Merge tag 'mm-hotfixes-stable-2024-07-26-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc hotfixes from Andrew Morton:
 "11 hotfixes, 7 of which are cc:stable.  7 are MM, 4 are other"

* tag 'mm-hotfixes-stable-2024-07-26-14-33' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm:
  nilfs2: handle inconsistent state in nilfs_btnode_create_block()
  selftests/mm: skip test for non-LPA2 and non-LVA systems
  mm/page_alloc: fix pcp->count race between drain_pages_zone() vs __rmqueue_pcplist()
  mm: memcg: add cacheline padding after lruvec in mem_cgroup_per_node
  alloc_tag: outline and export free_reserved_page()
  decompress_bunzip2: fix rare decompression failure
  mm/huge_memory: avoid PMD-size page cache if needed
  mm: huge_memory: use !CONFIG_64BIT to relax huge page alignment on 32 bit machines
  mm: fix old/young bit handling in the faulting path
  dt-bindings: arm: update James Clark's email address
  MAINTAINERS: mailmap: update James Clark's email address

14 files changed, 95 insertions, 42 deletions

diff --git a/.mailmap b/.mailmap
index cbdf5d63c381..e51d76df75c2 100644
--- a/.mailmap
+++ b/.mailmap
@@ -260,6 +260,7 @@ Jaegeuk Kim <[email protected]> <[email protected]>
 Jakub Kicinski <[email protected]> <[email protected]>
 James Bottomley <jejb@mulgrave.(none)>
 James Bottomley <[email protected]>
+James Clark <[email protected]> <[email protected]>
 James E Wilson <[email protected]>
 James Hogan <[email protected]> <[email protected]>
 James Hogan <[email protected]> <[email protected]>
diff --git a/Documentation/devicetree/bindings/arm/arm,coresight-dummy-sink.yaml b/Documentation/devicetree/bindings/arm/arm,coresight-dummy-sink.yaml
index c960c8e0a9a5..08b89b62c505 100644
--- a/Documentation/devicetree/bindings/arm/arm,coresight-dummy-sink.yaml
+++ b/Documentation/devicetree/bindings/arm/arm,coresight-dummy-sink.yaml
@@ -30,7 +30,7 @@ description: |
 maintainers:
   - Mike Leach <[email protected]>
   - Suzuki K Poulose <[email protected]>
-  - James Clark <[email protected]>
+  - James Clark <[email protected]>
   - Mao Jinlong <[email protected]>
   - Hao Zhang <[email protected]>
 
diff --git a/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml b/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml
index 6745b4cc8f1c..d50a60368e27 100644
--- a/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml
+++ b/Documentation/devicetree/bindings/arm/arm,coresight-dummy-source.yaml
@@ -29,7 +29,7 @@ description: |
 maintainers:
   - Mike Leach <[email protected]>
   - Suzuki K Poulose <[email protected]>
-  - James Clark <[email protected]>
+  - James Clark <[email protected]>
   - Mao Jinlong <[email protected]>
   - Hao Zhang <[email protected]>
 
diff --git a/MAINTAINERS b/MAINTAINERS
index c0a3d9e93689..5bbcfea5e3fa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2196,7 +2196,7 @@ N:	digicolor
 ARM/CORESIGHT FRAMEWORK AND DRIVERS
 M:	Suzuki K Poulose <[email protected]>
 R:	Mike Leach <[email protected]>
-R:	James Clark <[email protected]>
+R:	James Clark <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
 L:	[email protected] (moderated for non-subscribers)
 S:	Maintained
@@ -17894,7 +17894,7 @@ F:	tools/perf/
 PERFORMANCE EVENTS TOOLING ARM64
 R:	John Garry <[email protected]>
 R:	Will Deacon <[email protected]>
-R:	James Clark <[email protected]>
+R:	James Clark <[email protected]>
 R:	Mike Leach <[email protected]>
 R:	Leo Yan <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 0131d83b912d..c034080c334b 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -51,12 +51,21 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
 
 	bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node));
 	if (unlikely(!bh))
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	if (unlikely(buffer_mapped(bh) || buffer_uptodate(bh) ||
 		     buffer_dirty(bh))) {
-		brelse(bh);
-		BUG();
+		/*
+		 * The block buffer at the specified new address was already
+		 * in use.  This can happen if it is a virtual block number
+		 * and has been reallocated due to corruption of the bitmap
+		 * used to manage its allocation state (if not, the buffer
+		 * clearing of an abandoned b-tree node is missing somewhere).
+		 */
+		nilfs_error(inode->i_sb,
+			    "state inconsistency probably due to duplicate use of b-tree node block address %llu (ino=%lu)",
+			    (unsigned long long)blocknr, inode->i_ino);
+		goto failed;
 	}
 	memset(bh->b_data, 0, i_blocksize(inode));
 	bh->b_bdev = inode->i_sb->s_bdev;
@@ -67,6 +76,12 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
 	folio_unlock(bh->b_folio);
 	folio_put(bh->b_folio);
 	return bh;
+
+failed:
+	folio_unlock(bh->b_folio);
+	folio_put(bh->b_folio);
+	brelse(bh);
+	return ERR_PTR(-EIO);
 }
 
 int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
@@ -217,8 +232,8 @@ retry:
 	}
 
 	nbh = nilfs_btnode_create_block(btnc, newkey);
-	if (!nbh)
-		return -ENOMEM;
+	if (IS_ERR(nbh))
+		return PTR_ERR(nbh);
 
 	BUG_ON(nbh == obh);
 	ctxt->newbh = nbh;
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index a139970e4804..862bdf23120e 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -63,8 +63,8 @@ static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree,
 	struct buffer_head *bh;
 
 	bh = nilfs_btnode_create_block(btnc, ptr);
-	if (!bh)
-		return -ENOMEM;
+	if (IS_ERR(bh))
+		return PTR_ERR(bh);
 
 	set_buffer_nilfs_volatile(bh);
 	*bhp = bh;
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index cff002be83eb..e25d9ebfdf89 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -74,14 +74,20 @@ extern struct kobj_attribute thpsize_shmem_enabled_attr;
 #define THP_ORDERS_ALL_ANON	((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1)))
 
 /*
- * Mask of all large folio orders supported for file THP.
+ * Mask of all large folio orders supported for file THP. Folios in a DAX
+ * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to
+ * it.
  */
-#define THP_ORDERS_ALL_FILE	(BIT(PMD_ORDER) | BIT(PUD_ORDER))
+#define THP_ORDERS_ALL_FILE_DAX		\
+	(BIT(PMD_ORDER) | BIT(PUD_ORDER))
+#define THP_ORDERS_ALL_FILE_DEFAULT	\
+	((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0))
 
 /*
  * Mask of all large folio orders supported for THP.
  */
-#define THP_ORDERS_ALL		(THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE)
+#define THP_ORDERS_ALL	\
+	(THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DAX | THP_ORDERS_ALL_FILE_DEFAULT)
 
 #define TVA_SMAPS		(1 << 0)	/* Will be used for procfs */
 #define TVA_IN_PF		(1 << 1)	/* Page fault handler */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 7e2eb091049a..0e5bf25d324f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -109,6 +109,7 @@ struct mem_cgroup_per_node {
 
 	/* Fields which get updated often at the end. */
 	struct lruvec		lruvec;
+	CACHELINE_PADDING(_pad2_);
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 	struct mem_cgroup_reclaim_iter	iter;
 };
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4563b560ced7..c4b238a20b76 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3137,21 +3137,7 @@ extern void reserve_bootmem_region(phys_addr_t start,
 				   phys_addr_t end, int nid);
 
 /* Free the reserved page into the buddy system, so it gets managed. */
-static inline void free_reserved_page(struct page *page)
-{
-	if (mem_alloc_profiling_enabled()) {
-		union codetag_ref *ref = get_page_tag_ref(page);
-
-		if (ref) {
-			set_codetag_empty(ref);
-			put_page_tag_ref(ref);
-		}
-	}
-	ClearPageReserved(page);
-	init_page_count(page);
-	__free_page(page);
-	adjust_managed_page_count(page, 1);
-}
+void free_reserved_page(struct page *page);
 #define free_highmem_page(page) free_reserved_page(page)
 
 static inline void mark_page_reserved(struct page *page)
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 3518e7394eca..ca736166f100 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -232,7 +232,8 @@ static int INIT get_next_block(struct bunzip_data *bd)
 	   RUNB) */
 	symCount = symTotal+2;
 	for (j = 0; j < groupCount; j++) {
-		unsigned char length[MAX_SYMBOLS], temp[MAX_HUFCODE_BITS+1];
+		unsigned char length[MAX_SYMBOLS];
+		unsigned short temp[MAX_HUFCODE_BITS+1];
 		int	minLen,	maxLen, pp;
 		/* Read Huffman code lengths for each symbol.  They're
 		   stored in a way similar to mtf; record a starting
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f9696c94e211..f4be468e06a4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -89,9 +89,17 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
 	bool smaps = tva_flags & TVA_SMAPS;
 	bool in_pf = tva_flags & TVA_IN_PF;
 	bool enforce_sysfs = tva_flags & TVA_ENFORCE_SYSFS;
+	unsigned long supported_orders;
+
 	/* Check the intersection of requested and supported orders. */
-	orders &= vma_is_anonymous(vma) ?
-			THP_ORDERS_ALL_ANON : THP_ORDERS_ALL_FILE;
+	if (vma_is_anonymous(vma))
+		supported_orders = THP_ORDERS_ALL_ANON;
+	else if (vma_is_dax(vma))
+		supported_orders = THP_ORDERS_ALL_FILE_DAX;
+	else
+		supported_orders = THP_ORDERS_ALL_FILE_DEFAULT;
+
+	orders &= supported_orders;
 	if (!orders)
 		return 0;
 
@@ -877,7 +885,7 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
 	loff_t off_align = round_up(off, size);
 	unsigned long len_pad, ret, off_sub;
 
-	if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall())
+	if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall())
 		return 0;
 
 	if (off_end <= off_align || (off_end - off_align) < size)
diff --git a/mm/memory.c b/mm/memory.c
index 1ff7b6f51ec1..34f8402d2046 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4780,7 +4780,7 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio,
 {
 	struct vm_area_struct *vma = vmf->vma;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
-	bool prefault = in_range(vmf->address, addr, nr * PAGE_SIZE);
+	bool prefault = !in_range(vmf->address, addr, nr * PAGE_SIZE);
 	pte_t entry;
 
 	flush_icache_pages(vma, page, nr);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8337926b89d4..28f80daf5c04 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2343,16 +2343,20 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 static void drain_pages_zone(unsigned int cpu, struct zone *zone)
 {
 	struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
-	int count = READ_ONCE(pcp->count);
-
-	while (count) {
-		int to_drain = min(count, pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
-		count -= to_drain;
+	int count;
 
+	do {
 		spin_lock(&pcp->lock);
-		free_pcppages_bulk(zone, to_drain, pcp, 0);
+		count = pcp->count;
+		if (count) {
+			int to_drain = min(count,
+				pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
+
+			free_pcppages_bulk(zone, to_drain, pcp, 0);
+			count -= to_drain;
+		}
 		spin_unlock(&pcp->lock);
-	}
+	} while (count);
 }
 
 /*
@@ -5815,6 +5819,23 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char
 	return pages;
 }
 
+void free_reserved_page(struct page *page)
+{
+	if (mem_alloc_profiling_enabled()) {
+		union codetag_ref *ref = get_page_tag_ref(page);
+
+		if (ref) {
+			set_codetag_empty(ref);
+			put_page_tag_ref(ref);
+		}
+	}
+	ClearPageReserved(page);
+	init_page_count(page);
+	__free_page(page);
+	adjust_managed_page_count(page, 1);
+}
+EXPORT_SYMBOL(free_reserved_page);
+
 static int page_alloc_cpu_dead(unsigned int cpu)
 {
 	struct zone *zone;
diff --git a/tools/testing/selftests/mm/va_high_addr_switch.c b/tools/testing/selftests/mm/va_high_addr_switch.c
index fa7eabfaf841..896b3f73fc53 100644
--- a/tools/testing/selftests/mm/va_high_addr_switch.c
+++ b/tools/testing/selftests/mm/va_high_addr_switch.c
@@ -293,6 +293,20 @@ static int run_test(struct testcase *test, int count)
 	return ret;
 }
 
+#ifdef __aarch64__
+/* Check if userspace VA > 48 bits */
+static int high_address_present(void)
+{
+	void *ptr = mmap((void *)(1UL << 50), 1, PROT_READ | PROT_WRITE,
+			 MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
+	if (ptr == MAP_FAILED)
+		return 0;
+
+	munmap(ptr, 1);
+	return 1;
+}
+#endif
+
 static int supported_arch(void)
 {
 #if defined(__powerpc64__)
@@ -300,7 +314,7 @@ static int supported_arch(void)
 #elif defined(__x86_64__)
 	return 1;
 #elif defined(__aarch64__)
-	return 1;
+	return high_address_present();
 #else
 	return 0;
 #endif