Continuing the theme of separating out the GEM clutter.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190528092956.14910-8-chris@chris-wilson.co.uk

Continuing the decluttering of i915_gem.c, that of the read/write
domains, perhaps the biggest of GEM's follies?
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NMatthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190528092956.14910-7-chris@chris-wilson.co.uk

for restore-inhibit context, hardware will not load in-context mmios
(engine context part) to hardware, but hardware will save the mmio
values in hardware back to context image. So, in order to save correct
values of vGPU back to context image, values of vGPU mmios have to be
loaded into hardware first for restore-inhibit context.

In this patch, the mechanism is applied to all gen9 platform.

The reason excluding gen8 platforms is only because of lacking of testing
on those platforms.

v3: for mocs registers, goto in-context mmios save-restore path for skl
platform as well (weinan li)
v2: update vreg when scanning indirect context for inhibit context for
gen9

Cc: Weinan Li <weinan.z.li@intel.com>
Acked-by: NWeinan Li <weinan.z.li@intel.com>
Signed-off-by: NYan Zhao <yan.y.zhao@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

"To track whether a request has started on HW, we can emit a breadcrumb at
the beginning of the request and check its timeline's HWSP to see if the
breadcrumb has advanced past the start of this request." It means all the
request which timeline's has_init_breadcrumb is true, then the
emit_init_breadcrumb process must have before emitting the real commands,
otherwise, the scheduler might get a wrong state of this request during
reset. If the request is exactly the guilty one, the scheduler won't
terminate it with the wrong state. To avoid this, do emit_init_breadcrumb
for all the requests from gvt.

v2: cc to stable kernel

Fixes: 85474441 ("drm/i915: Identify active requests")
Cc: stable@vger.kernel.org
Acked-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: NWeinan <weinan.z.li@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

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: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190426163336.15906-7-chris@chris-wilson.co.uk

We want to pass in a intel_context into intel_context_pin() and that
requires us to first be able to lookup the intel_context!
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190426163336.15906-2-chris@chris-wilson.co.uk

Our eventual goal is to rid request construction of struct_mutex, with
the short term step of lifting the struct_mutex requirements into the
higher levels (i.e. the caller must ensure that the context is already
pinned into the GTT). In this patch, we pin GVT's shadow context upon
allocation and so keep them pinned into the GGTT for as long as the
virtual machine is alive, and so we can use the simpler request
construction path safe in the knowledge that the hard work is already
done.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Acked-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190426163336.15906-1-chris@chris-wilson.co.uk

Typedef is not recommended in the Linux kernel.The klocwork static code
analyzer takes the enumeration as the full range of intel_gvt_gtt_type_t.
But the intel_gvt_gtt_type_t will never be used in full range. For
example, the GTT_TYPE_INVALID will never be used as an index of an array.
Remove the typedef and let the enumeration starts from zero to pass
klocwork analysis.

This patch fixed the critial issues #483, #551, #665 reported by
klockwork.

v3:
- Remove the typedef and let the enumeration starts from zero.
Signed-off-by: NAleksei Gimbitskii <aleksei.gimbitskii@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
CC: Colin Xu <colin.xu@intel.com>
Reviewed-by: NColin Xu <colin.xu@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

We want to use intel_engine_mask_t inside i915_request.h, which means
extracting it from the general header file mess and placing it inside a
types.h. A knock on effect is that the compiler wants to warn about
type-contraction of ALL_ENGINES into intel_engine_maskt_t, so prepare
for the worst.

v2: Use intel_engine_mask_t consistently
v3: Move I915_NUM_ENGINES to its natural home at the end of the enum
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190401162641.10963-1-chris@chris-wilson.co.ukReviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>

in workload creation routine, if any failure occurs, do not queue this
workload for delivery. if this failure is fatal, enter into failsafe
mode.

Fixes: 6d763035 ("drm/i915/gvt: Move common vGPU workload creation into scheduler.c")
Cc: stable@vger.kernel.org #4.19+
Cc: zhenyuw@linux.intel.com
Signed-off-by: NYan Zhao <yan.y.zhao@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

Now that the internal code all works on intel_uncore, flip the
external-facing interface.

v2: fix GVT.
Signed-off-by: NDaniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190319183543.13679-4-daniele.ceraolospurio@intel.com

Large ppGTT are differentiated by the requirement to go to four levels
to address more than 32b. Given the introduction of more 4 level ppGTT
with different sizes of addressable bits, rename i915_vm_is_48b() to
better reflect the commonality of using 4 levels.

Based on a patch by Bob Paauwe.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Bob Paauwe <bob.j.paauwe@intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: NRodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190314223839.28258-4-chris@chris-wilson.co.uk

In the next patch, we are introducing a broad virtual engine to encompass
multiple physical engines, losing the 1:1 nature of BIT(engine->id). To
reflect the broader set of engines implied by the virtual instance, lets
store the full bitmask.

v2: Use intel_engine_mask_t (s/ring_mask/engine_mask/)
v3: Tvrtko voted for moah churn so teach everyone to not mention ring
and use $class$instance throughout.
v4: Comment upon the disparity in bspec for using VCS1,VCS2 in gen8 and
VCS[0-4] in later gen. We opt to keep the code consistent and use
0-index naming throughout.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190305180332.30900-1-chris@chris-wilson.co.uk

This moves ppgtt root hook out of scan and shadow function,
as it's only required at dispatch time. Also make sure this
checks against shadow mm to be ready, otherwise bail to fail
earlier.
Reviewed-by: NXiong Zhang <xiong.y.zhang@intel.com>
Cc: Xiong Zhang <xiong.y.zhang@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

As vGPU shadow ctx is loaded with guest context state, arbitrarily
submitting request in error workload dispatch path would cause trouble.
So don't try to submit in error path now like in previous code.
This is to fix VM failure when GPU hang happens.

Fixes: f0e99437 ("drm/i915/gvt: Fix workload request allocation before request add")
Reviewed-by: NXiong Zhang <xiong.y.zhang@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

There is one corner case that workload_thread may pick and dispatch one
workload of vgpu after it's already deactivated. Below is the scenario:

1. deactive_vgpu got the vgpu_lock, it found pending workload was
submitted, then it released the vgpu_lock and wait for vgpu idle.
2. before deactive_vgpu got the vgpu_lock back, workload_thread might pick
one new valid workload, then it was blocked by the vgpu_lock.
3. deactive_vgpu got the vgpu_lock again, finished the last processes of
deactivating, then release the vgpu_lock.
4. workload_thread got the vgpu_lock, then it will try to dispatch the
fetched workload. It's not expected one workload of deactivated vgpu is
dispatched.

The solution is to add condition check of the vgpu's active flag and stop
to schedule when it's inactive.
Reviewed-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: NWeinan Li <weinan.z.li@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

GVT-g will shadow the privilege batch buffer and the indirect context
during command scan, move the release process into
intel_vgpu_destroy_workload() to ensure the resources are recycled
properly.

Fixes: 0cce2823 ("drm/i915/gvt/kvmgt:Refine error handling for prepare_execlist_workload")
Reviewed-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: NWeinan Li <weinan.z.li@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

The majority of runtime-pm operations are bounded and scoped within a
function; these are easy to verify that the wakeref are handled
correctly. We can employ the compiler to help us, and reduce the number
of wakerefs tracked when debugging, by passing around cookies provided
by the various rpm_get functions to their rpm_put counterpart. This
makes the pairing explicit, and given the required wakeref cookie the
compiler can verify that we pass an initialised value to the rpm_put
(quite handy for double checking error paths).

For regular builds, the compiler should be able to eliminate the unused
local variables and the program growth should be minimal. Fwiw, it came
out as a net improvement as gcc was able to refactor rpm_get and
rpm_get_if_in_use together,

v2: Just s/rpm_put/rpm_put_unchecked/ everywhere, leaving the manual
mark up for smaller more targeted patches.
v3: Mention the cookie in Returns
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: NMika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190114142129.24398-2-chris@chris-wilson.co.uk

Use INTEL_GEN to simplify the code for SKL+ platforms.

v2:
- split the enabling code into final one to identify any regression.

Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Reviewed-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: NFei Jiang <fei.jiang@intel.com>
Signed-off-by: Nfred gao <fred.gao@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

In commit 6bb2a2af ("drm/i915/gvt: Fix crash after request->hw_context change"),
forgot to handle workload scan path in ELSP handler case which was to
optimize scanning earlier instead of in gvt submission thread, so request
alloc and add was splitting then which is against right process.

This trys to do a partial revert of that commit which still has workload
request alloc helper and make sure shadow state population is handled after
request alloc for target state buffer.

v3: Fix missed workload status setting in request alloc error path
v2: Fix dispatch workload err path that should add request after alloc anyway.

Fixes: 6bb2a2af ("drm/i915/gvt: Fix crash after request->hw_context change")
Cc: Bin Yang <bin.yang@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Tested-by: NBin Yang <bin.yang@intel.com>
Reviewed-by: NXiaolin Zhang <xiaolin.zhang@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

Recently gvt shadow ctx create ppgtt table and this ppgtt's root
pointer is modified at workload dispatch, then we lose the original
ppgtt's root pointer, this causes the ppgtt destroy function abnormal
as it will release the wrong root table.

This patch save i915 context ppgtt root pointer at shadow
ctx creation and restore it at shadow ctx destruction.

v2: Split save and restore function (Zhenyu)

Fixes:4f15665c("drm/i915: Add ppgtt to GVT GEM context")
Signed-off-by: NXiong Zhang <xiong.y.zhang@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

Currently the guest couldn't boot up under GVT-g environment as the
following call trace exists:
[  272.504762] BUG: unable to handle kernel NULL pointer dereference at 0000000000000100
[  272.504834] Call Trace:
[  272.504852]  execlists_context_pin+0x2b2/0x520 [i915]
[  272.504869]  intel_gvt_scan_and_shadow_workload+0x50/0x4d0 [i915]
[  272.504887]  intel_vgpu_create_workload+0x3e2/0x570 [i915]
[  272.504901]  intel_vgpu_submit_execlist+0xc0/0x2a0 [i915]
[  272.504916]  elsp_mmio_write+0xc7/0x130 [i915]
[  272.504930]  intel_vgpu_mmio_reg_rw+0x24a/0x4c0 [i915]
[  272.504944]  intel_vgpu_emulate_mmio_write+0xac/0x240 [i915]
[  272.504947]  intel_vgpu_rw+0x22d/0x270 [kvmgt]
[  272.504949]  intel_vgpu_write+0x164/0x1f0 [kvmgt]

GVT GEM context is created by i915_gem_context_create_gvt() which
doesn't allocate ppgtt. So GVT GEM context structure doesn't have
a valid i915_hw_ppgtt.

This patch create ppgtt table at GVT GEM context creation, then assign
shadow ppgtt's root table address to this ppgtt when shadow ppgtt will
be used on GPU. So GVT GEM context has valid ppgtt address. But note
that this ppgtt only contain valid ppgtt root table address, the table
entry in this ppgtt structure are invalid.

Fixes:4a3d3f67("drm/i915: Match code to comment and enforce ppgtt for execlists")
Signed-off-by: NXiong Zhang <xiong.y.zhang@intel.com>
Reviewed-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/1539841231-3157-1-git-send-email-xiong.y.zhang@intel.com

Some workloads may be prepared in vgpu's queue but not be scheduled
to run yet. If vgpu is released at this time, they will not be freed
in workload complete callback and so need to be freed in vgpu release
operation.

Add new vgpu_release operation in gvt_ops to stop vgpu and release
runtime resources. gvt_ops vgpu_deactivate operation will only stop
vgpu.

v2: add new gvt ops to clean vgpu running status (Xiong Zhang)
Signed-off-by: NHang Yuan <hang.yuan@linux.intel.com>
Reviewed-by: NXiong Zhang <xiong.y.zhang@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

Caught by W=1 to fix left wrong function comment doc.
Reviewed-by: NHang Yuan <hang.yuan@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

if a context is a restore inhibit context, gfx hw only load the first page
for ring context, so we only need to copy from guest the 1 page too.

v3: use "return" instead of "goto" for inhibit case. (zhenyu wang)
v2: move judgement of restore inhibit to a macro in  mmio_context.h
Signed-off-by: NZhao Yan <yan.y.zhao@intel.com>
Acked-by: NHang Yuan <hang.yuan@linux.intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

Handling such a late error in request construction is tricky, but to
accommodate future patches which may allocate here, we potentially could
err. To handle the error after already adjusting global state to track
the new request, we must finish and submit the request. But we don't
want to use the request as not everything is being tracked by it, so we
opt to cancel the commands inside the request.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706103947.15919-3-chris@chris-wilson.co.uk

BXT forcewake is handled in the same way as SKL/KBL.

v2: Add missing inhibit_context restore for BXT.
Signed-off-by: NColin Xu <colin.xu@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

Array 'pdp_pair' of size 1 may use index value(s) 1..7.
Changed to pdps[8] to avoid confusion.
Signed-off-by: NXinyun Liu <xinyun.liu@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

When we do shadowing, workload's request might not be allocated yet,
so we still require shadow context's object. And when complete workload,
delay to zero workload's request pointer after used for update guest context.

v2: Move request alloc earlier as already try to track shadow status
depending on request state, which also facilitate to use request->hw_context
for target engine context reference.

Fixes: 1fc44d9b ("drm/i915: Store a pointer to intel_context in i915_request")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Cc: Weinan Li <weinan.z.li@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180521081752.31056-1-zhenyuw@linux.intel.com

To ease the frequent and ugly pointer dance of
&request->gem_context->engine[request->engine->id] during request
submission, store that pointer as request->hw_context. One major
advantage that we will exploit later is that this decouples the logical
context state from the engine itself.

v2: Set mock_context->ops so we don't crash and burn in selftests.
    Cleanups from Tvrtko.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Acked-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517212633.24934-3-chris@chris-wilson.co.uk

In the next patch, we want to store the intel_context pointer inside
i915_request, as it is frequently access via a convoluted dance when
submitting the request to hw. Having two context pointers inside
i915_request leads to confusion so first rename the existing
i915_gem_context pointer to i915_request.gem_context.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517212633.24934-1-chris@chris-wilson.co.uk

The scheduler lock(gvt->sched_lock) is used to protect gvt
scheduler logic, including the gvt scheduler structure(gvt->scheduler
and per vgpu schedule data(vgpu->sched_data, vgpu->sched_ctl).

v9:
  - Change commit author since the patches are improved a lot compared
    with original version.
    Original author: Pei Zhang <pei.zhang@intel.com>
  - Rebase to latest gvt-staging.
v8:
  - Correct coding wqstyle.
  - Rebase to latest gvt-staging.
v7:
  - Remove gtt_lock since already proteced by gvt_lock and vgpu_lock.
v6:
  - Rebase to latest gvt-staging.
v5:
  - Rebase to latest gvt-staging.
v4:
  - Rebase to latest gvt-staging.
v3: update to latest code base
Signed-off-by: NPei Zhang <pei.zhang@intel.com>
Signed-off-by: NColin Xu <colin.xu@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

The patch set splits out 2 small locks from the original big gvt lock:
  - vgpu_lock protects per-vGPU data and logic, especially the vGPU
    trap emulation path.
  - sched_lock protects gvt scheudler structure, context schedule logic
    and vGPU's schedule data.

Use vgpu_lock to replace the gvt big lock. By doing this, the
mmio read/write trap path, vgpu virtual event emulation and other
vgpu related process, would be protected under per vgpu_lock.

v9:
  - Change commit author since the patches are improved a lot compared
    with original version.
    Original author: Pei Zhang <pei.zhang@intel.com>
  - Rebase to latest gvt-staging.
v8:
  - Correct coding and comment style.
  - Rebase to latest gvt-staging.
v7:
  - Remove gtt_lock since already proteced by gvt_lock and vgpu_lock.
  - Fix a typo in intel_gvt_deactivate_vgpu, unlock the wrong lock.
v6:
  - Rebase to latest gvt-staging.
v5:
  - Rebase to latest gvt-staging.
  - intel_vgpu_page_track_handler should use vgpu_lock.
v4:
  - Rebase to latest gvt-staging.
  - Protect vgpu->active access with vgpu_lock.
  - Do not wait gpu idle in vgpu_lock.
v3: update to latest code base
v2: add gvt->lock in function gvt_check_vblank_emulation

Performance comparison on Kabylake platform.
  - Configuration:
    Host: Ubuntu 16.04.
    Guest 1 & 2: Ubuntu 16.04.

glmark2 score comparison:
  - Configuration:
    Host: glxgears.
    Guests: glmark2.
+--------------------------------+-----------------+
| Setup                          | glmark2 score   |
+--------------------------------+-----------------+
| unified lock, iommu=on         | 58~62 (avg. 60) |
+--------------------------------+-----------------+
| unified lock, iommu=igfx_off   | 57~61 (avg. 59) |
+--------------------------------+-----------------+
| per-logic lock, iommu=on       | 60~68 (avg. 64) |
+--------------------------------+-----------------+
| per-logic lock, iommu=igfx_off | 61~67 (avg. 64) |
+--------------------------------+-----------------+

lock_stat comparison:
  - Configuration:
    Stop lock stat immediately after boot up.
    Boot 2 VM Guests.
    Run glmark2 in guests.
    Start perf lock_stat for 20 seconds and stop again.
  - Legend: c - contentions; w - waittime-avg
+------------+-----------------+-----------+---------------+------------+
|            | gvt_lock        |sched_lock | vgpu_lock     | gtt_lock   |
+ lock type; +-----------------+-----------+---------------+------------+
| iommu set  | c     | w       | c  | w    | c    | w      | c   | w    |
+------------+-------+---------+----+------+------+--------+-----+------+
| unified;   | 20697 | 839     |N/A | N/A  | N/A  | N/A    | N/A | N/A  |
| on         |       |         |    |      |      |        |     |      |
+------------+-------+---------+----+------+------+--------+-----+------+
| unified;   | 21838 | 658.15  |N/A | N/A  | N/A  | N/A    | N/A | N/A  |
| igfx_off   |       |         |    |      |      |        |     |      |
+------------+-------+---------+----+------+------+--------+-----+------+
| per-logic; | 1553  | 1599.96 |9458|429.97| 5846 | 274.33 | 0   | 0.00 |
| on         |       |         |    |      |      |        |     |      |
+------------+-------+---------+----+------+------+--------+-----+------+
| per-logic; | 1911  | 1678.32 |8335|445.16| 5451 | 244.80 | 0   | 0.00 |
| igfx_off   |       |         |    |      |      |        |     |      |
+------------+-------+---------+----+------+------+--------+-----+------+
Signed-off-by: NPei Zhang <pei.zhang@intel.com>
Signed-off-by: NColin Xu <colin.xu@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>

This reverts commit 11474e90.

There are issues which will block the host preemption before, instead of
disabling it use one workaround "setting max priority for gvt context"
to avoid the gvt context be preempted by the host. Now the issues have been
cleared, so revert this patch to enable host preemption.

v2:
- refine description(Zhenyu)
Signed-off-by: NWeinan Li <weinan.z.li@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: NZhi Wang <zhi.a.wang@intel.com>

Make life easier in upcoming patches by moving the context_pin and
context_unpin vfuncs into inline helpers.

v2: Fixup mock_engine to mark the context as pinned on use.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180430131503.5375-2-chris@chris-wilson.co.uk

The checks are misleading and not required [1].

[1] https://lkml.org/lkml/2018/3/19/1792

Addresses-Coverity-ID: 1466017
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NGustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: NChris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: NZhi Wang <zhi.a.wang@intel.com>

For perfomance purpose, scanning of non-privileged batch buffer is turned
off by default. But for debugging purpose, it can be turned on via debugfs.
After scanning, we submit the original non-privileged batch buffer into
hardware, so that the scanning is only a peeking window of guest submitted
commands and will not affect the execution results.

v4:
- refine debugfs print format&content (zhenyu wang)
- print engine id instread of engine name to prevent potential memory leak
  in debugfs warning message. (zhenyu wang)

v3:
- change vgpu->scan_nonprivbb from type bool to u32, so it is able to
  selectively turn on/off scanning of non-privileged batch buffer on engine
  level. e.g.
  if vgpu->scan_nonprivbb=3, then it will scan non-privileged batch buffer
  on engine 0 and 1.
- in debugfs interface to set vgpu->scan_nonprivbb, print warning message
  to warn user and explicitly tell state change in kernel log (zhenyu wang)
v2:
- rebase
- update comments for start_gma_offset (henry)
Signed-off-by: NZhao Yan <yan.y.zhao@intel.com>
Reviewed-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: NZhi Wang <zhi.a.wang@intel.com>

Today we only want to pass along the priority to engine->schedule(), but
in the future we want to have much more control over the various aspects
of the GPU during a context's execution, for example controlling the
frequency allowed. As we need an ever growing number of parameters for
scheduling, move those into a struct for convenience.

v2: Move the anonymous struct into its own function for legibility and
ye olde gcc.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NJoonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180418184052.7129-3-chris@chris-wilson.co.uk

Our shadow context content is from guest but with masked control reg like
CTX_CONTEXT_CONTROL, we need to make sure all settings from guest would be set
when this context is on hw, this trys to force mask enable bits for all to
ensure every bits setting would be effective on hw.

One regression found related to once inhibit bit is set, gpu engine are working
on inhibit state until MI_LOAD_REG_IMM command or context image clear inhibit
bit with mask bit set to 1, and val bit set to 0. In gvt-g currently workload
has the highest priority, so gvt-g workload could trigger preempt context
easily, preempt context set inhibit bit, then gvt-g workload is scheduled in,
but gvt-g workload shadow context image usually doesn't set inhibit mask bit,
so gpu is still in inhibit state when gvt workload is running. This caused gpu
hang.
Suggested-by: NZhang, Xiong <xiong.y.zhang@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>
Reviewed-by: NZhang, Xiong <xiong.y.zhang@intel.com>

The PDPs of a shadow page will only be valid after a vGPU mm is pinned.
So the PDPs in the shadow context should be updated then.
Signed-off-by: NZhi Wang <zhi.a.wang@intel.com>
Signed-off-by: NZhenyu Wang <zhenyuw@linux.intel.com>