6 files changed, 52 insertions, 50 deletions

diff --git a/arch/i386/mm/discontig.c b/arch/i386/mm/discontig.c
index 6711ce3f6916..244d8ec66be2 100644
--- a/arch/i386/mm/discontig.c
+++ b/arch/i386/mm/discontig.c
@@ -37,7 +37,7 @@
 #include <asm/mmzone.h>
 #include <bios_ebda.h>
 
-struct pglist_data *node_data[MAX_NUMNODES];
+struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 bootmem_data_t node0_bdata;
 
@@ -49,8 +49,8 @@ bootmem_data_t node0_bdata;
  * 2) node_start_pfn   - the starting page frame number for a node
  * 3) node_end_pfn     - the ending page fram number for a node
  */
-unsigned long node_start_pfn[MAX_NUMNODES];
-unsigned long node_end_pfn[MAX_NUMNODES];
+unsigned long node_start_pfn[MAX_NUMNODES] __read_mostly;
+unsigned long node_end_pfn[MAX_NUMNODES] __read_mostly;
 
 
 #ifdef CONFIG_DISCONTIGMEM
@@ -66,7 +66,7 @@ unsigned long node_end_pfn[MAX_NUMNODES];
  *     physnode_map[4-7] = 1;
  *     physnode_map[8- ] = -1;
  */
-s8 physnode_map[MAX_ELEMENTS] = { [0 ... (MAX_ELEMENTS - 1)] = -1};
+s8 physnode_map[MAX_ELEMENTS] __read_mostly = { [0 ... (MAX_ELEMENTS - 1)] = -1};
 EXPORT_SYMBOL(physnode_map);
 
 void memory_present(int nid, unsigned long start, unsigned long end)
diff --git a/arch/i386/mm/fault.c b/arch/i386/mm/fault.c
index 8e90339d6eaa..9edd4485b91e 100644
--- a/arch/i386/mm/fault.c
+++ b/arch/i386/mm/fault.c
@@ -21,6 +21,7 @@
 #include <linux/vt_kern.h>              /* For unblank_screen() */
 #include <linux/highmem.h>
 #include <linux/module.h>
+#include <linux/kprobes.h>
 
 #include <asm/system.h>
 #include <asm/uaccess.h>
@@ -199,6 +200,18 @@ static inline int is_prefetch(struct pt_regs *regs, unsigned long addr,
         return 0;
 } 
 
+static noinline void force_sig_info_fault(int si_signo, int si_code,
+        unsigned long address, struct task_struct *tsk)
+{
+        siginfo_t info;
+
+        info.si_signo = si_signo;
+        info.si_errno = 0;
+        info.si_code = si_code;
+        info.si_addr = (void __user *)address;
+        force_sig_info(si_signo, &info, tsk);
+}
+
 fastcall void do_invalid_op(struct pt_regs *, unsigned long);
 
 /*
@@ -211,18 +224,18 @@ fastcall void do_invalid_op(struct pt_regs *, unsigned long);
  *      bit 1 == 0 means read, 1 means write
  *      bit 2 == 0 means kernel, 1 means user-mode
  */
-fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code)
+fastcall void __kprobes do_page_fault(struct pt_regs *regs,
+                                      unsigned long error_code)
 {
         struct task_struct *tsk;
         struct mm_struct *mm;
         struct vm_area_struct * vma;
         unsigned long address;
         unsigned long page;
-        int write;
-        siginfo_t info;
+        int write, si_code;
 
         /* get the address */
-        __asm__("movl %%cr2,%0":"=r" (address));
+        address = read_cr2();
 
         if (notify_die(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
                                         SIGSEGV) == NOTIFY_STOP)
@@ -233,7 +246,7 @@ fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code)
 
         tsk = current;
 
-        info.si_code = SEGV_MAPERR;
+        si_code = SEGV_MAPERR;
 
         /*
          * We fault-in kernel-space virtual memory on-demand. The
@@ -313,7 +326,7 @@ fastcall void do_page_fault(struct pt_regs *regs, unsigned long error_code)
  * we can handle it..
  */
 good_area:
-        info.si_code = SEGV_ACCERR;
+        si_code = SEGV_ACCERR;
         write = 0;
         switch (error_code & 3) {
                 default:        /* 3: write, present */
@@ -387,11 +400,7 @@ bad_area_nosemaphore:
                 /* Kernel addresses are always protection faults */
                 tsk->thread.error_code = error_code | (address >= TASK_SIZE);
                 tsk->thread.trap_no = 14;
-                info.si_signo = SIGSEGV;
-                info.si_errno = 0;
-                /* info.si_code has been set above */
-                info.si_addr = (void __user *)address;
-                force_sig_info(SIGSEGV, &info, tsk);
+                force_sig_info_fault(SIGSEGV, si_code, address, tsk);
                 return;
         }
 
@@ -446,7 +455,7 @@ no_context:
         printk(" at virtual address %08lx\n",address);
         printk(KERN_ALERT " printing eip:\n");
         printk("%08lx\n", regs->eip);
-        asm("movl %%cr3,%0":"=r" (page));
+        page = read_cr3();
         page = ((unsigned long *) __va(page))[address >> 22];
         printk(KERN_ALERT "*pde = %08lx\n", page);
         /*
@@ -500,11 +509,7 @@ do_sigbus:
         tsk->thread.cr2 = address;
         tsk->thread.error_code = error_code;
         tsk->thread.trap_no = 14;
-        info.si_signo = SIGBUS;
-        info.si_errno = 0;
-        info.si_code = BUS_ADRERR;
-        info.si_addr = (void __user *)address;
-        force_sig_info(SIGBUS, &info, tsk);
+        force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
         return;
 
 vmalloc_fault:
@@ -523,7 +528,7 @@ vmalloc_fault:
                 pmd_t *pmd, *pmd_k;
                 pte_t *pte_k;
 
-                asm("movl %%cr3,%0":"=r" (pgd_paddr));
+                pgd_paddr = read_cr3();
                 pgd = index + (pgd_t *)__va(pgd_paddr);
                 pgd_k = init_mm.pgd + index;
 
diff --git a/arch/i386/mm/hugetlbpage.c b/arch/i386/mm/hugetlbpage.c
index 3b099f32b948..d524127c9afc 100644
--- a/arch/i386/mm/hugetlbpage.c
+++ b/arch/i386/mm/hugetlbpage.c
@@ -22,12 +22,15 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
 {
         pgd_t *pgd;
         pud_t *pud;
-        pmd_t *pmd = NULL;
+        pte_t *pte = NULL;
 
         pgd = pgd_offset(mm, addr);
         pud = pud_alloc(mm, pgd, addr);
-        pmd = pmd_alloc(mm, pud, addr);
-        return (pte_t *) pmd;
+        if (pud)
+                pte = (pte_t *) pmd_alloc(mm, pud, addr);
+        BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
+
+        return pte;
 }
 
 pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
@@ -37,8 +40,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
         pmd_t *pmd = NULL;
 
         pgd = pgd_offset(mm, addr);
-        pud = pud_offset(pgd, addr);
-        pmd = pmd_offset(pud, addr);
+        if (pgd_present(*pgd)) {
+                pud = pud_offset(pgd, addr);
+                if (pud_present(*pud))
+                        pmd = pmd_offset(pud, addr);
+        }
         return (pte_t *) pmd;
 }
 
@@ -118,17 +124,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 }
 #endif
 
-void hugetlb_clean_stale_pgtable(pte_t *pte)
-{
-        pmd_t *pmd = (pmd_t *) pte;
-        struct page *page;
-
-        page = pmd_page(*pmd);
-        pmd_clear(pmd);
-        dec_page_state(nr_page_table_pages);
-        page_cache_release(page);
-}
-
 /* x86_64 also uses this file */
 
 #ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index 12216b52e28b..2ebaf75f732e 100644
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -198,9 +198,10 @@ int page_is_ram(unsigned long pagenr)
 
         if (efi_enabled) {
                 efi_memory_desc_t *md;
+                void *p;
 
-                for (i = 0; i < memmap.nr_map; i++) {
-                        md = &memmap.map[i];
+                for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+                        md = p;
                         if (!is_available_memory(md))
                                 continue;
                         addr = (md->phys_addr+PAGE_SIZE-1) >> PAGE_SHIFT;
@@ -348,7 +349,7 @@ static void __init pagetable_init (void)
          * All user-space mappings are explicitly cleared after
          * SMP startup.
          */
-        pgd_base[0] = pgd_base[USER_PTRS_PER_PGD];
+        set_pgd(&pgd_base[0], pgd_base[USER_PTRS_PER_PGD]);
 #endif
 }
 
@@ -392,7 +393,7 @@ void zap_low_mappings (void)
 }
 
 static int disable_nx __initdata = 0;
-u64 __supported_pte_mask = ~_PAGE_NX;
+u64 __supported_pte_mask __read_mostly = ~_PAGE_NX;
 
 /*
  * noexec = on|off
diff --git a/arch/i386/mm/pageattr.c b/arch/i386/mm/pageattr.c
index cb3da6baa704..f600fc244f02 100644
--- a/arch/i386/mm/pageattr.c
+++ b/arch/i386/mm/pageattr.c
@@ -12,6 +12,7 @@
 #include <asm/uaccess.h>
 #include <asm/processor.h>
 #include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
 
 static DEFINE_SPINLOCK(cpa_lock);
 static struct list_head df_list = LIST_HEAD_INIT(df_list);
@@ -52,8 +53,8 @@ static struct page *split_large_page(unsigned long address, pgprot_t prot)
         addr = address & LARGE_PAGE_MASK; 
         pbase = (pte_t *)page_address(base);
         for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) {
-                pbase[i] = pfn_pte(addr >> PAGE_SHIFT, 
-                                   addr == address ? prot : PAGE_KERNEL);
+               set_pte(&pbase[i], pfn_pte(addr >> PAGE_SHIFT,
+                                          addr == address ? prot : PAGE_KERNEL));
         }
         return base;
 } 
@@ -62,7 +63,7 @@ static void flush_kernel_map(void *dummy)
 { 
         /* Could use CLFLUSH here if the CPU supports it (Hammer,P4) */
         if (boot_cpu_data.x86_model >= 4) 
-                asm volatile("wbinvd":::"memory"); 
+                wbinvd();
         /* Flush all to work around Errata in early athlons regarding 
          * large page flushing. 
          */
diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c
index bd2f7afc7a2a..dcdce2c6c532 100644
--- a/arch/i386/mm/pgtable.c
+++ b/arch/i386/mm/pgtable.c
@@ -207,19 +207,19 @@ void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused)
 {
         unsigned long flags;
 
-        if (PTRS_PER_PMD == 1)
+        if (PTRS_PER_PMD == 1) {
+                memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t));
                 spin_lock_irqsave(&pgd_lock, flags);
+        }
 
-        memcpy((pgd_t *)pgd + USER_PTRS_PER_PGD,
+        clone_pgd_range((pgd_t *)pgd + USER_PTRS_PER_PGD,
                         swapper_pg_dir + USER_PTRS_PER_PGD,
-                        (PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
-
+                        KERNEL_PGD_PTRS);
         if (PTRS_PER_PMD > 1)
                 return;
 
         pgd_list_add(pgd);
         spin_unlock_irqrestore(&pgd_lock, flags);
-        memset(pgd, 0, USER_PTRS_PER_PGD*sizeof(pgd_t));
 }
 
 /* never called when PTRS_PER_PMD > 1 */