Merge tag 'mm-hotfixes-stable-2023-04-19-16-36' of...

Merge tag 'mm-hotfixes-stable-2023-04-19-16-36' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "22 hotfixes.

  19 are cc:stable and the remainder address issues which were
  introduced during this merge cycle, or aren't considered suitable for
  -stable backporting.

  19 are for MM and the remainder are for other subsystems"

* tag 'mm-hotfixes-stable-2023-04-19-16-36' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (22 commits)
  nilfs2: initialize unused bytes in segment summary blocks
  mm: page_alloc: skip regions with hugetlbfs pages when allocating 1G pages
  mm/mmap: regression fix for unmapped_area{_topdown}
  maple_tree: fix mas_empty_area() search
  maple_tree: make maple state reusable after mas_empty_area_rev()
  mm: kmsan: handle alloc failures in kmsan_ioremap_page_range()
  mm: kmsan: handle alloc failures in kmsan_vmap_pages_range_noflush()
  tools/Makefile: do missed s/vm/mm/
  mm: fix memory leak on mm_init error handling
  mm/page_alloc: fix potential deadlock on zonelist_update_seq seqlock
  kernel/sys.c: fix and improve control flow in __sys_setres[ug]id()
  Revert "userfaultfd: don't fail on unrecognized features"
  writeback, cgroup: fix null-ptr-deref write in bdi_split_work_to_wbs
  maple_tree: fix a potential memory leak, OOB access, or other unpredictable bug
  tools/mm/page_owner_sort.c: fix TGID output when cull=tg is used
  mailmap: update jtoppins' entry to reference correct email
  mm/mempolicy: fix use-after-free of VMA iterator
  mm/huge_memory.c: warn with pr_warn_ratelimited instead of VM_WARN_ON_ONCE_FOLIO
  mm/mprotect: fix do_mprotect_pkey() return on error
  mm/khugepaged: check again on anon uffd-wp during isolation
  ...

.mailmap

@@ -232,6 +232,8 @@ Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com>
 John Crispin <john@phrozen.org> <blogic@openwrt.org>
 John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>
 John Stultz <johnstul@us.ibm.com>
+<jon.toppins+linux@gmail.com> <jtoppins@cumulusnetworks.com>
+<jon.toppins+linux@gmail.com> <jtoppins@redhat.com>
 Jordan Crouse <jordan@cosmicpenguin.net> <jcrouse@codeaurora.org>
 <josh@joshtriplett.org> <josh@freedesktop.org>
 <josh@joshtriplett.org> <josh@kernel.org>

fs/fs-writeback.c

@@ -978,6 +978,16 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
 			continue;
 		}
 
+		/*
+		 * If wb_tryget fails, the wb has been shutdown, skip it.
+		 *
+		 * Pin @wb so that it stays on @bdi->wb_list.  This allows
+		 * continuing iteration from @wb after dropping and
+		 * regrabbing rcu read lock.
+		 */
+		if (!wb_tryget(wb))
+			continue;
+
 		/* alloc failed, execute synchronously using on-stack fallback */
 		work = &fallback_work;
 		*work = *base_work;
@@ -986,13 +996,6 @@ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
 		work->done = &fallback_work_done;
 
 		wb_queue_work(wb, work);
-
-		/*
-		 * Pin @wb so that it stays on @bdi->wb_list.  This allows
-		 * continuing iteration from @wb after dropping and
-		 * regrabbing rcu read lock.
-		 */
-		wb_get(wb);
 		last_wb = wb;
 
 		rcu_read_unlock();

fs/nilfs2/segment.c

@@ -430,6 +430,23 @@ static int nilfs_segctor_reset_segment_buffer(struct nilfs_sc_info *sci)
 	return 0;
 }
 
+/**
+ * nilfs_segctor_zeropad_segsum - zero pad the rest of the segment summary area
+ * @sci: segment constructor object
+ *
+ * nilfs_segctor_zeropad_segsum() zero-fills unallocated space at the end of
+ * the current segment summary block.
+ */
+static void nilfs_segctor_zeropad_segsum(struct nilfs_sc_info *sci)
+{
+	struct nilfs_segsum_pointer *ssp;
+
+	ssp = sci->sc_blk_cnt > 0 ? &sci->sc_binfo_ptr : &sci->sc_finfo_ptr;
+	if (ssp->offset < ssp->bh->b_size)
+		memset(ssp->bh->b_data + ssp->offset, 0,
+		       ssp->bh->b_size - ssp->offset);
+}
+
 static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci)
 {
 	sci->sc_nblk_this_inc += sci->sc_curseg->sb_sum.nblocks;
@@ -438,6 +455,7 @@ static int nilfs_segctor_feed_segment(struct nilfs_sc_info *sci)
 				* The current segment is filled up
 				* (internal code)
 				*/
+	nilfs_segctor_zeropad_segsum(sci);
 	sci->sc_curseg = NILFS_NEXT_SEGBUF(sci->sc_curseg);
 	return nilfs_segctor_reset_segment_buffer(sci);
 }
@@ -542,6 +560,7 @@ static int nilfs_segctor_add_file_block(struct nilfs_sc_info *sci,
 		goto retry;
 	}
 	if (unlikely(required)) {
+		nilfs_segctor_zeropad_segsum(sci);
 		err = nilfs_segbuf_extend_segsum(segbuf);
 		if (unlikely(err))
 			goto failed;
@@ -1533,6 +1552,7 @@ static int nilfs_segctor_collect(struct nilfs_sc_info *sci,
 		nadd = min_t(int, nadd << 1, SC_MAX_SEGDELTA);
 		sci->sc_stage = prev_stage;
 	}
+	nilfs_segctor_zeropad_segsum(sci);
 	nilfs_segctor_truncate_segments(sci, sci->sc_curseg, nilfs->ns_sufile);
 	return 0;
 

fs/userfaultfd.c

@@ -1955,8 +1955,10 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api)))
 		goto out;
-	/* Ignore unsupported features (userspace built against newer kernel) */
-	features = uffdio_api.features & UFFD_API_FEATURES;
+	features = uffdio_api.features;
+	ret = -EINVAL;
+	if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES))
+		goto err_out;
 	ret = -EPERM;
 	if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE))
 		goto err_out;

include/linux/kmsan.h

@@ -134,11 +134,12 @@ void kmsan_kfree_large(const void *ptr);
  * @page_shift:	page_shift passed to vmap_range_noflush().
  *
  * KMSAN maps shadow and origin pages of @pages into contiguous ranges in
- * vmalloc metadata address range.
+ * vmalloc metadata address range. Returns 0 on success, callers must check
+ * for non-zero return value.
  */
-void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end,
-				    pgprot_t prot, struct page **pages,
-				    unsigned int page_shift);
+int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end,
+				   pgprot_t prot, struct page **pages,
+				   unsigned int page_shift);
 
 /**
  * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap.
@@ -159,11 +160,12 @@ void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end);
  * @page_shift:	page_shift argument passed to vmap_range_noflush().
  *
  * KMSAN creates new metadata pages for the physical pages mapped into the
- * virtual memory.
+ * virtual memory. Returns 0 on success, callers must check for non-zero return
+ * value.
  */
-void kmsan_ioremap_page_range(unsigned long addr, unsigned long end,
-			      phys_addr_t phys_addr, pgprot_t prot,
-			      unsigned int page_shift);
+int kmsan_ioremap_page_range(unsigned long addr, unsigned long end,
+			     phys_addr_t phys_addr, pgprot_t prot,
+			     unsigned int page_shift);
 
 /**
  * kmsan_iounmap_page_range() - Notify KMSAN about a iounmap_page_range() call.
@@ -281,12 +283,13 @@ static inline void kmsan_kfree_large(const void *ptr)
 {
 }
 
-static inline void kmsan_vmap_pages_range_noflush(unsigned long start,
-						  unsigned long end,
-						  pgprot_t prot,
-						  struct page **pages,
-						  unsigned int page_shift)
+static inline int kmsan_vmap_pages_range_noflush(unsigned long start,
+						 unsigned long end,
+						 pgprot_t prot,
+						 struct page **pages,
+						 unsigned int page_shift)
 {
+	return 0;
 }
 
 static inline void kmsan_vunmap_range_noflush(unsigned long start,
@@ -294,12 +297,12 @@ static inline void kmsan_vunmap_range_noflush(unsigned long start,
 {
 }
 
-static inline void kmsan_ioremap_page_range(unsigned long start,
-					    unsigned long end,
-					    phys_addr_t phys_addr,
-					    pgprot_t prot,
-					    unsigned int page_shift)
+static inline int kmsan_ioremap_page_range(unsigned long start,
+					   unsigned long end,
+					   phys_addr_t phys_addr, pgprot_t prot,
+					   unsigned int page_shift)
 {
+	return 0;
 }
 
 static inline void kmsan_iounmap_page_range(unsigned long start,

kernel/fork.c

@@ -1174,6 +1174,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 fail_pcpu:
 	while (i > 0)
 		percpu_counter_destroy(&mm->rss_stat[--i]);
+	destroy_context(mm);
 fail_nocontext:
 	mm_free_pgd(mm);
 fail_nopgd:

kernel/sys.c

@@ -664,6 +664,7 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
 	struct cred *new;
 	int retval;
 	kuid_t kruid, keuid, ksuid;
+	bool ruid_new, euid_new, suid_new;
 
 	kruid = make_kuid(ns, ruid);
 	keuid = make_kuid(ns, euid);
@@ -678,25 +679,29 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
 	if ((suid != (uid_t) -1) && !uid_valid(ksuid))
 		return -EINVAL;
 
+	old = current_cred();
+
+	/* check for no-op */
+	if ((ruid == (uid_t) -1 || uid_eq(kruid, old->uid)) &&
+	    (euid == (uid_t) -1 || (uid_eq(keuid, old->euid) &&
+				    uid_eq(keuid, old->fsuid))) &&
+	    (suid == (uid_t) -1 || uid_eq(ksuid, old->suid)))
+		return 0;
+
+	ruid_new = ruid != (uid_t) -1        && !uid_eq(kruid, old->uid) &&
+		   !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid);
+	euid_new = euid != (uid_t) -1        && !uid_eq(keuid, old->uid) &&
+		   !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid);
+	suid_new = suid != (uid_t) -1        && !uid_eq(ksuid, old->uid) &&
+		   !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid);
+	if ((ruid_new || euid_new || suid_new) &&
+	    !ns_capable_setid(old->user_ns, CAP_SETUID))
+		return -EPERM;
+
 	new = prepare_creds();
 	if (!new)
 		return -ENOMEM;
 
-	old = current_cred();
-
-	retval = -EPERM;
-	if (!ns_capable_setid(old->user_ns, CAP_SETUID)) {
-		if (ruid != (uid_t) -1        && !uid_eq(kruid, old->uid) &&
-		    !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid))
-			goto error;
-		if (euid != (uid_t) -1        && !uid_eq(keuid, old->uid) &&
-		    !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid))
-			goto error;
-		if (suid != (uid_t) -1        && !uid_eq(ksuid, old->uid) &&
-		    !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid))
-			goto error;
-	}
-
 	if (ruid != (uid_t) -1) {
 		new->uid = kruid;
 		if (!uid_eq(kruid, old->uid)) {
@@ -761,6 +766,7 @@ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
 	struct cred *new;
 	int retval;
 	kgid_t krgid, kegid, ksgid;
+	bool rgid_new, egid_new, sgid_new;
 
 	krgid = make_kgid(ns, rgid);
 	kegid = make_kgid(ns, egid);
@@ -773,23 +779,28 @@ long __sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
 	if ((sgid != (gid_t) -1) && !gid_valid(ksgid))
 		return -EINVAL;
 
+	old = current_cred();
+
+	/* check for no-op */
+	if ((rgid == (gid_t) -1 || gid_eq(krgid, old->gid)) &&
+	    (egid == (gid_t) -1 || (gid_eq(kegid, old->egid) &&
+				    gid_eq(kegid, old->fsgid))) &&
+	    (sgid == (gid_t) -1 || gid_eq(ksgid, old->sgid)))
+		return 0;
+
+	rgid_new = rgid != (gid_t) -1        && !gid_eq(krgid, old->gid) &&
+		   !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid);
+	egid_new = egid != (gid_t) -1        && !gid_eq(kegid, old->gid) &&
+		   !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid);
+	sgid_new = sgid != (gid_t) -1        && !gid_eq(ksgid, old->gid) &&
+		   !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid);
+	if ((rgid_new || egid_new || sgid_new) &&
+	    !ns_capable_setid(old->user_ns, CAP_SETGID))
+		return -EPERM;
+
 	new = prepare_creds();
 	if (!new)
 		return -ENOMEM;
-	old = current_cred();
-
-	retval = -EPERM;
-	if (!ns_capable_setid(old->user_ns, CAP_SETGID)) {
-		if (rgid != (gid_t) -1        && !gid_eq(krgid, old->gid) &&
-		    !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid))
-			goto error;
-		if (egid != (gid_t) -1        && !gid_eq(kegid, old->gid) &&
-		    !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid))
-			goto error;
-		if (sgid != (gid_t) -1        && !gid_eq(ksgid, old->gid) &&
-		    !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid))
-			goto error;
-	}
 
 	if (rgid != (gid_t) -1)
 		new->gid = krgid;

lib/maple_tree.c

@@ -1303,26 +1303,21 @@ static inline void mas_alloc_nodes(struct ma_state *mas, gfp_t gfp)
 	node = mas->alloc;
 	node->request_count = 0;
 	while (requested) {
-		max_req = MAPLE_ALLOC_SLOTS;
-		if (node->node_count) {
-			unsigned int offset = node->node_count;
-
-			slots = (void **)&node->slot[offset];
-			max_req -= offset;
-		} else {
-			slots = (void **)&node->slot;
-		}
-
+		max_req = MAPLE_ALLOC_SLOTS - node->node_count;
+		slots = (void **)&node->slot[node->node_count];
 		max_req = min(requested, max_req);
 		count = mt_alloc_bulk(gfp, max_req, slots);
 		if (!count)
 			goto nomem_bulk;
 
+		if (node->node_count == 0) {
+			node->slot[0]->node_count = 0;
+			node->slot[0]->request_count = 0;
+		}
+
 		node->node_count += count;
 		allocated += count;
 		node = node->slot[0];
-		node->node_count = 0;
-		node->request_count = 0;
 		requested -= count;
 	}
 	mas->alloc->total = allocated;
@@ -4970,7 +4965,8 @@ static inline void *mas_prev_entry(struct ma_state *mas, unsigned long min)
  * Return: True if found in a leaf, false otherwise.
  *
  */
-static bool mas_rev_awalk(struct ma_state *mas, unsigned long size)
+static bool mas_rev_awalk(struct ma_state *mas, unsigned long size,
+		unsigned long *gap_min, unsigned long *gap_max)
 {
 	enum maple_type type = mte_node_type(mas->node);
 	struct maple_node *node = mas_mn(mas);
@@ -5035,8 +5031,8 @@ static bool mas_rev_awalk(struct ma_state *mas, unsigned long size)
 
 	if (unlikely(ma_is_leaf(type))) {
 		mas->offset = offset;
-		mas->min = min;
-		mas->max = min + gap - 1;
+		*gap_min = min;
+		*gap_max = min + gap - 1;
 		return true;
 	}
 
@@ -5060,10 +5056,10 @@ static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size)
 {
 	enum maple_type type = mte_node_type(mas->node);
 	unsigned long pivot, min, gap = 0;
-	unsigned char offset;
-	unsigned long *gaps;
-	unsigned long *pivots = ma_pivots(mas_mn(mas), type);
-	void __rcu **slots = ma_slots(mas_mn(mas), type);
+	unsigned char offset, data_end;
+	unsigned long *gaps, *pivots;
+	void __rcu **slots;
+	struct maple_node *node;
 	bool found = false;
 
 	if (ma_is_dense(type)) {
@@ -5071,13 +5067,15 @@ static inline bool mas_anode_descend(struct ma_state *mas, unsigned long size)
 		return true;
 	}
 
-	gaps = ma_gaps(mte_to_node(mas->node), type);
+	node = mas_mn(mas);
+	pivots = ma_pivots(node, type);
+	slots = ma_slots(node, type);
+	gaps = ma_gaps(node, type);
 	offset = mas->offset;
 	min = mas_safe_min(mas, pivots, offset);
-	for (; offset < mt_slots[type]; offset++) {
-		pivot = mas_safe_pivot(mas, pivots, offset, type);
-		if (offset && !pivot)
-			break;
+	data_end = ma_data_end(node, type, pivots, mas->max);
+	for (; offset <= data_end; offset++) {
+		pivot = mas_logical_pivot(mas, pivots, offset, type);
 
 		/* Not within lower bounds */
 		if (mas->index > pivot)
@@ -5312,6 +5310,9 @@ int mas_empty_area(struct ma_state *mas, unsigned long min,
 	unsigned long *pivots;
 	enum maple_type mt;
 
+	if (min >= max)
+		return -EINVAL;
+
 	if (mas_is_start(mas))
 		mas_start(mas);
 	else if (mas->offset >= 2)
@@ -5366,6 +5367,9 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min,
 {
 	struct maple_enode *last = mas->node;
 
+	if (min >= max)
+		return -EINVAL;
+
 	if (mas_is_start(mas)) {
 		mas_start(mas);
 		mas->offset = mas_data_end(mas);
@@ -5385,7 +5389,7 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min,
 	mas->index = min;
 	mas->last = max;
 
-	while (!mas_rev_awalk(mas, size)) {
+	while (!mas_rev_awalk(mas, size, &min, &max)) {
 		if (last == mas->node) {
 			if (!mas_rewind_node(mas))
 				return -EBUSY;
@@ -5400,17 +5404,9 @@ int mas_empty_area_rev(struct ma_state *mas, unsigned long min,
 	if (unlikely(mas->offset == MAPLE_NODE_SLOTS))
 		return -EBUSY;
 
-	/*
-	 * mas_rev_awalk() has set mas->min and mas->max to the gap values.  If
-	 * the maximum is outside the window we are searching, then use the last
-	 * location in the search.
-	 * mas->max and mas->min is the range of the gap.
-	 * mas->index and mas->last are currently set to the search range.
-	 */
-
 	/* Trim the upper limit to the max. */
-	if (mas->max <= mas->last)
-		mas->last = mas->max;
+	if (max <= mas->last)
+		mas->last = max;
 
 	mas->index = mas->last - size + 1;
 	return 0;

mm/backing-dev.c

@@ -507,6 +507,15 @@ static LIST_HEAD(offline_cgwbs);
 static void cleanup_offline_cgwbs_workfn(struct work_struct *work);
 static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn);
 
+static void cgwb_free_rcu(struct rcu_head *rcu_head)
+{
+	struct bdi_writeback *wb = container_of(rcu_head,
+			struct bdi_writeback, rcu);
+
+	percpu_ref_exit(&wb->refcnt);
+	kfree(wb);
+}
+
 static void cgwb_release_workfn(struct work_struct *work)
 {
 	struct bdi_writeback *wb = container_of(work, struct bdi_writeback,
@@ -529,11 +538,10 @@ static void cgwb_release_workfn(struct work_struct *work)
 	list_del(&wb->offline_node);
 	spin_unlock_irq(&cgwb_lock);
 
-	percpu_ref_exit(&wb->refcnt);
 	wb_exit(wb);
 	bdi_put(bdi);
 	WARN_ON_ONCE(!list_empty(&wb->b_attached));
-	kfree_rcu(wb, rcu);
+	call_rcu(&wb->rcu, cgwb_free_rcu);
 }
 
 static void cgwb_release(struct percpu_ref *refcnt)

mm/huge_memory.c

@@ -1838,10 +1838,10 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	if (is_swap_pmd(*pmd)) {
 		swp_entry_t entry = pmd_to_swp_entry(*pmd);
 		struct page *page = pfn_swap_entry_to_page(entry);
+		pmd_t newpmd;
 
 		VM_BUG_ON(!is_pmd_migration_entry(*pmd));
 		if (is_writable_migration_entry(entry)) {
-			pmd_t newpmd;
 			/*
 			 * A protection check is difficult so
 			 * just be safe and disable write
@@ -1855,8 +1855,16 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 				newpmd = pmd_swp_mksoft_dirty(newpmd);
 			if (pmd_swp_uffd_wp(*pmd))
 				newpmd = pmd_swp_mkuffd_wp(newpmd);
-			set_pmd_at(mm, addr, pmd, newpmd);
+		} else {
+			newpmd = *pmd;
 		}
+
+		if (uffd_wp)
+			newpmd = pmd_swp_mkuffd_wp(newpmd);
+		else if (uffd_wp_resolve)
+			newpmd = pmd_swp_clear_uffd_wp(newpmd);
+		if (!pmd_same(*pmd, newpmd))
+			set_pmd_at(mm, addr, pmd, newpmd);
 		goto unlock;
 	}
 #endif
@@ -2657,9 +2665,10 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
 
 	is_hzp = is_huge_zero_page(&folio->page);
-	VM_WARN_ON_ONCE_FOLIO(is_hzp, folio);
-	if (is_hzp)
+	if (is_hzp) {
+		pr_warn_ratelimited("Called split_huge_page for huge zero page\n");
 		return -EBUSY;
+	}
 
 	if (folio_test_writeback(folio))
 		return -EBUSY;
@@ -3251,6 +3260,8 @@ int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 	pmdswp = swp_entry_to_pmd(entry);
 	if (pmd_soft_dirty(pmdval))
 		pmdswp = pmd_swp_mksoft_dirty(pmdswp);
+	if (pmd_uffd_wp(pmdval))
+		pmdswp = pmd_swp_mkuffd_wp(pmdswp);
 	set_pmd_at(mm, address, pvmw->pmd, pmdswp);
 	page_remove_rmap(page, vma, true);
 	put_page(page);

mm/khugepaged.c

@@ -572,6 +572,10 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 			result = SCAN_PTE_NON_PRESENT;
 			goto out;
 		}
+		if (pte_uffd_wp(pteval)) {
+			result = SCAN_PTE_UFFD_WP;
+			goto out;
+		}
 		page = vm_normal_page(vma, address, pteval);
 		if (unlikely(!page) || unlikely(is_zone_device_page(page))) {
 			result = SCAN_PAGE_NULL;

mm/kmsan/hooks.c

@@ -148,35 +148,74 @@ void kmsan_vunmap_range_noflush(unsigned long start, unsigned long end)
  * into the virtual memory. If those physical pages already had shadow/origin,
  * those are ignored.
  */
-void kmsan_ioremap_page_range(unsigned long start, unsigned long end,
-			      phys_addr_t phys_addr, pgprot_t prot,
-			      unsigned int page_shift)
+int kmsan_ioremap_page_range(unsigned long start, unsigned long end,
+			     phys_addr_t phys_addr, pgprot_t prot,
+			     unsigned int page_shift)
 {
 	gfp_t gfp_mask = GFP_KERNEL | __GFP_ZERO;
 	struct page *shadow, *origin;
 	unsigned long off = 0;
-	int nr;
+	int nr, err = 0, clean = 0, mapped;
 
 	if (!kmsan_enabled || kmsan_in_runtime())
-		return;
+		return 0;
 
 	nr = (end - start) / PAGE_SIZE;
 	kmsan_enter_runtime();
-	for (int i = 0; i < nr; i++, off += PAGE_SIZE) {
+	for (int i = 0; i < nr; i++, off += PAGE_SIZE, clean = i) {
 		shadow = alloc_pages(gfp_mask, 1);
 		origin = alloc_pages(gfp_mask, 1);
-		__vmap_pages_range_noflush(
+		if (!shadow || !origin) {
+			err = -ENOMEM;
+			goto ret;
+		}
+		mapped = __vmap_pages_range_noflush(
 			vmalloc_shadow(start + off),
 			vmalloc_shadow(start + off + PAGE_SIZE), prot, &shadow,
 			PAGE_SHIFT);
-		__vmap_pages_range_noflush(
+		if (mapped) {
+			err = mapped;
+			goto ret;
+		}
+		shadow = NULL;
+		mapped = __vmap_pages_range_noflush(
 			vmalloc_origin(start + off),
 			vmalloc_origin(start + off + PAGE_SIZE), prot, &origin,
 			PAGE_SHIFT);
+		if (mapped) {
+			__vunmap_range_noflush(
+				vmalloc_shadow(start + off),
+				vmalloc_shadow(start + off + PAGE_SIZE));
+			err = mapped;
+			goto ret;
+		}
+		origin = NULL;
+	}
+	/* Page mapping loop finished normally, nothing to clean up. */
+	clean = 0;
+
+ret:
+	if (clean > 0) {
+		/*
+		 * Something went wrong. Clean up shadow/origin pages allocated
+		 * on the last loop iteration, then delete mappings created
+		 * during the previous iterations.
+		 */
+		if (shadow)
+			__free_pages(shadow, 1);
+		if (origin)
+			__free_pages(origin, 1);
+		__vunmap_range_noflush(
+			vmalloc_shadow(start),
+			vmalloc_shadow(start + clean * PAGE_SIZE));
+		__vunmap_range_noflush(
+			vmalloc_origin(start),
+			vmalloc_origin(start + clean * PAGE_SIZE));
 	}
 	flush_cache_vmap(vmalloc_shadow(start), vmalloc_shadow(end));
 	flush_cache_vmap(vmalloc_origin(start), vmalloc_origin(end));
 	kmsan_leave_runtime();
+	return err;
 }
 
 void kmsan_iounmap_page_range(unsigned long start, unsigned long end)

mm/kmsan/shadow.c

@@ -216,27 +216,29 @@ void kmsan_free_page(struct page *page, unsigned int order)
 	kmsan_leave_runtime();
 }
 
-void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end,
-				    pgprot_t prot, struct page **pages,
-				    unsigned int page_shift)
+int kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end,
+				   pgprot_t prot, struct page **pages,
+				   unsigned int page_shift)
 {
 	unsigned long shadow_start, origin_start, shadow_end, origin_end;
 	struct page **s_pages, **o_pages;
-	int nr, mapped;
+	int nr, mapped, err = 0;
 
 	if (!kmsan_enabled)
-		return;
+		return 0;
 
 	shadow_start = vmalloc_meta((void *)start, KMSAN_META_SHADOW);
 	shadow_end = vmalloc_meta((void *)end, KMSAN_META_SHADOW);
 	if (!shadow_start)
-		return;
+		return 0;
 
 	nr = (end - start) / PAGE_SIZE;
 	s_pages = kcalloc(nr, sizeof(*s_pages), GFP_KERNEL);
 	o_pages = kcalloc(nr, sizeof(*o_pages), GFP_KERNEL);
-	if (!s_pages || !o_pages)
+	if (!s_pages || !o_pages) {
+		err = -ENOMEM;
 		goto ret;
+	}
 	for (int i = 0; i < nr; i++) {
 		s_pages[i] = shadow_page_for(pages[i]);
 		o_pages[i] = origin_page_for(pages[i]);
@@ -249,10 +251,16 @@ void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end,
 	kmsan_enter_runtime();
 	mapped = __vmap_pages_range_noflush(shadow_start, shadow_end, prot,
 					    s_pages, page_shift);
-	KMSAN_WARN_ON(mapped);
+	if (mapped) {
+		err = mapped;
+		goto ret;
+	}
 	mapped = __vmap_pages_range_noflush(origin_start, origin_end, prot,
 					    o_pages, page_shift);
-	KMSAN_WARN_ON(mapped);
+	if (mapped) {
+		err = mapped;
+		goto ret;
+	}
 	kmsan_leave_runtime();
 	flush_tlb_kernel_range(shadow_start, shadow_end);
 	flush_tlb_kernel_range(origin_start, origin_end);
@@ -262,6 +270,7 @@ void kmsan_vmap_pages_range_noflush(unsigned long start, unsigned long end,
 ret:
 	kfree(s_pages);
 	kfree(o_pages);
+	return err;
 }
 
 /* Allocate metadata for pages allocated at boot time. */

mm/mempolicy.c

@@ -790,61 +790,50 @@ static int vma_replace_policy(struct vm_area_struct *vma,
 	return err;
 }
 
-/* Step 2: apply policy to a range and do splits. */
-static int mbind_range(struct mm_struct *mm, unsigned long start,
-		       unsigned long end, struct mempolicy *new_pol)
+/* Split or merge the VMA (if required) and apply the new policy */
+static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma,
+		struct vm_area_struct **prev, unsigned long start,
+		unsigned long end, struct mempolicy *new_pol)
 {
-	VMA_ITERATOR(vmi, mm, start);
-	struct vm_area_struct *prev;
-	struct vm_area_struct *vma;
-	int err = 0;
+	struct vm_area_struct *merged;
+	unsigned long vmstart, vmend;
 	pgoff_t pgoff;
+	int err;
 
-	prev = vma_prev(&vmi);
-	vma = vma_find(&vmi, end);
-	if (WARN_ON(!vma))
+	vmend = min(end, vma->vm_end);
+	if (start > vma->vm_start) {
+		*prev = vma;
+		vmstart = start;
+	} else {
+		vmstart = vma->vm_start;
+	}
+
+	if (mpol_equal(vma_policy(vma), new_pol))
 		return 0;
 
-	if (start > vma->vm_start)
-		prev = vma;
-
-	do {
-		unsigned long vmstart = max(start, vma->vm_start);
-		unsigned long vmend = min(end, vma->vm_end);
-
-		if (mpol_equal(vma_policy(vma), new_pol))
-			goto next;
-
-		pgoff = vma->vm_pgoff +
-			((vmstart - vma->vm_start) >> PAGE_SHIFT);
-		prev = vma_merge(&vmi, mm, prev, vmstart, vmend, vma->vm_flags,
-				 vma->anon_vma, vma->vm_file, pgoff,
-				 new_pol, vma->vm_userfaultfd_ctx,
-				 anon_vma_name(vma));
-		if (prev) {
-			vma = prev;
-			goto replace;
-		}
-		if (vma->vm_start != vmstart) {
-			err = split_vma(&vmi, vma, vmstart, 1);
-			if (err)
-				goto out;
-		}
-		if (vma->vm_end != vmend) {
-			err = split_vma(&vmi, vma, vmend, 0);
-			if (err)
-				goto out;
-		}
-replace:
-		err = vma_replace_policy(vma, new_pol);
+	pgoff = vma->vm_pgoff + ((vmstart - vma->vm_start) >> PAGE_SHIFT);
+	merged = vma_merge(vmi, vma->vm_mm, *prev, vmstart, vmend, vma->vm_flags,
+			 vma->anon_vma, vma->vm_file, pgoff, new_pol,
+			 vma->vm_userfaultfd_ctx, anon_vma_name(vma));
+	if (merged) {
+		*prev = merged;
+		return vma_replace_policy(merged, new_pol);
+	}
+
+	if (vma->vm_start != vmstart) {
+		err = split_vma(vmi, vma, vmstart, 1);
 		if (err)
-			goto out;
-next:
-		prev = vma;
-	} for_each_vma_range(vmi, vma, end);
+			return err;
+	}
 
-out:
-	return err;
+	if (vma->vm_end != vmend) {
+		err = split_vma(vmi, vma, vmend, 0);
+		if (err)
+			return err;
+	}
+
+	*prev = vma;
+	return vma_replace_policy(vma, new_pol);
 }
 
 /* Set the process memory policy */
@@ -1259,6 +1248,8 @@ static long do_mbind(unsigned long start, unsigned long len,
 		     nodemask_t *nmask, unsigned long flags)
 {
 	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma, *prev;
+	struct vma_iterator vmi;
 	struct mempolicy *new;
 	unsigned long end;
 	int err;
@@ -1328,7 +1319,13 @@ static long do_mbind(unsigned long start, unsigned long len,
 		goto up_out;
 	}
 
-	err = mbind_range(mm, start, end, new);
+	vma_iter_init(&vmi, mm, start);
+	prev = vma_prev(&vmi);
+	for_each_vma_range(vmi, vma, end) {
+		err = mbind_range(&vmi, vma, &prev, start, end, new);
+		if (err)
+			break;
+	}
 
 	if (!err) {
 		int nr_failed = 0;
@@ -1489,10 +1486,8 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le
 		unsigned long, home_node, unsigned long, flags)
 {
 	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
+	struct vm_area_struct *vma, *prev;
 	struct mempolicy *new, *old;
-	unsigned long vmstart;
-	unsigned long vmend;
 	unsigned long end;
 	int err = -ENOENT;
 	VMA_ITERATOR(vmi, mm, start);
@@ -1521,6 +1516,7 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le
 	if (end == start)
 		return 0;
 	mmap_write_lock(mm);
+	prev = vma_prev(&vmi);
 	for_each_vma_range(vmi, vma, end) {
 		/*
 		 * If any vma in the range got policy other than MPOL_BIND
@@ -1541,9 +1537,7 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le
 		}
 
 		new->home_node = home_node;
-		vmstart = max(start, vma->vm_start);
-		vmend   = min(end, vma->vm_end);
-		err = mbind_range(mm, vmstart, vmend, new);
+		err = mbind_range(&vmi, vma, &prev, start, end, new);
 		mpol_put(new);
 		if (err)
 			break;

mm/mmap.c

@@ -1518,7 +1518,8 @@ static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags)
  */
 static unsigned long unmapped_area(struct vm_unmapped_area_info *info)
 {
-	unsigned long length, gap;
+	unsigned long length, gap, low_limit;
+	struct vm_area_struct *tmp;
 
 	MA_STATE(mas, &current->mm->mm_mt, 0, 0);
 
@@ -1527,12 +1528,29 @@ static unsigned long unmapped_area(struct vm_unmapped_area_info *info)
 	if (length < info->length)
 		return -ENOMEM;
 
-	if (mas_empty_area(&mas, info->low_limit, info->high_limit - 1,
-				  length))
+	low_limit = info->low_limit;
+retry:
+	if (mas_empty_area(&mas, low_limit, info->high_limit - 1, length))
 		return -ENOMEM;
 
 	gap = mas.index;
 	gap += (info->align_offset - gap) & info->align_mask;
+	tmp = mas_next(&mas, ULONG_MAX);
+	if (tmp && (tmp->vm_flags & VM_GROWSDOWN)) { /* Avoid prev check if possible */
+		if (vm_start_gap(tmp) < gap + length - 1) {
+			low_limit = tmp->vm_end;
+			mas_reset(&mas);
+			goto retry;
+		}
+	} else {
+		tmp = mas_prev(&mas, 0);
+		if (tmp && vm_end_gap(tmp) > gap) {
+			low_limit = vm_end_gap(tmp);
+			mas_reset(&mas);
+			goto retry;
+		}
+	}
+
 	return gap;
 }
 
@@ -1548,7 +1566,8 @@ static unsigned long unmapped_area(struct vm_unmapped_area_info *info)
  */
 static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
 {
-	unsigned long length, gap;
+	unsigned long length, gap, high_limit, gap_end;
+	struct vm_area_struct *tmp;
 
 	MA_STATE(mas, &current->mm->mm_mt, 0, 0);
 	/* Adjust search length to account for worst case alignment overhead */
@@ -1556,12 +1575,31 @@ static unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
 	if (length < info->length)
 		return -ENOMEM;
 
-	if (mas_empty_area_rev(&mas, info->low_limit, info->high_limit - 1,
+	high_limit = info->high_limit;
+retry:
+	if (mas_empty_area_rev(&mas, info->low_limit, high_limit - 1,
 				length))
 		return -ENOMEM;
 
 	gap = mas.last + 1 - info->length;
 	gap -= (gap - info->align_offset) & info->align_mask;
+	gap_end = mas.last;
+	tmp = mas_next(&mas, ULONG_MAX);
+	if (tmp && (tmp->vm_flags & VM_GROWSDOWN)) { /* Avoid prev check if possible */
+		if (vm_start_gap(tmp) <= gap_end) {
+			high_limit = vm_start_gap(tmp);
+			mas_reset(&mas);
+			goto retry;
+		}
+	} else {
+		tmp = mas_prev(&mas, 0);
+		if (tmp && vm_end_gap(tmp) > gap) {
+			high_limit = tmp->vm_start;
+			mas_reset(&mas);
+			goto retry;
+		}
+	}
+
 	return gap;
 }
 

mm/mprotect.c

@@ -838,7 +838,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	}
 	tlb_finish_mmu(&tlb);
 
-	if (vma_iter_end(&vmi) < end)
+	if (!error && vma_iter_end(&vmi) < end)
 		error = -ENOMEM;
 
 out:

mm/page_alloc.c

@@ -6632,7 +6632,21 @@ static void __build_all_zonelists(void *data)
 	int nid;
 	int __maybe_unused cpu;
 	pg_data_t *self = data;
+	unsigned long flags;
 
+	/*
+	 * Explicitly disable this CPU's interrupts before taking seqlock
+	 * to prevent any IRQ handler from calling into the page allocator
+	 * (e.g. GFP_ATOMIC) that could hit zonelist_iter_begin and livelock.
+	 */
+	local_irq_save(flags);
+	/*
+	 * Explicitly disable this CPU's synchronous printk() before taking
+	 * seqlock to prevent any printk() from trying to hold port->lock, for
+	 * tty_insert_flip_string_and_push_buffer() on other CPU might be
+	 * calling kmalloc(GFP_ATOMIC | __GFP_NOWARN) with port->lock held.
+	 */
+	printk_deferred_enter();
 	write_seqlock(&zonelist_update_seq);
 
 #ifdef CONFIG_NUMA
@@ -6671,6 +6685,8 @@ static void __build_all_zonelists(void *data)
 	}
 
 	write_sequnlock(&zonelist_update_seq);
+	printk_deferred_exit();
+	local_irq_restore(flags);
 }
 
 static noinline void __init
@@ -9450,6 +9466,9 @@ static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn,
 
 		if (PageReserved(page))
 			return false;
+
+		if (PageHuge(page))
+			return false;
 	}
 	return true;
 }

mm/swap.c

@@ -222,7 +222,7 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn)
 	if (lruvec)
 		unlock_page_lruvec_irqrestore(lruvec, flags);
 	folios_put(fbatch->folios, folio_batch_count(fbatch));
-	folio_batch_init(fbatch);
+	folio_batch_reinit(fbatch);
 }
 
 static void folio_batch_add_and_move(struct folio_batch *fbatch,

mm/vmalloc.c

@@ -313,8 +313,8 @@ int ioremap_page_range(unsigned long addr, unsigned long end,
 				 ioremap_max_page_shift);
 	flush_cache_vmap(addr, end);
 	if (!err)
-		kmsan_ioremap_page_range(addr, end, phys_addr, prot,
-					 ioremap_max_page_shift);
+		err = kmsan_ioremap_page_range(addr, end, phys_addr, prot,
+					       ioremap_max_page_shift);
 	return err;
 }
 
@@ -605,7 +605,11 @@ int __vmap_pages_range_noflush(unsigned long addr, unsigned long end,
 int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
 		pgprot_t prot, struct page **pages, unsigned int page_shift)
 {
-	kmsan_vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
+	int ret = kmsan_vmap_pages_range_noflush(addr, end, prot, pages,
+						 page_shift);
+
+	if (ret)
+		return ret;
 	return __vmap_pages_range_noflush(addr, end, prot, pages, page_shift);
 }
 

tools/Makefile

@@ -39,7 +39,7 @@ help:
 	@echo '  turbostat              - Intel CPU idle stats and freq reporting tool'
 	@echo '  usb                    - USB testing tools'
 	@echo '  virtio                 - vhost test module'
-	@echo '  vm                     - misc vm tools'
+	@echo '  mm                     - misc mm tools'
 	@echo '  wmi			- WMI interface examples'
 	@echo '  x86_energy_perf_policy - Intel energy policy tool'
 	@echo ''
@@ -69,7 +69,7 @@ acpi: FORCE
 cpupower: FORCE
 	$(call descend,power/$@)
 
-cgroup counter firewire hv guest bootconfig spi usb virtio vm bpf iio gpio objtool leds wmi pci firmware debugging tracing: FORCE
+cgroup counter firewire hv guest bootconfig spi usb virtio mm bpf iio gpio objtool leds wmi pci firmware debugging tracing: FORCE
 	$(call descend,$@)
 
 bpf/%: FORCE
@@ -118,7 +118,7 @@ kvm_stat: FORCE
 
 all: acpi cgroup counter cpupower gpio hv firewire \
 		perf selftests bootconfig spi turbostat usb \
-		virtio vm bpf x86_energy_perf_policy \
+		virtio mm bpf x86_energy_perf_policy \
 		tmon freefall iio objtool kvm_stat wmi \
 		pci debugging tracing thermal thermometer thermal-engine
 
@@ -128,7 +128,7 @@ acpi_install:
 cpupower_install:
 	$(call descend,power/$(@:_install=),install)
 
-cgroup_install counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install vm_install bpf_install objtool_install wmi_install pci_install debugging_install tracing_install:
+cgroup_install counter_install firewire_install gpio_install hv_install iio_install perf_install bootconfig_install spi_install usb_install virtio_install mm_install bpf_install objtool_install wmi_install pci_install debugging_install tracing_install:
 	$(call descend,$(@:_install=),install)
 
 selftests_install:
@@ -158,7 +158,7 @@ kvm_stat_install:
 install: acpi_install cgroup_install counter_install cpupower_install gpio_install \
 		hv_install firewire_install iio_install \
 		perf_install selftests_install turbostat_install usb_install \
-		virtio_install vm_install bpf_install x86_energy_perf_policy_install \
+		virtio_install mm_install bpf_install x86_energy_perf_policy_install \
 		tmon_install freefall_install objtool_install kvm_stat_install \
 		wmi_install pci_install debugging_install intel-speed-select_install \
 		tracing_install thermometer_install thermal-engine_install
@@ -169,7 +169,7 @@ acpi_clean:
 cpupower_clean:
 	$(call descend,power/cpupower,clean)
 
-cgroup_clean counter_clean hv_clean firewire_clean bootconfig_clean spi_clean usb_clean virtio_clean vm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean tracing_clean:
+cgroup_clean counter_clean hv_clean firewire_clean bootconfig_clean spi_clean usb_clean virtio_clean mm_clean wmi_clean bpf_clean iio_clean gpio_clean objtool_clean leds_clean pci_clean firmware_clean debugging_clean tracing_clean:
 	$(call descend,$(@:_clean=),clean)
 
 libapi_clean:
@@ -211,7 +211,7 @@ build_clean:
 
 clean: acpi_clean cgroup_clean counter_clean cpupower_clean hv_clean firewire_clean \
 		perf_clean selftests_clean turbostat_clean bootconfig_clean spi_clean usb_clean virtio_clean \
-		vm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
+		mm_clean bpf_clean iio_clean x86_energy_perf_policy_clean tmon_clean \
 		freefall_clean build_clean libbpf_clean libsubcmd_clean \
 		gpio_clean objtool_clean leds_clean wmi_clean pci_clean firmware_clean debugging_clean \
 		intel-speed-select_clean tracing_clean thermal_clean thermometer_clean thermal-engine_clean

tools/mm/page_owner_sort.c

@@ -857,7 +857,7 @@ int main(int argc, char **argv)
 			if (cull & CULL_PID || filter & FILTER_PID)
 				fprintf(fout, ", PID %d", list[i].pid);
 			if (cull & CULL_TGID || filter & FILTER_TGID)
-				fprintf(fout, ", TGID %d", list[i].pid);
+				fprintf(fout, ", TGID %d", list[i].tgid);
 			if (cull & CULL_COMM || filter & FILTER_COMM)
 				fprintf(fout, ", task_comm_name: %s", list[i].comm);
 			if (cull & CULL_ALLOCATOR) {