diff options
author | Chris Wilson <chris@chris-wilson.co.uk> | 2019-01-29 20:52:29 +0000 |
---|---|---|
committer | Chris Wilson <chris@chris-wilson.co.uk> | 2019-01-29 21:45:22 +0000 |
commit | 52c0fdb25c7c919334b97976d05096b441a3eada (patch) | |
tree | 23b9d41a8b270d4f2d6b34d3843224ada5012526 /drivers/gpu/drm/i915/selftests/lib_sw_fence.c | |
parent | 3df0bd19193c47c48b7904e5f41c3041a431da33 (diff) | |
download | linux-52c0fdb25c7c919334b97976d05096b441a3eada.tar.bz2 |
drm/i915: Replace global breadcrumbs with per-context interrupt tracking
A few years ago, see commit 688e6c725816 ("drm/i915: Slaughter the
thundering i915_wait_request herd"), the issue of handling multiple
clients waiting in parallel was brought to our attention. The
requirement was that every client should be woken immediately upon its
request being signaled, without incurring any cpu overhead.
To handle certain fragility of our hw meant that we could not do a
simple check inside the irq handler (some generations required almost
unbounded delays before we could be sure of seqno coherency) and so
request completion checking required delegation.
Before commit 688e6c725816, the solution was simple. Every client
waiting on a request would be woken on every interrupt and each would do
a heavyweight check to see if their request was complete. Commit
688e6c725816 introduced an rbtree so that only the earliest waiter on
the global timeline would woken, and would wake the next and so on.
(Along with various complications to handle requests being reordered
along the global timeline, and also a requirement for kthread to provide
a delegate for fence signaling that had no process context.)
The global rbtree depends on knowing the execution timeline (and global
seqno). Without knowing that order, we must instead check all contexts
queued to the HW to see which may have advanced. We trim that list by
only checking queued contexts that are being waited on, but still we
keep a list of all active contexts and their active signalers that we
inspect from inside the irq handler. By moving the waiters onto the fence
signal list, we can combine the client wakeup with the dma_fence
signaling (a dramatic reduction in complexity, but does require the HW
being coherent, the seqno must be visible from the cpu before the
interrupt is raised - we keep a timer backup just in case).
Having previously fixed all the issues with irq-seqno serialisation (by
inserting delays onto the GPU after each request instead of random delays
on the CPU after each interrupt), we can rely on the seqno state to
perfom direct wakeups from the interrupt handler. This allows us to
preserve our single context switch behaviour of the current routine,
with the only downside that we lose the RT priority sorting of wakeups.
In general, direct wakeup latency of multiple clients is about the same
(about 10% better in most cases) with a reduction in total CPU time spent
in the waiter (about 20-50% depending on gen). Average herd behaviour is
improved, but at the cost of not delegating wakeups on task_prio.
v2: Capture fence signaling state for error state and add comments to
warm even the most cold of hearts.
v3: Check if the request is still active before busywaiting
v4: Reduce the amount of pointer misdirection with list_for_each_safe
and using a local i915_request variable inside the loops
v5: Add a missing pluralisation to a purely informative selftest message.
References: 688e6c725816 ("drm/i915: Slaughter the thundering i915_wait_request herd")
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/20190129205230.19056-2-chris@chris-wilson.co.uk
Diffstat (limited to 'drivers/gpu/drm/i915/selftests/lib_sw_fence.c')
-rw-r--r-- | drivers/gpu/drm/i915/selftests/lib_sw_fence.c | 54 |
1 files changed, 54 insertions, 0 deletions
diff --git a/drivers/gpu/drm/i915/selftests/lib_sw_fence.c b/drivers/gpu/drm/i915/selftests/lib_sw_fence.c index b26f07b55d86..2bfa72c1654b 100644 --- a/drivers/gpu/drm/i915/selftests/lib_sw_fence.c +++ b/drivers/gpu/drm/i915/selftests/lib_sw_fence.c @@ -76,3 +76,57 @@ void timed_fence_fini(struct timed_fence *tf) destroy_timer_on_stack(&tf->timer); i915_sw_fence_fini(&tf->fence); } + +struct heap_fence { + struct i915_sw_fence fence; + union { + struct kref ref; + struct rcu_head rcu; + }; +}; + +static int __i915_sw_fence_call +heap_fence_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state) +{ + struct heap_fence *h = container_of(fence, typeof(*h), fence); + + switch (state) { + case FENCE_COMPLETE: + break; + + case FENCE_FREE: + heap_fence_put(&h->fence); + } + + return NOTIFY_DONE; +} + +struct i915_sw_fence *heap_fence_create(gfp_t gfp) +{ + struct heap_fence *h; + + h = kmalloc(sizeof(*h), gfp); + if (!h) + return NULL; + + i915_sw_fence_init(&h->fence, heap_fence_notify); + refcount_set(&h->ref.refcount, 2); + + return &h->fence; +} + +static void heap_fence_release(struct kref *ref) +{ + struct heap_fence *h = container_of(ref, typeof(*h), ref); + + i915_sw_fence_fini(&h->fence); + + kfree_rcu(h, rcu); +} + +void heap_fence_put(struct i915_sw_fence *fence) +{ + struct heap_fence *h = container_of(fence, typeof(*h), fence); + + kref_put(&h->ref, heap_fence_release); +} |