[PATCH 3/3] drm/amdgpu/vcn: Use offsets local to VCN/JPEG in VF

[Jane Jian]

For VCN/JPEG 4.0.3, use only the local addressing scheme.

- Mask bit higher than AID0 range
- Remove gmc v9 mmhub vmid replacement, since the bit will be masked later in register write/wait

Signed-off-by: Jane Jian <Jane.Jian at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c    |  5 ---
 drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c | 19 ++++++++--
 drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c  | 46 ++++++++++++++++++++++--
 3 files changed, 60 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index b73136d390cc..2c7b4002ed72 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -844,11 +844,6 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
 	req = hub->vm_inv_eng0_req + hub->eng_distance * eng;
 	ack = hub->vm_inv_eng0_ack + hub->eng_distance * eng;
 
-	if (vmhub >= AMDGPU_MMHUB0(0))
-		inst = 0;
-	else
-		inst = vmhub;
-
 	/* This is necessary for SRIOV as well as for GFXOFF to function
 	 * properly under bare metal
 	 */
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
index 30a143ab592d..ad524ddc9760 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
@@ -32,6 +32,9 @@
 #include "vcn/vcn_4_0_3_sh_mask.h"
 #include "ivsrcid/vcn/irqsrcs_vcn_4_0.h"
 
+#define NORMALIZE_JPEG_REG_OFFSET(offset) \
+		(offset & 0x1FFFF)
+
 enum jpeg_engin_status {
 	UVD_PGFSM_STATUS__UVDJ_PWR_ON  = 0,
 	UVD_PGFSM_STATUS__UVDJ_PWR_OFF = 2,
@@ -824,7 +827,13 @@ void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring,
 void jpeg_v4_0_3_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
 				uint32_t val, uint32_t mask)
 {
-	uint32_t reg_offset = (reg << 2);
+	uint32_t reg_offset;
+
+	/* For VF, only local offsets should be used */
+	if (amdgpu_sriov_vf(ring->adev))
+		reg = NORMALIZE_JPEG_REG_OFFSET(reg);
+
+	reg_offset = (reg << 2);
 
 	amdgpu_ring_write(ring, PACKETJ(regUVD_JRBC_RB_COND_RD_TIMER_INTERNAL_OFFSET,
 		0, 0, PACKETJ_TYPE0));
@@ -865,7 +874,13 @@ void jpeg_v4_0_3_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
 
 void jpeg_v4_0_3_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
 {
-	uint32_t reg_offset = (reg << 2);
+	uint32_t reg_offset;
+
+	/* For VF, only local offsets should be used */
+	if (amdgpu_sriov_vf(ring->adev))
+		reg = NORMALIZE_JPEG_REG_OFFSET(reg);
+
+	reg_offset = (reg << 2);
 
 	amdgpu_ring_write(ring,	PACKETJ(regUVD_JRBC_EXTERNAL_REG_INTERNAL_OFFSET,
 		0, 0, PACKETJ_TYPE0));
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
index 101b120f6fbd..9bae95538b62 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_3.c
@@ -45,6 +45,9 @@
 #define VCN_VID_SOC_ADDRESS_2_0		0x1fb00
 #define VCN1_VID_SOC_ADDRESS_3_0	0x48300
 
+#define NORMALIZE_VCN_REG_OFFSET(offset) \
+		(offset & 0x1FFFF)
+
 static int vcn_v4_0_3_start_sriov(struct amdgpu_device *adev);
 static void vcn_v4_0_3_set_unified_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v4_0_3_set_irq_funcs(struct amdgpu_device *adev);
@@ -1375,6 +1378,43 @@ static uint64_t vcn_v4_0_3_unified_ring_get_wptr(struct amdgpu_ring *ring)
 				    regUVD_RB_WPTR);
 }
 
+static void vcn_v4_0_3_enc_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+				uint32_t val, uint32_t mask)
+{
+	/* For VF, only local offsets should be used */
+	if (amdgpu_sriov_vf(ring->adev))
+		reg = NORMALIZE_VCN_REG_OFFSET(reg);
+
+	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WAIT);
+	amdgpu_ring_write(ring, reg << 2);
+	amdgpu_ring_write(ring, mask);
+	amdgpu_ring_write(ring, val);
+}
+
+static void vcn_v4_0_3_enc_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val)
+{
+	/* For VF, only local offsets should be used */
+	if (amdgpu_sriov_vf(ring->adev))
+		reg = NORMALIZE_VCN_REG_OFFSET(reg);
+
+	amdgpu_ring_write(ring, VCN_ENC_CMD_REG_WRITE);
+	amdgpu_ring_write(ring,	reg << 2);
+	amdgpu_ring_write(ring, val);
+}
+
+static void vcn_v4_0_3_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
+				unsigned int vmid, uint64_t pd_addr)
+{
+	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->vm_hub];
+
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
+
+	/* wait for reg writes */
+	vcn_v4_0_3_enc_ring_emit_reg_wait(ring, hub->ctx0_ptb_addr_lo32 +
+					vmid * hub->ctx_addr_distance,
+					lower_32_bits(pd_addr), 0xffffffff);
+}
+
 static void vcn_v4_0_3_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	/* VCN engine access for HDP flush doesn't work when RRMT is enabled.
@@ -1421,7 +1461,7 @@ static const struct amdgpu_ring_funcs vcn_v4_0_3_unified_ring_vm_funcs = {
 	.emit_ib_size = 5, /* vcn_v2_0_enc_ring_emit_ib */
 	.emit_ib = vcn_v2_0_enc_ring_emit_ib,
 	.emit_fence = vcn_v2_0_enc_ring_emit_fence,
-	.emit_vm_flush = vcn_v2_0_enc_ring_emit_vm_flush,
+	.emit_vm_flush = vcn_v4_0_3_enc_ring_emit_vm_flush,
 	.emit_hdp_flush = vcn_v4_0_3_ring_emit_hdp_flush,
 	.test_ring = amdgpu_vcn_enc_ring_test_ring,
 	.test_ib = amdgpu_vcn_unified_ring_test_ib,
@@ -1430,8 +1470,8 @@ static const struct amdgpu_ring_funcs vcn_v4_0_3_unified_ring_vm_funcs = {
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = amdgpu_vcn_ring_begin_use,
 	.end_use = amdgpu_vcn_ring_end_use,
-	.emit_wreg = vcn_v2_0_enc_ring_emit_wreg,
-	.emit_reg_wait = vcn_v2_0_enc_ring_emit_reg_wait,
+	.emit_wreg = vcn_v4_0_3_enc_ring_emit_wreg,
+	.emit_reg_wait = vcn_v4_0_3_enc_ring_emit_reg_wait,
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
-- 
2.34.1