drm/amdgpu: invalidate mmhub semaphore workaround in gmc9/gmc10

It may lose gpuvm invalidate acknowldege state across power-gating off
cycle. To avoid this issue in gmc9/gmc10 invalidation, add semaphore acquire
before invalidation and semaphore release after invalidation.

After adding semaphore acquire before invalidation, the semaphore
register become read-only if another process try to acquire semaphore.
Then it will not be able to release this semaphore. Then it may cause
deadlock problem. If this deadlock problem happens, it needs a semaphore
firmware fix.

Signed-off-by: changzhu <Changfeng.Zhu@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 27f68d32bfec10fa8cf12f14092f381134a4a89f..321f8a997be8e1ce44ea77ee4228b5237277c9ad 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -235,6 +235,29 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
        const unsigned eng = 17;
        unsigned int i;
 
+       spin_lock(&adev->gmc.invalidate_lock);
+       /*
+        * It may lose gpuvm invalidate acknowldege state across power-gating
+        * off cycle, add semaphore acquire before invalidation and semaphore
+        * release after invalidation to avoid entering power gated state
+        * to WA the Issue
+        */
+
+       /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+       if (vmhub == AMDGPU_MMHUB_0 ||
+           vmhub == AMDGPU_MMHUB_1) {
+               for (i = 0; i < adev->usec_timeout; i++) {
+                       /* a read return value of 1 means semaphore acuqire */
+                       tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng);
+                       if (tmp & 0x1)
+                               break;
+                       udelay(1);
+               }
+
+               if (i >= adev->usec_timeout)
+                       DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n");
+       }
+
        WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, tmp);
 
        /*
@@ -254,6 +277,17 @@ static void gmc_v10_0_flush_vm_hub(struct amdgpu_device *adev, uint32_t vmid,
                udelay(1);
        }
 
+       /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+       if (vmhub == AMDGPU_MMHUB_0 ||
+           vmhub == AMDGPU_MMHUB_1)
+               /*
+                * add semaphore release after invalidation,
+                * write with 0 means semaphore release
+                */
+               WREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng, 0);
+
+       spin_unlock(&adev->gmc.invalidate_lock);
+
        if (i < adev->usec_timeout)
                return;
 
@@ -338,6 +372,20 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
        uint32_t req = gmc_v10_0_get_invalidate_req(vmid, 0);
        unsigned eng = ring->vm_inv_eng;
 
+       /*
+        * It may lose gpuvm invalidate acknowldege state across power-gating
+        * off cycle, add semaphore acquire before invalidation and semaphore
+        * release after invalidation to avoid entering power gated state
+        * to WA the Issue
+        */
+
+       /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+       if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+           ring->funcs->vmhub == AMDGPU_MMHUB_1)
+               /* a read return value of 1 means semaphore acuqire */
+               amdgpu_ring_emit_reg_wait(ring,
+                                         hub->vm_inv_eng0_sem + eng, 0x1, 0x1);
+
        amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid),
                              lower_32_bits(pd_addr));
 
@@ -348,6 +396,15 @@ static uint64_t gmc_v10_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
                                            hub->vm_inv_eng0_ack + eng,
                                            req, 1 << vmid);
 
+       /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+       if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+           ring->funcs->vmhub == AMDGPU_MMHUB_1)
+               /*
+                * add semaphore release after invalidation,
+                * write with 0 means semaphore release
+                */
+               amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem + eng, 0);
+
        return pd_addr;
 }
 

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 5f4a6cdf83a775c44cba0b5de03a878f3b5fdb83..365a88ecdec4248cfa70230f12392be0f2202a4e 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -459,6 +459,29 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
        }
 
        spin_lock(&adev->gmc.invalidate_lock);
+
+       /*
+        * It may lose gpuvm invalidate acknowldege state across power-gating
+        * off cycle, add semaphore acquire before invalidation and semaphore
+        * release after invalidation to avoid entering power gated state
+        * to WA the Issue
+        */
+
+       /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+       if (vmhub == AMDGPU_MMHUB_0 ||
+           vmhub == AMDGPU_MMHUB_1) {
+               for (j = 0; j < adev->usec_timeout; j++) {
+                       /* a read return value of 1 means semaphore acuqire */
+                       tmp = RREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng);
+                       if (tmp & 0x1)
+                               break;
+                       udelay(1);
+               }
+
+               if (j >= adev->usec_timeout)
+                       DRM_ERROR("Timeout waiting for sem acquire in VM flush!\n");
+       }
+
        WREG32_NO_KIQ(hub->vm_inv_eng0_req + eng, tmp);
 
        /*
@@ -474,7 +497,18 @@ static void gmc_v9_0_flush_gpu_tlb(struct amdgpu_device *adev, uint32_t vmid,
                        break;
                udelay(1);
        }
+
+       /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+       if (vmhub == AMDGPU_MMHUB_0 ||
+           vmhub == AMDGPU_MMHUB_1)
+               /*
+                * add semaphore release after invalidation,
+                * write with 0 means semaphore release
+                */
+               WREG32_NO_KIQ(hub->vm_inv_eng0_sem + eng, 0);
+
        spin_unlock(&adev->gmc.invalidate_lock);
+
        if (j < adev->usec_timeout)
                return;
 
@@ -489,6 +523,20 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
        uint32_t req = gmc_v9_0_get_invalidate_req(vmid, 0);
        unsigned eng = ring->vm_inv_eng;
 
+       /*
+        * It may lose gpuvm invalidate acknowldege state across power-gating
+        * off cycle, add semaphore acquire before invalidation and semaphore
+        * release after invalidation to avoid entering power gated state
+        * to WA the Issue
+        */
+
+       /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+       if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+           ring->funcs->vmhub == AMDGPU_MMHUB_1)
+               /* a read return value of 1 means semaphore acuqire */
+               amdgpu_ring_emit_reg_wait(ring,
+                                         hub->vm_inv_eng0_sem + eng, 0x1, 0x1);
+
        amdgpu_ring_emit_wreg(ring, hub->ctx0_ptb_addr_lo32 + (2 * vmid),
                              lower_32_bits(pd_addr));
 
@@ -499,6 +547,15 @@ static uint64_t gmc_v9_0_emit_flush_gpu_tlb(struct amdgpu_ring *ring,
                                            hub->vm_inv_eng0_ack + eng,
                                            req, 1 << vmid);
 
+       /* TODO: It needs to continue working on debugging with semaphore for GFXHUB as well. */
+       if (ring->funcs->vmhub == AMDGPU_MMHUB_0 ||
+           ring->funcs->vmhub == AMDGPU_MMHUB_1)
+               /*
+                * add semaphore release after invalidation,
+                * write with 0 means semaphore release
+                */
+               amdgpu_ring_emit_wreg(ring, hub->vm_inv_eng0_sem + eng, 0);
+
        return pd_addr;
 }
 

diff --git a/drivers/gpu/drm/amd/amdgpu/soc15.h b/drivers/gpu/drm/amd/amdgpu/soc15.h
index 344280b869c482ce0fdcb59651cffef305f704cf..d0fb7a67c1a38d59f3d2622947adaf66452dc215 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/soc15.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15.h
@@ -28,8 +28,8 @@
 #include "nbio_v7_0.h"
 #include "nbio_v7_4.h"
 
-#define SOC15_FLUSH_GPU_TLB_NUM_WREG           4
-#define SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT       1
+#define SOC15_FLUSH_GPU_TLB_NUM_WREG           6
+#define SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT       3
 
 extern const struct amd_ip_funcs soc15_common_ip_funcs;