xen: correctly rebuild mfn list list after migration.
Otherwise the second migration attempt fails because the mfn_list_list
still refers to all the old mfns.
We need to update the entires in both p2m_top_mfn and the mid_mfn
pages which p2m_top_mfn refers to.
In order to do this we need to keep track of the virtual addresses
mapping the p2m_mid_mfn pages since we cannot rely on
mfn_to_virt(p2m_top_mfn[idx]) since p2m_top_mfn[idx] will still
contain the old MFN after a migration, which may now belong to another
domain and hence have a different mapping in the m2p.
Therefore add and maintain a third top level page, p2m_top_mfn_p[],
which tracks the virtual addresses of the mfns contained in
p2m_top_mfn[].
We also need to update the content of the p2m_mid_missing_mfn page on
resume to refer to the page's new mfn.
p2m_missing does not need updating since the migration process takes
care of the leaf p2m pages for us.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 67b4101..e41683c 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -187,6 +187,8 @@
* / \ / \ / /
* p2m p2m p2m p2m p2m p2m p2m ...
*
+ * The p2m_mid_mfn pages are mapped by p2m_top_mfn_p.
+ *
* The p2m_top and p2m_top_mfn levels are limited to 1 page, so the
* maximum representable pseudo-physical address space is:
* P2M_TOP_PER_PAGE * P2M_MID_PER_PAGE * P2M_PER_PAGE pages
@@ -211,6 +213,7 @@
static RESERVE_BRK_ARRAY(unsigned long **, p2m_top, P2M_TOP_PER_PAGE);
static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE);
+static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE);
RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE)));
@@ -247,6 +250,14 @@
top[i] = virt_to_mfn(p2m_mid_missing_mfn);
}
+static void p2m_top_mfn_p_init(unsigned long **top)
+{
+ unsigned i;
+
+ for (i = 0; i < P2M_TOP_PER_PAGE; i++)
+ top[i] = p2m_mid_missing_mfn;
+}
+
static void p2m_mid_init(unsigned long **mid)
{
unsigned i;
@@ -283,33 +294,43 @@
*/
void xen_build_mfn_list_list(void)
{
- unsigned pfn;
+ unsigned long pfn;
/* Pre-initialize p2m_top_mfn to be completely missing */
if (p2m_top_mfn == NULL) {
p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_mid_mfn_init(p2m_mid_missing_mfn);
+ p2m_top_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
+ p2m_top_mfn_p_init(p2m_top_mfn_p);
+
p2m_top_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_top_mfn_init(p2m_top_mfn);
+ } else {
+ /* Reinitialise, mfn's all change after migration */
+ p2m_mid_mfn_init(p2m_mid_missing_mfn);
}
for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) {
unsigned topidx = p2m_top_index(pfn);
unsigned mididx = p2m_mid_index(pfn);
unsigned long **mid;
- unsigned long mid_mfn;
unsigned long *mid_mfn_p;
mid = p2m_top[topidx];
+ mid_mfn_p = p2m_top_mfn_p[topidx];
/* Don't bother allocating any mfn mid levels if
- they're just missing */
- if (mid[mididx] == p2m_missing)
+ * they're just missing, just update the stored mfn,
+ * since all could have changed over a migrate.
+ */
+ if (mid == p2m_mid_missing) {
+ BUG_ON(mididx);
+ BUG_ON(mid_mfn_p != p2m_mid_missing_mfn);
+ p2m_top_mfn[topidx] = virt_to_mfn(p2m_mid_missing_mfn);
+ pfn += (P2M_MID_PER_PAGE - 1) * P2M_PER_PAGE;
continue;
-
- mid_mfn = p2m_top_mfn[topidx];
- mid_mfn_p = mfn_to_virt(mid_mfn);
+ }
if (mid_mfn_p == p2m_mid_missing_mfn) {
/*
@@ -321,11 +342,10 @@
mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE);
p2m_mid_mfn_init(mid_mfn_p);
- mid_mfn = virt_to_mfn(mid_mfn_p);
-
- p2m_top_mfn[topidx] = mid_mfn;
+ p2m_top_mfn_p[topidx] = mid_mfn_p;
}
+ p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p);
mid_mfn_p[mididx] = virt_to_mfn(mid[mididx]);
}
}
@@ -344,7 +364,7 @@
{
unsigned long *mfn_list = (unsigned long *)xen_start_info->mfn_list;
unsigned long max_pfn = min(MAX_DOMAIN_PAGES, xen_start_info->nr_pages);
- unsigned pfn;
+ unsigned long pfn;
xen_max_p2m_pfn = max_pfn;
@@ -434,7 +454,9 @@
}
top_mfn_p = &p2m_top_mfn[topidx];
- mid_mfn = mfn_to_virt(*top_mfn_p);
+ mid_mfn = p2m_top_mfn_p[topidx];
+
+ BUG_ON(virt_to_mfn(mid_mfn) != *top_mfn_p);
if (mid_mfn == p2m_mid_missing_mfn) {
/* Separately check the mid mfn level */
@@ -446,11 +468,13 @@
return false;
p2m_mid_mfn_init(mid_mfn);
-
+
missing_mfn = virt_to_mfn(p2m_mid_missing_mfn);
mid_mfn_mfn = virt_to_mfn(mid_mfn);
if (cmpxchg(top_mfn_p, missing_mfn, mid_mfn_mfn) != missing_mfn)
free_p2m_page(mid_mfn);
+ else
+ p2m_top_mfn_p[topidx] = mid_mfn;
}
if (p2m_top[topidx][mididx] == p2m_missing) {
