Handle guest mm access life cycle properly with mmget()/mmput().
As noted by Linus, use_mm() depends on valid live page table but
KVM's mmgrab() doesn't guarantee that. As vGPU usage depends on
guest VM life cycle, need to make sure to use mmget()/mmput() to
guarantee VM address access.
v3: fix build
v2: v1 caused a weird dependence issue which failed for vfio
device release, which result invalid mdev vgpu and kvm state
without proper release taken. This trys to put right reference
around VM address space access instead.
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
info.index can be indirectly controlled by user-space, hence leading
to a potential exploitation of the Spectre variant 1 vulnerability.
This issue was detected with the help of Smatch:
drivers/gpu/drm/i915/gvt/kvmgt.c:1232 intel_vgpu_ioctl() warn:
potential spectre issue 'vgpu->vdev.region' [r]
Fix this by sanitizing info.index before indirectly using it to index
vgpu->vdev.region
Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].
[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2
Cc: stable@vger.kernel.org
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Currently, the mutex used in GVT dmabuf support is not initialized until
vgpu device is opened. If one vgpu device is opened and then removed, the
mutex will be used in vgpu remove operation without initialization. This
patch initializes the mutex in vgpu create operation to avoid the problem.
Fixes: e546e281d33d("drm/i915/gvt: Dmabuf support for GVT-g")
Signed-off-by: Hang Yuan <hang.yuan@linux.intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Some workloads may be prepared in vgpu's queue but not be scheduled
to run yet. If vgpu is released at this time, they will not be freed
in workload complete callback and so need to be freed in vgpu release
operation.
Add new vgpu_release operation in gvt_ops to stop vgpu and release
runtime resources. gvt_ops vgpu_deactivate operation will only stop
vgpu.
v2: add new gvt ops to clean vgpu running status (Xiong Zhang)
Signed-off-by: Hang Yuan <hang.yuan@linux.intel.com>
Reviewed-by: Xiong Zhang <xiong.y.zhang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
The dma_mapping_error() returns true on error but we want to return
-ENOMEM here.
Fixes: 79e542f5af ("drm/i915/kvmgt: Support setting dma map for huge pages")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
On GEM side:
- GuC related fixes (Chris, Michal)
- GTT read-only pages support (Jon, Chris)
- More selftests fixes (Chris)
- More GPU reset improvements (Chris)
- Flush caches after GGTT writes (Chris)
- Handle recursive shrinker for vma->last_active allocation (Chris)
- Other execlists fixes (Chris)
On Display side:
- GLK HDMI fix (Clint)
- Rework and cleanup around HPD pin (Ville)
- Preparation work for Display Stream Compression support coming on ICL (Anusha)
- Nuke LVDS lid notification (Ville)
- Assume eDP is always connected (Ville)
- Kill intel panel detection (Ville)
Signed-off-by: Dave Airlie <airlied@redhat.com>
# gpg: Signature made Fri 20 Jul 2018 01:51:45 AM AEST
# gpg: using RSA key FA625F640EEB13CA
# gpg: Good signature from "Rodrigo Vivi <rodrigo.vivi@intel.com>"
# gpg: aka "Rodrigo Vivi <rodrigo.vivi@gmail.com>"
# gpg: WARNING: This key is not certified with a trusted signature!
# gpg: There is no indication that the signature belongs to the owner.
# Primary key fingerprint: 6D20 7068 EEDD 6509 1C2C E2A3 FA62 5F64 0EEB 13CA
# Conflicts:
# drivers/gpu/drm/i915/intel_lrc.c
Link: https://patchwork.freedesktop.org/patch/msgid/20180719171257.GA12199@intel.com
To support huge gtt, we need to support huge pages in kvmgt first.
This patch adds a 'size' param to the intel_gvt_mpt::dma_map_guest_page
API and implements it in kvmgt.
v2: rebase.
Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
kvmgt get msi eventfd_ctx at qemu vfio set irq eventfd, then
msi eventfd_ctx should be put at some point.
The first point is kvmgt handle qemu vfio_disable_irqindex()
call which has DATA_NONE and ACTION_TRIGGER in flags.
If qemu doesn't call vfio_disable_irqindex(), the second point
is vgpu release function.
v2: Don't inject msi interrupt into guest if eventfd_ctx is dereferenced
Signed-off-by: Xiong Zhang <xiong.y.zhang@intel.com>
Reviewed-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Add a new debugfs entry kvmgt_nr_cache_entries under vgpu which shows
the number of entry in dma cache.
$ cat /sys/kernel/debug/gvt/vgpu1/kvmgt_nr_cache_entries
10101
v3: fix compiling error for some configuration. (Xiong Zhang <xiong.y.zhang@intel.com>)
v2: keep debugfs layout flat.
Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
The implementation of current kvmgt implicitly setup dma mapping at MPT
API gfn_to_mfn. First this design against the API's original purpose.
Second, there is no unmap hit in this design. The result is that the
dma mapping keep growing larger and larger. For mutl-vm case, they will
consume IOMMU IOVA low 4GB address space quickly and so tons of rbtree
entries crated in the IOMMU IOVA allocator. Finally, single IOVA
allocation can take as long as ~70ms. Such latency is intolerable.
To address both above issues, this patch introduced two new MPT API:
o dma_map_guest_page - setup dma map for guest page
o dma_unmap_guest_page - cancel dma map for guest page
The kvmgt implements these 2 API. And to reduce dma setup overhead for
duplicated pages (eg. scratch pages), two caches are used: one is for
mapping gfn to struct gvt_dma, another is for mapping dma addr to
struct gvt_dma.
With these 2 new API, the gtt now is able to cancel dma mapping when page
table is invalidated. The dma mapping is not in a gradual increase now.
v2: follow the old logic for VFIO_IOMMU_NOTIFY_DMA_UNMAP at this point.
Cc: Hang Yuan <hang.yuan@intel.com>
Cc: Xiong Zhang <xiong.y.zhang@intel.com>
Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Fix check error at
CHECK drivers/gpu/drm/i915//gvt/kvmgt.c
drivers/gpu/drm/i915//gvt/kvmgt.c:455 intel_vgpu_create() error: we previously assumed 'vgpu' could be null (see line 454)
For failed vgpu create, just show error return in failure message.
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
The kvmgt's implementation of mpt api {set,unset}_wp_page is not real
write-protection - the data get written before invoke this two api.
As discussed, change the mpt api to match the real behavior.
Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
GGTT is in BAR0 with 8 bytes aligned. With a qemu patch (commit:
38d49e8c1523d97d2191190d3f7b4ce7a0ab5aa3), VFIO can use 8-byte reads/
writes to access it.
This patch is to support the 8-byte GGTT reads/writes.
Ideally, we would like to support 8-byte reads/writes for the total BAR0.
But it needs more work for handling 8-byte MMIO reads/writes.
This patch can fix the issue caused by partial updating GGTT entry, during
guest booting up.
v3:
- Use intel_vgpu_get_bar_gpa() stead. (Zhenyu)
- Include all the GGTT checking logic in gtt_entry(). (Zhenyu)
v2:
- Limit to GGTT entry. (Zhenyu)
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Pull more drm updates from Dave Airlie:
"Ben missed sending his nouveau tree, but he really didn't have much
stuff in it:
- GP108 acceleration support is enabled by "secure boot" support
- some clockgating work on Kepler, and bunch of fixes
- the bulk of the diff is regenerated firmware files, the change to
them really isn't that large.
Otherwise this contains regular Intel and AMDGPU fixes"
* tag 'drm-for-v4.16-part2-fixes' of git://people.freedesktop.org/~airlied/linux: (59 commits)
drm/i915/bios: add DP max link rate to VBT child device struct
drm/i915/cnp: Properly handle VBT ddc pin out of bounds.
drm/i915/cnp: Ignore VBT request for know invalid DDC pin.
drm/i915/cmdparser: Do not check past the cmd length.
drm/i915/cmdparser: Check reg_table_count before derefencing.
drm/i915/bxt, glk: Increase PCODE timeouts during CDCLK freq changing
drm/i915/gvt: Use KVM r/w to access guest opregion
drm/i915/gvt: Fix aperture read/write emulation when enable x-no-mmap=on
drm/i915/gvt: only reset execlist state of one engine during VM engine reset
drm/i915/gvt: refine intel_vgpu_submission_ops as per engine ops
drm/amdgpu: re-enable CGCG on CZ and disable on ST
drm/nouveau/clk: fix gcc-7 -Wint-in-bool-context warning
drm/nouveau/mmu: Fix trailing semicolon
drm/nouveau: Introduce NvPmEnableGating option
drm/nouveau: Add support for SLCG for Kepler2
drm/nouveau: Add support for BLCG on Kepler2
drm/nouveau: Add support for BLCG on Kepler1
drm/nouveau: Add support for basic clockgating on Kepler1
drm/nouveau/kms/nv50: fix handling of gamma since atomic conversion
drm/nouveau/kms/nv50: use INTERPOLATE_257_UNITY_RANGE LUT on newer chipsets
...
When add 'x-no-mmap=on' for vfio-pci option, aperture access in guest
is emulated. But the vgpu_aperture_rw() function take wrong offset when
do memcpy, since vgpu->gm.aperture_va is not the base of entire aperture.
This mistake cause GPU command in guest get lost and so the seqno is not
updated in engine HWSP.
This patch fix this, and it also move the emulation code to kvmgt.
Because only vfio need to emulate it. Put aperture rw to MMIO emulation
path breaks assumptions in xengt.
v2: Remove PAGE_ALIGN for size (zhenyu)
Fixes: f090a00df9 ("drm/i915/gvt: Add emulation for BAR2 (aperture) with normal file RW approach")
Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Pull drm updates from Dave Airlie:
"This seems to have been a comparatively quieter merge window, I assume
due to holidays etc. The "biggest" change is AMD header cleanups, which
merge/remove a bunch of them. The AMD gpu scheduler is now being made generic
with the etnaviv driver wanting to reuse the code, hopefully other drivers
can go in the same direction.
Otherwise it's the usual lots of stuff in i915/amdgpu, not so much stuff
elsewhere.
Core:
- Add .last_close and .output_poll_changed helpers to reduce driver footprints
- Fix plane clipping
- Improved debug printing support
- Add panel orientation property
- Update edid derived properties at edid setting
- Reduction in fbdev driver footprint
- Move amdgpu scheduler into core for other drivers to use.
i915:
- Selftest and IGT improvements
- Fast boot prep work on IPS, pipe config
- HW workarounds for Cannonlake, Geminilake
- Cannonlake clock and HDMI2.0 fixes
- GPU cache invalidation and context switch improvements
- Display planes cleanup
- New PMU interface for perf queries
- New firmware support for KBL/SKL
- Geminilake HW workaround for perforamce
- Coffeelake stolen memory improvements
- GPU reset robustness work
- Cannonlake horizontal plane flipping
- GVT work
amdgpu/radeon:
- RV and Vega header file cleanups (lots of lines gone!)
- TTM operation context support
- 48-bit GPUVM support for Vega/RV
- ECC support for Vega
- Resizeable BAR support
- Multi-display sync support
- Enable swapout for reserved BOs during allocation
- S3 fixes on Raven
- GPU reset cleanup and fixes
- 2+1 level GPU page table
amdkfd:
- GFX7/8 SDMA user queues support
- Hardware scheduling for multiple processes
- dGPU prep work
rcar:
- Added R8A7743/5 support
- System suspend/resume support
sun4i:
- Multi-plane support for YUV formats
- A83T and LVDS support
msm:
- Devfreq support for GPU
tegra:
- Prep work for adding Tegra186 support
- Tegra186 HDMI support
- HDMI2.0 and zpos support by using generic helpers
tilcdc:
- Misc fixes
omapdrm:
- Support memory bandwidth limits
- DSI command mode panel cleanups
- DMM error handling
exynos:
- drop the old IPP subdriver.
etnaviv:
- Occlusion query fixes
- Job handling fixes
- Prep work for hooking in gpu scheduler
armada:
- Move closer to atomic modesetting
- Allow disabling primary plane if overlay is full screen
imx:
- Format modifier support
- Add tile prefetch to PRE
- Runtime PM support for PRG
ast:
- fix LUT loading"
* tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux: (1471 commits)
drm/ast: Load lut in crtc_commit
drm: Check for lessee in DROP_MASTER ioctl
drm: fix gpu scheduler link order
drm/amd/display: Demote error print to debug print when ATOM impl missing
dma-buf: fix reservation_object_wait_timeout_rcu once more v2
drm/amdgpu: Avoid leaking PM domain on driver unbind (v2)
drm/amd/amdgpu: Add Polaris version check
drm/amdgpu: Reenable manual GPU reset from sysfs
drm/amdgpu: disable MMHUB power gating on raven
drm/ttm: Don't unreserve swapped BOs that were previously reserved
drm/ttm: Don't add swapped BOs to swap-LRU list
drm/amdgpu: only check for ECC on Vega10
drm/amd/powerplay: Fix smu_table_entry.handle type
drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global count
drm: Fix PANEL_ORIENTATION_QUIRKS breaking the Kconfig DRM menuconfig
drm/radeon: fill in rb backend map on evergreen/ni.
drm/amdgpu/gfx9: fix ngg enablement to clear gds reserved memory (v2)
drm/ttm: only free pages rather than update global memory count together
drm/amdgpu: fix CPU based VM updates
drm/amdgpu: fix typo in amdgpu_vce_validate_bo
...
GVT may receive partial write on one guest PTE update. Validate gfn
not to translate incomplete gfn. This avoids some unnecessary error
messages incurred by the incomplete gfn translating. Also fix the
bug that the whole PPGTT shadow page update is aborted on any invalid
gfn entry.
gfn validation relys on hypervisor's help. Add one MPT module function
to provide the function.
Signed-off-by: Hang Yuan <hang.yuan@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
It's a bit confusing that page write protect handler is live in
mmio emulation handler. This moves it to stand alone gvt ops.
Also remove unnecessary check of write protected page access
in mmio read handler and cleanup handling of failsafe case.
v2: rebase
Reviewed-by: Xiong Zhang <xiong.y.zhang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
The vfio_info_add_capability() helper requires the caller to pass a
capability ID, which it then uses to fill in header fields, assuming
hard coded versions. This makes for an awkward and rigid interface.
The only thing we want this helper to do is allocate sufficient
space in the caps buffer and chain this capability into the list.
Reduce it to that simple task.
Reviewed-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Reviewed-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Both ROM/VGA region are not supported for vGPU in GVT. But if the device
model want to get those region, we should return the correct information
but not leave the structure with random data. Change to same operation
of BAR3-BAR5 which are also not supported by vGPU.
Refer to function @intel_vgpu_rw.
Signed-off-by: Pei Zhang <pei.zhang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
This patch introduces a guest's framebuffer sharing mechanism based on
dma-buf subsystem. With this sharing mechanism, guest's framebuffer can
be shared between guest VM and host.
v17:
- modify VFIO_DEVICE_GET_GFX_DMABUF interface. (Alex)
v16:
- add x_hot and y_hot. (Gerd)
- add flag validation for VFIO_DEVICE_GET_GFX_DMABUF. (Alex)
- rebase 4.14.0-rc6.
v15:
- add VFIO_DEVICE_GET_GFX_DMABUF ABI. (Gerd)
- add intel_vgpu_dmabuf_cleanup() to clean up the vGPU's dmabuf. (Gerd)
v14:
- add PROBE, DMABUF and REGION flags. (Alex)
v12:
- refine the lifecycle of dmabuf.
v9:
- remove dma-buf management. (Alex)
- track the dma-buf create and release in kernel mode. (Gerd) (Daniel)
v8:
- refine the dma-buf ioctl definition.(Alex)
- add a lock to protect the dmabuf list. (Alex)
v7:
- release dma-buf related allocations in dma-buf's associated release
function. (Alex)
- refine ioctl interface for querying plane info or create dma-buf.
(Alex)
v6:
- align the dma-buf life cycle with the vfio device. (Alex)
- add the dma-buf related operations in a separate patch. (Gerd)
- i915 related changes. (Chris)
v5:
- fix bug while checking whether the gem obj is gvt's dma-buf when user
change caching mode or domains. Add a helper function to do it.
(Xiaoguang)
- add definition for the query plane and create dma-buf. (Xiaoguang)
v4:
- fix bug while checking whether the gem obj is gvt's dma-buf when set
caching mode or doamins. (Xiaoguang)
v3:
- declare a new flag I915_GEM_OBJECT_IS_GVT_DMABUF in drm_i915_gem_object
to represent the gem obj for gvt's dma-buf. The tiling mode, caching
mode and domains can not be changed for this kind of gem object. (Alex)
- change dma-buf related information to be more generic. So other vendor
can use the same interface. (Alex)
v2:
- create a management fd for dma-buf operations. (Alex)
- alloc gem object's backing storage in gem obj's get_pages() callback.
(Chris)
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Windows guest driver needs vbt in opregion, to configure the setting
for display. Without opregion support, the display registers won't
be set and this blocks display model to get the correct information
of the guest display plane.
This patch is to provide a virtual opregion for guest. The original
author of this patch is Xiaoguang Chen.
This patch is split from the "Dma-buf support for GVT-g" patch set,
with being rebased to the latest gvt-staging branch.
v3:
- add checking region index during intel_vgpu_rw. (Xiong)
v2:
- refine intel_vgpu_reg_release_opregion. (Xiong)
Here are the previous version comments:
v18:
- unmap vgpu's opregion when destroying vgpu.
v16:
- rebase to 4.14.0-rc6.
Signed-off-by: Bing Niu <bing.niu@intel.com>
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Tested-by: Xiong Zhang <xiong.y.zhang@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
all the vGPU type related code in kvmgt will be moved into
gvt.c/gvt.h files while the common vGPU type related interfaces
will be called.
v2:
- intel_gvt_{init,cleanup}_vgpu_type_groups are initialized in
gvt part. (Wang, Zhi)
Signed-off-by: fred gao <fred.gao@intel.com>
Reviewed-by: Zhi Wang <zhi.a.wang@intel.com>
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
For vfio-pci, if the region support MMAP then it should support both
mmap and normal file access. The user-space is free to choose which is
being used. For qemu, we just need add 'x-no-mmap=on' for vfio-pci
option.
Currently GVTg only support MMAP for BAR2. So GVTg will not work when
user turn on x-no-mmap option.
This patch added file style access for BAR2, aka the GPU aperture. We
map the entire aperture partition of active vGPU to kernel space when
guest driver try to enable PCI Memory Space. Then we redirect the file
RW operation from kvmgt to this mapped area.
Link: https://bugzilla.redhat.com/show_bug.cgi?id=1458032
Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
For PCI, 64bit bar consumes two BAR registers, but this doesn't mean
both of two BAR are valid. Actually the second BAR is regarded as
reserved in this case. So we shouldn't emulate the second BAR.
Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
This exposes vGPU context hw id in mdev sysfs which is used to
do vGPU based profiling. Retrieved vGPU context hw id can be set
through i915 perf ioctl to set profiling for target vGPU.
Cc: Jiao Pengyuan <pengyuan.jiao@intel.com>
Cc: Niu Bing <bing.niu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
There are two kinds of locking sequence.
One is in the thread which is started by vfio ioctl to do
the iommu unmapping. The locking sequence is:
down_read(&group_lock) ----> mutex_lock(&cached_lock)
The other is in the vfio release thread which will unpin all
the cached pages. The lock sequence is:
mutex_lock(&cached_lock) ---> down_read(&group_lock)
And, the cache_lock is used to protect the rb tree of the cache
node and doing vfio unpin doesn't require this lock. Move the
vfio unpin out of the cache_lock protected region.
v2:
- use for style instead of do{}while(1). (Zhenyu)
Fixes: f30437c5e7 ("drm/i915/gvt: add KVMGT support")
Signed-off-by: Chuanxiao Dong <chuanxiao.dong@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: stable@vger.kernel.org # v4.10+
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
The variable info is never NULL, which is checked by the caller. This
patch removes the redundant info NULL check logic.
Fixes: 695fbc08d8 ("drm/i915/gvt: replace the gvt_err with gvt_vgpu_err")
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
(cherry picked from commit 865f03d42e)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
This patch introduces two functions for activating/de-activating vGPU in
mdev ops.
A racing condition was found between virtual vblank emulation and KVGMT
mdev release path. V-blank emulation will emulate and inject V-blank
interrupt for every active vGPU with holding gvt->lock, while in mdev
release path, it will directly release hypervisor handle without changing
vGPU status or taking gvt->lock, so a kernel oops is encountered when
vblank emulation is injecting a interrupt with a invalid hypervisor
handle. (Reported by Terrence)
To solve this problem, we factor out vGPU activation/de-activation from
vGPU creation/destruction path and let KVMGT mdev release ops de-activate
the vGPU before release hypervisor handle. Once a vGPU is de-activated,
GVT-g will not emulate v-blank for it or touch the hypervisor handle.
Fixes: 659643f ("drm/i915/gvt/kvmgt: add vfio/mdev support to KVMGT")
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
The weight defines proportional control of physical GPU resource
shared between vGPUs. So far the weight is tied to a specific vGPU
type, i.e when creating multiple vGPUs with different types, they
will inherit different weights.
e.g. The weight of type GVTg_V5_2 is 8, the weight of type GVTg_V5_4
is 4, so vGPU of type GVTg_V5_2 has double vGPU resource of vGPU type
GVTg_V5_4.
TODO: allow user control the weight setting in the future.
Signed-off-by: Ping Gao <ping.a.gao@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
The variable info is never NULL, which is checked by the caller. This
patch removes the redundant info NULL check logic.
Fixes: 695fbc08d8 ("drm/i915/gvt: replace the gvt_err with gvt_vgpu_err")
Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
This adds initial attribute group for mdev to hold vGPU related
for each mdev device, currently just vGPU id is shown.
v2: rename group name as "intel_vgpu"
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
The kvmgt code keeps a pointer to the struct kvm associated with the
device, but doesn't actually hold a reference to it. If we do unclean
shutdown testing (ie. killing the user process), then we can see the
kvm association to the device unset, which causes kvmgt to trigger a
device release via a work queue. Naturally we cannot guarantee that
the cached struct kvm pointer is still valid at this point without
holding a reference. The observed failure in this case is a stuck
cpu trying to acquire the spinlock from the invalid reference, but
other failure modes are clearly possible. Hold a reference to avoid
this.
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Cc: stable@vger.kernel.org #v4.10
Cc: Jike Song <jike.song@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Reviewed-by: Jike Song <jike.song@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
