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/amdgpu_trace.h | 138 +++++++++++++++++++++++++++++++++++----------
1 files changed, 106 insertions(+), 32 deletions(-)
diff --git a/kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index db9907f..86cfb3d 100644
--- a/kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/kernel/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -28,8 +28,6 @@
#include <linux/types.h>
#include <linux/tracepoint.h>
-#include <drm/drmP.h>
-
#undef TRACE_SYSTEM
#define TRACE_SYSTEM amdgpu
#define TRACE_INCLUDE_FILE amdgpu_trace
@@ -37,7 +35,7 @@
#define AMDGPU_JOB_GET_TIMELINE_NAME(job) \
job->base.s_fence->finished.ops->get_timeline_name(&job->base.s_fence->finished)
-TRACE_EVENT(amdgpu_mm_rreg,
+TRACE_EVENT(amdgpu_device_rreg,
TP_PROTO(unsigned did, uint32_t reg, uint32_t value),
TP_ARGS(did, reg, value),
TP_STRUCT__entry(
@@ -56,7 +54,7 @@
(unsigned long)__entry->value)
);
-TRACE_EVENT(amdgpu_mm_wreg,
+TRACE_EVENT(amdgpu_device_wreg,
TP_PROTO(unsigned did, uint32_t reg, uint32_t value),
TP_ARGS(did, reg, value),
TP_STRUCT__entry(
@@ -76,9 +74,10 @@
);
TRACE_EVENT(amdgpu_iv,
- TP_PROTO(struct amdgpu_iv_entry *iv),
- TP_ARGS(iv),
+ TP_PROTO(unsigned ih, struct amdgpu_iv_entry *iv),
+ TP_ARGS(ih, iv),
TP_STRUCT__entry(
+ __field(unsigned, ih)
__field(unsigned, client_id)
__field(unsigned, src_id)
__field(unsigned, ring_id)
@@ -90,6 +89,7 @@
__array(unsigned, src_data, 4)
),
TP_fast_assign(
+ __entry->ih = ih;
__entry->client_id = iv->client_id;
__entry->src_id = iv->src_id;
__entry->ring_id = iv->ring_id;
@@ -103,8 +103,9 @@
__entry->src_data[2] = iv->src_data[2];
__entry->src_data[3] = iv->src_data[3];
),
- TP_printk("client_id:%u src_id:%u ring:%u vmid:%u timestamp: %llu pasid:%u src_data: %08x %08x %08x %08x\n",
- __entry->client_id, __entry->src_id,
+ TP_printk("ih:%u client_id:%u src_id:%u ring:%u vmid:%u "
+ "timestamp: %llu pasid:%u src_data: %08x %08x %08x %08x",
+ __entry->ih, __entry->client_id, __entry->src_id,
__entry->ring_id, __entry->vmid,
__entry->timestamp, __entry->pasid,
__entry->src_data[0], __entry->src_data[1],
@@ -150,10 +151,10 @@
TP_fast_assign(
__entry->bo_list = p->bo_list;
- __entry->ring = p->ring->idx;
+ __entry->ring = to_amdgpu_ring(p->entity->rq->sched)->idx;
__entry->dw = p->job->ibs[i].length_dw;
__entry->fences = amdgpu_fence_count_emitted(
- p->ring);
+ to_amdgpu_ring(p->entity->rq->sched));
),
TP_printk("bo_list=%p, ring=%u, dw=%u, fences=%u",
__entry->bo_list, __entry->ring, __entry->dw,
@@ -169,7 +170,7 @@
__field(unsigned int, context)
__field(unsigned int, seqno)
__field(struct dma_fence *, fence)
- __field(char *, ring_name)
+ __string(ring, to_amdgpu_ring(job->base.sched)->name)
__field(u32, num_ibs)
),
@@ -178,12 +179,12 @@
__assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
__entry->context = job->base.s_fence->finished.context;
__entry->seqno = job->base.s_fence->finished.seqno;
- __entry->ring_name = to_amdgpu_ring(job->base.sched)->name;
+ __assign_str(ring, to_amdgpu_ring(job->base.sched)->name)
__entry->num_ibs = job->num_ibs;
),
TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
__entry->sched_job_id, __get_str(timeline), __entry->context,
- __entry->seqno, __entry->ring_name, __entry->num_ibs)
+ __entry->seqno, __get_str(ring), __entry->num_ibs)
);
TRACE_EVENT(amdgpu_sched_run_job,
@@ -194,7 +195,7 @@
__string(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
__field(unsigned int, context)
__field(unsigned int, seqno)
- __field(char *, ring_name)
+ __string(ring, to_amdgpu_ring(job->base.sched)->name)
__field(u32, num_ibs)
),
@@ -203,12 +204,12 @@
__assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
__entry->context = job->base.s_fence->finished.context;
__entry->seqno = job->base.s_fence->finished.seqno;
- __entry->ring_name = to_amdgpu_ring(job->base.sched)->name;
+ __assign_str(ring, to_amdgpu_ring(job->base.sched)->name)
__entry->num_ibs = job->num_ibs;
),
TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
__entry->sched_job_id, __get_str(timeline), __entry->context,
- __entry->seqno, __entry->ring_name, __entry->num_ibs)
+ __entry->seqno, __get_str(ring), __entry->num_ibs)
);
@@ -218,6 +219,7 @@
TP_ARGS(vm, ring, job),
TP_STRUCT__entry(
__field(u32, pasid)
+ __string(ring, ring->name)
__field(u32, ring)
__field(u32, vmid)
__field(u32, vm_hub)
@@ -227,14 +229,14 @@
TP_fast_assign(
__entry->pasid = vm->pasid;
- __entry->ring = ring->idx;
+ __assign_str(ring, ring->name)
__entry->vmid = job->vmid;
__entry->vm_hub = ring->funcs->vmhub,
__entry->pd_addr = job->vm_pd_addr;
__entry->needs_flush = job->vm_needs_flush;
),
- TP_printk("pasid=%d, ring=%u, id=%u, hub=%u, pd_addr=%010Lx needs_flush=%u",
- __entry->pasid, __entry->ring, __entry->vmid,
+ TP_printk("pasid=%d, ring=%s, id=%u, hub=%u, pd_addr=%010Lx needs_flush=%u",
+ __entry->pasid, __get_str(ring), __entry->vmid,
__entry->vm_hub, __entry->pd_addr, __entry->needs_flush)
);
@@ -319,16 +321,60 @@
TP_ARGS(mapping)
);
+TRACE_EVENT(amdgpu_vm_update_ptes,
+ TP_PROTO(struct amdgpu_vm_update_params *p,
+ uint64_t start, uint64_t end,
+ unsigned int nptes, uint64_t dst,
+ uint64_t incr, uint64_t flags,
+ pid_t pid, uint64_t vm_ctx),
+ TP_ARGS(p, start, end, nptes, dst, incr, flags, pid, vm_ctx),
+ TP_STRUCT__entry(
+ __field(u64, start)
+ __field(u64, end)
+ __field(u64, flags)
+ __field(unsigned int, nptes)
+ __field(u64, incr)
+ __field(pid_t, pid)
+ __field(u64, vm_ctx)
+ __dynamic_array(u64, dst, nptes)
+ ),
+
+ TP_fast_assign(
+ unsigned int i;
+
+ __entry->start = start;
+ __entry->end = end;
+ __entry->flags = flags;
+ __entry->incr = incr;
+ __entry->nptes = nptes;
+ __entry->pid = pid;
+ __entry->vm_ctx = vm_ctx;
+ for (i = 0; i < nptes; ++i) {
+ u64 addr = p->pages_addr ? amdgpu_vm_map_gart(
+ p->pages_addr, dst) : dst;
+
+ ((u64 *)__get_dynamic_array(dst))[i] = addr;
+ dst += incr;
+ }
+ ),
+ TP_printk("pid:%u vm_ctx:0x%llx start:0x%010llx end:0x%010llx,"
+ " flags:0x%llx, incr:%llu, dst:\n%s", __entry->pid,
+ __entry->vm_ctx, __entry->start, __entry->end,
+ __entry->flags, __entry->incr, __print_array(
+ __get_dynamic_array(dst), __entry->nptes, 8))
+);
+
TRACE_EVENT(amdgpu_vm_set_ptes,
TP_PROTO(uint64_t pe, uint64_t addr, unsigned count,
- uint32_t incr, uint64_t flags),
- TP_ARGS(pe, addr, count, incr, flags),
+ uint32_t incr, uint64_t flags, bool direct),
+ TP_ARGS(pe, addr, count, incr, flags, direct),
TP_STRUCT__entry(
__field(u64, pe)
__field(u64, addr)
__field(u32, count)
__field(u32, incr)
__field(u64, flags)
+ __field(bool, direct)
),
TP_fast_assign(
@@ -337,28 +383,32 @@
__entry->count = count;
__entry->incr = incr;
__entry->flags = flags;
+ __entry->direct = direct;
),
- TP_printk("pe=%010Lx, addr=%010Lx, incr=%u, flags=%llx, count=%u",
- __entry->pe, __entry->addr, __entry->incr,
- __entry->flags, __entry->count)
+ TP_printk("pe=%010Lx, addr=%010Lx, incr=%u, flags=%llx, count=%u, "
+ "direct=%d", __entry->pe, __entry->addr, __entry->incr,
+ __entry->flags, __entry->count, __entry->direct)
);
TRACE_EVENT(amdgpu_vm_copy_ptes,
- TP_PROTO(uint64_t pe, uint64_t src, unsigned count),
- TP_ARGS(pe, src, count),
+ TP_PROTO(uint64_t pe, uint64_t src, unsigned count, bool direct),
+ TP_ARGS(pe, src, count, direct),
TP_STRUCT__entry(
__field(u64, pe)
__field(u64, src)
__field(u32, count)
+ __field(bool, direct)
),
TP_fast_assign(
__entry->pe = pe;
__entry->src = src;
__entry->count = count;
+ __entry->direct = direct;
),
- TP_printk("pe=%010Lx, src=%010Lx, count=%u",
- __entry->pe, __entry->src, __entry->count)
+ TP_printk("pe=%010Lx, src=%010Lx, count=%u, direct=%d",
+ __entry->pe, __entry->src, __entry->count,
+ __entry->direct)
);
TRACE_EVENT(amdgpu_vm_flush,
@@ -366,20 +416,20 @@
uint64_t pd_addr),
TP_ARGS(ring, vmid, pd_addr),
TP_STRUCT__entry(
- __field(u32, ring)
+ __string(ring, ring->name)
__field(u32, vmid)
__field(u32, vm_hub)
__field(u64, pd_addr)
),
TP_fast_assign(
- __entry->ring = ring->idx;
+ __assign_str(ring, ring->name)
__entry->vmid = vmid;
__entry->vm_hub = ring->funcs->vmhub;
__entry->pd_addr = pd_addr;
),
- TP_printk("ring=%u, id=%u, hub=%u, pd_addr=%010Lx",
- __entry->ring, __entry->vmid,
+ TP_printk("ring=%s, id=%u, hub=%u, pd_addr=%010Lx",
+ __get_str(ring), __entry->vmid,
__entry->vm_hub,__entry->pd_addr)
);
@@ -462,6 +512,30 @@
__entry->new_placement, __entry->bo_size)
);
+TRACE_EVENT(amdgpu_ib_pipe_sync,
+ TP_PROTO(struct amdgpu_job *sched_job, struct dma_fence *fence),
+ TP_ARGS(sched_job, fence),
+ TP_STRUCT__entry(
+ __string(ring, sched_job->base.sched->name)
+ __field(uint64_t, id)
+ __field(struct dma_fence *, fence)
+ __field(uint64_t, ctx)
+ __field(unsigned, seqno)
+ ),
+
+ TP_fast_assign(
+ __assign_str(ring, sched_job->base.sched->name)
+ __entry->id = sched_job->base.id;
+ __entry->fence = fence;
+ __entry->ctx = fence->context;
+ __entry->seqno = fence->seqno;
+ ),
+ TP_printk("job ring=%s, id=%llu, need pipe sync to fence=%p, context=%llu, seq=%u",
+ __get_str(ring), __entry->id,
+ __entry->fence, __entry->ctx,
+ __entry->seqno)
+);
+
#undef AMDGPU_JOB_GET_TIMELINE_NAME
#endif
--
Gitblit v1.6.2