2014-11-12 22:10:30

by Jesse Barnes

[permalink] [raw]
Subject: [PATCH 1/2] mm: export find_extend_vma and handle_mm_fault for driver use

This lets drivers like the AMD IOMMUv2 driver handle faults a bit more
simply, rather than doing tricks with page refs and get_user_pages().

Signed-off-by: Jesse Barnes <[email protected]>
---
mm/memory.c | 1 +
mm/mmap.c | 2 ++
2 files changed, 3 insertions(+)

diff --git a/mm/memory.c b/mm/memory.c
index 1cc6bfb..969ff0c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3378,6 +3378,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,

return ret;
}
+EXPORT_SYMBOL_GPL(handle_mm_fault);

#ifndef __PAGETABLE_PUD_FOLDED
/*
diff --git a/mm/mmap.c b/mm/mmap.c
index 7f85520..2ee7971 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2359,6 +2359,8 @@ find_extend_vma(struct mm_struct *mm, unsigned long addr)
}
#endif

+EXPORT_SYMBOL_GPL(find_extend_vma);
+
/*
* Ok - we have the memory areas we should free on the vma list,
* so release them, and do the vma updates.
--
1.9.1


2014-11-12 22:17:11

by Jesse Barnes

[permalink] [raw]
Subject: [PATCH 2/2] iommu/amd: use handle_mm_fault directly v2

This could be useful for debug in the future if we want to track
major/minor faults more closely, and also avoids the put_page trick we
used with gup.

In order to do this, we also track the task struct in the PASID state
structure. This lets us update the appropriate task stats after the
fault has been handled, and may aid with debug in the future as well.

v2: drop task accounting; GPU activity may have been submitted by a
different thread than the one binding the PASID (Joerg)

Tested-by: Oded Gabbay <[email protected]>
Signed-off-by: Jesse Barnes <[email protected]>
---
drivers/iommu/amd_iommu_v2.c | 84 ++++++++++++++++++++++++++++----------------
1 file changed, 53 insertions(+), 31 deletions(-)

diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 90d734b..9c0d6e2 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -513,45 +513,67 @@ static void finish_pri_tag(struct device_state *dev_state,
spin_unlock_irqrestore(&pasid_state->lock, flags);
}

+static void handle_fault_error(struct fault *fault)
+{
+ int status;
+
+ if (!fault->dev_state->inv_ppr_cb) {
+ set_pri_tag_status(fault->state, fault->tag, PPR_INVALID);
+ return;
+ }
+
+ status = fault->dev_state->inv_ppr_cb(fault->dev_state->pdev,
+ fault->pasid,
+ fault->address,
+ fault->flags);
+ switch (status) {
+ case AMD_IOMMU_INV_PRI_RSP_SUCCESS:
+ set_pri_tag_status(fault->state, fault->tag, PPR_SUCCESS);
+ break;
+ case AMD_IOMMU_INV_PRI_RSP_INVALID:
+ set_pri_tag_status(fault->state, fault->tag, PPR_INVALID);
+ break;
+ case AMD_IOMMU_INV_PRI_RSP_FAIL:
+ set_pri_tag_status(fault->state, fault->tag, PPR_FAILURE);
+ break;
+ default:
+ BUG();
+ }
+}
+
static void do_fault(struct work_struct *work)
{
struct fault *fault = container_of(work, struct fault, work);
- int npages, write;
- struct page *page;
+ struct mm_struct *mm;
+ struct vm_area_struct *vma;
+ u64 address;
+ int ret, write;

write = !!(fault->flags & PPR_FAULT_WRITE);

- down_read(&fault->state->mm->mmap_sem);
- npages = get_user_pages(NULL, fault->state->mm,
- fault->address, 1, write, 0, &page, NULL);
- up_read(&fault->state->mm->mmap_sem);
-
- if (npages == 1) {
- put_page(page);
- } else if (fault->dev_state->inv_ppr_cb) {
- int status;
-
- status = fault->dev_state->inv_ppr_cb(fault->dev_state->pdev,
- fault->pasid,
- fault->address,
- fault->flags);
- switch (status) {
- case AMD_IOMMU_INV_PRI_RSP_SUCCESS:
- set_pri_tag_status(fault->state, fault->tag, PPR_SUCCESS);
- break;
- case AMD_IOMMU_INV_PRI_RSP_INVALID:
- set_pri_tag_status(fault->state, fault->tag, PPR_INVALID);
- break;
- case AMD_IOMMU_INV_PRI_RSP_FAIL:
- set_pri_tag_status(fault->state, fault->tag, PPR_FAILURE);
- break;
- default:
- BUG();
- }
- } else {
- set_pri_tag_status(fault->state, fault->tag, PPR_INVALID);
+ mm = fault->state->mm;
+ address = fault->address;
+
+ down_read(&mm->mmap_sem);
+ vma = find_extend_vma(mm, address);
+ if (!vma || address < vma->vm_start) {
+ /* failed to get a vma in the right range */
+ up_read(&mm->mmap_sem);
+ handle_fault_error(fault);
+ goto out;
+ }
+
+ ret = handle_mm_fault(mm, vma, address, write);
+ if (ret & VM_FAULT_ERROR) {
+ /* failed to service fault */
+ up_read(&mm->mmap_sem);
+ handle_fault_error(fault);
+ goto out;
}

+ up_read(&mm->mmap_sem);
+
+out:
finish_pri_tag(fault->dev_state, fault->state, fault->tag);

put_pasid_state(fault->state);
--
1.9.1