drm/amd/amdgpu: re-factor debugfs wave reader
Move IP version specific code into a callback. Also add support for gfx7 devices. Signed-off-by: Tom St Denis <tom.stdenis@amd.com> Reviewed-by: Alex Deucher <alexander.deucher@amd.com> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
parent
394fdde256
commit
472259f026
|
@ -840,6 +840,7 @@ struct amdgpu_gfx_funcs {
|
|||
/* get the gpu clock counter */
|
||||
uint64_t (*get_gpu_clock_counter)(struct amdgpu_device *adev);
|
||||
void (*select_se_sh)(struct amdgpu_device *adev, u32 se_num, u32 sh_num, u32 instance);
|
||||
void (*read_wave_data)(struct amdgpu_device *adev, uint32_t simd, uint32_t wave, uint32_t *dst, int *no_fields);
|
||||
};
|
||||
|
||||
struct amdgpu_gfx {
|
||||
|
|
|
@ -2966,19 +2966,13 @@ static ssize_t amdgpu_debugfs_sensor_read(struct file *f, char __user *buf,
|
|||
return !r ? 4 : r;
|
||||
}
|
||||
|
||||
static uint32_t wave_read_ind(struct amdgpu_device *adev, uint32_t SQ_INDEX, uint32_t SQ_DATA, uint32_t simd, uint32_t wave, uint32_t address)
|
||||
{
|
||||
WREG32(SQ_INDEX, (wave & 0xF) | ((simd & 0x3) << 4) | (address << 16) | (1 << 13));
|
||||
return RREG32(SQ_DATA);
|
||||
}
|
||||
|
||||
static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
|
||||
size_t size, loff_t *pos)
|
||||
{
|
||||
struct amdgpu_device *adev = f->f_inode->i_private;
|
||||
int r, x;
|
||||
ssize_t result=0;
|
||||
uint32_t offset, se, sh, cu, wave, simd, data[16];
|
||||
uint32_t offset, se, sh, cu, wave, simd, data[32];
|
||||
|
||||
if (size & 3 || *pos & 3)
|
||||
return -EINVAL;
|
||||
|
@ -2990,25 +2984,14 @@ static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
|
|||
cu = ((*pos >> 23) & 0xFF);
|
||||
wave = ((*pos >> 31) & 0xFF);
|
||||
simd = ((*pos >> 37) & 0xFF);
|
||||
*pos &= 0x7F;
|
||||
|
||||
/* switch to the specific se/sh/cu */
|
||||
mutex_lock(&adev->grbm_idx_mutex);
|
||||
amdgpu_gfx_select_se_sh(adev, se, sh, cu);
|
||||
|
||||
x = 0;
|
||||
if (adev->family == AMDGPU_FAMILY_CZ || adev->family == AMDGPU_FAMILY_VI) {
|
||||
/* type 0 wave data */
|
||||
data[x++] = 0;
|
||||
data[x++] = wave_read_ind(adev, 0x2378, 0x2379, simd, wave, 0x12);
|
||||
data[x++] = wave_read_ind(adev, 0x2378, 0x2379, simd, wave, 0x18);
|
||||
data[x++] = wave_read_ind(adev, 0x2378, 0x2379, simd, wave, 0x19);
|
||||
data[x++] = wave_read_ind(adev, 0x2378, 0x2379, simd, wave, 0x27E);
|
||||
data[x++] = wave_read_ind(adev, 0x2378, 0x2379, simd, wave, 0x27F);
|
||||
data[x++] = wave_read_ind(adev, 0x2378, 0x2379, simd, wave, 0x14);
|
||||
data[x++] = wave_read_ind(adev, 0x2378, 0x2379, simd, wave, 0x1A);
|
||||
data[x++] = wave_read_ind(adev, 0x2378, 0x2379, simd, wave, 0x1B);
|
||||
}
|
||||
if (adev->gfx.funcs->read_wave_data)
|
||||
adev->gfx.funcs->read_wave_data(adev, simd, wave, data, &x);
|
||||
|
||||
amdgpu_gfx_select_se_sh(adev, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF);
|
||||
mutex_unlock(&adev->grbm_idx_mutex);
|
||||
|
@ -3016,17 +2999,17 @@ static ssize_t amdgpu_debugfs_wave_read(struct file *f, char __user *buf,
|
|||
if (!x)
|
||||
return -EINVAL;
|
||||
|
||||
while (size && (*pos < x * 4)) {
|
||||
while (size && (offset < x * 4)) {
|
||||
uint32_t value;
|
||||
|
||||
value = data[*pos >> 2];
|
||||
value = data[offset >> 2];
|
||||
r = put_user(value, (uint32_t *)buf);
|
||||
if (r)
|
||||
return r;
|
||||
|
||||
result += 4;
|
||||
buf += 4;
|
||||
*pos += 4;
|
||||
offset += 4;
|
||||
size -= 4;
|
||||
}
|
||||
|
||||
|
|
|
@ -4357,9 +4357,34 @@ static void gfx_v7_0_ring_emit_gds_switch(struct amdgpu_ring *ring,
|
|||
amdgpu_ring_write(ring, (1 << (oa_size + oa_base)) - (1 << oa_base));
|
||||
}
|
||||
|
||||
static uint32_t wave_read_ind(struct amdgpu_device *adev, uint32_t simd, uint32_t wave, uint32_t address)
|
||||
{
|
||||
WREG32(mmSQ_IND_INDEX, (wave & 0xF) | ((simd & 0x3) << 4) | (address << 16) | (1 << 13));
|
||||
return RREG32(mmSQ_IND_DATA);
|
||||
}
|
||||
|
||||
static void gfx_v7_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, uint32_t wave, uint32_t *dst, int *no_fields)
|
||||
{
|
||||
/* type 0 wave data */
|
||||
dst[(*no_fields)++] = 0;
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_STATUS);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_PC_LO);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_PC_HI);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_EXEC_LO);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_EXEC_HI);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_HW_ID);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_INST_DW0);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_INST_DW1);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_GPR_ALLOC);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_LDS_ALLOC);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_TRAPSTS);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_IB_STS);
|
||||
}
|
||||
|
||||
static const struct amdgpu_gfx_funcs gfx_v7_0_gfx_funcs = {
|
||||
.get_gpu_clock_counter = &gfx_v7_0_get_gpu_clock_counter,
|
||||
.select_se_sh = &gfx_v7_0_select_se_sh,
|
||||
.read_wave_data = &gfx_v7_0_read_wave_data,
|
||||
};
|
||||
|
||||
static const struct amdgpu_rlc_funcs gfx_v7_0_rlc_funcs = {
|
||||
|
|
|
@ -5441,9 +5441,35 @@ static void gfx_v8_0_ring_emit_gds_switch(struct amdgpu_ring *ring,
|
|||
amdgpu_ring_write(ring, (1 << (oa_size + oa_base)) - (1 << oa_base));
|
||||
}
|
||||
|
||||
static uint32_t wave_read_ind(struct amdgpu_device *adev, uint32_t simd, uint32_t wave, uint32_t address)
|
||||
{
|
||||
WREG32(mmSQ_IND_INDEX, (wave & 0xF) | ((simd & 0x3) << 4) | (address << 16) | (1 << 13));
|
||||
return RREG32(mmSQ_IND_DATA);
|
||||
}
|
||||
|
||||
static void gfx_v8_0_read_wave_data(struct amdgpu_device *adev, uint32_t simd, uint32_t wave, uint32_t *dst, int *no_fields)
|
||||
{
|
||||
/* type 0 wave data */
|
||||
dst[(*no_fields)++] = 0;
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_STATUS);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_PC_LO);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_PC_HI);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_EXEC_LO);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_EXEC_HI);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_HW_ID);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_INST_DW0);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_INST_DW1);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_GPR_ALLOC);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_LDS_ALLOC);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_TRAPSTS);
|
||||
dst[(*no_fields)++] = wave_read_ind(adev, simd, wave, ixSQ_WAVE_IB_STS);
|
||||
}
|
||||
|
||||
|
||||
static const struct amdgpu_gfx_funcs gfx_v8_0_gfx_funcs = {
|
||||
.get_gpu_clock_counter = &gfx_v8_0_get_gpu_clock_counter,
|
||||
.select_se_sh = &gfx_v8_0_select_se_sh,
|
||||
.read_wave_data = &gfx_v8_0_read_wave_data,
|
||||
};
|
||||
|
||||
static int gfx_v8_0_early_init(void *handle)
|
||||
|
|
Loading…
Reference in New Issue