From: "Ghimiray, Himal Prasad" <himal.prasad.ghimiray@intel.com>
To: Matthew Brost <matthew.brost@intel.com>,
<intel-xe@lists.freedesktop.org>,
<dri-devel@lists.freedesktop.org>
Cc: <apopple@nvidia.com>, <airlied@gmail.com>,
<thomas.hellstrom@linux.intel.com>, <simona.vetter@ffwll.ch>,
<felix.kuehling@amd.com>, <dakr@kernel.org>
Subject: Re: [PATCH v5 29/32] drm/xe: Add SVM debug
Date: Thu, 13 Feb 2025 17:00:44 +0530 [thread overview]
Message-ID: <33cb3eb0-9dd6-4723-afcd-18d76f3e3eff@intel.com> (raw)
In-Reply-To: <20250213021112.1228481-30-matthew.brost@intel.com>
On 13-02-2025 07:41, Matthew Brost wrote:
> Add some useful SVM debug logging fro SVM range which prints the range's
> state.
>
> v2:
> - Update logging with latest structure layout
> v3:
> - Better commit message (Thomas)
> - New range structure (Thomas)
> - s/COLLECTOT/s/COLLECTOR (Thomas)
> v4:
> - Drop partial evict message (Thomas)
> - Use %p for pointers print (Thomas)
>
> Signed-off-by: Matthew Brost <matthew.brost@intel.com>
> Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> ---
> drivers/gpu/drm/xe/xe_pt.c | 8 ++++
> drivers/gpu/drm/xe/xe_svm.c | 84 +++++++++++++++++++++++++++++++++----
> drivers/gpu/drm/xe/xe_svm.h | 2 +
> 3 files changed, 87 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
> index f8d06c70f77d..29ade504e1c1 100644
> --- a/drivers/gpu/drm/xe/xe_pt.c
> +++ b/drivers/gpu/drm/xe/xe_pt.c
> @@ -647,6 +647,7 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
> /* Move this entire thing to xe_svm.c? */
> xe_svm_notifier_lock(xe_vma_vm(vma));
> if (!xe_svm_range_pages_valid(range)) {
> + xe_svm_range_debug(range, "BIND PREPARE - RETRY");
> xe_svm_notifier_unlock(xe_vma_vm(vma));
> return -EAGAIN;
> }
> @@ -655,6 +656,10 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
> range->base.itree.last + 1 - range->base.itree.start,
> &curs);
> is_devmem = xe_res_is_vram(&curs);
> + if (is_devmem)
> + xe_svm_range_debug(range, "BIND PREPARE - DMA VRAM");
> + else
> + xe_svm_range_debug(range, "BIND PREPARE - DMA");
> } else {
> xe_assert(xe, false);
> }
> @@ -1429,10 +1434,13 @@ static int xe_pt_svm_pre_commit(struct xe_migrate_pt_update *pt_update)
> if (op->subop == XE_VMA_SUBOP_UNMAP_RANGE)
> continue;
>
> + xe_svm_range_debug(range, "PRE-COMMIT");
> +
> xe_assert(vm->xe, xe_vma_is_cpu_addr_mirror(op->map_range.vma));
> xe_assert(vm->xe, op->subop == XE_VMA_SUBOP_MAP_RANGE);
>
> if (!xe_svm_range_pages_valid(range)) {
> + xe_svm_range_debug(range, "PRE-COMMIT - RETRY");
> xe_svm_notifier_unlock(vm);
> return -EAGAIN;
> }
> diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
> index ea43dd00d226..8fd1750b5b04 100644
> --- a/drivers/gpu/drm/xe/xe_svm.c
> +++ b/drivers/gpu/drm/xe/xe_svm.c
> @@ -12,6 +12,18 @@
> #include "xe_vm.h"
> #include "xe_vm_types.h"
>
> +static bool xe_svm_range_in_vram(struct xe_svm_range *range)
> +{
> + /* Not reliable without notifier lock */
> + return range->base.flags.has_devmem_pages;
> +}
> +
> +static bool xe_svm_range_has_vram_binding(struct xe_svm_range *range)
> +{
> + /* Not reliable without notifier lock */
> + return xe_svm_range_in_vram(range) && range->tile_present;
> +}
> +
> static struct xe_vm *gpusvm_to_vm(struct drm_gpusvm *gpusvm)
> {
> return container_of(gpusvm, struct xe_vm, svm.gpusvm);
> @@ -37,6 +49,23 @@ static unsigned long xe_svm_range_size(struct xe_svm_range *range)
> return drm_gpusvm_range_size(&range->base);
> }
>
> +#define range_debug(r__, operaton__) \
> + vm_dbg(&range_to_vm(&(r__)->base)->xe->drm, \
> + "%s: asid=%u, gpusvm=%p, vram=%d,%d, seqno=%lu, " \
> + "start=0x%014lx, end=0x%014lx, size=%lu", \
> + (operaton__), range_to_vm(&(r__)->base)->usm.asid, \
> + (r__)->base.gpusvm, \
> + xe_svm_range_in_vram((r__)) ? 1 : 0, \
> + xe_svm_range_has_vram_binding((r__)) ? 1 : 0, \
> + (r__)->base.notifier_seq, \
> + xe_svm_range_start((r__)), xe_svm_range_end((r__)), \
> + xe_svm_range_size((r__)))
> +
> +void xe_svm_range_debug(struct xe_svm_range *range, const char *operation)
> +{
> + range_debug(range, operation);
> +}
> +
> static void *xe_svm_devm_owner(struct xe_device *xe)
> {
> return xe;
> @@ -74,6 +103,8 @@ xe_svm_garbage_collector_add_range(struct xe_vm *vm, struct xe_svm_range *range,
> {
> struct xe_device *xe = vm->xe;
>
> + range_debug(range, "GARBAGE COLLECTOR ADD");
> +
> drm_gpusvm_range_set_unmapped(&range->base, mmu_range);
>
> spin_lock(&vm->svm.garbage_collector.lock);
> @@ -99,10 +130,14 @@ xe_svm_range_notifier_event_begin(struct xe_vm *vm, struct drm_gpusvm_range *r,
>
> xe_svm_assert_in_notifier(vm);
>
> + range_debug(range, "NOTIFIER");
> +
> /* Skip if already unmapped or if no binding exist */
> if (range->base.flags.unmapped || !range->tile_present)
> return 0;
>
> + range_debug(range, "NOTIFIER - EXECUTE");
> +
> /* Adjust invalidation to range boundaries */
> if (xe_svm_range_start(range) < mmu_range->start)
> *adj_start = xe_svm_range_start(range);
> @@ -155,6 +190,11 @@ static void xe_svm_invalidate(struct drm_gpusvm *gpusvm,
>
> xe_svm_assert_in_notifier(vm);
>
> + vm_dbg(&gpusvm_to_vm(gpusvm)->xe->drm,
> + "INVALIDATE: asid=%u, gpusvm=%p, seqno=%lu, start=0x%016lx, end=0x%016lx, event=%d",
> + vm->usm.asid, gpusvm, notifier->notifier.invalidate_seq,
> + mmu_range->start, mmu_range->end, mmu_range->event);
> +
> /* Adjust invalidation to notifier boundaries */
> if (adj_start < drm_gpusvm_notifier_start(notifier))
> adj_start = drm_gpusvm_notifier_start(notifier);
> @@ -241,6 +281,8 @@ static int __xe_svm_garbage_collector(struct xe_vm *vm,
> {
> struct dma_fence *fence;
>
> + range_debug(range, "GARBAGE COLLECTOR");
> +
> xe_vm_lock(vm, false);
> fence = xe_vm_range_unbind(vm, range);
> xe_vm_unlock(vm);
> @@ -400,16 +442,23 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
> int incr = (match && last) ? 1 : 0;
>
> if (vram_addr != XE_VRAM_ADDR_INVALID) {
> - if (sram)
> + if (sram) {
> + vm_dbg(&tile->xe->drm,
> + "COPY TO SRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld",
> + vram_addr, dma_addr[pos], i - pos + incr);
> __fence = xe_migrate_from_vram(tile->migrate,
> i - pos + incr,
> vram_addr,
> dma_addr + pos);
> - else
> + } else {
> + vm_dbg(&tile->xe->drm,
> + "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%ld",
> + dma_addr[pos], vram_addr, i - pos + incr);
> __fence = xe_migrate_to_vram(tile->migrate,
> i - pos + incr,
> dma_addr + pos,
> vram_addr);
> + }
> if (IS_ERR(__fence)) {
> err = PTR_ERR(__fence);
> goto err_out;
> @@ -429,14 +478,21 @@ static int xe_svm_copy(struct page **pages, dma_addr_t *dma_addr,
>
> /* Extra mismatched device page, copy it */
> if (!match && last && vram_addr != XE_VRAM_ADDR_INVALID) {
> - if (sram)
> + if (sram) {
> + vm_dbg(&tile->xe->drm,
> + "COPY TO SRAM - 0x%016llx -> 0x%016llx, NPAGES=%d",
> + vram_addr, dma_addr[pos], 1);
> __fence = xe_migrate_from_vram(tile->migrate, 1,
> vram_addr,
> dma_addr + pos);
> - else
> + } else {
> + vm_dbg(&tile->xe->drm,
> + "COPY TO VRAM - 0x%016llx -> 0x%016llx, NPAGES=%d",
> + dma_addr[pos], vram_addr, 1);
> __fence = xe_migrate_to_vram(tile->migrate, 1,
> dma_addr + pos,
> vram_addr);
> + }
> if (IS_ERR(__fence)) {
> err = PTR_ERR(__fence);
> goto err_out;
> @@ -613,6 +669,8 @@ static struct xe_bo *xe_svm_alloc_vram(struct xe_vm *vm, struct xe_tile *tile,
> ktime_t end = 0;
> int err;
>
> + range_debug(range, "ALLOCATE VRAM");
> +
> if (!mmget_not_zero(mm))
> return ERR_PTR(-EFAULT);
> mmap_read_lock(mm);
> @@ -716,6 +774,8 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
> if (xe_svm_range_is_valid(range, tile))
> return 0;
>
> + range_debug(range, "PAGE FAULT");
> +
> /* XXX: Add migration policy, for now migrate range once */
> if (!range->migrated && range->base.flags.migrate_devmem &&
> xe_svm_range_size(range) >= SZ_64K) {
> @@ -731,18 +791,26 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
> }
> }
>
> + range_debug(range, "GET PAGES");
> err = drm_gpusvm_range_get_pages(&vm->svm.gpusvm, r, &ctx);
> /* Corner where CPU mappings have changed */
> if (err == -EOPNOTSUPP || err == -EFAULT || err == -EPERM) {
> - if (err == -EOPNOTSUPP)
> + if (err == -EOPNOTSUPP) {
> + range_debug(range, "PAGE FAULT - EVICT PAGES");
> drm_gpusvm_range_evict(&vm->svm.gpusvm, &range->base);
> + }
> drm_info(&vm->xe->drm,
> "Get pages failed, falling back to retrying, asid=%u, gpusvm=%p, errno %pe\n",
> vm->usm.asid, &vm->svm.gpusvm, ERR_PTR(err));
> + range_debug(range, "PAGE FAULT - RETRY PAGES");
> goto retry;
> }
> - if (err)
> + if (err) {
> + range_debug(range, "PAGE FAULT - FAIL PAGE COLLECT");
> goto err_out;
> + }
> +
> + range_debug(range, "PAGE FAULT - BIND");
>
> retry_bind:
> drm_exec_init(&exec, 0, 0);
> @@ -758,8 +826,10 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
> if (IS_ERR(fence)) {
> drm_exec_fini(&exec);
> err = PTR_ERR(fence);
> - if (err == -EAGAIN)
> + if (err == -EAGAIN) {
> + range_debug(range, "PAGE FAULT - RETRY BIND");
> goto retry;
> + }
> if (xe_vm_validate_should_retry(&exec, err, &end))
> goto retry_bind;
> goto err_out;
> diff --git a/drivers/gpu/drm/xe/xe_svm.h b/drivers/gpu/drm/xe/xe_svm.h
> index ff43a6193536..1de3ade10fbf 100644
> --- a/drivers/gpu/drm/xe/xe_svm.h
> +++ b/drivers/gpu/drm/xe/xe_svm.h
> @@ -57,6 +57,8 @@ int xe_svm_handle_pagefault(struct xe_vm *vm, struct xe_vma *vma,
>
> bool xe_svm_has_mapping(struct xe_vm *vm, u64 start, u64 end);
>
> +void xe_svm_range_debug(struct xe_svm_range *range, const char *operation);
> +
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
> int xe_svm_bo_evict(struct xe_bo *bo);
>
> /**
next prev parent reply other threads:[~2025-02-13 11:30 UTC|newest]
Thread overview: 75+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-13 2:10 [PATCH v5 00/32] Introduce GPU SVM and Xe SVM implementation Matthew Brost
2025-02-13 2:10 ` [PATCH v5 01/32] drm/xe: Retry BO allocation Matthew Brost
2025-02-13 2:10 ` [PATCH v5 02/32] mm/migrate: Add migrate_device_pfns Matthew Brost
2025-02-13 2:10 ` [PATCH v5 03/32] mm/migrate: Trylock device page in do_swap_page Matthew Brost
2025-02-19 5:36 ` Alistair Popple
2025-02-19 6:08 ` Matthew Brost
2025-02-19 6:25 ` Alistair Popple
2025-02-20 13:28 ` Gwan-gyeong Mun
2025-02-20 20:03 ` Matthew Brost
2025-02-13 2:10 ` [PATCH v5 04/32] drm/pagemap: Add DRM pagemap Matthew Brost
2025-02-20 13:53 ` Gwan-gyeong Mun
2025-02-13 2:10 ` [PATCH v5 05/32] drm/xe/bo: Introduce xe_bo_put_async Matthew Brost
2025-02-14 9:52 ` Ghimiray, Himal Prasad
2025-02-20 14:33 ` Gwan-gyeong Mun
2025-02-13 2:10 ` [PATCH v5 06/32] drm/gpusvm: Add support for GPU Shared Virtual Memory Matthew Brost
2025-02-19 8:59 ` Thomas Hellström
2025-02-13 2:10 ` [PATCH v5 07/32] drm/xe: Select DRM_GPUSVM Kconfig Matthew Brost
2025-02-13 2:10 ` [PATCH v5 08/32] drm/xe/uapi: Add DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR Matthew Brost
2025-02-13 2:10 ` [PATCH v5 09/32] drm/xe: Add SVM init / close / fini to faulting VMs Matthew Brost
2025-02-13 2:10 ` [PATCH v5 10/32] drm/xe: Add dma_addr res cursor Matthew Brost
2025-02-13 2:10 ` [PATCH v5 11/32] drm/xe: Nuke VM's mapping upon close Matthew Brost
2025-02-13 2:10 ` [PATCH v5 12/32] drm/xe: Add SVM range invalidation and page fault Matthew Brost
2025-02-13 10:05 ` Ghimiray, Himal Prasad
2025-02-13 2:10 ` [PATCH v5 13/32] drm/gpuvm: Add DRM_GPUVA_OP_DRIVER Matthew Brost
2025-02-13 2:10 ` [PATCH v5 14/32] drm/xe: Add (re)bind to SVM page fault handler Matthew Brost
2025-02-13 2:10 ` [PATCH v5 15/32] drm/xe: Add SVM garbage collector Matthew Brost
2025-02-13 10:07 ` Ghimiray, Himal Prasad
2025-02-13 2:10 ` [PATCH v5 16/32] drm/xe: Add unbind to " Matthew Brost
2025-02-19 15:05 ` Thomas Hellström
2025-02-13 2:10 ` [PATCH v5 17/32] drm/xe: Do not allow CPU address mirror VMA unbind if the GPU has bindings Matthew Brost
2025-02-13 11:28 ` Ghimiray, Himal Prasad
2025-02-13 2:10 ` [PATCH v5 18/32] drm/xe: Enable CPU address mirror uAPI Matthew Brost
2025-02-13 11:26 ` Ghimiray, Himal Prasad
2025-02-13 2:10 ` [PATCH v5 19/32] drm/xe/uapi: Add DRM_XE_QUERY_CONFIG_FLAG_HAS_CPU_ADDR_MIRROR Matthew Brost
2025-02-13 2:11 ` [PATCH v5 20/32] drm/xe: Add migrate layer functions for SVM support Matthew Brost
2025-02-13 2:11 ` [PATCH v5 21/32] drm/xe: Add SVM device memory mirroring Matthew Brost
2025-02-13 11:28 ` Ghimiray, Himal Prasad
2025-02-13 2:11 ` [PATCH v5 22/32] drm/xe: Add drm_gpusvm_devmem to xe_bo Matthew Brost
2025-02-13 11:29 ` Ghimiray, Himal Prasad
2025-02-13 2:11 ` [PATCH v5 23/32] drm/xe: Add drm_pagemap ops to SVM Matthew Brost
2025-02-13 2:11 ` [PATCH v5 24/32] drm/xe: Add GPUSVM device memory copy vfunc functions Matthew Brost
2025-02-13 2:11 ` [PATCH v5 25/32] drm/xe: Add Xe SVM populate_devmem_pfn GPU SVM vfunc Matthew Brost
2025-02-13 2:11 ` [PATCH v5 26/32] drm/xe: Add Xe SVM devmem_release " Matthew Brost
2025-02-13 18:29 ` Ghimiray, Himal Prasad
2025-02-13 2:11 ` [PATCH v5 27/32] drm/xe: Add SVM VRAM migration Matthew Brost
2025-02-13 18:28 ` Ghimiray, Himal Prasad
2025-02-18 21:54 ` Matthew Brost
2025-02-19 2:59 ` Ghimiray, Himal Prasad
2025-02-19 3:05 ` Matthew Brost
2025-02-19 3:40 ` Ghimiray, Himal Prasad
2025-02-19 10:30 ` Thomas Hellström
2025-02-19 17:38 ` Matthew Brost
2025-02-20 15:53 ` Matthew Auld
2025-02-20 15:59 ` Thomas Hellström
2025-02-20 19:55 ` Matthew Brost
2025-02-21 15:15 ` Matthew Auld
2025-02-21 15:22 ` Matthew Brost
2025-02-13 2:11 ` [PATCH v5 28/32] drm/xe: Basic SVM BO eviction Matthew Brost
2025-02-13 2:11 ` [PATCH v5 29/32] drm/xe: Add SVM debug Matthew Brost
2025-02-13 11:30 ` Ghimiray, Himal Prasad [this message]
2025-02-13 2:11 ` [PATCH v5 30/32] drm/xe: Add modparam for SVM notifier size Matthew Brost
2025-02-13 11:31 ` Ghimiray, Himal Prasad
2025-02-13 2:11 ` [PATCH v5 31/32] drm/xe: Add always_migrate_to_vram modparam Matthew Brost
2025-02-13 11:31 ` Ghimiray, Himal Prasad
2025-02-13 2:11 ` [PATCH v5 32/32] drm/doc: gpusvm: Add GPU SVM documentation Matthew Brost
2025-02-13 3:35 ` ✓ CI.Patch_applied: success for Introduce GPU SVM and Xe SVM implementation (rev5) Patchwork
2025-02-13 3:36 ` ✗ CI.checkpatch: warning " Patchwork
2025-02-13 3:37 ` ✗ CI.KUnit: failure " Patchwork
2025-02-13 21:23 ` [PATCH v5 00/32] Introduce GPU SVM and Xe SVM implementation Demi Marie Obenour
2025-02-14 8:47 ` Thomas Hellström
2025-02-14 9:07 ` Ghimiray, Himal Prasad
2025-02-14 9:10 ` Ghimiray, Himal Prasad
2025-02-14 16:14 ` Demi Marie Obenour
2025-02-14 16:26 ` Thomas Hellström
2025-02-14 18:36 ` Demi Marie Obenour
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=33cb3eb0-9dd6-4723-afcd-18d76f3e3eff@intel.com \
--to=himal.prasad.ghimiray@intel.com \
--cc=airlied@gmail.com \
--cc=apopple@nvidia.com \
--cc=dakr@kernel.org \
--cc=dri-devel@lists.freedesktop.org \
--cc=felix.kuehling@amd.com \
--cc=intel-xe@lists.freedesktop.org \
--cc=matthew.brost@intel.com \
--cc=simona.vetter@ffwll.ch \
--cc=thomas.hellstrom@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox