Merge branch 'mm-hotfixes-stable' into mm-stable

10 files changed, 43 insertions, 22 deletions

diff --git a/.mailmap b/.mailmap
index aec51726551f..f5bd014469d7 100644
--- a/.mailmap
+++ b/.mailmap
@@ -287,6 +287,7 @@ Matthew Wilcox <willy@infradead.org> <willy@linux.intel.com>
 Matthew Wilcox <willy@infradead.org> <willy@parisc-linux.org>
 Matthias Fuchs <socketcan@esd.eu> <matthias.fuchs@esd.eu>
 Matthieu CASTET <castet.matthieu@free.fr>
+Matti Vaittinen <mazziesaccount@gmail.com> <matti.vaittinen@fi.rohmeurope.com>
 Matt Ranostay <matt.ranostay@konsulko.com> <matt@ranostay.consulting>
 Matt Ranostay <mranostay@gmail.com> Matthew Ranostay <mranostay@embeddedalley.com>
 Matt Ranostay <mranostay@gmail.com> <matt.ranostay@intel.com>
@@ -372,6 +373,8 @@ Ricardo Ribalda <ribalda@kernel.org> <ricardo.ribalda@gmail.com>
 Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com>
 Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com>
 Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru>
+Muchun Song <muchun.song@linux.dev> <songmuchun@bytedance.com>
+Muchun Song <muchun.song@linux.dev> <smuchun@gmail.com>
 Ross Zwisler <zwisler@kernel.org> <ross.zwisler@linux.intel.com>
 Rudolf Marek <R.Marek@sh.cvut.cz>
 Rui Saraiva <rmps@joel.ist.utl.pt>
diff --git a/MAINTAINERS b/MAINTAINERS
index 7b6b8034811c..6044301ee9bd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5299,7 +5299,7 @@ M:	Johannes Weiner <hannes@cmpxchg.org>
 M:	Michal Hocko <mhocko@kernel.org>
 M:	Roman Gushchin <roman.gushchin@linux.dev>
 M:	Shakeel Butt <shakeelb@google.com>
-R:	Muchun Song <songmuchun@bytedance.com>
+R:	Muchun Song <muchun.song@linux.dev>
 L:	cgroups@vger.kernel.org
 L:	linux-mm@kvack.org
 S:	Maintained
@@ -9443,7 +9443,7 @@ F:	drivers/net/ethernet/huawei/hinic/
 
 HUGETLB SUBSYSTEM
 M:	Mike Kravetz <mike.kravetz@oracle.com>
-M:	Muchun Song <songmuchun@bytedance.com>
+M:	Muchun Song <muchun.song@linux.dev>
 L:	linux-mm@kvack.org
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-kernel-mm-hugepages
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 528bd44b59e2..2b7d077de7ef 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -68,6 +68,7 @@ struct css_task_iter {
 	struct list_head		iters_node;	/* css_set->task_iters */
 };
 
+extern struct file_system_type cgroup_fs_type;
 extern struct cgroup_root cgrp_dfl_root;
 extern struct css_set init_css_set;
 
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index 27ade4f22abb..b982dd614572 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -33,11 +33,13 @@
  * can use the extra bits to store other information besides PFN.
  */
 #ifdef MAX_PHYSMEM_BITS
-#define SWP_PFN_BITS			(MAX_PHYSMEM_BITS - PAGE_SHIFT)
+#define SWP_PFN_BITS		(MAX_PHYSMEM_BITS - PAGE_SHIFT)
 #else  /* MAX_PHYSMEM_BITS */
-#define SWP_PFN_BITS			(BITS_PER_LONG - PAGE_SHIFT)
+#define SWP_PFN_BITS		min_t(int, \
+				      sizeof(phys_addr_t) * 8 - PAGE_SHIFT, \
+				      SWP_TYPE_SHIFT)
 #endif	/* MAX_PHYSMEM_BITS */
-#define SWP_PFN_MASK			(BIT(SWP_PFN_BITS) - 1)
+#define SWP_PFN_MASK		(BIT(SWP_PFN_BITS) - 1)
 
 /**
  * Migration swap entry specific bitfield definitions.  Layout:
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index fd4020835ec6..367b0a42ada9 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -167,7 +167,6 @@ struct cgroup_mgctx {
 extern spinlock_t css_set_lock;
 extern struct cgroup_subsys *cgroup_subsys[];
 extern struct list_head cgroup_roots;
-extern struct file_system_type cgroup_fs_type;
 
 /* iterate across the hierarchies */
 #define for_each_root(root)						\
diff --git a/mm/gup.c b/mm/gup.c
index 90ae44f24870..2860cf4a85e1 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2767,7 +2767,7 @@ static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned lo
 		next = pud_addr_end(addr, end);
 		if (unlikely(!pud_present(pud)))
 			return 0;
-		if (unlikely(pud_huge(pud))) {
+		if (unlikely(pud_huge(pud) || pud_devmap(pud))) {
 			if (!gup_huge_pud(pud, pudp, addr, next, flags,
 					  pages, nr))
 				return 0;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 23750cec0036..2c7a91689fef 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4836,6 +4836,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 	unsigned int efd, cfd;
 	struct fd efile;
 	struct fd cfile;
+	struct dentry *cdentry;
 	const char *name;
 	char *endp;
 	int ret;
@@ -4890,6 +4891,16 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 		goto out_put_cfile;
 
 	/*
+	 * The control file must be a regular cgroup1 file. As a regular cgroup
+	 * file can't be renamed, it's safe to access its name afterwards.
+	 */
+	cdentry = cfile.file->f_path.dentry;
+	if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) {
+		ret = -EINVAL;
+		goto out_put_cfile;
+	}
+
+	/*
 	 * Determine the event callbacks and set them in @event.  This used
 	 * to be done via struct cftype but cgroup core no longer knows
 	 * about these events.  The following is crude but the whole thing
@@ -4897,7 +4908,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 	 *
 	 * DO NOT ADD NEW FILES.
 	 */
-	name = cfile.file->f_path.dentry->d_name.name;
+	name = cdentry->d_name.name;
 
 	if (!strcmp(name, "memory.usage_in_bytes")) {
 		event->register_event = mem_cgroup_usage_register_event;
@@ -4921,7 +4932,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
 	 * automatically removed on cgroup destruction but the removal is
 	 * asynchronous, so take an extra ref on @css.
 	 */
-	cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent,
+	cfile_css = css_tryget_online_from_dir(cdentry->d_parent,
 					       &memory_cgrp_subsys);
 	ret = -EINVAL;
 	if (IS_ERR(cfile_css))
diff --git a/mm/mmap.c b/mm/mmap.c
index 4624ff3ded29..1741273ac34c 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -226,8 +226,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 		/* Search one past newbrk */
 		mas_set(&mas, newbrk);
 		brkvma = mas_find(&mas, oldbrk);
-		BUG_ON(brkvma == NULL);
-		if (brkvma->vm_start >= oldbrk)
+		if (!brkvma || brkvma->vm_start >= oldbrk)
 			goto out; /* mapping intersects with an existing non-brk vma. */
 		/*
 		 * mm->brk must be protected by write mmap_lock.
@@ -2949,9 +2948,9 @@ static int do_brk_flags(struct ma_state *mas, struct vm_area_struct *vma,
 	 * Expand the existing vma if possible; Note that singular lists do not
 	 * occur after forking, so the expand will only happen on new VMAs.
 	 */
-	if (vma &&
-	    (!vma->anon_vma || list_is_singular(&vma->anon_vma_chain)) &&
-	    ((vma->vm_flags & ~VM_SOFTDIRTY) == flags)) {
+	if (vma && vma->vm_end == addr && !vma_policy(vma) &&
+	    can_vma_merge_after(vma, flags, NULL, NULL,
+				addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL)) {
 		mas_set_range(mas, vma->vm_start, addr + len - 1);
 		if (mas_preallocate(mas, vma, GFP_KERNEL))
 			return -ENOMEM;
@@ -3038,11 +3037,6 @@ int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
 		goto munmap_failed;
 
 	vma = mas_prev(&mas, 0);
-	if (!vma || vma->vm_end != addr || vma_policy(vma) ||
-	    !can_vma_merge_after(vma, flags, NULL, NULL,
-				 addr >> PAGE_SHIFT, NULL_VM_UFFD_CTX, NULL))
-		vma = NULL;
-
 	ret = do_brk_flags(&mas, vma, addr, len, flags);
 	populate = ((mm->def_flags & VM_LOCKED) != 0);
 	mmap_write_unlock(mm);
diff --git a/mm/shmem.c b/mm/shmem.c
index f418d21205be..17adb7f6f6e4 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -950,6 +950,15 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		cond_resched();
 	}
 
+	/*
+	 * When undoing a failed fallocate, we want none of the partial folio
+	 * zeroing and splitting below, but shall want to truncate the whole
+	 * folio when !uptodate indicates that it was added by this fallocate,
+	 * even when [lstart, lend] covers only a part of the folio.
+	 */
+	if (unfalloc)
+		goto whole_folios;
+
 	same_folio = (lstart >> PAGE_SHIFT) == (lend >> PAGE_SHIFT);
 	folio = shmem_get_partial_folio(inode, lstart >> PAGE_SHIFT);
 	if (folio) {
@@ -975,6 +984,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		folio_put(folio);
 	}
 
+whole_folios:
+
 	index = start;
 	while (index < end) {
 		cond_resched();
diff --git a/tools/testing/selftests/cgroup/test_kmem.c b/tools/testing/selftests/cgroup/test_kmem.c
index 22b31ebb3513..258ddc565deb 100644
--- a/tools/testing/selftests/cgroup/test_kmem.c
+++ b/tools/testing/selftests/cgroup/test_kmem.c
@@ -19,12 +19,12 @@
 
 
 /*
- * Memory cgroup charging is performed using percpu batches 32 pages
+ * Memory cgroup charging is performed using percpu batches 64 pages
  * big (look at MEMCG_CHARGE_BATCH), whereas memory.stat is exact. So
  * the maximum discrepancy between charge and vmstat entries is number
- * of cpus multiplied by 32 pages.
+ * of cpus multiplied by 64 pages.
  */
-#define MAX_VMSTAT_ERROR (4096 * 32 * get_nprocs())
+#define MAX_VMSTAT_ERROR (4096 * 64 * get_nprocs())
 
 
 static int alloc_dcache(const char *cgroup, void *arg)