drm/amdgpu: update ring reset function signature

Going forward, we'll need more than just the vmid.  Add the
guilty amdgpu_fence.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Alex Deucher
2025-06-05 16:12:08 -04:00
parent d0c35c84dc
commit 787e2ce10f
22 changed files with 70 additions and 26 deletions

View File

@@ -155,7 +155,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
if (is_guilty)
dma_fence_set_error(&s_job->s_fence->finished, -ETIME);
r = amdgpu_ring_reset(ring, job->vmid);
r = amdgpu_ring_reset(ring, job->vmid, NULL);
if (!r) {
if (amdgpu_ring_sched_ready(ring))
drm_sched_stop(&ring->sched, s_job);

View File

@@ -268,7 +268,8 @@ struct amdgpu_ring_funcs {
void (*patch_cntl)(struct amdgpu_ring *ring, unsigned offset);
void (*patch_ce)(struct amdgpu_ring *ring, unsigned offset);
void (*patch_de)(struct amdgpu_ring *ring, unsigned offset);
int (*reset)(struct amdgpu_ring *ring, unsigned int vmid);
int (*reset)(struct amdgpu_ring *ring, unsigned int vmid,
struct amdgpu_fence *timedout_fence);
void (*emit_cleaner_shader)(struct amdgpu_ring *ring);
bool (*is_guilty)(struct amdgpu_ring *ring);
};
@@ -425,7 +426,7 @@ struct amdgpu_ring {
#define amdgpu_ring_patch_cntl(r, o) ((r)->funcs->patch_cntl((r), (o)))
#define amdgpu_ring_patch_ce(r, o) ((r)->funcs->patch_ce((r), (o)))
#define amdgpu_ring_patch_de(r, o) ((r)->funcs->patch_de((r), (o)))
#define amdgpu_ring_reset(r, v) (r)->funcs->reset((r), (v))
#define amdgpu_ring_reset(r, v, f) (r)->funcs->reset((r), (v), (f))
unsigned int amdgpu_ring_max_ibs(enum amdgpu_ring_type type);
int amdgpu_ring_alloc(struct amdgpu_ring *ring, unsigned ndw);

View File

@@ -9522,7 +9522,9 @@ static void gfx_v10_ring_insert_nop(struct amdgpu_ring *ring, uint32_t num_nop)
amdgpu_ring_insert_nop(ring, num_nop - 1);
}
static int gfx_v10_0_reset_kgq(struct amdgpu_ring *ring, unsigned int vmid)
static int gfx_v10_0_reset_kgq(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
struct amdgpu_kiq *kiq = &adev->gfx.kiq[0];
@@ -9579,7 +9581,8 @@ static int gfx_v10_0_reset_kgq(struct amdgpu_ring *ring, unsigned int vmid)
}
static int gfx_v10_0_reset_kcq(struct amdgpu_ring *ring,
unsigned int vmid)
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
struct amdgpu_kiq *kiq = &adev->gfx.kiq[0];

View File

@@ -6811,7 +6811,9 @@ static int gfx_v11_reset_gfx_pipe(struct amdgpu_ring *ring)
return 0;
}
static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring, unsigned int vmid)
static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
int r;
@@ -6973,7 +6975,9 @@ static int gfx_v11_0_reset_compute_pipe(struct amdgpu_ring *ring)
return 0;
}
static int gfx_v11_0_reset_kcq(struct amdgpu_ring *ring, unsigned int vmid)
static int gfx_v11_0_reset_kcq(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
int r = 0;

View File

@@ -5307,7 +5307,9 @@ static int gfx_v12_reset_gfx_pipe(struct amdgpu_ring *ring)
return 0;
}
static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring, unsigned int vmid)
static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
int r;
@@ -5421,7 +5423,9 @@ static int gfx_v12_0_reset_compute_pipe(struct amdgpu_ring *ring)
return 0;
}
static int gfx_v12_0_reset_kcq(struct amdgpu_ring *ring, unsigned int vmid)
static int gfx_v12_0_reset_kcq(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
int r;

View File

@@ -7172,7 +7172,8 @@ static void gfx_v9_ring_insert_nop(struct amdgpu_ring *ring, uint32_t num_nop)
}
static int gfx_v9_0_reset_kcq(struct amdgpu_ring *ring,
unsigned int vmid)
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
struct amdgpu_kiq *kiq = &adev->gfx.kiq[0];

View File

@@ -3552,7 +3552,8 @@ static int gfx_v9_4_3_reset_hw_pipe(struct amdgpu_ring *ring)
}
static int gfx_v9_4_3_reset_kcq(struct amdgpu_ring *ring,
unsigned int vmid)
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
struct amdgpu_kiq *kiq = &adev->gfx.kiq[ring->xcc_id];

View File

@@ -764,7 +764,9 @@ static int jpeg_v2_0_process_interrupt(struct amdgpu_device *adev,
return 0;
}
static int jpeg_v2_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
static int jpeg_v2_0_ring_reset(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
jpeg_v2_0_stop(ring->adev);
jpeg_v2_0_start(ring->adev);

View File

@@ -643,7 +643,9 @@ static int jpeg_v2_5_process_interrupt(struct amdgpu_device *adev,
return 0;
}
static int jpeg_v2_5_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
static int jpeg_v2_5_ring_reset(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
jpeg_v2_5_stop_inst(ring->adev, ring->me);
jpeg_v2_5_start_inst(ring->adev, ring->me);

View File

@@ -555,7 +555,9 @@ static int jpeg_v3_0_process_interrupt(struct amdgpu_device *adev,
return 0;
}
static int jpeg_v3_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
static int jpeg_v3_0_ring_reset(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
jpeg_v3_0_stop(ring->adev);
jpeg_v3_0_start(ring->adev);

View File

@@ -720,7 +720,9 @@ static int jpeg_v4_0_process_interrupt(struct amdgpu_device *adev,
return 0;
}
static int jpeg_v4_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
static int jpeg_v4_0_ring_reset(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
if (amdgpu_sriov_vf(ring->adev))
return -EINVAL;

View File

@@ -1143,7 +1143,9 @@ static void jpeg_v4_0_3_core_stall_reset(struct amdgpu_ring *ring)
WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 0x00);
}
static int jpeg_v4_0_3_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
static int jpeg_v4_0_3_ring_reset(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
if (amdgpu_sriov_vf(ring->adev))
return -EOPNOTSUPP;

View File

@@ -834,7 +834,9 @@ static void jpeg_v5_0_1_core_stall_reset(struct amdgpu_ring *ring)
WREG32_SOC15(JPEG, jpeg_inst, regJPEG_CORE_RST_CTRL, 0x00);
}
static int jpeg_v5_0_1_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
static int jpeg_v5_0_1_ring_reset(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
if (amdgpu_sriov_vf(ring->adev))
return -EOPNOTSUPP;

View File

@@ -1675,7 +1675,9 @@ static bool sdma_v4_4_2_page_ring_is_guilty(struct amdgpu_ring *ring)
return sdma_v4_4_2_is_queue_selected(adev, instance_id, true);
}
static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
static int sdma_v4_4_2_reset_queue(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
u32 id = ring->me;

View File

@@ -1539,7 +1539,9 @@ static int sdma_v5_0_soft_reset(struct amdgpu_ip_block *ip_block)
return 0;
}
static int sdma_v5_0_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
static int sdma_v5_0_reset_queue(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
u32 inst_id = ring->me;

View File

@@ -1452,7 +1452,9 @@ static int sdma_v5_2_wait_for_idle(struct amdgpu_ip_block *ip_block)
return -ETIMEDOUT;
}
static int sdma_v5_2_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
static int sdma_v5_2_reset_queue(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
u32 inst_id = ring->me;

View File

@@ -1550,7 +1550,9 @@ static int sdma_v6_0_ring_preempt_ib(struct amdgpu_ring *ring)
return r;
}
static int sdma_v6_0_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
static int sdma_v6_0_reset_queue(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
int i, r;

View File

@@ -802,7 +802,9 @@ static bool sdma_v7_0_check_soft_reset(struct amdgpu_ip_block *ip_block)
return false;
}
static int sdma_v7_0_reset_queue(struct amdgpu_ring *ring, unsigned int vmid)
static int sdma_v7_0_reset_queue(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
int i, r;

View File

@@ -1967,7 +1967,9 @@ static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
return 0;
}
static int vcn_v4_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
static int vcn_v4_0_ring_reset(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[ring->me];

View File

@@ -1594,7 +1594,9 @@ static void vcn_v4_0_3_unified_ring_set_wptr(struct amdgpu_ring *ring)
}
}
static int vcn_v4_0_3_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
static int vcn_v4_0_3_ring_reset(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
int r = 0;
int vcn_inst;

View File

@@ -1465,7 +1465,9 @@ static void vcn_v4_0_5_unified_ring_set_wptr(struct amdgpu_ring *ring)
}
}
static int vcn_v4_0_5_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
static int vcn_v4_0_5_ring_reset(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[ring->me];

View File

@@ -1192,7 +1192,9 @@ static void vcn_v5_0_0_unified_ring_set_wptr(struct amdgpu_ring *ring)
}
}
static int vcn_v5_0_0_ring_reset(struct amdgpu_ring *ring, unsigned int vmid)
static int vcn_v5_0_0_ring_reset(struct amdgpu_ring *ring,
unsigned int vmid,
struct amdgpu_fence *timedout_fence)
{
struct amdgpu_device *adev = ring->adev;
struct amdgpu_vcn_inst *vinst = &adev->vcn.inst[ring->me];