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/sdma_v2_4.c | 159 +++++++++++++++++-----------------------------------
1 files changed, 53 insertions(+), 106 deletions(-)
diff --git a/kernel/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/kernel/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index 15ae4bc..5f304d6 100644
--- a/kernel/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/kernel/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -21,8 +21,11 @@
*
* Authors: Alex Deucher
*/
+
+#include <linux/delay.h>
#include <linux/firmware.h>
-#include <drm/drmP.h>
+#include <linux/module.h>
+
#include "amdgpu.h"
#include "amdgpu_ucode.h"
#include "amdgpu_trace.h"
@@ -225,7 +228,7 @@
static void sdma_v2_4_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
{
- struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ring);
+ struct amdgpu_sdma_instance *sdma = amdgpu_sdma_get_instance_from_ring(ring);
int i;
for (i = 0; i < count; i++)
@@ -245,11 +248,14 @@
* Schedule an IB in the DMA ring (VI).
*/
static void sdma_v2_4_ring_emit_ib(struct amdgpu_ring *ring,
+ struct amdgpu_job *job,
struct amdgpu_ib *ib,
- unsigned vmid, bool ctx_switch)
+ uint32_t flags)
{
+ unsigned vmid = AMDGPU_JOB_GET_VMID(job);
+
/* IB packet must end on a 8 DW boundary */
- sdma_v2_4_ring_insert_nop(ring, (10 - (lower_32_bits(ring->wptr) & 7)) % 8);
+ sdma_v2_4_ring_insert_nop(ring, (2 - lower_32_bits(ring->wptr)) & 7);
amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_INDIRECT) |
SDMA_PKT_INDIRECT_HEADER_VMID(vmid & 0xf));
@@ -349,8 +355,6 @@
ib_cntl = REG_SET_FIELD(ib_cntl, SDMA0_GFX_IB_CNTL, IB_ENABLE, 0);
WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl);
}
- sdma0->ready = false;
- sdma1->ready = false;
}
/**
@@ -471,17 +475,15 @@
/* enable DMA IBs */
WREG32(mmSDMA0_GFX_IB_CNTL + sdma_offsets[i], ib_cntl);
- ring->ready = true;
+ ring->sched.ready = true;
}
sdma_v2_4_enable(adev, true);
for (i = 0; i < adev->sdma.num_instances; i++) {
ring = &adev->sdma.instance[i].ring;
- r = amdgpu_ring_test_ring(ring);
- if (r) {
- ring->ready = false;
+ r = amdgpu_ring_test_helper(ring);
+ if (r)
return r;
- }
if (adev->mman.buffer_funcs_ring == ring)
amdgpu_ttm_set_buffer_funcs_status(adev, true);
@@ -504,41 +506,6 @@
return 0;
}
-/**
- * sdma_v2_4_load_microcode - load the sDMA ME ucode
- *
- * @adev: amdgpu_device pointer
- *
- * Loads the sDMA0/1 ucode.
- * Returns 0 for success, -EINVAL if the ucode is not available.
- */
-static int sdma_v2_4_load_microcode(struct amdgpu_device *adev)
-{
- const struct sdma_firmware_header_v1_0 *hdr;
- const __le32 *fw_data;
- u32 fw_size;
- int i, j;
-
- /* halt the MEs */
- sdma_v2_4_enable(adev, false);
-
- for (i = 0; i < adev->sdma.num_instances; i++) {
- if (!adev->sdma.instance[i].fw)
- return -EINVAL;
- hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma.instance[i].fw->data;
- amdgpu_ucode_print_sdma_hdr(&hdr->header);
- fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
- fw_data = (const __le32 *)
- (adev->sdma.instance[i].fw->data +
- le32_to_cpu(hdr->header.ucode_array_offset_bytes));
- WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
- for (j = 0; j < fw_size; j++)
- WREG32(mmSDMA0_UCODE_DATA + sdma_offsets[i], le32_to_cpup(fw_data++));
- WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], adev->sdma.instance[i].fw_version);
- }
-
- return 0;
-}
/**
* sdma_v2_4_start - setup and start the async dma engines
@@ -551,13 +518,6 @@
static int sdma_v2_4_start(struct amdgpu_device *adev)
{
int r;
-
-
- if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
- r = sdma_v2_4_load_microcode(adev);
- if (r)
- return r;
- }
/* halt the engine before programing */
sdma_v2_4_enable(adev, false);
@@ -592,21 +552,16 @@
u64 gpu_addr;
r = amdgpu_device_wb_get(adev, &index);
- if (r) {
- dev_err(adev->dev, "(%d) failed to allocate wb slot\n", r);
+ if (r)
return r;
- }
gpu_addr = adev->wb.gpu_addr + (index * 4);
tmp = 0xCAFEDEAD;
adev->wb.wb[index] = cpu_to_le32(tmp);
r = amdgpu_ring_alloc(ring, 5);
- if (r) {
- DRM_ERROR("amdgpu: dma failed to lock ring %d (%d).\n", ring->idx, r);
- amdgpu_device_wb_free(adev, index);
- return r;
- }
+ if (r)
+ goto error_free_wb;
amdgpu_ring_write(ring, SDMA_PKT_HEADER_OP(SDMA_OP_WRITE) |
SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_WRITE_LINEAR));
@@ -620,18 +575,14 @@
tmp = le32_to_cpu(adev->wb.wb[index]);
if (tmp == 0xDEADBEEF)
break;
- DRM_UDELAY(1);
+ udelay(1);
}
- if (i < adev->usec_timeout) {
- 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",
- ring->idx, tmp);
- r = -EINVAL;
- }
+ if (i >= adev->usec_timeout)
+ r = -ETIMEDOUT;
+
+error_free_wb:
amdgpu_device_wb_free(adev, index);
-
return r;
}
@@ -654,20 +605,17 @@
long r;
r = amdgpu_device_wb_get(adev, &index);
- if (r) {
- dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
+ if (r)
return r;
- }
gpu_addr = adev->wb.gpu_addr + (index * 4);
tmp = 0xCAFEDEAD;
adev->wb.wb[index] = cpu_to_le32(tmp);
memset(&ib, 0, sizeof(ib));
- r = amdgpu_ib_get(adev, NULL, 256, &ib);
- if (r) {
- DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
+ r = amdgpu_ib_get(adev, NULL, 256,
+ AMDGPU_IB_POOL_DIRECT, &ib);
+ if (r)
goto err0;
- }
ib.ptr[0] = SDMA_PKT_HEADER_OP(SDMA_OP_WRITE) |
SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_WRITE_LINEAR);
@@ -686,21 +634,16 @@
r = dma_fence_wait_timeout(f, false, timeout);
if (r == 0) {
- DRM_ERROR("amdgpu: IB test timed out\n");
r = -ETIMEDOUT;
goto err1;
} else if (r < 0) {
- DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
goto err1;
}
tmp = le32_to_cpu(adev->wb.wb[index]);
- if (tmp == 0xDEADBEEF) {
- DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
+ if (tmp == 0xDEADBEEF)
r = 0;
- } else {
- DRM_ERROR("amdgpu: ib test failed (0x%08X)\n", tmp);
+ else
r = -EINVAL;
- }
err1:
amdgpu_ib_free(adev, &ib, NULL);
@@ -802,11 +745,11 @@
*/
static void sdma_v2_4_ring_pad_ib(struct amdgpu_ring *ring, struct amdgpu_ib *ib)
{
- struct amdgpu_sdma_instance *sdma = amdgpu_get_sdma_instance(ring);
+ struct amdgpu_sdma_instance *sdma = amdgpu_sdma_get_instance_from_ring(ring);
u32 pad_count;
int i;
- pad_count = (8 - (ib->length_dw & 0x7)) % 8;
+ pad_count = (-ib->length_dw) & 7;
for (i = 0; i < pad_count; i++)
if (sdma && sdma->burst_nop && (i == 0))
ib->ptr[ib->length_dw++] =
@@ -898,19 +841,19 @@
struct amdgpu_device *adev = (struct amdgpu_device *)handle;
/* SDMA trap event */
- r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_TRAP,
+ r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_TRAP,
&adev->sdma.trap_irq);
if (r)
return r;
/* SDMA Privileged inst */
- r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 241,
+ r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, 241,
&adev->sdma.illegal_inst_irq);
if (r)
return r;
/* SDMA Privileged inst */
- r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_SRBM_WRITE,
+ r = amdgpu_irq_add_id(adev, AMDGPU_IRQ_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_SRBM_WRITE,
&adev->sdma.illegal_inst_irq);
if (r)
return r;
@@ -929,8 +872,9 @@
r = amdgpu_ring_init(adev, ring, 1024,
&adev->sdma.trap_irq,
(i == 0) ?
- AMDGPU_SDMA_IRQ_TRAP0 :
- AMDGPU_SDMA_IRQ_TRAP1);
+ AMDGPU_SDMA_IRQ_INSTANCE0 :
+ AMDGPU_SDMA_IRQ_INSTANCE1,
+ AMDGPU_RING_PRIO_DEFAULT);
if (r)
return r;
}
@@ -1065,7 +1009,7 @@
u32 sdma_cntl;
switch (type) {
- case AMDGPU_SDMA_IRQ_TRAP0:
+ case AMDGPU_SDMA_IRQ_INSTANCE0:
switch (state) {
case AMDGPU_IRQ_STATE_DISABLE:
sdma_cntl = RREG32(mmSDMA0_CNTL + SDMA0_REGISTER_OFFSET);
@@ -1081,7 +1025,7 @@
break;
}
break;
- case AMDGPU_SDMA_IRQ_TRAP1:
+ case AMDGPU_SDMA_IRQ_INSTANCE1:
switch (state) {
case AMDGPU_IRQ_STATE_DISABLE:
sdma_cntl = RREG32(mmSDMA0_CNTL + SDMA1_REGISTER_OFFSET);
@@ -1147,8 +1091,14 @@
struct amdgpu_irq_src *source,
struct amdgpu_iv_entry *entry)
{
+ u8 instance_id, queue_id;
+
DRM_ERROR("Illegal instruction in SDMA command stream\n");
- schedule_work(&adev->reset_work);
+ instance_id = (entry->ring_id & 0x3) >> 0;
+ queue_id = (entry->ring_id & 0xc) >> 2;
+
+ if (instance_id <= 1 && queue_id == 0)
+ drm_sched_fault(&adev->sdma.instance[instance_id].ring.sched);
return 0;
}
@@ -1250,7 +1200,8 @@
static void sdma_v2_4_emit_copy_buffer(struct amdgpu_ib *ib,
uint64_t src_offset,
uint64_t dst_offset,
- uint32_t byte_count)
+ uint32_t byte_count,
+ bool tmz)
{
ib->ptr[ib->length_dw++] = SDMA_PKT_HEADER_OP(SDMA_OP_COPY) |
SDMA_PKT_HEADER_SUB_OP(SDMA_SUBOP_COPY_LINEAR);
@@ -1296,10 +1247,8 @@
static void sdma_v2_4_set_buffer_funcs(struct amdgpu_device *adev)
{
- if (adev->mman.buffer_funcs == NULL) {
- adev->mman.buffer_funcs = &sdma_v2_4_buffer_funcs;
- adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
- }
+ adev->mman.buffer_funcs = &sdma_v2_4_buffer_funcs;
+ adev->mman.buffer_funcs_ring = &adev->sdma.instance[0].ring;
}
static const struct amdgpu_vm_pte_funcs sdma_v2_4_vm_pte_funcs = {
@@ -1314,14 +1263,12 @@
{
unsigned i;
- if (adev->vm_manager.vm_pte_funcs == NULL) {
- adev->vm_manager.vm_pte_funcs = &sdma_v2_4_vm_pte_funcs;
- for (i = 0; i < adev->sdma.num_instances; i++)
- adev->vm_manager.vm_pte_rings[i] =
- &adev->sdma.instance[i].ring;
-
- adev->vm_manager.vm_pte_num_rings = adev->sdma.num_instances;
+ adev->vm_manager.vm_pte_funcs = &sdma_v2_4_vm_pte_funcs;
+ for (i = 0; i < adev->sdma.num_instances; i++) {
+ adev->vm_manager.vm_pte_scheds[i] =
+ &adev->sdma.instance[i].ring.sched;
}
+ adev->vm_manager.vm_pte_num_scheds = adev->sdma.num_instances;
}
const struct amdgpu_ip_block_version sdma_v2_4_ip_block =
--
Gitblit v1.6.2