Merge tag 'drm-intel-next-fixes-2022-08-11' of git://anongit.freedesktop.org/drm/drm-intel into drm-fixes

- disable pci resize on 32-bit systems (Nirmoy)
- don't leak the ccs state (Matt)
- TLB invalidation fixes (Chris)
[now with all fixes of fixes]

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YvVumNCga+90fYN0@intel.com

7 files changed, 123 insertions, 22 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index 68c2b0d8f187..f435e06125aa 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -11,7 +11,9 @@
 #include "pxp/intel_pxp.h"
 
 #include "i915_drv.h"
+#include "i915_perf_oa_regs.h"
 #include "intel_context.h"
+#include "intel_engine_pm.h"
 #include "intel_engine_regs.h"
 #include "intel_ggtt_gmch.h"
 #include "intel_gt.h"
@@ -36,8 +38,6 @@ static void __intel_gt_init_early(struct intel_gt *gt)
 {
 	spin_lock_init(&gt->irq_lock);
 
-	mutex_init(&gt->tlb_invalidate_lock);
-
 	INIT_LIST_HEAD(&gt->closed_vma);
 	spin_lock_init(&gt->closed_lock);
 
@@ -48,6 +48,8 @@ static void __intel_gt_init_early(struct intel_gt *gt)
 	intel_gt_init_reset(gt);
 	intel_gt_init_requests(gt);
 	intel_gt_init_timelines(gt);
+	mutex_init(&gt->tlb.invalidate_lock);
+	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
 	intel_gt_pm_init_early(gt);
 
 	intel_uc_init_early(&gt->uc);
@@ -768,6 +770,7 @@ void intel_gt_driver_late_release_all(struct drm_i915_private *i915)
 		intel_gt_fini_requests(gt);
 		intel_gt_fini_reset(gt);
 		intel_gt_fini_timelines(gt);
+		mutex_destroy(&gt->tlb.invalidate_lock);
 		intel_engines_free(gt);
 	}
 }
@@ -906,7 +909,7 @@ get_reg_and_bit(const struct intel_engine_cs *engine, const bool gen8,
 	return rb;
 }
 
-void intel_gt_invalidate_tlbs(struct intel_gt *gt)
+static void mmio_invalidate_full(struct intel_gt *gt)
 {
 	static const i915_reg_t gen8_regs[] = {
 		[RENDER_CLASS]			= GEN8_RTCR,
@@ -924,13 +927,11 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 	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;
 
-	if (I915_SELFTEST_ONLY(gt->awake == -ENODEV))
-		return;
-
 	if (GRAPHICS_VER(i915) == 12) {
 		regs = gen12_regs;
 		num = ARRAY_SIZE(gen12_regs);
@@ -945,28 +946,41 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 			  "Platform does not implement TLB invalidation!"))
 		return;
 
-	GEM_TRACE("\n");
-
-	assert_rpm_wakelock_held(&i915->runtime_pm);
-
-	mutex_lock(&gt->tlb_invalidate_lock);
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
 	spin_lock_irq(&uncore->lock); /* serialise invalidate with GT reset */
 
+	awake = 0;
 	for_each_engine(engine, gt, id) {
 		struct reg_and_bit rb;
 
+		if (!intel_engine_pm_is_awake(engine))
+			continue;
+
 		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
 		if (!i915_mmio_reg_offset(rb.reg))
 			continue;
 
 		intel_uncore_write_fw(uncore, rb.reg, rb.bit);
+		awake |= engine->mask;
 	}
 
+	GT_TRACE(gt, "invalidated engines %08x\n", awake);
+
+	/* Wa_2207587034:tgl,dg1,rkl,adl-s,adl-p */
+	if (awake &&
+	    (IS_TIGERLAKE(i915) ||
+	     IS_DG1(i915) ||
+	     IS_ROCKETLAKE(i915) ||
+	     IS_ALDERLAKE_S(i915) ||
+	     IS_ALDERLAKE_P(i915)))
+		intel_uncore_write_fw(uncore, GEN12_OA_TLB_INV_CR, 1);
+
 	spin_unlock_irq(&uncore->lock);
 
-	for_each_engine(engine, gt, id) {
+	for_each_engine_masked(engine, gt, awake, tmp) {
+		struct reg_and_bit rb;
+
 		/*
 		 * HW architecture suggest typical invalidation time at 40us,
 		 * with pessimistic cases up to 100us and a recommendation to
@@ -974,12 +988,8 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 		 */
 		const unsigned int timeout_us = 100;
 		const unsigned int timeout_ms = 4;
-		struct reg_and_bit rb;
 
 		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
-		if (!i915_mmio_reg_offset(rb.reg))
-			continue;
-
 		if (__intel_wait_for_register_fw(uncore,
 						 rb.reg, rb.bit, 0,
 						 timeout_us, timeout_ms,
@@ -996,5 +1006,38 @@ void intel_gt_invalidate_tlbs(struct intel_gt *gt)
 	 * transitions.
 	 */
 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
-	mutex_unlock(&gt->tlb_invalidate_lock);
+}
+
+static bool tlb_seqno_passed(const struct intel_gt *gt, u32 seqno)
+{
+	u32 cur = intel_gt_tlb_seqno(gt);
+
+	/* Only skip if a *full* TLB invalidate barrier has passed */
+	return (s32)(cur - ALIGN(seqno, 2)) > 0;
+}
+
+void intel_gt_invalidate_tlb(struct intel_gt *gt, u32 seqno)
+{
+	intel_wakeref_t wakeref;
+
+	if (I915_SELFTEST_ONLY(gt->awake == -ENODEV))
+		return;
+
+	if (intel_gt_is_wedged(gt))
+		return;
+
+	if (tlb_seqno_passed(gt, seqno))
+		return;
+
+	with_intel_gt_pm_if_awake(gt, wakeref) {
+		mutex_lock(&gt->tlb.invalidate_lock);
+		if (tlb_seqno_passed(gt, seqno))
+			goto unlock;
+
+		mmio_invalidate_full(gt);
+
+		write_seqcount_invalidate(&gt->tlb.seqno);
+unlock:
+		mutex_unlock(&gt->tlb.invalidate_lock);
+	}
 }
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.h b/drivers/gpu/drm/i915/gt/intel_gt.h
index 82d6f248d876..40b06adf509a 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -101,6 +101,16 @@ void intel_gt_info_print(const struct intel_gt_info *info,
 
 void intel_gt_watchdog_work(struct work_struct *work);
 
-void intel_gt_invalidate_tlbs(struct intel_gt *gt);
+static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt)
+{
+	return seqprop_sequence(&gt->tlb.seqno);
+}
+
+static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt)
+{
+	return intel_gt_tlb_seqno(gt) | 1;
+}
+
+void intel_gt_invalidate_tlb(struct intel_gt *gt, u32 seqno);
 
 #endif /* __INTEL_GT_H__ */
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_pm.h b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
index bc898df7a48c..a334787a4939 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_pm.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_pm.h
@@ -55,6 +55,9 @@ static inline void intel_gt_pm_might_put(struct intel_gt *gt)
 	for (tmp = 1, intel_gt_pm_get(gt); tmp; \
 	     intel_gt_pm_put(gt), tmp = 0)
 
+#define with_intel_gt_pm_if_awake(gt, wf) \
+	for (wf = intel_gt_pm_get_if_awake(gt); wf; intel_gt_pm_put_async(gt), wf = 0)
+
 static inline int intel_gt_pm_wait_for_idle(struct intel_gt *gt)
 {
 	return intel_wakeref_wait_for_idle(&gt->wakeref);
diff --git a/drivers/gpu/drm/i915/gt/intel_gt_types.h b/drivers/gpu/drm/i915/gt/intel_gt_types.h
index df708802889d..3804a583382b 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt_types.h
@@ -11,6 +11,7 @@
 #include <linux/llist.h>
 #include <linux/mutex.h>
 #include <linux/notifier.h>
+#include <linux/seqlock.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/workqueue.h>
@@ -83,7 +84,22 @@ struct intel_gt {
 	struct intel_uc uc;
 	struct intel_gsc gsc;
 
-	struct mutex tlb_invalidate_lock;
+	struct {
+		/* Serialize global tlb invalidations */
+		struct mutex invalidate_lock;
+
+		/*
+		 * Batch TLB invalidations
+		 *
+		 * After unbinding the PTE, we need to ensure the TLB
+		 * are invalidated prior to releasing the physical pages.
+		 * But we only need one such invalidation for all unbinds,
+		 * so we track how many TLB invalidations have been
+		 * performed since unbind the PTE and only emit an extra
+		 * invalidate if no full barrier has been passed.
+		 */
+		seqcount_mutex_t seqno;
+	} tlb;
 
 	struct i915_wa_list wa_list;
 
diff --git a/drivers/gpu/drm/i915/gt/intel_migrate.c b/drivers/gpu/drm/i915/gt/intel_migrate.c
index 2c35324b5f68..2b10b96b17b5 100644
--- a/drivers/gpu/drm/i915/gt/intel_migrate.c
+++ b/drivers/gpu/drm/i915/gt/intel_migrate.c
@@ -708,7 +708,7 @@ intel_context_migrate_copy(struct intel_context *ce,
 	u8 src_access, dst_access;
 	struct i915_request *rq;
 	int src_sz, dst_sz;
-	bool ccs_is_src;
+	bool ccs_is_src, overwrite_ccs;
 	int err;
 
 	GEM_BUG_ON(ce->vm != ce->engine->gt->migrate.context->vm);
@@ -749,6 +749,8 @@ intel_context_migrate_copy(struct intel_context *ce,
 			get_ccs_sg_sgt(&it_ccs, bytes_to_cpy);
 	}
 
+	overwrite_ccs = HAS_FLAT_CCS(i915) && !ccs_bytes_to_cpy && dst_is_lmem;
+
 	src_offset = 0;
 	dst_offset = CHUNK_SZ;
 	if (HAS_64K_PAGES(ce->engine->i915)) {
@@ -852,6 +854,25 @@ intel_context_migrate_copy(struct intel_context *ce,
 			if (err)
 				goto out_rq;
 			ccs_bytes_to_cpy -= ccs_sz;
+		} else if (overwrite_ccs) {
+			err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+			if (err)
+				goto out_rq;
+
+			/*
+			 * While we can't always restore/manage the CCS state,
+			 * we still need to ensure we don't leak the CCS state
+			 * from the previous user, so make sure we overwrite it
+			 * with something.
+			 */
+			err = emit_copy_ccs(rq, dst_offset, INDIRECT_ACCESS,
+					    dst_offset, DIRECT_ACCESS, len);
+			if (err)
+				goto out_rq;
+
+			err = rq->engine->emit_flush(rq, EMIT_INVALIDATE);
+			if (err)
+				goto out_rq;
 		}
 
 		/* Arbitration is re-enabled between requests. */
diff --git a/drivers/gpu/drm/i915/gt/intel_ppgtt.c b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
index d8b94d638559..6ee8d1127016 100644
--- a/drivers/gpu/drm/i915/gt/intel_ppgtt.c
+++ b/drivers/gpu/drm/i915/gt/intel_ppgtt.c
@@ -206,8 +206,12 @@ void ppgtt_bind_vma(struct i915_address_space *vm,
 void ppgtt_unbind_vma(struct i915_address_space *vm,
 		      struct i915_vma_resource *vma_res)
 {
-	if (vma_res->allocated)
-		vm->clear_range(vm, vma_res->start, vma_res->vma_size);
+	if (!vma_res->allocated)
+		return;
+
+	vm->clear_range(vm, vma_res->start, vma_res->vma_size);
+	if (vma_res->tlb)
+		vma_invalidate_tlb(vm, vma_res->tlb);
 }
 
 static unsigned long pd_count(u64 size, int shift)
diff --git a/drivers/gpu/drm/i915/gt/intel_region_lmem.c b/drivers/gpu/drm/i915/gt/intel_region_lmem.c
index 6e90032e12e9..aa6aed837194 100644
--- a/drivers/gpu/drm/i915/gt/intel_region_lmem.c
+++ b/drivers/gpu/drm/i915/gt/intel_region_lmem.c
@@ -15,6 +15,7 @@
 #include "gt/intel_gt_mcr.h"
 #include "gt/intel_gt_regs.h"
 
+#ifdef CONFIG_64BIT
 static void _release_bars(struct pci_dev *pdev)
 {
 	int resno;
@@ -111,6 +112,9 @@ static void i915_resize_lmem_bar(struct drm_i915_private *i915, resource_size_t
 	pci_assign_unassigned_bus_resources(pdev->bus);
 	pci_write_config_dword(pdev, PCI_COMMAND, pci_cmd);
 }
+#else
+static void i915_resize_lmem_bar(struct drm_i915_private *i915, resource_size_t lmem_size) {}
+#endif
 
 static int
 region_lmem_release(struct intel_memory_region *mem)