15 hotfixes. 11 are cc:stable and the remainder address post-6.16 issues

or aren't considered necessary for -stable kernels.  13 of these fixes are
 for MM.
 
 The usual shower of singletons, plus
 
 - A 5 patch series from Hugh which addresses various misbehaviors in
   get_user_pages()
 
 - A 2 patch series from SeongJae which addresses a quite severe issue in
   DAMON
 
 - A 3 patch series also from SeongJae which completes some fixes for a
   DAMON startup issue
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYKAB0WIQTTMBEPP41GrTpTJgfdBJ7gKXxAjgUCaMuGSgAKCRDdBJ7gKXxA
 junjAP9b9pqZ+xh/MhDWObiRilS8wRDF76NDj237x2oqKTTnmAEA1Rxnqf9nQotP
 XyuXfMZnHDcAHLc1EnsG7OjtMd7QDgU=
 =lifP
 -----END PGP SIGNATURE-----

Merge tag 'mm-hotfixes-stable-2025-09-17-21-10' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "15 hotfixes. 11 are cc:stable and the remainder address post-6.16
  issues or aren't considered necessary for -stable kernels. 13 of these
  fixes are for MM.

  The usual shower of singletons, plus

   - fixes from Hugh to address various misbehaviors in get_user_pages()

   - patches from SeongJae to address a quite severe issue in DAMON

   - another series also from SeongJae which completes some fixes for a
     DAMON startup issue"

* tag 'mm-hotfixes-stable-2025-09-17-21-10' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  zram: fix slot write race condition
  nilfs2: fix CFI failure when accessing /sys/fs/nilfs2/features/*
  samples/damon/mtier: avoid starting DAMON before initialization
  samples/damon/prcl: avoid starting DAMON before initialization
  samples/damon/wsse: avoid starting DAMON before initialization
  MAINTAINERS: add Lance Yang as a THP reviewer
  MAINTAINERS: add Jann Horn as rmap reviewer
  mm/damon/sysfs: use dynamically allocated repeat mode damon_call_control
  mm/damon/core: introduce damon_call_control->dealloc_on_cancel
  mm: folio_may_be_lru_cached() unless folio_test_large()
  mm: revert "mm: vmscan.c: fix OOM on swap stress test"
  mm: revert "mm/gup: clear the LRU flag of a page before adding to LRU batch"
  mm/gup: local lru_add_drain() to avoid lru_add_drain_all()
  mm/gup: check ref_count instead of lru before migration

MAINTAINERS

@@ -16196,6 +16196,7 @@ R:	Rik van Riel <riel@surriel.com>
 R:	Liam R. Howlett <Liam.Howlett@oracle.com>
 R:	Vlastimil Babka <vbabka@suse.cz>
 R:	Harry Yoo <harry.yoo@oracle.com>
+R:	Jann Horn <jannh@google.com>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	include/linux/rmap.h
@@ -16240,6 +16241,7 @@ R:	Nico Pache <npache@redhat.com>
 R:	Ryan Roberts <ryan.roberts@arm.com>
 R:	Dev Jain <dev.jain@arm.com>
 R:	Barry Song <baohua@kernel.org>
+R:	Lance Yang <lance.yang@linux.dev>
 L:	linux-mm@kvack.org
 S:	Maintained
 W:	http://www.linux-mm.org

drivers/block/zram/zram_drv.c

@@ -1795,6 +1795,7 @@ static int write_same_filled_page(struct zram *zram, unsigned long fill,
 				  u32 index)
 {
 	zram_slot_lock(zram, index);
+	zram_free_page(zram, index);
 	zram_set_flag(zram, index, ZRAM_SAME);
 	zram_set_handle(zram, index, fill);
 	zram_slot_unlock(zram, index);
@@ -1832,6 +1833,7 @@ static int write_incompressible_page(struct zram *zram, struct page *page,
 	kunmap_local(src);
 
 	zram_slot_lock(zram, index);
+	zram_free_page(zram, index);
 	zram_set_flag(zram, index, ZRAM_HUGE);
 	zram_set_handle(zram, index, handle);
 	zram_set_obj_size(zram, index, PAGE_SIZE);
@@ -1855,11 +1857,6 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index)
 	unsigned long element;
 	bool same_filled;
 
-	/* First, free memory allocated to this slot (if any) */
-	zram_slot_lock(zram, index);
-	zram_free_page(zram, index);
-	zram_slot_unlock(zram, index);
-
 	mem = kmap_local_page(page);
 	same_filled = page_same_filled(mem, &element);
 	kunmap_local(mem);
@@ -1901,6 +1898,7 @@ static int zram_write_page(struct zram *zram, struct page *page, u32 index)
 	zcomp_stream_put(zstrm);
 
 	zram_slot_lock(zram, index);
+	zram_free_page(zram, index);
 	zram_set_handle(zram, index, handle);
 	zram_set_obj_size(zram, index, comp_len);
 	zram_slot_unlock(zram, index);

drivers/md/dm-integrity.c

@@ -133,7 +133,7 @@ struct journal_sector {
 	commit_id_t commit_id;
 };
 
-#define MAX_TAG_SIZE			(JOURNAL_SECTOR_DATA - JOURNAL_MAC_PER_SECTOR - offsetof(struct journal_entry, last_bytes[MAX_SECTORS_PER_BLOCK]))
+#define MAX_TAG_SIZE			255
 
 #define METADATA_PADDING_SECTORS	8
 

drivers/md/dm-raid.c

@@ -3813,8 +3813,10 @@ static void raid_io_hints(struct dm_target *ti, struct queue_limits *limits)
 	struct raid_set *rs = ti->private;
 	unsigned int chunk_size_bytes = to_bytes(rs->md.chunk_sectors);
 
-	limits->io_min = chunk_size_bytes;
+	if (chunk_size_bytes) {
-	limits->io_opt = chunk_size_bytes * mddev_data_stripes(rs);
+		limits->io_min = chunk_size_bytes;
+		limits->io_opt = chunk_size_bytes * mddev_data_stripes(rs);
+	}
 }
 
 static void raid_presuspend(struct dm_target *ti)

drivers/md/dm-stripe.c

@@ -456,11 +456,15 @@ static void stripe_io_hints(struct dm_target *ti,
 			    struct queue_limits *limits)
 {
 	struct stripe_c *sc = ti->private;
-	unsigned int chunk_size = sc->chunk_size << SECTOR_SHIFT;
+	unsigned int io_min, io_opt;
 
 	limits->chunk_sectors = sc->chunk_size;
-	limits->io_min = chunk_size;
+
-	limits->io_opt = chunk_size * sc->stripes;
+	if (!check_shl_overflow(sc->chunk_size, SECTOR_SHIFT, &io_min) &&
+	    !check_mul_overflow(io_min, sc->stripes, &io_opt)) {
+		limits->io_min = io_min;
+		limits->io_opt = io_opt;
+	}
 }
 
 static struct target_type stripe_target = {

drivers/power/supply/bq27xxx_battery.c

@@ -1919,8 +1919,8 @@ static void bq27xxx_battery_update_unlocked(struct bq27xxx_device_info *di)
 	bool has_singe_flag = di->opts & BQ27XXX_O_ZERO;
 
 	cache.flags = bq27xxx_read(di, BQ27XXX_REG_FLAGS, has_singe_flag);
-	if ((cache.flags & 0xff) == 0xff)
+	if (di->chip == BQ27000 && (cache.flags & 0xff) == 0xff)
-		cache.flags = -1; /* read error */
+		cache.flags = -ENODEV; /* bq27000 hdq read error */
 	if (cache.flags >= 0) {
 		cache.capacity = bq27xxx_battery_read_soc(di);
 

fs/btrfs/block-group.c

@@ -1795,7 +1795,14 @@ static int reclaim_bgs_cmp(void *unused, const struct list_head *a,
 	bg1 = list_entry(a, struct btrfs_block_group, bg_list);
 	bg2 = list_entry(b, struct btrfs_block_group, bg_list);
 
-	return bg1->used > bg2->used;
+	/*
+	 * Some other task may be updating the ->used field concurrently, but it
+	 * is not serious if we get a stale value or load/store tearing issues,
+	 * as sorting the list of block groups to reclaim is not critical and an
+	 * occasional imperfect order is ok. So silence KCSAN and avoid the
+	 * overhead of locking or any other synchronization.
+	 */
+	return data_race(bg1->used > bg2->used);
 }
 
 static inline bool btrfs_should_reclaim(const struct btrfs_fs_info *fs_info)

fs/btrfs/delayed-inode.c

@@ -1843,7 +1843,6 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans,
 
 int btrfs_fill_inode(struct btrfs_inode *inode, u32 *rdev)
 {
-	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_delayed_node *delayed_node;
 	struct btrfs_inode_item *inode_item;
 	struct inode *vfs_inode = &inode->vfs_inode;
@@ -1864,8 +1863,6 @@ int btrfs_fill_inode(struct btrfs_inode *inode, u32 *rdev)
 	i_uid_write(vfs_inode, btrfs_stack_inode_uid(inode_item));
 	i_gid_write(vfs_inode, btrfs_stack_inode_gid(inode_item));
 	btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item));
-	btrfs_inode_set_file_extent_range(inode, 0,
-			round_up(i_size_read(vfs_inode), fs_info->sectorsize));
 	vfs_inode->i_mode = btrfs_stack_inode_mode(inode_item);
 	set_nlink(vfs_inode, btrfs_stack_inode_nlink(inode_item));
 	inode_set_bytes(vfs_inode, btrfs_stack_inode_nbytes(inode_item));

fs/btrfs/inode.c

@@ -3885,10 +3885,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path
 	bool filled = false;
 	int first_xattr_slot;
 
-	ret = btrfs_init_file_extent_tree(inode);
-	if (ret)
-		goto out;
-
 	ret = btrfs_fill_inode(inode, &rdev);
 	if (!ret)
 		filled = true;
@@ -3920,8 +3916,6 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path
 	i_uid_write(vfs_inode, btrfs_inode_uid(leaf, inode_item));
 	i_gid_write(vfs_inode, btrfs_inode_gid(leaf, inode_item));
 	btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item));
-	btrfs_inode_set_file_extent_range(inode, 0,
-			round_up(i_size_read(vfs_inode), fs_info->sectorsize));
 
 	inode_set_atime(vfs_inode, btrfs_timespec_sec(leaf, &inode_item->atime),
 			btrfs_timespec_nsec(leaf, &inode_item->atime));
@@ -3953,6 +3947,11 @@ static int btrfs_read_locked_inode(struct btrfs_inode *inode, struct btrfs_path
 	btrfs_set_inode_mapping_order(inode);
 
 cache_index:
+	ret = btrfs_init_file_extent_tree(inode);
+	if (ret)
+		goto out;
+	btrfs_inode_set_file_extent_range(inode, 0,
+			round_up(i_size_read(vfs_inode), fs_info->sectorsize));
 	/*
 	 * If we were modified in the current generation and evicted from memory
 	 * and then re-read we need to do a full sync since we don't have any

fs/btrfs/tree-log.c

@@ -1964,7 +1964,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 
 	search_key.objectid = log_key.objectid;
 	search_key.type = BTRFS_INODE_EXTREF_KEY;
-	search_key.offset = key->objectid;
+	search_key.offset = btrfs_extref_hash(key->objectid, name.name, name.len);
 	ret = backref_in_log(root->log_root, &search_key, key->objectid, &name);
 	if (ret < 0) {
 		goto out;

fs/btrfs/zoned.c

@@ -2582,9 +2582,9 @@ again:
 			spin_lock(&space_info->lock);
 			space_info->total_bytes -= bg->length;
 			space_info->disk_total -= bg->length * factor;
+			space_info->disk_total -= bg->zone_unusable;
 			/* There is no allocation ever happened. */
 			ASSERT(bg->used == 0);
-			ASSERT(bg->zone_unusable == 0);
 			/* No super block in a block group on the zoned setup. */
 			ASSERT(bg->bytes_super == 0);
 			spin_unlock(&space_info->lock);

fs/nilfs2/sysfs.c

@@ -1075,7 +1075,7 @@ void nilfs_sysfs_delete_device_group(struct the_nilfs *nilfs)
  ************************************************************************/
 
 static ssize_t nilfs_feature_revision_show(struct kobject *kobj,
-					    struct attribute *attr, char *buf)
+					    struct kobj_attribute *attr, char *buf)
 {
 	return sysfs_emit(buf, "%d.%d\n",
 			NILFS_CURRENT_REV, NILFS_MINOR_REV);
@@ -1087,7 +1087,7 @@ static const char features_readme_str[] =
 	"(1) revision\n\tshow current revision of NILFS file system driver.\n";
 
 static ssize_t nilfs_feature_README_show(struct kobject *kobj,
-					 struct attribute *attr,
+					 struct kobj_attribute *attr,
 					 char *buf)
 {
 	return sysfs_emit(buf, features_readme_str);

fs/nilfs2/sysfs.h

@@ -50,16 +50,16 @@ struct nilfs_sysfs_dev_subgroups {
 	struct completion sg_segments_kobj_unregister;
 };
 
-#define NILFS_COMMON_ATTR_STRUCT(name) \
+#define NILFS_KOBJ_ATTR_STRUCT(name) \
 struct nilfs_##name##_attr { \
 	struct attribute attr; \
-	ssize_t (*show)(struct kobject *, struct attribute *, \
+	ssize_t (*show)(struct kobject *, struct kobj_attribute *, \
 			char *); \
-	ssize_t (*store)(struct kobject *, struct attribute *, \
+	ssize_t (*store)(struct kobject *, struct kobj_attribute *, \
 			 const char *, size_t); \
 }
 
-NILFS_COMMON_ATTR_STRUCT(feature);
+NILFS_KOBJ_ATTR_STRUCT(feature);
 
 #define NILFS_DEV_ATTR_STRUCT(name) \
 struct nilfs_##name##_attr { \

fs/smb/server/transport_rdma.c

@@ -554,7 +554,7 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	case SMB_DIRECT_MSG_DATA_TRANSFER: {
 		struct smb_direct_data_transfer *data_transfer =
 			(struct smb_direct_data_transfer *)recvmsg->packet;
-		unsigned int data_length;
+		u32 remaining_data_length, data_offset, data_length;
 		int avail_recvmsg_count, receive_credits;
 
 		if (wc->byte_len <
@@ -564,15 +564,25 @@ static void recv_done(struct ib_cq *cq, struct ib_wc *wc)
 			return;
 		}
 
+		remaining_data_length = le32_to_cpu(data_transfer->remaining_data_length);
 		data_length = le32_to_cpu(data_transfer->data_length);
-		if (data_length) {
+		data_offset = le32_to_cpu(data_transfer->data_offset);
-			if (wc->byte_len < sizeof(struct smb_direct_data_transfer) +
+		if (wc->byte_len < data_offset ||
-			    (u64)data_length) {
+		    wc->byte_len < (u64)data_offset + data_length) {
-				put_recvmsg(t, recvmsg);
+			put_recvmsg(t, recvmsg);
-				smb_direct_disconnect_rdma_connection(t);
+			smb_direct_disconnect_rdma_connection(t);
-				return;
+			return;
-			}
+		}
+		if (remaining_data_length > t->max_fragmented_recv_size ||
+		    data_length > t->max_fragmented_recv_size ||
+		    (u64)remaining_data_length + (u64)data_length >
+		    (u64)t->max_fragmented_recv_size) {
+			put_recvmsg(t, recvmsg);
+			smb_direct_disconnect_rdma_connection(t);
+			return;
+		}
 
+		if (data_length) {
 			if (t->full_packet_received)
 				recvmsg->first_segment = true;
 
@@ -1209,78 +1219,130 @@ static int smb_direct_writev(struct ksmbd_transport *t,
 			     bool need_invalidate, unsigned int remote_key)
 {
 	struct smb_direct_transport *st = smb_trans_direct_transfort(t);
-	int remaining_data_length;
+	size_t remaining_data_length;
-	int start, i, j;
+	size_t iov_idx;
-	int max_iov_size = st->max_send_size -
+	size_t iov_ofs;
+	size_t max_iov_size = st->max_send_size -
 			sizeof(struct smb_direct_data_transfer);
 	int ret;
-	struct kvec vec;
 	struct smb_direct_send_ctx send_ctx;
+	int error = 0;
 
 	if (st->status != SMB_DIRECT_CS_CONNECTED)
 		return -ENOTCONN;
 
 	//FIXME: skip RFC1002 header..
+	if (WARN_ON_ONCE(niovs <= 1 || iov[0].iov_len != 4))
+		return -EINVAL;
 	buflen -= 4;
+	iov_idx = 1;
+	iov_ofs = 0;
 
 	remaining_data_length = buflen;
 	ksmbd_debug(RDMA, "Sending smb (RDMA): smb_len=%u\n", buflen);
 
 	smb_direct_send_ctx_init(st, &send_ctx, need_invalidate, remote_key);
-	start = i = 1;
+	while (remaining_data_length) {
-	buflen = 0;
+		struct kvec vecs[SMB_DIRECT_MAX_SEND_SGES - 1]; /* minus smbdirect hdr */
-	while (true) {
+		size_t possible_bytes = max_iov_size;
-		buflen += iov[i].iov_len;
+		size_t possible_vecs;
-		if (buflen > max_iov_size) {
+		size_t bytes = 0;
-			if (i > start) {
+		size_t nvecs = 0;
-				remaining_data_length -=
-					(buflen - iov[i].iov_len);
-				ret = smb_direct_post_send_data(st, &send_ctx,
-								&iov[start], i - start,
-								remaining_data_length);
-				if (ret)
-					goto done;
-			} else {
-				/* iov[start] is too big, break it */
-				int nvec  = (buflen + max_iov_size - 1) /
-						max_iov_size;
 
-				for (j = 0; j < nvec; j++) {
+		/*
-					vec.iov_base =
+		 * For the last message remaining_data_length should be
-						(char *)iov[start].iov_base +
+		 * have been 0 already!
-						j * max_iov_size;
+		 */
-					vec.iov_len =
+		if (WARN_ON_ONCE(iov_idx >= niovs)) {
-						min_t(int, max_iov_size,
+			error = -EINVAL;
-						      buflen - max_iov_size * j);
+			goto done;
-					remaining_data_length -= vec.iov_len;
+		}
-					ret = smb_direct_post_send_data(st, &send_ctx, &vec, 1,
+
-									remaining_data_length);
+		/*
-					if (ret)
+		 * We have 2 factors which limit the arguments we pass
-						goto done;
+		 * to smb_direct_post_send_data():
-				}
+		 *
-				i++;
+		 * 1. The number of supported sges for the send,
-				if (i == niovs)
+		 *    while one is reserved for the smbdirect header.
-					break;
+		 *    And we currently need one SGE per page.
-			}
+		 * 2. The number of negotiated payload bytes per send.
-			start = i;
+		 */
-			buflen = 0;
+		possible_vecs = min_t(size_t, ARRAY_SIZE(vecs), niovs - iov_idx);
-		} else {
+
-			i++;
+		while (iov_idx < niovs && possible_vecs && possible_bytes) {
-			if (i == niovs) {
+			struct kvec *v = &vecs[nvecs];
-				/* send out all remaining vecs */
+			int page_count;
-				remaining_data_length -= buflen;
+
-				ret = smb_direct_post_send_data(st, &send_ctx,
+			v->iov_base = ((u8 *)iov[iov_idx].iov_base) + iov_ofs;
-								&iov[start], i - start,
+			v->iov_len = min_t(size_t,
-								remaining_data_length);
+					   iov[iov_idx].iov_len - iov_ofs,
-				if (ret)
+					   possible_bytes);
+			page_count = get_buf_page_count(v->iov_base, v->iov_len);
+			if (page_count > possible_vecs) {
+				/*
+				 * If the number of pages in the buffer
+				 * is to much (because we currently require
+				 * one SGE per page), we need to limit the
+				 * length.
+				 *
+				 * We know possible_vecs is at least 1,
+				 * so we always keep the first page.
+				 *
+				 * We need to calculate the number extra
+				 * pages (epages) we can also keep.
+				 *
+				 * We calculate the number of bytes in the
+				 * first page (fplen), this should never be
+				 * larger than v->iov_len because page_count is
+				 * at least 2, but adding a limitation feels
+				 * better.
+				 *
+				 * Then we calculate the number of bytes (elen)
+				 * we can keep for the extra pages.
+				 */
+				size_t epages = possible_vecs - 1;
+				size_t fpofs = offset_in_page(v->iov_base);
+				size_t fplen = min_t(size_t, PAGE_SIZE - fpofs, v->iov_len);
+				size_t elen = min_t(size_t, v->iov_len - fplen, epages*PAGE_SIZE);
+
+				v->iov_len = fplen + elen;
+				page_count = get_buf_page_count(v->iov_base, v->iov_len);
+				if (WARN_ON_ONCE(page_count > possible_vecs)) {
+					/*
+					 * Something went wrong in the above
+					 * logic...
+					 */
+					error = -EINVAL;
 					goto done;
-				break;
+				}
 			}
+			possible_vecs -= page_count;
+			nvecs += 1;
+			possible_bytes -= v->iov_len;
+			bytes += v->iov_len;
+
+			iov_ofs += v->iov_len;
+			if (iov_ofs >= iov[iov_idx].iov_len) {
+				iov_idx += 1;
+				iov_ofs = 0;
+			}
+		}
+
+		remaining_data_length -= bytes;
+
+		ret = smb_direct_post_send_data(st, &send_ctx,
+						vecs, nvecs,
+						remaining_data_length);
+		if (unlikely(ret)) {
+			error = ret;
+			goto done;
 		}
 	}
 
 done:
 	ret = smb_direct_flush_send_list(st, &send_ctx, true);
+	if (unlikely(!ret && error))
+		ret = error;
 
 	/*
 	 * As an optimization, we don't wait for individual I/O to finish
@@ -1744,6 +1806,11 @@ static int smb_direct_init_params(struct smb_direct_transport *t,
 		return -EINVAL;
 	}
 
+	if (device->attrs.max_send_sge < SMB_DIRECT_MAX_SEND_SGES) {
+		pr_err("warning: device max_send_sge = %d too small\n",
+		       device->attrs.max_send_sge);
+		return -EINVAL;
+	}
 	if (device->attrs.max_recv_sge < SMB_DIRECT_MAX_RECV_SGES) {
 		pr_err("warning: device max_recv_sge = %d too small\n",
 		       device->attrs.max_recv_sge);
@@ -1767,7 +1834,7 @@ static int smb_direct_init_params(struct smb_direct_transport *t,
 
 	cap->max_send_wr = max_send_wrs;
 	cap->max_recv_wr = t->recv_credit_max;
-	cap->max_send_sge = max_sge_per_wr;
+	cap->max_send_sge = SMB_DIRECT_MAX_SEND_SGES;
 	cap->max_recv_sge = SMB_DIRECT_MAX_RECV_SGES;
 	cap->max_inline_data = 0;
 	cap->max_rdma_ctxs = t->max_rw_credits;

include/linux/damon.h

@@ -636,6 +636,7 @@ struct damon_operations {
  * @data:		Data that will be passed to @fn.
  * @repeat:		Repeat invocations.
  * @return_code:	Return code from @fn invocation.
+ * @dealloc_on_cancel:	De-allocate when canceled.
  *
  * Control damon_call(), which requests specific kdamond to invoke a given
  * function.  Refer to damon_call() for more details.
@@ -645,6 +646,7 @@ struct damon_call_control {
 	void *data;
 	bool repeat;
 	int return_code;
+	bool dealloc_on_cancel;
 /* private: internal use only */
 	/* informs if the kdamond finished handling of the request */
 	struct completion completion;

include/linux/swap.h

@@ -385,6 +385,16 @@ void folio_add_lru_vma(struct folio *, struct vm_area_struct *);
 void mark_page_accessed(struct page *);
 void folio_mark_accessed(struct folio *);
 
+static inline bool folio_may_be_lru_cached(struct folio *folio)
+{
+	/*
+	 * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting.
+	 * Holding small numbers of low-order mTHP folios in per-CPU LRU cache
+	 * will be sensible, but nobody has implemented and tested that yet.
+	 */
+	return !folio_test_large(folio);
+}
+
 extern atomic_t lru_disable_count;
 
 static inline bool lru_cache_disabled(void)

kernel/cgroup/cgroup.c

@@ -126,8 +126,31 @@ DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem);
  * of concurrent destructions.  Use a separate workqueue so that cgroup
  * destruction work items don't end up filling up max_active of system_wq
  * which may lead to deadlock.
+ *
+ * A cgroup destruction should enqueue work sequentially to:
+ * cgroup_offline_wq: use for css offline work
+ * cgroup_release_wq: use for css release work
+ * cgroup_free_wq: use for free work
+ *
+ * Rationale for using separate workqueues:
+ * The cgroup root free work may depend on completion of other css offline
+ * operations. If all tasks were enqueued to a single workqueue, this could
+ * create a deadlock scenario where:
+ * - Free work waits for other css offline work to complete.
+ * - But other css offline work is queued after free work in the same queue.
+ *
+ * Example deadlock scenario with single workqueue (cgroup_destroy_wq):
+ * 1. umount net_prio
+ * 2. net_prio root destruction enqueues work to cgroup_destroy_wq (CPUx)
+ * 3. perf_event CSS A offline enqueues work to same cgroup_destroy_wq (CPUx)
+ * 4. net_prio cgroup_destroy_root->cgroup_lock_and_drain_offline.
+ * 5. net_prio root destruction blocks waiting for perf_event CSS A offline,
+ *    which can never complete as it's behind in the same queue and
+ *    workqueue's max_active is 1.
  */
-static struct workqueue_struct *cgroup_destroy_wq;
+static struct workqueue_struct *cgroup_offline_wq;
+static struct workqueue_struct *cgroup_release_wq;
+static struct workqueue_struct *cgroup_free_wq;
 
 /* generate an array of cgroup subsystem pointers */
 #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,
@@ -4159,6 +4182,7 @@ static void cgroup_file_release(struct kernfs_open_file *of)
 		cft->release(of);
 	put_cgroup_ns(ctx->ns);
 	kfree(ctx);
+	of->priv = NULL;
 }
 
 static ssize_t cgroup_file_write(struct kernfs_open_file *of, char *buf,
@@ -5558,7 +5582,7 @@ static void css_release_work_fn(struct work_struct *work)
 	cgroup_unlock();
 
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
-	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
+	queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);
 }
 
 static void css_release(struct percpu_ref *ref)
@@ -5567,7 +5591,7 @@ static void css_release(struct percpu_ref *ref)
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
 	INIT_WORK(&css->destroy_work, css_release_work_fn);
-	queue_work(cgroup_destroy_wq, &css->destroy_work);
+	queue_work(cgroup_release_wq, &css->destroy_work);
 }
 
 static void init_and_link_css(struct cgroup_subsys_state *css,
@@ -5701,7 +5725,7 @@ err_list_del:
 	list_del_rcu(&css->sibling);
 err_free_css:
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
-	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
+	queue_rcu_work(cgroup_free_wq, &css->destroy_rwork);
 	return ERR_PTR(err);
 }
 
@@ -5939,7 +5963,7 @@ static void css_killed_ref_fn(struct percpu_ref *ref)
 
 	if (atomic_dec_and_test(&css->online_cnt)) {
 		INIT_WORK(&css->destroy_work, css_killed_work_fn);
-		queue_work(cgroup_destroy_wq, &css->destroy_work);
+		queue_work(cgroup_offline_wq, &css->destroy_work);
 	}
 }
 
@@ -6325,8 +6349,14 @@ static int __init cgroup_wq_init(void)
 	 * We would prefer to do this in cgroup_init() above, but that
 	 * is called before init_workqueues(): so leave this until after.
 	 */
-	cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
+	cgroup_offline_wq = alloc_workqueue("cgroup_offline", 0, 1);
-	BUG_ON(!cgroup_destroy_wq);
+	BUG_ON(!cgroup_offline_wq);
+
+	cgroup_release_wq = alloc_workqueue("cgroup_release", 0, 1);
+	BUG_ON(!cgroup_release_wq);
+
+	cgroup_free_wq = alloc_workqueue("cgroup_free", 0, 1);
+	BUG_ON(!cgroup_free_wq);
 	return 0;
 }
 core_initcall(cgroup_wq_init);

kernel/sched/core.c

@@ -9551,7 +9551,7 @@ static unsigned long tg_weight(struct task_group *tg)
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	return scale_load_down(tg->shares);
 #else
-	return sched_weight_from_cgroup(tg->scx_weight);
+	return sched_weight_from_cgroup(tg->scx.weight);
 #endif
 }
 

kernel/sched/ext.c

@@ -6788,12 +6788,8 @@ __bpf_kfunc u32 scx_bpf_reenqueue_local(void)
 		 * CPUs disagree, they use %ENQUEUE_RESTORE which is bypassed to
 		 * the current local DSQ for running tasks and thus are not
 		 * visible to the BPF scheduler.
-		 *
-		 * Also skip re-enqueueing tasks that can only run on this
-		 * CPU, as they would just be re-added to the same local
-		 * DSQ without any benefit.
 		 */
-		if (p->migration_pending || is_migration_disabled(p) || p->nr_cpus_allowed == 1)
+		if (p->migration_pending)
 			continue;
 
 		dispatch_dequeue(rq, p);

kernel/trace/trace_kprobe.c

@@ -908,6 +908,8 @@ static int trace_kprobe_create_internal(int argc, const char *argv[],
 			return -EINVAL;
 		}
 		buf = kmemdup(&argv[0][1], len + 1, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
 		buf[len] = '\0';
 		ret = kstrtouint(buf, 0, &maxactive);
 		if (ret || !maxactive) {

mm/damon/core.c

@@ -2479,10 +2479,14 @@ static void kdamond_call(struct damon_ctx *ctx, bool cancel)
 		mutex_lock(&ctx->call_controls_lock);
 		list_del(&control->list);
 		mutex_unlock(&ctx->call_controls_lock);
-		if (!control->repeat)
+		if (!control->repeat) {
 			complete(&control->completion);
-		else
+		} else if (control->canceled && control->dealloc_on_cancel) {
+			kfree(control);
+			continue;
+		} else {
 			list_add(&control->list, &repeat_controls);
+		}
 	}
 	control = list_first_entry_or_null(&repeat_controls,
 			struct damon_call_control, list);

mm/damon/sysfs.c

@@ -1534,14 +1534,10 @@ static int damon_sysfs_repeat_call_fn(void *data)
 	return 0;
 }
 
-static struct damon_call_control damon_sysfs_repeat_call_control = {
-	.fn = damon_sysfs_repeat_call_fn,
-	.repeat = true,
-};
-
 static int damon_sysfs_turn_damon_on(struct damon_sysfs_kdamond *kdamond)
 {
 	struct damon_ctx *ctx;
+	struct damon_call_control *repeat_call_control;
 	int err;
 
 	if (damon_sysfs_kdamond_running(kdamond))
@@ -1554,18 +1550,29 @@ static int damon_sysfs_turn_damon_on(struct damon_sysfs_kdamond *kdamond)
 		damon_destroy_ctx(kdamond->damon_ctx);
 	kdamond->damon_ctx = NULL;
 
+	repeat_call_control = kmalloc(sizeof(*repeat_call_control),
+			GFP_KERNEL);
+	if (!repeat_call_control)
+		return -ENOMEM;
+
 	ctx = damon_sysfs_build_ctx(kdamond->contexts->contexts_arr[0]);
-	if (IS_ERR(ctx))
+	if (IS_ERR(ctx)) {
+		kfree(repeat_call_control);
 		return PTR_ERR(ctx);
+	}
 	err = damon_start(&ctx, 1, false);
 	if (err) {
+		kfree(repeat_call_control);
 		damon_destroy_ctx(ctx);
 		return err;
 	}
 	kdamond->damon_ctx = ctx;
 
-	damon_sysfs_repeat_call_control.data = kdamond;
+	repeat_call_control->fn = damon_sysfs_repeat_call_fn;
-	damon_call(ctx, &damon_sysfs_repeat_call_control);
+	repeat_call_control->data = kdamond;
+	repeat_call_control->repeat = true;
+	repeat_call_control->dealloc_on_cancel = true;
+	damon_call(ctx, repeat_call_control);
 	return err;
 }
 

mm/gup.c

@@ -2287,8 +2287,8 @@ static unsigned long collect_longterm_unpinnable_folios(
 		struct pages_or_folios *pofs)
 {
 	unsigned long collected = 0;
-	bool drain_allow = true;
 	struct folio *folio;
+	int drained = 0;
 	long i = 0;
 
 	for (folio = pofs_get_folio(pofs, i); folio;
@@ -2307,9 +2307,17 @@ static unsigned long collect_longterm_unpinnable_folios(
 			continue;
 		}
 
-		if (!folio_test_lru(folio) && drain_allow) {
+		if (drained == 0 && folio_may_be_lru_cached(folio) &&
+				folio_ref_count(folio) !=
+				folio_expected_ref_count(folio) + 1) {
+			lru_add_drain();
+			drained = 1;
+		}
+		if (drained == 1 && folio_may_be_lru_cached(folio) &&
+				folio_ref_count(folio) !=
+				folio_expected_ref_count(folio) + 1) {
 			lru_add_drain_all();
-			drain_allow = false;
+			drained = 2;
 		}
 
 		if (!folio_isolate_lru(folio))

mm/mlock.c

@@ -255,7 +255,7 @@ void mlock_folio(struct folio *folio)
 
 	folio_get(folio);
 	if (!folio_batch_add(fbatch, mlock_lru(folio)) ||
-	    folio_test_large(folio) || lru_cache_disabled())
+	    !folio_may_be_lru_cached(folio) || lru_cache_disabled())
 		mlock_folio_batch(fbatch);
 	local_unlock(&mlock_fbatch.lock);
 }
@@ -278,7 +278,7 @@ void mlock_new_folio(struct folio *folio)
 
 	folio_get(folio);
 	if (!folio_batch_add(fbatch, mlock_new(folio)) ||
-	    folio_test_large(folio) || lru_cache_disabled())
+	    !folio_may_be_lru_cached(folio) || lru_cache_disabled())
 		mlock_folio_batch(fbatch);
 	local_unlock(&mlock_fbatch.lock);
 }
@@ -299,7 +299,7 @@ void munlock_folio(struct folio *folio)
 	 */
 	folio_get(folio);
 	if (!folio_batch_add(fbatch, folio) ||
-	    folio_test_large(folio) || lru_cache_disabled())
+	    !folio_may_be_lru_cached(folio) || lru_cache_disabled())
 		mlock_folio_batch(fbatch);
 	local_unlock(&mlock_fbatch.lock);
 }

mm/swap.c

@@ -164,6 +164,10 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn)
 	for (i = 0; i < folio_batch_count(fbatch); i++) {
 		struct folio *folio = fbatch->folios[i];
 
+		/* block memcg migration while the folio moves between lru */
+		if (move_fn != lru_add && !folio_test_clear_lru(folio))
+			continue;
+
 		folio_lruvec_relock_irqsave(folio, &lruvec, &flags);
 		move_fn(lruvec, folio);
 
@@ -176,14 +180,10 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn)
 }
 
 static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch,
-		struct folio *folio, move_fn_t move_fn,
+		struct folio *folio, move_fn_t move_fn, bool disable_irq)
-		bool on_lru, bool disable_irq)
 {
 	unsigned long flags;
 
-	if (on_lru && !folio_test_clear_lru(folio))
-		return;
-
 	folio_get(folio);
 
 	if (disable_irq)
@@ -191,8 +191,8 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch,
 	else
 		local_lock(&cpu_fbatches.lock);
 
-	if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || folio_test_large(folio) ||
+	if (!folio_batch_add(this_cpu_ptr(fbatch), folio) ||
-	    lru_cache_disabled())
+			!folio_may_be_lru_cached(folio) || lru_cache_disabled())
 		folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn);
 
 	if (disable_irq)
@@ -201,13 +201,13 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch,
 		local_unlock(&cpu_fbatches.lock);
 }
 
-#define folio_batch_add_and_move(folio, op, on_lru)						\
+#define folio_batch_add_and_move(folio, op)		\
-	__folio_batch_add_and_move(								\
+	__folio_batch_add_and_move(			\
-		&cpu_fbatches.op,								\
+		&cpu_fbatches.op,			\
-		folio,										\
+		folio,					\
-		op,										\
+		op,					\
-		on_lru,										\
+		offsetof(struct cpu_fbatches, op) >=	\
-		offsetof(struct cpu_fbatches, op) >= offsetof(struct cpu_fbatches, lock_irq)	\
+		offsetof(struct cpu_fbatches, lock_irq)	\
 	)
 
 static void lru_move_tail(struct lruvec *lruvec, struct folio *folio)
@@ -231,10 +231,10 @@ static void lru_move_tail(struct lruvec *lruvec, struct folio *folio)
 void folio_rotate_reclaimable(struct folio *folio)
 {
 	if (folio_test_locked(folio) || folio_test_dirty(folio) ||
-	    folio_test_unevictable(folio))
+	    folio_test_unevictable(folio) || !folio_test_lru(folio))
 		return;
 
-	folio_batch_add_and_move(folio, lru_move_tail, true);
+	folio_batch_add_and_move(folio, lru_move_tail);
 }
 
 void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file,
@@ -328,10 +328,11 @@ static void folio_activate_drain(int cpu)
 
 void folio_activate(struct folio *folio)
 {
-	if (folio_test_active(folio) || folio_test_unevictable(folio))
+	if (folio_test_active(folio) || folio_test_unevictable(folio) ||
+	    !folio_test_lru(folio))
 		return;
 
-	folio_batch_add_and_move(folio, lru_activate, true);
+	folio_batch_add_and_move(folio, lru_activate);
 }
 
 #else
@@ -507,7 +508,7 @@ void folio_add_lru(struct folio *folio)
 	    lru_gen_in_fault() && !(current->flags & PF_MEMALLOC))
 		folio_set_active(folio);
 
-	folio_batch_add_and_move(folio, lru_add, false);
+	folio_batch_add_and_move(folio, lru_add);
 }
 EXPORT_SYMBOL(folio_add_lru);
 
@@ -685,13 +686,13 @@ void lru_add_drain_cpu(int cpu)
 void deactivate_file_folio(struct folio *folio)
 {
 	/* Deactivating an unevictable folio will not accelerate reclaim */
-	if (folio_test_unevictable(folio))
+	if (folio_test_unevictable(folio) || !folio_test_lru(folio))
 		return;
 
 	if (lru_gen_enabled() && lru_gen_clear_refs(folio))
 		return;
 
-	folio_batch_add_and_move(folio, lru_deactivate_file, true);
+	folio_batch_add_and_move(folio, lru_deactivate_file);
 }
 
 /*
@@ -704,13 +705,13 @@ void deactivate_file_folio(struct folio *folio)
  */
 void folio_deactivate(struct folio *folio)
 {
-	if (folio_test_unevictable(folio))
+	if (folio_test_unevictable(folio) || !folio_test_lru(folio))
 		return;
 
 	if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio))
 		return;
 
-	folio_batch_add_and_move(folio, lru_deactivate, true);
+	folio_batch_add_and_move(folio, lru_deactivate);
 }
 
 /**
@@ -723,10 +724,11 @@ void folio_deactivate(struct folio *folio)
 void folio_mark_lazyfree(struct folio *folio)
 {
 	if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) ||
+	    !folio_test_lru(folio) ||
 	    folio_test_swapcache(folio) || folio_test_unevictable(folio))
 		return;
 
-	folio_batch_add_and_move(folio, lru_lazyfree, true);
+	folio_batch_add_and_move(folio, lru_lazyfree);
 }
 
 void lru_add_drain(void)

mm/vmscan.c

@@ -4507,7 +4507,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	}
 
 	/* ineligible */
-	if (!folio_test_lru(folio) || zone > sc->reclaim_idx) {
+	if (zone > sc->reclaim_idx) {
 		gen = folio_inc_gen(lruvec, folio, false);
 		list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
 		return true;

samples/damon/mtier.c

@@ -208,6 +208,9 @@ static int damon_sample_mtier_enable_store(
 	if (enabled == is_enabled)
 		return 0;
 
+	if (!init_called)
+		return 0;
+
 	if (enabled) {
 		err = damon_sample_mtier_start();
 		if (err)

samples/damon/prcl.c

@@ -137,6 +137,9 @@ static int damon_sample_prcl_enable_store(
 	if (enabled == is_enabled)
 		return 0;
 
+	if (!init_called)
+		return 0;
+
 	if (enabled) {
 		err = damon_sample_prcl_start();
 		if (err)

samples/damon/wsse.c

@@ -118,6 +118,9 @@ static int damon_sample_wsse_enable_store(
 		return 0;
 
 	if (enabled) {
+		if (!init_called)
+			return 0;
+
 		err = damon_sample_wsse_start();
 		if (err)
 			enabled = false;

tools/lib/subcmd/help.c

@@ -75,6 +75,9 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes)
 	size_t ci, cj, ei;
 	int cmp;
 
+	if (!excludes->cnt)
+		return;
+
 	ci = cj = ei = 0;
 	while (ci < cmds->cnt && ei < excludes->cnt) {
 		cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name);

tools/perf/builtin-lock.c

@@ -2009,6 +2009,7 @@ static int __cmd_contention(int argc, const char **argv)
 		.owner = show_lock_owner,
 		.cgroups = RB_ROOT,
 	};
+	struct perf_env host_env;
 
 	lockhash_table = calloc(LOCKHASH_SIZE, sizeof(*lockhash_table));
 	if (!lockhash_table)
@@ -2024,7 +2025,10 @@ static int __cmd_contention(int argc, const char **argv)
 	eops.mmap		 = perf_event__process_mmap;
 	eops.tracing_data	 = perf_event__process_tracing_data;
 
-	session = perf_session__new(use_bpf ? NULL : &data, &eops);
+	perf_env__init(&host_env);
+	session = __perf_session__new(use_bpf ? NULL : &data, &eops,
+				/*trace_event_repipe=*/false, &host_env);
+
 	if (IS_ERR(session)) {
 		pr_err("Initializing perf session failed\n");
 		err = PTR_ERR(session);
@@ -2142,6 +2146,7 @@ out_delete:
 	evlist__delete(con.evlist);
 	lock_contention_finish(&con);
 	perf_session__delete(session);
+	perf_env__exit(&host_env);
 	zfree(&lockhash_table);
 	return err;
 }

tools/perf/util/maps.c

@@ -477,6 +477,7 @@ static int __maps__insert(struct maps *maps, struct map *new)
 	}
 	/* Insert the value at the end. */
 	maps_by_address[nr_maps] = map__get(new);
+	map__set_kmap_maps(new, maps);
 	if (maps_by_name)
 		maps_by_name[nr_maps] = map__get(new);
 
@@ -502,8 +503,6 @@ static int __maps__insert(struct maps *maps, struct map *new)
 	if (map__end(new) < map__start(new))
 		RC_CHK_ACCESS(maps)->ends_broken = true;
 
-	map__set_kmap_maps(new, maps);
-
 	return 0;
 }
 
@@ -891,6 +890,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new)
 		if (before) {
 			map__put(maps_by_address[i]);
 			maps_by_address[i] = before;
+			map__set_kmap_maps(before, maps);
 
 			if (maps_by_name) {
 				map__put(maps_by_name[ni]);
@@ -918,6 +918,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new)
 			 */
 			map__put(maps_by_address[i]);
 			maps_by_address[i] = map__get(new);
+			map__set_kmap_maps(new, maps);
 
 			if (maps_by_name) {
 				map__put(maps_by_name[ni]);
@@ -942,14 +943,13 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new)
 				 */
 				map__put(maps_by_address[i]);
 				maps_by_address[i] = map__get(new);
+				map__set_kmap_maps(new, maps);
 
 				if (maps_by_name) {
 					map__put(maps_by_name[ni]);
 					maps_by_name[ni] = map__get(new);
 				}
 
-				map__set_kmap_maps(new, maps);
-
 				check_invariants(maps);
 				return err;
 			}
@@ -1019,6 +1019,7 @@ int maps__copy_from(struct maps *dest, struct maps *parent)
 				err = unwind__prepare_access(dest, new, NULL);
 				if (!err) {
 					dest_maps_by_address[i] = new;
+					map__set_kmap_maps(new, dest);
 					if (dest_maps_by_name)
 						dest_maps_by_name[i] = map__get(new);
 					RC_CHK_ACCESS(dest)->nr_maps = i + 1;