5 files changed, 54 insertions, 2 deletions

diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 7db7723d1f32..d56187c6b838 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -299,6 +299,7 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 /* Install a pte for a particular vaddr in kernel space. */
 void set_pte_vaddr(unsigned long vaddr, pte_t pte);
 
+extern void native_pagetable_reserve(u64 start, u64 end);
 #ifdef CONFIG_X86_32
 extern void native_pagetable_setup_start(pgd_t *base);
 extern void native_pagetable_setup_done(pgd_t *base);
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 643ebf2e2ad8..d3d859035af9 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -68,6 +68,17 @@ struct x86_init_oem {
 };
 
 /**
+ * struct x86_init_mapping - platform specific initial kernel pagetable setup
+ * @pagetable_reserve:  reserve a range of addresses for kernel pagetable usage
+ *
+ * For more details on the purpose of this hook, look in
+ * init_memory_mapping and the commit that added it.
+ */
+struct x86_init_mapping {
+        void (*pagetable_reserve)(u64 start, u64 end);
+};
+
+/**
  * struct x86_init_paging - platform specific paging functions
  * @pagetable_setup_start:      platform specific pre paging_init() call
  * @pagetable_setup_done:       platform specific post paging_init() call
@@ -123,6 +134,7 @@ struct x86_init_ops {
         struct x86_init_mpparse         mpparse;
         struct x86_init_irqs            irqs;
         struct x86_init_oem             oem;
+        struct x86_init_mapping         mapping;
         struct x86_init_paging          paging;
         struct x86_init_timers          timers;
         struct x86_init_iommu           iommu;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index c11514e9128b..75ef4b18e9b7 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -61,6 +61,10 @@ struct x86_init_ops x86_init __initdata = {
                 .banner                 = default_banner,
         },
 
+        .mapping = {
+                .pagetable_reserve              = native_pagetable_reserve,
+        },
+
         .paging = {
                 .pagetable_setup_start  = native_pagetable_setup_start,
                 .pagetable_setup_done   = native_pagetable_setup_done,
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 286d289b039b..722a4c372ce3 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -81,6 +81,11 @@ static void __init find_early_table_space(unsigned long end, int use_pse,
                 end, pgt_buf_start << PAGE_SHIFT, pgt_buf_top << PAGE_SHIFT);
 }
 
+void native_pagetable_reserve(u64 start, u64 end)
+{
+        memblock_x86_reserve_range(start, end, "PGTABLE");
+}
+
 struct map_range {
         unsigned long start;
         unsigned long end;
@@ -272,9 +277,24 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 
         __flush_tlb_all();
 
+        /*
+         * Reserve the kernel pagetable pages we used (pgt_buf_start -
+         * pgt_buf_end) and free the other ones (pgt_buf_end - pgt_buf_top)
+         * so that they can be reused for other purposes.
+         *
+         * On native it just means calling memblock_x86_reserve_range, on Xen it
+         * also means marking RW the pagetable pages that we allocated before
+         * but that haven't been used.
+         *
+         * In fact on xen we mark RO the whole range pgt_buf_start -
+         * pgt_buf_top, because we have to make sure that when
+         * init_memory_mapping reaches the pagetable pages area, it maps
+         * RO all the pagetable pages, including the ones that are beyond
+         * pgt_buf_end at that time.
+         */
         if (!after_bootmem && pgt_buf_end > pgt_buf_start)
-                memblock_x86_reserve_range(pgt_buf_start << PAGE_SHIFT,
-                                 pgt_buf_end << PAGE_SHIFT, "PGTABLE");
+                x86_init.mapping.pagetable_reserve(PFN_PHYS(pgt_buf_start),
+                                PFN_PHYS(pgt_buf_end));
 
         if (!after_bootmem)
                 early_memtest(start, end);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index cf4ef61e425b..0684f3c74d53 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1275,6 +1275,20 @@ static __init void xen_pagetable_setup_start(pgd_t *base)
 {
 }
 
+static __init void xen_mapping_pagetable_reserve(u64 start, u64 end)
+{
+        /* reserve the range used */
+        native_pagetable_reserve(start, end);
+
+        /* set as RW the rest */
+        printk(KERN_DEBUG "xen: setting RW the range %llx - %llx\n", end,
+                        PFN_PHYS(pgt_buf_top));
+        while (end < PFN_PHYS(pgt_buf_top)) {
+                make_lowmem_page_readwrite(__va(end));
+                end += PAGE_SIZE;
+        }
+}
+
 static void xen_post_allocator_init(void);
 
 static __init void xen_pagetable_setup_done(pgd_t *base)
@@ -2105,6 +2119,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 void __init xen_init_mmu_ops(void)
 {
+        x86_init.mapping.pagetable_reserve = xen_mapping_pagetable_reserve;
         x86_init.paging.pagetable_setup_start = xen_pagetable_setup_start;
         x86_init.paging.pagetable_setup_done = xen_pagetable_setup_done;
         pv_mmu_ops = xen_mmu_ops;