userfaultfd: hugetlbfs: allow registration of ranges containing huge pages

Expand the userfaultfd_register/unregister routines to allow VM_HUGETLB
vmas.  huge page alignment checking is performed after a VM_HUGETLB vma
is encountered.

Also, since there is no UFFDIO_ZEROPAGE support for huge pages do not
return that as a valid ioctl method for huge page ranges.

Link: http://lkml.kernel.org/r/20161216144821.5183-22-aarcange@redhat.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Michael Rapoport <RAPOPORT@il.ibm.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 26e1ef0..5139d05 100644 (file)
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -27,6 +27,7 @@
 #include <linux/mempolicy.h>
 #include <linux/ioctl.h>
 #include <linux/security.h>
+#include <linux/hugetlb.h>
 
 static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly;
 
@@ -1058,6 +1059,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
        struct uffdio_register __user *user_uffdio_register;
        unsigned long vm_flags, new_flags;
        bool found;
+       bool huge_pages;
        unsigned long start, end, vma_end;
 
        user_uffdio_register = (struct uffdio_register __user *) arg;
@@ -1108,6 +1110,17 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
        if (vma->vm_start >= end)
                goto out_unlock;
 
+       /*
+        * If the first vma contains huge pages, make sure start address
+        * is aligned to huge page size.
+        */
+       if (is_vm_hugetlb_page(vma)) {
+               unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
+
+               if (start & (vma_hpagesize - 1))
+                       goto out_unlock;
+       }
+
        /*
         * Search for not compatible vmas.
         *
@@ -1116,6 +1129,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
         * on anonymous vmas).
         */
        found = false;
+       huge_pages = false;
        for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
                cond_resched();
 
@@ -1124,8 +1138,21 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 
                /* check not compatible vmas */
                ret = -EINVAL;
-               if (!vma_is_anonymous(cur))
+               if (!vma_is_anonymous(cur) && !is_vm_hugetlb_page(cur))
                        goto out_unlock;
+               /*
+                * If this vma contains ending address, and huge pages
+                * check alignment.
+                */
+               if (is_vm_hugetlb_page(cur) && end <= cur->vm_end &&
+                   end > cur->vm_start) {
+                       unsigned long vma_hpagesize = vma_kernel_pagesize(cur);
+
+                       ret = -EINVAL;
+
+                       if (end & (vma_hpagesize - 1))
+                               goto out_unlock;
+               }
 
                /*
                 * Check that this vma isn't already owned by a
@@ -1138,6 +1165,12 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
                    cur->vm_userfaultfd_ctx.ctx != ctx)
                        goto out_unlock;
 
+               /*
+                * Note vmas containing huge pages
+                */
+               if (is_vm_hugetlb_page(cur))
+                       huge_pages = true;
+
                found = true;
        }
        BUG_ON(!found);
@@ -1149,7 +1182,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
        do {
                cond_resched();
 
-               BUG_ON(!vma_is_anonymous(vma));
+               BUG_ON(!vma_is_anonymous(vma) && !is_vm_hugetlb_page(vma));
                BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
                       vma->vm_userfaultfd_ctx.ctx != ctx);
 
@@ -1207,7 +1240,8 @@ out_unlock:
                 * userland which ioctls methods are guaranteed to
                 * succeed on this range.
                 */
-               if (put_user(UFFD_API_RANGE_IOCTLS,
+               if (put_user(huge_pages ? UFFD_API_RANGE_IOCTLS_HPAGE :
+                            UFFD_API_RANGE_IOCTLS,
                             &user_uffdio_register->ioctls))
                        ret = -EFAULT;
        }
@@ -1253,6 +1287,17 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
        if (vma->vm_start >= end)
                goto out_unlock;
 
+       /*
+        * If the first vma contains huge pages, make sure start address
+        * is aligned to huge page size.
+        */
+       if (is_vm_hugetlb_page(vma)) {
+               unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
+
+               if (start & (vma_hpagesize - 1))
+                       goto out_unlock;
+       }
+
        /*
         * Search for not compatible vmas.
         *
@@ -1275,7 +1320,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
                 * provides for more strict behavior to notice
                 * unregistration errors.
                 */
-               if (!vma_is_anonymous(cur))
+               if (!vma_is_anonymous(cur) && !is_vm_hugetlb_page(cur))
                        goto out_unlock;
 
                found = true;
@@ -1289,7 +1334,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
        do {
                cond_resched();
 
-               BUG_ON(!vma_is_anonymous(vma));
+               BUG_ON(!vma_is_anonymous(vma) && !is_vm_hugetlb_page(vma));
 
                /*
                 * Nothing to do: this vma is already registered into this

diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index 2bbf323..a3828a9 100644 (file)
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -29,6 +29,9 @@
        ((__u64)1 << _UFFDIO_WAKE |             \
         (__u64)1 << _UFFDIO_COPY |             \
         (__u64)1 << _UFFDIO_ZEROPAGE)
+#define UFFD_API_RANGE_IOCTLS_HPAGE            \
+       ((__u64)1 << _UFFDIO_WAKE |             \
+        (__u64)1 << _UFFDIO_COPY)
 
 /*
  * Valid ioctl command number range with this API is from 0x00 to