drm/xe: Add a shrinker for xe bos

Rather than relying on the TTM watermark accounting add a shrinker
for xe_bos in TT or system memory.

Leverage the newly added TTM per-page shrinking and shmem backup
support.

Although xe doesn't fully support WONTNEED (purgeable) bos yet,
introduce and add shrinker support for purgeable ttm_tts.

v2:
- Cleanups bugfixes and a KUNIT shrinker test.
- Add writeback support, and activate if kswapd.
v3:
- Move the try_shrink() helper to core TTM.
- Minor cleanups.
v4:
- Add runtime pm for the shrinker. Shrinking may require an active
  device for CCS metadata copying.
v5:
- Separately purge ghost- and zombie objects in the shrinker.
- Fix a format specifier - type inconsistency. (Kernel test robot).
v7:
- s/long/s64/ (Christian König)
- s/sofar/progress/ (Matt Brost)
v8:
- Rebase on Xe KUNIT update.
- Add content verifying to the shrinker kunit test.
- Split out TTM changes to a separate patch.
- Get rid of multiple bool arguments for clarity (Matt Brost)
- Avoid an error pointer dereference (Matt Brost)
- Avoid an integer overflow (Matt Auld)
- Address misc review comments by Matt Brost.
v9:
- Fix a compliation error.
- Rebase.
v10:
- Update to new LRU walk interface.
- Rework ghost-, zombie and purged object shrinking.
- Rebase.
v11:
- Use additional TTM helpers.
- Honor __GFP_FS and __GFP_IO
- Rebase.
v13:
- Use ttm_tt_setup_backup().
v14:
- Don't set up backup on imported bos.
v15:
- Rebase on backup interface changes.

Cc: Christian König <christian.koenig@amd.com>
Cc: Somalapuram Amaranath <Amaranath.Somalapuram@amd.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <dri-devel@lists.freedesktop.org>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Acked-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/intel-xe/20250305092220.123405-7-thomas.hellstrom@linux.intel.com

drivers/gpu/drm/xe/Makefile

@@ -94,6 +94,7 @@ xe-y += xe_bb.o \
 	xe_ring_ops.o \
 	xe_sa.o \
 	xe_sched_job.o \
+	xe_shrinker.o \
 	xe_step.o \
 	xe_sync.o \
 	xe_tile.o \

drivers/gpu/drm/xe/tests/xe_bo.c

@@ -514,8 +514,13 @@ static int shrink_test_run_device(struct xe_device *xe)
 		 * other way around, they may not be subject to swapping...
 		 */
 		if (alloced < purgeable) {
+			xe_ttm_tt_account_subtract(&xe_tt->ttm);
 			xe_tt->purgeable = true;
+			xe_ttm_tt_account_add(&xe_tt->ttm);
 			bo->ttm.priority = 0;
+			spin_lock(&bo->ttm.bdev->lru_lock);
+			ttm_bo_move_to_lru_tail(&bo->ttm);
+			spin_unlock(&bo->ttm.bdev->lru_lock);
 		} else {
 			int ret = shrink_test_fill_random(bo, &prng, link);
 
@@ -570,7 +575,6 @@ static int shrink_test_run_device(struct xe_device *xe)
 				if (ret == -EINTR)
 					intr = true;
 			} while (ret == -EINTR && !signal_pending(current));
-
 			if (!ret && !purgeable)
 				failed = shrink_test_verify(test, bo, count, &prng, link);
 

drivers/gpu/drm/xe/xe_bo.c

@@ -10,6 +10,7 @@
 #include <drm/drm_drv.h>
 #include <drm/drm_gem_ttm_helper.h>
 #include <drm/drm_managed.h>
+#include <drm/ttm/ttm_backup.h>
 #include <drm/ttm/ttm_device.h>
 #include <drm/ttm/ttm_placement.h>
 #include <drm/ttm/ttm_tt.h>
@@ -25,6 +26,7 @@
 #include "xe_pm.h"
 #include "xe_preempt_fence.h"
 #include "xe_res_cursor.h"
+#include "xe_shrinker.h"
 #include "xe_trace_bo.h"
 #include "xe_ttm_stolen_mgr.h"
 #include "xe_vm.h"
@@ -281,9 +283,11 @@ static void xe_evict_flags(struct ttm_buffer_object *tbo,
 	}
 }
 
+/* struct xe_ttm_tt - Subclassed ttm_tt for xe */
 struct xe_ttm_tt {
 	struct ttm_tt ttm;
-	struct device *dev;
+	/** @xe - The xe device */
+	struct xe_device *xe;
 	struct sg_table sgt;
 	struct sg_table *sg;
 	/** @purgeable: Whether the content of the pages of @ttm is purgeable. */
@@ -296,21 +300,22 @@ static int xe_tt_map_sg(struct ttm_tt *tt)
 	unsigned long num_pages = tt->num_pages;
 	int ret;
 
-	XE_WARN_ON(tt->page_flags & TTM_TT_FLAG_EXTERNAL);
+	XE_WARN_ON((tt->page_flags & TTM_TT_FLAG_EXTERNAL) &&
+		   !(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE));
 
 	if (xe_tt->sg)
 		return 0;
 
 	ret = sg_alloc_table_from_pages_segment(&xe_tt->sgt, tt->pages,
 						num_pages, 0,
 						(u64)num_pages << PAGE_SHIFT,
-						xe_sg_segment_size(xe_tt->dev),
+						xe_sg_segment_size(xe_tt->xe->drm.dev),
 						GFP_KERNEL);
 	if (ret)
 		return ret;
 
 	xe_tt->sg = &xe_tt->sgt;
-	ret = dma_map_sgtable(xe_tt->dev, xe_tt->sg, DMA_BIDIRECTIONAL,
+	ret = dma_map_sgtable(xe_tt->xe->drm.dev, xe_tt->sg, DMA_BIDIRECTIONAL,
 			      DMA_ATTR_SKIP_CPU_SYNC);
 	if (ret) {
 		sg_free_table(xe_tt->sg);
@@ -326,7 +331,7 @@ static void xe_tt_unmap_sg(struct ttm_tt *tt)
 	struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm);
 
 	if (xe_tt->sg) {
-		dma_unmap_sgtable(xe_tt->dev, xe_tt->sg,
+		dma_unmap_sgtable(xe_tt->xe->drm.dev, xe_tt->sg,
 				  DMA_BIDIRECTIONAL, 0);
 		sg_free_table(xe_tt->sg);
 		xe_tt->sg = NULL;
@@ -341,21 +346,47 @@ struct sg_table *xe_bo_sg(struct xe_bo *bo)
 	return xe_tt->sg;
 }
 
+/*
+ * Account ttm pages against the device shrinker's shrinkable and
+ * purgeable counts.
+ */
+static void xe_ttm_tt_account_add(struct ttm_tt *tt)
+{
+	struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm);
+
+	if (xe_tt->purgeable)
+		xe_shrinker_mod_pages(xe_tt->xe->mem.shrinker, 0, tt->num_pages);
+	else
+		xe_shrinker_mod_pages(xe_tt->xe->mem.shrinker, tt->num_pages, 0);
+}
+
+static void xe_ttm_tt_account_subtract(struct ttm_tt *tt)
+{
+	struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm);
+
+	if (xe_tt->purgeable)
+		xe_shrinker_mod_pages(xe_tt->xe->mem.shrinker, 0, -(long)tt->num_pages);
+	else
+		xe_shrinker_mod_pages(xe_tt->xe->mem.shrinker, -(long)tt->num_pages, 0);
+}
+
 static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
 				       u32 page_flags)
 {
 	struct xe_bo *bo = ttm_to_xe_bo(ttm_bo);
 	struct xe_device *xe = xe_bo_device(bo);
-	struct xe_ttm_tt *tt;
+	struct xe_ttm_tt *xe_tt;
+	struct ttm_tt *tt;
 	unsigned long extra_pages;
 	enum ttm_caching caching = ttm_cached;
 	int err;
 
-	tt = kzalloc(sizeof(*tt), GFP_KERNEL);
-	if (!tt)
+	xe_tt = kzalloc(sizeof(*xe_tt), GFP_KERNEL);
+	if (!xe_tt)
 		return NULL;
 
-	tt->dev = xe->drm.dev;
+	tt = &xe_tt->ttm;
+	xe_tt->xe = xe;
 
 	extra_pages = 0;
 	if (xe_bo_needs_ccs_pages(bo))
@@ -401,42 +432,66 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
 		caching = ttm_uncached;
 	}
 
-	err = ttm_tt_init(&tt->ttm, &bo->ttm, page_flags, caching, extra_pages);
+	if (ttm_bo->type != ttm_bo_type_sg)
+		page_flags |= TTM_TT_FLAG_EXTERNAL | TTM_TT_FLAG_EXTERNAL_MAPPABLE;
+
+	err = ttm_tt_init(tt, &bo->ttm, page_flags, caching, extra_pages);
 	if (err) {
-		kfree(tt);
+		kfree(xe_tt);
 		return NULL;
 	}
 
-	return &tt->ttm;
+	if (ttm_bo->type != ttm_bo_type_sg) {
+		err = ttm_tt_setup_backup(tt);
+		if (err) {
+			ttm_tt_fini(tt);
+			kfree(xe_tt);
+			return NULL;
+		}
+	}
+
+	return tt;
 }
 
 static int xe_ttm_tt_populate(struct ttm_device *ttm_dev, struct ttm_tt *tt,
 			      struct ttm_operation_ctx *ctx)
 {
+	struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm);
 	int err;
 
 	/*
 	 * dma-bufs are not populated with pages, and the dma-
 	 * addresses are set up when moved to XE_PL_TT.
 	 */
-	if (tt->page_flags & TTM_TT_FLAG_EXTERNAL)
+	if ((tt->page_flags & TTM_TT_FLAG_EXTERNAL) &&
+	    !(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE))
 		return 0;
 
-	err = ttm_pool_alloc(&ttm_dev->pool, tt, ctx);
+	if (ttm_tt_is_backed_up(tt) && !xe_tt->purgeable) {
+		err = ttm_tt_restore(ttm_dev, tt, ctx);
+	} else {
+		ttm_tt_clear_backed_up(tt);
+		err = ttm_pool_alloc(&ttm_dev->pool, tt, ctx);
+	}
 	if (err)
 		return err;
 
-	return err;
+	xe_tt->purgeable = false;
+	xe_ttm_tt_account_add(tt);
+
+	return 0;
 }
 
 static void xe_ttm_tt_unpopulate(struct ttm_device *ttm_dev, struct ttm_tt *tt)
 {
-	if (tt->page_flags & TTM_TT_FLAG_EXTERNAL)
+	if ((tt->page_flags & TTM_TT_FLAG_EXTERNAL) &&
+	    !(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE))
 		return;
 
 	xe_tt_unmap_sg(tt);
 
-	return ttm_pool_free(&ttm_dev->pool, tt);
+	ttm_pool_free(&ttm_dev->pool, tt);
+	xe_ttm_tt_account_subtract(tt);
 }
 
 static void xe_ttm_tt_destroy(struct ttm_device *ttm_dev, struct ttm_tt *tt)
@@ -871,6 +926,111 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 	return ret;
 }
 
+static long xe_bo_shrink_purge(struct ttm_operation_ctx *ctx,
+			       struct ttm_buffer_object *bo,
+			       unsigned long *scanned)
+{
+	long lret;
+
+	/* Fake move to system, without copying data. */
+	if (bo->resource->mem_type != XE_PL_SYSTEM) {
+		struct ttm_resource *new_resource;
+
+		lret = ttm_bo_wait_ctx(bo, ctx);
+		if (lret)
+			return lret;
+
+		lret = ttm_bo_mem_space(bo, &sys_placement, &new_resource, ctx);
+		if (lret)
+			return lret;
+
+		xe_tt_unmap_sg(bo->ttm);
+		ttm_bo_move_null(bo, new_resource);
+	}
+
+	*scanned += bo->ttm->num_pages;
+	lret = ttm_bo_shrink(ctx, bo, (struct ttm_bo_shrink_flags)
+			     {.purge = true,
+			      .writeback = false,
+			      .allow_move = false});
+
+	if (lret > 0)
+		xe_ttm_tt_account_subtract(bo->ttm);
+
+	return lret;
+}
+
+/**
+ * xe_bo_shrink() - Try to shrink an xe bo.
+ * @ctx: The struct ttm_operation_ctx used for shrinking.
+ * @bo: The TTM buffer object whose pages to shrink.
+ * @flags: Flags governing the shrink behaviour.
+ * @scanned: Pointer to a counter of the number of pages
+ * attempted to shrink.
+ *
+ * Try to shrink- or purge a bo, and if it succeeds, unmap dma.
+ * Note that we need to be able to handle also non xe bos
+ * (ghost bos), but only if the struct ttm_tt is embedded in
+ * a struct xe_ttm_tt. When the function attempts to shrink
+ * the pages of a buffer object, The value pointed to by @scanned
+ * is updated.
+ *
+ * Return: The number of pages shrunken or purged, or negative error
+ * code on failure.
+ */
+long xe_bo_shrink(struct ttm_operation_ctx *ctx, struct ttm_buffer_object *bo,
+		  const struct xe_bo_shrink_flags flags,
+		  unsigned long *scanned)
+{
+	struct ttm_tt *tt = bo->ttm;
+	struct xe_ttm_tt *xe_tt = container_of(tt, struct xe_ttm_tt, ttm);
+	struct ttm_place place = {.mem_type = bo->resource->mem_type};
+	struct xe_bo *xe_bo = ttm_to_xe_bo(bo);
+	struct xe_device *xe = xe_tt->xe;
+	bool needs_rpm;
+	long lret = 0L;
+
+	if (!(tt->page_flags & TTM_TT_FLAG_EXTERNAL_MAPPABLE) ||
+	    (flags.purge && !xe_tt->purgeable))
+		return -EBUSY;
+
+	if (!ttm_bo_eviction_valuable(bo, &place))
+		return -EBUSY;
+
+	if (!xe_bo_is_xe_bo(bo) || !xe_bo_get_unless_zero(xe_bo))
+		return xe_bo_shrink_purge(ctx, bo, scanned);
+
+	if (xe_tt->purgeable) {
+		if (bo->resource->mem_type != XE_PL_SYSTEM)
+			lret = xe_bo_move_notify(xe_bo, ctx);
+		if (!lret)
+			lret = xe_bo_shrink_purge(ctx, bo, scanned);
+		goto out_unref;
+	}
+
+	/* System CCS needs gpu copy when moving PL_TT -> PL_SYSTEM */
+	needs_rpm = (!IS_DGFX(xe) && bo->resource->mem_type != XE_PL_SYSTEM &&
+		     xe_bo_needs_ccs_pages(xe_bo));
+	if (needs_rpm && !xe_pm_runtime_get_if_active(xe))
+		goto out_unref;
+
+	*scanned += tt->num_pages;
+	lret = ttm_bo_shrink(ctx, bo, (struct ttm_bo_shrink_flags)
+			     {.purge = false,
+			      .writeback = flags.writeback,
+			      .allow_move = true});
+	if (needs_rpm)
+		xe_pm_runtime_put(xe);
+
+	if (lret > 0)
+		xe_ttm_tt_account_subtract(tt);
+
+out_unref:
+	xe_bo_put(xe_bo);
+
+	return lret;
+}
+
 /**
  * xe_bo_evict_pinned() - Evict a pinned VRAM object to system memory
  * @bo: The buffer object to move.
@@ -1885,6 +2045,8 @@ int xe_bo_pin_external(struct xe_bo *bo)
 	}
 
 	ttm_bo_pin(&bo->ttm);
+	if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm))
+		xe_ttm_tt_account_subtract(bo->ttm.ttm);
 
 	/*
 	 * FIXME: If we always use the reserve / unreserve functions for locking
@@ -1944,6 +2106,8 @@ int xe_bo_pin(struct xe_bo *bo)
 	}
 
 	ttm_bo_pin(&bo->ttm);
+	if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm))
+		xe_ttm_tt_account_subtract(bo->ttm.ttm);
 
 	/*
 	 * FIXME: If we always use the reserve / unreserve functions for locking
@@ -1978,6 +2142,8 @@ void xe_bo_unpin_external(struct xe_bo *bo)
 	spin_unlock(&xe->pinned.lock);
 
 	ttm_bo_unpin(&bo->ttm);
+	if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm))
+		xe_ttm_tt_account_add(bo->ttm.ttm);
 
 	/*
 	 * FIXME: If we always use the reserve / unreserve functions for locking
@@ -2001,6 +2167,8 @@ void xe_bo_unpin(struct xe_bo *bo)
 		spin_unlock(&xe->pinned.lock);
 	}
 	ttm_bo_unpin(&bo->ttm);
+	if (bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm))
+		xe_ttm_tt_account_add(bo->ttm.ttm);
 }
 
 /**