vserver 1.9.5.x5

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

diff --git a/mm/fremap.c b/mm/fremap.c
index c708a58..036ccfb 100644 (file)
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -14,6 +14,7 @@
 #include <linux/swapops.h>
 #include <linux/rmap.h>
 #include <linux/module.h>
+#include <linux/syscalls.h>
 #include <linux/vs_memory.h>
 
 #include <asm/mmu_context.h>
@@ -57,25 +58,26 @@ static inline void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
                unsigned long addr, struct page *page, pgprot_t prot)
 {
+       struct inode *inode;
+       pgoff_t size;
        int err = -ENOMEM;
        pte_t *pte;
-       pgd_t *pgd;
        pmd_t *pmd;
+       pud_t *pud;
+       pgd_t *pgd;
        pte_t pte_val;
 
-       /*
-        * We use page_add_file_rmap below: if install_page is
-        * ever extended to anonymous pages, this will warn us.
-        */
-       BUG_ON(!page_mapping(page));
-
        pgd = pgd_offset(mm, addr);
        spin_lock(&mm->page_table_lock);
 
        if (!vx_rsspages_avail(mm, 1))
                goto err_unlock;
+       
+       pud = pud_alloc(mm, pgd, addr);
+       if (!pud)
+               goto err_unlock;
 
-       pmd = pmd_alloc(mm, pgd, addr);
+       pmd = pmd_alloc(mm, pud, addr);
        if (!pmd)
                goto err_unlock;
 
@@ -83,6 +85,16 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma,
        if (!pte)
                goto err_unlock;
 
+       /*
+        * This page may have been truncated. Tell the
+        * caller about it.
+        */
+       err = -EINVAL;
+       inode = vma->vm_file->f_mapping->host;
+       size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+       if (!page->mapping || page->index >= size)
+               goto err_unlock;
+
        zap_pte(mm, vma, addr, pte);
 
        // mm->rss++;
@@ -111,14 +123,19 @@ int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 {
        int err = -ENOMEM;
        pte_t *pte;
-       pgd_t *pgd;
        pmd_t *pmd;
+       pud_t *pud;
+       pgd_t *pgd;
        pte_t pte_val;
 
        pgd = pgd_offset(mm, addr);
        spin_lock(&mm->page_table_lock);
+       
+       pud = pud_alloc(mm, pgd, addr);
+       if (!pud)
+               goto err_unlock;
 
-       pmd = pmd_alloc(mm, pgd, addr);
+       pmd = pmd_alloc(mm, pud, addr);
        if (!pmd)
                goto err_unlock;
 
@@ -167,6 +184,7 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
        unsigned long end = start + size;
        struct vm_area_struct *vma;
        int err = -EINVAL;
+       int has_write_lock = 0;
 
        if (__prot)
                return err;
@@ -187,7 +205,8 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
 #endif
 
        /* We need down_write() to change vma->vm_flags. */
-       down_write(&mm->mmap_sem);
+       down_read(&mm->mmap_sem);
+ retry:
        vma = find_vma(mm, start);
 
        /*
@@ -198,7 +217,8 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
         * or VM_LOCKED, but VM_LOCKED could be revoked later on).
         */
        if (vma && (vma->vm_flags & VM_SHARED) &&
-               (!vma->vm_private_data || (vma->vm_flags & VM_RESERVED)) &&
+               (!vma->vm_private_data ||
+                       (vma->vm_flags & (VM_NONLINEAR|VM_RESERVED))) &&
                vma->vm_ops && vma->vm_ops->populate &&
                        end > start && start >= vma->vm_start &&
                                end <= vma->vm_end) {
@@ -206,20 +226,22 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
                /* Must set VM_NONLINEAR before any pages are populated. */
                if (pgoff != linear_page_index(vma, start) &&
                    !(vma->vm_flags & VM_NONLINEAR)) {
+                       if (!has_write_lock) {
+                               up_read(&mm->mmap_sem);
+                               down_write(&mm->mmap_sem);
+                               has_write_lock = 1;
+                               goto retry;
+                       }
                        mapping = vma->vm_file->f_mapping;
                        spin_lock(&mapping->i_mmap_lock);
                        flush_dcache_mmap_lock(mapping);
                        vma->vm_flags |= VM_NONLINEAR;
                        vma_prio_tree_remove(vma, &mapping->i_mmap);
-                       vma_prio_tree_init(vma);
-                       list_add_tail(&vma->shared.vm_set.list,
-                                       &mapping->i_mmap_nonlinear);
+                       vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
                        flush_dcache_mmap_unlock(mapping);
                        spin_unlock(&mapping->i_mmap_lock);
                }
 
-               /* ->populate can take a long time, so downgrade the lock. */
-               downgrade_write(&mm->mmap_sem);
                err = vma->vm_ops->populate(vma, start, size,
                                            vma->vm_page_prot,
                                            pgoff, flags & MAP_NONBLOCK);
@@ -229,10 +251,11 @@ asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
                 * it after ->populate completes, and that would prevent
                 * downgrading the lock.  (Locks can't be upgraded).
                 */
+       }
+       if (likely(!has_write_lock))
                up_read(&mm->mmap_sem);
-       } else {
+       else
                up_write(&mm->mmap_sem);
-       }
 
        return err;
 }