Merge tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull MM updates from Andrew Morton:

 - Yu Zhao's Multi-Gen LRU patches are here. They've been under test in
   linux-next for a couple of months without, to my knowledge, any
   negative reports (or any positive ones, come to that).

 - Also the Maple Tree from Liam Howlett. An overlapping range-based
   tree for vmas. It it apparently slightly more efficient in its own
   right, but is mainly targeted at enabling work to reduce mmap_lock
   contention.

   Liam has identified a number of other tree users in the kernel which
   could be beneficially onverted to mapletrees.

   Yu Zhao has identified a hard-to-hit but "easy to fix" lockdep splat
   at [1]. This has yet to be addressed due to Liam's unfortunately
   timed vacation. He is now back and we'll get this fixed up.

 - Dmitry Vyukov introduces KMSAN: the Kernel Memory Sanitizer. It uses
   clang-generated instrumentation to detect used-unintialized bugs down
   to the single bit level.

   KMSAN keeps finding bugs. New ones, as well as the legacy ones.

 - Yang Shi adds a userspace mechanism (madvise) to induce a collapse of
   memory into THPs.

 - Zach O'Keefe has expanded Yang Shi's madvise(MADV_COLLAPSE) to
   support file/shmem-backed pages.

 - userfaultfd updates from Axel Rasmussen

 - zsmalloc cleanups from Alexey Romanov

 - cleanups from Miaohe Lin: vmscan, hugetlb_cgroup, hugetlb and
   memory-failure

 - Huang Ying adds enhancements to NUMA balancing memory tiering mode's
   page promotion, with a new way of detecting hot pages.

 - memcg updates from Shakeel Butt: charging optimizations and reduced
   memory consumption.

 - memcg cleanups from Kairui Song.

 - memcg fixes and cleanups from Johannes Weiner.

 - Vishal Moola provides more folio conversions

 - Zhang Yi removed ll_rw_block() :(

 - migration enhancements from Peter Xu

 - migration error-path bugfixes from Huang Ying

 - Aneesh Kumar added ability for a device driver to alter the memory
   tiering promotion paths. For optimizations by PMEM drivers, DRM
   drivers, etc.

 - vma merging improvements from Jakub Matěn.

 - NUMA hinting cleanups from David Hildenbrand.

 - xu xin added aditional userspace visibility into KSM merging
   activity.

 - THP & KSM code consolidation from Qi Zheng.

 - more folio work from Matthew Wilcox.

 - KASAN updates from Andrey Konovalov.

 - DAMON cleanups from Kaixu Xia.

 - DAMON work from SeongJae Park: fixes, cleanups.

 - hugetlb sysfs cleanups from Muchun Song.

 - Mike Kravetz fixes locking issues in hugetlbfs and in hugetlb core.

Link: https://lkml.kernel.org/r/CAOUHufZabH85CeUN-MEMgL8gJGzJEWUrkiM58JkTbBhh-jew0Q@mail.gmail.com [1]

* tag 'mm-stable-2022-10-08' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (555 commits)
  hugetlb: allocate vma lock for all sharable vmas
  hugetlb: take hugetlb vma_lock when clearing vma_lock->vma pointer
  hugetlb: fix vma lock handling during split vma and range unmapping
  mglru: mm/vmscan.c: fix imprecise comments
  mm/mglru: don't sync disk for each aging cycle
  mm: memcontrol: drop dead CONFIG_MEMCG_SWAP config symbol
  mm: memcontrol: use do_memsw_account() in a few more places
  mm: memcontrol: deprecate swapaccounting=0 mode
  mm: memcontrol: don't allocate cgroup swap arrays when memcg is disabled
  mm/secretmem: remove reduntant return value
  mm/hugetlb: add available_huge_pages() func
  mm: remove unused inline functions from include/linux/mm_inline.h
  selftests/vm: add selftest for MADV_COLLAPSE of uffd-minor memory
  selftests/vm: add file/shmem MADV_COLLAPSE selftest for cleared pmd
  selftests/vm: add thp collapse shmem testing
  selftests/vm: add thp collapse file and tmpfs testing
  selftests/vm: modularize thp collapse memory operations
  selftests/vm: dedup THP helpers
  mm/khugepaged: add tracepoint to hpage_collapse_scan_file()
  mm/madvise: add file and shmem support to MADV_COLLAPSE
  ...

1 files changed, 39 insertions, 3 deletions

diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index a37622060fff..4852a2dbdb27 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -11,9 +11,17 @@
 #include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
+#include <linux/memory-tiers.h>
 #include "dax-private.h"
 #include "bus.h"
 
+/*
+ * Default abstract distance assigned to the NUMA node onlined
+ * by DAX/kmem if the low level platform driver didn't initialize
+ * one for this NUMA node.
+ */
+#define MEMTIER_DEFAULT_DAX_ADISTANCE	(MEMTIER_ADISTANCE_DRAM * 5)
+
 /* Memory resource name used for add_memory_driver_managed(). */
 static const char *kmem_name;
 /* Set if any memory will remain added when the driver will be unloaded. */
@@ -41,6 +49,7 @@ struct dax_kmem_data {
 	struct resource *res[];
 };
 
+static struct memory_dev_type *dax_slowmem_type;
 static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 {
 	struct device *dev = &dev_dax->dev;
@@ -79,11 +88,13 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
 		return -EINVAL;
 	}
 
+	init_node_memory_type(numa_node, dax_slowmem_type);
+
+	rc = -ENOMEM;
 	data = kzalloc(struct_size(data, res, dev_dax->nr_range), GFP_KERNEL);
 	if (!data)
-		return -ENOMEM;
+		goto err_dax_kmem_data;
 
-	rc = -ENOMEM;
 	data->res_name = kstrdup(dev_name(dev), GFP_KERNEL);
 	if (!data->res_name)
 		goto err_res_name;
@@ -155,6 +166,8 @@ err_reg_mgid:
 	kfree(data->res_name);
 err_res_name:
 	kfree(data);
+err_dax_kmem_data:
+	clear_node_memory_type(numa_node, dax_slowmem_type);
 	return rc;
 }
 
@@ -162,6 +175,7 @@ err_res_name:
 static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
 {
 	int i, success = 0;
+	int node = dev_dax->target_node;
 	struct device *dev = &dev_dax->dev;
 	struct dax_kmem_data *data = dev_get_drvdata(dev);
 
@@ -198,6 +212,14 @@ static void dev_dax_kmem_remove(struct dev_dax *dev_dax)
 		kfree(data->res_name);
 		kfree(data);
 		dev_set_drvdata(dev, NULL);
+		/*
+		 * Clear the memtype association on successful unplug.
+		 * If not, we have memory blocks left which can be
+		 * offlined/onlined later. We need to keep memory_dev_type
+		 * for that. This implies this reference will be around
+		 * till next reboot.
+		 */
+		clear_node_memory_type(node, dax_slowmem_type);
 	}
 }
 #else
@@ -228,9 +250,22 @@ static int __init dax_kmem_init(void)
 	if (!kmem_name)
 		return -ENOMEM;
 
+	dax_slowmem_type = alloc_memory_type(MEMTIER_DEFAULT_DAX_ADISTANCE);
+	if (IS_ERR(dax_slowmem_type)) {
+		rc = PTR_ERR(dax_slowmem_type);
+		goto err_dax_slowmem_type;
+	}
+
 	rc = dax_driver_register(&device_dax_kmem_driver);
 	if (rc)
-		kfree_const(kmem_name);
+		goto error_dax_driver;
+
+	return rc;
+
+error_dax_driver:
+	destroy_memory_type(dax_slowmem_type);
+err_dax_slowmem_type:
+	kfree_const(kmem_name);
 	return rc;
 }
 
@@ -239,6 +274,7 @@ static void __exit dax_kmem_exit(void)
 	dax_driver_unregister(&device_dax_kmem_driver);
 	if (!any_hotremove_failed)
 		kfree_const(kmem_name);
+	destroy_memory_type(dax_slowmem_type);
 }
 
 MODULE_AUTHOR("Intel Corporation");