1 files changed, 66 insertions, 40 deletions

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 745d66b843c8..b299724f6e34 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -53,25 +53,14 @@
 #include <asm/page_types.h>
 #include <asm/init.h>
 
+#include "mm_internal.h"
+
 unsigned long highstart_pfn, highend_pfn;
 
 static noinline int do_test_wp_bit(void);
 
 bool __read_mostly __vmalloc_start_set = false;
 
-static __init void *alloc_low_page(void)
-{
-        unsigned long pfn = pgt_buf_end++;
-        void *adr;
-
-        if (pfn >= pgt_buf_top)
-                panic("alloc_low_page: ran out of memory");
-
-        adr = __va(pfn * PAGE_SIZE);
-        clear_page(adr);
-        return adr;
-}
-
 /*
  * Creates a middle page table and puts a pointer to it in the
  * given global directory entry. This only returns the gd entry
@@ -84,10 +73,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 
 #ifdef CONFIG_X86_PAE
         if (!(pgd_val(*pgd) & _PAGE_PRESENT)) {
-                if (after_bootmem)
-                        pmd_table = (pmd_t *)alloc_bootmem_pages(PAGE_SIZE);
-                else
-                        pmd_table = (pmd_t *)alloc_low_page();
+                pmd_table = (pmd_t *)alloc_low_page();
                 paravirt_alloc_pmd(&init_mm, __pa(pmd_table) >> PAGE_SHIFT);
                 set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
                 pud = pud_offset(pgd, 0);
@@ -109,17 +95,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 static pte_t * __init one_page_table_init(pmd_t *pmd)
 {
         if (!(pmd_val(*pmd) & _PAGE_PRESENT)) {
-                pte_t *page_table = NULL;
-
-                if (after_bootmem) {
-#if defined(CONFIG_DEBUG_PAGEALLOC) || defined(CONFIG_KMEMCHECK)
-                        page_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
-#endif
-                        if (!page_table)
-                                page_table =
-                                (pte_t *)alloc_bootmem_pages(PAGE_SIZE);
-                } else
-                        page_table = (pte_t *)alloc_low_page();
+                pte_t *page_table = (pte_t *)alloc_low_page();
 
                 paravirt_alloc_pte(&init_mm, __pa(page_table) >> PAGE_SHIFT);
                 set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
@@ -146,8 +122,39 @@ pte_t * __init populate_extra_pte(unsigned long vaddr)
         return one_page_table_init(pmd) + pte_idx;
 }
 
+static unsigned long __init
+page_table_range_init_count(unsigned long start, unsigned long end)
+{
+        unsigned long count = 0;
+#ifdef CONFIG_HIGHMEM
+        int pmd_idx_kmap_begin = fix_to_virt(FIX_KMAP_END) >> PMD_SHIFT;
+        int pmd_idx_kmap_end = fix_to_virt(FIX_KMAP_BEGIN) >> PMD_SHIFT;
+        int pgd_idx, pmd_idx;
+        unsigned long vaddr;
+
+        if (pmd_idx_kmap_begin == pmd_idx_kmap_end)
+                return 0;
+
+        vaddr = start;
+        pgd_idx = pgd_index(vaddr);
+
+        for ( ; (pgd_idx < PTRS_PER_PGD) && (vaddr != end); pgd_idx++) {
+                for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
+                                                        pmd_idx++) {
+                        if ((vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin &&
+                            (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end)
+                                count++;
+                        vaddr += PMD_SIZE;
+                }
+                pmd_idx = 0;
+        }
+#endif
+        return count;
+}
+
 static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
-                                           unsigned long vaddr, pte_t *lastpte)
+                                           unsigned long vaddr, pte_t *lastpte,
+                                           void **adr)
 {
 #ifdef CONFIG_HIGHMEM
         /*
@@ -161,16 +168,15 @@ static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
 
         if (pmd_idx_kmap_begin != pmd_idx_kmap_end
             && (vaddr >> PMD_SHIFT) >= pmd_idx_kmap_begin
-            && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end
-            && ((__pa(pte) >> PAGE_SHIFT) < pgt_buf_start
-                || (__pa(pte) >> PAGE_SHIFT) >= pgt_buf_end)) {
+            && (vaddr >> PMD_SHIFT) <= pmd_idx_kmap_end) {
                 pte_t *newpte;
                 int i;
 
                 BUG_ON(after_bootmem);
-                newpte = alloc_low_page();
+                newpte = *adr;
                 for (i = 0; i < PTRS_PER_PTE; i++)
                         set_pte(newpte + i, pte[i]);
+                *adr = (void *)(((unsigned long)(*adr)) + PAGE_SIZE);
 
                 paravirt_alloc_pte(&init_mm, __pa(newpte) >> PAGE_SHIFT);
                 set_pmd(pmd, __pmd(__pa(newpte)|_PAGE_TABLE));
@@ -204,6 +210,11 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
         pgd_t *pgd;
         pmd_t *pmd;
         pte_t *pte = NULL;
+        unsigned long count = page_table_range_init_count(start, end);
+        void *adr = NULL;
+
+        if (count)
+                adr = alloc_low_pages(count);
 
         vaddr = start;
         pgd_idx = pgd_index(vaddr);
@@ -216,7 +227,7 @@ page_table_range_init(unsigned long start, unsigned long end, pgd_t *pgd_base)
                 for (; (pmd_idx < PTRS_PER_PMD) && (vaddr != end);
                                                         pmd++, pmd_idx++) {
                         pte = page_table_kmap_check(one_page_table_init(pmd),
-                                                    pmd, vaddr, pte);
+                                                    pmd, vaddr, pte, &adr);
 
                         vaddr += PMD_SIZE;
                 }
@@ -310,6 +321,7 @@ repeat:
                                         __pgprot(PTE_IDENT_ATTR |
                                                  _PAGE_PSE);
 
+                                pfn &= PMD_MASK >> PAGE_SHIFT;
                                 addr2 = (pfn + PTRS_PER_PTE-1) * PAGE_SIZE +
                                         PAGE_OFFSET + PAGE_SIZE-1;
 
@@ -455,9 +467,14 @@ void __init native_pagetable_init(void)
 
         /*
          * Remove any mappings which extend past the end of physical
-         * memory from the boot time page table:
+         * memory from the boot time page table.
+         * In virtual address space, we should have at least two pages
+         * from VMALLOC_END to pkmap or fixmap according to VMALLOC_END
+         * definition. And max_low_pfn is set to VMALLOC_END physical
+         * address. If initial memory mapping is doing right job, we
+         * should have pte used near max_low_pfn or one pmd is not present.
          */
-        for (pfn = max_low_pfn + 1; pfn < 1<<(32-PAGE_SHIFT); pfn++) {
+        for (pfn = max_low_pfn; pfn < 1<<(32-PAGE_SHIFT); pfn++) {
                 va = PAGE_OFFSET + (pfn<<PAGE_SHIFT);
                 pgd = base + pgd_index(va);
                 if (!pgd_present(*pgd))
@@ -468,10 +485,19 @@ void __init native_pagetable_init(void)
                 if (!pmd_present(*pmd))
                         break;
 
+                /* should not be large page here */
+                if (pmd_large(*pmd)) {
+                        pr_warn("try to clear pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx, but pmd is big page and is not using pte !\n",
+                                pfn, pmd, __pa(pmd));
+                        BUG_ON(1);
+                }
+
                 pte = pte_offset_kernel(pmd, va);
                 if (!pte_present(*pte))
                         break;
 
+                printk(KERN_DEBUG "clearing pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx pte: %p pte phys: %lx\n",
+                                pfn, pmd, __pa(pmd), pte, __pa(pte));
                 pte_clear(NULL, va, pte);
         }
         paravirt_alloc_pmd(&init_mm, __pa(base) >> PAGE_SHIFT);
@@ -550,7 +576,7 @@ early_param("highmem", parse_highmem);
  * artificially via the highmem=x boot parameter then create
  * it:
  */
-void __init lowmem_pfn_init(void)
+static void __init lowmem_pfn_init(void)
 {
         /* max_low_pfn is 0, we already have early_res support */
         max_low_pfn = max_pfn;
@@ -586,7 +612,7 @@ void __init lowmem_pfn_init(void)
  * We have more RAM than fits into lowmem - we try to put it into
  * highmem, also taking the highmem=x boot parameter into account:
  */
-void __init highmem_pfn_init(void)
+static void __init highmem_pfn_init(void)
 {
         max_low_pfn = MAXMEM_PFN;
 
@@ -669,8 +695,6 @@ void __init setup_bootmem_allocator(void)
         printk(KERN_INFO "  mapped low ram: 0 - %08lx\n",
                  max_pfn_mapped<<PAGE_SHIFT);
         printk(KERN_INFO "  low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
-
-        after_bootmem = 1;
 }
 
 /*
@@ -753,6 +777,8 @@ void __init mem_init(void)
                 if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
                         reservedpages++;
 
+        after_bootmem = 1;
+
         codesize =  (unsigned long) &_etext - (unsigned long) &_text;
         datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
         initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;