Merge tag 'drm-intel-gt-next-2023-08-04' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Driver Changes:

- Avoid infinite GPU waits by avoidin premature release of request's
  reusable memory (Chris, Janusz)
- Expose RPS thresholds in sysfs (Tvrtko)
- Apply GuC SLPC min frequency softlimit correctly (Vinay)
- Restore SLPC efficient freq earlier (Vinay)
- Consider OA buffer boundary when zeroing out reports (Umesh)
- Extend Wa_14015795083 to TGL, RKL, DG1 and ADL (Matt R)
- Fix context workarounds with non-masked regs on MTL/DG2 (Lucas)
- Enable the CCS_FLUSH bit in the pipe control and in the CS for MTL+ (Andi)
- Update MTL workarounds 14018778641, 22016122933 (Tejas, Zhanjun)
- Ensure memory quiesced before AUX CCS invalidation (Jonathan)

- Add a gsc_info debugfs (Daniele)
- Invalidate the TLBs on each GT on multi-GT device (Chris)
- Fix a VMA UAF for multi-gt platform (Nirmoy)
- Do not use stolen on MTL due to HW bug (Nirmoy)
- Check HuC and GuC version compatibility on MTL (Daniele)
- Dump perf_limit_reasons for slow GuC init debug (Vinay)
- Replace kmap() with kmap_local_page() (Sumitra, Ira)
- Add sentinel to xehp_oa_b_counters for KASAN (Andrzej)
- Add the gen12_needs_ccs_aux_inv helper (Andi)
- Fixes and updates for GSC memory allocation (Daniele)
- Fix one wrong caching mode enum usage (Tvrtko)
- Fixes for GSC wakeref (Alan)

- Static checker fixes (Harshit, Arnd, Dan, Cristophe, David, Andi)
- Rename flags with bit_group_X according to the datasheet (Andi)
- Use direct alias for i915 in requests (Andrzej)
- Replace i915->gt0 with to_gt(i915) (Andi)
- Use the i915_vma_flush_writes helper (Tvrtko)
- Selftest improvements (Alan)
- Remove dead code (Tvrtko)

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

# Conflicts:
#	drivers/gpu/drm/i915/gt/uc/intel_gsc_fw.c
From: Joonas Lahtinen <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: airlied

drivers/gpu/drm/i915/Makefile

@@ -132,6 +132,7 @@ gt-y += \
 	gt/intel_sseu.o \
 	gt/intel_sseu_debugfs.o \
 	gt/intel_timeline.o \
+	gt/intel_tlb.o \
 	gt/intel_wopcm.o \
 	gt/intel_workarounds.o \
 	gt/shmem_utils.o \
@@ -197,7 +198,8 @@ i915-y += \
 	  gt/uc/intel_gsc_fw.o \
 	  gt/uc/intel_gsc_proxy.o \
 	  gt/uc/intel_gsc_uc.o \
-	  gt/uc/intel_gsc_uc_heci_cmd_submit.o\
+	  gt/uc/intel_gsc_uc_debugfs.o \
+	  gt/uc/intel_gsc_uc_heci_cmd_submit.o \
 	  gt/uc/intel_guc.o \
 	  gt/uc/intel_guc_ads.o \
 	  gt/uc/intel_guc_capture.o \

drivers/gpu/drm/i915/gem/i915_gem_domain.c

@@ -68,10 +68,8 @@ flush_write_domain(struct drm_i915_gem_object *obj, unsigned int flush_domains)
 	switch (obj->write_domain) {
 	case I915_GEM_DOMAIN_GTT:
 		spin_lock(&obj->vma.lock);
-		for_each_ggtt_vma(vma, obj) {
-			if (i915_vma_unset_ggtt_write(vma))
-				intel_gt_flush_ggtt_writes(vma->vm->gt);
-		}
+		for_each_ggtt_vma(vma, obj)
+			i915_vma_flush_writes(vma);
 		spin_unlock(&obj->vma.lock);
 
 		i915_gem_object_flush_frontbuffer(obj, ORIGIN_CPU);

drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c

@@ -2229,8 +2229,8 @@ static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
 	u32 *cs;
 	int i;
 
-	if (GRAPHICS_VER(rq->engine->i915) != 7 || rq->engine->id != RCS0) {
-		drm_dbg(&rq->engine->i915->drm, "sol reset is gen7/rcs only\n");
+	if (GRAPHICS_VER(rq->i915) != 7 || rq->engine->id != RCS0) {
+		drm_dbg(&rq->i915->drm, "sol reset is gen7/rcs only\n");
 		return -EINVAL;
 	}
 
@@ -2691,6 +2691,7 @@ static int
 eb_select_engine(struct i915_execbuffer *eb)
 {
 	struct intel_context *ce, *child;
+	struct intel_gt *gt;
 	unsigned int idx;
 	int err;
 
@@ -2714,10 +2715,17 @@ eb_select_engine(struct i915_execbuffer *eb)
 		}
 	}
 	eb->num_batches = ce->parallel.number_children + 1;
+	gt = ce->engine->gt;
 
 	for_each_child(ce, child)
 		intel_context_get(child);
-	intel_gt_pm_get(ce->engine->gt);
+	intel_gt_pm_get(gt);
+	/*
+	 * Keep GT0 active on MTL so that i915_vma_parked() doesn't
+	 * free VMAs while execbuf ioctl is validating VMAs.
+	 */
+	if (gt->info.id)
+		intel_gt_pm_get(to_gt(gt->i915));
 
 	if (!test_bit(CONTEXT_ALLOC_BIT, &ce->flags)) {
 		err = intel_context_alloc_state(ce);
@@ -2756,7 +2764,10 @@ eb_select_engine(struct i915_execbuffer *eb)
 	return err;
 
 err:
-	intel_gt_pm_put(ce->engine->gt);
+	if (gt->info.id)
+		intel_gt_pm_put(to_gt(gt->i915));
+
+	intel_gt_pm_put(gt);
 	for_each_child(ce, child)
 		intel_context_put(child);
 	intel_context_put(ce);
@@ -2769,6 +2780,12 @@ eb_put_engine(struct i915_execbuffer *eb)
 	struct intel_context *child;
 
 	i915_vm_put(eb->context->vm);
+	/*
+	 * This works in conjunction with eb_select_engine() to prevent
+	 * i915_vma_parked() from interfering while execbuf validates vmas.
+	 */
+	if (eb->gt->info.id)
+		intel_gt_pm_put(to_gt(eb->gt->i915));
 	intel_gt_pm_put(eb->gt);
 	for_each_child(eb->context, child)
 		intel_context_put(child);

drivers/gpu/drm/i915/gem/i915_gem_object_types.h

@@ -17,6 +17,8 @@
 #include "i915_selftest.h"
 #include "i915_vma_resource.h"
 
+#include "gt/intel_gt_defines.h"
+
 struct drm_i915_gem_object;
 struct intel_fronbuffer;
 struct intel_memory_region;
@@ -675,7 +677,7 @@ struct drm_i915_gem_object {
 		 */
 		bool dirty:1;
 
-		u32 tlb;
+		u32 tlb[I915_MAX_GT];
 	} mm;
 
 	struct {

drivers/gpu/drm/i915/gem/i915_gem_pages.c

@@ -7,7 +7,7 @@
 #include <drm/drm_cache.h>
 
 #include "gt/intel_gt.h"
-#include "gt/intel_gt_pm.h"
+#include "gt/intel_tlb.h"
 
 #include "i915_drv.h"
 #include "i915_gem_object.h"
@@ -193,13 +193,16 @@ static void unmap_object(struct drm_i915_gem_object *obj, void *ptr)
 static void flush_tlb_invalidate(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	struct intel_gt *gt = to_gt(i915);
+	struct intel_gt *gt;
+	int id;
 
-	if (!obj->mm.tlb)
-		return;
+	for_each_gt(gt, i915, id) {
+		if (!obj->mm.tlb[id])
+			return;
 
-	intel_gt_invalidate_tlb(gt, obj->mm.tlb);
-	obj->mm.tlb = 0;
+		intel_gt_invalidate_tlb_full(gt, obj->mm.tlb[id]);
+		obj->mm.tlb[id] = 0;
+	}
 }
 
 struct sg_table *

drivers/gpu/drm/i915/gem/i915_gem_stolen.c

@@ -892,7 +892,7 @@ i915_gem_stolen_lmem_setup(struct drm_i915_private *i915, u16 type,
 	} else {
 		resource_size_t lmem_range;
 
-		lmem_range = intel_gt_mcr_read_any(&i915->gt0, XEHP_TILE0_ADDR_RANGE) & 0xFFFF;
+		lmem_range = intel_gt_mcr_read_any(to_gt(i915), XEHP_TILE0_ADDR_RANGE) & 0xFFFF;
 		lmem_size = lmem_range >> XEHP_TILE_LMEM_RANGE_SHIFT;
 		lmem_size *= SZ_1G;
 	}

drivers/gpu/drm/i915/gem/selftests/huge_pages.c

@@ -1246,8 +1246,10 @@ static int igt_write_huge(struct drm_i915_private *i915,
 	 * times in succession a possibility by enlarging the permutation array.
 	 */
 	order = i915_random_order(count * count, &prng);
-	if (!order)
-		return -ENOMEM;
+	if (!order) {
+		err = -ENOMEM;
+		goto out;
+	}
 
 	max_page_size = rounddown_pow_of_two(obj->mm.page_sizes.sg);
 	max = div_u64(max - size, max_page_size);

drivers/gpu/drm/i915/gt/gen2_engine_cs.c

@@ -76,7 +76,7 @@ int gen4_emit_flush_rcs(struct i915_request *rq, u32 mode)
 	cmd = MI_FLUSH;
 	if (mode & EMIT_INVALIDATE) {
 		cmd |= MI_EXE_FLUSH;
-		if (IS_G4X(rq->engine->i915) || GRAPHICS_VER(rq->engine->i915) == 5)
+		if (IS_G4X(rq->i915) || GRAPHICS_VER(rq->i915) == 5)
 			cmd |= MI_INVALIDATE_ISP;
 	}