summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/lockd/host.c9
-rw-r--r--fs/nfs/callback.c109
-rw-r--r--fs/nfs/callback.h4
-rw-r--r--fs/nfs/callback_proc.c12
-rw-r--r--fs/nfs/callback_xdr.c5
-rw-r--r--fs/nfs/client.c15
-rw-r--r--fs/nfs/delegation.c6
-rw-r--r--fs/nfs/direct.c34
-rw-r--r--fs/nfs/inode.c26
-rw-r--r--fs/nfs/internal.h3
-rw-r--r--fs/nfs/nfs3acl.c4
-rw-r--r--fs/nfs/nfs3xdr.c5
-rw-r--r--fs/nfs/nfs4filelayoutdev.c9
-rw-r--r--fs/nfs/nfs4proc.c30
-rw-r--r--fs/nfs/nfs4state.c6
-rw-r--r--fs/nfs/nfs4xdr.c9
-rw-r--r--fs/nfs/pnfs.c2
-rw-r--r--fs/nfs/write.c2
-rw-r--r--fs/nfs_common/nfsacl.c54
-rw-r--r--fs/posix_acl.c17
-rw-r--r--fs/xfs/linux-2.6/xfs_ioctl.c20
-rw-r--r--fs/xfs/quota/xfs_qm.c46
-rw-r--r--fs/xfs/xfs_alloc.h16
-rw-r--r--fs/xfs/xfs_bmap.c61
-rw-r--r--fs/xfs/xfs_buf_item.c12
-rw-r--r--fs/xfs/xfs_extfree_item.c3
-rw-r--r--fs/xfs/xfs_iomap.c7
-rw-r--r--fs/xfs/xfs_log.h2
-rw-r--r--fs/xfs/xfs_log_cil.c15
-rw-r--r--fs/xfs/xfs_trans.c41
30 files changed, 322 insertions, 262 deletions
diff --git a/fs/lockd/host.c b/fs/lockd/host.c
index 5f1bcb2f06f3..b7c99bfb3da6 100644
--- a/fs/lockd/host.c
+++ b/fs/lockd/host.c
@@ -520,7 +520,7 @@ static struct nlm_host *next_host_state(struct hlist_head *cache,
struct nsm_handle *nsm,
const struct nlm_reboot *info)
{
- struct nlm_host *host = NULL;
+ struct nlm_host *host;
struct hlist_head *chain;
struct hlist_node *pos;
@@ -532,12 +532,13 @@ static struct nlm_host *next_host_state(struct hlist_head *cache,
host->h_state++;
nlm_get_host(host);
- goto out;
+ mutex_unlock(&nlm_host_mutex);
+ return host;
}
}
-out:
+
mutex_unlock(&nlm_host_mutex);
- return host;
+ return NULL;
}
/**
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 199016528fcb..e3d294269058 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -135,33 +135,6 @@ out_err:
#if defined(CONFIG_NFS_V4_1)
/*
- * * CB_SEQUENCE operations will fail until the callback sessionid is set.
- * */
-int nfs4_set_callback_sessionid(struct nfs_client *clp)
-{
- struct svc_serv *serv = clp->cl_rpcclient->cl_xprt->bc_serv;
- struct nfs4_sessionid *bc_sid;
-
- if (!serv->sv_bc_xprt)
- return -EINVAL;
-
- /* on success freed in xprt_free */
- bc_sid = kmalloc(sizeof(struct nfs4_sessionid), GFP_KERNEL);
- if (!bc_sid)
- return -ENOMEM;
- memcpy(bc_sid->data, &clp->cl_session->sess_id.data,
- NFS4_MAX_SESSIONID_LEN);
- spin_lock_bh(&serv->sv_cb_lock);
- serv->sv_bc_xprt->xpt_bc_sid = bc_sid;
- spin_unlock_bh(&serv->sv_cb_lock);
- dprintk("%s set xpt_bc_sid=%u:%u:%u:%u for sv_bc_xprt %p\n", __func__,
- ((u32 *)bc_sid->data)[0], ((u32 *)bc_sid->data)[1],
- ((u32 *)bc_sid->data)[2], ((u32 *)bc_sid->data)[3],
- serv->sv_bc_xprt);
- return 0;
-}
-
-/*
* The callback service for NFSv4.1 callbacks
*/
static int
@@ -266,10 +239,6 @@ static inline void nfs_callback_bc_serv(u32 minorversion, struct rpc_xprt *xprt,
struct nfs_callback_data *cb_info)
{
}
-int nfs4_set_callback_sessionid(struct nfs_client *clp)
-{
- return 0;
-}
#endif /* CONFIG_NFS_V4_1 */
/*
@@ -359,78 +328,58 @@ void nfs_callback_down(int minorversion)
mutex_unlock(&nfs_callback_mutex);
}
-static int check_gss_callback_principal(struct nfs_client *clp,
- struct svc_rqst *rqstp)
+/* Boolean check of RPC_AUTH_GSS principal */
+int
+check_gss_callback_principal(struct nfs_client *clp, struct svc_rqst *rqstp)
{
struct rpc_clnt *r = clp->cl_rpcclient;
char *p = svc_gss_principal(rqstp);
+ if (rqstp->rq_authop->flavour != RPC_AUTH_GSS)
+ return 1;
+
/* No RPC_AUTH_GSS on NFSv4.1 back channel yet */
if (clp->cl_minorversion != 0)
- return SVC_DROP;
+ return 0;
/*
* It might just be a normal user principal, in which case
* userspace won't bother to tell us the name at all.
*/
if (p == NULL)
- return SVC_DENIED;
+ return 0;
/* Expect a GSS_C_NT_HOSTBASED_NAME like "nfs@serverhostname" */
if (memcmp(p, "nfs@", 4) != 0)
- return SVC_DENIED;
+ return 0;
p += 4;
if (strcmp(p, r->cl_server) != 0)
- return SVC_DENIED;
- return SVC_OK;
+ return 0;
+ return 1;
}
-/* pg_authenticate method helper */
-static struct nfs_client *nfs_cb_find_client(struct svc_rqst *rqstp)
-{
- struct nfs4_sessionid *sessionid = bc_xprt_sid(rqstp);
- int is_cb_compound = rqstp->rq_proc == CB_COMPOUND ? 1 : 0;
-
- dprintk("--> %s rq_proc %d\n", __func__, rqstp->rq_proc);
- if (svc_is_backchannel(rqstp))
- /* Sessionid (usually) set after CB_NULL ping */
- return nfs4_find_client_sessionid(svc_addr(rqstp), sessionid,
- is_cb_compound);
- else
- /* No callback identifier in pg_authenticate */
- return nfs4_find_client_no_ident(svc_addr(rqstp));
-}
-
-/* pg_authenticate method for nfsv4 callback threads. */
+/*
+ * pg_authenticate method for nfsv4 callback threads.
+ *
+ * The authflavor has been negotiated, so an incorrect flavor is a server
+ * bug. Drop packets with incorrect authflavor.
+ *
+ * All other checking done after NFS decoding where the nfs_client can be
+ * found in nfs4_callback_compound
+ */
static int nfs_callback_authenticate(struct svc_rqst *rqstp)
{
- struct nfs_client *clp;
- RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
- int ret = SVC_OK;
-
- /* Don't talk to strangers */
- clp = nfs_cb_find_client(rqstp);
- if (clp == NULL)
- return SVC_DROP;
-
- dprintk("%s: %s NFSv4 callback!\n", __func__,
- svc_print_addr(rqstp, buf, sizeof(buf)));
-
switch (rqstp->rq_authop->flavour) {
- case RPC_AUTH_NULL:
- if (rqstp->rq_proc != CB_NULL)
- ret = SVC_DENIED;
- break;
- case RPC_AUTH_UNIX:
- break;
- case RPC_AUTH_GSS:
- ret = check_gss_callback_principal(clp, rqstp);
- break;
- default:
- ret = SVC_DENIED;
+ case RPC_AUTH_NULL:
+ if (rqstp->rq_proc != CB_NULL)
+ return SVC_DROP;
+ break;
+ case RPC_AUTH_GSS:
+ /* No RPC_AUTH_GSS support yet in NFSv4.1 */
+ if (svc_is_backchannel(rqstp))
+ return SVC_DROP;
}
- nfs_put_client(clp);
- return ret;
+ return SVC_OK;
}
/*
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index d3b44f9bd747..46d93ce7311b 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -7,6 +7,7 @@
*/
#ifndef __LINUX_FS_NFS_CALLBACK_H
#define __LINUX_FS_NFS_CALLBACK_H
+#include <linux/sunrpc/svc.h>
#define NFS4_CALLBACK 0x40000000
#define NFS4_CALLBACK_XDRSIZE 2048
@@ -37,7 +38,6 @@ enum nfs4_callback_opnum {
struct cb_process_state {
__be32 drc_status;
struct nfs_client *clp;
- struct nfs4_sessionid *svc_sid; /* v4.1 callback service sessionid */
};
struct cb_compound_hdr_arg {
@@ -168,7 +168,7 @@ extern unsigned nfs4_callback_layoutrecall(
extern void nfs4_check_drain_bc_complete(struct nfs4_session *ses);
extern void nfs4_cb_take_slot(struct nfs_client *clp);
#endif /* CONFIG_NFS_V4_1 */
-
+extern int check_gss_callback_principal(struct nfs_client *, struct svc_rqst *);
extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
struct cb_getattrres *res,
struct cb_process_state *cps);
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 4bb91cb2620d..89587573fe50 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -373,17 +373,11 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
{
struct nfs_client *clp;
int i;
- __be32 status;
+ __be32 status = htonl(NFS4ERR_BADSESSION);
cps->clp = NULL;
- status = htonl(NFS4ERR_BADSESSION);
- /* Incoming session must match the callback session */
- if (memcmp(&args->csa_sessionid, cps->svc_sid, NFS4_MAX_SESSIONID_LEN))
- goto out;
-
- clp = nfs4_find_client_sessionid(args->csa_addr,
- &args->csa_sessionid, 1);
+ clp = nfs4_find_client_sessionid(args->csa_addr, &args->csa_sessionid);
if (clp == NULL)
goto out;
@@ -414,9 +408,9 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1;
nfs4_cb_take_slot(clp);
- cps->clp = clp; /* put in nfs4_callback_compound */
out:
+ cps->clp = clp; /* put in nfs4_callback_compound */
for (i = 0; i < args->csa_nrclists; i++)
kfree(args->csa_rclists[i].rcl_refcalls);
kfree(args->csa_rclists);
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index 23112c263f81..14e0f9371d14 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -794,10 +794,9 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
if (hdr_arg.minorversion == 0) {
cps.clp = nfs4_find_client_ident(hdr_arg.cb_ident);
- if (!cps.clp)
+ if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp))
return rpc_drop_reply;
- } else
- cps.svc_sid = bc_xprt_sid(rqstp);
+ }
hdr_res.taglen = hdr_arg.taglen;
hdr_res.tag = hdr_arg.tag;
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 192f2f860265..bd3ca32879e7 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1206,16 +1206,11 @@ nfs4_find_client_ident(int cb_ident)
* For CB_COMPOUND calls, find a client by IP address, protocol version,
* minorversion, and sessionID
*
- * CREATE_SESSION triggers a CB_NULL ping from servers. The callback service
- * sessionid can only be set after the CREATE_SESSION return, so a CB_NULL
- * can arrive before the callback sessionid is set. For CB_NULL calls,
- * find a client by IP address protocol version, and minorversion.
- *
* Returns NULL if no such client
*/
struct nfs_client *
nfs4_find_client_sessionid(const struct sockaddr *addr,
- struct nfs4_sessionid *sid, int is_cb_compound)
+ struct nfs4_sessionid *sid)
{
struct nfs_client *clp;
@@ -1227,9 +1222,9 @@ nfs4_find_client_sessionid(const struct sockaddr *addr,
if (!nfs4_has_session(clp))
continue;
- /* Match sessionid unless cb_null call*/
- if (is_cb_compound && (memcmp(clp->cl_session->sess_id.data,
- sid->data, NFS4_MAX_SESSIONID_LEN) != 0))
+ /* Match sessionid*/
+ if (memcmp(clp->cl_session->sess_id.data,
+ sid->data, NFS4_MAX_SESSIONID_LEN) != 0)
continue;
atomic_inc(&clp->cl_count);
@@ -1244,7 +1239,7 @@ nfs4_find_client_sessionid(const struct sockaddr *addr,
struct nfs_client *
nfs4_find_client_sessionid(const struct sockaddr *addr,
- struct nfs4_sessionid *sid, int is_cb_compound)
+ struct nfs4_sessionid *sid)
{
return NULL;
}
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 364e4328f392..bbbc6bf5cb2e 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -23,8 +23,6 @@
static void nfs_do_free_delegation(struct nfs_delegation *delegation)
{
- if (delegation->cred)
- put_rpccred(delegation->cred);
kfree(delegation);
}
@@ -37,6 +35,10 @@ static void nfs_free_delegation_callback(struct rcu_head *head)
static void nfs_free_delegation(struct nfs_delegation *delegation)
{
+ if (delegation->cred) {
+ put_rpccred(delegation->cred);
+ delegation->cred = NULL;
+ }
call_rcu(&delegation->rcu, nfs_free_delegation_callback);
}
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index e6ace0d93c71..9943a75bb6d1 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -407,15 +407,18 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
pos += vec->iov_len;
}
+ /*
+ * If no bytes were started, return the error, and let the
+ * generic layer handle the completion.
+ */
+ if (requested_bytes == 0) {
+ nfs_direct_req_release(dreq);
+ return result < 0 ? result : -EIO;
+ }
+
if (put_dreq(dreq))
nfs_direct_complete(dreq);
-
- if (requested_bytes != 0)
- return 0;
-
- if (result < 0)
- return result;
- return -EIO;
+ return 0;
}
static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov,
@@ -841,15 +844,18 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
pos += vec->iov_len;
}
+ /*
+ * If no bytes were started, return the error, and let the
+ * generic layer handle the completion.
+ */
+ if (requested_bytes == 0) {
+ nfs_direct_req_release(dreq);
+ return result < 0 ? result : -EIO;
+ }
+
if (put_dreq(dreq))
nfs_direct_write_complete(dreq, dreq->inode);
-
- if (requested_bytes != 0)
- return 0;
-
- if (result < 0)
- return result;
- return -EIO;
+ return 0;
}
static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov,
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index d8512423ba72..1cc600e77bb4 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -881,9 +881,10 @@ out:
return ret;
}
-static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
+static unsigned long nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
{
struct nfs_inode *nfsi = NFS_I(inode);
+ unsigned long ret = 0;
if ((fattr->valid & NFS_ATTR_FATTR_PRECHANGE)
&& (fattr->valid & NFS_ATTR_FATTR_CHANGE)
@@ -891,25 +892,32 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
nfsi->change_attr = fattr->change_attr;
if (S_ISDIR(inode->i_mode))
nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+ ret |= NFS_INO_INVALID_ATTR;
}
/* If we have atomic WCC data, we may update some attributes */
if ((fattr->valid & NFS_ATTR_FATTR_PRECTIME)
&& (fattr->valid & NFS_ATTR_FATTR_CTIME)
- && timespec_equal(&inode->i_ctime, &fattr->pre_ctime))
- memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
+ && timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) {
+ memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
+ ret |= NFS_INO_INVALID_ATTR;
+ }
if ((fattr->valid & NFS_ATTR_FATTR_PREMTIME)
&& (fattr->valid & NFS_ATTR_FATTR_MTIME)
&& timespec_equal(&inode->i_mtime, &fattr->pre_mtime)) {
- memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
- if (S_ISDIR(inode->i_mode))
- nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+ memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
+ if (S_ISDIR(inode->i_mode))
+ nfsi->cache_validity |= NFS_INO_INVALID_DATA;
+ ret |= NFS_INO_INVALID_ATTR;
}
if ((fattr->valid & NFS_ATTR_FATTR_PRESIZE)
&& (fattr->valid & NFS_ATTR_FATTR_SIZE)
&& i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size)
- && nfsi->npages == 0)
- i_size_write(inode, nfs_size_to_loff_t(fattr->size));
+ && nfsi->npages == 0) {
+ i_size_write(inode, nfs_size_to_loff_t(fattr->size));
+ ret |= NFS_INO_INVALID_ATTR;
+ }
+ return ret;
}
/**
@@ -1223,7 +1231,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
| NFS_INO_REVAL_PAGECACHE);
/* Do atomic weak cache consistency updates */
- nfs_wcc_update_inode(inode, fattr);
+ invalid |= nfs_wcc_update_inode(inode, fattr);
/* More cache consistency checks */
if (fattr->valid & NFS_ATTR_FATTR_CHANGE) {
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 4644f04b4b46..cf9fdbdabc67 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -133,8 +133,7 @@ extern void nfs_put_client(struct nfs_client *);
extern struct nfs_client *nfs4_find_client_no_ident(const struct sockaddr *);
extern struct nfs_client *nfs4_find_client_ident(int);
extern struct nfs_client *
-nfs4_find_client_sessionid(const struct sockaddr *, struct nfs4_sessionid *,
- int);
+nfs4_find_client_sessionid(const struct sockaddr *, struct nfs4_sessionid *);
extern struct nfs_server *nfs_create_server(
const struct nfs_parsed_mount_data *,
struct nfs_fh *);
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index 9f88c5f4c7e2..274342771655 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -311,8 +311,8 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
if (!nfs_server_capable(inode, NFS_CAP_ACLS))
goto out;
- /* We are doing this here, because XDR marshalling can only
- return -ENOMEM. */
+ /* We are doing this here because XDR marshalling does not
+ * return any results, it BUGs. */
status = -ENOSPC;
if (acl != NULL && acl->a_count > NFS_ACL_MAX_ENTRIES)
goto out;
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 01c5e8b1941d..183c6b123d0f 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1328,10 +1328,13 @@ static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req,
encode_nfs_fh3(xdr, NFS_FH(args->inode));
encode_uint32(xdr, args->mask);
+
+ base = req->rq_slen;
if (args->npages != 0)
xdr_write_pages(xdr, args->pages, 0, args->len);
+ else
+ xdr_reserve_space(xdr, NFS_ACL_INLINE_BUFSIZE);
- base = req->rq_slen;
error = nfsacl_encode(xdr->buf, base, args->inode,
(args->mask & NFS_ACL) ?
args->acl_access : NULL, 1, 0);
diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index 51fe64ace55a..f5c9b125e8cc 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -214,7 +214,7 @@ decode_and_add_ds(__be32 **pp, struct inode *inode)
/* ipv6 length plus port is legal */
if (rlen > INET6_ADDRSTRLEN + 8) {
- dprintk("%s Invalid address, length %d\n", __func__,
+ dprintk("%s: Invalid address, length %d\n", __func__,
rlen);
goto out_err;
}
@@ -225,6 +225,11 @@ decode_and_add_ds(__be32 **pp, struct inode *inode)
/* replace the port dots with dashes for the in4_pton() delimiter*/
for (i = 0; i < 2; i++) {
char *res = strrchr(buf, '.');
+ if (!res) {
+ dprintk("%s: Failed finding expected dots in port\n",
+ __func__);
+ goto out_free;
+ }
*res = '-';
}
@@ -240,7 +245,7 @@ decode_and_add_ds(__be32 **pp, struct inode *inode)
port = htons((tmp[0] << 8) | (tmp[1]));
ds = nfs4_pnfs_ds_add(inode, ip_addr, port);
- dprintk("%s Decoded address and port %s\n", __func__, buf);
+ dprintk("%s: Decoded address and port %s\n", __func__, buf);
out_free:
kfree(buf);
out_err:
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 9d992b0346e3..78936a8f40ab 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -50,6 +50,7 @@
#include <linux/module.h>
#include <linux/sunrpc/bc_xprt.h>
#include <linux/xattr.h>
+#include <linux/utsname.h>
#include "nfs4_fs.h"
#include "delegation.h"
@@ -4572,27 +4573,16 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred)
*p = htonl((u32)clp->cl_boot_time.tv_nsec);
args.verifier = &verifier;
- while (1) {
- args.id_len = scnprintf(args.id, sizeof(args.id),
- "%s/%s %u",
- clp->cl_ipaddr,
- rpc_peeraddr2str(clp->cl_rpcclient,
- RPC_DISPLAY_ADDR),
- clp->cl_id_uniquifier);
-
- status = rpc_call_sync(clp->cl_rpcclient, &msg, 0);
-
- if (status != -NFS4ERR_CLID_INUSE)
- break;
-
- if (signalled())
- break;
-
- if (++clp->cl_id_uniquifier == 0)
- break;
- }
+ args.id_len = scnprintf(args.id, sizeof(args.id),
+ "%s/%s.%s/%u",
+ clp->cl_ipaddr,
+ init_utsname()->nodename,
+ init_utsname()->domainname,
+ clp->cl_rpcclient->cl_auth->au_flavor);
- status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags);
+ status = rpc_call_sync(clp->cl_rpcclient, &msg, 0);
+ if (!status)
+ status = nfs4_check_cl_exchange_flags(clp->cl_exchange_flags);
dprintk("<-- %s status= %d\n", __func__, status);
return status;
}
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 2336d532cf66..e6742b57a04c 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -232,12 +232,6 @@ int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
status = nfs4_proc_create_session(clp);
if (status != 0)
goto out;
- status = nfs4_set_callback_sessionid(clp);
- if (status != 0) {
- printk(KERN_WARNING "Sessionid not set. No callback service\n");
- nfs_callback_down(1);
- status = 0;
- }
nfs41_setup_state_renewal(clp);
nfs_mark_client_ready(clp, NFS_CS_READY);
out:
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 2ab8e5cb8f59..4e2c168b6ee9 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -6086,11 +6086,11 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
__be32 *p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
goto out_overflow;
- if (!ntohl(*p++)) {
+ if (*p == xdr_zero) {
p = xdr_inline_decode(xdr, 4);
if (unlikely(!p))
goto out_overflow;
- if (!ntohl(*p++))
+ if (*p == xdr_zero)
return -EAGAIN;
entry->eof = 1;
return -EBADCOOKIE;
@@ -6101,7 +6101,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
goto out_overflow;
entry->prev_cookie = entry->cookie;
p = xdr_decode_hyper(p, &entry->cookie);
- entry->len = ntohl(*p++);
+ entry->len = be32_to_cpup(p);
p = xdr_inline_decode(xdr, entry->len);
if (unlikely(!p))
@@ -6132,9 +6132,6 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
if (entry->fattr->valid & NFS_ATTR_FATTR_TYPE)
entry->d_type = nfs_umode_to_dtype(entry->fattr->mode);
- if (verify_attr_len(xdr, p, len) < 0)
- goto out_overflow;
-
return 0;
out_overflow:
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index bc4089769735..1b1bc1a0fb0a 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -951,7 +951,7 @@ pnfs_put_deviceid_cache(struct nfs_client *clp)
{
struct pnfs_deviceid_cache *local = clp->cl_devid_cache;
- dprintk("--> %s cl_devid_cache %p\n", __func__, clp->cl_devid_cache);
+ dprintk("--> %s ({%d})\n", __func__, atomic_read(&local->dc_ref));
if (atomic_dec_and_lock(&local->dc_ref, &clp->cl_lock)) {
int i;
/* Verify cache is empty */
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 10d648ea128b..c8278f4046cb 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -932,7 +932,7 @@ out_bad:
while (!list_empty(&list)) {
data = list_entry(list.next, struct nfs_write_data, pages);
list_del(&data->pages);
- nfs_writedata_release(data);
+ nfs_writedata_free(data);
}
nfs_redirty_request(req);
return -ENOMEM;
diff --git a/fs/nfs_common/nfsacl.c b/fs/nfs_common/nfsacl.c
index fc1c52571c03..84c27d69d421 100644
--- a/fs/nfs_common/nfsacl.c
+++ b/fs/nfs_common/nfsacl.c
@@ -42,6 +42,11 @@ struct nfsacl_encode_desc {
gid_t gid;
};
+struct nfsacl_simple_acl {
+ struct posix_acl acl;
+ struct posix_acl_entry ace[4];
+};
+
static int
xdr_nfsace_encode(struct xdr_array2_desc *desc, void *elem)
{
@@ -72,9 +77,20 @@ xdr_nfsace_encode(struct xdr_array2_desc *desc, void *elem)
return 0;
}
-unsigned int
-nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
- struct posix_acl *acl, int encode_entries, int typeflag)
+/**
+ * nfsacl_encode - Encode an NFSv3 ACL
+ *
+ * @buf: destination xdr_buf to contain XDR encoded ACL
+ * @base: byte offset in xdr_buf where XDR'd ACL begins
+ * @inode: inode of file whose ACL this is
+ * @acl: posix_acl to encode
+ * @encode_entries: whether to encode ACEs as well
+ * @typeflag: ACL type: NFS_ACL_DEFAULT or zero
+ *
+ * Returns size of encoded ACL in bytes or a negative errno value.
+ */
+int nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
+ struct posix_acl *acl, int encode_entries, int typeflag)
{
int entries = (acl && acl->a_count) ? max_t(int, acl->a_count, 4) : 0;
struct nfsacl_encode_desc nfsacl_desc = {
@@ -88,17 +104,22 @@ nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
.uid = inode->i_uid,
.gid = inode->i_gid,
};
+ struct nfsacl_simple_acl aclbuf;
int err;
- struct posix_acl *acl2 = NULL;
if (entries > NFS_ACL_MAX_ENTRIES ||
xdr_encode_word(buf, base, entries))
return -EINVAL;
if (encode_entries && acl && acl->a_count == 3) {
- /* Fake up an ACL_MASK entry. */
- acl2 = posix_acl_alloc(4, GFP_KERNEL);
- if (!acl2)
- return -ENOMEM;
+ struct posix_acl *acl2 = &aclbuf.acl;
+
+ /* Avoid the use of posix_acl_alloc(). nfsacl_encode() is
+ * invoked in contexts where a memory allocation failure is
+ * fatal. Fortunately this fake ACL is small enough to
+ * construct on the stack. */
+ memset(acl2, 0, sizeof(acl2));
+ posix_acl_init(acl2, 4);
+
/* Insert entries in canonical order: other orders seem
to confuse Solaris VxFS. */
acl2->a_entries[0] = acl->a_entries[0]; /* ACL_USER_OBJ */
@@ -109,8 +130,6 @@ nfsacl_encode(struct xdr_buf *buf, unsigned int base, struct inode *inode,
nfsacl_desc.acl = acl2;
}
err = xdr_encode_array2(buf, base + 4, &nfsacl_desc.desc);
- if (acl2)
- posix_acl_release(acl2);
if (!err)
err = 8 + nfsacl_desc.desc.elem_size *
nfsacl_desc.desc.array_len;
@@ -224,9 +243,18 @@ posix_acl_from_nfsacl(struct posix_acl *acl)
return 0;
}
-unsigned int
-nfsacl_decode(struct xdr_buf *buf, unsigned int base, unsigned int *aclcnt,
- struct posix_acl **pacl)
+/**
+ * nfsacl_decode - Decode an NFSv3 ACL
+ *
+ * @buf: xdr_buf containing XDR'd ACL data to decode
+ * @base: byte offset in xdr_buf where XDR'd ACL begins
+ * @aclcnt: count of ACEs in decoded posix_acl
+ * @pacl: buffer in which to place decoded posix_acl
+ *
+ * Returns the length of the decoded ACL in bytes, or a negative errno value.
+ */
+int nfsacl_decode(struct xdr_buf *buf, unsigned int base, unsigned int *aclcnt,
+ struct posix_acl **pacl)
{
struct nfsacl_decode_desc nfsacl_desc = {
.desc = {
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 39df95a0ec25..b1cf6bf4b41d 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -22,6 +22,7 @@
#include <linux/errno.h>
+EXPORT_SYMBOL(posix_acl_init);
EXPORT_SYMBOL(posix_acl_alloc);
EXPORT_SYMBOL(posix_acl_clone);
EXPORT_SYMBOL(posix_acl_valid);
@@ -32,6 +33,16 @@ EXPORT_SYMBOL(posix_acl_chmod_masq);
EXPORT_SYMBOL(posix_acl_permission);
/*
+ * Init a fresh posix_acl
+ */
+void
+posix_acl_init(struct posix_acl *acl, int count)
+{
+ atomic_set(&acl->a_refcount, 1);
+ acl->a_count = count;
+}
+
+/*
* Allocate a new ACL with the specified number of entries.
*/
struct posix_acl *
@@ -40,10 +51,8 @@ posix_acl_alloc(int count, gfp_t flags)
const size_t size = sizeof(struct posix_acl) +
count * sizeof(struct posix_acl_entry);
struct posix_acl *acl = kmalloc(size, flags);
- if (acl) {
- atomic_set(&acl->a_refcount, 1);
- acl->a_count = count;
- }
+ if (acl)
+ posix_acl_init(acl, count);
return acl;
}
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index b06ede1d0bed..f5e2a19e0f8e 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -985,10 +985,22 @@ xfs_ioctl_setattr(
/*
* Extent size must be a multiple of the appropriate block
- * size, if set at all.
+ * size, if set at all. It must also be smaller than the
+ * maximum extent size supported by the filesystem.
+ *
+ * Also, for non-realtime files, limit the extent size hint to
+ * half the size of the AGs in the filesystem so alignment
+ * doesn't result in extents larger than an AG.
*/
if (fa->fsx_extsize != 0) {
- xfs_extlen_t size;
+ xfs_extlen_t size;
+ xfs_fsblock_t extsize_fsb;
+
+ extsize_fsb = XFS_B_TO_FSB(mp, fa->fsx_extsize);
+ if (extsize_fsb > MAXEXTLEN) {
+ code = XFS_ERROR(EINVAL);
+ goto error_return;
+ }
if (XFS_IS_REALTIME_INODE(ip) ||
((mask & FSX_XFLAGS) &&
@@ -997,6 +1009,10 @@ xfs_ioctl_setattr(
mp->m_sb.sb_blocklog;
} else {
size = mp->m_sb.sb_blocksize;
+ if (extsize_fsb > mp->m_sb.sb_agblocks / 2) {
+ code = XFS_ERROR(EINVAL);
+ goto error_return;
+ }
}
if (fa->fsx_extsize % size) {
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index f8e854b4fde8..206a2815ced6 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -1863,12 +1863,14 @@ xfs_qm_dqreclaim_one(void)
xfs_dquot_t *dqpout;
xfs_dquot_t *dqp;
int restarts;
+ int startagain;
restarts = 0;
dqpout = NULL;
/* lockorder: hashchainlock, freelistlock, mplistlock, dqlock, dqflock */
-startagain:
+again:
+ startagain = 0;
mutex_lock(&xfs_Gqm->qm_dqfrlist_lock);
list_for_each_entry(dqp, &xfs_Gqm->qm_dqfrlist, q_freelist) {
@@ -1885,13 +1887,10 @@ startagain:
ASSERT(! (dqp->dq_flags & XFS_DQ_INACTIVE));
trace_xfs_dqreclaim_want(dqp);
-
- xfs_dqunlock(dqp);
- mutex_unlock(&xfs_Gqm->qm_dqfrlist_lock);
- if (++restarts >= XFS_QM_RECLAIM_MAX_RESTARTS)
- return NULL;
XQM_STATS_INC(xqmstats.xs_qm_dqwants);
- goto startagain;
+ restarts++;
+ startagain = 1;
+ goto dqunlock;
}
/*
@@ -1906,23 +1905,20 @@ startagain:
ASSERT(list_empty(&dqp->q_mplist));
list_del_init(&dqp->q_freelist);
xfs_Gqm->qm_dqfrlist_cnt--;
- xfs_dqunlock(dqp);
dqpout = dqp;
XQM_STATS_INC(xqmstats.xs_qm_dqinact_reclaims);
- break;
+ goto dqunlock;
}
ASSERT(dqp->q_hash);
ASSERT(!list_empty(&dqp->q_mplist));
/*
- * Try to grab the flush lock. If this dquot is in the process of
- * getting flushed to disk, we don't want to reclaim it.
+ * Try to grab the flush lock. If this dquot is in the process
+ * of getting flushed to disk, we don't want to reclaim it.
*/
- if (!xfs_dqflock_nowait(dqp)) {
- xfs_dqunlock(dqp);
- continue;
- }
+ if (!xfs_dqflock_nowait(dqp))
+ goto dqunlock;
/*
* We have the flush lock so we know that this is not in the
@@ -1944,8 +1940,7 @@ startagain:
xfs_fs_cmn_err(CE_WARN, mp,
"xfs_qm_dqreclaim: dquot %p flush failed", dqp);
}
- xfs_dqunlock(dqp); /* dqflush unlocks dqflock */
- continue;
+ goto dqunlock;
}
/*
@@ -1967,13 +1962,8 @@ startagain:
*/
if (!mutex_trylock(&mp->m_quotainfo->qi_dqlist_lock)) {
restarts++;
- mutex_unlock(&dqp->q_hash->qh_lock);
- xfs_dqfunlock(dqp);
- xfs_dqunlock(dqp);
- mutex_unlock(&xfs_Gqm->qm_dqfrlist_lock);
- if (restarts++ >= XFS_QM_RECLAIM_MAX_RESTARTS)
- return NULL;
- goto startagain;
+ startagain = 1;
+ goto qhunlock;
}
ASSERT(dqp->q_nrefs == 0);
@@ -1986,14 +1976,20 @@ startagain:
xfs_Gqm->qm_dqfrlist_cnt--;
dqpout = dqp;
mutex_unlock(&mp->m_quotainfo->qi_dqlist_lock);
+qhunlock:
mutex_unlock(&dqp->q_hash->qh_lock);
dqfunlock:
xfs_dqfunlock(dqp);
+dqunlock:
xfs_dqunlock(dqp);
if (dqpout)
break;
if (restarts >= XFS_QM_RECLAIM_MAX_RESTARTS)
- return NULL;
+ break;
+ if (startagain) {
+ mutex_unlock(&xfs_Gqm->qm_dqfrlist_lock);
+ goto again;
+ }
}
mutex_unlock(&xfs_Gqm->qm_dqfrlist_lock);
return dqpout;
diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h
index 0ab56b32c7eb..d0b3bc72005b 100644
--- a/fs/xfs/xfs_alloc.h
+++ b/fs/xfs/xfs_alloc.h
@@ -75,6 +75,22 @@ typedef unsigned int xfs_alloctype_t;
#define XFS_ALLOC_SET_ASIDE(mp) (4 + ((mp)->m_sb.sb_agcount * 4))
/*
+ * When deciding how much space to allocate out of an AG, we limit the
+ * allocation maximum size to the size the AG. However, we cannot use all the
+ * blocks in the AG - some are permanently used by metadata. These
+ * blocks are generally:
+ * - the AG superblock, AGF, AGI and AGFL
+ * - the AGF (bno and cnt) and AGI btree root blocks
+ * - 4 blocks on the AGFL according to XFS_ALLOC_SET_ASIDE() limits
+ *
+ * The AG headers are sector sized, so the amount of space they take up is
+ * dependent on filesystem geometry. The others are all single blocks.
+ */
+#define XFS_ALLOC_AG_MAX_USABLE(mp) \
+ ((mp)->m_sb.sb_agblocks - XFS_BB_TO_FSB(mp, XFS_FSS_TO_BB(mp, 4)) - 7)
+
+
+/*
* Argument structure for xfs_alloc routines.
* This is turned into a structure to avoid having 20 arguments passed
* down several levels of the stack.
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 4111cd3966c7..dc3afd7739ff 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -1038,17 +1038,34 @@ xfs_bmap_add_extent_delay_real(
* Filling in the middle part of a previous delayed allocation.
* Contiguity is impossible here.
* This case is avoided almost all the time.
+ *
+ * We start with a delayed allocation:
+ *
+ * +ddddddddddddddddddddddddddddddddddddddddddddddddddddddd+
+ * PREV @ idx
+ *
+ * and we are allocating:
+ * +rrrrrrrrrrrrrrrrr+
+ * new
+ *
+ * and we set it up for insertion as:
+ * +ddddddddddddddddddd+rrrrrrrrrrrrrrrrr+ddddddddddddddddd+
+ * new
+ * PREV @ idx LEFT RIGHT
+ * inserted at idx + 1
*/
temp = new->br_startoff - PREV.br_startoff;
- trace_xfs_bmap_pre_update(ip, idx, 0, _THIS_IP_);
- xfs_bmbt_set_blockcount(ep, temp);
- r[0] = *new;
- r[1].br_state = PREV.br_state;
- r[1].br_startblock = 0;
- r[1].br_startoff = new_endoff;
temp2 = PREV.br_startoff + PREV.br_blockcount - new_endoff;
- r[1].br_blockcount = temp2;
- xfs_iext_insert(ip, idx + 1, 2, &r[0], state);
+ trace_xfs_bmap_pre_update(ip, idx, 0, _THIS_IP_);
+ xfs_bmbt_set_blockcount(ep, temp); /* truncate PREV */
+ LEFT = *new;
+ RIGHT.br_state = PREV.br_state;
+ RIGHT.br_startblock = nullstartblock(
+ (int)xfs_bmap_worst_indlen(ip, temp2));
+ RIGHT.br_startoff = new_endoff;
+ RIGHT.br_blockcount = temp2;
+ /* insert LEFT (r[0]) and RIGHT (r[1]) at the same time */
+ xfs_iext_insert(ip, idx + 1, 2, &LEFT, state);
ip->i_df.if_lastex = idx + 1;
ip->i_d.di_nextents++;
if (cur == NULL)
@@ -2430,7 +2447,7 @@ xfs_bmap_btalloc_nullfb(
startag = ag = 0;
pag = xfs_perag_get(mp, ag);
- while (*blen < ap->alen) {
+ while (*blen < args->maxlen) {
if (!pag->pagf_init) {
error = xfs_alloc_pagf_init(mp, args->tp, ag,
XFS_ALLOC_FLAG_TRYLOCK);
@@ -2452,7 +2469,7 @@ xfs_bmap_btalloc_nullfb(
notinit = 1;
if (xfs_inode_is_filestream(ap->ip)) {
- if (*blen >= ap->alen)
+ if (*blen >= args->maxlen)
break;
if (ap->userdata) {
@@ -2498,14 +2515,14 @@ xfs_bmap_btalloc_nullfb(
* If the best seen length is less than the request
* length, use the best as the minimum.
*/
- else if (*blen < ap->alen)
+ else if (*blen < args->maxlen)
args->minlen = *blen;
/*
- * Otherwise we've seen an extent as big as alen,
+ * Otherwise we've seen an extent as big as maxlen,
* use that as the minimum.
*/
else
- args->minlen = ap->alen;
+ args->minlen = args->maxlen;
/*
* set the failure fallback case to look in the selected
@@ -2573,7 +2590,9 @@ xfs_bmap_btalloc(
args.tp = ap->tp;
args.mp = mp;
args.fsbno = ap->rval;
- args.maxlen = MIN(ap->alen, mp->m_sb.sb_agblocks);
+
+ /* Trim the allocation back to the maximum an AG can fit. */
+ args.maxlen = MIN(ap->alen, XFS_ALLOC_AG_MAX_USABLE(mp));
args.firstblock = ap->firstblock;
blen = 0;
if (nullfb) {
@@ -2621,7 +2640,7 @@ xfs_bmap_btalloc(
/*
* Adjust for alignment
*/
- if (blen > args.alignment && blen <= ap->alen)
+ if (blen > args.alignment && blen <= args.maxlen)
args.minlen = blen - args.alignment;
args.minalignslop = 0;
} else {
@@ -2640,7 +2659,7 @@ xfs_bmap_btalloc(
* of minlen+alignment+slop doesn't go up
* between the calls.
*/
- if (blen > mp->m_dalign && blen <= ap->alen)
+ if (blen > mp->m_dalign && blen <= args.maxlen)
nextminlen = blen - mp->m_dalign;
else
nextminlen = args.minlen;
@@ -4485,6 +4504,16 @@ xfs_bmapi(
/* Figure out the extent size, adjust alen */
extsz = xfs_get_extsz_hint(ip);
if (extsz) {
+ /*
+ * make sure we don't exceed a single
+ * extent length when we align the
+ * extent by reducing length we are
+ * going to allocate by the maximum
+ * amount extent size aligment may
+ * require.
+ */
+ alen = XFS_FILBLKS_MIN(len,
+ MAXEXTLEN - (2 * extsz - 1));
error = xfs_bmap_extsize_align(mp,
&got, &prev, extsz,
rt, eof,
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 98c6f73b6752..6f8c21ce0d6d 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -427,13 +427,15 @@ xfs_buf_item_unpin(
if (remove) {
/*
- * We have to remove the log item from the transaction
- * as we are about to release our reference to the
- * buffer. If we don't, the unlock that occurs later
- * in xfs_trans_uncommit() will ry to reference the
+ * If we are in a transaction context, we have to
+ * remove the log item from the transaction as we are
+ * about to release our reference to the buffer. If we
+ * don't, the unlock that occurs later in
+ * xfs_trans_uncommit() will try to reference the
* buffer which we no longer have a hold on.
*/
- xfs_trans_del_item(lip);
+ if (lip->li_desc)
+ xfs_trans_del_item(lip);
/*
* Since the transaction no longer refers to the buffer,
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index 75f2ef60e579..d22e62623437 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -138,7 +138,8 @@ xfs_efi_item_unpin(
if (remove) {
ASSERT(!(lip->li_flags & XFS_LI_IN_AIL));
- xfs_trans_del_item(lip);
+ if (lip->li_desc)
+ xfs_trans_del_item(lip);
xfs_efi_item_free(efip);
return;
}
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 55582bd66659..8a0f044750c3 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -337,7 +337,12 @@ xfs_iomap_prealloc_size(
int shift = 0;
int64_t freesp;
- alloc_blocks = XFS_B_TO_FSB(mp, ip->i_size);
+ /*
+ * rounddown_pow_of_two() returns an undefined result
+ * if we pass in alloc_blocks = 0. Hence the "+ 1" to
+ * ensure we always pass in a non-zero value.
+ */
+ alloc_blocks = XFS_B_TO_FSB(mp, ip->i_size) + 1;
alloc_blocks = XFS_FILEOFF_MIN(MAXEXTLEN,
rounddown_pow_of_two(alloc_blocks));
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 916eb7db14d9..3bd3291ef8d2 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -191,7 +191,7 @@ void xfs_log_ticket_put(struct xlog_ticket *ticket);
xlog_tid_t xfs_log_get_trans_ident(struct xfs_trans *tp);
-int xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp,
+void xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp,
struct xfs_log_vec *log_vector,
xfs_lsn_t *commit_lsn, int flags);
bool xfs_log_item_in_current_chkpt(struct xfs_log_item *lip);
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 9dc8125d04e5..9ca59be08977 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -543,7 +543,7 @@ xlog_cil_push(
error = xlog_write(log, &lvhdr, tic, &ctx->start_lsn, NULL, 0);
if (error)
- goto out_abort;
+ goto out_abort_free_ticket;
/*
* now that we've written the checkpoint into the log, strictly
@@ -569,8 +569,9 @@ restart:
}
spin_unlock(&cil->xc_cil_lock);
+ /* xfs_log_done always frees the ticket on error. */
commit_lsn = xfs_log_done(log->l_mp, tic, &commit_iclog, 0);
- if (error || commit_lsn == -1)
+ if (commit_lsn == -1)
goto out_abort;
/* attach all the transactions w/ busy extents to iclog */
@@ -600,6 +601,8 @@ out_free_ticket:
kmem_free(new_ctx);
return 0;
+out_abort_free_ticket:
+ xfs_log_ticket_put(tic);
out_abort:
xlog_cil_committed(ctx, XFS_LI_ABORTED);
return XFS_ERROR(EIO);
@@ -622,7 +625,7 @@ out_abort:
* background commit, returns without it held once background commits are
* allowed again.
*/
-int
+void
xfs_log_commit_cil(
struct xfs_mount *mp,
struct xfs_trans *tp,
@@ -637,11 +640,6 @@ xfs_log_commit_cil(
if (flags & XFS_TRANS_RELEASE_LOG_RES)
log_flags = XFS_LOG_REL_PERM_RESERV;
- if (XLOG_FORCED_SHUTDOWN(log)) {
- xlog_cil_free_logvec(log_vector);
- return XFS_ERROR(EIO);
- }
-
/*
* do all the hard work of formatting items (including memory
* allocation) outside the CIL context lock. This prevents stalling CIL
@@ -701,7 +699,6 @@ xfs_log_commit_cil(
*/
if (push)
xlog_cil_push(log, 0);
- return 0;
}
/*
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 33dbc4e0ad62..76922793f64f 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1446,6 +1446,14 @@ xfs_log_item_batch_insert(
* Bulk operation version of xfs_trans_committed that takes a log vector of
* items to insert into the AIL. This uses bulk AIL insertion techniques to
* minimise lock traffic.
+ *
+ * If we are called with the aborted flag set, it is because a log write during
+ * a CIL checkpoint commit has failed. In this case, all the items in the
+ * checkpoint have already gone through IOP_COMMITED and IOP_UNLOCK, which
+ * means that checkpoint commit abort handling is treated exactly the same
+ * as an iclog write error even though we haven't started any IO yet. Hence in
+ * this case all we need to do is IOP_COMMITTED processing, followed by an
+ * IOP_UNPIN(aborted) call.
*/
void
xfs_trans_committed_bulk(
@@ -1472,6 +1480,16 @@ xfs_trans_committed_bulk(
if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0)
continue;
+ /*
+ * if we are aborting the operation, no point in inserting the
+ * object into the AIL as we are in a shutdown situation.
+ */
+ if (aborted) {
+ ASSERT(XFS_FORCED_SHUTDOWN(ailp->xa_mount));
+ IOP_UNPIN(lip, 1);
+ continue;
+ }
+
if (item_lsn != commit_lsn) {
/*
@@ -1503,20 +1521,24 @@ xfs_trans_committed_bulk(
}
/*
- * Called from the trans_commit code when we notice that
- * the filesystem is in the middle of a forced shutdown.
+ * Called from the trans_commit code when we notice that the filesystem is in
+ * the middle of a forced shutdown.
+ *
+ * When we are called here, we have already pinned all the items in the
+ * transaction. However, neither IOP_COMMITTING or IOP_UNLOCK has been called
+ * so we can simply walk the items in the transaction, unpin them with an abort
+ * flag and then free the items. Note that unpinning the items can result in
+ * them being freed immediately, so we need to use a safe list traversal method
+ * here.
*/
STATIC void
xfs_trans_uncommit(
struct xfs_trans *tp,
uint flags)
{
- struct xfs_log_item_desc *lidp;
+ struct xfs_log_item_desc *lidp, *n;
- list_for_each_entry(lidp, &tp->t_items, lid_trans) {
- /*
- * Unpin all but those that aren't dirty.
- */
+ list_for_each_entry_safe(lidp, n, &tp->t_items, lid_trans) {
if (lidp->lid_flags & XFS_LID_DIRTY)
IOP_UNPIN(lidp->lid_item, 1);
}
@@ -1733,7 +1755,6 @@ xfs_trans_commit_cil(
int flags)
{
struct xfs_log_vec *log_vector;
- int error;
/*
* Get each log item to allocate a vector structure for
@@ -1744,9 +1765,7 @@ xfs_trans_commit_cil(
if (!log_vector)
return ENOMEM;
- error = xfs_log_commit_cil(mp, tp, log_vector, commit_lsn, flags);
- if (error)
- return error;
+ xfs_log_commit_cil(mp, tp, log_vector, commit_lsn, flags);
current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
xfs_trans_free(tp);
generated by cgit v1.2.3-58-ga151 (git 2.39.0) at 2024-12-26 08:14:33 +0000