Merge tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Nick Piggin's "shoot lazy tlbs" series, to improve the peformance of
   switching from a user process to a kernel thread.

 - More folio conversions from Kefeng Wang, Zhang Peng and Pankaj
   Raghav.

 - zsmalloc performance improvements from Sergey Senozhatsky.

 - Yue Zhao has found and fixed some data race issues around the
   alteration of memcg userspace tunables.

 - VFS rationalizations from Christoph Hellwig:
     - removal of most of the callers of write_one_page()
     - make __filemap_get_folio()'s return value more useful

 - Luis Chamberlain has changed tmpfs so it no longer requires swap
   backing. Use `mount -o noswap'.

 - Qi Zheng has made the slab shrinkers operate locklessly, providing
   some scalability benefits.

 - Keith Busch has improved dmapool's performance, making part of its
   operations O(1) rather than O(n).

 - Peter Xu adds the UFFD_FEATURE_WP_UNPOPULATED feature to userfaultd,
   permitting userspace to wr-protect anon memory unpopulated ptes.

 - Kirill Shutemov has changed MAX_ORDER's meaning to be inclusive
   rather than exclusive, and has fixed a bunch of errors which were
   caused by its unintuitive meaning.

 - Axel Rasmussen give userfaultfd the UFFDIO_CONTINUE_MODE_WP feature,
   which causes minor faults to install a write-protected pte.

 - Vlastimil Babka has done some maintenance work on vma_merge():
   cleanups to the kernel code and improvements to our userspace test
   harness.

 - Cleanups to do_fault_around() by Lorenzo Stoakes.

 - Mike Rapoport has moved a lot of initialization code out of various
   mm/ files and into mm/mm_init.c.

 - Lorenzo Stoakes removd vmf_insert_mixed_prot(), which was added for
   DRM, but DRM doesn't use it any more.

 - Lorenzo has also coverted read_kcore() and vread() to use iterators
   and has thereby removed the use of bounce buffers in some cases.

 - Lorenzo has also contributed further cleanups of vma_merge().

 - Chaitanya Prakash provides some fixes to the mmap selftesting code.

 - Matthew Wilcox changes xfs and afs so they no longer take sleeping
   locks in ->map_page(), a step towards RCUification of pagefaults.

 - Suren Baghdasaryan has improved mmap_lock scalability by switching to
   per-VMA locking.

 - Frederic Weisbecker has reworked the percpu cache draining so that it
   no longer causes latency glitches on cpu isolated workloads.

 - Mike Rapoport cleans up and corrects the ARCH_FORCE_MAX_ORDER Kconfig
   logic.

 - Liu Shixin has changed zswap's initialization so we no longer waste a
   chunk of memory if zswap is not being used.

 - Yosry Ahmed has improved the performance of memcg statistics
   flushing.

 - David Stevens has fixed several issues involving khugepaged,
   userfaultfd and shmem.

 - Christoph Hellwig has provided some cleanup work to zram's IO-related
   code paths.

 - David Hildenbrand has fixed up some issues in the selftest code's
   testing of our pte state changing.

 - Pankaj Raghav has made page_endio() unneeded and has removed it.

 - Peter Xu contributed some rationalizations of the userfaultfd
   selftests.

 - Yosry Ahmed has fixed an issue around memcg's page recalim
   accounting.

 - Chaitanya Prakash has fixed some arm-related issues in the
   selftests/mm code.

 - Longlong Xia has improved the way in which KSM handles hwpoisoned
   pages.

 - Peter Xu fixes a few issues with uffd-wp at fork() time.

 - Stefan Roesch has changed KSM so that it may now be used on a
   per-process and per-cgroup basis.

* tag 'mm-stable-2023-04-27-15-30' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (369 commits)
  mm,unmap: avoid flushing TLB in batch if PTE is inaccessible
  shmem: restrict noswap option to initial user namespace
  mm/khugepaged: fix conflicting mods to collapse_file()
  sparse: remove unnecessary 0 values from rc
  mm: move 'mmap_min_addr' logic from callers into vm_unmapped_area()
  hugetlb: pte_alloc_huge() to replace huge pte_alloc_map()
  maple_tree: fix allocation in mas_sparse_area()
  mm: do not increment pgfault stats when page fault handler retries
  zsmalloc: allow only one active pool compaction context
  selftests/mm: add new selftests for KSM
  mm: add new KSM process and sysfs knobs
  mm: add new api to enable ksm per process
  mm: shrinkers: fix debugfs file permissions
  mm: don't check VMA write permissions if the PTE/PMD indicates write permissions
  migrate_pages_batch: fix statistics for longterm pin retry
  userfaultfd: use helper function range_in_vma()
  lib/show_mem.c: use for_each_populated_zone() simplify code
  mm: correct arg in reclaim_pages()/reclaim_clean_pages_from_list()
  fs/buffer: convert create_page_buffers to folio_create_buffers
  fs/buffer: add folio_create_empty_buffers helper
  ...

1 files changed, 17 insertions, 26 deletions

diff --git a/mm/shrinker_debug.c b/mm/shrinker_debug.c
index 39c3491e28a3..3f83b10c5031 100644
--- a/mm/shrinker_debug.c
+++ b/mm/shrinker_debug.c
@@ -5,10 +5,12 @@
 #include <linux/seq_file.h>
 #include <linux/shrinker.h>
 #include <linux/memcontrol.h>
+#include <linux/srcu.h>
 
 /* defined in vmscan.c */
-extern struct rw_semaphore shrinker_rwsem;
+extern struct mutex shrinker_mutex;
 extern struct list_head shrinker_list;
+extern struct srcu_struct shrinker_srcu;
 
 static DEFINE_IDA(shrinker_debugfs_ida);
 static struct dentry *shrinker_debugfs_root;
@@ -49,18 +51,13 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v)
 	struct mem_cgroup *memcg;
 	unsigned long total;
 	bool memcg_aware;
-	int ret, nid;
+	int ret = 0, nid, srcu_idx;
 
 	count_per_node = kcalloc(nr_node_ids, sizeof(unsigned long), GFP_KERNEL);
 	if (!count_per_node)
 		return -ENOMEM;
 
-	ret = down_read_killable(&shrinker_rwsem);
-	if (ret) {
-		kfree(count_per_node);
-		return ret;
-	}
-	rcu_read_lock();
+	srcu_idx = srcu_read_lock(&shrinker_srcu);
 
 	memcg_aware = shrinker->flags & SHRINKER_MEMCG_AWARE;
 
@@ -91,8 +88,7 @@ static int shrinker_debugfs_count_show(struct seq_file *m, void *v)
 		}
 	} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
 
-	rcu_read_unlock();
-	up_read(&shrinker_rwsem);
+	srcu_read_unlock(&shrinker_srcu, srcu_idx);
 
 	kfree(count_per_node);
 	return ret;
@@ -115,9 +111,8 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file,
 		.gfp_mask = GFP_KERNEL,
 	};
 	struct mem_cgroup *memcg = NULL;
-	int nid;
+	int nid, srcu_idx;
 	char kbuf[72];
-	ssize_t ret;
 
 	read_len = size < (sizeof(kbuf) - 1) ? size : (sizeof(kbuf) - 1);
 	if (copy_from_user(kbuf, buf, read_len))
@@ -146,11 +141,7 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file,
 		return -EINVAL;
 	}
 
-	ret = down_read_killable(&shrinker_rwsem);
-	if (ret) {
-		mem_cgroup_put(memcg);
-		return ret;
-	}
+	srcu_idx = srcu_read_lock(&shrinker_srcu);
 
 	sc.nid = nid;
 	sc.memcg = memcg;
@@ -159,7 +150,7 @@ static ssize_t shrinker_debugfs_scan_write(struct file *file,
 
 	shrinker->scan_objects(shrinker, &sc);
 
-	up_read(&shrinker_rwsem);
+	srcu_read_unlock(&shrinker_srcu, srcu_idx);
 	mem_cgroup_put(memcg);
 
 	return size;
@@ -177,7 +168,7 @@ int shrinker_debugfs_add(struct shrinker *shrinker)
 	char buf[128];
 	int id;
 
-	lockdep_assert_held(&shrinker_rwsem);
+	lockdep_assert_held(&shrinker_mutex);
 
 	/* debugfs isn't initialized yet, add debugfs entries later. */
 	if (!shrinker_debugfs_root)
@@ -198,9 +189,9 @@ int shrinker_debugfs_add(struct shrinker *shrinker)
 	}
 	shrinker->debugfs_entry = entry;
 
-	debugfs_create_file("count", 0220, entry, shrinker,
+	debugfs_create_file("count", 0440, entry, shrinker,
 			    &shrinker_debugfs_count_fops);
-	debugfs_create_file("scan", 0440, entry, shrinker,
+	debugfs_create_file("scan", 0220, entry, shrinker,
 			    &shrinker_debugfs_scan_fops);
 	return 0;
 }
@@ -220,7 +211,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...)
 	if (!new)
 		return -ENOMEM;
 
-	down_write(&shrinker_rwsem);
+	mutex_lock(&shrinker_mutex);
 
 	old = shrinker->name;
 	shrinker->name = new;
@@ -238,7 +229,7 @@ int shrinker_debugfs_rename(struct shrinker *shrinker, const char *fmt, ...)
 			shrinker->debugfs_entry = entry;
 	}
 
-	up_write(&shrinker_rwsem);
+	mutex_unlock(&shrinker_mutex);
 
 	kfree_const(old);
 
@@ -250,7 +241,7 @@ struct dentry *shrinker_debugfs_remove(struct shrinker *shrinker)
 {
 	struct dentry *entry = shrinker->debugfs_entry;
 
-	lockdep_assert_held(&shrinker_rwsem);
+	lockdep_assert_held(&shrinker_mutex);
 
 	kfree_const(shrinker->name);
 	shrinker->name = NULL;
@@ -275,14 +266,14 @@ static int __init shrinker_debugfs_init(void)
 	shrinker_debugfs_root = dentry;
 
 	/* Create debugfs entries for shrinkers registered at boot */
-	down_write(&shrinker_rwsem);
+	mutex_lock(&shrinker_mutex);
 	list_for_each_entry(shrinker, &shrinker_list, list)
 		if (!shrinker->debugfs_entry) {
 			ret = shrinker_debugfs_add(shrinker);
 			if (ret)
 				break;
 		}
-	up_write(&shrinker_rwsem);
+	mutex_unlock(&shrinker_mutex);
 
 	return ret;
 }