summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_device.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c9
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c10
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h11
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c2
-rw-r--r--drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h1
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c111
-rw-r--r--drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c24
-rw-r--r--drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h4
-rw-r--r--drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c28
-rw-r--r--drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h3
13 files changed, 194 insertions, 19 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e8b41756c9f9..37da3537ba2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4625,7 +4625,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
retry: /* Rest of adevs pre asic reset from XGMI hive. */
list_for_each_entry(tmp_adev, device_list_handle, gmc.xgmi.head) {
r = amdgpu_device_pre_asic_reset(tmp_adev,
- NULL,
+ (tmp_adev == adev) ? job : NULL,
&need_full_reset);
/*TODO Should we stop ?*/
if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
index 18be544d8c1e..96a9699f87ba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
@@ -208,7 +208,8 @@ static int psp_sw_fini(void *handle)
adev->psp.ta_fw = NULL;
}
- if (adev->asic_type == CHIP_NAVI10)
+ if (adev->asic_type == CHIP_NAVI10 ||
+ adev->asic_type == CHIP_SIENNA_CICHLID)
psp_sysfs_fini(adev);
return 0;
@@ -1750,6 +1751,12 @@ static int psp_get_fw_type(struct amdgpu_firmware_info *ucode,
case AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM:
*type = GFX_FW_TYPE_RLC_RESTORE_LIST_SRM_MEM;
break;
+ case AMDGPU_UCODE_ID_RLC_IRAM:
+ *type = GFX_FW_TYPE_RLC_IRAM;
+ break;
+ case AMDGPU_UCODE_ID_RLC_DRAM:
+ *type = GFX_FW_TYPE_RLC_DRAM_BOOT;
+ break;
case AMDGPU_UCODE_ID_SMC:
*type = GFX_FW_TYPE_SMU;
break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index 8bf6a7c056bc..4e36551ab50b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -1986,7 +1986,8 @@ static int amdgpu_ras_check_asic_type(struct amdgpu_device *adev)
{
if (adev->asic_type != CHIP_VEGA10 &&
adev->asic_type != CHIP_VEGA20 &&
- adev->asic_type != CHIP_ARCTURUS)
+ adev->asic_type != CHIP_ARCTURUS &&
+ adev->asic_type != CHIP_SIENNA_CICHLID)
return 1;
else
return 0;
@@ -2030,7 +2031,6 @@ static void amdgpu_ras_check_supported(struct amdgpu_device *adev,
*supported = amdgpu_ras_enable == 0 ?
0 : *hw_supported & amdgpu_ras_mask;
-
adev->ras_features = *supported;
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
index 60bb3e8b3118..aeaaae713c59 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
@@ -168,12 +168,16 @@ struct amdgpu_rlc {
u32 save_restore_list_cntl_size_bytes;
u32 save_restore_list_gpm_size_bytes;
u32 save_restore_list_srm_size_bytes;
+ u32 rlc_iram_ucode_size_bytes;
+ u32 rlc_dram_ucode_size_bytes;
u32 *register_list_format;
u32 *register_restore;
u8 *save_restore_list_cntl;
u8 *save_restore_list_gpm;
u8 *save_restore_list_srm;
+ u8 *rlc_iram_ucode;
+ u8 *rlc_dram_ucode;
bool is_rlc_v2_1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
index 55fe19a2f332..b313ce4c3e97 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -500,6 +500,8 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL &&
ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM &&
ucode->ucode_id != AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM &&
+ ucode->ucode_id != AMDGPU_UCODE_ID_RLC_IRAM &&
+ ucode->ucode_id != AMDGPU_UCODE_ID_RLC_DRAM &&
ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_ERAM &&
ucode->ucode_id != AMDGPU_UCODE_ID_DMCU_INTV &&
ucode->ucode_id != AMDGPU_UCODE_ID_DMCUB)) {
@@ -556,6 +558,14 @@ static int amdgpu_ucode_init_single_fw(struct amdgpu_device *adev,
ucode->ucode_size = adev->gfx.rlc.save_restore_list_srm_size_bytes;
memcpy(ucode->kaddr, adev->gfx.rlc.save_restore_list_srm,
ucode->ucode_size);
+ } else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_IRAM) {
+ ucode->ucode_size = adev->gfx.rlc.rlc_iram_ucode_size_bytes;
+ memcpy(ucode->kaddr, adev->gfx.rlc.rlc_iram_ucode,
+ ucode->ucode_size);
+ } else if (ucode->ucode_id == AMDGPU_UCODE_ID_RLC_DRAM) {
+ ucode->ucode_size = adev->gfx.rlc.rlc_dram_ucode_size_bytes;
+ memcpy(ucode->kaddr, adev->gfx.rlc.rlc_dram_ucode,
+ ucode->ucode_size);
} else if (ucode->ucode_id == AMDGPU_UCODE_ID_CP_MES) {
ucode->ucode_size = le32_to_cpu(mes_hdr->mes_ucode_size_bytes);
memcpy(ucode->kaddr, (void *)((uint8_t *)adev->mes.fw->data +
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
index 3c23c6293ff9..0e43b46d3ab5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.h
@@ -222,6 +222,15 @@ struct rlc_firmware_header_v2_1 {
uint32_t save_restore_list_srm_offset_bytes;
};
+/* version_major=2, version_minor=1 */
+struct rlc_firmware_header_v2_2 {
+ struct rlc_firmware_header_v2_1 v2_1;
+ uint32_t rlc_iram_ucode_size_bytes;
+ uint32_t rlc_iram_ucode_offset_bytes;
+ uint32_t rlc_dram_ucode_size_bytes;
+ uint32_t rlc_dram_ucode_offset_bytes;
+};
+
/* version_major=1, version_minor=0 */
struct sdma_firmware_header_v1_0 {
struct common_firmware_header header;
@@ -339,6 +348,8 @@ enum AMDGPU_UCODE_ID {
AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL,
AMDGPU_UCODE_ID_RLC_RESTORE_LIST_GPM_MEM,
AMDGPU_UCODE_ID_RLC_RESTORE_LIST_SRM_MEM,
+ AMDGPU_UCODE_ID_RLC_IRAM,
+ AMDGPU_UCODE_ID_RLC_DRAM,
AMDGPU_UCODE_ID_RLC_G,
AMDGPU_UCODE_ID_STORAGE,
AMDGPU_UCODE_ID_SMC,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 495c3d7bb2b2..f3b7287e84c4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -68,6 +68,7 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
INIT_DELAYED_WORK(&adev->vcn.idle_work, amdgpu_vcn_idle_work_handler);
mutex_init(&adev->vcn.vcn_pg_lock);
+ mutex_init(&adev->vcn.vcn1_jpeg1_workaround);
atomic_set(&adev->vcn.total_submission_cnt, 0);
for (i = 0; i < adev->vcn.num_vcn_inst; i++)
atomic_set(&adev->vcn.inst[i].dpg_enc_submission_cnt, 0);
@@ -237,6 +238,7 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
}
release_firmware(adev->vcn.fw);
+ mutex_destroy(&adev->vcn.vcn1_jpeg1_workaround);
mutex_destroy(&adev->vcn.vcn_pg_lock);
return 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 7a9b804bc988..17691158f783 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -220,6 +220,7 @@ struct amdgpu_vcn {
struct amdgpu_vcn_inst inst[AMDGPU_MAX_VCN_INSTANCES];
struct amdgpu_vcn_reg internal;
struct mutex vcn_pg_lock;
+ struct mutex vcn1_jpeg1_workaround;
atomic_t total_submission_cnt;
unsigned harvest_config;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 9792ec737029..56fdbe626d30 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -112,6 +112,22 @@
#define mmCP_HYP_ME_UCODE_DATA 0x5817
#define mmCP_HYP_ME_UCODE_DATA_BASE_IDX 1
+//CC_GC_SA_UNIT_DISABLE
+#define mmCC_GC_SA_UNIT_DISABLE 0x0fe9
+#define mmCC_GC_SA_UNIT_DISABLE_BASE_IDX 0
+#define CC_GC_SA_UNIT_DISABLE__SA_DISABLE__SHIFT 0x8
+#define CC_GC_SA_UNIT_DISABLE__SA_DISABLE_MASK 0x0000FF00L
+//GC_USER_SA_UNIT_DISABLE
+#define mmGC_USER_SA_UNIT_DISABLE 0x0fea
+#define mmGC_USER_SA_UNIT_DISABLE_BASE_IDX 0
+#define GC_USER_SA_UNIT_DISABLE__SA_DISABLE__SHIFT 0x8
+#define GC_USER_SA_UNIT_DISABLE__SA_DISABLE_MASK 0x0000FF00L
+//PA_SC_ENHANCE_3
+#define mmPA_SC_ENHANCE_3 0x1085
+#define mmPA_SC_ENHANCE_3_BASE_IDX 0
+#define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO__SHIFT 0x3
+#define PA_SC_ENHANCE_3__FORCE_PBB_WORKLOAD_MODE_TO_ZERO_MASK 0x00000008L
+
MODULE_FIRMWARE("amdgpu/navi10_ce.bin");
MODULE_FIRMWARE("amdgpu/navi10_pfp.bin");
MODULE_FIRMWARE("amdgpu/navi10_me.bin");
@@ -3091,6 +3107,7 @@ static const struct soc15_reg_golden golden_settings_gc_10_3[] =
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_ADDR_MATCH_MASK, 0xffffffff, 0xffffffcf),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CM_CTRL1, 0xff8fff0f, 0x580f1008),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmGL2C_CTRL3, 0xf7ffffff, 0x10f80988),
+ SOC15_REG_GOLDEN_VALUE(GC, 0, mmLDS_CONFIG, 0x00000020, 0x00000020),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_CL_ENHANCE, 0xf17fffff, 0x01200007),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_BINNER_TIMEOUT_COUNTER, 0xffffffff, 0x00000800),
SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_2, 0xffffffbf, 0x00000820),
@@ -3188,6 +3205,8 @@ static int gfx_v10_0_wait_for_rlc_autoload_complete(struct amdgpu_device *adev);
static void gfx_v10_0_ring_emit_ce_meta(struct amdgpu_ring *ring, bool resume);
static void gfx_v10_0_ring_emit_de_meta(struct amdgpu_ring *ring, bool resume);
static void gfx_v10_0_ring_emit_frame_cntl(struct amdgpu_ring *ring, bool start, bool secure);
+static u32 gfx_v10_3_get_disabled_sa(struct amdgpu_device *adev);
+static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev);
static void gfx10_kiq_set_resources(struct amdgpu_ring *kiq_ring, uint64_t queue_mask)
{
@@ -3586,6 +3605,17 @@ static void gfx_v10_0_init_rlc_ext_microcode(struct amdgpu_device *adev)
le32_to_cpu(rlc_hdr->reg_list_format_direct_reg_list_length);
}
+static void gfx_v10_0_init_rlc_iram_dram_microcode(struct amdgpu_device *adev)
+{
+ const struct rlc_firmware_header_v2_2 *rlc_hdr;
+
+ rlc_hdr = (const struct rlc_firmware_header_v2_2 *)adev->gfx.rlc_fw->data;
+ adev->gfx.rlc.rlc_iram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_iram_ucode_size_bytes);
+ adev->gfx.rlc.rlc_iram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_iram_ucode_offset_bytes);
+ adev->gfx.rlc.rlc_dram_ucode_size_bytes = le32_to_cpu(rlc_hdr->rlc_dram_ucode_size_bytes);
+ adev->gfx.rlc.rlc_dram_ucode = (u8 *)rlc_hdr + le32_to_cpu(rlc_hdr->rlc_dram_ucode_offset_bytes);
+}
+
static bool gfx_v10_0_navi10_gfxoff_should_enable(struct amdgpu_device *adev)
{
bool ret = false;
@@ -3701,8 +3731,6 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
rlc_hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
version_major = le16_to_cpu(rlc_hdr->header.header_version_major);
version_minor = le16_to_cpu(rlc_hdr->header.header_version_minor);
- if (version_major == 2 && version_minor == 1)
- adev->gfx.rlc.is_rlc_v2_1 = true;
adev->gfx.rlc_fw_version = le32_to_cpu(rlc_hdr->header.ucode_version);
adev->gfx.rlc_feature_version = le32_to_cpu(rlc_hdr->ucode_feature_version);
@@ -3744,8 +3772,12 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++)
adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]);
- if (adev->gfx.rlc.is_rlc_v2_1)
- gfx_v10_0_init_rlc_ext_microcode(adev);
+ if (version_major == 2) {
+ if (version_minor >= 1)
+ gfx_v10_0_init_rlc_ext_microcode(adev);
+ if (version_minor == 2)
+ gfx_v10_0_init_rlc_iram_dram_microcode(adev);
+ }
}
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks);
@@ -3806,8 +3838,7 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
adev->firmware.fw_size +=
ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
}
- if (adev->gfx.rlc.is_rlc_v2_1 &&
- adev->gfx.rlc.save_restore_list_cntl_size_bytes &&
+ if (adev->gfx.rlc.save_restore_list_cntl_size_bytes &&
adev->gfx.rlc.save_restore_list_gpm_size_bytes &&
adev->gfx.rlc.save_restore_list_srm_size_bytes) {
info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL];
@@ -3827,6 +3858,21 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
info->fw = adev->gfx.rlc_fw;
adev->firmware.fw_size +=
ALIGN(adev->gfx.rlc.save_restore_list_srm_size_bytes, PAGE_SIZE);
+
+ if (adev->gfx.rlc.rlc_iram_ucode_size_bytes &&
+ adev->gfx.rlc.rlc_dram_ucode_size_bytes) {
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_IRAM];
+ info->ucode_id = AMDGPU_UCODE_ID_RLC_IRAM;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.rlc_iram_ucode_size_bytes, PAGE_SIZE);
+
+ info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_DRAM];
+ info->ucode_id = AMDGPU_UCODE_ID_RLC_DRAM;
+ info->fw = adev->gfx.rlc_fw;
+ adev->firmware.fw_size +=
+ ALIGN(adev->gfx.rlc.rlc_dram_ucode_size_bytes, PAGE_SIZE);
+ }
}
info = &adev->firmware.ucode[AMDGPU_UCODE_ID_CP_MEC1];
@@ -4536,12 +4582,17 @@ static void gfx_v10_0_setup_rb(struct amdgpu_device *adev)
int i, j;
u32 data;
u32 active_rbs = 0;
+ u32 bitmap;
u32 rb_bitmap_width_per_sh = adev->gfx.config.max_backends_per_se /
adev->gfx.config.max_sh_per_se;
mutex_lock(&adev->grbm_idx_mutex);
for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+ bitmap = i * adev->gfx.config.max_sh_per_se + j;
+ if ((adev->asic_type == CHIP_SIENNA_CICHLID) &&
+ ((gfx_v10_3_get_disabled_sa(adev) >> bitmap) & 1))
+ continue;
gfx_v10_0_select_se_sh(adev, i, j, 0xffffffff);
data = gfx_v10_0_get_rb_active_bitmap(adev);
active_rbs |= data << ((i * adev->gfx.config.max_sh_per_se + j) *
@@ -6950,6 +7001,9 @@ static int gfx_v10_0_hw_init(void *handle)
if (r)
return r;
+ if (adev->asic_type == CHIP_SIENNA_CICHLID)
+ gfx_v10_3_program_pbb_mode(adev);
+
return r;
}
@@ -8763,6 +8817,10 @@ static int gfx_v10_0_get_cu_info(struct amdgpu_device *adev,
mutex_lock(&adev->grbm_idx_mutex);
for (i = 0; i < adev->gfx.config.max_shader_engines; i++) {
for (j = 0; j < adev->gfx.config.max_sh_per_se; j++) {
+ bitmap = i * adev->gfx.config.max_sh_per_se + j;
+ if ((adev->asic_type == CHIP_SIENNA_CICHLID) &&
+ ((gfx_v10_3_get_disabled_sa(adev) >> bitmap) & 1))
+ continue;
mask = 1;
ao_bitmap = 0;
counter = 0;
@@ -8797,6 +8855,47 @@ static int gfx_v10_0_get_cu_info(struct amdgpu_device *adev,
return 0;
}
+static u32 gfx_v10_3_get_disabled_sa(struct amdgpu_device *adev)
+{
+ uint32_t efuse_setting, vbios_setting, disabled_sa, max_sa_mask;
+
+ efuse_setting = RREG32_SOC15(GC, 0, mmCC_GC_SA_UNIT_DISABLE);
+ efuse_setting &= CC_GC_SA_UNIT_DISABLE__SA_DISABLE_MASK;
+ efuse_setting >>= CC_GC_SA_UNIT_DISABLE__SA_DISABLE__SHIFT;
+
+ vbios_setting = RREG32_SOC15(GC, 0, mmGC_USER_SA_UNIT_DISABLE);
+ vbios_setting &= GC_USER_SA_UNIT_DISABLE__SA_DISABLE_MASK;
+ vbios_setting >>= GC_USER_SA_UNIT_DISABLE__SA_DISABLE__SHIFT;
+
+ max_sa_mask = amdgpu_gfx_create_bitmask(adev->gfx.config.max_sh_per_se *
+ adev->gfx.config.max_shader_engines);
+ disabled_sa = efuse_setting | vbios_setting;
+ disabled_sa &= max_sa_mask;
+
+ return disabled_sa;
+}
+
+static void gfx_v10_3_program_pbb_mode(struct amdgpu_device *adev)
+{
+ uint32_t max_sa_per_se, max_sa_per_se_mask, max_shader_engines;
+ uint32_t disabled_sa_mask, se_index, disabled_sa_per_se;
+
+ disabled_sa_mask = gfx_v10_3_get_disabled_sa(adev);
+
+ max_sa_per_se = adev->gfx.config.max_sh_per_se;
+ max_sa_per_se_mask = (1 << max_sa_per_se) - 1;
+ max_shader_engines = adev->gfx.config.max_shader_engines;
+
+ for (se_index = 0; max_shader_engines > se_index; se_index++) {
+ disabled_sa_per_se = disabled_sa_mask >> (se_index * max_sa_per_se);
+ disabled_sa_per_se &= max_sa_per_se_mask;
+ if (disabled_sa_per_se == max_sa_per_se_mask) {
+ WREG32_FIELD15(GC, 0, PA_SC_ENHANCE_3, FORCE_PBB_WORKLOAD_MODE_TO_ZERO, 1);
+ break;
+ }
+ }
+}
+
const struct amdgpu_ip_block_version gfx_v10_0_ip_block =
{
.type = AMD_IP_BLOCK_TYPE_GFX,
diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
index bc300283b6ab..c600b61b5f45 100644
--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
@@ -33,6 +33,7 @@
static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev);
+static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring);
static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val)
{
@@ -564,8 +565,8 @@ static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = {
.insert_start = jpeg_v1_0_decode_ring_insert_start,
.insert_end = jpeg_v1_0_decode_ring_insert_end,
.pad_ib = amdgpu_ring_generic_pad_ib,
- .begin_use = vcn_v1_0_ring_begin_use,
- .end_use = amdgpu_vcn_ring_end_use,
+ .begin_use = jpeg_v1_0_ring_begin_use,
+ .end_use = vcn_v1_0_ring_end_use,
.emit_wreg = jpeg_v1_0_decode_ring_emit_wreg,
.emit_reg_wait = jpeg_v1_0_decode_ring_emit_reg_wait,
.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
@@ -586,3 +587,22 @@ static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev)
{
adev->jpeg.inst->irq.funcs = &jpeg_v1_0_irq_funcs;
}
+
+static void jpeg_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);
+ int cnt = 0;
+
+ mutex_lock(&adev->vcn.vcn1_jpeg1_workaround);
+
+ if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_dec))
+ DRM_ERROR("JPEG dec: vcn dec ring may not be empty\n");
+
+ for (cnt = 0; cnt < adev->vcn.num_enc_rings; cnt++) {
+ if (amdgpu_fence_wait_empty(&adev->vcn.inst->ring_enc[cnt]))
+ DRM_ERROR("JPEG dec: vcn enc ring[%d] may not be empty\n", cnt);
+ }
+
+ vcn_v1_0_set_pg_for_begin_use(ring, set_clocks);
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
index 1ef2f5b1d828..4137dc710aaf 100644
--- a/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
+++ b/drivers/gpu/drm/amd/amdgpu/psp_gfx_if.h
@@ -201,7 +201,7 @@ enum psp_gfx_fw_type {
GFX_FW_TYPE_UVD1 = 23, /* UVD1 VG-20 */
GFX_FW_TYPE_TOC = 24, /* TOC NV-10 */
GFX_FW_TYPE_RLC_P = 25, /* RLC P NV */
- GFX_FW_TYPE_RLX6 = 26, /* RLX6 NV */
+ GFX_FW_TYPE_RLC_IRAM = 26, /* RLC_IRAM NV */
GFX_FW_TYPE_GLOBAL_TAP_DELAYS = 27, /* GLOBAL TAP DELAYS NV */
GFX_FW_TYPE_SE0_TAP_DELAYS = 28, /* SE0 TAP DELAYS NV */
GFX_FW_TYPE_SE1_TAP_DELAYS = 29, /* SE1 TAP DELAYS NV */
@@ -223,7 +223,7 @@ enum psp_gfx_fw_type {
GFX_FW_TYPE_ACCUM_CTRL_RAM = 45, /* ACCUM CTRL RAM NV */
GFX_FW_TYPE_RLCP_CAM = 46, /* RLCP CAM NV */
GFX_FW_TYPE_RLC_SPP_CAM_EXT = 47, /* RLC SPP CAM EXT NV */
- GFX_FW_TYPE_RLX6_DRAM_BOOT = 48, /* RLX6 DRAM BOOT NV */
+ GFX_FW_TYPE_RLC_DRAM_BOOT = 48, /* RLC DRAM BOOT NV */
GFX_FW_TYPE_VCN0_RAM = 49, /* VCN_RAM NV + RN */
GFX_FW_TYPE_VCN1_RAM = 50, /* VCN_RAM NV + RN */
GFX_FW_TYPE_DMUB = 51, /* DMUB RN */
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 73699eafb51e..86e1ef732ebe 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -54,6 +54,7 @@ static int vcn_v1_0_pause_dpg_mode(struct amdgpu_device *adev,
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
@@ -1804,11 +1805,24 @@ static void vcn_v1_0_idle_work_handler(struct work_struct *work)
}
}
-void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
+static void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
{
- struct amdgpu_device *adev = ring->adev;
+ 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)
@@ -1844,6 +1858,12 @@ void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring)
}
}
+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,
@@ -1891,7 +1911,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_dec_ring_vm_funcs = {
.insert_end = vcn_v1_0_dec_ring_insert_end,
.pad_ib = amdgpu_ring_generic_pad_ib,
.begin_use = vcn_v1_0_ring_begin_use,
- .end_use = amdgpu_vcn_ring_end_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,
@@ -1923,7 +1943,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_enc_ring_vm_funcs = {
.insert_end = vcn_v1_0_enc_ring_insert_end,
.pad_ib = amdgpu_ring_generic_pad_ib,
.begin_use = vcn_v1_0_ring_begin_use,
- .end_use = amdgpu_vcn_ring_end_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,
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h
index f67d7391fc21..1f1cc7f0ece7 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.h
@@ -24,7 +24,8 @@
#ifndef __VCN_V1_0_H__
#define __VCN_V1_0_H__
-void vcn_v1_0_ring_begin_use(struct amdgpu_ring *ring);
+void vcn_v1_0_ring_end_use(struct amdgpu_ring *ring);
+void vcn_v1_0_set_pg_for_begin_use(struct amdgpu_ring *ring, bool set_clocks);
extern const struct amdgpu_ip_block_version vcn_v1_0_ip_block;
generated by cgit (git 2.34.1) at 2024-06-04 12:35:51 +0000