From 4ca1fd418338d4d135428a0eb1e16e3b3ce17ee8 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Tue, 17 Dec 2024 21:31:21 -0800
Subject: [PATCH 01/16] drm/xe: Fix fault on fd close after unbind

If userspace holds an fd open, unbinds the device and then closes it,
the driver shouldn't try to access the hardware. Protect it by using
drm_dev_enter()/drm_dev_exit(). This fixes the following page fault:

<6> [IGT] xe_wedged: exiting, ret=98
<1> BUG: unable to handle page fault for address: ffffc901bc5e508c
<1> #PF: supervisor read access in kernel mode
<1> #PF: error_code(0x0000) - not-present page
...
<4>   xe_lrc_update_timestamp+0x1c/0xd0 [xe]
<4>   xe_exec_queue_update_run_ticks+0x50/0xb0 [xe]
<4>   xe_exec_queue_fini+0x16/0xb0 [xe]
<4>   __guc_exec_queue_fini_async+0xc4/0x190 [xe]
<4>   guc_exec_queue_fini_async+0xa0/0xe0 [xe]
<4>   guc_exec_queue_fini+0x23/0x40 [xe]
<4>   xe_exec_queue_destroy+0xb3/0xf0 [xe]
<4>   xe_file_close+0xd4/0x1a0 [xe]
<4>   drm_file_free+0x210/0x280 [drm]
<4>   drm_close_helper.isra.0+0x6d/0x80 [drm]
<4>   drm_release_noglobal+0x20/0x90 [drm]

Fixes: 83db047d9425 ("drm/xe: Stop accumulating LRC timestamp on job_free")
Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/3421
Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241218053122.2730195-1-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 9c94be571900..8005530b5e51 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -8,6 +8,7 @@
 #include <linux/nospec.h>
 
 #include <drm/drm_device.h>
+#include <drm/drm_drv.h>
 #include <drm/drm_file.h>
 #include <uapi/drm/xe_drm.h>
 
@@ -768,9 +769,11 @@ bool xe_exec_queue_is_idle(struct xe_exec_queue *q)
  */
 void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 {
+	struct xe_device *xe = gt_to_xe(q->gt);
 	struct xe_file *xef;
 	struct xe_lrc *lrc;
 	u32 old_ts, new_ts;
+	int idx;
 
 	/*
 	 * Jobs that are run during driver load may use an exec_queue, but are
@@ -780,6 +783,10 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 	if (!q->vm || !q->vm->xef)
 		return;
 
+	/* Synchronize with unbind while holding the xe file open */
+	if (!drm_dev_enter(&xe->drm, &idx))
+		return;
+
 	xef = q->vm->xef;
 
 	/*
@@ -793,6 +800,8 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 	lrc = q->lrc[0];
 	new_ts = xe_lrc_update_timestamp(lrc, &old_ts);
 	xef->run_ticks[q->class] += (new_ts - old_ts) * q->width;
+
+	drm_dev_exit(idx);
 }
 
 /**
-- 
2.51.0


From 2054d38ccf708e1add482c6345f7f349059b56e0 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Tue, 17 Dec 2024 21:31:22 -0800
Subject: [PATCH 02/16] drm/xe: Use q->xef for accessing xe file

No need to traverse through the vm object as each exec queue maintains a
reference to xe_file. Also improve/simplify the comment on why xef is
checked.

Reviewed-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241218053122.2730195-2-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 8005530b5e51..8948f50ee58f 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -770,25 +770,21 @@ bool xe_exec_queue_is_idle(struct xe_exec_queue *q)
 void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 {
 	struct xe_device *xe = gt_to_xe(q->gt);
-	struct xe_file *xef;
 	struct xe_lrc *lrc;
 	u32 old_ts, new_ts;
 	int idx;
 
 	/*
-	 * Jobs that are run during driver load may use an exec_queue, but are
-	 * not associated with a user xe file, so avoid accumulating busyness
-	 * for kernel specific work.
+	 * Jobs that are executed by kernel doesn't have a corresponding xe_file
+	 * and thus are not accounted.
 	 */
-	if (!q->vm || !q->vm->xef)
+	if (!q->xef)
 		return;
 
 	/* Synchronize with unbind while holding the xe file open */
 	if (!drm_dev_enter(&xe->drm, &idx))
 		return;
 
-	xef = q->vm->xef;
-
 	/*
 	 * Only sample the first LRC. For parallel submission, all of them are
 	 * scheduled together and we compensate that below by multiplying by
@@ -799,7 +795,7 @@ void xe_exec_queue_update_run_ticks(struct xe_exec_queue *q)
 	 */
 	lrc = q->lrc[0];
 	new_ts = xe_lrc_update_timestamp(lrc, &old_ts);
-	xef->run_ticks[q->class] += (new_ts - old_ts) * q->width;
+	q->xef->run_ticks[q->class] += (new_ts - old_ts) * q->width;
 
 	drm_dev_exit(idx);
 }
-- 
2.51.0


From 07089083a526ea19daa72a1edf9d6e209615b77c Mon Sep 17 00:00:00 2001
From: =?utf8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Mon, 23 Dec 2024 14:42:50 +0100
Subject: [PATCH 03/16] drm/xe/tracing: Fix a potential TP_printk UAF
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

The commit
afd2627f727b ("tracing: Check "%s" dereference via the field and not the TP_printk format")
exposes potential UAFs in the xe_bo_move trace event.

Fix those by avoiding dereferencing the
xe_mem_type_to_name[] array at TP_printk time.

Since some code refactoring has taken place, explicit backporting may
be needed for kernels older than 6.10.

Fixes: e46d3f813abd ("drm/xe/trace: Extract bo, vm, vma traces")
Cc: Gustavo Sousa <gustavo.sousa@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: "Thomas Hellström" <thomas.hellstrom@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: intel-xe@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v6.11+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241223134250.14345-1-thomas.hellstrom@linux.intel.com
---
 drivers/gpu/drm/xe/xe_trace_bo.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_trace_bo.h b/drivers/gpu/drm/xe/xe_trace_bo.h
index 1762dd30ba6d..ea50fee50c7d 100644
--- a/drivers/gpu/drm/xe/xe_trace_bo.h
+++ b/drivers/gpu/drm/xe/xe_trace_bo.h
@@ -60,8 +60,8 @@ TRACE_EVENT(xe_bo_move,
 	    TP_STRUCT__entry(
 		     __field(struct xe_bo *, bo)
 		     __field(size_t, size)
-		     __field(u32, new_placement)
-		     __field(u32, old_placement)
+		     __string(new_placement_name, xe_mem_type_to_name[new_placement])
+		     __string(old_placement_name, xe_mem_type_to_name[old_placement])
 		     __string(device_id, __dev_name_bo(bo))
 		     __field(bool, move_lacks_source)
 			),
@@ -69,15 +69,15 @@ TRACE_EVENT(xe_bo_move,
 	    TP_fast_assign(
 		   __entry->bo      = bo;
 		   __entry->size = bo->size;
-		   __entry->new_placement = new_placement;
-		   __entry->old_placement = old_placement;
+		   __assign_str(new_placement_name);
+		   __assign_str(old_placement_name);
 		   __assign_str(device_id);
 		   __entry->move_lacks_source = move_lacks_source;
 		   ),
 	    TP_printk("move_lacks_source:%s, migrate object %p [size %zu] from %s to %s device_id:%s",
 		      __entry->move_lacks_source ? "yes" : "no", __entry->bo, __entry->size,
-		      xe_mem_type_to_name[__entry->old_placement],
-		      xe_mem_type_to_name[__entry->new_placement], __get_str(device_id))
+		      __get_str(old_placement_name),
+		      __get_str(new_placement_name), __get_str(device_id))
 );
 
 DECLARE_EVENT_CLASS(xe_vma,
-- 
2.51.0


From 55039832f98c7e05f1cf9e0d8c12b2490abd0f16 Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Fri, 20 Dec 2024 09:19:18 -0800
Subject: [PATCH 04/16] xe/oa: Fix query mode of operation for OAR/OAC

This is a set of squashed commits to facilitate smooth applying to
stable. Each commit message is retained for reference.

1) Allow a GGTT mapped batch to be submitted to user exec queue

For a OA use case, one of the HW registers needs to be modified by
submitting an MI_LOAD_REGISTER_IMM command to the users exec queue, so
that the register is modified in the user's hardware context. In order
to do this a batch that is mapped in GGTT, needs to be submitted to the
user exec queue. Since all user submissions use q->vm and hence PPGTT,
add some plumbing to enable submission of batches mapped in GGTT.

v2: ggtt is zero-initialized, so no need to set it false (Matt Brost)

2) xe/oa: Use MI_LOAD_REGISTER_IMMEDIATE to enable OAR/OAC

To enable OAR/OAC, a bit in RING_CONTEXT_CONTROL needs to be set.
Setting this bit cause the context image size to change and if not done
correct, can cause undesired hangs.

Current code uses a separate exec_queue to modify this bit and is
error-prone. As per HW recommendation, submit MI_LOAD_REGISTER_IMM to
the target hardware context to modify the relevant bit.

In v2 version, an attempt to submit everything to the user-queue was
made, but it failed the unprivileged-single-ctx-counters test. It
appears that the OACTXCONTROL must be modified from a remote context.

In v3 version, all context specific register configurations were moved
to use LOAD_REGISTER_IMMEDIATE and that seems to work well. This is a
cleaner way, since we can now submit all configuration to user
exec_queue and the fence handling is simplified.

v2:
(Matt)
- set job->ggtt to true if create job is successful
- unlock vm on job error

(Ashutosh)
- don't wait on job submission
- use kernel exec queue where possible

v3:
(Ashutosh)
- Fix checkpatch issues
- Remove extra spaces/new-lines
- Add Fixes: and Cc: tags
- Reset context control bit when OA stream is closed
- Submit all config via MI_LOAD_REGISTER_IMMEDIATE

(Umesh)
- Update commit message for v3 experiment
- Squash patches for easier port to stable

v4:
(Ashutosh)
- No need to pass q to xe_oa_submit_bb
- Do not support exec queues with width > 1
- Fix disabling of CTX_CTRL_OAC_CONTEXT_ENABLE

v5:
(Ashutosh)
- Drop reg_lri related comments
- Use XE_OA_SUBMIT_NO_DEPS in xe_oa_load_with_lri

Fixes: 8135f1c09dd2 ("drm/xe/oa: Don't reset OAC_CONTEXT_ENABLE on OA stream close")
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com> # commit 1
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241220171919.571528-2-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/xe/xe_oa.c              | 136 ++++++++----------------
 drivers/gpu/drm/xe/xe_ring_ops.c        |   5 +-
 drivers/gpu/drm/xe/xe_sched_job_types.h |   2 +
 3 files changed, 51 insertions(+), 92 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index ae94490b0eac..9add60097ab5 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -74,12 +74,6 @@ struct xe_oa_config {
 	struct rcu_head rcu;
 };
 
-struct flex {
-	struct xe_reg reg;
-	u32 offset;
-	u32 value;
-};
-
 struct xe_oa_open_param {
 	struct xe_file *xef;
 	u32 oa_unit_id;
@@ -605,19 +599,38 @@ static __poll_t xe_oa_poll(struct file *file, poll_table *wait)
 	return ret;
 }
 
+static void xe_oa_lock_vma(struct xe_exec_queue *q)
+{
+	if (q->vm) {
+		down_read(&q->vm->lock);
+		xe_vm_lock(q->vm, false);
+	}
+}
+
+static void xe_oa_unlock_vma(struct xe_exec_queue *q)
+{
+	if (q->vm) {
+		xe_vm_unlock(q->vm);
+		up_read(&q->vm->lock);
+	}
+}
+
 static struct dma_fence *xe_oa_submit_bb(struct xe_oa_stream *stream, enum xe_oa_submit_deps deps,
 					 struct xe_bb *bb)
 {
+	struct xe_exec_queue *q = stream->exec_q ?: stream->k_exec_q;
 	struct xe_sched_job *job;
 	struct dma_fence *fence;
 	int err = 0;
 
-	/* Kernel configuration is issued on stream->k_exec_q, not stream->exec_q */
-	job = xe_bb_create_job(stream->k_exec_q, bb);
+	xe_oa_lock_vma(q);
+
+	job = xe_bb_create_job(q, bb);
 	if (IS_ERR(job)) {
 		err = PTR_ERR(job);
 		goto exit;
 	}
+	job->ggtt = true;
 
 	if (deps == XE_OA_SUBMIT_ADD_DEPS) {
 		for (int i = 0; i < stream->num_syncs && !err; i++)
@@ -632,10 +645,13 @@ static struct dma_fence *xe_oa_submit_bb(struct xe_oa_stream *stream, enum xe_oa
 	fence = dma_fence_get(&job->drm.s_fence->finished);
 	xe_sched_job_push(job);
 
+	xe_oa_unlock_vma(q);
+
 	return fence;
 err_put_job:
 	xe_sched_job_put(job);
 exit:
+	xe_oa_unlock_vma(q);
 	return ERR_PTR(err);
 }
 
@@ -684,65 +700,19 @@ static void xe_oa_free_configs(struct xe_oa_stream *stream)
 	dma_fence_put(stream->last_fence);
 }
 
-static void xe_oa_store_flex(struct xe_oa_stream *stream, struct xe_lrc *lrc,
-			     struct xe_bb *bb, const struct flex *flex, u32 count)
-{
-	u32 offset = xe_bo_ggtt_addr(lrc->bo);
-
-	do {
-		bb->cs[bb->len++] = MI_STORE_DATA_IMM | MI_SDI_GGTT |
-				    MI_FORCE_WRITE_COMPLETION_CHECK |
-				    MI_SDI_NUM_DW(1);
-		bb->cs[bb->len++] = offset + flex->offset * sizeof(u32);
-		bb->cs[bb->len++] = 0;
-		bb->cs[bb->len++] = flex->value;
-
-	} while (flex++, --count);
-}
-
-static int xe_oa_modify_ctx_image(struct xe_oa_stream *stream, struct xe_lrc *lrc,
-				  const struct flex *flex, u32 count)
-{
-	struct dma_fence *fence;
-	struct xe_bb *bb;
-	int err;
-
-	bb = xe_bb_new(stream->gt, 4 * count, false);
-	if (IS_ERR(bb)) {
-		err = PTR_ERR(bb);
-		goto exit;
-	}
-
-	xe_oa_store_flex(stream, lrc, bb, flex, count);
-
-	fence = xe_oa_submit_bb(stream, XE_OA_SUBMIT_NO_DEPS, bb);
-	if (IS_ERR(fence)) {
-		err = PTR_ERR(fence);
-		goto free_bb;
-	}
-	xe_bb_free(bb, fence);
-	dma_fence_put(fence);
-
-	return 0;
-free_bb:
-	xe_bb_free(bb, NULL);
-exit:
-	return err;
-}
-
-static int xe_oa_load_with_lri(struct xe_oa_stream *stream, struct xe_oa_reg *reg_lri)
+static int xe_oa_load_with_lri(struct xe_oa_stream *stream, struct xe_oa_reg *reg_lri, u32 count)
 {
 	struct dma_fence *fence;
 	struct xe_bb *bb;
 	int err;
 
-	bb = xe_bb_new(stream->gt, 3, false);
+	bb = xe_bb_new(stream->gt, 2 * count + 1, false);
 	if (IS_ERR(bb)) {
 		err = PTR_ERR(bb);
 		goto exit;
 	}
 
-	write_cs_mi_lri(bb, reg_lri, 1);
+	write_cs_mi_lri(bb, reg_lri, count);
 
 	fence = xe_oa_submit_bb(stream, XE_OA_SUBMIT_NO_DEPS, bb);
 	if (IS_ERR(fence)) {
@@ -762,71 +732,55 @@ exit:
 static int xe_oa_configure_oar_context(struct xe_oa_stream *stream, bool enable)
 {
 	const struct xe_oa_format *format = stream->oa_buffer.format;
-	struct xe_lrc *lrc = stream->exec_q->lrc[0];
-	u32 regs_offset = xe_lrc_regs_offset(lrc) / sizeof(u32);
 	u32 oacontrol = __format_to_oactrl(format, OAR_OACONTROL_COUNTER_SEL_MASK) |
 		(enable ? OAR_OACONTROL_COUNTER_ENABLE : 0);
 
-	struct flex regs_context[] = {
+	struct xe_oa_reg reg_lri[] = {
 		{
 			OACTXCONTROL(stream->hwe->mmio_base),
-			stream->oa->ctx_oactxctrl_offset[stream->hwe->class] + 1,
 			enable ? OA_COUNTER_RESUME : 0,
 		},
+		{
+			OAR_OACONTROL,
+			oacontrol,
+		},
 		{
 			RING_CONTEXT_CONTROL(stream->hwe->mmio_base),
-			regs_offset + CTX_CONTEXT_CONTROL,
-			_MASKED_BIT_ENABLE(CTX_CTRL_OAC_CONTEXT_ENABLE),
+			_MASKED_FIELD(CTX_CTRL_OAC_CONTEXT_ENABLE,
+				      enable ? CTX_CTRL_OAC_CONTEXT_ENABLE : 0)
 		},
 	};
-	struct xe_oa_reg reg_lri = { OAR_OACONTROL, oacontrol };
-	int err;
-
-	/* Modify stream hwe context image with regs_context */
-	err = xe_oa_modify_ctx_image(stream, stream->exec_q->lrc[0],
-				     regs_context, ARRAY_SIZE(regs_context));
-	if (err)
-		return err;
 
-	/* Apply reg_lri using LRI */
-	return xe_oa_load_with_lri(stream, &reg_lri);
+	return xe_oa_load_with_lri(stream, reg_lri, ARRAY_SIZE(reg_lri));
 }
 
 static int xe_oa_configure_oac_context(struct xe_oa_stream *stream, bool enable)
 {
 	const struct xe_oa_format *format = stream->oa_buffer.format;
-	struct xe_lrc *lrc = stream->exec_q->lrc[0];
-	u32 regs_offset = xe_lrc_regs_offset(lrc) / sizeof(u32);
 	u32 oacontrol = __format_to_oactrl(format, OAR_OACONTROL_COUNTER_SEL_MASK) |
 		(enable ? OAR_OACONTROL_COUNTER_ENABLE : 0);
-	struct flex regs_context[] = {
+	struct xe_oa_reg reg_lri[] = {
 		{
 			OACTXCONTROL(stream->hwe->mmio_base),
-			stream->oa->ctx_oactxctrl_offset[stream->hwe->class] + 1,
 			enable ? OA_COUNTER_RESUME : 0,
 		},
+		{
+			OAC_OACONTROL,
+			oacontrol
+		},
 		{
 			RING_CONTEXT_CONTROL(stream->hwe->mmio_base),
-			regs_offset + CTX_CONTEXT_CONTROL,
-			_MASKED_BIT_ENABLE(CTX_CTRL_OAC_CONTEXT_ENABLE) |
+			_MASKED_FIELD(CTX_CTRL_OAC_CONTEXT_ENABLE,
+				      enable ? CTX_CTRL_OAC_CONTEXT_ENABLE : 0) |
 			_MASKED_FIELD(CTX_CTRL_RUN_ALONE, enable ? CTX_CTRL_RUN_ALONE : 0),
 		},
 	};
-	struct xe_oa_reg reg_lri = { OAC_OACONTROL, oacontrol };
-	int err;
 
 	/* Set ccs select to enable programming of OAC_OACONTROL */
 	xe_mmio_write32(&stream->gt->mmio, __oa_regs(stream)->oa_ctrl,
 			__oa_ccs_select(stream));
 
-	/* Modify stream hwe context image with regs_context */
-	err = xe_oa_modify_ctx_image(stream, stream->exec_q->lrc[0],
-				     regs_context, ARRAY_SIZE(regs_context));
-	if (err)
-		return err;
-
-	/* Apply reg_lri using LRI */
-	return xe_oa_load_with_lri(stream, &reg_lri);
+	return xe_oa_load_with_lri(stream, reg_lri, ARRAY_SIZE(reg_lri));
 }
 
 static int xe_oa_configure_oa_context(struct xe_oa_stream *stream, bool enable)
@@ -2110,8 +2064,8 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 		if (XE_IOCTL_DBG(oa->xe, !param.exec_q))
 			return -ENOENT;
 
-		if (param.exec_q->width > 1)
-			drm_dbg(&oa->xe->drm, "exec_q->width > 1, programming only exec_q->lrc[0]\n");
+		if (XE_IOCTL_DBG(oa->xe, param.exec_q->width > 1))
+			return -EOPNOTSUPP;
 	}
 
 	/*
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index 3a75a08b6be9..c8ab37fa0d19 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -223,7 +223,10 @@ static int emit_pipe_imm_ggtt(u32 addr, u32 value, bool stall_only, u32 *dw,
 
 static u32 get_ppgtt_flag(struct xe_sched_job *job)
 {
-	return job->q->vm ? BIT(8) : 0;
+	if (job->q->vm && !job->ggtt)
+		return BIT(8);
+
+	return 0;
 }
 
 static int emit_copy_timestamp(struct xe_lrc *lrc, u32 *dw, int i)
diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h
index f13f333f00be..d942b20a9f29 100644
--- a/drivers/gpu/drm/xe/xe_sched_job_types.h
+++ b/drivers/gpu/drm/xe/xe_sched_job_types.h
@@ -56,6 +56,8 @@ struct xe_sched_job {
 	u32 migrate_flush_flags;
 	/** @ring_ops_flush_tlb: The ring ops need to flush TLB before payload. */
 	bool ring_ops_flush_tlb;
+	/** @ggtt: mapped in ggtt. */
+	bool ggtt;
 	/** @ptrs: per instance pointers. */
 	struct xe_job_ptrs ptrs[];
 };
-- 
2.51.0


From fba0f039affdd0c8767f24e41d5dbef49addea78 Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Fri, 20 Dec 2024 09:19:19 -0800
Subject: [PATCH 05/16] xe/oa: Drop the unused logic to parse context image

Now that all register configurations are using MI_LOAD_REGISTER_IMM,
drop the logic to parse context image for offset.

v2: Remove unused lrc headers (Ashutosh)

Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Signed-off-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241220171919.571528-3-umesh.nerlige.ramappa@intel.com
---
 drivers/gpu/drm/xe/xe_oa.c       | 88 --------------------------------
 drivers/gpu/drm/xe/xe_oa_types.h |  3 --
 2 files changed, 91 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index 9add60097ab5..4e00a77289c5 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -16,7 +16,6 @@
 #include "instructions/xe_mi_commands.h"
 #include "regs/xe_engine_regs.h"
 #include "regs/xe_gt_regs.h"
-#include "regs/xe_lrc_layout.h"
 #include "regs/xe_oa_regs.h"
 #include "xe_assert.h"
 #include "xe_bb.h"
@@ -28,7 +27,6 @@
 #include "xe_gt_mcr.h"
 #include "xe_gt_printk.h"
 #include "xe_guc_pc.h"
-#include "xe_lrc.h"
 #include "xe_macros.h"
 #include "xe_mmio.h"
 #include "xe_oa.h"
@@ -1673,81 +1671,6 @@ static const struct file_operations xe_oa_fops = {
 	.mmap		= xe_oa_mmap,
 };
 
-static bool engine_supports_mi_query(struct xe_hw_engine *hwe)
-{
-	return hwe->class == XE_ENGINE_CLASS_RENDER ||
-		hwe->class == XE_ENGINE_CLASS_COMPUTE;
-}
-
-static bool xe_oa_find_reg_in_lri(u32 *state, u32 reg, u32 *offset, u32 end)
-{
-	u32 idx = *offset;
-	u32 len = min(MI_LRI_LEN(state[idx]) + idx, end);
-	bool found = false;
-
-	idx++;
-	for (; idx < len; idx += 2) {
-		if (state[idx] == reg) {
-			found = true;
-			break;
-		}
-	}
-
-	*offset = idx;
-	return found;
-}
-
-#define IS_MI_LRI_CMD(x) (REG_FIELD_GET(MI_OPCODE, (x)) == \
-			  REG_FIELD_GET(MI_OPCODE, MI_LOAD_REGISTER_IMM))
-
-static u32 xe_oa_context_image_offset(struct xe_oa_stream *stream, u32 reg)
-{
-	struct xe_lrc *lrc = stream->exec_q->lrc[0];
-	u32 len = (xe_gt_lrc_size(stream->gt, stream->hwe->class) +
-		   lrc->ring.size) / sizeof(u32);
-	u32 offset = xe_lrc_regs_offset(lrc) / sizeof(u32);
-	u32 *state = (u32 *)lrc->bo->vmap.vaddr;
-
-	if (drm_WARN_ON(&stream->oa->xe->drm, !state))
-		return U32_MAX;
-
-	for (; offset < len; ) {
-		if (IS_MI_LRI_CMD(state[offset])) {
-			/*
-			 * We expect reg-value pairs in MI_LRI command, so
-			 * MI_LRI_LEN() should be even
-			 */
-			drm_WARN_ON(&stream->oa->xe->drm,
-				    MI_LRI_LEN(state[offset]) & 0x1);
-
-			if (xe_oa_find_reg_in_lri(state, reg, &offset, len))
-				break;
-		} else {
-			offset++;
-		}
-	}
-
-	return offset < len ? offset : U32_MAX;
-}
-
-static int xe_oa_set_ctx_ctrl_offset(struct xe_oa_stream *stream)
-{
-	struct xe_reg reg = OACTXCONTROL(stream->hwe->mmio_base);
-	u32 offset = stream->oa->ctx_oactxctrl_offset[stream->hwe->class];
-
-	/* Do this only once. Failure is stored as offset of U32_MAX */
-	if (offset)
-		goto exit;
-
-	offset = xe_oa_context_image_offset(stream, reg.addr);
-	stream->oa->ctx_oactxctrl_offset[stream->hwe->class] = offset;
-
-	drm_dbg(&stream->oa->xe->drm, "%s oa ctx control at 0x%08x dword offset\n",
-		stream->hwe->name, offset);
-exit:
-	return offset && offset != U32_MAX ? 0 : -ENODEV;
-}
-
 static int xe_oa_stream_init(struct xe_oa_stream *stream,
 			     struct xe_oa_open_param *param)
 {
@@ -1785,17 +1708,6 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream,
 	else
 		stream->oa_buffer.circ_size = param->oa_buffer_size;
 
-	if (stream->exec_q && engine_supports_mi_query(stream->hwe)) {
-		/* If we don't find the context offset, just return error */
-		ret = xe_oa_set_ctx_ctrl_offset(stream);
-		if (ret) {
-			drm_err(&stream->oa->xe->drm,
-				"xe_oa_set_ctx_ctrl_offset failed for %s\n",
-				stream->hwe->name);
-			goto exit;
-		}
-	}
-
 	stream->oa_config = xe_oa_get_oa_config(stream->oa, param->metric_set);
 	if (!stream->oa_config) {
 		drm_dbg(&stream->oa->xe->drm, "Invalid OA config id=%i\n", param->metric_set);
diff --git a/drivers/gpu/drm/xe/xe_oa_types.h b/drivers/gpu/drm/xe/xe_oa_types.h
index 2dcd3b9562e9..52e33c37d5ee 100644
--- a/drivers/gpu/drm/xe/xe_oa_types.h
+++ b/drivers/gpu/drm/xe/xe_oa_types.h
@@ -138,9 +138,6 @@ struct xe_oa {
 	/** @metrics_idr: List of dynamic configurations (struct xe_oa_config) */
 	struct idr metrics_idr;
 
-	/** @ctx_oactxctrl_offset: offset of OACTXCONTROL register in context image */
-	u32 ctx_oactxctrl_offset[XE_ENGINE_CLASS_MAX];
-
 	/** @oa_formats: tracks all OA formats across platforms */
 	const struct xe_oa_format *oa_formats;
 
-- 
2.51.0


From 88fca61ba5e2ecd0552b9dea2500a16da12d0106 Mon Sep 17 00:00:00 2001
From: =?utf8?q?Jos=C3=A9=20Roberto=20de=20Souza?= <jose.souza@intel.com>
Date: Fri, 27 Dec 2024 10:32:19 -0800
Subject: [PATCH 06/16] Revert "drm/xe: Force write completion of
 MI_STORE_DATA_IMM"
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

This reverts commit 1460bb1fef9ccf7390af0d74a15252442fd6effd.

In all places the MI_STORE_DATA_IMM are not followed by a read of
the same memory address in the same batch buffer and the posted writes
are flushed with PIPE_CONTROL or MI_FLUSH_DW in xe_ring_ops.c functions
so there is no need to set this register.

Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Ashutosh Dixit <ashutosh.dixit@intel.com>
Fixes: 1460bb1fef9c ("drm/xe: Force write completion of MI_STORE_DATA_IMM")
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241227183230.101334-1-jose.souza@intel.com
---
 drivers/gpu/drm/xe/instructions/xe_mi_commands.h | 13 ++++++-------
 drivers/gpu/drm/xe/xe_migrate.c                  | 11 +++--------
 drivers/gpu/drm/xe/xe_ring_ops.c                 |  6 ++----
 3 files changed, 11 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
index f4ee910f0943..10ec2920d31b 100644
--- a/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
+++ b/drivers/gpu/drm/xe/instructions/xe_mi_commands.h
@@ -33,13 +33,12 @@
 #define MI_TOPOLOGY_FILTER		__MI_INSTR(0xD)
 #define MI_FORCE_WAKEUP			__MI_INSTR(0x1D)
 
-#define MI_STORE_DATA_IMM			__MI_INSTR(0x20)
-#define   MI_SDI_GGTT				REG_BIT(22)
-#define   MI_FORCE_WRITE_COMPLETION_CHECK	REG_BIT(10)
-#define   MI_SDI_LEN_DW				GENMASK(9, 0)
-#define   MI_SDI_NUM_DW(x)			REG_FIELD_PREP(MI_SDI_LEN_DW, (x) + 3 - 2)
-#define   MI_SDI_NUM_QW(x)			(REG_FIELD_PREP(MI_SDI_LEN_DW, 2 * (x) + 3 - 2) | \
-						 REG_BIT(21))
+#define MI_STORE_DATA_IMM		__MI_INSTR(0x20)
+#define   MI_SDI_GGTT			REG_BIT(22)
+#define   MI_SDI_LEN_DW			GENMASK(9, 0)
+#define   MI_SDI_NUM_DW(x)		REG_FIELD_PREP(MI_SDI_LEN_DW, (x) + 3 - 2)
+#define   MI_SDI_NUM_QW(x)		(REG_FIELD_PREP(MI_SDI_LEN_DW, 2 * (x) + 3 - 2) | \
+					 REG_BIT(21))
 
 #define MI_LOAD_REGISTER_IMM		__MI_INSTR(0x22)
 #define   MI_LRI_LRM_CS_MMIO		REG_BIT(19)
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 8b32fad67878..1b97d90aadda 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -581,9 +581,7 @@ static void emit_pte(struct xe_migrate *m,
 	while (ptes) {
 		u32 chunk = min(MAX_PTE_PER_SDI, ptes);
 
-		bb->cs[bb->len++] = MI_STORE_DATA_IMM |
-				    MI_FORCE_WRITE_COMPLETION_CHECK |
-				    MI_SDI_NUM_QW(chunk);
+		bb->cs[bb->len++] = MI_STORE_DATA_IMM | MI_SDI_NUM_QW(chunk);
 		bb->cs[bb->len++] = ofs;
 		bb->cs[bb->len++] = 0;
 
@@ -1225,9 +1223,7 @@ static void write_pgtable(struct xe_tile *tile, struct xe_bb *bb, u64 ppgtt_ofs,
 		if (!(bb->len & 1))
 			bb->cs[bb->len++] = MI_NOOP;
 
-		bb->cs[bb->len++] = MI_STORE_DATA_IMM |
-				    MI_FORCE_WRITE_COMPLETION_CHECK |
-				    MI_SDI_NUM_QW(chunk);
+		bb->cs[bb->len++] = MI_STORE_DATA_IMM | MI_SDI_NUM_QW(chunk);
 		bb->cs[bb->len++] = lower_32_bits(addr);
 		bb->cs[bb->len++] = upper_32_bits(addr);
 		if (pt_op->bind)
@@ -1392,8 +1388,7 @@ __xe_migrate_update_pgtables(struct xe_migrate *m,
 			u32 idx = 0;
 
 			bb->cs[bb->len++] = MI_STORE_DATA_IMM |
-					    MI_FORCE_WRITE_COMPLETION_CHECK |
-					    MI_SDI_NUM_QW(chunk);
+				MI_SDI_NUM_QW(chunk);
 			bb->cs[bb->len++] = ofs;
 			bb->cs[bb->len++] = 0; /* upper_32_bits */
 
diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
index c8ab37fa0d19..9f327f27c072 100644
--- a/drivers/gpu/drm/xe/xe_ring_ops.c
+++ b/drivers/gpu/drm/xe/xe_ring_ops.c
@@ -72,8 +72,7 @@ static int emit_user_interrupt(u32 *dw, int i)
 
 static int emit_store_imm_ggtt(u32 addr, u32 value, u32 *dw, int i)
 {
-	dw[i++] = MI_STORE_DATA_IMM | MI_SDI_GGTT |
-		  MI_FORCE_WRITE_COMPLETION_CHECK | MI_SDI_NUM_DW(1);
+	dw[i++] = MI_STORE_DATA_IMM | MI_SDI_GGTT | MI_SDI_NUM_DW(1);
 	dw[i++] = addr;
 	dw[i++] = 0;
 	dw[i++] = value;
@@ -163,8 +162,7 @@ static int emit_pipe_invalidate(u32 mask_flags, bool invalidate_tlb, u32 *dw,
 static int emit_store_imm_ppgtt_posted(u64 addr, u64 value,
 				       u32 *dw, int i)
 {
-	dw[i++] = MI_STORE_DATA_IMM | MI_FORCE_WRITE_COMPLETION_CHECK |
-		  MI_SDI_NUM_QW(1);
+	dw[i++] = MI_STORE_DATA_IMM | MI_SDI_NUM_QW(1);
 	dw[i++] = lower_32_bits(addr);
 	dw[i++] = upper_32_bits(addr);
 	dw[i++] = lower_32_bits(value);
-- 
2.51.0


From 5001ef3af8f2c972d6fd9c5221a8457556f8bea6 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 2 Jan 2025 16:11:10 -0800
Subject: [PATCH 07/16] drm/xe: Fix tlb invalidation when wedging

If GuC fails to load, the driver wedges, but in the process it tries to
do stuff that may not be initialized yet. This moves the
xe_gt_tlb_invalidation_init() to be done earlier: as its own doc says,
it's a software-only initialization and should had been named with the
_early() suffix.

Move it to be called by xe_gt_init_early(), so the locks and seqno are
initialized, avoiding a NULL ptr deref when wedging:

	xe 0000:03:00.0: [drm] *ERROR* GT0: load failed: status: Reset = 0, BootROM = 0x50, UKernel = 0x00, MIA = 0x00, Auth = 0x01
	xe 0000:03:00.0: [drm] *ERROR* GT0: firmware signature verification failed
	xe 0000:03:00.0: [drm] *ERROR* CRITICAL: Xe has declared device 0000:03:00.0 as wedged.
	...
	BUG: kernel NULL pointer dereference, address: 0000000000000000
	#PF: supervisor read access in kernel mode
	#PF: error_code(0x0000) - not-present page
	PGD 0 P4D 0
	Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
	CPU: 9 UID: 0 PID: 3908 Comm: modprobe Tainted: G     U  W          6.13.0-rc4-xe+ #3
	Tainted: [U]=USER, [W]=WARN
	Hardware name: Intel Corporation Alder Lake Client Platform/AlderLake-S ADP-S DDR5 UDIMM CRB, BIOS ADLSFWI1.R00.3275.A00.2207010640 07/01/2022
	RIP: 0010:xe_gt_tlb_invalidation_reset+0x75/0x110 [xe]

This can be easily triggered by poking the GuC binary to force a
signature failure. There will still be an extra message,

	xe 0000:03:00.0: [drm] *ERROR* GT0: GuC mmio request 0x4100: no reply 0x4100

but that's better than a NULL ptr deref.

Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/3956
Fixes: 7dbe8af13c18 ("drm/xe: Wedge the entire device")
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250103001111.331684-2-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_gt.c                  | 8 ++++----
 drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 4 ++--
 drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h | 3 ++-
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 41ab7fbebc19..26e64530ada2 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -387,6 +387,10 @@ int xe_gt_init_early(struct xe_gt *gt)
 	xe_force_wake_init_gt(gt, gt_to_fw(gt));
 	spin_lock_init(&gt->global_invl_lock);
 
+	err = xe_gt_tlb_invalidation_init_early(gt);
+	if (err)
+		return err;
+
 	return 0;
 }
 
@@ -588,10 +592,6 @@ int xe_gt_init(struct xe_gt *gt)
 		xe_hw_fence_irq_init(&gt->fence_irq[i]);
 	}
 
-	err = xe_gt_tlb_invalidation_init(gt);
-	if (err)
-		return err;
-
 	err = xe_gt_pagefault_init(gt);
 	if (err)
 		return err;
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 665927b80e9e..257b500e1703 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -106,7 +106,7 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
 }
 
 /**
- * xe_gt_tlb_invalidation_init - Initialize GT TLB invalidation state
+ * xe_gt_tlb_invalidation_init_early - Initialize GT TLB invalidation state
  * @gt: graphics tile
  *
  * Initialize GT TLB invalidation state, purely software initialization, should
@@ -114,7 +114,7 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
  *
  * Return: 0 on success, negative error code on error.
  */
-int xe_gt_tlb_invalidation_init(struct xe_gt *gt)
+int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt)
 {
 	gt->tlb_invalidation.seqno = 1;
 	INIT_LIST_HEAD(&gt->tlb_invalidation.pending_fences);
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
index 00b1c6c01e8d..672acfcdf0d7 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.h
@@ -14,7 +14,8 @@ struct xe_gt;
 struct xe_guc;
 struct xe_vma;
 
-int xe_gt_tlb_invalidation_init(struct xe_gt *gt);
+int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt);
+
 void xe_gt_tlb_invalidation_reset(struct xe_gt *gt);
 int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt);
 int xe_gt_tlb_invalidation_vma(struct xe_gt *gt,
-- 
2.51.0


From 6acea03f98f5d0028cae1d9d4c60914bfdfb6d27 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 2 Jan 2025 16:11:11 -0800
Subject: [PATCH 08/16] drm/xe: Remove "graphics tile" from kernel doc

Avoid using "graphics tile" to refer to GT since it's ambiguous: it's
**part** of a tile and there's also "media gt". In several places it's
documented as "GT structure", so just follow it.

Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250103001111.331684-3-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
---
 drivers/gpu/drm/xe/xe_exec_queue_types.h    |  2 +-
 drivers/gpu/drm/xe/xe_gt_stats.c            |  4 ++--
 drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c | 12 ++++++------
 drivers/gpu/drm/xe/xe_hw_engine_types.h     |  2 +-
 drivers/gpu/drm/xe/xe_hw_fence_types.h      |  2 +-
 5 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index eec8f9935a58..5af5419cec7a 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -41,7 +41,7 @@ struct xe_exec_queue {
 	/** @xef: Back pointer to xe file if this is user created exec queue */
 	struct xe_file *xef;
 
-	/** @gt: graphics tile this exec queue can submit to */
+	/** @gt: GT structure this exec queue can submit to */
 	struct xe_gt *gt;
 	/**
 	 * @hwe: A hardware of the same class. May (physical engine) or may not
diff --git a/drivers/gpu/drm/xe/xe_gt_stats.c b/drivers/gpu/drm/xe/xe_gt_stats.c
index c7364a5aef8f..7a6c1d808e41 100644
--- a/drivers/gpu/drm/xe/xe_gt_stats.c
+++ b/drivers/gpu/drm/xe/xe_gt_stats.c
@@ -12,7 +12,7 @@
 
 /**
  * xe_gt_stats_incr - Increments the specified stats counter
- * @gt: graphics tile
+ * @gt: GT structure
  * @id: xe_gt_stats_id type id that needs to be incremented
  * @incr: value to be incremented with
  *
@@ -32,7 +32,7 @@ static const char *const stat_description[__XE_GT_STATS_NUM_IDS] = {
 
 /**
  * xe_gt_stats_print_info - Print the GT stats
- * @gt: graphics tile
+ * @gt: GT structure
  * @p: drm_printer where it will be printed out.
  *
  * This prints out all the available GT stats.
diff --git a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
index 257b500e1703..0a93831c0a02 100644
--- a/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
+++ b/drivers/gpu/drm/xe/xe_gt_tlb_invalidation.c
@@ -107,7 +107,7 @@ static void xe_gt_tlb_fence_timeout(struct work_struct *work)
 
 /**
  * xe_gt_tlb_invalidation_init_early - Initialize GT TLB invalidation state
- * @gt: graphics tile
+ * @gt: GT structure
  *
  * Initialize GT TLB invalidation state, purely software initialization, should
  * be called once during driver load.
@@ -128,7 +128,7 @@ int xe_gt_tlb_invalidation_init_early(struct xe_gt *gt)
 
 /**
  * xe_gt_tlb_invalidation_reset - Initialize GT TLB invalidation reset
- * @gt: graphics tile
+ * @gt: GT structure
  *
  * Signal any pending invalidation fences, should be called during a GT reset
  */
@@ -244,7 +244,7 @@ static int send_tlb_invalidation(struct xe_guc *guc,
 
 /**
  * xe_gt_tlb_invalidation_guc - Issue a TLB invalidation on this GT for the GuC
- * @gt: graphics tile
+ * @gt: GT structure
  * @fence: invalidation fence which will be signal on TLB invalidation
  * completion
  *
@@ -277,7 +277,7 @@ static int xe_gt_tlb_invalidation_guc(struct xe_gt *gt,
 
 /**
  * xe_gt_tlb_invalidation_ggtt - Issue a TLB invalidation on this GT for the GGTT
- * @gt: graphics tile
+ * @gt: GT structure
  *
  * Issue a TLB invalidation for the GGTT. Completion of TLB invalidation is
  * synchronous.
@@ -326,7 +326,7 @@ int xe_gt_tlb_invalidation_ggtt(struct xe_gt *gt)
  * xe_gt_tlb_invalidation_range - Issue a TLB invalidation on this GT for an
  * address range
  *
- * @gt: graphics tile
+ * @gt: GT structure
  * @fence: invalidation fence which will be signal on TLB invalidation
  * completion
  * @start: start address
@@ -412,7 +412,7 @@ int xe_gt_tlb_invalidation_range(struct xe_gt *gt,
 
 /**
  * xe_gt_tlb_invalidation_vma - Issue a TLB invalidation on this GT for a VMA
- * @gt: graphics tile
+ * @gt: GT structure
  * @fence: invalidation fence which will be signal on TLB invalidation
  * completion, can be NULL
  * @vma: VMA to invalidate
diff --git a/drivers/gpu/drm/xe/xe_hw_engine_types.h b/drivers/gpu/drm/xe/xe_hw_engine_types.h
index e14bee95e364..e4191a7a2c31 100644
--- a/drivers/gpu/drm/xe/xe_hw_engine_types.h
+++ b/drivers/gpu/drm/xe/xe_hw_engine_types.h
@@ -106,7 +106,7 @@ struct xe_hw_engine_class_intf {
  * Contains all the hardware engine state for physical instances.
  */
 struct xe_hw_engine {
-	/** @gt: graphics tile this hw engine belongs to */
+	/** @gt: GT structure this hw engine belongs to */
 	struct xe_gt *gt;
 	/** @name: name of this hw engine */
 	const char *name;
diff --git a/drivers/gpu/drm/xe/xe_hw_fence_types.h b/drivers/gpu/drm/xe/xe_hw_fence_types.h
index 364a61f4bfda..58a8d09afe5c 100644
--- a/drivers/gpu/drm/xe/xe_hw_fence_types.h
+++ b/drivers/gpu/drm/xe/xe_hw_fence_types.h
@@ -41,7 +41,7 @@ struct xe_hw_fence_irq {
  * to a xe_hw_fence_irq, maintains serial seqno.
  */
 struct xe_hw_fence_ctx {
-	/** @gt: graphics tile of hardware fence context */
+	/** @gt: GT structure of hardware fence context */
 	struct xe_gt *gt;
 	/** @irq: fence irq handler */
 	struct xe_hw_fence_irq *irq;
-- 
2.51.0


From 40fbc59e7c6d48d406274433601124d9d495090a Mon Sep 17 00:00:00 2001
From: Jakub Kolakowski <jakub1.kolakowski@intel.com>
Date: Wed, 11 Dec 2024 07:42:09 +0100
Subject: [PATCH 09/16] drm/xe/vf: Don't check has flat ccs in bios on VF
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

Don't check for flat ccs from VF-level as VF does not have direct
access to the register.

If the BIOS disables FlatCCS support (a use-case that will nearly never
be used) and the has_flat_ccs flag is set, there shouldn't be
any functional impact. The hardware will drop writes to the CCS region,
and reads from the CCS region will always return 0.
For the native case, the flag is disabled if the BIOS disables
it to avoid unnecessary overhead in buffer object (BO) creation
and migration.

Signed-off-by: Jakub Kolakowski <jakub1.kolakowski@intel.com>
Suggested-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Adam Miszczak <adam.miszczak@linux.intel.com>
Cc: Jakub Kolakowski <jakub1.kolakowski@intel.com>
Cc: Lukasz Laguna <lukasz.laguna@intel.com>
Cc: Marcin Bernatowicz <marcin.bernatowicz@linux.intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Cc: Narasimha C V <narasimha.c.v@intel.com>
Cc: Piotr Piorkowski <piotr.piorkowski@intel.com>
Cc: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Cc: Tomasz Lis <tomasz.lis@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Marcin Bernatowicz <marcin.bernatowicz@linux.intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241211064211.781820-2-marcin.bernatowicz@linux.intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/xe/xe_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index 7f021ec5f8e7..bb627247c9c8 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -607,7 +607,7 @@ static int probe_has_flat_ccs(struct xe_device *xe)
 	u32 reg;
 
 	/* Always enabled/disabled, no runtime check to do */
-	if (GRAPHICS_VER(xe) < 20 || !xe->info.has_flat_ccs)
+	if (GRAPHICS_VER(xe) < 20 || !xe->info.has_flat_ccs || IS_SRIOV_VF(xe))
 		return 0;
 
 	gt = xe_root_mmio_gt(xe);
-- 
2.51.0


From c2e52eb73d9914d8e1bebfe98a9e1991d63c12d0 Mon Sep 17 00:00:00 2001
From: Marcin Bernatowicz <marcin.bernatowicz@linux.intel.com>
Date: Wed, 11 Dec 2024 07:42:10 +0100
Subject: [PATCH 10/16] drm/xe/rtp: Add match helper to omit SR-IOV VF device

Add a match helper that allows the application of a workaround
when the device is not an SR-IOV VF (Virtual Function) device.

Signed-off-by: Marcin Bernatowicz <marcin.bernatowicz@linux.intel.com>
Cc: Adam Miszczak <adam.miszczak@linux.intel.com>
Cc: Jakub Kolakowski <jakub1.kolakowski@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Lukasz Laguna <lukasz.laguna@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Cc: Narasimha C V <narasimha.c.v@intel.com>
Cc: Piotr Piorkowski <piotr.piorkowski@intel.com>
Cc: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Cc: Tomasz Lis <tomasz.lis@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241211064211.781820-3-marcin.bernatowicz@linux.intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/xe/xe_rtp.c |  5 +++++
 drivers/gpu/drm/xe/xe_rtp.h | 11 +++++++++++
 2 files changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_rtp.c b/drivers/gpu/drm/xe/xe_rtp.c
index b13d4d62f0b1..7a1c78fdfc92 100644
--- a/drivers/gpu/drm/xe/xe_rtp.c
+++ b/drivers/gpu/drm/xe/xe_rtp.c
@@ -340,3 +340,8 @@ bool xe_rtp_match_first_gslice_fused_off(const struct xe_gt *gt,
 	return dss >= dss_per_gslice;
 }
 
+bool xe_rtp_match_not_sriov_vf(const struct xe_gt *gt,
+			       const struct xe_hw_engine *hwe)
+{
+	return !IS_SRIOV_VF(gt_to_xe(gt));
+}
diff --git a/drivers/gpu/drm/xe/xe_rtp.h b/drivers/gpu/drm/xe/xe_rtp.h
index 827d932b6908..7dea10d732d7 100644
--- a/drivers/gpu/drm/xe/xe_rtp.h
+++ b/drivers/gpu/drm/xe/xe_rtp.h
@@ -476,4 +476,15 @@ bool xe_rtp_match_first_render_or_compute(const struct xe_gt *gt,
 bool xe_rtp_match_first_gslice_fused_off(const struct xe_gt *gt,
 					 const struct xe_hw_engine *hwe);
 
+/*
+ * xe_rtp_match_not_sriov_vf - Match when not on SR-IOV VF device
+ *
+ * @gt: GT structure
+ * @hwe: Engine instance
+ *
+ * Returns: true if device is not VF, false otherwise.
+ */
+bool xe_rtp_match_not_sriov_vf(const struct xe_gt *gt,
+			       const struct xe_hw_engine *hwe);
+
 #endif
-- 
2.51.0


From 70b8e6e3226fe2ae514a324ff0c64f074f6f419b Mon Sep 17 00:00:00 2001
From: Marcin Bernatowicz <marcin.bernatowicz@linux.intel.com>
Date: Wed, 11 Dec 2024 07:42:11 +0100
Subject: [PATCH 11/16] drm/xe/vf: Don't apply Wa_22019338487 for VF

Don't use Wa_22019338487 for VF.

Signed-off-by: Marcin Bernatowicz <marcin.bernatowicz@linux.intel.com>
Cc: Adam Miszczak <adam.miszczak@linux.intel.com>
Cc: Jakub Kolakowski <jakub1.kolakowski@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Lukasz Laguna <lukasz.laguna@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Cc: Narasimha C V <narasimha.c.v@intel.com>
Cc: Piotr Piorkowski <piotr.piorkowski@intel.com>
Cc: Satyanarayana K V P <satyanarayana.k.v.p@intel.com>
Cc: Tomasz Lis <tomasz.lis@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241211064211.781820-4-marcin.bernatowicz@linux.intel.com
Signed-off-by: Matt Roper <matthew.d.roper@intel.com>
---
 drivers/gpu/drm/xe/xe_wa_oob.rules | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_wa_oob.rules b/drivers/gpu/drm/xe/xe_wa_oob.rules
index 3ed12a85cc60..40438c3d9b72 100644
--- a/drivers/gpu/drm/xe/xe_wa_oob.rules
+++ b/drivers/gpu/drm/xe/xe_wa_oob.rules
@@ -34,7 +34,7 @@
 		GRAPHICS_VERSION(2004)
 22019338487	MEDIA_VERSION(2000)
 		GRAPHICS_VERSION(2001)
-		MEDIA_VERSION(3000), MEDIA_STEP(A0, B0)
+		MEDIA_VERSION(3000), MEDIA_STEP(A0, B0), FUNC(xe_rtp_match_not_sriov_vf)
 22019338487_display	PLATFORM(LUNARLAKE)
 16023588340	GRAPHICS_VERSION(2001)
 14019789679	GRAPHICS_VERSION(1255)
-- 
2.51.0


From c6aac2fa77a3221f2ed0484bf019030f0749d863 Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Fri, 20 Dec 2024 10:29:36 -0500
Subject: [PATCH 12/16] drm/xe: Introduce the RPa information

RPa is the Achievable frequency, defined by PCODE at runtime
based on multiple running conditions.

v2: Remove RPA_MASK from i915 file

Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Reviewed-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241220152936.623627-1-rodrigo.vivi@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_regs.h    |  4 +++
 drivers/gpu/drm/xe/xe_gt_freq.c      | 15 ++++++++
 drivers/gpu/drm/xe/xe_guc_pc.c       | 53 ++++++++++++++++++++++++++--
 drivers/gpu/drm/xe/xe_guc_pc.h       |  1 +
 drivers/gpu/drm/xe/xe_guc_pc_types.h |  2 ++
 5 files changed, 73 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_regs.h b/drivers/gpu/drm/xe/regs/xe_regs.h
index 3293172b0128..6cf282618836 100644
--- a/drivers/gpu/drm/xe/regs/xe_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_regs.h
@@ -44,12 +44,16 @@
 
 #define MTL_RP_STATE_CAP			XE_REG(0x138000)
 
+#define MTL_GT_RPA_FREQUENCY			XE_REG(0x138008)
 #define MTL_GT_RPE_FREQUENCY			XE_REG(0x13800c)
 
 #define MTL_MEDIAP_STATE_CAP			XE_REG(0x138020)
 #define   MTL_RPN_CAP_MASK			REG_GENMASK(24, 16)
 #define   MTL_RP0_CAP_MASK			REG_GENMASK(8, 0)
 
+#define MTL_MPA_FREQUENCY			XE_REG(0x138028)
+#define   MTL_RPA_MASK				REG_GENMASK(8, 0)
+
 #define MTL_MPE_FREQUENCY			XE_REG(0x13802c)
 #define   MTL_RPE_MASK				REG_GENMASK(8, 0)
 
diff --git a/drivers/gpu/drm/xe/xe_gt_freq.c b/drivers/gpu/drm/xe/xe_gt_freq.c
index 6bd39b2c5003..604bdc7c8173 100644
--- a/drivers/gpu/drm/xe/xe_gt_freq.c
+++ b/drivers/gpu/drm/xe/xe_gt_freq.c
@@ -115,6 +115,20 @@ static ssize_t rpe_freq_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(rpe_freq);
 
+static ssize_t rpa_freq_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct xe_guc_pc *pc = dev_to_pc(dev);
+	u32 freq;
+
+	xe_pm_runtime_get(dev_to_xe(dev));
+	freq = xe_guc_pc_get_rpa_freq(pc);
+	xe_pm_runtime_put(dev_to_xe(dev));
+
+	return sysfs_emit(buf, "%d\n", freq);
+}
+static DEVICE_ATTR_RO(rpa_freq);
+
 static ssize_t rpn_freq_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
@@ -202,6 +216,7 @@ static const struct attribute *freq_attrs[] = {
 	&dev_attr_act_freq.attr,
 	&dev_attr_cur_freq.attr,
 	&dev_attr_rp0_freq.attr,
+	&dev_attr_rpa_freq.attr,
 	&dev_attr_rpe_freq.attr,
 	&dev_attr_rpn_freq.attr,
 	&dev_attr_min_freq.attr,
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index e8b9faeaef64..a6fdd2c062ff 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -38,6 +38,7 @@
 
 #define FREQ_INFO_REC	XE_REG(MCHBAR_MIRROR_BASE_SNB + 0x5ef0)
 #define   RPE_MASK		REG_GENMASK(15, 8)
+#define   RPA_MASK		REG_GENMASK(31, 16)
 
 #define GT_PERF_STATUS		XE_REG(0x1381b4)
 #define   CAGF_MASK	REG_GENMASK(19, 11)
@@ -328,6 +329,19 @@ static int pc_set_max_freq(struct xe_guc_pc *pc, u32 freq)
 				   freq);
 }
 
+static void mtl_update_rpa_value(struct xe_guc_pc *pc)
+{
+	struct xe_gt *gt = pc_to_gt(pc);
+	u32 reg;
+
+	if (xe_gt_is_media_type(gt))
+		reg = xe_mmio_read32(&gt->mmio, MTL_MPA_FREQUENCY);
+	else
+		reg = xe_mmio_read32(&gt->mmio, MTL_GT_RPA_FREQUENCY);
+
+	pc->rpa_freq = decode_freq(REG_FIELD_GET(MTL_RPA_MASK, reg));
+}
+
 static void mtl_update_rpe_value(struct xe_guc_pc *pc)
 {
 	struct xe_gt *gt = pc_to_gt(pc);
@@ -341,6 +355,25 @@ static void mtl_update_rpe_value(struct xe_guc_pc *pc)
 	pc->rpe_freq = decode_freq(REG_FIELD_GET(MTL_RPE_MASK, reg));
 }
 
+static void tgl_update_rpa_value(struct xe_guc_pc *pc)
+{
+	struct xe_gt *gt = pc_to_gt(pc);
+	struct xe_device *xe = gt_to_xe(gt);
+	u32 reg;
+
+	/*
+	 * For PVC we still need to use fused RP1 as the approximation for RPe
+	 * For other platforms than PVC we get the resolved RPe directly from
+	 * PCODE at a different register
+	 */
+	if (xe->info.platform == XE_PVC)
+		reg = xe_mmio_read32(&gt->mmio, PVC_RP_STATE_CAP);
+	else
+		reg = xe_mmio_read32(&gt->mmio, FREQ_INFO_REC);
+
+	pc->rpa_freq = REG_FIELD_GET(RPA_MASK, reg) * GT_FREQUENCY_MULTIPLIER;
+}
+
 static void tgl_update_rpe_value(struct xe_guc_pc *pc)
 {
 	struct xe_gt *gt = pc_to_gt(pc);
@@ -365,10 +398,13 @@ static void pc_update_rp_values(struct xe_guc_pc *pc)
 	struct xe_gt *gt = pc_to_gt(pc);
 	struct xe_device *xe = gt_to_xe(gt);
 
-	if (GRAPHICS_VERx100(xe) >= 1270)
+	if (GRAPHICS_VERx100(xe) >= 1270) {
+		mtl_update_rpa_value(pc);
 		mtl_update_rpe_value(pc);
-	else
+	} else {
+		tgl_update_rpa_value(pc);
 		tgl_update_rpe_value(pc);
+	}
 
 	/*
 	 * RPe is decided at runtime by PCODE. In the rare case where that's
@@ -447,6 +483,19 @@ u32 xe_guc_pc_get_rp0_freq(struct xe_guc_pc *pc)
 	return pc->rp0_freq;
 }
 
+/**
+ * xe_guc_pc_get_rpa_freq - Get the RPa freq
+ * @pc: The GuC PC
+ *
+ * Returns: RPa freq.
+ */
+u32 xe_guc_pc_get_rpa_freq(struct xe_guc_pc *pc)
+{
+	pc_update_rp_values(pc);
+
+	return pc->rpa_freq;
+}
+
 /**
  * xe_guc_pc_get_rpe_freq - Get the RPe freq
  * @pc: The GuC PC
diff --git a/drivers/gpu/drm/xe/xe_guc_pc.h b/drivers/gpu/drm/xe/xe_guc_pc.h
index efda432fadfc..619f59cd633c 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.h
+++ b/drivers/gpu/drm/xe/xe_guc_pc.h
@@ -21,6 +21,7 @@ int xe_guc_pc_unset_gucrc_mode(struct xe_guc_pc *pc);
 u32 xe_guc_pc_get_act_freq(struct xe_guc_pc *pc);
 int xe_guc_pc_get_cur_freq(struct xe_guc_pc *pc, u32 *freq);
 u32 xe_guc_pc_get_rp0_freq(struct xe_guc_pc *pc);
+u32 xe_guc_pc_get_rpa_freq(struct xe_guc_pc *pc);
 u32 xe_guc_pc_get_rpe_freq(struct xe_guc_pc *pc);
 u32 xe_guc_pc_get_rpn_freq(struct xe_guc_pc *pc);
 int xe_guc_pc_get_min_freq(struct xe_guc_pc *pc, u32 *freq);
diff --git a/drivers/gpu/drm/xe/xe_guc_pc_types.h b/drivers/gpu/drm/xe/xe_guc_pc_types.h
index 13810be015db..2978ac9a249b 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_pc_types.h
@@ -17,6 +17,8 @@ struct xe_guc_pc {
 	struct xe_bo *bo;
 	/** @rp0_freq: HW RP0 frequency - The Maximum one */
 	u32 rp0_freq;
+	/** @rpa_freq: HW RPa frequency - The Achievable one */
+	u32 rpa_freq;
 	/** @rpe_freq: HW RPe frequency - The Efficient one */
 	u32 rpe_freq;
 	/** @rpn_freq: HW RPN frequency - The Minimum one */
-- 
2.51.0


From 3259ff4eff330f8451e8f569951752f5aea38405 Mon Sep 17 00:00:00 2001
From: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Date: Mon, 16 Dec 2024 11:41:19 -0800
Subject: [PATCH 13/16] drm/xe/slpc: Remove unnecessary force wakes

FORCEWAKE_ALL is not needed when we are trying to read the cur_freq,
we just need to wake up the GT domain. We also do not need a force wake
to for a H2G query to obtain min frequency.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241216194119.3017792-1-vinay.belgaumkar@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_pc.c | 26 +++++++-------------------
 1 file changed, 7 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index a6fdd2c062ff..df7f130fb663 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -457,8 +457,8 @@ int xe_guc_pc_get_cur_freq(struct xe_guc_pc *pc, u32 *freq)
 	 * GuC SLPC plays with cur freq request when GuCRC is enabled
 	 * Block RC6 for a more reliable read.
 	 */
-	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
-	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) {
+	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FW_GT)) {
 		xe_force_wake_put(gt_to_fw(gt), fw_ref);
 		return -ETIMEDOUT;
 	}
@@ -530,10 +530,10 @@ u32 xe_guc_pc_get_rpn_freq(struct xe_guc_pc *pc)
  */
 int xe_guc_pc_get_min_freq(struct xe_guc_pc *pc, u32 *freq)
 {
-	struct xe_gt *gt = pc_to_gt(pc);
-	unsigned int fw_ref;
 	int ret;
 
+	xe_device_assert_mem_access(pc_to_xe(pc));
+
 	mutex_lock(&pc->freq_lock);
 	if (!pc->freq_ready) {
 		/* Might be in the middle of a gt reset */
@@ -541,24 +541,12 @@ int xe_guc_pc_get_min_freq(struct xe_guc_pc *pc, u32 *freq)
 		goto out;
 	}
 
-	/*
-	 * GuC SLPC plays with min freq request when GuCRC is enabled
-	 * Block RC6 for a more reliable read.
-	 */
-	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
-	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) {
-		ret = -ETIMEDOUT;
-		goto fw;
-	}
-
 	ret = pc_action_query_task_state(pc);
 	if (ret)
-		goto fw;
+		goto out;
 
 	*freq = pc_get_min_freq(pc);
 
-fw:
-	xe_force_wake_put(gt_to_fw(gt), fw_ref);
 out:
 	mutex_unlock(&pc->freq_lock);
 	return ret;
@@ -1018,8 +1006,8 @@ int xe_guc_pc_start(struct xe_guc_pc *pc)
 
 	xe_gt_assert(gt, xe_device_uc_enabled(xe));
 
-	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FORCEWAKE_ALL);
-	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FORCEWAKE_ALL)) {
+	fw_ref = xe_force_wake_get(gt_to_fw(gt), XE_FW_GT);
+	if (!xe_force_wake_ref_has_domain(fw_ref, XE_FW_GT)) {
 		xe_force_wake_put(gt_to_fw(gt), fw_ref);
 		return -ETIMEDOUT;
 	}
-- 
2.51.0


From 75fd04f276de31cc59419fda169232d097fbf291 Mon Sep 17 00:00:00 2001
From: Nitin Gote <nitin.r.gote@intel.com>
Date: Mon, 6 Jan 2025 15:56:46 +0530
Subject: [PATCH 14/16] drm/xe: Fix all typos in xe

Fix all typos in files of xe, reported by codespell tool.

Signed-off-by: Nitin Gote <nitin.r.gote@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Reviewed-by: Stuart Summers <stuart.summers@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250106102646.1400146-2-nitin.r.gote@intel.com
Signed-off-by: Nirmoy Das <nirmoy.das@intel.com>
---
 drivers/gpu/drm/xe/Kconfig.debug           | 4 ++--
 drivers/gpu/drm/xe/abi/guc_capture_abi.h   | 2 +-
 drivers/gpu/drm/xe/abi/guc_klvs_abi.h      | 6 +++---
 drivers/gpu/drm/xe/regs/xe_reg_defs.h      | 2 +-
 drivers/gpu/drm/xe/tests/xe_mocs.c         | 2 +-
 drivers/gpu/drm/xe/xe_bb.c                 | 2 +-
 drivers/gpu/drm/xe/xe_bo.c                 | 8 ++++----
 drivers/gpu/drm/xe/xe_bo_doc.h             | 2 +-
 drivers/gpu/drm/xe/xe_devcoredump.c        | 2 +-
 drivers/gpu/drm/xe/xe_device.c             | 2 +-
 drivers/gpu/drm/xe/xe_drm_client.c         | 2 +-
 drivers/gpu/drm/xe/xe_exec.c               | 2 +-
 drivers/gpu/drm/xe/xe_ggtt.c               | 2 +-
 drivers/gpu/drm/xe/xe_gt.h                 | 2 +-
 drivers/gpu/drm/xe/xe_gt_mcr.c             | 2 +-
 drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c | 2 +-
 drivers/gpu/drm/xe/xe_guc_capture.c        | 2 +-
 drivers/gpu/drm/xe/xe_guc_capture_types.h  | 4 ++--
 drivers/gpu/drm/xe/xe_guc_ct.c             | 4 ++--
 drivers/gpu/drm/xe/xe_guc_submit.c         | 2 +-
 drivers/gpu/drm/xe/xe_hmm.c                | 2 +-
 drivers/gpu/drm/xe/xe_migrate.c            | 2 +-
 drivers/gpu/drm/xe/xe_pci.c                | 4 ++--
 drivers/gpu/drm/xe/xe_pcode.c              | 2 +-
 drivers/gpu/drm/xe/xe_pm.c                 | 2 +-
 drivers/gpu/drm/xe/xe_pt.c                 | 2 +-
 drivers/gpu/drm/xe/xe_rtp.h                | 4 ++--
 drivers/gpu/drm/xe/xe_uc_fw_types.h        | 2 +-
 drivers/gpu/drm/xe/xe_vm.c                 | 4 ++--
 29 files changed, 40 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/xe/Kconfig.debug b/drivers/gpu/drm/xe/Kconfig.debug
index 2de0de41b8dd..0d749ed44878 100644
--- a/drivers/gpu/drm/xe/Kconfig.debug
+++ b/drivers/gpu/drm/xe/Kconfig.debug
@@ -66,7 +66,7 @@ config DRM_XE_DEBUG_MEM
 	bool "Enable passing SYS/VRAM addresses to user space"
 	default n
 	help
-	  Pass object location trough uapi. Intended for extended
+	  Pass object location through uapi. Intended for extended
 	  testing and development only.
 
 	  Recommended for driver developers only.
@@ -104,5 +104,5 @@ config DRM_XE_USERPTR_INVAL_INJECT
          Choose this option when debugging error paths that
 	 are hit during checks for userptr invalidations.
 
-	 Recomended for driver developers only.
+	 Recommended for driver developers only.
 	 If in doubt, say "N".
diff --git a/drivers/gpu/drm/xe/abi/guc_capture_abi.h b/drivers/gpu/drm/xe/abi/guc_capture_abi.h
index e7898edc6236..dd4117553739 100644
--- a/drivers/gpu/drm/xe/abi/guc_capture_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_capture_abi.h
@@ -25,7 +25,7 @@ enum guc_state_capture_type {
 
 #define GUC_STATE_CAPTURE_TYPE_MAX	(GUC_STATE_CAPTURE_TYPE_ENGINE_INSTANCE + 1)
 
-/* Class indecies for capture_class and capture_instance arrays */
+/* Class indices for capture_class and capture_instance arrays */
 enum guc_capture_list_class_type {
 	GUC_CAPTURE_LIST_CLASS_RENDER_COMPUTE = 0,
 	GUC_CAPTURE_LIST_CLASS_VIDEO = 1,
diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
index 7dcb118e3d9f..d633f1c739e4 100644
--- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
@@ -132,7 +132,7 @@ enum  {
  * _`GUC_KLV_VGT_POLICY_SCHED_IF_IDLE` : 0x8001
  *      This config sets whether strict scheduling is enabled whereby any VF
  *      that doesn’t have work to submit is still allocated a fixed execution
- *      time-slice to ensure active VFs execution is always consitent even
+ *      time-slice to ensure active VFs execution is always consistent even
  *      during other VF reprovisiong / rebooting events. Changing this KLV
  *      impacts all VFs and takes effect on the next VF-Switch event.
  *
@@ -207,7 +207,7 @@ enum  {
  *      of and this will never be perfectly-exact (accumulated nano-second
  *      granularity) since the GPUs clock time runs off a different crystal
  *      from the CPUs clock. Changing this KLV on a VF that is currently
- *      running a context wont take effect until a new context is scheduled in.
+ *      running a context won't take effect until a new context is scheduled in.
  *      That said, when the PF is changing this value from 0x0 to
  *      a non-zero value, it might never take effect if the VF is running an
  *      infinitely long compute or shader kernel. In such a scenario, the
@@ -227,7 +227,7 @@ enum  {
  *      HW is capable and this will never be perfectly-exact (accumulated
  *      nano-second granularity) since the GPUs clock time runs off a
  *      different crystal from the CPUs clock. Changing this KLV on a VF
- *      that is currently running a context wont take effect until a new
+ *      that is currently running a context won't take effect until a new
  *      context is scheduled in.
  *      That said, when the PF is changing this value from 0x0 to
  *      a non-zero value, it might never take effect if the VF is running an
diff --git a/drivers/gpu/drm/xe/regs/xe_reg_defs.h b/drivers/gpu/drm/xe/regs/xe_reg_defs.h
index 51fd40ffafcb..0eedd6c26b1b 100644
--- a/drivers/gpu/drm/xe/regs/xe_reg_defs.h
+++ b/drivers/gpu/drm/xe/regs/xe_reg_defs.h
@@ -13,7 +13,7 @@
 /**
  * struct xe_reg - Register definition
  *
- * Register defintion to be used by the individual register. Although the same
+ * Register definition to be used by the individual register. Although the same
  * definition is used for xe_reg and xe_reg_mcr, they use different internal
  * APIs for accesses.
  */
diff --git a/drivers/gpu/drm/xe/tests/xe_mocs.c b/drivers/gpu/drm/xe/tests/xe_mocs.c
index 6f9b7a266b41..d3f71d13eb81 100644
--- a/drivers/gpu/drm/xe/tests/xe_mocs.c
+++ b/drivers/gpu/drm/xe/tests/xe_mocs.c
@@ -58,7 +58,7 @@ static void read_l3cc_table(struct xe_gt *gt,
 
 			mocs_dbg(gt, "reg_val=0x%x\n", reg_val);
 		} else {
-			/* Just re-use value read on previous iteration */
+			/* Just reuse value read on previous iteration */
 			reg_val >>= 16;
 		}
 
diff --git a/drivers/gpu/drm/xe/xe_bb.c b/drivers/gpu/drm/xe/xe_bb.c
index ef777dbdf4ec..9570672fce33 100644
--- a/drivers/gpu/drm/xe/xe_bb.c
+++ b/drivers/gpu/drm/xe/xe_bb.c
@@ -41,7 +41,7 @@ struct xe_bb *xe_bb_new(struct xe_gt *gt, u32 dwords, bool usm)
 	/*
 	 * We need to allocate space for the requested number of dwords,
 	 * one additional MI_BATCH_BUFFER_END dword, and additional buffer
-	 * space to accomodate the platform-specific hardware prefetch
+	 * space to accommodate the platform-specific hardware prefetch
 	 * requirements.
 	 */
 	bb->bo = xe_sa_bo_new(!usm ? tile->mem.kernel_bb_pool : gt->usm.bb_pool,
diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index e6c896ad5602..3f5391d416d4 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -786,7 +786,7 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 		 * / resume, some of the pinned memory is required for the
 		 * device to resume / use the GPU to move other evicted memory
 		 * (user memory) around. This likely could be optimized a bit
-		 * futher where we find the minimum set of pinned memory
+		 * further where we find the minimum set of pinned memory
 		 * required for resume but for simplity doing a memcpy for all
 		 * pinned memory.
 		 */
@@ -875,7 +875,7 @@ out:
  * xe_bo_evict_pinned() - Evict a pinned VRAM object to system memory
  * @bo: The buffer object to move.
  *
- * On successful completion, the object memory will be moved to sytem memory.
+ * On successful completion, the object memory will be moved to system memory.
  *
  * This is needed to for special handling of pinned VRAM object during
  * suspend-resume.
@@ -1370,7 +1370,7 @@ static const struct drm_gem_object_funcs xe_gem_object_funcs = {
 /**
  * xe_bo_alloc - Allocate storage for a struct xe_bo
  *
- * This funcition is intended to allocate storage to be used for input
+ * This function is intended to allocate storage to be used for input
  * to __xe_bo_create_locked(), in the case a pointer to the bo to be
  * created is needed before the call to __xe_bo_create_locked().
  * If __xe_bo_create_locked ends up never to be called, then the
@@ -2412,7 +2412,7 @@ int xe_bo_migrate(struct xe_bo *bo, u32 mem_type)
  * @force_alloc: Set force_alloc in ttm_operation_ctx
  *
  * On successful completion, the object memory will be moved to evict
- * placement. Ths function blocks until the object has been fully moved.
+ * placement. This function blocks until the object has been fully moved.
  *
  * Return: 0 on success. Negative error code on failure.
  */
diff --git a/drivers/gpu/drm/xe/xe_bo_doc.h b/drivers/gpu/drm/xe/xe_bo_doc.h
index f57d440cc95a..25a884c64bf1 100644
--- a/drivers/gpu/drm/xe/xe_bo_doc.h
+++ b/drivers/gpu/drm/xe/xe_bo_doc.h
@@ -41,7 +41,7 @@
  * created the BO can be mmap'd (via DRM_IOCTL_XE_GEM_MMAP_OFFSET) for user
  * access and it can be bound for GPU access (via DRM_IOCTL_XE_VM_BIND). All
  * user BOs are evictable and user BOs are never pinned by XE. The allocation of
- * the backing store can be defered from creation time until first use which is
+ * the backing store can be deferred from creation time until first use which is
  * either mmap, bind, or pagefault.
  *
  * Private BOs
diff --git a/drivers/gpu/drm/xe/xe_devcoredump.c b/drivers/gpu/drm/xe/xe_devcoredump.c
index 6980304c8903..81dc7795c065 100644
--- a/drivers/gpu/drm/xe/xe_devcoredump.c
+++ b/drivers/gpu/drm/xe/xe_devcoredump.c
@@ -48,7 +48,7 @@
  *
  * **Coredump release**:
  *   After a coredump is generated, it stays in kernel memory until released by
- *   userpace by writing anything to it, or after an internal timer expires. The
+ *   userspace by writing anything to it, or after an internal timer expires. The
  *   exact timeout may vary and should not be relied upon. Example to release
  *   a coredump:
  *
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index bb627247c9c8..5cbc96b214fe 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -1000,7 +1000,7 @@ static void xe_device_wedged_fini(struct drm_device *drm, void *arg)
  * xe_device_declare_wedged - Declare device wedged
  * @xe: xe device instance
  *
- * This is a final state that can only be cleared with a mudule
+ * This is a final state that can only be cleared with a module
  * re-probe (unbind + bind).
  * In this state every IOCTL will be blocked so the GT cannot be used.
  * In general it will be called upon any critical error such as gt reset
diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c
index 298a587da7f1..a1710591a8d6 100644
--- a/drivers/gpu/drm/xe/xe_drm_client.c
+++ b/drivers/gpu/drm/xe/xe_drm_client.c
@@ -384,7 +384,7 @@ static void show_run_ticks(struct drm_printer *p, struct drm_file *file)
  * @p: The drm_printer ptr
  * @file: The drm_file ptr
  *
- * This is callabck for drm fdinfo interface. Register this callback
+ * This is callback for drm fdinfo interface. Register this callback
  * in drm driver ops for show_fdinfo.
  *
  * Return: void
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index 31cca938956f..df8ce550deb4 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -33,7 +33,7 @@
  *
  * In XE we avoid all of this complication by not allowing a BO list to be
  * passed into an exec, using the dma-buf implicit sync uAPI, have binds as
- * seperate operations, and using the DRM scheduler to flow control the ring.
+ * separate operations, and using the DRM scheduler to flow control the ring.
  * Let's deep dive on each of these.
  *
  * We can get away from a BO list by forcing the user to use in / out fences on
diff --git a/drivers/gpu/drm/xe/xe_ggtt.c b/drivers/gpu/drm/xe/xe_ggtt.c
index 05154f9de1a6..5fcb2b4c2c13 100644
--- a/drivers/gpu/drm/xe/xe_ggtt.c
+++ b/drivers/gpu/drm/xe/xe_ggtt.c
@@ -362,7 +362,7 @@ int xe_ggtt_init(struct xe_ggtt *ggtt)
 
 	/*
 	 * So we don't need to worry about 64K GGTT layout when dealing with
-	 * scratch entires, rather keep the scratch page in system memory on
+	 * scratch entries, rather keep the scratch page in system memory on
 	 * platforms where 64K pages are needed for VRAM.
 	 */
 	flags = XE_BO_FLAG_PINNED;
diff --git a/drivers/gpu/drm/xe/xe_gt.h b/drivers/gpu/drm/xe/xe_gt.h
index 82b9b7f82fca..4e4e8e103419 100644
--- a/drivers/gpu/drm/xe/xe_gt.h
+++ b/drivers/gpu/drm/xe/xe_gt.h
@@ -37,7 +37,7 @@ int xe_gt_record_default_lrcs(struct xe_gt *gt);
 
 /**
  * xe_gt_record_user_engines - save data related to engines available to
- * usersapce
+ * userspace
  * @gt: GT structure
  *
  * Walk the available HW engines from gt->info.engine_mask and calculate data
diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.c b/drivers/gpu/drm/xe/xe_gt_mcr.c
index 5013d674e17d..71485b96fc6f 100644
--- a/drivers/gpu/drm/xe/xe_gt_mcr.c
+++ b/drivers/gpu/drm/xe/xe_gt_mcr.c
@@ -371,7 +371,7 @@ void xe_gt_mcr_get_dss_steering(struct xe_gt *gt, unsigned int dss, u16 *group,
  * @group: steering group ID
  * @instance: steering instance ID
  *
- * Return: the coverted DSS id.
+ * Return: the converted DSS id.
  */
 u32 xe_gt_mcr_steering_info_to_dss_id(struct xe_gt *gt, u16 group, u16 instance)
 {
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index bd621df3ab91..878e96281c03 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -2161,7 +2161,7 @@ bool xe_gt_sriov_pf_config_is_empty(struct xe_gt *gt, unsigned int vfid)
  *
  * This function can only be called on PF.
  *
- * Return: mininum size of the buffer or the number of bytes saved,
+ * Return: minimum size of the buffer or the number of bytes saved,
  *         or a negative error code on failure.
  */
 ssize_t xe_gt_sriov_pf_config_save(struct xe_gt *gt, unsigned int vfid, void *buf, size_t size)
diff --git a/drivers/gpu/drm/xe/xe_guc_capture.c b/drivers/gpu/drm/xe/xe_guc_capture.c
index 137571fae4ed..f6d523e4c5fe 100644
--- a/drivers/gpu/drm/xe/xe_guc_capture.c
+++ b/drivers/gpu/drm/xe/xe_guc_capture.c
@@ -1955,7 +1955,7 @@ xe_engine_snapshot_capture_for_queue(struct xe_exec_queue *q)
 }
 
 /*
- * xe_guc_capture_put_matched_nodes - Cleanup macthed nodes
+ * xe_guc_capture_put_matched_nodes - Cleanup matched nodes
  * @guc: The GuC object
  *
  * Free matched node and all nodes with the equal guc_id from
diff --git a/drivers/gpu/drm/xe/xe_guc_capture_types.h b/drivers/gpu/drm/xe/xe_guc_capture_types.h
index 2057125b1bfa..ca2d390ccbee 100644
--- a/drivers/gpu/drm/xe/xe_guc_capture_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_capture_types.h
@@ -22,7 +22,7 @@ enum capture_register_data_type {
  * struct __guc_mmio_reg_descr - GuC mmio register descriptor
  *
  * xe_guc_capture module uses these structures to define a register
- * (offsets, names, flags,...) that are used at the ADS regisration
+ * (offsets, names, flags,...) that are used at the ADS registration
  * time as well as during runtime processing and reporting of error-
  * capture states generated by GuC just prior to engine reset events.
  */
@@ -48,7 +48,7 @@ struct __guc_mmio_reg_descr {
  *
  * xe_guc_capture module uses these structures to maintain static
  * tables (per unique platform) that consists of lists of registers
- * (offsets, names, flags,...) that are used at the ADS regisration
+ * (offsets, names, flags,...) that are used at the ADS registration
  * time as well as during runtime processing and reporting of error-
  * capture states generated by GuC just prior to engine reset events.
  */
diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 7d33f3a11e61..8b65c5e959cc 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -710,7 +710,7 @@ static int h2g_write(struct xe_guc_ct *ct, const u32 *action, u32 len,
 	--len;
 	++action;
 
-	/* Write H2G ensuring visable before descriptor update */
+	/* Write H2G ensuring visible before descriptor update */
 	xe_map_memcpy_to(xe, &map, 0, cmd, H2G_CT_HEADERS * sizeof(u32));
 	xe_map_memcpy_to(xe, &map, H2G_CT_HEADERS * sizeof(u32), action, len * sizeof(u32));
 	xe_device_wmb(xe);
@@ -1383,7 +1383,7 @@ static int g2h_read(struct xe_guc_ct *ct, u32 *msg, bool fast_path)
 		 * this function and nowhere else. Hence, they cannot be different
 		 * unless two g2h_read calls are running concurrently. Which is not
 		 * possible because it is guarded by ct->fast_lock. And yet, some
-		 * discrete platforms are reguarly hitting this error :(.
+		 * discrete platforms are regularly hitting this error :(.
 		 *
 		 * desc_head rolling backwards shouldn't cause any noticeable
 		 * problems - just a delay in GuC being allowed to proceed past that
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 9c36329fe857..913c74d6e2ae 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1226,7 +1226,7 @@ sched_enable:
 	enable_scheduling(q);
 rearm:
 	/*
-	 * XXX: Ideally want to adjust timeout based on current exection time
+	 * XXX: Ideally want to adjust timeout based on current execution time
 	 * but there is not currently an easy way to do in DRM scheduler. With
 	 * some thought, do this in a follow up.
 	 */
diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index 2c32dc46f7d4..089834467880 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -159,7 +159,7 @@ void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma)
  * This function allocates the storage of the userptr sg table.
  * It is caller's responsibility to free it calling sg_free_table.
  *
- * returns: 0 for succuss; negative error no on failure
+ * returns: 0 for success; negative error no on failure
  */
 int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 				  bool is_mm_mmap_locked)
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 1b97d90aadda..278bc96cf593 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -1506,7 +1506,7 @@ err_bb:
  * using the default engine for the updates, they will be performed in the
  * order they grab the job_mutex. If different engines are used, external
  * synchronization is needed for overlapping updates to maintain page-table
- * consistency. Note that the meaing of "overlapping" is that the updates
+ * consistency. Note that the meaning of "overlapping" is that the updates
  * touch the same page-table, which might be a higher-level page-directory.
  * If no pipelining is needed, then updates may be performed by the cpu.
  *
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 6b7f77425c7f..39be74848e44 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -490,7 +490,7 @@ static void read_gmdid(struct xe_device *xe, enum xe_gmdid_type type, u32 *ver,
 		 * least basic xe_gt and xe_guc initialization.
 		 *
 		 * Since to obtain the value of GMDID_MEDIA we need to use the
-		 * media GuC, temporarly tweak the gt type.
+		 * media GuC, temporarily tweak the gt type.
 		 */
 		xe_gt_assert(gt, gt->info.type == XE_GT_TYPE_UNINITIALIZED);
 
@@ -781,7 +781,7 @@ static void xe_pci_remove(struct pci_dev *pdev)
  * error injectable functions is proper handling of the error code by the
  * caller for recovery, which is always the case here. The second
  * requirement is that no state is changed before the first error return.
- * It is not strictly fullfilled for all initialization functions using the
+ * It is not strictly fulfilled for all initialization functions using the
  * ALLOW_ERROR_INJECTION() macro but this is acceptable because for those
  * error cases at probe time, the error code is simply propagated up by the
  * caller. Therefore there is no consequence on those specific callers when
diff --git a/drivers/gpu/drm/xe/xe_pcode.c b/drivers/gpu/drm/xe/xe_pcode.c
index d95d9835de42..9333ce776a6e 100644
--- a/drivers/gpu/drm/xe/xe_pcode.c
+++ b/drivers/gpu/drm/xe/xe_pcode.c
@@ -217,7 +217,7 @@ out:
  *
  * It returns 0 on success, and -ERROR number on failure, -EINVAL if max
  * frequency is higher then the minimal, and other errors directly translated
- * from the PCODE Error returs:
+ * from the PCODE Error returns:
  * - -ENXIO: "Illegal Command"
  * - -ETIMEDOUT: "Timed out"
  * - -EINVAL: "Illegal Data"
diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index 85cfec5ec9af..e434b0b1870b 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -391,7 +391,7 @@ int xe_pm_runtime_suspend(struct xe_device *xe)
 
 	/*
 	 * Applying lock for entire list op as xe_ttm_bo_destroy and xe_bo_move_notify
-	 * also checks and delets bo entry from user fault list.
+	 * also checks and deletes bo entry from user fault list.
 	 */
 	mutex_lock(&xe->mem_access.vram_userfault.lock);
 	list_for_each_entry_safe(bo, on,
diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 65c3c1688710..1ddcc7e79a93 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -276,7 +276,7 @@ struct xe_pt_stage_bind_walk {
 	/* Also input, but is updated during the walk*/
 	/** @curs: The DMA address cursor. */
 	struct xe_res_cursor *curs;
-	/** @va_curs_start: The Virtual address coresponding to @curs->start */
+	/** @va_curs_start: The Virtual address corresponding to @curs->start */
 	u64 va_curs_start;
 
 	/* Output */
diff --git a/drivers/gpu/drm/xe/xe_rtp.h b/drivers/gpu/drm/xe/xe_rtp.h
index 7dea10d732d7..38b9f13bba5e 100644
--- a/drivers/gpu/drm/xe/xe_rtp.h
+++ b/drivers/gpu/drm/xe/xe_rtp.h
@@ -131,7 +131,7 @@ struct xe_reg_sr;
  * @ver_end__: Last graphics IP version to match
  *
  * Note that the range matching this rule is [ @ver_start__, @ver_end__ ], i.e.
- * inclusive on boths sides
+ * inclusive on both sides
  *
  * Refer to XE_RTP_RULES() for expected usage.
  */
@@ -169,7 +169,7 @@ struct xe_reg_sr;
  * @ver_end__: Last media IP version to match
  *
  * Note that the range matching this rule is [ @ver_start__, @ver_end__ ], i.e.
- * inclusive on boths sides
+ * inclusive on both sides
  *
  * Refer to XE_RTP_RULES() for expected usage.
  */
diff --git a/drivers/gpu/drm/xe/xe_uc_fw_types.h b/drivers/gpu/drm/xe/xe_uc_fw_types.h
index 0d8caa0e7354..ad3b35a0e6eb 100644
--- a/drivers/gpu/drm/xe/xe_uc_fw_types.h
+++ b/drivers/gpu/drm/xe/xe_uc_fw_types.h
@@ -92,7 +92,7 @@ struct xe_uc_fw {
 		const enum xe_uc_fw_status status;
 		/**
 		 * @__status: private firmware load status - only to be used
-		 * by firmware laoding code
+		 * by firmware loading code
 		 */
 		enum xe_uc_fw_status __status;
 	};
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 74d684708b00..e86c4cc47884 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1025,7 +1025,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 
 		/*
 		 * Since userptr pages are not pinned, we can't remove
-		 * the notifer until we're sure the GPU is not accessing
+		 * the notifier until we're sure the GPU is not accessing
 		 * them anymore
 		 */
 		mmu_interval_notifier_remove(&userptr->notifier);
@@ -2108,7 +2108,7 @@ static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op)
 			}
 		}
 
-		/* Adjust for partial unbind after removin VMA from VM */
+		/* Adjust for partial unbind after removing VMA from VM */
 		if (!err) {
 			op->base.remap.unmap->va->va.addr = op->remap.start;
 			op->base.remap.unmap->va->va.range = op->remap.range;
-- 
2.51.0


From ee5a1321df90891d59d83b7c9d5b6c5b755d059d Mon Sep 17 00:00:00 2001
From: Jesus Narvaez <jesus.narvaez@intel.com>
Date: Thu, 12 Dec 2024 11:01:00 -0800
Subject: [PATCH 15/16] drm/xe/guc: Adding steering info support for GuC
 register lists

The guc_mmio_reg interface supports steering, but it is currently not
implemented. This will allow the GuC to control steering of MMIO
registers after save-restore and avoid reading from fused off MCR
register instances.

Fixes: 9c57bc08652a ("drm/xe/lnl: Drop force_probe requirement")
Signed-off-by: Jesus Narvaez <jesus.narvaez@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241212190100.3768068-1-jesus.narvaez@intel.com
---
 drivers/gpu/drm/xe/xe_gt_mcr.c  |  6 +++---
 drivers/gpu/drm/xe/xe_gt_mcr.h  |  4 ++++
 drivers/gpu/drm/xe/xe_guc_ads.c | 15 +++++++++++++++
 3 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.c b/drivers/gpu/drm/xe/xe_gt_mcr.c
index 71485b96fc6f..a1676b787fdc 100644
--- a/drivers/gpu/drm/xe/xe_gt_mcr.c
+++ b/drivers/gpu/drm/xe/xe_gt_mcr.c
@@ -550,9 +550,9 @@ void xe_gt_mcr_set_implicit_defaults(struct xe_gt *gt)
  * Returns true if the caller should steer to the @group/@instance values
  * returned.  Returns false if the caller need not perform any steering
  */
-static bool xe_gt_mcr_get_nonterminated_steering(struct xe_gt *gt,
-						 struct xe_reg_mcr reg_mcr,
-						 u8 *group, u8 *instance)
+bool xe_gt_mcr_get_nonterminated_steering(struct xe_gt *gt,
+					  struct xe_reg_mcr reg_mcr,
+					  u8 *group, u8 *instance)
 {
 	const struct xe_reg reg = to_xe_reg(reg_mcr);
 	const struct xe_mmio_range *implicit_ranges;
diff --git a/drivers/gpu/drm/xe/xe_gt_mcr.h b/drivers/gpu/drm/xe/xe_gt_mcr.h
index c0cd36021c24..bc06520befab 100644
--- a/drivers/gpu/drm/xe/xe_gt_mcr.h
+++ b/drivers/gpu/drm/xe/xe_gt_mcr.h
@@ -26,6 +26,10 @@ void xe_gt_mcr_unicast_write(struct xe_gt *gt, struct xe_reg_mcr mcr_reg,
 void xe_gt_mcr_multicast_write(struct xe_gt *gt, struct xe_reg_mcr mcr_reg,
 			       u32 value);
 
+bool xe_gt_mcr_get_nonterminated_steering(struct xe_gt *gt,
+					  struct xe_reg_mcr reg_mcr,
+					  u8 *group, u8 *instance);
+
 void xe_gt_mcr_steering_dump(struct xe_gt *gt, struct drm_printer *p);
 void xe_gt_mcr_get_dss_steering(struct xe_gt *gt, unsigned int dss, u16 *group, u16 *instance);
 u32 xe_gt_mcr_steering_info_to_dss_id(struct xe_gt *gt, u16 group, u16 instance);
diff --git a/drivers/gpu/drm/xe/xe_guc_ads.c b/drivers/gpu/drm/xe/xe_guc_ads.c
index 943146e5b460..fab259adc380 100644
--- a/drivers/gpu/drm/xe/xe_guc_ads.c
+++ b/drivers/gpu/drm/xe/xe_guc_ads.c
@@ -29,6 +29,7 @@
 #include "xe_platform_types.h"
 #include "xe_uc_fw.h"
 #include "xe_wa.h"
+#include "xe_gt_mcr.h"
 
 /* Slack of a few additional entries per engine */
 #define ADS_REGSET_EXTRA_MAX	8
@@ -696,6 +697,20 @@ static void guc_mmio_regset_write_one(struct xe_guc_ads *ads,
 		.flags = reg.masked ? GUC_REGSET_MASKED : 0,
 	};
 
+	if (reg.mcr) {
+		struct xe_reg_mcr mcr_reg = XE_REG_MCR(reg.addr);
+		u8 group, instance;
+
+		bool steer = xe_gt_mcr_get_nonterminated_steering(ads_to_gt(ads), mcr_reg,
+								  &group, &instance);
+
+		if (steer) {
+			entry.flags |= FIELD_PREP(GUC_REGSET_STEERING_GROUP, group);
+			entry.flags |= FIELD_PREP(GUC_REGSET_STEERING_INSTANCE, instance);
+			entry.flags |= GUC_REGSET_STEERING_NEEDED;
+		}
+	}
+
 	xe_map_memcpy_to(ads_to_xe(ads), regset_map, n_entry * sizeof(entry),
 			 &entry, sizeof(entry));
 }
-- 
2.51.0


From 6a04bb5a2046067681257d5dd69a724856c8fbcb Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 9 Jan 2025 12:50:32 +0200
Subject: [PATCH 16/16] drm/xe: remove unused xe_pciids.h harder, add missing
 PCI ID

Commit 493454445c95 ("drm/xe: switch to common PCI ID macros") removed
xe_pciids.h via drm-intel-next. In the mean time, commit ae78ec0a52c4
("drm/xe/ptl: Add another PTL PCI ID") added to xe_pciids.h via
drm-xe-next.

The two commits were merged in commit 8f109f287fdc ("Merge drm/drm-next
into drm-xe-next"), but xe_pciids.h wasn't removed, and the PCI ID
wasn't added to pciids.h.

Remove xe_pciids.h, and add the PCI ID to pciids.h.

Cc: Matt Atwood <matthew.s.atwood@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Fixes: 8f109f287fdc ("Merge drm/drm-next into drm-xe-next")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/r/20241125120921.1bbc1930@canb.auug.org.au
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250109105032.2585416-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
---
 include/drm/intel/pciids.h    |   3 +-
 include/drm/intel/xe_pciids.h | 235 ----------------------------------
 2 files changed, 2 insertions(+), 236 deletions(-)
 delete mode 100644 include/drm/intel/xe_pciids.h

diff --git a/include/drm/intel/pciids.h b/include/drm/intel/pciids.h
index 32480b5563db..7883384acd5e 100644
--- a/include/drm/intel/pciids.h
+++ b/include/drm/intel/pciids.h
@@ -829,6 +829,7 @@
 	MACRO__(0xB092, ## __VA_ARGS__), \
 	MACRO__(0xB0A0, ## __VA_ARGS__), \
 	MACRO__(0xB0A1, ## __VA_ARGS__), \
-	MACRO__(0xB0A2, ## __VA_ARGS__)
+	MACRO__(0xB0A2, ## __VA_ARGS__), \
+	MACRO__(0xB0B0, ## __VA_ARGS__)
 
 #endif /* __PCIIDS_H__ */
diff --git a/include/drm/intel/xe_pciids.h b/include/drm/intel/xe_pciids.h
deleted file mode 100644
index 16d4b8bb590a..000000000000
--- a/include/drm/intel/xe_pciids.h
+++ /dev/null
@@ -1,235 +0,0 @@
-/* SPDX-License-Identifier: MIT */
-/*
- * Copyright © 2022 Intel Corporation
- */
-
-#ifndef _XE_PCIIDS_H_
-#define _XE_PCIIDS_H_
-
-/*
- * Lists below can be turned into initializers for a struct pci_device_id
- * by defining INTEL_VGA_DEVICE:
- *
- * #define INTEL_VGA_DEVICE(id, info) { \
- *	0x8086, id,			\
- *	~0, ~0,				\
- *	0x030000, 0xff0000,		\
- *	(unsigned long) info }
- *
- * And then calling like:
- *
- * XE_TGL_12_GT1_IDS(INTEL_VGA_DEVICE, ## __VA_ARGS__)
- *
- * To turn them into something else, just provide a different macro passed as
- * first argument.
- */
-
-/* TGL */
-#define XE_TGL_GT1_IDS(MACRO__, ...)		\
-	MACRO__(0x9A60, ## __VA_ARGS__),	\
-	MACRO__(0x9A68, ## __VA_ARGS__),	\
-	MACRO__(0x9A70, ## __VA_ARGS__)
-
-#define XE_TGL_GT2_IDS(MACRO__, ...)		\
-	MACRO__(0x9A40, ## __VA_ARGS__),	\
-	MACRO__(0x9A49, ## __VA_ARGS__),	\
-	MACRO__(0x9A59, ## __VA_ARGS__),	\
-	MACRO__(0x9A78, ## __VA_ARGS__),	\
-	MACRO__(0x9AC0, ## __VA_ARGS__),	\
-	MACRO__(0x9AC9, ## __VA_ARGS__),	\
-	MACRO__(0x9AD9, ## __VA_ARGS__),	\
-	MACRO__(0x9AF8, ## __VA_ARGS__)
-
-#define XE_TGL_IDS(MACRO__, ...)		\
-	XE_TGL_GT1_IDS(MACRO__, ## __VA_ARGS__),\
-	XE_TGL_GT2_IDS(MACRO__, ## __VA_ARGS__)
-
-/* RKL */
-#define XE_RKL_IDS(MACRO__, ...)		\
-	MACRO__(0x4C80, ## __VA_ARGS__),	\
-	MACRO__(0x4C8A, ## __VA_ARGS__),	\
-	MACRO__(0x4C8B, ## __VA_ARGS__),	\
-	MACRO__(0x4C8C, ## __VA_ARGS__),	\
-	MACRO__(0x4C90, ## __VA_ARGS__),	\
-	MACRO__(0x4C9A, ## __VA_ARGS__)
-
-/* DG1 */
-#define XE_DG1_IDS(MACRO__, ...)		\
-	MACRO__(0x4905, ## __VA_ARGS__),	\
-	MACRO__(0x4906, ## __VA_ARGS__),	\
-	MACRO__(0x4907, ## __VA_ARGS__),	\
-	MACRO__(0x4908, ## __VA_ARGS__),	\
-	MACRO__(0x4909, ## __VA_ARGS__)
-
-/* ADL-S */
-#define XE_ADLS_IDS(MACRO__, ...)		\
-	MACRO__(0x4680, ## __VA_ARGS__),	\
-	MACRO__(0x4682, ## __VA_ARGS__),	\
-	MACRO__(0x4688, ## __VA_ARGS__),	\
-	MACRO__(0x468A, ## __VA_ARGS__),	\
-	MACRO__(0x468B, ## __VA_ARGS__),	\
-	MACRO__(0x4690, ## __VA_ARGS__),	\
-	MACRO__(0x4692, ## __VA_ARGS__),	\
-	MACRO__(0x4693, ## __VA_ARGS__)
-
-/* ADL-P */
-#define XE_ADLP_IDS(MACRO__, ...)		\
-	MACRO__(0x46A0, ## __VA_ARGS__),	\
-	MACRO__(0x46A1, ## __VA_ARGS__),	\
-	MACRO__(0x46A2, ## __VA_ARGS__),	\
-	MACRO__(0x46A3, ## __VA_ARGS__),	\
-	MACRO__(0x46A6, ## __VA_ARGS__),	\
-	MACRO__(0x46A8, ## __VA_ARGS__),	\
-	MACRO__(0x46AA, ## __VA_ARGS__),	\
-	MACRO__(0x462A, ## __VA_ARGS__),	\
-	MACRO__(0x4626, ## __VA_ARGS__),	\
-	MACRO__(0x4628, ## __VA_ARGS__),	\
-	MACRO__(0x46B0, ## __VA_ARGS__),	\
-	MACRO__(0x46B1, ## __VA_ARGS__),	\
-	MACRO__(0x46B2, ## __VA_ARGS__),	\
-	MACRO__(0x46B3, ## __VA_ARGS__),	\
-	MACRO__(0x46C0, ## __VA_ARGS__),	\
-	MACRO__(0x46C1, ## __VA_ARGS__),	\
-	MACRO__(0x46C2, ## __VA_ARGS__),	\
-	MACRO__(0x46C3, ## __VA_ARGS__)
-
-/* ADL-N */
-#define XE_ADLN_IDS(MACRO__, ...)		\
-	MACRO__(0x46D0, ## __VA_ARGS__),	\
-	MACRO__(0x46D1, ## __VA_ARGS__),	\
-	MACRO__(0x46D2, ## __VA_ARGS__),	\
-	MACRO__(0x46D3, ## __VA_ARGS__),	\
-	MACRO__(0x46D4, ## __VA_ARGS__)
-
-/* RPL-S */
-#define XE_RPLS_IDS(MACRO__, ...)		\
-	MACRO__(0xA780, ## __VA_ARGS__),	\
-	MACRO__(0xA781, ## __VA_ARGS__),	\
-	MACRO__(0xA782, ## __VA_ARGS__),	\
-	MACRO__(0xA783, ## __VA_ARGS__),	\
-	MACRO__(0xA788, ## __VA_ARGS__),	\
-	MACRO__(0xA789, ## __VA_ARGS__),	\
-	MACRO__(0xA78A, ## __VA_ARGS__),	\
-	MACRO__(0xA78B, ## __VA_ARGS__)
-
-/* RPL-U */
-#define XE_RPLU_IDS(MACRO__, ...)		\
-	MACRO__(0xA721, ## __VA_ARGS__),	\
-	MACRO__(0xA7A1, ## __VA_ARGS__),	\
-	MACRO__(0xA7A9, ## __VA_ARGS__),	\
-	MACRO__(0xA7AC, ## __VA_ARGS__),	\
-	MACRO__(0xA7AD, ## __VA_ARGS__)
-
-/* RPL-P */
-#define XE_RPLP_IDS(MACRO__, ...)		\
-	MACRO__(0xA720, ## __VA_ARGS__),	\
-	MACRO__(0xA7A0, ## __VA_ARGS__),	\
-	MACRO__(0xA7A8, ## __VA_ARGS__),	\
-	MACRO__(0xA7AA, ## __VA_ARGS__),	\
-	MACRO__(0xA7AB, ## __VA_ARGS__)
-
-/* DG2 */
-#define XE_DG2_G10_IDS(MACRO__, ...)		\
-	MACRO__(0x5690, ## __VA_ARGS__),	\
-	MACRO__(0x5691, ## __VA_ARGS__),	\
-	MACRO__(0x5692, ## __VA_ARGS__),	\
-	MACRO__(0x56A0, ## __VA_ARGS__),	\
-	MACRO__(0x56A1, ## __VA_ARGS__),	\
-	MACRO__(0x56A2, ## __VA_ARGS__),	\
-	MACRO__(0x56BE, ## __VA_ARGS__),	\
-	MACRO__(0x56BF, ## __VA_ARGS__)
-
-#define XE_DG2_G11_IDS(MACRO__, ...)		\
-	MACRO__(0x5693, ## __VA_ARGS__),	\
-	MACRO__(0x5694, ## __VA_ARGS__),	\
-	MACRO__(0x5695, ## __VA_ARGS__),	\
-	MACRO__(0x56A5, ## __VA_ARGS__),	\
-	MACRO__(0x56A6, ## __VA_ARGS__),	\
-	MACRO__(0x56B0, ## __VA_ARGS__),	\
-	MACRO__(0x56B1, ## __VA_ARGS__),	\
-	MACRO__(0x56BA, ## __VA_ARGS__),	\
-	MACRO__(0x56BB, ## __VA_ARGS__),	\
-	MACRO__(0x56BC, ## __VA_ARGS__),	\
-	MACRO__(0x56BD, ## __VA_ARGS__)
-
-#define XE_DG2_G12_IDS(MACRO__, ...)		\
-	MACRO__(0x5696, ## __VA_ARGS__),	\
-	MACRO__(0x5697, ## __VA_ARGS__),	\
-	MACRO__(0x56A3, ## __VA_ARGS__),	\
-	MACRO__(0x56A4, ## __VA_ARGS__),	\
-	MACRO__(0x56B2, ## __VA_ARGS__),	\
-	MACRO__(0x56B3, ## __VA_ARGS__)
-
-#define XE_DG2_IDS(MACRO__, ...)		\
-	XE_DG2_G10_IDS(MACRO__, ## __VA_ARGS__),\
-	XE_DG2_G11_IDS(MACRO__, ## __VA_ARGS__),\
-	XE_DG2_G12_IDS(MACRO__, ## __VA_ARGS__)
-
-#define XE_ATS_M150_IDS(MACRO__, ...)		\
-	MACRO__(0x56C0, ## __VA_ARGS__),	\
-	MACRO__(0x56C2, ## __VA_ARGS__)
-
-#define XE_ATS_M75_IDS(MACRO__, ...)		\
-	MACRO__(0x56C1, ## __VA_ARGS__)
-
-#define XE_ATS_M_IDS(MACRO__, ...)		\
-	XE_ATS_M150_IDS(MACRO__, ## __VA_ARGS__),\
-	XE_ATS_M75_IDS(MACRO__, ## __VA_ARGS__)
-
-/* ARL */
-#define XE_ARL_IDS(MACRO__, ...)		\
-	MACRO__(0x7D41, ## __VA_ARGS__),	\
-	MACRO__(0x7D51, ## __VA_ARGS__),        \
-	MACRO__(0x7D67, ## __VA_ARGS__),	\
-	MACRO__(0x7DD1, ## __VA_ARGS__),	\
-	MACRO__(0xB640, ## __VA_ARGS__)
-
-/* MTL */
-#define XE_MTL_IDS(MACRO__, ...)		\
-	MACRO__(0x7D40, ## __VA_ARGS__),	\
-	MACRO__(0x7D45, ## __VA_ARGS__),	\
-	MACRO__(0x7D55, ## __VA_ARGS__),	\
-	MACRO__(0x7D60, ## __VA_ARGS__),	\
-	MACRO__(0x7DD5, ## __VA_ARGS__)
-
-/* PVC */
-#define XE_PVC_IDS(MACRO__, ...)		\
-	MACRO__(0x0B69, ## __VA_ARGS__),	\
-	MACRO__(0x0B6E, ## __VA_ARGS__),	\
-	MACRO__(0x0BD4, ## __VA_ARGS__),	\
-	MACRO__(0x0BD5, ## __VA_ARGS__),	\
-	MACRO__(0x0BD6, ## __VA_ARGS__),	\
-	MACRO__(0x0BD7, ## __VA_ARGS__),	\
-	MACRO__(0x0BD8, ## __VA_ARGS__),	\
-	MACRO__(0x0BD9, ## __VA_ARGS__),	\
-	MACRO__(0x0BDA, ## __VA_ARGS__),	\
-	MACRO__(0x0BDB, ## __VA_ARGS__),	\
-	MACRO__(0x0BE0, ## __VA_ARGS__),	\
-	MACRO__(0x0BE1, ## __VA_ARGS__),	\
-	MACRO__(0x0BE5, ## __VA_ARGS__)
-
-#define XE_LNL_IDS(MACRO__, ...) \
-	MACRO__(0x6420, ## __VA_ARGS__), \
-	MACRO__(0x64A0, ## __VA_ARGS__), \
-	MACRO__(0x64B0, ## __VA_ARGS__)
-
-#define XE_BMG_IDS(MACRO__, ...) \
-	MACRO__(0xE202, ## __VA_ARGS__), \
-	MACRO__(0xE20B, ## __VA_ARGS__), \
-	MACRO__(0xE20C, ## __VA_ARGS__), \
-	MACRO__(0xE20D, ## __VA_ARGS__), \
-	MACRO__(0xE212, ## __VA_ARGS__)
-
-#define XE_PTL_IDS(MACRO__, ...) \
-	MACRO__(0xB080, ## __VA_ARGS__), \
-	MACRO__(0xB081, ## __VA_ARGS__), \
-	MACRO__(0xB082, ## __VA_ARGS__), \
-	MACRO__(0xB090, ## __VA_ARGS__), \
-	MACRO__(0xB091, ## __VA_ARGS__), \
-	MACRO__(0xB092, ## __VA_ARGS__), \
-	MACRO__(0xB0A0, ## __VA_ARGS__), \
-	MACRO__(0xB0A1, ## __VA_ARGS__), \
-	MACRO__(0xB0A2, ## __VA_ARGS__), \
-	MACRO__(0xB0B0, ## __VA_ARGS__)
-
-#endif
-- 
2.51.0