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>

5 files changed, 24 insertions, 20 deletions

diff --git a/arch/x86/xen/grant-table.c b/arch/x86/xen/grant-table.c
index 6bbfd7a..5a40d24 100644
--- a/arch/x86/xen/grant-table.c
+++ b/arch/x86/xen/grant-table.c
@@ -71,7 +71,7 @@ int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
 
 	if (shared == NULL) {
 		struct vm_struct *area =
-			alloc_vm_area(PAGE_SIZE * max_nr_gframes);
+			alloc_vm_area(PAGE_SIZE * max_nr_gframes, NULL);
 		BUG_ON(area == NULL);
 		shared = area->addr;
 		*__shared = shared;
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 81c3ce6..1906125 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -35,6 +35,7 @@
 #include <linux/vmalloc.h>
 #include <linux/export.h>
 #include <asm/xen/hypervisor.h>
+#include <asm/xen/page.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/event_channel.h>
 #include <xen/events.h>
@@ -436,19 +437,20 @@ EXPORT_SYMBOL_GPL(xenbus_free_evtchn);
 int xenbus_map_ring_valloc(struct xenbus_device *dev, int gnt_ref, void **vaddr)
 {
 	struct gnttab_map_grant_ref op = {
-		.flags = GNTMAP_host_map,
+		.flags = GNTMAP_host_map | GNTMAP_contains_pte,
 		.ref   = gnt_ref,
 		.dom   = dev->otherend_id,
 	};
 	struct vm_struct *area;
+	pte_t *pte;
 
 	*vaddr = NULL;
 
-	area = alloc_vm_area(PAGE_SIZE);
+	area = alloc_vm_area(PAGE_SIZE, &pte);
 	if (!area)
 		return -ENOMEM;
 
-	op.host_addr = (unsigned long)area->addr;
+	op.host_addr = arbitrary_virt_to_machine(pte).maddr;
 
 	if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
 		BUG();
@@ -527,6 +529,7 @@ int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr)
 	struct gnttab_unmap_grant_ref op = {
 		.host_addr = (unsigned long)vaddr,
 	};
+	unsigned int level;
 
 	/* It'd be nice if linux/vmalloc.h provided a find_vm_area(void *addr)
 	 * method so that we don't have to muck with vmalloc internals here.
@@ -548,6 +551,8 @@ int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr)
 	}
 
 	op.handle = (grant_handle_t)area->phys_addr;
+	op.host_addr = arbitrary_virt_to_machine(
+		lookup_address((unsigned long)vaddr, &level)).maddr;
 
 	if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1))
 		BUG();
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 687fb11..4bde182 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -119,7 +119,7 @@ unmap_kernel_range(unsigned long addr, unsigned long size)
 #endif
 
 /* Allocate/destroy a 'vmalloc' VM area. */
-extern struct vm_struct *alloc_vm_area(size_t size);
+extern struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes);
 extern void free_vm_area(struct vm_struct *area);
 
 /* for /dev/kmem */
diff --git a/mm/nommu.c b/mm/nommu.c
index 73419c5..b982290 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 b669aa6..3231bf3 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);