The patch titled
Subject: hugetlbfs: accept subpool min_size mount option and setup accordingly
has been added to the -mm tree. Its filename is
hugetlbfs-accept-subpool-min_size-mount-option-and-setup-accordingly.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/hugetlbfs-accept-subpool-min_size-mount-option-and-setup-accordingly.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/hugetlbfs-accept-subpool-min_size-mount-option-and-setup-accordingly.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Subject: hugetlbfs: accept subpool min_size mount option and setup accordingly
Make 'min_size=' be an option when mounting a hugetlbfs. This option
takes the same value as the 'size' option. min_size can be specified with
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@xxxxxxxxxx>
Cc: Davidlohr Bueso <dave@xxxxxxxxxxxx>
Cc: Aneesh Kumar <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Andi Kleen <andi@xxxxxxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/hugetlbfs/inode.c | 75 +++++++++++++++++++++++++++++---------
include/linux/hugetlb.h | 3 +
mm/hugetlb.c | 23 ++++++++++-
3 files changed, 80 insertions(+), 21 deletions(-)
diff -puN fs/hugetlbfs/inode.c~hugetlbfs-accept-subpool-min_size-mount-option-and-setup-accordingly fs/hugetlbfs/inode.c
--- a/fs/hugetlbfs/inode.c~hugetlbfs-accept-subpool-min_size-mount-option-and-setup-accordingly
+++ a/fs/hugetlbfs/inode.c
@@ -50,6 +50,7 @@ struct hugetlbfs_config {
long nr_blocks;
long nr_inodes;
struct hstate *hstate;
+ long min_size;
};
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 +756,32 @@ static const struct super_operations hug
.show_options = generic_show_options,
};
+enum { NO_SIZE, SIZE_STD, SIZE_PERCENT };
+
+static bool
+hugetlbfs_options_setsize(struct hstate *h, long long *size, int setsize)
+{
+ if (setsize == NO_SIZE)
+ return false;
+
+ if (setsize == SIZE_PERCENT) {
+ *size <<= huge_page_shift(h);
+ *size *= h->max_huge_pages;
+ do_div(*size, 100);
+ }
+
+ *size >>= huge_page_shift(h);
+ return true;
+}
+
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 = 0, min_size = 0;
+ int max_setsize = NO_SIZE, min_setsize = NO_SIZE;
if (!options)
return 0;
@@ -799,10 +819,10 @@ hugetlbfs_parse_options(char *options, s
/* 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 = memparse(args[0].from, &rest);
+ max_setsize = SIZE_STD;
if (*rest == '%')
- setsize = SIZE_PERCENT;
+ max_setsize = SIZE_PERCENT;
break;
}
@@ -825,6 +845,17 @@ hugetlbfs_parse_options(char *options, s
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 = memparse(args[0].from, &rest);
+ min_setsize = SIZE_STD;
+ if (*rest == '%')
+ min_setsize = SIZE_PERCENT;
+ break;
+ }
+
default:
pr_err("Bad mount option: \"%s\"\n", p);
return -EINVAL;
@@ -832,15 +863,17 @@ hugetlbfs_parse_options(char *options, s
}
}
- /* 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));
+ /* Calculate number of huge pages based on hstate */
+ if (hugetlbfs_options_setsize(pconfig->hstate, &max_size, max_setsize))
+ pconfig->nr_blocks = max_size;
+ if (hugetlbfs_options_setsize(pconfig->hstate, &min_size, min_setsize))
+ pconfig->min_size = min_size;
+
+ /* If max_size specified, then min_size must be smaller */
+ if (max_setsize > NO_SIZE && min_setsize > NO_SIZE &&
+ pconfig->min_size > pconfig->nr_blocks) {
+ pr_err("minimum size can not be greater than maximum size\n");
+ return -EINVAL;
}
return 0;
@@ -865,6 +898,7 @@ hugetlbfs_fill_super(struct super_block
config.gid = current_fsgid();
config.mode = 0755;
config.hstate = &default_hstate;
+ config.min_size = 0; /* No default minimum size */
ret = hugetlbfs_parse_options(data, &config);
if (ret)
return ret;
@@ -878,8 +912,15 @@ hugetlbfs_fill_super(struct super_block
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.nr_blocks != -1 || config.min_size != 0) {
+ sbinfo->spool = hugepage_new_subpool(config.hstate,
+ config.nr_blocks,
+ config.min_size);
if (!sbinfo->spool)
goto out_free;
}
diff -puN include/linux/hugetlb.h~hugetlbfs-accept-subpool-min_size-mount-option-and-setup-accordingly include/linux/hugetlb.h
--- a/include/linux/hugetlb.h~hugetlbfs-accept-subpool-min_size-mount-option-and-setup-accordingly
+++ a/include/linux/hugetlb.h
@@ -42,7 +42,8 @@ extern int hugetlb_max_hstate __read_mos
#define for_each_hstate(h) \
for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++)
-struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
+struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long nr_blocks,
+ long min_size);
void hugepage_put_subpool(struct hugepage_subpool *spool);
int PageHuge(struct page *page);
diff -puN mm/hugetlb.c~hugetlbfs-accept-subpool-min_size-mount-option-and-setup-accordingly mm/hugetlb.c
--- a/mm/hugetlb.c~hugetlbfs-accept-subpool-min_size-mount-option-and-setup-accordingly
+++ a/mm/hugetlb.c
@@ -61,6 +61,9 @@ DEFINE_SPINLOCK(hugetlb_lock);
static int num_fault_mutexes;
static struct mutex *htlb_fault_mutex_table ____cacheline_aligned_in_smp;
+/* Forward declaration */
+static int hugetlb_acct_memory(struct hstate *h, long delta);
+
static inline void unlock_or_release_subpool(struct hugepage_subpool *spool)
{
bool free = (spool->count == 0) && (spool->used_hpages == 0);
@@ -68,12 +71,18 @@ static inline void unlock_or_release_sub
spin_unlock(&spool->lock);
/* If no pages are used, and no other handles to the subpool
- * remain, free the subpool the subpool remain */
- if (free)
+ * remain, give up any reservations mased on minimum size and
+ * free the subpool */
+ if (free) {
+ if (spool->min_hpages)
+ hugetlb_acct_memory(spool->hstate,
+ -spool->min_hpages);
kfree(spool);
+ }
}
-struct hugepage_subpool *hugepage_new_subpool(long nr_blocks)
+struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long nr_blocks,
+ long min_size)
{
struct hugepage_subpool *spool;
@@ -84,6 +93,14 @@ struct hugepage_subpool *hugepage_new_su
spin_lock_init(&spool->lock);
spool->count = 1;
spool->max_hpages = nr_blocks;
+ spool->hstate = h;
+ spool->min_hpages = min_size;
+
+ if (min_size && hugetlb_acct_memory(h, min_size)) {
+ kfree(spool);
+ return NULL;
+ }
+ spool->rsv_hpages = min_size;
return spool;
}
_
Patches currently in -mm which might be from mike.kravetz@xxxxxxxxxx are
hugetlbfs-add-minimum-size-tracking-fields-to-subpool-structure.patch
hugetlbfs-add-minimum-size-tracking-fields-to-subpool-structure-fix.patch
hugetlbfs-add-minimum-size-accounting-to-subpools.patch
hugetlbfs-add-minimum-size-accounting-to-subpools-fix.patch
hugetlbfs-accept-subpool-min_size-mount-option-and-setup-accordingly.patch
hugetlbfs-document-min_size-mount-option.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
