mm: add a might_sleep_if() to dma_pool_alloc()

[linux-2.6.git] / mm / fremap.c

diff --git a/mm/fremap.c b/mm/fremap.c
index 37a93f8f3aec724437cef7aa0cba1633b44cdcd1..ec520c7b28dffedb5027de6b27834831938671cd 100644 (file)
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -15,11 +15,14 @@
 #include <linux/rmap.h>
 #include <linux/module.h>
 #include <linux/syscalls.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 
+#include "internal.h"
+
 static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
                        unsigned long addr, pte_t *ptep)
 {
@@ -34,10 +37,10 @@ static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
                if (page) {
                        if (pte_dirty(pte))
                                set_page_dirty(page);
-                       page_remove_rmap(page, vma);
+                       page_remove_rmap(page);
                        page_cache_release(page);
                        update_hiwater_rss(mm);
-                       dec_mm_counter(mm, file_rss);
+                       dec_mm_counter(mm, MM_FILEPAGES);
                }
        } else {
                if (!pte_file(pte))
@@ -97,35 +100,36 @@ static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma,
 
 }
 
-/***
- * sys_remap_file_pages - remap arbitrary pages of a shared backing store
- *                        file within an existing vma.
+/**
+ * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma
  * @start: start of the remapped virtual memory range
  * @size: size of the remapped virtual memory range
- * @prot: new protection bits of the range
- * @pgoff: to be mapped page of the backing store file
+ * @prot: new protection bits of the range (see NOTE)
+ * @pgoff: to-be-mapped page of the backing store file
  * @flags: 0 or MAP_NONBLOCKED - the later will cause no IO.
  *
- * this syscall works purely via pagetables, so it's the most efficient
+ * sys_remap_file_pages remaps arbitrary pages of an existing VM_SHARED vma
+ * (shared backing store file).
+ *
+ * This syscall works purely via pagetables, so it's the most efficient
  * way to map the same (large) file into a given virtual window. Unlike
  * mmap()/mremap() it does not create any new vmas. The new mappings are
  * also safe across swapout.
  *
- * NOTE: the 'prot' parameter right now is ignored, and the vma's default
- * protection is used. Arbitrary protections might be implemented in the
- * future.
+ * NOTE: the @prot parameter right now is ignored (but must be zero),
+ * and the vma's default protection is used. Arbitrary protections
+ * might be implemented in the future.
  */
-asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
-       unsigned long __prot, unsigned long pgoff, unsigned long flags)
+SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+               unsigned long, prot, unsigned long, pgoff, unsigned long, flags)
 {
        struct mm_struct *mm = current->mm;
        struct address_space *mapping;
-       unsigned long end = start + size;
        struct vm_area_struct *vma;
        int err = -EINVAL;
        int has_write_lock = 0;
 
-       if (__prot)
+       if (prot)
                return err;
        /*
         * Sanitize the syscall parameters:
@@ -137,6 +141,10 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
        if (start + size <= start)
                return err;
 
+       /* Does pgoff wrap? */
+       if (pgoff + (size >> PAGE_SHIFT) < pgoff)
+               return err;
+
        /* Can we represent this offset inside this architecture's pte's? */
 #if PTE_FILE_MAX_BITS < BITS_PER_LONG
        if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS))
@@ -163,7 +171,7 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
        if (!(vma->vm_flags & VM_CAN_NONLINEAR))
                goto out;
 
-       if (end <= start || start < vma->vm_start || end > vma->vm_end)
+       if (start < vma->vm_start || start + size > vma->vm_end)
                goto out;
 
        /* Must set VM_NONLINEAR before any pages are populated. */
@@ -188,10 +196,13 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
                 */
                if (mapping_cap_account_dirty(mapping)) {
                        unsigned long addr;
+                       struct file *file = vma->vm_file;
 
                        flags &= MAP_NONBLOCK;
-                       addr = mmap_region(vma->vm_file, start, size,
-                                       flags, vma->vm_flags, pgoff, 1);
+                       get_file(file);
+                       addr = mmap_region(file, start, size,
+                                       flags, vma->vm_flags, pgoff);
+                       fput(file);
                        if (IS_ERR_VALUE(addr)) {
                                err = addr;
                        } else {
@@ -209,13 +220,31 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
                spin_unlock(&mapping->i_mmap_lock);
        }
 
+       if (vma->vm_flags & VM_LOCKED) {
+               /*
+                * drop PG_Mlocked flag for over-mapped range
+                */
+               unsigned int saved_flags = vma->vm_flags;
+               munlock_vma_pages_range(vma, start, start + size);
+               vma->vm_flags = saved_flags;
+       }
+
+       mmu_notifier_invalidate_range_start(mm, start, start + size);
        err = populate_range(mm, vma, start, size, pgoff);
+       mmu_notifier_invalidate_range_end(mm, start, start + size);
        if (!err && !(flags & MAP_NONBLOCK)) {
-               if (unlikely(has_write_lock)) {
-                       downgrade_write(&mm->mmap_sem);
-                       has_write_lock = 0;
+               if (vma->vm_flags & VM_LOCKED) {
+                       /*
+                        * might be mapping previously unmapped range of file
+                        */
+                       mlock_vma_pages_range(vma, start, start + size);
+               } else {
+                       if (unlikely(has_write_lock)) {
+                               downgrade_write(&mm->mmap_sem);
+                               has_write_lock = 0;
+                       }
+                       make_pages_present(start, start+size);
                }
-               make_pages_present(start, start+size);
        }
 
        /*
@@ -232,4 +261,3 @@ out:
 
        return err;
 }
-