Merge tag 'drm-xe-next-2024-08-28' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next

UAPI Changes:
- Fix OA format masks which were breaking build with gcc-5

Cross-subsystem Changes:

Driver Changes:
- Use dma_fence_chain_free in chain fence unused as a sync (Matthew Brost)
- Refactor hw engine lookup and mmio access to be used in more places
  (Dominik, Matt Auld, Mika Kuoppala)
- Enable priority mem read for Xe2 and later (Pallavi Mishra)
- Fix PL1 disable flow in xe_hwmon_power_max_write (Karthik)
- Fix refcount and speedup devcoredump (Matthew Brost)
- Add performance tuning changes to Xe2 (Akshata, Shekhar)
- Fix OA sysfs entry (Ashutosh)
- Add first GuC firmware support for BMG (Julia)
- Bump minimum GuC firmware for platforms under force_probe to match LNL
  and BMG (Julia)
- Fix access check on user fence creation (Nirmoy)
- Add/document workarounds for Xe2 (Julia, Daniele, John, Tejas)
- Document workaround and use proper WA infra (Matt Roper)
- Fix VF configuration on media GT (Michal Wajdeczko)
- Fix VM dma-resv lock (Matthew Brost)
- Allow suspend/resume exec queue backend op to be called multiple times
  (Matthew Brost)
- Add GT stats to debugfs (Nirmoy)
- Add hwconfig to debugfs (Matt Roper)
- Compile out all debugfs code with ONFIG_DEUBG_FS=n (Lucas)
- Remove dead kunit code (Jani Nikula)
- Refactor drvdata storing to help display (Jani Nikula)
- Cleanup unsused xe parameter in pte handling (Himal)
- Rename s/enable_display/probe_display/ for clarity (Lucas)
- Fix missing MCR annotation in couple of registers (Tejas)
- Fix DGFX display suspend/resume (Maarten)
- Prepare exec_queue_kill for PXP handling (Daniele)
- Fix devm/drmm issues (Daniele, Matthew Brost)
- Fix tile and ggtt fini sequences (Matthew Brost)
- Fix crashes when probing without firmware in place (Daniele, Matthew Brost)
- Use xe_managed for kernel BOs (Daniele, Matthew Brost)
- Future-proof dss_per_group calculation by using hwconfig (Matt Roper)
- Use reserved copy engine for user binds on faulting devices
  (Matthew Brost)
- Allow mixing dma-fence jobs and long-running faulting jobs (Francois)
- Cleanup redundant arg when creating use BO (Nirmoy)
- Prevent UAF around preempt fence (Auld)
- Fix display suspend/resume (Maarten)
- Use vma_pages() helper (Thorsten)
- Calculate pagefault queue size (Stuart, Matthew Auld)
- Fix missing pagefault wq destroy (Stuart)
- Fix lifetime handling of HW fence ctx (Matthew Brost)
- Fix order destroy order for jobs (Matthew Brost)
- Fix TLB invalidation for media GT (Matthew Brost)
- Document GGTT (Rodrigo Vivi)
- Refactor GGTT layering and fix runtime outer protection (Rodrigo Vivi)
- Handle HPD polling on display pm runtime suspend/resume (Imre, Vinod)
- Drop unrequired NULL checks (Apoorva, Himal)
- Use separate rpm lockdep map for non-d3cold-capable devices (Thomas Hellström)
- Support "nomodeset" kernel command-line option (Thomas Zimmermann)
- Drop force_probe requirement for LNL and BMG (Lucas, Balasubramani)

Signed-off-by: Dave Airlie <[email protected]>

From: Lucas De Marchi <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/wd42jsh4i3q5zlrmi2cljejohdsrqc6hvtxf76lbxsp3ibrgmz@y54fa7wwxgsd

Author: airlied

Documentation/gpu/xe/xe_mm.rst

@@ -7,6 +7,21 @@ Memory Management
 .. kernel-doc:: drivers/gpu/drm/xe/xe_bo_doc.h
    :doc: Buffer Objects (BO)
 
+GGTT
+====
+
+.. kernel-doc:: drivers/gpu/drm/xe/xe_ggtt.c
+   :doc: Global Graphics Translation Table (GGTT)
+
+GGTT Internal API
+-----------------
+
+.. kernel-doc:: drivers/gpu/drm/xe/xe_ggtt_types.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/xe/xe_ggtt.c
+   :internal:
+
 Pagetable building
 ==================
 

drivers/gpu/drm/drm_print.c

@@ -100,8 +100,9 @@ void __drm_puts_coredump(struct drm_printer *p, const char *str)
 			copy = iterator->remain;
 
 		/* Copy out the bit of the string that we need */
-		memcpy(iterator->data,
-			str + (iterator->start - iterator->offset), copy);
+		if (iterator->data)
+			memcpy(iterator->data,
+			       str + (iterator->start - iterator->offset), copy);
 
 		iterator->offset = iterator->start + copy;
 		iterator->remain -= copy;
@@ -110,7 +111,8 @@ void __drm_puts_coredump(struct drm_printer *p, const char *str)
 
 		len = min_t(ssize_t, strlen(str), iterator->remain);
 
-		memcpy(iterator->data + pos, str, len);
+		if (iterator->data)
+			memcpy(iterator->data + pos, str, len);
 
 		iterator->offset += len;
 		iterator->remain -= len;
@@ -140,8 +142,9 @@ void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf)
 	if ((iterator->offset >= iterator->start) && (len < iterator->remain)) {
 		ssize_t pos = iterator->offset - iterator->start;
 
-		snprintf(((char *) iterator->data) + pos,
-			iterator->remain, "%pV", vaf);
+		if (iterator->data)
+			snprintf(((char *) iterator->data) + pos,
+				 iterator->remain, "%pV", vaf);
 
 		iterator->offset += len;
 		iterator->remain -= len;

drivers/gpu/drm/i915/display/intel_dpt.c

@@ -317,3 +317,7 @@ void intel_dpt_destroy(struct i915_address_space *vm)
 	i915_vm_put(&dpt->vm);
 }
 
+u64 intel_dpt_offset(struct i915_vma *dpt_vma)
+{
+	return dpt_vma->node.start;
+}

drivers/gpu/drm/i915/display/intel_dpt.h

@@ -6,6 +6,8 @@
 #ifndef __INTEL_DPT_H__
 #define __INTEL_DPT_H__
 
+#include <linux/types.h>
+
 struct drm_i915_private;
 
 struct i915_address_space;
@@ -20,5 +22,6 @@ void intel_dpt_suspend(struct drm_i915_private *i915);
 void intel_dpt_resume(struct drm_i915_private *i915);
 struct i915_address_space *
 intel_dpt_create(struct intel_framebuffer *fb);
+u64 intel_dpt_offset(struct i915_vma *dpt_vma);
 
 #endif /* __INTEL_DPT_H__ */

drivers/gpu/drm/i915/display/skl_universal_plane.c

@@ -14,6 +14,7 @@
 #include "intel_de.h"
 #include "intel_display_irq.h"
 #include "intel_display_types.h"
+#include "intel_dpt.h"
 #include "intel_fb.h"
 #include "intel_fbc.h"
 #include "intel_frontbuffer.h"
@@ -1162,7 +1163,7 @@ static u32 skl_surf_address(const struct intel_plane_state *plane_state,
 		 * within the DPT is always 0.
 		 */
 		drm_WARN_ON(&i915->drm, plane_state->dpt_vma &&
-			    plane_state->dpt_vma->node.start);
+			    intel_dpt_offset(plane_state->dpt_vma));
 		drm_WARN_ON(&i915->drm, offset & 0x1fffff);
 		return offset >> 9;
 	} else {

drivers/gpu/drm/xe/Makefile

@@ -28,7 +28,6 @@ $(obj)/generated/%_wa_oob.c $(obj)/generated/%_wa_oob.h: $(obj)/xe_gen_wa_oob \
 xe-y += xe_bb.o \
 	xe_bo.o \
 	xe_bo_evict.o \
-	xe_debugfs.o \
 	xe_devcoredump.o \
 	xe_device.o \
 	xe_device_sysfs.o \
@@ -46,7 +45,6 @@ xe-y += xe_bb.o \
 	xe_gt.o \
 	xe_gt_ccs_mode.o \
 	xe_gt_clock.o \
-	xe_gt_debugfs.o \
 	xe_gt_freq.o \
 	xe_gt_idle.o \
 	xe_gt_mcr.o \
@@ -59,7 +57,6 @@ xe-y += xe_bb.o \
 	xe_guc_ads.o \
 	xe_guc_ct.o \
 	xe_guc_db_mgr.o \
-	xe_guc_debugfs.o \
 	xe_guc_hwconfig.o \
 	xe_guc_id_mgr.o \
 	xe_guc_klv_helpers.o \
@@ -69,9 +66,9 @@ xe-y += xe_bb.o \
 	xe_heci_gsc.o \
 	xe_hw_engine.o \
 	xe_hw_engine_class_sysfs.o \
+	xe_hw_engine_group.o \
 	xe_hw_fence.o \
 	xe_huc.o \
-	xe_huc_debugfs.o \
 	xe_irq.o \
 	xe_lrc.o \
 	xe_migrate.o \
@@ -107,7 +104,6 @@ xe-y += xe_bb.o \
 	xe_ttm_vram_mgr.o \
 	xe_tuning.o \
 	xe_uc.o \
-	xe_uc_debugfs.o \
 	xe_uc_fw.o \
 	xe_vm.o \
 	xe_vram.o \
@@ -124,7 +120,6 @@ xe-$(CONFIG_HWMON) += xe_hwmon.o
 # graphics virtualization (SR-IOV) support
 xe-y += \
 	xe_gt_sriov_vf.o \
-	xe_gt_sriov_vf_debugfs.o \
 	xe_guc_relay.o \
 	xe_memirq.o \
 	xe_sriov.o
@@ -133,7 +128,6 @@ xe-$(CONFIG_PCI_IOV) += \
 	xe_gt_sriov_pf.o \
 	xe_gt_sriov_pf_config.o \
 	xe_gt_sriov_pf_control.o \
-	xe_gt_sriov_pf_debugfs.o \
 	xe_gt_sriov_pf_monitor.o \
 	xe_gt_sriov_pf_policy.o \
 	xe_gt_sriov_pf_service.o \
@@ -281,6 +275,16 @@ ifeq ($(CONFIG_DRM_FBDEV_EMULATION),y)
 endif
 
 ifeq ($(CONFIG_DEBUG_FS),y)
+	xe-y += xe_debugfs.o \
+		xe_gt_debugfs.o \
+		xe_gt_sriov_vf_debugfs.o \
+		xe_gt_stats.o \
+		xe_guc_debugfs.o \
+		xe_huc_debugfs.o \
+		xe_uc_debugfs.o
+
+	xe-$(CONFIG_PCI_IOV) += xe_gt_sriov_pf_debugfs.o
+
 	xe-$(CONFIG_DRM_XE_DISPLAY) += \
 		i915-display/intel_display_debugfs.o \
 		i915-display/intel_display_debugfs_params.o \

drivers/gpu/drm/xe/abi/guc_klvs_abi.h

@@ -351,6 +351,7 @@ enum xe_guc_klv_ids {
 	GUC_WORKAROUND_KLV_ID_GAM_PFQ_SHADOW_TAIL_POLLING				= 0x9005,
 	GUC_WORKAROUND_KLV_ID_DISABLE_MTP_DURING_ASYNC_COMPUTE				= 0x9007,
 	GUC_WA_KLV_NP_RD_WRITE_TO_CLEAR_RCSM_AT_CGP_LATE_RESTORE			= 0x9008,
+	GUC_WORKAROUND_KLV_ID_BACK_TO_BACK_RCS_ENGINE_RESET				= 0x9009,
 };
 
 #endif

drivers/gpu/drm/xe/compat-i915-headers/i915_vma.h

@@ -7,7 +7,8 @@
 #define I915_VMA_H
 
 #include <uapi/drm/i915_drm.h>
-#include <drm/drm_mm.h>
+
+#include "xe_ggtt_types.h"
 
 /* We don't want these from i915_drm.h in case of Xe */
 #undef I915_TILING_X
@@ -19,7 +20,7 @@ struct xe_bo;
 
 struct i915_vma {
 	struct xe_bo *bo, *dpt;
-	struct drm_mm_node node;
+	struct xe_ggtt_node *node;
 };
 
 #define i915_ggtt_clear_scanout(bo) do { } while (0)
@@ -28,7 +29,7 @@ struct i915_vma {
 
 static inline u32 i915_ggtt_offset(const struct i915_vma *vma)
 {
-	return vma->node.start;
+	return vma->node->base.start;
 }
 
 #endif