
{
|
|
u64 ns;
|
|
struct rq_flags rf;
|
|
struct rq *rq;
|
|
|
|
rq = task_rq_lock(t, &rf);
|
|
ns = t->se.sum_exec_runtime;
|
|
task_rq_unlock(rq, t, &rf);
|
|
|
|
return ns;
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* Accumulate raw cputime values of dead tasks (sig->[us]time) and live
|
|
* tasks (sum on group iteration) belonging to @tsk's group.
|
|
*/
|
|
void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
|
|
{
|
|
struct signal_struct *sig = tsk->signal;
|
|
u64 utime, stime;
|
|
struct task_struct *t;
|
|
unsigned int seq, nextseq;
|
|
unsigned long flags;
|
|
|
|
/*
|
|
* Update current task runtime to account pending time since last
|
|
* scheduler action or thread_group_cputime() call. This thread group
|
|
* might have other running tasks on different CPUs, but updating
|
|
* their runtime can affect syscall performance, so we skip account
|
|
* those pending times and rely only on values updated on tick or
|
|
* other scheduler action.
|
|
*/
|
|
if (same_thread_group(current, tsk))
|
|
(void) task_sched_runtime(current);
|
|
|
|
rcu_read_lock();
|
|
/* Attempt a lockless read on the first round. */
|
|
nextseq = 0;
|
|
do {
|
|
seq = nextseq;
|
|
flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq);
|
|
times->utime = sig->utime;
|
|
times->stime = sig->stime;
|
|
times->sum_exec_runtime = sig->sum_sched_runtime;
|
|
|
|
for_each_thread(tsk, t) {
|
|
task_cputime(t, &utime, &stime);
|
|
times->utime += utime;
|
|
times->stime += stime;
|
|
times->sum_exec_runtime += read_sum_exec_runtime(t);
|
|
}
|
|
/* If lockless access failed, take the lock. */
|
|
nextseq = 1;
|
|
} while (need_seqretry(&sig->stats_lock, seq));
|
|
done_seqretry_irqrestore(&sig->stats_lock, seq, flags);
|
|
rcu_read_unlock();
|
|
}
|
|
|
|
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
|
|
/*
|
|
* Account a tick to a process and cpustat
|
|
* @p: the process that the CPU time gets accounted to
|
|
* @user_tick: is the tick from userspace
|
|
* @rq: the pointer to rq
|
|
*
|
|
* Tick demultiplexing follows the order
|
|
* - pending hardirq update
|
|
* - pending softirq update
|
|
* - user_time
|
|
* - idle_time
|
|
* - system time
|
|
* - check for guest_time
|
|
* - else account as system_time
|
|
*
|
|
* Check for hardirq is done both for system and user time as there is
|
|
* no timer going off while we are on hardirq and hence we may never get an
|
|
* opportunity to update it solely in system time.
|
|
* p->stime and friends are only updated on system time and not on irq
|
|
* softirq as those do not count in task exec_runtime any more.
|
|
*/
|
|
static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
|
|
struct rq *rq, int ticks)
|
|
{
|
|
u64 other, cputime = TICK_NSEC * ticks;
|
|
|
|
/*
|
|
* When returning from idle, many ticks can get accounted at
|
|
* once, including some ticks of steal, irq, and softirq time.
|
|
* Subtract those ticks from the amount of time accounted to
|
|
* idle, or potentially user or system time. Due to rounding,
|
|
* other time can exceed ticks occasionally.
|
|
*/
|
|
other = account_other_time(ULONG_MAX);
|
|
if (other >= cputime)
|
|
return;
|
|
|
|
cputime -= other;
|
|
|
|
if (this_cpu_ksoftirqd() == p) {
|
|
/*
|
|
* ksoftirqd time do not get accounted in cpu_softirq_time.
|
|
* So, we have to handle it separately here.
|
|
* Also, p->stime needs to be updated for ksoftirqd.
|
|
*/
|
|
account_system_index_time(p, cputime, CPUTIME_SOFTIRQ);
|
|
} else if (user_tick) {
|
|
account_user_time(p, cputime);
|
|
} else if (p == rq->idle) {
|
|
account_idle_time(cputime);
|
|
} else if (p->flags & PF_VCPU) { /* System time or guest time */
|
|
account_guest_time(p, cputime);
|
|
} else {
|
|
account_system_index_time(p, cputime, CPUTIME_SYSTEM);
|
|
}
|
|
}
|
|
|
|
static void irqtime_account_idle_ticks(int ticks)
|
|
{
|
|
struct rq *rq = this_rq();
|
|
|
|
irqtime_account_process_tick(current, 0, rq, ticks);
|
|
}
|
|
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
|
|
static inline void irqtime_account_idle_ticks(int ticks) { }
|
|
static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
|
|
struct rq *rq, int nr_ticks) { }
|
|
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
|
|
|
|
/*
|
|
* Use precise platform statistics if available:
|
|
*/
|
|
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
|
|
# ifndef __ARCH_HAS_VTIME_TASK_SWITCH
|
|
void vtime_common_task_switch(struct task_struct *prev)
|
|
{
|
|
if (is_idle_task(prev))
|
|
vtime_account_idle(prev);
|
|
else
|
|
vtime_account_system(prev);
|
|
|
|
vtime_flush(prev);
|
|
arch_vtime_task_switch(prev);
|
|
}
|
|
# endif
|
|
#endif /* CONFIG_VIRT_CPU_ACCOUNTING */
|
|
|
|
|
|
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
|
|
/*
|
|
* Archs that account the whole time spent in the idle task
|
|
* (outside irq) as idle time can rely on this and just implement
|
|
* vtime_account_system() and vtime_account_idle(). Archs that
|
|
* have other meaning of the idle time (s390 only includes the
|
|
* time spent by the CPU when it's in low power mode) must override
|
|
* vtime_account().
|
|
*/
|
|
#ifndef __ARCH_HAS_VTIME_ACCOUNT
|
|
void vtime_account_irq_enter(struct task_struct *tsk)
|
|
{
|
|
if (!in_interrupt() && is_idle_task(tsk))
|
|
vtime_account_idle(tsk);
|
|
else
|
|
vtime_account_system(tsk);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
|
|
#endif /* __ARCH_HAS_VTIME_ACCOUNT */
|
|
|
|
void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
|
|
u64 *ut, u64 *st)
|
|
{
|
|
*ut = curr->utime;
|
|
*st = curr->stime;
|
|
}
|
|
|
|
void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
|
|
{
|
|
*ut = p->utime;
|
|
*st = p->stime;
|
|
}
|
|
EXPORT_SYMBOL_GPL(task_cputime_adjusted);
|
|
|
|
void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
|
|
{
|
|
struct task_cputime cputime;
|
|
|
|
thread_group_cputime(p, &cputime);
|
|
|
|
*ut = cputime.utime;
|
|
*st = cputime.stime;
|
|
}
|
|
|
|
#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE: */
|
|
|
|
/*
|
|
* Account a single tick of CPU time.
|
|
* @p: the process that the CPU time gets accounted to
|
|
* @user_tick: indicates if the tick is a user or a system tick
|
|
*/
|
|
void account_process_tick(struct task_struct *p, int user_tick)
|
|
{
|
|
u64 cputime, steal;
|
|
struct rq *rq = this_rq();
|
|
|
|
if (vtime_accounting_cpu_enabled())
|
|
return;
|
|
|
|
if (sched_clock_irqtime) {
|
|
irqtime_account_process_tick(p, user_tick, rq, 1);
|
|
return;
|
|
}
|
|
|
|
cputime = TICK_NSEC;
|
|
steal = steal_account_process_time(ULONG_MAX);
|
|
|
|
if (steal >= cputime)
|
|
return;
|
|
|
|
cputime -= steal;
|
|
|
|
if (user_tick)
|
|
account_user_time(p, cputime);
|
|
else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
|
|
account_system_time(p, HARDIRQ_OFFSET, cputime);
|
|
else
|
|
account_idle_time(cputime);
|
|
}
|
|
|
|
/*
|
|
* Account multiple ticks of idle time.
|
|
* @ticks: number of stolen ticks
|
|
*/
|
|
void account_idle_ticks(unsigned long ticks)
|
|
{
|
|
u64 cputime, steal;
|
|
|
|
if (sched_clock_irqtime) {
|
|
irqtime_account_idle_ticks(ticks);
|
|
return;
|
|
}
|
|
|
|
cputime = ticks * TICK_NSEC;
|
|
steal = steal_account_process_time(ULONG_MAX);
|
|
|
|
if (steal >= cputime)
|
|
return;
|
|
|
|
cputime -= steal;
|
|
account_idle_time(cputime);
|
|
}
|
|
|
|
/*
|
|
* Perform (stime * rtime) / total, but avoid multiplication overflow by
|
|
* loosing precision when the numbers are big.
|
|
*/
|
|
static u64 scale_stime(u64 stime, u64 rtime, u64 total)
|
|
{
|
|
u64 scaled;
|
|
|
|
for (;;) {
|
|
/* Make sure "rtime" is the bigger of stime/rtime */
|
|
if (stime > rtime)
|
|
swap(rtime, stime);
|
|
|
|
/* Make sure 'total' fits in 32 bits */
|
|
if (total >> 32)
|
|
goto drop_precision;
|
|
|
|
/* Does rtime (and thus stime) fit in 32 bits? */
|
|
if (!(rtime >> 32))
|
|
break;
|
|
|
|
/* Can we just balance rtime/stime rather than dropping bits? */
|
|
if (stime >> 31)
|
|
goto drop_precision;
|
|
|
|
/* We can grow stime and shrink rtime and try to make them both fit */
|
|
stime <<= 1;
|
|
rtime >>= 1;
|
|
continue;
|
|
|
|
drop_precision:
|
|
/* We drop from rtime, it has more bits than stime */
|
|
rtime >>= 1;
|
|
total >>= 1;
|
|
}
|
|
|
|
/*
|
|
* Make sure gcc understands that this is a 32x32->64 multiply,
|
|
* followed by a 64/32->64 divide.
|
|
*/
|
|
scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total);
|
|
return scaled;
|
|
}
|
|
|
|
/*
|
|
* Adjust tick based cputime random precision against scheduler runtime
|
|
* accounting.
|
|
*
|
|
* Tick based cputime accounting depend on random scheduling timeslices of a
|
|
* task to be interrupted or not by the timer. Depending on these
|
|
* circumstances, the number of these interrupts may be over or
|
|
* under-optimistic, matching the real user and system cputime with a variable
|
|
* precision.
|
|
*
|
|
* Fix this by scaling these tick based values against the total runtime
|
|
* accounted by the CFS scheduler.
|
|
*
|
|
* This code provides the following guarantees:
|
|
*
|
|
* stime + utime == rtime
|
|
* stime_i+1 >= stime_i, utime_i+1 >= utime_i
|
|
*
|
|
* Assuming that rtime_i+1 >= rtime_i.
|
|
*/
|
|
void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
|
|
u64 *ut, u64 *st)
|
|
{
|
|
u64 rtime, stime, utime;
|
|
unsigned long flags;
|
|
|
|
/* Serialize concurrent callers such that we can honour our guarantees */
|
|
raw_spin_lock_irqsave(&prev->lock, flags);
|
|
rtime = curr->sum_exec_runtime;
|
|
|
|
/*
|
|
* This is possible under two circumstances:
|
|
* - rtime isn't monotonic after all (a bug);
|
|
* - we got reordered by the lock.
|
|
*
|
|
* In both cases this acts as a filter such that the rest of the code
|
|
* can assume it is monotonic regardless of anything else.
|
|
*/
|
|
if (prev->stime + prev->utime >= rtime)
|
|
goto out;
|
|
|
|
stime = curr->stime;
|
|
utime = curr->utime;
|
|
|
|
/*
|
|
* If either stime or utime are 0, assume all runtime is userspace.
|
|
* Once a task gets some ticks, the monotonicy code at 'update:'
|
|
* will ensure things converge to the observed ratio.
|
|
*/
|
|
if (stime == 0) {
|
|
utime = rtime;
|
|
goto update;
|
|
}
|
|
|
|
if (utime == 0) {
|
|
stime = rtime;
|
|
goto update;
|
|
}
|
|
|
|
stime = scale_stime(stime, rtime, stime + utime);
|
|
|
|
update:
|
|
/*
|
|
* Make sure stime doesn't go backwards; this preserves monotonicity
|
|
* for utime because rtime is monotonic.
|
|
*
|
|
* utime_i+1 = rtime_i+1 - stime_i
|
|
* = rtime_i+1 - (rtime_i - utime_i)
|
|
* = (rtime_i+1 - rtime_i) + utime_i
|
|
* >= utime_i
|
|
*/
|
|
if (stime < prev->stime)
|
|
stime = prev->stime;
|
|
utime = rtime - stime;
|
|
|
|
/*
|
|
* Make sure utime doesn't go backwards; this still preserves
|
|
* monotonicity for stime, analogous argument to above.
|
|
*/
|
|
if (utime < prev->utime) {
|
|
utime = prev->utime;
|
|
stime = rtime - utime;
|
|
}
|
|
|
|
prev->stime = stime;
|
|
prev->utime = utime;
|
|
out:
|
|
*ut = prev->utime;
|
|
*st = prev->stime;
|
|
raw_spin_unlock_irqrestore(&prev->lock, flags);
|
|
}
|
|
|
|
void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
|
|
{
|
|
struct task_cputime cputime = {
|
|
.sum_exec_runtime = p->se.sum_exec_runtime,
|
|
};
|
|
|
|
task_cputime(p, &cputime.utime, &cputime.stime);
|
|
cputime_adjust(&cputime, &p->prev_cputime, ut, st);
|
|
}
|
|
EXPORT_SYMBOL_GPL(task_cputime_adjusted);
|
|
|
|
void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
|
|
{
|
|
struct task_cputime cputime;
|
|
|
|
thread_group_cputime(p, &cputime);
|
|
cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st);
|
|
}
|
|
#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
|
|
|
|
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
|
|
static u64 vtime_delta(struct vtime *vtime)
|
|
{
|
|
unsigned long long clock;
|
|
|
|
clock = sched_clock();
|
|
if (clock < vtime->starttime)
|
|
return 0;
|
|
|
|
return clock - vtime->starttime;
|
|
}
|
|
|
|
static u64 get_vtime_delta(struct vtime *vtime)
|
|
{
|
|
u64 delta = vtime_delta(vtime);
|
|
u64 other;
|
|
|
|
/*
|
|
* Unlike tick based timing, vtime based timing never has lost
|
|
* ticks, and no need for steal time accounting to make up for
|
|
* lost ticks. Vtime accounts a rounded version of actual
|
|
* elapsed time. Limit account_other_time to prevent rounding
|
|
* errors from causing elapsed vtime to go negative.
|
|
*/
|
|
other = account_other_time(delta);
|
|
WARN_ON_ONCE(vtime->state == VTIME_INACTIVE);
|
|
vtime->starttime += delta;
|
|
|
|
return delta - other;
|
|
}
|
|
|
|
static void __vtime_account_system(struct task_struct *tsk,
|
|
struct vtime *vtime)
|
|
{
|
|
vtime->stime += get_vtime_delta(vtime);
|
|
if (vtime->stime >= TICK_NSEC) {
|
|
account_system_time(tsk, irq_count(), vtime->stime);
|
|
vtime->stime = 0;
|
|
}
|
|
}
|
|
|
|
static void vtime_account_guest(struct task_struct *tsk,
|
|
struct vtime *vtime)
|
|
{
|
|
vtime->gtime += get_vtime_delta(vtime);
|
|
if (vtime->gtime >= TICK_NSEC) {
|
|
account_guest_time(tsk, vtime->gtime);
|
|
vtime->gtime = 0;
|
|
}
|
|
}
|
|
|
|
void vtime_account_system(struct task_struct *tsk)
|
|
{
|
|
struct vtime *vtime = &tsk->vtime;
|
|
|
|
if (!vtime_delta(vtime))
|
|
return;
|
|
|
|
write_seqcount_begin(&vtime->seqcount);
|
|
/* We might have scheduled out from guest path */
|
|
if (tsk->flags & PF_VCPU)
|
|
vtime_account_guest(tsk, vtime);
|
|
else
|
|
__vtime_account_system(tsk, vtime);
|
|
write_seqcount_end(&vtime->seqcount);
|
|
}
|
|
|
|
void vtime_user_enter(struct task_struct *tsk)
|
|
{
|
|
struct vtime *vtime = &tsk->vtime;
|
|
|
|
write_seqcount_begin(&vtime->seqcount);
|
|
__vtime_account_system(tsk, vtime);
|
|
vtime->state = VTIME_USER;
|
|
write_seqcount_end(&vtime->seqcount);
|
|
}
|
|
|
|
void vtime_user_exit(struct task_struct *tsk)
|
|
{
|
|
struct vtime *vtime = &tsk->vtime;
|
|
|
|
write_seqcount_begin(&vtime->seqcount);
|
|
vtime->utime += get_vtime_delta(vtime);
|
|
if (vtime->utime >= TICK_NSEC) {
|
|
account_user_time(tsk, vtime->utime);
|
|
vtime->utime = 0;
|
|
}
|
|
vtime->state = VTIME_SYS;
|
|
write_seqcount_end(&vtime->seqcount);
|
|
}
|
|
|
|
void vtime_guest_enter(struct task_struct *tsk)
|
|
{
|
|
struct vtime *vtime = &tsk->vtime;
|
|
/*
|
|
* The flags must be updated under the lock with
|
|
* the vtime_starttime flush and update.
|
|
* That enforces a right ordering and update sequence
|
|
* synchronization against the reader (task_gtime())
|
|
* that can thus safely catch up with a tickless delta.
|
|
*/
|
|
write_seqcount_begin(&vtime->seqcount);
|
|
__vtime_account_system(tsk, vtime);
|
|
tsk->flags |= PF_VCPU;
|
|
write_seqcount_end(&vtime->seqcount);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vtime_guest_enter);
|
|
|
|
void vtime_guest_exit(struct task_struct *tsk)
|
|
{
|
|
struct vtime *vtime = &tsk->vtime;
|
|
|
|
write_seqcount_begin(&vtime->seqcount);
|
|
vtime_account_guest(tsk, vtime);
|
|
tsk->flags &= ~PF_VCPU;
|
|
write_seqcount_end(&vtime->seqcount);
|
|
}
|
|
EXPORT_SYMBOL_GPL(vtime_guest_exit);
|
|
|
|
void vtime_account_idle(struct task_struct *tsk)
|
|
{
|
|
account_idle_time(get_vtime_delta(&tsk->vtime));
|
|
}
|
|
|
|
void arch_vtime_task_switch(struct task_struct *prev)
|
|
{
|
|
struct vtime *vtime = &prev->vtime;
|
|
|
|
write_seqcount_begin(&vtime->seqcount);
|
|
vtime->state = VTIME_INACTIVE;
|
|
write_seqcount_end(&vtime->seqcount);
|
|
|
|
vtime = ¤t->vtime;
|
|
|
|
write_seqcount_begin(&vtime->seqcount);
|
|
vtime->state = VTIME_SYS;
|
|
vtime->starttime = sched_clock();
|
|
write_seqcount_end(&vtime->seqcount);
|
|
}
|
|
|
|
void vtime_init_idle(struct task_struct *t, int cpu)
|
|
{
|
|
struct vtime *vtime = &t->vtime;
|
|
unsigned long flags;
|
|
|
|
local_irq_save(flags);
|
|
write_seqcount_begin(&vtime->seqcount);
|
|
vtime->state = VTIME_SYS;
|
|
vtime->starttime = sched_clock();
|
|
write_seqcount_end(&vtime->seqcount);
|
|
local_irq_restore(flags);
|
|
}
|
|
|
|
u64 task_gtime(struct task_struct *t)
|
|
{
|
|
struct vtime *vtime = &t->vtime;
|
|
unsigned int seq;
|
|
u64 gtime;
|
|
|
|
if (!vtime_accounting_enabled())
|
|
return t->gtime;
|
|
|
|
do {
|
|
seq = read_seqcount_begin(&vtime->seqcount);
|
|
|
|
gtime = t->gtime;
|
|
if (vtime->state == VTIME_SYS && t->flags & PF_VCPU)
|
|
gtime += vtime->gtime + vtime_delta(vtime);
|
|
|
|
} while (read_seqcount_retry(&vtime->seqcount, seq));
|
|
|
|
return gtime;
|
|
}
|
|
|
|
/*
|
|
* Fetch cputime raw values from fields of task_struct and
|
|
* add up the pending nohz execution time since the last
|
|
* cputime snapshot.
|
|
*/
|
|
void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
|
|
{
|
|
struct vtime *vtime = &t->vtime;
|
|
unsigned int seq;
|
|
u64 delta;
|
|
|
|
if (!vtime_accounting_enabled()) {
|
|
*utime = t->utime;
|
|
*stime = t->stime;
|
|
return;
|
|
}
|
|
|
|
do {
|
|
seq = read_seqcount_begin(&vtime->seqcount);
|
|
|
|
*utime = t->utime;
|
|
*stime = t->stime;
|
|
|
|
/* Task is sleeping, nothing to add */
|
|
if (vtime->state == VTIME_INACTIVE || is_idle_task(t))
|
|
continue;
|
|
|
|
delta = vtime_delta(vtime);
|
|
|
|
/*
|
|
* Task runs either in user or kernel space, add pending nohz time to
|
|
* the right place.
|
|
*/
|
|
if (vtime->state == VTIME_USER || t->flags & PF_VCPU)
|
|
*utime += vtime->utime + delta;
|
|
else if (vtime->state == VTIME_SYS)
|
|
*stime += vtime->stime + delta;
|
|
} while (read_seqcount_retry(&vtime->seqcount, seq));
|
|
}
|
|
#endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */
|