Merge tag 'drm-intel-next-fixes-2022-12-01' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

airlied · airlied · commit b2268e26869a · 2022-12-09T10:30:07.000+10:00
- Multi-cast register fix (Matt) - Fix workarounds on gen2-3 (Tvrtko) - Bigjoiner fix (Ville) - Make Guc default_list a const data (Jani) - Acquire forcewake before uncore read (Umesh) - Selftest fix (Umesh) - HuC related fixes (Daniele) - Fix some incorrect return values (Janusz) - Fix a memory leak in bios related code (Xia) - Fix VBT send packet port selection (Mikko) - DG2's DMC fix bump for Register noclaims and few restore (Gustavo) Signed-off-by: Dave Airlie <airlied@redhat.com> From: Rodrigo Vivi <rodrigo.vivi@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/Y4jZBRw9KvlKgkr6@intel.com
diff --git a/drivers/gpu/drm/i915/display/intel_bios.c b/drivers/gpu/drm/i915/display/intel_bios.c
@@ -414,7 +414,7 @@ static void *generate_lfp_data_ptrs(struct drm_i915_private *i915,
 		ptrs->lvds_entries++;
 
 	if (size != 0 || ptrs->lvds_entries != 3) {
-		kfree(ptrs);
+		kfree(ptrs_block);
 		return NULL;
 	}
 
diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
@@ -3733,12 +3733,16 @@ static bool ilk_get_pipe_config(struct intel_crtc *crtc,
 
 static u8 bigjoiner_pipes(struct drm_i915_private *i915)
 {
+	u8 pipes;
+
 	if (DISPLAY_VER(i915) >= 12)
-		return BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D);
+		pipes = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C) | BIT(PIPE_D);
 	else if (DISPLAY_VER(i915) >= 11)
-		return BIT(PIPE_B) | BIT(PIPE_C);
+		pipes = BIT(PIPE_B) | BIT(PIPE_C);
 	else
-		return 0;
+		pipes = 0;
+
+	return pipes & RUNTIME_INFO(i915)->pipe_mask;
 }
 
 static bool transcoder_ddi_func_is_enabled(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/display/intel_dmc.c b/drivers/gpu/drm/i915/display/intel_dmc.c
@@ -52,8 +52,8 @@
 
 #define DISPLAY_VER12_DMC_MAX_FW_SIZE	ICL_DMC_MAX_FW_SIZE
 
-#define DG2_DMC_PATH			DMC_PATH(dg2, 2, 07)
-#define DG2_DMC_VERSION_REQUIRED	DMC_VERSION(2, 07)
+#define DG2_DMC_PATH			DMC_PATH(dg2, 2, 08)
+#define DG2_DMC_VERSION_REQUIRED	DMC_VERSION(2, 8)
 MODULE_FIRMWARE(DG2_DMC_PATH);
 
 #define ADLP_DMC_PATH			DMC_PATH(adlp, 2, 16)
diff --git a/drivers/gpu/drm/i915/display/intel_dsi_vbt.c b/drivers/gpu/drm/i915/display/intel_dsi_vbt.c
@@ -137,9 +137,9 @@ static enum port intel_dsi_seq_port_to_port(struct intel_dsi *intel_dsi,
 		return ffs(intel_dsi->ports) - 1;
 
 	if (seq_port) {
-		if (intel_dsi->ports & PORT_B)
+		if (intel_dsi->ports & BIT(PORT_B))
 			return PORT_B;
-		else if (intel_dsi->ports & PORT_C)
+		else if (intel_dsi->ports & BIT(PORT_C))
 			return PORT_C;
 	}
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -677,8 +677,13 @@ int intel_gt_wait_for_idle(struct intel_gt *gt, long timeout)
 			return -EINTR;
 	}
 
-	return timeout ? timeout : intel_uc_wait_for_idle(&gt->uc,
-							  remaining_timeout);
+	if (timeout)
+		return timeout;
+
+	if (remaining_timeout < 0)
+		remaining_timeout = 0;
+
+	return intel_uc_wait_for_idle(&gt->uc, remaining_timeout);
 }
 
 int intel_gt_init(struct intel_gt *gt)
@@ -1035,9 +1040,9 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
 static int wait_for_invalidate(struct intel_gt *gt, struct reg_and_bit rb)
 {
 	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
-		return intel_gt_mcr_wait_for_reg_fw(gt, rb.mcr_reg, rb.bit, 0,
-						    TLB_INVAL_TIMEOUT_US,
-						    TLB_INVAL_TIMEOUT_MS);
+		return intel_gt_mcr_wait_for_reg(gt, rb.mcr_reg, rb.bit, 0,
+						 TLB_INVAL_TIMEOUT_US,
+						 TLB_INVAL_TIMEOUT_MS);
 	else
 		return __intel_wait_for_register_fw(gt->uncore, rb.reg, rb.bit, 0,
 						    TLB_INVAL_TIMEOUT_US,
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.c b/drivers/gpu/drm/i915/gt/intel_gt_mcr.c
@@ -730,17 +730,19 @@ void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss,
  *
  * Return: 0 if the register matches the desired condition, or -ETIMEDOUT.
  */
-int intel_gt_mcr_wait_for_reg_fw(struct intel_gt *gt,
-				 i915_mcr_reg_t reg,
-				 u32 mask,
-				 u32 value,
-				 unsigned int fast_timeout_us,
-				 unsigned int slow_timeout_ms)
+int intel_gt_mcr_wait_for_reg(struct intel_gt *gt,
+			      i915_mcr_reg_t reg,
+			      u32 mask,
+			      u32 value,
+			      unsigned int fast_timeout_us,
+			      unsigned int slow_timeout_ms)
 {
-	u32 reg_value = 0;
-#define done (((reg_value = intel_gt_mcr_read_any_fw(gt, reg)) & mask) == value)
 	int ret;
 
+	lockdep_assert_not_held(&gt->uncore->lock);
+
+#define done ((intel_gt_mcr_read_any(gt, reg) & mask) == value)
+
 	/* Catch any overuse of this function */
 	might_sleep_if(slow_timeout_ms);
 	GEM_BUG_ON(fast_timeout_us > 20000);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_mcr.h b/drivers/gpu/drm/i915/gt/intel_gt_mcr.h
@@ -37,12 +37,12 @@ void intel_gt_mcr_report_steering(struct drm_printer *p, struct intel_gt *gt,
 void intel_gt_mcr_get_ss_steering(struct intel_gt *gt, unsigned int dss,
 				  unsigned int *group, unsigned int *instance);
 
-int intel_gt_mcr_wait_for_reg_fw(struct intel_gt *gt,
-				 i915_mcr_reg_t reg,
-				 u32 mask,
-				 u32 value,
-				 unsigned int fast_timeout_us,
-				 unsigned int slow_timeout_ms);
+int intel_gt_mcr_wait_for_reg(struct intel_gt *gt,
+			      i915_mcr_reg_t reg,
+			      u32 mask,
+			      u32 value,
+			      unsigned int fast_timeout_us,
+			      unsigned int slow_timeout_ms);
 
 /*
  * Helper for for_each_ss_steering loop.  On pre-Xe_HP platforms, subslice
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_requests.c b/drivers/gpu/drm/i915/gt/intel_gt_requests.c
@@ -199,7 +199,7 @@ out_active:	spin_lock(&timelines->lock);
 	if (remaining_timeout)
 		*remaining_timeout = timeout;
 
-	return active_count ? timeout : 0;
+	return active_count ? timeout ?: -ETIME : 0;
 }
 
 static void retire_work_handler(struct work_struct *work)
diff --git a/drivers/gpu/drm/i915/gt/intel_workarounds.c b/drivers/gpu/drm/i915/gt/intel_workarounds.c
@@ -3011,7 +3011,7 @@ general_render_compute_wa_init(struct intel_engine_cs *engine, struct i915_wa_li
 static void
 engine_init_workarounds(struct intel_engine_cs *engine, struct i915_wa_list *wal)
 {
-	if (I915_SELFTEST_ONLY(GRAPHICS_VER(engine->i915) < 4))
+	if (GRAPHICS_VER(engine->i915) < 4)
 		return;
 
 	engine_fake_wa_init(engine, wal);
@@ -3036,9 +3036,6 @@ void intel_engine_init_workarounds(struct intel_engine_cs *engine)
 {
 	struct i915_wa_list *wal = &engine->wa_list;
 
-	if (GRAPHICS_VER(engine->i915) < 4)
-		return;
-
 	wa_init_start(wal, engine->gt, "engine", engine->name);
 	engine_init_workarounds(engine, wal);
 	wa_init_finish(wal);
diff --git a/drivers/gpu/drm/i915/gt/selftest_engine_pm.c b/drivers/gpu/drm/i915/gt/selftest_engine_pm.c
@@ -317,7 +317,7 @@ static int live_engine_busy_stats(void *arg)
 		ENGINE_TRACE(engine, "measuring busy time\n");
 		preempt_disable();
 		de = intel_engine_get_busy_time(engine, &t[0]);
-		mdelay(10);
+		mdelay(100);
 		de = ktime_sub(intel_engine_get_busy_time(engine, &t[1]), de);
 		preempt_enable();
 		dt = ktime_sub(t[1], t[0]);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_capture.c
@@ -170,7 +170,7 @@ static const struct __guc_mmio_reg_descr empty_regs_list[] = {
 	}
 
 /* List of lists */
-static struct __guc_mmio_reg_descr_group default_lists[] = {
+static const struct __guc_mmio_reg_descr_group default_lists[] = {
 	MAKE_REGLIST(default_global_regs, PF, GLOBAL, 0),
 	MAKE_REGLIST(default_rc_class_regs, PF, ENGINE_CLASS, GUC_RENDER_CLASS),
 	MAKE_REGLIST(xe_lpd_rc_inst_regs, PF, ENGINE_INSTANCE, GUC_RENDER_CLASS),
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -211,6 +211,30 @@ void intel_huc_unregister_gsc_notifier(struct intel_huc *huc, struct bus_type *b
 	huc->delayed_load.nb.notifier_call = NULL;
 }
 
+static void delayed_huc_load_init(struct intel_huc *huc)
+{
+	/*
+	 * Initialize fence to be complete as this is expected to be complete
+	 * unless there is a delayed HuC load in progress.
+	 */
+	i915_sw_fence_init(&huc->delayed_load.fence,
+			   sw_fence_dummy_notify);
+	i915_sw_fence_commit(&huc->delayed_load.fence);
+
+	hrtimer_init(&huc->delayed_load.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	huc->delayed_load.timer.function = huc_delayed_load_timer_callback;
+}
+
+static void delayed_huc_load_fini(struct intel_huc *huc)
+{
+	/*
+	 * the fence is initialized in init_early, so we need to clean it up
+	 * even if HuC loading is off.
+	 */
+	delayed_huc_load_complete(huc);
+	i915_sw_fence_fini(&huc->delayed_load.fence);
+}
+
 static bool vcs_supported(struct intel_gt *gt)
 {
 	intel_engine_mask_t mask = gt->info.engine_mask;
@@ -241,6 +265,15 @@ void intel_huc_init_early(struct intel_huc *huc)
 
 	intel_uc_fw_init_early(&huc->fw, INTEL_UC_FW_TYPE_HUC);
 
+	/*
+	 * we always init the fence as already completed, even if HuC is not
+	 * supported. This way we don't have to distinguish between HuC not
+	 * supported/disabled or already loaded, and can focus on if the load
+	 * is currently in progress (fence not complete) or not, which is what
+	 * we care about for stalling userspace submissions.
+	 */
+	delayed_huc_load_init(huc);
+
 	if (!vcs_supported(gt)) {
 		intel_uc_fw_change_status(&huc->fw, INTEL_UC_FIRMWARE_NOT_SUPPORTED);
 		return;
@@ -255,17 +288,6 @@ void intel_huc_init_early(struct intel_huc *huc)
 		huc->status.mask = HUC_FW_VERIFIED;
 		huc->status.value = HUC_FW_VERIFIED;
 	}
-
-	/*
-	 * Initialize fence to be complete as this is expected to be complete
-	 * unless there is a delayed HuC reload in progress.
-	 */
-	i915_sw_fence_init(&huc->delayed_load.fence,
-			   sw_fence_dummy_notify);
-	i915_sw_fence_commit(&huc->delayed_load.fence);
-
-	hrtimer_init(&huc->delayed_load.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	huc->delayed_load.timer.function = huc_delayed_load_timer_callback;
 }
 
 #define HUC_LOAD_MODE_STRING(x) (x ? "GSC" : "legacy")
@@ -329,13 +351,14 @@ int intel_huc_init(struct intel_huc *huc)
 
 void intel_huc_fini(struct intel_huc *huc)
 {
-	if (!intel_uc_fw_is_loadable(&huc->fw))
-		return;
-
-	delayed_huc_load_complete(huc);
+	/*
+	 * the fence is initialized in init_early, so we need to clean it up
+	 * even if HuC loading is off.
+	 */
+	delayed_huc_load_fini(huc);
 
-	i915_sw_fence_fini(&huc->delayed_load.fence);
-	intel_uc_fw_fini(&huc->fw);
+	if (intel_uc_fw_is_loadable(&huc->fw))
+		intel_uc_fw_fini(&huc->fw);
 }
 
 void intel_huc_suspend(struct intel_huc *huc)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -722,6 +722,7 @@ int intel_uc_runtime_resume(struct intel_uc *uc)
 
 static const struct intel_uc_ops uc_ops_off = {
 	.init_hw = __uc_check_hw,
+	.fini = __uc_fini, /* to clean-up the init_early initialization */
 };
 
 static const struct intel_uc_ops uc_ops_on = {
diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
@@ -382,20 +382,6 @@ __uncore_write(write_notrace, 32, l, false)
  */
 __uncore_read(read64, 64, q, true)
 
-static inline u64
-intel_uncore_read64_2x32(struct intel_uncore *uncore,
-			 i915_reg_t lower_reg, i915_reg_t upper_reg)
-{
-	u32 upper, lower, old_upper, loop = 0;
-	upper = intel_uncore_read(uncore, upper_reg);
-	do {
-		old_upper = upper;
-		lower = intel_uncore_read(uncore, lower_reg);
-		upper = intel_uncore_read(uncore, upper_reg);
-	} while (upper != old_upper && loop++ < 2);
-	return (u64)upper << 32 | lower;
-}
-
 #define intel_uncore_posting_read(...) ((void)intel_uncore_read_notrace(__VA_ARGS__))
 #define intel_uncore_posting_read16(...) ((void)intel_uncore_read16_notrace(__VA_ARGS__))
 
@@ -455,6 +441,36 @@ static inline void intel_uncore_rmw_fw(struct intel_uncore *uncore,
 		intel_uncore_write_fw(uncore, reg, val);
 }
 
+static inline u64
+intel_uncore_read64_2x32(struct intel_uncore *uncore,
+			 i915_reg_t lower_reg, i915_reg_t upper_reg)
+{
+	u32 upper, lower, old_upper, loop = 0;
+	enum forcewake_domains fw_domains;
+	unsigned long flags;
+
+	fw_domains = intel_uncore_forcewake_for_reg(uncore, lower_reg,
+						    FW_REG_READ);
+
+	fw_domains |= intel_uncore_forcewake_for_reg(uncore, upper_reg,
+						    FW_REG_READ);
+
+	spin_lock_irqsave(&uncore->lock, flags);
+	intel_uncore_forcewake_get__locked(uncore, fw_domains);
+
+	upper = intel_uncore_read_fw(uncore, upper_reg);
+	do {
+		old_upper = upper;
+		lower = intel_uncore_read_fw(uncore, lower_reg);
+		upper = intel_uncore_read_fw(uncore, upper_reg);
+	} while (upper != old_upper && loop++ < 2);
+
+	intel_uncore_forcewake_put__locked(uncore, fw_domains);
+	spin_unlock_irqrestore(&uncore->lock, flags);
+
+	return (u64)upper << 32 | lower;
+}
+
 static inline int intel_uncore_write_and_verify(struct intel_uncore *uncore,
 						i915_reg_t reg, u32 val,
 						u32 mask, u32 expected_val)

Original file line number	Diff line number	Diff line change
`@@ -414,7 +414,7 @@ static void generate_lfp_data_ptrs(struct drm_i915_private i915,`
`414`	`414`	`ptrs->lvds_entries++;`
`415`	`415`
`416`	`416`	`if (size != 0 \|\| ptrs->lvds_entries != 3) {`
`417`		`- kfree(ptrs);`
	`417`	`+ kfree(ptrs_block);`
`418`	`418`	`return NULL;`
`419`	`419`	`}`
`420`	`420`
Original file line number	Diff line number	Diff line change
`@@ -199,7 +199,7 @@ out_active: spin_lock(&timelines->lock);`
`199`	`199`	`if (remaining_timeout)`
`200`	`200`	`*remaining_timeout = timeout;`
`201`	`201`
`202`		`- return active_count ? timeout : 0;`
	`202`	`+ return active_count ? timeout ?: -ETIME : 0;`
`203`	`203`	`}`
`204`	`204`
`205`	`205`	`static void retire_work_handler(struct work_struct *work)`