[PATCH v10 0/4] io-pgtable-arm + drm/msm: Extend iova fault debugging

[PATCH v10 0/4] io-pgtable-arm + drm/msm: Extend iova fault debugging

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

This series extends io-pgtable-arm with a method to retrieve the page
table entries traversed in the process of address translation, and then
beefs up drm/msm gpu devcore dump to include this (and additional info)
in the devcore dump.

This is a respin of https://patchwork.freedesktop.org/series/94968/
(minus a patch that was already merged)

v2:  Fix an armv7/32b build error in the last patch
v3:  Incorperate Will Deacon's suggestion to make the interface
     callback based.
v4:  Actually wire up the callback
v5:  Drop the callback approach
v6:  Make walk-data struct pgtable specific and rename
     io_pgtable_walk_data to arm_lpae_io_pgtable_walk_data
v7:  Re-use the pgtable walker added for arm_lpae_read_and_clear_dirty()
v8:  Pass pte pointer to callback so it can modify the actual pte
v9:  Fix selftests_running case
v10: Call visit cb for all nodes traversed, leave the decision about
     whether to care about non-leaf nodes to the callback

Rob Clark (4):
  iommu/io-pgtable-arm: Make pgtable walker more generic
  iommu/io-pgtable-arm: Re-use the pgtable walk for iova_to_phys
  iommu/io-pgtable-arm: Add way to debug pgtable walk
  drm/msm: Extend gpu devcore dumps with pgtbl info

 drivers/gpu/drm/msm/adreno/adreno_gpu.c |  10 ++
 drivers/gpu/drm/msm/msm_gpu.c           |   9 ++
 drivers/gpu/drm/msm/msm_gpu.h           |   8 ++
 drivers/gpu/drm/msm/msm_iommu.c         |  22 ++++
 drivers/gpu/drm/msm/msm_mmu.h           |   3 +-
 drivers/iommu/io-pgtable-arm.c          | 156 +++++++++++++++---------
 include/linux/io-pgtable.h              |  15 +++
 7 files changed, 166 insertions(+), 57 deletions(-)

-- 
2.47.0

[PATCH v10 1/4] iommu/io-pgtable-arm: Make pgtable walker more generic

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

We can re-use this basic pgtable walk logic in a few places.

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/iommu/io-pgtable-arm.c | 67 ++++++++++++++++++++++------------
 1 file changed, 43 insertions(+), 24 deletions(-)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 0e67f1721a3d..7e9c0f8ae138 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -749,33 +749,33 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
 }
 
 struct io_pgtable_walk_data {
-	struct iommu_dirty_bitmap	*dirty;
+	struct io_pgtable		*iop;
+	void				*data;
+	int (*visit)(struct io_pgtable_walk_data *walk_data, int lvl,
+		     arm_lpae_iopte *ptep, size_t size);
 	unsigned long			flags;
 	u64				addr;
 	const u64			end;
 };
 
-static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data,
-				       struct io_pgtable_walk_data *walk_data,
-				       arm_lpae_iopte *ptep,
-				       int lvl);
+static int __arm_lpae_iopte_walk(struct arm_lpae_io_pgtable *data,
+				 struct io_pgtable_walk_data *walk_data,
+				 arm_lpae_iopte *ptep,
+				 int lvl);
 
-static int io_pgtable_visit_dirty(struct arm_lpae_io_pgtable *data,
-				  struct io_pgtable_walk_data *walk_data,
-				  arm_lpae_iopte *ptep, int lvl)
+static int io_pgtable_visit(struct arm_lpae_io_pgtable *data,
+			    struct io_pgtable_walk_data *walk_data,
+			    arm_lpae_iopte *ptep, int lvl)
 {
 	struct io_pgtable *iop = &data->iop;
 	arm_lpae_iopte pte = READ_ONCE(*ptep);
 
-	if (iopte_leaf(pte, lvl, iop->fmt)) {
-		size_t size = ARM_LPAE_BLOCK_SIZE(lvl, data);
+	size_t size = ARM_LPAE_BLOCK_SIZE(lvl, data);
+	int ret = walk_data->visit(walk_data, lvl, ptep, size);
+	if (ret)
+		return ret;
 
-		if (iopte_writeable_dirty(pte)) {
-			iommu_dirty_bitmap_record(walk_data->dirty,
-						  walk_data->addr, size);
-			if (!(walk_data->flags & IOMMU_DIRTY_NO_CLEAR))
-				iopte_set_writeable_clean(ptep);
-		}
+	if (iopte_leaf(pte, lvl, iop->fmt)) {
 		walk_data->addr += size;
 		return 0;
 	}
@@ -784,13 +784,13 @@ static int io_pgtable_visit_dirty(struct arm_lpae_io_pgtable *data,
 		return -EINVAL;
 
 	ptep = iopte_deref(pte, data);
-	return __arm_lpae_iopte_walk_dirty(data, walk_data, ptep, lvl + 1);
+	return __arm_lpae_iopte_walk(data, walk_data, ptep, lvl + 1);
 }
 
-static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data,
-				       struct io_pgtable_walk_data *walk_data,
-				       arm_lpae_iopte *ptep,
-				       int lvl)
+static int __arm_lpae_iopte_walk(struct arm_lpae_io_pgtable *data,
+				 struct io_pgtable_walk_data *walk_data,
+				 arm_lpae_iopte *ptep,
+				 int lvl)
 {
 	u32 idx;
 	int max_entries, ret;
@@ -805,7 +805,7 @@ static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data,
 
 	for (idx = ARM_LPAE_LVL_IDX(walk_data->addr, lvl, data);
 	     (idx < max_entries) && (walk_data->addr < walk_data->end); ++idx) {
-		ret = io_pgtable_visit_dirty(data, walk_data, ptep + idx, lvl);
+		ret = io_pgtable_visit(data, walk_data, ptep + idx, lvl);
 		if (ret)
 			return ret;
 	}
@@ -813,6 +813,23 @@ static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data,
 	return 0;
 }
 
+static int visit_dirty(struct io_pgtable_walk_data *walk_data, int lvl,
+		       arm_lpae_iopte *ptep, size_t size)
+{
+	struct iommu_dirty_bitmap *dirty = walk_data->data;
+
+	if (!iopte_leaf(*ptep, lvl, walk_data->iop->fmt))
+		return 0;
+
+	if (iopte_writeable_dirty(*ptep)) {
+		iommu_dirty_bitmap_record(dirty, walk_data->addr, size);
+		if (!(walk_data->flags & IOMMU_DIRTY_NO_CLEAR))
+			iopte_set_writeable_clean(ptep);
+	}
+
+	return 0;
+}
+
 static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops,
 					 unsigned long iova, size_t size,
 					 unsigned long flags,
@@ -821,7 +838,9 @@ static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops,
 	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
 	struct io_pgtable_cfg *cfg = &data->iop.cfg;
 	struct io_pgtable_walk_data walk_data = {
-		.dirty = dirty,
+		.iop = &data->iop,
+		.data = dirty,
+		.visit = visit_dirty,
 		.flags = flags,
 		.addr = iova,
 		.end = iova + size,
@@ -836,7 +855,7 @@ static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops,
 	if (data->iop.fmt != ARM_64_LPAE_S1)
 		return -EINVAL;
 
-	return __arm_lpae_iopte_walk_dirty(data, &walk_data, ptep, lvl);
+	return __arm_lpae_iopte_walk(data, &walk_data, ptep, lvl);
 }
 
 static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg)
-- 
2.47.0

Re: [PATCH v10 1/4] iommu/io-pgtable-arm: Make pgtable walker more generic

[Mostafa Saleh]

Hi Rob,

On Mon, Oct 28, 2024 at 02:31:37PM -0700, Rob Clark wrote:
> From: Rob Clark <robdclark@chromium.org>
> 
> We can re-use this basic pgtable walk logic in a few places.
> 
> Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Mostafa Saleh <smostafa@google.com>

> ---
>  drivers/iommu/io-pgtable-arm.c | 67 ++++++++++++++++++++++------------
>  1 file changed, 43 insertions(+), 24 deletions(-)
> 
> diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
> index 0e67f1721a3d..7e9c0f8ae138 100644
> --- a/drivers/iommu/io-pgtable-arm.c
> +++ b/drivers/iommu/io-pgtable-arm.c
> @@ -749,33 +749,33 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
>  }
>  
>  struct io_pgtable_walk_data {
> -	struct iommu_dirty_bitmap	*dirty;
> +	struct io_pgtable		*iop;
> +	void				*data;
> +	int (*visit)(struct io_pgtable_walk_data *walk_data, int lvl,
> +		     arm_lpae_iopte *ptep, size_t size);
>  	unsigned long			flags;
>  	u64				addr;
>  	const u64			end;
>  };
>  
> -static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data,
> -				       struct io_pgtable_walk_data *walk_data,
> -				       arm_lpae_iopte *ptep,
> -				       int lvl);
> +static int __arm_lpae_iopte_walk(struct arm_lpae_io_pgtable *data,
> +				 struct io_pgtable_walk_data *walk_data,
> +				 arm_lpae_iopte *ptep,
> +				 int lvl);
>  
> -static int io_pgtable_visit_dirty(struct arm_lpae_io_pgtable *data,
> -				  struct io_pgtable_walk_data *walk_data,
> -				  arm_lpae_iopte *ptep, int lvl)
> +static int io_pgtable_visit(struct arm_lpae_io_pgtable *data,
> +			    struct io_pgtable_walk_data *walk_data,
> +			    arm_lpae_iopte *ptep, int lvl)
>  {
>  	struct io_pgtable *iop = &data->iop;
>  	arm_lpae_iopte pte = READ_ONCE(*ptep);
>  
> -	if (iopte_leaf(pte, lvl, iop->fmt)) {
> -		size_t size = ARM_LPAE_BLOCK_SIZE(lvl, data);
> +	size_t size = ARM_LPAE_BLOCK_SIZE(lvl, data);
> +	int ret = walk_data->visit(walk_data, lvl, ptep, size);
> +	if (ret)
> +		return ret;
>  
> -		if (iopte_writeable_dirty(pte)) {
> -			iommu_dirty_bitmap_record(walk_data->dirty,
> -						  walk_data->addr, size);
> -			if (!(walk_data->flags & IOMMU_DIRTY_NO_CLEAR))
> -				iopte_set_writeable_clean(ptep);
> -		}
> +	if (iopte_leaf(pte, lvl, iop->fmt)) {
>  		walk_data->addr += size;
>  		return 0;
>  	}
> @@ -784,13 +784,13 @@ static int io_pgtable_visit_dirty(struct arm_lpae_io_pgtable *data,
>  		return -EINVAL;
>  
>  	ptep = iopte_deref(pte, data);
> -	return __arm_lpae_iopte_walk_dirty(data, walk_data, ptep, lvl + 1);
> +	return __arm_lpae_iopte_walk(data, walk_data, ptep, lvl + 1);
>  }
>  
> -static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data,
> -				       struct io_pgtable_walk_data *walk_data,
> -				       arm_lpae_iopte *ptep,
> -				       int lvl)
> +static int __arm_lpae_iopte_walk(struct arm_lpae_io_pgtable *data,
> +				 struct io_pgtable_walk_data *walk_data,
> +				 arm_lpae_iopte *ptep,
> +				 int lvl)
>  {
>  	u32 idx;
>  	int max_entries, ret;
> @@ -805,7 +805,7 @@ static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data,
>  
>  	for (idx = ARM_LPAE_LVL_IDX(walk_data->addr, lvl, data);
>  	     (idx < max_entries) && (walk_data->addr < walk_data->end); ++idx) {
> -		ret = io_pgtable_visit_dirty(data, walk_data, ptep + idx, lvl);
> +		ret = io_pgtable_visit(data, walk_data, ptep + idx, lvl);
>  		if (ret)
>  			return ret;
>  	}
> @@ -813,6 +813,23 @@ static int __arm_lpae_iopte_walk_dirty(struct arm_lpae_io_pgtable *data,
>  	return 0;
>  }
>  
> +static int visit_dirty(struct io_pgtable_walk_data *walk_data, int lvl,
> +		       arm_lpae_iopte *ptep, size_t size)
> +{
> +	struct iommu_dirty_bitmap *dirty = walk_data->data;
> +
> +	if (!iopte_leaf(*ptep, lvl, walk_data->iop->fmt))
> +		return 0;
> +
> +	if (iopte_writeable_dirty(*ptep)) {
> +		iommu_dirty_bitmap_record(dirty, walk_data->addr, size);
> +		if (!(walk_data->flags & IOMMU_DIRTY_NO_CLEAR))
> +			iopte_set_writeable_clean(ptep);
> +	}
> +
> +	return 0;
> +}
> +
>  static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops,
>  					 unsigned long iova, size_t size,
>  					 unsigned long flags,
> @@ -821,7 +838,9 @@ static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops,
>  	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
>  	struct io_pgtable_cfg *cfg = &data->iop.cfg;
>  	struct io_pgtable_walk_data walk_data = {
> -		.dirty = dirty,
> +		.iop = &data->iop,
> +		.data = dirty,
> +		.visit = visit_dirty,
>  		.flags = flags,
>  		.addr = iova,
>  		.end = iova + size,
> @@ -836,7 +855,7 @@ static int arm_lpae_read_and_clear_dirty(struct io_pgtable_ops *ops,
>  	if (data->iop.fmt != ARM_64_LPAE_S1)
>  		return -EINVAL;
>  
> -	return __arm_lpae_iopte_walk_dirty(data, &walk_data, ptep, lvl);
> +	return __arm_lpae_iopte_walk(data, &walk_data, ptep, lvl);
>  }
>  
>  static void arm_lpae_restrict_pgsizes(struct io_pgtable_cfg *cfg)
> -- 
> 2.47.0
> 

[PATCH v10 2/4] iommu/io-pgtable-arm: Re-use the pgtable walk for iova_to_phys

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

Re-use the generic pgtable walk path.

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/iommu/io-pgtable-arm.c | 74 +++++++++++++++++-----------------
 1 file changed, 37 insertions(+), 37 deletions(-)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 7e9c0f8ae138..88b128c77893 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -712,42 +712,6 @@ static size_t arm_lpae_unmap_pages(struct io_pgtable_ops *ops, unsigned long iov
 				data->start_level, ptep);
 }
 
-static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
-					 unsigned long iova)
-{
-	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
-	arm_lpae_iopte pte, *ptep = data->pgd;
-	int lvl = data->start_level;
-
-	do {
-		/* Valid IOPTE pointer? */
-		if (!ptep)
-			return 0;
-
-		/* Grab the IOPTE we're interested in */
-		ptep += ARM_LPAE_LVL_IDX(iova, lvl, data);
-		pte = READ_ONCE(*ptep);
-
-		/* Valid entry? */
-		if (!pte)
-			return 0;
-
-		/* Leaf entry? */
-		if (iopte_leaf(pte, lvl, data->iop.fmt))
-			goto found_translation;
-
-		/* Take it to the next level */
-		ptep = iopte_deref(pte, data);
-	} while (++lvl < ARM_LPAE_MAX_LEVELS);
-
-	/* Ran out of page tables to walk */
-	return 0;
-
-found_translation:
-	iova &= (ARM_LPAE_BLOCK_SIZE(lvl, data) - 1);
-	return iopte_to_paddr(pte, data) | iova;
-}
-
 struct io_pgtable_walk_data {
 	struct io_pgtable		*iop;
 	void				*data;
@@ -763,6 +727,41 @@ static int __arm_lpae_iopte_walk(struct arm_lpae_io_pgtable *data,
 				 arm_lpae_iopte *ptep,
 				 int lvl);
 
+struct iova_to_phys_data {
+	arm_lpae_iopte pte;
+	int lvl;
+};
+
+static int visit_iova_to_phys(struct io_pgtable_walk_data *walk_data, int lvl,
+			      arm_lpae_iopte *ptep, size_t size)
+{
+	struct iova_to_phys_data *data = walk_data->data;
+	data->pte = *ptep;
+	data->lvl = lvl;
+	return 0;
+}
+
+static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
+					 unsigned long iova)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct iova_to_phys_data d;
+	struct io_pgtable_walk_data walk_data = {
+		.data = &d,
+		.visit = visit_iova_to_phys,
+		.addr = iova,
+		.end = iova + 1,
+	};
+	int ret;
+
+	ret = __arm_lpae_iopte_walk(data, &walk_data, data->pgd, data->start_level);
+	if (ret)
+		return 0;
+
+	iova &= (ARM_LPAE_BLOCK_SIZE(d.lvl, data) - 1);
+	return iopte_to_paddr(d.pte, data) | iova;
+}
+
 static int io_pgtable_visit(struct arm_lpae_io_pgtable *data,
 			    struct io_pgtable_walk_data *walk_data,
 			    arm_lpae_iopte *ptep, int lvl)
@@ -780,8 +779,9 @@ static int io_pgtable_visit(struct arm_lpae_io_pgtable *data,
 		return 0;
 	}
 
-	if (WARN_ON(!iopte_table(pte, lvl)))
+	if (!iopte_table(pte, lvl)) {
 		return -EINVAL;
+	}
 
 	ptep = iopte_deref(pte, data);
 	return __arm_lpae_iopte_walk(data, walk_data, ptep, lvl + 1);
-- 
2.47.0

Re: [PATCH v10 2/4] iommu/io-pgtable-arm: Re-use the pgtable walk for iova_to_phys

[Mostafa Saleh]

Hi Rob,

On Mon, Oct 28, 2024 at 02:31:38PM -0700, Rob Clark wrote:
> From: Rob Clark <robdclark@chromium.org>
> 
> Re-use the generic pgtable walk path.
> 
> Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Mostafa Saleh <smostafa@google.com>

Thanks,
Mostafa

> ---
>  drivers/iommu/io-pgtable-arm.c | 74 +++++++++++++++++-----------------
>  1 file changed, 37 insertions(+), 37 deletions(-)
> 
> diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
> index 7e9c0f8ae138..88b128c77893 100644
> --- a/drivers/iommu/io-pgtable-arm.c
> +++ b/drivers/iommu/io-pgtable-arm.c
> @@ -712,42 +712,6 @@ static size_t arm_lpae_unmap_pages(struct io_pgtable_ops *ops, unsigned long iov
>  				data->start_level, ptep);
>  }
>  
> -static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
> -					 unsigned long iova)
> -{
> -	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
> -	arm_lpae_iopte pte, *ptep = data->pgd;
> -	int lvl = data->start_level;
> -
> -	do {
> -		/* Valid IOPTE pointer? */
> -		if (!ptep)
> -			return 0;
> -
> -		/* Grab the IOPTE we're interested in */
> -		ptep += ARM_LPAE_LVL_IDX(iova, lvl, data);
> -		pte = READ_ONCE(*ptep);
> -
> -		/* Valid entry? */
> -		if (!pte)
> -			return 0;
> -
> -		/* Leaf entry? */
> -		if (iopte_leaf(pte, lvl, data->iop.fmt))
> -			goto found_translation;
> -
> -		/* Take it to the next level */
> -		ptep = iopte_deref(pte, data);
> -	} while (++lvl < ARM_LPAE_MAX_LEVELS);
> -
> -	/* Ran out of page tables to walk */
> -	return 0;
> -
> -found_translation:
> -	iova &= (ARM_LPAE_BLOCK_SIZE(lvl, data) - 1);
> -	return iopte_to_paddr(pte, data) | iova;
> -}
> -
>  struct io_pgtable_walk_data {
>  	struct io_pgtable		*iop;
>  	void				*data;
> @@ -763,6 +727,41 @@ static int __arm_lpae_iopte_walk(struct arm_lpae_io_pgtable *data,
>  				 arm_lpae_iopte *ptep,
>  				 int lvl);
>  
> +struct iova_to_phys_data {
> +	arm_lpae_iopte pte;
> +	int lvl;
> +};
> +
> +static int visit_iova_to_phys(struct io_pgtable_walk_data *walk_data, int lvl,
> +			      arm_lpae_iopte *ptep, size_t size)
> +{
> +	struct iova_to_phys_data *data = walk_data->data;
> +	data->pte = *ptep;
> +	data->lvl = lvl;
> +	return 0;
> +}
> +
> +static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
> +					 unsigned long iova)
> +{
> +	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
> +	struct iova_to_phys_data d;
> +	struct io_pgtable_walk_data walk_data = {
> +		.data = &d,
> +		.visit = visit_iova_to_phys,
> +		.addr = iova,
> +		.end = iova + 1,
> +	};
> +	int ret;
> +
> +	ret = __arm_lpae_iopte_walk(data, &walk_data, data->pgd, data->start_level);
> +	if (ret)
> +		return 0;
> +
> +	iova &= (ARM_LPAE_BLOCK_SIZE(d.lvl, data) - 1);
> +	return iopte_to_paddr(d.pte, data) | iova;
> +}
> +
>  static int io_pgtable_visit(struct arm_lpae_io_pgtable *data,
>  			    struct io_pgtable_walk_data *walk_data,
>  			    arm_lpae_iopte *ptep, int lvl)
> @@ -780,8 +779,9 @@ static int io_pgtable_visit(struct arm_lpae_io_pgtable *data,
>  		return 0;
>  	}
>  
> -	if (WARN_ON(!iopte_table(pte, lvl)))
> +	if (!iopte_table(pte, lvl)) {
>  		return -EINVAL;
> +	}
>  
>  	ptep = iopte_deref(pte, data);
>  	return __arm_lpae_iopte_walk(data, walk_data, ptep, lvl + 1);
> -- 
> 2.47.0
> 

[PATCH v10 3/4] iommu/io-pgtable-arm: Add way to debug pgtable walk

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

Add an io-pgtable method to walk the pgtable returning the raw PTEs that
would be traversed for a given iova access.

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/iommu/io-pgtable-arm.c | 25 +++++++++++++++++++++++++
 include/linux/io-pgtable.h     | 15 +++++++++++++++
 2 files changed, 40 insertions(+)

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 88b128c77893..6739e1fa54ec 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -762,6 +762,30 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
 	return iopte_to_paddr(d.pte, data) | iova;
 }
 
+static int visit_pgtable_walk(struct io_pgtable_walk_data *walk_data, int lvl,
+			      arm_lpae_iopte *ptep, size_t size)
+{
+	struct arm_lpae_io_pgtable_walk_data *data = walk_data->data;
+	data->ptes[data->level++] = *ptep;
+	return 0;
+}
+
+static int arm_lpae_pgtable_walk(struct io_pgtable_ops *ops, unsigned long iova,
+				 void *wd)
+{
+	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
+	struct io_pgtable_walk_data walk_data = {
+		.data = wd,
+		.visit = visit_pgtable_walk,
+		.addr = iova,
+		.end = iova + 1,
+	};
+
+	((struct arm_lpae_io_pgtable_walk_data *)wd)->level = 0;
+
+	return __arm_lpae_iopte_walk(data, &walk_data, data->pgd, data->start_level);
+}
+
 static int io_pgtable_visit(struct arm_lpae_io_pgtable *data,
 			    struct io_pgtable_walk_data *walk_data,
 			    arm_lpae_iopte *ptep, int lvl)
@@ -937,6 +961,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
 		.unmap_pages	= arm_lpae_unmap_pages,
 		.iova_to_phys	= arm_lpae_iova_to_phys,
 		.read_and_clear_dirty = arm_lpae_read_and_clear_dirty,
+		.pgtable_walk	= arm_lpae_pgtable_walk,
 	};
 
 	return data;
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index b1ecfc3cd5bc..d7bfbf351975 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -178,12 +178,26 @@ struct io_pgtable_cfg {
 	};
 };
 
+/**
+ * struct arm_lpae_io_pgtable_walk_data - information from a pgtable walk
+ *
+ * @ptes:     The recorded PTE values from the walk
+ * @level:    The level of the last PTE
+ *
+ * @level also specifies the last valid index in @ptes
+ */
+struct arm_lpae_io_pgtable_walk_data {
+	u64 ptes[4];
+	int level;
+};
+
 /**
  * struct io_pgtable_ops - Page table manipulation API for IOMMU drivers.
  *
  * @map_pages:    Map a physically contiguous range of pages of the same size.
  * @unmap_pages:  Unmap a range of virtually contiguous pages of the same size.
  * @iova_to_phys: Translate iova to physical address.
+ * @pgtable_walk: (optional) Perform a page table walk for a given iova.
  *
  * These functions map directly onto the iommu_ops member functions with
  * the same names.
@@ -197,6 +211,7 @@ struct io_pgtable_ops {
 			      struct iommu_iotlb_gather *gather);
 	phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
 				    unsigned long iova);
+	int (*pgtable_walk)(struct io_pgtable_ops *ops, unsigned long iova, void *wd);
 	int (*read_and_clear_dirty)(struct io_pgtable_ops *ops,
 				    unsigned long iova, size_t size,
 				    unsigned long flags,
-- 
2.47.0

Re: [PATCH v10 3/4] iommu/io-pgtable-arm: Add way to debug pgtable walk

[Mostafa Saleh]

Hi Rob,

On Mon, Oct 28, 2024 at 02:31:39PM -0700, Rob Clark wrote:
> From: Rob Clark <robdclark@chromium.org>
> 
> Add an io-pgtable method to walk the pgtable returning the raw PTEs that
> would be traversed for a given iova access.
> 
> Signed-off-by: Rob Clark <robdclark@chromium.org>
> ---
>  drivers/iommu/io-pgtable-arm.c | 25 +++++++++++++++++++++++++
>  include/linux/io-pgtable.h     | 15 +++++++++++++++
>  2 files changed, 40 insertions(+)
> 
> diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
> index 88b128c77893..6739e1fa54ec 100644
> --- a/drivers/iommu/io-pgtable-arm.c
> +++ b/drivers/iommu/io-pgtable-arm.c
> @@ -762,6 +762,30 @@ static phys_addr_t arm_lpae_iova_to_phys(struct io_pgtable_ops *ops,
>  	return iopte_to_paddr(d.pte, data) | iova;
>  }
>  
> +static int visit_pgtable_walk(struct io_pgtable_walk_data *walk_data, int lvl,
> +			      arm_lpae_iopte *ptep, size_t size)
> +{
> +	struct arm_lpae_io_pgtable_walk_data *data = walk_data->data;
> +	data->ptes[data->level++] = *ptep;
> +	return 0;
> +}
> +
> +static int arm_lpae_pgtable_walk(struct io_pgtable_ops *ops, unsigned long iova,
> +				 void *wd)
> +{
> +	struct arm_lpae_io_pgtable *data = io_pgtable_ops_to_data(ops);
> +	struct io_pgtable_walk_data walk_data = {
> +		.data = wd,
> +		.visit = visit_pgtable_walk,
> +		.addr = iova,
> +		.end = iova + 1,
> +	};
> +
> +	((struct arm_lpae_io_pgtable_walk_data *)wd)->level = 0;

I think this is a bit fragile, as it only works because the walk spans
one address, otherwise it breaks, the visitor will keep incrementing
the level. IMO, this should be removed, and the visitor already knows
the level as it's passed as an argument, so something like this:

diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
index 6739e1fa54ec..bc73f9edae8a 100644
--- a/drivers/iommu/io-pgtable-arm.c
+++ b/drivers/iommu/io-pgtable-arm.c
@@ -766,7 +766,8 @@ static int visit_pgtable_walk(struct io_pgtable_walk_data *walk_data, int lvl,
 			      arm_lpae_iopte *ptep, size_t size)
 {
 	struct arm_lpae_io_pgtable_walk_data *data = walk_data->data;
-	data->ptes[data->level++] = *ptep;
+	data->ptes[lvl] = *ptep;
+	data->level = lvl + 1;
 	return 0;
 }
 
@@ -781,8 +782,6 @@ static int arm_lpae_pgtable_walk(struct io_pgtable_ops *ops, unsigned long iova,
 		.end = iova + 1,
 	};
 
-	((struct arm_lpae_io_pgtable_walk_data *)wd)->level = 0;
-
 	return __arm_lpae_iopte_walk(data, &walk_data, data->pgd, data->start_level);
 }
 
Thanks,
Mostafa
> +
> +	return __arm_lpae_iopte_walk(data, &walk_data, data->pgd, data->start_level);
> +}
> +
>  static int io_pgtable_visit(struct arm_lpae_io_pgtable *data,
>  			    struct io_pgtable_walk_data *walk_data,
>  			    arm_lpae_iopte *ptep, int lvl)
> @@ -937,6 +961,7 @@ arm_lpae_alloc_pgtable(struct io_pgtable_cfg *cfg)
>  		.unmap_pages	= arm_lpae_unmap_pages,
>  		.iova_to_phys	= arm_lpae_iova_to_phys,
>  		.read_and_clear_dirty = arm_lpae_read_and_clear_dirty,
> +		.pgtable_walk	= arm_lpae_pgtable_walk,
>  	};
>  
>  	return data;
> diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
> index b1ecfc3cd5bc..d7bfbf351975 100644
> --- a/include/linux/io-pgtable.h
> +++ b/include/linux/io-pgtable.h
> @@ -178,12 +178,26 @@ struct io_pgtable_cfg {
>  	};
>  };
>  
> +/**
> + * struct arm_lpae_io_pgtable_walk_data - information from a pgtable walk
> + *
> + * @ptes:     The recorded PTE values from the walk
> + * @level:    The level of the last PTE
> + *
> + * @level also specifies the last valid index in @ptes
> + */
> +struct arm_lpae_io_pgtable_walk_data {
> +	u64 ptes[4];
> +	int level;
> +};
> +
>  /**
>   * struct io_pgtable_ops - Page table manipulation API for IOMMU drivers.
>   *
>   * @map_pages:    Map a physically contiguous range of pages of the same size.
>   * @unmap_pages:  Unmap a range of virtually contiguous pages of the same size.
>   * @iova_to_phys: Translate iova to physical address.
> + * @pgtable_walk: (optional) Perform a page table walk for a given iova.
>   *
>   * These functions map directly onto the iommu_ops member functions with
>   * the same names.
> @@ -197,6 +211,7 @@ struct io_pgtable_ops {
>  			      struct iommu_iotlb_gather *gather);
>  	phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
>  				    unsigned long iova);
> +	int (*pgtable_walk)(struct io_pgtable_ops *ops, unsigned long iova, void *wd);
>  	int (*read_and_clear_dirty)(struct io_pgtable_ops *ops,
>  				    unsigned long iova, size_t size,
>  				    unsigned long flags,
> -- 
> 2.47.0
> 

Re: [PATCH v10 0/4] io-pgtable-arm + drm/msm: Extend iova fault debugging

[Will Deacon]

Hi Rob,

On Mon, Oct 28, 2024 at 02:31:36PM -0700, Rob Clark wrote:
> From: Rob Clark <robdclark@chromium.org>
> 
> This series extends io-pgtable-arm with a method to retrieve the page
> table entries traversed in the process of address translation, and then
> beefs up drm/msm gpu devcore dump to include this (and additional info)
> in the devcore dump.
> 
> This is a respin of https://patchwork.freedesktop.org/series/94968/
> (minus a patch that was already merged)
> 
> v2:  Fix an armv7/32b build error in the last patch
> v3:  Incorperate Will Deacon's suggestion to make the interface
>      callback based.
> v4:  Actually wire up the callback
> v5:  Drop the callback approach
> v6:  Make walk-data struct pgtable specific and rename
>      io_pgtable_walk_data to arm_lpae_io_pgtable_walk_data
> v7:  Re-use the pgtable walker added for arm_lpae_read_and_clear_dirty()
> v8:  Pass pte pointer to callback so it can modify the actual pte
> v9:  Fix selftests_running case
> v10: Call visit cb for all nodes traversed, leave the decision about
>      whether to care about non-leaf nodes to the callback

Do you plan to respin this? I see Mostafa left a proposal on patch 3.

Thanks,

Will

Re: [PATCH v10 0/4] io-pgtable-arm + drm/msm: Extend iova fault debugging

[Rob Clark]

On Tue, Dec 10, 2024 at 3:14 AM Will Deacon <will@kernel.org> wrote:
>
> Hi Rob,
>
> On Mon, Oct 28, 2024 at 02:31:36PM -0700, Rob Clark wrote:
> > From: Rob Clark <robdclark@chromium.org>
> >
> > This series extends io-pgtable-arm with a method to retrieve the page
> > table entries traversed in the process of address translation, and then
> > beefs up drm/msm gpu devcore dump to include this (and additional info)
> > in the devcore dump.
> >
> > This is a respin of https://patchwork.freedesktop.org/series/94968/
> > (minus a patch that was already merged)
> >
> > v2:  Fix an armv7/32b build error in the last patch
> > v3:  Incorperate Will Deacon's suggestion to make the interface
> >      callback based.
> > v4:  Actually wire up the callback
> > v5:  Drop the callback approach
> > v6:  Make walk-data struct pgtable specific and rename
> >      io_pgtable_walk_data to arm_lpae_io_pgtable_walk_data
> > v7:  Re-use the pgtable walker added for arm_lpae_read_and_clear_dirty()
> > v8:  Pass pte pointer to callback so it can modify the actual pte
> > v9:  Fix selftests_running case
> > v10: Call visit cb for all nodes traversed, leave the decision about
> >      whether to care about non-leaf nodes to the callback
>
> Do you plan to respin this? I see Mostafa left a proposal on patch 3.

Yeah, his suggestion looked reasonable.  I'll try to get back to this
patchset today.

BR,
-R