From d2ccde1c8e90d38cee87a1b0309ad2827f3fd30d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 11 Dec 2023 02:45:28 +0000
Subject: [PATCH] add boot partition size
---
kernel/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c | 204 +++++++++++++++++++++++++-------------------------
1 files changed, 103 insertions(+), 101 deletions(-)
diff --git a/kernel/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/kernel/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index ce16b83..b44c867 100644
--- a/kernel/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/kernel/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -22,7 +22,7 @@
*/
#include <linux/firmware.h>
-#include <drm/drmP.h>
+
#include "amdgpu.h"
#include "amdgpu_uvd.h"
#include "soc15.h"
@@ -183,11 +183,8 @@
return 0;
r = amdgpu_ring_alloc(ring, 16);
- if (r) {
- DRM_ERROR("amdgpu: uvd enc failed to lock (%d)ring %d (%d).\n",
- ring->me, ring->idx, r);
+ if (r)
return r;
- }
rptr = amdgpu_ring_get_rptr(ring);
@@ -197,17 +194,11 @@
for (i = 0; i < adev->usec_timeout; i++) {
if (amdgpu_ring_get_rptr(ring) != rptr)
break;
- DRM_UDELAY(1);
+ udelay(1);
}
- if (i < adev->usec_timeout) {
- DRM_DEBUG("(%d)ring test on %d succeeded in %d usecs\n",
- ring->me, ring->idx, i);
- } else {
- DRM_ERROR("amdgpu: (%d)ring %d test failed\n",
- ring->me, ring->idx);
+ if (i >= adev->usec_timeout)
r = -ETIMEDOUT;
- }
return r;
}
@@ -223,29 +214,31 @@
* Open up a stream for HW test
*/
static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
+ struct amdgpu_bo *bo,
struct dma_fence **fence)
{
const unsigned ib_size_dw = 16;
struct amdgpu_job *job;
struct amdgpu_ib *ib;
struct dma_fence *f = NULL;
- uint64_t dummy;
+ uint64_t addr;
int i, r;
- r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
+ r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4,
+ AMDGPU_IB_POOL_DIRECT, &job);
if (r)
return r;
ib = &job->ibs[0];
- dummy = ib->gpu_addr + 1024;
+ addr = amdgpu_bo_gpu_offset(bo);
ib->length_dw = 0;
ib->ptr[ib->length_dw++] = 0x00000018;
ib->ptr[ib->length_dw++] = 0x00000001; /* session info */
ib->ptr[ib->length_dw++] = handle;
ib->ptr[ib->length_dw++] = 0x00000000;
- ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
- ib->ptr[ib->length_dw++] = dummy;
+ ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+ ib->ptr[ib->length_dw++] = addr;
ib->ptr[ib->length_dw++] = 0x00000014;
ib->ptr[ib->length_dw++] = 0x00000002; /* task info */
@@ -283,30 +276,32 @@
*
* Close up a stream for HW test or if userspace failed to do so
*/
-int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
- bool direct, struct dma_fence **fence)
+static int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
+ struct amdgpu_bo *bo,
+ struct dma_fence **fence)
{
const unsigned ib_size_dw = 16;
struct amdgpu_job *job;
struct amdgpu_ib *ib;
struct dma_fence *f = NULL;
- uint64_t dummy;
+ uint64_t addr;
int i, r;
- r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
+ r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4,
+ AMDGPU_IB_POOL_DIRECT, &job);
if (r)
return r;
ib = &job->ibs[0];
- dummy = ib->gpu_addr + 1024;
+ addr = amdgpu_bo_gpu_offset(bo);
ib->length_dw = 0;
ib->ptr[ib->length_dw++] = 0x00000018;
ib->ptr[ib->length_dw++] = 0x00000001;
ib->ptr[ib->length_dw++] = handle;
ib->ptr[ib->length_dw++] = 0x00000000;
- ib->ptr[ib->length_dw++] = upper_32_bits(dummy);
- ib->ptr[ib->length_dw++] = dummy;
+ ib->ptr[ib->length_dw++] = upper_32_bits(addr);
+ ib->ptr[ib->length_dw++] = addr;
ib->ptr[ib->length_dw++] = 0x00000014;
ib->ptr[ib->length_dw++] = 0x00000002;
@@ -320,11 +315,7 @@
for (i = ib->length_dw; i < ib_size_dw; ++i)
ib->ptr[i] = 0x0;
- if (direct)
- r = amdgpu_job_submit_direct(job, ring, &f);
- else
- r = amdgpu_job_submit(job, &ring->adev->vce.entity,
- AMDGPU_FENCE_OWNER_UNDEFINED, &f);
+ r = amdgpu_job_submit_direct(job, ring, &f);
if (r)
goto err;
@@ -347,32 +338,33 @@
static int uvd_v7_0_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout)
{
struct dma_fence *fence = NULL;
+ struct amdgpu_bo *bo = NULL;
long r;
- r = uvd_v7_0_enc_get_create_msg(ring, 1, NULL);
- if (r) {
- DRM_ERROR("amdgpu: (%d)failed to get create msg (%ld).\n", ring->me, r);
- goto error;
- }
+ r = amdgpu_bo_create_reserved(ring->adev, 128 * 1024, PAGE_SIZE,
+ AMDGPU_GEM_DOMAIN_VRAM,
+ &bo, NULL, NULL);
+ if (r)
+ return r;
- r = uvd_v7_0_enc_get_destroy_msg(ring, 1, true, &fence);
- if (r) {
- DRM_ERROR("amdgpu: (%d)failed to get destroy ib (%ld).\n", ring->me, r);
+ r = uvd_v7_0_enc_get_create_msg(ring, 1, bo, NULL);
+ if (r)
goto error;
- }
+
+ r = uvd_v7_0_enc_get_destroy_msg(ring, 1, bo, &fence);
+ if (r)
+ goto error;
r = dma_fence_wait_timeout(fence, false, timeout);
- if (r == 0) {
- DRM_ERROR("amdgpu: (%d)IB test timed out.\n", ring->me);
+ if (r == 0)
r = -ETIMEDOUT;
- } else if (r < 0) {
- DRM_ERROR("amdgpu: (%d)fence wait failed (%ld).\n", ring->me, r);
- } else {
- DRM_DEBUG("ib test on (%d)ring %d succeeded\n", ring->me, ring->idx);
+ else if (r > 0)
r = 0;
- }
+
error:
dma_fence_put(fence);
+ amdgpu_bo_unreserve(bo);
+ amdgpu_bo_unref(&bo);
return r;
}
@@ -444,6 +436,13 @@
adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].fw = adev->uvd.fw;
adev->firmware.fw_size +=
ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
+
+ if (adev->uvd.num_uvd_inst == UVD7_MAX_HW_INSTANCES_VEGA20) {
+ adev->firmware.ucode[AMDGPU_UCODE_ID_UVD1].ucode_id = AMDGPU_UCODE_ID_UVD1;
+ adev->firmware.ucode[AMDGPU_UCODE_ID_UVD1].fw = adev->uvd.fw;
+ adev->firmware.fw_size +=
+ ALIGN(le32_to_cpu(hdr->ucode_size_bytes), PAGE_SIZE);
+ }
DRM_INFO("PSP loading UVD firmware\n");
}
@@ -452,15 +451,17 @@
continue;
if (!amdgpu_sriov_vf(adev)) {
ring = &adev->uvd.inst[j].ring;
- sprintf(ring->name, "uvd<%d>", j);
- r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst[j].irq, 0);
+ sprintf(ring->name, "uvd_%d", ring->me);
+ r = amdgpu_ring_init(adev, ring, 512,
+ &adev->uvd.inst[j].irq, 0,
+ AMDGPU_RING_PRIO_DEFAULT);
if (r)
return r;
}
for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
ring = &adev->uvd.inst[j].ring_enc[i];
- sprintf(ring->name, "uvd_enc%d<%d>", i, j);
+ sprintf(ring->name, "uvd_enc_%d.%d", ring->me, i);
if (amdgpu_sriov_vf(adev)) {
ring->use_doorbell = true;
@@ -468,11 +469,13 @@
* sriov, so set unused location for other unused rings.
*/
if (i == 0)
- ring->doorbell_index = AMDGPU_DOORBELL64_UVD_RING0_1 * 2;
+ ring->doorbell_index = adev->doorbell_index.uvd_vce.uvd_ring0_1 * 2;
else
- ring->doorbell_index = AMDGPU_DOORBELL64_UVD_RING2_3 * 2 + 1;
+ ring->doorbell_index = adev->doorbell_index.uvd_vce.uvd_ring2_3 * 2 + 1;
}
- r = amdgpu_ring_init(adev, ring, 512, &adev->uvd.inst[j].irq, 0);
+ r = amdgpu_ring_init(adev, ring, 512,
+ &adev->uvd.inst[j].irq, 0,
+ AMDGPU_RING_PRIO_DEFAULT);
if (r)
return r;
}
@@ -540,12 +543,9 @@
ring = &adev->uvd.inst[j].ring;
if (!amdgpu_sriov_vf(adev)) {
- ring->ready = true;
- r = amdgpu_ring_test_ring(ring);
- if (r) {
- ring->ready = false;
+ r = amdgpu_ring_test_helper(ring);
+ if (r)
goto done;
- }
r = amdgpu_ring_alloc(ring, 10);
if (r) {
@@ -582,12 +582,9 @@
for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
ring = &adev->uvd.inst[j].ring_enc[i];
- ring->ready = true;
- r = amdgpu_ring_test_ring(ring);
- if (r) {
- ring->ready = false;
+ r = amdgpu_ring_test_helper(ring);
+ if (r)
goto done;
- }
}
}
done:
@@ -607,19 +604,12 @@
static int uvd_v7_0_hw_fini(void *handle)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- int i;
if (!amdgpu_sriov_vf(adev))
uvd_v7_0_stop(adev);
else {
/* full access mode, so don't touch any UVD register */
DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
- }
-
- for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
- if (adev->uvd.harvest_config & (1 << i))
- continue;
- adev->uvd.inst[i].ring.ready = false;
}
return 0;
@@ -667,9 +657,14 @@
continue;
if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
- lower_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
+ i == 0 ?
+ adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].tmr_mc_addr_lo:
+ adev->firmware.ucode[AMDGPU_UCODE_ID_UVD1].tmr_mc_addr_lo);
WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
- upper_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
+ i == 0 ?
+ adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].tmr_mc_addr_hi:
+ adev->firmware.ucode[AMDGPU_UCODE_ID_UVD1].tmr_mc_addr_hi);
+ WREG32_SOC15(UVD, i, mmUVD_VCPU_CACHE_OFFSET0, 0);
offset = 0;
} else {
WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
@@ -677,10 +672,10 @@
WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH,
upper_32_bits(adev->uvd.inst[i].gpu_addr));
offset = size;
+ WREG32_SOC15(UVD, i, mmUVD_VCPU_CACHE_OFFSET0,
+ AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
}
- WREG32_SOC15(UVD, i, mmUVD_VCPU_CACHE_OFFSET0,
- AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
WREG32_SOC15(UVD, i, mmUVD_VCPU_CACHE_SIZE0, size);
WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW,
@@ -805,10 +800,13 @@
0xFFFFFFFF, 0x00000004);
/* mc resume*/
if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
- MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
- lower_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
- MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
- upper_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
+ MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i,
+ mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
+ adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].tmr_mc_addr_lo);
+ MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i,
+ mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
+ adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].tmr_mc_addr_hi);
+ MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0), 0);
offset = 0;
} else {
MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW),
@@ -816,10 +814,11 @@
MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH),
upper_32_bits(adev->uvd.inst[i].gpu_addr));
offset = size;
+ MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, 0, mmUVD_VCPU_CACHE_OFFSET0),
+ AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
+
}
- MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_OFFSET0),
- AMDGPU_UVD_FIRMWARE_OFFSET >> 3);
MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_VCPU_CACHE_SIZE0), size);
MMSCH_V1_0_INSERT_DIRECT_WT(SOC15_REG_OFFSET(UVD, i, mmUVD_LMI_VCPU_CACHE1_64BIT_BAR_LOW),
@@ -1074,7 +1073,7 @@
WREG32_SOC15(UVD, k, mmUVD_RBC_RB_RPTR_ADDR,
(upper_32_bits(ring->gpu_addr) >> 2));
- /* programm the RB_BASE for ring buffer */
+ /* program the RB_BASE for ring buffer */
WREG32_SOC15(UVD, k, mmUVD_LMI_RBC_RB_64BIT_BAR_LOW,
lower_32_bits(ring->gpu_addr));
WREG32_SOC15(UVD, k, mmUVD_LMI_RBC_RB_64BIT_BAR_HIGH,
@@ -1230,11 +1229,9 @@
WREG32_SOC15(UVD, ring->me, mmUVD_CONTEXT_ID, 0xCAFEDEAD);
r = amdgpu_ring_alloc(ring, 3);
- if (r) {
- DRM_ERROR("amdgpu: (%d)cp failed to lock ring %d (%d).\n",
- ring->me, ring->idx, r);
+ if (r)
return r;
- }
+
amdgpu_ring_write(ring,
PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_CONTEXT_ID), 0));
amdgpu_ring_write(ring, 0xDEADBEEF);
@@ -1243,17 +1240,12 @@
tmp = RREG32_SOC15(UVD, ring->me, mmUVD_CONTEXT_ID);
if (tmp == 0xDEADBEEF)
break;
- DRM_UDELAY(1);
+ udelay(1);
}
- if (i < adev->usec_timeout) {
- DRM_DEBUG("(%d)ring test on %d succeeded in %d usecs\n",
- ring->me, ring->idx, i);
- } else {
- DRM_ERROR("(%d)amdgpu: ring %d test failed (0x%08X)\n",
- ring->me, ring->idx, tmp);
- r = -EINVAL;
- }
+ if (i >= adev->usec_timeout)
+ r = -ETIMEDOUT;
+
return r;
}
@@ -1267,11 +1259,12 @@
static int uvd_v7_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
uint32_t ib_idx)
{
+ struct amdgpu_ring *ring = to_amdgpu_ring(p->entity->rq->sched);
struct amdgpu_ib *ib = &p->job->ibs[ib_idx];
unsigned i;
/* No patching necessary for the first instance */
- if (!p->ring->me)
+ if (!ring->me)
return 0;
for (i = 0; i < ib->length_dw; i += 2) {
@@ -1294,10 +1287,12 @@
* Write ring commands to execute the indirect buffer
*/
static void uvd_v7_0_ring_emit_ib(struct amdgpu_ring *ring,
+ struct amdgpu_job *job,
struct amdgpu_ib *ib,
- unsigned vmid, bool ctx_switch)
+ uint32_t flags)
{
struct amdgpu_device *adev = ring->adev;
+ unsigned vmid = AMDGPU_JOB_GET_VMID(job);
amdgpu_ring_write(ring,
PACKET0(SOC15_REG_OFFSET(UVD, ring->me, mmUVD_LMI_RBC_IB_VMID), 0));
@@ -1323,8 +1318,12 @@
* 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 vmid, bool ctx_switch)
+ struct amdgpu_job *job,
+ struct amdgpu_ib *ib,
+ uint32_t flags)
{
+ unsigned vmid = AMDGPU_JOB_GET_VMID(job);
+
amdgpu_ring_write(ring, HEVC_ENC_CMD_IB_VM);
amdgpu_ring_write(ring, vmid);
amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
@@ -1376,7 +1375,7 @@
pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
/* wait for reg writes */
- data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
+ data0 = hub->ctx0_ptb_addr_lo32 + vmid * hub->ctx_addr_distance;
data1 = lower_32_bits(pd_addr);
mask = 0xffffffff;
uvd_v7_0_ring_emit_reg_wait(ring, data0, data1, mask);
@@ -1418,7 +1417,8 @@
pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
/* wait for reg writes */
- uvd_v7_0_enc_ring_emit_reg_wait(ring, hub->ctx0_ptb_addr_lo32 + vmid * 2,
+ uvd_v7_0_enc_ring_emit_reg_wait(ring, hub->ctx0_ptb_addr_lo32 +
+ vmid * hub->ctx_addr_distance,
lower_32_bits(pd_addr), 0xffffffff);
}
@@ -1694,7 +1694,7 @@
enum amd_clockgating_state state)
{
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
- bool enable = (state == AMD_CG_STATE_GATE) ? true : false;
+ bool enable = (state == AMD_CG_STATE_GATE);
uvd_v7_0_set_bypass_mode(adev, enable);
@@ -1773,7 +1773,8 @@
.type = AMDGPU_RING_TYPE_UVD,
.align_mask = 0xf,
.support_64bit_ptrs = false,
- .vmhub = AMDGPU_MMHUB,
+ .no_user_fence = true,
+ .vmhub = AMDGPU_MMHUB_0,
.get_rptr = uvd_v7_0_ring_get_rptr,
.get_wptr = uvd_v7_0_ring_get_wptr,
.set_wptr = uvd_v7_0_ring_set_wptr,
@@ -1805,7 +1806,8 @@
.align_mask = 0x3f,
.nop = HEVC_ENC_CMD_NO_OP,
.support_64bit_ptrs = false,
- .vmhub = AMDGPU_MMHUB,
+ .no_user_fence = true,
+ .vmhub = AMDGPU_MMHUB_0,
.get_rptr = uvd_v7_0_enc_ring_get_rptr,
.get_wptr = uvd_v7_0_enc_ring_get_wptr,
.set_wptr = uvd_v7_0_enc_ring_set_wptr,
--
Gitblit v1.6.2