summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-02-01 17:48:47 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-02-01 17:48:47 -0800
commit4bf772b14675411a69b3c807f73006de0fe4b649 (patch)
treeb841e3ba0e3429695589cb0ab73871fa12f42c38 /drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
parent3879ae653a3e98380fe2daf653338830b7ca0097 (diff)
parent24b8ef699e8221d2b7f813adaab13eec053e1507 (diff)
Merge tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux
Pull drm updates from Dave Airlie: "This seems to have been a comparatively quieter merge window, I assume due to holidays etc. The "biggest" change is AMD header cleanups, which merge/remove a bunch of them. The AMD gpu scheduler is now being made generic with the etnaviv driver wanting to reuse the code, hopefully other drivers can go in the same direction. Otherwise it's the usual lots of stuff in i915/amdgpu, not so much stuff elsewhere. Core: - Add .last_close and .output_poll_changed helpers to reduce driver footprints - Fix plane clipping - Improved debug printing support - Add panel orientation property - Update edid derived properties at edid setting - Reduction in fbdev driver footprint - Move amdgpu scheduler into core for other drivers to use. i915: - Selftest and IGT improvements - Fast boot prep work on IPS, pipe config - HW workarounds for Cannonlake, Geminilake - Cannonlake clock and HDMI2.0 fixes - GPU cache invalidation and context switch improvements - Display planes cleanup - New PMU interface for perf queries - New firmware support for KBL/SKL - Geminilake HW workaround for perforamce - Coffeelake stolen memory improvements - GPU reset robustness work - Cannonlake horizontal plane flipping - GVT work amdgpu/radeon: - RV and Vega header file cleanups (lots of lines gone!) - TTM operation context support - 48-bit GPUVM support for Vega/RV - ECC support for Vega - Resizeable BAR support - Multi-display sync support - Enable swapout for reserved BOs during allocation - S3 fixes on Raven - GPU reset cleanup and fixes - 2+1 level GPU page table amdkfd: - GFX7/8 SDMA user queues support - Hardware scheduling for multiple processes - dGPU prep work rcar: - Added R8A7743/5 support - System suspend/resume support sun4i: - Multi-plane support for YUV formats - A83T and LVDS support msm: - Devfreq support for GPU tegra: - Prep work for adding Tegra186 support - Tegra186 HDMI support - HDMI2.0 and zpos support by using generic helpers tilcdc: - Misc fixes omapdrm: - Support memory bandwidth limits - DSI command mode panel cleanups - DMM error handling exynos: - drop the old IPP subdriver. etnaviv: - Occlusion query fixes - Job handling fixes - Prep work for hooking in gpu scheduler armada: - Move closer to atomic modesetting - Allow disabling primary plane if overlay is full screen imx: - Format modifier support - Add tile prefetch to PRE - Runtime PM support for PRG ast: - fix LUT loading" * tag 'drm-for-v4.16' of git://people.freedesktop.org/~airlied/linux: (1471 commits) drm/ast: Load lut in crtc_commit drm: Check for lessee in DROP_MASTER ioctl drm: fix gpu scheduler link order drm/amd/display: Demote error print to debug print when ATOM impl missing dma-buf: fix reservation_object_wait_timeout_rcu once more v2 drm/amdgpu: Avoid leaking PM domain on driver unbind (v2) drm/amd/amdgpu: Add Polaris version check drm/amdgpu: Reenable manual GPU reset from sysfs drm/amdgpu: disable MMHUB power gating on raven drm/ttm: Don't unreserve swapped BOs that were previously reserved drm/ttm: Don't add swapped BOs to swap-LRU list drm/amdgpu: only check for ECC on Vega10 drm/amd/powerplay: Fix smu_table_entry.handle type drm/ttm: add VADDR_FLAG_UPDATED_COUNT to correctly update dma_page global count drm: Fix PANEL_ORIENTATION_QUIRKS breaking the Kconfig DRM menuconfig drm/radeon: fill in rb backend map on evergreen/ni. drm/amdgpu/gfx9: fix ngg enablement to clear gds reserved memory (v2) drm/ttm: only free pages rather than update global memory count together drm/amdgpu: fix CPU based VM updates drm/amdgpu: fix typo in amdgpu_vce_validate_bo ...
Diffstat (limited to 'drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c')
-rw-r--r--drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c112
1 files changed, 68 insertions, 44 deletions
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 6634545060fd..6b95f4f344b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -29,16 +29,15 @@
#include "soc15_common.h"
#include "mmsch_v1_0.h"
-#include "vega10/soc15ip.h"
-#include "vega10/UVD/uvd_7_0_offset.h"
-#include "vega10/UVD/uvd_7_0_sh_mask.h"
-#include "vega10/VCE/vce_4_0_offset.h"
-#include "vega10/VCE/vce_4_0_default.h"
-#include "vega10/VCE/vce_4_0_sh_mask.h"
-#include "vega10/NBIF/nbif_6_1_offset.h"
-#include "vega10/HDP/hdp_4_0_offset.h"
-#include "vega10/MMHUB/mmhub_1_0_offset.h"
-#include "vega10/MMHUB/mmhub_1_0_sh_mask.h"
+#include "uvd/uvd_7_0_offset.h"
+#include "uvd/uvd_7_0_sh_mask.h"
+#include "vce/vce_4_0_offset.h"
+#include "vce/vce_4_0_default.h"
+#include "vce/vce_4_0_sh_mask.h"
+#include "nbif/nbif_6_1_offset.h"
+#include "hdp/hdp_4_0_offset.h"
+#include "mmhub/mmhub_1_0_offset.h"
+#include "mmhub/mmhub_1_0_sh_mask.h"
static void uvd_v7_0_set_ring_funcs(struct amdgpu_device *adev);
static void uvd_v7_0_set_enc_ring_funcs(struct amdgpu_device *adev);
@@ -184,7 +183,7 @@ static int uvd_v7_0_enc_ring_test_ring(struct amdgpu_ring *ring)
}
if (i < adev->usec_timeout) {
- DRM_INFO("ring test on %d succeeded in %d usecs\n",
+ DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
ring->idx, i);
} else {
DRM_ERROR("amdgpu: ring %d test failed\n",
@@ -359,7 +358,7 @@ static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
} else if (r < 0) {
DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
} else {
- DRM_INFO("ib test on ring %d succeeded\n", ring->idx);
+ DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
r = 0;
}
error:
@@ -385,7 +384,7 @@ static int uvd_v7_0_early_init(void *handle)
static int uvd_v7_0_sw_init(void *handle)
{
struct amdgpu_ring *ring;
- struct amd_sched_rq *rq;
+ struct drm_sched_rq *rq;
int i, r;
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
@@ -416,9 +415,9 @@ static int uvd_v7_0_sw_init(void *handle)
}
ring = &adev->uvd.ring_enc[0];
- rq = &ring->sched.sched_rq[AMD_SCHED_PRIORITY_NORMAL];
- r = amd_sched_entity_init(&ring->sched, &adev->uvd.entity_enc,
- rq, amdgpu_sched_jobs);
+ rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+ r = drm_sched_entity_init(&ring->sched, &adev->uvd.entity_enc,
+ rq, amdgpu_sched_jobs, NULL);
if (r) {
DRM_ERROR("Failed setting up UVD ENC run queue.\n");
return r;
@@ -472,7 +471,7 @@ static int uvd_v7_0_sw_fini(void *handle)
if (r)
return r;
- amd_sched_entity_fini(&adev->uvd.ring_enc[0].sched, &adev->uvd.entity_enc);
+ drm_sched_entity_fini(&adev->uvd.ring_enc[0].sched, &adev->uvd.entity_enc);
for (i = 0; i < adev->uvd.num_enc_rings; ++i)
amdgpu_ring_fini(&adev->uvd.ring_enc[i]);
@@ -616,7 +615,7 @@ static int uvd_v7_0_resume(void *handle)
*/
static void uvd_v7_0_mc_resume(struct amdgpu_device *adev)
{
- uint32_t size = AMDGPU_GPU_PAGE_ALIGN(adev->uvd.fw->size + 4);
+ uint32_t size = AMDGPU_UVD_FIRMWARE_SIZE(adev);
uint32_t offset;
if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
@@ -1086,6 +1085,8 @@ static void uvd_v7_0_stop(struct amdgpu_device *adev)
static void uvd_v7_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
unsigned flags)
{
+ struct amdgpu_device *adev = ring->adev;
+
WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
amdgpu_ring_write(ring,
@@ -1123,6 +1124,7 @@ static void uvd_v7_0_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq
static void uvd_v7_0_enc_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
u64 seq, unsigned flags)
{
+
WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
amdgpu_ring_write(ring, HEVC_ENC_CMD_FENCE);
@@ -1141,6 +1143,8 @@ static void uvd_v7_0_enc_ring_emit_fence(struct amdgpu_ring *ring, u64 addr,
*/
static void uvd_v7_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
{
+ struct amdgpu_device *adev = ring->adev;
+
amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(NBIF, 0,
mmHDP_MEM_COHERENCY_FLUSH_CNTL), 0));
amdgpu_ring_write(ring, 0);
@@ -1155,6 +1159,8 @@ static void uvd_v7_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
*/
static void uvd_v7_0_ring_emit_hdp_invalidate(struct amdgpu_ring *ring)
{
+ struct amdgpu_device *adev = ring->adev;
+
amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(HDP, 0, mmHDP_READ_CACHE_INVALIDATE), 0));
amdgpu_ring_write(ring, 1);
}
@@ -1192,7 +1198,7 @@ static int uvd_v7_0_ring_test_ring(struct amdgpu_ring *ring)
}
if (i < adev->usec_timeout) {
- DRM_INFO("ring test on %d succeeded in %d usecs\n",
+ DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
ring->idx, i);
} else {
DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
@@ -1212,11 +1218,13 @@ static int uvd_v7_0_ring_test_ring(struct amdgpu_ring *ring)
*/
static void uvd_v7_0_ring_emit_ib(struct amdgpu_ring *ring,
struct amdgpu_ib *ib,
- unsigned vm_id, bool ctx_switch)
+ unsigned vmid, bool ctx_switch)
{
+ struct amdgpu_device *adev = ring->adev;
+
amdgpu_ring_write(ring,
PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_RBC_IB_VMID), 0));
- amdgpu_ring_write(ring, vm_id);
+ amdgpu_ring_write(ring, vmid);
amdgpu_ring_write(ring,
PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_RBC_IB_64BIT_BAR_LOW), 0));
@@ -1238,10 +1246,10 @@ static void uvd_v7_0_ring_emit_ib(struct amdgpu_ring *ring,
* Write enc ring commands to execute the indirect buffer
*/
static void uvd_v7_0_enc_ring_emit_ib(struct amdgpu_ring *ring,
- struct amdgpu_ib *ib, unsigned int vm_id, bool ctx_switch)
+ struct amdgpu_ib *ib, unsigned int vmid, bool ctx_switch)
{
amdgpu_ring_write(ring, HEVC_ENC_CMD_IB_VM);
- amdgpu_ring_write(ring, vm_id);
+ amdgpu_ring_write(ring, vmid);
amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
amdgpu_ring_write(ring, ib->length_dw);
@@ -1250,6 +1258,8 @@ static void uvd_v7_0_enc_ring_emit_ib(struct amdgpu_ring *ring,
static void uvd_v7_0_vm_reg_write(struct amdgpu_ring *ring,
uint32_t data0, uint32_t data1)
{
+ struct amdgpu_device *adev = ring->adev;
+
amdgpu_ring_write(ring,
PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0), 0));
amdgpu_ring_write(ring, data0);
@@ -1264,6 +1274,8 @@ static void uvd_v7_0_vm_reg_write(struct amdgpu_ring *ring,
static void uvd_v7_0_vm_reg_wait(struct amdgpu_ring *ring,
uint32_t data0, uint32_t data1, uint32_t mask)
{
+ struct amdgpu_device *adev = ring->adev;
+
amdgpu_ring_write(ring,
PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_GPCOM_VCPU_DATA0), 0));
amdgpu_ring_write(ring, data0);
@@ -1279,25 +1291,26 @@ static void uvd_v7_0_vm_reg_wait(struct amdgpu_ring *ring,
}
static void uvd_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
- unsigned vm_id, uint64_t pd_addr)
+ unsigned vmid, uint64_t pd_addr)
{
struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
- uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vm_id);
- uint32_t data0, data1, mask;
+ uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vmid);
+ uint64_t flags = AMDGPU_PTE_VALID;
unsigned eng = ring->vm_inv_eng;
+ uint32_t data0, data1, mask;
- pd_addr = amdgpu_gart_get_vm_pde(ring->adev, pd_addr);
- pd_addr |= AMDGPU_PTE_VALID;
+ amdgpu_gart_get_vm_pde(ring->adev, -1, &pd_addr, &flags);
+ pd_addr |= flags;
- data0 = (hub->ctx0_ptb_addr_hi32 + vm_id * 2) << 2;
+ data0 = (hub->ctx0_ptb_addr_hi32 + vmid * 2) << 2;
data1 = upper_32_bits(pd_addr);
uvd_v7_0_vm_reg_write(ring, data0, data1);
- data0 = (hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2;
+ data0 = (hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2;
data1 = lower_32_bits(pd_addr);
uvd_v7_0_vm_reg_write(ring, data0, data1);
- data0 = (hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2;
+ data0 = (hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2;
data1 = lower_32_bits(pd_addr);
mask = 0xffffffff;
uvd_v7_0_vm_reg_wait(ring, data0, data1, mask);
@@ -1309,36 +1322,47 @@ static void uvd_v7_0_ring_emit_vm_flush(struct amdgpu_ring *ring,
/* wait for flush */
data0 = (hub->vm_inv_eng0_ack + eng) << 2;
- data1 = 1 << vm_id;
- mask = 1 << vm_id;
+ data1 = 1 << vmid;
+ mask = 1 << vmid;
uvd_v7_0_vm_reg_wait(ring, data0, data1, mask);
}
+static void uvd_v7_0_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+ int i;
+ struct amdgpu_device *adev = ring->adev;
+
+ for (i = 0; i < count; i++)
+ amdgpu_ring_write(ring, PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP), 0));
+
+}
+
static void uvd_v7_0_enc_ring_insert_end(struct amdgpu_ring *ring)
{
amdgpu_ring_write(ring, HEVC_ENC_CMD_END);
}
static void uvd_v7_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
- unsigned int vm_id, uint64_t pd_addr)
+ unsigned int vmid, uint64_t pd_addr)
{
struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
- uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vm_id);
+ uint32_t req = ring->adev->gart.gart_funcs->get_invalidate_req(vmid);
+ uint64_t flags = AMDGPU_PTE_VALID;
unsigned eng = ring->vm_inv_eng;
- pd_addr = amdgpu_gart_get_vm_pde(ring->adev, pd_addr);
- pd_addr |= AMDGPU_PTE_VALID;
+ amdgpu_gart_get_vm_pde(ring->adev, -1, &pd_addr, &flags);
+ pd_addr |= flags;
amdgpu_ring_write(ring, HEVC_ENC_CMD_REG_WRITE);
- amdgpu_ring_write(ring, (hub->ctx0_ptb_addr_hi32 + vm_id * 2) << 2);
+ amdgpu_ring_write(ring, (hub->ctx0_ptb_addr_hi32 + vmid * 2) << 2);
amdgpu_ring_write(ring, upper_32_bits(pd_addr));
amdgpu_ring_write(ring, HEVC_ENC_CMD_REG_WRITE);
- amdgpu_ring_write(ring, (hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2);
+ amdgpu_ring_write(ring, (hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2);
amdgpu_ring_write(ring, lower_32_bits(pd_addr));
amdgpu_ring_write(ring, HEVC_ENC_CMD_REG_WAIT);
- amdgpu_ring_write(ring, (hub->ctx0_ptb_addr_lo32 + vm_id * 2) << 2);
+ amdgpu_ring_write(ring, (hub->ctx0_ptb_addr_lo32 + vmid * 2) << 2);
amdgpu_ring_write(ring, 0xffffffff);
amdgpu_ring_write(ring, lower_32_bits(pd_addr));
@@ -1350,8 +1374,8 @@ static void uvd_v7_0_enc_ring_emit_vm_flush(struct amdgpu_ring *ring,
/* wait for flush */
amdgpu_ring_write(ring, HEVC_ENC_CMD_REG_WAIT);
amdgpu_ring_write(ring, (hub->vm_inv_eng0_ack + eng) << 2);
- amdgpu_ring_write(ring, 1 << vm_id);
- amdgpu_ring_write(ring, 1 << vm_id);
+ amdgpu_ring_write(ring, 1 << vmid);
+ amdgpu_ring_write(ring, 1 << vmid);
}
#if 0
@@ -1681,7 +1705,7 @@ const struct amd_ip_funcs uvd_v7_0_ip_funcs = {
static const struct amdgpu_ring_funcs uvd_v7_0_ring_vm_funcs = {
.type = AMDGPU_RING_TYPE_UVD,
.align_mask = 0xf,
- .nop = PACKET0(SOC15_REG_OFFSET(UVD, 0, mmUVD_NO_OP), 0),
+ .nop = PACKET0(0x81ff, 0),
.support_64bit_ptrs = false,
.vmhub = AMDGPU_MMHUB,
.get_rptr = uvd_v7_0_ring_get_rptr,
@@ -1700,7 +1724,7 @@ static const struct amdgpu_ring_funcs uvd_v7_0_ring_vm_funcs = {
.emit_hdp_invalidate = uvd_v7_0_ring_emit_hdp_invalidate,
.test_ring = uvd_v7_0_ring_test_ring,
.test_ib = amdgpu_uvd_ring_test_ib,
- .insert_nop = amdgpu_ring_insert_nop,
+ .insert_nop = uvd_v7_0_ring_insert_nop,
.pad_ib = amdgpu_ring_generic_pad_ib,
.begin_use = amdgpu_uvd_ring_begin_use,
.end_use = amdgpu_uvd_ring_end_use,