* [PATCH v3 001/114] nfsd: fix file access refcount leak when nfsd4_truncate fails
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 002/114] nfsd: Protect addition to the file_hashtbl Jeff Layton
` (112 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Christoph Hellwig
From: Christoph Hellwig <hch@infradead.org>
nfsd4_process_open2 will currently will get access to the file, and then
call nfsd4_truncate to (possibly) truncate it. If that operation fails
though, then the access references will never be released as the
nfs4_ol_stateid is never initialized.
Fix by moving the nfsd4_truncate call into nfs4_get_vfs_file, ensuring
that the refcounts are properly put if the truncate fails.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Signed-off-by: Christoph Hellwig <hch@infradead.org>
---
fs/nfsd/nfs4state.c | 62 ++++++++++++++++++++++++++---------------------------
1 file changed, 30 insertions(+), 32 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 8242385a249c..c473bd6d52c8 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3046,6 +3046,21 @@ static inline int nfs4_access_to_access(u32 nfs4_access)
return flags;
}
+static inline __be32
+nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh,
+ struct nfsd4_open *open)
+{
+ struct iattr iattr = {
+ .ia_valid = ATTR_SIZE,
+ .ia_size = 0,
+ };
+ if (!open->op_truncate)
+ return 0;
+ if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
+ return nfserr_inval;
+ return nfsd_setattr(rqstp, fh, &iattr, 0, (time_t)0);
+}
+
static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
struct svc_fh *cur_fh, struct nfsd4_open *open)
{
@@ -3057,53 +3072,39 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
status = nfsd_open(rqstp, cur_fh, S_IFREG, access,
&fp->fi_fds[oflag]);
if (status)
- return status;
+ goto out;
}
nfs4_file_get_access(fp, oflag);
+ status = nfsd4_truncate(rqstp, cur_fh, open);
+ if (status)
+ goto out_put_access;
+
return nfs_ok;
-}
-static inline __be32
-nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh,
- struct nfsd4_open *open)
-{
- struct iattr iattr = {
- .ia_valid = ATTR_SIZE,
- .ia_size = 0,
- };
- if (!open->op_truncate)
- return 0;
- if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE))
- return nfserr_inval;
- return nfsd_setattr(rqstp, fh, &iattr, 0, (time_t)0);
+out_put_access:
+ nfs4_file_put_access(fp, oflag);
+out:
+ return status;
}
static __be32
nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open)
{
u32 op_share_access = open->op_share_access;
- bool new_access;
__be32 status;
- new_access = !test_access(op_share_access, stp);
- if (new_access) {
+ if (!test_access(op_share_access, stp))
status = nfs4_get_vfs_file(rqstp, fp, cur_fh, open);
- if (status)
- return status;
- }
- status = nfsd4_truncate(rqstp, cur_fh, open);
- if (status) {
- if (new_access) {
- int oflag = nfs4_access_to_omode(op_share_access);
- nfs4_file_put_access(fp, oflag);
- }
+ else
+ status = nfsd4_truncate(rqstp, cur_fh, open);
+
+ if (status)
return status;
- }
+
/* remember the open */
set_access(op_share_access, stp);
set_deny(open->op_share_deny, stp);
-
return nfs_ok;
}
@@ -3354,9 +3355,6 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
status = nfs4_get_vfs_file(rqstp, fp, current_fh, open);
if (status)
goto out;
- status = nfsd4_truncate(rqstp, current_fh, open);
- if (status)
- goto out;
stp = open->op_stp;
open->op_stp = NULL;
init_open_stateid(stp, fp, open);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 002/114] nfsd: Protect addition to the file_hashtbl
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
2014-06-30 15:48 ` [PATCH v3 001/114] nfsd: fix file access refcount leak when nfsd4_truncate fails Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 20:28 ` J. Bruce Fields
2014-06-30 15:48 ` [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it Jeff Layton
` (111 subsequent siblings)
113 siblings, 1 reply; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Ensure that we only can have a single struct nfs4_file per inode
in the file_hashtbl and make addition atomic with respect to lookup.
To prevent an i_lock/state_lock inversion, change nfsd4_init_file to
use ihold instead if igrab. That's also more efficient anyway as we
definitely hold a reference to the inode at that point.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4state.c | 49 +++++++++++++++++++++++++++++++++++++------------
1 file changed, 37 insertions(+), 12 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c473bd6d52c8..29788fd0da24 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2611,17 +2611,18 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct inode *ino)
{
unsigned int hashval = file_hashval(ino);
+ lockdep_assert_held(&state_lock);
+
atomic_set(&fp->fi_ref, 1);
INIT_LIST_HEAD(&fp->fi_stateids);
INIT_LIST_HEAD(&fp->fi_delegations);
- fp->fi_inode = igrab(ino);
+ ihold(ino);
+ fp->fi_inode = ino;
fp->fi_had_conflict = false;
fp->fi_lease = NULL;
memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
memset(fp->fi_access, 0, sizeof(fp->fi_access));
- spin_lock(&state_lock);
hlist_add_head(&fp->fi_hash, &file_hashtbl[hashval]);
- spin_unlock(&state_lock);
}
void
@@ -2787,23 +2788,49 @@ find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
/* search file_hashtbl[] for file */
static struct nfs4_file *
-find_file(struct inode *ino)
+find_file_locked(struct inode *ino)
{
unsigned int hashval = file_hashval(ino);
struct nfs4_file *fp;
- spin_lock(&state_lock);
+ lockdep_assert_held(&state_lock);
+
hlist_for_each_entry(fp, &file_hashtbl[hashval], fi_hash) {
if (fp->fi_inode == ino) {
get_nfs4_file(fp);
- spin_unlock(&state_lock);
return fp;
}
}
- spin_unlock(&state_lock);
return NULL;
}
+static struct nfs4_file *
+find_file(struct inode *ino)
+{
+ struct nfs4_file *fp;
+
+ spin_lock(&state_lock);
+ fp = find_file_locked(ino);
+ spin_unlock(&state_lock);
+ return fp;
+}
+
+static struct nfs4_file *
+find_or_add_file(struct inode *ino, struct nfs4_file *new)
+{
+ struct nfs4_file *fp;
+
+ spin_lock(&state_lock);
+ fp = find_file_locked(ino);
+ if (fp == NULL) {
+ nfsd4_init_file(new, ino);
+ fp = new;
+ }
+ spin_unlock(&state_lock);
+
+ return fp;
+}
+
/*
* Called to check deny when READ with all zero stateid or
* WRITE with all zero or all one stateid
@@ -3325,21 +3352,19 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
* and check for delegations in the process of being recalled.
* If not found, create the nfs4_file struct
*/
- fp = find_file(ino);
- if (fp) {
+ fp = find_or_add_file(ino, open->op_file);
+ if (fp != open->op_file) {
if ((status = nfs4_check_open(fp, open, &stp)))
goto out;
status = nfs4_check_deleg(cl, open, &dp);
if (status)
goto out;
} else {
+ open->op_file = NULL;
status = nfserr_bad_stateid;
if (nfsd4_is_deleg_cur(open))
goto out;
status = nfserr_jukebox;
- fp = open->op_file;
- open->op_file = NULL;
- nfsd4_init_file(fp, ino);
}
/*
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* Re: [PATCH v3 002/114] nfsd: Protect addition to the file_hashtbl
2014-06-30 15:48 ` [PATCH v3 002/114] nfsd: Protect addition to the file_hashtbl Jeff Layton
@ 2014-06-30 20:28 ` J. Bruce Fields
2014-06-30 20:32 ` Jeff Layton
0 siblings, 1 reply; 151+ messages in thread
From: J. Bruce Fields @ 2014-06-30 20:28 UTC (permalink / raw)
To: Jeff Layton; +Cc: linux-nfs, Trond Myklebust
On Mon, Jun 30, 2014 at 11:48:31AM -0400, Jeff Layton wrote:
> From: Trond Myklebust <trond.myklebust@primarydata.com>
>
> Ensure that we only can have a single struct nfs4_file per inode
> in the file_hashtbl and make addition atomic with respect to lookup.
This changelog gives the impression it's a bugfix, and it isn't. I
understand it's tedious in this series, but really I think at a minimum
a changelog should always make it clear whether a patch is a bugfix or
not. Applying with changelog rewritten to:
Current code depends on the client_mutex to guarantee a single
struct nfs4_file per inode in the file_hashtbl and make addition
atomic with respect to lookup. Rely instead on the state_Lock,
to make it easier to stop taking the client_mutex here later.
...
--b.
>
> To prevent an i_lock/state_lock inversion, change nfsd4_init_file to
> use ihold instead if igrab. That's also more efficient anyway as we
> definitely hold a reference to the inode at that point.
>
> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
> Signed-off-by: Jeff Layton <jlayton@primarydata.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> ---
> fs/nfsd/nfs4state.c | 49 +++++++++++++++++++++++++++++++++++++------------
> 1 file changed, 37 insertions(+), 12 deletions(-)
>
> diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
> index c473bd6d52c8..29788fd0da24 100644
> --- a/fs/nfsd/nfs4state.c
> +++ b/fs/nfsd/nfs4state.c
> @@ -2611,17 +2611,18 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct inode *ino)
> {
> unsigned int hashval = file_hashval(ino);
>
> + lockdep_assert_held(&state_lock);
> +
> atomic_set(&fp->fi_ref, 1);
> INIT_LIST_HEAD(&fp->fi_stateids);
> INIT_LIST_HEAD(&fp->fi_delegations);
> - fp->fi_inode = igrab(ino);
> + ihold(ino);
> + fp->fi_inode = ino;
> fp->fi_had_conflict = false;
> fp->fi_lease = NULL;
> memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
> memset(fp->fi_access, 0, sizeof(fp->fi_access));
> - spin_lock(&state_lock);
> hlist_add_head(&fp->fi_hash, &file_hashtbl[hashval]);
> - spin_unlock(&state_lock);
> }
>
> void
> @@ -2787,23 +2788,49 @@ find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
>
> /* search file_hashtbl[] for file */
> static struct nfs4_file *
> -find_file(struct inode *ino)
> +find_file_locked(struct inode *ino)
> {
> unsigned int hashval = file_hashval(ino);
> struct nfs4_file *fp;
>
> - spin_lock(&state_lock);
> + lockdep_assert_held(&state_lock);
> +
> hlist_for_each_entry(fp, &file_hashtbl[hashval], fi_hash) {
> if (fp->fi_inode == ino) {
> get_nfs4_file(fp);
> - spin_unlock(&state_lock);
> return fp;
> }
> }
> - spin_unlock(&state_lock);
> return NULL;
> }
>
> +static struct nfs4_file *
> +find_file(struct inode *ino)
> +{
> + struct nfs4_file *fp;
> +
> + spin_lock(&state_lock);
> + fp = find_file_locked(ino);
> + spin_unlock(&state_lock);
> + return fp;
> +}
> +
> +static struct nfs4_file *
> +find_or_add_file(struct inode *ino, struct nfs4_file *new)
> +{
> + struct nfs4_file *fp;
> +
> + spin_lock(&state_lock);
> + fp = find_file_locked(ino);
> + if (fp == NULL) {
> + nfsd4_init_file(new, ino);
> + fp = new;
> + }
> + spin_unlock(&state_lock);
> +
> + return fp;
> +}
> +
> /*
> * Called to check deny when READ with all zero stateid or
> * WRITE with all zero or all one stateid
> @@ -3325,21 +3352,19 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
> * and check for delegations in the process of being recalled.
> * If not found, create the nfs4_file struct
> */
> - fp = find_file(ino);
> - if (fp) {
> + fp = find_or_add_file(ino, open->op_file);
> + if (fp != open->op_file) {
> if ((status = nfs4_check_open(fp, open, &stp)))
> goto out;
> status = nfs4_check_deleg(cl, open, &dp);
> if (status)
> goto out;
> } else {
> + open->op_file = NULL;
> status = nfserr_bad_stateid;
> if (nfsd4_is_deleg_cur(open))
> goto out;
> status = nfserr_jukebox;
> - fp = open->op_file;
> - open->op_file = NULL;
> - nfsd4_init_file(fp, ino);
> }
>
> /*
> --
> 1.9.3
>
^ permalink raw reply [flat|nested] 151+ messages in thread* Re: [PATCH v3 002/114] nfsd: Protect addition to the file_hashtbl
2014-06-30 20:28 ` J. Bruce Fields
@ 2014-06-30 20:32 ` Jeff Layton
0 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 20:32 UTC (permalink / raw)
To: J. Bruce Fields; +Cc: linux-nfs, Trond Myklebust
On Mon, 30 Jun 2014 16:28:19 -0400
"J. Bruce Fields" <bfields@fieldses.org> wrote:
> On Mon, Jun 30, 2014 at 11:48:31AM -0400, Jeff Layton wrote:
> > From: Trond Myklebust <trond.myklebust@primarydata.com>
> >
> > Ensure that we only can have a single struct nfs4_file per inode
> > in the file_hashtbl and make addition atomic with respect to lookup.
>
> This changelog gives the impression it's a bugfix, and it isn't. I
> understand it's tedious in this series, but really I think at a minimum
> a changelog should always make it clear whether a patch is a bugfix or
> not. Applying with changelog rewritten to:
>
> Current code depends on the client_mutex to guarantee a single
> struct nfs4_file per inode in the file_hashtbl and make addition
> atomic with respect to lookup. Rely instead on the state_Lock,
> to make it easier to stop taking the client_mutex here later.
> ...
>
> --b.
>
Thanks and sorry, it's definitely correct that it's not a bugfix wrt
the existing code. I thought I had updated that patch to spell it out,
but I guess I missed that one...
> >
> > To prevent an i_lock/state_lock inversion, change nfsd4_init_file to
> > use ihold instead if igrab. That's also more efficient anyway as we
> > definitely hold a reference to the inode at that point.
> >
> > Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
> > Signed-off-by: Jeff Layton <jlayton@primarydata.com>
> > Reviewed-by: Christoph Hellwig <hch@lst.de>
> > ---
> > fs/nfsd/nfs4state.c | 49 +++++++++++++++++++++++++++++++++++++------------
> > 1 file changed, 37 insertions(+), 12 deletions(-)
> >
> > diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
> > index c473bd6d52c8..29788fd0da24 100644
> > --- a/fs/nfsd/nfs4state.c
> > +++ b/fs/nfsd/nfs4state.c
> > @@ -2611,17 +2611,18 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct inode *ino)
> > {
> > unsigned int hashval = file_hashval(ino);
> >
> > + lockdep_assert_held(&state_lock);
> > +
> > atomic_set(&fp->fi_ref, 1);
> > INIT_LIST_HEAD(&fp->fi_stateids);
> > INIT_LIST_HEAD(&fp->fi_delegations);
> > - fp->fi_inode = igrab(ino);
> > + ihold(ino);
> > + fp->fi_inode = ino;
> > fp->fi_had_conflict = false;
> > fp->fi_lease = NULL;
> > memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
> > memset(fp->fi_access, 0, sizeof(fp->fi_access));
> > - spin_lock(&state_lock);
> > hlist_add_head(&fp->fi_hash, &file_hashtbl[hashval]);
> > - spin_unlock(&state_lock);
> > }
> >
> > void
> > @@ -2787,23 +2788,49 @@ find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
> >
> > /* search file_hashtbl[] for file */
> > static struct nfs4_file *
> > -find_file(struct inode *ino)
> > +find_file_locked(struct inode *ino)
> > {
> > unsigned int hashval = file_hashval(ino);
> > struct nfs4_file *fp;
> >
> > - spin_lock(&state_lock);
> > + lockdep_assert_held(&state_lock);
> > +
> > hlist_for_each_entry(fp, &file_hashtbl[hashval], fi_hash) {
> > if (fp->fi_inode == ino) {
> > get_nfs4_file(fp);
> > - spin_unlock(&state_lock);
> > return fp;
> > }
> > }
> > - spin_unlock(&state_lock);
> > return NULL;
> > }
> >
> > +static struct nfs4_file *
> > +find_file(struct inode *ino)
> > +{
> > + struct nfs4_file *fp;
> > +
> > + spin_lock(&state_lock);
> > + fp = find_file_locked(ino);
> > + spin_unlock(&state_lock);
> > + return fp;
> > +}
> > +
> > +static struct nfs4_file *
> > +find_or_add_file(struct inode *ino, struct nfs4_file *new)
> > +{
> > + struct nfs4_file *fp;
> > +
> > + spin_lock(&state_lock);
> > + fp = find_file_locked(ino);
> > + if (fp == NULL) {
> > + nfsd4_init_file(new, ino);
> > + fp = new;
> > + }
> > + spin_unlock(&state_lock);
> > +
> > + return fp;
> > +}
> > +
> > /*
> > * Called to check deny when READ with all zero stateid or
> > * WRITE with all zero or all one stateid
> > @@ -3325,21 +3352,19 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
> > * and check for delegations in the process of being recalled.
> > * If not found, create the nfs4_file struct
> > */
> > - fp = find_file(ino);
> > - if (fp) {
> > + fp = find_or_add_file(ino, open->op_file);
> > + if (fp != open->op_file) {
> > if ((status = nfs4_check_open(fp, open, &stp)))
> > goto out;
> > status = nfs4_check_deleg(cl, open, &dp);
> > if (status)
> > goto out;
> > } else {
> > + open->op_file = NULL;
> > status = nfserr_bad_stateid;
> > if (nfsd4_is_deleg_cur(open))
> > goto out;
> > status = nfserr_jukebox;
> > - fp = open->op_file;
> > - open->op_file = NULL;
> > - nfsd4_init_file(fp, ino);
> > }
> >
> > /*
> > --
> > 1.9.3
> >
--
Jeff Layton <jlayton@primarydata.com>
^ permalink raw reply [flat|nested] 151+ messages in thread
* [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
2014-06-30 15:48 ` [PATCH v3 001/114] nfsd: fix file access refcount leak when nfsd4_truncate fails Jeff Layton
2014-06-30 15:48 ` [PATCH v3 002/114] nfsd: Protect addition to the file_hashtbl Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-07-08 21:11 ` J. Bruce Fields
2014-06-30 15:48 ` [PATCH v3 004/114] nfsd: Avoid taking state_lock while holding inode lock in nfsd_break_one_deleg Jeff Layton
` (110 subsequent siblings)
113 siblings, 1 reply; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
There's a fair chance we won't ever need this work struct, so we might
as well delay initializing it until just before we're going to use it.
In a later patch, we'll need to intialize the work with a different
function for delegation callbacks. By delaying this, we avoid having
to do it twice.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4callback.c | 10 +++++-----
fs/nfsd/nfs4state.c | 2 --
fs/nfsd/state.h | 1 -
3 files changed, 5 insertions(+), 8 deletions(-)
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 2c73cae9899d..00cb9b7a75f6 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -43,6 +43,7 @@
#define NFSDDBG_FACILITY NFSDDBG_PROC
static void nfsd4_mark_cb_fault(struct nfs4_client *, int reason);
+static void nfsd4_do_callback_rpc(struct work_struct *w);
#define NFSPROC4_CB_NULL 0
#define NFSPROC4_CB_COMPOUND 1
@@ -763,6 +764,8 @@ static void do_probe_callback(struct nfs4_client *clp)
cb->cb_ops = &nfsd4_cb_probe_ops;
+ INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
+
run_nfsd4_cb(cb);
}
@@ -1031,11 +1034,6 @@ static void nfsd4_do_callback_rpc(struct work_struct *w)
cb->cb_ops, cb);
}
-void nfsd4_init_callback(struct nfsd4_callback *cb)
-{
- INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
-}
-
void nfsd4_cb_recall(struct nfs4_delegation *dp)
{
struct nfsd4_callback *cb = &dp->dl_recall;
@@ -1053,5 +1051,7 @@ void nfsd4_cb_recall(struct nfs4_delegation *dp)
INIT_LIST_HEAD(&cb->cb_per_client);
cb->cb_done = true;
+ INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
+
run_nfsd4_cb(&dp->dl_recall);
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 29788fd0da24..b49b46b0ce23 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -466,7 +466,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle);
dp->dl_time = 0;
atomic_set(&dp->dl_count, 1);
- nfsd4_init_callback(&dp->dl_recall);
return dp;
}
@@ -1472,7 +1471,6 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
spin_unlock(&nn->client_lock);
return NULL;
}
- nfsd4_init_callback(&clp->cl_cb_null);
clp->cl_time = get_seconds();
clear_bit(0, &clp->cl_cb_slot_busy);
copy_verf(clp, verf);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 374c66283ac5..9447f86f2778 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -464,7 +464,6 @@ extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
struct nfsd_net *nn);
extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions, struct nfsd_net *nn);
extern int set_callback_cred(void);
-extern void nfsd4_init_callback(struct nfsd4_callback *);
extern void nfsd4_probe_callback(struct nfs4_client *clp);
extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* Re: [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it
2014-06-30 15:48 ` [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it Jeff Layton
@ 2014-07-08 21:11 ` J. Bruce Fields
2014-07-08 23:32 ` Jeff Layton
2014-07-09 8:21 ` Christoph Hellwig
0 siblings, 2 replies; 151+ messages in thread
From: J. Bruce Fields @ 2014-07-08 21:11 UTC (permalink / raw)
To: Jeff Layton; +Cc: linux-nfs
On Mon, Jun 30, 2014 at 11:48:32AM -0400, Jeff Layton wrote:
> There's a fair chance we won't ever need this work struct, so we might
> as well delay initializing it until just before we're going to use it.
> In a later patch, we'll need to intialize the work with a different
> function for delegation callbacks. By delaying this, we avoid having
> to do it twice.
When I run
./nfs4.1/testserver.py f19:/exports/xfs/FUBAR --maketree --rundeps COMP1
I get crashes like:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
IP: [<ffffffff810890b1>] process_one_work+0x31/0x500
PGD 0
Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
Modules linked in: nfsd auth_rpcgss oid_registry nfs_acl lockd sunrpc
CPU: 2 PID: 30 Comm: kworker/u8:1 Not tainted 3.16.0-rc2-00023-g30c1d16 #3051
Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
task: ffff88003d9cc810 ti: ffff88003d9d0000 task.ti: ffff88003d9d0000
RIP: 0010:[<ffffffff810890b1>] [<ffffffff810890b1>] process_one_work+0x31/0x500
RSP: 0018:ffff88003d9d3d68 EFLAGS: 00010046
RAX: 0000000000000100 RBX: ffff88003d9caf80 RCX: dead000000200200
RDX: 0000000000000100 RSI: ffff880031429b38 RDI: ffff88003d9caf80
RBP: ffff88003d9d3dd8 R08: ffff88003dcb7800 R09: 0000000001c40000
R10: 0000000000000000 R11: 000000000006b5b0 R12: ffff88003dcb7800
R13: 0000000000000000 R14: ffff880031429b38 R15: ffff88003d9caf80
FS: 0000000000000000(0000) GS:ffff88003fb00000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
CR2: 0000000000000138 CR3: 0000000027744000 CR4: 00000000000006e0
Stack:
000000003d9d3d88 ffff88003dcb7818 ffff88003d9cafb0 ffff88003dcb7800
ffff88003dcb7800 ffff88003dcb7800 ffff88003dcb7800 ffff88003d9cafb0
ffff88003d9d3dd8 ffff88003dcb7800 ffff88003dcb7848 ffff88003d9cafb0
Call Trace:
[<ffffffff81089b9b>] worker_thread+0x11b/0x4f0
[<ffffffff81089a80>] ? init_pwq+0x190/0x190
[<ffffffff81090ac4>] kthread+0xe4/0x100
[<ffffffff810909e0>] ? __init_kthread_worker+0x70/0x70
[<ffffffff81a4ca2c>] ret_from_fork+0x7c/0xb0
[<ffffffff810909e0>] ? __init_kthread_worker+0x70/0x70
Code: 48 89 e5 41 57 41 56 49 89 f6 41 55 45 31 ed 41 54 53 48 89 fb 48 83 ec 48 48 8b 06 4c 8b 67 48 48 89 c2 30 d2 a8 04 4c 0f 45 ea <49> 8b 45 08 48 c7 45 b8 00 00 00 00 48 c7 45 c0 00 00 00 00 8b
RIP [<ffffffff810890b1>] process_one_work+0x31/0x500
RSP <ffff88003d9d3d68>
CR2: 0000000000000008
and I'm suspicious of this:
> @@ -763,6 +764,8 @@ static void do_probe_callback(struct nfs4_client *clp)
>
> cb->cb_ops = &nfsd4_cb_probe_ops;
>
> + INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
> +
> run_nfsd4_cb(cb);
> }
This is called all over the place, possibly multiple times on the same
client, so we're calling INIT_WORK on something that may already be in
use--I doubt that's safe.
I'm backing out this patch for now.
--b.
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it
2014-07-08 21:11 ` J. Bruce Fields
@ 2014-07-08 23:32 ` Jeff Layton
2014-07-09 8:21 ` Christoph Hellwig
1 sibling, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-07-08 23:32 UTC (permalink / raw)
To: J. Bruce Fields; +Cc: linux-nfs, Christoph Hellwig
On Tue, 8 Jul 2014 17:11:34 -0400
"J. Bruce Fields" <bfields@fieldses.org> wrote:
> On Mon, Jun 30, 2014 at 11:48:32AM -0400, Jeff Layton wrote:
> > There's a fair chance we won't ever need this work struct, so we might
> > as well delay initializing it until just before we're going to use it.
> > In a later patch, we'll need to intialize the work with a different
> > function for delegation callbacks. By delaying this, we avoid having
> > to do it twice.
>
> When I run
>
> ./nfs4.1/testserver.py f19:/exports/xfs/FUBAR --maketree --rundeps COMP1
>
> I get crashes like:
>
> BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
> IP: [<ffffffff810890b1>] process_one_work+0x31/0x500
> PGD 0
> Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
> Modules linked in: nfsd auth_rpcgss oid_registry nfs_acl lockd sunrpc
> CPU: 2 PID: 30 Comm: kworker/u8:1 Not tainted 3.16.0-rc2-00023-g30c1d16 #3051
> Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
> task: ffff88003d9cc810 ti: ffff88003d9d0000 task.ti: ffff88003d9d0000
> RIP: 0010:[<ffffffff810890b1>] [<ffffffff810890b1>] process_one_work+0x31/0x500
> RSP: 0018:ffff88003d9d3d68 EFLAGS: 00010046
> RAX: 0000000000000100 RBX: ffff88003d9caf80 RCX: dead000000200200
> RDX: 0000000000000100 RSI: ffff880031429b38 RDI: ffff88003d9caf80
> RBP: ffff88003d9d3dd8 R08: ffff88003dcb7800 R09: 0000000001c40000
> R10: 0000000000000000 R11: 000000000006b5b0 R12: ffff88003dcb7800
> R13: 0000000000000000 R14: ffff880031429b38 R15: ffff88003d9caf80
> FS: 0000000000000000(0000) GS:ffff88003fb00000(0000) knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
> CR2: 0000000000000138 CR3: 0000000027744000 CR4: 00000000000006e0
> Stack:
> 000000003d9d3d88 ffff88003dcb7818 ffff88003d9cafb0 ffff88003dcb7800
> ffff88003dcb7800 ffff88003dcb7800 ffff88003dcb7800 ffff88003d9cafb0
> ffff88003d9d3dd8 ffff88003dcb7800 ffff88003dcb7848 ffff88003d9cafb0
> Call Trace:
> [<ffffffff81089b9b>] worker_thread+0x11b/0x4f0
> [<ffffffff81089a80>] ? init_pwq+0x190/0x190
> [<ffffffff81090ac4>] kthread+0xe4/0x100
> [<ffffffff810909e0>] ? __init_kthread_worker+0x70/0x70
> [<ffffffff81a4ca2c>] ret_from_fork+0x7c/0xb0
> [<ffffffff810909e0>] ? __init_kthread_worker+0x70/0x70
> Code: 48 89 e5 41 57 41 56 49 89 f6 41 55 45 31 ed 41 54 53 48 89 fb 48 83 ec 48 48 8b 06 4c 8b 67 48 48 89 c2 30 d2 a8 04 4c 0f 45 ea <49> 8b 45 08 48 c7 45 b8 00 00 00 00 48 c7 45 c0 00 00 00 00 8b
> RIP [<ffffffff810890b1>] process_one_work+0x31/0x500
> RSP <ffff88003d9d3d68>
> CR2: 0000000000000008
>
> and I'm suspicious of this:
>
> > @@ -763,6 +764,8 @@ static void do_probe_callback(struct nfs4_client *clp)
> >
> > cb->cb_ops = &nfsd4_cb_probe_ops;
> >
> > + INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
> > +
> > run_nfsd4_cb(cb);
> > }
>
> This is called all over the place, possibly multiple times on the same
> client, so we're calling INIT_WORK on something that may already be in
> use--I doubt that's safe.
>
Doh! That makes total sense, and yes it would almost certainly wreak
havoc to reinitialize a workqueue job that has already been queued.
> I'm backing out this patch for now.
>
Yes, please do. Christoph, I think we'll just have to live with the
double initialization here.
Cheers,
--
Jeff Layton <jlayton@primarydata.com>
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it
2014-07-08 21:11 ` J. Bruce Fields
2014-07-08 23:32 ` Jeff Layton
@ 2014-07-09 8:21 ` Christoph Hellwig
2014-07-09 19:41 ` J. Bruce Fields
1 sibling, 1 reply; 151+ messages in thread
From: Christoph Hellwig @ 2014-07-09 8:21 UTC (permalink / raw)
To: J. Bruce Fields; +Cc: Jeff Layton, linux-nfs
On Tue, Jul 08, 2014 at 05:11:34PM -0400, J. Bruce Fields wrote:
> BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
> IP: [<ffffffff810890b1>] process_one_work+0x31/0x500
> PGD 0
> Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
> Modules linked in: nfsd auth_rpcgss oid_registry nfs_acl lockd sunrpc
> CPU: 2 PID: 30 Comm: kworker/u8:1 Not tainted 3.16.0-rc2-00023-g30c1d16 #3051
> Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
> task: ffff88003d9cc810 ti: ffff88003d9d0000 task.ti: ffff88003d9d0000
> RIP: 0010:[<ffffffff810890b1>] [<ffffffff810890b1>] process_one_work+0x31/0x500
> RSP: 0018:ffff88003d9d3d68 EFLAGS: 00010046
> RAX: 0000000000000100 RBX: ffff88003d9caf80 RCX: dead000000200200
> RDX: 0000000000000100 RSI: ffff880031429b38 RDI: ffff88003d9caf80
> RBP: ffff88003d9d3dd8 R08: ffff88003dcb7800 R09: 0000000001c40000
> R10: 0000000000000000 R11: 000000000006b5b0 R12: ffff88003dcb7800
> R13: 0000000000000000 R14: ffff880031429b38 R15: ffff88003d9caf80
> FS: 0000000000000000(0000) GS:ffff88003fb00000(0000) knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
> CR2: 0000000000000138 CR3: 0000000027744000 CR4: 00000000000006e0
> Stack:
> 000000003d9d3d88 ffff88003dcb7818 ffff88003d9cafb0 ffff88003dcb7800
> ffff88003dcb7800 ffff88003dcb7800 ffff88003dcb7800 ffff88003d9cafb0
> ffff88003d9d3dd8 ffff88003dcb7800 ffff88003dcb7848 ffff88003d9cafb0
> Call Trace:
> [<ffffffff81089b9b>] worker_thread+0x11b/0x4f0
> [<ffffffff81089a80>] ? init_pwq+0x190/0x190
> [<ffffffff81090ac4>] kthread+0xe4/0x100
> [<ffffffff810909e0>] ? __init_kthread_worker+0x70/0x70
> [<ffffffff81a4ca2c>] ret_from_fork+0x7c/0xb0
> [<ffffffff810909e0>] ? __init_kthread_worker+0x70/0x70
> Code: 48 89 e5 41 57 41 56 49 89 f6 41 55 45 31 ed 41 54 53 48 89 fb 48 83 ec 48 48 8b 06 4c 8b 67 48 48 89 c2 30 d2 a8 04 4c 0f 45 ea <49> 8b 45 08 48 c7 45 b8 00 00 00 00 48 c7 45 c0 00 00 00 00 8b
> RIP [<ffffffff810890b1>] process_one_work+0x31/0x500
> RSP <ffff88003d9d3d68>
> CR2: 0000000000000008
>
> and I'm suspicious of this:
>
> > @@ -763,6 +764,8 @@ static void do_probe_callback(struct nfs4_client *clp)
> >
> > cb->cb_ops = &nfsd4_cb_probe_ops;
> >
> > + INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
> > +
> > run_nfsd4_cb(cb);
> > }
>
> This is called all over the place, possibly multiple times on the same
> client, so we're calling INIT_WORK on something that may already be in
> use--I doubt that's safe.
>
> I'm backing out this patch for now.
If that's the case all of do_probe_callback seems very fishy to me, as
it scrambles all over the callback structure. I guess we need to move
more of it to an init function then, and have different init functions
for the different callbacks.
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it
2014-07-09 8:21 ` Christoph Hellwig
@ 2014-07-09 19:41 ` J. Bruce Fields
2014-07-09 20:37 ` Jeff Layton
0 siblings, 1 reply; 151+ messages in thread
From: J. Bruce Fields @ 2014-07-09 19:41 UTC (permalink / raw)
To: Christoph Hellwig; +Cc: Jeff Layton, linux-nfs
On Wed, Jul 09, 2014 at 01:21:21AM -0700, Christoph Hellwig wrote:
> On Tue, Jul 08, 2014 at 05:11:34PM -0400, J. Bruce Fields wrote:
> > BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
> > IP: [<ffffffff810890b1>] process_one_work+0x31/0x500
> > PGD 0
> > Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
> > Modules linked in: nfsd auth_rpcgss oid_registry nfs_acl lockd sunrpc
> > CPU: 2 PID: 30 Comm: kworker/u8:1 Not tainted 3.16.0-rc2-00023-g30c1d16 #3051
> > Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
> > task: ffff88003d9cc810 ti: ffff88003d9d0000 task.ti: ffff88003d9d0000
> > RIP: 0010:[<ffffffff810890b1>] [<ffffffff810890b1>] process_one_work+0x31/0x500
> > RSP: 0018:ffff88003d9d3d68 EFLAGS: 00010046
> > RAX: 0000000000000100 RBX: ffff88003d9caf80 RCX: dead000000200200
> > RDX: 0000000000000100 RSI: ffff880031429b38 RDI: ffff88003d9caf80
> > RBP: ffff88003d9d3dd8 R08: ffff88003dcb7800 R09: 0000000001c40000
> > R10: 0000000000000000 R11: 000000000006b5b0 R12: ffff88003dcb7800
> > R13: 0000000000000000 R14: ffff880031429b38 R15: ffff88003d9caf80
> > FS: 0000000000000000(0000) GS:ffff88003fb00000(0000) knlGS:0000000000000000
> > CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
> > CR2: 0000000000000138 CR3: 0000000027744000 CR4: 00000000000006e0
> > Stack:
> > 000000003d9d3d88 ffff88003dcb7818 ffff88003d9cafb0 ffff88003dcb7800
> > ffff88003dcb7800 ffff88003dcb7800 ffff88003dcb7800 ffff88003d9cafb0
> > ffff88003d9d3dd8 ffff88003dcb7800 ffff88003dcb7848 ffff88003d9cafb0
> > Call Trace:
> > [<ffffffff81089b9b>] worker_thread+0x11b/0x4f0
> > [<ffffffff81089a80>] ? init_pwq+0x190/0x190
> > [<ffffffff81090ac4>] kthread+0xe4/0x100
> > [<ffffffff810909e0>] ? __init_kthread_worker+0x70/0x70
> > [<ffffffff81a4ca2c>] ret_from_fork+0x7c/0xb0
> > [<ffffffff810909e0>] ? __init_kthread_worker+0x70/0x70
> > Code: 48 89 e5 41 57 41 56 49 89 f6 41 55 45 31 ed 41 54 53 48 89 fb 48 83 ec 48 48 8b 06 4c 8b 67 48 48 89 c2 30 d2 a8 04 4c 0f 45 ea <49> 8b 45 08 48 c7 45 b8 00 00 00 00 48 c7 45 c0 00 00 00 00 8b
> > RIP [<ffffffff810890b1>] process_one_work+0x31/0x500
> > RSP <ffff88003d9d3d68>
> > CR2: 0000000000000008
> >
> > and I'm suspicious of this:
> >
> > > @@ -763,6 +764,8 @@ static void do_probe_callback(struct nfs4_client *clp)
> > >
> > > cb->cb_ops = &nfsd4_cb_probe_ops;
> > >
> > > + INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
> > > +
> > > run_nfsd4_cb(cb);
> > > }
> >
> > This is called all over the place, possibly multiple times on the same
> > client, so we're calling INIT_WORK on something that may already be in
> > use--I doubt that's safe.
> >
> > I'm backing out this patch for now.
>
> If that's the case all of do_probe_callback seems very fishy to me, as
> it scrambles all over the callback structure. I guess we need to move
> more of it to an init function then, and have different init functions
> for the different callbacks.
Taking a look.... It does look fishy, but those fields are constant, so
I don't see a bug.
In delegation recall case (nfsd4_cb_recall()) those fields aren't
constant, but we guarantee it's only called once.
--b.
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it
2014-07-09 19:41 ` J. Bruce Fields
@ 2014-07-09 20:37 ` Jeff Layton
2014-07-09 20:51 ` J. Bruce Fields
` (2 more replies)
0 siblings, 3 replies; 151+ messages in thread
From: Jeff Layton @ 2014-07-09 20:37 UTC (permalink / raw)
To: J. Bruce Fields; +Cc: Christoph Hellwig, linux-nfs
On Wed, 9 Jul 2014 15:41:14 -0400
"J. Bruce Fields" <bfields@fieldses.org> wrote:
> On Wed, Jul 09, 2014 at 01:21:21AM -0700, Christoph Hellwig wrote:
> > On Tue, Jul 08, 2014 at 05:11:34PM -0400, J. Bruce Fields wrote:
> > > BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
> > > IP: [<ffffffff810890b1>] process_one_work+0x31/0x500
> > > PGD 0
> > > Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
> > > Modules linked in: nfsd auth_rpcgss oid_registry nfs_acl lockd sunrpc
> > > CPU: 2 PID: 30 Comm: kworker/u8:1 Not tainted 3.16.0-rc2-00023-g30c1d16 #3051
> > > Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
> > > task: ffff88003d9cc810 ti: ffff88003d9d0000 task.ti: ffff88003d9d0000
> > > RIP: 0010:[<ffffffff810890b1>] [<ffffffff810890b1>] process_one_work+0x31/0x500
> > > RSP: 0018:ffff88003d9d3d68 EFLAGS: 00010046
> > > RAX: 0000000000000100 RBX: ffff88003d9caf80 RCX: dead000000200200
> > > RDX: 0000000000000100 RSI: ffff880031429b38 RDI: ffff88003d9caf80
> > > RBP: ffff88003d9d3dd8 R08: ffff88003dcb7800 R09: 0000000001c40000
> > > R10: 0000000000000000 R11: 000000000006b5b0 R12: ffff88003dcb7800
> > > R13: 0000000000000000 R14: ffff880031429b38 R15: ffff88003d9caf80
> > > FS: 0000000000000000(0000) GS:ffff88003fb00000(0000) knlGS:0000000000000000
> > > CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
> > > CR2: 0000000000000138 CR3: 0000000027744000 CR4: 00000000000006e0
> > > Stack:
> > > 000000003d9d3d88 ffff88003dcb7818 ffff88003d9cafb0 ffff88003dcb7800
> > > ffff88003dcb7800 ffff88003dcb7800 ffff88003dcb7800 ffff88003d9cafb0
> > > ffff88003d9d3dd8 ffff88003dcb7800 ffff88003dcb7848 ffff88003d9cafb0
> > > Call Trace:
> > > [<ffffffff81089b9b>] worker_thread+0x11b/0x4f0
> > > [<ffffffff81089a80>] ? init_pwq+0x190/0x190
> > > [<ffffffff81090ac4>] kthread+0xe4/0x100
> > > [<ffffffff810909e0>] ? __init_kthread_worker+0x70/0x70
> > > [<ffffffff81a4ca2c>] ret_from_fork+0x7c/0xb0
> > > [<ffffffff810909e0>] ? __init_kthread_worker+0x70/0x70
> > > Code: 48 89 e5 41 57 41 56 49 89 f6 41 55 45 31 ed 41 54 53 48 89 fb 48 83 ec 48 48 8b 06 4c 8b 67 48 48 89 c2 30 d2 a8 04 4c 0f 45 ea <49> 8b 45 08 48 c7 45 b8 00 00 00 00 48 c7 45 c0 00 00 00 00 8b
> > > RIP [<ffffffff810890b1>] process_one_work+0x31/0x500
> > > RSP <ffff88003d9d3d68>
> > > CR2: 0000000000000008
> > >
> > > and I'm suspicious of this:
> > >
> > > > @@ -763,6 +764,8 @@ static void do_probe_callback(struct nfs4_client *clp)
> > > >
> > > > cb->cb_ops = &nfsd4_cb_probe_ops;
> > > >
> > > > + INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
> > > > +
> > > > run_nfsd4_cb(cb);
> > > > }
> > >
> > > This is called all over the place, possibly multiple times on the same
> > > client, so we're calling INIT_WORK on something that may already be in
> > > use--I doubt that's safe.
> > >
> > > I'm backing out this patch for now.
> >
> > If that's the case all of do_probe_callback seems very fishy to me, as
> > it scrambles all over the callback structure. I guess we need to move
> > more of it to an init function then, and have different init functions
> > for the different callbacks.
>
> Taking a look.... It does look fishy, but those fields are constant, so
> I don't see a bug.
>
> In delegation recall case (nfsd4_cb_recall()) those fields aren't
> constant, but we guarantee it's only called once.
>
Yes. I'm inclined to leave well enough alone on this and to leave any
cleanup in this area to Christoph since he said he was overhauling that
code anyway.
I didn't see where you had reverted the patch in your repo, so I went
ahead and did it and then rebased the series on top of the revert.
There were some merge conflicts, but I at least was able to get rid of
the double INIT_WORK calls in the case of a delegation (and do some
related cleanup in this area):
http://git.samba.org/?p=jlayton/linux.git;a=commitdiff;h=60b61375d6a84e74bf1c3c7c230712721e14773d
http://git.samba.org/?p=jlayton/linux.git;a=commitdiff;h=491192c3e6f0966722c34ba36adfde7575640544
Unfortunately there are a few (fairly trivial) merge conflicts later in
the series due to this change. Bruce, do you want me to repost the
whole set, or would you rather just cherry-pick them from my updated
branch?
--
Jeff Layton <jlayton@primarydata.com>
^ permalink raw reply [flat|nested] 151+ messages in thread* Re: [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it
2014-07-09 20:37 ` Jeff Layton
@ 2014-07-09 20:51 ` J. Bruce Fields
2014-07-10 7:40 ` Christoph Hellwig
2014-07-10 10:53 ` Christoph Hellwig
2 siblings, 0 replies; 151+ messages in thread
From: J. Bruce Fields @ 2014-07-09 20:51 UTC (permalink / raw)
To: Jeff Layton; +Cc: Christoph Hellwig, linux-nfs
On Wed, Jul 09, 2014 at 04:37:44PM -0400, Jeff Layton wrote:
> On Wed, 9 Jul 2014 15:41:14 -0400
> "J. Bruce Fields" <bfields@fieldses.org> wrote:
>
> > On Wed, Jul 09, 2014 at 01:21:21AM -0700, Christoph Hellwig wrote:
> > > On Tue, Jul 08, 2014 at 05:11:34PM -0400, J. Bruce Fields wrote:
> > > > BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
> > > > IP: [<ffffffff810890b1>] process_one_work+0x31/0x500
> > > > PGD 0
> > > > Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC
> > > > Modules linked in: nfsd auth_rpcgss oid_registry nfs_acl lockd sunrpc
> > > > CPU: 2 PID: 30 Comm: kworker/u8:1 Not tainted 3.16.0-rc2-00023-g30c1d16 #3051
> > > > Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011
> > > > task: ffff88003d9cc810 ti: ffff88003d9d0000 task.ti: ffff88003d9d0000
> > > > RIP: 0010:[<ffffffff810890b1>] [<ffffffff810890b1>] process_one_work+0x31/0x500
> > > > RSP: 0018:ffff88003d9d3d68 EFLAGS: 00010046
> > > > RAX: 0000000000000100 RBX: ffff88003d9caf80 RCX: dead000000200200
> > > > RDX: 0000000000000100 RSI: ffff880031429b38 RDI: ffff88003d9caf80
> > > > RBP: ffff88003d9d3dd8 R08: ffff88003dcb7800 R09: 0000000001c40000
> > > > R10: 0000000000000000 R11: 000000000006b5b0 R12: ffff88003dcb7800
> > > > R13: 0000000000000000 R14: ffff880031429b38 R15: ffff88003d9caf80
> > > > FS: 0000000000000000(0000) GS:ffff88003fb00000(0000) knlGS:0000000000000000
> > > > CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b
> > > > CR2: 0000000000000138 CR3: 0000000027744000 CR4: 00000000000006e0
> > > > Stack:
> > > > 000000003d9d3d88 ffff88003dcb7818 ffff88003d9cafb0 ffff88003dcb7800
> > > > ffff88003dcb7800 ffff88003dcb7800 ffff88003dcb7800 ffff88003d9cafb0
> > > > ffff88003d9d3dd8 ffff88003dcb7800 ffff88003dcb7848 ffff88003d9cafb0
> > > > Call Trace:
> > > > [<ffffffff81089b9b>] worker_thread+0x11b/0x4f0
> > > > [<ffffffff81089a80>] ? init_pwq+0x190/0x190
> > > > [<ffffffff81090ac4>] kthread+0xe4/0x100
> > > > [<ffffffff810909e0>] ? __init_kthread_worker+0x70/0x70
> > > > [<ffffffff81a4ca2c>] ret_from_fork+0x7c/0xb0
> > > > [<ffffffff810909e0>] ? __init_kthread_worker+0x70/0x70
> > > > Code: 48 89 e5 41 57 41 56 49 89 f6 41 55 45 31 ed 41 54 53 48 89 fb 48 83 ec 48 48 8b 06 4c 8b 67 48 48 89 c2 30 d2 a8 04 4c 0f 45 ea <49> 8b 45 08 48 c7 45 b8 00 00 00 00 48 c7 45 c0 00 00 00 00 8b
> > > > RIP [<ffffffff810890b1>] process_one_work+0x31/0x500
> > > > RSP <ffff88003d9d3d68>
> > > > CR2: 0000000000000008
> > > >
> > > > and I'm suspicious of this:
> > > >
> > > > > @@ -763,6 +764,8 @@ static void do_probe_callback(struct nfs4_client *clp)
> > > > >
> > > > > cb->cb_ops = &nfsd4_cb_probe_ops;
> > > > >
> > > > > + INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
> > > > > +
> > > > > run_nfsd4_cb(cb);
> > > > > }
> > > >
> > > > This is called all over the place, possibly multiple times on the same
> > > > client, so we're calling INIT_WORK on something that may already be in
> > > > use--I doubt that's safe.
> > > >
> > > > I'm backing out this patch for now.
> > >
> > > If that's the case all of do_probe_callback seems very fishy to me, as
> > > it scrambles all over the callback structure. I guess we need to move
> > > more of it to an init function then, and have different init functions
> > > for the different callbacks.
> >
> > Taking a look.... It does look fishy, but those fields are constant, so
> > I don't see a bug.
> >
> > In delegation recall case (nfsd4_cb_recall()) those fields aren't
> > constant, but we guarantee it's only called once.
> >
>
> Yes. I'm inclined to leave well enough alone on this and to leave any
> cleanup in this area to Christoph since he said he was overhauling that
> code anyway.
>
> I didn't see where you had reverted the patch in your repo,
Yeah, reverted locally but I had a testing problem that's kept me from
pushing it out yet.
> so I went
> ahead and did it and then rebased the series on top of the revert.
> There were some merge conflicts, but I at least was able to get rid of
> the double INIT_WORK calls in the case of a delegation (and do some
> related cleanup in this area):
>
> http://git.samba.org/?p=jlayton/linux.git;a=commitdiff;h=60b61375d6a84e74bf1c3c7c230712721e14773d
> http://git.samba.org/?p=jlayton/linux.git;a=commitdiff;h=491192c3e6f0966722c34ba36adfde7575640544
>
> Unfortunately there are a few (fairly trivial) merge conflicts later in
> the series due to this change. Bruce, do you want me to repost the
> whole set, or would you rather just cherry-pick them from my updated
> branch?
Let's spare everyone a reposting and I'll see how far I can get with
fixing up the conflicts myself and/or cherry-picking from your updated
branch.
--b.
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it
2014-07-09 20:37 ` Jeff Layton
2014-07-09 20:51 ` J. Bruce Fields
@ 2014-07-10 7:40 ` Christoph Hellwig
2014-07-10 10:53 ` Christoph Hellwig
2 siblings, 0 replies; 151+ messages in thread
From: Christoph Hellwig @ 2014-07-10 7:40 UTC (permalink / raw)
To: Jeff Layton; +Cc: J. Bruce Fields, Christoph Hellwig, linux-nfs
On Wed, Jul 09, 2014 at 04:37:44PM -0400, Jeff Layton wrote:
> I didn't see where you had reverted the patch in your repo, so I went
> ahead and did it and then rebased the series on top of the revert.
> There were some merge conflicts, but I at least was able to get rid of
> the double INIT_WORK calls in the case of a delegation (and do some
> related cleanup in this area):
This looks reasonable to me.
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it
2014-07-09 20:37 ` Jeff Layton
2014-07-09 20:51 ` J. Bruce Fields
2014-07-10 7:40 ` Christoph Hellwig
@ 2014-07-10 10:53 ` Christoph Hellwig
2014-07-10 13:23 ` Jeff Layton
2 siblings, 1 reply; 151+ messages in thread
From: Christoph Hellwig @ 2014-07-10 10:53 UTC (permalink / raw)
To: Jeff Layton; +Cc: J. Bruce Fields, Christoph Hellwig, linux-nfs
> Unfortunately there are a few (fairly trivial) merge conflicts later in
> the series due to this change. Bruce, do you want me to repost the
> whole set, or would you rather just cherry-pick them from my updated
> branch?
Can you resend just the whole fi_fds and access/deny mode patches as a
series for the next step? This seems useful and complicated enough to
do a standalone review. I also don't think the additional few spinlocks
would have enough performance impact to avoid them until the big client
lock is gone, although all those logic changes could probably be done
easily enough without the new locking if someone cared enough (I don't).
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it
2014-07-10 10:53 ` Christoph Hellwig
@ 2014-07-10 13:23 ` Jeff Layton
0 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-07-10 13:23 UTC (permalink / raw)
To: Christoph Hellwig; +Cc: Jeff Layton, J. Bruce Fields, linux-nfs
On Thu, 10 Jul 2014 03:53:43 -0700
Christoph Hellwig <hch@infradead.org> wrote:
> > Unfortunately there are a few (fairly trivial) merge conflicts later in
> > the series due to this change. Bruce, do you want me to repost the
> > whole set, or would you rather just cherry-pick them from my updated
> > branch?
>
> Can you resend just the whole fi_fds and access/deny mode patches as a
> series for the next step? This seems useful and complicated enough to
> do a standalone review. I also don't think the additional few spinlocks
> would have enough performance impact to avoid them until the big client
> lock is gone, although all those logic changes could probably be done
> easily enough without the new locking if someone cared enough (I don't).
>
Yes, that sounds reasonable. I'll go ahead and move the patches
necessary for it to the front of the series and address your comments
and we can see about getting them merged ahead of the rest.
I agree that the extra spinlocking probably won't matter while the
client_mutex is in play. If it does, then not needing to walk the whole
stateids list in order to do deny mode enforcement may help make up for
it.
--
Jeff Layton <jlayton@primarydata.com>
^ permalink raw reply [flat|nested] 151+ messages in thread
* [PATCH v3 004/114] nfsd: Avoid taking state_lock while holding inode lock in nfsd_break_one_deleg
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (2 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 003/114] nfsd: wait to initialize work struct just prior to using it Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-07-02 21:14 ` J. Bruce Fields
2014-06-30 15:48 ` [PATCH v3 005/114] nfsd: nfs4_preprocess_seqid_op should only set *stpp on success Jeff Layton
` (109 subsequent siblings)
113 siblings, 1 reply; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
state_lock is a heavily contended global lock. We don't want to grab
that while simultaneously holding the inode->i_lock.
Add a new per-nfs4_file lock that we can use to protect the
per-nfs4_file delegation list. Hold that while walking the list in the
break_deleg callback and queue the workqueue job for each one.
The workqueue job can then take the state_lock and do the list
manipulations without the i_lock being held prior to starting the
rpc call.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4callback.c | 28 +++++++++++++++++++++-------
fs/nfsd/nfs4state.c | 43 ++++++++++++++++++++++++++++---------------
fs/nfsd/state.h | 2 ++
3 files changed, 51 insertions(+), 22 deletions(-)
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 00cb9b7a75f6..cba4ca375f5e 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -43,7 +43,7 @@
#define NFSDDBG_FACILITY NFSDDBG_PROC
static void nfsd4_mark_cb_fault(struct nfs4_client *, int reason);
-static void nfsd4_do_callback_rpc(struct work_struct *w);
+static void nfsd4_run_cb_null(struct work_struct *w);
#define NFSPROC4_CB_NULL 0
#define NFSPROC4_CB_COMPOUND 1
@@ -764,7 +764,7 @@ static void do_probe_callback(struct nfs4_client *clp)
cb->cb_ops = &nfsd4_cb_probe_ops;
- INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
+ INIT_WORK(&cb->cb_work, nfsd4_run_cb_null);
run_nfsd4_cb(cb);
}
@@ -936,7 +936,7 @@ void nfsd4_shutdown_callback(struct nfs4_client *clp)
set_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags);
/*
* Note this won't actually result in a null callback;
- * instead, nfsd4_do_callback_rpc() will detect the killed
+ * instead, nfsd4_run_cb_null() will detect the killed
* client, destroy the rpc client, and stop:
*/
do_probe_callback(clp);
@@ -1014,9 +1014,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
run_nfsd4_cb(cb);
}
-static void nfsd4_do_callback_rpc(struct work_struct *w)
+static void nfsd4_run_callback_rpc(struct nfsd4_callback *cb)
{
- struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback, cb_work);
struct nfs4_client *clp = cb->cb_clp;
struct rpc_clnt *clnt;
@@ -1034,6 +1033,22 @@ static void nfsd4_do_callback_rpc(struct work_struct *w)
cb->cb_ops, cb);
}
+static void nfsd4_run_cb_null(struct work_struct *w)
+{
+ struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback,
+ cb_work);
+ nfsd4_run_callback_rpc(cb);
+}
+
+static void nfsd4_run_cb_recall(struct work_struct *w)
+{
+ struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback,
+ cb_work);
+
+ nfsd4_prepare_cb_recall(cb->cb_op);
+ nfsd4_run_callback_rpc(cb);
+}
+
void nfsd4_cb_recall(struct nfs4_delegation *dp)
{
struct nfsd4_callback *cb = &dp->dl_recall;
@@ -1050,8 +1065,7 @@ void nfsd4_cb_recall(struct nfs4_delegation *dp)
INIT_LIST_HEAD(&cb->cb_per_client);
cb->cb_done = true;
-
- INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
+ INIT_WORK(&cb->cb_work, nfsd4_run_cb_recall);
run_nfsd4_cb(&dp->dl_recall);
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b49b46b0ce23..461229a01963 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -513,7 +513,9 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
lockdep_assert_held(&state_lock);
dp->dl_stid.sc_type = NFS4_DELEG_STID;
+ spin_lock(&fp->fi_lock);
list_add(&dp->dl_perfile, &fp->fi_delegations);
+ spin_unlock(&fp->fi_lock);
list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
}
@@ -521,14 +523,18 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
static void
unhash_delegation(struct nfs4_delegation *dp)
{
+ struct nfs4_file *fp = dp->dl_file;
+
spin_lock(&state_lock);
list_del_init(&dp->dl_perclnt);
- list_del_init(&dp->dl_perfile);
list_del_init(&dp->dl_recall_lru);
+ spin_lock(&fp->fi_lock);
+ list_del_init(&dp->dl_perfile);
+ spin_unlock(&fp->fi_lock);
spin_unlock(&state_lock);
- if (dp->dl_file) {
- nfs4_put_deleg_lease(dp->dl_file);
- put_nfs4_file(dp->dl_file);
+ if (fp) {
+ nfs4_put_deleg_lease(fp);
+ put_nfs4_file(fp);
dp->dl_file = NULL;
}
}
@@ -2612,6 +2618,7 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct inode *ino)
lockdep_assert_held(&state_lock);
atomic_set(&fp->fi_ref, 1);
+ spin_lock_init(&fp->fi_lock);
INIT_LIST_HEAD(&fp->fi_stateids);
INIT_LIST_HEAD(&fp->fi_delegations);
ihold(ino);
@@ -2857,26 +2864,32 @@ out:
return ret;
}
-static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
+void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp)
{
struct nfs4_client *clp = dp->dl_stid.sc_client;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
- lockdep_assert_held(&state_lock);
+ /*
+ * We can't do this in nfsd_break_deleg_cb because it is
+ * already holding inode->i_lock
+ */
+ spin_lock(&state_lock);
+ if (list_empty(&dp->dl_recall_lru)) {
+ dp->dl_time = get_seconds();
+ list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
+ }
+ spin_unlock(&state_lock);
+}
+
+static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
+{
/* We're assuming the state code never drops its reference
* without first removing the lease. Since we're in this lease
* callback (and since the lease code is serialized by the kernel
* lock) we know the server hasn't removed the lease yet, we know
* it's safe to take a reference: */
atomic_inc(&dp->dl_count);
-
- list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
-
- /* Only place dl_time is set; protected by i_lock: */
- dp->dl_time = get_seconds();
-
block_delegations(&dp->dl_fh);
-
nfsd4_cb_recall(dp);
}
@@ -2901,11 +2914,11 @@ static void nfsd_break_deleg_cb(struct file_lock *fl)
*/
fl->fl_break_time = 0;
- spin_lock(&state_lock);
fp->fi_had_conflict = true;
+ spin_lock(&fp->fi_lock);
list_for_each_entry(dp, &fp->fi_delegations, dl_perfile)
nfsd_break_one_deleg(dp);
- spin_unlock(&state_lock);
+ spin_unlock(&fp->fi_lock);
}
static
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 9447f86f2778..7d6ba06c1abe 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -382,6 +382,7 @@ static inline struct nfs4_lockowner * lockowner(struct nfs4_stateowner *so)
/* nfs4_file: a file opened by some number of (open) nfs4_stateowners. */
struct nfs4_file {
atomic_t fi_ref;
+ spinlock_t fi_lock;
struct hlist_node fi_hash; /* hash by "struct inode *" */
struct list_head fi_stateids;
struct list_head fi_delegations;
@@ -471,6 +472,7 @@ extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
extern int nfsd4_create_callback_queue(void);
extern void nfsd4_destroy_callback_queue(void);
extern void nfsd4_shutdown_callback(struct nfs4_client *);
+extern void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp);
extern void nfs4_put_delegation(struct nfs4_delegation *dp);
extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
struct nfsd_net *nn);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* Re: [PATCH v3 004/114] nfsd: Avoid taking state_lock while holding inode lock in nfsd_break_one_deleg
2014-06-30 15:48 ` [PATCH v3 004/114] nfsd: Avoid taking state_lock while holding inode lock in nfsd_break_one_deleg Jeff Layton
@ 2014-07-02 21:14 ` J. Bruce Fields
2014-07-03 11:20 ` Jeff Layton
0 siblings, 1 reply; 151+ messages in thread
From: J. Bruce Fields @ 2014-07-02 21:14 UTC (permalink / raw)
To: Jeff Layton; +Cc: linux-nfs
On Mon, Jun 30, 2014 at 11:48:33AM -0400, Jeff Layton wrote:
> state_lock is a heavily contended global lock. We don't want to grab
> that while simultaneously holding the inode->i_lock.
>
> Add a new per-nfs4_file lock that we can use to protect the
> per-nfs4_file delegation list. Hold that while walking the list in the
> break_deleg callback and queue the workqueue job for each one.
>
> The workqueue job can then take the state_lock and do the list
> manipulations without the i_lock being held prior to starting the
> rpc call.
The code tends to assume that the callback thread only works with the
delegation struct itself and puts it when done but doesn't otherwise
touch other state.
I wonder how this interacts with state shutdown....
E.g. in nfs4_state_shutdown_net() we walk the dl_recall_lru and destroy
everything we find, but this callback workqueue is still running so I
think another delegation could get added to that list after this? Does
that cause bugs?
And it'd also be worth checking delegreturn and destroy_client.
Maybe there's no bug, or they just need to flush the workqueue at the
appropriate point.
There's also a preexisting expire_client/laundromat vs break race:
- expire_client/laundromat adds a delegation to its local
reaplist using the same dl_recall_lru field that a delegation
uses to track its position on the recall lru and drops the
state lock.
- a concurrent break_lease adds the delegation to the lru.
- expire/client/laundromat then walks it reaplist and sees the
lru head as just another delegation on the list....
Possibly unrelated, but it might be good to fix that first.
--b.
>
> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
> Signed-off-by: Jeff Layton <jlayton@primarydata.com>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> ---
> fs/nfsd/nfs4callback.c | 28 +++++++++++++++++++++-------
> fs/nfsd/nfs4state.c | 43 ++++++++++++++++++++++++++++---------------
> fs/nfsd/state.h | 2 ++
> 3 files changed, 51 insertions(+), 22 deletions(-)
>
> diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
> index 00cb9b7a75f6..cba4ca375f5e 100644
> --- a/fs/nfsd/nfs4callback.c
> +++ b/fs/nfsd/nfs4callback.c
> @@ -43,7 +43,7 @@
> #define NFSDDBG_FACILITY NFSDDBG_PROC
>
> static void nfsd4_mark_cb_fault(struct nfs4_client *, int reason);
> -static void nfsd4_do_callback_rpc(struct work_struct *w);
> +static void nfsd4_run_cb_null(struct work_struct *w);
>
> #define NFSPROC4_CB_NULL 0
> #define NFSPROC4_CB_COMPOUND 1
> @@ -764,7 +764,7 @@ static void do_probe_callback(struct nfs4_client *clp)
>
> cb->cb_ops = &nfsd4_cb_probe_ops;
>
> - INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
> + INIT_WORK(&cb->cb_work, nfsd4_run_cb_null);
>
> run_nfsd4_cb(cb);
> }
> @@ -936,7 +936,7 @@ void nfsd4_shutdown_callback(struct nfs4_client *clp)
> set_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags);
> /*
> * Note this won't actually result in a null callback;
> - * instead, nfsd4_do_callback_rpc() will detect the killed
> + * instead, nfsd4_run_cb_null() will detect the killed
> * client, destroy the rpc client, and stop:
> */
> do_probe_callback(clp);
> @@ -1014,9 +1014,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
> run_nfsd4_cb(cb);
> }
>
> -static void nfsd4_do_callback_rpc(struct work_struct *w)
> +static void nfsd4_run_callback_rpc(struct nfsd4_callback *cb)
> {
> - struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback, cb_work);
> struct nfs4_client *clp = cb->cb_clp;
> struct rpc_clnt *clnt;
>
> @@ -1034,6 +1033,22 @@ static void nfsd4_do_callback_rpc(struct work_struct *w)
> cb->cb_ops, cb);
> }
>
> +static void nfsd4_run_cb_null(struct work_struct *w)
> +{
> + struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback,
> + cb_work);
> + nfsd4_run_callback_rpc(cb);
> +}
> +
> +static void nfsd4_run_cb_recall(struct work_struct *w)
> +{
> + struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback,
> + cb_work);
> +
> + nfsd4_prepare_cb_recall(cb->cb_op);
> + nfsd4_run_callback_rpc(cb);
> +}
> +
> void nfsd4_cb_recall(struct nfs4_delegation *dp)
> {
> struct nfsd4_callback *cb = &dp->dl_recall;
> @@ -1050,8 +1065,7 @@ void nfsd4_cb_recall(struct nfs4_delegation *dp)
>
> INIT_LIST_HEAD(&cb->cb_per_client);
> cb->cb_done = true;
> -
> - INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
> + INIT_WORK(&cb->cb_work, nfsd4_run_cb_recall);
>
> run_nfsd4_cb(&dp->dl_recall);
> }
> diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
> index b49b46b0ce23..461229a01963 100644
> --- a/fs/nfsd/nfs4state.c
> +++ b/fs/nfsd/nfs4state.c
> @@ -513,7 +513,9 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
> lockdep_assert_held(&state_lock);
>
> dp->dl_stid.sc_type = NFS4_DELEG_STID;
> + spin_lock(&fp->fi_lock);
> list_add(&dp->dl_perfile, &fp->fi_delegations);
> + spin_unlock(&fp->fi_lock);
> list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
> }
>
> @@ -521,14 +523,18 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
> static void
> unhash_delegation(struct nfs4_delegation *dp)
> {
> + struct nfs4_file *fp = dp->dl_file;
> +
> spin_lock(&state_lock);
> list_del_init(&dp->dl_perclnt);
> - list_del_init(&dp->dl_perfile);
> list_del_init(&dp->dl_recall_lru);
> + spin_lock(&fp->fi_lock);
> + list_del_init(&dp->dl_perfile);
> + spin_unlock(&fp->fi_lock);
> spin_unlock(&state_lock);
> - if (dp->dl_file) {
> - nfs4_put_deleg_lease(dp->dl_file);
> - put_nfs4_file(dp->dl_file);
> + if (fp) {
> + nfs4_put_deleg_lease(fp);
> + put_nfs4_file(fp);
> dp->dl_file = NULL;
> }
> }
> @@ -2612,6 +2618,7 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct inode *ino)
> lockdep_assert_held(&state_lock);
>
> atomic_set(&fp->fi_ref, 1);
> + spin_lock_init(&fp->fi_lock);
> INIT_LIST_HEAD(&fp->fi_stateids);
> INIT_LIST_HEAD(&fp->fi_delegations);
> ihold(ino);
> @@ -2857,26 +2864,32 @@ out:
> return ret;
> }
>
> -static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
> +void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp)
> {
> struct nfs4_client *clp = dp->dl_stid.sc_client;
> struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
>
> - lockdep_assert_held(&state_lock);
> + /*
> + * We can't do this in nfsd_break_deleg_cb because it is
> + * already holding inode->i_lock
> + */
> + spin_lock(&state_lock);
> + if (list_empty(&dp->dl_recall_lru)) {
> + dp->dl_time = get_seconds();
> + list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
> + }
> + spin_unlock(&state_lock);
> +}
> +
> +static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
> +{
> /* We're assuming the state code never drops its reference
> * without first removing the lease. Since we're in this lease
> * callback (and since the lease code is serialized by the kernel
> * lock) we know the server hasn't removed the lease yet, we know
> * it's safe to take a reference: */
> atomic_inc(&dp->dl_count);
> -
> - list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
> -
> - /* Only place dl_time is set; protected by i_lock: */
> - dp->dl_time = get_seconds();
> -
> block_delegations(&dp->dl_fh);
> -
> nfsd4_cb_recall(dp);
> }
>
> @@ -2901,11 +2914,11 @@ static void nfsd_break_deleg_cb(struct file_lock *fl)
> */
> fl->fl_break_time = 0;
>
> - spin_lock(&state_lock);
> fp->fi_had_conflict = true;
> + spin_lock(&fp->fi_lock);
> list_for_each_entry(dp, &fp->fi_delegations, dl_perfile)
> nfsd_break_one_deleg(dp);
> - spin_unlock(&state_lock);
> + spin_unlock(&fp->fi_lock);
> }
>
> static
> diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
> index 9447f86f2778..7d6ba06c1abe 100644
> --- a/fs/nfsd/state.h
> +++ b/fs/nfsd/state.h
> @@ -382,6 +382,7 @@ static inline struct nfs4_lockowner * lockowner(struct nfs4_stateowner *so)
> /* nfs4_file: a file opened by some number of (open) nfs4_stateowners. */
> struct nfs4_file {
> atomic_t fi_ref;
> + spinlock_t fi_lock;
> struct hlist_node fi_hash; /* hash by "struct inode *" */
> struct list_head fi_stateids;
> struct list_head fi_delegations;
> @@ -471,6 +472,7 @@ extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
> extern int nfsd4_create_callback_queue(void);
> extern void nfsd4_destroy_callback_queue(void);
> extern void nfsd4_shutdown_callback(struct nfs4_client *);
> +extern void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp);
> extern void nfs4_put_delegation(struct nfs4_delegation *dp);
> extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
> struct nfsd_net *nn);
> --
> 1.9.3
>
^ permalink raw reply [flat|nested] 151+ messages in thread* Re: [PATCH v3 004/114] nfsd: Avoid taking state_lock while holding inode lock in nfsd_break_one_deleg
2014-07-02 21:14 ` J. Bruce Fields
@ 2014-07-03 11:20 ` Jeff Layton
2014-07-03 14:40 ` J. Bruce Fields
0 siblings, 1 reply; 151+ messages in thread
From: Jeff Layton @ 2014-07-03 11:20 UTC (permalink / raw)
To: J. Bruce Fields; +Cc: linux-nfs
On Wed, 2 Jul 2014 17:14:24 -0400
"J. Bruce Fields" <bfields@fieldses.org> wrote:
> On Mon, Jun 30, 2014 at 11:48:33AM -0400, Jeff Layton wrote:
> > state_lock is a heavily contended global lock. We don't want to grab
> > that while simultaneously holding the inode->i_lock.
> >
> > Add a new per-nfs4_file lock that we can use to protect the
> > per-nfs4_file delegation list. Hold that while walking the list in the
> > break_deleg callback and queue the workqueue job for each one.
> >
> > The workqueue job can then take the state_lock and do the list
> > manipulations without the i_lock being held prior to starting the
> > rpc call.
>
> The code tends to assume that the callback thread only works with the
> delegation struct itself and puts it when done but doesn't otherwise
> touch other state.
>
> I wonder how this interacts with state shutdown....
>
> E.g. in nfs4_state_shutdown_net() we walk the dl_recall_lru and destroy
> everything we find, but this callback workqueue is still running so I
> think another delegation could get added to that list after this? Does
> that cause bugs?
>
I don't see what would prevent those bugs today and I'm unclear on why
you think this patch will make things worse. All this patch really does
is protect the dl_perfile list manipulations with a new per-nfs4_file
lock, and have it lock that when walking the perfile list. Then it has
the workqueue callback do the work of adding it to the del_recall_lru
list.
Why wouldn't you have the same problem if you do the queueing to the
LRU list in break_deleg codepath with the code as it is today?
That said, the delegation code is horribly complex so it's possible
I've missed something here.
> And it'd also be worth checking delegreturn and destroy_client.
>
> Maybe there's no bug, or they just need to flush the workqueue at the
> appropriate point.
>
> There's also a preexisting expire_client/laundromat vs break race:
>
> - expire_client/laundromat adds a delegation to its local
> reaplist using the same dl_recall_lru field that a delegation
> uses to track its position on the recall lru and drops the
> state lock.
>
> - a concurrent break_lease adds the delegation to the lru.
>
> - expire/client/laundromat then walks it reaplist and sees the
> lru head as just another delegation on the list....
>
> Possibly unrelated, but it might be good to fix that first.
>
> --b.
>
I was thinking that that would be fixed up in a later patch:
nfsd: Fix delegation revocation
...but now I'm not so sure. Once you drop the fi_lock, you could end up
with the race above.
Honestly, the locking around the delegation code is still a mess, even
with this series. I don't care much for the state_lock/recall_lock at
all. It seems like we ought to be able to do something more granular
there. Let me give it some thought -- maybe I can come up with a better
way to handle this.
> >
> > Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
> > Signed-off-by: Jeff Layton <jlayton@primarydata.com>
> > Reviewed-by: Christoph Hellwig <hch@lst.de>
> > ---
> > fs/nfsd/nfs4callback.c | 28 +++++++++++++++++++++-------
> > fs/nfsd/nfs4state.c | 43 ++++++++++++++++++++++++++++---------------
> > fs/nfsd/state.h | 2 ++
> > 3 files changed, 51 insertions(+), 22 deletions(-)
> >
> > diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
> > index 00cb9b7a75f6..cba4ca375f5e 100644
> > --- a/fs/nfsd/nfs4callback.c
> > +++ b/fs/nfsd/nfs4callback.c
> > @@ -43,7 +43,7 @@
> > #define NFSDDBG_FACILITY NFSDDBG_PROC
> >
> > static void nfsd4_mark_cb_fault(struct nfs4_client *, int reason);
> > -static void nfsd4_do_callback_rpc(struct work_struct *w);
> > +static void nfsd4_run_cb_null(struct work_struct *w);
> >
> > #define NFSPROC4_CB_NULL 0
> > #define NFSPROC4_CB_COMPOUND 1
> > @@ -764,7 +764,7 @@ static void do_probe_callback(struct nfs4_client *clp)
> >
> > cb->cb_ops = &nfsd4_cb_probe_ops;
> >
> > - INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
> > + INIT_WORK(&cb->cb_work, nfsd4_run_cb_null);
> >
> > run_nfsd4_cb(cb);
> > }
> > @@ -936,7 +936,7 @@ void nfsd4_shutdown_callback(struct nfs4_client *clp)
> > set_bit(NFSD4_CLIENT_CB_KILL, &clp->cl_flags);
> > /*
> > * Note this won't actually result in a null callback;
> > - * instead, nfsd4_do_callback_rpc() will detect the killed
> > + * instead, nfsd4_run_cb_null() will detect the killed
> > * client, destroy the rpc client, and stop:
> > */
> > do_probe_callback(clp);
> > @@ -1014,9 +1014,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
> > run_nfsd4_cb(cb);
> > }
> >
> > -static void nfsd4_do_callback_rpc(struct work_struct *w)
> > +static void nfsd4_run_callback_rpc(struct nfsd4_callback *cb)
> > {
> > - struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback, cb_work);
> > struct nfs4_client *clp = cb->cb_clp;
> > struct rpc_clnt *clnt;
> >
> > @@ -1034,6 +1033,22 @@ static void nfsd4_do_callback_rpc(struct work_struct *w)
> > cb->cb_ops, cb);
> > }
> >
> > +static void nfsd4_run_cb_null(struct work_struct *w)
> > +{
> > + struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback,
> > + cb_work);
> > + nfsd4_run_callback_rpc(cb);
> > +}
> > +
> > +static void nfsd4_run_cb_recall(struct work_struct *w)
> > +{
> > + struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback,
> > + cb_work);
> > +
> > + nfsd4_prepare_cb_recall(cb->cb_op);
> > + nfsd4_run_callback_rpc(cb);
> > +}
> > +
> > void nfsd4_cb_recall(struct nfs4_delegation *dp)
> > {
> > struct nfsd4_callback *cb = &dp->dl_recall;
> > @@ -1050,8 +1065,7 @@ void nfsd4_cb_recall(struct nfs4_delegation *dp)
> >
> > INIT_LIST_HEAD(&cb->cb_per_client);
> > cb->cb_done = true;
> > -
> > - INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
> > + INIT_WORK(&cb->cb_work, nfsd4_run_cb_recall);
> >
> > run_nfsd4_cb(&dp->dl_recall);
> > }
> > diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
> > index b49b46b0ce23..461229a01963 100644
> > --- a/fs/nfsd/nfs4state.c
> > +++ b/fs/nfsd/nfs4state.c
> > @@ -513,7 +513,9 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
> > lockdep_assert_held(&state_lock);
> >
> > dp->dl_stid.sc_type = NFS4_DELEG_STID;
> > + spin_lock(&fp->fi_lock);
> > list_add(&dp->dl_perfile, &fp->fi_delegations);
> > + spin_unlock(&fp->fi_lock);
> > list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
> > }
> >
> > @@ -521,14 +523,18 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
> > static void
> > unhash_delegation(struct nfs4_delegation *dp)
> > {
> > + struct nfs4_file *fp = dp->dl_file;
> > +
> > spin_lock(&state_lock);
> > list_del_init(&dp->dl_perclnt);
> > - list_del_init(&dp->dl_perfile);
> > list_del_init(&dp->dl_recall_lru);
> > + spin_lock(&fp->fi_lock);
> > + list_del_init(&dp->dl_perfile);
> > + spin_unlock(&fp->fi_lock);
> > spin_unlock(&state_lock);
> > - if (dp->dl_file) {
> > - nfs4_put_deleg_lease(dp->dl_file);
> > - put_nfs4_file(dp->dl_file);
> > + if (fp) {
> > + nfs4_put_deleg_lease(fp);
> > + put_nfs4_file(fp);
> > dp->dl_file = NULL;
> > }
> > }
> > @@ -2612,6 +2618,7 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct inode *ino)
> > lockdep_assert_held(&state_lock);
> >
> > atomic_set(&fp->fi_ref, 1);
> > + spin_lock_init(&fp->fi_lock);
> > INIT_LIST_HEAD(&fp->fi_stateids);
> > INIT_LIST_HEAD(&fp->fi_delegations);
> > ihold(ino);
> > @@ -2857,26 +2864,32 @@ out:
> > return ret;
> > }
> >
> > -static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
> > +void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp)
> > {
> > struct nfs4_client *clp = dp->dl_stid.sc_client;
> > struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
> >
> > - lockdep_assert_held(&state_lock);
> > + /*
> > + * We can't do this in nfsd_break_deleg_cb because it is
> > + * already holding inode->i_lock
> > + */
> > + spin_lock(&state_lock);
> > + if (list_empty(&dp->dl_recall_lru)) {
> > + dp->dl_time = get_seconds();
> > + list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
> > + }
> > + spin_unlock(&state_lock);
> > +}
> > +
> > +static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
> > +{
> > /* We're assuming the state code never drops its reference
> > * without first removing the lease. Since we're in this lease
> > * callback (and since the lease code is serialized by the kernel
> > * lock) we know the server hasn't removed the lease yet, we know
> > * it's safe to take a reference: */
> > atomic_inc(&dp->dl_count);
> > -
> > - list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
> > -
> > - /* Only place dl_time is set; protected by i_lock: */
> > - dp->dl_time = get_seconds();
> > -
> > block_delegations(&dp->dl_fh);
> > -
> > nfsd4_cb_recall(dp);
> > }
> >
> > @@ -2901,11 +2914,11 @@ static void nfsd_break_deleg_cb(struct file_lock *fl)
> > */
> > fl->fl_break_time = 0;
> >
> > - spin_lock(&state_lock);
> > fp->fi_had_conflict = true;
> > + spin_lock(&fp->fi_lock);
> > list_for_each_entry(dp, &fp->fi_delegations, dl_perfile)
> > nfsd_break_one_deleg(dp);
> > - spin_unlock(&state_lock);
> > + spin_unlock(&fp->fi_lock);
> > }
> >
> > static
> > diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
> > index 9447f86f2778..7d6ba06c1abe 100644
> > --- a/fs/nfsd/state.h
> > +++ b/fs/nfsd/state.h
> > @@ -382,6 +382,7 @@ static inline struct nfs4_lockowner * lockowner(struct nfs4_stateowner *so)
> > /* nfs4_file: a file opened by some number of (open) nfs4_stateowners. */
> > struct nfs4_file {
> > atomic_t fi_ref;
> > + spinlock_t fi_lock;
> > struct hlist_node fi_hash; /* hash by "struct inode *" */
> > struct list_head fi_stateids;
> > struct list_head fi_delegations;
> > @@ -471,6 +472,7 @@ extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
> > extern int nfsd4_create_callback_queue(void);
> > extern void nfsd4_destroy_callback_queue(void);
> > extern void nfsd4_shutdown_callback(struct nfs4_client *);
> > +extern void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp);
> > extern void nfs4_put_delegation(struct nfs4_delegation *dp);
> > extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
> > struct nfsd_net *nn);
> > --
> > 1.9.3
> >
--
Jeff Layton <jlayton@primarydata.com>
^ permalink raw reply [flat|nested] 151+ messages in thread* Re: [PATCH v3 004/114] nfsd: Avoid taking state_lock while holding inode lock in nfsd_break_one_deleg
2014-07-03 11:20 ` Jeff Layton
@ 2014-07-03 14:40 ` J. Bruce Fields
0 siblings, 0 replies; 151+ messages in thread
From: J. Bruce Fields @ 2014-07-03 14:40 UTC (permalink / raw)
To: Jeff Layton; +Cc: linux-nfs
On Thu, Jul 03, 2014 at 07:20:12AM -0400, Jeff Layton wrote:
> On Wed, 2 Jul 2014 17:14:24 -0400
> "J. Bruce Fields" <bfields@fieldses.org> wrote:
>
> > On Mon, Jun 30, 2014 at 11:48:33AM -0400, Jeff Layton wrote:
> > > state_lock is a heavily contended global lock. We don't want to grab
> > > that while simultaneously holding the inode->i_lock.
> > >
> > > Add a new per-nfs4_file lock that we can use to protect the
> > > per-nfs4_file delegation list. Hold that while walking the list in the
> > > break_deleg callback and queue the workqueue job for each one.
> > >
> > > The workqueue job can then take the state_lock and do the list
> > > manipulations without the i_lock being held prior to starting the
> > > rpc call.
> >
> > The code tends to assume that the callback thread only works with the
> > delegation struct itself and puts it when done but doesn't otherwise
> > touch other state.
> >
> > I wonder how this interacts with state shutdown....
> >
> > E.g. in nfs4_state_shutdown_net() we walk the dl_recall_lru and destroy
> > everything we find, but this callback workqueue is still running so I
> > think another delegation could get added to that list after this? Does
> > that cause bugs?
> >
>
> I don't see what would prevent those bugs today and I'm unclear on why
> you think this patch will make things worse. All this patch really does
> is protect the dl_perfile list manipulations with a new per-nfs4_file
> lock, and have it lock that when walking the perfile list. Then it has
> the workqueue callback do the work of adding it to the del_recall_lru
> list.
>
> Why wouldn't you have the same problem if you do the queueing to the
> LRU list in break_deleg codepath with the code as it is today?
Yeah, I suppose so.
> That said, the delegation code is horribly complex so it's possible
> I've missed something here.
>
> > And it'd also be worth checking delegreturn and destroy_client.
> >
> > Maybe there's no bug, or they just need to flush the workqueue at the
> > appropriate point.
> >
> > There's also a preexisting expire_client/laundromat vs break race:
> >
> > - expire_client/laundromat adds a delegation to its local
> > reaplist using the same dl_recall_lru field that a delegation
> > uses to track its position on the recall lru and drops the
> > state lock.
> >
> > - a concurrent break_lease adds the delegation to the lru.
> >
> > - expire/client/laundromat then walks it reaplist and sees the
> > lru head as just another delegation on the list....
> >
> > Possibly unrelated, but it might be good to fix that first.
> >
> > --b.
> >
>
> I was thinking that that would be fixed up in a later patch:
>
> nfsd: Fix delegation revocation
>
> ...but now I'm not so sure. Once you drop the fi_lock, you could end up
> with the race above.
>
> Honestly, the locking around the delegation code is still a mess, even
> with this series. I don't care much for the state_lock/recall_lock at
> all. It seems like we ought to be able to do something more granular
> there. Let me give it some thought -- maybe I can come up with a better
> way to handle this.
OK. I agree that it's too complicated.
--b.
^ permalink raw reply [flat|nested] 151+ messages in thread
* [PATCH v3 005/114] nfsd: nfs4_preprocess_seqid_op should only set *stpp on success
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (3 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 004/114] nfsd: Avoid taking state_lock while holding inode lock in nfsd_break_one_deleg Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 006/114] nfsd: Cleanup nfs4svc_encode_compoundres Jeff Layton
` (108 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Not technically a bugfix, since nothing tries to use the return pointer
if this function doesn't return success, but it could be a problem
with some coming changes.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4state.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 461229a01963..3ce5dc30f767 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3964,6 +3964,7 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
{
__be32 status;
struct nfs4_stid *s;
+ struct nfs4_ol_stateid *stp = NULL;
dprintk("NFSD: %s: seqid=%d stateid = " STATEID_FMT "\n", __func__,
seqid, STATEID_VAL(stateid));
@@ -3973,11 +3974,14 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
cstate->minorversion, nn);
if (status)
return status;
- *stpp = openlockstateid(s);
+ stp = openlockstateid(s);
if (!nfsd4_has_session(cstate))
- cstate->replay_owner = (*stpp)->st_stateowner;
+ cstate->replay_owner = stp->st_stateowner;
- return nfs4_seqid_op_checks(cstate, stateid, seqid, *stpp);
+ status = nfs4_seqid_op_checks(cstate, stateid, seqid, stp);
+ if (!status)
+ *stpp = stp;
+ return status;
}
static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 006/114] nfsd: Cleanup nfs4svc_encode_compoundres
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (4 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 005/114] nfsd: nfs4_preprocess_seqid_op should only set *stpp on success Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 007/114] nfsd: declare v4.1+ openowners confirmed on creation Jeff Layton
` (107 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Move the slot return, put session etc into a helper in fs/nfsd/nfs4state.c
instead of open coding in nfs4svc_encode_compoundres.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4state.c | 35 ++++++++++++++++++++++-------------
fs/nfsd/nfs4xdr.c | 15 +--------------
fs/nfsd/state.h | 1 -
fs/nfsd/xdr4.h | 2 +-
4 files changed, 24 insertions(+), 29 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 3ce5dc30f767..ade15fcddd08 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -203,18 +203,6 @@ static void put_client_renew_locked(struct nfs4_client *clp)
renew_client_locked(clp);
}
-void put_client_renew(struct nfs4_client *clp)
-{
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
-
- if (!atomic_dec_and_lock(&clp->cl_refcount, &nn->client_lock))
- return;
- if (!is_client_expired(clp))
- renew_client_locked(clp);
- spin_unlock(&nn->client_lock);
-}
-
-
static inline u32
opaque_hashval(const void *ptr, int nbytes)
{
@@ -1650,7 +1638,7 @@ out_err:
/*
* Cache a reply. nfsd4_check_resp_size() has bounded the cache size.
*/
-void
+static void
nfsd4_store_cache_entry(struct nfsd4_compoundres *resp)
{
struct xdr_buf *buf = resp->xdr.buf;
@@ -2422,6 +2410,27 @@ out_put_client:
goto out_no_session;
}
+void
+nfsd4_sequence_done(struct nfsd4_compoundres *resp)
+{
+ struct nfsd4_compound_state *cs = &resp->cstate;
+
+ if (nfsd4_has_session(cs)) {
+ struct nfs4_client *clp = cs->session->se_client;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ if (cs->status != nfserr_replay_cache) {
+ nfsd4_store_cache_entry(resp);
+ cs->slot->sl_flags &= ~NFSD4_SLOT_INUSE;
+ }
+ /* Renew the clientid on success and on replay */
+ spin_lock(&nn->client_lock);
+ nfsd4_put_session(cs->session);
+ put_client_renew_locked(clp);
+ spin_unlock(&nn->client_lock);
+ }
+}
+
__be32
nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_destroy_clientid *dc)
{
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index a1c48b4111d2..1c5e87e660cd 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4006,7 +4006,6 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
/*
* All that remains is to write the tag and operation count...
*/
- struct nfsd4_compound_state *cs = &resp->cstate;
struct xdr_buf *buf = resp->xdr.buf;
WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len +
@@ -4020,19 +4019,7 @@ nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compo
p += XDR_QUADLEN(resp->taglen);
*p++ = htonl(resp->opcnt);
- if (nfsd4_has_session(cs)) {
- struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
- struct nfs4_client *clp = cs->session->se_client;
- if (cs->status != nfserr_replay_cache) {
- nfsd4_store_cache_entry(resp);
- cs->slot->sl_flags &= ~NFSD4_SLOT_INUSE;
- }
- /* Renew the clientid on success and on replay */
- spin_lock(&nn->client_lock);
- nfsd4_put_session(cs->session);
- spin_unlock(&nn->client_lock);
- put_client_renew(clp);
- }
+ nfsd4_sequence_done(resp);
return 1;
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 7d6ba06c1abe..24eec922685c 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -477,7 +477,6 @@ extern void nfs4_put_delegation(struct nfs4_delegation *dp);
extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(const char *name,
struct nfsd_net *nn);
extern bool nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn);
-extern void put_client_renew(struct nfs4_client *clp);
/* nfs4recover operations */
extern int nfsd4_client_tracking_init(struct net *net);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 18cbb6d9c8a9..7d8af164523b 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -574,7 +574,6 @@ extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
struct nfsd4_compound_state *,
struct nfsd4_setclientid_confirm *setclientid_confirm);
-extern void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp);
extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp,
struct nfsd4_compound_state *, struct nfsd4_exchange_id *);
extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_backchannel_ctl *);
@@ -585,6 +584,7 @@ extern __be32 nfsd4_create_session(struct svc_rqst *,
extern __be32 nfsd4_sequence(struct svc_rqst *,
struct nfsd4_compound_state *,
struct nfsd4_sequence *);
+extern void nfsd4_sequence_done(struct nfsd4_compoundres *resp);
extern __be32 nfsd4_destroy_session(struct svc_rqst *,
struct nfsd4_compound_state *,
struct nfsd4_destroy_session *);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 007/114] nfsd: declare v4.1+ openowners confirmed on creation
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (5 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 006/114] nfsd: Cleanup nfs4svc_encode_compoundres Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 008/114] nfsd: clean up nfsd4_close_open_stateid Jeff Layton
` (106 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
There's no need to confirm an openowner in v4.1 and above, so we can
go ahead and set NFS4_OO_CONFIRMED when we create openowners in
those versions. This will also be necessary when we remove the
client_mutex, as it'll be possible for two concurrent opens to race
in versions >4.0.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4state.c | 16 ++++++++++------
1 file changed, 10 insertions(+), 6 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ade15fcddd08..e77e34002913 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2724,7 +2724,10 @@ static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, u
}
static struct nfs4_openowner *
-alloc_init_open_stateowner(unsigned int strhashval, struct nfs4_client *clp, struct nfsd4_open *open) {
+alloc_init_open_stateowner(unsigned int strhashval, struct nfs4_client *clp,
+ struct nfsd4_open *open,
+ struct nfsd4_compound_state *cstate)
+{
struct nfs4_openowner *oo;
oo = alloc_stateowner(openowner_slab, &open->op_owner, clp);
@@ -2733,6 +2736,8 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfs4_client *clp, str
oo->oo_owner.so_is_open_owner = 1;
oo->oo_owner.so_seqid = open->op_seqid;
oo->oo_flags = NFS4_OO_NEW;
+ if (nfsd4_has_session(cstate))
+ oo->oo_flags |= NFS4_OO_CONFIRMED;
oo->oo_time = 0;
oo->oo_last_closed_stid = NULL;
INIT_LIST_HEAD(&oo->oo_close_lru);
@@ -2998,7 +3003,7 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate,
clp = oo->oo_owner.so_client;
goto alloc_stateid;
new_owner:
- oo = alloc_init_open_stateowner(strhashval, clp, open);
+ oo = alloc_init_open_stateowner(strhashval, clp, open, cstate);
if (oo == NULL)
return nfserr_jukebox;
open->op_openowner = oo;
@@ -3408,8 +3413,6 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
if (nfsd4_has_session(&resp->cstate)) {
- open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
-
if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) {
open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT;
open->op_why_no_deleg = WND4_NOT_WANTED;
@@ -3803,8 +3806,9 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
nfs4_lock_state();
- status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
- &s, cstate->minorversion, nn);
+ status = nfsd4_lookup_stateid(stateid,
+ NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
+ &s, cstate->minorversion, nn);
if (status)
goto out;
status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate));
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 008/114] nfsd: clean up nfsd4_close_open_stateid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (6 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 007/114] nfsd: declare v4.1+ openowners confirmed on creation Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 18:01 ` Christoph Hellwig
2014-06-30 15:48 ` [PATCH v3 009/114] nfsd: lock owners are not per open stateid Jeff Layton
` (105 subsequent siblings)
113 siblings, 1 reply; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Minor cleanup that should introduce no behavioral changes.
Currently this function just unhashes the stateid and leaves the caller
to do the work of the CLOSE processing.
Change nfsd4_close_open_stateid so that it handles doing all of the work
of closing a stateid. Move the handling of the unhashed stateid into it
instead of doing that work in nfsd4_close. This will help isolate some
coming changes to stateid handling from nfsd4_close.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 38 ++++++++++++++++++--------------------
1 file changed, 18 insertions(+), 20 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e77e34002913..08586646e962 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4140,8 +4140,25 @@ out:
static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
{
- unhash_open_stateid(s);
+ struct nfs4_client *clp = s->st_stid.sc_client;
+ struct nfs4_openowner *oo = openowner(s->st_stateowner);
+
s->st_stid.sc_type = NFS4_CLOSED_STID;
+ unhash_open_stateid(s);
+
+ if (clp->cl_minorversion) {
+ free_generic_stateid(s);
+ if (list_empty(&oo->oo_owner.so_stateids))
+ release_openowner(oo);
+ } else {
+ oo->oo_last_closed_stid = s;
+ /*
+ * In the 4.0 case we need to keep the owners around a
+ * little while to handle CLOSE replay.
+ */
+ if (list_empty(&oo->oo_owner.so_stateids))
+ move_to_close_lru(oo, clp->net);
+ }
}
/*
@@ -4152,7 +4169,6 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_close *close)
{
__be32 status;
- struct nfs4_openowner *oo;
struct nfs4_ol_stateid *stp;
struct net *net = SVC_NET(rqstp);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
@@ -4168,28 +4184,10 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfsd4_bump_seqid(cstate, status);
if (status)
goto out;
- oo = openowner(stp->st_stateowner);
update_stateid(&stp->st_stid.sc_stateid);
memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
nfsd4_close_open_stateid(stp);
-
- if (cstate->minorversion)
- free_generic_stateid(stp);
- else
- oo->oo_last_closed_stid = stp;
-
- if (list_empty(&oo->oo_owner.so_stateids)) {
- if (cstate->minorversion)
- release_openowner(oo);
- else {
- /*
- * In the 4.0 case we need to keep the owners around a
- * little while to handle CLOSE replay.
- */
- move_to_close_lru(oo, SVC_NET(rqstp));
- }
- }
out:
if (!cstate->replay_owner)
nfs4_unlock_state();
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* Re: [PATCH v3 008/114] nfsd: clean up nfsd4_close_open_stateid
2014-06-30 15:48 ` [PATCH v3 008/114] nfsd: clean up nfsd4_close_open_stateid Jeff Layton
@ 2014-06-30 18:01 ` Christoph Hellwig
0 siblings, 0 replies; 151+ messages in thread
From: Christoph Hellwig @ 2014-06-30 18:01 UTC (permalink / raw)
To: Jeff Layton; +Cc: bfields, linux-nfs, Trond Myklebust
On Mon, Jun 30, 2014 at 11:48:37AM -0400, Jeff Layton wrote:
> From: Trond Myklebust <trond.myklebust@primarydata.com>
>
> Minor cleanup that should introduce no behavioral changes.
>
> Currently this function just unhashes the stateid and leaves the caller
> to do the work of the CLOSE processing.
>
> Change nfsd4_close_open_stateid so that it handles doing all of the work
> of closing a stateid. Move the handling of the unhashed stateid into it
> instead of doing that work in nfsd4_close. This will help isolate some
> coming changes to stateid handling from nfsd4_close.
>
> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Looks good,
Reviewed-by: Christoph Hellwig <hch@lst.de>
^ permalink raw reply [flat|nested] 151+ messages in thread
* [PATCH v3 009/114] nfsd: lock owners are not per open stateid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (7 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 008/114] nfsd: clean up nfsd4_close_open_stateid Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 010/114] nfsd: Allow lockowners to hold several stateids Jeff Layton
` (104 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
In the NFSv4 spec, lock stateids are per-file objects. Lockowners are not.
This patch replaces the current list of lock owners in the open stateids
with a list of lock stateids.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4state.c | 53 +++++++++++++++++++++++++++++++++++------------------
fs/nfsd/state.h | 3 +--
2 files changed, 36 insertions(+), 20 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 08586646e962..a3321601f55f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -700,10 +700,11 @@ static void free_generic_stateid(struct nfs4_ol_stateid *stp)
nfs4_free_stid(stateid_slab, &stp->st_stid);
}
-static void release_lock_stateid(struct nfs4_ol_stateid *stp)
+static void __release_lock_stateid(struct nfs4_ol_stateid *stp)
{
struct file *file;
+ list_del(&stp->st_locks);
unhash_generic_stateid(stp);
unhash_stid(&stp->st_stid);
file = find_any_file(stp->st_file);
@@ -718,12 +719,11 @@ static void unhash_lockowner(struct nfs4_lockowner *lo)
struct nfs4_ol_stateid *stp;
list_del(&lo->lo_owner.so_strhash);
- list_del(&lo->lo_perstateid);
list_del(&lo->lo_owner_ino_hash);
while (!list_empty(&lo->lo_owner.so_stateids)) {
stp = list_first_entry(&lo->lo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
- release_lock_stateid(stp);
+ __release_lock_stateid(stp);
}
}
@@ -739,22 +739,36 @@ static void release_lockowner(struct nfs4_lockowner *lo)
nfs4_free_lockowner(lo);
}
-static void
-release_stateid_lockowners(struct nfs4_ol_stateid *open_stp)
+static void release_lockowner_if_empty(struct nfs4_lockowner *lo)
+{
+ if (list_empty(&lo->lo_owner.so_stateids))
+ release_lockowner(lo);
+}
+
+static void release_lock_stateid(struct nfs4_ol_stateid *stp)
{
struct nfs4_lockowner *lo;
- while (!list_empty(&open_stp->st_lockowners)) {
- lo = list_entry(open_stp->st_lockowners.next,
- struct nfs4_lockowner, lo_perstateid);
- release_lockowner(lo);
+ lo = lockowner(stp->st_stateowner);
+ __release_lock_stateid(stp);
+ release_lockowner_if_empty(lo);
+}
+
+static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp)
+{
+ struct nfs4_ol_stateid *stp;
+
+ while (!list_empty(&open_stp->st_locks)) {
+ stp = list_entry(open_stp->st_locks.next,
+ struct nfs4_ol_stateid, st_locks);
+ release_lock_stateid(stp);
}
}
static void unhash_open_stateid(struct nfs4_ol_stateid *stp)
{
unhash_generic_stateid(stp);
- release_stateid_lockowners(stp);
+ release_open_stateid_locks(stp);
close_generic_stateid(stp);
}
@@ -2749,7 +2763,7 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
struct nfs4_openowner *oo = open->op_openowner;
stp->st_stid.sc_type = NFS4_OPEN_STID;
- INIT_LIST_HEAD(&stp->st_lockowners);
+ INIT_LIST_HEAD(&stp->st_locks);
list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
list_add(&stp->st_perfile, &fp->fi_stateids);
stp->st_stateowner = &oo->oo_owner;
@@ -4346,7 +4360,6 @@ static void hash_lockowner(struct nfs4_lockowner *lo, unsigned int strhashval, s
list_add(&lo->lo_owner.so_strhash, &nn->ownerstr_hashtbl[strhashval]);
list_add(&lo->lo_owner_ino_hash, &nn->lockowner_ino_hashtbl[inohash]);
- list_add(&lo->lo_perstateid, &open_stp->st_lockowners);
}
/*
@@ -4391,6 +4404,7 @@ alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct
stp->st_access_bmap = 0;
stp->st_deny_bmap = open_stp->st_deny_bmap;
stp->st_openstp = open_stp;
+ list_add(&stp->st_locks, &open_stp->st_locks);
return stp;
}
@@ -4978,18 +4992,21 @@ static void nfsd_print_count(struct nfs4_client *clp, unsigned int count,
printk(KERN_INFO "NFS Client: %s has %u %s\n", buf, count, type);
}
-static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max, void (*func)(struct nfs4_lockowner *))
+static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max,
+ void (*func)(struct nfs4_ol_stateid *))
{
struct nfs4_openowner *oop;
- struct nfs4_lockowner *lop, *lo_next;
struct nfs4_ol_stateid *stp, *st_next;
+ struct nfs4_ol_stateid *lst, *lst_next;
u64 count = 0;
list_for_each_entry(oop, &clp->cl_openowners, oo_perclient) {
- list_for_each_entry_safe(stp, st_next, &oop->oo_owner.so_stateids, st_perstateowner) {
- list_for_each_entry_safe(lop, lo_next, &stp->st_lockowners, lo_perstateid) {
+ list_for_each_entry_safe(stp, st_next,
+ &oop->oo_owner.so_stateids, st_perstateowner) {
+ list_for_each_entry_safe(lst, lst_next,
+ &stp->st_locks, st_locks) {
if (func)
- func(lop);
+ func(lst);
if (++count == max)
return count;
}
@@ -5001,7 +5018,7 @@ static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max, void (*fun
u64 nfsd_forget_client_locks(struct nfs4_client *clp, u64 max)
{
- return nfsd_foreach_client_lock(clp, max, release_lockowner);
+ return nfsd_foreach_client_lock(clp, max, release_lock_stateid);
}
u64 nfsd_print_client_locks(struct nfs4_client *clp, u64 max)
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 24eec922685c..4c6d6c3f8eae 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -365,7 +365,6 @@ struct nfs4_openowner {
struct nfs4_lockowner {
struct nfs4_stateowner lo_owner; /* must be first element */
struct list_head lo_owner_ino_hash; /* hash by owner,file */
- struct list_head lo_perstateid;
struct list_head lo_list; /* for temporary uses */
};
@@ -434,7 +433,7 @@ struct nfs4_ol_stateid {
struct nfs4_stid st_stid; /* must be first field */
struct list_head st_perfile;
struct list_head st_perstateowner;
- struct list_head st_lockowners;
+ struct list_head st_locks;
struct nfs4_stateowner * st_stateowner;
struct nfs4_file * st_file;
unsigned long st_access_bmap;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 010/114] nfsd: Allow lockowners to hold several stateids
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (8 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 009/114] nfsd: lock owners are not per open stateid Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 011/114] nfsd: NFSv4 lock-owners are not associated to a specific file Jeff Layton
` (103 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
A lockowner can have more than one lock stateid. For instance, if a
process has more than one file open and has locks on both, then the same
lockowner has more than one stateid associated with it. Change it so
that this reality is better reflected by the objects that nfsd uses.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4state.c | 55 ++++++++++++++++++++++++++++++++---------------------
1 file changed, 33 insertions(+), 22 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index a3321601f55f..dfa68cce12c3 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3881,12 +3881,7 @@ nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp)
if (check_for_locks(stp->st_file, lo))
return nfserr_locks_held;
- /*
- * Currently there's a 1-1 lock stateid<->lockowner
- * correspondance, and we have to delete the lockowner when we
- * delete the lock stateid:
- */
- release_lockowner(lo);
+ release_lockowner_if_empty(lo);
return nfs_ok;
}
@@ -4408,6 +4403,19 @@ alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct
return stp;
}
+static struct nfs4_ol_stateid *
+find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
+{
+ struct nfs4_ol_stateid *lst;
+
+ list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) {
+ if (lst->st_file == fp)
+ return lst;
+ }
+ return NULL;
+}
+
+
static int
check_lock_length(u64 offset, u64 length)
{
@@ -4437,25 +4445,28 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, s
lo = find_lockowner_str(fi->fi_inode, &cl->cl_clientid,
&lock->v.new.owner, nn);
- if (lo) {
- if (!cstate->minorversion)
+ if (!lo) {
+ strhashval = ownerstr_hashval(cl->cl_clientid.cl_id,
+ &lock->v.new.owner);
+ lo = alloc_init_lock_stateowner(strhashval, cl, ost, lock);
+ if (lo == NULL)
+ return nfserr_jukebox;
+ } else {
+ /* with an existing lockowner, seqids must be the same */
+ if (!cstate->minorversion &&
+ lock->lk_new_lock_seqid != lo->lo_owner.so_seqid)
return nfserr_bad_seqid;
- /* XXX: a lockowner always has exactly one stateid: */
- *lst = list_first_entry(&lo->lo_owner.so_stateids,
- struct nfs4_ol_stateid, st_perstateowner);
- return nfs_ok;
}
- strhashval = ownerstr_hashval(cl->cl_clientid.cl_id,
- &lock->v.new.owner);
- lo = alloc_init_lock_stateowner(strhashval, cl, ost, lock);
- if (lo == NULL)
- return nfserr_jukebox;
- *lst = alloc_init_lock_stateid(lo, fi, ost);
+
+ *lst = find_lock_stateid(lo, fi);
if (*lst == NULL) {
- release_lockowner(lo);
- return nfserr_jukebox;
+ *lst = alloc_init_lock_stateid(lo, fi, ost);
+ if (*lst == NULL) {
+ release_lockowner_if_empty(lo);
+ return nfserr_jukebox;
+ }
+ *new = true;
}
- *new = true;
return nfs_ok;
}
@@ -4612,7 +4623,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
}
out:
if (status && new_state)
- release_lockowner(lock_sop);
+ release_lockowner_if_empty(lock_sop);
nfsd4_bump_seqid(cstate, status);
if (!cstate->replay_owner)
nfs4_unlock_state();
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 011/114] nfsd: NFSv4 lock-owners are not associated to a specific file
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (9 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 010/114] nfsd: Allow lockowners to hold several stateids Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 012/114] nfsd: clean up nfsd4_release_lockowner Jeff Layton
` (102 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Just like open-owners, lock-owners are associated with a name, a clientid
and, in the case of minor version 0, a sequence id. There is no association
to a file.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/netns.h | 4 ---
fs/nfsd/nfs4state.c | 73 ++++++++++-------------------------------------------
fs/nfsd/state.h | 1 -
3 files changed, 14 insertions(+), 64 deletions(-)
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index d32b3aa6600d..beaceac90ad3 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -29,9 +29,6 @@
#define CLIENT_HASH_SIZE (1 << CLIENT_HASH_BITS)
#define CLIENT_HASH_MASK (CLIENT_HASH_SIZE - 1)
-#define LOCKOWNER_INO_HASH_BITS 8
-#define LOCKOWNER_INO_HASH_SIZE (1 << LOCKOWNER_INO_HASH_BITS)
-
#define SESSION_HASH_SIZE 512
struct cld_net;
@@ -67,7 +64,6 @@ struct nfsd_net {
struct list_head *unconf_id_hashtbl;
struct rb_root unconf_name_tree;
struct list_head *ownerstr_hashtbl;
- struct list_head *lockowner_ino_hashtbl;
struct list_head *sessionid_hashtbl;
/*
* client_lru holds client queue ordered by nfs4_client.cl_time
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index dfa68cce12c3..e7b77c0ff15a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -719,7 +719,6 @@ static void unhash_lockowner(struct nfs4_lockowner *lo)
struct nfs4_ol_stateid *stp;
list_del(&lo->lo_owner.so_strhash);
- list_del(&lo->lo_owner_ino_hash);
while (!list_empty(&lo->lo_owner.so_stateids)) {
stp = list_first_entry(&lo->lo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
@@ -4236,8 +4235,6 @@ out:
#define LOFF_OVERFLOW(start, len) ((u64)(len) > ~(u64)(start))
-#define LOCKOWNER_INO_HASH_MASK (LOCKOWNER_INO_HASH_SIZE - 1)
-
static inline u64
end_offset(u64 start, u64 len)
{
@@ -4258,13 +4255,6 @@ last_byte_offset(u64 start, u64 len)
return end > start ? end - 1: NFS4_MAX_UINT64;
}
-static unsigned int lockowner_ino_hashval(struct inode *inode, u32 cl_id, struct xdr_netobj *ownername)
-{
- return (file_hashval(inode) + cl_id
- + opaque_hashval(ownername->data, ownername->len))
- & LOCKOWNER_INO_HASH_MASK;
-}
-
/*
* TODO: Linux file offsets are _signed_ 64-bit quantities, which means that
* we can't properly handle lock requests that go beyond the (2^63 - 1)-th
@@ -4317,46 +4307,23 @@ nevermind:
deny->ld_type = NFS4_WRITE_LT;
}
-static bool same_lockowner_ino(struct nfs4_lockowner *lo, struct inode *inode, clientid_t *clid, struct xdr_netobj *owner)
-{
- struct nfs4_ol_stateid *lst;
-
- if (!same_owner_str(&lo->lo_owner, owner, clid))
- return false;
- if (list_empty(&lo->lo_owner.so_stateids)) {
- WARN_ON_ONCE(1);
- return false;
- }
- lst = list_first_entry(&lo->lo_owner.so_stateids,
- struct nfs4_ol_stateid, st_perstateowner);
- return lst->st_file->fi_inode == inode;
-}
-
static struct nfs4_lockowner *
-find_lockowner_str(struct inode *inode, clientid_t *clid,
- struct xdr_netobj *owner, struct nfsd_net *nn)
+find_lockowner_str(clientid_t *clid, struct xdr_netobj *owner,
+ struct nfsd_net *nn)
{
- unsigned int hashval = lockowner_ino_hashval(inode, clid->cl_id, owner);
- struct nfs4_lockowner *lo;
+ unsigned int strhashval = ownerstr_hashval(clid->cl_id, owner);
+ struct nfs4_stateowner *so;
- list_for_each_entry(lo, &nn->lockowner_ino_hashtbl[hashval], lo_owner_ino_hash) {
- if (same_lockowner_ino(lo, inode, clid, owner))
- return lo;
+ list_for_each_entry(so, &nn->ownerstr_hashtbl[strhashval], so_strhash) {
+ if (so->so_is_open_owner)
+ continue;
+ if (!same_owner_str(so, owner, clid))
+ continue;
+ return lockowner(so);
}
return NULL;
}
-static void hash_lockowner(struct nfs4_lockowner *lo, unsigned int strhashval, struct nfs4_client *clp, struct nfs4_ol_stateid *open_stp)
-{
- struct inode *inode = open_stp->st_file->fi_inode;
- unsigned int inohash = lockowner_ino_hashval(inode,
- clp->cl_clientid.cl_id, &lo->lo_owner.so_owner);
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
-
- list_add(&lo->lo_owner.so_strhash, &nn->ownerstr_hashtbl[strhashval]);
- list_add(&lo->lo_owner_ino_hash, &nn->lockowner_ino_hashtbl[inohash]);
-}
-
/*
* Alloc a lock owner structure.
* Called in nfsd4_lock - therefore, OPEN and OPEN_CONFIRM (if needed) has
@@ -4364,10 +4331,10 @@ static void hash_lockowner(struct nfs4_lockowner *lo, unsigned int strhashval, s
*
* strhashval = ownerstr_hashval
*/
-
static struct nfs4_lockowner *
alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, struct nfs4_ol_stateid *open_stp, struct nfsd4_lock *lock) {
struct nfs4_lockowner *lo;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
lo = alloc_stateowner(lockowner_slab, &lock->lk_new_owner, clp);
if (!lo)
@@ -4377,7 +4344,7 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, str
/* It is the openowner seqid that will be incremented in encode in the
* case of new lockowners; so increment the lock seqid manually: */
lo->lo_owner.so_seqid = lock->lk_new_lock_seqid + 1;
- hash_lockowner(lo, strhashval, clp, open_stp);
+ list_add(&lo->lo_owner.so_strhash, &nn->ownerstr_hashtbl[strhashval]);
return lo;
}
@@ -4443,8 +4410,7 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, s
unsigned int strhashval;
struct nfsd_net *nn = net_generic(cl->net, nfsd_net_id);
- lo = find_lockowner_str(fi->fi_inode, &cl->cl_clientid,
- &lock->v.new.owner, nn);
+ lo = find_lockowner_str(&cl->cl_clientid, &lock->v.new.owner, nn);
if (!lo) {
strhashval = ownerstr_hashval(cl->cl_clientid.cl_id,
&lock->v.new.owner);
@@ -4658,7 +4624,6 @@ __be32
nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_lockt *lockt)
{
- struct inode *inode;
struct file_lock *file_lock = NULL;
struct nfs4_lockowner *lo;
__be32 status;
@@ -4681,7 +4646,6 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0)))
goto out;
- inode = cstate->current_fh.fh_dentry->d_inode;
file_lock = locks_alloc_lock();
if (!file_lock) {
dprintk("NFSD: %s: unable to allocate lock!\n", __func__);
@@ -4704,7 +4668,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out;
}
- lo = find_lockowner_str(inode, &lockt->lt_clientid, &lockt->lt_owner, nn);
+ lo = find_lockowner_str(&lockt->lt_clientid, &lockt->lt_owner, nn);
if (lo)
file_lock->fl_owner = (fl_owner_t)lo;
file_lock->fl_pid = current->tgid;
@@ -5198,10 +5162,6 @@ static int nfs4_state_create_net(struct net *net)
OWNER_HASH_SIZE, GFP_KERNEL);
if (!nn->ownerstr_hashtbl)
goto err_ownerstr;
- nn->lockowner_ino_hashtbl = kmalloc(sizeof(struct list_head) *
- LOCKOWNER_INO_HASH_SIZE, GFP_KERNEL);
- if (!nn->lockowner_ino_hashtbl)
- goto err_lockowner_ino;
nn->sessionid_hashtbl = kmalloc(sizeof(struct list_head) *
SESSION_HASH_SIZE, GFP_KERNEL);
if (!nn->sessionid_hashtbl)
@@ -5213,8 +5173,6 @@ static int nfs4_state_create_net(struct net *net)
}
for (i = 0; i < OWNER_HASH_SIZE; i++)
INIT_LIST_HEAD(&nn->ownerstr_hashtbl[i]);
- for (i = 0; i < LOCKOWNER_INO_HASH_SIZE; i++)
- INIT_LIST_HEAD(&nn->lockowner_ino_hashtbl[i]);
for (i = 0; i < SESSION_HASH_SIZE; i++)
INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]);
nn->conf_name_tree = RB_ROOT;
@@ -5230,8 +5188,6 @@ static int nfs4_state_create_net(struct net *net)
return 0;
err_sessionid:
- kfree(nn->lockowner_ino_hashtbl);
-err_lockowner_ino:
kfree(nn->ownerstr_hashtbl);
err_ownerstr:
kfree(nn->unconf_id_hashtbl);
@@ -5263,7 +5219,6 @@ nfs4_state_destroy_net(struct net *net)
}
kfree(nn->sessionid_hashtbl);
- kfree(nn->lockowner_ino_hashtbl);
kfree(nn->ownerstr_hashtbl);
kfree(nn->unconf_id_hashtbl);
kfree(nn->conf_id_hashtbl);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 4c6d6c3f8eae..2fe58f5f4833 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -364,7 +364,6 @@ struct nfs4_openowner {
struct nfs4_lockowner {
struct nfs4_stateowner lo_owner; /* must be first element */
- struct list_head lo_owner_ino_hash; /* hash by owner,file */
struct list_head lo_list; /* for temporary uses */
};
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 012/114] nfsd: clean up nfsd4_release_lockowner
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (10 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 011/114] nfsd: NFSv4 lock-owners are not associated to a specific file Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 18:02 ` Christoph Hellwig
2014-06-30 15:48 ` [PATCH v3 013/114] nfsd: Don't get a session reference without a client reference Jeff Layton
` (101 subsequent siblings)
113 siblings, 1 reply; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Now that we know that we won't have several lockowners with the same,
owner->data, we can simplify nfsd4_release_lockowner and get rid of
the lo_list in the process.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 46 ++++++++++++++++++++++------------------------
fs/nfsd/state.h | 1 -
2 files changed, 22 insertions(+), 25 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e7b77c0ff15a..65b093d2aa16 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4794,11 +4794,10 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
struct nfsd4_release_lockowner *rlockowner)
{
clientid_t *clid = &rlockowner->rl_clientid;
- struct nfs4_stateowner *sop;
+ struct nfs4_stateowner *sop = NULL, *tmp;
struct nfs4_lockowner *lo;
struct nfs4_ol_stateid *stp;
struct xdr_netobj *owner = &rlockowner->rl_owner;
- struct list_head matches;
unsigned int hashval = ownerstr_hashval(clid->cl_id, owner);
__be32 status;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
@@ -4813,33 +4812,32 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
goto out;
status = nfserr_locks_held;
- INIT_LIST_HEAD(&matches);
- list_for_each_entry(sop, &nn->ownerstr_hashtbl[hashval], so_strhash) {
- if (sop->so_is_open_owner)
- continue;
- if (!same_owner_str(sop, owner, clid))
+ /* Find the matching lock stateowner */
+ list_for_each_entry(tmp, &nn->ownerstr_hashtbl[hashval], so_strhash) {
+ if (tmp->so_is_open_owner)
continue;
- list_for_each_entry(stp, &sop->so_stateids,
- st_perstateowner) {
- lo = lockowner(sop);
- if (check_for_locks(stp->st_file, lo))
- goto out;
- list_add(&lo->lo_list, &matches);
+ if (same_owner_str(tmp, owner, clid)) {
+ sop = tmp;
+ break;
}
}
- /* Clients probably won't expect us to return with some (but not all)
- * of the lockowner state released; so don't release any until all
- * have been checked. */
- status = nfs_ok;
- while (!list_empty(&matches)) {
- lo = list_entry(matches.next, struct nfs4_lockowner,
- lo_list);
- /* unhash_stateowner deletes so_perclient only
- * for openowners. */
- list_del(&lo->lo_list);
- release_lockowner(lo);
+
+ /* No matching owner found, maybe a replay? Just declare victory... */
+ if (!sop) {
+ status = nfs_ok;
+ goto out;
+ }
+
+ lo = lockowner(sop);
+ /* see if there are still any locks associated with it */
+ list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) {
+ if (check_for_locks(stp->st_file, lo))
+ goto out;
}
+
+ status = nfs_ok;
+ release_lockowner(lo);
out:
nfs4_unlock_state();
return status;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 2fe58f5f4833..a7d13cd97921 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -364,7 +364,6 @@ struct nfs4_openowner {
struct nfs4_lockowner {
struct nfs4_stateowner lo_owner; /* must be first element */
- struct list_head lo_list; /* for temporary uses */
};
static inline struct nfs4_openowner * openowner(struct nfs4_stateowner *so)
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 013/114] nfsd: Don't get a session reference without a client reference
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (11 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 012/114] nfsd: clean up nfsd4_release_lockowner Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 014/114] nfsd: Cleanup - Let nfsd4_lookup_stateid() take a cstate argument Jeff Layton
` (100 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
If the client were to disappear from underneath us while we're holding
a session reference, things would be bad. This cleanup helps ensure
that it cannot, which will be a possibility when the client_mutex is
removed.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4state.c | 112 +++++++++++++++++++++++++++++++---------------------
fs/nfsd/state.h | 2 -
2 files changed, 68 insertions(+), 46 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 65b093d2aa16..8c9b1498aa38 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -103,12 +103,6 @@ static bool is_session_dead(struct nfsd4_session *ses)
return ses->se_flags & NFS4_SESSION_DEAD;
}
-void nfsd4_put_session(struct nfsd4_session *ses)
-{
- if (atomic_dec_and_test(&ses->se_ref) && is_session_dead(ses))
- free_session(ses);
-}
-
static __be32 mark_session_dead_locked(struct nfsd4_session *ses, int ref_held_by_me)
{
if (atomic_read(&ses->se_ref) > ref_held_by_me)
@@ -117,14 +111,6 @@ static __be32 mark_session_dead_locked(struct nfsd4_session *ses, int ref_held_b
return nfs_ok;
}
-static __be32 nfsd4_get_session_locked(struct nfsd4_session *ses)
-{
- if (is_session_dead(ses))
- return nfserr_badsession;
- atomic_inc(&ses->se_ref);
- return nfs_ok;
-}
-
void
nfs4_unlock_state(void)
{
@@ -203,6 +189,39 @@ static void put_client_renew_locked(struct nfs4_client *clp)
renew_client_locked(clp);
}
+static __be32 nfsd4_get_session_locked(struct nfsd4_session *ses)
+{
+ __be32 status;
+
+ if (is_session_dead(ses))
+ return nfserr_badsession;
+ status = get_client_locked(ses->se_client);
+ if (status)
+ return status;
+ atomic_inc(&ses->se_ref);
+ return nfs_ok;
+}
+
+static void nfsd4_put_session_locked(struct nfsd4_session *ses)
+{
+ struct nfs4_client *clp = ses->se_client;
+
+ if (atomic_dec_and_test(&ses->se_ref) && is_session_dead(ses))
+ free_session(ses);
+ put_client_renew_locked(clp);
+}
+
+static void nfsd4_put_session(struct nfsd4_session *ses)
+{
+ struct nfs4_client *clp = ses->se_client;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ spin_lock(&nn->client_lock);
+ nfsd4_put_session_locked(ses);
+ spin_unlock(&nn->client_lock);
+}
+
+
static inline u32
opaque_hashval(const void *ptr, int nbytes)
{
@@ -1126,7 +1145,7 @@ static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, stru
/* caller must hold client_lock */
static struct nfsd4_session *
-find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net)
+__find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net)
{
struct nfsd4_session *elem;
int idx;
@@ -1146,6 +1165,24 @@ find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net)
return NULL;
}
+static struct nfsd4_session *
+find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net,
+ __be32 *ret)
+{
+ struct nfsd4_session *session;
+ __be32 status = nfserr_badsession;
+
+ session = __find_in_sessionid_hashtbl(sessionid, net);
+ if (!session)
+ goto out;
+ status = nfsd4_get_session_locked(session);
+ if (status)
+ session = NULL;
+out:
+ *ret = status;
+ return session;
+}
+
/* caller must hold client_lock */
static void
unhash_session(struct nfsd4_session *ses)
@@ -2161,17 +2198,17 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
__be32 status;
struct nfsd4_conn *conn;
struct nfsd4_session *session;
- struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+ struct net *net = SVC_NET(rqstp);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (!nfsd4_last_compound_op(rqstp))
return nfserr_not_only_op;
nfs4_lock_state();
spin_lock(&nn->client_lock);
- session = find_in_sessionid_hashtbl(&bcts->sessionid, SVC_NET(rqstp));
+ session = find_in_sessionid_hashtbl(&bcts->sessionid, net, &status);
spin_unlock(&nn->client_lock);
- status = nfserr_badsession;
if (!session)
- goto out;
+ goto out_no_session;
status = nfserr_wrong_cred;
if (!mach_creds_match(session->se_client, rqstp))
goto out;
@@ -2185,6 +2222,8 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
nfsd4_init_conn(rqstp, conn, session);
status = nfs_ok;
out:
+ nfsd4_put_session(session);
+out_no_session:
nfs4_unlock_state();
return status;
}
@@ -2204,7 +2243,8 @@ nfsd4_destroy_session(struct svc_rqst *r,
struct nfsd4_session *ses;
__be32 status;
int ref_held_by_me = 0;
- struct nfsd_net *nn = net_generic(SVC_NET(r), nfsd_net_id);
+ struct net *net = SVC_NET(r);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
nfs4_lock_state();
status = nfserr_not_only_op;
@@ -2215,14 +2255,12 @@ nfsd4_destroy_session(struct svc_rqst *r,
}
dump_sessionid(__func__, &sessionid->sessionid);
spin_lock(&nn->client_lock);
- ses = find_in_sessionid_hashtbl(&sessionid->sessionid, SVC_NET(r));
- status = nfserr_badsession;
+ ses = find_in_sessionid_hashtbl(&sessionid->sessionid, net, &status);
if (!ses)
goto out_client_lock;
status = nfserr_wrong_cred;
if (!mach_creds_match(ses->se_client, r))
- goto out_client_lock;
- nfsd4_get_session_locked(ses);
+ goto out_put_session;
status = mark_session_dead_locked(ses, 1 + ref_held_by_me);
if (status)
goto out_put_session;
@@ -2234,7 +2272,7 @@ nfsd4_destroy_session(struct svc_rqst *r,
spin_lock(&nn->client_lock);
status = nfs_ok;
out_put_session:
- nfsd4_put_session(ses);
+ nfsd4_put_session_locked(ses);
out_client_lock:
spin_unlock(&nn->client_lock);
out:
@@ -2309,7 +2347,8 @@ nfsd4_sequence(struct svc_rqst *rqstp,
struct nfsd4_conn *conn;
__be32 status;
int buflen;
- struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+ struct net *net = SVC_NET(rqstp);
+ struct nfsd_net *nn = net_generic(net, nfsd_net_id);
if (resp->opcnt != 1)
return nfserr_sequence_pos;
@@ -2323,17 +2362,10 @@ nfsd4_sequence(struct svc_rqst *rqstp,
return nfserr_jukebox;
spin_lock(&nn->client_lock);
- status = nfserr_badsession;
- session = find_in_sessionid_hashtbl(&seq->sessionid, SVC_NET(rqstp));
+ session = find_in_sessionid_hashtbl(&seq->sessionid, net, &status);
if (!session)
goto out_no_session;
clp = session->se_client;
- status = get_client_locked(clp);
- if (status)
- goto out_no_session;
- status = nfsd4_get_session_locked(session);
- if (status)
- goto out_put_client;
status = nfserr_too_many_ops;
if (nfsd4_session_too_many_ops(rqstp, session))
@@ -2417,9 +2449,7 @@ out_no_session:
spin_unlock(&nn->client_lock);
return status;
out_put_session:
- nfsd4_put_session(session);
-out_put_client:
- put_client_renew_locked(clp);
+ nfsd4_put_session_locked(session);
goto out_no_session;
}
@@ -2429,18 +2459,12 @@ nfsd4_sequence_done(struct nfsd4_compoundres *resp)
struct nfsd4_compound_state *cs = &resp->cstate;
if (nfsd4_has_session(cs)) {
- struct nfs4_client *clp = cs->session->se_client;
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
-
if (cs->status != nfserr_replay_cache) {
nfsd4_store_cache_entry(resp);
cs->slot->sl_flags &= ~NFSD4_SLOT_INUSE;
}
- /* Renew the clientid on success and on replay */
- spin_lock(&nn->client_lock);
+ /* Drop session reference that was taken in nfsd4_sequence() */
nfsd4_put_session(cs->session);
- put_client_renew_locked(clp);
- spin_unlock(&nn->client_lock);
}
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index a7d13cd97921..305414a083c5 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -212,8 +212,6 @@ struct nfsd4_session {
struct nfsd4_slot *se_slots[]; /* forward channel slots */
};
-extern void nfsd4_put_session(struct nfsd4_session *ses);
-
/* formatted contents of nfs4_sessionid */
struct nfsd4_sessionid {
clientid_t clientid;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 014/114] nfsd: Cleanup - Let nfsd4_lookup_stateid() take a cstate argument
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (12 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 013/114] nfsd: Don't get a session reference without a client reference Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client Jeff Layton
` (99 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
The cstate already holds information about the session, and hence
the client id, so it makes more sense to pass that information
rather than the current practice of passing a 'minor version' number.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4state.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 8c9b1498aa38..e9bb39ecebae 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3792,12 +3792,14 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
}
}
-static __be32 nfsd4_lookup_stateid(stateid_t *stateid, unsigned char typemask,
- struct nfs4_stid **s, bool sessions,
- struct nfsd_net *nn)
+static __be32
+nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
+ stateid_t *stateid, unsigned char typemask,
+ struct nfs4_stid **s, struct nfsd_net *nn)
{
struct nfs4_client *cl;
__be32 status;
+ bool sessions = cstate->minorversion != 0;
if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
return nfserr_bad_stateid;
@@ -3843,9 +3845,9 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
nfs4_lock_state();
- status = nfsd4_lookup_stateid(stateid,
+ status = nfsd4_lookup_stateid(cstate, stateid,
NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
- &s, cstate->minorversion, nn);
+ &s, nn);
if (status)
goto out;
status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate));
@@ -4015,8 +4017,7 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
seqid, STATEID_VAL(stateid));
*stpp = NULL;
- status = nfsd4_lookup_stateid(stateid, typemask, &s,
- cstate->minorversion, nn);
+ status = nfsd4_lookup_stateid(cstate, stateid, typemask, &s, nn);
if (status)
return status;
stp = openlockstateid(s);
@@ -4240,8 +4241,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return status;
nfs4_lock_state();
- status = nfsd4_lookup_stateid(stateid, NFS4_DELEG_STID, &s,
- cstate->minorversion, nn);
+ status = nfsd4_lookup_stateid(cstate, stateid, NFS4_DELEG_STID, &s, nn);
if (status)
goto out;
dp = delegstateid(s);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (13 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 014/114] nfsd: Cleanup - Let nfsd4_lookup_stateid() take a cstate argument Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 18:03 ` Christoph Hellwig
` (2 more replies)
2014-06-30 15:48 ` [PATCH v3 016/114] nfsd: Convert nfsd4_process_open1() to work with lookup_clientid() Jeff Layton
` (98 subsequent siblings)
113 siblings, 3 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
We want to use the nfsd4_compound_state to cache the nfs4_client in
order to optimise away extra lookups of the clid.
In the v4.0 case, we use this to ensure that we only have to look up the
client at most once per compound for each call into lookup_clientid. For
v4.1+ we set the pointer in the cstate during SEQUENCE processing so we
should never need to do a search for it.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 74 +++++++++++++++++++++++++++++++++++++----------------
fs/nfsd/xdr4.h | 1 +
2 files changed, 53 insertions(+), 22 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e9bb39ecebae..4d162a0e4c6d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -189,6 +189,15 @@ static void put_client_renew_locked(struct nfs4_client *clp)
renew_client_locked(clp);
}
+static void put_client_renew(struct nfs4_client *clp)
+{
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ spin_lock(&nn->client_lock);
+ put_client_renew_locked(clp);
+ spin_unlock(&nn->client_lock);
+}
+
static __be32 nfsd4_get_session_locked(struct nfsd4_session *ses)
{
__be32 status;
@@ -2395,6 +2404,7 @@ nfsd4_sequence(struct svc_rqst *rqstp,
goto out_put_session;
cstate->slot = slot;
cstate->session = session;
+ cstate->clp = clp;
/* Return the cached reply status and set cstate->status
* for nfsd4_proc_compound processing */
status = nfsd4_replay_cache_entry(resp, seq);
@@ -2429,6 +2439,7 @@ nfsd4_sequence(struct svc_rqst *rqstp,
cstate->slot = slot;
cstate->session = session;
+ cstate->clp = clp;
out:
switch (clp->cl_cb_state) {
@@ -2465,7 +2476,8 @@ nfsd4_sequence_done(struct nfsd4_compoundres *resp)
}
/* Drop session reference that was taken in nfsd4_sequence() */
nfsd4_put_session(cs->session);
- }
+ } else if (cs->clp)
+ put_client_renew(cs->clp);
}
__be32
@@ -2997,6 +3009,38 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4
return nfserr_bad_seqid;
}
+static __be32 lookup_clientid(clientid_t *clid,
+ struct nfsd4_compound_state *cstate,
+ struct nfsd_net *nn)
+{
+ struct nfs4_client *found;
+
+ if (cstate->clp) {
+ found = cstate->clp;
+ if (!same_clid(&found->cl_clientid, clid))
+ return nfserr_stale_clientid;
+ return nfs_ok;
+ }
+
+ if (STALE_CLIENTID(clid, nn))
+ return nfserr_stale_clientid;
+
+ /*
+ * For v4.1+ we get the client in the SEQUENCE op. If we don't have one
+ * cached already then we know this is for is for v4.0 and "sessions"
+ * will be false.
+ */
+ WARN_ON_ONCE(cstate->session);
+ found = find_confirmed_client(clid, false, nn);
+ if (!found)
+ return nfserr_expired;
+
+ /* Cache the nfs4_client in cstate! */
+ cstate->clp = found;
+ atomic_inc(&found->cl_refcount);
+ return nfs_ok;
+}
+
__be32
nfsd4_process_open1(struct nfsd4_compound_state *cstate,
struct nfsd4_open *open, struct nfsd_net *nn)
@@ -3509,18 +3553,6 @@ void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status)
free_generic_stateid(open->op_stp);
}
-static __be32 lookup_clientid(clientid_t *clid, bool session, struct nfsd_net *nn, struct nfs4_client **clp)
-{
- struct nfs4_client *found;
-
- if (STALE_CLIENTID(clid, nn))
- return nfserr_stale_clientid;
- found = find_confirmed_client(clid, session, nn);
- if (clp)
- *clp = found;
- return found ? nfs_ok : nfserr_expired;
-}
-
__be32
nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
clientid_t *clid)
@@ -3532,9 +3564,10 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfs4_lock_state();
dprintk("process_renew(%08x/%08x): starting\n",
clid->cl_boot, clid->cl_id);
- status = lookup_clientid(clid, cstate->minorversion, nn, &clp);
+ status = lookup_clientid(clid, cstate, nn);
if (status)
goto out;
+ clp = cstate->clp;
status = nfserr_cb_path_down;
if (!list_empty(&clp->cl_delegations)
&& clp->cl_cb_state != NFSD4_CB_UP)
@@ -3797,22 +3830,19 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
stateid_t *stateid, unsigned char typemask,
struct nfs4_stid **s, struct nfsd_net *nn)
{
- struct nfs4_client *cl;
__be32 status;
- bool sessions = cstate->minorversion != 0;
if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
return nfserr_bad_stateid;
- status = lookup_clientid(&stateid->si_opaque.so_clid, sessions,
- nn, &cl);
+ status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn);
if (status == nfserr_stale_clientid) {
- if (sessions)
+ if (cstate->session)
return nfserr_bad_stateid;
return nfserr_stale_stateid;
}
if (status)
return status;
- *s = find_stateid_by_type(cl, stateid, typemask);
+ *s = find_stateid_by_type(cstate->clp, stateid, typemask);
if (!*s)
return nfserr_bad_stateid;
return nfs_ok;
@@ -4662,7 +4692,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfs4_lock_state();
if (!nfsd4_has_session(cstate)) {
- status = lookup_clientid(&lockt->lt_clientid, false, nn, NULL);
+ status = lookup_clientid(&lockt->lt_clientid, cstate, nn);
if (status)
goto out;
}
@@ -4831,7 +4861,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
nfs4_lock_state();
- status = lookup_clientid(clid, cstate->minorversion, nn, NULL);
+ status = lookup_clientid(clid, cstate, nn);
if (status)
goto out;
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 7d8af164523b..312f6483a48e 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -55,6 +55,7 @@ struct nfsd4_compound_state {
struct svc_fh current_fh;
struct svc_fh save_fh;
struct nfs4_stateowner *replay_owner;
+ struct nfs4_client *clp;
/* For sessions DRC */
struct nfsd4_session *session;
struct nfsd4_slot *slot;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-06-30 15:48 ` [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client Jeff Layton
@ 2014-06-30 18:03 ` Christoph Hellwig
2014-07-03 15:18 ` J. Bruce Fields
2014-07-03 20:32 ` J. Bruce Fields
2 siblings, 0 replies; 151+ messages in thread
From: Christoph Hellwig @ 2014-06-30 18:03 UTC (permalink / raw)
To: Jeff Layton; +Cc: bfields, linux-nfs
On Mon, Jun 30, 2014 at 11:48:44AM -0400, Jeff Layton wrote:
> We want to use the nfsd4_compound_state to cache the nfs4_client in
> order to optimise away extra lookups of the clid.
>
> In the v4.0 case, we use this to ensure that we only have to look up the
> client at most once per compound for each call into lookup_clientid. For
> v4.1+ we set the pointer in the cstate during SEQUENCE processing so we
> should never need to do a search for it.
>
> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Looks good,
Reviewed-by: Christoph Hellwig <hch@lst.de>
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-06-30 15:48 ` [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client Jeff Layton
2014-06-30 18:03 ` Christoph Hellwig
@ 2014-07-03 15:18 ` J. Bruce Fields
2014-07-03 15:20 ` Jeff Layton
2014-07-03 20:32 ` J. Bruce Fields
2 siblings, 1 reply; 151+ messages in thread
From: J. Bruce Fields @ 2014-07-03 15:18 UTC (permalink / raw)
To: Jeff Layton; +Cc: linux-nfs
On Mon, Jun 30, 2014 at 11:48:44AM -0400, Jeff Layton wrote:
> @@ -2997,6 +3009,38 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4
> return nfserr_bad_seqid;
> }
>
> +static __be32 lookup_clientid(clientid_t *clid,
> + struct nfsd4_compound_state *cstate,
> + struct nfsd_net *nn)
> +{
> + struct nfs4_client *found;
> +
> + if (cstate->clp) {
> + found = cstate->clp;
> + if (!same_clid(&found->cl_clientid, clid))
> + return nfserr_stale_clientid;
That's new behavior, isn't it?
But sending a single compound that references multiple clients sounds
nuts even in the 4.0 case, OK. Applying.
(And I've merged all but the delegation locking change up through here
so far.)
--b.
> + return nfs_ok;
> + }
> +
> + if (STALE_CLIENTID(clid, nn))
> + return nfserr_stale_clientid;
> +
> + /*
> + * For v4.1+ we get the client in the SEQUENCE op. If we don't have one
> + * cached already then we know this is for is for v4.0 and "sessions"
> + * will be false.
> + */
> + WARN_ON_ONCE(cstate->session);
> + found = find_confirmed_client(clid, false, nn);
> + if (!found)
> + return nfserr_expired;
> +
> + /* Cache the nfs4_client in cstate! */
> + cstate->clp = found;
> + atomic_inc(&found->cl_refcount);
> + return nfs_ok;
> +}
> +
> __be32
> nfsd4_process_open1(struct nfsd4_compound_state *cstate,
> struct nfsd4_open *open, struct nfsd_net *nn)
> @@ -3509,18 +3553,6 @@ void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status)
> free_generic_stateid(open->op_stp);
> }
>
> -static __be32 lookup_clientid(clientid_t *clid, bool session, struct nfsd_net *nn, struct nfs4_client **clp)
> -{
> - struct nfs4_client *found;
> -
> - if (STALE_CLIENTID(clid, nn))
> - return nfserr_stale_clientid;
> - found = find_confirmed_client(clid, session, nn);
> - if (clp)
> - *clp = found;
> - return found ? nfs_ok : nfserr_expired;
> -}
> -
> __be32
> nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
> clientid_t *clid)
> @@ -3532,9 +3564,10 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
> nfs4_lock_state();
> dprintk("process_renew(%08x/%08x): starting\n",
> clid->cl_boot, clid->cl_id);
> - status = lookup_clientid(clid, cstate->minorversion, nn, &clp);
> + status = lookup_clientid(clid, cstate, nn);
> if (status)
> goto out;
> + clp = cstate->clp;
> status = nfserr_cb_path_down;
> if (!list_empty(&clp->cl_delegations)
> && clp->cl_cb_state != NFSD4_CB_UP)
> @@ -3797,22 +3830,19 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
> stateid_t *stateid, unsigned char typemask,
> struct nfs4_stid **s, struct nfsd_net *nn)
> {
> - struct nfs4_client *cl;
> __be32 status;
> - bool sessions = cstate->minorversion != 0;
>
> if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
> return nfserr_bad_stateid;
> - status = lookup_clientid(&stateid->si_opaque.so_clid, sessions,
> - nn, &cl);
> + status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn);
> if (status == nfserr_stale_clientid) {
> - if (sessions)
> + if (cstate->session)
> return nfserr_bad_stateid;
> return nfserr_stale_stateid;
> }
> if (status)
> return status;
> - *s = find_stateid_by_type(cl, stateid, typemask);
> + *s = find_stateid_by_type(cstate->clp, stateid, typemask);
> if (!*s)
> return nfserr_bad_stateid;
> return nfs_ok;
> @@ -4662,7 +4692,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
> nfs4_lock_state();
>
> if (!nfsd4_has_session(cstate)) {
> - status = lookup_clientid(&lockt->lt_clientid, false, nn, NULL);
> + status = lookup_clientid(&lockt->lt_clientid, cstate, nn);
> if (status)
> goto out;
> }
> @@ -4831,7 +4861,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
>
> nfs4_lock_state();
>
> - status = lookup_clientid(clid, cstate->minorversion, nn, NULL);
> + status = lookup_clientid(clid, cstate, nn);
> if (status)
> goto out;
>
> diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
> index 7d8af164523b..312f6483a48e 100644
> --- a/fs/nfsd/xdr4.h
> +++ b/fs/nfsd/xdr4.h
> @@ -55,6 +55,7 @@ struct nfsd4_compound_state {
> struct svc_fh current_fh;
> struct svc_fh save_fh;
> struct nfs4_stateowner *replay_owner;
> + struct nfs4_client *clp;
> /* For sessions DRC */
> struct nfsd4_session *session;
> struct nfsd4_slot *slot;
> --
> 1.9.3
>
^ permalink raw reply [flat|nested] 151+ messages in thread* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-07-03 15:18 ` J. Bruce Fields
@ 2014-07-03 15:20 ` Jeff Layton
2014-07-03 15:32 ` J. Bruce Fields
0 siblings, 1 reply; 151+ messages in thread
From: Jeff Layton @ 2014-07-03 15:20 UTC (permalink / raw)
To: J. Bruce Fields; +Cc: linux-nfs
On Thu, 3 Jul 2014 11:18:19 -0400
"J. Bruce Fields" <bfields@fieldses.org> wrote:
> On Mon, Jun 30, 2014 at 11:48:44AM -0400, Jeff Layton wrote:
> > @@ -2997,6 +3009,38 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4
> > return nfserr_bad_seqid;
> > }
> >
> > +static __be32 lookup_clientid(clientid_t *clid,
> > + struct nfsd4_compound_state *cstate,
> > + struct nfsd_net *nn)
> > +{
> > + struct nfs4_client *found;
> > +
> > + if (cstate->clp) {
> > + found = cstate->clp;
> > + if (!same_clid(&found->cl_clientid, clid))
> > + return nfserr_stale_clientid;
>
> That's new behavior, isn't it?
>
Yeah, I suppose it is, but it's hard to understand a valid use-case for
sending multiple ops in a compound with different clientids. Certainly
no well-behaved client would do that, would it? (Hmm, that might be an
interesting pynfs test, come to think of it).
> But sending a single compound that references multiple clients sounds
> nuts even in the 4.0 case, OK. Applying.
>
> (And I've merged all but the delegation locking change up through here
> so far.)
>
> --b.
>
Thanks!
> > + return nfs_ok;
> > + }
> > +
> > + if (STALE_CLIENTID(clid, nn))
> > + return nfserr_stale_clientid;
> > +
> > + /*
> > + * For v4.1+ we get the client in the SEQUENCE op. If we
> > don't have one
> > + * cached already then we know this is for is for v4.0 and
> > "sessions"
> > + * will be false.
> > + */
> > + WARN_ON_ONCE(cstate->session);
> > + found = find_confirmed_client(clid, false, nn);
> > + if (!found)
> > + return nfserr_expired;
> > +
> > + /* Cache the nfs4_client in cstate! */
> > + cstate->clp = found;
> > + atomic_inc(&found->cl_refcount);
> > + return nfs_ok;
> > +}
> > +
> > __be32
> > nfsd4_process_open1(struct nfsd4_compound_state *cstate,
> > struct nfsd4_open *open, struct nfsd_net *nn)
> > @@ -3509,18 +3553,6 @@ void nfsd4_cleanup_open_state(struct
> > nfsd4_open *open, __be32 status) free_generic_stateid(open->op_stp);
> > }
> >
> > -static __be32 lookup_clientid(clientid_t *clid, bool session,
> > struct nfsd_net *nn, struct nfs4_client **clp) -{
> > - struct nfs4_client *found;
> > -
> > - if (STALE_CLIENTID(clid, nn))
> > - return nfserr_stale_clientid;
> > - found = find_confirmed_client(clid, session, nn);
> > - if (clp)
> > - *clp = found;
> > - return found ? nfs_ok : nfserr_expired;
> > -}
> > -
> > __be32
> > nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state
> > *cstate, clientid_t *clid)
> > @@ -3532,9 +3564,10 @@ nfsd4_renew(struct svc_rqst *rqstp, struct
> > nfsd4_compound_state *cstate, nfs4_lock_state();
> > dprintk("process_renew(%08x/%08x): starting\n",
> > clid->cl_boot, clid->cl_id);
> > - status = lookup_clientid(clid, cstate->minorversion, nn,
> > &clp);
> > + status = lookup_clientid(clid, cstate, nn);
> > if (status)
> > goto out;
> > + clp = cstate->clp;
> > status = nfserr_cb_path_down;
> > if (!list_empty(&clp->cl_delegations)
> > && clp->cl_cb_state != NFSD4_CB_UP)
> > @@ -3797,22 +3830,19 @@ nfsd4_lookup_stateid(struct
> > nfsd4_compound_state *cstate, stateid_t *stateid, unsigned char
> > typemask, struct nfs4_stid **s, struct nfsd_net *nn)
> > {
> > - struct nfs4_client *cl;
> > __be32 status;
> > - bool sessions = cstate->minorversion != 0;
> >
> > if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
> > return nfserr_bad_stateid;
> > - status = lookup_clientid(&stateid->si_opaque.so_clid,
> > sessions,
> > - nn, &cl);
> > + status = lookup_clientid(&stateid->si_opaque.so_clid,
> > cstate, nn); if (status == nfserr_stale_clientid) {
> > - if (sessions)
> > + if (cstate->session)
> > return nfserr_bad_stateid;
> > return nfserr_stale_stateid;
> > }
> > if (status)
> > return status;
> > - *s = find_stateid_by_type(cl, stateid, typemask);
> > + *s = find_stateid_by_type(cstate->clp, stateid, typemask);
> > if (!*s)
> > return nfserr_bad_stateid;
> > return nfs_ok;
> > @@ -4662,7 +4692,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct
> > nfsd4_compound_state *cstate, nfs4_lock_state();
> >
> > if (!nfsd4_has_session(cstate)) {
> > - status = lookup_clientid(&lockt->lt_clientid,
> > false, nn, NULL);
> > + status = lookup_clientid(&lockt->lt_clientid,
> > cstate, nn); if (status)
> > goto out;
> > }
> > @@ -4831,7 +4861,7 @@ nfsd4_release_lockowner(struct svc_rqst
> > *rqstp,
> > nfs4_lock_state();
> >
> > - status = lookup_clientid(clid, cstate->minorversion, nn,
> > NULL);
> > + status = lookup_clientid(clid, cstate, nn);
> > if (status)
> > goto out;
> >
> > diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
> > index 7d8af164523b..312f6483a48e 100644
> > --- a/fs/nfsd/xdr4.h
> > +++ b/fs/nfsd/xdr4.h
> > @@ -55,6 +55,7 @@ struct nfsd4_compound_state {
> > struct svc_fh current_fh;
> > struct svc_fh save_fh;
> > struct nfs4_stateowner *replay_owner;
> > + struct nfs4_client *clp;
> > /* For sessions DRC */
> > struct nfsd4_session *session;
> > struct nfsd4_slot *slot;
> > --
> > 1.9.3
> >
--
Jeff Layton <jlayton@primarydata.com>
^ permalink raw reply [flat|nested] 151+ messages in thread* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-07-03 15:20 ` Jeff Layton
@ 2014-07-03 15:32 ` J. Bruce Fields
2014-07-03 15:37 ` Jeff Layton
2014-07-03 16:11 ` Christoph Hellwig
0 siblings, 2 replies; 151+ messages in thread
From: J. Bruce Fields @ 2014-07-03 15:32 UTC (permalink / raw)
To: Jeff Layton; +Cc: linux-nfs
On Thu, Jul 03, 2014 at 11:20:50AM -0400, Jeff Layton wrote:
> On Thu, 3 Jul 2014 11:18:19 -0400
> "J. Bruce Fields" <bfields@fieldses.org> wrote:
>
> > On Mon, Jun 30, 2014 at 11:48:44AM -0400, Jeff Layton wrote:
> > > @@ -2997,6 +3009,38 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4
> > > return nfserr_bad_seqid;
> > > }
> > >
> > > +static __be32 lookup_clientid(clientid_t *clid,
> > > + struct nfsd4_compound_state *cstate,
> > > + struct nfsd_net *nn)
> > > +{
> > > + struct nfs4_client *found;
> > > +
> > > + if (cstate->clp) {
> > > + found = cstate->clp;
> > > + if (!same_clid(&found->cl_clientid, clid))
> > > + return nfserr_stale_clientid;
> >
> > That's new behavior, isn't it?
> >
>
> Yeah, I suppose it is, but it's hard to understand a valid use-case for
> sending multiple ops in a compound with different clientids. Certainly
> no well-behaved client would do that, would it? (Hmm, that might be an
> interesting pynfs test, come to think of it).
We could ask for a clarification in 3530bis if there's not already
something there that clearly forbids this, but I'm not sure if it's even
worth it.
--b.
^ permalink raw reply [flat|nested] 151+ messages in thread* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-07-03 15:32 ` J. Bruce Fields
@ 2014-07-03 15:37 ` Jeff Layton
2014-07-03 16:11 ` Christoph Hellwig
1 sibling, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-07-03 15:37 UTC (permalink / raw)
To: J. Bruce Fields; +Cc: Jeff Layton, linux-nfs, Tom Haynes
On Thu, 3 Jul 2014 11:32:08 -0400
"J. Bruce Fields" <bfields@fieldses.org> wrote:
> On Thu, Jul 03, 2014 at 11:20:50AM -0400, Jeff Layton wrote:
> > On Thu, 3 Jul 2014 11:18:19 -0400
> > "J. Bruce Fields" <bfields@fieldses.org> wrote:
> >
> > > On Mon, Jun 30, 2014 at 11:48:44AM -0400, Jeff Layton wrote:
> > > > @@ -2997,6 +3009,38 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4
> > > > return nfserr_bad_seqid;
> > > > }
> > > >
> > > > +static __be32 lookup_clientid(clientid_t *clid,
> > > > + struct nfsd4_compound_state *cstate,
> > > > + struct nfsd_net *nn)
> > > > +{
> > > > + struct nfs4_client *found;
> > > > +
> > > > + if (cstate->clp) {
> > > > + found = cstate->clp;
> > > > + if (!same_clid(&found->cl_clientid, clid))
> > > > + return nfserr_stale_clientid;
> > >
> > > That's new behavior, isn't it?
> > >
> >
> > Yeah, I suppose it is, but it's hard to understand a valid use-case for
> > sending multiple ops in a compound with different clientids. Certainly
> > no well-behaved client would do that, would it? (Hmm, that might be an
> > interesting pynfs test, come to think of it).
>
> We could ask for a clarification in 3530bis if there's not already
> something there that clearly forbids this, but I'm not sure if it's even
> worth it.
>
I'm not inclined to pursue it, unless Tom thinks it's worthwhile. Tom,
do you happen to care?
--
Jeff Layton <jlayton@primarydata.com>
^ permalink raw reply [flat|nested] 151+ messages in thread* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-07-03 15:32 ` J. Bruce Fields
2014-07-03 15:37 ` Jeff Layton
@ 2014-07-03 16:11 ` Christoph Hellwig
2014-07-03 16:28 ` Trond Myklebust
2014-07-03 19:07 ` Jeff Layton
1 sibling, 2 replies; 151+ messages in thread
From: Christoph Hellwig @ 2014-07-03 16:11 UTC (permalink / raw)
To: J. Bruce Fields; +Cc: Jeff Layton, linux-nfs
On Thu, Jul 03, 2014 at 11:32:08AM -0400, J. Bruce Fields wrote:
> > > > + struct nfs4_client *found;
> > > > +
> > > > + if (cstate->clp) {
> > > > + found = cstate->clp;
> > > > + if (!same_clid(&found->cl_clientid, clid))
> > > > + return nfserr_stale_clientid;
> > >
> > > That's new behavior, isn't it?
> > >
> >
> > Yeah, I suppose it is, but it's hard to understand a valid use-case for
> > sending multiple ops in a compound with different clientids. Certainly
> > no well-behaved client would do that, would it? (Hmm, that might be an
> > interesting pynfs test, come to think of it).
>
> We could ask for a clarification in 3530bis if there's not already
> something there that clearly forbids this, but I'm not sure if it's even
> worth it.
Or just handle it and be done with me. After all we'd just need to put
the existing client, and store the new one in the cstate.
^ permalink raw reply [flat|nested] 151+ messages in thread* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-07-03 16:11 ` Christoph Hellwig
@ 2014-07-03 16:28 ` Trond Myklebust
2014-07-03 19:07 ` Jeff Layton
1 sibling, 0 replies; 151+ messages in thread
From: Trond Myklebust @ 2014-07-03 16:28 UTC (permalink / raw)
To: Christoph Hellwig; +Cc: J. Bruce Fields, Jeff Layton, Linux NFS Mailing List
On Thu, Jul 3, 2014 at 12:11 PM, Christoph Hellwig <hch@infradead.org> wrote:
> On Thu, Jul 03, 2014 at 11:32:08AM -0400, J. Bruce Fields wrote:
>> > > > + struct nfs4_client *found;
>> > > > +
>> > > > + if (cstate->clp) {
>> > > > + found = cstate->clp;
>> > > > + if (!same_clid(&found->cl_clientid, clid))
>> > > > + return nfserr_stale_clientid;
>> > >
>> > > That's new behavior, isn't it?
>> > >
>> >
>> > Yeah, I suppose it is, but it's hard to understand a valid use-case for
>> > sending multiple ops in a compound with different clientids. Certainly
>> > no well-behaved client would do that, would it? (Hmm, that might be an
>> > interesting pynfs test, come to think of it).
>>
>> We could ask for a clarification in 3530bis if there's not already
>> something there that clearly forbids this, but I'm not sure if it's even
>> worth it.
>
> Or just handle it and be done with me. After all we'd just need to put
> the existing client, and store the new one in the cstate.
It is definitely not allowed in NFSv4.1. There is a special place in
hell^W^W^Werrorcode NFS4ERR_SEQUENCE_POS that tells you that your
compound is insane.
--
Trond Myklebust
Linux NFS client maintainer, PrimaryData
trond.myklebust@primarydata.com
^ permalink raw reply [flat|nested] 151+ messages in thread* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-07-03 16:11 ` Christoph Hellwig
2014-07-03 16:28 ` Trond Myklebust
@ 2014-07-03 19:07 ` Jeff Layton
1 sibling, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-07-03 19:07 UTC (permalink / raw)
To: Christoph Hellwig; +Cc: J. Bruce Fields, Jeff Layton, linux-nfs
On Thu, 3 Jul 2014 09:11:40 -0700
Christoph Hellwig <hch@infradead.org> wrote:
> On Thu, Jul 03, 2014 at 11:32:08AM -0400, J. Bruce Fields wrote:
> > > > > + struct nfs4_client *found;
> > > > > +
> > > > > + if (cstate->clp) {
> > > > > + found = cstate->clp;
> > > > > + if (!same_clid(&found->cl_clientid, clid))
> > > > > + return nfserr_stale_clientid;
> > > >
> > > > That's new behavior, isn't it?
> > > >
> > >
> > > Yeah, I suppose it is, but it's hard to understand a valid use-case for
> > > sending multiple ops in a compound with different clientids. Certainly
> > > no well-behaved client would do that, would it? (Hmm, that might be an
> > > interesting pynfs test, come to think of it).
> >
> > We could ask for a clarification in 3530bis if there's not already
> > something there that clearly forbids this, but I'm not sure if it's even
> > worth it.
>
> Or just handle it and be done with me. After all we'd just need to put
> the existing client, and store the new one in the cstate.
>
Meh, ok... I suppose there's no harm in doing that and since that's the
behavior that was there before, we should probably go with it for the
v4.0 case. I'll have the next iteration do that instead.
Thanks,
--
Jeff Layton <jlayton@primarydata.com>
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-06-30 15:48 ` [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client Jeff Layton
2014-06-30 18:03 ` Christoph Hellwig
2014-07-03 15:18 ` J. Bruce Fields
@ 2014-07-03 20:32 ` J. Bruce Fields
2014-07-03 21:35 ` J. Bruce Fields
2 siblings, 1 reply; 151+ messages in thread
From: J. Bruce Fields @ 2014-07-03 20:32 UTC (permalink / raw)
To: Jeff Layton; +Cc: linux-nfs
On Mon, Jun 30, 2014 at 11:48:44AM -0400, Jeff Layton wrote:
> We want to use the nfsd4_compound_state to cache the nfs4_client in
> order to optimise away extra lookups of the clid.
>
> In the v4.0 case, we use this to ensure that we only have to look up the
> client at most once per compound for each call into lookup_clientid. For
> v4.1+ we set the pointer in the cstate during SEQUENCE processing so we
> should never need to do a search for it.
The connectathon locking test is failing for me in the nfsv4/krb5i case
as of this commit.
Which makes no sense to me whatsoever, so it's entirely possible this is
some unrelated problem on my side. I'll let you know when I've figured
out anything more.
--b.
>
> Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
> ---
> fs/nfsd/nfs4state.c | 74 +++++++++++++++++++++++++++++++++++++----------------
> fs/nfsd/xdr4.h | 1 +
> 2 files changed, 53 insertions(+), 22 deletions(-)
>
> diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
> index e9bb39ecebae..4d162a0e4c6d 100644
> --- a/fs/nfsd/nfs4state.c
> +++ b/fs/nfsd/nfs4state.c
> @@ -189,6 +189,15 @@ static void put_client_renew_locked(struct nfs4_client *clp)
> renew_client_locked(clp);
> }
>
> +static void put_client_renew(struct nfs4_client *clp)
> +{
> + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
> +
> + spin_lock(&nn->client_lock);
> + put_client_renew_locked(clp);
> + spin_unlock(&nn->client_lock);
> +}
> +
> static __be32 nfsd4_get_session_locked(struct nfsd4_session *ses)
> {
> __be32 status;
> @@ -2395,6 +2404,7 @@ nfsd4_sequence(struct svc_rqst *rqstp,
> goto out_put_session;
> cstate->slot = slot;
> cstate->session = session;
> + cstate->clp = clp;
> /* Return the cached reply status and set cstate->status
> * for nfsd4_proc_compound processing */
> status = nfsd4_replay_cache_entry(resp, seq);
> @@ -2429,6 +2439,7 @@ nfsd4_sequence(struct svc_rqst *rqstp,
>
> cstate->slot = slot;
> cstate->session = session;
> + cstate->clp = clp;
>
> out:
> switch (clp->cl_cb_state) {
> @@ -2465,7 +2476,8 @@ nfsd4_sequence_done(struct nfsd4_compoundres *resp)
> }
> /* Drop session reference that was taken in nfsd4_sequence() */
> nfsd4_put_session(cs->session);
> - }
> + } else if (cs->clp)
> + put_client_renew(cs->clp);
> }
>
> __be32
> @@ -2997,6 +3009,38 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4
> return nfserr_bad_seqid;
> }
>
> +static __be32 lookup_clientid(clientid_t *clid,
> + struct nfsd4_compound_state *cstate,
> + struct nfsd_net *nn)
> +{
> + struct nfs4_client *found;
> +
> + if (cstate->clp) {
> + found = cstate->clp;
> + if (!same_clid(&found->cl_clientid, clid))
> + return nfserr_stale_clientid;
> + return nfs_ok;
> + }
> +
> + if (STALE_CLIENTID(clid, nn))
> + return nfserr_stale_clientid;
> +
> + /*
> + * For v4.1+ we get the client in the SEQUENCE op. If we don't have one
> + * cached already then we know this is for is for v4.0 and "sessions"
> + * will be false.
> + */
> + WARN_ON_ONCE(cstate->session);
> + found = find_confirmed_client(clid, false, nn);
> + if (!found)
> + return nfserr_expired;
> +
> + /* Cache the nfs4_client in cstate! */
> + cstate->clp = found;
> + atomic_inc(&found->cl_refcount);
> + return nfs_ok;
> +}
> +
> __be32
> nfsd4_process_open1(struct nfsd4_compound_state *cstate,
> struct nfsd4_open *open, struct nfsd_net *nn)
> @@ -3509,18 +3553,6 @@ void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status)
> free_generic_stateid(open->op_stp);
> }
>
> -static __be32 lookup_clientid(clientid_t *clid, bool session, struct nfsd_net *nn, struct nfs4_client **clp)
> -{
> - struct nfs4_client *found;
> -
> - if (STALE_CLIENTID(clid, nn))
> - return nfserr_stale_clientid;
> - found = find_confirmed_client(clid, session, nn);
> - if (clp)
> - *clp = found;
> - return found ? nfs_ok : nfserr_expired;
> -}
> -
> __be32
> nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
> clientid_t *clid)
> @@ -3532,9 +3564,10 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
> nfs4_lock_state();
> dprintk("process_renew(%08x/%08x): starting\n",
> clid->cl_boot, clid->cl_id);
> - status = lookup_clientid(clid, cstate->minorversion, nn, &clp);
> + status = lookup_clientid(clid, cstate, nn);
> if (status)
> goto out;
> + clp = cstate->clp;
> status = nfserr_cb_path_down;
> if (!list_empty(&clp->cl_delegations)
> && clp->cl_cb_state != NFSD4_CB_UP)
> @@ -3797,22 +3830,19 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
> stateid_t *stateid, unsigned char typemask,
> struct nfs4_stid **s, struct nfsd_net *nn)
> {
> - struct nfs4_client *cl;
> __be32 status;
> - bool sessions = cstate->minorversion != 0;
>
> if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
> return nfserr_bad_stateid;
> - status = lookup_clientid(&stateid->si_opaque.so_clid, sessions,
> - nn, &cl);
> + status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn);
> if (status == nfserr_stale_clientid) {
> - if (sessions)
> + if (cstate->session)
> return nfserr_bad_stateid;
> return nfserr_stale_stateid;
> }
> if (status)
> return status;
> - *s = find_stateid_by_type(cl, stateid, typemask);
> + *s = find_stateid_by_type(cstate->clp, stateid, typemask);
> if (!*s)
> return nfserr_bad_stateid;
> return nfs_ok;
> @@ -4662,7 +4692,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
> nfs4_lock_state();
>
> if (!nfsd4_has_session(cstate)) {
> - status = lookup_clientid(&lockt->lt_clientid, false, nn, NULL);
> + status = lookup_clientid(&lockt->lt_clientid, cstate, nn);
> if (status)
> goto out;
> }
> @@ -4831,7 +4861,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
>
> nfs4_lock_state();
>
> - status = lookup_clientid(clid, cstate->minorversion, nn, NULL);
> + status = lookup_clientid(clid, cstate, nn);
> if (status)
> goto out;
>
> diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
> index 7d8af164523b..312f6483a48e 100644
> --- a/fs/nfsd/xdr4.h
> +++ b/fs/nfsd/xdr4.h
> @@ -55,6 +55,7 @@ struct nfsd4_compound_state {
> struct svc_fh current_fh;
> struct svc_fh save_fh;
> struct nfs4_stateowner *replay_owner;
> + struct nfs4_client *clp;
> /* For sessions DRC */
> struct nfsd4_session *session;
> struct nfsd4_slot *slot;
> --
> 1.9.3
>
^ permalink raw reply [flat|nested] 151+ messages in thread* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-07-03 20:32 ` J. Bruce Fields
@ 2014-07-03 21:35 ` J. Bruce Fields
2014-07-03 21:50 ` Jeff Layton
2014-07-03 22:31 ` Jeff Layton
0 siblings, 2 replies; 151+ messages in thread
From: J. Bruce Fields @ 2014-07-03 21:35 UTC (permalink / raw)
To: Jeff Layton; +Cc: linux-nfs
On Thu, Jul 03, 2014 at 04:32:59PM -0400, J. Bruce Fields wrote:
> On Mon, Jun 30, 2014 at 11:48:44AM -0400, Jeff Layton wrote:
> > We want to use the nfsd4_compound_state to cache the nfs4_client in
> > order to optimise away extra lookups of the clid.
> >
> > In the v4.0 case, we use this to ensure that we only have to look up the
> > client at most once per compound for each call into lookup_clientid. For
> > v4.1+ we set the pointer in the cstate during SEQUENCE processing so we
> > should never need to do a search for it.
>
> The connectathon locking test is failing for me in the nfsv4/krb5i case
> as of this commit.
>
> Which makes no sense to me whatsoever, so it's entirely possible this is
> some unrelated problem on my side. I'll let you know when I've figured
> out anything more.
It's intermittent.
I've reproduced it on the previous commit so I know at least that this
one isn't at fault.
I doubt it's really dependent on krb5i, at most that's probably just
making it more likely to reproduce.
--b.
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-07-03 21:35 ` J. Bruce Fields
@ 2014-07-03 21:50 ` Jeff Layton
2014-07-03 22:31 ` Jeff Layton
1 sibling, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-07-03 21:50 UTC (permalink / raw)
To: J. Bruce Fields; +Cc: linux-nfs
On Thu, 3 Jul 2014 17:35:26 -0400
"J. Bruce Fields" <bfields@fieldses.org> wrote:
> On Thu, Jul 03, 2014 at 04:32:59PM -0400, J. Bruce Fields wrote:
> > On Mon, Jun 30, 2014 at 11:48:44AM -0400, Jeff Layton wrote:
> > > We want to use the nfsd4_compound_state to cache the nfs4_client in
> > > order to optimise away extra lookups of the clid.
> > >
> > > In the v4.0 case, we use this to ensure that we only have to look up the
> > > client at most once per compound for each call into lookup_clientid. For
> > > v4.1+ we set the pointer in the cstate during SEQUENCE processing so we
> > > should never need to do a search for it.
> >
> > The connectathon locking test is failing for me in the nfsv4/krb5i case
> > as of this commit.
> >
> > Which makes no sense to me whatsoever, so it's entirely possible this is
> > some unrelated problem on my side. I'll let you know when I've figured
> > out anything more.
>
> It's intermittent.
>
> I've reproduced it on the previous commit so I know at least that this
> one isn't at fault.
>
> I doubt it's really dependent on krb5i, at most that's probably just
> making it more likely to reproduce.
>
> --b.
I haven't been able to reproduce it yet, but I suspect you're hitting
this check in lookup_or_create_lock_state:
/* with an existing lockowner, seqids must be the same */
status = nfserr_bad_seqid;
if (!cstate->minorversion &&
lock->lk_new_lock_seqid != lo->lo_owner.so_seqid)
goto out;
Hmmm...there are some changes that go in in this patch wrt to lock
seqid handling:
nfsd: clean up lockowner refcounting when finding them
Perhaps those need to go in earlier? Though when I looked at that
originally, I figured that we wouldn't need those until the refcounting
changes went in (which is why I didn't put them in). It might be
interesting to look at traces and see whether they're consistent with
hitting that check (or maybe put some debug printks in)?
--
Jeff Layton <jlayton@primarydata.com>
^ permalink raw reply [flat|nested] 151+ messages in thread* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-07-03 21:35 ` J. Bruce Fields
2014-07-03 21:50 ` Jeff Layton
@ 2014-07-03 22:31 ` Jeff Layton
2014-07-04 12:14 ` Jeff Layton
1 sibling, 1 reply; 151+ messages in thread
From: Jeff Layton @ 2014-07-03 22:31 UTC (permalink / raw)
To: J. Bruce Fields; +Cc: linux-nfs
[-- Attachment #1: Type: text/plain, Size: 1443 bytes --]
On Thu, 3 Jul 2014 17:35:26 -0400
"J. Bruce Fields" <bfields@fieldses.org> wrote:
> On Thu, Jul 03, 2014 at 04:32:59PM -0400, J. Bruce Fields wrote:
> > On Mon, Jun 30, 2014 at 11:48:44AM -0400, Jeff Layton wrote:
> > > We want to use the nfsd4_compound_state to cache the nfs4_client in
> > > order to optimise away extra lookups of the clid.
> > >
> > > In the v4.0 case, we use this to ensure that we only have to look up the
> > > client at most once per compound for each call into lookup_clientid. For
> > > v4.1+ we set the pointer in the cstate during SEQUENCE processing so we
> > > should never need to do a search for it.
> >
> > The connectathon locking test is failing for me in the nfsv4/krb5i case
> > as of this commit.
> >
> > Which makes no sense to me whatsoever, so it's entirely possible this is
> > some unrelated problem on my side. I'll let you know when I've figured
> > out anything more.
>
> It's intermittent.
>
> I've reproduced it on the previous commit so I know at least that this
> one isn't at fault.
>
> I doubt it's really dependent on krb5i, at most that's probably just
> making it more likely to reproduce.
>
> --b.
Bruce,
Does this patch help? I suspect this is where the bug crept in, but I'm
unclear on why it would be intermittent...
FWIW, this all gets cleaned up in a later patch that changes how the
refcounting on lock and openowners works.
--
Jeff Layton <jlayton@primarydata.com>
[-- Attachment #2: 0001-nfsd-fix-lock-stateid-cleanup-on-error-in-nfsd4_lock.patch --]
[-- Type: text/x-patch, Size: 1337 bytes --]
>From 84884320b983eaeb68c652de8fe4b48aad4052c3 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@primarydata.com>
Date: Thu, 3 Jul 2014 18:20:31 -0400
Subject: [PATCH] nfsd: fix lock stateid cleanup on error in nfsd4_lock
commit 43a1b041e3b changed nfsd4_lock to call release_lockowner_if_empty
if the the lock stateid was new and the function was going to return an
error.
This is wrong. The lockowner will never be empty in that situation since
it still has the new lock stateid attached to it. Change it to call
release_lock_stateid instead, which will destroy the lock stateid and
then release the lockowner if it's empty at that point.
Cc: Trond Myklebust <trond.myklebust@primarydata.com>
Reported-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index a22c73f14a17..b2ea0a06fbf2 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4600,7 +4600,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
}
out:
if (status && new_state)
- release_lockowner_if_empty(lock_sop);
+ release_lock_stateid(lock_stp);
nfsd4_bump_seqid(cstate, status);
if (!cstate->replay_owner)
nfs4_unlock_state();
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread
* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-07-03 22:31 ` Jeff Layton
@ 2014-07-04 12:14 ` Jeff Layton
2014-07-07 18:23 ` J. Bruce Fields
0 siblings, 1 reply; 151+ messages in thread
From: Jeff Layton @ 2014-07-04 12:14 UTC (permalink / raw)
To: J. Bruce Fields; +Cc: linux-nfs
On Thu, 3 Jul 2014 18:31:15 -0400
Jeff Layton <jeff.layton@primarydata.com> wrote:
> On Thu, 3 Jul 2014 17:35:26 -0400
> "J. Bruce Fields" <bfields@fieldses.org> wrote:
>
> > On Thu, Jul 03, 2014 at 04:32:59PM -0400, J. Bruce Fields wrote:
> > > On Mon, Jun 30, 2014 at 11:48:44AM -0400, Jeff Layton wrote:
> > > > We want to use the nfsd4_compound_state to cache the nfs4_client in
> > > > order to optimise away extra lookups of the clid.
> > > >
> > > > In the v4.0 case, we use this to ensure that we only have to look up the
> > > > client at most once per compound for each call into lookup_clientid. For
> > > > v4.1+ we set the pointer in the cstate during SEQUENCE processing so we
> > > > should never need to do a search for it.
> > >
> > > The connectathon locking test is failing for me in the nfsv4/krb5i case
> > > as of this commit.
> > >
> > > Which makes no sense to me whatsoever, so it's entirely possible this is
> > > some unrelated problem on my side. I'll let you know when I've figured
> > > out anything more.
> >
> > It's intermittent.
> >
> > I've reproduced it on the previous commit so I know at least that this
> > one isn't at fault.
> >
> > I doubt it's really dependent on krb5i, at most that's probably just
> > making it more likely to reproduce.
> >
> > --b.
>
> Bruce,
>
> Does this patch help? I suspect this is where the bug crept in, but I'm
> unclear on why it would be intermittent...
>
> FWIW, this all gets cleaned up in a later patch that changes how the
> refcounting on lock and openowners works.
>
I was finally able to reproduce this after a running the cthon lock
tests in a loop, with krb5i. With the patch that I sent earlier, I was
able to run 100 iterations of it without a failure, so I think that was
the bug.
Cheers!
--
Jeff Layton <jlayton@primarydata.com>
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client
2014-07-04 12:14 ` Jeff Layton
@ 2014-07-07 18:23 ` J. Bruce Fields
0 siblings, 0 replies; 151+ messages in thread
From: J. Bruce Fields @ 2014-07-07 18:23 UTC (permalink / raw)
To: Jeff Layton; +Cc: linux-nfs
On Fri, Jul 04, 2014 at 08:14:49AM -0400, Jeff Layton wrote:
> On Thu, 3 Jul 2014 18:31:15 -0400
> Jeff Layton <jeff.layton@primarydata.com> wrote:
>
> > On Thu, 3 Jul 2014 17:35:26 -0400
> > "J. Bruce Fields" <bfields@fieldses.org> wrote:
> >
> > > On Thu, Jul 03, 2014 at 04:32:59PM -0400, J. Bruce Fields wrote:
> > > > On Mon, Jun 30, 2014 at 11:48:44AM -0400, Jeff Layton wrote:
> > > > > We want to use the nfsd4_compound_state to cache the nfs4_client in
> > > > > order to optimise away extra lookups of the clid.
> > > > >
> > > > > In the v4.0 case, we use this to ensure that we only have to look up the
> > > > > client at most once per compound for each call into lookup_clientid. For
> > > > > v4.1+ we set the pointer in the cstate during SEQUENCE processing so we
> > > > > should never need to do a search for it.
> > > >
> > > > The connectathon locking test is failing for me in the nfsv4/krb5i case
> > > > as of this commit.
> > > >
> > > > Which makes no sense to me whatsoever, so it's entirely possible this is
> > > > some unrelated problem on my side. I'll let you know when I've figured
> > > > out anything more.
> > >
> > > It's intermittent.
> > >
> > > I've reproduced it on the previous commit so I know at least that this
> > > one isn't at fault.
> > >
> > > I doubt it's really dependent on krb5i, at most that's probably just
> > > making it more likely to reproduce.
> > >
> > > --b.
> >
> > Bruce,
> >
> > Does this patch help? I suspect this is where the bug crept in, but I'm
> > unclear on why it would be intermittent...
> >
> > FWIW, this all gets cleaned up in a later patch that changes how the
> > refcounting on lock and openowners works.
> >
>
> I was finally able to reproduce this after a running the cthon lock
> tests in a loop, with krb5i. With the patch that I sent earlier, I was
> able to run 100 iterations of it without a failure, so I think that was
> the bug.
Thanks! That seems to be holding up for me too.
I'll continue slowly applying your patches to for-3.17.
--b.
^ permalink raw reply [flat|nested] 151+ messages in thread
* [PATCH v3 016/114] nfsd: Convert nfsd4_process_open1() to work with lookup_clientid()
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (14 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 015/114] nfsd: Allow struct nfsd4_compound_state to cache the nfs4_client Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 017/114] nfsd: Always use lookup_clientid() in nfsd4_process_open1 Jeff Layton
` (97 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
...and have alloc_init_open_stateowner just use the cstate->clp pointer
instead of passing in a clp separately. This allows us to use the
cached nfs4_client pointer in the cstate instead of having to look it
up again.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4state.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4d162a0e4c6d..199e9d5e23ac 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2773,10 +2773,10 @@ static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, u
}
static struct nfs4_openowner *
-alloc_init_open_stateowner(unsigned int strhashval, struct nfs4_client *clp,
- struct nfsd4_open *open,
+alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
struct nfsd4_compound_state *cstate)
{
+ struct nfs4_client *clp = cstate->clp;
struct nfs4_openowner *oo;
oo = alloc_stateowner(openowner_slab, &open->op_owner, clp);
@@ -3065,10 +3065,10 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate,
oo = find_openstateowner_str(strhashval, open, cstate->minorversion, nn);
open->op_openowner = oo;
if (!oo) {
- clp = find_confirmed_client(clientid, cstate->minorversion,
- nn);
- if (clp == NULL)
- return nfserr_expired;
+ status = lookup_clientid(clientid, cstate, nn);
+ if (status)
+ return status;
+ clp = cstate->clp;
goto new_owner;
}
if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
@@ -3084,7 +3084,7 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate,
clp = oo->oo_owner.so_client;
goto alloc_stateid;
new_owner:
- oo = alloc_init_open_stateowner(strhashval, clp, open, cstate);
+ oo = alloc_init_open_stateowner(strhashval, open, cstate);
if (oo == NULL)
return nfserr_jukebox;
open->op_openowner = oo;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 017/114] nfsd: Always use lookup_clientid() in nfsd4_process_open1
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (15 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 016/114] nfsd: Convert nfsd4_process_open1() to work with lookup_clientid() Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 018/114] nfsd: Convert nfs4_check_open_reclaim() to work with lookup_clientid() Jeff Layton
` (96 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
In later patches, we'll be moving the stateowner table into the
nfs4_client, and by doing this we ensure that we have a cached
nfs4_client pointer.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4state.c | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 199e9d5e23ac..a482fb97964f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3061,19 +3061,19 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate,
if (open->op_file == NULL)
return nfserr_jukebox;
+ status = lookup_clientid(clientid, cstate, nn);
+ if (status)
+ return status;
+ clp = cstate->clp;
+
strhashval = ownerstr_hashval(clientid->cl_id, &open->op_owner);
oo = find_openstateowner_str(strhashval, open, cstate->minorversion, nn);
open->op_openowner = oo;
if (!oo) {
- status = lookup_clientid(clientid, cstate, nn);
- if (status)
- return status;
- clp = cstate->clp;
goto new_owner;
}
if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
/* Replace unconfirmed owners without checking for replay. */
- clp = oo->oo_owner.so_client;
release_openowner(oo);
open->op_openowner = NULL;
goto new_owner;
@@ -3081,7 +3081,6 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate,
status = nfsd4_check_seqid(cstate, &oo->oo_owner, open->op_seqid);
if (status)
return status;
- clp = oo->oo_owner.so_client;
goto alloc_stateid;
new_owner:
oo = alloc_init_open_stateowner(strhashval, open, cstate);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 018/114] nfsd: Convert nfs4_check_open_reclaim() to work with lookup_clientid()
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (16 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 017/114] nfsd: Always use lookup_clientid() in nfsd4_process_open1 Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 019/114] nfsd: Move the delegation reference counter into the struct nfs4_stid Jeff Layton
` (95 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
lookup_clientid is preferable to find_confirmed_client since it's able
to use the cached client in the compound state.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4proc.c | 3 +--
fs/nfsd/nfs4state.c | 15 ++++++++++-----
fs/nfsd/state.h | 3 ++-
3 files changed, 13 insertions(+), 8 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 7aa83bf34fa9..3c72eef479a3 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -431,8 +431,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
break;
case NFS4_OPEN_CLAIM_PREVIOUS:
status = nfs4_check_open_reclaim(&open->op_clientid,
- cstate->minorversion,
- nn);
+ cstate, nn);
if (status)
goto out;
open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index a482fb97964f..c3b537570bce 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4980,16 +4980,21 @@ nfsd4_find_reclaim_client(const char *recdir, struct nfsd_net *nn)
* Called from OPEN. Look for clientid in reclaim list.
*/
__be32
-nfs4_check_open_reclaim(clientid_t *clid, bool sessions, struct nfsd_net *nn)
+nfs4_check_open_reclaim(clientid_t *clid,
+ struct nfsd4_compound_state *cstate,
+ struct nfsd_net *nn)
{
- struct nfs4_client *clp;
+ __be32 status;
/* find clientid in conf_id_hashtbl */
- clp = find_confirmed_client(clid, sessions, nn);
- if (clp == NULL)
+ status = lookup_clientid(clid, cstate, nn);
+ if (status)
return nfserr_reclaim_bad;
- return nfsd4_client_record_check(clp) ? nfserr_reclaim_bad : nfs_ok;
+ if (nfsd4_client_record_check(cstate->clp))
+ return nfserr_reclaim_bad;
+
+ return nfs_ok;
}
#ifdef CONFIG_NFSD_FAULT_INJECTION
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 305414a083c5..b2c9afce33bf 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -458,7 +458,8 @@ void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *, struct nfsd_net *)
extern void nfs4_release_reclaim(struct nfsd_net *);
extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
struct nfsd_net *nn);
-extern __be32 nfs4_check_open_reclaim(clientid_t *clid, bool sessions, struct nfsd_net *nn);
+extern __be32 nfs4_check_open_reclaim(clientid_t *clid,
+ struct nfsd4_compound_state *cstate, struct nfsd_net *nn);
extern int set_callback_cred(void);
extern void nfsd4_probe_callback(struct nfs4_client *clp);
extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 019/114] nfsd: Move the delegation reference counter into the struct nfs4_stid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (17 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 018/114] nfsd: Convert nfs4_check_open_reclaim() to work with lookup_clientid() Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 020/114] nfsd4: use cl_lock to synchronize all stateid idr calls Jeff Layton
` (94 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
We will want to add reference counting to the lock stateid and open
stateids too in later patches.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 13 +++++++------
fs/nfsd/state.h | 2 +-
2 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c3b537570bce..7f81207c3862 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -360,6 +360,7 @@ kmem_cache *slab)
stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
/* Will be incremented before return to client: */
stid->sc_stateid.si_generation = 0;
+ atomic_set(&stid->sc_count, 1);
/*
* It shouldn't be a problem to reuse an opaque stateid value.
@@ -481,7 +482,6 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
dp->dl_type = NFS4_OPEN_DELEGATE_READ;
fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle);
dp->dl_time = 0;
- atomic_set(&dp->dl_count, 1);
return dp;
}
@@ -500,7 +500,7 @@ static void nfs4_free_stid(struct kmem_cache *slab, struct nfs4_stid *s)
void
nfs4_put_delegation(struct nfs4_delegation *dp)
{
- if (atomic_dec_and_test(&dp->dl_count)) {
+ if (atomic_dec_and_test(&dp->dl_stid.sc_count)) {
nfs4_free_stid(deleg_slab, &dp->dl_stid);
num_delegations--;
}
@@ -2948,10 +2948,11 @@ static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
{
/* We're assuming the state code never drops its reference
* without first removing the lease. Since we're in this lease
- * callback (and since the lease code is serialized by the kernel
- * lock) we know the server hasn't removed the lease yet, we know
- * it's safe to take a reference: */
- atomic_inc(&dp->dl_count);
+ * callback (and since the lease code is serialized by the i_lock
+ * we know the server hasn't removed the lease yet, we know it's
+ * safe to take a reference.
+ */
+ atomic_inc(&dp->dl_stid.sc_count);
block_delegations(&dp->dl_fh);
nfsd4_cb_recall(dp);
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index b2c9afce33bf..9eb4fe673014 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -73,6 +73,7 @@ struct nfsd4_callback {
};
struct nfs4_stid {
+ atomic_t sc_count;
#define NFS4_OPEN_STID 1
#define NFS4_LOCK_STID 2
#define NFS4_DELEG_STID 4
@@ -90,7 +91,6 @@ struct nfs4_delegation {
struct list_head dl_perfile;
struct list_head dl_perclnt;
struct list_head dl_recall_lru; /* delegation recalled */
- atomic_t dl_count; /* ref count */
struct nfs4_file *dl_file;
u32 dl_type;
time_t dl_time;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 020/114] nfsd4: use cl_lock to synchronize all stateid idr calls
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (18 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 019/114] nfsd: Move the delegation reference counter into the struct nfs4_stid Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 021/114] nfsd: Add fine grained protection for the nfs4_file->fi_stateids list Jeff Layton
` (93 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Benny Halevy
From: Benny Halevy <bhalevy@primarydata.com>
Currently, this is serialized by the client_mutex, which is slated for
removal. Add finer-grained locking here.
Signed-off-by: Benny Halevy <bhalevy@primarydata.com>
---
fs/nfsd/nfs4state.c | 17 +++++++++++++----
1 file changed, 13 insertions(+), 4 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 7f81207c3862..993aa196dd9e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -343,7 +343,6 @@ static void nfs4_file_put_access(struct nfs4_file *fp, int oflag)
static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct
kmem_cache *slab)
{
- struct idr *stateids = &cl->cl_stateids;
struct nfs4_stid *stid;
int new_id;
@@ -351,7 +350,11 @@ kmem_cache *slab)
if (!stid)
return NULL;
- new_id = idr_alloc_cyclic(stateids, stid, 0, 0, GFP_KERNEL);
+ idr_preload(GFP_KERNEL);
+ spin_lock(&cl->cl_lock);
+ new_id = idr_alloc_cyclic(&cl->cl_stateids, stid, 0, 0, GFP_NOWAIT);
+ spin_unlock(&cl->cl_lock);
+ idr_preload_end();
if (new_id < 0)
goto out_free;
stid->sc_client = cl;
@@ -487,9 +490,11 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
static void remove_stid(struct nfs4_stid *s)
{
- struct idr *stateids = &s->sc_client->cl_stateids;
+ struct nfs4_client *clp = s->sc_client;
- idr_remove(stateids, s->sc_stateid.si_opaque.so_id);
+ spin_lock(&clp->cl_lock);
+ idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
+ spin_unlock(&clp->cl_lock);
}
static void nfs4_free_stid(struct kmem_cache *slab, struct nfs4_stid *s)
@@ -1263,7 +1268,9 @@ free_client(struct nfs4_client *clp)
rpc_destroy_wait_queue(&clp->cl_cb_waitq);
free_svc_cred(&clp->cl_cred);
kfree(clp->cl_name.data);
+ spin_lock(&clp->cl_lock);
idr_destroy(&clp->cl_stateids);
+ spin_unlock(&clp->cl_lock);
kfree(clp);
}
@@ -1486,7 +1493,9 @@ static struct nfs4_stid *find_stateid(struct nfs4_client *cl, stateid_t *t)
{
struct nfs4_stid *ret;
+ spin_lock(&cl->cl_lock);
ret = idr_find(&cl->cl_stateids, t->si_opaque.so_id);
+ spin_unlock(&cl->cl_lock);
if (!ret || !ret->sc_type)
return NULL;
return ret;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 021/114] nfsd: Add fine grained protection for the nfs4_file->fi_stateids list
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (19 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 020/114] nfsd4: use cl_lock to synchronize all stateid idr calls Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 022/114] nfsd: Add a mutex to protect the NFSv4.0 open owner replay cache Jeff Layton
` (92 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Access to this list is currently serialized by the client_mutex. Add
finer grained locking around this list in preparation for its removal.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 20 +++++++++++++++++---
1 file changed, 17 insertions(+), 3 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 993aa196dd9e..0721c77a38c9 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -716,7 +716,11 @@ release_all_access(struct nfs4_ol_stateid *stp)
static void unhash_generic_stateid(struct nfs4_ol_stateid *stp)
{
+ struct nfs4_file *fp = stp->st_file;
+
+ spin_lock(&fp->fi_lock);
list_del(&stp->st_perfile);
+ spin_unlock(&fp->fi_lock);
list_del(&stp->st_perstateowner);
}
@@ -2809,7 +2813,6 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
stp->st_stid.sc_type = NFS4_OPEN_STID;
INIT_LIST_HEAD(&stp->st_locks);
list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
- list_add(&stp->st_perfile, &fp->fi_stateids);
stp->st_stateowner = &oo->oo_owner;
get_nfs4_file(fp);
stp->st_file = fp;
@@ -2818,6 +2821,9 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
set_access(open->op_share_access, stp);
set_deny(open->op_share_deny, stp);
stp->st_openstp = NULL;
+ spin_lock(&fp->fi_lock);
+ list_add(&stp->st_perfile, &fp->fi_stateids);
+ spin_unlock(&fp->fi_lock);
}
static void
@@ -2925,6 +2931,7 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
return nfs_ok;
ret = nfserr_locked;
/* Search for conflicting share reservations */
+ spin_lock(&fp->fi_lock);
list_for_each_entry(stp, &fp->fi_stateids, st_perfile) {
if (test_deny(deny_type, stp) ||
test_deny(NFS4_SHARE_DENY_BOTH, stp))
@@ -2932,6 +2939,7 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
}
ret = nfs_ok;
out:
+ spin_unlock(&fp->fi_lock);
put_nfs4_file(fp);
return ret;
}
@@ -3163,6 +3171,7 @@ nfs4_check_open(struct nfs4_file *fp, struct nfsd4_open *open, struct nfs4_ol_st
struct nfs4_ol_stateid *local;
struct nfs4_openowner *oo = open->op_openowner;
+ spin_lock(&fp->fi_lock);
list_for_each_entry(local, &fp->fi_stateids, st_perfile) {
/* ignore lock owners */
if (local->st_stateowner->so_is_open_owner == 0)
@@ -3171,9 +3180,12 @@ nfs4_check_open(struct nfs4_file *fp, struct nfsd4_open *open, struct nfs4_ol_st
if (local->st_stateowner == &oo->oo_owner)
*stpp = local;
/* check for conflicting share reservations */
- if (!test_share(local, open))
+ if (!test_share(local, open)) {
+ spin_unlock(&fp->fi_lock);
return nfserr_share_denied;
+ }
}
+ spin_unlock(&fp->fi_lock);
return nfs_ok;
}
@@ -4421,7 +4433,6 @@ alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct
if (stp == NULL)
return NULL;
stp->st_stid.sc_type = NFS4_LOCK_STID;
- list_add(&stp->st_perfile, &fp->fi_stateids);
list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
stp->st_stateowner = &lo->lo_owner;
get_nfs4_file(fp);
@@ -4430,6 +4441,9 @@ alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct
stp->st_deny_bmap = open_stp->st_deny_bmap;
stp->st_openstp = open_stp;
list_add(&stp->st_locks, &open_stp->st_locks);
+ spin_lock(&fp->fi_lock);
+ list_add(&stp->st_perfile, &fp->fi_stateids);
+ spin_unlock(&fp->fi_lock);
return stp;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 022/114] nfsd: Add a mutex to protect the NFSv4.0 open owner replay cache
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (20 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 021/114] nfsd: Add fine grained protection for the nfs4_file->fi_stateids list Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 023/114] nfsd: Add locking to the nfs4_file->fi_fds[] array Jeff Layton
` (91 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
We don't want to rely on the client_mutex for protection in the case of
NFSv4 open owners. Instead, we add a mutex that will only be taken for
NFSv4.0 state mutating operations, and that will be released once the
entire compound is done.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4proc.c | 13 +++++--------
fs/nfsd/nfs4state.c | 21 ++++++++-------------
fs/nfsd/nfs4xdr.c | 2 --
fs/nfsd/state.h | 1 +
fs/nfsd/xdr4.h | 21 +++++++++++++++++++++
5 files changed, 35 insertions(+), 23 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 3c72eef479a3..fc48d1d51f1d 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -468,11 +468,11 @@ out:
kfree(resfh);
}
nfsd4_cleanup_open_state(open, status);
- if (open->op_openowner && !nfsd4_has_session(cstate))
- cstate->replay_owner = &open->op_openowner->oo_owner;
+ if (open->op_openowner)
+ nfsd4_cstate_assign_replay(cstate,
+ &open->op_openowner->oo_owner);
nfsd4_bump_seqid(cstate, status);
- if (!cstate->replay_owner)
- nfs4_unlock_state();
+ nfs4_unlock_state();
return status;
}
@@ -1394,10 +1394,7 @@ encode_op:
args->ops, args->opcnt, resp->opcnt, op->opnum,
be32_to_cpu(status));
- if (cstate->replay_owner) {
- nfs4_unlock_state();
- cstate->replay_owner = NULL;
- }
+ nfsd4_cstate_clear_replay(cstate);
/* XXX Ugh, we need to get rid of this kind of special case: */
if (op->opnum == OP_READ && op->u.read.rd_filp)
fput(op->u.read.rd_filp);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 0721c77a38c9..72f8aeaf44ac 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -885,7 +885,7 @@ void nfsd4_bump_seqid(struct nfsd4_compound_state *cstate, __be32 nfserr)
return;
if (!seqid_mutating_err(ntohl(nfserr))) {
- cstate->replay_owner = NULL;
+ nfsd4_cstate_clear_replay(cstate);
return;
}
if (!so)
@@ -2754,6 +2754,7 @@ static void init_nfs4_replay(struct nfs4_replay *rp)
rp->rp_status = nfserr_serverfault;
rp->rp_buflen = 0;
rp->rp_buf = rp->rp_ibuf;
+ mutex_init(&rp->rp_mutex);
}
static inline void *alloc_stateowner(struct kmem_cache *slab, struct xdr_netobj *owner, struct nfs4_client *clp)
@@ -4072,8 +4073,7 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
if (status)
return status;
stp = openlockstateid(s);
- if (!nfsd4_has_session(cstate))
- cstate->replay_owner = stp->st_stateowner;
+ nfsd4_cstate_assign_replay(cstate, stp->st_stateowner);
status = nfs4_seqid_op_checks(cstate, stateid, seqid, stp);
if (!status)
@@ -4134,8 +4134,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = nfs_ok;
out:
nfsd4_bump_seqid(cstate, status);
- if (!cstate->replay_owner)
- nfs4_unlock_state();
+ nfs4_unlock_state();
return status;
}
@@ -4217,8 +4216,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
status = nfs_ok;
out:
nfsd4_bump_seqid(cstate, status);
- if (!cstate->replay_owner)
- nfs4_unlock_state();
+ nfs4_unlock_state();
return status;
}
@@ -4273,8 +4271,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfsd4_close_open_stateid(stp);
out:
- if (!cstate->replay_owner)
- nfs4_unlock_state();
+ nfs4_unlock_state();
return status;
}
@@ -4668,8 +4665,7 @@ out:
if (status && new_state)
release_lockowner_if_empty(lock_sop);
nfsd4_bump_seqid(cstate, status);
- if (!cstate->replay_owner)
- nfs4_unlock_state();
+ nfs4_unlock_state();
if (file_lock)
locks_free_lock(file_lock);
if (conflock)
@@ -4830,8 +4826,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
out:
nfsd4_bump_seqid(cstate, status);
- if (!cstate->replay_owner)
- nfs4_unlock_state();
+ nfs4_unlock_state();
if (file_lock)
locks_free_lock(file_lock);
return status;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 1c5e87e660cd..a4349619217e 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3931,8 +3931,6 @@ status:
*
* XDR note: do not encode rp->rp_buflen: the buffer contains the
* previously sent already encoded operation.
- *
- * called with nfs4_lock_state() held
*/
void
nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op)
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 9eb4fe673014..30ad57089896 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -327,6 +327,7 @@ struct nfs4_replay {
unsigned int rp_buflen;
char *rp_buf;
struct knfsd_fh rp_openfh;
+ struct mutex rp_mutex;
char rp_ibuf[NFSD4_REPLAY_ISIZE];
};
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 312f6483a48e..ec9674a009bd 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -74,6 +74,27 @@ static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs)
return cs->slot != NULL;
}
+static inline void
+nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate,
+ struct nfs4_stateowner *so)
+{
+ if (!nfsd4_has_session(cstate)) {
+ mutex_lock(&so->so_replay.rp_mutex);
+ cstate->replay_owner = so;
+ }
+}
+
+static inline void
+nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate)
+{
+ struct nfs4_stateowner *so = cstate->replay_owner;
+
+ if (so != NULL) {
+ cstate->replay_owner = NULL;
+ mutex_unlock(&so->so_replay.rp_mutex);
+ }
+}
+
struct nfsd4_change_info {
u32 atomic;
bool change_supported;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 023/114] nfsd: Add locking to the nfs4_file->fi_fds[] array
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (21 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 022/114] nfsd: Add a mutex to protect the NFSv4.0 open owner replay cache Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 024/114] nfsd: clean up helper __release_lock_stateid Jeff Layton
` (90 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Preparation for removal of the client_mutex, which currently protects
this array.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 105 ++++++++++++++++++++++++++++++++++++++++++++--------
fs/nfsd/state.h | 26 -------------
2 files changed, 89 insertions(+), 42 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 72f8aeaf44ac..05f6e1761821 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -266,6 +266,52 @@ get_nfs4_file(struct nfs4_file *fi)
atomic_inc(&fi->fi_ref);
}
+static struct file *__nfs4_get_fd(struct nfs4_file *f, int oflag)
+{
+ if (f->fi_fds[oflag])
+ return get_file(f->fi_fds[oflag]);
+ return NULL;
+}
+
+static struct file *find_writeable_file(struct nfs4_file *f)
+{
+ struct file *ret;
+
+ spin_lock(&f->fi_lock);
+ ret = __nfs4_get_fd(f, O_WRONLY);
+ if (!ret)
+ ret = __nfs4_get_fd(f, O_RDWR);
+ spin_unlock(&f->fi_lock);
+ return ret;
+}
+
+static struct file *find_readable_file(struct nfs4_file *f)
+{
+ struct file *ret;
+
+ spin_lock(&f->fi_lock);
+ ret = __nfs4_get_fd(f, O_RDONLY);
+ if (!ret)
+ ret = __nfs4_get_fd(f, O_RDWR);
+ spin_unlock(&f->fi_lock);
+ return ret;
+}
+
+static struct file *find_any_file(struct nfs4_file *f)
+{
+ struct file *ret;
+
+ spin_lock(&f->fi_lock);
+ ret = __nfs4_get_fd(f, O_RDWR);
+ if (!ret) {
+ ret = __nfs4_get_fd(f, O_WRONLY);
+ if (!ret)
+ ret = __nfs4_get_fd(f, O_RDONLY);
+ }
+ spin_unlock(&f->fi_lock);
+ return ret;
+}
+
static int num_delegations;
unsigned long max_delegations;
@@ -314,20 +360,29 @@ static void nfs4_file_get_access(struct nfs4_file *fp, int oflag)
__nfs4_file_get_access(fp, oflag);
}
-static void nfs4_file_put_fd(struct nfs4_file *fp, int oflag)
+static struct file *nfs4_file_put_fd(struct nfs4_file *fp, int oflag)
{
- if (fp->fi_fds[oflag]) {
- fput(fp->fi_fds[oflag]);
- fp->fi_fds[oflag] = NULL;
- }
+ struct file *filp;
+
+ filp = fp->fi_fds[oflag];
+ fp->fi_fds[oflag] = NULL;
+ return filp;
}
static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
{
- if (atomic_dec_and_test(&fp->fi_access[oflag])) {
- nfs4_file_put_fd(fp, oflag);
+ if (atomic_dec_and_lock(&fp->fi_access[oflag], &fp->fi_lock)) {
+ struct file *f1 = NULL;
+ struct file *f2 = NULL;
+
+ f1 = nfs4_file_put_fd(fp, oflag);
if (atomic_read(&fp->fi_access[1 - oflag]) == 0)
- nfs4_file_put_fd(fp, O_RDWR);
+ f2 = nfs4_file_put_fd(fp, O_RDWR);
+ spin_unlock(&fp->fi_lock);
+ if (f1)
+ fput(f1);
+ if (f2)
+ fput(f2);
}
}
@@ -745,8 +800,10 @@ static void __release_lock_stateid(struct nfs4_ol_stateid *stp)
unhash_generic_stateid(stp);
unhash_stid(&stp->st_stid);
file = find_any_file(stp->st_file);
- if (file)
+ if (file) {
locks_remove_posix(file, (fl_owner_t)lockowner(stp->st_stateowner));
+ fput(file);
+ }
close_generic_stateid(stp);
free_generic_stateid(stp);
}
@@ -3219,17 +3276,27 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh,
static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
struct svc_fh *cur_fh, struct nfsd4_open *open)
{
+ struct file *filp = NULL;
__be32 status;
int oflag = nfs4_access_to_omode(open->op_share_access);
int access = nfs4_access_to_access(open->op_share_access);
+ spin_lock(&fp->fi_lock);
if (!fp->fi_fds[oflag]) {
- status = nfsd_open(rqstp, cur_fh, S_IFREG, access,
- &fp->fi_fds[oflag]);
+ spin_unlock(&fp->fi_lock);
+ status = nfsd_open(rqstp, cur_fh, S_IFREG, access, &filp);
if (status)
goto out;
+ spin_lock(&fp->fi_lock);
+ if (!fp->fi_fds[oflag]) {
+ fp->fi_fds[oflag] = filp;
+ filp = NULL;
+ }
}
nfs4_file_get_access(fp, oflag);
+ spin_unlock(&fp->fi_lock);
+ if (filp)
+ fput(filp);
status = nfsd4_truncate(rqstp, cur_fh, open);
if (status)
@@ -3314,13 +3381,15 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
if (status)
goto out_free;
fp->fi_lease = fl;
- fp->fi_deleg_file = get_file(fl->fl_file);
+ fp->fi_deleg_file = fl->fl_file;
atomic_set(&fp->fi_delegees, 1);
spin_lock(&state_lock);
hash_delegation_locked(dp, fp);
spin_unlock(&state_lock);
return 0;
out_free:
+ if (fl->fl_file)
+ fput(fl->fl_file);
locks_free_lock(fl);
return status;
}
@@ -3918,6 +3987,7 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
status = nfserr_serverfault;
goto out;
}
+ get_file(file);
}
break;
case NFS4_OPEN_STID:
@@ -3945,7 +4015,7 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
}
status = nfs_ok;
if (file)
- *filpp = get_file(file);
+ *filpp = file;
out:
nfs4_unlock_state();
return status;
@@ -4662,6 +4732,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
break;
}
out:
+ if (filp)
+ fput(filp);
if (status && new_state)
release_lockowner_if_empty(lock_sop);
nfsd4_bump_seqid(cstate, status);
@@ -4801,7 +4873,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (!file_lock) {
dprintk("NFSD: %s: unable to allocate lock!\n", __func__);
status = nfserr_jukebox;
- goto out;
+ goto fput;
}
locks_init_lock(file_lock);
file_lock->fl_type = F_UNLCK;
@@ -4823,7 +4895,8 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
}
update_stateid(&stp->st_stid.sc_stateid);
memcpy(&locku->lu_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
-
+fput:
+ fput(filp);
out:
nfsd4_bump_seqid(cstate, status);
nfs4_unlock_state();
@@ -4833,7 +4906,7 @@ out:
out_nfserr:
status = nfserrno(err);
- goto out;
+ goto fput;
}
/*
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 30ad57089896..dc56ec234df7 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -399,32 +399,6 @@ struct nfs4_file {
bool fi_had_conflict;
};
-/* XXX: for first cut may fall back on returning file that doesn't work
- * at all? */
-static inline struct file *find_writeable_file(struct nfs4_file *f)
-{
- if (f->fi_fds[O_WRONLY])
- return f->fi_fds[O_WRONLY];
- return f->fi_fds[O_RDWR];
-}
-
-static inline struct file *find_readable_file(struct nfs4_file *f)
-{
- if (f->fi_fds[O_RDONLY])
- return f->fi_fds[O_RDONLY];
- return f->fi_fds[O_RDWR];
-}
-
-static inline struct file *find_any_file(struct nfs4_file *f)
-{
- if (f->fi_fds[O_RDWR])
- return f->fi_fds[O_RDWR];
- else if (f->fi_fds[O_WRONLY])
- return f->fi_fds[O_WRONLY];
- else
- return f->fi_fds[O_RDONLY];
-}
-
/* "ol" stands for "Open or Lock". Better suggestions welcome. */
struct nfs4_ol_stateid {
struct nfs4_stid st_stid; /* must be first field */
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 024/114] nfsd: clean up helper __release_lock_stateid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (22 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 023/114] nfsd: Add locking to the nfs4_file->fi_fds[] array Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 025/114] nfsd: refactor nfs4_file_get_access and nfs4_file_put_access Jeff Layton
` (89 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Use filp_close instead of open coding. filp_close does a bit more than
just release the locks and put the filp. It also calls ->flush and
dnotify_flush, both of which should be done here anyway.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
fs/nfsd/nfs4state.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 05f6e1761821..b201f1c4695c 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -800,10 +800,8 @@ static void __release_lock_stateid(struct nfs4_ol_stateid *stp)
unhash_generic_stateid(stp);
unhash_stid(&stp->st_stid);
file = find_any_file(stp->st_file);
- if (file) {
- locks_remove_posix(file, (fl_owner_t)lockowner(stp->st_stateowner));
- fput(file);
- }
+ if (file)
+ filp_close(file, (fl_owner_t)lockowner(stp->st_stateowner));
close_generic_stateid(stp);
free_generic_stateid(stp);
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 025/114] nfsd: refactor nfs4_file_get_access and nfs4_file_put_access
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (23 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 024/114] nfsd: clean up helper __release_lock_stateid Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 026/114] nfsd: remove nfs4_file_put_fd Jeff Layton
` (88 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Have them take NFS4_SHARE_ACCESS_* flags instead of an open mode. This
spares the callers from having to convert it themselves.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 58 ++++++++++++++++++++++++++++++++---------------------
1 file changed, 35 insertions(+), 23 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b201f1c4695c..6d8be6c235ca 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -337,6 +337,20 @@ static unsigned int ownerstr_hashval(u32 clientid, struct xdr_netobj *ownername)
#define FILE_HASH_BITS 8
#define FILE_HASH_SIZE (1 << FILE_HASH_BITS)
+static int nfs4_access_to_omode(u32 access)
+{
+ switch (access & NFS4_SHARE_ACCESS_BOTH) {
+ case NFS4_SHARE_ACCESS_READ:
+ return O_RDONLY;
+ case NFS4_SHARE_ACCESS_WRITE:
+ return O_WRONLY;
+ case NFS4_SHARE_ACCESS_BOTH:
+ return O_RDWR;
+ }
+ WARN_ON_ONCE(1);
+ return O_RDONLY;
+}
+
static unsigned int file_hashval(struct inode *ino)
{
/* XXX: why are we hashing on inode pointer, anyway? */
@@ -351,8 +365,15 @@ static void __nfs4_file_get_access(struct nfs4_file *fp, int oflag)
atomic_inc(&fp->fi_access[oflag]);
}
-static void nfs4_file_get_access(struct nfs4_file *fp, int oflag)
+static void nfs4_file_get_access(struct nfs4_file *fp, u32 access)
{
+ int oflag = nfs4_access_to_omode(access);
+
+ /* Note: relies on NFS4_SHARE_ACCESS_BOTH == READ|WRITE */
+ access &= (NFS4_SHARE_ACCESS_READ|NFS4_SHARE_ACCESS_WRITE);
+ if (access == 0)
+ return;
+
if (oflag == O_RDWR) {
__nfs4_file_get_access(fp, O_RDONLY);
__nfs4_file_get_access(fp, O_WRONLY);
@@ -386,8 +407,15 @@ static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
}
}
-static void nfs4_file_put_access(struct nfs4_file *fp, int oflag)
+static void nfs4_file_put_access(struct nfs4_file *fp, u32 access)
{
+ int oflag;
+
+ access &= (NFS4_SHARE_ACCESS_READ|NFS4_SHARE_ACCESS_WRITE);
+ if (!access)
+ return;
+
+ oflag = nfs4_access_to_omode(access);
if (oflag == O_RDWR) {
__nfs4_file_put_access(fp, O_RDONLY);
__nfs4_file_put_access(fp, O_WRONLY);
@@ -741,20 +769,6 @@ test_deny(u32 access, struct nfs4_ol_stateid *stp)
return test_bit(access, &stp->st_deny_bmap);
}
-static int nfs4_access_to_omode(u32 access)
-{
- switch (access & NFS4_SHARE_ACCESS_BOTH) {
- case NFS4_SHARE_ACCESS_READ:
- return O_RDONLY;
- case NFS4_SHARE_ACCESS_WRITE:
- return O_WRONLY;
- case NFS4_SHARE_ACCESS_BOTH:
- return O_RDWR;
- }
- WARN_ON_ONCE(1);
- return O_RDONLY;
-}
-
/* release all access and file references for a given stateid */
static void
release_all_access(struct nfs4_ol_stateid *stp)
@@ -763,8 +777,7 @@ release_all_access(struct nfs4_ol_stateid *stp)
for (i = 1; i < 4; i++) {
if (test_access(i, stp))
- nfs4_file_put_access(stp->st_file,
- nfs4_access_to_omode(i));
+ nfs4_file_put_access(stp->st_file, i);
clear_access(i, stp);
}
}
@@ -3291,7 +3304,7 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
filp = NULL;
}
}
- nfs4_file_get_access(fp, oflag);
+ nfs4_file_get_access(fp, open->op_share_access);
spin_unlock(&fp->fi_lock);
if (filp)
fput(filp);
@@ -3303,7 +3316,7 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
return nfs_ok;
out_put_access:
- nfs4_file_put_access(fp, oflag);
+ nfs4_file_put_access(fp, open->op_share_access);
out:
return status;
}
@@ -4210,7 +4223,7 @@ static inline void nfs4_stateid_downgrade_bit(struct nfs4_ol_stateid *stp, u32 a
{
if (!test_access(access, stp))
return;
- nfs4_file_put_access(stp->st_file, nfs4_access_to_omode(access));
+ nfs4_file_put_access(stp->st_file, access);
clear_access(access, stp);
}
@@ -4535,11 +4548,10 @@ check_lock_length(u64 offset, u64 length)
static void get_lock_access(struct nfs4_ol_stateid *lock_stp, u32 access)
{
struct nfs4_file *fp = lock_stp->st_file;
- int oflag = nfs4_access_to_omode(access);
if (test_access(access, lock_stp))
return;
- nfs4_file_get_access(fp, oflag);
+ nfs4_file_get_access(fp, access);
set_access(access, lock_stp);
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 026/114] nfsd: remove nfs4_file_put_fd
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (24 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 025/114] nfsd: refactor nfs4_file_get_access and nfs4_file_put_access Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 027/114] nfsd: shrink st_access_bmap and st_deny_bmap Jeff Layton
` (87 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
...and replace it with a simple swap call.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 13 ++-----------
1 file changed, 2 insertions(+), 11 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 6d8be6c235ca..485a0dc039d5 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -381,24 +381,15 @@ static void nfs4_file_get_access(struct nfs4_file *fp, u32 access)
__nfs4_file_get_access(fp, oflag);
}
-static struct file *nfs4_file_put_fd(struct nfs4_file *fp, int oflag)
-{
- struct file *filp;
-
- filp = fp->fi_fds[oflag];
- fp->fi_fds[oflag] = NULL;
- return filp;
-}
-
static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
{
if (atomic_dec_and_lock(&fp->fi_access[oflag], &fp->fi_lock)) {
struct file *f1 = NULL;
struct file *f2 = NULL;
- f1 = nfs4_file_put_fd(fp, oflag);
+ swap(f1, fp->fi_fds[oflag]);
if (atomic_read(&fp->fi_access[1 - oflag]) == 0)
- f2 = nfs4_file_put_fd(fp, O_RDWR);
+ swap(f2, fp->fi_fds[O_RDWR]);
spin_unlock(&fp->fi_lock);
if (f1)
fput(f1);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 027/114] nfsd: shrink st_access_bmap and st_deny_bmap
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (25 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 026/114] nfsd: remove nfs4_file_put_fd Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-07-01 10:51 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 028/114] nfsd: set stateid access and deny bits in nfs4_get_vfs_file Jeff Layton
` (86 subsequent siblings)
113 siblings, 1 reply; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
We never use anything above bit #3, so an unsigned long for each is
wasteful. Shrink them to a char each, and add some WARN_ON_ONCE calls if
we try to set or clear bits that would go outside those sizes.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 26 +++++++++++++++-----------
fs/nfsd/state.h | 4 ++--
2 files changed, 17 insertions(+), 13 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 485a0dc039d5..9dba8b7baf3b 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -722,42 +722,46 @@ test_share(struct nfs4_ol_stateid *stp, struct nfsd4_open *open) {
static inline void
set_access(u32 access, struct nfs4_ol_stateid *stp)
{
- __set_bit(access, &stp->st_access_bmap);
+ WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
+ __set_bit(access, (unsigned long *)&stp->st_access_bmap);
}
/* clear share access for a given stateid */
static inline void
clear_access(u32 access, struct nfs4_ol_stateid *stp)
{
- __clear_bit(access, &stp->st_access_bmap);
+ WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
+ __clear_bit(access, (unsigned long *)&stp->st_access_bmap);
}
/* test whether a given stateid has access */
static inline bool
test_access(u32 access, struct nfs4_ol_stateid *stp)
{
- return test_bit(access, &stp->st_access_bmap);
+ return test_bit(access, (unsigned long *)&stp->st_access_bmap);
}
/* set share deny for a given stateid */
static inline void
-set_deny(u32 access, struct nfs4_ol_stateid *stp)
+set_deny(u32 deny, struct nfs4_ol_stateid *stp)
{
- __set_bit(access, &stp->st_deny_bmap);
+ WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
+ __set_bit(deny, (unsigned long *)&stp->st_deny_bmap);
}
/* clear share deny for a given stateid */
static inline void
-clear_deny(u32 access, struct nfs4_ol_stateid *stp)
+clear_deny(u32 deny, struct nfs4_ol_stateid *stp)
{
- __clear_bit(access, &stp->st_deny_bmap);
+ WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
+ __clear_bit(deny, (unsigned long *)&stp->st_deny_bmap);
}
/* test whether a given stateid is denying specific access */
static inline bool
-test_deny(u32 access, struct nfs4_ol_stateid *stp)
+test_deny(u32 deny, struct nfs4_ol_stateid *stp)
{
- return test_bit(access, &stp->st_deny_bmap);
+ return test_bit(deny, (unsigned long *)&stp->st_deny_bmap);
}
/* release all access and file references for a given stateid */
@@ -4270,12 +4274,12 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
goto out;
status = nfserr_inval;
if (!test_access(od->od_share_access, stp)) {
- dprintk("NFSD: access not a subset current bitmap: 0x%lx, input access=%08x\n",
+ dprintk("NFSD: access not a subset of current bitmap: 0x%hhx, input access=%08x\n",
stp->st_access_bmap, od->od_share_access);
goto out;
}
if (!test_deny(od->od_share_deny, stp)) {
- dprintk("NFSD:deny not a subset current bitmap: 0x%lx, input deny=%08x\n",
+ dprintk("NFSD: deny not a subset of current bitmap: 0x%hhx, input deny=%08x\n",
stp->st_deny_bmap, od->od_share_deny);
goto out;
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index dc56ec234df7..949b331d9e13 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -407,8 +407,8 @@ struct nfs4_ol_stateid {
struct list_head st_locks;
struct nfs4_stateowner * st_stateowner;
struct nfs4_file * st_file;
- unsigned long st_access_bmap;
- unsigned long st_deny_bmap;
+ unsigned char st_access_bmap;
+ unsigned char st_deny_bmap;
struct nfs4_ol_stateid * st_openstp;
};
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* Re: [PATCH v3 027/114] nfsd: shrink st_access_bmap and st_deny_bmap
2014-06-30 15:48 ` [PATCH v3 027/114] nfsd: shrink st_access_bmap and st_deny_bmap Jeff Layton
@ 2014-07-01 10:51 ` Jeff Layton
0 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-07-01 10:51 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Christoph Hellwig
On Mon, 30 Jun 2014 11:48:56 -0400
Jeff Layton <jlayton@primarydata.com> wrote:
> We never use anything above bit #3, so an unsigned long for each is
> wasteful. Shrink them to a char each, and add some WARN_ON_ONCE calls if
> we try to set or clear bits that would go outside those sizes.
>
> Signed-off-by: Jeff Layton <jlayton@primarydata.com>
> ---
> fs/nfsd/nfs4state.c | 26 +++++++++++++++-----------
> fs/nfsd/state.h | 4 ++--
> 2 files changed, 17 insertions(+), 13 deletions(-)
>
> diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
> index 485a0dc039d5..9dba8b7baf3b 100644
> --- a/fs/nfsd/nfs4state.c
> +++ b/fs/nfsd/nfs4state.c
> @@ -722,42 +722,46 @@ test_share(struct nfs4_ol_stateid *stp, struct nfsd4_open *open) {
> static inline void
> set_access(u32 access, struct nfs4_ol_stateid *stp)
> {
> - __set_bit(access, &stp->st_access_bmap);
> + WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
> + __set_bit(access, (unsigned long *)&stp->st_access_bmap);
Doh! Stupid braino on my part here, and self-NAK on this patch.
The above won't work (or be safe) on a big-endian machine. Probably, the
thing to do is to convert this not to use atomic bitops since atomicity
doesn't seem to be a huge factor anyway. Let me respin this patch and do
that. Luckily the rest of the series shouldn't be greatly affected by
this (aside from a few merge conflicts).
> }
>
> /* clear share access for a given stateid */
> static inline void
> clear_access(u32 access, struct nfs4_ol_stateid *stp)
> {
> - __clear_bit(access, &stp->st_access_bmap);
> + WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH);
> + __clear_bit(access, (unsigned long *)&stp->st_access_bmap);
> }
>
> /* test whether a given stateid has access */
> static inline bool
> test_access(u32 access, struct nfs4_ol_stateid *stp)
> {
> - return test_bit(access, &stp->st_access_bmap);
> + return test_bit(access, (unsigned long *)&stp->st_access_bmap);
> }
>
> /* set share deny for a given stateid */
> static inline void
> -set_deny(u32 access, struct nfs4_ol_stateid *stp)
> +set_deny(u32 deny, struct nfs4_ol_stateid *stp)
> {
> - __set_bit(access, &stp->st_deny_bmap);
> + WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
> + __set_bit(deny, (unsigned long *)&stp->st_deny_bmap);
> }
>
> /* clear share deny for a given stateid */
> static inline void
> -clear_deny(u32 access, struct nfs4_ol_stateid *stp)
> +clear_deny(u32 deny, struct nfs4_ol_stateid *stp)
> {
> - __clear_bit(access, &stp->st_deny_bmap);
> + WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH);
> + __clear_bit(deny, (unsigned long *)&stp->st_deny_bmap);
> }
>
> /* test whether a given stateid is denying specific access */
> static inline bool
> -test_deny(u32 access, struct nfs4_ol_stateid *stp)
> +test_deny(u32 deny, struct nfs4_ol_stateid *stp)
> {
> - return test_bit(access, &stp->st_deny_bmap);
> + return test_bit(deny, (unsigned long *)&stp->st_deny_bmap);
> }
>
> /* release all access and file references for a given stateid */
> @@ -4270,12 +4274,12 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
> goto out;
> status = nfserr_inval;
> if (!test_access(od->od_share_access, stp)) {
> - dprintk("NFSD: access not a subset current bitmap: 0x%lx, input access=%08x\n",
> + dprintk("NFSD: access not a subset of current bitmap: 0x%hhx, input access=%08x\n",
> stp->st_access_bmap, od->od_share_access);
> goto out;
> }
> if (!test_deny(od->od_share_deny, stp)) {
> - dprintk("NFSD:deny not a subset current bitmap: 0x%lx, input deny=%08x\n",
> + dprintk("NFSD: deny not a subset of current bitmap: 0x%hhx, input deny=%08x\n",
> stp->st_deny_bmap, od->od_share_deny);
> goto out;
> }
> diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
> index dc56ec234df7..949b331d9e13 100644
> --- a/fs/nfsd/state.h
> +++ b/fs/nfsd/state.h
> @@ -407,8 +407,8 @@ struct nfs4_ol_stateid {
> struct list_head st_locks;
> struct nfs4_stateowner * st_stateowner;
> struct nfs4_file * st_file;
> - unsigned long st_access_bmap;
> - unsigned long st_deny_bmap;
> + unsigned char st_access_bmap;
> + unsigned char st_deny_bmap;
> struct nfs4_ol_stateid * st_openstp;
> };
>
--
Jeff Layton <jlayton@poochiereds.net>
^ permalink raw reply [flat|nested] 151+ messages in thread
* [PATCH v3 028/114] nfsd: set stateid access and deny bits in nfs4_get_vfs_file
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (26 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 027/114] nfsd: shrink st_access_bmap and st_deny_bmap Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 029/114] nfsd: clean up reset_union_bmap_deny Jeff Layton
` (85 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Cleanup -- ensure that the stateid bits are set at the same time that
the file access refcounts are incremented. Keeping them coherent like
this makes it easier to ensure that we account for all of the
references.
Since the initialization of the st_*_bmap fields is done when it's
hashed, we go ahead and hash the stateid before getting access to the
file and unhash it if that function returns error. This will be
necessary anyway in a follow-on patch that will overhaul deny mode
handling.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 23 ++++++++++++-----------
1 file changed, 12 insertions(+), 11 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9dba8b7baf3b..343b8de6309d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3280,7 +3280,8 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh,
}
static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
- struct svc_fh *cur_fh, struct nfsd4_open *open)
+ struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp,
+ struct nfsd4_open *open)
{
struct file *filp = NULL;
__be32 status;
@@ -3308,6 +3309,9 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
if (status)
goto out_put_access;
+ /* Set access and deny bits in stateid */
+ set_access(open->op_share_access, stp);
+ set_deny(open->op_share_deny, stp);
return nfs_ok;
out_put_access:
@@ -3319,20 +3323,15 @@ out:
static __be32
nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open)
{
- u32 op_share_access = open->op_share_access;
__be32 status;
- if (!test_access(op_share_access, stp))
- status = nfs4_get_vfs_file(rqstp, fp, cur_fh, open);
+ if (!test_access(open->op_share_access, stp))
+ status = nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open);
else
status = nfsd4_truncate(rqstp, cur_fh, open);
if (status)
return status;
-
- /* remember the open */
- set_access(op_share_access, stp);
- set_deny(open->op_share_deny, stp);
return nfs_ok;
}
@@ -3580,12 +3579,14 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
if (status)
goto out;
} else {
- status = nfs4_get_vfs_file(rqstp, fp, current_fh, open);
- if (status)
- goto out;
stp = open->op_stp;
open->op_stp = NULL;
init_open_stateid(stp, fp, open);
+ status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open);
+ if (status) {
+ release_open_stateid(stp);
+ goto out;
+ }
}
update_stateid(&stp->st_stid.sc_stateid);
memcpy(&open->op_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 029/114] nfsd: clean up reset_union_bmap_deny
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (27 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 028/114] nfsd: set stateid access and deny bits in nfs4_get_vfs_file Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:48 ` [PATCH v3 030/114] nfsd: make deny mode enforcement more efficient and close races in it Jeff Layton
` (84 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Fix the "deny" argument type, and start the loop at 1. The 0 iteration
is always a noop.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 343b8de6309d..d0e465cb0781 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4242,10 +4242,11 @@ static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_ac
}
static void
-reset_union_bmap_deny(unsigned long deny, struct nfs4_ol_stateid *stp)
+reset_union_bmap_deny(u32 deny, struct nfs4_ol_stateid *stp)
{
int i;
- for (i = 0; i < 4; i++) {
+
+ for (i = 1; i < 4; i++) {
if ((i & deny) != i)
clear_deny(i, stp);
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 030/114] nfsd: make deny mode enforcement more efficient and close races in it
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (28 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 029/114] nfsd: clean up reset_union_bmap_deny Jeff Layton
@ 2014-06-30 15:48 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 031/114] nfsd: cleanup nfs4_check_open Jeff Layton
` (83 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:48 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
The current enforcement of deny modes is both inefficient and scattered
across several places, which makes it hard to guarantee atomicity. The
inefficiency is a problem now, and the lack of atomicity will mean races
once the client_mutex is removed.
First, we address the inefficiency. We have to track deny modes on a
per-stateid basis to ensure that open downgrades are sane, but when the
server goes to enforce them it has to walk the entire list of stateids
and check against each one.
Instead of doing that, maintain a per-nfs4_file deny mode. When a file
is opened, we simply set any deny bits in that mode that were specified
in the OPEN call. We can then use that unified deny mode to do a simple
check to see whether there are any conflicts without needing to walk the
entire stateid list.
The only time we'll need to walk the entire list of stateids is when a
stateid that has a deny mode on it is being released, or one is having
its deny mode downgraded. In that case, we must walk the entire list and
recalculate the fi_share_deny field. Since deny modes are pretty rare
today, this should be very rare under normal workloads.
To address the potential for races once the client_mutex is removed,
protect fi_share_deny with the fi_lock. In nfs4_get_vfs_file, check to
make sure that any deny mode we want to apply won't conflict with
existing access. If that's ok, then have nfs4_file_get_access check that
new access to the file won't conflict with existing deny modes.
If that also passes, then get file access references, set the correct
access and deny bits in the stateid, and update the fi_share_deny field.
If opening the file or truncating it fails, then unwind the whole mess
and return the appropriate error.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 216 +++++++++++++++++++++++++++++++++++-----------------
fs/nfsd/state.h | 1 +
2 files changed, 148 insertions(+), 69 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d0e465cb0781..7eea841aa825 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -359,26 +359,53 @@ static unsigned int file_hashval(struct inode *ino)
static struct hlist_head file_hashtbl[FILE_HASH_SIZE];
-static void __nfs4_file_get_access(struct nfs4_file *fp, int oflag)
+static void
+__nfs4_file_get_access(struct nfs4_file *fp, u32 access)
{
- WARN_ON_ONCE(!(fp->fi_fds[oflag] || fp->fi_fds[O_RDWR]));
- atomic_inc(&fp->fi_access[oflag]);
+ int oflag = nfs4_access_to_omode(access);
+
+ if (oflag == O_RDWR) {
+ atomic_inc(&fp->fi_access[O_RDONLY]);
+ atomic_inc(&fp->fi_access[O_WRONLY]);
+ } else
+ atomic_inc(&fp->fi_access[oflag]);
}
-static void nfs4_file_get_access(struct nfs4_file *fp, u32 access)
+static __be32
+nfs4_file_get_access(struct nfs4_file *fp, u32 access)
{
- int oflag = nfs4_access_to_omode(access);
+ lockdep_assert_held(&fp->fi_lock);
/* Note: relies on NFS4_SHARE_ACCESS_BOTH == READ|WRITE */
- access &= (NFS4_SHARE_ACCESS_READ|NFS4_SHARE_ACCESS_WRITE);
+ access &= NFS4_SHARE_ACCESS_BOTH;
+
+ /* Does this access mask make sense? */
if (access == 0)
- return;
+ return nfserr_inval;
- if (oflag == O_RDWR) {
- __nfs4_file_get_access(fp, O_RDONLY);
- __nfs4_file_get_access(fp, O_WRONLY);
- } else
- __nfs4_file_get_access(fp, oflag);
+ /* Does it conflict with a deny mode already set? */
+ if ((access & fp->fi_share_deny) != 0)
+ return nfserr_share_denied;
+
+ __nfs4_file_get_access(fp, access);
+ return nfs_ok;
+}
+
+static __be32 nfs4_file_check_deny(struct nfs4_file *fp, u32 deny)
+{
+ /* Common case is that there is no deny mode. */
+ deny &= NFS4_SHARE_DENY_BOTH;
+ if (deny) {
+ /* Note: relies on NFS4_SHARE_DENY_BOTH == READ|WRITE */
+ if ((deny & NFS4_SHARE_DENY_READ) &&
+ atomic_read(&fp->fi_access[O_RDONLY]))
+ return nfserr_share_denied;
+
+ if ((deny & NFS4_SHARE_DENY_WRITE) &&
+ atomic_read(&fp->fi_access[O_WRONLY]))
+ return nfserr_share_denied;
+ }
+ return nfs_ok;
}
static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
@@ -707,17 +734,6 @@ bmap_to_share_mode(unsigned long bmap) {
return access;
}
-static bool
-test_share(struct nfs4_ol_stateid *stp, struct nfsd4_open *open) {
- unsigned int access, deny;
-
- access = bmap_to_share_mode(stp->st_access_bmap);
- deny = bmap_to_share_mode(stp->st_deny_bmap);
- if ((access & open->op_share_deny) || (deny & open->op_share_access))
- return false;
- return true;
-}
-
/* set share access for a given stateid */
static inline void
set_access(u32 access, struct nfs4_ol_stateid *stp)
@@ -764,11 +780,49 @@ test_deny(u32 deny, struct nfs4_ol_stateid *stp)
return test_bit(deny, (unsigned long *)&stp->st_deny_bmap);
}
+/*
+ * A stateid that had a deny mode associated with it is being released
+ * or downgraded. Recalculate the deny mode on the file.
+ */
+static void
+recalculate_deny_mode(struct nfs4_file *fp)
+{
+ struct nfs4_ol_stateid *stp;
+
+ spin_lock(&fp->fi_lock);
+ fp->fi_share_deny = 0;
+ list_for_each_entry(stp, &fp->fi_stateids, st_perfile)
+ fp->fi_share_deny |= bmap_to_share_mode(stp->st_deny_bmap);
+ spin_unlock(&fp->fi_lock);
+}
+
+static void
+reset_union_bmap_deny(u32 deny, struct nfs4_ol_stateid *stp)
+{
+ int i;
+ bool change = false;
+
+ for (i = 1; i < 4; i++) {
+ if ((i & deny) != i) {
+ change = true;
+ clear_deny(i, stp);
+ }
+ }
+
+ /* Recalculate per-file deny mode if there was a change */
+ if (change)
+ recalculate_deny_mode(stp->st_file);
+}
+
/* release all access and file references for a given stateid */
static void
release_all_access(struct nfs4_ol_stateid *stp)
{
int i;
+ struct nfs4_file *fp = stp->st_file;
+
+ if (fp && stp->st_deny_bmap != 0)
+ recalculate_deny_mode(fp);
for (i = 1; i < 4; i++) {
if (test_access(i, stp))
@@ -2759,6 +2813,7 @@ static void nfsd4_init_file(struct nfs4_file *fp, struct inode *ino)
fp->fi_inode = ino;
fp->fi_had_conflict = false;
fp->fi_lease = NULL;
+ fp->fi_share_deny = 0;
memset(fp->fi_fds, 0, sizeof(fp->fi_fds));
memset(fp->fi_access, 0, sizeof(fp->fi_access));
hlist_add_head(&fp->fi_hash, &file_hashtbl[hashval]);
@@ -2987,22 +3042,15 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
{
struct inode *ino = current_fh->fh_dentry->d_inode;
struct nfs4_file *fp;
- struct nfs4_ol_stateid *stp;
- __be32 ret;
+ __be32 ret = nfs_ok;
fp = find_file(ino);
if (!fp)
- return nfs_ok;
- ret = nfserr_locked;
- /* Search for conflicting share reservations */
+ return ret;
+ /* Check for conflicting share reservations */
spin_lock(&fp->fi_lock);
- list_for_each_entry(stp, &fp->fi_stateids, st_perfile) {
- if (test_deny(deny_type, stp) ||
- test_deny(NFS4_SHARE_DENY_BOTH, stp))
- goto out;
- }
- ret = nfs_ok;
-out:
+ if (fp->fi_share_deny & deny_type)
+ ret = nfserr_locked;
spin_unlock(&fp->fi_lock);
put_nfs4_file(fp);
return ret;
@@ -3241,12 +3289,9 @@ nfs4_check_open(struct nfs4_file *fp, struct nfsd4_open *open, struct nfs4_ol_st
if (local->st_stateowner->so_is_open_owner == 0)
continue;
/* remember if we have seen this open owner */
- if (local->st_stateowner == &oo->oo_owner)
+ if (local->st_stateowner == &oo->oo_owner) {
*stpp = local;
- /* check for conflicting share reservations */
- if (!test_share(local, open)) {
- spin_unlock(&fp->fi_lock);
- return nfserr_share_denied;
+ break;
}
}
spin_unlock(&fp->fi_lock);
@@ -3287,20 +3332,47 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
__be32 status;
int oflag = nfs4_access_to_omode(open->op_share_access);
int access = nfs4_access_to_access(open->op_share_access);
+ unsigned char old_access_bmap, old_deny_bmap;
spin_lock(&fp->fi_lock);
+
+ /*
+ * Are we trying to set a deny mode that would conflict with
+ * current access?
+ */
+ status = nfs4_file_check_deny(fp, open->op_share_deny);
+ if (status != nfs_ok) {
+ spin_unlock(&fp->fi_lock);
+ goto out;
+ }
+
+ /* set access to the file */
+ status = nfs4_file_get_access(fp, open->op_share_access);
+ if (status != nfs_ok) {
+ spin_unlock(&fp->fi_lock);
+ goto out;
+ }
+
+ /* Set access bits in stateid */
+ old_access_bmap = stp->st_access_bmap;
+ set_access(open->op_share_access, stp);
+
+ /* Set new deny mask */
+ old_deny_bmap = stp->st_deny_bmap;
+ set_deny(open->op_share_deny, stp);
+ fp->fi_share_deny |= (open->op_share_deny & NFS4_SHARE_DENY_BOTH);
+
if (!fp->fi_fds[oflag]) {
spin_unlock(&fp->fi_lock);
status = nfsd_open(rqstp, cur_fh, S_IFREG, access, &filp);
if (status)
- goto out;
+ goto out_put_access;
spin_lock(&fp->fi_lock);
if (!fp->fi_fds[oflag]) {
fp->fi_fds[oflag] = filp;
filp = NULL;
}
}
- nfs4_file_get_access(fp, open->op_share_access);
spin_unlock(&fp->fi_lock);
if (filp)
fput(filp);
@@ -3308,33 +3380,43 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp,
status = nfsd4_truncate(rqstp, cur_fh, open);
if (status)
goto out_put_access;
-
- /* Set access and deny bits in stateid */
- set_access(open->op_share_access, stp);
- set_deny(open->op_share_deny, stp);
- return nfs_ok;
-
-out_put_access:
- nfs4_file_put_access(fp, open->op_share_access);
out:
return status;
+out_put_access:
+ stp->st_access_bmap = old_access_bmap;
+ nfs4_file_put_access(fp, open->op_share_access);
+ reset_union_bmap_deny(bmap_to_share_mode(old_deny_bmap), stp);
+ goto out;
}
static __be32
nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open)
{
__be32 status;
+ unsigned char old_deny_bmap;
if (!test_access(open->op_share_access, stp))
- status = nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open);
- else
- status = nfsd4_truncate(rqstp, cur_fh, open);
+ return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open);
- if (status)
+ /* test and set deny mode */
+ spin_lock(&fp->fi_lock);
+ status = nfs4_file_check_deny(fp, open->op_share_deny);
+ if (status == nfs_ok) {
+ old_deny_bmap = stp->st_deny_bmap;
+ set_deny(open->op_share_deny, stp);
+ fp->fi_share_deny |=
+ (open->op_share_deny & NFS4_SHARE_DENY_BOTH);
+ }
+ spin_unlock(&fp->fi_lock);
+
+ if (status != nfs_ok)
return status;
- return nfs_ok;
-}
+ status = nfsd4_truncate(rqstp, cur_fh, open);
+ if (status != nfs_ok)
+ reset_union_bmap_deny(old_deny_bmap, stp);
+ return status;
+}
static void
nfs4_set_claim_prev(struct nfsd4_open *open, bool has_session)
@@ -3556,7 +3638,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
*/
fp = find_or_add_file(ino, open->op_file);
if (fp != open->op_file) {
- if ((status = nfs4_check_open(fp, open, &stp)))
+ status = nfs4_check_open(fp, open, &stp);
+ if (status)
goto out;
status = nfs4_check_deleg(cl, open, &dp);
if (status)
@@ -4241,17 +4324,6 @@ static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_ac
}
}
-static void
-reset_union_bmap_deny(u32 deny, struct nfs4_ol_stateid *stp)
-{
- int i;
-
- for (i = 1; i < 4; i++) {
- if ((i & deny) != i)
- clear_deny(i, stp);
- }
-}
-
__be32
nfsd4_open_downgrade(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
@@ -4546,9 +4618,15 @@ static void get_lock_access(struct nfs4_ol_stateid *lock_stp, u32 access)
{
struct nfs4_file *fp = lock_stp->st_file;
+ /*
+ * Lock stateids inherit the same access as the open stateid from which
+ * they are descended. We don't need to worry about holding the
+ * fp->fi_lock here since there is no danger of the access refcounts
+ * going to zero.
+ */
if (test_access(access, lock_stp))
return;
- nfs4_file_get_access(fp, access);
+ __nfs4_file_get_access(fp, access);
set_access(access, lock_stp);
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 949b331d9e13..e1f6b8847670 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -392,6 +392,7 @@ struct nfs4_file {
* + 1 to both of the above if NFS4_SHARE_ACCESS_BOTH is set.
*/
atomic_t fi_access[2];
+ u32 fi_share_deny;
struct file *fi_deleg_file;
struct file_lock *fi_lease;
atomic_t fi_delegees;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 031/114] nfsd: cleanup nfs4_check_open
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (29 preceding siblings ...)
2014-06-30 15:48 ` [PATCH v3 030/114] nfsd: make deny mode enforcement more efficient and close races in it Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 032/114] locks: add file_has_lease to prevent delegation break races Jeff Layton
` (82 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Rename it to better describe what it does, and have it just return the
stateid instead of a __be32 (which is now always nfs_ok). Also, do the
search for an existing stateid after the delegation check, to reduce
cleanup if the delegation check returns error.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 14 ++++++--------
1 file changed, 6 insertions(+), 8 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 7eea841aa825..f2ab4b39be22 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3277,10 +3277,10 @@ out:
return nfs_ok;
}
-static __be32
-nfs4_check_open(struct nfs4_file *fp, struct nfsd4_open *open, struct nfs4_ol_stateid **stpp)
+static struct nfs4_ol_stateid *
+nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
{
- struct nfs4_ol_stateid *local;
+ struct nfs4_ol_stateid *local, *ret = NULL;
struct nfs4_openowner *oo = open->op_openowner;
spin_lock(&fp->fi_lock);
@@ -3290,12 +3290,12 @@ nfs4_check_open(struct nfs4_file *fp, struct nfsd4_open *open, struct nfs4_ol_st
continue;
/* remember if we have seen this open owner */
if (local->st_stateowner == &oo->oo_owner) {
- *stpp = local;
+ ret = local;
break;
}
}
spin_unlock(&fp->fi_lock);
- return nfs_ok;
+ return ret;
}
static inline int nfs4_access_to_access(u32 nfs4_access)
@@ -3638,12 +3638,10 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf
*/
fp = find_or_add_file(ino, open->op_file);
if (fp != open->op_file) {
- status = nfs4_check_open(fp, open, &stp);
- if (status)
- goto out;
status = nfs4_check_deleg(cl, open, &dp);
if (status)
goto out;
+ stp = nfsd4_find_existing_open(fp, open);
} else {
open->op_file = NULL;
status = nfserr_bad_stateid;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 032/114] locks: add file_has_lease to prevent delegation break races
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (30 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 031/114] nfsd: cleanup nfs4_check_open Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 033/114] nfsd: Protect the nfs4_file delegation fields using the fi_lock Jeff Layton
` (81 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Once we remove the client_mutex, we'll have a potential race between
setting a lease on a file and breaking the delegation. We may set the
lease, but by the time we go to hash it, it may have already been
broken. Currently, we know that this won't happen as the nfs4_laundromat
takes the client_mutex, but we want to remove that.
As part of that fix, add a function that can tell us whether a
particular file has a lease set on it. In a later nfsd patch, we'll use
that to close the potential race window.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/locks.c | 26 ++++++++++++++++++++++++++
include/linux/fs.h | 6 ++++++
2 files changed, 32 insertions(+)
diff --git a/fs/locks.c b/fs/locks.c
index 717fbc404e6b..005cc86927e3 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1308,6 +1308,32 @@ static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker)
}
/**
+ * file_has_lease - does the given file have a lease set on it?
+ * @file: struct file on which we want to check the lease
+ *
+ * Returns true if a lease was is set on the given file description,
+ * false otherwise.
+ */
+bool
+file_has_lease(struct file *file)
+{
+ bool ret = false;
+ struct inode *inode = file_inode(file);
+ struct file_lock *fl;
+
+ spin_lock(&inode->i_lock);
+ for (fl = inode->i_flock; fl && IS_LEASE(fl); fl = fl->fl_next) {
+ if (fl->fl_file == file) {
+ ret = true;
+ break;
+ }
+ }
+ spin_unlock(&inode->i_lock);
+ return ret;
+}
+EXPORT_SYMBOL(file_has_lease);
+
+/**
* __break_lease - revoke all outstanding leases on file
* @inode: the inode of the file to return
* @mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR:
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e11d60cc867b..7ae6f4869669 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -953,6 +953,7 @@ extern int vfs_test_lock(struct file *, struct file_lock *);
extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
+extern bool file_has_lease(struct file *file);
extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
extern void lease_get_mtime(struct inode *, struct timespec *time);
extern int generic_setlease(struct file *, long, struct file_lock **);
@@ -1064,6 +1065,11 @@ static inline int flock_lock_file_wait(struct file *filp,
return -ENOLCK;
}
+static inline bool file_has_lease(struct file *file)
+{
+ return false;
+}
+
static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
{
return 0;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 033/114] nfsd: Protect the nfs4_file delegation fields using the fi_lock
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (31 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 032/114] locks: add file_has_lease to prevent delegation break races Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 034/114] nfsd: Simplify stateid management Jeff Layton
` (80 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Move more of the delegation fields to be protected by the fi_lock. It's
more granular than the state_lock and in later patches we'll want to
be able to rely on it in addition to the state_lock.
Also, the current code in nfs4_setlease calls vfs_setlease and uses the
client_mutex to ensure that it doesn't disappear before we can hash the
delegation. With the client_mutex gone, we'll have a potential race
condition.
It's possible that the delegation could be recalled after we acquire the
lease but before we ever get around to hashing it. If that happens, then
we'd have a nfs4_file that *thinks* it has a delegation, when it
actually has none.
Attempt to acquire a delegation. If that succeeds, take the state_lock
and recheck to make sure the lease is still there. If it is, then take
the fi_lock and set up the rest of the delegation fields. This prevents
the race because the delegation break workqueue job must also take the
state_lock.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 51 ++++++++++++++++++++++++++++++++++++++-------------
1 file changed, 38 insertions(+), 13 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f2ab4b39be22..f14b925f9de0 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -614,6 +614,8 @@ nfs4_put_delegation(struct nfs4_delegation *dp)
static void nfs4_put_deleg_lease(struct nfs4_file *fp)
{
+ lockdep_assert_held(&state_lock);
+
if (!fp->fi_lease)
return;
if (atomic_dec_and_test(&fp->fi_delegees)) {
@@ -633,11 +635,10 @@ static void
hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
{
lockdep_assert_held(&state_lock);
+ lockdep_assert_held(&fp->fi_lock);
dp->dl_stid.sc_type = NFS4_DELEG_STID;
- spin_lock(&fp->fi_lock);
list_add(&dp->dl_perfile, &fp->fi_delegations);
- spin_unlock(&fp->fi_lock);
list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
}
@@ -648,17 +649,17 @@ unhash_delegation(struct nfs4_delegation *dp)
struct nfs4_file *fp = dp->dl_file;
spin_lock(&state_lock);
+ spin_lock(&fp->fi_lock);
list_del_init(&dp->dl_perclnt);
list_del_init(&dp->dl_recall_lru);
- spin_lock(&fp->fi_lock);
list_del_init(&dp->dl_perfile);
spin_unlock(&fp->fi_lock);
- spin_unlock(&state_lock);
if (fp) {
nfs4_put_deleg_lease(fp);
- put_nfs4_file(fp);
dp->dl_file = NULL;
}
+ spin_unlock(&state_lock);
+ put_nfs4_file(fp);
}
@@ -3458,7 +3459,7 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
{
struct nfs4_file *fp = dp->dl_file;
struct file_lock *fl;
- int status;
+ int status = 0;
fl = nfs4_alloc_init_lease(dp, NFS4_OPEN_DELEGATE_READ);
if (!fl)
@@ -3466,15 +3467,31 @@ static int nfs4_setlease(struct nfs4_delegation *dp)
fl->fl_file = find_readable_file(fp);
status = vfs_setlease(fl->fl_file, fl->fl_type, &fl);
if (status)
- goto out_free;
+ goto out_fput;
+ spin_lock(&state_lock);
+ /* Did the lease get broken before we took the lock? */
+ status = -EAGAIN;
+ if (!file_has_lease(fl->fl_file))
+ goto out_unlock;
+ spin_lock(&fp->fi_lock);
+ /* Race breaker */
+ if (fp->fi_lease) {
+ status = 0;
+ atomic_inc(&fp->fi_delegees);
+ hash_delegation_locked(dp, fp);
+ spin_unlock(&fp->fi_lock);
+ goto out_unlock;
+ }
fp->fi_lease = fl;
fp->fi_deleg_file = fl->fl_file;
atomic_set(&fp->fi_delegees, 1);
- spin_lock(&state_lock);
hash_delegation_locked(dp, fp);
+ spin_unlock(&fp->fi_lock);
spin_unlock(&state_lock);
return 0;
-out_free:
+out_unlock:
+ spin_unlock(&state_lock);
+out_fput:
if (fl->fl_file)
fput(fl->fl_file);
locks_free_lock(fl);
@@ -3483,19 +3500,27 @@ out_free:
static int nfs4_set_delegation(struct nfs4_delegation *dp, struct nfs4_file *fp)
{
+ int status = 0;
+
if (fp->fi_had_conflict)
return -EAGAIN;
get_nfs4_file(fp);
+ spin_lock(&state_lock);
+ spin_lock(&fp->fi_lock);
dp->dl_file = fp;
- if (!fp->fi_lease)
+ if (!fp->fi_lease) {
+ spin_unlock(&fp->fi_lock);
+ spin_unlock(&state_lock);
return nfs4_setlease(dp);
- spin_lock(&state_lock);
+ }
atomic_inc(&fp->fi_delegees);
if (fp->fi_had_conflict) {
- spin_unlock(&state_lock);
- return -EAGAIN;
+ status = -EAGAIN;
+ goto out_unlock;
}
hash_delegation_locked(dp, fp);
+out_unlock:
+ spin_unlock(&fp->fi_lock);
spin_unlock(&state_lock);
return 0;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 034/114] nfsd: Simplify stateid management
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (32 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 033/114] nfsd: Protect the nfs4_file delegation fields using the fi_lock Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 035/114] nfsd: Fix delegation revocation Jeff Layton
` (79 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Don't allow stateids to clear the open file pointer until they are
being destroyed. Also, move to kzalloc and get rid of explicit
zeroing of fields.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 21 ++++++++++-----------
1 file changed, 10 insertions(+), 11 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f14b925f9de0..fdbd209b02a6 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -447,7 +447,7 @@ kmem_cache *slab)
struct nfs4_stid *stid;
int new_id;
- stid = kmem_cache_alloc(slab, GFP_KERNEL);
+ stid = kmem_cache_zalloc(slab, GFP_KERNEL);
if (!stid)
return NULL;
@@ -459,11 +459,9 @@ kmem_cache *slab)
if (new_id < 0)
goto out_free;
stid->sc_client = cl;
- stid->sc_type = 0;
stid->sc_stateid.si_opaque.so_id = new_id;
stid->sc_stateid.si_opaque.so_clid = cl->cl_clientid;
/* Will be incremented before return to client: */
- stid->sc_stateid.si_generation = 0;
atomic_set(&stid->sc_count, 1);
/*
@@ -582,10 +580,8 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
INIT_LIST_HEAD(&dp->dl_perfile);
INIT_LIST_HEAD(&dp->dl_perclnt);
INIT_LIST_HEAD(&dp->dl_recall_lru);
- dp->dl_file = NULL;
dp->dl_type = NFS4_OPEN_DELEGATE_READ;
fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle);
- dp->dl_time = 0;
return dp;
}
@@ -607,6 +603,8 @@ void
nfs4_put_delegation(struct nfs4_delegation *dp)
{
if (atomic_dec_and_test(&dp->dl_stid.sc_count)) {
+ if (dp->dl_file)
+ put_nfs4_file(dp->dl_file);
nfs4_free_stid(deleg_slab, &dp->dl_stid);
num_delegations--;
}
@@ -654,12 +652,9 @@ unhash_delegation(struct nfs4_delegation *dp)
list_del_init(&dp->dl_recall_lru);
list_del_init(&dp->dl_perfile);
spin_unlock(&fp->fi_lock);
- if (fp) {
+ if (fp)
nfs4_put_deleg_lease(fp);
- dp->dl_file = NULL;
- }
spin_unlock(&state_lock);
- put_nfs4_file(fp);
}
@@ -845,13 +840,13 @@ static void unhash_generic_stateid(struct nfs4_ol_stateid *stp)
static void close_generic_stateid(struct nfs4_ol_stateid *stp)
{
release_all_access(stp);
- put_nfs4_file(stp->st_file);
- stp->st_file = NULL;
}
static void free_generic_stateid(struct nfs4_ol_stateid *stp)
{
remove_stid(&stp->st_stid);
+ if (stp->st_file)
+ put_nfs4_file(stp->st_file);
nfs4_free_stid(stateid_slab, &stp->st_stid);
}
@@ -4406,6 +4401,10 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
if (list_empty(&oo->oo_owner.so_stateids))
release_openowner(oo);
} else {
+ if (s->st_file) {
+ put_nfs4_file(s->st_file);
+ s->st_file = NULL;
+ }
oo->oo_last_closed_stid = s;
/*
* In the 4.0 case we need to keep the owners around a
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 035/114] nfsd: Fix delegation revocation
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (33 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 034/114] nfsd: Simplify stateid management Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 036/114] nfsd: Add reference counting to the lock and open stateids Jeff Layton
` (78 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Ensure that the delegations cannot be found by the laundromat etc once
we add them to the various 'revoke' lists.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 56 +++++++++++++++++++++++++++++++++--------------------
1 file changed, 35 insertions(+), 21 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index fdbd209b02a6..befeb322cb92 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -640,13 +640,13 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
}
-/* Called under the state lock. */
static void
-unhash_delegation(struct nfs4_delegation *dp)
+unhash_delegation_locked(struct nfs4_delegation *dp)
{
struct nfs4_file *fp = dp->dl_file;
- spin_lock(&state_lock);
+ lockdep_assert_held(&state_lock);
+
spin_lock(&fp->fi_lock);
list_del_init(&dp->dl_perclnt);
list_del_init(&dp->dl_recall_lru);
@@ -654,23 +654,32 @@ unhash_delegation(struct nfs4_delegation *dp)
spin_unlock(&fp->fi_lock);
if (fp)
nfs4_put_deleg_lease(fp);
- spin_unlock(&state_lock);
}
+static void
+unhash_delegation(struct nfs4_delegation *dp)
+{
+ spin_lock(&state_lock);
+ unhash_delegation_locked(dp);
+ spin_unlock(&state_lock);
+}
-
-static void destroy_revoked_delegation(struct nfs4_delegation *dp)
+static void destroy_delegation(struct nfs4_delegation *dp)
{
- list_del_init(&dp->dl_recall_lru);
remove_stid(&dp->dl_stid);
nfs4_put_delegation(dp);
}
-static void destroy_delegation(struct nfs4_delegation *dp)
+static void unhash_and_destroy_delegation(struct nfs4_delegation *dp)
{
unhash_delegation(dp);
- remove_stid(&dp->dl_stid);
- nfs4_put_delegation(dp);
+ destroy_delegation(dp);
+}
+
+static void destroy_revoked_delegation(struct nfs4_delegation *dp)
+{
+ list_del_init(&dp->dl_recall_lru);
+ destroy_delegation(dp);
}
static void revoke_delegation(struct nfs4_delegation *dp)
@@ -678,11 +687,10 @@ static void revoke_delegation(struct nfs4_delegation *dp)
struct nfs4_client *clp = dp->dl_stid.sc_client;
if (clp->cl_minorversion == 0)
- destroy_delegation(dp);
+ destroy_revoked_delegation(dp);
else {
- unhash_delegation(dp);
dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID;
- list_add(&dp->dl_recall_lru, &clp->cl_revoked);
+ list_move(&dp->dl_recall_lru, &clp->cl_revoked);
}
}
@@ -1416,12 +1424,13 @@ destroy_client(struct nfs4_client *clp)
spin_lock(&state_lock);
while (!list_empty(&clp->cl_delegations)) {
dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt);
- list_del_init(&dp->dl_perclnt);
- list_move(&dp->dl_recall_lru, &reaplist);
+ unhash_delegation_locked(dp);
+ list_add(&dp->dl_recall_lru, &reaplist);
}
spin_unlock(&state_lock);
while (!list_empty(&reaplist)) {
dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
+ list_del_init(&dp->dl_recall_lru);
destroy_delegation(dp);
}
list_splice_init(&clp->cl_revoked, &reaplist);
@@ -3604,7 +3613,7 @@ nfs4_open_delegation(struct net *net, struct svc_fh *fh,
open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
return;
out_free:
- destroy_delegation(dp);
+ unhash_and_destroy_delegation(dp);
out_no_deleg:
open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE;
if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS &&
@@ -3843,7 +3852,8 @@ nfs4_laundromat(struct nfsd_net *nn)
new_timeo = min(new_timeo, t);
break;
}
- list_move(&dp->dl_recall_lru, &reaplist);
+ unhash_delegation_locked(dp);
+ list_add(&dp->dl_recall_lru, &reaplist);
}
spin_unlock(&state_lock);
list_for_each_safe(pos, next, &reaplist) {
@@ -4469,7 +4479,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
goto out;
- destroy_delegation(dp);
+ unhash_and_destroy_delegation(dp);
out:
nfs4_unlock_state();
@@ -5293,8 +5303,10 @@ static u64 nfsd_find_all_delegations(struct nfs4_client *clp, u64 max,
lockdep_assert_held(&state_lock);
list_for_each_entry_safe(dp, next, &clp->cl_delegations, dl_perclnt) {
- if (victims)
- list_move(&dp->dl_recall_lru, victims);
+ if (victims) {
+ unhash_delegation_locked(dp);
+ list_add(&dp->dl_recall_lru, victims);
+ }
if (++count == max)
break;
}
@@ -5543,11 +5555,13 @@ nfs4_state_shutdown_net(struct net *net)
spin_lock(&state_lock);
list_for_each_safe(pos, next, &nn->del_recall_lru) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
- list_move(&dp->dl_recall_lru, &reaplist);
+ unhash_delegation_locked(dp);
+ list_add(&dp->dl_recall_lru, &reaplist);
}
spin_unlock(&state_lock);
list_for_each_safe(pos, next, &reaplist) {
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
+ list_del_init(&dp->dl_recall_lru);
destroy_delegation(dp);
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 036/114] nfsd: Add reference counting to the lock and open stateids
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (34 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 035/114] nfsd: Fix delegation revocation Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 037/114] nfsd: Add a struct nfs4_file field to struct nfs4_stid Jeff Layton
` (77 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
When we remove the client_mutex, we'll need to be able to ensure that
these objects aren't destroyed while we're not holding locks.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 14 ++++++++------
1 file changed, 8 insertions(+), 6 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index befeb322cb92..380abf2258b3 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -850,8 +850,10 @@ static void close_generic_stateid(struct nfs4_ol_stateid *stp)
release_all_access(stp);
}
-static void free_generic_stateid(struct nfs4_ol_stateid *stp)
+static void put_generic_stateid(struct nfs4_ol_stateid *stp)
{
+ if (!atomic_dec_and_test(&stp->st_stid.sc_count))
+ return;
remove_stid(&stp->st_stid);
if (stp->st_file)
put_nfs4_file(stp->st_file);
@@ -869,7 +871,7 @@ static void __release_lock_stateid(struct nfs4_ol_stateid *stp)
if (file)
filp_close(file, (fl_owner_t)lockowner(stp->st_stateowner));
close_generic_stateid(stp);
- free_generic_stateid(stp);
+ put_generic_stateid(stp);
}
static void unhash_lockowner(struct nfs4_lockowner *lo)
@@ -932,7 +934,7 @@ static void unhash_open_stateid(struct nfs4_ol_stateid *stp)
static void release_open_stateid(struct nfs4_ol_stateid *stp)
{
unhash_open_stateid(stp);
- free_generic_stateid(stp);
+ put_generic_stateid(stp);
}
static void unhash_openowner(struct nfs4_openowner *oo)
@@ -953,7 +955,7 @@ static void release_last_closed_stateid(struct nfs4_openowner *oo)
struct nfs4_ol_stateid *s = oo->oo_last_closed_stid;
if (s) {
- free_generic_stateid(s);
+ put_generic_stateid(s);
oo->oo_last_closed_stid = NULL;
}
}
@@ -3758,7 +3760,7 @@ void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status)
if (open->op_file)
nfsd4_free_file(open->op_file);
if (open->op_stp)
- free_generic_stateid(open->op_stp);
+ put_generic_stateid(open->op_stp);
}
__be32
@@ -4407,9 +4409,9 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
unhash_open_stateid(s);
if (clp->cl_minorversion) {
- free_generic_stateid(s);
if (list_empty(&oo->oo_owner.so_stateids))
release_openowner(oo);
+ put_generic_stateid(s);
} else {
if (s->st_file) {
put_nfs4_file(s->st_file);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 037/114] nfsd: Add a struct nfs4_file field to struct nfs4_stid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (35 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 036/114] nfsd: Add reference counting to the lock and open stateids Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 038/114] nfsd: Replace nfs4_ol_stateid->st_file with the st_stid.sc_file Jeff Layton
` (76 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
All stateids are associated with a nfs4_file. Let's consolidate.
Start by replacing delegation->dl_file with the dl_stid.sc_file
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 18 +++++++++---------
fs/nfsd/state.h | 2 +-
2 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 380abf2258b3..76066ca9219c 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -596,6 +596,8 @@ static void remove_stid(struct nfs4_stid *s)
static void nfs4_free_stid(struct kmem_cache *slab, struct nfs4_stid *s)
{
+ if (s->sc_file)
+ put_nfs4_file(s->sc_file);
kmem_cache_free(slab, s);
}
@@ -603,8 +605,6 @@ void
nfs4_put_delegation(struct nfs4_delegation *dp)
{
if (atomic_dec_and_test(&dp->dl_stid.sc_count)) {
- if (dp->dl_file)
- put_nfs4_file(dp->dl_file);
nfs4_free_stid(deleg_slab, &dp->dl_stid);
num_delegations--;
}
@@ -643,7 +643,7 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
static void
unhash_delegation_locked(struct nfs4_delegation *dp)
{
- struct nfs4_file *fp = dp->dl_file;
+ struct nfs4_file *fp = dp->dl_stid.sc_file;
lockdep_assert_held(&state_lock);
@@ -3065,8 +3065,8 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type)
void nfsd4_prepare_cb_recall(struct nfs4_delegation *dp)
{
- struct nfs4_client *clp = dp->dl_stid.sc_client;
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(dp->dl_stid.sc_client->net,
+ nfsd_net_id);
/*
* We can't do this in nfsd_break_deleg_cb because it is
@@ -3456,14 +3456,14 @@ static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp, int f
fl->fl_flags = FL_DELEG;
fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
fl->fl_end = OFFSET_MAX;
- fl->fl_owner = (fl_owner_t)(dp->dl_file);
+ fl->fl_owner = (fl_owner_t)(dp->dl_stid.sc_file);
fl->fl_pid = current->tgid;
return fl;
}
static int nfs4_setlease(struct nfs4_delegation *dp)
{
- struct nfs4_file *fp = dp->dl_file;
+ struct nfs4_file *fp = dp->dl_stid.sc_file;
struct file_lock *fl;
int status = 0;
@@ -3513,7 +3513,7 @@ static int nfs4_set_delegation(struct nfs4_delegation *dp, struct nfs4_file *fp)
get_nfs4_file(fp);
spin_lock(&state_lock);
spin_lock(&fp->fi_lock);
- dp->dl_file = fp;
+ dp->dl_stid.sc_file = fp;
if (!fp->fi_lease) {
spin_unlock(&fp->fi_lock);
spin_unlock(&state_lock);
@@ -4101,7 +4101,7 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
if (status)
goto out;
if (filpp) {
- file = dp->dl_file->fi_deleg_file;
+ file = dp->dl_stid.sc_file->fi_deleg_file;
if (!file) {
WARN_ON_ONCE(1);
status = nfserr_serverfault;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index e1f6b8847670..339f430fd69f 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -84,6 +84,7 @@ struct nfs4_stid {
unsigned char sc_type;
stateid_t sc_stateid;
struct nfs4_client *sc_client;
+ struct nfs4_file *sc_file;
};
struct nfs4_delegation {
@@ -91,7 +92,6 @@ struct nfs4_delegation {
struct list_head dl_perfile;
struct list_head dl_perclnt;
struct list_head dl_recall_lru; /* delegation recalled */
- struct nfs4_file *dl_file;
u32 dl_type;
time_t dl_time;
/* For recall: */
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 038/114] nfsd: Replace nfs4_ol_stateid->st_file with the st_stid.sc_file
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (36 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 037/114] nfsd: Add a struct nfs4_file field to struct nfs4_stid Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 039/114] nfsd: Ensure stateids remain unique until they are freed Jeff Layton
` (75 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 50 +++++++++++++++++++++++++-------------------------
fs/nfsd/state.h | 1 -
2 files changed, 25 insertions(+), 26 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 76066ca9219c..0d62692b525b 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -815,7 +815,7 @@ reset_union_bmap_deny(u32 deny, struct nfs4_ol_stateid *stp)
/* Recalculate per-file deny mode if there was a change */
if (change)
- recalculate_deny_mode(stp->st_file);
+ recalculate_deny_mode(stp->st_stid.sc_file);
}
/* release all access and file references for a given stateid */
@@ -823,21 +823,21 @@ static void
release_all_access(struct nfs4_ol_stateid *stp)
{
int i;
- struct nfs4_file *fp = stp->st_file;
+ struct nfs4_file *fp = stp->st_stid.sc_file;
if (fp && stp->st_deny_bmap != 0)
recalculate_deny_mode(fp);
for (i = 1; i < 4; i++) {
if (test_access(i, stp))
- nfs4_file_put_access(stp->st_file, i);
+ nfs4_file_put_access(stp->st_stid.sc_file, i);
clear_access(i, stp);
}
}
static void unhash_generic_stateid(struct nfs4_ol_stateid *stp)
{
- struct nfs4_file *fp = stp->st_file;
+ struct nfs4_file *fp = stp->st_stid.sc_file;
spin_lock(&fp->fi_lock);
list_del(&stp->st_perfile);
@@ -855,8 +855,6 @@ static void put_generic_stateid(struct nfs4_ol_stateid *stp)
if (!atomic_dec_and_test(&stp->st_stid.sc_count))
return;
remove_stid(&stp->st_stid);
- if (stp->st_file)
- put_nfs4_file(stp->st_file);
nfs4_free_stid(stateid_slab, &stp->st_stid);
}
@@ -867,7 +865,7 @@ static void __release_lock_stateid(struct nfs4_ol_stateid *stp)
list_del(&stp->st_locks);
unhash_generic_stateid(stp);
unhash_stid(&stp->st_stid);
- file = find_any_file(stp->st_file);
+ file = find_any_file(stp->st_stid.sc_file);
if (file)
filp_close(file, (fl_owner_t)lockowner(stp->st_stateowner));
close_generic_stateid(stp);
@@ -2941,7 +2939,7 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
stp->st_stateowner = &oo->oo_owner;
get_nfs4_file(fp);
- stp->st_file = fp;
+ stp->st_stid.sc_file = fp;
stp->st_access_bmap = 0;
stp->st_deny_bmap = 0;
set_access(open->op_share_access, stp);
@@ -3604,7 +3602,7 @@ nfs4_open_delegation(struct net *net, struct svc_fh *fh,
dp = alloc_init_deleg(oo->oo_owner.so_client, stp, fh);
if (dp == NULL)
goto out_no_deleg;
- status = nfs4_set_delegation(dp, stp->st_file);
+ status = nfs4_set_delegation(dp, stp->st_stid.sc_file);
if (status)
goto out_free;
@@ -3895,7 +3893,7 @@ laundromat_main(struct work_struct *laundry)
static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp)
{
- if (fhp->fh_dentry->d_inode != stp->st_file->fi_inode)
+ if (fhp->fh_dentry->d_inode != stp->st_stid.sc_file->fi_inode)
return nfserr_bad_stateid;
return nfs_ok;
}
@@ -4123,10 +4121,12 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
if (status)
goto out;
if (filpp) {
+ struct nfs4_file *fp = stp->st_stid.sc_file;
+
if (flags & RD_STATE)
- file = find_readable_file(stp->st_file);
+ file = find_readable_file(fp);
else
- file = find_writeable_file(stp->st_file);
+ file = find_writeable_file(fp);
}
break;
default:
@@ -4146,7 +4146,7 @@ nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp)
{
struct nfs4_lockowner *lo = lockowner(stp->st_stateowner);
- if (check_for_locks(stp->st_file, lo))
+ if (check_for_locks(stp->st_stid.sc_file, lo))
return nfserr_locks_held;
release_lockowner_if_empty(lo);
return nfs_ok;
@@ -4332,7 +4332,7 @@ static inline void nfs4_stateid_downgrade_bit(struct nfs4_ol_stateid *stp, u32 a
{
if (!test_access(access, stp))
return;
- nfs4_file_put_access(stp->st_file, access);
+ nfs4_file_put_access(stp->st_stid.sc_file, access);
clear_access(access, stp);
}
@@ -4413,9 +4413,9 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
release_openowner(oo);
put_generic_stateid(s);
} else {
- if (s->st_file) {
- put_nfs4_file(s->st_file);
- s->st_file = NULL;
+ if (s->st_stid.sc_file) {
+ put_nfs4_file(s->st_stid.sc_file);
+ s->st_stid.sc_file = NULL;
}
oo->oo_last_closed_stid = s;
/*
@@ -4617,7 +4617,7 @@ alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct
list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
stp->st_stateowner = &lo->lo_owner;
get_nfs4_file(fp);
- stp->st_file = fp;
+ stp->st_stid.sc_file = fp;
stp->st_access_bmap = 0;
stp->st_deny_bmap = open_stp->st_deny_bmap;
stp->st_openstp = open_stp;
@@ -4634,7 +4634,7 @@ find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
struct nfs4_ol_stateid *lst;
list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) {
- if (lst->st_file == fp)
+ if (lst->st_stid.sc_file == fp)
return lst;
}
return NULL;
@@ -4650,7 +4650,7 @@ check_lock_length(u64 offset, u64 length)
static void get_lock_access(struct nfs4_ol_stateid *lock_stp, u32 access)
{
- struct nfs4_file *fp = lock_stp->st_file;
+ struct nfs4_file *fp = lock_stp->st_stid.sc_file;
/*
* Lock stateids inherit the same access as the open stateid from which
@@ -4666,7 +4666,7 @@ static void get_lock_access(struct nfs4_ol_stateid *lock_stp, u32 access)
static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *ost, struct nfsd4_lock *lock, struct nfs4_ol_stateid **lst, bool *new)
{
- struct nfs4_file *fi = ost->st_file;
+ struct nfs4_file *fi = ost->st_stid.sc_file;
struct nfs4_openowner *oo = openowner(ost->st_stateowner);
struct nfs4_client *cl = oo->oo_owner.so_client;
struct nfs4_lockowner *lo;
@@ -4793,14 +4793,14 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
switch (lock->lk_type) {
case NFS4_READ_LT:
case NFS4_READW_LT:
- filp = find_readable_file(lock_stp->st_file);
+ filp = find_readable_file(lock_stp->st_stid.sc_file);
if (filp)
get_lock_access(lock_stp, NFS4_SHARE_ACCESS_READ);
file_lock->fl_type = F_RDLCK;
break;
case NFS4_WRITE_LT:
case NFS4_WRITEW_LT:
- filp = find_writeable_file(lock_stp->st_file);
+ filp = find_writeable_file(lock_stp->st_stid.sc_file);
if (filp)
get_lock_access(lock_stp, NFS4_SHARE_ACCESS_WRITE);
file_lock->fl_type = F_WRLCK;
@@ -4983,7 +4983,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
&stp, nn);
if (status)
goto out;
- filp = find_any_file(stp->st_file);
+ filp = find_any_file(stp->st_stid.sc_file);
if (!filp) {
status = nfserr_lock_range;
goto out;
@@ -5096,7 +5096,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
lo = lockowner(sop);
/* see if there are still any locks associated with it */
list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) {
- if (check_for_locks(stp->st_file, lo))
+ if (check_for_locks(stp->st_stid.sc_file, lo))
goto out;
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 339f430fd69f..722adb4e144b 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -407,7 +407,6 @@ struct nfs4_ol_stateid {
struct list_head st_perstateowner;
struct list_head st_locks;
struct nfs4_stateowner * st_stateowner;
- struct nfs4_file * st_file;
unsigned char st_access_bmap;
unsigned char st_deny_bmap;
struct nfs4_ol_stateid * st_openstp;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 039/114] nfsd: Ensure stateids remain unique until they are freed
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (37 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 038/114] nfsd: Replace nfs4_ol_stateid->st_file with the st_stid.sc_file Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 040/114] nfsd: Ensure atomicity of stateid destruction and idr tree removal Jeff Layton
` (74 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Add an extra delegation state to allow the stateid to remain in the idr
tree until the last reference has been released. This will be necessary
to ensure uniqueness once the client_mutex is removed.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 8 +++++---
fs/nfsd/state.h | 1 +
2 files changed, 6 insertions(+), 3 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 0d62692b525b..902e5f54c166 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -596,6 +596,7 @@ static void remove_stid(struct nfs4_stid *s)
static void nfs4_free_stid(struct kmem_cache *slab, struct nfs4_stid *s)
{
+ remove_stid(s);
if (s->sc_file)
put_nfs4_file(s->sc_file);
kmem_cache_free(slab, s);
@@ -666,7 +667,7 @@ unhash_delegation(struct nfs4_delegation *dp)
static void destroy_delegation(struct nfs4_delegation *dp)
{
- remove_stid(&dp->dl_stid);
+ dp->dl_stid.sc_type = NFS4_CLOSED_DELEG_STID;
nfs4_put_delegation(dp);
}
@@ -679,7 +680,7 @@ static void unhash_and_destroy_delegation(struct nfs4_delegation *dp)
static void destroy_revoked_delegation(struct nfs4_delegation *dp)
{
list_del_init(&dp->dl_recall_lru);
- destroy_delegation(dp);
+ nfs4_put_delegation(dp);
}
static void revoke_delegation(struct nfs4_delegation *dp)
@@ -854,7 +855,6 @@ static void put_generic_stateid(struct nfs4_ol_stateid *stp)
{
if (!atomic_dec_and_test(&stp->st_stid.sc_count))
return;
- remove_stid(&stp->st_stid);
nfs4_free_stid(stateid_slab, &stp->st_stid);
}
@@ -4029,7 +4029,9 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
return nfs_ok;
default:
printk("unknown stateid type %x\n", s->sc_type);
+ /* Fallthrough */
case NFS4_CLOSED_STID:
+ case NFS4_CLOSED_DELEG_STID:
return nfserr_bad_stateid;
}
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 722adb4e144b..95d04fae365a 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -81,6 +81,7 @@ struct nfs4_stid {
#define NFS4_CLOSED_STID 8
/* For a deleg stateid kept around only to process free_stateid's: */
#define NFS4_REVOKED_DELEG_STID 16
+#define NFS4_CLOSED_DELEG_STID 32
unsigned char sc_type;
stateid_t sc_stateid;
struct nfs4_client *sc_client;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 040/114] nfsd: Ensure atomicity of stateid destruction and idr tree removal
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (38 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 039/114] nfsd: Ensure stateids remain unique until they are freed Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 041/114] nfsd: Cleanup the freeing of stateids Jeff Layton
` (73 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Preparation for removal of the client_mutex. Ensure that they are done
while holding the clp->cl_lock.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 27 ++++++++++++++++-----------
1 file changed, 16 insertions(+), 11 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 902e5f54c166..e51df8c590be 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -585,30 +585,37 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
return dp;
}
-static void remove_stid(struct nfs4_stid *s)
+static void remove_stid_locked(struct nfs4_client *clp, struct nfs4_stid *s)
{
- struct nfs4_client *clp = s->sc_client;
+ lockdep_assert_held(&clp->cl_lock);
- spin_lock(&clp->cl_lock);
idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
- spin_unlock(&clp->cl_lock);
}
static void nfs4_free_stid(struct kmem_cache *slab, struct nfs4_stid *s)
{
- remove_stid(s);
if (s->sc_file)
put_nfs4_file(s->sc_file);
kmem_cache_free(slab, s);
}
+static bool nfs4_put_stid(struct kmem_cache *slab, struct nfs4_stid *s)
+{
+ struct nfs4_client *clp = s->sc_client;
+
+ if (!atomic_dec_and_lock(&s->sc_count, &clp->cl_lock))
+ return false;
+ remove_stid_locked(clp, s);
+ spin_unlock(&clp->cl_lock);
+ nfs4_free_stid(slab, s);
+ return true;
+}
+
void
nfs4_put_delegation(struct nfs4_delegation *dp)
{
- if (atomic_dec_and_test(&dp->dl_stid.sc_count)) {
- nfs4_free_stid(deleg_slab, &dp->dl_stid);
+ if (nfs4_put_stid(deleg_slab, &dp->dl_stid))
num_delegations--;
- }
}
static void nfs4_put_deleg_lease(struct nfs4_file *fp)
@@ -853,9 +860,7 @@ static void close_generic_stateid(struct nfs4_ol_stateid *stp)
static void put_generic_stateid(struct nfs4_ol_stateid *stp)
{
- if (!atomic_dec_and_test(&stp->st_stid.sc_count))
- return;
- nfs4_free_stid(stateid_slab, &stp->st_stid);
+ nfs4_put_stid(stateid_slab, &stp->st_stid);
}
static void __release_lock_stateid(struct nfs4_ol_stateid *stp)
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 041/114] nfsd: Cleanup the freeing of stateids
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (39 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 040/114] nfsd: Ensure atomicity of stateid destruction and idr tree removal Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 042/114] nfsd: do filp_close in sc_free callback for lock stateids Jeff Layton
` (72 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Add a ->free() callback to the struct nfs4_stid, so that we can
release a reference to the stid without caring about the contents.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 62 +++++++++++++++++++++++++++++++++++------------------
fs/nfsd/state.h | 2 ++
2 files changed, 43 insertions(+), 21 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e51df8c590be..ed3df2cdd025 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -71,6 +71,7 @@ static u64 current_sessionid = 1;
/* forward declarations */
static int check_for_locks(struct nfs4_file *filp, struct nfs4_lockowner *lowner);
+static void nfs4_free_generic_stateid(struct nfs4_stid *stid);
/* Locking: */
@@ -441,8 +442,15 @@ static void nfs4_file_put_access(struct nfs4_file *fp, u32 access)
__nfs4_file_put_access(fp, oflag);
}
-static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct
-kmem_cache *slab)
+static void nfs4_free_stid(struct kmem_cache *slab, struct nfs4_stid *s)
+{
+ if (s->sc_file)
+ put_nfs4_file(s->sc_file);
+ kmem_cache_free(slab, s);
+}
+
+static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl,
+ struct kmem_cache *slab)
{
struct nfs4_stid *stid;
int new_id;
@@ -481,7 +489,22 @@ out_free:
static struct nfs4_ol_stateid * nfs4_alloc_stateid(struct nfs4_client *clp)
{
- return openlockstateid(nfs4_alloc_stid(clp, stateid_slab));
+ struct nfs4_stid *stid;
+ struct nfs4_ol_stateid *stp;
+
+ stid = nfs4_alloc_stid(clp, stateid_slab);
+ if (!stid)
+ return NULL;
+
+ stp = openlockstateid(stid);
+ stp->st_stid.sc_free = nfs4_free_generic_stateid;
+ return stp;
+}
+
+static void nfs4_free_deleg(struct nfs4_stid *stid)
+{
+ nfs4_free_stid(deleg_slab, stid);
+ num_delegations--;
}
/*
@@ -570,6 +593,8 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
if (dp == NULL)
return dp;
+
+ dp->dl_stid.sc_free = nfs4_free_deleg;
/*
* delegation seqid's are never incremented. The 4.1 special
* meaning of seqid 0 isn't meaningful, really, but let's avoid
@@ -592,30 +617,21 @@ static void remove_stid_locked(struct nfs4_client *clp, struct nfs4_stid *s)
idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id);
}
-static void nfs4_free_stid(struct kmem_cache *slab, struct nfs4_stid *s)
-{
- if (s->sc_file)
- put_nfs4_file(s->sc_file);
- kmem_cache_free(slab, s);
-}
-
-static bool nfs4_put_stid(struct kmem_cache *slab, struct nfs4_stid *s)
+static void nfs4_put_stid(struct nfs4_stid *s)
{
struct nfs4_client *clp = s->sc_client;
if (!atomic_dec_and_lock(&s->sc_count, &clp->cl_lock))
- return false;
+ return;
remove_stid_locked(clp, s);
spin_unlock(&clp->cl_lock);
- nfs4_free_stid(slab, s);
- return true;
+ s->sc_free(s);
}
void
nfs4_put_delegation(struct nfs4_delegation *dp)
{
- if (nfs4_put_stid(deleg_slab, &dp->dl_stid))
- num_delegations--;
+ nfs4_put_stid(&dp->dl_stid);
}
static void nfs4_put_deleg_lease(struct nfs4_file *fp)
@@ -853,14 +869,17 @@ static void unhash_generic_stateid(struct nfs4_ol_stateid *stp)
list_del(&stp->st_perstateowner);
}
-static void close_generic_stateid(struct nfs4_ol_stateid *stp)
+static void nfs4_free_generic_stateid(struct nfs4_stid *stid)
{
+ struct nfs4_ol_stateid *stp = openlockstateid(stid);
+
release_all_access(stp);
+ nfs4_free_stid(stateid_slab, stid);
}
static void put_generic_stateid(struct nfs4_ol_stateid *stp)
{
- nfs4_put_stid(stateid_slab, &stp->st_stid);
+ nfs4_put_stid(&stp->st_stid);
}
static void __release_lock_stateid(struct nfs4_ol_stateid *stp)
@@ -873,7 +892,6 @@ static void __release_lock_stateid(struct nfs4_ol_stateid *stp)
file = find_any_file(stp->st_stid.sc_file);
if (file)
filp_close(file, (fl_owner_t)lockowner(stp->st_stateowner));
- close_generic_stateid(stp);
put_generic_stateid(stp);
}
@@ -931,7 +949,6 @@ static void unhash_open_stateid(struct nfs4_ol_stateid *stp)
{
unhash_generic_stateid(stp);
release_open_stateid_locks(stp);
- close_generic_stateid(stp);
}
static void release_open_stateid(struct nfs4_ol_stateid *stp)
@@ -4427,8 +4444,11 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
oo->oo_last_closed_stid = s;
/*
* In the 4.0 case we need to keep the owners around a
- * little while to handle CLOSE replay.
+ * little while to handle CLOSE replay. We still do need
+ * to release any file access that is held by them
+ * before returning however.
*/
+ release_all_access(s);
if (list_empty(&oo->oo_owner.so_stateids))
move_to_close_lru(oo, clp->net);
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 95d04fae365a..7188dcd45ef7 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -86,6 +86,8 @@ struct nfs4_stid {
stateid_t sc_stateid;
struct nfs4_client *sc_client;
struct nfs4_file *sc_file;
+
+ void (*sc_free)(struct nfs4_stid *);
};
struct nfs4_delegation {
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 042/114] nfsd: do filp_close in sc_free callback for lock stateids
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (40 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 041/114] nfsd: Cleanup the freeing of stateids Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 043/114] nfsd: Add locking to protect the state owner lists Jeff Layton
` (71 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Releasing locks when we unhash the stateid instead of doing so only when
the stateid is actually released is problematic and will complicate some
later changes.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 18 +++++++++++++-----
1 file changed, 13 insertions(+), 5 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ed3df2cdd025..aea256264266 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -877,6 +877,18 @@ static void nfs4_free_generic_stateid(struct nfs4_stid *stid)
nfs4_free_stid(stateid_slab, stid);
}
+static void nfs4_free_lock_stateid(struct nfs4_stid *stid)
+{
+ struct nfs4_ol_stateid *stp = openlockstateid(stid);
+ struct nfs4_lockowner *lo = lockowner(stp->st_stateowner);
+ struct file *file;
+
+ file = find_any_file(stp->st_stid.sc_file);
+ if (file)
+ filp_close(file, (fl_owner_t)lo);
+ nfs4_free_generic_stateid(stid);
+}
+
static void put_generic_stateid(struct nfs4_ol_stateid *stp)
{
nfs4_put_stid(&stp->st_stid);
@@ -884,14 +896,9 @@ static void put_generic_stateid(struct nfs4_ol_stateid *stp)
static void __release_lock_stateid(struct nfs4_ol_stateid *stp)
{
- struct file *file;
-
list_del(&stp->st_locks);
unhash_generic_stateid(stp);
unhash_stid(&stp->st_stid);
- file = find_any_file(stp->st_stid.sc_file);
- if (file)
- filp_close(file, (fl_owner_t)lockowner(stp->st_stateowner));
put_generic_stateid(stp);
}
@@ -4645,6 +4652,7 @@ alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct
stp->st_stateowner = &lo->lo_owner;
get_nfs4_file(fp);
stp->st_stid.sc_file = fp;
+ stp->st_stid.sc_free = nfs4_free_lock_stateid;
stp->st_access_bmap = 0;
stp->st_deny_bmap = open_stp->st_deny_bmap;
stp->st_openstp = open_stp;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 043/114] nfsd: Add locking to protect the state owner lists
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (41 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 042/114] nfsd: do filp_close in sc_free callback for lock stateids Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 044/114] nfsd: clean up races in lock stateid searching and creation Jeff Layton
` (70 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Change to using the clp->cl_lock for this. For now, there's a lot of
cl_lock thrashing, but in later patches we'll eliminate that and close
the potential races that can occur when releasing the cl_lock while
walking the lists. For now, the client_mutex prevents those races.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 21 +++++++++++++++++++--
1 file changed, 19 insertions(+), 2 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index aea256264266..05d0fac2e50a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -863,6 +863,8 @@ static void unhash_generic_stateid(struct nfs4_ol_stateid *stp)
{
struct nfs4_file *fp = stp->st_stid.sc_file;
+ lockdep_assert_held(&stp->st_stateowner->so_client->cl_lock);
+
spin_lock(&fp->fi_lock);
list_del(&stp->st_perfile);
spin_unlock(&fp->fi_lock);
@@ -896,9 +898,13 @@ static void put_generic_stateid(struct nfs4_ol_stateid *stp)
static void __release_lock_stateid(struct nfs4_ol_stateid *stp)
{
+ struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
+
+ spin_lock(&oo->oo_owner.so_client->cl_lock);
list_del(&stp->st_locks);
unhash_generic_stateid(stp);
unhash_stid(&stp->st_stid);
+ spin_unlock(&oo->oo_owner.so_client->cl_lock);
put_generic_stateid(stp);
}
@@ -942,20 +948,26 @@ static void release_lock_stateid(struct nfs4_ol_stateid *stp)
}
static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp)
+ __releases(&open_stp->st_stateowner->so_client->cl_lock)
+ __acquires(&open_stp->st_stateowner->so_client->cl_lock)
{
struct nfs4_ol_stateid *stp;
while (!list_empty(&open_stp->st_locks)) {
stp = list_entry(open_stp->st_locks.next,
struct nfs4_ol_stateid, st_locks);
+ spin_unlock(&open_stp->st_stateowner->so_client->cl_lock);
release_lock_stateid(stp);
+ spin_lock(&open_stp->st_stateowner->so_client->cl_lock);
}
}
static void unhash_open_stateid(struct nfs4_ol_stateid *stp)
{
+ spin_lock(&stp->st_stateowner->so_client->cl_lock);
unhash_generic_stateid(stp);
release_open_stateid_locks(stp);
+ spin_unlock(&stp->st_stateowner->so_client->cl_lock);
}
static void release_open_stateid(struct nfs4_ol_stateid *stp)
@@ -2965,7 +2977,6 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
stp->st_stid.sc_type = NFS4_OPEN_STID;
INIT_LIST_HEAD(&stp->st_locks);
- list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
stp->st_stateowner = &oo->oo_owner;
get_nfs4_file(fp);
stp->st_stid.sc_file = fp;
@@ -2974,9 +2985,12 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
set_access(open->op_share_access, stp);
set_deny(open->op_share_deny, stp);
stp->st_openstp = NULL;
+ spin_lock(&oo->oo_owner.so_client->cl_lock);
+ list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
spin_lock(&fp->fi_lock);
list_add(&stp->st_perfile, &fp->fi_stateids);
spin_unlock(&fp->fi_lock);
+ spin_unlock(&oo->oo_owner.so_client->cl_lock);
}
static void
@@ -4641,6 +4655,7 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, str
static struct nfs4_ol_stateid *
alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct nfs4_ol_stateid *open_stp)
{
+ struct nfs4_openowner *oo = openowner(open_stp->st_stateowner);
struct nfs4_ol_stateid *stp;
struct nfs4_client *clp = lo->lo_owner.so_client;
@@ -4648,7 +4663,6 @@ alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct
if (stp == NULL)
return NULL;
stp->st_stid.sc_type = NFS4_LOCK_STID;
- list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
stp->st_stateowner = &lo->lo_owner;
get_nfs4_file(fp);
stp->st_stid.sc_file = fp;
@@ -4656,10 +4670,13 @@ alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct
stp->st_access_bmap = 0;
stp->st_deny_bmap = open_stp->st_deny_bmap;
stp->st_openstp = open_stp;
+ spin_lock(&oo->oo_owner.so_client->cl_lock);
list_add(&stp->st_locks, &open_stp->st_locks);
+ list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
spin_lock(&fp->fi_lock);
list_add(&stp->st_perfile, &fp->fi_stateids);
spin_unlock(&fp->fi_lock);
+ spin_unlock(&oo->oo_owner.so_client->cl_lock);
return stp;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 044/114] nfsd: clean up races in lock stateid searching and creation
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (42 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 043/114] nfsd: Add locking to protect the state owner lists Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 045/114] nfsd: Convert delegation counter to an atomic_long_t type Jeff Layton
` (69 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Preparation for removal of the client_mutex.
Currently, no lock aside from the client_mutex is held when calling
find_lock_state. Ensure that the cl_lock is held by adding a lockdep
assertion.
Once we remove the client_mutex, it'll be possible for another thread to
race in and insert a lock state for the same file after we search but
before we insert a new one. Ensure that doesn't happen by redoing the
search after allocating a new stid that we plan to insert. If one is
found just put the one we just allocated.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 58 +++++++++++++++++++++++++++++++++++++----------------
1 file changed, 41 insertions(+), 17 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 05d0fac2e50a..60cc162cc8a5 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4652,16 +4652,14 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, str
return lo;
}
-static struct nfs4_ol_stateid *
-alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct nfs4_ol_stateid *open_stp)
+static void
+init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
+ struct nfs4_file *fp, struct nfs4_ol_stateid *open_stp)
{
- struct nfs4_openowner *oo = openowner(open_stp->st_stateowner);
- struct nfs4_ol_stateid *stp;
struct nfs4_client *clp = lo->lo_owner.so_client;
- stp = nfs4_alloc_stateid(clp);
- if (stp == NULL)
- return NULL;
+ lockdep_assert_held(&clp->cl_lock);
+
stp->st_stid.sc_type = NFS4_LOCK_STID;
stp->st_stateowner = &lo->lo_owner;
get_nfs4_file(fp);
@@ -4670,20 +4668,20 @@ alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct
stp->st_access_bmap = 0;
stp->st_deny_bmap = open_stp->st_deny_bmap;
stp->st_openstp = open_stp;
- spin_lock(&oo->oo_owner.so_client->cl_lock);
list_add(&stp->st_locks, &open_stp->st_locks);
list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids);
spin_lock(&fp->fi_lock);
list_add(&stp->st_perfile, &fp->fi_stateids);
spin_unlock(&fp->fi_lock);
- spin_unlock(&oo->oo_owner.so_client->cl_lock);
- return stp;
}
static struct nfs4_ol_stateid *
find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
{
struct nfs4_ol_stateid *lst;
+ struct nfs4_client *clp = lo->lo_owner.so_client;
+
+ lockdep_assert_held(&clp->cl_lock);
list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) {
if (lst->st_stid.sc_file == fp)
@@ -4692,6 +4690,36 @@ find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
return NULL;
}
+static struct nfs4_ol_stateid *
+find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi,
+ struct nfs4_ol_stateid *ost, bool *new)
+{
+ struct nfs4_ol_stateid *lst, *nst = NULL;
+ struct nfs4_openowner *oo = openowner(ost->st_stateowner);
+ struct nfs4_client *clp = oo->oo_owner.so_client;
+
+ spin_lock(&clp->cl_lock);
+ lst = find_lock_stateid(lo, fi);
+ if (lst == NULL) {
+ spin_unlock(&clp->cl_lock);
+ nst = nfs4_alloc_stateid(clp);
+ if (nst == NULL)
+ return NULL;
+
+ spin_lock(&clp->cl_lock);
+ lst = find_lock_stateid(lo, fi);
+ if (likely(!lst)) {
+ init_lock_stateid(nst, lo, fi, ost);
+ lst = nst;
+ nst = NULL;
+ *new = true;
+ }
+ }
+ spin_unlock(&clp->cl_lock);
+ if (nst)
+ put_generic_stateid(nst);
+ return lst;
+}
static int
check_lock_length(u64 offset, u64 length)
@@ -4739,14 +4767,10 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, s
return nfserr_bad_seqid;
}
- *lst = find_lock_stateid(lo, fi);
+ *lst = find_or_create_lock_stateid(lo, fi, ost, new);
if (*lst == NULL) {
- *lst = alloc_init_lock_stateid(lo, fi, ost);
- if (*lst == NULL) {
- release_lockowner_if_empty(lo);
- return nfserr_jukebox;
- }
- *new = true;
+ release_lockowner_if_empty(lo);
+ return nfserr_jukebox;
}
return nfs_ok;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 045/114] nfsd: Convert delegation counter to an atomic_long_t type
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (43 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 044/114] nfsd: clean up races in lock stateid searching and creation Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 046/114] nfsd: Slight cleanup of find_stateid() Jeff Layton
` (68 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
We want to convert to an atomic type so that we don't need to lock
across the call to alloc_init_deleg(). Then convert to a long type so
that we match the size of 'max_delegations'.
None of this is a problem today, but it will be once we remove
client_mutex protection.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 18 +++++++++++-------
1 file changed, 11 insertions(+), 7 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 60cc162cc8a5..f5865a8e3081 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -313,7 +313,7 @@ static struct file *find_any_file(struct nfs4_file *f)
return ret;
}
-static int num_delegations;
+static atomic_long_t num_delegations;
unsigned long max_delegations;
/*
@@ -504,7 +504,7 @@ static struct nfs4_ol_stateid * nfs4_alloc_stateid(struct nfs4_client *clp)
static void nfs4_free_deleg(struct nfs4_stid *stid)
{
nfs4_free_stid(deleg_slab, stid);
- num_delegations--;
+ atomic_long_dec(&num_delegations);
}
/*
@@ -584,15 +584,17 @@ static struct nfs4_delegation *
alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct svc_fh *current_fh)
{
struct nfs4_delegation *dp;
+ long n;
dprintk("NFSD alloc_init_deleg\n");
- if (num_delegations > max_delegations)
- return NULL;
+ n = atomic_long_inc_return(&num_delegations);
+ if (n < 0 || n > max_delegations)
+ goto out_dec;
if (delegation_blocked(¤t_fh->fh_handle))
- return NULL;
+ goto out_dec;
dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab));
if (dp == NULL)
- return dp;
+ goto out_dec;
dp->dl_stid.sc_free = nfs4_free_deleg;
/*
@@ -601,13 +603,15 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
* 0 anyway just for consistency and use 1:
*/
dp->dl_stid.sc_stateid.si_generation = 1;
- num_delegations++;
INIT_LIST_HEAD(&dp->dl_perfile);
INIT_LIST_HEAD(&dp->dl_perclnt);
INIT_LIST_HEAD(&dp->dl_recall_lru);
dp->dl_type = NFS4_OPEN_DELEGATE_READ;
fh_copy_shallow(&dp->dl_fh, ¤t_fh->fh_handle);
return dp;
+out_dec:
+ atomic_long_dec(&num_delegations);
+ return NULL;
}
static void remove_stid_locked(struct nfs4_client *clp, struct nfs4_stid *s)
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 046/114] nfsd: Slight cleanup of find_stateid()
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (44 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 045/114] nfsd: Convert delegation counter to an atomic_long_t type Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 047/114] nfsd: ensure atomicity in nfsd4_free_stateid and nfsd4_validate_stateid Jeff Layton
` (67 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
In preparation of reference counting.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 27 ++++++++++++++++++---------
1 file changed, 18 insertions(+), 9 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f5865a8e3081..54c9631a602c 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1660,28 +1660,37 @@ static void gen_confirm(struct nfs4_client *clp)
memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data));
}
-static struct nfs4_stid *find_stateid(struct nfs4_client *cl, stateid_t *t)
+static struct nfs4_stid *
+find_stateid_locked(struct nfs4_client *cl, stateid_t *t)
{
struct nfs4_stid *ret;
- spin_lock(&cl->cl_lock);
ret = idr_find(&cl->cl_stateids, t->si_opaque.so_id);
- spin_unlock(&cl->cl_lock);
if (!ret || !ret->sc_type)
return NULL;
return ret;
}
+static struct nfs4_stid *find_stateid(struct nfs4_client *cl, stateid_t *t)
+{
+ struct nfs4_stid *ret;
+
+ spin_lock(&cl->cl_lock);
+ ret = find_stateid_locked(cl, t);
+ spin_unlock(&cl->cl_lock);
+ return ret;
+}
+
static struct nfs4_stid *find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask)
{
struct nfs4_stid *s;
- s = find_stateid(cl, t);
- if (!s)
- return NULL;
- if (typemask & s->sc_type)
- return s;
- return NULL;
+ spin_lock(&cl->cl_lock);
+ s = find_stateid_locked(cl, t);
+ if (s != NULL && !(typemask & s->sc_type))
+ s = NULL;
+ spin_unlock(&cl->cl_lock);
+ return s;
}
static struct nfs4_client *create_client(struct xdr_netobj name,
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 047/114] nfsd: ensure atomicity in nfsd4_free_stateid and nfsd4_validate_stateid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (45 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 046/114] nfsd: Slight cleanup of find_stateid() Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 048/114] nfsd: Add reference counting to lock stateids Jeff Layton
` (66 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Hold the cl_lock over the bulk of these functions. In addition to
ensuring that they aren't freed prematurely, this will also help prevent
a potential race that could be introduced later. Once we remove the
client_mutex, it'll be possible for FREE_STATEID and CLOSE to race and
for both to try to put the "persistent" reference to the stateid.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 67 ++++++++++++++++++++++++++++-------------------------
1 file changed, 35 insertions(+), 32 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 54c9631a602c..e56071ef945a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1671,16 +1671,6 @@ find_stateid_locked(struct nfs4_client *cl, stateid_t *t)
return ret;
}
-static struct nfs4_stid *find_stateid(struct nfs4_client *cl, stateid_t *t)
-{
- struct nfs4_stid *ret;
-
- spin_lock(&cl->cl_lock);
- ret = find_stateid_locked(cl, t);
- spin_unlock(&cl->cl_lock);
- return ret;
-}
-
static struct nfs4_stid *find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask)
{
struct nfs4_stid *s;
@@ -4051,10 +4041,10 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
{
struct nfs4_stid *s;
struct nfs4_ol_stateid *ols;
- __be32 status;
+ __be32 status = nfserr_bad_stateid;
if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
- return nfserr_bad_stateid;
+ return status;
/* Client debugging aid. */
if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) {
char addr_str[INET6_ADDRSTRLEN];
@@ -4062,34 +4052,42 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid)
sizeof(addr_str));
pr_warn_ratelimited("NFSD: client %s testing state ID "
"with incorrect client ID\n", addr_str);
- return nfserr_bad_stateid;
+ return status;
}
- s = find_stateid(cl, stateid);
+ spin_lock(&cl->cl_lock);
+ s = find_stateid_locked(cl, stateid);
if (!s)
- return nfserr_bad_stateid;
+ goto out_unlock;
status = check_stateid_generation(stateid, &s->sc_stateid, 1);
if (status)
- return status;
+ goto out_unlock;
switch (s->sc_type) {
case NFS4_DELEG_STID:
- return nfs_ok;
+ status = nfs_ok;
+ break;
case NFS4_REVOKED_DELEG_STID:
- return nfserr_deleg_revoked;
+ status = nfserr_deleg_revoked;
+ break;
case NFS4_OPEN_STID:
case NFS4_LOCK_STID:
ols = openlockstateid(s);
if (ols->st_stateowner->so_is_open_owner
&& !(openowner(ols->st_stateowner)->oo_flags
& NFS4_OO_CONFIRMED))
- return nfserr_bad_stateid;
- return nfs_ok;
+ status = nfserr_bad_stateid;
+ else
+ status = nfs_ok;
+ break;
default:
printk("unknown stateid type %x\n", s->sc_type);
/* Fallthrough */
case NFS4_CLOSED_STID:
case NFS4_CLOSED_DELEG_STID:
- return nfserr_bad_stateid;
+ status = nfserr_bad_stateid;
}
+out_unlock:
+ spin_unlock(&cl->cl_lock);
+ return status;
}
static __be32
@@ -4240,31 +4238,36 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
__be32 ret = nfserr_bad_stateid;
nfs4_lock_state();
- s = find_stateid(cl, stateid);
+ spin_lock(&cl->cl_lock);
+ s = find_stateid_locked(cl, stateid);
if (!s)
- goto out;
+ goto out_unlock;
switch (s->sc_type) {
case NFS4_DELEG_STID:
ret = nfserr_locks_held;
- goto out;
+ break;
case NFS4_OPEN_STID:
case NFS4_LOCK_STID:
ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
if (ret)
- goto out;
- if (s->sc_type == NFS4_LOCK_STID)
- ret = nfsd4_free_lock_stateid(openlockstateid(s));
- else
+ break;
+ if (s->sc_type != NFS4_LOCK_STID) {
ret = nfserr_locks_held;
- break;
+ break;
+ }
+ spin_unlock(&cl->cl_lock);
+ ret = nfsd4_free_lock_stateid(openlockstateid(s));
+ goto out;
case NFS4_REVOKED_DELEG_STID:
+ spin_unlock(&cl->cl_lock);
dp = delegstateid(s);
destroy_revoked_delegation(dp);
ret = nfs_ok;
- break;
- default:
- ret = nfserr_bad_stateid;
+ goto out;
+ /* Default falls through and returns nfserr_bad_stateid */
}
+out_unlock:
+ spin_unlock(&cl->cl_lock);
out:
nfs4_unlock_state();
return ret;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 048/114] nfsd: Add reference counting to lock stateids
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (46 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 047/114] nfsd: ensure atomicity in nfsd4_free_stateid and nfsd4_validate_stateid Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 049/114] nfsd: nfsd4_locku() must reference the lock stateid Jeff Layton
` (65 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Ensure that nfsd4_lock() references the lock stateid while it is
manipulating it. Not currently necessary, but will be once the
client_mutex is removed.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 15 ++++++++++++---
1 file changed, 12 insertions(+), 3 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e56071ef945a..06411edf9a9f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4676,6 +4676,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
lockdep_assert_held(&clp->cl_lock);
+ atomic_inc(&stp->st_stid.sc_count);
stp->st_stid.sc_type = NFS4_LOCK_STID;
stp->st_stateowner = &lo->lo_owner;
get_nfs4_file(fp);
@@ -4700,8 +4701,10 @@ find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp)
lockdep_assert_held(&clp->cl_lock);
list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) {
- if (lst->st_stid.sc_file == fp)
+ if (lst->st_stid.sc_file == fp) {
+ atomic_inc(&lst->st_stid.sc_count);
return lst;
+ }
}
return NULL;
}
@@ -4800,7 +4803,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
{
struct nfs4_openowner *open_sop = NULL;
struct nfs4_lockowner *lock_sop = NULL;
- struct nfs4_ol_stateid *lock_stp;
+ struct nfs4_ol_stateid *lock_stp = NULL;
struct file *filp = NULL;
struct file_lock *file_lock = NULL;
struct file_lock *conflock = NULL;
@@ -4853,11 +4856,15 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out;
status = lookup_or_create_lock_state(cstate, open_stp, lock,
&lock_stp, &new_state);
- } else
+ } else {
status = nfs4_preprocess_seqid_op(cstate,
lock->lk_old_lock_seqid,
&lock->lk_old_lock_stateid,
NFS4_LOCK_STID, &lock_stp, nn);
+ /* FIXME: move into nfs4_preprocess_seqid_op */
+ if (!status)
+ atomic_inc(&lock_stp->st_stid.sc_count);
+ }
if (status)
goto out;
lock_sop = lockowner(lock_stp->st_stateowner);
@@ -4945,6 +4952,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
out:
if (filp)
fput(filp);
+ if (lock_stp)
+ put_generic_stateid(lock_stp);
if (status && new_state)
release_lockowner_if_empty(lock_sop);
nfsd4_bump_seqid(cstate, status);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 049/114] nfsd: nfsd4_locku() must reference the lock stateid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (47 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 048/114] nfsd: Add reference counting to lock stateids Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 050/114] nfsd: Ensure that nfs4_open_delegation() references the delegation stateid Jeff Layton
` (64 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Ensure that nfsd4_locku() keeps a reference to the lock stateid
until it is done working with it. Necessary step toward client_mutex
removal.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 06411edf9a9f..73e94d3e6161 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5084,10 +5084,12 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
&stp, nn);
if (status)
goto out;
+ /* FIXME: move into nfs4_preprocess_seqid_op */
+ atomic_inc(&stp->st_stid.sc_count);
filp = find_any_file(stp->st_stid.sc_file);
if (!filp) {
status = nfserr_lock_range;
- goto out;
+ goto put_stateid;
}
file_lock = locks_alloc_lock();
if (!file_lock) {
@@ -5117,6 +5119,8 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
memcpy(&locku->lu_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
fput:
fput(filp);
+put_stateid:
+ put_generic_stateid(stp);
out:
nfsd4_bump_seqid(cstate, status);
nfs4_unlock_state();
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 050/114] nfsd: Ensure that nfs4_open_delegation() references the delegation stateid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (48 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 049/114] nfsd: nfsd4_locku() must reference the lock stateid Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 051/114] nfsd: nfsd4_process_open2() must reference " Jeff Layton
` (63 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Ensure that nfs4_open_delegation() keeps a reference to the delegation
stateid until it is done working with it. Necessary step toward
client_mutex removal.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 73e94d3e6161..7dfef1647a01 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -663,6 +663,7 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp)
lockdep_assert_held(&state_lock);
lockdep_assert_held(&fp->fi_lock);
+ atomic_inc(&dp->dl_stid.sc_count);
dp->dl_stid.sc_type = NFS4_DELEG_STID;
list_add(&dp->dl_perfile, &fp->fi_delegations);
list_add(&dp->dl_perclnt, &dp->dl_stid.sc_client->cl_delegations);
@@ -3657,6 +3658,7 @@ nfs4_open_delegation(struct net *net, struct svc_fh *fh,
dprintk("NFSD: delegation stateid=" STATEID_FMT "\n",
STATEID_VAL(&dp->dl_stid.sc_stateid));
open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
+ nfs4_put_delegation(dp);
return;
out_free:
unhash_and_destroy_delegation(dp);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 051/114] nfsd: nfsd4_process_open2() must reference the delegation stateid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (49 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 050/114] nfsd: Ensure that nfs4_open_delegation() references the delegation stateid Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 052/114] nfsd: nfsd4_process_open2() must reference the open stateid Jeff Layton
` (62 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Ensure that nfsd4_process_open2() keeps a reference to the delegation
stateid until it is done working with it. Necessary step toward
client_mutex removal.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 18 +++++++++++++-----
1 file changed, 13 insertions(+), 5 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 7dfef1647a01..96ae19a0597d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3297,6 +3297,8 @@ static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, statei
ret = find_stateid_by_type(cl, s, NFS4_DELEG_STID);
if (!ret)
return NULL;
+ /* FIXME: move into find_stateid_by_type */
+ atomic_inc(&ret->sc_count);
return delegstateid(ret);
}
@@ -3312,14 +3314,18 @@ nfs4_check_deleg(struct nfs4_client *cl, struct nfsd4_open *open,
{
int flags;
__be32 status = nfserr_bad_stateid;
+ struct nfs4_delegation *deleg;
- *dp = find_deleg_stateid(cl, &open->op_delegate_stateid);
- if (*dp == NULL)
+ deleg = find_deleg_stateid(cl, &open->op_delegate_stateid);
+ if (deleg == NULL)
goto out;
flags = share_access_to_flags(open->op_share_access);
- status = nfs4_check_delegmode(*dp, flags);
- if (status)
- *dp = NULL;
+ status = nfs4_check_delegmode(deleg, flags);
+ if (status) {
+ nfs4_put_delegation(deleg);
+ goto out;
+ }
+ *dp = deleg;
out:
if (!nfsd4_is_deleg_cur(open))
return nfs_ok;
@@ -3784,6 +3790,8 @@ out:
if (!(open->op_openowner->oo_flags & NFS4_OO_CONFIRMED) &&
!nfsd4_has_session(&resp->cstate))
open->op_rflags |= NFS4_OPEN_RESULT_CONFIRM;
+ if (dp)
+ nfs4_put_delegation(dp);
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 052/114] nfsd: nfsd4_process_open2() must reference the open stateid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (50 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 051/114] nfsd: nfsd4_process_open2() must reference " Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 053/114] nfsd: Prepare nfsd4_close() for open stateid referencing Jeff Layton
` (61 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Ensure that nfsd4_process_open2() keeps a reference to the open
stateid until it is done working with it. Necessary step toward
client_mutex removal.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 96ae19a0597d..9bf706f4b82b 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2979,6 +2979,7 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp, struct nfsd4_open *open) {
struct nfs4_openowner *oo = open->op_openowner;
+ atomic_inc(&stp->st_stid.sc_count);
stp->st_stid.sc_type = NFS4_OPEN_STID;
INIT_LIST_HEAD(&stp->st_locks);
stp->st_stateowner = &oo->oo_owner;
@@ -3349,6 +3350,7 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open)
/* remember if we have seen this open owner */
if (local->st_stateowner == &oo->oo_owner) {
ret = local;
+ atomic_inc(&ret->st_stid.sc_count);
break;
}
}
@@ -3792,6 +3794,8 @@ out:
open->op_rflags |= NFS4_OPEN_RESULT_CONFIRM;
if (dp)
nfs4_put_delegation(dp);
+ if (stp)
+ put_generic_stateid(stp);
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 053/114] nfsd: Prepare nfsd4_close() for open stateid referencing
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (51 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 052/114] nfsd: nfsd4_process_open2() must reference the open stateid Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 054/114] nfsd: nfsd4_open_confirm() must reference the open stateid Jeff Layton
` (60 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Prepare nfsd4_close for a future where nfs4_preprocess_seqid_op()
hands it a fully referenced open stateid. Necessary step toward
client_mutex removal.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9bf706f4b82b..08e3ab9c82f0 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4528,10 +4528,15 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfsd4_bump_seqid(cstate, status);
if (status)
goto out;
+ /* FIXME: move into nfs4_preprocess_seqid_op */
+ atomic_inc(&stp->st_stid.sc_count);
update_stateid(&stp->st_stid.sc_stateid);
memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
nfsd4_close_open_stateid(stp);
+
+ /* put reference from nfs4_preprocess_seqid_op */
+ put_generic_stateid(stp);
out:
nfs4_unlock_state();
return status;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 054/114] nfsd: nfsd4_open_confirm() must reference the open stateid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (52 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 053/114] nfsd: Prepare nfsd4_close() for open stateid referencing Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 055/114] nfsd: Add reference counting to nfs4_preprocess_confirmed_seqid_op Jeff Layton
` (59 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Ensure that nfsd4_open_confirm() keeps a reference to the open
stateid until it is done working with it.
Necessary step toward client_mutex removal.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 08e3ab9c82f0..8ed48d0015e1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4385,10 +4385,12 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
NFS4_OPEN_STID, &stp, nn);
if (status)
goto out;
+ /* FIXME: move into nfs4_preprocess_seqid_op */
+ atomic_inc(&stp->st_stid.sc_count);
oo = openowner(stp->st_stateowner);
status = nfserr_bad_stateid;
if (oo->oo_flags & NFS4_OO_CONFIRMED)
- goto out;
+ goto put_stateid;
oo->oo_flags |= NFS4_OO_CONFIRMED;
update_stateid(&stp->st_stid.sc_stateid);
memcpy(&oc->oc_resp_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
@@ -4397,6 +4399,8 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfsd4_client_record_create(oo->oo_owner.so_client);
status = nfs_ok;
+put_stateid:
+ put_generic_stateid(stp);
out:
nfsd4_bump_seqid(cstate, status);
nfs4_unlock_state();
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 055/114] nfsd: Add reference counting to nfs4_preprocess_confirmed_seqid_op
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (53 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 054/114] nfsd: nfsd4_open_confirm() must reference the open stateid Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 056/114] nfsd: Migrate the stateid reference into nfs4_preprocess_seqid_op Jeff Layton
` (58 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Ensure that all the callers put the open stateid after use.
Necessary step toward client_mutex removal.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 8ed48d0015e1..f2df0778448e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4356,6 +4356,8 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs
NFS4_OPEN_STID, stpp, nn);
if (status)
return status;
+ /* FIXME: move into nfs4_preprocess_seqid_op */
+ atomic_inc(&(*stpp)->st_stid.sc_count);
oo = openowner((*stpp)->st_stateowner);
if (!(oo->oo_flags & NFS4_OO_CONFIRMED))
return nfserr_bad_stateid;
@@ -4459,12 +4461,12 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
if (!test_access(od->od_share_access, stp)) {
dprintk("NFSD: access not a subset of current bitmap: 0x%hhx, input access=%08x\n",
stp->st_access_bmap, od->od_share_access);
- goto out;
+ goto put_stateid;
}
if (!test_deny(od->od_share_deny, stp)) {
dprintk("NFSD: deny not a subset of current bitmap: 0x%hhx, input deny=%08x\n",
stp->st_deny_bmap, od->od_share_deny);
- goto out;
+ goto put_stateid;
}
nfs4_stateid_downgrade(stp, od->od_share_access);
@@ -4473,6 +4475,8 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
update_stateid(&stp->st_stid.sc_stateid);
memcpy(&od->od_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
status = nfs_ok;
+put_stateid:
+ put_generic_stateid(stp);
out:
nfsd4_bump_seqid(cstate, status);
nfs4_unlock_state();
@@ -4827,6 +4831,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfs4_openowner *open_sop = NULL;
struct nfs4_lockowner *lock_sop = NULL;
struct nfs4_ol_stateid *lock_stp = NULL;
+ struct nfs4_ol_stateid *open_stp = NULL;
struct file *filp = NULL;
struct file_lock *file_lock = NULL;
struct file_lock *conflock = NULL;
@@ -4853,8 +4858,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfs4_lock_state();
if (lock->lk_is_new) {
- struct nfs4_ol_stateid *open_stp = NULL;
-
if (nfsd4_has_session(cstate))
/* See rfc 5661 18.10.3: given clientid is ignored: */
memcpy(&lock->v.new.clientid,
@@ -4977,6 +4980,8 @@ out:
fput(filp);
if (lock_stp)
put_generic_stateid(lock_stp);
+ if (open_stp)
+ put_generic_stateid(open_stp);
if (status && new_state)
release_lockowner_if_empty(lock_sop);
nfsd4_bump_seqid(cstate, status);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 056/114] nfsd: Migrate the stateid reference into nfs4_preprocess_seqid_op
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (54 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 055/114] nfsd: Add reference counting to nfs4_preprocess_confirmed_seqid_op Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 057/114] nfsd: Migrate the stateid reference into nfs4_lookup_stateid() Jeff Layton
` (57 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Allow nfs4_preprocess_seqid_op to take the stateid reference, instead
of having all the callers do so.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 26 +++++++++++---------------
1 file changed, 11 insertions(+), 15 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f2df0778448e..2b7ce084eb04 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4341,8 +4341,11 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
nfsd4_cstate_assign_replay(cstate, stp->st_stateowner);
status = nfs4_seqid_op_checks(cstate, stateid, seqid, stp);
- if (!status)
+ if (!status) {
+ /* FIXME: move into find_stateid_by_type */
+ atomic_inc(&stp->st_stid.sc_count);
*stpp = stp;
+ }
return status;
}
@@ -4351,16 +4354,18 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs
{
__be32 status;
struct nfs4_openowner *oo;
+ struct nfs4_ol_stateid *stp;
status = nfs4_preprocess_seqid_op(cstate, seqid, stateid,
- NFS4_OPEN_STID, stpp, nn);
+ NFS4_OPEN_STID, &stp, nn);
if (status)
return status;
- /* FIXME: move into nfs4_preprocess_seqid_op */
- atomic_inc(&(*stpp)->st_stid.sc_count);
- oo = openowner((*stpp)->st_stateowner);
- if (!(oo->oo_flags & NFS4_OO_CONFIRMED))
+ oo = openowner(stp->st_stateowner);
+ if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) {
+ put_generic_stateid(stp);
return nfserr_bad_stateid;
+ }
+ *stpp = stp;
return nfs_ok;
}
@@ -4387,8 +4392,6 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
NFS4_OPEN_STID, &stp, nn);
if (status)
goto out;
- /* FIXME: move into nfs4_preprocess_seqid_op */
- atomic_inc(&stp->st_stid.sc_count);
oo = openowner(stp->st_stateowner);
status = nfserr_bad_stateid;
if (oo->oo_flags & NFS4_OO_CONFIRMED)
@@ -4536,8 +4539,6 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfsd4_bump_seqid(cstate, status);
if (status)
goto out;
- /* FIXME: move into nfs4_preprocess_seqid_op */
- atomic_inc(&stp->st_stid.sc_count);
update_stateid(&stp->st_stid.sc_stateid);
memcpy(&close->cl_stateid, &stp->st_stid.sc_stateid, sizeof(stateid_t));
@@ -4887,9 +4888,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
lock->lk_old_lock_seqid,
&lock->lk_old_lock_stateid,
NFS4_LOCK_STID, &lock_stp, nn);
- /* FIXME: move into nfs4_preprocess_seqid_op */
- if (!status)
- atomic_inc(&lock_stp->st_stid.sc_count);
}
if (status)
goto out;
@@ -5112,8 +5110,6 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
&stp, nn);
if (status)
goto out;
- /* FIXME: move into nfs4_preprocess_seqid_op */
- atomic_inc(&stp->st_stid.sc_count);
filp = find_any_file(stp->st_stid.sc_file);
if (!filp) {
status = nfserr_lock_range;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 057/114] nfsd: Migrate the stateid reference into nfs4_lookup_stateid()
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (55 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 056/114] nfsd: Migrate the stateid reference into nfs4_preprocess_seqid_op Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 058/114] nfsd: Migrate the stateid reference into nfs4_find_stateid_by_type() Jeff Layton
` (56 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Allow nfs4_lookup_stateid to take the stateid reference, instead
of having all the callers do so.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 17 +++++++++++------
1 file changed, 11 insertions(+), 6 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2b7ce084eb04..9d9cb26c391c 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4124,6 +4124,8 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
*s = find_stateid_by_type(cstate->clp, stateid, typemask);
if (!*s)
return nfserr_bad_stateid;
+ /* FIXME: move into find_stateid_by_type */
+ atomic_inc(&(*s)->sc_count);
return nfs_ok;
}
@@ -4158,7 +4160,7 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
&s, nn);
if (status)
- goto out;
+ goto unlock_state;
status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate));
if (status)
goto out;
@@ -4207,6 +4209,8 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
if (file)
*filpp = file;
out:
+ nfs4_put_stid(s);
+unlock_state:
nfs4_unlock_state();
return status;
}
@@ -4341,11 +4345,10 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid,
nfsd4_cstate_assign_replay(cstate, stp->st_stateowner);
status = nfs4_seqid_op_checks(cstate, stateid, seqid, stp);
- if (!status) {
- /* FIXME: move into find_stateid_by_type */
- atomic_inc(&stp->st_stid.sc_count);
+ if (!status)
*stpp = stp;
- }
+ else
+ put_generic_stateid(stp);
return status;
}
@@ -4571,9 +4574,11 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
dp = delegstateid(s);
status = check_stateid_generation(stateid, &dp->dl_stid.sc_stateid, nfsd4_has_session(cstate));
if (status)
- goto out;
+ goto put_stateid;
unhash_and_destroy_delegation(dp);
+put_stateid:
+ nfs4_put_delegation(dp);
out:
nfs4_unlock_state();
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 058/114] nfsd: Migrate the stateid reference into nfs4_find_stateid_by_type()
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (56 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 057/114] nfsd: Migrate the stateid reference into nfs4_lookup_stateid() Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 059/114] nfsd: Add reference counting to state owners Jeff Layton
` (55 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Allow nfs4_find_stateid_by_type to take the stateid reference, while
still holding the &cl->cl_lock. Necessary step toward client_mutex
removal.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9d9cb26c391c..0f30716c9093 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1678,8 +1678,12 @@ static struct nfs4_stid *find_stateid_by_type(struct nfs4_client *cl, stateid_t
spin_lock(&cl->cl_lock);
s = find_stateid_locked(cl, t);
- if (s != NULL && !(typemask & s->sc_type))
- s = NULL;
+ if (s != NULL) {
+ if (typemask & s->sc_type)
+ atomic_inc(&s->sc_count);
+ else
+ s = NULL;
+ }
spin_unlock(&cl->cl_lock);
return s;
}
@@ -3298,8 +3302,6 @@ static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, statei
ret = find_stateid_by_type(cl, s, NFS4_DELEG_STID);
if (!ret)
return NULL;
- /* FIXME: move into find_stateid_by_type */
- atomic_inc(&ret->sc_count);
return delegstateid(ret);
}
@@ -4124,8 +4126,6 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate,
*s = find_stateid_by_type(cstate->clp, stateid, typemask);
if (!*s)
return nfserr_bad_stateid;
- /* FIXME: move into find_stateid_by_type */
- atomic_inc(&(*s)->sc_count);
return nfs_ok;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 059/114] nfsd: Add reference counting to state owners
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (57 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 058/114] nfsd: Migrate the stateid reference into nfs4_find_stateid_by_type() Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 060/114] nfsd: Keep a reference to the open stateid for the NFSv4.0 replay cache Jeff Layton
` (54 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
The way stateowners are managed today is somewhat awkward. They need to
be explicitly destroyed, even though the stateids reference them. This
will be particularly problematic when we remove the client_mutex.
We may create a new stateowner and attempt to open a file or set a lock,
and have that fail. In the meantime, another RPC may come in that uses
that same stateowner and succeed. We can't have the first task tearing
down the stateowner in that situation.
To fix this, we need to change how stateowners are tracked altogether.
Refcount them and only destroy them once all stateids that reference
them have been destroyed. This patch starts by adding the refcounting
necessary to do that.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 43 +++++++++++++++++++++++++++++--------------
fs/nfsd/state.h | 3 +++
2 files changed, 32 insertions(+), 14 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 0f30716c9093..d260bb3145ed 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -72,6 +72,7 @@ static u64 current_sessionid = 1;
/* forward declarations */
static int check_for_locks(struct nfs4_file *filp, struct nfs4_lockowner *lowner);
static void nfs4_free_generic_stateid(struct nfs4_stid *stid);
+static void nfs4_put_stateowner(struct nfs4_stateowner *sop);
/* Locking: */
@@ -925,16 +926,10 @@ static void unhash_lockowner(struct nfs4_lockowner *lo)
}
}
-static void nfs4_free_lockowner(struct nfs4_lockowner *lo)
-{
- kfree(lo->lo_owner.so_owner.data);
- kmem_cache_free(lockowner_slab, lo);
-}
-
static void release_lockowner(struct nfs4_lockowner *lo)
{
unhash_lockowner(lo);
- nfs4_free_lockowner(lo);
+ nfs4_put_stateowner(&lo->lo_owner);
}
static void release_lockowner_if_empty(struct nfs4_lockowner *lo)
@@ -1004,18 +999,12 @@ static void release_last_closed_stateid(struct nfs4_openowner *oo)
}
}
-static void nfs4_free_openowner(struct nfs4_openowner *oo)
-{
- kfree(oo->oo_owner.so_owner.data);
- kmem_cache_free(openowner_slab, oo);
-}
-
static void release_openowner(struct nfs4_openowner *oo)
{
unhash_openowner(oo);
list_del(&oo->oo_close_lru);
release_last_closed_stateid(oo);
- nfs4_free_openowner(oo);
+ nfs4_put_stateowner(&oo->oo_owner);
}
static inline int
@@ -2947,9 +2936,17 @@ static inline void *alloc_stateowner(struct kmem_cache *slab, struct xdr_netobj
INIT_LIST_HEAD(&sop->so_stateids);
sop->so_client = clp;
init_nfs4_replay(&sop->so_replay);
+ atomic_set(&sop->so_count, 1);
return sop;
}
+static void nfs4_put_stateowner(struct nfs4_stateowner *sop)
+{
+ if (!atomic_dec_and_test(&sop->so_count))
+ return;
+ sop->so_free(sop);
+}
+
static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, unsigned int strhashval)
{
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
@@ -2958,6 +2955,14 @@ static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, u
list_add(&oo->oo_perclient, &clp->cl_openowners);
}
+static void nfs4_free_openowner(struct nfs4_stateowner *so)
+{
+ struct nfs4_openowner *oo = openowner(so);
+
+ kfree(oo->oo_owner.so_owner.data);
+ kmem_cache_free(openowner_slab, oo);
+}
+
static struct nfs4_openowner *
alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
struct nfsd4_compound_state *cstate)
@@ -2968,6 +2973,7 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
oo = alloc_stateowner(openowner_slab, &open->op_owner, clp);
if (!oo)
return NULL;
+ oo->oo_owner.so_free = nfs4_free_openowner;
oo->oo_owner.so_is_open_owner = 1;
oo->oo_owner.so_seqid = open->op_seqid;
oo->oo_flags = NFS4_OO_NEW;
@@ -4677,6 +4683,14 @@ find_lockowner_str(clientid_t *clid, struct xdr_netobj *owner,
return NULL;
}
+static void nfs4_free_lockowner(struct nfs4_stateowner *sop)
+{
+ struct nfs4_lockowner *lo = lockowner(sop);
+
+ kfree(lo->lo_owner.so_owner.data);
+ kmem_cache_free(lockowner_slab, lo);
+}
+
/*
* Alloc a lock owner structure.
* Called in nfsd4_lock - therefore, OPEN and OPEN_CONFIRM (if needed) has
@@ -4697,6 +4711,7 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, str
/* It is the openowner seqid that will be incremented in encode in the
* case of new lockowners; so increment the lock seqid manually: */
lo->lo_owner.so_seqid = lock->lk_new_lock_seqid + 1;
+ lo->lo_owner.so_free = nfs4_free_lockowner;
list_add(&lo->lo_owner.so_strhash, &nn->ownerstr_hashtbl[strhashval]);
return lo;
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 7188dcd45ef7..eba7283a2613 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -340,10 +340,13 @@ struct nfs4_stateowner {
struct nfs4_client * so_client;
/* after increment in ENCODE_SEQID_OP_TAIL, represents the next
* sequence id expected from the client: */
+ atomic_t so_count;
u32 so_seqid;
struct xdr_netobj so_owner; /* open owner name */
struct nfs4_replay so_replay;
bool so_is_open_owner;
+
+ void (*so_free)(struct nfs4_stateowner *);
};
struct nfs4_openowner {
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 060/114] nfsd: Keep a reference to the open stateid for the NFSv4.0 replay cache
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (58 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 059/114] nfsd: Add reference counting to state owners Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 061/114] nfsd: clean up lockowner refcounting when finding them Jeff Layton
` (53 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Ensure that nfsd4_cstate_assign_replay/nfsd4_cstate_clear_replay take
a reference to the stateowner when they are using it for NFSv4.0
open and lock replay caching.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4proc.c | 5 +----
fs/nfsd/nfs4state.c | 26 +++++++++++++++++++++++++-
fs/nfsd/xdr4.h | 26 ++++----------------------
3 files changed, 30 insertions(+), 27 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index fc48d1d51f1d..cdce2f39b09c 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -467,10 +467,7 @@ out:
fh_put(resfh);
kfree(resfh);
}
- nfsd4_cleanup_open_state(open, status);
- if (open->op_openowner)
- nfsd4_cstate_assign_replay(cstate,
- &open->op_openowner->oo_owner);
+ nfsd4_cleanup_open_state(cstate, open, status);
nfsd4_bump_seqid(cstate, status);
nfs4_unlock_state();
return status;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d260bb3145ed..98cbe9b7c01e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2918,6 +2918,27 @@ static void init_nfs4_replay(struct nfs4_replay *rp)
mutex_init(&rp->rp_mutex);
}
+static void nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate,
+ struct nfs4_stateowner *so)
+{
+ if (!nfsd4_has_session(cstate)) {
+ mutex_lock(&so->so_replay.rp_mutex);
+ cstate->replay_owner = so;
+ atomic_inc(&so->so_count);
+ }
+}
+
+void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate)
+{
+ struct nfs4_stateowner *so = cstate->replay_owner;
+
+ if (so != NULL) {
+ cstate->replay_owner = NULL;
+ mutex_unlock(&so->so_replay.rp_mutex);
+ nfs4_put_stateowner(so);
+ }
+}
+
static inline void *alloc_stateowner(struct kmem_cache *slab, struct xdr_netobj *owner, struct nfs4_client *clp)
{
struct nfs4_stateowner *sop;
@@ -3808,7 +3829,8 @@ out:
return status;
}
-void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status)
+void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate,
+ struct nfsd4_open *open, __be32 status)
{
if (open->op_openowner) {
struct nfs4_openowner *oo = open->op_openowner;
@@ -3822,6 +3844,8 @@ void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status)
} else
oo->oo_flags &= ~NFS4_OO_NEW;
}
+ if (open->op_openowner)
+ nfsd4_cstate_assign_replay(cstate, &oo->oo_owner);
}
if (open->op_file)
nfsd4_free_file(open->op_file);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index ec9674a009bd..634e016f50d3 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -74,27 +74,6 @@ static inline bool nfsd4_has_session(struct nfsd4_compound_state *cs)
return cs->slot != NULL;
}
-static inline void
-nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate,
- struct nfs4_stateowner *so)
-{
- if (!nfsd4_has_session(cstate)) {
- mutex_lock(&so->so_replay.rp_mutex);
- cstate->replay_owner = so;
- }
-}
-
-static inline void
-nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate)
-{
- struct nfs4_stateowner *so = cstate->replay_owner;
-
- if (so != NULL) {
- cstate->replay_owner = NULL;
- mutex_unlock(&so->so_replay.rp_mutex);
- }
-}
-
struct nfsd4_change_info {
u32 atomic;
bool change_supported;
@@ -616,7 +595,9 @@ extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *,
struct nfsd4_open *open, struct nfsd_net *nn);
extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp,
struct svc_fh *current_fh, struct nfsd4_open *open);
-extern void nfsd4_cleanup_open_state(struct nfsd4_open *open, __be32 status);
+extern void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate);
+extern void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate,
+ struct nfsd4_open *open, __be32 status);
extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp,
struct nfsd4_compound_state *, struct nfsd4_open_confirm *oc);
extern __be32 nfsd4_close(struct svc_rqst *rqstp,
@@ -647,6 +628,7 @@ extern __be32 nfsd4_test_stateid(struct svc_rqst *rqstp,
extern __be32 nfsd4_free_stateid(struct svc_rqst *rqstp,
struct nfsd4_compound_state *, struct nfsd4_free_stateid *free_stateid);
extern void nfsd4_bump_seqid(struct nfsd4_compound_state *, __be32 nfserr);
+
#endif
/*
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 061/114] nfsd: clean up lockowner refcounting when finding them
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (59 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 060/114] nfsd: Keep a reference to the open stateid for the NFSv4.0 replay cache Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 062/114] nfsd: add an operation for unhashing a stateowner Jeff Layton
` (52 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Ensure that when finding or creating a lockowner, that we get a
reference to it. For now, we also take an extra reference when a
lockowner is created that can be put when release_lockowner is called,
but we'll remove that in a later patch once we change how references are
held.
Since we no longer destroy lockowners in the event of an error in
nfsd4_lock, we must change how the seqid gets bumped in the lk_is_new
case. Instead of doing so on creation, do it manually in nfsd4_lock.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 51 ++++++++++++++++++++++++++++++++++++++-------------
1 file changed, 38 insertions(+), 13 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 98cbe9b7c01e..395232b7efef 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4702,6 +4702,7 @@ find_lockowner_str(clientid_t *clid, struct xdr_netobj *owner,
continue;
if (!same_owner_str(so, owner, clid))
continue;
+ atomic_inc(&so->so_count);
return lockowner(so);
}
return NULL;
@@ -4732,9 +4733,7 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, str
return NULL;
INIT_LIST_HEAD(&lo->lo_owner.so_stateids);
lo->lo_owner.so_is_open_owner = 0;
- /* It is the openowner seqid that will be incremented in encode in the
- * case of new lockowners; so increment the lock seqid manually: */
- lo->lo_owner.so_seqid = lock->lk_new_lock_seqid + 1;
+ lo->lo_owner.so_seqid = lock->lk_new_lock_seqid;
lo->lo_owner.so_free = nfs4_free_lockowner;
list_add(&lo->lo_owner.so_strhash, &nn->ownerstr_hashtbl[strhashval]);
return lo;
@@ -4835,8 +4834,13 @@ static void get_lock_access(struct nfs4_ol_stateid *lock_stp, u32 access)
set_access(access, lock_stp);
}
-static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *ost, struct nfsd4_lock *lock, struct nfs4_ol_stateid **lst, bool *new)
+static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
+ struct nfs4_ol_stateid *ost,
+ struct nfsd4_lock *lock,
+ struct nfs4_ol_stateid **lst,
+ bool *new)
{
+ __be32 status;
struct nfs4_file *fi = ost->st_stid.sc_file;
struct nfs4_openowner *oo = openowner(ost->st_stateowner);
struct nfs4_client *cl = oo->oo_owner.so_client;
@@ -4851,19 +4855,26 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate, s
lo = alloc_init_lock_stateowner(strhashval, cl, ost, lock);
if (lo == NULL)
return nfserr_jukebox;
+ /* FIXME: extra reference for new lockowners for the client */
+ atomic_inc(&lo->lo_owner.so_count);
} else {
/* with an existing lockowner, seqids must be the same */
+ status = nfserr_bad_seqid;
if (!cstate->minorversion &&
lock->lk_new_lock_seqid != lo->lo_owner.so_seqid)
- return nfserr_bad_seqid;
+ goto out;
}
*lst = find_or_create_lock_stateid(lo, fi, ost, new);
if (*lst == NULL) {
release_lockowner_if_empty(lo);
- return nfserr_jukebox;
+ status = nfserr_jukebox;
+ goto out;
}
- return nfs_ok;
+ status = nfs_ok;
+out:
+ nfs4_put_stateowner(&lo->lo_owner);
+ return status;
}
/*
@@ -4881,9 +4892,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct file_lock *file_lock = NULL;
struct file_lock *conflock = NULL;
__be32 status = 0;
- bool new_state = false;
int lkflg;
int err;
+ bool new = false;
struct net *net = SVC_NET(rqstp);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
@@ -4926,7 +4937,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
&lock->v.new.clientid))
goto out;
status = lookup_or_create_lock_state(cstate, open_stp, lock,
- &lock_stp, &new_state);
+ &lock_stp, &new);
} else {
status = nfs4_preprocess_seqid_op(cstate,
lock->lk_old_lock_seqid,
@@ -5020,12 +5031,24 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
out:
if (filp)
fput(filp);
- if (lock_stp)
+ if (lock_stp) {
+ /* Bump seqid manually if the 4.0 replay owner is openowner */
+ if (cstate->replay_owner &&
+ cstate->replay_owner != &lock_sop->lo_owner &&
+ seqid_mutating_err(ntohl(status)))
+ lock_sop->lo_owner.so_seqid++;
+
+ /*
+ * If this is a new, never-before-used stateid, and we are
+ * returning an error, then just go ahead and release it.
+ */
+ if (status && new)
+ release_lock_stateid(lock_stp);
+
put_generic_stateid(lock_stp);
+ }
if (open_stp)
put_generic_stateid(open_stp);
- if (status && new_state)
- release_lockowner_if_empty(lock_sop);
nfsd4_bump_seqid(cstate, status);
nfs4_unlock_state();
if (file_lock)
@@ -5060,7 +5083,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_lockt *lockt)
{
struct file_lock *file_lock = NULL;
- struct nfs4_lockowner *lo;
+ struct nfs4_lockowner *lo = NULL;
__be32 status;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
@@ -5123,6 +5146,8 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
nfs4_set_lock_denied(file_lock, &lockt->lt_denied);
}
out:
+ if (lo)
+ nfs4_put_stateowner(&lo->lo_owner);
nfs4_unlock_state();
if (file_lock)
locks_free_lock(file_lock);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 062/114] nfsd: add an operation for unhashing a stateowner
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (60 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 061/114] nfsd: clean up lockowner refcounting when finding them Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 063/114] nfsd: Make lock stateid take a reference to the lockowner Jeff Layton
` (51 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Allow stateowners to be unhashed and destroyed when the last reference
is put. The unhashing must be idempotent. In a future patch, we'll add
some locking around it, but for now it's only protected by the
client_mutex.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 45 +++++++++++++++++++++++++++++++++++----------
fs/nfsd/state.h | 1 +
2 files changed, 36 insertions(+), 10 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 395232b7efef..effce92b54de 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -916,9 +916,13 @@ static void __release_lock_stateid(struct nfs4_ol_stateid *stp)
static void unhash_lockowner(struct nfs4_lockowner *lo)
{
+ list_del_init(&lo->lo_owner.so_strhash);
+}
+
+static void release_lockowner_stateids(struct nfs4_lockowner *lo)
+{
struct nfs4_ol_stateid *stp;
- list_del(&lo->lo_owner.so_strhash);
while (!list_empty(&lo->lo_owner.so_stateids)) {
stp = list_first_entry(&lo->lo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
@@ -929,6 +933,7 @@ static void unhash_lockowner(struct nfs4_lockowner *lo)
static void release_lockowner(struct nfs4_lockowner *lo)
{
unhash_lockowner(lo);
+ release_lockowner_stateids(lo);
nfs4_put_stateowner(&lo->lo_owner);
}
@@ -978,15 +983,8 @@ static void release_open_stateid(struct nfs4_ol_stateid *stp)
static void unhash_openowner(struct nfs4_openowner *oo)
{
- struct nfs4_ol_stateid *stp;
-
- list_del(&oo->oo_owner.so_strhash);
- list_del(&oo->oo_perclient);
- while (!list_empty(&oo->oo_owner.so_stateids)) {
- stp = list_first_entry(&oo->oo_owner.so_stateids,
- struct nfs4_ol_stateid, st_perstateowner);
- release_open_stateid(stp);
- }
+ list_del_init(&oo->oo_owner.so_strhash);
+ list_del_init(&oo->oo_perclient);
}
static void release_last_closed_stateid(struct nfs4_openowner *oo)
@@ -999,9 +997,21 @@ static void release_last_closed_stateid(struct nfs4_openowner *oo)
}
}
+static void release_openowner_stateids(struct nfs4_openowner *oo)
+{
+ struct nfs4_ol_stateid *stp;
+
+ while (!list_empty(&oo->oo_owner.so_stateids)) {
+ stp = list_first_entry(&oo->oo_owner.so_stateids,
+ struct nfs4_ol_stateid, st_perstateowner);
+ release_open_stateid(stp);
+ }
+}
+
static void release_openowner(struct nfs4_openowner *oo)
{
unhash_openowner(oo);
+ release_openowner_stateids(oo);
list_del(&oo->oo_close_lru);
release_last_closed_stateid(oo);
nfs4_put_stateowner(&oo->oo_owner);
@@ -2965,6 +2975,7 @@ static void nfs4_put_stateowner(struct nfs4_stateowner *sop)
{
if (!atomic_dec_and_test(&sop->so_count))
return;
+ sop->so_unhash(sop);
sop->so_free(sop);
}
@@ -2976,6 +2987,13 @@ static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, u
list_add(&oo->oo_perclient, &clp->cl_openowners);
}
+static void nfs4_unhash_openowner(struct nfs4_stateowner *so)
+{
+ struct nfs4_openowner *oo = openowner(so);
+
+ unhash_openowner(oo);
+}
+
static void nfs4_free_openowner(struct nfs4_stateowner *so)
{
struct nfs4_openowner *oo = openowner(so);
@@ -2995,6 +3013,7 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
if (!oo)
return NULL;
oo->oo_owner.so_free = nfs4_free_openowner;
+ oo->oo_owner.so_unhash = nfs4_unhash_openowner;
oo->oo_owner.so_is_open_owner = 1;
oo->oo_owner.so_seqid = open->op_seqid;
oo->oo_flags = NFS4_OO_NEW;
@@ -4708,6 +4727,11 @@ find_lockowner_str(clientid_t *clid, struct xdr_netobj *owner,
return NULL;
}
+static void nfs4_unhash_lockowner(struct nfs4_stateowner *sop)
+{
+ unhash_lockowner(lockowner(sop));
+}
+
static void nfs4_free_lockowner(struct nfs4_stateowner *sop)
{
struct nfs4_lockowner *lo = lockowner(sop);
@@ -4735,6 +4759,7 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, str
lo->lo_owner.so_is_open_owner = 0;
lo->lo_owner.so_seqid = lock->lk_new_lock_seqid;
lo->lo_owner.so_free = nfs4_free_lockowner;
+ lo->lo_owner.so_unhash = nfs4_unhash_lockowner;
list_add(&lo->lo_owner.so_strhash, &nn->ownerstr_hashtbl[strhashval]);
return lo;
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index eba7283a2613..f6639fb5a56f 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -347,6 +347,7 @@ struct nfs4_stateowner {
bool so_is_open_owner;
void (*so_free)(struct nfs4_stateowner *);
+ void (*so_unhash)(struct nfs4_stateowner *);
};
struct nfs4_openowner {
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 063/114] nfsd: Make lock stateid take a reference to the lockowner
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (61 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 062/114] nfsd: add an operation for unhashing a stateowner Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 064/114] nfsd: clean up refcounting for lockowners Jeff Layton
` (50 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
A necessary step toward client_mutex removal.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index effce92b54de..9a760aac6ef2 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -882,6 +882,8 @@ static void nfs4_free_generic_stateid(struct nfs4_stid *stid)
struct nfs4_ol_stateid *stp = openlockstateid(stid);
release_all_access(stp);
+ if (stp->st_stateowner && stid->sc_type == NFS4_LOCK_STID)
+ nfs4_put_stateowner(stp->st_stateowner);
nfs4_free_stid(stateid_slab, stid);
}
@@ -4775,6 +4777,7 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo,
atomic_inc(&stp->st_stid.sc_count);
stp->st_stid.sc_type = NFS4_LOCK_STID;
stp->st_stateowner = &lo->lo_owner;
+ atomic_inc(&lo->lo_owner.so_count);
get_nfs4_file(fp);
stp->st_stid.sc_file = fp;
stp->st_stid.sc_free = nfs4_free_lock_stateid;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 064/114] nfsd: clean up refcounting for lockowners
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (62 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 063/114] nfsd: Make lock stateid take a reference to the lockowner Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 065/114] nfsd: make openstateids hold references to their openowners Jeff Layton
` (49 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Ensure that lockowner references are only held by lockstateids and
operations that are in-progress. With this, we can get rid of
release_lockowner_if_empty, which will be racy once we remove
client_mutex protection.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 29 +++++++----------------------
1 file changed, 7 insertions(+), 22 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9a760aac6ef2..b658fd481c4e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -904,7 +904,7 @@ static void put_generic_stateid(struct nfs4_ol_stateid *stp)
nfs4_put_stid(&stp->st_stid);
}
-static void __release_lock_stateid(struct nfs4_ol_stateid *stp)
+static void release_lock_stateid(struct nfs4_ol_stateid *stp)
{
struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
@@ -928,7 +928,7 @@ static void release_lockowner_stateids(struct nfs4_lockowner *lo)
while (!list_empty(&lo->lo_owner.so_stateids)) {
stp = list_first_entry(&lo->lo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
- __release_lock_stateid(stp);
+ release_lock_stateid(stp);
}
}
@@ -939,21 +939,6 @@ static void release_lockowner(struct nfs4_lockowner *lo)
nfs4_put_stateowner(&lo->lo_owner);
}
-static void release_lockowner_if_empty(struct nfs4_lockowner *lo)
-{
- if (list_empty(&lo->lo_owner.so_stateids))
- release_lockowner(lo);
-}
-
-static void release_lock_stateid(struct nfs4_ol_stateid *stp)
-{
- struct nfs4_lockowner *lo;
-
- lo = lockowner(stp->st_stateowner);
- __release_lock_stateid(stp);
- release_lockowner_if_empty(lo);
-}
-
static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp)
__releases(&open_stp->st_stateowner->so_client->cl_lock)
__acquires(&open_stp->st_stateowner->so_client->cl_lock)
@@ -4273,7 +4258,7 @@ nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp)
if (check_for_locks(stp->st_stid.sc_file, lo))
return nfserr_locks_held;
- release_lockowner_if_empty(lo);
+ release_lock_stateid(stp);
return nfs_ok;
}
@@ -4883,8 +4868,6 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
lo = alloc_init_lock_stateowner(strhashval, cl, ost, lock);
if (lo == NULL)
return nfserr_jukebox;
- /* FIXME: extra reference for new lockowners for the client */
- atomic_inc(&lo->lo_owner.so_count);
} else {
/* with an existing lockowner, seqids must be the same */
status = nfserr_bad_seqid;
@@ -4895,7 +4878,6 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
*lst = find_or_create_lock_stateid(lo, fi, ost, new);
if (*lst == NULL) {
- release_lockowner_if_empty(lo);
status = nfserr_jukebox;
goto out;
}
@@ -5309,6 +5291,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
continue;
if (same_owner_str(tmp, owner, clid)) {
sop = tmp;
+ atomic_inc(&sop->so_count);
break;
}
}
@@ -5322,8 +5305,10 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
lo = lockowner(sop);
/* see if there are still any locks associated with it */
list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) {
- if (check_for_locks(stp->st_stid.sc_file, lo))
+ if (check_for_locks(stp->st_stid.sc_file, lo)) {
+ nfs4_put_stateowner(sop);
goto out;
+ }
}
status = nfs_ok;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 065/114] nfsd: make openstateids hold references to their openowners
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (63 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 064/114] nfsd: clean up refcounting for lockowners Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 066/114] nfsd: don't allow CLOSE to proceed until refcount on stateid drops Jeff Layton
` (48 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Change it so that only openstateids hold persistent references to
openowners. References can still be held by compounds in progress.
With this, we can get rid of NFS4_OO_NEW. It's possible that we
will create a new openowner in the process of doing the open, but
something later fails. In the meantime, another task could find
that openowner and start using it on a successful open. If that
occurs we don't necessarily want to tear it down, just put the
reference that the failing compound holds.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 71 +++++++++++++++++++++++------------------------------
fs/nfsd/state.h | 1 -
2 files changed, 31 insertions(+), 41 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b658fd481c4e..d97f3d3743f3 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -882,7 +882,7 @@ static void nfs4_free_generic_stateid(struct nfs4_stid *stid)
struct nfs4_ol_stateid *stp = openlockstateid(stid);
release_all_access(stp);
- if (stp->st_stateowner && stid->sc_type == NFS4_LOCK_STID)
+ if (stp->st_stateowner)
nfs4_put_stateowner(stp->st_stateowner);
nfs4_free_stid(stateid_slab, stid);
}
@@ -979,8 +979,9 @@ static void release_last_closed_stateid(struct nfs4_openowner *oo)
struct nfs4_ol_stateid *s = oo->oo_last_closed_stid;
if (s) {
- put_generic_stateid(s);
+ list_del_init(&oo->oo_close_lru);
oo->oo_last_closed_stid = NULL;
+ put_generic_stateid(s);
}
}
@@ -999,7 +1000,6 @@ static void release_openowner(struct nfs4_openowner *oo)
{
unhash_openowner(oo);
release_openowner_stateids(oo);
- list_del(&oo->oo_close_lru);
release_last_closed_stateid(oo);
nfs4_put_stateowner(&oo->oo_owner);
}
@@ -1472,6 +1472,7 @@ destroy_client(struct nfs4_client *clp)
}
while (!list_empty(&clp->cl_openowners)) {
oo = list_entry(clp->cl_openowners.next, struct nfs4_openowner, oo_perclient);
+ atomic_inc(&oo->oo_owner.so_count);
release_openowner(oo);
}
nfsd4_shutdown_callback(clp);
@@ -3003,7 +3004,7 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
oo->oo_owner.so_unhash = nfs4_unhash_openowner;
oo->oo_owner.so_is_open_owner = 1;
oo->oo_owner.so_seqid = open->op_seqid;
- oo->oo_flags = NFS4_OO_NEW;
+ oo->oo_flags = 0;
if (nfsd4_has_session(cstate))
oo->oo_flags |= NFS4_OO_CONFIRMED;
oo->oo_time = 0;
@@ -3020,6 +3021,7 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
stp->st_stid.sc_type = NFS4_OPEN_STID;
INIT_LIST_HEAD(&stp->st_locks);
stp->st_stateowner = &oo->oo_owner;
+ atomic_inc(&stp->st_stateowner->so_count);
get_nfs4_file(fp);
stp->st_stid.sc_file = fp;
stp->st_access_bmap = 0;
@@ -3035,13 +3037,27 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
spin_unlock(&oo->oo_owner.so_client->cl_lock);
}
+/*
+ * In the 4.0 case we need to keep the owners around a little while to handle
+ * CLOSE replay. We still do need to release any file access that is held by
+ * them before returning however.
+ */
static void
-move_to_close_lru(struct nfs4_openowner *oo, struct net *net)
+move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
{
- struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ struct nfs4_openowner *oo = openowner(s->st_stateowner);
+ struct nfsd_net *nn = net_generic(s->st_stid.sc_client->net,
+ nfsd_net_id);
dprintk("NFSD: move_to_close_lru nfs4_openowner %p\n", oo);
+ release_all_access(s);
+ if (s->st_stid.sc_file) {
+ put_nfs4_file(s->st_stid.sc_file);
+ s->st_stid.sc_file = NULL;
+ }
+ release_last_closed_stateid(oo);
+ oo->oo_last_closed_stid = s;
list_move_tail(&oo->oo_close_lru, &nn->close_lru);
oo->oo_time = get_seconds();
}
@@ -3072,6 +3088,7 @@ find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
if ((bool)clp->cl_minorversion != sessions)
return NULL;
renew_client(oo->oo_owner.so_client);
+ atomic_inc(&oo->oo_owner.so_count);
return oo;
}
}
@@ -3839,19 +3856,10 @@ void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate,
struct nfsd4_open *open, __be32 status)
{
if (open->op_openowner) {
- struct nfs4_openowner *oo = open->op_openowner;
-
- if (!list_empty(&oo->oo_owner.so_stateids))
- list_del_init(&oo->oo_close_lru);
- if (oo->oo_flags & NFS4_OO_NEW) {
- if (status) {
- release_openowner(oo);
- open->op_openowner = NULL;
- } else
- oo->oo_flags &= ~NFS4_OO_NEW;
- }
- if (open->op_openowner)
- nfsd4_cstate_assign_replay(cstate, &oo->oo_owner);
+ struct nfs4_stateowner *so = &open->op_openowner->oo_owner;
+
+ nfsd4_cstate_assign_replay(cstate, so);
+ nfs4_put_stateowner(so);
}
if (open->op_file)
nfsd4_free_file(open->op_file);
@@ -3965,7 +3973,7 @@ nfs4_laundromat(struct nfsd_net *nn)
new_timeo = min(new_timeo, t);
break;
}
- release_openowner(oo);
+ release_last_closed_stateid(oo);
}
new_timeo = max_t(time_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
nfs4_unlock_state();
@@ -4528,31 +4536,14 @@ out:
static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
{
struct nfs4_client *clp = s->st_stid.sc_client;
- struct nfs4_openowner *oo = openowner(s->st_stateowner);
s->st_stid.sc_type = NFS4_CLOSED_STID;
unhash_open_stateid(s);
- if (clp->cl_minorversion) {
- if (list_empty(&oo->oo_owner.so_stateids))
- release_openowner(oo);
+ if (clp->cl_minorversion)
put_generic_stateid(s);
- } else {
- if (s->st_stid.sc_file) {
- put_nfs4_file(s->st_stid.sc_file);
- s->st_stid.sc_file = NULL;
- }
- oo->oo_last_closed_stid = s;
- /*
- * In the 4.0 case we need to keep the owners around a
- * little while to handle CLOSE replay. We still do need
- * to release any file access that is held by them
- * before returning however.
- */
- release_all_access(s);
- if (list_empty(&oo->oo_owner.so_stateids))
- move_to_close_lru(oo, clp->net);
- }
+ else
+ move_to_close_lru(s, clp->net);
}
/*
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index f6639fb5a56f..9e9e45278b40 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -364,7 +364,6 @@ struct nfs4_openowner {
struct nfs4_ol_stateid *oo_last_closed_stid;
time_t oo_time; /* time of placement on so_close_lru */
#define NFS4_OO_CONFIRMED 1
-#define NFS4_OO_NEW 4
unsigned char oo_flags;
};
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 066/114] nfsd: don't allow CLOSE to proceed until refcount on stateid drops
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (64 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 065/114] nfsd: make openstateids hold references to their openowners Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 067/114] nfsd: Protect adding/removing open state owners using client_lock Jeff Layton
` (47 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Once we remove client_mutex protection, it'll be possible to have an
in-flight operation using an openstateid when a CLOSE call comes in.
If that happens, we can't just put the sc_file reference and clear its
pointer without risking an oops.
Fix this by ensuring that v4.0 CLOSE operations wait for the refcount
to drop before proceeding to do so.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 22 +++++++++++++++++++++-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d97f3d3743f3..4d504c83d8d8 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -86,6 +86,12 @@ static DEFINE_MUTEX(client_mutex);
*/
static DEFINE_SPINLOCK(state_lock);
+/*
+ * A waitqueue for all in-progress 4.0 CLOSE operations that are waiting for
+ * the refcount on the open stateid to drop.
+ */
+static DECLARE_WAIT_QUEUE_HEAD(close_wq);
+
static struct kmem_cache *openowner_slab;
static struct kmem_cache *lockowner_slab;
static struct kmem_cache *file_slab;
@@ -626,8 +632,10 @@ static void nfs4_put_stid(struct nfs4_stid *s)
{
struct nfs4_client *clp = s->sc_client;
- if (!atomic_dec_and_lock(&s->sc_count, &clp->cl_lock))
+ if (!atomic_dec_and_lock(&s->sc_count, &clp->cl_lock)) {
+ wake_up_all(&close_wq);
return;
+ }
remove_stid_locked(clp, s);
spin_unlock(&clp->cl_lock);
s->sc_free(s);
@@ -3051,11 +3059,23 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
dprintk("NFSD: move_to_close_lru nfs4_openowner %p\n", oo);
+ /*
+ * We know that we hold one reference via nfsd4_close, and another
+ * "persistent" reference for the client. If the refcount is higher
+ * than 2, then there are still calls in progress that are using this
+ * stateid. We can't put the sc_file reference until they are finished.
+ * Wait for the refcount to drop to 2. Since it has been unhashed,
+ * there should be no danger of the refcount going back up again at
+ * this point.
+ */
+ wait_event(close_wq, atomic_read(&s->st_stid.sc_count) == 2);
+
release_all_access(s);
if (s->st_stid.sc_file) {
put_nfs4_file(s->st_stid.sc_file);
s->st_stid.sc_file = NULL;
}
+
release_last_closed_stateid(oo);
oo->oo_last_closed_stid = s;
list_move_tail(&oo->oo_close_lru, &nn->close_lru);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 067/114] nfsd: Protect adding/removing open state owners using client_lock
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (65 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 066/114] nfsd: don't allow CLOSE to proceed until refcount on stateid drops Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 068/114] nfsd: Protect adding/removing lock " Jeff Layton
` (46 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Once we remove client mutex protection, we'll need to ensure that
stateowner lookup and creation are atomic between concurrent compounds.
Ensure that alloc_init_open_stateowner checks the hashtable under the
client_lock before adding a new element.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 63 +++++++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 54 insertions(+), 9 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4d504c83d8d8..661af4bf0296 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -72,6 +72,9 @@ static u64 current_sessionid = 1;
/* forward declarations */
static int check_for_locks(struct nfs4_file *filp, struct nfs4_lockowner *lowner);
static void nfs4_free_generic_stateid(struct nfs4_stid *stid);
+static struct nfs4_openowner *find_openstateowner_str_locked(
+ unsigned int hashval, struct nfsd4_open *open,
+ bool sessions, struct nfsd_net *nn);
static void nfs4_put_stateowner(struct nfs4_stateowner *sop);
/* Locking: */
@@ -976,8 +979,13 @@ static void release_open_stateid(struct nfs4_ol_stateid *stp)
put_generic_stateid(stp);
}
-static void unhash_openowner(struct nfs4_openowner *oo)
+static void unhash_openowner_locked(struct nfs4_openowner *oo)
{
+ struct nfsd_net *nn = net_generic(oo->oo_owner.so_client->net,
+ nfsd_net_id);
+
+ lockdep_assert_held(&nn->client_lock);
+
list_del_init(&oo->oo_owner.so_strhash);
list_del_init(&oo->oo_perclient);
}
@@ -996,18 +1004,29 @@ static void release_last_closed_stateid(struct nfs4_openowner *oo)
static void release_openowner_stateids(struct nfs4_openowner *oo)
{
struct nfs4_ol_stateid *stp;
+ struct nfsd_net *nn = net_generic(oo->oo_owner.so_client->net,
+ nfsd_net_id);
+
+ lockdep_assert_held(&nn->client_lock);
while (!list_empty(&oo->oo_owner.so_stateids)) {
stp = list_first_entry(&oo->oo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
+ spin_unlock(&nn->client_lock);
release_open_stateid(stp);
+ spin_lock(&nn->client_lock);
}
}
static void release_openowner(struct nfs4_openowner *oo)
{
- unhash_openowner(oo);
+ struct nfsd_net *nn = net_generic(oo->oo_owner.so_client->net,
+ nfsd_net_id);
+
+ spin_lock(&nn->client_lock);
+ unhash_openowner_locked(oo);
release_openowner_stateids(oo);
+ spin_unlock(&nn->client_lock);
release_last_closed_stateid(oo);
nfs4_put_stateowner(&oo->oo_owner);
}
@@ -2986,8 +3005,11 @@ static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, u
static void nfs4_unhash_openowner(struct nfs4_stateowner *so)
{
struct nfs4_openowner *oo = openowner(so);
+ struct nfsd_net *nn = net_generic(so->so_client->net, nfsd_net_id);
- unhash_openowner(oo);
+ spin_lock(&nn->client_lock);
+ unhash_openowner_locked(oo);
+ spin_unlock(&nn->client_lock);
}
static void nfs4_free_openowner(struct nfs4_stateowner *so)
@@ -3003,7 +3025,8 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
struct nfsd4_compound_state *cstate)
{
struct nfs4_client *clp = cstate->clp;
- struct nfs4_openowner *oo;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+ struct nfs4_openowner *oo, *ret;
oo = alloc_stateowner(openowner_slab, &open->op_owner, clp);
if (!oo)
@@ -3018,7 +3041,15 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
oo->oo_time = 0;
oo->oo_last_closed_stid = NULL;
INIT_LIST_HEAD(&oo->oo_close_lru);
- hash_openowner(oo, clp, strhashval);
+ spin_lock(&nn->client_lock);
+ ret = find_openstateowner_str_locked(strhashval,
+ open, clp->cl_minorversion, nn);
+ if (ret == NULL) {
+ hash_openowner(oo, clp, strhashval);
+ ret = oo;
+ } else
+ nfs4_free_openowner(&oo->oo_owner);
+ spin_unlock(&nn->client_lock);
return oo;
}
@@ -3092,13 +3123,15 @@ same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner,
}
static struct nfs4_openowner *
-find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
+find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open,
bool sessions, struct nfsd_net *nn)
{
struct nfs4_stateowner *so;
struct nfs4_openowner *oo;
struct nfs4_client *clp;
+ lockdep_assert_held(&nn->client_lock);
+
list_for_each_entry(so, &nn->ownerstr_hashtbl[hashval], so_strhash) {
if (!so->so_is_open_owner)
continue;
@@ -3106,15 +3139,27 @@ find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
oo = openowner(so);
clp = oo->oo_owner.so_client;
if ((bool)clp->cl_minorversion != sessions)
- return NULL;
- renew_client(oo->oo_owner.so_client);
- atomic_inc(&oo->oo_owner.so_count);
+ break;
+ renew_client_locked(clp);
+ atomic_inc(&so->so_count);
return oo;
}
}
return NULL;
}
+static struct nfs4_openowner *
+find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
+ bool sessions, struct nfsd_net *nn)
+{
+ struct nfs4_openowner *oo;
+
+ spin_lock(&nn->client_lock);
+ oo = find_openstateowner_str_locked(hashval, open, sessions, nn);
+ spin_unlock(&nn->client_lock);
+ return oo;
+}
+
/* search file_hashtbl[] for file */
static struct nfs4_file *
find_file_locked(struct inode *ino)
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 068/114] nfsd: Protect adding/removing lock owners using client_lock
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (66 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 067/114] nfsd: Protect adding/removing open state owners using client_lock Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 069/114] nfsd: Move the open owner hash table into struct nfs4_client Jeff Layton
` (45 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Once we remove client mutex protection, we'll need to ensure that
stateowner lookup and creation are atomic between concurrent compounds.
Ensure that alloc_init_lock_stateowner checks the hashtable under the
client_lock before adding a new element.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++-------
1 file changed, 61 insertions(+), 8 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 661af4bf0296..41800f2ddd01 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -927,26 +927,42 @@ static void release_lock_stateid(struct nfs4_ol_stateid *stp)
put_generic_stateid(stp);
}
-static void unhash_lockowner(struct nfs4_lockowner *lo)
+static void unhash_lockowner_locked(struct nfs4_lockowner *lo)
{
+ struct nfsd_net *nn = net_generic(lo->lo_owner.so_client->net,
+ nfsd_net_id);
+
+ lockdep_assert_held(&nn->client_lock);
+
list_del_init(&lo->lo_owner.so_strhash);
}
static void release_lockowner_stateids(struct nfs4_lockowner *lo)
{
+ struct nfsd_net *nn = net_generic(lo->lo_owner.so_client->net,
+ nfsd_net_id);
struct nfs4_ol_stateid *stp;
+ lockdep_assert_held(&nn->client_lock);
+
while (!list_empty(&lo->lo_owner.so_stateids)) {
stp = list_first_entry(&lo->lo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
+ spin_unlock(&nn->client_lock);
release_lock_stateid(stp);
+ spin_lock(&nn->client_lock);
}
}
static void release_lockowner(struct nfs4_lockowner *lo)
{
- unhash_lockowner(lo);
+ struct nfsd_net *nn = net_generic(lo->lo_owner.so_client->net,
+ nfsd_net_id);
+
+ spin_lock(&nn->client_lock);
+ unhash_lockowner_locked(lo);
release_lockowner_stateids(lo);
+ spin_unlock(&nn->client_lock);
nfs4_put_stateowner(&lo->lo_owner);
}
@@ -4753,7 +4769,7 @@ nevermind:
}
static struct nfs4_lockowner *
-find_lockowner_str(clientid_t *clid, struct xdr_netobj *owner,
+find_lockowner_str_locked(clientid_t *clid, struct xdr_netobj *owner,
struct nfsd_net *nn)
{
unsigned int strhashval = ownerstr_hashval(clid->cl_id, owner);
@@ -4770,9 +4786,25 @@ find_lockowner_str(clientid_t *clid, struct xdr_netobj *owner,
return NULL;
}
+static struct nfs4_lockowner *
+find_lockowner_str(clientid_t *clid, struct xdr_netobj *owner,
+ struct nfsd_net *nn)
+{
+ struct nfs4_lockowner *lo;
+
+ spin_lock(&nn->client_lock);
+ lo = find_lockowner_str_locked(clid, owner, nn);
+ spin_unlock(&nn->client_lock);
+ return lo;
+}
+
static void nfs4_unhash_lockowner(struct nfs4_stateowner *sop)
{
- unhash_lockowner(lockowner(sop));
+ struct nfsd_net *nn = net_generic(sop->so_client->net, nfsd_net_id);
+
+ spin_lock(&nn->client_lock);
+ unhash_lockowner_locked(lockowner(sop));
+ spin_unlock(&nn->client_lock);
}
static void nfs4_free_lockowner(struct nfs4_stateowner *sop)
@@ -4791,9 +4823,12 @@ static void nfs4_free_lockowner(struct nfs4_stateowner *sop)
* strhashval = ownerstr_hashval
*/
static struct nfs4_lockowner *
-alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, struct nfs4_ol_stateid *open_stp, struct nfsd4_lock *lock) {
- struct nfs4_lockowner *lo;
+alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp,
+ struct nfs4_ol_stateid *open_stp,
+ struct nfsd4_lock *lock)
+{
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+ struct nfs4_lockowner *lo, *ret;
lo = alloc_stateowner(lockowner_slab, &lock->lk_new_owner, clp);
if (!lo)
@@ -4803,7 +4838,16 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, str
lo->lo_owner.so_seqid = lock->lk_new_lock_seqid;
lo->lo_owner.so_free = nfs4_free_lockowner;
lo->lo_owner.so_unhash = nfs4_unhash_lockowner;
- list_add(&lo->lo_owner.so_strhash, &nn->ownerstr_hashtbl[strhashval]);
+ spin_lock(&nn->client_lock);
+ ret = find_lockowner_str_locked(&clp->cl_clientid,
+ &lock->lk_new_owner, nn);
+ if (ret == NULL) {
+ list_add(&lo->lo_owner.so_strhash,
+ &nn->ownerstr_hashtbl[strhashval]);
+ ret = lo;
+ } else
+ nfs4_free_lockowner(&lo->lo_owner);
+ spin_unlock(&nn->client_lock);
return lo;
}
@@ -5329,6 +5373,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
unsigned int hashval = ownerstr_hashval(clid->cl_id, owner);
__be32 status;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+ struct nfs4_client *clp;
dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n",
clid->cl_boot, clid->cl_id);
@@ -5342,6 +5387,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
status = nfserr_locks_held;
/* Find the matching lock stateowner */
+ spin_lock(&nn->client_lock);
list_for_each_entry(tmp, &nn->ownerstr_hashtbl[hashval], so_strhash) {
if (tmp->so_is_open_owner)
continue;
@@ -5351,6 +5397,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
break;
}
}
+ spin_unlock(&nn->client_lock);
/* No matching owner found, maybe a replay? Just declare victory... */
if (!sop) {
@@ -5360,16 +5407,22 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
lo = lockowner(sop);
/* see if there are still any locks associated with it */
+ clp = cstate->clp;
+ spin_lock(&clp->cl_lock);
list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) {
if (check_for_locks(stp->st_stid.sc_file, lo)) {
- nfs4_put_stateowner(sop);
+ spin_unlock(&clp->cl_lock);
goto out;
}
}
+ spin_unlock(&clp->cl_lock);
status = nfs_ok;
+ sop = NULL;
release_lockowner(lo);
out:
+ if (sop)
+ nfs4_put_stateowner(sop);
nfs4_unlock_state();
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 069/114] nfsd: Move the open owner hash table into struct nfs4_client
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (67 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 068/114] nfsd: Protect adding/removing lock " Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 070/114] nfsd: clean up and reorganize release_lockowner Jeff Layton
` (44 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Preparation for removing the client_mutex.
Convert the open owner hash table into a per-client table and protect it
using the nfs4_client->cl_lock spin lock.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/netns.h | 1 -
fs/nfsd/nfs4state.c | 188 ++++++++++++++++++++++++----------------------------
fs/nfsd/state.h | 1 +
3 files changed, 87 insertions(+), 103 deletions(-)
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index beaceac90ad3..f89042ae0056 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -63,7 +63,6 @@ struct nfsd_net {
struct rb_root conf_name_tree;
struct list_head *unconf_id_hashtbl;
struct rb_root unconf_name_tree;
- struct list_head *ownerstr_hashtbl;
struct list_head *sessionid_hashtbl;
/*
* client_lru holds client queue ordered by nfs4_client.cl_time
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 41800f2ddd01..1bd7b2b0a4b1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -74,7 +74,7 @@ static int check_for_locks(struct nfs4_file *filp, struct nfs4_lockowner *lowner
static void nfs4_free_generic_stateid(struct nfs4_stid *stid);
static struct nfs4_openowner *find_openstateowner_str_locked(
unsigned int hashval, struct nfsd4_open *open,
- bool sessions, struct nfsd_net *nn);
+ struct nfs4_client *clp);
static void nfs4_put_stateowner(struct nfs4_stateowner *sop);
/* Locking: */
@@ -335,12 +335,11 @@ unsigned long max_delegations;
#define OWNER_HASH_SIZE (1 << OWNER_HASH_BITS)
#define OWNER_HASH_MASK (OWNER_HASH_SIZE - 1)
-static unsigned int ownerstr_hashval(u32 clientid, struct xdr_netobj *ownername)
+static unsigned int ownerstr_hashval(struct xdr_netobj *ownername)
{
unsigned int ret;
ret = opaque_hashval(ownername->data, ownername->len);
- ret += clientid;
return ret & OWNER_HASH_MASK;
}
@@ -929,40 +928,37 @@ static void release_lock_stateid(struct nfs4_ol_stateid *stp)
static void unhash_lockowner_locked(struct nfs4_lockowner *lo)
{
- struct nfsd_net *nn = net_generic(lo->lo_owner.so_client->net,
- nfsd_net_id);
+ struct nfs4_client *clp = lo->lo_owner.so_client;
- lockdep_assert_held(&nn->client_lock);
+ lockdep_assert_held(&clp->cl_lock);
list_del_init(&lo->lo_owner.so_strhash);
}
static void release_lockowner_stateids(struct nfs4_lockowner *lo)
{
- struct nfsd_net *nn = net_generic(lo->lo_owner.so_client->net,
- nfsd_net_id);
+ struct nfs4_client *clp = lo->lo_owner.so_client;
struct nfs4_ol_stateid *stp;
- lockdep_assert_held(&nn->client_lock);
+ lockdep_assert_held(&clp->cl_lock);
while (!list_empty(&lo->lo_owner.so_stateids)) {
stp = list_first_entry(&lo->lo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
- spin_unlock(&nn->client_lock);
+ spin_unlock(&clp->cl_lock);
release_lock_stateid(stp);
- spin_lock(&nn->client_lock);
+ spin_lock(&clp->cl_lock);
}
}
static void release_lockowner(struct nfs4_lockowner *lo)
{
- struct nfsd_net *nn = net_generic(lo->lo_owner.so_client->net,
- nfsd_net_id);
+ struct nfs4_client *clp = lo->lo_owner.so_client;
- spin_lock(&nn->client_lock);
+ spin_lock(&clp->cl_lock);
unhash_lockowner_locked(lo);
release_lockowner_stateids(lo);
- spin_unlock(&nn->client_lock);
+ spin_unlock(&clp->cl_lock);
nfs4_put_stateowner(&lo->lo_owner);
}
@@ -997,10 +993,9 @@ static void release_open_stateid(struct nfs4_ol_stateid *stp)
static void unhash_openowner_locked(struct nfs4_openowner *oo)
{
- struct nfsd_net *nn = net_generic(oo->oo_owner.so_client->net,
- nfsd_net_id);
+ struct nfs4_client *clp = oo->oo_owner.so_client;
- lockdep_assert_held(&nn->client_lock);
+ lockdep_assert_held(&clp->cl_lock);
list_del_init(&oo->oo_owner.so_strhash);
list_del_init(&oo->oo_perclient);
@@ -1020,29 +1015,27 @@ static void release_last_closed_stateid(struct nfs4_openowner *oo)
static void release_openowner_stateids(struct nfs4_openowner *oo)
{
struct nfs4_ol_stateid *stp;
- struct nfsd_net *nn = net_generic(oo->oo_owner.so_client->net,
- nfsd_net_id);
+ struct nfs4_client *clp = oo->oo_owner.so_client;
- lockdep_assert_held(&nn->client_lock);
+ lockdep_assert_held(&clp->cl_lock);
while (!list_empty(&oo->oo_owner.so_stateids)) {
stp = list_first_entry(&oo->oo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
- spin_unlock(&nn->client_lock);
+ spin_unlock(&clp->cl_lock);
release_open_stateid(stp);
- spin_lock(&nn->client_lock);
+ spin_lock(&clp->cl_lock);
}
}
static void release_openowner(struct nfs4_openowner *oo)
{
- struct nfsd_net *nn = net_generic(oo->oo_owner.so_client->net,
- nfsd_net_id);
+ struct nfs4_client *clp = oo->oo_owner.so_client;
- spin_lock(&nn->client_lock);
+ spin_lock(&clp->cl_lock);
unhash_openowner_locked(oo);
release_openowner_stateids(oo);
- spin_unlock(&nn->client_lock);
+ spin_unlock(&clp->cl_lock);
release_last_closed_stateid(oo);
nfs4_put_stateowner(&oo->oo_owner);
}
@@ -1426,15 +1419,20 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn)
static struct nfs4_client *alloc_client(struct xdr_netobj name)
{
struct nfs4_client *clp;
+ int i;
clp = kzalloc(sizeof(struct nfs4_client), GFP_KERNEL);
if (clp == NULL)
return NULL;
clp->cl_name.data = kmemdup(name.data, name.len, GFP_KERNEL);
- if (clp->cl_name.data == NULL) {
- kfree(clp);
- return NULL;
- }
+ if (clp->cl_name.data == NULL)
+ goto err_no_name;
+ clp->cl_ownerstr_hashtbl = kmalloc(sizeof(struct list_head) *
+ OWNER_HASH_SIZE, GFP_KERNEL);
+ if (!clp->cl_ownerstr_hashtbl)
+ goto err_no_hashtbl;
+ for (i = 0; i < OWNER_HASH_SIZE; i++)
+ INIT_LIST_HEAD(&clp->cl_ownerstr_hashtbl[i]);
clp->cl_name.len = name.len;
INIT_LIST_HEAD(&clp->cl_sessions);
idr_init(&clp->cl_stateids);
@@ -1449,6 +1447,11 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name)
spin_lock_init(&clp->cl_lock);
rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table");
return clp;
+err_no_hashtbl:
+ kfree(clp->cl_name.data);
+err_no_name:
+ kfree(clp);
+ return NULL;
}
static void
@@ -1467,6 +1470,7 @@ free_client(struct nfs4_client *clp)
}
rpc_destroy_wait_queue(&clp->cl_cb_waitq);
free_svc_cred(&clp->cl_cred);
+ kfree(clp->cl_ownerstr_hashtbl);
kfree(clp->cl_name.data);
spin_lock(&clp->cl_lock);
idr_destroy(&clp->cl_stateids);
@@ -3012,20 +3016,20 @@ static void nfs4_put_stateowner(struct nfs4_stateowner *sop)
static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, unsigned int strhashval)
{
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+ lockdep_assert_held(&clp->cl_lock);
- list_add(&oo->oo_owner.so_strhash, &nn->ownerstr_hashtbl[strhashval]);
+ list_add(&oo->oo_owner.so_strhash,
+ &clp->cl_ownerstr_hashtbl[strhashval]);
list_add(&oo->oo_perclient, &clp->cl_openowners);
}
static void nfs4_unhash_openowner(struct nfs4_stateowner *so)
{
- struct nfs4_openowner *oo = openowner(so);
- struct nfsd_net *nn = net_generic(so->so_client->net, nfsd_net_id);
+ struct nfs4_client *clp = so->so_client;
- spin_lock(&nn->client_lock);
- unhash_openowner_locked(oo);
- spin_unlock(&nn->client_lock);
+ spin_lock(&clp->cl_lock);
+ unhash_openowner_locked(openowner(so));
+ spin_unlock(&clp->cl_lock);
}
static void nfs4_free_openowner(struct nfs4_stateowner *so)
@@ -3041,7 +3045,6 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
struct nfsd4_compound_state *cstate)
{
struct nfs4_client *clp = cstate->clp;
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct nfs4_openowner *oo, *ret;
oo = alloc_stateowner(openowner_slab, &open->op_owner, clp);
@@ -3057,15 +3060,14 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open,
oo->oo_time = 0;
oo->oo_last_closed_stid = NULL;
INIT_LIST_HEAD(&oo->oo_close_lru);
- spin_lock(&nn->client_lock);
- ret = find_openstateowner_str_locked(strhashval,
- open, clp->cl_minorversion, nn);
+ spin_lock(&clp->cl_lock);
+ ret = find_openstateowner_str_locked(strhashval, open, clp);
if (ret == NULL) {
hash_openowner(oo, clp, strhashval);
ret = oo;
} else
nfs4_free_openowner(&oo->oo_owner);
- spin_unlock(&nn->client_lock);
+ spin_unlock(&clp->cl_lock);
return oo;
}
@@ -3130,35 +3132,27 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
}
static int
-same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner,
- clientid_t *clid)
+same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner)
{
return (sop->so_owner.len == owner->len) &&
- 0 == memcmp(sop->so_owner.data, owner->data, owner->len) &&
- (sop->so_client->cl_clientid.cl_id == clid->cl_id);
+ 0 == memcmp(sop->so_owner.data, owner->data, owner->len);
}
static struct nfs4_openowner *
find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open,
- bool sessions, struct nfsd_net *nn)
+ struct nfs4_client *clp)
{
struct nfs4_stateowner *so;
- struct nfs4_openowner *oo;
- struct nfs4_client *clp;
- lockdep_assert_held(&nn->client_lock);
+ lockdep_assert_held(&clp->cl_lock);
- list_for_each_entry(so, &nn->ownerstr_hashtbl[hashval], so_strhash) {
+ list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[hashval],
+ so_strhash) {
if (!so->so_is_open_owner)
continue;
- if (same_owner_str(so, &open->op_owner, &open->op_clientid)) {
- oo = openowner(so);
- clp = oo->oo_owner.so_client;
- if ((bool)clp->cl_minorversion != sessions)
- break;
- renew_client_locked(clp);
+ if (same_owner_str(so, &open->op_owner)) {
atomic_inc(&so->so_count);
- return oo;
+ return openowner(so);
}
}
return NULL;
@@ -3166,13 +3160,13 @@ find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open,
static struct nfs4_openowner *
find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open,
- bool sessions, struct nfsd_net *nn)
+ struct nfs4_client *clp)
{
struct nfs4_openowner *oo;
- spin_lock(&nn->client_lock);
- oo = find_openstateowner_str_locked(hashval, open, sessions, nn);
- spin_unlock(&nn->client_lock);
+ spin_lock(&clp->cl_lock);
+ oo = find_openstateowner_str_locked(hashval, open, clp);
+ spin_unlock(&clp->cl_lock);
return oo;
}
@@ -3384,8 +3378,8 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate,
return status;
clp = cstate->clp;
- strhashval = ownerstr_hashval(clientid->cl_id, &open->op_owner);
- oo = find_openstateowner_str(strhashval, open, cstate->minorversion, nn);
+ strhashval = ownerstr_hashval(&open->op_owner);
+ oo = find_openstateowner_str(strhashval, open, clp);
open->op_openowner = oo;
if (!oo) {
goto new_owner;
@@ -4770,15 +4764,16 @@ nevermind:
static struct nfs4_lockowner *
find_lockowner_str_locked(clientid_t *clid, struct xdr_netobj *owner,
- struct nfsd_net *nn)
+ struct nfs4_client *clp)
{
- unsigned int strhashval = ownerstr_hashval(clid->cl_id, owner);
+ unsigned int strhashval = ownerstr_hashval(owner);
struct nfs4_stateowner *so;
- list_for_each_entry(so, &nn->ownerstr_hashtbl[strhashval], so_strhash) {
+ list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[strhashval],
+ so_strhash) {
if (so->so_is_open_owner)
continue;
- if (!same_owner_str(so, owner, clid))
+ if (!same_owner_str(so, owner))
continue;
atomic_inc(&so->so_count);
return lockowner(so);
@@ -4788,23 +4783,23 @@ find_lockowner_str_locked(clientid_t *clid, struct xdr_netobj *owner,
static struct nfs4_lockowner *
find_lockowner_str(clientid_t *clid, struct xdr_netobj *owner,
- struct nfsd_net *nn)
+ struct nfs4_client *clp)
{
struct nfs4_lockowner *lo;
- spin_lock(&nn->client_lock);
- lo = find_lockowner_str_locked(clid, owner, nn);
- spin_unlock(&nn->client_lock);
+ spin_lock(&clp->cl_lock);
+ lo = find_lockowner_str_locked(clid, owner, clp);
+ spin_unlock(&clp->cl_lock);
return lo;
}
static void nfs4_unhash_lockowner(struct nfs4_stateowner *sop)
{
- struct nfsd_net *nn = net_generic(sop->so_client->net, nfsd_net_id);
+ struct nfs4_client *clp = sop->so_client;
- spin_lock(&nn->client_lock);
+ spin_lock(&clp->cl_lock);
unhash_lockowner_locked(lockowner(sop));
- spin_unlock(&nn->client_lock);
+ spin_unlock(&clp->cl_lock);
}
static void nfs4_free_lockowner(struct nfs4_stateowner *sop)
@@ -4827,7 +4822,6 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp,
struct nfs4_ol_stateid *open_stp,
struct nfsd4_lock *lock)
{
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct nfs4_lockowner *lo, *ret;
lo = alloc_stateowner(lockowner_slab, &lock->lk_new_owner, clp);
@@ -4838,16 +4832,16 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp,
lo->lo_owner.so_seqid = lock->lk_new_lock_seqid;
lo->lo_owner.so_free = nfs4_free_lockowner;
lo->lo_owner.so_unhash = nfs4_unhash_lockowner;
- spin_lock(&nn->client_lock);
+ spin_lock(&clp->cl_lock);
ret = find_lockowner_str_locked(&clp->cl_clientid,
- &lock->lk_new_owner, nn);
+ &lock->lk_new_owner, clp);
if (ret == NULL) {
list_add(&lo->lo_owner.so_strhash,
- &nn->ownerstr_hashtbl[strhashval]);
+ &clp->cl_ownerstr_hashtbl[strhashval]);
ret = lo;
} else
nfs4_free_lockowner(&lo->lo_owner);
- spin_unlock(&nn->client_lock);
+ spin_unlock(&clp->cl_lock);
return lo;
}
@@ -4959,12 +4953,10 @@ static __be32 lookup_or_create_lock_state(struct nfsd4_compound_state *cstate,
struct nfs4_client *cl = oo->oo_owner.so_client;
struct nfs4_lockowner *lo;
unsigned int strhashval;
- struct nfsd_net *nn = net_generic(cl->net, nfsd_net_id);
- lo = find_lockowner_str(&cl->cl_clientid, &lock->v.new.owner, nn);
+ lo = find_lockowner_str(&cl->cl_clientid, &lock->v.new.owner, cl);
if (!lo) {
- strhashval = ownerstr_hashval(cl->cl_clientid.cl_id,
- &lock->v.new.owner);
+ strhashval = ownerstr_hashval(&lock->v.new.owner);
lo = alloc_init_lock_stateowner(strhashval, cl, ost, lock);
if (lo == NULL)
return nfserr_jukebox;
@@ -5236,7 +5228,8 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out;
}
- lo = find_lockowner_str(&lockt->lt_clientid, &lockt->lt_owner, nn);
+ lo = find_lockowner_str(&lockt->lt_clientid, &lockt->lt_owner,
+ cstate->clp);
if (lo)
file_lock->fl_owner = (fl_owner_t)lo;
file_lock->fl_pid = current->tgid;
@@ -5370,7 +5363,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
struct nfs4_lockowner *lo;
struct nfs4_ol_stateid *stp;
struct xdr_netobj *owner = &rlockowner->rl_owner;
- unsigned int hashval = ownerstr_hashval(clid->cl_id, owner);
+ unsigned int hashval = ownerstr_hashval(owner);
__be32 status;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
struct nfs4_client *clp;
@@ -5386,29 +5379,29 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
status = nfserr_locks_held;
+ clp = cstate->clp;
/* Find the matching lock stateowner */
- spin_lock(&nn->client_lock);
- list_for_each_entry(tmp, &nn->ownerstr_hashtbl[hashval], so_strhash) {
+ spin_lock(&clp->cl_lock);
+ list_for_each_entry(tmp, &clp->cl_ownerstr_hashtbl[hashval],
+ so_strhash) {
if (tmp->so_is_open_owner)
continue;
- if (same_owner_str(tmp, owner, clid)) {
+ if (same_owner_str(tmp, owner)) {
sop = tmp;
atomic_inc(&sop->so_count);
break;
}
}
- spin_unlock(&nn->client_lock);
/* No matching owner found, maybe a replay? Just declare victory... */
if (!sop) {
+ spin_unlock(&clp->cl_lock);
status = nfs_ok;
goto out;
}
lo = lockowner(sop);
/* see if there are still any locks associated with it */
- clp = cstate->clp;
- spin_lock(&clp->cl_lock);
list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) {
if (check_for_locks(stp->st_stid.sc_file, lo)) {
spin_unlock(&clp->cl_lock);
@@ -5747,10 +5740,6 @@ static int nfs4_state_create_net(struct net *net)
CLIENT_HASH_SIZE, GFP_KERNEL);
if (!nn->unconf_id_hashtbl)
goto err_unconf_id;
- nn->ownerstr_hashtbl = kmalloc(sizeof(struct list_head) *
- OWNER_HASH_SIZE, GFP_KERNEL);
- if (!nn->ownerstr_hashtbl)
- goto err_ownerstr;
nn->sessionid_hashtbl = kmalloc(sizeof(struct list_head) *
SESSION_HASH_SIZE, GFP_KERNEL);
if (!nn->sessionid_hashtbl)
@@ -5760,8 +5749,6 @@ static int nfs4_state_create_net(struct net *net)
INIT_LIST_HEAD(&nn->conf_id_hashtbl[i]);
INIT_LIST_HEAD(&nn->unconf_id_hashtbl[i]);
}
- for (i = 0; i < OWNER_HASH_SIZE; i++)
- INIT_LIST_HEAD(&nn->ownerstr_hashtbl[i]);
for (i = 0; i < SESSION_HASH_SIZE; i++)
INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]);
nn->conf_name_tree = RB_ROOT;
@@ -5777,8 +5764,6 @@ static int nfs4_state_create_net(struct net *net)
return 0;
err_sessionid:
- kfree(nn->ownerstr_hashtbl);
-err_ownerstr:
kfree(nn->unconf_id_hashtbl);
err_unconf_id:
kfree(nn->conf_id_hashtbl);
@@ -5808,7 +5793,6 @@ nfs4_state_destroy_net(struct net *net)
}
kfree(nn->sessionid_hashtbl);
- kfree(nn->ownerstr_hashtbl);
kfree(nn->unconf_id_hashtbl);
kfree(nn->conf_id_hashtbl);
put_net(net);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 9e9e45278b40..7e395f665b0f 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -237,6 +237,7 @@ struct nfsd4_sessionid {
struct nfs4_client {
struct list_head cl_idhash; /* hash by cl_clientid.id */
struct rb_node cl_namenode; /* link into by-name trees */
+ struct list_head *cl_ownerstr_hashtbl;
struct list_head cl_openowners;
struct idr cl_stateids; /* stateid lookup */
struct list_head cl_delegations;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 070/114] nfsd: clean up and reorganize release_lockowner
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (68 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 069/114] nfsd: Move the open owner hash table into struct nfs4_client Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 071/114] lockdep: add lockdep_assert_not_held Jeff Layton
` (43 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Do more within the main loop, and simplify the function a bit. Also,
there's no need to take a stateowner reference unless we're going to call
release_lockowner.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 49 ++++++++++++++++++-------------------------------
1 file changed, 18 insertions(+), 31 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 1bd7b2b0a4b1..4f82e502f53a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5359,8 +5359,8 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
struct nfsd4_release_lockowner *rlockowner)
{
clientid_t *clid = &rlockowner->rl_clientid;
- struct nfs4_stateowner *sop = NULL, *tmp;
- struct nfs4_lockowner *lo;
+ struct nfs4_stateowner *sop;
+ struct nfs4_lockowner *lo = NULL;
struct nfs4_ol_stateid *stp;
struct xdr_netobj *owner = &rlockowner->rl_owner;
unsigned int hashval = ownerstr_hashval(owner);
@@ -5377,45 +5377,32 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
if (status)
goto out;
- status = nfserr_locks_held;
-
clp = cstate->clp;
/* Find the matching lock stateowner */
spin_lock(&clp->cl_lock);
- list_for_each_entry(tmp, &clp->cl_ownerstr_hashtbl[hashval],
+ list_for_each_entry(sop, &clp->cl_ownerstr_hashtbl[hashval],
so_strhash) {
- if (tmp->so_is_open_owner)
- continue;
- if (same_owner_str(tmp, owner)) {
- sop = tmp;
- atomic_inc(&sop->so_count);
- break;
- }
- }
- /* No matching owner found, maybe a replay? Just declare victory... */
- if (!sop) {
- spin_unlock(&clp->cl_lock);
- status = nfs_ok;
- goto out;
- }
+ if (sop->so_is_open_owner || !same_owner_str(sop, owner))
+ continue;
- lo = lockowner(sop);
- /* see if there are still any locks associated with it */
- list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) {
- if (check_for_locks(stp->st_stid.sc_file, lo)) {
- spin_unlock(&clp->cl_lock);
- goto out;
+ /* see if there are still any locks associated with it */
+ lo = lockowner(sop);
+ list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) {
+ if (check_for_locks(stp->st_stid.sc_file, lo)) {
+ status = nfserr_locks_held;
+ spin_unlock(&clp->cl_lock);
+ goto out;
+ }
}
+
+ atomic_inc(&sop->so_count);
+ break;
}
spin_unlock(&clp->cl_lock);
-
- status = nfs_ok;
- sop = NULL;
- release_lockowner(lo);
+ if (lo)
+ release_lockowner(lo);
out:
- if (sop)
- nfs4_put_stateowner(sop);
nfs4_unlock_state();
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 071/114] lockdep: add lockdep_assert_not_held
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (69 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 070/114] nfsd: clean up and reorganize release_lockowner Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-07-01 10:03 ` Peter Zijlstra
2014-06-30 15:49 ` [PATCH v3 072/114] nfsd: add locking to stateowner release Jeff Layton
` (42 subsequent siblings)
113 siblings, 1 reply; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Peter Zijlstra, Ingo Molnar
We currently have the ability to call lockdep_assert_held to throw a
warning when a spinlock isn't held in a codepath. There are also times
when we'd like to throw a warning when a lock is held (i.e. when there
is the potential for deadlock with atomic_dec_and_lock or similar).
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 4 ++++
include/linux/lockdep.h | 4 ++++
2 files changed, 8 insertions(+)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4f82e502f53a..1446cbfc42b4 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -263,6 +263,8 @@ static void nfsd4_free_file(struct nfs4_file *f)
static inline void
put_nfs4_file(struct nfs4_file *fi)
{
+ lockdep_assert_not_held(&state_lock);
+
if (atomic_dec_and_lock(&fi->fi_ref, &state_lock)) {
hlist_del(&fi->fi_hash);
spin_unlock(&state_lock);
@@ -420,6 +422,8 @@ static __be32 nfs4_file_check_deny(struct nfs4_file *fp, u32 deny)
static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag)
{
+ lockdep_assert_not_held(&fp->fi_lock);
+
if (atomic_dec_and_lock(&fp->fi_access[oflag], &fp->fi_lock)) {
struct file *f1 = NULL;
struct file *f2 = NULL;
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 008388f920d7..1e5f1d544029 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -362,6 +362,8 @@ extern void lockdep_trace_alloc(gfp_t mask);
WARN_ON(debug_locks && !lockdep_is_held(l)); \
} while (0)
+#define lockdep_assert_not_held(l) WARN_ON(debug_locks && lockdep_is_held(l))
+
#define lockdep_recursing(tsk) ((tsk)->lockdep_recursion)
#else /* !CONFIG_LOCKDEP */
@@ -413,6 +415,8 @@ struct lock_class_key { };
#define lockdep_assert_held(l) do { (void)(l); } while (0)
+#define lockdep_assert_not_held(l) (void)(l)
+
#define lockdep_recursing(tsk) (0)
#endif /* !LOCKDEP */
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* Re: [PATCH v3 071/114] lockdep: add lockdep_assert_not_held
2014-06-30 15:49 ` [PATCH v3 071/114] lockdep: add lockdep_assert_not_held Jeff Layton
@ 2014-07-01 10:03 ` Peter Zijlstra
2014-07-01 10:11 ` Peter Zijlstra
0 siblings, 1 reply; 151+ messages in thread
From: Peter Zijlstra @ 2014-07-01 10:03 UTC (permalink / raw)
To: Jeff Layton; +Cc: bfields, linux-nfs, Ingo Molnar
[-- Attachment #1: Type: text/plain, Size: 539 bytes --]
On Mon, Jun 30, 2014 at 11:49:40AM -0400, Jeff Layton wrote:
> We currently have the ability to call lockdep_assert_held to throw a
> warning when a spinlock isn't held in a codepath. There are also times
> when we'd like to throw a warning when a lock is held (i.e. when there
> is the potential for deadlock with atomic_dec_and_lock or similar).
So I'm not getting it; if there's deadlock potential, lockdep would
already report so, right?
That is, lockdep is very good a yelling when you try to acquire a lock
you're already holding.
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 071/114] lockdep: add lockdep_assert_not_held
2014-07-01 10:03 ` Peter Zijlstra
@ 2014-07-01 10:11 ` Peter Zijlstra
2014-07-01 10:41 ` Jeff Layton
0 siblings, 1 reply; 151+ messages in thread
From: Peter Zijlstra @ 2014-07-01 10:11 UTC (permalink / raw)
To: Jeff Layton; +Cc: bfields, linux-nfs, Ingo Molnar
[-- Attachment #1: Type: text/plain, Size: 870 bytes --]
On Tue, Jul 01, 2014 at 12:03:35PM +0200, Peter Zijlstra wrote:
> On Mon, Jun 30, 2014 at 11:49:40AM -0400, Jeff Layton wrote:
> > We currently have the ability to call lockdep_assert_held to throw a
> > warning when a spinlock isn't held in a codepath. There are also times
> > when we'd like to throw a warning when a lock is held (i.e. when there
> > is the potential for deadlock with atomic_dec_and_lock or similar).
>
> So I'm not getting it; if there's deadlock potential, lockdep would
> already report so, right?
>
> That is, lockdep is very good a yelling when you try to acquire a lock
> you're already holding.
Ah, I think I see what you're trying to do.
You're wanting to use might_lock() and might_lock_read(). Which are used
to make conditional lock acquisitions unconditional, so as to more
reliably trigger the deadlock detection.
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 071/114] lockdep: add lockdep_assert_not_held
2014-07-01 10:11 ` Peter Zijlstra
@ 2014-07-01 10:41 ` Jeff Layton
2014-07-01 11:07 ` Peter Zijlstra
0 siblings, 1 reply; 151+ messages in thread
From: Jeff Layton @ 2014-07-01 10:41 UTC (permalink / raw)
To: Peter Zijlstra; +Cc: bfields, linux-nfs, Ingo Molnar
On Tue, 1 Jul 2014 12:11:08 +0200
Peter Zijlstra <peterz@infradead.org> wrote:
> On Tue, Jul 01, 2014 at 12:03:35PM +0200, Peter Zijlstra wrote:
> > On Mon, Jun 30, 2014 at 11:49:40AM -0400, Jeff Layton wrote:
> > > We currently have the ability to call lockdep_assert_held to throw a
> > > warning when a spinlock isn't held in a codepath. There are also times
> > > when we'd like to throw a warning when a lock is held (i.e. when there
> > > is the potential for deadlock with atomic_dec_and_lock or similar).
> >
> > So I'm not getting it; if there's deadlock potential, lockdep would
> > already report so, right?
> >
> > That is, lockdep is very good a yelling when you try to acquire a lock
> > you're already holding.
>
> Ah, I think I see what you're trying to do.
>
> You're wanting to use might_lock() and might_lock_read(). Which are used
> to make conditional lock acquisitions unconditional, so as to more
> reliably trigger the deadlock detection.
Right -- in the case of something like atomic_dec_and_lock, we only
take the spinlock if we think the count might go to zero. So, we might
miss catching some places that could deadlock if the refcounts don't go
to zero in the testing we're doing.
might_lock may be what we need, but I don't see any callers of it, and
at a quick glance it doesn't appear to be disabled if debug_locks is
false.
--
Jeff Layton <jlayton@primarydata.com>
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 071/114] lockdep: add lockdep_assert_not_held
2014-07-01 10:41 ` Jeff Layton
@ 2014-07-01 11:07 ` Peter Zijlstra
2014-07-01 11:10 ` Jeff Layton
0 siblings, 1 reply; 151+ messages in thread
From: Peter Zijlstra @ 2014-07-01 11:07 UTC (permalink / raw)
To: Jeff Layton; +Cc: bfields, linux-nfs, Ingo Molnar
[-- Attachment #1: Type: text/plain, Size: 747 bytes --]
On Tue, Jul 01, 2014 at 06:41:11AM -0400, Jeff Layton wrote:
> Right -- in the case of something like atomic_dec_and_lock, we only
> take the spinlock if we think the count might go to zero. So, we might
> miss catching some places that could deadlock if the refcounts don't go
> to zero in the testing we're doing.
>
> might_lock may be what we need, but I don't see any callers of it,
might_fault()
might_lock_read(¤t->mm->mmap_sem)
I'm not sure we have others; but this is the one I remember providing
this for.
> and
> at a quick glance it doesn't appear to be disabled if debug_locks is
> false.
The whole of lockdep gets killed, and that would include the
lock_acquire/lock_release used to implement these.
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply [flat|nested] 151+ messages in thread
* Re: [PATCH v3 071/114] lockdep: add lockdep_assert_not_held
2014-07-01 11:07 ` Peter Zijlstra
@ 2014-07-01 11:10 ` Jeff Layton
0 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-07-01 11:10 UTC (permalink / raw)
To: Peter Zijlstra; +Cc: Jeff Layton, bfields, linux-nfs, Ingo Molnar
On Tue, 1 Jul 2014 13:07:18 +0200
Peter Zijlstra <peterz@infradead.org> wrote:
> On Tue, Jul 01, 2014 at 06:41:11AM -0400, Jeff Layton wrote:
> > Right -- in the case of something like atomic_dec_and_lock, we only
> > take the spinlock if we think the count might go to zero. So, we might
> > miss catching some places that could deadlock if the refcounts don't go
> > to zero in the testing we're doing.
> >
> > might_lock may be what we need, but I don't see any callers of it,
>
> might_fault()
> might_lock_read(¤t->mm->mmap_sem)
>
> I'm not sure we have others; but this is the one I remember providing
> this for.
>
> > and
> > at a quick glance it doesn't appear to be disabled if debug_locks is
> > false.
>
> The whole of lockdep gets killed, and that would include the
> lock_acquire/lock_release used to implement these.
Ok, good. Let's just drop this patch then and I'll plan to use
might_lock instead of this call.
Thanks!
--
Jeff Layton <jlayton@primarydata.com>
^ permalink raw reply [flat|nested] 151+ messages in thread
* [PATCH v3 072/114] nfsd: add locking to stateowner release
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (70 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 071/114] lockdep: add lockdep_assert_not_held Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 073/114] nfsd: optimize destroy_lockowner cl_lock thrashing Jeff Layton
` (41 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Once we remove the client_mutex, we'll need to properly protect
the stateowner reference counts using the cl_lock.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 17 ++++++++---------
1 file changed, 8 insertions(+), 9 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 1446cbfc42b4..90e92f671900 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -638,6 +638,8 @@ static void nfs4_put_stid(struct nfs4_stid *s)
{
struct nfs4_client *clp = s->sc_client;
+ lockdep_assert_not_held(&clp->cl_lock);
+
if (!atomic_dec_and_lock(&s->sc_count, &clp->cl_lock)) {
wake_up_all(&close_wq);
return;
@@ -3012,9 +3014,14 @@ static inline void *alloc_stateowner(struct kmem_cache *slab, struct xdr_netobj
static void nfs4_put_stateowner(struct nfs4_stateowner *sop)
{
- if (!atomic_dec_and_test(&sop->so_count))
+ struct nfs4_client *clp = sop->so_client;
+
+ lockdep_assert_not_held(&clp->cl_lock);
+
+ if (!atomic_dec_and_lock(&sop->so_count, &clp->cl_lock))
return;
sop->so_unhash(sop);
+ spin_unlock(&clp->cl_lock);
sop->so_free(sop);
}
@@ -3029,11 +3036,7 @@ static void hash_openowner(struct nfs4_openowner *oo, struct nfs4_client *clp, u
static void nfs4_unhash_openowner(struct nfs4_stateowner *so)
{
- struct nfs4_client *clp = so->so_client;
-
- spin_lock(&clp->cl_lock);
unhash_openowner_locked(openowner(so));
- spin_unlock(&clp->cl_lock);
}
static void nfs4_free_openowner(struct nfs4_stateowner *so)
@@ -4799,11 +4802,7 @@ find_lockowner_str(clientid_t *clid, struct xdr_netobj *owner,
static void nfs4_unhash_lockowner(struct nfs4_stateowner *sop)
{
- struct nfs4_client *clp = sop->so_client;
-
- spin_lock(&clp->cl_lock);
unhash_lockowner_locked(lockowner(sop));
- spin_unlock(&clp->cl_lock);
}
static void nfs4_free_lockowner(struct nfs4_stateowner *sop)
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 073/114] nfsd: optimize destroy_lockowner cl_lock thrashing
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (71 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 072/114] nfsd: add locking to stateowner release Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 074/114] nfsd: close potential race in nfsd4_free_stateid Jeff Layton
` (40 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Reduce the cl_lock trashing in destroy_lockowner. Unhash all of the
lockstateids on the lockowner's list. Put the reference under the lock
and see if it was the last one. If so, then add it to a private list
to be destroyed after we drop the lock.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 50 +++++++++++++++++++++++++++++++++-----------------
1 file changed, 33 insertions(+), 17 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 90e92f671900..e840d41fe2c9 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -920,14 +920,23 @@ static void put_generic_stateid(struct nfs4_ol_stateid *stp)
nfs4_put_stid(&stp->st_stid);
}
-static void release_lock_stateid(struct nfs4_ol_stateid *stp)
+static void unhash_lock_stateid(struct nfs4_ol_stateid *stp)
{
struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
- spin_lock(&oo->oo_owner.so_client->cl_lock);
- list_del(&stp->st_locks);
+ lockdep_assert_held(&oo->oo_owner.so_client->cl_lock);
+
+ list_del_init(&stp->st_locks);
unhash_generic_stateid(stp);
unhash_stid(&stp->st_stid);
+}
+
+static void release_lock_stateid(struct nfs4_ol_stateid *stp)
+{
+ struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
+
+ spin_lock(&oo->oo_owner.so_client->cl_lock);
+ unhash_lock_stateid(stp);
spin_unlock(&oo->oo_owner.so_client->cl_lock);
put_generic_stateid(stp);
}
@@ -941,30 +950,37 @@ static void unhash_lockowner_locked(struct nfs4_lockowner *lo)
list_del_init(&lo->lo_owner.so_strhash);
}
-static void release_lockowner_stateids(struct nfs4_lockowner *lo)
+static void release_lockowner(struct nfs4_lockowner *lo)
{
struct nfs4_client *clp = lo->lo_owner.so_client;
struct nfs4_ol_stateid *stp;
+ struct list_head reaplist;
- lockdep_assert_held(&clp->cl_lock);
+ INIT_LIST_HEAD(&reaplist);
+ spin_lock(&clp->cl_lock);
+ unhash_lockowner_locked(lo);
while (!list_empty(&lo->lo_owner.so_stateids)) {
stp = list_first_entry(&lo->lo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
- spin_unlock(&clp->cl_lock);
- release_lock_stateid(stp);
- spin_lock(&clp->cl_lock);
+ unhash_lock_stateid(stp);
+ /*
+ * We now know that no new references can be added to the
+ * stateid. If ours is the last one, finish the unhashing
+ * and put it on the list to be reaped.
+ */
+ if (atomic_dec_and_test(&stp->st_stid.sc_count)) {
+ remove_stid_locked(clp, &stp->st_stid);
+ list_add(&stp->st_locks, &reaplist);
+ }
}
-}
-
-static void release_lockowner(struct nfs4_lockowner *lo)
-{
- struct nfs4_client *clp = lo->lo_owner.so_client;
-
- spin_lock(&clp->cl_lock);
- unhash_lockowner_locked(lo);
- release_lockowner_stateids(lo);
spin_unlock(&clp->cl_lock);
+ while (!list_empty(&reaplist)) {
+ stp = list_first_entry(&reaplist, struct nfs4_ol_stateid,
+ st_locks);
+ list_del(&stp->st_locks);
+ stp->st_stid.sc_free(&stp->st_stid);
+ }
nfs4_put_stateowner(&lo->lo_owner);
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 074/114] nfsd: close potential race in nfsd4_free_stateid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (72 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 073/114] nfsd: optimize destroy_lockowner cl_lock thrashing Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 075/114] nfsd: reduce cl_lock thrashing in release_openowner Jeff Layton
` (39 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Once we remove the client_mutex, it'll be possible for the sc_type of a
lock stateid to change after it's found and checked, but before we can
go to destroy it. If that happens, we can end up putting the persistent
reference to the stateid more than once, and unhash it more than once.
Fix this by unhashing the lock stateid prior to dropping the cl_lock but
after finding it.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 24 +++++++++---------------
1 file changed, 9 insertions(+), 15 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e840d41fe2c9..0f56fb179e8a 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4357,17 +4357,6 @@ unlock_state:
return status;
}
-static __be32
-nfsd4_free_lock_stateid(struct nfs4_ol_stateid *stp)
-{
- struct nfs4_lockowner *lo = lockowner(stp->st_stateowner);
-
- if (check_for_locks(stp->st_stid.sc_file, lo))
- return nfserr_locks_held;
- release_lock_stateid(stp);
- return nfs_ok;
-}
-
/*
* Test if the stateid is valid
*/
@@ -4394,6 +4383,7 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
stateid_t *stateid = &free_stateid->fr_stateid;
struct nfs4_stid *s;
struct nfs4_delegation *dp;
+ struct nfs4_ol_stateid *stp;
struct nfs4_client *cl = cstate->session->se_client;
__be32 ret = nfserr_bad_stateid;
@@ -4411,12 +4401,16 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
ret = check_stateid_generation(stateid, &s->sc_stateid, 1);
if (ret)
break;
- if (s->sc_type != NFS4_LOCK_STID) {
- ret = nfserr_locks_held;
+ stp = openlockstateid(s);
+ ret = nfserr_locks_held;
+ if (s->sc_type == NFS4_OPEN_STID ||
+ check_for_locks(s->sc_file,
+ lockowner(stp->st_stateowner)))
break;
- }
+ unhash_lock_stateid(stp);
spin_unlock(&cl->cl_lock);
- ret = nfsd4_free_lock_stateid(openlockstateid(s));
+ put_generic_stateid(stp);
+ ret = nfs_ok;
goto out;
case NFS4_REVOKED_DELEG_STID:
spin_unlock(&cl->cl_lock);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 075/114] nfsd: reduce cl_lock thrashing in release_openowner
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (73 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 074/114] nfsd: close potential race in nfsd4_free_stateid Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 076/114] nfsd: don't thrash the cl_lock while freeing an open stateid Jeff Layton
` (38 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Releasing an openowner is a bit inefficient as it can potentially thrash
the cl_lock if you have a lot of stateids attached to it. Once we remove
the client_mutex, it'll also potentially be dangerous to do this.
Add some functions to make it easier to defer the part of putting a
generic stateid reference that needs to be done outside the cl_lock while
doing the parts that must be done while holding it under a single lock.
First we unhash each open stateid. Then we call
put_generic_stateid_locked which will put the reference to an
nfs4_ol_stateid. If it turns out to be the last reference, it'll go
ahead and remove the stid from the IDR tree and put it onto the reaplist
using the st_locks list_head.
Then, after dropping the lock we'll call free_stateid_reaplist to walk
the list of stateids that are fully unhashed and ready to be freed, and
free each of them. This function can sleep, so it must be done outside
any spinlocks.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 95 +++++++++++++++++++++++++++++++++++------------------
1 file changed, 63 insertions(+), 32 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 0f56fb179e8a..7ef64e090436 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -920,6 +920,30 @@ static void put_generic_stateid(struct nfs4_ol_stateid *stp)
nfs4_put_stid(&stp->st_stid);
}
+/*
+ * Put the persistent reference to an already unhashed generic stateid, while
+ * holding the cl_lock. If it's the last reference, then put it onto the
+ * reaplist for later destruction.
+ */
+static void put_generic_stateid_locked(struct nfs4_ol_stateid *stp,
+ struct list_head *reaplist)
+{
+ struct nfs4_stid *s = &stp->st_stid;
+ struct nfs4_client *clp = s->sc_client;
+
+ lockdep_assert_held(&clp->cl_lock);
+
+ WARN_ON_ONCE(!list_empty(&stp->st_locks));
+
+ if (!atomic_dec_and_test(&s->sc_count)) {
+ wake_up_all(&close_wq);
+ return;
+ }
+
+ remove_stid_locked(clp, s);
+ list_add(&stp->st_locks, reaplist);
+}
+
static void unhash_lock_stateid(struct nfs4_ol_stateid *stp)
{
struct nfs4_openowner *oo = openowner(stp->st_openstp->st_stateowner);
@@ -950,6 +974,25 @@ static void unhash_lockowner_locked(struct nfs4_lockowner *lo)
list_del_init(&lo->lo_owner.so_strhash);
}
+/*
+ * Free a list of generic stateids that were collected earlier after being
+ * fully unhashed.
+ */
+static void
+free_stateid_reaplist(struct list_head *reaplist)
+{
+ struct nfs4_ol_stateid *stp;
+
+ might_sleep();
+
+ while (!list_empty(reaplist)) {
+ stp = list_first_entry(reaplist, struct nfs4_ol_stateid,
+ st_locks);
+ list_del(&stp->st_locks);
+ stp->st_stid.sc_free(&stp->st_stid);
+ }
+}
+
static void release_lockowner(struct nfs4_lockowner *lo)
{
struct nfs4_client *clp = lo->lo_owner.so_client;
@@ -964,23 +1007,10 @@ static void release_lockowner(struct nfs4_lockowner *lo)
stp = list_first_entry(&lo->lo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
unhash_lock_stateid(stp);
- /*
- * We now know that no new references can be added to the
- * stateid. If ours is the last one, finish the unhashing
- * and put it on the list to be reaped.
- */
- if (atomic_dec_and_test(&stp->st_stid.sc_count)) {
- remove_stid_locked(clp, &stp->st_stid);
- list_add(&stp->st_locks, &reaplist);
- }
+ put_generic_stateid_locked(stp, &reaplist);
}
spin_unlock(&clp->cl_lock);
- while (!list_empty(&reaplist)) {
- stp = list_first_entry(&reaplist, struct nfs4_ol_stateid,
- st_locks);
- list_del(&stp->st_locks);
- stp->st_stid.sc_free(&stp->st_stid);
- }
+ free_stateid_reaplist(&reaplist);
nfs4_put_stateowner(&lo->lo_owner);
}
@@ -1001,16 +1031,21 @@ static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp)
static void unhash_open_stateid(struct nfs4_ol_stateid *stp)
{
- spin_lock(&stp->st_stateowner->so_client->cl_lock);
+ lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);
+
unhash_generic_stateid(stp);
release_open_stateid_locks(stp);
- spin_unlock(&stp->st_stateowner->so_client->cl_lock);
}
static void release_open_stateid(struct nfs4_ol_stateid *stp)
{
+ LIST_HEAD(reaplist);
+
+ spin_lock(&stp->st_stid.sc_client->cl_lock);
unhash_open_stateid(stp);
- put_generic_stateid(stp);
+ put_generic_stateid_locked(stp, &reaplist);
+ spin_unlock(&stp->st_stid.sc_client->cl_lock);
+ free_stateid_reaplist(&reaplist);
}
static void unhash_openowner_locked(struct nfs4_openowner *oo)
@@ -1034,30 +1069,24 @@ static void release_last_closed_stateid(struct nfs4_openowner *oo)
}
}
-static void release_openowner_stateids(struct nfs4_openowner *oo)
+static void release_openowner(struct nfs4_openowner *oo)
{
struct nfs4_ol_stateid *stp;
struct nfs4_client *clp = oo->oo_owner.so_client;
+ struct list_head reaplist;
- lockdep_assert_held(&clp->cl_lock);
+ INIT_LIST_HEAD(&reaplist);
+ spin_lock(&clp->cl_lock);
+ unhash_openowner_locked(oo);
while (!list_empty(&oo->oo_owner.so_stateids)) {
stp = list_first_entry(&oo->oo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
- spin_unlock(&clp->cl_lock);
- release_open_stateid(stp);
- spin_lock(&clp->cl_lock);
+ unhash_open_stateid(stp);
+ put_generic_stateid_locked(stp, &reaplist);
}
-}
-
-static void release_openowner(struct nfs4_openowner *oo)
-{
- struct nfs4_client *clp = oo->oo_owner.so_client;
-
- spin_lock(&clp->cl_lock);
- unhash_openowner_locked(oo);
- release_openowner_stateids(oo);
spin_unlock(&clp->cl_lock);
+ free_stateid_reaplist(&reaplist);
release_last_closed_stateid(oo);
nfs4_put_stateowner(&oo->oo_owner);
}
@@ -4630,7 +4659,9 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
struct nfs4_client *clp = s->st_stid.sc_client;
s->st_stid.sc_type = NFS4_CLOSED_STID;
+ spin_lock(&clp->cl_lock);
unhash_open_stateid(s);
+ spin_unlock(&clp->cl_lock);
if (clp->cl_minorversion)
put_generic_stateid(s);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 076/114] nfsd: don't thrash the cl_lock while freeing an open stateid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (74 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 075/114] nfsd: reduce cl_lock thrashing in release_openowner Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 077/114] nfsd: Ensure struct nfs4_client is unhashed before we try to destroy it Jeff Layton
` (37 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
When we remove the client_mutex, we'll have a potential race between
FREE_STATEID and CLOSE.
The root of the problem is that we are walking the st_locks list,
dropping the spinlock and then trying to release the persistent
reference to the lockstateid. In between, a FREE_STATEID call can come
along and take the lock, find the stateid and then try to put the
reference. That leads to a double put.
Fix this by not releasing the cl_lock in order to release each lock
stateid. Use put_generic_stateid_locked to unhash them and gather
them onto a list, and free_stateid_reaplist to free any that end up
on the list.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 34 +++++++++++++++++++---------------
1 file changed, 19 insertions(+), 15 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 7ef64e090436..9bb2336467f9 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1014,27 +1014,26 @@ static void release_lockowner(struct nfs4_lockowner *lo)
nfs4_put_stateowner(&lo->lo_owner);
}
-static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp)
- __releases(&open_stp->st_stateowner->so_client->cl_lock)
- __acquires(&open_stp->st_stateowner->so_client->cl_lock)
+static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp,
+ struct list_head *reaplist)
{
struct nfs4_ol_stateid *stp;
while (!list_empty(&open_stp->st_locks)) {
stp = list_entry(open_stp->st_locks.next,
struct nfs4_ol_stateid, st_locks);
- spin_unlock(&open_stp->st_stateowner->so_client->cl_lock);
- release_lock_stateid(stp);
- spin_lock(&open_stp->st_stateowner->so_client->cl_lock);
+ unhash_lock_stateid(stp);
+ put_generic_stateid_locked(stp, reaplist);
}
}
-static void unhash_open_stateid(struct nfs4_ol_stateid *stp)
+static void unhash_open_stateid(struct nfs4_ol_stateid *stp,
+ struct list_head *reaplist)
{
lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);
unhash_generic_stateid(stp);
- release_open_stateid_locks(stp);
+ release_open_stateid_locks(stp, reaplist);
}
static void release_open_stateid(struct nfs4_ol_stateid *stp)
@@ -1042,7 +1041,7 @@ static void release_open_stateid(struct nfs4_ol_stateid *stp)
LIST_HEAD(reaplist);
spin_lock(&stp->st_stid.sc_client->cl_lock);
- unhash_open_stateid(stp);
+ unhash_open_stateid(stp, &reaplist);
put_generic_stateid_locked(stp, &reaplist);
spin_unlock(&stp->st_stid.sc_client->cl_lock);
free_stateid_reaplist(&reaplist);
@@ -1082,7 +1081,7 @@ static void release_openowner(struct nfs4_openowner *oo)
while (!list_empty(&oo->oo_owner.so_stateids)) {
stp = list_first_entry(&oo->oo_owner.so_stateids,
struct nfs4_ol_stateid, st_perstateowner);
- unhash_open_stateid(stp);
+ unhash_open_stateid(stp, &reaplist);
put_generic_stateid_locked(stp, &reaplist);
}
spin_unlock(&clp->cl_lock);
@@ -4657,16 +4656,21 @@ out:
static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
{
struct nfs4_client *clp = s->st_stid.sc_client;
+ LIST_HEAD(reaplist);
s->st_stid.sc_type = NFS4_CLOSED_STID;
spin_lock(&clp->cl_lock);
- unhash_open_stateid(s);
- spin_unlock(&clp->cl_lock);
+ unhash_open_stateid(s, &reaplist);
- if (clp->cl_minorversion)
- put_generic_stateid(s);
- else
+ if (clp->cl_minorversion) {
+ put_generic_stateid_locked(s, &reaplist);
+ spin_unlock(&clp->cl_lock);
+ free_stateid_reaplist(&reaplist);
+ } else {
+ spin_unlock(&clp->cl_lock);
+ free_stateid_reaplist(&reaplist);
move_to_close_lru(s, clp->net);
+ }
}
/*
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 077/114] nfsd: Ensure struct nfs4_client is unhashed before we try to destroy it
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (75 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 076/114] nfsd: don't thrash the cl_lock while freeing an open stateid Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 078/114] nfsd: Ensure that the laundromat unhashes the client before releasing locks Jeff Layton
` (36 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
When we remove the client_mutex protection, we will need to ensure
that it can't be found by other threads while we're destroying it.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 43 +++++++++++++++++++++++++++++++++----------
1 file changed, 33 insertions(+), 10 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9bb2336467f9..db35f7893b37 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1529,12 +1529,23 @@ free_client(struct nfs4_client *clp)
}
/* must be called under the client_lock */
-static inline void
+static void
unhash_client_locked(struct nfs4_client *clp)
{
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct nfsd4_session *ses;
- list_del(&clp->cl_lru);
+ /* Mark the client as expired! */
+ clp->cl_time = 0;
+ /* Make it invisible */
+ if (!list_empty(&clp->cl_idhash)) {
+ list_del_init(&clp->cl_idhash);
+ if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
+ rb_erase(&clp->cl_namenode, &nn->conf_name_tree);
+ else
+ rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
+ }
+ list_del_init(&clp->cl_lru);
spin_lock(&clp->cl_lock);
list_for_each_entry(ses, &clp->cl_sessions, se_perclnt)
list_del_init(&ses->se_hash);
@@ -1542,7 +1553,17 @@ unhash_client_locked(struct nfs4_client *clp)
}
static void
-destroy_client(struct nfs4_client *clp)
+unhash_client(struct nfs4_client *clp)
+{
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ spin_lock(&nn->client_lock);
+ unhash_client_locked(clp);
+ spin_unlock(&nn->client_lock);
+}
+
+static void
+__destroy_client(struct nfs4_client *clp)
{
struct nfs4_openowner *oo;
struct nfs4_delegation *dp;
@@ -1575,22 +1596,24 @@ destroy_client(struct nfs4_client *clp)
nfsd4_shutdown_callback(clp);
if (clp->cl_cb_conn.cb_xprt)
svc_xprt_put(clp->cl_cb_conn.cb_xprt);
- list_del(&clp->cl_idhash);
- if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags))
- rb_erase(&clp->cl_namenode, &nn->conf_name_tree);
- else
- rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
spin_lock(&nn->client_lock);
- unhash_client_locked(clp);
WARN_ON_ONCE(atomic_read(&clp->cl_refcount));
free_client(clp);
spin_unlock(&nn->client_lock);
}
+static void
+destroy_client(struct nfs4_client *clp)
+{
+ unhash_client(clp);
+ __destroy_client(clp);
+}
+
static void expire_client(struct nfs4_client *clp)
{
+ unhash_client(clp);
nfsd4_client_record_remove(clp);
- destroy_client(clp);
+ __destroy_client(clp);
}
static void copy_verf(struct nfs4_client *target, nfs4_verifier *source)
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 078/114] nfsd: Ensure that the laundromat unhashes the client before releasing locks
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (76 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 077/114] nfsd: Ensure struct nfs4_client is unhashed before we try to destroy it Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 079/114] nfsd: Don't require client_lock in free_client Jeff Layton
` (35 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
If we leave the client on the confirmed/unconfirmed tables, and leave
the sessions visible on the sessionid_hashtbl, then someone might
find them before we've had a chance to destroy them.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index db35f7893b37..77f516c907e7 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4088,13 +4088,15 @@ nfs4_laundromat(struct nfsd_net *nn)
clp->cl_clientid.cl_id);
continue;
}
- list_move(&clp->cl_lru, &reaplist);
+ unhash_client_locked(clp);
+ list_add(&clp->cl_lru, &reaplist);
}
spin_unlock(&nn->client_lock);
list_for_each_safe(pos, next, &reaplist) {
clp = list_entry(pos, struct nfs4_client, cl_lru);
dprintk("NFSD: purging unused client (clientid %08x)\n",
clp->cl_clientid.cl_id);
+ list_del_init(&clp->cl_lru);
expire_client(clp);
}
spin_lock(&state_lock);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 079/114] nfsd: Don't require client_lock in free_client
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (77 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 078/114] nfsd: Ensure that the laundromat unhashes the client before releasing locks Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 080/114] nfsd: Move create_client() call outside the lock Jeff Layton
` (34 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
The struct nfs_client is supposed to be invisible and unreferenced
before it gets here.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 13 -------------
1 file changed, 13 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 77f516c907e7..e107f0c8ea74 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1355,9 +1355,6 @@ static void __free_session(struct nfsd4_session *ses)
static void free_session(struct nfsd4_session *ses)
{
- struct nfsd_net *nn = net_generic(ses->se_client->net, nfsd_net_id);
-
- lockdep_assert_held(&nn->client_lock);
nfsd4_del_conns(ses);
nfsd4_put_drc_mem(&ses->se_fchannel);
__free_session(ses);
@@ -1507,9 +1504,6 @@ err_no_name:
static void
free_client(struct nfs4_client *clp)
{
- struct nfsd_net __maybe_unused *nn = net_generic(clp->net, nfsd_net_id);
-
- lockdep_assert_held(&nn->client_lock);
while (!list_empty(&clp->cl_sessions)) {
struct nfsd4_session *ses;
ses = list_entry(clp->cl_sessions.next, struct nfsd4_session,
@@ -1568,7 +1562,6 @@ __destroy_client(struct nfs4_client *clp)
struct nfs4_openowner *oo;
struct nfs4_delegation *dp;
struct list_head reaplist;
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
INIT_LIST_HEAD(&reaplist);
spin_lock(&state_lock);
@@ -1596,10 +1589,7 @@ __destroy_client(struct nfs4_client *clp)
nfsd4_shutdown_callback(clp);
if (clp->cl_cb_conn.cb_xprt)
svc_xprt_put(clp->cl_cb_conn.cb_xprt);
- spin_lock(&nn->client_lock);
- WARN_ON_ONCE(atomic_read(&clp->cl_refcount));
free_client(clp);
- spin_unlock(&nn->client_lock);
}
static void
@@ -1802,7 +1792,6 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
struct sockaddr *sa = svc_addr(rqstp);
int ret;
struct net *net = SVC_NET(rqstp);
- struct nfsd_net *nn = net_generic(net, nfsd_net_id);
clp = alloc_client(name);
if (clp == NULL)
@@ -1810,9 +1799,7 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
ret = copy_cred(&clp->cl_cred, &rqstp->rq_cred);
if (ret) {
- spin_lock(&nn->client_lock);
free_client(clp);
- spin_unlock(&nn->client_lock);
return NULL;
}
clp->cl_time = get_seconds();
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 080/114] nfsd: Move create_client() call outside the lock
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (78 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 079/114] nfsd: Don't require client_lock in free_client Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 081/114] nfsd: Protect unconfirmed client creation using client_lock Jeff Layton
` (33 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
For efficiency reasons, and because we want to use spin locks instead
of relying on the client_mutex.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 35 +++++++++++++++++++----------------
1 file changed, 19 insertions(+), 16 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e107f0c8ea74..d85985171cdd 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2120,6 +2120,10 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
return nfserr_encr_alg_unsupp;
}
+ new = create_client(exid->clname, rqstp, &verf);
+ if (new == NULL)
+ return nfserr_jukebox;
+
/* Cases below refer to rfc 5661 section 18.35.4: */
nfs4_lock_state();
conf = find_confirmed_client_by_name(&exid->clname, nn);
@@ -2146,7 +2150,6 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
}
/* case 6 */
exid->flags |= EXCHGID4_FLAG_CONFIRMED_R;
- new = conf;
goto out_copy;
}
if (!creds_match) { /* case 3 */
@@ -2159,7 +2162,6 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
}
if (verfs_match) { /* case 2 */
conf->cl_exchange_flags |= EXCHGID4_FLAG_CONFIRMED_R;
- new = conf;
goto out_copy;
}
/* case 5, client reboot */
@@ -2177,29 +2179,28 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
/* case 1 (normal case) */
out_new:
- new = create_client(exid->clname, rqstp, &verf);
- if (new == NULL) {
- status = nfserr_jukebox;
- goto out;
- }
new->cl_minorversion = cstate->minorversion;
new->cl_mach_cred = (exid->spa_how == SP4_MACH_CRED);
gen_clid(new, nn);
add_to_unconfirmed(new);
+ conf = new;
+ new = NULL;
out_copy:
- exid->clientid.cl_boot = new->cl_clientid.cl_boot;
- exid->clientid.cl_id = new->cl_clientid.cl_id;
+ exid->clientid.cl_boot = conf->cl_clientid.cl_boot;
+ exid->clientid.cl_id = conf->cl_clientid.cl_id;
- exid->seqid = new->cl_cs_slot.sl_seqid + 1;
- nfsd4_set_ex_flags(new, exid);
+ exid->seqid = conf->cl_cs_slot.sl_seqid + 1;
+ nfsd4_set_ex_flags(conf, exid);
dprintk("nfsd4_exchange_id seqid %d flags %x\n",
- new->cl_cs_slot.sl_seqid, new->cl_exchange_flags);
+ conf->cl_cs_slot.sl_seqid, conf->cl_exchange_flags);
status = nfs_ok;
out:
nfs4_unlock_state();
+ if (new)
+ free_client(new);
return status;
}
@@ -2842,6 +2843,9 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
__be32 status;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+ new = create_client(clname, rqstp, &clverifier);
+ if (new == NULL)
+ return nfserr_jukebox;
/* Cases below refer to rfc 3530 section 14.2.33: */
nfs4_lock_state();
conf = find_confirmed_client_by_name(&clname, nn);
@@ -2862,10 +2866,6 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
unconf = find_unconfirmed_client_by_name(&clname, nn);
if (unconf)
expire_client(unconf);
- status = nfserr_jukebox;
- new = create_client(clname, rqstp, &clverifier);
- if (new == NULL)
- goto out;
if (conf && same_verf(&conf->cl_verifier, &clverifier))
/* case 1: probable callback update */
copy_clid(new, conf);
@@ -2877,9 +2877,12 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
setclid->se_clientid.cl_boot = new->cl_clientid.cl_boot;
setclid->se_clientid.cl_id = new->cl_clientid.cl_id;
memcpy(setclid->se_confirm.data, new->cl_confirm.data, sizeof(setclid->se_confirm.data));
+ new = NULL;
status = nfs_ok;
out:
nfs4_unlock_state();
+ if (new)
+ free_client(new);
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 081/114] nfsd: Protect unconfirmed client creation using client_lock
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (79 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 080/114] nfsd: Move create_client() call outside the lock Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 082/114] nfsd: Protect session creation and client confirm " Jeff Layton
` (32 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
...instead of relying on the client_mutex.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 33 ++++++++++++++++++++++-----------
1 file changed, 22 insertions(+), 11 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d85985171cdd..8ec86da6eff8 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1862,7 +1862,7 @@ add_to_unconfirmed(struct nfs4_client *clp)
add_clp_to_name_tree(clp, &nn->unconf_name_tree);
idhashval = clientid_hashval(clp->cl_clientid.cl_id);
list_add(&clp->cl_idhash, &nn->unconf_id_hashtbl[idhashval]);
- renew_client(clp);
+ renew_client_locked(clp);
}
static void
@@ -1876,7 +1876,7 @@ move_to_confirmed(struct nfs4_client *clp)
rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
add_clp_to_name_tree(clp, &nn->conf_name_tree);
set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags);
- renew_client(clp);
+ renew_client_locked(clp);
}
static struct nfs4_client *
@@ -1889,7 +1889,7 @@ find_client_in_id_table(struct list_head *tbl, clientid_t *clid, bool sessions)
if (same_clid(&clp->cl_clientid, clid)) {
if ((bool)clp->cl_minorversion != sessions)
return NULL;
- renew_client(clp);
+ renew_client_locked(clp);
return clp;
}
}
@@ -2091,7 +2091,8 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
struct nfsd4_compound_state *cstate,
struct nfsd4_exchange_id *exid)
{
- struct nfs4_client *unconf, *conf, *new;
+ struct nfs4_client *conf, *new;
+ struct nfs4_client *unconf = NULL;
__be32 status;
char addr_str[INET6_ADDRSTRLEN];
nfs4_verifier verf = exid->verifier;
@@ -2126,6 +2127,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
/* Cases below refer to rfc 5661 section 18.35.4: */
nfs4_lock_state();
+ spin_lock(&nn->client_lock);
conf = find_confirmed_client_by_name(&exid->clname, nn);
if (conf) {
bool creds_match = same_creds(&conf->cl_cred, &rqstp->rq_cred);
@@ -2157,7 +2159,6 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
status = nfserr_clid_inuse;
goto out;
}
- expire_client(conf);
goto out_new;
}
if (verfs_match) { /* case 2 */
@@ -2165,6 +2166,7 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
goto out_copy;
}
/* case 5, client reboot */
+ conf = NULL;
goto out_new;
}
@@ -2175,17 +2177,18 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
unconf = find_unconfirmed_client_by_name(&exid->clname, nn);
if (unconf) /* case 4, possible retry or client restart */
- expire_client(unconf);
+ unhash_client_locked(unconf);
/* case 1 (normal case) */
out_new:
+ if (conf)
+ unhash_client_locked(conf);
new->cl_minorversion = cstate->minorversion;
new->cl_mach_cred = (exid->spa_how == SP4_MACH_CRED);
gen_clid(new, nn);
add_to_unconfirmed(new);
- conf = new;
- new = NULL;
+ swap(new, conf);
out_copy:
exid->clientid.cl_boot = conf->cl_clientid.cl_boot;
exid->clientid.cl_id = conf->cl_clientid.cl_id;
@@ -2198,9 +2201,12 @@ out_copy:
status = nfs_ok;
out:
+ spin_unlock(&nn->client_lock);
nfs4_unlock_state();
if (new)
- free_client(new);
+ expire_client(new);
+ if (unconf)
+ expire_client(unconf);
return status;
}
@@ -2839,7 +2845,8 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
{
struct xdr_netobj clname = setclid->se_name;
nfs4_verifier clverifier = setclid->se_verf;
- struct nfs4_client *conf, *unconf, *new;
+ struct nfs4_client *conf, *new;
+ struct nfs4_client *unconf = NULL;
__be32 status;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
@@ -2848,6 +2855,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return nfserr_jukebox;
/* Cases below refer to rfc 3530 section 14.2.33: */
nfs4_lock_state();
+ spin_lock(&nn->client_lock);
conf = find_confirmed_client_by_name(&clname, nn);
if (conf) {
/* case 0: */
@@ -2865,7 +2873,7 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
}
unconf = find_unconfirmed_client_by_name(&clname, nn);
if (unconf)
- expire_client(unconf);
+ unhash_client_locked(unconf);
if (conf && same_verf(&conf->cl_verifier, &clverifier))
/* case 1: probable callback update */
copy_clid(new, conf);
@@ -2880,9 +2888,12 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
new = NULL;
status = nfs_ok;
out:
+ spin_unlock(&nn->client_lock);
nfs4_unlock_state();
if (new)
free_client(new);
+ if (unconf)
+ expire_client(unconf);
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 082/114] nfsd: Protect session creation and client confirm using client_lock
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (80 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 081/114] nfsd: Protect unconfirmed client creation using client_lock Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 083/114] nfsd: Protect nfsd4_destroy_clientid " Jeff Layton
` (31 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
In particular, we want to ensure that the move_to_confirmed() is
protected by the nn->client_lock spin lock, so that we can use that when
looking up the clientid etc. instead of relying on the client_mutex.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 65 ++++++++++++++++++++++++++++++++---------------------
1 file changed, 39 insertions(+), 26 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 8ec86da6eff8..10d78a6cd158 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -141,17 +141,6 @@ static __be32 mark_client_expired_locked(struct nfs4_client *clp)
return nfs_ok;
}
-static __be32 mark_client_expired(struct nfs4_client *clp)
-{
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
- __be32 ret;
-
- spin_lock(&nn->client_lock);
- ret = mark_client_expired_locked(clp);
- spin_unlock(&nn->client_lock);
- return ret;
-}
-
static __be32 get_client_locked(struct nfs4_client *clp)
{
if (is_client_expired(clp))
@@ -1376,12 +1365,10 @@ static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, stru
new->se_cb_sec = cses->cb_sec;
atomic_set(&new->se_ref, 0);
idx = hash_sessionid(&new->se_sessionid);
- spin_lock(&nn->client_lock);
list_add(&new->se_hash, &nn->sessionid_hashtbl[idx]);
spin_lock(&clp->cl_lock);
list_add(&new->se_perclnt, &clp->cl_sessions);
spin_unlock(&clp->cl_lock);
- spin_unlock(&nn->client_lock);
if (cses->flags & SESSION4_BACK_CHAN) {
struct sockaddr *sa = svc_addr(rqstp);
@@ -2350,6 +2337,7 @@ nfsd4_create_session(struct svc_rqst *rqstp,
{
struct sockaddr *sa = svc_addr(rqstp);
struct nfs4_client *conf, *unconf;
+ struct nfs4_client *old = NULL;
struct nfsd4_session *new;
struct nfsd4_conn *conn;
struct nfsd4_clid_slot *cs_slot = NULL;
@@ -2376,6 +2364,7 @@ nfsd4_create_session(struct svc_rqst *rqstp,
goto out_free_session;
nfs4_lock_state();
+ spin_lock(&nn->client_lock);
unconf = find_unconfirmed_client(&cr_ses->clientid, true, nn);
conf = find_confirmed_client(&cr_ses->clientid, true, nn);
WARN_ON_ONCE(conf && unconf);
@@ -2394,7 +2383,6 @@ nfsd4_create_session(struct svc_rqst *rqstp,
goto out_free_conn;
}
} else if (unconf) {
- struct nfs4_client *old;
if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) ||
!rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) {
status = nfserr_clid_inuse;
@@ -2412,10 +2400,10 @@ nfsd4_create_session(struct svc_rqst *rqstp,
}
old = find_confirmed_client_by_name(&unconf->cl_name, nn);
if (old) {
- status = mark_client_expired(old);
+ status = mark_client_expired_locked(old);
if (status)
goto out_free_conn;
- expire_client(old);
+ unhash_client_locked(old);
}
move_to_confirmed(unconf);
conf = unconf;
@@ -2431,20 +2419,29 @@ nfsd4_create_session(struct svc_rqst *rqstp,
cr_ses->flags &= ~SESSION4_RDMA;
init_session(rqstp, new, conf, cr_ses);
- nfsd4_init_conn(rqstp, conn, new);
+ nfsd4_get_session_locked(new);
memcpy(cr_ses->sessionid.data, new->se_sessionid.data,
NFS4_MAX_SESSIONID_LEN);
cs_slot->sl_seqid++;
cr_ses->seqid = cs_slot->sl_seqid;
- /* cache solo and embedded create sessions under the state lock */
+ /* cache solo and embedded create sessions under the client_lock */
nfsd4_cache_create_session(cr_ses, cs_slot, status);
+ spin_unlock(&nn->client_lock);
+ /* init connection and backchannel */
+ nfsd4_init_conn(rqstp, conn, new);
+ nfsd4_put_session(new);
nfs4_unlock_state();
+ if (old)
+ expire_client(old);
return status;
out_free_conn:
+ spin_unlock(&nn->client_lock);
nfs4_unlock_state();
free_conn(conn);
+ if (old)
+ expire_client(old);
out_free_session:
__free_session(new);
out_release_drc_mem:
@@ -2904,6 +2901,7 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
struct nfsd4_setclientid_confirm *setclientid_confirm)
{
struct nfs4_client *conf, *unconf;
+ struct nfs4_client *old = NULL;
nfs4_verifier confirm = setclientid_confirm->sc_confirm;
clientid_t * clid = &setclientid_confirm->sc_clientid;
__be32 status;
@@ -2913,6 +2911,7 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
return nfserr_stale_clientid;
nfs4_lock_state();
+ spin_lock(&nn->client_lock);
conf = find_confirmed_client(clid, false, nn);
unconf = find_unconfirmed_client(clid, false, nn);
/*
@@ -2936,21 +2935,29 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
}
status = nfs_ok;
if (conf) { /* case 1: callback update */
+ old = unconf;
+ unhash_client_locked(old);
nfsd4_change_callback(conf, &unconf->cl_cb_conn);
- nfsd4_probe_callback(conf);
- expire_client(unconf);
} else { /* case 3: normal case; new or rebooted client */
- conf = find_confirmed_client_by_name(&unconf->cl_name, nn);
- if (conf) {
- status = mark_client_expired(conf);
+ old = find_confirmed_client_by_name(&unconf->cl_name, nn);
+ if (old) {
+ status = mark_client_expired_locked(old);
if (status)
goto out;
- expire_client(conf);
+ unhash_client_locked(old);
}
move_to_confirmed(unconf);
- nfsd4_probe_callback(unconf);
+ conf = unconf;
}
+ get_client_locked(conf);
+ spin_unlock(&nn->client_lock);
+ nfsd4_probe_callback(conf);
+ spin_lock(&nn->client_lock);
+ put_client_renew_locked(conf);
out:
+ spin_unlock(&nn->client_lock);
+ if (old)
+ expire_client(old);
nfs4_unlock_state();
return status;
}
@@ -5586,7 +5593,13 @@ nfs4_check_open_reclaim(clientid_t *clid,
u64 nfsd_forget_client(struct nfs4_client *clp, u64 max)
{
- if (mark_client_expired(clp))
+ __be32 ret;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ spin_lock(&nn->client_lock);
+ ret = mark_client_expired_locked(clp);
+ spin_unlock(&nn->client_lock);
+ if (ret != nfs_ok)
return 0;
expire_client(clp);
return 1;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 083/114] nfsd: Protect nfsd4_destroy_clientid using client_lock
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (81 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 082/114] nfsd: Protect session creation and client confirm " Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 084/114] nfsd: Ensure lookup_clientid() takes client_lock Jeff Layton
` (30 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
...instead of relying on the client_mutex.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 10d78a6cd158..e8d92b468218 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2765,22 +2765,23 @@ nfsd4_sequence_done(struct nfsd4_compoundres *resp)
__be32
nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_destroy_clientid *dc)
{
- struct nfs4_client *conf, *unconf, *clp;
+ struct nfs4_client *conf, *unconf;
+ struct nfs4_client *clp = NULL;
__be32 status = 0;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
nfs4_lock_state();
+ spin_lock(&nn->client_lock);
unconf = find_unconfirmed_client(&dc->clientid, true, nn);
conf = find_confirmed_client(&dc->clientid, true, nn);
WARN_ON_ONCE(conf && unconf);
if (conf) {
- clp = conf;
-
if (client_has_state(conf)) {
status = nfserr_clientid_busy;
goto out;
}
+ clp = conf;
} else if (unconf)
clp = unconf;
else {
@@ -2788,12 +2789,16 @@ nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
goto out;
}
if (!mach_creds_match(clp, rqstp)) {
+ clp = NULL;
status = nfserr_wrong_cred;
goto out;
}
- expire_client(clp);
+ unhash_client_locked(clp);
out:
+ spin_unlock(&nn->client_lock);
nfs4_unlock_state();
+ if (clp)
+ expire_client(clp);
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 084/114] nfsd: Ensure lookup_clientid() takes client_lock
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (82 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 083/114] nfsd: Protect nfsd4_destroy_clientid " Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 085/114] nfsd: Add lockdep assertions to document the nfs4_client/session locking Jeff Layton
` (29 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Ensure that the client lookup is done safely under the client_lock, so
we're not relying on the client_mutex.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index e8d92b468218..dd7667008554 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3430,13 +3430,17 @@ static __be32 lookup_clientid(clientid_t *clid,
* will be false.
*/
WARN_ON_ONCE(cstate->session);
+ spin_lock(&nn->client_lock);
found = find_confirmed_client(clid, false, nn);
- if (!found)
+ if (!found) {
+ spin_unlock(&nn->client_lock);
return nfserr_expired;
+ }
+ atomic_inc(&found->cl_refcount);
+ spin_unlock(&nn->client_lock);
/* Cache the nfs4_client in cstate! */
cstate->clp = found;
- atomic_inc(&found->cl_refcount);
return nfs_ok;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 085/114] nfsd: Add lockdep assertions to document the nfs4_client/session locking
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (83 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 084/114] nfsd: Ensure lookup_clientid() takes client_lock Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 086/114] nfsd: protect the close_lru list and oo_last_closed_stid with client_lock Jeff Layton
` (28 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 30 ++++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index dd7667008554..b215911cc67c 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -143,6 +143,10 @@ static __be32 mark_client_expired_locked(struct nfs4_client *clp)
static __be32 get_client_locked(struct nfs4_client *clp)
{
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ lockdep_assert_held(&nn->client_lock);
+
if (is_client_expired(clp))
return nfserr_expired;
atomic_inc(&clp->cl_refcount);
@@ -183,6 +187,10 @@ renew_client(struct nfs4_client *clp)
static void put_client_renew_locked(struct nfs4_client *clp)
{
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ lockdep_assert_held(&nn->client_lock);
+
if (!atomic_dec_and_test(&clp->cl_refcount))
return;
if (!is_client_expired(clp))
@@ -214,6 +222,9 @@ static __be32 nfsd4_get_session_locked(struct nfsd4_session *ses)
static void nfsd4_put_session_locked(struct nfsd4_session *ses)
{
struct nfs4_client *clp = ses->se_client;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ lockdep_assert_held(&nn->client_lock);
if (atomic_dec_and_test(&ses->se_ref) && is_session_dead(ses))
free_session(ses);
@@ -1392,6 +1403,8 @@ __find_in_sessionid_hashtbl(struct nfs4_sessionid *sessionid, struct net *net)
int idx;
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+ lockdep_assert_held(&nn->client_lock);
+
dump_sessionid(__func__, sessionid);
idx = hash_sessionid(sessionid);
/* Search in the appropriate list */
@@ -1428,6 +1441,11 @@ out:
static void
unhash_session(struct nfsd4_session *ses)
{
+ struct nfs4_client *clp = ses->se_client;
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ lockdep_assert_held(&nn->client_lock);
+
list_del(&ses->se_hash);
spin_lock(&ses->se_client->cl_lock);
list_del(&ses->se_perclnt);
@@ -1516,6 +1534,8 @@ unhash_client_locked(struct nfs4_client *clp)
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
struct nfsd4_session *ses;
+ lockdep_assert_held(&nn->client_lock);
+
/* Mark the client as expired! */
clp->cl_time = 0;
/* Make it invisible */
@@ -1845,6 +1865,8 @@ add_to_unconfirmed(struct nfs4_client *clp)
unsigned int idhashval;
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+ lockdep_assert_held(&nn->client_lock);
+
clear_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags);
add_clp_to_name_tree(clp, &nn->unconf_name_tree);
idhashval = clientid_hashval(clp->cl_clientid.cl_id);
@@ -1858,6 +1880,8 @@ move_to_confirmed(struct nfs4_client *clp)
unsigned int idhashval = clientid_hashval(clp->cl_clientid.cl_id);
struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+ lockdep_assert_held(&nn->client_lock);
+
dprintk("NFSD: move_to_confirm nfs4_client %p\n", clp);
list_move(&clp->cl_idhash, &nn->conf_id_hashtbl[idhashval]);
rb_erase(&clp->cl_namenode, &nn->unconf_name_tree);
@@ -1888,6 +1912,7 @@ find_confirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn)
{
struct list_head *tbl = nn->conf_id_hashtbl;
+ lockdep_assert_held(&nn->client_lock);
return find_client_in_id_table(tbl, clid, sessions);
}
@@ -1896,6 +1921,7 @@ find_unconfirmed_client(clientid_t *clid, bool sessions, struct nfsd_net *nn)
{
struct list_head *tbl = nn->unconf_id_hashtbl;
+ lockdep_assert_held(&nn->client_lock);
return find_client_in_id_table(tbl, clid, sessions);
}
@@ -1907,12 +1933,14 @@ static bool clp_used_exchangeid(struct nfs4_client *clp)
static struct nfs4_client *
find_confirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn)
{
+ lockdep_assert_held(&nn->client_lock);
return find_clp_in_name_tree(name, &nn->conf_name_tree);
}
static struct nfs4_client *
find_unconfirmed_client_by_name(struct xdr_netobj *name, struct nfsd_net *nn)
{
+ lockdep_assert_held(&nn->client_lock);
return find_clp_in_name_tree(name, &nn->unconf_name_tree);
}
@@ -4863,6 +4891,8 @@ find_lockowner_str_locked(clientid_t *clid, struct xdr_netobj *owner,
unsigned int strhashval = ownerstr_hashval(owner);
struct nfs4_stateowner *so;
+ lockdep_assert_held(&clp->cl_lock);
+
list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[strhashval],
so_strhash) {
if (so->so_is_open_owner)
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 086/114] nfsd: protect the close_lru list and oo_last_closed_stid with client_lock
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (84 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 085/114] nfsd: Add lockdep assertions to document the nfs4_client/session locking Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 087/114] nfsd: ensure that clp->cl_revoked list is protected by clp->cl_lock Jeff Layton
` (27 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Currently, it's protected by the client_mutex. Move it so that the list
and the fields in the openowner are protected by the client_lock.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 37 ++++++++++++++++++++++++++++++-------
1 file changed, 30 insertions(+), 7 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b215911cc67c..9a8f9ab37d19 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1059,13 +1059,19 @@ static void unhash_openowner_locked(struct nfs4_openowner *oo)
static void release_last_closed_stateid(struct nfs4_openowner *oo)
{
- struct nfs4_ol_stateid *s = oo->oo_last_closed_stid;
+ struct nfsd_net *nn = net_generic(oo->oo_owner.so_client->net,
+ nfsd_net_id);
+ struct nfs4_ol_stateid *s;
+ spin_lock(&nn->client_lock);
+ s = oo->oo_last_closed_stid;
if (s) {
list_del_init(&oo->oo_close_lru);
oo->oo_last_closed_stid = NULL;
- put_generic_stateid(s);
}
+ spin_unlock(&nn->client_lock);
+ if (s)
+ put_generic_stateid(s);
}
static void release_openowner(struct nfs4_openowner *oo)
@@ -3217,6 +3223,7 @@ static void init_open_stateid(struct nfs4_ol_stateid *stp, struct nfs4_file *fp,
static void
move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
{
+ struct nfs4_ol_stateid *last;
struct nfs4_openowner *oo = openowner(s->st_stateowner);
struct nfsd_net *nn = net_generic(s->st_stid.sc_client->net,
nfsd_net_id);
@@ -3240,10 +3247,14 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net)
s->st_stid.sc_file = NULL;
}
- release_last_closed_stateid(oo);
+ spin_lock(&nn->client_lock);
+ last = oo->oo_last_closed_stid;
oo->oo_last_closed_stid = s;
list_move_tail(&oo->oo_close_lru, &nn->close_lru);
oo->oo_time = get_seconds();
+ spin_unlock(&nn->client_lock);
+ if (last)
+ put_generic_stateid(last);
}
static int
@@ -4111,6 +4122,7 @@ nfs4_laundromat(struct nfsd_net *nn)
struct nfs4_client *clp;
struct nfs4_openowner *oo;
struct nfs4_delegation *dp;
+ struct nfs4_ol_stateid *stp;
struct list_head *pos, *next, reaplist;
time_t cutoff = get_seconds() - nn->nfsd4_lease;
time_t t, new_timeo = nn->nfsd4_lease;
@@ -4162,15 +4174,26 @@ nfs4_laundromat(struct nfsd_net *nn)
dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
revoke_delegation(dp);
}
- list_for_each_safe(pos, next, &nn->close_lru) {
- oo = container_of(pos, struct nfs4_openowner, oo_close_lru);
- if (time_after((unsigned long)oo->oo_time, (unsigned long)cutoff)) {
+
+ spin_lock(&nn->client_lock);
+ while (!list_empty(&nn->close_lru)) {
+ oo = list_first_entry(&nn->close_lru, struct nfs4_openowner,
+ oo_close_lru);
+ if (time_after((unsigned long)oo->oo_time,
+ (unsigned long)cutoff)) {
t = oo->oo_time - cutoff;
new_timeo = min(new_timeo, t);
break;
}
- release_last_closed_stateid(oo);
+ list_del_init(&oo->oo_close_lru);
+ stp = oo->oo_last_closed_stid;
+ oo->oo_last_closed_stid = NULL;
+ spin_unlock(&nn->client_lock);
+ put_generic_stateid(stp);
+ spin_lock(&nn->client_lock);
}
+ spin_unlock(&nn->client_lock);
+
new_timeo = max_t(time_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
nfs4_unlock_state();
return new_timeo;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 087/114] nfsd: ensure that clp->cl_revoked list is protected by clp->cl_lock
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (85 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 086/114] nfsd: protect the close_lru list and oo_last_closed_stid with client_lock Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 088/114] nfsd: move unhash_client_locked call into mark_client_expired_locked Jeff Layton
` (26 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Currently, both destroy_revoked_delegation and revoke_delegation
manipulate the cl_revoked list without any locking aside from the
client_mutex. Ensure that the clp->cl_lock is held when manipulating it,
except for the list walking in destroy_client. At that point, the client
should no longer be in use, and so it should be safe to walk the list
without any locking. That also means that we don't need to do the
list_splice_init there either.
Also, the fact that destroy_revoked_delegation and revoke_delegation
delete dl_recall_lru without any locking makes it difficult to know
whether they're doing so safely in all cases. Move the list_del_init
calls into the callers, and add WARN_ONs in the event that these calls
are passed a delegation that has a non-empty list_head.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 21 ++++++++++++++-------
1 file changed, 14 insertions(+), 7 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9a8f9ab37d19..5194ebb0a56f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -724,7 +724,7 @@ static void unhash_and_destroy_delegation(struct nfs4_delegation *dp)
static void destroy_revoked_delegation(struct nfs4_delegation *dp)
{
- list_del_init(&dp->dl_recall_lru);
+ WARN_ON(!list_empty(&dp->dl_recall_lru));
nfs4_put_delegation(dp);
}
@@ -732,11 +732,15 @@ static void revoke_delegation(struct nfs4_delegation *dp)
{
struct nfs4_client *clp = dp->dl_stid.sc_client;
+ WARN_ON(!list_empty(&dp->dl_recall_lru));
+
if (clp->cl_minorversion == 0)
destroy_revoked_delegation(dp);
else {
dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID;
- list_move(&dp->dl_recall_lru, &clp->cl_revoked);
+ spin_lock(&clp->cl_lock);
+ list_add(&dp->dl_recall_lru, &clp->cl_revoked);
+ spin_unlock(&clp->cl_lock);
}
}
@@ -1589,9 +1593,9 @@ __destroy_client(struct nfs4_client *clp)
list_del_init(&dp->dl_recall_lru);
destroy_delegation(dp);
}
- list_splice_init(&clp->cl_revoked, &reaplist);
- while (!list_empty(&reaplist)) {
+ while (!list_empty(&clp->cl_revoked)) {
dp = list_entry(reaplist.next, struct nfs4_delegation, dl_recall_lru);
+ list_del_init(&dp->dl_recall_lru);
destroy_revoked_delegation(dp);
}
while (!list_empty(&clp->cl_openowners)) {
@@ -4170,8 +4174,10 @@ nfs4_laundromat(struct nfsd_net *nn)
list_add(&dp->dl_recall_lru, &reaplist);
}
spin_unlock(&state_lock);
- list_for_each_safe(pos, next, &reaplist) {
- dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru);
+ while (!list_empty(&reaplist)) {
+ dp = list_first_entry(&reaplist, struct nfs4_delegation,
+ dl_recall_lru);
+ list_del_init(&dp->dl_recall_lru);
revoke_delegation(dp);
}
@@ -4534,8 +4540,9 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
ret = nfs_ok;
goto out;
case NFS4_REVOKED_DELEG_STID:
- spin_unlock(&cl->cl_lock);
dp = delegstateid(s);
+ list_del_init(&dp->dl_recall_lru);
+ spin_unlock(&cl->cl_lock);
destroy_revoked_delegation(dp);
ret = nfs_ok;
goto out;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 088/114] nfsd: move unhash_client_locked call into mark_client_expired_locked
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (86 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 087/114] nfsd: ensure that clp->cl_revoked list is protected by clp->cl_lock Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 089/114] nfsd: don't destroy client if mark_client_expired_locked fails Jeff Layton
` (25 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
All the callers except for the fault injection code call it directly
afterward, and in the fault injection case it won't hurt to do so
anyway.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 5194ebb0a56f..75d0f5cec1b1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -70,6 +70,7 @@ static u64 current_sessionid = 1;
#define CURRENT_STATEID(stateid) (!memcmp((stateid), ¤tstateid, sizeof(stateid_t)))
/* forward declarations */
+static void unhash_client_locked(struct nfs4_client *clp);
static int check_for_locks(struct nfs4_file *filp, struct nfs4_lockowner *lowner);
static void nfs4_free_generic_stateid(struct nfs4_stid *stid);
static struct nfs4_openowner *find_openstateowner_str_locked(
@@ -137,7 +138,7 @@ static __be32 mark_client_expired_locked(struct nfs4_client *clp)
{
if (atomic_read(&clp->cl_refcount))
return nfserr_jukebox;
- clp->cl_time = 0;
+ unhash_client_locked(clp);
return nfs_ok;
}
@@ -2441,7 +2442,6 @@ nfsd4_create_session(struct svc_rqst *rqstp,
status = mark_client_expired_locked(old);
if (status)
goto out_free_conn;
- unhash_client_locked(old);
}
move_to_confirmed(unconf);
conf = unconf;
@@ -2987,7 +2987,6 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
status = mark_client_expired_locked(old);
if (status)
goto out;
- unhash_client_locked(old);
}
move_to_confirmed(unconf);
conf = unconf;
@@ -4149,7 +4148,6 @@ nfs4_laundromat(struct nfsd_net *nn)
clp->cl_clientid.cl_id);
continue;
}
- unhash_client_locked(clp);
list_add(&clp->cl_lru, &reaplist);
}
spin_unlock(&nn->client_lock);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 089/114] nfsd: don't destroy client if mark_client_expired_locked fails
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (87 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 088/114] nfsd: move unhash_client_locked call into mark_client_expired_locked Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:49 ` [PATCH v3 090/114] nfsd: don't destroy clients that are busy Jeff Layton
` (24 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
If it fails, it means that the client is in use and so destroying it
would be bad. Currently, the client_mutex prevents this from happening
but once we remove it, we won't be able to do this.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 75d0f5cec1b1..4c7b1326046e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2440,8 +2440,10 @@ nfsd4_create_session(struct svc_rqst *rqstp,
old = find_confirmed_client_by_name(&unconf->cl_name, nn);
if (old) {
status = mark_client_expired_locked(old);
- if (status)
+ if (status) {
+ old = NULL;
goto out_free_conn;
+ }
}
move_to_confirmed(unconf);
conf = unconf;
@@ -2985,8 +2987,10 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
old = find_confirmed_client_by_name(&unconf->cl_name, nn);
if (old) {
status = mark_client_expired_locked(old);
- if (status)
+ if (status) {
+ old = NULL;
goto out;
+ }
}
move_to_confirmed(unconf);
conf = unconf;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 090/114] nfsd: don't destroy clients that are busy
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (88 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 089/114] nfsd: don't destroy client if mark_client_expired_locked fails Jeff Layton
@ 2014-06-30 15:49 ` Jeff Layton
2014-06-30 15:50 ` [PATCH v3 091/114] nfsd: protect clid and verifier generation with client_lock Jeff Layton
` (23 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:49 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
It's possible that we'll have an in-progress call on some of the clients
while a rogue EXCHANGE_ID or DESTROY_CLIENTID call comes in. Be sure to
try and mark the client expired first, so that the refcount is
respected.
This will only be a problem once the client_mutex is removed.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4c7b1326046e..0298dac8009c 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2207,8 +2207,11 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
/* case 1 (normal case) */
out_new:
- if (conf)
- unhash_client_locked(conf);
+ if (conf) {
+ status = mark_client_expired_locked(conf);
+ if (status)
+ goto out;
+ }
new->cl_minorversion = cstate->minorversion;
new->cl_mach_cred = (exid->spa_how == SP4_MACH_CRED);
@@ -2821,6 +2824,9 @@ nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
status = nfserr_clientid_busy;
goto out;
}
+ status = mark_client_expired_locked(conf);
+ if (status)
+ goto out;
clp = conf;
} else if (unconf)
clp = unconf;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 091/114] nfsd: protect clid and verifier generation with client_lock
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (89 preceding siblings ...)
2014-06-30 15:49 ` [PATCH v3 090/114] nfsd: don't destroy clients that are busy Jeff Layton
@ 2014-06-30 15:50 ` Jeff Layton
2014-06-30 15:50 ` [PATCH v3 092/114] nfsd: abstract out the get and set routines into the fault injection ops Jeff Layton
` (22 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:50 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
The clid counter is a global counter currently. Move it to be a per-net
property so that it can be properly protected by the nn->client_lock
instead of relying on the client_mutex.
The verifier generator is also potentially racy if there are two
simultaneous callers. Generate the verifier when we generate the clid
value, so it's also created under the client_lock. With this, there's
no need to keep two counters as they'd always be in sync anyway, so
just use the clientid_counter for both.
As Trond points out, what would be best is to eventually move this
code to use IDR instead of the hash tables. That would also help ensure
uniqueness, but that's probably best done as a separate project.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/netns.h | 6 +++---
fs/nfsd/nfs4state.c | 21 +++++++++------------
2 files changed, 12 insertions(+), 15 deletions(-)
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index f89042ae0056..831abbdc6c52 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -92,11 +92,11 @@ struct nfsd_net {
bool nfsd_net_up;
bool lockd_up;
- /*
- * Time of server startup
- */
+ /* Time of server startup */
struct timeval nfssvc_boot;
+ u32 clientid_counter;
+
struct svc_serv *nfsd_serv;
};
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 0298dac8009c..4799d6e652d0 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1754,28 +1754,26 @@ static bool mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp)
return 0 == strcmp(cl->cl_cred.cr_principal, cr->cr_principal);
}
-static void gen_clid(struct nfs4_client *clp, struct nfsd_net *nn)
-{
- static u32 current_clientid = 1;
-
- clp->cl_clientid.cl_boot = nn->boot_time;
- clp->cl_clientid.cl_id = current_clientid++;
-}
-
-static void gen_confirm(struct nfs4_client *clp)
+static void gen_confirm(struct nfs4_client *clp, struct nfsd_net *nn)
{
__be32 verf[2];
- static u32 i;
/*
* This is opaque to client, so no need to byte-swap. Use
* __force to keep sparse happy
*/
verf[0] = (__force __be32)get_seconds();
- verf[1] = (__force __be32)i++;
+ verf[1] = (__force __be32)nn->clientid_counter;
memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data));
}
+static void gen_clid(struct nfs4_client *clp, struct nfsd_net *nn)
+{
+ clp->cl_clientid.cl_boot = nn->boot_time;
+ clp->cl_clientid.cl_id = nn->clientid_counter++;
+ gen_confirm(clp, nn);
+}
+
static struct nfs4_stid *
find_stateid_locked(struct nfs4_client *cl, stateid_t *t)
{
@@ -1824,7 +1822,6 @@ static struct nfs4_client *create_client(struct xdr_netobj name,
clear_bit(0, &clp->cl_cb_slot_busy);
copy_verf(clp, verf);
rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa);
- gen_confirm(clp);
clp->cl_cb_session = NULL;
clp->net = net;
return clp;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 092/114] nfsd: abstract out the get and set routines into the fault injection ops
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (90 preceding siblings ...)
2014-06-30 15:50 ` [PATCH v3 091/114] nfsd: protect clid and verifier generation with client_lock Jeff Layton
@ 2014-06-30 15:50 ` Jeff Layton
2014-06-30 15:50 ` [PATCH v3 093/114] nfsd: add a forget_clients "get" routine with proper locking Jeff Layton
` (21 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:50 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Now that we've added more granular locking in other places, it's time
to address the fault injection code. This code is currently quite
reliant on the client_mutex for protection. Start to change this by
adding a new set of fault injection op vectors.
For now they all use the legacy ones. In later patches we'll add new
routines that can deal with more granular locking.
Also, move some of the printk routines into the callers to make the
results of the operations more uniform.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/fault_inject.c | 129 ++++++++++++++++++++++++++++++-------------------
1 file changed, 78 insertions(+), 51 deletions(-)
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index f1333fc35b33..b1159900d934 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -17,79 +17,50 @@
struct nfsd_fault_inject_op {
char *file;
+ u64 (*get)(struct nfsd_fault_inject_op *);
+ u64 (*set_val)(struct nfsd_fault_inject_op *, u64);
+ u64 (*set_clnt)(struct nfsd_fault_inject_op *,
+ struct sockaddr_storage *, size_t);
u64 (*forget)(struct nfs4_client *, u64);
u64 (*print)(struct nfs4_client *, u64);
};
-static struct nfsd_fault_inject_op inject_ops[] = {
- {
- .file = "forget_clients",
- .forget = nfsd_forget_client,
- .print = nfsd_print_client,
- },
- {
- .file = "forget_locks",
- .forget = nfsd_forget_client_locks,
- .print = nfsd_print_client_locks,
- },
- {
- .file = "forget_openowners",
- .forget = nfsd_forget_client_openowners,
- .print = nfsd_print_client_openowners,
- },
- {
- .file = "forget_delegations",
- .forget = nfsd_forget_client_delegations,
- .print = nfsd_print_client_delegations,
- },
- {
- .file = "recall_delegations",
- .forget = nfsd_recall_client_delegations,
- .print = nfsd_print_client_delegations,
- },
-};
-
-static long int NUM_INJECT_OPS = sizeof(inject_ops) / sizeof(struct nfsd_fault_inject_op);
static struct dentry *debug_dir;
-static void nfsd_inject_set(struct nfsd_fault_inject_op *op, u64 val)
+static u64 nfsd_inject_set(struct nfsd_fault_inject_op *op, u64 val)
{
- u64 count = 0;
-
- if (val == 0)
- printk(KERN_INFO "NFSD Fault Injection: %s (all)", op->file);
- else
- printk(KERN_INFO "NFSD Fault Injection: %s (n = %llu)", op->file, val);
+ u64 count;
nfs4_lock_state();
count = nfsd_for_n_state(val, op->forget);
nfs4_unlock_state();
- printk(KERN_INFO "NFSD: %s: found %llu", op->file, count);
+ return count;
}
-static void nfsd_inject_set_client(struct nfsd_fault_inject_op *op,
+static u64 nfsd_inject_set_client(struct nfsd_fault_inject_op *op,
struct sockaddr_storage *addr,
size_t addr_size)
{
- char buf[INET6_ADDRSTRLEN];
struct nfs4_client *clp;
- u64 count;
+ u64 count = 0;
nfs4_lock_state();
clp = nfsd_find_client(addr, addr_size);
- if (clp) {
+ if (clp)
count = op->forget(clp, 0);
- rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf));
- printk(KERN_INFO "NFSD [%s]: Client %s had %llu state object(s)\n", op->file, buf, count);
- }
nfs4_unlock_state();
+ return count;
}
-static void nfsd_inject_get(struct nfsd_fault_inject_op *op, u64 *val)
+static u64 nfsd_inject_get(struct nfsd_fault_inject_op *op)
{
+ u64 count;
+
nfs4_lock_state();
- *val = nfsd_for_n_state(0, op->print);
+ count = nfsd_for_n_state(0, op->print);
nfs4_unlock_state();
+
+ return count;
}
static ssize_t fault_inject_read(struct file *file, char __user *buf,
@@ -99,9 +70,10 @@ static ssize_t fault_inject_read(struct file *file, char __user *buf,
char read_buf[25];
size_t size;
loff_t pos = *ppos;
+ struct nfsd_fault_inject_op *op = file_inode(file)->i_private;
if (!pos)
- nfsd_inject_get(file_inode(file)->i_private, &val);
+ val = op->get(op);
size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val);
return simple_read_from_buffer(buf, len, ppos, read_buf, size);
@@ -114,6 +86,7 @@ static ssize_t fault_inject_write(struct file *file, const char __user *buf,
size_t size = min(sizeof(write_buf) - 1, len);
struct net *net = current->nsproxy->net_ns;
struct sockaddr_storage sa;
+ struct nfsd_fault_inject_op *op = file_inode(file)->i_private;
u64 val;
char *nl;
@@ -129,11 +102,20 @@ static ssize_t fault_inject_write(struct file *file, const char __user *buf,
}
size = rpc_pton(net, write_buf, size, (struct sockaddr *)&sa, sizeof(sa));
- if (size > 0)
- nfsd_inject_set_client(file_inode(file)->i_private, &sa, size);
- else {
+ if (size > 0) {
+ val = op->set_clnt(op, &sa, size);
+ if (val)
+ pr_info("NFSD [%s]: Client %s had %llu state object(s)\n",
+ op->file, write_buf, val);
+ } else {
val = simple_strtoll(write_buf, NULL, 0);
- nfsd_inject_set(file_inode(file)->i_private, val);
+ if (val == 0)
+ pr_info("NFSD Fault Injection: %s (all)", op->file);
+ else
+ pr_info("NFSD Fault Injection: %s (n = %llu)",
+ op->file, val);
+ val = op->set_val(op, val);
+ pr_info("NFSD: %s: found %llu", op->file, val);
}
return len; /* on success, claim we got the whole input */
}
@@ -149,6 +131,51 @@ void nfsd_fault_inject_cleanup(void)
debugfs_remove_recursive(debug_dir);
}
+static struct nfsd_fault_inject_op inject_ops[] = {
+ {
+ .file = "forget_clients",
+ .get = nfsd_inject_get,
+ .set_val = nfsd_inject_set,
+ .set_clnt = nfsd_inject_set_client,
+ .forget = nfsd_forget_client,
+ .print = nfsd_print_client,
+ },
+ {
+ .file = "forget_locks",
+ .get = nfsd_inject_get,
+ .set_val = nfsd_inject_set,
+ .set_clnt = nfsd_inject_set_client,
+ .forget = nfsd_forget_client_locks,
+ .print = nfsd_print_client_locks,
+ },
+ {
+ .file = "forget_openowners",
+ .get = nfsd_inject_get,
+ .set_val = nfsd_inject_set,
+ .set_clnt = nfsd_inject_set_client,
+ .forget = nfsd_forget_client_openowners,
+ .print = nfsd_print_client_openowners,
+ },
+ {
+ .file = "forget_delegations",
+ .get = nfsd_inject_get,
+ .set_val = nfsd_inject_set,
+ .set_clnt = nfsd_inject_set_client,
+ .forget = nfsd_forget_client_delegations,
+ .print = nfsd_print_client_delegations,
+ },
+ {
+ .file = "recall_delegations",
+ .get = nfsd_inject_get,
+ .set_val = nfsd_inject_set,
+ .set_clnt = nfsd_inject_set_client,
+ .forget = nfsd_recall_client_delegations,
+ .print = nfsd_print_client_delegations,
+ },
+};
+
+#define NUM_INJECT_OPS (sizeof(inject_ops)/sizeof(struct nfsd_fault_inject_op))
+
int nfsd_fault_inject_init(void)
{
unsigned int i;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 093/114] nfsd: add a forget_clients "get" routine with proper locking
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (91 preceding siblings ...)
2014-06-30 15:50 ` [PATCH v3 092/114] nfsd: abstract out the get and set routines into the fault injection ops Jeff Layton
@ 2014-06-30 15:50 ` Jeff Layton
2014-06-30 15:50 ` [PATCH v3 094/114] nfsd: add a forget_client set_clnt routine Jeff Layton
` (20 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:50 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Add a new "get" routine for forget_clients that relies on the
client_lock instead of the client_mutex.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/fault_inject.c | 3 +--
fs/nfsd/nfs4state.c | 30 ++++++++++++++++++++++--------
fs/nfsd/state.h | 4 +++-
3 files changed, 26 insertions(+), 11 deletions(-)
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index b1159900d934..a0387fd47e14 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -134,11 +134,10 @@ void nfsd_fault_inject_cleanup(void)
static struct nfsd_fault_inject_op inject_ops[] = {
{
.file = "forget_clients",
- .get = nfsd_inject_get,
+ .get = nfsd_inject_print_clients,
.set_val = nfsd_inject_set,
.set_clnt = nfsd_inject_set_client,
.forget = nfsd_forget_client,
- .print = nfsd_print_client,
},
{
.file = "forget_locks",
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4799d6e652d0..ade71f32a070 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5664,6 +5664,28 @@ nfs4_check_open_reclaim(clientid_t *clid,
}
#ifdef CONFIG_NFSD_FAULT_INJECTION
+u64
+nfsd_inject_print_clients(struct nfsd_fault_inject_op *op)
+{
+ struct nfs4_client *clp;
+ u64 count = 0;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+ char buf[INET6_ADDRSTRLEN];
+
+ if (!nfsd_netns_ready(nn))
+ return 0;
+
+ spin_lock(&nn->client_lock);
+ list_for_each_entry(clp, &nn->client_lru, cl_lru) {
+ rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf));
+ pr_info("NFS Client: %s\n", buf);
+ ++count;
+ }
+ spin_unlock(&nn->client_lock);
+
+ return count;
+}
u64 nfsd_forget_client(struct nfs4_client *clp, u64 max)
{
@@ -5679,14 +5701,6 @@ u64 nfsd_forget_client(struct nfs4_client *clp, u64 max)
return 1;
}
-u64 nfsd_print_client(struct nfs4_client *clp, u64 num)
-{
- char buf[INET6_ADDRSTRLEN];
- rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf));
- printk(KERN_INFO "NFS Client: %s\n", buf);
- return 1;
-}
-
static void nfsd_print_count(struct nfs4_client *clp, unsigned int count,
const char *type)
{
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 7e395f665b0f..e0bf42051c1f 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -466,18 +466,20 @@ extern void nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time);
/* nfs fault injection functions */
#ifdef CONFIG_NFSD_FAULT_INJECTION
+struct nfsd_fault_inject_op;
+
int nfsd_fault_inject_init(void);
void nfsd_fault_inject_cleanup(void);
u64 nfsd_for_n_state(u64, u64 (*)(struct nfs4_client *, u64));
struct nfs4_client *nfsd_find_client(struct sockaddr_storage *, size_t);
+u64 nfsd_inject_print_clients(struct nfsd_fault_inject_op *op);
u64 nfsd_forget_client(struct nfs4_client *, u64);
u64 nfsd_forget_client_locks(struct nfs4_client*, u64);
u64 nfsd_forget_client_openowners(struct nfs4_client *, u64);
u64 nfsd_forget_client_delegations(struct nfs4_client *, u64);
u64 nfsd_recall_client_delegations(struct nfs4_client *, u64);
-u64 nfsd_print_client(struct nfs4_client *, u64);
u64 nfsd_print_client_locks(struct nfs4_client *, u64);
u64 nfsd_print_client_openowners(struct nfs4_client *, u64);
u64 nfsd_print_client_delegations(struct nfs4_client *, u64);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 094/114] nfsd: add a forget_client set_clnt routine
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (92 preceding siblings ...)
2014-06-30 15:50 ` [PATCH v3 093/114] nfsd: add a forget_clients "get" routine with proper locking Jeff Layton
@ 2014-06-30 15:50 ` Jeff Layton
2014-06-30 15:50 ` [PATCH v3 095/114] nfsd: add nfsd_inject_forget_clients Jeff Layton
` (19 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:50 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
...that relies on the client_lock instead of client_mutex.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/fault_inject.c | 2 +-
fs/nfsd/nfs4state.c | 28 ++++++++++++++++++++++++++++
fs/nfsd/state.h | 3 +++
3 files changed, 32 insertions(+), 1 deletion(-)
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index a0387fd47e14..5f3ead0c72fb 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -136,7 +136,7 @@ static struct nfsd_fault_inject_op inject_ops[] = {
.file = "forget_clients",
.get = nfsd_inject_print_clients,
.set_val = nfsd_inject_set,
- .set_clnt = nfsd_inject_set_client,
+ .set_clnt = nfsd_inject_forget_client,
.forget = nfsd_forget_client,
},
{
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ade71f32a070..2795f549e29e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5701,6 +5701,34 @@ u64 nfsd_forget_client(struct nfs4_client *clp, u64 max)
return 1;
}
+u64
+nfsd_inject_forget_client(struct nfsd_fault_inject_op *op,
+ struct sockaddr_storage *addr, size_t addr_size)
+{
+ u64 count = 0;
+ struct nfs4_client *clp;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+
+ if (!nfsd_netns_ready(nn))
+ return count;
+
+ spin_lock(&nn->client_lock);
+ clp = nfsd_find_client(addr, addr_size);
+ if (clp) {
+ if (mark_client_expired_locked(clp) == nfs_ok)
+ ++count;
+ else
+ clp = NULL;
+ }
+ spin_unlock(&nn->client_lock);
+
+ if (clp)
+ expire_client(clp);
+
+ return count;
+}
+
static void nfsd_print_count(struct nfs4_client *clp, unsigned int count,
const char *type)
{
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index e0bf42051c1f..ead0fe9027fb 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -475,6 +475,9 @@ struct nfs4_client *nfsd_find_client(struct sockaddr_storage *, size_t);
u64 nfsd_inject_print_clients(struct nfsd_fault_inject_op *op);
u64 nfsd_forget_client(struct nfs4_client *, u64);
+u64 nfsd_inject_forget_client(struct nfsd_fault_inject_op *,
+ struct sockaddr_storage *, size_t);
+
u64 nfsd_forget_client_locks(struct nfs4_client*, u64);
u64 nfsd_forget_client_openowners(struct nfs4_client *, u64);
u64 nfsd_forget_client_delegations(struct nfs4_client *, u64);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 095/114] nfsd: add nfsd_inject_forget_clients
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (93 preceding siblings ...)
2014-06-30 15:50 ` [PATCH v3 094/114] nfsd: add a forget_client set_clnt routine Jeff Layton
@ 2014-06-30 15:50 ` Jeff Layton
2014-06-30 15:50 ` [PATCH v3 096/114] nfsd: add a list_head arg to nfsd_foreach_client_lock Jeff Layton
` (18 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:50 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
...which uses the client_lock for protection instead of client_mutex.
Also remove nfsd_forget_client as there are no more callers.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/fault_inject.c | 3 +--
fs/nfsd/nfs4state.c | 42 ++++++++++++++++++++++++++++--------------
fs/nfsd/state.h | 2 +-
3 files changed, 30 insertions(+), 17 deletions(-)
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index 5f3ead0c72fb..76ecdff37ea2 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -135,9 +135,8 @@ static struct nfsd_fault_inject_op inject_ops[] = {
{
.file = "forget_clients",
.get = nfsd_inject_print_clients,
- .set_val = nfsd_inject_set,
+ .set_val = nfsd_inject_forget_clients,
.set_clnt = nfsd_inject_forget_client,
- .forget = nfsd_forget_client,
},
{
.file = "forget_locks",
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2795f549e29e..f395afc19d4c 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5687,20 +5687,6 @@ nfsd_inject_print_clients(struct nfsd_fault_inject_op *op)
return count;
}
-u64 nfsd_forget_client(struct nfs4_client *clp, u64 max)
-{
- __be32 ret;
- struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
-
- spin_lock(&nn->client_lock);
- ret = mark_client_expired_locked(clp);
- spin_unlock(&nn->client_lock);
- if (ret != nfs_ok)
- return 0;
- expire_client(clp);
- return 1;
-}
-
u64
nfsd_inject_forget_client(struct nfsd_fault_inject_op *op,
struct sockaddr_storage *addr, size_t addr_size)
@@ -5729,6 +5715,34 @@ nfsd_inject_forget_client(struct nfsd_fault_inject_op *op,
return count;
}
+u64
+nfsd_inject_forget_clients(struct nfsd_fault_inject_op *op, u64 max)
+{
+ u64 count = 0;
+ struct nfs4_client *clp, *next;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+ LIST_HEAD(reaplist);
+
+ if (!nfsd_netns_ready(nn))
+ return count;
+
+ spin_lock(&nn->client_lock);
+ list_for_each_entry_safe(clp, next, &nn->client_lru, cl_lru) {
+ if (mark_client_expired_locked(clp) == nfs_ok) {
+ list_add(&clp->cl_lru, &reaplist);
+ if (max != 0 && ++count >= max)
+ break;
+ }
+ }
+ spin_unlock(&nn->client_lock);
+
+ list_for_each_entry_safe(clp, next, &reaplist, cl_lru)
+ expire_client(clp);
+
+ return count;
+}
+
static void nfsd_print_count(struct nfs4_client *clp, unsigned int count,
const char *type)
{
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index ead0fe9027fb..25b4df7bc57a 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -474,9 +474,9 @@ u64 nfsd_for_n_state(u64, u64 (*)(struct nfs4_client *, u64));
struct nfs4_client *nfsd_find_client(struct sockaddr_storage *, size_t);
u64 nfsd_inject_print_clients(struct nfsd_fault_inject_op *op);
-u64 nfsd_forget_client(struct nfs4_client *, u64);
u64 nfsd_inject_forget_client(struct nfsd_fault_inject_op *,
struct sockaddr_storage *, size_t);
+u64 nfsd_inject_forget_clients(struct nfsd_fault_inject_op *, u64);
u64 nfsd_forget_client_locks(struct nfs4_client*, u64);
u64 nfsd_forget_client_openowners(struct nfs4_client *, u64);
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 096/114] nfsd: add a list_head arg to nfsd_foreach_client_lock
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (94 preceding siblings ...)
2014-06-30 15:50 ` [PATCH v3 095/114] nfsd: add nfsd_inject_forget_clients Jeff Layton
@ 2014-06-30 15:50 ` Jeff Layton
2014-06-30 15:50 ` [PATCH v3 097/114] nfsd: add more granular locking to forget_locks fault injector Jeff Layton
` (17 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:50 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
In a later patch, we'll want to collect the locks onto a list for later
destruction. If "func" is defined and "collect" is defined, then we'll
add the lock stateid to the list.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f395afc19d4c..2f57fa4fd244 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5752,6 +5752,7 @@ static void nfsd_print_count(struct nfs4_client *clp, unsigned int count,
}
static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max,
+ struct list_head *collect,
void (*func)(struct nfs4_ol_stateid *))
{
struct nfs4_openowner *oop;
@@ -5764,8 +5765,12 @@ static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max,
&oop->oo_owner.so_stateids, st_perstateowner) {
list_for_each_entry_safe(lst, lst_next,
&stp->st_locks, st_locks) {
- if (func)
+ if (func) {
func(lst);
+ if (collect)
+ list_add(&lst->st_locks,
+ collect);
+ }
if (++count == max)
return count;
}
@@ -5777,12 +5782,12 @@ static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max,
u64 nfsd_forget_client_locks(struct nfs4_client *clp, u64 max)
{
- return nfsd_foreach_client_lock(clp, max, release_lock_stateid);
+ return nfsd_foreach_client_lock(clp, max, NULL, release_lock_stateid);
}
u64 nfsd_print_client_locks(struct nfs4_client *clp, u64 max)
{
- u64 count = nfsd_foreach_client_lock(clp, max, NULL);
+ u64 count = nfsd_foreach_client_lock(clp, max, NULL, NULL);
nfsd_print_count(clp, count, "locked files");
return count;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 097/114] nfsd: add more granular locking to forget_locks fault injector
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (95 preceding siblings ...)
2014-06-30 15:50 ` [PATCH v3 096/114] nfsd: add a list_head arg to nfsd_foreach_client_lock Jeff Layton
@ 2014-06-30 15:50 ` Jeff Layton
2014-06-30 15:50 ` [PATCH v3 098/114] nfsd: add more granular locking to forget_openowners " Jeff Layton
` (16 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:50 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
...instead of relying on the client_mutex.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/fault_inject.c | 8 ++-
fs/nfsd/nfs4state.c | 136 +++++++++++++++++++++++++++++++++++++++++++++----
fs/nfsd/state.h | 7 ++-
3 files changed, 135 insertions(+), 16 deletions(-)
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index 76ecdff37ea2..a444d821d2a5 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -140,11 +140,9 @@ static struct nfsd_fault_inject_op inject_ops[] = {
},
{
.file = "forget_locks",
- .get = nfsd_inject_get,
- .set_val = nfsd_inject_set,
- .set_clnt = nfsd_inject_set_client,
- .forget = nfsd_forget_client_locks,
- .print = nfsd_print_client_locks,
+ .get = nfsd_inject_print_locks,
+ .set_val = nfsd_inject_forget_locks,
+ .set_clnt = nfsd_inject_forget_client_locks,
},
{
.file = "forget_openowners",
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2f57fa4fd244..a00244918cd1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5664,6 +5664,16 @@ nfs4_check_open_reclaim(clientid_t *clid,
}
#ifdef CONFIG_NFSD_FAULT_INJECTION
+static void
+put_client(struct nfs4_client *clp)
+{
+ struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id);
+
+ spin_lock(&nn->client_lock);
+ atomic_dec(&clp->cl_refcount);
+ spin_unlock(&nn->client_lock);
+}
+
u64
nfsd_inject_print_clients(struct nfsd_fault_inject_op *op)
{
@@ -5751,6 +5761,22 @@ static void nfsd_print_count(struct nfs4_client *clp, unsigned int count,
printk(KERN_INFO "NFS Client: %s has %u %s\n", buf, count, type);
}
+static void
+nfsd_inject_add_lock_to_list(struct nfs4_ol_stateid *lst,
+ struct list_head *collect)
+{
+ struct nfs4_client *clp = lst->st_stid.sc_client;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+
+ if (!collect)
+ return;
+
+ lockdep_assert_held(&nn->client_lock);
+ atomic_inc(&clp->cl_refcount);
+ list_add(&lst->st_locks, collect);
+}
+
static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max,
struct list_head *collect,
void (*func)(struct nfs4_ol_stateid *))
@@ -5760,6 +5786,7 @@ static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max,
struct nfs4_ol_stateid *lst, *lst_next;
u64 count = 0;
+ spin_lock(&clp->cl_lock);
list_for_each_entry(oop, &clp->cl_openowners, oo_perclient) {
list_for_each_entry_safe(stp, st_next,
&oop->oo_owner.so_stateids, st_perstateowner) {
@@ -5767,31 +5794,122 @@ static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max,
&stp->st_locks, st_locks) {
if (func) {
func(lst);
- if (collect)
- list_add(&lst->st_locks,
- collect);
+ nfsd_inject_add_lock_to_list(lst,
+ collect);
}
- if (++count == max)
- return count;
+ ++count;
+ /*
+ * Despite the fact that these functions deal
+ * with 64-bit integers for "count", we must
+ * ensure that it doesn't blow up the
+ * clp->cl_refcount. Throw a warning if we
+ * start to approach INT_MAX here.
+ */
+ WARN_ON_ONCE(count == (INT_MAX / 2));
+ if (count == max)
+ goto out;
}
}
}
+out:
+ spin_unlock(&clp->cl_lock);
return count;
}
-u64 nfsd_forget_client_locks(struct nfs4_client *clp, u64 max)
+static u64
+nfsd_collect_client_locks(struct nfs4_client *clp, struct list_head *collect,
+ u64 max)
{
- return nfsd_foreach_client_lock(clp, max, NULL, release_lock_stateid);
+ return nfsd_foreach_client_lock(clp, max, collect, unhash_lock_stateid);
}
-u64 nfsd_print_client_locks(struct nfs4_client *clp, u64 max)
+static u64
+nfsd_print_client_locks(struct nfs4_client *clp)
{
- u64 count = nfsd_foreach_client_lock(clp, max, NULL, NULL);
+ u64 count = nfsd_foreach_client_lock(clp, 0, NULL, NULL);
nfsd_print_count(clp, count, "locked files");
return count;
}
+u64
+nfsd_inject_print_locks(struct nfsd_fault_inject_op *op)
+{
+ struct nfs4_client *clp;
+ u64 count = 0;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+
+ if (!nfsd_netns_ready(nn))
+ return 0;
+
+ spin_lock(&nn->client_lock);
+ list_for_each_entry(clp, &nn->client_lru, cl_lru)
+ count += nfsd_print_client_locks(clp);
+ spin_unlock(&nn->client_lock);
+
+ return count;
+}
+
+static void
+nfsd_reap_locks(struct list_head *reaplist)
+{
+ struct nfs4_client *clp;
+ struct nfs4_ol_stateid *stp, *next;
+
+ list_for_each_entry_safe(stp, next, reaplist, st_locks) {
+ list_del_init(&stp->st_locks);
+ clp = stp->st_stid.sc_client;
+ put_generic_stateid(stp);
+ put_client(clp);
+ }
+}
+
+u64
+nfsd_inject_forget_client_locks(struct nfsd_fault_inject_op *op,
+ struct sockaddr_storage *addr, size_t addr_size)
+{
+ unsigned int count = 0;
+ struct nfs4_client *clp;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+ LIST_HEAD(reaplist);
+
+ if (!nfsd_netns_ready(nn))
+ return count;
+
+ spin_lock(&nn->client_lock);
+ clp = nfsd_find_client(addr, addr_size);
+ if (clp)
+ count = nfsd_collect_client_locks(clp, &reaplist, 0);
+ spin_unlock(&nn->client_lock);
+ nfsd_reap_locks(&reaplist);
+ return count;
+}
+
+u64
+nfsd_inject_forget_locks(struct nfsd_fault_inject_op *op, u64 max)
+{
+ u64 count = 0;
+ struct nfs4_client *clp;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+ LIST_HEAD(reaplist);
+
+ if (!nfsd_netns_ready(nn))
+ return count;
+
+ spin_lock(&nn->client_lock);
+ list_for_each_entry(clp, &nn->client_lru, cl_lru) {
+ count += nfsd_collect_client_locks(clp, &reaplist, max - count);
+ if (max != 0 && count >= max)
+ break;
+ }
+ spin_unlock(&nn->client_lock);
+ nfsd_reap_locks(&reaplist);
+ return count;
+}
+
static u64 nfsd_foreach_client_open(struct nfs4_client *clp, u64 max, void (*func)(struct nfs4_openowner *))
{
struct nfs4_openowner *oop, *next;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 25b4df7bc57a..5015ad3c9282 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -478,12 +478,15 @@ u64 nfsd_inject_forget_client(struct nfsd_fault_inject_op *,
struct sockaddr_storage *, size_t);
u64 nfsd_inject_forget_clients(struct nfsd_fault_inject_op *, u64);
-u64 nfsd_forget_client_locks(struct nfs4_client*, u64);
+u64 nfsd_inject_print_locks(struct nfsd_fault_inject_op *);
+u64 nfsd_inject_forget_client_locks(struct nfsd_fault_inject_op *,
+ struct sockaddr_storage *, size_t);
+u64 nfsd_inject_forget_locks(struct nfsd_fault_inject_op *, u64);
+
u64 nfsd_forget_client_openowners(struct nfs4_client *, u64);
u64 nfsd_forget_client_delegations(struct nfs4_client *, u64);
u64 nfsd_recall_client_delegations(struct nfs4_client *, u64);
-u64 nfsd_print_client_locks(struct nfs4_client *, u64);
u64 nfsd_print_client_openowners(struct nfs4_client *, u64);
u64 nfsd_print_client_delegations(struct nfs4_client *, u64);
#else /* CONFIG_NFSD_FAULT_INJECTION */
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 098/114] nfsd: add more granular locking to forget_openowners fault injector
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (96 preceding siblings ...)
2014-06-30 15:50 ` [PATCH v3 097/114] nfsd: add more granular locking to forget_locks fault injector Jeff Layton
@ 2014-06-30 15:50 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 099/114] nfsd: add more granular locking to *_delegations fault injectors Jeff Layton
` (15 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:50 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
...instead of relying on the client_mutex.
Also, fix up the printk output that is generated when the file is read.
It currently says that it's reporting the number of open files, but
it's actually reporting the number of openowners.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/fault_inject.c | 8 ++--
fs/nfsd/nfs4state.c | 122 +++++++++++++++++++++++++++++++++++++++++++++----
fs/nfsd/state.h | 7 ++-
3 files changed, 122 insertions(+), 15 deletions(-)
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index a444d821d2a5..d4472cd19807 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -146,11 +146,9 @@ static struct nfsd_fault_inject_op inject_ops[] = {
},
{
.file = "forget_openowners",
- .get = nfsd_inject_get,
- .set_val = nfsd_inject_set,
- .set_clnt = nfsd_inject_set_client,
- .forget = nfsd_forget_client_openowners,
- .print = nfsd_print_client_openowners,
+ .get = nfsd_inject_print_openowners,
+ .set_val = nfsd_inject_forget_openowners,
+ .set_clnt = nfsd_inject_forget_client_openowners,
},
{
.file = "forget_delegations",
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index a00244918cd1..207d16f48761 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5910,30 +5910,136 @@ nfsd_inject_forget_locks(struct nfsd_fault_inject_op *op, u64 max)
return count;
}
-static u64 nfsd_foreach_client_open(struct nfs4_client *clp, u64 max, void (*func)(struct nfs4_openowner *))
+static u64
+nfsd_foreach_client_openowner(struct nfs4_client *clp, u64 max,
+ struct list_head *collect,
+ void (*func)(struct nfs4_openowner *))
{
struct nfs4_openowner *oop, *next;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
u64 count = 0;
+ lockdep_assert_held(&nn->client_lock);
+
+ spin_lock(&clp->cl_lock);
list_for_each_entry_safe(oop, next, &clp->cl_openowners, oo_perclient) {
- if (func)
+ if (func) {
func(oop);
- if (++count == max)
+ if (collect) {
+ atomic_inc(&clp->cl_refcount);
+ list_add(&oop->oo_perclient, collect);
+ }
+ }
+ ++count;
+ /*
+ * Despite the fact that these functions deal with
+ * 64-bit integers for "count", we must ensure that
+ * it doesn't blow up the clp->cl_refcount. Throw a
+ * warning if we start to approach INT_MAX here.
+ */
+ WARN_ON_ONCE(count == (INT_MAX / 2));
+ if (count == max)
break;
}
+ spin_unlock(&clp->cl_lock);
+
+ return count;
+}
+static u64
+nfsd_print_client_openowners(struct nfs4_client *clp)
+{
+ u64 count = nfsd_foreach_client_openowner(clp, 0, NULL, NULL);
+
+ nfsd_print_count(clp, count, "openowners");
return count;
}
-u64 nfsd_forget_client_openowners(struct nfs4_client *clp, u64 max)
+static u64
+nfsd_collect_client_openowners(struct nfs4_client *clp,
+ struct list_head *collect, u64 max)
{
- return nfsd_foreach_client_open(clp, max, release_openowner);
+ return nfsd_foreach_client_openowner(clp, max, collect,
+ unhash_openowner_locked);
}
-u64 nfsd_print_client_openowners(struct nfs4_client *clp, u64 max)
+u64
+nfsd_inject_print_openowners(struct nfsd_fault_inject_op *op)
{
- u64 count = nfsd_foreach_client_open(clp, max, NULL);
- nfsd_print_count(clp, count, "open files");
+ struct nfs4_client *clp;
+ u64 count = 0;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+
+ if (!nfsd_netns_ready(nn))
+ return 0;
+
+ spin_lock(&nn->client_lock);
+ list_for_each_entry(clp, &nn->client_lru, cl_lru)
+ count += nfsd_print_client_openowners(clp);
+ spin_unlock(&nn->client_lock);
+
+ return count;
+}
+
+static void
+nfsd_reap_openowners(struct list_head *reaplist)
+{
+ struct nfs4_client *clp;
+ struct nfs4_openowner *oop, *next;
+
+ list_for_each_entry_safe(oop, next, reaplist, oo_perclient) {
+ list_del_init(&oop->oo_perclient);
+ clp = oop->oo_owner.so_client;
+ release_openowner(oop);
+ put_client(clp);
+ }
+}
+
+u64
+nfsd_inject_forget_client_openowners(struct nfsd_fault_inject_op *op,
+ struct sockaddr_storage *addr, size_t addr_size)
+{
+ unsigned int count = 0;
+ struct nfs4_client *clp;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+ LIST_HEAD(reaplist);
+
+ if (!nfsd_netns_ready(nn))
+ return count;
+
+ spin_lock(&nn->client_lock);
+ clp = nfsd_find_client(addr, addr_size);
+ if (clp)
+ count = nfsd_collect_client_openowners(clp, &reaplist, 0);
+ spin_unlock(&nn->client_lock);
+ nfsd_reap_openowners(&reaplist);
+ return count;
+}
+
+u64
+nfsd_inject_forget_openowners(struct nfsd_fault_inject_op *op, u64 max)
+{
+ u64 count = 0;
+ struct nfs4_client *clp;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+ LIST_HEAD(reaplist);
+
+ if (!nfsd_netns_ready(nn))
+ return count;
+
+ spin_lock(&nn->client_lock);
+ list_for_each_entry(clp, &nn->client_lru, cl_lru) {
+ count += nfsd_collect_client_openowners(clp, &reaplist,
+ max - count);
+ if (max != 0 && count >= max)
+ break;
+ }
+ spin_unlock(&nn->client_lock);
+ nfsd_reap_openowners(&reaplist);
return count;
}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 5015ad3c9282..36651017697b 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -483,11 +483,14 @@ u64 nfsd_inject_forget_client_locks(struct nfsd_fault_inject_op *,
struct sockaddr_storage *, size_t);
u64 nfsd_inject_forget_locks(struct nfsd_fault_inject_op *, u64);
-u64 nfsd_forget_client_openowners(struct nfs4_client *, u64);
+u64 nfsd_inject_print_openowners(struct nfsd_fault_inject_op *);
+u64 nfsd_inject_forget_client_openowners(struct nfsd_fault_inject_op *,
+ struct sockaddr_storage *, size_t);
+u64 nfsd_inject_forget_openowners(struct nfsd_fault_inject_op *, u64);
+
u64 nfsd_forget_client_delegations(struct nfs4_client *, u64);
u64 nfsd_recall_client_delegations(struct nfs4_client *, u64);
-u64 nfsd_print_client_openowners(struct nfs4_client *, u64);
u64 nfsd_print_client_delegations(struct nfs4_client *, u64);
#else /* CONFIG_NFSD_FAULT_INJECTION */
static inline int nfsd_fault_inject_init(void) { return 0; }
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 099/114] nfsd: add more granular locking to *_delegations fault injectors
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (97 preceding siblings ...)
2014-06-30 15:50 ` [PATCH v3 098/114] nfsd: add more granular locking to forget_openowners " Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 100/114] nfsd: remove old fault injection infrastructure Jeff Layton
` (14 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
...instead of relying on the client_mutex.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/fault_inject.c | 16 ++---
fs/nfsd/nfs4state.c | 167 ++++++++++++++++++++++++++++++++++++++++++-------
fs/nfsd/state.h | 11 ++--
3 files changed, 157 insertions(+), 37 deletions(-)
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index d4472cd19807..2479dba71c3c 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -152,19 +152,15 @@ static struct nfsd_fault_inject_op inject_ops[] = {
},
{
.file = "forget_delegations",
- .get = nfsd_inject_get,
- .set_val = nfsd_inject_set,
- .set_clnt = nfsd_inject_set_client,
- .forget = nfsd_forget_client_delegations,
- .print = nfsd_print_client_delegations,
+ .get = nfsd_inject_print_delegations,
+ .set_val = nfsd_inject_forget_delegations,
+ .set_clnt = nfsd_inject_forget_client_delegations,
},
{
.file = "recall_delegations",
- .get = nfsd_inject_get,
- .set_val = nfsd_inject_set,
- .set_clnt = nfsd_inject_set_client,
- .forget = nfsd_recall_client_delegations,
- .print = nfsd_print_client_delegations,
+ .get = nfsd_inject_print_delegations,
+ .set_val = nfsd_inject_recall_delegations,
+ .set_clnt = nfsd_inject_recall_client_delegations,
},
};
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 207d16f48761..91a19ac5ea4c 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -6047,60 +6047,180 @@ static u64 nfsd_find_all_delegations(struct nfs4_client *clp, u64 max,
struct list_head *victims)
{
struct nfs4_delegation *dp, *next;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
u64 count = 0;
- lockdep_assert_held(&state_lock);
+ lockdep_assert_held(&nn->client_lock);
+
+ spin_lock(&state_lock);
list_for_each_entry_safe(dp, next, &clp->cl_delegations, dl_perclnt) {
if (victims) {
+ atomic_inc(&clp->cl_refcount);
unhash_delegation_locked(dp);
list_add(&dp->dl_recall_lru, victims);
}
- if (++count == max)
+ ++count;
+ /*
+ * Despite the fact that these functions deal with
+ * 64-bit integers for "count", we must ensure that
+ * it doesn't blow up the clp->cl_refcount. Throw a
+ * warning if we start to approach INT_MAX here.
+ */
+ WARN_ON_ONCE(count == (INT_MAX / 2));
+ if (count == max)
break;
}
+ spin_unlock(&state_lock);
return count;
}
-u64 nfsd_forget_client_delegations(struct nfs4_client *clp, u64 max)
+static u64
+nfsd_print_client_delegations(struct nfs4_client *clp)
{
- struct nfs4_delegation *dp, *next;
- LIST_HEAD(victims);
- u64 count;
+ u64 count = nfsd_find_all_delegations(clp, 0, NULL);
- spin_lock(&state_lock);
- count = nfsd_find_all_delegations(clp, max, &victims);
- spin_unlock(&state_lock);
+ nfsd_print_count(clp, count, "delegations");
+ return count;
+}
+
+u64
+nfsd_inject_print_delegations(struct nfsd_fault_inject_op *op)
+{
+ struct nfs4_client *clp;
+ u64 count = 0;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+
+ if (!nfsd_netns_ready(nn))
+ return 0;
+
+ spin_lock(&nn->client_lock);
+ list_for_each_entry(clp, &nn->client_lru, cl_lru)
+ count += nfsd_print_client_delegations(clp);
+ spin_unlock(&nn->client_lock);
+
+ return count;
+}
- list_for_each_entry_safe(dp, next, &victims, dl_recall_lru)
+static void
+nfsd_forget_delegations(struct list_head *reaplist)
+{
+ struct nfs4_client *clp;
+ struct nfs4_delegation *dp, *next;
+
+ list_for_each_entry_safe(dp, next, reaplist, dl_recall_lru) {
+ list_del_init(&dp->dl_recall_lru);
+ clp = dp->dl_stid.sc_client;
revoke_delegation(dp);
+ put_client(clp);
+ }
+}
+
+u64
+nfsd_inject_forget_client_delegations(struct nfsd_fault_inject_op *op,
+ struct sockaddr_storage *addr, size_t addr_size)
+{
+ u64 count = 0;
+ struct nfs4_client *clp;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+ LIST_HEAD(reaplist);
+
+ if (!nfsd_netns_ready(nn))
+ return count;
+
+ spin_lock(&nn->client_lock);
+ clp = nfsd_find_client(addr, addr_size);
+ if (clp)
+ count = nfsd_find_all_delegations(clp, 0, &reaplist);
+ spin_unlock(&nn->client_lock);
+
+ nfsd_forget_delegations(&reaplist);
+ return count;
+}
+
+u64
+nfsd_inject_forget_delegations(struct nfsd_fault_inject_op *op, u64 max)
+{
+ u64 count = 0;
+ struct nfs4_client *clp;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+ LIST_HEAD(reaplist);
+
+ if (!nfsd_netns_ready(nn))
+ return count;
+ spin_lock(&nn->client_lock);
+ list_for_each_entry(clp, &nn->client_lru, cl_lru) {
+ count += nfsd_find_all_delegations(clp, max - count, &reaplist);
+ if (max != 0 && count >= max)
+ break;
+ }
+ spin_unlock(&nn->client_lock);
+ nfsd_forget_delegations(&reaplist);
return count;
}
-u64 nfsd_recall_client_delegations(struct nfs4_client *clp, u64 max)
+static void
+nfsd_recall_delegations(struct list_head *reaplist)
{
+ struct nfs4_client *clp;
struct nfs4_delegation *dp, *next;
- LIST_HEAD(victims);
- u64 count;
- spin_lock(&state_lock);
- count = nfsd_find_all_delegations(clp, max, &victims);
- list_for_each_entry_safe(dp, next, &victims, dl_recall_lru)
+ list_for_each_entry_safe(dp, next, reaplist, dl_recall_lru) {
+ list_del_init(&dp->dl_recall_lru);
+ clp = dp->dl_stid.sc_client;
nfsd_break_one_deleg(dp);
- spin_unlock(&state_lock);
+ put_client(clp);
+ }
+}
+
+u64
+nfsd_inject_recall_client_delegations(struct nfsd_fault_inject_op *op,
+ struct sockaddr_storage *addr,
+ size_t addr_size)
+{
+ u64 count = 0;
+ struct nfs4_client *clp;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+ LIST_HEAD(reaplist);
+
+ if (!nfsd_netns_ready(nn))
+ return count;
+
+ spin_lock(&nn->client_lock);
+ clp = nfsd_find_client(addr, addr_size);
+ if (clp)
+ count = nfsd_find_all_delegations(clp, 0, &reaplist);
+ spin_unlock(&nn->client_lock);
+ nfsd_recall_delegations(&reaplist);
return count;
}
-u64 nfsd_print_client_delegations(struct nfs4_client *clp, u64 max)
+u64
+nfsd_inject_recall_delegations(struct nfsd_fault_inject_op *op, u64 max)
{
u64 count = 0;
+ struct nfs4_client *clp, *next;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+ LIST_HEAD(reaplist);
- spin_lock(&state_lock);
- count = nfsd_find_all_delegations(clp, max, NULL);
- spin_unlock(&state_lock);
+ if (!nfsd_netns_ready(nn))
+ return count;
- nfsd_print_count(clp, count, "delegations");
+ spin_lock(&nn->client_lock);
+ list_for_each_entry_safe(clp, next, &nn->client_lru, cl_lru) {
+ count += nfsd_find_all_delegations(clp, max - count, &reaplist);
+ if (max != 0 && ++count >= max)
+ break;
+ }
+ spin_unlock(&nn->client_lock);
+ nfsd_recall_delegations(&reaplist);
return count;
}
@@ -6108,7 +6228,8 @@ u64 nfsd_for_n_state(u64 max, u64 (*func)(struct nfs4_client *, u64))
{
struct nfs4_client *clp, *next;
u64 count = 0;
- struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, nfsd_net_id);
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
if (!nfsd_netns_ready(nn))
return 0;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 36651017697b..9bdf6807d063 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -488,10 +488,13 @@ u64 nfsd_inject_forget_client_openowners(struct nfsd_fault_inject_op *,
struct sockaddr_storage *, size_t);
u64 nfsd_inject_forget_openowners(struct nfsd_fault_inject_op *, u64);
-u64 nfsd_forget_client_delegations(struct nfs4_client *, u64);
-u64 nfsd_recall_client_delegations(struct nfs4_client *, u64);
-
-u64 nfsd_print_client_delegations(struct nfs4_client *, u64);
+u64 nfsd_inject_print_delegations(struct nfsd_fault_inject_op *);
+u64 nfsd_inject_forget_client_delegations(struct nfsd_fault_inject_op *,
+ struct sockaddr_storage *, size_t);
+u64 nfsd_inject_forget_delegations(struct nfsd_fault_inject_op *, u64);
+u64 nfsd_inject_recall_client_delegations(struct nfsd_fault_inject_op *,
+ struct sockaddr_storage *, size_t);
+u64 nfsd_inject_recall_delegations(struct nfsd_fault_inject_op *, u64);
#else /* CONFIG_NFSD_FAULT_INJECTION */
static inline int nfsd_fault_inject_init(void) { return 0; }
static inline void nfsd_fault_inject_cleanup(void) {}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 100/114] nfsd: remove old fault injection infrastructure
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (98 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 099/114] nfsd: add more granular locking to *_delegations fault injectors Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 101/114] nfsd: Remove nfs4_lock_state(): nfs4_preprocess_stateid_op() Jeff Layton
` (13 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Remove the old nfsd_for_n_state function and move nfsd_find_client
higher up into the file to get rid of forward declaration. Remove
the struct nfsd_fault_inject_op arguments from the operations as
they are no longer needed by any of them.
Finally, remove the old "standard" get and set routines, which
also eliminates the client_mutex from this code.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/fault_inject.c | 51 ++++-------------------------
fs/nfsd/nfs4state.c | 87 +++++++++++++++++++-------------------------------
fs/nfsd/state.h | 45 +++++++++++---------------
3 files changed, 57 insertions(+), 126 deletions(-)
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index 2479dba71c3c..c16bf5af6831 100644
--- a/fs/nfsd/fault_inject.c
+++ b/fs/nfsd/fault_inject.c
@@ -17,52 +17,13 @@
struct nfsd_fault_inject_op {
char *file;
- u64 (*get)(struct nfsd_fault_inject_op *);
- u64 (*set_val)(struct nfsd_fault_inject_op *, u64);
- u64 (*set_clnt)(struct nfsd_fault_inject_op *,
- struct sockaddr_storage *, size_t);
- u64 (*forget)(struct nfs4_client *, u64);
- u64 (*print)(struct nfs4_client *, u64);
+ u64 (*get)(void);
+ u64 (*set_val)(u64);
+ u64 (*set_clnt)(struct sockaddr_storage *, size_t);
};
static struct dentry *debug_dir;
-static u64 nfsd_inject_set(struct nfsd_fault_inject_op *op, u64 val)
-{
- u64 count;
-
- nfs4_lock_state();
- count = nfsd_for_n_state(val, op->forget);
- nfs4_unlock_state();
- return count;
-}
-
-static u64 nfsd_inject_set_client(struct nfsd_fault_inject_op *op,
- struct sockaddr_storage *addr,
- size_t addr_size)
-{
- struct nfs4_client *clp;
- u64 count = 0;
-
- nfs4_lock_state();
- clp = nfsd_find_client(addr, addr_size);
- if (clp)
- count = op->forget(clp, 0);
- nfs4_unlock_state();
- return count;
-}
-
-static u64 nfsd_inject_get(struct nfsd_fault_inject_op *op)
-{
- u64 count;
-
- nfs4_lock_state();
- count = nfsd_for_n_state(0, op->print);
- nfs4_unlock_state();
-
- return count;
-}
-
static ssize_t fault_inject_read(struct file *file, char __user *buf,
size_t len, loff_t *ppos)
{
@@ -73,7 +34,7 @@ static ssize_t fault_inject_read(struct file *file, char __user *buf,
struct nfsd_fault_inject_op *op = file_inode(file)->i_private;
if (!pos)
- val = op->get(op);
+ val = op->get();
size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val);
return simple_read_from_buffer(buf, len, ppos, read_buf, size);
@@ -103,7 +64,7 @@ static ssize_t fault_inject_write(struct file *file, const char __user *buf,
size = rpc_pton(net, write_buf, size, (struct sockaddr *)&sa, sizeof(sa));
if (size > 0) {
- val = op->set_clnt(op, &sa, size);
+ val = op->set_clnt(&sa, size);
if (val)
pr_info("NFSD [%s]: Client %s had %llu state object(s)\n",
op->file, write_buf, val);
@@ -114,7 +75,7 @@ static ssize_t fault_inject_write(struct file *file, const char __user *buf,
else
pr_info("NFSD Fault Injection: %s (n = %llu)",
op->file, val);
- val = op->set_val(op, val);
+ val = op->set_val(val);
pr_info("NFSD: %s: found %llu", op->file, val);
}
return len; /* on success, claim we got the whole input */
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 91a19ac5ea4c..9d6ecbdd2eae 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5674,8 +5674,25 @@ put_client(struct nfs4_client *clp)
spin_unlock(&nn->client_lock);
}
+static struct nfs4_client *
+nfsd_find_client(struct sockaddr_storage *addr, size_t addr_size)
+{
+ struct nfs4_client *clp;
+ struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
+ nfsd_net_id);
+
+ if (!nfsd_netns_ready(nn))
+ return NULL;
+
+ list_for_each_entry(clp, &nn->client_lru, cl_lru) {
+ if (memcmp(&clp->cl_addr, addr, addr_size) == 0)
+ return clp;
+ }
+ return NULL;
+}
+
u64
-nfsd_inject_print_clients(struct nfsd_fault_inject_op *op)
+nfsd_inject_print_clients(void)
{
struct nfs4_client *clp;
u64 count = 0;
@@ -5698,8 +5715,7 @@ nfsd_inject_print_clients(struct nfsd_fault_inject_op *op)
}
u64
-nfsd_inject_forget_client(struct nfsd_fault_inject_op *op,
- struct sockaddr_storage *addr, size_t addr_size)
+nfsd_inject_forget_client(struct sockaddr_storage *addr, size_t addr_size)
{
u64 count = 0;
struct nfs4_client *clp;
@@ -5726,7 +5742,7 @@ nfsd_inject_forget_client(struct nfsd_fault_inject_op *op,
}
u64
-nfsd_inject_forget_clients(struct nfsd_fault_inject_op *op, u64 max)
+nfsd_inject_forget_clients(u64 max)
{
u64 count = 0;
struct nfs4_client *clp, *next;
@@ -5833,7 +5849,7 @@ nfsd_print_client_locks(struct nfs4_client *clp)
}
u64
-nfsd_inject_print_locks(struct nfsd_fault_inject_op *op)
+nfsd_inject_print_locks(void)
{
struct nfs4_client *clp;
u64 count = 0;
@@ -5866,8 +5882,7 @@ nfsd_reap_locks(struct list_head *reaplist)
}
u64
-nfsd_inject_forget_client_locks(struct nfsd_fault_inject_op *op,
- struct sockaddr_storage *addr, size_t addr_size)
+nfsd_inject_forget_client_locks(struct sockaddr_storage *addr, size_t addr_size)
{
unsigned int count = 0;
struct nfs4_client *clp;
@@ -5888,7 +5903,7 @@ nfsd_inject_forget_client_locks(struct nfsd_fault_inject_op *op,
}
u64
-nfsd_inject_forget_locks(struct nfsd_fault_inject_op *op, u64 max)
+nfsd_inject_forget_locks(u64 max)
{
u64 count = 0;
struct nfs4_client *clp;
@@ -5965,7 +5980,7 @@ nfsd_collect_client_openowners(struct nfs4_client *clp,
}
u64
-nfsd_inject_print_openowners(struct nfsd_fault_inject_op *op)
+nfsd_inject_print_openowners(void)
{
struct nfs4_client *clp;
u64 count = 0;
@@ -5998,8 +6013,8 @@ nfsd_reap_openowners(struct list_head *reaplist)
}
u64
-nfsd_inject_forget_client_openowners(struct nfsd_fault_inject_op *op,
- struct sockaddr_storage *addr, size_t addr_size)
+nfsd_inject_forget_client_openowners(struct sockaddr_storage *addr,
+ size_t addr_size)
{
unsigned int count = 0;
struct nfs4_client *clp;
@@ -6020,7 +6035,7 @@ nfsd_inject_forget_client_openowners(struct nfsd_fault_inject_op *op,
}
u64
-nfsd_inject_forget_openowners(struct nfsd_fault_inject_op *op, u64 max)
+nfsd_inject_forget_openowners(u64 max)
{
u64 count = 0;
struct nfs4_client *clp;
@@ -6085,7 +6100,7 @@ nfsd_print_client_delegations(struct nfs4_client *clp)
}
u64
-nfsd_inject_print_delegations(struct nfsd_fault_inject_op *op)
+nfsd_inject_print_delegations(void)
{
struct nfs4_client *clp;
u64 count = 0;
@@ -6118,8 +6133,8 @@ nfsd_forget_delegations(struct list_head *reaplist)
}
u64
-nfsd_inject_forget_client_delegations(struct nfsd_fault_inject_op *op,
- struct sockaddr_storage *addr, size_t addr_size)
+nfsd_inject_forget_client_delegations(struct sockaddr_storage *addr,
+ size_t addr_size)
{
u64 count = 0;
struct nfs4_client *clp;
@@ -6141,7 +6156,7 @@ nfsd_inject_forget_client_delegations(struct nfsd_fault_inject_op *op,
}
u64
-nfsd_inject_forget_delegations(struct nfsd_fault_inject_op *op, u64 max)
+nfsd_inject_forget_delegations(u64 max)
{
u64 count = 0;
struct nfs4_client *clp;
@@ -6178,8 +6193,7 @@ nfsd_recall_delegations(struct list_head *reaplist)
}
u64
-nfsd_inject_recall_client_delegations(struct nfsd_fault_inject_op *op,
- struct sockaddr_storage *addr,
+nfsd_inject_recall_client_delegations(struct sockaddr_storage *addr,
size_t addr_size)
{
u64 count = 0;
@@ -6202,7 +6216,7 @@ nfsd_inject_recall_client_delegations(struct nfsd_fault_inject_op *op,
}
u64
-nfsd_inject_recall_delegations(struct nfsd_fault_inject_op *op, u64 max)
+nfsd_inject_recall_delegations(u64 max)
{
u64 count = 0;
struct nfs4_client *clp, *next;
@@ -6223,41 +6237,6 @@ nfsd_inject_recall_delegations(struct nfsd_fault_inject_op *op, u64 max)
nfsd_recall_delegations(&reaplist);
return count;
}
-
-u64 nfsd_for_n_state(u64 max, u64 (*func)(struct nfs4_client *, u64))
-{
- struct nfs4_client *clp, *next;
- u64 count = 0;
- struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
- nfsd_net_id);
-
- if (!nfsd_netns_ready(nn))
- return 0;
-
- list_for_each_entry_safe(clp, next, &nn->client_lru, cl_lru) {
- count += func(clp, max - count);
- if ((max != 0) && (count >= max))
- break;
- }
-
- return count;
-}
-
-struct nfs4_client *nfsd_find_client(struct sockaddr_storage *addr, size_t addr_size)
-{
- struct nfs4_client *clp;
- struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, nfsd_net_id);
-
- if (!nfsd_netns_ready(nn))
- return NULL;
-
- list_for_each_entry(clp, &nn->client_lru, cl_lru) {
- if (memcmp(&clp->cl_addr, addr, addr_size) == 0)
- return clp;
- }
- return NULL;
-}
-
#endif /* CONFIG_NFSD_FAULT_INJECTION */
/*
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 9bdf6807d063..c39ff5e1509f 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -466,35 +466,26 @@ extern void nfsd4_record_grace_done(struct nfsd_net *nn, time_t boot_time);
/* nfs fault injection functions */
#ifdef CONFIG_NFSD_FAULT_INJECTION
-struct nfsd_fault_inject_op;
-
int nfsd_fault_inject_init(void);
void nfsd_fault_inject_cleanup(void);
-u64 nfsd_for_n_state(u64, u64 (*)(struct nfs4_client *, u64));
-struct nfs4_client *nfsd_find_client(struct sockaddr_storage *, size_t);
-
-u64 nfsd_inject_print_clients(struct nfsd_fault_inject_op *op);
-u64 nfsd_inject_forget_client(struct nfsd_fault_inject_op *,
- struct sockaddr_storage *, size_t);
-u64 nfsd_inject_forget_clients(struct nfsd_fault_inject_op *, u64);
-
-u64 nfsd_inject_print_locks(struct nfsd_fault_inject_op *);
-u64 nfsd_inject_forget_client_locks(struct nfsd_fault_inject_op *,
- struct sockaddr_storage *, size_t);
-u64 nfsd_inject_forget_locks(struct nfsd_fault_inject_op *, u64);
-
-u64 nfsd_inject_print_openowners(struct nfsd_fault_inject_op *);
-u64 nfsd_inject_forget_client_openowners(struct nfsd_fault_inject_op *,
- struct sockaddr_storage *, size_t);
-u64 nfsd_inject_forget_openowners(struct nfsd_fault_inject_op *, u64);
-
-u64 nfsd_inject_print_delegations(struct nfsd_fault_inject_op *);
-u64 nfsd_inject_forget_client_delegations(struct nfsd_fault_inject_op *,
- struct sockaddr_storage *, size_t);
-u64 nfsd_inject_forget_delegations(struct nfsd_fault_inject_op *, u64);
-u64 nfsd_inject_recall_client_delegations(struct nfsd_fault_inject_op *,
- struct sockaddr_storage *, size_t);
-u64 nfsd_inject_recall_delegations(struct nfsd_fault_inject_op *, u64);
+
+u64 nfsd_inject_print_clients(void);
+u64 nfsd_inject_forget_client(struct sockaddr_storage *, size_t);
+u64 nfsd_inject_forget_clients(u64);
+
+u64 nfsd_inject_print_locks(void);
+u64 nfsd_inject_forget_client_locks(struct sockaddr_storage *, size_t);
+u64 nfsd_inject_forget_locks(u64);
+
+u64 nfsd_inject_print_openowners(void);
+u64 nfsd_inject_forget_client_openowners(struct sockaddr_storage *, size_t);
+u64 nfsd_inject_forget_openowners(u64);
+
+u64 nfsd_inject_print_delegations(void);
+u64 nfsd_inject_forget_client_delegations(struct sockaddr_storage *, size_t);
+u64 nfsd_inject_forget_delegations(u64);
+u64 nfsd_inject_recall_client_delegations(struct sockaddr_storage *, size_t);
+u64 nfsd_inject_recall_delegations(u64);
#else /* CONFIG_NFSD_FAULT_INJECTION */
static inline int nfsd_fault_inject_init(void) { return 0; }
static inline void nfsd_fault_inject_cleanup(void) {}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 101/114] nfsd: Remove nfs4_lock_state(): nfs4_preprocess_stateid_op()
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (99 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 100/114] nfsd: remove old fault injection infrastructure Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 102/114] nfsd: Remove nfs4_lock_state(): nfsd4_test_stateid/nfsd4_free_stateid Jeff Layton
` (12 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 6 +-----
1 file changed, 1 insertion(+), 5 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9d6ecbdd2eae..2ba896fb8d31 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4428,13 +4428,11 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
if (ZERO_STATEID(stateid) || ONE_STATEID(stateid))
return check_special_stateids(net, current_fh, stateid, flags);
- nfs4_lock_state();
-
status = nfsd4_lookup_stateid(cstate, stateid,
NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID,
&s, nn);
if (status)
- goto unlock_state;
+ return status;
status = check_stateid_generation(stateid, &s->sc_stateid, nfsd4_has_session(cstate));
if (status)
goto out;
@@ -4484,8 +4482,6 @@ nfs4_preprocess_stateid_op(struct net *net, struct nfsd4_compound_state *cstate,
*filpp = file;
out:
nfs4_put_stid(s);
-unlock_state:
- nfs4_unlock_state();
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 102/114] nfsd: Remove nfs4_lock_state(): nfsd4_test_stateid/nfsd4_free_stateid
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (100 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 101/114] nfsd: Remove nfs4_lock_state(): nfs4_preprocess_stateid_op() Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 103/114] nfsd: Remove nfs4_lock_state(): nfsd4_release_lockowner Jeff Layton
` (11 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 2ba896fb8d31..34aba2ae6911 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4495,11 +4495,9 @@ nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfsd4_test_stateid_id *stateid;
struct nfs4_client *cl = cstate->session->se_client;
- nfs4_lock_state();
list_for_each_entry(stateid, &test_stateid->ts_stateid_list, ts_id_list)
stateid->ts_id_status =
nfsd4_validate_stateid(cl, &stateid->ts_id_stateid);
- nfs4_unlock_state();
return nfs_ok;
}
@@ -4515,7 +4513,6 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
struct nfs4_client *cl = cstate->session->se_client;
__be32 ret = nfserr_bad_stateid;
- nfs4_lock_state();
spin_lock(&cl->cl_lock);
s = find_stateid_locked(cl, stateid);
if (!s)
@@ -4552,7 +4549,6 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
out_unlock:
spin_unlock(&cl->cl_lock);
out:
- nfs4_unlock_state();
return ret;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 103/114] nfsd: Remove nfs4_lock_state(): nfsd4_release_lockowner
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (101 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 102/114] nfsd: Remove nfs4_lock_state(): nfsd4_test_stateid/nfsd4_free_stateid Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 104/114] nfsd: Remove nfs4_lock_state(): nfsd4_lock/locku/lockt() Jeff Layton
` (10 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 8 ++------
1 file changed, 2 insertions(+), 6 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 34aba2ae6911..99e51d4e097e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5518,11 +5518,9 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n",
clid->cl_boot, clid->cl_id);
- nfs4_lock_state();
-
status = lookup_clientid(clid, cstate, nn);
if (status)
- goto out;
+ return status;
clp = cstate->clp;
/* Find the matching lock stateowner */
@@ -5539,7 +5537,7 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
if (check_for_locks(stp->st_stid.sc_file, lo)) {
status = nfserr_locks_held;
spin_unlock(&clp->cl_lock);
- goto out;
+ return status;
}
}
@@ -5549,8 +5547,6 @@ nfsd4_release_lockowner(struct svc_rqst *rqstp,
spin_unlock(&clp->cl_lock);
if (lo)
release_lockowner(lo);
-out:
- nfs4_unlock_state();
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 104/114] nfsd: Remove nfs4_lock_state(): nfsd4_lock/locku/lockt()
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (102 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 103/114] nfsd: Remove nfs4_lock_state(): nfsd4_release_lockowner Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 105/114] nfsd: Remove nfs4_lock_state(): nfsd4_open_downgrade + nfsd4_close Jeff Layton
` (9 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 9 ---------
1 file changed, 9 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 99e51d4e097e..ba42aa4e4b51 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5160,8 +5160,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
return status;
}
- nfs4_lock_state();
-
if (lock->lk_is_new) {
if (nfsd4_has_session(cstate))
/* See rfc 5661 18.10.3: given clientid is ignored: */
@@ -5299,7 +5297,6 @@ out:
if (open_stp)
put_generic_stateid(open_stp);
nfsd4_bump_seqid(cstate, status);
- nfs4_unlock_state();
if (file_lock)
locks_free_lock(file_lock);
if (conflock)
@@ -5342,8 +5339,6 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (check_lock_length(lockt->lt_offset, lockt->lt_length))
return nfserr_inval;
- nfs4_lock_state();
-
if (!nfsd4_has_session(cstate)) {
status = lookup_clientid(&lockt->lt_clientid, cstate, nn);
if (status)
@@ -5398,7 +5393,6 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
out:
if (lo)
nfs4_put_stateowner(&lo->lo_owner);
- nfs4_unlock_state();
if (file_lock)
locks_free_lock(file_lock);
return status;
@@ -5422,8 +5416,6 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (check_lock_length(locku->lu_offset, locku->lu_length))
return nfserr_inval;
- nfs4_lock_state();
-
status = nfs4_preprocess_seqid_op(cstate, locku->lu_seqid,
&locku->lu_stateid, NFS4_LOCK_STID,
&stp, nn);
@@ -5466,7 +5458,6 @@ put_stateid:
put_generic_stateid(stp);
out:
nfsd4_bump_seqid(cstate, status);
- nfs4_unlock_state();
if (file_lock)
locks_free_lock(file_lock);
return status;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 105/114] nfsd: Remove nfs4_lock_state(): nfsd4_open_downgrade + nfsd4_close
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (103 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 104/114] nfsd: Remove nfs4_lock_state(): nfsd4_lock/locku/lockt() Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 106/114] nfsd: Remove nfs4_lock_state(): nfsd4_delegreturn() Jeff Layton
` (8 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index ba42aa4e4b51..7910c9b1dc3f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4672,7 +4672,6 @@ put_stateid:
put_generic_stateid(stp);
out:
nfsd4_bump_seqid(cstate, status);
- nfs4_unlock_state();
return status;
}
@@ -4719,7 +4718,6 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
dprintk("NFSD: %s: od_deleg_want=0x%x ignored\n", __func__,
od->od_deleg_want);
- nfs4_lock_state();
status = nfs4_preprocess_confirmed_seqid_op(cstate, od->od_seqid,
&od->od_stateid, &stp, nn);
if (status)
@@ -4785,7 +4783,6 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
dprintk("NFSD: nfsd4_close on file %pd\n",
cstate->current_fh.fh_dentry);
- nfs4_lock_state();
status = nfs4_preprocess_seqid_op(cstate, close->cl_seqid,
&close->cl_stateid,
NFS4_OPEN_STID|NFS4_CLOSED_STID,
@@ -4801,7 +4798,6 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
/* put reference from nfs4_preprocess_seqid_op */
put_generic_stateid(stp);
out:
- nfs4_unlock_state();
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 106/114] nfsd: Remove nfs4_lock_state(): nfsd4_delegreturn()
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (104 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 105/114] nfsd: Remove nfs4_lock_state(): nfsd4_open_downgrade + nfsd4_close Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 107/114] nfsd: Remove nfs4_lock_state(): nfsd4_open and nfsd4_open_confirm Jeff Layton
` (7 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 7910c9b1dc3f..952aca4d3b2d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4814,7 +4814,6 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0)))
return status;
- nfs4_lock_state();
status = nfsd4_lookup_stateid(cstate, stateid, NFS4_DELEG_STID, &s, nn);
if (status)
goto out;
@@ -4827,8 +4826,6 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
put_stateid:
nfs4_put_delegation(dp);
out:
- nfs4_unlock_state();
-
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 107/114] nfsd: Remove nfs4_lock_state(): nfsd4_open and nfsd4_open_confirm
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (105 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 106/114] nfsd: Remove nfs4_lock_state(): nfsd4_delegreturn() Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 108/114] nfsd: Remove nfs4_lock_state(): exchange_id, create/destroy_session() Jeff Layton
` (6 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4proc.c | 3 ---
fs/nfsd/nfs4state.c | 6 ------
2 files changed, 9 deletions(-)
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index cdce2f39b09c..8381f9429340 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -385,8 +385,6 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (nfsd4_has_session(cstate))
copy_clientid(&open->op_clientid, cstate->session);
- nfs4_lock_state();
-
/* check seqid for replay. set nfs4_owner */
resp = rqstp->rq_resp;
status = nfsd4_process_open1(&resp->cstate, open, nn);
@@ -469,7 +467,6 @@ out:
}
nfsd4_cleanup_open_state(cstate, open, status);
nfsd4_bump_seqid(cstate, status);
- nfs4_unlock_state();
return status;
}
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 952aca4d3b2d..13615fe64b48 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3969,9 +3969,6 @@ static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open,
*/
}
-/*
- * called with nfs4_lock_state() held.
- */
__be32
nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
{
@@ -4649,8 +4646,6 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (status)
return status;
- nfs4_lock_state();
-
status = nfs4_preprocess_seqid_op(cstate,
oc->oc_seqid, &oc->oc_req_stateid,
NFS4_OPEN_STID, &stp, nn);
@@ -4744,7 +4739,6 @@ put_stateid:
put_generic_stateid(stp);
out:
nfsd4_bump_seqid(cstate, status);
- nfs4_unlock_state();
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 108/114] nfsd: Remove nfs4_lock_state(): exchange_id, create/destroy_session()
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (106 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 107/114] nfsd: Remove nfs4_lock_state(): nfsd4_open and nfsd4_open_confirm Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 109/114] nfsd: Remove nfs4_lock_state(): setclientid, setclientid_confirm, renew Jeff Layton
` (5 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Also destroy_clientid and bind_conn_to_session.
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 11 -----------
1 file changed, 11 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 13615fe64b48..afe9602ca208 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2149,7 +2149,6 @@ nfsd4_exchange_id(struct svc_rqst *rqstp,
return nfserr_jukebox;
/* Cases below refer to rfc 5661 section 18.35.4: */
- nfs4_lock_state();
spin_lock(&nn->client_lock);
conf = find_confirmed_client_by_name(&exid->clname, nn);
if (conf) {
@@ -2228,7 +2227,6 @@ out_copy:
out:
spin_unlock(&nn->client_lock);
- nfs4_unlock_state();
if (new)
expire_client(new);
if (unconf)
@@ -2402,7 +2400,6 @@ nfsd4_create_session(struct svc_rqst *rqstp,
if (!conn)
goto out_free_session;
- nfs4_lock_state();
spin_lock(&nn->client_lock);
unconf = find_unconfirmed_client(&cr_ses->clientid, true, nn);
conf = find_confirmed_client(&cr_ses->clientid, true, nn);
@@ -2472,13 +2469,11 @@ nfsd4_create_session(struct svc_rqst *rqstp,
/* init connection and backchannel */
nfsd4_init_conn(rqstp, conn, new);
nfsd4_put_session(new);
- nfs4_unlock_state();
if (old)
expire_client(old);
return status;
out_free_conn:
spin_unlock(&nn->client_lock);
- nfs4_unlock_state();
free_conn(conn);
if (old)
expire_client(old);
@@ -2534,7 +2529,6 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
if (!nfsd4_last_compound_op(rqstp))
return nfserr_not_only_op;
- nfs4_lock_state();
spin_lock(&nn->client_lock);
session = find_in_sessionid_hashtbl(&bcts->sessionid, net, &status);
spin_unlock(&nn->client_lock);
@@ -2555,7 +2549,6 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
out:
nfsd4_put_session(session);
out_no_session:
- nfs4_unlock_state();
return status;
}
@@ -2577,7 +2570,6 @@ nfsd4_destroy_session(struct svc_rqst *r,
struct net *net = SVC_NET(r);
struct nfsd_net *nn = net_generic(net, nfsd_net_id);
- nfs4_lock_state();
status = nfserr_not_only_op;
if (nfsd4_compound_in_session(cstate->session, &sessionid->sessionid)) {
if (!nfsd4_last_compound_op(r))
@@ -2607,7 +2599,6 @@ out_put_session:
out_client_lock:
spin_unlock(&nn->client_lock);
out:
- nfs4_unlock_state();
return status;
}
@@ -2810,7 +2801,6 @@ nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
__be32 status = 0;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
- nfs4_lock_state();
spin_lock(&nn->client_lock);
unconf = find_unconfirmed_client(&dc->clientid, true, nn);
conf = find_confirmed_client(&dc->clientid, true, nn);
@@ -2839,7 +2829,6 @@ nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
unhash_client_locked(clp);
out:
spin_unlock(&nn->client_lock);
- nfs4_unlock_state();
if (clp)
expire_client(clp);
return status;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 109/114] nfsd: Remove nfs4_lock_state(): setclientid, setclientid_confirm, renew
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (107 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 108/114] nfsd: Remove nfs4_lock_state(): exchange_id, create/destroy_session() Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 110/114] nfsd: Remove nfs4_lock_state(): reclaim_complete() Jeff Layton
` (4 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 6 ------
1 file changed, 6 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index afe9602ca208..f074d1b2d8ce 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2888,7 +2888,6 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
if (new == NULL)
return nfserr_jukebox;
/* Cases below refer to rfc 3530 section 14.2.33: */
- nfs4_lock_state();
spin_lock(&nn->client_lock);
conf = find_confirmed_client_by_name(&clname, nn);
if (conf) {
@@ -2923,7 +2922,6 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
status = nfs_ok;
out:
spin_unlock(&nn->client_lock);
- nfs4_unlock_state();
if (new)
free_client(new);
if (unconf)
@@ -2946,7 +2944,6 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
if (STALE_CLIENTID(clid, nn))
return nfserr_stale_clientid;
- nfs4_lock_state();
spin_lock(&nn->client_lock);
conf = find_confirmed_client(clid, false, nn);
@@ -2996,7 +2993,6 @@ out:
spin_unlock(&nn->client_lock);
if (old)
expire_client(old);
- nfs4_unlock_state();
return status;
}
@@ -4076,7 +4072,6 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
__be32 status;
struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
- nfs4_lock_state();
dprintk("process_renew(%08x/%08x): starting\n",
clid->cl_boot, clid->cl_id);
status = lookup_clientid(clid, cstate, nn);
@@ -4089,7 +4084,6 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
goto out;
status = nfs_ok;
out:
- nfs4_unlock_state();
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 110/114] nfsd: Remove nfs4_lock_state(): reclaim_complete()
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (108 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 109/114] nfsd: Remove nfs4_lock_state(): setclientid, setclientid_confirm, renew Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 111/114] nfsd: remove nfs4_lock_state: nfs4_laundromat Jeff Layton
` (3 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs, Trond Myklebust
From: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
---
fs/nfsd/nfs4state.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f074d1b2d8ce..740f4ea47d48 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2849,7 +2849,6 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
return nfs_ok;
}
- nfs4_lock_state();
status = nfserr_complete_already;
if (test_and_set_bit(NFSD4_CLIENT_RECLAIM_COMPLETE,
&cstate->session->se_client->cl_flags))
@@ -2869,7 +2868,6 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *csta
status = nfs_ok;
nfsd4_client_record_create(cstate->session->se_client);
out:
- nfs4_unlock_state();
return status;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 111/114] nfsd: remove nfs4_lock_state: nfs4_laundromat
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (109 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 110/114] nfsd: Remove nfs4_lock_state(): reclaim_complete() Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:54 ` [PATCH v3 112/114] nfsd: remove nfs4_lock_state: nfs4_state_shutdown_net Jeff Layton
` (2 subsequent siblings)
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 740f4ea47d48..5d3c4679d48d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4115,8 +4115,6 @@ nfs4_laundromat(struct nfsd_net *nn)
time_t cutoff = get_seconds() - nn->nfsd4_lease;
time_t t, new_timeo = nn->nfsd4_lease;
- nfs4_lock_state();
-
dprintk("NFSD: laundromat service - starting\n");
nfsd4_end_grace(nn);
INIT_LIST_HEAD(&reaplist);
@@ -4184,7 +4182,6 @@ nfs4_laundromat(struct nfsd_net *nn)
spin_unlock(&nn->client_lock);
new_timeo = max_t(time_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT);
- nfs4_unlock_state();
return new_timeo;
}
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 112/114] nfsd: remove nfs4_lock_state: nfs4_state_shutdown_net
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (110 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 111/114] nfsd: remove nfs4_lock_state: nfs4_laundromat Jeff Layton
@ 2014-06-30 15:54 ` Jeff Layton
2014-06-30 15:55 ` [PATCH v3 113/114] nfsd: remove the client_mutex and the nfs4_lock/unlock_state wrappers Jeff Layton
2014-06-30 15:55 ` [PATCH v3 114/114] nfsd: add some comments to the nfsd4 object definitions Jeff Layton
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:54 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 2 --
1 file changed, 2 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 5d3c4679d48d..36a8ba158ed3 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -6333,7 +6333,6 @@ nfs4_state_shutdown_net(struct net *net)
cancel_delayed_work_sync(&nn->laundromat_work);
locks_end_grace(&nn->nfsd4_manager);
- nfs4_lock_state();
INIT_LIST_HEAD(&reaplist);
spin_lock(&state_lock);
list_for_each_safe(pos, next, &nn->del_recall_lru) {
@@ -6350,7 +6349,6 @@ nfs4_state_shutdown_net(struct net *net)
nfsd4_client_tracking_exit(net);
nfs4_state_destroy_net(net);
- nfs4_unlock_state();
}
void
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 113/114] nfsd: remove the client_mutex and the nfs4_lock/unlock_state wrappers
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (111 preceding siblings ...)
2014-06-30 15:54 ` [PATCH v3 112/114] nfsd: remove nfs4_lock_state: nfs4_state_shutdown_net Jeff Layton
@ 2014-06-30 15:55 ` Jeff Layton
2014-06-30 15:55 ` [PATCH v3 114/114] nfsd: add some comments to the nfsd4 object definitions Jeff Layton
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:55 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/nfs4state.c | 15 ---------------
1 file changed, 15 deletions(-)
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 36a8ba158ed3..6895bc518d88 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -80,9 +80,6 @@ static void nfs4_put_stateowner(struct nfs4_stateowner *sop);
/* Locking: */
-/* Currently used for almost all code touching nfsv4 state: */
-static DEFINE_MUTEX(client_mutex);
-
/*
* Currently used for the del_recall_lru and file hash table. In an
* effort to decrease the scope of the client_mutex, this spinlock may
@@ -102,12 +99,6 @@ static struct kmem_cache *file_slab;
static struct kmem_cache *stateid_slab;
static struct kmem_cache *deleg_slab;
-void
-nfs4_lock_state(void)
-{
- mutex_lock(&client_mutex);
-}
-
static void free_session(struct nfsd4_session *);
static bool is_session_dead(struct nfsd4_session *ses)
@@ -123,12 +114,6 @@ static __be32 mark_session_dead_locked(struct nfsd4_session *ses, int ref_held_b
return nfs_ok;
}
-void
-nfs4_unlock_state(void)
-{
- mutex_unlock(&client_mutex);
-}
-
static bool is_client_expired(struct nfs4_client *clp)
{
return clp->cl_time == 0;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread* [PATCH v3 114/114] nfsd: add some comments to the nfsd4 object definitions
2014-06-30 15:48 [PATCH v3 000/114] nfsd: eliminate the client_mutex Jeff Layton
` (112 preceding siblings ...)
2014-06-30 15:55 ` [PATCH v3 113/114] nfsd: remove the client_mutex and the nfs4_lock/unlock_state wrappers Jeff Layton
@ 2014-06-30 15:55 ` Jeff Layton
113 siblings, 0 replies; 151+ messages in thread
From: Jeff Layton @ 2014-06-30 15:55 UTC (permalink / raw)
To: bfields; +Cc: linux-nfs
Add some comments that describe what each of these objects is, and how
they related to one another.
Signed-off-by: Jeff Layton <jlayton@primarydata.com>
---
fs/nfsd/netns.h | 8 +++++
fs/nfsd/state.h | 91 ++++++++++++++++++++++++++++++++++++++++++++++++++++-----
2 files changed, 92 insertions(+), 7 deletions(-)
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 831abbdc6c52..4daa485a4a1d 100644
--- a/fs/nfsd/netns.h
+++ b/fs/nfsd/netns.h
@@ -34,6 +34,14 @@
struct cld_net;
struct nfsd4_client_tracking_ops;
+/*
+ * Represents a nfsd "container". With respect to nfsv4 state tracking, the
+ * fields of interest are the *_id_hashtbls and the *_name_tree. These track
+ * the nfs4_client objects by either short or long form clientid.
+ *
+ * Each nfsd_net runs a nfs4_laundromat workqueue job every lease period to
+ * clean up expired clients and delegations within the container.
+ */
struct nfsd_net {
struct cld_net *cld_net;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index c39ff5e1509f..806225fcda11 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -72,6 +72,11 @@ struct nfsd4_callback {
bool cb_done;
};
+/*
+ * A core object that represents a "common" stateid. These are generally
+ * embedded within the different (more specific) stateid objects and contain
+ * fields that are of general use to any stateid.
+ */
struct nfs4_stid {
atomic_t sc_count;
#define NFS4_OPEN_STID 1
@@ -90,6 +95,18 @@ struct nfs4_stid {
void (*sc_free)(struct nfs4_stid *);
};
+/*
+ * Represents a delegation stateid. The nfs4_client holds references to these
+ * and they are put when it is being destroyed or when the delegation is
+ * returned by the client.
+ *
+ * If the server attempts to recall a delegation and the client doesn't do so
+ * before a timeout, the server may also revoke the delegation. In that case,
+ * the object will either be destroyed (v4.0) or moved to a per-client list of
+ * revoked delegations (v4.1+).
+ *
+ * This object is a superset of the nfs4_stid.
+ */
struct nfs4_delegation {
struct nfs4_stid dl_stid; /* must be first field */
struct list_head dl_perfile;
@@ -197,6 +214,11 @@ struct nfsd4_conn {
unsigned char cn_flags;
};
+/*
+ * Representation of a v4.1+ session. These are refcounted in a similar fashion
+ * to the nfs4_client. References are only taken when the server is actively
+ * working on the object (primarily during the processing of compounds).
+ */
struct nfsd4_session {
atomic_t se_ref;
struct list_head se_hash; /* hash by sessionid */
@@ -226,13 +248,30 @@ struct nfsd4_sessionid {
/*
* struct nfs4_client - one per client. Clientids live here.
- * o Each nfs4_client is hashed by clientid.
*
- * o Each nfs4_clients is also hashed by name
- * (the opaque quantity initially sent by the client to identify itself).
+ * The initial object created by an NFS client using SETCLIENTID (for NFSv4.0)
+ * or EXCHANGE_ID (for NFSv4.1+). These objects are refcounted and timestamped.
+ * Each nfsd_net_ns object contains a set of these and they are tracked via
+ * short and long form clientid. They are hashed and searched for under the
+ * per-nfsd_net client_lock spinlock.
+ *
+ * References to it are only held during the processing of compounds, and in
+ * certain other operations. In their "resting state" they have a refcount of
+ * 0. If they are not renewed within a lease period, they become eligible for
+ * destruction by the laundromat.
+ *
+ * These objects can also be destroyed prematurely by the fault injection code,
+ * or if the client sends certain forms of SETCLIENTID or EXCHANGE_ID updates.
+ * Care is taken *not* to do this however when the objects have an elevated
+ * refcount.
+ *
+ * o Each nfs4_client is hashed by clientid
+ *
+ * o Each nfs4_clients is also hashed by name (the opaque quantity initially
+ * sent by the client to identify itself).
*
- * o cl_perclient list is used to ensure no dangling stateowner references
- * when we expire the nfs4_client
+ * o cl_perclient list is used to ensure no dangling stateowner references
+ * when we expire the nfs4_client
*/
struct nfs4_client {
struct list_head cl_idhash; /* hash by cl_clientid.id */
@@ -335,6 +374,12 @@ struct nfs4_replay {
char rp_ibuf[NFSD4_REPLAY_ISIZE];
};
+/*
+ * A core object that represents either an open or lock owner. The object and
+ * lock owner objects have one of these embedded within them. Refcounts and
+ * other fields common to both owner types are contained within these
+ * structures.
+ */
struct nfs4_stateowner {
struct list_head so_strhash; /* hash by op_name */
struct list_head so_stateids;
@@ -351,6 +396,12 @@ struct nfs4_stateowner {
void (*so_unhash)(struct nfs4_stateowner *);
};
+/*
+ * When a file is opened, the client provides an open state owner opaque string
+ * that indicates the "owner" of that open. These objects are refcounted.
+ * References to it are held by each open state associated with it. This object
+ * is a superset of the nfs4_stateowner struct.
+ */
struct nfs4_openowner {
struct nfs4_stateowner oo_owner; /* must be first field */
struct list_head oo_perclient;
@@ -368,6 +419,12 @@ struct nfs4_openowner {
unsigned char oo_flags;
};
+/*
+ * Represents a generic "lockowner". Similar to an openowner. References to it
+ * are held by the lock stateids that are created on its behalf. This object is
+ * a superset of the nfs4_stateowner struct (or would be if it needed any extra
+ * fields).
+ */
struct nfs4_lockowner {
struct nfs4_stateowner lo_owner; /* must be first element */
};
@@ -382,7 +439,14 @@ static inline struct nfs4_lockowner * lockowner(struct nfs4_stateowner *so)
return container_of(so, struct nfs4_lockowner, lo_owner);
}
-/* nfs4_file: a file opened by some number of (open) nfs4_stateowners. */
+/*
+ * nfs4_file: a file opened by some number of (open) nfs4_stateowners.
+ *
+ * These objects are global. nfsd only keeps one instance of a nfs4_file per
+ * inode (though it may keep multiple file descriptors open per inode). These
+ * are tracked in the file_hashtbl which is protected by the state_lock
+ * spinlock.
+ */
struct nfs4_file {
atomic_t fi_ref;
spinlock_t fi_lock;
@@ -407,7 +471,20 @@ struct nfs4_file {
bool fi_had_conflict;
};
-/* "ol" stands for "Open or Lock". Better suggestions welcome. */
+/*
+ * A generic struct representing either a open or lock stateid. The nfs4_client
+ * holds a reference to each of these objects, and they in turn hold a
+ * reference to their respective stateowners. The client's reference is
+ * released in response to a close or unlock (depending on whether it's an open
+ * or lock stateid) or when the client is being destroyed.
+ *
+ * In the case of v4.0 open stateids, these objects are preserved for a little
+ * while after close in order to handle CLOSE replays. Those are eventually
+ * reclaimed via a LRU scheme by the laundromat.
+ *
+ * This object is a superset of the nfs4_stid. "ol" stands for "Open or Lock".
+ * Better suggestions welcome.
+ */
struct nfs4_ol_stateid {
struct nfs4_stid st_stid; /* must be first field */
struct list_head st_perfile;
--
1.9.3
^ permalink raw reply related [flat|nested] 151+ messages in thread