hugetlbfs: accept subpool min_size mount option and setup accordingly

Make 'min_size=<value>' be an option when mounting a hugetlbfs.  This
option takes the same value as the 'size' option.  min_size can be
specified without specifying size.  If both are specified, min_size must
be less that or equal to size else the mount will fail.  If min_size is
specified, then at mount time an attempt is made to reserve min_size
pages.  If the reservation fails, the mount fails.  At umount time, the
reserved pages are released.

Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 71 insertions, 19 deletions

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index db76cec3ce21..3a8f12762821 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -47,9 +47,10 @@ struct hugetlbfs_config {
 	kuid_t   uid;
 	kgid_t   gid;
 	umode_t mode;
-	long	nr_blocks;
+	long	max_hpages;
 	long	nr_inodes;
 	struct hstate *hstate;
+	long    min_hpages;
 };
 
 struct hugetlbfs_inode_info {
@@ -67,7 +68,7 @@ int sysctl_hugetlb_shm_group;
 enum {
 	Opt_size, Opt_nr_inodes,
 	Opt_mode, Opt_uid, Opt_gid,
-	Opt_pagesize,
+	Opt_pagesize, Opt_min_size,
 	Opt_err,
 };
 
@@ -78,6 +79,7 @@ static const match_table_t tokens = {
 	{Opt_uid,	"uid=%u"},
 	{Opt_gid,	"gid=%u"},
 	{Opt_pagesize,	"pagesize=%s"},
+	{Opt_min_size,	"min_size=%s"},
 	{Opt_err,	NULL},
 };
 
@@ -754,14 +756,38 @@ static const struct super_operations hugetlbfs_ops = {
 	.show_options	= generic_show_options,
 };
 
+enum { NO_SIZE, SIZE_STD, SIZE_PERCENT };
+
+/*
+ * Convert size option passed from command line to number of huge pages
+ * in the pool specified by hstate.  Size option could be in bytes
+ * (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT).
+ */
+static long long
+hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt,
+								int val_type)
+{
+	if (val_type == NO_SIZE)
+		return -1;
+
+	if (val_type == SIZE_PERCENT) {
+		size_opt <<= huge_page_shift(h);
+		size_opt *= h->max_huge_pages;
+		do_div(size_opt, 100);
+	}
+
+	size_opt >>= huge_page_shift(h);
+	return size_opt;
+}
+
 static int
 hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
 {
 	char *p, *rest;
 	substring_t args[MAX_OPT_ARGS];
 	int option;
-	unsigned long long size = 0;
-	enum { NO_SIZE, SIZE_STD, SIZE_PERCENT } setsize = NO_SIZE;
+	unsigned long long max_size_opt = 0, min_size_opt = 0;
+	int max_val_type = NO_SIZE, min_val_type = NO_SIZE;
 
 	if (!options)
 		return 0;
@@ -799,10 +825,10 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
 			/* memparse() will accept a K/M/G without a digit */
 			if (!isdigit(*args[0].from))
 				goto bad_val;
-			size = memparse(args[0].from, &rest);
-			setsize = SIZE_STD;
+			max_size_opt = memparse(args[0].from, &rest);
+			max_val_type = SIZE_STD;
 			if (*rest == '%')
-				setsize = SIZE_PERCENT;
+				max_val_type = SIZE_PERCENT;
 			break;
 		}
 
@@ -825,6 +851,17 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
 			break;
 		}
 
+		case Opt_min_size: {
+			/* memparse() will accept a K/M/G without a digit */
+			if (!isdigit(*args[0].from))
+				goto bad_val;
+			min_size_opt = memparse(args[0].from, &rest);
+			min_val_type = SIZE_STD;
+			if (*rest == '%')
+				min_val_type = SIZE_PERCENT;
+			break;
+		}
+
 		default:
 			pr_err("Bad mount option: \"%s\"\n", p);
 			return -EINVAL;
@@ -832,15 +869,22 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
 		}
 	}
 
-	/* Do size after hstate is set up */
-	if (setsize > NO_SIZE) {
-		struct hstate *h = pconfig->hstate;
-		if (setsize == SIZE_PERCENT) {
-			size <<= huge_page_shift(h);
-			size *= h->max_huge_pages;
-			do_div(size, 100);
-		}
-		pconfig->nr_blocks = (size >> huge_page_shift(h));
+	/*
+	 * Use huge page pool size (in hstate) to convert the size
+	 * options to number of huge pages.  If NO_SIZE, -1 is returned.
+	 */
+	pconfig->max_hpages = hugetlbfs_size_to_hpages(pconfig->hstate,
+						max_size_opt, max_val_type);
+	pconfig->min_hpages = hugetlbfs_size_to_hpages(pconfig->hstate,
+						min_size_opt, min_val_type);
+
+	/*
+	 * If max_size was specified, then min_size must be smaller
+	 */
+	if (max_val_type > NO_SIZE &&
+	    pconfig->min_hpages > pconfig->max_hpages) {
+		pr_err("minimum size can not be greater than maximum size\n");
+		return -EINVAL;
 	}
 
 	return 0;
@@ -859,12 +903,13 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
 
 	save_mount_options(sb, data);
 
-	config.nr_blocks = -1; /* No limit on size by default */
+	config.max_hpages = -1; /* No limit on size by default */
 	config.nr_inodes = -1; /* No limit on number of inodes by default */
 	config.uid = current_fsuid();
 	config.gid = current_fsgid();
 	config.mode = 0755;
 	config.hstate = &default_hstate;
+	config.min_hpages = -1; /* No default minimum size */
 	ret = hugetlbfs_parse_options(data, &config);
 	if (ret)
 		return ret;
@@ -878,8 +923,15 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
 	sbinfo->max_inodes = config.nr_inodes;
 	sbinfo->free_inodes = config.nr_inodes;
 	sbinfo->spool = NULL;
-	if (config.nr_blocks != -1) {
-		sbinfo->spool = hugepage_new_subpool(config.nr_blocks);
+	/*
+	 * Allocate and initialize subpool if maximum or minimum size is
+	 * specified.  Any needed reservations (for minimim size) are taken
+	 * taken when the subpool is created.
+	 */
+	if (config.max_hpages != -1 || config.min_hpages != -1) {
+		sbinfo->spool = hugepage_new_subpool(config.hstate,
+							config.max_hpages,
+							config.min_hpages);
 		if (!sbinfo->spool)
 			goto out_free;
 	}