The cpufreq update util calls after update_task_ravg() are
no longer needed. This is taken care in WALT when a window is
rolled over. Besides these calls were ineffectual since
SCHED_CPUFREQ_WALT wasn't passed in the flag parameter.
Change-Id: I28ac40b33662584ec9f8fff116e66a6f33a8d010
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
With commit d8c5bfcc07 ("sched: Make sure window start passed to
schedutil is consistent"), the rq->load_reported_window is presented
to the governor as the window_start marker. The rq->load_reported_window
is updated when load is reported to governor only during a window rollover.
So it should be consistent with the current window start mark. But for a
just hotplugged in CPU, the rq->load_reported_window is not updated
until the next window rollover.
If the load is reported for any other reason before the next window
rollover, the window start marker passed to the schedutil would be
stale and leads to a BUG_ON() in schedutil. The recent window start marker
is cached in WALT in walt_irq_work_lastq_ws. Use this instead of
load_reported_window to fix this problem.
The rq->window_start is cached in rq->load_reported_window to filter
the utilization updates in the same window. This is not needed since
utilization updates are not sent when SCHED_CPUFREQ_WALT flag is not
set. So kill the load_reported_window maintenance.
Change-Id: Idaefcb0b9cecb15ea436ac7a66cb6da81e3852a1
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
When SCHED_CORE_ROTATE config is enabled, the CPUs that are
eligible for isolation are kept rotated for every system
suspend and resume cycle. cluster->set_cur holds this eligible
mask. It is also reconfigured when min_cpus tunable is changed.
The CPUs that are part of this eligible mask are only isolated
in try_to_isolate(). A CPU that is part of this mask but is busy
at that time left isolated. Since the new need is same as the
last need, eval_need() does not kick core_ctl thread next time
when the CPU becomes idle. To fix this issue, kick the core_ctl
thread when there more active CPUs than currently needed. The kicks
are rate limited by an existing tunable called offline_delay_ms.
Change-Id: I9d3815c6c6bede4b93a708ae6edb15f94d296399
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
BUG() is only needed for pi case which needed
call to a rtmutex function and grab a spin_lock.
While in pi case is a simplified logic to normalize
tasks, it is safe to be called from interrupt
context.
CRs-Fixed: 2101157
Change-Id: Icdcb9356692fc30d7b5af40f816381df5b0f0d58
Signed-off-by: Maria Yu <aiquny@codeaurora.org>
* refs/heads/tmp-960923f:
Linux 4.9.89
usb: gadget: bdc: 64-bit pointer capability check
usb: dwc3: Fix GDBGFIFOSPACE_TYPE values
USB: gadget: udc: Add missing platform_device_put() on error in bdc_pci_probe()
scsi: qla2xxx: Fix extraneous ref on sp's after adapter break
btrfs: Fix use-after-free when cleaning up fs_devs with a single stale device
btrfs: alloc_chunk: fix DUP stripe size handling
scsi: sg: only check for dxfer_len greater than 256M
scsi: sg: fix static checker warning in sg_is_valid_dxfer
scsi: sg: fix SG_DXFER_FROM_DEV transfers
irqchip/gic-v3-its: Ensure nr_ites >= nr_lpis
fs/aio: Use RCU accessors for kioctx_table->table[]
fs/aio: Add explicit RCU grace period when freeing kioctx
lock_parent() needs to recheck if dentry got __dentry_kill'ed under it
fs: Teach path_connected to handle nfs filesystems with multiple roots.
drm/amdgpu/dce: Don't turn off DP sink when disconnected
drm/amdgpu: fix prime teardown order
ALSA: seq: Clear client entry before deleting else at closing
ALSA: seq: Fix possible UAF in snd_seq_check_queue()
ALSA: hda - Revert power_save option default value
ALSA: pcm: Fix UAF in snd_pcm_oss_get_formats()
parisc: Handle case where flush_cache_range is called with no context
x86/mm: Fix vmalloc_fault to use pXd_large
x86/speculation: Remove Skylake C2 from Speculation Control microcode blacklist
x86/speculation, objtool: Annotate indirect calls/jumps for objtool on 32-bit kernels
x86/vm86/32: Fix POPF emulation
selftests/x86/entry_from_vm86: Add test cases for POPF
selftests/x86: Add tests for the STR and SLDT instructions
selftests/x86: Add tests for User-Mode Instruction Prevention
selftests/x86/entry_from_vm86: Exit with 1 if we fail
x86/cpufeatures: Add Intel PCONFIG cpufeature
x86/boot/32: Fix UP boot on Quark and possibly other platforms
net: hns: Some checkpatch.pl script & warning fixes
ima: relax requiring a file signature for new files with zero length
locking/locktorture: Fix num reader/writer corner cases
rcutorture/configinit: Fix build directory error message
ipvlan: add L2 check for packets arriving via virtual devices
ASoC: nuc900: Fix a loop timeout test
mac80211: remove BUG() when interface type is invalid
mac80211_hwsim: enforce PS_MANUAL_POLL to be set after PS_ENABLED
agp/intel: Flush all chipset writes after updating the GGTT
powerpc/modules: Don't try to restore r2 after a sibling call
drm/amdkfd: Fix memory leaks in kfd topology
veth: set peer GSO values
media: cpia2: Fix a couple off by one bugs
media: vsp1: Prevent suspending and resuming DRM pipelines
scsi: dh: add new rdac devices
scsi: devinfo: apply to HP XP the same flags as Hitachi VSP
scsi: core: scsi_get_device_flags_keyed(): Always return device flags
bnxt_en: Don't print "Link speed -1 no longer supported" messages.
spi: sun6i: disable/unprepare clocks on remove
tools/usbip: fixes build with musl libc toolchain
ath10k: fix invalid STS_CAP_OFFSET_MASK
mwifiex: cfg80211: do not change virtual interface during scan processing
clk: qcom: msm8916: fix mnd_width for codec_digcodec
pwm: stmpe: Fix wrong register offset for hwpwm=2 case
scsi: ses: don't ask for diagnostic pages repeatedly during probe
ath10k: update tdls teardown state to target
power: supply: ab8500_charger: Bail out in case of error in 'ab8500_charger_init_hw_registers()'
power: supply: ab8500_charger: Fix an error handling path
leds: pm8058: Silence pointer to integer size warning
userns: Don't fail follow_automount based on s_user_ns
mtd: nand: ifc: update bufnum mask for ver >= 2.0.0
ARM: dts: omap3-n900: Fix the audio CODEC's reset pin
ARM: dts: am335x-pepper: Fix the audio CODEC's reset pin
net: thunderx: Set max queue count taking XDP_TX into account
mtd: nand: fix interpretation of NAND_CMD_NONE in nand_command[_lp]()
net: xfrm: allow clearing socket xfrm policies.
net: ieee802154: adf7242: Fix bug if defined DEBUG
test_firmware: fix setting old custom fw path back on exit
sched: Stop resched_cpu() from sending IPIs to offline CPUs
sched: Stop switched_to_rt() from sending IPIs to offline CPUs
ARM: dts: exynos: Correct Trats2 panel reset line
clk: meson: gxbb: fix wrong clock for SARADC/SANA
iwlwifi: mvm: rs: don't override the rate history in the search cycle
HID: elo: clear BTN_LEFT mapping
video/hdmi: Allow "empty" HDMI infoframes
drm/edid: set ELD connector type in drm_edid_to_eld()
mwifiex: Fix invalid port issue
perf stat: Fix bug in handling events in error state
wil6210: fix memory access violation in wil_memcpy_from/toio_32
wil6210: fix protection against connections during reset
ath10k: fix compile time sanity check for CE4 buffer size
mac80211_hwsim: use per-interface power level
Bluetooth: 6lowpan: fix delay work init in add_peer_chan()
Bluetooth: Avoid bt_accept_unlink() double unlinking
clk: qcom: msm8996: Fix the vfe1 powerdomain name
pwm: tegra: Increase precision in PWM rate calculation
kprobes/x86: Set kprobes pages read-only
kprobes/x86: Fix kprobe-booster not to boost far call instructions
ALSA: hda: Add Geminilake id to SKL_PLUS
scsi: sg: close race condition in sg_remove_sfp_usercontext()
scsi: sg: check for valid direction before starting the request
vfio/spapr_tce: Check kzalloc() return when preregistering memory
vfio/powerpc/spapr_tce: Enforce IOMMU type compatibility check
perf session: Don't rely on evlist in pipe mode
net: fec: add phy-reset-gpios PROBE_DEFER check
perf inject: Copy events when reordering events in pipe mode
drivers/perf: arm_pmu: handle no platform_device
iwlwifi: mvm: fix RX SKB header size and align it properly
perf evsel: Return exact sub event which failed with EPERM for wildcards
usb: gadget: dummy_hcd: Fix wrong power status bit clear/reset in dummy_hub_control()
usb: dwc2: Make sure we disconnect the gadget state
powerpc/nohash: Fix use of mmu_has_feature() in setup_initial_memory_limit()
md.c:didn't unlock the mddev before return EINVAL in array_size_store
md/raid6: Fix anomily when recovering a single device in RAID6.
regulator: isl9305: fix array size
v4l: vsp1: Register pipe with output WPF
v4l: vsp1: Prevent multiple streamon race commencing pipeline early
MIPS: r2-on-r6-emu: Clear BLTZALL and BGEZALL debugfs counters
MIPS: r2-on-r6-emu: Fix BLEZL and BGTZL identification
MIPS: BPF: Fix multiple problems in JIT skb access helpers.
MIPS: BPF: Quit clobbering callee saved registers in JIT code.
serial: imx: setup DCEDTE early and ensure DCD and RI irqs to be off
tty: amba-pl011: Fix spurious TX interrupts
lkdtm: turn off kcov for lkdtm_rodata_do_nothing:
coresight: Fixes coresight DT parse to get correct output port ID.
i40e: only register client on iWarp-capable devices
drm/rockchip: vop: Enable pm domain before vop_initial
drm/amdgpu: Fail fb creation from imported dma-bufs. (v2)
drm/radeon: Fail fb creation from imported dma-bufs.
video: ARM CLCD: fix dma allocation size
kvm: nVMX: Disallow userspace-injected exceptions in guest mode
kvm/svm: Setup MCG_CAP on AMD properly
iommu/iova: Fix underflow bug in __alloc_and_insert_iova_range
apparmor: Make path_max parameter readonly
qed: Correct MSI-x for storage
scsi: ses: don't get power status of SES device slot on probe
EDAC, altera: Fix peripheral warnings for Cyclone5
fm10k: correctly check if interface is removed
ALSA: firewire-digi00x: handle all MIDI messages on streaming packets
ALSA: firewire-digi00x: add support for console models of Digi00x series
IB/hfi1: Check for QSFP presence before attempting reads
ASoC: rt5677: Add OF device ID table
reiserfs: Make cancel_old_flush() reliable
ARM: dts: koelsch: Correct clock frequency of X2 DU clock input
drm: rcar-du: Handle event when disabling CRTCs
printk: Correctly handle preemption in console_unlock()
rtmutex: Fix PI chain order integrity
qed: Fix TM block ILT allocation
net/faraday: Add missing include of of.h
net: hns: Correct HNS RSS key set function
powerpc: Avoid taking a data miss on every userspace instruction miss
ARM: dts: r8a7793: Correct parent of SSI[0-9] clocks
ARM: dts: r8a7791: Correct parent of SSI[0-9] clocks
ARM: dts: r8a7790: Correct parent of SSI[0-9] clocks
ARM: dts: r7s72100: fix ethernet clock parent
NFC: pn533: change order of free_irq and dev unregistration
NFC: nfcmrvl: double free on error path
NFC: nfcmrvl: Include unaligned.h instead of access_ok.h
vxlan: vxlan dev should inherit lowerdev's gso_max_size
drm/vmwgfx: Fixes to vmwgfx_fb
braille-console: Fix value returned by _braille_console_setup
powerpc/mm/hugetlb: Filter out hugepage size not supported by page table layout
PCI: Apply Cavium ACS quirk only to CN81xx/CN83xx/CN88xx devices
bonding: refine bond_fold_stats() wrap detection
drm/ttm: never add BO that failed to validate to the LRU list
f2fs: relax node version check for victim data in gc
perf trace: Handle unpaired raw_syscalls:sys_exit event
regulator: core: Limit propagation of parent voltage count and list
blk-throttle: make sure expire time isn't too big
ARM: dts: silk: Correct clock of DU1
ARM: dts: r8a7794: Correct clock of DU1
ARM: dts: r8a7794: Add DU1 clock to device tree
ALSA: firewire-lib: add a quirk of packet without valid EOH in CIP format
mm: Fix false-positive VM_BUG_ON() in page_cache_{get,add}_speculative()
bonding: make speed, duplex setting consistent with link state
driver: (adm1275) set the m,b and R coefficients correctly for power
scsi: be2iscsi: Check tag in beiscsi_mccq_compl_wait
i40e/i40evf: Fix use after free in Rx cleanup path
perf buildid: Do not assume that readlink() returns a null terminated string
perf annotate: Fix a bug following symbolic link of a build-id file
ARM: dts: bcm2835: add index to the ethernet alias
usb: dwc3: make sure UX_EXIT_PX is cleared
dmaengine: imx-sdma: add 1ms delay to ensure SDMA channel is stopped
tcp: sysctl: Fix a race to avoid unexpected 0 window from space
spi: omap2-mcspi: poll OMAP2_MCSPI_CHSTAT_RXS for PIO transfer
ASoC: rcar: ssi: don't set SSICR.CKDV = 000 with SSIWSR.CONT
PCI: hv: Lock PCI bus on device eject
PCI: hv: Properly handle PCI bus remove
sched: act_csum: don't mangle TCP and UDP GSO packets
Input: qt1070 - add OF device ID table
sysrq: Reset the watchdog timers while displaying high-resolution timers
timers, sched_clock: Update timeout for clock wrap
media: i2c/soc_camera: fix ov6650 sensor getting wrong clock
scsi: ipr: Fix missed EH wakeup
scsi: fnic: Fix for "Number of Active IOs" in fnicstats becoming negative
x86/boot/32: Defer resyncing initial_page_table until per-cpu is set up
solo6x10: release vb2 buffers in solo_stop_streaming()
of: fix of_device_get_modalias returned length when truncating buffers
batman-adv: handle race condition for claims between gateways
zd1211rw: fix NULL-deref at probe
s390/topology: fix typo in early topology code
qed: Always publish VF link from leading hwfn
ARM: dts: Adjust moxart IRQ controller and flags
net/8021q: create device with all possible features in wanted_features
HID: clamp input to logical range if no null state
perf probe: Return errno when not hitting any event
perf probe: Fix concat_probe_trace_events
omapfb: dss: Handle return errors in dss_init_ports()
x86/mce: Init some CPU features early
netem: apply correct delay when rate throttling
net: ethernet: bgmac: Allow MAC address to be specified in DTB
ARM: bcm2835: Enable missing CMA settings for VC4 driver
usb: misc: lvs: fix race condition in disconnect handling
ath10k: fix fetching channel during potential radar detection
ath10k: disallow DFS simulation if DFS channel is not enabled
drm: Defer disabling the vblank IRQ until the next interrupt (for instant-off)
drivers: net: xgene: Fix Rx checksum validation logic
drivers: net: xgene: Fix wrong logical operation
drivers: net: phy: xgene: Fix mdio write
drivers: net: xgene: Fix hardware checksum setting
ARM: brcmstb: Enable ZONE_DMA for non 64-bit capable peripherals
perf tools: Make perf_event__synthesize_mmap_events() scale
i40e: fix ethtool to get EEPROM data from X722 interface
i40e: Acquire NVM lock before reads on all devices
eventpoll.h: fix epoll event masks
x86/mce: Handle broadcasted MCE gracefully with kexec
perf sort: Fix segfault with basic block 'cycles' sort dimension
x86/mm: Make mmap(MAP_32BIT) work correctly
selinux: check for address length in selinux_socket_bind()
PCI/MSI: Stop disabling MSI/MSI-X in pci_device_shutdown()
drm/sun4i: Fix TCON clock and regmap initialization sequence
ath10k: fix a warning during channel switch with multiple vaps
drm/sun4i: Set drm_crtc.port to the underlying TCON's output port node
drm/sun4i: Fix up error path cleanup for master bind function
arm64: dts: r8a7796: Remove unit-address and reg from integrated cache
ARM: dts: r8a7794: Remove unit-address and reg from integrated cache
ARM: dts: r8a7793: Remove unit-address and reg from integrated cache
ARM: dts: r8a7792: Remove unit-address and reg from integrated cache
ARM: dts: r8a7791: Remove unit-address and reg from integrated cache
drm: qxl: Don't alloc fbdev if emulation is not supported
HID: reject input outside logical range only if null state is set
staging: wilc1000: add check for kmalloc allocation failure.
staging: speakup: Replace BUG_ON() with WARN_ON().
perf stat: Issue a HW watchdog disable hint
Input: tsc2007 - check for presence and power down tsc2007 during probe
blkcg: fix double free of new_blkg in blkcg_init_queue
staging: android: ashmem: Fix possible deadlock in ashmem_ioctl
Conflicts:
drivers/net/wireless/ath/wil6210/main.c
drivers/usb/dwc3/core.h
Change-Id: I2d77962cfc3dbc8b051ba51bf10b577d327ffaa9
Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>
Skip the CPU selection algorithm for high wakeup rate tasks and select
the previous CPU if it is idle.
Change-Id: I99493c8c37e091c79723ee22a5230fbb6f4e33b9
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
The cycle counter read is a bit of an expensive operation and requires
locking across all CPUs in a frequency domain. Optimize this by
returning the same value if the delta between two reads is zero i.e
two reads are done in the same sched context for the same CPU.
Change-Id: I99da5a704d3652f53c8564ba7532783d3288f227
Signed-off-by: Vikram Mulukutla <markivx@codeaurora.org>
[pkondeti@codeaurora.org: limit the optimization to the
same CPU for the sched context]
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
A CPU capacity is updated in update_cpu_capacity(). This is called
when the CPU is doing load balance in the lowest level sched domain.
The load balance is disabled for the lowest level sched domain, when
there is only 1 CPU in the higher level domain. When there is only
1 CPU in the higher capacity cluster, the CPU capacity and the
root domain's max_cpu_capacity are not getting updated correctly.
Due to the above mentioned problem, a task running on the lower
capacity CPU never upmigrates to the higher capacity CPU thinking
it is running on the max capacity CPU. Fix this by forcing the
CPU capacity update from a higher level sched domain if it has
only 1 CPU.
Change-Id: Iddb900962ab988ffbd08bc92348bd491fa2002ad
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
sched_ravg_window and sysctl_sched_use_walt_cpu_util are WALT specific
tunables. These are used outside !SCHED_WALT in schedutil. Add stubs
for these to fix compilation with WALT disabled.
Change-Id: I3f61cf06a857d52da5eda1d51701ad7cc21598d3
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
sched_smp_overlap_capacity decideds the packing on the primary
cluster on a SMP system with more than 1 cluster. Currently this
threshold is defined in WALT but it is accessed outside WALT code.
Bring it out of WALT to fix compilation issue when WALT is disabled.
Change-Id: I731e736f7a3717ff9998a1d2cdbc6709f5ce1c4e
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
Mark the source/destination CPUs correctly for inter cluster
migration.
Change-Id: I771b9357d20cb0270465abd594fb94bb3669c936
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
The find_best_target() checks if packing is eligible or not on
an active CPU before selecting it as the primary candidate CPU.
The is_packing_eligible() function checks if the currently
waking task can fit on the active CPU without increasing the
OPP or not. The current implementation only works for WALT. Make
it work even when WALT is disabled.
Change-Id: Iba7a2b6aca2dd2feca6f2e910888276113969186
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
The misfit task count tracking is currently implemented only for
WALT. Refactor the mistfit task update in task_tick_fair() to
avoid accessing misfit method in task_struct when WALT is disabled.
Change-Id: I5ce1a7ed7edfe1f119e8a13b8b1fbe06ee0b5ab8
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
Currently the sched_boost is compiled only for WALT. But sched_boost
defines are accessed outside WALT in RT code. Move these definitions
outside WALT to fix compilation issues.
Change-Id: I38d006c9edb8c859aa10d0638aa271eaaa4db40d
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
A CPU is marked as reserved when a task is under active migration to
that CPU. The reserved CPUs are excluded from CPU selection in
find_best_target(). This reservation scheme is currently tied to WALT.
So add a stub function for is_reserved() to avoid compilation issue
when WALT is disabled.
Change-Id: I77c6a8fd3f24f1763fd97fce18574613e9e947ff
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
find_rtg_target() is a WALT specific function. Accessing it outside
WALT code is resulting in a compilation error. Fix this by adding
a stub for find_rtg_target().
Change-Id: Iccc2c2ef1490e66f7c33b8d6d4afda18c398d438
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
walt_cpu_high_irqload() is a WALT specific function that indicates
whether a CPU is busy with high irq load or not. This function
is called from CPU selection code which is not tied to WALT which
results in a compilation error. Fix this by adding a stub for
walt_cpu_high_irqload().
Change-Id: Ib0da7c178f90f5b48c168f2143281745297bb593
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
schedtune_attach() functionality is only needed when WALT is enabled.
Define a stub function for it when WALT is disabled.
Change-Id: I57a9543f53cdee1e5930756f3f06f47b2f88152e
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
sched_irqload() is a WALT specific function which returns the average
IRQ load on a given CPU. It is accessed in sched_cpu_util trace point
for printing the IRQ load on different CPUs evaluated in CPU selection
algorithm. This trace point is not tied to WALT, so define a stub
function for sched_irqload().
Change-Id: Ie8f5365ddd5b7a4a0dea3a190b18c54d4d3c2d4b
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
sched_task_util trace point depends on task's mark_start for
calculating the time taken for CPU selection algorithm in
select_energy_cpu_brute(). This results in a compilation error,
since the mark_start is not available when SCHED_WALT is disabled.
sched_task_util trace point is not tied to WALT. Fix this issue by
using sched_clock() instead of mark_start. The sched_clock() is
accessed only when the trace point is enabled, so there will not be
any additional overhead.
Change-Id: Ide67741a188da13911929422c0bb1b5af2d29826
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
A tasks that is not fit on its current CPU is actively migrated
to a higher capacity CPU from the scheduler tick path. Since
active migration involves stopping the currently running task
and migrating to a different CPU, it is better to do this only
if the target CPU is idle. The task does not have to necessarily
run on the lower capacity cluster until the next tick. When a
higher capacity CPU becomes idle, it can pull the misfit task
running on the lower capacity CPU.
Change-Id: Idda0bd6ac8cc4bc22f5eddc69236014d04708ecd
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
The find_best_target() selects an active CPU and an idle CPU as
two candidate CPUs. Whichever CPUs saves the most energy compared
to the previous CPU is selected finally. An idle CPU i.e no runnable
tasks but also outside c-state is a good candidate to run the
waking task since the task can run immediately and there is no
idle exit latency. Hence consider such CPU as an active CPU which
helps both power and performance.
Change-Id: I34f40c2dbca70995a8e6b4a8d5876f802bc000bc
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
Changes in 4.9.89
blkcg: fix double free of new_blkg in blkcg_init_queue
Input: tsc2007 - check for presence and power down tsc2007 during probe
perf stat: Issue a HW watchdog disable hint
staging: speakup: Replace BUG_ON() with WARN_ON().
staging: wilc1000: add check for kmalloc allocation failure.
HID: reject input outside logical range only if null state is set
drm: qxl: Don't alloc fbdev if emulation is not supported
ARM: dts: r8a7791: Remove unit-address and reg from integrated cache
ARM: dts: r8a7792: Remove unit-address and reg from integrated cache
ARM: dts: r8a7793: Remove unit-address and reg from integrated cache
ARM: dts: r8a7794: Remove unit-address and reg from integrated cache
arm64: dts: r8a7796: Remove unit-address and reg from integrated cache
drm/sun4i: Fix up error path cleanup for master bind function
drm/sun4i: Set drm_crtc.port to the underlying TCON's output port node
ath10k: fix a warning during channel switch with multiple vaps
drm/sun4i: Fix TCON clock and regmap initialization sequence
PCI/MSI: Stop disabling MSI/MSI-X in pci_device_shutdown()
selinux: check for address length in selinux_socket_bind()
x86/mm: Make mmap(MAP_32BIT) work correctly
perf sort: Fix segfault with basic block 'cycles' sort dimension
x86/mce: Handle broadcasted MCE gracefully with kexec
eventpoll.h: fix epoll event masks
i40e: Acquire NVM lock before reads on all devices
i40e: fix ethtool to get EEPROM data from X722 interface
perf tools: Make perf_event__synthesize_mmap_events() scale
ARM: brcmstb: Enable ZONE_DMA for non 64-bit capable peripherals
drivers: net: xgene: Fix hardware checksum setting
drivers: net: phy: xgene: Fix mdio write
drivers: net: xgene: Fix wrong logical operation
drivers: net: xgene: Fix Rx checksum validation logic
drm: Defer disabling the vblank IRQ until the next interrupt (for instant-off)
ath10k: disallow DFS simulation if DFS channel is not enabled
ath10k: fix fetching channel during potential radar detection
usb: misc: lvs: fix race condition in disconnect handling
ARM: bcm2835: Enable missing CMA settings for VC4 driver
net: ethernet: bgmac: Allow MAC address to be specified in DTB
netem: apply correct delay when rate throttling
x86/mce: Init some CPU features early
omapfb: dss: Handle return errors in dss_init_ports()
perf probe: Fix concat_probe_trace_events
perf probe: Return errno when not hitting any event
HID: clamp input to logical range if no null state
net/8021q: create device with all possible features in wanted_features
ARM: dts: Adjust moxart IRQ controller and flags
qed: Always publish VF link from leading hwfn
s390/topology: fix typo in early topology code
zd1211rw: fix NULL-deref at probe
batman-adv: handle race condition for claims between gateways
of: fix of_device_get_modalias returned length when truncating buffers
solo6x10: release vb2 buffers in solo_stop_streaming()
x86/boot/32: Defer resyncing initial_page_table until per-cpu is set up
scsi: fnic: Fix for "Number of Active IOs" in fnicstats becoming negative
scsi: ipr: Fix missed EH wakeup
media: i2c/soc_camera: fix ov6650 sensor getting wrong clock
timers, sched_clock: Update timeout for clock wrap
sysrq: Reset the watchdog timers while displaying high-resolution timers
Input: qt1070 - add OF device ID table
sched: act_csum: don't mangle TCP and UDP GSO packets
PCI: hv: Properly handle PCI bus remove
PCI: hv: Lock PCI bus on device eject
ASoC: rcar: ssi: don't set SSICR.CKDV = 000 with SSIWSR.CONT
spi: omap2-mcspi: poll OMAP2_MCSPI_CHSTAT_RXS for PIO transfer
tcp: sysctl: Fix a race to avoid unexpected 0 window from space
dmaengine: imx-sdma: add 1ms delay to ensure SDMA channel is stopped
usb: dwc3: make sure UX_EXIT_PX is cleared
ARM: dts: bcm2835: add index to the ethernet alias
perf annotate: Fix a bug following symbolic link of a build-id file
perf buildid: Do not assume that readlink() returns a null terminated string
i40e/i40evf: Fix use after free in Rx cleanup path
scsi: be2iscsi: Check tag in beiscsi_mccq_compl_wait
driver: (adm1275) set the m,b and R coefficients correctly for power
bonding: make speed, duplex setting consistent with link state
mm: Fix false-positive VM_BUG_ON() in page_cache_{get,add}_speculative()
ALSA: firewire-lib: add a quirk of packet without valid EOH in CIP format
ARM: dts: r8a7794: Add DU1 clock to device tree
ARM: dts: r8a7794: Correct clock of DU1
ARM: dts: silk: Correct clock of DU1
blk-throttle: make sure expire time isn't too big
regulator: core: Limit propagation of parent voltage count and list
perf trace: Handle unpaired raw_syscalls:sys_exit event
f2fs: relax node version check for victim data in gc
drm/ttm: never add BO that failed to validate to the LRU list
bonding: refine bond_fold_stats() wrap detection
PCI: Apply Cavium ACS quirk only to CN81xx/CN83xx/CN88xx devices
powerpc/mm/hugetlb: Filter out hugepage size not supported by page table layout
braille-console: Fix value returned by _braille_console_setup
drm/vmwgfx: Fixes to vmwgfx_fb
vxlan: vxlan dev should inherit lowerdev's gso_max_size
NFC: nfcmrvl: Include unaligned.h instead of access_ok.h
NFC: nfcmrvl: double free on error path
NFC: pn533: change order of free_irq and dev unregistration
ARM: dts: r7s72100: fix ethernet clock parent
ARM: dts: r8a7790: Correct parent of SSI[0-9] clocks
ARM: dts: r8a7791: Correct parent of SSI[0-9] clocks
ARM: dts: r8a7793: Correct parent of SSI[0-9] clocks
powerpc: Avoid taking a data miss on every userspace instruction miss
net: hns: Correct HNS RSS key set function
net/faraday: Add missing include of of.h
qed: Fix TM block ILT allocation
rtmutex: Fix PI chain order integrity
printk: Correctly handle preemption in console_unlock()
drm: rcar-du: Handle event when disabling CRTCs
ARM: dts: koelsch: Correct clock frequency of X2 DU clock input
reiserfs: Make cancel_old_flush() reliable
ASoC: rt5677: Add OF device ID table
IB/hfi1: Check for QSFP presence before attempting reads
ALSA: firewire-digi00x: add support for console models of Digi00x series
ALSA: firewire-digi00x: handle all MIDI messages on streaming packets
fm10k: correctly check if interface is removed
EDAC, altera: Fix peripheral warnings for Cyclone5
scsi: ses: don't get power status of SES device slot on probe
qed: Correct MSI-x for storage
apparmor: Make path_max parameter readonly
iommu/iova: Fix underflow bug in __alloc_and_insert_iova_range
kvm/svm: Setup MCG_CAP on AMD properly
kvm: nVMX: Disallow userspace-injected exceptions in guest mode
video: ARM CLCD: fix dma allocation size
drm/radeon: Fail fb creation from imported dma-bufs.
drm/amdgpu: Fail fb creation from imported dma-bufs. (v2)
drm/rockchip: vop: Enable pm domain before vop_initial
i40e: only register client on iWarp-capable devices
coresight: Fixes coresight DT parse to get correct output port ID.
lkdtm: turn off kcov for lkdtm_rodata_do_nothing:
tty: amba-pl011: Fix spurious TX interrupts
serial: imx: setup DCEDTE early and ensure DCD and RI irqs to be off
MIPS: BPF: Quit clobbering callee saved registers in JIT code.
MIPS: BPF: Fix multiple problems in JIT skb access helpers.
MIPS: r2-on-r6-emu: Fix BLEZL and BGTZL identification
MIPS: r2-on-r6-emu: Clear BLTZALL and BGEZALL debugfs counters
v4l: vsp1: Prevent multiple streamon race commencing pipeline early
v4l: vsp1: Register pipe with output WPF
regulator: isl9305: fix array size
md/raid6: Fix anomily when recovering a single device in RAID6.
md.c:didn't unlock the mddev before return EINVAL in array_size_store
powerpc/nohash: Fix use of mmu_has_feature() in setup_initial_memory_limit()
usb: dwc2: Make sure we disconnect the gadget state
usb: gadget: dummy_hcd: Fix wrong power status bit clear/reset in dummy_hub_control()
perf evsel: Return exact sub event which failed with EPERM for wildcards
iwlwifi: mvm: fix RX SKB header size and align it properly
drivers/perf: arm_pmu: handle no platform_device
perf inject: Copy events when reordering events in pipe mode
net: fec: add phy-reset-gpios PROBE_DEFER check
perf session: Don't rely on evlist in pipe mode
vfio/powerpc/spapr_tce: Enforce IOMMU type compatibility check
vfio/spapr_tce: Check kzalloc() return when preregistering memory
scsi: sg: check for valid direction before starting the request
scsi: sg: close race condition in sg_remove_sfp_usercontext()
ALSA: hda: Add Geminilake id to SKL_PLUS
kprobes/x86: Fix kprobe-booster not to boost far call instructions
kprobes/x86: Set kprobes pages read-only
pwm: tegra: Increase precision in PWM rate calculation
clk: qcom: msm8996: Fix the vfe1 powerdomain name
Bluetooth: Avoid bt_accept_unlink() double unlinking
Bluetooth: 6lowpan: fix delay work init in add_peer_chan()
mac80211_hwsim: use per-interface power level
ath10k: fix compile time sanity check for CE4 buffer size
wil6210: fix protection against connections during reset
wil6210: fix memory access violation in wil_memcpy_from/toio_32
perf stat: Fix bug in handling events in error state
mwifiex: Fix invalid port issue
drm/edid: set ELD connector type in drm_edid_to_eld()
video/hdmi: Allow "empty" HDMI infoframes
HID: elo: clear BTN_LEFT mapping
iwlwifi: mvm: rs: don't override the rate history in the search cycle
clk: meson: gxbb: fix wrong clock for SARADC/SANA
ARM: dts: exynos: Correct Trats2 panel reset line
sched: Stop switched_to_rt() from sending IPIs to offline CPUs
sched: Stop resched_cpu() from sending IPIs to offline CPUs
test_firmware: fix setting old custom fw path back on exit
net: ieee802154: adf7242: Fix bug if defined DEBUG
net: xfrm: allow clearing socket xfrm policies.
mtd: nand: fix interpretation of NAND_CMD_NONE in nand_command[_lp]()
net: thunderx: Set max queue count taking XDP_TX into account
ARM: dts: am335x-pepper: Fix the audio CODEC's reset pin
ARM: dts: omap3-n900: Fix the audio CODEC's reset pin
mtd: nand: ifc: update bufnum mask for ver >= 2.0.0
userns: Don't fail follow_automount based on s_user_ns
leds: pm8058: Silence pointer to integer size warning
power: supply: ab8500_charger: Fix an error handling path
power: supply: ab8500_charger: Bail out in case of error in 'ab8500_charger_init_hw_registers()'
ath10k: update tdls teardown state to target
scsi: ses: don't ask for diagnostic pages repeatedly during probe
pwm: stmpe: Fix wrong register offset for hwpwm=2 case
clk: qcom: msm8916: fix mnd_width for codec_digcodec
mwifiex: cfg80211: do not change virtual interface during scan processing
ath10k: fix invalid STS_CAP_OFFSET_MASK
tools/usbip: fixes build with musl libc toolchain
spi: sun6i: disable/unprepare clocks on remove
bnxt_en: Don't print "Link speed -1 no longer supported" messages.
scsi: core: scsi_get_device_flags_keyed(): Always return device flags
scsi: devinfo: apply to HP XP the same flags as Hitachi VSP
scsi: dh: add new rdac devices
media: vsp1: Prevent suspending and resuming DRM pipelines
media: cpia2: Fix a couple off by one bugs
veth: set peer GSO values
drm/amdkfd: Fix memory leaks in kfd topology
powerpc/modules: Don't try to restore r2 after a sibling call
agp/intel: Flush all chipset writes after updating the GGTT
mac80211_hwsim: enforce PS_MANUAL_POLL to be set after PS_ENABLED
mac80211: remove BUG() when interface type is invalid
ASoC: nuc900: Fix a loop timeout test
ipvlan: add L2 check for packets arriving via virtual devices
rcutorture/configinit: Fix build directory error message
locking/locktorture: Fix num reader/writer corner cases
ima: relax requiring a file signature for new files with zero length
net: hns: Some checkpatch.pl script & warning fixes
x86/boot/32: Fix UP boot on Quark and possibly other platforms
x86/cpufeatures: Add Intel PCONFIG cpufeature
selftests/x86/entry_from_vm86: Exit with 1 if we fail
selftests/x86: Add tests for User-Mode Instruction Prevention
selftests/x86: Add tests for the STR and SLDT instructions
selftests/x86/entry_from_vm86: Add test cases for POPF
x86/vm86/32: Fix POPF emulation
x86/speculation, objtool: Annotate indirect calls/jumps for objtool on 32-bit kernels
x86/speculation: Remove Skylake C2 from Speculation Control microcode blacklist
x86/mm: Fix vmalloc_fault to use pXd_large
parisc: Handle case where flush_cache_range is called with no context
ALSA: pcm: Fix UAF in snd_pcm_oss_get_formats()
ALSA: hda - Revert power_save option default value
ALSA: seq: Fix possible UAF in snd_seq_check_queue()
ALSA: seq: Clear client entry before deleting else at closing
drm/amdgpu: fix prime teardown order
drm/amdgpu/dce: Don't turn off DP sink when disconnected
fs: Teach path_connected to handle nfs filesystems with multiple roots.
lock_parent() needs to recheck if dentry got __dentry_kill'ed under it
fs/aio: Add explicit RCU grace period when freeing kioctx
fs/aio: Use RCU accessors for kioctx_table->table[]
irqchip/gic-v3-its: Ensure nr_ites >= nr_lpis
scsi: sg: fix SG_DXFER_FROM_DEV transfers
scsi: sg: fix static checker warning in sg_is_valid_dxfer
scsi: sg: only check for dxfer_len greater than 256M
btrfs: alloc_chunk: fix DUP stripe size handling
btrfs: Fix use-after-free when cleaning up fs_devs with a single stale device
scsi: qla2xxx: Fix extraneous ref on sp's after adapter break
USB: gadget: udc: Add missing platform_device_put() on error in bdc_pci_probe()
usb: dwc3: Fix GDBGFIFOSPACE_TYPE values
usb: gadget: bdc: 64-bit pointer capability check
Linux 4.9.89
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
[ Upstream commit a0982dfa03efca6c239c52cabebcea4afb93ea6b ]
The rcutorture test suite occasionally provokes a splat due to invoking
resched_cpu() on an offline CPU:
WARNING: CPU: 2 PID: 8 at /home/paulmck/public_git/linux-rcu/arch/x86/kernel/smp.c:128 native_smp_send_reschedule+0x37/0x40
Modules linked in:
CPU: 2 PID: 8 Comm: rcu_preempt Not tainted 4.14.0-rc4+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
task: ffff902ede9daf00 task.stack: ffff96c50010c000
RIP: 0010:native_smp_send_reschedule+0x37/0x40
RSP: 0018:ffff96c50010fdb8 EFLAGS: 00010096
RAX: 000000000000002e RBX: ffff902edaab4680 RCX: 0000000000000003
RDX: 0000000080000003 RSI: 0000000000000000 RDI: 00000000ffffffff
RBP: ffff96c50010fdb8 R08: 0000000000000000 R09: 0000000000000001
R10: 0000000000000000 R11: 00000000299f36ae R12: 0000000000000001
R13: ffffffff9de64240 R14: 0000000000000001 R15: ffffffff9de64240
FS: 0000000000000000(0000) GS:ffff902edfc80000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000f7d4c642 CR3: 000000001e0e2000 CR4: 00000000000006e0
Call Trace:
resched_curr+0x8f/0x1c0
resched_cpu+0x2c/0x40
rcu_implicit_dynticks_qs+0x152/0x220
force_qs_rnp+0x147/0x1d0
? sync_rcu_exp_select_cpus+0x450/0x450
rcu_gp_kthread+0x5a9/0x950
kthread+0x142/0x180
? force_qs_rnp+0x1d0/0x1d0
? kthread_create_on_node+0x40/0x40
ret_from_fork+0x27/0x40
Code: 14 01 0f 92 c0 84 c0 74 14 48 8b 05 14 4f f4 00 be fd 00 00 00 ff 90 a0 00 00 00 5d c3 89 fe 48 c7 c7 38 89 ca 9d e8 e5 56 08 00 <0f> ff 5d c3 0f 1f 44 00 00 8b 05 52 9e 37 02 85 c0 75 38 55 48
---[ end trace 26df9e5df4bba4ac ]---
This splat cannot be generated by expedited grace periods because they
always invoke resched_cpu() on the current CPU, which is good because
expedited grace periods require that resched_cpu() unconditionally
succeed. However, other parts of RCU can tolerate resched_cpu() acting
as a no-op, at least as long as it doesn't happen too often.
This commit therefore makes resched_cpu() invoke resched_curr() only if
the CPU is either online or is the current CPU.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
[ Upstream commit 2fe2582649aa2355f79acddb86bd4d6c5363eb63 ]
The rcutorture test suite occasionally provokes a splat due to invoking
rt_mutex_lock() which needs to boost the priority of a task currently
sitting on a runqueue that belongs to an offline CPU:
WARNING: CPU: 0 PID: 12 at /home/paulmck/public_git/linux-rcu/arch/x86/kernel/smp.c:128 native_smp_send_reschedule+0x37/0x40
Modules linked in:
CPU: 0 PID: 12 Comm: rcub/7 Not tainted 4.14.0-rc4+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
task: ffff9ed3de5f8cc0 task.stack: ffffbbf80012c000
RIP: 0010:native_smp_send_reschedule+0x37/0x40
RSP: 0018:ffffbbf80012fd10 EFLAGS: 00010082
RAX: 000000000000002f RBX: ffff9ed3dd9cb300 RCX: 0000000000000004
RDX: 0000000080000004 RSI: 0000000000000086 RDI: 00000000ffffffff
RBP: ffffbbf80012fd10 R08: 000000000009da7a R09: 0000000000007b9d
R10: 0000000000000001 R11: ffffffffbb57c2cd R12: 000000000000000d
R13: ffff9ed3de5f8cc0 R14: 0000000000000061 R15: ffff9ed3ded59200
FS: 0000000000000000(0000) GS:ffff9ed3dea00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00000000080686f0 CR3: 000000001b9e0000 CR4: 00000000000006f0
Call Trace:
resched_curr+0x61/0xd0
switched_to_rt+0x8f/0xa0
rt_mutex_setprio+0x25c/0x410
task_blocks_on_rt_mutex+0x1b3/0x1f0
rt_mutex_slowlock+0xa9/0x1e0
rt_mutex_lock+0x29/0x30
rcu_boost_kthread+0x127/0x3c0
kthread+0x104/0x140
? rcu_report_unblock_qs_rnp+0x90/0x90
? kthread_create_on_node+0x40/0x40
ret_from_fork+0x22/0x30
Code: f0 00 0f 92 c0 84 c0 74 14 48 8b 05 34 74 c5 00 be fd 00 00 00 ff 90 a0 00 00 00 5d c3 89 fe 48 c7 c7 a0 c6 fc b9 e8 d5 b5 06 00 <0f> ff 5d c3 0f 1f 44 00 00 8b 05 a2 d1 13 02 85 c0 75 38 55 48
But the target task's priority has already been adjusted, so the only
purpose of switched_to_rt() invoking resched_curr() is to wake up the
CPU running some task that needs to be preempted by the boosted task.
But the CPU is offline, which presumably means that the task must be
migrated to some other CPU, and that this other CPU will undertake any
needed preemption at the time of migration. Because the runqueue lock
is held when resched_curr() is invoked, we know that the boosted task
cannot go anywhere, so it is not necessary to invoke resched_curr()
in this particular case.
This commit therefore makes switched_to_rt() refrain from invoking
resched_curr() when the target CPU is offline.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
WARN_ON is used in calculating schedutil average capacity
this is called under rq->lock held, when WARN_ON is triggered
it tries to wake_up the process on the same CPU for debug
prints inturn waits for the rq->lock triggering dead lock
Update WARN_ON with BUG_ON avoiding the debug prints.
Change-Id: I8db35a2165e68765b4ab2f132a571ad00311ba25
Signed-off-by: Santosh Mardi <gsantosh@codeaurora.org>
The scheduler sends some notifications for individual CPUs. If these
events happen close to the window boundary, the window_start passed
to schedutil may go out of order.
Change-Id: Ib6338bd4bc3b1c41c424ec959056c57c0ed7507e
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
* origin/dev/msm-4.9-sched:
ARM: dts: msm: Update silver CPUs's idle cost data for SDM845v2
sched/fair: prevent possible infinite loop in sched_group_energy
sched: Update WALT stats also in boosted_cpu_util()
sched/fair: Add provision to control the spreading on SMP
sched/fair: Add EAS_USE_NEED_IDLE feature
sched/fair: Turn off FBT_STRICT_ORDER feature
sched/fair: fix incorrect CPU selection for non latency sensitive tasks
sched: Add task placement snapshot
sched/fair: select the most energy-efficient CPU candidate on wake-up
sched/fair: fix array out of bounds access in select_energy_cpu_idx()
sched/fair: use min capacity when evaluating active cpus
sched/fair: use min capacity when evaluating idle backup cpus
sched/fair: use min capacity when evaluating placement energy costs
sched/fair: introduce minimum capacity capping sched feature
arm/topology: link arch_scale_min_freq_capacity to cpufreq
arm64/topology: link arch_scale_min_freq_capacity to cpufreq
sched: add arch_scale_min_freq_capacity to track minimum capacity caps
cpufreq: add scaled minimum capacity tracking for policy changes
arm64: enable max frequency capping
arm: enable max frequency capping
cpufreq: implement max frequency capping
sched/fair: introduce an arch scaling function for max frequency capping
cpufreq: remove max frequency capping from scale_freq_capacity()
Revert "ANDROID: cpufreq: Max freq invariant scheduler load-tracking and cpu capacity support"
Revert "ANDROID: arm: Enable max freq invariant scheduler load-tracking and capacity support"
Revert "ANDROID: arm64: Enable max freq invariant scheduler load-tracking and capacity support"
sched/fair: reduce rounding errors in energy computations
sched/fair: re-factor energy_diff to use a single (extensible) energy_env
sched/fair: cleanup select_energy_cpu_brute to be more consistent
sched/fair: remove capacity tracking from energy_diff
sched/fair: remove energy_diff tracepoint in preparation to re-factoring
sched/fair: use *p to reference task_structs
sched: EAS: Fix the calculation of group util in group_idle_state()
cpufreq: Drop schedfreq governor
sched: Sync EAS codebase to android-4.9
sched: Move core_ctl callback from tick to WALT IRQ work
sched: fair: Always use energy aware wakeups
sched: Introduce new workload differentiation
sched: Introduce a different version of freq aggregation
sched: report group load to the cpufreq
sched: Start reporting top task load to cpufreq
sched: Introduce scheduler boost related placement changes
sched: Port boost setting mechanisms to EAS
sched: integrate core_ctl with EAS
sched: EAS: add infrastructure for core_ctl
sched: EAS: add core isolation support
sched: Introduce an irq_work to report WALT load
sched: introduce small wakee task on waker
sched: fair: Ignore energy-diff calculations for colocated tasks
sched: change default group upmigrate and downmigrate values
sched: EAS: colocate related threads
sched: cpufreq: Use per_cpu_ptr instead of this_cpu_ptr when reporting load
sched: cpufreq: Use sched_clock instead of rq_clock when updating schedutil
sched: cpufreq: Update cpufreq once in a WALT window
ARM: dts: msm: Add an energy model for the SDM845 CPUs
Conflicts:
kernel/sched/fair.c
Change-Id: Ieaeecb28e57955db3b13d6d9c1d81b204caf0fcf
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
There is a race between hotplug and energy_diff which might result
in endless loop in sched_group_energy. When this happens, the end
condition cannot be detected.
We can store how many CPUs we need to visit at the beginning, and
bail out of the energy calculation if we visit more cpus than expected.
Bug: 72311797 72202633
Change-Id: I8dda75468ee1570da4071cd8165ef5131a8205d8
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
Git-commit: 8a174b4749
Git-repo: https://android.googlesource.com/kernel/common/
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
The schedutil is calling twice into the scheduler while querying
the load of each CPU. The cpu_util_freq() is called first to
get the CPU un-boosted load and WALT stats. Then boosted_cpu_util()
is called to get the boosted CPU load. This results in doing the
the same calculations twice in the scheduler and printing
sched_load_to_gov trace point twice. Fix this inefficiency by
changing boosted_cpu_util() to update WALT stats along with
boosted CPU load.
Change-Id: Ia825cafca6a25c56b0edb1ae8c55e7c7277f2968
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
Spreading the tasks across CPUs in different groups/clusters
may hurt power on some SMP systems. Start spreading the tasks
only if all the CPUs in the primary group/cluster are utilized
above sched_smp_overlap_capacity threshold.
When placement boost is active, the task is placed on the
least loaded CPU across all groups/clusters.
Change-Id: I5da67ed9230f651921bd901cbcc4e0cc55064155
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
The schedtune.prefer_idle flag makes scheduler to look for an idle
CPU across all clusters. Where as the need_idle flag limits the
search to the lower capacity cluster which strikes a better
balance between power and performance compared to prefer_idle.
Add EAS_USE_NEED_IDLE feature, when enabled need_idle path is
enforced for tasks that has schedtune.prefer_idle set.
Change-Id: Ic83cd9f8bae1112efa4e62de3c60a86ba9c777d7
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
Turning off FBT_STRICT_ORDER feature selects whichever of target CPU
or backup CPU that saves the most energy. The ftrace analysis
indicate that excessive packing can be avoided by placing the
task on backup CPU when it is idle.
Change-Id: I281c599f6236aa8c9b41c56509a533048a01da91
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
The Non latency sensitive tasks CPU selection targets for an active
CPU in the little cluster. The shallowest c-state CPU is stored as
a backup. However if all CPUs in the little cluster are idle, we pick
an active CPU in the BIG cluster as the target CPU. This incorrect
choice of the target CPU may not get corrected by the
select_energy_cpu_idx() depending on the energy difference between
previous CPU and target CPU.
This can be fixed easily by maintaining the same variable that tracks
maximum capacity of the traversed CPU for both idle and active CPUs.
Change-Id: I3efb8bc82ff005383163921ef2bd39fcac4589ad
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
This snapshot is taken as of msm-4.9 'commit f85a9dec59
("sched: walt: Fix cpu_capacity_orig stuck issue")'.
Change-Id: I5bc0f0648bbab48da0f13600ea2fcbd9c1b7f0e8
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
commit 4d09122c18 ("sched: Fix spinlock recursion in sched_exit()")
moved freeing of task's current and previous window arrays outside
the rq->lock. These arrays can be accessed from another CPU in parallel
and end up using freed memory. For example,
CPU#0 CPU#1
---------------------------------- -------------------------------
sched_exit() try_to_wake_up()--> The task wakes
up on CPU#0
task_rq_lock() set_task_cpu()
fixup_busy_time() --> waiting for
CPU#0's rq->lock
task_rq_unlock() fixup_busy_time()-->lock acquired
free_task_load_ptrs()
kfree(p->ravg.curr_window_cpu) update_task_ravg()-->called on
current of CPU#0
trace_sched_update_task_ravg()
--> access freed memory
p->ravg.curr_window_cpu = NULL;
To fix this issue, window array pointers must be set to NULL before
freeing the memory. Since this happens outside the lock, memory barriers
are needed on write and read paths. A much simpler alternative would be
skipping update_task_ravg() trace point for tasks that are marked as dead.
The window stats of dead tasks are not updated any ways. While at it, skip
this trace point for newly created tasks for which also window stats are
not updated.
Change-Id: I4d7cb8a3cf7cf84270b09721140d35205643b7ab
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
Currently, we are exposing the initial_task_util tunable but not
honoring it. Fix it by using the tunable for initial load to newly
created tasks.
Since this tunable is used in end user builds, move the tunable
out of SCHED_DEBUG.
Change-Id: I17a89b7a99d43c9cc230536ad7d9238de9833473
Signed-off-by: Lingutla Chandrasekhar <clingutla@codeaurora.org>
