On resume, we know that the only pinned contexts in danger of seeing
corruption are the kernel context, and so we do not need to walk the
list of all GEM contexts as we tracked them on each engine.
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/20190410190120.830-1-chris@chris-wilson.co.uk
It used to be handy that we only had a couple of headers, but over time
intel_drv.h has become unwieldy. Extract declarations to a separate
header file corresponding to the implementation module, clarifying the
modularity of the driver.
Ensure the new header is self-contained, and do so with minimal further
includes, using forward declarations as needed. Include the new header
only where needed, and sort the modified include directives while at it
and as needed.
No functional changes.
v2: gen6_rps_reset_ei() is in i915_irq.c not intel_pm.c.
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/adc6463b95eef3440fba9826793f7d1c5f3b0b4a.1554461791.git.jani.nikula@intel.com
Mixing u8 and -1u together leads to zero-extended integer expansion, and
comparing 0x000000ff against 0xffffffff, causing us to report a mixed
uabi-class request as not busy.
The input flag is a u8, and we want to generate a u32 uABI response,
mark our functions so.
Fixes: c8b502422b ("drm/i915: Remove last traces of exec-id (GEM_BUSY)")
Testcase: igt/gem_exec_balance/busy
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190404101914.7231-1-chris@chris-wilson.co.uk
If the user passes in a pointer to a GGTT mmaping of the same buffer
being written to, we can hit a deadlock in acquiring the shmemfs page
(once as the write destination and then as the read source).
[<0>] io_schedule+0xd/0x30
[<0>] __lock_page+0x105/0x1b0
[<0>] find_lock_entry+0x55/0x90
[<0>] shmem_getpage_gfp+0xbb/0x800
[<0>] shmem_read_mapping_page_gfp+0x2d/0x50
[<0>] shmem_get_pages+0x158/0x5d0 [i915]
[<0>] ____i915_gem_object_get_pages+0x17/0x90 [i915]
[<0>] __i915_gem_object_get_pages+0x57/0x70 [i915]
[<0>] i915_gem_fault+0x1b4/0x5c0 [i915]
[<0>] __do_fault+0x2d/0x80
[<0>] __handle_mm_fault+0xad4/0xfb0
[<0>] handle_mm_fault+0xe6/0x1f0
[<0>] __do_page_fault+0x18f/0x3f0
[<0>] page_fault+0x1b/0x20
[<0>] copy_user_enhanced_fast_string+0x7/0x10
[<0>] _copy_from_user+0x37/0x60
[<0>] shmem_pwrite+0xf0/0x160 [i915]
[<0>] i915_gem_pwrite_ioctl+0x14e/0x520 [i915]
[<0>] drm_ioctl_kernel+0x81/0xd0
[<0>] drm_ioctl+0x1a7/0x310
[<0>] do_vfs_ioctl+0x88/0x5d0
[<0>] ksys_ioctl+0x35/0x70
[<0>] __x64_sys_ioctl+0x11/0x20
[<0>] do_syscall_64+0x39/0xe0
[<0>] entry_SYSCALL_64_after_hwframe+0x44/0xa9
We can reduce (but not eliminate!) the chance of this happening by
faulting the user_data before we take the page lock in
pagecache_write_begin(). One way to eliminate the potential recursion
here is by disabling pagefaults for the copy, and handling the fallback
to use an alternative method -- so convert to use kmap_atomic (which
should disable preemption and pagefaulting for the copy) and report
ENODEV instead of EFAULT so that our caller tries again with a different
copy mechanism -- we already check that the page should have been
faultable so a false negative should be rare.
Testcase: igt/gem_pwrite/self
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190401133909.31203-1-chris@chris-wilson.co.uk
When we return pages to the system, we release control over them and
should defensively return them to the CPU write domain so that we catch
any external writes on reacquiring them (e.g. to transparently
swapout/swapin). While we did this defensive clflushing for ordinary
shmem pages, it was forgotten for userptr. Fortunately, userptr objects
are normally cache coherent and so oblivious to the forgotten domain
tracking.
References: a679f58d05 ("drm/i915: Flush pages on acquisition")
References: 754a254427 ("drm/i915: Skip object locking around a no-op set-domain ioctl")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190331094620.15185-1-chris@chris-wilson.co.uk
Since GEM_CREATE is trying to outsmart the user by rounding up unaligned
objects, we used to update the size returned to userspace.
This update seems to have been lost throughout the history.
v2: Use round_up(), reorder locals (Chris)
References: ff72145bad ("drm: dumb scanout create/mmap for intel/radeon (v3)")
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Janusz Krzysztofik <janusz.krzysztofik@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190326170218.13255-1-michal.winiarski@intel.com
Since commit b7137e0cf1 ("drm/i915: Defer enabling rc6 til after we
submit the first batch/context"), intel_suspend_gt_powersave() has been
a no-op. As we still do not need to do anything explicitly on suspend
(we do everything required on idling), remove the defunct function.
References: b7137e0cf1 ("drm/i915: Defer enabling rc6 til after we submit the first batch/context")
Suggested-by: "Hiatt, Don" <don.hiatt@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190323214009.23294-1-chris@chris-wilson.co.uk
Adding a call to intel_uc_suspend in i915_gem_suspend, which
is a common point for the suspend/resume and hibernate paths.
This fixes an unbalanced call that causes issues with the CTB
register/deregister.
v2: Making the call unconditional (Daniele)
Moving the call to after the GEM_BUG_ON (Chris)
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Sujaritha Sundaresan <sujaritha.sundaresan@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190321203804.6845-1-sujaritha.sundaresan@intel.com
If we are already in the desired write domain of a set-domain ioctl,
then there is nothing for us to do and we can quickly return back to
userspace, avoiding any lock contention. By recognising that the
write_domain is always a subset of the read_domains, and excluding the
no-op case of requiring 0 read_domains in the ioctl, we can infer if the
current write_domain matches the target read_domains, there is nothing
for us to do.
Secondary aspect of this is that we undo the arbitrary fetching and
potential flushing of all pages for a set-domain(.write=CPU) call on a
fresh object -- which was introduced simply because we do the get-pages
before taking the struct_mutex.
References: 40e62d5d6b ("drm/i915: Acquire the backing storage outside of struct_mutex in set-domain")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190321161908.8007-2-chris@chris-wilson.co.uk
When we return pages to the system, we ensure that they are marked as
being in the CPU domain since any external access is uncontrolled and we
must assume the worst. This means that we need to always flush the pages
on acquisition if we need to use them on the GPU, and from the beginning
have used set-domain. Set-domain is overkill for the purpose as it is a
general synchronisation barrier, but our intent is to only flush the
pages being swapped in. If we move that flush into the pages acquisition
phase, we know then that when we have obj->mm.pages, they are coherent
with the GPU and need only maintain that status without resorting to
heavy handed use of set-domain.
The principle knock-on effect for userspace is through mmap-gtt
pagefaulting. Our uAPI has always implied that the GTT mmap was async
(especially as when any pagefault occurs is unpredicatable to userspace)
and so userspace had to apply explicit domain control itself
(set-domain). However, swapping is transparent to the kernel, and so on
first fault we need to acquire the pages and make them coherent for
access through the GTT. Our use of set-domain here leaks into the uABI
that the first pagefault was synchronous. This is unintentional and
baring a few igt should be unoticed, nevertheless we bump the uABI
version for mmap-gtt to reflect the change in behaviour.
Another implication of the change is that gem_create() is presumed to
create an object that is coherent with the CPU and is in the CPU write
domain, so a set-domain(CPU) following a gem_create() would be a minor
operation that merely checked whether we could allocate all pages for
the object. On applying this change, a set-domain(CPU) causes a clflush
as we acquire the pages. This will have a small impact on mesa as we move
the clflush here on !llc from execbuf time to create, but that should
have minimal performance impact as the same clflush exists but is now
done early and because of the clflush issue, userspace recycles bo and
so should resist allocating fresh objects.
Internally, the presumption that objects are created in the CPU
write-domain and remain so through writes to obj->mm.mapping is more
prevalent than I expected; but easy enough to catch and apply a manual
flush.
For the future, we should push the page flush from the central
set_pages() into the callers so that we can more finely control when it
is applied, but for now doing it one location is easier to validate, at
the cost of sometimes flushing when there is no need.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Antonio Argenziano <antonio.argenziano@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190321161908.8007-1-chris@chris-wilson.co.uk
Now that the internal code all works on intel_uncore, flip the
external-facing interface.
v2: fix GVT.
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190319183543.13679-4-daniele.ceraolospurio@intel.com
Switch to bitmap_zalloc() to show clearly what we are allocating.
Besides that it returns pointer of bitmap type instead of opaque void *.
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190304092908.57382-2-andriy.shevchenko@linux.intel.com
We assumed that vm_mmap() would reject an attempt to mmap past the end of
the filp (our object), but we were wrong.
Applications that tried to use the mmap beyond the end of the object
would be greeted by a SIGBUS. After this patch, those applications will
be told about the error on creating the mmap, rather than at a random
moment on later access.
Reported-by: Antonio Argenziano <antonio.argenziano@intel.com>
Testcase: igt/gem_mmap/bad-size
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Antonio Argenziano <antonio.argenziano@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190314075829.16838-1-chris@chris-wilson.co.uk
It is debatable whether having an error message on suspend for forcibly
cancelling outstanding work is worthwhile. We want to know if it occurs
in the wild (as we will then have to reconsider the approach!), but
equally is not fatal across suspend, as upon resume we automatically
clear the wedged status.
However, CI does trigger this scenario with gem_eio/suspend; as there we
are intentionally wedging the device upon suspend. The dilemma is how
not to trigger a failure report for the dmesg spam, for which the
quickest response is to suppress the warning in the kernel. I'd rather
mark it as accepted in gem_eio, but for now detecting when gem_eio is
playing games and cancelling the warning for that case seems a barely
acceptable hack.
Testcase: igt/gem_eio/suspend
Reference: 5861b013e2 ("drm/i915: Do a synchronous switch-to-kernel-context on idling")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190308134512.19115-1-chris@chris-wilson.co.uk
Introduce a mutex to start locking the HW contexts independently of
struct_mutex, with a view to reducing the coarse struct_mutex. The
intel_context.pin_mutex is used to guard the transition to and from being
pinned on the gpu, and so is required before starting to build any
request. The intel_context will then remain pinned until the request
completes, but the mutex can be released immediately unpin completion of
pinning the context.
A slight variant of the above is used by per-context sseu that wants to
inspect the pinned status of the context, and requires that it remains
stable (either !pinned or pinned) across its operation. By using the
pin_mutex to serialise operations while pin_count==0, we can take that
pin_mutex for stabilise the boolean pin status.
v2: for Tvrtko!
* Improved commit message.
* Dropped _gpu suffix from gen8_modify_rpcs_gpu.
v3: Repair the locking for sseu selftests
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190308132522.21573-7-chris@chris-wilson.co.uk
In preparation for an ever growing number of engines and so ever
increasing static array of HW contexts within the GEM context, move the
array over to an rbtree, allocated upon first use.
Unfortunately, this imposes an rbtree lookup at a few frequent callsites,
but we should be able to mitigate those by moving over to using the HW
context as our primary type and so only incur the lookup on the boundary
with the user GEM context and engines.
v2: Check for no HW context in guc_stage_desc_init
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190308132522.21573-4-chris@chris-wilson.co.uk
We can no longer assume execution ordering, and in particular we cannot
assume which context will execute last. One side-effect of this is that
we cannot determine if the kernel-context is resident on the GPU, so
remove the routines that claimed to do so.
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/20190308093657.8640-4-chris@chris-wilson.co.uk
Currently we assume that we know the order in which requests run and so
can determine if we need to reissue a switch-to-kernel-context prior to
idling. That assumption does not hold for the future, so instead of
tracking which barriers have been used, simply determine if we have ever
switched away from the kernel context by using the engine and before
idling ensure that all engines that have been used since the last idle
are synchronously switched back to the kernel context for safety (and
else of shrinking memory while idle).
v2: Use intel_engine_mask_t and ALL_ENGINES
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/20190308093657.8640-3-chris@chris-wilson.co.uk
We load a context (the kernel context) on both module load and resume in
order to initialise some logical state onto the GPU. We can use the same
routine for both operations, which will become more useful as we
refactor rc6/rps enabling.
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/20190308093657.8640-2-chris@chris-wilson.co.uk
When the system idles, we switch to the kernel context as a defensive
measure (no users are harmed if the kernel context is lost). Currently,
we issue a switch to kernel context and then come back later to see if
the kernel context is still current and the system is idle. However,
if we are no longer privy to the runqueue ordering, then we have to
relax our assumptions about the logical state of the GPU and the only
way to ensure that the kernel context is currently loaded is by issuing
a request to run after all others, and wait for it to complete all while
preventing anyone else from issuing their own requests.
v2: Pull wedging into switch_to_kernel_context_sync() but only after
waiting (though only for the same short delay) for the active context to
finish.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190308093657.8640-1-chris@chris-wilson.co.uk
To facilitate the next patch to allow preemptible kernels not to incur
the wrath of hangcheck, we need to ensure that we can still suspend and
shutdown. That is we will not be able to rely on hangcheck to terminate
a blocking kernel and instead must manually do so ourselves. The
advantage is that we can apply more pressure!
As we now perform a GPU reset to clean up any residual kernels, we leave
the GPU in an unknown state and in particular can not talk to the GuC
before we reinitialise it following resume. For example, we no longer
need to tell the GuC to suspend itself, as it is already reset.
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/20190307104530.21745-2-chris@chris-wilson.co.uk
Currently we use HZ/5 for detecting a dead gpu on startup, and we will
wish to reuse this value for detecting a dead gpu on suspend, so convert
it into a macro for later convenience.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190307104530.21745-1-chris@chris-wilson.co.uk
Legacy behaviour was to allow non-page-aligned mmap requests, as does the
linux mmap(2) implementation by virtue of automatically rounding up for
the caller.
To avoid breaking legacy userspace relax the newly introduced fix.
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Fixes: 5c4604e757 ("drm/i915: Prevent a race during I915_GEM_MMAP ioctl with WC set")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Cc: Adam Zabrocki <adamza@microsoft.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: <stable@vger.kernel.org> # v4.0+
Cc: Akash Goel <akash.goel@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: intel-gfx@lists.freedesktop.org
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190305110409.28633-1-tvrtko.ursulin@linux.intel.com
To find the active request, we need only search along the individual
engine for the right request. This does not require touching any global
GEM state, so move it into the engine compartment.
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/20190305180332.30900-3-chris@chris-wilson.co.uk
As we allow per-context engine allows the legacy concept of
I915_EXEC_RING no longer applies universally. We are still exposing the
unrelated exec-id in GEM_BUSY, so transition this ioctl (once more
slightly changing its ABI, but no one cares) over to only reporting the
uabi-class (not instance as we can not foreseeably fit those into the
small bitmask).
The only user of the extended ring information from GEM_BUSY is ddx/sna,
which tries to use the non-rcs business information to guide which
engine to use for subsequent operations on foreign bo. All that matters
for it is the decision between rcs and !rcs, so it is unaffected by the
change in higher bits.
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/20190305162643.20243-1-chris@chris-wilson.co.uk
We currently use a worker queued from an rcu callback to determine when
a how grace period has elapsed while we remained idle. We use this idle
delay to infer that we will be idle for a while and this is a suitable
point at which we can trim our global memory caches.
Since we wrote that, this mechanism now exists as rcu_work, and having
converted the idle shrinkers over to using that, we can remove our own
variant.
v2: Say goodbye to gt.epoch as well.
v3: Remove the misplaced and redundant comment before parking globals
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190228102035.5857-3-chris@chris-wilson.co.uk
As kmem_caches share the same properties (size, allocation/free behaviour)
for all potential devices, we can use global caches. While this
potential has worse fragmentation behaviour (one can argue that
different devices would have different activity lifetimes, but you can
also argue that activity is temporal across the system) it is the
default behaviour of the system at large to amalgamate matching caches.
The benefit for us is much reduced pointer dancing along the frequent
allocation paths.
v2: Defer shrinking until after a global grace period for futureproofing
multiple consumers of the slab caches, similar to the current strategy
for avoiding shrinking too early.
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/20190228102035.5857-1-chris@chris-wilson.co.uk
unlikely has already included in IS_ERR(), so just
remove redundant likely/unlikely annotation.
Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190221020819.21832-1-cgxu519@gmx.com
Annoyingly, struct_mutex was not entirely eliminated from the reset
pathway; for reasons of its own, intel_display_resume() requires
struct_mutex to prepare the planes it already captured. To avoid the
immediate problem of a deadlock between the struct_mutex and the reset
srcu, we have to acquire the reset_lock before struct_mutex in
i915_gem_fault(). Now any wait underneath struct_mutex will result us in
having to forcibly reset all inflight rendering, less than ideal, but
better than a deadlock (and will do for the short term).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190221102924.13442-1-chris@chris-wilson.co.uk
At a few points in our uABI, we check to see if the driver is wedged and
report -EIO back to the user in that case. However, as we perform the
check and reset asynchronously (where once before they were both
serialised by the struct_mutex), we may instead see the temporary wedging
used to cancel inflight rendering to avoid a deadlock during reset
(caused by either us timing out in our reset handler,
i915_wedge_on_timeout or with malice aforethought in intel_reset_prepare
for a stuck modeset). If we suspect this is the case, that is we see a
wedged driver *and* reset in progress, then wait until the reset is
resolved before reporting upon the wedged status.
v2: might_sleep() (Mika)
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109580
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190220145637.23503-1-chris@chris-wilson.co.uk
As time goes by, usage of generic ioctls such as drm_syncobj and
sync_file are on the increase bypassing i915-specific ioctls like
GEM_WAIT. Currently, we only apply waitboosting to our driver ioctls as
we track the file/client and account the waitboosting to them. However,
since commit 7b92c1bd05 ("drm/i915: Avoid keeping waitboost active for
signaling threads"), we no longer have been applying the client
ratelimiting on waitboosts and so that information has only been used
for debug tracking.
Push the application of waitboosting down to the common
i915_request_wait, and apply it to all foreign fence waits as well.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Eero Tamminen <eero.t.tamminen@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190213092504.25709-1-chris@chris-wilson.co.uk
We cannot nest i915_reset_trylock() as the inner may wait for the
I915_RESET_BACKOFF which in turn is waiting upon sync_srcu who is
waiting for our outermost lock. As we take the reset srcu around the
fence update, we have to defer taking it in i915_gem_fault() until after
we acquire the pin on the fence to avoid nesting. This is a little ugly,
but still works. If a reset occurs between i915_vma_pin_fence() and the
second reset lock, the reset will restore the fence register back to the
pinned value before the reset lock allows us to proceed (our mmap won't
be revoked as we haven't yet marked it as being a userfault as that
requires us to hold the reset lock), so the pagefault is still
serialised with the revocation in reset.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109605
Fixes: 2caffbf117 ("drm/i915: Revoke mmaps and prevent access to fence registers across reset")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190212130831.14425-1-chris@chris-wilson.co.uk
- Expose RPCS (SSEU) configuration to userspace for Ice Lake
in order to allow userspace to reconfigure the subslice config
per context basis. (Tvrtko, Lionel)
Driver Changes:
- Execbuf and preemption improvements including selftests (Chris)
- Rename HAS_GMCH_DISPLAY/HAS_GMCH (Rodrigo)
- Debugfs error handling fix for robustness (Greg)
- Improve reg_rw traces (Ville)
- Push clear_intel_crtc_state onto the heap (Chris)
- Watermark fixes for Ice Lake (Ville)
- Fix enable count array size and bounds checking (Tvrtko)
- MST Fixes (Lyude)
- Prevent race and handle error on I915_GEM_MMAP (Joonas)
- Initial rework for an full atomic gamma mode (Ville)
-----BEGIN PGP SIGNATURE-----
iQEcBAABAgAGBQJcXJw7AAoJEPpiX2QO6xPKWuQH/i3o86TqLheae2vdi8X/yp92
XeZbmNfaL7Gui6ggZpRMREjIIiDZ0nFga5INcVtrak6JRjeefb+wQsy38tdb98ne
EPn6eif0nO/uxc7BsdW2ndIDBSWC+ZW7gt4rzY5zLG/WCmX1qfOOS9GdUpXPF3jY
sB8Af6lsGSxrCFkBzUB9Z7AyoP/Yq+YeamFOtXLufhtQb4GL3djjdugaUBBfQmNn
FvZTxhhsXn3HU9Jy1AjRFALhqXvTjZt1L5myav4sCJ2qlsr2dL9y3c7evbO5jrZY
4TSlKUi5XwfW1RlHTQN43fTq7yWFwoF1FsR4LaKS0a8bKIXiBLwset7YA1m6wmY=
=Woo8
-----END PGP SIGNATURE-----
Merge tag 'drm-intel-next-2019-02-07' of git://anongit.freedesktop.org/drm/drm-intel into drm-next
UAPI Changes:
- Expose RPCS (SSEU) configuration to userspace for Ice Lake
in order to allow userspace to reconfigure the subslice config
per context basis. (Tvrtko, Lionel)
Driver Changes:
- Execbuf and preemption improvements including selftests (Chris)
- Rename HAS_GMCH_DISPLAY/HAS_GMCH (Rodrigo)
- Debugfs error handling fix for robustness (Greg)
- Improve reg_rw traces (Ville)
- Push clear_intel_crtc_state onto the heap (Chris)
- Watermark fixes for Ice Lake (Ville)
- Fix enable count array size and bounds checking (Tvrtko)
- MST Fixes (Lyude)
- Prevent race and handle error on I915_GEM_MMAP (Joonas)
- Initial rework for an full atomic gamma mode (Ville)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190208165000.GA30314@intel.com
Previously, we were able to rely on the recursive properties of
struct_mutex to allow us to serialise revoking mmaps and reacquiring the
FENCE registers with them being clobbered over a global device reset.
I then proceeded to throw out the baby with the bath water in order to
pursue a struct_mutex-less reset.
Perusing LWN for alternative strategies, the dilemma on how to serialise
access to a global resource on one side was answered by
https://lwn.net/Articles/202847/ -- Sleepable RCU:
1 int readside(void) {
2 int idx;
3 rcu_read_lock();
4 if (nomoresrcu) {
5 rcu_read_unlock();
6 return -EINVAL;
7 }
8 idx = srcu_read_lock(&ss);
9 rcu_read_unlock();
10 /* SRCU read-side critical section. */
11 srcu_read_unlock(&ss, idx);
12 return 0;
13 }
14
15 void cleanup(void)
16 {
17 nomoresrcu = 1;
18 synchronize_rcu();
19 synchronize_srcu(&ss);
20 cleanup_srcu_struct(&ss);
21 }
No more worrying about stop_machine, just an uber-complex mutex,
optimised for reads, with the overhead pushed to the rare reset path.
However, we do run the risk of a deadlock as we allocate underneath the
SRCU read lock, and the allocation may require a GPU reset, causing a
dependency cycle via the in-flight requests. We resolve that by declaring
the driver wedged and cancelling all in-flight rendering.
v2: Use expedited rcu barriers to match our earlier timing
characteristics.
v3: Try to annotate locking contexts for sparse
v4: Reduce selftest lock duration to avoid a reset deadlock with fences
v5: s/srcu/reset_backoff_srcu/
v6: Remove more stale comments
Testcase: igt/gem_mmap_gtt/hang
Fixes: eb8d0f5af4 ("drm/i915: Remove GPU reset dependence on struct_mutex")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190208153708.20023-2-chris@chris-wilson.co.uk
Add err goto label and use it when VMA can't be established or changes
underneath.
v2:
- Dropping Fixes: as it's indeed impossible to race an object to the
error address. (Chris)
v3:
- Use IS_ERR_VALUE (Chris)
Reported-by: Adam Zabrocki <adamza@microsoft.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Adam Zabrocki <adamza@microsoft.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> #v2
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190207085454.10598-2-joonas.lahtinen@linux.intel.com
Make sure the underlying VMA in the process address space is the
same as it was during vm_mmap to avoid applying WC to wrong VMA.
A more long-term solution would be to have vm_mmap_locked variant
in linux/mmap.h for when caller wants to hold mmap_sem for an
extended duration.
v2:
- Refactor the compare function
Fixes: 1816f92363 ("drm/i915: Support creation of unbound wc user mappings for objects")
Reported-by: Adam Zabrocki <adamza@microsoft.com>
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: <stable@vger.kernel.org> # v4.0+
Cc: Akash Goel <akash.goel@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Cc: Adam Zabrocki <adamza@microsoft.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> #v1
Link: https://patchwork.freedesktop.org/patch/msgid/20190207085454.10598-1-joonas.lahtinen@linux.intel.com
Looking forward, we need to break the struct_mutex dependency on
i915_gem_active. In the meantime, external use of i915_gem_active is
quite beguiling, little do new users suspect that it implies a barrier
as each request it tracks must be ordered wrt the previous one. As one
of many, it can be used to track activity across multiple timelines, a
shared fence, which fits our unordered request submission much better. We
need to steer external users away from the singular, exclusive fence
imposed by i915_gem_active to i915_active instead. As part of that
process, we move i915_gem_active out of i915_request.c into
i915_active.c to start separating the two concepts, and rename it to
i915_active_request (both to tie it to the concept of tracking just one
request, and to give it a longer, less appealing name).
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/20190205130005.2807-5-chris@chris-wilson.co.uk
- Icelake display fixes (Ville, Imre)
- Workarounds fixes and reorg (Tvrtko, Talha)
- Enable fastboot by default on VLV and CHV (Hans)
- Add another PCI ID for Coffee Lake (Rodrigo)
-----BEGIN PGP SIGNATURE-----
iQEcBAABAgAGBQJcVVKOAAoJEPpiX2QO6xPKzpEH/11faCaucfkejXnR2ff3H/Rc
EQILDB+SFwzKYaxd8pLHXJ7D8stmBGW4i086bic1JFTxIi/MtQv5rfOO87jqu1DU
3FFgCLuovzmheKVMuPxnSwGXn2ZI3RWPoDrH7OGaOtKuNAfoFTL9upZYsmBOyA+8
srraU1zHhhR3pawqqVpGrXCVToKSYQc/mh9Od1v491yoqMEhC6r2JaGiePZQldn9
J99ouBDOHMM1f45UX4+ORNQB951sQhJ4SW8e2bi2jKuc5WNmX3+tGLYdKemq3OYN
vi3a4xwSPkhbGWUSQtT7Cy6e2p43p/k7CwVl1iEESVB7HOqINwmxY/UIxm3ap1s=
=Q8JK
-----END PGP SIGNATURE-----
Merge tag 'drm-intel-next-2019-02-02' of git://anongit.freedesktop.org/drm/drm-intel into drm-next
- Make background color and LUT more robust (Matt)
- Icelake display fixes (Ville, Imre)
- Workarounds fixes and reorg (Tvrtko, Talha)
- Enable fastboot by default on VLV and CHV (Hans)
- Add another PCI ID for Coffee Lake (Rodrigo)
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190202082911.GA6615@intel.com
UAPI Changes:
Cross-subsystem Changes:
Core Changes:
- Split out some part of drm_crtc_helper.h into drm_probe_helper.h
- DRIVER_* flags improvements
- New tasks on the TODO-list
- Improvements to the documentation
Driver Changes:
- Continual of drmP.h removal in multiple drivers
- Removal of FBINFO_(FLAG_)DEFAULT in multiple drivers
- sun4i: Addition of the A23 support, multiple fixes for the tiled
formats
- atmel-hlcdc: Fix of clipping and rotation properties
- qxl: various BO-related improvements, prime and generic fbdev emulation
support
- dw-hdmi: Support for HDMI2.0 2160p modes and YUV420 output
- New Sitronix ST7701 panel driver
- New Kingdisplay KD097D04 panel driver
- New LeMaker BL035-RGB-002 panel driver
- New PDA 91-00156-A0 panel driver
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQRcEzekXsqa64kGDp7j7w1vZxhRxQUCXFRb/wAKCRDj7w1vZxhR
xXj2AQDFAkH0/tksJ+T6yrHZXQE7q/6fAWTlrDXLo7Nb1hhfswEA1AyaHmZJA0Ar
u7S+4Gfzs/gisw9Jr4bqQaerEpYJxQA=
=qumD
-----END PGP SIGNATURE-----
Merge tag 'drm-misc-next-2019-02-01' of git://anongit.freedesktop.org/drm/drm-misc into drm-next
drm-misc-next for 5.1:
UAPI Changes:
Cross-subsystem Changes:
Core Changes:
- Split out some part of drm_crtc_helper.h into drm_probe_helper.h
- DRIVER_* flags improvements
- New tasks on the TODO-list
- Improvements to the documentation
Driver Changes:
- Continual of drmP.h removal in multiple drivers
- Removal of FBINFO_(FLAG_)DEFAULT in multiple drivers
- sun4i: Addition of the A23 support, multiple fixes for the tiled
formats
- atmel-hlcdc: Fix of clipping and rotation properties
- qxl: various BO-related improvements, prime and generic fbdev emulation
support
- dw-hdmi: Support for HDMI2.0 2160p modes and YUV420 output
- New Sitronix ST7701 panel driver
- New Kingdisplay KD097D04 panel driver
- New LeMaker BL035-RGB-002 panel driver
- New PDA 91-00156-A0 panel driver
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190201144749.t3abxvguhstu6bcl@flea
To allow requests to forgo a common execution timeline, one question we
need to be able to answer is "is this request running?". To track
whether a request has started on HW, we can emit a breadcrumb at the
beginning of the request and check its timeline's HWSP to see if the
breadcrumb has advanced past the start of this request. (This is in
contrast to the global timeline where we need only ask if we are on the
global timeline and if the timeline has advanced past the end of the
previous request.)
There is still confusion from a preempted request, which has already
started but relinquished the HW to a high priority request. For the
common case, this discrepancy should be negligible. However, for
identification of hung requests, knowing which one was running at the
time of the hang will be much more important.
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/20190129185452.20989-2-chris@chris-wilson.co.uk
Now that we pin timelines around use, we have a clearly defined lifetime
and convenient points at which we can track only the active timelines.
This allows us to reduce the list iteration to only consider those
active timelines and not all.
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/20190128181812.22804-6-chris@chris-wilson.co.uk
Now that we have allocated ourselves a cacheline to store a breadcrumb,
we can emit a write from the GPU into the timeline's HWSP of the
per-context seqno as we complete each request. This drops the mirroring
of the per-engine HWSP and allows each context to operate independently.
We do not need to unwind the per-context timeline, and so requests are
always consistent with the timeline breadcrumb, greatly simplifying the
completion checks as we no longer need to be concerned about the
global_seqno changing mid check.
One complication though is that we have to be wary that the request may
outlive the HWSP and so avoid touching the potentially danging pointer
after we have retired the fence. We also have to guard our access of the
HWSP with RCU, the release of the obj->mm.pages should already be RCU-safe.
At this point, we are emitting both per-context and global seqno and
still using the single per-engine execution timeline for resolving
interrupts.
v2: s/fake_complete/mark_complete/
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/20190128181812.22804-5-chris@chris-wilson.co.uk
Currently, the list of timelines is serialised by the struct_mutex, but
to alleviate difficulties with using that mutex in future, move the
list management under its own dedicated mutex.
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/20190128102356.15037-5-chris@chris-wilson.co.uk
Remove the struct_mutex requirement for looking up the vma for an
object.
v2: Highlight how the race for duplicate vma creation is resolved on
reacquiring the lock with a short comment.
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/20190128102356.15037-3-chris@chris-wilson.co.uk
A starting point to counter the pervasive struct_mutex. For the goal of
avoiding (or at least blocking under them!) global locks during user
request submission, a simple but important step is being able to manage
each clients GTT separately. For which, we want to replace using the
struct_mutex as the guard for all things GTT/VM and switch instead to a
specific mutex inside i915_address_space.
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/20190128102356.15037-2-chris@chris-wilson.co.uk
Our goal is to remove struct_mutex and replace it with fine grained
locking. One of the thorny issues is our eviction logic for reclaiming
space for an execbuffer (or GTT mmaping, among a few other examples).
While eviction itself is easy to move under a per-VM mutex, performing
the activity tracking is less agreeable. One solution is not to do any
MRU tracking and do a simple coarse evaluation during eviction of
active/inactive, with a loose temporal ordering of last
insertion/evaluation. That keeps all the locking constrained to when we
are manipulating the VM itself, neatly avoiding the tricky handling of
possible recursive locking during execbuf and elsewhere.
Note that discarding the MRU (currently implemented as a pair of lists,
to avoid scanning the active list for a NONBLOCKING search) is unlikely
to impact upon our efficiency to reclaim VM space (where we think a LRU
model is best) as our current strategy is to use random idle replacement
first before doing a search, and over time the use of softpinned 48b
per-ppGTT is growing (thereby eliminating any need to perform any eviction
searches, in theory at least) with the remaining users being found on
much older devices (gen2-gen6).
v2: Changelog and commentary rewritten to elaborate on the duality of a
single list being both an inactive and active list.
v3: Consolidate bool parameters into a single set of flags; don't
comment on the duality of a single variable being a multiplicity of
bits.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190128102356.15037-1-chris@chris-wilson.co.uk
Now that the submission backends are controlled via their own spinlocks,
with a wave of a magic wand we can lift the struct_mutex requirement
around GPU reset. That is we allow the submission frontend (userspace)
to keep on submitting while we process the GPU reset as we can suspend
the backend independently.
The major change is around the backoff/handoff strategy for performing
the reset. With no mutex deadlock, we no longer have to coordinate with
any waiter, and just perform the reset immediately.
Testcase: igt/gem_mmap_gtt/hang # regresses
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190125132230.22221-3-chris@chris-wilson.co.uk
