x86/events/amd/iommu: Fix invalid Perf result due to IOMMU PMC power-gating
On certain AMD platforms, when the IOMMU performance counter source
(csource) field is zero, power-gating for the counter is enabled, which
prevents write access and returns zero for read access.
This can cause invalid perf result especially when event multiplexing
is needed (i.e. more number of events than available counters) since
the current logic keeps track of the previously read counter value,
and subsequently re-program the counter to continue counting the event.
With power-gating enabled, we cannot gurantee successful re-programming
of the counter.
Workaround this issue by :
1. Modifying the ordering of setting/reading counters and enabing/
disabling csources to only access the counter when the csource
is set to non-zero.
2. Since AMD IOMMU PMU does not support interrupt mode, the logic
can be simplified to always start counting with value zero,
and accumulate the counter value when stopping without the need
to keep track and reprogram the counter with the previously read
counter value.
This has been tested on systems with and without power-gating.
Odin Ugedal [Sat, 1 May 2021 14:19:50 +0000 (16:19 +0200)]
sched/fair: Fix unfairness caused by missing load decay
This fixes an issue where old load on a cfs_rq is not properly decayed,
resulting in strange behavior where fairness can decrease drastically.
Real workloads with equally weighted control groups have ended up
getting a respective 99% and 1%(!!) of cpu time.
When an idle task is attached to a cfs_rq by attaching a pid to a cgroup,
the old load of the task is attached to the new cfs_rq and sched_entity by
attach_entity_cfs_rq. If the task is then moved to another cpu (and
therefore cfs_rq) before being enqueued/woken up, the load will be moved
to cfs_rq->removed from the sched_entity. Such a move will happen when
enforcing a cpuset on the task (eg. via a cgroup) that force it to move.
The load will however not be removed from the task_group itself, making
it look like there is a constant load on that cfs_rq. This causes the
vruntime of tasks on other sibling cfs_rq's to increase faster than they
are supposed to; causing severe fairness issues. If no other task is
started on the given cfs_rq, and due to the cpuset it would not happen,
this load would never be properly unloaded. With this patch the load
will be properly removed inside update_blocked_averages. This also
applies to tasks moved to the fair scheduling class and moved to another
cpu, and this path will also fix that. For fork, the entity is queued
right away, so this problem does not affect that.
This applies to cases where the new process is the first in the cfs_rq,
issue introduced 3d30544f0212 ("sched/fair: Apply more PELT fixes"), and
when there has previously been load on the cgroup but the cgroup was
removed from the leaflist due to having null PELT load, indroduced
in 039ae8bcf7a5 ("sched/fair: Fix O(nr_cgroups) in the load balancing
path").
For a simple cgroup hierarchy (as seen below) with two equally weighted
groups, that in theory should get 50/50 of cpu time each, it often leads
to a load of 60/40 or 70/30.
If the hierarchy is deeper (as seen below), while keeping cg-1 and cg-2
equally weighted, they should still get a 50/50 balance of cpu time.
This however sometimes results in a balance of 10/90 or 1/99(!!) between
the task groups.
This can be reproduced by attaching an idle process to a cgroup and
moving it to a given cpuset before it wakes up. The issue is evident in
many (if not most) container runtimes, and has been reproduced
with both crun and runc (and therefore docker and all its "derivatives"),
and with both cgroup v1 and v2.
Util-clamp places tasks in different buckets based on their clamp values
for performance reasons. However, the size of buckets is currently
computed using a rounding division, which can lead to an off-by-one
error in some configurations.
For instance, with 20 buckets, the bucket size will be 1024/20=51. A
task with a clamp of 1024 will be mapped to bucket id 1024/51=20. Sadly,
correct indexes are in range [0,19], hence leading to an out of bound
memory access.
Johannes Weiner [Mon, 3 May 2021 17:49:17 +0000 (13:49 -0400)]
psi: Fix psi state corruption when schedule() races with cgroup move
4117cebf1a9f ("psi: Optimize task switch inside shared cgroups")
introduced a race condition that corrupts internal psi state. This
manifests as kernel warnings, sometimes followed by bogusly high IO
pressure:
psi: task underflow! cpu=1 t=2 tasks=[0 0 0 0] clear=c set=0
(schedule() decreasing RUNNING and ONCPU, both of which are 0)
psi: incosistent task state! task=2412744:systemd cpu=17 psi_flags=e clear=3 set=0
(cgroup_move_task() clearing MEMSTALL and IOWAIT, but task is MEMSTALL | RUNNING | ONCPU)
What the offending commit does is batch the two psi callbacks in
schedule() to reduce the number of cgroup tree updates. When prev is
deactivated and removed from the runqueue, nothing is done in psi at
first; when the task switch completes, TSK_RUNNING and TSK_IOWAIT are
updated along with TSK_ONCPU.
However, the deactivation and the task switch inside schedule() aren't
atomic: pick_next_task() may drop the rq lock for load balancing. When
this happens, cgroup_move_task() can run after the task has been
physically dequeued, but the psi updates are still pending. Since it
looks at the task's scheduler state, it doesn't move everything to the
new cgroup that the task switch that follows is about to clear from
it. cgroup_move_task() will leak the TSK_RUNNING count in the old
cgroup, and psi_sched_switch() will underflow it in the new cgroup.
A similar thing can happen for iowait. TSK_IOWAIT is usually set when
a p->in_iowait task is dequeued, but again this update is deferred to
the switch. cgroup_move_task() can see an unqueued p->in_iowait task
and move a non-existent TSK_IOWAIT. This results in the inconsistent
task state warning, as well as a counter underflow that will result in
permanent IO ghost pressure being reported.
Fix this bug by making cgroup_move_task() use task->psi_flags instead
of looking at the potentially mismatching scheduler state.
[ We used the scheduler state historically in order to not rely on
task->psi_flags for anything but debugging. But that ship has sailed
anyway, and this is simpler and more robust.
We previously already batched TSK_ONCPU clearing with the
TSK_RUNNING update inside the deactivation call from schedule(). But
that ordering was safe and didn't result in TSK_ONCPU corruption:
unlike most places in the scheduler, cgroup_move_task() only checked
task_current() and handled TSK_ONCPU if the task was still queued. ]
Shaokun Zhang [Thu, 6 May 2021 05:54:22 +0000 (13:54 +0800)]
arm64: kernel: Update the stale comment
Commit af391b15f7b5 ("arm64: kernel: rename __cpu_suspend to keep it aligned with arm")
has used @index instead of @arg, but the comment is stale, update it.
Hui Wang [Tue, 4 May 2021 07:39:17 +0000 (15:39 +0800)]
ALSA: hda: generic: change the DAC ctl name for LO+SPK or LO+HP
Without this change, the DAC ctl's name could be changed only when
the machine has both Speaker and Headphone, but we met some machines
which only has Lineout and Headhpone, and the Lineout and Headphone
share the Audio Mixer0 and DAC0, the ctl's name is set to "Front".
On most of machines, the "Front" is used for Speaker only or Lineout
only, but on this machine it is shared by Lineout and Headphone,
This introduces an issue in the pipewire and pulseaudio, suppose users
want the Headphone to be on and the Speaker/Lineout to be off, they
could turn off the "Front", this works on most of the machines, but on
this machine, the "Front" couldn't be turned off otherwise the
headphone will be off too. Here we do some change to let the ctl's
name change to "Headphone+LO" on this machine, and pipewire and
pulseaudio already could handle "Headphone+LO" and "Speaker+LO".
(https://gitlab.freedesktop.org/pipewire/pipewire/-/issues/747)
The m_can_start_xmit() function checks if the cdev->tx_skb is NULL and
returns with NETDEV_TX_BUSY in case tx_sbk is not NULL.
There is a race condition in the m_can_tx_work_queue(), where first
the skb is send to the driver and then the case tx_sbk is set to NULL.
A TX complete IRQ might come in between and wake the queue, which
results in tx_skb not being cleared yet.
Fixes: f524f829b75a ("can: m_can: Create a m_can platform framework") Tested-by: Torin Cooper-Bennun <[email protected]> Signed-off-by: Marc Kleine-Budde <[email protected]>
can: mcp251x: fix resume from sleep before interface was brought up
Since 8ce8c0abcba3 the driver queues work via priv->restart_work when
resuming after suspend, even when the interface was not previously
enabled. This causes a null dereference error as the workqueue is only
allocated and initialized in mcp251x_open().
To fix this we move the workqueue init to mcp251x_can_probe() as there
is no reason to do it later and repeat it whenever mcp251x_open() is
called.
Dan Carpenter [Mon, 3 May 2021 14:49:09 +0000 (17:49 +0300)]
can: mcp251xfd: mcp251xfd_probe(): fix an error pointer dereference in probe
When we converted this code to use dev_err_probe() we accidentally
removed a return. It means that if devm_clk_get() it will lead to an
Oops when we call clk_get_rate() on the next line.
drm/amdgpu: Use device specific BO size & stride check.
The builtin size check isn't really the right thing for AMD
modifiers due to a couple of reasons:
1) In the format structs we don't do set any of the tilesize / blocks
etc. to avoid having format arrays per modifier/GPU
2) The pitch on the main plane is pixel_pitch * bytes_per_pixel even
for tiled ...
3) The pitch for the DCC planes is really the pixel pitch of the main
surface that would be covered by it ...
Note that we only handle GFX9+ case but we do this after converting
the implicit modifier to an explicit modifier, so on GFX9+ all
framebuffers should be checked here.
There is a TODO about DCC alignment, but it isn't worse than before
and I'd need to dig a bunch into the specifics. Getting this out in
a reasonable timeframe to make sure it gets the appropriate testing
seemed more important.
Finally as I've found that debugging addfb2 failures is a pita I was
generous adding explicit error messages to every failure case.
Fixes: f258907fdd83 ("drm/amdgpu: Verify bo size can fit framebuffer size on init.") Tested-by: Simon Ser <[email protected]> Signed-off-by: Bas Nieuwenhuizen <[email protected]> Signed-off-by: Alex Deucher <[email protected]>
x86/process: setup io_threads more like normal user space threads
As io_threads are fully set up USER threads it's clearer to separate the
code path from the KTHREAD logic.
The only remaining difference to user space threads is that io_threads
never return to user space again. Instead they loop within the given
worker function.
The fact that they never return to user space means they don't have an
user space thread stack. In order to indicate that to tools like gdb we
reset the stack and instruction pointers to 0.
This allows gdb attach to user space processes using io-uring, which like
means that they have io_threads, without printing worrying message like
this:
warning: Selected architecture i386:x86-64 is not compatible with reported target architecture i386
netfilter: remove BUG_ON() after skb_header_pointer()
Several conntrack helpers and the TCP tracker assume that
skb_header_pointer() never fails based on upfront header validation.
Even if this should not ever happen, BUG_ON() is a too drastic measure,
remove them.
KVM: x86: Consolidate guest enter/exit logic to common helpers
Move the enter/exit logic in {svm,vmx}_vcpu_enter_exit() to common
helpers. Opportunistically update the somewhat stale comment about the
updates needing to occur immediately after VM-Exit.
context_tracking: KVM: Move guest enter/exit wrappers to KVM's domain
Move the guest enter/exit wrappers to kvm_host.h so that KVM can manage
its context tracking vs. vtime accounting without bleeding too many KVM
details into the context tracking code.
Consolidate the guest enter/exit wrappers, providing and tweaking stubs
as needed. This will allow moving the wrappers under KVM without having
to bleed #ifdefs into the soon-to-be KVM code.
sched/vtime: Move guest enter/exit vtime accounting to vtime.h
Provide separate helpers for guest enter vtime accounting (in addition to
the existing guest exit helpers), and move all vtime accounting helpers
to vtime.h where the existing #ifdef infrastructure can be leveraged to
better delineate the different types of accounting. This will also allow
future cleanups via deduplication of context tracking code.
Opportunstically delete the vtime_account_kernel() stub now that all
callers are wrapped with CONFIG_VIRT_CPU_ACCOUNTING_NATIVE=y.
Move the blob of external declarations (and their stubs) above the set of
inline definitions (and their stubs) for vtime accounting. This will
allow a future patch to bring in more inline definitions without also
having to shuffle large chunks of code.
Wanpeng Li [Wed, 5 May 2021 00:27:30 +0000 (17:27 -0700)]
KVM: x86: Defer vtime accounting 'til after IRQ handling
Defer the call to account guest time until after servicing any IRQ(s)
that happened in the guest or immediately after VM-Exit. Tick-based
accounting of vCPU time relies on PF_VCPU being set when the tick IRQ
handler runs, and IRQs are blocked throughout the main sequence of
vcpu_enter_guest(), including the call into vendor code to actually
enter and exit the guest.
This fixes a bug where reported guest time remains '0', even when
running an infinite loop in the guest:
Wanpeng Li [Wed, 5 May 2021 00:27:29 +0000 (17:27 -0700)]
context_tracking: Move guest exit vtime accounting to separate helpers
Provide separate vtime accounting functions for guest exit instead of
open coding the logic within the context tracking code. This will allow
KVM x86 to handle vtime accounting slightly differently when using
tick-based accounting.
Wanpeng Li [Wed, 5 May 2021 00:27:28 +0000 (17:27 -0700)]
context_tracking: Move guest exit context tracking to separate helpers
Provide separate context tracking helpers for guest exit, the standalone
helpers will be called separately by KVM x86 in later patches to fix
tick-based accounting.
Lai Jiangshan [Tue, 4 May 2021 19:50:14 +0000 (21:50 +0200)]
KVM/VMX: Invoke NMI non-IST entry instead of IST entry
In VMX, the host NMI handler needs to be invoked after NMI VM-Exit.
Before commit 1a5488ef0dcf6 ("KVM: VMX: Invoke NMI handler via indirect
call instead of INTn"), this was done by INTn ("int $2"). But INTn
microcode is relatively expensive, so the commit reworked NMI VM-Exit
handling to invoke the kernel handler by function call.
But this missed a detail. The NMI entry point for direct invocation is
fetched from the IDT table and called on the kernel stack. But on 64-bit
the NMI entry installed in the IDT expects to be invoked on the IST stack.
It relies on the "NMI executing" variable on the IST stack to work
correctly, which is at a fixed position in the IST stack. When the entry
point is unexpectedly called on the kernel stack, the RSP-addressed "NMI
executing" variable is obviously also on the kernel stack and is
"uninitialized" and can cause the NMI entry code to run in the wrong way.
Provide a non-ist entry point for VMX which shares the C-function with
the regular NMI entry and invoke the new asm entry point instead.
On 32-bit this just maps to the regular NMI entry point as 32-bit has no
ISTs and is not affected.
[ tglx: Made it independent for backporting, massaged changelog ]
Linus Torvalds [Wed, 5 May 2021 20:50:15 +0000 (13:50 -0700)]
Merge branch 'akpm' (patches from Andrew)
Merge more updates from Andrew Morton:
"The remainder of the main mm/ queue.
143 patches.
Subsystems affected by this patch series (all mm): pagecache, hugetlb,
userfaultfd, vmscan, compaction, migration, cma, ksm, vmstat, mmap,
kconfig, util, memory-hotplug, zswap, zsmalloc, highmem, cleanups, and
kfence"
* emailed patches from Andrew Morton <[email protected]>: (143 commits)
kfence: use power-efficient work queue to run delayed work
kfence: maximize allocation wait timeout duration
kfence: await for allocation using wait_event
kfence: zero guard page after out-of-bounds access
mm/process_vm_access.c: remove duplicate include
mm/mempool: minor coding style tweaks
mm/highmem.c: fix coding style issue
btrfs: use memzero_page() instead of open coded kmap pattern
iov_iter: lift memzero_page() to highmem.h
mm/zsmalloc: use BUG_ON instead of if condition followed by BUG.
mm/zswap.c: switch from strlcpy to strscpy
arm64/Kconfig: introduce ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
x86/Kconfig: introduce ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
mm,memory_hotplug: add kernel boot option to enable memmap_on_memory
acpi,memhotplug: enable MHP_MEMMAP_ON_MEMORY when supported
mm,memory_hotplug: allocate memmap from the added memory range
mm,memory_hotplug: factor out adjusting present pages into adjust_present_page_count()
mm,memory_hotplug: relax fully spanned sections check
drivers/base/memory: introduce memory_block_{online,offline}
mm/memory_hotplug: remove broken locking of zone PCP structures during hot remove
...
Linus Torvalds [Wed, 5 May 2021 20:44:19 +0000 (13:44 -0700)]
Merge tag 'nfsd-5.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux
Pull more nfsd updates from Chuck Lever:
"Additional fixes and clean-ups for NFSD since tags/nfsd-5.13,
including a fix to grant read delegations for files open for writing"
* tag 'nfsd-5.13-1' of git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux:
SUNRPC: Fix null pointer dereference in svc_rqst_free()
SUNRPC: fix ternary sign expansion bug in tracing
nfsd: Fix fall-through warnings for Clang
nfsd: grant read delegations to clients holding writes
nfsd: reshuffle some code
nfsd: track filehandle aliasing in nfs4_files
nfsd: hash nfs4_files by inode number
nfsd: ensure new clients break delegations
nfsd: removed unused argument in nfsd_startup_generic()
nfsd: remove unused function
svcrdma: Pass a useful error code to the send_err tracepoint
svcrdma: Rename goto labels in svc_rdma_sendto()
svcrdma: Don't leak send_ctxt on Send errors
Linus Torvalds [Wed, 5 May 2021 20:37:07 +0000 (13:37 -0700)]
Merge tag '5.13-rc-smb3-part2' of git://git.samba.org/sfrench/cifs-2.6
Pull cifs updates from Steve French:
"Ten CIFS/SMB3 changes - including two marked for stable - including
some important multichannel fixes, as well as support for handle
leases (deferred close) and shutdown support:
- some important multichannel fixes
- support for handle leases (deferred close)
- shutdown support (which is also helpful since it enables multiple
xfstests)
- enable negotiating stronger encryption by default (GCM256)
- improve wireshark debugging by allowing more options for root to
dump decryption keys
SambaXP and the SMB3 Plugfest test event are going on now so I am
expecting more patches over the next few days due to extra testing
(including more multichannel fixes)"
* tag '5.13-rc-smb3-part2' of git://git.samba.org/sfrench/cifs-2.6:
fs/cifs: Fix resource leak
Cifs: Fix kernel oops caused by deferred close for files.
cifs: fix regression when mounting shares with prefix paths
cifs: use echo_interval even when connection not ready.
cifs: detect dead connections only when echoes are enabled.
smb3.1.1: allow dumping keys for multiuser mounts
smb3.1.1: allow dumping GCM256 keys to improve debugging of encrypted shares
cifs: add shutdown support
cifs: Deferred close for files
smb3.1.1: enable negotiating stronger encryption by default
Linus Torvalds [Wed, 5 May 2021 20:31:39 +0000 (13:31 -0700)]
Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost
Pull virtio updates from Michael Tsirkin:
"A bunch of new drivers including vdpa support for block and
virtio-vdpa.
Beginning of vq kick (aka doorbell) mapping support.
Misc fixes"
* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (40 commits)
virtio_pci_modern: correct sparse tags for notify
virtio_pci_modern: __force cast the notify mapping
vDPA/ifcvf: get_config_size should return dev specific config size
vDPA/ifcvf: enable Intel C5000X-PL virtio-block for vDPA
vDPA/ifcvf: deduce VIRTIO device ID when probe
vdpa_sim_blk: add support for vdpa management tool
vdpa_sim_blk: handle VIRTIO_BLK_T_GET_ID
vdpa_sim_blk: implement ramdisk behaviour
vdpa: add vdpa simulator for block device
vhost/vdpa: Remove the restriction that only supports virtio-net devices
vhost/vdpa: use get_config_size callback in vhost_vdpa_config_validate()
vdpa: add get_config_size callback in vdpa_config_ops
vdpa_sim: cleanup kiovs in vdpasim_free()
vringh: add vringh_kiov_length() helper
vringh: implement vringh_kiov_advance()
vringh: explain more about cleaning riov and wiov
vringh: reset kiov 'consumed' field in __vringh_iov()
vringh: add 'iotlb_lock' to synchronize iotlb accesses
vdpa_sim: use iova module to allocate IOVA addresses
vDPA/ifcvf: deduce VIRTIO device ID from pdev ids
...
Power management:
- Fix acpi_pci_set_power_state() debug message (Rafael J. Wysocki)
- Fix runtime PM imbalance (Dinghao Liu)
Virtualization:
- Increase delay after FLR to work around Intel DC P4510 NVMe erratum
(Raphael Norwitz)
MSI:
- Convert rcar, tegra, xilinx to MSI domains (Marc Zyngier)
- For rcar, xilinx, use controller address as MSI doorbell (Marc
Zyngier)
- Remove unused hv msi_controller struct (Marc Zyngier)
- Remove unused PCI core msi_controller support (Marc Zyngier)
- Remove struct msi_controller altogether (Marc Zyngier)
- Remove unused default_teardown_msi_irqs() (Marc Zyngier)
- Let host bridges declare their reliance on MSI domains (Marc
Zyngier)
- Make pci_host_common_probe() declare its reliance on MSI domains
(Marc Zyngier)
- Advertise mediatek lack of built-in MSI handling (Thomas Gleixner)
- Document ways of ending up with NO_MSI (Marc Zyngier)
- Refactor HT advertising of NO_MSI flag (Marc Zyngier)
VPD:
- Remove obsolete Broadcom NIC VPD length-limiting quirk (Heiner
Kallweit)
- Remove sysfs VPD size checking dead code (Heiner Kallweit)
- Convert VPF sysfs file to static attribute (Heiner Kallweit)
- Remove unnecessary pci_set_vpd_size() (Heiner Kallweit)
- Tone down "missing VPD" message (Heiner Kallweit)
Endpoint framework:
- Fix NULL pointer dereference when epc_features not implemented
(Shradha Todi)
- Add missing destroy_workqueue() in endpoint test (Yang Yingliang)
Amazon Annapurna Labs PCIe controller driver:
- Fix compile testing without CONFIG_PCI_ECAM (Arnd Bergmann)
- Fix "no symbols" warnings when compile testing with
CONFIG_TRIM_UNUSED_KSYMS (Arnd Bergmann)
Intel VMD host bridge driver:
- Program IRTE with Requester ID of VMD endpoint, not child device
(Jon Derrick)
- Disable VMD MSI-X remapping when possible so children can use more
MSI-X vectors (Jon Derrick)
MediaTek PCIe controller driver:
- Configure FC and FTS for functions other than 0 (Ryder Lee)
- Add YAML schema for MediaTek (Jianjun Wang)
- Export pci_pio_to_address() for module use (Jianjun Wang)
- Add MediaTek MT8192 PCIe controller driver (Jianjun Wang)
- Add MediaTek MT8192 INTx support (Jianjun Wang)
- Add MediaTek MT8192 MSI support (Jianjun Wang)
- Add MediaTek MT8192 system power management support (Jianjun Wang)
- Add missing MODULE_DEVICE_TABLE (Qiheng Lin)
Microchip PolarFlare PCIe controller driver:
- Make several symbols static (Wei Yongjun)
NVIDIA Tegra PCIe controller driver:
- Add MCFG quirks for Tegra194 ECAM errata (Vidya Sagar)
- Make several symbols const (Rikard Falkeborn)
- Fix Kconfig host/endpoint typo (Wesley Sheng)
SiFive FU740 PCIe controller driver:
- Add pcie_aux clock to prci driver (Greentime Hu)
- Use reset-simple in prci driver for PCIe (Greentime Hu)
- Add SiFive FU740 PCIe host controller driver and DT binding (Paul
Walmsley, Greentime Hu)
Synopsys DesignWare PCIe controller driver:
- Move MSI Receiver init to dw_pcie_host_init() so it is
re-initialized along with the RC in resume (Jisheng Zhang)
- Move iATU detection earlier to fix regression (Hou Zhiqiang)
TI J721E PCIe driver:
- Add DT binding and TI j721e support for refclk to PCIe connector
(Kishon Vijay Abraham I)
- Add host mode and endpoint mode DT bindings for TI AM64 SoC (Kishon
Vijay Abraham I)
TI Keystone PCIe controller driver:
- Use generic config accessors for TI AM65x (K3) to fix regression
(Kishon Vijay Abraham I)
Xilinx NWL PCIe controller driver:
- Add support for coherent PCIe DMA traffic using CCI (Bharat Kumar
Gogada)
- Add optional "dma-coherent" DT property (Bharat Kumar Gogada)
Linus Torvalds [Wed, 5 May 2021 19:53:16 +0000 (12:53 -0700)]
Merge tag 'pwm/for-5.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/thierry.reding/linux-pwm
Pull pwm updates from Thierry Reding:
"This adds support for the PWM controller found on Toshiba Visconti
SoCs and converts a couple of drivers to the atomic API.
There's also a bunch of cleanups and minor fixes across the board"
* tag 'pwm/for-5.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/thierry.reding/linux-pwm: (35 commits)
pwm: Reword docs about pwm_apply_state()
pwm: atmel: Improve duty cycle calculation in .apply()
pwm: atmel: Fix duty cycle calculation in .get_state()
pwm: visconti: Add Toshiba Visconti SoC PWM support
dt-bindings: pwm: Add bindings for Toshiba Visconti PWM Controller
arm64: dts: rockchip: Remove clock-names from PWM nodes
ARM: dts: rockchip: Remove clock-names from PWM nodes
dt-bindings: pwm: rockchip: Add more compatible strings
dt-bindings: pwm: Convert pwm-rockchip.txt to YAML
pwm: mediatek: Remove unused function
pwm: pca9685: Improve runtime PM behavior
pwm: pca9685: Support hardware readout
pwm: pca9685: Switch to atomic API
pwm: lpss: Don't modify HW state in .remove callback
pwm: sti: Free resources only after pwmchip_remove()
pwm: sti: Don't modify HW state in .remove callback
pwm: lpc3200: Don't modify HW state in .remove callback
pwm: lpc18xx-sct: Free resources only after pwmchip_remove()
pwm: bcm-kona: Don't modify HW state in .remove callback
pwm: bcm2835: Free resources only after pwmchip_remove()
...
Cong Wang [Wed, 5 May 2021 19:40:48 +0000 (12:40 -0700)]
smc: disallow TCP_ULP in smc_setsockopt()
syzbot is able to setup kTLS on an SMC socket which coincidentally
uses sk_user_data too. Later, kTLS treats it as psock so triggers a
refcnt warning. The root cause is that smc_setsockopt() simply calls
TCP setsockopt() which includes TCP_ULP. I do not think it makes
sense to setup kTLS on top of SMC sockets, so we should just disallow
this setup.
It is hard to find a commit to blame, but we can apply this patch
since the beginning of TCP_ULP.
x86/cpu: Remove write_tsc() and write_rdtscp_aux() wrappers
Drop write_tsc() and write_rdtscp_aux(); the former has no users, and the
latter has only a single user and is slightly misleading since the only
in-kernel consumer of MSR_TSC_AUX is RDPID, not RDTSCP.
x86/cpu: Initialize MSR_TSC_AUX if RDTSCP *or* RDPID is supported
Initialize MSR_TSC_AUX with CPU node information if RDTSCP or RDPID is
supported. This fixes a bug where vdso_read_cpunode() will read garbage
via RDPID if RDPID is supported but RDTSCP is not. While no known CPU
supports RDPID but not RDTSCP, both Intel's SDM and AMD's APM allow for
RDPID to exist without RDTSCP, e.g. it's technically a legal CPU model
for a virtual machine.
Note, technically MSR_TSC_AUX could be initialized if and only if RDPID
is supported since RDTSCP is currently not used to retrieve the CPU node.
But, the cost of the superfluous WRMSR is negigible, whereas leaving
MSR_TSC_AUX uninitialized is just asking for future breakage if someone
decides to utilize RDTSCP.
- Fix memory leak and use after free errors in the core code (Daniel
Lezcano)
- Add the MDM9607 compatible bindings (Konrad Dybcio)
- Fix trivial spello in the copyright name for Hisilicon (Hao Fang)
- Fix negative index array access when converting the frequency to
power in the energy model (Brian-sy Yang)
- Add support for Gen2 new PMIC support for Qcom SPMI (David Collins)
- Update maintainer file for CPU cooling device section (Lukasz Luba)
- Fix missing put_device on error in the Qcom tsens driver (Guangqing
Zhu)
- Add compatible DT binding for sm8350 (Robert Foss)
- Add support for the MDM9607's tsens driver (Konrad Dybcio)
- Remove duplicate error messages in thermal_mmio and the bcm2835
driver (Ruiqi Gong)
- Add the Thermal Temperature Cooling driver (Zhang Rui)
- Remove duplicate error messages in the Hisilicon sensor driver (Ye
Bin)
- Use the devm_platform_ioremap_resource_byname() function instead of a
couple of corresponding calls (dingsenjie)
- Sort the headers alphabetically in the ti-bandgap driver (Zhen Lei)
- Add missing property in the DT thermal sensor binding (Rafał Miłecki)
- Remove dead code in the ti-bandgap sensor driver (Lin Ruizhe)
- Convert the BRCM DT bindings to the yaml schema (Rafał Miłecki)
- Replace the thermal_notify_framework() call by a call to the
thermal_zone_device_update() function. Remove the function as well as
the corresponding documentation (Thara Gopinath)
- Add support for the ipq8064-tsens sensor along with a set of cleanups
and code preparation (Ansuel Smith)
- Add a lockless __thermal_cdev_update() function to improve the
locking scheme in the core code and governors (Lukasz Luba)
- Remove unneeded variable initialization (Colin Ian King)
* tag 'thermal-v5.13-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/thermal/linux: (55 commits)
thermal/drivers/mtk_thermal: Remove redundant initializations of several variables
thermal/core/power allocator: Use the lockless __thermal_cdev_update() function
thermal/core/fair share: Use the lockless __thermal_cdev_update() function
thermal/core/fair share: Lock the thermal zone while looping over instances
thermal/core/power_allocator: Update once cooling devices when temp is low
thermal/core/power_allocator: Maintain the device statistics from going stale
thermal/core: Create a helper __thermal_cdev_update() without a lock
dt-bindings: thermal: tsens: Document ipq8064 bindings
thermal/drivers/tsens: Add support for ipq8064-tsens
thermal/drivers/tsens: Drop unused define for msm8960
thermal/drivers/tsens: Replace custom 8960 apis with generic apis
thermal/drivers/tsens: Fix bug in sensor enable for msm8960
thermal/drivers/tsens: Use init_common for msm8960
thermal/drivers/tsens: Add VER_0 tsens version
thermal/drivers/tsens: Convert msm8960 to reg_field
thermal/drivers/tsens: Don't hardcode sensor slope
Documentation: driver-api: thermal: Remove thermal_notify_framework from documentation
thermal/core: Remove thermal_notify_framework
iwlwifi: mvm: tt: Replace thermal_notify_framework
dt-bindings: thermal: brcm,ns-thermal: Convert to the json-schema
...
Íñigo Huguet [Wed, 5 May 2021 12:54:50 +0000 (14:54 +0200)]
net:CXGB4: fix leak if sk_buff is not used
An sk_buff is allocated to send a flow control message, but it's not
sent in all cases: in case the state is not appropiate to send it or if
it can't be enqueued.
In the first of these 2 cases, the sk_buff was discarded but not freed,
producing a memory leak.
ethtool: fix missing NLM_F_MULTI flag when dumping
When dumping the ethtool information from all the interfaces, the
netlink reply should contain the NLM_F_MULTI flag. This flag allows
userspace tools to identify that multiple messages are expected.
Linus Torvalds [Wed, 5 May 2021 19:39:29 +0000 (12:39 -0700)]
Merge tag 'gpio-updates-for-v5.13-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux
Pull gpio updates from Bartosz Golaszewski:
- new driver for the Realtek Otto GPIO controller
- ACPI support for gpio-mpc8xxx
- edge event support for gpio-sch (+ Kconfig fixes)
- Kconfig improvements in gpio-ich
- fixes to older issues in gpio-mockup
- ACPI quirk for ignoring EC wakeups on Dell Venue 10 Pro 5055
- improve the GPIO aggregator code by using more generic interfaces
instead of reimplementing them in the driver
- convert the DT bindings for gpio-74x164 to yaml
- documentation improvements
- a slew of other minor fixes and improvements to GPIO drivers
* tag 'gpio-updates-for-v5.13-v2' of git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux: (34 commits)
dt-bindings: gpio: add YAML description for rockchip,gpio-bank
gpio: mxs: remove useless function
dt-bindings: gpio: fairchild,74hc595: Convert to json-schema
gpio: it87: remove unused code
gpio: 104-dio-48e: Fix coding style issues
gpio: mpc8xxx: Add ACPI support
gpio: ich: Switch to be dependent on LPC_ICH
gpio: sch: Drop MFD_CORE selection
gpio: sch: depends on LPC_SCH
gpiolib: acpi: Add quirk to ignore EC wakeups on Dell Venue 10 Pro 5055
gpio: sch: Hook into ACPI GPE handler to catch GPIO edge events
gpio: sch: Add edge event support
gpio: aggregator: Replace custom get_arg() with a generic next_arg()
lib/cmdline: Export next_arg() for being used in modules
gpio: omap: Use device_get_match_data() helper
gpio: Add Realtek Otto GPIO support
dt-bindings: gpio: Binding for Realtek Otto GPIO
docs: kernel-parameters: Add gpio_mockup_named_lines
docs: kernel-parameters: Move gpio-mockup for alphabetic order
lib: bitmap: provide devm_bitmap_alloc() and devm_bitmap_zalloc()
...
Linus Torvalds [Wed, 5 May 2021 19:29:37 +0000 (12:29 -0700)]
Merge tag 'char-misc-5.13-rc1-round2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc
Pull char/misc driver fixes from Greg KH:
"Here are two char/misc fixes for 5.13-rc1 to resolve reported issues.
The first is a bugfix for the nitro_enclaves driver that fixed some
important problems. The second was a dyndbg bugfix that resolved some
reported problems in dynamic debugging control.
Both have been in linux-next for a while with no reported issues"
* tag 'char-misc-5.13-rc1-round2' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc:
dyndbg: fix parsing file query without a line-range suffix
nitro_enclaves: Fix stale file descriptors on failed usercopy
Linus Torvalds [Wed, 5 May 2021 19:24:29 +0000 (12:24 -0700)]
Merge branch 'turbostat' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux
Pull turbostat updates from Len Brown:
"Bug fixes and a smattering of features"
* 'turbostat' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux: (21 commits)
tools/power turbostat: version 2021.05.04
tools/power turbostat: Support "turbostat --hide idle"
tools/power turbostat: elevate priority of interval mode
tools/power turbostat: formatting
tools/power turbostat: rename tcc variables
tools/power turbostat: add TCC Offset support
tools/power turbostat: save original CPU model
tools/power turbostat: Fix Core C6 residency on Atom CPUs
tools/power turbostat: Print the C-state Pre-wake settings
tools/power turbostat: Enable tsc_tweak for Elkhart Lake and Jasper Lake
tools/power turbostat: unmark non-kernel-doc comment
tools/power/turbostat: Remove Package C6 Retention on Ice Lake Server
tools/power turbostat: Fix offset overflow issue in index converting
tools/power/turbostat: Fix turbostat for AMD Zen CPUs
tools/power turbostat: update version number
tools/power turbostat: Fix DRAM Energy Unit on SKX
Revert "tools/power turbostat: adjust for temperature offset"
tools/power turbostat: Support Ice Lake D
tools/power turbostat: Support Alder Lake Mobile
tools/power turbostat: print microcode patch level
...
Linus Torvalds [Wed, 5 May 2021 19:15:20 +0000 (12:15 -0700)]
Merge tag 'ktest-v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-ktest
Pull ktest updates from Steven Rostedt:
- Added a KTEST section in the MAINTAINERS file
- Included John Hawley as a co-maintainer
- Add an example config that would work with VMware workstation guests
- Cleanups to the code
* tag 'ktest-v5.13' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-ktest:
ktest: Add KTEST section to MAINTAINERS file
ktest: Re-arrange the code blocks for better discoverability
ktest: Further consistency cleanups
ktest: Fixing indentation to match expected pattern
ktest: Adding editor hints to improve consistency
ktest: Add example config for using VMware VMs
ktest: Minor cleanup with uninitialized variable $build_options
Marco Elver [Wed, 5 May 2021 01:40:27 +0000 (18:40 -0700)]
kfence: use power-efficient work queue to run delayed work
Use the power-efficient work queue, to avoid the pathological case where
we keep pinning ourselves on the same possibly idle CPU on systems that
want to be power-efficient (https://lwn.net/Articles/731052/).
Marco Elver [Wed, 5 May 2021 01:40:24 +0000 (18:40 -0700)]
kfence: maximize allocation wait timeout duration
The allocation wait timeout was initially added because of warnings due to
CONFIG_DETECT_HUNG_TASK=y [1]. While the 1 sec timeout is sufficient to
resolve the warnings (given the hung task timeout must be 1 sec or larger)
it may cause unnecessary wake-ups if the system is idle:
Marco Elver [Wed, 5 May 2021 01:40:21 +0000 (18:40 -0700)]
kfence: await for allocation using wait_event
Patch series "kfence: optimize timer scheduling", v2.
We have observed that mostly-idle systems with KFENCE enabled wake up
otherwise idle CPUs, preventing such to enter a lower power state.
Debugging revealed that KFENCE spends too much active time in
toggle_allocation_gate().
While the first version of KFENCE was using all the right bits to be
scheduling optimal, and thus power efficient, by simply using wait_event()
+ wake_up(), that code was unfortunately removed.
As KFENCE was exposed to various different configs and tests, the
scheduling optimal code slowly disappeared. First because of hung task
warnings, and finally because of deadlocks when an allocation is made by
timer code with debug objects enabled. Clearly, the "fixes" were not too
friendly for devices that want to be power efficient.
Therefore, let's try a little harder to fix the hung task and deadlock
problems that we have with wait_event() + wake_up(), while remaining as
scheduling friendly and power efficient as possible.
Crucially, we need to defer the wake_up() to an irq_work, avoiding any
potential for deadlock.
The result with this series is that on the devices where we observed a
power regression, power usage returns back to baseline levels.
This patch (of 3):
On mostly-idle systems, we have observed that toggle_allocation_gate() is
a cause of frequent wake-ups, preventing an otherwise idle CPU to go into
a lower power state.
A late change in KFENCE's development, due to a potential deadlock [1],
required changing the scheduling-friendly wait_event_timeout() and
wake_up() to an open-coded wait-loop using schedule_timeout(). [1]
https://lkml.kernel.org/r/000000000000c0645805b7f982e4@google.com
To avoid unnecessary wake-ups, switch to using wait_event_timeout().
Unfortunately, we still cannot use a version with direct wake_up() in
__kfence_alloc() due to the same potential for deadlock as in [1].
Instead, add a level of indirection via an irq_work that is scheduled if
we determine that the kfence_timer requires a wake_up().
Marco Elver [Wed, 5 May 2021 01:40:18 +0000 (18:40 -0700)]
kfence: zero guard page after out-of-bounds access
After an out-of-bounds accesses, zero the guard page before re-protecting
in kfence_guarded_free(). On one hand this helps make the failure mode of
subsequent out-of-bounds accesses more deterministic, but could also
prevent certain information leaks.
Ira Weiny [Wed, 5 May 2021 01:40:07 +0000 (18:40 -0700)]
btrfs: use memzero_page() instead of open coded kmap pattern
There are many places where kmap/memset/kunmap patterns occur.
Use the newly lifted memzero_page() to eliminate direct uses of kmap and
leverage the new core functions use of kmap_local_page().
The development of this patch was aided by the following coccinelle
script:
// <smpl>
// SPDX-License-Identifier: GPL-2.0-only
// Find kmap/memset/kunmap pattern and replace with memset*page calls
//
// NOTE: Offsets and other expressions may be more complex than what the script
// will automatically generate. Therefore a catchall rule is provided to find
// the pattern which then must be evaluated by hand.
//
// Confidence: Low
// Copyright: (C) 2021 Intel Corporation
// URL: http://coccinelle.lip6.fr/
// Comments:
// Options:
//
// Then the memset pattern
//
@ memset_rule1 @
expression page, V, L, Off;
identifier ptr;
type VP;
@@
Ira Weiny [Wed, 5 May 2021 01:40:03 +0000 (18:40 -0700)]
iov_iter: lift memzero_page() to highmem.h
Patch series "btrfs: Convert kmap/memset/kunmap to memzero_user()".
Lifting memzero_user(), convert it to kmap_local_page() and then use it
in btrfs.
This patch (of 3):
memzero_page() can replace the kmap/memset/kunmap pattern in other
places in the code. While zero_user() has the same interface it is not
the same call and its use should be limited and some of those calls may
be better converted from zero_user() to memzero_page().[1] But that is
not addressed in this series.
Zhiyuan Dai [Wed, 5 May 2021 01:39:57 +0000 (18:39 -0700)]
mm/zswap.c: switch from strlcpy to strscpy
strlcpy is marked as deprecated in Documentation/process/deprecated.rst,
and there is no functional difference when the caller expects truncation
(when not checking the return value). strscpy is relatively better as
it also avoids scanning the whole source string.
Oscar Salvador [Wed, 5 May 2021 01:39:48 +0000 (18:39 -0700)]
mm,memory_hotplug: add kernel boot option to enable memmap_on_memory
Self stored memmap leads to a sparse memory situation which is
unsuitable for workloads that requires large contiguous memory chunks,
so make this an opt-in which needs to be explicitly enabled.
To control this, let memory_hotplug have its own memory space, as
suggested by David, so we can add memory_hotplug.memmap_on_memory
parameter.
Oscar Salvador [Wed, 5 May 2021 01:39:45 +0000 (18:39 -0700)]
acpi,memhotplug: enable MHP_MEMMAP_ON_MEMORY when supported
Let the caller check whether it can pass MHP_MEMMAP_ON_MEMORY by
checking mhp_supports_memmap_on_memory(). MHP_MEMMAP_ON_MEMORY can only
be set in case ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE is enabled, the
architecture supports altmap, and the range to be added spans a single
memory block.
Oscar Salvador [Wed, 5 May 2021 01:39:42 +0000 (18:39 -0700)]
mm,memory_hotplug: allocate memmap from the added memory range
Physical memory hotadd has to allocate a memmap (struct page array) for
the newly added memory section. Currently, alloc_pages_node() is used
for those allocations.
This has some disadvantages:
a) an existing memory is consumed for that purpose
(eg: ~2MB per 128MB memory section on x86_64)
This can even lead to extreme cases where system goes OOM because
the physically hotplugged memory depletes the available memory before
it is onlined.
b) if the whole node is movable then we have off-node struct pages
which has performance drawbacks.
c) It might be there are no PMD_ALIGNED chunks so memmap array gets
populated with base pages.
This can be improved when CONFIG_SPARSEMEM_VMEMMAP is enabled.
Vmemap page tables can map arbitrary memory. That means that we can
reserve a part of the physically hotadded memory to back vmemmap page
tables. This implementation uses the beginning of the hotplugged memory
for that purpose.
There are some non-obviously things to consider though.
Vmemmap pages are allocated/freed during the memory hotplug events
(add_memory_resource(), try_remove_memory()) when the memory is
added/removed. This means that the reserved physical range is not
online although it is used. The most obvious side effect is that
pfn_to_online_page() returns NULL for those pfns. The current design
expects that this should be OK as the hotplugged memory is considered a
garbage until it is onlined. For example hibernation wouldn't save the
content of those vmmemmaps into the image so it wouldn't be restored on
resume but this should be OK as there no real content to recover anyway
while metadata is reachable from other data structures (e.g. vmemmap
page tables).
The reserved space is therefore (de)initialized during the {on,off}line
events (mhp_{de}init_memmap_on_memory). That is done by extracting page
allocator independent initialization from the regular onlining path.
The primary reason to handle the reserved space outside of
{on,off}line_pages is to make each initialization specific to the
purpose rather than special case them in a single function.
As per above, the functions that are introduced are:
- mhp_init_memmap_on_memory:
Initializes vmemmap pages by calling move_pfn_range_to_zone(), calls
kasan_add_zero_shadow(), and onlines as many sections as vmemmap pages
fully span.
- mhp_deinit_memmap_on_memory:
Offlines as many sections as vmemmap pages fully span, removes the
range from zhe zone by remove_pfn_range_from_zone(), and calls
kasan_remove_zero_shadow() for the range.
The new function memory_block_online() calls mhp_init_memmap_on_memory()
before doing the actual online_pages(). Should online_pages() fail, we
clean up by calling mhp_deinit_memmap_on_memory(). Adjusting of
present_pages is done at the end once we know that online_pages()
succedeed.
On offline, memory_block_offline() needs to unaccount vmemmap pages from
present_pages() before calling offline_pages(). This is necessary because
offline_pages() tears down some structures based on the fact whether the
node or the zone become empty. If offline_pages() fails, we account back
vmemmap pages. If it succeeds, we call mhp_deinit_memmap_on_memory().
Hot-remove:
We need to be careful when removing memory, as adding and
removing memory needs to be done with the same granularity.
To check that this assumption is not violated, we check the
memory range we want to remove and if a) any memory block has
vmemmap pages and b) the range spans more than a single memory
block, we scream out loud and refuse to proceed.
If all is good and the range was using memmap on memory (aka vmemmap pages),
we construct an altmap structure so free_hugepage_table does the right
thing and calls vmem_altmap_free instead of free_pagetable.
We want {online,offline}_pages to operate on whole memblocks, but
memmap_on_memory will poke pageblock_nr_pages aligned holes in the
beginning, which is a special case we want to allow. Relax the check to
account for that case.
Patch series "Allocate memmap from hotadded memory (per device)", v10.
The primary goal of this patchset is to reduce memory overhead of the
hot-added memory (at least for SPARSEMEM_VMEMMAP memory model). The
current way we use to populate memmap (struct page array) has two main
drawbacks:
a) it consumes an additional memory until the hotadded memory itself is
onlined and
b) memmap might end up on a different numa node which is especially
true for movable_node configuration.
c) due to fragmentation we might end up populating memmap with base
pages
One way to mitigate all these issues is to simply allocate memmap array
(which is the largest memory footprint of the physical memory hotplug)
from the hot-added memory itself. SPARSEMEM_VMEMMAP memory model allows
us to map any pfn range so the memory doesn't need to be online to be
usable for the array. See patch 4 for more details. This feature is
only usable when CONFIG_SPARSEMEM_VMEMMAP is set.
[Overall design]:
Implementation wise we reuse vmem_altmap infrastructure to override the
default allocator used by vmemap_populate. memory_block structure gains a
new field called nr_vmemmap_pages, which accounts for the number of
vmemmap pages used by that memory_block. E.g: On x86_64, that is 512
vmemmap pages on small memory bloks and 4096 on large memory blocks (1GB)
We also introduce new two functions: memory_block_{online,offline}. These
functions take care of initializing/unitializing vmemmap pages prior to
calling {online,offline}_pages, so the latter functions can remain totally
untouched.
More details can be found in the respective changelogs.
This patch (of 8):
This is a preparatory patch that introduces two new functions:
memory_block_online() and memory_block_offline().
For now, these functions will only call online_pages() and offline_pages()
respectively, but they will be later in charge of preparing the vmemmap
pages, carrying out the initialization and proper accounting of such
pages.
Since memory_block struct contains all the information, pass this struct
down the chain till the end functions.
Mel Gorman [Wed, 5 May 2021 01:39:30 +0000 (18:39 -0700)]
mm/memory_hotplug: remove broken locking of zone PCP structures during hot remove
zone_pcp_reset allegedly protects against a race with drain_pages using
local_irq_save but this is bogus. local_irq_save only operates on the
local CPU. If memory hotplug is running on CPU A and drain_pages is
running on CPU B, disabling IRQs on CPU A does not affect CPU B and
offers no protection.
This patch deletes IRQ disable/enable on the grounds that IRQs protect
nothing and assumes the existing hotplug paths guarantees the PCP cannot
be used after zone_pcp_enable(). That should be the case already
because all the pages have been freed and there is no page to put on the
PCP lists.
Pavel Tatashin [Wed, 5 May 2021 01:39:27 +0000 (18:39 -0700)]
selftests/vm: gup_test: test faulting in kernel, and verify pinnable pages
When pages are pinned they can be faulted in userland and migrated, and
they can be faulted right in kernel without migration.
In either case, the pinned pages must end-up being pinnable (not
movable).
Add a new test to gup_test, to help verify that the gup/pup
(get_user_pages() / pin_user_pages()) behavior with respect to pinnable
and movable pages is reasonable and correct. Specifically, provide a
way to:
1) Verify that only "pinnable" pages are pinned. This is checked
automatically for you.
2) Verify that gup/pup performance is reasonable. This requires
comparing benchmarks between doing gup/pup on pages that have been
pre-faulted in from user space, vs. doing gup/pup on pages that are
not faulted in until gup/pup time (via FOLL_TOUCH). This decision is
controlled with the new -z command line option.
Pavel Tatashin [Wed, 5 May 2021 01:39:23 +0000 (18:39 -0700)]
selftests/vm: gup_test: fix test flag
In gup_test both gup_flags and test_flags use the same flags field.
This is broken.
Farther, in the actual gup_test.c all the passed gup_flags are erased
and unconditionally replaced with FOLL_WRITE.
Which means that test_flags are ignored, and code like this always
performs pin dump test:
155 if (gup->flags & GUP_TEST_FLAG_DUMP_PAGES_USE_PIN)
156 nr = pin_user_pages(addr, nr, gup->flags,
157 pages + i, NULL);
158 else
159 nr = get_user_pages(addr, nr, gup->flags,
160 pages + i, NULL);
161 break;
Add a new test_flags field, to allow raw gup_flags to work. Add a new
subcommand for DUMP_USER_PAGES_TEST to specify that pin test should be
performed.
Remove unconditional overwriting of gup_flags via FOLL_WRITE. But,
preserve the previous behaviour where FOLL_WRITE was the default flag,
and add a new option "-W" to unset FOLL_WRITE.
Pavel Tatashin [Wed, 5 May 2021 01:39:19 +0000 (18:39 -0700)]
mm/gup: longterm pin migration cleanup
When pages are longterm pinned, we must migrated them out of movable zone.
The function that migrates them has a hidden loop with goto. The loop is
to retry on isolation failures, and after successful migration.
Make this code better by moving this loop to the caller.
Pavel Tatashin [Wed, 5 May 2021 01:39:15 +0000 (18:39 -0700)]
mm/gup: change index type to long as it counts pages
In __get_user_pages_locked() i counts number of pages which should be
long, as long is used in all other places to contain number of pages, and
32-bit becomes increasingly small for handling page count proportional
values.
Pavel Tatashin [Wed, 5 May 2021 01:39:08 +0000 (18:39 -0700)]
mm/gup: migrate pinned pages out of movable zone
We should not pin pages in ZONE_MOVABLE. Currently, we do not pin only
movable CMA pages. Generalize the function that migrates CMA pages to
migrate all movable pages. Use is_pinnable_page() to check which pages
need to be migrated
Pavel Tatashin [Wed, 5 May 2021 01:39:04 +0000 (18:39 -0700)]
mm/gup: do not migrate zero page
On some platforms ZERO_PAGE(0) might end-up in a movable zone. Do not
migrate zero page in gup during longterm pinning as migration of zero page
is not allowed.
For example, in x86 QEMU with 16G of memory and kernelcore=5G parameter, I
see the following:
On x86, empty_zero_page is declared in .bss and depending on the loader
may end up in different physical locations during boots.
Also, move is_zero_pfn() my_zero_pfn() functions under CONFIG_MMU, because
zero_pfn that they are using is declared in memory.c which is compiled
with CONFIG_MMU.
Pavel Tatashin [Wed, 5 May 2021 01:39:00 +0000 (18:39 -0700)]
mm: honor PF_MEMALLOC_PIN for all movable pages
PF_MEMALLOC_PIN is only honored for CMA pages, extend this flag to work
for any allocations from ZONE_MOVABLE by removing __GFP_MOVABLE from
gfp_mask when this flag is passed in the current context.
Add is_pinnable_page() to return true if page is in a pinnable page. A
pinnable page is not in ZONE_MOVABLE and not of MIGRATE_CMA type.
Pavel Tatashin [Wed, 5 May 2021 01:38:57 +0000 (18:38 -0700)]
mm: apply per-task gfp constraints in fast path
Function current_gfp_context() is called after fast path. However, soon
we will add more constraints which will also limit zones based on
context. Move this call into fast path, and apply the correct
constraints for all allocations.
Also update .reclaim_idx based on value returned by
current_gfp_context() because it soon will modify the allowed zones.
Note:
With this patch we will do one extra current->flags load during fast path,
but we already load current->flags in fast-path:
Later, when we add the zone constrain logic to current_gfp_context() we
will be able to remove current->flags load from current_alloc_flags, and
therefore return fast-path to the current performance level.
Pavel Tatashin [Wed, 5 May 2021 01:38:53 +0000 (18:38 -0700)]
mm cma: rename PF_MEMALLOC_NOCMA to PF_MEMALLOC_PIN
PF_MEMALLOC_NOCMA is used ot guarantee that the allocator will not
return pages that might belong to CMA region. This is currently used
for long term gup to make sure that such pins are not going to be done
on any CMA pages.
When PF_MEMALLOC_NOCMA has been introduced we haven't realized that it
is focusing on CMA pages too much and that there is larger class of
pages that need the same treatment. MOVABLE zone cannot contain any
long term pins as well so it makes sense to reuse and redefine this flag
for that usecase as well. Rename the flag to PF_MEMALLOC_PIN which
defines an allocation context which can only get pages suitable for
long-term pins.
Also rename: memalloc_nocma_save()/memalloc_nocma_restore to
memalloc_pin_save()/memalloc_pin_restore() and make the new functions
common.
Pavel Tatashin [Wed, 5 May 2021 01:38:42 +0000 (18:38 -0700)]
mm/gup: check every subpage of a compound page during isolation
When pages are isolated in check_and_migrate_movable_pages() we skip
compound number of pages at a time. However, as Jason noted, it is not
necessary correct that pages[i] corresponds to the pages that we
skipped. This is because it is possible that the addresses in this
range had split_huge_pmd()/split_huge_pud(), and these functions do not
update the compound page metadata.
The problem can be reproduced if something like this occurs:
1. User faulted huge pages.
2. split_huge_pmd() was called for some reason
3. User has unmapped some sub-pages in the range
4. User tries to longterm pin the addresses.
The resulting pages[i] might end-up having pages which are not compound
size page aligned.
Pavel Tatashin [Wed, 5 May 2021 01:38:38 +0000 (18:38 -0700)]
mm/gup: don't pin migrated cma pages in movable zone
Patch series "prohibit pinning pages in ZONE_MOVABLE", v11.
When page is pinned it cannot be moved and its physical address stays
the same until pages is unpinned.
This is useful functionality to allows userland to implementation DMA
access. For example, it is used by vfio in vfio_pin_pages().
However, this functionality breaks memory hotplug/hotremove assumptions
that pages in ZONE_MOVABLE can always be migrated.
This patch series fixes this issue by forcing new allocations during
page pinning to omit ZONE_MOVABLE, and also to migrate any existing
pages from ZONE_MOVABLE during pinning.
It uses the same scheme logic that is currently used by CMA, and extends
the functionality for all allocations.
For more information read the discussion [1] about this problem.
[1] https://lore.kernel.org/lkml/CA+CK2bBffHBxjmb9jmSKacm0fJMinyt3Nhk8Nx6iudcQSj80_w@mail.gmail.com
This patch (of 14):
In order not to fragment CMA the pinned pages are migrated. However, they
are migrated to ZONE_MOVABLE, which also should not have pinned pages.
Remove __GFP_MOVABLE, so pages can be migrated to zones where pinning is
allowed.
HAVE_ARCH_TRANSPARENT_HUGEPAGE has duplicate definitions on platforms
that subscribe it. Drop these reduntant definitions and instead just
select it on applicable platforms.
ARCH_ENABLE_SPLIT_PMD_PTLOCKS has duplicate definitions on platforms
that subscribe it. Drop these redundant definitions and instead just
select it on applicable platforms.
mm: drop redundant ARCH_ENABLE_[HUGEPAGE|THP]_MIGRATION
ARCH_ENABLE_[HUGEPAGE|THP]_MIGRATION configs have duplicate definitions on
platforms that subscribe them. Drop these reduntant definitions and
instead just select them appropriately.
ARCH_ENABLE_MEMORY_[HOTPLUG|HOTREMOVE] configs have duplicate
definitions on platforms that subscribe them. Instead, just make them
generic options which can be selected on applicable platforms.
mm: generalize SYS_SUPPORTS_HUGETLBFS (rename as ARCH_SUPPORTS_HUGETLBFS)
SYS_SUPPORTS_HUGETLBFS config has duplicate definitions on platforms
that subscribe it. Instead, just make it a generic option which can be
selected on applicable platforms.
Also rename it as ARCH_SUPPORTS_HUGETLBFS instead. This reduces code
duplication and makes it cleaner.
This series contains config cleanup patches which reduces code
duplication across platforms and also improves maintainability. There
is no functional change intended with this series.
This patch (of 6):
ARCH_HAS_CACHE_LINE_SIZE config has duplicate definitions on platforms
that subscribe it. Instead, just make it a generic option which can be
selected on applicable platforms. This change reduces code duplication
and makes it cleaner.
Liam Howlett [Wed, 5 May 2021 01:38:06 +0000 (18:38 -0700)]
mm/mmap.c: don't unlock VMAs in remap_file_pages()
Since this call uses MAP_FIXED, do_mmap() will munlock the necessary
range. There is also an error in the loop test expression which will
evaluate as false and the loop body has never execute.
Saravanan D [Wed, 5 May 2021 01:38:03 +0000 (18:38 -0700)]
x86/mm: track linear mapping split events
To help with debugging the sluggishness caused by TLB miss/reload, we
introduce monotonic hugepage [direct mapped] split event counts since
system state: SYSTEM_RUNNING to be displayed as part of /proc/vmstat in
x86 servers
The lifetime split event information will be displayed at the bottom of
/proc/vmstat
....
swap_ra 0
swap_ra_hit 0
direct_map_level2_splits 94
direct_map_level3_splits 4
nr_unstable 0
....
One of the many lasting sources of direct hugepage splits is kernel
tracing (kprobes, tracepoints).
Note that the kernel's code segment [512 MB] points to the same physical
addresses that have been already mapped in the kernel's direct mapping
range.
Source : Documentation/x86/x86_64/mm.rst
When we enable kernel tracing, the kernel has to modify
attributes/permissions of the text segment hugepages that are direct
mapped causing them to split.
Kernel's direct mapped hugepages do not coalesce back after split and
remain in place for the remainder of the lifetime.
An instance of direct page splits when we turn on dynamic kernel tracing
....
cat /proc/vmstat | grep -i direct_map_level
direct_map_level2_splits 784
direct_map_level3_splits 12
bpftrace -e 'tracepoint:raw_syscalls:sys_enter { @ [pid, comm] =
count(); }'
cat /proc/vmstat | grep -i
direct_map_level
direct_map_level2_splits 789
direct_map_level3_splits 12
....
Hugh Dickins [Wed, 5 May 2021 01:38:00 +0000 (18:38 -0700)]
mm: /proc/sys/vm/stat_refresh stop checking monotonic numa stats
All of the VM NUMA stats are event counts, incremented never
decremented: it is not very useful for vmstat_refresh() to check them
throughout their first aeon, then warn on them throughout their next.
Hugh Dickins [Wed, 5 May 2021 01:37:57 +0000 (18:37 -0700)]
mm: /proc/sys/vm/stat_refresh skip checking known negative stats
vmstat_refresh() can occasionally catch nr_zone_write_pending and
nr_writeback when they are transiently negative. The reason is partly
that the interrupt which decrements them in test_clear_page_writeback()
can come in before __test_set_page_writeback() got to increment them;
but transient negatives are still seen even when that is prevented, and
I am not yet certain why (but see Roman's note below). Those stats are
not buggy, they have never been seen to drift away from 0 permanently:
so just avoid the annoyance of showing a warning on them.
Similarly avoid showing a warning on nr_free_cma: CMA users have seen
that one reported negative from /proc/sys/vm/stat_refresh too, but it
does drift away permanently: I believe that's because its incrementation
and decrementation are decided by page migratetype, but the migratetype
of a pageblock is not guaranteed to be constant.
Roman Gushchin points out:
"For performance reasons, vmstat counters are incremented and
decremented using per-cpu batches. vmstat_refresh() flushes the
per-cpu batches on all CPUs, to get values as accurate as possible;
but this method is not atomic, so the resulting value is not always
precise.
As a consequence, for those counters whose actual value is close to 0,
a small negative value may occasionally be reported. If the value is
small and the state is transient, it is not an indication of an error"
Hugh Dickins [Wed, 5 May 2021 01:37:54 +0000 (18:37 -0700)]
mm: no more EINVAL from /proc/sys/vm/stat_refresh
EINVAL was good for drawing the refresher's attention to a warning in
dmesg, but became very tiresome when running test suites scripted with
"set -e": an underflow from a bug in one feature would cause unrelated
tests much later to fail, just because their /proc/sys/vm/stat_refresh
touch failed with that error. Stop doing that.
Hugh Dickins [Wed, 5 May 2021 01:37:51 +0000 (18:37 -0700)]
mm: restore node stat checking in /proc/sys/vm/stat_refresh
In v4.7 commit 52b6f46bc163 ("mm: /proc/sys/vm/stat_refresh to force
vmstat update") introduced vmstat_refresh(), with its vmstat underflow
checking; then in v4.8 commit 75ef71840539 ("mm, vmstat: add
infrastructure for per-node vmstats") split NR_VM_NODE_STAT_ITEMS out of
NR_VM_ZONE_STAT_ITEMS without updating vmstat_refresh(): so it has been
missing out much of the vmstat underflow checking ever since.
Reinstate it.
Thanks to Roman Gushchin <[email protected]> for tangentially pointing this out.
Chengyang Fan [Wed, 5 May 2021 01:37:48 +0000 (18:37 -0700)]
mm/ksm: remove unused parameter from remove_trailing_rmap_items()
Since commit 6514d511dbe5 ("ksm: singly-linked rmap_list") was merged,
remove_trailing_rmap_items() doesn't use the 'mm_slot' parameter. So
remove it, and update caller accordingly.
Miaohe Lin [Wed, 5 May 2021 01:37:45 +0000 (18:37 -0700)]
ksm: fix potential missing rmap_item for stable_node
When removing rmap_item from stable tree, STABLE_FLAG of rmap_item is
cleared with head reserved. So the following scenario might happen: For
ksm page with rmap_item1:
cmp_and_merge_page
stable_node->head = &migrate_nodes;
remove_rmap_item_from_tree, but head still equal to stable_node;
try_to_merge_with_ksm_page failed;
return;
For the same ksm page with rmap_item2, stable node migration succeed this
time. The stable_node->head does not equal to migrate_nodes now. For ksm
page with rmap_item1 again:
We would miss the rmap_item for stable_node and might result in failed
rmap_walk_ksm(). Fix this by set rmap_item->head to NULL when rmap_item
is removed from stable tree.
projects / linux.git / log