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>hifive-unleashed-5.1
parent
1ea6b8f489
commit
cd12909cb5
|
@ -71,7 +71,7 @@ int arch_gnttab_map_shared(unsigned long *frames, unsigned long nr_gframes,
|
||||||
|
|
||||||
if (shared == NULL) {
|
if (shared == NULL) {
|
||||||
struct vm_struct *area =
|
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);
|
BUG_ON(area == NULL);
|
||||||
shared = area->addr;
|
shared = area->addr;
|
||||||
*__shared = shared;
|
*__shared = shared;
|
||||||
|
|
|
@ -35,6 +35,7 @@
|
||||||
#include <linux/vmalloc.h>
|
#include <linux/vmalloc.h>
|
||||||
#include <linux/export.h>
|
#include <linux/export.h>
|
||||||
#include <asm/xen/hypervisor.h>
|
#include <asm/xen/hypervisor.h>
|
||||||
|
#include <asm/xen/page.h>
|
||||||
#include <xen/interface/xen.h>
|
#include <xen/interface/xen.h>
|
||||||
#include <xen/interface/event_channel.h>
|
#include <xen/interface/event_channel.h>
|
||||||
#include <xen/events.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)
|
int xenbus_map_ring_valloc(struct xenbus_device *dev, int gnt_ref, void **vaddr)
|
||||||
{
|
{
|
||||||
struct gnttab_map_grant_ref op = {
|
struct gnttab_map_grant_ref op = {
|
||||||
.flags = GNTMAP_host_map,
|
.flags = GNTMAP_host_map | GNTMAP_contains_pte,
|
||||||
.ref = gnt_ref,
|
.ref = gnt_ref,
|
||||||
.dom = dev->otherend_id,
|
.dom = dev->otherend_id,
|
||||||
};
|
};
|
||||||
struct vm_struct *area;
|
struct vm_struct *area;
|
||||||
|
pte_t *pte;
|
||||||
|
|
||||||
*vaddr = NULL;
|
*vaddr = NULL;
|
||||||
|
|
||||||
area = alloc_vm_area(PAGE_SIZE);
|
area = alloc_vm_area(PAGE_SIZE, &pte);
|
||||||
if (!area)
|
if (!area)
|
||||||
return -ENOMEM;
|
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))
|
if (HYPERVISOR_grant_table_op(GNTTABOP_map_grant_ref, &op, 1))
|
||||||
BUG();
|
BUG();
|
||||||
|
@ -527,6 +529,7 @@ int xenbus_unmap_ring_vfree(struct xenbus_device *dev, void *vaddr)
|
||||||
struct gnttab_unmap_grant_ref op = {
|
struct gnttab_unmap_grant_ref op = {
|
||||||
.host_addr = (unsigned long)vaddr,
|
.host_addr = (unsigned long)vaddr,
|
||||||
};
|
};
|
||||||
|
unsigned int level;
|
||||||
|
|
||||||
/* It'd be nice if linux/vmalloc.h provided a find_vm_area(void *addr)
|
/* 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.
|
* 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.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))
|
if (HYPERVISOR_grant_table_op(GNTTABOP_unmap_grant_ref, &op, 1))
|
||||||
BUG();
|
BUG();
|
||||||
|
|
|
@ -119,7 +119,7 @@ unmap_kernel_range(unsigned long addr, unsigned long size)
|
||||||
#endif
|
#endif
|
||||||
|
|
||||||
/* Allocate/destroy a 'vmalloc' VM area. */
|
/* 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);
|
extern void free_vm_area(struct vm_struct *area);
|
||||||
|
|
||||||
/* for /dev/kmem */
|
/* for /dev/kmem */
|
||||||
|
|
|
@ -454,7 +454,7 @@ void __attribute__((weak)) vmalloc_sync_all(void)
|
||||||
* between processes, it syncs the pagetable across all
|
* between processes, it syncs the pagetable across all
|
||||||
* processes.
|
* processes.
|
||||||
*/
|
*/
|
||||||
struct vm_struct *alloc_vm_area(size_t size)
|
struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
|
||||||
{
|
{
|
||||||
BUG();
|
BUG();
|
||||||
return NULL;
|
return NULL;
|
||||||
|
|
27
mm/vmalloc.c
27
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)
|
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;
|
return 0;
|
||||||
}
|
}
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* alloc_vm_area - allocate a range of kernel address space
|
* alloc_vm_area - allocate a range of kernel address space
|
||||||
* @size: size of the area
|
* @size: size of the area
|
||||||
|
* @ptes: returns the PTEs for the address space
|
||||||
*
|
*
|
||||||
* Returns: NULL on failure, vm_struct on success
|
* Returns: NULL on failure, vm_struct on success
|
||||||
*
|
*
|
||||||
* This function reserves a range of kernel address space, and
|
* This function reserves a range of kernel address space, and
|
||||||
* allocates pagetables to map that range. No actual mappings
|
* allocates pagetables to map that range. No actual mappings
|
||||||
* are created. If the kernel address space is not shared
|
* are created.
|
||||||
* between processes, it syncs the pagetable across all
|
*
|
||||||
* processes.
|
* 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;
|
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.
|
* of kernel virtual address space and mapped into init_mm.
|
||||||
*/
|
*/
|
||||||
if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
|
if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
|
||||||
area->size, f, NULL)) {
|
size, f, ptes ? &ptes : NULL)) {
|
||||||
free_vm_area(area);
|
free_vm_area(area);
|
||||||
return NULL;
|
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;
|
return area;
|
||||||
}
|
}
|
||||||
EXPORT_SYMBOL_GPL(alloc_vm_area);
|
EXPORT_SYMBOL_GPL(alloc_vm_area);
|
||||||
|
|
Loading…
Reference in New Issue