Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "257 patches.

  Subsystems affected by this patch series: scripts, ocfs2, vfs, and
  mm (slab-generic, slab, slub, kconfig, dax, kasan, debug, pagecache,
  gup, swap, memcg, pagemap, mprotect, mremap, iomap, tracing, vmalloc,
  pagealloc, memory-failure, hugetlb, userfaultfd, vmscan, tools,
  memblock, oom-kill, hugetlbfs, migration, thp, readahead, nommu, ksm,
  vmstat, madvise, memory-hotplug, rmap, zsmalloc, highmem, zram,
  cleanups, kfence, and damon)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (257 commits)
  mm/damon: remove return value from before_terminate callback
  mm/damon: fix a few spelling mistakes in comments and a pr_debug message
  mm/damon: simplify stop mechanism
  Docs/admin-guide/mm/pagemap: wordsmith page flags descriptions
  Docs/admin-guide/mm/damon/start: simplify the content
  Docs/admin-guide/mm/damon/start: fix a wrong link
  Docs/admin-guide/mm/damon/start: fix wrong example commands
  mm/damon/dbgfs: add adaptive_targets list check before enable monitor_on
  mm/damon: remove unnecessary variable initialization
  Documentation/admin-guide/mm/damon: add a document for DAMON_RECLAIM
  mm/damon: introduce DAMON-based Reclamation (DAMON_RECLAIM)
  selftests/damon: support watermarks
  mm/damon/dbgfs: support watermarks
  mm/damon/schemes: activate schemes based on a watermarks mechanism
  tools/selftests/damon: update for regions prioritization of schemes
  mm/damon/dbgfs: support prioritization weights
  mm/damon/vaddr,paddr: support pageout prioritization
  mm/damon/schemes: prioritize regions within the quotas
  mm/damon/selftests: support schemes quotas
  mm/damon/dbgfs: support quotas of schemes
  ...

10 files changed, 79 insertions, 7 deletions

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 2a9695ccb65f..d0e163a02099 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -69,6 +69,13 @@
 DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key);
 DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key);
 
+/*
+ * There could be abnormal cpuset configurations for cpu or memory
+ * node binding, add this key to provide a quick low-cost judgement
+ * of the situation.
+ */
+DEFINE_STATIC_KEY_FALSE(cpusets_insane_config_key);
+
 /* See "Frequency meter" comments, below. */
 
 struct fmeter {
@@ -372,6 +379,17 @@ static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn);
 
 static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq);
 
+static inline void check_insane_mems_config(nodemask_t *nodes)
+{
+	if (!cpusets_insane_config() &&
+		movable_only_nodes(nodes)) {
+		static_branch_enable(&cpusets_insane_config_key);
+		pr_info("Unsupported (movable nodes only) cpuset configuration detected (nmask=%*pbl)!\n"
+			"Cpuset allocations might fail even with a lot of memory available.\n",
+			nodemask_pr_args(nodes));
+	}
+}
+
 /*
  * Cgroup v2 behavior is used on the "cpus" and "mems" control files when
  * on default hierarchy or when the cpuset_v2_mode flag is set by mounting
@@ -1870,6 +1888,8 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 	if (retval < 0)
 		goto done;
 
+	check_insane_mems_config(&trialcs->mems_allowed);
+
 	spin_lock_irq(&callback_lock);
 	cs->mems_allowed = trialcs->mems_allowed;
 	spin_unlock_irq(&callback_lock);
@@ -3173,6 +3193,9 @@ update_tasks:
 	cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
 	mems_updated = !nodes_equal(new_mems, cs->effective_mems);
 
+	if (mems_updated)
+		check_insane_mems_config(&new_mems);
+
 	if (is_in_v2_mode())
 		hotplug_update_tasks(cs, &new_cpus, &new_mems,
 				     cpus_updated, mems_updated);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 6fab31ea47d6..8e840fbbed7c 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -247,7 +247,7 @@ swiotlb_init(int verbose)
 	return;
 
 fail_free_mem:
-	memblock_free_early(__pa(tlb), bytes);
+	memblock_free(tlb, bytes);
 fail:
 	pr_warn("Cannot allocate buffer");
 }
diff --git a/kernel/extable.c b/kernel/extable.c
index b0ea5eb0c3b4..290661f68e6b 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -76,7 +76,7 @@ int notrace core_kernel_text(unsigned long addr)
 	    addr < (unsigned long)_etext)
 		return 1;
 
-	if (system_state < SYSTEM_RUNNING &&
+	if (system_state < SYSTEM_FREEING_INITMEM &&
 	    init_kernel_text(addr))
 		return 1;
 	return 0;
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 33400ff051a8..8347fc158d2b 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -556,6 +556,11 @@ static int kexec_walk_memblock(struct kexec_buf *kbuf,
 	if (kbuf->image->type == KEXEC_TYPE_CRASH)
 		return func(&crashk_res, kbuf);
 
+	/*
+	 * Using MEMBLOCK_NONE will properly skip MEMBLOCK_DRIVER_MANAGED. See
+	 * IORESOURCE_SYSRAM_DRIVER_MANAGED handling in
+	 * locate_mem_hole_callback().
+	 */
 	if (kbuf->top_down) {
 		for_each_free_mem_range_reverse(i, NUMA_NO_NODE, MEMBLOCK_NONE,
 						&mstart, &mend, NULL) {
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 7096384dc60f..74d371665747 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -788,6 +788,21 @@ static int very_verbose(struct lock_class *class)
  * Is this the address of a static object:
  */
 #ifdef __KERNEL__
+/*
+ * Check if an address is part of freed initmem. After initmem is freed,
+ * memory can be allocated from it, and such allocations would then have
+ * addresses within the range [_stext, _end].
+ */
+#ifndef arch_is_kernel_initmem_freed
+static int arch_is_kernel_initmem_freed(unsigned long addr)
+{
+	if (system_state < SYSTEM_FREEING_INITMEM)
+		return 0;
+
+	return init_section_contains((void *)addr, 1);
+}
+#endif
+
 static int static_obj(const void *obj)
 {
 	unsigned long start = (unsigned long) &_stext,
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 9e5dfb1896a9..013bfd6dcc34 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1166,9 +1166,9 @@ void __init setup_log_buf(int early)
 	return;
 
 err_free_descs:
-	memblock_free_ptr(new_descs, new_descs_size);
+	memblock_free(new_descs, new_descs_size);
 err_free_log_buf:
-	memblock_free_ptr(new_log_buf, new_log_buf_len);
+	memblock_free(new_log_buf, new_log_buf_len);
 }
 
 static bool __read_mostly ignore_loglevel;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 30169c7685b6..d201a7052a29 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1492,7 +1492,6 @@ static int			sched_domains_curr_level;
 int				sched_max_numa_distance;
 static int			*sched_domains_numa_distance;
 static struct cpumask		***sched_domains_numa_masks;
-int __read_mostly		node_reclaim_distance = RECLAIM_DISTANCE;
 
 static unsigned long __read_mostly *sched_numa_onlined_nodes;
 #endif
diff --git a/kernel/stacktrace.c b/kernel/stacktrace.c
index 9f8117c7cfdd..9c625257023d 100644
--- a/kernel/stacktrace.c
+++ b/kernel/stacktrace.c
@@ -13,6 +13,7 @@
 #include <linux/export.h>
 #include <linux/kallsyms.h>
 #include <linux/stacktrace.h>
+#include <linux/interrupt.h>
 
 /**
  * stack_trace_print - Print the entries in the stack trace
@@ -373,3 +374,32 @@ unsigned int stack_trace_save_user(unsigned long *store, unsigned int size)
 #endif /* CONFIG_USER_STACKTRACE_SUPPORT */
 
 #endif /* !CONFIG_ARCH_STACKWALK */
+
+static inline bool in_irqentry_text(unsigned long ptr)
+{
+	return (ptr >= (unsigned long)&__irqentry_text_start &&
+		ptr < (unsigned long)&__irqentry_text_end) ||
+		(ptr >= (unsigned long)&__softirqentry_text_start &&
+		 ptr < (unsigned long)&__softirqentry_text_end);
+}
+
+/**
+ * filter_irq_stacks - Find first IRQ stack entry in trace
+ * @entries:	Pointer to stack trace array
+ * @nr_entries:	Number of entries in the storage array
+ *
+ * Return: Number of trace entries until IRQ stack starts.
+ */
+unsigned int filter_irq_stacks(unsigned long *entries, unsigned int nr_entries)
+{
+	unsigned int i;
+
+	for (i = 0; i < nr_entries; i++) {
+		if (in_irqentry_text(entries[i])) {
+			/* Include the irqentry function into the stack. */
+			return i + 1;
+		}
+	}
+	return nr_entries;
+}
+EXPORT_SYMBOL_GPL(filter_irq_stacks);
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 257ffb993ea2..f00de83d0246 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -137,7 +137,7 @@ static void __acct_update_integrals(struct task_struct *tsk,
 	 * the rest of the math is done in xacct_add_tsk.
 	 */
 	tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm) >> 10;
-	tsk->acct_vm_mem1 += delta * tsk->mm->total_vm >> 10;
+	tsk->acct_vm_mem1 += delta * READ_ONCE(tsk->mm->total_vm) >> 10;
 }
 
 /**
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 1a7df882f55e..613917bbc4e7 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1351,7 +1351,7 @@ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work,
 	struct worker_pool *pool = pwq->pool;
 
 	/* record the work call stack in order to print it in KASAN reports */
-	kasan_record_aux_stack(work);
+	kasan_record_aux_stack_noalloc(work);
 
 	/* we own @work, set data and link */
 	set_work_pwq(work, pwq, extra_flags);