Merge tag 'nfs-for-6.17-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

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

  Stable fixes:
   - don't inherit NFS filesystem capabilities when crossing from one
     filesystem to another

  Bugfixes:
   - NFS wakeup of __nfs_lookup_revalidate() needs memory barriers
   - NFS improve bounds checking in nfs_fh_to_dentry()
   - NFS Fix allocation errors when writing to a NFS file backed
     loopback device
   - NFSv4: More listxattr fixes
   - SUNRPC: fix client handling of TLS alerts
   - pNFS block/scsi layout fix for an uninitialised pointer
     dereference
   - pNFS block/scsi layout fixes for the extent encoding, stripe
     mapping, and disk offset overflows
   - pNFS layoutcommit work around for RPC size limitations
   - pNFS/flexfiles avoid looping when handling fatal errors after
     layoutget
   - localio: fix various race conditions

  Features and cleanups:
   - Add NFSv4 support for retrieving the btime
   - NFS: Allow folio migration for the case of mode == MIGRATE_SYNC
   - NFS: Support using a kernel keyring to store TLS certificates
   - NFSv4: Speed up delegation lookup using a hash table
   - Assorted cleanups to remove unused variables and struct fields
   - Assorted new tracepoints to improve debugging"

* tag 'nfs-for-6.17-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (44 commits)
  NFS/localio: nfs_uuid_put() fix the wake up after unlinking the file
  NFS/localio: nfs_uuid_put() fix races with nfs_open/close_local_fh()
  NFS/localio: nfs_close_local_fh() fix check for file closed
  NFSv4: Remove duplicate lookups, capability probes and fsinfo calls
  NFS: Fix the setting of capabilities when automounting a new filesystem
  sunrpc: fix client side handling of tls alerts
  nfs/localio: use read_seqbegin() rather than read_seqbegin_or_lock()
  NFS: Fixup allocation flags for nfsiod's __GFP_NORETRY
  NFSv4.2: another fix for listxattr
  NFS: Fix filehandle bounds checking in nfs_fh_to_dentry()
  SUNRPC: Silence warnings about parameters not being described
  NFS: Clean up pnfs_put_layout_hdr()/pnfs_destroy_layout_final()
  NFS: Fix wakeup of __nfs_lookup_revalidate() in unblock_revalidate()
  NFS: use a hash table for delegation lookup
  NFS: track active delegations per-server
  NFS: move the delegation_watermark module parameter
  NFS: cleanup nfs_inode_reclaim_delegation
  NFS: cleanup error handling in nfs4_server_common_setup
  pNFS/flexfiles: don't attempt pnfs on fatal DS errors
  NFS: drop __exit from nfs_exit_keyring
  ...

Author: torvalds

fs/nfs/blocklayout/blocklayout.c

@@ -149,8 +149,8 @@ do_add_page_to_bio(struct bio *bio, int npg, enum req_op op, sector_t isect,
 
 	/* limit length to what the device mapping allows */
 	end = disk_addr + *len;
-	if (end >= map->start + map->len)
-		*len = map->start + map->len - disk_addr;
+	if (end >= map->disk_offset + map->len)
+		*len = map->disk_offset + map->len - disk_addr;
 
 retry:
 	if (!bio) {

fs/nfs/blocklayout/dev.c

@@ -257,10 +257,11 @@ static bool bl_map_stripe(struct pnfs_block_dev *dev, u64 offset,
 	struct pnfs_block_dev *child;
 	u64 chunk;
 	u32 chunk_idx;
+	u64 disk_chunk;
 	u64 disk_offset;
 
 	chunk = div_u64(offset, dev->chunk_size);
-	div_u64_rem(chunk, dev->nr_children, &chunk_idx);
+	disk_chunk = div_u64_rem(chunk, dev->nr_children, &chunk_idx);
 
 	if (chunk_idx >= dev->nr_children) {
 		dprintk("%s: invalid chunk idx %d (%lld/%lld)\n",
@@ -273,7 +274,7 @@ static bool bl_map_stripe(struct pnfs_block_dev *dev, u64 offset,
 	offset = chunk * dev->chunk_size;
 
 	/* disk offset of the stripe */
-	disk_offset = div_u64(offset, dev->nr_children);
+	disk_offset = disk_chunk * dev->chunk_size;
 
 	child = &dev->children[chunk_idx];
 	child->map(child, disk_offset, map);

fs/nfs/blocklayout/extent_tree.c

@@ -6,6 +6,7 @@
 #include <linux/vmalloc.h>
 
 #include "blocklayout.h"
+#include "../nfs4trace.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS_LD
 
@@ -520,10 +521,71 @@ static __be32 *encode_scsi_range(struct pnfs_block_extent *be, __be32 *p)
 	return xdr_encode_hyper(p, be->be_length << SECTOR_SHIFT);
 }
 
-static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
+/**
+ * ext_tree_try_encode_commit - try to encode all extents into the buffer
+ * @bl: pointer to the layout
+ * @p: pointer to the output buffer
+ * @buffer_size: size of the output buffer
+ * @count: output pointer to the number of encoded extents
+ * @lastbyte: output pointer to the last written byte
+ *
+ * Return values:
+ *   %0: Success, all required extents encoded, outputs are valid
+ *   %-ENOSPC: Buffer too small, nothing encoded, outputs are invalid
+ */
+static int
+ext_tree_try_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
 		size_t buffer_size, size_t *count, __u64 *lastbyte)
 {
 	struct pnfs_block_extent *be;
+
+	spin_lock(&bl->bl_ext_lock);
+	for (be = ext_tree_first(&bl->bl_ext_rw); be; be = ext_tree_next(be)) {
+		if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
+		    be->be_tag != EXTENT_WRITTEN)
+			continue;
+
+		(*count)++;
+		if (ext_tree_layoutupdate_size(bl, *count) > buffer_size) {
+			spin_unlock(&bl->bl_ext_lock);
+			return -ENOSPC;
+		}
+	}
+	for (be = ext_tree_first(&bl->bl_ext_rw); be; be = ext_tree_next(be)) {
+		if (be->be_state != PNFS_BLOCK_INVALID_DATA ||
+		    be->be_tag != EXTENT_WRITTEN)
+			continue;
+
+		if (bl->bl_scsi_layout)
+			p = encode_scsi_range(be, p);
+		else
+			p = encode_block_extent(be, p);
+		be->be_tag = EXTENT_COMMITTING;
+	}
+	*lastbyte = (bl->bl_lwb != 0) ? bl->bl_lwb - 1 : U64_MAX;
+	bl->bl_lwb = 0;
+	spin_unlock(&bl->bl_ext_lock);
+
+	return 0;
+}
+
+/**
+ * ext_tree_encode_commit - encode as much as possible extents into the buffer
+ * @bl: pointer to the layout
+ * @p: pointer to the output buffer
+ * @buffer_size: size of the output buffer
+ * @count: output pointer to the number of encoded extents
+ * @lastbyte: output pointer to the last written byte
+ *
+ * Return values:
+ *   %0: Success, all required extents encoded, outputs are valid
+ *   %-ENOSPC: Buffer too small, some extents are encoded, outputs are valid
+ */
+static int
+ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
+		size_t buffer_size, size_t *count, __u64 *lastbyte)
+{
+	struct pnfs_block_extent *be, *be_prev;
 	int ret = 0;
 
 	spin_lock(&bl->bl_ext_lock);
@@ -534,24 +596,40 @@ static int ext_tree_encode_commit(struct pnfs_block_layout *bl, __be32 *p,
 
 		(*count)++;
 		if (ext_tree_layoutupdate_size(bl, *count) > buffer_size) {
-			/* keep counting.. */
+			(*count)--;
 			ret = -ENOSPC;
-			continue;
+			break;
 		}
 
 		if (bl->bl_scsi_layout)
 			p = encode_scsi_range(be, p);
 		else
 			p = encode_block_extent(be, p);
 		be->be_tag = EXTENT_COMMITTING;
+		be_prev = be;
+	}
+	if (!ret) {
+		*lastbyte = (bl->bl_lwb != 0) ? bl->bl_lwb - 1 : U64_MAX;
+		bl->bl_lwb = 0;
+	} else {
+		*lastbyte = be_prev->be_f_offset + be_prev->be_length;
+		*lastbyte <<= SECTOR_SHIFT;
+		*lastbyte -= 1;
 	}
-	*lastbyte = bl->bl_lwb - 1;
-	bl->bl_lwb = 0;
 	spin_unlock(&bl->bl_ext_lock);
 
 	return ret;
 }
 
+/**
+ * ext_tree_prepare_commit - encode extents that need to be committed
+ * @arg: layout commit data
+ *
+ * Return values:
+ *   %0: Success, all required extents are encoded
+ *   %-ENOSPC: Some extents are encoded, but not all, due to RPC size limit
+ *   %-ENOMEM: Out of memory, extents not encoded
+ */
 int
 ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)
 {
@@ -560,20 +638,18 @@ ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)
 	__be32 *start_p;
 	int ret;
 
-	dprintk("%s enter\n", __func__);
-
 	arg->layoutupdate_page = alloc_page(GFP_NOFS);
 	if (!arg->layoutupdate_page)
 		return -ENOMEM;
 	start_p = page_address(arg->layoutupdate_page);
 	arg->layoutupdate_pages = &arg->layoutupdate_page;
 
-retry:
-	ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size, &count, &arg->lastbytewritten);
+	ret = ext_tree_try_encode_commit(bl, start_p + 1, buffer_size,
+			&count, &arg->lastbytewritten);
 	if (unlikely(ret)) {
 		ext_tree_free_commitdata(arg, buffer_size);
 
-		buffer_size = ext_tree_layoutupdate_size(bl, count);
+		buffer_size = NFS_SERVER(arg->inode)->wsize;
 		count = 0;
 
 		arg->layoutupdate_pages =
@@ -588,7 +664,8 @@ ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)
 			return -ENOMEM;
 		}
 
-		goto retry;
+		ret = ext_tree_encode_commit(bl, start_p + 1, buffer_size,
+				&count, &arg->lastbytewritten);
 	}
 
 	*start_p = cpu_to_be32(count);
@@ -607,8 +684,9 @@ ext_tree_prepare_commit(struct nfs4_layoutcommit_args *arg)
 		}
 	}
 
-	dprintk("%s found %zu ranges\n", __func__, count);
-	return 0;
+	trace_bl_ext_tree_prepare_commit(ret, count,
+			arg->lastbytewritten, !!ret);
+	return ret;
 }
 
 void

fs/nfs/client.c

@@ -682,6 +682,44 @@ struct nfs_client *nfs_init_client(struct nfs_client *clp,
 }
 EXPORT_SYMBOL_GPL(nfs_init_client);
 
+static void nfs4_server_set_init_caps(struct nfs_server *server)
+{
+#if IS_ENABLED(CONFIG_NFS_V4)
+	/* Set the basic capabilities */
+	server->caps = server->nfs_client->cl_mvops->init_caps;
+	if (server->flags & NFS_MOUNT_NORDIRPLUS)
+		server->caps &= ~NFS_CAP_READDIRPLUS;
+	if (server->nfs_client->cl_proto == XPRT_TRANSPORT_RDMA)
+		server->caps &= ~NFS_CAP_READ_PLUS;
+
+	/*
+	 * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower
+	 * authentication.
+	 */
+	if (nfs4_disable_idmapping &&
+	    server->client->cl_auth->au_flavor == RPC_AUTH_UNIX)
+		server->caps |= NFS_CAP_UIDGID_NOMAP;
+#endif
+}
+
+void nfs_server_set_init_caps(struct nfs_server *server)
+{
+	switch (server->nfs_client->rpc_ops->version) {
+	case 2:
+		server->caps = NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS;
+		break;
+	case 3:
+		server->caps = NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS;
+		if (!(server->flags & NFS_MOUNT_NORDIRPLUS))
+			server->caps |= NFS_CAP_READDIRPLUS;
+		break;
+	default:
+		nfs4_server_set_init_caps(server);
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(nfs_server_set_init_caps);
+
 /*
  * Create a version 2 or 3 client
  */
@@ -726,7 +764,6 @@ static int nfs_init_server(struct nfs_server *server,
 	/* Initialise the client representation from the mount data */
 	server->flags = ctx->flags;
 	server->options = ctx->options;
-	server->caps |= NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS;
 
 	switch (clp->rpc_ops->version) {
 	case 2:
@@ -762,6 +799,8 @@ static int nfs_init_server(struct nfs_server *server,
 	if (error < 0)
 		goto error;
 
+	nfs_server_set_init_caps(server);
+
 	/* Preserve the values of mount_server-related mount options */
 	if (ctx->mount_server.addrlen) {
 		memcpy(&server->mountd_address, &ctx->mount_server.address,
@@ -814,7 +853,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 		server->wsize = max_rpc_payload;
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
 		server->wsize = NFS_MAX_FILE_IO_SIZE;
-	server->wpages = (server->wsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
 
@@ -831,7 +869,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 
 	server->maxfilesize = fsinfo->maxfilesize;
 
-	server->time_delta = fsinfo->time_delta;
 	server->change_attr_type = fsinfo->change_attr_type;
 
 	server->clone_blksize = fsinfo->clone_blksize;
@@ -936,7 +973,6 @@ void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *sour
 	target->acregmax = source->acregmax;
 	target->acdirmin = source->acdirmin;
 	target->acdirmax = source->acdirmax;
-	target->caps = source->caps;
 	target->options = source->options;
 	target->auth_info = source->auth_info;
 	target->port = source->port;
@@ -1007,6 +1043,7 @@ struct nfs_server *nfs_alloc_server(void)
 	INIT_LIST_HEAD(&server->ss_src_copies);
 
 	atomic_set(&server->active, 0);
+	atomic_long_set(&server->nr_active_delegations, 0);
 
 	server->io_stats = nfs_alloc_iostats();
 	if (!server->io_stats) {
@@ -1170,6 +1207,8 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
 	if (error < 0)
 		goto out_free_server;
 
+	nfs_server_set_init_caps(server);
+
 	/* probe the filesystem info for this server filesystem */
 	error = nfs_probe_server(server, fh);
 	if (error < 0)