Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Oak Zeng <oak.zeng@intel.com>
To: intel-xe@lists.freedesktop.org
Subject: [CI 40/42] drm/xe/svm: Determine a vma is backed by device memory
Date: Thu, 13 Jun 2024 11:31:26 -0400	[thread overview]
Message-ID: <20240613153128.681864-40-oak.zeng@intel.com> (raw)
In-Reply-To: <20240613153128.681864-1-oak.zeng@intel.com>

With system allocator, a userptr can now be back by device
memory also. Introduce a helper function xe_vma_is_devmem
to determine whether a range of vma is backed by device memory.

Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Brian Welty <brian.welty@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Signed-off-by: Oak Zeng <oak.zeng@intel.com>
---
 drivers/gpu/drm/xe/xe_pt.c | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index f6fc2dcb3767..c68ff02a931e 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -3,6 +3,7 @@
  * Copyright © 2022 Intel Corporation
  */
 
+#include <linux/hmm.h>
 #include "xe_pt.h"
 
 #include "regs/xe_gtt_defs.h"
@@ -578,6 +579,28 @@ static const struct xe_pt_walk_ops xe_pt_stage_bind_ops = {
 	.pt_entry = xe_pt_stage_bind_entry,
 };
 
+static bool xe_vma_is_devmem(struct xe_vma *vma, u64 start)
+{
+	if (xe_vma_is_userptr(vma)) {
+		struct xe_userptr_vma *uvma = to_userptr_vma(vma);
+		struct drm_hmmptr *hmmptr = &uvma->userptr.hmmptr;
+		u64 offset = start - xe_vma_start(vma);
+		u64 page_idx = offset >> PAGE_SHIFT;
+		u64 hmm_pfn = hmmptr->pfn[page_idx];
+		struct page *page = hmm_pfn_to_page(hmm_pfn);
+
+		/**
+		 * FIXME: Assume there is no mixture system memory and device
+		 * memory placement in the [start, end) range of vma. We might
+		 * need to relook at this in the future.
+		 */
+		return is_device_private_page(page);
+	} else {
+		struct xe_bo *bo = xe_vma_bo(vma);
+		return bo && (xe_bo_is_vram(bo) || xe_bo_is_stolen_devmem(bo));
+	}
+}
+
 /**
  * xe_pt_stage_bind() - Build a disconnected page-table tree for a given address
  * range.
@@ -604,8 +627,7 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma, u64 start, u64 end,
 {
 	struct xe_device *xe = tile_to_xe(tile);
 	struct xe_bo *bo = xe_vma_bo(vma);
-	bool is_devmem = !xe_vma_is_userptr(vma) && bo &&
-		(xe_bo_is_vram(bo) || xe_bo_is_stolen_devmem(bo));
+	bool is_devmem = xe_vma_is_devmem(vma, start);
 	struct xe_res_cursor curs;
 	struct xe_pt_stage_bind_walk xe_walk = {
 		.base = {
-- 
2.26.3


  parent reply	other threads:[~2024-06-13 15:21 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-06-13 15:30 [CI 01/42] mm/hmm: let users to tag specific PFNs Oak Zeng
2024-06-13 15:30 ` [CI 02/42] dma-mapping: provide an interface to allocate IOVA Oak Zeng
2024-06-13 15:30 ` [CI 03/42] dma-mapping: provide callbacks to link/unlink pages to specific IOVA Oak Zeng
2024-06-13 15:30 ` [CI 04/42] iommu/dma: Provide an interface to allow preallocate IOVA Oak Zeng
2024-06-13 15:30 ` [CI 05/42] iommu/dma: Prepare map/unmap page functions to receive IOVA Oak Zeng
2024-06-13 15:30 ` [CI 06/42] iommu/dma: Implement link/unlink page callbacks Oak Zeng
2024-06-13 15:30 ` [CI 07/42] drm: Move GPUVA_START/LAST to drm_gpuvm.h Oak Zeng
2024-06-13 15:30 ` [CI 08/42] drm/svm: Mark drm_gpuvm to participate SVM Oak Zeng
2024-06-13 15:30 ` [CI 09/42] drm/svm: introduce drm_mem_region concept Oak Zeng
2024-06-13 15:30 ` [CI 10/42] drm/svm: introduce hmmptr and helper functions Oak Zeng
2024-06-13 15:30 ` [CI 11/42] drm/svm: Introduce helper to remap drm memory region Oak Zeng
2024-06-13 15:30 ` [CI 12/42] drm/svm: handle CPU page fault Oak Zeng
2024-06-13 15:30 ` [CI 13/42] drm/svm: Migrate a range of hmmptr to vram Oak Zeng
2024-06-13 15:31 ` [CI 14/42] drm/svm: Add DRM SVM documentation Oak Zeng
2024-06-13 15:31 ` [CI 15/42] drm/xe: s/xe_tile_migrate_engine/xe_tile_migrate_exec_queue Oak Zeng
2024-06-13 15:31 ` [CI 16/42] drm/xe: Add xe_vm_pgtable_update_op to xe_vma_ops Oak Zeng
2024-06-13 15:31 ` [CI 17/42] drm/xe: Convert multiple bind ops into single job Oak Zeng
2024-06-13 15:31 ` [CI 18/42] drm/xe: Update VM trace events Oak Zeng
2024-06-13 15:31 ` [CI 19/42] drm/xe: Update PT layer with better error handling Oak Zeng
2024-06-13 15:31 ` [CI 20/42] drm/xe: Retry BO allocation Oak Zeng
2024-06-13 15:31 ` [CI 21/42] drm/xe/uapi: Add DRM_XE_VM_BIND_FLAG_SYSTEM_ALLOCATOR flag Oak Zeng
2024-06-13 15:31 ` [CI 22/42] drm/xe: Add a helper to calculate userptr end address Oak Zeng
2024-06-13 15:31 ` [CI 23/42] drm/xe: Add dma_addr res cursor Oak Zeng
2024-06-13 15:31 ` [CI 24/42] drm/xe: Use drm_mem_region for xe Oak Zeng
2024-06-13 15:31 ` [CI 25/42] drm/xe: use drm_hmmptr in xe Oak Zeng
2024-06-13 15:31 ` [CI 26/42] drm/xe: Moving to range based vma invalidation Oak Zeng
2024-06-13 15:31 ` [CI 27/42] drm/xe: Support range based page table update Oak Zeng
2024-06-13 15:31 ` [CI 28/42] drm/xe/uapi: Add DRM_XE_VM_CREATE_FLAG_PARTICIPATE_SVM flag Oak Zeng
2024-06-13 15:31 ` [CI 29/42] drm/xe/svm: Create userptr if page fault occurs on system_allocator VMA Oak Zeng
2024-06-13 15:31 ` [CI 30/42] drm/xe/svm: Add faulted userptr VMA garbage collector Oak Zeng
2024-06-13 15:31 ` [CI 31/42] drm/xe: Introduce helper to get tile from memory region Oak Zeng
2024-06-13 15:31 ` [CI 32/42] drm/xe/svm: implement functions to allocate and free device memory Oak Zeng
2024-06-13 15:31 ` [CI 33/42] drm/xe/svm: Get drm device from drm memory region Oak Zeng
2024-06-13 15:31 ` [CI 34/42] drm/xe/svm: Get page map owner of a " Oak Zeng
2024-06-13 15:31 ` [CI 35/42] drm/xe/svm: Add migrate layer functions for SVM support Oak Zeng
2024-06-13 15:31 ` [CI 36/42] drm/xe/svm: introduce svm migration function Oak Zeng
2024-06-13 15:31 ` [CI 37/42] drm/xe/svm: Register xe memory region to drm layer Oak Zeng
2024-06-13 15:31 ` [CI 38/42] drm/xe/svm: Introduce DRM_XE_SVM kernel config Oak Zeng
2024-06-13 15:31 ` [CI 39/42] drm/xe/svm: Migration from sram to vram for system allocator Oak Zeng
2024-06-13 15:31 ` Oak Zeng [this message]
2024-06-13 15:31 ` [CI 41/42] drm/xe/svm: Introduce hmm_pfn array based resource cursor Oak Zeng
2024-06-13 15:31 ` [CI 42/42] drm/xe: Enable system allocator uAPI Oak Zeng
2024-06-13 15:53 ` ✓ CI.Patch_applied: success for series starting with [CI,01/42] mm/hmm: let users to tag specific PFNs Patchwork
2024-06-13 15:54 ` ✗ CI.checkpatch: warning " Patchwork
2024-06-13 15:54 ` ✗ CI.KUnit: failure " Patchwork
  -- strict thread matches above, loose matches on Subject: below --
2024-06-13  4:23 [CI 01/42] " Oak Zeng
2024-06-13  4:24 ` [CI 40/42] drm/xe/svm: Determine a vma is backed by device memory Oak Zeng

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=20240613153128.681864-40-oak.zeng@intel.com \
    --to=oak.zeng@intel.com \
    --cc=intel-xe@lists.freedesktop.org \
    /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