10 files changed, 47 insertions, 78 deletions

diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index afe68ddbe6a4..052ee643a32e 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -5,7 +5,7 @@ Virtual memory map with 4 level page tables:
 
 0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
 hole caused by [48:63] sign extension
-ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
+ffff800000000000 - ffff87ffffffffff (=43 bits) guard hole, reserved for hypervisor
 ffff880000000000 - ffffc7ffffffffff (=64 TB) direct mapping of all phys. memory
 ffffc80000000000 - ffffc8ffffffffff (=40 bits) hole
 ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 4064acae625d..01b493e5a99b 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -9,7 +9,6 @@
 #ifdef CONFIG_NUMA
 
 #define NR_NODE_MEMBLKS         (MAX_NUMNODES*2)
-#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
 
 /*
  * Too small node sizes may confuse the VM badly. Usually they
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 9ee322103c6d..b6c0b404898a 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -32,9 +32,6 @@ static inline void pgtable_cache_init(void) { }
 static inline void check_pgt_cache(void) { }
 void paging_init(void);
 
-extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
-
-
 /*
  * Define this if things work differently on an i386 and an i486:
  * it will (on an i486) warn about kernel memory accesses that are
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 3874693c0e53..4572b2f30237 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -116,7 +116,8 @@ static inline void native_pgd_clear(pgd_t *pgd)
         native_set_pgd(pgd, native_make_pgd(0));
 }
 
-extern void sync_global_pgds(unsigned long start, unsigned long end);
+extern void sync_global_pgds(unsigned long start, unsigned long end,
+                             int removed);
 
 /*
  * Conversion functions: convert a page and protection to a page entry,
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 988c00a1f60d..49f886481615 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -682,15 +682,14 @@ void __init parse_e820_ext(u64 phys_addr, u32 data_len)
  * hibernation (32 bit) or software suspend and suspend to RAM (64 bit).
  *
  * This function requires the e820 map to be sorted and without any
- * overlapping entries and assumes the first e820 area to be RAM.
+ * overlapping entries.
  */
 void __init e820_mark_nosave_regions(unsigned long limit_pfn)
 {
         int i;
-        unsigned long pfn;
+        unsigned long pfn = 0;
 
-        pfn = PFN_DOWN(e820.map[0].addr + e820.map[0].size);
-        for (i = 1; i < e820.nr_map; i++) {
+        for (i = 0; i < e820.nr_map; i++) {
                 struct e820entry *ei = &e820.map[i];
 
                 if (pfn < PFN_UP(ei->addr))
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 9c5b32e2bdc0..d973e61e450d 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -349,7 +349,7 @@ out:
 
 void vmalloc_sync_all(void)
 {
-        sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END);
+        sync_global_pgds(VMALLOC_START & PGDIR_MASK, VMALLOC_END, 0);
 }
 
 /*
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 5d984769cbd8..4cb8763868fc 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -178,7 +178,7 @@ __setup("noexec32=", nonx32_setup);
  * When memory was added/removed make sure all the processes MM have
  * suitable PGD entries in the local PGD level page.
  */
-void sync_global_pgds(unsigned long start, unsigned long end)
+void sync_global_pgds(unsigned long start, unsigned long end, int removed)
 {
         unsigned long address;
 
@@ -186,7 +186,12 @@ void sync_global_pgds(unsigned long start, unsigned long end)
                 const pgd_t *pgd_ref = pgd_offset_k(address);
                 struct page *page;
 
-                if (pgd_none(*pgd_ref))
+                /*
+                 * When it is called after memory hot remove, pgd_none()
+                 * returns true. In this case (removed == 1), we must clear
+                 * the PGD entries in the local PGD level page.
+                 */
+                if (pgd_none(*pgd_ref) && !removed)
                         continue;
 
                 spin_lock(&pgd_lock);
@@ -199,12 +204,18 @@ void sync_global_pgds(unsigned long start, unsigned long end)
                         pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
                         spin_lock(pgt_lock);
 
-                        if (pgd_none(*pgd))
-                                set_pgd(pgd, *pgd_ref);
-                        else
+                        if (!pgd_none(*pgd_ref) && !pgd_none(*pgd))
                                 BUG_ON(pgd_page_vaddr(*pgd)
                                        != pgd_page_vaddr(*pgd_ref));
 
+                        if (removed) {
+                                if (pgd_none(*pgd_ref) && !pgd_none(*pgd))
+                                        pgd_clear(pgd);
+                        } else {
+                                if (pgd_none(*pgd))
+                                        set_pgd(pgd, *pgd_ref);
+                        }
+
                         spin_unlock(pgt_lock);
                 }
                 spin_unlock(&pgd_lock);
@@ -633,7 +644,7 @@ kernel_physical_mapping_init(unsigned long start,
         }
 
         if (pgd_changed)
-                sync_global_pgds(addr, end - 1);
+                sync_global_pgds(addr, end - 1, 0);
 
         __flush_tlb_all();
 
@@ -976,25 +987,26 @@ static void __meminit
 remove_pagetable(unsigned long start, unsigned long end, bool direct)
 {
         unsigned long next;
+        unsigned long addr;
         pgd_t *pgd;
         pud_t *pud;
         bool pgd_changed = false;
 
-        for (; start < end; start = next) {
-                next = pgd_addr_end(start, end);
+        for (addr = start; addr < end; addr = next) {
+                next = pgd_addr_end(addr, end);
 
-                pgd = pgd_offset_k(start);
+                pgd = pgd_offset_k(addr);
                 if (!pgd_present(*pgd))
                         continue;
 
                 pud = (pud_t *)pgd_page_vaddr(*pgd);
-                remove_pud_table(pud, start, next, direct);
+                remove_pud_table(pud, addr, next, direct);