Merge tag 'for-5.7/block-2020-03-29' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Online capacity resizing (Balbir)

 - Number of hardware queue change fixes (Bart)

 - null_blk fault injection addition (Bart)

 - Cleanup of queue allocation, unifying the node/no-node API
   (Christoph)

 - Cleanup of genhd, moving code to where it makes sense (Christoph)

 - Cleanup of the partition handling code (Christoph)

 - disk stat fixes/improvements (Konstantin)

 - BFQ improvements (Paolo)

 - Various fixes and improvements

* tag 'for-5.7/block-2020-03-29' of git://git.kernel.dk/linux-block: (72 commits)
  block: return NULL in blk_alloc_queue() on error
  block: move bio_map_* to blk-map.c
  Revert "blkdev: check for valid request queue before issuing flush"
  block: simplify queue allocation
  bcache: pass the make_request methods to blk_queue_make_request
  null_blk: use blk_mq_init_queue_data
  block: add a blk_mq_init_queue_data helper
  block: move the ->devnode callback to struct block_device_operations
  block: move the part_stat* helpers from genhd.h to a new header
  block: move block layer internals out of include/linux/genhd.h
  block: move guard_bio_eod to bio.c
  block: unexport get_gendisk
  block: unexport disk_map_sector_rcu
  block: unexport disk_get_part
  block: mark part_in_flight and part_in_flight_rw static
  block: mark block_depr static
  block: factor out requeue handling from dispatch code
  block/diskstats: replace time_in_queue with sum of request times
  block/diskstats: accumulate all per-cpu counters in one pass
  block/diskstats: more accurate approximation of io_ticks for slow disks
  ...

1 files changed, 192 insertions, 27 deletions

diff --git a/block/genhd.c b/block/genhd.c
index 9c2e13ce0d19..06b642b23a07 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/ctype.h>
 #include <linux/fs.h>
 #include <linux/genhd.h>
 #include <linux/kdev_t.h>
@@ -26,7 +27,7 @@
 #include "blk.h"
 
 static DEFINE_MUTEX(block_class_lock);
-struct kobject *block_depr;
+static struct kobject *block_depr;
 
 /* for extended dynamic devt allocation, currently only one major is used */
 #define NR_EXT_DEVT		(1 << MINORBITS)
@@ -46,6 +47,78 @@ static void disk_add_events(struct gendisk *disk);
 static void disk_del_events(struct gendisk *disk);
 static void disk_release_events(struct gendisk *disk);
 
+/*
+ * Set disk capacity and notify if the size is not currently
+ * zero and will not be set to zero
+ */
+void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+					bool revalidate)
+{
+	sector_t capacity = get_capacity(disk);
+
+	set_capacity(disk, size);
+
+	if (revalidate)
+		revalidate_disk(disk);
+
+	if (capacity != size && capacity != 0 && size != 0) {
+		char *envp[] = { "RESIZE=1", NULL };
+
+		kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
+	}
+}
+
+EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify);
+
+/*
+ * Format the device name of the indicated disk into the supplied buffer and
+ * return a pointer to that same buffer for convenience.
+ */
+char *disk_name(struct gendisk *hd, int partno, char *buf)
+{
+	if (!partno)
+		snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name);
+	else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1]))
+		snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno);
+	else
+		snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno);
+
+	return buf;
+}
+
+const char *bdevname(struct block_device *bdev, char *buf)
+{
+	return disk_name(bdev->bd_disk, bdev->bd_part->partno, buf);
+}
+EXPORT_SYMBOL(bdevname);
+
+#ifdef CONFIG_SMP
+static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
+{
+	int cpu;
+
+	memset(stat, 0, sizeof(struct disk_stats));
+	for_each_possible_cpu(cpu) {
+		struct disk_stats *ptr = per_cpu_ptr(part->dkstats, cpu);
+		int group;
+
+		for (group = 0; group < NR_STAT_GROUPS; group++) {
+			stat->nsecs[group] += ptr->nsecs[group];
+			stat->sectors[group] += ptr->sectors[group];
+			stat->ios[group] += ptr->ios[group];
+			stat->merges[group] += ptr->merges[group];
+		}
+
+		stat->io_ticks += ptr->io_ticks;
+	}
+}
+#else /* CONFIG_SMP */
+static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
+{
+	memcpy(stat, &part->dkstats, sizeof(struct disk_stats));
+}
+#endif /* CONFIG_SMP */
+
 void part_inc_in_flight(struct request_queue *q, struct hd_struct *part, int rw)
 {
 	if (queue_is_mq(q))
@@ -66,7 +139,8 @@ void part_dec_in_flight(struct request_queue *q, struct hd_struct *part, int rw)
 		part_stat_local_dec(&part_to_disk(part)->part0, in_flight[rw]);
 }
 
-unsigned int part_in_flight(struct request_queue *q, struct hd_struct *part)
+static unsigned int part_in_flight(struct request_queue *q,
+		struct hd_struct *part)
 {
 	int cpu;
 	unsigned int inflight;
@@ -86,8 +160,8 @@ unsigned int part_in_flight(struct request_queue *q, struct hd_struct *part)
 	return inflight;
 }
 
-void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
-		       unsigned int inflight[2])
+static void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+		unsigned int inflight[2])
 {
 	int cpu;
 
@@ -143,7 +217,6 @@ struct hd_struct *disk_get_part(struct gendisk *disk, int partno)
 
 	return part;
 }
-EXPORT_SYMBOL_GPL(disk_get_part);
 
 /**
  * disk_part_iter_init - initialize partition iterator
@@ -299,7 +372,6 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
 	}
 	return &disk->part0;
 }
-EXPORT_SYMBOL_GPL(disk_map_sector_rcu);
 
 /**
  * disk_has_partitions
@@ -944,7 +1016,6 @@ struct gendisk *get_gendisk(dev_t devt, int *partno)
 	}
 	return disk;
 }
-EXPORT_SYMBOL(get_gendisk);
 
 /**
  * bdget_disk - do bdget() by gendisk and partition number
@@ -1190,6 +1261,67 @@ static ssize_t disk_ro_show(struct device *dev,
 	return sprintf(buf, "%d\n", get_disk_ro(disk) ? 1 : 0);
 }
 
+ssize_t part_size_show(struct device *dev,
+		       struct device_attribute *attr, char *buf)
+{
+	struct hd_struct *p = dev_to_part(dev);
+
+	return sprintf(buf, "%llu\n",
+		(unsigned long long)part_nr_sects_read(p));
+}
+
+ssize_t part_stat_show(struct device *dev,
+		       struct device_attribute *attr, char *buf)
+{
+	struct hd_struct *p = dev_to_part(dev);
+	struct request_queue *q = part_to_disk(p)->queue;
+	struct disk_stats stat;
+	unsigned int inflight;
+
+	part_stat_read_all(p, &stat);
+	inflight = part_in_flight(q, p);
+
+	return sprintf(buf,
+		"%8lu %8lu %8llu %8u "
+		"%8lu %8lu %8llu %8u "
+		"%8u %8u %8u "
+		"%8lu %8lu %8llu %8u "
+		"%8lu %8u"
+		"\n",
+		stat.ios[STAT_READ],
+		stat.merges[STAT_READ],
+		(unsigned long long)stat.sectors[STAT_READ],
+		(unsigned int)div_u64(stat.nsecs[STAT_READ], NSEC_PER_MSEC),
+		stat.ios[STAT_WRITE],
+		stat.merges[STAT_WRITE],
+		(unsigned long long)stat.sectors[STAT_WRITE],
+		(unsigned int)div_u64(stat.nsecs[STAT_WRITE], NSEC_PER_MSEC),
+		inflight,
+		jiffies_to_msecs(stat.io_ticks),
+		(unsigned int)div_u64(stat.nsecs[STAT_READ] +
+				      stat.nsecs[STAT_WRITE] +
+				      stat.nsecs[STAT_DISCARD] +
+				      stat.nsecs[STAT_FLUSH],
+						NSEC_PER_MSEC),
+		stat.ios[STAT_DISCARD],
+		stat.merges[STAT_DISCARD],
+		(unsigned long long)stat.sectors[STAT_DISCARD],
+		(unsigned int)div_u64(stat.nsecs[STAT_DISCARD], NSEC_PER_MSEC),
+		stat.ios[STAT_FLUSH],
+		(unsigned int)div_u64(stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC));
+}
+
+ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	struct hd_struct *p = dev_to_part(dev);
+	struct request_queue *q = part_to_disk(p)->queue;
+	unsigned int inflight[2];
+
+	part_in_flight_rw(q, p, inflight);
+	return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
+}
+
 static ssize_t disk_capability_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
@@ -1228,10 +1360,33 @@ static DEVICE_ATTR(capability, 0444, disk_capability_show, NULL);
 static DEVICE_ATTR(stat, 0444, part_stat_show, NULL);
 static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL);
 static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store);
+
 #ifdef CONFIG_FAIL_MAKE_REQUEST
+ssize_t part_fail_show(struct device *dev,
+		       struct device_attribute *attr, char *buf)
+{
+	struct hd_struct *p = dev_to_part(dev);
+
+	return sprintf(buf, "%d\n", p->make_it_fail);
+}
+
+ssize_t part_fail_store(struct device *dev,
+			struct device_attribute *attr,
+			const char *buf, size_t count)
+{
+	struct hd_struct *p = dev_to_part(dev);
+	int i;
+
+	if (count > 0 && sscanf(buf, "%d", &i) > 0)
+		p->make_it_fail = (i == 0) ? 0 : 1;
+
+	return count;
+}
+
 static struct device_attribute dev_attr_fail =
 	__ATTR(make-it-fail, 0644, part_fail_show, part_fail_store);
-#endif
+#endif /* CONFIG_FAIL_MAKE_REQUEST */
+
 #ifdef CONFIG_FAIL_IO_TIMEOUT
 static struct device_attribute dev_attr_fail_timeout =
 	__ATTR(io-timeout-fail, 0644, part_timeout_show, part_timeout_store);
@@ -1378,8 +1533,8 @@ static char *block_devnode(struct device *dev, umode_t *mode,
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
-	if (disk->devnode)
-		return disk->devnode(disk, mode);
+	if (disk->fops->devnode)
+		return disk->fops->devnode(disk, mode);
 	return NULL;
 }
 
@@ -1405,6 +1560,7 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 	struct hd_struct *hd;
 	char buf[BDEVNAME_SIZE];
 	unsigned int inflight;
+	struct disk_stats stat;
 
 	/*
 	if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next)
@@ -1416,7 +1572,9 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 
 	disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
 	while ((hd = disk_part_iter_next(&piter))) {
+		part_stat_read_all(hd, &stat);
 		inflight = part_in_flight(gp->queue, hd);
+
 		seq_printf(seqf, "%4d %7d %s "
 			   "%lu %lu %lu %u "
 			   "%lu %lu %lu %u "
@@ -1426,23 +1584,31 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   "\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
-			   part_stat_read(hd, ios[STAT_READ]),
-			   part_stat_read(hd, merges[STAT_READ]),
-			   part_stat_read(hd, sectors[STAT_READ]),
-			   (unsigned int)part_stat_read_msecs(hd, STAT_READ),
-			   part_stat_read(hd, ios[STAT_WRITE]),
-			   part_stat_read(hd, merges[STAT_WRITE]),
-			   part_stat_read(hd, sectors[STAT_WRITE]),
-			   (unsigned int)part_stat_read_msecs(hd, STAT_WRITE),
+			   stat.ios[STAT_READ],
+			   stat.merges[STAT_READ],
+			   stat.sectors[STAT_READ],
+			   (unsigned int)div_u64(stat.nsecs[STAT_READ],
+							NSEC_PER_MSEC),
+			   stat.ios[STAT_WRITE],
+			   stat.merges[STAT_WRITE],
+			   stat.sectors[STAT_WRITE],
+			   (unsigned int)div_u64(stat.nsecs[STAT_WRITE],
+							NSEC_PER_MSEC),
 			   inflight,
-			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
-			   jiffies_to_msecs(part_stat_read(hd, time_in_queue)),
-			   part_stat_read(hd, ios[STAT_DISCARD]),
-			   part_stat_read(hd, merges[STAT_DISCARD]),
-			   part_stat_read(hd, sectors[STAT_DISCARD]),
-			   (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD),
-			   part_stat_read(hd, ios[STAT_FLUSH]),
-			   (unsigned int)part_stat_read_msecs(hd, STAT_FLUSH)
+			   jiffies_to_msecs(stat.io_ticks),
+			   (unsigned int)div_u64(stat.nsecs[STAT_READ] +
+						 stat.nsecs[STAT_WRITE] +
+						 stat.nsecs[STAT_DISCARD] +
+						 stat.nsecs[STAT_FLUSH],
+							NSEC_PER_MSEC),
+			   stat.ios[STAT_DISCARD],
+			   stat.merges[STAT_DISCARD],
+			   stat.sectors[STAT_DISCARD],
+			   (unsigned int)div_u64(stat.nsecs[STAT_DISCARD],
+						 NSEC_PER_MSEC),
+			   stat.ios[STAT_FLUSH],
+			   (unsigned int)div_u64(stat.nsecs[STAT_FLUSH],
+						 NSEC_PER_MSEC)
 			);
 	}
 	disk_part_iter_exit(&piter);
@@ -1499,7 +1665,6 @@ dev_t blk_lookup_devt(const char *name, int partno)
 	class_dev_iter_exit(&iter);
 	return devt;
 }
-EXPORT_SYMBOL(blk_lookup_devt);
 
 struct gendisk *__alloc_disk_node(int minors, int node_id)
 {