On Tue, Sep 06, 2011 at 12:35:53PM -0400, Konrad Rzeszutek Wilk wrote:
> On Fri, Sep 02, 2011 at 03:32:04PM -0700, Andrew Morton wrote:
> > On Fri, 2 Sep 2011 12:39:19 +0100
> > David Vrabel <david.vrabel@xxxxxxxxxx> wrote:
> >
> > > Xen backend drivers (e.g., blkback and netback) would sometimes fail
> > > to map grant pages into the vmalloc address space allocated with
> > > alloc_vm_area(). The GNTTABOP_map_grant_ref would fail because Xen
> > > could not find the page (in the L2 table) containing the PTEs it
> > > needed to update.
> > >
> > > (XEN) mm.c:3846:d0 Could not find L1 PTE for address fbb42000
> > >
> > > netback and blkback were making the hypercall from a kernel thread
> > > where task->active_mm != &init_mm and alloc_vm_area() was only
> > > updating the page tables for init_mm. The usual method of deferring
> > > the update to the page tables of other processes (i.e., after taking a
> > > fault) doesn't work as a fault cannot occur during the hypercall.
> > >
> > > This would work on some systems depending on what else was using
> > > vmalloc.
> > >
> > > Fix this by reverting ef691947d8a3d479e67652312783aedcf629320a
> > > (vmalloc: remove vmalloc_sync_all() from alloc_vm_area()) and add a
> > > comment to explain why it's needed.
> >
> > oookay, I queued this for 3.1 and tagged it for a 3.0.x backport. I
> > *think* that's the outcome of this discussion, for the short-term?
>
> <nods> Yup. Thanks!
Hey Andrew,
The long term outcome is the patchset that David worked on. I've sent
a GIT PULL to Linus to pick up the Xen related patches that switch over
the users of the right API:
(xen) stable/vmalloc-3.2 for Linux 3.2-rc0
(https://lkml.org/lkml/2011/10/29/82)
And then on top of that use this patch:
[Note, I am still waiting for Linus to pull that patchset above.. so not
sure on the outcome. perhaps a better way would be for you to pull
all patches in your tree?]
Also, not sure what you thought of this patch below?
>From b9acd3abc12972be0d938d7bc2466d899023e757 Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@xxxxxxxxxx>
Date: Thu, 29 Sep 2011 16:53:32 +0100
Subject: [PATCH] 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@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Jeremy Fitzhardinge <jeremy@xxxxxxxx>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@xxxxxxxxxx>
---
arch/x86/xen/grant-table.c | 2 +-
drivers/xen/xenbus/xenbus_client.c | 11 ++++++++---
include/linux/vmalloc.h | 2 +-
mm/vmalloc.c | 27 +++++++++++++--------------
4 files changed, 23 insertions(+), 19 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 229d3ad..52bc57f 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -34,6 +34,7 @@
#include <linux/types.h>
#include <linux/vmalloc.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>
@@ -435,19 +436,20 @@ 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();
@@ -526,6 +528,7 @@ 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.
@@ -547,6 +550,8 @@ 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 9332e52..1a77252 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -118,7 +118,7 @@ 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/vmalloc.c b/mm/vmalloc.c
index 5016f19..b5deec6 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2105,23 +2105,30 @@ 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;
@@ -2135,19 +2142,11 @@ 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);
--
1.7.7.1
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel
|
Home