1 files changed, 284 insertions, 18 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 973c24ce59ad..316adb968b65 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -12,6 +12,7 @@
 #include <linux/thread_info.h>
 #include <asm/current.h>
 #include <linux/sched.h>		/* remove ASAP */
+#include <linux/falloc.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/file.h>
@@ -84,6 +85,29 @@ static const match_table_t tokens = {
 	{Opt_err,	NULL},
 };
 
+#ifdef CONFIG_NUMA
+static inline void hugetlb_set_vma_policy(struct vm_area_struct *vma,
+					struct inode *inode, pgoff_t index)
+{
+	vma->vm_policy = mpol_shared_policy_lookup(&HUGETLBFS_I(inode)->policy,
+							index);
+}
+
+static inline void hugetlb_drop_vma_policy(struct vm_area_struct *vma)
+{
+	mpol_cond_put(vma->vm_policy);
+}
+#else
+static inline void hugetlb_set_vma_policy(struct vm_area_struct *vma,
+					struct inode *inode, pgoff_t index)
+{
+}
+
+static inline void hugetlb_drop_vma_policy(struct vm_area_struct *vma)
+{
+}
+#endif
+
 static void huge_pagevec_release(struct pagevec *pvec)
 {
 	int i;
@@ -293,26 +317,61 @@ static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
 	return -EINVAL;
 }
 
-static void truncate_huge_page(struct page *page)
+static void remove_huge_page(struct page *page)
 {
 	ClearPageDirty(page);
 	ClearPageUptodate(page);
 	delete_from_page_cache(page);
 }
 
-static void truncate_hugepages(struct inode *inode, loff_t lstart)
+
+/*
+ * 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.
+ * 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.
+ * 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.
+ */
+static void remove_inode_hugepages(struct inode *inode, loff_t lstart,
+				   loff_t lend)
 {
 	struct hstate *h = hstate_inode(inode);
 	struct address_space *mapping = &inode->i_data;
 	const pgoff_t start = lstart >> huge_page_shift(h);
+	const pgoff_t end = lend >> huge_page_shift(h);
+	struct vm_area_struct pseudo_vma;
 	struct pagevec pvec;
 	pgoff_t next;
 	int i, freed = 0;
+	long lookup_nr = PAGEVEC_SIZE;
+	bool truncate_op = (lend == LLONG_MAX);
 
+	memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
+	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
 	pagevec_init(&pvec, 0);
 	next = start;
-	while (1) {
-		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+	while (next < end) {
+		/*
+		 * Make sure to never grab more pages that we
+		 * might possibly need.
+		 */
+		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.
+		 */
+		if (!pagevec_lookup(&pvec, mapping, next, lookup_nr)) {
 			if (next == start)
 				break;
 			next = start;
@@ -321,26 +380,69 @@ static void truncate_hugepages(struct inode *inode, loff_t lstart)
 
 		for (i = 0; i < pagevec_count(&pvec); ++i) {
 			struct page *page = pvec.pages[i];
+			u32 hash;
+
+			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.
+			 */
+			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 (page->index > next)
 				next = page->index;
+
 			++next;
-			truncate_huge_page(page);
 			unlock_page(page);
-			freed++;
+
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 		}
 		huge_pagevec_release(&pvec);
 	}
-	BUG_ON(!lstart && mapping->nrpages);
-	hugetlb_unreserve_pages(inode, start, freed);
+
+	if (truncate_op)
+		(void)hugetlb_unreserve_pages(inode, start, LONG_MAX, freed);
 }
 
 static void hugetlbfs_evict_inode(struct inode *inode)
 {
 	struct resv_map *resv_map;
 
-	truncate_hugepages(inode, 0);
+	remove_inode_hugepages(inode, 0, LLONG_MAX);
 	resv_map = (struct resv_map *)inode->i_mapping->private_data;
 	/* root inode doesn't have the resv_map, so we should check it */
 	if (resv_map)
@@ -349,11 +451,15 @@ static void hugetlbfs_evict_inode(struct inode *inode)
 }
 
 static inline void
-hugetlb_vmtruncate_list(struct rb_root *root, pgoff_t pgoff)
+hugetlb_vmdelete_list(struct rb_root *root, pgoff_t start, pgoff_t end)
 {
 	struct vm_area_struct *vma;
 
-	vma_interval_tree_foreach(vma, root, pgoff, ULONG_MAX) {
+	/*
+	 * 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;
 
 		/*
@@ -362,13 +468,20 @@ hugetlb_vmtruncate_list(struct rb_root *root, pgoff_t pgoff)
 		 * 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 < pgoff)
-			v_offset = (pgoff - vma->vm_pgoff) << PAGE_SHIFT;
+		if (vma->vm_pgoff < start)
+			v_offset = (start - vma->vm_pgoff) << PAGE_SHIFT;
 		else
 			v_offset = 0;
 
-		unmap_hugepage_range(vma, vma->vm_start + v_offset,
-				     vma->vm_end, NULL);
+		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);
 	}
 }
 
@@ -384,12 +497,164 @@ static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
 	i_size_write(inode, offset);
 	i_mmap_lock_write(mapping);
 	if (!RB_EMPTY_ROOT(&mapping->i_mmap))
-		hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
+		hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0);
 	i_mmap_unlock_write(mapping);
-	truncate_hugepages(inode, offset);
+	remove_inode_hugepages(inode, offset, LLONG_MAX);
 	return 0;
 }
 
+static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
+{
+	struct hstate *h = hstate_inode(inode);
+	loff_t hpage_size = huge_page_size(h);
+	loff_t hole_start, hole_end;
+
+	/*
+	 * For hole punch round up the beginning offset of the hole and
+	 * round down the end.
+	 */
+	hole_start = round_up(offset, hpage_size);
+	hole_end = round_down(offset + len, hpage_size);
+
+	if (hole_end > hole_start) {
+		struct address_space *mapping = inode->i_mapping;
+
+		mutex_lock(&inode->i_mutex);
+		i_mmap_lock_write(mapping);
+		if (!RB_EMPTY_ROOT(&mapping->i_mmap))
+			hugetlb_vmdelete_list(&mapping->i_mmap,
+						hole_start >> PAGE_SHIFT,
+						hole_end  >> PAGE_SHIFT);
+		i_mmap_unlock_write(mapping);
+		remove_inode_hugepages(inode, hole_start, hole_end);
+		mutex_unlock(&inode->i_mutex);
+	}
+
+	return 0;
+}
+
+static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
+				loff_t len)
+{
+	struct inode *inode = file_inode(file);
+	struct address_space *mapping = inode->i_mapping;
+	struct hstate *h = hstate_inode(inode);
+	struct vm_area_struct pseudo_vma;
+	struct mm_struct *mm = current->mm;
+	loff_t hpage_size = huge_page_size(h);
+	unsigned long hpage_shift = huge_page_shift(h);
+	pgoff_t start, index, end;
+	int error;
+	u32 hash;
+
+	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
+		return -EOPNOTSUPP;
+
+	if (mode & FALLOC_FL_PUNCH_HOLE)
+		return hugetlbfs_punch_hole(inode, offset, len);
+
+	/*
+	 * Default preallocate case.
+	 * For this range, start is rounded down and end is rounded up
+	 * as well as being converted to page offsets.
+	 */
+	start = offset >> hpage_shift;
+	end = (offset + len + hpage_size - 1) >> hpage_shift;
+
+	mutex_lock(&inode->i_mutex);
+
+	/* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */
+	error = inode_newsize_ok(inode, offset + len);
+	if (error)
+		goto out;
+
+	/*
+	 * Initialize a pseudo vma as this is required by the huge page
+	 * allocation routines.  If NUMA is configured, use page index
+	 * as input to create an allocation policy.
+	 */
+	memset(&pseudo_vma, 0, sizeof(struct vm_area_struct));
+	pseudo_vma.vm_flags = (VM_HUGETLB | VM_MAYSHARE | VM_SHARED);
+	pseudo_vma.vm_file = file;
+
+	for (index = start; index < end; index++) {
+		/*
+		 * This is supposed to be the vaddr where the page is being
+		 * faulted in, but we have no vaddr here.
+		 */
+		struct page *page;
+		unsigned long addr;
+		int avoid_reserve = 0;
+
+		cond_resched();
+
+		/*
+		 * fallocate(2) manpage permits EINTR; we may have been
+		 * interrupted because we are using up too much memory.
+		 */
+		if (signal_pending(current)) {
+			error = -EINTR;
+			break;
+		}
+
+		/* Set numa allocation policy based on index */
+		hugetlb_set_vma_policy(&pseudo_vma, inode, index);
+
+		/* addr is the offset within the file (zero based) */
+		addr = index * hpage_size;
+
+		/* mutex taken here, fault path and hole punch */
+		hash = hugetlb_fault_mutex_hash(h, mm, &pseudo_vma, mapping,
+						index, addr);
+		mutex_lock(&hugetlb_fault_mutex_table[hash]);
+
+		/* See if already present in mapping to avoid alloc/free */
+		page = find_get_page(mapping, index);
+		if (page) {
+			put_page(page);
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			hugetlb_drop_vma_policy(&pseudo_vma);
+			continue;
+		}
+
+		/* Allocate page and add to page cache */
+		page = alloc_huge_page(&pseudo_vma, addr, avoid_reserve);
+		hugetlb_drop_vma_policy(&pseudo_vma);
+		if (IS_ERR(page)) {
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			error = PTR_ERR(page);
+			goto out;
+		}
+		clear_huge_page(page, addr, pages_per_huge_page(h));
+		__SetPageUptodate(page);
+		error = huge_add_to_page_cache(page, mapping, index);
+		if (unlikely(error)) {
+			put_page(page);
+			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+			goto out;
+		}
+
+		mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+
+		/*
+		 * page_put due to reference from alloc_huge_page()
+		 * unlock_page because locked by add_to_page_cache()
+		 */
+		put_page(page);
+		unlock_page(page);
+	}
+
+	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);
+	return error;
+}
+
 static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
@@ -701,7 +966,8 @@ const struct file_operations hugetlbfs_file_operations = {
 	.mmap			= hugetlbfs_file_mmap,
 	.fsync			= noop_fsync,
 	.get_unmapped_area	= hugetlb_get_unmapped_area,
-	.llseek		= default_llseek,
+	.llseek			= default_llseek,
+	.fallocate		= hugetlbfs_fallocate,
 };
 
 static const struct inode_operations hugetlbfs_dir_inode_operations = {