X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=fs%2Fhugetlbfs%2Finode.c;h=f568102da1e8df3be5126e91a50914d55dc5c0bb;hb=c2642ab05b855d2d3b850ddf90dbb02b1b9358ac;hp=2627efe767cf485257f381530ab8234cfb7a218d;hpb=4c887265977213985091476be40ab11dfdcb4caf;p=linux-2.6

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 2627efe767..f568102da1 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -18,6 +18,7 @@
 #include <linux/highmem.h>
 #include <linux/init.h>
 #include <linux/string.h>
+#include <linux/capability.h>
 #include <linux/backing-dev.h>
 #include <linux/hugetlb.h>
 #include <linux/pagevec.h>
@@ -45,15 +46,61 @@ static struct backing_dev_info hugetlbfs_backing_dev_info = {
 
 int sysctl_hugetlb_shm_group;
 
+static void huge_pagevec_release(struct pagevec *pvec)
+{
+	int i;
+
+	for (i = 0; i < pagevec_count(pvec); ++i)
+		put_page(pvec->pages[i]);
+
+	pagevec_reinit(pvec);
+}
+
+/*
+ * huge_pages_needed tries to determine the number of new huge pages that
+ * will be required to fully populate this VMA.  This will be equal to
+ * the size of the VMA in huge pages minus the number of huge pages
+ * (covered by this VMA) that are found in the page cache.
+ *
+ * Result is in bytes to be compatible with is_hugepage_mem_enough()
+ */
+static unsigned long
+huge_pages_needed(struct address_space *mapping, struct vm_area_struct *vma)
+{
+	int i;
+	struct pagevec pvec;
+	unsigned long start = vma->vm_start;
+	unsigned long end = vma->vm_end;
+	unsigned long hugepages = (end - start) >> HPAGE_SHIFT;
+	pgoff_t next = vma->vm_pgoff;
+	pgoff_t endpg = next + ((end - start) >> PAGE_SHIFT);
+
+	pagevec_init(&pvec, 0);
+	while (next < endpg) {
+		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE))
+			break;
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+			if (page->index > next)
+				next = page->index;
+			if (page->index >= endpg)
+				break;
+			next++;
+			hugepages--;
+		}
+		huge_pagevec_release(&pvec);
+	}
+	return hugepages << HPAGE_SHIFT;
+}
+
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_dentry->d_inode;
+	struct address_space *mapping = inode->i_mapping;
+	unsigned long bytes;
 	loff_t len, vma_len;
 	int ret;
 
-	if ((vma->vm_flags & (VM_MAYSHARE | VM_WRITE)) == VM_WRITE)
-		return -EINVAL;
-
 	if (vma->vm_pgoff & (HPAGE_SIZE / PAGE_SIZE - 1))
 		return -EINVAL;
 
@@ -66,9 +113,13 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (vma->vm_end - vma->vm_start < HPAGE_SIZE)
 		return -EINVAL;
 
+	bytes = huge_pages_needed(mapping, vma);
+	if (!is_hugepage_mem_enough(bytes))
+		return -ENOMEM;
+
 	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
 
-	down(&inode->i_sem);
+	mutex_lock(&inode->i_mutex);
 	file_accessed(file);
 	vma->vm_flags |= VM_HUGETLB | VM_RESERVED;
 	vma->vm_ops = &hugetlb_vm_ops;
@@ -83,7 +134,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (inode->i_size < len)
 		inode->i_size = len;
 out:
-	up(&inode->i_sem);
+	mutex_unlock(&inode->i_mutex);
 
 	return ret;
 }
@@ -168,16 +219,6 @@ static int hugetlbfs_commit_write(struct file *file,
 	return -EINVAL;
 }
 
-static void huge_pagevec_release(struct pagevec *pvec)
-{
-	int i;
-
-	for (i = 0; i < pagevec_count(pvec); ++i)
-		put_page(pvec->pages[i]);
-
-	pagevec_reinit(pvec);
-}
-
 static void truncate_huge_page(struct page *page)
 {
 	clear_page_dirty(page);
@@ -361,7 +402,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid,
 		inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		info = HUGETLBFS_I(inode);
-		mpol_shared_policy_init(&info->policy);
+		mpol_shared_policy_init(&info->policy, MPOL_DEFAULT, NULL);
 		switch (mode & S_IFMT) {
 		default:
 			init_special_inode(inode, mode, dev);
@@ -469,10 +510,14 @@ static int hugetlbfs_statfs(struct super_block *sb, struct kstatfs *buf)
 	buf->f_bsize = HPAGE_SIZE;
 	if (sbinfo) {
 		spin_lock(&sbinfo->stat_lock);
-		buf->f_blocks = sbinfo->max_blocks;
-		buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
-		buf->f_files = sbinfo->max_inodes;
-		buf->f_ffree = sbinfo->free_inodes;
+		/* If no limits set, just report 0 for max/free/used
+		 * blocks, like simple_statfs() */
+		if (sbinfo->max_blocks >= 0) {
+			buf->f_blocks = sbinfo->max_blocks;
+			buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
+			buf->f_files = sbinfo->max_inodes;
+			buf->f_ffree = sbinfo->free_inodes;
+		}
 		spin_unlock(&sbinfo->stat_lock);
 	}
 	buf->f_namelen = NAME_MAX;