Merge tag 'mm-hotfixes-stable-2023-06-20-12-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

torvalds · torvalds · commit 8ba90f5cc717 · 2023-06-20T17:20:22.000-07:00
Pull hotfixes from Andrew Morton: "19 hotfixes. 8 of these are cc:stable. This includes a wholesale reversion of the post-6.4 series 'make slab shrink lockless'. After input from Dave Chinner it has been decided that we should go a different way [1]" Link: https://lkml.kernel.org/r/ZH6K0McWBeCjaf16@dread.disaster.area [1] * tag 'mm-hotfixes-stable-2023-06-20-12-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: selftests/mm: fix cross compilation with LLVM mailmap: add entries for Ben Dooks nilfs2: prevent general protection fault in nilfs_clear_dirty_page() Revert "mm: vmscan: make global slab shrink lockless" Revert "mm: vmscan: make memcg slab shrink lockless" Revert "mm: vmscan: add shrinker_srcu_generation" Revert "mm: shrinkers: make count and scan in shrinker debugfs lockless" Revert "mm: vmscan: hold write lock to reparent shrinker nr_deferred" Revert "mm: vmscan: remove shrinker_rwsem from synchronize_shrinkers()" Revert "mm: shrinkers: convert shrinker_rwsem to mutex" nilfs2: fix buffer corruption due to concurrent device reads scripts/gdb: fix SB_* constants parsing scripts: fix the gfp flags header path in gfp-translate udmabuf: revert 'Add support for mapping hugepages (v4)' mm/khugepaged: fix iteration in collapse_file memfd: check for non-NULL file_seals in memfd_create() syscall mm/vmalloc: do not output a spurious warning when huge vmalloc() fails mm/mprotect: fix do_mprotect_pkey() limit check writeback: fix dereferencing NULL mapping->host on writeback_page_template
diff --git a/.mailmap b/.mailmap
@@ -70,6 +70,8 @@ Baolin Wang <baolin.wang@linux.alibaba.com> <baolin.wang@unisoc.com>
 Baolin Wang <baolin.wang@linux.alibaba.com> <baolin.wang7@gmail.com>
 Bart Van Assche <bvanassche@acm.org> <bart.vanassche@sandisk.com>
 Bart Van Assche <bvanassche@acm.org> <bart.vanassche@wdc.com>
+Ben Dooks <ben-linux@fluff.org> <ben.dooks@simtec.co.uk>
+Ben Dooks <ben-linux@fluff.org> <ben.dooks@sifive.com>
 Ben Gardner <bgardner@wabtec.com>
 Ben M Cahill <ben.m.cahill@intel.com>
 Ben Widawsky <bwidawsk@kernel.org> <ben@bwidawsk.net>
diff --git a/drivers/dma-buf/udmabuf.c b/drivers/dma-buf/udmabuf.c
@@ -12,7 +12,6 @@
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/udmabuf.h>
-#include <linux/hugetlb.h>
 #include <linux/vmalloc.h>
 #include <linux/iosys-map.h>
 
@@ -207,9 +206,7 @@ static long udmabuf_create(struct miscdevice *device,
 	struct udmabuf *ubuf;
 	struct dma_buf *buf;
 	pgoff_t pgoff, pgcnt, pgidx, pgbuf = 0, pglimit;
-	struct page *page, *hpage = NULL;
-	pgoff_t subpgoff, maxsubpgs;
-	struct hstate *hpstate;
+	struct page *page;
 	int seals, ret = -EINVAL;
 	u32 i, flags;
 
@@ -245,7 +242,7 @@ static long udmabuf_create(struct miscdevice *device,
 		if (!memfd)
 			goto err;
 		mapping = memfd->f_mapping;
-		if (!shmem_mapping(mapping) && !is_file_hugepages(memfd))
+		if (!shmem_mapping(mapping))
 			goto err;
 		seals = memfd_fcntl(memfd, F_GET_SEALS, 0);
 		if (seals == -EINVAL)
@@ -256,48 +253,16 @@ static long udmabuf_create(struct miscdevice *device,
 			goto err;
 		pgoff = list[i].offset >> PAGE_SHIFT;
 		pgcnt = list[i].size   >> PAGE_SHIFT;
-		if (is_file_hugepages(memfd)) {
-			hpstate = hstate_file(memfd);
-			pgoff = list[i].offset >> huge_page_shift(hpstate);
-			subpgoff = (list[i].offset &
-				    ~huge_page_mask(hpstate)) >> PAGE_SHIFT;
-			maxsubpgs = huge_page_size(hpstate) >> PAGE_SHIFT;
-		}
 		for (pgidx = 0; pgidx < pgcnt; pgidx++) {
-			if (is_file_hugepages(memfd)) {
-				if (!hpage) {
-					hpage = find_get_page_flags(mapping, pgoff,
-								    FGP_ACCESSED);
-					if (!hpage) {
-						ret = -EINVAL;
-						goto err;
-					}
-				}
-				page = hpage + subpgoff;
-				get_page(page);
-				subpgoff++;
-				if (subpgoff == maxsubpgs) {
-					put_page(hpage);
-					hpage = NULL;
-					subpgoff = 0;
-					pgoff++;
-				}
-			} else {
-				page = shmem_read_mapping_page(mapping,
-							       pgoff + pgidx);
-				if (IS_ERR(page)) {
-					ret = PTR_ERR(page);
-					goto err;
-				}
+			page = shmem_read_mapping_page(mapping, pgoff + pgidx);
+			if (IS_ERR(page)) {
+				ret = PTR_ERR(page);
+				goto err;
 			}
 			ubuf->pages[pgbuf++] = page;
 		}
 		fput(memfd);
 		memfd = NULL;
-		if (hpage) {
-			put_page(hpage);
-			hpage = NULL;
-		}
 	}
 
 	exp_info.ops  = &udmabuf_ops;
diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c
@@ -1828,7 +1828,7 @@ int dm_cache_metadata_abort(struct dm_cache_metadata *cmd)
 	 * Replacement block manager (new_bm) is created and old_bm destroyed outside of
 	 * cmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of
 	 * shrinker associated with the block manager's bufio client vs cmd root_lock).
-	 * - must take shrinker_mutex without holding cmd->root_lock
+	 * - must take shrinker_rwsem without holding cmd->root_lock
 	 */
 	new_bm = dm_block_manager_create(cmd->bdev, DM_CACHE_METADATA_BLOCK_SIZE << SECTOR_SHIFT,
 					 CACHE_MAX_CONCURRENT_LOCKS);
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
@@ -1891,7 +1891,7 @@ int dm_pool_abort_metadata(struct dm_pool_metadata *pmd)
 	 * Replacement block manager (new_bm) is created and old_bm destroyed outside of
 	 * pmd root_lock to avoid ABBA deadlock that would result (due to life-cycle of
 	 * shrinker associated with the block manager's bufio client vs pmd root_lock).
-	 * - must take shrinker_mutex without holding pmd->root_lock
+	 * - must take shrinker_rwsem without holding pmd->root_lock
 	 */
 	new_bm = dm_block_manager_create(pmd->bdev, THIN_METADATA_BLOCK_SIZE << SECTOR_SHIFT,
 					 THIN_MAX_CONCURRENT_LOCKS);
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
@@ -370,7 +370,15 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
 			struct folio *folio = fbatch.folios[i];
 
 			folio_lock(folio);
-			nilfs_clear_dirty_page(&folio->page, silent);
+
+			/*
+			 * This folio may have been removed from the address
+			 * space by truncation or invalidation when the lock
+			 * was acquired.  Skip processing in that case.
+			 */
+			if (likely(folio->mapping == mapping))
+				nilfs_clear_dirty_page(&folio->page, silent);
+
 			folio_unlock(folio);
 		}
 		folio_batch_release(&fbatch);
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
@@ -101,6 +101,12 @@ int nilfs_segbuf_extend_segsum(struct nilfs_segment_buffer *segbuf)
 	if (unlikely(!bh))
 		return -ENOMEM;
 
+	lock_buffer(bh);
+	if (!buffer_uptodate(bh)) {
+		memset(bh->b_data, 0, bh->b_size);
+		set_buffer_uptodate(bh);
+	}
+	unlock_buffer(bh);
 	nilfs_segbuf_add_segsum_buffer(segbuf, bh);
 	return 0;
 }
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
@@ -981,10 +981,13 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci,
 	unsigned int isz, srsz;
 
 	bh_sr = NILFS_LAST_SEGBUF(&sci->sc_segbufs)->sb_super_root;
+
+	lock_buffer(bh_sr);
 	raw_sr = (struct nilfs_super_root *)bh_sr->b_data;
 	isz = nilfs->ns_inode_size;
 	srsz = NILFS_SR_BYTES(isz);
 
+	raw_sr->sr_sum = 0;  /* Ensure initialization within this update */
 	raw_sr->sr_bytes = cpu_to_le16(srsz);
 	raw_sr->sr_nongc_ctime
 		= cpu_to_le64(nilfs_doing_gc() ?
@@ -998,6 +1001,8 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci,
 	nilfs_write_inode_common(nilfs->ns_sufile, (void *)raw_sr +
 				 NILFS_SR_SUFILE_OFFSET(isz), 1);
 	memset((void *)raw_sr + srsz, 0, nilfs->ns_blocksize - srsz);
+	set_buffer_uptodate(bh_sr);
+	unlock_buffer(bh_sr);
 }
 
 static void nilfs_redirty_inodes(struct list_head *head)
@@ -1780,6 +1785,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 	list_for_each_entry(segbuf, logs, sb_list) {
 		list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
 				    b_assoc_buffers) {
+			clear_buffer_uptodate(bh);
 			if (bh->b_page != bd_page) {
 				if (bd_page)
 					end_page_writeback(bd_page);
@@ -1791,6 +1797,7 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
 				    b_assoc_buffers) {
 			clear_buffer_async_write(bh);
 			if (bh == segbuf->sb_super_root) {
+				clear_buffer_uptodate(bh);
 				if (bh->b_page != bd_page) {
 					end_page_writeback(bd_page);
 					bd_page = bh->b_page;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
@@ -372,10 +372,31 @@ static int nilfs_move_2nd_super(struct super_block *sb, loff_t sb2off)
 		goto out;
 	}
 	nsbp = (void *)nsbh->b_data + offset;
-	memset(nsbp, 0, nilfs->ns_blocksize);
 
+	lock_buffer(nsbh);
 	if (sb2i >= 0) {
+		/*
+		 * The position of the second superblock only changes by 4KiB,
+		 * which is larger than the maximum superblock data size
+		 * (= 1KiB), so there is no need to use memmove() to allow
+		 * overlap between source and destination.
+		 */
 		memcpy(nsbp, nilfs->ns_sbp[sb2i], nilfs->ns_sbsize);
+
+		/*
+		 * Zero fill after copy to avoid overwriting in case of move
+		 * within the same block.
+		 */
+		memset(nsbh->b_data, 0, offset);
+		memset((void *)nsbp + nilfs->ns_sbsize, 0,
+		       nsbh->b_size - offset - nilfs->ns_sbsize);
+	} else {
+		memset(nsbh->b_data, 0, nsbh->b_size);
+	}
+	set_buffer_uptodate(nsbh);
+	unlock_buffer(nsbh);
+
+	if (sb2i >= 0) {
 		brelse(nilfs->ns_sbh[sb2i]);
 		nilfs->ns_sbh[sb2i] = nsbh;
 		nilfs->ns_sbp[sb2i] = nsbp;
diff --git a/fs/super.c b/fs/super.c
@@ -54,7 +54,7 @@ static char *sb_writers_name[SB_FREEZE_LEVELS] = {
  * One thing we have to be careful of with a per-sb shrinker is that we don't
  * drop the last active reference to the superblock from within the shrinker.
  * If that happens we could trigger unregistering the shrinker from within the
- * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we
+ * shrinker path and that leads to deadlock on the shrinker_rwsem. Hence we
  * take a passive reference to the superblock to avoid this from occurring.
  */
 static unsigned long super_cache_scan(struct shrinker *shrink,
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
@@ -68,7 +68,7 @@ DECLARE_EVENT_CLASS(writeback_folio_template,
 		strscpy_pad(__entry->name,
 			    bdi_dev_name(mapping ? inode_to_bdi(mapping->host) :
 					 NULL), 32);
-		__entry->ino = mapping ? mapping->host->i_ino : 0;
+		__entry->ino = (mapping && mapping->host) ? mapping->host->i_ino : 0;
 		__entry->index = folio->index;
 	),
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
@@ -2070,7 +2070,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
 					TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH);
 
 		xas_lock_irq(&xas);
-		xas_set(&xas, index);
 
 		VM_BUG_ON_PAGE(page != xas_load(&xas), page);
 
diff --git a/mm/memfd.c b/mm/memfd.c
@@ -371,12 +371,15 @@ SYSCALL_DEFINE2(memfd_create,
 
 		inode->i_mode &= ~0111;
 		file_seals = memfd_file_seals_ptr(file);
-		*file_seals &= ~F_SEAL_SEAL;
-		*file_seals |= F_SEAL_EXEC;
+		if (file_seals) {
+			*file_seals &= ~F_SEAL_SEAL;
+			*file_seals |= F_SEAL_EXEC;
+		}
 	} else if (flags & MFD_ALLOW_SEALING) {
 		/* MFD_EXEC and MFD_ALLOW_SEALING are set */
 		file_seals = memfd_file_seals_ptr(file);
-		*file_seals &= ~F_SEAL_SEAL;
+		if (file_seals)
+			*file_seals &= ~F_SEAL_SEAL;
 	}
 
 	fd_install(fd, file);
diff --git a/mm/mprotect.c b/mm/mprotect.c
@@ -867,7 +867,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	}
 	tlb_finish_mmu(&tlb);
 
-	if (!error && vma_iter_end(&vmi) < end)
+	if (!error && tmp < end)
 		error = -ENOMEM;
 
 out:
diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c
@@ -5,12 +5,10 @@
 #include <linux/seq_file.h>
 #include <linux/shrinker.h>
 #include <linux/memcontrol.h>
-#include <linux/srcu.h>
 
 /* defined in vmscan.c */
-extern struct mutex shrinker_mutex;
+extern struct rw_semaphore shrinker_rwsem;
 extern struct list_head shrinker_list;
-extern struct srcu_struct shrinker_srcu;
 
 static DEFINE_IDA(shrinker_debugfs_ida);
 static struct dentry *shrinker_debugfs_root;
@@ -51,13 +49,18 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v)
 	struct mem_cgroup *memcg;
 	unsigned long total;
 	bool memcg_aware;
-	int ret = 0, nid, srcu_idx;
+	int ret, nid;
 
 	count_per_node = kcalloc(nr_node_ids, sizeof(unsigned long), GFP_KERNEL);
 	if (!count_per_node)
 		return -ENOMEM;
 
-	srcu_idx = srcu_read_lock(&shrinker_srcu);
+	ret = down_read_killable(&shrinker_rwsem);
+	if (ret) {
+		kfree(count_per_node);
+		return ret;
+	}
+	rcu_read_lock();
 
 	memcg_aware = shrinker->flags & SHRINKER_MEMCG_AWARE;
 
@@ -88,7 +91,8 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v)
 		}
 	} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
 
-	srcu_read_unlock(&shrinker_srcu, srcu_idx);
+	rcu_read_unlock();
+	up_read(&shrinker_rwsem);
 
 	kfree(count_per_node);
 	return ret;
@@ -111,8 +115,9 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file,
 		.gfp_mask = GFP_KERNEL,
 	};
 	struct mem_cgroup *memcg = NULL;
-	int nid, srcu_idx;
+	int nid;
 	char kbuf[72];
+	ssize_t ret;
 
 	read_len = size < (sizeof(kbuf) - 1) ? size : (sizeof(kbuf) - 1);
 	if (copy_from_user(kbuf, buf, read_len))
@@ -141,7 +146,11 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file,
 		return -EINVAL;
 	}
 
-	srcu_idx = srcu_read_lock(&shrinker_srcu);
+	ret = down_read_killable(&shrinker_rwsem);
+	if (ret) {
+		mem_cgroup_put(memcg);
+		return ret;
+	}
 
 	sc.nid = nid;
 	sc.memcg = memcg;
@@ -150,7 +159,7 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file,
 
 	shrinker->scan_objects(shrinker, &sc);
 
-	srcu_read_unlock(&shrinker_srcu, srcu_idx);
+	up_read(&shrinker_rwsem);
 	mem_cgroup_put(memcg);
 
 	return size;
@@ -168,7 +177,7 @@ int shrinker_debugfs_add(struct shrinker *shrinker)
 	char buf[128];
 	int id;
 
-	lockdep_assert_held(&shrinker_mutex);
+	lockdep_assert_held(&shrinker_rwsem);
 
 	/* debugfs isn't initialized yet, add debugfs entries later. */
 	if (!shrinker_debugfs_root)
@@ -211,7 +220,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...)
 	if (!new)
 		return -ENOMEM;
 
-	mutex_lock(&shrinker_mutex);
+	down_write(&shrinker_rwsem);
 
 	old = shrinker->name;
 	shrinker->name = new;
@@ -229,7 +238,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...)
 			shrinker->debugfs_entry = entry;
 	}
 
-	mutex_unlock(&shrinker_mutex);
+	up_write(&shrinker_rwsem);
 
 	kfree_const(old);
 
@@ -242,7 +251,7 @@ struct dentry *shrinker_debugfs_detach(struct shrinker *shrinker,
 {
 	struct dentry *entry = shrinker->debugfs_entry;
 
-	lockdep_assert_held(&shrinker_mutex);
+	lockdep_assert_held(&shrinker_rwsem);
 
 	kfree_const(shrinker->name);
 	shrinker->name = NULL;
@@ -271,14 +280,14 @@ static int __init shrinker_debugfs_init(void)
 	shrinker_debugfs_root = dentry;
 
 	/* Create debugfs entries for shrinkers registered at boot */
-	mutex_lock(&shrinker_mutex);
+	down_write(&shrinker_rwsem);
 	list_for_each_entry(shrinker, &shrinker_list, list)
 		if (!shrinker->debugfs_entry) {
 			ret = shrinker_debugfs_add(shrinker);
 			if (ret)
 				break;
 		}
-	mutex_unlock(&shrinker_mutex);
+	up_write(&shrinker_rwsem);
 
 	return ret;
 }
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
diff --git a/mm/vmscan.c b/mm/vmscan.c
diff --git a/scripts/gdb/linux/constants.py.in b/scripts/gdb/linux/constants.py.in
diff --git a/scripts/gfp-translate b/scripts/gfp-translate
diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
