[PATCH 04/17] drm/amdgpu: implement jpeg enc ring functions
boyuan.zhang at amd.com
boyuan.zhang at amd.com
Thu Jul 4 16:04:16 UTC 2019
From: Boyuan Zhang <boyuan.zhang at amd.com>
Implement all ring functions needed for jpeg encode ring.
Signed-off-by: Boyuan Zhang <boyuan.zhang at amd.com>
Reviewed-by: Alex Deucher <alexander.deucher at amd.com>
---
drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c | 267 ++++++++++++++++++++++++++
1 file changed, 267 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
index 4bdd73c33262..b953f6422560 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v2_0.c
@@ -1669,6 +1669,273 @@ static void vcn_v2_0_jpeg_ring_nop(struct amdgpu_ring *ring, uint32_t count)
}
}
+/**
+ * vcn_v2_0_jpeg_enc_ring_get_rptr - get read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware read pointer
+ */
+static uint64_t vcn_v2_0_jpeg_enc_ring_get_rptr(struct amdgpu_ring *ring)
+{
+ struct amdgpu_device *adev = ring->adev;
+
+ return RREG32_SOC15(UVD, 0, mmUVD_JRBC_ENC_RB_RPTR);
+}
+
+/**
+ * vcn_v2_0_jpeg_enc_ring_get_wptr - get write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware write pointer
+ */
+static uint64_t vcn_v2_0_jpeg_enc_ring_get_wptr(struct amdgpu_ring *ring)
+{
+ struct amdgpu_device *adev = ring->adev;
+
+ if (ring->use_doorbell)
+ return adev->wb.wb[ring->wptr_offs];
+ else
+ return RREG32_SOC15(UVD, 0, mmUVD_JRBC_ENC_RB_WPTR);
+}
+
+/**
+ * vcn_v2_0_jpeg_enc_ring_set_wptr - set write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the write pointer to the hardware
+ */
+static void vcn_v2_0_jpeg_enc_ring_set_wptr(struct amdgpu_ring *ring)
+{
+ struct amdgpu_device *adev = ring->adev;
+
+ if (ring->use_doorbell) {
+ adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr);
+ WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr));
+ } else
+ WREG32_SOC15(UVD, 0, mmUVD_JRBC_ENC_RB_WPTR, lower_32_bits(ring->wptr));
+}
+
+/**
+ * vcn_v2_0_jpeg_enc_ring_insert_start - insert a start command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a start command to the ring.
+ */
+static void vcn_v2_0_jpeg_enc_ring_insert_start(struct amdgpu_ring *ring)
+{
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_ENC_EXTERNAL_REG_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, 0x68e04);
+
+ amdgpu_ring_write(ring, PACKETJ(JRBC_ENC_EXTERNAL_REG_WRITE_ADDR,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, 0x80004000);
+}
+
+/**
+ * vcn_v2_0_jpeg_enc_ring_insert_end - insert a end command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a end command to the ring.
+ */
+static void vcn_v2_0_jpeg_enc_ring_insert_end(struct amdgpu_ring *ring)
+{
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_ENC_EXTERNAL_REG_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, 0x68e04);
+
+ amdgpu_ring_write(ring, PACKETJ(JRBC_ENC_EXTERNAL_REG_WRITE_ADDR,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, 0x00004000);
+}
+
+/**
+ * vcn_v2_0_jpeg_enc_ring_emit_fence - emit an fence & trap command
+ *
+ * @ring: amdgpu_ring pointer
+ * @fence: fence to emit
+ *
+ * Write a fence and a trap command to the ring.
+ */
+static void vcn_v2_0_jpeg_enc_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+ unsigned flags)
+{
+ WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JPEG_ENC_GPCOM_DATA0_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, seq);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JPEG_ENC_GPCOM_DATA1_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, seq);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_EJRBC_RB_MEM_WR_64BIT_BAR_LOW_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, lower_32_bits(addr));
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_EJRBC_RB_MEM_WR_64BIT_BAR_HIGH_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, upper_32_bits(addr));
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JPEG_ENC_GPCOM_CMD_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, 0x8);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JPEG_ENC_GPCOM_CMD_INTERNAL_OFFSET,
+ 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
+ amdgpu_ring_write(ring, 0);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_ENC_EXTERNAL_REG_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, 0x3fbc);
+
+ amdgpu_ring_write(ring, PACKETJ(JRBC_ENC_EXTERNAL_REG_WRITE_ADDR,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, 0x1);
+
+ amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE7));
+ amdgpu_ring_write(ring, 0);
+}
+
+/**
+ * vcn_v2_0_jpeg_enc_ring_emit_ib - execute indirect buffer
+ *
+ * @ring: amdgpu_ring pointer
+ * @ib: indirect buffer to execute
+ *
+ * Write ring commands to execute the indirect buffer.
+ */
+static void vcn_v2_0_jpeg_enc_ring_emit_ib(struct amdgpu_ring *ring,
+ struct amdgpu_job *job,
+ struct amdgpu_ib *ib,
+ uint32_t flags)
+{
+ unsigned vmid = AMDGPU_JOB_GET_VMID(job);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JMI_ENC_JRBC_IB_VMID_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JMI_ENC_JPEG_VMID_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_EJRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_EJRBC_IB_64BIT_BAR_HIGH_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_ENC_IB_SIZE_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, ib->length_dw);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_EJRBC_RB_MEM_RD_64BIT_BAR_LOW_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr));
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_EJRBC_RB_MEM_RD_64BIT_BAR_HIGH_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, upper_32_bits(ring->gpu_addr));
+
+ amdgpu_ring_write(ring, PACKETJ(0, 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE2));
+ amdgpu_ring_write(ring, 0);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_ENC_RB_COND_RD_TIMER_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, 0x01400200);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_ENC_RB_REF_DATA_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, 0x2);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_ENC_STATUS_INTERNAL_OFFSET,
+ 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3));
+ amdgpu_ring_write(ring, 0x2);
+}
+
+static void vcn_v2_0_jpeg_enc_ring_emit_reg_wait(struct amdgpu_ring *ring,
+ uint32_t reg, uint32_t val,
+ uint32_t mask)
+{
+ uint32_t reg_offset = (reg << 2);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_ENC_RB_COND_RD_TIMER_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, 0x01400200);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_ENC_RB_REF_DATA_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ amdgpu_ring_write(ring, val);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_ENC_EXTERNAL_REG_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ if (reg_offset >= 0x10000 && reg_offset <= 0x105ff) {
+ amdgpu_ring_write(ring, 0);
+ amdgpu_ring_write(ring,
+ PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3));
+ } else {
+ amdgpu_ring_write(ring, reg_offset);
+ amdgpu_ring_write(ring, PACKETJ(JRBC_ENC_EXTERNAL_REG_WRITE_ADDR,
+ 0, 0, PACKETJ_TYPE3));
+ }
+ amdgpu_ring_write(ring, mask);
+}
+
+static void vcn_v2_0_jpeg_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
+ unsigned vmid, uint64_t pd_addr)
+{
+ struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
+ uint32_t data0, data1, mask;
+
+ pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
+
+ /* wait for register write */
+ data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
+ data1 = lower_32_bits(pd_addr);
+ mask = 0xffffffff;
+ vcn_v2_0_jpeg_ring_emit_reg_wait(ring, data0, data1, mask);
+}
+
+static void vcn_v2_0_jpeg_enc_ring_emit_wreg(struct amdgpu_ring *ring,
+ uint32_t reg, uint32_t val)
+{
+ uint32_t reg_offset = (reg << 2);
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_JRBC_ENC_EXTERNAL_REG_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+ if (reg_offset >= 0x10000 && reg_offset <= 0x105ff) {
+ amdgpu_ring_write(ring, 0);
+ amdgpu_ring_write(ring,
+ PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0));
+ } else {
+ amdgpu_ring_write(ring, reg_offset);
+ amdgpu_ring_write(ring, PACKETJ(JRBC_ENC_EXTERNAL_REG_WRITE_ADDR,
+ 0, 0, PACKETJ_TYPE0));
+ }
+ amdgpu_ring_write(ring, val);
+}
+
+static void vcn_v2_0_jpeg_enc_ring_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+ int i;
+
+ WARN_ON(ring->wptr % 2 || count % 2);
+
+ for (i = 0; i < count / 2; i++) {
+ amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
+ amdgpu_ring_write(ring, 0);
+ }
+}
+
static int vcn_v2_0_set_interrupt_state(struct amdgpu_device *adev,
struct amdgpu_irq_src *source,
unsigned type,
--
2.17.1
More information about the amd-gfx
mailing list