[PATCH v3 01/13] mm: hugetlb: Track used_hpages when getting/putting pages from subpool

From: Ackerley Tng <[email protected]>

hugepage_subpool_put_pages() currently has two distinct responsibilities
that conflict:

1. When size is specified for the mount, max_hpages != -1: Keep track of
   total active pages (allocated + reserved) and decrement this count
   (used_hpages) when a page is freed or allocation fails.
2. When min_size is specified for the mount, min_hpages != -1: Ensure we
   don't drop below the guaranteed minimum, and restore a reservation
   (rsv_hpages) if we do.

This causes trouble because when allocation fails (refer to
alloc_hugetlb_folio()) if gbl_chg = 1 (i.e. no subpool reservation was
taken):

+ To keep used_hpages consistent, HugeTLB needs to call
  hugepage_subpool_put_pages() to restore undo used_hpages being
  incremented
+ But can't call hugepage_subpool_put_pages() if no reservation was
  consumed.

One option would be to conditionally do subpool tracking updates outside of
the hugepage_subpool_put_pages() function, but that would spread logic all
over.

Instead, always track used_hpages, regardless of whether a max_size was
requested for the mount, so that the subpool always knows how many pages
were allocated through it. Every page allocated through the subpool
increments used_hpages, regardless of whether a reservation was taken from
it.

Conceptually, now, every allocation involving a subpool uses a page from
the subpool, which must be returned to the subpool. Every page taken from
the subpool tries to use a subpool reservation. Restoring a page to the
subpool reservations only if the page was taken from subpool
reservations. (If used_hpages >= min_hpages, the page must have not have
been taken from the reservations.)

Always tracking used_hpages provides the subpool with information of both
used and reserved counts to make the correct decision for both max_size and
min_size correctly.

With used_hpages always tracked,

+ subpool_is_free() can be simplified, such that the subpool can be
  declared free if there are no more pages in use.
+ open-coding in hugetlb_reserve_pages() can be removed.

Also update the documentation for used_hpages, since it no longer matters
whether the used pages count against the maximum.

Also update statfs reporting. Previously, if max_hpages is negative,
used_hpages is static at 0, so returning max_hpages - used_hpages returns
-1 and is always correct. Now, if the subpool doesn't have a maximum
requested size, indicate no limit for free pages (-1). If it does have a
maximum size, report the difference between the requested size and the
number of used pages. This difference is always positive, because if the
mount does have a maximum size, hugepage_subpool_get_pages() ensures that
the subpool usage never exceeds the maximum.

This fixes a bug in hugetlb_unreserve_pages(), where pages are returned to
the subpool regardless of whether it consumed a reservation. The
corresponding bug in the failure handling path of alloc_hugetlb_folio() was
fixed in a833a693a490e.

Fixes: 1c5ecae3a93fa ("hugetlbfs: add minimum size accounting to subpools")
Cc: [email protected]
Signed-off-by: Ackerley Tng <[email protected]>
---
 fs/hugetlbfs/inode.c    |  8 ++++--
 include/linux/hugetlb.h |  4 +--
 mm/hugetlb.c            | 71 +++++++++++++++++++++++--------------------------
 3 files changed, 41 insertions(+), 42 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 216e1a0dd0b23..26c0187340636 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1109,8 +1109,12 @@ static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 			spin_lock_irq(&sbinfo->spool->lock);
 			buf->f_blocks = sbinfo->spool->max_hpages;
-			free_pages = sbinfo->spool->max_hpages
-				- sbinfo->spool->used_hpages;
+			if (sbinfo->spool->max_hpages == -1) {
+				free_pages = -1;
+			} else {
+				free_pages = sbinfo->spool->max_hpages -
+					     sbinfo->spool->used_hpages;
+			}
 			buf->f_bavail = buf->f_bfree = free_pages;
 			spin_unlock_irq(&sbinfo->spool->lock);
 			buf->f_files = sbinfo->max_inodes;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 2abaf99321e90..34b9a3e1be0fa 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -38,8 +38,8 @@ struct hugepage_subpool {
 	spinlock_t lock;
 	long count;
 	long max_hpages;	/* Maximum huge pages or -1 if no maximum. */
-	long used_hpages;	/* Used count against maximum, includes */
-				/* both allocated and reserved pages. */
+	long used_hpages;	/* Used page count, includes both */
+				/* allocated and reserved pages. */
 	struct hstate *hstate;
 	long min_hpages;	/* Minimum huge pages or -1 if no minimum. */
 	long rsv_hpages;	/* Pages reserved against global pool to */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 571212b80835e..eef9610a0593c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -129,12 +129,8 @@ static inline bool subpool_is_free(struct hugepage_subpool *spool)
 {
 	if (spool->count)
 		return false;
-	if (spool->max_hpages != -1)
-		return spool->used_hpages == 0;
-	if (spool->min_hpages != -1)
-		return spool->rsv_hpages == spool->min_hpages;
 
-	return true;
+	return spool->used_hpages == 0;
 }
 
 static inline void unlock_or_release_subpool(struct hugepage_subpool *spool,
@@ -205,15 +201,14 @@ static long hugepage_subpool_get_pages(struct hugepage_subpool *spool,
 
 	spin_lock_irq(&spool->lock);
 
-	if (spool->max_hpages != -1) {		/* maximum size accounting */
-		if ((spool->used_hpages + delta) <= spool->max_hpages)
-			spool->used_hpages += delta;
-		else {
-			ret = -ENOMEM;
-			goto unlock_ret;
-		}
+	if (spool->max_hpages != -1 &&
+	    spool->used_hpages + delta > spool->max_hpages) {
+		ret = -ENOMEM;
+		goto unlock_ret;
 	}
 
+	spool->used_hpages += delta;
+
 	/* minimum size accounting */
 	if (spool->min_hpages != -1 && spool->rsv_hpages) {
 		if (delta > spool->rsv_hpages) {
@@ -251,19 +246,24 @@ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool,
 
 	spin_lock_irqsave(&spool->lock, flags);
 
-	if (spool->max_hpages != -1)		/* maximum size accounting */
-		spool->used_hpages -= delta;
+	spool->used_hpages -= delta;
 
 	 /* minimum size accounting */
 	if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) {
-		if (spool->rsv_hpages + delta <= spool->min_hpages)
+		/*
+		 * limit is the maximum number of reservations that
+		 * can be restored to this subpool.
+		 */
+		long limit = spool->min_hpages - spool->used_hpages;
+
+		if (spool->rsv_hpages + delta <= limit)
 			ret = 0;
 		else
-			ret = spool->rsv_hpages + delta - spool->min_hpages;
+			ret = spool->rsv_hpages + delta - limit;
 
 		spool->rsv_hpages += delta;
-		if (spool->rsv_hpages > spool->min_hpages)
-			spool->rsv_hpages = spool->min_hpages;
+		if (spool->rsv_hpages > limit)
+			spool->rsv_hpages = limit;
 	}
 
 	/*
@@ -6542,7 +6542,7 @@ long hugetlb_reserve_pages(struct inode *inode,
 		struct vm_area_struct *vma,
 		vma_flags_t vma_flags)
 {
-	long chg = -1, add = -1, spool_resv, gbl_resv;
+	long chg = -1, add = -1, gbl_resv;
 	struct hstate *h = hstate_inode(inode);
 	struct hugepage_subpool *spool = subpool_inode(inode);
 	struct resv_map *resv_map;
@@ -6687,26 +6687,21 @@ long hugetlb_reserve_pages(struct inode *inode,
 	}
 	return chg;
 
-out_put_pages:
-	spool_resv = chg - gbl_reserve;
-	if (spool_resv) {
-		/* put sub pool's reservation back, chg - gbl_reserve */
-		gbl_resv = hugepage_subpool_put_pages(spool, spool_resv);
-		/*
-		 * subpool's reserved pages can not be put back due to race,
-		 * return to hstate.
-		 */
-		hugetlb_acct_memory(h, -gbl_resv);
-	}
-	/* Restore used_hpages for pages that failed global reservation */
-	if (gbl_reserve && spool) {
-		unsigned long flags;
+ out_put_pages:
+	/*
+	 * Return all that was requested from the subpool, let subpool
+	 * tell us the new number of reservations that need to be
+	 * returned to the global pool.
+	 */
+	gbl_resv = hugepage_subpool_put_pages(spool, chg);
+	/*
+	 * There may be a difference between the number of
+	 * reservations to consume and the number to restore now if
+	 * there are multiple threads interacting with the subpool -
+	 * restore the difference.
+	 */
+	hugetlb_acct_memory(h, -(gbl_resv - gbl_reserve));
 
-		spin_lock_irqsave(&spool->lock, flags);
-		if (spool->max_hpages != -1)
-			spool->used_hpages -= gbl_reserve;
-		unlock_or_release_subpool(spool, flags);
-	}
 out_uncharge_cgroup:
 	hugetlb_cgroup_uncharge_cgroup_rsvd(hstate_index(h),
 					    chg * pages_per_huge_page(h), h_cg);

-- 
2.55.0.229.g6434b31f56-goog