drm/amdgpu: protect ring overrun

Wait for the oldest sequence on the ring
to be signaled in order to make sure there
will be no command overrun.

v2: fix coding stype and remove abs operation
v3: remove the initialization of variable r

Signed-off-by: Yintian Tao <yttao@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 7531527..d878fe7 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -192,14 +192,22 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
  * Used For polling fence.
  * Returns 0 on success, -ENOMEM on failure.
  */
-int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s)
+int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s,
+                             uint32_t timeout)
 {
        uint32_t seq;
+       signed long r;
 
        if (!s)
                return -EINVAL;
 
        seq = ++ring->fence_drv.sync_seq;
+       r = amdgpu_fence_wait_polling(ring,
+                                     seq - ring->fence_drv.num_fences_mask,
+                                     timeout);
+       if (r < 1)
+               return -ETIMEDOUT;
+
        amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
                               seq, 0);
 

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index a721b0e..0103acc 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -675,13 +675,15 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
 
        spin_lock_irqsave(&kiq->ring_lock, flags);
        if (amdgpu_device_wb_get(adev, &reg_val_offs)) {
-               spin_unlock_irqrestore(&kiq->ring_lock, flags);
                pr_err("critical bug! too many kiq readers\n");
-               goto failed_kiq_read;
+               goto failed_unlock;
        }
        amdgpu_ring_alloc(ring, 32);
        amdgpu_ring_emit_rreg(ring, reg, reg_val_offs);
-       amdgpu_fence_emit_polling(ring, &seq);
+       r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
+       if (r)
+               goto failed_undo;
+
        amdgpu_ring_commit(ring);
        spin_unlock_irqrestore(&kiq->ring_lock, flags);
 
@@ -712,7 +714,13 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg)
        amdgpu_device_wb_free(adev, reg_val_offs);
        return value;
 
+failed_undo:
+       amdgpu_ring_undo(ring);
+failed_unlock:
+       spin_unlock_irqrestore(&kiq->ring_lock, flags);
 failed_kiq_read:
+       if (reg_val_offs)
+               amdgpu_device_wb_free(adev, reg_val_offs);
        pr_err("failed to read reg:%x\n", reg);
        return ~0;
 }
@@ -730,7 +738,10 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
        spin_lock_irqsave(&kiq->ring_lock, flags);
        amdgpu_ring_alloc(ring, 32);
        amdgpu_ring_emit_wreg(ring, reg, v);
-       amdgpu_fence_emit_polling(ring, &seq);
+       r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
+       if (r)
+               goto failed_undo;
+
        amdgpu_ring_commit(ring);
        spin_unlock_irqrestore(&kiq->ring_lock, flags);
 
@@ -759,6 +770,9 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
 
        return;
 
+failed_undo:
+       amdgpu_ring_undo(ring);
+       spin_unlock_irqrestore(&kiq->ring_lock, flags);
 failed_kiq_write:
        pr_err("failed to write reg:%x\n", reg);
 }

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index e1d894f..7d39064 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -105,7 +105,8 @@ void amdgpu_fence_driver_suspend(struct amdgpu_device *adev);
 void amdgpu_fence_driver_resume(struct amdgpu_device *adev);
 int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **fence,
                      unsigned flags);
-int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s);
+int amdgpu_fence_emit_polling(struct amdgpu_ring *ring, uint32_t *s,
+                             uint32_t timeout);
 bool amdgpu_fence_process(struct amdgpu_ring *ring);
 int amdgpu_fence_wait_empty(struct amdgpu_ring *ring);
 signed long amdgpu_fence_wait_polling(struct amdgpu_ring *ring,

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index 8c10084..cbbb8d0 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -60,7 +60,10 @@ void amdgpu_virt_kiq_reg_write_reg_wait(struct amdgpu_device *adev,
        amdgpu_ring_alloc(ring, 32);
        amdgpu_ring_emit_reg_write_reg_wait(ring, reg0, reg1,
                                            ref, mask);
-       amdgpu_fence_emit_polling(ring, &seq);
+       r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
+       if (r)
+               goto failed_undo;
+
        amdgpu_ring_commit(ring);
        spin_unlock_irqrestore(&kiq->ring_lock, flags);
 
@@ -82,6 +85,9 @@ void amdgpu_virt_kiq_reg_write_reg_wait(struct amdgpu_device *adev,
 
        return;
 
+failed_undo:
+       amdgpu_ring_undo(ring);
+       spin_unlock_irqrestore(&kiq->ring_lock, flags);
 failed_kiq:
        pr_err("failed to write reg %x wait reg %x\n", reg0, reg1);
 }

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 496205a..6c5ba34 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -4054,9 +4054,8 @@ static uint64_t gfx_v9_0_kiq_read_clock(struct amdgpu_device *adev)
 
        spin_lock_irqsave(&kiq->ring_lock, flags);
        if (amdgpu_device_wb_get(adev, &reg_val_offs)) {
-               spin_unlock_irqrestore(&kiq->ring_lock, flags);
                pr_err("critical bug! too many kiq readers\n");
-               goto failed_kiq_read;
+               goto failed_unlock;
        }
        amdgpu_ring_alloc(ring, 32);
        amdgpu_ring_write(ring, PACKET3(PACKET3_COPY_DATA, 4));
@@ -4070,7 +4069,10 @@ static uint64_t gfx_v9_0_kiq_read_clock(struct amdgpu_device *adev)
                                reg_val_offs * 4));
        amdgpu_ring_write(ring, upper_32_bits(adev->wb.gpu_addr +
                                reg_val_offs * 4));
-       amdgpu_fence_emit_polling(ring, &seq);
+       r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
+       if (r)
+               goto failed_undo;
+
        amdgpu_ring_commit(ring);
        spin_unlock_irqrestore(&kiq->ring_lock, flags);
 
@@ -4102,7 +4104,13 @@ static uint64_t gfx_v9_0_kiq_read_clock(struct amdgpu_device *adev)
        amdgpu_device_wb_free(adev, reg_val_offs);
        return value;
 
+failed_undo:
+       amdgpu_ring_undo(ring);
+failed_unlock:
+       spin_unlock_irqrestore(&kiq->ring_lock, flags);
 failed_kiq_read:
+       if (reg_val_offs)
+               amdgpu_device_wb_free(adev, reg_val_offs);
        pr_err("failed to read gpu clock\n");
        return ~0;
 }

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 94a6096..cd67aad 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -426,7 +426,13 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
                amdgpu_ring_alloc(ring, kiq->pmf->invalidate_tlbs_size + 8);
                kiq->pmf->kiq_invalidate_tlbs(ring,
                                        pasid, flush_type, all_hub);
-               amdgpu_fence_emit_polling(ring, &seq);
+               r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
+               if (r) {
+                       amdgpu_ring_undo(ring);
+                       spin_unlock(&kiq->ring_lock);
+                       return -ETIME;
+               }
+
                amdgpu_ring_commit(ring);
                spin_unlock(&adev->gfx.kiq.ring_lock);
                r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index fecdbc4..0a60263 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -621,7 +621,13 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
                                                      pasid, 2, all_hub);
                kiq->pmf->kiq_invalidate_tlbs(ring,
                                        pasid, flush_type, all_hub);
-               amdgpu_fence_emit_polling(ring, &seq);
+               r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT);
+               if (r) {
+                       amdgpu_ring_undo(ring);
+                       spin_unlock(&kiq->ring_lock);
+                       return -ETIME;
+               }
+
                amdgpu_ring_commit(ring);
                spin_unlock(&adev->gfx.kiq.ring_lock);
                r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);