IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an
email to Administrator. User accounts are meant only to access repo
and report issues and/or generate pull requests.
This is a purpose-specific Git hosting for
BaseALT
projects. Thank you for your understanding!
Только зарегистрированные пользователи имеют доступ к сервису!
Для получения аккаунта, обратитесь к администратору.
A bug recently encountered involved the issue where are we were
submitting requests to different ppGTT, each would pin a segment of the
GGTT for its logical context and ring. However, this is invisible to
eviction as we do not tie the context/ring VMA to a request and so do
not automatically wait upon it them (instead they are marked as pinned,
preventing eviction entirely). Instead the eviction code must flush those
contexts by switching to the kernel context. This selftest tries to
fill the GGTT with contexts to exercise a path where the
switch-to-kernel-context failed to make forward progress and we fail
with ENOSPC.
v2: Make the hole in the filled GGTT explicit.
v3: Swap out the arbitrary timeout for a private notification from
i915_gem_evict_something()
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171012125726.14736-3-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
For some selftests, we want to issue requests but delay them going to
hardware. Furthermore, we don't want those requests to block
indefinitely (or else we may hang the driver and block testing) so we
want to employ a timeout. So naturally we want a fence that is
automatically signaled by a timer.
v2: Add kselftests.
v3: Limit the API available to selftests; there isn't an overwhelming
reason to export it universally.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171012125726.14736-2-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
stop_machine is not really a locking primitive we should use, except
when the hw folks tell us the hw is broken and that's the only way to
work around it.
This patch tries to address the locking abuse of stop_machine() from
commit 20e4933c478a1ca694b38fa4ac44d99e659941f5
Author: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue Nov 22 14:41:21 2016 +0000
drm/i915: Stop the machine as we install the wedged submit_request handler
Chris said parts of the reasons for going with stop_machine() was that
it's no overhead for the fast-path. But these callbacks use irqsave
spinlocks and do a bunch of MMIO, and rcu_read_lock is _real_ fast.
To stay as close as possible to the stop_machine semantics we first
update all the submit function pointers to the nop handler, then call
synchronize_rcu() to make sure no new requests can be submitted. This
should give us exactly the huge barrier we want.
I pondered whether we should annotate engine->submit_request as __rcu
and use rcu_assign_pointer and rcu_dereference on it. But the reason
behind those is to make sure the compiler/cpu barriers are there for
when you have an actual data structure you point at, to make sure all
the writes are seen correctly on the read side. But we just have a
function pointer, and .text isn't changed, so no need for these
barriers and hence no need for annotations.
Unfortunately there's a complication with the call to
intel_engine_init_global_seqno:
- Without stop_machine we must hold the corresponding spinlock.
- Without stop_machine we must ensure that all requests are marked as
having failed with dma_fence_set_error() before we call it. That
means we need to split the nop request submission into two phases,
both synchronized with rcu:
1. Only stop submitting the requests to hw and mark them as failed.
2. After all pending requests in the scheduler/ring are suitably
marked up as failed and we can force complete them all, also force
complete by calling intel_engine_init_global_seqno().
This should fix the followwing lockdep splat:
======================================================
WARNING: possible circular locking dependency detected
4.14.0-rc3-CI-CI_DRM_3179+ #1 Tainted: G U
------------------------------------------------------
kworker/3:4/562 is trying to acquire lock:
(cpu_hotplug_lock.rw_sem){++++}, at: [<ffffffff8113d4bc>] stop_machine+0x1c/0x40
but task is already holding lock:
(&dev->struct_mutex){+.+.}, at: [<ffffffffa0136588>] i915_reset_device+0x1e8/0x260 [i915]
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #6 (&dev->struct_mutex){+.+.}:
__lock_acquire+0x1420/0x15e0
lock_acquire+0xb0/0x200
__mutex_lock+0x86/0x9b0
mutex_lock_interruptible_nested+0x1b/0x20
i915_mutex_lock_interruptible+0x51/0x130 [i915]
i915_gem_fault+0x209/0x650 [i915]
__do_fault+0x1e/0x80
__handle_mm_fault+0xa08/0xed0
handle_mm_fault+0x156/0x300
__do_page_fault+0x2c5/0x570
do_page_fault+0x28/0x250
page_fault+0x22/0x30
-> #5 (&mm->mmap_sem){++++}:
__lock_acquire+0x1420/0x15e0
lock_acquire+0xb0/0x200
__might_fault+0x68/0x90
_copy_to_user+0x23/0x70
filldir+0xa5/0x120
dcache_readdir+0xf9/0x170
iterate_dir+0x69/0x1a0
SyS_getdents+0xa5/0x140
entry_SYSCALL_64_fastpath+0x1c/0xb1
-> #4 (&sb->s_type->i_mutex_key#5){++++}:
down_write+0x3b/0x70
handle_create+0xcb/0x1e0
devtmpfsd+0x139/0x180
kthread+0x152/0x190
ret_from_fork+0x27/0x40
-> #3 ((complete)&req.done){+.+.}:
__lock_acquire+0x1420/0x15e0
lock_acquire+0xb0/0x200
wait_for_common+0x58/0x210
wait_for_completion+0x1d/0x20
devtmpfs_create_node+0x13d/0x160
device_add+0x5eb/0x620
device_create_groups_vargs+0xe0/0xf0
device_create+0x3a/0x40
msr_device_create+0x2b/0x40
cpuhp_invoke_callback+0xc9/0xbf0
cpuhp_thread_fun+0x17b/0x240
smpboot_thread_fn+0x18a/0x280
kthread+0x152/0x190
ret_from_fork+0x27/0x40
-> #2 (cpuhp_state-up){+.+.}:
__lock_acquire+0x1420/0x15e0
lock_acquire+0xb0/0x200
cpuhp_issue_call+0x133/0x1c0
__cpuhp_setup_state_cpuslocked+0x139/0x2a0
__cpuhp_setup_state+0x46/0x60
page_writeback_init+0x43/0x67
pagecache_init+0x3d/0x42
start_kernel+0x3a8/0x3fc
x86_64_start_reservations+0x2a/0x2c
x86_64_start_kernel+0x6d/0x70
verify_cpu+0x0/0xfb
-> #1 (cpuhp_state_mutex){+.+.}:
__lock_acquire+0x1420/0x15e0
lock_acquire+0xb0/0x200
__mutex_lock+0x86/0x9b0
mutex_lock_nested+0x1b/0x20
__cpuhp_setup_state_cpuslocked+0x53/0x2a0
__cpuhp_setup_state+0x46/0x60
page_alloc_init+0x28/0x30
start_kernel+0x145/0x3fc
x86_64_start_reservations+0x2a/0x2c
x86_64_start_kernel+0x6d/0x70
verify_cpu+0x0/0xfb
-> #0 (cpu_hotplug_lock.rw_sem){++++}:
check_prev_add+0x430/0x840
__lock_acquire+0x1420/0x15e0
lock_acquire+0xb0/0x200
cpus_read_lock+0x3d/0xb0
stop_machine+0x1c/0x40
i915_gem_set_wedged+0x1a/0x20 [i915]
i915_reset+0xb9/0x230 [i915]
i915_reset_device+0x1f6/0x260 [i915]
i915_handle_error+0x2d8/0x430 [i915]
hangcheck_declare_hang+0xd3/0xf0 [i915]
i915_hangcheck_elapsed+0x262/0x2d0 [i915]
process_one_work+0x233/0x660
worker_thread+0x4e/0x3b0
kthread+0x152/0x190
ret_from_fork+0x27/0x40
other info that might help us debug this:
Chain exists of:
cpu_hotplug_lock.rw_sem --> &mm->mmap_sem --> &dev->struct_mutex
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(&dev->struct_mutex);
lock(&mm->mmap_sem);
lock(&dev->struct_mutex);
lock(cpu_hotplug_lock.rw_sem);
*** DEADLOCK ***
3 locks held by kworker/3:4/562:
#0: ("events_long"){+.+.}, at: [<ffffffff8109c64a>] process_one_work+0x1aa/0x660
#1: ((&(&i915->gpu_error.hangcheck_work)->work)){+.+.}, at: [<ffffffff8109c64a>] process_one_work+0x1aa/0x660
#2: (&dev->struct_mutex){+.+.}, at: [<ffffffffa0136588>] i915_reset_device+0x1e8/0x260 [i915]
stack backtrace:
CPU: 3 PID: 562 Comm: kworker/3:4 Tainted: G U 4.14.0-rc3-CI-CI_DRM_3179+ #1
Hardware name: /NUC7i5BNB, BIOS BNKBL357.86A.0048.2017.0704.1415 07/04/2017
Workqueue: events_long i915_hangcheck_elapsed [i915]
Call Trace:
dump_stack+0x68/0x9f
print_circular_bug+0x235/0x3c0
? lockdep_init_map_crosslock+0x20/0x20
check_prev_add+0x430/0x840
? irq_work_queue+0x86/0xe0
? wake_up_klogd+0x53/0x70
__lock_acquire+0x1420/0x15e0
? __lock_acquire+0x1420/0x15e0
? lockdep_init_map_crosslock+0x20/0x20
lock_acquire+0xb0/0x200
? stop_machine+0x1c/0x40
? i915_gem_object_truncate+0x50/0x50 [i915]
cpus_read_lock+0x3d/0xb0
? stop_machine+0x1c/0x40
stop_machine+0x1c/0x40
i915_gem_set_wedged+0x1a/0x20 [i915]
i915_reset+0xb9/0x230 [i915]
i915_reset_device+0x1f6/0x260 [i915]
? gen8_gt_irq_ack+0x170/0x170 [i915]
? work_on_cpu_safe+0x60/0x60
i915_handle_error+0x2d8/0x430 [i915]
? vsnprintf+0xd1/0x4b0
? scnprintf+0x3a/0x70
hangcheck_declare_hang+0xd3/0xf0 [i915]
? intel_runtime_pm_put+0x56/0xa0 [i915]
i915_hangcheck_elapsed+0x262/0x2d0 [i915]
process_one_work+0x233/0x660
worker_thread+0x4e/0x3b0
kthread+0x152/0x190
? process_one_work+0x660/0x660
? kthread_create_on_node+0x40/0x40
ret_from_fork+0x27/0x40
Setting dangerous option reset - tainting kernel
i915 0000:00:02.0: Resetting chip after gpu hang
Setting dangerous option reset - tainting kernel
i915 0000:00:02.0: Resetting chip after gpu hang
v2: Have 1 global synchronize_rcu() barrier across all engines, and
improve commit message.
v3: We need to protect the seqno update with the timeline spinlock (in
set_wedged) to avoid racing with other updates of the seqno, like we
already do in nop_submit_request (Chris).
v4: Use two-phase sequence to plug the race Chris spotted where we can
complete requests before they're marked up with -EIO.
v5: Review from Chris:
- simplify nop_submit_request.
- Add comment to rcu_read_lock section.
- Align comments with the new style.
v6: Remove unused variable to appease CI.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102886
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103096
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Marta Lofstedt <marta.lofstedt@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171011091019.1425-1-daniel.vetter@ffwll.ch
There's really no good reason to be using the kernel context for the
huge-page livetests. Also with the introduction of commit bef27bdb6cfb
("drm/i915: Assert we do not try to expand VMA for hugepage inside GGTT")
we start hitting the bug on in the selftests, since the kernel context
will always return true for i915_vma_is_ggtt(), so now seems like the
opportune time to instead create our own context.
Fixes: 4049866f0913 ("drm/i915/selftests: huge page tests")
Fixes: bef27bdb6cfb ("drm/i915: Assert we do not try to expand VMA for hugepage inside GGTT")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171010133030.12112-1-matthew.auld@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
It's a little unclear what the sg_mask actually is, so prefer the more
meaningful name of sg_page_sizes.
Suggested-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171009110024.29114-1-matthew.auld@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acquire the fence register for the iomap in i915_vma_pin_iomap() on
behalf of the caller.
We probably want for the caller to specify whether the fence should be
pinned for their usage, but at the moment all callers do want the
associated fence, or none, so take it on their behalf.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171009084401.29090-1-chris@chris-wilson.co.uk
The lowlevel reset functions expect the caller to be holding the rpm
wakeref for the device access across the reset. We were not explicitly
doing this in the sefltest, so for simplicity acquire the wakeref for
the duration of all subtests.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171009110301.21705-4-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
During hangcheck testing, we try to execute requests following the GPU
reset, and in particular want to try and debug when those fail.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171009110301.21705-2-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
v2: mock test page support configurations and add MI_STORE_DWORD test
v3: run all mockable huge page tests on all platforms via the mock_device
v4: add pin_update regression test
various improvements suggested by Chris
v5: fix issues reported by kbuild
test single sg spanning multiple page sizes
don't explode when running the live-tests through the appgtt
v6: lots of improvements from Chris
v7: run on each engine for igt_write_huge
add simple tmpfs fallback test
v8: size_t is bad
don't break the i386 build
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006145041.21673-18-matthew.auld@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006221833.32439-17-chris@chris-wilson.co.uk
Move the setting/clearing of the vma->pages to a vm operation. Doing so
neatens things up a little, but more importantly gives us a sane place
to also set/clear the vma->pages_sizes, which we introduce later in
preparation for supporting huge-pages.
v2: remove redundant vma->pages check
v3: GEM_BUG_ON(vma->pages) following i915_vma_remove
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006145041.21673-8-matthew.auld@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006221833.32439-7-chris@chris-wilson.co.uk
In preparation for supporting huge gtt pages for the ppgtt, we introduce
page size members for gem objects. We fill in the page sizes by
scanning the sg table.
v2: pass the sg_mask to set_pages
v3: calculate the sg_mask inline with populating the sg_table where
possible, and pass to set_pages along with the pages.
v4: bunch of improvements from Joonas
v5: fix num_pages blunder
introduce i915_sg_page_sizes helper
v6: prefer GEM_BUG_ON(sizes == 0)
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel@ffwll.ch>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006145041.21673-7-matthew.auld@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006221833.32439-6-chris@chris-wilson.co.uk
Each backend is now responsible for calling __i915_gem_object_set_pages
upon successfully gathering its backing storage. This eliminates the
inconsistency between the async and sync paths, which stands out even
more when we start throwing around an sg_mask in a later patch.
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006145041.21673-6-matthew.auld@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006221833.32439-5-chris@chris-wilson.co.uk
In preparation for huge gtt pages expose page_sizes as part of the
device info, to indicate the page sizes supported by the HW. Currently
only 4K is supported.
v2: s/page_size_mask/page_sizes/
v3: introduce I915_GTT_MAX_PAGE_SIZE
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006145041.21673-5-matthew.auld@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006221833.32439-4-chris@chris-wilson.co.uk
Not a fully blown gemfs, just our very own tmpfs kernel mount. Doing so
moves us away from the shmemfs shm_mnt, and gives us the much needed
flexibility to do things like set our own mount options, namely huge=
which should allow us to enable the use of transparent-huge-pages for
our shmem backed objects.
v2: various improvements suggested by Joonas
v3: move gemfs instance to i915.mm and simplify now that we have
file_setup_with_mnt
v4: fallback to tmpfs shm_mnt upon failure to setup gemfs
v5: make tmpfs fallback kinder
v5: better gemfs failure message
flags variable
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Hugh Dickins <hughd@google.com>
Cc: linux-mm@kvack.org
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006145041.21673-3-matthew.auld@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20171006221833.32439-2-chris@chris-wilson.co.uk
An earlier bugfix tried to work around this build failure:
drivers/gpu/drm/i915/selftests/mock_gem_device.c: In function 'mock_gem_device':
drivers/gpu/drm/i915/selftests/mock_gem_device.c:151:20: error: 'struct dev_archdata' has no member named 'iommu'
Checking for CONFIG_IOMMU_API is not sufficient as a compile-time
test since that may be enabled in configurations that have neither
INTEL_IOMMU not AMD_IOMMU enabled. This changes the check to
INTEL_IOMMU instead, as this is the only case we actually care about.
Fixes: f46f156ea770 ("drm/i915/selftests: Only touch archdata.iommu when it exists")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20171005120749.400818-1-arnd@arndb.de
For the fake device we have our own set of mock contexts that need to
match the real contexts we normally create. Currently this requires us
to manually instantiate them for the selftests, which I forgot.
Reported-by: Matthew Auld <matthew.william.auld@gmail.com>
Fixes: e7af3116836f ("drm/i915: Introduce a preempt context")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171005105927.22991-1-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Currently, we are being fairly lazy and only using a wmb() following an
update to an active batch. Previously, we have found that to be
insufficient to ensure that a write from the CPU reaches memory in a
timely fashion, and in some caches we may need to flush a chipset cache.
To that end, we have i915_gem_chipset_flush() so use it.
Suggested-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170926153409.7928-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
If we see the seqno stop progressing, we abandon the test for fear that
the GPU died following the reset. However, during test teardown we still
wait for the GPU to idle before continuing, but we have already
confirmed that the GPU is dead. Furthermore, since we are inside a reset
test, we have disabled the hangchecker, and so there is no safety net and
we wait indefinitely. Detect the stuck GPU and declare it wedged as a
state of emergency so we can escape.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jari Tahvanainen <jari.tahvanainen@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170915130929.18892-1-chris@chris-wilson.co.uk
Tested-by: Jari Tahvanainen <jari.tahvanainen@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
archdata.iommu only exists when CONFIG_IOMMU_API is enabled (and only
applies to intel-iommu in our case) so conditionally compile it out when
it doesn't exist.
Fixes: b5891fb520f7 ("drm/i915/selftests: Disable iommu for the mock device")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170918164652.14200-1-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
On some machines, the iommu cannot allocate a domain for the mock device
causing the dma_map_sg() to fail, and the selftest to fail with -ENOMEM.
For the mock selftests, we are using a fake device and do not care about
iommu; so convince intel_iommu to treat us as a dummy device with an
identity mapping (and no iommu domain).
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101080
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170914162240.18310-1-chris@chris-wilson.co.uk
Tested-by: Elizabeth De La Torre Mena <elizabethx.de.la.torre.mena@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com
GFP_TEMPORARY was introduced by commit e12ba74d8ff3 ("Group short-lived
and reclaimable kernel allocations") along with __GFP_RECLAIMABLE. It's
primary motivation was to allow users to tell that an allocation is
short lived and so the allocator can try to place such allocations close
together and prevent long term fragmentation. As much as this sounds
like a reasonable semantic it becomes much less clear when to use the
highlevel GFP_TEMPORARY allocation flag. How long is temporary? Can the
context holding that memory sleep? Can it take locks? It seems there is
no good answer for those questions.
The current implementation of GFP_TEMPORARY is basically GFP_KERNEL |
__GFP_RECLAIMABLE which in itself is tricky because basically none of
the existing caller provide a way to reclaim the allocated memory. So
this is rather misleading and hard to evaluate for any benefits.
I have checked some random users and none of them has added the flag
with a specific justification. I suspect most of them just copied from
other existing users and others just thought it might be a good idea to
use without any measuring. This suggests that GFP_TEMPORARY just
motivates for cargo cult usage without any reasoning.
I believe that our gfp flags are quite complex already and especially
those with highlevel semantic should be clearly defined to prevent from
confusion and abuse. Therefore I propose dropping GFP_TEMPORARY and
replace all existing users to simply use GFP_KERNEL. Please note that
SLAB users with shrinkers will still get __GFP_RECLAIMABLE heuristic and
so they will be placed properly for memory fragmentation prevention.
I can see reasons we might want some gfp flag to reflect shorterm
allocations but I propose starting from a clear semantic definition and
only then add users with proper justification.
This was been brought up before LSF this year by Matthew [1] and it
turned out that GFP_TEMPORARY really doesn't have a clear semantic. It
seems to be a heuristic without any measured advantage for most (if not
all) its current users. The follow up discussion has revealed that
opinions on what might be temporary allocation differ a lot between
developers. So rather than trying to tweak existing users into a
semantic which they haven't expected I propose to simply remove the flag
and start from scratch if we really need a semantic for short term
allocations.
[1] http://lkml.kernel.org/r/20170118054945.GD18349@bombadil.infradead.org
[akpm@linux-foundation.org: fix typo]
[akpm@linux-foundation.org: coding-style fixes]
[sfr@canb.auug.org.au: drm/i915: fix up]
Link: http://lkml.kernel.org/r/20170816144703.378d4f4d@canb.auug.org.au
Link: http://lkml.kernel.org/r/20170728091904.14627-1-mhocko@kernel.org
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Mel Gorman <mgorman@suse.de>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Neil Brown <neilb@suse.de>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
As realised by commit 9e3d6223d209 ("math64, timers: Fix 32bit
mul_u64_u32_shr() and friends"), GCC does not always generate ideal code
for performing a 32b x 32b multiply returning a 64b result (i.e. where
we idiomatically use u64 result = (u64)x * (u32)x).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913105154.2910-2-chris@chris-wilson.co.uk
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
This was the competing idea long ago, but it was only with the rewrite
of the idr as an radixtree and using the radixtree directly ourselves,
along with the realisation that we can store the vma directly in the
radixtree and only need a list for the reverse mapping, that made the
patch performant enough to displace using a hashtable. Though the vma ht
is fast and doesn't require any extra allocation (as we can embed the node
inside the vma), it does require a thread for resizing and serialization
and will have the occasional slow lookup. That is hairy enough to
investigate alternatives and favour them if equivalent in peak performance.
One advantage of allocating an indirection entry is that we can support a
single shared bo between many clients, something that was done on a
first-come first-serve basis for shared GGTT vma previously. To offset
the extra allocations, we create yet another kmem_cache for them.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170816085210.4199-5-chris@chris-wilson.co.uk
MI_STORE_DWORD_IMM just doesn't work on the video decode engine under
Sandybridge, so refrain from using it. Then switch the selftests over to
using the now common test prior to using MI_STORE_DWORD_IMM.
Fixes: 7dd4f6729f92 ("drm/i915: Async GPU relocation processing")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: <drm-intel-fixes@lists.freedesktop.org> # v4.13-rc1+
Link: https://patchwork.freedesktop.org/patch/msgid/20170816085210.4199-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Another month, another story in the cache coherency saga. This time, we
come to the realisation that i915_gem_object_is_coherent() has been
reporting whether we can read from the target without requiring a cache
invalidate; but we were using it in places for testing whether we could
write into the object without requiring a cache flush. So split the
tracking into two, one to decide before reads, one after writes.
See commit e27ab73d17ef ("drm/i915: Mark CPU cache as dirty on every
transition for CPU writes") for the previous entry in this saga.
v2: Be verbose
v3: Remove unused function (i915_gem_object_is_coherent)
v4: Fix inverted coherency check prior to execbuf (from v2)
v5: Add comment for nasty code where we are optimising on gcc's behalf.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101109
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101555
Testcase: igt/kms_mmap_write_crc
Testcase: igt/kms_pwrite_crc
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Dongwon Kim <dongwon.kim@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Tested-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170811111116.10373-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
In the original selftest, we didn't care what the engine->id was, just
that it could uniquely identify it. Later though, we started tracking
the mock engines in the fixed size arrays around the drm_i915_private and
so we now require their indices to be correct. This becomes an issue when
using the standalone harness which runs all available tests at module load,
and so we quickly assign an out-of-bounds index to an engine as we
reallocate the mock GEM device between tests. It doesn't show up in
igt/drv_selftest as that runs each subtest individually.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102045
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170809163930.26470-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
The purpose of the test was to check per-engine resets would fallback to
the global reset when required, but first we actually need a test for a
basic i915_handle_error()!
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170728112110.6464-1-chris@chris-wilson.co.uk
After applying af2788925ae0 ("drm/i915: Squelch reset messages during
selftests") out of sequence, I missed fixing up a call to i915_reset().
Reported-by: kbuild test robot <kbuild-all@01.org>
Fixes: af2788925ae0 ("drm/i915: Squelch reset messages during selftests")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170725125336.11969-1-chris@chris-wilson.co.uk
Reviewed-by: David Weinehall <david.weinehall@linux.intel.com
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
During our selftests, we try reseting the GPU tens of thousands of
times, flooding the dmesg with our reset spam drowning out any potential
warnings. Add an option to i915_reset()/i915_reset_engine() to specify a
quiet reset for selftesting.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170721123238.16428-19-chris@chris-wilson.co.uk
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Extract the common barrier against rogue hangchecks from disrupting our
direct testing of resets, and in the process expand the lock to include
the per-engine reset shortcuts.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170721123238.16428-17-chris@chris-wilson.co.uk
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
If all goes well, resetting one engine should not affect the operation of
any others. So to test this, we setup a continuous stream of requests
onto to each of the "innocent" engines whilst constantly resetting our
target engine.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170721123238.16428-16-chris@chris-wilson.co.uk
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Goto the right label in case of error, otherwise there is a leak.
This has been introduced by c5cf9a9147ff. In this patch a goto has not been
updated.
Fixes: c5cf9a9147ff ("drm/i915: Create a kmem_cache to allocate struct i915_priolist from")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://patchwork.freedesktop.org/patch/msgid/20170719223503.30580-1-christophe.jaillet@wanadoo.fr
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
We need to unpin the last retired context early in the shutdown sequence
so that its RCU free is done before we try to free the context ida. I
included this in a later patch ("drm/i915: Keep a recent cache of freed
contexts objects for reuse") and so missed that the selftests were broken
in the meantime.
Reported-by: Matthew Auld <matthew.auld@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101627
Fixes: 5f09a9c8ab6b ("drm/i915: Allow contexts to be unreferenced locklessly")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170719135957.14603-1-chris@chris-wilson.co.uk
Tested-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Supply a pm_domain and its ops for our mock GEM device so that
device runtime pm doesn't complain even though we only want to mark it
permanently active!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170718173028.31207-1-chris@chris-wilson.co.uk
Tested-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Workers on the i915->wq may rearm themselves so for completeness we need
to replace our flush_workqueue() with a call to drain_workqueue() before
unloading the device.
v2: Reinforce the drain_workqueue with an preceding rcu_barrier() as a
few of the tasks that need to be drained may first be armed by RCU.
References: https://bugs.freedesktop.org/show_bug.cgi?id=101627
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170718134124.14832-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
'dma_buf_vmap' returns NULL on error, not an error pointer.
Fixes: 6cca22ede8a4 ("drm/i915: Add some mock tests for dmabuf interop")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: http://patchwork.freedesktop.org/patch/msgid/20170627053854.21152-1-christophe.jaillet@wanadoo.fr
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
The vma already contains most of the information we need for insertion.
But also in preparation for supporting huge gtt pages, it would be
useful to know the details of the vma, such that we can we can easily
determine the page sizes we are allowed to use when inserting into the
48b PPGTT. This is especially true for 64K where we can't just
arbitrarily use it, since we require aligning/padding the vm space to
2M, which sometimes we can't enforce in the upper levels.
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/20170622095836.6800-1-matthew.auld@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
If we enter i915_handle_error() a second time and a global reset is
already in progress, we can simply wait for completion of the first
reset. Currently we exit early prior to the actual reset being
performed -- the worst of both worlds!
v2: Plug into the existing reset_queue, and remember that kselftests is
playing games with I915_RESET_BACKOFF to prevent hangcheck from screwing
up.
v3: Rename to i915_reset_device to fit in better with i915_reset_engine
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170620095751.13127-2-chris@chris-wilson.co.uk
If we move the actual cleanup of the context to a worker, we can allow
the final free to be called from any context and avoid undue latency in
the caller.
v2: Negotiate handling the delayed contexts free by flushing the
workqueue before calling i915_gem_context_fini() and performing the final
free of the kernel context directly
v3: Flush deferred frees before new context allocations
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170620110547.15947-2-chris@chris-wilson.co.uk
The major scaling bottleneck in execbuffer is the processing of the
execobjects. Creating an auxiliary list is inefficient when compared to
using the execobject array we already have allocated.
Reservation is then split into phases. As we lookup up the VMA, we
try and bind it back into active location. Only if that fails, do we add
it to the unbound list for phase 2. In phase 2, we try and add all those
objects that could not fit into their previous location, with fallback
to retrying all objects and evicting the VM in case of severe
fragmentation. (This is the same as before, except that phase 1 is now
done inline with looking up the VMA to avoid an iteration over the
execobject array. In the ideal case, we eliminate the separate reservation
phase). During the reservation phase, we only evict from the VM between
passes (rather than currently as we try to fit every new VMA). In
testing with Unreal Engine's Atlantis demo which stresses the eviction
logic on gen7 class hardware, this speed up the framerate by a factor of
2.
The second loop amalgamation is between move_to_gpu and move_to_active.
As we always submit the request, even if incomplete, we can use the
current request to track active VMA as we perform the flushes and
synchronisation required.
The next big advancement is to avoid copying back to the user any
execobjects and relocations that are not changed.
v2: Add a Theory of Operation spiel.
v3: Fall back to slow relocations in preparation for flushing userptrs.
v4: Document struct members, factor out eb_validate_vma(), add a few
more comments to explain some magic and hide other magic behind macros.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
The advent of full-ppgtt lead to an extra indirection between the object
and its binding. That extra indirection has a noticeable impact on how
fast we can convert from the user handles to our internal vma for
execbuffer. In order to bypass the extra indirection, we use a
resizable hashtable to jump from the object to the per-ctx vma.
rhashtable was considered but we don't need the online resizing feature
and the extra complexity proved to undermine its usefulness. Instead, we
simply reallocate the hastable on demand in a background task and
serialize it before iterating.
In non-full-ppgtt modes, multiple files and multiple contexts can share
the same vma. This leads to having multiple possible handle->vma links,
so we only use the first to establish the fast path. The majority of
buffers are not shared and so we should still be able to realise
speedups with multiple clients.
v2: Prettier names, more magic.
v3: Many style tweaks, most notably hiding the misuse of execobj[].rsvd2
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
For ease of use (i.e. avoiding a few checks and function calls), store
the object's cache coherency next to the cache is dirty bit.
Specifically this patch aims to reduce the frequency of no-op calls to
i915_gem_object_clflush() to counter-act the increase of such calls for
GPU only objects in the previous patch.
v2: Replace cache_dirty & ~cache_coherent with cache_dirty &&
!cache_coherent as gcc generates much better code for the latter
(Tvrtko)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Dongwon Kim <dongwon.kim@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Tested-by: Dongwon Kim <dongwon.kim@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170616105455.16977-1-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Currently, we only mark the CPU cache as dirty if we skip a clflush.
This leads to some confusion where we have to ask if the object is in
the write domain or missed a clflush. If we always mark the cache as
dirty, this becomes a much simply question to answer.
The goal remains to do as few clflushes as required and to do them as
late as possible, in the hope of deferring the work to a kthread and not
block the caller (e.g. execbuf, flips).
v2: Always call clflush before GPU execution when the cache_dirty flag
is set. This may cause some extra work on llc systems that migrate dirty
buffers back and forth - but we do try to limit that by only setting
cache_dirty at the end of the gpu sequence.
v3: Always mark the cache as dirty upon a level change, as we need to
invalidate any stale cachelines due to external writes.
Reported-by: Dongwon Kim <dongwon.kim@intel.com>
Fixes: a6a7cc4b7db6 ("drm/i915: Always flush the dirty CPU cache when pinning the scanout")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Dongwon Kim <dongwon.kim@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Tested-by: Dongwon Kim <dongwon.kim@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170615123850.26843-1-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
