x86/EFI: properly handle run time memory regions outside the 1:1 map

Namely with PFN compression, MMIO ranges that the firmware may need
runtime access to can live in the holes that gets shrunk/eliminated by
PFN compression, and hence no mappings would result from simply
copying Xen's direct mapping table's L3 page table entries. Build
mappings for this "manually" in the EFI runtime call 1:1 page tables.

Use the opportunity to also properly identify (via a forcibly undefined
manifest constant) all the disabled code regions associated with it not
being acceptable for us to call SetVirtualAddressMap().

Signed-off-by: Jan Beulich <jbeulich@suse.com>
master commit: a350f3f43bcfac9c1591e28d8e43c505fcb172a5
master date: 2013-09-09 10:40:11 +0200

1 files changed, 91 insertions, 11 deletions

diff --git a/xen/arch/x86/efi/boot.c b/xen/arch/x86/efi/boot.c
index 184448c4d8..5fe31d63f3 100644
--- a/xen/arch/x86/efi/boot.c
+++ b/xen/arch/x86/efi/boot.c
@@ -21,6 +21,9 @@
 #include <asm/msr.h>
 #include <asm/processor.h>
 
+/* Using SetVirtualAddressMap() is incompatible with kexec: */
+#undef USE_SET_VIRTUAL_ADDRESS_MAP
+
 extern char start[];
 extern u32 cpuid_ext_features;
 
@@ -1290,7 +1293,7 @@ efi_start(EFI_HANDLE ImageHandle, EFI_SYSTEM_TABLE *SystemTable)
 
     /* Adjust pointers into EFI. */
     efi_ct = (void *)efi_ct + DIRECTMAP_VIRT_START;
-#if 0 /* Only needed when using virtual mode (see efi_init_memory()). */
+#ifdef USE_SET_VIRTUAL_ADDRESS_MAP
     efi_rs = (void *)efi_rs + DIRECTMAP_VIRT_START;
 #endif
     efi_memmap = (void *)efi_memmap + DIRECTMAP_VIRT_START;
@@ -1333,6 +1336,7 @@ efi_start(EFI_HANDLE ImageHandle, EFI_SYSTEM_TABLE *SystemTable)
     for( ; ; ); /* not reached */
 }
 
+#ifndef USE_SET_VIRTUAL_ADDRESS_MAP
 static __init void copy_mapping(unsigned long mfn, unsigned long end,
                                 bool_t (*is_valid)(unsigned long smfn,
                                                    unsigned long emfn))
@@ -1376,6 +1380,7 @@ static bool_t __init rt_range_valid(unsigned long smfn, unsigned long emfn)
 {
     return 1;
 }
+#endif
 
 #define INVALID_VIRTUAL_ADDRESS (0xBAAADUL << \
                                  (EFI_PAGE_SHIFT + BITS_PER_LONG - 32))
@@ -1383,6 +1388,13 @@ static bool_t __init rt_range_valid(unsigned long smfn, unsigned long emfn)
 void __init efi_init_memory(void)
 {
     unsigned int i;
+#ifndef USE_SET_VIRTUAL_ADDRESS_MAP
+    struct rt_extra {
+        struct rt_extra *next;
+        unsigned long smfn, emfn;
+        unsigned int prot;
+    } *extra, *extra_head = NULL;
+#endif
 
     printk(XENLOG_INFO "EFI memory map:\n");
     for ( i = 0; i < efi_memmap_size; i += efi_mdesc_size )
@@ -1437,15 +1449,29 @@ void __init efi_init_memory(void)
                 printk(XENLOG_ERR "Could not map MFNs %#lx-%#lx\n",
                        smfn, emfn - 1);
         }
+#ifndef USE_SET_VIRTUAL_ADDRESS_MAP
+        else if ( !((desc->PhysicalStart + len - 1) >> (VADDR_BITS - 1)) &&
+                  (extra = xmalloc(struct rt_extra)) != NULL )
+        {
+            extra->smfn = smfn;
+            extra->emfn = emfn;
+            extra->prot = prot & ~_PAGE_GLOBAL;
+            extra->next = extra_head;
+            extra_head = extra;
+            desc->VirtualStart = desc->PhysicalStart;
+        }
+#endif
         else
         {
+#ifdef USE_SET_VIRTUAL_ADDRESS_MAP
             /* XXX allocate e.g. down from FIXADDR_START */
+#endif
             printk(XENLOG_ERR "No mapping for MFNs %#lx-%#lx\n",
                    smfn, emfn - 1);
         }
     }
 
-#if 0 /* Incompatible with kexec. */
+#ifdef USE_SET_VIRTUAL_ADDRESS_MAP
     efi_rs->SetVirtualAddressMap(efi_memmap_size, efi_mdesc_size,
                                  mdesc_ver, efi_memmap);
 #else
@@ -1456,20 +1482,74 @@ void __init efi_init_memory(void)
 
     copy_mapping(0, max_page, ram_range_valid);
 
-    /* Insert non-RAM runtime mappings. */
+    /* Insert non-RAM runtime mappings inside the direct map. */
     for ( i = 0; i < efi_memmap_size; i += efi_mdesc_size )
     {
         const EFI_MEMORY_DESCRIPTOR *desc = efi_memmap + i;
 
-        if ( desc->Attribute & EFI_MEMORY_RUNTIME )
+        if ( (desc->Attribute & EFI_MEMORY_RUNTIME) &&
+             desc->VirtualStart != INVALID_VIRTUAL_ADDRESS &&
+             desc->VirtualStart != desc->PhysicalStart )
+            copy_mapping(PFN_DOWN(desc->PhysicalStart),
+                         PFN_UP(desc->PhysicalStart +
+                                (desc->NumberOfPages << EFI_PAGE_SHIFT)),
+                         rt_range_valid);
+    }
+
+    /* Insert non-RAM runtime mappings outside of the direct map. */
+    while ( (extra = extra_head) != NULL )
+    {
+        unsigned long addr = extra->smfn << PAGE_SHIFT;
+        l4_pgentry_t l4e = efi_l4_pgtable[l4_table_offset(addr)];
+        l3_pgentry_t *pl3e;
+        l2_pgentry_t *pl2e;
+        l1_pgentry_t *l1t;
+
+        if ( !(l4e_get_flags(l4e) & _PAGE_PRESENT) )
         {
-            if ( desc->VirtualStart != INVALID_VIRTUAL_ADDRESS )
-                copy_mapping(PFN_DOWN(desc->PhysicalStart),
-                             PFN_UP(desc->PhysicalStart +
-                                    (desc->NumberOfPages << EFI_PAGE_SHIFT)),
-                             rt_range_valid);
-            else
-                /* XXX */;
+            pl3e = alloc_xen_pagetable();
+            BUG_ON(!pl3e);
+            clear_page(pl3e);
+            efi_l4_pgtable[l4_table_offset(addr)] =
+                l4e_from_paddr(virt_to_maddr(pl3e), __PAGE_HYPERVISOR);
+        }
+        else
+            pl3e = l4e_to_l3e(l4e);
+        pl3e += l3_table_offset(addr);
+        if ( !(l3e_get_flags(*pl3e) & _PAGE_PRESENT) )
+        {
+            pl2e = alloc_xen_pagetable();
+            BUG_ON(!pl2e);
+            clear_page(pl2e);
+            *pl3e = l3e_from_paddr(virt_to_maddr(pl2e), __PAGE_HYPERVISOR);
+        }
+        else
+        {
+            BUG_ON(l3e_get_flags(*pl3e) & _PAGE_PSE);
+            pl2e = l3e_to_l2e(*pl3e);
+        }
+        pl2e += l2_table_offset(addr);
+        if ( !(l2e_get_flags(*pl2e) & _PAGE_PRESENT) )
+        {
+            l1t = alloc_xen_pagetable();
+            BUG_ON(!l1t);
+            clear_page(l1t);
+            *pl2e = l2e_from_paddr(virt_to_maddr(l1t), __PAGE_HYPERVISOR);
+        }
+        else
+        {
+            BUG_ON(l2e_get_flags(*pl2e) & _PAGE_PSE);
+            l1t = l2e_to_l1e(*pl2e);
+        }
+        for ( i = l1_table_offset(addr);
+              i < L1_PAGETABLE_ENTRIES && extra->smfn < extra->emfn;
+              ++i, ++extra->smfn )
+            l1t[i] = l1e_from_pfn(extra->smfn, extra->prot);
+
+        if ( extra->smfn == extra->emfn )
+        {
+            extra_head = extra->next;
+            xfree(extra);
         }
     }