[Intel-gfx] [PATCH v2 0/2] Move TLB invalidation code for its own file and document it

[Intel-gfx] [PATCH v2 0/2] Move TLB invalidation code for its own file and document it

[Mauro Carvalho Chehab]

There are more things to be added to TLB invalidation. Before doing that,
move the code to its own file, and add the relevant documentation.

Patch 1 only moves the code and do some function renames. No functional
change.

Patch 2 adds documentation for the TLB invalidation algorithm and functions.

---

v2: only patch 2 (kernel-doc) was modified:

  - The kernel-doc markups for TLB were added to i915.rst doc;
  - Some minor fixes at the texts;
  - Use a table instead of a literal block while explaining how the algorithm works.
    That should make easier to understand the logic, both in text form and after
    its conversion to HTML/PDF;
  - Remove mention for GuC, as this depends on a series that will be sent later.

Chris Wilson (1):
  drm/i915/gt: Move TLB invalidation to its own file

Mauro Carvalho Chehab (1):
  drm/i915/gt: document TLB cache invalidation functions

 Documentation/gpu/i915.rst                |   7 +
 drivers/gpu/drm/i915/Makefile             |   1 +
 drivers/gpu/drm/i915/gem/i915_gem_pages.c |   4 +-
 drivers/gpu/drm/i915/gt/intel_gt.c        | 168 +----------------
 drivers/gpu/drm/i915/gt/intel_gt.h        |  12 --
 drivers/gpu/drm/i915/gt/intel_tlb.c       | 208 ++++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_tlb.h       | 130 ++++++++++++++
 drivers/gpu/drm/i915/i915_vma.c           |   1 +
 8 files changed, 352 insertions(+), 179 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/gt/intel_tlb.c
 create mode 100644 drivers/gpu/drm/i915/gt/intel_tlb.h

-- 
2.36.1

[PATCH v2 0/2] Move TLB invalidation code for its own file and document it

[Mauro Carvalho Chehab]

There are more things to be added to TLB invalidation. Before doing that,
move the code to its own file, and add the relevant documentation.

Patch 1 only moves the code and do some function renames. No functional
change.

Patch 2 adds documentation for the TLB invalidation algorithm and functions.

---

v2: only patch 2 (kernel-doc) was modified:

  - The kernel-doc markups for TLB were added to i915.rst doc;
  - Some minor fixes at the texts;
  - Use a table instead of a literal block while explaining how the algorithm works.
    That should make easier to understand the logic, both in text form and after
    its conversion to HTML/PDF;
  - Remove mention for GuC, as this depends on a series that will be sent later.

Chris Wilson (1):
  drm/i915/gt: Move TLB invalidation to its own file

Mauro Carvalho Chehab (1):
  drm/i915/gt: document TLB cache invalidation functions

 Documentation/gpu/i915.rst                |   7 +
 drivers/gpu/drm/i915/Makefile             |   1 +
 drivers/gpu/drm/i915/gem/i915_gem_pages.c |   4 +-
 drivers/gpu/drm/i915/gt/intel_gt.c        | 168 +----------------
 drivers/gpu/drm/i915/gt/intel_gt.h        |  12 --
 drivers/gpu/drm/i915/gt/intel_tlb.c       | 208 ++++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_tlb.h       | 130 ++++++++++++++
 drivers/gpu/drm/i915/i915_vma.c           |   1 +
 8 files changed, 352 insertions(+), 179 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/gt/intel_tlb.c
 create mode 100644 drivers/gpu/drm/i915/gt/intel_tlb.h

-- 
2.36.1

[PATCH v2 0/2] Move TLB invalidation code for its own file and document it

[Mauro Carvalho Chehab]

There are more things to be added to TLB invalidation. Before doing that,
move the code to its own file, and add the relevant documentation.

Patch 1 only moves the code and do some function renames. No functional
change.

Patch 2 adds documentation for the TLB invalidation algorithm and functions.

---

v2: only patch 2 (kernel-doc) was modified:

  - The kernel-doc markups for TLB were added to i915.rst doc;
  - Some minor fixes at the texts;
  - Use a table instead of a literal block while explaining how the algorithm works.
    That should make easier to understand the logic, both in text form and after
    its conversion to HTML/PDF;
  - Remove mention for GuC, as this depends on a series that will be sent later.

Chris Wilson (1):
  drm/i915/gt: Move TLB invalidation to its own file

Mauro Carvalho Chehab (1):
  drm/i915/gt: document TLB cache invalidation functions

 Documentation/gpu/i915.rst                |   7 +
 drivers/gpu/drm/i915/Makefile             |   1 +
 drivers/gpu/drm/i915/gem/i915_gem_pages.c |   4 +-
 drivers/gpu/drm/i915/gt/intel_gt.c        | 168 +----------------
 drivers/gpu/drm/i915/gt/intel_gt.h        |  12 --
 drivers/gpu/drm/i915/gt/intel_tlb.c       | 208 ++++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_tlb.h       | 130 ++++++++++++++
 drivers/gpu/drm/i915/i915_vma.c           |   1 +
 8 files changed, 352 insertions(+), 179 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/gt/intel_tlb.c
 create mode 100644 drivers/gpu/drm/i915/gt/intel_tlb.h

-- 
2.36.1

[Intel-gfx] [PATCH v2 1/2] drm/i915/gt: Move TLB invalidation to its own file

[Mauro Carvalho Chehab]

From: Chris Wilson <chris.p.wilson@intel.com>

Prepare for supporting more TLB invalidation scenarios by moving
the current MMIO invalidation to its own file.

Signed-off-by: Chris Wilson <chris.p.wilson@intel.com>
Cc: Fei Yang <fei.yang@intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---

To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
See [PATCH v2 0/2] at: https://lore.kernel.org/all/cover.1659077372.git.mchehab@kernel.org/

 drivers/gpu/drm/i915/Makefile             |   1 +
 drivers/gpu/drm/i915/gem/i915_gem_pages.c |   4 +-
 drivers/gpu/drm/i915/gt/intel_gt.c        | 168 +-------------------
 drivers/gpu/drm/i915/gt/intel_gt.h        |  12 --
 drivers/gpu/drm/i915/gt/intel_tlb.c       | 183 ++++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_tlb.h       |  29 ++++
 drivers/gpu/drm/i915/i915_vma.c           |   1 +
 7 files changed, 219 insertions(+), 179 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/gt/intel_tlb.c
 create mode 100644 drivers/gpu/drm/i915/gt/intel_tlb.h

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 522ef9b4aff3..d3df9832d1f7 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -126,6 +126,7 @@ gt-y += \
 	gt/intel_sseu.o \
 	gt/intel_sseu_debugfs.o \
 	gt/intel_timeline.o \
+	gt/intel_tlb.o \
 	gt/intel_workarounds.o \
 	gt/shmem_utils.o \
 	gt/sysfs_engines.o
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 8357dbdcab5c..1cd76cc5d9f3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -7,7 +7,7 @@
 #include <drm/drm_cache.h>
 
 #include "gt/intel_gt.h"
-#include "gt/intel_gt_pm.h"
+#include "gt/intel_tlb.h"
 
 #include "i915_drv.h"
 #include "i915_gem_object.h"
@@ -199,7 +199,7 @@ static void flush_tlb_invalidate(struct drm_i915_gem_object *obj)
 	if (!obj->mm.tlb)
 		return;
 
-	intel_gt_invalidate_tlb(gt, obj->mm.tlb);
+	intel_gt_invalidate_tlb_full(gt, obj->mm.tlb);
 	obj->mm.tlb = 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index f435e06125aa..18d82cd620bd 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -11,9 +11,7 @@
 #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"
@@ -31,6 +29,7 @@
 #include "intel_renderstate.h"
 #include "intel_rps.h"
 #include "intel_gt_sysfs.h"
+#include "intel_tlb.h"
 #include "intel_uncore.h"
 #include "shmem_utils.h"
 
@@ -48,8 +47,7 @@ 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_init_tlb(gt);
 	intel_gt_pm_init_early(gt);
 
 	intel_uc_init_early(&gt->uc);
@@ -770,7 +768,7 @@ 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_gt_fini_tlb(gt);
 		intel_engines_free(gt);
 	}
 }
@@ -881,163 +879,3 @@ void intel_gt_info_print(const struct intel_gt_info *info,
 
 	intel_sseu_dump(&info->sseu, p);
 }
-
-struct reg_and_bit {
-	i915_reg_t 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 (drm_WARN_ON_ONCE(&engine->i915->drm,
-			     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;
-}
-
-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,
-	};
-	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 (GRAPHICS_VER(i915) == 12) {
-		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 (drm_WARN_ONCE(&i915->drm, !num,
-			  "Platform does not implement TLB invalidation!"))
-		return;
-
-	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_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
-		 * cap at 1ms. We go a bit higher just in case.
-		 */
-		const unsigned int timeout_us = 100;
-		const unsigned int timeout_ms = 4;
-
-		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
-		if (__intel_wait_for_register_fw(uncore,
-						 rb.reg, rb.bit, 0,
-						 timeout_us, timeout_ms,
-						 NULL))
-			drm_err_ratelimited(&gt->i915->drm,
-					    "%s TLB invalidation did not complete in %ums!\n",
-					    engine->name, timeout_ms);
-	}
-
-	/*
-	 * Use delayed put since a) we mostly expect a flurry of TLB
-	 * invalidations so it is good to avoid paying the forcewake cost and
-	 * b) it works around a bug in Icelake which cannot cope with too rapid
-	 * transitions.
-	 */
-	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
-}
-
-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 40b06adf509a..b4bba16cdb53 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -101,16 +101,4 @@ void intel_gt_info_print(const struct intel_gt_info *info,
 
 void intel_gt_watchdog_work(struct work_struct *work);
 
-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_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c
new file mode 100644
index 000000000000..af8cae979489
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_tlb.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "i915_perf_oa_regs.h"
+#include "intel_engine_pm.h"
+#include "intel_gt.h"
+#include "intel_gt_pm.h"
+#include "intel_gt_regs.h"
+#include "intel_tlb.h"
+
+struct reg_and_bit {
+	i915_reg_t 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 (drm_WARN_ON_ONCE(&engine->i915->drm,
+			     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;
+}
+
+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;
+}
+
+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,
+	};
+	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 (GRAPHICS_VER(i915) == 12) {
+		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 (drm_WARN_ONCE(&i915->drm, !num,
+			  "Platform does not implement TLB invalidation!"))
+		return;
+
+	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_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
+		 * cap at 1ms. We go a bit higher just in case.
+		 */
+		const unsigned int timeout_us = 100;
+		const unsigned int timeout_ms = 4;
+
+		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+		if (__intel_wait_for_register_fw(uncore,
+						 rb.reg, rb.bit, 0,
+						 timeout_us, timeout_ms,
+						 NULL))
+			drm_err_ratelimited(&gt->i915->drm,
+					    "%s TLB invalidation did not complete in %ums!\n",
+					    engine->name, timeout_ms);
+	}
+
+	/*
+	 * Use delayed put since a) we mostly expect a flurry of TLB
+	 * invalidations so it is good to avoid paying the forcewake cost and
+	 * b) it works around a bug in Icelake which cannot cope with too rapid
+	 * transitions.
+	 */
+	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
+}
+
+void intel_gt_invalidate_tlb_full(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);
+	}
+}
+
+void intel_gt_init_tlb(struct intel_gt *gt)
+{
+	mutex_init(&gt->tlb.invalidate_lock);
+	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
+}
+
+void intel_gt_fini_tlb(struct intel_gt *gt)
+{
+	mutex_destroy(&gt->tlb.invalidate_lock);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.h b/drivers/gpu/drm/i915/gt/intel_tlb.h
new file mode 100644
index 000000000000..46ce25bf5afe
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_tlb.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef INTEL_TLB_H
+#define INTEL_TLB_H
+
+#include <linux/seqlock.h>
+#include <linux/types.h>
+
+#include "intel_gt_types.h"
+
+void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno);
+
+void intel_gt_init_tlb(struct intel_gt *gt);
+void intel_gt_fini_tlb(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;
+}
+
+#endif /* INTEL_TLB_H */
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 84a9ccbc5fc5..fe947d1456d5 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -33,6 +33,7 @@
 #include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_requests.h"
+#include "gt/intel_tlb.h"
 
 #include "i915_drv.h"
 #include "i915_gem_evict.h"
-- 
2.36.1

[PATCH v2 1/2] drm/i915/gt: Move TLB invalidation to its own file

[Mauro Carvalho Chehab]

From: Chris Wilson <chris.p.wilson@intel.com>

Prepare for supporting more TLB invalidation scenarios by moving
the current MMIO invalidation to its own file.

Signed-off-by: Chris Wilson <chris.p.wilson@intel.com>
Cc: Fei Yang <fei.yang@intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---

To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
See [PATCH v2 0/2] at: https://lore.kernel.org/all/cover.1659077372.git.mchehab@kernel.org/

 drivers/gpu/drm/i915/Makefile             |   1 +
 drivers/gpu/drm/i915/gem/i915_gem_pages.c |   4 +-
 drivers/gpu/drm/i915/gt/intel_gt.c        | 168 +-------------------
 drivers/gpu/drm/i915/gt/intel_gt.h        |  12 --
 drivers/gpu/drm/i915/gt/intel_tlb.c       | 183 ++++++++++++++++++++++
 drivers/gpu/drm/i915/gt/intel_tlb.h       |  29 ++++
 drivers/gpu/drm/i915/i915_vma.c           |   1 +
 7 files changed, 219 insertions(+), 179 deletions(-)
 create mode 100644 drivers/gpu/drm/i915/gt/intel_tlb.c
 create mode 100644 drivers/gpu/drm/i915/gt/intel_tlb.h

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 522ef9b4aff3..d3df9832d1f7 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -126,6 +126,7 @@ gt-y += \
 	gt/intel_sseu.o \
 	gt/intel_sseu_debugfs.o \
 	gt/intel_timeline.o \
+	gt/intel_tlb.o \
 	gt/intel_workarounds.o \
 	gt/shmem_utils.o \
 	gt/sysfs_engines.o
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
index 8357dbdcab5c..1cd76cc5d9f3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
@@ -7,7 +7,7 @@
 #include <drm/drm_cache.h>
 
 #include "gt/intel_gt.h"
-#include "gt/intel_gt_pm.h"
+#include "gt/intel_tlb.h"
 
 #include "i915_drv.h"
 #include "i915_gem_object.h"
@@ -199,7 +199,7 @@ static void flush_tlb_invalidate(struct drm_i915_gem_object *obj)
 	if (!obj->mm.tlb)
 		return;
 
-	intel_gt_invalidate_tlb(gt, obj->mm.tlb);
+	intel_gt_invalidate_tlb_full(gt, obj->mm.tlb);
 	obj->mm.tlb = 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
index f435e06125aa..18d82cd620bd 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.c
+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
@@ -11,9 +11,7 @@
 #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"
@@ -31,6 +29,7 @@
 #include "intel_renderstate.h"
 #include "intel_rps.h"
 #include "intel_gt_sysfs.h"
+#include "intel_tlb.h"
 #include "intel_uncore.h"
 #include "shmem_utils.h"
 
@@ -48,8 +47,7 @@ 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_init_tlb(gt);
 	intel_gt_pm_init_early(gt);
 
 	intel_uc_init_early(&gt->uc);
@@ -770,7 +768,7 @@ 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_gt_fini_tlb(gt);
 		intel_engines_free(gt);
 	}
 }
@@ -881,163 +879,3 @@ void intel_gt_info_print(const struct intel_gt_info *info,
 
 	intel_sseu_dump(&info->sseu, p);
 }
-
-struct reg_and_bit {
-	i915_reg_t 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 (drm_WARN_ON_ONCE(&engine->i915->drm,
-			     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;
-}
-
-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,
-	};
-	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 (GRAPHICS_VER(i915) == 12) {
-		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 (drm_WARN_ONCE(&i915->drm, !num,
-			  "Platform does not implement TLB invalidation!"))
-		return;
-
-	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_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
-		 * cap at 1ms. We go a bit higher just in case.
-		 */
-		const unsigned int timeout_us = 100;
-		const unsigned int timeout_ms = 4;
-
-		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
-		if (__intel_wait_for_register_fw(uncore,
-						 rb.reg, rb.bit, 0,
-						 timeout_us, timeout_ms,
-						 NULL))
-			drm_err_ratelimited(&gt->i915->drm,
-					    "%s TLB invalidation did not complete in %ums!\n",
-					    engine->name, timeout_ms);
-	}
-
-	/*
-	 * Use delayed put since a) we mostly expect a flurry of TLB
-	 * invalidations so it is good to avoid paying the forcewake cost and
-	 * b) it works around a bug in Icelake which cannot cope with too rapid
-	 * transitions.
-	 */
-	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
-}
-
-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 40b06adf509a..b4bba16cdb53 100644
--- a/drivers/gpu/drm/i915/gt/intel_gt.h
+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
@@ -101,16 +101,4 @@ void intel_gt_info_print(const struct intel_gt_info *info,
 
 void intel_gt_watchdog_work(struct work_struct *work);
 
-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_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c
new file mode 100644
index 000000000000..af8cae979489
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_tlb.c
@@ -0,0 +1,183 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#include "i915_drv.h"
+#include "i915_perf_oa_regs.h"
+#include "intel_engine_pm.h"
+#include "intel_gt.h"
+#include "intel_gt_pm.h"
+#include "intel_gt_regs.h"
+#include "intel_tlb.h"
+
+struct reg_and_bit {
+	i915_reg_t 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 (drm_WARN_ON_ONCE(&engine->i915->drm,
+			     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;
+}
+
+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;
+}
+
+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,
+	};
+	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 (GRAPHICS_VER(i915) == 12) {
+		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 (drm_WARN_ONCE(&i915->drm, !num,
+			  "Platform does not implement TLB invalidation!"))
+		return;
+
+	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_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
+		 * cap at 1ms. We go a bit higher just in case.
+		 */
+		const unsigned int timeout_us = 100;
+		const unsigned int timeout_ms = 4;
+
+		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
+		if (__intel_wait_for_register_fw(uncore,
+						 rb.reg, rb.bit, 0,
+						 timeout_us, timeout_ms,
+						 NULL))
+			drm_err_ratelimited(&gt->i915->drm,
+					    "%s TLB invalidation did not complete in %ums!\n",
+					    engine->name, timeout_ms);
+	}
+
+	/*
+	 * Use delayed put since a) we mostly expect a flurry of TLB
+	 * invalidations so it is good to avoid paying the forcewake cost and
+	 * b) it works around a bug in Icelake which cannot cope with too rapid
+	 * transitions.
+	 */
+	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
+}
+
+void intel_gt_invalidate_tlb_full(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);
+	}
+}
+
+void intel_gt_init_tlb(struct intel_gt *gt)
+{
+	mutex_init(&gt->tlb.invalidate_lock);
+	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
+}
+
+void intel_gt_fini_tlb(struct intel_gt *gt)
+{
+	mutex_destroy(&gt->tlb.invalidate_lock);
+}
diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.h b/drivers/gpu/drm/i915/gt/intel_tlb.h
new file mode 100644
index 000000000000..46ce25bf5afe
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/intel_tlb.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef INTEL_TLB_H
+#define INTEL_TLB_H
+
+#include <linux/seqlock.h>
+#include <linux/types.h>
+
+#include "intel_gt_types.h"
+
+void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno);
+
+void intel_gt_init_tlb(struct intel_gt *gt);
+void intel_gt_fini_tlb(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;
+}
+
+#endif /* INTEL_TLB_H */
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 84a9ccbc5fc5..fe947d1456d5 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -33,6 +33,7 @@
 #include "gt/intel_engine_heartbeat.h"
 #include "gt/intel_gt.h"
 #include "gt/intel_gt_requests.h"
+#include "gt/intel_tlb.h"
 
 #include "i915_drv.h"
 #include "i915_gem_evict.h"
-- 
2.36.1

[Intel-gfx] [PATCH v2 2/2] drm/i915/gt: document TLB cache invalidation functions

[Mauro Carvalho Chehab]

Add a description for the TLB cache invalidation algorithm and for
the related kAPI functions.

Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---

To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
See [PATCH v2 0/2] at: https://lore.kernel.org/all/cover.1659077372.git.mchehab@kernel.org/

 Documentation/gpu/i915.rst          |   7 ++
 drivers/gpu/drm/i915/gt/intel_tlb.c |  25 +++++++
 drivers/gpu/drm/i915/gt/intel_tlb.h | 101 ++++++++++++++++++++++++++++
 3 files changed, 133 insertions(+)

diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 4e59db1cfb00..46911fdd79e8 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -58,6 +58,13 @@ Intel GVT-g Host Support(vGPU device model)
 .. kernel-doc:: drivers/gpu/drm/i915/intel_gvt.c
    :internal:
 
+TLB cache invalidation
+----------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.h
+
+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.c
+
 Workarounds
 -----------
 
diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c
index af8cae979489..4873b7ecc015 100644
--- a/drivers/gpu/drm/i915/gt/intel_tlb.c
+++ b/drivers/gpu/drm/i915/gt/intel_tlb.c
@@ -145,6 +145,18 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
 }
 
+/**
+ * intel_gt_invalidate_tlb_full - do full TLB cache invalidation
+ * @gt: GT structure
+ * @seqno: sequence number
+ *
+ * Do a full TLB cache invalidation if the @seqno is bigger than the last
+ * full TLB cache invalidation.
+ *
+ * Note:
+ * The TLB cache invalidation logic depends on GEN-specific registers.
+ * It currently supports MMIO-based TLB flush for GEN8 to GEN12.
+ */
 void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
 {
 	intel_wakeref_t wakeref;
@@ -171,12 +183,25 @@ void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
 	}
 }
 
+/**
+ * intel_gt_init_tlb - initialize TLB-specific vars
+ * @gt: GT structure
+ *
+ * TLB cache invalidation logic internally uses some resources that require
+ * initialization. Should be called before doing any TLB cache invalidation.
+ */
 void intel_gt_init_tlb(struct intel_gt *gt)
 {
 	mutex_init(&gt->tlb.invalidate_lock);
 	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
 }
 
+/**
+ * intel_gt_fini_tlb - initialize TLB-specific vars
+ * @gt: GT structure
+ *
+ * Frees any resources needed by TLB cache invalidation logic.
+ */
 void intel_gt_fini_tlb(struct intel_gt *gt)
 {
 	mutex_destroy(&gt->tlb.invalidate_lock);
diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.h b/drivers/gpu/drm/i915/gt/intel_tlb.h
index 46ce25bf5afe..dca70c33bd61 100644
--- a/drivers/gpu/drm/i915/gt/intel_tlb.h
+++ b/drivers/gpu/drm/i915/gt/intel_tlb.h
@@ -11,16 +11,117 @@
 
 #include "intel_gt_types.h"
 
+/**
+ * DOC: TLB cache invalidation logic
+ *
+ * The way the current algorithm works is that a struct drm_i915_gem_object can
+ * be created on any order. At unbind/evict time, the object is warranted that
+ * it won't be used anymore. So, a sequence number provided by
+ * intel_gt_next_invalidate_tlb_full() is stored on it. This can happen either
+ * at __vma_put_pages() - for VMA sync unbind, or at ppgtt_unbind_vma() - for
+ * VMA async VMA bind.
+ *
+ * At __i915_gem_object_unset_pages(), intel_gt_invalidate_tlb_full() is called,
+ * where it checks if the sequence number of the object was already invalidated
+ * or not. If not, it flushes the TLB and increments the sequence number::
+ *
+ *   void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
+ *   {
+ *   ...
+ * 	with_intel_gt_pm_if_awake(gt, wakeref) {
+ * 		mutex_lock(&gt->tlb.invalidate_lock);
+ * 		if (tlb_seqno_passed(gt, seqno))
+ * 				goto unlock;
+ *
+ * 		// Some code to do TLB invalidation
+ *   ...
+ *
+ * 		write_seqcount_invalidate(&gt->tlb.seqno); // increment seqno
+ * 		mutex_lock(&gt->tlb.invalidate_lock);
+ *      }
+ *
+ * So, let's say the current seqno is 2 and 3 new objects were created,
+ * on this order::
+ *
+ * 	obj1
+ * 	obj2
+ * 	obj3
+ *
+ * They can be unbind/evict on a different order. At unbind/evict time,
+ * the mm.tlb will be stamped with the sequence number, using the number
+ * from the last TLB flush, plus 1.
+ *
+ * Different threads may be used on unbind/evict and/or unset pages.
+ * As the logic at void intel_gt_invalidate_tlb_full() is protected by a mutex,
+ * for simplicity, let's consider just two threads:
+ *
+ * +-------------------+-------------------------+---------------------------------+
+ * | sequence number   | Thread 0                | Thread 1                        +
+ * +===================+=========================+=================================+
+ * | seqno=2           |                         |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   | unbind/evict obj3.      |                                 |
+ * |                   |                         |                                 |
+ * |                   | obj3.mm.tlb = seqno | 1 |                                 |
+ * |                   | // obj3.mm.tlb = 3      |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   | unbind/evict obj1.      |                                 |
+ * |                   |                         |                                 |
+ * |                   | obj1.mm.tlb = seqno | 1 |                                 |
+ * |                   | // obj1.mm.tlb = 3      |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   |                         | __i915_gem_object_unset_pages() |
+ * |                   |                         | called for obj3 => TLB flush    |
+ * |                   |                         | invalidating both obj1 and obj2.|
+ * |                   |                         |                                 |
+ * |                   |                         | seqno += 2                      |
+ * +-------------------+-------------------------+---------------------------------+
+ * | seqno=4           |                         |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   | unbind/evict obj2.      |                                 |
+ * |                   |                         |                                 |
+ * |                   | obj2.mm.tlb = seqno | 1 |                                 |
+ * |                   | // obj2.mm.tlb = 5      |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   |                         | __i915_gem_object_unset_pages() |
+ * |                   |                         | called for obj1, don't flush    |
+ * |                   |                         | as past flush invalidated obj1. |
+ * |                   +-------------------------+---------------------------------+
+ * |                   |                         | __i915_gem_object_unset_pages() |
+ * |                   |                         | called for obj2 => TLB flush.   |
+ * |                   |                         | invalidating obj2.              |
+ * |                   |                         |                                 |
+ * |                   |                         | seqno += 2                      |
+ * +-------------------+-------------------------+---------------------------------+
+ * | seqno=6           |                         |                                 |
+ * +-------------------+-------------------------+---------------------------------+
+ */
+
 void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno);
 
 void intel_gt_init_tlb(struct intel_gt *gt);
 void intel_gt_fini_tlb(struct intel_gt *gt);
 
+/**
+ * intel_gt_tlb_seqno - Returns the current TLB invlidation sequence number
+ *
+ * @gt: GT structure
+ *
+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
+ */
 static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt)
 {
 	return seqprop_sequence(&gt->tlb.seqno);
 }
 
+/**
+ * intel_gt_next_invalidate_tlb_full - Returns the next TLB full invalidation
+ *	sequence number
+ *
+ * @gt: GT structure
+ *
+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
+ */
 static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt)
 {
 	return intel_gt_tlb_seqno(gt) | 1;
-- 
2.36.1

[PATCH v2 2/2] drm/i915/gt: document TLB cache invalidation functions

[Mauro Carvalho Chehab]

Add a description for the TLB cache invalidation algorithm and for
the related kAPI functions.

Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---

To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
See [PATCH v2 0/2] at: https://lore.kernel.org/all/cover.1659077372.git.mchehab@kernel.org/

 Documentation/gpu/i915.rst          |   7 ++
 drivers/gpu/drm/i915/gt/intel_tlb.c |  25 +++++++
 drivers/gpu/drm/i915/gt/intel_tlb.h | 101 ++++++++++++++++++++++++++++
 3 files changed, 133 insertions(+)

diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 4e59db1cfb00..46911fdd79e8 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -58,6 +58,13 @@ Intel GVT-g Host Support(vGPU device model)
 .. kernel-doc:: drivers/gpu/drm/i915/intel_gvt.c
    :internal:
 
+TLB cache invalidation
+----------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.h
+
+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.c
+
 Workarounds
 -----------
 
diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c
index af8cae979489..4873b7ecc015 100644
--- a/drivers/gpu/drm/i915/gt/intel_tlb.c
+++ b/drivers/gpu/drm/i915/gt/intel_tlb.c
@@ -145,6 +145,18 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
 }
 
+/**
+ * intel_gt_invalidate_tlb_full - do full TLB cache invalidation
+ * @gt: GT structure
+ * @seqno: sequence number
+ *
+ * Do a full TLB cache invalidation if the @seqno is bigger than the last
+ * full TLB cache invalidation.
+ *
+ * Note:
+ * The TLB cache invalidation logic depends on GEN-specific registers.
+ * It currently supports MMIO-based TLB flush for GEN8 to GEN12.
+ */
 void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
 {
 	intel_wakeref_t wakeref;
@@ -171,12 +183,25 @@ void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
 	}
 }
 
+/**
+ * intel_gt_init_tlb - initialize TLB-specific vars
+ * @gt: GT structure
+ *
+ * TLB cache invalidation logic internally uses some resources that require
+ * initialization. Should be called before doing any TLB cache invalidation.
+ */
 void intel_gt_init_tlb(struct intel_gt *gt)
 {
 	mutex_init(&gt->tlb.invalidate_lock);
 	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
 }
 
+/**
+ * intel_gt_fini_tlb - initialize TLB-specific vars
+ * @gt: GT structure
+ *
+ * Frees any resources needed by TLB cache invalidation logic.
+ */
 void intel_gt_fini_tlb(struct intel_gt *gt)
 {
 	mutex_destroy(&gt->tlb.invalidate_lock);
diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.h b/drivers/gpu/drm/i915/gt/intel_tlb.h
index 46ce25bf5afe..dca70c33bd61 100644
--- a/drivers/gpu/drm/i915/gt/intel_tlb.h
+++ b/drivers/gpu/drm/i915/gt/intel_tlb.h
@@ -11,16 +11,117 @@
 
 #include "intel_gt_types.h"
 
+/**
+ * DOC: TLB cache invalidation logic
+ *
+ * The way the current algorithm works is that a struct drm_i915_gem_object can
+ * be created on any order. At unbind/evict time, the object is warranted that
+ * it won't be used anymore. So, a sequence number provided by
+ * intel_gt_next_invalidate_tlb_full() is stored on it. This can happen either
+ * at __vma_put_pages() - for VMA sync unbind, or at ppgtt_unbind_vma() - for
+ * VMA async VMA bind.
+ *
+ * At __i915_gem_object_unset_pages(), intel_gt_invalidate_tlb_full() is called,
+ * where it checks if the sequence number of the object was already invalidated
+ * or not. If not, it flushes the TLB and increments the sequence number::
+ *
+ *   void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
+ *   {
+ *   ...
+ * 	with_intel_gt_pm_if_awake(gt, wakeref) {
+ * 		mutex_lock(&gt->tlb.invalidate_lock);
+ * 		if (tlb_seqno_passed(gt, seqno))
+ * 				goto unlock;
+ *
+ * 		// Some code to do TLB invalidation
+ *   ...
+ *
+ * 		write_seqcount_invalidate(&gt->tlb.seqno); // increment seqno
+ * 		mutex_lock(&gt->tlb.invalidate_lock);
+ *      }
+ *
+ * So, let's say the current seqno is 2 and 3 new objects were created,
+ * on this order::
+ *
+ * 	obj1
+ * 	obj2
+ * 	obj3
+ *
+ * They can be unbind/evict on a different order. At unbind/evict time,
+ * the mm.tlb will be stamped with the sequence number, using the number
+ * from the last TLB flush, plus 1.
+ *
+ * Different threads may be used on unbind/evict and/or unset pages.
+ * As the logic at void intel_gt_invalidate_tlb_full() is protected by a mutex,
+ * for simplicity, let's consider just two threads:
+ *
+ * +-------------------+-------------------------+---------------------------------+
+ * | sequence number   | Thread 0                | Thread 1                        +
+ * +===================+=========================+=================================+
+ * | seqno=2           |                         |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   | unbind/evict obj3.      |                                 |
+ * |                   |                         |                                 |
+ * |                   | obj3.mm.tlb = seqno | 1 |                                 |
+ * |                   | // obj3.mm.tlb = 3      |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   | unbind/evict obj1.      |                                 |
+ * |                   |                         |                                 |
+ * |                   | obj1.mm.tlb = seqno | 1 |                                 |
+ * |                   | // obj1.mm.tlb = 3      |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   |                         | __i915_gem_object_unset_pages() |
+ * |                   |                         | called for obj3 => TLB flush    |
+ * |                   |                         | invalidating both obj1 and obj2.|
+ * |                   |                         |                                 |
+ * |                   |                         | seqno += 2                      |
+ * +-------------------+-------------------------+---------------------------------+
+ * | seqno=4           |                         |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   | unbind/evict obj2.      |                                 |
+ * |                   |                         |                                 |
+ * |                   | obj2.mm.tlb = seqno | 1 |                                 |
+ * |                   | // obj2.mm.tlb = 5      |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   |                         | __i915_gem_object_unset_pages() |
+ * |                   |                         | called for obj1, don't flush    |
+ * |                   |                         | as past flush invalidated obj1. |
+ * |                   +-------------------------+---------------------------------+
+ * |                   |                         | __i915_gem_object_unset_pages() |
+ * |                   |                         | called for obj2 => TLB flush.   |
+ * |                   |                         | invalidating obj2.              |
+ * |                   |                         |                                 |
+ * |                   |                         | seqno += 2                      |
+ * +-------------------+-------------------------+---------------------------------+
+ * | seqno=6           |                         |                                 |
+ * +-------------------+-------------------------+---------------------------------+
+ */
+
 void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno);
 
 void intel_gt_init_tlb(struct intel_gt *gt);
 void intel_gt_fini_tlb(struct intel_gt *gt);
 
+/**
+ * intel_gt_tlb_seqno - Returns the current TLB invlidation sequence number
+ *
+ * @gt: GT structure
+ *
+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
+ */
 static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt)
 {
 	return seqprop_sequence(&gt->tlb.seqno);
 }
 
+/**
+ * intel_gt_next_invalidate_tlb_full - Returns the next TLB full invalidation
+ *	sequence number
+ *
+ * @gt: GT structure
+ *
+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
+ */
 static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt)
 {
 	return intel_gt_tlb_seqno(gt) | 1;
-- 
2.36.1

[PATCH v2 2/2] drm/i915/gt: document TLB cache invalidation functions

[Mauro Carvalho Chehab]

Add a description for the TLB cache invalidation algorithm and for
the related kAPI functions.

Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
---

To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
See [PATCH v2 0/2] at: https://lore.kernel.org/all/cover.1659077372.git.mchehab@kernel.org/

 Documentation/gpu/i915.rst          |   7 ++
 drivers/gpu/drm/i915/gt/intel_tlb.c |  25 +++++++
 drivers/gpu/drm/i915/gt/intel_tlb.h | 101 ++++++++++++++++++++++++++++
 3 files changed, 133 insertions(+)

diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
index 4e59db1cfb00..46911fdd79e8 100644
--- a/Documentation/gpu/i915.rst
+++ b/Documentation/gpu/i915.rst
@@ -58,6 +58,13 @@ Intel GVT-g Host Support(vGPU device model)
 .. kernel-doc:: drivers/gpu/drm/i915/intel_gvt.c
    :internal:
 
+TLB cache invalidation
+----------------------
+
+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.h
+
+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.c
+
 Workarounds
 -----------
 
diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c
index af8cae979489..4873b7ecc015 100644
--- a/drivers/gpu/drm/i915/gt/intel_tlb.c
+++ b/drivers/gpu/drm/i915/gt/intel_tlb.c
@@ -145,6 +145,18 @@ static void mmio_invalidate_full(struct intel_gt *gt)
 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
 }
 
+/**
+ * intel_gt_invalidate_tlb_full - do full TLB cache invalidation
+ * @gt: GT structure
+ * @seqno: sequence number
+ *
+ * Do a full TLB cache invalidation if the @seqno is bigger than the last
+ * full TLB cache invalidation.
+ *
+ * Note:
+ * The TLB cache invalidation logic depends on GEN-specific registers.
+ * It currently supports MMIO-based TLB flush for GEN8 to GEN12.
+ */
 void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
 {
 	intel_wakeref_t wakeref;
@@ -171,12 +183,25 @@ void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
 	}
 }
 
+/**
+ * intel_gt_init_tlb - initialize TLB-specific vars
+ * @gt: GT structure
+ *
+ * TLB cache invalidation logic internally uses some resources that require
+ * initialization. Should be called before doing any TLB cache invalidation.
+ */
 void intel_gt_init_tlb(struct intel_gt *gt)
 {
 	mutex_init(&gt->tlb.invalidate_lock);
 	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
 }
 
+/**
+ * intel_gt_fini_tlb - initialize TLB-specific vars
+ * @gt: GT structure
+ *
+ * Frees any resources needed by TLB cache invalidation logic.
+ */
 void intel_gt_fini_tlb(struct intel_gt *gt)
 {
 	mutex_destroy(&gt->tlb.invalidate_lock);
diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.h b/drivers/gpu/drm/i915/gt/intel_tlb.h
index 46ce25bf5afe..dca70c33bd61 100644
--- a/drivers/gpu/drm/i915/gt/intel_tlb.h
+++ b/drivers/gpu/drm/i915/gt/intel_tlb.h
@@ -11,16 +11,117 @@
 
 #include "intel_gt_types.h"
 
+/**
+ * DOC: TLB cache invalidation logic
+ *
+ * The way the current algorithm works is that a struct drm_i915_gem_object can
+ * be created on any order. At unbind/evict time, the object is warranted that
+ * it won't be used anymore. So, a sequence number provided by
+ * intel_gt_next_invalidate_tlb_full() is stored on it. This can happen either
+ * at __vma_put_pages() - for VMA sync unbind, or at ppgtt_unbind_vma() - for
+ * VMA async VMA bind.
+ *
+ * At __i915_gem_object_unset_pages(), intel_gt_invalidate_tlb_full() is called,
+ * where it checks if the sequence number of the object was already invalidated
+ * or not. If not, it flushes the TLB and increments the sequence number::
+ *
+ *   void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
+ *   {
+ *   ...
+ * 	with_intel_gt_pm_if_awake(gt, wakeref) {
+ * 		mutex_lock(&gt->tlb.invalidate_lock);
+ * 		if (tlb_seqno_passed(gt, seqno))
+ * 				goto unlock;
+ *
+ * 		// Some code to do TLB invalidation
+ *   ...
+ *
+ * 		write_seqcount_invalidate(&gt->tlb.seqno); // increment seqno
+ * 		mutex_lock(&gt->tlb.invalidate_lock);
+ *      }
+ *
+ * So, let's say the current seqno is 2 and 3 new objects were created,
+ * on this order::
+ *
+ * 	obj1
+ * 	obj2
+ * 	obj3
+ *
+ * They can be unbind/evict on a different order. At unbind/evict time,
+ * the mm.tlb will be stamped with the sequence number, using the number
+ * from the last TLB flush, plus 1.
+ *
+ * Different threads may be used on unbind/evict and/or unset pages.
+ * As the logic at void intel_gt_invalidate_tlb_full() is protected by a mutex,
+ * for simplicity, let's consider just two threads:
+ *
+ * +-------------------+-------------------------+---------------------------------+
+ * | sequence number   | Thread 0                | Thread 1                        +
+ * +===================+=========================+=================================+
+ * | seqno=2           |                         |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   | unbind/evict obj3.      |                                 |
+ * |                   |                         |                                 |
+ * |                   | obj3.mm.tlb = seqno | 1 |                                 |
+ * |                   | // obj3.mm.tlb = 3      |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   | unbind/evict obj1.      |                                 |
+ * |                   |                         |                                 |
+ * |                   | obj1.mm.tlb = seqno | 1 |                                 |
+ * |                   | // obj1.mm.tlb = 3      |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   |                         | __i915_gem_object_unset_pages() |
+ * |                   |                         | called for obj3 => TLB flush    |
+ * |                   |                         | invalidating both obj1 and obj2.|
+ * |                   |                         |                                 |
+ * |                   |                         | seqno += 2                      |
+ * +-------------------+-------------------------+---------------------------------+
+ * | seqno=4           |                         |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   | unbind/evict obj2.      |                                 |
+ * |                   |                         |                                 |
+ * |                   | obj2.mm.tlb = seqno | 1 |                                 |
+ * |                   | // obj2.mm.tlb = 5      |                                 |
+ * |                   +-------------------------+---------------------------------+
+ * |                   |                         | __i915_gem_object_unset_pages() |
+ * |                   |                         | called for obj1, don't flush    |
+ * |                   |                         | as past flush invalidated obj1. |
+ * |                   +-------------------------+---------------------------------+
+ * |                   |                         | __i915_gem_object_unset_pages() |
+ * |                   |                         | called for obj2 => TLB flush.   |
+ * |                   |                         | invalidating obj2.              |
+ * |                   |                         |                                 |
+ * |                   |                         | seqno += 2                      |
+ * +-------------------+-------------------------+---------------------------------+
+ * | seqno=6           |                         |                                 |
+ * +-------------------+-------------------------+---------------------------------+
+ */
+
 void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno);
 
 void intel_gt_init_tlb(struct intel_gt *gt);
 void intel_gt_fini_tlb(struct intel_gt *gt);
 
+/**
+ * intel_gt_tlb_seqno - Returns the current TLB invlidation sequence number
+ *
+ * @gt: GT structure
+ *
+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
+ */
 static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt)
 {
 	return seqprop_sequence(&gt->tlb.seqno);
 }
 
+/**
+ * intel_gt_next_invalidate_tlb_full - Returns the next TLB full invalidation
+ *	sequence number
+ *
+ * @gt: GT structure
+ *
+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
+ */
 static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt)
 {
 	return intel_gt_tlb_seqno(gt) | 1;
-- 
2.36.1

[Intel-gfx] ✗ Fi.CI.BUILD: failure for Move TLB invalidation code for its own file and document it (rev2)

[Patchwork]

== Series Details ==

Series: Move TLB invalidation code for its own file and document it (rev2)
URL   : https://patchwork.freedesktop.org/series/106805/
State : failure

== Summary ==

Error: patch https://patchwork.freedesktop.org/api/1.0/series/106805/revisions/2/mbox/ not applied
Applying: drm/i915/gt: Move TLB invalidation to its own file
Using index info to reconstruct a base tree...
M	drivers/gpu/drm/i915/gem/i915_gem_pages.c
M	drivers/gpu/drm/i915/gt/intel_gt.c
M	drivers/gpu/drm/i915/gt/intel_gt.h
M	drivers/gpu/drm/i915/i915_vma.c
Falling back to patching base and 3-way merge...
Auto-merging drivers/gpu/drm/i915/i915_vma.c
Auto-merging drivers/gpu/drm/i915/gt/intel_gt.h
CONFLICT (content): Merge conflict in drivers/gpu/drm/i915/gt/intel_gt.h
Auto-merging drivers/gpu/drm/i915/gt/intel_gt.c
CONFLICT (content): Merge conflict in drivers/gpu/drm/i915/gt/intel_gt.c
Auto-merging drivers/gpu/drm/i915/gem/i915_gem_pages.c
CONFLICT (content): Merge conflict in drivers/gpu/drm/i915/gem/i915_gem_pages.c
error: Failed to merge in the changes.
hint: Use 'git am --show-current-patch=diff' to see the failed patch
Patch failed at 0001 drm/i915/gt: Move TLB invalidation to its own file
When you have resolved this problem, run "git am --continue".
If you prefer to skip this patch, run "git am --skip" instead.
To restore the original branch and stop patching, run "git am --abort".

[Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for Move TLB invalidation code for its own file and document it (rev3)

[Patchwork]

== Series Details ==

Series: Move TLB invalidation code for its own file and document it (rev3)
URL   : https://patchwork.freedesktop.org/series/106805/
State : warning

== Summary ==

Error: dim checkpatch failed
6e8221ff3e55 drm/i915/gt: Move TLB invalidation to its own file
Traceback (most recent call last):
  File "scripts/spdxcheck.py", line 11, in <module>
    import git
ModuleNotFoundError: No module named 'git'
Traceback (most recent call last):
  File "scripts/spdxcheck.py", line 11, in <module>
    import git
ModuleNotFoundError: No module named 'git'
-:274: WARNING:FILE_PATH_CHANGES: added, moved or deleted file(s), does MAINTAINERS need updating?
#274: 
new file mode 100644

total: 0 errors, 1 warnings, 0 checks, 294 lines checked
b5743e507945 drm/i915/gt: document TLB cache invalidation functions
-:103: WARNING:SPACE_BEFORE_TAB: please, no space before tabs
#103: FILE: drivers/gpu/drm/i915/gt/intel_tlb.h:31:
+ * ^Iwith_intel_gt_pm_if_awake(gt, wakeref) {$

-:104: WARNING:SPACE_BEFORE_TAB: please, no space before tabs
#104: FILE: drivers/gpu/drm/i915/gt/intel_tlb.h:32:
+ * ^I^Imutex_lock(&gt->tlb.invalidate_lock);$

-:105: WARNING:SPACE_BEFORE_TAB: please, no space before tabs
#105: FILE: drivers/gpu/drm/i915/gt/intel_tlb.h:33:
+ * ^I^Iif (tlb_seqno_passed(gt, seqno))$

-:106: WARNING:SPACE_BEFORE_TAB: please, no space before tabs
#106: FILE: drivers/gpu/drm/i915/gt/intel_tlb.h:34:
+ * ^I^I^I^Igoto unlock;$

-:108: WARNING:SPACE_BEFORE_TAB: please, no space before tabs
#108: FILE: drivers/gpu/drm/i915/gt/intel_tlb.h:36:
+ * ^I^I// Some code to do TLB invalidation$

-:111: WARNING:SPACE_BEFORE_TAB: please, no space before tabs
#111: FILE: drivers/gpu/drm/i915/gt/intel_tlb.h:39:
+ * ^I^Iwrite_seqcount_invalidate(&gt->tlb.seqno); // increment seqno$

-:112: WARNING:SPACE_BEFORE_TAB: please, no space before tabs
#112: FILE: drivers/gpu/drm/i915/gt/intel_tlb.h:40:
+ * ^I^Imutex_lock(&gt->tlb.invalidate_lock);$

-:118: WARNING:SPACE_BEFORE_TAB: please, no space before tabs
#118: FILE: drivers/gpu/drm/i915/gt/intel_tlb.h:46:
+ * ^Iobj1$

-:119: WARNING:SPACE_BEFORE_TAB: please, no space before tabs
#119: FILE: drivers/gpu/drm/i915/gt/intel_tlb.h:47:
+ * ^Iobj2$

-:120: WARNING:SPACE_BEFORE_TAB: please, no space before tabs
#120: FILE: drivers/gpu/drm/i915/gt/intel_tlb.h:48:
+ * ^Iobj3$

total: 0 errors, 10 warnings, 0 checks, 173 lines checked

[Intel-gfx] ✗ Fi.CI.SPARSE: warning for Move TLB invalidation code for its own file and document it (rev3)

[Patchwork]

== Series Details ==

Series: Move TLB invalidation code for its own file and document it (rev3)
URL   : https://patchwork.freedesktop.org/series/106805/
State : warning

== Summary ==

Error: dim sparse failed
Sparse version: v0.6.2
Fast mode used, each commit won't be checked separately.

[Intel-gfx] ✓ Fi.CI.BAT: success for Move TLB invalidation code for its own file and document it (rev3)

[Patchwork]

[-- Attachment #1: Type: text/plain, Size: 6708 bytes --]

== Series Details ==

Series: Move TLB invalidation code for its own file and document it (rev3)
URL   : https://patchwork.freedesktop.org/series/106805/
State : success

== Summary ==

CI Bug Log - changes from CI_DRM_11960 -> Patchwork_106805v3
====================================================

Summary
-------

  **SUCCESS**

  No regressions found.

  External URL: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/index.html

Participating hosts (43 -> 40)
------------------------------

  Additional (1): bat-jsl-3 
  Missing    (4): fi-ctg-p8600 bat-dg2-9 fi-bdw-samus fi-hsw-4200u 

Possible new issues
-------------------

  Here are the unknown changes that may have been introduced in Patchwork_106805v3:

### IGT changes ###

#### Suppressed ####

  The following results come from untrusted machines, tests, or statuses.
  They do not affect the overall result.

  * igt@i915_selftest@live@gt_mocs:
    - {bat-adlp-6}:       [PASS][1] -> [INCOMPLETE][2]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/bat-adlp-6/igt@i915_selftest@live@gt_mocs.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/bat-adlp-6/igt@i915_selftest@live@gt_mocs.html

  * igt@i915_selftest@live@hugepages:
    - {bat-rplp-1}:       [PASS][3] -> [DMESG-WARN][4]
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/bat-rplp-1/igt@i915_selftest@live@hugepages.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/bat-rplp-1/igt@i915_selftest@live@hugepages.html

  
Known issues
------------

  Here are the changes found in Patchwork_106805v3 that come from known issues:

### IGT changes ###

#### Issues hit ####

  * igt@i915_selftest@live@gem:
    - fi-blb-e6850:       NOTRUN -> [DMESG-FAIL][5] ([i915#4528])
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/fi-blb-e6850/igt@i915_selftest@live@gem.html

  * igt@i915_selftest@live@gt_engines:
    - bat-dg1-6:          [PASS][6] -> [INCOMPLETE][7] ([i915#4418])
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/bat-dg1-6/igt@i915_selftest@live@gt_engines.html
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/bat-dg1-6/igt@i915_selftest@live@gt_engines.html

  * igt@i915_suspend@basic-s2idle-without-i915:
    - fi-bdw-gvtdvm:      NOTRUN -> [INCOMPLETE][8] ([i915#4817])
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/fi-bdw-gvtdvm/igt@i915_suspend@basic-s2idle-without-i915.html

  * igt@i915_suspend@basic-s3-without-i915:
    - fi-bdw-5557u:       [PASS][9] -> [INCOMPLETE][10] ([i915#146])
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/fi-bdw-5557u/igt@i915_suspend@basic-s3-without-i915.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/fi-bdw-5557u/igt@i915_suspend@basic-s3-without-i915.html

  * igt@kms_chamelium@common-hpd-after-suspend:
    - fi-hsw-4770:        NOTRUN -> [SKIP][11] ([fdo#109271] / [fdo#111827])
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/fi-hsw-4770/igt@kms_chamelium@common-hpd-after-suspend.html

  
#### Possible fixes ####

  * igt@gem_lmem_swapping@random-engines@lmem0:
    - {bat-dg2-8}:        [INCOMPLETE][12] ([i915#5763]) -> [PASS][13]
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/bat-dg2-8/igt@gem_lmem_swapping@random-engines@lmem0.html
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/bat-dg2-8/igt@gem_lmem_swapping@random-engines@lmem0.html

  * igt@i915_selftest@live@execlists:
    - fi-bdw-gvtdvm:      [INCOMPLETE][14] ([i915#2940]) -> [PASS][15]
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/fi-bdw-gvtdvm/igt@i915_selftest@live@execlists.html
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/fi-bdw-gvtdvm/igt@i915_selftest@live@execlists.html

  * igt@i915_selftest@live@hangcheck:
    - fi-hsw-4770:        [INCOMPLETE][16] ([i915#4785]) -> [PASS][17]
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/fi-hsw-4770/igt@i915_selftest@live@hangcheck.html
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/fi-hsw-4770/igt@i915_selftest@live@hangcheck.html

  * igt@i915_selftest@live@requests:
    - fi-blb-e6850:       [DMESG-FAIL][18] ([i915#4528]) -> [PASS][19]
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/fi-blb-e6850/igt@i915_selftest@live@requests.html
   [19]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/fi-blb-e6850/igt@i915_selftest@live@requests.html

  
  {name}: This element is suppressed. This means it is ignored when computing
          the status of the difference (SUCCESS, WARNING, or FAILURE).

  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [fdo#109285]: https://bugs.freedesktop.org/show_bug.cgi?id=109285
  [fdo#109295]: https://bugs.freedesktop.org/show_bug.cgi?id=109295
  [fdo#111827]: https://bugs.freedesktop.org/show_bug.cgi?id=111827
  [i915#146]: https://gitlab.freedesktop.org/drm/intel/issues/146
  [i915#2190]: https://gitlab.freedesktop.org/drm/intel/issues/2190
  [i915#2940]: https://gitlab.freedesktop.org/drm/intel/issues/2940
  [i915#3003]: https://gitlab.freedesktop.org/drm/intel/issues/3003
  [i915#3301]: https://gitlab.freedesktop.org/drm/intel/issues/3301
  [i915#3555]: https://gitlab.freedesktop.org/drm/intel/issues/3555
  [i915#4103]: https://gitlab.freedesktop.org/drm/intel/issues/4103
  [i915#4312]: https://gitlab.freedesktop.org/drm/intel/issues/4312
  [i915#4418]: https://gitlab.freedesktop.org/drm/intel/issues/4418
  [i915#4528]: https://gitlab.freedesktop.org/drm/intel/issues/4528
  [i915#4613]: https://gitlab.freedesktop.org/drm/intel/issues/4613
  [i915#4785]: https://gitlab.freedesktop.org/drm/intel/issues/4785
  [i915#4817]: https://gitlab.freedesktop.org/drm/intel/issues/4817
  [i915#5354]: https://gitlab.freedesktop.org/drm/intel/issues/5354
  [i915#5763]: https://gitlab.freedesktop.org/drm/intel/issues/5763
  [i915#5903]: https://gitlab.freedesktop.org/drm/intel/issues/5903


Build changes
-------------

  * Linux: CI_DRM_11960 -> Patchwork_106805v3

  CI-20190529: 20190529
  CI_DRM_11960: 16ef7aef4dd813fae8ef0ccf50fd69f1c0e8cf11 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_6605: 1596683606cafa391f5d8f6b68e0c888233c0738 @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
  Patchwork_106805v3: 16ef7aef4dd813fae8ef0ccf50fd69f1c0e8cf11 @ git://anongit.freedesktop.org/gfx-ci/linux


### Linux commits

35c30d9f9c9f drm/i915/gt: document TLB cache invalidation functions
6e2efa70d033 drm/i915/gt: Move TLB invalidation to its own file

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/index.html

[-- Attachment #2: Type: text/html, Size: 6937 bytes --]

[Intel-gfx] ✗ Fi.CI.IGT: failure for Move TLB invalidation code for its own file and document it (rev3)

[Patchwork]

[-- Attachment #1: Type: text/plain, Size: 52079 bytes --]

== Series Details ==

Series: Move TLB invalidation code for its own file and document it (rev3)
URL   : https://patchwork.freedesktop.org/series/106805/
State : failure

== Summary ==

CI Bug Log - changes from CI_DRM_11960_full -> Patchwork_106805v3_full
====================================================

Summary
-------

  **FAILURE**

  Serious unknown changes coming with Patchwork_106805v3_full absolutely need to be
  verified manually.
  
  If you think the reported changes have nothing to do with the changes
  introduced in Patchwork_106805v3_full, please notify your bug team to allow them
  to document this new failure mode, which will reduce false positives in CI.

  

Participating hosts (13 -> 13)
------------------------------

  No changes in participating hosts

Possible new issues
-------------------

  Here are the unknown changes that may have been introduced in Patchwork_106805v3_full:

### IGT changes ###

#### Possible regressions ####

  * igt@i915_pm_rpm@system-suspend-modeset:
    - shard-iclb:         [PASS][1] -> [INCOMPLETE][2]
   [1]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-iclb5/igt@i915_pm_rpm@system-suspend-modeset.html
   [2]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb4/igt@i915_pm_rpm@system-suspend-modeset.html

  
Known issues
------------

  Here are the changes found in Patchwork_106805v3_full that come from known issues:

### CI changes ###

#### Possible fixes ####

  * boot:
    - shard-apl:          ([PASS][3], [PASS][4], [FAIL][5], [PASS][6], [PASS][7], [PASS][8], [PASS][9], [PASS][10], [PASS][11], [PASS][12], [PASS][13], [PASS][14], [PASS][15], [PASS][16], [PASS][17], [PASS][18], [PASS][19], [PASS][20], [PASS][21], [PASS][22], [PASS][23], [PASS][24], [PASS][25], [PASS][26], [PASS][27]) ([i915#4386]) -> ([PASS][28], [PASS][29], [PASS][30], [PASS][31], [PASS][32], [PASS][33], [PASS][34], [PASS][35], [PASS][36], [PASS][37], [PASS][38], [PASS][39], [PASS][40], [PASS][41], [PASS][42], [PASS][43], [PASS][44], [PASS][45], [PASS][46], [PASS][47], [PASS][48], [PASS][49], [PASS][50], [PASS][51], [PASS][52])
   [3]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl2/boot.html
   [4]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl2/boot.html
   [5]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl2/boot.html
   [6]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl3/boot.html
   [7]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl3/boot.html
   [8]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl4/boot.html
   [9]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl4/boot.html
   [10]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl4/boot.html
   [11]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl4/boot.html
   [12]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl4/boot.html
   [13]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl6/boot.html
   [14]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl6/boot.html
   [15]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl6/boot.html
   [16]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl7/boot.html
   [17]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl7/boot.html
   [18]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl7/boot.html
   [19]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl8/boot.html
   [20]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl8/boot.html
   [21]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl8/boot.html
   [22]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl8/boot.html
   [23]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl1/boot.html
   [24]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl1/boot.html
   [25]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl1/boot.html
   [26]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl2/boot.html
   [27]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl2/boot.html
   [28]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl1/boot.html
   [29]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl1/boot.html
   [30]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl1/boot.html
   [31]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl2/boot.html
   [32]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl2/boot.html
   [33]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl2/boot.html
   [34]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl3/boot.html
   [35]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl3/boot.html
   [36]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl3/boot.html
   [37]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl3/boot.html
   [38]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl3/boot.html
   [39]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl4/boot.html
   [40]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl4/boot.html
   [41]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl4/boot.html
   [42]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl4/boot.html
   [43]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl6/boot.html
   [44]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl6/boot.html
   [45]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl6/boot.html
   [46]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl6/boot.html
   [47]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl7/boot.html
   [48]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl7/boot.html
   [49]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl7/boot.html
   [50]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl8/boot.html
   [51]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl8/boot.html
   [52]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl8/boot.html

  

### IGT changes ###

#### Issues hit ####

  * igt@gem_ctx_param@set-priority-not-supported:
    - shard-iclb:         NOTRUN -> [SKIP][53] ([fdo#109314])
   [53]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@gem_ctx_param@set-priority-not-supported.html

  * igt@gem_exec_balancer@parallel-bb-first:
    - shard-iclb:         [PASS][54] -> [SKIP][55] ([i915#4525]) +1 similar issue
   [54]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-iclb1/igt@gem_exec_balancer@parallel-bb-first.html
   [55]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb3/igt@gem_exec_balancer@parallel-bb-first.html

  * igt@gem_exec_fair@basic-deadline:
    - shard-skl:          NOTRUN -> [FAIL][56] ([i915#2846])
   [56]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl7/igt@gem_exec_fair@basic-deadline.html

  * igt@gem_exec_fair@basic-pace-share@rcs0:
    - shard-kbl:          [PASS][57] -> [FAIL][58] ([i915#2842]) +1 similar issue
   [57]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-kbl4/igt@gem_exec_fair@basic-pace-share@rcs0.html
   [58]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl1/igt@gem_exec_fair@basic-pace-share@rcs0.html

  * igt@gem_exec_fair@basic-pace@rcs0:
    - shard-glk:          [PASS][59] -> [FAIL][60] ([i915#2842])
   [59]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-glk3/igt@gem_exec_fair@basic-pace@rcs0.html
   [60]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-glk8/igt@gem_exec_fair@basic-pace@rcs0.html

  * igt@gem_huc_copy@huc-copy:
    - shard-tglb:         [PASS][61] -> [SKIP][62] ([i915#2190])
   [61]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-tglb8/igt@gem_huc_copy@huc-copy.html
   [62]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-tglb7/igt@gem_huc_copy@huc-copy.html

  * igt@gem_lmem_swapping@heavy-random:
    - shard-apl:          NOTRUN -> [SKIP][63] ([fdo#109271] / [i915#4613])
   [63]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl8/igt@gem_lmem_swapping@heavy-random.html

  * igt@gem_lmem_swapping@heavy-verify-multi-ccs:
    - shard-skl:          NOTRUN -> [SKIP][64] ([fdo#109271] / [i915#4613])
   [64]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl10/igt@gem_lmem_swapping@heavy-verify-multi-ccs.html

  * igt@gem_lmem_swapping@parallel-random-verify:
    - shard-iclb:         NOTRUN -> [SKIP][65] ([i915#4613])
   [65]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@gem_lmem_swapping@parallel-random-verify.html

  * igt@gem_lmem_swapping@verify:
    - shard-kbl:          NOTRUN -> [SKIP][66] ([fdo#109271] / [i915#4613]) +1 similar issue
   [66]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl4/igt@gem_lmem_swapping@verify.html

  * igt@gem_pxp@create-regular-buffer:
    - shard-iclb:         NOTRUN -> [SKIP][67] ([i915#4270])
   [67]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@gem_pxp@create-regular-buffer.html

  * igt@gem_userptr_blits@coherency-sync:
    - shard-iclb:         NOTRUN -> [SKIP][68] ([fdo#109290])
   [68]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@gem_userptr_blits@coherency-sync.html

  * igt@gem_userptr_blits@dmabuf-sync:
    - shard-skl:          NOTRUN -> [SKIP][69] ([fdo#109271] / [i915#3323])
   [69]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl10/igt@gem_userptr_blits@dmabuf-sync.html

  * igt@gem_userptr_blits@input-checking:
    - shard-skl:          NOTRUN -> [DMESG-WARN][70] ([i915#4991])
   [70]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl10/igt@gem_userptr_blits@input-checking.html

  * igt@gem_workarounds@suspend-resume:
    - shard-apl:          [PASS][71] -> [DMESG-WARN][72] ([i915#180]) +2 similar issues
   [71]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl2/igt@gem_workarounds@suspend-resume.html
   [72]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl6/igt@gem_workarounds@suspend-resume.html

  * igt@gen7_exec_parse@basic-allocation:
    - shard-iclb:         NOTRUN -> [SKIP][73] ([fdo#109289])
   [73]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@gen7_exec_parse@basic-allocation.html

  * igt@i915_module_load@load:
    - shard-iclb:         NOTRUN -> [SKIP][74] ([i915#6227])
   [74]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@i915_module_load@load.html

  * igt@i915_pm_lpsp@kms-lpsp@kms-lpsp-hdmi-a:
    - shard-glk:          NOTRUN -> [SKIP][75] ([fdo#109271] / [i915#1937])
   [75]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-glk2/igt@i915_pm_lpsp@kms-lpsp@kms-lpsp-hdmi-a.html

  * igt@i915_pm_rpm@dpms-lpsp:
    - shard-kbl:          NOTRUN -> [SKIP][76] ([fdo#109271]) +69 similar issues
   [76]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl1/igt@i915_pm_rpm@dpms-lpsp.html

  * igt@i915_selftest@live@objects:
    - shard-skl:          [PASS][77] -> [INCOMPLETE][78] ([i915#6155])
   [77]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-skl7/igt@i915_selftest@live@objects.html
   [78]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl2/igt@i915_selftest@live@objects.html

  * igt@kms_big_fb@4-tiled-16bpp-rotate-180:
    - shard-iclb:         NOTRUN -> [SKIP][79] ([i915#5286]) +1 similar issue
   [79]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@kms_big_fb@4-tiled-16bpp-rotate-180.html

  * igt@kms_big_fb@x-tiled-64bpp-rotate-180:
    - shard-skl:          [PASS][80] -> [DMESG-WARN][81] ([i915#1982])
   [80]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-skl9/igt@kms_big_fb@x-tiled-64bpp-rotate-180.html
   [81]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl4/igt@kms_big_fb@x-tiled-64bpp-rotate-180.html

  * igt@kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-0-async-flip:
    - shard-skl:          NOTRUN -> [FAIL][82] ([i915#3743])
   [82]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl7/igt@kms_big_fb@x-tiled-max-hw-stride-32bpp-rotate-0-async-flip.html

  * igt@kms_big_fb@y-tiled-32bpp-rotate-180:
    - shard-skl:          [PASS][83] -> [TIMEOUT][84] ([i915#6473])
   [83]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-skl7/igt@kms_big_fb@y-tiled-32bpp-rotate-180.html
   [84]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl5/igt@kms_big_fb@y-tiled-32bpp-rotate-180.html

  * igt@kms_ccs@pipe-a-bad-pixel-format-y_tiled_gen12_mc_ccs:
    - shard-iclb:         NOTRUN -> [SKIP][85] ([fdo#109278] / [i915#3886])
   [85]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@kms_ccs@pipe-a-bad-pixel-format-y_tiled_gen12_mc_ccs.html

  * igt@kms_ccs@pipe-a-missing-ccs-buffer-y_tiled_gen12_rc_ccs:
    - shard-iclb:         NOTRUN -> [SKIP][86] ([fdo#109278]) +5 similar issues
   [86]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@kms_ccs@pipe-a-missing-ccs-buffer-y_tiled_gen12_rc_ccs.html

  * igt@kms_ccs@pipe-b-missing-ccs-buffer-y_tiled_gen12_rc_ccs_cc:
    - shard-apl:          NOTRUN -> [SKIP][87] ([fdo#109271] / [i915#3886]) +5 similar issues
   [87]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl8/igt@kms_ccs@pipe-b-missing-ccs-buffer-y_tiled_gen12_rc_ccs_cc.html

  * igt@kms_ccs@pipe-b-random-ccs-data-y_tiled_gen12_mc_ccs:
    - shard-skl:          NOTRUN -> [SKIP][88] ([fdo#109271] / [i915#3886]) +4 similar issues
   [88]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl10/igt@kms_ccs@pipe-b-random-ccs-data-y_tiled_gen12_mc_ccs.html

  * igt@kms_ccs@pipe-c-crc-primary-basic-y_tiled_gen12_rc_ccs_cc:
    - shard-kbl:          NOTRUN -> [SKIP][89] ([fdo#109271] / [i915#3886]) +3 similar issues
   [89]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl4/igt@kms_ccs@pipe-c-crc-primary-basic-y_tiled_gen12_rc_ccs_cc.html

  * igt@kms_chamelium@hdmi-edid-change-during-suspend:
    - shard-skl:          NOTRUN -> [SKIP][90] ([fdo#109271] / [fdo#111827]) +7 similar issues
   [90]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl7/igt@kms_chamelium@hdmi-edid-change-during-suspend.html

  * igt@kms_color_chamelium@pipe-b-degamma:
    - shard-iclb:         NOTRUN -> [SKIP][91] ([fdo#109284] / [fdo#111827]) +1 similar issue
   [91]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@kms_color_chamelium@pipe-b-degamma.html

  * igt@kms_color_chamelium@pipe-c-ctm-blue-to-red:
    - shard-kbl:          NOTRUN -> [SKIP][92] ([fdo#109271] / [fdo#111827]) +3 similar issues
   [92]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl4/igt@kms_color_chamelium@pipe-c-ctm-blue-to-red.html

  * igt@kms_color_chamelium@pipe-d-ctm-max:
    - shard-apl:          NOTRUN -> [SKIP][93] ([fdo#109271] / [fdo#111827]) +4 similar issues
   [93]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl1/igt@kms_color_chamelium@pipe-d-ctm-max.html

  * igt@kms_content_protection@atomic:
    - shard-kbl:          NOTRUN -> [TIMEOUT][94] ([i915#1319])
   [94]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl6/igt@kms_content_protection@atomic.html

  * igt@kms_cursor_legacy@flip-vs-cursor@atomic-transitions-varying-size:
    - shard-glk:          [PASS][95] -> [FAIL][96] ([i915#2346])
   [95]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-glk9/igt@kms_cursor_legacy@flip-vs-cursor@atomic-transitions-varying-size.html
   [96]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-glk9/igt@kms_cursor_legacy@flip-vs-cursor@atomic-transitions-varying-size.html

  * igt@kms_dp_tiled_display@basic-test-pattern-with-chamelium:
    - shard-iclb:         NOTRUN -> [SKIP][97] ([i915#3528])
   [97]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@kms_dp_tiled_display@basic-test-pattern-with-chamelium.html

  * igt@kms_draw_crc@draw-method-xrgb2101010-mmap-cpu-4tiled:
    - shard-iclb:         NOTRUN -> [SKIP][98] ([i915#5287])
   [98]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@kms_draw_crc@draw-method-xrgb2101010-mmap-cpu-4tiled.html

  * igt@kms_fbcon_fbt@psr-suspend:
    - shard-skl:          NOTRUN -> [FAIL][99] ([i915#4767])
   [99]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl10/igt@kms_fbcon_fbt@psr-suspend.html

  * igt@kms_flip@2x-flip-vs-fences:
    - shard-iclb:         NOTRUN -> [SKIP][100] ([fdo#109274]) +1 similar issue
   [100]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@kms_flip@2x-flip-vs-fences.html

  * igt@kms_flip_scaled_crc@flip-64bpp-4tile-to-16bpp-4tile-downscaling@pipe-a-valid-mode:
    - shard-iclb:         NOTRUN -> [SKIP][101] ([i915#2672]) +7 similar issues
   [101]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb7/igt@kms_flip_scaled_crc@flip-64bpp-4tile-to-16bpp-4tile-downscaling@pipe-a-valid-mode.html

  * igt@kms_frontbuffer_tracking@fbc-suspend:
    - shard-kbl:          [PASS][102] -> [DMESG-WARN][103] ([i915#180]) +4 similar issues
   [102]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-kbl1/igt@kms_frontbuffer_tracking@fbc-suspend.html
   [103]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl7/igt@kms_frontbuffer_tracking@fbc-suspend.html

  * igt@kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-cur-indfb-draw-render:
    - shard-iclb:         NOTRUN -> [SKIP][104] ([fdo#109280]) +5 similar issues
   [104]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@kms_frontbuffer_tracking@fbcpsr-2p-scndscrn-cur-indfb-draw-render.html

  * igt@kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-onoff:
    - shard-glk:          NOTRUN -> [SKIP][105] ([fdo#109271]) +5 similar issues
   [105]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-glk2/igt@kms_frontbuffer_tracking@psr-2p-primscrn-spr-indfb-onoff.html

  * igt@kms_frontbuffer_tracking@psr-2p-scndscrn-spr-indfb-draw-render:
    - shard-apl:          NOTRUN -> [SKIP][106] ([fdo#109271]) +89 similar issues
   [106]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl4/igt@kms_frontbuffer_tracking@psr-2p-scndscrn-spr-indfb-draw-render.html

  * igt@kms_plane@plane-panning-bottom-right-suspend@pipe-a-planes:
    - shard-kbl:          [PASS][107] -> [INCOMPLETE][108] ([i915#3614] / [i915#4939])
   [107]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-kbl7/igt@kms_plane@plane-panning-bottom-right-suspend@pipe-a-planes.html
   [108]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl6/igt@kms_plane@plane-panning-bottom-right-suspend@pipe-a-planes.html

  * igt@kms_plane_alpha_blend@pipe-a-constant-alpha-min:
    - shard-skl:          [PASS][109] -> [FAIL][110] ([fdo#108145] / [i915#265])
   [109]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-skl7/igt@kms_plane_alpha_blend@pipe-a-constant-alpha-min.html
   [110]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl5/igt@kms_plane_alpha_blend@pipe-a-constant-alpha-min.html

  * igt@kms_plane_alpha_blend@pipe-b-alpha-opaque-fb:
    - shard-kbl:          NOTRUN -> [FAIL][111] ([fdo#108145] / [i915#265])
   [111]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl4/igt@kms_plane_alpha_blend@pipe-b-alpha-opaque-fb.html

  * igt@kms_plane_alpha_blend@pipe-b-alpha-transparent-fb:
    - shard-apl:          NOTRUN -> [FAIL][112] ([i915#265])
   [112]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl8/igt@kms_plane_alpha_blend@pipe-b-alpha-transparent-fb.html

  * igt@kms_plane_scaling@plane-downscale-with-pixel-format-factor-0-5@pipe-a-edp-1:
    - shard-iclb:         [PASS][113] -> [SKIP][114] ([i915#5176]) +2 similar issues
   [113]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-iclb3/igt@kms_plane_scaling@plane-downscale-with-pixel-format-factor-0-5@pipe-a-edp-1.html
   [114]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb2/igt@kms_plane_scaling@plane-downscale-with-pixel-format-factor-0-5@pipe-a-edp-1.html

  * igt@kms_plane_scaling@plane-downscale-with-rotation-factor-0-25@pipe-b-edp-1:
    - shard-iclb:         NOTRUN -> [SKIP][115] ([i915#5176]) +2 similar issues
   [115]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@kms_plane_scaling@plane-downscale-with-rotation-factor-0-25@pipe-b-edp-1.html

  * igt@kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-5@pipe-b-edp-1:
    - shard-iclb:         [PASS][116] -> [SKIP][117] ([i915#5235]) +2 similar issues
   [116]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-iclb3/igt@kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-5@pipe-b-edp-1.html
   [117]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb2/igt@kms_plane_scaling@planes-upscale-20x20-downscale-factor-0-5@pipe-b-edp-1.html

  * igt@kms_psr2_sf@cursor-plane-move-continuous-exceed-fully-sf:
    - shard-kbl:          NOTRUN -> [SKIP][118] ([fdo#109271] / [i915#658])
   [118]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl4/igt@kms_psr2_sf@cursor-plane-move-continuous-exceed-fully-sf.html

  * igt@kms_psr2_sf@cursor-plane-move-continuous-sf:
    - shard-apl:          NOTRUN -> [SKIP][119] ([fdo#109271] / [i915#658])
   [119]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl8/igt@kms_psr2_sf@cursor-plane-move-continuous-sf.html

  * igt@kms_psr2_sf@overlay-plane-move-continuous-exceed-fully-sf:
    - shard-iclb:         NOTRUN -> [SKIP][120] ([i915#658])
   [120]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@kms_psr2_sf@overlay-plane-move-continuous-exceed-fully-sf.html

  * igt@kms_psr2_sf@overlay-plane-move-continuous-exceed-sf:
    - shard-skl:          NOTRUN -> [SKIP][121] ([fdo#109271] / [i915#658])
   [121]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl10/igt@kms_psr2_sf@overlay-plane-move-continuous-exceed-sf.html

  * igt@kms_psr@psr2_primary_render:
    - shard-iclb:         NOTRUN -> [SKIP][122] ([fdo#109441])
   [122]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@kms_psr@psr2_primary_render.html

  * igt@kms_psr@psr2_sprite_blt:
    - shard-iclb:         [PASS][123] -> [SKIP][124] ([fdo#109441]) +1 similar issue
   [123]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-iclb2/igt@kms_psr@psr2_sprite_blt.html
   [124]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb6/igt@kms_psr@psr2_sprite_blt.html

  * igt@kms_psr_stress_test@flip-primary-invalidate-overlay:
    - shard-iclb:         [PASS][125] -> [SKIP][126] ([i915#5519])
   [125]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-iclb3/igt@kms_psr_stress_test@flip-primary-invalidate-overlay.html
   [126]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb7/igt@kms_psr_stress_test@flip-primary-invalidate-overlay.html

  * igt@kms_vrr@flipline:
    - shard-skl:          NOTRUN -> [SKIP][127] ([fdo#109271]) +66 similar issues
   [127]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl10/igt@kms_vrr@flipline.html

  * igt@nouveau_crc@pipe-b-source-outp-inactive:
    - shard-iclb:         NOTRUN -> [SKIP][128] ([i915#2530])
   [128]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@nouveau_crc@pipe-b-source-outp-inactive.html

  * igt@perf@blocking:
    - shard-skl:          NOTRUN -> [FAIL][129] ([i915#1542])
   [129]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl10/igt@perf@blocking.html

  * igt@prime_nv_test@i915_import_gtt_mmap:
    - shard-iclb:         NOTRUN -> [SKIP][130] ([fdo#109291])
   [130]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@prime_nv_test@i915_import_gtt_mmap.html

  * igt@sysfs_clients@fair-1:
    - shard-apl:          NOTRUN -> [SKIP][131] ([fdo#109271] / [i915#2994])
   [131]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl1/igt@sysfs_clients@fair-1.html

  * igt@sysfs_clients@sema-50:
    - shard-iclb:         NOTRUN -> [SKIP][132] ([i915#2994])
   [132]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@sysfs_clients@sema-50.html

  * igt@sysfs_clients@split-10:
    - shard-kbl:          NOTRUN -> [SKIP][133] ([fdo#109271] / [i915#2994])
   [133]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl4/igt@sysfs_clients@split-10.html

  
#### Possible fixes ####

  * igt@gem_ctx_exec@basic-nohangcheck:
    - shard-tglb:         [FAIL][134] ([i915#6268]) -> [PASS][135]
   [134]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-tglb2/igt@gem_ctx_exec@basic-nohangcheck.html
   [135]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-tglb1/igt@gem_ctx_exec@basic-nohangcheck.html

  * igt@gem_ctx_isolation@preservation-s3@vcs0:
    - shard-kbl:          [DMESG-WARN][136] ([i915#180]) -> [PASS][137] +4 similar issues
   [136]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-kbl7/igt@gem_ctx_isolation@preservation-s3@vcs0.html
   [137]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl4/igt@gem_ctx_isolation@preservation-s3@vcs0.html

  * igt@gem_ctx_persistence@legacy-engines-hang@bsd2:
    - {shard-dg1}:        [FAIL][138] ([i915#4883]) -> [PASS][139]
   [138]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-dg1-19/igt@gem_ctx_persistence@legacy-engines-hang@bsd2.html
   [139]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-dg1-17/igt@gem_ctx_persistence@legacy-engines-hang@bsd2.html

  * igt@gem_eio@in-flight-contexts-1us:
    - shard-tglb:         [TIMEOUT][140] ([i915#3063]) -> [PASS][141]
   [140]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-tglb5/igt@gem_eio@in-flight-contexts-1us.html
   [141]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-tglb6/igt@gem_eio@in-flight-contexts-1us.html

  * igt@gem_exec_balancer@parallel-keep-in-fence:
    - shard-iclb:         [SKIP][142] ([i915#4525]) -> [PASS][143]
   [142]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-iclb3/igt@gem_exec_balancer@parallel-keep-in-fence.html
   [143]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb2/igt@gem_exec_balancer@parallel-keep-in-fence.html

  * igt@gem_exec_fair@basic-none-solo@rcs0:
    - shard-apl:          [FAIL][144] ([i915#2842]) -> [PASS][145]
   [144]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl4/igt@gem_exec_fair@basic-none-solo@rcs0.html
   [145]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl7/igt@gem_exec_fair@basic-none-solo@rcs0.html

  * igt@gem_exec_fence@basic-wait@bcs0:
    - {shard-rkl}:        [SKIP][146] ([i915#6251]) -> [PASS][147]
   [146]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-rkl-5/igt@gem_exec_fence@basic-wait@bcs0.html
   [147]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-rkl-1/igt@gem_exec_fence@basic-wait@bcs0.html

  * igt@gem_exec_flush@basic-batch-kernel-default-cmd:
    - {shard-rkl}:        [SKIP][148] ([fdo#109313]) -> [PASS][149]
   [148]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-rkl-2/igt@gem_exec_flush@basic-batch-kernel-default-cmd.html
   [149]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-rkl-5/igt@gem_exec_flush@basic-batch-kernel-default-cmd.html

  * igt@gem_exec_reloc@basic-write-cpu:
    - {shard-rkl}:        [SKIP][150] ([i915#3281]) -> [PASS][151] +4 similar issues
   [150]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-rkl-2/igt@gem_exec_reloc@basic-write-cpu.html
   [151]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-rkl-5/igt@gem_exec_reloc@basic-write-cpu.html

  * igt@gem_exec_whisper@basic-queues-forked-all:
    - shard-iclb:         [INCOMPLETE][152] ([i915#5304] / [i915#5498]) -> [PASS][153]
   [152]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-iclb6/igt@gem_exec_whisper@basic-queues-forked-all.html
   [153]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb1/igt@gem_exec_whisper@basic-queues-forked-all.html

  * igt@gen9_exec_parse@allowed-single:
    - shard-glk:          [DMESG-WARN][154] ([i915#5566] / [i915#716]) -> [PASS][155]
   [154]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-glk1/igt@gen9_exec_parse@allowed-single.html
   [155]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-glk2/igt@gen9_exec_parse@allowed-single.html

  * igt@i915_pm_rpm@dpms-non-lpsp:
    - {shard-dg1}:        [SKIP][156] ([i915#1397]) -> [PASS][157]
   [156]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-dg1-13/igt@i915_pm_rpm@dpms-non-lpsp.html
   [157]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-dg1-15/igt@i915_pm_rpm@dpms-non-lpsp.html

  * igt@i915_suspend@debugfs-reader:
    - shard-apl:          [DMESG-WARN][158] ([i915#180]) -> [PASS][159] +1 similar issue
   [158]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl8/igt@i915_suspend@debugfs-reader.html
   [159]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl4/igt@i915_suspend@debugfs-reader.html

  * igt@kms_async_flips@alternate-sync-async-flip@pipe-c-edp-1:
    - shard-skl:          [FAIL][160] ([i915#2521]) -> [PASS][161]
   [160]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-skl10/igt@kms_async_flips@alternate-sync-async-flip@pipe-c-edp-1.html
   [161]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl9/igt@kms_async_flips@alternate-sync-async-flip@pipe-c-edp-1.html

  * igt@kms_ccs@pipe-b-missing-ccs-buffer-y_tiled_gen12_rc_ccs:
    - {shard-rkl}:        [SKIP][162] ([i915#1845] / [i915#4098]) -> [PASS][163] +7 similar issues
   [162]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-rkl-5/igt@kms_ccs@pipe-b-missing-ccs-buffer-y_tiled_gen12_rc_ccs.html
   [163]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-rkl-6/igt@kms_ccs@pipe-b-missing-ccs-buffer-y_tiled_gen12_rc_ccs.html

  * igt@kms_cursor_legacy@flip-vs-cursor@atomic-transitions:
    - shard-glk:          [FAIL][164] ([i915#2346]) -> [PASS][165]
   [164]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-glk9/igt@kms_cursor_legacy@flip-vs-cursor@atomic-transitions.html
   [165]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-glk9/igt@kms_cursor_legacy@flip-vs-cursor@atomic-transitions.html

  * igt@kms_draw_crc@draw-method-xrgb2101010-render-ytiled:
    - {shard-rkl}:        [SKIP][166] ([fdo#111314] / [i915#4098] / [i915#4369]) -> [PASS][167] +3 similar issues
   [166]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-rkl-5/igt@kms_draw_crc@draw-method-xrgb2101010-render-ytiled.html
   [167]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-rkl-6/igt@kms_draw_crc@draw-method-xrgb2101010-render-ytiled.html

  * igt@kms_fbcon_fbt@fbc-suspend:
    - shard-apl:          [INCOMPLETE][168] ([i915#180] / [i915#1982] / [i915#4939]) -> [PASS][169]
   [168]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl4/igt@kms_fbcon_fbt@fbc-suspend.html
   [169]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl2/igt@kms_fbcon_fbt@fbc-suspend.html

  * igt@kms_flip@flip-vs-expired-vblank@a-edp1:
    - shard-skl:          [FAIL][170] ([i915#79]) -> [PASS][171]
   [170]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-skl6/igt@kms_flip@flip-vs-expired-vblank@a-edp1.html
   [171]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl6/igt@kms_flip@flip-vs-expired-vblank@a-edp1.html

  * igt@kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-draw-mmap-gtt:
    - {shard-rkl}:        [SKIP][172] ([i915#1849] / [i915#4098]) -> [PASS][173] +3 similar issues
   [172]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-rkl-5/igt@kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-draw-mmap-gtt.html
   [173]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-rkl-6/igt@kms_frontbuffer_tracking@fbc-1p-primscrn-spr-indfb-draw-mmap-gtt.html

  * igt@kms_hdr@bpc-switch-suspend@pipe-a-dp-1:
    - shard-kbl:          [FAIL][174] ([i915#1188]) -> [PASS][175]
   [174]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-kbl4/igt@kms_hdr@bpc-switch-suspend@pipe-a-dp-1.html
   [175]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl1/igt@kms_hdr@bpc-switch-suspend@pipe-a-dp-1.html

  * igt@kms_plane_alpha_blend@pipe-a-constant-alpha-mid:
    - {shard-rkl}:        [SKIP][176] ([i915#1849] / [i915#3546] / [i915#4098]) -> [PASS][177]
   [176]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-rkl-5/igt@kms_plane_alpha_blend@pipe-a-constant-alpha-mid.html
   [177]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-rkl-6/igt@kms_plane_alpha_blend@pipe-a-constant-alpha-mid.html

  * igt@kms_psr2_su@frontbuffer-xrgb8888:
    - shard-iclb:         [SKIP][178] ([fdo#109642] / [fdo#111068] / [i915#658]) -> [PASS][179]
   [178]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-iclb4/igt@kms_psr2_su@frontbuffer-xrgb8888.html
   [179]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb2/igt@kms_psr2_su@frontbuffer-xrgb8888.html

  * igt@kms_psr@psr2_cursor_plane_move:
    - shard-iclb:         [SKIP][180] ([fdo#109441]) -> [PASS][181]
   [180]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-iclb3/igt@kms_psr@psr2_cursor_plane_move.html
   [181]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb2/igt@kms_psr@psr2_cursor_plane_move.html

  * igt@kms_psr_stress_test@flip-primary-invalidate-overlay:
    - shard-tglb:         [SKIP][182] ([i915#5519]) -> [PASS][183]
   [182]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-tglb5/igt@kms_psr_stress_test@flip-primary-invalidate-overlay.html
   [183]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-tglb8/igt@kms_psr_stress_test@flip-primary-invalidate-overlay.html

  * igt@perf@polling-parameterized:
    - shard-skl:          [FAIL][184] ([i915#5639]) -> [PASS][185]
   [184]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-skl5/igt@perf@polling-parameterized.html
   [185]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl10/igt@perf@polling-parameterized.html

  * igt@prime_vgem@basic-fence-flip:
    - {shard-rkl}:        [SKIP][186] ([fdo#109295] / [i915#3708] / [i915#4098]) -> [PASS][187]
   [186]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-rkl-5/igt@prime_vgem@basic-fence-flip.html
   [187]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-rkl-6/igt@prime_vgem@basic-fence-flip.html

  
#### Warnings ####

  * igt@gem_eio@kms:
    - shard-tglb:         [FAIL][188] ([i915#5784]) -> [TIMEOUT][189] ([i915#3063])
   [188]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-tglb8/igt@gem_eio@kms.html
   [189]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-tglb2/igt@gem_eio@kms.html

  * igt@kms_ccs@pipe-d-crc-primary-rotation-180-4_tiled_dg2_rc_ccs_cc:
    - shard-glk:          [SKIP][190] ([fdo#109271]) -> [SKIP][191] ([fdo#109271] / [i915#1888])
   [190]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-glk2/igt@kms_ccs@pipe-d-crc-primary-rotation-180-4_tiled_dg2_rc_ccs_cc.html
   [191]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-glk3/igt@kms_ccs@pipe-d-crc-primary-rotation-180-4_tiled_dg2_rc_ccs_cc.html

  * igt@kms_dsc@basic-dsc:
    - shard-skl:          [SKIP][192] ([fdo#109271]) -> [SKIP][193] ([fdo#109271] / [i915#1888])
   [192]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-skl7/igt@kms_dsc@basic-dsc.html
   [193]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-skl2/igt@kms_dsc@basic-dsc.html

  * igt@kms_fbcon_fbt@fbc-suspend:
    - shard-kbl:          [INCOMPLETE][194] ([i915#180] / [i915#4939]) -> [FAIL][195] ([i915#4767])
   [194]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-kbl7/igt@kms_fbcon_fbt@fbc-suspend.html
   [195]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl1/igt@kms_fbcon_fbt@fbc-suspend.html

  * igt@kms_psr2_sf@overlay-primary-update-sf-dmg-area:
    - shard-iclb:         [SKIP][196] ([i915#2920]) -> [SKIP][197] ([fdo#111068] / [i915#658]) +1 similar issue
   [196]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-iclb2/igt@kms_psr2_sf@overlay-primary-update-sf-dmg-area.html
   [197]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb6/igt@kms_psr2_sf@overlay-primary-update-sf-dmg-area.html

  * igt@kms_psr2_sf@primary-plane-update-sf-dmg-area:
    - shard-iclb:         [SKIP][198] ([fdo#111068] / [i915#658]) -> [SKIP][199] ([i915#2920]) +1 similar issue
   [198]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-iclb3/igt@kms_psr2_sf@primary-plane-update-sf-dmg-area.html
   [199]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-iclb2/igt@kms_psr2_sf@primary-plane-update-sf-dmg-area.html

  * igt@runner@aborted:
    - shard-apl:          ([FAIL][200], [FAIL][201], [FAIL][202], [FAIL][203], [FAIL][204], [FAIL][205]) ([i915#180] / [i915#3002] / [i915#4312] / [i915#5257]) -> ([FAIL][206], [FAIL][207], [FAIL][208], [FAIL][209], [FAIL][210]) ([fdo#109271] / [i915#180] / [i915#3002] / [i915#4312] / [i915#5257])
   [200]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl4/igt@runner@aborted.html
   [201]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl4/igt@runner@aborted.html
   [202]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl8/igt@runner@aborted.html
   [203]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl2/igt@runner@aborted.html
   [204]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl4/igt@runner@aborted.html
   [205]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-apl7/igt@runner@aborted.html
   [206]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl3/igt@runner@aborted.html
   [207]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl6/igt@runner@aborted.html
   [208]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl3/igt@runner@aborted.html
   [209]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl6/igt@runner@aborted.html
   [210]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-apl3/igt@runner@aborted.html
    - shard-kbl:          ([FAIL][211], [FAIL][212], [FAIL][213], [FAIL][214], [FAIL][215], [FAIL][216]) ([i915#180] / [i915#3002] / [i915#4312] / [i915#5257] / [i915#92]) -> ([FAIL][217], [FAIL][218], [FAIL][219], [FAIL][220], [FAIL][221], [FAIL][222], [FAIL][223], [FAIL][224]) ([fdo#109271] / [i915#180] / [i915#3002] / [i915#4312] / [i915#5257])
   [211]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-kbl1/igt@runner@aborted.html
   [212]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-kbl7/igt@runner@aborted.html
   [213]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-kbl7/igt@runner@aborted.html
   [214]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-kbl7/igt@runner@aborted.html
   [215]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-kbl7/igt@runner@aborted.html
   [216]: https://intel-gfx-ci.01.org/tree/drm-tip/CI_DRM_11960/shard-kbl7/igt@runner@aborted.html
   [217]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl7/igt@runner@aborted.html
   [218]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl7/igt@runner@aborted.html
   [219]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl7/igt@runner@aborted.html
   [220]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl7/igt@runner@aborted.html
   [221]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl7/igt@runner@aborted.html
   [222]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl7/igt@runner@aborted.html
   [223]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl7/igt@runner@aborted.html
   [224]: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/shard-kbl1/igt@runner@aborted.html

  
  {name}: This element is suppressed. This means it is ignored when computing
          the status of the difference (SUCCESS, WARNING, or FAILURE).

  [fdo#108145]: https://bugs.freedesktop.org/show_bug.cgi?id=108145
  [fdo#109271]: https://bugs.freedesktop.org/show_bug.cgi?id=109271
  [fdo#109274]: https://bugs.freedesktop.org/show_bug.cgi?id=109274
  [fdo#109278]: https://bugs.freedesktop.org/show_bug.cgi?id=109278
  [fdo#109280]: https://bugs.freedesktop.org/show_bug.cgi?id=109280
  [fdo#109283]: https://bugs.freedesktop.org/show_bug.cgi?id=109283
  [fdo#109284]: https://bugs.freedesktop.org/show_bug.cgi?id=109284
  [fdo#109289]: https://bugs.freedesktop.org/show_bug.cgi?id=109289
  [fdo#109290]: https://bugs.freedesktop.org/show_bug.cgi?id=109290
  [fdo#109291]: https://bugs.freedesktop.org/show_bug.cgi?id=109291
  [fdo#109295]: https://bugs.freedesktop.org/show_bug.cgi?id=109295
  [fdo#109300]: https://bugs.freedesktop.org/show_bug.cgi?id=109300
  [fdo#109303]: https://bugs.freedesktop.org/show_bug.cgi?id=109303
  [fdo#109309]: https://bugs.freedesktop.org/show_bug.cgi?id=109309
  [fdo#109313]: https://bugs.freedesktop.org/show_bug.cgi?id=109313
  [fdo#109314]: https://bugs.freedesktop.org/show_bug.cgi?id=109314
  [fdo#109441]: https://bugs.freedesktop.org/show_bug.cgi?id=109441
  [fdo#109506]: https://bugs.freedesktop.org/show_bug.cgi?id=109506
  [fdo#109642]: https://bugs.freedesktop.org/show_bug.cgi?id=109642
  [fdo#110189]: https://bugs.freedesktop.org/show_bug.cgi?id=110189
  [fdo#110723]: https://bugs.freedesktop.org/show_bug.cgi?id=110723
  [fdo#111068]: https://bugs.freedesktop.org/show_bug.cgi?id=111068
  [fdo#111314]: https://bugs.freedesktop.org/show_bug.cgi?id=111314
  [fdo#111614]: https://bugs.freedesktop.org/show_bug.cgi?id=111614
  [fdo#111615]: https://bugs.freedesktop.org/show_bug.cgi?id=111615
  [fdo#111825]: https://bugs.freedesktop.org/show_bug.cgi?id=111825
  [fdo#111827]: https://bugs.freedesktop.org/show_bug.cgi?id=111827
  [fdo#112283]: https://bugs.freedesktop.org/show_bug.cgi?id=112283
  [i915#1063]: https://gitlab.freedesktop.org/drm/intel/issues/1063
  [i915#1072]: https://gitlab.freedesktop.org/drm/intel/issues/1072
  [i915#1155]: https://gitlab.freedesktop.org/drm/intel/issues/1155
  [i915#1188]: https://gitlab.freedesktop.org/drm/intel/issues/1188
  [i915#1319]: https://gitlab.freedesktop.org/drm/intel/issues/1319
  [i915#132]: https://gitlab.freedesktop.org/drm/intel/issues/132
  [i915#1397]: https://gitlab.freedesktop.org/drm/intel/issues/1397
  [i915#1542]: https://gitlab.freedesktop.org/drm/intel/issues/1542
  [i915#1769]: https://gitlab.freedesktop.org/drm/intel/issues/1769
  [i915#180]: https://gitlab.freedesktop.org/drm/intel/issues/180
  [i915#1825]: https://gitlab.freedesktop.org/drm/intel/issues/1825
  [i915#1836]: https://gitlab.freedesktop.org/drm/intel/issues/1836
  [i915#1839]: https://gitlab.freedesktop.org/drm/intel/issues/1839
  [i915#1845]: https://gitlab.freedesktop.org/drm/intel/issues/1845
  [i915#1849]: https://gitlab.freedesktop.org/drm/intel/issues/1849
  [i915#1888]: https://gitlab.freedesktop.org/drm/intel/issues/1888
  [i915#1937]: https://gitlab.freedesktop.org/drm/intel/issues/1937
  [i915#1982]: https://gitlab.freedesktop.org/drm/intel/issues/1982
  [i915#2190]: https://gitlab.freedesktop.org/drm/intel/issues/2190
  [i915#2346]: https://gitlab.freedesktop.org/drm/intel/issues/2346
  [i915#2437]: https://gitlab.freedesktop.org/drm/intel/issues/2437
  [i915#2521]: https://gitlab.freedesktop.org/drm/intel/issues/2521
  [i915#2527]: https://gitlab.freedesktop.org/drm/intel/issues/2527
  [i915#2530]: https://gitlab.freedesktop.org/drm/intel/issues/2530
  [i915#2582]: https://gitlab.freedesktop.org/drm/intel/issues/2582
  [i915#265]: https://gitlab.freedesktop.org/drm/intel/issues/265
  [i915#2672]: https://gitlab.freedesktop.org/drm/intel/issues/2672
  [i915#2705]: https://gitlab.freedesktop.org/drm/intel/issues/2705
  [i915#280]: https://gitlab.freedesktop.org/drm/intel/issues/280
  [i915#284]: https://gitlab.freedesktop.org/drm/intel/issues/284
  [i915#2842]: https://gitlab.freedesktop.org/drm/intel/issues/2842
  [i915#2846]: https://gitlab.freedesktop.org/drm/intel/issues/2846
  [i915#2856]: https://gitlab.freedesktop.org/drm/intel/issues/2856
  [i915#2920]: https://gitlab.freedesktop.org/drm/intel/issues/2920
  [i915#2994]: https://gitlab.freedesktop.org/drm/intel/issues/2994
  [i915#3002]: https://gitlab.freedesktop.org/drm/intel/issues/3002
  [i915#3063]: https://gitlab.freedesktop.org/drm/intel/issues/3063
  [i915#3116]: https://gitlab.freedesktop.org/drm/intel/issues/3116
  [i915#3281]: https://gitlab.freedesktop.org/drm/intel/issues/3281
  [i915#3282]: https://gitlab.freedesktop.org/drm/intel/issues/3282
  [i915#3291]: https://gitlab.freedesktop.org/drm/intel/issues/3291
  [i915#3297]: https://gitlab.freedesktop.org/drm/intel/issues/3297
  [i915#3299]: https://gitlab.freedesktop.org/drm/intel/issues/3299
  [i915#3323]: https://gitlab.freedesktop.org/drm/intel/issues/3323
  [i915#3458]: https://gitlab.freedesktop.org/drm/intel/issues/3458
  [i915#3528]: https://gitlab.freedesktop.org/drm/intel/issues/3528
  [i915#3539]: https://gitlab.freedesktop.org/drm/intel/issues/3539
  [i915#3546]: https://gitlab.freedesktop.org/drm/intel/issues/3546
  [i915#3555]: https://gitlab.freedesktop.org/drm/intel/issues/3555
  [i915#3558]: https://gitlab.freedesktop.org/drm/intel/issues/3558
  [i915#3614]: https://gitlab.freedesktop.org/drm/intel/issues/3614
  [i915#3637]: https://gitlab.freedesktop.org/drm/intel/issues/3637
  [i915#3638]: https://gitlab.freedesktop.org/drm/intel/issues/3638
  [i915#3689]: https://gitlab.freedesktop.org/drm/intel/issues/3689
  [i915#3708]: https://gitlab.freedesktop.org/drm/intel/issues/3708
  [i915#3734]: https://gitlab.freedesktop.org/drm/intel/issues/3734
  [i915#3742]: https://gitlab.freedesktop.org/drm/intel/issues/3742
  [i915#3743]: https://gitlab.freedesktop.org/drm/intel/issues/3743
  [i915#3810]: https://gitlab.freedesktop.org/drm/intel/issues/3810
  [i915#3828]: https://gitlab.freedesktop.org/drm/intel/issues/3828
  [i915#3886]: https://gitlab.freedesktop.org/drm/intel/issues/3886
  [i915#3989]: https://gitlab.freedesktop.org/drm/intel/issues/3989
  [i915#4070]: https://gitlab.freedesktop.org/drm/intel/issues/4070
  [i915#4077]: https://gitlab.freedesktop.org/drm/intel/issues/4077
  [i915#4078]: https://gitlab.freedesktop.org/drm/intel/issues/4078
  [i915#4079]: https://gitlab.freedesktop.org/drm/intel/issues/4079
  [i915#4098]: https://gitlab.freedesktop.org/drm/intel/issues/4098
  [i915#4103]: https://gitlab.freedesktop.org/drm/intel/issues/4103
  [i915#4171]: https://gitlab.freedesktop.org/drm/intel/issues/4171
  [i915#426]: https://gitlab.freedesktop.org/drm/intel/issues/426
  [i915#4270]: https://gitlab.freedesktop.org/drm/intel/issues/4270
  [i915#4312]: https://gitlab.freedesktop.org/drm/intel/issues/4312
  [i915#4369]: https://gitlab.freedesktop.org/drm/intel/issues/4369
  [i915#4386]: https://gitlab.freedesktop.org/drm/intel/issues/4386
  [i915#4525]: https://gitlab.freedesktop.org/drm/intel/issues/4525
  [i915#4538]: https://gitlab.freedesktop.org/drm/intel/issues/4538
  [i915#4613]: https://gitlab.freedesktop.org/drm/intel/issues/4613
  [i915#4767]: https://gitlab.freedesktop.org/drm/intel/issues/4767
  [i915#4833]: https://gitlab.freedesktop.org/drm/intel/issues/4833
  [i915#4852]: https://gitlab.freedesktop.org/drm/intel/issues/4852
  [i915#4853]: https://gitlab.freedesktop.org/drm/intel/issues/4853
  [i915#4877]: https://gitlab.freedesktop.org/drm/intel/issues/4877
  [i915#4883]: https://gitlab.freedesktop.org/drm/intel/issues/4883
  [i915#4939]: https://gitlab.freedesktop.org/drm/intel/issues/4939
  [i915#4991]: https://gitlab.freedesktop.org/drm/intel/issues/4991
  [i915#5176]: https://gitlab.freedesktop.org/drm/intel/issues/5176
  [i915#5235]: https://gitlab.freedesktop.org/drm/intel/issues/5235
  [i915#5257]: https://gitlab.freedesktop.org/drm/intel/issues/5257
  [i915#5286]: https://gitlab.freedesktop.org/drm/intel/issues/5286
  [i915#5287]: https://gitlab.freedesktop.org/drm/intel/issues/5287
  [i915#5289]: https://gitlab.freedesktop.org/drm/intel/issues/5289
  [i915#5304]: https://gitlab.freedesktop.org/drm/intel/issues/5304
  [i915#5325]: https://gitlab.freedesktop.org/drm/intel/issues/5325
  [i915#5327]: https://gitlab.freedesktop.org/drm/intel/issues/5327
  [i915#533]: https://gitlab.freedesktop.org/drm/intel/issues/533
  [i915#5439]: https://gitlab.freedesktop.org/drm/intel/issues/5439
  [i915#5461]: https://gitlab.freedesktop.org/drm/intel/issues/5461
  [i915#5498]: https://gitlab.freedesktop.org/drm/intel/issues/5498
  [i915#5519]: https://gitlab.freedesktop.org/drm/intel/issues/5519
  [i915#5566]: https://gitlab.freedesktop.org/drm/intel/issues/5566
  [i915#5639]: https://gitlab.freedesktop.org/drm/intel/issues/5639
  [i915#5723]: https://gitlab.freedesktop.org/drm/intel/issues/5723
  [i915#5784]: https://gitlab.freedesktop.org/drm/intel/issues/5784
  [i915#6095]: https://gitlab.freedesktop.org/drm/intel/issues/6095
  [i915#6155]: https://gitlab.freedesktop.org/drm/intel/issues/6155
  [i915#6227]: https://gitlab.freedesktop.org/drm/intel/issues/6227
  [i915#6247]: https://gitlab.freedesktop.org/drm/intel/issues/6247
  [i915#6248]: https://gitlab.freedesktop.org/drm/intel/issues/6248
  [i915#6251]: https://gitlab.freedesktop.org/drm/intel/issues/6251
  [i915#6252]: https://gitlab.freedesktop.org/drm/intel/issues/6252
  [i915#6259]: https://gitlab.freedesktop.org/drm/intel/issues/6259
  [i915#6268]: https://gitlab.freedesktop.org/drm/intel/issues/6268
  [i915#6334]: https://gitlab.freedesktop.org/drm/intel/issues/6334
  [i915#6473]: https://gitlab.freedesktop.org/drm/intel/issues/6473
  [i915#6496]: https://gitlab.freedesktop.org/drm/intel/issues/6496
  [i915#6497]: https://gitlab.freedesktop.org/drm/intel/issues/6497
  [i915#658]: https://gitlab.freedesktop.org/drm/intel/issues/658
  [i915#716]: https://gitlab.freedesktop.org/drm/intel/issues/716
  [i915#79]: https://gitlab.freedesktop.org/drm/intel/issues/79
  [i915#92]: https://gitlab.freedesktop.org/drm/intel/issues/92


Build changes
-------------

  * Linux: CI_DRM_11960 -> Patchwork_106805v3

  CI-20190529: 20190529
  CI_DRM_11960: 16ef7aef4dd813fae8ef0ccf50fd69f1c0e8cf11 @ git://anongit.freedesktop.org/gfx-ci/linux
  IGT_6605: 1596683606cafa391f5d8f6b68e0c888233c0738 @ https://gitlab.freedesktop.org/drm/igt-gpu-tools.git
  Patchwork_106805v3: 16ef7aef4dd813fae8ef0ccf50fd69f1c0e8cf11 @ git://anongit.freedesktop.org/gfx-ci/linux
  piglit_4509: fdc5a4ca11124ab8413c7988896eec4c97336694 @ git://anongit.freedesktop.org/piglit

== Logs ==

For more details see: https://intel-gfx-ci.01.org/tree/drm-tip/Patchwork_106805v3/index.html

[-- Attachment #2: Type: text/html, Size: 56491 bytes --]

Re: [Intel-gfx] [PATCH v2 1/2] drm/i915/gt: Move TLB invalidation to its own file

[Niranjana Vishwanathapura]

On Fri, Jul 29, 2022 at 09:03:54AM +0200, Mauro Carvalho Chehab wrote:
>From: Chris Wilson <chris.p.wilson@intel.com>
>
>Prepare for supporting more TLB invalidation scenarios by moving
>the current MMIO invalidation to its own file.

And looks like,
1. Rename intel_gt_invalidate_tlb() to intel_gt_invalidate_tlb_full()
2. Add intel_gt_init_tlb() and intel_gt_fini_tlb() abstracts.

Reviewed-by: Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com>

>
>Signed-off-by: Chris Wilson <chris.p.wilson@intel.com>
>Cc: Fei Yang <fei.yang@intel.com>
>Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
>---
>
>To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
>See [PATCH v2 0/2] at: https://lore.kernel.org/all/cover.1659077372.git.mchehab@kernel.org/
>
> drivers/gpu/drm/i915/Makefile             |   1 +
> drivers/gpu/drm/i915/gem/i915_gem_pages.c |   4 +-
> drivers/gpu/drm/i915/gt/intel_gt.c        | 168 +-------------------
> drivers/gpu/drm/i915/gt/intel_gt.h        |  12 --
> drivers/gpu/drm/i915/gt/intel_tlb.c       | 183 ++++++++++++++++++++++
> drivers/gpu/drm/i915/gt/intel_tlb.h       |  29 ++++
> drivers/gpu/drm/i915/i915_vma.c           |   1 +
> 7 files changed, 219 insertions(+), 179 deletions(-)
> create mode 100644 drivers/gpu/drm/i915/gt/intel_tlb.c
> create mode 100644 drivers/gpu/drm/i915/gt/intel_tlb.h
>
>diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
>index 522ef9b4aff3..d3df9832d1f7 100644
>--- a/drivers/gpu/drm/i915/Makefile
>+++ b/drivers/gpu/drm/i915/Makefile
>@@ -126,6 +126,7 @@ gt-y += \
> 	gt/intel_sseu.o \
> 	gt/intel_sseu_debugfs.o \
> 	gt/intel_timeline.o \
>+	gt/intel_tlb.o \
> 	gt/intel_workarounds.o \
> 	gt/shmem_utils.o \
> 	gt/sysfs_engines.o
>diff --git a/drivers/gpu/drm/i915/gem/i915_gem_pages.c b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
>index 8357dbdcab5c..1cd76cc5d9f3 100644
>--- a/drivers/gpu/drm/i915/gem/i915_gem_pages.c
>+++ b/drivers/gpu/drm/i915/gem/i915_gem_pages.c
>@@ -7,7 +7,7 @@
> #include <drm/drm_cache.h>
>
> #include "gt/intel_gt.h"
>-#include "gt/intel_gt_pm.h"
>+#include "gt/intel_tlb.h"
>
> #include "i915_drv.h"
> #include "i915_gem_object.h"
>@@ -199,7 +199,7 @@ static void flush_tlb_invalidate(struct drm_i915_gem_object *obj)
> 	if (!obj->mm.tlb)
> 		return;
>
>-	intel_gt_invalidate_tlb(gt, obj->mm.tlb);
>+	intel_gt_invalidate_tlb_full(gt, obj->mm.tlb);
> 	obj->mm.tlb = 0;
> }
>
>diff --git a/drivers/gpu/drm/i915/gt/intel_gt.c b/drivers/gpu/drm/i915/gt/intel_gt.c
>index f435e06125aa..18d82cd620bd 100644
>--- a/drivers/gpu/drm/i915/gt/intel_gt.c
>+++ b/drivers/gpu/drm/i915/gt/intel_gt.c
>@@ -11,9 +11,7 @@
> #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"
>@@ -31,6 +29,7 @@
> #include "intel_renderstate.h"
> #include "intel_rps.h"
> #include "intel_gt_sysfs.h"
>+#include "intel_tlb.h"
> #include "intel_uncore.h"
> #include "shmem_utils.h"
>
>@@ -48,8 +47,7 @@ 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_init_tlb(gt);
> 	intel_gt_pm_init_early(gt);
>
> 	intel_uc_init_early(&gt->uc);
>@@ -770,7 +768,7 @@ 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_gt_fini_tlb(gt);
> 		intel_engines_free(gt);
> 	}
> }
>@@ -881,163 +879,3 @@ void intel_gt_info_print(const struct intel_gt_info *info,
>
> 	intel_sseu_dump(&info->sseu, p);
> }
>-
>-struct reg_and_bit {
>-	i915_reg_t 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 (drm_WARN_ON_ONCE(&engine->i915->drm,
>-			     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;
>-}
>-
>-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,
>-	};
>-	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 (GRAPHICS_VER(i915) == 12) {
>-		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 (drm_WARN_ONCE(&i915->drm, !num,
>-			  "Platform does not implement TLB invalidation!"))
>-		return;
>-
>-	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_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
>-		 * cap at 1ms. We go a bit higher just in case.
>-		 */
>-		const unsigned int timeout_us = 100;
>-		const unsigned int timeout_ms = 4;
>-
>-		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
>-		if (__intel_wait_for_register_fw(uncore,
>-						 rb.reg, rb.bit, 0,
>-						 timeout_us, timeout_ms,
>-						 NULL))
>-			drm_err_ratelimited(&gt->i915->drm,
>-					    "%s TLB invalidation did not complete in %ums!\n",
>-					    engine->name, timeout_ms);
>-	}
>-
>-	/*
>-	 * Use delayed put since a) we mostly expect a flurry of TLB
>-	 * invalidations so it is good to avoid paying the forcewake cost and
>-	 * b) it works around a bug in Icelake which cannot cope with too rapid
>-	 * transitions.
>-	 */
>-	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
>-}
>-
>-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 40b06adf509a..b4bba16cdb53 100644
>--- a/drivers/gpu/drm/i915/gt/intel_gt.h
>+++ b/drivers/gpu/drm/i915/gt/intel_gt.h
>@@ -101,16 +101,4 @@ void intel_gt_info_print(const struct intel_gt_info *info,
>
> void intel_gt_watchdog_work(struct work_struct *work);
>
>-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_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c
>new file mode 100644
>index 000000000000..af8cae979489
>--- /dev/null
>+++ b/drivers/gpu/drm/i915/gt/intel_tlb.c
>@@ -0,0 +1,183 @@
>+// SPDX-License-Identifier: MIT
>+/*
>+ * Copyright © 2022 Intel Corporation
>+ */
>+
>+#include "i915_drv.h"
>+#include "i915_perf_oa_regs.h"
>+#include "intel_engine_pm.h"
>+#include "intel_gt.h"
>+#include "intel_gt_pm.h"
>+#include "intel_gt_regs.h"
>+#include "intel_tlb.h"
>+
>+struct reg_and_bit {
>+	i915_reg_t 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 (drm_WARN_ON_ONCE(&engine->i915->drm,
>+			     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;
>+}
>+
>+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;
>+}
>+
>+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,
>+	};
>+	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 (GRAPHICS_VER(i915) == 12) {
>+		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 (drm_WARN_ONCE(&i915->drm, !num,
>+			  "Platform does not implement TLB invalidation!"))
>+		return;
>+
>+	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_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
>+		 * cap at 1ms. We go a bit higher just in case.
>+		 */
>+		const unsigned int timeout_us = 100;
>+		const unsigned int timeout_ms = 4;
>+
>+		rb = get_reg_and_bit(engine, regs == gen8_regs, regs, num);
>+		if (__intel_wait_for_register_fw(uncore,
>+						 rb.reg, rb.bit, 0,
>+						 timeout_us, timeout_ms,
>+						 NULL))
>+			drm_err_ratelimited(&gt->i915->drm,
>+					    "%s TLB invalidation did not complete in %ums!\n",
>+					    engine->name, timeout_ms);
>+	}
>+
>+	/*
>+	 * Use delayed put since a) we mostly expect a flurry of TLB
>+	 * invalidations so it is good to avoid paying the forcewake cost and
>+	 * b) it works around a bug in Icelake which cannot cope with too rapid
>+	 * transitions.
>+	 */
>+	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
>+}
>+
>+void intel_gt_invalidate_tlb_full(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);
>+	}
>+}
>+
>+void intel_gt_init_tlb(struct intel_gt *gt)
>+{
>+	mutex_init(&gt->tlb.invalidate_lock);
>+	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
>+}
>+
>+void intel_gt_fini_tlb(struct intel_gt *gt)
>+{
>+	mutex_destroy(&gt->tlb.invalidate_lock);
>+}
>diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.h b/drivers/gpu/drm/i915/gt/intel_tlb.h
>new file mode 100644
>index 000000000000..46ce25bf5afe
>--- /dev/null
>+++ b/drivers/gpu/drm/i915/gt/intel_tlb.h
>@@ -0,0 +1,29 @@
>+/* SPDX-License-Identifier: MIT */
>+/*
>+ * Copyright © 2022 Intel Corporation
>+ */
>+
>+#ifndef INTEL_TLB_H
>+#define INTEL_TLB_H
>+
>+#include <linux/seqlock.h>
>+#include <linux/types.h>
>+
>+#include "intel_gt_types.h"
>+
>+void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno);
>+
>+void intel_gt_init_tlb(struct intel_gt *gt);
>+void intel_gt_fini_tlb(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;
>+}
>+
>+#endif /* INTEL_TLB_H */
>diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
>index 84a9ccbc5fc5..fe947d1456d5 100644
>--- a/drivers/gpu/drm/i915/i915_vma.c
>+++ b/drivers/gpu/drm/i915/i915_vma.c
>@@ -33,6 +33,7 @@
> #include "gt/intel_engine_heartbeat.h"
> #include "gt/intel_gt.h"
> #include "gt/intel_gt_requests.h"
>+#include "gt/intel_tlb.h"
>
> #include "i915_drv.h"
> #include "i915_gem_evict.h"
>-- 
>2.36.1
>

Re: [Intel-gfx] [PATCH v2 2/2] drm/i915/gt: document TLB cache invalidation functions

[Niranjana Vishwanathapura]

On Fri, Jul 29, 2022 at 09:03:55AM +0200, Mauro Carvalho Chehab wrote:
>Add a description for the TLB cache invalidation algorithm and for
>the related kAPI functions.
>
>Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
>---
>
>To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
>See [PATCH v2 0/2] at: https://lore.kernel.org/all/cover.1659077372.git.mchehab@kernel.org/
>
> Documentation/gpu/i915.rst          |   7 ++
> drivers/gpu/drm/i915/gt/intel_tlb.c |  25 +++++++
> drivers/gpu/drm/i915/gt/intel_tlb.h | 101 ++++++++++++++++++++++++++++
> 3 files changed, 133 insertions(+)
>
>diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
>index 4e59db1cfb00..46911fdd79e8 100644
>--- a/Documentation/gpu/i915.rst
>+++ b/Documentation/gpu/i915.rst
>@@ -58,6 +58,13 @@ Intel GVT-g Host Support(vGPU device model)
> .. kernel-doc:: drivers/gpu/drm/i915/intel_gvt.c
>    :internal:
>
>+TLB cache invalidation
>+----------------------
>+
>+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.h
>+
>+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.c
>+
> Workarounds
> -----------
>
>diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c
>index af8cae979489..4873b7ecc015 100644
>--- a/drivers/gpu/drm/i915/gt/intel_tlb.c
>+++ b/drivers/gpu/drm/i915/gt/intel_tlb.c
>@@ -145,6 +145,18 @@ static void mmio_invalidate_full(struct intel_gt *gt)
> 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
> }
>
>+/**
>+ * intel_gt_invalidate_tlb_full - do full TLB cache invalidation
>+ * @gt: GT structure
>+ * @seqno: sequence number
>+ *
>+ * Do a full TLB cache invalidation if the @seqno is bigger than the last
>+ * full TLB cache invalidation.
>+ *
>+ * Note:
>+ * The TLB cache invalidation logic depends on GEN-specific registers.
>+ * It currently supports MMIO-based TLB flush for GEN8 to GEN12.
>+ */
> void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> {
> 	intel_wakeref_t wakeref;
>@@ -171,12 +183,25 @@ void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> 	}
> }
>
>+/**
>+ * intel_gt_init_tlb - initialize TLB-specific vars
>+ * @gt: GT structure
>+ *
>+ * TLB cache invalidation logic internally uses some resources that require
>+ * initialization. Should be called before doing any TLB cache invalidation.
>+ */
> void intel_gt_init_tlb(struct intel_gt *gt)
> {
> 	mutex_init(&gt->tlb.invalidate_lock);
> 	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
> }
>
>+/**
>+ * intel_gt_fini_tlb - initialize TLB-specific vars

Free TLB-specific vars

>+ * @gt: GT structure
>+ *
>+ * Frees any resources needed by TLB cache invalidation logic.
>+ */
> void intel_gt_fini_tlb(struct intel_gt *gt)
> {
> 	mutex_destroy(&gt->tlb.invalidate_lock);
>diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.h b/drivers/gpu/drm/i915/gt/intel_tlb.h
>index 46ce25bf5afe..dca70c33bd61 100644
>--- a/drivers/gpu/drm/i915/gt/intel_tlb.h
>+++ b/drivers/gpu/drm/i915/gt/intel_tlb.h
>@@ -11,16 +11,117 @@
>
> #include "intel_gt_types.h"
>
>+/**
>+ * DOC: TLB cache invalidation logic
>+ *
>+ * The way the current algorithm works is that a struct drm_i915_gem_object can
>+ * be created on any order. At unbind/evict time, the object is warranted that
>+ * it won't be used anymore. So, a sequence number provided by
>+ * intel_gt_next_invalidate_tlb_full() is stored on it. This can happen either
>+ * at __vma_put_pages() - for VMA sync unbind, or at ppgtt_unbind_vma() - for
>+ * VMA async VMA bind.
>+ *
>+ * At __i915_gem_object_unset_pages(), intel_gt_invalidate_tlb_full() is called,
>+ * where it checks if the sequence number of the object was already invalidated
>+ * or not. If not, it flushes the TLB and increments the sequence number::
>+ *
>+ *   void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
>+ *   {
>+ *   ...
>+ * 	with_intel_gt_pm_if_awake(gt, wakeref) {
>+ * 		mutex_lock(&gt->tlb.invalidate_lock);
>+ * 		if (tlb_seqno_passed(gt, seqno))
>+ * 				goto unlock;
>+ *
>+ * 		// Some code to do TLB invalidation
>+ *   ...
>+ *
>+ * 		write_seqcount_invalidate(&gt->tlb.seqno); // increment seqno
>+ * 		mutex_lock(&gt->tlb.invalidate_lock);
>+ *      }
>+ *
>+ * So, let's say the current seqno is 2 and 3 new objects were created,
>+ * on this order::
>+ *
>+ * 	obj1
>+ * 	obj2
>+ * 	obj3
>+ *
>+ * They can be unbind/evict on a different order. At unbind/evict time,
>+ * the mm.tlb will be stamped with the sequence number, using the number
>+ * from the last TLB flush, plus 1.

I am trying to get my head around the below function.

void vma_invalidate_tlb(struct i915_address_space *vm, u32 tlb)
{
        WRITE_ONCE(tlb, intel_gt_next_invalidate_tlb_full(vm->gt));
}

Though we pass obj->mm.tlb for 'tlb' while calling this function,
aren't we writing to local 'tlb' variable here instead of obj->mm.tlb?

>+ *
>+ * Different threads may be used on unbind/evict and/or unset pages.
>+ * As the logic at void intel_gt_invalidate_tlb_full() is protected by a mutex,

May be we can skip 'void' and just keep function name here.

>+ * for simplicity, let's consider just two threads:
>+ *
>+ * +-------------------+-------------------------+---------------------------------+
>+ * | sequence number   | Thread 0                | Thread 1                        +
>+ * +===================+=========================+=================================+
>+ * | seqno=2           |                         |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   | unbind/evict obj3.      |                                 |
>+ * |                   |                         |                                 |
>+ * |                   | obj3.mm.tlb = seqno | 1 |                                 |
>+ * |                   | // obj3.mm.tlb = 3      |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   | unbind/evict obj1.      |                                 |
>+ * |                   |                         |                                 |
>+ * |                   | obj1.mm.tlb = seqno | 1 |                                 |
>+ * |                   | // obj1.mm.tlb = 3      |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   |                         | __i915_gem_object_unset_pages() |
>+ * |                   |                         | called for obj3 => TLB flush    |
>+ * |                   |                         | invalidating both obj1 and obj2.|
>+ * |                   |                         |                                 |
>+ * |                   |                         | seqno += 2                      |
>+ * +-------------------+-------------------------+---------------------------------+
>+ * | seqno=4           |                         |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   | unbind/evict obj2.      |                                 |
>+ * |                   |                         |                                 |
>+ * |                   | obj2.mm.tlb = seqno | 1 |                                 |
>+ * |                   | // obj2.mm.tlb = 5      |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   |                         | __i915_gem_object_unset_pages() |
>+ * |                   |                         | called for obj1, don't flush    |
>+ * |                   |                         | as past flush invalidated obj1. |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   |                         | __i915_gem_object_unset_pages() |
>+ * |                   |                         | called for obj2 => TLB flush.   |
>+ * |                   |                         | invalidating obj2.              |
>+ * |                   |                         |                                 |
>+ * |                   |                         | seqno += 2                      |
>+ * +-------------------+-------------------------+---------------------------------+
>+ * | seqno=6           |                         |                                 |
>+ * +-------------------+-------------------------+---------------------------------+
>+ */
>+
> void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno);
>
> void intel_gt_init_tlb(struct intel_gt *gt);
> void intel_gt_fini_tlb(struct intel_gt *gt);
>
>+/**
>+ * intel_gt_tlb_seqno - Returns the current TLB invlidation sequence number
>+ *

Probably this empty comment line needs to be removed before the parameter
description below?

>+ * @gt: GT structure
>+ *
>+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
>+ */
> static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt)
> {
> 	return seqprop_sequence(&gt->tlb.seqno);
> }
>
>+/**
>+ * intel_gt_next_invalidate_tlb_full - Returns the next TLB full invalidation
>+ *	sequence number
>+ *

Same here.

-Niranjana

>+ * @gt: GT structure
>+ *
>+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
>+ */
> static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt)
> {
> 	return intel_gt_tlb_seqno(gt) | 1;
>-- 
>2.36.1
>

Re: [Intel-gfx] [PATCH v2 2/2] drm/i915/gt: document TLB cache invalidation functions

[Niranjana Vishwanathapura]

On Fri, Jul 29, 2022 at 09:03:55AM +0200, Mauro Carvalho Chehab wrote:
>Add a description for the TLB cache invalidation algorithm and for
>the related kAPI functions.
>
>Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
>---
>
>To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
>See [PATCH v2 0/2] at: https://lore.kernel.org/all/cover.1659077372.git.mchehab@kernel.org/
>
> Documentation/gpu/i915.rst          |   7 ++
> drivers/gpu/drm/i915/gt/intel_tlb.c |  25 +++++++
> drivers/gpu/drm/i915/gt/intel_tlb.h | 101 ++++++++++++++++++++++++++++
> 3 files changed, 133 insertions(+)
>
>diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
>index 4e59db1cfb00..46911fdd79e8 100644
>--- a/Documentation/gpu/i915.rst
>+++ b/Documentation/gpu/i915.rst
>@@ -58,6 +58,13 @@ Intel GVT-g Host Support(vGPU device model)
> .. kernel-doc:: drivers/gpu/drm/i915/intel_gvt.c
>    :internal:
>
>+TLB cache invalidation
>+----------------------
>+
>+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.h
>+
>+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.c
>+
> Workarounds
> -----------
>
>diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c
>index af8cae979489..4873b7ecc015 100644
>--- a/drivers/gpu/drm/i915/gt/intel_tlb.c
>+++ b/drivers/gpu/drm/i915/gt/intel_tlb.c
>@@ -145,6 +145,18 @@ static void mmio_invalidate_full(struct intel_gt *gt)
> 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
> }
>
>+/**
>+ * intel_gt_invalidate_tlb_full - do full TLB cache invalidation
>+ * @gt: GT structure
>+ * @seqno: sequence number
>+ *
>+ * Do a full TLB cache invalidation if the @seqno is bigger than the last
>+ * full TLB cache invalidation.
>+ *
>+ * Note:
>+ * The TLB cache invalidation logic depends on GEN-specific registers.
>+ * It currently supports MMIO-based TLB flush for GEN8 to GEN12.
>+ */
> void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> {
> 	intel_wakeref_t wakeref;
>@@ -171,12 +183,25 @@ void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> 	}
> }
>
>+/**
>+ * intel_gt_init_tlb - initialize TLB-specific vars
>+ * @gt: GT structure
>+ *
>+ * TLB cache invalidation logic internally uses some resources that require
>+ * initialization. Should be called before doing any TLB cache invalidation.
>+ */
> void intel_gt_init_tlb(struct intel_gt *gt)
> {
> 	mutex_init(&gt->tlb.invalidate_lock);
> 	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
> }
>
>+/**
>+ * intel_gt_fini_tlb - initialize TLB-specific vars

Free TLB-specific vars

>+ * @gt: GT structure
>+ *
>+ * Frees any resources needed by TLB cache invalidation logic.
>+ */
> void intel_gt_fini_tlb(struct intel_gt *gt)
> {
> 	mutex_destroy(&gt->tlb.invalidate_lock);
>diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.h b/drivers/gpu/drm/i915/gt/intel_tlb.h
>index 46ce25bf5afe..dca70c33bd61 100644
>--- a/drivers/gpu/drm/i915/gt/intel_tlb.h
>+++ b/drivers/gpu/drm/i915/gt/intel_tlb.h
>@@ -11,16 +11,117 @@
>
> #include "intel_gt_types.h"
>
>+/**
>+ * DOC: TLB cache invalidation logic
>+ *
>+ * The way the current algorithm works is that a struct drm_i915_gem_object can
>+ * be created on any order. At unbind/evict time, the object is warranted that
>+ * it won't be used anymore. So, a sequence number provided by
>+ * intel_gt_next_invalidate_tlb_full() is stored on it. This can happen either
>+ * at __vma_put_pages() - for VMA sync unbind, or at ppgtt_unbind_vma() - for
>+ * VMA async VMA bind.
>+ *
>+ * At __i915_gem_object_unset_pages(), intel_gt_invalidate_tlb_full() is called,
>+ * where it checks if the sequence number of the object was already invalidated
>+ * or not. If not, it flushes the TLB and increments the sequence number::
>+ *
>+ *   void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
>+ *   {
>+ *   ...
>+ * 	with_intel_gt_pm_if_awake(gt, wakeref) {
>+ * 		mutex_lock(&gt->tlb.invalidate_lock);
>+ * 		if (tlb_seqno_passed(gt, seqno))
>+ * 				goto unlock;
>+ *
>+ * 		// Some code to do TLB invalidation
>+ *   ...
>+ *
>+ * 		write_seqcount_invalidate(&gt->tlb.seqno); // increment seqno
>+ * 		mutex_lock(&gt->tlb.invalidate_lock);
>+ *      }
>+ *
>+ * So, let's say the current seqno is 2 and 3 new objects were created,
>+ * on this order::
>+ *
>+ * 	obj1
>+ * 	obj2
>+ * 	obj3
>+ *
>+ * They can be unbind/evict on a different order. At unbind/evict time,
>+ * the mm.tlb will be stamped with the sequence number, using the number
>+ * from the last TLB flush, plus 1.

I am trying to get my head around the below function.

void vma_invalidate_tlb(struct i915_address_space *vm, u32 tlb)
{
        WRITE_ONCE(tlb, intel_gt_next_invalidate_tlb_full(vm->gt));
}

Though we pass obj->mm.tlb for 'tlb' while calling this function,
aren't we writing to local 'tlb' variable here instead of obj->mm.tlb?

>+ *
>+ * Different threads may be used on unbind/evict and/or unset pages.
>+ * As the logic at void intel_gt_invalidate_tlb_full() is protected by a mutex,

May be we can skip 'void' and just keep function name here.

>+ * for simplicity, let's consider just two threads:
>+ *
>+ * +-------------------+-------------------------+---------------------------------+
>+ * | sequence number   | Thread 0                | Thread 1                        +
>+ * +===================+=========================+=================================+
>+ * | seqno=2           |                         |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   | unbind/evict obj3.      |                                 |
>+ * |                   |                         |                                 |
>+ * |                   | obj3.mm.tlb = seqno | 1 |                                 |
>+ * |                   | // obj3.mm.tlb = 3      |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   | unbind/evict obj1.      |                                 |
>+ * |                   |                         |                                 |
>+ * |                   | obj1.mm.tlb = seqno | 1 |                                 |
>+ * |                   | // obj1.mm.tlb = 3      |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   |                         | __i915_gem_object_unset_pages() |
>+ * |                   |                         | called for obj3 => TLB flush    |
>+ * |                   |                         | invalidating both obj1 and obj2.|
>+ * |                   |                         |                                 |
>+ * |                   |                         | seqno += 2                      |
>+ * +-------------------+-------------------------+---------------------------------+
>+ * | seqno=4           |                         |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   | unbind/evict obj2.      |                                 |
>+ * |                   |                         |                                 |
>+ * |                   | obj2.mm.tlb = seqno | 1 |                                 |
>+ * |                   | // obj2.mm.tlb = 5      |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   |                         | __i915_gem_object_unset_pages() |
>+ * |                   |                         | called for obj1, don't flush    |
>+ * |                   |                         | as past flush invalidated obj1. |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   |                         | __i915_gem_object_unset_pages() |
>+ * |                   |                         | called for obj2 => TLB flush.   |
>+ * |                   |                         | invalidating obj2.              |
>+ * |                   |                         |                                 |
>+ * |                   |                         | seqno += 2                      |
>+ * +-------------------+-------------------------+---------------------------------+
>+ * | seqno=6           |                         |                                 |
>+ * +-------------------+-------------------------+---------------------------------+
>+ */
>+
> void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno);
>
> void intel_gt_init_tlb(struct intel_gt *gt);
> void intel_gt_fini_tlb(struct intel_gt *gt);
>
>+/**
>+ * intel_gt_tlb_seqno - Returns the current TLB invlidation sequence number
>+ *

Probably this empty comment line needs to be removed before the parameter
description below?

>+ * @gt: GT structure
>+ *
>+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
>+ */
> static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt)
> {
> 	return seqprop_sequence(&gt->tlb.seqno);
> }
>
>+/**
>+ * intel_gt_next_invalidate_tlb_full - Returns the next TLB full invalidation
>+ *	sequence number
>+ *

Same here.

-Niranjana

>+ * @gt: GT structure
>+ *
>+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
>+ */
> static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt)
> {
> 	return intel_gt_tlb_seqno(gt) | 1;
>-- 
>2.36.1
>

Re: [Intel-gfx] [PATCH v2 2/2] drm/i915/gt: document TLB cache invalidation functions

[Niranjana Vishwanathapura]

On Fri, Jul 29, 2022 at 09:03:55AM +0200, Mauro Carvalho Chehab wrote:
>Add a description for the TLB cache invalidation algorithm and for
>the related kAPI functions.
>
>Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
>---
>
>To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
>See [PATCH v2 0/2] at: https://lore.kernel.org/all/cover.1659077372.git.mchehab@kernel.org/
>
> Documentation/gpu/i915.rst          |   7 ++
> drivers/gpu/drm/i915/gt/intel_tlb.c |  25 +++++++
> drivers/gpu/drm/i915/gt/intel_tlb.h | 101 ++++++++++++++++++++++++++++
> 3 files changed, 133 insertions(+)
>
>diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
>index 4e59db1cfb00..46911fdd79e8 100644
>--- a/Documentation/gpu/i915.rst
>+++ b/Documentation/gpu/i915.rst
>@@ -58,6 +58,13 @@ Intel GVT-g Host Support(vGPU device model)
> .. kernel-doc:: drivers/gpu/drm/i915/intel_gvt.c
>    :internal:
>
>+TLB cache invalidation
>+----------------------
>+
>+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.h
>+
>+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.c
>+
> Workarounds
> -----------
>
>diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c
>index af8cae979489..4873b7ecc015 100644
>--- a/drivers/gpu/drm/i915/gt/intel_tlb.c
>+++ b/drivers/gpu/drm/i915/gt/intel_tlb.c
>@@ -145,6 +145,18 @@ static void mmio_invalidate_full(struct intel_gt *gt)
> 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
> }
>
>+/**
>+ * intel_gt_invalidate_tlb_full - do full TLB cache invalidation
>+ * @gt: GT structure
>+ * @seqno: sequence number
>+ *
>+ * Do a full TLB cache invalidation if the @seqno is bigger than the last
>+ * full TLB cache invalidation.
>+ *
>+ * Note:
>+ * The TLB cache invalidation logic depends on GEN-specific registers.
>+ * It currently supports MMIO-based TLB flush for GEN8 to GEN12.
>+ */
> void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> {
> 	intel_wakeref_t wakeref;
>@@ -171,12 +183,25 @@ void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> 	}
> }
>
>+/**
>+ * intel_gt_init_tlb - initialize TLB-specific vars
>+ * @gt: GT structure
>+ *
>+ * TLB cache invalidation logic internally uses some resources that require
>+ * initialization. Should be called before doing any TLB cache invalidation.
>+ */
> void intel_gt_init_tlb(struct intel_gt *gt)
> {
> 	mutex_init(&gt->tlb.invalidate_lock);
> 	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
> }
>
>+/**
>+ * intel_gt_fini_tlb - initialize TLB-specific vars

Free TLB-specific vars

>+ * @gt: GT structure
>+ *
>+ * Frees any resources needed by TLB cache invalidation logic.
>+ */
> void intel_gt_fini_tlb(struct intel_gt *gt)
> {
> 	mutex_destroy(&gt->tlb.invalidate_lock);
>diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.h b/drivers/gpu/drm/i915/gt/intel_tlb.h
>index 46ce25bf5afe..dca70c33bd61 100644
>--- a/drivers/gpu/drm/i915/gt/intel_tlb.h
>+++ b/drivers/gpu/drm/i915/gt/intel_tlb.h
>@@ -11,16 +11,117 @@
>
> #include "intel_gt_types.h"
>
>+/**
>+ * DOC: TLB cache invalidation logic
>+ *
>+ * The way the current algorithm works is that a struct drm_i915_gem_object can
>+ * be created on any order. At unbind/evict time, the object is warranted that
>+ * it won't be used anymore. So, a sequence number provided by
>+ * intel_gt_next_invalidate_tlb_full() is stored on it. This can happen either
>+ * at __vma_put_pages() - for VMA sync unbind, or at ppgtt_unbind_vma() - for
>+ * VMA async VMA bind.
>+ *
>+ * At __i915_gem_object_unset_pages(), intel_gt_invalidate_tlb_full() is called,
>+ * where it checks if the sequence number of the object was already invalidated
>+ * or not. If not, it flushes the TLB and increments the sequence number::
>+ *
>+ *   void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
>+ *   {
>+ *   ...
>+ * 	with_intel_gt_pm_if_awake(gt, wakeref) {
>+ * 		mutex_lock(&gt->tlb.invalidate_lock);
>+ * 		if (tlb_seqno_passed(gt, seqno))
>+ * 				goto unlock;
>+ *
>+ * 		// Some code to do TLB invalidation
>+ *   ...
>+ *
>+ * 		write_seqcount_invalidate(&gt->tlb.seqno); // increment seqno
>+ * 		mutex_lock(&gt->tlb.invalidate_lock);
>+ *      }
>+ *
>+ * So, let's say the current seqno is 2 and 3 new objects were created,
>+ * on this order::
>+ *
>+ * 	obj1
>+ * 	obj2
>+ * 	obj3
>+ *
>+ * They can be unbind/evict on a different order. At unbind/evict time,
>+ * the mm.tlb will be stamped with the sequence number, using the number
>+ * from the last TLB flush, plus 1.

I am trying to get my head around the below function.

void vma_invalidate_tlb(struct i915_address_space *vm, u32 tlb)
{
        WRITE_ONCE(tlb, intel_gt_next_invalidate_tlb_full(vm->gt));
}

Though we pass obj->mm.tlb for 'tlb' while calling this function,
aren't we writing to local 'tlb' variable here instead of obj->mm.tlb?

>+ *
>+ * Different threads may be used on unbind/evict and/or unset pages.
>+ * As the logic at void intel_gt_invalidate_tlb_full() is protected by a mutex,

May be we can skip 'void' and just keep function name here.

>+ * for simplicity, let's consider just two threads:
>+ *
>+ * +-------------------+-------------------------+---------------------------------+
>+ * | sequence number   | Thread 0                | Thread 1                        +
>+ * +===================+=========================+=================================+
>+ * | seqno=2           |                         |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   | unbind/evict obj3.      |                                 |
>+ * |                   |                         |                                 |
>+ * |                   | obj3.mm.tlb = seqno | 1 |                                 |
>+ * |                   | // obj3.mm.tlb = 3      |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   | unbind/evict obj1.      |                                 |
>+ * |                   |                         |                                 |
>+ * |                   | obj1.mm.tlb = seqno | 1 |                                 |
>+ * |                   | // obj1.mm.tlb = 3      |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   |                         | __i915_gem_object_unset_pages() |
>+ * |                   |                         | called for obj3 => TLB flush    |
>+ * |                   |                         | invalidating both obj1 and obj2.|
>+ * |                   |                         |                                 |
>+ * |                   |                         | seqno += 2                      |
>+ * +-------------------+-------------------------+---------------------------------+
>+ * | seqno=4           |                         |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   | unbind/evict obj2.      |                                 |
>+ * |                   |                         |                                 |
>+ * |                   | obj2.mm.tlb = seqno | 1 |                                 |
>+ * |                   | // obj2.mm.tlb = 5      |                                 |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   |                         | __i915_gem_object_unset_pages() |
>+ * |                   |                         | called for obj1, don't flush    |
>+ * |                   |                         | as past flush invalidated obj1. |
>+ * |                   +-------------------------+---------------------------------+
>+ * |                   |                         | __i915_gem_object_unset_pages() |
>+ * |                   |                         | called for obj2 => TLB flush.   |
>+ * |                   |                         | invalidating obj2.              |
>+ * |                   |                         |                                 |
>+ * |                   |                         | seqno += 2                      |
>+ * +-------------------+-------------------------+---------------------------------+
>+ * | seqno=6           |                         |                                 |
>+ * +-------------------+-------------------------+---------------------------------+
>+ */
>+
> void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno);
>
> void intel_gt_init_tlb(struct intel_gt *gt);
> void intel_gt_fini_tlb(struct intel_gt *gt);
>
>+/**
>+ * intel_gt_tlb_seqno - Returns the current TLB invlidation sequence number
>+ *

Probably this empty comment line needs to be removed before the parameter
description below?

>+ * @gt: GT structure
>+ *
>+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
>+ */
> static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt)
> {
> 	return seqprop_sequence(&gt->tlb.seqno);
> }
>
>+/**
>+ * intel_gt_next_invalidate_tlb_full - Returns the next TLB full invalidation
>+ *	sequence number
>+ *

Same here.

-Niranjana

>+ * @gt: GT structure
>+ *
>+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
>+ */
> static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt)
> {
> 	return intel_gt_tlb_seqno(gt) | 1;
>-- 
>2.36.1
>

Re: [Intel-gfx] [PATCH v2 1/2] drm/i915/gt: Move TLB invalidation to its own file

[Andi Shyti]

Hi Mauro,

On Fri, Jul 29, 2022 at 09:03:54AM +0200, Mauro Carvalho Chehab wrote:
> From: Chris Wilson <chris.p.wilson@intel.com>
> 
> Prepare for supporting more TLB invalidation scenarios by moving
> the current MMIO invalidation to its own file.
> 
> Signed-off-by: Chris Wilson <chris.p.wilson@intel.com>
> Cc: Fei Yang <fei.yang@intel.com>
> Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>

I already reviewed this patch... anyway I checked it again and
it's all correct.

Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>

Thanks,
Andi

Re: [PATCH v2 1/2] drm/i915/gt: Move TLB invalidation to its own file

[Andi Shyti]

Hi Mauro,

On Fri, Jul 29, 2022 at 09:03:54AM +0200, Mauro Carvalho Chehab wrote:
> From: Chris Wilson <chris.p.wilson@intel.com>
> 
> Prepare for supporting more TLB invalidation scenarios by moving
> the current MMIO invalidation to its own file.
> 
> Signed-off-by: Chris Wilson <chris.p.wilson@intel.com>
> Cc: Fei Yang <fei.yang@intel.com>
> Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>

I already reviewed this patch... anyway I checked it again and
it's all correct.

Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>

Thanks,
Andi

Re: [Intel-gfx] [PATCH v2 2/2] drm/i915/gt: document TLB cache invalidation functions

[Mauro Carvalho Chehab]

On Tue, 2 Aug 2022 15:30:44 -0700
Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com> wrote:

> On Fri, Jul 29, 2022 at 09:03:55AM +0200, Mauro Carvalho Chehab wrote:
> >Add a description for the TLB cache invalidation algorithm and for
> >the related kAPI functions.
> >
> >Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
> >---
> >
> >To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
> >See [PATCH v2 0/2] at: https://lore.kernel.org/all/cover.1659077372.git.mchehab@kernel.org/
> >
> > Documentation/gpu/i915.rst          |   7 ++
> > drivers/gpu/drm/i915/gt/intel_tlb.c |  25 +++++++
> > drivers/gpu/drm/i915/gt/intel_tlb.h | 101 ++++++++++++++++++++++++++++
> > 3 files changed, 133 insertions(+)
> >
> >diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
> >index 4e59db1cfb00..46911fdd79e8 100644
> >--- a/Documentation/gpu/i915.rst
> >+++ b/Documentation/gpu/i915.rst
> >@@ -58,6 +58,13 @@ Intel GVT-g Host Support(vGPU device model)
> > .. kernel-doc:: drivers/gpu/drm/i915/intel_gvt.c
> >    :internal:
> >
> >+TLB cache invalidation
> >+----------------------
> >+
> >+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.h
> >+
> >+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.c
> >+
> > Workarounds
> > -----------
> >
> >diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c
> >index af8cae979489..4873b7ecc015 100644
> >--- a/drivers/gpu/drm/i915/gt/intel_tlb.c
> >+++ b/drivers/gpu/drm/i915/gt/intel_tlb.c
> >@@ -145,6 +145,18 @@ static void mmio_invalidate_full(struct intel_gt *gt)
> > 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
> > }
> >
> >+/**
> >+ * intel_gt_invalidate_tlb_full - do full TLB cache invalidation
> >+ * @gt: GT structure
> >+ * @seqno: sequence number
> >+ *
> >+ * Do a full TLB cache invalidation if the @seqno is bigger than the last
> >+ * full TLB cache invalidation.
> >+ *
> >+ * Note:
> >+ * The TLB cache invalidation logic depends on GEN-specific registers.
> >+ * It currently supports MMIO-based TLB flush for GEN8 to GEN12.
> >+ */
> > void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> > {
> > 	intel_wakeref_t wakeref;
> >@@ -171,12 +183,25 @@ void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> > 	}
> > }
> >
> >+/**
> >+ * intel_gt_init_tlb - initialize TLB-specific vars
> >+ * @gt: GT structure
> >+ *
> >+ * TLB cache invalidation logic internally uses some resources that require
> >+ * initialization. Should be called before doing any TLB cache invalidation.
> >+ */
> > void intel_gt_init_tlb(struct intel_gt *gt)
> > {
> > 	mutex_init(&gt->tlb.invalidate_lock);
> > 	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
> > }
> >
> >+/**
> >+ * intel_gt_fini_tlb - initialize TLB-specific vars  
> 
> Free TLB-specific vars

OK.

> 
> >+ * @gt: GT structure
> >+ *
> >+ * Frees any resources needed by TLB cache invalidation logic.
> >+ */
> > void intel_gt_fini_tlb(struct intel_gt *gt)
> > {
> > 	mutex_destroy(&gt->tlb.invalidate_lock);
> >diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.h b/drivers/gpu/drm/i915/gt/intel_tlb.h
> >index 46ce25bf5afe..dca70c33bd61 100644
> >--- a/drivers/gpu/drm/i915/gt/intel_tlb.h
> >+++ b/drivers/gpu/drm/i915/gt/intel_tlb.h
> >@@ -11,16 +11,117 @@
> >
> > #include "intel_gt_types.h"
> >
> >+/**
> >+ * DOC: TLB cache invalidation logic
> >+ *
> >+ * The way the current algorithm works is that a struct drm_i915_gem_object can
> >+ * be created on any order. At unbind/evict time, the object is warranted that
> >+ * it won't be used anymore. So, a sequence number provided by
> >+ * intel_gt_next_invalidate_tlb_full() is stored on it. This can happen either
> >+ * at __vma_put_pages() - for VMA sync unbind, or at ppgtt_unbind_vma() - for
> >+ * VMA async VMA bind.
> >+ *
> >+ * At __i915_gem_object_unset_pages(), intel_gt_invalidate_tlb_full() is called,
> >+ * where it checks if the sequence number of the object was already invalidated
> >+ * or not. If not, it flushes the TLB and increments the sequence number::
> >+ *
> >+ *   void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> >+ *   {
> >+ *   ...
> >+ * 	with_intel_gt_pm_if_awake(gt, wakeref) {
> >+ * 		mutex_lock(&gt->tlb.invalidate_lock);
> >+ * 		if (tlb_seqno_passed(gt, seqno))
> >+ * 				goto unlock;
> >+ *
> >+ * 		// Some code to do TLB invalidation
> >+ *   ...
> >+ *
> >+ * 		write_seqcount_invalidate(&gt->tlb.seqno); // increment seqno
> >+ * 		mutex_lock(&gt->tlb.invalidate_lock);
> >+ *      }
> >+ *
> >+ * So, let's say the current seqno is 2 and 3 new objects were created,
> >+ * on this order::
> >+ *
> >+ * 	obj1
> >+ * 	obj2
> >+ * 	obj3
> >+ *
> >+ * They can be unbind/evict on a different order. At unbind/evict time,
> >+ * the mm.tlb will be stamped with the sequence number, using the number
> >+ * from the last TLB flush, plus 1.  
> 
> I am trying to get my head around the below function.
> 
> void vma_invalidate_tlb(struct i915_address_space *vm, u32 tlb)
> {
>         WRITE_ONCE(tlb, intel_gt_next_invalidate_tlb_full(vm->gt));
> }
> 
> Though we pass obj->mm.tlb for 'tlb' while calling this function,
> aren't we writing to local 'tlb' variable here instead of obj->mm.tlb?

It should be passing a pointer. I wrote such fix after a review,
but somehow it ended getting lost. I'll send the fix at v3.

> >+ *
> >+ * Different threads may be used on unbind/evict and/or unset pages.
> >+ * As the logic at void intel_gt_invalidate_tlb_full() is protected by a mutex,  
> 
> May be we can skip 'void' and just keep function name here.

Sure.

> >+ * for simplicity, let's consider just two threads:
> >+ *
> >+ * +-------------------+-------------------------+---------------------------------+
> >+ * | sequence number   | Thread 0                | Thread 1                        +
> >+ * +===================+=========================+=================================+
> >+ * | seqno=2           |                         |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   | unbind/evict obj3.      |                                 |
> >+ * |                   |                         |                                 |
> >+ * |                   | obj3.mm.tlb = seqno | 1 |                                 |
> >+ * |                   | // obj3.mm.tlb = 3      |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   | unbind/evict obj1.      |                                 |
> >+ * |                   |                         |                                 |
> >+ * |                   | obj1.mm.tlb = seqno | 1 |                                 |
> >+ * |                   | // obj1.mm.tlb = 3      |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   |                         | __i915_gem_object_unset_pages() |
> >+ * |                   |                         | called for obj3 => TLB flush    |
> >+ * |                   |                         | invalidating both obj1 and obj2.|
> >+ * |                   |                         |                                 |
> >+ * |                   |                         | seqno += 2                      |
> >+ * +-------------------+-------------------------+---------------------------------+
> >+ * | seqno=4           |                         |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   | unbind/evict obj2.      |                                 |
> >+ * |                   |                         |                                 |
> >+ * |                   | obj2.mm.tlb = seqno | 1 |                                 |
> >+ * |                   | // obj2.mm.tlb = 5      |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   |                         | __i915_gem_object_unset_pages() |
> >+ * |                   |                         | called for obj1, don't flush    |
> >+ * |                   |                         | as past flush invalidated obj1. |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   |                         | __i915_gem_object_unset_pages() |
> >+ * |                   |                         | called for obj2 => TLB flush.   |
> >+ * |                   |                         | invalidating obj2.              |
> >+ * |                   |                         |                                 |
> >+ * |                   |                         | seqno += 2                      |
> >+ * +-------------------+-------------------------+---------------------------------+
> >+ * | seqno=6           |                         |                                 |
> >+ * +-------------------+-------------------------+---------------------------------+
> >+ */
> >+
> > void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno);
> >
> > void intel_gt_init_tlb(struct intel_gt *gt);
> > void intel_gt_fini_tlb(struct intel_gt *gt);
> >
> >+/**
> >+ * intel_gt_tlb_seqno - Returns the current TLB invlidation sequence number
> >+ *  
> 
> Probably this empty comment line needs to be removed before the parameter
> description below?

Kernel-doc actually accepts both with or without a blank line. My
personal preference is to place a blank line, because sometimes the
function description plus function name is bigger than one line.
So, it is usually clearer when adding a blank line than doing
something like this (perfectly valid kerneldoc markup):

	/**
	 * long_function_name_foo - Lorem ipsum dolor sit amet, consectetur
	 * adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore.
	 * @bar: some parameter
	 *  ...

But yeah, kernel-doc documentation example doesn't have a blank
line. So, I'll drop it.

> 
> >+ * @gt: GT structure
> >+ *
> >+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
> >+ */
> > static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt)
> > {
> > 	return seqprop_sequence(&gt->tlb.seqno);
> > }
> >
> >+/**
> >+ * intel_gt_next_invalidate_tlb_full - Returns the next TLB full invalidation
> >+ *	sequence number
> >+ *  
> 
> Same here.
> 
> -Niranjana
> 
> >+ * @gt: GT structure
> >+ *
> >+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
> >+ */
> > static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt)
> > {
> > 	return intel_gt_tlb_seqno(gt) | 1;
> >-- 
> >2.36.1
> >  

Thanks!
Mauro

Re: [Intel-gfx] [PATCH v2 2/2] drm/i915/gt: document TLB cache invalidation functions

[Mauro Carvalho Chehab]

On Tue, 2 Aug 2022 15:30:44 -0700
Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com> wrote:

> On Fri, Jul 29, 2022 at 09:03:55AM +0200, Mauro Carvalho Chehab wrote:
> >Add a description for the TLB cache invalidation algorithm and for
> >the related kAPI functions.
> >
> >Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
> >---
> >
> >To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
> >See [PATCH v2 0/2] at: https://lore.kernel.org/all/cover.1659077372.git.mchehab@kernel.org/
> >
> > Documentation/gpu/i915.rst          |   7 ++
> > drivers/gpu/drm/i915/gt/intel_tlb.c |  25 +++++++
> > drivers/gpu/drm/i915/gt/intel_tlb.h | 101 ++++++++++++++++++++++++++++
> > 3 files changed, 133 insertions(+)
> >
> >diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
> >index 4e59db1cfb00..46911fdd79e8 100644
> >--- a/Documentation/gpu/i915.rst
> >+++ b/Documentation/gpu/i915.rst
> >@@ -58,6 +58,13 @@ Intel GVT-g Host Support(vGPU device model)
> > .. kernel-doc:: drivers/gpu/drm/i915/intel_gvt.c
> >    :internal:
> >
> >+TLB cache invalidation
> >+----------------------
> >+
> >+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.h
> >+
> >+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.c
> >+
> > Workarounds
> > -----------
> >
> >diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c
> >index af8cae979489..4873b7ecc015 100644
> >--- a/drivers/gpu/drm/i915/gt/intel_tlb.c
> >+++ b/drivers/gpu/drm/i915/gt/intel_tlb.c
> >@@ -145,6 +145,18 @@ static void mmio_invalidate_full(struct intel_gt *gt)
> > 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
> > }
> >
> >+/**
> >+ * intel_gt_invalidate_tlb_full - do full TLB cache invalidation
> >+ * @gt: GT structure
> >+ * @seqno: sequence number
> >+ *
> >+ * Do a full TLB cache invalidation if the @seqno is bigger than the last
> >+ * full TLB cache invalidation.
> >+ *
> >+ * Note:
> >+ * The TLB cache invalidation logic depends on GEN-specific registers.
> >+ * It currently supports MMIO-based TLB flush for GEN8 to GEN12.
> >+ */
> > void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> > {
> > 	intel_wakeref_t wakeref;
> >@@ -171,12 +183,25 @@ void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> > 	}
> > }
> >
> >+/**
> >+ * intel_gt_init_tlb - initialize TLB-specific vars
> >+ * @gt: GT structure
> >+ *
> >+ * TLB cache invalidation logic internally uses some resources that require
> >+ * initialization. Should be called before doing any TLB cache invalidation.
> >+ */
> > void intel_gt_init_tlb(struct intel_gt *gt)
> > {
> > 	mutex_init(&gt->tlb.invalidate_lock);
> > 	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
> > }
> >
> >+/**
> >+ * intel_gt_fini_tlb - initialize TLB-specific vars  
> 
> Free TLB-specific vars

OK.

> 
> >+ * @gt: GT structure
> >+ *
> >+ * Frees any resources needed by TLB cache invalidation logic.
> >+ */
> > void intel_gt_fini_tlb(struct intel_gt *gt)
> > {
> > 	mutex_destroy(&gt->tlb.invalidate_lock);
> >diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.h b/drivers/gpu/drm/i915/gt/intel_tlb.h
> >index 46ce25bf5afe..dca70c33bd61 100644
> >--- a/drivers/gpu/drm/i915/gt/intel_tlb.h
> >+++ b/drivers/gpu/drm/i915/gt/intel_tlb.h
> >@@ -11,16 +11,117 @@
> >
> > #include "intel_gt_types.h"
> >
> >+/**
> >+ * DOC: TLB cache invalidation logic
> >+ *
> >+ * The way the current algorithm works is that a struct drm_i915_gem_object can
> >+ * be created on any order. At unbind/evict time, the object is warranted that
> >+ * it won't be used anymore. So, a sequence number provided by
> >+ * intel_gt_next_invalidate_tlb_full() is stored on it. This can happen either
> >+ * at __vma_put_pages() - for VMA sync unbind, or at ppgtt_unbind_vma() - for
> >+ * VMA async VMA bind.
> >+ *
> >+ * At __i915_gem_object_unset_pages(), intel_gt_invalidate_tlb_full() is called,
> >+ * where it checks if the sequence number of the object was already invalidated
> >+ * or not. If not, it flushes the TLB and increments the sequence number::
> >+ *
> >+ *   void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> >+ *   {
> >+ *   ...
> >+ * 	with_intel_gt_pm_if_awake(gt, wakeref) {
> >+ * 		mutex_lock(&gt->tlb.invalidate_lock);
> >+ * 		if (tlb_seqno_passed(gt, seqno))
> >+ * 				goto unlock;
> >+ *
> >+ * 		// Some code to do TLB invalidation
> >+ *   ...
> >+ *
> >+ * 		write_seqcount_invalidate(&gt->tlb.seqno); // increment seqno
> >+ * 		mutex_lock(&gt->tlb.invalidate_lock);
> >+ *      }
> >+ *
> >+ * So, let's say the current seqno is 2 and 3 new objects were created,
> >+ * on this order::
> >+ *
> >+ * 	obj1
> >+ * 	obj2
> >+ * 	obj3
> >+ *
> >+ * They can be unbind/evict on a different order. At unbind/evict time,
> >+ * the mm.tlb will be stamped with the sequence number, using the number
> >+ * from the last TLB flush, plus 1.  
> 
> I am trying to get my head around the below function.
> 
> void vma_invalidate_tlb(struct i915_address_space *vm, u32 tlb)
> {
>         WRITE_ONCE(tlb, intel_gt_next_invalidate_tlb_full(vm->gt));
> }
> 
> Though we pass obj->mm.tlb for 'tlb' while calling this function,
> aren't we writing to local 'tlb' variable here instead of obj->mm.tlb?

It should be passing a pointer. I wrote such fix after a review,
but somehow it ended getting lost. I'll send the fix at v3.

> >+ *
> >+ * Different threads may be used on unbind/evict and/or unset pages.
> >+ * As the logic at void intel_gt_invalidate_tlb_full() is protected by a mutex,  
> 
> May be we can skip 'void' and just keep function name here.

Sure.

> >+ * for simplicity, let's consider just two threads:
> >+ *
> >+ * +-------------------+-------------------------+---------------------------------+
> >+ * | sequence number   | Thread 0                | Thread 1                        +
> >+ * +===================+=========================+=================================+
> >+ * | seqno=2           |                         |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   | unbind/evict obj3.      |                                 |
> >+ * |                   |                         |                                 |
> >+ * |                   | obj3.mm.tlb = seqno | 1 |                                 |
> >+ * |                   | // obj3.mm.tlb = 3      |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   | unbind/evict obj1.      |                                 |
> >+ * |                   |                         |                                 |
> >+ * |                   | obj1.mm.tlb = seqno | 1 |                                 |
> >+ * |                   | // obj1.mm.tlb = 3      |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   |                         | __i915_gem_object_unset_pages() |
> >+ * |                   |                         | called for obj3 => TLB flush    |
> >+ * |                   |                         | invalidating both obj1 and obj2.|
> >+ * |                   |                         |                                 |
> >+ * |                   |                         | seqno += 2                      |
> >+ * +-------------------+-------------------------+---------------------------------+
> >+ * | seqno=4           |                         |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   | unbind/evict obj2.      |                                 |
> >+ * |                   |                         |                                 |
> >+ * |                   | obj2.mm.tlb = seqno | 1 |                                 |
> >+ * |                   | // obj2.mm.tlb = 5      |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   |                         | __i915_gem_object_unset_pages() |
> >+ * |                   |                         | called for obj1, don't flush    |
> >+ * |                   |                         | as past flush invalidated obj1. |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   |                         | __i915_gem_object_unset_pages() |
> >+ * |                   |                         | called for obj2 => TLB flush.   |
> >+ * |                   |                         | invalidating obj2.              |
> >+ * |                   |                         |                                 |
> >+ * |                   |                         | seqno += 2                      |
> >+ * +-------------------+-------------------------+---------------------------------+
> >+ * | seqno=6           |                         |                                 |
> >+ * +-------------------+-------------------------+---------------------------------+
> >+ */
> >+
> > void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno);
> >
> > void intel_gt_init_tlb(struct intel_gt *gt);
> > void intel_gt_fini_tlb(struct intel_gt *gt);
> >
> >+/**
> >+ * intel_gt_tlb_seqno - Returns the current TLB invlidation sequence number
> >+ *  
> 
> Probably this empty comment line needs to be removed before the parameter
> description below?

Kernel-doc actually accepts both with or without a blank line. My
personal preference is to place a blank line, because sometimes the
function description plus function name is bigger than one line.
So, it is usually clearer when adding a blank line than doing
something like this (perfectly valid kerneldoc markup):

	/**
	 * long_function_name_foo - Lorem ipsum dolor sit amet, consectetur
	 * adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore.
	 * @bar: some parameter
	 *  ...

But yeah, kernel-doc documentation example doesn't have a blank
line. So, I'll drop it.

> 
> >+ * @gt: GT structure
> >+ *
> >+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
> >+ */
> > static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt)
> > {
> > 	return seqprop_sequence(&gt->tlb.seqno);
> > }
> >
> >+/**
> >+ * intel_gt_next_invalidate_tlb_full - Returns the next TLB full invalidation
> >+ *	sequence number
> >+ *  
> 
> Same here.
> 
> -Niranjana
> 
> >+ * @gt: GT structure
> >+ *
> >+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
> >+ */
> > static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt)
> > {
> > 	return intel_gt_tlb_seqno(gt) | 1;
> >-- 
> >2.36.1
> >  

Thanks!
Mauro

Re: [Intel-gfx] [PATCH v2 2/2] drm/i915/gt: document TLB cache invalidation functions

[Mauro Carvalho Chehab]

On Tue, 2 Aug 2022 15:30:44 -0700
Niranjana Vishwanathapura <niranjana.vishwanathapura@intel.com> wrote:

> On Fri, Jul 29, 2022 at 09:03:55AM +0200, Mauro Carvalho Chehab wrote:
> >Add a description for the TLB cache invalidation algorithm and for
> >the related kAPI functions.
> >
> >Signed-off-by: Mauro Carvalho Chehab <mchehab@kernel.org>
> >---
> >
> >To avoid mailbombing on a large number of people, only mailing lists were C/C on the cover.
> >See [PATCH v2 0/2] at: https://lore.kernel.org/all/cover.1659077372.git.mchehab@kernel.org/
> >
> > Documentation/gpu/i915.rst          |   7 ++
> > drivers/gpu/drm/i915/gt/intel_tlb.c |  25 +++++++
> > drivers/gpu/drm/i915/gt/intel_tlb.h | 101 ++++++++++++++++++++++++++++
> > 3 files changed, 133 insertions(+)
> >
> >diff --git a/Documentation/gpu/i915.rst b/Documentation/gpu/i915.rst
> >index 4e59db1cfb00..46911fdd79e8 100644
> >--- a/Documentation/gpu/i915.rst
> >+++ b/Documentation/gpu/i915.rst
> >@@ -58,6 +58,13 @@ Intel GVT-g Host Support(vGPU device model)
> > .. kernel-doc:: drivers/gpu/drm/i915/intel_gvt.c
> >    :internal:
> >
> >+TLB cache invalidation
> >+----------------------
> >+
> >+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.h
> >+
> >+.. kernel-doc:: drivers/gpu/drm/i915/gt/intel_tlb.c
> >+
> > Workarounds
> > -----------
> >
> >diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.c b/drivers/gpu/drm/i915/gt/intel_tlb.c
> >index af8cae979489..4873b7ecc015 100644
> >--- a/drivers/gpu/drm/i915/gt/intel_tlb.c
> >+++ b/drivers/gpu/drm/i915/gt/intel_tlb.c
> >@@ -145,6 +145,18 @@ static void mmio_invalidate_full(struct intel_gt *gt)
> > 	intel_uncore_forcewake_put_delayed(uncore, FORCEWAKE_ALL);
> > }
> >
> >+/**
> >+ * intel_gt_invalidate_tlb_full - do full TLB cache invalidation
> >+ * @gt: GT structure
> >+ * @seqno: sequence number
> >+ *
> >+ * Do a full TLB cache invalidation if the @seqno is bigger than the last
> >+ * full TLB cache invalidation.
> >+ *
> >+ * Note:
> >+ * The TLB cache invalidation logic depends on GEN-specific registers.
> >+ * It currently supports MMIO-based TLB flush for GEN8 to GEN12.
> >+ */
> > void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> > {
> > 	intel_wakeref_t wakeref;
> >@@ -171,12 +183,25 @@ void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> > 	}
> > }
> >
> >+/**
> >+ * intel_gt_init_tlb - initialize TLB-specific vars
> >+ * @gt: GT structure
> >+ *
> >+ * TLB cache invalidation logic internally uses some resources that require
> >+ * initialization. Should be called before doing any TLB cache invalidation.
> >+ */
> > void intel_gt_init_tlb(struct intel_gt *gt)
> > {
> > 	mutex_init(&gt->tlb.invalidate_lock);
> > 	seqcount_mutex_init(&gt->tlb.seqno, &gt->tlb.invalidate_lock);
> > }
> >
> >+/**
> >+ * intel_gt_fini_tlb - initialize TLB-specific vars  
> 
> Free TLB-specific vars

OK.

> 
> >+ * @gt: GT structure
> >+ *
> >+ * Frees any resources needed by TLB cache invalidation logic.
> >+ */
> > void intel_gt_fini_tlb(struct intel_gt *gt)
> > {
> > 	mutex_destroy(&gt->tlb.invalidate_lock);
> >diff --git a/drivers/gpu/drm/i915/gt/intel_tlb.h b/drivers/gpu/drm/i915/gt/intel_tlb.h
> >index 46ce25bf5afe..dca70c33bd61 100644
> >--- a/drivers/gpu/drm/i915/gt/intel_tlb.h
> >+++ b/drivers/gpu/drm/i915/gt/intel_tlb.h
> >@@ -11,16 +11,117 @@
> >
> > #include "intel_gt_types.h"
> >
> >+/**
> >+ * DOC: TLB cache invalidation logic
> >+ *
> >+ * The way the current algorithm works is that a struct drm_i915_gem_object can
> >+ * be created on any order. At unbind/evict time, the object is warranted that
> >+ * it won't be used anymore. So, a sequence number provided by
> >+ * intel_gt_next_invalidate_tlb_full() is stored on it. This can happen either
> >+ * at __vma_put_pages() - for VMA sync unbind, or at ppgtt_unbind_vma() - for
> >+ * VMA async VMA bind.
> >+ *
> >+ * At __i915_gem_object_unset_pages(), intel_gt_invalidate_tlb_full() is called,
> >+ * where it checks if the sequence number of the object was already invalidated
> >+ * or not. If not, it flushes the TLB and increments the sequence number::
> >+ *
> >+ *   void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno)
> >+ *   {
> >+ *   ...
> >+ * 	with_intel_gt_pm_if_awake(gt, wakeref) {
> >+ * 		mutex_lock(&gt->tlb.invalidate_lock);
> >+ * 		if (tlb_seqno_passed(gt, seqno))
> >+ * 				goto unlock;
> >+ *
> >+ * 		// Some code to do TLB invalidation
> >+ *   ...
> >+ *
> >+ * 		write_seqcount_invalidate(&gt->tlb.seqno); // increment seqno
> >+ * 		mutex_lock(&gt->tlb.invalidate_lock);
> >+ *      }
> >+ *
> >+ * So, let's say the current seqno is 2 and 3 new objects were created,
> >+ * on this order::
> >+ *
> >+ * 	obj1
> >+ * 	obj2
> >+ * 	obj3
> >+ *
> >+ * They can be unbind/evict on a different order. At unbind/evict time,
> >+ * the mm.tlb will be stamped with the sequence number, using the number
> >+ * from the last TLB flush, plus 1.  
> 
> I am trying to get my head around the below function.
> 
> void vma_invalidate_tlb(struct i915_address_space *vm, u32 tlb)
> {
>         WRITE_ONCE(tlb, intel_gt_next_invalidate_tlb_full(vm->gt));
> }
> 
> Though we pass obj->mm.tlb for 'tlb' while calling this function,
> aren't we writing to local 'tlb' variable here instead of obj->mm.tlb?

It should be passing a pointer. I wrote such fix after a review,
but somehow it ended getting lost. I'll send the fix at v3.

> >+ *
> >+ * Different threads may be used on unbind/evict and/or unset pages.
> >+ * As the logic at void intel_gt_invalidate_tlb_full() is protected by a mutex,  
> 
> May be we can skip 'void' and just keep function name here.

Sure.

> >+ * for simplicity, let's consider just two threads:
> >+ *
> >+ * +-------------------+-------------------------+---------------------------------+
> >+ * | sequence number   | Thread 0                | Thread 1                        +
> >+ * +===================+=========================+=================================+
> >+ * | seqno=2           |                         |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   | unbind/evict obj3.      |                                 |
> >+ * |                   |                         |                                 |
> >+ * |                   | obj3.mm.tlb = seqno | 1 |                                 |
> >+ * |                   | // obj3.mm.tlb = 3      |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   | unbind/evict obj1.      |                                 |
> >+ * |                   |                         |                                 |
> >+ * |                   | obj1.mm.tlb = seqno | 1 |                                 |
> >+ * |                   | // obj1.mm.tlb = 3      |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   |                         | __i915_gem_object_unset_pages() |
> >+ * |                   |                         | called for obj3 => TLB flush    |
> >+ * |                   |                         | invalidating both obj1 and obj2.|
> >+ * |                   |                         |                                 |
> >+ * |                   |                         | seqno += 2                      |
> >+ * +-------------------+-------------------------+---------------------------------+
> >+ * | seqno=4           |                         |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   | unbind/evict obj2.      |                                 |
> >+ * |                   |                         |                                 |
> >+ * |                   | obj2.mm.tlb = seqno | 1 |                                 |
> >+ * |                   | // obj2.mm.tlb = 5      |                                 |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   |                         | __i915_gem_object_unset_pages() |
> >+ * |                   |                         | called for obj1, don't flush    |
> >+ * |                   |                         | as past flush invalidated obj1. |
> >+ * |                   +-------------------------+---------------------------------+
> >+ * |                   |                         | __i915_gem_object_unset_pages() |
> >+ * |                   |                         | called for obj2 => TLB flush.   |
> >+ * |                   |                         | invalidating obj2.              |
> >+ * |                   |                         |                                 |
> >+ * |                   |                         | seqno += 2                      |
> >+ * +-------------------+-------------------------+---------------------------------+
> >+ * | seqno=6           |                         |                                 |
> >+ * +-------------------+-------------------------+---------------------------------+
> >+ */
> >+
> > void intel_gt_invalidate_tlb_full(struct intel_gt *gt, u32 seqno);
> >
> > void intel_gt_init_tlb(struct intel_gt *gt);
> > void intel_gt_fini_tlb(struct intel_gt *gt);
> >
> >+/**
> >+ * intel_gt_tlb_seqno - Returns the current TLB invlidation sequence number
> >+ *  
> 
> Probably this empty comment line needs to be removed before the parameter
> description below?

Kernel-doc actually accepts both with or without a blank line. My
personal preference is to place a blank line, because sometimes the
function description plus function name is bigger than one line.
So, it is usually clearer when adding a blank line than doing
something like this (perfectly valid kerneldoc markup):

	/**
	 * long_function_name_foo - Lorem ipsum dolor sit amet, consectetur
	 * adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore.
	 * @bar: some parameter
	 *  ...

But yeah, kernel-doc documentation example doesn't have a blank
line. So, I'll drop it.

> 
> >+ * @gt: GT structure
> >+ *
> >+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
> >+ */
> > static inline u32 intel_gt_tlb_seqno(const struct intel_gt *gt)
> > {
> > 	return seqprop_sequence(&gt->tlb.seqno);
> > }
> >
> >+/**
> >+ * intel_gt_next_invalidate_tlb_full - Returns the next TLB full invalidation
> >+ *	sequence number
> >+ *  
> 
> Same here.
> 
> -Niranjana
> 
> >+ * @gt: GT structure
> >+ *
> >+ * There's no need to lock while calling it, as seqprop_sequence is thread-safe
> >+ */
> > static inline u32 intel_gt_next_invalidate_tlb_full(const struct intel_gt *gt)
> > {
> > 	return intel_gt_tlb_seqno(gt) | 1;
> >-- 
> >2.36.1
> >  

Thanks!
Mauro