incoming

@@ -66,10 +66,17 @@ struct rlimit64 {
 #define _STK_LIM	(8*1024*1024)
 
 /*
- * GPG2 wants 64kB of mlocked memory, to make sure pass phrases
- * and other sensitive information are never written to disk.
+ * Limit the amount of locked memory by some sane default:
+ * root can always increase this limit if needed.
+ *
+ * The main use-cases are (1) preventing sensitive memory
+ * from being swapped; (2) real-time operations; (3) via
+ * IOURING_REGISTER_BUFFERS.
+ *
+ * The first two don't need much. The latter will take as
+ * much as it can get. 8MB is a reasonably sane default.
  */
-#define MLOCK_LIMIT	((PAGE_SIZE > 64*1024) ? PAGE_SIZE : 64*1024)
+#define MLOCK_LIMIT	((PAGE_SIZE > 8*1024*1024) ? PAGE_SIZE : 8*1024*1024)
 
 /*
  * Due to binary compatibility, the actual resource numbers

@@ -3253,8 +3253,6 @@ static struct page *next_uptodate_page(s
 			goto skip;
 		if (!PageUptodate(page) || PageReadahead(page))
 			goto skip;
-		if (PageHWPoison(page))
-			goto skip;
 		if (!trylock_page(page))
 			goto skip;
 		if (page->mapping != mapping)

@@ -20,6 +20,7 @@
  */
 
 #include <linux/math.h>
+#include <linux/sched.h>
 
 extern unsigned long loops_per_jiffy;
 

@@ -58,7 +59,18 @@ void calibrate_delay(void);
 void __attribute__((weak)) calibration_delay_done(void);
 void msleep(unsigned int msecs);
 unsigned long msleep_interruptible(unsigned int msecs);
-void usleep_range(unsigned long min, unsigned long max);
+void usleep_range_state(unsigned long min, unsigned long max,
+			unsigned int state);
+
+static inline void usleep_range(unsigned long min, unsigned long max)
+{
+	usleep_range_state(min, max, TASK_UNINTERRUPTIBLE);
+}
+
+static inline void usleep_idle_range(unsigned long min, unsigned long max)
+{
+	usleep_range_state(min, max, TASK_IDLE);
+}
 
 static inline void ssleep(unsigned int seconds)
 {

@@ -2054,26 +2054,28 @@ unsigned long msleep_interruptible(unsig
 EXPORT_SYMBOL(msleep_interruptible);
 
 /**
- * usleep_range - Sleep for an approximate time
- * @min: Minimum time in usecs to sleep
- * @max: Maximum time in usecs to sleep
+ * usleep_range_state - Sleep for an approximate time in a given state
+ * @min:	Minimum time in usecs to sleep
+ * @max:	Maximum time in usecs to sleep
+ * @state:	State of the current task that will be while sleeping
  *
  * In non-atomic context where the exact wakeup time is flexible, use
- * usleep_range() instead of udelay().  The sleep improves responsiveness
+ * usleep_range_state() instead of udelay().  The sleep improves responsiveness
  * by avoiding the CPU-hogging busy-wait of udelay(), and the range reduces
  * power usage by allowing hrtimers to take advantage of an already-
  * scheduled interrupt instead of scheduling a new one just for this sleep.
  */
-void __sched usleep_range(unsigned long min, unsigned long max)
+void __sched usleep_range_state(unsigned long min, unsigned long max,
+				unsigned int state)
 {
 	ktime_t exp = ktime_add_us(ktime_get(), min);
 	u64 delta = (u64)(max - min) * NSEC_PER_USEC;
 
 	for (;;) {
-		__set_current_state(TASK_UNINTERRUPTIBLE);
+		__set_current_state(state);
 		/* Do not return before the requested sleep time has elapsed */
 		if (!schedule_hrtimeout_range(&exp, delta, HRTIMER_MODE_ABS))
 			break;
 	}
 }
-EXPORT_SYMBOL(usleep_range);
+EXPORT_SYMBOL(usleep_range_state);

@@ -981,9 +981,9 @@ static unsigned long damos_wmark_wait_us
 static void kdamond_usleep(unsigned long usecs)
 {
 	if (usecs > 100 * 1000)
-		schedule_timeout_interruptible(usecs_to_jiffies(usecs));
+		schedule_timeout_idle(usecs_to_jiffies(usecs));
 	else
-		usleep_range(usecs, usecs + 1);
+		usleep_idle_range(usecs, usecs + 1);
 }
 
 /* Returns negative error code if it's not activated but should return */

@@ -1038,7 +1038,7 @@ static int kdamond_fn(void *data)
 				ctx->callback.after_sampling(ctx))
 			done = true;
 
-		usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
+		kdamond_usleep(ctx->sample_interval);
 
 		if (ctx->primitive.check_accesses)
 			max_nr_accesses = ctx->primitive.check_accesses(ctx);

@@ -980,7 +980,8 @@ static unsigned long damos_wmark_wait_us
 
 static void kdamond_usleep(unsigned long usecs)
 {
-	if (usecs > 100 * 1000)
+	/* See Documentation/timers/timers-howto.rst for the thresholds */
+	if (usecs > 20 * USEC_PER_MSEC)
 		schedule_timeout_idle(usecs_to_jiffies(usecs));
 	else
 		usleep_idle_range(usecs, usecs + 1);

@@ -210,10 +210,8 @@ static struct damos **str_to_schemes(con
 				&wmarks.low, &parsed);
 		if (ret != 18)
 			break;
-		if (!damos_action_valid(action)) {
-			pr_err("wrong action %d\n", action);
+		if (!damos_action_valid(action))
 			goto fail;
-		}
 
 		pos += parsed;
 		scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a,

@@ -282,7 +282,6 @@ int damon_set_targets(struct damon_ctx *
 	for (i = 0; i < nr_ids; i++) {
 		t = damon_new_target(ids[i]);
 		if (!t) {
-			pr_err("Failed to alloc damon_target\n");
 			/* The caller should do cleanup of the ids itself */
 			damon_for_each_target_safe(t, next, ctx)
 				damon_destroy_target(t);

@@ -312,16 +311,10 @@ int damon_set_attrs(struct damon_ctx *ct
 		    unsigned long aggr_int, unsigned long primitive_upd_int,
 		    unsigned long min_nr_reg, unsigned long max_nr_reg)
 {
-	if (min_nr_reg < 3) {
-		pr_err("min_nr_regions (%lu) must be at least 3\n",
-				min_nr_reg);
+	if (min_nr_reg < 3)
 		return -EINVAL;
-	}
-	if (min_nr_reg > max_nr_reg) {
-		pr_err("invalid nr_regions.  min (%lu) > max (%lu)\n",
-				min_nr_reg, max_nr_reg);
+	if (min_nr_reg > max_nr_reg)
 		return -EINVAL;
-	}
 
 	ctx->sample_interval = sample_int;
 	ctx->aggr_interval = aggr_int;

@@ -627,7 +627,6 @@ int damon_va_apply_scheme(struct damon_c
 	case DAMOS_STAT:
 		return 0;
 	default:
-		pr_warn("Wrong action %d\n", scheme->action);
 		return -EINVAL;
 	}
 

@@ -252,59 +252,62 @@ static void damon_test_apply_three_regio
 			new_three_regions, expected, ARRAY_SIZE(expected));
 }
 
-static void damon_test_split_evenly(struct kunit *test)
+static void damon_test_split_evenly_fail(struct kunit *test,
+		unsigned long start, unsigned long end, unsigned int nr_pieces)
 {
-	struct damon_ctx *c = damon_new_ctx();
-	struct damon_target *t;
-	struct damon_region *r;
-	unsigned long i;
-
-	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5),
-			-EINVAL);
-
-	t = damon_new_target(42);
-	r = damon_new_region(0, 100);
-	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 0), -EINVAL);
+	struct damon_target *t = damon_new_target(42);
+	struct damon_region *r = damon_new_region(start, end);
 
 	damon_add_region(r, t);
-	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 10), 0);
-	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 10u);
+	KUNIT_EXPECT_EQ(test,
+			damon_va_evenly_split_region(t, r, nr_pieces), -EINVAL);
+	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u);
 
-	i = 0;
 	damon_for_each_region(r, t) {
-		KUNIT_EXPECT_EQ(test, r->ar.start, i++ * 10);
-		KUNIT_EXPECT_EQ(test, r->ar.end, i * 10);
+		KUNIT_EXPECT_EQ(test, r->ar.start, start);
+		KUNIT_EXPECT_EQ(test, r->ar.end, end);
 	}
+
 	damon_free_target(t);
+}
+
+static void damon_test_split_evenly_succ(struct kunit *test,
+	unsigned long start, unsigned long end, unsigned int nr_pieces)
+{
+	struct damon_target *t = damon_new_target(42);
+	struct damon_region *r = damon_new_region(start, end);
+	unsigned long expected_width = (end - start) / nr_pieces;
+	unsigned long i = 0;
 
-	t = damon_new_target(42);
-	r = damon_new_region(5, 59);
 	damon_add_region(r, t);
-	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 5), 0);
-	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 5u);
+	KUNIT_EXPECT_EQ(test,
+			damon_va_evenly_split_region(t, r, nr_pieces), 0);
+	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), nr_pieces);
 
-	i = 0;
 	damon_for_each_region(r, t) {
-		if (i == 4)
+		if (i == nr_pieces - 1)
 			break;
-		KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i++);
-		KUNIT_EXPECT_EQ(test, r->ar.end, 5 + 10 * i);
+		KUNIT_EXPECT_EQ(test,
+				r->ar.start, start + i++ * expected_width);
+		KUNIT_EXPECT_EQ(test, r->ar.end, start + i * expected_width);
 	}
-	KUNIT_EXPECT_EQ(test, r->ar.start, 5 + 10 * i);
-	KUNIT_EXPECT_EQ(test, r->ar.end, 59ul);
+	KUNIT_EXPECT_EQ(test, r->ar.start, start + i * expected_width);
+	KUNIT_EXPECT_EQ(test, r->ar.end, end);
 	damon_free_target(t);
+}
 
-	t = damon_new_target(42);
-	r = damon_new_region(5, 6);
-	damon_add_region(r, t);
-	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(t, r, 2), -EINVAL);
-	KUNIT_EXPECT_EQ(test, damon_nr_regions(t), 1u);
+static void damon_test_split_evenly(struct kunit *test)
+{
+	struct damon_ctx *c = damon_new_ctx();
+
+	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5),
+			-EINVAL);
+
+	damon_test_split_evenly_fail(test, 0, 100, 0);
+	damon_test_split_evenly_succ(test, 0, 100, 10);
+	damon_test_split_evenly_succ(test, 5, 59, 5);
+	damon_test_split_evenly_fail(test, 5, 6, 2);
 
-	damon_for_each_region(r, t) {
-		KUNIT_EXPECT_EQ(test, r->ar.start, 5ul);
-		KUNIT_EXPECT_EQ(test, r->ar.end, 6ul);
-	}
-	damon_free_target(t);
 	damon_destroy_ctx(c);
 }
 

@@ -135,7 +135,6 @@ static void damon_do_test_apply_three_re
 				struct damon_addr_range *three_regions,
 				unsigned long *expected, int nr_expected)
 {
-	struct damon_ctx *ctx = damon_new_ctx();
 	struct damon_target *t;
 	struct damon_region *r;
 	int i;

@@ -145,7 +144,6 @@ static void damon_do_test_apply_three_re
 		r = damon_new_region(regions[i * 2], regions[i * 2 + 1]);
 		damon_add_region(r, t);
 	}
-	damon_add_target(ctx, t);
 
 	damon_va_apply_three_regions(t, three_regions);
 

@@ -154,8 +152,6 @@ static void damon_do_test_apply_three_re
 		KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]);
 		KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]);
 	}
-
-	damon_destroy_ctx(ctx);
 }
 
 /*

@@ -298,8 +294,6 @@ static void damon_test_split_evenly_succ
 
 static void damon_test_split_evenly(struct kunit *test)
 {
-	struct damon_ctx *c = damon_new_ctx();
-
 	KUNIT_EXPECT_EQ(test, damon_va_evenly_split_region(NULL, NULL, 5),
 			-EINVAL);
 

@@ -307,8 +301,6 @@ static void damon_test_split_evenly(stru
 	damon_test_split_evenly_succ(test, 0, 100, 10);
 	damon_test_split_evenly_succ(test, 5, 59, 5);
 	damon_test_split_evenly_fail(test, 5, 6, 2);
-
-	damon_destroy_ctx(c);
 }
 
 static struct kunit_case damon_test_cases[] = {

@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: SeongJae Park <[email protected]>
+ */
+
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdio.h>
+
+void write_read_with_huge_count(char *file)
+{
+	int filedesc = open(file, O_RDWR);
+	char buf[25];
+	int ret;
+
+	printf("%s %s\n", __func__, file);
+	if (filedesc < 0) {
+		fprintf(stderr, "failed opening %s\n", file);
+		exit(1);
+	}
+
+	write(filedesc, "", 0xfffffffful);
+	perror("after write: ");
+	ret = read(filedesc, buf, 0xfffffffful);
+	perror("after read: ");
+	close(filedesc);
+}
+
+int main(int argc, char *argv[])
+{
+	if (argc != 2) {
+		fprintf(stderr, "Usage: %s <file>\n", argv[0]);
+		exit(1);
+	}
+	write_read_with_huge_count(argv[1]);
+
+	return 0;
+}

@@ -5081,6 +5081,7 @@ struct loc_track {
 	unsigned long max;
 	unsigned long count;
 	struct location *loc;
+	loff_t idx;
 };
 
 static struct dentry *slab_debugfs_root;

@@ -6052,11 +6053,11 @@ __initcall(slab_sysfs_init);
 #if defined(CONFIG_SLUB_DEBUG) && defined(CONFIG_DEBUG_FS)
 static int slab_debugfs_show(struct seq_file *seq, void *v)
 {
-
-	struct location *l;
-	unsigned int idx = *(unsigned int *)v;
 	struct loc_track *t = seq->private;
+	struct location *l;
+	unsigned long idx;
 
+	idx = (unsigned long) t->idx;
 	if (idx < t->count) {
 		l = &t->loc[idx];
 

@@ -6105,16 +6106,18 @@ static void *slab_debugfs_next(struct se
 {
 	struct loc_track *t = seq->private;
 
-	v = ppos;
-	++*ppos;
+	t->idx = ++(*ppos);
 	if (*ppos <= t->count)
-		return v;
+		return ppos;
 
 	return NULL;
 }
 
 static void *slab_debugfs_start(struct seq_file *seq, loff_t *ppos)
 {
+	struct loc_track *t = seq->private;
+
+	t->idx = *ppos;
 	return ppos;
 }
 

@@ -776,24 +776,6 @@ void __mod_lruvec_kmem_state(void *p, en
 	rcu_read_unlock();
 }
 
-/*
- * mod_objcg_mlstate() may be called with irq enabled, so
- * mod_memcg_lruvec_state() should be used.
- */
-static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
-				     struct pglist_data *pgdat,
-				     enum node_stat_item idx, int nr)
-{
-	struct mem_cgroup *memcg;
-	struct lruvec *lruvec;
-
-	rcu_read_lock();
-	memcg = obj_cgroup_memcg(objcg);
-	lruvec = mem_cgroup_lruvec(memcg, pgdat);
-	mod_memcg_lruvec_state(lruvec, idx, nr);
-	rcu_read_unlock();
-}
-
 /**
  * __count_memcg_events - account VM events in a cgroup
  * @memcg: the memory cgroup

@@ -2137,41 +2119,6 @@ static bool obj_stock_flush_required(str
 }
 #endif
 
-/*
- * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
- * sequence used in this case to access content from object stock is slow.
- * To optimize for user context access, there are now two object stocks for
- * task context and interrupt context access respectively.
- *
- * The task context object stock can be accessed by disabling preemption only
- * which is cheap in non-preempt kernel. The interrupt context object stock
- * can only be accessed after disabling interrupt. User context code can
- * access interrupt object stock, but not vice versa.
- */
-static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
-{
-	struct memcg_stock_pcp *stock;
-
-	if (likely(in_task())) {
-		*pflags = 0UL;
-		preempt_disable();
-		stock = this_cpu_ptr(&memcg_stock);
-		return &stock->task_obj;
-	}
-
-	local_irq_save(*pflags);
-	stock = this_cpu_ptr(&memcg_stock);
-	return &stock->irq_obj;
-}
-
-static inline void put_obj_stock(unsigned long flags)
-{
-	if (likely(in_task()))
-		preempt_enable();
-	else
-		local_irq_restore(flags);
-}
-
 /**
  * consume_stock: Try to consume stocked charge on this cpu.
  * @memcg: memcg to consume from.

@@ -2816,6 +2763,59 @@ retry:
  */
 #define OBJCGS_CLEAR_MASK	(__GFP_DMA | __GFP_RECLAIMABLE | __GFP_ACCOUNT)
 
+/*
+ * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
+ * sequence used in this case to access content from object stock is slow.
+ * To optimize for user context access, there are now two object stocks for
+ * task context and interrupt context access respectively.
+ *
+ * The task context object stock can be accessed by disabling preemption only
+ * which is cheap in non-preempt kernel. The interrupt context object stock
+ * can only be accessed after disabling interrupt. User context code can
+ * access interrupt object stock, but not vice versa.
+ */
+static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
+{
+	struct memcg_stock_pcp *stock;
+
+	if (likely(in_task())) {
+		*pflags = 0UL;
+		preempt_disable();
+		stock = this_cpu_ptr(&memcg_stock);
+		return &stock->task_obj;
+	}
+
+	local_irq_save(*pflags);
+	stock = this_cpu_ptr(&memcg_stock);
+	return &stock->irq_obj;
+}
+
+static inline void put_obj_stock(unsigned long flags)
+{
+	if (likely(in_task()))
+		preempt_enable();
+	else
+		local_irq_restore(flags);
+}
+
+/*
+ * mod_objcg_mlstate() may be called with irq enabled, so
+ * mod_memcg_lruvec_state() should be used.
+ */
+static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
+				     struct pglist_data *pgdat,
+				     enum node_stat_item idx, int nr)
+{
+	struct mem_cgroup *memcg;
+	struct lruvec *lruvec;
+
+	rcu_read_lock();
+	memcg = obj_cgroup_memcg(objcg);
+	lruvec = mem_cgroup_lruvec(memcg, pgdat);
+	mod_memcg_lruvec_state(lruvec, idx, nr);
+	rcu_read_unlock();
+}
+
 int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s,
 				 gfp_t gfp, bool new_page)
 {

@@ -2973,7 +2973,7 @@ int __alloc_bootmem_huge_page(struct hst
 	struct huge_bootmem_page *m = NULL; /* initialize for clang */
 	int nr_nodes, node;
 
-	if (nid >= nr_online_nodes)
+	if (nid != NUMA_NO_NODE && nid >= nr_online_nodes)
 		return 0;
 	/* do node specific alloc */
 	if (nid != NUMA_NO_NODE) {

@@ -945,6 +945,13 @@ void bdi_unregister(struct backing_dev_i
 	wb_shutdown(&bdi->wb);
 	cgwb_bdi_unregister(bdi);
 
+	/*
+	 * If this BDI's min ratio has been set, use bdi_set_min_ratio() to
+	 * update the global bdi_min_ratio.
+	 */
+	if (bdi->min_ratio)
+		bdi_set_min_ratio(bdi, 0);
+
 	if (bdi->dev) {
 		bdi_debug_unregister(bdi);
 		device_unregister(bdi->dev);