1 files changed, 278 insertions, 155 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c2b9ba3a54..c445e6fd85 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -35,6 +35,7 @@
 #include <linux/delayacct.h>
 #include <linux/memory.h>
 #include <linux/mm_inline.h>
+#include <linux/padata.h>
 
 #include <asm/page.h>
 #include <asm/pgalloc.h>
@@ -68,7 +69,7 @@ static bool hugetlb_cma_folio(struct folio *folio, unsigned int order)
 #endif
 static unsigned long hugetlb_cma_size __initdata;
 
-__initdata LIST_HEAD(huge_boot_pages);
+__initdata struct list_head huge_boot_pages[MAX_NUMNODES];
 
 /* for command line parsing */
 static struct hstate * __initdata parsed_hstate;
@@ -1464,15 +1465,15 @@ static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed)
  * next node from which to allocate, handling wrap at end of node
  * mask.
  */
-static int hstate_next_node_to_alloc(struct hstate *h,
+static int hstate_next_node_to_alloc(int *next_node,
 					nodemask_t *nodes_allowed)
 {
 	int nid;
 
 	VM_BUG_ON(!nodes_allowed);
 
-	nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed);
-	h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed);
+	nid = get_valid_node_allowed(*next_node, nodes_allowed);
+	*next_node = next_node_allowed(nid, nodes_allowed);
 
 	return nid;
 }
@@ -1495,10 +1496,10 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
 	return nid;
 }
 
-#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask)		\
+#define for_each_node_mask_to_alloc(next_node, nr_nodes, node, mask)		\
 	for (nr_nodes = nodes_weight(*mask);				\
 		nr_nodes > 0 &&						\
-		((node = hstate_next_node_to_alloc(hs, mask)) || 1);	\
+		((node = hstate_next_node_to_alloc(next_node, mask)) || 1);	\
 		nr_nodes--)
 
 #define for_each_node_mask_to_free(hs, nr_nodes, node, mask)		\
@@ -2334,12 +2335,13 @@ static void prep_and_add_allocated_folios(struct hstate *h,
  */
 static struct folio *alloc_pool_huge_folio(struct hstate *h,
 					nodemask_t *nodes_allowed,
-					nodemask_t *node_alloc_noretry)
+					nodemask_t *node_alloc_noretry,
+					int *next_node)
 {
 	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
 	int nr_nodes, node;
 
-	for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
+	for_each_node_mask_to_alloc(next_node, nr_nodes, node, nodes_allowed) {
 		struct folio *folio;
 
 		folio = only_alloc_fresh_hugetlb_folio(h, gfp_mask, node,
@@ -3013,21 +3015,9 @@ static int alloc_and_dissolve_hugetlb_folio(struct hstate *h,
 {
 	gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
 	int nid = folio_nid(old_folio);
-	struct folio *new_folio;
+	struct folio *new_folio = NULL;
 	int ret = 0;
 
-	/*
-	 * Before dissolving the folio, we need to allocate a new one for the
-	 * pool to remain stable.  Here, we allocate the folio and 'prep' it
-	 * by doing everything but actually updating counters and adding to
-	 * the pool.  This simplifies and let us do most of the processing
-	 * under the lock.
-	 */
-	new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid, NULL, NULL);
-	if (!new_folio)
-		return -ENOMEM;
-	__prep_new_hugetlb_folio(h, new_folio);
-
 retry:
 	spin_lock_irq(&hugetlb_lock);
 	if (!folio_test_hugetlb(old_folio)) {
@@ -3057,6 +3047,16 @@ retry:
 		cond_resched();
 		goto retry;
 	} else {
+		if (!new_folio) {
+			spin_unlock_irq(&hugetlb_lock);
+			new_folio = alloc_buddy_hugetlb_folio(h, gfp_mask, nid,
+							      NULL, NULL);
+			if (!new_folio)
+				return -ENOMEM;
+			__prep_new_hugetlb_folio(h, new_folio);
+			goto retry;
+		}
+
 		/*
 		 * Ok, old_folio is still a genuine free hugepage. Remove it from
 		 * the freelist and decrease the counters. These will be
@@ -3084,9 +3084,11 @@ retry:
 
 free_new:
 	spin_unlock_irq(&hugetlb_lock);
-	/* Folio has a zero ref count, but needs a ref to be freed */
-	folio_ref_unfreeze(new_folio, 1);
-	update_and_free_hugetlb_folio(h, new_folio, false);
+	if (new_folio) {
+		/* Folio has a zero ref count, but needs a ref to be freed */
+		folio_ref_unfreeze(new_folio, 1);
+		update_and_free_hugetlb_folio(h, new_folio, false);
+	}
 
 	return ret;
 }
@@ -3286,7 +3288,7 @@ int alloc_bootmem_huge_page(struct hstate *h, int nid)
 int __alloc_bootmem_huge_page(struct hstate *h, int nid)
 {
 	struct huge_bootmem_page *m = NULL; /* initialize for clang */
-	int nr_nodes, node;
+	int nr_nodes, node = nid;
 
 	/* do node specific alloc */
 	if (nid != NUMA_NO_NODE) {
@@ -3297,7 +3299,7 @@ int __alloc_bootmem_huge_page(struct hstate *h, int nid)
 		goto found;
 	}
 	/* allocate from next node when distributing huge pages */
-	for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
+	for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, &node_states[N_MEMORY]) {
 		m = memblock_alloc_try_nid_raw(
 				huge_page_size(h), huge_page_size(h),
 				0, MEMBLOCK_ALLOC_ACCESSIBLE, node);
@@ -3324,7 +3326,7 @@ found:
 		huge_page_size(h) - PAGE_SIZE);
 	/* Put them into a private list first because mem_map is not up yet */
 	INIT_LIST_HEAD(&m->list);
-	list_add(&m->list, &huge_boot_pages);
+	list_add(&m->list, &huge_boot_pages[node]);
 	m->hstate = h;
 	return 1;
 }
@@ -3375,8 +3377,6 @@ static void __init prep_and_add_bootmem_folios(struct hstate *h,
 	/* Send list for bulk vmemmap optimization processing */
 	hugetlb_vmemmap_optimize_folios(h, folio_list);
 
-	/* Add all new pool pages to free lists in one lock cycle */
-	spin_lock_irqsave(&hugetlb_lock, flags);
 	list_for_each_entry_safe(folio, tmp_f, folio_list, lru) {
 		if (!folio_test_hugetlb_vmemmap_optimized(folio)) {
 			/*
@@ -3389,23 +3389,25 @@ static void __init prep_and_add_bootmem_folios(struct hstate *h,
 					HUGETLB_VMEMMAP_RESERVE_PAGES,
 					pages_per_huge_page(h));
 		}
+		/* Subdivide locks to achieve better parallel performance */
+		spin_lock_irqsave(&hugetlb_lock, flags);
 		__prep_account_new_huge_page(h, folio_nid(folio));
 		enqueue_hugetlb_folio(h, folio);
+		spin_unlock_irqrestore(&hugetlb_lock, flags);
 	}
-	spin_unlock_irqrestore(&hugetlb_lock, flags);
 }
 
 /*
  * Put bootmem huge pages into the standard lists after mem_map is up.
  * Note: This only applies to gigantic (order > MAX_PAGE_ORDER) pages.
  */
-static void __init gather_bootmem_prealloc(void)
+static void __init gather_bootmem_prealloc_node(unsigned long nid)
 {
 	LIST_HEAD(folio_list);
 	struct huge_bootmem_page *m;
 	struct hstate *h = NULL, *prev_h = NULL;
 
-	list_for_each_entry(m, &huge_boot_pages, list) {
+	list_for_each_entry(m, &huge_boot_pages[nid], list) {
 		struct page *page = virt_to_page(m);
 		struct folio *folio = (void *)page;
 
@@ -3438,6 +3440,31 @@ static void __init gather_bootmem_prealloc(void)
 	prep_and_add_bootmem_folios(h, &folio_list);
 }
 
+static void __init gather_bootmem_prealloc_parallel(unsigned long start,
+						    unsigned long end, void *arg)
+{
+	int nid;
+
+	for (nid = start; nid < end; nid++)
+		gather_bootmem_prealloc_node(nid);
+}
+
+static void __init gather_bootmem_prealloc(void)
+{
+	struct padata_mt_job job = {
+		.thread_fn	= gather_bootmem_prealloc_parallel,
+		.fn_arg		= NULL,
+		.start		= 0,
+		.size		= num_node_state(N_MEMORY),
+		.align		= 1,
+		.min_chunk	= 1,
+		.max_threads	= num_node_state(N_MEMORY),
+		.numa_aware	= true,
+	};
+
+	padata_do_multithreaded(&job);
+}
+
 static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid)
 {
 	unsigned long i;
@@ -3469,6 +3496,108 @@ static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid)
 	h->max_huge_pages_node[nid] = i;
 }
 
+static bool __init hugetlb_hstate_alloc_pages_specific_nodes(struct hstate *h)
+{
+	int i;
+	bool node_specific_alloc = false;
+
+	for_each_online_node(i) {
+		if (h->max_huge_pages_node[i] > 0) {
+			hugetlb_hstate_alloc_pages_onenode(h, i);
+			node_specific_alloc = true;
+		}
+	}
+
+	return node_specific_alloc;
+}
+
+static void __init hugetlb_hstate_alloc_pages_errcheck(unsigned long allocated, struct hstate *h)
+{
+	if (allocated < h->max_huge_pages) {
+		char buf[32];
+
+		string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
+		pr_warn("HugeTLB: allocating %lu of page size %s failed.  Only allocated %lu hugepages.\n",
+			h->max_huge_pages, buf, allocated);
+		h->max_huge_pages = allocated;
+	}
+}
+
+static void __init hugetlb_pages_alloc_boot_node(unsigned long start, unsigned long end, void *arg)
+{
+	struct hstate *h = (struct hstate *)arg;
+	int i, num = end - start;
+	nodemask_t node_alloc_noretry;
+	LIST_HEAD(folio_list);
+	int next_node = first_online_node;
+
+	/* Bit mask controlling how hard we retry per-node allocations.*/
+	nodes_clear(node_alloc_noretry);
+
+	for (i = 0; i < num; ++i) {
+		struct folio *folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY],
+						&node_alloc_noretry, &next_node);
+		if (!folio)
+			break;
+
+		list_move(&folio->lru, &folio_list);
+		cond_resched();
+	}
+
+	prep_and_add_allocated_folios(h, &folio_list);
+}
+
+static unsigned long __init hugetlb_gigantic_pages_alloc_boot(struct hstate *h)
+{
+	unsigned long i;
+
+	for (i = 0; i < h->max_huge_pages; ++i) {
+		if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE))
+			break;
+		cond_resched();
+	}
+
+	return i;
+}
+
+static unsigned long __init hugetlb_pages_alloc_boot(struct hstate *h)
+{
+	struct padata_mt_job job = {
+		.fn_arg		= h,
+		.align		= 1,
+		.numa_aware	= true
+	};
+
+	job.thread_fn	= hugetlb_pages_alloc_boot_node;
+	job.start	= 0;
+	job.size	= h->max_huge_pages;
+
+	/*
+	 * job.max_threads is twice the num_node_state(N_MEMORY),
+	 *
+	 * Tests below indicate that a multiplier of 2 significantly improves
+	 * performance, and although larger values also provide improvements,
+	 * the gains are marginal.
+	 *
+	 * Therefore, choosing 2 as the multiplier strikes a good balance between
+	 * enhancing parallel processing capabilities and maintaining efficient
+	 * resource management.
+	 *
+	 * +------------+-------+-------+-------+-------+-------+
+	 * | multiplier |   1   |   2   |   3   |   4   |   5   |
+	 * +------------+-------+-------+-------+-------+-------+
+	 * | 256G 2node | 358ms | 215ms | 157ms | 134ms | 126ms |
+	 * | 2T   4node | 979ms | 679ms | 543ms | 489ms | 481ms |
+	 * | 50G  2node | 71ms  | 44ms  | 37ms  | 30ms  | 31ms  |
+	 * +------------+-------+-------+-------+-------+-------+
+	 */
+	job.max_threads	= num_node_state(N_MEMORY) * 2;
+	job.min_chunk	= h->max_huge_pages / num_node_state(N_MEMORY) / 2;
+	padata_do_multithreaded(&job);
+
+	return h->nr_huge_pages;
+}
+
 /*
  * NOTE: this routine is called in different contexts for gigantic and
  * non-gigantic pages.
@@ -3482,11 +3611,8 @@ static void __init hugetlb_hstate_alloc_pages_onenode(struct hstate *h, int nid)
  */
 static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 {
-	unsigned long i;
-	struct folio *folio;
-	LIST_HEAD(folio_list);
-	nodemask_t *node_alloc_noretry;
-	bool node_specific_alloc = false;
+	unsigned long allocated;
+	static bool initialized __initdata;
 
 	/* skip gigantic hugepages allocation if hugetlb_cma enabled */
 	if (hstate_is_gigantic(h) && hugetlb_cma_size) {
@@ -3494,66 +3620,26 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 		return;
 	}
 
-	/* do node specific alloc */
-	for_each_online_node(i) {
-		if (h->max_huge_pages_node[i] > 0) {
-			hugetlb_hstate_alloc_pages_onenode(h, i);
-			node_specific_alloc = true;
-		}
+	/* hugetlb_hstate_alloc_pages will be called many times, initialize huge_boot_pages once */
+	if (!initialized) {
+		int i = 0;
+
+		for (i = 0; i < MAX_NUMNODES; i++)
+			INIT_LIST_HEAD(&huge_boot_pages[i]);
+		initialized = true;
 	}
 
-	if (node_specific_alloc)
+	/* do node specific alloc */
+	if (hugetlb_hstate_alloc_pages_specific_nodes(h))
 		return;
 
 	/* below will do all node balanced alloc */
-	if (!hstate_is_gigantic(h)) {
-		/*
-		 * Bit mask controlling how hard we retry per-node allocations.
-		 * Ignore errors as lower level routines can deal with
-		 * node_alloc_noretry == NULL.  If this kmalloc fails at boot
-		 * time, we are likely in bigger trouble.
-		 */
-		node_alloc_noretry = kmalloc(sizeof(*node_alloc_noretry),
-						GFP_KERNEL);
-	} else {
-		/* allocations done at boot time */
-		node_alloc_noretry = NULL;
-	}
-
-	/* bit mask controlling how hard we retry per-node allocations */
-	if (node_alloc_noretry)
-		nodes_clear(*node_alloc_noretry);
-
-	for (i = 0; i < h->max_huge_pages; ++i) {
-		if (hstate_is_gigantic(h)) {
-			/*
-			 * gigantic pages not added to list as they are not
-			 * added to pools now.
-			 */
-			if (!alloc_bootmem_huge_page(h, NUMA_NO_NODE))
-				break;
-		} else {
-			folio = alloc_pool_huge_folio(h, &node_states[N_MEMORY],
-							node_alloc_noretry);
-			if (!folio)
-				break;
-			list_add(&folio->lru, &folio_list);
-		}
-		cond_resched();
-	}
-
-	/* list will be empty if hstate_is_gigantic */
-	prep_and_add_allocated_folios(h, &folio_list);
-
-	if (i < h->max_huge_pages) {
-		char buf[32];
+	if (hstate_is_gigantic(h))
+		allocated = hugetlb_gigantic_pages_alloc_boot(h);
+	else
+		allocated = hugetlb_pages_alloc_boot(h);
 
-		string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
-		pr_warn("HugeTLB: allocating %lu of page size %s failed.  Only allocated %lu hugepages.\n",
-			h->max_huge_pages, buf, i);
-		h->max_huge_pages = i;
-	}
-	kfree(node_alloc_noretry);
+	hugetlb_hstate_alloc_pages_errcheck(allocated, h);
 }
 
 static void __init hugetlb_init_hstates(void)
@@ -3655,7 +3741,7 @@ static int adjust_pool_surplus(struct hstate *h, nodemask_t *nodes_allowed,
 	VM_BUG_ON(delta != -1 && delta != 1);
 
 	if (delta < 0) {
-		for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
+		for_each_node_mask_to_alloc(&h->next_nid_to_alloc, nr_nodes, node, nodes_allowed) {
 			if (h->surplus_huge_pages_node[node])
 				goto found;
 		}
@@ -3770,7 +3856,8 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
 		cond_resched();
 
 		folio = alloc_pool_huge_folio(h, nodes_allowed,
-						node_alloc_noretry);
+						node_alloc_noretry,
+						&h->next_nid_to_alloc);
 		if (!folio) {
 			prep_and_add_allocated_folios(h, &page_list);
 			spin_lock_irq(&hugetlb_lock);
@@ -5572,6 +5659,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	struct page *page;
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
+	bool adjust_reservation = false;
 	unsigned long last_addr_mask;
 	bool force_flush = false;
 
@@ -5664,7 +5752,43 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		hugetlb_count_sub(pages_per_huge_page(h), mm);
 		hugetlb_remove_rmap(page_folio(page));
 
+		/*
+		 * Restore the reservation for anonymous page, otherwise the
+		 * backing page could be stolen by someone.
+		 * If there we are freeing a surplus, do not set the restore
+		 * reservation bit.
+		 */
+		if (!h->surplus_huge_pages && __vma_private_lock(vma) &&
+		    folio_test_anon(page_folio(page))) {
+			folio_set_hugetlb_restore_reserve(page_folio(page));
+			/* Reservation to be adjusted after the spin lock */
+			adjust_reservation = true;
+		}
+
 		spin_unlock(ptl);
+
+		/*
+		 * Adjust the reservation for the region that will have the
+		 * reserve restored. Keep in mind that vma_needs_reservation() changes
+		 * resv->adds_in_progress if it succeeds. If this is not done,
+		 * do_exit() will not see it, and will keep the reservation
+		 * forever.
+		 */
+		if (adjust_reservation) {
+			int rc = vma_needs_reservation(h, vma, address);
+
+			if (rc < 0)
+				/* Pressumably allocate_file_region_entries failed
+				 * to allocate a file_region struct. Clear
+				 * hugetlb_restore_reserve so that global reserve
+				 * count will not be incremented by free_huge_folio.
+				 * Act as if we consumed the reservation.
+				 */
+				folio_clear_hugetlb_restore_reserve(page_folio(page));
+			else if (rc)
+				vma_add_reservation(h, vma, address);
+		}
+
 		tlb_remove_page_size(tlb, page, huge_page_size(h));
 		/*
 		 * Bail out after unmapping reference page if supplied
@@ -5813,7 +5937,8 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
  */
 static vm_fault_t hugetlb_wp(struct mm_struct *mm, struct vm_area_struct *vma,
 		       unsigned long address, pte_t *ptep, unsigned int flags,
-		       struct folio *pagecache_folio, spinlock_t *ptl)
+		       struct folio *pagecache_folio, spinlock_t *ptl,
+		       struct vm_fault *vmf)
 {
 	const bool unshare = flags & FAULT_FLAG_UNSHARE;
 	pte_t pte = huge_ptep_get(ptep);
@@ -5947,10 +6072,9 @@ retry_avoidcopy:
 	 * When the original hugepage is shared one, it does not have
 	 * anon_vma prepared.
 	 */
-	if (unlikely(anon_vma_prepare(vma))) {
-		ret = VM_FAULT_OOM;
+	ret = vmf_anon_prepare(vmf);
+	if (unlikely(ret))
 		goto out_release_all;
-	}
 
 	if (copy_user_large_folio(new_folio, old_folio, address, vma)) {
 		ret = VM_FAULT_HWPOISON_LARGE;
@@ -6047,39 +6171,21 @@ int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping
 	return 0;
 }
 
-static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma,
+static inline vm_fault_t hugetlb_handle_userfault(struct vm_fault *vmf,
 						  struct address_space *mapping,
-						  pgoff_t idx,
-						  unsigned int flags,
-						  unsigned long haddr,
-						  unsigned long addr,
 						  unsigned long reason)
 {
 	u32 hash;
-	struct vm_fault vmf = {
-		.vma = vma,
-		.address = haddr,
-		.real_address = addr,
-		.flags = flags,
-
-		/*
-		 * Hard to debug if it ends up being
-		 * used by a callee that assumes
-		 * something about the other
-		 * uninitialized fields... same as in
-		 * memory.c
-		 */
-	};
 
 	/*
 	 * vma_lock and hugetlb_fault_mutex must be dropped before handling
 	 * userfault. Also mmap_lock could be dropped due to handling
 	 * userfault, any vma operation should be careful from here.
 	 */
-	hugetlb_vma_unlock_read(vma);
-	hash = hugetlb_fault_mutex_hash(mapping, idx);
+	hugetlb_vma_unlock_read(vmf->vma);
+	hash = hugetlb_fault_mutex_hash(mapping, vmf->pgoff);
 	mutex_unlock(&hugetlb_fault_mutex_table[hash]);
-	return handle_userfault(&vmf, reason);
+	return handle_userfault(vmf, reason);
 }
 
 /*
@@ -6103,7 +6209,8 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 			struct vm_area_struct *vma,
 			struct address_space *mapping, pgoff_t idx,
 			unsigned long address, pte_t *ptep,
-			pte_t old_pte, unsigned int flags)
+			pte_t old_pte, unsigned int flags,
+			struct vm_fault *vmf)
 {
 	struct hstate *h = hstate_vma(vma);
 	vm_fault_t ret = VM_FAULT_SIGBUS;
@@ -6162,11 +6269,16 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 				goto out;
 			}
 
-			return hugetlb_handle_userfault(vma, mapping, idx, flags,
-							haddr, address,
+			return hugetlb_handle_userfault(vmf, mapping,
 							VM_UFFD_MISSING);
 		}
 
+		if (!(vma->vm_flags & VM_MAYSHARE)) {
+			ret = vmf_anon_prepare(vmf);
+			if (unlikely(ret))
+				goto out;
+		}
+
 		folio = alloc_hugetlb_folio(vma, haddr, 0);
 		if (IS_ERR(folio)) {
 			/*
@@ -6203,15 +6315,12 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 				 */
 				restore_reserve_on_error(h, vma, haddr, folio);
 				folio_put(folio);
+				ret = VM_FAULT_SIGBUS;
 				goto out;
 			}
 			new_pagecache_folio = true;
 		} else {
 			folio_lock(folio);
-			if (unlikely(anon_vma_prepare(vma))) {
-				ret = VM_FAULT_OOM;
-				goto backout_unlocked;
-			}
 			anon_rmap = 1;
 		}
 	} else {
@@ -6235,8 +6344,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 				ret = 0;
 				goto out;
 			}
-			return hugetlb_handle_userfault(vma, mapping, idx, flags,
-							haddr, address,
+			return hugetlb_handle_userfault(vmf, mapping,
 							VM_UFFD_MINOR);
 		}
 	}
@@ -6279,7 +6387,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
 	hugetlb_count_add(pages_per_huge_page(h), mm);
 	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
 		/* Optimization, do the COW without a second fault */
-		ret = hugetlb_wp(mm, vma, address, ptep, flags, folio, ptl);
+		ret = hugetlb_wp(mm, vma, address, ptep, flags, folio, ptl, vmf);
 	}
 
 	spin_unlock(ptl);
@@ -6340,19 +6448,25 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	spinlock_t *ptl;
 	vm_fault_t ret;
 	u32 hash;
-	pgoff_t idx;
 	struct folio *folio = NULL;
 	struct folio *pagecache_folio = NULL;
 	struct hstate *h = hstate_vma(vma);
 	struct address_space *mapping;
 	int need_wait_lock = 0;
 	unsigned long haddr = address & huge_page_mask(h);
+	struct vm_fault vmf = {
+		.vma = vma,
+		.address = haddr,
+		.real_address = address,
+		.flags = flags,
+		.pgoff = vma_hugecache_offset(h, vma, haddr),
+		/* TODO: Track hugetlb faults using vm_fault */
 
-	/* TODO: Handle faults under the VMA lock */
-	if (flags & FAULT_FLAG_VMA_LOCK) {
-		vma_end_read(vma);
-		return VM_FAULT_RETRY;
-	}
+		/*
+		 * Some fields may not be initialized, be careful as it may
+		 * be hard to debug if called functions make assumptions
+		 */
+	};
 
 	/*
 	 * Serialize hugepage allocation and instantiation, so that we don't
@@ -6360,8 +6474,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * the same page in the page cache.
 	 */
 	mapping = vma->vm_file->f_mapping;
-	idx = vma_hugecache_offset(h, vma, haddr);
-	hash = hugetlb_fault_mutex_hash(mapping, idx);
+	hash = hugetlb_fault_mutex_hash(mapping, vmf.pgoff);
 	mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 	/*
@@ -6395,8 +6508,8 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * hugetlb_no_page will drop vma lock and hugetlb fault
 		 * mutex internally, which make us return immediately.
 		 */
-		return hugetlb_no_page(mm, vma, mapping, idx, address, ptep,
-				      entry, flags);
+		return hugetlb_no_page(mm, vma, mapping, vmf.pgoff, address,
+					ptep, entry, flags, &vmf);
 	}
 
 	ret = 0;
@@ -6442,7 +6555,8 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* Just decrements count, does not deallocate */
 		vma_end_reservation(h, vma, haddr);
 
-		pagecache_folio = filemap_lock_hugetlb_folio(h, mapping, idx);
+		pagecache_folio = filemap_lock_hugetlb_folio(h, mapping,
+							     vmf.pgoff);
 		if (IS_ERR(pagecache_folio))
 			pagecache_folio = NULL;
 	}
@@ -6457,13 +6571,6 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (userfaultfd_wp(vma) && huge_pte_uffd_wp(huge_ptep_get(ptep)) &&
 	    (flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) {
 		if (!userfaultfd_wp_async(vma)) {
-			struct vm_fault vmf = {
-				.vma = vma,
-				.address = haddr,
-				.real_address = address,
-				.flags = flags,
-			};
-
 			spin_unlock(ptl);
 			if (pagecache_folio) {
 				folio_unlock(pagecache_folio);
@@ -6497,7 +6604,7 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) {
 		if (!huge_pte_write(entry)) {
 			ret = hugetlb_wp(mm, vma, address, ptep, flags,
-					 pagecache_folio, ptl);
+					 pagecache_folio, ptl, &vmf);
 			goto out_put_page;
 		} else if (likely(flags & FAULT_FLAG_WRITE)) {
 			entry = huge_pte_mkdirty(entry);
@@ -6675,11 +6782,20 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 	}
 
 	/*
-	 * The memory barrier inside __folio_mark_uptodate makes sure that
-	 * preceding stores to the page contents become visible before
-	 * the set_pte_at() write.
+	 * If we just allocated a new page, we need a memory barrier to ensure
+	 * that preceding stores to the page become visible before the
+	 * set_pte_at() write. The memory barrier inside __folio_mark_uptodate
+	 * is what we need.
+	 *
+	 * In the case where we have not allocated a new page (is_continue),
+	 * the page must already be uptodate. UFFDIO_CONTINUE already includes
+	 * an earlier smp_wmb() to ensure that prior stores will be visible
+	 * before the set_pte_at() write.
 	 */
-	__folio_mark_uptodate(folio);
+	if (!is_continue)
+		__folio_mark_uptodate(folio);
+	else
+		WARN_ON_ONCE(!folio_test_uptodate(folio));
 
 	/* Add shared, newly allocated pages to the page cache. */
 	if (vm_shared && !is_continue) {
@@ -7686,6 +7802,13 @@ void __init hugetlb_cma_reserve(int order)
 	bool node_specific_cma_alloc = false;
 	int nid;
 
+	/*
+	 * HugeTLB CMA reservation is required for gigantic
+	 * huge pages which could not be allocated via the
+	 * page allocator. Just warn if there is any change
+	 * breaking this assumption.
+	 */
+	VM_WARN_ON(order <= MAX_PAGE_ORDER);
 	cma_reserve_called = true;
 
 	if (!hugetlb_cma_size)
@@ -7756,9 +7879,9 @@ void __init hugetlb_cma_reserve(int order)
 		 * huge page demotion.
 		 */
 		res = cma_declare_contiguous_nid(0, size, 0,
-						PAGE_SIZE << HUGETLB_PAGE_ORDER,
-						 0, false, name,
-						 &hugetlb_cma[nid], nid);
+					PAGE_SIZE << HUGETLB_PAGE_ORDER,
+					HUGETLB_PAGE_ORDER, false, name,
+					&hugetlb_cma[nid], nid);
 		if (res) {
 			pr_warn("hugetlb_cma: reservation failed: err %d, node %d",
 				res, nid);