Merge tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block

Pull block updates from Jens Axboe:

 - Two NVMe pull requests:
     - ana log parse fix from Anton
     - nvme quirks support for Apple devices from Ben
     - fix missing bio completion tracing for multipath stack devices
       from Hannes and Mikhail
     - IP TOS settings for nvme rdma and tcp transports from Israel
     - rq_dma_dir cleanups from Israel
     - tracing for Get LBA Status command from Minwoo
     - Some nvme-tcp cleanups from Minwoo, Potnuri and Myself
     - Some consolidation between the fabrics transports for handling
       the CAP register
     - reset race with ns scanning fix for fabrics (move fabrics
       commands to a dedicated request queue with a different lifetime
       from the admin request queue)."
     - controller reset and namespace scan races fixes
     - nvme discovery log change uevent support
     - naming improvements from Keith
     - multiple discovery controllers reject fix from James
     - some regular cleanups from various people

 - Series fixing (and re-fixing) null_blk debug printing and nr_devices
   checks (André)

 - A few pull requests from Song, with fixes from Andy, Guoqing,
   Guilherme, Neil, Nigel, and Yufen.

 - REQ_OP_ZONE_RESET_ALL support (Chaitanya)

 - Bio merge handling unification (Christoph)

 - Pick default elevator correctly for devices with special needs
   (Damien)

 - Block stats fixes (Hou)

 - Timeout and support devices nbd fixes (Mike)

 - Series fixing races around elevator switching and device add/remove
   (Ming)

 - sed-opal cleanups (Revanth)

 - Per device weight support for BFQ (Fam)

 - Support for blk-iocost, a new model that can properly account cost of
   IO workloads. (Tejun)

 - blk-cgroup writeback fixes (Tejun)

 - paride queue init fixes (zhengbin)

 - blk_set_runtime_active() cleanup (Stanley)

 - Block segment mapping optimizations (Bart)

 - lightnvm fixes (Hans/Minwoo/YueHaibing)

 - Various little fixes and cleanups

* tag 'for-5.4/block-2019-09-16' of git://git.kernel.dk/linux-block: (186 commits)
  null_blk: format pr_* logs with pr_fmt
  null_blk: match the type of parameter nr_devices
  null_blk: do not fail the module load with zero devices
  block: also check RQF_STATS in blk_mq_need_time_stamp()
  block: make rq sector size accessible for block stats
  bfq: Fix bfq linkage error
  raid5: use bio_end_sector in r5_next_bio
  raid5: remove STRIPE_OPS_REQ_PENDING
  md: add feature flag MD_FEATURE_RAID0_LAYOUT
  md/raid0: avoid RAID0 data corruption due to layout confusion.
  raid5: don't set STRIPE_HANDLE to stripe which is in batch list
  raid5: don't increment read_errors on EILSEQ return
  nvmet: fix a wrong error status returned in error log page
  nvme: send discovery log page change events to userspace
  nvme: add uevent variables for controller devices
  nvme: enable aen regardless of the presence of I/O queues
  nvme-fabrics: allow discovery subsystems accept a kato
  nvmet: Use PTR_ERR_OR_ZERO() in nvmet_init_discovery()
  nvme: Remove redundant assignment of cq vector
  nvme: Assign subsys instance from first ctrl
  ...

2 files changed, 304 insertions, 0 deletions

diff --git a/include/trace/events/iocost.h b/include/trace/events/iocost.h
new file mode 100644
index 000000000000..7ecaa65b7106
--- /dev/null
+++ b/include/trace/events/iocost.h
@@ -0,0 +1,178 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM iocost
+
+struct ioc;
+struct ioc_now;
+struct ioc_gq;
+
+#if !defined(_TRACE_BLK_IOCOST_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BLK_IOCOST_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(iocost_iocg_activate,
+
+	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+		u64 last_period, u64 cur_period, u64 vtime),
+
+	TP_ARGS(iocg, path, now, last_period, cur_period, vtime),
+
+	TP_STRUCT__entry (
+		__string(devname, ioc_name(iocg->ioc))
+		__string(cgroup, path)
+		__field(u64, now)
+		__field(u64, vnow)
+		__field(u64, vrate)
+		__field(u64, last_period)
+		__field(u64, cur_period)
+		__field(u64, last_vtime)
+		__field(u64, vtime)
+		__field(u32, weight)
+		__field(u32, inuse)
+		__field(u64, hweight_active)
+		__field(u64, hweight_inuse)
+	),
+
+	TP_fast_assign(
+		__assign_str(devname, ioc_name(iocg->ioc));
+		__assign_str(cgroup, path);
+		__entry->now = now->now;
+		__entry->vnow = now->vnow;
+		__entry->vrate = now->vrate;
+		__entry->last_period = last_period;
+		__entry->cur_period = cur_period;
+		__entry->last_vtime = iocg->last_vtime;
+		__entry->vtime = vtime;
+		__entry->weight = iocg->weight;
+		__entry->inuse = iocg->inuse;
+		__entry->hweight_active = iocg->hweight_active;
+		__entry->hweight_inuse = iocg->hweight_inuse;
+	),
+
+	TP_printk("[%s:%s] now=%llu:%llu vrate=%llu "
+		  "period=%llu->%llu vtime=%llu->%llu "
+		  "weight=%u/%u hweight=%llu/%llu",
+		__get_str(devname), __get_str(cgroup),
+		__entry->now, __entry->vnow, __entry->vrate,
+		__entry->last_period, __entry->cur_period,
+		__entry->last_vtime, __entry->vtime,
+		__entry->inuse, __entry->weight,
+		__entry->hweight_inuse, __entry->hweight_active
+	)
+);
+
+DECLARE_EVENT_CLASS(iocg_inuse_update,
+
+	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+		u32 old_inuse, u32 new_inuse,
+		u64 old_hw_inuse, u64 new_hw_inuse),
+
+	TP_ARGS(iocg, path, now, old_inuse, new_inuse,
+		old_hw_inuse, new_hw_inuse),
+
+	TP_STRUCT__entry (
+		__string(devname, ioc_name(iocg->ioc))
+		__string(cgroup, path)
+		__field(u64, now)
+		__field(u32, old_inuse)
+		__field(u32, new_inuse)
+		__field(u64, old_hweight_inuse)
+		__field(u64, new_hweight_inuse)
+	),
+
+	TP_fast_assign(
+		__assign_str(devname, ioc_name(iocg->ioc));
+		__assign_str(cgroup, path);
+		__entry->now = now->now;
+		__entry->old_inuse = old_inuse;
+		__entry->new_inuse = new_inuse;
+		__entry->old_hweight_inuse = old_hw_inuse;
+		__entry->new_hweight_inuse = new_hw_inuse;
+	),
+
+	TP_printk("[%s:%s] now=%llu inuse=%u->%u hw_inuse=%llu->%llu",
+		__get_str(devname), __get_str(cgroup), __entry->now,
+		__entry->old_inuse, __entry->new_inuse,
+		__entry->old_hweight_inuse, __entry->new_hweight_inuse
+	)
+);
+
+DEFINE_EVENT(iocg_inuse_update, iocost_inuse_takeback,
+
+	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+		u32 old_inuse, u32 new_inuse,
+		u64 old_hw_inuse, u64 new_hw_inuse),
+
+	TP_ARGS(iocg, path, now, old_inuse, new_inuse,
+		old_hw_inuse, new_hw_inuse)
+);
+
+DEFINE_EVENT(iocg_inuse_update, iocost_inuse_giveaway,
+
+	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+		u32 old_inuse, u32 new_inuse,
+		u64 old_hw_inuse, u64 new_hw_inuse),
+
+	TP_ARGS(iocg, path, now, old_inuse, new_inuse,
+		old_hw_inuse, new_hw_inuse)
+);
+
+DEFINE_EVENT(iocg_inuse_update, iocost_inuse_reset,
+
+	TP_PROTO(struct ioc_gq *iocg, const char *path, struct ioc_now *now,
+		u32 old_inuse, u32 new_inuse,
+		u64 old_hw_inuse, u64 new_hw_inuse),
+
+	TP_ARGS(iocg, path, now, old_inuse, new_inuse,
+		old_hw_inuse, new_hw_inuse)
+);
+
+TRACE_EVENT(iocost_ioc_vrate_adj,
+
+	TP_PROTO(struct ioc *ioc, u64 new_vrate, u32 (*missed_ppm)[2],
+		u32 rq_wait_pct, int nr_lagging, int nr_shortages,
+		int nr_surpluses),
+
+	TP_ARGS(ioc, new_vrate, missed_ppm, rq_wait_pct, nr_lagging, nr_shortages,
+		nr_surpluses),
+
+	TP_STRUCT__entry (
+		__string(devname, ioc_name(ioc))
+		__field(u64, old_vrate)
+		__field(u64, new_vrate)
+		__field(int, busy_level)
+		__field(u32, read_missed_ppm)
+		__field(u32, write_missed_ppm)
+		__field(u32, rq_wait_pct)
+		__field(int, nr_lagging)
+		__field(int, nr_shortages)
+		__field(int, nr_surpluses)
+	),
+
+	TP_fast_assign(
+		__assign_str(devname, ioc_name(ioc));
+		__entry->old_vrate = atomic64_read(&ioc->vtime_rate);;
+		__entry->new_vrate = new_vrate;
+		__entry->busy_level = ioc->busy_level;
+		__entry->read_missed_ppm = (*missed_ppm)[READ];
+		__entry->write_missed_ppm = (*missed_ppm)[WRITE];
+		__entry->rq_wait_pct = rq_wait_pct;
+		__entry->nr_lagging = nr_lagging;
+		__entry->nr_shortages = nr_shortages;
+		__entry->nr_surpluses = nr_surpluses;
+	),
+
+	TP_printk("[%s] vrate=%llu->%llu busy=%d missed_ppm=%u:%u rq_wait_pct=%u lagging=%d shortages=%d surpluses=%d",
+		__get_str(devname), __entry->old_vrate, __entry->new_vrate,
+		__entry->busy_level,
+		__entry->read_missed_ppm, __entry->write_missed_ppm,
+		__entry->rq_wait_pct, __entry->nr_lagging, __entry->nr_shortages,
+		__entry->nr_surpluses
+	)
+);
+
+#endif /* _TRACE_BLK_IOCOST_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index aa7f3aeac740..3a27335fce2c 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -176,6 +176,132 @@ static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *w
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 #endif	/* CREATE_TRACE_POINTS */
 
+#ifdef CONFIG_CGROUP_WRITEBACK
+TRACE_EVENT(inode_foreign_history,
+
+	TP_PROTO(struct inode *inode, struct writeback_control *wbc,
+		 unsigned int history),
+
+	TP_ARGS(inode, wbc, history),
+
+	TP_STRUCT__entry(
+		__array(char,		name, 32)
+		__field(unsigned long,	ino)
+		__field(unsigned int,	cgroup_ino)
+		__field(unsigned int,	history)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(inode_to_bdi(inode)->dev), 32);
+		__entry->ino		= inode->i_ino;
+		__entry->cgroup_ino	= __trace_wbc_assign_cgroup(wbc);
+		__entry->history	= history;
+	),
+
+	TP_printk("bdi %s: ino=%lu cgroup_ino=%u history=0x%x",
+		__entry->name,
+		__entry->ino,
+		__entry->cgroup_ino,
+		__entry->history
+	)
+);
+
+TRACE_EVENT(inode_switch_wbs,
+
+	TP_PROTO(struct inode *inode, struct bdi_writeback *old_wb,
+		 struct bdi_writeback *new_wb),
+
+	TP_ARGS(inode, old_wb, new_wb),
+
+	TP_STRUCT__entry(
+		__array(char,		name, 32)
+		__field(unsigned long,	ino)
+		__field(unsigned int,	old_cgroup_ino)
+		__field(unsigned int,	new_cgroup_ino)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name,	dev_name(old_wb->bdi->dev), 32);
+		__entry->ino		= inode->i_ino;
+		__entry->old_cgroup_ino	= __trace_wb_assign_cgroup(old_wb);
+		__entry->new_cgroup_ino	= __trace_wb_assign_cgroup(new_wb);
+	),
+
+	TP_printk("bdi %s: ino=%lu old_cgroup_ino=%u new_cgroup_ino=%u",
+		__entry->name,
+		__entry->ino,
+		__entry->old_cgroup_ino,
+		__entry->new_cgroup_ino
+	)
+);
+
+TRACE_EVENT(track_foreign_dirty,
+
+	TP_PROTO(struct page *page, struct bdi_writeback *wb),
+
+	TP_ARGS(page, wb),
+
+	TP_STRUCT__entry(
+		__array(char,		name, 32)
+		__field(u64,		bdi_id)
+		__field(unsigned long,	ino)
+		__field(unsigned int,	memcg_id)
+		__field(unsigned int,	cgroup_ino)
+		__field(unsigned int,	page_cgroup_ino)
+	),
+
+	TP_fast_assign(
+		struct address_space *mapping = page_mapping(page);
+		struct inode *inode = mapping ? mapping->host : NULL;
+
+		strncpy(__entry->name,	dev_name(wb->bdi->dev), 32);
+		__entry->bdi_id		= wb->bdi->id;
+		__entry->ino		= inode ? inode->i_ino : 0;
+		__entry->memcg_id	= wb->memcg_css->id;
+		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
+		__entry->page_cgroup_ino = page->mem_cgroup->css.cgroup->kn->id.ino;
+	),
+
+	TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%u page_cgroup_ino=%u",
+		__entry->name,
+		__entry->bdi_id,
+		__entry->ino,
+		__entry->memcg_id,
+		__entry->cgroup_ino,
+		__entry->page_cgroup_ino
+	)
+);
+
+TRACE_EVENT(flush_foreign,
+
+	TP_PROTO(struct bdi_writeback *wb, unsigned int frn_bdi_id,
+		 unsigned int frn_memcg_id),
+
+	TP_ARGS(wb, frn_bdi_id, frn_memcg_id),
+
+	TP_STRUCT__entry(
+		__array(char,		name, 32)
+		__field(unsigned int,	cgroup_ino)
+		__field(unsigned int,	frn_bdi_id)
+		__field(unsigned int,	frn_memcg_id)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name,	dev_name(wb->bdi->dev), 32);
+		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
+		__entry->frn_bdi_id	= frn_bdi_id;
+		__entry->frn_memcg_id	= frn_memcg_id;
+	),
+
+	TP_printk("bdi %s: cgroup_ino=%u frn_bdi_id=%u frn_memcg_id=%u",
+		__entry->name,
+		__entry->cgroup_ino,
+		__entry->frn_bdi_id,
+		__entry->frn_memcg_id
+	)
+);
+#endif
+
 DECLARE_EVENT_CLASS(writeback_write_inode_template,
 
 	TP_PROTO(struct inode *inode, struct writeback_control *wbc),