diff options
author | Chris Wilson <chris@chris-wilson.co.uk> | 2016-10-28 13:58:44 +0100 |
---|---|---|
committer | Chris Wilson <chris@chris-wilson.co.uk> | 2016-10-28 20:53:50 +0100 |
commit | d07f0e59b2c762584478920cd2d11fba2980a94a (patch) | |
tree | a9fc0cade87570bdec356493e6744ee5223bdaaf /drivers/gpu/drm/i915/i915_gem_execbuffer.c | |
parent | f0cd518206e1a47e57bc251e1faba9d38eadcc59 (diff) |
drm/i915: Move GEM activity tracking into a common struct reservation_object
In preparation to support many distinct timelines, we need to expand the
activity tracking on the GEM object to handle more than just a request
per engine. We already use the struct reservation_object on the dma-buf
to handle many fence contexts, so integrating that into the GEM object
itself is the preferred solution. (For example, we can now share the same
reservation_object between every consumer/producer using this buffer and
skip the manual import/export via dma-buf.)
v2: Reimplement busy-ioctl (by walking the reservation object), postpone
the ABI change for another day. Similarly use the reservation object to
find the last_write request (if active and from i915) for choosing
display CS flips.
Caveats:
* busy-ioctl: busy-ioctl only reports on the native fences, it will not
warn of stalls (in set-domain-ioctl, pread/pwrite etc) if the object is
being rendered to by external fences. It also will not report the same
busy state as wait-ioctl (or polling on the dma-buf) in the same
circumstances. On the plus side, it does retain reporting of which
*i915* engines are engaged with this object.
* non-blocking atomic modesets take a step backwards as the wait for
render completion blocks the ioctl. This is fixed in a subsequent
patch to use a fence instead for awaiting on the rendering, see
"drm/i915: Restore nonblocking awaits for modesetting"
* dynamic array manipulation for shared-fences in reservation is slower
than the previous lockless static assignment (e.g. gem_exec_lut_handle
runtime on ivb goes from 42s to 66s), mainly due to atomic operations
(maintaining the fence refcounts).
* loss of object-level retirement callbacks, emulated by VMA retirement
tracking.
* minor loss of object-level last activity information from debugfs,
could be replaced with per-vma information if desired
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/20161028125858.23563-21-chris@chris-wilson.co.uk
Diffstat (limited to 'drivers/gpu/drm/i915/i915_gem_execbuffer.c')
-rw-r--r-- | drivers/gpu/drm/i915/i915_gem_execbuffer.c | 55 |
1 files changed, 11 insertions, 44 deletions
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index d95c4e02eeb9..c35e847bb8bc 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -34,7 +34,6 @@ #include <drm/i915_drm.h> #include "i915_drv.h" -#include "i915_gem_dmabuf.h" #include "i915_trace.h" #include "intel_drv.h" #include "intel_frontbuffer.h" @@ -1101,45 +1100,20 @@ err: return ret; } -static unsigned int eb_other_engines(struct drm_i915_gem_request *req) -{ - unsigned int mask; - - mask = ~intel_engine_flag(req->engine) & I915_BO_ACTIVE_MASK; - mask <<= I915_BO_ACTIVE_SHIFT; - - return mask; -} - static int i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req, struct list_head *vmas) { - const unsigned int other_rings = eb_other_engines(req); struct i915_vma *vma; int ret; list_for_each_entry(vma, vmas, exec_list) { struct drm_i915_gem_object *obj = vma->obj; - struct reservation_object *resv; - if (obj->flags & other_rings) { - ret = i915_gem_request_await_object - (req, obj, obj->base.pending_write_domain); - if (ret) - return ret; - } - - resv = i915_gem_object_get_dmabuf_resv(obj); - if (resv) { - ret = i915_sw_fence_await_reservation - (&req->submit, resv, &i915_fence_ops, - obj->base.pending_write_domain, - I915_FENCE_TIMEOUT, - GFP_KERNEL | __GFP_NOWARN); - if (ret < 0) - return ret; - } + ret = i915_gem_request_await_object + (req, obj, obj->base.pending_write_domain); + if (ret) + return ret; if (obj->base.write_domain & I915_GEM_DOMAIN_CPU) i915_gem_clflush_object(obj, false); @@ -1281,8 +1255,6 @@ void i915_vma_move_to_active(struct i915_vma *vma, GEM_BUG_ON(!drm_mm_node_allocated(&vma->node)); - obj->mm.dirty = true; /* be paranoid */ - /* Add a reference if we're newly entering the active list. * The order in which we add operations to the retirement queue is * vital here: mark_active adds to the start of the callback list, @@ -1290,11 +1262,14 @@ void i915_vma_move_to_active(struct i915_vma *vma, * add the active reference first and queue for it to be dropped * *last*. */ - i915_gem_object_set_active(obj, idx); - i915_gem_active_set(&obj->last_read[idx], req); + if (!i915_vma_is_active(vma)) + obj->active_count++; + i915_vma_set_active(vma, idx); + i915_gem_active_set(&vma->last_read[idx], req); + list_move_tail(&vma->vm_link, &vma->vm->active_list); if (flags & EXEC_OBJECT_WRITE) { - i915_gem_active_set(&obj->last_write, req); + i915_gem_active_set(&vma->last_write, req); intel_fb_obj_invalidate(obj, ORIGIN_CS); @@ -1304,21 +1279,13 @@ void i915_vma_move_to_active(struct i915_vma *vma, if (flags & EXEC_OBJECT_NEEDS_FENCE) i915_gem_active_set(&vma->last_fence, req); - - i915_vma_set_active(vma, idx); - i915_gem_active_set(&vma->last_read[idx], req); - list_move_tail(&vma->vm_link, &vma->vm->active_list); } static void eb_export_fence(struct drm_i915_gem_object *obj, struct drm_i915_gem_request *req, unsigned int flags) { - struct reservation_object *resv; - - resv = i915_gem_object_get_dmabuf_resv(obj); - if (!resv) - return; + struct reservation_object *resv = obj->resv; /* Ignore errors from failing to allocate the new fence, we can't * handle an error right now. Worst case should be missed |