Merge tag 'vfs-6.6-merge-2' of ssh://gitolite.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull filesystem freezing updates from Darrick Wong:

New code for 6.6:

 * Allow the kernel to initiate a freeze of a filesystem.  The kernel
   and userspace can both hold a freeze on a filesystem at the same
   time; the freeze is not lifted until /both/ holders lift it.  This
   will enable us to fix a longstanding bug in XFS online fsck.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Message-Id: <20230822182604.GB11286@frogsfrogsfrogs>
Signed-off-by: Christian Brauner <brauner@kernel.org>

18 files changed, 97 insertions, 31 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 0587354ba678..9c59409104f6 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -578,7 +578,6 @@
 		*(.text.unlikely .text.unlikely.*)			\
 		*(.text.unknown .text.unknown.*)			\
 		NOINSTR_TEXT						\
-		*(.text..refcount)					\
 		*(.ref.text)						\
 		*(.text.asan.* .text.tsan.*)				\
 	MEM_KEEP(init.text*)						\
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index e95b4837e5a3..f9544d9b670d 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -583,15 +583,14 @@ void drm_sched_entity_set_priority(struct drm_sched_entity *entity,
 bool drm_sched_entity_is_ready(struct drm_sched_entity *entity);
 int drm_sched_entity_error(struct drm_sched_entity *entity);
 
-void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence,
-				struct dma_fence *fence);
 struct drm_sched_fence *drm_sched_fence_alloc(
 	struct drm_sched_entity *s_entity, void *owner);
 void drm_sched_fence_init(struct drm_sched_fence *fence,
 			  struct drm_sched_entity *entity);
 void drm_sched_fence_free(struct drm_sched_fence *fence);
 
-void drm_sched_fence_scheduled(struct drm_sched_fence *fence);
+void drm_sched_fence_scheduled(struct drm_sched_fence *fence,
+			       struct dma_fence *parent);
 void drm_sched_fence_finished(struct drm_sched_fence *fence, int result);
 
 unsigned long drm_sched_suspend_timeout(struct drm_gpu_scheduler *sched);
diff --git a/include/linux/blk-crypto-profile.h b/include/linux/blk-crypto-profile.h
index e6802b69cdd6..90ab33cb5d0e 100644
--- a/include/linux/blk-crypto-profile.h
+++ b/include/linux/blk-crypto-profile.h
@@ -111,6 +111,7 @@ struct blk_crypto_profile {
 	 * keyslots while ensuring that they can't be changed concurrently.
 	 */
 	struct rw_semaphore lock;
+	struct lock_class_key lockdep_key;
 
 	/* List of idle slots, with least recently used slot at front */
 	wait_queue_head_t idle_slots_wait_queue;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 2b7fb8e87793..b96e00499f9e 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -158,13 +158,13 @@ struct request {
 
 	/*
 	 * The rb_node is only used inside the io scheduler, requests
-	 * are pruned when moved to the dispatch queue. So let the
-	 * completion_data share space with the rb_node.
+	 * are pruned when moved to the dispatch queue. special_vec must
+	 * only be used if RQF_SPECIAL_PAYLOAD is set, and those cannot be
+	 * insert into an IO scheduler.
 	 */
 	union {
 		struct rb_node rb_node;	/* sort/lookup */
 		struct bio_vec special_vec;
-		void *completion_data;
 	};
 
 	/*
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index d54b595a0fe0..0d678e9a7b24 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -606,7 +606,7 @@ static inline signed long dma_fence_wait(struct dma_fence *fence, bool intr)
 void dma_fence_set_deadline(struct dma_fence *fence, ktime_t deadline);
 
 struct dma_fence *dma_fence_get_stub(void);
-struct dma_fence *dma_fence_allocate_private_stub(void);
+struct dma_fence *dma_fence_allocate_private_stub(ktime_t timestamp);
 u64 dma_fence_context_alloc(unsigned num);
 
 extern const struct dma_fence_ops dma_fence_array_ops;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a63da68305e9..ca8ceccde3d6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1149,7 +1149,8 @@ enum {
 #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
 
 struct sb_writers {
-	int				frozen;		/* Is sb frozen? */
+	unsigned short			frozen;		/* Is sb frozen? */
+	unsigned short			freeze_holders;	/* Who froze fs? */
 	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
 };
 
@@ -1904,6 +1905,10 @@ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 					struct file *dst_file, loff_t dst_pos,
 					loff_t len, unsigned int remap_flags);
 
+enum freeze_holder {
+	FREEZE_HOLDER_KERNEL	= (1U << 0),
+	FREEZE_HOLDER_USERSPACE	= (1U << 1),
+};
 
 struct super_operations {
    	struct inode *(*alloc_inode)(struct super_block *sb);
@@ -1916,9 +1921,9 @@ struct super_operations {
 	void (*evict_inode) (struct inode *);
 	void (*put_super) (struct super_block *);
 	int (*sync_fs)(struct super_block *sb, int wait);
-	int (*freeze_super) (struct super_block *);
+	int (*freeze_super) (struct super_block *, enum freeze_holder who);
 	int (*freeze_fs) (struct super_block *);
-	int (*thaw_super) (struct super_block *);
+	int (*thaw_super) (struct super_block *, enum freeze_holder who);
 	int (*unfreeze_fs) (struct super_block *);
 	int (*statfs) (struct dentry *, struct kstatfs *);
 	int (*remount_fs) (struct super_block *, int *, char *);
@@ -2292,8 +2297,8 @@ extern int unregister_filesystem(struct file_system_type *);
 extern int vfs_statfs(const struct path *, struct kstatfs *);
 extern int user_statfs(const char __user *, struct kstatfs *);
 extern int fd_statfs(int, struct kstatfs *);
-extern int freeze_super(struct super_block *super);
-extern int thaw_super(struct super_block *super);
+int freeze_super(struct super_block *super, enum freeze_holder who);
+int thaw_super(struct super_block *super, enum freeze_holder who);
 extern __printf(2, 3)
 int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
 extern int super_setup_bdi(struct super_block *sb);
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 8e59bd954153..ce156c7704ee 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -41,6 +41,15 @@ struct ftrace_ops;
 struct ftrace_regs;
 struct dyn_ftrace;
 
+char *arch_ftrace_match_adjust(char *str, const char *search);
+
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL
+struct fgraph_ret_regs;
+unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs);
+#else
+unsigned long ftrace_return_to_handler(unsigned long frame_pointer);
+#endif
+
 #ifdef CONFIG_FUNCTION_TRACER
 /*
  * If the arch's mcount caller does not support all of ftrace's
diff --git a/include/linux/ism.h b/include/linux/ism.h
index ea2bcdae7401..9a4c204df3da 100644
--- a/include/linux/ism.h
+++ b/include/linux/ism.h
@@ -44,9 +44,7 @@ struct ism_dev {
 	u64 local_gid;
 	int ieq_idx;
 
-	atomic_t free_clients_cnt;
-	atomic_t add_dev_cnt;
-	wait_queue_head_t waitq;
+	struct ism_client *subs[MAX_CLIENTS];
 };
 
 struct ism_event {
@@ -68,9 +66,6 @@ struct ism_client {
 	 */
 	void (*handle_irq)(struct ism_dev *dev, unsigned int bit, u16 dmbemask);
 	/* Private area - don't touch! */
-	struct work_struct remove_work;
-	struct work_struct add_work;
-	struct ism_dev *tgt_ism;
 	u8 id;
 };
 
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 182b6d614eb1..26dd3f859d9d 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -473,7 +473,7 @@ struct nvme_id_ns_nvm {
 };
 
 enum {
-	NVME_ID_NS_NVM_STS_MASK		= 0x3f,
+	NVME_ID_NS_NVM_STS_MASK		= 0x7f,
 	NVME_ID_NS_NVM_GUARD_SHIFT	= 7,
 	NVME_ID_NS_NVM_GUARD_MASK	= 0x3,
 };
diff --git a/include/linux/psi.h b/include/linux/psi.h
index ab26200c2803..e0745873e3f2 100644
--- a/include/linux/psi.h
+++ b/include/linux/psi.h
@@ -23,8 +23,9 @@ void psi_memstall_enter(unsigned long *flags);
 void psi_memstall_leave(unsigned long *flags);
 
 int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
-struct psi_trigger *psi_trigger_create(struct psi_group *group,
-			char *buf, enum psi_res res, struct file *file);
+struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf,
+				       enum psi_res res, struct file *file,
+				       struct kernfs_open_file *of);
 void psi_trigger_destroy(struct psi_trigger *t);
 
 __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file,
diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index 040c089581c6..f1fd3a8044e0 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -137,6 +137,9 @@ struct psi_trigger {
 	/* Wait queue for polling */
 	wait_queue_head_t event_wait;
 
+	/* Kernfs file for cgroup triggers */
+	struct kernfs_open_file *of;
+
 	/* Pending event flag */
 	int event;
 
diff --git a/include/linux/rethook.h b/include/linux/rethook.h
index fdf26cd0e742..26b6f3c81a76 100644
--- a/include/linux/rethook.h
+++ b/include/linux/rethook.h
@@ -59,6 +59,7 @@ struct rethook_node {
 };
 
 struct rethook *rethook_alloc(void *data, rethook_handler_t handler);
+void rethook_stop(struct rethook *rh);
 void rethook_free(struct rethook *rh);
 void rethook_add_node(struct rethook *rh, struct rethook_node *node);
 struct rethook_node *rethook_try_get(struct rethook *rh);
diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h
index 9334371c94e2..f7dd950ff250 100644
--- a/include/net/netfilter/nf_conntrack_tuple.h
+++ b/include/net/netfilter/nf_conntrack_tuple.h
@@ -67,6 +67,9 @@ struct nf_conntrack_tuple {
 		/* The protocol. */
 		u_int8_t protonum;
 
+		/* The direction must be ignored for the tuplehash */
+		struct { } __nfct_hash_offsetend;
+
 		/* The direction (for tuplehash) */
 		u_int8_t dir;
 	} dst;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 84f2fd85fd5a..640441a2f926 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1211,6 +1211,29 @@ int __nft_release_basechain(struct nft_ctx *ctx);
 
 unsigned int nft_do_chain(struct nft_pktinfo *pkt, void *priv);
 
+static inline bool nft_use_inc(u32 *use)
+{
+	if (*use == UINT_MAX)
+		return false;
+
+	(*use)++;
+
+	return true;
+}
+
+static inline void nft_use_dec(u32 *use)
+{
+	WARN_ON_ONCE((*use)-- == 0);
+}
+
+/* For error and abort path: restore use counter to previous state. */
+static inline void nft_use_inc_restore(u32 *use)
+{
+	WARN_ON_ONCE(!nft_use_inc(use));
+}
+
+#define nft_use_dec_restore	nft_use_dec
+
 /**
  *	struct nft_table - nf_tables table
  *
@@ -1296,8 +1319,8 @@ struct nft_object {
 	struct list_head		list;
 	struct rhlist_head		rhlhead;
 	struct nft_object_hash_key	key;
-	u32				genmask:2,
-					use:30;
+	u32				genmask:2;
+	u32				use;
 	u64				handle;
 	u16				udlen;
 	u8				*udata;
@@ -1399,8 +1422,8 @@ struct nft_flowtable {
 	char				*name;
 	int				hooknum;
 	int				ops_len;
-	u32				genmask:2,
-					use:30;
+	u32				genmask:2;
+	u32				use;
 	u64				handle;
 	/* runtime data below here */
 	struct list_head		hook_list ____cacheline_aligned;
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index e98aac9d5ad5..15960564e0c3 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -134,7 +134,7 @@ extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1];
  */
 static inline unsigned int psched_mtu(const struct net_device *dev)
 {
-	return dev->mtu + dev->hard_header_len;
+	return READ_ONCE(dev->mtu) + dev->hard_header_len;
 }
 
 static inline struct net *qdisc_net(struct Qdisc *q)
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 22aae505c813..a8c2817335b9 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -663,6 +663,7 @@ struct ocelot_ops {
 			      struct flow_stats *stats);
 	void (*cut_through_fwd)(struct ocelot *ocelot);
 	void (*tas_clock_adjust)(struct ocelot *ocelot);
+	void (*tas_guard_bands_update)(struct ocelot *ocelot, int port);
 	void (*update_stats)(struct ocelot *ocelot);
 };
 
@@ -863,12 +864,12 @@ struct ocelot {
 	struct mutex			stat_view_lock;
 	/* Lock for serializing access to the MAC table */
 	struct mutex			mact_lock;
-	/* Lock for serializing forwarding domain changes */
+	/* Lock for serializing forwarding domain changes, including the
+	 * configuration of the Time-Aware Shaper, MAC Merge layer and
+	 * cut-through forwarding, on which it depends
+	 */
 	struct mutex			fwd_domain_lock;
 
-	/* Lock for serializing Time-Aware Shaper changes */
-	struct mutex			tas_lock;
-
 	struct workqueue_struct		*owq;
 
 	u8				ptp:1;
diff --git a/include/uapi/scsi/scsi_bsg_ufs.h b/include/uapi/scsi/scsi_bsg_ufs.h
index 2801b65299aa..fd3f9e5ee241 100644
--- a/include/uapi/scsi/scsi_bsg_ufs.h
+++ b/include/uapi/scsi/scsi_bsg_ufs.h
@@ -71,6 +71,31 @@ struct utp_upiu_query {
 };
 
 /**
+ * struct utp_upiu_query_v4_0 - upiu request buffer structure for
+ * query request >= UFS 4.0 spec.
+ * @opcode: command to perform B-0
+ * @idn: a value that indicates the particular type of data B-1
+ * @index: Index to further identify data B-2
+ * @selector: Index to further identify data B-3
+ * @osf4: spec field B-5
+ * @osf5: spec field B 6,7
+ * @osf6: spec field DW 8,9
+ * @osf7: spec field DW 10,11
+ */
+struct utp_upiu_query_v4_0 {
+	__u8 opcode;
+	__u8 idn;
+	__u8 index;
+	__u8 selector;
+	__u8 osf3;
+	__u8 osf4;
+	__be16 osf5;
+	__be32 osf6;
+	__be32 osf7;
+	__be32 reserved;
+};
+
+/**
  * struct utp_upiu_cmd - Command UPIU structure
  * @data_transfer_len: Data Transfer Length DW-3
  * @cdb: Command Descriptor Block CDB DW-4 to DW-7
diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h
index 4e8d6240e589..198cb391f9db 100644
--- a/include/ufs/ufs.h
+++ b/include/ufs/ufs.h
@@ -170,6 +170,7 @@ enum attr_idn {
 	QUERY_ATTR_IDN_WB_BUFF_LIFE_TIME_EST    = 0x1E,
 	QUERY_ATTR_IDN_CURR_WB_BUFF_SIZE        = 0x1F,
 	QUERY_ATTR_IDN_EXT_IID_EN		= 0x2A,
+	QUERY_ATTR_IDN_TIMESTAMP		= 0x30
 };
 
 /* Descriptor idn for Query requests */