x86/setup: move vm_init() before acpi calls

For direct map removal and also for live update, we want to be able
to use vmap() early. Make it capable of using the boot allocator for
its page tables and data structures, and call vm_init() earlier in boot.

Combined effort from Wei, Hongyan and David.

Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David Woodhouse <dwmw2@amazon.co.uk>
Signed-off-by: Hongyan Xia <hongyxia@amazon.com>

diff --git a/xen/arch/arm/setup.c b/xen/arch/arm/setup.c
index 7968cee47d059f0099ced521bc75ab09509bc5b3..8f0ac87419ef7431311b3480c62b9b6d79d62a5c 100644 (file)
--- a/xen/arch/arm/setup.c
+++ b/xen/arch/arm/setup.c
@@ -822,6 +822,8 @@ void __init start_xen(unsigned long boot_phys_offset,
 
     setup_mm();
 
+    vm_init();
+
     /* Parse the ACPI tables for possible boot-time configuration */
     acpi_boot_table_init();
 
@@ -833,8 +835,6 @@ void __init start_xen(unsigned long boot_phys_offset,
      */
     system_state = SYS_STATE_boot;
 
-    vm_init();
-
     if ( acpi_disabled )
     {
         printk("Booting using Device Tree\n");

diff --git a/xen/arch/x86/setup.c b/xen/arch/x86/setup.c
index 72724ffe6fce0a22a3f7b04add5052e198f74d54..30068eace2ebe0039ea956f4da467aef7434b3a3 100644 (file)
--- a/xen/arch/x86/setup.c
+++ b/xen/arch/x86/setup.c
@@ -778,6 +778,7 @@ void __init noreturn __start_xen(unsigned long mbi_p)
     unsigned long nr_pages, raw_max_page, modules_headroom, module_map[1];
     int i, j, e820_warn = 0, bytes = 0;
     bool acpi_boot_table_init_done = false, relocated = false;
+    bool vm_init_done = false;
     int ret;
     struct ns16550_defaults ns16550 = {
         .data_bits = 8,
@@ -1384,12 +1385,23 @@ void __init noreturn __start_xen(unsigned long mbi_p)
             continue;
 
         if ( !acpi_boot_table_init_done &&
-             s >= (1ULL << 32) &&
-             !acpi_boot_table_init() )
+             s >= (1ULL << 32) )
         {
-            acpi_boot_table_init_done = true;
-            srat_parse_regions(s);
-            setup_max_pdx(raw_max_page);
+            /*
+             * We only initialise vmap and acpi after going through the bottom
+             * 4GiB, so that we have enough pages in the boot allocator.
+             */
+            if ( !vm_init_done )
+            {
+                vm_init();
+                vm_init_done = true;
+            }
+            if ( !acpi_boot_table_init() )
+            {
+                acpi_boot_table_init_done = true;
+                srat_parse_regions(s);
+                setup_max_pdx(raw_max_page);
+            }
         }
 
         if ( pfn_to_pdx((e - 1) >> PAGE_SHIFT) >= max_pdx )
@@ -1566,6 +1578,9 @@ void __init noreturn __start_xen(unsigned long mbi_p)
 
     init_frametable();
 
+    if ( !vm_init_done )
+        vm_init();
+
     if ( !acpi_boot_table_init_done )
         acpi_boot_table_init();
 
@@ -1603,12 +1618,6 @@ void __init noreturn __start_xen(unsigned long mbi_p)
         end_boot_allocator();
 
     system_state = SYS_STATE_boot;
-    /*
-     * No calls involving ACPI code should go between the setting of
-     * SYS_STATE_boot and vm_init() (or else acpi_os_{,un}map_memory()
-     * will break).
-     */
-    vm_init();
 
     console_init_ring();
     vesa_init();

diff --git a/xen/common/vmap.c b/xen/common/vmap.c
index faebc1ddf1145210d95144606107a0a16c9c561e..15c21bae776fae894db5f3dd2ab206ddf9c0a348 100644 (file)
--- a/xen/common/vmap.c
+++ b/xen/common/vmap.c
@@ -34,9 +34,20 @@ void __init vm_init_type(enum vmap_region type, void *start, void *end)
 
     for ( i = 0, va = (unsigned long)vm_bitmap(type); i < nr; ++i, va += PAGE_SIZE )
     {
-        struct page_info *pg = alloc_domheap_page(NULL, 0);
+        mfn_t mfn;
+        int rc;
 
-        map_pages_to_xen(va, page_to_mfn(pg), 1, PAGE_HYPERVISOR);
+        if ( system_state == SYS_STATE_early_boot )
+            mfn = alloc_boot_pages(1, 1);
+        else
+        {
+            struct page_info *pg = alloc_domheap_page(NULL, 0);
+
+            BUG_ON(!pg);
+            mfn = page_to_mfn(pg);
+        }
+        rc = map_pages_to_xen(va, mfn, 1, PAGE_HYPERVISOR);
+        BUG_ON(rc);
         clear_page((void *)va);
     }
     bitmap_fill(vm_bitmap(type), vm_low[type]);
@@ -62,7 +73,7 @@ static void *vm_alloc(unsigned int nr, unsigned int align,
     spin_lock(&vm_lock);
     for ( ; ; )
     {
-        struct page_info *pg;
+        mfn_t mfn;
 
         ASSERT(vm_low[t] == vm_top[t] || !test_bit(vm_low[t], vm_bitmap(t)));
         for ( start = vm_low[t]; start < vm_top[t]; )
@@ -97,9 +108,16 @@ static void *vm_alloc(unsigned int nr, unsigned int align,
         if ( vm_top[t] >= vm_end[t] )
             return NULL;
 
-        pg = alloc_domheap_page(NULL, 0);
-        if ( !pg )
-            return NULL;
+        if ( system_state == SYS_STATE_early_boot )
+            mfn = alloc_boot_pages(1, 1);
+        else
+        {
+            struct page_info *pg = alloc_domheap_page(NULL, 0);
+
+            if ( !pg )
+                return NULL;
+            mfn = page_to_mfn(pg);
+        }
 
         spin_lock(&vm_lock);
 
@@ -107,7 +125,7 @@ static void *vm_alloc(unsigned int nr, unsigned int align,
         {
             unsigned long va = (unsigned long)vm_bitmap(t) + vm_top[t] / 8;
 
-            if ( !map_pages_to_xen(va, page_to_mfn(pg), 1, PAGE_HYPERVISOR) )
+            if ( !map_pages_to_xen(va, mfn, 1, PAGE_HYPERVISOR) )
             {
                 clear_page((void *)va);
                 vm_top[t] += PAGE_SIZE * 8;
@@ -117,7 +135,10 @@ static void *vm_alloc(unsigned int nr, unsigned int align,
             }
         }
 
-        free_domheap_page(pg);
+        if ( system_state == SYS_STATE_early_boot )
+            init_boot_pages(mfn_to_maddr(mfn), mfn_to_maddr(mfn) + PAGE_SIZE);
+        else
+            free_domheap_page(mfn_to_page(mfn));
 
         if ( start >= vm_top[t] )
         {