[PATCH v9 0/4] io-pgtable-arm + drm/msm: Extend iova fault debugging

[PATCH v9 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

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          | 149 +++++++++++++++---------
 include/linux/io-pgtable.h              |  15 +++
 7 files changed, 160 insertions(+), 56 deletions(-)

-- 
2.46.0

[PATCH v9 4/4] drm/msm: Extend gpu devcore dumps with pgtbl info

[Rob Clark]

From: Rob Clark <robdclark@chromium.org>

In the case of iova fault triggered devcore dumps, include additional
debug information based on what we think is the current page tables,
including the TTBR0 value (which should match what we have in
adreno_smmu_fault_info unless things have gone horribly wrong), and
the pagetable entries traversed in the process of resolving the
faulting iova.

Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 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 ++-
 5 files changed, 51 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 1c6626747b98..3848b5a64351 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -864,6 +864,16 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 		drm_printf(p, "  - dir=%s\n", info->flags & IOMMU_FAULT_WRITE ? "WRITE" : "READ");
 		drm_printf(p, "  - type=%s\n", info->type);
 		drm_printf(p, "  - source=%s\n", info->block);
+
+		/* Information extracted from what we think are the current
+		 * pgtables.  Hopefully the TTBR0 matches what we've extracted
+		 * from the SMMU registers in smmu_info!
+		 */
+		drm_puts(p, "pgtable-fault-info:\n");
+		drm_printf(p, "  - ttbr0: %.16llx\n", (u64)info->pgtbl_ttbr0);
+		drm_printf(p, "  - asid: %d\n", info->asid);
+		drm_printf(p, "  - ptes: %.16llx %.16llx %.16llx %.16llx\n",
+			   info->ptes[0], info->ptes[1], info->ptes[2], info->ptes[3]);
 	}
 
 	drm_printf(p, "rbbm-status: 0x%08x\n", state->rbbm_status);
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 3666b42b4ecd..bf2f8b2a7ccc 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -281,6 +281,15 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
 	if (submit) {
 		int i;
 
+		if (state->fault_info.ttbr0) {
+			struct msm_gpu_fault_info *info = &state->fault_info;
+			struct msm_mmu *mmu = submit->aspace->mmu;
+
+			msm_iommu_pagetable_params(mmu, &info->pgtbl_ttbr0,
+						   &info->asid);
+			msm_iommu_pagetable_walk(mmu, info->iova, info->ptes);
+		}
+
 		state->bos = kcalloc(submit->nr_bos,
 			sizeof(struct msm_gpu_state_bo), GFP_KERNEL);
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 1f02bb9956be..82e838ba8c80 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -101,6 +101,14 @@ struct msm_gpu_fault_info {
 	int flags;
 	const char *type;
 	const char *block;
+
+	/* Information about what we think/expect is the current SMMU state,
+	 * for example expected_ttbr0 should match smmu_info.ttbr0 which
+	 * was read back from SMMU registers.
+	 */
+	phys_addr_t pgtbl_ttbr0;
+	u64 ptes[4];
+	int asid;
 };
 
 /**
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index 2a94e82316f9..3e692818ba1f 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -195,6 +195,28 @@ struct iommu_domain_geometry *msm_iommu_get_geometry(struct msm_mmu *mmu)
 	return &iommu->domain->geometry;
 }
 
+int
+msm_iommu_pagetable_walk(struct msm_mmu *mmu, unsigned long iova, uint64_t ptes[4])
+{
+	struct msm_iommu_pagetable *pagetable;
+	struct arm_lpae_io_pgtable_walk_data wd = {};
+
+	if (mmu->type != MSM_MMU_IOMMU_PAGETABLE)
+		return -EINVAL;
+
+	pagetable = to_pagetable(mmu);
+
+	if (!pagetable->pgtbl_ops->pgtable_walk)
+		return -EINVAL;
+
+	pagetable->pgtbl_ops->pgtable_walk(pagetable->pgtbl_ops, iova, &wd);
+
+	for (int i = 0; i < ARRAY_SIZE(wd.ptes); i++)
+		ptes[i] = wd.ptes[i];
+
+	return 0;
+}
+
 static const struct msm_mmu_funcs pagetable_funcs = {
 		.map = msm_iommu_pagetable_map,
 		.unmap = msm_iommu_pagetable_unmap,
diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h
index 88af4f490881..96e509bd96a6 100644
--- a/drivers/gpu/drm/msm/msm_mmu.h
+++ b/drivers/gpu/drm/msm/msm_mmu.h
@@ -53,7 +53,8 @@ static inline void msm_mmu_set_fault_handler(struct msm_mmu *mmu, void *arg,
 struct msm_mmu *msm_iommu_pagetable_create(struct msm_mmu *parent);
 
 int msm_iommu_pagetable_params(struct msm_mmu *mmu, phys_addr_t *ttbr,
-		int *asid);
+			       int *asid);
+int msm_iommu_pagetable_walk(struct msm_mmu *mmu, unsigned long iova, uint64_t ptes[4]);
 struct iommu_domain_geometry *msm_iommu_get_geometry(struct msm_mmu *mmu);
 
 #endif /* __MSM_MMU_H__ */
-- 
2.46.0

Re: [PATCH v9 0/4] io-pgtable-arm + drm/msm: Extend iova fault debugging

[Mostafa Saleh]

Hi Rob,

On Tue, Aug 27, 2024 at 11:17:08AM -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
> 
> 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

Do you have plans to post another version of this series, as I am
working on some patches, that would use some of the common page walk
logic, so it would be more convenient to have them upstream.
Otherwise, I can have your series as a dependency.

Thanks,
Mostafa


> 
>  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          | 149 +++++++++++++++---------
>  include/linux/io-pgtable.h              |  15 +++
>  7 files changed, 160 insertions(+), 56 deletions(-)
> 
> -- 
> 2.46.0
> 

Re: [PATCH v9 0/4] io-pgtable-arm + drm/msm: Extend iova fault debugging

[Rob Clark]

On Mon, Oct 28, 2024 at 4:53 AM Mostafa Saleh <smostafa@google.com> wrote:
>
> Hi Rob,
>
> On Tue, Aug 27, 2024 at 11:17:08AM -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
> >
> > 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
>
> Do you have plans to post another version of this series, as I am
> working on some patches, that would use some of the common page walk
> logic, so it would be more convenient to have them upstream.
> Otherwise, I can have your series as a dependency.

Sorry, this had dropped off my radar, I'll post an updated iteration
in a couple minutes.

BR,
-R

> Thanks,
> Mostafa
>
>
> >
> >  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          | 149 +++++++++++++++---------
> >  include/linux/io-pgtable.h              |  15 +++
> >  7 files changed, 160 insertions(+), 56 deletions(-)
> >
> > --
> > 2.46.0
> >