summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2019-12-06 10:28:09 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2019-12-06 10:28:09 -0800
commit7ada90eb9c7ae4a8eb066f8e9b4d80122f0363db (patch)
treefbc06c7dacd988b6bed69b509ceef7cd41d743ac /drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
parent9feb1af97e7366b512ecb9e4dd61d3252074cda3 (diff)
parent9c1867d730a6e1dc23dd633392d102860578c047 (diff)
Merge tag 'drm-next-2019-12-06' of git://anongit.freedesktop.org/drm/drm
Pull more drm updates from Dave Airlie: "Rob pointed out I missed his pull request for msm-next, it's been in next for a while outside of my tree so shouldn't cause any unexpected issues, it has some OCMEM support in drivers/soc that is acked by other maintainers as it's outside my tree. Otherwise it's a usual fixes pull, i915, amdgpu, the main ones, with some tegra, omap, mgag200 and one core fix. Summary: msm-next: - OCMEM support for a3xx and a4xx GPUs. - a510 support + display support core: - mst payload deletion fix i915: - uapi alignment fix - fix for power usage regression due to security fixes - change default preemption timeout to 640ms from 100ms - EHL voltage level display fixes - TGL DGL PHY fix - gvt - MI_ATOMIC cmd parser fix, CFL non-priv warning - CI spotted deadlock fix - EHL port D programming fix amdgpu: - VRAM lost fixes on BACO for CI/VI - navi14 DC fixes - misc SR-IOV, gfx10 fixes - XGMI fixes for arcturus - SRIOV fixes amdkfd: - KFD on ppc64le enabled - page table optimisations radeon: - fix for r1xx/2xx register checker. tegra: - displayport regression fixes - DMA API regression fixes mgag200: - fix devices that can't scanout except at 0 addr omap: - fix dma_addr refcounting" * tag 'drm-next-2019-12-06' of git://anongit.freedesktop.org/drm/drm: (100 commits) drm/dp_mst: Correct the bug in drm_dp_update_payload_part1() drm/omap: fix dma_addr refcounting drm/tegra: Run hub cleanup on ->remove() drm/tegra: sor: Make the +5V HDMI supply optional drm/tegra: Silence expected errors on IOMMU attach drm/tegra: vic: Export module device table drm/tegra: sor: Implement system suspend/resume drm/tegra: Use proper IOVA address for cursor image drm/tegra: gem: Remove premature import restrictions drm/tegra: gem: Properly pin imported buffers drm/tegra: hub: Remove bogus connection mutex check ia64: agp: Replace empty define with do while agp: Add bridge parameter documentation agp: remove unused variable num_segments agp: move AGPGART_MINOR to include/linux/miscdevice.h agp: remove unused variable size in agp_generic_create_gatt_table drm/dp_mst: Fix build on systems with STACKTRACE_SUPPORT=n drm/radeon: fix r1xx/r2xx register checker for POT textures drm/amdgpu: fix GFX10 missing CSIB set(v3) drm/amdgpu: should stop GFX ring in hw_fini ...
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c178
1 files changed, 51 insertions, 127 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index ca5f0e7ea1ac..f2c1b026397b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -690,59 +690,61 @@ static int gfx_v10_0_init_microcode(struct amdgpu_device *adev)
adev->gfx.ce_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
adev->gfx.ce_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
- snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
- err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
- if (err)
- goto out;
- err = amdgpu_ucode_validate(adev->gfx.rlc_fw);
- 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);
- adev->gfx.rlc.save_and_restore_offset =
+ if (!amdgpu_sriov_vf(adev)) {
+ snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
+ err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
+ if (err)
+ goto out;
+ err = amdgpu_ucode_validate(adev->gfx.rlc_fw);
+ 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);
+ adev->gfx.rlc.save_and_restore_offset =
le32_to_cpu(rlc_hdr->save_and_restore_offset);
- adev->gfx.rlc.clear_state_descriptor_offset =
+ adev->gfx.rlc.clear_state_descriptor_offset =
le32_to_cpu(rlc_hdr->clear_state_descriptor_offset);
- adev->gfx.rlc.avail_scratch_ram_locations =
+ adev->gfx.rlc.avail_scratch_ram_locations =
le32_to_cpu(rlc_hdr->avail_scratch_ram_locations);
- adev->gfx.rlc.reg_restore_list_size =
+ adev->gfx.rlc.reg_restore_list_size =
le32_to_cpu(rlc_hdr->reg_restore_list_size);
- adev->gfx.rlc.reg_list_format_start =
+ adev->gfx.rlc.reg_list_format_start =
le32_to_cpu(rlc_hdr->reg_list_format_start);
- adev->gfx.rlc.reg_list_format_separate_start =
+ adev->gfx.rlc.reg_list_format_separate_start =
le32_to_cpu(rlc_hdr->reg_list_format_separate_start);
- adev->gfx.rlc.starting_offsets_start =
+ adev->gfx.rlc.starting_offsets_start =
le32_to_cpu(rlc_hdr->starting_offsets_start);
- adev->gfx.rlc.reg_list_format_size_bytes =
+ adev->gfx.rlc.reg_list_format_size_bytes =
le32_to_cpu(rlc_hdr->reg_list_format_size_bytes);
- adev->gfx.rlc.reg_list_size_bytes =
+ adev->gfx.rlc.reg_list_size_bytes =
le32_to_cpu(rlc_hdr->reg_list_size_bytes);
- adev->gfx.rlc.register_list_format =
+ adev->gfx.rlc.register_list_format =
kmalloc(adev->gfx.rlc.reg_list_format_size_bytes +
- adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL);
- if (!adev->gfx.rlc.register_list_format) {
- err = -ENOMEM;
- goto out;
- }
+ adev->gfx.rlc.reg_list_size_bytes, GFP_KERNEL);
+ if (!adev->gfx.rlc.register_list_format) {
+ err = -ENOMEM;
+ goto out;
+ }
- tmp = (unsigned int *)((uintptr_t)rlc_hdr +
- le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes));
- for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++)
- adev->gfx.rlc.register_list_format[i] = le32_to_cpu(tmp[i]);
+ tmp = (unsigned int *)((uintptr_t)rlc_hdr +
+ le32_to_cpu(rlc_hdr->reg_list_format_array_offset_bytes));
+ for (i = 0 ; i < (rlc_hdr->reg_list_format_size_bytes >> 2); i++)
+ adev->gfx.rlc.register_list_format[i] = le32_to_cpu(tmp[i]);
- adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i;
+ adev->gfx.rlc.register_restore = adev->gfx.rlc.register_list_format + i;
- tmp = (unsigned int *)((uintptr_t)rlc_hdr +
- le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes));
- for (i = 0 ; i < (rlc_hdr->reg_list_size_bytes >> 2); i++)
- adev->gfx.rlc.register_restore[i] = le32_to_cpu(tmp[i]);
+ tmp = (unsigned int *)((uintptr_t)rlc_hdr +
+ le32_to_cpu(rlc_hdr->reg_list_array_offset_bytes));
+ 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 (adev->gfx.rlc.is_rlc_v2_1)
+ gfx_v10_0_init_rlc_ext_microcode(adev);
+ }
snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec%s.bin", chip_name, wks);
err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
@@ -993,39 +995,6 @@ static int gfx_v10_0_rlc_init(struct amdgpu_device *adev)
return 0;
}
-static int gfx_v10_0_csb_vram_pin(struct amdgpu_device *adev)
-{
- int r;
-
- r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
- if (unlikely(r != 0))
- return r;
-
- r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj,
- AMDGPU_GEM_DOMAIN_VRAM);
- if (!r)
- adev->gfx.rlc.clear_state_gpu_addr =
- amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj);
-
- amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
-
- return r;
-}
-
-static void gfx_v10_0_csb_vram_unpin(struct amdgpu_device *adev)
-{
- int r;
-
- if (!adev->gfx.rlc.clear_state_obj)
- return;
-
- r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true);
- if (likely(r == 0)) {
- amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
- amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
- }
-}
-
static void gfx_v10_0_mec_fini(struct amdgpu_device *adev)
{
amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
@@ -1787,25 +1756,7 @@ static void gfx_v10_0_enable_gui_idle_interrupt(struct amdgpu_device *adev,
static int gfx_v10_0_init_csb(struct amdgpu_device *adev)
{
- int r;
-
- if (adev->in_gpu_reset) {
- r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
- if (r)
- return r;
-
- r = amdgpu_bo_kmap(adev->gfx.rlc.clear_state_obj,
- (void **)&adev->gfx.rlc.cs_ptr);
- if (!r) {
- adev->gfx.rlc.funcs->get_csb_buffer(adev,
- adev->gfx.rlc.cs_ptr);
- amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj);
- }
-
- amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
- if (r)
- return r;
- }
+ adev->gfx.rlc.funcs->get_csb_buffer(adev, adev->gfx.rlc.cs_ptr);
/* csib */
WREG32_SOC15(GC, 0, mmRLC_CSIB_ADDR_HI,
@@ -1817,22 +1768,6 @@ static int gfx_v10_0_init_csb(struct amdgpu_device *adev)
return 0;
}
-static int gfx_v10_0_init_pg(struct amdgpu_device *adev)
-{
- int i;
- int r;
-
- r = gfx_v10_0_init_csb(adev);
- if (r)
- return r;
-
- for (i = 0; i < adev->num_vmhubs; i++)
- amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0);
-
- /* TODO: init power gating */
- return 0;
-}
-
void gfx_v10_0_rlc_stop(struct amdgpu_device *adev)
{
u32 tmp = RREG32_SOC15(GC, 0, mmRLC_CNTL);
@@ -1925,21 +1860,16 @@ static int gfx_v10_0_rlc_resume(struct amdgpu_device *adev)
{
int r;
- if (amdgpu_sriov_vf(adev))
- return 0;
-
if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
- r = gfx_v10_0_wait_for_rlc_autoload_complete(adev);
- if (r)
- return r;
- r = gfx_v10_0_init_pg(adev);
+ r = gfx_v10_0_wait_for_rlc_autoload_complete(adev);
if (r)
return r;
- /* enable RLC SRM */
- gfx_v10_0_rlc_enable_srm(adev);
+ gfx_v10_0_init_csb(adev);
+ if (!amdgpu_sriov_vf(adev)) /* enable RLC SRM */
+ gfx_v10_0_rlc_enable_srm(adev);
} else {
adev->gfx.rlc.funcs->stop(adev);
@@ -1961,9 +1891,7 @@ static int gfx_v10_0_rlc_resume(struct amdgpu_device *adev)
return r;
}
- r = gfx_v10_0_init_pg(adev);
- if (r)
- return r;
+ gfx_v10_0_init_csb(adev);
adev->gfx.rlc.funcs->start(adev);
@@ -2825,7 +2753,7 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
/* Init gfx ring 0 for pipe 0 */
mutex_lock(&adev->srbm_mutex);
gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID0);
- mutex_unlock(&adev->srbm_mutex);
+
/* Set ring buffer size */
ring = &adev->gfx.gfx_ring[0];
rb_bufsz = order_base_2(ring->ring_size / 8);
@@ -2863,11 +2791,11 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
WREG32_SOC15(GC, 0, mmCP_RB_ACTIVE, 1);
gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
+ mutex_unlock(&adev->srbm_mutex);
/* Init gfx ring 1 for pipe 1 */
mutex_lock(&adev->srbm_mutex);
gfx_v10_0_cp_gfx_switch_pipe(adev, PIPE_ID1);
- mutex_unlock(&adev->srbm_mutex);
ring = &adev->gfx.gfx_ring[1];
rb_bufsz = order_base_2(ring->ring_size / 8);
tmp = REG_SET_FIELD(0, CP_RB1_CNTL, RB_BUFSZ, rb_bufsz);
@@ -2897,6 +2825,7 @@ static int gfx_v10_0_cp_gfx_resume(struct amdgpu_device *adev)
WREG32_SOC15(GC, 0, mmCP_RB1_ACTIVE, 1);
gfx_v10_0_cp_gfx_set_doorbell(adev, ring);
+ mutex_unlock(&adev->srbm_mutex);
/* Switch to pipe 0 */
mutex_lock(&adev->srbm_mutex);
@@ -3775,10 +3704,6 @@ static int gfx_v10_0_hw_init(void *handle)
int r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- r = gfx_v10_0_csb_vram_pin(adev);
- if (r)
- return r;
-
if (!amdgpu_emu_mode)
gfx_v10_0_init_golden_registers(adev);
@@ -3861,12 +3786,11 @@ static int gfx_v10_0_hw_fini(void *handle)
if (amdgpu_gfx_disable_kcq(adev))
DRM_ERROR("KCQ disable failed\n");
if (amdgpu_sriov_vf(adev)) {
- pr_debug("For SRIOV client, shouldn't do anything.\n");
+ gfx_v10_0_cp_gfx_enable(adev, false);
return 0;
}
gfx_v10_0_cp_enable(adev, false);
gfx_v10_0_enable_gui_idle_interrupt(adev, false);
- gfx_v10_0_csb_vram_unpin(adev);
return 0;
}