diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-03 11:44:24 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-03 11:44:24 -0700 |
commit | 2f34c1231bfc9f2550f934acb268ac7315fb3837 (patch) | |
tree | ff8114b3b4ec4723a11b041c6b74c389e9f0eeb9 /drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | |
parent | a3719f34fdb664ffcfaec2160ef20fca7becf2ee (diff) | |
parent | 8b03d1ed2c43a2ba5ef3381322ee4515b97381bf (diff) | |
download | linux-2f34c1231bfc9f2550f934acb268ac7315fb3837.tar.gz linux-2f34c1231bfc9f2550f934acb268ac7315fb3837.tar.bz2 linux-2f34c1231bfc9f2550f934acb268ac7315fb3837.zip |
Merge tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux
Pull drm u pdates from Dave Airlie:
"This is the main drm pull request for v4.12. Apart from two fixes
pulls, everything should have been in drm-next for at least 2 weeks.
The biggest thing in here is AMD released the public headers for their
upcoming VEGA GPUs. These as always are quite a sizeable chunk of
header files. They've also added initial non-display support for those
GPUs, though they aren't available in production yet.
Otherwise it's pretty much normal.
New bridge drivers:
- megachips-stdpxxxx-ge-b850v3-fw LVDS->DP++
- generic LVDS bridge support.
Core:
- Displayport link train failure reporting to userspace
- debugfs interface cleaned up
- subsystem TODO in kerneldoc now
- Extended fbdev support (flipping and vblank wait)
- drm_platform removed
- EDP CRC support in helper
- HF-VSDB SCDC support in EDID parser
- Lots of code cleanups and header extraction
- Thunderbolt external GPU awareness
- Atomic helper improvements
- Documentation improvements
panel:
- Sitronix and Samsung new panel support
amdgpu:
- Preliminary vega10 support
- Multi-level page table support
- GPU sensor support for userspace
- PRT support for sparse buffers
- SR-IOV improvements
- Non-contig VRAM CPU mapping
i915:
- Atomic modesetting enabled by default on Gen5+
- LSPCON improvements
- Atomic state handling for cdclk
- GPU reset improvements
- In-kernel unit tests
- Geminilake improvements and color manager support
- Designware i2c fixes
- vblank evasion improvements
- Hotplug safe connector iterators
- GVT scheduler QoS support
- GVT Kabylake support
nouveau:
- Acceleration support for Pascal (GP10x).
- Rearchitecture of code handling proprietary signed firmware
- Fix GTX 970 with odd MMU configuration
- GP10B support
- GP107 acceleration support
vmwgfx:
- Atomic modesetting support for vmwgfx
omapdrm:
- Support for render nodes
- Refactor omapdss code
- Fix some probe ordering issues
- Fix too dark RGB565 rendering
sunxi:
- prelim rework for multiple pipes.
mali-dp:
- Color management support
- Plane scaling
- Power management improvements
imx-drm:
- Prefetch Resolve Engine/Gasket on i.MX6QP
- Deferred plane disabling
- Separate alpha support
mediatek:
- Mediatek SoC MT2701 support
rcar-du:
- Gen3 HDMI support
msm:
- 4k support for newer chips
- OPP bindings for gpu
- prep work for per-process pagetables
vc4:
- HDMI audio support
- fixes
qxl:
- minor fixes.
dw-hdmi:
- PHY improvements
- CSC fixes
- Amlogic GX SoC support"
* tag 'drm-for-v4.12' of git://people.freedesktop.org/~airlied/linux: (1778 commits)
drm/nouveau/fb/gf100-: Fix 32 bit wraparound in new ram detection
drm/nouveau/secboot/gm20b: fix the error return code in gm20b_secboot_tegra_read_wpr()
drm/nouveau/kms: Increase max retries in scanout position queries.
drm/nouveau/bios/bitP: check that table is long enough for optional pointers
drm/nouveau/fifo/nv40: no ctxsw for pre-nv44 mpeg engine
drm: mali-dp: use div_u64 for expensive 64-bit divisions
drm/i915: Confirm the request is still active before adding it to the await
drm/i915: Avoid busy-spinning on VLV_GLTC_PW_STATUS mmio
drm/i915/selftests: Allocate inode/file dynamically
drm/i915: Fix system hang with EI UP masked on Haswell
drm/i915: checking for NULL instead of IS_ERR() in mock selftests
drm/i915: Perform link quality check unconditionally during long pulse
drm/i915: Fix use after free in lpe_audio_platdev_destroy()
drm/i915: Use the right mapping_gfp_mask for final shmem allocation
drm/i915: Make legacy cursor updates more unsynced
drm/i915: Apply a cond_resched() to the saturated signaler
drm/i915: Park the signaler before sleeping
drm: mali-dp: Check the mclk rate and allow up/down scaling
drm: mali-dp: Enable image enhancement when scaling
drm: mali-dp: Add plane upscaling support
...
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c')
-rw-r--r-- | drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 49 |
1 files changed, 29 insertions, 20 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c index 011800f621c6..a69e5d4e1d2a 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c @@ -310,7 +310,7 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev) if (adev->sdma.instance[i].feature_version >= 20) adev->sdma.instance[i].burst_nop = true; - if (adev->firmware.smu_load) { + if (adev->firmware.load_type == AMDGPU_FW_LOAD_SMU) { info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i]; info->ucode_id = AMDGPU_UCODE_ID_SDMA0 + i; info->fw = adev->sdma.instance[i].fw; @@ -321,9 +321,7 @@ static int sdma_v3_0_init_microcode(struct amdgpu_device *adev) } out: if (err) { - printk(KERN_ERR - "sdma_v3_0: Failed to load firmware \"%s\"\n", - fw_name); + pr_err("sdma_v3_0: Failed to load firmware \"%s\"\n", fw_name); for (i = 0; i < adev->sdma.num_instances; i++) { release_firmware(adev->sdma.instance[i].fw); adev->sdma.instance[i].fw = NULL; @@ -339,7 +337,7 @@ out: * * Get the current rptr from the hardware (VI+). */ -static uint32_t sdma_v3_0_ring_get_rptr(struct amdgpu_ring *ring) +static uint64_t sdma_v3_0_ring_get_rptr(struct amdgpu_ring *ring) { /* XXX check if swapping is necessary on BE */ return ring->adev->wb.wb[ring->rptr_offs] >> 2; @@ -352,7 +350,7 @@ static uint32_t sdma_v3_0_ring_get_rptr(struct amdgpu_ring *ring) * * Get the current wptr from the hardware (VI+). */ -static uint32_t sdma_v3_0_ring_get_wptr(struct amdgpu_ring *ring) +static uint64_t sdma_v3_0_ring_get_wptr(struct amdgpu_ring *ring) { struct amdgpu_device *adev = ring->adev; u32 wptr; @@ -382,12 +380,12 @@ static void sdma_v3_0_ring_set_wptr(struct amdgpu_ring *ring) if (ring->use_doorbell) { /* XXX check if swapping is necessary on BE */ - adev->wb.wb[ring->wptr_offs] = ring->wptr << 2; - WDOORBELL32(ring->doorbell_index, ring->wptr << 2); + adev->wb.wb[ring->wptr_offs] = lower_32_bits(ring->wptr) << 2; + WDOORBELL32(ring->doorbell_index, lower_32_bits(ring->wptr) << 2); } else { int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1; - WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], ring->wptr << 2); + WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], lower_32_bits(ring->wptr) << 2); } } @@ -419,7 +417,7 @@ static void sdma_v3_0_ring_emit_ib(struct amdgpu_ring *ring, u32 vmid = vm_id & 0xf; /* IB packet must end on a 8 DW boundary */ - sdma_v3_0_ring_insert_nop(ring, (10 - (ring->wptr & 7)) % 8); + sdma_v3_0_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8); amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) | SDMA_PKT_INDIRECT_HEADER_VMID(vmid)); @@ -615,6 +613,7 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev) for (i = 0; i < adev->sdma.num_instances; i++) { ring = &adev->sdma.instance[i].ring; + amdgpu_ring_clear_ring(ring); wb_offset = (ring->rptr_offs * 4); mutex_lock(&adev->srbm_mutex); @@ -661,7 +660,7 @@ static int sdma_v3_0_gfx_resume(struct amdgpu_device *adev) WREG32(mmSDMA0_GFX_RB_BASE_HI + sdma_offsets[i], ring->gpu_addr >> 40); ring->wptr = 0; - WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], ring->wptr << 2); + WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[i], lower_32_bits(ring->wptr) << 2); doorbell = RREG32(mmSDMA0_GFX_DOORBELL + sdma_offsets[i]); @@ -772,7 +771,7 @@ static int sdma_v3_0_start(struct amdgpu_device *adev) int r, i; if (!adev->pp_enabled) { - if (!adev->firmware.smu_load) { + if (adev->firmware.load_type != AMDGPU_FW_LOAD_SMU) { r = sdma_v3_0_load_microcode(adev); if (r) return r; @@ -1008,14 +1007,14 @@ static void sdma_v3_0_vm_write_pte(struct amdgpu_ib *ib, uint64_t pe, */ static void sdma_v3_0_vm_set_pte_pde(struct amdgpu_ib *ib, uint64_t pe, uint64_t addr, unsigned count, - uint32_t incr, uint32_t flags) + uint32_t incr, uint64_t flags) { /* for physically contiguous pages (vram) */ ib->ptr[ib->length_dw++] = SDMA_PKT_HEADER_OP(SDMA_OP_GEN_PTEPDE); ib->ptr[ib->length_dw++] = lower_32_bits(pe); /* dst addr */ ib->ptr[ib->length_dw++] = upper_32_bits(pe); - ib->ptr[ib->length_dw++] = flags; /* mask */ - ib->ptr[ib->length_dw++] = 0; + ib->ptr[ib->length_dw++] = lower_32_bits(flags); /* mask */ + ib->ptr[ib->length_dw++] = upper_32_bits(flags); ib->ptr[ib->length_dw++] = lower_32_bits(addr); /* value */ ib->ptr[ib->length_dw++] = upper_32_bits(addr); ib->ptr[ib->length_dw++] = incr; /* increment size */ @@ -1138,17 +1137,20 @@ static int sdma_v3_0_sw_init(void *handle) struct amdgpu_device *adev = (struct amdgpu_device *)handle; /* SDMA trap event */ - r = amdgpu_irq_add_id(adev, 224, &adev->sdma.trap_irq); + r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 224, + &adev->sdma.trap_irq); if (r) return r; /* SDMA Privileged inst */ - r = amdgpu_irq_add_id(adev, 241, &adev->sdma.illegal_inst_irq); + r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 241, + &adev->sdma.illegal_inst_irq); if (r) return r; /* SDMA Privileged inst */ - r = amdgpu_irq_add_id(adev, 247, &adev->sdma.illegal_inst_irq); + r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 247, + &adev->sdma.illegal_inst_irq); if (r) return r; @@ -1512,14 +1514,17 @@ static int sdma_v3_0_set_clockgating_state(void *handle, { struct amdgpu_device *adev = (struct amdgpu_device *)handle; + if (amdgpu_sriov_vf(adev)) + return 0; + switch (adev->asic_type) { case CHIP_FIJI: case CHIP_CARRIZO: case CHIP_STONEY: sdma_v3_0_update_sdma_medium_grain_clock_gating(adev, - state == AMD_CG_STATE_GATE ? true : false); + state == AMD_CG_STATE_GATE); sdma_v3_0_update_sdma_medium_grain_light_sleep(adev, - state == AMD_CG_STATE_GATE ? true : false); + state == AMD_CG_STATE_GATE); break; default: break; @@ -1538,6 +1543,9 @@ static void sdma_v3_0_get_clockgating_state(void *handle, u32 *flags) struct amdgpu_device *adev = (struct amdgpu_device *)handle; int data; + if (amdgpu_sriov_vf(adev)) + *flags = 0; + /* AMD_CG_SUPPORT_SDMA_MGCG */ data = RREG32(mmSDMA0_CLK_CTRL + sdma_offsets[0]); if (!(data & SDMA0_CLK_CTRL__SOFT_OVERRIDE0_MASK)) @@ -1574,6 +1582,7 @@ static const struct amdgpu_ring_funcs sdma_v3_0_ring_funcs = { .type = AMDGPU_RING_TYPE_SDMA, .align_mask = 0xf, .nop = SDMA_PKT_NOP_HEADER_OP(SDMA_OP_NOP), + .support_64bit_ptrs = false, .get_rptr = sdma_v3_0_ring_get_rptr, .get_wptr = sdma_v3_0_ring_get_wptr, .set_wptr = sdma_v3_0_ring_set_wptr, |