mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-25 13:43:55 +08:00
ade8febde0
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>
941 lines
23 KiB
C
941 lines
23 KiB
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 <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_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 i_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->inode->i_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->inode->i_lock);
|
|
ret = pnfs_generic_transfer_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_locked(bucket->wlseg);
|
|
bucket->wlseg = NULL;
|
|
}
|
|
}
|
|
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->inode->i_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->inode->i_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->inode->i_lock);
|
|
pnfs_put_lseg(freeme);
|
|
spin_lock(&cinfo->inode->i_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;
|
|
LIST_HEAD(pages);
|
|
int i;
|
|
|
|
spin_lock(&cinfo->inode->i_lock);
|
|
for (i = idx; i < fl_cinfo->nbuckets; i++) {
|
|
bucket = &fl_cinfo->buckets[i];
|
|
if (list_empty(&bucket->committing))
|
|
continue;
|
|
freeme = bucket->clseg;
|
|
bucket->clseg = NULL;
|
|
list_splice_init(&bucket->committing, &pages);
|
|
spin_unlock(&cinfo->inode->i_lock);
|
|
nfs_retry_commit(&pages, freeme, cinfo, i);
|
|
pnfs_put_lseg(freeme);
|
|
spin_lock(&cinfo->inode->i_lock);
|
|
}
|
|
spin_unlock(&cinfo->inode->i_lock);
|
|
}
|
|
|
|
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;
|
|
list_add(&data->pages, list);
|
|
nreq++;
|
|
}
|
|
|
|
/* Clean up on error */
|
|
pnfs_generic_retry_commit(cinfo, i);
|
|
return nreq;
|
|
}
|
|
|
|
static inline
|
|
void pnfs_fetch_commit_bucket_list(struct list_head *pages,
|
|
struct nfs_commit_data *data,
|
|
struct nfs_commit_info *cinfo)
|
|
{
|
|
struct pnfs_commit_bucket *bucket;
|
|
|
|
bucket = &cinfo->ds->buckets[data->ds_commit_index];
|
|
spin_lock(&cinfo->inode->i_lock);
|
|
list_splice_init(&bucket->committing, pages);
|
|
data->lseg = bucket->clseg;
|
|
bucket->clseg = NULL;
|
|
spin_unlock(&cinfo->inode->i_lock);
|
|
|
|
}
|
|
|
|
/* Helper function for pnfs_generic_commit_pagelist to catch an empty
|
|
* page list. This can happen when two commits race. */
|
|
static bool
|
|
pnfs_generic_commit_cancel_empty_pagelist(struct list_head *pages,
|
|
struct nfs_commit_data *data,
|
|
struct nfs_commit_info *cinfo)
|
|
{
|
|
if (list_empty(pages)) {
|
|
if (atomic_dec_and_test(&cinfo->mds->rpcs_out))
|
|
wake_up_atomic_t(&cinfo->mds->rpcs_out);
|
|
nfs_commitdata_release(data);
|
|
return true;
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
/* 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->ds_commit_index = -1;
|
|
list_add(&data->pages, &list);
|
|
nreq++;
|
|
} else {
|
|
nfs_retry_commit(mds_pages, NULL, cinfo, 0);
|
|
pnfs_generic_retry_commit(cinfo, 0);
|
|
return -ENOMEM;
|
|
}
|
|
}
|
|
|
|
nreq += pnfs_generic_alloc_ds_commits(cinfo, &list);
|
|
|
|
if (nreq == 0)
|
|
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->ds_commit_index < 0) {
|
|
/* another commit raced with us */
|
|
if (pnfs_generic_commit_cancel_empty_pagelist(mds_pages,
|
|
data, cinfo))
|
|
continue;
|
|
|
|
nfs_init_commit(data, mds_pages, NULL, cinfo);
|
|
nfs_initiate_commit(NFS_CLIENT(inode), data,
|
|
NFS_PROTO(data->inode),
|
|
data->mds_ops, how, 0);
|
|
} else {
|
|
LIST_HEAD(pages);
|
|
|
|
pnfs_fetch_commit_bucket_list(&pages, data, cinfo);
|
|
|
|
/* another commit raced with us */
|
|
if (pnfs_generic_commit_cancel_empty_pagelist(&pages,
|
|
data, cinfo))
|
|
continue;
|
|
|
|
nfs_init_commit(data, &pages, 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;
|
|
}
|
|
|
|
/*
|
|
* 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 (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);
|
|
|
|
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_client *mds_clp,
|
|
const struct sockaddr *ds_addr,
|
|
int ds_addrlen,
|
|
int ds_proto,
|
|
unsigned int ds_timeo,
|
|
unsigned int ds_retrans,
|
|
rpc_authflavor_t au_flavor);
|
|
|
|
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;
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(nfs4_pnfs_v3_ds_connect_unload);
|
|
|
|
static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
|
|
struct nfs4_pnfs_ds *ds,
|
|
unsigned int timeo,
|
|
unsigned int retrans,
|
|
rpc_authflavor_t au_flavor)
|
|
{
|
|
struct nfs_client *clp = ERR_PTR(-EIO);
|
|
struct nfs4_pnfs_ds_addr *da;
|
|
int status = 0;
|
|
|
|
dprintk("--> %s DS %s au_flavor %d\n", __func__,
|
|
ds->ds_remotestr, au_flavor);
|
|
|
|
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);
|
|
} else
|
|
clp = get_v3_ds_connect(mds_srv->nfs_client,
|
|
(struct sockaddr *)&da->da_addr,
|
|
da->da_addrlen, IPPROTO_TCP,
|
|
timeo, retrans, au_flavor);
|
|
}
|
|
|
|
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,
|
|
rpc_authflavor_t au_flavor)
|
|
{
|
|
struct nfs_client *clp = ERR_PTR(-EIO);
|
|
struct nfs4_pnfs_ds_addr *da;
|
|
int status = 0;
|
|
|
|
dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr,
|
|
au_flavor);
|
|
|
|
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);
|
|
|
|
clp = nfs4_set_ds_client(mds_srv->nfs_client,
|
|
(struct sockaddr *)&da->da_addr,
|
|
da->da_addrlen, IPPROTO_TCP,
|
|
timeo, retrans, minor_version,
|
|
au_flavor);
|
|
if (!IS_ERR(clp))
|
|
break;
|
|
}
|
|
|
|
if (IS_ERR(clp)) {
|
|
status = PTR_ERR(clp);
|
|
goto out;
|
|
}
|
|
|
|
status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time);
|
|
if (status)
|
|
goto out_put;
|
|
|
|
smp_wmb();
|
|
ds->ds_clp = clp;
|
|
dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
|
|
out:
|
|
return status;
|
|
out_put:
|
|
nfs_put_client(clp);
|
|
goto out;
|
|
}
|
|
|
|
/*
|
|
* Create an rpc connection to the nfs4_pnfs_ds data server.
|
|
* Currently only supports IPv4 and IPv6 addresses.
|
|
* If connection fails, make devid unavailable.
|
|
*/
|
|
void 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, rpc_authflavor_t au_flavor)
|
|
{
|
|
if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
|
|
int err = 0;
|
|
|
|
if (version == 3) {
|
|
err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo,
|
|
retrans, au_flavor);
|
|
} else if (version == 4) {
|
|
err = _nfs4_pnfs_v4_ds_connect(mds_srv, ds, timeo,
|
|
retrans, minor_version,
|
|
au_flavor);
|
|
} else {
|
|
dprintk("%s: unsupported DS version %d\n", __func__,
|
|
version);
|
|
err = -EPROTONOSUPPORT;
|
|
}
|
|
|
|
if (err)
|
|
nfs4_mark_deviceid_unavailable(devid);
|
|
nfs4_clear_ds_conn_bit(ds);
|
|
} else {
|
|
nfs4_wait_ds_connect(ds);
|
|
}
|
|
}
|
|
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_bucket *buckets;
|
|
|
|
spin_lock(&cinfo->inode->i_lock);
|
|
buckets = cinfo->ds->buckets;
|
|
list = &buckets[ds_commit_idx].written;
|
|
if (list_empty(list)) {
|
|
if (!pnfs_is_valid_lseg(lseg)) {
|
|
spin_unlock(&cinfo->inode->i_lock);
|
|
cinfo->completion_ops->resched_write(cinfo, req);
|
|
return;
|
|
}
|
|
/* 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);
|
|
spin_unlock(&cinfo->inode->i_lock);
|
|
nfs_mark_page_unstable(req->wb_page, cinfo);
|
|
}
|
|
EXPORT_SYMBOL_GPL(pnfs_layout_mark_request_commit);
|
|
|
|
int
|
|
pnfs_nfs_generic_sync(struct inode *inode, bool datasync)
|
|
{
|
|
if (datasync)
|
|
return 0;
|
|
return pnfs_layoutcommit_inode(inode, true);
|
|
}
|
|
EXPORT_SYMBOL_GPL(pnfs_nfs_generic_sync);
|
|
|