Merge tag 'nfs-for-7.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client updates from Trond Myklebust:
 "Highlights include:

  Stable fixes:
   - Use-after-free fixes for the sunrpc client code
   - Delegation hash table leak
   - NULL dereference on lockowner allocation failure
   - Fix a handshake completion race in the TLS code
   - Fix an error sign checking issue when deciding whether the pNFS
     layout is still in use, or can be returned
   - Fix a layout segment leak in pnfs_layout_process()

  Other bugfixes:
   - Fix a missing NULL check in the rpcbind client
   - annotate shared socket callbacks with READ_ONCE/WRITE_ONCE
   - nfs_inode_set_delegation() error paths should return the delegation
   - Use clear_and_wake_up_bit() in nfs_clear_invalid_mapping() and the
     pNFS code.
   - Fix the nfs4_alloc_client() error paths to free the IDR allocation
   - fix folio dereference before NULL check in
     nfs_inode_remove_request()
   - Fix delayed delegation return
   - Fix another state manager race with umount
   - Fix device leaks on parse failure
   - Avoid cancelling in-flight I/O during a layout recall if the server
     doesn't require it
   - flexfiles: report cancelled I/O as a layout error
   - flexfiles: fix NULL dereference for NFSv4.0 data servers
   - Fix incorrect argument passed to nfs4_delete_lease()
   - Fix several symlink issues resulting from nfs_atomic_open_v23()
   - Fix an uninitialised variable issue in the NFSv4.1 callback code
   - fix LAYOUTSTATS send buffer exhaustion

  Features and cleanups:
   - NFSv4.2: Allow the server to specify that file data may not be cached
   - localio: optimise I/O submission when when not doing memory reclaim
   - localio: Remove duplicate wait code in nfs_local_commit
   - flexfiles: support loosely coupled NFSv4.x data servers
   - pNFS: key the data server cache on the NFS version"

* tag 'nfs-for-7.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (33 commits)
  NFSv4.1: fix layout segment leak on the pnfs_layout_process() forget path
  NFSv4/pnfs: key the data server cache on the NFS version
  NFSv4.2: fix LAYOUTSTATS send buffer exhaustion
  pNFS: Fix EBUSY check in pnfs_layout_need_return
  NFSv4.1: zero referring call lists before decoding
  nfs: fix ENXIO on O_CREAT open of existing symlink over NFSv3
  SUNRPC: wait for in-flight client TLS handshake callback
  NFSv4: Fix incorrect argument passed to nfs4_delete_lease() in nfs4_add_lease()
  lockd: fix NULL dereference on lockowner allocation failure
  NFS: fix delegation_hash_table leak when nfs4_server_common_setup() fails
  NFSv4/flexfiles: support loosely coupled data servers
  NFSv4/flexfiles: fix NULL dereference for NFSv4.0 data servers
  NFSv4: pin the superblock for active state owners
  sunrpc: fix use-after-free in __rpc_clnt_handle_event and __rpc_clnt_remove_pipedir
  NFS/localio: issue commit inline when not in a memory-reclaim context
  NFS/localio: remove dead FLUSH_SYNC handling from nfs_local_commit
  NFS/localio: issue IO inline when not in a memory-reclaim context
  NFS: Fix delayed delegation return list handling
  NFS: Verify symlink inode before caching target
  NFS: fix folio dereference before NULL check in nfs_inode_remove_request()
  ...

4 files changed, 22 insertions, 2 deletions

diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 44e5e9fa12e1..1a3981c26b23 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -390,6 +390,14 @@ enum {
 };
 
 /*
+ * Symbol name and value are from draft-ietf-nfsv4-uncacheable-files
+ * Section 7.  "XDR for Uncacheable Attribute"
+ */
+enum {
+	FATTR4_UNCACHEABLE_FILE_DATA	= 87,
+};
+
+/*
  * The following internal definitions enable processing the above
  * attribute bits within 32-bit word boundaries.
  */
@@ -475,6 +483,7 @@ enum {
 #define FATTR4_WORD2_ACL_TRUEFORM_SCOPE	BIT(FATTR4_ACL_TRUEFORM_SCOPE - 64)
 #define FATTR4_WORD2_POSIX_DEFAULT_ACL	BIT(FATTR4_POSIX_DEFAULT_ACL - 64)
 #define FATTR4_WORD2_POSIX_ACCESS_ACL	BIT(FATTR4_POSIX_ACCESS_ACL - 64)
+#define FATTR4_WORD2_UNCACHEABLE_FILE_DATA	BIT(FATTR4_UNCACHEABLE_FILE_DATA - 64)
 
 /* MDS threshold bitmap bits */
 #define THRESHOLD_RD                    (1UL << 0)
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index ec17e602c979..48b806aa3a2f 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -110,6 +110,7 @@ struct nfs_open_context {
 #define NFS_CONTEXT_UNLOCK	(3)
 #define NFS_CONTEXT_FILE_OPEN		(4)
 #define NFS_CONTEXT_WRITE_SYNC		(5)
+#define NFS_CONTEXT_O_DIRECT		(6)
 
 	struct nfs4_threshold	*mdsthreshold;
 	struct list_head list;
@@ -162,6 +163,8 @@ struct nfs_inode {
 
 	struct timespec64	btime;
 
+	bool			uncacheable_file_data : 1;
+
 	/*
 	 * read_cache_jiffies is when we started read-caching this inode.
 	 * attrtimeo is for how long the cached information is assumed
@@ -319,6 +322,7 @@ struct nfs4_copy_state {
 #define NFS_INO_INVALID_NLINK	BIT(16)		/* cached nlinks is invalid */
 #define NFS_INO_INVALID_MODE	BIT(17)		/* cached mode is invalid */
 #define NFS_INO_INVALID_BTIME	BIT(18)		/* cached btime is invalid */
+#define NFS_INO_INVALID_UNCACHEABLE_FILE_DATA	BIT(19)		/* cached uncacheable_file_data is invalid */
 
 #define NFS_INO_INVALID_ATTR	(NFS_INO_INVALID_CHANGE \
 		| NFS_INO_INVALID_CTIME \
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 11c5b31cfc7d..7ed8fdb930d6 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -17,6 +17,9 @@
 
 #define NFS_BITMASK_SZ		3
 
+/* aux_flags in nfs_fattr */
+#define NFS_AUX_UNCACHEABLE_FILE_DATA	BIT(0)
+
 struct nfs4_string {
 	unsigned int len;
 	char *data;
@@ -68,6 +71,7 @@ struct nfs_fattr {
 	struct timespec64	mtime;
 	struct timespec64	ctime;
 	struct timespec64	btime;
+	__u32			aux_flags;	/* NFSv4 auxiliary flags bitfield */
 	__u64			change_attr;	/* NFSv4 change attribute */
 	__u64			pre_change_attr;/* pre-op NFSv4 change attribute */
 	__u64			pre_size;	/* pre_op_attr.size	  */
@@ -108,6 +112,7 @@ struct nfs_fattr {
 #define NFS_ATTR_FATTR_GROUP_NAME	BIT_ULL(24)
 #define NFS_ATTR_FATTR_V4_SECURITY_LABEL BIT_ULL(25)
 #define NFS_ATTR_FATTR_BTIME		BIT_ULL(26)
+#define NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA	BIT_ULL(27)
 
 #define NFS_ATTR_FATTR (NFS_ATTR_FATTR_TYPE \
 		| NFS_ATTR_FATTR_MODE \
@@ -129,7 +134,8 @@ struct nfs_fattr {
 #define NFS_ATTR_FATTR_V4 (NFS_ATTR_FATTR \
 		| NFS_ATTR_FATTR_SPACE_USED \
 		| NFS_ATTR_FATTR_BTIME \
-		| NFS_ATTR_FATTR_V4_SECURITY_LABEL)
+		| NFS_ATTR_FATTR_V4_SECURITY_LABEL \
+		| NFS_ATTR_FATTR_UNCACHEABLE_FILE_DATA)
 
 /*
  * Maximal number of supported layout drivers.
@@ -354,7 +360,7 @@ struct nfs4_layoutreturn {
 	struct nfs4_xdr_opaque_data ld_private;
 };
 
-#define PNFS_LAYOUTSTATS_MAXSIZE 256
+#define PNFS_LAYOUTSTATS_MAXSIZE 384
 
 struct nfs42_layoutstat_args;
 struct nfs42_layoutstat_devinfo;
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index a283766a192a..c8a36423cb34 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -661,6 +661,7 @@ extern void workqueue_set_min_active(struct workqueue_struct *wq,
 				     int min_active);
 extern struct work_struct *current_work(void);
 extern bool current_is_workqueue_rescuer(void);
+extern bool current_is_workqueue_mem_reclaim(void);
 extern bool workqueue_congested(int cpu, struct workqueue_struct *wq);
 extern unsigned int work_busy(struct work_struct *work);
 extern __printf(1, 2) void set_worker_desc(const char *fmt, ...);