Both kvm (in bd2fae8da794 ("KVM: do not assume PTE is writable after
follow_pfn")) and vfio (in 07956b6269d3 ("vfio/type1: Use
follow_pte()")) have lost their callsites of follow_pfn(). All the
other ones have been switched over to unsafe_follow_pfn because they
cannot be fixed without breaking userspace api.
Argueably the vfio code is still racy, but that's kinda a bigger
picture. But since it does leak the pte beyond where it drops the pt
lock, without anything else like an mmu notifier guaranteeing
coherence, the problem is at least clearly visible in the vfio code.
So good enough with me.
I've decided to keep the explanation that after dropping the pt lock
you must have an mmu notifier if you keep using the pte somehow by
adjusting it and moving it into the kerneldoc for the new follow_pte()
function.
Cc: 3pvd@xxxxxxxxxx
Cc: Jann Horn <jannh@xxxxxxxxxx>
Cc: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxx>
Cc: Cornelia Huck <cohuck@xxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Alex Williamson <alex.williamson@xxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx
Cc: linux-arm-kernel@xxxxxxxxxxxxxxxxxxx
Cc: linux-samsung-soc@xxxxxxxxxxxxxxx
Cc: linux-media@xxxxxxxxxxxxxxx
Cc: kvm@xxxxxxxxxxxxxxx
Signed-off-by: Daniel Vetter <daniel.vetter@xxxxxxxxx>
---
include/linux/mm.h | 2 --
mm/memory.c | 26 +++++---------------------
mm/nommu.c | 13 +------------
3 files changed, 6 insertions(+), 35 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index caec8b25d66f..304588e2f829 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1693,8 +1693,6 @@ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
pmd_t **pmdpp, spinlock_t **ptlp);
int follow_pte(struct mm_struct *mm, unsigned long address,
pte_t **ptepp, spinlock_t **ptlp);
-int follow_pfn(struct vm_area_struct *vma, unsigned long address,
- unsigned long *pfn);
int unsafe_follow_pfn(struct vm_area_struct *vma, unsigned long address,
unsigned long *pfn);
int follow_phys(struct vm_area_struct *vma, unsigned long address,
diff --git a/mm/memory.c b/mm/memory.c
index e8a145505b69..317e653c8aeb 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4724,7 +4724,10 @@ int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
* should be taken for read.
*
* KVM uses this function. While it is arguably less bad than ``follow_pfn``,
- * it is not a good general-purpose API.
+ * it is not a good general-purpose API: If callers use the pte after they've
+ * unlocked @ptlp they must ensure coherency with pte updates by using a
+ * &mmu_notifier to follow updates. Any caller not following these requirements
+ * must use unsafe_follow_pfn() instead.
*
* Return: zero on success, -ve otherwise.
*/
@@ -4735,25 +4738,7 @@ int follow_pte(struct mm_struct *mm, unsigned long address,
}
EXPORT_SYMBOL_GPL(follow_pte);
-/**
- * follow_pfn - look up PFN at a user virtual address
- * @vma: memory mapping
- * @address: user virtual address
- * @pfn: location to store found PFN
- *
- * Only IO mappings and raw PFN mappings are allowed. Note that callers must
- * ensure coherency with pte updates by using a &mmu_notifier to follow updates.
- * If this is not feasible, or the access to the @pfn is only very short term,
- * use follow_pte_pmd() instead and hold the pagetable lock for the duration of
- * the access instead. Any caller not following these requirements must use
- * unsafe_follow_pfn() instead.
- *
- * This function does not allow the caller to read the permissions
- * of the PTE. Do not use it.
- *
- * Return: zero and the pfn at @pfn on success, -ve otherwise.
- */
-int follow_pfn(struct vm_area_struct *vma, unsigned long address,
+static int follow_pfn(struct vm_area_struct *vma, unsigned long address,
unsigned long *pfn)
{
int ret = -EINVAL;
@@ -4770,7 +4755,6 @@ int follow_pfn(struct vm_area_struct *vma, unsigned long address,
pte_unmap_unlock(ptep, ptl);
return 0;
}
-EXPORT_SYMBOL_GPL(follow_pfn);
/**
* unsafe_follow_pfn - look up PFN at a user virtual address
diff --git a/mm/nommu.c b/mm/nommu.c
index 1dc983f50e2c..cee29d0791b3 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -111,17 +111,7 @@ unsigned int kobjsize(const void *objp)
return page_size(page);
}
-/**
- * follow_pfn - look up PFN at a user virtual address
- * @vma: memory mapping
- * @address: user virtual address
- * @pfn: location to store found PFN
- *
- * Only IO mappings and raw PFN mappings are allowed.
- *
- * Returns zero and the pfn at @pfn on success, -ve otherwise.
- */
-int follow_pfn(struct vm_area_struct *vma, unsigned long address,
+static int follow_pfn(struct vm_area_struct *vma, unsigned long address,
unsigned long *pfn)
{
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
@@ -130,7 +120,6 @@ int follow_pfn(struct vm_area_struct *vma, unsigned long address,
*pfn = address >> PAGE_SHIFT;
return 0;
}
-EXPORT_SYMBOL_GPL(follow_pfn);
/**
* unsafe_follow_pfn - look up PFN at a user virtual address
--
2.30.0
