drm/amdgpu/gfx11: Refactor compute pipe reset and add HQD cleanup

Refactor gfx_v11_0_reset_compute_pipe() to accept explicit me, pipe, and
queue parameters instead of deriving them from the ring structure. This
enables the function to be used in generic pipe reset flows.

Introduce gfx_v11_0_clear_hqds_on_mec_pipe() to properly clear
CP_HQD_ACTIVE and CP_HQD_DEQUEUE_REQUEST for all queues on a given MEC
pipe while the pipe reset is asserted, ensuring the HQDs are torn down
correctly before deasserting reset.

Switch the KCQ reset path to use the common MEC pipe reset helper
amdgpu_gfx_mec_pipe_reset_run(), which coordinates the reset sequence
including KFD suspend/resume to avoid conflicts with user mode queues.

v2: just update the sequence (Alex)
v3: directly clear ACTIVE and DEQUEUE_REQUEST (Shaoyun Liu)

Suggested-by:  Manu Rastogi <manu.rastogi@amd.com>
Suggested-by:  Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Jesse Zhang <jesse.zhang@amd.com>
Reviewed-by: Prike Liang <Prike.Liang@amd.com>
Reviewed-by: Shaoyun Liu <shaoyun.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 890f45413fc5ac00cd721eb0d3bedcd94fe8075b..c1efb778ebcbc3575736862207815730a3e90a6a 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -6913,11 +6913,29 @@ static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring,
        return amdgpu_ring_reset_helper_end(ring, timedout_fence);
 }
 
-static int gfx_v11_0_reset_compute_pipe(struct amdgpu_ring *ring)
+/*
+ * With MEC pipe reset asserted, clear CP_HQD_ACTIVE / CP_HQD_DEQUEUE_REQUEST for
+ * every queue on (me, pipe). HQDs must be torn down while pipe reset stays
+ * asserted; only then clear the pipe reset bit.
+ * Caller must hold adev->srbm_mutex.
+ */
+static void gfx_v11_0_clear_hqds_on_mec_pipe(struct amdgpu_device *adev, u32 me,
+                                            u32 pipe)
 {
+       unsigned int q;
 
-       struct amdgpu_device *adev = ring->adev;
-       uint32_t reset_pipe = 0, clean_pipe = 0;
+       for (q = 0; q < adev->gfx.mec.num_queue_per_pipe; q++) {
+               soc21_grbm_select(adev, me, pipe, q, 0);
+               /* Start from a clean HQD dequeue state before forcing HQD inactive. */
+               WREG32_SOC15(GC, 0, regCP_HQD_ACTIVE, 0);
+               WREG32_SOC15(GC, 0, regCP_HQD_DEQUEUE_REQUEST, 0);
+       }
+}
+
+static int gfx_v11_0_reset_compute_pipe(struct amdgpu_device *adev,
+                                          u32 me, u32 pipe, u32 queue)
+{
+       uint32_t reset_val, clean_val;
        int r;
 
        if (!gfx_v11_pipe_reset_support(adev))
@@ -6925,109 +6943,113 @@ static int gfx_v11_0_reset_compute_pipe(struct amdgpu_ring *ring)
 
        gfx_v11_0_set_safe_mode(adev, 0);
        mutex_lock(&adev->srbm_mutex);
-       soc21_grbm_select(adev, ring->me, ring->pipe, ring->queue, 0);
-
-       reset_pipe = RREG32_SOC15(GC, 0, regCP_MEC_RS64_CNTL);
-       clean_pipe = reset_pipe;
+       soc21_grbm_select(adev, me, pipe, queue, 0);
 
        if (adev->gfx.rs64_enable) {
+               reset_val = RREG32_SOC15(GC, 0, regCP_MEC_RS64_CNTL);
+               clean_val = reset_val;
 
-               switch (ring->pipe) {
+               switch (pipe) {
                case 0:
-                       reset_pipe = REG_SET_FIELD(reset_pipe, CP_MEC_RS64_CNTL,
-                                                  MEC_PIPE0_RESET, 1);
-                       clean_pipe = REG_SET_FIELD(clean_pipe, CP_MEC_RS64_CNTL,
-                                                  MEC_PIPE0_RESET, 0);
+                       reset_val = REG_SET_FIELD(reset_val, CP_MEC_RS64_CNTL,
+                                                 MEC_PIPE0_RESET, 1);
+                       clean_val = REG_SET_FIELD(clean_val, CP_MEC_RS64_CNTL,
+                                                 MEC_PIPE0_RESET, 0);
                        break;
                case 1:
-                       reset_pipe = REG_SET_FIELD(reset_pipe, CP_MEC_RS64_CNTL,
-                                                  MEC_PIPE1_RESET, 1);
-                       clean_pipe = REG_SET_FIELD(clean_pipe, CP_MEC_RS64_CNTL,
-                                                  MEC_PIPE1_RESET, 0);
+                       reset_val = REG_SET_FIELD(reset_val, CP_MEC_RS64_CNTL,
+                                                 MEC_PIPE1_RESET, 1);
+                       clean_val = REG_SET_FIELD(clean_val, CP_MEC_RS64_CNTL,
+                                                 MEC_PIPE1_RESET, 0);
                        break;
                case 2:
-                       reset_pipe = REG_SET_FIELD(reset_pipe, CP_MEC_RS64_CNTL,
-                                                  MEC_PIPE2_RESET, 1);
-                       clean_pipe = REG_SET_FIELD(clean_pipe, CP_MEC_RS64_CNTL,
-                                                  MEC_PIPE2_RESET, 0);
+                       reset_val = REG_SET_FIELD(reset_val, CP_MEC_RS64_CNTL,
+                                                 MEC_PIPE2_RESET, 1);
+                       clean_val = REG_SET_FIELD(clean_val, CP_MEC_RS64_CNTL,
+                                                 MEC_PIPE2_RESET, 0);
                        break;
                case 3:
-                       reset_pipe = REG_SET_FIELD(reset_pipe, CP_MEC_RS64_CNTL,
-                                                  MEC_PIPE3_RESET, 1);
-                       clean_pipe = REG_SET_FIELD(clean_pipe, CP_MEC_RS64_CNTL,
-                                                  MEC_PIPE3_RESET, 0);
+                       reset_val = REG_SET_FIELD(reset_val, CP_MEC_RS64_CNTL,
+                                                 MEC_PIPE3_RESET, 1);
+                       clean_val = REG_SET_FIELD(clean_val, CP_MEC_RS64_CNTL,
+                                                 MEC_PIPE3_RESET, 0);
                        break;
                default:
                        break;
                }
-               WREG32_SOC15(GC, 0, regCP_MEC_RS64_CNTL, reset_pipe);
-               WREG32_SOC15(GC, 0, regCP_MEC_RS64_CNTL, clean_pipe);
+               WREG32_SOC15(GC, 0, regCP_MEC_RS64_CNTL, reset_val);
+               gfx_v11_0_clear_hqds_on_mec_pipe(adev, me, pipe);
+               WREG32_SOC15(GC, 0, regCP_MEC_RS64_CNTL, clean_val);
                r = (RREG32_SOC15(GC, 0, regCP_MEC_RS64_INSTR_PNTR) << 2) -
                                        RS64_FW_UC_START_ADDR_LO;
        } else {
-               if (ring->me == 1) {
-                       switch (ring->pipe) {
+               reset_val = RREG32_SOC15(GC, 0, regCP_MEC_CNTL);
+               clean_val = reset_val;
+
+               if (me == 1) {
+                       switch (pipe) {
                        case 0:
-                               reset_pipe = REG_SET_FIELD(reset_pipe, CP_MEC_CNTL,
-                                                          MEC_ME1_PIPE0_RESET, 1);
-                               clean_pipe = REG_SET_FIELD(clean_pipe, CP_MEC_CNTL,
-                                                          MEC_ME1_PIPE0_RESET, 0);
+                               reset_val = REG_SET_FIELD(reset_val, CP_MEC_CNTL,
+                                                         MEC_ME1_PIPE0_RESET, 1);
+                               clean_val = REG_SET_FIELD(clean_val, CP_MEC_CNTL,
+                                                         MEC_ME1_PIPE0_RESET, 0);
                                break;
                        case 1:
-                               reset_pipe = REG_SET_FIELD(reset_pipe, CP_MEC_CNTL,
-                                                          MEC_ME1_PIPE1_RESET, 1);
-                               clean_pipe = REG_SET_FIELD(clean_pipe, CP_MEC_CNTL,
-                                                          MEC_ME1_PIPE1_RESET, 0);
+                               reset_val = REG_SET_FIELD(reset_val, CP_MEC_CNTL,
+                                                         MEC_ME1_PIPE1_RESET, 1);
+                               clean_val = REG_SET_FIELD(clean_val, CP_MEC_CNTL,
+                                                         MEC_ME1_PIPE1_RESET, 0);
                                break;
                        case 2:
-                               reset_pipe = REG_SET_FIELD(reset_pipe, CP_MEC_CNTL,
-                                                          MEC_ME1_PIPE2_RESET, 1);
-                               clean_pipe = REG_SET_FIELD(clean_pipe, CP_MEC_CNTL,
-                                                          MEC_ME1_PIPE2_RESET, 0);
+                               reset_val = REG_SET_FIELD(reset_val, CP_MEC_CNTL,
+                                                         MEC_ME1_PIPE2_RESET, 1);
+                               clean_val = REG_SET_FIELD(clean_val, CP_MEC_CNTL,
+                                                         MEC_ME1_PIPE2_RESET, 0);
                                break;
                        case 3:
-                               reset_pipe = REG_SET_FIELD(reset_pipe, CP_MEC_CNTL,
-                                                          MEC_ME1_PIPE3_RESET, 1);
-                               clean_pipe = REG_SET_FIELD(clean_pipe, CP_MEC_CNTL,
-                                                          MEC_ME1_PIPE3_RESET, 0);
+                               reset_val = REG_SET_FIELD(reset_val, CP_MEC_CNTL,
+                                                         MEC_ME1_PIPE3_RESET, 1);
+                               clean_val = REG_SET_FIELD(clean_val, CP_MEC_CNTL,
+                                                         MEC_ME1_PIPE3_RESET, 0);
                                break;
                        default:
                                break;
                        }
                        /* mec1 fw pc: CP_MEC1_INSTR_PNTR */
                } else {
-                       switch (ring->pipe) {
+                       switch (pipe) {
                        case 0:
-                               reset_pipe = REG_SET_FIELD(reset_pipe, CP_MEC_CNTL,
-                                                          MEC_ME2_PIPE0_RESET, 1);
-                               clean_pipe = REG_SET_FIELD(clean_pipe, CP_MEC_CNTL,
-                                                          MEC_ME2_PIPE0_RESET, 0);
+                               reset_val = REG_SET_FIELD(reset_val, CP_MEC_CNTL,
+                                                         MEC_ME2_PIPE0_RESET, 1);
+                               clean_val = REG_SET_FIELD(clean_val, CP_MEC_CNTL,
+                                                         MEC_ME2_PIPE0_RESET, 0);
                                break;
                        case 1:
-                               reset_pipe = REG_SET_FIELD(reset_pipe, CP_MEC_CNTL,
-                                                          MEC_ME2_PIPE1_RESET, 1);
-                               clean_pipe = REG_SET_FIELD(clean_pipe, CP_MEC_CNTL,
-                                                          MEC_ME2_PIPE1_RESET, 0);
+                               reset_val = REG_SET_FIELD(reset_val, CP_MEC_CNTL,
+                                                         MEC_ME2_PIPE1_RESET, 1);
+                               clean_val = REG_SET_FIELD(clean_val, CP_MEC_CNTL,
+                                                         MEC_ME2_PIPE1_RESET, 0);
                                break;
                        case 2:
-                               reset_pipe = REG_SET_FIELD(reset_pipe, CP_MEC_CNTL,
-                                                          MEC_ME2_PIPE2_RESET, 1);
-                               clean_pipe = REG_SET_FIELD(clean_pipe, CP_MEC_CNTL,
-                                                          MEC_ME2_PIPE2_RESET, 0);
+                               reset_val = REG_SET_FIELD(reset_val, CP_MEC_CNTL,
+                                                         MEC_ME2_PIPE2_RESET, 1);
+                               clean_val = REG_SET_FIELD(clean_val, CP_MEC_CNTL,
+                                                         MEC_ME2_PIPE2_RESET, 0);
                                break;
                        case 3:
-                               reset_pipe = REG_SET_FIELD(reset_pipe, CP_MEC_CNTL,
-                                                          MEC_ME2_PIPE3_RESET, 1);
-                               clean_pipe = REG_SET_FIELD(clean_pipe, CP_MEC_CNTL,
-                                                          MEC_ME2_PIPE3_RESET, 0);
+                               reset_val = REG_SET_FIELD(reset_val, CP_MEC_CNTL,
+                                                         MEC_ME2_PIPE3_RESET, 1);
+                               clean_val = REG_SET_FIELD(clean_val, CP_MEC_CNTL,
+                                                         MEC_ME2_PIPE3_RESET, 0);
                                break;
                        default:
                                break;
                        }
                        /* mec2 fw pc: CP:CP_MEC2_INSTR_PNTR */
                }
-               WREG32_SOC15(GC, 0, regCP_MEC_CNTL, reset_pipe);
-               WREG32_SOC15(GC, 0, regCP_MEC_CNTL, clean_pipe);
+               WREG32_SOC15(GC, 0, regCP_MEC_CNTL, reset_val);
+               gfx_v11_0_clear_hqds_on_mec_pipe(adev, me, pipe);
+               WREG32_SOC15(GC, 0, regCP_MEC_CNTL, clean_val);
                r = RREG32(SOC15_REG_OFFSET(GC, 0, regCP_MEC1_INSTR_PNTR));
        }
 
@@ -7035,8 +7057,8 @@ static int gfx_v11_0_reset_compute_pipe(struct amdgpu_ring *ring)
        mutex_unlock(&adev->srbm_mutex);
        gfx_v11_0_unset_safe_mode(adev, 0);
 
-       dev_info(adev->dev, "The ring %s pipe resets to MEC FW start PC: %s\n", ring->name,
-                       r == 0 ? "successfully" : "failed");
+       dev_dbg(adev->dev, "MEC pipe me%u pipe%u queue%u resets to MEC FW start PC: %s\n",
+               me, pipe, queue, r == 0 ? "successfully" : "failed");
        /*FIXME:Sometimes driver can't cache the MEC firmware start PC correctly, so the pipe
         * reset status relies on the compute ring test result.
         */
@@ -7056,7 +7078,7 @@ static int gfx_v11_0_reset_kcq(struct amdgpu_ring *ring,
        r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, use_mmio, 0);
        if (r) {
                dev_warn(adev->dev, "fail(%d) to reset kcq and try pipe reset\n", r);
-               r = gfx_v11_0_reset_compute_pipe(ring);
+               r = gfx_v11_0_reset_compute_pipe(adev, ring->me, ring->pipe, ring->queue);
                if (r)
                        return r;
        }