OpenCloudOS-Kernel/fs/nfs/pnfs_nfs.c

1228 lines
30 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* 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 <linux/module.h>
#include "nfs4session.h"
#include "internal.h"
#include "pnfs.h"
#define NFSDBG_FACILITY NFSDBG_PNFS
void pnfs_generic_rw_release(void *data)
{
struct nfs_pgio_header *hdr = data;
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_writeverf *verf = data->res.verf;
data->task.tk_status = 0;
memset(&verf->verifier, 0, sizeof(verf->verifier));
verf->committed = NFS_UNSTABLE;
}
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 nfsi->commit_mutex
*/
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(freeme);
}
EXPORT_SYMBOL_GPL(pnfs_generic_clear_request_commit);
struct pnfs_commit_array *
pnfs_alloc_commit_array(size_t n, gfp_t gfp_flags)
{
struct pnfs_commit_array *p;
struct pnfs_commit_bucket *b;
p = kmalloc(struct_size(p, buckets, n), gfp_flags);
if (!p)
return NULL;
p->nbuckets = n;
INIT_LIST_HEAD(&p->cinfo_list);
INIT_LIST_HEAD(&p->lseg_list);
p->lseg = NULL;
for (b = &p->buckets[0]; n != 0; b++, n--) {
INIT_LIST_HEAD(&b->written);
INIT_LIST_HEAD(&b->committing);
b->wlseg = NULL;
b->clseg = NULL;
b->direct_verf.committed = NFS_INVALID_STABLE_HOW;
}
return p;
}
EXPORT_SYMBOL_GPL(pnfs_alloc_commit_array);
void
pnfs_free_commit_array(struct pnfs_commit_array *p)
{
kfree_rcu(p, rcu);
}
EXPORT_SYMBOL_GPL(pnfs_free_commit_array);
static struct pnfs_commit_array *
pnfs_find_commit_array_by_lseg(struct pnfs_ds_commit_info *fl_cinfo,
struct pnfs_layout_segment *lseg)
{
struct pnfs_commit_array *array;
list_for_each_entry_rcu(array, &fl_cinfo->commits, cinfo_list) {
if (array->lseg == lseg)
return array;
}
return NULL;
}
struct pnfs_commit_array *
pnfs_add_commit_array(struct pnfs_ds_commit_info *fl_cinfo,
struct pnfs_commit_array *new,
struct pnfs_layout_segment *lseg)
{
struct pnfs_commit_array *array;
array = pnfs_find_commit_array_by_lseg(fl_cinfo, lseg);
if (array)
return array;
new->lseg = lseg;
refcount_set(&new->refcount, 1);
list_add_rcu(&new->cinfo_list, &fl_cinfo->commits);
list_add(&new->lseg_list, &lseg->pls_commits);
return new;
}
EXPORT_SYMBOL_GPL(pnfs_add_commit_array);
static void
pnfs_setup_ds_info(struct pnfs_ds_commit_info *fl_cinfo,
struct pnfs_layout_segment *lseg)
{
struct inode *inode = lseg->pls_layout->plh_inode;
struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
if (ld->setup_ds_info != NULL)
ld->setup_ds_info(fl_cinfo, lseg);
}
static struct pnfs_commit_array *
pnfs_lookup_commit_array(struct pnfs_ds_commit_info *fl_cinfo,
struct pnfs_layout_segment *lseg)
{
struct pnfs_commit_array *array;
rcu_read_lock();
array = pnfs_find_commit_array_by_lseg(fl_cinfo, lseg);
if (!array) {
rcu_read_unlock();
pnfs_setup_ds_info(fl_cinfo, lseg);
rcu_read_lock();
array = pnfs_find_commit_array_by_lseg(fl_cinfo, lseg);
}
rcu_read_unlock();
return array;
}
static void
pnfs_release_commit_array_locked(struct pnfs_commit_array *array)
{
list_del_rcu(&array->cinfo_list);
list_del(&array->lseg_list);
pnfs_free_commit_array(array);
}
static void
pnfs_put_commit_array_locked(struct pnfs_commit_array *array)
{
if (refcount_dec_and_test(&array->refcount))
pnfs_release_commit_array_locked(array);
}
static void
pnfs_put_commit_array(struct pnfs_commit_array *array, struct inode *inode)
{
if (refcount_dec_and_lock(&array->refcount, &inode->i_lock)) {
pnfs_release_commit_array_locked(array);
spin_unlock(&inode->i_lock);
}
}
static struct pnfs_commit_array *
pnfs_get_commit_array(struct pnfs_commit_array *array)
{
if (refcount_inc_not_zero(&array->refcount))
return array;
return NULL;
}
static void
pnfs_remove_and_free_commit_array(struct pnfs_commit_array *array)
{
array->lseg = NULL;
list_del_init(&array->lseg_list);
pnfs_put_commit_array_locked(array);
}
void
pnfs_generic_ds_cinfo_release_lseg(struct pnfs_ds_commit_info *fl_cinfo,
struct pnfs_layout_segment *lseg)
{
struct pnfs_commit_array *array, *tmp;
list_for_each_entry_safe(array, tmp, &lseg->pls_commits, lseg_list)
pnfs_remove_and_free_commit_array(array);
}
EXPORT_SYMBOL_GPL(pnfs_generic_ds_cinfo_release_lseg);
void
pnfs_generic_ds_cinfo_destroy(struct pnfs_ds_commit_info *fl_cinfo)
{
struct pnfs_commit_array *array, *tmp;
list_for_each_entry_safe(array, tmp, &fl_cinfo->commits, cinfo_list)
pnfs_remove_and_free_commit_array(array);
}
EXPORT_SYMBOL_GPL(pnfs_generic_ds_cinfo_destroy);
/*
* Locks the nfs_page requests for commit and moves them to
* @bucket->committing.
*/
static int
pnfs_bucket_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(&NFS_I(cinfo->inode)->commit_mutex);
ret = nfs_scan_commit_list(src, dst, cinfo, max);
if (ret) {
cinfo->ds->nwritten -= ret;
cinfo->ds->ncommitting += ret;
if (bucket->clseg == NULL)
bucket->clseg = pnfs_get_lseg(bucket->wlseg);
if (list_empty(src)) {
pnfs_put_lseg(bucket->wlseg);
bucket->wlseg = NULL;
}
}
return ret;
}
static int pnfs_bucket_scan_array(struct nfs_commit_info *cinfo,
struct pnfs_commit_bucket *buckets,
unsigned int nbuckets,
int max)
{
unsigned int i;
int rv = 0, cnt;
for (i = 0; i < nbuckets && max != 0; i++) {
cnt = pnfs_bucket_scan_ds_commit_list(&buckets[i], cinfo, max);
rv += cnt;
max -= cnt;
}
return rv;
}
/* 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)
{
struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
struct pnfs_commit_array *array;
int rv = 0, cnt;
rcu_read_lock();
list_for_each_entry_rcu(array, &fl_cinfo->commits, cinfo_list) {
if (!array->lseg || !pnfs_get_commit_array(array))
continue;
rcu_read_unlock();
cnt = pnfs_bucket_scan_array(cinfo, array->buckets,
array->nbuckets, max);
rcu_read_lock();
pnfs_put_commit_array(array, cinfo->inode);
rv += cnt;
max -= cnt;
if (!max)
break;
}
rcu_read_unlock();
return rv;
}
EXPORT_SYMBOL_GPL(pnfs_generic_scan_commit_lists);
static unsigned int
pnfs_bucket_recover_commit_reqs(struct list_head *dst,
struct pnfs_commit_bucket *buckets,
unsigned int nbuckets,
struct nfs_commit_info *cinfo)
{
struct pnfs_commit_bucket *b;
struct pnfs_layout_segment *freeme;
unsigned int nwritten, ret = 0;
unsigned int i;
restart:
for (i = 0, b = buckets; i < nbuckets; i++, b++) {
nwritten = nfs_scan_commit_list(&b->written, dst, cinfo, 0);
if (!nwritten)
continue;
ret += nwritten;
if (list_empty(&b->written)) {
freeme = b->wlseg;
b->wlseg = NULL;
pnfs_put_lseg(freeme);
goto restart;
}
}
return ret;
}
/* 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_ds_commit_info *fl_cinfo = cinfo->ds;
struct pnfs_commit_array *array;
unsigned int nwritten;
lockdep_assert_held(&NFS_I(cinfo->inode)->commit_mutex);
rcu_read_lock();
list_for_each_entry_rcu(array, &fl_cinfo->commits, cinfo_list) {
if (!array->lseg || !pnfs_get_commit_array(array))
continue;
rcu_read_unlock();
nwritten = pnfs_bucket_recover_commit_reqs(dst,
array->buckets,
array->nbuckets,
cinfo);
rcu_read_lock();
pnfs_put_commit_array(array, cinfo->inode);
fl_cinfo->nwritten -= nwritten;
}
rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(pnfs_generic_recover_commit_reqs);
static struct nfs_page *
pnfs_bucket_search_commit_reqs(struct pnfs_commit_bucket *buckets,
unsigned int nbuckets, struct page *page)
{
struct nfs_page *req;
struct pnfs_commit_bucket *b;
unsigned int i;
/* Linearly search the commit lists for each bucket until a matching
* request is found */
for (i = 0, b = buckets; i < nbuckets; i++, b++) {
list_for_each_entry(req, &b->written, wb_list) {
if (req->wb_page == page)
return req->wb_head;
}
list_for_each_entry(req, &b->committing, wb_list) {
if (req->wb_page == page)
return req->wb_head;
}
}
return NULL;
}
/* pnfs_generic_search_commit_reqs - Search lists in @cinfo for the head reqest
* for @page
* @cinfo - commit info for current inode
* @page - page to search for matching head request
*
* Returns a the head request if one is found, otherwise returns NULL.
*/
struct nfs_page *
pnfs_generic_search_commit_reqs(struct nfs_commit_info *cinfo, struct page *page)
{
struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
struct pnfs_commit_array *array;
struct nfs_page *req;
list_for_each_entry(array, &fl_cinfo->commits, cinfo_list) {
req = pnfs_bucket_search_commit_reqs(array->buckets,
array->nbuckets, page);
if (req)
return req;
}
return NULL;
}
EXPORT_SYMBOL_GPL(pnfs_generic_search_commit_reqs);
static struct pnfs_layout_segment *
pnfs_bucket_get_committing(struct list_head *head,
struct pnfs_commit_bucket *bucket,
struct nfs_commit_info *cinfo)
{
struct pnfs_layout_segment *freeme;
struct list_head *pos;
list_for_each(pos, &bucket->committing)
cinfo->ds->ncommitting--;
list_splice_init(&bucket->committing, head);
freeme = bucket->clseg;
bucket->clseg = NULL;
return freeme;
}
static struct nfs_commit_data *
pnfs_bucket_fetch_commitdata(struct pnfs_commit_bucket *bucket,
struct nfs_commit_info *cinfo)
{
struct nfs_commit_data *data = nfs_commitdata_alloc(false);
if (!data)
return NULL;
data->lseg = pnfs_bucket_get_committing(&data->pages, bucket, cinfo);
return data;
}
static void pnfs_generic_retry_commit(struct pnfs_commit_bucket *buckets,
unsigned int nbuckets,
struct nfs_commit_info *cinfo,
unsigned int idx)
{
struct pnfs_commit_bucket *bucket;
struct pnfs_layout_segment *freeme;
LIST_HEAD(pages);
for (bucket = buckets; idx < nbuckets; bucket++, idx++) {
if (list_empty(&bucket->committing))
continue;
mutex_lock(&NFS_I(cinfo->inode)->commit_mutex);
freeme = pnfs_bucket_get_committing(&pages, bucket, cinfo);
mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
nfs_retry_commit(&pages, freeme, cinfo, idx);
pnfs_put_lseg(freeme);
}
}
static unsigned int
pnfs_bucket_alloc_ds_commits(struct list_head *list,
struct pnfs_commit_bucket *buckets,
unsigned int nbuckets,
struct nfs_commit_info *cinfo)
{
struct pnfs_commit_bucket *bucket;
struct nfs_commit_data *data;
unsigned int i;
unsigned int nreq = 0;
for (i = 0, bucket = buckets; i < nbuckets; i++, bucket++) {
if (list_empty(&bucket->committing))
continue;
mutex_lock(&NFS_I(cinfo->inode)->commit_mutex);
if (!list_empty(&bucket->committing)) {
data = pnfs_bucket_fetch_commitdata(bucket, cinfo);
if (!data)
goto out_error;
data->ds_commit_index = i;
list_add_tail(&data->list, list);
atomic_inc(&cinfo->mds->rpcs_out);
nreq++;
}
mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
}
return nreq;
out_error:
mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
/* Clean up on error */
pnfs_generic_retry_commit(buckets, nbuckets, cinfo, i);
return nreq;
nfs: avoid race that crashes nfs_init_commit Since the patch "NFS: Allow multiple commit requests in flight per file" we can run multiple simultaneous commits on the same inode. This introduced a race over collecting pages to commit that made it possible to call nfs_init_commit() with an empty list - which causes crashes like the one below. The fix is to catch this race and avoid calling nfs_init_commit and initiate_commit when there is no work to do. Here is the crash: [600522.076832] BUG: unable to handle kernel NULL pointer dereference at 0000000000000040 [600522.078475] IP: [<ffffffffa0479e72>] nfs_init_commit+0x22/0x130 [nfs] [600522.078745] PGD 4272b1067 PUD 4272cb067 PMD 0 [600522.078972] Oops: 0000 [#1] SMP [600522.079204] Modules linked in: nfsv3 nfs_layout_flexfiles rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache dcdbas ip6t_rpfilter ip6t_REJECT nf_reject_ipv6 xt_conntrack ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw vmw_vsock_vmci_transport vsock bonding ipmi_devintf ipmi_msghandler coretemp crct10dif_pclmul crc32_pclmul ghash_clmulni_intel ppdev vmw_balloon parport_pc parport acpi_cpufreq vmw_vmci i2c_piix4 shpchp nfsd auth_rpcgss nfs_acl lockd grace sunrpc xfs libcrc32c vmwgfx drm_kms_helper ttm drm crc32c_intel serio_raw vmxnet3 [600522.081380] vmw_pvscsi ata_generic pata_acpi [600522.081809] CPU: 3 PID: 15667 Comm: /usr/bin/python Not tainted 4.1.9-100.pd.88.el7.x86_64 #1 [600522.082281] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 09/30/2014 [600522.082814] task: ffff8800bbbfa780 ti: ffff88042ae84000 task.ti: ffff88042ae84000 [600522.083378] RIP: 0010:[<ffffffffa0479e72>] [<ffffffffa0479e72>] nfs_init_commit+0x22/0x130 [nfs] [600522.083973] RSP: 0018:ffff88042ae87438 EFLAGS: 00010246 [600522.084571] RAX: 0000000000000000 RBX: ffff880003485e40 RCX: ffff88042ae87588 [600522.085188] RDX: 0000000000000000 RSI: ffff88042ae874b0 RDI: ffff880003485e40 [600522.085756] RBP: ffff88042ae87448 R08: ffff880003486010 R09: ffff88042ae874b0 [600522.086332] R10: 0000000000000000 R11: 0000000000000005 R12: ffff88042ae872d0 [600522.086905] R13: ffff88042ae874b0 R14: ffff880003485e40 R15: ffff88042704c840 [600522.087484] FS: 00007f4728ff2740(0000) GS:ffff88043fd80000(0000) knlGS:0000000000000000 [600522.088070] CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b [600522.088663] CR2: 0000000000000040 CR3: 000000042b6aa000 CR4: 00000000001406e0 [600522.089327] Stack: [600522.089926] 0000000000000001 ffff88042ae87588 ffff88042ae874f8 ffffffffa04f09fa [600522.090549] 0000000000017840 0000000000017840 ffff88042ae87588 ffff8803258d9930 [600522.091169] ffff88042ae87578 ffffffffa0563d80 0000000000000000 ffff88042704c840 [600522.091789] Call Trace: [600522.092420] [<ffffffffa04f09fa>] pnfs_generic_commit_pagelist+0x1da/0x320 [nfsv4] [600522.093052] [<ffffffffa0563d80>] ? ff_layout_commit_prepare_v3+0x30/0x30 [nfs_layout_flexfiles] [600522.093696] [<ffffffffa0562645>] ff_layout_commit_pagelist+0x15/0x20 [nfs_layout_flexfiles] [600522.094359] [<ffffffffa047bc78>] nfs_generic_commit_list+0xe8/0x120 [nfs] [600522.095032] [<ffffffffa047bd6a>] nfs_commit_inode+0xba/0x110 [nfs] [600522.095719] [<ffffffffa046ac54>] nfs_release_page+0x44/0xd0 [nfs] [600522.096410] [<ffffffff811a8122>] try_to_release_page+0x32/0x50 [600522.097109] [<ffffffff811bd4f1>] shrink_page_list+0x961/0xb30 [600522.097812] [<ffffffff811bdced>] shrink_inactive_list+0x1cd/0x550 [600522.098530] [<ffffffff811bea65>] shrink_lruvec+0x635/0x840 [600522.099250] [<ffffffff811bed60>] shrink_zone+0xf0/0x2f0 [600522.099974] [<ffffffff811bf312>] do_try_to_free_pages+0x192/0x470 [600522.100709] [<ffffffff811bf6ca>] try_to_free_pages+0xda/0x170 [600522.101464] [<ffffffff811b2198>] __alloc_pages_nodemask+0x588/0x970 [600522.102235] [<ffffffff811fbbd5>] alloc_pages_vma+0xb5/0x230 [600522.103000] [<ffffffff813a1589>] ? cpumask_any_but+0x39/0x50 [600522.103774] [<ffffffff811d6115>] wp_page_copy.isra.55+0x95/0x490 [600522.104558] [<ffffffff810e3438>] ? __wake_up+0x48/0x60 [600522.105357] [<ffffffff811d7d3b>] do_wp_page+0xab/0x4f0 [600522.106137] [<ffffffff810a1bbb>] ? release_task+0x36b/0x470 [600522.106902] [<ffffffff8126dbd7>] ? eventfd_ctx_read+0x67/0x1c0 [600522.107659] [<ffffffff811da2a8>] handle_mm_fault+0xc78/0x1900 [600522.108431] [<ffffffff81067ef1>] __do_page_fault+0x181/0x420 [600522.109173] [<ffffffff811446a6>] ? __audit_syscall_exit+0x1e6/0x280 [600522.109893] [<ffffffff810681c0>] do_page_fault+0x30/0x80 [600522.110594] [<ffffffff81024f36>] ? syscall_trace_leave+0xc6/0x120 [600522.111288] [<ffffffff81790a58>] page_fault+0x28/0x30 [600522.111947] Code: 5d c3 0f 1f 80 00 00 00 00 0f 1f 44 00 00 55 4c 8d 87 d0 01 00 00 48 89 e5 53 48 89 fb 48 83 ec 08 4c 8b 0e 49 8b 41 18 4c 39 ce <48> 8b 40 40 4c 8b 50 30 74 24 48 8b 87 d0 01 00 00 48 8b 7e 08 [600522.113343] RIP [<ffffffffa0479e72>] nfs_init_commit+0x22/0x130 [nfs] [600522.114003] RSP <ffff88042ae87438> [600522.114636] CR2: 0000000000000040 Fixes: af7cf057 (NFS: Allow multiple commit requests in flight per file) CC: stable@vger.kernel.org Signed-off-by: Weston Andros Adamson <dros@primarydata.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
2016-05-25 22:07:23 +08:00
}
static unsigned int
pnfs_alloc_ds_commits_list(struct list_head *list,
struct pnfs_ds_commit_info *fl_cinfo,
struct nfs_commit_info *cinfo)
{
struct pnfs_commit_array *array;
unsigned int ret = 0;
rcu_read_lock();
list_for_each_entry_rcu(array, &fl_cinfo->commits, cinfo_list) {
if (!array->lseg || !pnfs_get_commit_array(array))
continue;
rcu_read_unlock();
ret += pnfs_bucket_alloc_ds_commits(list, array->buckets,
array->nbuckets, cinfo);
rcu_read_lock();
pnfs_put_commit_array(array, cinfo->inode);
}
return ret;
}
/* 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 pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
struct nfs_commit_data *data, *tmp;
LIST_HEAD(list);
unsigned int nreq = 0;
if (!list_empty(mds_pages)) {
NFS: fix usage of mempools. When passed GFP flags that allow sleeping (such as GFP_NOIO), mempool_alloc() will never return NULL, it will wait until memory is available. This means that we don't need to handle failure, but that we do need to ensure one thread doesn't call mempool_alloc() twice on the one pool without queuing or freeing the first allocation. If multiple threads did this during times of high memory pressure, the pool could be exhausted and a deadlock could result. pnfs_generic_alloc_ds_commits() attempts to allocate from the nfs_commit_mempool while already holding an allocation from that pool. This is not safe. So change nfs_commitdata_alloc() to take a flag that indicates whether failure is acceptable. In pnfs_generic_alloc_ds_commits(), accept failure and handle it as we currently do. Else where, do not accept failure, and do not handle it. Even when failure is acceptable, we want to succeed if possible. That means both - using an entry from the pool if there is one - waiting for direct reclaim is there isn't. We call mempool_alloc(GFP_NOWAIT) to achieve the first, then kmem_cache_alloc(GFP_NOIO|__GFP_NORETRY) to achieve the second. Each of these can fail, but together they do the best they can without blocking indefinitely. The objects returned by kmem_cache_alloc() will still be freed by mempool_free(). This is safe as mempool_alloc() uses exactly the same function to allocate objects (since the mempool was created with mempool_create_slab_pool()). The object returned by mempool_alloc() and kmem_cache_alloc() are indistinguishable so mempool_free() will handle both identically, either adding to the pool or calling kmem_cache_free(). Also, don't test for failure when allocating from nfs_wdata_mempool. Signed-off-by: NeilBrown <neilb@suse.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2017-04-10 10:22:09 +08:00
data = nfs_commitdata_alloc(true);
data->ds_commit_index = -1;
list_splice_init(mds_pages, &data->pages);
list_add_tail(&data->list, &list);
atomic_inc(&cinfo->mds->rpcs_out);
NFS: fix usage of mempools. When passed GFP flags that allow sleeping (such as GFP_NOIO), mempool_alloc() will never return NULL, it will wait until memory is available. This means that we don't need to handle failure, but that we do need to ensure one thread doesn't call mempool_alloc() twice on the one pool without queuing or freeing the first allocation. If multiple threads did this during times of high memory pressure, the pool could be exhausted and a deadlock could result. pnfs_generic_alloc_ds_commits() attempts to allocate from the nfs_commit_mempool while already holding an allocation from that pool. This is not safe. So change nfs_commitdata_alloc() to take a flag that indicates whether failure is acceptable. In pnfs_generic_alloc_ds_commits(), accept failure and handle it as we currently do. Else where, do not accept failure, and do not handle it. Even when failure is acceptable, we want to succeed if possible. That means both - using an entry from the pool if there is one - waiting for direct reclaim is there isn't. We call mempool_alloc(GFP_NOWAIT) to achieve the first, then kmem_cache_alloc(GFP_NOIO|__GFP_NORETRY) to achieve the second. Each of these can fail, but together they do the best they can without blocking indefinitely. The objects returned by kmem_cache_alloc() will still be freed by mempool_free(). This is safe as mempool_alloc() uses exactly the same function to allocate objects (since the mempool was created with mempool_create_slab_pool()). The object returned by mempool_alloc() and kmem_cache_alloc() are indistinguishable so mempool_free() will handle both identically, either adding to the pool or calling kmem_cache_free(). Also, don't test for failure when allocating from nfs_wdata_mempool. Signed-off-by: NeilBrown <neilb@suse.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2017-04-10 10:22:09 +08:00
nreq++;
}
nreq += pnfs_alloc_ds_commits_list(&list, fl_cinfo, cinfo);
if (nreq == 0)
goto out;
list_for_each_entry_safe(data, tmp, &list, list) {
list_del(&data->list);
if (data->ds_commit_index < 0) {
nfs_init_commit(data, NULL, NULL, cinfo);
nfs_initiate_commit(NFS_CLIENT(inode), data,
NFS_PROTO(data->inode),
data->mds_ops, how, 0);
} else {
nfs_init_commit(data, NULL, data->lseg, cinfo);
initiate_commit(data, how);
}
}
out:
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,
refcount_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;
}
/*
* Checks if 'dsaddrs1' contains a subset of 'dsaddrs2'. If it does,
* declare a match.
*/
static bool
_same_data_server_addrs_locked(const struct list_head *dsaddrs1,
const struct list_head *dsaddrs2)
{
struct nfs4_pnfs_ds_addr *da1, *da2;
struct sockaddr *sa1, *sa2;
bool match = false;
list_for_each_entry(da1, dsaddrs1, da_node) {
sa1 = (struct sockaddr *)&da1->da_addr;
match = false;
list_for_each_entry(da2, dsaddrs2, da_node) {
sa2 = (struct sockaddr *)&da2->da_addr;
match = same_sockaddr(sa1, sa2);
if (match)
break;
}
if (!match)
break;
}
return match;
}
/*
* 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 (refcount_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;
refcount_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);
refcount_inc(&tmp_ds->ds_count);
dprintk("%s data server %s found, inc'ed ds_count to %d\n",
__func__, tmp_ds->ds_remotestr,
refcount_read(&tmp_ds->ds_count));
ds = tmp_ds;
}
spin_unlock(&nfs4_ds_cache_lock);
out:
return ds;
}
EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_add);
static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
{
might_sleep();
wait_on_bit(&ds->ds_state, NFS4DS_CONNECTING,
TASK_KILLABLE);
}
static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
{
smp_mb__before_atomic();
clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
smp_mb__after_atomic();
wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
}
static struct nfs_client *(*get_v3_ds_connect)(
struct nfs_server *mds_srv,
const struct sockaddr *ds_addr,
int ds_addrlen,
int ds_proto,
unsigned int ds_timeo,
unsigned int ds_retrans);
static bool load_v3_ds_connect(void)
{
if (!get_v3_ds_connect) {
get_v3_ds_connect = symbol_request(nfs3_set_ds_client);
WARN_ON_ONCE(!get_v3_ds_connect);
}
return(get_v3_ds_connect != NULL);
}
void nfs4_pnfs_v3_ds_connect_unload(void)
{
if (get_v3_ds_connect) {
symbol_put(nfs3_set_ds_client);
get_v3_ds_connect = NULL;
}
}
static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
struct nfs4_pnfs_ds *ds,
unsigned int timeo,
unsigned int retrans)
{
struct nfs_client *clp = ERR_PTR(-EIO);
struct nfs4_pnfs_ds_addr *da;
int status = 0;
dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr);
if (!load_v3_ds_connect())
goto out;
list_for_each_entry(da, &ds->ds_addrs, da_node) {
dprintk("%s: DS %s: trying address %s\n",
__func__, ds->ds_remotestr, da->da_remotestr);
if (!IS_ERR(clp)) {
struct xprt_create xprt_args = {
.ident = XPRT_TRANSPORT_TCP,
.net = clp->cl_net,
.dstaddr = (struct sockaddr *)&da->da_addr,
.addrlen = da->da_addrlen,
.servername = clp->cl_hostname,
};
/* Add this address as an alias */
rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
rpc_clnt_test_and_add_xprt, NULL);
continue;
}
clp = get_v3_ds_connect(mds_srv,
(struct sockaddr *)&da->da_addr,
da->da_addrlen, IPPROTO_TCP,
timeo, retrans);
if (IS_ERR(clp))
continue;
clp->cl_rpcclient->cl_softerr = 0;
clp->cl_rpcclient->cl_softrtry = 0;
}
if (IS_ERR(clp)) {
status = PTR_ERR(clp);
goto out;
}
smp_wmb();
ds->ds_clp = clp;
dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
out:
return status;
}
static int _nfs4_pnfs_v4_ds_connect(struct nfs_server *mds_srv,
struct nfs4_pnfs_ds *ds,
unsigned int timeo,
unsigned int retrans,
u32 minor_version)
{
struct nfs_client *clp = ERR_PTR(-EIO);
struct nfs4_pnfs_ds_addr *da;
int status = 0;
dprintk("--> %s DS %s\n", __func__, ds->ds_remotestr);
list_for_each_entry(da, &ds->ds_addrs, da_node) {
dprintk("%s: DS %s: trying address %s\n",
__func__, ds->ds_remotestr, da->da_remotestr);
if (!IS_ERR(clp) && clp->cl_mvops->session_trunk) {
struct xprt_create xprt_args = {
.ident = XPRT_TRANSPORT_TCP,
.net = clp->cl_net,
.dstaddr = (struct sockaddr *)&da->da_addr,
.addrlen = da->da_addrlen,
.servername = clp->cl_hostname,
};
struct nfs4_add_xprt_data xprtdata = {
.clp = clp,
.cred = nfs4_get_clid_cred(clp),
};
struct rpc_add_xprt_test rpcdata = {
.add_xprt_test = clp->cl_mvops->session_trunk,
.data = &xprtdata,
};
/**
* Test this address for session trunking and
* add as an alias
*/
rpc_clnt_add_xprt(clp->cl_rpcclient, &xprt_args,
rpc_clnt_setup_test_and_add_xprt,
&rpcdata);
if (xprtdata.cred)
put_cred(xprtdata.cred);
} else {
clp = nfs4_set_ds_client(mds_srv,
(struct sockaddr *)&da->da_addr,
da->da_addrlen, IPPROTO_TCP,
timeo, retrans, minor_version);
if (IS_ERR(clp))
continue;
status = nfs4_init_ds_session(clp,
mds_srv->nfs_client->cl_lease_time);
if (status) {
nfs_put_client(clp);
clp = ERR_PTR(-EIO);
continue;
}
}
}
if (IS_ERR(clp)) {
status = PTR_ERR(clp);
goto out;
}
smp_wmb();
ds->ds_clp = clp;
dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
out:
return status;
}
/*
* Create an rpc connection to the nfs4_pnfs_ds data server.
* Currently only supports IPv4 and IPv6 addresses.
* If connection fails, make devid unavailable and return a -errno.
*/
int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
struct nfs4_deviceid_node *devid, unsigned int timeo,
unsigned int retrans, u32 version, u32 minor_version)
{
int err;
again:
err = 0;
if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
if (version == 3) {
err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo,
retrans);
} else if (version == 4) {
err = _nfs4_pnfs_v4_ds_connect(mds_srv, ds, timeo,
retrans, minor_version);
} else {
dprintk("%s: unsupported DS version %d\n", __func__,
version);
err = -EPROTONOSUPPORT;
}
nfs4_clear_ds_conn_bit(ds);
} else {
nfs4_wait_ds_connect(ds);
/* what was waited on didn't connect AND didn't mark unavail */
if (!ds->ds_clp && !nfs4_test_deviceid_unavailable(devid))
goto again;
}
/*
* At this point the ds->ds_clp should be ready, but it might have
* hit an error.
*/
if (!err) {
if (!ds->ds_clp || !nfs_client_init_is_complete(ds->ds_clp)) {
WARN_ON_ONCE(ds->ds_clp ||
!nfs4_test_deviceid_unavailable(devid));
return -EINVAL;
}
err = nfs_client_init_status(ds->ds_clp);
}
return err;
}
EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_connect);
/*
* 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);
void
pnfs_layout_mark_request_commit(struct nfs_page *req,
struct pnfs_layout_segment *lseg,
struct nfs_commit_info *cinfo,
u32 ds_commit_idx)
{
struct list_head *list;
struct pnfs_commit_array *array;
struct pnfs_commit_bucket *buckets;
mutex_lock(&NFS_I(cinfo->inode)->commit_mutex);
array = pnfs_lookup_commit_array(cinfo->ds, lseg);
if (!array)
goto out_resched;
buckets = array->buckets;
list = &buckets[ds_commit_idx].written;
if (list_empty(list)) {
if (!pnfs_is_valid_lseg(lseg))
goto out_resched;
/* Non-empty buckets hold a reference on the lseg. That ref
* is normally transferred to the COMMIT call and released
* there. It could also be released if the last req is pulled
* off due to a rewrite, in which case it will be done in
* pnfs_common_clear_request_commit
*/
WARN_ON_ONCE(buckets[ds_commit_idx].wlseg != NULL);
buckets[ds_commit_idx].wlseg = pnfs_get_lseg(lseg);
}
set_bit(PG_COMMIT_TO_DS, &req->wb_flags);
cinfo->ds->nwritten++;
nfs_request_add_commit_list_locked(req, list, cinfo);
mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
nfs_mark_page_unstable(req->wb_page, cinfo);
return;
out_resched:
mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
cinfo->completion_ops->resched_write(cinfo, req);
}
EXPORT_SYMBOL_GPL(pnfs_layout_mark_request_commit);
int
pnfs_nfs_generic_sync(struct inode *inode, bool datasync)
{
int ret;
if (!pnfs_layoutcommit_outstanding(inode))
return 0;
ret = nfs_commit_inode(inode, FLUSH_SYNC);
if (ret < 0)
return ret;
if (datasync)
return 0;
return pnfs_layoutcommit_inode(inode, true);
}
EXPORT_SYMBOL_GPL(pnfs_nfs_generic_sync);