Merge tag 'for-6.7/block-2023-10-30' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - Improvements to the queue_rqs() support, and adding null_blk support
   for that as well (Chengming)

 - Series improving badblocks support (Coly)

 - Key store support for sed-opal (Greg)

 - IBM partition string handling improvements (Jan)

 - Make number of ublk devices supported configurable (Mike)

 - Cancelation improvements for ublk (Ming)

 - MD pull requests via Song:
     - Handle timeout in md-cluster, by Denis Plotnikov
     - Cleanup pers->prepare_suspend, by Yu Kuai
     - Rewrite mddev_suspend(), by Yu Kuai
     - Simplify md_seq_ops, by Yu Kuai
     - Reduce unnecessary locking array_state_store(), by Mariusz
       Tkaczyk
     - Make rdev add/remove independent from daemon thread, by Yu Kuai
     - Refactor code around quiesce() and mddev_suspend(), by Yu Kuai

 - NVMe pull request via Keith:
     - nvme-auth updates (Mark)
     - nvme-tcp tls (Hannes)
     - nvme-fc annotaions (Kees)

 - Misc cleanups and improvements (Jiapeng, Joel)

* tag 'for-6.7/block-2023-10-30' of git://git.kernel.dk/linux: (95 commits)
  block: ublk_drv: Remove unused function
  md: cleanup pers->prepare_suspend()
  nvme-auth: allow mixing of secret and hash lengths
  nvme-auth: use transformed key size to create resp
  nvme-auth: alloc nvme_dhchap_key as single buffer
  nvmet-tcp: use 'spin_lock_bh' for state_lock()
  powerpc/pseries: PLPKS SED Opal keystore support
  block: sed-opal: keystore access for SED Opal keys
  block:sed-opal: SED Opal keystore
  ublk: simplify aborting request
  ublk: replace monitor with cancelable uring_cmd
  ublk: quiesce request queue when aborting queue
  ublk: rename mm_lock as lock
  ublk: move ublk_cancel_dev() out of ub->mutex
  ublk: make sure io cmd handled in submitter task context
  ublk: don't get ublk device reference in ublk_abort_queue()
  ublk: Make ublks_max configurable
  ublk: Limit dev_id/ub_number values
  md-cluster: check for timeout while a new disk adding
  nvme: rework NVME_AUTH Kconfig selection
  ...

arch/powerpc/platforms/pseries/Kconfig

@@ -164,6 +164,12 @@ config PSERIES_PLPKS
 	# This option is selected by in-kernel consumers that require
 	# access to the PKS.
 
+config PSERIES_PLPKS_SED
+	depends on PPC_PSERIES
+	bool
+	# This option is selected by in-kernel consumers that require
+	# access to the SED PKS keystore.
+
 config PAPR_SCM
 	depends on PPC_PSERIES && MEMORY_HOTPLUG && LIBNVDIMM
 	tristate "Support for the PAPR Storage Class Memory interface"

arch/powerpc/platforms/pseries/Makefile

@@ -29,6 +29,7 @@ obj-$(CONFIG_PPC_SVM)		+= svm.o
 obj-$(CONFIG_FA_DUMP)		+= rtas-fadump.o
 obj-$(CONFIG_PSERIES_PLPKS)	+= plpks.o
 obj-$(CONFIG_PPC_SECURE_BOOT)	+= plpks-secvar.o
+obj-$(CONFIG_PSERIES_PLPKS_SED)	+= plpks_sed_ops.o
 obj-$(CONFIG_SUSPEND)		+= suspend.o
 obj-$(CONFIG_PPC_VAS)		+= vas.o vas-sysfs.o
 

arch/powerpc/platforms/pseries/plpks_sed_ops.c

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * POWER Platform specific code for non-volatile SED key access
+ * Copyright (C) 2022 IBM Corporation
+ *
+ * Define operations for SED Opal to read/write keys
+ * from POWER LPAR Platform KeyStore(PLPKS).
+ *
+ * Self Encrypting Drives(SED) key storage using PLPKS
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/ioctl.h>
+#include <linux/sed-opal-key.h>
+#include <asm/plpks.h>
+
+static bool plpks_sed_initialized = false;
+static bool plpks_sed_available = false;
+
+/*
+ * structure that contains all SED data
+ */
+struct plpks_sed_object_data {
+	u_char version;
+	u_char pad1[7];
+	u_long authority;
+	u_long range;
+	u_int  key_len;
+	u_char key[32];
+};
+
+#define PLPKS_SED_OBJECT_DATA_V0        0
+#define PLPKS_SED_MANGLED_LABEL         "/default/pri"
+#define PLPKS_SED_COMPONENT             "sed-opal"
+#define PLPKS_SED_KEY                   "opal-boot-pin"
+
+/*
+ * authority is admin1 and range is global
+ */
+#define PLPKS_SED_AUTHORITY  0x0000000900010001
+#define PLPKS_SED_RANGE      0x0000080200000001
+
+static void plpks_init_var(struct plpks_var *var, char *keyname)
+{
+	if (!plpks_sed_initialized) {
+		plpks_sed_initialized = true;
+		plpks_sed_available = plpks_is_available();
+		if (!plpks_sed_available)
+			pr_err("SED: plpks not available\n");
+	}
+
+	var->name = keyname;
+	var->namelen = strlen(keyname);
+	if (strcmp(PLPKS_SED_KEY, keyname) == 0) {
+		var->name = PLPKS_SED_MANGLED_LABEL;
+		var->namelen = strlen(keyname);
+	}
+	var->policy = PLPKS_WORLDREADABLE;
+	var->os = PLPKS_VAR_COMMON;
+	var->data = NULL;
+	var->datalen = 0;
+	var->component = PLPKS_SED_COMPONENT;
+}
+
+/*
+ * Read the SED Opal key from PLPKS given the label
+ */
+int sed_read_key(char *keyname, char *key, u_int *keylen)
+{
+	struct plpks_var var;
+	struct plpks_sed_object_data data;
+	int ret;
+	u_int len;
+
+	plpks_init_var(&var, keyname);
+
+	if (!plpks_sed_available)
+		return -EOPNOTSUPP;
+
+	var.data = (u8 *)&data;
+	var.datalen = sizeof(data);
+
+	ret = plpks_read_os_var(&var);
+	if (ret != 0)
+		return ret;
+
+	len = min_t(u16, be32_to_cpu(data.key_len), var.datalen);
+	memcpy(key, data.key, len);
+	key[len] = '\0';
+	*keylen = len;
+
+	return 0;
+}
+
+/*
+ * Write the SED Opal key to PLPKS given the label
+ */
+int sed_write_key(char *keyname, char *key, u_int keylen)
+{
+	struct plpks_var var;
+	struct plpks_sed_object_data data;
+	struct plpks_var_name vname;
+
+	plpks_init_var(&var, keyname);
+
+	if (!plpks_sed_available)
+		return -EOPNOTSUPP;
+
+	var.datalen = sizeof(struct plpks_sed_object_data);
+	var.data = (u8 *)&data;
+
+	/* initialize SED object */
+	data.version = PLPKS_SED_OBJECT_DATA_V0;
+	data.authority = cpu_to_be64(PLPKS_SED_AUTHORITY);
+	data.range = cpu_to_be64(PLPKS_SED_RANGE);
+	memset(&data.pad1, '\0', sizeof(data.pad1));
+	data.key_len = cpu_to_be32(keylen);
+	memcpy(data.key, (char *)key, keylen);
+
+	/*
+	 * Key update requires remove first. The return value
+	 * is ignored since it's okay if the key doesn't exist.
+	 */
+	vname.namelen = var.namelen;
+	vname.name = var.name;
+	plpks_remove_var(var.component, var.os, vname);
+
+	return plpks_write_var(var);
+}

block/Kconfig

@@ -186,6 +186,7 @@ config BLK_SED_OPAL
 	bool "Logic for interfacing with Opal enabled SEDs"
 	depends on KEYS
 	select PSERIES_PLPKS if PPC_PSERIES
+	select PSERIES_PLPKS_SED if PPC_PSERIES
 	help
 	Builds Logic for interfacing with Opal enabled controllers.
 	Enabling this option enables users to setup/unlock/lock

block/blk-flush.c

@@ -323,16 +323,9 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq,
 	flush_rq->mq_ctx = first_rq->mq_ctx;
 	flush_rq->mq_hctx = first_rq->mq_hctx;
 
-	if (!q->elevator) {
+	if (!q->elevator)
 		flush_rq->tag = first_rq->tag;
-
-		/*
-		 * We borrow data request's driver tag, so have to mark
-		 * this flush request as INFLIGHT for avoiding double
-		 * account of this driver tag
-		 */
-		flush_rq->rq_flags |= RQF_MQ_INFLIGHT;
-	} else
+	else
 		flush_rq->internal_tag = first_rq->internal_tag;
 
 	flush_rq->cmd_flags = REQ_OP_FLUSH | REQ_PREFLUSH;

block/blk-mq-debugfs.c

@@ -246,7 +246,6 @@ static const char *const rqf_name[] = {
 	RQF_NAME(STARTED),
 	RQF_NAME(FLUSH_SEQ),
 	RQF_NAME(MIXED_MERGE),
-	RQF_NAME(MQ_INFLIGHT),
 	RQF_NAME(DONTPREP),
 	RQF_NAME(SCHED_TAGS),
 	RQF_NAME(USE_SCHED),

block/blk-mq.c

@@ -426,6 +426,8 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data)
 		rq_list_add(data->cached_rq, rq);
 		nr++;
 	}
+	if (!(data->rq_flags & RQF_SCHED_TAGS))
+		blk_mq_add_active_requests(data->hctx, nr);
 	/* caller already holds a reference, add for remainder */
 	percpu_ref_get_many(&data->q->q_usage_counter, nr - 1);
 	data->nr_tags -= nr;
@@ -510,6 +512,8 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
 		goto retry;
 	}
 
+	if (!(data->rq_flags & RQF_SCHED_TAGS))
+		blk_mq_inc_active_requests(data->hctx);
 	rq = blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag);
 	blk_mq_rq_time_init(rq, alloc_time_ns);
 	return rq;
@@ -669,6 +673,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 	tag = blk_mq_get_tag(&data);
 	if (tag == BLK_MQ_NO_TAG)
 		goto out_queue_exit;
+	if (!(data.rq_flags & RQF_SCHED_TAGS))
+		blk_mq_inc_active_requests(data.hctx);
 	rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag);
 	blk_mq_rq_time_init(rq, alloc_time_ns);
 	rq->__data_len = 0;
@@ -708,11 +714,10 @@ static void __blk_mq_free_request(struct request *rq)
 	blk_pm_mark_last_busy(rq);
 	rq->mq_hctx = NULL;
 
-	if (rq->rq_flags & RQF_MQ_INFLIGHT)
-		__blk_mq_dec_active_requests(hctx);
-
-	if (rq->tag != BLK_MQ_NO_TAG)
+	if (rq->tag != BLK_MQ_NO_TAG) {
+		blk_mq_dec_active_requests(hctx);
 		blk_mq_put_tag(hctx->tags, ctx, rq->tag);
+	}
 	if (sched_tag != BLK_MQ_NO_TAG)
 		blk_mq_put_tag(hctx->sched_tags, ctx, sched_tag);
 	blk_mq_sched_restart(hctx);
@@ -1061,12 +1066,7 @@ static inline void blk_mq_flush_tag_batch(struct blk_mq_hw_ctx *hctx,
 {
 	struct request_queue *q = hctx->queue;
 
-	/*
-	 * All requests should have been marked as RQF_MQ_INFLIGHT, so
-	 * update hctx->nr_active in batch
-	 */
-	if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
-		__blk_mq_sub_active_requests(hctx, nr_tags);
+	blk_mq_sub_active_requests(hctx, nr_tags);
 
 	blk_mq_put_tags(hctx->tags, tag_array, nr_tags);
 	percpu_ref_put_many(&q->q_usage_counter, nr_tags);
@@ -1259,6 +1259,7 @@ void blk_mq_start_request(struct request *rq)
 
 	blk_add_timer(rq);
 	WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT);
+	rq->mq_hctx->tags->rqs[rq->tag] = rq;
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 	if (blk_integrity_rq(rq) && req_op(rq) == REQ_OP_WRITE)
@@ -1748,7 +1749,7 @@ struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 	return data.rq;
 }
 
-static bool __blk_mq_alloc_driver_tag(struct request *rq)
+bool __blk_mq_alloc_driver_tag(struct request *rq)
 {
 	struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags;
 	unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags;
@@ -1769,20 +1770,7 @@ static bool __blk_mq_alloc_driver_tag(struct request *rq)
 		return false;
 
 	rq->tag = tag + tag_offset;
-	return true;
-}
-
-bool __blk_mq_get_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq)
-{
-	if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_alloc_driver_tag(rq))
-		return false;
-
-	if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) &&
-			!(rq->rq_flags & RQF_MQ_INFLIGHT)) {
-		rq->rq_flags |= RQF_MQ_INFLIGHT;
-		__blk_mq_inc_active_requests(hctx);
-	}
-	hctx->tags->rqs[rq->tag] = rq;
+	blk_mq_inc_active_requests(rq->mq_hctx);
 	return true;
 }
 
@@ -2794,13 +2782,8 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 		 * If we do, we can dispatch the whole plug list in one go. We
 		 * already know at this point that all requests belong to the
 		 * same queue, caller must ensure that's the case.
-		 *
-		 * Since we pass off the full list to the driver at this point,
-		 * we do not increment the active request count for the queue.
-		 * Bypass shared tags for now because of that.
 		 */
-		if (q->mq_ops->queue_rqs &&
-		    !(rq->mq_hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
+		if (q->mq_ops->queue_rqs) {
 			blk_mq_run_dispatch_ops(q,
 				__blk_mq_flush_plug_list(q, plug));
 			if (rq_list_empty(plug->mq_list))

block/blk-mq.h

@@ -271,12 +271,18 @@ static inline int blk_mq_get_rq_budget_token(struct request *rq)
 	return -1;
 }
 
-static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
+static inline void __blk_mq_add_active_requests(struct blk_mq_hw_ctx *hctx,
+						int val)
 {
 	if (blk_mq_is_shared_tags(hctx->flags))
-		atomic_inc(&hctx->queue->nr_active_requests_shared_tags);
+		atomic_add(val, &hctx->queue->nr_active_requests_shared_tags);
 	else
-		atomic_inc(&hctx->nr_active);
+		atomic_add(val, &hctx->nr_active);
+}
+
+static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	__blk_mq_add_active_requests(hctx, 1);
 }
 
 static inline void __blk_mq_sub_active_requests(struct blk_mq_hw_ctx *hctx,
@@ -293,6 +299,32 @@ static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
 	__blk_mq_sub_active_requests(hctx, 1);
 }
 
+static inline void blk_mq_add_active_requests(struct blk_mq_hw_ctx *hctx,
+					      int val)
+{
+	if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
+		__blk_mq_add_active_requests(hctx, val);
+}
+
+static inline void blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
+		__blk_mq_inc_active_requests(hctx);
+}
+
+static inline void blk_mq_sub_active_requests(struct blk_mq_hw_ctx *hctx,
+					      int val)
+{
+	if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
+		__blk_mq_sub_active_requests(hctx, val);
+}
+
+static inline void blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx)
+{
+	if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)
+		__blk_mq_dec_active_requests(hctx);
+}
+
 static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx)
 {
 	if (blk_mq_is_shared_tags(hctx->flags))
@@ -302,13 +334,9 @@ static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx)
 static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx,
 					   struct request *rq)
 {
+	blk_mq_dec_active_requests(hctx);
 	blk_mq_put_tag(hctx->tags, rq->mq_ctx, rq->tag);
 	rq->tag = BLK_MQ_NO_TAG;
-
-	if (rq->rq_flags & RQF_MQ_INFLIGHT) {
-		rq->rq_flags &= ~RQF_MQ_INFLIGHT;
-		__blk_mq_dec_active_requests(hctx);
-	}
 }
 
 static inline void blk_mq_put_driver_tag(struct request *rq)
@@ -319,19 +347,14 @@ static inline void blk_mq_put_driver_tag(struct request *rq)
 	__blk_mq_put_driver_tag(rq->mq_hctx, rq);
 }
 
-bool __blk_mq_get_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq);
+bool __blk_mq_alloc_driver_tag(struct request *rq);
 
 static inline bool blk_mq_get_driver_tag(struct request *rq)
 {
-	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
-
-	if (rq->tag != BLK_MQ_NO_TAG &&
-	    !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) {
-		hctx->tags->rqs[rq->tag] = rq;
-		return true;
-	}
+	if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_alloc_driver_tag(rq))
+		return false;
 
-	return __blk_mq_get_driver_tag(hctx, rq);
+	return true;
 }
 
 static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap)

block/partitions/ibm.c

@@ -61,6 +61,47 @@ static sector_t cchhb2blk(struct vtoc_cchhb *ptr, struct hd_geometry *geo)
 		ptr->b;
 }
 
+/* Volume Label Type/ID Length */
+#define DASD_VOL_TYPE_LEN	4
+#define DASD_VOL_ID_LEN		6
+
+/* Volume Label Types */
+#define DASD_VOLLBL_TYPE_VOL1 0
+#define DASD_VOLLBL_TYPE_LNX1 1
+#define DASD_VOLLBL_TYPE_CMS1 2
+
+struct dasd_vollabel {
+	char *type;
+	int idx;
+};
+
+static struct dasd_vollabel dasd_vollabels[] = {
+	[DASD_VOLLBL_TYPE_VOL1] = {
+		.type = "VOL1",
+		.idx = DASD_VOLLBL_TYPE_VOL1,
+	},
+	[DASD_VOLLBL_TYPE_LNX1] = {
+		.type = "LNX1",
+		.idx = DASD_VOLLBL_TYPE_LNX1,
+	},
+	[DASD_VOLLBL_TYPE_CMS1] = {
+		.type = "CMS1",
+		.idx = DASD_VOLLBL_TYPE_CMS1,
+	},
+};
+
+static int get_label_by_type(const char *type)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dasd_vollabels); i++) {
+		if (!memcmp(type, dasd_vollabels[i].type, DASD_VOL_TYPE_LEN))
+			return dasd_vollabels[i].idx;
+	}
+
+	return -1;
+}
+
 static int find_label(struct parsed_partitions *state,
 		      dasd_information2_t *info,
 		      struct hd_geometry *geo,
@@ -70,12 +111,10 @@ static int find_label(struct parsed_partitions *state,
 		      char type[],
 		      union label_t *label)
 {
-	Sector sect;
-	unsigned char *data;
 	sector_t testsect[3];
-	unsigned char temp[5];
-	int found = 0;
 	int i, testcount;
+	Sector sect;
+	void *data;
 
 	/* There a three places where we may find a valid label:
 	 * - on an ECKD disk it's block 2
@@ -103,31 +142,27 @@ static int find_label(struct parsed_partitions *state,
 		if (data == NULL)
 			continue;
 		memcpy(label, data, sizeof(*label));
-		memcpy(temp, data, 4);
-		temp[4] = 0;
-		EBCASC(temp, 4);
+		memcpy(type, data, DASD_VOL_TYPE_LEN);
+		EBCASC(type, DASD_VOL_TYPE_LEN);
 		put_dev_sector(sect);
-		if (!strcmp(temp, "VOL1") ||
-		    !strcmp(temp, "LNX1") ||
-		    !strcmp(temp, "CMS1")) {
-			if (!strcmp(temp, "VOL1")) {
-				strncpy(type, label->vol.vollbl, 4);
-				strncpy(name, label->vol.volid, 6);
-			} else {
-				strncpy(type, label->lnx.vollbl, 4);
-				strncpy(name, label->lnx.volid, 6);
-			}
-			EBCASC(type, 4);
-			EBCASC(name, 6);
+		switch (get_label_by_type(type)) {
+		case DASD_VOLLBL_TYPE_VOL1:
+			memcpy(name, label->vol.volid, DASD_VOL_ID_LEN);
+			EBCASC(name, DASD_VOL_ID_LEN);
+			*labelsect = testsect[i];
+			return 1;
+		case DASD_VOLLBL_TYPE_LNX1:
+		case DASD_VOLLBL_TYPE_CMS1:
+			memcpy(name, label->lnx.volid, DASD_VOL_ID_LEN);
+			EBCASC(name, DASD_VOL_ID_LEN);
 			*labelsect = testsect[i];
-			found = 1;
+			return 1;
+		default:
 			break;
 		}
 	}
-	if (!found)
-		memset(label, 0, sizeof(*label));
 
-	return found;
+	return 0;
 }
 
 static int find_vol1_partitions(struct parsed_partitions *state,
@@ -297,8 +332,8 @@ int ibm_partition(struct parsed_partitions *state)
 	sector_t nr_sectors;
 	dasd_information2_t *info;
 	struct hd_geometry *geo;
-	char type[5] = {0,};
-	char name[7] = {0,};
+	char type[DASD_VOL_TYPE_LEN + 1] = "";
+	char name[DASD_VOL_ID_LEN + 1] = "";
 	sector_t labelsect;
 	union label_t *label;
 
@@ -330,18 +365,21 @@ int ibm_partition(struct parsed_partitions *state)
 		info = NULL;
 	}
 
-	if (find_label(state, info, geo, blocksize, &labelsect, name, type,
-		       label)) {
-		if (!strncmp(type, "VOL1", 4)) {
+	if (find_label(state, info, geo, blocksize, &labelsect, name, type, label)) {
+		switch (get_label_by_type(type)) {
+		case DASD_VOLLBL_TYPE_VOL1:
 			res = find_vol1_partitions(state, geo, blocksize, name,
 						   label);
-		} else if (!strncmp(type, "LNX1", 4)) {
+			break;
+		case DASD_VOLLBL_TYPE_LNX1:
 			res = find_lnx1_partitions(state, geo, blocksize, name,
 						   label, labelsect, nr_sectors,
 						   info);
-		} else if (!strncmp(type, "CMS1", 4)) {
+			break;
+		case DASD_VOLLBL_TYPE_CMS1:
 			res = find_cms1_partitions(state, geo, blocksize, name,
 						   label, labelsect);
+			break;
 		}
 	} else if (info) {
 		/*

block/sed-opal.c

@@ -18,6 +18,7 @@
 #include <linux/uaccess.h>
 #include <uapi/linux/sed-opal.h>
 #include <linux/sed-opal.h>
+#include <linux/sed-opal-key.h>
 #include <linux/string.h>
 #include <linux/kdev_t.h>
 #include <linux/key.h>
@@ -3018,7 +3019,13 @@ static int opal_set_new_pw(struct opal_dev *dev, struct opal_new_pw *opal_pw)
 	if (ret)
 		return ret;
 
-	/* update keyring with new password */
+	/* update keyring and key store with new password */
+	ret = sed_write_key(OPAL_AUTH_KEY,
+			    opal_pw->new_user_pw.opal_key.key,
+			    opal_pw->new_user_pw.opal_key.key_len);
+	if (ret != -EOPNOTSUPP)
+		pr_warn("error updating SED key: %d\n", ret);
+
 	ret = update_sed_opal_key(OPAL_AUTH_KEY,
 				  opal_pw->new_user_pw.opal_key.key,
 				  opal_pw->new_user_pw.opal_key.key_len);
@@ -3291,6 +3298,8 @@ EXPORT_SYMBOL_GPL(sed_ioctl);
 static int __init sed_opal_init(void)
 {
 	struct key *kr;
+	char init_sed_key[OPAL_KEY_MAX];
+	int keylen = OPAL_KEY_MAX - 1;
 
 	kr = keyring_alloc(".sed_opal",
 			   GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, current_cred(),
@@ -3303,6 +3312,11 @@ static int __init sed_opal_init(void)
 
 	sed_opal_keyring = kr;
 
-	return 0;
+	if (sed_read_key(OPAL_AUTH_KEY, init_sed_key, &keylen) < 0) {
+		memset(init_sed_key, '\0', sizeof(init_sed_key));
+		keylen = OPAL_KEY_MAX - 1;
+	}
+
+	return update_sed_opal_key(OPAL_AUTH_KEY, init_sed_key, keylen);
 }
 late_initcall(sed_opal_init);

drivers/block/aoe/aoenet.c

@@ -39,8 +39,7 @@ static struct ktstate kts;
 #ifndef MODULE
 static int __init aoe_iflist_setup(char *str)
 {
-	strncpy(aoe_iflist, str, IFLISTSZ);
-	aoe_iflist[IFLISTSZ - 1] = '\0';
+	strscpy(aoe_iflist, str, IFLISTSZ);
 	return 1;
 }
 

drivers/block/null_blk/main.c

@@ -1750,6 +1750,25 @@ static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
 	return null_handle_cmd(cmd, sector, nr_sectors, req_op(rq));
 }
 
+static void null_queue_rqs(struct request **rqlist)
+{
+	struct request *requeue_list = NULL;
+	struct request **requeue_lastp = &requeue_list;
+	struct blk_mq_queue_data bd = { };
+	blk_status_t ret;
+
+	do {
+		struct request *rq = rq_list_pop(rqlist);
+
+		bd.rq = rq;
+		ret = null_queue_rq(rq->mq_hctx, &bd);
+		if (ret != BLK_STS_OK)
+			rq_list_add_tail(&requeue_lastp, rq);
+	} while (!rq_list_empty(*rqlist));
+
+	*rqlist = requeue_list;
+}
+
 static void cleanup_queue(struct nullb_queue *nq)
 {
 	bitmap_free(nq->tag_map);
@@ -1802,6 +1821,7 @@ static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *driver_data,
 
 static const struct blk_mq_ops null_mq_ops = {
 	.queue_rq       = null_queue_rq,
+	.queue_rqs	= null_queue_rqs,
 	.complete	= null_complete_rq,
 	.timeout	= null_timeout_rq,
 	.poll		= null_poll,
@@ -1946,7 +1966,7 @@ static int null_gendisk_register(struct nullb *nullb)
 	else
 		disk->fops		= &null_bio_ops;
 	disk->private_data	= nullb;
-	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+	strscpy_pad(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
 
 	if (nullb->dev->zoned) {
 		int ret = null_register_zoned_dev(nullb);

drivers/block/virtio_blk.c

@@ -470,8 +470,6 @@ static bool virtblk_prep_rq_batch(struct request *req)
 	struct virtio_blk *vblk = req->mq_hctx->queue->queuedata;
 	struct virtblk_req *vbr = blk_mq_rq_to_pdu(req);
 
-	req->mq_hctx->tags->rqs[req->tag] = req;
-
 	return virtblk_prep_rq(req->mq_hctx, vblk, req, vbr) == BLK_STS_OK;
 }
 

drivers/cdrom/cdrom.c

@@ -3655,7 +3655,6 @@ static struct ctl_table cdrom_table[] = {
 		.mode		= 0644,
 		.proc_handler	= cdrom_sysctl_handler
 	},
-	{ }
 };
 static struct ctl_table_header *cdrom_sysctl_header;
 

drivers/md/dm-raid.c

@@ -749,7 +749,11 @@ static struct raid_set *raid_set_alloc(struct dm_target *ti, struct raid_type *r
 		return ERR_PTR(-ENOMEM);
 	}
 
-	mddev_init(&rs->md);
+	if (mddev_init(&rs->md)) {
+		kfree(rs);
+		ti->error = "Cannot initialize raid context";
+		return ERR_PTR(-ENOMEM);
+	}
 
 	rs->raid_disks = raid_devs;
 	rs->delta_disks = 0;
@@ -798,6 +802,7 @@ static void raid_set_free(struct raid_set *rs)
 			dm_put_device(rs->ti, rs->dev[i].data_dev);
 	}
 
+	mddev_destroy(&rs->md);
 	kfree(rs);
 }
 
@@ -3239,7 +3244,7 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	set_bit(MD_RECOVERY_FROZEN, &rs->md.recovery);
 
 	/* Has to be held on running the array */
-	mddev_lock_nointr(&rs->md);
+	mddev_suspend_and_lock_nointr(&rs->md);
 	r = md_run(&rs->md);
 	rs->md.in_sync = 0; /* Assume already marked dirty */
 	if (r) {
@@ -3263,7 +3268,6 @@ static int raid_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		}
 	}
 
-	mddev_suspend(&rs->md);
 	set_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags);
 
 	/* Try to adjust the raid4/5/6 stripe cache size to the stripe size */
@@ -3793,9 +3797,7 @@ static void raid_postsuspend(struct dm_target *ti)
 		if (!test_bit(MD_RECOVERY_FROZEN, &rs->md.recovery))
 			md_stop_writes(&rs->md);
 
-		mddev_lock_nointr(&rs->md);
-		mddev_suspend(&rs->md);
-		mddev_unlock(&rs->md);
+		mddev_suspend(&rs->md, false);
 	}
 }
 
@@ -4054,8 +4056,7 @@ static void raid_resume(struct dm_target *ti)
 		clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery);
 		mddev->ro = 0;
 		mddev->in_sync = 0;
-		mddev_resume(mddev);
-		mddev_unlock(mddev);
+		mddev_unlock_and_resume(mddev);
 	}
 }
 

drivers/md/md-autodetect.c

@@ -175,7 +175,7 @@ static void __init md_setup_drive(struct md_setup_args *args)
 		return;
 	}
 
-	err = mddev_lock(mddev);
+	err = mddev_suspend_and_lock(mddev);
 	if (err) {
 		pr_err("md: failed to lock array %s\n", name);
 		goto out_mddev_put;
@@ -221,7 +221,7 @@ static void __init md_setup_drive(struct md_setup_args *args)
 	if (err)
 		pr_warn("md: starting %s failed\n", name);
 out_unlock:
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 out_mddev_put:
 	mddev_put(mddev);
 }

drivers/md/md-bitmap.c

@@ -1861,7 +1861,7 @@ void md_bitmap_destroy(struct mddev *mddev)
 
 	md_bitmap_wait_behind_writes(mddev);
 	if (!mddev->serialize_policy)
-		mddev_destroy_serial_pool(mddev, NULL, true);
+		mddev_destroy_serial_pool(mddev, NULL);
 
 	mutex_lock(&mddev->bitmap_info.mutex);
 	spin_lock(&mddev->lock);
@@ -1977,7 +1977,7 @@ int md_bitmap_load(struct mddev *mddev)
 		goto out;
 
 	rdev_for_each(rdev, mddev)
-		mddev_create_serial_pool(mddev, rdev, true);
+		mddev_create_serial_pool(mddev, rdev);
 
 	if (mddev_is_clustered(mddev))
 		md_cluster_ops->load_bitmaps(mddev, mddev->bitmap_info.nodes);
@@ -2348,14 +2348,11 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 {
 	int rv;
 
-	rv = mddev_lock(mddev);
+	rv = mddev_suspend_and_lock(mddev);
 	if (rv)
 		return rv;
+
 	if (mddev->pers) {
-		if (!mddev->pers->quiesce) {
-			rv = -EBUSY;
-			goto out;
-		}
 		if (mddev->recovery || mddev->sync_thread) {
 			rv = -EBUSY;
 			goto out;
@@ -2369,11 +2366,8 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 			rv = -EBUSY;
 			goto out;
 		}
-		if (mddev->pers) {
-			mddev_suspend(mddev);
-			md_bitmap_destroy(mddev);
-			mddev_resume(mddev);
-		}
+
+		md_bitmap_destroy(mddev);
 		mddev->bitmap_info.offset = 0;
 		if (mddev->bitmap_info.file) {
 			struct file *f = mddev->bitmap_info.file;
@@ -2383,6 +2377,8 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 	} else {
 		/* No bitmap, OK to set a location */
 		long long offset;
+		struct bitmap *bitmap;
+
 		if (strncmp(buf, "none", 4) == 0)
 			/* nothing to be done */;
 		else if (strncmp(buf, "file:", 5) == 0) {
@@ -2406,25 +2402,20 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 				rv = -EINVAL;
 				goto out;
 			}
+
 			mddev->bitmap_info.offset = offset;
-			if (mddev->pers) {
-				struct bitmap *bitmap;
-				bitmap = md_bitmap_create(mddev, -1);
-				mddev_suspend(mddev);
-				if (IS_ERR(bitmap))
-					rv = PTR_ERR(bitmap);
-				else {
-					mddev->bitmap = bitmap;
-					rv = md_bitmap_load(mddev);
-					if (rv)
-						mddev->bitmap_info.offset = 0;
-				}
-				if (rv) {
-					md_bitmap_destroy(mddev);
-					mddev_resume(mddev);
-					goto out;
-				}
-				mddev_resume(mddev);
+			bitmap = md_bitmap_create(mddev, -1);
+			if (IS_ERR(bitmap)) {
+				rv = PTR_ERR(bitmap);
+				goto out;
+			}
+
+			mddev->bitmap = bitmap;
+			rv = md_bitmap_load(mddev);
+			if (rv) {
+				mddev->bitmap_info.offset = 0;
+				md_bitmap_destroy(mddev);
+				goto out;
 			}
 		}
 	}
@@ -2437,7 +2428,7 @@ location_store(struct mddev *mddev, const char *buf, size_t len)
 	}
 	rv = 0;
 out:
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	if (rv)
 		return rv;
 	return len;
@@ -2546,7 +2537,7 @@ backlog_store(struct mddev *mddev, const char *buf, size_t len)
 	if (backlog > COUNTER_MAX)
 		return -EINVAL;
 
-	rv = mddev_lock(mddev);
+	rv = mddev_suspend_and_lock(mddev);
 	if (rv)
 		return rv;
 
@@ -2571,16 +2562,16 @@ backlog_store(struct mddev *mddev, const char *buf, size_t len)
 	if (!backlog && mddev->serial_info_pool) {
 		/* serial_info_pool is not needed if backlog is zero */
 		if (!mddev->serialize_policy)
-			mddev_destroy_serial_pool(mddev, NULL, false);
+			mddev_destroy_serial_pool(mddev, NULL);
 	} else if (backlog && !mddev->serial_info_pool) {
 		/* serial_info_pool is needed since backlog is not zero */
 		rdev_for_each(rdev, mddev)
-			mddev_create_serial_pool(mddev, rdev, false);
+			mddev_create_serial_pool(mddev, rdev);
 	}
 	if (old_mwb != backlog)
 		md_bitmap_update_sb(mddev->bitmap);
 
-	mddev_unlock(mddev);
+	mddev_unlock_and_resume(mddev);
 	return len;
 }
 

drivers/md/md-cluster.c

@@ -501,7 +501,7 @@ static void process_suspend_info(struct mddev *mddev,
 	mddev->pers->quiesce(mddev, 0);
 }
 
-static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
+static int process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
 {
 	char disk_uuid[64];
 	struct md_cluster_info *cinfo = mddev->cluster_info;
@@ -509,6 +509,7 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
 	char raid_slot[16];
 	char *envp[] = {event_name, disk_uuid, raid_slot, NULL};
 	int len;
+	int res = 0;
 
 	len = snprintf(disk_uuid, 64, "DEVICE_UUID=");
 	sprintf(disk_uuid + len, "%pU", cmsg->uuid);
@@ -517,9 +518,14 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
 	init_completion(&cinfo->newdisk_completion);
 	set_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state);
 	kobject_uevent_env(&disk_to_dev(mddev->gendisk)->kobj, KOBJ_CHANGE, envp);
-	wait_for_completion_timeout(&cinfo->newdisk_completion,
-			NEW_DEV_TIMEOUT);
+	if (!wait_for_completion_timeout(&cinfo->newdisk_completion,
+					NEW_DEV_TIMEOUT)) {
+		pr_err("md-cluster(%s:%d): timeout on a new disk adding\n",
+			__func__, __LINE__);
+		res = -1;
+	}
 	clear_bit(MD_CLUSTER_WAITING_FOR_NEWDISK, &cinfo->state);
+	return res;
 }
 
 
@@ -594,7 +600,8 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 				     le64_to_cpu(msg->high));
 		break;
 	case NEWDISK:
-		process_add_new_disk(mddev, msg);
+		if (process_add_new_disk(mddev, msg))
+			ret = -1;
 		break;
 	case REMOVE:
 		process_remove_disk(mddev, msg);

drivers/md/md-linear.c

@@ -69,6 +69,19 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 	if (!conf)
 		return NULL;
 
+	/*
+	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
+	 * keep a copy of mddev->raid_disks in struct linear_conf is,
+	 * mddev->raid_disks may not be consistent with pointers number of
+	 * conf->disks[] when it is updated in linear_add() and used to
+	 * iterate old conf->disks[] earray in linear_congested().
+	 * Here conf->raid_disks is always consitent with number of
+	 * pointers in conf->disks[] array, and mddev->private is updated
+	 * with rcu_assign_pointer() in linear_addr(), such race can be
+	 * avoided.
+	 */
+	conf->raid_disks = raid_disks;
+
 	cnt = 0;
 	conf->array_sectors = 0;
 
@@ -112,19 +125,6 @@ static struct linear_conf *linear_conf(struct mddev *mddev, int raid_disks)
 			conf->disks[i-1].end_sector +
 			conf->disks[i].rdev->sectors;
 
-	/*
-	 * conf->raid_disks is copy of mddev->raid_disks. The reason to
-	 * keep a copy of mddev->raid_disks in struct linear_conf is,
-	 * mddev->raid_disks may not be consistent with pointers number of
-	 * conf->disks[] when it is updated in linear_add() and used to
-	 * iterate old conf->disks[] earray in linear_congested().
-	 * Here conf->raid_disks is always consitent with number of
-	 * pointers in conf->disks[] array, and mddev->private is updated
-	 * with rcu_assign_pointer() in linear_addr(), such race can be
-	 * avoided.
-	 */
-	conf->raid_disks = raid_disks;
-
 	return conf;
 
 out:
@@ -183,7 +183,6 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	 * in linear_congested(), therefore kfree_rcu() is used to free
 	 * oldconf until no one uses it anymore.
 	 */
-	mddev_suspend(mddev);
 	oldconf = rcu_dereference_protected(mddev->private,
 			lockdep_is_held(&mddev->reconfig_mutex));
 	mddev->raid_disks++;
@@ -192,7 +191,6 @@ static int linear_add(struct mddev *mddev, struct md_rdev *rdev)
 	rcu_assign_pointer(mddev->private, newconf);
 	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity_and_notify(mddev->gendisk, mddev->array_sectors);
-	mddev_resume(mddev);
 	kfree_rcu(oldconf, rcu);
 	return 0;
 }

drivers/md/md-linear.h

@@ -12,6 +12,6 @@ struct linear_conf
 	struct rcu_head		rcu;
 	sector_t		array_sectors;
 	int			raid_disks; /* a copy of mddev->raid_disks */
-	struct dev_info		disks[];
+	struct dev_info		disks[] __counted_by(raid_disks);
 };
 #endif

drivers/md/md.h

@@ -246,10 +246,6 @@ struct md_cluster_info;
  *			    become failed.
  * @MD_HAS_PPL:  The raid array has PPL feature set.
  * @MD_HAS_MULTIPLE_PPLS: The raid array has multiple PPLs feature set.
- * @MD_ALLOW_SB_UPDATE: md_check_recovery is allowed to update the metadata
- *			 without taking reconfig_mutex.
- * @MD_UPDATING_SB: md_check_recovery is updating the metadata without
- *		     explicitly holding reconfig_mutex.
  * @MD_NOT_READY: do_md_run() is active, so 'array_state', ust not report that
  *		   array is ready yet.
  * @MD_BROKEN: This is used to stop writes and mark array as failed.
@@ -266,8 +262,6 @@ enum mddev_flags {
 	MD_FAILFAST_SUPPORTED,
 	MD_HAS_PPL,
 	MD_HAS_MULTIPLE_PPLS,
-	MD_ALLOW_SB_UPDATE,
-	MD_UPDATING_SB,
 	MD_NOT_READY,
 	MD_BROKEN,
 	MD_DELETED,
@@ -314,6 +308,7 @@ struct mddev {
 	unsigned long			sb_flags;
 
 	int				suspended;
+	struct mutex			suspend_mutex;
 	struct percpu_ref		active_io;
 	int				ro;
 	int				sysfs_active; /* set when sysfs deletes
@@ -451,7 +446,10 @@ struct mddev {
 	struct kernfs_node		*sysfs_degraded;	/*handle for 'degraded' */
 	struct kernfs_node		*sysfs_level;		/*handle for 'level' */
 
-	struct work_struct del_work;	/* used for delayed sysfs removal */
+	/* used for delayed sysfs removal */
+	struct work_struct del_work;
+	/* used for register new sync thread */
+	struct work_struct sync_work;
 
 	/* "lock" protects:
 	 *   flush_bio transition from NULL to !NULL
@@ -565,23 +563,6 @@ enum recovery_flags {
 	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
 };
 
-enum md_ro_state {
-	MD_RDWR,
-	MD_RDONLY,
-	MD_AUTO_READ,
-	MD_MAX_STATE
-};
-
-static inline bool md_is_rdwr(struct mddev *mddev)
-{
-	return (mddev->ro == MD_RDWR);
-}
-
-static inline bool is_md_suspended(struct mddev *mddev)
-{
-	return percpu_ref_is_dying(&mddev->active_io);
-}
-
 static inline int __must_check mddev_lock(struct mddev *mddev)
 {
 	return mutex_lock_interruptible(&mddev->reconfig_mutex);
@@ -641,7 +622,6 @@ struct md_personality
 	int (*start_reshape) (struct mddev *mddev);
 	void (*finish_reshape) (struct mddev *mddev);
 	void (*update_reshape_pos) (struct mddev *mddev);
-	void (*prepare_suspend) (struct mddev *mddev);
 	/* quiesce suspends or resumes internal processing.
 	 * 1 - stop new actions and wait for action io to complete
 	 * 0 - return to normal behaviour
@@ -766,7 +746,6 @@ extern void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **t
 extern void md_wakeup_thread(struct md_thread __rcu *thread);
 extern void md_check_recovery(struct mddev *mddev);
 extern void md_reap_sync_thread(struct mddev *mddev);
-extern int mddev_init_writes_pending(struct mddev *mddev);
 extern bool md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_inc(struct mddev *mddev, struct bio *bi);
 extern void md_write_end(struct mddev *mddev);
@@ -793,7 +772,8 @@ extern int md_integrity_register(struct mddev *mddev);
 extern int md_integrity_add_rdev(struct md_rdev *rdev, struct mddev *mddev);
 extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
 
-extern void mddev_init(struct mddev *mddev);
+extern int mddev_init(struct mddev *mddev);
+extern void mddev_destroy(struct mddev *mddev);
 struct mddev *md_alloc(dev_t dev, char *name);
 void mddev_put(struct mddev *mddev);
 extern int md_run(struct mddev *mddev);
@@ -804,15 +784,14 @@ extern int md_rdev_init(struct md_rdev *rdev);
 extern void md_rdev_clear(struct md_rdev *rdev);
 
 extern void md_handle_request(struct mddev *mddev, struct bio *bio);
-extern void mddev_suspend(struct mddev *mddev);
+extern int mddev_suspend(struct mddev *mddev, bool interruptible);
 extern void mddev_resume(struct mddev *mddev);
 
 extern void md_reload_sb(struct mddev *mddev, int raid_disk);
 extern void md_update_sb(struct mddev *mddev, int force);
-extern void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
-				     bool is_suspend);
-extern void mddev_destroy_serial_pool(struct mddev *mddev, struct md_rdev *rdev,
-				      bool is_suspend);
+extern void mddev_create_serial_pool(struct mddev *mddev, struct md_rdev *rdev);
+extern void mddev_destroy_serial_pool(struct mddev *mddev,
+				      struct md_rdev *rdev);
 struct md_rdev *md_find_rdev_nr_rcu(struct mddev *mddev, int nr);
 struct md_rdev *md_find_rdev_rcu(struct mddev *mddev, dev_t dev);
 
@@ -850,6 +829,33 @@ static inline void mddev_check_write_zeroes(struct mddev *mddev, struct bio *bio
 		mddev->queue->limits.max_write_zeroes_sectors = 0;
 }
 
+static inline int mddev_suspend_and_lock(struct mddev *mddev)
+{
+	int ret;
+
+	ret = mddev_suspend(mddev, true);
+	if (ret)
+		return ret;
+
+	ret = mddev_lock(mddev);
+	if (ret)
+		mddev_resume(mddev);
+
+	return ret;
+}
+
+static inline void mddev_suspend_and_lock_nointr(struct mddev *mddev)
+{
+	mddev_suspend(mddev, false);
+	mutex_lock(&mddev->reconfig_mutex);
+}
+
+static inline void mddev_unlock_and_resume(struct mddev *mddev)
+{
+	mddev_unlock(mddev);
+	mddev_resume(mddev);
+}
+
 struct mdu_array_info_s;
 struct mdu_disk_info_s;
 

drivers/md/raid1.c

@@ -1345,6 +1345,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 	int first_clone;
 	int max_sectors;
 	bool write_behind = false;
+	bool is_discard = (bio_op(bio) == REQ_OP_DISCARD);
 
 	if (mddev_is_clustered(mddev) &&
 	     md_cluster_ops->area_resyncing(mddev, WRITE,
@@ -1405,7 +1406,7 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
 		 * write-mostly, which means we could allocate write behind
 		 * bio later.
 		 */
-		if (rdev && test_bit(WriteMostly, &rdev->flags))
+		if (!is_discard && rdev && test_bit(WriteMostly, &rdev->flags))
 			write_behind = true;
 
 		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
@@ -3122,8 +3123,7 @@ static int raid1_run(struct mddev *mddev)
 			mdname(mddev));
 		return -EIO;
 	}
-	if (mddev_init_writes_pending(mddev) < 0)
-		return -ENOMEM;
+
 	/*
 	 * copy the already verified devices into our private RAID1
 	 * bookkeeping area. [whatever we allocate in run(),

drivers/md/raid10.c

@@ -4154,9 +4154,6 @@ static int raid10_run(struct mddev *mddev)
 	sector_t min_offset_diff = 0;
 	int first = 1;
 
-	if (mddev_init_writes_pending(mddev) < 0)
-		return -ENOMEM;
-
 	if (mddev->private == NULL) {
 		conf = setup_conf(mddev);
 		if (IS_ERR(conf))

drivers/nvme/common/Kconfig

@@ -2,3 +2,16 @@
 
 config NVME_COMMON
        tristate
+
+config NVME_KEYRING
+       bool
+       select KEYS
+
+config NVME_AUTH
+	bool
+	select CRYPTO
+	select CRYPTO_HMAC
+	select CRYPTO_SHA256
+	select CRYPTO_SHA512
+	select CRYPTO_DH
+	select CRYPTO_DH_RFC7919_GROUPS

drivers/nvme/common/Makefile

@@ -4,4 +4,5 @@ ccflags-y			+= -I$(src)
 
 obj-$(CONFIG_NVME_COMMON)	+= nvme-common.o
 
-nvme-common-y			+= auth.o
+nvme-common-$(CONFIG_NVME_AUTH)	+= auth.o
+nvme-common-$(CONFIG_NVME_KEYRING) += keyring.o

drivers/nvme/common/auth.c

@@ -150,6 +150,14 @@ size_t nvme_auth_hmac_hash_len(u8 hmac_id)
 }
 EXPORT_SYMBOL_GPL(nvme_auth_hmac_hash_len);
 
+u32 nvme_auth_key_struct_size(u32 key_len)
+{
+	struct nvme_dhchap_key key;
+
+	return struct_size(&key, key, key_len);
+}
+EXPORT_SYMBOL_GPL(nvme_auth_key_struct_size);
+
 struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret,
 					      u8 key_hash)
 {
@@ -163,14 +171,9 @@ struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret,
 	p = strrchr(secret, ':');
 	if (p)
 		allocated_len = p - secret;
-	key = kzalloc(sizeof(*key), GFP_KERNEL);
+	key = nvme_auth_alloc_key(allocated_len, 0);
 	if (!key)
 		return ERR_PTR(-ENOMEM);
-	key->key = kzalloc(allocated_len, GFP_KERNEL);
-	if (!key->key) {
-		ret = -ENOMEM;
-		goto out_free_key;
-	}
 
 	key_len = base64_decode(secret, allocated_len, key->key);
 	if (key_len < 0) {
@@ -187,14 +190,6 @@ struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret,
 		goto out_free_secret;
 	}
 
-	if (key_hash > 0 &&
-	    (key_len - 4) != nvme_auth_hmac_hash_len(key_hash)) {
-		pr_err("Mismatched key len %d for %s\n", key_len,
-		       nvme_auth_hmac_name(key_hash));
-		ret = -EINVAL;
-		goto out_free_secret;
-	}
-
 	/* The last four bytes is the CRC in little-endian format */
 	key_len -= 4;
 	/*
@@ -213,37 +208,51 @@ struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret,
 	key->hash = key_hash;
 	return key;
 out_free_secret:
-	kfree_sensitive(key->key);
-out_free_key:
-	kfree(key);
+	nvme_auth_free_key(key);
 	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(nvme_auth_extract_key);
 
+struct nvme_dhchap_key *nvme_auth_alloc_key(u32 len, u8 hash)
+{
+	u32 num_bytes = nvme_auth_key_struct_size(len);
+	struct nvme_dhchap_key *key = kzalloc(num_bytes, GFP_KERNEL);
+
+	if (key) {
+		key->len = len;
+		key->hash = hash;
+	}
+	return key;
+}
+EXPORT_SYMBOL_GPL(nvme_auth_alloc_key);
+
 void nvme_auth_free_key(struct nvme_dhchap_key *key)
 {
 	if (!key)
 		return;
-	kfree_sensitive(key->key);
-	kfree(key);
+	kfree_sensitive(key);
 }
 EXPORT_SYMBOL_GPL(nvme_auth_free_key);
 
-u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn)
+struct nvme_dhchap_key *nvme_auth_transform_key(
+		struct nvme_dhchap_key *key, char *nqn)
 {
 	const char *hmac_name;
 	struct crypto_shash *key_tfm;
 	struct shash_desc *shash;
-	u8 *transformed_key;
-	int ret;
+	struct nvme_dhchap_key *transformed_key;
+	int ret, key_len;
 
-	if (!key || !key->key) {
+	if (!key) {
 		pr_warn("No key specified\n");
 		return ERR_PTR(-ENOKEY);
 	}
 	if (key->hash == 0) {
-		transformed_key = kmemdup(key->key, key->len, GFP_KERNEL);
-		return transformed_key ? transformed_key : ERR_PTR(-ENOMEM);
+		key_len = nvme_auth_key_struct_size(key->len);
+		transformed_key = kmemdup(key, key_len, GFP_KERNEL);
+		if (!transformed_key)
+			return ERR_PTR(-ENOMEM);
+		return transformed_key;
 	}
 	hmac_name = nvme_auth_hmac_name(key->hash);
 	if (!hmac_name) {
@@ -253,7 +262,7 @@ u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn)
 
 	key_tfm = crypto_alloc_shash(hmac_name, 0, 0);
 	if (IS_ERR(key_tfm))
-		return (u8 *)key_tfm;
+		return ERR_CAST(key_tfm);
 
 	shash = kmalloc(sizeof(struct shash_desc) +
 			crypto_shash_descsize(key_tfm),
@@ -263,7 +272,8 @@ u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn)
 		goto out_free_key;
 	}
 
-	transformed_key = kzalloc(crypto_shash_digestsize(key_tfm), GFP_KERNEL);
+	key_len = crypto_shash_digestsize(key_tfm);
+	transformed_key = nvme_auth_alloc_key(key_len, key->hash);
 	if (!transformed_key) {
 		ret = -ENOMEM;
 		goto out_free_shash;
@@ -282,7 +292,7 @@ u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn)
 	ret = crypto_shash_update(shash, "NVMe-over-Fabrics", 17);
 	if (ret < 0)
 		goto out_free_transformed_key;
-	ret = crypto_shash_final(shash, transformed_key);
+	ret = crypto_shash_final(shash, transformed_key->key);
 	if (ret < 0)
 		goto out_free_transformed_key;
 
@@ -292,7 +302,7 @@ u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn)
 	return transformed_key;
 
 out_free_transformed_key:
-	kfree_sensitive(transformed_key);
+	nvme_auth_free_key(transformed_key);
 out_free_shash:
 	kfree(shash);
 out_free_key:

drivers/nvme/host/Kconfig

@@ -92,16 +92,26 @@ config NVME_TCP
 
 	  If unsure, say N.
 
-config NVME_AUTH
+config NVME_TCP_TLS
+	bool "NVMe over Fabrics TCP TLS encryption support"
+	depends on NVME_TCP
+	select NVME_COMMON
+	select NVME_KEYRING
+	select NET_HANDSHAKE
+	select KEYS
+	help
+	  Enables TLS encryption for NVMe TCP using the netlink handshake API.
+
+	  The TLS handshake daemon is availble at
+	  https://github.com/oracle/ktls-utils.
+
+	  If unsure, say N.
+
+config NVME_HOST_AUTH
 	bool "NVM Express over Fabrics In-Band Authentication"
 	depends on NVME_CORE
 	select NVME_COMMON
-	select CRYPTO
-	select CRYPTO_HMAC
-	select CRYPTO_SHA256
-	select CRYPTO_SHA512
-	select CRYPTO_DH
-	select CRYPTO_DH_RFC7919_GROUPS
+	select NVME_AUTH
 	help
 	  This provides support for NVMe over Fabrics In-Band Authentication.
 

drivers/nvme/host/pci.c

@@ -924,7 +924,6 @@ static bool nvme_prep_rq_batch(struct nvme_queue *nvmeq, struct request *req)
 	if (unlikely(!nvme_check_ready(&nvmeq->dev->ctrl, req, true)))
 		return false;
 
-	req->mq_hctx->tags->rqs[req->tag] = req;
 	return nvme_prep_rq(nvmeq->dev, req) == BLK_STS_OK;
 }