Merge tag 'vfs-7.3-rc3.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs

Pull vfs fixes from Christian Brauner:

 - netfs:

     - Fix an uninitialized return value in netfs_unbuffered_write()
       when preparing the first subrequest fails

     - For partial unbuffered/DIO writes return the amount transferred
       rather than an error

     - Update i_size with the amount actually written when a partial
       transfer ends in an error

     - Fix a subrequest reference leak when the io_iter ends up empty

     - Handle netfs_alloc_subrequest() failure during unbuffered writes

     - Load all readahead folios into the rolling buffer upfront and
       drop the readahead references once the first subrequest is
       dispatched

     - Mark folios for copy-to-cache while issuing subrequests

     - Fix read progress reporting

 - afs:

     - Add the missing kunmap in the error path of afs_dir_search_bucket()

     - Fix a double kunmap in afs_edit_dir_remove()

     - Don't free an existing server's endpoint state when cleaning up a
       candidate server in afs_lookup_server()

     - Unbind peers removed from a server's address list

 - ufs:

     - Load the cylinder group metadata before creating the root dentry

     - Validate the cylinder group index and rotor positions before
       caching them

     - Treat an unreadable directory block as not empty

 - exec:

     - Close the close-on-exec files before taking exec_update_lock

       Closing a file can block on the filesystem, so a hung filesystem
       blocked everything that takes exec_update_lock and a FUSE server
       inspecting the calling process could deadlock

     - Drop the bprm loader before closing bprm->file in free_bprm()

 - exit: Hold a reference to thread_pid across proc_flush_pid()

 - reboot: Fix a use-after-free on cad_pid

 - nsfs: Keep the namespace tree fields out of the rcu_head used by
   kfree_rcu()

 - nstree: Check listing permission before taking a namespace
   reference in listns()

 - super: Return 0 when a nested thaw drops its hold while other
   freezers remain

 - ext4: Don't set I_METADATA_WRITEBACK during fastcommit replay

 - adfs: Free s_fs_info in ->kill_sb()

 - autofs: Free the inode info allocated in autofs_fill_super() when
   the root inode allocation fails

 - ovl: Return EINVAL instead of EIO on a user namespace mismatch now
   that it's a plain refusal and not an internal error

 - cachefiles: Don't cast the variable-length coherency data to a
   __be64 in the coherency tracepoint

* tag 'vfs-7.3-rc3.fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/vfs/vfs: (28 commits)
  nstree: check listing permission before taking a namespace reference
  exec: do_close_on_exec() before taking exec_update_lock
  exit: hold a reference to thread_pid across proc_flush_pid
  fs: autofs: fix memory leak in autofs_fill_super()
  exec: Drop bprm loader before closing bprm->file
  afs: Clear stale peer app data after address list changes
  afs: Fix incorrect free in candidate cleanup in afs_lookup_server()
  afs: Fix double-unmap of directory block
  afs: Fix missing kunmap in afs_dir_search_bucket()
  ovl: return EINVAL instead of EIO in case of mismatched user_ns
  reboot: fix cad_pid use-after-free race
  cachefiles: Fix potential UAF/KASAN warning
  netfs: Fix read progress reporting
  netfs: Mark folios with COPY_TO_CACHE whilst issuing subreqs
  netfs: Fix readahead synchronisation issues by loading all folios upfront
  netfs: break unbuffered write when netfs_alloc_subrequest() fails
  netfs: Fix subreq ref leak
  netfs: Fix i_size update for partial transfer
  netfs: Fix error vs transferred passed to ->ki_complete()
  netfs: Fix unbuffered/DIO write partial transfer error return
  ...

7 files changed, 55 insertions, 18 deletions

diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index f837a501008c..b4dd32863dd4 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -246,6 +246,7 @@ struct netfs_io_request {
 	unsigned long long	submitted;	/* Amount submitted for I/O so far */
 	unsigned long long	len;		/* Length of the request */
 	size_t			transferred;	/* Amount to be indicated as transferred */
+	size_t			progress_at;	/* Report read progress when hit this much read */
 	long			error;		/* 0 or error that occurred */
 	unsigned long long	i_size;		/* Size of the file */
 	unsigned long long	start;		/* Start position */
@@ -262,7 +263,6 @@ struct netfs_io_request {
 	atomic_t		subreq_counter;	/* Next subreq->debug_index */
 	unsigned int		nr_group_rel;	/* Number of refs to release on ->group */
 	spinlock_t		lock;		/* Lock for queuing subreqs */
-	unsigned char		front_folio_order; /* Order (size) of front folio */
 	enum netfs_io_origin	origin;		/* Origin of the request */
 	bool			direct_bv_unpin; /* T if direct_bv[] must be unpinned */
 	refcount_t		ref;
@@ -275,9 +275,10 @@ struct netfs_io_request {
 #define NETFS_RREQ_SHORT_TRANSFER	5	/* Set if we have a short transfer */
 #define NETFS_RREQ_OFFLOAD_COLLECTION	8	/* Offload collection to workqueue */
 #define NETFS_RREQ_NO_UNLOCK_FOLIO	9	/* Don't unlock no_unlock_folio on completion */
-#define NETFS_RREQ_FOLIO_COPY_TO_CACHE	10	/* Copy current folio to cache from read */
+#define NETFS_RREQ_CANCEL_CACHING	10	/* Set to cancel caching */
 #define NETFS_RREQ_UPLOAD_TO_SERVER	11	/* Need to write to the server */
 #define NETFS_RREQ_USE_IO_ITER		12	/* Use ->io_iter rather than ->i_pages */
+#define NETFS_RREQ_NEED_PUT_RA_REFS	17	/* Need to put the folio refs RA gave us */
 #define NETFS_RREQ_USE_PGPRIV2		31	/* [DEPRECATED] Use PG_private_2 to mark
 						 * write to cache on read */
 	const struct netfs_request_ops *netfs_ops;
diff --git a/include/linux/ns/ns_common_types.h b/include/linux/ns/ns_common_types.h
index ea45c54e4435..6ed6b497831c 100644
--- a/include/linux/ns/ns_common_types.h
+++ b/include/linux/ns/ns_common_types.h
@@ -116,10 +116,8 @@ struct ns_common {
 	struct dentry *stashed;
 	const struct proc_ns_operations *ops;
 	unsigned int inum;
-	union {
-		struct ns_tree;
-		struct rcu_head ns_rcu;
-	};
+	struct ns_tree;
+	struct rcu_head ns_rcu;
 };
 
 #define to_ns_common(__ns)                                    \
diff --git a/include/linux/rolling_buffer.h b/include/linux/rolling_buffer.h
index 9e5dad29669c..a97f7cfaacaa 100644
--- a/include/linux/rolling_buffer.h
+++ b/include/linux/rolling_buffer.h
@@ -45,9 +45,9 @@ struct rolling_buffer_snapshot {
 int rolling_buffer_init(struct rolling_buffer *roll, unsigned int rreq_id,
 			unsigned int direction, gfp_t gfp);
 int rolling_buffer_make_space(struct rolling_buffer *roll, gfp_t gfp);
-ssize_t rolling_buffer_load_from_ra(struct rolling_buffer *roll,
-				    struct readahead_control *ractl,
-				    struct folio_batch *put_batch);
+ssize_t rolling_buffer_bulk_load_from_ra(struct rolling_buffer *roll,
+					 struct readahead_control *ractl,
+					 unsigned int rreq_id, gfp_t gfp);
 ssize_t rolling_buffer_append(struct rolling_buffer *roll, struct folio *folio,
 			      unsigned int flags, gfp_t gfp);
 struct folio_queue *rolling_buffer_delete_spent(struct rolling_buffer *roll);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 8b3d47a325cc..705970d07614 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1787,7 +1787,7 @@ static inline bool is_lazy_mmu_mode_active(void)
 }
 #endif
 
-extern struct pid *cad_pid;
+extern struct pid __rcu *cad_pid;
 
 /*
  * Per process flags
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index 584ae88b435e..d45a5476b97d 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -562,10 +562,7 @@ static inline sigset_t *sigmask_to_save(void)
 	return res;
 }
 
-static inline int kill_cad_pid(int sig, int priv)
-{
-	return kill_pid(cad_pid, sig, priv);
-}
+int kill_cad_pid(int sig, int priv);
 
 /* These can be the second arg to send_sig_info/send_group_sig_info.  */
 #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0)
diff --git a/include/trace/events/cachefiles.h b/include/trace/events/cachefiles.h
index 9259bc71049e..e3101410e8b2 100644
--- a/include/trace/events/cachefiles.h
+++ b/include/trace/events/cachefiles.h
@@ -372,7 +372,7 @@ TRACE_EVENT(cachefiles_rename,
 TRACE_EVENT(cachefiles_coherency,
 	    TP_PROTO(struct cachefiles_object *obj,
 		     ino_t ino,
-		     u64 disk_aux,
+		     const void *disk_aux,
 		     enum cachefiles_content content,
 		     enum cachefiles_coherency_trace why),
 
@@ -389,12 +389,27 @@ TRACE_EVENT(cachefiles_coherency,
 			     ),
 
 	    TP_fast_assign(
+		    union {
+			    __be16 s[4];
+			    __be64 ll;
+		    } x;
+
 		    __entry->obj	= obj->debug_id;
 		    __entry->why	= why;
 		    __entry->content	= content;
 		    __entry->ino	= ino;
 		    __entry->aux	= be64_to_cpup((__be64 *)obj->cookie->inline_aux);
-		    __entry->disk_aux	= disk_aux;
+
+		    /* cachefiles_xattr::data is 2-byte aligned but not 8-byte aligned. */
+		    if (disk_aux) {
+			    x.s[0] = ((__be16 *)disk_aux)[0];
+			    x.s[1] = ((__be16 *)disk_aux)[1];
+			    x.s[2] = ((__be16 *)disk_aux)[2];
+			    x.s[3] = ((__be16 *)disk_aux)[3];
+			    __entry->disk_aux = be64_to_cpu(x.ll);
+		    } else {
+			    __entry->disk_aux = 0;
+		    }
 			   ),
 
 	    TP_printk("o=%08x %s B=%llx c=%u aux=%llx dsk=%llx",
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index 082cb03c6131..3fec3e8f91c8 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -59,6 +59,7 @@
 	EM(netfs_rreq_trace_free,		"FREE   ")	\
 	EM(netfs_rreq_trace_intr,		"INTR   ")	\
 	EM(netfs_rreq_trace_ki_complete,	"KI-CMPL")	\
+	EM(netfs_rreq_trace_ra_put_ref,		"RA-PUT ")	\
 	EM(netfs_rreq_trace_recollect,		"RECLLCT")	\
 	EM(netfs_rreq_trace_redirty,		"REDIRTY")	\
 	EM(netfs_rreq_trace_resubmit,		"RESUBMT")	\
@@ -70,9 +71,11 @@
 	EM(netfs_rreq_trace_unpause,		"UNPAUSE")	\
 	EM(netfs_rreq_trace_wait_ip,		"WAIT-IP")	\
 	EM(netfs_rreq_trace_wait_pause,		"--PAUSED--")	\
+	EM(netfs_rreq_trace_wait_put_ra_refs,	"WAIT-P-RA")	\
 	EM(netfs_rreq_trace_wait_quiesce,	"WAIT-QUIESCE")	\
 	EM(netfs_rreq_trace_waited_ip,		"DONE-IP")	\
 	EM(netfs_rreq_trace_waited_pause,	"--UNPAUSED--")	\
+	EM(netfs_rreq_trace_waited_put_ra_refs,	"DONE-P-RA")	\
 	EM(netfs_rreq_trace_waited_quiesce,	"DONE-QUIESCE")	\
 	EM(netfs_rreq_trace_wake_ip,		"WAKE-IP")	\
 	EM(netfs_rreq_trace_wake_queue,		"WAKE-Q ")	\
@@ -195,7 +198,6 @@
 	EM(netfs_folio_trace_clear_cc,		"clear-cc")	\
 	EM(netfs_folio_trace_clear_g,		"clear-g")	\
 	EM(netfs_folio_trace_clear_s,		"clear-s")	\
-	EM(netfs_folio_trace_copy_to_cache,	"mark-copy")	\
 	EM(netfs_folio_trace_end_copy,		"end-copy")	\
 	EM(netfs_folio_trace_filled_gaps,	"filled-gaps")	\
 	EM(netfs_folio_trace_invalidate_all,	"inval-all")	\
@@ -206,16 +208,19 @@
 	EM(netfs_folio_trace_kill_cc,		"kill-cc")	\
 	EM(netfs_folio_trace_kill_g,		"kill-g")	\
 	EM(netfs_folio_trace_kill_s,		"kill-s")	\
+	EM(netfs_folio_trace_mark_copy,		"mark-copy")	\
 	EM(netfs_folio_trace_mkwrite,		"mkwrite")	\
 	EM(netfs_folio_trace_mkwrite_plus,	"mkwrite+")	\
-	EM(netfs_folio_trace_not_under_wback,	"!wback")	\
 	EM(netfs_folio_trace_not_locked,	"!locked")	\
+	EM(netfs_folio_trace_not_under_wback,	"!wback")	\
+	EM(netfs_folio_trace_pgpriv2_copy,	"pgpriv2-copy")	\
 	EM(netfs_folio_trace_put,		"put")		\
 	EM(netfs_folio_trace_read,		"read")		\
 	EM(netfs_folio_trace_read_done,		"read-done")	\
 	EM(netfs_folio_trace_read_gaps,		"read-gaps")	\
 	EM(netfs_folio_trace_read_unlock,	"read-unlock")	\
 	EM(netfs_folio_trace_redirtied,		"redirtied")	\
+	EM(netfs_folio_trace_sched_copy,	"sched-copy")	\
 	EM(netfs_folio_trace_store,		"store")	\
 	EM(netfs_folio_trace_store_copy,	"store-copy")	\
 	EM(netfs_folio_trace_store_plus,	"store+")	\
@@ -786,6 +791,27 @@ TRACE_EVENT(netfs_folioq,
 		      __print_symbolic(__entry->trace, netfs_folioq_traces))
 	    );
 
+TRACE_EVENT(netfs_read_progress_at,
+	    TP_PROTO(const struct netfs_io_request *rreq),
+
+	    TP_ARGS(rreq),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,	rreq)
+		    __field(size_t,		progress_at)
+		    __field(size_t,		cleaned_to)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->rreq	= rreq->debug_id;
+		    __entry->cleaned_to	= rreq->cleaned_to - rreq->start;
+		    __entry->progress_at = rreq->progress_at;
+			   ),
+
+	    TP_printk("R=%08x cln=%zx prg=%zx",
+		      __entry->rreq, __entry->cleaned_to, __entry->progress_at)
+	    );
+
 #undef EM
 #undef E_
 #endif /* _TRACE_NETFS_H */