1 files changed, 111 insertions, 125 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 316adb968b65..4ea71eba40a5 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -4,11 +4,11 @@
  * Nadia Yvette Chambers, 2002
  *
  * Copyright (C) 2002 Linus Torvalds.
+ * License: GPL
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/module.h>
 #include <linux/thread_info.h>
 #include <asm/current.h>
 #include <linux/sched.h>		/* remove ASAP */
@@ -141,7 +141,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 	file_accessed(file);
 
 	ret = -ENOMEM;
@@ -157,7 +157,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (vma->vm_flags & VM_WRITE && inode->i_size < len)
 		inode->i_size = len;
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 
 	return ret;
 }
@@ -213,12 +213,12 @@ hugetlbfs_read_actor(struct page *page, unsigned long offset,
 	int i, chunksize;
 
 	/* Find which 4k chunk and offset with in that chunk */
-	i = offset >> PAGE_CACHE_SHIFT;
-	offset = offset & ~PAGE_CACHE_MASK;
+	i = offset >> PAGE_SHIFT;
+	offset = offset & ~PAGE_MASK;
 
 	while (size) {
 		size_t n;
-		chunksize = PAGE_CACHE_SIZE;
+		chunksize = PAGE_SIZE;
 		if (offset)
 			chunksize -= offset;
 		if (chunksize > size)
@@ -237,7 +237,7 @@ hugetlbfs_read_actor(struct page *page, unsigned long offset,
 /*
  * Support for read() - Find the page attached to f_mapping and copy out the
  * data. Its *very* similar to do_generic_mapping_read(), we can't use that
- * since it has PAGE_CACHE_SIZE assumptions.
+ * since it has PAGE_SIZE assumptions.
  */
 static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
@@ -285,7 +285,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 			 * We have the page, copy it to user space buffer.
 			 */
 			copied = hugetlbfs_read_actor(page, offset, to, nr);
-			page_cache_release(page);
+			put_page(page);
 		}
 		offset += copied;
 		retval += copied;
@@ -324,20 +324,62 @@ static void remove_huge_page(struct page *page)
 	delete_from_page_cache(page);
 }
 
+static void
+hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end)
+{
+	struct vm_area_struct *vma;
+
+	/*
+	 * end == 0 indicates that the entire range after
+	 * start should be unmapped.
+	 */
+	vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) {
+		unsigned long v_offset;
+		unsigned long v_end;
+
+		/*
+		 * Can the expression below overflow on 32-bit arches?
+		 * No, because the interval tree returns us only those vmas
+		 * which overlap the truncated area starting at pgoff,
+		 * and no vma on a 32-bit arch can span beyond the 4GB.
+		 */
+		if (vma->vm_pgoff < start)
+			v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT;
+		else
+			v_offset = 0;
+
+		if (!end)
+			v_end = vma->vm_end;
+		else {
+			v_end = ((end - vma->vm_pgoff) << PAGE_SHIFT)
+							+ vma->vm_start;
+			if (v_end > vma->vm_end)
+				v_end = vma->vm_end;
+		}
+
+		unmap_hugepage_range(vma, vma->vm_start + v_offset, v_end,
+									NULL);
+	}
+}
 
 /*
  * remove_inode_hugepages handles two distinct cases: truncation and hole
  * punch.  There are subtle differences in operation for each case.
-
+ *
  * truncation is indicated by end of range being LLONG_MAX
  *	In this case, we first scan the range and release found pages.
  *	After releasing pages, hugetlb_unreserve_pages cleans up region/reserv
- *	maps and global counts.
+ *	maps and global counts.  Page faults can not race with truncation
+ *	in this routine.  hugetlb_no_page() prevents page faults in the
+ *	truncated range.  It checks i_size before allocation, and again after
+ *	with the page table lock for the page held.  The same lock must be
+ *	acquired to unmap a page.
  * hole punch is indicated if end is not LLONG_MAX
  *	In the hole punch case we scan the range and release found pages.
  *	Only when releasing a page is the associated region/reserv map
  *	deleted.  The region/reserv map for ranges without associated
- *	pages are not modified.
+ *	pages are not modified.  Page faults can race with hole punch.
+ *	This is indicated if we find a mapped page.
  * Note: If the passed end of range value is beyond the end of file, but
  * not LLONG_MAX this routine still performs a hole punch operation.
  */
@@ -361,77 +403,81 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
 	next = start;
 	while (next < end) {
 		/*
-		 * Make sure to never grab more pages that we
-		 * might possibly need.
+		 * Don't grab more pages than the number left in the range.
 		 */
 		if (end - next < lookup_nr)
 			lookup_nr = end - next;
 
 		/*
-		 * This pagevec_lookup() may return pages past 'end',
-		 * so we must check for page->index > end.
+		 * When no more pages are found, we are done.
 		 */
-		if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) {
-			if (next == start)
-				break;
-			next = start;
-			continue;
-		}
+		if (!pagevec_lookup(&pvec, mapping, next, lookup_nr))
+			break;
 
 		for (i = 0; i < pagevec_count(&pvec); ++i) {
 			struct page *page = pvec.pages[i];
+			bool rsv_on_error;
 			u32 hash;
 
+			/*
+			 * The page (index) could be beyond end.  This is
+			 * only possible in the punch hole case as end is
+			 * max page offset in the truncate case.
+			 */
+			next = page->index;
+			if (next >= end)
+				break;
+
 			hash = hugetlb_fault_mutex_hash(h, current->mm,
 							&pseudo_vma,
 							mapping, next, 0);
 			mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
-			lock_page(page);
-			if (page->index >= end) {
-				unlock_page(page);
-				mutex_unlock(&hugetlb_fault_mutex_table[hash]);
-				next = end;	/* we are done */
-				break;
-			}
-
 			/*
 			 * If page is mapped, it was faulted in after being
-			 * unmapped.  Do nothing in this race case.  In the
-			 * normal case page is not mapped.
+			 * unmapped in caller.  Unmap (again) now after taking
+			 * the fault mutex.  The mutex will prevent faults
+			 * until we finish removing the page.
+			 *
+			 * This race can only happen in the hole punch case.
+			 * Getting here in a truncate operation is a bug.
 			 */
-			if (!page_mapped(page)) {
-				bool rsv_on_error = !PagePrivate(page);
-				/*
-				 * We must free the huge page and remove
-				 * from page cache (remove_huge_page) BEFORE
-				 * removing the region/reserve map
-				 * (hugetlb_unreserve_pages).  In rare out
-				 * of memory conditions, removal of the
-				 * region/reserve map could fail.  Before
-				 * free'ing the page, note PagePrivate which
-				 * is used in case of error.
-				 */
-				remove_huge_page(page);
-				freed++;
-				if (!truncate_op) {
-					if (unlikely(hugetlb_unreserve_pages(
-							inode, next,
-							next + 1, 1)))
-						hugetlb_fix_reserve_counts(
-							inode, rsv_on_error);
-				}
+			if (unlikely(page_mapped(page))) {
+				BUG_ON(truncate_op);
+
+				i_mmap_lock_write(mapping);
+				hugetlb_vmdelete_list(&mapping->i_mmap,
+					next * pages_per_huge_page(h),
+					(next + 1) * pages_per_huge_page(h));
+				i_mmap_unlock_write(mapping);
 			}
 
-			if (page->index > next)
-				next = page->index;
+			lock_page(page);
+			/*
+			 * We must free the huge page and remove from page
+			 * cache (remove_huge_page) BEFORE removing the
+			 * region/reserve map (hugetlb_unreserve_pages).  In
+			 * rare out of memory conditions, removal of the
+			 * region/reserve map could fail.  Before free'ing
+			 * the page, note PagePrivate which is used in case
+			 * of error.
+			 */
+			rsv_on_error = !PagePrivate(page);
+			remove_huge_page(page);
+			freed++;
+			if (!truncate_op) {
+				if (unlikely(hugetlb_unreserve_pages(inode,
+							next, next + 1, 1)))
+					hugetlb_fix_reserve_counts(inode,
+								rsv_on_error);
+			}
 
-			++next;
 			unlock_page(page);
-
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		}
+		++next;
 		huge_pagevec_release(&pvec);
+		cond_resched();
 	}
 
 	if (truncate_op)
@@ -450,41 +496,6 @@ static void hugetlbfs_evict_inode(struct inode *inode)
 	clear_inode(inode);
 }
 
-static inline void
-hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end)
-{
-	struct vm_area_struct *vma;
-
-	/*
-	 * end == 0 indicates that the entire range after
-	 * start should be unmapped.
-	 */
-	vma_interval_tree_foreach(vma, root, start, end ? end : ULONG_MAX) {
-		unsigned long v_offset;
-
-		/*
-		 * Can the expression below overflow on 32-bit arches?
-		 * No, because the interval tree returns us only those vmas
-		 * which overlap the truncated area starting at pgoff,
-		 * and no vma on a 32-bit arch can span beyond the 4GB.
-		 */
-		if (vma->vm_pgoff < start)
-			v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT;
-		else
-			v_offset = 0;
-
-		if (end) {
-			end = ((end - start) << PAGE_SHIFT) +
-			       vma->vm_start + v_offset;
-			if (end > vma->vm_end)
-				end = vma->vm_end;
-		} else
-			end = vma->vm_end;
-
-		unmap_hugepage_range(vma, vma->vm_start + v_offset, end, NULL);
-	}
-}
-
 static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 {
 	pgoff_t pgoff;
@@ -519,7 +530,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	if (hole_end > hole_start) {
 		struct address_space *mapping = inode->i_mapping;
 
-		mutex_lock(&inode->i_mutex);
+		inode_lock(inode);
 		i_mmap_lock_write(mapping);
 		if (!RB_EMPTY_ROOT(&mapping->i_mmap))
 			hugetlb_vmdelete_list(&mapping->i_mmap,
@@ -527,7 +538,7 @@ static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 						hole_end  >> PAGE_SHIFT);
 		i_mmap_unlock_write(mapping);
 		remove_inode_hugepages(inode, hole_start, hole_end);
-		mutex_unlock(&inode->i_mutex);
+		inode_unlock(inode);
 	}
 
 	return 0;
@@ -561,7 +572,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	start = offset >> hpage_shift;
 	end = (offset + len + hpage_size - 1) >> hpage_shift;
 
-	mutex_lock(&inode->i_mutex);
+	inode_lock(inode);
 
 	/* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */
 	error = inode_newsize_ok(inode, offset + len);
@@ -647,11 +658,8 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 	if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
 		i_size_write(inode, offset + len);
 	inode->i_ctime = CURRENT_TIME;
-	spin_lock(&inode->i_lock);
-	inode->i_private = NULL;
-	spin_unlock(&inode->i_lock);
 out:
-	mutex_unlock(&inode->i_mutex);
+	inode_unlock(inode);
 	return error;
 }
 
@@ -709,7 +717,7 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 /*
  * Hugetlbfs is not reclaimable; therefore its i_mmap_rwsem will never
  * be taken from reclaim -- unlike regular filesystems. This needs an
- * annotation because huge_pmd_share() does an allocation under
+ * annotation because huge_pmd_share() does an allocation under hugetlb's
  * i_mmap_rwsem.
  */
 static struct lock_class_key hugetlbfs_i_mmap_rwsem_key;
@@ -739,7 +747,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		/*
 		 * The policy is initialized here even if we are creating a
 		 * private inode because initialization simply creates an
-		 * an empty rb tree and calls spin_lock_init(), later when we
+		 * an empty rb tree and calls rwlock_init(), later when we
 		 * call mpol_free_shared_policy() it will just return because
 		 * the rb tree will still be empty.
 		 */
@@ -761,6 +769,7 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 			break;
 		case S_IFLNK:
 			inode->i_op = &page_symlink_inode_operations;
+			inode_nohighmem(inode);
 			break;
 		}
 		lockdep_annotate_inode_mutex_key(inode);
@@ -1202,7 +1211,6 @@ static struct file_system_type hugetlbfs_fs_type = {
 	.mount		= hugetlbfs_mount,
 	.kill_sb	= kill_litter_super,
 };
-MODULE_ALIAS_FS("hugetlbfs");
 
 static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE];
 
@@ -1322,7 +1330,7 @@ static int __init init_hugetlbfs_fs(void)
 	error = -ENOMEM;
 	hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
 					sizeof(struct hugetlbfs_inode_info),
-					0, 0, init_once);
+					0, SLAB_ACCOUNT, init_once);
 	if (hugetlbfs_inode_cachep == NULL)
 		goto out2;
 
@@ -1356,26 +1364,4 @@ static int __init init_hugetlbfs_fs(void)
  out2:
 	return error;
 }
-
-static void __exit exit_hugetlbfs_fs(void)
-{
-	struct hstate *h;
-	int i;
-
-
-	/*
-	 * Make sure all delayed rcu free inodes are flushed before we
-	 * destroy cache.
-	 */
-	rcu_barrier();
-	kmem_cache_destroy(hugetlbfs_inode_cachep);
-	i = 0;
-	for_each_hstate(h)
-		kern_unmount(hugetlbfs_vfsmount[i++]);
-	unregister_filesystem(&hugetlbfs_fs_type);
-}
-
-module_init(init_hugetlbfs_fs)
-module_exit(exit_hugetlbfs_fs)
-
-MODULE_LICENSE("GPL");
+fs_initcall(init_hugetlbfs_fs)