META-DATA is used in GFX cmd submit, we have two
types of META-DATA now, one is legacy and the other
is for chained-ib-preemption, which is used in vulkan
UMD.
Change-Id: I17324905b4822a93fd3ffb3e8f86e544871b89ab
Signed-off-by: Monk Liu <Monk.Liu at amd.com>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h | 1 +
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 8 +++
drivers/gpu/drm/amd/amdgpu/vi.h | 112 +++++++++++++++++++++++++++++++
3 files changed, 121 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index fa1d569..cf1c94b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -34,6 +34,7 @@ struct amdgpu_virt {
uint32_t caps;
struct amdgpu_bo *csa_obj;
uint64_t csa_vmid0_addr;
+ bool chained_ib_support;
};
#define AMDGPU_CSA_SIZE (8 * 1024)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index a9087f0..375784d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -941,6 +941,14 @@ static int gfx_v8_0_init_microcode(struct amdgpu_device *adev)
goto out;
cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data;
adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
+
+ /* chain ib ucode isn't formal released, use fake number 999 should be enough
+ * we need to change 999 to a correct value after chain ib preemption landed in
+ * formal ucode release
+ */
+ if (adev->gfx.me_fw_version > 999) {
+ adev->virt.chained_ib_support = true;
+ }
adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.h b/drivers/gpu/drm/amd/amdgpu/vi.h
index 575d7ae..719587b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.h
+++ b/drivers/gpu/drm/amd/amdgpu/vi.h
@@ -28,4 +28,116 @@ void vi_srbm_select(struct amdgpu_device *adev,
u32 me, u32 pipe, u32 queue, u32 vmid);
int vi_set_ip_blocks(struct amdgpu_device *adev);
+struct amdgpu_ce_ib_state
+{
+ uint32_t ce_ib_completion_status;
+ uint32_t ce_constegnine_count;
+ uint32_t ce_ibOffset_ib1;
+ uint32_t ce_ibOffset_ib2;
+}; /* Total of 4 DWORD */
+
+struct amdgpu_de_ib_state
+{
+ uint32_t ib_completion_status;
+ uint32_t de_constEngine_count;
+ uint32_t ib_offset_ib1;
+ uint32_t ib_offset_ib2;
+ uint32_t preamble_begin_ib1;
+ uint32_t preamble_begin_ib2;
+ uint32_t preamble_end_ib1;
+ uint32_t preamble_end_ib2;
+ uint32_t draw_indirect_baseLo;
+ uint32_t draw_indirect_baseHi;
+ uint32_t disp_indirect_baseLo;
+ uint32_t disp_indirect_baseHi;
+ uint32_t gds_backup_addrlo;
+ uint32_t gds_backup_addrhi;
+ uint32_t index_base_addrlo;
+ uint32_t index_base_addrhi;
+ uint32_t sample_cntl;
+}; /* Total of 17 DWORD */
+
+struct amdgpu_ce_ib_state_chained_ib
+{
+ /* section of non chained ib part */
+ uint32_t ce_ib_completion_status;
+ uint32_t ce_constegnine_count;
+ uint32_t ce_ibOffset_ib1;
+ uint32_t ce_ibOffset_ib2;
+
+ /* section of chained ib */
+ uint32_t ce_chainib_addrlo_ib1;
+ uint32_t ce_chainib_addrlo_ib2;
+ uint32_t ce_chainib_addrhi_ib1;
+ uint32_t ce_chainib_addrhi_ib2;
+ uint32_t ce_chainib_size_ib1;
+ uint32_t ce_chainib_size_ib2;
+}; /* total 10 DWORD */
+
+struct amdgpu_de_ib_state_chained_ib
+{
+ /* section of non chained ib part */
+ uint32_t ib_completion_status;
+ uint32_t de_constEngine_count;
+ uint32_t ib_offset_ib1;
+ uint32_t ib_offset_ib2;
+
+ /* section of chained ib */
+ uint32_t chain_ib_addrlo_ib1;
+ uint32_t chain_ib_addrlo_ib2;
+ uint32_t chain_ib_addrhi_ib1;
+ uint32_t chain_ib_addrhi_ib2;
+ uint32_t chain_ib_size_ib1;
+ uint32_t chain_ib_size_ib2;
+
+ /* section of non chained ib part */
+ uint32_t preamble_begin_ib1;
+ uint32_t preamble_begin_ib2;
+ uint32_t preamble_end_ib1;
+ uint32_t preamble_end_ib2;
+
+ /* section of chained ib */
+ uint32_t chain_ib_pream_addrlo_ib1;
+ uint32_t chain_ib_pream_addrlo_ib2;
+ uint32_t chain_ib_pream_addrhi_ib1;
+ uint32_t chain_ib_pream_addrhi_ib2;
+
+ /* section of non chained ib part */
+ uint32_t draw_indirect_baseLo;
+ uint32_t draw_indirect_baseHi;
+ uint32_t disp_indirect_baseLo;
+ uint32_t disp_indirect_baseHi;
+ uint32_t gds_backup_addrlo;
+ uint32_t gds_backup_addrhi;
+ uint32_t index_base_addrlo;
+ uint32_t index_base_addrhi;
+ uint32_t sample_cntl;
+}; /* Total of 27 DWORD */
+
+struct amdgpu_gfx_meta_data
+{
+ /* 4 DWORD, address must be 4KB aligned */
+ struct amdgpu_ce_ib_state ce_payload;
+ uint32_t reserved1[60];
+ /* 17 DWORD, address must be 64B aligned */
+ struct amdgpu_de_ib_state de_payload;
+ /* PFP IB base address which get pre-empted */
+ uint32_t DeIbBaseAddrLo;
+ uint32_t DeIbBaseAddrHi;
+ uint32_t reserved2[941];
+}; /* Total of 4K Bytes */
+
+struct amdgpu_gfx_meta_data_chained_ib
+{
+ /* 10 DWORD, address must be 4KB aligned */
+ struct amdgpu_ce_ib_state_chained_ib ce_payload;
+ uint32_t reserved1[54];
+ /* 27 DWORD, address must be 64B aligned */
+ struct amdgpu_de_ib_state_chained_ib de_payload;
+ /* PFP IB base address which get pre-empted */
+ uint32_t DeIbBaseAddrLo;
+ uint32_t DeIbBaseAddrHi;
+ uint32_t reserved2[931];
+}; /* Total of 4K Bytes */
+
#endif
--
2.7.4
