[PATCH v1 0/3] drm/msm: Add dependencies for per-instance pagetables

[PATCH v1 0/3] drm/msm: Add dependencies for per-instance pagetables

[Jordan Crouse]

These are a few support changes in advance of per-instance pagetables. These
can be added to msm-next immediately since they don't require anything external
support and they are mostly benign on their own without the more aggressive
changes coming up later.

Jordan Crouse (3):
  drm/msm/adreno: Enable 64 bit mode by default on a5xx and a6xx targets
  drm/msm: Print all 64 bits of the faulting IOMMU address
  drm/msm: Pass the MMU domain index in struct msm_file_private

 drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 14 ++++++++++++++
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 14 ++++++++++++++
 drivers/gpu/drm/msm/msm_drv.c         |  2 ++
 drivers/gpu/drm/msm/msm_drv.h         |  1 +
 drivers/gpu/drm/msm/msm_gem.h         |  1 +
 drivers/gpu/drm/msm/msm_gem_submit.c  | 13 ++++++++-----
 drivers/gpu/drm/msm/msm_gpu.c         |  5 ++---
 drivers/gpu/drm/msm/msm_iommu.c       |  2 +-
 8 files changed, 43 insertions(+), 9 deletions(-)

-- 
2.7.4

[PATCH v1 1/3] drm/msm/adreno: Enable 64 bit mode by default on a5xx and a6xx targets

[Jordan Crouse]

A5XX and newer GPUs can be run in either 32 or 64 bit mode. The GPU
registers and the microcode use 64 bit virtual addressing in either
case but the upper 32 bits are ignored if the GPU is in 32 bit mode.
There is no performance disadvantage to remaining in 64 bit mode even
if we are only generating 32 bit addresses so switch over now to prepare
for using addresses above 4G on targets that support them.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
---

 drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 14 ++++++++++++++
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 14 ++++++++++++++
 2 files changed, 28 insertions(+)

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index e5fcefa..43a2b4a 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -642,6 +642,20 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 		REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000);
 	gpu_write(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000);
 
+	/* Put the GPU into 64 bit by default */
+	gpu_write(gpu, REG_A5XX_CP_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_VSC_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_GRAS_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_RB_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_PC_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_HLSQ_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_VFD_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_VPC_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_UCHE_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_SP_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_TPL1_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A5XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL, 0x1);
+
 	ret = adreno_hw_init(gpu);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index ec24508..360c070 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -391,6 +391,20 @@ static int a6xx_hw_init(struct msm_gpu *gpu)
 		REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000);
 	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000);
 
+	/* Turn on 64 bit addressing for all blocks */
+	gpu_write(gpu, REG_A6XX_CP_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_VSC_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_GRAS_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_RB_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_PC_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_HLSQ_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_VFD_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_VPC_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_UCHE_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_SP_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_TPL1_ADDR_MODE_CNTL, 0x1);
+	gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_ADDR_MODE_CNTL, 0x1);
+
 	/* enable hardware clockgating */
 	a6xx_set_hwcg(gpu, true);
 
-- 
2.7.4

[PATCH v1 2/3] drm/msm: Print all 64 bits of the faulting IOMMU address

[Jordan Crouse]

When we move to 64 bit addressing for a5xx and a6xx targets we will start
seeing pagefaults at larger addresses so format them appropriately in the
log message for easier debugging.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
---

 drivers/gpu/drm/msm/msm_iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 12bb54c..1926329 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -30,7 +30,7 @@ static int msm_fault_handler(struct iommu_domain *domain, struct device *dev,
 	struct msm_iommu *iommu = arg;
 	if (iommu->base.handler)
 		return iommu->base.handler(iommu->base.arg, iova, flags);
-	pr_warn_ratelimited("*** fault: iova=%08lx, flags=%d\n", iova, flags);
+	pr_warn_ratelimited("*** fault: iova=%16lx, flags=%d\n", iova, flags);
 	return 0;
 }
 
-- 
2.7.4

Re: [Freedreno] [PATCH v1 2/3] drm/msm: Print all 64 bits of the faulting IOMMU address

[Kristian Høgsberg]

On Tue, May 7, 2019 at 11:02 AM Jordan Crouse <jcrouse@codeaurora.org> wrote:
>
> When we move to 64 bit addressing for a5xx and a6xx targets we will start
> seeing pagefaults at larger addresses so format them appropriately in the
> log message for easier debugging.

Yes please, this has confused me more than once.

Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>

> Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
> ---
>
>  drivers/gpu/drm/msm/msm_iommu.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
> index 12bb54c..1926329 100644
> --- a/drivers/gpu/drm/msm/msm_iommu.c
> +++ b/drivers/gpu/drm/msm/msm_iommu.c
> @@ -30,7 +30,7 @@ static int msm_fault_handler(struct iommu_domain *domain, struct device *dev,
>         struct msm_iommu *iommu = arg;
>         if (iommu->base.handler)
>                 return iommu->base.handler(iommu->base.arg, iova, flags);
> -       pr_warn_ratelimited("*** fault: iova=%08lx, flags=%d\n", iova, flags);
> +       pr_warn_ratelimited("*** fault: iova=%16lx, flags=%d\n", iova, flags);
>         return 0;
>  }
>
> --
> 2.7.4
>
> _______________________________________________
> Freedreno mailing list
> Freedreno@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/freedreno

[PATCH v1 3/3] drm/msm: Pass the MMU domain index in struct msm_file_private

[Jordan Crouse]

Pass the index of the MMU domain in struct msm_file_private instead
of assuming gpu->id throughout the submit path. This clears the way
to change ctx->aspace to a per-instance pagetable.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
---

 drivers/gpu/drm/msm/msm_drv.c        |  2 ++
 drivers/gpu/drm/msm/msm_drv.h        |  1 +
 drivers/gpu/drm/msm/msm_gem.h        |  1 +
 drivers/gpu/drm/msm/msm_gem_submit.c | 13 ++++++++-----
 drivers/gpu/drm/msm/msm_gpu.c        |  5 ++---
 5 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 154dab0..cac101f 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -611,6 +611,7 @@ static void load_gpu(struct drm_device *dev)
 
 static int context_init(struct drm_device *dev, struct drm_file *file)
 {
+	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_file_private *ctx;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -619,6 +620,7 @@ static int context_init(struct drm_device *dev, struct drm_file *file)
 
 	msm_submitqueue_init(dev, ctx);
 
+	ctx->aspace = priv->gpu->aspace;
 	file->driver_priv = ctx;
 
 	return 0;
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index bbf739d..07ae89f 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -68,6 +68,7 @@ struct msm_file_private {
 	rwlock_t queuelock;
 	struct list_head submitqueues;
 	int queueid;
+	struct msm_gem_address_space *aspace;
 };
 
 enum msm_mdp_plane_property {
diff --git a/drivers/gpu/drm/msm/msm_gem.h b/drivers/gpu/drm/msm/msm_gem.h
index c5ac781..1c75310 100644
--- a/drivers/gpu/drm/msm/msm_gem.h
+++ b/drivers/gpu/drm/msm/msm_gem.h
@@ -145,6 +145,7 @@ void msm_gem_free_work(struct work_struct *work);
 struct msm_gem_submit {
 	struct drm_device *dev;
 	struct msm_gpu *gpu;
+	struct msm_gem_address_space *aspace;
 	struct list_head node;   /* node in ring submit list */
 	struct list_head bo_list;
 	struct ww_acquire_ctx ticket;
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 648e0c1..e19e083 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -32,8 +32,9 @@
 #define BO_PINNED   0x2000
 
 static struct msm_gem_submit *submit_create(struct drm_device *dev,
-		struct msm_gpu *gpu, struct msm_gpu_submitqueue *queue,
-		uint32_t nr_bos, uint32_t nr_cmds)
+		struct msm_gpu *gpu, struct msm_gem_address_space *aspace,
+		struct msm_gpu_submitqueue *queue, uint32_t nr_bos,
+		uint32_t nr_cmds)
 {
 	struct msm_gem_submit *submit;
 	uint64_t sz = sizeof(*submit) + ((u64)nr_bos * sizeof(submit->bos[0])) +
@@ -47,6 +48,7 @@ static struct msm_gem_submit *submit_create(struct drm_device *dev,
 		return NULL;
 
 	submit->dev = dev;
+	submit->aspace = aspace;
 	submit->gpu = gpu;
 	submit->fence = NULL;
 	submit->cmd = (void *)&submit->bos[nr_bos];
@@ -160,7 +162,7 @@ static void submit_unlock_unpin_bo(struct msm_gem_submit *submit,
 	struct msm_gem_object *msm_obj = submit->bos[i].obj;
 
 	if (submit->bos[i].flags & BO_PINNED)
-		msm_gem_unpin_iova(&msm_obj->base, submit->gpu->aspace);
+		msm_gem_unpin_iova(&msm_obj->base, submit->aspace);
 
 	if (submit->bos[i].flags & BO_LOCKED)
 		ww_mutex_unlock(&msm_obj->resv->lock);
@@ -264,7 +266,7 @@ static int submit_pin_objects(struct msm_gem_submit *submit)
 
 		/* if locking succeeded, pin bo: */
 		ret = msm_gem_get_and_pin_iova(&msm_obj->base,
-				submit->gpu->aspace, &iova);
+				submit->aspace, &iova);
 
 		if (ret)
 			break;
@@ -477,7 +479,8 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		}
 	}
 
-	submit = submit_create(dev, gpu, queue, args->nr_bos, args->nr_cmds);
+	submit = submit_create(dev, gpu, ctx->aspace, queue, args->nr_bos,
+		args->nr_cmds);
 	if (!submit) {
 		ret = -ENOMEM;
 		goto out_unlock;
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index bf4ee27..0a4c77f 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -684,7 +684,7 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
 		struct msm_gem_object *msm_obj = submit->bos[i].obj;
 		/* move to inactive: */
 		msm_gem_move_to_inactive(&msm_obj->base);
-		msm_gem_unpin_iova(&msm_obj->base, gpu->aspace);
+		msm_gem_unpin_iova(&msm_obj->base, submit->aspace);
 		drm_gem_object_put(&msm_obj->base);
 	}
 
@@ -768,8 +768,7 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 
 		/* submit takes a reference to the bo and iova until retired: */
 		drm_gem_object_get(&msm_obj->base);
-		msm_gem_get_and_pin_iova(&msm_obj->base,
-				submit->gpu->aspace, &iova);
+		msm_gem_get_and_pin_iova(&msm_obj->base, submit->aspace, &iova);
 
 		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
 			msm_gem_move_to_active(&msm_obj->base, gpu, true, submit->fence);
-- 
2.7.4