x86: fix memory cut-off when using PFN compression

For one setup_max_pdx(), when invoked a second time (after SRAT got
parsed), needs to start from the original max_page value again (using
the already adjusted one from the first invocation would not allow the
cut-off boundary to be moved up).

Second, _if_ we need to cut off some part of memory, we must not allow
this to also propagate into the NUMA accounting. Otherwise
cutoff_node() results in nodes_cover_memory() to find some parts of
memory apparently not having a PXM association, causing all SRAT info
to be ignored.

The only possibly problematic consumer of node_spanned_pages (the
meaning of which gets altered here in that it now also includes memory
Xen can't actively make use of) is XEN_SYSCTL_numainfo: At a first
glance the potentially larger reported memory size shouldn't confuse
tool stacks.

And finally we must not put our boot time modules at addresses which
(at that time) can't be guaranteed to be accessible later. This applies
to both the EFI boot loader and the module relocation code.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Keir Fraser <keir@xen.org>
Acked-by: Dario Faggioli <dario.faggioli@citrix.com>
master commit: 8efce9d69998a3d3c720ac7dbdb9b7e240369957
master date: 2013-09-12 09:52:53 +0200

2 files changed, 13 insertions, 9 deletions

diff --git a/xen/arch/x86/efi/boot.c b/xen/arch/x86/efi/boot.c
index 055ac13ce6..66a6fdba21 100644
--- a/xen/arch/x86/efi/boot.c
+++ b/xen/arch/x86/efi/boot.c
@@ -459,7 +459,8 @@ static bool_t __init read_file(EFI_FILE_HANDLE dir_handle, CHAR16 *name,
         what = what ?: L"Seek";
     else
     {
-        file->addr = (EFI_PHYSICAL_ADDRESS)1 << (32 + PAGE_SHIFT);
+        file->addr = min(1UL << (32 + PAGE_SHIFT),
+                         HYPERVISOR_VIRT_END - DIRECTMAP_VIRT_START);
         ret = efi_bs->AllocatePages(AllocateMaxAddress, EfiLoaderData,
                                     PFN_UP(size), &file->addr);
     }
diff --git a/xen/arch/x86/setup.c b/xen/arch/x86/setup.c
index a70d31bbbb..0b92874596 100644
--- a/xen/arch/x86/setup.c
+++ b/xen/arch/x86/setup.c
@@ -377,9 +377,9 @@ static uint64_t __init consider_modules(
     return e;
 }
 
-static void __init setup_max_pdx(void)
+static void __init setup_max_pdx(unsigned long top_page)
 {
-    max_pdx = pfn_to_pdx(max_page - 1) + 1;
+    max_pdx = pfn_to_pdx(top_page - 1) + 1;
 
     if ( max_pdx > (DIRECTMAP_SIZE >> PAGE_SHIFT) )
         max_pdx = DIRECTMAP_SIZE >> PAGE_SHIFT;
@@ -547,7 +547,7 @@ void __init __start_xen(unsigned long mbi_p)
     unsigned int initrdidx;
     multiboot_info_t *mbi = __va(mbi_p);
     module_t *mod = (module_t *)__va(mbi->mods_addr);
-    unsigned long nr_pages, modules_headroom, *module_map;
+    unsigned long nr_pages, raw_max_page, modules_headroom, *module_map;
     int i, j, e820_warn = 0, bytes = 0;
     bool_t acpi_boot_table_init_done = 0;
     struct ns16550_defaults ns16550 = {
@@ -751,7 +751,7 @@ void __init __start_xen(unsigned long mbi_p)
     }
 
     /* Sanitise the raw E820 map to produce a final clean version. */
-    max_page = init_e820(memmap_type, e820_raw, &e820_raw_nr);
+    max_page = raw_max_page = init_e820(memmap_type, e820_raw, &e820_raw_nr);
 
     /* Create a temporary copy of the E820 map. */
     memcpy(&boot_e820, &e820, sizeof(e820));
@@ -820,7 +820,10 @@ void __init __start_xen(unsigned long mbi_p)
                              (end - s) >> PAGE_SHIFT, PAGE_HYPERVISOR);
         }
 
-        e = min_t(uint64_t, e, 1ULL << (PAGE_SHIFT + 32));
+        if ( e > min(HYPERVISOR_VIRT_END - DIRECTMAP_VIRT_START,
+                     1UL << (PAGE_SHIFT + 32)) )
+            e = min(HYPERVISOR_VIRT_END - DIRECTMAP_VIRT_START,
+                    1UL << (PAGE_SHIFT + 32));
 #define reloc_size ((__pa(&_end) + mask) & ~mask)
         /* Is the region suitable for relocating Xen? */
         if ( !xen_phys_start && e <= limit )
@@ -969,7 +972,7 @@ void __init __start_xen(unsigned long mbi_p)
     /* Late kexec reservation (dynamic start address). */
     kexec_reserve_area(&boot_e820);
 
-    setup_max_pdx();
+    setup_max_pdx(raw_max_page);
     if ( highmem_start )
         xenheap_max_mfn(PFN_DOWN(highmem_start));
 
@@ -995,7 +998,7 @@ void __init __start_xen(unsigned long mbi_p)
         {
             acpi_boot_table_init_done = 1;
             srat_parse_regions(s);
-            setup_max_pdx();
+            setup_max_pdx(raw_max_page);
         }
 
         if ( pfn_to_pdx((e - 1) >> PAGE_SHIFT) >= max_pdx )
@@ -1133,7 +1136,7 @@ void __init __start_xen(unsigned long mbi_p)
 
     acpi_numa_init();
 
-    numa_initmem_init(0, max_page);
+    numa_initmem_init(0, raw_max_page);
 
     end_boot_allocator();
     system_state = SYS_STATE_boot;