[PATCH 2/4] drm/xe: Add explicit abort page reclaim list

[Brian Nguyen <brian3.nguyen@intel.com>]

PRLs could be invalidated to indicate its getting dropped from current
scope but are still valid. So standardize calls and add abort to clearly
define when an invalidation is a real abort and PRL should fallback.

Signed-off-by: Brian Nguyen <brian3.nguyen@intel.com>
---
 drivers/gpu/drm/xe/xe_page_reclaim.c  | 23 +++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_page_reclaim.h  |  3 +++
 drivers/gpu/drm/xe/xe_pt.c            | 21 +++++++++------------
 drivers/gpu/drm/xe/xe_tlb_inval_job.c |  2 +-
 4 files changed, 36 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_page_reclaim.c b/drivers/gpu/drm/xe/xe_page_reclaim.c
index 94d4608ebd74..9f086067a4a1 100644
--- a/drivers/gpu/drm/xe/xe_page_reclaim.c
+++ b/drivers/gpu/drm/xe/xe_page_reclaim.c
@@ -100,6 +100,29 @@ void xe_page_reclaim_list_invalidate(struct xe_page_reclaim_list *prl)
 	prl->num_entries = XE_PAGE_RECLAIM_INVALID_LIST;
 }
 
+/**
+ * xe_page_reclaim_list_abort() - Abort a PRL, invalidate it, and log
+ * @gt: GT associated with this PRL
+ * @prl: Page reclaim list to invalidate
+ * @format: printf-style format string for vm_dbg
+ *
+ * This is intended for PRL abort paths where we want to track aborted PRLs
+ */
+void xe_page_reclaim_list_abort(struct xe_gt *gt, struct xe_page_reclaim_list *prl,
+				const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list va_args;
+
+	xe_page_reclaim_list_invalidate(prl);
+
+	va_start(va_args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &va_args;
+	vm_dbg(&gt_to_xe(gt)->drm, "PRL aborted: %pV", &vaf);
+	va_end(va_args);
+}
+
 /**
  * xe_page_reclaim_list_init() - Initialize a page reclaim list
  * @prl: Page reclaim list to initialize
diff --git a/drivers/gpu/drm/xe/xe_page_reclaim.h b/drivers/gpu/drm/xe/xe_page_reclaim.h
index a4f58e0ce9b4..2464268dba69 100644
--- a/drivers/gpu/drm/xe/xe_page_reclaim.h
+++ b/drivers/gpu/drm/xe/xe_page_reclaim.h
@@ -19,6 +19,7 @@
 struct xe_tlb_inval;
 struct xe_tlb_inval_fence;
 struct xe_tile;
+struct xe_gt;
 struct xe_vma;
 
 struct xe_guc_page_reclaim_entry {
@@ -75,6 +76,8 @@ struct drm_suballoc *xe_page_reclaim_create_prl_bo(struct xe_tlb_inval *tlb_inva
 						   struct xe_page_reclaim_list *prl,
 						   struct xe_tlb_inval_fence *fence);
 void xe_page_reclaim_list_invalidate(struct xe_page_reclaim_list *prl);
+void xe_page_reclaim_list_abort(struct xe_gt *gt, struct xe_page_reclaim_list *prl,
+				const char *format, ...);
 void xe_page_reclaim_list_init(struct xe_page_reclaim_list *prl);
 int xe_page_reclaim_list_alloc_entries(struct xe_page_reclaim_list *prl);
 /**
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 6cd78bb2b652..2752a5a48a97 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -1618,10 +1618,9 @@ static int generate_reclaim_entry(struct xe_tile *tile,
 	} else if (is_2m_pte(xe_child)) {
 		reclamation_size = COMPUTE_RECLAIM_ADDRESS_MASK(SZ_2M);  /* reclamation_size = 9 */
 	} else {
-		xe_page_reclaim_list_invalidate(prl);
-		vm_dbg(&tile_to_xe(tile)->drm,
-		       "PRL invalidate: unsupported PTE level=%u pte=%#llx\n",
-		       xe_child->level, pte);
+		xe_page_reclaim_list_abort(tile->primary_gt, prl,
+					   "unsupported PTE level=%u pte=%#llx",
+					   xe_child->level, pte);
 		return -EINVAL;
 	}
 
@@ -1670,10 +1669,9 @@ static int xe_pt_stage_unbind_entry(struct xe_ptw *parent, pgoff_t offset,
 					break;
 			} else {
 				/* overflow, mark as invalid */
-				xe_page_reclaim_list_invalidate(xe_walk->prl);
-				vm_dbg(&xe->drm,
-				       "PRL invalidate: overflow while adding pte=%#llx",
-				       pte);
+				xe_page_reclaim_list_abort(xe_walk->tile->primary_gt, xe_walk->prl,
+							   "overflow while adding pte=%#llx",
+							   pte);
 				break;
 			}
 		}
@@ -1682,10 +1680,9 @@ static int xe_pt_stage_unbind_entry(struct xe_ptw *parent, pgoff_t offset,
 	/* If aborting page walk early, invalidate PRL since PTE may be dropped from this abort */
 	if (xe_pt_check_kill(addr, next, level - 1, xe_child, action, walk) &&
 	    xe_walk->prl && level > 1 && xe_child->base.children && xe_child->num_live != 0) {
-		xe_page_reclaim_list_invalidate(xe_walk->prl);
-		vm_dbg(&xe->drm,
-		       "PRL invalidate: kill at level=%u addr=%#llx next=%#llx num_live=%u\n",
-		       level, addr, next, xe_child->num_live);
+		xe_page_reclaim_list_abort(xe_walk->tile->primary_gt, xe_walk->prl,
+					   "kill at level=%u addr=%#llx next=%#llx num_live=%u\n",
+					   level, addr, next, xe_child->num_live);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/xe/xe_tlb_inval_job.c b/drivers/gpu/drm/xe/xe_tlb_inval_job.c
index 6a7bd6315797..b8916552101c 100644
--- a/drivers/gpu/drm/xe/xe_tlb_inval_job.c
+++ b/drivers/gpu/drm/xe/xe_tlb_inval_job.c
@@ -182,7 +182,7 @@ static void xe_tlb_inval_job_destroy(struct kref *ref)
 	struct xe_vm *vm = job->vm;
 
 	/* BO creation retains a copy (if used), so no longer needed */
-	xe_page_reclaim_entries_put(job->prl.entries);
+	xe_page_reclaim_list_invalidate(&job->prl);
 
 	if (!job->fence_armed)
 		kfree(ifence);
-- 
2.52.0