[PATCH 2/2] drm/amdgpu:impl virt_gart_flush_tlbs

[Monk Liu]

a new gart flush tlb function implemented for SRIOV,
and invoke it during RUNTIME for gart flush TLBs

this could avoid the issue that gart flush (via CPU MMIO)
being interrupted by word switch which lead to DMAR error
on Host/IOMMU side, with this function the gart flush
tlbs always run on KIQ with single PM4 package so it won't
get interrupted before the flushing finished.

Change-Id: I0849658d7945c3874b3cc0d9369a50e1aedb8312
Signed-off-by: Monk Liu <Monk.Liu at amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c | 27 +++++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h |  1 +
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c    |  3 +++
 3 files changed, 31 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
index e7dfb7b..7a6ef64 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
@@ -172,6 +172,33 @@ void amdgpu_virt_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v)
 		DRM_ERROR("wait for kiq fence error: %ld\n", r);
 }
 
+int amdgpu_virt_gart_flush_tlbs(struct amdgpu_device *adev)
+{
+	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
+	struct amdgpu_ring *ring = &kiq->ring;
+	unsigned long flags;
+	signed long r;
+	uint32_t seq;
+
+	if(!ring->funcs->emit_invalidate_tlbs)
+		return -ENOENT;
+
+	spin_lock_irqsave(&kiq->ring_lock, flags);
+	amdgpu_ring_alloc(ring, 16);
+	amdgpu_ring_emit_invalidate_tlbs(ring);
+	amdgpu_fence_emit_polling(ring, &seq);
+	amdgpu_ring_commit(ring);
+	spin_unlock_irqrestore(&kiq->ring_lock, flags);
+
+	r = amdgpu_fence_wait_polling(ring, seq, MAX_KIQ_REG_WAIT);
+	if (r < 1) {
+		DRM_ERROR("wait for kiq invalidate tlbs error: %ld\n", r);
+		return -ETIME;
+	}
+
+	return 0;
+}
+
 /**
  * amdgpu_virt_request_full_gpu() - request full gpu access
  * @amdgpu:	amdgpu device.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
index 6a83425..935fed3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
@@ -297,5 +297,6 @@ int amdgpu_virt_fw_reserve_get_checksum(void *obj, unsigned long obj_size,
 					unsigned int key,
 					unsigned int chksum);
 void amdgpu_virt_init_data_exchange(struct amdgpu_device *adev);
+int amdgpu_virt_gart_flush_tlbs(struct amdgpu_device *adev);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 1b5dfcc..a195039 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -332,6 +332,9 @@ static void gmc_v9_0_gart_flush_gpu_tlb(struct amdgpu_device *adev,
 	/* flush hdp cache */
 	adev->nbio_funcs->hdp_flush(adev);
 
+	if (amdgpu_sriov_runtime(adev) && !amdgpu_virt_gart_flush_tlbs(adev))
+		return;
+
 	spin_lock(&adev->mc.invalidate_lock);
 
 	for (i = 0; i < AMDGPU_MAX_VMHUBS; ++i) {
-- 
2.7.4