mirrors/linux
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-05-05 19:24:01 -04:00
Code Issues Packages Projects Releases Wiki Activity
1,281,010 Commits 1 Branch 929 Tags
33991ae8f40a8245f68e8e442766bf9072eaaa2a
Commit Graph

1281010 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Matthew Brost
33991ae8f4 drm/xe: Simplify locking in new_vma 
Rather than acquiring and dropping the VM / BO dma-resv around
xe_vma_create and do the same thing upon adding preempt fences or an
error, hold these locks through the entire new_vma() function.

v2:
 - Rebase (CI)

Cc: Fei Yang <fei.yang@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jagmeet Randhawa <jagmeet.randhawa@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618003859.3239239-1-matthew.brost@intel.com
 2024-06-20 15:33:48 -07:00
Matthew Brost
0d39640ace drm/xe: Invert runnable_state / pending enable check and assert 
Rather than checking for pending enable and asserting runnable_state ==
1 in sched done handler, invert these. This is more robust code taking
action based on the G2H message and asserting KMD tracking state is
correct.

Suggested-by: 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>
Link: https://patchwork.freedesktop.org/patch/msgid/20240614061343.2931649-1-matthew.brost@intel.com
 2024-06-20 15:33:14 -07:00
Michal Wajdeczko
2b79878b07 drm/xe/vf: Custom HuC initialization if VF 
The HuC firmware is loaded and initialized by the PF driver. Make
sure VF driver performs only limited data structure initialization.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619214557.905-10-michal.wajdeczko@intel.com
 2024-06-20 19:49:43 +02:00
Michal Wajdeczko
7875fe7c24 drm/xe/vf: Skip engine ring enabling if VF 
All engines will be correctly initialized by the PF driver.
Moreover, VF drivers can't access related engine registers.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619214557.905-9-michal.wajdeczko@intel.com
 2024-06-20 19:49:42 +02:00
Michal Wajdeczko
ef3fcfe063 drm/xe/vf: Don't use register based TLB invalidation if VF 
VF drivers can only use GuC-based TLB invalidation, as they don't
have access to the related registers. However, VFs shouldn't need
any explicit TLB invalidation before enabling CTB communication,
as there will be an implicit GGTT TLB invalidation issued by the
GuC itself as part of MMIO-based action handling.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619214557.905-8-michal.wajdeczko@intel.com
 2024-06-20 19:49:41 +02:00
Michal Wajdeczko
ecab82af27 drm/xe/vf: Don't support gtidle if VF 
VF drivers can't access any of gtidle control registers as this
functionality is owned by the PF driver.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619214557.905-7-michal.wajdeczko@intel.com
 2024-06-20 19:49:40 +02:00
Michal Wajdeczko
5aa326f528 drm/xe/vf: Don't initialize OA if VF 
We don't support Observation Architecture on the VF device.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Ashutosh Dixit <ashutosh.dixit@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619214557.905-6-michal.wajdeczko@intel.com
 2024-06-20 19:49:39 +02:00
Michal Wajdeczko
f2800572cc drm/xe/vf: Don't change hwe IRQ masks if using memory IRQs 
We currently do not support changing the engine interrupt enable
mask on the per-engine basis when using memory based interrupts.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619214557.905-5-michal.wajdeczko@intel.com
 2024-06-20 19:49:37 +02:00
Michal Wajdeczko
f20535ce1d drm/xe/vf: Don't apply tile workarounds if VF 
The VF drivers can't apply any workarounds as they don't have
access to related registers. Since xe_wa_apply_tile_workarounds()
function is not using RTP yet, we have to add early return.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619214557.905-4-michal.wajdeczko@intel.com
 2024-06-20 19:49:36 +02:00
Michal Wajdeczko
9632dfb0de drm/xe/vf: Don't run any save-restore RTP actions if VF 
There are no RTP save-restore actions applicable for VFs on
current platforms. If any future platform will require some,
we will need to update the RTP framework to support VF_READY
or VF_ONLY actions. In the meantime, just skip all actions if
we are running as VF driver.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619214557.905-3-michal.wajdeczko@intel.com
 2024-06-20 19:49:35 +02:00
Michal Wajdeczko
65336c3fa2 drm/xe/vf: Disable features that do not apply to VFs 
We already maintain several flags that control the availability
of features on a given device. Disable features, like PCODE or
GuC PC or GSC, that do not apply to a VF device.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240620100147.949-1-michal.wajdeczko@intel.com
 2024-06-20 19:49:34 +02:00
Sai Teja Pottumuttu
d35386b3a7 drm/xe/xelpgp: Extend Wa_14019877138 to graphics 12.74 
Wa_14019877138 is also needed for xe_lpgp graphics 12.74

Signed-off-by: Sai Teja Pottumuttu <sai.teja.pottumuttu@intel.com>
Reviewed-by: Shekhar Chauhan <shekhar.chauhan@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619065614.131151-1-sai.teja.pottumuttu@intel.com
 2024-06-20 09:45:00 -07:00
Ashutosh Dixit
93d2d3e4c5 drm/xe/oa: Remove WARN_ON's for unsupported configurations 
The OA ioctl's already have drm_dbg's which are sufficient to tell the user
that OA is not supported on unsupported configurations (execlist mode and
platform gen < 12). Having additional WARN_ON's for these during driver
probe create unnecessary noise. Just remove these WARN_ON's.

Suggested-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619225617.3465899-1-ashutosh.dixit@intel.com
 2024-06-20 09:18:20 -07:00
José Roberto de Souza
3516b2913e drm/xe/oa: Call xe_oa_emit_oa_config() with new config when updating config 
When UMD ask config to be updated, xe_oa_config_locked() was calling
xe_oa_emit_oa_config() that would use stream->oa_config but that is
only changed to the next oa_config after xe_oa_emit_oa_config() finish.
So it was setting the same config for all DRM_XE_PERF_IOCTL_CONFIG
calls.

Cc: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619192854.199289-1-jose.souza@intel.com
 2024-06-20 09:18:17 -07:00
Michal Wajdeczko
cb925d31f0 drm/xe/oa: Fix potential NPD when OA is not initialized 
If oa->xe can be NULL then we shall not use it as a valid pointer.

Fixes: cdf02fe1a9 ("drm/xe/oa/uapi: Add/remove OA config perf ops")
Fixes: b6fd51c621 ("drm/xe/oa/uapi: Define and parse OA stream properties")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Ashutosh Dixit <ashutosh.dixit@intel.com>
Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619175427.861-1-michal.wajdeczko@intel.com
 2024-06-20 09:13:47 -07:00
Michal Wajdeczko
7a893345a4 drm/xe/guc: Move ARAT interrupts enabling to the upload step 
Even though ARAT interrupts are enabled by default, we still want
to keep the code that enables them. But instead doing that in the
CTB enabling step, move this code to the upload step, where we
already setup few other registers related to GuC.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240619163413.817-1-michal.wajdeczko@intel.com
 2024-06-20 11:03:03 +02:00
Michal Wajdeczko
8e7455dd0d drm/xe: Use ttm_uncached for BO with NEEDS_UC flag 
We should honor requested uncached mode also at the TTM layer.
Otherwise, we risk losing updates to the memory based interrupts
source or status vectors, as those require uncached memory.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Acked-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618104947.729-1-michal.wajdeczko@intel.com
 2024-06-19 13:45:16 +02:00
Ashutosh Dixit
cffd77865f drm/xe/oa: Enable Xe2+ overrun mode 
Enable Xe2+ overrun mode. For Xe2+, when overrun mode is enabled, there are
no partial reports at the end of buffer, making the OA buffer effectively a
non-power-of-2 size circular buffer whose size, circ_size, is a multiple of
the report size.

v2: Fix implementation of xe_oa_circ_diff/xe_oa_circ_incr (Umesh)

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-18-ashutosh.dixit@intel.com
 2024-06-18 12:40:45 -07:00
Ashutosh Dixit
3a1fc394ba drm/xe/oa: Changes to OA_TAKEN 
Rename OA_TAKEN to xe_oa_circ_diff, since xe_oa_circ_diff better describes
what the macro actually does. Also convert to function and add xe_oa_stream
arg. These will be used in the following patch.

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-17-ashutosh.dixit@intel.com
 2024-06-18 12:40:44 -07:00
Ashutosh Dixit
70af432b9a drm/xe/oa: Override GuC RC with OA on PVC 
On PVC, a w/a resets RCS/CCS before it goes into RC6. This breaks OA since
OA does not expect engine resets during its use. Fix it by disabling RC6.

v2: Convert to gt oriented error/warn messages (Michal)

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-16-ashutosh.dixit@intel.com
 2024-06-18 12:40:43 -07:00
Ashutosh Dixit
828a8eaf37 drm/xe/oa: Add MMIO trigger support 
Add MMIO trigger support and allow-list required registers for MMIO trigger
use case. Registers are whitelisted for the lifetime of the driver but MMIO
trigger is enabled only for the duration of the stream.

Bspec: 45925, 60340, 61228

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-15-ashutosh.dixit@intel.com
 2024-06-18 12:40:42 -07:00
Ashutosh Dixit
392bf22238 drm/xe/oa/uapi: OA buffer mmap 
Allow the OA buffer to be mmap'd to userspace. This is needed for the MMIO
trigger use case. Even otherwise, with whitelisted OA head/tail ptr
registers, userspace can receive/interpret OA data from the mmap'd buffer
without issuing read()'s on the OA stream fd.

v2: Remove unmap_mapping_range from xe_oa_release (Thomas H)
    Use vm_flags_mod (Umesh)

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Suggested-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-14-ashutosh.dixit@intel.com
 2024-06-18 12:40:41 -07:00
Ashutosh Dixit
dd6b4718c3 drm/xe/oa/uapi: Query OA unit properties 
Implement query for properties of OA units present on a device.

v2: Clean up reserved/pad fields (Umesh)
    Follow the same scheme as other query structs
v3: Skip reporting reserved engines attached to OA units
v4: Expose oa_buf_size via DRM_XE_PERF_IOCTL_INFO (Umesh)
v5: Don't expose capabilities as OR of properties (Umesh)
v6: Add extensions to query output structs: drm_xe_oa_unit,
    drm_xe_query_oa_units and drm_xe_oa_stream_info
v7: Change oa_units[] array to __u64 type

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-13-ashutosh.dixit@intel.com
 2024-06-18 12:40:40 -07:00
Ashutosh Dixit
14e077f800 drm/xe/oa: Add OAC support 
Similar to OAR, allow userspace to execute MI_REPORT_PERF_COUNT on compute
engines of a specified exec queue.

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-12-ashutosh.dixit@intel.com
 2024-06-18 12:40:39 -07:00
Ashutosh Dixit
2f4a730fcd drm/xe/oa: Add OAR support 
Add OAR support to allow userspace to execute MI_REPORT_PERF_COUNT on
render engines. Configuration batches are used to program the OAR unit, as
well as modifying the render engine context image of a specified exec queue
(to have correct register values when that context switches in).

v2: Rename/refactor xe_oa_modify_self (Umesh)
v3: Move IS_MI_LRI_CMD() into xe_oa.c (Michal)

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-11-ashutosh.dixit@intel.com
 2024-06-18 12:40:38 -07:00
Ashutosh Dixit
efb315d0a0 drm/xe/oa/uapi: Read file_operation 
Implement the OA stream read file_operation. Both blocking and non-blocking
reads are supported. As part of read system call, the read copies OA perf
data from the OA buffer to the user buffer, after appending packet headers
for status and data packets.

v2: Drop OA report headers, implement DRM_XE_PERF_IOCTL_STATUS (Umesh)
v3: Introduce 'struct drm_xe_oa_stream_status'
v4: Define oa_status register bitfields (Umesh)
v5: Add extensions to 'struct drm_xe_oa_stream_status'
v6: Minor cleanup, eliminate report32 variable
v7: Use -EIO to signal to userspace to read OASTATUS using
    DRM_XE_PERF_IOCTL_STATUS, change previous sites returning -EIO to
    return -EINVAL
    Make drm_xe_oa_stream_status bits contiguous (Jose, Umesh)
    rmw oa_status bits (Umesh)

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-10-ashutosh.dixit@intel.com
 2024-06-18 12:40:36 -07:00
Ashutosh Dixit
e936f885f1 drm/xe/oa/uapi: Expose OA stream fd 
The OA stream open perf op returns an fd with its own file_operations for
the newly initialized OA stream. These file_operations allow userspace to
enable or disable the stream, as well as apply a different metric
configuration for the OA stream. Userspace can also poll for data
availability. OA stream initialization is completed in this commit by
enabling the OA stream. When sampling is enabled this starts a hrtimer
which periodically checks for data availablility.

v2: Use stream properties for stream reconfiguration with
    DRM_XE_PERF_IOCTL_CONFIG
v3: Hold runtime_pm reference across oa buffer alloc/free
v4: Fix 32 bit build

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-9-ashutosh.dixit@intel.com
 2024-06-18 12:40:35 -07:00
Ashutosh Dixit
1db9a9dc90 drm/xe/oa: OA stream initialization (OAG) 
Implement majority of OA stream initialization (as part of OA stream open)
ioctl). OAG buffer is allocated for receiving perf counter samples from
HW. OAG unit is initialized and the selected OA metric configuration is
programmed into OAG unit HW using a command/batch buffer.

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-8-ashutosh.dixit@intel.com
 2024-06-18 12:40:33 -07:00
Ashutosh Dixit
b6fd51c621 drm/xe/oa/uapi: Define and parse OA stream properties 
Properties for OA streams are specified by user space, when the stream is
opened, as a chain of drm_xe_ext_set_property struct's. Parse and validate
these stream properties.

v2: Remove struct drm_xe_oa_open_param (Harish Chegondi)
    Drop DRM_XE_OA_PROPERTY_POLL_OA_PERIOD_US (Umesh)
    Eliminate comparison with xe_oa_max_sample_rate (Umesh)
    Drop 'struct drm_xe_oa_record_header' (Umesh)
v3: s/DRM_XE_OA_PROPERTY_OA_EXPONENT/ \
    DRM_XE_OA_PROPERTY_OA_PERIOD_EXPONENT/ (Jose)
v4: Fix 32 bit build
v5: Add non-static function kernel doc (Michal)

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-7-ashutosh.dixit@intel.com
 2024-06-18 12:40:32 -07:00
Ashutosh Dixit
cdf02fe1a9 drm/xe/oa/uapi: Add/remove OA config perf ops 
Introduce add/remove config perf ops for OA. OA configurations consist of a
set of event/counter select register address/value pairs. The add_config
perf op validates and stores such configurations and also exposes them in
the metrics sysfs. These configurations will be programmed to OA unit HW
when an OA stream using a configuration is opened. The OA stream can also
switch to other stored configurations.

v2: Start config id's from 1 and other minor review comments (Umesh)
v3: Add 32 bit build
v4: Add kernel doc for non-static functions (Michal)

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-6-ashutosh.dixit@intel.com
 2024-06-18 12:40:31 -07:00
Ashutosh Dixit
a9f905ae7b drm/xe/oa/uapi: Initialize OA units 
Initialize OA unit data struct's for each gt during device probe. Also
assign OA units for hardware engines.

v2: Remove XE_OA_UNIT_OAG/XE_OA_UNIT_OAM_SAMEDIA_0 enum (Umesh)
    Change mtl_oa_base to 0x13000 (Umesh)
v3: Switch to drmm_ functions and other cleanups (Michal)

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-5-ashutosh.dixit@intel.com
 2024-06-18 12:40:29 -07:00
Ashutosh Dixit
67977882a2 drm/xe/oa/uapi: Add OA data formats 
Add and initialize supported OA data formats for various platforms
(including Xe2). User can request OA data in any supported format.

Bspec: 52198, 60942, 61101

v2: Start 'xe_oa_format_name' enum from 0 (Umesh)
    Fix error rewind with OA (Umesh)
v3: Use graphics versions rather than absolute platform names
v4: Add missing kernel doc for struct memebers and enum and other minor
    changes (Michal)

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-4-ashutosh.dixit@intel.com
 2024-06-18 12:40:27 -07:00
Ashutosh Dixit
fe8929bdf8 drm/xe/perf/uapi: Add perf_stream_paranoid sysctl 
Normally only superuser/root can access perf counter data. However,
superuser can set perf_stream_paranoid sysctl to 0 to allow non-privileged
users to also access perf data. perf_stream_paranoid is introduced at the
perf layer to allow different perf stream types to share this access
mechanism.

v2: Add kernel doc for non-static functions (Michal)

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-3-ashutosh.dixit@intel.com
 2024-06-18 12:40:26 -07:00
Ashutosh Dixit
52c2e956dc drm/xe/perf/uapi: "Perf" layer to support multiple perf counter stream types 
In Xe, the plan is to support multiple types of perf counter streams (OA is
only one type of these streams). Rather than introduce NxM ioctls for
these (N perf streams with M ioctl's per perf stream), we decide to
multiplex these (N different stream types and the M ops for each of these
stream types) through a single PERF ioctl. This multiplexing is the purpose
of the PERF layer.

In addition to PERF DRM ioctl's, another set of ioctl's on the PERF fd are
defined. These are expected to be common to different PERF stream types and
therefore defined at the PERF layer itself.

v2: Add param_size to 'struct drm_xe_perf_param' (Umesh)
v3: Rename 'enum drm_xe_perf_ops' to
    'enum drm_xe_perf_ioctls' (Guy Zadicario)
    Add DRM_ prefix to ioctl names to indicate uapi names
v4: Add 'enum drm_xe_perf_op' previously missed out (Guy Zadicario)
v5: Squash the ops and PERF layer patches into a single patch (Umesh)
    Remove param_size from struct 'drm_xe_perf_param' (Umesh)
v6: Add DRM_XE_PERF_IOCTL_STATUS
v7: Add DRM_XE_PERF_IOCTL_INFO
v8: Fix Copyright years, fix DRM_XE_PERF_TYPE_MAX, move '#include
    "xe_perf.h"' to xe_perf.c, add kernel doc (Michal)

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Guy Zadicario <gzadicario@habana.ai>
Acked-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618014609.3233427-2-ashutosh.dixit@intel.com
 2024-06-18 12:40:24 -07:00
Lucas De Marchi
62712be3a4 drm/xe/xe2: Add proper check for media in Wa_14020756599 
A temporary fixup was made in commit 24d0d98af1 ("drm/xe/xe2lpm: Fixup
Wa_14020756599") due to limitations in the RTP infra. Now that RTP has
support for OR condition that change can be removed. RTP now also
supports checking any GT, so use that instead of the more specific
xe_rtp_match_when_media2000() used in that commit.

Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618050044.324454-6-lucas.demarchi@intel.com
 2024-06-18 12:03:30 -07:00
Lucas De Marchi
c8c00286f5 drm/xe/rtp: Add match on any GT 
One surprising factor of GRAPHICS_VERSION()/MEDIA_VERSION() matching for
people adding new WAs is that it implicitly checks that the
graphics/media IP under check is of that specific type and not that the
device contains a media/graphics IP of that version. Add a new
*_ANY_GT() variant that can be used in that case.

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618050044.324454-5-lucas.demarchi@intel.com
 2024-06-18 12:03:29 -07:00
Lucas De Marchi
dc72c52a42 drm/xe/rtp: Allow to OR rules 
Some workarounds started to depend on different set of conditions where
the action should be applied if any of them match. See e.g.
commit 24d0d98af1 ("drm/xe/xe2lpm: Fixup Wa_14020756599"). Add
XE_RTP_MATCH_OR that allows to implement a logical OR for the rules.
Normal precedence applies:

	r1, r2, OR, r3

means

	(r1 AND r2) OR r3

The check is shortcut as soon as a set of conditions match.

v2: Do not match on empty number of rules-other-than-OR evaluated

Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618050044.324454-4-lucas.demarchi@intel.com
 2024-06-18 12:03:28 -07:00
Lucas De Marchi
512660cd1f drm/xe/rtp: Expand max rules/actions per entry 
Having at most 4 rules per entry is already reaching the maximum.
Expand it to 6 to allow for more room. With the addition of OR
condition for rules, this will very soon not be sufficient.

Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618050044.324454-3-lucas.demarchi@intel.com
 2024-06-18 12:03:27 -07:00
Lucas De Marchi
6045473650 drm/xe/rtp: Allow to match 0 sr entries 
If none of the rules match, there should be 0 entries in the sr xarray,
so none of them should have a register matching.

Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240618050044.324454-2-lucas.demarchi@intel.com
 2024-06-18 12:03:27 -07:00
Michal Wajdeczko
f0ccd2d805 drm/xe/vf: Don't touch GuC irq registers if using memory irqs 
On platforms where VFs are using memory based interrupts, we
missed invalid access to no longer existing interrupt registers,
as we keep them marked with XE_REG_OPTION_VF. To fix that just
either setup memirq vectors in GuC or enable legacy interrupts.

Fixes: aef4eb7c7d ("drm/xe/vf: Setup memory based interrupts in GuC")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240617154736.685-1-michal.wajdeczko@intel.com
 2024-06-18 12:33:06 +02:00
Michal Wajdeczko
0e6745de6d drm/xe: Allow const pointer when checking SR-IOV mode 
It seems that more and more parts of the driver code rely on
having only a const pointer to the xe_device. Allow to check
SR-IOV mode in that code as well.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240617122613.553-1-michal.wajdeczko@intel.com
 2024-06-18 10:51:59 +02:00
Francois Dugast
731e46c032 drm/xe/exec_queue: Rename xe_exec_queue::compute to xe_exec_queue::lr 
The properties of this struct are used in long running context so
make that clear by renaming it to lr, in alignment with the rest
of the code.

Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240613170348.723245-1-francois.dugast@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
 2024-06-17 16:46:52 -04:00
Akshata Jahagirdar
5d7612ae20 drm/xe/xe2lpg: Add Wa_14021490052 
Add Wa_14021490052 for Xe2LPG 20.04.

Signed-off-by: Akshata Jahagirdar <akshata.jahagirdar@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240614182455.2370059-2-matthew.d.roper@intel.com
 2024-06-15 21:13:28 -07:00
Michal Wajdeczko
0d2ca8fd28 drm/xe/uc: Fix and start using xe_uc_fw_sanitize() 
Helper xe_uc_fw_sanitize() was defined but never used. First fix
it by properly exiting also from the LOAD_FAIL state, then use it
in GuC and HuC sanitize code.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240613153424.2120-1-michal.wajdeczko@intel.com
 2024-06-14 23:33:22 +02:00
Michal Wajdeczko
97fedf015c drm/xe: Use fixed CCS mode when running in SR-IOV mode 
We don't support changing CCS mode when running in SR-IOV mode yet.
When running as a PF driver just apply default ccs_mode=1 that VF
drivers will assume as already applied and fixed.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240614101415.2208-1-michal.wajdeczko@intel.com
 2024-06-14 23:26:26 +02:00
Francois Dugast
de8390b101 drm/xe/sched_job: Promote xe_sched_job_add_deps() 
Move it out of the xe_migrate compilation unit so it can be re-used in
other places.

Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240614094433.775866-1-francois.dugast@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
 2024-06-14 16:51:43 -04:00
Michal Wajdeczko
8c57c4dc2a drm/xe: Drop duplicated declaration 
The declaration of xe_reg_whitelist_process_engine() function does
not fit into "xe_wa.h" and is already a duplicate.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240613195702.2164-1-michal.wajdeczko@intel.com
 2024-06-14 12:52:46 +02:00
Michal Wajdeczko
6aaf3fd08d drm/xe/vf: Use correct check for being a VF driver 
The IS_SRIOV macro returns true also when we are running as a PF
driver. Use correct IS_SRIOV_VF macro to skip force-wake management.

Fixes: 513ea833c2 ("drm/xe/vf: Ignore force-wake requests if VF")
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Nirmoy Das <nirmoy.das@intel.com>
Reviewed-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240613120749.2032-1-michal.wajdeczko@intel.com
 2024-06-13 20:31:24 +02:00
Matthew Brost
7ddb9403dd drm/xe: Sample ctx timestamp to determine if jobs have timed out 
In GuC TDR sample ctx timestamp to determine if jobs have timed out. The
scheduling enable needs to be toggled to properly sample the timestamp.
If a job has not been running for longer than the timeout period,
re-enable scheduling and restart the TDR.

v2:
 - Use GT clock to msec helper (Umesh, off list)
 - s/ctx_timestamp_job/ctx_job_timestamp
v3:
 - Fix state machine for TDR, mainly decouple sched disable and
   deregister (testing)
 - Rebase (CI)
v4:
 - Fix checkpatch && newline issue (CI)
 - Do not deregister on wedged or unregistered (CI)
 - Fix refcounting bugs (CI)
 - Move devcoredump above VM / kernel job check (John H)
 - Add comment for check_timeout state usage (John H)
 - Assert pending disable not inflight when enabling scheduling (John H)
 - Use enable_scheduling in other scheduling enable code (John H)
 - Add comments on a few steps in TDR (John H)
 - Add assert for timestamp overflow protection (John H)
v6:
 - Use mul_u64_u32_div (CI, checkpath)
 - Change check time to dbg level (Paulo)
 - Add immediate mode to sched disable (inspection)
 - Use xe_gt_* messages (John H)
 - Fix typo in comment (John H)
 - Check timeout before clearing pending disable (Paulo)
v7:
 - Fix ADJUST_FIVE_PERCENT macro (checkpatch)
 - Don't print sched disable failure message on GT reset (John H)
 - Move kernel / VM jobs WARNs near comment (John H)

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240611144053.2805091-12-matthew.brost@intel.com
 2024-06-12 19:14:10 -07:00
Matthew Brost
b47b83ef16 drm/xe: Add killed, banned, or wedged as stick bit during GuC reset 
These bits should be persistent across reset, treat them as such.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240611144053.2805091-11-matthew.brost@intel.com
 2024-06-12 19:10:26 -07:00