Merge tag 'mm-hotfixes-stable-2023-12-07-18-47' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Pull misc fixes from Andrew Morton:
 "31 hotfixes. Ten of these address pre-6.6 issues and are marked
  cc:stable. The remainder address post-6.6 issues or aren't considered
  serious enough to justify backporting"

* tag 'mm-hotfixes-stable-2023-12-07-18-47' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (31 commits)
  mm/madvise: add cond_resched() in madvise_cold_or_pageout_pte_range()
  nilfs2: prevent WARNING in nilfs_sufile_set_segment_usage()
  mm/hugetlb: have CONFIG_HUGETLB_PAGE select CONFIG_XARRAY_MULTI
  scripts/gdb: fix lx-device-list-bus and lx-device-list-class
  MAINTAINERS: drop Antti Palosaari
  highmem: fix a memory copy problem in memcpy_from_folio
  nilfs2: fix missing error check for sb_set_blocksize call
  kernel/Kconfig.kexec: drop select of KEXEC for CRASH_DUMP
  units: add missing header
  drivers/base/cpu: crash data showing should depends on KEXEC_CORE
  mm/damon/sysfs-schemes: add timeout for update_schemes_tried_regions
  scripts/gdb/tasks: fix lx-ps command error
  mm/Kconfig: make userfaultfd a menuconfig
  selftests/mm: prevent duplicate runs caused by TEST_GEN_PROGS
  mm/damon/core: copy nr_accesses when splitting region
  lib/group_cpus.c: avoid acquiring cpu hotplug lock in group_cpus_evenly
  checkstack: fix printed address
  mm/memory_hotplug: fix error handling in add_memory_resource()
  mm/memory_hotplug: add missing mem_hotplug_lock
  .mailmap: add a new address mapping for Chester Lin
  ...

1 files changed, 16 insertions, 6 deletions

diff --git a/lib/group_cpus.c b/lib/group_cpus.c
index aa3f6815bb12..ee272c4cefcc 100644
--- a/lib/group_cpus.c
+++ b/lib/group_cpus.c
@@ -366,13 +366,25 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 	if (!masks)
 		goto fail_node_to_cpumask;
 
-	/* Stabilize the cpumasks */
-	cpus_read_lock();
 	build_node_to_cpumask(node_to_cpumask);
 
+	/*
+	 * Make a local cache of 'cpu_present_mask', so the two stages
+	 * spread can observe consistent 'cpu_present_mask' without holding
+	 * cpu hotplug lock, then we can reduce deadlock risk with cpu
+	 * hotplug code.
+	 *
+	 * Here CPU hotplug may happen when reading `cpu_present_mask`, and
+	 * we can live with the case because it only affects that hotplug
+	 * CPU is handled in the 1st or 2nd stage, and either way is correct
+	 * from API user viewpoint since 2-stage spread is sort of
+	 * optimization.
+	 */
+	cpumask_copy(npresmsk, data_race(cpu_present_mask));
+
 	/* grouping present CPUs first */
 	ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask,
-				  cpu_present_mask, nmsk, masks);
+				  npresmsk, nmsk, masks);
 	if (ret < 0)
 		goto fail_build_affinity;
 	nr_present = ret;
@@ -387,15 +399,13 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 		curgrp = 0;
 	else
 		curgrp = nr_present;
-	cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
+	cpumask_andnot(npresmsk, cpu_possible_mask, npresmsk);
 	ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask,
 				  npresmsk, nmsk, masks);
 	if (ret >= 0)
 		nr_others = ret;
 
  fail_build_affinity:
-	cpus_read_unlock();
-
 	if (ret >= 0)
 		WARN_ON(nr_present + nr_others < numgrps);