xen: map foreign pages for shared rings by updating the PTEs directly

When mapping a foreign page with xenbus_map_ring_valloc() with the
GNTTABOP_map_grant_ref hypercall, set the GNTMAP_contains_pte flag and
pass a pointer to the PTE (in init_mm).

After the page is mapped, the usual fault mechanism can be used to
update additional MMs.  This allows the vmalloc_sync_all() to be
removed from alloc_vm_area().

Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
[v1: Squashed fix by Michal for no-mmu case]
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Michal Simek <monstr@monstr.eu>

2 files changed, 14 insertions, 15 deletions

diff --git a/mm/nommu.c b/mm/nommu.c
index 73419c55eda..b982290fd96 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -454,7 +454,7 @@ void  __attribute__((weak)) vmalloc_sync_all(void)
  *	between processes, it syncs the pagetable across all
  *	processes.
  */
-struct vm_struct *alloc_vm_area(size_t size)
+struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
 {
 	BUG();
 	return NULL;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b669aa6f6ca..3231bf33287 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2141,23 +2141,30 @@ void  __attribute__((weak)) vmalloc_sync_all(void)
 
 static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
 {
-	/* apply_to_page_range() does all the hard work. */
+	pte_t ***p = data;
+
+	if (p) {
+		*(*p) = pte;
+		(*p)++;
+	}
 	return 0;
 }
 
 /**
  *	alloc_vm_area - allocate a range of kernel address space
  *	@size:		size of the area
+ *	@ptes:		returns the PTEs for the address space
  *
  *	Returns:	NULL on failure, vm_struct on success
  *
  *	This function reserves a range of kernel address space, and
  *	allocates pagetables to map that range.  No actual mappings
- *	are created.  If the kernel address space is not shared
- *	between processes, it syncs the pagetable across all
- *	processes.
+ *	are created.
+ *
+ *	If @ptes is non-NULL, pointers to the PTEs (in init_mm)
+ *	allocated for the VM area are returned.
  */
-struct vm_struct *alloc_vm_area(size_t size)
+struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
 {
 	struct vm_struct *area;
 
@@ -2171,19 +2178,11 @@ struct vm_struct *alloc_vm_area(size_t size)
 	 * of kernel virtual address space and mapped into init_mm.
 	 */
 	if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
-				area->size, f, NULL)) {
+				size, f, ptes ? &ptes : NULL)) {
 		free_vm_area(area);
 		return NULL;
 	}
 
-	/*
-	 * If the allocated address space is passed to a hypercall
-	 * before being used then we cannot rely on a page fault to
-	 * trigger an update of the page tables.  So sync all the page
-	 * tables here.
-	 */
-	vmalloc_sync_all();
-
 	return area;
 }
 EXPORT_SYMBOL_GPL(alloc_vm_area);