Add a new entry in stats to for svm page faults. If CONFIG_DEBUG_FS is
enabled, the count can be viewed with per GT stat debugfs file.
This is similar to what is already in place for vma page faults.
Example output:
cat /sys/kernel/debug/dri/0/gt0/stats
svm_pagefault_count: 6
tlb_inval_count: 78
vma_pagefault_count: 0
vma_pagefault_kb: 0
v2: Fix build with CONFIG_DRM_GPUSVM disabled
v3: Update argument in kernel doc
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250312092749.164232-1-francois.dugast@intel.com
Signed-off-by: Francois Dugast <francois.dugast@intel.com>
In commit 9632dfb0de ("drm/xe/vf: Don't run any save-restore
RTP actions if VF") we disabled processing of all RTP rules if
we were running as a VFs, since many of the RTP actions were
trying to access registers unaccessible for VFs.
This also included all of LRC WA rules, since some of them were
implemented in a way that required RMW pattern.
Now, as we can program LRC WAs without accessing such registers
from the driver, relying on the MI_MATH instruction instead, we
can unblock xe_rtp_process_to_sr() for VFs.
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/20250311105221.1910-1-michal.wajdeczko@intel.com
In a rare situation of thermal limit during resume, GuC can
be slow and run into delays like this:
xe 0000:00:02.0: [drm] GT1: excessive init time: 667ms! \
[status = 0x8002F034, timeouts = 0]
xe 0000:00:02.0: [drm] GT1: excessive init time: \
[freq = 100MHz (req = 800MHz), before = 100MHz, \
perf_limit_reasons = 0x1C001000]
xe 0000:00:02.0: [drm] *ERROR* GT1: GuC PC Start failed
------------[ cut here ]------------
xe 0000:00:02.0: [drm] GT1: Failed to start GuC PC: -EIO
When this happens, it will block entirely the GPU to be used.
So, let's try and with a huge timeout in the hope it comes back.
Also, let's collect some information on how long it is usually
taking on situations like this, so perhaps the time can be tuned
later.
Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250307160307.1093391-1-rodrigo.vivi@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
There's a mismatch on API: while xe_rtp_process_to_sr() processes
entries until an entry without name, the active tracking with
xe_rtp_process_ctx_enable_active_tracking() needs to use the number of
elements. The number of elements is taken everywhere using ARRAY_SIZE(),
but that will have one entry too many. This leads to the following
warning, as reported by lkp:
drivers/gpu/drm/xe/xe_tuning.c: In function 'xe_tuning_dump':
>> include/drm/drm_print.h:228:31: warning: '%s' directive argument is null [-Wformat-overflow=]
228 | drm_printf((printer), "%.*s" fmt, (indent), "\t\t\t\t\tX", ##__VA_ARGS__)
| ^~~~~~
drivers/gpu/drm/xe/xe_tuning.c:226:17: note: in expansion of macro 'drm_printf_indent'
226 | drm_printf_indent(p, 1, "%s\n", engine_tunings[idx].name);
| ^~~~~~~~~~~~~~~~~
That's because it will still process the last entry when tracking the
active tunings. The same issue exists in the WAs. Change
xe_rtp_process_to_sr() to also take the number of elements so the empty
entry can be removed and the warning should go away. Fixing on the
active-tracking side would more fragile as the it would need a `- 1`
everywhere and continue to use a different approach for number of
elements.
Aside from the warning, it's a non-issue as there would always be enough
bits allocated and the last entry would never be active since
xe_rtp_process_to_sr() stops on the sentinel.
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202503021906.P2MwAvyK-lkp@intel.com/
Cc: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306-fix-print-warning-v1-1-979c3dc03c0d@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Migration is implemented with range granularity, with VRAM backing being
a VM private TTM BO (i.e., shares dma-resv with VM). The lifetime of the
TTM BO is limited to when the SVM range is in VRAM (i.e., when a VRAM
SVM range is migrated to SRAM, the TTM BO is destroyed).
The design choice for using TTM BO for VRAM backing store, as opposed to
direct buddy allocation, is as follows:
- DRM buddy allocations are not at page granularity, offering no
advantage over a BO.
- Unified eviction is required (SVM VRAM and TTM BOs need to be able to
evict each other).
- For exhaustive eviction [1], SVM VRAM allocations will almost certainly
require a dma-resv.
- Likely allocation size is 2M which makes of size of BO (872)
acceptable per allocation (872 / 2M == .0004158).
With this, using TTM BO for VRAM backing store seems to be an obvious
choice as it allows leveraging of the TTM eviction code.
Current migration policy is migrate any SVM range greater than or equal
to 64k once.
[1] https://patchwork.freedesktop.org/series/133643/
v2:
- Rebase on latest GPU SVM
- Retry page fault on get pages returning mixed allocation
- Use drm_gpusvm_devmem
v3:
- Use new BO flags
- New range structure (Thomas)
- Hide migration behind Kconfig
- Kernel doc (Thomas)
- Use check_pages_threshold
v4:
- Don't evict partial unmaps in garbage collector (Thomas)
- Use %pe to print errors (Thomas)
- Use %p to print pointers (Thomas)
v5:
- Use range size helper (Thomas)
- Make BO external (Thomas)
- Set tile to NULL for BO creation (Thomas)
- Drop BO mirror flag (Thomas)
- Hold BO dma-resv lock across migration (Auld, Thomas)
v6:
- s/drm_info/drm_dbg (Thomas)
- s/migrated/skip_migrate (Himal)
- Better debug message on VRAM migration failure (Himal)
- Drop return BO from VRAM allocation function (Thomas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-28-matthew.brost@intel.com
Add GPUSVM device memory copy vfunc functions and connect to migration
layer. Used for device memory migration.
v2:
- Allow NULL device pages in xe_svm_copy
- Use new drm_gpusvm_devmem_ops
v3:
- Prefix defines with XE_ (Thomas)
- Change copy chunk size to 8M
- Add a bunch of comments to xe_svm_copy to clarify behavior (Thomas)
- Better commit message (Thomas)
v5:
- s/xe_mem_region/xe_vram_region (Rebase)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-25-matthew.brost@intel.com
uAPI is designed with the use case that only mapping a BO to a malloc'd
address will unbind a CPU-address mirror VMA. Therefore, allowing a
CPU-address mirror VMA to unbind when the GPU has bindings in the range
being unbound does not make much sense. This behavior is not supported,
as it simplifies the code. This decision can always be revisited if a
use case arises.
v3:
- s/arrises/arises (Thomas)
- s/system allocator/GPU address mirror (Thomas)
- Kernel doc (Thomas)
- Newline between function defs (Thomas)
v5:
- Kernel doc (Thomas)
v6:
- Only compile if CONFIG_DRM_GPUSVM selected (CI, Lucas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-18-matthew.brost@intel.com
Add unbind to SVM garbage collector. To facilitate add unbind support
function to VM layer which unbinds a SVM range. Also teach PT layer to
understand unbinds of SVM ranges.
v3:
- s/INVALID_VMA/XE_INVALID_VMA (Thomas)
- Kernel doc (Thomas)
- New GPU SVM range structure (Thomas)
- s/DRM_GPUVA_OP_USER/DRM_GPUVA_OP_DRIVER (Thomas)
v4:
- Use xe_vma_op_unmap_range (Himal)
v5:
- s/PY/PT (Thomas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-17-matthew.brost@intel.com
Add basic SVM garbage collector which destroy a SVM range upon a MMU
UNMAP event. The garbage collector runs on worker or in GPU fault
handler and is required as locks in the path of reclaim are required and
cannot be taken the notifier.
v2:
- Flush garbage collector in xe_svm_close
v3:
- Better commit message (Thomas)
- Kernel doc (Thomas)
- Use list_first_entry_or_null for garbage collector loop (Thomas)
- Don't add to garbage collector if VM is closed (Thomas)
v4:
- Use %pe to print error (Thomas)
v5:
- s/visable/visible (Thomas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-16-matthew.brost@intel.com
Add (re)bind to SVM page fault handler. To facilitate add support
function to VM layer which (re)binds a SVM range. Also teach PT layer to
understand (re)binds of SVM ranges.
v2:
- Don't assert BO lock held for range binds
- Use xe_svm_notifier_lock/unlock helper in xe_svm_close
- Use drm_pagemap dma cursor
- Take notifier lock in bind code to check range state
v3:
- Use new GPU SVM range structure (Thomas)
- Kernel doc (Thomas)
- s/DRM_GPUVA_OP_USER/DRM_GPUVA_OP_DRIVER (Thomas)
v5:
- Kernel doc (Thomas)
v6:
- Only compile if CONFIG_DRM_GPUSVM selected (CI, Lucas)
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Tested-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-15-matthew.brost@intel.com
Add SVM range invalidation vfunc which invalidates PTEs. A new PT layer
function which accepts a SVM range is added to support this. In
addition, add the basic page fault handler which allocates a SVM range
which is used by SVM range invalidation vfunc.
v2:
- Don't run invalidation if VM is closed
- Cycle notifier lock in xe_svm_close
- Drop xe_gt_tlb_invalidation_fence_fini
v3:
- Better commit message (Thomas)
- Add lockdep asserts (Thomas)
- Add kernel doc (Thomas)
- s/change/changed (Thomas)
- Use new GPU SVM range / notifier structures
- Ensure PTEs are zapped / dma mappings are unmapped on VM close (Thomas)
v4:
- Fix macro (Checkpatch)
v5:
- Use range start/end helpers (Thomas)
- Use notifier start/end helpers (Thomas)
v6:
- Use min/max helpers (Himal)
- Only compile if CONFIG_DRM_GPUSVM selected (CI, Lucas)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-13-matthew.brost@intel.com
Clear root PT entry and invalidate entire VM's address space when
closing the VM. Will prevent the GPU from accessing any of the VM's
memory after closing.
v2:
- s/vma/vm in kernel doc (CI)
- Don't nuke migration VM as this occur at driver unload (CI)
v3:
- Rebase and pull into SVM series (Thomas)
- Wait for pending binds (Thomas)
v5:
- Remove xe_gt_tlb_invalidation_fence_fini in error case (Matt Auld)
- Drop local migration bool (Thomas)
v7:
- Add drm_dev_enter/exit protecting invalidation (CI, Matt Auld)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-12-matthew.brost@intel.com
Add SVM init / close / fini to faulting VMs. Minimual implementation
acting as a placeholder for follow on patches.
v2:
- Add close function
v3:
- Better commit message (Thomas)
- Kernel doc (Thomas)
- Update chunk array to be unsigned long (Thomas)
- Use new drm_gpusvm.h header location (Thomas)
- Newlines between functions in xe_svm.h (Thomas)
- Call drm_gpusvm_driver_set_lock in init (Thomas)
v6:
- Only compile if CONFIG_DRM_GPUSVM selected (CI, Lucas)
v7:
- Only select CONFIG_DRM_GPUSVM if DEVICE_PRIVATE (CI)
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306012657.3505757-10-matthew.brost@intel.com
