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
  ...

include/linux/memcontrol.h

@@ -183,6 +183,23 @@ struct memcg_padding {
 #define MEMCG_PADDING(name)
 #endif
 
+/*
+ * Remember four most recent foreign writebacks with dirty pages in this
+ * cgroup.  Inode sharing is expected to be uncommon and, even if we miss
+ * one in a given round, we're likely to catch it later if it keeps
+ * foreign-dirtying, so a fairly low count should be enough.
+ *
+ * See mem_cgroup_track_foreign_dirty_slowpath() for details.
+ */
+#define MEMCG_CGWB_FRN_CNT	4
+
+struct memcg_cgwb_frn {
+	u64 bdi_id;			/* bdi->id of the foreign inode */
+	int memcg_id;			/* memcg->css.id of foreign inode */
+	u64 at;				/* jiffies_64 at the time of dirtying */
+	struct wb_completion done;	/* tracks in-flight foreign writebacks */
+};
+
 /*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
@@ -307,6 +324,7 @@ struct mem_cgroup {
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct list_head cgwb_list;
 	struct wb_domain cgwb_domain;
+	struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT];
 #endif
 
 	/* List of events which userspace want to receive */
@@ -1237,6 +1255,18 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
 			 unsigned long *pheadroom, unsigned long *pdirty,
 			 unsigned long *pwriteback);
 
+void mem_cgroup_track_foreign_dirty_slowpath(struct page *page,
+					     struct bdi_writeback *wb);
+
+static inline void mem_cgroup_track_foreign_dirty(struct page *page,
+						  struct bdi_writeback *wb)
+{
+	if (unlikely(&page->mem_cgroup->css != wb->memcg_css))
+		mem_cgroup_track_foreign_dirty_slowpath(page, wb);
+}
+
+void mem_cgroup_flush_foreign(struct bdi_writeback *wb);
+
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
 static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb)
@@ -1252,6 +1282,15 @@ static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb,
 {
 }
 
+static inline void mem_cgroup_track_foreign_dirty(struct page *page,
+						  struct bdi_writeback *wb)
+{
+}
+
+static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
+{
+}
+
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
 struct sock;