summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-07-01 12:53:43 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-07-01 12:53:43 -0700
commite058a84bfddc42ba356a2316f2cf1141974625c9 (patch)
treee6a02dd913e83f44ea9f5a779f9b9bd56d06a9e3 /drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
parentc288d9cd710433e5991d58a0764c4d08a933b871 (diff)
parent8a02ea42bc1d4c448caf1bab0e05899dad503f74 (diff)
Merge tag 'drm-next-2021-07-01' of git://anongit.freedesktop.org/drm/drm
Pull drm updates from Dave Airlie: "Highlights: - AMD enables two more GPUs, with resulting header files - i915 has started to move to TTM for discrete GPU and enable DG1 discrete GPU support (not by default yet) - new HyperV drm driver - vmwgfx adds arm64 support - TTM refactoring ongoing - 16bpc display support for AMD hw Otherwise it's just the usual insane amounts of work all over the place in lots of drivers and the core, as mostly summarised below: Core: - mark AGP ioctls as legacy - disable force probing for non-master clients - HDR metadata property helpers - HDMI infoframe signal colorimetry support - remove drm_device.pdev pointer - remove DRM_KMS_FB_HELPER config option - remove drm_pci_alloc/free - drm_err_*/drm_dbg_* helpers - use drm driver names for fbdev - leaked DMA handle fix - 16bpc fixed point format fourcc - add prefetching memcpy for WC - Documentation fixes aperture: - add aperture ownership helpers dp: - aux fixes - downstream 0 port handling - use extended base receiver capability DPCD - Rename DP_PSR_SELECTIVE_UPDATE to better mach eDP spec - mst: use khz as link rate during init - VCPI fixes for StarTech hub ttm: - provide tt_shrink file via debugfs - warn about freeing pinned BOs - fix swapping error handling - move page alignment into BO - cleanup ttm_agp_backend - add ttm_sys_manager - don't override vm_ops - ttm_bo_mmap removed - make ttm_resource base of all managers - remove VM_MIXEDMAP usage panel: - sysfs_emit support - simple: runtime PM support - simple: power up panel when reading EDID + caching bridge: - MHDP8546: HDCP support + DT bindings - MHDP8546: Register DP AUX channel with userspace - TI SN65DSI83 + SN65DSI84: add driver - Sil8620: Fix module dependencies - dw-hdmi: make CEC driver loading optional - Ti-sn65dsi86: refclk fixes, subdrivers, runtime pm - It66121: Add driver + DT bindings - Adv7511: Support I2S IEC958 encoding - Anx7625: fix power-on delay - Nwi-dsi: Modesetting fixes; Cleanups - lt6911: add missing MODULE_DEVICE_TABLE - cdns: fix PM reference leak hyperv: - add new DRM driver for HyperV graphics efifb: - non-PCI device handling fixes i915: - refactor IP/device versioning - XeLPD Display IP preperation work - ADL-P enablement patches - DG1 uAPI behind BROKEN - disable mmap ioctl for discerte GPUs - start enabling HuC loading for Gen12+ - major GuC backend rework for new platforms - initial TTM support for Discrete GPUs - locking rework for TTM prep - use correct max source link rate for eDP - %p4cc format printing - GLK display fixes - VLV DSI panel power fixes - PSR2 disabled for RKL and ADL-S - ACPI _DSM invalid access fixed - DMC FW path abstraction - ADL-S PCI ID update - uAPI headers converted to kerneldoc - initial LMEM support for DG1 - x86/gpu: add Jasperlake to gen11 early quirks amdgpu: - Aldebaran updates + initial SR-IOV - new GPU: Beige Goby and Yellow Carp support - more LTTPR display work - Vangogh updates - SDMA 5.x GCR fixes - PCIe ASPM support - Renoir TMZ enablement - initial multiple eDP panel support - use fdinfo to track devices/process info - pin/unpin TTM fixes - free resource on fence usage query - fix fence calculation - fix hotunplug/suspend issues - GC/MM register access macro cleanup for SR-IOV - W=1 fixes - ACPI ATCS/ATIF handling rework - 16bpc fixed point format support - Initial smartshift support - RV/PCO power tuning fixes - new INFO query for additional vbios info amdkfd: - SR-IOV aldebaran support - HMM SVM support radeon: - SMU regression fixes - Oland flickering fix vmwgfx: - enable console with fbdev emulation - fix cpu updates of coherent multisample surfaces - remove reservation semaphore - add initial SVGA3 support - support arm64 msm: - devcoredump support for display errors - dpu/dsi: yaml bindings conversion - mdp5: alpha/blend_mode/zpos support - a6xx: cached coherent buffer support - gpu iova fault improvement - a660 support rockchip: - RK3036 win1 scaling support - RK3066/3188 missing register support - RK3036/3066/3126/3188 alpha support mediatek: - MT8167 HDMI support - MT8183 DPI dual edge support tegra: - fixed YUV support/scaling on Tegra186+ ast: - use pcim_iomap - fix DP501 EDID bochs: - screen blanking support etnaviv: - export more GPU ID values to userspace - add HWDB entry for GPU on i.MX8MP - rework linear window calcs exynos: - pm runtime changes imx: - Annotate dma_fence critical section - fix PRG modifiers after drmm conversion - Add 8 pixel alignment fix for 1366x768 - fix YUV advertising - add color properties ingenic: - IPU planes fix panfrost: - Mediatek MT8183 support + DT bindings - export AFBC_FEATURES register to userspace simpledrm: - %pr for printing resources nouveau: - pin/unpin TTM fixes qxl: - unpin shadow BO virtio: - create dumb BOs as guest blob vkms: - drmm_universal_plane_alloc - add XRGB plane composition - overlay support" * tag 'drm-next-2021-07-01' of git://anongit.freedesktop.org/drm/drm: (1570 commits) drm/i915: Reinstate the mmap ioctl for some platforms drm/i915/dsc: abstract helpers to get bigjoiner primary/secondary crtc Revert "drm/msm/mdp5: provide dynamic bandwidth management" drm/msm/mdp5: provide dynamic bandwidth management drm/msm/mdp5: add perf blocks for holding fudge factors drm/msm/mdp5: switch to standard zpos property drm/msm/mdp5: add support for alpha/blend_mode properties drm/msm/mdp5: use drm_plane_state for pixel blend mode drm/msm/mdp5: use drm_plane_state for storing alpha value drm/msm/mdp5: use drm atomic helpers to handle base drm plane state drm/msm/dsi: do not enable PHYs when called for the slave DSI interface drm/msm: Add debugfs to trigger shrinker drm/msm/dpu: Avoid ABBA deadlock between IRQ modules drm/msm: devcoredump iommu fault support iommu/arm-smmu-qcom: Add stall support drm/msm: Improve the a6xx page fault handler iommu/arm-smmu-qcom: Add an adreno-smmu-priv callback to get pagefault info iommu/arm-smmu: Add support for driver IOMMU fault handlers drm/msm: export hangcheck_period in debugfs drm/msm/a6xx: add support for Adreno 660 GPU ...
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c171
1 files changed, 80 insertions, 91 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
index 3b23de996db2..47d4f04cbd69 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c
@@ -34,6 +34,8 @@
#include "vcn/vcn_3_0_0_sh_mask.h"
#include "ivsrcid/vcn/irqsrcs_vcn_2_0.h"
+#include <drm/drm_drv.h>
+
#define mmUVD_CONTEXT_ID_INTERNAL_OFFSET 0x27
#define mmUVD_GPCOM_VCPU_CMD_INTERNAL_OFFSET 0x0f
#define mmUVD_GPCOM_VCPU_DATA0_INTERNAL_OFFSET 0x10
@@ -85,16 +87,18 @@ static void vcn_v3_0_enc_ring_set_wptr(struct amdgpu_ring *ring);
static int vcn_v3_0_early_init(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ int i;
if (amdgpu_sriov_vf(adev)) {
- adev->vcn.num_vcn_inst = VCN_INSTANCES_SIENNA_CICHLID;
+ for (i = 0; i < VCN_INSTANCES_SIENNA_CICHLID; i++)
+ if (amdgpu_vcn_is_disabled_vcn(adev, VCN_DECODE_RING, i))
+ adev->vcn.num_vcn_inst++;
adev->vcn.harvest_config = 0;
adev->vcn.num_enc_rings = 1;
} else {
if (adev->asic_type == CHIP_SIENNA_CICHLID) {
u32 harvest;
- int i;
adev->vcn.num_vcn_inst = VCN_INSTANCES_SIENNA_CICHLID;
for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
@@ -110,7 +114,10 @@ static int vcn_v3_0_early_init(void *handle)
} else
adev->vcn.num_vcn_inst = 1;
- adev->vcn.num_enc_rings = 2;
+ if (adev->asic_type == CHIP_BEIGE_GOBY)
+ adev->vcn.num_enc_rings = 0;
+ else
+ adev->vcn.num_enc_rings = 2;
}
vcn_v3_0_set_dec_ring_funcs(adev);
@@ -146,7 +153,8 @@ static int vcn_v3_0_sw_init(void *handle)
adev->firmware.fw_size +=
ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
- if (adev->vcn.num_vcn_inst == VCN_INSTANCES_SIENNA_CICHLID) {
+ if ((adev->vcn.num_vcn_inst == VCN_INSTANCES_SIENNA_CICHLID) ||
+ (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID)) {
adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].ucode_id = AMDGPU_UCODE_ID_VCN1;
adev->firmware.ucode[AMDGPU_UCODE_ID_VCN1].fw = adev->vcn.fw;
adev->firmware.fw_size +=
@@ -268,16 +276,20 @@ static int vcn_v3_0_sw_init(void *handle)
static int vcn_v3_0_sw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- int i, r;
+ int i, r, idx;
- for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
- volatile struct amdgpu_fw_shared *fw_shared;
+ if (drm_dev_enter(&adev->ddev, &idx)) {
+ for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
+ volatile struct amdgpu_fw_shared *fw_shared;
- if (adev->vcn.harvest_config & (1 << i))
- continue;
- fw_shared = adev->vcn.inst[i].fw_shared_cpu_addr;
- fw_shared->present_flag_0 = 0;
- fw_shared->sw_ring.is_enabled = false;
+ if (adev->vcn.harvest_config & (1 << i))
+ continue;
+ fw_shared = adev->vcn.inst[i].fw_shared_cpu_addr;
+ fw_shared->present_flag_0 = 0;
+ fw_shared->sw_ring.is_enabled = false;
+ }
+
+ drm_dev_exit(idx);
}
if (amdgpu_sriov_vf(adev))
@@ -316,19 +328,17 @@ static int vcn_v3_0_hw_init(void *handle)
continue;
ring = &adev->vcn.inst[i].ring_dec;
- if (ring->sched.ready) {
- ring->wptr = 0;
- ring->wptr_old = 0;
- vcn_v3_0_dec_ring_set_wptr(ring);
- }
+ ring->wptr = 0;
+ ring->wptr_old = 0;
+ vcn_v3_0_dec_ring_set_wptr(ring);
+ ring->sched.ready = true;
for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
ring = &adev->vcn.inst[i].ring_enc[j];
- if (ring->sched.ready) {
- ring->wptr = 0;
- ring->wptr_old = 0;
- vcn_v3_0_enc_ring_set_wptr(ring);
- }
+ ring->wptr = 0;
+ ring->wptr_old = 0;
+ vcn_v3_0_enc_ring_set_wptr(ring);
+ ring->sched.ready = true;
}
}
} else {
@@ -1254,23 +1264,25 @@ static int vcn_v3_0_start(struct amdgpu_device *adev)
fw_shared->rb.wptr = lower_32_bits(ring->wptr);
fw_shared->multi_queue.decode_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
- fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
- ring = &adev->vcn.inst[i].ring_enc[0];
- WREG32_SOC15(VCN, i, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
- WREG32_SOC15(VCN, i, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
- WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO, ring->gpu_addr);
- WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
- WREG32_SOC15(VCN, i, mmUVD_RB_SIZE, ring->ring_size / 4);
- fw_shared->multi_queue.encode_generalpurpose_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
-
- fw_shared->multi_queue.encode_lowlatency_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
- ring = &adev->vcn.inst[i].ring_enc[1];
- WREG32_SOC15(VCN, i, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
- WREG32_SOC15(VCN, i, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
- WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO2, ring->gpu_addr);
- WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
- WREG32_SOC15(VCN, i, mmUVD_RB_SIZE2, ring->ring_size / 4);
- fw_shared->multi_queue.encode_lowlatency_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
+ if (adev->asic_type != CHIP_BEIGE_GOBY) {
+ fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
+ ring = &adev->vcn.inst[i].ring_enc[0];
+ WREG32_SOC15(VCN, i, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
+ WREG32_SOC15(VCN, i, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
+ WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO, ring->gpu_addr);
+ WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+ WREG32_SOC15(VCN, i, mmUVD_RB_SIZE, ring->ring_size / 4);
+ fw_shared->multi_queue.encode_generalpurpose_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
+
+ fw_shared->multi_queue.encode_lowlatency_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
+ ring = &adev->vcn.inst[i].ring_enc[1];
+ WREG32_SOC15(VCN, i, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
+ WREG32_SOC15(VCN, i, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
+ WREG32_SOC15(VCN, i, mmUVD_RB_BASE_LO2, ring->gpu_addr);
+ WREG32_SOC15(VCN, i, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+ WREG32_SOC15(VCN, i, mmUVD_RB_SIZE2, ring->ring_size / 4);
+ fw_shared->multi_queue.encode_lowlatency_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
+ }
}
return 0;
@@ -1293,8 +1305,6 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev)
uint32_t table_size;
uint32_t size, size_dw;
- bool is_vcn_ready;
-
struct mmsch_v3_0_cmd_direct_write
direct_wt = { {0} };
struct mmsch_v3_0_cmd_direct_read_modify_write
@@ -1486,30 +1496,6 @@ static int vcn_v3_0_start_sriov(struct amdgpu_device *adev)
}
}
- /* 6, check each VCN's init_status
- * if it remains as 0, then this VCN is not assigned to current VF
- * do not start ring for this VCN
- */
- size = sizeof(struct mmsch_v3_0_init_header);
- table_loc = (uint32_t *)table->cpu_addr;
- memcpy(&header, (void *)table_loc, size);
-
- for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
- if (adev->vcn.harvest_config & (1 << i))
- continue;
-
- is_vcn_ready = (header.inst[i].init_status == 1);
- if (!is_vcn_ready)
- DRM_INFO("VCN(%d) engine is disabled by hypervisor\n", i);
-
- ring = &adev->vcn.inst[i].ring_dec;
- ring->sched.ready = is_vcn_ready;
- for (j = 0; j < adev->vcn.num_enc_rings; ++j) {
- ring = &adev->vcn.inst[i].ring_enc[j];
- ring->sched.ready = is_vcn_ready;
- }
- }
-
return 0;
}
@@ -1650,31 +1636,33 @@ static int vcn_v3_0_pause_dpg_mode(struct amdgpu_device *adev,
UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK,
~UVD_POWER_STATUS__STALL_DPG_POWER_UP_MASK);
- /* Restore */
- fw_shared = adev->vcn.inst[inst_idx].fw_shared_cpu_addr;
- fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
- ring = &adev->vcn.inst[inst_idx].ring_enc[0];
- ring->wptr = 0;
- WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_LO, ring->gpu_addr);
- WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
- WREG32_SOC15(VCN, inst_idx, mmUVD_RB_SIZE, ring->ring_size / 4);
- WREG32_SOC15(VCN, inst_idx, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
- WREG32_SOC15(VCN, inst_idx, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
- fw_shared->multi_queue.encode_generalpurpose_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
-
- fw_shared->multi_queue.encode_lowlatency_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
- ring = &adev->vcn.inst[inst_idx].ring_enc[1];
- ring->wptr = 0;
- WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_LO2, ring->gpu_addr);
- WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
- WREG32_SOC15(VCN, inst_idx, mmUVD_RB_SIZE2, ring->ring_size / 4);
- WREG32_SOC15(VCN, inst_idx, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
- WREG32_SOC15(VCN, inst_idx, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
- fw_shared->multi_queue.encode_lowlatency_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
-
- /* restore wptr/rptr with pointers saved in FW shared memory*/
- WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_RPTR, fw_shared->rb.rptr);
- WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR, fw_shared->rb.wptr);
+ if (adev->asic_type != CHIP_BEIGE_GOBY) {
+ /* Restore */
+ fw_shared = adev->vcn.inst[inst_idx].fw_shared_cpu_addr;
+ fw_shared->multi_queue.encode_generalpurpose_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
+ ring = &adev->vcn.inst[inst_idx].ring_enc[0];
+ ring->wptr = 0;
+ WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_LO, ring->gpu_addr);
+ WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_HI, upper_32_bits(ring->gpu_addr));
+ WREG32_SOC15(VCN, inst_idx, mmUVD_RB_SIZE, ring->ring_size / 4);
+ WREG32_SOC15(VCN, inst_idx, mmUVD_RB_RPTR, lower_32_bits(ring->wptr));
+ WREG32_SOC15(VCN, inst_idx, mmUVD_RB_WPTR, lower_32_bits(ring->wptr));
+ fw_shared->multi_queue.encode_generalpurpose_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
+
+ fw_shared->multi_queue.encode_lowlatency_queue_mode |= cpu_to_le32(FW_QUEUE_RING_RESET);
+ ring = &adev->vcn.inst[inst_idx].ring_enc[1];
+ ring->wptr = 0;
+ WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_LO2, ring->gpu_addr);
+ WREG32_SOC15(VCN, inst_idx, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
+ WREG32_SOC15(VCN, inst_idx, mmUVD_RB_SIZE2, ring->ring_size / 4);
+ WREG32_SOC15(VCN, inst_idx, mmUVD_RB_RPTR2, lower_32_bits(ring->wptr));
+ WREG32_SOC15(VCN, inst_idx, mmUVD_RB_WPTR2, lower_32_bits(ring->wptr));
+ fw_shared->multi_queue.encode_lowlatency_queue_mode &= cpu_to_le32(~FW_QUEUE_RING_RESET);
+
+ /* restore wptr/rptr with pointers saved in FW shared memory*/
+ WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_RPTR, fw_shared->rb.rptr);
+ WREG32_SOC15(VCN, inst_idx, mmUVD_RBC_RB_WPTR, fw_shared->rb.wptr);
+ }
/* Unstall DPG */
WREG32_P(SOC15_REG_OFFSET(VCN, inst_idx, mmUVD_POWER_STATUS),
@@ -2131,7 +2119,8 @@ static void vcn_v3_0_set_enc_ring_funcs(struct amdgpu_device *adev)
adev->vcn.inst[i].ring_enc[j].funcs = &vcn_v3_0_enc_ring_vm_funcs;
adev->vcn.inst[i].ring_enc[j].me = i;
}
- DRM_INFO("VCN(%d) encode is enabled in VM mode\n", i);
+ if (adev->vcn.num_enc_rings > 0)
+ DRM_INFO("VCN(%d) encode is enabled in VM mode\n", i);
}
}