mm: provide a saner PTE walking API for modules

commit 9fd6dad1261a541b3f5fa7dc5b152222306e6702 upstream.

Currently, the follow_pfn function is exported for modules but
follow_pte is not.  However, follow_pfn is very easy to misuse,
because it does not provide protections (so most of its callers
assume the page is writable!) and because it returns after having
already unlocked the page table lock.

Provide instead a simplified version of follow_pte that does
not have the pmdpp and range arguments.  The older version
survives as follow_invalidate_pte() for use by fs/dax.c.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/dax.c b/fs/dax.c
index 26d5dcd2d69e5c0afd2c93d7042b54c3324b7342..b3d27fdc67752df52637bccdbde008c0086aa312 100644 (file)
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -810,11 +810,12 @@ static void dax_entry_mkclean(struct address_space *mapping, pgoff_t index,
                address = pgoff_address(index, vma);
 
                /*
-                * Note because we provide range to follow_pte it will call
+                * follow_invalidate_pte() will use the range to call
                 * mmu_notifier_invalidate_range_start() on our behalf before
                 * taking any lock.
                 */
-               if (follow_pte(vma->vm_mm, address, &range, &ptep, &pmdp, &ptl))
+               if (follow_invalidate_pte(vma->vm_mm, address, &range, &ptep,
+                                         &pmdp, &ptl))
                        continue;
 
                /*

diff --git a/include/linux/mm.h b/include/linux/mm.h
index f4a69d4905175e8d355c8bc3672648230cfd4304..b8eadd9f96802cb8609af4a3cc0ac1deb24507ea 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1655,9 +1655,11 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
                unsigned long end, unsigned long floor, unsigned long ceiling);
 int
 copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
+int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
+                         struct mmu_notifier_range *range, pte_t **ptepp,
+                         pmd_t **pmdpp, spinlock_t **ptlp);
 int follow_pte(struct mm_struct *mm, unsigned long address,
-               struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp,
-               spinlock_t **ptlp);
+              pte_t **ptepp, spinlock_t **ptlp);
 int 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 94c4b9af198ca59b632d2a0493c123d646ef4744..eb5722027160a7266938440437ff5938d55aec03 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4707,9 +4707,9 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 }
 #endif /* __PAGETABLE_PMD_FOLDED */
 
-int follow_pte(struct mm_struct *mm, unsigned long address,
-              struct mmu_notifier_range *range, pte_t **ptepp, pmd_t **pmdpp,
-              spinlock_t **ptlp)
+int follow_invalidate_pte(struct mm_struct *mm, unsigned long address,
+                         struct mmu_notifier_range *range, pte_t **ptepp,
+                         pmd_t **pmdpp, spinlock_t **ptlp)
 {
        pgd_t *pgd;
        p4d_t *p4d;
@@ -4774,6 +4774,34 @@ out:
        return -EINVAL;
 }
 
+/**
+ * follow_pte - look up PTE at a user virtual address
+ * @mm: the mm_struct of the target address space
+ * @address: user virtual address
+ * @ptepp: location to store found PTE
+ * @ptlp: location to store the lock for the PTE
+ *
+ * On a successful return, the pointer to the PTE is stored in @ptepp;
+ * the corresponding lock is taken and its location is stored in @ptlp.
+ * The contents of the PTE are only stable until @ptlp is released;
+ * any further use, if any, must be protected against invalidation
+ * with MMU notifiers.
+ *
+ * Only IO mappings and raw PFN mappings are allowed.  The mmap semaphore
+ * 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.
+ *
+ * Return: zero on success, -ve otherwise.
+ */
+int follow_pte(struct mm_struct *mm, unsigned long address,
+              pte_t **ptepp, spinlock_t **ptlp)
+{
+       return follow_invalidate_pte(mm, address, NULL, ptepp, NULL, ptlp);
+}
+EXPORT_SYMBOL_GPL(follow_pte);
+
 /**
  * follow_pfn - look up PFN at a user virtual address
  * @vma: memory mapping
@@ -4782,6 +4810,9 @@ out:
  *
  * Only IO mappings and raw PFN mappings are allowed.
  *
+ * 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,
@@ -4794,7 +4825,7 @@ int follow_pfn(struct vm_area_struct *vma, unsigned long address,
        if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
                return ret;
 
-       ret = follow_pte(vma->vm_mm, address, NULL, &ptep, NULL, &ptl);
+       ret = follow_pte(vma->vm_mm, address, &ptep, &ptl);
        if (ret)
                return ret;
        *pfn = pte_pfn(*ptep);
@@ -4815,7 +4846,7 @@ int follow_phys(struct vm_area_struct *vma,
        if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)))
                goto out;
 
-       if (follow_pte(vma->vm_mm, address, NULL, &ptep, NULL, &ptl))
+       if (follow_pte(vma->vm_mm, address, &ptep, &ptl))
                goto out;
        pte = *ptep;
 

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 2f84027bc3bea8afdc5f807584250ce045afd2cd..1bd7e5ee35505fff39563cad8fd70e1147fea7ea 100644 (file)
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1893,7 +1893,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
        spinlock_t *ptl;
        int r;
 
-       r = follow_pte(vma->vm_mm, addr, NULL, &ptep, NULL, &ptl);
+       r = follow_pte(vma->vm_mm, addr, &ptep, &ptl);
        if (r) {
                /*
                 * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does
@@ -1908,7 +1908,7 @@ static int hva_to_pfn_remapped(struct vm_area_struct *vma,
                if (r)
                        return r;
 
-               r = follow_pte(vma->vm_mm, addr, NULL, &ptep, NULL, &ptl);
+               r = follow_pte(vma->vm_mm, addr, &ptep, &ptl);
                if (r)
                        return r;
        }