Merge tag 'drm-intel-gt-next-2023-03-16' of git://anongit.freedesktop.org/drm/drm-intel into drm-next

Driver Changes:

- Fix issue #6333: "list_add corruption" and full system lockup from
  performance monitoring (Janusz)
- Give the punit time to settle before fatally failing (Aravind, Chris)
- Don't use stolen memory or BAR for ring buffers on LLC platforms (John)
- Add missing ecodes and correct timeline seqno on GuC error captures (John)
- Make sure DSM size has correct 1MiB granularity on Gen12+ (Nirmoy,
  Lucas)
- Fix potential SSEU max_subslices array-index-out-of-bounds access on Gen11 (Andrea)
- Whitelist COMMON_SLICE_CHICKEN3 for UMD access on Gen12+ (Matt R.)
- Apply Wa_1408615072/Wa_1407596294 correctly on Gen11 (Matt R)
- Apply LNCF/LBCF workarounds correctly on XeHP SDV/PVC/DG2 (Matt R)
- Implement Wa_1606376872 for Xe_LP (Gustavo)
- Consider GSI offset when doing MCR lookups on Meteorlake+ (Matt R.)
- Add engine TLB invalidation for Meteorlake (Matt R.)
- Fix GSC Driver-FLR completion on Meteorlake (Alan)
- Fix GSC races on driver load/unload on Meteorlake+ (Daniele)
- Disable MC6 for MTL A step (Badal)

- Consolidate TLB invalidation flow (Tvrtko)
- Improve debug GuC/HuC debug messages (Michal Wa., John)
- Move fd_install after last use of fence (Rob)
- Initialize the obj flags for shmem objects (Aravind)
- Fix missing debug object activation (Nirmoy)
- Probe lmem before the stolen portion (Matt A)
- Improve clean up of GuC busyness stats worker (John)
- Fix missing return code checks in GuC submission init (John)
- Annotate two more workaround/tuning registers as MCR on PVC (Matt R)
- Fix GEN8_MISCCPCTL definition and remove unused INF_UNIT_LEVEL_CLKGATE (Lucas)
- Use sysfs_emit() and sysfs_emit_at() (Nirmoy)
- Make kobj_type structures constant (Thomas W.)
- make kobj attributes const on gt/ (Jani)
- Remove the unused virtualized start hack on buddy allocator (Matt A)
- Remove redundant check for DG1 (Lucas)
- Move DG2 tuning to the right function (Lucas)
- Rename dev_priv to i915 for private data naming consistency in gt/ (Andi)
- Remove unnecessary whitelisting of CS_CTX_TIMESTAMP on Xe_HP platforms (Matt R.)
-

- Escape wildcard in method names in kerneldoc (Bagas)
- Selftest improvements (Chris, Jonathan, Tvrtko, Anshuman, Tejas)
- Fix sparse warnings (Jani)

[airlied: fix unused variable in intel_workarounds]
Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ZBMSb42yjjzczRhj@jlahtine-mobl.ger.corp.intel.com

1 files changed, 49 insertions, 116 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index f4f694f12907..256cecf99dd1 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -784,6 +784,29 @@ void intel_gt_driver_unregister(struct intel_gt *gt)
 	intel_gsc_fini(&gt->gsc);
 
 	/*
+	 * If we unload the driver and wedge before the GSC worker is complete,
+	 * the worker will hit an error on its submission to the GSC engine and
+	 * then exit. This is hard to hit for a user, but it is reproducible
+	 * with skipping selftests. The error is handled gracefully by the
+	 * worker, so there are no functional issues, but we still end up with
+	 * an error message in dmesg, which is something we want to avoid as
+	 * this is a supported scenario. We could modify the worker to better
+	 * handle a wedging occurring during its execution, but that gets
+	 * complicated for a couple of reasons:
+	 * - We do want the error on runtime wedging, because there are
+	 *   implications for subsystems outside of GT (i.e., PXP, HDCP), it's
+	 *   only the error on driver unload that we want to silence.
+	 * - The worker is responsible for multiple submissions (GSC FW load,
+	 *   HuC auth, SW proxy), so all of those will have to be adapted to
+	 *   handle the wedged_on_fini scenario.
+	 * Therefore, it's much simpler to just wait for the worker to be done
+	 * before wedging on driver removal, also considering that the worker
+	 * will likely already be idle in the great majority of non-selftest
+	 * scenarios.
+	 */
+	intel_gsc_uc_flush_work(&gt->uc.gsc);
+
+	/*
 	 * Upon unregistering the device to prevent any new users, cancel
 	 * all in-flight requests so that we can quickly unbind the active
 	 * resources.
@@ -981,35 +1004,6 @@ void intel_gt_info_print(const struct intel_gt_info *info,
 	intel_sseu_dump(&info->sseu, p);
 }
 
-struct reg_and_bit {
-	union {
-		i915_reg_t reg;
-		i915_mcr_reg_t mcr_reg;
-	};
-	u32 bit;
-};
-
-static struct reg_and_bit
-get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
-		const i915_reg_t *regs, const unsigned int num)
-{
-	const unsigned int class = engine->class;
-	struct reg_and_bit rb = { };
-
-	if (gt_WARN_ON_ONCE(engine->gt, class >= num || !regs[class].reg))
-		return rb;
-
-	rb.reg = regs[class];
-	if (gen8 && class == VIDEO_DECODE_CLASS)
-		rb.reg.reg += 4 * engine->instance; /* GEN8_M2TCR */
-	else
-		rb.bit = engine->instance;
-
-	rb.bit = BIT(rb.bit);
-
-	return rb;
-}
-
 /*
  * HW architecture suggest typical invalidation time at 40us,
  * with pessimistic cases up to 100us and a recommendation to
@@ -1023,14 +1017,20 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
  * but are now considered MCR registers.  Since they exist within a GAM range,
  * the primary instance of the register rolls up the status from each unit.
  */
-static int wait_for_invalidate(struct intel_gt *gt, struct reg_and_bit rb)
+static int wait_for_invalidate(struct intel_engine_cs *engine)
 {
-	if (GRAPHICS_VER_FULL(gt->i915) >= IP_VER(12, 50))
-		return intel_gt_mcr_wait_for_reg(gt, rb.mcr_reg, rb.bit, 0,
+	if (engine->tlb_inv.mcr)
+		return intel_gt_mcr_wait_for_reg(engine->gt,
+						 engine->tlb_inv.reg.mcr_reg,
+						 engine->tlb_inv.done,
+						 0,
 						 TLB_INVAL_TIMEOUT_US,
 						 TLB_INVAL_TIMEOUT_MS);
 	else
-		return __intel_wait_for_register_fw(gt->uncore, rb.reg, rb.bit, 0,
+		return __intel_wait_for_register_fw(engine->gt->uncore,
+						    engine->tlb_inv.reg.reg,
+						    engine->tlb_inv.done,
+						    0,
 						    TLB_INVAL_TIMEOUT_US,
 						    TLB_INVAL_TIMEOUT_MS,
 						    NULL);
@@ -1038,62 +1038,14 @@ static int wait_for_invalidate(struct intel_gt *gt, struct reg_and_bit rb)
 
 static void mmio_invalidate_full(struct intel_gt *gt)
 {
-	static const i915_reg_t gen8_regs[] = {
-		[RENDER_CLASS]			= GEN8_RTCR,
-		[VIDEO_DECODE_CLASS]		= GEN8_M1TCR, /* , GEN8_M2TCR */
-		[VIDEO_ENHANCEMENT_CLASS]	= GEN8_VTCR,
-		[COPY_ENGINE_CLASS]		= GEN8_BTCR,
-	};
-	static const i915_reg_t gen12_regs[] = {
-		[RENDER_CLASS]			= GEN12_GFX_TLB_INV_CR,
-		[VIDEO_DECODE_CLASS]		= GEN12_VD_TLB_INV_CR,
-		[VIDEO_ENHANCEMENT_CLASS]	= GEN12_VE_TLB_INV_CR,
-		[COPY_ENGINE_CLASS]		= GEN12_BLT_TLB_INV_CR,
-		[COMPUTE_CLASS]			= GEN12_COMPCTX_TLB_INV_CR,
-	};
-	static const i915_mcr_reg_t xehp_regs[] = {
-		[RENDER_CLASS]			= XEHP_GFX_TLB_INV_CR,
-		[VIDEO_DECODE_CLASS]		= XEHP_VD_TLB_INV_CR,
-		[VIDEO_ENHANCEMENT_CLASS]	= XEHP_VE_TLB_INV_CR,
-		[COPY_ENGINE_CLASS]		= XEHP_BLT_TLB_INV_CR,
-		[COMPUTE_CLASS]			= XEHP_COMPCTX_TLB_INV_CR,
-	};
 	struct drm_i915_private *i915 = gt->i915;
 	struct intel_uncore *uncore = gt->uncore;
 	struct intel_engine_cs *engine;
 	intel_engine_mask_t awake, tmp;
 	enum intel_engine_id id;
-	const i915_reg_t *regs;
-	unsigned int num = 0;
 	unsigned long flags;
 
-	/*
-	 * New platforms should not be added with catch-all-newer (>=)
-	 * condition so that any later platform added triggers the below warning
-	 * and in turn mandates a human cross-check of whether the invalidation
-	 * flows have compatible semantics.
-	 *
-	 * For instance with the 11.00 -> 12.00 transition three out of five
-	 * respective engine registers were moved to masked type. Then after the
-	 * 12.00 -> 12.50 transition multi cast handling is required too.
-	 */
-
-	if (GRAPHICS_VER_FULL(i915) == IP_VER(12, 50) ||
-	    GRAPHICS_VER_FULL(i915) == IP_VER(12, 55)) {
-		regs = NULL;
-		num = ARRAY_SIZE(xehp_regs);
-	} else if (GRAPHICS_VER_FULL(i915) == IP_VER(12, 0) ||
-		   GRAPHICS_VER_FULL(i915) == IP_VER(12, 10)) {
-		regs = gen12_regs;
-		num = ARRAY_SIZE(gen12_regs);
-	} else if (GRAPHICS_VER(i915) >= 8 && GRAPHICS_VER(i915) <= 11) {
-		regs = gen8_regs;
-		num = ARRAY_SIZE(gen8_regs);
-	} else if (GRAPHICS_VER(i915) < 8) {
-		return;
-	}
-
-	if (gt_WARN_ONCE(gt, !num, "Platform does not implement TLB invalidation!"))
+	if (GRAPHICS_VER(i915) < 8)
 		return;
 
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
@@ -1103,33 +1055,18 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 
 	awake = 0;
 	for_each_engine(engine, gt, id) {
-		struct reg_and_bit rb;
-
 		if (!intel_engine_pm_is_awake(engine))
 			continue;
 
-		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
-			u32 val = BIT(engine->instance);
-
-			if (engine->class == VIDEO_DECODE_CLASS ||
-			    engine->class == VIDEO_ENHANCEMENT_CLASS ||
-			    engine->class == COMPUTE_CLASS)
-				val = _MASKED_BIT_ENABLE(val);
+		if (engine->tlb_inv.mcr)
 			intel_gt_mcr_multicast_write_fw(gt,
-							xehp_regs[engine->class],
-							val);
-		} else {
-			rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
-			if (!i915_mmio_reg_offset(rb.reg))
-				continue;
-
-			if (GRAPHICS_VER(i915) == 12 && (engine->class == VIDEO_DECODE_CLASS ||
-			    engine->class == VIDEO_ENHANCEMENT_CLASS ||
-			    engine->class == COMPUTE_CLASS))
-				rb.bit = _MASKED_BIT_ENABLE(rb.bit);
-
-			intel_uncore_write_fw(uncore, rb.reg, rb.bit);
-		}
+							engine->tlb_inv.reg.mcr_reg,
+							engine->tlb_inv.request);
+		else
+			intel_uncore_write_fw(uncore,
+					      engine->tlb_inv.reg.reg,
+					      engine->tlb_inv.request);
+
 		awake |= engine->mask;
 	}
 
@@ -1148,17 +1085,9 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 	intel_gt_mcr_unlock(gt, flags);
 
 	for_each_engine_masked(engine, gt, awake, tmp) {
-		struct reg_and_bit rb;
-
-		if (GRAPHICS_VER_FULL(i915) >= IP_VER(12, 50)) {
-			rb.mcr_reg = xehp_regs[engine->class];
-			rb.bit = BIT(engine->instance);
-		} else {
-			rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
-		}
-
-		if (wait_for_invalidate(gt, rb))
-			gt_err_ratelimited(gt, "%s TLB invalidation did not complete in %ums!\n",
+		if (wait_for_invalidate(engine))
+			gt_err_ratelimited(gt,
+					   "%s TLB invalidation did not complete in %ums!\n",
 					   engine->name, TLB_INVAL_TIMEOUT_MS);
 	}
 
@@ -1204,3 +1133,7 @@ unlock:
 		mutex_unlock(&gt->tlb.invalidate_lock);
 	}
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+#include "selftest_tlb.c"
+#endif