Merge tag 'mm-hotfixes-stable-2024-09-19-00-31' of git://git.kernel.o…

…rg/pub/scm/linux/kernel/git/akpm/mm

Pull misc hotfixes from Andrew Morton:
 "12 hotfixes, 11 of which are cc:stable.

  Four fixes for longstanding ocfs2 issues and the remainder address
  random MM things"

* tag 'mm-hotfixes-stable-2024-09-19-00-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  mm/madvise: process_madvise() drop capability check if same mm
  mm/huge_memory: ensure huge_zero_folio won't have large_rmappable flag set
  mm/hugetlb.c: fix UAF of vma in hugetlb fault pathway
  mm: change vmf_anon_prepare() to __vmf_anon_prepare()
  resource: fix region_intersects() vs add_memory_driver_managed()
  zsmalloc: use unique zsmalloc caches names
  mm/damon/vaddr: protect vma traversal in __damon_va_thre_regions() with rcu read lock
  mm: vmscan.c: fix OOM on swap stress test
  ocfs2: cancel dqi_sync_work before freeing oinfo
  ocfs2: fix possible null-ptr-deref in ocfs2_set_buffer_uptodate
  ocfs2: remove unreasonable unlock in ocfs2_read_blocks
  ocfs2: fix null-ptr-deref when journal load failed.

fs/ocfs2/buffer_head_io.c

@@ -235,7 +235,6 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 		if (bhs[i] == NULL) {
 			bhs[i] = sb_getblk(sb, block++);
 			if (bhs[i] == NULL) {
-				ocfs2_metadata_cache_io_unlock(ci);
 				status = -ENOMEM;
 				mlog_errno(status);
 				/* Don't forget to put previous bh! */
@@ -389,7 +388,8 @@ int ocfs2_read_blocks(struct ocfs2_caching_info *ci, u64 block, int nr,
 		/* Always set the buffer in the cache, even if it was
 		 * a forced read, or read-ahead which hasn't yet
 		 * completed. */
-		ocfs2_set_buffer_uptodate(ci, bh);
+		if (bh)
+			ocfs2_set_buffer_uptodate(ci, bh);
 	}
 	ocfs2_metadata_cache_io_unlock(ci);
 

fs/ocfs2/journal.c

@@ -1055,7 +1055,7 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
 	if (!igrab(inode))
 		BUG();
 
-	num_running_trans = atomic_read(&(osb->journal->j_num_trans));
+	num_running_trans = atomic_read(&(journal->j_num_trans));
 	trace_ocfs2_journal_shutdown(num_running_trans);
 
 	/* Do a commit_cache here. It will flush our journal, *and*
@@ -1074,9 +1074,10 @@ void ocfs2_journal_shutdown(struct ocfs2_super *osb)
 		osb->commit_task = NULL;
 	}
 
-	BUG_ON(atomic_read(&(osb->journal->j_num_trans)) != 0);
+	BUG_ON(atomic_read(&(journal->j_num_trans)) != 0);
 
-	if (ocfs2_mount_local(osb)) {
+	if (ocfs2_mount_local(osb) &&
+	    (journal->j_journal->j_flags & JBD2_LOADED)) {
 		jbd2_journal_lock_updates(journal->j_journal);
 		status = jbd2_journal_flush(journal->j_journal, 0);
 		jbd2_journal_unlock_updates(journal->j_journal);

fs/ocfs2/quota_local.c

@@ -692,14 +692,15 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 	int status;
 	struct buffer_head *bh = NULL;
 	struct ocfs2_quota_recovery *rec;
-	int locked = 0;
+	int locked = 0, global_read = 0;
 
 	info->dqi_max_spc_limit = 0x7fffffffffffffffLL;
 	info->dqi_max_ino_limit = 0x7fffffffffffffffLL;
 	oinfo = kmalloc(sizeof(struct ocfs2_mem_dqinfo), GFP_NOFS);
 	if (!oinfo) {
 		mlog(ML_ERROR, "failed to allocate memory for ocfs2 quota"
 			       " info.");
+		status = -ENOMEM;
 		goto out_err;
 	}
 	info->dqi_priv = oinfo;
@@ -712,6 +713,7 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 	status = ocfs2_global_read_info(sb, type);
 	if (status < 0)
 		goto out_err;
+	global_read = 1;
 
 	status = ocfs2_inode_lock(lqinode, &oinfo->dqi_lqi_bh, 1);
 	if (status < 0) {
@@ -782,10 +784,12 @@ static int ocfs2_local_read_info(struct super_block *sb, int type)
 		if (locked)
 			ocfs2_inode_unlock(lqinode, 1);
 		ocfs2_release_local_quota_bitmaps(&oinfo->dqi_chunk);
+		if (global_read)
+			cancel_delayed_work_sync(&oinfo->dqi_sync_work);
 		kfree(oinfo);
 	}
 	brelse(bh);
-	return -1;
+	return status;
 }
 
 /* Write local info to quota file */

kernel/resource.c

@@ -540,20 +540,62 @@ static int __region_intersects(struct resource *parent, resource_size_t start,
 			       size_t size, unsigned long flags,
 			       unsigned long desc)
 {
-	struct resource res;
+	resource_size_t ostart, oend;
 	int type = 0; int other = 0;
-	struct resource *p;
+	struct resource *p, *dp;
+	bool is_type, covered;
+	struct resource res;
 
 	res.start = start;
 	res.end = start + size - 1;
 
 	for (p = parent->child; p ; p = p->sibling) {
-		bool is_type = (((p->flags & flags) == flags) &&
-				((desc == IORES_DESC_NONE) ||
-				 (desc == p->desc)));
-
-		if (resource_overlaps(p, &res))
-			is_type ? type++ : other++;
+		if (!resource_overlaps(p, &res))
+			continue;
+		is_type = (p->flags & flags) == flags &&
+			(desc == IORES_DESC_NONE || desc == p->desc);
+		if (is_type) {
+			type++;
+			continue;
+		}
+		/*
+		 * Continue to search in descendant resources as if the
+		 * matched descendant resources cover some ranges of 'p'.
+		 *
+		 * |------------- "CXL Window 0" ------------|
+		 * |-- "System RAM" --|
+		 *
+		 * will behave similar as the following fake resource
+		 * tree when searching "System RAM".
+		 *
+		 * |-- "System RAM" --||-- "CXL Window 0a" --|
+		 */
+		covered = false;
+		ostart = max(res.start, p->start);
+		oend = min(res.end, p->end);
+		for_each_resource(p, dp, false) {
+			if (!resource_overlaps(dp, &res))
+				continue;
+			is_type = (dp->flags & flags) == flags &&
+				(desc == IORES_DESC_NONE || desc == dp->desc);
+			if (is_type) {
+				type++;
+				/*
+				 * Range from 'ostart' to 'dp->start'
+				 * isn't covered by matched resource.
+				 */
+				if (dp->start > ostart)
+					break;
+				if (dp->end >= oend) {
+					covered = true;
+					break;
+				}
+				/* Remove covered range */
+				ostart = max(ostart, dp->end + 1);
+			}
+		}
+		if (!covered)
+			other++;
 	}
 
 	if (type == 0)

mm/damon/vaddr.c

@@ -126,6 +126,7 @@ static int __damon_va_three_regions(struct mm_struct *mm,
 	 * If this is too slow, it can be optimised to examine the maple
 	 * tree gaps.
 	 */
+	rcu_read_lock();
 	for_each_vma(vmi, vma) {
 		unsigned long gap;
 
@@ -146,6 +147,7 @@ static int __damon_va_three_regions(struct mm_struct *mm,
 next:
 		prev = vma;
 	}
+	rcu_read_unlock();
 
 	if (!sz_range(&second_gap) || !sz_range(&first_gap))
 		return -EINVAL;

mm/huge_memory.c

@@ -220,6 +220,8 @@ static bool get_huge_zero_page(void)
 		count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
 		return false;
 	}
+	/* Ensure zero folio won't have large_rmappable flag set. */
+	folio_clear_large_rmappable(zero_folio);
 	preempt_disable();
 	if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) {
 		preempt_enable();

mm/hugetlb.c

@@ -6048,7 +6048,7 @@ static vm_fault_t hugetlb_wp(struct folio *pagecache_folio,
 	 * When the original hugepage is shared one, it does not have
 	 * anon_vma prepared.
 	 */
-	ret = vmf_anon_prepare(vmf);
+	ret = __vmf_anon_prepare(vmf);
 	if (unlikely(ret))
 		goto out_release_all;
 
@@ -6247,7 +6247,7 @@ static vm_fault_t hugetlb_no_page(struct address_space *mapping,
 		}
 
 		if (!(vma->vm_flags & VM_MAYSHARE)) {
-			ret = vmf_anon_prepare(vmf);
+			ret = __vmf_anon_prepare(vmf);
 			if (unlikely(ret))
 				goto out;
 		}
@@ -6378,6 +6378,14 @@ static vm_fault_t hugetlb_no_page(struct address_space *mapping,
 	folio_unlock(folio);
 out:
 	hugetlb_vma_unlock_read(vma);
+
+	/*
+	 * We must check to release the per-VMA lock. __vmf_anon_prepare() is
+	 * the only way ret can be set to VM_FAULT_RETRY.
+	 */
+	if (unlikely(ret & VM_FAULT_RETRY))
+		vma_end_read(vma);
+
 	mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 	return ret;
 
@@ -6599,6 +6607,14 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 out_mutex:
 	hugetlb_vma_unlock_read(vma);
+
+	/*
+	 * We must check to release the per-VMA lock. __vmf_anon_prepare() in
+	 * hugetlb_wp() is the only way ret can be set to VM_FAULT_RETRY.
+	 */
+	if (unlikely(ret & VM_FAULT_RETRY))
+		vma_end_read(vma);
+
 	mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 	/*
 	 * Generally it's safe to hold refcount during waiting page lock. But

mm/internal.h

@@ -310,7 +310,16 @@ static inline void wake_throttle_isolated(pg_data_t *pgdat)
 		wake_up(wqh);
 }
 
-vm_fault_t vmf_anon_prepare(struct vm_fault *vmf);
+vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf);
+static inline vm_fault_t vmf_anon_prepare(struct vm_fault *vmf)
+{
+	vm_fault_t ret = __vmf_anon_prepare(vmf);
+
+	if (unlikely(ret & VM_FAULT_RETRY))
+		vma_end_read(vmf->vma);
+	return ret;
+}
+
 vm_fault_t do_swap_page(struct vm_fault *vmf);
 void folio_rotate_reclaimable(struct folio *folio);
 bool __folio_end_writeback(struct folio *folio);

mm/madvise.c

@@ -1527,7 +1527,7 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, const struct iovec __user *, vec,
 	 * Require CAP_SYS_NICE for influencing process performance. Note that
 	 * only non-destructive hints are currently supported.
 	 */
-	if (!capable(CAP_SYS_NICE)) {
+	if (mm != current->mm && !capable(CAP_SYS_NICE)) {
 		ret = -EPERM;
 		goto release_mm;
 	}

mm/memory.c

@@ -3276,7 +3276,7 @@ static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf)
 }
 
 /**
- * vmf_anon_prepare - Prepare to handle an anonymous fault.
+ * __vmf_anon_prepare - Prepare to handle an anonymous fault.
  * @vmf: The vm_fault descriptor passed from the fault handler.
  *
  * When preparing to insert an anonymous page into a VMA from a
@@ -3290,18 +3290,16 @@ static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf)
  * Return: 0 if fault handling can proceed.  Any other value should be
  * returned to the caller.
  */
-vm_fault_t vmf_anon_prepare(struct vm_fault *vmf)
+vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	vm_fault_t ret = 0;
 
 	if (likely(vma->anon_vma))
 		return 0;
 	if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
-		if (!mmap_read_trylock(vma->vm_mm)) {
-			vma_end_read(vma);
+		if (!mmap_read_trylock(vma->vm_mm))
 			return VM_FAULT_RETRY;
-		}
 	}
 	if (__anon_vma_prepare(vma))
 		ret = VM_FAULT_OOM;

mm/vmscan.c

@@ -4300,7 +4300,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
 	}
 
 	/* ineligible */
-	if (zone > sc->reclaim_idx) {
+	if (!folio_test_lru(folio) || zone > sc->reclaim_idx) {
 		gen = folio_inc_gen(lruvec, folio, false);
 		list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
 		return true;

mm/zsmalloc.c

@@ -54,6 +54,7 @@
 #include <linux/vmalloc.h>
 #include <linux/preempt.h>
 #include <linux/spinlock.h>
+#include <linux/sprintf.h>
 #include <linux/shrinker.h>
 #include <linux/types.h>
 #include <linux/debugfs.h>
@@ -293,17 +294,27 @@ static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) {}
 
 static int create_cache(struct zs_pool *pool)
 {
-	pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE,
-					0, 0, NULL);
+	char *name;
+
+	name = kasprintf(GFP_KERNEL, "zs_handle-%s", pool->name);
+	if (!name)
+		return -ENOMEM;
+	pool->handle_cachep = kmem_cache_create(name, ZS_HANDLE_SIZE,
+						0, 0, NULL);
+	kfree(name);
 	if (!pool->handle_cachep)
-		return 1;
+		return -EINVAL;
 
-	pool->zspage_cachep = kmem_cache_create("zspage", sizeof(struct zspage),
-					0, 0, NULL);
+	name = kasprintf(GFP_KERNEL, "zspage-%s", pool->name);
+	if (!name)
+		return -ENOMEM;
+	pool->zspage_cachep = kmem_cache_create(name, sizeof(struct zspage),
+						0, 0, NULL);
+	kfree(name);
 	if (!pool->zspage_cachep) {
 		kmem_cache_destroy(pool->handle_cachep);
 		pool->handle_cachep = NULL;
-		return 1;
+		return -EINVAL;
 	}
 
 	return 0;