Merge tag 'for-6.15/block-20250322' of git://git.kernel.dk/linux

Pull block updates from Jens Axboe:

 - Fixes for integrity handling

 - NVMe pull request via Keith:
      - Secure concatenation for TCP transport (Hannes)
      - Multipath sysfs visibility (Nilay)
      - Various cleanups (Qasim, Baruch, Wang, Chen, Mike, Damien, Li)
      - Correct use of 64-bit BARs for pci-epf target (Niklas)
      - Socket fix for selinux when used in containers (Peijie)

 - MD pull request via Yu:
      - fix recovery can preempt resync (Li Nan)
      - fix md-bitmap IO limit (Su Yue)
      - fix raid10 discard with REQ_NOWAIT (Xiao Ni)
      - fix raid1 memory leak (Zheng Qixing)
      - fix mddev uaf (Yu Kuai)
      - fix raid1,raid10 IO flags (Yu Kuai)
      - some refactor and cleanup (Yu Kuai)

 - Series cleaning up and fixing bugs in the bad block handling code

 - Improve support for write failure simulation in null_blk

 - Various lock ordering fixes

 - Fixes for locking for debugfs attributes

 - Various ublk related fixes and improvements

 - Cleanups for blk-rq-qos wait handling

 - blk-throttle fixes

 - Fixes for loop dio and sync handling

 - Fixes and cleanups for the auto-PI code

 - Block side support for hardware encryption keys in blk-crypto

 - Various cleanups and fixes

* tag 'for-6.15/block-20250322' of git://git.kernel.dk/linux: (105 commits)
  nvmet: replace max(a, min(b, c)) by clamp(val, lo, hi)
  nvme-tcp: fix selinux denied when calling sock_sendmsg
  nvmet: pci-epf: Always configure BAR0 as 64-bit
  nvmet: Remove duplicate uuid_copy
  nvme: zns: Simplify nvme_zone_parse_entry()
  nvmet: pci-epf: Remove redundant 'flush_workqueue()' calls
  nvmet-fc: Remove unused functions
  nvme-pci: remove stale comment
  nvme-fc: Utilise min3() to simplify queue count calculation
  nvme-multipath: Add visibility for queue-depth io-policy
  nvme-multipath: Add visibility for numa io-policy
  nvme-multipath: Add visibility for round-robin io-policy
  nvmet: add tls_concat and tls_key debugfs entries
  nvmet-tcp: support secure channel concatenation
  nvmet: Add 'sq' argument to alloc_ctrl_args
  nvme-fabrics: reset admin connection for secure concatenation
  nvme-tcp: request secure channel concatenation
  nvme-keyring: add nvme_tls_psk_refresh()
  nvme: add nvme_auth_derive_tls_psk()
  nvme: add nvme_auth_generate_digest()
  ...

1 files changed, 63 insertions, 10 deletions

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1994a11ff903..5905f277057b 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -816,6 +816,41 @@ int blkg_conf_open_bdev(struct blkg_conf_ctx *ctx)
 	ctx->bdev = bdev;
 	return 0;
 }
+/*
+ * Similar to blkg_conf_open_bdev, but additionally freezes the queue,
+ * acquires q->elevator_lock, and ensures the correct locking order
+ * between q->elevator_lock and q->rq_qos_mutex.
+ *
+ * This function returns negative error on failure. On success it returns
+ * memflags which must be saved and later passed to blkg_conf_exit_frozen
+ * for restoring the memalloc scope.
+ */
+unsigned long __must_check blkg_conf_open_bdev_frozen(struct blkg_conf_ctx *ctx)
+{
+	int ret;
+	unsigned long memflags;
+
+	if (ctx->bdev)
+		return -EINVAL;
+
+	ret = blkg_conf_open_bdev(ctx);
+	if (ret < 0)
+		return ret;
+	/*
+	 * At this point, we haven’t started protecting anything related to QoS,
+	 * so we release q->rq_qos_mutex here, which was first acquired in blkg_
+	 * conf_open_bdev. Later, we re-acquire q->rq_qos_mutex after freezing
+	 * the queue and acquiring q->elevator_lock to maintain the correct
+	 * locking order.
+	 */
+	mutex_unlock(&ctx->bdev->bd_queue->rq_qos_mutex);
+
+	memflags = blk_mq_freeze_queue(ctx->bdev->bd_queue);
+	mutex_lock(&ctx->bdev->bd_queue->elevator_lock);
+	mutex_lock(&ctx->bdev->bd_queue->rq_qos_mutex);
+
+	return memflags;
+}
 
 /**
  * blkg_conf_prep - parse and prepare for per-blkg config update
@@ -972,6 +1007,22 @@ void blkg_conf_exit(struct blkg_conf_ctx *ctx)
 }
 EXPORT_SYMBOL_GPL(blkg_conf_exit);
 
+/*
+ * Similar to blkg_conf_exit, but also unfreezes the queue and releases
+ * q->elevator_lock. Should be used when blkg_conf_open_bdev_frozen
+ * is used to open the bdev.
+ */
+void blkg_conf_exit_frozen(struct blkg_conf_ctx *ctx, unsigned long memflags)
+{
+	if (ctx->bdev) {
+		struct request_queue *q = ctx->bdev->bd_queue;
+
+		blkg_conf_exit(ctx);
+		mutex_unlock(&q->elevator_lock);
+		blk_mq_unfreeze_queue(q, memflags);
+	}
+}
+
 static void blkg_iostat_add(struct blkg_iostat *dst, struct blkg_iostat *src)
 {
 	int i;
@@ -1728,27 +1779,27 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 	struct blkcg *blkcg;
 	int i, ret;
 
+	/*
+	 * Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs, and policy
+	 * without pd_alloc_fn/pd_free_fn can't be activated.
+	 */
+	if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) ||
+	    (!pol->pd_alloc_fn ^ !pol->pd_free_fn))
+		return -EINVAL;
+
 	mutex_lock(&blkcg_pol_register_mutex);
 	mutex_lock(&blkcg_pol_mutex);
 
 	/* find an empty slot */
-	ret = -ENOSPC;
 	for (i = 0; i < BLKCG_MAX_POLS; i++)
 		if (!blkcg_policy[i])
 			break;
 	if (i >= BLKCG_MAX_POLS) {
 		pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n");
+		ret = -ENOSPC;
 		goto err_unlock;
 	}
 
-	/*
-	 * Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs, and policy
-	 * without pd_alloc_fn/pd_free_fn can't be activated.
-	 */
-	if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) ||
-	    (!pol->pd_alloc_fn ^ !pol->pd_free_fn))
-		goto err_unlock;
-
 	/* register @pol */
 	pol->plid = i;
 	blkcg_policy[pol->plid] = pol;
@@ -1759,8 +1810,10 @@ int blkcg_policy_register(struct blkcg_policy *pol)
 			struct blkcg_policy_data *cpd;
 
 			cpd = pol->cpd_alloc_fn(GFP_KERNEL);
-			if (!cpd)
+			if (!cpd) {
+				ret = -ENOMEM;
 				goto err_free_cpds;
+			}
 
 			blkcg->cpd[pol->plid] = cpd;
 			cpd->blkcg = blkcg;