kernel / kernel-source

Clone
Source Code
GIT

Files

  1.   7df24046a1510e64670d278fbacd785c50635908
  2.   patches.suse
  3.   0672-drm-amdgpu-protect-ring-overrun.patch
Blob Blame History Raw 
From 8391f2cf393a852865f75a3f468cb9c9e6da7090 Mon Sep 17 00:00:00 2001
From: Yintian Tao <yttao@amd.com>
Date: Thu, 23 Apr 2020 12:05:54 +0800
Subject: drm/amdgpu: protect ring overrun
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
Git-commit: 04e4e2e9558326316cf3e32d46cca83cc3861ef0
Patch-mainline: v5.8-rc1
References: jsc#SLE-12680, jsc#SLE-12880, jsc#SLE-12882, jsc#SLE-12883, jsc#SLE-13496, jsc#SLE-15322

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>
Signed-off-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 10 +++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c   | 22 ++++++++++++++++++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h  |  3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c  |  8 +++++++-
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c     | 14 +++++++++++---
 drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c    |  8 +++++++-
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c     |  8 +++++++-
 7 files changed, 61 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 7531527067df..d878fe7fee51 100644
--- 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 a721b0e0ff69..0103acc57474 100644
--- 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 e1d894f0d654..7d39064f9361 100644
--- 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 8c10084f44ef..cbbb8d02535a 100644
--- 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 6ced055a910b..462fb6c15f12 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -4056,9 +4056,8 @@ 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));
@@ -4072,7 +4071,10 @@ 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);
 
@@ -4104,7 +4106,13 @@ 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 94a6096a81f4..cd67aad3ae75 100644
--- 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 fecdbc471983..0a6026308343 100644
--- 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);
-- 
2.28.0
Powered by Pagure 5.13.3
Documentation • About this Instance • SSH Hostkey/Fingerprint
© Red Hat, Inc. and others.