fs/nfs/pnfs_nfs.c

/*
 * Common NFS I/O  operations for the pnfs file based
 * layout drivers.
 *
 * Copyright (c) 2014, Primary Data, Inc. All rights reserved.
 *
 * Tom Haynes <loghyr@primarydata.com>
 */

#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
#include <linux/sunrpc/addr.h>

#include "internal.h"
#include "pnfs.h"

#define NFSDBG_FACILITY		NFSDBG_PNFS

static void pnfs_generic_fenceme(struct inode *inode,
				 struct pnfs_layout_hdr *lo)
{
	if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
		return;
	pnfs_return_layout(inode);
}

void pnfs_generic_rw_release(void *data)
{
	struct nfs_pgio_header *hdr = data;
	struct pnfs_layout_hdr *lo = hdr->lseg->pls_layout;

	pnfs_generic_fenceme(lo->plh_inode, lo);
	nfs_put_client(hdr->ds_clp);
	hdr->mds_ops->rpc_release(data);
}
EXPORT_SYMBOL_GPL(pnfs_generic_rw_release);

/* Fake up some data that will cause nfs_commit_release to retry the writes. */
void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data)
{
	struct nfs_page *first = nfs_list_entry(data->pages.next);

	data->task.tk_status = 0;
	memcpy(&data->verf.verifier, &first->wb_verf,
	       sizeof(data->verf.verifier));
	data->verf.verifier.data[0]++; /* ensure verifier mismatch */
}
EXPORT_SYMBOL_GPL(pnfs_generic_prepare_to_resend_writes);

void pnfs_generic_write_commit_done(struct rpc_task *task, void *data)
{
	struct nfs_commit_data *wdata = data;

	/* Note this may cause RPC to be resent */
	wdata->mds_ops->rpc_call_done(task, data);
}
EXPORT_SYMBOL_GPL(pnfs_generic_write_commit_done);

void pnfs_generic_commit_release(void *calldata)
{
	struct nfs_commit_data *data = calldata;

	data->completion_ops->completion(data);
	pnfs_put_lseg(data->lseg);
	nfs_put_client(data->ds_clp);
	nfs_commitdata_release(data);
}
EXPORT_SYMBOL_GPL(pnfs_generic_commit_release);

/* The generic layer is about to remove the req from the commit list.
 * If this will make the bucket empty, it will need to put the lseg reference.
 * Note this must be called holding the inode (/cinfo) lock
 */
void
pnfs_generic_clear_request_commit(struct nfs_page *req,
				  struct nfs_commit_info *cinfo)
{
	struct pnfs_layout_segment *freeme = NULL;

	if (!test_and_clear_bit(PG_COMMIT_TO_DS, &req->wb_flags))
		goto out;
	cinfo->ds->nwritten--;
	if (list_is_singular(&req->wb_list)) {
		struct pnfs_commit_bucket *bucket;

		bucket = list_first_entry(&req->wb_list,
					  struct pnfs_commit_bucket,
					  written);
		freeme = bucket->wlseg;
		bucket->wlseg = NULL;
	}
out:
	nfs_request_remove_commit_list(req, cinfo);
	pnfs_put_lseg_locked(freeme);
}
EXPORT_SYMBOL_GPL(pnfs_generic_clear_request_commit);

static int
pnfs_generic_transfer_commit_list(struct list_head *src, struct list_head *dst,
				  struct nfs_commit_info *cinfo, int max)
{
	struct nfs_page *req, *tmp;
	int ret = 0;

	list_for_each_entry_safe(req, tmp, src, wb_list) {
		if (!nfs_lock_request(req))
			continue;
		kref_get(&req->wb_kref);
		if (cond_resched_lock(cinfo->lock))
			list_safe_reset_next(req, tmp, wb_list);
		nfs_request_remove_commit_list(req, cinfo);
		clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
		nfs_list_add_request(req, dst);
		ret++;
		if ((ret == max) && !cinfo->dreq)
			break;
	}
	return ret;
}

static int
pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
				 struct nfs_commit_info *cinfo,
				 int max)
{
	struct list_head *src = &bucket->written;
	struct list_head *dst = &bucket->committing;
	int ret;

	lockdep_assert_held(cinfo->lock);
	ret = pnfs_generic_transfer_commit_list(src, dst, cinfo, max);
	if (ret) {
		cinfo->ds->nwritten -= ret;
		cinfo->ds->ncommitting += ret;
		bucket->clseg = bucket->wlseg;
		if (list_empty(src))
			bucket->wlseg = NULL;
		else
			pnfs_get_lseg(bucket->clseg);
	}
	return ret;
}

/* Move reqs from written to committing lists, returning count
 * of number moved.
 */
int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo,
				   int max)
{
	int i, rv = 0, cnt;

	lockdep_assert_held(cinfo->lock);
	for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) {
		cnt = pnfs_generic_scan_ds_commit_list(&cinfo->ds->buckets[i],
						       cinfo, max);
		max -= cnt;
		rv += cnt;
	}
	return rv;
}
EXPORT_SYMBOL_GPL(pnfs_generic_scan_commit_lists);

/* Pull everything off the committing lists and dump into @dst.  */
void pnfs_generic_recover_commit_reqs(struct list_head *dst,
				      struct nfs_commit_info *cinfo)
{
	struct pnfs_commit_bucket *b;
	struct pnfs_layout_segment *freeme;
	int i;

	lockdep_assert_held(cinfo->lock);
restart:
	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
		if (pnfs_generic_transfer_commit_list(&b->written, dst,
						      cinfo, 0)) {
			freeme = b->wlseg;
			b->wlseg = NULL;
			spin_unlock(cinfo->lock);
			pnfs_put_lseg(freeme);
			spin_lock(cinfo->lock);
			goto restart;
		}
	}
	cinfo->ds->nwritten = 0;
}
EXPORT_SYMBOL_GPL(pnfs_generic_recover_commit_reqs);

static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
{
	struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
	struct pnfs_commit_bucket *bucket;
	struct pnfs_layout_segment *freeme;
	int i;

	for (i = idx; i < fl_cinfo->nbuckets; i++) {
		bucket = &fl_cinfo->buckets[i];
		if (list_empty(&bucket->committing))
			continue;
		nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo);
		spin_lock(cinfo->lock);
		freeme = bucket->clseg;
		bucket->clseg = NULL;
		spin_unlock(cinfo->lock);
		pnfs_put_lseg(freeme);
	}
}

static unsigned int
pnfs_generic_alloc_ds_commits(struct nfs_commit_info *cinfo,
			      struct list_head *list)
{
	struct pnfs_ds_commit_info *fl_cinfo;
	struct pnfs_commit_bucket *bucket;
	struct nfs_commit_data *data;
	int i;
	unsigned int nreq = 0;

	fl_cinfo = cinfo->ds;
	bucket = fl_cinfo->buckets;
	for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) {
		if (list_empty(&bucket->committing))
			continue;
		data = nfs_commitdata_alloc();
		if (!data)
			break;
		data->ds_commit_index = i;
		spin_lock(cinfo->lock);
		data->lseg = bucket->clseg;
		bucket->clseg = NULL;
		spin_unlock(cinfo->lock);
		list_add(&data->pages, list);
		nreq++;
	}

	/* Clean up on error */
	pnfs_generic_retry_commit(cinfo, i);
	return nreq;
}

/* This follows nfs_commit_list pretty closely */
int
pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
			     int how, struct nfs_commit_info *cinfo,
			     int (*initiate_commit)(struct nfs_commit_data *data,
						    int how))
{
	struct nfs_commit_data *data, *tmp;
	LIST_HEAD(list);
	unsigned int nreq = 0;

	if (!list_empty(mds_pages)) {
		data = nfs_commitdata_alloc();
		if (data != NULL) {
			data->lseg = NULL;
			list_add(&data->pages, &list);
			nreq++;
		} else {
			nfs_retry_commit(mds_pages, NULL, cinfo);
			pnfs_generic_retry_commit(cinfo, 0);
			cinfo->completion_ops->error_cleanup(NFS_I(inode));
			return -ENOMEM;
		}
	}

	nreq += pnfs_generic_alloc_ds_commits(cinfo, &list);

	if (nreq == 0) {
		cinfo->completion_ops->error_cleanup(NFS_I(inode));
		goto out;
	}

	atomic_add(nreq, &cinfo->mds->rpcs_out);

	list_for_each_entry_safe(data, tmp, &list, pages) {
		list_del_init(&data->pages);
		if (!data->lseg) {
			nfs_init_commit(data, mds_pages, NULL, cinfo);
			nfs_initiate_commit(NFS_CLIENT(inode), data,
					    data->mds_ops, how, 0);
		} else {
			struct pnfs_commit_bucket *buckets;

			buckets = cinfo->ds->buckets;
			nfs_init_commit(data,
					&buckets[data->ds_commit_index].committing,
					data->lseg,
					cinfo);
			initiate_commit(data, how);
		}
	}
out:
	cinfo->ds->ncommitting = 0;
	return PNFS_ATTEMPTED;
}
EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist);

/*
 * Data server cache
 *
 * Data servers can be mapped to different device ids.
 * nfs4_pnfs_ds reference counting
 *   - set to 1 on allocation
 *   - incremented when a device id maps a data server already in the cache.
 *   - decremented when deviceid is removed from the cache.
 */
static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
static LIST_HEAD(nfs4_data_server_cache);

/* Debug routines */
static void
print_ds(struct nfs4_pnfs_ds *ds)
{
	if (ds == NULL) {
		printk(KERN_WARNING "%s NULL device\n", __func__);
		return;
	}
	printk(KERN_WARNING "        ds %s\n"
		"        ref count %d\n"
		"        client %p\n"
		"        cl_exchange_flags %x\n",
		ds->ds_remotestr,
		atomic_read(&ds->ds_count), ds->ds_clp,
		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
}

static bool
same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
{
	struct sockaddr_in *a, *b;
	struct sockaddr_in6 *a6, *b6;

	if (addr1->sa_family != addr2->sa_family)
		return false;

	switch (addr1->sa_family) {
	case AF_INET:
		a = (struct sockaddr_in *)addr1;
		b = (struct sockaddr_in *)addr2;

		if (a->sin_addr.s_addr == b->sin_addr.s_addr &&
		    a->sin_port == b->sin_port)
			return true;
		break;

	case AF_INET6:
		a6 = (struct sockaddr_in6 *)addr1;
		b6 = (struct sockaddr_in6 *)addr2;

		/* LINKLOCAL addresses must have matching scope_id */
		if (ipv6_addr_src_scope(&a6->sin6_addr) ==
		    IPV6_ADDR_SCOPE_LINKLOCAL &&
		    a6->sin6_scope_id != b6->sin6_scope_id)
			return false;

		if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) &&
		    a6->sin6_port == b6->sin6_port)
			return true;
		break;

	default:
		dprintk("%s: unhandled address family: %u\n",
			__func__, addr1->sa_family);
		return false;
	}

	return false;
}

static bool
_same_data_server_addrs_locked(const struct list_head *dsaddrs1,
			       const struct list_head *dsaddrs2)
{
	struct nfs4_pnfs_ds_addr *da1, *da2;

	/* step through both lists, comparing as we go */
	for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node),
	     da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node);
	     da1 != NULL && da2 != NULL;
	     da1 = list_entry(da1->da_node.next, typeof(*da1), da_node),
	     da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) {
		if (!same_sockaddr((struct sockaddr *)&da1->da_addr,
				   (struct sockaddr *)&da2->da_addr))
			return false;
	}
	if (da1 == NULL && da2 == NULL)
		return true;

	return false;
}

/*
 * Lookup DS by addresses.  nfs4_ds_cache_lock is held
 */
static struct nfs4_pnfs_ds *
_data_server_lookup_locked(const struct list_head *dsaddrs)
{
	struct nfs4_pnfs_ds *ds;

	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
		if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
			return ds;
	return NULL;
}

static void destroy_ds(struct nfs4_pnfs_ds *ds)
{
	struct nfs4_pnfs_ds_addr *da;

	dprintk("--> %s\n", __func__);
	ifdebug(FACILITY)
		print_ds(ds);

	nfs_put_client(ds->ds_clp);

	while (!list_empty(&ds->ds_addrs)) {
		da = list_first_entry(&ds->ds_addrs,
				      struct nfs4_pnfs_ds_addr,
				      da_node);
		list_del_init(&da->da_node);
		kfree(da->da_remotestr);
		kfree(da);
	}

	kfree(ds->ds_remotestr);
	kfree(ds);
}

void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds)
{
	if (atomic_dec_and_lock(&ds->ds_count,
				&nfs4_ds_cache_lock)) {
		list_del_init(&ds->ds_node);
		spin_unlock(&nfs4_ds_cache_lock);
		destroy_ds(ds);
	}
}
EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_put);

/*
 * Create a string with a human readable address and port to avoid
 * complicated setup around many dprinks.
 */
static char *
nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags)
{
	struct nfs4_pnfs_ds_addr *da;
	char *remotestr;
	size_t len;
	char *p;

	len = 3;        /* '{', '}' and eol */
	list_for_each_entry(da, dsaddrs, da_node) {
		len += strlen(da->da_remotestr) + 1;    /* string plus comma */
	}

	remotestr = kzalloc(len, gfp_flags);
	if (!remotestr)
		return NULL;

	p = remotestr;
	*(p++) = '{';
	len--;
	list_for_each_entry(da, dsaddrs, da_node) {
		size_t ll = strlen(da->da_remotestr);

		if (ll > len)
			goto out_err;

		memcpy(p, da->da_remotestr, ll);
		p += ll;
		len -= ll;

		if (len < 1)
			goto out_err;
		(*p++) = ',';
		len--;
	}
	if (len < 2)
		goto out_err;
	*(p++) = '}';
	*p = '\0';
	return remotestr;
out_err:
	kfree(remotestr);
	return NULL;
}

/*
 * Given a list of multipath struct nfs4_pnfs_ds_addr, add it to ds cache if
 * uncached and return cached struct nfs4_pnfs_ds.
 */
struct nfs4_pnfs_ds *
nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
{
	struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
	char *remotestr;

	if (list_empty(dsaddrs)) {
		dprintk("%s: no addresses defined\n", __func__);
		goto out;
	}

	ds = kzalloc(sizeof(*ds), gfp_flags);
	if (!ds)
		goto out;

	/* this is only used for debugging, so it's ok if its NULL */
	remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);

	spin_lock(&nfs4_ds_cache_lock);
	tmp_ds = _data_server_lookup_locked(dsaddrs);
	if (tmp_ds == NULL) {
		INIT_LIST_HEAD(&ds->ds_addrs);
		list_splice_init(dsaddrs, &ds->ds_addrs);
		ds->ds_remotestr = remotestr;
		atomic_set(&ds->ds_count, 1);
		INIT_LIST_HEAD(&ds->ds_node);
		ds->ds_clp = NULL;
		list_add(&ds->ds_node, &nfs4_data_server_cache);
		dprintk("%s add new data server %s\n", __func__,
			ds->ds_remotestr);
	} else {
		kfree(remotestr);
		kfree(ds);
		atomic_inc(&tmp_ds->ds_count);
		dprintk("%s data server %s found, inc'ed ds_count to %d\n",
			__func__, tmp_ds->ds_remotestr,
			atomic_read(&tmp_ds->ds_count));
		ds = tmp_ds;
	}
	spin_unlock(&nfs4_ds_cache_lock);
out:
	return ds;
}
EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_add);

/*
 * Currently only supports ipv4, ipv6 and one multi-path address.
 */
struct nfs4_pnfs_ds_addr *
nfs4_decode_mp_ds_addr(struct net *net, struct xdr_stream *xdr, gfp_t gfp_flags)
{
	struct nfs4_pnfs_ds_addr *da = NULL;
	char *buf, *portstr;
	__be16 port;
	int nlen, rlen;
	int tmp[2];
	__be32 *p;
	char *netid, *match_netid;
	size_t len, match_netid_len;
	char *startsep = "";
	char *endsep = "";


	/* r_netid */
	p = xdr_inline_decode(xdr, 4);
	if (unlikely(!p))
		goto out_err;
	nlen = be32_to_cpup(p++);

	p = xdr_inline_decode(xdr, nlen);
	if (unlikely(!p))
		goto out_err;

	netid = kmalloc(nlen+1, gfp_flags);
	if (unlikely(!netid))
		goto out_err;

	netid[nlen] = '\0';
	memcpy(netid, p, nlen);

	/* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */
	p = xdr_inline_decode(xdr, 4);
	if (unlikely(!p))
		goto out_free_netid;
	rlen = be32_to_cpup(p);

	p = xdr_inline_decode(xdr, rlen);
	if (unlikely(!p))
		goto out_free_netid;

	/* port is ".ABC.DEF", 8 chars max */
	if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) {
		dprintk("%s: Invalid address, length %d\n", __func__,
			rlen);
		goto out_free_netid;
	}
	buf = kmalloc(rlen + 1, gfp_flags);
	if (!buf) {
		dprintk("%s: Not enough memory\n", __func__);
		goto out_free_netid;
	}
	buf[rlen] = '\0';
	memcpy(buf, p, rlen);

	/* replace port '.' with '-' */
	portstr = strrchr(buf, '.');
	if (!portstr) {
		dprintk("%s: Failed finding expected dot in port\n",
			__func__);
		goto out_free_buf;
	}
	*portstr = '-';

	/* find '.' between address and port */
	portstr = strrchr(buf, '.');
	if (!portstr) {
		dprintk("%s: Failed finding expected dot between address and "
			"port\n", __func__);
		goto out_free_buf;
	}
	*portstr = '\0';

	da = kzalloc(sizeof(*da), gfp_flags);
	if (unlikely(!da))
		goto out_free_buf;

	INIT_LIST_HEAD(&da->da_node);

	if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr,
		      sizeof(da->da_addr))) {
		dprintk("%s: error parsing address %s\n", __func__, buf);
		goto out_free_da;
	}

	portstr++;
	sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]);
	port = htons((tmp[0] << 8) | (tmp[1]));

	switch (da->da_addr.ss_family) {
	case AF_INET:
		((struct sockaddr_in *)&da->da_addr)->sin_port = port;
		da->da_addrlen = sizeof(struct sockaddr_in);
		match_netid = "tcp";
		match_netid_len = 3;
		break;

	case AF_INET6:
		((struct sockaddr_in6 *)&da->da_addr)->sin6_port = port;
		da->da_addrlen = sizeof(struct sockaddr_in6);
		match_netid = "tcp6";
		match_netid_len = 4;
		startsep = "[";
		endsep = "]";
		break;

	default:
		dprintk("%s: unsupported address family: %u\n",
			__func__, da->da_addr.ss_family);
		goto out_free_da;
	}

	if (nlen != match_netid_len || strncmp(netid, match_netid, nlen)) {
		dprintk("%s: ERROR: r_netid \"%s\" != \"%s\"\n",
			__func__, netid, match_netid);
		goto out_free_da;
	}

	/* save human readable address */
	len = strlen(startsep) + strlen(buf) + strlen(endsep) + 7;
	da->da_remotestr = kzalloc(len, gfp_flags);

	/* NULL is ok, only used for dprintk */
	if (da->da_remotestr)
		snprintf(da->da_remotestr, len, "%s%s%s:%u", startsep,
			 buf, endsep, ntohs(port));

	dprintk("%s: Parsed DS addr %s\n", __func__, da->da_remotestr);
	kfree(buf);
	kfree(netid);
	return da;

out_free_da:
	kfree(da);
out_free_buf:
	dprintk("%s: Error parsing DS addr: %s\n", __func__, buf);
	kfree(buf);
out_free_netid:
	kfree(netid);
out_err:
	return NULL;
}
EXPORT_SYMBOL_GPL(nfs4_decode_mp_ds_addr);