[PATCH v4 6/6] mm: hugetlb: Refactor out hugetlb_alloc_folio()

[Ackerley Tng via B4 Relay]

From: Ackerley Tng <ackerleytng@xxxxxxxxxx>

Refactor out hugetlb_alloc_folio() from alloc_hugetlb_folio(), which
handles allocation of a folio and memory and HugeTLB charging to cgroups.

This refactoring decouples the HugeTLB page allocation from VMAs,
specifically:

1. Reservations (as in resv_map) are stored in the vma
2. mpol is stored at vma->vm_policy
3. A vma must be used for allocation even if the pages are not meant to be
   used by host process.

Without this coupling, VMAs are no longer a requirement for
allocation. This opens up the allocation routine for usage without VMAs,
which will allow guest_memfd to use HugeTLB as a more generic allocator of
huge pages, since guest_memfd memory may not have any associated VMAs by
design. In addition, direct allocations from HugeTLB could possibly be
refactored to avoid the use of a pseudo-VMA.

Also, this decouples HugeTLB page allocation from HugeTLBfs, where the
subpool is stored at the fs mount. This is also a requirement for
guest_memfd, where the plan is to have a subpool created per-fd and stored
on the inode.

Provide and use alloc_flags to allow more allocation knobs in future
without expanding the number of parameters in hugetlb_alloc_folio().

No functional change intended.

Signed-off-by: Ackerley Tng <ackerleytng@xxxxxxxxxx>
---
 include/linux/hugetlb.h |  18 +++++
 mm/hugetlb.c            | 206 ++++++++++++++++++++++++++----------------------
 2 files changed, 131 insertions(+), 93 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 2abaf99321e90..d506348ae2f0e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_HUGETLB_H
 #define _LINUX_HUGETLB_H
 
+#include <linux/mempolicy.h>
 #include <linux/mm.h>
 #include <linux/mm_types.h>
 #include <linux/mmdebug.h>
@@ -691,6 +692,23 @@ bool hugetlb_bootmem_page_zones_valid(int nid, struct huge_bootmem_page *m);
 int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list);
 int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn);
 void wait_for_freed_hugetlb_folios(void);
+
+struct mempolicy_interpreted {
+	int nid;
+	nodemask_t *nodemask;
+	enum mempolicy_mode mode;
+};
+
+enum hugetlb_alloc_flag {
+	HUGETLB_ALLOC_CHARGE_CGROUP_RSVD_BIT = 0,
+	HUGETLB_ALLOC_USE_GLOBAL_RESERVATIONS_BIT,
+};
+
+#define HUGETLB_ALLOC_CHARG_CGROUP_RSVD BIT(HUGETLB_ALLOC_CHARGE_CGROUP_RSVD_BIT)
+#define HUGETLB_ALLOC_USE_GLOBAL_RESERVATIONS BIT(HUGETLB_ALLOC_USE_GLOBAL_RESERVATIONS_BIT)
+
+struct folio *hugetlb_alloc_folio(struct hstate *h,
+		struct mempolicy_interpreted *mpoli, u8 alloc_flags);
 struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 				unsigned long addr, bool cow_from_owner);
 struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 08ac28111e694..9a639800eb79c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1317,12 +1317,6 @@ static unsigned long available_huge_pages(struct hstate *h)
 	return h->free_huge_pages - h->resv_huge_pages;
 }
 
-struct mempolicy_interpreted {
-	int nid;
-	nodemask_t *nodemask;
-	enum mempolicy_mode mode;
-};
-
 static struct folio *dequeue_hugetlb_folio(struct hstate *h, gfp_t gfp_mask,
 					   struct mempolicy_interpreted *mpoli)
 {
@@ -2812,6 +2806,104 @@ void wait_for_freed_hugetlb_folios(void)
 	flush_work(&free_hpage_work);
 }
 
+/**
+ * hugetlb_alloc_folio - Allocate a hugetlb folio.
+ * @h: Hugetlb state control block.
+ * @mpoli: Interpreted memory policy to use for allocation.
+ * @alloc_flags: Flags controlling the allocation behavior.
+ *
+ * Allocates a hugetlb folio and handles cgroup charging and global hstate
+ * reservations.
+ *
+ * Return: A pointer to the allocated folio, or an ERR_PTR on failure.
+ *         -ENOSPC if cgroup charging fails or no folio is available.
+ *         -ENOMEM if mem cgroup charging fails.
+ */
+struct folio *hugetlb_alloc_folio(struct hstate *h,
+		struct mempolicy_interpreted *mpoli, u8 alloc_flags)
+{
+	bool charge_hugetlb_cgroup_rsvd = alloc_flags &
+					  HUGETLB_ALLOC_CHARG_CGROUP_RSVD;
+	bool use_global_reservation = alloc_flags &
+				      HUGETLB_ALLOC_USE_GLOBAL_RESERVATIONS;
+	size_t nr_pages = pages_per_huge_page(h);
+	struct hugetlb_cgroup *h_cg_rsvd = NULL;
+	struct hugetlb_cgroup *h_cg = NULL;
+	gfp_t gfp = htlb_alloc_mask(h);
+	int idx = hstate_index(h);
+	struct folio *folio;
+	int ret;
+
+	if (charge_hugetlb_cgroup_rsvd &&
+	    hugetlb_cgroup_charge_cgroup_rsvd(idx, nr_pages, &h_cg_rsvd))
+		return ERR_PTR(-ENOSPC);
+
+	if (hugetlb_cgroup_charge_cgroup(idx, nr_pages, &h_cg)) {
+		ret = -ENOSPC;
+		goto err_uncharge_hugetlb_cgroup_rsvd;
+	}
+
+	spin_lock_irq(&hugetlb_lock);
+
+	folio = NULL;
+	if (use_global_reservation || available_huge_pages(h))
+		folio = dequeue_hugetlb_folio(h, gfp, mpoli);
+
+	if (!folio) {
+		spin_unlock_irq(&hugetlb_lock);
+		folio = alloc_buddy_hugetlb_folio(h, gfp, mpoli);
+		if (!folio) {
+			ret = -ENOSPC;
+			goto err_uncharge_hugetlb_cgroup;
+		}
+		spin_lock_irq(&hugetlb_lock);
+		list_add(&folio->lru, &h->hugepage_activelist);
+		folio_ref_unfreeze(folio, 1);
+	}
+
+	if (use_global_reservation) {
+		folio_set_hugetlb_restore_reserve(folio);
+		h->resv_huge_pages--;
+	}
+
+	hugetlb_cgroup_commit_charge(idx, nr_pages, h_cg, folio);
+
+	if (charge_hugetlb_cgroup_rsvd) {
+		hugetlb_cgroup_commit_charge_rsvd(idx, nr_pages, h_cg_rsvd,
+						  folio);
+	}
+
+	spin_unlock_irq(&hugetlb_lock);
+
+	ret = mem_cgroup_charge_hugetlb(folio, gfp | __GFP_RETRY_MAYFAIL);
+	/*
+	 * Unconditionally increment NR_HUGETLB here because if
+	 * mem_cgroup_charge_hugetlb failed, freeing the page will
+	 * decrement NR_HUGETLB.
+	 */
+	lruvec_stat_mod_folio(folio, NR_HUGETLB, nr_pages);
+
+	if (ret == -ENOMEM) {
+		free_huge_folio(folio);
+		/*
+		 * Skip uncharging hugetlb_cgroup since the charges
+		 * were committed to the folio and freeing the folio
+		 * would have cleared those up.
+		 */
+		return ERR_PTR(ret);
+	}
+
+	return folio;
+
+ err_uncharge_hugetlb_cgroup:
+	hugetlb_cgroup_uncharge_cgroup(idx, nr_pages, h_cg);
+ err_uncharge_hugetlb_cgroup_rsvd:
+	if (charge_hugetlb_cgroup_rsvd)
+		hugetlb_cgroup_uncharge_cgroup_rsvd(idx, nr_pages, h_cg_rsvd);
+
+	return ERR_PTR(ret);
+}
+
 typedef enum {
 	/*
 	 * For either 0/1: we checked the per-vma resv map, and one resv
@@ -2846,16 +2938,13 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	struct folio *folio;
 	long retval, gbl_chg, gbl_reserve;
 	map_chg_state map_chg;
-	int ret, idx;
-	struct hugetlb_cgroup *h_cg = NULL;
-	struct hugetlb_cgroup *h_cg_rsvd = NULL;
 	struct mempolicy_interpreted mpoli;
 	gfp_t gfp = htlb_alloc_mask(h);
 	struct mempolicy *mpol;
 	nodemask_t *nodemask;
+	u8 alloc_flags = 0;
 	int nid;
-
-	idx = hstate_index(h);
+	int ret;
 
 	/* Whether we need a separate per-vma reservation? */
 	if (cow_from_owner) {
@@ -2900,23 +2989,18 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 	}
 
 	/*
-	 * If this allocation is not consuming a per-vma reservation,
-	 * charge the hugetlb cgroup now.
+	 * If allocation doesn't reuse a reservation in the resv_map,
+	 * charge for the reservation.
 	 */
-	if (map_chg) {
-		ret = hugetlb_cgroup_charge_cgroup_rsvd(
-			idx, pages_per_huge_page(h), &h_cg_rsvd);
-		if (ret) {
-			ret = -ENOSPC;
-			goto out_subpool_put;
-		}
-	}
+	if (map_chg != MAP_CHG_REUSE)
+		alloc_flags |= HUGETLB_ALLOC_CHARG_CGROUP_RSVD;
 
-	ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg);
-	if (ret) {
-		ret = -ENOSPC;
-		goto out_uncharge_cgroup_reservation;
-	}
+	/*
+	 * gbl_chg == 0 indicates a reservation exists for this
+	 * allocation, so try to use it.
+	 */
+	if (gbl_chg == 0)
+		alloc_flags |= HUGETLB_ALLOC_USE_GLOBAL_RESERVATIONS;
 
 	/* Takes reference on mpol. */
 	nid = huge_node(vma, addr, gfp, &mpol, &nodemask);
@@ -2930,69 +3014,12 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 		.nodemask = nodemask,
 	};
 
-	spin_lock_irq(&hugetlb_lock);
-
-	/*
-	 * gbl_chg == 0 indicates a reservation exists for the
-	 * allocation, so try dequeuing a page. In case there was no
-	 * reservation, try dequeuing a page if there are available
-	 * pages in the global pool.
-	 */
-	folio = NULL;
-	if (!gbl_chg || available_huge_pages(h))
-		folio = dequeue_hugetlb_folio(h, gfp, &mpoli);
-
-	if (!folio) {
-		spin_unlock_irq(&hugetlb_lock);
-		folio = alloc_buddy_hugetlb_folio(h, gfp, &mpoli);
-		if (!folio) {
-			mpol_cond_put(mpol);
-			ret = -ENOSPC;
-			goto out_uncharge_cgroup;
-		}
-		spin_lock_irq(&hugetlb_lock);
-		list_add(&folio->lru, &h->hugepage_activelist);
-		folio_ref_unfreeze(folio, 1);
-		/* Fall through */
-	}
+	folio = hugetlb_alloc_folio(h, &mpoli, alloc_flags);
 
 	mpol_cond_put(mpol);
 
-	/*
-	 * Either dequeued or buddy-allocated folio needs to add special
-	 * mark to the folio when it consumes a global reservation.
-	 */
-	if (!gbl_chg) {
-		folio_set_hugetlb_restore_reserve(folio);
-		h->resv_huge_pages--;
-	}
-
-	hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, folio);
-	/* If allocation is not consuming a reservation, also store the
-	 * hugetlb_cgroup pointer on the page.
-	 */
-	if (map_chg) {
-		hugetlb_cgroup_commit_charge_rsvd(idx, pages_per_huge_page(h),
-						  h_cg_rsvd, folio);
-	}
-
-	spin_unlock_irq(&hugetlb_lock);
-
-	ret = mem_cgroup_charge_hugetlb(folio, gfp | __GFP_RETRY_MAYFAIL);
-	/*
-	 * Unconditionally increment NR_HUGETLB here. If it turns out that
-	 * mem_cgroup_charge_hugetlb failed, then immediately free the page and
-	 * decrement NR_HUGETLB.
-	 */
-	lruvec_stat_mod_folio(folio, NR_HUGETLB, pages_per_huge_page(h));
-
-	if (ret == -ENOMEM) {
-		free_huge_folio(folio);
-		/*
-		 * Skip uncharging hugetlb_cgroup since the charges
-		 * were committed to the folio and freeing the folio
-		 * would have cleared those up.
-		 */
+	if (IS_ERR(folio)) {
+		ret = PTR_ERR(folio);
 		goto out_subpool_put;
 	}
 
@@ -3025,12 +3052,6 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 
 	return folio;
 
-out_uncharge_cgroup:
-	hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg);
-out_uncharge_cgroup_reservation:
-	if (map_chg)
-		hugetlb_cgroup_uncharge_cgroup_rsvd(idx, pages_per_huge_page(h),
-						    h_cg_rsvd);
 out_subpool_put:
 	/*
 	 * put page to subpool iff the quota of subpool's rsv_hpages is used
@@ -3041,7 +3062,6 @@ struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 		hugetlb_acct_memory(h, -gbl_reserve);
 	}
 
-
 out_end_reservation:
 	if (map_chg != MAP_CHG_ENFORCED)
 		vma_end_reservation(h, vma, addr);

-- 
2.55.0.rc0.799.gd6f94ed593-goog