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 31dae08acb09a578f1ceed560d9e67980db4b85c..3b0e5da96d541ec3e7ab1dce8187dc276507a0ac 100644 (file)
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -794,11 +794,12 @@ 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 bbdeb172912fbea2ded9bb748d01f427953828e6..c63e4b38b7fe02ec7c5621cdda4e562e61def071 100644 (file)
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1466,9 +1466,11 @@ 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 mm_struct *dst, struct mm_struct *src,
                        struct vm_area_struct *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 64b347fb9cf8353fc10bc494d3189c3b4a95155e..b23831132933a4377247a85b5c9ba8f1677883e2 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4222,9 +4222,9 @@ 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;
@@ -4289,6 +4289,34 @@ 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
@@ -4297,6 +4325,9 @@ 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,
@@ -4309,7 +4340,7 @@ 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);
@@ -4330,7 +4361,7 @@ 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 04535e9d9183610382e1a4a8e100b1c1cdfe58ba..19de91b896ff8f192a95e52762171f10395a8b88 100644 (file)
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1603,7 +1603,7 @@ 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
@@ -1618,7 +1618,7 @@ 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;
        }