This bug is marked as fixed by commit:
KVM: x86: Remove WARN sanity check on hypervisor timer vs. UNINITIALIZED vCPU
But I can't find it in the tested trees[1] for more than 90 days.
Is it a correct commit? Please update it by replying:
#syz fix: exact-commit-title
Until then the bug is still co
From: Guo Ren
patch[1 - 8]: Native qspinlock
patch[9 -14]: Paravirt qspinlock
This series based on:
- v6.7-rc7
- Rework & improve riscv cmpxchg.h and atomic.h
https://lore.kernel.org/linux-riscv/20230810040349.92279-2-leob...@redhat.com/
You can directly try it:
https://github.com/guore
From: Guo Ren
The arch_spinlock_t of qspinlock has contained the atomic_t val, which
satisfies the ticket-lock requirement. Thus, unify the arch_spinlock_t
into qspinlock_types.h. This is the preparation for the next combo
spinlock.
Reviewed-by: Leonardo Bras
Suggested-by: Arnd Bergmann
Link:
From: Guo Ren
Add a separate ticket-lock.h to include multiple spinlock versions and
select one at compile time or runtime.
Reviewed-by: Leonardo Bras
Suggested-by: Arnd Bergmann
Link:
https://lore.kernel.org/linux-riscv/cak8p3a2rnz9mqqhn6-e0cguuv9rntrelfdxt_weid7fxh7f...@mail.gmail.com/
Sign
From: Guo Ren
Move errata vendor func-id definitions from errata_list into
vendorid_list.h. Unifying these definitions is also for following
rwonce errata implementation.
Suggested-by: Leonardo Bras
Link: https://lore.kernel.org/linux-riscv/zqlfj1cmq8pao...@redhat.com/
Signed-off-by: Guo Ren
S
From: Guo Ren
The early version of T-Head C9xx cores has a store merge buffer
delay problem. The store merge buffer could improve the store queue
performance by merging multi-store requests, but when there are not
continued store requests, the prior single store request would be
waiting in the st
From: Guo Ren
The requirements of qspinlock have been documented by commit:
a8ad07e5240c ("asm-generic: qspinlock: Indicate the use of mixed-size
atomics").
Although RISC-V ISA gives out a weaker forward guarantee LR/SC, which
doesn't satisfy the requirements of qspinlock above, it won't prevent
From: Guo Ren
Combo spinlock could support queued and ticket in one Linux Image and
select them during boot time via command line. Here is the func
size (Bytes) comparison table below:
TYPE: COMBO | TICKET | QUEUED
arch_spin_lock : 106 | 60 | 50
arch_spin_unloc
From: Guo Ren
Add a static key controlling whether virt_spin_lock() should be
called or not. When running on bare metal set the new key to
false.
The VM guests should fall back to a Test-and-Set spinlock,
because fair locks have horrible lock 'holder' preemption issues.
The virt_spin_lock_key wo
From: Guo Ren
Force to enable virt_spin_lock when KVM guest, because fair locks
have horrible lock 'holder' preemption issues.
Suggested-by: Leonardo Bras
Link: https://lkml.kernel.org/kvm/zqk9-tn2mepxl...@redhat.com/
Signed-off-by: Guo Ren
Signed-off-by: Guo Ren
---
arch/riscv/include/asm/s
From: Guo Ren
Add the files functions needed to support the SBI PVLOCK (paravirt
qspinlock kick_cpu) extension. Implement kvm_sbi_ext_pvlock_kick_-
cpu(), and we only need to call the kvm_vcpu_kick() and bring
target_vcpu from the halt state. No irq raised, no other request,
just a pure vcpu_kick
From: Guo Ren
Using static_call to switch between:
native_queued_spin_lock_slowpath()__pv_queued_spin_lock_slowpath()
native_queued_spin_unlock() __pv_queued_spin_unlock()
Finish the pv_wait implementation, but pv_kick needs the SBI
definition of the next patches.
Reviewed-by:
From: Guo Ren
Implement pv_kick with SBI guest implementation, and add
SBI_EXT_PVLOCK extension detection. The backend part is
in the KVM pvqspinlock patch.
Reviewed-by: Leonardo Bras
Signed-off-by: Guo Ren
Signed-off-by: Guo Ren
---
arch/riscv/include/asm/sbi.h | 6 ++
arch/ri
From: Guo Ren
Disables the qspinlock slow path using PV optimizations which
allow the hypervisor to 'idle' the guest on lock contention.
Reviewed-by: Leonardo Bras
Signed-off-by: Guo Ren
Signed-off-by: Guo Ren
---
Documentation/admin-guide/kernel-parameters.txt | 2 +-
arch/riscv/kernel/qsp
From: Guo Ren
Add kconfig entry for paravirt_spinlock, an unfair qspinlock
virtualization-friendly backend, by halting the virtual CPU rather
than spinning.
Reviewed-by: Leonardo Bras
Signed-off-by: Guo Ren
Signed-off-by: Guo Ren
---
arch/riscv/Kconfig | 12
arch/riscv/k
From: Guo Ren
Add trace point for pv_kick&wait, here is the output:
ls /sys/kernel/debug/tracing/events/paravirt/
enable filter pv_kick pv_wait
cat /sys/kernel/debug/tracing/trace
entries-in-buffer/entries-written: 33927/33927 #P:12
_-=> irqs-off/BH
The following changes since commit cefc9ba6aed48a3aa085888e3262ac2aa975714b:
pds_vdpa: set features order (2023-12-01 09:55:01 -0500)
are available in the Git repository at:
https://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git tags/for_linus
for you to fetch changes up to b8e079244
This series prevents the change of virtqueue address or state when a
device is in DRIVER_OK and not suspended. The virtio spec doesn't
allow changing virtqueue addresses and state in DRIVER_OK, but some devices
do support this operation when the device is suspended. The series
leaves the door open
Set vdpa device suspended state on successful suspend. Clear it on
successful resume and reset.
The state will be locked by the vhost_vdpa mutex. The mutex is taken
during suspend, resume and reset in vhost_vdpa_unlocked_ioctl. The
exception is vhost_vdpa_open which does a device reset but that sh
The virtio standard doesn't allow for virtqueue address and state
changes when the device is in DRIVER_OK. Return an error in such cases
unless the device is suspended.
The suspended device exception is needed because some devices support
virtqueue changes when the device is suspended.
Signed-off
On Fri, 2023-12-22 at 11:51 +0100, Dragos Tatulea wrote:
> On Fri, 2023-12-22 at 03:29 -0500, Michael S. Tsirkin wrote:
> > On Thu, Dec 21, 2023 at 03:07:22PM +, Dragos Tatulea wrote:
> > > > > > In that case you're right, we don't need feature flags. But I think
> > > > > > it
> > > > > > wou
On Mon, Dec 25, 2023 at 03:42:08PM +0200, Dragos Tatulea wrote:
> This series prevents the change of virtqueue address or state when a
> device is in DRIVER_OK and not suspended. The virtio spec doesn't
> allow changing virtqueue addresses and state in DRIVER_OK, but some devices
> do support this
On Tue, Dec 19, 2023 at 08:08:43PM +0200, Dragos Tatulea wrote:
> Add support for resumable vqs in the mlx5_vdpa driver. This is a
> firmware feature that can be used for the following benefits:
> - Full device .suspend/.resume.
> - .set_map doesn't need to destroy and create new vqs anymore just t
On Mon, 2023-12-25 at 09:41 -0500, Michael S. Tsirkin wrote:
> On Tue, Dec 19, 2023 at 08:08:43PM +0200, Dragos Tatulea wrote:
> > Add support for resumable vqs in the mlx5_vdpa driver. This is a
> > firmware feature that can be used for the following benefits:
> > - Full device .suspend/.resume.
>
On Mon, 2023-12-25 at 09:40 -0500, Michael S. Tsirkin wrote:
> On Mon, Dec 25, 2023 at 03:42:08PM +0200, Dragos Tatulea wrote:
> > This series prevents the change of virtqueue address or state when a
> > device is in DRIVER_OK and not suspended. The virtio spec doesn't
> > allow changing virtqueue
Add support for resumable vqs in the mlx5_vdpa driver. This is a
firmware feature that can be used for the following benefits:
- Full device .suspend/.resume.
- .set_map doesn't need to destroy and create new vqs anymore just to
update the map. When resumable vqs are supported it is enough to
s
Necessary for checking if resumable vqs are supported by the hardware.
Actual support will be added in a downstream patch.
Reviewed-by: Gal Pressman
Acked-by: Eugenio Pérez
Signed-off-by: Dragos Tatulea
---
include/linux/mlx5/mlx5_ifc.h | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
Add a bitmask variable that tracks hw vq field changes that
are supposed to be modified on next hw vq change command.
This will be useful to set multiple vq fields when resuming the vq.
Reviewed-by: Gal Pressman
Acked-by: Eugenio Pérez
Acked-by: Jason Wang
Signed-off-by: Dragos Tatulea
---
d
Implement vdpa vq and device resume if capability detected. Add support
for suspend -> ready state change.
Reviewed-by: Gal Pressman
Acked-by: Eugenio Pérez
Acked-by: Jason Wang
Signed-off-by: Dragos Tatulea
---
drivers/vdpa/mlx5/net/mlx5_vnet.c | 69 +++
1 file ch
Addresses get set by .set_vq_address. hw vq addresses will be updated on
next modify_virtqueue.
Reviewed-by: Gal Pressman
Signed-off-by: Dragos Tatulea
---
drivers/vdpa/mlx5/net/mlx5_vnet.c | 9 +
include/linux/mlx5/mlx5_ifc_vdpa.h | 1 +
2 files changed, 10 insertions(+)
diff --git a
Deleting the old mr during mr update (.set_map) and then modifying the
vqs with the new mr is not a good flow for firmware. The firmware
expects that mkeys are deleted after there are no more vqs referencing
them.
Introduce reference counting for mrs to fix this. It is the only way to
make sure th
.set_vq_state will set the indices and mark the fields to be modified in
the hw vq.
Advertise that the device supports changing the vq state when the device
is in DRIVER_OK state and suspended.
Reviewed-by: Gal Pressman
Signed-off-by: Dragos Tatulea
Acked-by: Jason Wang
---
drivers/vdpa/mlx5/
Instead of tearing down and setting up vq resources, use vq
suspend/resume during .set_map to speed things up a bit.
The vq mr is updated with the new mapping while the vqs are suspended.
If the device doesn't support resumable vqs, do the old teardown and
setup dance.
Reviewed-by: Gal Pressman
Track allocated mrs in a list and show warning when leaks are detected
on device free or reset.
Reviewed-by: Gal Pressman
Acked-by: Eugenio Pérez
Signed-off-by: Dragos Tatulea
---
drivers/vdpa/mlx5/core/mlx5_vdpa.h | 2 ++
drivers/vdpa/mlx5/core/mr.c| 23 +++
drive
Hi, Ahelenia Ziemiańska! Thanks a lot for all this splice-related hard work!
In
https://lore.kernel.org/lkml/CAHk-=wgG_2cmHgZwKjydi7=iimyhyn8aessnbm9xq9ufbau...@mail.gmail.com/
Linus said:
> I have grown to pretty much hate
> splice() over the years, just because it's been a constant source of
>
On Tue, Dec 26, 2023 at 12:34:44AM +0300, Askar Safin wrote:
> In
> https://lore.kernel.org/lkml/CAHk-=wgG_2cmHgZwKjydi7=iimyhyn8aessnbm9xq9ufbau...@mail.gmail.com/
> Linus said:
> > I have grown to pretty much hate
> > splice() over the years, just because it's been a constant source of
> > sorro
The pull request you sent on Mon, 25 Dec 2023 08:27:49 -0500:
> https://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git tags/for_linus
has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/fbafc3e621c3f4ded43720fdb1d6ce1728ec664e
Thank you!
--
Deet-doot-dot, I am a b
Hi,
On Mon, 18 Dec 2023 22:13:46 +0900
"Masami Hiramatsu (Google)" wrote:
> @@ -408,15 +395,51 @@ int function_graph_enter(unsigned long ret, unsigned
> long func,
> return -EBUSY;
> }
>
> +/* This is called from ftrace_graph_func() via ftrace */
> +int function_graph_enter_ops(unsigne
Sorry, I missed people on the list.
F.Y.I
Waiman Long
Boqun Feng
Here is Link:
https://lore.kernel.org/linux-riscv/20231225125847.2778638-1-guo...@kernel.org/
On Mon, Dec 25, 2023 at 8:59 PM wrote:
>
> From: Guo Ren
>
> patch[1 - 8]: Native qspinlock
> patch[9 -14]: Paravirt qspinlock
>
>
Sometimes we need to track the processing order of
requests with ioprio set, especially when using
mq-deadline. So the ioprio of request can be useful
information.
Signed-off-by: Dongliang Cui
---
include/trace/events/block.h | 20 ++--
1 file changed, 14 insertions(+), 6 deletio
On 21-12-23, 16:24, Vincent Guittot wrote:
> arch_update_thermal_pressure() aims to update fast changing signal which
> should be averaged using PELT filtering before being provided to the
> scheduler which can't make smart use of fast changing signal.
> cpufreq now provides the maximum freq_qos pr
41 matches
Mail list logo
