1 files changed, 26 insertions, 45 deletions

diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index b1dbdaa23ecc..b5a7f928234b 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -23,7 +23,6 @@
 #include <xen/interface/callback.h>
 #include <xen/interface/memory.h>
 #include <xen/interface/physdev.h>
-#include <xen/interface/memory.h>
 #include <xen/features.h>
 
 #include "xen-ops.h"
@@ -118,16 +117,18 @@ static unsigned long __init xen_return_unused_memory(unsigned long max_pfn,
                                                      const struct e820map *e820)
 {
         phys_addr_t max_addr = PFN_PHYS(max_pfn);
-        phys_addr_t last_end = 0;
+        phys_addr_t last_end = ISA_END_ADDRESS;
         unsigned long released = 0;
         int i;
 
+        /* Free any unused memory above the low 1Mbyte. */
         for (i = 0; i < e820->nr_map && last_end < max_addr; i++) {
                 phys_addr_t end = e820->map[i].addr;
                 end = min(max_addr, end);
 
-                released += xen_release_chunk(last_end, end);
-                last_end = e820->map[i].addr + e820->map[i].size;
+                if (last_end < end)
+                        released += xen_release_chunk(last_end, end);
+                last_end = max(last_end, e820->map[i].addr + e820->map[i].size);
         }
 
         if (last_end < max_addr)
@@ -164,6 +165,7 @@ char * __init xen_memory_setup(void)
                 XENMEM_memory_map;
         rc = HYPERVISOR_memory_op(op, &memmap);
         if (rc == -ENOSYS) {
+                BUG_ON(xen_initial_domain());
                 memmap.nr_entries = 1;
                 map[0].addr = 0ULL;
                 map[0].size = mem_end;
@@ -179,34 +181,32 @@ char * __init xen_memory_setup(void)
         for (i = 0; i < memmap.nr_entries; i++) {
                 unsigned long long end = map[i].addr + map[i].size;
 
-                if (map[i].type == E820_RAM) {
-                        if (map[i].addr < mem_end && end > mem_end) {
-                                /* Truncate region to max_mem. */
-                                u64 delta = end - mem_end;
+                if (map[i].type == E820_RAM && end > mem_end) {
+                        /* RAM off the end - may be partially included */
+                        u64 delta = min(map[i].size, end - mem_end);
 
-                                map[i].size -= delta;
-                                extra_pages += PFN_DOWN(delta);
+                        map[i].size -= delta;
+                        end -= delta;
 
-                                end = mem_end;
-                        }
+                        extra_pages += PFN_DOWN(delta);
                 }
 
-                if (end > xen_extra_mem_start)
+                if (map[i].size > 0 && end > xen_extra_mem_start)
                         xen_extra_mem_start = end;
 
-                /* If region is non-RAM or below mem_end, add what remains */
-                if ((map[i].type != E820_RAM || map[i].addr < mem_end) &&
-                    map[i].size > 0)
+                /* Add region if any remains */
+                if (map[i].size > 0)
                         e820_add_region(map[i].addr, map[i].size, map[i].type);
         }
 
         /*
-         * Even though this is normal, usable memory under Xen, reserve
-         * ISA memory anyway because too many things think they can poke
+         * In domU, the ISA region is normal, usable memory, but we
+         * reserve ISA memory anyway because too many things poke
          * about in there.
          *
-         * In a dom0 kernel, this region is identity mapped with the
-         * hardware ISA area, so it really is out of bounds.
+         * In Dom0, the host E820 information can leave gaps in the
+         * ISA range, which would cause us to release those pages.  To
+         * avoid this, we unconditionally reserve them here.
          */
         e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
                         E820_RESERVED);
@@ -244,26 +244,11 @@ char * __init xen_memory_setup(void)
         else
                 extra_pages = 0;
 
-        if (!xen_initial_domain())
-                xen_add_extra_mem(extra_pages);
+        xen_add_extra_mem(extra_pages);
 
         return "Xen";
 }
 
-static void xen_idle(void)
-{
-        local_irq_disable();
-
-        if (need_resched())
-                local_irq_enable();
-        else {
-                current_thread_info()->status &= ~TS_POLLING;
-                smp_mb__after_clear_bit();
-                safe_halt();
-                current_thread_info()->status |= TS_POLLING;
-        }
-}
-
 /*
  * Set the bit indicating "nosegneg" library variants should be used.
  * We only need to bother in pure 32-bit mode; compat 32-bit processes
@@ -333,9 +318,6 @@ void __cpuinit xen_enable_syscall(void)
 
 void __init xen_arch_setup(void)
 {
-        struct physdev_set_iopl set_iopl;
-        int rc;
-
         xen_panic_handler_init();
 
         HYPERVISOR_vm_assist(VMASST_CMD_enable, VMASST_TYPE_4gb_segments);
@@ -352,11 +334,6 @@ void __init xen_arch_setup(void)
         xen_enable_sysenter();
         xen_enable_syscall();
 
-        set_iopl.iopl = 1;
-        rc = HYPERVISOR_physdev_op(PHYSDEVOP_set_iopl, &set_iopl);
-        if (rc != 0)
-                printk(KERN_INFO "physdev_op failed %d\n", rc);
-
 #ifdef CONFIG_ACPI
         if (!(xen_start_info->flags & SIF_INITDOMAIN)) {
                 printk(KERN_INFO "ACPI in unprivileged domain disabled\n");
@@ -368,7 +345,11 @@ void __init xen_arch_setup(void)
                MAX_GUEST_CMDLINE > COMMAND_LINE_SIZE ?
                COMMAND_LINE_SIZE : MAX_GUEST_CMDLINE);
 
-        pm_idle = xen_idle;
+        /* Set up idle, making sure it calls safe_halt() pvop */
+#ifdef CONFIG_X86_32
+        boot_cpu_data.hlt_works_ok = 1;
+#endif
+        pm_idle = default_idle;
 
         fiddle_vdso();
 }