Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

xdp_return_frame_bulk() needs to pass a xdp_buff
to __xdp_return().

strlcpy got converted to strscpy but here it makes no
functional difference, so just keep the right code.

Conflicts:
	net/netfilter/nf_tables_api.c

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

17 files changed, 162 insertions, 104 deletions

diff --git a/fs/afs/super.c b/fs/afs/super.c
index 6c5900df6aa5..e38bb1e7a4d2 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -230,6 +230,9 @@ static int afs_parse_source(struct fs_context *fc, struct fs_parameter *param)
 
 	_enter(",%s", name);
 
+	if (fc->source)
+		return invalf(fc, "kAFS: Multiple sources not supported");
+
 	if (!name) {
 		printk(KERN_ERR "kAFS: no volume name specified\n");
 		return -EINVAL;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 28c1459fb0fc..44f9cce57099 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -4546,7 +4546,8 @@ static void set_root_ses(struct cifs_sb_info *cifs_sb, struct cifs_ses *ses,
 	if (ses) {
 		spin_lock(&cifs_tcp_ses_lock);
 		ses->ses_count++;
-		ses->tcon_ipc->remap = cifs_remap(cifs_sb);
+		if (ses->tcon_ipc)
+			ses->tcon_ipc->remap = cifs_remap(cifs_sb);
 		spin_unlock(&cifs_tcp_ses_lock);
 	}
 	*root_ses = ses;
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index dab94f67c988..3d914d7d0d11 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -3114,8 +3114,8 @@ smb2_query_reparse_tag(const unsigned int xid, struct cifs_tcon *tcon,
 	rqst[1].rq_nvec = SMB2_IOCTL_IOV_SIZE;
 
 	rc = SMB2_ioctl_init(tcon, server,
-			     &rqst[1], fid.persistent_fid,
-			     fid.volatile_fid, FSCTL_GET_REPARSE_POINT,
+			     &rqst[1], COMPOUND_FID,
+			     COMPOUND_FID, FSCTL_GET_REPARSE_POINT,
 			     true /* is_fctl */, NULL, 0,
 			     CIFSMaxBufSize -
 			     MAX_SMB2_CREATE_RESPONSE_SIZE -
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 445e80862865..acb72705062d 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2272,17 +2272,15 @@ static struct crt_sd_ctxt *
 create_sd_buf(umode_t mode, bool set_owner, unsigned int *len)
 {
 	struct crt_sd_ctxt *buf;
-	struct cifs_ace *pace;
-	unsigned int sdlen, acelen;
+	__u8 *ptr, *aclptr;
+	unsigned int acelen, acl_size, ace_count;
 	unsigned int owner_offset = 0;
 	unsigned int group_offset = 0;
+	struct smb3_acl acl;
 
-	*len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 2), 8);
+	*len = roundup(sizeof(struct crt_sd_ctxt) + (sizeof(struct cifs_ace) * 4), 8);
 
 	if (set_owner) {
-		/* offset fields are from beginning of security descriptor not of create context */
-		owner_offset = sizeof(struct smb3_acl) + (sizeof(struct cifs_ace) * 2);
-
 		/* sizeof(struct owner_group_sids) is already multiple of 8 so no need to round */
 		*len += sizeof(struct owner_group_sids);
 	}
@@ -2291,26 +2289,22 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len)
 	if (buf == NULL)
 		return buf;
 
+	ptr = (__u8 *)&buf[1];
 	if (set_owner) {
+		/* offset fields are from beginning of security descriptor not of create context */
+		owner_offset = ptr - (__u8 *)&buf->sd;
 		buf->sd.OffsetOwner = cpu_to_le32(owner_offset);
-		group_offset = owner_offset + sizeof(struct owner_sid);
+		group_offset = owner_offset + offsetof(struct owner_group_sids, group);
 		buf->sd.OffsetGroup = cpu_to_le32(group_offset);
+
+		setup_owner_group_sids(ptr);
+		ptr += sizeof(struct owner_group_sids);
 	} else {
 		buf->sd.OffsetOwner = 0;
 		buf->sd.OffsetGroup = 0;
 	}
 
-	sdlen = sizeof(struct smb3_sd) + sizeof(struct smb3_acl) +
-		 2 * sizeof(struct cifs_ace);
-	if (set_owner) {
-		sdlen += sizeof(struct owner_group_sids);
-		setup_owner_group_sids(owner_offset + sizeof(struct create_context) + 8 /* name */
-			+ (char *)buf);
-	}
-
-	buf->ccontext.DataOffset = cpu_to_le16(offsetof
-					(struct crt_sd_ctxt, sd));
-	buf->ccontext.DataLength = cpu_to_le32(sdlen);
+	buf->ccontext.DataOffset = cpu_to_le16(offsetof(struct crt_sd_ctxt, sd));
 	buf->ccontext.NameOffset = cpu_to_le16(offsetof(struct crt_sd_ctxt, Name));
 	buf->ccontext.NameLength = cpu_to_le16(4);
 	/* SMB2_CREATE_SD_BUFFER_TOKEN is "SecD" */
@@ -2319,6 +2313,7 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len)
 	buf->Name[2] = 'c';
 	buf->Name[3] = 'D';
 	buf->sd.Revision = 1;  /* Must be one see MS-DTYP 2.4.6 */
+
 	/*
 	 * ACL is "self relative" ie ACL is stored in contiguous block of memory
 	 * and "DP" ie the DACL is present
@@ -2326,28 +2321,38 @@ create_sd_buf(umode_t mode, bool set_owner, unsigned int *len)
 	buf->sd.Control = cpu_to_le16(ACL_CONTROL_SR | ACL_CONTROL_DP);
 
 	/* offset owner, group and Sbz1 and SACL are all zero */
-	buf->sd.OffsetDacl = cpu_to_le32(sizeof(struct smb3_sd));
-	buf->acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */
+	buf->sd.OffsetDacl = cpu_to_le32(ptr - (__u8 *)&buf->sd);
+	/* Ship the ACL for now. we will copy it into buf later. */
+	aclptr = ptr;
+	ptr += sizeof(struct cifs_acl);
 
 	/* create one ACE to hold the mode embedded in reserved special SID */
-	pace = (struct cifs_ace *)(sizeof(struct crt_sd_ctxt) + (char *)buf);
-	acelen = setup_special_mode_ACE(pace, (__u64)mode);
+	acelen = setup_special_mode_ACE((struct cifs_ace *)ptr, (__u64)mode);
+	ptr += acelen;
+	acl_size = acelen + sizeof(struct smb3_acl);
+	ace_count = 1;
 
 	if (set_owner) {
 		/* we do not need to reallocate buffer to add the two more ACEs. plenty of space */
-		pace = (struct cifs_ace *)(acelen + (sizeof(struct crt_sd_ctxt) + (char *)buf));
-		acelen += setup_special_user_owner_ACE(pace);
-		/* it does not appear necessary to add an ACE for the NFS group SID */
-		buf->acl.AceCount = cpu_to_le16(3);
-	} else
-		buf->acl.AceCount = cpu_to_le16(2);
+		acelen = setup_special_user_owner_ACE((struct cifs_ace *)ptr);
+		ptr += acelen;
+		acl_size += acelen;
+		ace_count += 1;
+	}
 
 	/* and one more ACE to allow access for authenticated users */
-	pace = (struct cifs_ace *)(acelen + (sizeof(struct crt_sd_ctxt) +
-		(char *)buf));
-	acelen += setup_authusers_ACE(pace);
-
-	buf->acl.AclSize = cpu_to_le16(sizeof(struct cifs_acl) + acelen);
+	acelen = setup_authusers_ACE((struct cifs_ace *)ptr);
+	ptr += acelen;
+	acl_size += acelen;
+	ace_count += 1;
+
+	acl.AclRevision = ACL_REVISION; /* See 2.4.4.1 of MS-DTYP */
+	acl.AclSize = cpu_to_le16(acl_size);
+	acl.AceCount = cpu_to_le16(ace_count);
+	memcpy(aclptr, &acl, sizeof(struct cifs_acl));
+
+	buf->ccontext.DataLength = cpu_to_le32(ptr - (__u8 *)&buf->sd);
+	*len = ptr - (__u8 *)buf;
 
 	return buf;
 }
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index f05f9b12f689..fa57b03ca98c 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -963,8 +963,6 @@ struct crt_sd_ctxt {
 	struct create_context ccontext;
 	__u8	Name[8];
 	struct smb3_sd sd;
-	struct smb3_acl acl;
-	/* Followed by at least 4 ACEs */
 } __packed;
 
 
diff --git a/fs/coredump.c b/fs/coredump.c
index 0cd9056d79cc..c6acfc694f65 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -229,7 +229,8 @@ static int format_corename(struct core_name *cn, struct coredump_params *cprm,
 		 */
 		if (ispipe) {
 			if (isspace(*pat_ptr)) {
-				was_space = true;
+				if (cn->used != 0)
+					was_space = true;
 				pat_ptr++;
 				continue;
 			} else if (was_space) {
diff --git a/fs/io_uring.c b/fs/io_uring.c
index 1023f7b44cea..a2a7c65a77aa 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -4499,7 +4499,8 @@ static int __io_compat_recvmsg_copy_hdr(struct io_kiocb *req,
 			return -EFAULT;
 		if (clen < 0)
 			return -EINVAL;
-		sr->len = iomsg->iov[0].iov_len;
+		sr->len = clen;
+		iomsg->iov[0].iov_len = clen;
 		iomsg->iov = NULL;
 	} else {
 		ret = __import_iovec(READ, (struct iovec __user *)uiov, len,
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 88e1763e02f3..e2a488d403a6 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -205,3 +205,12 @@ config NFS_DISABLE_UDP_SUPPORT
 	 Choose Y here to disable the use of NFS over UDP. NFS over UDP
 	 on modern networks (1Gb+) can lead to data corruption caused by
 	 fragmentation during high loads.
+
+config NFS_V4_2_READ_PLUS
+	bool "NFS: Enable support for the NFSv4.2 READ_PLUS operation"
+	depends on NFS_V4_2
+	default n
+	help
+	 This is intended for developers only. The READ_PLUS operation has
+	 been shown to have issues under specific conditions and should not
+	 be used in production.
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index a163533446fa..24bf5797f88a 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -838,7 +838,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	struct nfs_pgio_mirror *pgm;
 	struct nfs4_ff_layout_mirror *mirror;
 	struct nfs4_pnfs_ds *ds;
-	u32 ds_idx, i;
+	u32 ds_idx;
 
 retry:
 	ff_layout_pg_check_layout(pgio, req);
@@ -864,11 +864,9 @@ retry:
 		goto retry;
 	}
 
-	for (i = 0; i < pgio->pg_mirror_count; i++) {
-		mirror = FF_LAYOUT_COMP(pgio->pg_lseg, i);
-		pgm = &pgio->pg_mirrors[i];
-		pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
-	}
+	mirror = FF_LAYOUT_COMP(pgio->pg_lseg, ds_idx);
+	pgm = &pgio->pg_mirrors[0];
+	pgm->pg_bsize = mirror->mirror_ds->ds_versions[0].rsize;
 
 	pgio->pg_mirror_idx = ds_idx;
 
@@ -985,6 +983,21 @@ out:
 	return 1;
 }
 
+static u32
+ff_layout_pg_set_mirror_write(struct nfs_pageio_descriptor *desc, u32 idx)
+{
+	u32 old = desc->pg_mirror_idx;
+
+	desc->pg_mirror_idx = idx;
+	return old;
+}
+
+static struct nfs_pgio_mirror *
+ff_layout_pg_get_mirror_write(struct nfs_pageio_descriptor *desc, u32 idx)
+{
+	return &desc->pg_mirrors[idx];
+}
+
 static const struct nfs_pageio_ops ff_layout_pg_read_ops = {
 	.pg_init = ff_layout_pg_init_read,
 	.pg_test = pnfs_generic_pg_test,
@@ -998,6 +1011,8 @@ static const struct nfs_pageio_ops ff_layout_pg_write_ops = {
 	.pg_doio = pnfs_generic_pg_writepages,
 	.pg_get_mirror_count = ff_layout_pg_get_mirror_count_write,
 	.pg_cleanup = pnfs_generic_pg_cleanup,
+	.pg_get_mirror = ff_layout_pg_get_mirror_write,
+	.pg_set_mirror = ff_layout_pg_set_mirror_write,
 };
 
 static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs)
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index 2b2211d1234e..4fc61e3d098d 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -1241,12 +1241,13 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf,
 		.rpc_resp	= &res,
 	};
 	u32 xdrlen;
-	int ret, np;
+	int ret, np, i;
 
 
+	ret = -ENOMEM;
 	res.scratch = alloc_page(GFP_KERNEL);
 	if (!res.scratch)
-		return -ENOMEM;
+		goto out;
 
 	xdrlen = nfs42_listxattr_xdrsize(buflen);
 	if (xdrlen > server->lxasize)
@@ -1254,9 +1255,12 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf,
 	np = xdrlen / PAGE_SIZE + 1;
 
 	pages = kcalloc(np, sizeof(struct page *), GFP_KERNEL);
-	if (pages == NULL) {
-		__free_page(res.scratch);
-		return -ENOMEM;
+	if (!pages)
+		goto out_free_scratch;
+	for (i = 0; i < np; i++) {
+		pages[i] = alloc_page(GFP_KERNEL);
+		if (!pages[i])
+			goto out_free_pages;
 	}
 
 	arg.xattr_pages = pages;
@@ -1271,14 +1275,15 @@ static ssize_t _nfs42_proc_listxattrs(struct inode *inode, void *buf,
 		*eofp = res.eof;
 	}
 
+out_free_pages:
 	while (--np >= 0) {
 		if (pages[np])
 			__free_page(pages[np]);
 	}
-
-	__free_page(res.scratch);
 	kfree(pages);
-
+out_free_scratch:
+	__free_page(res.scratch);
+out:
 	return ret;
 
 }
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 6e060a88f98c..8432bd6b95f0 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -1528,7 +1528,6 @@ static void nfs4_xdr_enc_listxattrs(struct rpc_rqst *req,
 
 	rpc_prepare_reply_pages(req, args->xattr_pages, 0, args->count,
 	    hdr.replen);
-	req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES;
 
 	encode_nops(&hdr);
 }
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 9d354de613da..57b3821d975a 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -377,10 +377,10 @@ static struct file *__nfs42_ssc_open(struct vfsmount *ss_mnt,
 		goto out_stateowner;
 
 	set_bit(NFS_SRV_SSC_COPY_STATE, &ctx->state->flags);
-	set_bit(NFS_OPEN_STATE, &ctx->state->flags);
 	memcpy(&ctx->state->open_stateid.other, &stateid->other,
 	       NFS4_STATEID_OTHER_SIZE);
 	update_open_stateid(ctx->state, stateid, NULL, filep->f_mode);
+	set_bit(NFS_OPEN_STATE, &ctx->state->flags);
 
 	nfs_file_set_open_context(filep, ctx);
 	put_nfs_open_context(ctx);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 9e0ca9b2b210..e89468678ae1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -5309,7 +5309,7 @@ static int nfs4_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 				    nfs4_read_done_cb(task, hdr);
 }
 
-#ifdef CONFIG_NFS_V4_2
+#if defined CONFIG_NFS_V4_2 && defined CONFIG_NFS_V4_2_READ_PLUS
 static void nfs42_read_plus_support(struct nfs_server *server, struct rpc_message *msg)
 {
 	if (server->caps & NFS_CAP_READ_PLUS)
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 6985cacf4700..78c9c4bdef2b 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -31,13 +31,29 @@
 static struct kmem_cache *nfs_page_cachep;
 static const struct rpc_call_ops nfs_pgio_common_ops;
 
+static struct nfs_pgio_mirror *
+nfs_pgio_get_mirror(struct nfs_pageio_descriptor *desc, u32 idx)
+{
+	if (desc->pg_ops->pg_get_mirror)
+		return desc->pg_ops->pg_get_mirror(desc, idx);
+	return &desc->pg_mirrors[0];
+}
+
 struct nfs_pgio_mirror *
 nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc)
 {
-	return &desc->pg_mirrors[desc->pg_mirror_idx];
+	return nfs_pgio_get_mirror(desc, desc->pg_mirror_idx);
 }
 EXPORT_SYMBOL_GPL(nfs_pgio_current_mirror);
 
+static u32
+nfs_pgio_set_current_mirror(struct nfs_pageio_descriptor *desc, u32 idx)
+{
+	if (desc->pg_ops->pg_set_mirror)
+		return desc->pg_ops->pg_set_mirror(desc, idx);
+	return desc->pg_mirror_idx;
+}
+
 void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
 		       struct nfs_pgio_header *hdr,
 		       void (*release)(struct nfs_pgio_header *hdr))
@@ -1259,7 +1275,7 @@ static void nfs_pageio_error_cleanup(struct nfs_pageio_descriptor *desc)
 		return;
 
 	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
-		mirror = &desc->pg_mirrors[midx];
+		mirror = nfs_pgio_get_mirror(desc, midx);
 		desc->pg_completion_ops->error_cleanup(&mirror->pg_list,
 				desc->pg_error);
 	}
@@ -1293,12 +1309,12 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
 			goto out_failed;
 		}
 
-		desc->pg_mirror_idx = midx;
+		nfs_pgio_set_current_mirror(desc, midx);
 		if (!nfs_pageio_add_request_mirror(desc, dupreq))
 			goto out_cleanup_subreq;
 	}
 
-	desc->pg_mirror_idx = 0;
+	nfs_pgio_set_current_mirror(desc, 0);
 	if (!nfs_pageio_add_request_mirror(desc, req))
 		goto out_failed;
 
@@ -1320,10 +1336,12 @@ out_failed:
 static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc,
 				       u32 mirror_idx)
 {
-	struct nfs_pgio_mirror *mirror = &desc->pg_mirrors[mirror_idx];
-	u32 restore_idx = desc->pg_mirror_idx;
+	struct nfs_pgio_mirror *mirror;
+	u32 restore_idx;
+
+	restore_idx = nfs_pgio_set_current_mirror(desc, mirror_idx);
+	mirror = nfs_pgio_current_mirror(desc);
 
-	desc->pg_mirror_idx = mirror_idx;
 	for (;;) {
 		nfs_pageio_doio(desc);
 		if (desc->pg_error < 0 || !mirror->pg_recoalesce)
@@ -1331,7 +1349,7 @@ static void nfs_pageio_complete_mirror(struct nfs_pageio_descriptor *desc,
 		if (!nfs_do_recoalesce(desc))
 			break;
 	}
-	desc->pg_mirror_idx = restore_idx;
+	nfs_pgio_set_current_mirror(desc, restore_idx);
 }
 
 /*
@@ -1405,7 +1423,7 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index)
 	u32 midx;
 
 	for (midx = 0; midx < desc->pg_mirror_count; midx++) {
-		mirror = &desc->pg_mirrors[midx];
+		mirror = nfs_pgio_get_mirror(desc, midx);
 		if (!list_empty(&mirror->pg_list)) {
 			prev = nfs_list_entry(mirror->pg_list.prev);
 			if (index != prev->wb_index + 1) {
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 217aa2705d5d..ee5a235b3056 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1599,11 +1599,15 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 
 	src = *ppos;
 	svpfn = src / PM_ENTRY_BYTES;
-	start_vaddr = svpfn << PAGE_SHIFT;
 	end_vaddr = mm->task_size;
 
 	/* watch out for wraparound */
-	if (svpfn > mm->task_size >> PAGE_SHIFT)
+	start_vaddr = end_vaddr;
+	if (svpfn <= (ULONG_MAX >> PAGE_SHIFT))
+		start_vaddr = untagged_addr(svpfn << PAGE_SHIFT);
+
+	/* Ensure the address is inside the task */
+	if (start_vaddr > mm->task_size)
 		start_vaddr = end_vaddr;
 
 	/*
diff --git a/fs/seq_file.c b/fs/seq_file.c
index 3b20e21604e7..03a369ccd28c 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -168,12 +168,14 @@ EXPORT_SYMBOL(seq_read);
 ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 {
 	struct seq_file *m = iocb->ki_filp->private_data;
-	size_t size = iov_iter_count(iter);
 	size_t copied = 0;
 	size_t n;
 	void *p;
 	int err = 0;
 
+	if (!iov_iter_count(iter))
+		return 0;
+
 	mutex_lock(&m->lock);
 
 	/*
@@ -206,36 +208,34 @@ ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 		if (!m->buf)
 			goto Enomem;
 	}
-	/* if not empty - flush it first */
+	// something left in the buffer - copy it out first
 	if (m->count) {
-		n = min(m->count, size);
-		if (copy_to_iter(m->buf + m->from, n, iter) != n)
-			goto Efault;
+		n = copy_to_iter(m->buf + m->from, m->count, iter);
 		m->count -= n;
 		m->from += n;
-		size -= n;
 		copied += n;
-		if (!size)
+		if (m->count)	// hadn't managed to copy everything
 			goto Done;
 	}
-	/* we need at least one record in buffer */
+	// get a non-empty record in the buffer
 	m->from = 0;
 	p = m->op->start(m, &m->index);
 	while (1) {
 		err = PTR_ERR(p);
-		if (!p || IS_ERR(p))
+		if (!p || IS_ERR(p))	// EOF or an error
 			break;
 		err = m->op->show(m, p);
-		if (err < 0)
+		if (err < 0)		// hard error
 			break;
-		if (unlikely(err))
+		if (unlikely(err))	// ->show() says "skip it"
 			m->count = 0;
-		if (unlikely(!m->count)) {
+		if (unlikely(!m->count)) { // empty record
 			p = m->op->next(m, p, &m->index);
 			continue;
 		}
-		if (m->count < m->size)
+		if (!seq_has_overflowed(m)) // got it
 			goto Fill;
+		// need a bigger buffer
 		m->op->stop(m, p);
 		kvfree(m->buf);
 		m->count = 0;
@@ -244,11 +244,14 @@ ssize_t seq_read_iter(struct kiocb *iocb, struct iov_iter *iter)
 			goto Enomem;
 		p = m->op->start(m, &m->index);
 	}
+	// EOF or an error
 	m->op->stop(m, p);
 	m->count = 0;
 	goto Done;
 Fill:
-	/* they want more? let's try to get some more */
+	// one non-empty record is in the buffer; if they want more,
+	// try to fit more in, but in any case we need to advance
+	// the iterator once for every record shown.
 	while (1) {
 		size_t offs = m->count;
 		loff_t pos = m->index;
@@ -259,30 +262,27 @@ Fill:
 					    m->op->next);
 			m->index++;
 		}
-		if (!p || IS_ERR(p)) {
-			err = PTR_ERR(p);
+		if (!p || IS_ERR(p))	// no next record for us
 			break;
-		}
-		if (m->count >= size)
+		if (m->count >= iov_iter_count(iter))
 			break;
 		err = m->op->show(m, p);
-		if (seq_has_overflowed(m) || err) {
+		if (err > 0) {		// ->show() says "skip it"
 			m->count = offs;
-			if (likely(err <= 0))
-				break;
+		} else if (err || seq_has_overflowed(m)) {
+			m->count = offs;
+			break;
 		}
 	}
 	m->op->stop(m, p);
-	n = min(m->count, size);
-	if (copy_to_iter(m->buf, n, iter) != n)
-		goto Efault;
+	n = copy_to_iter(m->buf, m->count, iter);
 	copied += n;
 	m->count -= n;
 	m->from = n;
 Done:
-	if (!copied)
-		copied = err;
-	else {
+	if (unlikely(!copied)) {
+		copied = m->count ? -EFAULT : err;
+	} else {
 		iocb->ki_pos += copied;
 		m->read_pos += copied;
 	}
@@ -291,9 +291,6 @@ Done:
 Enomem:
 	err = -ENOMEM;
 	goto Done;
-Efault:
-	err = -EFAULT;
-	goto Done;
 }
 EXPORT_SYMBOL(seq_read_iter);
 
diff --git a/fs/zonefs/super.c b/fs/zonefs/super.c
index ff5930be096c..bec47f2d074b 100644
--- a/fs/zonefs/super.c
+++ b/fs/zonefs/super.c
@@ -691,21 +691,23 @@ static ssize_t zonefs_file_dio_append(struct kiocb *iocb, struct iov_iter *from)
 		bio->bi_opf |= REQ_FUA;
 
 	ret = bio_iov_iter_get_pages(bio, from);
-	if (unlikely(ret)) {
-		bio_io_error(bio);
-		return ret;
-	}
+	if (unlikely(ret))
+		goto out_release;
+
 	size = bio->bi_iter.bi_size;
-	task_io_account_write(ret);
+	task_io_account_write(size);
 
 	if (iocb->ki_flags & IOCB_HIPRI)
 		bio_set_polled(bio, iocb);
 
 	ret = submit_bio_wait(bio);
 
+	zonefs_file_write_dio_end_io(iocb, size, ret, 0);
+
+out_release:
+	bio_release_pages(bio, false);
 	bio_put(bio);
 
-	zonefs_file_write_dio_end_io(iocb, size, ret, 0);
 	if (ret >= 0) {
 		iocb->ki_pos += size;
 		return size;