Commit 6860c981 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs 

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

  Stable fixes:

   - SUNRPC: Ensure bvecs are re-synced when we re-encode the RPC
     request

   - Fix an Oops in ff_layout_track_ds_error due to a PTR_ERR()
     dereference

   - Revert buggy NFS readdirplus optimisation

   - NFSv4: Handle the special Linux file open access mode

   - pnfs: Fix a problem where we gratuitously start doing I/O through
     the MDS

  Features:

   - Allow NFS client to set up multiple TCP connections to the server
     using a new 'nconnect=X' mount option. Queue length is used to
     balance load.

   - Enhance statistics reporting to report on all transports when using
     multiple connections.

   - Speed up SUNRPC by removing bh-safe spinlocks

   - Add a mechanism to allow NFSv4 to request that containers set a
     unique per-host identifier for when the hostname is not set.

   - Ensure NFSv4 updates the lease_time after a clientid update

  Bugfixes and cleanup:

   - Fix use-after-free in rpcrdma_post_recvs

   - Fix a memory leak when nfs_match_client() is interrupted

   - Fix buggy file access checking in NFSv4 open for execute

   - disable unsupported client side deduplication

   - Fix spurious client disconnections

   - Fix occasional RDMA transport deadlock

   - Various RDMA cleanups

   - Various tracepoint fixes

   - Fix the TCP callback channel to guarantee the server can actually
     send the number of callback requests that was negotiated at mount
     time"

* tag 'nfs-for-5.3-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (68 commits)
  pnfs/flexfiles: Add tracepoints for detecting pnfs fallback to MDS
  pnfs: Fix a problem where we gratuitously start doing I/O through the MDS
  SUNRPC: Optimise transport balancing code
  SUNRPC: Ensure the bvecs are reset when we re-encode the RPC request
  pnfs/flexfiles: Fix PTR_ERR() dereferences in ff_layout_track_ds_error
  NFSv4: Don't use the zero stateid with layoutget
  SUNRPC: Fix up backchannel slot table accounting
  SUNRPC: Fix initialisation of struct rpc_xprt_switch
  SUNRPC: Skip zero-refcount transports
  SUNRPC: Replace division by multiplication in calculation of queue length
  NFSv4: Validate the stateid before applying it to state recovery
  nfs4.0: Refetch lease_time after clientid update
  nfs4: Rename nfs41_setup_state_renewal
  nfs4: Make nfs4_proc_get_lease_time available for nfs4.0
  nfs: Fix copy-and-paste error in debug message
  NFS: Replace 16 seq_printf() calls by seq_puts()
  NFS: Use seq_putc() in nfs_show_stats()
  Revert "NFS: readdirplus optimization by cache mechanism" (memleak)
  SUNRPC: Fix transport accounting when caller specifies an rpc_xprt
  NFS: Record task, client ID, and XID in xdr_status trace points
  ...
parents 0570bc8b d5b9216f

fs/nfs/Makefile

+2 −1
Original line number Diff line number Diff line
@@ -8,7 +8,8 @@ obj-$(CONFIG_NFS_FS) += nfs.o 
CFLAGS_nfstrace.o += -I$(src)

nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o \

			   io.o direct.o pagelist.o read.o symlink.o unlink.o \

			   write.o namespace.o mount_clnt.o nfstrace.o export.o

			   write.o namespace.o mount_clnt.o nfstrace.o \

			   export.o sysfs.o

nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o

nfs-$(CONFIG_SYSCTL)	+= sysctl.o

nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o

fs/nfs/callback_proc.c

+20 −8
Original line number Diff line number Diff line
@@ -414,27 +414,39 @@ static __be32 
validate_seqid(const struct nfs4_slot_table *tbl, const struct nfs4_slot *slot,

		const struct cb_sequenceargs * args)

{

	__be32 ret;



	ret = cpu_to_be32(NFS4ERR_BADSLOT);

	if (args->csa_slotid > tbl->server_highest_slotid)

		return htonl(NFS4ERR_BADSLOT);

		goto out_err;



	/* Replay */

	if (args->csa_sequenceid == slot->seq_nr) {

		ret = cpu_to_be32(NFS4ERR_DELAY);

		if (nfs4_test_locked_slot(tbl, slot->slot_nr))

			return htonl(NFS4ERR_DELAY);

			goto out_err;



		/* Signal process_op to set this error on next op */

		ret = cpu_to_be32(NFS4ERR_RETRY_UNCACHED_REP);

		if (args->csa_cachethis == 0)

			return htonl(NFS4ERR_RETRY_UNCACHED_REP);

			goto out_err;



		/* Liar! We never allowed you to set csa_cachethis != 0 */

		return htonl(NFS4ERR_SEQ_FALSE_RETRY);

		ret = cpu_to_be32(NFS4ERR_SEQ_FALSE_RETRY);

		goto out_err;

	}



	/* Note: wraparound relies on seq_nr being of type u32 */

	if (likely(args->csa_sequenceid == slot->seq_nr + 1))

		return htonl(NFS4_OK);



	/* Misordered request */

	return htonl(NFS4ERR_SEQ_MISORDERED);

	ret = cpu_to_be32(NFS4ERR_SEQ_MISORDERED);

	if (args->csa_sequenceid != slot->seq_nr + 1)

		goto out_err;



	return cpu_to_be32(NFS4_OK);



out_err:

	trace_nfs4_cb_seqid_err(args, ret);

	return ret;

}



/*

fs/nfs/client.c

+20 −4
Original line number Diff line number Diff line
@@ -49,6 +49,7 @@ 
#include "pnfs.h"

#include "nfs.h"

#include "netns.h"

#include "sysfs.h"



#define NFSDBG_FACILITY		NFSDBG_CLIENT
@@ -175,6 +176,7 @@ struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) 
	clp->cl_rpcclient = ERR_PTR(-EINVAL);



	clp->cl_proto = cl_init->proto;

	clp->cl_nconnect = cl_init->nconnect;

	clp->cl_net = get_net(cl_init->net);



	clp->cl_principal = "*";
@@ -192,7 +194,7 @@ error_0: 
EXPORT_SYMBOL_GPL(nfs_alloc_client);



#if IS_ENABLED(CONFIG_NFS_V4)

void nfs_cleanup_cb_ident_idr(struct net *net)

static void nfs_cleanup_cb_ident_idr(struct net *net)

{

	struct nfs_net *nn = net_generic(net, nfs_net_id);
@@ -214,7 +216,7 @@ static void pnfs_init_server(struct nfs_server *server) 
}



#else

void nfs_cleanup_cb_ident_idr(struct net *net)

static void nfs_cleanup_cb_ident_idr(struct net *net)

{

}
@@ -406,10 +408,10 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init) 
		clp = nfs_match_client(cl_init);

		if (clp) {

			spin_unlock(&nn->nfs_client_lock);

			if (IS_ERR(clp))

				return clp;

			if (new)

				new->rpc_ops->free_client(new);

			if (IS_ERR(clp))

				return clp;

			return nfs_found_client(cl_init, clp);

		}

		if (new) {
@@ -493,6 +495,7 @@ int nfs_create_rpc_client(struct nfs_client *clp, 
	struct rpc_create_args args = {

		.net		= clp->cl_net,

		.protocol	= clp->cl_proto,

		.nconnect	= clp->cl_nconnect,

		.address	= (struct sockaddr *)&clp->cl_addr,

		.addrsize	= clp->cl_addrlen,

		.timeout	= cl_init->timeparms,
@@ -658,6 +661,7 @@ static int nfs_init_server(struct nfs_server *server, 
		.net = data->net,

		.timeparms = &timeparms,

		.cred = server->cred,

		.nconnect = data->nfs_server.nconnect,

	};

	struct nfs_client *clp;

	int error;
@@ -1072,6 +1076,18 @@ void nfs_clients_init(struct net *net) 
#endif

	spin_lock_init(&nn->nfs_client_lock);

	nn->boot_time = ktime_get_real();



	nfs_netns_sysfs_setup(nn, net);

}



void nfs_clients_exit(struct net *net)

{

	struct nfs_net *nn = net_generic(net, nfs_net_id);



	nfs_netns_sysfs_destroy(nn);

	nfs_cleanup_cb_ident_idr(net);

	WARN_ON_ONCE(!list_empty(&nn->nfs_client_list));

	WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list));

}



#ifdef CONFIG_PROC_FS

fs/nfs/dir.c

+10 −84
Original line number Diff line number Diff line
@@ -80,6 +80,10 @@ static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir 
		ctx->dup_cookie = 0;

		ctx->cred = get_cred(cred);

		spin_lock(&dir->i_lock);

		if (list_empty(&nfsi->open_files) &&

		    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))

			nfsi->cache_validity |= NFS_INO_INVALID_DATA |

				NFS_INO_REVAL_FORCED;

		list_add(&ctx->list, &nfsi->open_files);

		spin_unlock(&dir->i_lock);

		return ctx;
@@ -140,19 +144,12 @@ struct nfs_cache_array { 
	struct nfs_cache_array_entry array[0];

};



struct readdirvec {

	unsigned long nr;

	unsigned long index;

	struct page *pages[NFS_MAX_READDIR_RAPAGES];

};



typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, bool);

typedef struct {

	struct file	*file;

	struct page	*page;

	struct dir_context *ctx;

	unsigned long	page_index;

	struct readdirvec pvec;

	u64		*dir_cookie;

	u64		last_cookie;

	loff_t		current_index;
@@ -532,10 +529,6 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en 
	struct nfs_cache_array *array;

	unsigned int count = 0;

	int status;

	int max_rapages = NFS_MAX_READDIR_RAPAGES;



	desc->pvec.index = desc->page_index;

	desc->pvec.nr = 0;



	scratch = alloc_page(GFP_KERNEL);

	if (scratch == NULL)
@@ -560,40 +553,20 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en 
		if (desc->plus)

			nfs_prime_dcache(file_dentry(desc->file), entry);



		status = nfs_readdir_add_to_array(entry, desc->pvec.pages[desc->pvec.nr]);

		if (status == -ENOSPC) {

			desc->pvec.nr++;

			if (desc->pvec.nr == max_rapages)

				break;

			status = nfs_readdir_add_to_array(entry, desc->pvec.pages[desc->pvec.nr]);

		}

		status = nfs_readdir_add_to_array(entry, page);

		if (status != 0)

			break;

	} while (!entry->eof);



	/*

	 * page and desc->pvec.pages[0] are valid, don't need to check

	 * whether or not to be NULL.

	 */

	copy_highpage(page, desc->pvec.pages[0]);



out_nopages:

	if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) {

		array = kmap_atomic(desc->pvec.pages[desc->pvec.nr]);

		array = kmap(page);

		array->eof_index = array->size;

		status = 0;

		kunmap_atomic(array);

		kunmap(page);

	}



	put_page(scratch);



	/*

	 * desc->pvec.nr > 0 means at least one page was completely filled,

	 * we should return -ENOSPC. Otherwise function

	 * nfs_readdir_xdr_to_array will enter infinite loop.

	 */

	if (desc->pvec.nr > 0)

		return -ENOSPC;

	return status;

}
@@ -627,24 +600,6 @@ out_freepages: 
	return -ENOMEM;

}



/*

 * nfs_readdir_rapages_init initialize rapages by nfs_cache_array structure.

 */

static

void nfs_readdir_rapages_init(nfs_readdir_descriptor_t *desc)

{

	struct nfs_cache_array *array;

	int max_rapages = NFS_MAX_READDIR_RAPAGES;

	int index;



	for (index = 0; index < max_rapages; index++) {

		array = kmap_atomic(desc->pvec.pages[index]);

		memset(array, 0, sizeof(struct nfs_cache_array));

		array->eof_index = -1;

		kunmap_atomic(array);

	}

}



static

int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, struct inode *inode)

{
@@ -655,12 +610,6 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, 
	int status = -ENOMEM;

	unsigned int array_size = ARRAY_SIZE(pages);



	/*

	 * This means we hit readdir rdpages miss, the preallocated rdpages

	 * are useless, the preallocate rdpages should be reinitialized.

	 */

	nfs_readdir_rapages_init(desc);



	entry.prev_cookie = 0;

	entry.cookie = desc->last_cookie;

	entry.eof = 0;
@@ -721,24 +670,9 @@ int nfs_readdir_filler(void *data, struct page* page) 
	struct inode	*inode = file_inode(desc->file);

	int ret;



	/*

	 * If desc->page_index in range desc->pvec.index and

	 * desc->pvec.index + desc->pvec.nr, we get readdir cache hit.

	 */

	if (desc->page_index >= desc->pvec.index &&

		desc->page_index < (desc->pvec.index + desc->pvec.nr)) {

		/*

		 * page and desc->pvec.pages[x] are valid, don't need to check

		 * whether or not to be NULL.

		 */

		copy_highpage(page, desc->pvec.pages[desc->page_index - desc->pvec.index]);

		ret = 0;

	} else {

	ret = nfs_readdir_xdr_to_array(desc, page, inode);

	if (ret < 0)

		goto error;

	}



	SetPageUptodate(page);



	if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) {
@@ -903,7 +837,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) 
			*desc = &my_desc;

	struct nfs_open_dir_context *dir_ctx = file->private_data;

	int res = 0;

	int max_rapages = NFS_MAX_READDIR_RAPAGES;



	dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n",

			file, (long long)ctx->pos);
@@ -923,12 +856,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) 
	desc->decode = NFS_PROTO(inode)->decode_dirent;

	desc->plus = nfs_use_readdirplus(inode, ctx);



	res = nfs_readdir_alloc_pages(desc->pvec.pages, max_rapages);

	if (res < 0)

		return -ENOMEM;



	nfs_readdir_rapages_init(desc);



	if (ctx->pos == 0 || nfs_attribute_cache_expired(inode))

		res = nfs_revalidate_mapping(inode, file->f_mapping);

	if (res < 0)
@@ -964,7 +891,6 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx) 
			break;

	} while (!desc->eof);

out:

	nfs_readdir_free_pages(desc->pvec.pages, max_rapages);

	if (res > 0)

		res = 0;

	dfprintk(FILE, "NFS: readdir(%pD2) returns %d\n", file, res);

fs/nfs/flexfilelayout/flexfilelayout.c

+26 −0
Original line number Diff line number Diff line
@@ -934,6 +934,10 @@ out_nolseg: 
	if (pgio->pg_error < 0)

		return;

out_mds:

	trace_pnfs_mds_fallback_pg_init_read(pgio->pg_inode,

			0, NFS4_MAX_UINT64, IOMODE_READ,

			NFS_I(pgio->pg_inode)->layout,

			pgio->pg_lseg);

	pnfs_put_lseg(pgio->pg_lseg);

	pgio->pg_lseg = NULL;

	nfs_pageio_reset_read_mds(pgio);
@@ -1000,6 +1004,10 @@ retry: 
	return;



out_mds:

	trace_pnfs_mds_fallback_pg_init_write(pgio->pg_inode,

			0, NFS4_MAX_UINT64, IOMODE_RW,

			NFS_I(pgio->pg_inode)->layout,

			pgio->pg_lseg);

	pnfs_put_lseg(pgio->pg_lseg);

	pgio->pg_lseg = NULL;

	nfs_pageio_reset_write_mds(pgio);
@@ -1026,6 +1034,10 @@ ff_layout_pg_get_mirror_count_write(struct nfs_pageio_descriptor *pgio, 
	if (pgio->pg_lseg)

		return FF_LAYOUT_MIRROR_COUNT(pgio->pg_lseg);



	trace_pnfs_mds_fallback_pg_get_mirror_count(pgio->pg_inode,

			0, NFS4_MAX_UINT64, IOMODE_RW,

			NFS_I(pgio->pg_inode)->layout,

			pgio->pg_lseg);

	/* no lseg means that pnfs is not in use, so no mirroring here */

	nfs_pageio_reset_write_mds(pgio);

out:
@@ -1075,6 +1087,10 @@ static void ff_layout_reset_write(struct nfs_pgio_header *hdr, bool retry_pnfs) 
			hdr->args.count,

			(unsigned long long)hdr->args.offset);



		trace_pnfs_mds_fallback_write_done(hdr->inode,

				hdr->args.offset, hdr->args.count,

				IOMODE_RW, NFS_I(hdr->inode)->layout,

				hdr->lseg);

		task->tk_status = pnfs_write_done_resend_to_mds(hdr);

	}

}
@@ -1094,6 +1110,10 @@ static void ff_layout_reset_read(struct nfs_pgio_header *hdr) 
			hdr->args.count,

			(unsigned long long)hdr->args.offset);



		trace_pnfs_mds_fallback_read_done(hdr->inode,

				hdr->args.offset, hdr->args.count,

				IOMODE_READ, NFS_I(hdr->inode)->layout,

				hdr->lseg);

		task->tk_status = pnfs_read_done_resend_to_mds(hdr);

	}

}
@@ -1827,6 +1847,9 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr) 
out_failed:

	if (ff_layout_avoid_mds_available_ds(lseg))

		return PNFS_TRY_AGAIN;

	trace_pnfs_mds_fallback_read_pagelist(hdr->inode,

			hdr->args.offset, hdr->args.count,

			IOMODE_READ, NFS_I(hdr->inode)->layout, lseg);

	return PNFS_NOT_ATTEMPTED;

}
@@ -1892,6 +1915,9 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync) 
out_failed:

	if (ff_layout_avoid_mds_available_ds(lseg))

		return PNFS_TRY_AGAIN;

	trace_pnfs_mds_fallback_write_pagelist(hdr->inode,

			hdr->args.offset, hdr->args.count,

			IOMODE_RW, NFS_I(hdr->inode)->layout, lseg);

	return PNFS_NOT_ATTEMPTED;

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE