Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Signed-off-by: David S. Miller <davem@davemloft.net>

18 files changed, 348 insertions, 176 deletions

diff --git a/mm/highmem.c b/mm/highmem.c
index 874b732b120c..6ef8f5e05e7e 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -368,20 +368,24 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
 
 	BUG_ON(end1 > page_size(page) || end2 > page_size(page));
 
+	if (start1 >= end1)
+		start1 = end1 = 0;
+	if (start2 >= end2)
+		start2 = end2 = 0;
+
 	for (i = 0; i < compound_nr(page); i++) {
 		void *kaddr = NULL;
 
-		if (start1 < PAGE_SIZE || start2 < PAGE_SIZE)
-			kaddr = kmap_atomic(page + i);
-
 		if (start1 >= PAGE_SIZE) {
 			start1 -= PAGE_SIZE;
 			end1 -= PAGE_SIZE;
 		} else {
 			unsigned this_end = min_t(unsigned, end1, PAGE_SIZE);
 
-			if (end1 > start1)
+			if (end1 > start1) {
+				kaddr = kmap_atomic(page + i);
 				memset(kaddr + start1, 0, this_end - start1);
+			}
 			end1 -= this_end;
 			start1 = 0;
 		}
@@ -392,8 +396,11 @@ void zero_user_segments(struct page *page, unsigned start1, unsigned end1,
 		} else {
 			unsigned this_end = min_t(unsigned, end2, PAGE_SIZE);
 
-			if (end2 > start2)
+			if (end2 > start2) {
+				if (!kaddr)
+					kaddr = kmap_atomic(page + i);
 				memset(kaddr + start2, 0, this_end - start2);
+			}
 			end2 -= this_end;
 			start2 = 0;
 		}
@@ -611,7 +618,7 @@ void __kmap_local_sched_out(void)
 		int idx;
 
 		/* With debug all even slots are unmapped and act as guard */
-		if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) {
+		if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
 			WARN_ON_ONCE(!pte_none(pteval));
 			continue;
 		}
@@ -647,7 +654,7 @@ void __kmap_local_sched_in(void)
 		int idx;
 
 		/* With debug all even slots are unmapped and act as guard */
-		if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !(i & 0x01)) {
+		if (IS_ENABLED(CONFIG_DEBUG_KMAP_LOCAL) && !(i & 0x01)) {
 			WARN_ON_ONCE(!pte_none(pteval));
 			continue;
 		}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 395c75111d33..ae907a9c2050 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1100,9 +1100,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	 * best effort that the pinned pages won't be replaced by another
 	 * random page during the coming copy-on-write.
 	 */
-	if (unlikely(is_cow_mapping(vma->vm_flags) &&
-		     atomic_read(&src_mm->has_pinned) &&
-		     page_maybe_dma_pinned(src_page))) {
+	if (unlikely(page_needs_cow_for_dma(vma, src_page))) {
 		pte_free(dst_mm, pgtable);
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
@@ -1214,9 +1212,7 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	}
 
 	/* Please refer to comments in copy_huge_pmd() */
-	if (unlikely(is_cow_mapping(vma->vm_flags) &&
-		     atomic_read(&src_mm->has_pinned) &&
-		     page_maybe_dma_pinned(pud_page(pud)))) {
+	if (unlikely(page_needs_cow_for_dma(vma, pud_page(pud)))) {
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
 		__split_huge_pud(vma, src_pud, addr);
@@ -2471,7 +2467,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 	int i;
 
 	/* complete memcg works before add pages to LRU */
-	mem_cgroup_split_huge_fixup(head);
+	split_page_memcg(head, nr);
 
 	if (PageAnon(head) && PageSwapCache(head)) {
 		swp_entry_t entry = { .val = page_private(head) };
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8fb42c6dd74b..a86a58ef132d 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -280,6 +280,17 @@ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg,
 		nrg->reservation_counter =
 			&h_cg->rsvd_hugepage[hstate_index(h)];
 		nrg->css = &h_cg->css;
+		/*
+		 * The caller will hold exactly one h_cg->css reference for the
+		 * whole contiguous reservation region. But this area might be
+		 * scattered when there are already some file_regions reside in
+		 * it. As a result, many file_regions may share only one css
+		 * reference. In order to ensure that one file_region must hold
+		 * exactly one h_cg->css reference, we should do css_get for
+		 * each file_region and leave the reference held by caller
+		 * untouched.
+		 */
+		css_get(&h_cg->css);
 		if (!resv->pages_per_hpage)
 			resv->pages_per_hpage = pages_per_huge_page(h);
 		/* pages_per_hpage should be the same for all entries in
@@ -293,6 +304,14 @@ static void record_hugetlb_cgroup_uncharge_info(struct hugetlb_cgroup *h_cg,
 #endif
 }
 
+static void put_uncharge_info(struct file_region *rg)
+{
+#ifdef CONFIG_CGROUP_HUGETLB
+	if (rg->css)
+		css_put(rg->css);
+#endif
+}
+
 static bool has_same_uncharge_info(struct file_region *rg,
 				   struct file_region *org)
 {
@@ -316,6 +335,7 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
 		prg->to = rg->to;
 
 		list_del(&rg->link);
+		put_uncharge_info(rg);
 		kfree(rg);
 
 		rg = prg;
@@ -327,10 +347,29 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
 		nrg->from = rg->from;
 
 		list_del(&rg->link);
+		put_uncharge_info(rg);
 		kfree(rg);
 	}
 }
 
+static inline long
+hugetlb_resv_map_add(struct resv_map *map, struct file_region *rg, long from,
+		     long to, struct hstate *h, struct hugetlb_cgroup *cg,
+		     long *regions_needed)
+{
+	struct file_region *nrg;
+
+	if (!regions_needed) {
+		nrg = get_file_region_entry_from_cache(map, from, to);
+		record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg);
+		list_add(&nrg->link, rg->link.prev);
+		coalesce_file_region(map, nrg);
+	} else
+		*regions_needed += 1;
+
+	return to - from;
+}
+
 /*
  * Must be called with resv->lock held.
  *
@@ -346,7 +385,7 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
 	long add = 0;
 	struct list_head *head = &resv->regions;
 	long last_accounted_offset = f;
-	struct file_region *rg = NULL, *trg = NULL, *nrg = NULL;
+	struct file_region *rg = NULL, *trg = NULL;
 
 	if (regions_needed)
 		*regions_needed = 0;
@@ -369,24 +408,17 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
 		/* When we find a region that starts beyond our range, we've
 		 * finished.
 		 */
-		if (rg->from > t)
+		if (rg->from >= t)
 			break;
 
 		/* Add an entry for last_accounted_offset -> rg->from, and
 		 * update last_accounted_offset.
 		 */
-		if (rg->from > last_accounted_offset) {
-			add += rg->from - last_accounted_offset;
-			if (!regions_needed) {
-				nrg = get_file_region_entry_from_cache(
-					resv, last_accounted_offset, rg->from);
-				record_hugetlb_cgroup_uncharge_info(h_cg, h,
-								    resv, nrg);
-				list_add(&nrg->link, rg->link.prev);
-				coalesce_file_region(resv, nrg);
-			} else
-				*regions_needed += 1;
-		}
+		if (rg->from > last_accounted_offset)
+			add += hugetlb_resv_map_add(resv, rg,
+						    last_accounted_offset,
+						    rg->from, h, h_cg,
+						    regions_needed);
 
 		last_accounted_offset = rg->to;
 	}
@@ -394,17 +426,9 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
 	/* Handle the case where our range extends beyond
 	 * last_accounted_offset.
 	 */
-	if (last_accounted_offset < t) {
-		add += t - last_accounted_offset;
-		if (!regions_needed) {
-			nrg = get_file_region_entry_from_cache(
-				resv, last_accounted_offset, t);
-			record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg);
-			list_add(&nrg->link, rg->link.prev);
-			coalesce_file_region(resv, nrg);
-		} else
-			*regions_needed += 1;
-	}
+	if (last_accounted_offset < t)
+		add += hugetlb_resv_map_add(resv, rg, last_accounted_offset,
+					    t, h, h_cg, regions_needed);
 
 	VM_BUG_ON(add < 0);
 	return add;
@@ -659,7 +683,7 @@ retry:
 
 			del += t - f;
 			hugetlb_cgroup_uncharge_file_region(
-				resv, rg, t - f);
+				resv, rg, t - f, false);
 
 			/* New entry for end of split region */
 			nrg->from = t;
@@ -680,7 +704,7 @@ retry:
 		if (f <= rg->from && t >= rg->to) { /* Remove entire region */
 			del += rg->to - rg->from;
 			hugetlb_cgroup_uncharge_file_region(resv, rg,
-							    rg->to - rg->from);
+							    rg->to - rg->from, true);
 			list_del(&rg->link);
 			kfree(rg);
 			continue;
@@ -688,13 +712,13 @@ retry:
 
 		if (f <= rg->from) {	/* Trim beginning of region */
 			hugetlb_cgroup_uncharge_file_region(resv, rg,
-							    t - rg->from);
+							    t - rg->from, false);
 
 			del += t - rg->from;
 			rg->from = t;
 		} else {		/* Trim end of region */
 			hugetlb_cgroup_uncharge_file_region(resv, rg,
-							    rg->to - f);
+							    rg->to - f, false);
 
 			del += rg->to - f;
 			rg->to = f;
@@ -3725,21 +3749,32 @@ static bool is_hugetlb_entry_hwpoisoned(pte_t pte)
 		return false;
 }
 
+static void
+hugetlb_install_page(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr,
+		     struct page *new_page)
+{
+	__SetPageUptodate(new_page);
+	set_huge_pte_at(vma->vm_mm, addr, ptep, make_huge_pte(vma, new_page, 1));
+	hugepage_add_new_anon_rmap(new_page, vma, addr);
+	hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm);
+	ClearHPageRestoreReserve(new_page);
+	SetHPageMigratable(new_page);
+}
+
 int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			    struct vm_area_struct *vma)
 {
 	pte_t *src_pte, *dst_pte, entry, dst_entry;
 	struct page *ptepage;
 	unsigned long addr;
-	int cow;
+	bool cow = is_cow_mapping(vma->vm_flags);
 	struct hstate *h = hstate_vma(vma);
 	unsigned long sz = huge_page_size(h);
+	unsigned long npages = pages_per_huge_page(h);
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	struct mmu_notifier_range range;
 	int ret = 0;
 
-	cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
-
 	if (cow) {
 		mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src,
 					vma->vm_start,
@@ -3784,6 +3819,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 		entry = huge_ptep_get(src_pte);
 		dst_entry = huge_ptep_get(dst_pte);
+again:
 		if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) {
 			/*
 			 * Skip if src entry none.  Also, skip in the
@@ -3807,6 +3843,52 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			}
 			set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
 		} else {
+			entry = huge_ptep_get(src_pte);
+			ptepage = pte_page(entry);
+			get_page(ptepage);
+
+			/*
+			 * This is a rare case where we see pinned hugetlb
+			 * pages while they're prone to COW.  We need to do the
+			 * COW earlier during fork.
+			 *
+			 * When pre-allocating the page or copying data, we
+			 * need to be without the pgtable locks since we could
+			 * sleep during the process.
+			 */
+			if (unlikely(page_needs_cow_for_dma(vma, ptepage))) {
+				pte_t src_pte_old = entry;
+				struct page *new;
+
+				spin_unlock(src_ptl);
+				spin_unlock(dst_ptl);
+				/* Do not use reserve as it's private owned */
+				new = alloc_huge_page(vma, addr, 1);
+				if (IS_ERR(new)) {
+					put_page(ptepage);
+					ret = PTR_ERR(new);
+					break;
+				}
+				copy_user_huge_page(new, ptepage, addr, vma,
+						    npages);
+				put_page(ptepage);
+
+				/* Install the new huge page if src pte stable */
+				dst_ptl = huge_pte_lock(h, dst, dst_pte);
+				src_ptl = huge_pte_lockptr(h, src, src_pte);
+				spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+				entry = huge_ptep_get(src_pte);
+				if (!pte_same(src_pte_old, entry)) {
+					put_page(new);
+					/* dst_entry won't change as in child */
+					goto again;
+				}
+				hugetlb_install_page(vma, dst_pte, addr, new);
+				spin_unlock(src_ptl);
+				spin_unlock(dst_ptl);
+				continue;
+			}
+
 			if (cow) {
 				/*
 				 * No need to notify as we are downgrading page
@@ -3817,12 +3899,10 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 				 */
 				huge_ptep_set_wrprotect(src, addr, src_pte);
 			}
-			entry = huge_ptep_get(src_pte);
-			ptepage = pte_page(entry);
-			get_page(ptepage);
+
 			page_dup_rmap(ptepage, true);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
-			hugetlb_count_add(pages_per_huge_page(h), dst);
+			hugetlb_count_add(npages, dst);
 		}
 		spin_unlock(src_ptl);
 		spin_unlock(dst_ptl);
@@ -5128,6 +5208,10 @@ bool hugetlb_reserve_pages(struct inode *inode,
 			 */
 			long rsv_adjust;
 
+			/*
+			 * hugetlb_cgroup_uncharge_cgroup_rsvd() will put the
+			 * reference to h_cg->css. See comment below for detail.
+			 */
 			hugetlb_cgroup_uncharge_cgroup_rsvd(
 				hstate_index(h),
 				(chg - add) * pages_per_huge_page(h), h_cg);
@@ -5135,6 +5219,14 @@ bool hugetlb_reserve_pages(struct inode *inode,
 			rsv_adjust = hugepage_subpool_put_pages(spool,
 								chg - add);
 			hugetlb_acct_memory(h, -rsv_adjust);
+		} else if (h_cg) {
+			/*
+			 * The file_regions will hold their own reference to
+			 * h_cg->css. So we should release the reference held
+			 * via hugetlb_cgroup_charge_cgroup_rsvd() when we are
+			 * done.
+			 */
+			hugetlb_cgroup_put_rsvd_cgroup(h_cg);
 		}
 	}
 	return true;
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index f68b51fcda3d..603a131e262d 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -391,7 +391,8 @@ void hugetlb_cgroup_uncharge_counter(struct resv_map *resv, unsigned long start,
 
 void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
 					 struct file_region *rg,
-					 unsigned long nr_pages)
+					 unsigned long nr_pages,
+					 bool region_del)
 {
 	if (hugetlb_cgroup_disabled() || !resv || !rg || !nr_pages)
 		return;
@@ -400,7 +401,12 @@ void hugetlb_cgroup_uncharge_file_region(struct resv_map *resv,
 	    !resv->reservation_counter) {
 		page_counter_uncharge(rg->reservation_counter,
 				      nr_pages * resv->pages_per_hpage);
-		css_put(rg->css);
+		/*
+		 * Only do css_put(rg->css) when we delete the entire region
+		 * because one file_region must hold exactly one css reference.
+		 */
+		if (region_del)
+			css_put(rg->css);
 	}
 }
 
diff --git a/mm/internal.h b/mm/internal.h
index 9902648f2206..1432feec62df 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -296,11 +296,6 @@ static inline unsigned int buddy_order(struct page *page)
  */
 #define buddy_order_unsafe(page)	READ_ONCE(page_private(page))
 
-static inline bool is_cow_mapping(vm_flags_t flags)
-{
-	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
-}
-
 /*
  * These three helpers classifies VMAs for virtual memory accounting.
  */
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index 3b8ec938470a..d53c91f881a4 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -12,6 +12,7 @@
 #include <linux/debugfs.h>
 #include <linux/kcsan-checks.h>
 #include <linux/kfence.h>
+#include <linux/kmemleak.h>
 #include <linux/list.h>
 #include <linux/lockdep.h>
 #include <linux/memblock.h>
@@ -480,6 +481,14 @@ static bool __init kfence_init_pool(void)
 		addr += 2 * PAGE_SIZE;
 	}
 
+	/*
+	 * The pool is live and will never be deallocated from this point on.
+	 * Remove the pool object from the kmemleak object tree, as it would
+	 * otherwise overlap with allocations returned by kfence_alloc(), which
+	 * are registered with kmemleak through the slab post-alloc hook.
+	 */
+	kmemleak_free(__kfence_pool);
+
 	return true;
 
 err:
diff --git a/mm/kfence/report.c b/mm/kfence/report.c
index ab83d5a59bb1..e3f71451ad9e 100644
--- a/mm/kfence/report.c
+++ b/mm/kfence/report.c
@@ -20,6 +20,11 @@
 
 #include "kfence.h"
 
+/* May be overridden by <asm/kfence.h>. */
+#ifndef ARCH_FUNC_PREFIX
+#define ARCH_FUNC_PREFIX ""
+#endif
+
 extern bool no_hash_pointers;
 
 /* Helper function to either print to a seq_file or to console. */
@@ -67,8 +72,9 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries
 	for (skipnr = 0; skipnr < num_entries; skipnr++) {
 		int len = scnprintf(buf, sizeof(buf), "%ps", (void *)stack_entries[skipnr]);
 
-		if (str_has_prefix(buf, "kfence_") || str_has_prefix(buf, "__kfence_") ||
-		    !strncmp(buf, "__slab_free", len)) {
+		if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfence_") ||
+		    str_has_prefix(buf, ARCH_FUNC_PREFIX "__kfence_") ||
+		    !strncmp(buf, ARCH_FUNC_PREFIX "__slab_free", len)) {
 			/*
 			 * In case of tail calls from any of the below
 			 * to any of the above.
@@ -77,10 +83,10 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries
 		}
 
 		/* Also the *_bulk() variants by only checking prefixes. */
-		if (str_has_prefix(buf, "kfree") ||
-		    str_has_prefix(buf, "kmem_cache_free") ||
-		    str_has_prefix(buf, "__kmalloc") ||
-		    str_has_prefix(buf, "kmem_cache_alloc"))
+		if (str_has_prefix(buf, ARCH_FUNC_PREFIX "kfree") ||
+		    str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_free") ||
+		    str_has_prefix(buf, ARCH_FUNC_PREFIX "__kmalloc") ||
+		    str_has_prefix(buf, ARCH_FUNC_PREFIX "kmem_cache_alloc"))
 			goto found;
 	}
 	if (fallback < num_entries)
@@ -116,12 +122,12 @@ void kfence_print_object(struct seq_file *seq, const struct kfence_metadata *met
 	lockdep_assert_held(&meta->lock);
 
 	if (meta->state == KFENCE_OBJECT_UNUSED) {
-		seq_con_printf(seq, "kfence-#%zd unused\n", meta - kfence_metadata);
+		seq_con_printf(seq, "kfence-#%td unused\n", meta - kfence_metadata);
 		return;
 	}
 
 	seq_con_printf(seq,
-		       "kfence-#%zd [0x%p-0x%p"
+		       "kfence-#%td [0x%p-0x%p"
 		       ", size=%d, cache=%s] allocated by task %d:\n",
 		       meta - kfence_metadata, (void *)start, (void *)(start + size - 1), size,
 		       (cache && cache->name) ? cache->name : "<destroyed>", meta->alloc_track.pid);
@@ -204,7 +210,7 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r
 
 		pr_err("BUG: KFENCE: out-of-bounds %s in %pS\n\n", get_access_type(is_write),
 		       (void *)stack_entries[skipnr]);
-		pr_err("Out-of-bounds %s at 0x%p (%luB %s of kfence-#%zd):\n",
+		pr_err("Out-of-bounds %s at 0x%p (%luB %s of kfence-#%td):\n",
 		       get_access_type(is_write), (void *)address,
 		       left_of_object ? meta->addr - address : address - meta->addr,
 		       left_of_object ? "left" : "right", object_index);
@@ -213,14 +219,14 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r
 	case KFENCE_ERROR_UAF:
 		pr_err("BUG: KFENCE: use-after-free %s in %pS\n\n", get_access_type(is_write),
 		       (void *)stack_entries[skipnr]);
-		pr_err("Use-after-free %s at 0x%p (in kfence-#%zd):\n",
+		pr_err("Use-after-free %s at 0x%p (in kfence-#%td):\n",
 		       get_access_type(is_write), (void *)address, object_index);
 		break;
 	case KFENCE_ERROR_CORRUPTION:
 		pr_err("BUG: KFENCE: memory corruption in %pS\n\n", (void *)stack_entries[skipnr]);
 		pr_err("Corrupted memory at 0x%p ", (void *)address);
 		print_diff_canary(address, 16, meta);
-		pr_cont(" (in kfence-#%zd):\n", object_index);
+		pr_cont(" (in kfence-#%td):\n", object_index);
 		break;
 	case KFENCE_ERROR_INVALID:
 		pr_err("BUG: KFENCE: invalid %s in %pS\n\n", get_access_type(is_write),
@@ -230,7 +236,7 @@ void kfence_report_error(unsigned long address, bool is_write, struct pt_regs *r
 		break;
 	case KFENCE_ERROR_INVALID_FREE:
 		pr_err("BUG: KFENCE: invalid free in %pS\n\n", (void *)stack_entries[skipnr]);
-		pr_err("Invalid free of 0x%p (in kfence-#%zd):\n", (void *)address,
+		pr_err("Invalid free of 0x%p (in kfence-#%td):\n", (void *)address,
 		       object_index);
 		break;
 	}
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index c0014d3b91c1..fe6e3ae8e8c6 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -97,6 +97,7 @@
 #include <linux/atomic.h>
 
 #include <linux/kasan.h>
+#include <linux/kfence.h>
 #include <linux/kmemleak.h>
 #include <linux/memory_hotplug.h>
 
@@ -589,7 +590,7 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
 	atomic_set(&object->use_count, 1);
 	object->flags = OBJECT_ALLOCATED;
 	object->pointer = ptr;
-	object->size = size;
+	object->size = kfence_ksize((void *)ptr) ?: size;
 	object->excess_ref = 0;
 	object->min_count = min_count;
 	object->count = 0;			/* white color initially */
diff --git a/mm/madvise.c b/mm/madvise.c
index df692d2e35d4..01fef79ac761 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1198,12 +1198,22 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
 		goto release_task;
 	}
 
-	mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS);
+	/* Require PTRACE_MODE_READ to avoid leaking ASLR metadata. */
+	mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
 	if (IS_ERR_OR_NULL(mm)) {
 		ret = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
 		goto release_task;
 	}
 
+	/*
+	 * Require CAP_SYS_NICE for influencing process performance. Note that
+	 * only non-destructive hints are currently supported.
+	 */
+	if (!capable(CAP_SYS_NICE)) {
+		ret = -EPERM;
+		goto release_mm;
+	}
+
 	total_len = iov_iter_count(&iter);
 
 	while (iov_iter_count(&iter)) {
@@ -1218,6 +1228,7 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
 	if (ret == 0)
 		ret = total_len - iov_iter_count(&iter);
 
+release_mm:
 	mmput(mm);
 release_task:
 	put_task_struct(task);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 845eec01ef9d..e064ac0d850a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3287,24 +3287,21 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size)
 
 #endif /* CONFIG_MEMCG_KMEM */
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
- * Because page_memcg(head) is not set on compound tails, set it now.
+ * Because page_memcg(head) is not set on tails, set it now.
  */
-void mem_cgroup_split_huge_fixup(struct page *head)
+void split_page_memcg(struct page *head, unsigned int nr)
 {
 	struct mem_cgroup *memcg = page_memcg(head);
 	int i;
 
-	if (mem_cgroup_disabled())
+	if (mem_cgroup_disabled() || !memcg)
 		return;
 
-	for (i = 1; i < HPAGE_PMD_NR; i++) {
-		css_get(&memcg->css);
-		head[i].memcg_data = (unsigned long)memcg;
-	}
+	for (i = 1; i < nr; i++)
+		head[i].memcg_data = head->memcg_data;
+	css_get_many(&memcg->css, nr - 1);
 }
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #ifdef CONFIG_MEMCG_SWAP
 /**
diff --git a/mm/memory.c b/mm/memory.c
index c8e357627318..5efa07fb6cdc 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -809,12 +809,8 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 		  pte_t *dst_pte, pte_t *src_pte, unsigned long addr, int *rss,
 		  struct page **prealloc, pte_t pte, struct page *page)
 {
-	struct mm_struct *src_mm = src_vma->vm_mm;
 	struct page *new_page;
 
-	if (!is_cow_mapping(src_vma->vm_flags))
-		return 1;
-
 	/*
 	 * What we want to do is to check whether this page may
 	 * have been pinned by the parent process.  If so,
@@ -828,9 +824,7 @@ copy_present_page(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
 	 * the page count. That might give false positives for
 	 * for pinning, but it will work correctly.
 	 */
-	if (likely(!atomic_read(&src_mm->has_pinned)))
-		return 1;
-	if (likely(!page_maybe_dma_pinned(page)))
+	if (likely(!page_needs_cow_for_dma(src_vma, page)))
 		return 1;
 
 	new_page = *prealloc;
@@ -3103,6 +3097,14 @@ static vm_fault_t do_wp_page(struct vm_fault *vmf)
 		return handle_userfault(vmf, VM_UFFD_WP);
 	}
 
+	/*
+	 * Userfaultfd write-protect can defer flushes. Ensure the TLB
+	 * is flushed in this case before copying.
+	 */
+	if (unlikely(userfaultfd_wp(vmf->vma) &&
+		     mm_tlb_flush_pending(vmf->vma->vm_mm)))
+		flush_tlb_page(vmf->vma, vmf->address);
+
 	vmf->page = vm_normal_page(vma, vmf->address, vmf->orig_pte);
 	if (!vmf->page) {
 		/*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 5ba51a8bdaeb..0cdbbfbc5757 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1072,7 +1072,7 @@ static int online_memory_block(struct memory_block *mem, void *arg)
  */
 int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 {
-	struct mhp_params params = { .pgprot = PAGE_KERNEL };
+	struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) };
 	u64 start, size;
 	bool new_node = false;
 	int ret;
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 61ee40ed804e..459d195d2ff6 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -501,10 +501,33 @@ static int mn_hlist_invalidate_range_start(
 						"");
 				WARN_ON(mmu_notifier_range_blockable(range) ||
 					_ret != -EAGAIN);
+				/*
+				 * We call all the notifiers on any EAGAIN,
+				 * there is no way for a notifier to know if
+				 * its start method failed, thus a start that
+				 * does EAGAIN can't also do end.
+				 */
+				WARN_ON(ops->invalidate_range_end);
 				ret = _ret;
 			}
 		}
 	}
+
+	if (ret) {
+		/*
+		 * Must be non-blocking to get here.  If there are multiple
+		 * notifiers and one or more failed start, any that succeeded
+		 * start are expecting their end to be called.  Do so now.
+		 */
+		hlist_for_each_entry_rcu(subscription, &subscriptions->list,
+					 hlist, srcu_read_lock_held(&srcu)) {
+			if (!subscription->ops->invalidate_range_end)
+				continue;
+
+			subscription->ops->invalidate_range_end(subscription,
+								range);
+		}
+	}
 	srcu_read_unlock(&srcu, id);
 
 	return ret;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index eb34d204d4ee..9e35b636a393 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2833,6 +2833,22 @@ void wait_on_page_writeback(struct page *page)
 }
 EXPORT_SYMBOL_GPL(wait_on_page_writeback);
 
+/*
+ * Wait for a page to complete writeback.  Returns -EINTR if we get a
+ * fatal signal while waiting.
+ */
+int wait_on_page_writeback_killable(struct page *page)
+{
+	while (PageWriteback(page)) {
+		trace_wait_on_page_writeback(page, page_mapping(page));
+		if (wait_on_page_bit_killable(page, PG_writeback))
+			return -EINTR;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(wait_on_page_writeback_killable);
+
 /**
  * wait_for_stable_page() - wait for writeback to finish, if necessary.
  * @page:	The page to wait on.
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3e4b29ee2b1e..cfc72873961d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1282,6 +1282,12 @@ static __always_inline bool free_pages_prepare(struct page *page,
 	kernel_poison_pages(page, 1 << order);
 
 	/*
+	 * With hardware tag-based KASAN, memory tags must be set before the
+	 * page becomes unavailable via debug_pagealloc or arch_free_page.
+	 */
+	kasan_free_nondeferred_pages(page, order);
+
+	/*
 	 * arch_free_page() can make the page's contents inaccessible.  s390
 	 * does this.  So nothing which can access the page's contents should
 	 * happen after this.
@@ -1290,8 +1296,6 @@ static __always_inline bool free_pages_prepare(struct page *page,
 
 	debug_pagealloc_unmap_pages(page, 1 << order);
 
-	kasan_free_nondeferred_pages(page, order);
-
 	return true;
 }
 
@@ -3310,6 +3314,7 @@ void split_page(struct page *page, unsigned int order)
 	for (i = 1; i < (1 << order); i++)
 		set_page_refcounted(page + i);
 	split_page_owner(page, 1 << order);
+	split_page_memcg(page, 1 << order);
 }
 EXPORT_SYMBOL_GPL(split_page);
 
@@ -6259,12 +6264,65 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 	}
 }
 
+#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
+/*
+ * Only struct pages that correspond to ranges defined by memblock.memory
+ * are zeroed and initialized by going through __init_single_page() during
+ * memmap_init_zone().
+ *
+ * But, there could be struct pages that correspond to holes in
+ * memblock.memory. This can happen because of the following reasons:
+ * - physical memory bank size is not necessarily the exact multiple of the
+ *   arbitrary section size
+ * - early reserved memory may not be listed in memblock.memory
+ * - memory layouts defined with memmap= kernel parameter may not align
+ *   nicely with memmap sections
+ *
+ * Explicitly initialize those struct pages so that:
+ * - PG_Reserved is set
+ * - zone and node links point to zone and node that span the page if the
+ *   hole is in the middle of a zone
+ * - zone and node links point to adjacent zone/node if the hole falls on
+ *   the zone boundary; the pages in such holes will be prepended to the
+ *   zone/node above the hole except for the trailing pages in the last
+ *   section that will be appended to the zone/node below.
+ */
+static u64 __meminit init_unavailable_range(unsigned long spfn,
+					    unsigned long epfn,
+					    int zone, int node)
+{
+	unsigned long pfn;
+	u64 pgcnt = 0;
+
+	for (pfn = spfn; pfn < epfn; pfn++) {
+		if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
+			pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
+				+ pageblock_nr_pages - 1;
+			continue;
+		}
+		__init_single_page(pfn_to_page(pfn), pfn, zone, node);
+		__SetPageReserved(pfn_to_page(pfn));
+		pgcnt++;
+	}
+
+	return pgcnt;
+}
+#else
+static inline u64 init_unavailable_range(unsigned long spfn, unsigned long epfn,
+					 int zone, int node)
+{
+	return 0;
+}
+#endif
+
 void __meminit __weak memmap_init_zone(struct zone *zone)
 {
 	unsigned long zone_start_pfn = zone->zone_start_pfn;
 	unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages;
 	int i, nid = zone_to_nid(zone), zone_id = zone_idx(zone);
+	static unsigned long hole_pfn;
 	unsigned long start_pfn, end_pfn;
+	u64 pgcnt = 0;
 
 	for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
 		start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn);
@@ -6274,7 +6332,29 @@ void __meminit __weak memmap_init_zone(struct zone *zone)
 			memmap_init_range(end_pfn - start_pfn, nid,
 					zone_id, start_pfn, zone_end_pfn,
 					MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
+
+		if (hole_pfn < start_pfn)
+			pgcnt += init_unavailable_range(hole_pfn, start_pfn,
+							zone_id, nid);
+		hole_pfn = end_pfn;
 	}
+
+#ifdef CONFIG_SPARSEMEM
+	/*
+	 * Initialize the hole in the range [zone_end_pfn, section_end].
+	 * If zone boundary falls in the middle of a section, this hole
+	 * will be re-initialized during the call to this function for the
+	 * higher zone.
+	 */
+	end_pfn = round_up(zone_end_pfn, PAGES_PER_SECTION);
+	if (hole_pfn < end_pfn)
+		pgcnt += init_unavailable_range(hole_pfn, end_pfn,
+						zone_id, nid);
+#endif
+
+	if (pgcnt)
+		pr_info("  %s zone: %llu pages in unavailable ranges\n",
+			zone->name, pgcnt);
 }
 
 static int zone_batchsize(struct zone *zone)
@@ -7071,88 +7151,6 @@ void __init free_area_init_memoryless_node(int nid)
 	free_area_init_node(nid);
 }
 
-#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
-/*
- * Initialize all valid struct pages in the range [spfn, epfn) and mark them
- * PageReserved(). Return the number of struct pages that were initialized.
- */
-static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn)
-{
-	unsigned long pfn;
-	u64 pgcnt = 0;
-
-	for (pfn = spfn; pfn < epfn; pfn++) {
-		if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
-			pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
-				+ pageblock_nr_pages - 1;
-			continue;
-		}
-		/*
-		 * Use a fake node/zone (0) for now. Some of these pages
-		 * (in memblock.reserved but not in memblock.memory) will
-		 * get re-initialized via reserve_bootmem_region() later.
-		 */
-		__init_single_page(pfn_to_page(pfn), pfn, 0, 0);
-		__SetPageReserved(pfn_to_page(pfn));
-		pgcnt++;
-	}
-
-	return pgcnt;
-}
-
-/*
- * Only struct pages that are backed by physical memory are zeroed and
- * initialized by going through __init_single_page(). But, there are some
- * struct pages which are reserved in memblock allocator and their fields
- * may be accessed (for example page_to_pfn() on some configuration accesses
- * flags). We must explicitly initialize those struct pages.
- *
- * This function also addresses a similar issue where struct pages are left
- * uninitialized because the physical address range is not covered by
- * memblock.memory or memblock.reserved. That could happen when memblock
- * layout is manually configured via memmap=, or when the highest physical
- * address (max_pfn) does not end on a section boundary.
- */
-static void __init init_unavailable_mem(void)
-{
-	phys_addr_t start, end;
-	u64 i, pgcnt;
-	phys_addr_t next = 0;
-
-	/*
-	 * Loop through unavailable ranges not covered by memblock.memory.
-	 */
-	pgcnt = 0;
-	for_each_mem_range(i, &start, &end) {
-		if (next < start)
-			pgcnt += init_unavailable_range(PFN_DOWN(next),
-							PFN_UP(start));
-		next = end;
-	}
-
-	/*
-	 * Early sections always have a fully populated memmap for the whole
-	 * section - see pfn_valid(). If the last section has holes at the
-	 * end and that section is marked "online", the memmap will be
-	 * considered initialized. Make sure that memmap has a well defined
-	 * state.
-	 */
-	pgcnt += init_unavailable_range(PFN_DOWN(next),
-					round_up(max_pfn, PAGES_PER_SECTION));
-
-	/*
-	 * Struct pages that do not have backing memory. This could be because
-	 * firmware is using some of this memory, or for some other reasons.
-	 */
-	if (pgcnt)
-		pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt);
-}
-#else
-static inline void __init init_unavailable_mem(void)
-{
-}
-#endif /* !CONFIG_FLAT_NODE_MEM_MAP */
-
 #if MAX_NUMNODES > 1
 /*
  * Figure out the number of possible node ids.
@@ -7576,7 +7574,6 @@ void __init free_area_init(unsigned long *max_zone_pfn)
 	/* Initialise every node */
 	mminit_verify_pageflags_layout();
 	setup_nr_node_ids();
-	init_unavailable_mem();
 	for_each_online_node(nid) {
 		pg_data_t *pgdat = NODE_DATA(nid);
 		free_area_init_node(nid);
diff --git a/mm/slab.c b/mm/slab.c
index 51fd424e0d6d..ae651bf540b7 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2992,7 +2992,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 				gfp_t flags, void *objp, unsigned long caller)
 {
 	WARN_ON_ONCE(cachep->ctor && (flags & __GFP_ZERO));
-	if (!objp)
+	if (!objp || is_kfence_address(objp))
 		return objp;
 	if (cachep->flags & SLAB_POISON) {
 		check_poison_obj(cachep, objp);
diff --git a/mm/slub.c b/mm/slub.c
index e26c274b4657..3021ce9bf1b3 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1993,7 +1993,7 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 
 		t = acquire_slab(s, n, page, object == NULL, &objects);
 		if (!t)
-			continue; /* cmpxchg raced */
+			break;
 
 		available += objects;
 		if (!object) {
diff --git a/mm/z3fold.c b/mm/z3fold.c
index b5dafa7e44e4..9d889ad2bb86 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -1346,8 +1346,22 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 			page = list_entry(pos, struct page, lru);
 
 			zhdr = page_address(page);
-			if (test_bit(PAGE_HEADLESS, &page->private))
+			if (test_bit(PAGE_HEADLESS, &page->private)) {
+				/*
+				 * For non-headless pages, we wait to do this
+				 * until we have the page lock to avoid racing
+				 * with __z3fold_alloc(). Headless pages don't
+				 * have a lock (and __z3fold_alloc() will never
+				 * see them), but we still need to test and set
+				 * PAGE_CLAIMED to avoid racing with
+				 * z3fold_free(), so just do it now before
+				 * leaving the loop.
+				 */
+				if (test_and_set_bit(PAGE_CLAIMED, &page->private))
+					continue;
+
 				break;
+			}
 
 			if (kref_get_unless_zero(&zhdr->refcount) == 0) {
 				zhdr = NULL;