drm/amdgpu/vcn: identify unified queue in sw init

From Boyuan Zhang
44bb8f18a63b8f2c8e089558c00e8e45bc4b0346 in linux-6.6.y/6.6.48
ecfa23c8df7ef3ea2a429dfe039341bf792e95b4 in mainline linux

diff --git a/sys/dev/pci/drm/amd/amdgpu/amdgpu_vcn.c b/sys/dev/pci/drm/amd/amdgpu/amdgpu_vcn.c
index 4e8e3d3..3d295ba 100644 (file)
--- a/sys/dev/pci/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/sys/dev/pci/drm/amd/amdgpu/amdgpu_vcn.c
@@ -135,6 +135,10 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
                }
        }
 
+       /* from vcn4 and above, only unified queue is used */
+       adev->vcn.using_unified_queue =
+               adev->ip_versions[UVD_HWIP][0] >= IP_VERSION(4, 0, 0);
+
        hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
        adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
 
@@ -259,18 +263,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
        return 0;
 }
 
-/* from vcn4 and above, only unified queue is used */
-static bool amdgpu_vcn_using_unified_queue(struct amdgpu_ring *ring)
-{
-       struct amdgpu_device *adev = ring->adev;
-       bool ret = false;
-
-       if (adev->ip_versions[UVD_HWIP][0] >= IP_VERSION(4, 0, 0))
-               ret = true;
-
-       return ret;
-}
-
 bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type type, uint32_t vcn_instance)
 {
        bool ret = false;
@@ -707,12 +699,11 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
        struct amdgpu_job *job;
        struct amdgpu_ib *ib;
        uint64_t addr = AMDGPU_GPU_PAGE_ALIGN(ib_msg->gpu_addr);
-       bool sq = amdgpu_vcn_using_unified_queue(ring);
        uint32_t *ib_checksum;
        uint32_t ib_pack_in_dw;
        int i, r;
 
-       if (sq)
+       if (adev->vcn.using_unified_queue)
                ib_size_dw += 8;
 
        r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
@@ -725,7 +716,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
        ib->length_dw = 0;
 
        /* single queue headers */
-       if (sq) {
+       if (adev->vcn.using_unified_queue) {
                ib_pack_in_dw = sizeof(struct amdgpu_vcn_decode_buffer) / sizeof(uint32_t)
                                                + 4 + 2; /* engine info + decoding ib in dw */
                ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, ib_pack_in_dw, false);
@@ -744,7 +735,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
        for (i = ib->length_dw; i < ib_size_dw; ++i)
                ib->ptr[i] = 0x0;
 
-       if (sq)
+       if (adev->vcn.using_unified_queue)
                amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, ib_pack_in_dw);
 
        r = amdgpu_job_submit_direct(job, ring, &f);
@@ -834,15 +825,15 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
                                         struct dma_fence **fence)
 {
        unsigned int ib_size_dw = 16;
+       struct amdgpu_device *adev = ring->adev;
        struct amdgpu_job *job;
        struct amdgpu_ib *ib;
        struct dma_fence *f = NULL;
        uint32_t *ib_checksum = NULL;
        uint64_t addr;
-       bool sq = amdgpu_vcn_using_unified_queue(ring);
        int i, r;
 
-       if (sq)
+       if (adev->vcn.using_unified_queue)
                ib_size_dw += 8;
 
        r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
@@ -856,7 +847,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 
        ib->length_dw = 0;
 
-       if (sq)
+       if (adev->vcn.using_unified_queue)
                ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);
 
        ib->ptr[ib->length_dw++] = 0x00000018;
@@ -878,7 +869,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
        for (i = ib->length_dw; i < ib_size_dw; ++i)
                ib->ptr[i] = 0x0;
 
-       if (sq)
+       if (adev->vcn.using_unified_queue)
                amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);
 
        r = amdgpu_job_submit_direct(job, ring, &f);
@@ -901,15 +892,15 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
                                          struct dma_fence **fence)
 {
        unsigned int ib_size_dw = 16;
+       struct amdgpu_device *adev = ring->adev;
        struct amdgpu_job *job;
        struct amdgpu_ib *ib;
        struct dma_fence *f = NULL;
        uint32_t *ib_checksum = NULL;
        uint64_t addr;
-       bool sq = amdgpu_vcn_using_unified_queue(ring);
        int i, r;
 
-       if (sq)
+       if (adev->vcn.using_unified_queue)
                ib_size_dw += 8;
 
        r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
@@ -923,7 +914,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 
        ib->length_dw = 0;
 
-       if (sq)
+       if (adev->vcn.using_unified_queue)
                ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);
 
        ib->ptr[ib->length_dw++] = 0x00000018;
@@ -945,7 +936,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
        for (i = ib->length_dw; i < ib_size_dw; ++i)
                ib->ptr[i] = 0x0;
 
-       if (sq)
+       if (adev->vcn.using_unified_queue)
                amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);
 
        r = amdgpu_job_submit_direct(job, ring, &f);

diff --git a/sys/dev/pci/drm/amd/amdgpu/amdgpu_vcn.h b/sys/dev/pci/drm/amd/amdgpu/amdgpu_vcn.h
index 20fb7ee..160c24a 100644 (file)
--- a/sys/dev/pci/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/sys/dev/pci/drm/amd/amdgpu/amdgpu_vcn.h
@@ -284,6 +284,7 @@ struct amdgpu_vcn {
 
        uint16_t inst_mask;
        uint8_t num_inst_per_aid;
+       bool using_unified_queue;
 };
 
 struct amdgpu_fw_shared_rb_ptrs_struct {