[PATCH v2] drm/xe/lnl: Offload system clear page activity to GPU

[Nirmoy Das <nirmoy.das@xxxxxxxxx>]

On LNL because of flat CCS, driver creates a migrate job to clear
CCS meta data. Extend that to also clear system pages using GPU.
Inform TTM to allocate pages without __GFP_ZERO to avoid double page
clearing by clearing out TTM_TT_FLAG_ZERO_ALLOC flag.

v2: Handle regression on dgfx(Himal)
    Update commit message as no ttm API changes needed.

Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@xxxxxxxxx>
Cc: Matthew Auld <matthew.auld@xxxxxxxxx>
Cc: "Thomas Hellström" <thomas.hellstrom@xxxxxxxxxxxxxxx>
Signed-off-by: Nirmoy Das <nirmoy.das@xxxxxxxxx>

O
---
 drivers/gpu/drm/xe/xe_bo.c           | 4 ++++
 drivers/gpu/drm/xe/xe_device.c       | 7 +++++++
 drivers/gpu/drm/xe/xe_device_types.h | 2 ++
 drivers/gpu/drm/xe/xe_migrate.c      | 5 +++--
 4 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 65c696966e96..10ec02412dc4 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -387,6 +387,10 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
 		caching = ttm_uncached;
 	}
 
+	/* Clear TTM_TT_FLAG_ZERO_ALLOC when GPU is set to clear pages */
+	if (xe->mem.gpu_page_clear)
+		page_flags &= ~TTM_TT_FLAG_ZERO_ALLOC;
+
 	err = ttm_tt_init(&tt->ttm, &bo->ttm, page_flags, caching, extra_pages);
 	if (err) {
 		kfree(tt);
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 0d57eea8f083..b9ed30c84418 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -636,6 +636,13 @@ int xe_device_probe(struct xe_device *xe)
 	if (err)
 		goto err_irq_shutdown;
 
+	/**
+	 * On iGFX device with flat CCS, we clear CCS metadata, let's extend that
+	 * and use GPU to clear pages as well.
+	 */
+	if (xe_device_has_flat_ccs(xe) && !IS_DGFX(xe))
+		xe->mem.gpu_page_clear = true;
+
 	err = xe_vram_probe(xe);
 	if (err)
 		goto err_irq_shutdown;
diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index c37be471d11c..ece68c6f3668 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -325,6 +325,8 @@ struct xe_device {
 		struct xe_mem_region vram;
 		/** @mem.sys_mgr: system TTM manager */
 		struct ttm_resource_manager sys_mgr;
+		/** @gpu_page_clear: clear pages offloaded to GPU */
+		bool gpu_page_clear;
 	} mem;
 
 	/** @sriov: device level virtualization data */
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 05f933787860..7acf471a1a40 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -1003,6 +1003,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 	struct xe_gt *gt = m->tile->primary_gt;
 	struct xe_device *xe = gt_to_xe(gt);
 	bool clear_system_ccs = (xe_bo_needs_ccs_pages(bo) && !IS_DGFX(xe)) ? true : false;
+	bool clear_on_create = xe->mem.gpu_page_clear || clear_vram;
 	struct dma_fence *fence = NULL;
 	u64 size = bo->size;
 	struct xe_res_cursor src_it;
@@ -1032,7 +1033,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		batch_size = 2 +
 			pte_update_size(m, clear_vram, src, &src_it,
 					&clear_L0, &clear_L0_ofs, &clear_L0_pt,
-					clear_system_ccs ? 0 : emit_clear_cmd_len(gt), 0,
+					!clear_on_create ? 0 : emit_clear_cmd_len(gt), 0,
 					avail_pts);
 
 		if (xe_device_has_flat_ccs(xe))
@@ -1060,7 +1061,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 		update_idx = bb->len;
 
-		if (!clear_system_ccs)
+		if (clear_on_create)
 			emit_clear(gt, bb, clear_L0_ofs, clear_L0, XE_PAGE_SIZE, clear_vram);
 
 		if (xe_device_has_flat_ccs(xe)) {
-- 
2.42.0