leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
85dc28fa4e
linux/drivers/gpu/drm/i915/gem/i915_gem_context.c

2295 lines
56 KiB
C
Raw Normal View History

drm/i915: preliminary context support Very basic code for context setup/destruction in the driver. Adds the file i915_gem_context.c This file implements HW context support. On gen5+ a HW context consists of an opaque GPU object which is referenced at times of context saves and restores. With RC6 enabled, the context is also referenced as the GPU enters and exists from RC6 (GPU has it's own internal power context, except on gen5). Though something like a context does exist for the media ring, the code only supports contexts for the render ring. In software, there is a distinction between contexts created by the user, and the default HW context. The default HW context is used by GPU clients that do not request setup of their own hardware context. The default context's state is never restored to help prevent programming errors. This would happen if a client ran and piggy-backed off another clients GPU state. The default context only exists to give the GPU some offset to load as the current to invoke a save of the context we actually care about. In fact, the code could likely be constructed, albeit in a more complicated fashion, to never use the default context, though that limits the driver's ability to swap out, and/or destroy other contexts. All other contexts are created as a request by the GPU client. These contexts store GPU state, and thus allow GPU clients to not re-emit state (and potentially query certain state) at any time. The kernel driver makes certain that the appropriate commands are inserted. There are 4 entry points into the contexts, init, fini, open, close. The names are self-explanatory except that init can be called during reset, and also during pm thaw/resume. As we expect our context to be preserved across these events, we do not reinitialize in this case. As Adam Jackson pointed out, The cutoff of 1MB where a HW context is considered too big is arbitrary. The reason for this is even though context sizes are increasing with every generation, they have yet to eclipse even 32k. If we somehow read back way more than that, it probably means BIOS has done something strange, or we're running on a platform that wasn't designed for this. v2: rename load/unload to init/fini (daniel) remove ILK support for get_size() (indirectly daniel) add HAS_HW_CONTEXTS macro to clarify supported platforms (daniel) added comments (Ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:42 +00:00
/*
drm/i915: Move more GEM objects under gem/ Continuing the theme of separating out the GEM clutter. 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/20190528092956.14910-8-chris@chris-wilson.co.uk
2019-05-28 09:29:49 +00:00
* SPDX-License-Identifier: MIT
drm/i915: preliminary context support Very basic code for context setup/destruction in the driver. Adds the file i915_gem_context.c This file implements HW context support. On gen5+ a HW context consists of an opaque GPU object which is referenced at times of context saves and restores. With RC6 enabled, the context is also referenced as the GPU enters and exists from RC6 (GPU has it's own internal power context, except on gen5). Though something like a context does exist for the media ring, the code only supports contexts for the render ring. In software, there is a distinction between contexts created by the user, and the default HW context. The default HW context is used by GPU clients that do not request setup of their own hardware context. The default context's state is never restored to help prevent programming errors. This would happen if a client ran and piggy-backed off another clients GPU state. The default context only exists to give the GPU some offset to load as the current to invoke a save of the context we actually care about. In fact, the code could likely be constructed, albeit in a more complicated fashion, to never use the default context, though that limits the driver's ability to swap out, and/or destroy other contexts. All other contexts are created as a request by the GPU client. These contexts store GPU state, and thus allow GPU clients to not re-emit state (and potentially query certain state) at any time. The kernel driver makes certain that the appropriate commands are inserted. There are 4 entry points into the contexts, init, fini, open, close. The names are self-explanatory except that init can be called during reset, and also during pm thaw/resume. As we expect our context to be preserved across these events, we do not reinitialize in this case. As Adam Jackson pointed out, The cutoff of 1MB where a HW context is considered too big is arbitrary. The reason for this is even though context sizes are increasing with every generation, they have yet to eclipse even 32k. If we somehow read back way more than that, it probably means BIOS has done something strange, or we're running on a platform that wasn't designed for this. v2: rename load/unload to init/fini (daniel) remove ILK support for get_size() (indirectly daniel) add HAS_HW_CONTEXTS macro to clarify supported platforms (daniel) added comments (Ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:42 +00:00
*
drm/i915: Move more GEM objects under gem/ Continuing the theme of separating out the GEM clutter. 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/20190528092956.14910-8-chris@chris-wilson.co.uk
2019-05-28 09:29:49 +00:00
* Copyright © 2011-2012 Intel Corporation
drm/i915: preliminary context support Very basic code for context setup/destruction in the driver. Adds the file i915_gem_context.c This file implements HW context support. On gen5+ a HW context consists of an opaque GPU object which is referenced at times of context saves and restores. With RC6 enabled, the context is also referenced as the GPU enters and exists from RC6 (GPU has it's own internal power context, except on gen5). Though something like a context does exist for the media ring, the code only supports contexts for the render ring. In software, there is a distinction between contexts created by the user, and the default HW context. The default HW context is used by GPU clients that do not request setup of their own hardware context. The default context's state is never restored to help prevent programming errors. This would happen if a client ran and piggy-backed off another clients GPU state. The default context only exists to give the GPU some offset to load as the current to invoke a save of the context we actually care about. In fact, the code could likely be constructed, albeit in a more complicated fashion, to never use the default context, though that limits the driver's ability to swap out, and/or destroy other contexts. All other contexts are created as a request by the GPU client. These contexts store GPU state, and thus allow GPU clients to not re-emit state (and potentially query certain state) at any time. The kernel driver makes certain that the appropriate commands are inserted. There are 4 entry points into the contexts, init, fini, open, close. The names are self-explanatory except that init can be called during reset, and also during pm thaw/resume. As we expect our context to be preserved across these events, we do not reinitialize in this case. As Adam Jackson pointed out, The cutoff of 1MB where a HW context is considered too big is arbitrary. The reason for this is even though context sizes are increasing with every generation, they have yet to eclipse even 32k. If we somehow read back way more than that, it probably means BIOS has done something strange, or we're running on a platform that wasn't designed for this. v2: rename load/unload to init/fini (daniel) remove ILK support for get_size() (indirectly daniel) add HAS_HW_CONTEXTS macro to clarify supported platforms (daniel) added comments (Ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:42 +00:00
*/
/*
* This file implements HW context support. On gen5+ a HW context consists of an
* opaque GPU object which is referenced at times of context saves and restores.
* With RC6 enabled, the context is also referenced as the GPU enters and exists
* from RC6 (GPU has it's own internal power context, except on gen5). Though
* something like a context does exist for the media ring, the code only
* supports contexts for the render ring.
*
* In software, there is a distinction between contexts created by the user,
* and the default HW context. The default HW context is used by GPU clients
* that do not request setup of their own hardware context. The default
* context's state is never restored to help prevent programming errors. This
* would happen if a client ran and piggy-backed off another clients GPU state.
* The default context only exists to give the GPU some offset to load as the
* current to invoke a save of the context we actually care about. In fact, the
* code could likely be constructed, albeit in a more complicated fashion, to
* never use the default context, though that limits the driver's ability to
* swap out, and/or destroy other contexts.
*
* All other contexts are created as a request by the GPU client. These contexts
* store GPU state, and thus allow GPU clients to not re-emit state (and
* potentially query certain state) at any time. The kernel driver makes
* certain that the appropriate commands are inserted.
*
* The context life cycle is semi-complicated in that context BOs may live
* longer than the context itself because of the way the hardware, and object
* tracking works. Below is a very crude representation of the state machine
* describing the context life.
* refcount pincount active
* S0: initial state 0 0 0
* S1: context created 1 0 0
* S2: context is currently running 2 1 X
* S3: GPU referenced, but not current 2 0 1
* S4: context is current, but destroyed 1 1 0
* S5: like S3, but destroyed 1 0 1
*
* The most common (but not all) transitions:
* S0->S1: client creates a context
* S1->S2: client submits execbuf with context
* S2->S3: other clients submits execbuf with context
* S3->S1: context object was retired
* S3->S2: clients submits another execbuf
* S2->S4: context destroy called with current context
* S3->S5->S0: destroy path
* S4->S5->S0: destroy path on current context
*
* There are two confusing terms used above:
* The "current context" means the context which is currently running on the
drm/i915: It's its! Signed-off-by: Damien Lespiau <damien.lespiau@intel.com> Acked-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-08-30 13:40:26 +00:00
* GPU. The GPU has loaded its state already and has stored away the gtt
drm/i915: preliminary context support Very basic code for context setup/destruction in the driver. Adds the file i915_gem_context.c This file implements HW context support. On gen5+ a HW context consists of an opaque GPU object which is referenced at times of context saves and restores. With RC6 enabled, the context is also referenced as the GPU enters and exists from RC6 (GPU has it's own internal power context, except on gen5). Though something like a context does exist for the media ring, the code only supports contexts for the render ring. In software, there is a distinction between contexts created by the user, and the default HW context. The default HW context is used by GPU clients that do not request setup of their own hardware context. The default context's state is never restored to help prevent programming errors. This would happen if a client ran and piggy-backed off another clients GPU state. The default context only exists to give the GPU some offset to load as the current to invoke a save of the context we actually care about. In fact, the code could likely be constructed, albeit in a more complicated fashion, to never use the default context, though that limits the driver's ability to swap out, and/or destroy other contexts. All other contexts are created as a request by the GPU client. These contexts store GPU state, and thus allow GPU clients to not re-emit state (and potentially query certain state) at any time. The kernel driver makes certain that the appropriate commands are inserted. There are 4 entry points into the contexts, init, fini, open, close. The names are self-explanatory except that init can be called during reset, and also during pm thaw/resume. As we expect our context to be preserved across these events, we do not reinitialize in this case. As Adam Jackson pointed out, The cutoff of 1MB where a HW context is considered too big is arbitrary. The reason for this is even though context sizes are increasing with every generation, they have yet to eclipse even 32k. If we somehow read back way more than that, it probably means BIOS has done something strange, or we're running on a platform that wasn't designed for this. v2: rename load/unload to init/fini (daniel) remove ILK support for get_size() (indirectly daniel) add HAS_HW_CONTEXTS macro to clarify supported platforms (daniel) added comments (Ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:42 +00:00
* offset of the BO. The GPU is not actively referencing the data at this
* offset, but it will on the next context switch. The only way to avoid this
* is to do a GPU reset.
*
* An "active context' is one which was previously the "current context" and is
* on the active list waiting for the next context switch to occur. Until this
* happens, the object must remain at the same gtt offset. It is therefore
* possible to destroy a context, but it is still active.
*
*/
drm/i915: Store a direct lookup from object handle to vma 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>
2017-06-16 14:05:16 +00:00
#include <linux/log2.h>
drm/i915: Load balancing across a virtual engine Having allowed the user to define a set of engines that they will want to only use, we go one step further and allow them to bind those engines into a single virtual instance. Submitting a batch to the virtual engine will then forward it to any one of the set in a manner as best to distribute load. The virtual engine has a single timeline across all engines (it operates as a single queue), so it is not able to concurrently run batches across multiple engines by itself; that is left up to the user to submit multiple concurrent batches to multiple queues. Multiple users will be load balanced across the system. The mechanism used for load balancing in this patch is a late greedy balancer. When a request is ready for execution, it is added to each engine's queue, and when an engine is ready for its next request it claims it from the virtual engine. The first engine to do so, wins, i.e. the request is executed at the earliest opportunity (idle moment) in the system. As not all HW is created equal, the user is still able to skip the virtual engine and execute the batch on a specific engine, all within the same queue. It will then be executed in order on the correct engine, with execution on other virtual engines being moved away due to the load detection. A couple of areas for potential improvement left! - The virtual engine always take priority over equal-priority tasks. Mostly broken up by applying FQ_CODEL rules for prioritising new clients, and hopefully the virtual and real engines are not then congested (i.e. all work is via virtual engines, or all work is to the real engine). - We require the breadcrumb irq around every virtual engine request. For normal engines, we eliminate the need for the slow round trip via interrupt by using the submit fence and queueing in order. For virtual engines, we have to allow any job to transfer to a new ring, and cannot coalesce the submissions, so require the completion fence instead, forcing the persistent use of interrupts. - We only drip feed single requests through each virtual engine and onto the physical engines, even if there was enough work to fill all ELSP, leaving small stalls with an idle CS event at the end of every request. Could we be greedy and fill both slots? Being lazy is virtuous for load distribution on less-than-full workloads though. Other areas of improvement are more general, such as reducing lock contention, reducing dispatch overhead, looking at direct submission rather than bouncing around tasklets etc. sseu: Lift the restriction to allow sseu to be reconfigured on virtual engines composed of RENDER_CLASS (rcs). v2: macroize check_user_mbz() v3: Cancel virtual engines on wedging v4: Commence commenting v5: Replace 64b sibling_mask with a list of class:instance v6: Drop the one-element array in the uabi v7: Assert it is an virtual engine in to_virtual_engine() v8: Skip over holes in [class][inst] so we can selftest with (vcs0, vcs2) Link: https://github.com/intel/media-driver/pull/283 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/20190521211134.16117-6-chris@chris-wilson.co.uk
2019-05-21 21:11:30 +00:00
#include <linux/nospec.h>
drm/i915: Move GraphicsTechnology files under gt/ Start partitioning off the code that talks to the hardware (GT) from the uapi layers and move the device facing code under gt/ One casualty is s/intel_ringbuffer.h/intel_engine.h/ with the plan to subdivide that header and body further (and split out the submission code from the ringbuffer and logical context handling). This patch aims to be simple motion so git can fixup inflight patches with little mess. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Jani Nikula <jani.nikula@intel.com> Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190424174839.7141-1-chris@chris-wilson.co.uk
2019-04-24 17:48:39 +00:00
drm/i915: Implement SINGLE_TIMELINE with a syncobj (v4) This API is entirely unnecessary and I'd love to get rid of it. If userspace wants a single timeline across multiple contexts, they can either use implicit synchronization or a syncobj, both of which existed at the time this feature landed. The justification given at the time was that it would help GL drivers which are inherently single-timeline. However, neither of our GL drivers actually wanted the feature. i965 was already in maintenance mode at the time and iris uses syncobj for everything. Unfortunately, as much as I'd love to get rid of it, it is used by the media driver so we can't do that. We can, however, do the next-best thing which is to embed a syncobj in the context and do exactly what we'd expect from userspace internally. This isn't an entirely identical implementation because it's no longer atomic if userspace races with itself by calling execbuffer2 twice simultaneously from different threads. It won't crash in that case; it just doesn't guarantee any ordering between those two submits. It also means that sync files exported from different engines on a SINGLE_TIMELINE context will have different fence contexts. This is visible to userspace if it looks at the obj_name field of sync_fence_info. Moving SINGLE_TIMELINE to a syncobj emulation has a couple of technical advantages beyond mere annoyance. One is that intel_timeline is no longer an api-visible object and can remain entirely an implementation detail. This may be advantageous as we make scheduler changes going forward. Second is that, together with deleting the CLONE_CONTEXT API, we should now have a 1:1 mapping between intel_context and intel_timeline which may help us reduce locking. v2 (Tvrtko Ursulin): - Update the comment on i915_gem_context::syncobj to mention that it's an emulation and the possible race if userspace calls execbuffer2 twice on the same context concurrently. v2 (Jason Ekstrand): - Wrap the checks for eb.gem_context->syncobj in unlikely() - Drop the dma_fence reference - Improved commit message v3 (Jason Ekstrand): - Move the dma_fence_put() to before the error exit v4 (Tvrtko Ursulin): - Add a comment about fence contexts to the commit message Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-8-jason@jlekstrand.net
2021-07-08 15:48:12 +00:00
#include <drm/drm_syncobj.h>
drm/i915/gtt: split up i915_gem_gtt Attempt to split i915_gem_gtt.[ch] into more manageable chunks. Suggested-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Matthew Auld <matthew.auld@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> 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/20200107134009.3255354-1-chris@chris-wilson.co.uk
2020-01-07 13:40:09 +00:00
#include "gt/gen6_ppgtt.h"
drm/i915: Drop GEM context as a direct link from i915_request Keep the intel_context as being the primary state for i915_request, with the GEM context a backpointer from the low level state for the rarer cases we need client information. Our goal is to remove such references to clients from the backend, and leave the HW submission agnostic to client interfaces and self-contained. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191220101230.256839-1-chris@chris-wilson.co.uk
2019-12-20 10:12:29 +00:00
#include "gt/intel_context.h"
drm/i915: Allow userspace to specify ringsize on construction No good reason why we must always use a static ringsize, so let userspace select one during construction. Link: https://github.com/intel/compute-runtime/pull/261 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Steve Carbonari <steven.carbonari@intel.com> Reviewed-by: Janusz Krzysztofik <janusz.krzysztofik@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200225192206.1107336-2-chris@chris-wilson.co.uk
2020-02-25 19:22:05 +00:00
#include "gt/intel_context_param.h"
drm/i915/gem: Cancel contexts when hangchecking is disabled Normally, we rely on our hangcheck to prevent persistent batches from hogging the GPU. However, if the user disables hangcheck, this mechanism breaks down. Despite our insistence that this is unsafe, the users are equally insistent that they want to use endless batches and will disable the hangcheck mechanism. We are looking at replacing hangcheck, in the next patch, with a softer mechanism, that sends a pulse down the engine to check if it is well. We can use the same preemptive pulse to flush an active context off the GPU upon context close, preventing resources being lost and unkillable requests remaining on the GPU after process termination. Testcase: igt/gem_ctx_exec/basic-nohangcheck Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191023133108.21401-4-chris@chris-wilson.co.uk
2019-10-23 13:31:07 +00:00
#include "gt/intel_engine_heartbeat.h"
drm/i915/gt: Move the [class][inst] lookup for engines onto the GT To maintain a fast lookup from a GT centric irq handler, we want the engine lookup tables on the intel_gt. To avoid having multiple copies of the same multi-dimension lookup table, move the generic user engine lookup into an rbtree (for fast and flexible indexing). v2: Split uabi_instance cf uabi_class v3: Set uabi_class/uabi_instance after collating all engines to provide a stable uabi across parallel unordered construction. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> #v2 Link: https://patchwork.freedesktop.org/patch/msgid/20190806124300.24945-2-chris@chris-wilson.co.uk
2019-08-06 12:43:00 +00:00
#include "gt/intel_engine_user.h"
drm/i915/gt: Move gen8 CS emitters into gen8_engine_cs.h Reduce the pollution of intel_engine.h by moving gen8_emit_pipe_control and friends to gen8_engine_cs.h 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/20201216135452.6063-1-chris@chris-wilson.co.uk
2020-12-16 13:54:52 +00:00
#include "gt/intel_gpu_commands.h"
drm/i915/gt: Split intel_ring_submission Split the legacy submission backend from the common CS ring buffer handling. 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/20191024100344.5041-1-chris@chris-wilson.co.uk
2019-10-24 10:03:44 +00:00
#include "gt/intel_ring.h"
drm/i915: Move GraphicsTechnology files under gt/ Start partitioning off the code that talks to the hardware (GT) from the uapi layers and move the device facing code under gt/ One casualty is s/intel_ringbuffer.h/intel_engine.h/ with the plan to subdivide that header and body further (and split out the submission code from the ringbuffer and logical context handling). This patch aims to be simple motion so git can fixup inflight patches with little mess. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Jani Nikula <jani.nikula@intel.com> Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190424174839.7141-1-chris@chris-wilson.co.uk
2019-04-24 17:48:39 +00:00
drm/i915: Move more GEM objects under gem/ Continuing the theme of separating out the GEM clutter. 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/20190528092956.14910-8-chris@chris-wilson.co.uk
2019-05-28 09:29:49 +00:00
#include "i915_gem_context.h"
drm/i915: Add tracepoints to track a vm during its lifetime - ppgtt init/release: these tracepoints are useful for observing the creation and destruction of Full PPGTTs. - ctx create/free: we can use the ctx_free trace in combination with the ppgtt_release one to be sure that the ppgtt doesn't stay alive for too long after the ctx is destroyed. ctx_create is there for simmetry - switch_mm: important point in the lifetime of the vm v4: add DOC information v5: pull the DOC in drm.tmpl v6: clean ppgtt init/release traces + add ctx create/free and switch_mm tracepoints (Chris) v7: drop execlist_submit_context tracepoint Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-11-10 13:44:31 +00:00
#include "i915_trace.h"
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
#include "i915_user_extensions.h"
drm/i915: preliminary context support Very basic code for context setup/destruction in the driver. Adds the file i915_gem_context.c This file implements HW context support. On gen5+ a HW context consists of an opaque GPU object which is referenced at times of context saves and restores. With RC6 enabled, the context is also referenced as the GPU enters and exists from RC6 (GPU has it's own internal power context, except on gen5). Though something like a context does exist for the media ring, the code only supports contexts for the render ring. In software, there is a distinction between contexts created by the user, and the default HW context. The default HW context is used by GPU clients that do not request setup of their own hardware context. The default context's state is never restored to help prevent programming errors. This would happen if a client ran and piggy-backed off another clients GPU state. The default context only exists to give the GPU some offset to load as the current to invoke a save of the context we actually care about. In fact, the code could likely be constructed, albeit in a more complicated fashion, to never use the default context, though that limits the driver's ability to swap out, and/or destroy other contexts. All other contexts are created as a request by the GPU client. These contexts store GPU state, and thus allow GPU clients to not re-emit state (and potentially query certain state) at any time. The kernel driver makes certain that the appropriate commands are inserted. There are 4 entry points into the contexts, init, fini, open, close. The names are self-explanatory except that init can be called during reset, and also during pm thaw/resume. As we expect our context to be preserved across these events, we do not reinitialize in this case. As Adam Jackson pointed out, The cutoff of 1MB where a HW context is considered too big is arbitrary. The reason for this is even though context sizes are increasing with every generation, they have yet to eclipse even 32k. If we somehow read back way more than that, it probably means BIOS has done something strange, or we're running on a platform that wasn't designed for this. v2: rename load/unload to init/fini (daniel) remove ILK support for get_size() (indirectly daniel) add HAS_HW_CONTEXTS macro to clarify supported platforms (daniel) added comments (Ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:42 +00:00
drm/i915: Mark the current context as lost on suspend In order to force a reload of the context image upon resume, we first need to mark its absence on suspend. Currently we are failing to restore the golden context state and any context w/a to the default context after resume. One oversight corrected, is that we had forgotten to reapply the L3 remapping when restoring the lost default context. v2: Remove deprecated WARN. 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: http://patchwork.freedesktop.org/patch/msgid/1461833819-3991-7-git-send-email-chris@chris-wilson.co.uk
2016-04-28 08:56:41 +00:00
#define ALL_L3_SLICES(dev) (1 << NUM_L3_SLICES(dev)) - 1
drm/i915: move gem_context slab to direct module init/exit With the global kmem_cache shrink infrastructure gone there's nothing special and we can convert them over. I'm doing this split up into each patch because there's quite a bit of noise with removing the static global.slab_luts to just a slab_luts. v2: Make slab static (Jason, 0day) Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> Cc: Jason Ekstrand <jason@jlekstrand.net> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210727121037.2041102-5-daniel.vetter@ffwll.ch
2021-07-27 12:10:31 +00:00
static struct kmem_cache *slab_luts;
drm/i915: Make object/vma allocation caches global As our allocations are not device specific, we can move our slab caches to a global scope. 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/20190228102035.5857-2-chris@chris-wilson.co.uk
2019-02-28 10:20:34 +00:00
struct i915_lut_handle *i915_lut_handle_alloc(void)
{
drm/i915: move gem_context slab to direct module init/exit With the global kmem_cache shrink infrastructure gone there's nothing special and we can convert them over. I'm doing this split up into each patch because there's quite a bit of noise with removing the static global.slab_luts to just a slab_luts. v2: Make slab static (Jason, 0day) Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> Cc: Jason Ekstrand <jason@jlekstrand.net> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210727121037.2041102-5-daniel.vetter@ffwll.ch
2021-07-27 12:10:31 +00:00
return kmem_cache_alloc(slab_luts, GFP_KERNEL);
drm/i915: Make object/vma allocation caches global As our allocations are not device specific, we can move our slab caches to a global scope. 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/20190228102035.5857-2-chris@chris-wilson.co.uk
2019-02-28 10:20:34 +00:00
}
void i915_lut_handle_free(struct i915_lut_handle *lut)
{
drm/i915: move gem_context slab to direct module init/exit With the global kmem_cache shrink infrastructure gone there's nothing special and we can convert them over. I'm doing this split up into each patch because there's quite a bit of noise with removing the static global.slab_luts to just a slab_luts. v2: Make slab static (Jason, 0day) Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> Cc: Jason Ekstrand <jason@jlekstrand.net> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210727121037.2041102-5-daniel.vetter@ffwll.ch
2021-07-27 12:10:31 +00:00
return kmem_cache_free(slab_luts, lut);
drm/i915: Make object/vma allocation caches global As our allocations are not device specific, we can move our slab caches to a global scope. 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/20190228102035.5857-2-chris@chris-wilson.co.uk
2019-02-28 10:20:34 +00:00
}
drm/i915: Replace execbuf vma ht with an idr 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
2017-08-16 08:52:08 +00:00
static void lut_close(struct i915_gem_context *ctx)
drm/i915: Store a direct lookup from object handle to vma 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>
2017-06-16 14:05:16 +00:00
{
drm/i915: Replace execbuf vma ht with an idr 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
2017-08-16 08:52:08 +00:00
struct radix_tree_iter iter;
void __rcu **slot;
drm/i915/gem: Split the context's obj:vma lut into its own mutex Rather than reuse the common ctx->mutex for locking the execbuffer LUT, split it into its own lock to avoid being taken [as part of ctx->mutex] at inappropriate times. In particular to avoid the inversion from taking the timeline->mutex for the whole execbuf submission in the next patch. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200703004306.11117-1-chris@chris-wilson.co.uk
2020-07-03 00:43:06 +00:00
mutex_lock(&ctx->lut_mutex);
drm/i915: Hold rcu_read_lock when iterating over the radixtree (vma idr) Kasan spotted [IGT] gem_tiled_pread_pwrite: exiting, ret=0 ================================================================== BUG: KASAN: use-after-free in __i915_gem_object_reset_page_iter+0x15c/0x170 [i915] Read of size 8 at addr ffff8801359da310 by task kworker/3:2/182 CPU: 3 PID: 182 Comm: kworker/3:2 Tainted: G U 4.14.0-rc6-CI-Custom_3340+ #1 Hardware name: Intel Corp. Geminilake/GLK RVP1 DDR4 (05), BIOS GELKRVPA.X64.0062.B30.1708222146 08/22/2017 Workqueue: events __i915_gem_free_work [i915] Call Trace: dump_stack+0x68/0xa0 print_address_description+0x78/0x290 ? __i915_gem_object_reset_page_iter+0x15c/0x170 [i915] kasan_report+0x23d/0x350 __asan_report_load8_noabort+0x19/0x20 __i915_gem_object_reset_page_iter+0x15c/0x170 [i915] ? i915_gem_object_truncate+0x100/0x100 [i915] ? lock_acquire+0x380/0x380 __i915_gem_object_put_pages+0x30d/0x530 [i915] __i915_gem_free_objects+0x551/0xbd0 [i915] ? lock_acquire+0x13e/0x380 __i915_gem_free_work+0x4e/0x70 [i915] process_one_work+0x6f6/0x1590 ? pwq_dec_nr_in_flight+0x2b0/0x2b0 worker_thread+0xe6/0xe90 ? pci_mmcfg_check_reserved+0x110/0x110 kthread+0x309/0x410 ? process_one_work+0x1590/0x1590 ? kthread_create_on_node+0xb0/0xb0 ret_from_fork+0x27/0x40 Allocated by task 1801: save_stack_trace+0x1b/0x20 kasan_kmalloc+0xee/0x190 kasan_slab_alloc+0x12/0x20 kmem_cache_alloc+0xdc/0x2e0 radix_tree_node_alloc.constprop.12+0x48/0x330 __radix_tree_create+0x274/0x480 __radix_tree_insert+0xa2/0x610 i915_gem_object_get_sg+0x224/0x670 [i915] i915_gem_object_get_page+0xb5/0x1c0 [i915] i915_gem_pread_ioctl+0x822/0xf60 [i915] drm_ioctl_kernel+0x13f/0x1c0 drm_ioctl+0x6cf/0x980 do_vfs_ioctl+0x184/0xf30 SyS_ioctl+0x41/0x70 entry_SYSCALL_64_fastpath+0x1c/0xb1 Freed by task 37: save_stack_trace+0x1b/0x20 kasan_slab_free+0xaf/0x190 kmem_cache_free+0xbf/0x340 radix_tree_node_rcu_free+0x79/0x90 rcu_process_callbacks+0x46d/0xf40 __do_softirq+0x21c/0x8d3 The buggy address belongs to the object at ffff8801359da0f0 which belongs to the cache radix_tree_node of size 576 The buggy address is located 544 bytes inside of 576-byte region [ffff8801359da0f0, ffff8801359da330) The buggy address belongs to the page: page:ffffea0004d67600 count:1 mapcount:0 mapping: (null) index:0x0 compound_mapcount: 0 flags: 0x8000000000008100(slab|head) raw: 8000000000008100 0000000000000000 0000000000000000 0000000100110011 raw: ffffea0004b52920 ffffea0004b38020 ffff88015b416a80 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8801359da200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801359da280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8801359da300: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc ^ ffff8801359da380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff8801359da400: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Disabling lock debugging due to kernel taint which looks like the slab containing the radixtree iter was freed as we traversed the tree, taking the rcu read lock across the loop should prevent that (deferring all the frees until the end). Reported-by: Tomi Sarvela <tomi.p.sarvela@intel.com> Fixes: d1b48c1e7184 ("drm/i915: Replace execbuf vma ht with an idr") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171026130032.10677-2-chris@chris-wilson.co.uk Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
2017-10-26 13:00:32 +00:00
rcu_read_lock();
drm/i915: Replace execbuf vma ht with an idr 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
2017-08-16 08:52:08 +00:00
radix_tree_for_each_slot(slot, &ctx->handles_vma, &iter, 0) {
struct i915_vma *vma = rcu_dereference_raw(*slot);
drm/i915: Move object close under its own lock Use i915_gem_object_lock() to guard the LUT and active reference to allow us to break free of struct_mutex for handling GEM_CLOSE. Testcase: igt/gem_close_race Testcase: igt/gem_exec_parallel Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190606112320.9704-1-chris@chris-wilson.co.uk
2019-06-06 11:23:20 +00:00
struct drm_i915_gem_object *obj = vma->obj;
struct i915_lut_handle *lut;
if (!kref_get_unless_zero(&obj->base.refcount))
continue;
drm/i915: Store a direct lookup from object handle to vma 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>
2017-06-16 14:05:16 +00:00
drm/i915/gem: Move obj->lut_list under its own lock The obj->lut_list is traversed when the object is closed as the file table is destroyed during process termination. As this occurs before we kill any outstanding context if, due to some bug or another, the closure is blocked, then we fail to shootdown any inflight operations potentially leaving the GPU spinning forever. As we only need to guard the list against concurrent closures and insertions, the hold is short and merits being treated as a simple spinlock. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200701084439.17025-1-chris@chris-wilson.co.uk
2020-07-01 08:44:39 +00:00
spin_lock(&obj->lut_lock);
drm/i915: Move object close under its own lock Use i915_gem_object_lock() to guard the LUT and active reference to allow us to break free of struct_mutex for handling GEM_CLOSE. Testcase: igt/gem_close_race Testcase: igt/gem_exec_parallel Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190606112320.9704-1-chris@chris-wilson.co.uk
2019-06-06 11:23:20 +00:00
list_for_each_entry(lut, &obj->lut_list, obj_link) {
if (lut->ctx != ctx)
continue;
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
drm/i915: Move object close under its own lock Use i915_gem_object_lock() to guard the LUT and active reference to allow us to break free of struct_mutex for handling GEM_CLOSE. Testcase: igt/gem_close_race Testcase: igt/gem_exec_parallel Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190606112320.9704-1-chris@chris-wilson.co.uk
2019-06-06 11:23:20 +00:00
if (lut->handle != iter.index)
continue;
list_del(&lut->obj_link);
break;
}
drm/i915/gem: Move obj->lut_list under its own lock The obj->lut_list is traversed when the object is closed as the file table is destroyed during process termination. As this occurs before we kill any outstanding context if, due to some bug or another, the closure is blocked, then we fail to shootdown any inflight operations potentially leaving the GPU spinning forever. As we only need to guard the list against concurrent closures and insertions, the hold is short and merits being treated as a simple spinlock. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200701084439.17025-1-chris@chris-wilson.co.uk
2020-07-01 08:44:39 +00:00
spin_unlock(&obj->lut_lock);
drm/i915: Move object close under its own lock Use i915_gem_object_lock() to guard the LUT and active reference to allow us to break free of struct_mutex for handling GEM_CLOSE. Testcase: igt/gem_close_race Testcase: igt/gem_exec_parallel Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190606112320.9704-1-chris@chris-wilson.co.uk
2019-06-06 11:23:20 +00:00
if (&lut->obj_link != &obj->lut_list) {
i915_lut_handle_free(lut);
radix_tree_iter_delete(&ctx->handles_vma, &iter, slot);
drm/i915: Only close vma we open The history of i915_vma_close() is confusing, as is its use. As the lifetime of the i915_vma is currently bounded by the object it is attached to, we needed a means of identify when a vma was no longer in use by userspace (via the user's fd). This is further complicated by that only ppgtt vma should be closed at the user's behest, as the ggtt were always shared. Now that we attach the vma to a lut on the user's context, the open count does indicate how many unique and open context/vm are referencing this vma from the user. As such, we can and should just use the open_count to track when the vma is still in use by userspace. It's a poor man's replacement for reference counting. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1193 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200422190558.30509-1-chris@chris-wilson.co.uk
2020-04-22 19:05:58 +00:00
i915_vma_close(vma);
drm/i915: Move object close under its own lock Use i915_gem_object_lock() to guard the LUT and active reference to allow us to break free of struct_mutex for handling GEM_CLOSE. Testcase: igt/gem_close_race Testcase: igt/gem_exec_parallel Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190606112320.9704-1-chris@chris-wilson.co.uk
2019-06-06 11:23:20 +00:00
i915_gem_object_put(obj);
}
i915_gem_object_put(obj);
drm/i915: Store a direct lookup from object handle to vma 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>
2017-06-16 14:05:16 +00:00
}
drm/i915: Hold rcu_read_lock when iterating over the radixtree (vma idr) Kasan spotted [IGT] gem_tiled_pread_pwrite: exiting, ret=0 ================================================================== BUG: KASAN: use-after-free in __i915_gem_object_reset_page_iter+0x15c/0x170 [i915] Read of size 8 at addr ffff8801359da310 by task kworker/3:2/182 CPU: 3 PID: 182 Comm: kworker/3:2 Tainted: G U 4.14.0-rc6-CI-Custom_3340+ #1 Hardware name: Intel Corp. Geminilake/GLK RVP1 DDR4 (05), BIOS GELKRVPA.X64.0062.B30.1708222146 08/22/2017 Workqueue: events __i915_gem_free_work [i915] Call Trace: dump_stack+0x68/0xa0 print_address_description+0x78/0x290 ? __i915_gem_object_reset_page_iter+0x15c/0x170 [i915] kasan_report+0x23d/0x350 __asan_report_load8_noabort+0x19/0x20 __i915_gem_object_reset_page_iter+0x15c/0x170 [i915] ? i915_gem_object_truncate+0x100/0x100 [i915] ? lock_acquire+0x380/0x380 __i915_gem_object_put_pages+0x30d/0x530 [i915] __i915_gem_free_objects+0x551/0xbd0 [i915] ? lock_acquire+0x13e/0x380 __i915_gem_free_work+0x4e/0x70 [i915] process_one_work+0x6f6/0x1590 ? pwq_dec_nr_in_flight+0x2b0/0x2b0 worker_thread+0xe6/0xe90 ? pci_mmcfg_check_reserved+0x110/0x110 kthread+0x309/0x410 ? process_one_work+0x1590/0x1590 ? kthread_create_on_node+0xb0/0xb0 ret_from_fork+0x27/0x40 Allocated by task 1801: save_stack_trace+0x1b/0x20 kasan_kmalloc+0xee/0x190 kasan_slab_alloc+0x12/0x20 kmem_cache_alloc+0xdc/0x2e0 radix_tree_node_alloc.constprop.12+0x48/0x330 __radix_tree_create+0x274/0x480 __radix_tree_insert+0xa2/0x610 i915_gem_object_get_sg+0x224/0x670 [i915] i915_gem_object_get_page+0xb5/0x1c0 [i915] i915_gem_pread_ioctl+0x822/0xf60 [i915] drm_ioctl_kernel+0x13f/0x1c0 drm_ioctl+0x6cf/0x980 do_vfs_ioctl+0x184/0xf30 SyS_ioctl+0x41/0x70 entry_SYSCALL_64_fastpath+0x1c/0xb1 Freed by task 37: save_stack_trace+0x1b/0x20 kasan_slab_free+0xaf/0x190 kmem_cache_free+0xbf/0x340 radix_tree_node_rcu_free+0x79/0x90 rcu_process_callbacks+0x46d/0xf40 __do_softirq+0x21c/0x8d3 The buggy address belongs to the object at ffff8801359da0f0 which belongs to the cache radix_tree_node of size 576 The buggy address is located 544 bytes inside of 576-byte region [ffff8801359da0f0, ffff8801359da330) The buggy address belongs to the page: page:ffffea0004d67600 count:1 mapcount:0 mapping: (null) index:0x0 compound_mapcount: 0 flags: 0x8000000000008100(slab|head) raw: 8000000000008100 0000000000000000 0000000000000000 0000000100110011 raw: ffffea0004b52920 ffffea0004b38020 ffff88015b416a80 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8801359da200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8801359da280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8801359da300: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc ^ ffff8801359da380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ffff8801359da400: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc ================================================================== Disabling lock debugging due to kernel taint which looks like the slab containing the radixtree iter was freed as we traversed the tree, taking the rcu read lock across the loop should prevent that (deferring all the frees until the end). Reported-by: Tomi Sarvela <tomi.p.sarvela@intel.com> Fixes: d1b48c1e7184 ("drm/i915: Replace execbuf vma ht with an idr") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171026130032.10677-2-chris@chris-wilson.co.uk Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
2017-10-26 13:00:32 +00:00
rcu_read_unlock();
drm/i915/gem: Split the context's obj:vma lut into its own mutex Rather than reuse the common ctx->mutex for locking the execbuffer LUT, split it into its own lock to avoid being taken [as part of ctx->mutex] at inappropriate times. In particular to avoid the inversion from taking the timeline->mutex for the whole execbuf submission in the next patch. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200703004306.11117-1-chris@chris-wilson.co.uk
2020-07-03 00:43:06 +00:00
mutex_unlock(&ctx->lut_mutex);
drm/i915: Store a direct lookup from object handle to vma 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>
2017-06-16 14:05:16 +00:00
}
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
static struct intel_context *
drm/i915: Allow a context to define its set of engines Over the last few years, we have debated how to extend the user API to support an increase in the number of engines, that may be sparse and even be heterogeneous within a class (not all video decoders created equal). We settled on using (class, instance) tuples to identify a specific engine, with an API for the user to construct a map of engines to capabilities. Into this picture, we then add a challenge of virtual engines; one user engine that maps behind the scenes to any number of physical engines. To keep it general, we want the user to have full control over that mapping. To that end, we allow the user to constrain a context to define the set of engines that it can access, order fully controlled by the user via (class, instance). With such precise control in context setup, we can continue to use the existing execbuf uABI of specifying a single index; only now it doesn't automagically map onto the engines, it uses the user defined engine map from the context. v2: Fixup freeing of local on success of get_engines() v3: Allow empty engines[] v4: s/nengine/num_engines/ v5: Replace 64 limit on num_engines with a note that execbuf is currently limited to only using the first 64 engines. v6: Actually use the engines_mutex to guard the ctx->engines. Testcase: igt/gem_ctx_engines 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/20190521211134.16117-2-chris@chris-wilson.co.uk
2019-05-21 21:11:26 +00:00
lookup_user_engine(struct i915_gem_context *ctx,
unsigned long flags,
const struct i915_engine_class_instance *ci)
#define LOOKUP_USER_INDEX BIT(0)
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
{
drm/i915: Allow a context to define its set of engines Over the last few years, we have debated how to extend the user API to support an increase in the number of engines, that may be sparse and even be heterogeneous within a class (not all video decoders created equal). We settled on using (class, instance) tuples to identify a specific engine, with an API for the user to construct a map of engines to capabilities. Into this picture, we then add a challenge of virtual engines; one user engine that maps behind the scenes to any number of physical engines. To keep it general, we want the user to have full control over that mapping. To that end, we allow the user to constrain a context to define the set of engines that it can access, order fully controlled by the user via (class, instance). With such precise control in context setup, we can continue to use the existing execbuf uABI of specifying a single index; only now it doesn't automagically map onto the engines, it uses the user defined engine map from the context. v2: Fixup freeing of local on success of get_engines() v3: Allow empty engines[] v4: s/nengine/num_engines/ v5: Replace 64 limit on num_engines with a note that execbuf is currently limited to only using the first 64 engines. v6: Actually use the engines_mutex to guard the ctx->engines. Testcase: igt/gem_ctx_engines 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/20190521211134.16117-2-chris@chris-wilson.co.uk
2019-05-21 21:11:26 +00:00
int idx;
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
drm/i915: Allow a context to define its set of engines Over the last few years, we have debated how to extend the user API to support an increase in the number of engines, that may be sparse and even be heterogeneous within a class (not all video decoders created equal). We settled on using (class, instance) tuples to identify a specific engine, with an API for the user to construct a map of engines to capabilities. Into this picture, we then add a challenge of virtual engines; one user engine that maps behind the scenes to any number of physical engines. To keep it general, we want the user to have full control over that mapping. To that end, we allow the user to constrain a context to define the set of engines that it can access, order fully controlled by the user via (class, instance). With such precise control in context setup, we can continue to use the existing execbuf uABI of specifying a single index; only now it doesn't automagically map onto the engines, it uses the user defined engine map from the context. v2: Fixup freeing of local on success of get_engines() v3: Allow empty engines[] v4: s/nengine/num_engines/ v5: Replace 64 limit on num_engines with a note that execbuf is currently limited to only using the first 64 engines. v6: Actually use the engines_mutex to guard the ctx->engines. Testcase: igt/gem_ctx_engines 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/20190521211134.16117-2-chris@chris-wilson.co.uk
2019-05-21 21:11:26 +00:00
if (!!(flags & LOOKUP_USER_INDEX) != i915_gem_context_user_engines(ctx))
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
return ERR_PTR(-EINVAL);
drm/i915: Allow a context to define its set of engines Over the last few years, we have debated how to extend the user API to support an increase in the number of engines, that may be sparse and even be heterogeneous within a class (not all video decoders created equal). We settled on using (class, instance) tuples to identify a specific engine, with an API for the user to construct a map of engines to capabilities. Into this picture, we then add a challenge of virtual engines; one user engine that maps behind the scenes to any number of physical engines. To keep it general, we want the user to have full control over that mapping. To that end, we allow the user to constrain a context to define the set of engines that it can access, order fully controlled by the user via (class, instance). With such precise control in context setup, we can continue to use the existing execbuf uABI of specifying a single index; only now it doesn't automagically map onto the engines, it uses the user defined engine map from the context. v2: Fixup freeing of local on success of get_engines() v3: Allow empty engines[] v4: s/nengine/num_engines/ v5: Replace 64 limit on num_engines with a note that execbuf is currently limited to only using the first 64 engines. v6: Actually use the engines_mutex to guard the ctx->engines. Testcase: igt/gem_ctx_engines 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/20190521211134.16117-2-chris@chris-wilson.co.uk
2019-05-21 21:11:26 +00:00
if (!i915_gem_context_user_engines(ctx)) {
struct intel_engine_cs *engine;
engine = intel_engine_lookup_user(ctx->i915,
ci->engine_class,
ci->engine_instance);
if (!engine)
return ERR_PTR(-EINVAL);
drm/i915: Fix up the inverse mapping for default ctx->engines[] The order in which we store the engines inside default_engines() for the legacy ctx->engines[] has to match the legacy I915_EXEC_RING selector mapping in execbuf::user_map. If we present VCS2 as being the second instance of the video engine, legacy userspace calls that I915_EXEC_BSD2 and so we need to insert it into the second video slot. v2: Record the legacy mapping (hopefully we can remove this need in the future) Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111328 Fixes: 2edda80db3d0 ("drm/i915: Rename engines to match their user interface") 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> #v1 Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808110612.23539-2-chris@chris-wilson.co.uk
2019-08-08 11:06:12 +00:00
idx = engine->legacy_idx;
drm/i915: Allow a context to define its set of engines Over the last few years, we have debated how to extend the user API to support an increase in the number of engines, that may be sparse and even be heterogeneous within a class (not all video decoders created equal). We settled on using (class, instance) tuples to identify a specific engine, with an API for the user to construct a map of engines to capabilities. Into this picture, we then add a challenge of virtual engines; one user engine that maps behind the scenes to any number of physical engines. To keep it general, we want the user to have full control over that mapping. To that end, we allow the user to constrain a context to define the set of engines that it can access, order fully controlled by the user via (class, instance). With such precise control in context setup, we can continue to use the existing execbuf uABI of specifying a single index; only now it doesn't automagically map onto the engines, it uses the user defined engine map from the context. v2: Fixup freeing of local on success of get_engines() v3: Allow empty engines[] v4: s/nengine/num_engines/ v5: Replace 64 limit on num_engines with a note that execbuf is currently limited to only using the first 64 engines. v6: Actually use the engines_mutex to guard the ctx->engines. Testcase: igt/gem_ctx_engines 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/20190521211134.16117-2-chris@chris-wilson.co.uk
2019-05-21 21:11:26 +00:00
} else {
idx = ci->engine_instance;
}
return i915_gem_context_get_engine(ctx, idx);
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
}
drm/i915/gem: Add a separate validate_priority helper With the proto-context stuff added later in this series, we end up having to duplicate set_priority. This lets us avoid duplicating the validation logic. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-15-jason@jlekstrand.net
2021-07-08 15:48:19 +00:00
static int validate_priority(struct drm_i915_private *i915,
const struct drm_i915_gem_context_param *args)
{
s64 priority = args->value;
if (args->size)
return -EINVAL;
if (!(i915->caps.scheduler & I915_SCHEDULER_CAP_PRIORITY))
return -ENODEV;
if (priority > I915_CONTEXT_MAX_USER_PRIORITY ||
priority < I915_CONTEXT_MIN_USER_PRIORITY)
return -EINVAL;
if (priority > I915_CONTEXT_DEFAULT_PRIORITY &&
!capable(CAP_SYS_NICE))
return -EPERM;
return 0;
}
drm/i915/gem: Add an intermediate proto_context struct (v5) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. Unfortunately, both methods of setting the VM and the engine set are in active use today so we can't simply disallow setting the VM or engine set vial SET_CONTEXT_PARAM. In order to work around this wart, this commit adds a proto-context struct which contains all the context create parameters. v2 (Daniel Vetter): - Better commit message - Use __set/clear_bit instead of set/clear_bit because there's no race and we don't need the atomics v3 (Daniel Vetter): - Use manual bitops and BIT() instead of __set_bit v4 (Daniel Vetter): - Add a changelog to the commit message - Better hyperlinking in docs - Create the default PPGTT in i915_gem_create_context v5 (Daniel Vetter): - Hand-roll the initialization of UCONTEXT_PERSISTENCE Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-17-jason@jlekstrand.net
2021-07-08 15:48:21 +00:00
static void proto_context_close(struct i915_gem_proto_context *pc)
{
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
int i;
drm/i915/gem: Add an intermediate proto_context struct (v5) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. Unfortunately, both methods of setting the VM and the engine set are in active use today so we can't simply disallow setting the VM or engine set vial SET_CONTEXT_PARAM. In order to work around this wart, this commit adds a proto-context struct which contains all the context create parameters. v2 (Daniel Vetter): - Better commit message - Use __set/clear_bit instead of set/clear_bit because there's no race and we don't need the atomics v3 (Daniel Vetter): - Use manual bitops and BIT() instead of __set_bit v4 (Daniel Vetter): - Add a changelog to the commit message - Better hyperlinking in docs - Create the default PPGTT in i915_gem_create_context v5 (Daniel Vetter): - Hand-roll the initialization of UCONTEXT_PERSISTENCE Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-17-jason@jlekstrand.net
2021-07-08 15:48:21 +00:00
if (pc->vm)
i915_vm_put(pc->vm);
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
if (pc->user_engines) {
for (i = 0; i < pc->num_user_engines; i++)
kfree(pc->user_engines[i].siblings);
kfree(pc->user_engines);
}
drm/i915/gem: Add an intermediate proto_context struct (v5) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. Unfortunately, both methods of setting the VM and the engine set are in active use today so we can't simply disallow setting the VM or engine set vial SET_CONTEXT_PARAM. In order to work around this wart, this commit adds a proto-context struct which contains all the context create parameters. v2 (Daniel Vetter): - Better commit message - Use __set/clear_bit instead of set/clear_bit because there's no race and we don't need the atomics v3 (Daniel Vetter): - Use manual bitops and BIT() instead of __set_bit v4 (Daniel Vetter): - Add a changelog to the commit message - Better hyperlinking in docs - Create the default PPGTT in i915_gem_create_context v5 (Daniel Vetter): - Hand-roll the initialization of UCONTEXT_PERSISTENCE Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-17-jason@jlekstrand.net
2021-07-08 15:48:21 +00:00
kfree(pc);
}
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
static int proto_context_set_persistence(struct drm_i915_private *i915,
struct i915_gem_proto_context *pc,
bool persist)
{
if (persist) {
/*
* Only contexts that are short-lived [that will expire or be
* reset] are allowed to survive past termination. We require
* hangcheck to ensure that the persistent requests are healthy.
*/
if (!i915->params.enable_hangcheck)
return -EINVAL;
pc->user_flags |= BIT(UCONTEXT_PERSISTENCE);
} else {
/* To cancel a context we use "preempt-to-idle" */
if (!(i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
return -ENODEV;
/*
* If the cancel fails, we then need to reset, cleanly!
*
* If the per-engine reset fails, all hope is lost! We resort
* to a full GPU reset in that unlikely case, but realistically
* if the engine could not reset, the full reset does not fare
* much better. The damage has been done.
*
* However, if we cannot reset an engine by itself, we cannot
* cleanup a hanging persistent context without causing
* colateral damage, and we should not pretend we can by
* exposing the interface.
*/
if (!intel_has_reset_engine(&i915->gt))
return -ENODEV;
pc->user_flags &= ~BIT(UCONTEXT_PERSISTENCE);
}
return 0;
}
drm/i915/gem: Add an intermediate proto_context struct (v5) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. Unfortunately, both methods of setting the VM and the engine set are in active use today so we can't simply disallow setting the VM or engine set vial SET_CONTEXT_PARAM. In order to work around this wart, this commit adds a proto-context struct which contains all the context create parameters. v2 (Daniel Vetter): - Better commit message - Use __set/clear_bit instead of set/clear_bit because there's no race and we don't need the atomics v3 (Daniel Vetter): - Use manual bitops and BIT() instead of __set_bit v4 (Daniel Vetter): - Add a changelog to the commit message - Better hyperlinking in docs - Create the default PPGTT in i915_gem_create_context v5 (Daniel Vetter): - Hand-roll the initialization of UCONTEXT_PERSISTENCE Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-17-jason@jlekstrand.net
2021-07-08 15:48:21 +00:00
static struct i915_gem_proto_context *
proto_context_create(struct drm_i915_private *i915, unsigned int flags)
{
struct i915_gem_proto_context *pc, *err;
pc = kzalloc(sizeof(*pc), GFP_KERNEL);
if (!pc)
return ERR_PTR(-ENOMEM);
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
pc->num_user_engines = -1;
pc->user_engines = NULL;
drm/i915/gem: Add an intermediate proto_context struct (v5) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. Unfortunately, both methods of setting the VM and the engine set are in active use today so we can't simply disallow setting the VM or engine set vial SET_CONTEXT_PARAM. In order to work around this wart, this commit adds a proto-context struct which contains all the context create parameters. v2 (Daniel Vetter): - Better commit message - Use __set/clear_bit instead of set/clear_bit because there's no race and we don't need the atomics v3 (Daniel Vetter): - Use manual bitops and BIT() instead of __set_bit v4 (Daniel Vetter): - Add a changelog to the commit message - Better hyperlinking in docs - Create the default PPGTT in i915_gem_create_context v5 (Daniel Vetter): - Hand-roll the initialization of UCONTEXT_PERSISTENCE Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-17-jason@jlekstrand.net
2021-07-08 15:48:21 +00:00
pc->user_flags = BIT(UCONTEXT_BANNABLE) |
BIT(UCONTEXT_RECOVERABLE);
if (i915->params.enable_hangcheck)
pc->user_flags |= BIT(UCONTEXT_PERSISTENCE);
pc->sched.priority = I915_PRIORITY_NORMAL;
if (flags & I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE) {
if (!HAS_EXECLISTS(i915)) {
err = ERR_PTR(-EINVAL);
goto proto_close;
}
pc->single_timeline = true;
}
return pc;
proto_close:
proto_context_close(pc);
return err;
}
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
static int proto_context_register_locked(struct drm_i915_file_private *fpriv,
struct i915_gem_proto_context *pc,
u32 *id)
{
int ret;
void *old;
lockdep_assert_held(&fpriv->proto_context_lock);
ret = xa_alloc(&fpriv->context_xa, id, NULL, xa_limit_32b, GFP_KERNEL);
if (ret)
return ret;
old = xa_store(&fpriv->proto_context_xa, *id, pc, GFP_KERNEL);
if (xa_is_err(old)) {
xa_erase(&fpriv->context_xa, *id);
return xa_err(old);
}
WARN_ON(old);
return 0;
}
static int proto_context_register(struct drm_i915_file_private *fpriv,
struct i915_gem_proto_context *pc,
u32 *id)
{
int ret;
mutex_lock(&fpriv->proto_context_lock);
ret = proto_context_register_locked(fpriv, pc, id);
mutex_unlock(&fpriv->proto_context_lock);
return ret;
}
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
static int set_proto_ctx_vm(struct drm_i915_file_private *fpriv,
struct i915_gem_proto_context *pc,
const struct drm_i915_gem_context_param *args)
{
struct drm_i915_private *i915 = fpriv->dev_priv;
struct i915_address_space *vm;
if (args->size)
return -EINVAL;
if (!HAS_FULL_PPGTT(i915))
return -ENODEV;
if (upper_32_bits(args->value))
return -ENOENT;
vm = i915_gem_vm_lookup(fpriv, args->value);
if (!vm)
return -ENOENT;
if (pc->vm)
i915_vm_put(pc->vm);
pc->vm = vm;
return 0;
}
struct set_proto_ctx_engines {
struct drm_i915_private *i915;
unsigned num_engines;
struct i915_gem_proto_engine *engines;
};
static int
set_proto_ctx_engines_balance(struct i915_user_extension __user *base,
void *data)
{
struct i915_context_engines_load_balance __user *ext =
container_of_user(base, typeof(*ext), base);
const struct set_proto_ctx_engines *set = data;
struct drm_i915_private *i915 = set->i915;
struct intel_engine_cs **siblings;
u16 num_siblings, idx;
unsigned int n;
int err;
if (!HAS_EXECLISTS(i915))
return -ENODEV;
if (get_user(idx, &ext->engine_index))
return -EFAULT;
if (idx >= set->num_engines) {
drm_dbg(&i915->drm, "Invalid placement value, %d >= %d\n",
idx, set->num_engines);
return -EINVAL;
}
idx = array_index_nospec(idx, set->num_engines);
if (set->engines[idx].type != I915_GEM_ENGINE_TYPE_INVALID) {
drm_dbg(&i915->drm,
"Invalid placement[%d], already occupied\n", idx);
return -EEXIST;
}
if (get_user(num_siblings, &ext->num_siblings))
return -EFAULT;
err = check_user_mbz(&ext->flags);
if (err)
return err;
err = check_user_mbz(&ext->mbz64);
if (err)
return err;
if (num_siblings == 0)
return 0;
siblings = kmalloc_array(num_siblings, sizeof(*siblings), GFP_KERNEL);
if (!siblings)
return -ENOMEM;
for (n = 0; n < num_siblings; n++) {
struct i915_engine_class_instance ci;
if (copy_from_user(&ci, &ext->engines[n], sizeof(ci))) {
err = -EFAULT;
goto err_siblings;
}
siblings[n] = intel_engine_lookup_user(i915,
ci.engine_class,
ci.engine_instance);
if (!siblings[n]) {
drm_dbg(&i915->drm,
"Invalid sibling[%d]: { class:%d, inst:%d }\n",
n, ci.engine_class, ci.engine_instance);
err = -EINVAL;
goto err_siblings;
}
}
if (num_siblings == 1) {
set->engines[idx].type = I915_GEM_ENGINE_TYPE_PHYSICAL;
set->engines[idx].engine = siblings[0];
kfree(siblings);
} else {
set->engines[idx].type = I915_GEM_ENGINE_TYPE_BALANCED;
set->engines[idx].num_siblings = num_siblings;
set->engines[idx].siblings = siblings;
}
return 0;
err_siblings:
kfree(siblings);
return err;
}
static int
set_proto_ctx_engines_bond(struct i915_user_extension __user *base, void *data)
{
struct i915_context_engines_bond __user *ext =
container_of_user(base, typeof(*ext), base);
const struct set_proto_ctx_engines *set = data;
struct drm_i915_private *i915 = set->i915;
struct i915_engine_class_instance ci;
struct intel_engine_cs *master;
u16 idx, num_bonds;
int err, n;
if (get_user(idx, &ext->virtual_index))
return -EFAULT;
if (idx >= set->num_engines) {
drm_dbg(&i915->drm,
"Invalid index for virtual engine: %d >= %d\n",
idx, set->num_engines);
return -EINVAL;
}
idx = array_index_nospec(idx, set->num_engines);
if (set->engines[idx].type == I915_GEM_ENGINE_TYPE_INVALID) {
drm_dbg(&i915->drm, "Invalid engine at %d\n", idx);
return -EINVAL;
}
if (set->engines[idx].type != I915_GEM_ENGINE_TYPE_PHYSICAL) {
drm_dbg(&i915->drm,
"Bonding with virtual engines not allowed\n");
return -EINVAL;
}
err = check_user_mbz(&ext->flags);
if (err)
return err;
for (n = 0; n < ARRAY_SIZE(ext->mbz64); n++) {
err = check_user_mbz(&ext->mbz64[n]);
if (err)
return err;
}
if (copy_from_user(&ci, &ext->master, sizeof(ci)))
return -EFAULT;
master = intel_engine_lookup_user(i915,
ci.engine_class,
ci.engine_instance);
if (!master) {
drm_dbg(&i915->drm,
"Unrecognised master engine: { class:%u, instance:%u }\n",
ci.engine_class, ci.engine_instance);
return -EINVAL;
}
drm/i915/guc: Disable bonding extension with GuC submission Update the bonding extension to return -ENODEV when using GuC submission as this extension fundamentally will not work with the GuC submission interface. Signed-off-by: Matthew Brost <matthew.brost@intel.com> Reviewed-by: John Harrison <John.C.Harrison@Intel.com> Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210727002348.97202-5-matthew.brost@intel.com
2021-07-27 00:23:19 +00:00
if (intel_engine_uses_guc(master)) {
DRM_DEBUG("bonding extension not supported with GuC submission");
return -ENODEV;
}
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
if (get_user(num_bonds, &ext->num_bonds))
return -EFAULT;
for (n = 0; n < num_bonds; n++) {
struct intel_engine_cs *bond;
if (copy_from_user(&ci, &ext->engines[n], sizeof(ci)))
return -EFAULT;
bond = intel_engine_lookup_user(i915,
ci.engine_class,
ci.engine_instance);
if (!bond) {
drm_dbg(&i915->drm,
"Unrecognised engine[%d] for bonding: { class:%d, instance: %d }\n",
n, ci.engine_class, ci.engine_instance);
return -EINVAL;
}
}
return 0;
}
static const i915_user_extension_fn set_proto_ctx_engines_extensions[] = {
[I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE] = set_proto_ctx_engines_balance,
[I915_CONTEXT_ENGINES_EXT_BOND] = set_proto_ctx_engines_bond,
};
static int set_proto_ctx_engines(struct drm_i915_file_private *fpriv,
struct i915_gem_proto_context *pc,
const struct drm_i915_gem_context_param *args)
{
struct drm_i915_private *i915 = fpriv->dev_priv;
struct set_proto_ctx_engines set = { .i915 = i915 };
struct i915_context_param_engines __user *user =
u64_to_user_ptr(args->value);
unsigned int n;
u64 extensions;
int err;
if (pc->num_user_engines >= 0) {
drm_dbg(&i915->drm, "Cannot set engines twice");
return -EINVAL;
}
if (args->size < sizeof(*user) ||
!IS_ALIGNED(args->size - sizeof(*user), sizeof(*user->engines))) {
drm_dbg(&i915->drm, "Invalid size for engine array: %d\n",
args->size);
return -EINVAL;
}
set.num_engines = (args->size - sizeof(*user)) / sizeof(*user->engines);
/* RING_MASK has no shift so we can use it directly here */
if (set.num_engines > I915_EXEC_RING_MASK + 1)
return -EINVAL;
set.engines = kmalloc_array(set.num_engines, sizeof(*set.engines), GFP_KERNEL);
if (!set.engines)
return -ENOMEM;
for (n = 0; n < set.num_engines; n++) {
struct i915_engine_class_instance ci;
struct intel_engine_cs *engine;
if (copy_from_user(&ci, &user->engines[n], sizeof(ci))) {
kfree(set.engines);
return -EFAULT;
}
memset(&set.engines[n], 0, sizeof(set.engines[n]));
if (ci.engine_class == (u16)I915_ENGINE_CLASS_INVALID &&
ci.engine_instance == (u16)I915_ENGINE_CLASS_INVALID_NONE)
continue;
engine = intel_engine_lookup_user(i915,
ci.engine_class,
ci.engine_instance);
if (!engine) {
drm_dbg(&i915->drm,
"Invalid engine[%d]: { class:%d, instance:%d }\n",
n, ci.engine_class, ci.engine_instance);
kfree(set.engines);
return -ENOENT;
}
set.engines[n].type = I915_GEM_ENGINE_TYPE_PHYSICAL;
set.engines[n].engine = engine;
}
err = -EFAULT;
if (!get_user(extensions, &user->extensions))
err = i915_user_extensions(u64_to_user_ptr(extensions),
set_proto_ctx_engines_extensions,
ARRAY_SIZE(set_proto_ctx_engines_extensions),
&set);
if (err) {
kfree(set.engines);
return err;
}
pc->num_user_engines = set.num_engines;
pc->user_engines = set.engines;
return 0;
}
static int set_proto_ctx_sseu(struct drm_i915_file_private *fpriv,
struct i915_gem_proto_context *pc,
struct drm_i915_gem_context_param *args)
{
struct drm_i915_private *i915 = fpriv->dev_priv;
struct drm_i915_gem_context_param_sseu user_sseu;
struct intel_sseu *sseu;
int ret;
if (args->size < sizeof(user_sseu))
return -EINVAL;
if (GRAPHICS_VER(i915) != 11)
return -ENODEV;
if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
sizeof(user_sseu)))
return -EFAULT;
if (user_sseu.rsvd)
return -EINVAL;
if (user_sseu.flags & ~(I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX))
return -EINVAL;
if (!!(user_sseu.flags & I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX) != (pc->num_user_engines >= 0))
return -EINVAL;
if (pc->num_user_engines >= 0) {
int idx = user_sseu.engine.engine_instance;
struct i915_gem_proto_engine *pe;
if (idx >= pc->num_user_engines)
return -EINVAL;
pe = &pc->user_engines[idx];
/* Only render engine supports RPCS configuration. */
if (pe->engine->class != RENDER_CLASS)
return -EINVAL;
sseu = &pe->sseu;
} else {
/* Only render engine supports RPCS configuration. */
if (user_sseu.engine.engine_class != I915_ENGINE_CLASS_RENDER)
return -EINVAL;
/* There is only one render engine */
if (user_sseu.engine.engine_instance != 0)
return -EINVAL;
sseu = &pc->legacy_rcs_sseu;
}
ret = i915_gem_user_to_context_sseu(&i915->gt, &user_sseu, sseu);
if (ret)
return ret;
args->size = sizeof(user_sseu);
return 0;
}
static int set_proto_ctx_param(struct drm_i915_file_private *fpriv,
struct i915_gem_proto_context *pc,
struct drm_i915_gem_context_param *args)
{
int ret = 0;
switch (args->param) {
case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
if (args->size)
ret = -EINVAL;
else if (args->value)
pc->user_flags |= BIT(UCONTEXT_NO_ERROR_CAPTURE);
else
pc->user_flags &= ~BIT(UCONTEXT_NO_ERROR_CAPTURE);
break;
case I915_CONTEXT_PARAM_BANNABLE:
if (args->size)
ret = -EINVAL;
else if (!capable(CAP_SYS_ADMIN) && !args->value)
ret = -EPERM;
else if (args->value)
pc->user_flags |= BIT(UCONTEXT_BANNABLE);
else
pc->user_flags &= ~BIT(UCONTEXT_BANNABLE);
break;
case I915_CONTEXT_PARAM_RECOVERABLE:
if (args->size)
ret = -EINVAL;
else if (args->value)
pc->user_flags |= BIT(UCONTEXT_RECOVERABLE);
else
pc->user_flags &= ~BIT(UCONTEXT_RECOVERABLE);
break;
case I915_CONTEXT_PARAM_PRIORITY:
ret = validate_priority(fpriv->dev_priv, args);
if (!ret)
pc->sched.priority = args->value;
break;
case I915_CONTEXT_PARAM_SSEU:
ret = set_proto_ctx_sseu(fpriv, pc, args);
break;
case I915_CONTEXT_PARAM_VM:
ret = set_proto_ctx_vm(fpriv, pc, args);
break;
case I915_CONTEXT_PARAM_ENGINES:
ret = set_proto_ctx_engines(fpriv, pc, args);
break;
case I915_CONTEXT_PARAM_PERSISTENCE:
if (args->size)
ret = -EINVAL;
ret = proto_context_set_persistence(fpriv->dev_priv, pc,
args->value);
break;
case I915_CONTEXT_PARAM_NO_ZEROMAP:
case I915_CONTEXT_PARAM_BAN_PERIOD:
case I915_CONTEXT_PARAM_RINGSIZE:
default:
ret = -EINVAL;
break;
}
return ret;
}
drm/i915/gem: Safely acquire the ctx->vm when copying As we read the ctx->vm unlocked before cloning/exporting, we should validate our reference is correct before returning it. We already do for clone_vm() but were not so strict around get_ppgtt(). Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191106091312.12921-1-chris@chris-wilson.co.uk
2019-11-06 09:13:12 +00:00
static struct i915_address_space *
context_get_vm_rcu(struct i915_gem_context *ctx)
{
GEM_BUG_ON(!rcu_access_pointer(ctx->vm));
do {
struct i915_address_space *vm;
/*
* We do not allow downgrading from full-ppgtt [to a shared
* global gtt], so ctx->vm cannot become NULL.
*/
vm = rcu_dereference(ctx->vm);
if (!kref_get_unless_zero(&vm->ref))
continue;
/*
* This ppgtt may have be reallocated between
* the read and the kref, and reassigned to a third
* context. In order to avoid inadvertent sharing
* of this ppgtt with that third context (and not
* src), we have to confirm that we have the same
* ppgtt after passing through the strong memory
* barrier implied by a successful
* kref_get_unless_zero().
*
* Once we have acquired the current ppgtt of ctx,
* we no longer care if it is released from ctx, as
* it cannot be reallocated elsewhere.
*/
if (vm == rcu_access_pointer(ctx->vm))
return rcu_pointer_handoff(vm);
i915_vm_put(vm);
} while (1);
}
drm/i915/gem: Optionally set SSEU in intel_context_set_gem For now this is a no-op because everyone passes in a null SSEU but it lets us get some of the error handling and selftest refactoring plumbed through. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-19-jason@jlekstrand.net
2021-07-08 15:48:23 +00:00
static int intel_context_set_gem(struct intel_context *ce,
struct i915_gem_context *ctx,
struct intel_sseu sseu)
drm/i915: Remove i915->kernel_context Allocate only an internal intel_context for the kernel_context, forgoing a global GEM context for internal use as we only require a separate address space (for our own protection). Now having weaned GT from requiring ce->gem_context, we can stop referencing it entirely. This also means we no longer have to create random and unnecessary GEM contexts for internal use. GEM contexts are now entirely for tracking GEM clients, and intel_context the execution environment on the GPU. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Acked-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191221160324.1073045-1-chris@chris-wilson.co.uk
2019-12-21 16:03:24 +00:00
{
drm/i915/gem: Optionally set SSEU in intel_context_set_gem For now this is a no-op because everyone passes in a null SSEU but it lets us get some of the error handling and selftest refactoring plumbed through. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-19-jason@jlekstrand.net
2021-07-08 15:48:23 +00:00
int ret = 0;
drm/i915: Mark the GEM context link as RCU protected The only protection for intel_context.gem_cotext is granted by RCU, so annotate it as a rcu protected pointer and carefully dereference it in the few occasions we need to use it. Fixes: 9f3ccd40acf4 ("drm/i915: Drop GEM context as a direct link from i915_request") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Acked-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191222233558.2201901-1-chris@chris-wilson.co.uk
2019-12-22 23:35:58 +00:00
GEM_BUG_ON(rcu_access_pointer(ce->gem_context));
RCU_INIT_POINTER(ce->gem_context, ctx);
drm/i915: Remove i915->kernel_context Allocate only an internal intel_context for the kernel_context, forgoing a global GEM context for internal use as we only require a separate address space (for our own protection). Now having weaned GT from requiring ce->gem_context, we can stop referencing it entirely. This also means we no longer have to create random and unnecessary GEM contexts for internal use. GEM contexts are now entirely for tracking GEM clients, and intel_context the execution environment on the GPU. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Acked-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191221160324.1073045-1-chris@chris-wilson.co.uk
2019-12-21 16:03:24 +00:00
drm/i915: Stop storing the ring size in the ring pointer (v3) Previously, we were storing the ring size in the ring pointer before it was actually allocated. We would then guard setting the ring size on checking for CONTEXT_ALLOC_BIT. This is error-prone at best and really only saves us a few bytes on something that already burns at least 4K. Instead, this patch adds a new ring_size field and makes everything use that. v2 (Daniel Vetter): - Replace 512 * SZ_4K with SZ_2M v2 (Jason Ekstrand): - Rebase on top of page migration code Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-3-jason@jlekstrand.net
2021-07-08 15:48:07 +00:00
ce->ring_size = SZ_16K;
drm/i915: Remove i915->kernel_context Allocate only an internal intel_context for the kernel_context, forgoing a global GEM context for internal use as we only require a separate address space (for our own protection). Now having weaned GT from requiring ce->gem_context, we can stop referencing it entirely. This also means we no longer have to create random and unnecessary GEM contexts for internal use. GEM contexts are now entirely for tracking GEM clients, and intel_context the execution environment on the GPU. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Acked-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191221160324.1073045-1-chris@chris-wilson.co.uk
2019-12-21 16:03:24 +00:00
if (rcu_access_pointer(ctx->vm)) {
struct i915_address_space *vm;
rcu_read_lock();
vm = context_get_vm_rcu(ctx); /* hmm */
rcu_read_unlock();
i915_vm_put(ce->vm);
ce->vm = vm;
}
if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
drm/i915/guc: Disable semaphores when using GuC scheduling Semaphores are an optimization and not required for basic GuC submission to work properly. Disable until we have time to do the implementation to enable semaphores and tune them for performance. Also long direction is just to delete semaphores from the i915 so another reason to not enable these for GuC submission. This patch fixes an existing bugs where I915_ENGINE_HAS_SEMAPHORES was not honored correctly. v2: Reword commit message v3: (John H) - Add text to commit indicating this also fixing an existing bug v4: (John H) - s/bug/bugs Cc: John Harrison <john.c.harrison@intel.com> Signed-off-by: Matthew Brost <matthew.brost@intel.com> Reviewed-by: John Harrison <John.C.Harrison@Intel.com> Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210721215101.139794-14-matthew.brost@intel.com
2021-07-21 21:50:56 +00:00
intel_engine_has_timeslices(ce->engine) &&
intel_engine_has_semaphores(ce->engine))
drm/i915: Remove i915->kernel_context Allocate only an internal intel_context for the kernel_context, forgoing a global GEM context for internal use as we only require a separate address space (for our own protection). Now having weaned GT from requiring ce->gem_context, we can stop referencing it entirely. This also means we no longer have to create random and unnecessary GEM contexts for internal use. GEM contexts are now entirely for tracking GEM clients, and intel_context the execution environment on the GPU. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Acked-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191221160324.1073045-1-chris@chris-wilson.co.uk
2019-12-21 16:03:24 +00:00
__set_bit(CONTEXT_USE_SEMAPHORES, &ce->flags);
drm/i915: Fail too long user submissions by default A new Kconfig option CONFIG_DRM_I915_REQUEST_TIMEOUT is added, defaulting to 20s, and this timeout is applied to all users contexts using the previously added watchdog facility. Result of this is that any user submission will simply fail after this timeout, either causing a reset (for non-preemptable), or incomplete results. This can have an effect that workloads which used to work fine will suddenly start failing. Even workloads comprised of short batches but in long dependency chains can be terminated. And because of lack of agreement on usefulness and safety of fence error propagation this partial execution can be invisible to userspace even if it is "listening" to returned fence status. Another interaction is with hangcheck where care needs to be taken timeout is not set lower or close to three times the heartbeat interval. Otherwise a hang in any application can cause complete termination of all submissions from unrelated clients. Any users modifying the per engine heartbeat intervals therefore need to be aware of this potential denial of service to avoid inadvertently enabling it. Given all this I am personally not convinced the scheme is a good idea. Intuitively it feels object importers would be better positioned to enforce the time they are willing to wait for something to complete. v2: * Improved commit message and Kconfig text. * Pull in some helper code from patch which got dropped. v3: * Bump timeout to 20s to see if it helps Tigerlake. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Daniel Vetter <daniel.vetter@ffwll.ch> Acked-by: Matthew Auld <matthew.auld@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210324121335.2307063-7-tvrtko.ursulin@linux.intel.com
2021-03-24 12:13:34 +00:00
drm/i915/gem: Set the watchdog timeout directly in intel_context_set_gem (v2) Instead of handling it like a context param, unconditionally set it when intel_contexts are created. For years we've had the idea of a watchdog uAPI floating about. The aim was for media, so that they could set very tight deadlines for their transcodes jobs, so that if you have a corrupt bitstream (especially for decoding) you don't hang your desktop too hard. But it's been stuck in limbo since forever, and this simplifies things a bit in preparation for the proto-context work. If we decide to actually make said uAPI a reality, we can do it through the proto- context easily enough. This does mean that we move from reading the request_timeout_ms param once per engine when engines are created instead of once at context creation. If someone changes request_timeout_ms between creating a context and setting engines, it will mean that they get the new timeout. If someone races setting request_timeout_ms and context creation, they can theoretically end up with different timeouts. However, since both of these are fairly harmless and require changing kernel params, we don't care. v2 (Tvrtko Ursulin): - Add a comment about races with request_timeout_ms Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-5-jason@jlekstrand.net
2021-07-08 15:48:09 +00:00
if (IS_ACTIVE(CONFIG_DRM_I915_REQUEST_TIMEOUT) &&
ctx->i915->params.request_timeout_ms) {
unsigned int timeout_ms = ctx->i915->params.request_timeout_ms;
intel_context_set_watchdog_us(ce, (u64)timeout_ms * 1000);
}
drm/i915/gem: Optionally set SSEU in intel_context_set_gem For now this is a no-op because everyone passes in a null SSEU but it lets us get some of the error handling and selftest refactoring plumbed through. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-19-jason@jlekstrand.net
2021-07-08 15:48:23 +00:00
/* A valid SSEU has no zero fields */
if (sseu.slice_mask && !WARN_ON(ce->engine->class != RENDER_CLASS))
ret = intel_context_reconfigure_sseu(ce, sseu);
return ret;
drm/i915: Remove i915->kernel_context Allocate only an internal intel_context for the kernel_context, forgoing a global GEM context for internal use as we only require a separate address space (for our own protection). Now having weaned GT from requiring ce->gem_context, we can stop referencing it entirely. This also means we no longer have to create random and unnecessary GEM contexts for internal use. GEM contexts are now entirely for tracking GEM clients, and intel_context the execution environment on the GPU. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Acked-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191221160324.1073045-1-chris@chris-wilson.co.uk
2019-12-21 16:03:24 +00:00
}
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
static void __free_engines(struct i915_gem_engines *e, unsigned int count)
drm/i915: context basic create & destroy Invent an abstraction for a hw context which is passed around through the core functions. The main bit a hw context holds is the buffer object which backs the context. The rest of the members are just helper functions. Specifically the ring member, which could likely go away if we decide to never implement whatever other hw context support exists. Of note here is the introduction of the 64k alignment constraint for the BO. If contexts become heavily used, we should consider tweaking this down to 4k. Until the contexts are merged and tested a bit though, I think 64k is a nice start (based on docs). Since we don't yet switch contexts, there is really not much complexity here. Creation/destruction works pretty much as one would expect. An idr is used to generate the context id numbers which are unique per file descriptor. v2: add DRM_DEBUG_DRIVERS to distinguish ENOMEM failures (ben) convert a BUG_ON to WARN_ON, default destruction is still fatal (ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:43 +00:00
{
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
while (count--) {
if (!e->engines[count])
continue;
intel_context_put(e->engines[count]);
}
kfree(e);
}
static void free_engines(struct i915_gem_engines *e)
{
__free_engines(e, e->num_engines);
}
drm/i915: Move object close under its own lock Use i915_gem_object_lock() to guard the LUT and active reference to allow us to break free of struct_mutex for handling GEM_CLOSE. Testcase: igt/gem_close_race Testcase: igt/gem_exec_parallel Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190606112320.9704-1-chris@chris-wilson.co.uk
2019-06-06 11:23:20 +00:00
static void free_engines_rcu(struct rcu_head *rcu)
drm/i915: Allow a context to define its set of engines Over the last few years, we have debated how to extend the user API to support an increase in the number of engines, that may be sparse and even be heterogeneous within a class (not all video decoders created equal). We settled on using (class, instance) tuples to identify a specific engine, with an API for the user to construct a map of engines to capabilities. Into this picture, we then add a challenge of virtual engines; one user engine that maps behind the scenes to any number of physical engines. To keep it general, we want the user to have full control over that mapping. To that end, we allow the user to constrain a context to define the set of engines that it can access, order fully controlled by the user via (class, instance). With such precise control in context setup, we can continue to use the existing execbuf uABI of specifying a single index; only now it doesn't automagically map onto the engines, it uses the user defined engine map from the context. v2: Fixup freeing of local on success of get_engines() v3: Allow empty engines[] v4: s/nengine/num_engines/ v5: Replace 64 limit on num_engines with a note that execbuf is currently limited to only using the first 64 engines. v6: Actually use the engines_mutex to guard the ctx->engines. Testcase: igt/gem_ctx_engines 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/20190521211134.16117-2-chris@chris-wilson.co.uk
2019-05-21 21:11:26 +00:00
{
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
struct i915_gem_engines *engines =
container_of(rcu, struct i915_gem_engines, rcu);
i915_sw_fence_fini(&engines->fence);
free_engines(engines);
drm/i915: Allow a context to define its set of engines Over the last few years, we have debated how to extend the user API to support an increase in the number of engines, that may be sparse and even be heterogeneous within a class (not all video decoders created equal). We settled on using (class, instance) tuples to identify a specific engine, with an API for the user to construct a map of engines to capabilities. Into this picture, we then add a challenge of virtual engines; one user engine that maps behind the scenes to any number of physical engines. To keep it general, we want the user to have full control over that mapping. To that end, we allow the user to constrain a context to define the set of engines that it can access, order fully controlled by the user via (class, instance). With such precise control in context setup, we can continue to use the existing execbuf uABI of specifying a single index; only now it doesn't automagically map onto the engines, it uses the user defined engine map from the context. v2: Fixup freeing of local on success of get_engines() v3: Allow empty engines[] v4: s/nengine/num_engines/ v5: Replace 64 limit on num_engines with a note that execbuf is currently limited to only using the first 64 engines. v6: Actually use the engines_mutex to guard the ctx->engines. Testcase: igt/gem_ctx_engines 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/20190521211134.16117-2-chris@chris-wilson.co.uk
2019-05-21 21:11:26 +00:00
}
drm/i915/gem: Take a copy of the engines for context_barrier_task When applying the context-barrier, we only care about the current engines, as the next set of engines will be naturally after the barrier. So we can skip holding the ctx->engines_mutex while constructing the request by taking a sneaky reference to the i915_gem_engines instead. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200311221739.30375-2-chris@chris-wilson.co.uk
2020-03-11 22:17:39 +00:00
static int __i915_sw_fence_call
engines_notify(struct i915_sw_fence *fence, enum i915_sw_fence_notify state)
{
struct i915_gem_engines *engines =
container_of(fence, typeof(*engines), fence);
switch (state) {
case FENCE_COMPLETE:
if (!list_empty(&engines->link)) {
struct i915_gem_context *ctx = engines->ctx;
unsigned long flags;
spin_lock_irqsave(&ctx->stale.lock, flags);
list_del(&engines->link);
spin_unlock_irqrestore(&ctx->stale.lock, flags);
}
i915_gem_context_put(engines->ctx);
break;
case FENCE_FREE:
init_rcu_head(&engines->rcu);
call_rcu(&engines->rcu, free_engines_rcu);
break;
}
return NOTIFY_DONE;
}
static struct i915_gem_engines *alloc_engines(unsigned int count)
{
struct i915_gem_engines *e;
e = kzalloc(struct_size(e, engines, count), GFP_KERNEL);
if (!e)
return NULL;
i915_sw_fence_init(&e->fence, engines_notify);
return e;
}
drm/i915/gem: Optionally set SSEU in intel_context_set_gem For now this is a no-op because everyone passes in a null SSEU but it lets us get some of the error handling and selftest refactoring plumbed through. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-19-jason@jlekstrand.net
2021-07-08 15:48:23 +00:00
static struct i915_gem_engines *default_engines(struct i915_gem_context *ctx,
struct intel_sseu rcs_sseu)
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
{
drm/i915: Fix up the inverse mapping for default ctx->engines[] The order in which we store the engines inside default_engines() for the legacy ctx->engines[] has to match the legacy I915_EXEC_RING selector mapping in execbuf::user_map. If we present VCS2 as being the second instance of the video engine, legacy userspace calls that I915_EXEC_BSD2 and so we need to insert it into the second video slot. v2: Record the legacy mapping (hopefully we can remove this need in the future) Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111328 Fixes: 2edda80db3d0 ("drm/i915: Rename engines to match their user interface") 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> #v1 Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808110612.23539-2-chris@chris-wilson.co.uk
2019-08-08 11:06:12 +00:00
const struct intel_gt *gt = &ctx->i915->gt;
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
struct intel_engine_cs *engine;
drm/i915/gem: Rework error handling in default_engines Since free_engines works for partially constructed engine sets, we can use the usual goto pattern. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-18-jason@jlekstrand.net
2021-07-08 15:48:22 +00:00
struct i915_gem_engines *e, *err;
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
enum intel_engine_id id;
drm/i915/gem: Take a copy of the engines for context_barrier_task When applying the context-barrier, we only care about the current engines, as the next set of engines will be naturally after the barrier. So we can skip holding the ctx->engines_mutex while constructing the request by taking a sneaky reference to the i915_gem_engines instead. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200311221739.30375-2-chris@chris-wilson.co.uk
2020-03-11 22:17:39 +00:00
e = alloc_engines(I915_NUM_ENGINES);
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
if (!e)
return ERR_PTR(-ENOMEM);
drm/i915: Fix up the inverse mapping for default ctx->engines[] The order in which we store the engines inside default_engines() for the legacy ctx->engines[] has to match the legacy I915_EXEC_RING selector mapping in execbuf::user_map. If we present VCS2 as being the second instance of the video engine, legacy userspace calls that I915_EXEC_BSD2 and so we need to insert it into the second video slot. v2: Record the legacy mapping (hopefully we can remove this need in the future) Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111328 Fixes: 2edda80db3d0 ("drm/i915: Rename engines to match their user interface") 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> #v1 Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808110612.23539-2-chris@chris-wilson.co.uk
2019-08-08 11:06:12 +00:00
for_each_engine(engine, gt, id) {
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
struct intel_context *ce;
drm/i915/gem: Optionally set SSEU in intel_context_set_gem For now this is a no-op because everyone passes in a null SSEU but it lets us get some of the error handling and selftest refactoring plumbed through. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-19-jason@jlekstrand.net
2021-07-08 15:48:23 +00:00
struct intel_sseu sseu = {};
int ret;
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
drm/i915: Make for_each_engine_masked work on intel_gt Medium term goal is to eliminate the i915->engine[] array and to get there we have recently introduced equivalent array in intel_gt. Now we need to migrate the code further towards this state. This next step is to eliminate usage of i915->engines[] from the for_each_engine_masked iterator. For this to work we also need to use engine->id as index when populating the gt->engine[] array and adjust the default engine set indexing to use engine->legacy_idx instead of assuming gt->engines[] indexing. v2: * Populate gt->engine[] earlier. * Check that we don't duplicate engine->legacy_idx v3: * Work around the initialization order issue between default_engines() and intel_engines_driver_register() which sets engine->legacy_idx for now. It will be fixed properly later. v4: * Merge with forgotten v2.5. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> 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/20191017161852.8836-1-tvrtko.ursulin@linux.intel.com
2019-10-17 16:18:52 +00:00
if (engine->legacy_idx == INVALID_ENGINE)
continue;
GEM_BUG_ON(engine->legacy_idx >= I915_NUM_ENGINES);
GEM_BUG_ON(e->engines[engine->legacy_idx]);
drm/i915: Remove i915->kernel_context Allocate only an internal intel_context for the kernel_context, forgoing a global GEM context for internal use as we only require a separate address space (for our own protection). Now having weaned GT from requiring ce->gem_context, we can stop referencing it entirely. This also means we no longer have to create random and unnecessary GEM contexts for internal use. GEM contexts are now entirely for tracking GEM clients, and intel_context the execution environment on the GPU. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Acked-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191221160324.1073045-1-chris@chris-wilson.co.uk
2019-12-21 16:03:24 +00:00
ce = intel_context_create(engine);
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
if (IS_ERR(ce)) {
drm/i915/gem: Rework error handling in default_engines Since free_engines works for partially constructed engine sets, we can use the usual goto pattern. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-18-jason@jlekstrand.net
2021-07-08 15:48:22 +00:00
err = ERR_CAST(ce);
goto free_engines;
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
}
drm/i915: context basic create & destroy Invent an abstraction for a hw context which is passed around through the core functions. The main bit a hw context holds is the buffer object which backs the context. The rest of the members are just helper functions. Specifically the ring member, which could likely go away if we decide to never implement whatever other hw context support exists. Of note here is the introduction of the 64k alignment constraint for the BO. If contexts become heavily used, we should consider tweaking this down to 4k. Until the contexts are merged and tested a bit though, I think 64k is a nice start (based on docs). Since we don't yet switch contexts, there is really not much complexity here. Creation/destruction works pretty much as one would expect. An idr is used to generate the context id numbers which are unique per file descriptor. v2: add DRM_DEBUG_DRIVERS to distinguish ENOMEM failures (ben) convert a BUG_ON to WARN_ON, default destruction is still fatal (ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:43 +00:00
drm/i915: Make for_each_engine_masked work on intel_gt Medium term goal is to eliminate the i915->engine[] array and to get there we have recently introduced equivalent array in intel_gt. Now we need to migrate the code further towards this state. This next step is to eliminate usage of i915->engines[] from the for_each_engine_masked iterator. For this to work we also need to use engine->id as index when populating the gt->engine[] array and adjust the default engine set indexing to use engine->legacy_idx instead of assuming gt->engines[] indexing. v2: * Populate gt->engine[] earlier. * Check that we don't duplicate engine->legacy_idx v3: * Work around the initialization order issue between default_engines() and intel_engines_driver_register() which sets engine->legacy_idx for now. It will be fixed properly later. v4: * Merge with forgotten v2.5. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> 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/20191017161852.8836-1-tvrtko.ursulin@linux.intel.com
2019-10-17 16:18:52 +00:00
e->engines[engine->legacy_idx] = ce;
drm/i915/gem: Rework error handling in default_engines Since free_engines works for partially constructed engine sets, we can use the usual goto pattern. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-18-jason@jlekstrand.net
2021-07-08 15:48:22 +00:00
e->num_engines = max(e->num_engines, engine->legacy_idx + 1);
drm/i915/gem: Optionally set SSEU in intel_context_set_gem For now this is a no-op because everyone passes in a null SSEU but it lets us get some of the error handling and selftest refactoring plumbed through. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-19-jason@jlekstrand.net
2021-07-08 15:48:23 +00:00
if (engine->class == RENDER_CLASS)
sseu = rcs_sseu;
ret = intel_context_set_gem(ce, ctx, sseu);
if (ret) {
err = ERR_PTR(ret);
goto free_engines;
}
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
}
return e;
drm/i915/gem: Rework error handling in default_engines Since free_engines works for partially constructed engine sets, we can use the usual goto pattern. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-18-jason@jlekstrand.net
2021-07-08 15:48:22 +00:00
free_engines:
free_engines(e);
return err;
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
}
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
static struct i915_gem_engines *user_engines(struct i915_gem_context *ctx,
unsigned int num_engines,
struct i915_gem_proto_engine *pe)
{
struct i915_gem_engines *e, *err;
unsigned int n;
e = alloc_engines(num_engines);
for (n = 0; n < num_engines; n++) {
struct intel_context *ce;
int ret;
switch (pe[n].type) {
case I915_GEM_ENGINE_TYPE_PHYSICAL:
ce = intel_context_create(pe[n].engine);
break;
case I915_GEM_ENGINE_TYPE_BALANCED:
drm/i915/guc: GuC virtual engines Implement GuC virtual engines. Rather simple implementation, basically just allocate an engine, setup context enter / exit function to virtual engine specific functions, set all other variables / functions to guc versions, and set the engine mask to that of all the siblings. v2: Update to work with proto-ctx v3: (Daniele) - Drop include, add comment to intel_virtual_engine_has_heartbeat Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Signed-off-by: Matthew Brost <matthew.brost@intel.com> Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210727002348.97202-2-matthew.brost@intel.com
2021-07-27 00:23:16 +00:00
ce = intel_engine_create_virtual(pe[n].siblings,
pe[n].num_siblings);
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
break;
case I915_GEM_ENGINE_TYPE_INVALID:
default:
GEM_WARN_ON(pe[n].type != I915_GEM_ENGINE_TYPE_INVALID);
continue;
}
if (IS_ERR(ce)) {
err = ERR_CAST(ce);
goto free_engines;
}
e->engines[n] = ce;
ret = intel_context_set_gem(ce, ctx, pe->sseu);
if (ret) {
err = ERR_PTR(ret);
goto free_engines;
}
}
e->num_engines = num_engines;
return e;
free_engines:
free_engines(e);
return err;
}
drm/i915/gem: Drop free_work for GEM contexts The free_list and worker was introduced in commit 5f09a9c8ab6b ("drm/i915: Allow contexts to be unreferenced locklessly"), but subsequently made redundant by the removal of the last sleeping lock in commit 2935ed5339c4 ("drm/i915: Remove logical HW ID"). As we can now free the GEM context immediately from any context, remove the deferral of the free_list v2: Lift removing the context from the global list into close(). 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> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Matthew Brost <matthew.brost@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20201215152138.8158-1-chris@chris-wilson.co.uk
2020-12-15 15:21:38 +00:00
void i915_gem_context_release(struct kref *ref)
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
{
drm/i915/gem: Drop free_work for GEM contexts The free_list and worker was introduced in commit 5f09a9c8ab6b ("drm/i915: Allow contexts to be unreferenced locklessly"), but subsequently made redundant by the removal of the last sleeping lock in commit 2935ed5339c4 ("drm/i915: Remove logical HW ID"). As we can now free the GEM context immediately from any context, remove the deferral of the free_list v2: Lift removing the context from the global list into close(). 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> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Matthew Brost <matthew.brost@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20201215152138.8158-1-chris@chris-wilson.co.uk
2020-12-15 15:21:38 +00:00
struct i915_gem_context *ctx = container_of(ref, typeof(*ctx), ref);
drm/i915: Add tracepoints to track a vm during its lifetime - ppgtt init/release: these tracepoints are useful for observing the creation and destruction of Full PPGTTs. - ctx create/free: we can use the ctx_free trace in combination with the ppgtt_release one to be sure that the ppgtt doesn't stay alive for too long after the ctx is destroyed. ctx_create is there for simmetry - switch_mm: important point in the lifetime of the vm v4: add DOC information v5: pull the DOC in drm.tmpl v6: clean ppgtt init/release traces + add ctx create/free and switch_mm tracepoints (Chris) v7: drop execlist_submit_context tracepoint Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-11-10 13:44:31 +00:00
drm/i915/gem: Drop free_work for GEM contexts The free_list and worker was introduced in commit 5f09a9c8ab6b ("drm/i915: Allow contexts to be unreferenced locklessly"), but subsequently made redundant by the removal of the last sleeping lock in commit 2935ed5339c4 ("drm/i915: Remove logical HW ID"). As we can now free the GEM context immediately from any context, remove the deferral of the free_list v2: Lift removing the context from the global list into close(). 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> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Matthew Brost <matthew.brost@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20201215152138.8158-1-chris@chris-wilson.co.uk
2020-12-15 15:21:38 +00:00
trace_i915_context_free(ctx);
GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
mutex_destroy(&ctx->engines_mutex);
drm/i915/gem: Split the context's obj:vma lut into its own mutex Rather than reuse the common ctx->mutex for locking the execbuffer LUT, split it into its own lock to avoid being taken [as part of ctx->mutex] at inappropriate times. In particular to avoid the inversion from taking the timeline->mutex for the whole execbuf submission in the next patch. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200703004306.11117-1-chris@chris-wilson.co.uk
2020-07-03 00:43:06 +00:00
mutex_destroy(&ctx->lut_mutex);
drm/i915: Merge legacy+execlists context structs struct intel_context contains two substructs, one for the legacy RCS and one for every execlists engine. Since legacy RCS is a subset of the execlists engine support, just combine the two substructs. v2: Only pin the default context for legacy mode (the object only exists for legacy, but adding i915.enable_execlists provides symmetry with the cleanup functions). Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1464098023-3294-8-git-send-email-chris@chris-wilson.co.uk
2016-05-24 13:53:41 +00:00
drm/i915: Move debug only per-request pid tracking from request to ctx Since contexts are not currently shared between userspace processes, we have an exact correspondence between context creator and guilty batch submitter. Therefore we can save some per-batch work by inspecting the context->pid upon error instead. Note that we take the context's creator's pid rather than the file's pid in order to better track fd passed over sockets. 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/1471254551-25805-29-git-send-email-chris@chris-wilson.co.uk
2016-08-15 09:49:08 +00:00
put_pid(ctx->pid);
drm/i915: Track active engines within a context For use in the next patch, if we track which engines have been used by the HW, we can reduce the work required to flush our state off the HW to those 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/20190308132522.21573-1-chris@chris-wilson.co.uk
2019-03-08 13:25:16 +00:00
mutex_destroy(&ctx->mutex);
drm/i915: Assign every HW context a unique ID The hardware tracks contexts and expects all live contexts (those active on the hardware) to have a unique identifier. This is used by the hardware to assign pagefaults and the like to a particular context. v2: Reorder to make sure ctx->link is not left dangling if the assignment of a hw_id fails (Mika). v3: We have 21bits of context space, not 20. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1461833819-3991-17-git-send-email-chris@chris-wilson.co.uk
2016-04-28 08:56:51 +00:00
drm/i915: Enable rcu-only context lookups Whilst the contents of the context is still protected by the big struct_mutex, this is not much of an improvement. It is just one tiny step towards reducing our BKL. 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/20170620110547.15947-3-chris@chris-wilson.co.uk
2017-06-20 11:05:47 +00:00
kfree_rcu(ctx, rcu);
drm/i915: context basic create & destroy Invent an abstraction for a hw context which is passed around through the core functions. The main bit a hw context holds is the buffer object which backs the context. The rest of the members are just helper functions. Specifically the ring member, which could likely go away if we decide to never implement whatever other hw context support exists. Of note here is the introduction of the 64k alignment constraint for the BO. If contexts become heavily used, we should consider tweaking this down to 4k. Until the contexts are merged and tested a bit though, I think 64k is a nice start (based on docs). Since we don't yet switch contexts, there is really not much complexity here. Creation/destruction works pretty much as one would expect. An idr is used to generate the context id numbers which are unique per file descriptor. v2: add DRM_DEBUG_DRIVERS to distinguish ENOMEM failures (ben) convert a BUG_ON to WARN_ON, default destruction is still fatal (ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:43 +00:00
}
drm/i915/gem: Cancel contexts when hangchecking is disabled Normally, we rely on our hangcheck to prevent persistent batches from hogging the GPU. However, if the user disables hangcheck, this mechanism breaks down. Despite our insistence that this is unsafe, the users are equally insistent that they want to use endless batches and will disable the hangcheck mechanism. We are looking at replacing hangcheck, in the next patch, with a softer mechanism, that sends a pulse down the engine to check if it is well. We can use the same preemptive pulse to flush an active context off the GPU upon context close, preventing resources being lost and unkillable requests remaining on the GPU after process termination. Testcase: igt/gem_ctx_exec/basic-nohangcheck Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191023133108.21401-4-chris@chris-wilson.co.uk
2019-10-23 13:31:07 +00:00
static inline struct i915_gem_engines *
__context_engines_static(const struct i915_gem_context *ctx)
{
return rcu_dereference_protected(ctx->engines, true);
}
static void __reset_context(struct i915_gem_context *ctx,
struct intel_engine_cs *engine)
{
intel_gt_handle_error(engine->gt, engine->mask, 0,
"context closure in %s", ctx->name);
}
static bool __cancel_engine(struct intel_engine_cs *engine)
{
/*
* Send a "high priority pulse" down the engine to cause the
* current request to be momentarily preempted. (If it fails to
* be preempted, it will be reset). As we have marked our context
* as banned, any incomplete request, including any running, will
* be skipped following the preemption.
*
* If there is no hangchecking (one of the reasons why we try to
* cancel the context) and no forced preemption, there may be no
* means by which we reset the GPU and evict the persistent hog.
* Ergo if we are unable to inject a preemptive pulse that can
* kill the banned context, we fallback to doing a local reset
* instead.
*/
drm/i915/gem: Always test execution status on closing the context Verify that if a context is active at the time it is closed, that it is either persistent and preemptible (with hangcheck running) or it shall be removed from execution. Fixes: 9a40bddd47ca ("drm/i915/gt: Expose heartbeat interval via sysfs") Testcase: igt/gem_ctx_persistence/heartbeat-close Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: <stable@vger.kernel.org> # v5.7+ Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200928221510.26044-3-chris@chris-wilson.co.uk (cherry picked from commit d3bb2f9b5ee66d5e000293edd6b6575e59d11db9) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2020-09-28 22:15:10 +00:00
return intel_engine_pulse(engine) == 0;
drm/i915/gem: Cancel contexts when hangchecking is disabled Normally, we rely on our hangcheck to prevent persistent batches from hogging the GPU. However, if the user disables hangcheck, this mechanism breaks down. Despite our insistence that this is unsafe, the users are equally insistent that they want to use endless batches and will disable the hangcheck mechanism. We are looking at replacing hangcheck, in the next patch, with a softer mechanism, that sends a pulse down the engine to check if it is well. We can use the same preemptive pulse to flush an active context off the GPU upon context close, preventing resources being lost and unkillable requests remaining on the GPU after process termination. Testcase: igt/gem_ctx_exec/basic-nohangcheck Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191023133108.21401-4-chris@chris-wilson.co.uk
2019-10-23 13:31:07 +00:00
}
drm/i915/gem: Refine occupancy test in kill_context() Don't just look at the very last request in a queue when deciding if we need to evict the context from the GPU, as that request may still be in the submission queue while the rest of the context is running! Instead, walk back along the queued requests looking for the active request and checking that. Fixes: 2e0986a58cc4 ("drm/i915/gem: Cancel contexts when hangchecking is disabled") Testcase: igt/gem_ctx_persistence/queued Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Cc: Matthew Auld <matthew.auld@intel.com> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191031090104.22245-1-chris@chris-wilson.co.uk
2019-10-31 09:01:04 +00:00
static struct intel_engine_cs *active_engine(struct intel_context *ce)
{
struct intel_engine_cs *engine = NULL;
struct i915_request *rq;
drm/i915/gem: Peek at the inflight context If supported by the backend, we can quickly look at the context's inflight engine rather than search along the active list to confirm. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20201229144114.31686-1-chris@chris-wilson.co.uk
2020-12-29 14:41:14 +00:00
if (intel_context_has_inflight(ce))
return intel_context_inflight(ce);
drm/i915/gem: Refine occupancy test in kill_context() Don't just look at the very last request in a queue when deciding if we need to evict the context from the GPU, as that request may still be in the submission queue while the rest of the context is running! Instead, walk back along the queued requests looking for the active request and checking that. Fixes: 2e0986a58cc4 ("drm/i915/gem: Cancel contexts when hangchecking is disabled") Testcase: igt/gem_ctx_persistence/queued Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Cc: Matthew Auld <matthew.auld@intel.com> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191031090104.22245-1-chris@chris-wilson.co.uk
2019-10-31 09:01:04 +00:00
if (!ce->timeline)
return NULL;
drm/i915/gem: Hold request reference for canceling an active context We have to be very careful while walking the timeline->requests list under the RCU guard, as the requests (and so rq->link) use SLAB_TYPESAFE_BY_RCU and so the requests may be reallocated within an rcu grace period. As the requests are reallocated, they are removed from one list and placed on another, and if we are iterating over that request at that moment, the list iteration jumps from one list to the next and promptly gets confused. Verify we hold the request reference to ensure that the request is not added to a new list behind our backs. <4> [582.745252] general protection fault, probably for non-canonical address 0xcccccccccccccd5c: 0000 [#1] PREEMPT SMP PTI <4> [582.745297] CPU: 0 PID: 1475 Comm: gem_ctx_persist Not tainted 5.9.0-rc1-CI-CI_DRM_8908+ #1 <4> [582.745304] Hardware name: Intel Corporation NUC7CJYH/NUC7JYB, BIOS JYGLKCPX.86A.0027.2018.0125.1347 01/25/2018 <4> [582.745317] RIP: 0010:__lock_acquire+0x2c3/0x1f40 <4> [582.745323] Code: 00 65 8b 05 c7 8a ef 7e 85 c0 0f 85 b4 07 00 00 44 8b 9d c4 08 00 00 45 85 db 0f 84 0f 01 00 00 ba 05 00 00 00 e9 c8 06 00 00 <48> 81 3f c0 89 c7 82 b8 00 00 00 00 41 0f 45 c0 83 fe 01 41 89 c3 <4> [582.745334] RSP: 0018:ffffc9000461bc40 EFLAGS: 00010002 <4> [582.745340] RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 <4> [582.745345] RDX: 0000000000000000 RSI: 0000000000000000 RDI: cccccccccccccd5c <4> [582.745350] RBP: ffff8881ec4a2880 R08: 0000000000000001 R09: 0000000000000001 <4> [582.745356] R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 <4> [582.745361] R13: 0000000000000000 R14: 0000000000000000 R15: cccccccccccccd5c <4> [582.745367] FS: 00007fb44da78e40(0000) GS:ffff888278000000(0000) knlGS:0000000000000000 <4> [582.745373] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4> [582.745378] CR2: 00007fb44daad040 CR3: 0000000268428000 CR4: 0000000000350ef0 <4> [582.745383] Call Trace: <4> [582.745390] ? __lock_acquire+0x913/0x1f40 <4> [582.745397] lock_acquire+0xb5/0x3c0 <4> [582.745526] ? kill_engines+0x19a/0x4b0 [i915] <4> [582.745533] ? find_held_lock+0x2d/0x90 <4> [582.745541] _raw_spin_lock_irq+0x30/0x40 <4> [582.745635] ? kill_engines+0x19a/0x4b0 [i915] <4> [582.745727] kill_engines+0x19a/0x4b0 [i915] <4> [582.745820] context_close+0x195/0x410 [i915] <4> [582.745912] i915_gem_context_close+0x5b/0x160 [i915] <4> [582.745994] i915_driver_postclose+0x14/0x40 [i915] <4> [582.746003] drm_file_free.part.13+0x240/0x290 <4> [582.746009] drm_release_noglobal+0x16/0x50 <4> [582.746016] __fput+0xa5/0x250 <4> [582.746021] task_work_run+0x6e/0xb0 <4> [582.746028] exit_to_user_mode_prepare+0x178/0x180 <4> [582.746034] syscall_exit_to_user_mode+0x36/0x220 <4> [582.746040] entry_SYSCALL_64_after_hwframe+0x44/0xa9 <4> [582.746045] RIP: 0033:0x7fb44d1dc421 <4> [582.746050] Code: f7 d8 64 89 02 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 8b 05 ea cf 20 00 85 c0 75 16 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 3f f3 c3 0f 1f 44 00 00 53 89 fb 48 83 ec 10 <4> [582.746062] RSP: 002b:00007ffed2e83818 EFLAGS: 00000246 ORIG_RAX: 0000000000000003 <4> [582.746069] RAX: 0000000000000000 RBX: 0000556410bfe840 RCX: 00007fb44d1dc421 <4> [582.746075] RDX: 000000000000000a RSI: 00000000c0406469 RDI: 0000000000000008 <4> [582.746080] RBP: 0000000000000008 R08: 00007fb44d1c51cc R09: 00007fb44d1c5240 <4> [582.746086] R10: 0000000000000001 R11: 0000000000000246 R12: 00000000fffffffb <4> [582.746091] R13: 0000000000000006 R14: 0000000000000000 R15: 000000000000000a <4> [582.746099] Modules linked in: vgem mei_hdcp snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio btusb btrtl btbcm btintel x86_pkg_temp_thermal coretemp crct10dif_pclmul crc32_pclmul bluetooth ghash_clmulni_intel ecdh_generic ecc i915 r8169 realtek mei_me mei snd_hda_intel i2c_hid snd_intel_dspcfg snd_hda_codec snd_hwdep snd_hda_core snd_pcm pinctrl_geminilake pinctrl_intel prime_numbers [last unloaded: test_drm_mm] Fixes: 736e785f9b28 ("drm/i915/gem: Reduce context termination list iteration guard to RCU") 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/20200925101107.27869-2-chris@chris-wilson.co.uk (cherry picked from commit badef44deff1fae8d21c5c1cfc4dde95fb5bf993) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2020-09-25 10:11:07 +00:00
/*
* rq->link is only SLAB_TYPESAFE_BY_RCU, we need to hold a reference
* to the request to prevent it being transferred to a new timeline
* (and onto a new timeline->requests list).
*/
drm/i915/gem: Reduce context termination list iteration guard to RCU As we now protect the timeline list using RCU, we can drop the timeline->mutex for guarding the list iteration during context close, as we are searching for an inflight request. Any new request will see the context is banned and not be submitted. In doing so, pull the checks for a concurrent submission of the request (notably the i915_request_completed()) under the engine spinlock, to fully serialise with __i915_request_submit()). That is in the case of preempt-to-busy where the request may be completed during the __i915_request_submit(), we need to be careful that we sample the request status after serialising so that we don't miss the request the engine is actually submitting. Fixes: 4a3174152147 ("drm/i915/gem: Refine occupancy test in kill_context()") References: d22d2d073ef8 ("drm/i915: Protect i915_request_await_start from early waits") # rcu protection of timeline->requests References: https://gitlab.freedesktop.org/drm/intel/-/issues/1622 References: https://gitlab.freedesktop.org/drm/intel/-/issues/2158 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/20200806105954.7766-1-chris@chris-wilson.co.uk Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
2020-08-06 10:59:54 +00:00
rcu_read_lock();
drm/i915/gem: Hold request reference for canceling an active context We have to be very careful while walking the timeline->requests list under the RCU guard, as the requests (and so rq->link) use SLAB_TYPESAFE_BY_RCU and so the requests may be reallocated within an rcu grace period. As the requests are reallocated, they are removed from one list and placed on another, and if we are iterating over that request at that moment, the list iteration jumps from one list to the next and promptly gets confused. Verify we hold the request reference to ensure that the request is not added to a new list behind our backs. <4> [582.745252] general protection fault, probably for non-canonical address 0xcccccccccccccd5c: 0000 [#1] PREEMPT SMP PTI <4> [582.745297] CPU: 0 PID: 1475 Comm: gem_ctx_persist Not tainted 5.9.0-rc1-CI-CI_DRM_8908+ #1 <4> [582.745304] Hardware name: Intel Corporation NUC7CJYH/NUC7JYB, BIOS JYGLKCPX.86A.0027.2018.0125.1347 01/25/2018 <4> [582.745317] RIP: 0010:__lock_acquire+0x2c3/0x1f40 <4> [582.745323] Code: 00 65 8b 05 c7 8a ef 7e 85 c0 0f 85 b4 07 00 00 44 8b 9d c4 08 00 00 45 85 db 0f 84 0f 01 00 00 ba 05 00 00 00 e9 c8 06 00 00 <48> 81 3f c0 89 c7 82 b8 00 00 00 00 41 0f 45 c0 83 fe 01 41 89 c3 <4> [582.745334] RSP: 0018:ffffc9000461bc40 EFLAGS: 00010002 <4> [582.745340] RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 <4> [582.745345] RDX: 0000000000000000 RSI: 0000000000000000 RDI: cccccccccccccd5c <4> [582.745350] RBP: ffff8881ec4a2880 R08: 0000000000000001 R09: 0000000000000001 <4> [582.745356] R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 <4> [582.745361] R13: 0000000000000000 R14: 0000000000000000 R15: cccccccccccccd5c <4> [582.745367] FS: 00007fb44da78e40(0000) GS:ffff888278000000(0000) knlGS:0000000000000000 <4> [582.745373] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4> [582.745378] CR2: 00007fb44daad040 CR3: 0000000268428000 CR4: 0000000000350ef0 <4> [582.745383] Call Trace: <4> [582.745390] ? __lock_acquire+0x913/0x1f40 <4> [582.745397] lock_acquire+0xb5/0x3c0 <4> [582.745526] ? kill_engines+0x19a/0x4b0 [i915] <4> [582.745533] ? find_held_lock+0x2d/0x90 <4> [582.745541] _raw_spin_lock_irq+0x30/0x40 <4> [582.745635] ? kill_engines+0x19a/0x4b0 [i915] <4> [582.745727] kill_engines+0x19a/0x4b0 [i915] <4> [582.745820] context_close+0x195/0x410 [i915] <4> [582.745912] i915_gem_context_close+0x5b/0x160 [i915] <4> [582.745994] i915_driver_postclose+0x14/0x40 [i915] <4> [582.746003] drm_file_free.part.13+0x240/0x290 <4> [582.746009] drm_release_noglobal+0x16/0x50 <4> [582.746016] __fput+0xa5/0x250 <4> [582.746021] task_work_run+0x6e/0xb0 <4> [582.746028] exit_to_user_mode_prepare+0x178/0x180 <4> [582.746034] syscall_exit_to_user_mode+0x36/0x220 <4> [582.746040] entry_SYSCALL_64_after_hwframe+0x44/0xa9 <4> [582.746045] RIP: 0033:0x7fb44d1dc421 <4> [582.746050] Code: f7 d8 64 89 02 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 8b 05 ea cf 20 00 85 c0 75 16 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 3f f3 c3 0f 1f 44 00 00 53 89 fb 48 83 ec 10 <4> [582.746062] RSP: 002b:00007ffed2e83818 EFLAGS: 00000246 ORIG_RAX: 0000000000000003 <4> [582.746069] RAX: 0000000000000000 RBX: 0000556410bfe840 RCX: 00007fb44d1dc421 <4> [582.746075] RDX: 000000000000000a RSI: 00000000c0406469 RDI: 0000000000000008 <4> [582.746080] RBP: 0000000000000008 R08: 00007fb44d1c51cc R09: 00007fb44d1c5240 <4> [582.746086] R10: 0000000000000001 R11: 0000000000000246 R12: 00000000fffffffb <4> [582.746091] R13: 0000000000000006 R14: 0000000000000000 R15: 000000000000000a <4> [582.746099] Modules linked in: vgem mei_hdcp snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio btusb btrtl btbcm btintel x86_pkg_temp_thermal coretemp crct10dif_pclmul crc32_pclmul bluetooth ghash_clmulni_intel ecdh_generic ecc i915 r8169 realtek mei_me mei snd_hda_intel i2c_hid snd_intel_dspcfg snd_hda_codec snd_hwdep snd_hda_core snd_pcm pinctrl_geminilake pinctrl_intel prime_numbers [last unloaded: test_drm_mm] Fixes: 736e785f9b28 ("drm/i915/gem: Reduce context termination list iteration guard to RCU") 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/20200925101107.27869-2-chris@chris-wilson.co.uk (cherry picked from commit badef44deff1fae8d21c5c1cfc4dde95fb5bf993) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2020-09-25 10:11:07 +00:00
list_for_each_entry_reverse(rq, &ce->timeline->requests, link) {
bool found;
/* timeline is already completed upto this point? */
if (!i915_request_get_rcu(rq))
break;
drm/i915/gem: Refine occupancy test in kill_context() Don't just look at the very last request in a queue when deciding if we need to evict the context from the GPU, as that request may still be in the submission queue while the rest of the context is running! Instead, walk back along the queued requests looking for the active request and checking that. Fixes: 2e0986a58cc4 ("drm/i915/gem: Cancel contexts when hangchecking is disabled") Testcase: igt/gem_ctx_persistence/queued Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Cc: Matthew Auld <matthew.auld@intel.com> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191031090104.22245-1-chris@chris-wilson.co.uk
2019-10-31 09:01:04 +00:00
/* Check with the backend if the request is inflight */
drm/i915/gem: Hold request reference for canceling an active context We have to be very careful while walking the timeline->requests list under the RCU guard, as the requests (and so rq->link) use SLAB_TYPESAFE_BY_RCU and so the requests may be reallocated within an rcu grace period. As the requests are reallocated, they are removed from one list and placed on another, and if we are iterating over that request at that moment, the list iteration jumps from one list to the next and promptly gets confused. Verify we hold the request reference to ensure that the request is not added to a new list behind our backs. <4> [582.745252] general protection fault, probably for non-canonical address 0xcccccccccccccd5c: 0000 [#1] PREEMPT SMP PTI <4> [582.745297] CPU: 0 PID: 1475 Comm: gem_ctx_persist Not tainted 5.9.0-rc1-CI-CI_DRM_8908+ #1 <4> [582.745304] Hardware name: Intel Corporation NUC7CJYH/NUC7JYB, BIOS JYGLKCPX.86A.0027.2018.0125.1347 01/25/2018 <4> [582.745317] RIP: 0010:__lock_acquire+0x2c3/0x1f40 <4> [582.745323] Code: 00 65 8b 05 c7 8a ef 7e 85 c0 0f 85 b4 07 00 00 44 8b 9d c4 08 00 00 45 85 db 0f 84 0f 01 00 00 ba 05 00 00 00 e9 c8 06 00 00 <48> 81 3f c0 89 c7 82 b8 00 00 00 00 41 0f 45 c0 83 fe 01 41 89 c3 <4> [582.745334] RSP: 0018:ffffc9000461bc40 EFLAGS: 00010002 <4> [582.745340] RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 <4> [582.745345] RDX: 0000000000000000 RSI: 0000000000000000 RDI: cccccccccccccd5c <4> [582.745350] RBP: ffff8881ec4a2880 R08: 0000000000000001 R09: 0000000000000001 <4> [582.745356] R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 <4> [582.745361] R13: 0000000000000000 R14: 0000000000000000 R15: cccccccccccccd5c <4> [582.745367] FS: 00007fb44da78e40(0000) GS:ffff888278000000(0000) knlGS:0000000000000000 <4> [582.745373] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4> [582.745378] CR2: 00007fb44daad040 CR3: 0000000268428000 CR4: 0000000000350ef0 <4> [582.745383] Call Trace: <4> [582.745390] ? __lock_acquire+0x913/0x1f40 <4> [582.745397] lock_acquire+0xb5/0x3c0 <4> [582.745526] ? kill_engines+0x19a/0x4b0 [i915] <4> [582.745533] ? find_held_lock+0x2d/0x90 <4> [582.745541] _raw_spin_lock_irq+0x30/0x40 <4> [582.745635] ? kill_engines+0x19a/0x4b0 [i915] <4> [582.745727] kill_engines+0x19a/0x4b0 [i915] <4> [582.745820] context_close+0x195/0x410 [i915] <4> [582.745912] i915_gem_context_close+0x5b/0x160 [i915] <4> [582.745994] i915_driver_postclose+0x14/0x40 [i915] <4> [582.746003] drm_file_free.part.13+0x240/0x290 <4> [582.746009] drm_release_noglobal+0x16/0x50 <4> [582.746016] __fput+0xa5/0x250 <4> [582.746021] task_work_run+0x6e/0xb0 <4> [582.746028] exit_to_user_mode_prepare+0x178/0x180 <4> [582.746034] syscall_exit_to_user_mode+0x36/0x220 <4> [582.746040] entry_SYSCALL_64_after_hwframe+0x44/0xa9 <4> [582.746045] RIP: 0033:0x7fb44d1dc421 <4> [582.746050] Code: f7 d8 64 89 02 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 8b 05 ea cf 20 00 85 c0 75 16 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 3f f3 c3 0f 1f 44 00 00 53 89 fb 48 83 ec 10 <4> [582.746062] RSP: 002b:00007ffed2e83818 EFLAGS: 00000246 ORIG_RAX: 0000000000000003 <4> [582.746069] RAX: 0000000000000000 RBX: 0000556410bfe840 RCX: 00007fb44d1dc421 <4> [582.746075] RDX: 000000000000000a RSI: 00000000c0406469 RDI: 0000000000000008 <4> [582.746080] RBP: 0000000000000008 R08: 00007fb44d1c51cc R09: 00007fb44d1c5240 <4> [582.746086] R10: 0000000000000001 R11: 0000000000000246 R12: 00000000fffffffb <4> [582.746091] R13: 0000000000000006 R14: 0000000000000000 R15: 000000000000000a <4> [582.746099] Modules linked in: vgem mei_hdcp snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio btusb btrtl btbcm btintel x86_pkg_temp_thermal coretemp crct10dif_pclmul crc32_pclmul bluetooth ghash_clmulni_intel ecdh_generic ecc i915 r8169 realtek mei_me mei snd_hda_intel i2c_hid snd_intel_dspcfg snd_hda_codec snd_hwdep snd_hda_core snd_pcm pinctrl_geminilake pinctrl_intel prime_numbers [last unloaded: test_drm_mm] Fixes: 736e785f9b28 ("drm/i915/gem: Reduce context termination list iteration guard to RCU") 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/20200925101107.27869-2-chris@chris-wilson.co.uk (cherry picked from commit badef44deff1fae8d21c5c1cfc4dde95fb5bf993) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2020-09-25 10:11:07 +00:00
found = true;
if (likely(rcu_access_pointer(rq->timeline) == ce->timeline))
drm/i915: Extract active lookup engine to a helper Move active engine lookup to exported i915_request_active_engine. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Matthew Auld <matthew.auld@intel.com> [danvet: Slight rebase, engine->sched.lock is still called engine->active.lock.] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210324121335.2307063-2-tvrtko.ursulin@linux.intel.com
2021-03-24 12:13:29 +00:00
found = i915_request_active_engine(rq, &engine);
drm/i915/gem: Hold request reference for canceling an active context We have to be very careful while walking the timeline->requests list under the RCU guard, as the requests (and so rq->link) use SLAB_TYPESAFE_BY_RCU and so the requests may be reallocated within an rcu grace period. As the requests are reallocated, they are removed from one list and placed on another, and if we are iterating over that request at that moment, the list iteration jumps from one list to the next and promptly gets confused. Verify we hold the request reference to ensure that the request is not added to a new list behind our backs. <4> [582.745252] general protection fault, probably for non-canonical address 0xcccccccccccccd5c: 0000 [#1] PREEMPT SMP PTI <4> [582.745297] CPU: 0 PID: 1475 Comm: gem_ctx_persist Not tainted 5.9.0-rc1-CI-CI_DRM_8908+ #1 <4> [582.745304] Hardware name: Intel Corporation NUC7CJYH/NUC7JYB, BIOS JYGLKCPX.86A.0027.2018.0125.1347 01/25/2018 <4> [582.745317] RIP: 0010:__lock_acquire+0x2c3/0x1f40 <4> [582.745323] Code: 00 65 8b 05 c7 8a ef 7e 85 c0 0f 85 b4 07 00 00 44 8b 9d c4 08 00 00 45 85 db 0f 84 0f 01 00 00 ba 05 00 00 00 e9 c8 06 00 00 <48> 81 3f c0 89 c7 82 b8 00 00 00 00 41 0f 45 c0 83 fe 01 41 89 c3 <4> [582.745334] RSP: 0018:ffffc9000461bc40 EFLAGS: 00010002 <4> [582.745340] RAX: 0000000000000000 RBX: 0000000000000001 RCX: 0000000000000000 <4> [582.745345] RDX: 0000000000000000 RSI: 0000000000000000 RDI: cccccccccccccd5c <4> [582.745350] RBP: ffff8881ec4a2880 R08: 0000000000000001 R09: 0000000000000001 <4> [582.745356] R10: 0000000000000001 R11: 0000000000000001 R12: 0000000000000000 <4> [582.745361] R13: 0000000000000000 R14: 0000000000000000 R15: cccccccccccccd5c <4> [582.745367] FS: 00007fb44da78e40(0000) GS:ffff888278000000(0000) knlGS:0000000000000000 <4> [582.745373] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4> [582.745378] CR2: 00007fb44daad040 CR3: 0000000268428000 CR4: 0000000000350ef0 <4> [582.745383] Call Trace: <4> [582.745390] ? __lock_acquire+0x913/0x1f40 <4> [582.745397] lock_acquire+0xb5/0x3c0 <4> [582.745526] ? kill_engines+0x19a/0x4b0 [i915] <4> [582.745533] ? find_held_lock+0x2d/0x90 <4> [582.745541] _raw_spin_lock_irq+0x30/0x40 <4> [582.745635] ? kill_engines+0x19a/0x4b0 [i915] <4> [582.745727] kill_engines+0x19a/0x4b0 [i915] <4> [582.745820] context_close+0x195/0x410 [i915] <4> [582.745912] i915_gem_context_close+0x5b/0x160 [i915] <4> [582.745994] i915_driver_postclose+0x14/0x40 [i915] <4> [582.746003] drm_file_free.part.13+0x240/0x290 <4> [582.746009] drm_release_noglobal+0x16/0x50 <4> [582.746016] __fput+0xa5/0x250 <4> [582.746021] task_work_run+0x6e/0xb0 <4> [582.746028] exit_to_user_mode_prepare+0x178/0x180 <4> [582.746034] syscall_exit_to_user_mode+0x36/0x220 <4> [582.746040] entry_SYSCALL_64_after_hwframe+0x44/0xa9 <4> [582.746045] RIP: 0033:0x7fb44d1dc421 <4> [582.746050] Code: f7 d8 64 89 02 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 66 90 8b 05 ea cf 20 00 85 c0 75 16 b8 03 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 3f f3 c3 0f 1f 44 00 00 53 89 fb 48 83 ec 10 <4> [582.746062] RSP: 002b:00007ffed2e83818 EFLAGS: 00000246 ORIG_RAX: 0000000000000003 <4> [582.746069] RAX: 0000000000000000 RBX: 0000556410bfe840 RCX: 00007fb44d1dc421 <4> [582.746075] RDX: 000000000000000a RSI: 00000000c0406469 RDI: 0000000000000008 <4> [582.746080] RBP: 0000000000000008 R08: 00007fb44d1c51cc R09: 00007fb44d1c5240 <4> [582.746086] R10: 0000000000000001 R11: 0000000000000246 R12: 00000000fffffffb <4> [582.746091] R13: 0000000000000006 R14: 0000000000000000 R15: 000000000000000a <4> [582.746099] Modules linked in: vgem mei_hdcp snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio btusb btrtl btbcm btintel x86_pkg_temp_thermal coretemp crct10dif_pclmul crc32_pclmul bluetooth ghash_clmulni_intel ecdh_generic ecc i915 r8169 realtek mei_me mei snd_hda_intel i2c_hid snd_intel_dspcfg snd_hda_codec snd_hwdep snd_hda_core snd_pcm pinctrl_geminilake pinctrl_intel prime_numbers [last unloaded: test_drm_mm] Fixes: 736e785f9b28 ("drm/i915/gem: Reduce context termination list iteration guard to RCU") 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/20200925101107.27869-2-chris@chris-wilson.co.uk (cherry picked from commit badef44deff1fae8d21c5c1cfc4dde95fb5bf993) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2020-09-25 10:11:07 +00:00
i915_request_put(rq);
if (found)
drm/i915/gem: Refine occupancy test in kill_context() Don't just look at the very last request in a queue when deciding if we need to evict the context from the GPU, as that request may still be in the submission queue while the rest of the context is running! Instead, walk back along the queued requests looking for the active request and checking that. Fixes: 2e0986a58cc4 ("drm/i915/gem: Cancel contexts when hangchecking is disabled") Testcase: igt/gem_ctx_persistence/queued Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Cc: Matthew Auld <matthew.auld@intel.com> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191031090104.22245-1-chris@chris-wilson.co.uk
2019-10-31 09:01:04 +00:00
break;
}
drm/i915/gem: Reduce context termination list iteration guard to RCU As we now protect the timeline list using RCU, we can drop the timeline->mutex for guarding the list iteration during context close, as we are searching for an inflight request. Any new request will see the context is banned and not be submitted. In doing so, pull the checks for a concurrent submission of the request (notably the i915_request_completed()) under the engine spinlock, to fully serialise with __i915_request_submit()). That is in the case of preempt-to-busy where the request may be completed during the __i915_request_submit(), we need to be careful that we sample the request status after serialising so that we don't miss the request the engine is actually submitting. Fixes: 4a3174152147 ("drm/i915/gem: Refine occupancy test in kill_context()") References: d22d2d073ef8 ("drm/i915: Protect i915_request_await_start from early waits") # rcu protection of timeline->requests References: https://gitlab.freedesktop.org/drm/intel/-/issues/1622 References: https://gitlab.freedesktop.org/drm/intel/-/issues/2158 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/20200806105954.7766-1-chris@chris-wilson.co.uk Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
2020-08-06 10:59:54 +00:00
rcu_read_unlock();
drm/i915/gem: Refine occupancy test in kill_context() Don't just look at the very last request in a queue when deciding if we need to evict the context from the GPU, as that request may still be in the submission queue while the rest of the context is running! Instead, walk back along the queued requests looking for the active request and checking that. Fixes: 2e0986a58cc4 ("drm/i915/gem: Cancel contexts when hangchecking is disabled") Testcase: igt/gem_ctx_persistence/queued Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Cc: Matthew Auld <matthew.auld@intel.com> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191031090104.22245-1-chris@chris-wilson.co.uk
2019-10-31 09:01:04 +00:00
return engine;
}
drm/i915/gem: Always test execution status on closing the context Verify that if a context is active at the time it is closed, that it is either persistent and preemptible (with hangcheck running) or it shall be removed from execution. Fixes: 9a40bddd47ca ("drm/i915/gt: Expose heartbeat interval via sysfs") Testcase: igt/gem_ctx_persistence/heartbeat-close Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: <stable@vger.kernel.org> # v5.7+ Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200928221510.26044-3-chris@chris-wilson.co.uk (cherry picked from commit d3bb2f9b5ee66d5e000293edd6b6575e59d11db9) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2020-09-28 22:15:10 +00:00
static void kill_engines(struct i915_gem_engines *engines, bool ban)
drm/i915/gem: Cancel contexts when hangchecking is disabled Normally, we rely on our hangcheck to prevent persistent batches from hogging the GPU. However, if the user disables hangcheck, this mechanism breaks down. Despite our insistence that this is unsafe, the users are equally insistent that they want to use endless batches and will disable the hangcheck mechanism. We are looking at replacing hangcheck, in the next patch, with a softer mechanism, that sends a pulse down the engine to check if it is well. We can use the same preemptive pulse to flush an active context off the GPU upon context close, preventing resources being lost and unkillable requests remaining on the GPU after process termination. Testcase: igt/gem_ctx_exec/basic-nohangcheck Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191023133108.21401-4-chris@chris-wilson.co.uk
2019-10-23 13:31:07 +00:00
{
struct i915_gem_engines_iter it;
struct intel_context *ce;
/*
* Map the user's engine back to the actual engines; one virtual
* engine will be mapped to multiple engines, and using ctx->engine[]
* the same engine may be have multiple instances in the user's map.
* However, we only care about pending requests, so only include
* engines on which there are incomplete requests.
*/
drm/i915/gem: Don't leak non-persistent requests on changing engines If we have a set of active engines marked as being non-persistent, we lose track of those if the user replaces those engines with I915_CONTEXT_PARAM_ENGINES. As part of our uABI contract is that non-persistent requests are terminated if they are no longer being tracked by the user's context (in order to prevent a lost request causing an untracked and so unstoppable GPU hang), we need to apply the same context cancellation upon changing engines. v2: Track stale engines[] so we only reap at context closure. v3: Tvrtko spotted races with closing contexts and set-engines, so add a veneer of kill-everything paranoia to clean up after losing a race. Fixes: a0e047156cde ("drm/i915/gem: Make context persistence optional") Testcase: igt/gem_ctx_peristence/replace 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/20200211144831.1011498-1-chris@chris-wilson.co.uk
2020-02-11 14:48:31 +00:00
for_each_gem_engine(ce, engines, it) {
drm/i915/gem: Cancel contexts when hangchecking is disabled Normally, we rely on our hangcheck to prevent persistent batches from hogging the GPU. However, if the user disables hangcheck, this mechanism breaks down. Despite our insistence that this is unsafe, the users are equally insistent that they want to use endless batches and will disable the hangcheck mechanism. We are looking at replacing hangcheck, in the next patch, with a softer mechanism, that sends a pulse down the engine to check if it is well. We can use the same preemptive pulse to flush an active context off the GPU upon context close, preventing resources being lost and unkillable requests remaining on the GPU after process termination. Testcase: igt/gem_ctx_exec/basic-nohangcheck Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191023133108.21401-4-chris@chris-wilson.co.uk
2019-10-23 13:31:07 +00:00
struct intel_engine_cs *engine;
drm/i915/guc: Implement banned contexts for GuC submission When using GuC submission, if a context gets banned disable scheduling and mark all inflight requests as complete. Cc: John Harrison <John.C.Harrison@Intel.com> Signed-off-by: Matthew Brost <matthew.brost@intel.com> Reviewed-by: John Harrison <John.C.Harrison@Intel.com> Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210727002348.97202-25-matthew.brost@intel.com
2021-07-27 00:23:39 +00:00
if (ban && intel_context_ban(ce, NULL))
drm/i915: Drop GEM context as a direct link from i915_request Keep the intel_context as being the primary state for i915_request, with the GEM context a backpointer from the low level state for the rarer cases we need client information. Our goal is to remove such references to clients from the backend, and leave the HW submission agnostic to client interfaces and self-contained. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191220101230.256839-1-chris@chris-wilson.co.uk
2019-12-20 10:12:29 +00:00
continue;
drm/i915/gem: Refine occupancy test in kill_context() Don't just look at the very last request in a queue when deciding if we need to evict the context from the GPU, as that request may still be in the submission queue while the rest of the context is running! Instead, walk back along the queued requests looking for the active request and checking that. Fixes: 2e0986a58cc4 ("drm/i915/gem: Cancel contexts when hangchecking is disabled") Testcase: igt/gem_ctx_persistence/queued Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Cc: Matthew Auld <matthew.auld@intel.com> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191031090104.22245-1-chris@chris-wilson.co.uk
2019-10-31 09:01:04 +00:00
/*
* Check the current active state of this context; if we
* are currently executing on the GPU we need to evict
* ourselves. On the other hand, if we haven't yet been
* submitted to the GPU or if everything is complete,
* we have nothing to do.
*/
engine = active_engine(ce);
drm/i915/gem: Cancel contexts when hangchecking is disabled Normally, we rely on our hangcheck to prevent persistent batches from hogging the GPU. However, if the user disables hangcheck, this mechanism breaks down. Despite our insistence that this is unsafe, the users are equally insistent that they want to use endless batches and will disable the hangcheck mechanism. We are looking at replacing hangcheck, in the next patch, with a softer mechanism, that sends a pulse down the engine to check if it is well. We can use the same preemptive pulse to flush an active context off the GPU upon context close, preventing resources being lost and unkillable requests remaining on the GPU after process termination. Testcase: igt/gem_ctx_exec/basic-nohangcheck Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191023133108.21401-4-chris@chris-wilson.co.uk
2019-10-23 13:31:07 +00:00
/* First attempt to gracefully cancel the context */
drm/i915/gem: Always test execution status on closing the context Verify that if a context is active at the time it is closed, that it is either persistent and preemptible (with hangcheck running) or it shall be removed from execution. Fixes: 9a40bddd47ca ("drm/i915/gt: Expose heartbeat interval via sysfs") Testcase: igt/gem_ctx_persistence/heartbeat-close Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: <stable@vger.kernel.org> # v5.7+ Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200928221510.26044-3-chris@chris-wilson.co.uk (cherry picked from commit d3bb2f9b5ee66d5e000293edd6b6575e59d11db9) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2020-09-28 22:15:10 +00:00
if (engine && !__cancel_engine(engine) && ban)
drm/i915/gem: Cancel contexts when hangchecking is disabled Normally, we rely on our hangcheck to prevent persistent batches from hogging the GPU. However, if the user disables hangcheck, this mechanism breaks down. Despite our insistence that this is unsafe, the users are equally insistent that they want to use endless batches and will disable the hangcheck mechanism. We are looking at replacing hangcheck, in the next patch, with a softer mechanism, that sends a pulse down the engine to check if it is well. We can use the same preemptive pulse to flush an active context off the GPU upon context close, preventing resources being lost and unkillable requests remaining on the GPU after process termination. Testcase: igt/gem_ctx_exec/basic-nohangcheck Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191023133108.21401-4-chris@chris-wilson.co.uk
2019-10-23 13:31:07 +00:00
/*
* If we are unable to send a preemptive pulse to bump
* the context from the GPU, we have to resort to a full
* reset. We hope the collateral damage is worth it.
*/
drm/i915/gem: Don't leak non-persistent requests on changing engines If we have a set of active engines marked as being non-persistent, we lose track of those if the user replaces those engines with I915_CONTEXT_PARAM_ENGINES. As part of our uABI contract is that non-persistent requests are terminated if they are no longer being tracked by the user's context (in order to prevent a lost request causing an untracked and so unstoppable GPU hang), we need to apply the same context cancellation upon changing engines. v2: Track stale engines[] so we only reap at context closure. v3: Tvrtko spotted races with closing contexts and set-engines, so add a veneer of kill-everything paranoia to clean up after losing a race. Fixes: a0e047156cde ("drm/i915/gem: Make context persistence optional") Testcase: igt/gem_ctx_peristence/replace 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/20200211144831.1011498-1-chris@chris-wilson.co.uk
2020-02-11 14:48:31 +00:00
__reset_context(engines->ctx, engine);
}
}
drm/i915/gem: Always test execution status on closing the context Verify that if a context is active at the time it is closed, that it is either persistent and preemptible (with hangcheck running) or it shall be removed from execution. Fixes: 9a40bddd47ca ("drm/i915/gt: Expose heartbeat interval via sysfs") Testcase: igt/gem_ctx_persistence/heartbeat-close Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: <stable@vger.kernel.org> # v5.7+ Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200928221510.26044-3-chris@chris-wilson.co.uk (cherry picked from commit d3bb2f9b5ee66d5e000293edd6b6575e59d11db9) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2020-09-28 22:15:10 +00:00
static void kill_context(struct i915_gem_context *ctx)
drm/i915/gem: Don't leak non-persistent requests on changing engines If we have a set of active engines marked as being non-persistent, we lose track of those if the user replaces those engines with I915_CONTEXT_PARAM_ENGINES. As part of our uABI contract is that non-persistent requests are terminated if they are no longer being tracked by the user's context (in order to prevent a lost request causing an untracked and so unstoppable GPU hang), we need to apply the same context cancellation upon changing engines. v2: Track stale engines[] so we only reap at context closure. v3: Tvrtko spotted races with closing contexts and set-engines, so add a veneer of kill-everything paranoia to clean up after losing a race. Fixes: a0e047156cde ("drm/i915/gem: Make context persistence optional") Testcase: igt/gem_ctx_peristence/replace 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/20200211144831.1011498-1-chris@chris-wilson.co.uk
2020-02-11 14:48:31 +00:00
{
drm/i915/gem: Always test execution status on closing the context Verify that if a context is active at the time it is closed, that it is either persistent and preemptible (with hangcheck running) or it shall be removed from execution. Fixes: 9a40bddd47ca ("drm/i915/gt: Expose heartbeat interval via sysfs") Testcase: igt/gem_ctx_persistence/heartbeat-close Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: <stable@vger.kernel.org> # v5.7+ Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200928221510.26044-3-chris@chris-wilson.co.uk (cherry picked from commit d3bb2f9b5ee66d5e000293edd6b6575e59d11db9) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2020-09-28 22:15:10 +00:00
bool ban = (!i915_gem_context_is_persistent(ctx) ||
!ctx->i915->params.enable_hangcheck);
drm/i915/gem: Don't leak non-persistent requests on changing engines If we have a set of active engines marked as being non-persistent, we lose track of those if the user replaces those engines with I915_CONTEXT_PARAM_ENGINES. As part of our uABI contract is that non-persistent requests are terminated if they are no longer being tracked by the user's context (in order to prevent a lost request causing an untracked and so unstoppable GPU hang), we need to apply the same context cancellation upon changing engines. v2: Track stale engines[] so we only reap at context closure. v3: Tvrtko spotted races with closing contexts and set-engines, so add a veneer of kill-everything paranoia to clean up after losing a race. Fixes: a0e047156cde ("drm/i915/gem: Make context persistence optional") Testcase: igt/gem_ctx_peristence/replace 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/20200211144831.1011498-1-chris@chris-wilson.co.uk
2020-02-11 14:48:31 +00:00
struct i915_gem_engines *pos, *next;
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
spin_lock_irq(&ctx->stale.lock);
GEM_BUG_ON(!i915_gem_context_is_closed(ctx));
drm/i915/gem: Don't leak non-persistent requests on changing engines If we have a set of active engines marked as being non-persistent, we lose track of those if the user replaces those engines with I915_CONTEXT_PARAM_ENGINES. As part of our uABI contract is that non-persistent requests are terminated if they are no longer being tracked by the user's context (in order to prevent a lost request causing an untracked and so unstoppable GPU hang), we need to apply the same context cancellation upon changing engines. v2: Track stale engines[] so we only reap at context closure. v3: Tvrtko spotted races with closing contexts and set-engines, so add a veneer of kill-everything paranoia to clean up after losing a race. Fixes: a0e047156cde ("drm/i915/gem: Make context persistence optional") Testcase: igt/gem_ctx_peristence/replace 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/20200211144831.1011498-1-chris@chris-wilson.co.uk
2020-02-11 14:48:31 +00:00
list_for_each_entry_safe(pos, next, &ctx->stale.engines, link) {
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
if (!i915_sw_fence_await(&pos->fence)) {
list_del_init(&pos->link);
drm/i915/gem: Don't leak non-persistent requests on changing engines If we have a set of active engines marked as being non-persistent, we lose track of those if the user replaces those engines with I915_CONTEXT_PARAM_ENGINES. As part of our uABI contract is that non-persistent requests are terminated if they are no longer being tracked by the user's context (in order to prevent a lost request causing an untracked and so unstoppable GPU hang), we need to apply the same context cancellation upon changing engines. v2: Track stale engines[] so we only reap at context closure. v3: Tvrtko spotted races with closing contexts and set-engines, so add a veneer of kill-everything paranoia to clean up after losing a race. Fixes: a0e047156cde ("drm/i915/gem: Make context persistence optional") Testcase: igt/gem_ctx_peristence/replace 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/20200211144831.1011498-1-chris@chris-wilson.co.uk
2020-02-11 14:48:31 +00:00
continue;
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
}
drm/i915/gem: Don't leak non-persistent requests on changing engines If we have a set of active engines marked as being non-persistent, we lose track of those if the user replaces those engines with I915_CONTEXT_PARAM_ENGINES. As part of our uABI contract is that non-persistent requests are terminated if they are no longer being tracked by the user's context (in order to prevent a lost request causing an untracked and so unstoppable GPU hang), we need to apply the same context cancellation upon changing engines. v2: Track stale engines[] so we only reap at context closure. v3: Tvrtko spotted races with closing contexts and set-engines, so add a veneer of kill-everything paranoia to clean up after losing a race. Fixes: a0e047156cde ("drm/i915/gem: Make context persistence optional") Testcase: igt/gem_ctx_peristence/replace 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/20200211144831.1011498-1-chris@chris-wilson.co.uk
2020-02-11 14:48:31 +00:00
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
spin_unlock_irq(&ctx->stale.lock);
drm/i915/gem: Don't leak non-persistent requests on changing engines If we have a set of active engines marked as being non-persistent, we lose track of those if the user replaces those engines with I915_CONTEXT_PARAM_ENGINES. As part of our uABI contract is that non-persistent requests are terminated if they are no longer being tracked by the user's context (in order to prevent a lost request causing an untracked and so unstoppable GPU hang), we need to apply the same context cancellation upon changing engines. v2: Track stale engines[] so we only reap at context closure. v3: Tvrtko spotted races with closing contexts and set-engines, so add a veneer of kill-everything paranoia to clean up after losing a race. Fixes: a0e047156cde ("drm/i915/gem: Make context persistence optional") Testcase: igt/gem_ctx_peristence/replace 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/20200211144831.1011498-1-chris@chris-wilson.co.uk
2020-02-11 14:48:31 +00:00
drm/i915/gem: Always test execution status on closing the context Verify that if a context is active at the time it is closed, that it is either persistent and preemptible (with hangcheck running) or it shall be removed from execution. Fixes: 9a40bddd47ca ("drm/i915/gt: Expose heartbeat interval via sysfs") Testcase: igt/gem_ctx_persistence/heartbeat-close Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: <stable@vger.kernel.org> # v5.7+ Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200928221510.26044-3-chris@chris-wilson.co.uk (cherry picked from commit d3bb2f9b5ee66d5e000293edd6b6575e59d11db9) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2020-09-28 22:15:10 +00:00
kill_engines(pos, ban);
drm/i915/gem: Don't leak non-persistent requests on changing engines If we have a set of active engines marked as being non-persistent, we lose track of those if the user replaces those engines with I915_CONTEXT_PARAM_ENGINES. As part of our uABI contract is that non-persistent requests are terminated if they are no longer being tracked by the user's context (in order to prevent a lost request causing an untracked and so unstoppable GPU hang), we need to apply the same context cancellation upon changing engines. v2: Track stale engines[] so we only reap at context closure. v3: Tvrtko spotted races with closing contexts and set-engines, so add a veneer of kill-everything paranoia to clean up after losing a race. Fixes: a0e047156cde ("drm/i915/gem: Make context persistence optional") Testcase: igt/gem_ctx_peristence/replace 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/20200211144831.1011498-1-chris@chris-wilson.co.uk
2020-02-11 14:48:31 +00:00
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
spin_lock_irq(&ctx->stale.lock);
GEM_BUG_ON(i915_sw_fence_signaled(&pos->fence));
drm/i915/gem: Don't leak non-persistent requests on changing engines If we have a set of active engines marked as being non-persistent, we lose track of those if the user replaces those engines with I915_CONTEXT_PARAM_ENGINES. As part of our uABI contract is that non-persistent requests are terminated if they are no longer being tracked by the user's context (in order to prevent a lost request causing an untracked and so unstoppable GPU hang), we need to apply the same context cancellation upon changing engines. v2: Track stale engines[] so we only reap at context closure. v3: Tvrtko spotted races with closing contexts and set-engines, so add a veneer of kill-everything paranoia to clean up after losing a race. Fixes: a0e047156cde ("drm/i915/gem: Make context persistence optional") Testcase: igt/gem_ctx_peristence/replace 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/20200211144831.1011498-1-chris@chris-wilson.co.uk
2020-02-11 14:48:31 +00:00
list_safe_reset_next(pos, next, link);
list_del_init(&pos->link); /* decouple from FENCE_COMPLETE */
i915_sw_fence_complete(&pos->fence);
drm/i915/gem: Cancel contexts when hangchecking is disabled Normally, we rely on our hangcheck to prevent persistent batches from hogging the GPU. However, if the user disables hangcheck, this mechanism breaks down. Despite our insistence that this is unsafe, the users are equally insistent that they want to use endless batches and will disable the hangcheck mechanism. We are looking at replacing hangcheck, in the next patch, with a softer mechanism, that sends a pulse down the engine to check if it is well. We can use the same preemptive pulse to flush an active context off the GPU upon context close, preventing resources being lost and unkillable requests remaining on the GPU after process termination. Testcase: igt/gem_ctx_exec/basic-nohangcheck Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191023133108.21401-4-chris@chris-wilson.co.uk
2019-10-23 13:31:07 +00:00
}
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
spin_unlock_irq(&ctx->stale.lock);
drm/i915/gem: Don't leak non-persistent requests on changing engines If we have a set of active engines marked as being non-persistent, we lose track of those if the user replaces those engines with I915_CONTEXT_PARAM_ENGINES. As part of our uABI contract is that non-persistent requests are terminated if they are no longer being tracked by the user's context (in order to prevent a lost request causing an untracked and so unstoppable GPU hang), we need to apply the same context cancellation upon changing engines. v2: Track stale engines[] so we only reap at context closure. v3: Tvrtko spotted races with closing contexts and set-engines, so add a veneer of kill-everything paranoia to clean up after losing a race. Fixes: a0e047156cde ("drm/i915/gem: Make context persistence optional") Testcase: igt/gem_ctx_peristence/replace 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/20200211144831.1011498-1-chris@chris-wilson.co.uk
2020-02-11 14:48:31 +00:00
}
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
static void engines_idle_release(struct i915_gem_context *ctx,
struct i915_gem_engines *engines)
{
struct i915_gem_engines_iter it;
struct intel_context *ce;
INIT_LIST_HEAD(&engines->link);
engines->ctx = i915_gem_context_get(ctx);
for_each_gem_engine(ce, engines, it) {
drm/i915/gem: Wait until the context is finally retired before releasing engines If we want to percolate information back from the HW, up through the GEM context, we need to wait until the intel_context is scheduled out for the last time. This is handled by the retirement of the intel_context's barrier, i.e. by listening to the pulse after the notional unpin. So wait until the intel_context is finally retired before releasing the engine, so that we can inspect the final context state and pass it on. 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/20200406155840.1728-3-chris@chris-wilson.co.uk
2020-04-06 15:58:40 +00:00
int err;
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
/* serialises with execbuf */
drm/i915: Use explicit flag to mark unreachable intel_context I need to keep the GEM context around a bit longer so adding an explicit flag for syncing execbuf with closed/abandonded contexts. v2: * Use already available context flags. (Chris) Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@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/20200319170707.8262-1-chris@chris-wilson.co.uk
2020-03-19 17:07:06 +00:00
set_bit(CONTEXT_CLOSED_BIT, &ce->flags);
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
if (!intel_context_pin_if_active(ce))
continue;
drm/i915/gem: Wait until the context is finally retired before releasing engines If we want to percolate information back from the HW, up through the GEM context, we need to wait until the intel_context is scheduled out for the last time. This is handled by the retirement of the intel_context's barrier, i.e. by listening to the pulse after the notional unpin. So wait until the intel_context is finally retired before releasing the engine, so that we can inspect the final context state and pass it on. 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/20200406155840.1728-3-chris@chris-wilson.co.uk
2020-04-06 15:58:40 +00:00
/* Wait until context is finally scheduled out and retired */
err = i915_sw_fence_await_active(&engines->fence,
&ce->active,
I915_ACTIVE_AWAIT_BARRIER);
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
intel_context_unpin(ce);
drm/i915/gem: Wait until the context is finally retired before releasing engines If we want to percolate information back from the HW, up through the GEM context, we need to wait until the intel_context is scheduled out for the last time. This is handled by the retirement of the intel_context's barrier, i.e. by listening to the pulse after the notional unpin. So wait until the intel_context is finally retired before releasing the engine, so that we can inspect the final context state and pass it on. 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/20200406155840.1728-3-chris@chris-wilson.co.uk
2020-04-06 15:58:40 +00:00
if (err)
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
goto kill;
}
spin_lock_irq(&ctx->stale.lock);
if (!i915_gem_context_is_closed(ctx))
list_add_tail(&engines->link, &ctx->stale.engines);
spin_unlock_irq(&ctx->stale.lock);
kill:
if (list_empty(&engines->link)) /* raced, already closed */
drm/i915/gem: Always test execution status on closing the context Verify that if a context is active at the time it is closed, that it is either persistent and preemptible (with hangcheck running) or it shall be removed from execution. Fixes: 9a40bddd47ca ("drm/i915/gt: Expose heartbeat interval via sysfs") Testcase: igt/gem_ctx_persistence/heartbeat-close Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: <stable@vger.kernel.org> # v5.7+ Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200928221510.26044-3-chris@chris-wilson.co.uk (cherry picked from commit d3bb2f9b5ee66d5e000293edd6b6575e59d11db9) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2020-09-28 22:15:10 +00:00
kill_engines(engines, true);
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
i915_sw_fence_commit(&engines->fence);
drm/i915/gem: Cancel contexts when hangchecking is disabled Normally, we rely on our hangcheck to prevent persistent batches from hogging the GPU. However, if the user disables hangcheck, this mechanism breaks down. Despite our insistence that this is unsafe, the users are equally insistent that they want to use endless batches and will disable the hangcheck mechanism. We are looking at replacing hangcheck, in the next patch, with a softer mechanism, that sends a pulse down the engine to check if it is well. We can use the same preemptive pulse to flush an active context off the GPU upon context close, preventing resources being lost and unkillable requests remaining on the GPU after process termination. Testcase: igt/gem_ctx_exec/basic-nohangcheck Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191023133108.21401-4-chris@chris-wilson.co.uk
2019-10-23 13:31:07 +00:00
}
drm/i915/gem: Update context name on closing Update the context.name on closing so that the persistent requests are clear in debug prints. 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/20191111114323.5833-3-chris@chris-wilson.co.uk
2019-11-11 11:43:21 +00:00
static void set_closed_name(struct i915_gem_context *ctx)
{
char *s;
/* Replace '[]' with '<>' to indicate closed in debug prints */
s = strrchr(ctx->name, '[');
if (!s)
return;
*s = '<';
s = strchr(s + 1, ']');
if (s)
*s = '>';
}
drm/i915: Mark the context and address space as closed When the user closes the context mark it and the dependent address space as closed. As we use an asynchronous destruct method, this has two purposes. First it allows us to flag the closed context and detect internal errors if we to create any new objects for it (as it is removed from the user's namespace, these should be internal bugs only). And secondly, it allows us to immediately reap stale vma. 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/1470293567-10811-27-git-send-email-chris@chris-wilson.co.uk
2016-08-04 06:52:46 +00:00
static void context_close(struct i915_gem_context *ctx)
{
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
struct i915_address_space *vm;
drm/i915: Pull i915_vma_pin under the vm->mutex Replace the struct_mutex requirement for pinning the i915_vma with the local vm->mutex instead. Note that the vm->mutex is tainted by the shrinker (we require unbinding from inside fs-reclaim) and so we cannot allocate while holding that mutex. Instead we have to preallocate workers to do allocate and apply the PTE updates after we have we reserved their slot in the drm_mm (using fences to order the PTE writes with the GPU work and with later unbind). In adding the asynchronous vma binding, one subtle requirement is to avoid coupling the binding fence into the backing object->resv. That is the asynchronous binding only applies to the vma timeline itself and not to the pages as that is a more global timeline (the binding of one vma does not need to be ordered with another vma, nor does the implicit GEM fencing depend on a vma, only on writes to the backing store). Keeping the vma binding distinct from the backing store timelines is verified by a number of async gem_exec_fence and gem_exec_schedule tests. The way we do this is quite simple, we keep the fence for the vma binding separate and only wait on it as required, and never add it to the obj->resv itself. Another consequence in reducing the locking around the vma is the destruction of the vma is no longer globally serialised by struct_mutex. A natural solution would be to add a kref to i915_vma, but that requires decoupling the reference cycles, possibly by introducing a new i915_mm_pages object that is own by both obj->mm and vma->pages. However, we have not taken that route due to the overshadowing lmem/ttm discussions, and instead play a series of complicated games with trylocks to (hopefully) ensure that only one destruction path is called! v2: Add some commentary, and some helpers to reduce patch churn. 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/20191004134015.13204-4-chris@chris-wilson.co.uk
2019-10-04 13:39:58 +00:00
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
/* Flush any concurrent set_engines() */
mutex_lock(&ctx->engines_mutex);
engines_idle_release(ctx, rcu_replace_pointer(ctx->engines, NULL, 1));
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
i915_gem_context_set_closed(ctx);
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
mutex_unlock(&ctx->engines_mutex);
drm/i915: Pull i915_vma_pin under the vm->mutex Replace the struct_mutex requirement for pinning the i915_vma with the local vm->mutex instead. Note that the vm->mutex is tainted by the shrinker (we require unbinding from inside fs-reclaim) and so we cannot allocate while holding that mutex. Instead we have to preallocate workers to do allocate and apply the PTE updates after we have we reserved their slot in the drm_mm (using fences to order the PTE writes with the GPU work and with later unbind). In adding the asynchronous vma binding, one subtle requirement is to avoid coupling the binding fence into the backing object->resv. That is the asynchronous binding only applies to the vma timeline itself and not to the pages as that is a more global timeline (the binding of one vma does not need to be ordered with another vma, nor does the implicit GEM fencing depend on a vma, only on writes to the backing store). Keeping the vma binding distinct from the backing store timelines is verified by a number of async gem_exec_fence and gem_exec_schedule tests. The way we do this is quite simple, we keep the fence for the vma binding separate and only wait on it as required, and never add it to the obj->resv itself. Another consequence in reducing the locking around the vma is the destruction of the vma is no longer globally serialised by struct_mutex. A natural solution would be to add a kref to i915_vma, but that requires decoupling the reference cycles, possibly by introducing a new i915_mm_pages object that is own by both obj->mm and vma->pages. However, we have not taken that route due to the overshadowing lmem/ttm discussions, and instead play a series of complicated games with trylocks to (hopefully) ensure that only one destruction path is called! v2: Add some commentary, and some helpers to reduce patch churn. 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/20191004134015.13204-4-chris@chris-wilson.co.uk
2019-10-04 13:39:58 +00:00
drm/i915: Move object close under its own lock Use i915_gem_object_lock() to guard the LUT and active reference to allow us to break free of struct_mutex for handling GEM_CLOSE. Testcase: igt/gem_close_race Testcase: igt/gem_exec_parallel Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190606112320.9704-1-chris@chris-wilson.co.uk
2019-06-06 11:23:20 +00:00
mutex_lock(&ctx->mutex);
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
set_closed_name(ctx);
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
vm = i915_gem_context_vm(ctx);
if (vm)
i915_vm_close(vm);
drm/i915: Implement SINGLE_TIMELINE with a syncobj (v4) This API is entirely unnecessary and I'd love to get rid of it. If userspace wants a single timeline across multiple contexts, they can either use implicit synchronization or a syncobj, both of which existed at the time this feature landed. The justification given at the time was that it would help GL drivers which are inherently single-timeline. However, neither of our GL drivers actually wanted the feature. i965 was already in maintenance mode at the time and iris uses syncobj for everything. Unfortunately, as much as I'd love to get rid of it, it is used by the media driver so we can't do that. We can, however, do the next-best thing which is to embed a syncobj in the context and do exactly what we'd expect from userspace internally. This isn't an entirely identical implementation because it's no longer atomic if userspace races with itself by calling execbuffer2 twice simultaneously from different threads. It won't crash in that case; it just doesn't guarantee any ordering between those two submits. It also means that sync files exported from different engines on a SINGLE_TIMELINE context will have different fence contexts. This is visible to userspace if it looks at the obj_name field of sync_fence_info. Moving SINGLE_TIMELINE to a syncobj emulation has a couple of technical advantages beyond mere annoyance. One is that intel_timeline is no longer an api-visible object and can remain entirely an implementation detail. This may be advantageous as we make scheduler changes going forward. Second is that, together with deleting the CLONE_CONTEXT API, we should now have a 1:1 mapping between intel_context and intel_timeline which may help us reduce locking. v2 (Tvrtko Ursulin): - Update the comment on i915_gem_context::syncobj to mention that it's an emulation and the possible race if userspace calls execbuffer2 twice on the same context concurrently. v2 (Jason Ekstrand): - Wrap the checks for eb.gem_context->syncobj in unlikely() - Drop the dma_fence reference - Improved commit message v3 (Jason Ekstrand): - Move the dma_fence_put() to before the error exit v4 (Tvrtko Ursulin): - Add a comment about fence contexts to the commit message Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-8-jason@jlekstrand.net
2021-07-08 15:48:12 +00:00
if (ctx->syncobj)
drm_syncobj_put(ctx->syncobj);
drm/i915: Move object close under its own lock Use i915_gem_object_lock() to guard the LUT and active reference to allow us to break free of struct_mutex for handling GEM_CLOSE. Testcase: igt/gem_close_race Testcase: igt/gem_exec_parallel Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190606112320.9704-1-chris@chris-wilson.co.uk
2019-06-06 11:23:20 +00:00
ctx->file_priv = ERR_PTR(-EBADF);
drm/i915: Replace execbuf vma ht with an idr 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
2017-08-16 08:52:08 +00:00
drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU When we close the VMA, we unbind it from the ppgtt and tear down the page directory pointing at it. That may trigger us to return WC pages back to the system, requiring conversion back to WB which itself may sleep. That makes i915_vma_close() unsuitable for use inside the RCU read lock, which we need to hold to iterate the radixtree. The fix is quite simple, we can close all the VMA as we close the ppgtt, we only need to do that instead of closing them during destruction of the LUT. v2: Order between closing the LUT and the ppgtt is important; we use the vma inside the LUT as a means of retrieving the object, and so we must clear the LUT before freeing the VMA when closing the ppgtt. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103638 Fixes: 547da76b5777 ("drm/i915: Hold rcu_read_lock when iterating over the radixtree (vma idr)") Fixes: d1b48c1e7184 ("drm/i915: Replace execbuf vma ht with an idr") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@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/20171109085540.32264-1-chris@chris-wilson.co.uk Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
2017-11-09 08:55:40 +00:00
/*
* The LUT uses the VMA as a backpointer to unref the object,
* so we need to clear the LUT before we close all the VMA (inside
* the ppgtt).
*/
drm/i915: Replace execbuf vma ht with an idr 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
2017-08-16 08:52:08 +00:00
lut_close(ctx);
drm/i915/gem: Drop free_work for GEM contexts The free_list and worker was introduced in commit 5f09a9c8ab6b ("drm/i915: Allow contexts to be unreferenced locklessly"), but subsequently made redundant by the removal of the last sleeping lock in commit 2935ed5339c4 ("drm/i915: Remove logical HW ID"). As we can now free the GEM context immediately from any context, remove the deferral of the free_list v2: Lift removing the context from the global list into close(). 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> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Matthew Brost <matthew.brost@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20201215152138.8158-1-chris@chris-wilson.co.uk
2020-12-15 15:21:38 +00:00
spin_lock(&ctx->i915->gem.contexts.lock);
list_del(&ctx->link);
spin_unlock(&ctx->i915->gem.contexts.lock);
drm/i915: Move object close under its own lock Use i915_gem_object_lock() to guard the LUT and active reference to allow us to break free of struct_mutex for handling GEM_CLOSE. Testcase: igt/gem_close_race Testcase: igt/gem_exec_parallel Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190606112320.9704-1-chris@chris-wilson.co.uk
2019-06-06 11:23:20 +00:00
mutex_unlock(&ctx->mutex);
drm/i915/gem: Cancel contexts when hangchecking is disabled Normally, we rely on our hangcheck to prevent persistent batches from hogging the GPU. However, if the user disables hangcheck, this mechanism breaks down. Despite our insistence that this is unsafe, the users are equally insistent that they want to use endless batches and will disable the hangcheck mechanism. We are looking at replacing hangcheck, in the next patch, with a softer mechanism, that sends a pulse down the engine to check if it is well. We can use the same preemptive pulse to flush an active context off the GPU upon context close, preventing resources being lost and unkillable requests remaining on the GPU after process termination. Testcase: igt/gem_ctx_exec/basic-nohangcheck Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191023133108.21401-4-chris@chris-wilson.co.uk
2019-10-23 13:31:07 +00:00
/*
* If the user has disabled hangchecking, we can not be sure that
* the batches will ever complete after the context is closed,
* keeping the context and all resources pinned forever. So in this
* case we opt to forcibly kill off all remaining requests on
* context close.
*/
drm/i915/gem: Always test execution status on closing the context Verify that if a context is active at the time it is closed, that it is either persistent and preemptible (with hangcheck running) or it shall be removed from execution. Fixes: 9a40bddd47ca ("drm/i915/gt: Expose heartbeat interval via sysfs") Testcase: igt/gem_ctx_persistence/heartbeat-close Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: <stable@vger.kernel.org> # v5.7+ Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Acked-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200928221510.26044-3-chris@chris-wilson.co.uk (cherry picked from commit d3bb2f9b5ee66d5e000293edd6b6575e59d11db9) Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
2020-09-28 22:15:10 +00:00
kill_context(ctx);
drm/i915/gem: Cancel contexts when hangchecking is disabled Normally, we rely on our hangcheck to prevent persistent batches from hogging the GPU. However, if the user disables hangcheck, this mechanism breaks down. Despite our insistence that this is unsafe, the users are equally insistent that they want to use endless batches and will disable the hangcheck mechanism. We are looking at replacing hangcheck, in the next patch, with a softer mechanism, that sends a pulse down the engine to check if it is well. We can use the same preemptive pulse to flush an active context off the GPU upon context close, preventing resources being lost and unkillable requests remaining on the GPU after process termination. Testcase: igt/gem_ctx_exec/basic-nohangcheck Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191023133108.21401-4-chris@chris-wilson.co.uk
2019-10-23 13:31:07 +00:00
drm/i915: Mark the context and address space as closed When the user closes the context mark it and the dependent address space as closed. As we use an asynchronous destruct method, this has two purposes. First it allows us to flag the closed context and detect internal errors if we to create any new objects for it (as it is removed from the user's namespace, these should be internal bugs only). And secondly, it allows us to immediately reap stale vma. 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/1470293567-10811-27-git-send-email-chris@chris-wilson.co.uk
2016-08-04 06:52:46 +00:00
i915_gem_context_put(ctx);
}
drm/i915/gem: Make context persistence optional Our existing behaviour is to allow contexts and their GPU requests to persist past the point of closure until the requests are complete. This allows clients to operate in a 'fire-and-forget' manner where they can setup a rendering pipeline and hand it over to the display server and immediately exit. As the rendering pipeline is kept alive until completion, the display server (or other consumer) can use the results in the future and present them to the user. The compute model is a little different. They have little to no buffer sharing between processes as their kernels tend to operate on a continuous stream, feeding the results back to the client application. These kernels operate for an indeterminate length of time, with many clients wishing that the kernel was always running for as long as they keep feeding in the data, i.e. acting like a DSP. Not all clients want this persistent "desktop" behaviour and would prefer that the contexts are cleaned up immediately upon closure. This ensures that when clients are run without hangchecking (e.g. for compute kernels of indeterminate runtime), any GPU hang or other unexpected workloads are terminated with the process and does not continue to hog resources. The default behaviour for new contexts is the legacy persistence mode, as some desktop applications are dependent upon the existing behaviour. New clients will have to opt in to immediate cleanup on context closure. If the hangchecking modparam is disabled, so is persistent context support -- all contexts will be terminated on closure. We expect this behaviour change to be welcomed by compute users, who have often been caught between a rock and a hard place. They disable hangchecking to avoid their kernels being "unfairly" declared hung, but have also experienced true hangs that the system was then unable to clean up. Naturally, this leads to bug reports. Testcase: igt/gem_ctx_persistence Link: https://github.com/intel/compute-runtime/pull/228 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Jason Ekstrand <jason@jlekstrand.net> Link: https://patchwork.freedesktop.org/patch/msgid/20191029202338.8841-1-chris@chris-wilson.co.uk
2019-10-29 20:23:38 +00:00
static int __context_set_persistence(struct i915_gem_context *ctx, bool state)
{
if (i915_gem_context_is_persistent(ctx) == state)
return 0;
if (state) {
/*
* Only contexts that are short-lived [that will expire or be
* reset] are allowed to survive past termination. We require
* hangcheck to ensure that the persistent requests are healthy.
*/
drm/i915/params: switch to device specific parameters Start using device specific parameters instead of module parameters for most things. The module parameters become the immutable initial values for i915 parameters. The device specific parameters in i915->params start life as a copy of i915_modparams. Any later changes are only reflected in the debugfs. The stragglers are: * i915.force_probe and i915.modeset. Needed before dev_priv is available. This is fine because the parameters are read-only and never modified. * i915.verbose_state_checks. Passing dev_priv to I915_STATE_WARN and I915_STATE_WARN_ON would result in massive and ugly churn. This is handled by not exposing the parameter via debugfs, and leaving the parameter writable in sysfs. This may be fixed up in follow-up work. * i915.inject_probe_failure. Only makes sense in terms of the module, not the device. This is handled by not exposing the parameter via debugfs. v2: Fix uc i915 lookup code (Michał Winiarski) Cc: Juha-Pekka Heikkilä <juha-pekka.heikkila@intel.com> Cc: Venkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Acked-by: Michał Winiarski <michal.winiarski@intel.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/20200618150402.14022-1-jani.nikula@intel.com
2020-06-18 15:04:02 +00:00
if (!ctx->i915->params.enable_hangcheck)
drm/i915/gem: Make context persistence optional Our existing behaviour is to allow contexts and their GPU requests to persist past the point of closure until the requests are complete. This allows clients to operate in a 'fire-and-forget' manner where they can setup a rendering pipeline and hand it over to the display server and immediately exit. As the rendering pipeline is kept alive until completion, the display server (or other consumer) can use the results in the future and present them to the user. The compute model is a little different. They have little to no buffer sharing between processes as their kernels tend to operate on a continuous stream, feeding the results back to the client application. These kernels operate for an indeterminate length of time, with many clients wishing that the kernel was always running for as long as they keep feeding in the data, i.e. acting like a DSP. Not all clients want this persistent "desktop" behaviour and would prefer that the contexts are cleaned up immediately upon closure. This ensures that when clients are run without hangchecking (e.g. for compute kernels of indeterminate runtime), any GPU hang or other unexpected workloads are terminated with the process and does not continue to hog resources. The default behaviour for new contexts is the legacy persistence mode, as some desktop applications are dependent upon the existing behaviour. New clients will have to opt in to immediate cleanup on context closure. If the hangchecking modparam is disabled, so is persistent context support -- all contexts will be terminated on closure. We expect this behaviour change to be welcomed by compute users, who have often been caught between a rock and a hard place. They disable hangchecking to avoid their kernels being "unfairly" declared hung, but have also experienced true hangs that the system was then unable to clean up. Naturally, this leads to bug reports. Testcase: igt/gem_ctx_persistence Link: https://github.com/intel/compute-runtime/pull/228 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Jason Ekstrand <jason@jlekstrand.net> Link: https://patchwork.freedesktop.org/patch/msgid/20191029202338.8841-1-chris@chris-wilson.co.uk
2019-10-29 20:23:38 +00:00
return -EINVAL;
i915_gem_context_set_persistence(ctx);
} else {
/* To cancel a context we use "preempt-to-idle" */
if (!(ctx->i915->caps.scheduler & I915_SCHEDULER_CAP_PREEMPTION))
return -ENODEV;
drm/i915/gem: Require per-engine reset support for non-persistent contexts To enable non-persistent contexts, we require a means of cancelling any inflight work from that context. This is first done "gracefully" by using preemption to kick the active context off the engine, and then forcefully by resetting the engine if it is active. If we are unable to reset the engine to remove hostile userspace, we should not allow userspace to opt into using non-persistent contexts. If the per-engine reset fails, we still do a full GPU reset, but that is rare and usually indicative of much deeper issues. The damage is already done. However, the goal of the interface to allow long running compute jobs without causing collateral damage elsewhere, and if we are unable to support that we should make that known by not providing the interface (and falsely pretending we can). Fixes: a0e047156cde ("drm/i915/gem: Make context persistence optional") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200130164553.1937718-1-chris@chris-wilson.co.uk
2020-01-30 16:45:53 +00:00
/*
* If the cancel fails, we then need to reset, cleanly!
*
* If the per-engine reset fails, all hope is lost! We resort
* to a full GPU reset in that unlikely case, but realistically
* if the engine could not reset, the full reset does not fare
* much better. The damage has been done.
*
* However, if we cannot reset an engine by itself, we cannot
* cleanup a hanging persistent context without causing
* colateral damage, and we should not pretend we can by
* exposing the interface.
*/
if (!intel_has_reset_engine(&ctx->i915->gt))
return -ENODEV;
drm/i915/gem: Make context persistence optional Our existing behaviour is to allow contexts and their GPU requests to persist past the point of closure until the requests are complete. This allows clients to operate in a 'fire-and-forget' manner where they can setup a rendering pipeline and hand it over to the display server and immediately exit. As the rendering pipeline is kept alive until completion, the display server (or other consumer) can use the results in the future and present them to the user. The compute model is a little different. They have little to no buffer sharing between processes as their kernels tend to operate on a continuous stream, feeding the results back to the client application. These kernels operate for an indeterminate length of time, with many clients wishing that the kernel was always running for as long as they keep feeding in the data, i.e. acting like a DSP. Not all clients want this persistent "desktop" behaviour and would prefer that the contexts are cleaned up immediately upon closure. This ensures that when clients are run without hangchecking (e.g. for compute kernels of indeterminate runtime), any GPU hang or other unexpected workloads are terminated with the process and does not continue to hog resources. The default behaviour for new contexts is the legacy persistence mode, as some desktop applications are dependent upon the existing behaviour. New clients will have to opt in to immediate cleanup on context closure. If the hangchecking modparam is disabled, so is persistent context support -- all contexts will be terminated on closure. We expect this behaviour change to be welcomed by compute users, who have often been caught between a rock and a hard place. They disable hangchecking to avoid their kernels being "unfairly" declared hung, but have also experienced true hangs that the system was then unable to clean up. Naturally, this leads to bug reports. Testcase: igt/gem_ctx_persistence Link: https://github.com/intel/compute-runtime/pull/228 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Jason Ekstrand <jason@jlekstrand.net> Link: https://patchwork.freedesktop.org/patch/msgid/20191029202338.8841-1-chris@chris-wilson.co.uk
2019-10-29 20:23:38 +00:00
i915_gem_context_clear_persistence(ctx);
}
return 0;
}
drm/i915/gem: Utilize rcu iteration of context engines Now that we can peek at GEM->engines[] and obtain a reference to them using RCU, do so for instances where we can safely iterate the potentially old copy of the engines. For setting, we can do this when we know the engine properties are copied over before swapping, so we know the new engines already have the global property and we update the old before they are discarded. For reading, we only need to be safe; as we do so on behalf of the user, their races are their own problem. 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/20200402124218.6375-1-chris@chris-wilson.co.uk
2020-04-02 12:42:18 +00:00
static inline struct i915_gem_engines *
drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source When cloning the engines from the source context, we need to ensure that the engines are not freed as we copy them, and that the flags we clone from the source correspond with the engines we copy across. To do this we need only take a reference to the src->engines, rather than hold the src->engine_mutex, so long as we verify that nothing changed under the read. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210114135612.13210-3-chris@chris-wilson.co.uk
2021-01-14 13:56:10 +00:00
__context_engines_await(const struct i915_gem_context *ctx,
bool *user_engines)
drm/i915/gem: Utilize rcu iteration of context engines Now that we can peek at GEM->engines[] and obtain a reference to them using RCU, do so for instances where we can safely iterate the potentially old copy of the engines. For setting, we can do this when we know the engine properties are copied over before swapping, so we know the new engines already have the global property and we update the old before they are discarded. For reading, we only need to be safe; as we do so on behalf of the user, their races are their own problem. 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/20200402124218.6375-1-chris@chris-wilson.co.uk
2020-04-02 12:42:18 +00:00
{
struct i915_gem_engines *engines;
rcu_read_lock();
do {
engines = rcu_dereference(ctx->engines);
GEM_BUG_ON(!engines);
drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source When cloning the engines from the source context, we need to ensure that the engines are not freed as we copy them, and that the flags we clone from the source correspond with the engines we copy across. To do this we need only take a reference to the src->engines, rather than hold the src->engine_mutex, so long as we verify that nothing changed under the read. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210114135612.13210-3-chris@chris-wilson.co.uk
2021-01-14 13:56:10 +00:00
if (user_engines)
*user_engines = i915_gem_context_user_engines(ctx);
/* successful await => strong mb */
drm/i915/gem: Utilize rcu iteration of context engines Now that we can peek at GEM->engines[] and obtain a reference to them using RCU, do so for instances where we can safely iterate the potentially old copy of the engines. For setting, we can do this when we know the engine properties are copied over before swapping, so we know the new engines already have the global property and we update the old before they are discarded. For reading, we only need to be safe; as we do so on behalf of the user, their races are their own problem. 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/20200402124218.6375-1-chris@chris-wilson.co.uk
2020-04-02 12:42:18 +00:00
if (unlikely(!i915_sw_fence_await(&engines->fence)))
continue;
if (likely(engines == rcu_access_pointer(ctx->engines)))
break;
i915_sw_fence_complete(&engines->fence);
} while (1);
rcu_read_unlock();
return engines;
}
drm/i915/gem: Return void from context_apply_all None of the callbacks we use with it return an error code anymore; they all return 0 unconditionally. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-6-jason@jlekstrand.net
2021-07-08 15:48:10 +00:00
static void
drm/i915: Push the ring creation flags to the backend Push the ring creation flags from the outer GEM context to the inner intel_context to avoid an unsightly back-reference from inside the backend. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190809182518.20486-3-chris@chris-wilson.co.uk
2019-08-09 18:25:17 +00:00
context_apply_all(struct i915_gem_context *ctx,
drm/i915/gem: Return void from context_apply_all None of the callbacks we use with it return an error code anymore; they all return 0 unconditionally. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-6-jason@jlekstrand.net
2021-07-08 15:48:10 +00:00
void (*fn)(struct intel_context *ce, void *data),
drm/i915: Push the ring creation flags to the backend Push the ring creation flags from the outer GEM context to the inner intel_context to avoid an unsightly back-reference from inside the backend. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190809182518.20486-3-chris@chris-wilson.co.uk
2019-08-09 18:25:17 +00:00
void *data)
{
struct i915_gem_engines_iter it;
drm/i915/gem: Utilize rcu iteration of context engines Now that we can peek at GEM->engines[] and obtain a reference to them using RCU, do so for instances where we can safely iterate the potentially old copy of the engines. For setting, we can do this when we know the engine properties are copied over before swapping, so we know the new engines already have the global property and we update the old before they are discarded. For reading, we only need to be safe; as we do so on behalf of the user, their races are their own problem. 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/20200402124218.6375-1-chris@chris-wilson.co.uk
2020-04-02 12:42:18 +00:00
struct i915_gem_engines *e;
drm/i915: Push the ring creation flags to the backend Push the ring creation flags from the outer GEM context to the inner intel_context to avoid an unsightly back-reference from inside the backend. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190809182518.20486-3-chris@chris-wilson.co.uk
2019-08-09 18:25:17 +00:00
struct intel_context *ce;
drm/i915/gem: Reduce ctx->engine_mutex for reading the clone source When cloning the engines from the source context, we need to ensure that the engines are not freed as we copy them, and that the flags we clone from the source correspond with the engines we copy across. To do this we need only take a reference to the src->engines, rather than hold the src->engine_mutex, so long as we verify that nothing changed under the read. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210114135612.13210-3-chris@chris-wilson.co.uk
2021-01-14 13:56:10 +00:00
e = __context_engines_await(ctx, NULL);
drm/i915/gem: Return void from context_apply_all None of the callbacks we use with it return an error code anymore; they all return 0 unconditionally. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-6-jason@jlekstrand.net
2021-07-08 15:48:10 +00:00
for_each_gem_engine(ce, e, it)
fn(ce, data);
drm/i915/gem: Utilize rcu iteration of context engines Now that we can peek at GEM->engines[] and obtain a reference to them using RCU, do so for instances where we can safely iterate the potentially old copy of the engines. For setting, we can do this when we know the engine properties are copied over before swapping, so we know the new engines already have the global property and we update the old before they are discarded. For reading, we only need to be safe; as we do so on behalf of the user, their races are their own problem. 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/20200402124218.6375-1-chris@chris-wilson.co.uk
2020-04-02 12:42:18 +00:00
i915_sw_fence_complete(&e->fence);
drm/i915: Push the ring creation flags to the backend Push the ring creation flags from the outer GEM context to the inner intel_context to avoid an unsightly back-reference from inside the backend. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190809182518.20486-3-chris@chris-wilson.co.uk
2019-08-09 18:25:17 +00:00
}
drm/i915: Rename struct intel_context Our goal is to rename the anonymous per-engine struct beneath the current intel_context. However, after a lively debate resolving around the confusion between intel_context_engine and intel_engine_context, the realisation is that the two structs target different users. The outer struct is API / user facing, and so carries the higher level GEM information. The inner struct is hw facing. Thus we want to name the inner struct intel_context and the outer one i915_gem_context. As the first step, we need to rename the current struct: s/struct intel_context/struct i915_gem_context/ which fits much better with its constructors already conveying the i915_gem_context prefix! Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dave Gordon <david.s.gordon@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1464098023-3294-1-git-send-email-chris@chris-wilson.co.uk
2016-05-24 13:53:34 +00:00
static struct i915_gem_context *
drm/i915/gem: Add an intermediate proto_context struct (v5) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. Unfortunately, both methods of setting the VM and the engine set are in active use today so we can't simply disallow setting the VM or engine set vial SET_CONTEXT_PARAM. In order to work around this wart, this commit adds a proto-context struct which contains all the context create parameters. v2 (Daniel Vetter): - Better commit message - Use __set/clear_bit instead of set/clear_bit because there's no race and we don't need the atomics v3 (Daniel Vetter): - Use manual bitops and BIT() instead of __set_bit v4 (Daniel Vetter): - Add a changelog to the commit message - Better hyperlinking in docs - Create the default PPGTT in i915_gem_create_context v5 (Daniel Vetter): - Hand-roll the initialization of UCONTEXT_PERSISTENCE Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-17-jason@jlekstrand.net
2021-07-08 15:48:21 +00:00
i915_gem_create_context(struct drm_i915_private *i915,
const struct i915_gem_proto_context *pc)
drm/i915: preliminary context support Very basic code for context setup/destruction in the driver. Adds the file i915_gem_context.c This file implements HW context support. On gen5+ a HW context consists of an opaque GPU object which is referenced at times of context saves and restores. With RC6 enabled, the context is also referenced as the GPU enters and exists from RC6 (GPU has it's own internal power context, except on gen5). Though something like a context does exist for the media ring, the code only supports contexts for the render ring. In software, there is a distinction between contexts created by the user, and the default HW context. The default HW context is used by GPU clients that do not request setup of their own hardware context. The default context's state is never restored to help prevent programming errors. This would happen if a client ran and piggy-backed off another clients GPU state. The default context only exists to give the GPU some offset to load as the current to invoke a save of the context we actually care about. In fact, the code could likely be constructed, albeit in a more complicated fashion, to never use the default context, though that limits the driver's ability to swap out, and/or destroy other contexts. All other contexts are created as a request by the GPU client. These contexts store GPU state, and thus allow GPU clients to not re-emit state (and potentially query certain state) at any time. The kernel driver makes certain that the appropriate commands are inserted. There are 4 entry points into the contexts, init, fini, open, close. The names are self-explanatory except that init can be called during reset, and also during pm thaw/resume. As we expect our context to be preserved across these events, we do not reinitialize in this case. As Adam Jackson pointed out, The cutoff of 1MB where a HW context is considered too big is arbitrary. The reason for this is even though context sizes are increasing with every generation, they have yet to eclipse even 32k. If we somehow read back way more than that, it probably means BIOS has done something strange, or we're running on a platform that wasn't designed for this. v2: rename load/unload to init/fini (daniel) remove ILK support for get_size() (indirectly daniel) add HAS_HW_CONTEXTS macro to clarify supported platforms (daniel) added comments (Ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:42 +00:00
{
drm/i915: Rename struct intel_context Our goal is to rename the anonymous per-engine struct beneath the current intel_context. However, after a lively debate resolving around the confusion between intel_context_engine and intel_engine_context, the realisation is that the two structs target different users. The outer struct is API / user facing, and so carries the higher level GEM information. The inner struct is hw facing. Thus we want to name the inner struct intel_context and the outer one i915_gem_context. As the first step, we need to rename the current struct: s/struct intel_context/struct i915_gem_context/ which fits much better with its constructors already conveying the i915_gem_context prefix! Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dave Gordon <david.s.gordon@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1464098023-3294-1-git-send-email-chris@chris-wilson.co.uk
2016-05-24 13:53:34 +00:00
struct i915_gem_context *ctx;
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
struct i915_address_space *vm = NULL;
struct i915_gem_engines *e;
int err;
int i;
drm/i915: context basic create & destroy Invent an abstraction for a hw context which is passed around through the core functions. The main bit a hw context holds is the buffer object which backs the context. The rest of the members are just helper functions. Specifically the ring member, which could likely go away if we decide to never implement whatever other hw context support exists. Of note here is the introduction of the 64k alignment constraint for the BO. If contexts become heavily used, we should consider tweaking this down to 4k. Until the contexts are merged and tested a bit though, I think 64k is a nice start (based on docs). Since we don't yet switch contexts, there is really not much complexity here. Creation/destruction works pretty much as one would expect. An idr is used to generate the context id numbers which are unique per file descriptor. v2: add DRM_DEBUG_DRIVERS to distinguish ENOMEM failures (ben) convert a BUG_ON to WARN_ON, default destruction is still fatal (ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:43 +00:00
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
if (!ctx)
return ERR_PTR(-ENOMEM);
kref_init(&ctx->ref);
ctx->i915 = i915;
ctx->sched = pc->sched;
mutex_init(&ctx->mutex);
INIT_LIST_HEAD(&ctx->link);
spin_lock_init(&ctx->stale.lock);
INIT_LIST_HEAD(&ctx->stale.engines);
drm/i915: context basic create & destroy Invent an abstraction for a hw context which is passed around through the core functions. The main bit a hw context holds is the buffer object which backs the context. The rest of the members are just helper functions. Specifically the ring member, which could likely go away if we decide to never implement whatever other hw context support exists. Of note here is the introduction of the 64k alignment constraint for the BO. If contexts become heavily used, we should consider tweaking this down to 4k. Until the contexts are merged and tested a bit though, I think 64k is a nice start (based on docs). Since we don't yet switch contexts, there is really not much complexity here. Creation/destruction works pretty much as one would expect. An idr is used to generate the context id numbers which are unique per file descriptor. v2: add DRM_DEBUG_DRIVERS to distinguish ENOMEM failures (ben) convert a BUG_ON to WARN_ON, default destruction is still fatal (ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:43 +00:00
drm/i915/gem: Add an intermediate proto_context struct (v5) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. Unfortunately, both methods of setting the VM and the engine set are in active use today so we can't simply disallow setting the VM or engine set vial SET_CONTEXT_PARAM. In order to work around this wart, this commit adds a proto-context struct which contains all the context create parameters. v2 (Daniel Vetter): - Better commit message - Use __set/clear_bit instead of set/clear_bit because there's no race and we don't need the atomics v3 (Daniel Vetter): - Use manual bitops and BIT() instead of __set_bit v4 (Daniel Vetter): - Add a changelog to the commit message - Better hyperlinking in docs - Create the default PPGTT in i915_gem_create_context v5 (Daniel Vetter): - Hand-roll the initialization of UCONTEXT_PERSISTENCE Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-17-jason@jlekstrand.net
2021-07-08 15:48:21 +00:00
if (pc->vm) {
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
vm = i915_vm_get(pc->vm);
drm/i915/gem: Add an intermediate proto_context struct (v5) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. Unfortunately, both methods of setting the VM and the engine set are in active use today so we can't simply disallow setting the VM or engine set vial SET_CONTEXT_PARAM. In order to work around this wart, this commit adds a proto-context struct which contains all the context create parameters. v2 (Daniel Vetter): - Better commit message - Use __set/clear_bit instead of set/clear_bit because there's no race and we don't need the atomics v3 (Daniel Vetter): - Use manual bitops and BIT() instead of __set_bit v4 (Daniel Vetter): - Add a changelog to the commit message - Better hyperlinking in docs - Create the default PPGTT in i915_gem_create_context v5 (Daniel Vetter): - Hand-roll the initialization of UCONTEXT_PERSISTENCE Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-17-jason@jlekstrand.net
2021-07-08 15:48:21 +00:00
} else if (HAS_FULL_PPGTT(i915)) {
drm/i915: Rename i915_hw_ppgtt to i915_ppgtt Keeping the _hw_ in there does not help to distinguish it from its only brethren i915_ggtt, so drop it. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190611091238.15808-2-chris@chris-wilson.co.uk
2019-06-11 09:12:38 +00:00
struct i915_ppgtt *ppgtt;
drm/i915: Do aliasing PPGTT init with contexts We have a default context which suits the aliasing PPGTT well. Tie them together so it looks like any other context/PPGTT pair. This makes the code cleaner as it won't have to special case aliasing as often. The patch has one slightly tricky part in the default context creation function. In the future (and on aliased setup) we create a new VM for a context (potentially). However, if we have aliasing PPGTT, which occurs at this point in time for all platforms GEN6+, we can simply manage the refcounting to allow things to behave as normal. Now is a good time to recall that the aliasing_ppgtt doesn't have a real VM, it uses the GGTT drm_mm. Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-12-06 22:11:18 +00:00
drm/i915/gtt: split up i915_gem_gtt Attempt to split i915_gem_gtt.[ch] into more manageable chunks. Suggested-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Matthew Auld <matthew.auld@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> 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/20200107134009.3255354-1-chris@chris-wilson.co.uk
2020-01-07 13:40:09 +00:00
ppgtt = i915_ppgtt_create(&i915->gt);
drm/i915: Move pinning of dev_priv->kernel_context into its creator Rather than have every context ask "am I owned by the kernel? pin!", move that logic into the creator of the kernel context, in order to improve code comprehension. v2: Throw away the user_handle on failure to allocate the ppgtt. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1464098023-3294-5-git-send-email-chris@chris-wilson.co.uk
2016-05-24 13:53:38 +00:00
if (IS_ERR(ppgtt)) {
drm/i915/gem: initial conversion to new logging macros using coccinelle First pass of conversion to the new struct drm_based device logging macros in the drm/i915/gem directory. This conversion was achieved using the following coccinelle script that transforms based on the existence of a straightforward struct drm_i915_private device: @rule1@ identifier fn, T; @@ fn(struct drm_i915_private *T,...) { <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } @rule2@ identifier fn, T; @@ fn(...) { ... struct drm_i915_private *T = ...; <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } Checkpatch warnings were addressed manually. Acked-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Wambui Karuga <wambui.karugax@gmail.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122125750.9737-2-wambui.karugax@gmail.com
2020-01-22 12:57:49 +00:00
drm_dbg(&i915->drm, "PPGTT setup failed (%ld)\n",
PTR_ERR(ppgtt));
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
err = PTR_ERR(ppgtt);
goto err_ctx;
drm/i915: Only track real ppgtt for a context There's a bit a confusion since we track the global gtt, the aliasing and real ppgtt in the ctx->vm pointer. And not all callers really bother to check for the different cases and just presume that it points to a real ppgtt. Now looking closely we don't actually need ->vm to always point at an address space - the only place that cares actually has fixup code already to decide whether to look at the per-proces or the global address space. So switch to just tracking the ppgtt directly and ditch all the extraneous code. v2: Fixup the ppgtt debugfs file to not oops on a NULL ctx->ppgtt. Also drop the early exit - without aliasing ppgtt we want to dump all the ppgtts of the contexts if we have full ppgtt. v3: Actually git add the compile fix. Reviewed-by: Michel Thierry <michel.thierry@intel.com> Cc: "Thierry, Michel" <michel.thierry@intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> OTC-Jira: VIZ-3724 [danvet: Resolve conflicts with execlist patches while applying.] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-06 13:04:53 +00:00
}
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
vm = &ppgtt->vm;
}
if (vm) {
RCU_INIT_POINTER(ctx->vm, i915_vm_open(vm));
drm/i915: Only track real ppgtt for a context There's a bit a confusion since we track the global gtt, the aliasing and real ppgtt in the ctx->vm pointer. And not all callers really bother to check for the different cases and just presume that it points to a real ppgtt. Now looking closely we don't actually need ->vm to always point at an address space - the only place that cares actually has fixup code already to decide whether to look at the per-proces or the global address space. So switch to just tracking the ppgtt directly and ditch all the extraneous code. v2: Fixup the ppgtt debugfs file to not oops on a NULL ctx->ppgtt. Also drop the early exit - without aliasing ppgtt we want to dump all the ppgtts of the contexts if we have full ppgtt. v3: Actually git add the compile fix. Reviewed-by: Michel Thierry <michel.thierry@intel.com> Cc: "Thierry, Michel" <michel.thierry@intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> OTC-Jira: VIZ-3724 [danvet: Resolve conflicts with execlist patches while applying.] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-06 13:04:53 +00:00
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
/* i915_vm_open() takes a reference */
i915_vm_put(vm);
drm/i915: Only track real ppgtt for a context There's a bit a confusion since we track the global gtt, the aliasing and real ppgtt in the ctx->vm pointer. And not all callers really bother to check for the different cases and just presume that it points to a real ppgtt. Now looking closely we don't actually need ->vm to always point at an address space - the only place that cares actually has fixup code already to decide whether to look at the per-proces or the global address space. So switch to just tracking the ppgtt directly and ditch all the extraneous code. v2: Fixup the ppgtt debugfs file to not oops on a NULL ctx->ppgtt. Also drop the early exit - without aliasing ppgtt we want to dump all the ppgtts of the contexts if we have full ppgtt. v3: Actually git add the compile fix. Reviewed-by: Michel Thierry <michel.thierry@intel.com> Cc: "Thierry, Michel" <michel.thierry@intel.com> Cc: Ville Syrjälä <ville.syrjala@linux.intel.com> OTC-Jira: VIZ-3724 [danvet: Resolve conflicts with execlist patches while applying.] Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-08-06 13:04:53 +00:00
}
drm/i915: Do aliasing PPGTT init with contexts We have a default context which suits the aliasing PPGTT well. Tie them together so it looks like any other context/PPGTT pair. This makes the code cleaner as it won't have to special case aliasing as often. The patch has one slightly tricky part in the default context creation function. In the future (and on aliased setup) we create a new VM for a context (potentially). However, if we have aliasing PPGTT, which occurs at this point in time for all platforms GEN6+, we can simply manage the refcounting to allow things to behave as normal. Now is a good time to recall that the aliasing_ppgtt doesn't have a real VM, it uses the GGTT drm_mm. Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-12-06 22:11:18 +00:00
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
mutex_init(&ctx->engines_mutex);
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
if (pc->num_user_engines >= 0) {
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
i915_gem_context_set_user_engines(ctx);
e = user_engines(ctx, pc->num_user_engines, pc->user_engines);
} else {
i915_gem_context_clear_user_engines(ctx);
e = default_engines(ctx, pc->legacy_rcs_sseu);
}
if (IS_ERR(e)) {
err = PTR_ERR(e);
goto err_vm;
}
RCU_INIT_POINTER(ctx->engines, e);
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
mutex_init(&ctx->lut_mutex);
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
/* NB: Mark all slices as needing a remap so that when the context first
* loads it will restore whatever remap state already exists. If there
* is no remap info, it will be a NOP. */
ctx->remap_slice = ALL_L3_SLICES(i915);
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
ctx->user_flags = pc->user_flags;
for (i = 0; i < ARRAY_SIZE(ctx->hang_timestamp); i++)
ctx->hang_timestamp[i] = jiffies - CONTEXT_FAST_HANG_JIFFIES;
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
drm/i915/gem: Add an intermediate proto_context struct (v5) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. Unfortunately, both methods of setting the VM and the engine set are in active use today so we can't simply disallow setting the VM or engine set vial SET_CONTEXT_PARAM. In order to work around this wart, this commit adds a proto-context struct which contains all the context create parameters. v2 (Daniel Vetter): - Better commit message - Use __set/clear_bit instead of set/clear_bit because there's no race and we don't need the atomics v3 (Daniel Vetter): - Use manual bitops and BIT() instead of __set_bit v4 (Daniel Vetter): - Add a changelog to the commit message - Better hyperlinking in docs - Create the default PPGTT in i915_gem_create_context v5 (Daniel Vetter): - Hand-roll the initialization of UCONTEXT_PERSISTENCE Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-17-jason@jlekstrand.net
2021-07-08 15:48:21 +00:00
if (pc->single_timeline) {
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
err = drm_syncobj_create(&ctx->syncobj,
drm/i915: Implement SINGLE_TIMELINE with a syncobj (v4) This API is entirely unnecessary and I'd love to get rid of it. If userspace wants a single timeline across multiple contexts, they can either use implicit synchronization or a syncobj, both of which existed at the time this feature landed. The justification given at the time was that it would help GL drivers which are inherently single-timeline. However, neither of our GL drivers actually wanted the feature. i965 was already in maintenance mode at the time and iris uses syncobj for everything. Unfortunately, as much as I'd love to get rid of it, it is used by the media driver so we can't do that. We can, however, do the next-best thing which is to embed a syncobj in the context and do exactly what we'd expect from userspace internally. This isn't an entirely identical implementation because it's no longer atomic if userspace races with itself by calling execbuffer2 twice simultaneously from different threads. It won't crash in that case; it just doesn't guarantee any ordering between those two submits. It also means that sync files exported from different engines on a SINGLE_TIMELINE context will have different fence contexts. This is visible to userspace if it looks at the obj_name field of sync_fence_info. Moving SINGLE_TIMELINE to a syncobj emulation has a couple of technical advantages beyond mere annoyance. One is that intel_timeline is no longer an api-visible object and can remain entirely an implementation detail. This may be advantageous as we make scheduler changes going forward. Second is that, together with deleting the CLONE_CONTEXT API, we should now have a 1:1 mapping between intel_context and intel_timeline which may help us reduce locking. v2 (Tvrtko Ursulin): - Update the comment on i915_gem_context::syncobj to mention that it's an emulation and the possible race if userspace calls execbuffer2 twice on the same context concurrently. v2 (Jason Ekstrand): - Wrap the checks for eb.gem_context->syncobj in unlikely() - Drop the dma_fence reference - Improved commit message v3 (Jason Ekstrand): - Move the dma_fence_put() to before the error exit v4 (Tvrtko Ursulin): - Add a comment about fence contexts to the commit message Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-8-jason@jlekstrand.net
2021-07-08 15:48:12 +00:00
DRM_SYNCOBJ_CREATE_SIGNALED,
NULL);
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
if (err)
goto err_engines;
drm/i915: Allow contexts to share a single timeline across all engines Previously, our view has been always to run the engines independently within a context. (Multiple engines happened before we had contexts and timelines, so they always operated independently and that behaviour persisted into contexts.) However, at the user level the context often represents a single timeline (e.g. GL contexts) and userspace must ensure that the individual engines are serialised to present that ordering to the client (or forgot about this detail entirely and hope no one notices - a fair ploy if the client can only directly control one engine themselves ;) In the next patch, we will want to construct a set of engines that operate as one, that have a single timeline interwoven between them, to present a single virtual engine to the user. (They submit to the virtual engine, then we decide which engine to execute on based.) To that end, we want to be able to create contexts which have a single timeline (fence context) shared between all engines, rather than multiple timelines. v2: Move the specialised timeline ordering to its own function. 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/20190322092325.5883-4-chris@chris-wilson.co.uk
2019-03-22 09:23:25 +00:00
}
drm/i915: Add tracepoints to track a vm during its lifetime - ppgtt init/release: these tracepoints are useful for observing the creation and destruction of Full PPGTTs. - ctx create/free: we can use the ctx_free trace in combination with the ppgtt_release one to be sure that the ppgtt doesn't stay alive for too long after the ctx is destroyed. ctx_create is there for simmetry - switch_mm: important point in the lifetime of the vm v4: add DOC information v5: pull the DOC in drm.tmpl v6: clean ppgtt init/release traces + add ctx create/free and switch_mm tracepoints (Chris) v7: drop execlist_submit_context tracepoint Cc: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-11-10 13:44:31 +00:00
trace_i915_context_create(ctx);
drm/i915: Generalize default context setup The plan to to make every file descriptor have a default context. To accommodate this, generalize out default context setup function so it can be used at file open time. Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-12-06 22:11:05 +00:00
return ctx;
drm/i915/gem: Roll all of context creation together Now that we have the whole engine set and VM at context creation time, we can just assign those fields instead of creating first and handling the VM and engines later. This lets us avoid creating useless VMs and engine sets and lets us get rid of the complex VM setting code. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-30-jason@jlekstrand.net
2021-07-08 15:48:34 +00:00
err_engines:
free_engines(e);
err_vm:
if (ctx->vm)
i915_vm_close(ctx->vm);
err_ctx:
kfree(ctx);
return ERR_PTR(err);
drm/i915: preliminary context support Very basic code for context setup/destruction in the driver. Adds the file i915_gem_context.c This file implements HW context support. On gen5+ a HW context consists of an opaque GPU object which is referenced at times of context saves and restores. With RC6 enabled, the context is also referenced as the GPU enters and exists from RC6 (GPU has it's own internal power context, except on gen5). Though something like a context does exist for the media ring, the code only supports contexts for the render ring. In software, there is a distinction between contexts created by the user, and the default HW context. The default HW context is used by GPU clients that do not request setup of their own hardware context. The default context's state is never restored to help prevent programming errors. This would happen if a client ran and piggy-backed off another clients GPU state. The default context only exists to give the GPU some offset to load as the current to invoke a save of the context we actually care about. In fact, the code could likely be constructed, albeit in a more complicated fashion, to never use the default context, though that limits the driver's ability to swap out, and/or destroy other contexts. All other contexts are created as a request by the GPU client. These contexts store GPU state, and thus allow GPU clients to not re-emit state (and potentially query certain state) at any time. The kernel driver makes certain that the appropriate commands are inserted. There are 4 entry points into the contexts, init, fini, open, close. The names are self-explanatory except that init can be called during reset, and also during pm thaw/resume. As we expect our context to be preserved across these events, we do not reinitialize in this case. As Adam Jackson pointed out, The cutoff of 1MB where a HW context is considered too big is arbitrary. The reason for this is even though context sizes are increasing with every generation, they have yet to eclipse even 32k. If we somehow read back way more than that, it probably means BIOS has done something strange, or we're running on a platform that wasn't designed for this. v2: rename load/unload to init/fini (daniel) remove ILK support for get_size() (indirectly daniel) add HAS_HW_CONTEXTS macro to clarify supported platforms (daniel) added comments (Ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:42 +00:00
}
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
static void init_contexts(struct i915_gem_contexts *gc)
drm/i915: Introduce a preempt context Add another perma-pinned context for using for preemption at any time. We cannot just reuse the existing kernel context, as first and foremost we need to ensure that we can preempt the kernel context itself, so require a distinct context id. Similar to the kernel context, we may want to interrupt execution and switch to the preempt context at any time, and so it needs to be permanently pinned and available. To compensate for yet another permanent allocation, we shrink the existing context and the new context by reducing their ringbuffer to the minimum. v2: Assert that we never allocate a request from the preemption context. v3: Limit perma-pin to engines that may preempt. v4: Onion cleanup for early driver death v5: Onion ordering in main driver cleanup as well. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Michał Winiarski <michal.winiarski@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171003203453.15692-4-chris@chris-wilson.co.uk
2017-10-03 20:34:48 +00:00
{
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
spin_lock_init(&gc->lock);
INIT_LIST_HEAD(&gc->list);
drm/i915: Introduce a preempt context Add another perma-pinned context for using for preemption at any time. We cannot just reuse the existing kernel context, as first and foremost we need to ensure that we can preempt the kernel context itself, so require a distinct context id. Similar to the kernel context, we may want to interrupt execution and switch to the preempt context at any time, and so it needs to be permanently pinned and available. To compensate for yet another permanent allocation, we shrink the existing context and the new context by reducing their ringbuffer to the minimum. v2: Assert that we never allocate a request from the preemption context. v3: Limit perma-pin to engines that may preempt. v4: Onion cleanup for early driver death v5: Onion ordering in main driver cleanup as well. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Michał Winiarski <michal.winiarski@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171003203453.15692-4-chris@chris-wilson.co.uk
2017-10-03 20:34:48 +00:00
}
drm/i915: Remove i915->kernel_context Allocate only an internal intel_context for the kernel_context, forgoing a global GEM context for internal use as we only require a separate address space (for our own protection). Now having weaned GT from requiring ce->gem_context, we can stop referencing it entirely. This also means we no longer have to create random and unnecessary GEM contexts for internal use. GEM contexts are now entirely for tracking GEM clients, and intel_context the execution environment on the GPU. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Acked-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191221160324.1073045-1-chris@chris-wilson.co.uk
2019-12-21 16:03:24 +00:00
void i915_gem_init__contexts(struct drm_i915_private *i915)
drm/i915: preliminary context support Very basic code for context setup/destruction in the driver. Adds the file i915_gem_context.c This file implements HW context support. On gen5+ a HW context consists of an opaque GPU object which is referenced at times of context saves and restores. With RC6 enabled, the context is also referenced as the GPU enters and exists from RC6 (GPU has it's own internal power context, except on gen5). Though something like a context does exist for the media ring, the code only supports contexts for the render ring. In software, there is a distinction between contexts created by the user, and the default HW context. The default HW context is used by GPU clients that do not request setup of their own hardware context. The default context's state is never restored to help prevent programming errors. This would happen if a client ran and piggy-backed off another clients GPU state. The default context only exists to give the GPU some offset to load as the current to invoke a save of the context we actually care about. In fact, the code could likely be constructed, albeit in a more complicated fashion, to never use the default context, though that limits the driver's ability to swap out, and/or destroy other contexts. All other contexts are created as a request by the GPU client. These contexts store GPU state, and thus allow GPU clients to not re-emit state (and potentially query certain state) at any time. The kernel driver makes certain that the appropriate commands are inserted. There are 4 entry points into the contexts, init, fini, open, close. The names are self-explanatory except that init can be called during reset, and also during pm thaw/resume. As we expect our context to be preserved across these events, we do not reinitialize in this case. As Adam Jackson pointed out, The cutoff of 1MB where a HW context is considered too big is arbitrary. The reason for this is even though context sizes are increasing with every generation, they have yet to eclipse even 32k. If we somehow read back way more than that, it probably means BIOS has done something strange, or we're running on a platform that wasn't designed for this. v2: rename load/unload to init/fini (daniel) remove ILK support for get_size() (indirectly daniel) add HAS_HW_CONTEXTS macro to clarify supported platforms (daniel) added comments (Ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:42 +00:00
{
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
init_contexts(&i915->gem.contexts);
drm/i915: preliminary context support Very basic code for context setup/destruction in the driver. Adds the file i915_gem_context.c This file implements HW context support. On gen5+ a HW context consists of an opaque GPU object which is referenced at times of context saves and restores. With RC6 enabled, the context is also referenced as the GPU enters and exists from RC6 (GPU has it's own internal power context, except on gen5). Though something like a context does exist for the media ring, the code only supports contexts for the render ring. In software, there is a distinction between contexts created by the user, and the default HW context. The default HW context is used by GPU clients that do not request setup of their own hardware context. The default context's state is never restored to help prevent programming errors. This would happen if a client ran and piggy-backed off another clients GPU state. The default context only exists to give the GPU some offset to load as the current to invoke a save of the context we actually care about. In fact, the code could likely be constructed, albeit in a more complicated fashion, to never use the default context, though that limits the driver's ability to swap out, and/or destroy other contexts. All other contexts are created as a request by the GPU client. These contexts store GPU state, and thus allow GPU clients to not re-emit state (and potentially query certain state) at any time. The kernel driver makes certain that the appropriate commands are inserted. There are 4 entry points into the contexts, init, fini, open, close. The names are self-explanatory except that init can be called during reset, and also during pm thaw/resume. As we expect our context to be preserved across these events, we do not reinitialize in this case. As Adam Jackson pointed out, The cutoff of 1MB where a HW context is considered too big is arbitrary. The reason for this is even though context sizes are increasing with every generation, they have yet to eclipse even 32k. If we somehow read back way more than that, it probably means BIOS has done something strange, or we're running on a platform that wasn't designed for this. v2: rename load/unload to init/fini (daniel) remove ILK support for get_size() (indirectly daniel) add HAS_HW_CONTEXTS macro to clarify supported platforms (daniel) added comments (Ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:42 +00:00
}
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
static void gem_context_register(struct i915_gem_context *ctx,
struct drm_i915_file_private *fpriv,
u32 id)
drm/i915: Separate GEM context construction and registration to userspace In later patches, it became apparent that userspace can see a partially constructed GEM context and begin using it before it was ready, to much hilarity. Close this window of opportunity by lifting the registration of the context with userspace (the insertion of the context into the filp's idr) to the very end of the CONTEXT_CREATE ioctl. 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/20190321140711.11190-1-chris@chris-wilson.co.uk
2019-03-21 14:07:08 +00:00
{
drm/i915/gem: Delay tracking the GEM context until it is registered Avoid exposing a partially constructed context by deferring the list_add() from the initial construction to the end of registration. Otherwise, if we peek into the list of contexts from inside debugfs, we may see the partially constructed context and chase down some dangling incomplete pointers. Reported-by: CQ Tang <cq.tang@intel.com> Fixes: 3aa9945a528e ("drm/i915: Separate GEM context construction and registration to userspace") References: f6e8aa387171 ("drm/i915: Report the number of closed vma held by each context in debugfs") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: CQ Tang <cq.tang@intel.com> Cc: <stable@vger.kernel.org> # v5.2+ Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200730092856.23615-1-chris@chris-wilson.co.uk Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
2020-07-30 09:28:56 +00:00
struct drm_i915_private *i915 = ctx->i915;
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
void *old;
drm/i915: Separate GEM context construction and registration to userspace In later patches, it became apparent that userspace can see a partially constructed GEM context and begin using it before it was ready, to much hilarity. Close this window of opportunity by lifting the registration of the context with userspace (the insertion of the context into the filp's idr) to the very end of the CONTEXT_CREATE ioctl. 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/20190321140711.11190-1-chris@chris-wilson.co.uk
2019-03-21 14:07:08 +00:00
ctx->file_priv = fpriv;
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
drm/i915: Separate GEM context construction and registration to userspace In later patches, it became apparent that userspace can see a partially constructed GEM context and begin using it before it was ready, to much hilarity. Close this window of opportunity by lifting the registration of the context with userspace (the insertion of the context into the filp's idr) to the very end of the CONTEXT_CREATE ioctl. 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/20190321140711.11190-1-chris@chris-wilson.co.uk
2019-03-21 14:07:08 +00:00
ctx->pid = get_task_pid(current, PIDTYPE_PID);
drm/i915/gem: Embed context/timeline name inside the GEM context Use a small char buffer inside the i915_gem_context to store the user friendly name so that ctx->name has the same lifetime as the RCU protected GEM context. That is, e.g. when using print_request() that prints the timeline name (ctx->name), the name will not be prematurely freed upon the context being closed and the last reference dropped. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Matthew Auld <matthew.auld@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191111114323.5833-2-chris@chris-wilson.co.uk
2019-11-11 11:43:20 +00:00
snprintf(ctx->name, sizeof(ctx->name), "%s[%d]",
current->comm, pid_nr(ctx->pid));
drm/i915: Separate GEM context construction and registration to userspace In later patches, it became apparent that userspace can see a partially constructed GEM context and begin using it before it was ready, to much hilarity. Close this window of opportunity by lifting the registration of the context with userspace (the insertion of the context into the filp's idr) to the very end of the CONTEXT_CREATE ioctl. 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/20190321140711.11190-1-chris@chris-wilson.co.uk
2019-03-21 14:07:08 +00:00
/* And finally expose ourselves to userspace via the idr */
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
old = xa_store(&fpriv->context_xa, id, ctx, GFP_KERNEL);
WARN_ON(old);
drm/i915/gem: Delay tracking the GEM context until it is registered Avoid exposing a partially constructed context by deferring the list_add() from the initial construction to the end of registration. Otherwise, if we peek into the list of contexts from inside debugfs, we may see the partially constructed context and chase down some dangling incomplete pointers. Reported-by: CQ Tang <cq.tang@intel.com> Fixes: 3aa9945a528e ("drm/i915: Separate GEM context construction and registration to userspace") References: f6e8aa387171 ("drm/i915: Report the number of closed vma held by each context in debugfs") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: CQ Tang <cq.tang@intel.com> Cc: <stable@vger.kernel.org> # v5.2+ Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200730092856.23615-1-chris@chris-wilson.co.uk Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
2020-07-30 09:28:56 +00:00
spin_lock(&i915->gem.contexts.lock);
list_add_tail(&ctx->link, &i915->gem.contexts.list);
spin_unlock(&i915->gem.contexts.lock);
drm/i915: Separate GEM context construction and registration to userspace In later patches, it became apparent that userspace can see a partially constructed GEM context and begin using it before it was ready, to much hilarity. Close this window of opportunity by lifting the registration of the context with userspace (the insertion of the context into the filp's idr) to the very end of the CONTEXT_CREATE ioctl. 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/20190321140711.11190-1-chris@chris-wilson.co.uk
2019-03-21 14:07:08 +00:00
}
drm/i915: Group all the global context information together Create a substruct to hold all the global context state under drm_i915_private. 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/20170620110547.15947-1-chris@chris-wilson.co.uk
2017-06-20 11:05:45 +00:00
int i915_gem_context_open(struct drm_i915_private *i915,
struct drm_file *file)
drm/i915: Add a context open function We'll be doing a bit more stuff with each file, so having our own open function should make things clean. This also allows us to easily add conditionals for stuff we don't want to do when we don't have HW contexts. Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-12-06 22:10:58 +00:00
{
struct drm_i915_file_private *file_priv = file->driver_priv;
drm/i915/gem: Add an intermediate proto_context struct (v5) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. Unfortunately, both methods of setting the VM and the engine set are in active use today so we can't simply disallow setting the VM or engine set vial SET_CONTEXT_PARAM. In order to work around this wart, this commit adds a proto-context struct which contains all the context create parameters. v2 (Daniel Vetter): - Better commit message - Use __set/clear_bit instead of set/clear_bit because there's no race and we don't need the atomics v3 (Daniel Vetter): - Use manual bitops and BIT() instead of __set_bit v4 (Daniel Vetter): - Add a changelog to the commit message - Better hyperlinking in docs - Create the default PPGTT in i915_gem_create_context v5 (Daniel Vetter): - Hand-roll the initialization of UCONTEXT_PERSISTENCE Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-17-jason@jlekstrand.net
2021-07-08 15:48:21 +00:00
struct i915_gem_proto_context *pc;
drm/i915: Rename struct intel_context Our goal is to rename the anonymous per-engine struct beneath the current intel_context. However, after a lively debate resolving around the confusion between intel_context_engine and intel_engine_context, the realisation is that the two structs target different users. The outer struct is API / user facing, and so carries the higher level GEM information. The inner struct is hw facing. Thus we want to name the inner struct intel_context and the outer one i915_gem_context. As the first step, we need to rename the current struct: s/struct intel_context/struct i915_gem_context/ which fits much better with its constructors already conveying the i915_gem_context prefix! Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dave Gordon <david.s.gordon@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1464098023-3294-1-git-send-email-chris@chris-wilson.co.uk
2016-05-24 13:53:34 +00:00
struct i915_gem_context *ctx;
drm/i915: Separate GEM context construction and registration to userspace In later patches, it became apparent that userspace can see a partially constructed GEM context and begin using it before it was ready, to much hilarity. Close this window of opportunity by lifting the registration of the context with userspace (the insertion of the context into the filp's idr) to the very end of the CONTEXT_CREATE ioctl. 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/20190321140711.11190-1-chris@chris-wilson.co.uk
2019-03-21 14:07:08 +00:00
int err;
drm/i915: Add a context open function We'll be doing a bit more stuff with each file, so having our own open function should make things clean. This also allows us to easily add conditionals for stuff we don't want to do when we don't have HW contexts. Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-12-06 22:10:58 +00:00
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
mutex_init(&file_priv->proto_context_lock);
xa_init_flags(&file_priv->proto_context_xa, XA_FLAGS_ALLOC);
/* 0 reserved for the default context */
xa_init_flags(&file_priv->context_xa, XA_FLAGS_ALLOC1);
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
drm/i915/gem: Convert vm idr to xarray Replace the vm_idr + vm_idr_mutex to an XArray. The XArray data structure is now used to implement IDRs, and provides its own locking. We can simply remove the IDR wrapper and in the process also remove our extra mutex. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122161531.508903-1-chris@chris-wilson.co.uk
2020-01-22 16:15:31 +00:00
/* 0 reserved for invalid/unassigned ppgtt */
xa_init_flags(&file_priv->vm_xa, XA_FLAGS_ALLOC1);
drm/i915: Add a context open function We'll be doing a bit more stuff with each file, so having our own open function should make things clean. This also allows us to easily add conditionals for stuff we don't want to do when we don't have HW contexts. Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-12-06 22:10:58 +00:00
drm/i915/gem: Add an intermediate proto_context struct (v5) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. Unfortunately, both methods of setting the VM and the engine set are in active use today so we can't simply disallow setting the VM or engine set vial SET_CONTEXT_PARAM. In order to work around this wart, this commit adds a proto-context struct which contains all the context create parameters. v2 (Daniel Vetter): - Better commit message - Use __set/clear_bit instead of set/clear_bit because there's no race and we don't need the atomics v3 (Daniel Vetter): - Use manual bitops and BIT() instead of __set_bit v4 (Daniel Vetter): - Add a changelog to the commit message - Better hyperlinking in docs - Create the default PPGTT in i915_gem_create_context v5 (Daniel Vetter): - Hand-roll the initialization of UCONTEXT_PERSISTENCE Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-17-jason@jlekstrand.net
2021-07-08 15:48:21 +00:00
pc = proto_context_create(i915, 0);
if (IS_ERR(pc)) {
err = PTR_ERR(pc);
goto err;
}
ctx = i915_gem_create_context(i915, pc);
proto_context_close(pc);
drm/i915: Kill private_default_ctx off It's barely alive now anyway, so give it the "coup de grâce". Signed-off-by: Oscar Mateo <oscar.mateo@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-05-22 13:13:38 +00:00
if (IS_ERR(ctx)) {
drm/i915: Separate GEM context construction and registration to userspace In later patches, it became apparent that userspace can see a partially constructed GEM context and begin using it before it was ready, to much hilarity. Close this window of opportunity by lifting the registration of the context with userspace (the insertion of the context into the filp's idr) to the very end of the CONTEXT_CREATE ioctl. 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/20190321140711.11190-1-chris@chris-wilson.co.uk
2019-03-21 14:07:08 +00:00
err = PTR_ERR(ctx);
goto err;
drm/i915: Create a per file_priv default context Every file will get it's own context, and we use this context instead of the default context. The default context still exists for future shrinker usage as well as reset handling. v2: Updated to address Mika's recent context guilty changes Some more changes around this come up in later patches as well. v3: Use a fake context to avoid allocation for the !HAS_HW_CONTEXT case. I've tried the alternatives. This looks the best to me. Removed hangstat stuff from v2 - for a separate patch Demote failed PPGTT set to DRM_DEBUG_DRIVER since it can now be invoked easily from userspace. Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-12-06 22:11:19 +00:00
}
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
gem_context_register(ctx, file_priv, 0);
drm/i915: Separate GEM context construction and registration to userspace In later patches, it became apparent that userspace can see a partially constructed GEM context and begin using it before it was ready, to much hilarity. Close this window of opportunity by lifting the registration of the context with userspace (the insertion of the context into the filp's idr) to the very end of the CONTEXT_CREATE ioctl. 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/20190321140711.11190-1-chris@chris-wilson.co.uk
2019-03-21 14:07:08 +00:00
drm/i915: Add a context open function We'll be doing a bit more stuff with each file, so having our own open function should make things clean. This also allows us to easily add conditionals for stuff we don't want to do when we don't have HW contexts. Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-12-06 22:10:58 +00:00
return 0;
drm/i915: Separate GEM context construction and registration to userspace In later patches, it became apparent that userspace can see a partially constructed GEM context and begin using it before it was ready, to much hilarity. Close this window of opportunity by lifting the registration of the context with userspace (the insertion of the context into the filp's idr) to the very end of the CONTEXT_CREATE ioctl. 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/20190321140711.11190-1-chris@chris-wilson.co.uk
2019-03-21 14:07:08 +00:00
drm/i915: Introduce a mutex for file_priv->context_idr Define a mutex for the exclusive use of interacting with the per-file context-idr, that was previously guarded by struct_mutex. This allows us to reduce the coverage of struct_mutex, with a view to removing the last bits coordinating GEM context later. (In the short term, we avoid taking struct_mutex while using the extended constructor functions, preventing some nasty recursion.) v2: s/context_lock/context_idr_lock/ 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/20190321140711.11190-2-chris@chris-wilson.co.uk
2019-03-21 14:07:09 +00:00
err:
drm/i915/gem: Convert vm idr to xarray Replace the vm_idr + vm_idr_mutex to an XArray. The XArray data structure is now used to implement IDRs, and provides its own locking. We can simply remove the IDR wrapper and in the process also remove our extra mutex. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122161531.508903-1-chris@chris-wilson.co.uk
2020-01-22 16:15:31 +00:00
xa_destroy(&file_priv->vm_xa);
drm/i915: Switch context id allocation directly to xarray IDR internally uses xarray so we can use it directly which simplifies our code by removing the need to do external locking. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@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/20191224095920.2386297-1-chris@chris-wilson.co.uk
2019-12-24 09:59:20 +00:00
xa_destroy(&file_priv->context_xa);
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
xa_destroy(&file_priv->proto_context_xa);
mutex_destroy(&file_priv->proto_context_lock);
drm/i915: Report the correct errno from i915_gem_context_open() Fixup the errno as we adjusted the error path to receive the errno and not compute it itself from ERR_PTR(ctx) anymore. drivers/gpu/drm/i915/i915_gem_context.c:793 i915_gem_context_open() warn: passing a valid pointer to 'PTR_ERR' Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Fixes: 3aa9945a528e ("drm/i915: Separate GEM context construction and registration to userspace") 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/20190325090413.19906-2-chris@chris-wilson.co.uk
2019-03-25 09:03:52 +00:00
return err;
drm/i915: Add a context open function We'll be doing a bit more stuff with each file, so having our own open function should make things clean. This also allows us to easily add conditionals for stuff we don't want to do when we don't have HW contexts. Signed-off-by: Ben Widawsky <ben@bwidawsk.net> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2013-12-06 22:10:58 +00:00
}
drm/i915: Group all the global context information together Create a substruct to hold all the global context state under drm_i915_private. 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/20170620110547.15947-1-chris@chris-wilson.co.uk
2017-06-20 11:05:45 +00:00
void i915_gem_context_close(struct drm_file *file)
drm/i915: preliminary context support Very basic code for context setup/destruction in the driver. Adds the file i915_gem_context.c This file implements HW context support. On gen5+ a HW context consists of an opaque GPU object which is referenced at times of context saves and restores. With RC6 enabled, the context is also referenced as the GPU enters and exists from RC6 (GPU has it's own internal power context, except on gen5). Though something like a context does exist for the media ring, the code only supports contexts for the render ring. In software, there is a distinction between contexts created by the user, and the default HW context. The default HW context is used by GPU clients that do not request setup of their own hardware context. The default context's state is never restored to help prevent programming errors. This would happen if a client ran and piggy-backed off another clients GPU state. The default context only exists to give the GPU some offset to load as the current to invoke a save of the context we actually care about. In fact, the code could likely be constructed, albeit in a more complicated fashion, to never use the default context, though that limits the driver's ability to swap out, and/or destroy other contexts. All other contexts are created as a request by the GPU client. These contexts store GPU state, and thus allow GPU clients to not re-emit state (and potentially query certain state) at any time. The kernel driver makes certain that the appropriate commands are inserted. There are 4 entry points into the contexts, init, fini, open, close. The names are self-explanatory except that init can be called during reset, and also during pm thaw/resume. As we expect our context to be preserved across these events, we do not reinitialize in this case. As Adam Jackson pointed out, The cutoff of 1MB where a HW context is considered too big is arbitrary. The reason for this is even though context sizes are increasing with every generation, they have yet to eclipse even 32k. If we somehow read back way more than that, it probably means BIOS has done something strange, or we're running on a platform that wasn't designed for this. v2: rename load/unload to init/fini (daniel) remove ILK support for get_size() (indirectly daniel) add HAS_HW_CONTEXTS macro to clarify supported platforms (daniel) added comments (Ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:42 +00:00
{
drm/i915: context basic create & destroy Invent an abstraction for a hw context which is passed around through the core functions. The main bit a hw context holds is the buffer object which backs the context. The rest of the members are just helper functions. Specifically the ring member, which could likely go away if we decide to never implement whatever other hw context support exists. Of note here is the introduction of the 64k alignment constraint for the BO. If contexts become heavily used, we should consider tweaking this down to 4k. Until the contexts are merged and tested a bit though, I think 64k is a nice start (based on docs). Since we don't yet switch contexts, there is really not much complexity here. Creation/destruction works pretty much as one would expect. An idr is used to generate the context id numbers which are unique per file descriptor. v2: add DRM_DEBUG_DRIVERS to distinguish ENOMEM failures (ben) convert a BUG_ON to WARN_ON, default destruction is still fatal (ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:43 +00:00
struct drm_i915_file_private *file_priv = file->driver_priv;
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
struct i915_gem_proto_context *pc;
drm/i915/gem: Convert vm idr to xarray Replace the vm_idr + vm_idr_mutex to an XArray. The XArray data structure is now used to implement IDRs, and provides its own locking. We can simply remove the IDR wrapper and in the process also remove our extra mutex. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122161531.508903-1-chris@chris-wilson.co.uk
2020-01-22 16:15:31 +00:00
struct i915_address_space *vm;
drm/i915: Switch context id allocation directly to xarray IDR internally uses xarray so we can use it directly which simplifies our code by removing the need to do external locking. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@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/20191224095920.2386297-1-chris@chris-wilson.co.uk
2019-12-24 09:59:20 +00:00
struct i915_gem_context *ctx;
unsigned long idx;
drm/i915: preliminary context support Very basic code for context setup/destruction in the driver. Adds the file i915_gem_context.c This file implements HW context support. On gen5+ a HW context consists of an opaque GPU object which is referenced at times of context saves and restores. With RC6 enabled, the context is also referenced as the GPU enters and exists from RC6 (GPU has it's own internal power context, except on gen5). Though something like a context does exist for the media ring, the code only supports contexts for the render ring. In software, there is a distinction between contexts created by the user, and the default HW context. The default HW context is used by GPU clients that do not request setup of their own hardware context. The default context's state is never restored to help prevent programming errors. This would happen if a client ran and piggy-backed off another clients GPU state. The default context only exists to give the GPU some offset to load as the current to invoke a save of the context we actually care about. In fact, the code could likely be constructed, albeit in a more complicated fashion, to never use the default context, though that limits the driver's ability to swap out, and/or destroy other contexts. All other contexts are created as a request by the GPU client. These contexts store GPU state, and thus allow GPU clients to not re-emit state (and potentially query certain state) at any time. The kernel driver makes certain that the appropriate commands are inserted. There are 4 entry points into the contexts, init, fini, open, close. The names are self-explanatory except that init can be called during reset, and also during pm thaw/resume. As we expect our context to be preserved across these events, we do not reinitialize in this case. As Adam Jackson pointed out, The cutoff of 1MB where a HW context is considered too big is arbitrary. The reason for this is even though context sizes are increasing with every generation, they have yet to eclipse even 32k. If we somehow read back way more than that, it probably means BIOS has done something strange, or we're running on a platform that wasn't designed for this. v2: rename load/unload to init/fini (daniel) remove ILK support for get_size() (indirectly daniel) add HAS_HW_CONTEXTS macro to clarify supported platforms (daniel) added comments (Ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:42 +00:00
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
xa_for_each(&file_priv->proto_context_xa, idx, pc)
proto_context_close(pc);
xa_destroy(&file_priv->proto_context_xa);
mutex_destroy(&file_priv->proto_context_lock);
drm/i915: Switch context id allocation directly to xarray IDR internally uses xarray so we can use it directly which simplifies our code by removing the need to do external locking. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@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/20191224095920.2386297-1-chris@chris-wilson.co.uk
2019-12-24 09:59:20 +00:00
xa_for_each(&file_priv->context_xa, idx, ctx)
context_close(ctx);
xa_destroy(&file_priv->context_xa);
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
drm/i915/gem: Convert vm idr to xarray Replace the vm_idr + vm_idr_mutex to an XArray. The XArray data structure is now used to implement IDRs, and provides its own locking. We can simply remove the IDR wrapper and in the process also remove our extra mutex. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122161531.508903-1-chris@chris-wilson.co.uk
2020-01-22 16:15:31 +00:00
xa_for_each(&file_priv->vm_xa, idx, vm)
i915_vm_put(vm);
xa_destroy(&file_priv->vm_xa);
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
}
int i915_gem_vm_create_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct drm_i915_private *i915 = to_i915(dev);
struct drm_i915_gem_vm_control *args = data;
struct drm_i915_file_private *file_priv = file->driver_priv;
drm/i915: Rename i915_hw_ppgtt to i915_ppgtt Keeping the _hw_ in there does not help to distinguish it from its only brethren i915_ggtt, so drop it. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190611091238.15808-2-chris@chris-wilson.co.uk
2019-06-11 09:12:38 +00:00
struct i915_ppgtt *ppgtt;
drm/i915/gem: Convert vm idr to xarray Replace the vm_idr + vm_idr_mutex to an XArray. The XArray data structure is now used to implement IDRs, and provides its own locking. We can simply remove the IDR wrapper and in the process also remove our extra mutex. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122161531.508903-1-chris@chris-wilson.co.uk
2020-01-22 16:15:31 +00:00
u32 id;
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
int err;
if (!HAS_FULL_PPGTT(i915))
return -ENODEV;
if (args->flags)
return -EINVAL;
drm/i915/gtt: split up i915_gem_gtt Attempt to split i915_gem_gtt.[ch] into more manageable chunks. Suggested-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Matthew Auld <matthew.auld@intel.com> Cc: Chris Wilson <chris@chris-wilson.co.uk> 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/20200107134009.3255354-1-chris@chris-wilson.co.uk
2020-01-07 13:40:09 +00:00
ppgtt = i915_ppgtt_create(&i915->gt);
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
if (IS_ERR(ppgtt))
return PTR_ERR(ppgtt);
if (args->extensions) {
err = i915_user_extensions(u64_to_user_ptr(args->extensions),
NULL, 0,
ppgtt);
if (err)
goto err_put;
}
drm/i915/gem: Convert vm idr to xarray Replace the vm_idr + vm_idr_mutex to an XArray. The XArray data structure is now used to implement IDRs, and provides its own locking. We can simply remove the IDR wrapper and in the process also remove our extra mutex. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122161531.508903-1-chris@chris-wilson.co.uk
2020-01-22 16:15:31 +00:00
err = xa_alloc(&file_priv->vm_xa, &id, &ppgtt->vm,
xa_limit_32b, GFP_KERNEL);
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
if (err)
goto err_put;
drm/i915/gem: Convert vm idr to xarray Replace the vm_idr + vm_idr_mutex to an XArray. The XArray data structure is now used to implement IDRs, and provides its own locking. We can simply remove the IDR wrapper and in the process also remove our extra mutex. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122161531.508903-1-chris@chris-wilson.co.uk
2020-01-22 16:15:31 +00:00
GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */
args->vm_id = id;
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
return 0;
err_put:
drm/i915: Pull kref into i915_address_space Make the kref common to both derived structs (i915_ggtt and i915_ppgtt) so that we can safely reference count an abstract ctx->vm address space. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190611091238.15808-1-chris@chris-wilson.co.uk
2019-06-11 09:12:37 +00:00
i915_vm_put(&ppgtt->vm);
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
return err;
}
int i915_gem_vm_destroy_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct drm_i915_file_private *file_priv = file->driver_priv;
struct drm_i915_gem_vm_control *args = data;
drm/i915: Pull kref into i915_address_space Make the kref common to both derived structs (i915_ggtt and i915_ppgtt) so that we can safely reference count an abstract ctx->vm address space. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190611091238.15808-1-chris@chris-wilson.co.uk
2019-06-11 09:12:37 +00:00
struct i915_address_space *vm;
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
if (args->flags)
return -EINVAL;
if (args->extensions)
return -EINVAL;
drm/i915/gem: Convert vm idr to xarray Replace the vm_idr + vm_idr_mutex to an XArray. The XArray data structure is now used to implement IDRs, and provides its own locking. We can simply remove the IDR wrapper and in the process also remove our extra mutex. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122161531.508903-1-chris@chris-wilson.co.uk
2020-01-22 16:15:31 +00:00
vm = xa_erase(&file_priv->vm_xa, args->vm_id);
drm/i915: Pull kref into i915_address_space Make the kref common to both derived structs (i915_ggtt and i915_ppgtt) so that we can safely reference count an abstract ctx->vm address space. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190611091238.15808-1-chris@chris-wilson.co.uk
2019-06-11 09:12:37 +00:00
if (!vm)
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
return -ENOENT;
drm/i915: Pull kref into i915_address_space Make the kref common to both derived structs (i915_ggtt and i915_ppgtt) so that we can safely reference count an abstract ctx->vm address space. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190611091238.15808-1-chris@chris-wilson.co.uk
2019-06-11 09:12:37 +00:00
i915_vm_put(vm);
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
return 0;
drm/i915: context basic create & destroy Invent an abstraction for a hw context which is passed around through the core functions. The main bit a hw context holds is the buffer object which backs the context. The rest of the members are just helper functions. Specifically the ring member, which could likely go away if we decide to never implement whatever other hw context support exists. Of note here is the introduction of the 64k alignment constraint for the BO. If contexts become heavily used, we should consider tweaking this down to 4k. Until the contexts are merged and tested a bit though, I think 64k is a nice start (based on docs). Since we don't yet switch contexts, there is really not much complexity here. Creation/destruction works pretty much as one would expect. An idr is used to generate the context id numbers which are unique per file descriptor. v2: add DRM_DEBUG_DRIVERS to distinguish ENOMEM failures (ben) convert a BUG_ON to WARN_ON, default destruction is still fatal (ben) Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
2012-06-04 21:42:43 +00:00
}
drm/i915: Avoid using ctx->file_priv during construction As we only set ctx->file_priv on registering the GEM context after construction, it is invalid to try and use it in the middle for setting various parameters. Indeed, we put the file_priv into struct create_ext so that we have the right file_private available without having to look at ctx->file_priv. However, it helps to use it! Reported-by: Jordan Justen <jordan.l.justen@intel.com> Fixes: b91715417244 ("drm/i915: Extend CONTEXT_CREATE to set parameters upon construction") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Jordan Justen <jordan.l.justen@intel.com> Reviewed-by: Jordan Justen <jordan.l.justen@intel.com> Tested-by: Jordan Justen <jordan.l.justen@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190330100349.30642-1-chris@chris-wilson.co.uk
2019-03-30 10:03:49 +00:00
static int get_ppgtt(struct drm_i915_file_private *file_priv,
struct i915_gem_context *ctx,
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
struct drm_i915_gem_context_param *args)
{
drm/i915: Pull kref into i915_address_space Make the kref common to both derived structs (i915_ggtt and i915_ppgtt) so that we can safely reference count an abstract ctx->vm address space. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190611091238.15808-1-chris@chris-wilson.co.uk
2019-06-11 09:12:37 +00:00
struct i915_address_space *vm;
drm/i915/gem: Convert vm idr to xarray Replace the vm_idr + vm_idr_mutex to an XArray. The XArray data structure is now used to implement IDRs, and provides its own locking. We can simply remove the IDR wrapper and in the process also remove our extra mutex. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122161531.508903-1-chris@chris-wilson.co.uk
2020-01-22 16:15:31 +00:00
int err;
u32 id;
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
if (!rcu_access_pointer(ctx->vm))
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
return -ENODEV;
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
rcu_read_lock();
drm/i915/gem: Safely acquire the ctx->vm when copying As we read the ctx->vm unlocked before cloning/exporting, we should validate our reference is correct before returning it. We already do for clone_vm() but were not so strict around get_ppgtt(). Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191106091312.12921-1-chris@chris-wilson.co.uk
2019-11-06 09:13:12 +00:00
vm = context_get_vm_rcu(ctx);
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
rcu_read_unlock();
drm/i915/gem: Prevent NULL pointer dereference on missing ctx->vm If the ctx->vm is freed before we can acquire a local reference to it, we proceed to call i915_vm_put(NULL), which is invalid. Reported-by: Colin Ian King <colin.king@canonical.com> Fixes: 5dbd2b7be61e ("drm/i915/gem: Convert vm idr to xarray") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Colin Ian King <colin.king@canonical.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200123152602.1432282-1-chris@chris-wilson.co.uk
2020-01-23 15:26:02 +00:00
if (!vm)
return -ENODEV;
err = xa_alloc(&file_priv->vm_xa, &id, vm, xa_limit_32b, GFP_KERNEL);
drm/i915/gem: Convert vm idr to xarray Replace the vm_idr + vm_idr_mutex to an XArray. The XArray data structure is now used to implement IDRs, and provides its own locking. We can simply remove the IDR wrapper and in the process also remove our extra mutex. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122161531.508903-1-chris@chris-wilson.co.uk
2020-01-22 16:15:31 +00:00
if (err)
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
goto err_put;
drm/i915: Pull i915_vma_pin under the vm->mutex Replace the struct_mutex requirement for pinning the i915_vma with the local vm->mutex instead. Note that the vm->mutex is tainted by the shrinker (we require unbinding from inside fs-reclaim) and so we cannot allocate while holding that mutex. Instead we have to preallocate workers to do allocate and apply the PTE updates after we have we reserved their slot in the drm_mm (using fences to order the PTE writes with the GPU work and with later unbind). In adding the asynchronous vma binding, one subtle requirement is to avoid coupling the binding fence into the backing object->resv. That is the asynchronous binding only applies to the vma timeline itself and not to the pages as that is a more global timeline (the binding of one vma does not need to be ordered with another vma, nor does the implicit GEM fencing depend on a vma, only on writes to the backing store). Keeping the vma binding distinct from the backing store timelines is verified by a number of async gem_exec_fence and gem_exec_schedule tests. The way we do this is quite simple, we keep the fence for the vma binding separate and only wait on it as required, and never add it to the obj->resv itself. Another consequence in reducing the locking around the vma is the destruction of the vma is no longer globally serialised by struct_mutex. A natural solution would be to add a kref to i915_vma, but that requires decoupling the reference cycles, possibly by introducing a new i915_mm_pages object that is own by both obj->mm and vma->pages. However, we have not taken that route due to the overshadowing lmem/ttm discussions, and instead play a series of complicated games with trylocks to (hopefully) ensure that only one destruction path is called! v2: Add some commentary, and some helpers to reduce patch churn. 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/20191004134015.13204-4-chris@chris-wilson.co.uk
2019-10-04 13:39:58 +00:00
i915_vm_open(vm);
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
drm/i915/gem: Convert vm idr to xarray Replace the vm_idr + vm_idr_mutex to an XArray. The XArray data structure is now used to implement IDRs, and provides its own locking. We can simply remove the IDR wrapper and in the process also remove our extra mutex. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122161531.508903-1-chris@chris-wilson.co.uk
2020-01-22 16:15:31 +00:00
GEM_BUG_ON(id == 0); /* reserved for invalid/unassigned ppgtt */
args->value = id;
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
args->size = 0;
err_put:
drm/i915: Pull kref into i915_address_space Make the kref common to both derived structs (i915_ggtt and i915_ppgtt) so that we can safely reference count an abstract ctx->vm address space. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190611091238.15808-1-chris@chris-wilson.co.uk
2019-06-11 09:12:37 +00:00
i915_vm_put(vm);
drm/i915/gem: Convert vm idr to xarray Replace the vm_idr + vm_idr_mutex to an XArray. The XArray data structure is now used to implement IDRs, and provides its own locking. We can simply remove the IDR wrapper and in the process also remove our extra mutex. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Michael J. Ruhl <michael.j.ruhl@intel.com> Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122161531.508903-1-chris@chris-wilson.co.uk
2020-01-22 16:15:31 +00:00
return err;
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
}
drm/i915/perf: introduce global sseu pinning On Gen11 powergating half the execution units is a functional requirement when using the VME samplers. Not fullfilling this requirement can lead to hangs. This unfortunately plays fairly poorly with the NOA requirements. NOA requires a stable power configuration to maintain its configuration. As a result using OA (and NOA feeding into it) so far has required us to use a power configuration that can work for all contexts. The only power configuration fullfilling this is powergating half the execution units. This makes performance analysis for 3D workloads somewhat pointless. Failing to find a solution that would work for everybody, this change introduces a new i915-perf stream open parameter that punts the decision off to userspace. If this parameter is omitted, the existing Gen11 behavior remains (half EU array powergating). This change takes the initiative to move all perf related sseu configuration into i915_perf.c v2: Make parameter priviliged if different from default v3: Fix context modifying its sseu config while i915-perf is enabled v4: Always consider global sseu a privileged operation (Tvrtko) Override req_sseu point in intel_sseu_make_rpcs() (Tvrtko) Remove unrelated changes (Tvrtko) v5: Some typos (Tvrtko) Process sseu param in read_properties_unlocked() (Tvrtko) v6: Actually commit the bits from v5... Fixup some checkpath warnings v7: Only compare engine uabi field (Chris) Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200317132222.2638719-3-lionel.g.landwerlin@intel.com
2020-03-17 13:22:22 +00:00
int
drm/i915/sseu: Move sseu_info under gt_info SSEUs are a GT capability, so track them under gt_info. Signed-off-by: Venkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com> Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Andi Shyti <andi.shyti@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/20200708003952.21831-8-daniele.ceraolospurio@intel.com
2020-07-08 00:39:50 +00:00
i915_gem_user_to_context_sseu(struct intel_gt *gt,
drm/i915/perf: introduce global sseu pinning On Gen11 powergating half the execution units is a functional requirement when using the VME samplers. Not fullfilling this requirement can lead to hangs. This unfortunately plays fairly poorly with the NOA requirements. NOA requires a stable power configuration to maintain its configuration. As a result using OA (and NOA feeding into it) so far has required us to use a power configuration that can work for all contexts. The only power configuration fullfilling this is powergating half the execution units. This makes performance analysis for 3D workloads somewhat pointless. Failing to find a solution that would work for everybody, this change introduces a new i915-perf stream open parameter that punts the decision off to userspace. If this parameter is omitted, the existing Gen11 behavior remains (half EU array powergating). This change takes the initiative to move all perf related sseu configuration into i915_perf.c v2: Make parameter priviliged if different from default v3: Fix context modifying its sseu config while i915-perf is enabled v4: Always consider global sseu a privileged operation (Tvrtko) Override req_sseu point in intel_sseu_make_rpcs() (Tvrtko) Remove unrelated changes (Tvrtko) v5: Some typos (Tvrtko) Process sseu param in read_properties_unlocked() (Tvrtko) v6: Actually commit the bits from v5... Fixup some checkpath warnings v7: Only compare engine uabi field (Chris) Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200317132222.2638719-3-lionel.g.landwerlin@intel.com
2020-03-17 13:22:22 +00:00
const struct drm_i915_gem_context_param_sseu *user,
struct intel_sseu *context)
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
{
drm/i915/sseu: Move sseu_info under gt_info SSEUs are a GT capability, so track them under gt_info. Signed-off-by: Venkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com> Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Andi Shyti <andi.shyti@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/20200708003952.21831-8-daniele.ceraolospurio@intel.com
2020-07-08 00:39:50 +00:00
const struct sseu_dev_info *device = &gt->info.sseu;
struct drm_i915_private *i915 = gt->i915;
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
/* No zeros in any field. */
if (!user->slice_mask || !user->subslice_mask ||
!user->min_eus_per_subslice || !user->max_eus_per_subslice)
return -EINVAL;
/* Max > min. */
if (user->max_eus_per_subslice < user->min_eus_per_subslice)
return -EINVAL;
/*
* Some future proofing on the types since the uAPI is wider than the
* current internal implementation.
*/
if (overflows_type(user->slice_mask, context->slice_mask) ||
overflows_type(user->subslice_mask, context->subslice_mask) ||
overflows_type(user->min_eus_per_subslice,
context->min_eus_per_subslice) ||
overflows_type(user->max_eus_per_subslice,
context->max_eus_per_subslice))
return -EINVAL;
/* Check validity against hardware. */
if (user->slice_mask & ~device->slice_mask)
return -EINVAL;
if (user->subslice_mask & ~device->subslice_mask[0])
return -EINVAL;
if (user->max_eus_per_subslice > device->max_eus_per_subslice)
return -EINVAL;
context->slice_mask = user->slice_mask;
context->subslice_mask = user->subslice_mask;
context->min_eus_per_subslice = user->min_eus_per_subslice;
context->max_eus_per_subslice = user->max_eus_per_subslice;
/* Part specific restrictions. */
drm/i915/gem: replace IS_GEN and friends with GRAPHICS_VER This was done by the following semantic patch: @@ expression i915; @@ - INTEL_GEN(i915) + GRAPHICS_VER(i915) @@ expression i915; expression E; @@ - INTEL_GEN(i915) >= E + GRAPHICS_VER(i915) >= E @@ expression dev_priv; expression E; @@ - !IS_GEN(dev_priv, E) + GRAPHICS_VER(dev_priv) != E @@ expression dev_priv; expression E; @@ - IS_GEN(dev_priv, E) + GRAPHICS_VER(dev_priv) == E @@ expression dev_priv; expression from, until; @@ - IS_GEN_RANGE(dev_priv, from, until) + IS_GRAPHICS_VER(dev_priv, from, until) @def@ expression E; identifier id =~ "^gen$"; @@ - id = GRAPHICS_VER(E) + ver = GRAPHICS_VER(E) @@ identifier def.id; @@ - id + ver It also takes care of renaming the variable we assign to GRAPHICS_VER() so to use "ver" rather than "gen". Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com> Reviewed-by: Matt Roper <matthew.d.roper@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210605155356.4183026-4-lucas.demarchi@intel.com
2021-06-05 15:53:54 +00:00
if (GRAPHICS_VER(i915) == 11) {
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
unsigned int hw_s = hweight8(device->slice_mask);
unsigned int hw_ss_per_s = hweight8(device->subslice_mask[0]);
unsigned int req_s = hweight8(context->slice_mask);
unsigned int req_ss = hweight8(context->subslice_mask);
/*
* Only full subslice enablement is possible if more than one
* slice is turned on.
*/
if (req_s > 1 && req_ss != hw_ss_per_s)
return -EINVAL;
/*
* If more than four (SScount bitfield limit) subslices are
* requested then the number has to be even.
*/
if (req_ss > 4 && (req_ss & 1))
return -EINVAL;
/*
* If only one slice is enabled and subslice count is below the
* device full enablement, it must be at most half of the all
* available subslices.
*/
if (req_s == 1 && req_ss < hw_ss_per_s &&
req_ss > (hw_ss_per_s / 2))
return -EINVAL;
/* ABI restriction - VME use case only. */
/* All slices or one slice only. */
if (req_s != 1 && req_s != hw_s)
return -EINVAL;
/*
* Half subslices or full enablement only when one slice is
* enabled.
*/
if (req_s == 1 &&
(req_ss != hw_ss_per_s && req_ss != (hw_ss_per_s / 2)))
return -EINVAL;
/* No EU configuration changes. */
if ((user->min_eus_per_subslice !=
device->max_eus_per_subslice) ||
(user->max_eus_per_subslice !=
device->max_eus_per_subslice))
return -EINVAL;
}
return 0;
}
static int set_sseu(struct i915_gem_context *ctx,
struct drm_i915_gem_context_param *args)
{
struct drm_i915_private *i915 = ctx->i915;
struct drm_i915_gem_context_param_sseu user_sseu;
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
struct intel_context *ce;
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
struct intel_sseu sseu;
drm/i915: Extend I915_CONTEXT_PARAM_SSEU to support local ctx->engine[] Allow the user to specify a local engine index (as opposed to class:index) that they can use to refer to a preset engine inside the ctx->engine[] array defined by an earlier I915_CONTEXT_PARAM_ENGINES. This will be useful for setting SSEU parameters on virtual engines that are local to the context and do not have a valid global class:instance lookup. Note that due to the ambiguity in using class:instance with ctx->engines[], if a user supplied engine map is active the user must specify the engine to alter by its index into the ctx->engines[]. 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/20190521211134.16117-3-chris@chris-wilson.co.uk
2019-05-21 21:11:27 +00:00
unsigned long lookup;
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
int ret;
if (args->size < sizeof(user_sseu))
return -EINVAL;
drm/i915/gem: replace IS_GEN and friends with GRAPHICS_VER This was done by the following semantic patch: @@ expression i915; @@ - INTEL_GEN(i915) + GRAPHICS_VER(i915) @@ expression i915; expression E; @@ - INTEL_GEN(i915) >= E + GRAPHICS_VER(i915) >= E @@ expression dev_priv; expression E; @@ - !IS_GEN(dev_priv, E) + GRAPHICS_VER(dev_priv) != E @@ expression dev_priv; expression E; @@ - IS_GEN(dev_priv, E) + GRAPHICS_VER(dev_priv) == E @@ expression dev_priv; expression from, until; @@ - IS_GEN_RANGE(dev_priv, from, until) + IS_GRAPHICS_VER(dev_priv, from, until) @def@ expression E; identifier id =~ "^gen$"; @@ - id = GRAPHICS_VER(E) + ver = GRAPHICS_VER(E) @@ identifier def.id; @@ - id + ver It also takes care of renaming the variable we assign to GRAPHICS_VER() so to use "ver" rather than "gen". Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com> Reviewed-by: Matt Roper <matthew.d.roper@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210605155356.4183026-4-lucas.demarchi@intel.com
2021-06-05 15:53:54 +00:00
if (GRAPHICS_VER(i915) != 11)
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
return -ENODEV;
if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
sizeof(user_sseu)))
return -EFAULT;
drm/i915: Extend I915_CONTEXT_PARAM_SSEU to support local ctx->engine[] Allow the user to specify a local engine index (as opposed to class:index) that they can use to refer to a preset engine inside the ctx->engine[] array defined by an earlier I915_CONTEXT_PARAM_ENGINES. This will be useful for setting SSEU parameters on virtual engines that are local to the context and do not have a valid global class:instance lookup. Note that due to the ambiguity in using class:instance with ctx->engines[], if a user supplied engine map is active the user must specify the engine to alter by its index into the ctx->engines[]. 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/20190521211134.16117-3-chris@chris-wilson.co.uk
2019-05-21 21:11:27 +00:00
if (user_sseu.rsvd)
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
return -EINVAL;
drm/i915: Extend I915_CONTEXT_PARAM_SSEU to support local ctx->engine[] Allow the user to specify a local engine index (as opposed to class:index) that they can use to refer to a preset engine inside the ctx->engine[] array defined by an earlier I915_CONTEXT_PARAM_ENGINES. This will be useful for setting SSEU parameters on virtual engines that are local to the context and do not have a valid global class:instance lookup. Note that due to the ambiguity in using class:instance with ctx->engines[], if a user supplied engine map is active the user must specify the engine to alter by its index into the ctx->engines[]. 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/20190521211134.16117-3-chris@chris-wilson.co.uk
2019-05-21 21:11:27 +00:00
if (user_sseu.flags & ~(I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX))
return -EINVAL;
lookup = 0;
if (user_sseu.flags & I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX)
lookup |= LOOKUP_USER_INDEX;
ce = lookup_user_engine(ctx, lookup, &user_sseu.engine);
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
if (IS_ERR(ce))
return PTR_ERR(ce);
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
/* Only render engine supports RPCS configuration. */
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
if (ce->engine->class != RENDER_CLASS) {
ret = -ENODEV;
goto out_ce;
}
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
drm/i915/sseu: Move sseu_info under gt_info SSEUs are a GT capability, so track them under gt_info. Signed-off-by: Venkata Sandeep Dhanalakota <venkata.s.dhanalakota@intel.com> Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Andi Shyti <andi.shyti@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/20200708003952.21831-8-daniele.ceraolospurio@intel.com
2020-07-08 00:39:50 +00:00
ret = i915_gem_user_to_context_sseu(ce->engine->gt, &user_sseu, &sseu);
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
if (ret)
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
goto out_ce;
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
ret = intel_context_reconfigure_sseu(ce, sseu);
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
if (ret)
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
goto out_ce;
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
args->size = sizeof(user_sseu);
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
out_ce:
intel_context_put(ce);
return ret;
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
}
drm/i915/gem: Make context persistence optional Our existing behaviour is to allow contexts and their GPU requests to persist past the point of closure until the requests are complete. This allows clients to operate in a 'fire-and-forget' manner where they can setup a rendering pipeline and hand it over to the display server and immediately exit. As the rendering pipeline is kept alive until completion, the display server (or other consumer) can use the results in the future and present them to the user. The compute model is a little different. They have little to no buffer sharing between processes as their kernels tend to operate on a continuous stream, feeding the results back to the client application. These kernels operate for an indeterminate length of time, with many clients wishing that the kernel was always running for as long as they keep feeding in the data, i.e. acting like a DSP. Not all clients want this persistent "desktop" behaviour and would prefer that the contexts are cleaned up immediately upon closure. This ensures that when clients are run without hangchecking (e.g. for compute kernels of indeterminate runtime), any GPU hang or other unexpected workloads are terminated with the process and does not continue to hog resources. The default behaviour for new contexts is the legacy persistence mode, as some desktop applications are dependent upon the existing behaviour. New clients will have to opt in to immediate cleanup on context closure. If the hangchecking modparam is disabled, so is persistent context support -- all contexts will be terminated on closure. We expect this behaviour change to be welcomed by compute users, who have often been caught between a rock and a hard place. They disable hangchecking to avoid their kernels being "unfairly" declared hung, but have also experienced true hangs that the system was then unable to clean up. Naturally, this leads to bug reports. Testcase: igt/gem_ctx_persistence Link: https://github.com/intel/compute-runtime/pull/228 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Jason Ekstrand <jason@jlekstrand.net> Link: https://patchwork.freedesktop.org/patch/msgid/20191029202338.8841-1-chris@chris-wilson.co.uk
2019-10-29 20:23:38 +00:00
static int
set_persistence(struct i915_gem_context *ctx,
const struct drm_i915_gem_context_param *args)
{
if (args->size)
return -EINVAL;
return __context_set_persistence(ctx, args->value);
}
drm/i915/gem: Return void from context_apply_all None of the callbacks we use with it return an error code anymore; they all return 0 unconditionally. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-6-jason@jlekstrand.net
2021-07-08 15:48:10 +00:00
static void __apply_priority(struct intel_context *ce, void *arg)
drm/i915: Push the use-semaphore marker onto the intel_context Instead of rummaging through the intel_context to peek at the GEM context in the middle of request submission to decide whether to use semaphores, store that information on the intel_context itself. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191220101230.256839-2-chris@chris-wilson.co.uk
2019-12-20 10:12:30 +00:00
{
struct i915_gem_context *ctx = arg;
drm/i915: Disable semaphore inter-engine sync without timeslicing Since the removal of the no-semaphore boosting, we rely on timeslicing to reorder passed inter-dependency hogs across the engines. However, we require preemption to support timeslicing into user payloads, and not all machine support preemption so we do not universally enable timeslicing, even when it would correctly preempt our own inter-engine semaphores. Since timeslicing and semaphore priority deboosting is now disabled on Broadwell/Braswell, we have to follow suite and not use semaphores. Testcase: igt/gem_exec_schedule/semaphore-codependency # bdw/bsw Fixes: 18e4af04d218 ("drm/i915: Drop no-semaphore boosting") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200521140617.30015-1-chris@chris-wilson.co.uk
2020-05-21 14:06:16 +00:00
if (!intel_engine_has_timeslices(ce->engine))
drm/i915/gem: Return void from context_apply_all None of the callbacks we use with it return an error code anymore; they all return 0 unconditionally. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-6-jason@jlekstrand.net
2021-07-08 15:48:10 +00:00
return;
drm/i915: Push the use-semaphore marker onto the intel_context Instead of rummaging through the intel_context to peek at the GEM context in the middle of request submission to decide whether to use semaphores, store that information on the intel_context itself. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191220101230.256839-2-chris@chris-wilson.co.uk
2019-12-20 10:12:30 +00:00
drm/i915/guc: Disable semaphores when using GuC scheduling Semaphores are an optimization and not required for basic GuC submission to work properly. Disable until we have time to do the implementation to enable semaphores and tune them for performance. Also long direction is just to delete semaphores from the i915 so another reason to not enable these for GuC submission. This patch fixes an existing bugs where I915_ENGINE_HAS_SEMAPHORES was not honored correctly. v2: Reword commit message v3: (John H) - Add text to commit indicating this also fixing an existing bug v4: (John H) - s/bug/bugs Cc: John Harrison <john.c.harrison@intel.com> Signed-off-by: Matthew Brost <matthew.brost@intel.com> Reviewed-by: John Harrison <John.C.Harrison@Intel.com> Signed-off-by: John Harrison <John.C.Harrison@Intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210721215101.139794-14-matthew.brost@intel.com
2021-07-21 21:50:56 +00:00
if (ctx->sched.priority >= I915_PRIORITY_NORMAL &&
intel_engine_has_semaphores(ce->engine))
drm/i915: Push the use-semaphore marker onto the intel_context Instead of rummaging through the intel_context to peek at the GEM context in the middle of request submission to decide whether to use semaphores, store that information on the intel_context itself. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191220101230.256839-2-chris@chris-wilson.co.uk
2019-12-20 10:12:30 +00:00
intel_context_set_use_semaphores(ce);
else
intel_context_clear_use_semaphores(ce);
}
static int set_priority(struct i915_gem_context *ctx,
const struct drm_i915_gem_context_param *args)
{
drm/i915/gem: Add a separate validate_priority helper With the proto-context stuff added later in this series, we end up having to duplicate set_priority. This lets us avoid duplicating the validation logic. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-15-jason@jlekstrand.net
2021-07-08 15:48:19 +00:00
int err;
drm/i915: Push the use-semaphore marker onto the intel_context Instead of rummaging through the intel_context to peek at the GEM context in the middle of request submission to decide whether to use semaphores, store that information on the intel_context itself. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191220101230.256839-2-chris@chris-wilson.co.uk
2019-12-20 10:12:30 +00:00
drm/i915/gem: Add a separate validate_priority helper With the proto-context stuff added later in this series, we end up having to duplicate set_priority. This lets us avoid duplicating the validation logic. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-15-jason@jlekstrand.net
2021-07-08 15:48:19 +00:00
err = validate_priority(ctx->i915, args);
if (err)
return err;
drm/i915: Push the use-semaphore marker onto the intel_context Instead of rummaging through the intel_context to peek at the GEM context in the middle of request submission to decide whether to use semaphores, store that information on the intel_context itself. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191220101230.256839-2-chris@chris-wilson.co.uk
2019-12-20 10:12:30 +00:00
drm/i915/gem: Add a separate validate_priority helper With the proto-context stuff added later in this series, we end up having to duplicate set_priority. This lets us avoid duplicating the validation logic. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-15-jason@jlekstrand.net
2021-07-08 15:48:19 +00:00
ctx->sched.priority = args->value;
drm/i915: Push the use-semaphore marker onto the intel_context Instead of rummaging through the intel_context to peek at the GEM context in the middle of request submission to decide whether to use semaphores, store that information on the intel_context itself. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191220101230.256839-2-chris@chris-wilson.co.uk
2019-12-20 10:12:30 +00:00
context_apply_all(ctx, __apply_priority, ctx);
return 0;
}
drm/i915: Avoid using ctx->file_priv during construction As we only set ctx->file_priv on registering the GEM context after construction, it is invalid to try and use it in the middle for setting various parameters. Indeed, we put the file_priv into struct create_ext so that we have the right file_private available without having to look at ctx->file_priv. However, it helps to use it! Reported-by: Jordan Justen <jordan.l.justen@intel.com> Fixes: b91715417244 ("drm/i915: Extend CONTEXT_CREATE to set parameters upon construction") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Jordan Justen <jordan.l.justen@intel.com> Reviewed-by: Jordan Justen <jordan.l.justen@intel.com> Tested-by: Jordan Justen <jordan.l.justen@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190330100349.30642-1-chris@chris-wilson.co.uk
2019-03-30 10:03:49 +00:00
static int ctx_setparam(struct drm_i915_file_private *fpriv,
struct i915_gem_context *ctx,
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
struct drm_i915_gem_context_param *args)
drm/i915: Add ioctl to set per-context parameters Sometimes we wish to tweak how an individual context behaves. Since we always create a context for every filp, this means that individual processes can fine tune their behaviour even if they do not explicitly create a context. The first example parameter here is to enable multi-process GPU testing, but the interface should be able to cope with passing arbitrarily complex parameters. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Testcase: igt/gem_reset_stats/ban-period-* Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-12-24 16:13:40 +00:00
{
drm/i915: Nuke struct_mutex from context_setparam Userspace should be free to race against itself and shoot itself in the foot if it so desires to adjust a parameter at the same time as submitting a batch to that context. As such, the struct_mutex in context setparam is only being used to serialise userspace against itself and not for any protection of internal structs and so is superfluous. v2: Separate user_flags from internal flags to reduce chance of interference; and use locked bit ops for user updates. 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/20180911132206.23032-1-chris@chris-wilson.co.uk
2018-09-11 13:22:06 +00:00
int ret = 0;
drm/i915: Add ioctl to set per-context parameters Sometimes we wish to tweak how an individual context behaves. Since we always create a context for every filp, this means that individual processes can fine tune their behaviour even if they do not explicitly create a context. The first example parameter here is to enable multi-process GPU testing, but the interface should be able to cope with passing arbitrarily complex parameters. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Testcase: igt/gem_reset_stats/ban-period-* Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-12-24 16:13:40 +00:00
switch (args->param) {
drm/i915: Allow userspace to request no-error-capture upon GPU hangs igt likes to inject GPU hangs into its command streams. However, as we expect these hangs, we don't actually want them recorded in the dmesg output or stored in the i915_error_state (usually). To accommodate this allow userspace to set a flag on the context that any hang emanating from that context will not be recorded. We still do the error capture (otherwise how do we find the guilty context and know its intent?) as part of the reason for random GPU hang injection is to exercise the race conditions between the error capture and normal execution. v2: Split out the request->ringbuf error capture changes. v3: Move the flag defines next to the intel_context->flags definition Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch> Reviewed-by: Dave Gordon <david.s.gordon@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1467616119-4093-9-git-send-email-chris@chris-wilson.co.uk
2016-07-04 07:08:39 +00:00
case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
drm/i915: Complete kerneldoc for struct i915_gem_context The existing kerneldoc was outdated, so time for a refresh. v2: Use single line kdoc, mention functions for manipulation Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161231112012.29263-3-chris@chris-wilson.co.uk
2016-12-31 11:20:11 +00:00
if (args->size)
drm/i915: Allow userspace to request no-error-capture upon GPU hangs igt likes to inject GPU hangs into its command streams. However, as we expect these hangs, we don't actually want them recorded in the dmesg output or stored in the i915_error_state (usually). To accommodate this allow userspace to set a flag on the context that any hang emanating from that context will not be recorded. We still do the error capture (otherwise how do we find the guilty context and know its intent?) as part of the reason for random GPU hang injection is to exercise the race conditions between the error capture and normal execution. v2: Split out the request->ringbuf error capture changes. v3: Move the flag defines next to the intel_context->flags definition Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch> Reviewed-by: Dave Gordon <david.s.gordon@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1467616119-4093-9-git-send-email-chris@chris-wilson.co.uk
2016-07-04 07:08:39 +00:00
ret = -EINVAL;
drm/i915: Complete kerneldoc for struct i915_gem_context The existing kerneldoc was outdated, so time for a refresh. v2: Use single line kdoc, mention functions for manipulation Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161231112012.29263-3-chris@chris-wilson.co.uk
2016-12-31 11:20:11 +00:00
else if (args->value)
i915_gem_context_set_no_error_capture(ctx);
else
i915_gem_context_clear_no_error_capture(ctx);
drm/i915: add a context parameter to {en, dis}able zero address mapping Export a new context parameter that can be set/queried through the context_{get,set}param ioctls. This parameter is passed as a context flag and decides whether or not a GPU address mapping is allowed to be made at address zero. The default is to allow such mappings. Signed-off-by: David Weinehall <david.weinehall@intel.com> Acked-by: "Zou, Nanhai" <nanhai.zou@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2015-05-20 14:00:13 +00:00
break;
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
drm/i915: Add bannable context parameter Now when driver has per context scoring of 'hanging badness' and also subsequent hangs during short windows are allowed, if there is progress made in between, it does not make sense to expose a ban timing window as a context parameter anymore. Let the scoring be the sole indicator for ban policy and substitute ban period context parameter as a boolean to get/set context bannable property. v2: allow non root to opt into being banned (Chris) Cc: Chris Wilson <chris@chris-wilson.co.uk> Suggested-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
2016-11-16 15:20:32 +00:00
case I915_CONTEXT_PARAM_BANNABLE:
if (args->size)
ret = -EINVAL;
else if (!capable(CAP_SYS_ADMIN) && !args->value)
ret = -EPERM;
drm/i915: Complete kerneldoc for struct i915_gem_context The existing kerneldoc was outdated, so time for a refresh. v2: Use single line kdoc, mention functions for manipulation Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161231112012.29263-3-chris@chris-wilson.co.uk
2016-12-31 11:20:11 +00:00
else if (args->value)
i915_gem_context_set_bannable(ctx);
drm/i915: Add bannable context parameter Now when driver has per context scoring of 'hanging badness' and also subsequent hangs during short windows are allowed, if there is progress made in between, it does not make sense to expose a ban timing window as a context parameter anymore. Let the scoring be the sole indicator for ban policy and substitute ban period context parameter as a boolean to get/set context bannable property. v2: allow non root to opt into being banned (Chris) Cc: Chris Wilson <chris@chris-wilson.co.uk> Suggested-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
2016-11-16 15:20:32 +00:00
else
drm/i915: Complete kerneldoc for struct i915_gem_context The existing kerneldoc was outdated, so time for a refresh. v2: Use single line kdoc, mention functions for manipulation Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: http://patchwork.freedesktop.org/patch/msgid/20161231112012.29263-3-chris@chris-wilson.co.uk
2016-12-31 11:20:11 +00:00
i915_gem_context_clear_bannable(ctx);
drm/i915: Add bannable context parameter Now when driver has per context scoring of 'hanging badness' and also subsequent hangs during short windows are allowed, if there is progress made in between, it does not make sense to expose a ban timing window as a context parameter anymore. Let the scoring be the sole indicator for ban policy and substitute ban period context parameter as a boolean to get/set context bannable property. v2: allow non root to opt into being banned (Chris) Cc: Chris Wilson <chris@chris-wilson.co.uk> Suggested-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Mika Kuoppala <mika.kuoppala@intel.com>
2016-11-16 15:20:32 +00:00
break;
drm/i915/scheduler: Support user-defined priorities Use a priority stored in the context as the initial value when submitting a request. This allows us to change the default priority on a per-context basis, allowing different contexts to be favoured with GPU time at the expense of lower importance work. The user can adjust the context's priority via I915_CONTEXT_PARAM_PRIORITY, with more positive values being higher priority (they will be serviced earlier, after their dependencies have been resolved). Any prerequisite work for an execbuf will have its priority raised to match the new request as required. Normal users can specify any value in the range of -1023 to 0 [default], i.e. they can reduce the priority of their workloads (and temporarily boost it back to normal if so desired). Privileged users can specify any value in the range of -1023 to 1023, [default is 0], i.e. they can raise their priority above all overs and so potentially starve the system. Note that the existing schedulers are not fair, nor load balancing, the execution is strictly by priority on a first-come, first-served basis, and the driver may choose to boost some requests above the range available to users. This priority was originally based around nice(2), but evolved to allow clients to adjust their priority within a small range, and allow for a privileged high priority range. For example, this can be used to implement EGL_IMG_context_priority https://www.khronos.org/registry/egl/extensions/IMG/EGL_IMG_context_priority.txt EGL_CONTEXT_PRIORITY_LEVEL_IMG determines the priority level of the context to be created. This attribute is a hint, as an implementation may not support multiple contexts at some priority levels and system policy may limit access to high priority contexts to appropriate system privilege level. The default value for EGL_CONTEXT_PRIORITY_LEVEL_IMG is EGL_CONTEXT_PRIORITY_MEDIUM_IMG." so we can map PRIORITY_HIGH -> 1023 [privileged, will failback to 0] PRIORITY_MED -> 0 [default] PRIORITY_LOW -> -1023 They also map onto the priorities used by VkQueue (and a VkQueue is essentially a timeline, our i915_gem_context under full-ppgtt). v2: s/CAP_SYS_ADMIN/CAP_SYS_NICE/ v3: Report min/max user priorities as defines in the uapi, and rebase internal priorities on the exposed values. Testcase: igt/gem_exec_schedule Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171003203453.15692-9-chris@chris-wilson.co.uk
2017-10-03 20:34:53 +00:00
drm/i915: Optionally disable automatic recovery after a GPU reset Some clients, such as mesa, may only emit minimal incremental batches that rely on the logical context state from previous batches. They know that recovery is impossible after a hang as their required GPU state is lost, and that each in flight and subsequent batch will hang (resetting the context image back to default perpetuating the problem). To avoid getting into the state in the first place, we can allow clients to opt out of automatic recovery and elect to ban any guilty context following a hang. This prevents the continual stream of hangs and allows the client to recreate their context and rebuild the state from scratch. v2: Prefer calling it recoverable rather than unrecoverable. References: https://lists.freedesktop.org/archives/mesa-dev/2019-February/215431.html Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Kenneth Graunke <kenneth@whitecape.org> Cc: Mika Kuoppala <mika.kuoppala@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Acked-by: Kenneth Graunke <kenneth@whitecape.org> # for mesa Link: https://patchwork.freedesktop.org/patch/msgid/20190218105821.17293-1-chris@chris-wilson.co.uk
2019-02-18 10:58:21 +00:00
case I915_CONTEXT_PARAM_RECOVERABLE:
if (args->size)
ret = -EINVAL;
else if (args->value)
i915_gem_context_set_recoverable(ctx);
else
i915_gem_context_clear_recoverable(ctx);
break;
drm/i915/scheduler: Support user-defined priorities Use a priority stored in the context as the initial value when submitting a request. This allows us to change the default priority on a per-context basis, allowing different contexts to be favoured with GPU time at the expense of lower importance work. The user can adjust the context's priority via I915_CONTEXT_PARAM_PRIORITY, with more positive values being higher priority (they will be serviced earlier, after their dependencies have been resolved). Any prerequisite work for an execbuf will have its priority raised to match the new request as required. Normal users can specify any value in the range of -1023 to 0 [default], i.e. they can reduce the priority of their workloads (and temporarily boost it back to normal if so desired). Privileged users can specify any value in the range of -1023 to 1023, [default is 0], i.e. they can raise their priority above all overs and so potentially starve the system. Note that the existing schedulers are not fair, nor load balancing, the execution is strictly by priority on a first-come, first-served basis, and the driver may choose to boost some requests above the range available to users. This priority was originally based around nice(2), but evolved to allow clients to adjust their priority within a small range, and allow for a privileged high priority range. For example, this can be used to implement EGL_IMG_context_priority https://www.khronos.org/registry/egl/extensions/IMG/EGL_IMG_context_priority.txt EGL_CONTEXT_PRIORITY_LEVEL_IMG determines the priority level of the context to be created. This attribute is a hint, as an implementation may not support multiple contexts at some priority levels and system policy may limit access to high priority contexts to appropriate system privilege level. The default value for EGL_CONTEXT_PRIORITY_LEVEL_IMG is EGL_CONTEXT_PRIORITY_MEDIUM_IMG." so we can map PRIORITY_HIGH -> 1023 [privileged, will failback to 0] PRIORITY_MED -> 0 [default] PRIORITY_LOW -> -1023 They also map onto the priorities used by VkQueue (and a VkQueue is essentially a timeline, our i915_gem_context under full-ppgtt). v2: s/CAP_SYS_ADMIN/CAP_SYS_NICE/ v3: Report min/max user priorities as defines in the uapi, and rebase internal priorities on the exposed values. Testcase: igt/gem_exec_schedule Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171003203453.15692-9-chris@chris-wilson.co.uk
2017-10-03 20:34:53 +00:00
case I915_CONTEXT_PARAM_PRIORITY:
drm/i915: Push the use-semaphore marker onto the intel_context Instead of rummaging through the intel_context to peek at the GEM context in the middle of request submission to decide whether to use semaphores, store that information on the intel_context itself. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Andi Shyti <andi.shyti@intel.com> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20191220101230.256839-2-chris@chris-wilson.co.uk
2019-12-20 10:12:30 +00:00
ret = set_priority(ctx, args);
drm/i915/scheduler: Support user-defined priorities Use a priority stored in the context as the initial value when submitting a request. This allows us to change the default priority on a per-context basis, allowing different contexts to be favoured with GPU time at the expense of lower importance work. The user can adjust the context's priority via I915_CONTEXT_PARAM_PRIORITY, with more positive values being higher priority (they will be serviced earlier, after their dependencies have been resolved). Any prerequisite work for an execbuf will have its priority raised to match the new request as required. Normal users can specify any value in the range of -1023 to 0 [default], i.e. they can reduce the priority of their workloads (and temporarily boost it back to normal if so desired). Privileged users can specify any value in the range of -1023 to 1023, [default is 0], i.e. they can raise their priority above all overs and so potentially starve the system. Note that the existing schedulers are not fair, nor load balancing, the execution is strictly by priority on a first-come, first-served basis, and the driver may choose to boost some requests above the range available to users. This priority was originally based around nice(2), but evolved to allow clients to adjust their priority within a small range, and allow for a privileged high priority range. For example, this can be used to implement EGL_IMG_context_priority https://www.khronos.org/registry/egl/extensions/IMG/EGL_IMG_context_priority.txt EGL_CONTEXT_PRIORITY_LEVEL_IMG determines the priority level of the context to be created. This attribute is a hint, as an implementation may not support multiple contexts at some priority levels and system policy may limit access to high priority contexts to appropriate system privilege level. The default value for EGL_CONTEXT_PRIORITY_LEVEL_IMG is EGL_CONTEXT_PRIORITY_MEDIUM_IMG." so we can map PRIORITY_HIGH -> 1023 [privileged, will failback to 0] PRIORITY_MED -> 0 [default] PRIORITY_LOW -> -1023 They also map onto the priorities used by VkQueue (and a VkQueue is essentially a timeline, our i915_gem_context under full-ppgtt). v2: s/CAP_SYS_ADMIN/CAP_SYS_NICE/ v3: Report min/max user priorities as defines in the uapi, and rebase internal priorities on the exposed values. Testcase: igt/gem_exec_schedule Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171003203453.15692-9-chris@chris-wilson.co.uk
2017-10-03 20:34:53 +00:00
break;
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
drm/i915: Expose RPCS (SSEU) configuration to userspace (Gen11 only) We want to allow userspace to reconfigure the subslice configuration on a per context basis. This is required for the functional requirement of shutting down non-VME enabled sub-slices on Gen11 parts. To do so, we expose a context parameter to allow adjustment of the RPCS register stored within the context image (and currently not accessible via LRI). If the context is adjusted before first use or whilst idle, the adjustment is for "free"; otherwise if the context is active we queue a request to do so (using the kernel context), following all other activity by that context, which is also marked as barrier for all following submission against the same context. Since the overhead of device re-configuration during context switching can be significant, especially in multi-context workloads, we limit this new uAPI to only support the Gen11 VME use case. In this use case either the device is fully enabled, and exactly one slice and half of the subslices are enabled. Example usage: struct drm_i915_gem_context_param_sseu sseu = { }; struct drm_i915_gem_context_param arg = { .param = I915_CONTEXT_PARAM_SSEU, .ctx_id = gem_context_create(fd), .size = sizeof(sseu), .value = to_user_pointer(&sseu) }; /* Query device defaults. */ gem_context_get_param(fd, &arg); /* Set VME configuration on a 1x6x8 part. */ sseu.slice_mask = 0x1; sseu.subslice_mask = 0xe0; gem_context_set_param(fd, &arg); v2: Fix offset of CTX_R_PWR_CLK_STATE in intel_lr_context_set_sseu() (Lionel) v3: Add ability to program this per engine (Chris) v4: Move most get_sseu() into i915_gem_context.c (Lionel) v5: Validate sseu configuration against the device's capabilities (Lionel) v6: Change context powergating settings through MI_SDM on kernel context (Chris) v7: Synchronize the requests following a powergating setting change using a global dependency (Chris) Iterate timelines through dev_priv.gt.active_rings (Tvrtko) Disable RPCS configuration setting for non capable users (Lionel/Tvrtko) v8: s/union intel_sseu/struct intel_sseu/ (Lionel) s/dev_priv/i915/ (Tvrtko) Change uapi class/instance fields to u16 (Tvrtko) Bump mask fields to 64bits (Lionel) Don't return EPERM when dynamic sseu is disabled (Tvrtko) v9: Import context image into kernel context's ppgtt only when reconfiguring powergated slice/subslices (Chris) Use aliasing ppgtt when needed (Michel) Tvrtko Ursulin: v10: * Update for upstream changes. * Request submit needs a RPM reference. * Reject on !FULL_PPGTT for simplicity. * Pull out get/set param to helpers for readability and less indent. * Use i915_request_await_dma_fence in add_global_barrier to skip waits on the same timeline and avoid GEM_BUG_ON. * No need to explicitly assign a NULL pointer to engine in legacy mode. * No need to move gen8_make_rpcs up. * Factored out global barrier as prep patch. * Allow to only CAP_SYS_ADMIN if !Gen11. v11: * Remove engine vfunc in favour of local helper. (Chris Wilson) * Stop retiring requests before updates since it is not needed (Chris Wilson) * Implement direct CPU update path for idle contexts. (Chris Wilson) * Left side dependency needs only be on the same context timeline. (Chris Wilson) * It is sufficient to order the timeline. (Chris Wilson) * Reject !RCS configuration attempts with -ENODEV for now. v12: * Rebase for make_rpcs. v13: * Centralize SSEU normalization to make_rpcs. * Type width checking (uAPI <-> implementation). * Gen11 restrictions uAPI checks. * Gen11 subslice count differences handling. Chris Wilson: * args->size handling fixes. * Update context image from GGTT. * Postpone context image update to pinning. * Use i915_gem_active_raw instead of last_request_on_engine. v14: * Add activity tracker on intel_context to fix the lifetime issues and simplify the code. (Chris Wilson) v15: * Fix context pin leak if no space in ring by simplifying the context pinning sequence. v16: * Rebase for context get/set param locking changes. * Just -ENODEV on !Gen11. (Joonas) v17: * Fix one Gen11 subslice enablement rule. * Handle error from i915_sw_fence_await_sw_fence_gfp. (Chris Wilson) v18: * Update commit message. (Joonas) * Restrict uAPI to VME use case. (Joonas) v19: * Rebase. v20: * Rebase for ce->active_tracker. v21: * Rebase for IS_GEN changes. v22: * Reserve uAPI for flags straight away. (Chris Wilson) v23: * Rebase for RUNTIME_INFO. v24: * Added some headline docs for the uapi usage. (Joonas/Chris) v25: * Renamed class/instance to engine_class/engine_instance to avoid clash with C++ keyword. (Tony Ye) v26: * Rebased for runtime pm api changes. v27: * Rebased for intel_context_init. * Wrap commit msg to 75. v28: (Chris Wilson) * Use i915_gem_ggtt. * Use i915_request_await_dma_fence to show a better example. v29: * i915_timeline_set_barrier can now fail. (Chris Wilson) v30: * Capture some acks. v31: * Drop the WARN_ON from use controllable paths. (Chris Wilson) * Use overflows_type for all checks. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100899 Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107634 Issue: https://github.com/intel/media-driver/issues/267 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> Cc: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Zhipeng Gong <zhipeng.gong@intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Tony Ye <tony.ye@intel.com> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Timo Aaltonen <timo.aaltonen@canonical.com> Acked-by: Takashi Iwai <tiwai@suse.de> Acked-by: Stéphane Marchesin <marcheu@chromium.org> Link: https://patchwork.freedesktop.org/patch/msgid/20190205095032.22673-4-tvrtko.ursulin@linux.intel.com
2019-02-05 09:50:31 +00:00
case I915_CONTEXT_PARAM_SSEU:
ret = set_sseu(ctx, args);
break;
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
drm/i915/gem: Make context persistence optional Our existing behaviour is to allow contexts and their GPU requests to persist past the point of closure until the requests are complete. This allows clients to operate in a 'fire-and-forget' manner where they can setup a rendering pipeline and hand it over to the display server and immediately exit. As the rendering pipeline is kept alive until completion, the display server (or other consumer) can use the results in the future and present them to the user. The compute model is a little different. They have little to no buffer sharing between processes as their kernels tend to operate on a continuous stream, feeding the results back to the client application. These kernels operate for an indeterminate length of time, with many clients wishing that the kernel was always running for as long as they keep feeding in the data, i.e. acting like a DSP. Not all clients want this persistent "desktop" behaviour and would prefer that the contexts are cleaned up immediately upon closure. This ensures that when clients are run without hangchecking (e.g. for compute kernels of indeterminate runtime), any GPU hang or other unexpected workloads are terminated with the process and does not continue to hog resources. The default behaviour for new contexts is the legacy persistence mode, as some desktop applications are dependent upon the existing behaviour. New clients will have to opt in to immediate cleanup on context closure. If the hangchecking modparam is disabled, so is persistent context support -- all contexts will be terminated on closure. We expect this behaviour change to be welcomed by compute users, who have often been caught between a rock and a hard place. They disable hangchecking to avoid their kernels being "unfairly" declared hung, but have also experienced true hangs that the system was then unable to clean up. Naturally, this leads to bug reports. Testcase: igt/gem_ctx_persistence Link: https://github.com/intel/compute-runtime/pull/228 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Jason Ekstrand <jason@jlekstrand.net> Link: https://patchwork.freedesktop.org/patch/msgid/20191029202338.8841-1-chris@chris-wilson.co.uk
2019-10-29 20:23:38 +00:00
case I915_CONTEXT_PARAM_PERSISTENCE:
ret = set_persistence(ctx, args);
break;
drm/i915: Drop I915_CONTEXT_PARAM_NO_ZEROMAP The idea behind this param is to support OpenCL drivers with relocations because OpenCL reserves 0x0 for NULL and, if we placed memory there, it would confuse CL kernels. It was originally sent out as part of a patch series including libdrm [1] and Beignet [2] support. However, the libdrm and Beignet patches never landed in their respective upstream projects so this API has never been used. It's never been used in Mesa or any other driver, either. Dropping this API allows us to delete a small bit of code. [1]: https://lists.freedesktop.org/archives/intel-gfx/2015-May/067030.html [2]: https://lists.freedesktop.org/archives/intel-gfx/2015-May/067031.html Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-4-jason@jlekstrand.net
2021-07-08 15:48:08 +00:00
case I915_CONTEXT_PARAM_NO_ZEROMAP:
drm/i915: Create/destroy VM (ppGTT) for use with contexts In preparation to making the ppGTT binding for a context explicit (to facilitate reusing the same ppGTT between different contexts), allow the user to create and destroy named ppGTT. v2: Replace global barrier for swapping over the ppgtt and tlbs with a local context barrier (Tvrtko) v3: serialise with struct_mutex; it's lazy but required dammit v4: Rewrite igt_ctx_shared_exec to be more different (aimed to be more similarly, turned out different!) v5: Fix up test unwind for aliasing-ppgtt (snb) v6: Tighten language for uapi struct drm_i915_gem_vm_control. v7: Patch the context image for runtime ppgtt switching! Testcase: igt/gem_vm_create Testcase: igt/gem_ctx_param/vm Testcase: igt/gem_ctx_clone/vm Testcase: igt/gem_ctx_shared 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/20190322092325.5883-2-chris@chris-wilson.co.uk
2019-03-22 09:23:23 +00:00
case I915_CONTEXT_PARAM_BAN_PERIOD:
drm/i915: Drop I915_CONTEXT_PARAM_RINGSIZE This reverts commit 88be76cdafc7 ("drm/i915: Allow userspace to specify ringsize on construction"). This API was originally added for OpenCL but the compute-runtime PR has sat open for a year without action so we can still pull it out if we want. I argue we should drop it for three reasons: 1. If the compute-runtime PR has sat open for a year, this clearly isn't that important. 2. It's a very leaky API. Ring size is an implementation detail of the current execlist scheduler and really only makes sense there. It can't apply to the older ring-buffer scheduler on pre-execlist hardware because that's shared across all contexts and it won't apply to the GuC scheduler that's in the pipeline. 3. Having userspace set a ring size in bytes is a bad solution to the problem of having too small a ring. There is no way that userspace has the information to know how to properly set the ring size so it's just going to detect the feature and always set it to the maximum of 512K. This is what the compute-runtime PR does. The scheduler in i915, on the other hand, does have the information to make an informed choice. It could detect if the ring size is a problem and grow it itself. Or, if that's too hard, we could just increase the default size from 16K to 32K or even 64K instead of relying on userspace to do it. Let's drop this API for now and, if someone decides they really care about solving this problem, they can do it properly. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-2-jason@jlekstrand.net
2021-07-08 15:48:06 +00:00
case I915_CONTEXT_PARAM_RINGSIZE:
drm/i915/gem: Don't allow changing the VM on running contexts (v4) When the APIs were added to manage VMs more directly from userspace, the questionable choice was made to allow changing out the VM on a context at any time. This is horribly racy and there's absolutely no reason why any userspace would want to do this outside of testing that exact race. By removing support for CONTEXT_PARAM_VM from ctx_setparam, we make it impossible to change out the VM after the context has been fully created. This lets us delete a bunch of deferred task code as well as a duplicated (and slightly different) copy of the code which programs the PPGTT registers. v2 (Jason Ekstrand): - Expand the commit message v3 (Daniel Vetter): - Don't drop the __rcu on the vm pointer v4 (Jason Ekstrand): - Make it more obvious that I915_CONTEXT_PARAM_VM returns -EINVAL Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-26-jason@jlekstrand.net
2021-07-08 15:48:30 +00:00
case I915_CONTEXT_PARAM_VM:
drm/i915/gem: Don't allow changing the engine set on running contexts (v3) When the APIs were added to manage the engine set on a GEM context directly from userspace, the questionable choice was made to allow changing the engine set on a context at any time. This is horribly racy and there's absolutely no reason why any userspace would want to do this outside of trying to exercise interesting race conditions. By removing support for CONTEXT_PARAM_ENGINES from ctx_setparam, we make it impossible to change the engine set after the context has been fully created. This doesn't yet let us delete all the deferred engine clean-up code as that's still used for handling the case where the client dies or calls GEM_CONTEXT_DESTROY while work is in flight. However, moving to an API where the engine set is effectively immutable gives us more options to potentially clean that code up a bit going forward. It also removes a whole class of ways in which a client can hurt itself or try to get around kernel context banning. v2 (Jason Ekstrand): - Expand the commit mesage v3 (Jason Ekstrand): - Make it more obvious that I915_CONTEXT_PARAM_ENGINES returns -EINVAL Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-27-jason@jlekstrand.net
2021-07-08 15:48:31 +00:00
case I915_CONTEXT_PARAM_ENGINES:
drm/i915: Add ioctl to set per-context parameters Sometimes we wish to tweak how an individual context behaves. Since we always create a context for every filp, this means that individual processes can fine tune their behaviour even if they do not explicitly create a context. The first example parameter here is to enable multi-process GPU testing, but the interface should be able to cope with passing arbitrarily complex parameters. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Testcase: igt/gem_reset_stats/ban-period-* Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-12-24 16:13:40 +00:00
default:
ret = -EINVAL;
break;
}
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
return ret;
}
struct create_ext {
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
struct i915_gem_proto_context *pc;
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
struct drm_i915_file_private *fpriv;
};
static int create_setparam(struct i915_user_extension __user *ext, void *data)
{
struct drm_i915_gem_context_create_ext_setparam local;
const struct create_ext *arg = data;
if (copy_from_user(&local, ext, sizeof(local)))
return -EFAULT;
if (local.param.ctx_id)
return -EINVAL;
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
return set_proto_ctx_param(arg->fpriv, arg->pc, &local.param);
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
}
drm/i915: Drop the CONTEXT_CLONE API (v2) This API allows one context to grab bits out of another context upon creation. It can be used as a short-cut for setparam(getparam()) for things like I915_CONTEXT_PARAM_VM. However, it's never been used by any real userspace. It's used by a few IGT tests and that's it. Since it doesn't add any real value (most of the stuff you can CLONE you can copy in other ways), drop it. There is one thing that this API allows you to clone which you cannot clone via getparam/setparam: timelines. However, timelines are an implementation detail of i915 and not really something that needs to be exposed to userspace. Also, sharing timelines between contexts isn't obviously useful and supporting it has the potential to complicate i915 internally. It also doesn't add any functionality that the client can't get in other ways. If a client really wants a shared timeline, they can use a syncobj and set it as an in and out fence on every submit. v2 (Jason Ekstrand): - More detailed commit message Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-7-jason@jlekstrand.net
2021-07-08 15:48:11 +00:00
static int invalid_ext(struct i915_user_extension __user *ext, void *data)
drm/i915: Allow userspace to clone contexts on creation A usecase arose out of handling context recovery in mesa, whereby they wish to recreate a context with fresh logical state but preserving all other details of the original. Currently, they create a new context and iterate over which bits they want to copy across, but it would much more convenient if they were able to just pass in a target context to clone during creation. This essentially extends the setparam during creation to pull the details from a target context instead of the user supplied parameters. The ideal here is that we don't expose control over anything more than can be obtained via CONTEXT_PARAM. That is userspace retains explicit control over all features, and this api is just convenience. For example, you could replace struct context_param p = { .param = CONTEXT_PARAM_VM }; param.ctx_id = old_id; gem_context_get_param(&p.param); new_id = gem_context_create(); param.ctx_id = new_id; gem_context_set_param(&p.param); gem_vm_destroy(param.value); /* drop the ref to VM_ID handle */ with struct create_ext_param p = { { .name = CONTEXT_CREATE_CLONE }, .clone_id = old_id, .flags = CLONE_FLAGS_VM } new_id = gem_context_create_ext(&p); and not have to worry about stray namespace pollution etc. 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/20190521211134.16117-5-chris@chris-wilson.co.uk
2019-05-21 21:11:29 +00:00
{
drm/i915: Drop the CONTEXT_CLONE API (v2) This API allows one context to grab bits out of another context upon creation. It can be used as a short-cut for setparam(getparam()) for things like I915_CONTEXT_PARAM_VM. However, it's never been used by any real userspace. It's used by a few IGT tests and that's it. Since it doesn't add any real value (most of the stuff you can CLONE you can copy in other ways), drop it. There is one thing that this API allows you to clone which you cannot clone via getparam/setparam: timelines. However, timelines are an implementation detail of i915 and not really something that needs to be exposed to userspace. Also, sharing timelines between contexts isn't obviously useful and supporting it has the potential to complicate i915 internally. It also doesn't add any functionality that the client can't get in other ways. If a client really wants a shared timeline, they can use a syncobj and set it as an in and out fence on every submit. v2 (Jason Ekstrand): - More detailed commit message Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-7-jason@jlekstrand.net
2021-07-08 15:48:11 +00:00
return -EINVAL;
drm/i915: Allow userspace to clone contexts on creation A usecase arose out of handling context recovery in mesa, whereby they wish to recreate a context with fresh logical state but preserving all other details of the original. Currently, they create a new context and iterate over which bits they want to copy across, but it would much more convenient if they were able to just pass in a target context to clone during creation. This essentially extends the setparam during creation to pull the details from a target context instead of the user supplied parameters. The ideal here is that we don't expose control over anything more than can be obtained via CONTEXT_PARAM. That is userspace retains explicit control over all features, and this api is just convenience. For example, you could replace struct context_param p = { .param = CONTEXT_PARAM_VM }; param.ctx_id = old_id; gem_context_get_param(&p.param); new_id = gem_context_create(); param.ctx_id = new_id; gem_context_set_param(&p.param); gem_vm_destroy(param.value); /* drop the ref to VM_ID handle */ with struct create_ext_param p = { { .name = CONTEXT_CREATE_CLONE }, .clone_id = old_id, .flags = CLONE_FLAGS_VM } new_id = gem_context_create_ext(&p); and not have to worry about stray namespace pollution etc. 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/20190521211134.16117-5-chris@chris-wilson.co.uk
2019-05-21 21:11:29 +00:00
}
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
static const i915_user_extension_fn create_extensions[] = {
[I915_CONTEXT_CREATE_EXT_SETPARAM] = create_setparam,
drm/i915: Drop the CONTEXT_CLONE API (v2) This API allows one context to grab bits out of another context upon creation. It can be used as a short-cut for setparam(getparam()) for things like I915_CONTEXT_PARAM_VM. However, it's never been used by any real userspace. It's used by a few IGT tests and that's it. Since it doesn't add any real value (most of the stuff you can CLONE you can copy in other ways), drop it. There is one thing that this API allows you to clone which you cannot clone via getparam/setparam: timelines. However, timelines are an implementation detail of i915 and not really something that needs to be exposed to userspace. Also, sharing timelines between contexts isn't obviously useful and supporting it has the potential to complicate i915 internally. It also doesn't add any functionality that the client can't get in other ways. If a client really wants a shared timeline, they can use a syncobj and set it as an in and out fence on every submit. v2 (Jason Ekstrand): - More detailed commit message Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-7-jason@jlekstrand.net
2021-07-08 15:48:11 +00:00
[I915_CONTEXT_CREATE_EXT_CLONE] = invalid_ext,
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
};
static bool client_is_banned(struct drm_i915_file_private *file_priv)
{
return atomic_read(&file_priv->ban_score) >= I915_CLIENT_SCORE_BANNED;
}
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
static inline struct i915_gem_context *
__context_lookup(struct drm_i915_file_private *file_priv, u32 id)
{
struct i915_gem_context *ctx;
rcu_read_lock();
ctx = xa_load(&file_priv->context_xa, id);
if (ctx && !kref_get_unless_zero(&ctx->ref))
ctx = NULL;
rcu_read_unlock();
return ctx;
}
static struct i915_gem_context *
finalize_create_context_locked(struct drm_i915_file_private *file_priv,
struct i915_gem_proto_context *pc, u32 id)
{
struct i915_gem_context *ctx;
void *old;
lockdep_assert_held(&file_priv->proto_context_lock);
ctx = i915_gem_create_context(file_priv->dev_priv, pc);
if (IS_ERR(ctx))
return ctx;
gem_context_register(ctx, file_priv, id);
old = xa_erase(&file_priv->proto_context_xa, id);
GEM_BUG_ON(old != pc);
proto_context_close(pc);
/* One for the xarray and one for the caller */
return i915_gem_context_get(ctx);
}
struct i915_gem_context *
i915_gem_context_lookup(struct drm_i915_file_private *file_priv, u32 id)
{
struct i915_gem_proto_context *pc;
struct i915_gem_context *ctx;
ctx = __context_lookup(file_priv, id);
if (ctx)
return ctx;
mutex_lock(&file_priv->proto_context_lock);
/* Try one more time under the lock */
ctx = __context_lookup(file_priv, id);
if (!ctx) {
pc = xa_load(&file_priv->proto_context_xa, id);
if (!pc)
ctx = ERR_PTR(-ENOENT);
else
ctx = finalize_create_context_locked(file_priv, pc, id);
}
mutex_unlock(&file_priv->proto_context_lock);
return ctx;
}
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct drm_i915_private *i915 = to_i915(dev);
struct drm_i915_gem_context_create_ext *args = data;
struct create_ext ext_data;
int ret;
drm/i915: Switch context id allocation directly to xarray IDR internally uses xarray so we can use it directly which simplifies our code by removing the need to do external locking. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@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/20191224095920.2386297-1-chris@chris-wilson.co.uk
2019-12-24 09:59:20 +00:00
u32 id;
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
if (!DRIVER_CAPS(i915)->has_logical_contexts)
return -ENODEV;
if (args->flags & I915_CONTEXT_CREATE_FLAGS_UNKNOWN)
return -EINVAL;
drm/i915/gt: Use intel_gt as the primary object for handling resets Having taken the first step in encapsulating the functionality by moving the related files under gt/, the next step is to start encapsulating by passing around the relevant structs rather than the global drm_i915_private. In this step, we pass intel_gt to intel_reset.c Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190712192953.9187-1-chris@chris-wilson.co.uk
2019-07-12 19:29:53 +00:00
ret = intel_gt_terminally_wedged(&i915->gt);
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
if (ret)
return ret;
ext_data.fpriv = file->driver_priv;
if (client_is_banned(ext_data.fpriv)) {
drm/i915/gem: initial conversion to new logging macros using coccinelle First pass of conversion to the new struct drm_based device logging macros in the drm/i915/gem directory. This conversion was achieved using the following coccinelle script that transforms based on the existence of a straightforward struct drm_i915_private device: @rule1@ identifier fn, T; @@ fn(struct drm_i915_private *T,...) { <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } @rule2@ identifier fn, T; @@ fn(...) { ... struct drm_i915_private *T = ...; <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } Checkpatch warnings were addressed manually. Acked-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Wambui Karuga <wambui.karugax@gmail.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122125750.9737-2-wambui.karugax@gmail.com
2020-01-22 12:57:49 +00:00
drm_dbg(&i915->drm,
"client %s[%d] banned from creating ctx\n",
current->comm, task_pid_nr(current));
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
return -EIO;
}
drm/i915/gem: Use the proto-context to handle create parameters (v5) This means that the proto-context needs to grow support for engine configuration information as well as setparam logic. Fortunately, we'll be deleting a lot of setparam logic on the primary context shortly so it will hopefully balance out. There's an extra bit of fun here when it comes to setting SSEU and the way it interacts with PARAM_ENGINES. Unfortunately, thanks to SET_CONTEXT_PARAM and not being allowed to pick the order in which we handle certain parameters, we have think about those interactions. v2 (Daniel Vetter): - Add a proto_context_free_user_engines helper - Comment on SSEU in the commit message - Use proto_context_set_persistence in set_proto_ctx_param v3 (Daniel Vetter): - Fix a doc comment - Do an explicit HAS_FULL_PPGTT check in set_proto_ctx_vm instead of relying on pc->vm != NULL. - Handle errors for CONTEXT_PARAM_PERSISTENCE - Don't allow more resetting user engines - Rework initialization of UCONTEXT_PERSISTENCE v4 (Jason Ekstrand): - Move hand-rolled initialization of UCONTEXT_PERSISTENCE to an earlier patch v5 (Jason Ekstrand): - Move proto_context_set_persistence to this patch Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-22-jason@jlekstrand.net
2021-07-08 15:48:26 +00:00
ext_data.pc = proto_context_create(i915, args->flags);
if (IS_ERR(ext_data.pc))
return PTR_ERR(ext_data.pc);
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
if (args->flags & I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS) {
ret = i915_user_extensions(u64_to_user_ptr(args->extensions),
create_extensions,
ARRAY_SIZE(create_extensions),
&ext_data);
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
if (ret)
goto err_pc;
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
}
drm/i915: Finalize contexts in GEM_CONTEXT_CREATE on version 13+ All the proto-context stuff for context creation exists to allow older userspace drivers to set VMs and engine sets via SET_CONTEXT_PARAM. Drivers need to update to use CONTEXT_CREATE_EXT_* for this going forward. Force the issue by blocking the old mechanism on any future hardware generations. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Cc: Carl Zhang <carl.zhang@intel.com> Cc: Michal Mrozek <michal.mrozek@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-31-jason@jlekstrand.net
2021-07-08 15:48:35 +00:00
if (GRAPHICS_VER(i915) > 12) {
struct i915_gem_context *ctx;
/* Get ourselves a context ID */
ret = xa_alloc(&ext_data.fpriv->context_xa, &id, NULL,
xa_limit_32b, GFP_KERNEL);
if (ret)
goto err_pc;
ctx = i915_gem_create_context(i915, ext_data.pc);
if (IS_ERR(ctx)) {
ret = PTR_ERR(ctx);
goto err_pc;
}
proto_context_close(ext_data.pc);
gem_context_register(ctx, ext_data.fpriv, id);
} else {
ret = proto_context_register(ext_data.fpriv, ext_data.pc, &id);
if (ret < 0)
goto err_pc;
}
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
drm/i915: Switch context id allocation directly to xarray IDR internally uses xarray so we can use it directly which simplifies our code by removing the need to do external locking. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@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/20191224095920.2386297-1-chris@chris-wilson.co.uk
2019-12-24 09:59:20 +00:00
args->ctx_id = id;
drm/i915/gem: initial conversion to new logging macros using coccinelle First pass of conversion to the new struct drm_based device logging macros in the drm/i915/gem directory. This conversion was achieved using the following coccinelle script that transforms based on the existence of a straightforward struct drm_i915_private device: @rule1@ identifier fn, T; @@ fn(struct drm_i915_private *T,...) { <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } @rule2@ identifier fn, T; @@ fn(...) { ... struct drm_i915_private *T = ...; <+... ( -DRM_INFO( +drm_info(&T->drm, ...) | -DRM_ERROR( +drm_err(&T->drm, ...) | -DRM_WARN( +drm_warn(&T->drm, ...) | -DRM_DEBUG( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_KMS( +drm_dbg_kms(&T->drm, ...) | -DRM_DEBUG_DRIVER( +drm_dbg(&T->drm, ...) | -DRM_DEBUG_ATOMIC( +drm_dbg_atomic(&T->drm, ...) ) ...+> } Checkpatch warnings were addressed manually. Acked-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Wambui Karuga <wambui.karugax@gmail.com> Signed-off-by: Jani Nikula <jani.nikula@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200122125750.9737-2-wambui.karugax@gmail.com
2020-01-22 12:57:49 +00:00
drm_dbg(&i915->drm, "HW context %d created\n", args->ctx_id);
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
return 0;
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
err_pc:
proto_context_close(ext_data.pc);
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
return ret;
}
int i915_gem_context_destroy_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct drm_i915_gem_context_destroy *args = data;
struct drm_i915_file_private *file_priv = file->driver_priv;
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
struct i915_gem_proto_context *pc;
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
struct i915_gem_context *ctx;
if (args->pad != 0)
return -EINVAL;
if (!args->ctx_id)
return -ENOENT;
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
/* We need to hold the proto-context lock here to prevent races
* with finalize_create_context_locked().
*/
mutex_lock(&file_priv->proto_context_lock);
drm/i915: Switch context id allocation directly to xarray IDR internally uses xarray so we can use it directly which simplifies our code by removing the need to do external locking. Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@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/20191224095920.2386297-1-chris@chris-wilson.co.uk
2019-12-24 09:59:20 +00:00
ctx = xa_erase(&file_priv->context_xa, args->ctx_id);
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
pc = xa_erase(&file_priv->proto_context_xa, args->ctx_id);
mutex_unlock(&file_priv->proto_context_lock);
if (!ctx && !pc)
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
return -ENOENT;
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
GEM_WARN_ON(ctx && pc);
if (pc)
proto_context_close(pc);
if (ctx)
context_close(ctx);
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
return 0;
}
static int get_sseu(struct i915_gem_context *ctx,
struct drm_i915_gem_context_param *args)
{
struct drm_i915_gem_context_param_sseu user_sseu;
struct intel_context *ce;
drm/i915: Extend I915_CONTEXT_PARAM_SSEU to support local ctx->engine[] Allow the user to specify a local engine index (as opposed to class:index) that they can use to refer to a preset engine inside the ctx->engine[] array defined by an earlier I915_CONTEXT_PARAM_ENGINES. This will be useful for setting SSEU parameters on virtual engines that are local to the context and do not have a valid global class:instance lookup. Note that due to the ambiguity in using class:instance with ctx->engines[], if a user supplied engine map is active the user must specify the engine to alter by its index into the ctx->engines[]. 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/20190521211134.16117-3-chris@chris-wilson.co.uk
2019-05-21 21:11:27 +00:00
unsigned long lookup;
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
int err;
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
if (args->size == 0)
goto out;
else if (args->size < sizeof(user_sseu))
return -EINVAL;
if (copy_from_user(&user_sseu, u64_to_user_ptr(args->value),
sizeof(user_sseu)))
return -EFAULT;
drm/i915: Extend I915_CONTEXT_PARAM_SSEU to support local ctx->engine[] Allow the user to specify a local engine index (as opposed to class:index) that they can use to refer to a preset engine inside the ctx->engine[] array defined by an earlier I915_CONTEXT_PARAM_ENGINES. This will be useful for setting SSEU parameters on virtual engines that are local to the context and do not have a valid global class:instance lookup. Note that due to the ambiguity in using class:instance with ctx->engines[], if a user supplied engine map is active the user must specify the engine to alter by its index into the ctx->engines[]. 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/20190521211134.16117-3-chris@chris-wilson.co.uk
2019-05-21 21:11:27 +00:00
if (user_sseu.rsvd)
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
return -EINVAL;
drm/i915: Extend I915_CONTEXT_PARAM_SSEU to support local ctx->engine[] Allow the user to specify a local engine index (as opposed to class:index) that they can use to refer to a preset engine inside the ctx->engine[] array defined by an earlier I915_CONTEXT_PARAM_ENGINES. This will be useful for setting SSEU parameters on virtual engines that are local to the context and do not have a valid global class:instance lookup. Note that due to the ambiguity in using class:instance with ctx->engines[], if a user supplied engine map is active the user must specify the engine to alter by its index into the ctx->engines[]. 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/20190521211134.16117-3-chris@chris-wilson.co.uk
2019-05-21 21:11:27 +00:00
if (user_sseu.flags & ~(I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX))
return -EINVAL;
lookup = 0;
if (user_sseu.flags & I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX)
lookup |= LOOKUP_USER_INDEX;
ce = lookup_user_engine(ctx, lookup, &user_sseu.engine);
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
if (IS_ERR(ce))
return PTR_ERR(ce);
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
err = intel_context_lock_pinned(ce); /* serialises with set_sseu */
if (err) {
intel_context_put(ce);
return err;
}
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
user_sseu.slice_mask = ce->sseu.slice_mask;
user_sseu.subslice_mask = ce->sseu.subslice_mask;
user_sseu.min_eus_per_subslice = ce->sseu.min_eus_per_subslice;
user_sseu.max_eus_per_subslice = ce->sseu.max_eus_per_subslice;
drm/i915: Pass intel_context to intel_context_pin_lock() Move the intel_context_instance() to the caller so that we can decouple ourselves from one context instance per engine. v2: Rename pin_lock() to lock_pinned(), hopefully that is clearer. 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/20190426163336.15906-5-chris@chris-wilson.co.uk
2019-04-26 16:33:32 +00:00
intel_context_unlock_pinned(ce);
intel_context_put(ce);
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
if (copy_to_user(u64_to_user_ptr(args->value), &user_sseu,
sizeof(user_sseu)))
return -EFAULT;
out:
args->size = sizeof(user_sseu);
return 0;
}
int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct drm_i915_file_private *file_priv = file->driver_priv;
struct drm_i915_gem_context_param *args = data;
struct i915_gem_context *ctx;
int ret = 0;
ctx = i915_gem_context_lookup(file_priv, args->ctx_id);
drm/i915/gem: Return an error ptr from context_lookup We're about to start doing lazy context creation which means contexts get created in i915_gem_context_lookup and we may start having more errors than -ENOENT. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-23-jason@jlekstrand.net
2021-07-08 15:48:27 +00:00
if (IS_ERR(ctx))
return PTR_ERR(ctx);
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
switch (args->param) {
case I915_CONTEXT_PARAM_GTT_SIZE:
args->size = 0;
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
rcu_read_lock();
if (rcu_access_pointer(ctx->vm))
args->value = rcu_dereference(ctx->vm)->total;
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
else
args->value = to_i915(dev)->ggtt.vm.total;
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
rcu_read_unlock();
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
break;
case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
args->size = 0;
args->value = i915_gem_context_no_error_capture(ctx);
break;
case I915_CONTEXT_PARAM_BANNABLE:
args->size = 0;
args->value = i915_gem_context_is_bannable(ctx);
break;
case I915_CONTEXT_PARAM_RECOVERABLE:
args->size = 0;
args->value = i915_gem_context_is_recoverable(ctx);
break;
case I915_CONTEXT_PARAM_PRIORITY:
args->size = 0;
drm/i915: Remove I915_USER_PRIORITY_SHIFT As we do not have any internal priority levels, the priority can be set directed from the user values. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Andi Shyti <andi.shyti@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210120121439.17600-2-chris@chris-wilson.co.uk Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2021-01-20 12:14:39 +00:00
args->value = ctx->sched.priority;
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
break;
case I915_CONTEXT_PARAM_SSEU:
ret = get_sseu(ctx, args);
break;
case I915_CONTEXT_PARAM_VM:
drm/i915: Avoid using ctx->file_priv during construction As we only set ctx->file_priv on registering the GEM context after construction, it is invalid to try and use it in the middle for setting various parameters. Indeed, we put the file_priv into struct create_ext so that we have the right file_private available without having to look at ctx->file_priv. However, it helps to use it! Reported-by: Jordan Justen <jordan.l.justen@intel.com> Fixes: b91715417244 ("drm/i915: Extend CONTEXT_CREATE to set parameters upon construction") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Jordan Justen <jordan.l.justen@intel.com> Reviewed-by: Jordan Justen <jordan.l.justen@intel.com> Tested-by: Jordan Justen <jordan.l.justen@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190330100349.30642-1-chris@chris-wilson.co.uk
2019-03-30 10:03:49 +00:00
ret = get_ppgtt(file_priv, ctx, args);
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
break;
drm/i915/gem: Make context persistence optional Our existing behaviour is to allow contexts and their GPU requests to persist past the point of closure until the requests are complete. This allows clients to operate in a 'fire-and-forget' manner where they can setup a rendering pipeline and hand it over to the display server and immediately exit. As the rendering pipeline is kept alive until completion, the display server (or other consumer) can use the results in the future and present them to the user. The compute model is a little different. They have little to no buffer sharing between processes as their kernels tend to operate on a continuous stream, feeding the results back to the client application. These kernels operate for an indeterminate length of time, with many clients wishing that the kernel was always running for as long as they keep feeding in the data, i.e. acting like a DSP. Not all clients want this persistent "desktop" behaviour and would prefer that the contexts are cleaned up immediately upon closure. This ensures that when clients are run without hangchecking (e.g. for compute kernels of indeterminate runtime), any GPU hang or other unexpected workloads are terminated with the process and does not continue to hog resources. The default behaviour for new contexts is the legacy persistence mode, as some desktop applications are dependent upon the existing behaviour. New clients will have to opt in to immediate cleanup on context closure. If the hangchecking modparam is disabled, so is persistent context support -- all contexts will be terminated on closure. We expect this behaviour change to be welcomed by compute users, who have often been caught between a rock and a hard place. They disable hangchecking to avoid their kernels being "unfairly" declared hung, but have also experienced true hangs that the system was then unable to clean up. Naturally, this leads to bug reports. Testcase: igt/gem_ctx_persistence Link: https://github.com/intel/compute-runtime/pull/228 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Michał Winiarski <michal.winiarski@intel.com> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Acked-by: Jason Ekstrand <jason@jlekstrand.net> Link: https://patchwork.freedesktop.org/patch/msgid/20191029202338.8841-1-chris@chris-wilson.co.uk
2019-10-29 20:23:38 +00:00
case I915_CONTEXT_PARAM_PERSISTENCE:
args->size = 0;
args->value = i915_gem_context_is_persistent(ctx);
break;
drm/i915: Drop I915_CONTEXT_PARAM_NO_ZEROMAP The idea behind this param is to support OpenCL drivers with relocations because OpenCL reserves 0x0 for NULL and, if we placed memory there, it would confuse CL kernels. It was originally sent out as part of a patch series including libdrm [1] and Beignet [2] support. However, the libdrm and Beignet patches never landed in their respective upstream projects so this API has never been used. It's never been used in Mesa or any other driver, either. Dropping this API allows us to delete a small bit of code. [1]: https://lists.freedesktop.org/archives/intel-gfx/2015-May/067030.html [2]: https://lists.freedesktop.org/archives/intel-gfx/2015-May/067031.html Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-4-jason@jlekstrand.net
2021-07-08 15:48:08 +00:00
case I915_CONTEXT_PARAM_NO_ZEROMAP:
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
case I915_CONTEXT_PARAM_BAN_PERIOD:
drm/i915: Drop getparam support for I915_CONTEXT_PARAM_ENGINES This has never been used by any userspace except IGT and provides no real functionality beyond parroting back parameters userspace passed in as part of context creation or via setparam. If the context is in legacy mode (where you use I915_EXEC_RENDER and friends), it returns success with zero data so it's not useful for discovering what engines are in the context. It's also not a replacement for the recently removed I915_CONTEXT_CLONE_ENGINES because it doesn't return any of the balancing or bonding information. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-9-jason@jlekstrand.net
2021-07-08 15:48:13 +00:00
case I915_CONTEXT_PARAM_ENGINES:
drm/i915: Drop I915_CONTEXT_PARAM_RINGSIZE This reverts commit 88be76cdafc7 ("drm/i915: Allow userspace to specify ringsize on construction"). This API was originally added for OpenCL but the compute-runtime PR has sat open for a year without action so we can still pull it out if we want. I argue we should drop it for three reasons: 1. If the compute-runtime PR has sat open for a year, this clearly isn't that important. 2. It's a very leaky API. Ring size is an implementation detail of the current execlist scheduler and really only makes sense there. It can't apply to the older ring-buffer scheduler on pre-execlist hardware because that's shared across all contexts and it won't apply to the GuC scheduler that's in the pipeline. 3. Having userspace set a ring size in bytes is a bad solution to the problem of having too small a ring. There is no way that userspace has the information to know how to properly set the ring size so it's just going to detect the feature and always set it to the maximum of 512K. This is what the compute-runtime PR does. The scheduler in i915, on the other hand, does have the information to make an informed choice. It could detect if the ring size is a problem and grow it itself. Or, if that's too hard, we could just increase the default size from 16K to 32K or even 64K instead of relying on userspace to do it. Let's drop this API for now and, if someone decides they really care about solving this problem, they can do it properly. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-2-jason@jlekstrand.net
2021-07-08 15:48:06 +00:00
case I915_CONTEXT_PARAM_RINGSIZE:
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
default:
ret = -EINVAL;
break;
}
i915_gem_context_put(ctx);
return ret;
}
int i915_gem_context_setparam_ioctl(struct drm_device *dev, void *data,
struct drm_file *file)
{
struct drm_i915_file_private *file_priv = file->driver_priv;
struct drm_i915_gem_context_param *args = data;
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
struct i915_gem_proto_context *pc;
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
struct i915_gem_context *ctx;
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
int ret = 0;
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
mutex_lock(&file_priv->proto_context_lock);
ctx = __context_lookup(file_priv, args->ctx_id);
if (!ctx) {
pc = xa_load(&file_priv->proto_context_xa, args->ctx_id);
drm/i915: Finalize contexts in GEM_CONTEXT_CREATE on version 13+ All the proto-context stuff for context creation exists to allow older userspace drivers to set VMs and engine sets via SET_CONTEXT_PARAM. Drivers need to update to use CONTEXT_CREATE_EXT_* for this going forward. Force the issue by blocking the old mechanism on any future hardware generations. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Cc: Carl Zhang <carl.zhang@intel.com> Cc: Michal Mrozek <michal.mrozek@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-31-jason@jlekstrand.net
2021-07-08 15:48:35 +00:00
if (pc) {
/* Contexts should be finalized inside
* GEM_CONTEXT_CREATE starting with graphics
* version 13.
*/
WARN_ON(GRAPHICS_VER(file_priv->dev_priv) > 12);
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
ret = set_proto_ctx_param(file_priv, pc, args);
drm/i915: Finalize contexts in GEM_CONTEXT_CREATE on version 13+ All the proto-context stuff for context creation exists to allow older userspace drivers to set VMs and engine sets via SET_CONTEXT_PARAM. Drivers need to update to use CONTEXT_CREATE_EXT_* for this going forward. Force the issue by blocking the old mechanism on any future hardware generations. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Cc: Carl Zhang <carl.zhang@intel.com> Cc: Michal Mrozek <michal.mrozek@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-31-jason@jlekstrand.net
2021-07-08 15:48:35 +00:00
} else {
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
ret = -ENOENT;
drm/i915: Finalize contexts in GEM_CONTEXT_CREATE on version 13+ All the proto-context stuff for context creation exists to allow older userspace drivers to set VMs and engine sets via SET_CONTEXT_PARAM. Drivers need to update to use CONTEXT_CREATE_EXT_* for this going forward. Force the issue by blocking the old mechanism on any future hardware generations. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Cc: Jon Bloomfield <jon.bloomfield@intel.com> Cc: Carl Zhang <carl.zhang@intel.com> Cc: Michal Mrozek <michal.mrozek@intel.com> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-31-jason@jlekstrand.net
2021-07-08 15:48:35 +00:00
}
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
}
mutex_unlock(&file_priv->proto_context_lock);
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
drm/i915/gem: Delay context creation (v3) The current context uAPI allows for two methods of setting context parameters: SET_CONTEXT_PARAM and CONTEXT_CREATE_EXT_SETPARAM. The former is allowed to be called at any time while the later happens as part of GEM_CONTEXT_CREATE. Currently, everything settable via one is settable via the other. While some params are fairly simple and setting them on a live context is harmless such as the context priority, others are far trickier such as the VM or the set of engines. In order to swap out the VM, for instance, we have to delay until all current in-flight work is complete, swap in the new VM, and then continue. This leads to a plethora of potential race conditions we'd really rather avoid. In previous patches, we added a i915_gem_proto_context struct which is capable of storing and tracking all such create parameters. This commit delays the creation of the actual context until after the client is done configuring it with SET_CONTEXT_PARAM. From the perspective of the client, it has the same u32 context ID the whole time. From the perspective of i915, however, it's an i915_gem_proto_context right up until the point where we attempt to do something which the proto-context can't handle. Then the real context gets created. This is accomplished via a little xarray dance. When GEM_CONTEXT_CREATE is called, we create a proto-context, reserve a slot in context_xa but leave it NULL, the proto-context in the corresponding slot in proto_context_xa. Then, whenever we go to look up a context, we first check context_xa. If it's there, we return the i915_gem_context and we're done. If it's not, we look in proto_context_xa and, if we find it there, we create the actual context and kill the proto-context. In order for this dance to work properly, everything which ever touches a proto-context is guarded by drm_i915_file_private::proto_context_lock, including context creation. Yes, this means context creation now takes a giant global lock but it can't really be helped and that should never be on any driver's fast-path anyway. v2 (Daniel Vetter): - Commit message grammatical fixes. - Use WARN_ON instead of GEM_BUG_ON - Rename lazy_create_context_locked to finalize_create_context_locked - Rework the control-flow logic in the setparam ioctl - Better documentation all around v3 (kernel test robot): - Make finalize_create_context_locked static Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-25-jason@jlekstrand.net
2021-07-08 15:48:29 +00:00
if (ctx) {
ret = ctx_setparam(file_priv, ctx, args);
i915_gem_context_put(ctx);
}
drm/i915: Extend CONTEXT_CREATE to set parameters upon construction It can be useful to have a single ioctl to create a context with all the initial parameters instead of a series of create + setparam + setparam ioctls. This extension to create context allows any of the parameters to be passed in as a linked list to be applied to the newly constructed context. v2: Make a local copy of user setparam (Tvrtko) v3: Use flags to detect availability of extension interface 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/20190322092325.5883-3-chris@chris-wilson.co.uk
2019-03-22 09:23:24 +00:00
drm/i915: Add ioctl to set per-context parameters Sometimes we wish to tweak how an individual context behaves. Since we always create a context for every filp, this means that individual processes can fine tune their behaviour even if they do not explicitly create a context. The first example parameter here is to enable multi-process GPU testing, but the interface should be able to cope with passing arbitrarily complex parameters. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Testcase: igt/gem_reset_stats/ban-period-* Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2014-12-24 16:13:40 +00:00
return ret;
}
drm/i915: Move get-reset-stats ioctl from intel_uncore.c to i915_gem_context.c The get-reset-stats ioctl reports upon the statistics (number of hangs, be it as a victim or the guilty party) of a particular context. It is semantically better as being part of i915_gem_context.c user interface, as opposed to the hardware level access of intel_uncore.c Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1463137042-9669-1-git-send-email-chris@chris-wilson.co.uk
2016-05-13 10:57:19 +00:00
int i915_gem_context_reset_stats_ioctl(struct drm_device *dev,
void *data, struct drm_file *file)
{
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
struct drm_i915_private *i915 = to_i915(dev);
drm/i915: Move get-reset-stats ioctl from intel_uncore.c to i915_gem_context.c The get-reset-stats ioctl reports upon the statistics (number of hangs, be it as a victim or the guilty party) of a particular context. It is semantically better as being part of i915_gem_context.c user interface, as opposed to the hardware level access of intel_uncore.c Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1463137042-9669-1-git-send-email-chris@chris-wilson.co.uk
2016-05-13 10:57:19 +00:00
struct drm_i915_reset_stats *args = data;
drm/i915: Rename struct intel_context Our goal is to rename the anonymous per-engine struct beneath the current intel_context. However, after a lively debate resolving around the confusion between intel_context_engine and intel_engine_context, the realisation is that the two structs target different users. The outer struct is API / user facing, and so carries the higher level GEM information. The inner struct is hw facing. Thus we want to name the inner struct intel_context and the outer one i915_gem_context. As the first step, we need to rename the current struct: s/struct intel_context/struct i915_gem_context/ which fits much better with its constructors already conveying the i915_gem_context prefix! Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Dave Gordon <david.s.gordon@intel.com> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1464098023-3294-1-git-send-email-chris@chris-wilson.co.uk
2016-05-24 13:53:34 +00:00
struct i915_gem_context *ctx;
drm/i915: Move get-reset-stats ioctl from intel_uncore.c to i915_gem_context.c The get-reset-stats ioctl reports upon the statistics (number of hangs, be it as a victim or the guilty party) of a particular context. It is semantically better as being part of i915_gem_context.c user interface, as opposed to the hardware level access of intel_uncore.c Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1463137042-9669-1-git-send-email-chris@chris-wilson.co.uk
2016-05-13 10:57:19 +00:00
if (args->flags || args->pad)
return -EINVAL;
drm/i915: Stop manually RCU banging in reset_stats_ioctl (v2) As far as I can tell, the only real reason for this is to avoid taking a reference to the i915_gem_context. The cost of those two atomics probably pales in comparison to the cost of the ioctl itself so we're really not buying ourselves anything here. We're about to make context lookup a tiny bit more complicated, so let's get rid of the one hand- rolled case. Some usermode drivers such as our Vulkan driver call GET_RESET_STATS on every execbuf so the perf here could theoretically be an issue. If this ever does become a performance issue for any such userspace drivers, they can use set CONTEXT_PARAM_RECOVERABLE to false and look for -EIO coming from execbuf to check for hangs instead. v2 (Daniel Vetter): - Add a comment in the commit message about recoverable contexts Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-14-jason@jlekstrand.net
2021-07-08 15:48:18 +00:00
ctx = i915_gem_context_lookup(file->driver_priv, args->ctx_id);
drm/i915/gem: Return an error ptr from context_lookup We're about to start doing lazy context creation which means contexts get created in i915_gem_context_lookup and we may start having more errors than -ENOENT. Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-23-jason@jlekstrand.net
2021-07-08 15:48:27 +00:00
if (IS_ERR(ctx))
return PTR_ERR(ctx);
drm/i915: Move get-reset-stats ioctl from intel_uncore.c to i915_gem_context.c The get-reset-stats ioctl reports upon the statistics (number of hangs, be it as a victim or the guilty party) of a particular context. It is semantically better as being part of i915_gem_context.c user interface, as opposed to the hardware level access of intel_uncore.c Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1463137042-9669-1-git-send-email-chris@chris-wilson.co.uk
2016-05-13 10:57:19 +00:00
drm/i915: Enable rcu-only context lookups Whilst the contents of the context is still protected by the big struct_mutex, this is not much of an improvement. It is just one tiny step towards reducing our BKL. 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/20170620110547.15947-3-chris@chris-wilson.co.uk
2017-06-20 11:05:47 +00:00
/*
* We opt for unserialised reads here. This may result in tearing
* in the extremely unlikely event of a GPU hang on this context
* as we are querying them. If we need that extra layer of protection,
* we should wrap the hangstats with a seqlock.
*/
drm/i915: Move get-reset-stats ioctl from intel_uncore.c to i915_gem_context.c The get-reset-stats ioctl reports upon the statistics (number of hangs, be it as a victim or the guilty party) of a particular context. It is semantically better as being part of i915_gem_context.c user interface, as opposed to the hardware level access of intel_uncore.c Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1463137042-9669-1-git-send-email-chris@chris-wilson.co.uk
2016-05-13 10:57:19 +00:00
if (capable(CAP_SYS_ADMIN))
drm/i915: Move context management under GEM Keep track of the GEM contexts underneath i915->gem.contexts and assign them their own lock for the purposes of list management. v2: Focus on lock tracking; ctx->vm is protected by ctx->mutex v3: Correct split with removal of logical HW ID 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/20191004134015.13204-15-chris@chris-wilson.co.uk
2019-10-04 13:40:09 +00:00
args->reset_count = i915_reset_count(&i915->gpu_error);
drm/i915: Move get-reset-stats ioctl from intel_uncore.c to i915_gem_context.c The get-reset-stats ioctl reports upon the statistics (number of hangs, be it as a victim or the guilty party) of a particular context. It is semantically better as being part of i915_gem_context.c user interface, as opposed to the hardware level access of intel_uncore.c Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1463137042-9669-1-git-send-email-chris@chris-wilson.co.uk
2016-05-13 10:57:19 +00:00
else
args->reset_count = 0;
drm/i915: Make i915_gem_context_mark_guilty() safe for unlocked updates Since we make call i915_gem_context_mark_guilty() concurrently when resetting different engines in parallel, we need to make sure that our updates are safe for the unlocked access. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Michel Thierry <michel.thierry@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20170721123238.16428-12-chris@chris-wilson.co.uk Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
2017-07-21 12:32:30 +00:00
args->batch_active = atomic_read(&ctx->guilty_count);
args->batch_pending = atomic_read(&ctx->active_count);
drm/i915: Move get-reset-stats ioctl from intel_uncore.c to i915_gem_context.c The get-reset-stats ioctl reports upon the statistics (number of hangs, be it as a victim or the guilty party) of a particular context. It is semantically better as being part of i915_gem_context.c user interface, as opposed to the hardware level access of intel_uncore.c Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1463137042-9669-1-git-send-email-chris@chris-wilson.co.uk
2016-05-13 10:57:19 +00:00
drm/i915: Stop manually RCU banging in reset_stats_ioctl (v2) As far as I can tell, the only real reason for this is to avoid taking a reference to the i915_gem_context. The cost of those two atomics probably pales in comparison to the cost of the ioctl itself so we're really not buying ourselves anything here. We're about to make context lookup a tiny bit more complicated, so let's get rid of the one hand- rolled case. Some usermode drivers such as our Vulkan driver call GET_RESET_STATS on every execbuf so the perf here could theoretically be an issue. If this ever does become a performance issue for any such userspace drivers, they can use set CONTEXT_PARAM_RECOVERABLE to false and look for -EIO coming from execbuf to check for hangs instead. v2 (Daniel Vetter): - Add a comment in the commit message about recoverable contexts Signed-off-by: Jason Ekstrand <jason@jlekstrand.net> Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch> Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch> Link: https://patchwork.freedesktop.org/patch/msgid/20210708154835.528166-14-jason@jlekstrand.net
2021-07-08 15:48:18 +00:00
i915_gem_context_put(ctx);
return 0;
drm/i915: Move get-reset-stats ioctl from intel_uncore.c to i915_gem_context.c The get-reset-stats ioctl reports upon the statistics (number of hangs, be it as a victim or the guilty party) of a particular context. It is semantically better as being part of i915_gem_context.c user interface, as opposed to the hardware level access of intel_uncore.c Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/1463137042-9669-1-git-send-email-chris@chris-wilson.co.uk
2016-05-13 10:57:19 +00:00
}
drm/i915: Mock infrastructure for request emission Create a fake engine that runs requests using a timer to simulate hw. v2: Prevent leaks of ctx->name along error paths Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/20170213171558.20942-8-chris@chris-wilson.co.uk
2017-02-13 17:15:19 +00:00
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
/* GEM context-engines iterator: for_each_gem_engine() */
struct intel_context *
i915_gem_engines_iter_next(struct i915_gem_engines_iter *it)
{
const struct i915_gem_engines *e = it->engines;
struct intel_context *ctx;
drm/i915/gem: Consolidate ctx->engines[] release Use the same engine_idle_release() routine for cleaning all old ctx->engine[] state, closing any potential races with concurrent execbuf submission. v2ish: Use the ce->pin_count to close the execbuf gap. Closes: https://gitlab.freedesktop.org/drm/intel/issues/1241 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20200303080546.1140508-1-chris@chris-wilson.co.uk
2020-03-03 08:05:44 +00:00
if (unlikely(!e))
return NULL;
drm/i915: Switch back to an array of logical per-engine HW contexts We switched to a tree of per-engine HW context to accommodate the introduction of virtual engines. However, we plan to also support multiple instances of the same engine within the GEM context, defeating our use of the engine as a key to looking up the HW context. Just allocate a logical per-engine instance and always use an index into the ctx->engines[]. Later on, this ctx->engines[] may be replaced by a user specified map. v2: Add for_each_gem_engine() helper to iterator within the engines lock v3: intel_context_create_request() helper v4: s/unsigned long/unsigned int/ 4 billion engines is quite enough. v5: Push iterator locking to caller 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/20190426163336.15906-7-chris@chris-wilson.co.uk
2019-04-26 16:33:34 +00:00
do {
if (it->idx >= e->num_engines)
return NULL;
ctx = e->engines[it->idx++];
} while (!ctx);
return ctx;
}
drm/i915: Mock infrastructure for request emission Create a fake engine that runs requests using a timer to simulate hw. v2: Prevent leaks of ctx->name along error paths Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/20170213171558.20942-8-chris@chris-wilson.co.uk
2017-02-13 17:15:19 +00:00
#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
#include "selftests/mock_context.c"
drm/i915: Live testing for context execution Check we can create and execution within a context. v2: Write one set of dwords through each context/engine to exercise more contexts within the same time period. 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/20170213171558.20942-38-chris@chris-wilson.co.uk
2017-02-13 17:15:49 +00:00
#include "selftests/i915_gem_context.c"
drm/i915: Mock infrastructure for request emission Create a fake engine that runs requests using a timer to simulate hw. v2: Prevent leaks of ctx->name along error paths Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/20170213171558.20942-8-chris@chris-wilson.co.uk
2017-02-13 17:15:19 +00:00
#endif
drm/i915: Make object/vma allocation caches global As our allocations are not device specific, we can move our slab caches to a global scope. 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/20190228102035.5857-2-chris@chris-wilson.co.uk
2019-02-28 10:20:34 +00:00
drm/i915: move gem_context slab to direct module init/exit With the global kmem_cache shrink infrastructure gone there's nothing special and we can convert them over. I'm doing this split up into each patch because there's quite a bit of noise with removing the static global.slab_luts to just a slab_luts. v2: Make slab static (Jason, 0day) Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> Cc: Jason Ekstrand <jason@jlekstrand.net> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210727121037.2041102-5-daniel.vetter@ffwll.ch
2021-07-27 12:10:31 +00:00
void i915_gem_context_module_exit(void)
drm/i915: Make object/vma allocation caches global As our allocations are not device specific, we can move our slab caches to a global scope. 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/20190228102035.5857-2-chris@chris-wilson.co.uk
2019-02-28 10:20:34 +00:00
{
drm/i915: move gem_context slab to direct module init/exit With the global kmem_cache shrink infrastructure gone there's nothing special and we can convert them over. I'm doing this split up into each patch because there's quite a bit of noise with removing the static global.slab_luts to just a slab_luts. v2: Make slab static (Jason, 0day) Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> Cc: Jason Ekstrand <jason@jlekstrand.net> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210727121037.2041102-5-daniel.vetter@ffwll.ch
2021-07-27 12:10:31 +00:00
kmem_cache_destroy(slab_luts);
drm/i915: Make object/vma allocation caches global As our allocations are not device specific, we can move our slab caches to a global scope. 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/20190228102035.5857-2-chris@chris-wilson.co.uk
2019-02-28 10:20:34 +00:00
}
drm/i915: move gem_context slab to direct module init/exit With the global kmem_cache shrink infrastructure gone there's nothing special and we can convert them over. I'm doing this split up into each patch because there's quite a bit of noise with removing the static global.slab_luts to just a slab_luts. v2: Make slab static (Jason, 0day) Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> Cc: Jason Ekstrand <jason@jlekstrand.net> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210727121037.2041102-5-daniel.vetter@ffwll.ch
2021-07-27 12:10:31 +00:00
int __init i915_gem_context_module_init(void)
drm/i915: Make object/vma allocation caches global As our allocations are not device specific, we can move our slab caches to a global scope. 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/20190228102035.5857-2-chris@chris-wilson.co.uk
2019-02-28 10:20:34 +00:00
{
drm/i915: move gem_context slab to direct module init/exit With the global kmem_cache shrink infrastructure gone there's nothing special and we can convert them over. I'm doing this split up into each patch because there's quite a bit of noise with removing the static global.slab_luts to just a slab_luts. v2: Make slab static (Jason, 0day) Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> Cc: Jason Ekstrand <jason@jlekstrand.net> Signed-off-by: Daniel Vetter <daniel.vetter@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20210727121037.2041102-5-daniel.vetter@ffwll.ch
2021-07-27 12:10:31 +00:00
slab_luts = KMEM_CACHE(i915_lut_handle, 0);
if (!slab_luts)
drm/i915: Use i915_global_register() Rather than manually add every new global into each hook, use i915_global_register() function and keep a list of registered globals to invoke instead. However, I haven't found a way for random drivers to add an .init table to avoid having to manually add ourselves to i915_globals_init() each time. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Link: https://patchwork.freedesktop.org/patch/msgid/20190305213830.18094-1-chris@chris-wilson.co.uk Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
2019-03-05 21:38:30 +00:00
return -ENOMEM;
return 0;
drm/i915: Make object/vma allocation caches global As our allocations are not device specific, we can move our slab caches to a global scope. 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/20190228102035.5857-2-chris@chris-wilson.co.uk
2019-02-28 10:20:34 +00:00
}
Reference in New Issue Copy Permalink