UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

drm/amdgpu: rework sdma structures 

Rework the sdma structures in the driver to
consolidate all of the sdma info into a single
structure and allow for asics that may have
different numbers of sdma instances.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Alex Deucher 2015-10-08 16:30:37 -04:00
parent 756e6880c5
commit c113ea1c4f
9 changed files with 244 additions and 257 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
drivers/gpu/drm/amd/amdgpu/amdgpu.h
View File

@ -1708,7 +1708,7 @@ struct amdgpu_vce {
/*
* SDMA
*/
struct amdgpu_sdma {
struct amdgpu_sdma_instance {
/* SDMA firmware */
const struct firmware *fw;
uint32_t fw_version;
@ -1718,6 +1718,13 @@ struct amdgpu_sdma {
bool burst_nop;
};
struct amdgpu_sdma {
struct amdgpu_sdma_instance instance[AMDGPU_MAX_SDMA_INSTANCES];
struct amdgpu_irq_src trap_irq;
struct amdgpu_irq_src illegal_inst_irq;
int num_instances;
};
/*
* Firmware
*/
@ -2064,9 +2071,7 @@ struct amdgpu_device {
struct amdgpu_gfx gfx;
/* sdma */
struct amdgpu_sdma sdma[AMDGPU_MAX_SDMA_INSTANCES];
struct amdgpu_irq_src sdma_trap_irq;
struct amdgpu_irq_src sdma_illegal_inst_irq;
struct amdgpu_sdma sdma;
/* uvd */
bool has_uvd;
@ -2203,17 +2208,18 @@ static inline void amdgpu_ring_write(struct amdgpu_ring *ring, uint32_t v)
ring->ring_free_dw--;
}
static inline struct amdgpu_sdma * amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
static inline struct amdgpu_sdma_instance *
amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
int i;
for (i = 0; i < AMDGPU_MAX_SDMA_INSTANCES; i++)
if (&adev->sdma[i].ring == ring)
for (i = 0; i < adev->sdma.num_instances; i++)
if (&adev->sdma.instance[i].ring == ring)
break;
if (i < AMDGPU_MAX_SDMA_INSTANCES)
return &adev->sdma[i];
return &adev->sdma.instance[i];
else
return NULL;
}

4
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
View File

@ -649,12 +649,12 @@ static uint16_t get_fw_version(struct kgd_dev *kgd, enum kgd_engine_type type)
case KGD_ENGINE_SDMA1:
hdr = (const union amdgpu_firmware_header *)
adev->sdma[0].fw->data;
adev->sdma.instance[0].fw->data;
break;
case KGD_ENGINE_SDMA2:
hdr = (const union amdgpu_firmware_header *)
adev->sdma[1].fw->data;
adev->sdma.instance[1].fw->data;
break;
default:

4
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
View File

@ -523,12 +523,12 @@ static uint16_t get_fw_version(struct kgd_dev *kgd, enum kgd_engine_type type)
case KGD_ENGINE_SDMA1:
hdr = (const union amdgpu_firmware_header *)
adev->sdma[0].fw->data;
adev->sdma.instance[0].fw->data;
break;
case KGD_ENGINE_SDMA2:
hdr = (const union amdgpu_firmware_header *)
adev->sdma[1].fw->data;
adev->sdma.instance[1].fw->data;
break;
default:

7
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
View File

@ -104,10 +104,11 @@ int amdgpu_cs_get_ring(struct amdgpu_device *adev, u32 ip_type,
}
break;
case AMDGPU_HW_IP_DMA:
if (ring < 2) {
*out_ring = &adev->sdma[ring].ring;
if (ring < adev->sdma.num_instances) {
*out_ring = &adev->sdma.instance[ring].ring;
} else {
DRM_ERROR("only two SDMA rings are supported\n");
DRM_ERROR("only %d SDMA rings are supported\n",
adev->sdma.num_instances);
return -EINVAL;
}
break;

10
drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
View File

@ -218,8 +218,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
break;
case AMDGPU_HW_IP_DMA:
type = AMD_IP_BLOCK_TYPE_SDMA;
ring_mask = adev->sdma[0].ring.ready ? 1 : 0;
ring_mask |= ((adev->sdma[1].ring.ready ? 1 : 0) << 1);
for (i = 0; i < adev->sdma.num_instances; i++)
ring_mask |= ((adev->sdma.instance[i].ring.ready ? 1 : 0) << i);
ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
ib_size_alignment = 1;
break;
@ -341,10 +341,10 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
fw_info.feature = 0;
break;
case AMDGPU_INFO_FW_SDMA:
if (info->query_fw.index >= 2)
if (info->query_fw.index >= adev->sdma.num_instances)
return -EINVAL;
fw_info.ver = adev->sdma[info->query_fw.index].fw_version;
fw_info.feature = adev->sdma[info->query_fw.index].feature_version;
fw_info.ver = adev->sdma.instance[info->query_fw.index].fw_version;
fw_info.feature = adev->sdma.instance[info->query_fw.index].feature_version;
break;
default:
return -EINVAL;

4
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
View File

@ -540,8 +540,8 @@ static int amdgpu_debugfs_ring_info(struct seq_file *m, void *data)
static int amdgpu_gfx_index = offsetof(struct amdgpu_device, gfx.gfx_ring[0]);
static int cayman_cp1_index = offsetof(struct amdgpu_device, gfx.compute_ring[0]);
static int cayman_cp2_index = offsetof(struct amdgpu_device, gfx.compute_ring[1]);
static int amdgpu_dma1_index = offsetof(struct amdgpu_device, sdma[0].ring);
static int amdgpu_dma2_index = offsetof(struct amdgpu_device, sdma[1].ring);
static int amdgpu_dma1_index = offsetof(struct amdgpu_device, sdma.instance[0].ring);
static int amdgpu_dma2_index = offsetof(struct amdgpu_device, sdma.instance[1].ring);
static int r600_uvd_index = offsetof(struct amdgpu_device, uvd.ring);
static int si_vce1_index = offsetof(struct amdgpu_device, vce.ring[0]);
static int si_vce2_index = offsetof(struct amdgpu_device, vce.ring[1]);

130
drivers/gpu/drm/amd/amdgpu/cik_sdma.c
View File

@ -96,7 +96,7 @@ static int cik_sdma_init_microcode(struct amdgpu_device *adev)
{
const char *chip_name;
char fw_name[30];
int err, i;
int err = 0, i;
DRM_DEBUG("\n");
@ -119,24 +119,24 @@ static int cik_sdma_init_microcode(struct amdgpu_device *adev)
default: BUG();
}
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
if (i == 0)
snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma.bin", chip_name);
else
snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma1.bin", chip_name);
err = request_firmware(&adev->sdma[i].fw, fw_name, adev->dev);
err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev);
if (err)
goto out;
err = amdgpu_ucode_validate(adev->sdma[i].fw);
err = amdgpu_ucode_validate(adev->sdma.instance[i].fw);
}
out:
if (err) {
printk(KERN_ERR
"cik_sdma: Failed to load firmware \"%s\"\n",
fw_name);
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
release_firmware(adev->sdma[i].fw);
adev->sdma[i].fw = NULL;
for (i = 0; i < adev->sdma.num_instances; i++) {
release_firmware(adev->sdma.instance[i].fw);
adev->sdma.instance[i].fw = NULL;
}
}
return err;
@ -168,7 +168,7 @@ static uint32_t cik_sdma_ring_get_rptr(struct amdgpu_ring *ring)
static uint32_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
u32 me = (ring == &adev->sdma[0].ring) ? 0 : 1;
u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
return (RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) & 0x3fffc) >> 2;
}
@ -183,14 +183,14 @@ static uint32_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring)
static void cik_sdma_ring_set_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
u32 me = (ring == &adev->sdma[0].ring) ? 0 : 1;
u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], (ring->wptr << 2) & 0x3fffc);
}
static void cik_sdma_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
{
struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ring);
struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ring);
int i;
for (i = 0; i < count; i++)
@ -248,7 +248,7 @@ static void cik_sdma_ring_emit_hdp_flush(struct amdgpu_ring *ring)
SDMA_POLL_REG_MEM_EXTRA_FUNC(3)); /* == */
u32 ref_and_mask;
if (ring == &ring->adev->sdma[0].ring)
if (ring == &ring->adev->sdma.instance[0].ring)
ref_and_mask = GPU_HDP_FLUSH_DONE__SDMA0_MASK;
else
ref_and_mask = GPU_HDP_FLUSH_DONE__SDMA1_MASK;
@ -327,8 +327,8 @@ static bool cik_sdma_ring_emit_semaphore(struct amdgpu_ring *ring,
*/
static void cik_sdma_gfx_stop(struct amdgpu_device *adev)
{
struct amdgpu_ring *sdma0 = &adev->sdma[0].ring;
struct amdgpu_ring *sdma1 = &adev->sdma[1].ring;
struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring;
struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring;
u32 rb_cntl;
int i;
@ -336,7 +336,7 @@ static void cik_sdma_gfx_stop(struct amdgpu_device *adev)
(adev->mman.buffer_funcs_ring == sdma1))
amdgpu_ttm_set_active_vram_size(adev, adev->mc.visible_vram_size);
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]);
rb_cntl &= ~SDMA0_GFX_RB_CNTL__RB_ENABLE_MASK;
WREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i], rb_cntl);
@ -376,7 +376,7 @@ static void cik_sdma_enable(struct amdgpu_device *adev, bool enable)
cik_sdma_rlc_stop(adev);
}
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
me_cntl = RREG32(mmSDMA0_F32_CNTL + sdma_offsets[i]);
if (enable)
me_cntl &= ~SDMA0_F32_CNTL__HALT_MASK;
@ -402,8 +402,8 @@ static int cik_sdma_gfx_resume(struct amdgpu_device *adev)
u32 wb_offset;
int i, j, r;
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
ring = &adev->sdma[i].ring;
for (i = 0; i < adev->sdma.num_instances; i++) {
ring = &adev->sdma.instance[i].ring;
wb_offset = (ring->rptr_offs * 4);
mutex_lock(&adev->srbm_mutex);
@ -502,26 +502,25 @@ static int cik_sdma_load_microcode(struct amdgpu_device *adev)
u32 fw_size;
int i, j;
if (!adev->sdma[0].fw || !adev->sdma[1].fw)
return -EINVAL;
/* halt the MEs */
cik_sdma_enable(adev, false);
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
for (i = 0; i < adev->sdma.num_instances; i++) {
if (!adev->sdma.instance[i].fw)
return -EINVAL;
hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
amdgpu_ucode_print_sdma_hdr(&hdr->header);
fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
if (adev->sdma[i].feature_version >= 20)
adev->sdma[i].burst_nop = true;
adev->sdma.instance[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
adev->sdma.instance[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
if (adev->sdma.instance[i].feature_version >= 20)
adev->sdma.instance[i].burst_nop = true;
fw_data = (const __le32 *)
(adev->sdma[i].fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes));
(adev->sdma.instance[i].fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes));
WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
for (j = 0; j < fw_size; j++)
WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++));
WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma[i].fw_version);
WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma.instance[i].fw_version);
}
return 0;
@ -830,7 +829,7 @@ static void cik_sdma_vm_set_pte_pde(struct amdgpu_ib *ib,
*/
static void cik_sdma_vm_pad_ib(struct amdgpu_ib *ib)
{
struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ib->ring);
struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ib->ring);
u32 pad_count;
int i;
@ -934,6 +933,8 @@ static int cik_sdma_early_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
adev->sdma.num_instances = SDMA_MAX_INSTANCE;
cik_sdma_set_ring_funcs(adev);
cik_sdma_set_irq_funcs(adev);
cik_sdma_set_buffer_funcs(adev);
@ -946,7 +947,7 @@ static int cik_sdma_sw_init(void *handle)
{
struct amdgpu_ring *ring;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int r;
int r, i;
r = cik_sdma_init_microcode(adev);
if (r) {
@ -955,43 +956,33 @@ static int cik_sdma_sw_init(void *handle)
}
/* SDMA trap event */
r = amdgpu_irq_add_id(adev, 224, &adev->sdma_trap_irq);
r = amdgpu_irq_add_id(adev, 224, &adev->sdma.trap_irq);
if (r)
return r;
/* SDMA Privileged inst */
r = amdgpu_irq_add_id(adev, 241, &adev->sdma_illegal_inst_irq);
r = amdgpu_irq_add_id(adev, 241, &adev->sdma.illegal_inst_irq);
if (r)
return r;
/* SDMA Privileged inst */
r = amdgpu_irq_add_id(adev, 247, &adev->sdma_illegal_inst_irq);
r = amdgpu_irq_add_id(adev, 247, &adev->sdma.illegal_inst_irq);
if (r)
return r;
ring = &adev->sdma[0].ring;
ring->ring_obj = NULL;
ring = &adev->sdma[1].ring;
ring->ring_obj = NULL;
ring = &adev->sdma[0].ring;
sprintf(ring->name, "sdma0");
r = amdgpu_ring_init(adev, ring, 256 * 1024,
SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0), 0xf,
&adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP0,
AMDGPU_RING_TYPE_SDMA);
if (r)
return r;
ring = &adev->sdma[1].ring;
sprintf(ring->name, "sdma1");
r = amdgpu_ring_init(adev, ring, 256 * 1024,
SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0), 0xf,
&adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP1,
AMDGPU_RING_TYPE_SDMA);
if (r)
return r;
for (i = 0; i < adev->sdma.num_instances; i++) {
ring = &adev->sdma.instance[i].ring;
ring->ring_obj = NULL;
sprintf(ring->name, "sdma%d", i);
r = amdgpu_ring_init(adev, ring, 256 * 1024,
SDMA_PACKET(SDMA_OPCODE_NOP, 0, 0), 0xf,
&adev->sdma.trap_irq,
(i == 0) ?
AMDGPU_SDMA_IRQ_TRAP0 : AMDGPU_SDMA_IRQ_TRAP1,
AMDGPU_RING_TYPE_SDMA);
if (r)
return r;
}
return r;
}
@ -999,9 +990,10 @@ static int cik_sdma_sw_init(void *handle)
static int cik_sdma_sw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int i;
amdgpu_ring_fini(&adev->sdma[0].ring);
amdgpu_ring_fini(&adev->sdma[1].ring);
for (i = 0; i < adev->sdma.num_instances; i++)
amdgpu_ring_fini(&adev->sdma.instance[i].ring);
return 0;
}
@ -1078,7 +1070,7 @@ static void cik_sdma_print_status(void *handle)
dev_info(adev->dev, "CIK SDMA registers\n");
dev_info(adev->dev, " SRBM_STATUS2=0x%08X\n",
RREG32(mmSRBM_STATUS2));
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
dev_info(adev->dev, " SDMA%d_STATUS_REG=0x%08X\n",
i, RREG32(mmSDMA0_STATUS_REG + sdma_offsets[i]));
dev_info(adev->dev, " SDMA%d_ME_CNTL=0x%08X\n",
@ -1223,7 +1215,7 @@ static int cik_sdma_process_trap_irq(struct amdgpu_device *adev,
case 0:
switch (queue_id) {
case 0:
amdgpu_fence_process(&adev->sdma[0].ring);
amdgpu_fence_process(&adev->sdma.instance[0].ring);
break;
case 1:
/* XXX compute */
@ -1236,7 +1228,7 @@ static int cik_sdma_process_trap_irq(struct amdgpu_device *adev,
case 1:
switch (queue_id) {
case 0:
amdgpu_fence_process(&adev->sdma[1].ring);
amdgpu_fence_process(&adev->sdma.instance[1].ring);
break;
case 1:
/* XXX compute */
@ -1334,8 +1326,10 @@ static const struct amdgpu_ring_funcs cik_sdma_ring_funcs = {
static void cik_sdma_set_ring_funcs(struct amdgpu_device *adev)
{
adev->sdma[0].ring.funcs = &cik_sdma_ring_funcs;
adev->sdma[1].ring.funcs = &cik_sdma_ring_funcs;
int i;
for (i = 0; i < adev->sdma.num_instances; i++)
adev->sdma.instance[i].ring.funcs = &cik_sdma_ring_funcs;
}
static const struct amdgpu_irq_src_funcs cik_sdma_trap_irq_funcs = {
@ -1349,9 +1343,9 @@ static const struct amdgpu_irq_src_funcs cik_sdma_illegal_inst_irq_funcs = {
static void cik_sdma_set_irq_funcs(struct amdgpu_device *adev)
{
adev->sdma_trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
adev->sdma_trap_irq.funcs = &cik_sdma_trap_irq_funcs;
adev->sdma_illegal_inst_irq.funcs = &cik_sdma_illegal_inst_irq_funcs;
adev->sdma.trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
adev->sdma.trap_irq.funcs = &cik_sdma_trap_irq_funcs;
adev->sdma.illegal_inst_irq.funcs = &cik_sdma_illegal_inst_irq_funcs;
}
/**
@ -1416,7 +1410,7 @@ static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev)
{
if (adev->mman.buffer_funcs == NULL) {
adev->mman.buffer_funcs = &cik_sdma_buffer_funcs;
adev->mman.buffer_funcs_ring = &adev->sdma[0].ring;
adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
}
}
@ -1431,7 +1425,7 @@ static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev)
{
if (adev->vm_manager.vm_pte_funcs == NULL) {
adev->vm_manager.vm_pte_funcs = &cik_sdma_vm_pte_funcs;
adev->vm_manager.vm_pte_funcs_ring = &adev->sdma[0].ring;
adev->vm_manager.vm_pte_funcs_ring = &adev->sdma.instance[0].ring;
adev->vm_manager.vm_pte_funcs_ring->is_pte_ring = true;
}
}

156
drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
View File

@ -118,7 +118,7 @@ static int sdma_v2_4_init_microcode(struct amdgpu_device *adev)
{
const char *chip_name;
char fw_name[30];
int err, i;
int err = 0, i;
struct amdgpu_firmware_info *info = NULL;
const struct common_firmware_header *header = NULL;
const struct sdma_firmware_header_v1_0 *hdr;
@ -132,27 +132,27 @@ static int sdma_v2_4_init_microcode(struct amdgpu_device *adev)
default: BUG();
}
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
if (i == 0)
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name);
else
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name);
err = request_firmware(&adev->sdma[i].fw, fw_name, adev->dev);
err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev);
if (err)
goto out;
err = amdgpu_ucode_validate(adev->sdma[i].fw);
err = amdgpu_ucode_validate(adev->sdma.instance[i].fw);
if (err)
goto out;
hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
if (adev->sdma[i].feature_version >= 20)
adev->sdma[i].burst_nop = true;
hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
adev->sdma.instance[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
adev->sdma.instance[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
if (adev->sdma.instance[i].feature_version >= 20)
adev->sdma.instance[i].burst_nop = true;
if (adev->firmware.smu_load) {
info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i];
info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i;
info->fw = adev->sdma[i].fw;
info->fw = adev->sdma.instance[i].fw;
header = (const struct common_firmware_header *)info->fw->data;
adev->firmware.fw_size +=
ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
@ -164,9 +164,9 @@ out:
printk(KERN_ERR
"sdma_v2_4: Failed to load firmware \"%s\"\n",
fw_name);
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
release_firmware(adev->sdma[i].fw);
adev->sdma[i].fw = NULL;
for (i = 0; i < adev->sdma.num_instances; i++) {
release_firmware(adev->sdma.instance[i].fw);
adev->sdma.instance[i].fw = NULL;
}
}
return err;
@ -199,7 +199,7 @@ static uint32_t sdma_v2_4_ring_get_rptr(struct amdgpu_ring *ring)
static uint32_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
int me = (ring == &ring->adev->sdma[0].ring) ? 0 : 1;
int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
u32 wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) >> 2;
return wptr;
@ -215,14 +215,14 @@ static uint32_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring)
static void sdma_v2_4_ring_set_wptr(struct amdgpu_ring *ring)
{
struct amdgpu_device *adev = ring->adev;
int me = (ring == &ring->adev->sdma[0].ring) ? 0 : 1;
int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], ring->wptr << 2);
}
static void sdma_v2_4_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
{
struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ring);
struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ring);
int i;
for (i = 0; i < count; i++)
@ -284,7 +284,7 @@ static void sdma_v2_4_ring_emit_hdp_flush(struct amdgpu_ring *ring)
{
u32 ref_and_mask = 0;
if (ring == &ring->adev->sdma[0].ring)
if (ring == &ring->adev->sdma.instance[0].ring)
ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA0, 1);
else
ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA1, 1);
@ -368,8 +368,8 @@ static bool sdma_v2_4_ring_emit_semaphore(struct amdgpu_ring *ring,
*/
static void sdma_v2_4_gfx_stop(struct amdgpu_device *adev)
{
struct amdgpu_ring *sdma0 = &adev->sdma[0].ring;
struct amdgpu_ring *sdma1 = &adev->sdma[1].ring;
struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring;
struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring;
u32 rb_cntl, ib_cntl;
int i;
@ -377,7 +377,7 @@ static void sdma_v2_4_gfx_stop(struct amdgpu_device *adev)
(adev->mman.buffer_funcs_ring == sdma1))
amdgpu_ttm_set_active_vram_size(adev, adev->mc.visible_vram_size);
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]);
rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0);
WREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i], rb_cntl);
@ -419,7 +419,7 @@ static void sdma_v2_4_enable(struct amdgpu_device *adev, bool enable)
sdma_v2_4_rlc_stop(adev);
}
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
f32_cntl = RREG32(mmSDMA0_F32_CNTL + sdma_offsets[i]);
if (enable)
f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, 0);
@ -445,8 +445,8 @@ static int sdma_v2_4_gfx_resume(struct amdgpu_device *adev)
u32 wb_offset;
int i, j, r;
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
ring = &adev->sdma[i].ring;
for (i = 0; i < adev->sdma.num_instances; i++) {
ring = &adev->sdma.instance[i].ring;
wb_offset = (ring->rptr_offs * 4);
mutex_lock(&adev->srbm_mutex);
@ -545,29 +545,23 @@ static int sdma_v2_4_load_microcode(struct amdgpu_device *adev)
const __le32 *fw_data;
u32 fw_size;
int i, j;
bool smc_loads_fw = false; /* XXX fix me */
if (!adev->sdma[0].fw || !adev->sdma[1].fw)
return -EINVAL;
/* halt the MEs */
sdma_v2_4_enable(adev, false);
if (smc_loads_fw) {
/* XXX query SMC for fw load complete */
} else {
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
amdgpu_ucode_print_sdma_hdr(&hdr->header);
fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
fw_data = (const __le32 *)
(adev->sdma[i].fw->data +
le32_to_cpu(hdr->header.ucode_array_offset_bytes));
WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
for (j = 0; j < fw_size; j++)
WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++));
WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma[i].fw_version);
}
for (i = 0; i < adev->sdma.num_instances; i++) {
if (!adev->sdma.instance[i].fw)
return -EINVAL;
hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
amdgpu_ucode_print_sdma_hdr(&hdr->header);
fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
fw_data = (const __le32 *)
(adev->sdma.instance[i].fw->data +
le32_to_cpu(hdr->header.ucode_array_offset_bytes));
WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
for (j = 0; j < fw_size; j++)
WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++));
WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma.instance[i].fw_version);
}
return 0;
@ -894,7 +888,7 @@ static void sdma_v2_4_vm_set_pte_pde(struct amdgpu_ib *ib,
*/
static void sdma_v2_4_vm_pad_ib(struct amdgpu_ib *ib)
{
struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ib->ring);
struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ib->ring);
u32 pad_count;
int i;
@ -952,6 +946,8 @@ static int sdma_v2_4_early_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
adev->sdma.num_instances = SDMA_MAX_INSTANCE;
sdma_v2_4_set_ring_funcs(adev);
sdma_v2_4_set_buffer_funcs(adev);
sdma_v2_4_set_vm_pte_funcs(adev);
@ -963,21 +959,21 @@ static int sdma_v2_4_early_init(void *handle)
static int sdma_v2_4_sw_init(void *handle)
{
struct amdgpu_ring *ring;
int r;
int r, i;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
/* SDMA trap event */
r = amdgpu_irq_add_id(adev, 224, &adev->sdma_trap_irq);
r = amdgpu_irq_add_id(adev, 224, &adev->sdma.trap_irq);
if (r)
return r;
/* SDMA Privileged inst */
r = amdgpu_irq_add_id(adev, 241, &adev->sdma_illegal_inst_irq);
r = amdgpu_irq_add_id(adev, 241, &adev->sdma.illegal_inst_irq);
if (r)
return r;
/* SDMA Privileged inst */
r = amdgpu_irq_add_id(adev, 247, &adev->sdma_illegal_inst_irq);
r = amdgpu_irq_add_id(adev, 247, &adev->sdma.illegal_inst_irq);
if (r)
return r;
@ -987,31 +983,20 @@ static int sdma_v2_4_sw_init(void *handle)
return r;
}
ring = &adev->sdma[0].ring;
ring->ring_obj = NULL;
ring->use_doorbell = false;
ring = &adev->sdma[1].ring;
ring->ring_obj = NULL;
ring->use_doorbell = false;
ring = &adev->sdma[0].ring;
sprintf(ring->name, "sdma0");
r = amdgpu_ring_init(adev, ring, 256 * 1024,
SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf,
&adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP0,
AMDGPU_RING_TYPE_SDMA);
if (r)
return r;
ring = &adev->sdma[1].ring;
sprintf(ring->name, "sdma1");
r = amdgpu_ring_init(adev, ring, 256 * 1024,
SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf,
&adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP1,
AMDGPU_RING_TYPE_SDMA);
if (r)
return r;
for (i = 0; i < adev->sdma.num_instances; i++) {
ring = &adev->sdma.instance[i].ring;
ring->ring_obj = NULL;
ring->use_doorbell = false;
sprintf(ring->name, "sdma%d", i);
r = amdgpu_ring_init(adev, ring, 256 * 1024,
SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf,
&adev->sdma.trap_irq,
(i == 0) ?
AMDGPU_SDMA_IRQ_TRAP0 : AMDGPU_SDMA_IRQ_TRAP1,
AMDGPU_RING_TYPE_SDMA);
if (r)
return r;
}
return r;
}
@ -1019,9 +1004,10 @@ static int sdma_v2_4_sw_init(void *handle)
static int sdma_v2_4_sw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int i;
amdgpu_ring_fini(&adev->sdma[0].ring);
amdgpu_ring_fini(&adev->sdma[1].ring);
for (i = 0; i < adev->sdma.num_instances; i++)
amdgpu_ring_fini(&adev->sdma.instance[i].ring);
return 0;
}
@ -1100,7 +1086,7 @@ static void sdma_v2_4_print_status(void *handle)
dev_info(adev->dev, "VI SDMA registers\n");
dev_info(adev->dev, " SRBM_STATUS2=0x%08X\n",
RREG32(mmSRBM_STATUS2));
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
dev_info(adev->dev, " SDMA%d_STATUS_REG=0x%08X\n",
i, RREG32(mmSDMA0_STATUS_REG + sdma_offsets[i]));
dev_info(adev->dev, " SDMA%d_F32_CNTL=0x%08X\n",
@ -1243,7 +1229,7 @@ static int sdma_v2_4_process_trap_irq(struct amdgpu_device *adev,
case 0:
switch (queue_id) {
case 0:
amdgpu_fence_process(&adev->sdma[0].ring);
amdgpu_fence_process(&adev->sdma.instance[0].ring);
break;
case 1:
/* XXX compute */
@ -1256,7 +1242,7 @@ static int sdma_v2_4_process_trap_irq(struct amdgpu_device *adev,
case 1:
switch (queue_id) {
case 0:
amdgpu_fence_process(&adev->sdma[1].ring);
amdgpu_fence_process(&adev->sdma.instance[1].ring);
break;
case 1:
/* XXX compute */
@ -1345,8 +1331,10 @@ static const struct amdgpu_ring_funcs sdma_v2_4_ring_funcs = {
static void sdma_v2_4_set_ring_funcs(struct amdgpu_device *adev)
{
adev->sdma[0].ring.funcs = &sdma_v2_4_ring_funcs;
adev->sdma[1].ring.funcs = &sdma_v2_4_ring_funcs;
int i;
for (i = 0; i < adev->sdma.num_instances; i++)
adev->sdma.instance[i].ring.funcs = &sdma_v2_4_ring_funcs;
}
static const struct amdgpu_irq_src_funcs sdma_v2_4_trap_irq_funcs = {
@ -1360,9 +1348,9 @@ static const struct amdgpu_irq_src_funcs sdma_v2_4_illegal_inst_irq_funcs = {
static void sdma_v2_4_set_irq_funcs(struct amdgpu_device *adev)
{
adev->sdma_trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
adev->sdma_trap_irq.funcs = &sdma_v2_4_trap_irq_funcs;
adev->sdma_illegal_inst_irq.funcs = &sdma_v2_4_illegal_inst_irq_funcs;
adev->sdma.trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
adev->sdma.trap_irq.funcs = &sdma_v2_4_trap_irq_funcs;
adev->sdma.illegal_inst_irq.funcs = &sdma_v2_4_illegal_inst_irq_funcs;
}
/**
@ -1428,7 +1416,7 @@ static void sdma_v2_4_set_buffer_funcs(struct amdgpu_device *adev)
{
if (adev->mman.buffer_funcs == NULL) {
adev->mman.buffer_funcs = &sdma_v2_4_buffer_funcs;
adev->mman.buffer_funcs_ring = &adev->sdma[0].ring;
adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
}
}
@ -1443,7 +1431,7 @@ static void sdma_v2_4_set_vm_pte_funcs(struct amdgpu_device *adev)
{
if (adev->vm_manager.vm_pte_funcs == NULL) {
adev->vm_manager.vm_pte_funcs = &sdma_v2_4_vm_pte_funcs;
adev->vm_manager.vm_pte_funcs_ring = &adev->sdma[0].ring;
adev->vm_manager.vm_pte_funcs_ring = &adev->sdma.instance[0].ring;
adev->vm_manager.vm_pte_funcs_ring->is_pte_ring = true;
}
}

164
drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
View File

@ -184,7 +184,7 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev)
{
const char *chip_name;
char fw_name[30];
int err, i;
int err = 0, i;
struct amdgpu_firmware_info *info = NULL;
const struct common_firmware_header *header = NULL;
const struct sdma_firmware_header_v1_0 *hdr;
@ -204,27 +204,27 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev)
default: BUG();
}
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
if (i == 0)
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name);
else
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name);
err = request_firmware(&adev->sdma[i].fw, fw_name, adev->dev);
err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev);
if (err)
goto out;
err = amdgpu_ucode_validate(adev->sdma[i].fw);
err = amdgpu_ucode_validate(adev->sdma.instance[i].fw);
if (err)
goto out;
hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
if (adev->sdma[i].feature_version >= 20)
adev->sdma[i].burst_nop = true;
hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
adev->sdma.instance[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
adev->sdma.instance[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
if (adev->sdma.instance[i].feature_version >= 20)
adev->sdma.instance[i].burst_nop = true;
if (adev->firmware.smu_load) {
info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i];
info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i;
info->fw = adev->sdma[i].fw;
info->fw = adev->sdma.instance[i].fw;
header = (const struct common_firmware_header *)info->fw->data;
adev->firmware.fw_size +=
ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
@ -235,9 +235,9 @@ out:
printk(KERN_ERR
"sdma_v3_0: Failed to load firmware \"%s\"\n",
fw_name);
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
release_firmware(adev->sdma[i].fw);
adev->sdma[i].fw = NULL;
for (i = 0; i < adev->sdma.num_instances; i++) {
release_firmware(adev->sdma.instance[i].fw);
adev->sdma.instance[i].fw = NULL;
}
}
return err;
@ -276,7 +276,7 @@ static uint32_t sdma_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
/* XXX check if swapping is necessary on BE */
wptr = ring->adev->wb.wb[ring->wptr_offs] >> 2;
} else {
int me = (ring == &ring->adev->sdma[0].ring) ? 0 : 1;
int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) >> 2;
}
@ -300,7 +300,7 @@ static void sdma_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
adev->wb.wb[ring->wptr_offs] = ring->wptr << 2;
WDOORBELL32(ring->doorbell_index, ring->wptr << 2);
} else {
int me = (ring == &ring->adev->sdma[0].ring) ? 0 : 1;
int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], ring->wptr << 2);
}
@ -308,7 +308,7 @@ static void sdma_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
static void sdma_v3_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
{
struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ring);
struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ring);
int i;
for (i = 0; i < count; i++)
@ -369,7 +369,7 @@ static void sdma_v3_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
{
u32 ref_and_mask = 0;
if (ring == &ring->adev->sdma[0].ring)
if (ring == &ring->adev->sdma.instance[0].ring)
ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA0, 1);
else
ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA1, 1);
@ -454,8 +454,8 @@ static bool sdma_v3_0_ring_emit_semaphore(struct amdgpu_ring *ring,
*/
static void sdma_v3_0_gfx_stop(struct amdgpu_device *adev)
{
struct amdgpu_ring *sdma0 = &adev->sdma[0].ring;
struct amdgpu_ring *sdma1 = &adev->sdma[1].ring;
struct amdgpu_ring *sdma0 = &adev->sdma.instance[0].ring;
struct amdgpu_ring *sdma1 = &adev->sdma.instance[1].ring;
u32 rb_cntl, ib_cntl;
int i;
@ -463,7 +463,7 @@ static void sdma_v3_0_gfx_stop(struct amdgpu_device *adev)
(adev->mman.buffer_funcs_ring == sdma1))
amdgpu_ttm_set_active_vram_size(adev, adev->mc.visible_vram_size);
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
rb_cntl = RREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i]);
rb_cntl = REG_SET_FIELD(rb_cntl, SDMA0_GFX_RB_CNTL, RB_ENABLE, 0);
WREG32(mmSDMA0_GFX_RB_CNTL + sdma_offsets[i], rb_cntl);
@ -500,7 +500,7 @@ static void sdma_v3_0_ctx_switch_enable(struct amdgpu_device *adev, bool enable)
u32 f32_cntl;
int i;
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
f32_cntl = RREG32(mmSDMA0_CNTL + sdma_offsets[i]);
if (enable)
f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_CNTL,
@ -530,7 +530,7 @@ static void sdma_v3_0_enable(struct amdgpu_device *adev, bool enable)
sdma_v3_0_rlc_stop(adev);
}
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
f32_cntl = RREG32(mmSDMA0_F32_CNTL + sdma_offsets[i]);
if (enable)
f32_cntl = REG_SET_FIELD(f32_cntl, SDMA0_F32_CNTL, HALT, 0);
@ -557,8 +557,8 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev)
u32 doorbell;
int i, j, r;
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
ring = &adev->sdma[i].ring;
for (i = 0; i < adev->sdma.num_instances; i++) {
ring = &adev->sdma.instance[i].ring;
wb_offset = (ring->rptr_offs * 4);
mutex_lock(&adev->srbm_mutex);
@ -669,23 +669,22 @@ static int sdma_v3_0_load_microcode(struct amdgpu_device *adev)
u32 fw_size;
int i, j;
if (!adev->sdma[0].fw || !adev->sdma[1].fw)
return -EINVAL;
/* halt the MEs */
sdma_v3_0_enable(adev, false);
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
for (i = 0; i < adev->sdma.num_instances; i++) {
if (!adev->sdma.instance[i].fw)
return -EINVAL;
hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
amdgpu_ucode_print_sdma_hdr(&hdr->header);
fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
fw_data = (const __le32 *)
(adev->sdma[i].fw->data +
(adev->sdma.instance[i].fw->data +
le32_to_cpu(hdr->header.ucode_array_offset_bytes));
WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
for (j = 0; j < fw_size; j++)
WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++));
WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma[i].fw_version);
WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma.instance[i].fw_version);
}
return 0;
@ -701,21 +700,21 @@ static int sdma_v3_0_load_microcode(struct amdgpu_device *adev)
*/
static int sdma_v3_0_start(struct amdgpu_device *adev)
{
int r;
int r, i;
if (!adev->firmware.smu_load) {
r = sdma_v3_0_load_microcode(adev);
if (r)
return r;
} else {
r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
AMDGPU_UCODE_ID_SDMA0);
if (r)
return -EINVAL;
r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
AMDGPU_UCODE_ID_SDMA1);
if (r)
return -EINVAL;
for (i = 0; i < adev->sdma.num_instances; i++) {
r = adev->smu.smumgr_funcs->check_fw_load_finish(adev,
(i == 0) ?
AMDGPU_UCODE_ID_SDMA0 :
AMDGPU_UCODE_ID_SDMA1);
if (r)
return -EINVAL;
}
}
/* unhalt the MEs */
@ -1013,7 +1012,7 @@ static void sdma_v3_0_vm_set_pte_pde(struct amdgpu_ib *ib,
*/
static void sdma_v3_0_vm_pad_ib(struct amdgpu_ib *ib)
{
struct amdgpu_sdma *sdma = amdgpu_get_sdma_instance(ib->ring);
struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ib->ring);
u32 pad_count;
int i;
@ -1071,6 +1070,12 @@ static int sdma_v3_0_early_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
switch (adev->asic_type) {
default:
adev->sdma.num_instances = SDMA_MAX_INSTANCE;
break;
}
sdma_v3_0_set_ring_funcs(adev);
sdma_v3_0_set_buffer_funcs(adev);
sdma_v3_0_set_vm_pte_funcs(adev);
@ -1082,21 +1087,21 @@ static int sdma_v3_0_early_init(void *handle)
static int sdma_v3_0_sw_init(void *handle)
{
struct amdgpu_ring *ring;
int r;
int r, i;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
/* SDMA trap event */
r = amdgpu_irq_add_id(adev, 224, &adev->sdma_trap_irq);
r = amdgpu_irq_add_id(adev, 224, &adev->sdma.trap_irq);
if (r)
return r;
/* SDMA Privileged inst */
r = amdgpu_irq_add_id(adev, 241, &adev->sdma_illegal_inst_irq);
r = amdgpu_irq_add_id(adev, 241, &adev->sdma.illegal_inst_irq);
if (r)
return r;
/* SDMA Privileged inst */
r = amdgpu_irq_add_id(adev, 247, &adev->sdma_illegal_inst_irq);
r = amdgpu_irq_add_id(adev, 247, &adev->sdma.illegal_inst_irq);
if (r)
return r;
@ -1106,33 +1111,23 @@ static int sdma_v3_0_sw_init(void *handle)
return r;
}
ring = &adev->sdma[0].ring;
ring->ring_obj = NULL;
ring->use_doorbell = true;
ring->doorbell_index = AMDGPU_DOORBELL_sDMA_ENGINE0;
for (i = 0; i < adev->sdma.num_instances; i++) {
ring = &adev->sdma.instance[i].ring;
ring->ring_obj = NULL;
ring->use_doorbell = true;
ring->doorbell_index = (i == 0) ?
AMDGPU_DOORBELL_sDMA_ENGINE0 : AMDGPU_DOORBELL_sDMA_ENGINE1;
ring = &adev->sdma[1].ring;
ring->ring_obj = NULL;
ring->use_doorbell = true;
ring->doorbell_index = AMDGPU_DOORBELL_sDMA_ENGINE1;
ring = &adev->sdma[0].ring;
sprintf(ring->name, "sdma0");
r = amdgpu_ring_init(adev, ring, 256 * 1024,
SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf,
&adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP0,
AMDGPU_RING_TYPE_SDMA);
if (r)
return r;
ring = &adev->sdma[1].ring;
sprintf(ring->name, "sdma1");
r = amdgpu_ring_init(adev, ring, 256 * 1024,
SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf,
&adev->sdma_trap_irq, AMDGPU_SDMA_IRQ_TRAP1,
AMDGPU_RING_TYPE_SDMA);
if (r)
return r;
sprintf(ring->name, "sdma%d", i);
r = amdgpu_ring_init(adev, ring, 256 * 1024,
SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), 0xf,
&adev->sdma.trap_irq,
(i == 0) ?
AMDGPU_SDMA_IRQ_TRAP0 : AMDGPU_SDMA_IRQ_TRAP1,
AMDGPU_RING_TYPE_SDMA);
if (r)
return r;
}
return r;
}
@ -1140,9 +1135,10 @@ static int sdma_v3_0_sw_init(void *handle)
static int sdma_v3_0_sw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
int i;
amdgpu_ring_fini(&adev->sdma[0].ring);
amdgpu_ring_fini(&adev->sdma[1].ring);
for (i = 0; i < adev->sdma.num_instances; i++)
amdgpu_ring_fini(&adev->sdma.instance[i].ring);
return 0;
}
@ -1222,7 +1218,7 @@ static void sdma_v3_0_print_status(void *handle)
dev_info(adev->dev, "VI SDMA registers\n");
dev_info(adev->dev, " SRBM_STATUS2=0x%08X\n",
RREG32(mmSRBM_STATUS2));
for (i = 0; i < SDMA_MAX_INSTANCE; i++) {
for (i = 0; i < adev->sdma.num_instances; i++) {
dev_info(adev->dev, " SDMA%d_STATUS_REG=0x%08X\n",
i, RREG32(mmSDMA0_STATUS_REG + sdma_offsets[i]));
dev_info(adev->dev, " SDMA%d_F32_CNTL=0x%08X\n",
@ -1367,7 +1363,7 @@ static int sdma_v3_0_process_trap_irq(struct amdgpu_device *adev,
case 0:
switch (queue_id) {
case 0:
amdgpu_fence_process(&adev->sdma[0].ring);
amdgpu_fence_process(&adev->sdma.instance[0].ring);
break;
case 1:
/* XXX compute */
@ -1380,7 +1376,7 @@ static int sdma_v3_0_process_trap_irq(struct amdgpu_device *adev,
case 1:
switch (queue_id) {
case 0:
amdgpu_fence_process(&adev->sdma[1].ring);
amdgpu_fence_process(&adev->sdma.instance[1].ring);
break;
case 1:
/* XXX compute */
@ -1468,8 +1464,10 @@ static const struct amdgpu_ring_funcs sdma_v3_0_ring_funcs = {
static void sdma_v3_0_set_ring_funcs(struct amdgpu_device *adev)
{
adev->sdma[0].ring.funcs = &sdma_v3_0_ring_funcs;
adev->sdma[1].ring.funcs = &sdma_v3_0_ring_funcs;
int i;
for (i = 0; i < adev->sdma.num_instances; i++)
adev->sdma.instance[i].ring.funcs = &sdma_v3_0_ring_funcs;
}
static const struct amdgpu_irq_src_funcs sdma_v3_0_trap_irq_funcs = {
@ -1483,9 +1481,9 @@ static const struct amdgpu_irq_src_funcs sdma_v3_0_illegal_inst_irq_funcs = {
static void sdma_v3_0_set_irq_funcs(struct amdgpu_device *adev)
{
adev->sdma_trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
adev->sdma_trap_irq.funcs = &sdma_v3_0_trap_irq_funcs;
adev->sdma_illegal_inst_irq.funcs = &sdma_v3_0_illegal_inst_irq_funcs;
adev->sdma.trap_irq.num_types = AMDGPU_SDMA_IRQ_LAST;
adev->sdma.trap_irq.funcs = &sdma_v3_0_trap_irq_funcs;
adev->sdma.illegal_inst_irq.funcs = &sdma_v3_0_illegal_inst_irq_funcs;
}
/**
@ -1551,7 +1549,7 @@ static void sdma_v3_0_set_buffer_funcs(struct amdgpu_device *adev)
{
if (adev->mman.buffer_funcs == NULL) {
adev->mman.buffer_funcs = &sdma_v3_0_buffer_funcs;
adev->mman.buffer_funcs_ring = &adev->sdma[0].ring;
adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
}
}
@ -1566,7 +1564,7 @@ static void sdma_v3_0_set_vm_pte_funcs(struct amdgpu_device *adev)
{
if (adev->vm_manager.vm_pte_funcs == NULL) {
adev->vm_manager.vm_pte_funcs = &sdma_v3_0_vm_pte_funcs;
adev->vm_manager.vm_pte_funcs_ring = &adev->sdma[0].ring;
adev->vm_manager.vm_pte_funcs_ring = &adev->sdma.instance[0].ring;
adev->vm_manager.vm_pte_funcs_ring->is_pte_ring = true;
}
}