Commit Graph

26 Commits

Author SHA1 Message Date
Christian König
76bf0db554 dma-buf/fence: make fence context 64 bit v2
Fence contexts are created on the fly (for example) by the GPU scheduler used
in the amdgpu driver as a result of an userspace request. Because of this
userspace could in theory force a wrap around of the 32bit context number
if it doesn't behave well.

Avoid this by increasing the context number to 64bits. This way even when
userspace manages to allocate a billion contexts per second it takes more
than 500 years for the context number to wrap around.

v2: fix printf formats as well.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Acked-by: Sumit Semwal <sumit.semwal@linaro.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1464786612-5010-2-git-send-email-deathsimple@vodafone.de
2016-06-02 08:27:41 +02:00
Daniel Vetter
1c0230de6d drm/vmwgfx: Nuke preclose hook
Again since the drm core takes care of event unlinking/disarming this
is now just needless code.

v2: I've completely missed eaction->fpriv_head and all the related
code. We need to nuke that too to avoid accidentally deferencing the
freed-up vmwgfx-private fpriv.

v3: Also remove vmw_fpriv->fence_events and unused variables I missed.

Cc: Thomas Hellström <thellstrom@vmware.com>
Acked-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1452548477-15905-23-git-send-email-daniel.vetter@ffwll.ch
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
2016-02-08 09:55:53 +01:00
Dan Carpenter
15b6b804b6 drm/vmwgfx: fix a NULL dereference
We dereference "eaction->event" inside the call to drm_send_event_locked()
so should hold off on setting it to NULL until afterward.

Fixes: fb740cf249 ("drm: Create drm_send_event helpers")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160128090646.GA5824@mwanda
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2016-01-28 10:28:15 +01:00
Daniel Vetter
fb740cf249 drm: Create drm_send_event helpers
Use them in the core vblank code and exynos/vmwgfx drivers.

Note that the difference between wake_up_all and _interruptible in
vmwgfx doesn't matter since the only waiter is the core code in
drm_fops.c. And that is interruptible.

v2: Adjust existing kerneldoc too.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com> (v1)
Acked-by: Daniel Stone <daniels@collabora.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Inki Dae <inki.dae@samsung.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1452548477-15905-6-git-send-email-daniel.vetter@ffwll.ch
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
[danvet: Squash in compile fixup, spotted by 0-day.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2016-01-25 19:34:43 +01:00
Daniel Vetter
6d3729ac13 drm/vmwgfx: Use the new event init/free functions
Cc: Rob Clark <robdclark@gmail.com
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Acked-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1452548477-15905-5-git-send-email-daniel.vetter@ffwll.ch
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2016-01-25 08:40:34 +01:00
Thomas Hellstrom
b76ff5ea1c drm/vmwgfx: Replace iowrite/ioread with volatile memory accesses
Now that we use memremap instead of ioremap, Use WRITE_ONCE / READ_ONCE
instead of iowrite / ioread.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
2015-11-02 00:16:05 -08:00
Sinclair Yeh
54fbde8a94 drm/vmwgfx: Fix copyright headers
Updating and fixing copyright headers.
Bump version minor to signal vgpu10 support.

Signed-off-by: Sinclair Yeh <syeh@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
2015-08-12 10:06:56 -07:00
Thomas Hellstrom
b9eb1a6174 drm/vmwgfx: Kill a bunch of sparse warnings
We're giving up all attempts to keep cpu- and device byte ordering separate.

This silences sparse when compiled using
make C=2 CF="-D__CHECK_ENDIAN__"

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
2015-08-05 14:01:11 +02:00
Thomas Hellstrom
496eb6fd2c drm/vmwgfx: Replace the hw mutex with a hw spinlock
Fixes a case where we call vmw_fifo_idle() from within a wait function with
task state !TASK_RUNNING, which is illegal.

In addition, make the locking fine-grained, so that it is performed once
for every read- and write operation. This is of course more costly, but we
don't perform much register access in the timing critical paths anyway. Instead
we have the extra benefit of being sure that we don't forget the hw lock around
register accesses. I think currently the kms code was quite buggy w r t this.

This fixes Red Hat Bugzilla Bug 1180796

Cc: stable@vger.kernel.org
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
2015-01-19 03:02:13 -08:00
Thomas Hellstrom
89669e7a7f drm/vmwgfx: Fix fence event code
The commit "vmwgfx: Rework fence event action" introduced a number of bugs
that are fixed with this commit:

a) A forgotten return stateemnt.
b) An if statement with identical branches.

Cc: <stable@vger.kernel.org>
Reported-by: Rob Clark <robdclark@gmail.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
2014-12-03 00:48:14 -08:00
Thomas Hellstrom
1f563a6a46 drm/vmwgfx: Don't use memory accounting for kernel-side fence objects
Kernel side fence objects are used when unbinding resources and may thus be
created as part of a memory reclaim operation. This might trigger recursive
memory reclaims and result in the kernel running out of stack space.

So a simple way out is to avoid accounting of these fence objects.
In principle this is OK since while user-space can trigger the creation of
such objects, it can't really hold on to them. However, their lifetime is
quite long, so some form of accounting should perhaps be implemented in the
future.

Fixes kernel crashes when running, for example viewperf11 ensight-04 test 3
with low system memory settings.

Cc: <stable@vger.kernel.org>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
2014-12-03 00:48:14 -08:00
Maarten Lankhorst
2298e804e9 drm/vmwgfx: rework to new fence interface, v2
Use the new fence interface on vmwgfx too.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>

---
Changes since v1:
Fix a sleeping function called from invalid context in enable_signaling.
2014-09-02 16:41:50 +02:00
Maarten Lankhorst
c060a4e135 drm/vmwgfx: get rid of different types of fence_flags entirely
Only one type was ever used. This is needed to simplify the fence
support in the next commit.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@canonical.com>
2014-09-02 16:41:50 +02:00
Rashika Kheria
94844cf065 drivers: gpu: Mark functions as static in vmwgfx_fence.c
Mark functions as static because they are not used outside the file
drm/vmwgfx/vmwgfx_fence.c.

This eliminates the following warnings in drm/vmwgfx/vmwgfx_fence.c:
drivers/gpu/drm/vmwgfx/vmwgfx_fence.c:274:6: warning: no previous prototype for ‘vmw_fences_perform_actions’ [-Wmissing-prototypes]
drivers/gpu/drm/vmwgfx/vmwgfx_fence.c:900:6: warning: no previous prototype for ‘vmw_fence_obj_add_action’ [-Wmissing-prototypes]
drivers/gpu/drm/vmwgfx/vmwgfx_fence.c:996:5: warning: no previous prototype for ‘vmw_event_fence_action_create’ [-Wmissing-prototypes]

Signed-off-by: Rashika Kheria <rashika.kheria@gmail.com>
Reviewed-by: Josh Triplett <josh@joshtriplett.org>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
2014-01-08 13:45:56 +01:00
Thomas Hellstrom
05efb1abec drm/ttm: ttm object security fixes for render nodes
When a client looks up a ttm object, don't look it up through the device hash
table, but rather from the file hash table. That makes sure that the client
has indeed put a reference on the object, or in gem terms, has opened
the object; either using prime or using the global "name".

To avoid a performance loss, make sure the file hash table entries can be
looked up from under an RCU lock, and as a consequence, replace the rwlock
with a spinlock, since we never need to take it in read mode only anymore.

Finally add a ttm object lookup function for the device hash table, that is
intended to be used when we put a ref object on a base object or, in  gem terms,
when we open the object.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
2014-01-08 10:11:57 +01:00
Thomas Hellstrom
35f62a5829 drm/vmwgfx: Free user-space fence objects correctly
They need to be freed after an rcu grace period.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2012-11-28 18:36:12 +10:00
David Howells
760285e7e7 UAPI: (Scripted) Convert #include "..." to #include <path/...> in drivers/gpu/
Convert #include "..." to #include <path/...> in drivers/gpu/.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Dave Airlie <airlied@redhat.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Dave Jones <davej@redhat.com>
2012-10-02 18:01:07 +01:00
Dan Carpenter
68c4fce737 vmwgfx: corruption in vmw_event_fence_action_create()
We don't allocate enough data for this struct.  As soon as we start
modifying event->event on the next lines, then we're going beyond the
end of the memory we allocated.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@gmail.com>
2012-09-26 18:40:06 +10:00
Thomas Hellstrom
6b82ef50d8 vmwgfx: Clean up pending event references to struct drm_file objects on close
Pending events may have stale pointer references to struct drm_file objects
after a file has been closed, but before the event is supposed to be
attached to the drm file. Remove such events on file close.

Tested with "modetest".

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2012-02-13 12:01:32 +00:00
Jakob Bornecrantz
8b7de6aa84 vmwgfx: Rework fence event action
Signed-off-by: Jakob Bornecrantz <jakob@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2012-02-13 12:01:31 +00:00
Dan Carpenter
0c5d37033b vmwgfx: memory leaks caused by double allocation
These variables get allocated twice so the first allocation is a
memory leak.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-10-18 10:41:31 +01:00
Thomas Hellstrom
57c5ee79ac vmwgfx: Add fence events
Add a way to send DRM events down the gpu fifo by attaching them to
fence objects. This may be useful for Xserver swapbuffer throttling and
page-flip done notifications.

Bump version to 2.2 to signal the availability of the FENCE_EVENT ioctl.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-10-10 15:46:55 +01:00
Thomas Hellstrom
e93daed8e2 vmwgfx: Allow reference and unreference of NULL fence objects.
The execbuf utils may call reference on NULL fence objects.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-10-05 10:17:21 +01:00
Thomas Hellstrom
ae2a104058 vmwgfx: Implement fence objects
Will be needed for queries and drm event-driven throttling.

As a benefit, they help avoid stale user-space fence handles.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-09-06 11:51:11 +01:00
Thomas Hellstrom
6bcd8d3c78 vmwgfx: Fix confusion caused by using "fence" in various places
This is needed before we introduce the fence objects.
Otherwise this will be even more confusing. The plan is to use the following:

seqno: A 32-bit sequence number that may be passed in the fifo.
marker: Objects, carrying a seqno, that track fifo submission time. They
are used for fifo lag based throttling.
fence objects: Kernel space objects, possibly accessible from user-space and
carrying a 32-bit seqno together with signaled status.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Jakob Bornecrantz <jakob@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2011-09-06 11:48:40 +01:00
Thomas Hellstrom
1925d45658 drm/vmwgfx: Add kernel throttling support. Bump minor.
The throttle_us member in the execbuf argument is now honored.
If the member is 0, no waiting for lag will occur, which
guarantees backwards compatibility with well-behaved clients.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
2010-06-01 09:37:15 +10:00