/**
* radeon_vce_cs_reloc - command submission relocation
*
* @p: parser context
* @lo: address of lower dword
* @hi: address of higher dword
* @size: size of checker for relocation buffer
*
* Patch relocation inside command stream with real buffer address
*/
int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi,
unsigned size)
{
struct radeon_cs_chunk *relocs_chunk;
struct radeon_cs_reloc *reloc;
uint64_t start, end, offset;
unsigned idx;
relocs_chunk = &p->chunks[p->chunk_relocs_idx];
offset = radeon_get_ib_value(p, lo);
idx = radeon_get_ib_value(p, hi);
if (idx >= relocs_chunk->length_dw) {
DRM_ERROR("Relocs at %d after relocations chunk end %d !\n",
idx, relocs_chunk->length_dw);
return -EINVAL;
}
reloc = p->relocs_ptr[(idx / 4)];
start = reloc->gpu_offset;
end = start + radeon_bo_size(reloc->robj);
start += offset;
p->ib.ptr[lo] = start & 0xFFFFFFFF;
p->ib.ptr[hi] = start >> 32;
if (end <= start) {
DRM_ERROR("invalid reloc offset %llX!\n", offset);
return -EINVAL;
}
if ((end - start) < size) {
DRM_ERROR("buffer to small (%d / %d)!\n",
(unsigned)(end - start), size);
return -EINVAL;
}
return 0;
}
/**
* radeon_vce_cs_reloc - command submission relocation
*
* @p: parser context
* @lo: address of lower dword
* @hi: address of higher dword
*
* Patch relocation inside command stream with real buffer address
*/
int radeon_vce_cs_reloc(struct radeon_cs_parser *p, int lo, int hi)
{
struct radeon_cs_chunk *relocs_chunk;
uint64_t offset;
unsigned idx;
relocs_chunk = &p->chunks[p->chunk_relocs_idx];
offset = radeon_get_ib_value(p, lo);
idx = radeon_get_ib_value(p, hi);
if (idx >= relocs_chunk->length_dw) {
DRM_ERROR("Relocs at %d after relocations chunk end %d !\n",
idx, relocs_chunk->length_dw);
return -EINVAL;
}
offset += p->relocs_ptr[(idx / 4)]->gpu_offset;
p->ib.ptr[lo] = offset & 0xFFFFFFFF;
p->ib.ptr[hi] = offset >> 32;
return 0;
}
/**
* radeon_cs_packet_parse() - parse cp packet and point ib index to next packet
* @parser: parser structure holding parsing context.
* @pkt: where to store packet information
*
* Assume that chunk_ib_index is properly set. Will return -EINVAL
* if packet is bigger than remaining ib size. or if packets is unknown.
**/
int radeon_cs_packet_parse(struct radeon_cs_parser *p,
struct radeon_cs_packet *pkt,
unsigned idx)
{
struct radeon_cs_chunk *ib_chunk = &p->chunks[p->chunk_ib_idx];
struct radeon_device *rdev = p->rdev;
uint32_t header;
if (idx >= ib_chunk->length_dw) {
DRM_ERROR("Can not parse packet at %d after CS end %d !\n",
idx, ib_chunk->length_dw);
return -EINVAL;
}
header = radeon_get_ib_value(p, idx);
pkt->idx = idx;
pkt->type = RADEON_CP_PACKET_GET_TYPE(header);
pkt->count = RADEON_CP_PACKET_GET_COUNT(header);
pkt->one_reg_wr = 0;
switch (pkt->type) {
case RADEON_PACKET_TYPE0:
if (rdev->family < CHIP_R600) {
pkt->reg = R100_CP_PACKET0_GET_REG(header);
pkt->one_reg_wr =
RADEON_CP_PACKET0_GET_ONE_REG_WR(header);
} else
pkt->reg = R600_CP_PACKET0_GET_REG(header);
break;
case RADEON_PACKET_TYPE3:
pkt->opcode = RADEON_CP_PACKET3_GET_OPCODE(header);
break;
case RADEON_PACKET_TYPE2:
pkt->count = -1;
break;
default:
DRM_ERROR("Unknown packet type %d at %d !\n", pkt->type, idx);
return -EINVAL;
}
if ((pkt->count + 1 + pkt->idx) >= ib_chunk->length_dw) {
DRM_ERROR("Packet (%d:%d:%d) end after CS buffer (%d) !\n",
pkt->idx, pkt->type, pkt->count, ib_chunk->length_dw);
return -EINVAL;
}
return 0;
}
/**
* radeon_cs_packet_next_reloc() - parse next (should be reloc) packet
* @parser: parser structure holding parsing context.
* @data: pointer to relocation data
* @offset_start: starting offset
* @offset_mask: offset mask (to align start offset on)
* @reloc: reloc informations
*
* Check if next packet is relocation packet3, do bo validation and compute
* GPU offset using the provided start.
**/
int radeon_cs_packet_next_reloc(struct radeon_cs_parser *p,
struct radeon_cs_reloc **cs_reloc,
int nomm)
{
struct radeon_cs_chunk *relocs_chunk;
struct radeon_cs_packet p3reloc;
unsigned idx;
int r;
if (p->chunk_relocs_idx == -1) {
DRM_ERROR("No relocation chunk !\n");
return -EINVAL;
}
*cs_reloc = NULL;
relocs_chunk = &p->chunks[p->chunk_relocs_idx];
r = radeon_cs_packet_parse(p, &p3reloc, p->idx);
if (r)
return r;
p->idx += p3reloc.count + 2;
if (p3reloc.type != RADEON_PACKET_TYPE3 ||
p3reloc.opcode != RADEON_PACKET3_NOP) {
DRM_ERROR("No packet3 for relocation for packet at %d.\n",
p3reloc.idx);
radeon_cs_dump_packet(p, &p3reloc);
return -EINVAL;
}
idx = radeon_get_ib_value(p, p3reloc.idx + 1);
if (idx >= relocs_chunk->length_dw) {
DRM_ERROR("Relocs at %d after relocations chunk end %d !\n",
idx, relocs_chunk->length_dw);
radeon_cs_dump_packet(p, &p3reloc);
return -EINVAL;
}
/* FIXME: we assume reloc size is 4 dwords */
if (nomm) {
*cs_reloc = p->relocs;
(*cs_reloc)->gpu_offset =
(u64)relocs_chunk->kdata[idx + 3] << 32;
(*cs_reloc)->gpu_offset |= relocs_chunk->kdata[idx + 0];
} else
*cs_reloc = p->relocs_ptr[(idx / 4)];
return 0;
}
/**
* radeon_vce_cs_parse - parse and validate the command stream
*
* @p: parser context
*
*/
int radeon_vce_cs_parse(struct radeon_cs_parser *p)
{
uint32_t handle = 0;
bool destroy = false;
int i, r;
while (p->idx < p->chunks[p->chunk_ib_idx].length_dw) {
uint32_t len = radeon_get_ib_value(p, p->idx);
uint32_t cmd = radeon_get_ib_value(p, p->idx + 1);
if ((len < 8) || (len & 3)) {
DRM_ERROR("invalid VCE command length (%d)!\n", len);
return -EINVAL;
}
switch (cmd) {
case 0x00000001: // session
handle = radeon_get_ib_value(p, p->idx + 2);
break;
case 0x00000002: // task info
case 0x01000001: // create
case 0x04000001: // config extension
case 0x04000002: // pic control
case 0x04000005: // rate control
case 0x04000007: // motion estimation
case 0x04000008: // rdo
break;
case 0x03000001: // encode
r = radeon_vce_cs_reloc(p, p->idx + 10, p->idx + 9);
if (r)
return r;
r = radeon_vce_cs_reloc(p, p->idx + 12, p->idx + 11);
if (r)
return r;
break;
case 0x02000001: // destroy
destroy = true;
break;
case 0x05000001: // context buffer
case 0x05000004: // video bitstream buffer
case 0x05000005: // feedback buffer
r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2);
if (r)
return r;
break;
default:
DRM_ERROR("invalid VCE command (0x%x)!\n", cmd);
return -EINVAL;
}
p->idx += len / 4;
}
if (destroy) {
/* IB contains a destroy msg, free the handle */
for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i)
atomic_cmpxchg(&p->rdev->vce.handles[i], handle, 0);
return 0;
}
/* create or encode, validate the handle */
for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i) {
if (atomic_read(&p->rdev->vce.handles[i]) == handle)
return 0;
}
/* handle not found try to alloc a new one */
for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i) {
if (!atomic_cmpxchg(&p->rdev->vce.handles[i], 0, handle)) {
p->rdev->vce.filp[i] = p->filp;
return 0;
}
}
DRM_ERROR("No more free VCE handles!\n");
return -EINVAL;
}
/**
* radeon_vce_cs_parse - parse and validate the command stream
*
* @p: parser context
*
*/
int radeon_vce_cs_parse(struct radeon_cs_parser *p)
{
int session_idx = -1;
bool destroyed = false;
uint32_t tmp, handle = 0;
uint32_t *size = &tmp;
int i, r;
while (p->idx < p->chunks[p->chunk_ib_idx].length_dw) {
uint32_t len = radeon_get_ib_value(p, p->idx);
uint32_t cmd = radeon_get_ib_value(p, p->idx + 1);
if ((len < 8) || (len & 3)) {
DRM_ERROR("invalid VCE command length (%d)!\n", len);
return -EINVAL;
}
if (destroyed) {
DRM_ERROR("No other command allowed after destroy!\n");
return -EINVAL;
}
switch (cmd) {
case 0x00000001: // session
handle = radeon_get_ib_value(p, p->idx + 2);
session_idx = radeon_vce_validate_handle(p, handle);
if (session_idx < 0)
return session_idx;
size = &p->rdev->vce.img_size[session_idx];
break;
case 0x00000002: // task info
break;
case 0x01000001: // create
*size = radeon_get_ib_value(p, p->idx + 8) *
radeon_get_ib_value(p, p->idx + 10) *
8 * 3 / 2;
break;
case 0x04000001: // config extension
case 0x04000002: // pic control
case 0x04000005: // rate control
case 0x04000007: // motion estimation
case 0x04000008: // rdo
break;
case 0x03000001: // encode
r = radeon_vce_cs_reloc(p, p->idx + 10, p->idx + 9,
*size);
if (r)
return r;
r = radeon_vce_cs_reloc(p, p->idx + 12, p->idx + 11,
*size / 3);
if (r)
return r;
break;
case 0x02000001: // destroy
destroyed = true;
break;
case 0x05000001: // context buffer
r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
*size * 2);
if (r)
return r;
break;
case 0x05000004: // video bitstream buffer
tmp = radeon_get_ib_value(p, p->idx + 4);
r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
tmp);
if (r)
return r;
break;
case 0x05000005: // feedback buffer
r = radeon_vce_cs_reloc(p, p->idx + 3, p->idx + 2,
4096);
if (r)
return r;
break;
default:
DRM_ERROR("invalid VCE command (0x%x)!\n", cmd);
return -EINVAL;
}
if (session_idx == -1) {
DRM_ERROR("no session command at start of IB\n");
return -EINVAL;
}
p->idx += len / 4;
}
if (destroyed) {
/* IB contains a destroy msg, free the handle */
for (i = 0; i < RADEON_MAX_VCE_HANDLES; ++i)
atomic_cmpxchg(&p->rdev->vce.handles[i], handle, 0);
}
return 0;
}