[WHY]
When SPM trace enabled, SPM_VMID should be updated with the current
vmid.
[HOW]
Add a chunk id, AMDGPU_CHUNK_ID_SPM_TRACE, so that UMD can tell us
which job should update SPM_VMID.
Right before a job is submitted to GPU, set the SPM_VMID accordingly.
[Limitation]
Running more than one SPM trace enabled processes simultaneously is
not supported.
Change-Id: Ic932ef6ac9dbf244f03aaee90550e8ff3a675666
Signed-off-by: Jacob He <jacob.he@xxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 7 +++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 10 +++++++---
drivers/gpu/drm/amd/amdgpu/amdgpu_job.h | 1 +
drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h | 1 +
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 15 ++++++++++++++-
drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c | 3 ++-
drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 3 ++-
drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 15 ++++++++++++++-
8 files changed, 48 insertions(+), 7 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index f9fa6e104fef..3f32c4db5232 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -113,6 +113,7 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs
uint32_t uf_offset = 0;
int i;
int ret;
+ bool update_spm_vmid = false;
if (cs->in.num_chunks == 0)
return 0;
@@ -221,6 +222,10 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs
case AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL:
break;
+ case AMDGPU_CHUNK_ID_SPM_TRACE:
+ update_spm_vmid = true;
+ break;
+
default:
ret = -EINVAL;
goto free_partial_kdata;
@@ -231,6 +236,8 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs
if (ret)
goto free_all_kdata;
+ p->job->need_update_spm_vmid = update_spm_vmid;
+
if (p->ctx->vram_lost_counter != p->job->vram_lost_counter) {
ret = -ECANCELED;
goto free_all_kdata;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index cae81914c821..36faab12b585 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -156,9 +156,13 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
return -EINVAL;
}
- if (vm && !job->vmid) {
- dev_err(adev->dev, "VM IB without ID\n");
- return -EINVAL;
+ if (vm) {
+ if (!job->vmid) {
+ dev_err(adev->dev, "VM IB without ID\n");
+ return -EINVAL;
+ } else if (adev->gfx.rlc.funcs->update_spm_vmid && job->need_update_spm_vmid) {
+ adev->gfx.rlc.funcs->update_spm_vmid(adev, job->vmid);
+ }
}
alloc_size = ring->funcs->emit_frame_size + num_ibs *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index 2e2110dddb76..4582536961c7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -52,6 +52,7 @@ struct amdgpu_job {
bool vm_needs_flush;
uint64_t vm_pd_addr;
unsigned vmid;
+ bool need_update_spm_vmid;
unsigned pasid;
uint32_t gds_base, gds_size;
uint32_t gws_base, gws_size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
index d3d4707f2168..52509c254cbd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_rlc.h
@@ -126,6 +126,7 @@ struct amdgpu_rlc_funcs {
void (*stop)(struct amdgpu_device *adev);
void (*reset)(struct amdgpu_device *adev);
void (*start)(struct amdgpu_device *adev);
+ void (*update_spm_vmid)(struct amdgpu_device *adev, unsigned vmid);
};
struct amdgpu_rlc {
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index 5e9fb0976c6c..91eb788d6229 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -4214,6 +4214,18 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev,
return 0;
}
+static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
+{
+ u32 data;
+
+ data = RREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL);
+
+ data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK;
+ data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT;
+
+ WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+}
+
static const struct amdgpu_rlc_funcs gfx_v10_0_rlc_funcs = {
.is_rlc_enabled = gfx_v10_0_is_rlc_enabled,
.set_safe_mode = gfx_v10_0_set_safe_mode,
@@ -4224,7 +4236,8 @@ static const struct amdgpu_rlc_funcs gfx_v10_0_rlc_funcs = {
.resume = gfx_v10_0_rlc_resume,
.stop = gfx_v10_0_rlc_stop,
.reset = gfx_v10_0_rlc_reset,
- .start = gfx_v10_0_rlc_start
+ .start = gfx_v10_0_rlc_start,
+ .update_spm_vmid = gfx_v10_0_update_spm_vmid
};
static int gfx_v10_0_set_powergating_state(void *handle,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 8f20a5dd44fe..b24fc55cf13a 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -4221,7 +4221,8 @@ static const struct amdgpu_rlc_funcs gfx_v7_0_rlc_funcs = {
.resume = gfx_v7_0_rlc_resume,
.stop = gfx_v7_0_rlc_stop,
.reset = gfx_v7_0_rlc_reset,
- .start = gfx_v7_0_rlc_start
+ .start = gfx_v7_0_rlc_start,
+ .update_spm_vmid = NULL
};
static int gfx_v7_0_early_init(void *handle)
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index fa245973de12..66640d2b6b37 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -5600,7 +5600,8 @@ static const struct amdgpu_rlc_funcs iceland_rlc_funcs = {
.resume = gfx_v8_0_rlc_resume,
.stop = gfx_v8_0_rlc_stop,
.reset = gfx_v8_0_rlc_reset,
- .start = gfx_v8_0_rlc_start
+ .start = gfx_v8_0_rlc_start,
+ .update_spm_vmid = NULL
};
static void gfx_v8_0_update_medium_grain_clock_gating(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 9b7ff783e9a5..df872f949f68 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -4704,6 +4704,18 @@ static int gfx_v9_0_update_gfx_clock_gating(struct amdgpu_device *adev,
return 0;
}
+static void gfx_v9_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid)
+{
+ u32 data;
+
+ data = RREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL);
+
+ data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK;
+ data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT;
+
+ WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data);
+}
+
static const struct amdgpu_rlc_funcs gfx_v9_0_rlc_funcs = {
.is_rlc_enabled = gfx_v9_0_is_rlc_enabled,
.set_safe_mode = gfx_v9_0_set_safe_mode,
@@ -4715,7 +4727,8 @@ static const struct amdgpu_rlc_funcs gfx_v9_0_rlc_funcs = {
.resume = gfx_v9_0_rlc_resume,
.stop = gfx_v9_0_rlc_stop,
.reset = gfx_v9_0_rlc_reset,
- .start = gfx_v9_0_rlc_start
+ .start = gfx_v9_0_rlc_start,
+ .update_spm_vmid = gfx_v9_0_update_spm_vmid
};
static int gfx_v9_0_set_powergating_state(void *handle,
--
2.17.1
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
