drm/i915: Define and use GuC and CTB TLB invalidation routines

The GuC firmware had defined the interface for Translation Look-Aside
Buffer (TLB) invalidation.  We should use this interface when
invalidating the engine and GuC TLBs.
Add additional functionality to intel_gt_invalidate_tlb, invalidating
the GuC TLBs and falling back to GT invalidation when the GuC is
disabled.
The invalidation is done by sending a request directly to the GuC
tlb_lookup that invalidates the table.  The invalidation is submitted as
a wait request and is performed in the CT event handler.  This means we
cannot perform this TLB invalidation path if the CT is not enabled.
If the request isn't fulfilled in two seconds, this would constitute
an error in the invalidation as that would constitute either a lost
request or a severe GuC overload.

With this new invalidation routine, we can perform GuC-based GGTT
invalidations.  GuC-based GGTT invalidation is incompatible with
MMIO invalidation so we should not perform MMIO invalidation when
GuC-based GGTT invalidation is expected.

The additional complexity incurred in this patch will be necessary for
range-based tlb invalidations, which will be platformed in the future.

Signed-off-by: Prathap Kumar Valsan <[email protected]>
Signed-off-by: Bruce Chang <[email protected]>
Signed-off-by: Chris Wilson <[email protected]>
Signed-off-by: Umesh Nerlige Ramappa <[email protected]>
Signed-off-by: Jonathan Cavitt <[email protected]>
Signed-off-by: Aravind Iddamsetty <[email protected]>
Signed-off-by: Fei Yang <[email protected]>
CC: Andi Shyti <[email protected]>
Reviewed-by: Andi Shyti <[email protected]>
Acked-by: Tvrtko Ursulin <[email protected]>
Acked-by: Nirmoy Das <[email protected]>
Reviewed-by: John Harrison <[email protected]>
Signed-off-by: Andi Shyti <[email protected]>
Link: https://patchwork.freedesktop.org/patch/msgid/[email protected]

Author: kvprathap

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

@@ -206,22 +206,36 @@ static void gen8_ggtt_invalidate(struct i915_ggtt *ggtt)
 	intel_uncore_write_fw(uncore, GFX_FLSH_CNTL_GEN6, GFX_FLSH_CNTL_EN);
 }
 
+static void guc_ggtt_ct_invalidate(struct intel_gt *gt)
+{
+	struct intel_uncore *uncore = gt->uncore;
+	intel_wakeref_t wakeref;
+
+	with_intel_runtime_pm_if_active(uncore->rpm, wakeref) {
+		struct intel_guc *guc = &gt->uc.guc;
+
+		intel_guc_invalidate_tlb_guc(guc);
+	}
+}
+
 static void guc_ggtt_invalidate(struct i915_ggtt *ggtt)
 {
 	struct drm_i915_private *i915 = ggtt->vm.i915;
+	struct intel_gt *gt;
 
 	gen8_ggtt_invalidate(ggtt);
 
-	if (GRAPHICS_VER(i915) >= 12) {
-		struct intel_gt *gt;
-
-		list_for_each_entry(gt, &ggtt->gt_list, ggtt_link)
+	list_for_each_entry(gt, &ggtt->gt_list, ggtt_link) {
+		if (intel_guc_tlb_invalidation_is_available(&gt->uc.guc)) {
+			guc_ggtt_ct_invalidate(gt);
+		} else if (GRAPHICS_VER(i915) >= 12) {
 			intel_uncore_write_fw(gt->uncore,
 					      GEN12_GUC_TLB_INV_CR,
 					      GEN12_GUC_TLB_INV_CR_INVALIDATE);
-	} else {
-		intel_uncore_write_fw(ggtt->vm.gt->uncore,
-				      GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+		} else {
+			intel_uncore_write_fw(gt->uncore,
+					      GEN8_GTCR, GEN8_GTCR_INVALIDATE);
+		}
 	}
 }
 
@@ -1243,7 +1257,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 		ggtt->vm.raw_insert_page = gen8_ggtt_insert_page;
 	}
 
-	if (intel_uc_wants_guc(&ggtt->vm.gt->uc))
+	if (intel_uc_wants_guc_submission(&ggtt->vm.gt->uc))
 		ggtt->invalidate = guc_ggtt_invalidate;
 	else
 		ggtt->invalidate = gen8_ggtt_invalidate;

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

@@ -12,6 +12,7 @@
 #include "intel_gt_print.h"
 #include "intel_gt_regs.h"
 #include "intel_tlb.h"
+#include "uc/intel_guc.h"
 
 /*
  * HW architecture suggest typical invalidation time at 40us,
@@ -131,11 +132,24 @@ void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
 		return;
 
 	with_intel_gt_pm_if_awake(gt, wakeref) {
+		struct intel_guc *guc = &gt->uc.guc;
+
 		mutex_lock(&gt->tlb.invalidate_lock);
 		if (tlb_seqno_passed(gt, seqno))
 			goto unlock;
 
-		mmio_invalidate_full(gt);
+		if (HAS_GUC_TLB_INVALIDATION(gt->i915)) {
+			/*
+			 * Only perform GuC TLB invalidation if GuC is ready.
+			 * The only time GuC could not be ready is on GT reset,
+			 * which would clobber all the TLBs anyways, making
+			 * any TLB invalidation path here unnecessary.
+			 */
+			if (intel_guc_is_ready(guc))
+				intel_guc_invalidate_tlb_engines(guc);
+		} else {
+			mmio_invalidate_full(gt);
+		}
 
 		write_seqcount_invalidate(&gt->tlb.seqno);
 unlock:

drivers/gpu/drm/i915/gt/uc/abi/guc_actions_abi.h

@@ -138,6 +138,8 @@ enum intel_guc_action {
 	INTEL_GUC_ACTION_REGISTER_CONTEXT_MULTI_LRC = 0x4601,
 	INTEL_GUC_ACTION_CLIENT_SOFT_RESET = 0x5507,
 	INTEL_GUC_ACTION_SET_ENG_UTIL_BUFF = 0x550A,
+	INTEL_GUC_ACTION_TLB_INVALIDATION = 0x7000,
+	INTEL_GUC_ACTION_TLB_INVALIDATION_DONE = 0x7001,
 	INTEL_GUC_ACTION_STATE_CAPTURE_NOTIFICATION = 0x8002,
 	INTEL_GUC_ACTION_NOTIFY_FLUSH_LOG_BUFFER_TO_FILE = 0x8003,
 	INTEL_GUC_ACTION_NOTIFY_CRASH_DUMP_POSTED = 0x8004,
@@ -181,4 +183,35 @@ enum intel_guc_state_capture_event_status {
 
 #define INTEL_GUC_STATE_CAPTURE_EVENT_STATUS_MASK      0x000000FF
 
+#define INTEL_GUC_TLB_INVAL_TYPE_MASK	REG_GENMASK(7, 0)
+#define INTEL_GUC_TLB_INVAL_MODE_MASK	REG_GENMASK(11, 8)
+#define INTEL_GUC_TLB_INVAL_FLUSH_CACHE REG_BIT(31)
+
+enum intel_guc_tlb_invalidation_type {
+	INTEL_GUC_TLB_INVAL_ENGINES = 0x0,
+	INTEL_GUC_TLB_INVAL_GUC = 0x3,
+};
+
+/*
+ * 0: Heavy mode of Invalidation:
+ * The pipeline of the engine(s) for which the invalidation is targeted to is
+ * blocked, and all the in-flight transactions are guaranteed to be Globally
+ * Observed before completing the TLB invalidation
+ * 1: Lite mode of Invalidation:
+ * TLBs of the targeted engine(s) are immediately invalidated.
+ * In-flight transactions are NOT guaranteed to be Globally Observed before
+ * completing TLB invalidation.
+ * Light Invalidation Mode is to be used only when
+ * it can be guaranteed (by SW) that the address translations remain invariant
+ * for the in-flight transactions across the TLB invalidation. In other words,
+ * this mode can be used when the TLB invalidation is intended to clear out the
+ * stale cached translations that are no longer in use. Light Invalidation Mode
+ * is much faster than the Heavy Invalidation Mode, as it does not wait for the
+ * in-flight transactions to be GOd.
+ */
+enum intel_guc_tlb_inval_mode {
+	INTEL_GUC_TLB_INVAL_MODE_HEAVY = 0x0,
+	INTEL_GUC_TLB_INVAL_MODE_LITE = 0x1,
+};
+
 #endif /* _ABI_GUC_ACTIONS_ABI_H */

drivers/gpu/drm/i915/gt/uc/intel_guc.h

@@ -79,6 +79,18 @@ struct intel_guc {
 	 */
 	atomic_t outstanding_submission_g2h;
 
+	/** @tlb_lookup: xarray to store all pending TLB invalidation requests */
+	struct xarray tlb_lookup;
+
+	/**
+	 * @serial_slot: id to the initial waiter created in tlb_lookup,
+	 * which is used only when failed to allocate new waiter.
+	 */
+	u32 serial_slot;
+
+	/** @next_seqno: the next id (sequence number) to allocate. */
+	u32 next_seqno;
+
 	/** @interrupts: pointers to GuC interrupt-managing functions. */
 	struct {
 		bool enabled;
@@ -288,6 +300,11 @@ struct intel_guc {
 #endif
 };
 
+struct intel_guc_tlb_wait {
+	struct wait_queue_head wq;
+	bool busy;
+};
+
 /*
  * GuC version number components are only 8-bit, so converting to a 32bit 8.8.8
  * integer works.
@@ -515,4 +532,9 @@ void intel_guc_dump_time_info(struct intel_guc *guc, struct drm_printer *p);
 
 int intel_guc_sched_disable_gucid_threshold_max(struct intel_guc *guc);
 
+bool intel_guc_tlb_invalidation_is_available(struct intel_guc *guc);
+int intel_guc_invalidate_tlb_engines(struct intel_guc *guc);
+int intel_guc_invalidate_tlb_guc(struct intel_guc *guc);
+int intel_guc_tlb_invalidation_done(struct intel_guc *guc,
+				    const u32 *payload, u32 len);
 #endif

drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c

@@ -1142,6 +1142,9 @@ static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *r
 	case INTEL_GUC_ACTION_NOTIFY_EXCEPTION:
 		ret = intel_guc_crash_process_msg(guc, action);
 		break;
+	case INTEL_GUC_ACTION_TLB_INVALIDATION_DONE:
+		ret = intel_guc_tlb_invalidation_done(guc, payload, len);
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 		break;
@@ -1213,9 +1216,17 @@ static int ct_handle_event(struct intel_guc_ct *ct, struct ct_incoming_msg *requ
 	switch (action) {
 	case INTEL_GUC_ACTION_SCHED_CONTEXT_MODE_DONE:
 	case INTEL_GUC_ACTION_DEREGISTER_CONTEXT_DONE:
+	case INTEL_GUC_ACTION_TLB_INVALIDATION_DONE:
 		g2h_release_space(ct, request->size);
 	}
 
+	/*
+	 * TLB invalidation responses must be handled immediately as processing
+	 * of other G2H notifications may be blocked by an invalidation request.
+	 */
+	if (action == INTEL_GUC_ACTION_TLB_INVALIDATION_DONE)
+		return ct_process_request(ct, request);
+
 	spin_lock_irqsave(&ct->requests.lock, flags);
 	list_add_tail(&request->link, &ct->requests.incoming);
 	spin_unlock_irqrestore(&ct->requests.lock, flags);

drivers/gpu/drm/i915/gt/uc/intel_guc_fwif.h

@@ -22,6 +22,7 @@
 /* Payload length only i.e. don't include G2H header length */
 #define G2H_LEN_DW_SCHED_CONTEXT_MODE_SET	2
 #define G2H_LEN_DW_DEREGISTER_CONTEXT		1
+#define G2H_LEN_DW_INVALIDATE_TLB		1
 
 #define GUC_CONTEXT_DISABLE		0
 #define GUC_CONTEXT_ENABLE		1