Merge tag 'drm-intel-next-fixes-2021-02-18' of...

Merge tag 'drm-intel-next-fixes-2021-02-18' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

- Restrict DRM_I915_DEBUG to developer builds (Chris)
- Fix return and error codes (Dan)
- Suspend/Resume fix (Chris)
- Disable atomics in L3 for gen9 (Chris)
- Flush before changing register state (Chris)
- Fix for GLK's HDMI (Ville)
- Fix ILK+'s plane strides with Xtiling (Ville)
- Correct surface base address for renderclear (Chris)
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YC7uQY1kt6w0tRp+@intel.com

drivers/gpu/drm/i915/Kconfig.debug

@@ -19,6 +19,8 @@ config DRM_I915_WERROR
 config DRM_I915_DEBUG
 	bool "Enable additional driver debugging"
 	depends on DRM_I915
+	depends on EXPERT # only for developers
+	depends on !COMPILE_TEST # never built by robots
 	select DEBUG_FS
 	select PREEMPT_COUNT
 	select I2C_CHARDEV

drivers/gpu/drm/i915/display/i9xx_plane.c

@@ -255,6 +255,33 @@ int i9xx_check_plane_surface(struct intel_plane_state *plane_state)
 	else
 		offset = 0;
 
+	/*
+	 * When using an X-tiled surface the plane starts to
+	 * misbehave if the x offset + width exceeds the stride.
+	 * hsw/bdw: underrun galore
+	 * ilk/snb/ivb: wrap to the next tile row mid scanout
+	 * i965/g4x: so far appear immune to this
+	 * vlv/chv: TODO check
+	 *
+	 * Linear surfaces seem to work just fine, even on hsw/bdw
+	 * despite them not using the linear offset anymore.
+	 */
+	if (INTEL_GEN(dev_priv) >= 4 && fb->modifier == I915_FORMAT_MOD_X_TILED) {
+		u32 alignment = intel_surf_alignment(fb, 0);
+		int cpp = fb->format->cpp[0];
+
+		while ((src_x + src_w) * cpp > plane_state->color_plane[0].stride) {
+			if (offset == 0) {
+				drm_dbg_kms(&dev_priv->drm,
+					    "Unable to find suitable display surface offset due to X-tiling\n");
+				return -EINVAL;
+			}
+
+			offset = intel_plane_adjust_aligned_offset(&src_x, &src_y, plane_state, 0,
+								   offset, offset - alignment);
+		}
+	}
+
 	/*
 	 * Put the final coordinates back so that the src
 	 * coordinate checks will see the right values.

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

@@ -1322,8 +1322,8 @@ static bool has_async_flips(struct drm_i915_private *i915)
 	return INTEL_GEN(i915) >= 5;
 }
 
-static unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
-					 int color_plane)
+unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
+				  int color_plane)
 {
 	struct drm_i915_private *dev_priv = to_i915(fb->dev);
 
@@ -1590,10 +1590,10 @@ static u32 intel_adjust_aligned_offset(int *x, int *y,
  * Adjust the tile offset by moving the difference into
  * the x/y offsets.
  */
-static u32 intel_plane_adjust_aligned_offset(int *x, int *y,
-					     const struct intel_plane_state *state,
-					     int color_plane,
-					     u32 old_offset, u32 new_offset)
+u32 intel_plane_adjust_aligned_offset(int *x, int *y,
+				      const struct intel_plane_state *state,
+				      int color_plane,
+				      u32 old_offset, u32 new_offset)
 {
 	return intel_adjust_aligned_offset(x, y, state->hw.fb, color_plane,
 					   state->hw.rotation,

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

@@ -653,6 +653,12 @@ void intel_plane_unpin_fb(struct intel_plane_state *old_plane_state);
 struct intel_encoder *
 intel_get_crtc_new_encoder(const struct intel_atomic_state *state,
 			   const struct intel_crtc_state *crtc_state);
+unsigned int intel_surf_alignment(const struct drm_framebuffer *fb,
+				  int color_plane);
+u32 intel_plane_adjust_aligned_offset(int *x, int *y,
+				      const struct intel_plane_state *state,
+				      int color_plane,
+				      u32 old_offset, u32 new_offset);
 
 /* modesetting */
 void intel_modeset_init_hw(struct drm_i915_private *i915);

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

@@ -2218,7 +2218,11 @@ hdmi_port_clock_valid(struct intel_hdmi *hdmi,
 					  has_hdmi_sink))
 		return MODE_CLOCK_HIGH;
 
-	/* BXT DPLL can't generate 223-240 MHz */
+	/* GLK DPLL can't generate 446-480 MHz */
+	if (IS_GEMINILAKE(dev_priv) && clock > 446666 && clock < 480000)
+		return MODE_CLOCK_RANGE;
+
+	/* BXT/GLK DPLL can't generate 223-240 MHz */
 	if (IS_GEN9_LP(dev_priv) && clock > 223333 && clock < 240000)
 		return MODE_CLOCK_RANGE;
 

drivers/gpu/drm/i915/gem/i915_gem_pm.c

@@ -85,6 +85,47 @@ void i915_gem_suspend_late(struct drm_i915_private *i915)
 		wbinvd_on_all_cpus();
 }
 
+int i915_gem_freeze(struct drm_i915_private *i915)
+{
+	/* Discard all purgeable objects, let userspace recover those as
+	 * required after resuming.
+	 */
+	i915_gem_shrink_all(i915);
+
+	return 0;
+}
+
+int i915_gem_freeze_late(struct drm_i915_private *i915)
+{
+	struct drm_i915_gem_object *obj;
+	intel_wakeref_t wakeref;
+
+	/*
+	 * Called just before we write the hibernation image.
+	 *
+	 * We need to update the domain tracking to reflect that the CPU
+	 * will be accessing all the pages to create and restore from the
+	 * hibernation, and so upon restoration those pages will be in the
+	 * CPU domain.
+	 *
+	 * To make sure the hibernation image contains the latest state,
+	 * we update that state just before writing out the image.
+	 *
+	 * To try and reduce the hibernation image, we manually shrink
+	 * the objects as well, see i915_gem_freeze()
+	 */
+
+	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
+		i915_gem_shrink(i915, -1UL, NULL, ~0);
+	i915_gem_drain_freed_objects(i915);
+
+	wbinvd_on_all_cpus();
+	list_for_each_entry(obj, &i915->mm.shrink_list, mm.link)
+		__start_cpu_write(obj);
+
+	return 0;
+}
+
 void i915_gem_resume(struct drm_i915_private *i915)
 {
 	GEM_TRACE("%s\n", dev_name(i915->drm.dev));

drivers/gpu/drm/i915/gem/i915_gem_pm.h

@@ -19,4 +19,7 @@ void i915_gem_idle_work_handler(struct work_struct *work);
 void i915_gem_suspend(struct drm_i915_private *i915);
 void i915_gem_suspend_late(struct drm_i915_private *i915);
 
+int i915_gem_freeze(struct drm_i915_private *i915);
+int i915_gem_freeze_late(struct drm_i915_private *i915);
+
 #endif /* __I915_GEM_PM_H__ */

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

@@ -753,22 +753,18 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *i915,
 	mutex_lock(&i915->mm.stolen_lock);
 	ret = drm_mm_reserve_node(&i915->mm.stolen, stolen);
 	mutex_unlock(&i915->mm.stolen_lock);
-	if (ret) {
-		obj = ERR_PTR(ret);
+	if (ret)
 		goto err_free;
-	}
 
 	obj = i915_gem_object_alloc();
 	if (!obj) {
-		obj = ERR_PTR(-ENOMEM);
+		ret = -ENOMEM;
 		goto err_stolen;
 	}
 
 	ret = __i915_gem_object_create_stolen(mem, obj, stolen);
-	if (ret) {
-		obj = ERR_PTR(ret);
+	if (ret)
 		goto err_object_free;
-	}
 
 	i915_gem_object_set_cache_coherency(obj, I915_CACHE_NONE);
 	return obj;
@@ -779,7 +775,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *i915,
 	i915_gem_stolen_remove_node(i915, stolen);
 err_free:
 	kfree(stolen);
-	return obj;
+	return ERR_PTR(ret);
 }
 
 bool i915_gem_object_is_stolen(const struct drm_i915_gem_object *obj)

drivers/gpu/drm/i915/gt/gen7_renderclear.c

@@ -240,7 +240,7 @@ gen7_emit_state_base_address(struct batch_chunk *batch,
 	/* general */
 	*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
 	/* surface */
-	*cs++ = batch_addr(batch) | surface_state_base | BASE_ADDRESS_MODIFY;
+	*cs++ = (batch_addr(batch) + surface_state_base) | BASE_ADDRESS_MODIFY;
 	/* dynamic */
 	*cs++ = batch_addr(batch) | BASE_ADDRESS_MODIFY;
 	/* indirect */
@@ -393,6 +393,7 @@ static void emit_batch(struct i915_vma * const vma,
 						     desc_count);
 
 	/* Reset inherited context registers */
+	gen7_emit_pipeline_flush(&cmds);
 	gen7_emit_pipeline_invalidate(&cmds);
 	batch_add(&cmds, MI_LOAD_REGISTER_IMM(2));
 	batch_add(&cmds, i915_mmio_reg_offset(CACHE_MODE_0_GEN7));

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

@@ -1834,6 +1834,14 @@ rcs_engine_wa_init(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 		wa_write_or(wal,
 			    GEN8_L3SQCREG4,
 			    GEN8_LQSC_FLUSH_COHERENT_LINES);
+
+		/* Disable atomics in L3 to prevent unrecoverable hangs */
+		wa_write_clr_set(wal, GEN9_SCRATCH_LNCF1,
+				 GEN9_LNCF_NONIA_COHERENT_ATOMICS_ENABLE, 0);
+		wa_write_clr_set(wal, GEN8_L3SQCREG4,
+				 GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE, 0);
+		wa_write_clr_set(wal, GEN9_SCRATCH1,
+				 EVICTION_PERF_FIX_ENABLE, 0);
 	}
 
 	if (IS_HASWELL(i915)) {

drivers/gpu/drm/i915/gvt/cmd_parser.c

@@ -3103,7 +3103,7 @@ void intel_gvt_update_reg_whitelist(struct intel_vgpu *vgpu)
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	struct i915_request *requests[I915_NUM_ENGINES] = {};
 	bool is_ctx_pinned[I915_NUM_ENGINES] = {};
-	int ret;
+	int ret = 0;
 
 	if (gvt->is_reg_whitelist_updated)
 		return;
@@ -3157,6 +3157,7 @@ void intel_gvt_update_reg_whitelist(struct intel_vgpu *vgpu)
 		if (IS_ERR(vaddr)) {
 			gvt_err("failed to pin init ctx obj, ring=%d, err=%lx\n",
 				id, PTR_ERR(vaddr));
+			ret = PTR_ERR(vaddr);
 			goto out;
 		}
 

drivers/gpu/drm/i915/i915_drv.c

@@ -65,6 +65,7 @@
 #include "gem/i915_gem_context.h"
 #include "gem/i915_gem_ioctls.h"
 #include "gem/i915_gem_mman.h"
+#include "gem/i915_gem_pm.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_rc6.h"

drivers/gpu/drm/i915/i915_drv.h

@@ -1800,8 +1800,6 @@ int i915_gem_init_userptr(struct drm_i915_private *dev_priv);
 void i915_gem_cleanup_userptr(struct drm_i915_private *dev_priv);
 void i915_gem_init_early(struct drm_i915_private *dev_priv);
 void i915_gem_cleanup_early(struct drm_i915_private *dev_priv);
-int i915_gem_freeze(struct drm_i915_private *dev_priv);
-int i915_gem_freeze_late(struct drm_i915_private *dev_priv);
 
 struct intel_memory_region *i915_gem_shmem_setup(struct drm_i915_private *i915);
 

drivers/gpu/drm/i915/i915_gem.c

@@ -1145,47 +1145,6 @@ void i915_gem_cleanup_early(struct drm_i915_private *dev_priv)
 	drm_WARN_ON(&dev_priv->drm, dev_priv->mm.shrink_count);
 }
 
-int i915_gem_freeze(struct drm_i915_private *dev_priv)
-{
-	/* Discard all purgeable objects, let userspace recover those as
-	 * required after resuming.
-	 */
-	i915_gem_shrink_all(dev_priv);
-
-	return 0;
-}
-
-int i915_gem_freeze_late(struct drm_i915_private *i915)
-{
-	struct drm_i915_gem_object *obj;
-	intel_wakeref_t wakeref;
-
-	/*
-	 * Called just before we write the hibernation image.
-	 *
-	 * We need to update the domain tracking to reflect that the CPU
-	 * will be accessing all the pages to create and restore from the
-	 * hibernation, and so upon restoration those pages will be in the
-	 * CPU domain.
-	 *
-	 * To make sure the hibernation image contains the latest state,
-	 * we update that state just before writing out the image.
-	 *
-	 * To try and reduce the hibernation image, we manually shrink
-	 * the objects as well, see i915_gem_freeze()
-	 */
-
-	with_intel_runtime_pm(&i915->runtime_pm, wakeref)
-		i915_gem_shrink(i915, -1UL, NULL, ~0);
-	i915_gem_drain_freed_objects(i915);
-
-	wbinvd_on_all_cpus();
-	list_for_each_entry(obj, &i915->mm.shrink_list, mm.link)
-		__start_cpu_write(obj);
-
-	return 0;
-}
-
 int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
 {
 	struct drm_i915_file_private *file_priv;

drivers/gpu/drm/i915/i915_reg.h

@@ -8225,6 +8225,7 @@ enum {
 #define  GEN11_LQSC_CLEAN_EVICT_DISABLE		(1 << 6)
 #define  GEN8_LQSC_RO_PERF_DIS			(1 << 27)
 #define  GEN8_LQSC_FLUSH_COHERENT_LINES		(1 << 21)
+#define  GEN8_LQSQ_NONIA_COHERENT_ATOMICS_ENABLE REG_BIT(22)
 
 /* GEN8 chicken */
 #define HDC_CHICKEN0				_MMIO(0x7300)
@@ -12107,6 +12108,12 @@ enum skl_power_gate {
 #define __GEN11_VCS2_MOCS0	0x10000
 #define GEN11_MFX2_MOCS(i)	_MMIO(__GEN11_VCS2_MOCS0 + (i) * 4)
 
+#define GEN9_SCRATCH_LNCF1		_MMIO(0xb008)
+#define   GEN9_LNCF_NONIA_COHERENT_ATOMICS_ENABLE REG_BIT(0)
+
+#define GEN9_SCRATCH1			_MMIO(0xb11c)
+#define   EVICTION_PERF_FIX_ENABLE	REG_BIT(8)
+
 #define GEN10_SCRATCH_LNCF2		_MMIO(0xb0a0)
 #define   PMFLUSHDONE_LNICRSDROP	(1 << 20)
 #define   PMFLUSH_GAPL3UNBLOCK		(1 << 21)

drivers/gpu/drm/i915/selftests/i915_gem.c

@@ -8,6 +8,7 @@
 
 #include "gem/selftests/igt_gem_utils.h"
 #include "gem/selftests/mock_context.h"
+#include "gem/i915_gem_pm.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"