This patch is analogous to the previous sync file export patch in that
it allows you to import a sync_file into a dma-buf. Unlike the previous
patch, however, this does add genuinely new functionality to dma-buf.
Without this, the only way to attach a sync_file to a dma-buf is to
submit a batch to your driver of choice which waits on the sync_file and
claims to write to the dma-buf. Even if said batch is a no-op, a submit
is typically way more overhead than just attaching a fence. A submit
may also imply extra synchronization with other work because it happens
on a hardware queue.
In the Vulkan world, this is useful for dealing with the out-fence from
vkQueuePresent. Current Linux window-systems (X11, Wayland, etc.) all
rely on dma-buf implicit sync. Since Vulkan is an explicit sync API, we
get a set of fences (VkSemaphores) in vkQueuePresent and have to stash
those as an exclusive (write) fence on the dma-buf. We handle it in
Mesa today with the above mentioned dummy submit trick. This ioctl
would allow us to set it directly without the dummy submit.
This may also open up possibilities for GPU drivers to move away from
implicit sync for their kernel driver uAPI and instead provide sync
files and rely on dma-buf import/export for communicating with other
implicit sync clients.
We make the explicit choice here to only allow setting RW fences which
translates to an exclusive fence on the dma_resv. There's no use for
read-only fences for communicating with other implicit sync userspace
and any such attempts are likely to be racy at best. When we got to
insert the RW fence, the actual fence we set as the new exclusive fence
is a combination of the sync_file provided by the user and all the other
fences on the dma_resv. This ensures that the newly added exclusive
fence will never signal before the old one would have and ensures that
we don't break any dma_resv contracts. We require userspace to specify
RW in the flags for symmetry with the export ioctl and in case we ever
want to support read fences in the future.
There is one downside here that's worth documenting: If two clients
writing to the same dma-buf using this API race with each other, their
actions on the dma-buf may happen in parallel or in an undefined order.
Both with and without this API, the pattern is the same: Collect all
the fences on dma-buf, submit work which depends on said fences, and
then set a new exclusive (write) fence on the dma-buf which depends on
said work. The difference is that, when it's all handled by the GPU
driver's submit ioctl, the three operations happen atomically under the
dma_resv lock. If two userspace submits race, one will happen before
the other. You aren't guaranteed which but you are guaranteed that
they're strictly ordered. If userspace manages the fences itself, then
these three operations happen separately and the two render operations
may happen genuinely in parallel or get interleaved. However, this is a
case of userspace racing with itself. As long as we ensure userspace
can't back the kernel into a corner, it should be fine.
v2 (Jason Ekstrand):
- Use a wrapper dma_fence_array of all fences including the new one
when importing an exclusive fence.
v3 (Jason Ekstrand):
- Lock around setting shared fences as well as exclusive
- Mark SIGNAL_SYNC_FILE as a read-write ioctl.
- Initialize ret to 0 in dma_buf_wait_sync_file
v4 (Jason Ekstrand):
- Use the new dma_resv_get_singleton helper
v5 (Jason Ekstrand):
- Rename the IOCTLs to import/export rather than wait/signal
- Drop the WRITE flag and always get/set the exclusive fence
v6 (Jason Ekstrand):
- Split import and export into separate patches
- New commit message
v7 (Daniel Vetter):
- Fix the uapi header to use the right struct in the ioctl
- Use a separate dma_buf_import_sync_file struct
- Add kerneldoc for dma_buf_import_sync_file
v8 (Jason Ekstrand):
- Rebase on Christian König's fence rework
v9 (Daniel Vetter):
- Fix -EINVAL checks for the flags parameter
- Add documentation about read/write fences
- Add documentation about the expected usage of import/export and
specifically call out the possible userspace race.
v10 (Simon Ser):
- Fix a typo in the docs
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Jason Ekstrand <jason.ekstrand@intel.com>
Signed-off-by: Jason Ekstrand <jason.ekstrand@collabora.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Simon Ser <contact@emersion.fr>
Link: https://patchwork.freedesktop.org/patch/msgid/20220608152142.14495-3-jason@jlekstrand.net
Modern userspace APIs like Vulkan are built on an explicit
synchronization model. This doesn't always play nicely with the
implicit synchronization used in the kernel and assumed by X11 and
Wayland. The client -> compositor half of the synchronization isn't too
bad, at least on intel, because we can control whether or not i915
synchronizes on the buffer and whether or not it's considered written.
The harder part is the compositor -> client synchronization when we get
the buffer back from the compositor. We're required to be able to
provide the client with a VkSemaphore and VkFence representing the point
in time where the window system (compositor and/or display) finished
using the buffer. With current APIs, it's very hard to do this in such
a way that we don't get confused by the Vulkan driver's access of the
buffer. In particular, once we tell the kernel that we're rendering to
the buffer again, any CPU waits on the buffer or GPU dependencies will
wait on some of the client rendering and not just the compositor.
This new IOCTL solves this problem by allowing us to get a snapshot of
the implicit synchronization state of a given dma-buf in the form of a
sync file. It's effectively the same as a poll() or I915_GEM_WAIT only,
instead of CPU waiting directly, it encapsulates the wait operation, at
the current moment in time, in a sync_file so we can check/wait on it
later. As long as the Vulkan driver does the sync_file export from the
dma-buf before we re-introduce it for rendering, it will only contain
fences from the compositor or display. This allows to accurately turn
it into a VkFence or VkSemaphore without any over-synchronization.
By making this an ioctl on the dma-buf itself, it allows this new
functionality to be used in an entirely driver-agnostic way without
having access to a DRM fd. This makes it ideal for use in driver-generic
code in Mesa or in a client such as a compositor where the DRM fd may be
hard to reach.
v2 (Jason Ekstrand):
- Use a wrapper dma_fence_array of all fences including the new one
when importing an exclusive fence.
v3 (Jason Ekstrand):
- Lock around setting shared fences as well as exclusive
- Mark SIGNAL_SYNC_FILE as a read-write ioctl.
- Initialize ret to 0 in dma_buf_wait_sync_file
v4 (Jason Ekstrand):
- Use the new dma_resv_get_singleton helper
v5 (Jason Ekstrand):
- Rename the IOCTLs to import/export rather than wait/signal
- Drop the WRITE flag and always get/set the exclusive fence
v6 (Jason Ekstrand):
- Drop the sync_file import as it was all-around sketchy and not nearly
as useful as import.
- Re-introduce READ/WRITE flag support for export
- Rework the commit message
v7 (Jason Ekstrand):
- Require at least one sync flag
- Fix a refcounting bug: dma_resv_get_excl() doesn't take a reference
- Use _rcu helpers since we're accessing the dma_resv read-only
v8 (Jason Ekstrand):
- Return -ENOMEM if the sync_file_create fails
- Predicate support on IS_ENABLED(CONFIG_SYNC_FILE)
v9 (Jason Ekstrand):
- Add documentation for the new ioctl
v10 (Jason Ekstrand):
- Go back to dma_buf_sync_file as the ioctl struct name
v11 (Daniel Vetter):
- Go back to dma_buf_export_sync_file as the ioctl struct name
- Better kerneldoc describing what the read/write flags do
v12 (Christian König):
- Document why we chose to make it an ioctl on dma-buf
v13 (Jason Ekstrand):
- Rebase on Christian König's fence rework
v14 (Daniel Vetter & Christian König):
- Use dma_rev_usage_rw to get the properly inverted usage to pass to
dma_resv_get_singleton()
- Clean up the sync_file and fd if copy_to_user() fails
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Jason Ekstrand <jason.ekstrand@intel.com>
Signed-off-by: Jason Ekstrand <jason.ekstrand@collabora.com>
Acked-by: Simon Ser <contact@emersion.fr>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Simon Ser <contact@emersion.fr>
Link: https://patchwork.freedesktop.org/patch/msgid/20220608152142.14495-2-jason@jlekstrand.net
Linux 5.18-rc5
There was a build fix for arm I wanted in drm-next, so backmerge rather then cherry-pick.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Pull kvm fixes from Paolo Bonzini:
"ARM:
- Take care of faults occuring between the PARange and IPA range by
injecting an exception
- Fix S2 faults taken from a host EL0 in protected mode
- Work around Oops caused by a PMU access from a 32bit guest when PMU
has been created. This is a temporary bodge until we fix it for
good.
x86:
- Fix potential races when walking host page table
- Fix shadow page table leak when KVM runs nested
- Work around bug in userspace when KVM synthesizes leaf 0x80000021
on older (pre-EPYC) or Intel processors
Generic (but affects only RISC-V):
- Fix bad user ABI for KVM_EXIT_SYSTEM_EVENT"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
KVM: x86: work around QEMU issue with synthetic CPUID leaves
Revert "x86/mm: Introduce lookup_address_in_mm()"
KVM: x86/mmu: fix potential races when walking host page table
KVM: fix bad user ABI for KVM_EXIT_SYSTEM_EVENT
KVM: x86/mmu: Do not create SPTEs for GFNs that exceed host.MAXPHYADDR
KVM: arm64: Inject exception on out-of-IPA-range translation fault
KVM/arm64: Don't emulate a PMU for 32-bit guests if feature not set
KVM: arm64: Handle host stage-2 faults from 32-bit EL0
Pull arm64 fix from Will Deacon:
"Rename and reallocate the PT_ARM_MEMTAG_MTE ELF segment type.
This is a fix to the MTE ELF ABI for a bug that was added during the
most recent merge window as part of the coredump support.
The issue is that the value assigned to the new PT_ARM_MEMTAG_MTE
segment type has already been allocated to PT_AARCH64_UNWIND by the
ELF ABI, so we've bumped the value and changed the name of the
identifier to be better aligned with the existing one"
* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
elf: Fix the arm64 MTE ELF segment name and value
Fixes for (relatively) old bugs, to be merged in both the -rc and next
development trees:
* Fix potential races when walking host page table
* Fix bad user ABI for KVM_EXIT_SYSTEM_EVENT
* Fix shadow page table leak when KVM runs nested
When KVM_EXIT_SYSTEM_EVENT was introduced, it included a flags
member that at the time was unused. Unfortunately this extensibility
mechanism has several issues:
- x86 is not writing the member, so it would not be possible to use it
on x86 except for new events
- the member is not aligned to 64 bits, so the definition of the
uAPI struct is incorrect for 32- on 64-bit userspace. This is a
problem for RISC-V, which supports CONFIG_KVM_COMPAT, but fortunately
usage of flags was only introduced in 5.18.
Since padding has to be introduced, place a new field in there
that tells if the flags field is valid. To allow further extensibility,
in fact, change flags to an array of 16 values, and store how many
of the values are valid. The availability of the new ndata field
is tied to a system capability; all architectures are changed to
fill in the field.
To avoid breaking compilation of userspace that was using the flags
field, provide a userspace-only union to overlap flags with data[0].
The new field is placed at the same offset for both 32- and 64-bit
userspace.
Cc: Will Deacon <will@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Peter Gonda <pgonda@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reported-by: kernel test robot <lkp@intel.com>
Message-Id: <20220422103013.34832-1-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Pull fbdev fixes and updates from Helge Deller:
"A bunch of outstanding fbdev patches - all trivial and small"
* tag 'for-5.18/fbdev-2' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/linux-fbdev:
video: fbdev: clps711x-fb: Use syscon_regmap_lookup_by_phandle
video: fbdev: mmp: replace usage of found with dedicated list iterator variable
video: fbdev: sh_mobile_lcdcfb: Remove sh_mobile_lcdc_check_var() declaration
video: fbdev: i740fb: Error out if 'pixclock' equals zero
video: fbdev: i740fb: use memset_io() to clear screen
video: fbdev: s3fb: Error out if 'pixclock' equals zero
video: fbdev: arkfb: Error out if 'pixclock' equals zero
video: fbdev: tridentfb: Error out if 'pixclock' equals zero
video: fbdev: vt8623fb: Error out if 'pixclock' equals zero
video: fbdev: kyro: Error out if 'lineclock' equals zero
video: fbdev: neofb: Fix the check of 'var->pixclock'
video: fbdev: imxfb: Fix missing of_node_put in imxfb_probe
video: fbdev: omap: Make it CCF clk API compatible
video: fbdev: aty/matrox/...: Prepare cleanup of powerpc's asm/prom.h
video: fbdev: pm2fb: Fix a kernel-doc formatting issue
linux/fb.h: Spelling s/palette/palette/
video: fbdev: sis: fix potential NULL dereference in sisfb_post_sis300()
video: fbdev: pxafb: use if else instead
video: fbdev: udlfb: properly check endpoint type
video: fbdev: of: display_timing: Remove a redundant zeroing of memory
Pull input fixes from Dmitry Torokhov:
- a new set of keycodes to be used by marine navigation systems
- minor fixes to omap4-keypad and cypress-sf drivers
* tag 'input-for-v5.18-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/dtor/input:
Input: add Marine Navigation Keycodes
Input: omap4-keypad - fix pm_runtime_get_sync() error checking
Input: cypress-sf - register a callback to disable the regulators
In order to get the GSC Support merged on drm-intel-gt-next
in a clean fashion we needed this ATS-M patch to avoid
conflict in i915_pci.c:
commit 412c942bdf ("drm/i915/ats-m: add ATS-M platform info")
--
Fixing a silent conflict on drivers/gpu/drm/i915/gt/intel_gt_gmch.c:
- if (!intel_vtd_active(i915))
+ if (!i915_vtd_active(i915))
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Pull io_uring fixes from Jens Axboe:
- Ensure we check and -EINVAL any use of reserved or struct padding.
Although we generally always do that, it's missed in two spots for
resource updates, one for the ring fd registration from this merge
window, and one for the extended arg. Make sure we have all of them
handled. (Dylan)
- A few fixes for the deferred file assignment (me, Pavel)
- Add a feature flag for the deferred file assignment so apps can tell
we handle it correctly (me)
- Fix a small perf regression with the current file position fix in
this merge window (me)
* tag 'io_uring-5.18-2022-04-14' of git://git.kernel.dk/linux-block:
io_uring: abort file assignment prior to assigning creds
io_uring: fix poll error reporting
io_uring: fix poll file assign deadlock
io_uring: use right issue_flags for splice/tee
io_uring: verify pad field is 0 in io_get_ext_arg
io_uring: verify resv is 0 in ringfd register/unregister
io_uring: verify that resv2 is 0 in io_uring_rsrc_update2
io_uring: move io_uring_rsrc_update2 validation
io_uring: fix assign file locking issue
io_uring: stop using io_wq_work as an fd placeholder
io_uring: move apoll->events cache
io_uring: io_kiocb_update_pos() should not touch file for non -1 offset
io_uring: flag the fact that linked file assignment is sane
Newer platforms have DSS that aren't necessarily available for both
geometry and compute, two queries will need to exist. This introduces
the first, when passing a valid engine class and engine instance in the
flags returns a topology describing geometry.
Based on past discussion, we currently only support this new query item
on Xe_HP and beyond; earlier platforms do not need to worry about
geometry and compute pipelines having access to different topology and
should continue to use the existing topology query.
v2: fix white space errors
v3: change flags from hosting 2 8 bit numbers to holding a
i915_engine_class_instance struct
v4: add error if non rcs engine passed.
v5 (by MattR):
- Improve kerneldoc and cross references to related structs/enums.
(Daniel)
- Clarify that geometry query is only supported on render engines
(Francisco)
- Clarify that the new query is only supported on Xe_HP+.
- Fix checkpatch warnings.
Cc: Ashutosh Dixit <ashutosh.dixit@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Francisco Jerez <currojerez@riseup.net>
UMD (mesa): https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14143
Testcase: igt@i915_query@test-query-geometry-subslices
Signed-off-by: Matt Atwood <matthew.s.atwood@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20220414192230.749771-4-matthew.d.roper@intel.com
Pull hardening fixes from Kees Cook:
- latent_entropy: Use /dev/urandom instead of small GCC seed (Jason
Donenfeld)
- uapi/stddef.h: add missed include guards (Tadeusz Struk)
* tag 'hardening-v5.18-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux:
gcc-plugins: latent_entropy: use /dev/urandom
uapi/linux/stddef.h: Add include guards
Sync up with v5.18-rc1, in particular to get 5e3094cfd9
("drm/i915/xehpsdv: Add has_flat_ccs to device info").
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Give applications a way to tell if the kernel supports sane linked files,
as in files being assigned at the right time to be able to reliably
do <open file direct into slot X><read file from slot X> while using
IOSQE_IO_LINK to order them.
Not really a bug fix, but flag it as such so that it gets pulled in with
backports of the deferred file assignment.
Fixes: 6bf9c47a39 ("io_uring: defer file assignment")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Jason Ekstrand
Dave Airlie
Linus Torvalds
Paolo Bonzini
Catalin Marinas
Rodrigo Vivi
Shelby Heffron
Matt Atwood
Matt Roper
Mika Kahola
Joonas Lahtinen
Jani Nikula
Jens Axboe
Maxime Ripard