xen: Add populate_pt_range interface to reserve non-leaf level table entries

On x86, for the pages mapped with PAGE_HYPERVISOR attribute
non-leaf page tables are allocated with valid pte entries.
and with MAP_SMALL_PAGES attribute only non-leaf page tables are
allocated with invalid (valid bit set to 0) pte entries.
However on arm this is not the case. On arm for the pages
mapped with PAGE_HYPERVISOR and MAP_SMALL_PAGES both
non-leaf and leaf level page table are allocated with valid bit
in pte entries.

This behaviour in arm makes common vmap code fail to
allocate memory beyond 128MB as described below.

In vm_init, map_pages_to_xen() is called for mapping
vm_bitmap. Initially one page of vm_bitmap is allocated
and mapped using PAGE_HYPERVISOR attribute.
For the rest of vm_bitmap pages, MAP_SMALL_PAGES attribute
is used to map.

In ARM for both PAGE_HYPERVISOR and MAP_SMALL_PAGES, valid bit
is set to 1 in pte entry for these mapping.

In vm_alloc(), map_pages_to_xen() is failing for >128MB because
for this next vm_bitmap page the mapping is already set in vm_init()
with valid bit set in pte entry. So map_pages_to_xen() in
ARM returns error.

With this patch, MAP_SMALL_PAGES is dropped and arch specific
populate_pt_range() api is introduced to populate non-leaf
page table entries for the requested pages. Added RESERVE option
to map non-leaf page table entries.

Signed-off-by: Vijaya Kumar K<Vijaya.Kumar@caviumnetworks.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
[ ijc -- rewrote subject line ]

diff --git a/xen/arch/arm/mm.c b/xen/arch/arm/mm.c
index 7d4ba0cf553a2152020100b23499c15c425f2fe5..d103f8feab88f4b9da4c992e043ccfc16f68a53d 100644 (file)
--- a/xen/arch/arm/mm.c
+++ b/xen/arch/arm/mm.c
@@ -827,7 +827,8 @@ static int create_xen_table(lpae_t *entry)
 
 enum xenmap_operation {
     INSERT,
-    REMOVE
+    REMOVE,
+    RESERVE
 };
 
 static int create_xen_entries(enum xenmap_operation op,
@@ -859,12 +860,15 @@ static int create_xen_entries(enum xenmap_operation op,
 
         switch ( op ) {
             case INSERT:
+            case RESERVE:
                 if ( third[third_table_offset(addr)].pt.valid )
                 {
                     printk("create_xen_entries: trying to replace an existing mapping addr=%lx mfn=%lx\n",
                            addr, mfn);
                     return -EINVAL;
                 }
+                if ( op == RESERVE )
+                    break;
                 pte = mfn_to_xen_entry(mfn, ai);
                 pte.pt.table = 1;
                 write_pte(&third[third_table_offset(addr)], pte);
@@ -898,6 +902,13 @@ int map_pages_to_xen(unsigned long virt,
 {
     return create_xen_entries(INSERT, virt, mfn, nr_mfns, flags);
 }
+
+int populate_pt_range(unsigned long virt, unsigned long mfn,
+                      unsigned long nr_mfns)
+{
+    return create_xen_entries(RESERVE, virt, mfn, nr_mfns, 0);
+}
+
 void destroy_xen_mappings(unsigned long v, unsigned long e)
 {
     create_xen_entries(REMOVE, v, 0, (e - v) >> PAGE_SHIFT, 0);

diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 8e29675582b9e299ec54785234539174245305d0..786ed4733179121a3c89bb0abb7725871d641402 100644 (file)
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -5725,6 +5725,12 @@ int map_pages_to_xen(
     return 0;
 }
 
+int populate_pt_range(unsigned long virt, unsigned long mfn,
+                      unsigned long nr_mfns)
+{
+    return map_pages_to_xen(virt, mfn, nr_mfns, MAP_SMALL_PAGES);
+}
+
 void destroy_xen_mappings(unsigned long s, unsigned long e)
 {
     bool_t locking = system_state > SYS_STATE_boot;

diff --git a/xen/common/vmap.c b/xen/common/vmap.c
index 783cea3fd8b12ce5ac66ea25eee94855881028ec..739d468df882f66f9c3be014b0fec01e5b1a96da 100644 (file)
--- a/xen/common/vmap.c
+++ b/xen/common/vmap.c
@@ -40,7 +40,7 @@ void __init vm_init(void)
     bitmap_fill(vm_bitmap, vm_low);
 
     /* Populate page tables for the bitmap if necessary. */
-    map_pages_to_xen(va, 0, vm_low - nr, MAP_SMALL_PAGES);
+    populate_pt_range(va, 0, vm_low - nr);
 }
 
 void *vm_alloc(unsigned int nr, unsigned int align)

diff --git a/xen/include/asm-arm/page.h b/xen/include/asm-arm/page.h
index 3e7b0ae7513f361743099b5bc789da9fd4c3b80f..8de5e26111431fbc0bd33b774d802cf7eaec27a3 100644 (file)
--- a/xen/include/asm-arm/page.h
+++ b/xen/include/asm-arm/page.h
@@ -64,7 +64,6 @@
 #define PAGE_HYPERVISOR         (WRITEALLOC)
 #define PAGE_HYPERVISOR_NOCACHE (DEV_SHARED)
 #define PAGE_HYPERVISOR_WC      (DEV_WC)
-#define MAP_SMALL_PAGES         PAGE_HYPERVISOR
 
 /*
  * Stage 2 Memory Type.

diff --git a/xen/include/xen/mm.h b/xen/include/xen/mm.h
index a769084d9adb9b00ce97f88eb854c16d204495a5..a06636391b359f41b2232e44c3316610f3fcaf52 100644 (file)
--- a/xen/include/xen/mm.h
+++ b/xen/include/xen/mm.h
@@ -55,7 +55,12 @@ int map_pages_to_xen(
     unsigned long nr_mfns,
     unsigned int flags);
 void destroy_xen_mappings(unsigned long v, unsigned long e);
-
+/*
+ * Create only non-leaf page table entries for the
+ * page range in Xen virtual address space.
+ */
+int populate_pt_range(unsigned long virt, unsigned long mfn,
+                      unsigned long nr_mfns);
 /* Claim handling */
 unsigned long domain_adjust_tot_pages(struct domain *d, long pages);
 int domain_set_outstanding_pages(struct domain *d, unsigned long pages);