x86/boot: Reserve live update boot memory

For live update to work, it will need a region of memory that can be
given to the boot allocator while it parses the state information from
the previous Xen and works out which of the other pages of memory it
can consume.

Reserve that like the crashdump region, and accept it on the command
line. Use only that region for early boot, and register the remaining
RAM (all of it for now, until the real live update happens) later.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>

diff --git a/xen/arch/x86/setup.c b/xen/arch/x86/setup.c
index ffeb887989e8d2318f4dbf44dd43918e1509e073..0374c060e93c9efe9421a55062ab85ed90c117a8 100644 (file)
--- a/xen/arch/x86/setup.c
+++ b/xen/arch/x86/setup.c
@@ -661,6 +661,42 @@ static char * __init cmdline_cook(char *p, const char *loader_name)
     return p;
 }
 
+
+static unsigned long lu_bootmem_start, lu_bootmem_size, lu_data;
+
+static int __init parse_liveupdate(const char *str)
+{
+    const char *cur;
+    lu_bootmem_size = parse_size_and_unit(cur = str, &str);
+    if (!lu_bootmem_size || cur == str)
+        return -EINVAL;
+
+    if (!*str) {
+        printk("Live update size 0x%lx\n", lu_bootmem_size);
+        return 0;
+    }
+    if (*str != '@')
+        return -EINVAL;
+    lu_bootmem_start = parse_size_and_unit(cur = str + 1, &str);
+    if (!lu_bootmem_start || cur == str)
+        return -EINVAL;
+
+    printk("Live update area 0x%lx-0x%lx (0x%lx)\n", lu_bootmem_start,
+           lu_bootmem_start + lu_bootmem_size, lu_bootmem_size);
+
+    if (!*str)
+        return 0;
+    if (*str != ':')
+        return -EINVAL;
+    lu_data = simple_strtoull(cur = str + 1, &str, 0);
+    if (!lu_data || cur == str)
+        return -EINVAL;
+
+    printk("Live update data at 0x%lx\n", lu_data);
+    return 0;
+}
+custom_param("liveupdate", parse_liveupdate);
+
 void __init noreturn __start_xen(unsigned long mbi_p)
 {
     char *memmap_type = NULL;
@@ -670,7 +706,7 @@ void __init noreturn __start_xen(unsigned long mbi_p)
     module_t *mod;
     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 acpi_boot_table_init_done = false, relocated = false, lu_reserved = false;
     struct ns16550_defaults ns16550 = {
         .data_bits = 8,
         .parity    = 'n',
@@ -946,6 +982,22 @@ void __init noreturn __start_xen(unsigned long mbi_p)
     set_kexec_crash_area_size((u64)nr_pages << PAGE_SHIFT);
     kexec_reserve_area(&boot_e820);
 
+    if ( lu_bootmem_start )
+    {
+        /* XX: Check it's in usable memory first */
+        reserve_e820_ram(&boot_e820, lu_bootmem_start, lu_bootmem_start + lu_bootmem_size);
+
+        /* Since it will already be out of the e820 map by the time the first
+         * loop over physical memory, map it manually already. */
+        set_pdx_range(lu_bootmem_start >> PAGE_SHIFT,
+                      (lu_bootmem_start + lu_bootmem_size) >> PAGE_SHIFT);
+        map_pages_to_xen((unsigned long)__va(lu_bootmem_start),
+                         maddr_to_mfn(lu_bootmem_start),
+                         PFN_DOWN(lu_bootmem_size), PAGE_HYPERVISOR);
+
+        lu_reserved = true;
+    }
+
     initial_images = mod;
     nr_initial_images = mbi->mods_count;
 
@@ -1161,6 +1213,16 @@ void __init noreturn __start_xen(unsigned long mbi_p)
             printk("New Xen image base address: %#lx\n", xen_phys_start);
         }
 
+        /* Is the region suitable for the live update bootmem region? */
+        if ( lu_bootmem_size && ! lu_bootmem_start && e < limit )
+        {
+            end = consider_modules(s, e, lu_bootmem_size, mod, mbi->mods_count + relocated, -1);
+            if ( end )
+            {
+                e = lu_bootmem_start = end - lu_bootmem_size;
+            }
+        }
+
         /* Is the region suitable for relocating the multiboot modules? */
         for ( j = mbi->mods_count - 1; j >= 0; j-- )
         {
@@ -1224,6 +1286,15 @@ void __init noreturn __start_xen(unsigned long mbi_p)
     if ( !xen_phys_start )
         panic("Not enough memory to relocate Xen.");
 
+    if ( lu_bootmem_start )
+    {
+        if ( !lu_reserved )
+            reserve_e820_ram(&boot_e820, lu_bootmem_start, lu_bootmem_start + lu_bootmem_size);
+        printk("LU bootmem: 0x%lx - 0x%lx\n", lu_bootmem_start, lu_bootmem_start + lu_bootmem_size);
+        init_boot_pages(lu_bootmem_start, lu_bootmem_start + lu_bootmem_size);
+        lu_reserved = true;
+    }
+
     /* This needs to remain in sync with xen_in_range(). */
     reserve_e820_ram(&boot_e820, __pa(_stext), __pa(__2M_rwdata_end));
 
@@ -1235,8 +1306,8 @@ void __init noreturn __start_xen(unsigned long mbi_p)
         xenheap_max_mfn(PFN_DOWN(highmem_start - 1));
 
     /*
-     * Walk every RAM region and map it in its entirety (on x86/64, at least)
-     * and notify it to the boot allocator.
+     * Walk every RAM region and map it in its entirety and (unless in
+     * live update mode) notify it to the boot allocator.
      */
     for ( i = 0; i < boot_e820.nr_map; i++ )
     {
@@ -1286,6 +1357,7 @@ void __init noreturn __start_xen(unsigned long mbi_p)
                 printk(XENLOG_WARNING "Ignoring inaccessible memory range"
                                       " %013"PRIx64"-%013"PRIx64"\n",
                        s, e);
+                reserve_e820_ram(&boot_e820, s, e);
                 continue;
             }
             map_e = e;
@@ -1293,6 +1365,7 @@ void __init noreturn __start_xen(unsigned long mbi_p)
             printk(XENLOG_WARNING "Ignoring inaccessible memory range"
                                   " %013"PRIx64"-%013"PRIx64"\n",
                    e, map_e);
+            reserve_e820_ram(&boot_e820, e, map_e);
         }
 
         set_pdx_range(s >> PAGE_SHIFT, e >> PAGE_SHIFT);
@@ -1303,7 +1376,9 @@ void __init noreturn __start_xen(unsigned long mbi_p)
                       ARRAY_SIZE(l2_identmap) << L2_PAGETABLE_SHIFT);
 
         /* Pass mapped memory to allocator /before/ creating new mappings. */
-        init_boot_pages(s, min(map_s, e));
+        if ( !lu_reserved)
+            init_boot_pages(s, min(map_s, e));
+
         s = map_s;
         if ( s < map_e )
         {
@@ -1311,7 +1386,8 @@ void __init noreturn __start_xen(unsigned long mbi_p)
 
             map_s = (s + mask) & ~mask;
             map_e &= ~mask;
-            init_boot_pages(map_s, map_e);
+            if ( !lu_reserved)
+                init_boot_pages(map_s, map_e);
         }
 
         if ( map_s > map_e )
@@ -1327,7 +1403,8 @@ void __init noreturn __start_xen(unsigned long mbi_p)
             {
                 map_pages_to_xen((unsigned long)__va(map_e), maddr_to_mfn(map_e),
                                  PFN_DOWN(end - map_e), PAGE_HYPERVISOR);
-                init_boot_pages(map_e, end);
+                if ( !lu_reserved)
+                    init_boot_pages(map_e, end);
                 map_e = end;
             }
         }
@@ -1342,7 +1419,8 @@ void __init noreturn __start_xen(unsigned long mbi_p)
         {
             map_pages_to_xen((unsigned long)__va(s), maddr_to_mfn(s),
                              PFN_DOWN(map_s - s), PAGE_HYPERVISOR);
-            init_boot_pages(s, map_s);
+            if ( !lu_reserved)
+                init_boot_pages(s, map_s);
         }
     }
 
@@ -1440,6 +1518,29 @@ void __init noreturn __start_xen(unsigned long mbi_p)
 
     numa_initmem_init(0, raw_max_page);
 
+    if ( lu_bootmem_start )
+    {
+        unsigned long limit = virt_to_mfn(HYPERVISOR_VIRT_END - 1);
+        uint64_t mask = PAGE_SIZE - 1;
+
+        for ( i = 0; i < boot_e820.nr_map; i++ )
+        {
+            uint64_t s, e;
+
+            if ( boot_e820.map[i].type != E820_RAM )
+                continue;
+            s = (boot_e820.map[i].addr + mask) & ~mask;
+            e = (boot_e820.map[i].addr + boot_e820.map[i].size) & ~mask;
+            s = max_t(uint64_t, s, 1<<20);
+            if ( PFN_DOWN(s) > limit )
+                continue;
+            if ( PFN_DOWN(e) > limit )
+                e = pfn_to_paddr(limit);
+
+            init_boot_pages(s, e);
+        }
+    }
+
     if ( max_page - 1 > virt_to_mfn(HYPERVISOR_VIRT_END - 1) )
     {
         unsigned long limit = virt_to_mfn(HYPERVISOR_VIRT_END - 1);