4 files changed, 26 insertions, 196 deletions

diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index ae1aa71d011..7e73e8c6909 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -16,169 +16,6 @@
 #include <asm/tlbflush.h>
 #include <asm/pgalloc.h>
 
-static unsigned long page_table_shareable(struct vm_area_struct *svma,
-				struct vm_area_struct *vma,
-				unsigned long addr, pgoff_t idx)
-{
-	unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) +
-				svma->vm_start;
-	unsigned long sbase = saddr & PUD_MASK;
-	unsigned long s_end = sbase + PUD_SIZE;
-
-	/* Allow segments to share if only one is marked locked */
-	unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
-	unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
-
-	/*
-	 * match the virtual addresses, permission and the alignment of the
-	 * page table page.
-	 */
-	if (pmd_index(addr) != pmd_index(saddr) ||
-	    vm_flags != svm_flags ||
-	    sbase < svma->vm_start || svma->vm_end < s_end)
-		return 0;
-
-	return saddr;
-}
-
-static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
-{
-	unsigned long base = addr & PUD_MASK;
-	unsigned long end = base + PUD_SIZE;
-
-	/*
-	 * check on proper vm_flags and page table alignment
-	 */
-	if (vma->vm_flags & VM_MAYSHARE &&
-	    vma->vm_start <= base && end <= vma->vm_end)
-		return 1;
-	return 0;
-}
-
-/*
- * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
- * and returns the corresponding pte. While this is not necessary for the
- * !shared pmd case because we can allocate the pmd later as well, it makes the
- * code much cleaner. pmd allocation is essential for the shared case because
- * pud has to be populated inside the same i_mmap_mutex section - otherwise
- * racing tasks could either miss the sharing (see huge_pte_offset) or select a
- * bad pmd for sharing.
- */
-static pte_t *
-huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
-{
-	struct vm_area_struct *vma = find_vma(mm, addr);
-	struct address_space *mapping = vma->vm_file->f_mapping;
-	pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
-			vma->vm_pgoff;
-	struct vm_area_struct *svma;
-	unsigned long saddr;
-	pte_t *spte = NULL;
-	pte_t *pte;
-
-	if (!vma_shareable(vma, addr))
-		return (pte_t *)pmd_alloc(mm, pud, addr);
-
-	mutex_lock(&mapping->i_mmap_mutex);
-	vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
-		if (svma == vma)
-			continue;
-
-		saddr = page_table_shareable(svma, vma, addr, idx);
-		if (saddr) {
-			spte = huge_pte_offset(svma->vm_mm, saddr);
-			if (spte) {
-				get_page(virt_to_page(spte));
-				break;
-			}
-		}
-	}
-
-	if (!spte)
-		goto out;
-
-	spin_lock(&mm->page_table_lock);
-	if (pud_none(*pud))
-		pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK));
-	else
-		put_page(virt_to_page(spte));
-	spin_unlock(&mm->page_table_lock);
-out:
-	pte = (pte_t *)pmd_alloc(mm, pud, addr);
-	mutex_unlock(&mapping->i_mmap_mutex);
-	return pte;
-}
-
-/*
- * unmap huge page backed by shared pte.
- *
- * Hugetlb pte page is ref counted at the time of mapping.  If pte is shared
- * indicated by page_count > 1, unmap is achieved by clearing pud and
- * decrementing the ref count. If count == 1, the pte page is not shared.
- *
- * called with vma->vm_mm->page_table_lock held.
- *
- * returns: 1 successfully unmapped a shared pte page
- *	    0 the underlying pte page is not shared, or it is the last user
- */
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
-{
-	pgd_t *pgd = pgd_offset(mm, *addr);
-	pud_t *pud = pud_offset(pgd, *addr);
-
-	BUG_ON(page_count(virt_to_page(ptep)) == 0);
-	if (page_count(virt_to_page(ptep)) == 1)
-		return 0;
-
-	pud_clear(pud);
-	put_page(virt_to_page(ptep));
-	*addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
-	return 1;
-}
-
-pte_t *huge_pte_alloc(struct mm_struct *mm,
-			unsigned long addr, unsigned long sz)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pte_t *pte = NULL;
-
-	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
-	if (pud) {
-		if (sz == PUD_SIZE) {
-			pte = (pte_t *)pud;
-		} else {
-			BUG_ON(sz != PMD_SIZE);
-			if (pud_none(*pud))
-				pte = huge_pmd_share(mm, addr, pud);
-			else
-				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)
-{
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd = NULL;
-
-	pgd = pgd_offset(mm, addr);
-	if (pgd_present(*pgd)) {
-		pud = pud_offset(pgd, addr);
-		if (pud_present(*pud)) {
-			if (pud_large(*pud))
-				return (pte_t *)pud;
-			pmd = pmd_offset(pud, addr);
-		}
-	}
-	return (pte_t *) pmd;
-}
-
 #if 0	/* This is just for testing */
 struct page *
 follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
@@ -240,30 +77,6 @@ int pud_huge(pud_t pud)
 	return !!(pud_val(pud) & _PAGE_PSE);
 }
 
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd, int write)
-{
-	struct page *page;
-
-	page = pte_page(*(pte_t *)pmd);
-	if (page)
-		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
-	return page;
-}
-
-struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
-		pud_t *pud, int write)
-{
-	struct page *page;
-
-	page = pte_page(*(pte_t *)pud);
-	if (page)
-		page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
-	return page;
-}
-
 #endif
 
 /* x86_64 also uses this file */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index fdc5dca14fb..1f34e921977 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -277,6 +277,9 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range,
 	end_pfn = limit_pfn;
 	nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
 
+	if (!after_bootmem)
+		adjust_range_page_size_mask(mr, nr_range);
+
 	/* try to merge same page size and continuous */
 	for (i = 0; nr_range > 1 && i < nr_range - 1; i++) {
 		unsigned long old_start;
@@ -291,9 +294,6 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range,
 		nr_range--;
 	}
 
-	if (!after_bootmem)
-		adjust_range_page_size_mask(mr, nr_range);
-
 	for (i = 0; i < nr_range; i++)
 		printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n",
 				mr[i].start, mr[i].end - 1,
@@ -359,7 +359,17 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 }
 
 /*
- * would have hole in the middle or ends, and only ram parts will be mapped.
+ * We need to iterate through the E820 memory map and create direct mappings
+ * for only E820_RAM and E820_KERN_RESERVED regions. We cannot simply
+ * create direct mappings for all pfns from [0 to max_low_pfn) and
+ * [4GB to max_pfn) because of possible memory holes in high addresses
+ * that cannot be marked as UC by fixed/variable range MTRRs.
+ * Depending on the alignment of E820 ranges, this may possibly result
+ * in using smaller size (i.e. 4K instead of 2M or 1G) page tables.
+ *
+ * init_mem_mapping() calls init_range_memory_mapping() with big range.
+ * That range would have hole in the middle or ends, and only ram parts
+ * will be mapped in init_range_memory_mapping().
  */
 static unsigned long __init init_range_memory_mapping(
 					   unsigned long r_start,
@@ -419,6 +429,13 @@ void __init init_mem_mapping(void)
 	max_pfn_mapped = 0; /* will get exact value next */
 	min_pfn_mapped = real_end >> PAGE_SHIFT;
 	last_start = start = real_end;
+
+	/*
+	 * We start from the top (end of memory) and go to the bottom.
+	 * The memblock_find_in_range() gets us a block of RAM from the
+	 * end of RAM in [min_pfn_mapped, max_pfn_mapped) used as new pages
+	 * for page table.
+	 */
 	while (last_start > ISA_END_ADDRESS) {
 		if (last_start > step_size) {
 			start = round_down(last_start - 1, step_size);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bb00c4672ad..b3940b6b4d7 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -368,7 +368,7 @@ void __init init_extra_mapping_uc(unsigned long phys, unsigned long size)
  *
  *   from __START_KERNEL_map to __START_KERNEL_map + size (== _end-_text)
  *
- * phys_addr holds the negative offset to the kernel, which is added
+ * phys_base holds the negative offset to the kernel, which is added
  * to the compile time generated pmds. This results in invalid pmds up
  * to the point where we hit the physaddr 0 mapping.
  *
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 9a1e6583910..0215e2c563e 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -501,15 +501,15 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
 	}
 
 	if (slot < 0) {
-		printk(KERN_INFO "early_iomap(%08llx, %08lx) not found slot\n",
-			 (u64)phys_addr, size);
+		printk(KERN_INFO "%s(%08llx, %08lx) not found slot\n",
+		       __func__, (u64)phys_addr, size);
 		WARN_ON(1);
 		return NULL;
 	}
 
 	if (early_ioremap_debug) {
-		printk(KERN_INFO "early_ioremap(%08llx, %08lx) [%d] => ",
-		       (u64)phys_addr, size, slot);
+		printk(KERN_INFO "%s(%08llx, %08lx) [%d] => ",
+		       __func__, (u64)phys_addr, size, slot);
 		dump_stack();
 	}