Merge commit 'linux-2.6/master' (early part) into oprofile/core

This branch depends on these apic patches:

      apic, x86: Use BIOS settings for IBS and MCE threshold interrupt LVT offsets
      apic, x86: Check if EILVT APIC registers are available (AMD only)

Signed-off-by: Robert Richter <robert.richter@amd.com>

1 files changed, 47 insertions, 2 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 9a6674689a20..c55f900fbf89 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -98,6 +98,43 @@ static int __init nonx32_setup(char *str)
 __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)
+{
+        unsigned long address;
+
+        for (address = start; address <= end; address += PGDIR_SIZE) {
+                const pgd_t *pgd_ref = pgd_offset_k(address);
+                unsigned long flags;
+                struct page *page;
+
+                if (pgd_none(*pgd_ref))
+                        continue;
+
+                spin_lock_irqsave(&pgd_lock, flags);
+                list_for_each_entry(page, &pgd_list, lru) {
+                        pgd_t *pgd;
+                        spinlock_t *pgt_lock;
+
+                        pgd = (pgd_t *)page_address(page) + pgd_index(address);
+                        pgt_lock = &pgd_page_get_mm(page)->page_table_lock;
+                        spin_lock(pgt_lock);
+
+                        if (pgd_none(*pgd))
+                                set_pgd(pgd, *pgd_ref);
+                        else
+                                BUG_ON(pgd_page_vaddr(*pgd)
+                                       != pgd_page_vaddr(*pgd_ref));
+
+                        spin_unlock(pgt_lock);
+                }
+                spin_unlock_irqrestore(&pgd_lock, flags);
+        }
+}
+
+/*
  * NOTE: This function is marked __ref because it calls __init function
  * (alloc_bootmem_pages). It's safe to do it ONLY when after_bootmem == 0.
  */
@@ -293,7 +330,7 @@ static __ref void *alloc_low_page(unsigned long *phys)
                 panic("alloc_low_page: ran out of memory");
 
         adr = early_memremap(pfn * PAGE_SIZE, PAGE_SIZE);
-        memset(adr, 0, PAGE_SIZE);
+        clear_page(adr);
         *phys  = pfn * PAGE_SIZE;
         return adr;
 }
@@ -534,11 +571,13 @@ kernel_physical_mapping_init(unsigned long start,
                              unsigned long end,
                              unsigned long page_size_mask)
 {
-
+        bool pgd_changed = false;
         unsigned long next, last_map_addr = end;
+        unsigned long addr;
 
         start = (unsigned long)__va(start);
         end = (unsigned long)__va(end);
+        addr = start;
 
         for (; start < end; start = next) {
                 pgd_t *pgd = pgd_offset_k(start);
@@ -563,7 +602,12 @@ kernel_physical_mapping_init(unsigned long start,
                 spin_lock(&init_mm.page_table_lock);
                 pgd_populate(&init_mm, pgd, __va(pud_phys));
                 spin_unlock(&init_mm.page_table_lock);
+                pgd_changed = true;
         }
+
+        if (pgd_changed)
+                sync_global_pgds(addr, end);
+
         __flush_tlb_all();
 
         return last_map_addr;
@@ -1003,6 +1047,7 @@ vmemmap_populate(struct page *start_page, unsigned long size, int node)
                 }
 
         }
+        sync_global_pgds((unsigned long)start_page, end);
         return 0;
 }