[PATCH v5] drm/i915/gvt: Correct the privilege shadow batch buffer address

[fred gao <fred.gao@xxxxxxxxx>]

Once the ring buffer is copied to ring_scan_buffer and scanned,
the shadow batch buffer start address is only updated into
ring_scan_buffer, not the real ring address allocated through
intel_ring_begin in later copy_workload_to_ring_buffer.

This patch is only to set the right shadow batch buffer address
from Ring buffer, not include the shadow_wa_ctx.

v2:
- refine some comments. (Zhenyu)
v3:
- fix typo in title. (Zhenyu)
v4:
- remove the unnecessary comments. (Zhenyu)
- add comments in bb_start_cmd_va update. (Zhenyu)

Fixes: 0a53bc07f044 ("drm/i915/gvt: Separate cmd scan from request allocation")
Cc: stable@xxxxxxxxxxxxxxx  # v4.15
Cc: Zhenyu Wang <zhenyuw@xxxxxxxxxxxxxxx>
Cc: Yulei Zhang <yulei.zhang@xxxxxxxxx>
Signed-off-by: fred gao <fred.gao@xxxxxxxxx>
---
 drivers/gpu/drm/i915/gvt/cmd_parser.c |  8 ++++++++
 drivers/gpu/drm/i915/gvt/scheduler.c  | 11 +++++++++++
 drivers/gpu/drm/i915/gvt/scheduler.h  |  1 +
 3 files changed, 20 insertions(+)

diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index c8454ac..db6b94d 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -471,6 +471,7 @@ struct parser_exec_state {
 	 * used when ret from 2nd level batch buffer
 	 */
 	int saved_buf_addr_type;
+	bool is_ctx_wa;
 
 	struct cmd_info *info;
 
@@ -1715,6 +1716,11 @@ static int perform_bb_shadow(struct parser_exec_state *s)
 	bb->accessing = true;
 	bb->bb_start_cmd_va = s->ip_va;
 
+	if ((s->buf_type == BATCH_BUFFER_INSTRUCTION) && (!s->is_ctx_wa))
+		bb->bb_offset = s->ip_va - s->rb_va;
+	else
+		bb->bb_offset = 0;
+
 	/*
 	 * ip_va saves the virtual address of the shadow batch buffer, while
 	 * ip_gma saves the graphics address of the original batch buffer.
@@ -2571,6 +2577,7 @@ static int scan_workload(struct intel_vgpu_workload *workload)
 	s.ring_tail = gma_tail;
 	s.rb_va = workload->shadow_ring_buffer_va;
 	s.workload = workload;
+	s.is_ctx_wa = false;
 
 	if ((bypass_scan_mask & (1 << workload->ring_id)) ||
 		gma_head == gma_tail)
@@ -2624,6 +2631,7 @@ static int scan_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	s.ring_tail = gma_tail;
 	s.rb_va = wa_ctx->indirect_ctx.shadow_va;
 	s.workload = workload;
+	s.is_ctx_wa = true;
 
 	if (!intel_gvt_ggtt_validate_range(s.vgpu, s.ring_start, s.ring_size)) {
 		ret = -EINVAL;
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 9b92b4e..256313c 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -381,6 +381,17 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 			goto err;
 		}
 
+		/* For privilge batch buffer and not wa_ctx, the bb_start_cmd_va
+		 * is only updated into ring_scan_buffer, not real ring address
+		 * allocated in later copy_workload_to_ring_buffer. pls be noted
+		 * shadow_ring_buffer_va is now pointed to real ring buffer va
+		 * in copy_workload_to_ring_buffer.
+		 */
+
+		if (bb->bb_offset)
+			bb->bb_start_cmd_va = workload->shadow_ring_buffer_va
+				+ bb->bb_offset;
+
 		/* relocate shadow batch buffer */
 		bb->bb_start_cmd_va[1] = i915_ggtt_offset(bb->vma);
 		if (gmadr_bytes == 8)
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index bab4097..68313d1 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -120,6 +120,7 @@ struct intel_vgpu_shadow_bb {
 	u32 *bb_start_cmd_va;
 	unsigned int clflush;
 	bool accessing;
+	unsigned long bb_offset;
 };
 
 #define workload_q_head(vgpu, ring_id) \
-- 
2.7.4