WSL2-Linux-Kernel/fs/nfs/pnfs.c

2423 строки
63 KiB
C
Исходник Обычный вид История

/*
* pNFS functions to call and manage layout drivers.
*
* Copyright (c) 2002 [year of first publication]
* The Regents of the University of Michigan
* All Rights Reserved
*
* Dean Hildebrand <dhildebz@umich.edu>
*
* Permission is granted to use, copy, create derivative works, and
* redistribute this software and such derivative works for any purpose,
* so long as the name of the University of Michigan is not used in
* any advertising or publicity pertaining to the use or distribution
* of this software without specific, written prior authorization. If
* the above copyright notice or any other identification of the
* University of Michigan is included in any copy of any portion of
* this software, then the disclaimer below must also be included.
*
* This software is provided as is, without representation or warranty
* of any kind either express or implied, including without limitation
* the implied warranties of merchantability, fitness for a particular
* purpose, or noninfringement. The Regents of the University of
* Michigan shall not be liable for any damages, including special,
* indirect, incidental, or consequential damages, with respect to any
* claim arising out of or in connection with the use of the software,
* even if it has been or is hereafter advised of the possibility of
* such damages.
*/
#include <linux/nfs_fs.h>
#include <linux/nfs_page.h>
#include <linux/module.h>
#include "internal.h"
#include "pnfs.h"
#include "iostat.h"
#include "nfs4trace.h"
#include "delegation.h"
#include "nfs42.h"
#define NFSDBG_FACILITY NFSDBG_PNFS
#define PNFS_LAYOUTGET_RETRY_TIMEOUT (120*HZ)
/* Locking:
*
* pnfs_spinlock:
* protects pnfs_modules_tbl.
*/
static DEFINE_SPINLOCK(pnfs_spinlock);
/*
* pnfs_modules_tbl holds all pnfs modules
*/
static LIST_HEAD(pnfs_modules_tbl);
static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo);
/* Return the registered pnfs layout driver module matching given id */
static struct pnfs_layoutdriver_type *
find_pnfs_driver_locked(u32 id)
{
struct pnfs_layoutdriver_type *local;
list_for_each_entry(local, &pnfs_modules_tbl, pnfs_tblid)
if (local->id == id)
goto out;
local = NULL;
out:
dprintk("%s: Searching for id %u, found %p\n", __func__, id, local);
return local;
}
static struct pnfs_layoutdriver_type *
find_pnfs_driver(u32 id)
{
struct pnfs_layoutdriver_type *local;
spin_lock(&pnfs_spinlock);
local = find_pnfs_driver_locked(id);
if (local != NULL && !try_module_get(local->owner)) {
dprintk("%s: Could not grab reference on module\n", __func__);
local = NULL;
}
spin_unlock(&pnfs_spinlock);
return local;
}
void
unset_pnfs_layoutdriver(struct nfs_server *nfss)
{
if (nfss->pnfs_curr_ld) {
if (nfss->pnfs_curr_ld->clear_layoutdriver)
nfss->pnfs_curr_ld->clear_layoutdriver(nfss);
/* Decrement the MDS count. Purge the deviceid cache if zero */
if (atomic_dec_and_test(&nfss->nfs_client->cl_mds_count))
nfs4_deviceid_purge_client(nfss->nfs_client);
module_put(nfss->pnfs_curr_ld->owner);
}
nfss->pnfs_curr_ld = NULL;
}
/*
* Try to set the server's pnfs module to the pnfs layout type specified by id.
* Currently only one pNFS layout driver per filesystem is supported.
*
* @id layout type. Zero (illegal layout type) indicates pNFS not in use.
*/
void
set_pnfs_layoutdriver(struct nfs_server *server, const struct nfs_fh *mntfh,
u32 id)
{
struct pnfs_layoutdriver_type *ld_type = NULL;
if (id == 0)
goto out_no_driver;
if (!(server->nfs_client->cl_exchange_flags &
(EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) {
printk(KERN_ERR "NFS: %s: id %u cl_exchange_flags 0x%x\n",
__func__, id, server->nfs_client->cl_exchange_flags);
goto out_no_driver;
}
ld_type = find_pnfs_driver(id);
if (!ld_type) {
request_module("%s-%u", LAYOUT_NFSV4_1_MODULE_PREFIX, id);
ld_type = find_pnfs_driver(id);
if (!ld_type) {
dprintk("%s: No pNFS module found for %u.\n",
__func__, id);
goto out_no_driver;
}
}
server->pnfs_curr_ld = ld_type;
if (ld_type->set_layoutdriver
&& ld_type->set_layoutdriver(server, mntfh)) {
printk(KERN_ERR "NFS: %s: Error initializing pNFS layout "
"driver %u.\n", __func__, id);
module_put(ld_type->owner);
goto out_no_driver;
}
/* Bump the MDS count */
atomic_inc(&server->nfs_client->cl_mds_count);
dprintk("%s: pNFS module for %u set\n", __func__, id);
return;
out_no_driver:
dprintk("%s: Using NFSv4 I/O\n", __func__);
server->pnfs_curr_ld = NULL;
}
int
pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
{
int status = -EINVAL;
struct pnfs_layoutdriver_type *tmp;
if (ld_type->id == 0) {
printk(KERN_ERR "NFS: %s id 0 is reserved\n", __func__);
return status;
}
if (!ld_type->alloc_lseg || !ld_type->free_lseg) {
printk(KERN_ERR "NFS: %s Layout driver must provide "
"alloc_lseg and free_lseg.\n", __func__);
return status;
}
spin_lock(&pnfs_spinlock);
tmp = find_pnfs_driver_locked(ld_type->id);
if (!tmp) {
list_add(&ld_type->pnfs_tblid, &pnfs_modules_tbl);
status = 0;
dprintk("%s Registering id:%u name:%s\n", __func__, ld_type->id,
ld_type->name);
} else {
printk(KERN_ERR "NFS: %s Module with id %d already loaded!\n",
__func__, ld_type->id);
}
spin_unlock(&pnfs_spinlock);
return status;
}
EXPORT_SYMBOL_GPL(pnfs_register_layoutdriver);
void
pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *ld_type)
{
dprintk("%s Deregistering id:%u\n", __func__, ld_type->id);
spin_lock(&pnfs_spinlock);
list_del(&ld_type->pnfs_tblid);
spin_unlock(&pnfs_spinlock);
}
EXPORT_SYMBOL_GPL(pnfs_unregister_layoutdriver);
/*
* pNFS client layout cache
*/
/* Need to hold i_lock if caller does not already hold reference */
void
pnfs_get_layout_hdr(struct pnfs_layout_hdr *lo)
{
atomic_inc(&lo->plh_refcount);
}
static struct pnfs_layout_hdr *
pnfs_alloc_layout_hdr(struct inode *ino, gfp_t gfp_flags)
{
struct pnfs_layoutdriver_type *ld = NFS_SERVER(ino)->pnfs_curr_ld;
return ld->alloc_layout_hdr(ino, gfp_flags);
}
static void
pnfs_free_layout_hdr(struct pnfs_layout_hdr *lo)
{
struct nfs_server *server = NFS_SERVER(lo->plh_inode);
struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld;
if (!list_empty(&lo->plh_layouts)) {
struct nfs_client *clp = server->nfs_client;
spin_lock(&clp->cl_lock);
list_del_init(&lo->plh_layouts);
spin_unlock(&clp->cl_lock);
}
put_rpccred(lo->plh_lc_cred);
return ld->free_layout_hdr(lo);
}
static void
pnfs_detach_layout_hdr(struct pnfs_layout_hdr *lo)
{
struct nfs_inode *nfsi = NFS_I(lo->plh_inode);
dprintk("%s: freeing layout cache %p\n", __func__, lo);
nfsi->layout = NULL;
/* Reset MDS Threshold I/O counters */
nfsi->write_io = 0;
nfsi->read_io = 0;
}
void
pnfs_put_layout_hdr(struct pnfs_layout_hdr *lo)
{
struct inode *inode = lo->plh_inode;
pnfs_layoutreturn_before_put_layout_hdr(lo);
if (atomic_dec_and_lock(&lo->plh_refcount, &inode->i_lock)) {
if (!list_empty(&lo->plh_segs))
WARN_ONCE(1, "NFS: BUG unfreed layout segments.\n");
pnfs_detach_layout_hdr(lo);
spin_unlock(&inode->i_lock);
pnfs_free_layout_hdr(lo);
}
}
static int
pnfs_iomode_to_fail_bit(u32 iomode)
{
return iomode == IOMODE_RW ?
NFS_LAYOUT_RW_FAILED : NFS_LAYOUT_RO_FAILED;
}
static void
pnfs_layout_set_fail_bit(struct pnfs_layout_hdr *lo, int fail_bit)
{
lo->plh_retry_timestamp = jiffies;
if (!test_and_set_bit(fail_bit, &lo->plh_flags))
atomic_inc(&lo->plh_refcount);
}
static void
pnfs_layout_clear_fail_bit(struct pnfs_layout_hdr *lo, int fail_bit)
{
if (test_and_clear_bit(fail_bit, &lo->plh_flags))
atomic_dec(&lo->plh_refcount);
}
static void
pnfs_layout_io_set_failed(struct pnfs_layout_hdr *lo, u32 iomode)
{
struct inode *inode = lo->plh_inode;
struct pnfs_layout_range range = {
.iomode = iomode,
.offset = 0,
.length = NFS4_MAX_UINT64,
};
LIST_HEAD(head);
spin_lock(&inode->i_lock);
pnfs_layout_set_fail_bit(lo, pnfs_iomode_to_fail_bit(iomode));
pnfs_mark_matching_lsegs_invalid(lo, &head, &range);
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&head);
dprintk("%s Setting layout IOMODE_%s fail bit\n", __func__,
iomode == IOMODE_RW ? "RW" : "READ");
}
static bool
pnfs_layout_io_test_failed(struct pnfs_layout_hdr *lo, u32 iomode)
{
unsigned long start, end;
int fail_bit = pnfs_iomode_to_fail_bit(iomode);
if (test_bit(fail_bit, &lo->plh_flags) == 0)
return false;
end = jiffies;
start = end - PNFS_LAYOUTGET_RETRY_TIMEOUT;
if (!time_in_range(lo->plh_retry_timestamp, start, end)) {
/* It is time to retry the failed layoutgets */
pnfs_layout_clear_fail_bit(lo, fail_bit);
return false;
}
return true;
}
static void
init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg)
{
INIT_LIST_HEAD(&lseg->pls_list);
INIT_LIST_HEAD(&lseg->pls_lc_list);
atomic_set(&lseg->pls_refcount, 1);
smp_mb();
set_bit(NFS_LSEG_VALID, &lseg->pls_flags);
lseg->pls_layout = lo;
}
static void pnfs_free_lseg(struct pnfs_layout_segment *lseg)
{
struct inode *ino = lseg->pls_layout->plh_inode;
NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
}
static void
pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
struct pnfs_layout_segment *lseg)
{
struct inode *inode = lo->plh_inode;
WARN_ON(test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
list_del_init(&lseg->pls_list);
/* Matched by pnfs_get_layout_hdr in pnfs_layout_insert_lseg */
atomic_dec(&lo->plh_refcount);
if (list_empty(&lo->plh_segs))
clear_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
}
void
pnfs_put_lseg(struct pnfs_layout_segment *lseg)
{
struct pnfs_layout_hdr *lo;
struct inode *inode;
if (!lseg)
return;
dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg,
atomic_read(&lseg->pls_refcount),
test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
lo = lseg->pls_layout;
inode = lo->plh_inode;
if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) {
if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) {
spin_unlock(&inode->i_lock);
return;
}
pnfs_get_layout_hdr(lo);
pnfs_layout_remove_lseg(lo, lseg);
spin_unlock(&inode->i_lock);
pnfs_free_lseg(lseg);
pnfs_put_layout_hdr(lo);
}
}
EXPORT_SYMBOL_GPL(pnfs_put_lseg);
static void pnfs_free_lseg_async_work(struct work_struct *work)
{
struct pnfs_layout_segment *lseg;
struct pnfs_layout_hdr *lo;
lseg = container_of(work, struct pnfs_layout_segment, pls_work);
lo = lseg->pls_layout;
pnfs_free_lseg(lseg);
pnfs_put_layout_hdr(lo);
}
static void pnfs_free_lseg_async(struct pnfs_layout_segment *lseg)
{
INIT_WORK(&lseg->pls_work, pnfs_free_lseg_async_work);
schedule_work(&lseg->pls_work);
}
void
pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg)
{
if (!lseg)
return;
assert_spin_locked(&lseg->pls_layout->plh_inode->i_lock);
dprintk("%s: lseg %p ref %d valid %d\n", __func__, lseg,
atomic_read(&lseg->pls_refcount),
test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
if (atomic_dec_and_test(&lseg->pls_refcount)) {
struct pnfs_layout_hdr *lo = lseg->pls_layout;
if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags))
return;
pnfs_get_layout_hdr(lo);
pnfs_layout_remove_lseg(lo, lseg);
pnfs_free_lseg_async(lseg);
}
}
EXPORT_SYMBOL_GPL(pnfs_put_lseg_locked);
static u64
end_offset(u64 start, u64 len)
{
u64 end;
end = start + len;
return end >= start ? end : NFS4_MAX_UINT64;
}
/*
* is l2 fully contained in l1?
* start1 end1
* [----------------------------------)
* start2 end2
* [----------------)
*/
static bool
pnfs_lseg_range_contained(const struct pnfs_layout_range *l1,
const struct pnfs_layout_range *l2)
{
u64 start1 = l1->offset;
u64 end1 = end_offset(start1, l1->length);
u64 start2 = l2->offset;
u64 end2 = end_offset(start2, l2->length);
return (start1 <= start2) && (end1 >= end2);
}
/*
* is l1 and l2 intersecting?
* start1 end1
* [----------------------------------)
* start2 end2
* [----------------)
*/
static bool
pnfs_lseg_range_intersecting(const struct pnfs_layout_range *l1,
const struct pnfs_layout_range *l2)
{
u64 start1 = l1->offset;
u64 end1 = end_offset(start1, l1->length);
u64 start2 = l2->offset;
u64 end2 = end_offset(start2, l2->length);
return (end1 == NFS4_MAX_UINT64 || end1 > start2) &&
(end2 == NFS4_MAX_UINT64 || end2 > start1);
}
static bool
should_free_lseg(const struct pnfs_layout_range *lseg_range,
const struct pnfs_layout_range *recall_range)
{
return (recall_range->iomode == IOMODE_ANY ||
lseg_range->iomode == recall_range->iomode) &&
pnfs_lseg_range_intersecting(lseg_range, recall_range);
}
static bool pnfs_lseg_dec_and_remove_zero(struct pnfs_layout_segment *lseg,
struct list_head *tmp_list)
{
if (!atomic_dec_and_test(&lseg->pls_refcount))
return false;
pnfs_layout_remove_lseg(lseg->pls_layout, lseg);
list_add(&lseg->pls_list, tmp_list);
return true;
}
/* Returns 1 if lseg is removed from list, 0 otherwise */
static int mark_lseg_invalid(struct pnfs_layout_segment *lseg,
struct list_head *tmp_list)
{
int rv = 0;
if (test_and_clear_bit(NFS_LSEG_VALID, &lseg->pls_flags)) {
/* Remove the reference keeping the lseg in the
* list. It will now be removed when all
* outstanding io is finished.
*/
dprintk("%s: lseg %p ref %d\n", __func__, lseg,
atomic_read(&lseg->pls_refcount));
if (pnfs_lseg_dec_and_remove_zero(lseg, tmp_list))
rv = 1;
}
return rv;
}
/* Returns count of number of matching invalid lsegs remaining in list
* after call.
*/
int
pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
struct list_head *tmp_list,
const struct pnfs_layout_range *recall_range)
{
struct pnfs_layout_segment *lseg, *next;
int remaining = 0;
dprintk("%s:Begin lo %p\n", __func__, lo);
if (list_empty(&lo->plh_segs))
return 0;
list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
if (!recall_range ||
should_free_lseg(&lseg->pls_range, recall_range)) {
dprintk("%s: freeing lseg %p iomode %d "
"offset %llu length %llu\n", __func__,
lseg, lseg->pls_range.iomode, lseg->pls_range.offset,
lseg->pls_range.length);
if (!mark_lseg_invalid(lseg, tmp_list))
remaining++;
}
dprintk("%s:Return %i\n", __func__, remaining);
return remaining;
}
/* note free_me must contain lsegs from a single layout_hdr */
void
pnfs_free_lseg_list(struct list_head *free_me)
{
struct pnfs_layout_segment *lseg, *tmp;
if (list_empty(free_me))
return;
list_for_each_entry_safe(lseg, tmp, free_me, pls_list) {
list_del(&lseg->pls_list);
pnfs_free_lseg(lseg);
}
}
void
pnfs_destroy_layout(struct nfs_inode *nfsi)
{
struct pnfs_layout_hdr *lo;
LIST_HEAD(tmp_list);
spin_lock(&nfsi->vfs_inode.i_lock);
lo = nfsi->layout;
if (lo) {
lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
pnfs_get_layout_hdr(lo);
pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RO_FAILED);
pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED);
spin_unlock(&nfsi->vfs_inode.i_lock);
pnfs_free_lseg_list(&tmp_list);
pnfs_put_layout_hdr(lo);
} else
spin_unlock(&nfsi->vfs_inode.i_lock);
}
EXPORT_SYMBOL_GPL(pnfs_destroy_layout);
static bool
pnfs_layout_add_bulk_destroy_list(struct inode *inode,
struct list_head *layout_list)
{
struct pnfs_layout_hdr *lo;
bool ret = false;
spin_lock(&inode->i_lock);
lo = NFS_I(inode)->layout;
if (lo != NULL && list_empty(&lo->plh_bulk_destroy)) {
pnfs_get_layout_hdr(lo);
list_add(&lo->plh_bulk_destroy, layout_list);
ret = true;
}
spin_unlock(&inode->i_lock);
return ret;
}
/* Caller must hold rcu_read_lock and clp->cl_lock */
static int
pnfs_layout_bulk_destroy_byserver_locked(struct nfs_client *clp,
struct nfs_server *server,
struct list_head *layout_list)
{
struct pnfs_layout_hdr *lo, *next;
struct inode *inode;
list_for_each_entry_safe(lo, next, &server->layouts, plh_layouts) {
inode = igrab(lo->plh_inode);
if (inode == NULL)
continue;
list_del_init(&lo->plh_layouts);
if (pnfs_layout_add_bulk_destroy_list(inode, layout_list))
continue;
rcu_read_unlock();
spin_unlock(&clp->cl_lock);
iput(inode);
spin_lock(&clp->cl_lock);
rcu_read_lock();
return -EAGAIN;
}
return 0;
}
static int
pnfs_layout_free_bulk_destroy_list(struct list_head *layout_list,
bool is_bulk_recall)
{
struct pnfs_layout_hdr *lo;
struct inode *inode;
struct pnfs_layout_range range = {
.iomode = IOMODE_ANY,
.offset = 0,
.length = NFS4_MAX_UINT64,
};
LIST_HEAD(lseg_list);
int ret = 0;
while (!list_empty(layout_list)) {
lo = list_entry(layout_list->next, struct pnfs_layout_hdr,
plh_bulk_destroy);
dprintk("%s freeing layout for inode %lu\n", __func__,
lo->plh_inode->i_ino);
inode = lo->plh_inode;
pnfs_layoutcommit_inode(inode, false);
spin_lock(&inode->i_lock);
list_del_init(&lo->plh_bulk_destroy);
lo->plh_block_lgets++; /* permanently block new LAYOUTGETs */
if (is_bulk_recall)
set_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
if (pnfs_mark_matching_lsegs_invalid(lo, &lseg_list, &range))
ret = -EAGAIN;
spin_unlock(&inode->i_lock);
pnfs_free_lseg_list(&lseg_list);
/* Free all lsegs that are attached to commit buckets */
nfs_commit_inode(inode, 0);
pnfs_put_layout_hdr(lo);
iput(inode);
}
return ret;
}
int
pnfs_destroy_layouts_byfsid(struct nfs_client *clp,
struct nfs_fsid *fsid,
bool is_recall)
{
struct nfs_server *server;
LIST_HEAD(layout_list);
spin_lock(&clp->cl_lock);
rcu_read_lock();
restart:
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
if (memcmp(&server->fsid, fsid, sizeof(*fsid)) != 0)
continue;
if (pnfs_layout_bulk_destroy_byserver_locked(clp,
server,
&layout_list) != 0)
goto restart;
}
rcu_read_unlock();
spin_unlock(&clp->cl_lock);
if (list_empty(&layout_list))
return 0;
return pnfs_layout_free_bulk_destroy_list(&layout_list, is_recall);
}
int
pnfs_destroy_layouts_byclid(struct nfs_client *clp,
bool is_recall)
{
struct nfs_server *server;
LIST_HEAD(layout_list);
spin_lock(&clp->cl_lock);
rcu_read_lock();
restart:
list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
if (pnfs_layout_bulk_destroy_byserver_locked(clp,
server,
&layout_list) != 0)
goto restart;
}
rcu_read_unlock();
spin_unlock(&clp->cl_lock);
if (list_empty(&layout_list))
return 0;
return pnfs_layout_free_bulk_destroy_list(&layout_list, is_recall);
}
/*
* Called by the state manger to remove all layouts established under an
* expired lease.
*/
void
pnfs_destroy_all_layouts(struct nfs_client *clp)
{
nfs4_deviceid_mark_client_invalid(clp);
nfs4_deviceid_purge_client(clp);
pnfs_destroy_layouts_byclid(clp, false);
}
/*
* Compare 2 layout stateid sequence ids, to see which is newer,
* taking into account wraparound issues.
*/
static bool pnfs_seqid_is_newer(u32 s1, u32 s2)
{
return (s32)(s1 - s2) > 0;
}
/* update lo->plh_stateid with new if is more recent */
void
pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, const nfs4_stateid *new,
bool update_barrier)
{
u32 oldseq, newseq, new_barrier;
int empty = list_empty(&lo->plh_segs);
oldseq = be32_to_cpu(lo->plh_stateid.seqid);
newseq = be32_to_cpu(new->seqid);
if (empty || pnfs_seqid_is_newer(newseq, oldseq)) {
nfs4_stateid_copy(&lo->plh_stateid, new);
if (update_barrier) {
new_barrier = be32_to_cpu(new->seqid);
} else {
/* Because of wraparound, we want to keep the barrier
* "close" to the current seqids.
*/
new_barrier = newseq - atomic_read(&lo->plh_outstanding);
}
if (empty || pnfs_seqid_is_newer(new_barrier, lo->plh_barrier))
lo->plh_barrier = new_barrier;
}
}
static bool
pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo,
const nfs4_stateid *stateid)
{
u32 seqid = be32_to_cpu(stateid->seqid);
return !pnfs_seqid_is_newer(seqid, lo->plh_barrier);
}
/* lget is set to 1 if called from inside send_layoutget call chain */
static bool
pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo)
{
return lo->plh_block_lgets ||
test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags);
}
int
pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
const struct pnfs_layout_range *range,
struct nfs4_state *open_state)
{
int status = 0;
dprintk("--> %s\n", __func__);
spin_lock(&lo->plh_inode->i_lock);
if (pnfs_layoutgets_blocked(lo)) {
status = -EAGAIN;
} else if (!nfs4_valid_open_stateid(open_state)) {
status = -EBADF;
} else if (list_empty(&lo->plh_segs) ||
test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags)) {
int seq;
do {
seq = read_seqbegin(&open_state->seqlock);
nfs4_stateid_copy(dst, &open_state->stateid);
} while (read_seqretry(&open_state->seqlock, seq));
} else
nfs4_stateid_copy(dst, &lo->plh_stateid);
spin_unlock(&lo->plh_inode->i_lock);
dprintk("<-- %s\n", __func__);
return status;
}
/*
* Get layout from server.
* for now, assume that whole file layouts are requested.
* arg->offset: 0
* arg->length: all ones
*/
static struct pnfs_layout_segment *
send_layoutget(struct pnfs_layout_hdr *lo,
struct nfs_open_context *ctx,
const struct pnfs_layout_range *range,
gfp_t gfp_flags)
{
struct inode *ino = lo->plh_inode;
struct nfs_server *server = NFS_SERVER(ino);
struct nfs4_layoutget *lgp;
struct pnfs_layout_segment *lseg;
loff_t i_size;
dprintk("--> %s\n", __func__);
/*
* Synchronously retrieve layout information from server and
* store in lseg. If we race with a concurrent seqid morphing
* op, then re-send the LAYOUTGET.
*/
do {
lgp = kzalloc(sizeof(*lgp), gfp_flags);
if (lgp == NULL)
return NULL;
i_size = i_size_read(ino);
lgp->args.minlength = PAGE_CACHE_SIZE;
if (lgp->args.minlength > range->length)
lgp->args.minlength = range->length;
if (range->iomode == IOMODE_READ) {
if (range->offset >= i_size)
lgp->args.minlength = 0;
else if (i_size - range->offset < lgp->args.minlength)
lgp->args.minlength = i_size - range->offset;
}
lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE;
pnfs_copy_range(&lgp->args.range, range);
lgp->args.type = server->pnfs_curr_ld->id;
lgp->args.inode = ino;
lgp->args.ctx = get_nfs_open_context(ctx);
lgp->gfp_flags = gfp_flags;
lgp->cred = lo->plh_lc_cred;
lseg = nfs4_proc_layoutget(lgp, gfp_flags);
} while (lseg == ERR_PTR(-EAGAIN));
if (IS_ERR(lseg) && !nfs_error_is_fatal(PTR_ERR(lseg)))
lseg = NULL;
else
pnfs_layout_clear_fail_bit(lo,
pnfs_iomode_to_fail_bit(range->iomode));
return lseg;
}
static void pnfs_clear_layoutcommit(struct inode *inode,
struct list_head *head)
{
struct nfs_inode *nfsi = NFS_I(inode);
struct pnfs_layout_segment *lseg, *tmp;
if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
return;
list_for_each_entry_safe(lseg, tmp, &nfsi->layout->plh_segs, pls_list) {
if (!test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
continue;
pnfs_lseg_dec_and_remove_zero(lseg, head);
}
}
void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
{
clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags);
smp_mb__after_atomic();
wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
}
static bool
pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
{
if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
return false;
lo->plh_return_iomode = 0;
pnfs_get_layout_hdr(lo);
clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
return true;
}
static int
pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, const nfs4_stateid *stateid,
enum pnfs_iomode iomode, bool sync)
{
struct inode *ino = lo->plh_inode;
struct nfs4_layoutreturn *lrp;
int status = 0;
lrp = kzalloc(sizeof(*lrp), GFP_NOFS);
if (unlikely(lrp == NULL)) {
status = -ENOMEM;
spin_lock(&ino->i_lock);
pnfs_clear_layoutreturn_waitbit(lo);
spin_unlock(&ino->i_lock);
pnfs_put_layout_hdr(lo);
goto out;
}
nfs4_stateid_copy(&lrp->args.stateid, stateid);
lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
lrp->args.inode = ino;
lrp->args.range.iomode = iomode;
lrp->args.range.offset = 0;
lrp->args.range.length = NFS4_MAX_UINT64;
lrp->args.layout = lo;
lrp->clp = NFS_SERVER(ino)->nfs_client;
lrp->cred = lo->plh_lc_cred;
status = nfs4_proc_layoutreturn(lrp, sync);
out:
dprintk("<-- %s status: %d\n", __func__, status);
return status;
}
/* Return true if layoutreturn is needed */
static bool
pnfs_layout_need_return(struct pnfs_layout_hdr *lo)
{
struct pnfs_layout_segment *s;
if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
return false;
/* Defer layoutreturn until all lsegs are done */
list_for_each_entry(s, &lo->plh_segs, pls_list) {
if (test_bit(NFS_LSEG_LAYOUTRETURN, &s->pls_flags))
return false;
}
return true;
}
static void pnfs_layoutreturn_before_put_layout_hdr(struct pnfs_layout_hdr *lo)
{
struct inode *inode= lo->plh_inode;
if (!test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags))
return;
spin_lock(&inode->i_lock);
if (pnfs_layout_need_return(lo)) {
nfs4_stateid stateid;
enum pnfs_iomode iomode;
bool send;
nfs4_stateid_copy(&stateid, &lo->plh_stateid);
iomode = lo->plh_return_iomode;
send = pnfs_prepare_layoutreturn(lo);
spin_unlock(&inode->i_lock);
if (send) {
/* Send an async layoutreturn so we dont deadlock */
pnfs_send_layoutreturn(lo, &stateid, iomode, false);
}
} else
spin_unlock(&inode->i_lock);
}
/*
* Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
* when the layout segment list is empty.
*
* Note that a pnfs_layout_hdr can exist with an empty layout segment
* list when LAYOUTGET has failed, or when LAYOUTGET succeeded, but the
* deviceid is marked invalid.
*/
int
_pnfs_return_layout(struct inode *ino)
{
struct pnfs_layout_hdr *lo = NULL;
struct nfs_inode *nfsi = NFS_I(ino);
LIST_HEAD(tmp_list);
nfs4_stateid stateid;
int status = 0, empty;
bool send;
dprintk("NFS: %s for inode %lu\n", __func__, ino->i_ino);
spin_lock(&ino->i_lock);
lo = nfsi->layout;
if (!lo) {
spin_unlock(&ino->i_lock);
dprintk("NFS: %s no layout to return\n", __func__);
goto out;
}
nfs4_stateid_copy(&stateid, &nfsi->layout->plh_stateid);
/* Reference matched in nfs4_layoutreturn_release */
pnfs_get_layout_hdr(lo);
empty = list_empty(&lo->plh_segs);
pnfs_clear_layoutcommit(ino, &tmp_list);
pnfs_mark_matching_lsegs_invalid(lo, &tmp_list, NULL);
if (NFS_SERVER(ino)->pnfs_curr_ld->return_range) {
struct pnfs_layout_range range = {
.iomode = IOMODE_ANY,
.offset = 0,
.length = NFS4_MAX_UINT64,
};
NFS_SERVER(ino)->pnfs_curr_ld->return_range(lo, &range);
}
/* Don't send a LAYOUTRETURN if list was initially empty */
if (empty) {
spin_unlock(&ino->i_lock);
dprintk("NFS: %s no layout segments to return\n", __func__);
goto out_put_layout_hdr;
}
set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
send = pnfs_prepare_layoutreturn(lo);
spin_unlock(&ino->i_lock);
pnfs_free_lseg_list(&tmp_list);
if (send)
status = pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true);
out_put_layout_hdr:
pnfs_put_layout_hdr(lo);
out:
dprintk("<-- %s status: %d\n", __func__, status);
return status;
}
EXPORT_SYMBOL_GPL(_pnfs_return_layout);
int
pnfs_commit_and_return_layout(struct inode *inode)
{
struct pnfs_layout_hdr *lo;
int ret;
spin_lock(&inode->i_lock);
lo = NFS_I(inode)->layout;
if (lo == NULL) {
spin_unlock(&inode->i_lock);
return 0;
}
pnfs_get_layout_hdr(lo);
/* Block new layoutgets and read/write to ds */
lo->plh_block_lgets++;
spin_unlock(&inode->i_lock);
filemap_fdatawait(inode->i_mapping);
ret = pnfs_layoutcommit_inode(inode, true);
if (ret == 0)
ret = _pnfs_return_layout(inode);
spin_lock(&inode->i_lock);
lo->plh_block_lgets--;
spin_unlock(&inode->i_lock);
pnfs_put_layout_hdr(lo);
return ret;
}
bool pnfs_roc(struct inode *ino)
{
struct nfs_inode *nfsi = NFS_I(ino);
struct nfs_open_context *ctx;
struct nfs4_state *state;
struct pnfs_layout_hdr *lo;
struct pnfs_layout_segment *lseg, *tmp;
nfs4_stateid stateid;
LIST_HEAD(tmp_list);
bool found = false, layoutreturn = false, roc = false;
spin_lock(&ino->i_lock);
lo = nfsi->layout;
if (!lo || test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags))
goto out_noroc;
/* no roc if we hold a delegation */
if (nfs4_check_delegation(ino, FMODE_READ))
goto out_noroc;
list_for_each_entry(ctx, &nfsi->open_files, list) {
state = ctx->state;
/* Don't return layout if there is open file state */
if (state != NULL && state->state != 0)
goto out_noroc;
}
nfs4_stateid_copy(&stateid, &lo->plh_stateid);
/* always send layoutreturn if being marked so */
if (test_and_clear_bit(NFS_LAYOUT_RETURN_REQUESTED,
&lo->plh_flags))
layoutreturn = pnfs_prepare_layoutreturn(lo);
list_for_each_entry_safe(lseg, tmp, &lo->plh_segs, pls_list)
/* If we are sending layoutreturn, invalidate all valid lsegs */
if (layoutreturn || test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) {
mark_lseg_invalid(lseg, &tmp_list);
found = true;
}
/* ROC in two conditions:
* 1. there are ROC lsegs
* 2. we don't send layoutreturn
*/
if (found && !layoutreturn) {
/* lo ref dropped in pnfs_roc_release() */
pnfs_get_layout_hdr(lo);
roc = true;
}
out_noroc:
spin_unlock(&ino->i_lock);
pnfs_free_lseg_list(&tmp_list);
pnfs_layoutcommit_inode(ino, true);
if (layoutreturn)
pnfs_send_layoutreturn(lo, &stateid, IOMODE_ANY, true);
return roc;
}
void pnfs_roc_release(struct inode *ino)
{
struct pnfs_layout_hdr *lo;
spin_lock(&ino->i_lock);
lo = NFS_I(ino)->layout;
pnfs_clear_layoutreturn_waitbit(lo);
if (atomic_dec_and_test(&lo->plh_refcount)) {
pnfs_detach_layout_hdr(lo);
spin_unlock(&ino->i_lock);
pnfs_free_layout_hdr(lo);
} else
spin_unlock(&ino->i_lock);
}
void pnfs_roc_set_barrier(struct inode *ino, u32 barrier)
{
struct pnfs_layout_hdr *lo;
spin_lock(&ino->i_lock);
lo = NFS_I(ino)->layout;
pnfs_mark_layout_returned_if_empty(lo);
if (pnfs_seqid_is_newer(barrier, lo->plh_barrier))
lo->plh_barrier = barrier;
spin_unlock(&ino->i_lock);
trace_nfs4_layoutreturn_on_close(ino, 0);
}
void pnfs_roc_get_barrier(struct inode *ino, u32 *barrier)
{
struct nfs_inode *nfsi = NFS_I(ino);
struct pnfs_layout_hdr *lo;
u32 current_seqid;
spin_lock(&ino->i_lock);
lo = nfsi->layout;
current_seqid = be32_to_cpu(lo->plh_stateid.seqid);
/* Since close does not return a layout stateid for use as
* a barrier, we choose the worst-case barrier.
*/
*barrier = current_seqid + atomic_read(&lo->plh_outstanding);
spin_unlock(&ino->i_lock);
}
bool pnfs_wait_on_layoutreturn(struct inode *ino, struct rpc_task *task)
{
struct nfs_inode *nfsi = NFS_I(ino);
struct pnfs_layout_hdr *lo;
bool sleep = false;
/* we might not have grabbed lo reference. so need to check under
* i_lock */
spin_lock(&ino->i_lock);
lo = nfsi->layout;
if (lo && test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
sleep = true;
spin_unlock(&ino->i_lock);
if (sleep)
rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
return sleep;
}
/*
* Compare two layout segments for sorting into layout cache.
* We want to preferentially return RW over RO layouts, so ensure those
* are seen first.
*/
static s64
pnfs_lseg_range_cmp(const struct pnfs_layout_range *l1,
const struct pnfs_layout_range *l2)
{
s64 d;
/* high offset > low offset */
d = l1->offset - l2->offset;
if (d)
return d;
/* short length > long length */
d = l2->length - l1->length;
if (d)
return d;
/* read > read/write */
return (int)(l1->iomode == IOMODE_READ) - (int)(l2->iomode == IOMODE_READ);
}
static bool
pnfs_lseg_range_is_after(const struct pnfs_layout_range *l1,
const struct pnfs_layout_range *l2)
{
return pnfs_lseg_range_cmp(l1, l2) > 0;
}
static bool
pnfs_lseg_no_merge(struct pnfs_layout_segment *lseg,
struct pnfs_layout_segment *old)
{
return false;
}
void
pnfs_generic_layout_insert_lseg(struct pnfs_layout_hdr *lo,
struct pnfs_layout_segment *lseg,
bool (*is_after)(const struct pnfs_layout_range *,
const struct pnfs_layout_range *),
bool (*do_merge)(struct pnfs_layout_segment *,
struct pnfs_layout_segment *),
struct list_head *free_me)
{
struct pnfs_layout_segment *lp, *tmp;
dprintk("%s:Begin\n", __func__);
list_for_each_entry_safe(lp, tmp, &lo->plh_segs, pls_list) {
if (test_bit(NFS_LSEG_VALID, &lp->pls_flags) == 0)
continue;
if (do_merge(lseg, lp)) {
mark_lseg_invalid(lp, free_me);
continue;
}
if (is_after(&lseg->pls_range, &lp->pls_range))
continue;
list_add_tail(&lseg->pls_list, &lp->pls_list);
dprintk("%s: inserted lseg %p "
"iomode %d offset %llu length %llu before "
"lp %p iomode %d offset %llu length %llu\n",
__func__, lseg, lseg->pls_range.iomode,
lseg->pls_range.offset, lseg->pls_range.length,
lp, lp->pls_range.iomode, lp->pls_range.offset,
lp->pls_range.length);
goto out;
}
list_add_tail(&lseg->pls_list, &lo->plh_segs);
dprintk("%s: inserted lseg %p "
"iomode %d offset %llu length %llu at tail\n",
__func__, lseg, lseg->pls_range.iomode,
lseg->pls_range.offset, lseg->pls_range.length);
out:
pnfs_get_layout_hdr(lo);
dprintk("%s:Return\n", __func__);
}
EXPORT_SYMBOL_GPL(pnfs_generic_layout_insert_lseg);
static void
pnfs_layout_insert_lseg(struct pnfs_layout_hdr *lo,
struct pnfs_layout_segment *lseg,
struct list_head *free_me)
{
struct inode *inode = lo->plh_inode;
struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
if (ld->add_lseg != NULL)
ld->add_lseg(lo, lseg, free_me);
else
pnfs_generic_layout_insert_lseg(lo, lseg,
pnfs_lseg_range_is_after,
pnfs_lseg_no_merge,
free_me);
}
static struct pnfs_layout_hdr *
alloc_init_layout_hdr(struct inode *ino,
struct nfs_open_context *ctx,
gfp_t gfp_flags)
{
struct pnfs_layout_hdr *lo;
lo = pnfs_alloc_layout_hdr(ino, gfp_flags);
if (!lo)
return NULL;
atomic_set(&lo->plh_refcount, 1);
INIT_LIST_HEAD(&lo->plh_layouts);
INIT_LIST_HEAD(&lo->plh_segs);
INIT_LIST_HEAD(&lo->plh_bulk_destroy);
lo->plh_inode = ino;
lo->plh_lc_cred = get_rpccred(ctx->cred);
return lo;
}
static struct pnfs_layout_hdr *
pnfs_find_alloc_layout(struct inode *ino,
struct nfs_open_context *ctx,
gfp_t gfp_flags)
{
struct nfs_inode *nfsi = NFS_I(ino);
struct pnfs_layout_hdr *new = NULL;
dprintk("%s Begin ino=%p layout=%p\n", __func__, ino, nfsi->layout);
if (nfsi->layout != NULL)
goto out_existing;
spin_unlock(&ino->i_lock);
new = alloc_init_layout_hdr(ino, ctx, gfp_flags);
spin_lock(&ino->i_lock);
if (likely(nfsi->layout == NULL)) { /* Won the race? */
nfsi->layout = new;
return new;
} else if (new != NULL)
pnfs_free_layout_hdr(new);
out_existing:
pnfs_get_layout_hdr(nfsi->layout);
return nfsi->layout;
}
/*
* iomode matching rules:
* iomode lseg match
* ----- ----- -----
* ANY READ true
* ANY RW true
* RW READ false
* RW RW true
* READ READ true
* READ RW true
*/
static bool
pnfs_lseg_range_match(const struct pnfs_layout_range *ls_range,
const struct pnfs_layout_range *range)
{
struct pnfs_layout_range range1;
if ((range->iomode == IOMODE_RW &&
ls_range->iomode != IOMODE_RW) ||
!pnfs_lseg_range_intersecting(ls_range, range))
return 0;
/* range1 covers only the first byte in the range */
range1 = *range;
range1.length = 1;
return pnfs_lseg_range_contained(ls_range, &range1);
}
/*
* lookup range in layout
*/
static struct pnfs_layout_segment *
pnfs_find_lseg(struct pnfs_layout_hdr *lo,
struct pnfs_layout_range *range)
{
struct pnfs_layout_segment *lseg, *ret = NULL;
dprintk("%s:Begin\n", __func__);
list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) &&
!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags) &&
pnfs_lseg_range_match(&lseg->pls_range, range)) {
ret = pnfs_get_lseg(lseg);
break;
}
}
dprintk("%s:Return lseg %p ref %d\n",
__func__, ret, ret ? atomic_read(&ret->pls_refcount) : 0);
return ret;
}
/*
* Use mdsthreshold hints set at each OPEN to determine if I/O should go
* to the MDS or over pNFS
*
* The nfs_inode read_io and write_io fields are cumulative counters reset
* when there are no layout segments. Note that in pnfs_update_layout iomode
* is set to IOMODE_READ for a READ request, and set to IOMODE_RW for a
* WRITE request.
*
* A return of true means use MDS I/O.
*
* From rfc 5661:
* If a file's size is smaller than the file size threshold, data accesses
* SHOULD be sent to the metadata server. If an I/O request has a length that
* is below the I/O size threshold, the I/O SHOULD be sent to the metadata
* server. If both file size and I/O size are provided, the client SHOULD
* reach or exceed both thresholds before sending its read or write
* requests to the data server.
*/
static bool pnfs_within_mdsthreshold(struct nfs_open_context *ctx,
struct inode *ino, int iomode)
{
struct nfs4_threshold *t = ctx->mdsthreshold;
struct nfs_inode *nfsi = NFS_I(ino);
loff_t fsize = i_size_read(ino);
bool size = false, size_set = false, io = false, io_set = false, ret = false;
if (t == NULL)
return ret;
dprintk("%s bm=0x%x rd_sz=%llu wr_sz=%llu rd_io=%llu wr_io=%llu\n",
__func__, t->bm, t->rd_sz, t->wr_sz, t->rd_io_sz, t->wr_io_sz);
switch (iomode) {
case IOMODE_READ:
if (t->bm & THRESHOLD_RD) {
dprintk("%s fsize %llu\n", __func__, fsize);
size_set = true;
if (fsize < t->rd_sz)
size = true;
}
if (t->bm & THRESHOLD_RD_IO) {
dprintk("%s nfsi->read_io %llu\n", __func__,
nfsi->read_io);
io_set = true;
if (nfsi->read_io < t->rd_io_sz)
io = true;
}
break;
case IOMODE_RW:
if (t->bm & THRESHOLD_WR) {
dprintk("%s fsize %llu\n", __func__, fsize);
size_set = true;
if (fsize < t->wr_sz)
size = true;
}
if (t->bm & THRESHOLD_WR_IO) {
dprintk("%s nfsi->write_io %llu\n", __func__,
nfsi->write_io);
io_set = true;
if (nfsi->write_io < t->wr_io_sz)
io = true;
}
break;
}
if (size_set && io_set) {
if (size && io)
ret = true;
} else if (size || io)
ret = true;
dprintk("<-- %s size %d io %d ret %d\n", __func__, size, io, ret);
return ret;
}
static bool pnfs_prepare_to_retry_layoutget(struct pnfs_layout_hdr *lo)
{
/*
* send layoutcommit as it can hold up layoutreturn due to lseg
* reference
*/
pnfs_layoutcommit_inode(lo->plh_inode, false);
return !wait_on_bit_action(&lo->plh_flags, NFS_LAYOUT_RETURN,
nfs_wait_bit_killable,
TASK_UNINTERRUPTIBLE);
}
static void pnfs_clear_first_layoutget(struct pnfs_layout_hdr *lo)
{
unsigned long *bitlock = &lo->plh_flags;
clear_bit_unlock(NFS_LAYOUT_FIRST_LAYOUTGET, bitlock);
smp_mb__after_atomic();
wake_up_bit(bitlock, NFS_LAYOUT_FIRST_LAYOUTGET);
}
/*
* Layout segment is retreived from the server if not cached.
* The appropriate layout segment is referenced and returned to the caller.
*/
struct pnfs_layout_segment *
pnfs_update_layout(struct inode *ino,
struct nfs_open_context *ctx,
loff_t pos,
u64 count,
enum pnfs_iomode iomode,
gfp_t gfp_flags)
{
struct pnfs_layout_range arg = {
.iomode = iomode,
.offset = pos,
.length = count,
};
unsigned pg_offset;
struct nfs_server *server = NFS_SERVER(ino);
struct nfs_client *clp = server->nfs_client;
struct pnfs_layout_hdr *lo;
struct pnfs_layout_segment *lseg = NULL;
bool first;
if (!pnfs_enabled_sb(NFS_SERVER(ino))) {
trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
PNFS_UPDATE_LAYOUT_NO_PNFS);
goto out;
}
if (iomode == IOMODE_READ && i_size_read(ino) == 0) {
trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
PNFS_UPDATE_LAYOUT_RD_ZEROLEN);
goto out;
}
if (pnfs_within_mdsthreshold(ctx, ino, iomode)) {
trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
PNFS_UPDATE_LAYOUT_MDSTHRESH);
goto out;
}
lookup_again:
first = false;
spin_lock(&ino->i_lock);
lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
if (lo == NULL) {
spin_unlock(&ino->i_lock);
trace_pnfs_update_layout(ino, pos, count, iomode, NULL,
PNFS_UPDATE_LAYOUT_NOMEM);
goto out;
}
/* Do we even need to bother with this? */
if (test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags)) {
trace_pnfs_update_layout(ino, pos, count, iomode, lo,
PNFS_UPDATE_LAYOUT_BULK_RECALL);
dprintk("%s matches recall, use MDS\n", __func__);
goto out_unlock;
}
/* if LAYOUTGET already failed once we don't try again */
if (pnfs_layout_io_test_failed(lo, iomode)) {
trace_pnfs_update_layout(ino, pos, count, iomode, lo,
PNFS_UPDATE_LAYOUT_IO_TEST_FAIL);
goto out_unlock;
}
first = list_empty(&lo->plh_segs);
if (first) {
/* The first layoutget for the file. Need to serialize per
* RFC 5661 Errata 3208.
*/
if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET,
&lo->plh_flags)) {
spin_unlock(&ino->i_lock);
wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET,
TASK_UNINTERRUPTIBLE);
pnfs_put_layout_hdr(lo);
goto lookup_again;
}
} else {
/* Check to see if the layout for the given range
* already exists
*/
lseg = pnfs_find_lseg(lo, &arg);
if (lseg) {
trace_pnfs_update_layout(ino, pos, count, iomode, lo,
PNFS_UPDATE_LAYOUT_FOUND_CACHED);
goto out_unlock;
}
}
/*
* Because we free lsegs before sending LAYOUTRETURN, we need to wait
* for LAYOUTRETURN even if first is true.
*/
if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags)) {
spin_unlock(&ino->i_lock);
dprintk("%s wait for layoutreturn\n", __func__);
if (pnfs_prepare_to_retry_layoutget(lo)) {
if (first)
pnfs_clear_first_layoutget(lo);
pnfs_put_layout_hdr(lo);
dprintk("%s retrying\n", __func__);
goto lookup_again;
}
trace_pnfs_update_layout(ino, pos, count, iomode, lo,
PNFS_UPDATE_LAYOUT_RETURN);
goto out_put_layout_hdr;
}
if (pnfs_layoutgets_blocked(lo)) {
trace_pnfs_update_layout(ino, pos, count, iomode, lo,
PNFS_UPDATE_LAYOUT_BLOCKED);
goto out_unlock;
}
atomic_inc(&lo->plh_outstanding);
spin_unlock(&ino->i_lock);
if (list_empty(&lo->plh_layouts)) {
/* The lo must be on the clp list if there is any
* chance of a CB_LAYOUTRECALL(FILE) coming in.
*/
spin_lock(&clp->cl_lock);
if (list_empty(&lo->plh_layouts))
list_add_tail(&lo->plh_layouts, &server->layouts);
spin_unlock(&clp->cl_lock);
}
pg_offset = arg.offset & ~PAGE_CACHE_MASK;
if (pg_offset) {
arg.offset -= pg_offset;
arg.length += pg_offset;
}
if (arg.length != NFS4_MAX_UINT64)
arg.length = PAGE_CACHE_ALIGN(arg.length);
lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
atomic_dec(&lo->plh_outstanding);
trace_pnfs_update_layout(ino, pos, count, iomode, lo,
PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET);
out_put_layout_hdr:
if (first)
pnfs_clear_first_layoutget(lo);
pnfs_put_layout_hdr(lo);
out:
dprintk("%s: inode %s/%llu pNFS layout segment %s for "
"(%s, offset: %llu, length: %llu)\n",
__func__, ino->i_sb->s_id,
(unsigned long long)NFS_FILEID(ino),
IS_ERR_OR_NULL(lseg) ? "not found" : "found",
iomode==IOMODE_RW ? "read/write" : "read-only",
(unsigned long long)pos,
(unsigned long long)count);
return lseg;
out_unlock:
spin_unlock(&ino->i_lock);
goto out_put_layout_hdr;
}
EXPORT_SYMBOL_GPL(pnfs_update_layout);
static bool
pnfs_sanity_check_layout_range(struct pnfs_layout_range *range)
{
switch (range->iomode) {
case IOMODE_READ:
case IOMODE_RW:
break;
default:
return false;
}
if (range->offset == NFS4_MAX_UINT64)
return false;
if (range->length == 0)
return false;
if (range->length != NFS4_MAX_UINT64 &&
range->length > NFS4_MAX_UINT64 - range->offset)
return false;
return true;
}
struct pnfs_layout_segment *
pnfs_layout_process(struct nfs4_layoutget *lgp)
{
struct pnfs_layout_hdr *lo = NFS_I(lgp->args.inode)->layout;
struct nfs4_layoutget_res *res = &lgp->res;
struct pnfs_layout_segment *lseg;
struct inode *ino = lo->plh_inode;
LIST_HEAD(free_me);
int status = -EINVAL;
if (!pnfs_sanity_check_layout_range(&res->range))
goto out;
/* Inject layout blob into I/O device driver */
lseg = NFS_SERVER(ino)->pnfs_curr_ld->alloc_lseg(lo, res, lgp->gfp_flags);
if (!lseg || IS_ERR(lseg)) {
if (!lseg)
status = -ENOMEM;
else
status = PTR_ERR(lseg);
dprintk("%s: Could not allocate layout: error %d\n",
__func__, status);
goto out;
}
init_lseg(lo, lseg);
lseg->pls_range = res->range;
spin_lock(&ino->i_lock);
if (pnfs_layoutgets_blocked(lo)) {
dprintk("%s forget reply due to state\n", __func__);
goto out_forget_reply;
}
if (nfs4_stateid_match_other(&lo->plh_stateid, &res->stateid)) {
/* existing state ID, make sure the sequence number matches. */
if (pnfs_layout_stateid_blocked(lo, &res->stateid)) {
dprintk("%s forget reply due to sequence\n", __func__);
status = -EAGAIN;
goto out_forget_reply;
}
pnfs_set_layout_stateid(lo, &res->stateid, false);
} else {
/*
* We got an entirely new state ID. Mark all segments for the
* inode invalid, and don't bother validating the stateid
* sequence number.
*/
pnfs_mark_matching_lsegs_invalid(lo, &free_me, NULL);
nfs4_stateid_copy(&lo->plh_stateid, &res->stateid);
lo->plh_barrier = be32_to_cpu(res->stateid.seqid);
}
clear_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
pnfs_get_lseg(lseg);
pnfs_layout_insert_lseg(lo, lseg, &free_me);
if (res->return_on_close)
set_bit(NFS_LSEG_ROC, &lseg->pls_flags);
spin_unlock(&ino->i_lock);
pnfs_free_lseg_list(&free_me);
return lseg;
out:
return ERR_PTR(status);
out_forget_reply:
spin_unlock(&ino->i_lock);
lseg->pls_layout = lo;
NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
goto out;
}
static void
pnfs_set_plh_return_iomode(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode)
{
if (lo->plh_return_iomode == iomode)
return;
if (lo->plh_return_iomode != 0)
iomode = IOMODE_ANY;
lo->plh_return_iomode = iomode;
}
int
pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
struct list_head *tmp_list,
const struct pnfs_layout_range *return_range)
{
struct pnfs_layout_segment *lseg, *next;
int remaining = 0;
dprintk("%s:Begin lo %p\n", __func__, lo);
if (list_empty(&lo->plh_segs))
return 0;
assert_spin_locked(&lo->plh_inode->i_lock);
list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
if (should_free_lseg(&lseg->pls_range, return_range)) {
dprintk("%s: marking lseg %p iomode %d "
"offset %llu length %llu\n", __func__,
lseg, lseg->pls_range.iomode,
lseg->pls_range.offset,
lseg->pls_range.length);
set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
pnfs_set_plh_return_iomode(lo, return_range->iomode);
if (!mark_lseg_invalid(lseg, tmp_list))
remaining++;
set_bit(NFS_LAYOUT_RETURN_REQUESTED,
&lo->plh_flags);
}
return remaining;
}
void pnfs_error_mark_layout_for_return(struct inode *inode,
struct pnfs_layout_segment *lseg)
{
struct pnfs_layout_hdr *lo = NFS_I(inode)->layout;
struct pnfs_layout_range range = {
.iomode = lseg->pls_range.iomode,
.offset = 0,
.length = NFS4_MAX_UINT64,
};
LIST_HEAD(free_me);
bool return_now = false;
spin_lock(&inode->i_lock);
pnfs_set_plh_return_iomode(lo, range.iomode);
/*
* mark all matching lsegs so that we are sure to have no live
* segments at hand when sending layoutreturn. See pnfs_put_lseg()
* for how it works.
*/
if (!pnfs_mark_matching_lsegs_return(lo, &free_me, &range)) {
nfs4_stateid stateid;
enum pnfs_iomode iomode = lo->plh_return_iomode;
nfs4_stateid_copy(&stateid, &lo->plh_stateid);
return_now = pnfs_prepare_layoutreturn(lo);
spin_unlock(&inode->i_lock);
if (return_now)
pnfs_send_layoutreturn(lo, &stateid, iomode, false);
} else {
spin_unlock(&inode->i_lock);
nfs_commit_inode(inode, 0);
}
pnfs_free_lseg_list(&free_me);
}
EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return);
void
pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
{
u64 rd_size = req->wb_bytes;
if (pgio->pg_lseg == NULL) {
if (pgio->pg_dreq == NULL)
rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
else
rd_size = nfs_dreq_bytes_left(pgio->pg_dreq);
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
req_offset(req),
rd_size,
IOMODE_READ,
GFP_KERNEL);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
pgio->pg_lseg = NULL;
return;
}
}
/* If no lseg, fall back to read through mds */
if (pgio->pg_lseg == NULL)
nfs_pageio_reset_read_mds(pgio);
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_read);
void
pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
struct nfs_page *req, u64 wb_size)
{
if (pgio->pg_lseg == NULL) {
pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
req->wb_context,
req_offset(req),
wb_size,
IOMODE_RW,
GFP_NOFS);
if (IS_ERR(pgio->pg_lseg)) {
pgio->pg_error = PTR_ERR(pgio->pg_lseg);
pgio->pg_lseg = NULL;
return;
}
}
/* If no lseg, fall back to write through mds */
if (pgio->pg_lseg == NULL)
nfs_pageio_reset_write_mds(pgio);
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write);
void
pnfs_generic_pg_cleanup(struct nfs_pageio_descriptor *desc)
{
if (desc->pg_lseg) {
pnfs_put_lseg(desc->pg_lseg);
desc->pg_lseg = NULL;
}
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_cleanup);
/*
* Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
* of bytes (maximum @req->wb_bytes) that can be coalesced.
*/
size_t
pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio,
struct nfs_page *prev, struct nfs_page *req)
{
unsigned int size;
pnfs: fix lockup caused by pnfs_generic_pg_test end_offset and req_offset both return u64 - avoid casting to u32 until it's needed, when it's less than the (u32) size returned by nfs_generic_pg_test. Also, fix the comments in pnfs_generic_pg_test. Running the cthon04 special tests caused this lockup in the "write/read at 2GB, 4GB edges" test when running against a file layout server: BUG: soft lockup - CPU#0 stuck for 22s! [bigfile2:823] Modules linked in: nfs_layout_nfsv41_files rpcsec_gss_krb5 nfsv4 nfs fscache ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_mangle ip6table_filter ip6_tables iptable_nat nf_nat_ipv4 nf_nat iptable_mangle ppdev crc32c_intel aesni_intel aes_x86_64 glue_helper lrw gf128mul ablk_helper cryptd serio_raw e1000 shpchp i2c_piix4 i2c_core parport_pc parport nfsd auth_rpcgss oid_registry exportfs nfs_acl lockd sunrpc btrfs xor zlib_deflate raid6_pq mptspi scsi_transport_spi mptscsih mptbase ata_generic floppy autofs4 irq event stamp: 205958 hardirqs last enabled at (205957): [<ffffffff814a62dc>] restore_args+0x0/0x30 hardirqs last disabled at (205958): [<ffffffff814ad96a>] apic_timer_interrupt+0x6a/0x80 softirqs last enabled at (205956): [<ffffffff8103ffb2>] __do_softirq+0x1ea/0x2ab softirqs last disabled at (205951): [<ffffffff8104026d>] irq_exit+0x44/0x9a CPU: 0 PID: 823 Comm: bigfile2 Not tainted 3.15.0-rc1-branch-pgio_plus+ #3 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/31/2013 task: ffff8800792ec480 ti: ffff880078c4e000 task.ti: ffff880078c4e000 RIP: 0010:[<ffffffffa02ce51f>] [<ffffffffa02ce51f>] nfs_page_group_unlock+0x3e/0x4b [nfs] RSP: 0018:ffff880078c4fab0 EFLAGS: 00000202 RAX: 0000000000000fff RBX: ffff88006bf83300 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff88006bf83300 RBP: ffff880078c4fab8 R08: 0000000000000001 R09: 0000000000000000 R10: ffffffff8249840c R11: 0000000000000000 R12: 0000000000000035 R13: ffff88007ffc72d8 R14: 0000000000000001 R15: 0000000000000000 FS: 00007f45f11b7740(0000) GS:ffff88007f200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3a8cb632d0 CR3: 000000007931c000 CR4: 00000000001407f0 Stack: ffff88006bf832c0 ffff880078c4fb00 ffffffffa02cec22 ffff880078c4fad8 00000fff810f9d99 ffff880078c4fca0 ffff88006bf832c0 ffff88006bf832c0 ffff880078c4fca0 ffff880078c4fd60 ffff880078c4fb28 ffffffffa02cee34 Call Trace: [<ffffffffa02cec22>] __nfs_pageio_add_request+0x298/0x34f [nfs] [<ffffffffa02cee34>] nfs_pageio_add_request+0x1f/0x42 [nfs] [<ffffffffa02d1722>] nfs_do_writepage+0x1b5/0x1e4 [nfs] [<ffffffffa02d1764>] nfs_writepages_callback+0x13/0x25 [nfs] [<ffffffffa02d1751>] ? nfs_do_writepage+0x1e4/0x1e4 [nfs] [<ffffffff810eb32d>] write_cache_pages+0x254/0x37f [<ffffffffa02d1751>] ? nfs_do_writepage+0x1e4/0x1e4 [nfs] [<ffffffff8149cf9e>] ? printk+0x54/0x56 [<ffffffff810eacca>] ? __set_page_dirty_nobuffers+0x22/0xe9 [<ffffffffa016d864>] ? put_rpccred+0x38/0x101 [sunrpc] [<ffffffffa02d1ae1>] nfs_writepages+0xb4/0xf8 [nfs] [<ffffffff810ec59c>] do_writepages+0x21/0x2f [<ffffffff810e36e8>] __filemap_fdatawrite_range+0x55/0x57 [<ffffffff810e374a>] filemap_write_and_wait_range+0x2d/0x5b [<ffffffffa030ba0a>] nfs4_file_fsync+0x3a/0x98 [nfsv4] [<ffffffff8114ee3c>] vfs_fsync_range+0x18/0x20 [<ffffffff810e40c2>] generic_file_aio_write+0xa7/0xbd [<ffffffffa02c5c6b>] nfs_file_write+0xf0/0x170 [nfs] [<ffffffff81129215>] do_sync_write+0x59/0x78 [<ffffffff8112956c>] vfs_write+0xab/0x107 [<ffffffff81129c8b>] SyS_write+0x49/0x7f [<ffffffff814acd12>] system_call_fastpath+0x16/0x1b Reported-by: Anna Schumaker <Anna.Schumaker@netapp.com> Signed-off-by: Weston Andros Adamson <dros@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2014-06-10 01:47:26 +04:00
u64 seg_end, req_start, seg_left;
size = nfs_generic_pg_test(pgio, prev, req);
if (!size)
return 0;
/*
pnfs: fix lockup caused by pnfs_generic_pg_test end_offset and req_offset both return u64 - avoid casting to u32 until it's needed, when it's less than the (u32) size returned by nfs_generic_pg_test. Also, fix the comments in pnfs_generic_pg_test. Running the cthon04 special tests caused this lockup in the "write/read at 2GB, 4GB edges" test when running against a file layout server: BUG: soft lockup - CPU#0 stuck for 22s! [bigfile2:823] Modules linked in: nfs_layout_nfsv41_files rpcsec_gss_krb5 nfsv4 nfs fscache ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_mangle ip6table_filter ip6_tables iptable_nat nf_nat_ipv4 nf_nat iptable_mangle ppdev crc32c_intel aesni_intel aes_x86_64 glue_helper lrw gf128mul ablk_helper cryptd serio_raw e1000 shpchp i2c_piix4 i2c_core parport_pc parport nfsd auth_rpcgss oid_registry exportfs nfs_acl lockd sunrpc btrfs xor zlib_deflate raid6_pq mptspi scsi_transport_spi mptscsih mptbase ata_generic floppy autofs4 irq event stamp: 205958 hardirqs last enabled at (205957): [<ffffffff814a62dc>] restore_args+0x0/0x30 hardirqs last disabled at (205958): [<ffffffff814ad96a>] apic_timer_interrupt+0x6a/0x80 softirqs last enabled at (205956): [<ffffffff8103ffb2>] __do_softirq+0x1ea/0x2ab softirqs last disabled at (205951): [<ffffffff8104026d>] irq_exit+0x44/0x9a CPU: 0 PID: 823 Comm: bigfile2 Not tainted 3.15.0-rc1-branch-pgio_plus+ #3 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/31/2013 task: ffff8800792ec480 ti: ffff880078c4e000 task.ti: ffff880078c4e000 RIP: 0010:[<ffffffffa02ce51f>] [<ffffffffa02ce51f>] nfs_page_group_unlock+0x3e/0x4b [nfs] RSP: 0018:ffff880078c4fab0 EFLAGS: 00000202 RAX: 0000000000000fff RBX: ffff88006bf83300 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff88006bf83300 RBP: ffff880078c4fab8 R08: 0000000000000001 R09: 0000000000000000 R10: ffffffff8249840c R11: 0000000000000000 R12: 0000000000000035 R13: ffff88007ffc72d8 R14: 0000000000000001 R15: 0000000000000000 FS: 00007f45f11b7740(0000) GS:ffff88007f200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3a8cb632d0 CR3: 000000007931c000 CR4: 00000000001407f0 Stack: ffff88006bf832c0 ffff880078c4fb00 ffffffffa02cec22 ffff880078c4fad8 00000fff810f9d99 ffff880078c4fca0 ffff88006bf832c0 ffff88006bf832c0 ffff880078c4fca0 ffff880078c4fd60 ffff880078c4fb28 ffffffffa02cee34 Call Trace: [<ffffffffa02cec22>] __nfs_pageio_add_request+0x298/0x34f [nfs] [<ffffffffa02cee34>] nfs_pageio_add_request+0x1f/0x42 [nfs] [<ffffffffa02d1722>] nfs_do_writepage+0x1b5/0x1e4 [nfs] [<ffffffffa02d1764>] nfs_writepages_callback+0x13/0x25 [nfs] [<ffffffffa02d1751>] ? nfs_do_writepage+0x1e4/0x1e4 [nfs] [<ffffffff810eb32d>] write_cache_pages+0x254/0x37f [<ffffffffa02d1751>] ? nfs_do_writepage+0x1e4/0x1e4 [nfs] [<ffffffff8149cf9e>] ? printk+0x54/0x56 [<ffffffff810eacca>] ? __set_page_dirty_nobuffers+0x22/0xe9 [<ffffffffa016d864>] ? put_rpccred+0x38/0x101 [sunrpc] [<ffffffffa02d1ae1>] nfs_writepages+0xb4/0xf8 [nfs] [<ffffffff810ec59c>] do_writepages+0x21/0x2f [<ffffffff810e36e8>] __filemap_fdatawrite_range+0x55/0x57 [<ffffffff810e374a>] filemap_write_and_wait_range+0x2d/0x5b [<ffffffffa030ba0a>] nfs4_file_fsync+0x3a/0x98 [nfsv4] [<ffffffff8114ee3c>] vfs_fsync_range+0x18/0x20 [<ffffffff810e40c2>] generic_file_aio_write+0xa7/0xbd [<ffffffffa02c5c6b>] nfs_file_write+0xf0/0x170 [nfs] [<ffffffff81129215>] do_sync_write+0x59/0x78 [<ffffffff8112956c>] vfs_write+0xab/0x107 [<ffffffff81129c8b>] SyS_write+0x49/0x7f [<ffffffff814acd12>] system_call_fastpath+0x16/0x1b Reported-by: Anna Schumaker <Anna.Schumaker@netapp.com> Signed-off-by: Weston Andros Adamson <dros@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2014-06-10 01:47:26 +04:00
* 'size' contains the number of bytes left in the current page (up
* to the original size asked for in @req->wb_bytes).
*
* Calculate how many bytes are left in the layout segment
* and if there are less bytes than 'size', return that instead.
*
* Please also note that 'end_offset' is actually the offset of the
* first byte that lies outside the pnfs_layout_range. FIXME?
*
*/
if (pgio->pg_lseg) {
pnfs: fix lockup caused by pnfs_generic_pg_test end_offset and req_offset both return u64 - avoid casting to u32 until it's needed, when it's less than the (u32) size returned by nfs_generic_pg_test. Also, fix the comments in pnfs_generic_pg_test. Running the cthon04 special tests caused this lockup in the "write/read at 2GB, 4GB edges" test when running against a file layout server: BUG: soft lockup - CPU#0 stuck for 22s! [bigfile2:823] Modules linked in: nfs_layout_nfsv41_files rpcsec_gss_krb5 nfsv4 nfs fscache ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_mangle ip6table_filter ip6_tables iptable_nat nf_nat_ipv4 nf_nat iptable_mangle ppdev crc32c_intel aesni_intel aes_x86_64 glue_helper lrw gf128mul ablk_helper cryptd serio_raw e1000 shpchp i2c_piix4 i2c_core parport_pc parport nfsd auth_rpcgss oid_registry exportfs nfs_acl lockd sunrpc btrfs xor zlib_deflate raid6_pq mptspi scsi_transport_spi mptscsih mptbase ata_generic floppy autofs4 irq event stamp: 205958 hardirqs last enabled at (205957): [<ffffffff814a62dc>] restore_args+0x0/0x30 hardirqs last disabled at (205958): [<ffffffff814ad96a>] apic_timer_interrupt+0x6a/0x80 softirqs last enabled at (205956): [<ffffffff8103ffb2>] __do_softirq+0x1ea/0x2ab softirqs last disabled at (205951): [<ffffffff8104026d>] irq_exit+0x44/0x9a CPU: 0 PID: 823 Comm: bigfile2 Not tainted 3.15.0-rc1-branch-pgio_plus+ #3 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/31/2013 task: ffff8800792ec480 ti: ffff880078c4e000 task.ti: ffff880078c4e000 RIP: 0010:[<ffffffffa02ce51f>] [<ffffffffa02ce51f>] nfs_page_group_unlock+0x3e/0x4b [nfs] RSP: 0018:ffff880078c4fab0 EFLAGS: 00000202 RAX: 0000000000000fff RBX: ffff88006bf83300 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff88006bf83300 RBP: ffff880078c4fab8 R08: 0000000000000001 R09: 0000000000000000 R10: ffffffff8249840c R11: 0000000000000000 R12: 0000000000000035 R13: ffff88007ffc72d8 R14: 0000000000000001 R15: 0000000000000000 FS: 00007f45f11b7740(0000) GS:ffff88007f200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3a8cb632d0 CR3: 000000007931c000 CR4: 00000000001407f0 Stack: ffff88006bf832c0 ffff880078c4fb00 ffffffffa02cec22 ffff880078c4fad8 00000fff810f9d99 ffff880078c4fca0 ffff88006bf832c0 ffff88006bf832c0 ffff880078c4fca0 ffff880078c4fd60 ffff880078c4fb28 ffffffffa02cee34 Call Trace: [<ffffffffa02cec22>] __nfs_pageio_add_request+0x298/0x34f [nfs] [<ffffffffa02cee34>] nfs_pageio_add_request+0x1f/0x42 [nfs] [<ffffffffa02d1722>] nfs_do_writepage+0x1b5/0x1e4 [nfs] [<ffffffffa02d1764>] nfs_writepages_callback+0x13/0x25 [nfs] [<ffffffffa02d1751>] ? nfs_do_writepage+0x1e4/0x1e4 [nfs] [<ffffffff810eb32d>] write_cache_pages+0x254/0x37f [<ffffffffa02d1751>] ? nfs_do_writepage+0x1e4/0x1e4 [nfs] [<ffffffff8149cf9e>] ? printk+0x54/0x56 [<ffffffff810eacca>] ? __set_page_dirty_nobuffers+0x22/0xe9 [<ffffffffa016d864>] ? put_rpccred+0x38/0x101 [sunrpc] [<ffffffffa02d1ae1>] nfs_writepages+0xb4/0xf8 [nfs] [<ffffffff810ec59c>] do_writepages+0x21/0x2f [<ffffffff810e36e8>] __filemap_fdatawrite_range+0x55/0x57 [<ffffffff810e374a>] filemap_write_and_wait_range+0x2d/0x5b [<ffffffffa030ba0a>] nfs4_file_fsync+0x3a/0x98 [nfsv4] [<ffffffff8114ee3c>] vfs_fsync_range+0x18/0x20 [<ffffffff810e40c2>] generic_file_aio_write+0xa7/0xbd [<ffffffffa02c5c6b>] nfs_file_write+0xf0/0x170 [nfs] [<ffffffff81129215>] do_sync_write+0x59/0x78 [<ffffffff8112956c>] vfs_write+0xab/0x107 [<ffffffff81129c8b>] SyS_write+0x49/0x7f [<ffffffff814acd12>] system_call_fastpath+0x16/0x1b Reported-by: Anna Schumaker <Anna.Schumaker@netapp.com> Signed-off-by: Weston Andros Adamson <dros@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2014-06-10 01:47:26 +04:00
seg_end = end_offset(pgio->pg_lseg->pls_range.offset,
pgio->pg_lseg->pls_range.length);
req_start = req_offset(req);
WARN_ON_ONCE(req_start >= seg_end);
pnfs: fix lockup caused by pnfs_generic_pg_test end_offset and req_offset both return u64 - avoid casting to u32 until it's needed, when it's less than the (u32) size returned by nfs_generic_pg_test. Also, fix the comments in pnfs_generic_pg_test. Running the cthon04 special tests caused this lockup in the "write/read at 2GB, 4GB edges" test when running against a file layout server: BUG: soft lockup - CPU#0 stuck for 22s! [bigfile2:823] Modules linked in: nfs_layout_nfsv41_files rpcsec_gss_krb5 nfsv4 nfs fscache ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_mangle ip6table_filter ip6_tables iptable_nat nf_nat_ipv4 nf_nat iptable_mangle ppdev crc32c_intel aesni_intel aes_x86_64 glue_helper lrw gf128mul ablk_helper cryptd serio_raw e1000 shpchp i2c_piix4 i2c_core parport_pc parport nfsd auth_rpcgss oid_registry exportfs nfs_acl lockd sunrpc btrfs xor zlib_deflate raid6_pq mptspi scsi_transport_spi mptscsih mptbase ata_generic floppy autofs4 irq event stamp: 205958 hardirqs last enabled at (205957): [<ffffffff814a62dc>] restore_args+0x0/0x30 hardirqs last disabled at (205958): [<ffffffff814ad96a>] apic_timer_interrupt+0x6a/0x80 softirqs last enabled at (205956): [<ffffffff8103ffb2>] __do_softirq+0x1ea/0x2ab softirqs last disabled at (205951): [<ffffffff8104026d>] irq_exit+0x44/0x9a CPU: 0 PID: 823 Comm: bigfile2 Not tainted 3.15.0-rc1-branch-pgio_plus+ #3 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/31/2013 task: ffff8800792ec480 ti: ffff880078c4e000 task.ti: ffff880078c4e000 RIP: 0010:[<ffffffffa02ce51f>] [<ffffffffa02ce51f>] nfs_page_group_unlock+0x3e/0x4b [nfs] RSP: 0018:ffff880078c4fab0 EFLAGS: 00000202 RAX: 0000000000000fff RBX: ffff88006bf83300 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff88006bf83300 RBP: ffff880078c4fab8 R08: 0000000000000001 R09: 0000000000000000 R10: ffffffff8249840c R11: 0000000000000000 R12: 0000000000000035 R13: ffff88007ffc72d8 R14: 0000000000000001 R15: 0000000000000000 FS: 00007f45f11b7740(0000) GS:ffff88007f200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3a8cb632d0 CR3: 000000007931c000 CR4: 00000000001407f0 Stack: ffff88006bf832c0 ffff880078c4fb00 ffffffffa02cec22 ffff880078c4fad8 00000fff810f9d99 ffff880078c4fca0 ffff88006bf832c0 ffff88006bf832c0 ffff880078c4fca0 ffff880078c4fd60 ffff880078c4fb28 ffffffffa02cee34 Call Trace: [<ffffffffa02cec22>] __nfs_pageio_add_request+0x298/0x34f [nfs] [<ffffffffa02cee34>] nfs_pageio_add_request+0x1f/0x42 [nfs] [<ffffffffa02d1722>] nfs_do_writepage+0x1b5/0x1e4 [nfs] [<ffffffffa02d1764>] nfs_writepages_callback+0x13/0x25 [nfs] [<ffffffffa02d1751>] ? nfs_do_writepage+0x1e4/0x1e4 [nfs] [<ffffffff810eb32d>] write_cache_pages+0x254/0x37f [<ffffffffa02d1751>] ? nfs_do_writepage+0x1e4/0x1e4 [nfs] [<ffffffff8149cf9e>] ? printk+0x54/0x56 [<ffffffff810eacca>] ? __set_page_dirty_nobuffers+0x22/0xe9 [<ffffffffa016d864>] ? put_rpccred+0x38/0x101 [sunrpc] [<ffffffffa02d1ae1>] nfs_writepages+0xb4/0xf8 [nfs] [<ffffffff810ec59c>] do_writepages+0x21/0x2f [<ffffffff810e36e8>] __filemap_fdatawrite_range+0x55/0x57 [<ffffffff810e374a>] filemap_write_and_wait_range+0x2d/0x5b [<ffffffffa030ba0a>] nfs4_file_fsync+0x3a/0x98 [nfsv4] [<ffffffff8114ee3c>] vfs_fsync_range+0x18/0x20 [<ffffffff810e40c2>] generic_file_aio_write+0xa7/0xbd [<ffffffffa02c5c6b>] nfs_file_write+0xf0/0x170 [nfs] [<ffffffff81129215>] do_sync_write+0x59/0x78 [<ffffffff8112956c>] vfs_write+0xab/0x107 [<ffffffff81129c8b>] SyS_write+0x49/0x7f [<ffffffff814acd12>] system_call_fastpath+0x16/0x1b Reported-by: Anna Schumaker <Anna.Schumaker@netapp.com> Signed-off-by: Weston Andros Adamson <dros@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2014-06-10 01:47:26 +04:00
/* start of request is past the last byte of this segment */
if (req_start >= seg_end) {
/* reference the new lseg */
if (pgio->pg_ops->pg_cleanup)
pgio->pg_ops->pg_cleanup(pgio);
if (pgio->pg_ops->pg_init)
pgio->pg_ops->pg_init(pgio, req);
return 0;
}
pnfs: fix lockup caused by pnfs_generic_pg_test end_offset and req_offset both return u64 - avoid casting to u32 until it's needed, when it's less than the (u32) size returned by nfs_generic_pg_test. Also, fix the comments in pnfs_generic_pg_test. Running the cthon04 special tests caused this lockup in the "write/read at 2GB, 4GB edges" test when running against a file layout server: BUG: soft lockup - CPU#0 stuck for 22s! [bigfile2:823] Modules linked in: nfs_layout_nfsv41_files rpcsec_gss_krb5 nfsv4 nfs fscache ip6t_REJECT nf_conntrack_ipv6 nf_defrag_ipv6 ip6table_mangle ip6table_filter ip6_tables iptable_nat nf_nat_ipv4 nf_nat iptable_mangle ppdev crc32c_intel aesni_intel aes_x86_64 glue_helper lrw gf128mul ablk_helper cryptd serio_raw e1000 shpchp i2c_piix4 i2c_core parport_pc parport nfsd auth_rpcgss oid_registry exportfs nfs_acl lockd sunrpc btrfs xor zlib_deflate raid6_pq mptspi scsi_transport_spi mptscsih mptbase ata_generic floppy autofs4 irq event stamp: 205958 hardirqs last enabled at (205957): [<ffffffff814a62dc>] restore_args+0x0/0x30 hardirqs last disabled at (205958): [<ffffffff814ad96a>] apic_timer_interrupt+0x6a/0x80 softirqs last enabled at (205956): [<ffffffff8103ffb2>] __do_softirq+0x1ea/0x2ab softirqs last disabled at (205951): [<ffffffff8104026d>] irq_exit+0x44/0x9a CPU: 0 PID: 823 Comm: bigfile2 Not tainted 3.15.0-rc1-branch-pgio_plus+ #3 Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/31/2013 task: ffff8800792ec480 ti: ffff880078c4e000 task.ti: ffff880078c4e000 RIP: 0010:[<ffffffffa02ce51f>] [<ffffffffa02ce51f>] nfs_page_group_unlock+0x3e/0x4b [nfs] RSP: 0018:ffff880078c4fab0 EFLAGS: 00000202 RAX: 0000000000000fff RBX: ffff88006bf83300 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff88006bf83300 RBP: ffff880078c4fab8 R08: 0000000000000001 R09: 0000000000000000 R10: ffffffff8249840c R11: 0000000000000000 R12: 0000000000000035 R13: ffff88007ffc72d8 R14: 0000000000000001 R15: 0000000000000000 FS: 00007f45f11b7740(0000) GS:ffff88007f200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007f3a8cb632d0 CR3: 000000007931c000 CR4: 00000000001407f0 Stack: ffff88006bf832c0 ffff880078c4fb00 ffffffffa02cec22 ffff880078c4fad8 00000fff810f9d99 ffff880078c4fca0 ffff88006bf832c0 ffff88006bf832c0 ffff880078c4fca0 ffff880078c4fd60 ffff880078c4fb28 ffffffffa02cee34 Call Trace: [<ffffffffa02cec22>] __nfs_pageio_add_request+0x298/0x34f [nfs] [<ffffffffa02cee34>] nfs_pageio_add_request+0x1f/0x42 [nfs] [<ffffffffa02d1722>] nfs_do_writepage+0x1b5/0x1e4 [nfs] [<ffffffffa02d1764>] nfs_writepages_callback+0x13/0x25 [nfs] [<ffffffffa02d1751>] ? nfs_do_writepage+0x1e4/0x1e4 [nfs] [<ffffffff810eb32d>] write_cache_pages+0x254/0x37f [<ffffffffa02d1751>] ? nfs_do_writepage+0x1e4/0x1e4 [nfs] [<ffffffff8149cf9e>] ? printk+0x54/0x56 [<ffffffff810eacca>] ? __set_page_dirty_nobuffers+0x22/0xe9 [<ffffffffa016d864>] ? put_rpccred+0x38/0x101 [sunrpc] [<ffffffffa02d1ae1>] nfs_writepages+0xb4/0xf8 [nfs] [<ffffffff810ec59c>] do_writepages+0x21/0x2f [<ffffffff810e36e8>] __filemap_fdatawrite_range+0x55/0x57 [<ffffffff810e374a>] filemap_write_and_wait_range+0x2d/0x5b [<ffffffffa030ba0a>] nfs4_file_fsync+0x3a/0x98 [nfsv4] [<ffffffff8114ee3c>] vfs_fsync_range+0x18/0x20 [<ffffffff810e40c2>] generic_file_aio_write+0xa7/0xbd [<ffffffffa02c5c6b>] nfs_file_write+0xf0/0x170 [nfs] [<ffffffff81129215>] do_sync_write+0x59/0x78 [<ffffffff8112956c>] vfs_write+0xab/0x107 [<ffffffff81129c8b>] SyS_write+0x49/0x7f [<ffffffff814acd12>] system_call_fastpath+0x16/0x1b Reported-by: Anna Schumaker <Anna.Schumaker@netapp.com> Signed-off-by: Weston Andros Adamson <dros@primarydata.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2014-06-10 01:47:26 +04:00
/* adjust 'size' iff there are fewer bytes left in the
* segment than what nfs_generic_pg_test returned */
seg_left = seg_end - req_start;
if (seg_left < size)
size = (unsigned int)seg_left;
}
return size;
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_test);
int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *hdr)
{
struct nfs_pageio_descriptor pgio;
/* Resend all requests through the MDS */
nfs_pageio_init_write(&pgio, hdr->inode, FLUSH_STABLE, true,
hdr->completion_ops);
set_bit(NFS_CONTEXT_RESEND_WRITES, &hdr->args.context->flags);
return nfs_pageio_resend(&pgio, hdr);
}
EXPORT_SYMBOL_GPL(pnfs_write_done_resend_to_mds);
static void pnfs_ld_handle_write_error(struct nfs_pgio_header *hdr)
{
dprintk("pnfs write error = %d\n", hdr->pnfs_error);
if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags &
PNFS_LAYOUTRET_ON_ERROR) {
pnfs_return_layout(hdr->inode);
}
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
hdr->task.tk_status = pnfs_write_done_resend_to_mds(hdr);
}
/*
* Called by non rpc-based layout drivers
*/
void pnfs_ld_write_done(struct nfs_pgio_header *hdr)
{
NFSv4.1/pnfs: Retry through MDS when getting bad length of data If non rpc-based layout driver return bad length of data, nfs retries by calling rpc_restart_call_prepare() that cause an NULL reference panic. This patch lets nfs retry through MDS for non rpc-based layout driver return bad length of data. [13034.883329] BUG: unable to handle kernel NULL pointer dereference at (null) [13034.884902] IP: [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.886558] PGD 0 [13034.888126] Oops: 0000 [#1] KASAN [13034.889710] Modules linked in: blocklayoutdriver(OE) nfsv4(OE) nfs(OE) fscache(E) nfsd(OE) xfs libcrc32c coretemp btrfs crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel ppdev vmw_balloon auth_rpcgss shpchp nfs_acl lockd vmw_vmci parport_pc xor raid6_pq grace parport sunrpc i2c_piix4 vmwgfx drm_kms_helper ttm drm mptspi e1000 serio_raw scsi_transport_spi mptscsih mptbase ata_generic pata_acpi [last unloaded: fscache] [13034.898260] CPU: 0 PID: 10112 Comm: kworker/0:1 Tainted: G OE 4.3.0-rc5+ #279 [13034.899932] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015 [13034.903342] Workqueue: events bl_read_cleanup [blocklayoutdriver] [13034.905059] task: ffff88006a9148c0 ti: ffff880035e90000 task.ti: ffff880035e90000 [13034.906827] RIP: 0010:[<ffffffffa00db372>] [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.910522] RSP: 0018:ffff880035e97b58 EFLAGS: 00010282 [13034.912378] RAX: fffffbfff04a5a94 RBX: ffff880068fe4858 RCX: 0000000000000003 [13034.914339] RDX: dffffc0000000000 RSI: 0000000000000003 RDI: 0000000000000282 [13034.916236] RBP: ffff880035e97b68 R08: 0000000000000001 R09: 0000000000000001 [13034.918229] R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000 [13034.920007] R13: ffff880068fe4858 R14: ffff880068fe4a60 R15: 0000000000001000 [13034.921845] FS: 0000000000000000(0000) GS:ffffffff82247000(0000) knlGS:0000000000000000 [13034.923645] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [13034.925525] CR2: 0000000000000000 CR3: 00000000063dd000 CR4: 00000000001406f0 [13034.932808] Stack: [13034.934813] ffff880068fe4780 0000000000001000 ffff880035e97ba8 ffffffffa08800d2 [13034.936675] ffffffffa088029d ffff880068fe4780 ffff880068fe4858 ffffffffa089c0a0 [13034.938593] ffff880068fe47e0 ffff88005d59faf0 ffff880035e97be0 ffffffffa087e08f [13034.940454] Call Trace: [13034.942388] [<ffffffffa08800d2>] nfs_readpage_result+0x112/0x200 [nfs] [13034.944317] [<ffffffffa088029d>] ? nfs_readpage_done+0xdd/0x160 [nfs] [13034.946267] [<ffffffffa087e08f>] nfs_pgio_result+0x9f/0x120 [nfs] [13034.948166] [<ffffffffa09266cc>] pnfs_ld_read_done+0x7c/0x1e0 [nfsv4] [13034.950247] [<ffffffffa03b07ee>] bl_read_cleanup+0x2e/0x60 [blocklayoutdriver] [13034.952156] [<ffffffff810ebf62>] process_one_work+0x412/0x870 [13034.954102] [<ffffffff810ebe84>] ? process_one_work+0x334/0x870 [13034.955949] [<ffffffff810ebb50>] ? queue_delayed_work_on+0x40/0x40 [13034.957985] [<ffffffff810ec441>] worker_thread+0x81/0x6a0 [13034.959817] [<ffffffff810ec3c0>] ? process_one_work+0x870/0x870 [13034.961785] [<ffffffff810f43bd>] kthread+0x17d/0x1a0 [13034.963544] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.965479] [<ffffffff81100428>] ? finish_task_switch+0x88/0x220 [13034.967223] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.968929] [<ffffffff81b6ae5f>] ret_from_fork+0x3f/0x70 [13034.970534] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.972176] Code: c7 43 50 40 84 0d a0 e8 3d fe 1c e1 48 8d 7b 58 c7 83 e4 00 00 00 00 00 00 00 e8 ca fe 1c e1 4c 8b 63 58 4c 89 e7 e8 be fe 1c e1 <49> 83 3c 24 00 74 12 48 c7 43 50 f0 a2 0e a0 b8 01 00 00 00 5b [13034.977148] RIP [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.978780] RSP <ffff880035e97b58> [13034.980399] CR2: 0000000000000000 Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2015-10-16 12:23:29 +03:00
if (likely(!hdr->pnfs_error)) {
pnfs_set_layoutcommit(hdr->inode, hdr->lseg,
hdr->mds_offset + hdr->res.count);
hdr->mds_ops->rpc_call_done(&hdr->task, hdr);
NFSv4.1/pnfs: Retry through MDS when getting bad length of data If non rpc-based layout driver return bad length of data, nfs retries by calling rpc_restart_call_prepare() that cause an NULL reference panic. This patch lets nfs retry through MDS for non rpc-based layout driver return bad length of data. [13034.883329] BUG: unable to handle kernel NULL pointer dereference at (null) [13034.884902] IP: [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.886558] PGD 0 [13034.888126] Oops: 0000 [#1] KASAN [13034.889710] Modules linked in: blocklayoutdriver(OE) nfsv4(OE) nfs(OE) fscache(E) nfsd(OE) xfs libcrc32c coretemp btrfs crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel ppdev vmw_balloon auth_rpcgss shpchp nfs_acl lockd vmw_vmci parport_pc xor raid6_pq grace parport sunrpc i2c_piix4 vmwgfx drm_kms_helper ttm drm mptspi e1000 serio_raw scsi_transport_spi mptscsih mptbase ata_generic pata_acpi [last unloaded: fscache] [13034.898260] CPU: 0 PID: 10112 Comm: kworker/0:1 Tainted: G OE 4.3.0-rc5+ #279 [13034.899932] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015 [13034.903342] Workqueue: events bl_read_cleanup [blocklayoutdriver] [13034.905059] task: ffff88006a9148c0 ti: ffff880035e90000 task.ti: ffff880035e90000 [13034.906827] RIP: 0010:[<ffffffffa00db372>] [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.910522] RSP: 0018:ffff880035e97b58 EFLAGS: 00010282 [13034.912378] RAX: fffffbfff04a5a94 RBX: ffff880068fe4858 RCX: 0000000000000003 [13034.914339] RDX: dffffc0000000000 RSI: 0000000000000003 RDI: 0000000000000282 [13034.916236] RBP: ffff880035e97b68 R08: 0000000000000001 R09: 0000000000000001 [13034.918229] R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000 [13034.920007] R13: ffff880068fe4858 R14: ffff880068fe4a60 R15: 0000000000001000 [13034.921845] FS: 0000000000000000(0000) GS:ffffffff82247000(0000) knlGS:0000000000000000 [13034.923645] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [13034.925525] CR2: 0000000000000000 CR3: 00000000063dd000 CR4: 00000000001406f0 [13034.932808] Stack: [13034.934813] ffff880068fe4780 0000000000001000 ffff880035e97ba8 ffffffffa08800d2 [13034.936675] ffffffffa088029d ffff880068fe4780 ffff880068fe4858 ffffffffa089c0a0 [13034.938593] ffff880068fe47e0 ffff88005d59faf0 ffff880035e97be0 ffffffffa087e08f [13034.940454] Call Trace: [13034.942388] [<ffffffffa08800d2>] nfs_readpage_result+0x112/0x200 [nfs] [13034.944317] [<ffffffffa088029d>] ? nfs_readpage_done+0xdd/0x160 [nfs] [13034.946267] [<ffffffffa087e08f>] nfs_pgio_result+0x9f/0x120 [nfs] [13034.948166] [<ffffffffa09266cc>] pnfs_ld_read_done+0x7c/0x1e0 [nfsv4] [13034.950247] [<ffffffffa03b07ee>] bl_read_cleanup+0x2e/0x60 [blocklayoutdriver] [13034.952156] [<ffffffff810ebf62>] process_one_work+0x412/0x870 [13034.954102] [<ffffffff810ebe84>] ? process_one_work+0x334/0x870 [13034.955949] [<ffffffff810ebb50>] ? queue_delayed_work_on+0x40/0x40 [13034.957985] [<ffffffff810ec441>] worker_thread+0x81/0x6a0 [13034.959817] [<ffffffff810ec3c0>] ? process_one_work+0x870/0x870 [13034.961785] [<ffffffff810f43bd>] kthread+0x17d/0x1a0 [13034.963544] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.965479] [<ffffffff81100428>] ? finish_task_switch+0x88/0x220 [13034.967223] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.968929] [<ffffffff81b6ae5f>] ret_from_fork+0x3f/0x70 [13034.970534] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.972176] Code: c7 43 50 40 84 0d a0 e8 3d fe 1c e1 48 8d 7b 58 c7 83 e4 00 00 00 00 00 00 00 e8 ca fe 1c e1 4c 8b 63 58 4c 89 e7 e8 be fe 1c e1 <49> 83 3c 24 00 74 12 48 c7 43 50 f0 a2 0e a0 b8 01 00 00 00 5b [13034.977148] RIP [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.978780] RSP <ffff880035e97b58> [13034.980399] CR2: 0000000000000000 Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2015-10-16 12:23:29 +03:00
}
trace_nfs4_pnfs_write(hdr, hdr->pnfs_error);
if (unlikely(hdr->pnfs_error))
pnfs_ld_handle_write_error(hdr);
hdr->mds_ops->rpc_release(hdr);
}
EXPORT_SYMBOL_GPL(pnfs_ld_write_done);
static void
pnfs_write_through_mds(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr)
{
struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
list_splice_tail_init(&hdr->pages, &mirror->pg_list);
nfs_pageio_reset_write_mds(desc);
mirror->pg_recoalesce = 1;
}
nfs_pgio_data_destroy(hdr);
hdr->release(hdr);
}
static enum pnfs_try_status
pnfs_try_to_write_data(struct nfs_pgio_header *hdr,
const struct rpc_call_ops *call_ops,
struct pnfs_layout_segment *lseg,
int how)
{
struct inode *inode = hdr->inode;
enum pnfs_try_status trypnfs;
struct nfs_server *nfss = NFS_SERVER(inode);
hdr->mds_ops = call_ops;
dprintk("%s: Writing ino:%lu %u@%llu (how %d)\n", __func__,
inode->i_ino, hdr->args.count, hdr->args.offset, how);
trypnfs = nfss->pnfs_curr_ld->write_pagelist(hdr, how);
if (trypnfs != PNFS_NOT_ATTEMPTED)
nfs_inc_stats(inode, NFSIOS_PNFS_WRITE);
dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs);
return trypnfs;
}
static void
pnfs_do_write(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr, int how)
{
const struct rpc_call_ops *call_ops = desc->pg_rpc_callops;
struct pnfs_layout_segment *lseg = desc->pg_lseg;
enum pnfs_try_status trypnfs;
trypnfs = pnfs_try_to_write_data(hdr, call_ops, lseg, how);
if (trypnfs == PNFS_NOT_ATTEMPTED)
pnfs_write_through_mds(desc, hdr);
}
static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
{
pnfs_put_lseg(hdr->lseg);
nfs_pgio_header_free(hdr);
}
int
pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
{
struct nfs_pgio_header *hdr;
int ret;
hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
if (!hdr) {
desc->pg_error = -ENOMEM;
return desc->pg_error;
}
nfs_pgheader_init(desc, hdr, pnfs_writehdr_free);
hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
ret = nfs_generic_pgio(desc, hdr);
if (!ret)
pnfs_do_write(desc, hdr, desc->pg_ioflags);
return ret;
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_writepages);
int pnfs_read_done_resend_to_mds(struct nfs_pgio_header *hdr)
{
struct nfs_pageio_descriptor pgio;
/* Resend all requests through the MDS */
nfs_pageio_init_read(&pgio, hdr->inode, true, hdr->completion_ops);
return nfs_pageio_resend(&pgio, hdr);
}
EXPORT_SYMBOL_GPL(pnfs_read_done_resend_to_mds);
static void pnfs_ld_handle_read_error(struct nfs_pgio_header *hdr)
{
dprintk("pnfs read error = %d\n", hdr->pnfs_error);
if (NFS_SERVER(hdr->inode)->pnfs_curr_ld->flags &
PNFS_LAYOUTRET_ON_ERROR) {
pnfs_return_layout(hdr->inode);
}
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags))
hdr->task.tk_status = pnfs_read_done_resend_to_mds(hdr);
}
/*
* Called by non rpc-based layout drivers
*/
void pnfs_ld_read_done(struct nfs_pgio_header *hdr)
{
if (likely(!hdr->pnfs_error)) {
__nfs4_read_done_cb(hdr);
hdr->mds_ops->rpc_call_done(&hdr->task, hdr);
NFSv4.1/pnfs: Retry through MDS when getting bad length of data If non rpc-based layout driver return bad length of data, nfs retries by calling rpc_restart_call_prepare() that cause an NULL reference panic. This patch lets nfs retry through MDS for non rpc-based layout driver return bad length of data. [13034.883329] BUG: unable to handle kernel NULL pointer dereference at (null) [13034.884902] IP: [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.886558] PGD 0 [13034.888126] Oops: 0000 [#1] KASAN [13034.889710] Modules linked in: blocklayoutdriver(OE) nfsv4(OE) nfs(OE) fscache(E) nfsd(OE) xfs libcrc32c coretemp btrfs crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel ppdev vmw_balloon auth_rpcgss shpchp nfs_acl lockd vmw_vmci parport_pc xor raid6_pq grace parport sunrpc i2c_piix4 vmwgfx drm_kms_helper ttm drm mptspi e1000 serio_raw scsi_transport_spi mptscsih mptbase ata_generic pata_acpi [last unloaded: fscache] [13034.898260] CPU: 0 PID: 10112 Comm: kworker/0:1 Tainted: G OE 4.3.0-rc5+ #279 [13034.899932] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 07/02/2015 [13034.903342] Workqueue: events bl_read_cleanup [blocklayoutdriver] [13034.905059] task: ffff88006a9148c0 ti: ffff880035e90000 task.ti: ffff880035e90000 [13034.906827] RIP: 0010:[<ffffffffa00db372>] [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.910522] RSP: 0018:ffff880035e97b58 EFLAGS: 00010282 [13034.912378] RAX: fffffbfff04a5a94 RBX: ffff880068fe4858 RCX: 0000000000000003 [13034.914339] RDX: dffffc0000000000 RSI: 0000000000000003 RDI: 0000000000000282 [13034.916236] RBP: ffff880035e97b68 R08: 0000000000000001 R09: 0000000000000001 [13034.918229] R10: 0000000000000000 R11: 0000000000000001 R12: 0000000000000000 [13034.920007] R13: ffff880068fe4858 R14: ffff880068fe4a60 R15: 0000000000001000 [13034.921845] FS: 0000000000000000(0000) GS:ffffffff82247000(0000) knlGS:0000000000000000 [13034.923645] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [13034.925525] CR2: 0000000000000000 CR3: 00000000063dd000 CR4: 00000000001406f0 [13034.932808] Stack: [13034.934813] ffff880068fe4780 0000000000001000 ffff880035e97ba8 ffffffffa08800d2 [13034.936675] ffffffffa088029d ffff880068fe4780 ffff880068fe4858 ffffffffa089c0a0 [13034.938593] ffff880068fe47e0 ffff88005d59faf0 ffff880035e97be0 ffffffffa087e08f [13034.940454] Call Trace: [13034.942388] [<ffffffffa08800d2>] nfs_readpage_result+0x112/0x200 [nfs] [13034.944317] [<ffffffffa088029d>] ? nfs_readpage_done+0xdd/0x160 [nfs] [13034.946267] [<ffffffffa087e08f>] nfs_pgio_result+0x9f/0x120 [nfs] [13034.948166] [<ffffffffa09266cc>] pnfs_ld_read_done+0x7c/0x1e0 [nfsv4] [13034.950247] [<ffffffffa03b07ee>] bl_read_cleanup+0x2e/0x60 [blocklayoutdriver] [13034.952156] [<ffffffff810ebf62>] process_one_work+0x412/0x870 [13034.954102] [<ffffffff810ebe84>] ? process_one_work+0x334/0x870 [13034.955949] [<ffffffff810ebb50>] ? queue_delayed_work_on+0x40/0x40 [13034.957985] [<ffffffff810ec441>] worker_thread+0x81/0x6a0 [13034.959817] [<ffffffff810ec3c0>] ? process_one_work+0x870/0x870 [13034.961785] [<ffffffff810f43bd>] kthread+0x17d/0x1a0 [13034.963544] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.965479] [<ffffffff81100428>] ? finish_task_switch+0x88/0x220 [13034.967223] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.968929] [<ffffffff81b6ae5f>] ret_from_fork+0x3f/0x70 [13034.970534] [<ffffffff810f4240>] ? kthread_create_on_node+0x330/0x330 [13034.972176] Code: c7 43 50 40 84 0d a0 e8 3d fe 1c e1 48 8d 7b 58 c7 83 e4 00 00 00 00 00 00 00 e8 ca fe 1c e1 4c 8b 63 58 4c 89 e7 e8 be fe 1c e1 <49> 83 3c 24 00 74 12 48 c7 43 50 f0 a2 0e a0 b8 01 00 00 00 5b [13034.977148] RIP [<ffffffffa00db372>] rpc_restart_call_prepare+0x62/0x90 [sunrpc] [13034.978780] RSP <ffff880035e97b58> [13034.980399] CR2: 0000000000000000 Signed-off-by: Kinglong Mee <kinglongmee@gmail.com> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
2015-10-16 12:23:29 +03:00
}
trace_nfs4_pnfs_read(hdr, hdr->pnfs_error);
if (unlikely(hdr->pnfs_error))
pnfs_ld_handle_read_error(hdr);
hdr->mds_ops->rpc_release(hdr);
}
EXPORT_SYMBOL_GPL(pnfs_ld_read_done);
static void
pnfs_read_through_mds(struct nfs_pageio_descriptor *desc,
struct nfs_pgio_header *hdr)
{
struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
list_splice_tail_init(&hdr->pages, &mirror->pg_list);
nfs_pageio_reset_read_mds(desc);
mirror->pg_recoalesce = 1;
}
nfs_pgio_data_destroy(hdr);
hdr->release(hdr);
}
/*
* Call the appropriate parallel I/O subsystem read function.
*/
static enum pnfs_try_status
pnfs_try_to_read_data(struct nfs_pgio_header *hdr,
const struct rpc_call_ops *call_ops,
struct pnfs_layout_segment *lseg)
{
struct inode *inode = hdr->inode;
struct nfs_server *nfss = NFS_SERVER(inode);
enum pnfs_try_status trypnfs;
hdr->mds_ops = call_ops;
dprintk("%s: Reading ino:%lu %u@%llu\n",
__func__, inode->i_ino, hdr->args.count, hdr->args.offset);
trypnfs = nfss->pnfs_curr_ld->read_pagelist(hdr);
if (trypnfs != PNFS_NOT_ATTEMPTED)
nfs_inc_stats(inode, NFSIOS_PNFS_READ);
dprintk("%s End (trypnfs:%d)\n", __func__, trypnfs);
return trypnfs;
}
/* Resend all requests through pnfs. */
int pnfs_read_resend_pnfs(struct nfs_pgio_header *hdr)
{
struct nfs_pageio_descriptor pgio;
nfs_pageio_init_read(&pgio, hdr->inode, false, hdr->completion_ops);
return nfs_pageio_resend(&pgio, hdr);
}
EXPORT_SYMBOL_GPL(pnfs_read_resend_pnfs);
static void
pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr)
{
const struct rpc_call_ops *call_ops = desc->pg_rpc_callops;
struct pnfs_layout_segment *lseg = desc->pg_lseg;
enum pnfs_try_status trypnfs;
int err = 0;
trypnfs = pnfs_try_to_read_data(hdr, call_ops, lseg);
if (trypnfs == PNFS_TRY_AGAIN)
err = pnfs_read_resend_pnfs(hdr);
if (trypnfs == PNFS_NOT_ATTEMPTED || err)
pnfs_read_through_mds(desc, hdr);
}
static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
{
pnfs_put_lseg(hdr->lseg);
nfs_pgio_header_free(hdr);
}
int
pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
{
struct nfs_pgio_header *hdr;
int ret;
hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
if (!hdr) {
desc->pg_error = -ENOMEM;
return desc->pg_error;
}
nfs_pgheader_init(desc, hdr, pnfs_readhdr_free);
hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
ret = nfs_generic_pgio(desc, hdr);
if (!ret)
pnfs_do_read(desc, hdr);
return ret;
}
EXPORT_SYMBOL_GPL(pnfs_generic_pg_readpages);
static void pnfs_clear_layoutcommitting(struct inode *inode)
{
unsigned long *bitlock = &NFS_I(inode)->flags;
clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
smp_mb__after_atomic();
wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
}
/*
* There can be multiple RW segments.
*/
static void pnfs_list_write_lseg(struct inode *inode, struct list_head *listp)
{
struct pnfs_layout_segment *lseg;
list_for_each_entry(lseg, &NFS_I(inode)->layout->plh_segs, pls_list) {
if (lseg->pls_range.iomode == IOMODE_RW &&
test_and_clear_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags))
list_add(&lseg->pls_lc_list, listp);
}
}
static void pnfs_list_write_lseg_done(struct inode *inode, struct list_head *listp)
{
struct pnfs_layout_segment *lseg, *tmp;
/* Matched by references in pnfs_set_layoutcommit */
list_for_each_entry_safe(lseg, tmp, listp, pls_lc_list) {
list_del_init(&lseg->pls_lc_list);
pnfs_put_lseg(lseg);
}
pnfs_clear_layoutcommitting(inode);
}
void pnfs_set_lo_fail(struct pnfs_layout_segment *lseg)
{
pnfs_layout_io_set_failed(lseg->pls_layout, lseg->pls_range.iomode);
}
EXPORT_SYMBOL_GPL(pnfs_set_lo_fail);
void
pnfs_set_layoutcommit(struct inode *inode, struct pnfs_layout_segment *lseg,
loff_t end_pos)
{
struct nfs_inode *nfsi = NFS_I(inode);
bool mark_as_dirty = false;
spin_lock(&inode->i_lock);
if (!test_and_set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags)) {
nfsi->layout->plh_lwb = end_pos;
mark_as_dirty = true;
dprintk("%s: Set layoutcommit for inode %lu ",
__func__, inode->i_ino);
} else if (end_pos > nfsi->layout->plh_lwb)
nfsi->layout->plh_lwb = end_pos;
if (!test_and_set_bit(NFS_LSEG_LAYOUTCOMMIT, &lseg->pls_flags)) {
/* references matched in nfs4_layoutcommit_release */
pnfs_get_lseg(lseg);
}
spin_unlock(&inode->i_lock);
dprintk("%s: lseg %p end_pos %llu\n",
__func__, lseg, nfsi->layout->plh_lwb);
/* if pnfs_layoutcommit_inode() runs between inode locks, the next one
* will be a noop because NFS_INO_LAYOUTCOMMIT will not be set */
if (mark_as_dirty)
mark_inode_dirty_sync(inode);
}
EXPORT_SYMBOL_GPL(pnfs_set_layoutcommit);
void pnfs_cleanup_layoutcommit(struct nfs4_layoutcommit_data *data)
{
struct nfs_server *nfss = NFS_SERVER(data->args.inode);
if (nfss->pnfs_curr_ld->cleanup_layoutcommit)
nfss->pnfs_curr_ld->cleanup_layoutcommit(data);
pnfs_list_write_lseg_done(data->args.inode, &data->lseg_list);
}
/*
* For the LAYOUT4_NFSV4_1_FILES layout type, NFS_DATA_SYNC WRITEs and
* NFS_UNSTABLE WRITEs with a COMMIT to data servers must store enough
* data to disk to allow the server to recover the data if it crashes.
* LAYOUTCOMMIT is only needed when the NFL4_UFLG_COMMIT_THRU_MDS flag
* is off, and a COMMIT is sent to a data server, or
* if WRITEs to a data server return NFS_DATA_SYNC.
*/
int
pnfs_layoutcommit_inode(struct inode *inode, bool sync)
{
struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
struct nfs4_layoutcommit_data *data;
struct nfs_inode *nfsi = NFS_I(inode);
loff_t end_pos;
int status;
if (!pnfs_layoutcommit_outstanding(inode))
return 0;
dprintk("--> %s inode %lu\n", __func__, inode->i_ino);
status = -EAGAIN;
if (test_and_set_bit(NFS_INO_LAYOUTCOMMITTING, &nfsi->flags)) {
if (!sync)
goto out;
sched: Remove proliferation of wait_on_bit() action functions The current "wait_on_bit" interface requires an 'action' function to be provided which does the actual waiting. There are over 20 such functions, many of them identical. Most cases can be satisfied by one of just two functions, one which uses io_schedule() and one which just uses schedule(). So: Rename wait_on_bit and wait_on_bit_lock to wait_on_bit_action and wait_on_bit_lock_action to make it explicit that they need an action function. Introduce new wait_on_bit{,_lock} and wait_on_bit{,_lock}_io which are *not* given an action function but implicitly use a standard one. The decision to error-out if a signal is pending is now made based on the 'mode' argument rather than being encoded in the action function. All instances of the old wait_on_bit and wait_on_bit_lock which can use the new version have been changed accordingly and their action functions have been discarded. wait_on_bit{_lock} does not return any specific error code in the event of a signal so the caller must check for non-zero and interpolate their own error code as appropriate. The wait_on_bit() call in __fscache_wait_on_invalidate() was ambiguous as it specified TASK_UNINTERRUPTIBLE but used fscache_wait_bit_interruptible as an action function. David Howells confirms this should be uniformly "uninterruptible" The main remaining user of wait_on_bit{,_lock}_action is NFS which needs to use a freezer-aware schedule() call. A comment in fs/gfs2/glock.c notes that having multiple 'action' functions is useful as they display differently in the 'wchan' field of 'ps'. (and /proc/$PID/wchan). As the new bit_wait{,_io} functions are tagged "__sched", they will not show up at all, but something higher in the stack. So the distinction will still be visible, only with different function names (gds2_glock_wait versus gfs2_glock_dq_wait in the gfs2/glock.c case). Since first version of this patch (against 3.15) two new action functions appeared, on in NFS and one in CIFS. CIFS also now uses an action function that makes the same freezer aware schedule call as NFS. Signed-off-by: NeilBrown <neilb@suse.de> Acked-by: David Howells <dhowells@redhat.com> (fscache, keys) Acked-by: Steven Whitehouse <swhiteho@redhat.com> (gfs2) Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Steve French <sfrench@samba.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/20140707051603.28027.72349.stgit@notabene.brown Signed-off-by: Ingo Molnar <mingo@kernel.org>
2014-07-07 09:16:04 +04:00
status = wait_on_bit_lock_action(&nfsi->flags,
NFS_INO_LAYOUTCOMMITTING,
nfs_wait_bit_killable,
TASK_KILLABLE);
if (status)
goto out;
}
status = -ENOMEM;
/* Note kzalloc ensures data->res.seq_res.sr_slot == NULL */
data = kzalloc(sizeof(*data), GFP_NOFS);
if (!data)
goto clear_layoutcommitting;
status = 0;
spin_lock(&inode->i_lock);
if (!test_and_clear_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags))
goto out_unlock;
INIT_LIST_HEAD(&data->lseg_list);
pnfs_list_write_lseg(inode, &data->lseg_list);
end_pos = nfsi->layout->plh_lwb;
nfs4_stateid_copy(&data->args.stateid, &nfsi->layout->plh_stateid);
spin_unlock(&inode->i_lock);
data->args.inode = inode;
data->cred = get_rpccred(nfsi->layout->plh_lc_cred);
nfs_fattr_init(&data->fattr);
data->args.bitmask = NFS_SERVER(inode)->cache_consistency_bitmask;
data->res.fattr = &data->fattr;
data->args.lastbytewritten = end_pos - 1;
data->res.server = NFS_SERVER(inode);
if (ld->prepare_layoutcommit) {
status = ld->prepare_layoutcommit(&data->args);
if (status) {
put_rpccred(data->cred);
spin_lock(&inode->i_lock);
set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
if (end_pos > nfsi->layout->plh_lwb)
nfsi->layout->plh_lwb = end_pos;
goto out_unlock;
}
}
status = nfs4_proc_layoutcommit(data, sync);
out:
if (status)
mark_inode_dirty_sync(inode);
dprintk("<-- %s status %d\n", __func__, status);
return status;
out_unlock:
spin_unlock(&inode->i_lock);
kfree(data);
clear_layoutcommitting:
pnfs_clear_layoutcommitting(inode);
goto out;
}
EXPORT_SYMBOL_GPL(pnfs_layoutcommit_inode);
int
pnfs_generic_sync(struct inode *inode, bool datasync)
{
return pnfs_layoutcommit_inode(inode, true);
}
EXPORT_SYMBOL_GPL(pnfs_generic_sync);
struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
{
struct nfs4_threshold *thp;
thp = kzalloc(sizeof(*thp), GFP_NOFS);
if (!thp) {
dprintk("%s mdsthreshold allocation failed\n", __func__);
return NULL;
}
return thp;
}
#if IS_ENABLED(CONFIG_NFS_V4_2)
int
pnfs_report_layoutstat(struct inode *inode, gfp_t gfp_flags)
{
struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
struct nfs_server *server = NFS_SERVER(inode);
struct nfs_inode *nfsi = NFS_I(inode);
struct nfs42_layoutstat_data *data;
struct pnfs_layout_hdr *hdr;
int status = 0;
if (!pnfs_enabled_sb(server) || !ld->prepare_layoutstats)
goto out;
if (!nfs_server_capable(inode, NFS_CAP_LAYOUTSTATS))
goto out;
if (test_and_set_bit(NFS_INO_LAYOUTSTATS, &nfsi->flags))
goto out;
spin_lock(&inode->i_lock);
if (!NFS_I(inode)->layout) {
spin_unlock(&inode->i_lock);
goto out;
}
hdr = NFS_I(inode)->layout;
pnfs_get_layout_hdr(hdr);
spin_unlock(&inode->i_lock);
data = kzalloc(sizeof(*data), gfp_flags);
if (!data) {
status = -ENOMEM;
goto out_put;
}
data->args.fh = NFS_FH(inode);
data->args.inode = inode;
nfs4_stateid_copy(&data->args.stateid, &hdr->plh_stateid);
status = ld->prepare_layoutstats(&data->args);
if (status)
goto out_free;
status = nfs42_proc_layoutstats_generic(NFS_SERVER(inode), data);
out:
dprintk("%s returns %d\n", __func__, status);
return status;
out_free:
kfree(data);
out_put:
pnfs_put_layout_hdr(hdr);
smp_mb__before_atomic();
clear_bit(NFS_INO_LAYOUTSTATS, &nfsi->flags);
smp_mb__after_atomic();
goto out;
}
EXPORT_SYMBOL_GPL(pnfs_report_layoutstat);
#endif
unsigned int layoutstats_timer;
module_param(layoutstats_timer, uint, 0644);
EXPORT_SYMBOL_GPL(layoutstats_timer);