summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c848
1 files changed, 252 insertions, 596 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index b4f84a820a44..d54d720b3cf6 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -25,32 +25,35 @@
#include "amdgpu.h"
#include "amdgpu_vcn.h"
+#include "amdgpu_pm.h"
#include "soc15.h"
#include "soc15d.h"
#include "soc15_common.h"
#include "vcn/vcn_1_0_offset.h"
#include "vcn/vcn_1_0_sh_mask.h"
-#include "hdp/hdp_4_0_offset.h"
#include "mmhub/mmhub_9_1_offset.h"
#include "mmhub/mmhub_9_1_sh_mask.h"
#include "ivsrcid/vcn/irqsrcs_vcn_1_0.h"
+#include "jpeg_v1_0.h"
+#include "vcn_v1_0.h"
-#define mmUVD_RBC_XX_IB_REG_CHECK 0x05ab
-#define mmUVD_RBC_XX_IB_REG_CHECK_BASE_IDX 1
-#define mmUVD_REG_XX_MASK 0x05ac
-#define mmUVD_REG_XX_MASK_BASE_IDX 1
+#define mmUVD_RBC_XX_IB_REG_CHECK_1_0 0x05ab
+#define mmUVD_RBC_XX_IB_REG_CHECK_1_0_BASE_IDX 1
+#define mmUVD_REG_XX_MASK_1_0 0x05ac
+#define mmUVD_REG_XX_MASK_1_0_BASE_IDX 1
static int vcn_v1_0_stop(struct amdgpu_device *adev);
static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev);
-static void vcn_v1_0_set_jpeg_ring_funcs(struct amdgpu_device *adev);
static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev);
-static void vcn_v1_0_jpeg_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr);
static int vcn_v1_0_set_powergating_state(void *handle, enum amd_powergating_state state);
static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
- struct dpg_pause_state *new_state);
+ int inst_idx, struct dpg_pause_state *new_state);
+
+static void vcn_v1_0_idle_work_handler(struct work_struct *work);
+static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring);
/**
* vcn_v1_0_early_init - set function pointers
@@ -63,14 +66,14 @@ static int vcn_v1_0_early_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- adev->vcn.num_vcn_inst = 1;
adev->vcn.num_enc_rings = 2;
vcn_v1_0_set_dec_ring_funcs(adev);
vcn_v1_0_set_enc_ring_funcs(adev);
- vcn_v1_0_set_jpeg_ring_funcs(adev);
vcn_v1_0_set_irq_funcs(adev);
+ jpeg_v1_0_early_init(handle);
+
return 0;
}
@@ -101,24 +104,14 @@ static int vcn_v1_0_sw_init(void *handle)
return r;
}
- /* VCN JPEG TRAP */
- r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, 126, &adev->vcn.inst->irq);
- if (r)
- return r;
-
r = amdgpu_vcn_sw_init(adev);
if (r)
return r;
- if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
- const struct common_firmware_header *hdr;
- hdr = (const struct common_firmware_header *)adev->vcn.fw->data;
- adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].ucode_id = AMDGPU_UCODE_ID_VCN;
- adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].fw = adev->vcn.fw;
- adev->firmware.fw_size +=
- ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
- DRM_INFO("PSP loading VCN firmware\n");
- }
+ /* Override the work func */
+ adev->vcn.idle_work.work.func = vcn_v1_0_idle_work_handler;
+
+ amdgpu_vcn_setup_ucode(adev);
r = amdgpu_vcn_resume(adev);
if (r)
@@ -126,7 +119,8 @@ static int vcn_v1_0_sw_init(void *handle)
ring = &adev->vcn.inst->ring_dec;
sprintf(ring->name, "vcn_dec");
- r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0);
+ r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0,
+ AMDGPU_RING_PRIO_DEFAULT, NULL);
if (r)
return r;
@@ -142,24 +136,21 @@ static int vcn_v1_0_sw_init(void *handle)
SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP);
for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
+ enum amdgpu_ring_priority_level hw_prio = amdgpu_vcn_get_enc_ring_prio(i);
+
ring = &adev->vcn.inst->ring_enc[i];
sprintf(ring->name, "vcn_enc%d", i);
- r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0);
+ r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0,
+ hw_prio, NULL);
if (r)
return r;
}
- ring = &adev->vcn.inst->ring_jpeg;
- sprintf(ring->name, "vcn_jpeg");
- r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.inst->irq, 0);
- if (r)
- return r;
-
adev->vcn.pause_dpg_mode = vcn_v1_0_pause_dpg_mode;
- adev->vcn.internal.jpeg_pitch = adev->vcn.inst->external.jpeg_pitch =
- SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_PITCH);
- return 0;
+ r = jpeg_v1_0_sw_init(handle);
+
+ return r;
}
/**
@@ -178,6 +169,8 @@ static int vcn_v1_0_sw_fini(void *handle)
if (r)
return r;
+ jpeg_v1_0_sw_fini(handle);
+
r = amdgpu_vcn_sw_fini(adev);
return r;
@@ -207,7 +200,7 @@ static int vcn_v1_0_hw_init(void *handle)
goto done;
}
- ring = &adev->vcn.inst->ring_jpeg;
+ ring = &adev->jpeg.inst->ring_dec;
r = amdgpu_ring_test_helper(ring);
if (r)
goto done;
@@ -230,13 +223,14 @@ done:
static int vcn_v1_0_hw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- struct amdgpu_ring *ring = &adev->vcn.inst->ring_dec;
+
+ cancel_delayed_work_sync(&adev->vcn.idle_work);
if ((adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) ||
- RREG32_SOC15(VCN, 0, mmUVD_STATUS))
+ (adev->vcn.cur_state != AMD_PG_STATE_GATE &&
+ RREG32_SOC15(VCN, 0, mmUVD_STATUS))) {
vcn_v1_0_set_powergating_state(adev, AMD_PG_STATE_GATE);
-
- ring->sched.ready = false;
+ }
return 0;
}
@@ -364,68 +358,68 @@ static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_device *adev)
/* cache window 0: fw */
if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_lo),
0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
(adev->firmware.ucode[AMDGPU_UCODE_ID_VCN].tmr_mc_addr_hi),
0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0, 0,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0, 0,
0xFFFFFFFF, 0);
offset = 0;
} else {
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
lower_32_bits(adev->vcn.inst->gpu_addr), 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
upper_32_bits(adev->vcn.inst->gpu_addr), 0xFFFFFFFF, 0);
offset = size;
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0,
AMDGPU_UVD_FIRMWARE_OFFSET >> 3, 0xFFFFFFFF, 0);
}
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_SIZE0, size, 0xFFFFFFFF, 0);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_VCPU_CACHE_SIZE0, size, 0xFFFFFFFF, 0);
/* cache window 1: stack */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
lower_32_bits(adev->vcn.inst->gpu_addr + offset), 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_HIGH,
upper_32_bits(adev->vcn.inst->gpu_addr + offset), 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_OFFSET1, 0,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_VCPU_CACHE_OFFSET1, 0,
0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_STACK_SIZE,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_VCPU_CACHE_SIZE1, AMDGPU_VCN_STACK_SIZE,
0xFFFFFFFF, 0);
/* cache window 2: context */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_LOW,
lower_32_bits(adev->vcn.inst->gpu_addr + offset + AMDGPU_VCN_STACK_SIZE),
0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_VCPU_CACHE2_64BIT_BAR_HIGH,
upper_32_bits(adev->vcn.inst->gpu_addr + offset + AMDGPU_VCN_STACK_SIZE),
0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_OFFSET2, 0, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CACHE_SIZE2, AMDGPU_VCN_CONTEXT_SIZE,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_VCPU_CACHE_OFFSET2, 0, 0xFFFFFFFF, 0);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_VCPU_CACHE_SIZE2, AMDGPU_VCN_CONTEXT_SIZE,
0xFFFFFFFF, 0);
/* VCN global tiling registers */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_UDEC_ADDR_CONFIG,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_UDEC_ADDR_CONFIG,
adev->gfx.config.gb_addr_config, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_UDEC_DB_ADDR_CONFIG,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_UDEC_DB_ADDR_CONFIG,
adev->gfx.config.gb_addr_config, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_UDEC_DBW_ADDR_CONFIG,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_UDEC_DBW_ADDR_CONFIG,
adev->gfx.config.gb_addr_config, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_UDEC_DBW_UV_ADDR_CONFIG,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_UDEC_DBW_UV_ADDR_CONFIG,
adev->gfx.config.gb_addr_config, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_MIF_CURR_ADDR_CONFIG,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MIF_CURR_ADDR_CONFIG,
adev->gfx.config.gb_addr_config, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_MIF_CURR_UV_ADDR_CONFIG,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MIF_CURR_UV_ADDR_CONFIG,
adev->gfx.config.gb_addr_config, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_MIF_RECON1_ADDR_CONFIG,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MIF_RECON1_ADDR_CONFIG,
adev->gfx.config.gb_addr_config, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_MIF_RECON1_UV_ADDR_CONFIG,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MIF_RECON1_UV_ADDR_CONFIG,
adev->gfx.config.gb_addr_config, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_MIF_REF_ADDR_CONFIG,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MIF_REF_ADDR_CONFIG,
adev->gfx.config.gb_addr_config, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_MIF_REF_UV_ADDR_CONFIG,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MIF_REF_UV_ADDR_CONFIG,
adev->gfx.config.gb_addr_config, 0xFFFFFFFF, 0);
}
@@ -433,7 +427,6 @@ static void vcn_v1_0_mc_resume_dpg_mode(struct amdgpu_device *adev)
* vcn_v1_0_disable_clock_gating - disable VCN clock gating
*
* @adev: amdgpu_device pointer
- * @sw: enable SW clock gating
*
* Disable clock gating for VCN block
*/
@@ -560,7 +553,6 @@ static void vcn_v1_0_disable_clock_gating(struct amdgpu_device *adev)
* vcn_v1_0_enable_clock_gating - enable VCN clock gating
*
* @adev: amdgpu_device pointer
- * @sw: enable SW clock gating
*
* Enable clock gating for VCN block
*/
@@ -640,9 +632,9 @@ static void vcn_v1_0_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t s
reg_data = 0 << JPEG_CGC_CTRL__DYN_CLOCK_MODE__SHIFT;
reg_data |= 1 << JPEG_CGC_CTRL__CLK_GATE_DLY_TIMER__SHIFT;
reg_data |= 4 << JPEG_CGC_CTRL__CLK_OFF_DELAY__SHIFT;
- WREG32_SOC15_DPG_MODE(UVD, 0, mmJPEG_CGC_CTRL, reg_data, 0xFFFFFFFF, sram_sel);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmJPEG_CGC_CTRL, reg_data, 0xFFFFFFFF, sram_sel);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmJPEG_CGC_GATE, 0, 0xFFFFFFFF, sram_sel);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmJPEG_CGC_GATE, 0, 0xFFFFFFFF, sram_sel);
/* enable sw clock gating control */
if (adev->cg_flags & AMD_CG_SUPPORT_VCN_MGCG)
@@ -671,22 +663,21 @@ static void vcn_v1_0_clock_gating_dpg_mode(struct amdgpu_device *adev, uint8_t s
UVD_CGC_CTRL__WCB_MODE_MASK |
UVD_CGC_CTRL__VCPU_MODE_MASK |
UVD_CGC_CTRL__SCPU_MODE_MASK);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_CGC_CTRL, reg_data, 0xFFFFFFFF, sram_sel);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_CGC_CTRL, reg_data, 0xFFFFFFFF, sram_sel);
/* turn off clock gating */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_CGC_GATE, 0, 0xFFFFFFFF, sram_sel);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_CGC_GATE, 0, 0xFFFFFFFF, sram_sel);
/* turn on SUVD clock gating */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_SUVD_CGC_GATE, 1, 0xFFFFFFFF, sram_sel);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_SUVD_CGC_GATE, 1, 0xFFFFFFFF, sram_sel);
/* turn on sw mode in UVD_SUVD_CGC_CTRL */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_SUVD_CGC_CTRL, 0, 0xFFFFFFFF, sram_sel);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_SUVD_CGC_CTRL, 0, 0xFFFFFFFF, sram_sel);
}
static void vcn_1_0_disable_static_power_gating(struct amdgpu_device *adev)
{
uint32_t data = 0;
- int ret;
if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
data = (1 << UVD_PGFSM_CONFIG__UVDM_PWR_CONFIG__SHIFT
@@ -702,7 +693,7 @@ static void vcn_1_0_disable_static_power_gating(struct amdgpu_device *adev)
| 2 << UVD_PGFSM_CONFIG__UVDW_PWR_CONFIG__SHIFT);
WREG32_SOC15(VCN, 0, mmUVD_PGFSM_CONFIG, data);
- SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_PGFSM_STATUS, UVD_PGFSM_STATUS__UVDM_UVDU_PWR_ON, 0xFFFFFF, ret);
+ SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_PGFSM_STATUS, UVD_PGFSM_STATUS__UVDM_UVDU_PWR_ON, 0xFFFFFF);
} else {
data = (1 << UVD_PGFSM_CONFIG__UVDM_PWR_CONFIG__SHIFT
| 1 << UVD_PGFSM_CONFIG__UVDU_PWR_CONFIG__SHIFT
@@ -716,7 +707,7 @@ static void vcn_1_0_disable_static_power_gating(struct amdgpu_device *adev)
| 1 << UVD_PGFSM_CONFIG__UVDE_PWR_CONFIG__SHIFT
| 1 << UVD_PGFSM_CONFIG__UVDW_PWR_CONFIG__SHIFT);
WREG32_SOC15(VCN, 0, mmUVD_PGFSM_CONFIG, data);
- SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_PGFSM_STATUS, 0, 0xFFFFFFFF, ret);
+ SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_PGFSM_STATUS, 0, 0xFFFFFFFF);
}
/* polling UVD_PGFSM_STATUS to confirm UVDM_PWR_STATUS , UVDU_PWR_STATUS are 0 (power on) */
@@ -732,7 +723,6 @@ static void vcn_1_0_disable_static_power_gating(struct amdgpu_device *adev)
static void vcn_1_0_enable_static_power_gating(struct amdgpu_device *adev)
{
uint32_t data = 0;
- int ret;
if (adev->pg_flags & AMD_PG_SUPPORT_VCN) {
/* Before power off, this indicator has to be turned on */
@@ -767,12 +757,12 @@ static void vcn_1_0_enable_static_power_gating(struct amdgpu_device *adev)
| 2 << UVD_PGFSM_STATUS__UVDTE_PWR_STATUS__SHIFT
| 2 << UVD_PGFSM_STATUS__UVDE_PWR_STATUS__SHIFT
| 2 << UVD_PGFSM_STATUS__UVDW_PWR_STATUS__SHIFT);
- SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_PGFSM_STATUS, data, 0xFFFFFFFF, ret);
+ SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_PGFSM_STATUS, data, 0xFFFFFFFF);
}
}
/**
- * vcn_v1_0_start - start VCN block
+ * vcn_v1_0_start_spg_mode - start VCN block
*
* @adev: amdgpu_device pointer
*
@@ -838,9 +828,9 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
vcn_v1_0_mc_resume_spg_mode(adev);
- WREG32_SOC15(UVD, 0, mmUVD_REG_XX_MASK, 0x10);
- WREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK,
- RREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK) | 0x3);
+ WREG32_SOC15(UVD, 0, mmUVD_REG_XX_MASK_1_0, 0x10);
+ WREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK_1_0,
+ RREG32_SOC15(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK_1_0) | 0x3);
/* enable VCPU clock */
WREG32_SOC15(UVD, 0, mmUVD_VCPU_CNTL, UVD_VCPU_CNTL__CLK_EN_MASK);
@@ -915,7 +905,7 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR_ADDR,
(upper_32_bits(ring->gpu_addr) >> 2));
- /* programm the RB_BASE for ring buffer */
+ /* program the RB_BASE for ring buffer */
WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
lower_32_bits(ring->gpu_addr));
WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
@@ -947,22 +937,7 @@ static int vcn_v1_0_start_spg_mode(struct amdgpu_device *adev)
WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4);
- ring = &adev->vcn.inst->ring_jpeg;
- WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
- WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_NO_FETCH_MASK |
- UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
- WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr));
- WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, upper_32_bits(ring->gpu_addr));
- WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR, 0);
- WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, 0);
- WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, UVD_JRBC_RB_CNTL__RB_RPTR_WR_EN_MASK);
-
- /* initialize wptr */
- ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-
- /* copy patch commands to the jpeg ring */
- vcn_v1_0_jpeg_ring_set_patch_ring(ring,
- (ring->wptr + ring->max_dw * amdgpu_sched_hw_submission));
+ jpeg_v1_0_start(adev, 0);
return 0;
}
@@ -991,14 +966,14 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
tmp = (0xFF << UVD_VCPU_CNTL__PRB_TIMEOUT_VAL__SHIFT);
tmp |= UVD_VCPU_CNTL__CLK_EN_MASK;
tmp |= UVD_VCPU_CNTL__MIF_WR_LOW_THRESHOLD_BP_MASK;
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_VCPU_CNTL, tmp, 0xFFFFFFFF, 0);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_VCPU_CNTL, tmp, 0xFFFFFFFF, 0);
/* disable interupt */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_MASTINT_EN,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MASTINT_EN,
0, UVD_MASTINT_EN__VCPU_EN_MASK, 0);
/* initialize VCN memory controller */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_CTRL,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_CTRL,
(8 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
@@ -1012,48 +987,48 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
/* swap (8 in 32) RB and IB */
lmi_swap_cntl = 0xa;
#endif
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_SWAP_CNTL, lmi_swap_cntl, 0xFFFFFFFF, 0);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_SWAP_CNTL, lmi_swap_cntl, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_MPC_CNTL,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MPC_CNTL,
0x2 << UVD_MPC_CNTL__REPLACEMENT_MODE__SHIFT, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_MPC_SET_MUXA0,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MPC_SET_MUXA0,
((0x1 << UVD_MPC_SET_MUXA0__VARA_1__SHIFT) |
(0x2 << UVD_MPC_SET_MUXA0__VARA_2__SHIFT) |
(0x3 << UVD_MPC_SET_MUXA0__VARA_3__SHIFT) |
(0x4 << UVD_MPC_SET_MUXA0__VARA_4__SHIFT)), 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_MPC_SET_MUXB0,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MPC_SET_MUXB0,
((0x1 << UVD_MPC_SET_MUXB0__VARB_1__SHIFT) |
(0x2 << UVD_MPC_SET_MUXB0__VARB_2__SHIFT) |
(0x3 << UVD_MPC_SET_MUXB0__VARB_3__SHIFT) |
(0x4 << UVD_MPC_SET_MUXB0__VARB_4__SHIFT)), 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_MPC_SET_MUX,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MPC_SET_MUX,
((0x0 << UVD_MPC_SET_MUX__SET_0__SHIFT) |
(0x1 << UVD_MPC_SET_MUX__SET_1__SHIFT) |
(0x2 << UVD_MPC_SET_MUX__SET_2__SHIFT)), 0xFFFFFFFF, 0);
vcn_v1_0_mc_resume_dpg_mode(adev);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_REG_XX_MASK, 0x10, 0xFFFFFFFF, 0);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK, 0x3, 0xFFFFFFFF, 0);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_REG_XX_MASK, 0x10, 0xFFFFFFFF, 0);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_RBC_XX_IB_REG_CHECK, 0x3, 0xFFFFFFFF, 0);
/* boot up the VCPU */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_SOFT_RESET, 0, 0xFFFFFFFF, 0);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_SOFT_RESET, 0, 0xFFFFFFFF, 0);
/* enable UMC */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_CTRL2,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_CTRL2,
0x1F << UVD_LMI_CTRL2__RE_OFLD_MIF_WR_REQ_NUM__SHIFT,
0xFFFFFFFF, 0);
/* enable master interrupt */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_MASTINT_EN,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_MASTINT_EN,
UVD_MASTINT_EN__VCPU_EN_MASK, UVD_MASTINT_EN__VCPU_EN_MASK, 0);
vcn_v1_0_clock_gating_dpg_mode(adev, 1);
/* setup mmUVD_LMI_CTRL */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_LMI_CTRL,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_LMI_CTRL,
(8 << UVD_LMI_CTRL__WRITE_CLEAN_TIMER__SHIFT) |
UVD_LMI_CTRL__WRITE_CLEAN_TIMER_EN_MASK |
UVD_LMI_CTRL__DATA_COHERENCY_EN_MASK |
@@ -1065,11 +1040,11 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
tmp = adev->gfx.config.gb_addr_config;
/* setup VCN global tiling registers */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_JPEG_ADDR_CONFIG, tmp, 0xFFFFFFFF, 1);
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_JPEG_UV_ADDR_CONFIG, tmp, 0xFFFFFFFF, 1);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_JPEG_ADDR_CONFIG, tmp, 0xFFFFFFFF, 1);
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_JPEG_UV_ADDR_CONFIG, tmp, 0xFFFFFFFF, 1);
/* enable System Interrupt for JRBC */
- WREG32_SOC15_DPG_MODE(UVD, 0, mmUVD_SYS_INT_EN,
+ WREG32_SOC15_DPG_MODE_1_0(UVD, 0, mmUVD_SYS_INT_EN,
UVD_SYS_INT_EN__UVD_JRBC_EN_MASK, 0xFFFFFFFF, 1);
/* force RBC into idle state */
@@ -1088,7 +1063,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
WREG32_SOC15(UVD, 0, mmUVD_RBC_RB_RPTR_ADDR,
(upper_32_bits(ring->gpu_addr) >> 2));
- /* programm the RB_BASE for ring buffer */
+ /* program the RB_BASE for ring buffer */
WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
lower_32_bits(ring->gpu_addr));
WREG32_SOC15(UVD, 0, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
@@ -1106,13 +1081,7 @@ static int vcn_v1_0_start_dpg_mode(struct amdgpu_device *adev)
WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_RBC_RB_CNTL), 0,
~UVD_RBC_RB_CNTL__RB_NO_FETCH_MASK);
- /* initialize JPEG wptr */
- ring = &adev->vcn.inst->ring_jpeg;
- ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-
- /* copy patch commands to the jpeg ring */
- vcn_v1_0_jpeg_ring_set_patch_ring(ring,
- (ring->wptr + ring->max_dw * amdgpu_sched_hw_submission));
+ jpeg_v1_0_start(adev, 1);
return 0;
}
@@ -1129,7 +1098,7 @@ static int vcn_v1_0_start(struct amdgpu_device *adev)
}
/**
- * vcn_v1_0_stop - stop VCN block
+ * vcn_v1_0_stop_spg_mode - stop VCN block
*
* @adev: amdgpu_device pointer
*
@@ -1137,24 +1106,24 @@ static int vcn_v1_0_start(struct amdgpu_device *adev)
*/
static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev)
{
- int ret_code, tmp;
+ int tmp;
- SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7, ret_code);
+ SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_STATUS, UVD_STATUS__IDLE, 0x7);
tmp = UVD_LMI_STATUS__VCPU_LMI_WRITE_CLEAN_MASK |
UVD_LMI_STATUS__READ_CLEAN_MASK |
UVD_LMI_STATUS__WRITE_CLEAN_MASK |
UVD_LMI_STATUS__WRITE_CLEAN_RAW_MASK;
- SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_LMI_STATUS, tmp, tmp, ret_code);
+ SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_LMI_STATUS, tmp, tmp);
- /* put VCPU into reset */
- WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET),
- UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK,
- ~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
+ /* stall UMC channel */
+ WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_CTRL2),
+ UVD_LMI_CTRL2__STALL_ARB_UMC_MASK,
+ ~UVD_LMI_CTRL2__STALL_ARB_UMC_MASK);
tmp = UVD_LMI_STATUS__UMC_READ_CLEAN_RAW_MASK |
UVD_LMI_STATUS__UMC_WRITE_CLEAN_RAW_MASK;
- SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_LMI_STATUS, tmp, tmp, ret_code);
+ SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_LMI_STATUS, tmp, tmp);
/* disable VCPU clock */
WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CNTL), 0,
@@ -1169,6 +1138,11 @@ static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev)
UVD_SOFT_RESET__LMI_SOFT_RESET_MASK,
~UVD_SOFT_RESET__LMI_SOFT_RESET_MASK);
+ /* put VCPU into reset */
+ WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_SOFT_RESET),
+ UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK,
+ ~UVD_SOFT_RESET__VCPU_SOFT_RESET_MASK);
+
WREG32_SOC15(UVD, 0, mmUVD_STATUS, 0);
vcn_v1_0_enable_clock_gating(adev);
@@ -1178,30 +1152,29 @@ static int vcn_v1_0_stop_spg_mode(struct amdgpu_device *adev)
static int vcn_v1_0_stop_dpg_mode(struct amdgpu_device *adev)
{
- int ret_code = 0;
uint32_t tmp;
/* Wait for power status to be UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF */
SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF,
- UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+ UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
/* wait for read ptr to be equal to write ptr */
tmp = RREG32_SOC15(UVD, 0, mmUVD_RB_WPTR);
- SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
+ SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RB_RPTR, tmp, 0xFFFFFFFF);
tmp = RREG32_SOC15(UVD, 0, mmUVD_RB_WPTR2);
- SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RB_RPTR2, tmp, 0xFFFFFFFF, ret_code);
+ SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RB_RPTR2, tmp, 0xFFFFFFFF);
tmp = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
- SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_JRBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
+ SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_JRBC_RB_RPTR, tmp, 0xFFFFFFFF);
tmp = RREG32_SOC15(UVD, 0, mmUVD_RBC_RB_WPTR) & 0x7FFFFFFF;
- SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RBC_RB_RPTR, tmp, 0xFFFFFFFF, ret_code);
+ SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_RBC_RB_RPTR, tmp, 0xFFFFFFFF);
SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF,
- UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+ UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
/* disable dynamic power gating mode */
WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_POWER_STATUS), 0,
@@ -1223,7 +1196,7 @@ static int vcn_v1_0_stop(struct amdgpu_device *adev)
}
static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
- struct dpg_pause_state *new_state)
+ int inst_idx, struct dpg_pause_state *new_state)
{
int ret_code;
uint32_t reg_data = 0;
@@ -1231,9 +1204,10 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
struct amdgpu_ring *ring;
/* pause/unpause if state is changed */
- if (adev->vcn.pause_state.fw_based != new_state->fw_based) {
+ if (adev->vcn.inst[inst_idx].pause_state.fw_based != new_state->fw_based) {
DRM_DEBUG("dpg pause state changed %d:%d -> %d:%d",
- adev->vcn.pause_state.fw_based, adev->vcn.pause_state.jpeg,
+ adev->vcn.inst[inst_idx].pause_state.fw_based,
+ adev->vcn.inst[inst_idx].pause_state.jpeg,
new_state->fw_based, new_state->jpeg);
reg_data = RREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE) &
@@ -1243,9 +1217,9 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
ret_code = 0;
if (!(reg_data & UVD_DPG_PAUSE__JPEG_PAUSE_DPG_ACK_MASK))
- SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
+ ret_code = SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF,
- UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+ UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
if (!ret_code) {
/* pause DPG non-jpeg */
@@ -1253,7 +1227,7 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
WREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE, reg_data);
SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_DPG_PAUSE,
UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK,
- UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK, ret_code);
+ UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK);
/* Restore */
ring = &adev->vcn.inst->ring_enc[0];
@@ -1275,20 +1249,21 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2) & 0x7FFFFFFF);
SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON,
- UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+ UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
}
} else {
/* unpause dpg non-jpeg, no need to wait */
reg_data &= ~UVD_DPG_PAUSE__NJ_PAUSE_DPG_REQ_MASK;
WREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE, reg_data);
}
- adev->vcn.pause_state.fw_based = new_state->fw_based;
+ adev->vcn.inst[inst_idx].pause_state.fw_based = new_state->fw_based;
}
/* pause/unpause if state is changed */
- if (adev->vcn.pause_state.jpeg != new_state->jpeg) {
+ if (adev->vcn.inst[inst_idx].pause_state.jpeg != new_state->jpeg) {
DRM_DEBUG("dpg pause state changed %d:%d -> %d:%d",
- adev->vcn.pause_state.fw_based, adev->vcn.pause_state.jpeg,
+ adev->vcn.inst[inst_idx].pause_state.fw_based,
+ adev->vcn.inst[inst_idx].pause_state.jpeg,
new_state->fw_based, new_state->jpeg);
reg_data = RREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE) &
@@ -1298,9 +1273,9 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
ret_code = 0;
if (!(reg_data & UVD_DPG_PAUSE__NJ_PAUSE_DPG_ACK_MASK))
- SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
+ ret_code = SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
UVD_POWER_STATUS__UVD_POWER_STATUS_TILES_OFF,
- UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+ UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
if (!ret_code) {
/* Make sure JPRG Snoop is disabled before sending the pause */
@@ -1313,10 +1288,10 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
WREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE, reg_data);
SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_DPG_PAUSE,
UVD_DPG_PAUSE__JPEG_PAUSE_DPG_ACK_MASK,
- UVD_DPG_PAUSE__JPEG_PAUSE_DPG_ACK_MASK, ret_code);
+ UVD_DPG_PAUSE__JPEG_PAUSE_DPG_ACK_MASK);
/* Restore */
- ring = &adev->vcn.inst->ring_jpeg;
+ ring = &adev->jpeg.inst->ring_dec;
WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL,
UVD_JRBC_RB_CNTL__RB_NO_FETCH_MASK |
@@ -1335,14 +1310,14 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
RREG32_SOC15(UVD, 0, mmUVD_SCRATCH2) & 0x7FFFFFFF);
SOC15_WAIT_ON_RREG(UVD, 0, mmUVD_POWER_STATUS,
UVD_PGFSM_CONFIG__UVDM_UVDU_PWR_ON,
- UVD_POWER_STATUS__UVD_POWER_STATUS_MASK, ret_code);
+ UVD_POWER_STATUS__UVD_POWER_STATUS_MASK);
}
} else {
/* unpause dpg jpeg, no need to wait */
reg_data &= ~UVD_DPG_PAUSE__JPEG_PAUSE_DPG_REQ_MASK;
WREG32_SOC15(UVD, 0, mmUVD_DPG_PAUSE, reg_data);
}
- adev->vcn.pause_state.jpeg = new_state->jpeg;
+ adev->vcn.inst[inst_idx].pause_state.jpeg = new_state->jpeg;
}
return 0;
@@ -1358,10 +1333,10 @@ static bool vcn_v1_0_is_idle(void *handle)
static int vcn_v1_0_wait_for_idle(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- int ret = 0;
+ int ret;
- SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_STATUS, UVD_STATUS__IDLE,
- UVD_STATUS__IDLE, ret);
+ ret = SOC15_WAIT_ON_RREG(VCN, 0, mmUVD_STATUS, UVD_STATUS__IDLE,
+ UVD_STATUS__IDLE);
return ret;
}
@@ -1370,11 +1345,11 @@ static int vcn_v1_0_set_clockgating_state(void *handle,
enum amd_clockgating_state state)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
+ bool enable = (state == AMD_CG_STATE_GATE);
if (enable) {
/* wait for STATUS to clear */
- if (vcn_v1_0_is_idle(handle))
+ if (!vcn_v1_0_is_idle(handle))
return -EBUSY;
vcn_v1_0_enable_clock_gating(adev);
} else {
@@ -1469,7 +1444,9 @@ static void vcn_v1_0_dec_ring_insert_end(struct amdgpu_ring *ring)
* vcn_v1_0_dec_ring_emit_fence - emit an fence & trap command
*
* @ring: amdgpu_ring pointer
- * @fence: fence to emit
+ * @addr: address
+ * @seq: sequence number
+ * @flags: fence related flags
*
* Write a fence and a trap command to the ring.
*/
@@ -1508,7 +1485,9 @@ static void vcn_v1_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64
* vcn_v1_0_dec_ring_emit_ib - execute indirect buffer
*
* @ring: amdgpu_ring pointer
+ * @job: job to retrieve vmid from
* @ib: indirect buffer to execute
+ * @flags: unused
*
* Write ring commands to execute the indirect buffer
*/
@@ -1564,7 +1543,7 @@ static void vcn_v1_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
/* wait for register write */
- data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
+ data0 = hub->ctx0_ptb_addr_lo32 + vmid * hub->ctx_addr_distance;
data1 = lower_32_bits(pd_addr);
mask = 0xffffffff;
vcn_v1_0_dec_ring_emit_reg_wait(ring, data0, data1, mask);
@@ -1643,7 +1622,9 @@ static void vcn_v1_0_enc_ring_set_wptr(struct amdgpu_ring *ring)
* vcn_v1_0_enc_ring_emit_fence - emit an enc fence & trap command
*
* @ring: amdgpu_ring pointer
- * @fence: fence to emit
+ * @addr: address
+ * @seq: sequence number
+ * @flags: fence related flags
*
* Write enc a fence and a trap command to the ring.
*/
@@ -1668,7 +1649,9 @@ static void vcn_v1_0_enc_ring_insert_end(struct amdgpu_ring *ring)
* vcn_v1_0_enc_ring_emit_ib - enc execute indirect buffer
*
* @ring: amdgpu_ring pointer
+ * @job: job to retrive vmid from
* @ib: indirect buffer to execute
+ * @flags: unused
*
* Write enc ring commands to execute the indirect buffer
*/
@@ -1704,7 +1687,8 @@ static void vcn_v1_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
/* wait for reg writes */
- vcn_v1_0_enc_ring_emit_reg_wait(ring, hub->ctx0_ptb_addr_lo32 + vmid * 2,
+ vcn_v1_0_enc_ring_emit_reg_wait(ring, hub->ctx0_ptb_addr_lo32 +
+ vmid * hub->ctx_addr_distance,
lower_32_bits(pd_addr), 0xffffffff);
}
@@ -1716,389 +1700,6 @@ static void vcn_v1_0_enc_ring_emit_wreg(struct amdgpu_ring *ring,
amdgpu_ring_write(ring, val);
}
-
-/**
- * vcn_v1_0_jpeg_ring_get_rptr - get read pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware read pointer
- */
-static uint64_t vcn_v1_0_jpeg_ring_get_rptr(struct amdgpu_ring *ring)
-{
- struct amdgpu_device *adev = ring->adev;
-
- return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_get_wptr - get write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Returns the current hardware write pointer
- */
-static uint64_t vcn_v1_0_jpeg_ring_get_wptr(struct amdgpu_ring *ring)
-{
- struct amdgpu_device *adev = ring->adev;
-
- return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_set_wptr - set write pointer
- *
- * @ring: amdgpu_ring pointer
- *
- * Commits the write pointer to the hardware
- */
-static void vcn_v1_0_jpeg_ring_set_wptr(struct amdgpu_ring *ring)
-{
- struct amdgpu_device *adev = ring->adev;
-
- WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
-}
-
-/**
- * vcn_v1_0_jpeg_ring_insert_start - insert a start command
- *
- * @ring: amdgpu_ring pointer
- *
- * Write a start command to the ring.
- */
-static void vcn_v1_0_jpeg_ring_insert_start(struct amdgpu_ring *ring)
-{
- struct amdgpu_device *adev = ring->adev;
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, 0x68e04);
-
- amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, 0x80010000);
-}
-
-/**
- * vcn_v1_0_jpeg_ring_insert_end - insert a end command
- *
- * @ring: amdgpu_ring pointer
- *
- * Write a end command to the ring.
- */
-static void vcn_v1_0_jpeg_ring_insert_end(struct amdgpu_ring *ring)
-{
- struct amdgpu_device *adev = ring->adev;
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, 0x68e04);
-
- amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, 0x00010000);
-}
-
-/**
- * vcn_v1_0_jpeg_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_v1_0_jpeg_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
- unsigned flags)
-{
- struct amdgpu_device *adev = ring->adev;
-
- WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_DATA0), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, seq);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_DATA1), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, seq);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, lower_32_bits(addr));
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, upper_32_bits(addr));
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_CMD), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, 0x8);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_CMD), 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
- amdgpu_ring_write(ring, 0);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, 0x01400200);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, seq);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, lower_32_bits(addr));
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, upper_32_bits(addr));
-
- amdgpu_ring_write(ring,
- PACKETJ(0, 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE2));
- amdgpu_ring_write(ring, 0xffffffff);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, 0x3fbc);
-
- amdgpu_ring_write(ring,
- PACKETJ(0, 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, 0x1);
-
- /* emit trap */
- amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE7));
- amdgpu_ring_write(ring, 0);
-}
-
-/**
- * vcn_v1_0_jpeg_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_v1_0_jpeg_ring_emit_ib(struct amdgpu_ring *ring,
- struct amdgpu_job *job,
- struct amdgpu_ib *ib,
- uint32_t flags)
-{
- struct amdgpu_device *adev = ring->adev;
- unsigned vmid = AMDGPU_JOB_GET_VMID(job);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, (vmid | (vmid << 4)));
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, (vmid | (vmid << 4)));
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_IB_SIZE), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, ib->length_dw);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr));
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 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(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, 0x01400200);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, 0x2);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_STATUS), 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3));
- amdgpu_ring_write(ring, 0x2);
-}
-
-static void vcn_v1_0_jpeg_ring_emit_reg_wait(struct amdgpu_ring *ring,
- uint32_t reg, uint32_t val,
- uint32_t mask)
-{
- struct amdgpu_device *adev = ring->adev;
- uint32_t reg_offset = (reg << 2);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, 0x01400200);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
- amdgpu_ring_write(ring, val);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
- if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
- ((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
- 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(0, 0, 0, PACKETJ_TYPE3));
- }
- amdgpu_ring_write(ring, mask);
-}
-
-static void vcn_v1_0_jpeg_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_v1_0_jpeg_ring_emit_reg_wait(ring, data0, data1, mask);
-}
-
-static void vcn_v1_0_jpeg_ring_emit_wreg(struct amdgpu_ring *ring,
- uint32_t reg, uint32_t val)
-{
- struct amdgpu_device *adev = ring->adev;
- uint32_t reg_offset = (reg << 2);
-
- amdgpu_ring_write(ring,
- PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
- if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
- ((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
- 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(0, 0, 0, PACKETJ_TYPE0));
- }
- amdgpu_ring_write(ring, val);
-}
-
-static void vcn_v1_0_jpeg_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 void vcn_v1_0_jpeg_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val)
-{
- struct amdgpu_device *adev = ring->adev;
- ring->ring[(*ptr)++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
- if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
- ((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
- ring->ring[(*ptr)++] = 0;
- ring->ring[(*ptr)++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0);
- } else {
- ring->ring[(*ptr)++] = reg_offset;
- ring->ring[(*ptr)++] = PACKETJ(0, 0, 0, PACKETJ_TYPE0);
- }
- ring->ring[(*ptr)++] = val;
-}
-
-static void vcn_v1_0_jpeg_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr)
-{
- struct amdgpu_device *adev = ring->adev;
-
- uint32_t reg, reg_offset, val, mask, i;
-
- // 1st: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW
- reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW);
- reg_offset = (reg << 2);
- val = lower_32_bits(ring->gpu_addr);
- vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
- // 2nd: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH
- reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH);
- reg_offset = (reg << 2);
- val = upper_32_bits(ring->gpu_addr);
- vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
- // 3rd to 5th: issue MEM_READ commands
- for (i = 0; i <= 2; i++) {
- ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE2);
- ring->ring[ptr++] = 0;
- }
-
- // 6th: program mmUVD_JRBC_RB_CNTL register to enable NO_FETCH and RPTR write ability
- reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
- reg_offset = (reg << 2);
- val = 0x13;
- vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
- // 7th: program mmUVD_JRBC_RB_REF_DATA
- reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA);
- reg_offset = (reg << 2);
- val = 0x1;
- vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
- // 8th: issue conditional register read mmUVD_JRBC_RB_CNTL
- reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
- reg_offset = (reg << 2);
- val = 0x1;
- mask = 0x1;
-
- ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0);
- ring->ring[ptr++] = 0x01400200;
- ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0);
- ring->ring[ptr++] = val;
- ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
- if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
- ((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
- ring->ring[ptr++] = 0;
- ring->ring[ptr++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3);
- } else {
- ring->ring[ptr++] = reg_offset;
- ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE3);
- }
- ring->ring[ptr++] = mask;
-
- //9th to 21st: insert no-op
- for (i = 0; i <= 12; i++) {
- ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
- ring->ring[ptr++] = 0;
- }
-
- //22nd: reset mmUVD_JRBC_RB_RPTR
- reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_RPTR);
- reg_offset = (reg << 2);
- val = 0;
- vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-
- //23rd: program mmUVD_JRBC_RB_CNTL to disable no_fetch
- reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
- reg_offset = (reg << 2);
- val = 0x12;
- vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
-}
-
static int vcn_v1_0_set_interrupt_state(struct amdgpu_device *adev,
struct amdgpu_irq_src *source,
unsigned type,
@@ -2123,9 +1724,6 @@ static int vcn_v1_0_process_interrupt(struct amdgpu_device *adev,
case 120:
amdgpu_fence_process(&adev->vcn.inst->ring_enc[1]);
break;
- case 126:
- amdgpu_fence_process(&adev->vcn.inst->ring_jpeg);
- break;
default:
DRM_ERROR("Unhandled interrupt: %d %d\n",
entry->src_id, entry->src_data[0]);
@@ -2174,6 +1772,105 @@ static int vcn_v1_0_set_powergating_state(void *handle,
return ret;
}
+static void vcn_v1_0_idle_work_handler(struct work_struct *work)
+{
+ struct amdgpu_device *adev =
+ container_of(work, struct amdgpu_device, vcn.idle_work.work);
+ unsigned int fences = 0, i;
+
+ for (i = 0; i < adev->vcn.num_enc_rings; ++i)
+ fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_enc[i]);
+
+ if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+ struct dpg_pause_state new_state;
+
+ if (fences)
+ new_state.fw_based = VCN_DPG_STATE__PAUSE;
+ else
+ new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
+
+ if (amdgpu_fence_count_emitted(&adev->jpeg.inst->ring_dec))
+ new_state.jpeg = VCN_DPG_STATE__PAUSE;
+ else
+ new_state.jpeg = VCN_DPG_STATE__UNPAUSE;
+
+ adev->vcn.pause_dpg_mode(adev, 0, &new_state);
+ }
+
+ fences += amdgpu_fence_count_emitted(&adev->jpeg.inst->ring_dec);
+ fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_dec);
+
+ if (fences == 0) {
+ amdgpu_gfx_off_ctrl(adev, true);
+ if (adev->pm.dpm_enabled)
+ amdgpu_dpm_enable_uvd(adev, false);
+ else
+ amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+ AMD_PG_STATE_GATE);
+ } else {
+ schedule_delayed_work(&adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
+ }
+}
+
+static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
+{
+ struct amdgpu_device *adev = ring->adev;
+ bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
+
+ mutex_lock(&adev->vcn.vcn1_jpeg1_workaround);
+
+ if (amdgpu_fence_wait_empty(&ring->adev->jpeg.inst->ring_dec))
+ DRM_ERROR("VCN dec: jpeg dec ring may not be empty\n");
+
+ vcn_v1_0_set_pg_for_begin_use(ring, set_clocks);
+
+}
+
+void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks)
+{
+ struct amdgpu_device *adev = ring->adev;
+
+ if (set_clocks) {
+ amdgpu_gfx_off_ctrl(adev, false);
+ if (adev->pm.dpm_enabled)
+ amdgpu_dpm_enable_uvd(adev, true);
+ else
+ amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+ AMD_PG_STATE_UNGATE);
+ }
+
+ if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+ struct dpg_pause_state new_state;
+ unsigned int fences = 0, i;
+
+ for (i = 0; i < adev->vcn.num_enc_rings; ++i)
+ fences += amdgpu_fence_count_emitted(&adev->vcn.inst->ring_enc[i]);
+
+ if (fences)
+ new_state.fw_based = VCN_DPG_STATE__PAUSE;
+ else
+ new_state.fw_based = VCN_DPG_STATE__UNPAUSE;
+
+ if (amdgpu_fence_count_emitted(&adev->jpeg.inst->ring_dec))
+ new_state.jpeg = VCN_DPG_STATE__PAUSE;
+ else
+ new_state.jpeg = VCN_DPG_STATE__UNPAUSE;
+
+ if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC)
+ new_state.fw_based = VCN_DPG_STATE__PAUSE;
+ else if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG)
+ new_state.jpeg = VCN_DPG_STATE__PAUSE;
+
+ adev->vcn.pause_dpg_mode(adev, 0, &new_state);
+ }
+}
+
+void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring)
+{
+ schedule_delayed_work(&ring->adev->vcn.idle_work, VCN_IDLE_TIMEOUT);
+ mutex_unlock(&ring->adev->vcn.vcn1_jpeg1_workaround);
+}
+
static const struct amd_ip_funcs vcn_v1_0_ip_funcs = {
.name = "vcn_v1_0",
.early_init = vcn_v1_0_early_init,
@@ -2220,8 +1917,8 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
.insert_start = vcn_v1_0_dec_ring_insert_start,
.insert_end = vcn_v1_0_dec_ring_insert_end,
.pad_ib = amdgpu_ring_generic_pad_ib,
- .begin_use = amdgpu_vcn_ring_begin_use,
- .end_use = amdgpu_vcn_ring_end_use,
+ .begin_use = vcn_v1_0_ring_begin_use,
+ .end_use = vcn_v1_0_ring_end_use,
.emit_wreg = vcn_v1_0_dec_ring_emit_wreg,
.emit_reg_wait = vcn_v1_0_dec_ring_emit_reg_wait,
.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
@@ -2252,48 +1949,13 @@ static const struct amdgpu_ring_funcs vcn_v1_0_enc_ring_vm_funcs = {
.insert_nop = amdgpu_ring_insert_nop,
.insert_end = vcn_v1_0_enc_ring_insert_end,
.pad_ib = amdgpu_ring_generic_pad_ib,
- .begin_use = amdgpu_vcn_ring_begin_use,
- .end_use = amdgpu_vcn_ring_end_use,
+ .begin_use = vcn_v1_0_ring_begin_use,
+ .end_use = vcn_v1_0_ring_end_use,
.emit_wreg = vcn_v1_0_enc_ring_emit_wreg,
.emit_reg_wait = vcn_v1_0_enc_ring_emit_reg_wait,
.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
};
-static const struct amdgpu_ring_funcs vcn_v1_0_jpeg_ring_vm_funcs = {
- .type = AMDGPU_RING_TYPE_VCN_JPEG,
- .align_mask = 0xf,
- .nop = PACKET0(0x81ff, 0),
- .support_64bit_ptrs = false,
- .no_user_fence = true,
- .vmhub = AMDGPU_MMHUB_0,
- .extra_dw = 64,
- .get_rptr = vcn_v1_0_jpeg_ring_get_rptr,
- .get_wptr = vcn_v1_0_jpeg_ring_get_wptr,
- .set_wptr = vcn_v1_0_jpeg_ring_set_wptr,
- .emit_frame_size =
- 6 + 6 + /* hdp invalidate / flush */
- SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
- SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
- 8 + /* vcn_v1_0_jpeg_ring_emit_vm_flush */
- 26 + 26 + /* vcn_v1_0_jpeg_ring_emit_fence x2 vm fence */
- 6,
- .emit_ib_size = 22, /* vcn_v1_0_jpeg_ring_emit_ib */
- .emit_ib = vcn_v1_0_jpeg_ring_emit_ib,
- .emit_fence = vcn_v1_0_jpeg_ring_emit_fence,
- .emit_vm_flush = vcn_v1_0_jpeg_ring_emit_vm_flush,
- .test_ring = amdgpu_vcn_jpeg_ring_test_ring,
- .test_ib = amdgpu_vcn_jpeg_ring_test_ib,
- .insert_nop = vcn_v1_0_jpeg_ring_nop,
- .insert_start = vcn_v1_0_jpeg_ring_insert_start,
- .insert_end = vcn_v1_0_jpeg_ring_insert_end,
- .pad_ib = amdgpu_ring_generic_pad_ib,
- .begin_use = amdgpu_vcn_ring_begin_use,
- .end_use = amdgpu_vcn_ring_end_use,
- .emit_wreg = vcn_v1_0_jpeg_ring_emit_wreg,
- .emit_reg_wait = vcn_v1_0_jpeg_ring_emit_reg_wait,
- .emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
-};
-
static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev)
{
adev->vcn.inst->ring_dec.funcs = &vcn_v1_0_dec_ring_vm_funcs;
@@ -2310,12 +1972,6 @@ static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev)
DRM_INFO("VCN encode is enabled in VM mode\n");
}
-static void vcn_v1_0_set_jpeg_ring_funcs(struct amdgpu_device *adev)
-{
- adev->vcn.inst->ring_jpeg.funcs = &vcn_v1_0_jpeg_ring_vm_funcs;
- DRM_INFO("VCN jpeg decode is enabled in VM mode\n");
-}
-
static const struct amdgpu_irq_src_funcs vcn_v1_0_irq_funcs = {
.set = vcn_v1_0_set_interrupt_state,
.process = vcn_v1_0_process_interrupt,
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-06-01 00:41:23 +0000