From bedbef8ad3e75a304af6361af235302bcc61d06b Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 14 May 2024 06:39:01 +0000
Subject: [PATCH] 修改内核路径
---
kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 177 ++++++++++++++++++++++++++++++++++++++--------------------
1 files changed, 116 insertions(+), 61 deletions(-)
diff --git a/kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index f4e9d1b..163188c 100644
--- a/kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -28,12 +28,16 @@
*/
#include <linux/seq_file.h>
#include <linux/slab.h>
-#include <drm/drmP.h>
+
#include <drm/amdgpu_drm.h>
+#include <drm/drm_debugfs.h>
+
#include "amdgpu.h"
#include "atom.h"
+#include "amdgpu_trace.h"
#define AMDGPU_IB_TEST_TIMEOUT msecs_to_jiffies(1000)
+#define AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT msecs_to_jiffies(2000)
/*
* IB
@@ -44,7 +48,6 @@
* produce command buffers which are send to the kernel and
* put in IBs for execution by the requested ring.
*/
-static int amdgpu_debugfs_sa_init(struct amdgpu_device *adev);
/**
* amdgpu_ib_get - request an IB (Indirect Buffer)
@@ -58,12 +61,13 @@
* Returns 0 on success, error on failure.
*/
int amdgpu_ib_get(struct amdgpu_device *adev, struct amdgpu_vm *vm,
- unsigned size, struct amdgpu_ib *ib)
+ unsigned size, enum amdgpu_ib_pool_type pool_type,
+ struct amdgpu_ib *ib)
{
int r;
if (size) {
- r = amdgpu_sa_bo_new(&adev->ring_tmp_bo,
+ r = amdgpu_sa_bo_new(&adev->ib_pools[pool_type],
&ib->sa_bo, size, 256);
if (r) {
dev_err(adev->dev, "failed to get a new IB (%d)\n", r);
@@ -71,6 +75,8 @@
}
ib->ptr = amdgpu_sa_bo_cpu_addr(ib->sa_bo);
+ /* flush the cache before commit the IB */
+ ib->flags = AMDGPU_IB_FLAG_EMIT_MEM_SYNC;
if (!vm)
ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo);
@@ -122,12 +128,13 @@
struct amdgpu_device *adev = ring->adev;
struct amdgpu_ib *ib = &ibs[0];
struct dma_fence *tmp = NULL;
- bool skip_preamble, need_ctx_switch;
+ bool need_ctx_switch;
unsigned patch_offset = ~0;
struct amdgpu_vm *vm;
uint64_t fence_ctx;
uint32_t status = 0, alloc_size;
unsigned fence_flags = 0;
+ bool secure;
unsigned i;
int r = 0;
@@ -146,13 +153,19 @@
fence_ctx = 0;
}
- if (!ring->ready) {
+ if (!ring->sched.ready) {
dev_err(adev->dev, "couldn't schedule ib on ring <%s>\n", ring->name);
return -EINVAL;
}
if (vm && !job->vmid) {
dev_err(adev->dev, "VM IB without ID\n");
+ return -EINVAL;
+ }
+
+ if ((ib->flags & AMDGPU_IB_FLAGS_SECURE) &&
+ (ring->funcs->type == AMDGPU_RING_TYPE_COMPUTE)) {
+ dev_err(adev->dev, "secure submissions not supported on compute rings\n");
return -EINVAL;
}
@@ -167,12 +180,19 @@
need_ctx_switch = ring->current_ctx != fence_ctx;
if (ring->funcs->emit_pipeline_sync && job &&
- ((tmp = amdgpu_sync_get_fence(&job->sched_sync, NULL)) ||
+ ((tmp = amdgpu_sync_get_fence(&job->sched_sync)) ||
(amdgpu_sriov_vf(adev) && need_ctx_switch) ||
amdgpu_vm_need_pipeline_sync(ring, job))) {
need_pipe_sync = true;
+
+ if (tmp)
+ trace_amdgpu_ib_pipe_sync(job, tmp);
+
dma_fence_put(tmp);
}
+
+ if ((ib->flags & AMDGPU_IB_FLAG_EMIT_MEM_SYNC) && ring->funcs->emit_mem_sync)
+ ring->funcs->emit_mem_sync(ring);
if (ring->funcs->insert_start)
ring->funcs->insert_start(ring);
@@ -198,32 +218,40 @@
amdgpu_asic_flush_hdp(adev, ring);
}
- skip_preamble = ring->current_ctx == fence_ctx;
- if (job && ring->funcs->emit_cntxcntl) {
- if (need_ctx_switch)
- status |= AMDGPU_HAVE_CTX_SWITCH;
- status |= job->preamble_status;
+ if (need_ctx_switch)
+ status |= AMDGPU_HAVE_CTX_SWITCH;
+ if (job && ring->funcs->emit_cntxcntl) {
+ status |= job->preamble_status;
+ status |= job->preemption_status;
amdgpu_ring_emit_cntxcntl(ring, status);
+ }
+
+ /* Setup initial TMZiness and send it off.
+ */
+ secure = false;
+ if (job && ring->funcs->emit_frame_cntl) {
+ secure = ib->flags & AMDGPU_IB_FLAGS_SECURE;
+ amdgpu_ring_emit_frame_cntl(ring, true, secure);
}
for (i = 0; i < num_ibs; ++i) {
ib = &ibs[i];
- /* drop preamble IBs if we don't have a context switch */
- if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) &&
- skip_preamble &&
- !(status & AMDGPU_PREAMBLE_IB_PRESENT_FIRST) &&
- !amdgpu_sriov_vf(adev)) /* for SRIOV preemption, Preamble CE ib must be inserted anyway */
- continue;
+ if (job && ring->funcs->emit_frame_cntl) {
+ if (secure != !!(ib->flags & AMDGPU_IB_FLAGS_SECURE)) {
+ amdgpu_ring_emit_frame_cntl(ring, false, secure);
+ secure = !secure;
+ amdgpu_ring_emit_frame_cntl(ring, true, secure);
+ }
+ }
- amdgpu_ring_emit_ib(ring, ib, job ? job->vmid : 0,
- need_ctx_switch);
- need_ctx_switch = false;
+ amdgpu_ring_emit_ib(ring, job, ib, status);
+ status &= ~AMDGPU_HAVE_CTX_SWITCH;
}
- if (ring->funcs->emit_tmz)
- amdgpu_ring_emit_tmz(ring, false);
+ if (job && ring->funcs->emit_frame_cntl)
+ amdgpu_ring_emit_frame_cntl(ring, false, secure);
#ifdef CONFIG_X86_64
if (!(adev->flags & AMD_IS_APU))
@@ -272,24 +300,32 @@
*/
int amdgpu_ib_pool_init(struct amdgpu_device *adev)
{
- int r;
+ unsigned size;
+ int r, i;
- if (adev->ib_pool_ready) {
+ if (adev->ib_pool_ready)
return 0;
- }
- r = amdgpu_sa_bo_manager_init(adev, &adev->ring_tmp_bo,
- AMDGPU_IB_POOL_SIZE*64*1024,
- AMDGPU_GPU_PAGE_SIZE,
- AMDGPU_GEM_DOMAIN_GTT);
- if (r) {
- return r;
- }
- adev->ib_pool_ready = true;
- if (amdgpu_debugfs_sa_init(adev)) {
- dev_err(adev->dev, "failed to register debugfs file for SA\n");
+ for (i = 0; i < AMDGPU_IB_POOL_MAX; i++) {
+ if (i == AMDGPU_IB_POOL_DIRECT)
+ size = PAGE_SIZE * 2;
+ else
+ size = AMDGPU_IB_POOL_SIZE;
+
+ r = amdgpu_sa_bo_manager_init(adev, &adev->ib_pools[i],
+ size, AMDGPU_GPU_PAGE_SIZE,
+ AMDGPU_GEM_DOMAIN_GTT);
+ if (r)
+ goto error;
}
+ adev->ib_pool_ready = true;
+
return 0;
+
+error:
+ while (i--)
+ amdgpu_sa_bo_manager_fini(adev, &adev->ib_pools[i]);
+ return r;
}
/**
@@ -302,10 +338,14 @@
*/
void amdgpu_ib_pool_fini(struct amdgpu_device *adev)
{
- if (adev->ib_pool_ready) {
- amdgpu_sa_bo_manager_fini(adev, &adev->ring_tmp_bo);
- adev->ib_pool_ready = false;
- }
+ int i;
+
+ if (!adev->ib_pool_ready)
+ return;
+
+ for (i = 0; i < AMDGPU_IB_POOL_MAX; i++)
+ amdgpu_sa_bo_manager_fini(adev, &adev->ib_pools[i]);
+ adev->ib_pool_ready = false;
}
/**
@@ -320,9 +360,9 @@
*/
int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
{
- unsigned i;
- int r, ret = 0;
long tmo_gfx, tmo_mm;
+ int r, ret = 0;
+ unsigned i;
tmo_mm = tmo_gfx = AMDGPU_IB_TEST_TIMEOUT;
if (amdgpu_sriov_vf(adev)) {
@@ -341,13 +381,18 @@
* cost waiting for it coming back under RUNTIME only
*/
tmo_gfx = 8 * AMDGPU_IB_TEST_TIMEOUT;
+ } else if (adev->gmc.xgmi.hive_id) {
+ tmo_gfx = AMDGPU_IB_TEST_GFX_XGMI_TIMEOUT;
}
- for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
+ for (i = 0; i < adev->num_rings; ++i) {
struct amdgpu_ring *ring = adev->rings[i];
long tmo;
- if (!ring || !ring->ready)
+ /* KIQ rings don't have an IB test because we never submit IBs
+ * to them and they have no interrupt support.
+ */
+ if (!ring->sched.ready || !ring->funcs->test_ib)
continue;
/* MM engine need more time */
@@ -362,20 +407,23 @@
tmo = tmo_gfx;
r = amdgpu_ring_test_ib(ring, tmo);
- if (r) {
- ring->ready = false;
+ if (!r) {
+ DRM_DEV_DEBUG(adev->dev, "ib test on %s succeeded\n",
+ ring->name);
+ continue;
+ }
- if (ring == &adev->gfx.gfx_ring[0]) {
- /* oh, oh, that's really bad */
- DRM_ERROR("amdgpu: failed testing IB on GFX ring (%d).\n", r);
- adev->accel_working = false;
- return r;
+ ring->sched.ready = false;
+ DRM_DEV_ERROR(adev->dev, "IB test failed on %s (%d).\n",
+ ring->name, r);
- } else {
- /* still not good, but we can live with it */
- DRM_ERROR("amdgpu: failed testing IB on ring %d (%d).\n", i, r);
- ret = r;
- }
+ if (ring == &adev->gfx.gfx_ring[0]) {
+ /* oh, oh, that's really bad */
+ adev->accel_working = false;
+ return r;
+
+ } else {
+ ret = r;
}
}
return ret;
@@ -390,12 +438,18 @@
{
struct drm_info_node *node = (struct drm_info_node *) m->private;
struct drm_device *dev = node->minor->dev;
- struct amdgpu_device *adev = dev->dev_private;
+ struct amdgpu_device *adev = drm_to_adev(dev);
- amdgpu_sa_bo_dump_debug_info(&adev->ring_tmp_bo, m);
+ seq_printf(m, "--------------------- DELAYED --------------------- \n");
+ amdgpu_sa_bo_dump_debug_info(&adev->ib_pools[AMDGPU_IB_POOL_DELAYED],
+ m);
+ seq_printf(m, "-------------------- IMMEDIATE -------------------- \n");
+ amdgpu_sa_bo_dump_debug_info(&adev->ib_pools[AMDGPU_IB_POOL_IMMEDIATE],
+ m);
+ seq_printf(m, "--------------------- DIRECT ---------------------- \n");
+ amdgpu_sa_bo_dump_debug_info(&adev->ib_pools[AMDGPU_IB_POOL_DIRECT], m);
return 0;
-
}
static const struct drm_info_list amdgpu_debugfs_sa_list[] = {
@@ -404,10 +458,11 @@
#endif
-static int amdgpu_debugfs_sa_init(struct amdgpu_device *adev)
+int amdgpu_debugfs_sa_init(struct amdgpu_device *adev)
{
#if defined(CONFIG_DEBUG_FS)
- return amdgpu_debugfs_add_files(adev, amdgpu_debugfs_sa_list, 1);
+ return amdgpu_debugfs_add_files(adev, amdgpu_debugfs_sa_list,
+ ARRAY_SIZE(amdgpu_debugfs_sa_list));
#else
return 0;
#endif
--
Gitblit v1.6.2