Merge tag 'for-6.3/block-2023-02-16' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - NVMe updates via Christoph:
      - Small improvements to the logging functionality (Amit Engel)
      - Authentication cleanups (Hannes Reinecke)
      - Cleanup and optimize the DMA mapping cod in the PCIe driver
        (Keith Busch)
      - Work around the command effects for Format NVM (Keith Busch)
      - Misc cleanups (Keith Busch, Christoph Hellwig)
      - Fix and cleanup freeing single sgl (Keith Busch)

 - MD updates via Song:
      - Fix a rare crash during the takeover process
      - Don't update recovery_cp when curr_resync is ACTIVE
      - Free writes_pending in md_stop
      - Change active_io to percpu

 - Updates to drbd, inching us closer to unifying the out-of-tree driver
   with the in-tree one (Andreas, Christoph, Lars, Robert)

 - BFQ update adding support for multi-actuator drives (Paolo, Federico,
   Davide)

 - Make brd compliant with REQ_NOWAIT (me)

 - Fix for IOPOLL and queue entering, fixing stalled IO waiting on
   timeouts (me)

 - Fix for REQ_NOWAIT with multiple bios (me)

 - Fix memory leak in blktrace cleanup (Greg)

 - Clean up sbitmap and fix a potential hang (Kemeng)

 - Clean up some bits in BFQ, and fix a bug in the request injection
   (Kemeng)

 - Clean up the request allocation and issue code, and fix some bugs
   related to that (Kemeng)

 - ublk updates and fixes:
      - Add support for unprivileged ublk (Ming)
      - Improve device deletion handling (Ming)
      - Misc (Liu, Ziyang)

 - s390 dasd fixes (Alexander, Qiheng)

 - Improve utility of request caching and fixes (Anuj, Xiao)

 - zoned cleanups (Pankaj)

 - More constification for kobjs (Thomas)

 - blk-iocost cleanups (Yu)

 - Remove bio splitting from drivers that don't need it (Christoph)

 - Switch blk-cgroups to use struct gendisk. Some of this is now
   incomplete as select late reverts were done. (Christoph)

 - Add bvec initialization helpers, and convert callers to use that
   rather than open-coding it (Christoph)

 - Misc fixes and cleanups (Jinke, Keith, Arnd, Bart, Li, Martin,
   Matthew, Ulf, Zhong)

* tag 'for-6.3/block-2023-02-16' of git://git.kernel.dk/linux: (169 commits)
  brd: use radix_tree_maybe_preload instead of radix_tree_preload
  block: use proper return value from bio_failfast()
  block: bio-integrity: Copy flags when bio_integrity_payload is cloned
  block: Fix io statistics for cgroup in throttle path
  brd: mark as nowait compatible
  brd: check for REQ_NOWAIT and set correct page allocation mask
  brd: return 0/-error from brd_insert_page()
  block: sync mixed merged request's failfast with 1st bio's
  Revert "blk-cgroup: pin the gendisk in struct blkcg_gq"
  Revert "blk-cgroup: pass a gendisk to blkg_lookup"
  Revert "blk-cgroup: delay blk-cgroup initialization until add_disk"
  Revert "blk-cgroup: delay calling blkcg_exit_disk until disk_release"
  Revert "blk-cgroup: move the cgroup information to struct gendisk"
  nvme-pci: remove iod use_sgls
  nvme-pci: fix freeing single sgl
  block: ublk: check IO buffer based on flag need_get_data
  s390/dasd: Fix potential memleak in dasd_eckd_init()
  s390/dasd: sort out physical vs virtual pointers usage
  block: Remove the ALLOC_CACHE_SLACK constant
  block: make kobj_type structures constant
  ...

8 files changed, 228 insertions, 120 deletions

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 43d4e073b111..b9637d63e6f0 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -288,6 +288,7 @@ struct queue_limits {
 	unsigned int		max_dev_sectors;
 	unsigned int		chunk_sectors;
 	unsigned int		max_sectors;
+	unsigned int		max_user_sectors;
 	unsigned int		max_segment_size;
 	unsigned int		physical_block_size;
 	unsigned int		logical_block_size;
@@ -484,6 +485,7 @@ struct request_queue {
 	DECLARE_BITMAP		(blkcg_pols, BLKCG_MAX_POLS);
 	struct blkcg_gq		*root_blkg;
 	struct list_head	blkg_list;
+	struct mutex		blkcg_mutex;
 #endif
 
 	struct queue_limits	limits;
@@ -1095,11 +1097,12 @@ static inline bool bdev_is_partition(struct block_device *bdev)
 enum blk_default_limits {
 	BLK_MAX_SEGMENTS	= 128,
 	BLK_SAFE_MAX_SECTORS	= 255,
-	BLK_DEF_MAX_SECTORS	= 2560,
 	BLK_MAX_SEGMENT_SIZE	= 65536,
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
 
+#define BLK_DEF_MAX_SECTORS 2560u
+
 static inline unsigned long queue_segment_boundary(const struct request_queue *q)
 {
 	return q->limits.seg_boundary_mask;
@@ -1283,12 +1286,12 @@ static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
 
 static inline bool bdev_is_zoned(struct block_device *bdev)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return blk_queue_is_zoned(q);
+	return blk_queue_is_zoned(bdev_get_queue(bdev));
+}
 
-	return false;
+static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec)
+{
+	return disk_zone_no(bdev->bd_disk, sec);
 }
 
 static inline bool bdev_op_is_zoned_write(struct block_device *bdev,
@@ -1309,6 +1312,18 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 	return q->limits.chunk_sectors;
 }
 
+static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev,
+						   sector_t sector)
+{
+	return sector & (bdev_zone_sectors(bdev) - 1);
+}
+
+static inline bool bdev_is_zone_start(struct block_device *bdev,
+				      sector_t sector)
+{
+	return bdev_offset_from_zone_start(bdev, sector) == 0;
+}
+
 static inline int queue_dma_alignment(const struct request_queue *q)
 {
 	return q ? q->limits.dma_alignment : 511;
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 35c25dff651a..555aae5448ae 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -12,7 +12,6 @@
 #include <linux/errno.h>
 #include <linux/limits.h>
 #include <linux/minmax.h>
-#include <linux/mm.h>
 #include <linux/types.h>
 
 struct page;
@@ -35,6 +34,46 @@ struct bio_vec {
 	unsigned int	bv_offset;
 };
 
+/**
+ * bvec_set_page - initialize a bvec based off a struct page
+ * @bv:		bvec to initialize
+ * @page:	page the bvec should point to
+ * @len:	length of the bvec
+ * @offset:	offset into the page
+ */
+static inline void bvec_set_page(struct bio_vec *bv, struct page *page,
+		unsigned int len, unsigned int offset)
+{
+	bv->bv_page = page;
+	bv->bv_len = len;
+	bv->bv_offset = offset;
+}
+
+/**
+ * bvec_set_folio - initialize a bvec based off a struct folio
+ * @bv:		bvec to initialize
+ * @folio:	folio the bvec should point to
+ * @len:	length of the bvec
+ * @offset:	offset into the folio
+ */
+static inline void bvec_set_folio(struct bio_vec *bv, struct folio *folio,
+		unsigned int len, unsigned int offset)
+{
+	bvec_set_page(bv, &folio->page, len, offset);
+}
+
+/**
+ * bvec_set_virt - initialize a bvec based on a virtual address
+ * @bv:		bvec to initialize
+ * @vaddr:	virtual address to set the bvec to
+ * @len:	length of the bvec
+ */
+static inline void bvec_set_virt(struct bio_vec *bv, void *vaddr,
+		unsigned int len)
+{
+	bvec_set_page(bv, virt_to_page(vaddr), len, offset_in_page(vaddr));
+}
+
 struct bvec_iter {
 	sector_t		bi_sector;	/* device address in 512 byte
 						   sectors */
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 5755537b51b1..5468a2399d48 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -38,13 +38,6 @@
 
 #endif
 
-extern const char *drbd_buildtag(void);
-#define REL_VERSION "8.4.11"
-#define API_VERSION 1
-#define PRO_VERSION_MIN 86
-#define PRO_VERSION_MAX 101
-
-
 enum drbd_io_error_p {
 	EP_PASS_ON, /* FIXME should the better be named "Ignore"? */
 	EP_CALL_HELPER,
diff --git a/include/linux/drbd_config.h b/include/linux/drbd_config.h
new file mode 100644
index 000000000000..d215365c6bb1
--- /dev/null
+++ b/include/linux/drbd_config.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * drbd_config.h
+ * DRBD's compile time configuration.
+ */
+
+#ifndef DRBD_CONFIG_H
+#define DRBD_CONFIG_H
+
+extern const char *drbd_buildtag(void);
+
+#define REL_VERSION "8.4.11"
+#define PRO_VERSION_MIN 86
+#define PRO_VERSION_MAX 101
+
+#endif
diff --git a/include/linux/drbd_genl_api.h b/include/linux/drbd_genl_api.h
index bd62efc29002..70682c058027 100644
--- a/include/linux/drbd_genl_api.h
+++ b/include/linux/drbd_genl_api.h
@@ -47,7 +47,7 @@ enum drbd_state_info_bcast_reason {
 #undef linux
 
 #include <linux/drbd.h>
-#define GENL_MAGIC_VERSION	API_VERSION
+#define GENL_MAGIC_VERSION	1
 #define GENL_MAGIC_FAMILY	drbd
 #define GENL_MAGIC_FAMILY_HDRSZ	sizeof(struct drbd_genlmsghdr)
 #define GENL_MAGIC_INCLUDE_FILE <linux/drbd_genl.h>
diff --git a/include/linux/drbd_limits.h b/include/linux/drbd_limits.h
index 9e33f7038bea..5b042fb427e9 100644
--- a/include/linux/drbd_limits.h
+++ b/include/linux/drbd_limits.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0 */
+/* SPDX-License-Identifier: GPL-2.0-only */
 /*
   drbd_limits.h
   This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
@@ -16,123 +16,123 @@
 
 #define DEBUG_RANGE_CHECK 0
 
-#define DRBD_MINOR_COUNT_MIN 1
-#define DRBD_MINOR_COUNT_MAX 255
-#define DRBD_MINOR_COUNT_DEF 32
+#define DRBD_MINOR_COUNT_MIN 1U
+#define DRBD_MINOR_COUNT_MAX 255U
+#define DRBD_MINOR_COUNT_DEF 32U
 #define DRBD_MINOR_COUNT_SCALE '1'
 
-#define DRBD_VOLUME_MAX 65535
+#define DRBD_VOLUME_MAX 65534U
 
-#define DRBD_DIALOG_REFRESH_MIN 0
-#define DRBD_DIALOG_REFRESH_MAX 600
+#define DRBD_DIALOG_REFRESH_MIN 0U
+#define DRBD_DIALOG_REFRESH_MAX 600U
 #define DRBD_DIALOG_REFRESH_SCALE '1'
 
 /* valid port number */
-#define DRBD_PORT_MIN 1
-#define DRBD_PORT_MAX 0xffff
+#define DRBD_PORT_MIN 1U
+#define DRBD_PORT_MAX 0xffffU
 #define DRBD_PORT_SCALE '1'
 
 /* startup { */
   /* if you want more than 3.4 days, disable */
-#define DRBD_WFC_TIMEOUT_MIN 0
-#define DRBD_WFC_TIMEOUT_MAX 300000
-#define DRBD_WFC_TIMEOUT_DEF 0
+#define DRBD_WFC_TIMEOUT_MIN 0U
+#define DRBD_WFC_TIMEOUT_MAX 300000U
+#define DRBD_WFC_TIMEOUT_DEF 0U
 #define DRBD_WFC_TIMEOUT_SCALE '1'
 
-#define DRBD_DEGR_WFC_TIMEOUT_MIN 0
-#define DRBD_DEGR_WFC_TIMEOUT_MAX 300000
-#define DRBD_DEGR_WFC_TIMEOUT_DEF 0
+#define DRBD_DEGR_WFC_TIMEOUT_MIN 0U
+#define DRBD_DEGR_WFC_TIMEOUT_MAX 300000U
+#define DRBD_DEGR_WFC_TIMEOUT_DEF 0U
 #define DRBD_DEGR_WFC_TIMEOUT_SCALE '1'
 
-#define DRBD_OUTDATED_WFC_TIMEOUT_MIN 0
-#define DRBD_OUTDATED_WFC_TIMEOUT_MAX 300000
-#define DRBD_OUTDATED_WFC_TIMEOUT_DEF 0
+#define DRBD_OUTDATED_WFC_TIMEOUT_MIN 0U
+#define DRBD_OUTDATED_WFC_TIMEOUT_MAX 300000U
+#define DRBD_OUTDATED_WFC_TIMEOUT_DEF 0U
 #define DRBD_OUTDATED_WFC_TIMEOUT_SCALE '1'
 /* }*/
 
 /* net { */
   /* timeout, unit centi seconds
    * more than one minute timeout is not useful */
-#define DRBD_TIMEOUT_MIN 1
-#define DRBD_TIMEOUT_MAX 600
-#define DRBD_TIMEOUT_DEF 60       /* 6 seconds */
+#define DRBD_TIMEOUT_MIN 1U
+#define DRBD_TIMEOUT_MAX 600U
+#define DRBD_TIMEOUT_DEF 60U       /* 6 seconds */
 #define DRBD_TIMEOUT_SCALE '1'
 
  /* If backing disk takes longer than disk_timeout, mark the disk as failed */
-#define DRBD_DISK_TIMEOUT_MIN 0    /* 0 = disabled */
-#define DRBD_DISK_TIMEOUT_MAX 6000 /* 10 Minutes */
-#define DRBD_DISK_TIMEOUT_DEF 0    /* disabled */
+#define DRBD_DISK_TIMEOUT_MIN 0U    /* 0 = disabled */
+#define DRBD_DISK_TIMEOUT_MAX 6000U /* 10 Minutes */
+#define DRBD_DISK_TIMEOUT_DEF 0U    /* disabled */
 #define DRBD_DISK_TIMEOUT_SCALE '1'
 
   /* active connection retries when C_WF_CONNECTION */
-#define DRBD_CONNECT_INT_MIN 1
-#define DRBD_CONNECT_INT_MAX 120
-#define DRBD_CONNECT_INT_DEF 10   /* seconds */
+#define DRBD_CONNECT_INT_MIN 1U
+#define DRBD_CONNECT_INT_MAX 120U
+#define DRBD_CONNECT_INT_DEF 10U   /* seconds */
 #define DRBD_CONNECT_INT_SCALE '1'
 
   /* keep-alive probes when idle */
-#define DRBD_PING_INT_MIN 1
-#define DRBD_PING_INT_MAX 120
-#define DRBD_PING_INT_DEF 10
+#define DRBD_PING_INT_MIN 1U
+#define DRBD_PING_INT_MAX 120U
+#define DRBD_PING_INT_DEF 10U
 #define DRBD_PING_INT_SCALE '1'
 
  /* timeout for the ping packets.*/
-#define DRBD_PING_TIMEO_MIN  1
-#define DRBD_PING_TIMEO_MAX  300
-#define DRBD_PING_TIMEO_DEF  5
+#define DRBD_PING_TIMEO_MIN  1U
+#define DRBD_PING_TIMEO_MAX  300U
+#define DRBD_PING_TIMEO_DEF  5U
 #define DRBD_PING_TIMEO_SCALE '1'
 
   /* max number of write requests between write barriers */
-#define DRBD_MAX_EPOCH_SIZE_MIN 1
-#define DRBD_MAX_EPOCH_SIZE_MAX 20000
-#define DRBD_MAX_EPOCH_SIZE_DEF 2048
+#define DRBD_MAX_EPOCH_SIZE_MIN 1U
+#define DRBD_MAX_EPOCH_SIZE_MAX 20000U
+#define DRBD_MAX_EPOCH_SIZE_DEF 2048U
 #define DRBD_MAX_EPOCH_SIZE_SCALE '1'
 
   /* I don't think that a tcp send buffer of more than 10M is useful */
-#define DRBD_SNDBUF_SIZE_MIN  0
-#define DRBD_SNDBUF_SIZE_MAX  (10<<20)
-#define DRBD_SNDBUF_SIZE_DEF  0
+#define DRBD_SNDBUF_SIZE_MIN  0U
+#define DRBD_SNDBUF_SIZE_MAX  (10U<<20)
+#define DRBD_SNDBUF_SIZE_DEF  0U
 #define DRBD_SNDBUF_SIZE_SCALE '1'
 
-#define DRBD_RCVBUF_SIZE_MIN  0
-#define DRBD_RCVBUF_SIZE_MAX  (10<<20)
-#define DRBD_RCVBUF_SIZE_DEF  0
+#define DRBD_RCVBUF_SIZE_MIN  0U
+#define DRBD_RCVBUF_SIZE_MAX  (10U<<20)
+#define DRBD_RCVBUF_SIZE_DEF  0U
 #define DRBD_RCVBUF_SIZE_SCALE '1'
 
   /* @4k PageSize -> 128kB - 512MB */
-#define DRBD_MAX_BUFFERS_MIN  32
-#define DRBD_MAX_BUFFERS_MAX  131072
-#define DRBD_MAX_BUFFERS_DEF  2048
+#define DRBD_MAX_BUFFERS_MIN  32U
+#define DRBD_MAX_BUFFERS_MAX  131072U
+#define DRBD_MAX_BUFFERS_DEF  2048U
 #define DRBD_MAX_BUFFERS_SCALE '1'
 
   /* @4k PageSize -> 4kB - 512MB */
-#define DRBD_UNPLUG_WATERMARK_MIN  1
-#define DRBD_UNPLUG_WATERMARK_MAX  131072
+#define DRBD_UNPLUG_WATERMARK_MIN  1U
+#define DRBD_UNPLUG_WATERMARK_MAX  131072U
 #define DRBD_UNPLUG_WATERMARK_DEF (DRBD_MAX_BUFFERS_DEF/16)
 #define DRBD_UNPLUG_WATERMARK_SCALE '1'
 
   /* 0 is disabled.
    * 200 should be more than enough even for very short timeouts */
-#define DRBD_KO_COUNT_MIN  0
-#define DRBD_KO_COUNT_MAX  200
-#define DRBD_KO_COUNT_DEF  7
+#define DRBD_KO_COUNT_MIN  0U
+#define DRBD_KO_COUNT_MAX  200U
+#define DRBD_KO_COUNT_DEF  7U
 #define DRBD_KO_COUNT_SCALE '1'
 /* } */
 
 /* syncer { */
   /* FIXME allow rate to be zero? */
-#define DRBD_RESYNC_RATE_MIN 1
+#define DRBD_RESYNC_RATE_MIN 1U
 /* channel bonding 10 GbE, or other hardware */
 #define DRBD_RESYNC_RATE_MAX (4 << 20)
-#define DRBD_RESYNC_RATE_DEF 250
+#define DRBD_RESYNC_RATE_DEF 250U
 #define DRBD_RESYNC_RATE_SCALE 'k'  /* kilobytes */
 
-#define DRBD_AL_EXTENTS_MIN  67
+#define DRBD_AL_EXTENTS_MIN  67U
   /* we use u16 as "slot number", (u16)~0 is "FREE".
    * If you use >= 292 kB on-disk ring buffer,
    * this is the maximum you can use: */
-#define DRBD_AL_EXTENTS_MAX  0xfffe
-#define DRBD_AL_EXTENTS_DEF  1237
+#define DRBD_AL_EXTENTS_MAX  0xfffeU
+#define DRBD_AL_EXTENTS_DEF  1237U
 #define DRBD_AL_EXTENTS_SCALE '1'
 
 #define DRBD_MINOR_NUMBER_MIN  -1
@@ -147,9 +147,9 @@
  * the upper limit with 64bit kernel, enough ram and flexible meta data
  * is 1 PiB, currently. */
 /* DRBD_MAX_SECTORS */
-#define DRBD_DISK_SIZE_MIN  0
-#define DRBD_DISK_SIZE_MAX  (1 * (2LLU << 40))
-#define DRBD_DISK_SIZE_DEF  0 /* = disabled = no user size... */
+#define DRBD_DISK_SIZE_MIN  0LLU
+#define DRBD_DISK_SIZE_MAX  (1LLU * (2LLU << 40))
+#define DRBD_DISK_SIZE_DEF  0LLU /* = disabled = no user size... */
 #define DRBD_DISK_SIZE_SCALE 's'  /* sectors */
 
 #define DRBD_ON_IO_ERROR_DEF EP_DETACH
@@ -162,39 +162,39 @@
 #define DRBD_ON_CONGESTION_DEF OC_BLOCK
 #define DRBD_READ_BALANCING_DEF RB_PREFER_LOCAL
 
-#define DRBD_MAX_BIO_BVECS_MIN 0
-#define DRBD_MAX_BIO_BVECS_MAX 128
-#define DRBD_MAX_BIO_BVECS_DEF 0
+#define DRBD_MAX_BIO_BVECS_MIN 0U
+#define DRBD_MAX_BIO_BVECS_MAX 128U
+#define DRBD_MAX_BIO_BVECS_DEF 0U
 #define DRBD_MAX_BIO_BVECS_SCALE '1'
 
-#define DRBD_C_PLAN_AHEAD_MIN  0
-#define DRBD_C_PLAN_AHEAD_MAX  300
-#define DRBD_C_PLAN_AHEAD_DEF  20
+#define DRBD_C_PLAN_AHEAD_MIN  0U
+#define DRBD_C_PLAN_AHEAD_MAX  300U
+#define DRBD_C_PLAN_AHEAD_DEF  20U
 #define DRBD_C_PLAN_AHEAD_SCALE '1'
 
-#define DRBD_C_DELAY_TARGET_MIN 1
-#define DRBD_C_DELAY_TARGET_MAX 100
-#define DRBD_C_DELAY_TARGET_DEF 10
+#define DRBD_C_DELAY_TARGET_MIN 1U
+#define DRBD_C_DELAY_TARGET_MAX 100U
+#define DRBD_C_DELAY_TARGET_DEF 10U
 #define DRBD_C_DELAY_TARGET_SCALE '1'
 
-#define DRBD_C_FILL_TARGET_MIN 0
-#define DRBD_C_FILL_TARGET_MAX (1<<20) /* 500MByte in sec */
-#define DRBD_C_FILL_TARGET_DEF 100 /* Try to place 50KiB in socket send buffer during resync */
+#define DRBD_C_FILL_TARGET_MIN 0U
+#define DRBD_C_FILL_TARGET_MAX (1U<<20) /* 500MByte in sec */
+#define DRBD_C_FILL_TARGET_DEF 100U /* Try to place 50KiB in socket send buffer during resync */
 #define DRBD_C_FILL_TARGET_SCALE 's'  /* sectors */
 
-#define DRBD_C_MAX_RATE_MIN     250
-#define DRBD_C_MAX_RATE_MAX     (4 << 20)
-#define DRBD_C_MAX_RATE_DEF     102400
+#define DRBD_C_MAX_RATE_MIN     250U
+#define DRBD_C_MAX_RATE_MAX     (4U << 20)
+#define DRBD_C_MAX_RATE_DEF     102400U
 #define DRBD_C_MAX_RATE_SCALE	'k'  /* kilobytes */
 
-#define DRBD_C_MIN_RATE_MIN     0
-#define DRBD_C_MIN_RATE_MAX     (4 << 20)
-#define DRBD_C_MIN_RATE_DEF     250
+#define DRBD_C_MIN_RATE_MIN     0U
+#define DRBD_C_MIN_RATE_MAX     (4U << 20)
+#define DRBD_C_MIN_RATE_DEF     250U
 #define DRBD_C_MIN_RATE_SCALE	'k'  /* kilobytes */
 
-#define DRBD_CONG_FILL_MIN	0
-#define DRBD_CONG_FILL_MAX	(10<<21) /* 10GByte in sectors */
-#define DRBD_CONG_FILL_DEF	0
+#define DRBD_CONG_FILL_MIN	0U
+#define DRBD_CONG_FILL_MAX	(10U<<21) /* 10GByte in sectors */
+#define DRBD_CONG_FILL_DEF	0U
 #define DRBD_CONG_FILL_SCALE	's'  /* sectors */
 
 #define DRBD_CONG_EXTENTS_MIN	DRBD_AL_EXTENTS_MIN
@@ -204,48 +204,48 @@
 
 #define DRBD_PROTOCOL_DEF DRBD_PROT_C
 
-#define DRBD_DISK_BARRIER_DEF	0
-#define DRBD_DISK_FLUSHES_DEF	1
-#define DRBD_DISK_DRAIN_DEF	1
-#define DRBD_MD_FLUSHES_DEF	1
-#define DRBD_TCP_CORK_DEF	1
-#define DRBD_AL_UPDATES_DEF     1
+#define DRBD_DISK_BARRIER_DEF	0U
+#define DRBD_DISK_FLUSHES_DEF	1U
+#define DRBD_DISK_DRAIN_DEF	1U
+#define DRBD_MD_FLUSHES_DEF	1U
+#define DRBD_TCP_CORK_DEF	1U
+#define DRBD_AL_UPDATES_DEF     1U
 
 /* We used to ignore the discard_zeroes_data setting.
  * To not change established (and expected) behaviour,
  * by default assume that, for discard_zeroes_data=0,
  * we can make that an effective discard_zeroes_data=1,
  * if we only explicitly zero-out unaligned partial chunks. */
-#define DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF 1
+#define DRBD_DISCARD_ZEROES_IF_ALIGNED_DEF 1U
 
 /* Some backends pretend to support WRITE SAME,
  * but fail such requests when they are actually submitted.
  * This is to tell DRBD to not even try. */
-#define DRBD_DISABLE_WRITE_SAME_DEF 0
+#define DRBD_DISABLE_WRITE_SAME_DEF 0U
 
-#define DRBD_ALLOW_TWO_PRIMARIES_DEF	0
-#define DRBD_ALWAYS_ASBP_DEF	0
-#define DRBD_USE_RLE_DEF	1
-#define DRBD_CSUMS_AFTER_CRASH_ONLY_DEF 0
+#define DRBD_ALLOW_TWO_PRIMARIES_DEF	0U
+#define DRBD_ALWAYS_ASBP_DEF	0U
+#define DRBD_USE_RLE_DEF	1U
+#define DRBD_CSUMS_AFTER_CRASH_ONLY_DEF 0U
 
-#define DRBD_AL_STRIPES_MIN     1
-#define DRBD_AL_STRIPES_MAX     1024
-#define DRBD_AL_STRIPES_DEF     1
+#define DRBD_AL_STRIPES_MIN     1U
+#define DRBD_AL_STRIPES_MAX     1024U
+#define DRBD_AL_STRIPES_DEF     1U
 #define DRBD_AL_STRIPES_SCALE   '1'
 
-#define DRBD_AL_STRIPE_SIZE_MIN   4
-#define DRBD_AL_STRIPE_SIZE_MAX   16777216
-#define DRBD_AL_STRIPE_SIZE_DEF   32
+#define DRBD_AL_STRIPE_SIZE_MIN   4U
+#define DRBD_AL_STRIPE_SIZE_MAX   16777216U
+#define DRBD_AL_STRIPE_SIZE_DEF   32U
 #define DRBD_AL_STRIPE_SIZE_SCALE 'k' /* kilobytes */
 
-#define DRBD_SOCKET_CHECK_TIMEO_MIN 0
+#define DRBD_SOCKET_CHECK_TIMEO_MIN 0U
 #define DRBD_SOCKET_CHECK_TIMEO_MAX DRBD_PING_TIMEO_MAX
-#define DRBD_SOCKET_CHECK_TIMEO_DEF 0
+#define DRBD_SOCKET_CHECK_TIMEO_DEF 0U
 #define DRBD_SOCKET_CHECK_TIMEO_SCALE '1'
 
-#define DRBD_RS_DISCARD_GRANULARITY_MIN 0
-#define DRBD_RS_DISCARD_GRANULARITY_MAX (1<<20)  /* 1MiByte */
-#define DRBD_RS_DISCARD_GRANULARITY_DEF 0     /* disabled by default */
+#define DRBD_RS_DISCARD_GRANULARITY_MIN 0U
+#define DRBD_RS_DISCARD_GRANULARITY_MAX (1U<<20)  /* 1MiByte */
+#define DRBD_RS_DISCARD_GRANULARITY_DEF 0U     /* disabled by default */
 #define DRBD_RS_DISCARD_GRANULARITY_SCALE '1' /* bytes */
 
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 853d08f7562b..6f6ce9ca7097 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1436,7 +1436,7 @@ struct task_struct {
 #endif
 
 #ifdef CONFIG_BLK_CGROUP
-	struct request_queue		*throttle_queue;
+	struct gendisk			*throttle_disk;
 #endif
 
 #ifdef CONFIG_UPROBES
diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h
index 8f88e3a29998..f6238ccc7800 100644
--- a/include/uapi/linux/ublk_cmd.h
+++ b/include/uapi/linux/ublk_cmd.h
@@ -19,6 +19,8 @@
 #define	UBLK_CMD_GET_PARAMS	0x09
 #define	UBLK_CMD_START_USER_RECOVERY	0x10
 #define	UBLK_CMD_END_USER_RECOVERY	0x11
+#define	UBLK_CMD_GET_DEV_INFO2		0x12
+
 /*
  * IO commands, issued by ublk server, and handled by ublk driver.
  *
@@ -79,6 +81,27 @@
 
 #define UBLK_F_USER_RECOVERY_REISSUE	(1UL << 4)
 
+/*
+ * Unprivileged user can create /dev/ublkcN and /dev/ublkbN.
+ *
+ * /dev/ublk-control needs to be available for unprivileged user, and it
+ * can be done via udev rule to make all control commands available to
+ * unprivileged user. Except for the command of UBLK_CMD_ADD_DEV, all
+ * other commands are only allowed for the owner of the specified device.
+ *
+ * When userspace sends UBLK_CMD_ADD_DEV, the device pair's owner_uid and
+ * owner_gid are stored to ublksrv_ctrl_dev_info by kernel, so far only
+ * the current user's uid/gid is stored, that said owner of the created
+ * device is always the current user.
+ *
+ * We still need udev rule to apply OWNER/GROUP with the stored owner_uid
+ * and owner_gid.
+ *
+ * Then ublk server can be run as unprivileged user, and /dev/ublkbN can
+ * be accessed and managed by its owner represented by owner_uid/owner_gid.
+ */
+#define UBLK_F_UNPRIVILEGED_DEV	(1UL << 5)
+
 /* device state */
 #define UBLK_S_DEV_DEAD	0
 #define UBLK_S_DEV_LIVE	1
@@ -98,7 +121,15 @@ struct ublksrv_ctrl_cmd {
 	__u64	addr;
 
 	/* inline data */
-	__u64	data[2];
+	__u64	data[1];
+
+	/*
+	 * Used for UBLK_F_UNPRIVILEGED_DEV and UBLK_CMD_GET_DEV_INFO2
+	 * only, include null char
+	 */
+	__u16	dev_path_len;
+	__u16	pad;
+	__u32	reserved;
 };
 
 struct ublksrv_ctrl_dev_info {
@@ -118,7 +149,8 @@ struct ublksrv_ctrl_dev_info {
 	/* For ublksrv internal use, invisible to ublk driver */
 	__u64	ublksrv_flags;
 
-	__u64	reserved0;
+	__u32	owner_uid;	/* store by kernel */
+	__u32	owner_gid;	/* store by kernel */
 	__u64	reserved1;
 	__u64   reserved2;
 };
@@ -214,6 +246,17 @@ struct ublk_param_discard {
 	__u16	reserved0;
 };
 
+/*
+ * read-only, can't set via UBLK_CMD_SET_PARAMS, disk_devt is available
+ * after device is started
+ */
+struct ublk_param_devt {
+	__u32   char_major;
+	__u32   char_minor;
+	__u32   disk_major;
+	__u32   disk_minor;
+};
+
 struct ublk_params {
 	/*
 	 * Total length of parameters, userspace has to set 'len' for both
@@ -224,10 +267,12 @@ struct ublk_params {
 	__u32	len;
 #define UBLK_PARAM_TYPE_BASIC           (1 << 0)
 #define UBLK_PARAM_TYPE_DISCARD         (1 << 1)
+#define UBLK_PARAM_TYPE_DEVT            (1 << 2)
 	__u32	types;			/* types of parameter included */
 
 	struct ublk_param_basic		basic;
 	struct ublk_param_discard	discard;
+	struct ublk_param_devt		devt;
 };
 
 #endif