From: "J. Bruce Fields" <bfields@fieldses.org>
To: Tejun Heo <tj@kernel.org>
Cc: akpm@linux-foundation.org, linux-kernel@vger.kernel.org,
rusty@rustcorp.com.au, skinsbursky@parallels.com,
ebiederm@xmission.com, jmorris@namei.org, axboe@kernel.dk
Subject: Re: [PATCHSET] idr: implement idr_alloc() and convert existing users
Date: Sun, 3 Feb 2013 19:15:58 -0500 [thread overview]
Message-ID: <20130204001557.GB24778@fieldses.org> (raw)
In-Reply-To: <20130203170241.GA24778@fieldses.org>
On Sun, Feb 03, 2013 at 12:02:41PM -0500, J. Bruce Fields wrote:
> On Sat, Feb 02, 2013 at 05:20:01PM -0800, Tejun Heo wrote:
> > * Bruce, I couldn't convert nfsd. Can you please help? More on it
> > later.
> ...
> > I converted all in-kernel users except nfsd and staging drivers. nfsd
> > splits preloading and actual id allocation in a way that per-cpu
> > preloading can't be used. I couldn't follow the control flow to
> > verify whether the current code is correct either. I think the best
> > way would be allocating ID upfront without installing the handle and
> > then later using idr_replace() to install the pointer when the ID
> > actually gets used. Bruce, would something like that be possible?
>
> Actually, I'm not even sure if that's necessary, we can probably just
> do it all at the start.
>
> I'll try to have a patch doing that tomorrow.
So, something like this.
--b.
commit 9847160469b40345e1d78a7cbf9536761bb47d91
Author: J. Bruce Fields <bfields@redhat.com>
Date: Sun Feb 3 12:23:01 2013 -0500
nfsd4: simplify idr allocation
We don't really need to preallocate at all; just allocate and initialize
everything at once, but leave the sc_type field initially 0 to prevent
finding the stateid till it's fully initialized.
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4db46aa..485b1f7 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -261,33 +261,46 @@ static inline int get_new_stid(struct nfs4_stid *stid)
return new_stid;
}
-static void init_stid(struct nfs4_stid *stid, struct nfs4_client *cl, unsigned char type)
+static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct
+kmem_cache *slab)
{
- stateid_t *s = &stid->sc_stateid;
+ struct idr *stateids = &cl->cl_stateids;
+ static int min_stateid = 0;
+ struct nfs4_stid *stid;
int new_id;
- stid->sc_type = type;
+ stid = kmem_cache_alloc(slab, GFP_KERNEL);
+ if (!stid)
+ return NULL;
+
+ if (!idr_pre_get(stateids, GFP_KERNEL))
+ goto out_free;
+ if (idr_get_new_above(stateids, stid, min_stateid, &new_id))
+ goto out_free;
stid->sc_client = cl;
- s->si_opaque.so_clid = cl->cl_clientid;
- new_id = get_new_stid(stid);
- s->si_opaque.so_id = (u32)new_id;
+ 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: */
- s->si_generation = 0;
-}
+ stid->sc_stateid.si_generation = 0;
-static struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *slab)
-{
- struct idr *stateids = &cl->cl_stateids;
-
- if (!idr_pre_get(stateids, GFP_KERNEL))
- return NULL;
/*
- * Note: if we fail here (or any time between now and the time
- * we actually get the new idr), we won't need to undo the idr
- * preallocation, since the idr code caps the number of
- * preallocated entries.
+ * It shouldn't be a problem to reuse an opaque stateid value.
+ * I don't think it is for 4.1. But with 4.0 I worry that, for
+ * example, a stray write retransmission could be accepted by
+ * the server when it should have been rejected. Therefore,
+ * adopt a trick from the sctp code to attempt to maximize the
+ * amount of time until an id is reused, by ensuring they always
+ * "increase" (mod INT_MAX):
*/
- return kmem_cache_alloc(slab, GFP_KERNEL);
+
+ min_stateid = new_id+1;
+ if (min_stateid == INT_MAX)
+ min_stateid = 0;
+ return stid;
+out_free:
+ kfree(stid);
+ return NULL;
}
static struct nfs4_ol_stateid * nfs4_alloc_stateid(struct nfs4_client *clp)
@@ -316,7 +329,7 @@ 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;
- init_stid(&dp->dl_stid, clp, NFS4_DELEG_STID);
+ dp->dl_stid.sc_type = NFS4_DELEG_STID;
/*
* delegation seqid's are never incremented. The 4.1 special
* meaning of seqid 0 isn't meaningful, really, but let's avoid
@@ -337,13 +350,21 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_ol_stateid *stp, struct sv
return dp;
}
+void free_stid(struct nfs4_stid *s, struct kmem_cache *slab)
+{
+ struct idr *stateids = &s->sc_client->cl_stateids;
+
+ idr_remove(stateids, s->sc_stateid.si_opaque.so_id);
+ kmem_cache_free(slab, s);
+}
+
void
nfs4_put_delegation(struct nfs4_delegation *dp)
{
if (atomic_dec_and_test(&dp->dl_count)) {
dprintk("NFSD: freeing dp %p\n",dp);
put_nfs4_file(dp->dl_file);
- kmem_cache_free(deleg_slab, dp);
+ free_stid(&dp->dl_stid, deleg_slab);
num_delegations--;
}
}
@@ -360,9 +381,7 @@ static void nfs4_put_deleg_lease(struct nfs4_file *fp)
static void unhash_stid(struct nfs4_stid *s)
{
- struct idr *stateids = &s->sc_client->cl_stateids;
-
- idr_remove(stateids, s->sc_stateid.si_opaque.so_id);
+ s->sc_type = 0;
}
/* Called under the state lock. */
@@ -519,7 +538,7 @@ static void close_generic_stateid(struct nfs4_ol_stateid *stp)
static void free_generic_stateid(struct nfs4_ol_stateid *stp)
{
- kmem_cache_free(stateid_slab, stp);
+ free_stid(&stp->st_stid, stateid_slab);
}
static void release_lock_stateid(struct nfs4_ol_stateid *stp)
@@ -1258,7 +1277,12 @@ static void gen_confirm(struct nfs4_client *clp)
static struct nfs4_stid *find_stateid(struct nfs4_client *cl, stateid_t *t)
{
- return idr_find(&cl->cl_stateids, t->si_opaque.so_id);
+ struct nfs4_stid *ret;
+
+ ret = idr_find(&cl->cl_stateids, t->si_opaque.so_id);
+ if (!ret || !ret->sc_type)
+ return NULL;
+ return ret;
}
static struct nfs4_stid *find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask)
@@ -2444,9 +2468,8 @@ alloc_init_open_stateowner(unsigned int strhashval, struct nfs4_client *clp, str
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;
- struct nfs4_client *clp = oo->oo_owner.so_client;
- init_stid(&stp->st_stid, clp, NFS4_OPEN_STID);
+ stp->st_stid.sc_type = NFS4_OPEN_STID;
INIT_LIST_HEAD(&stp->st_lockowners);
list_add(&stp->st_perstateowner, &oo->oo_owner.so_stateids);
list_add(&stp->st_perfile, &fp->fi_stateids);
@@ -4032,7 +4055,7 @@ alloc_init_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp, struct
stp = nfs4_alloc_stateid(clp);
if (stp == NULL)
return NULL;
- init_stid(&stp->st_stid, clp, NFS4_LOCK_STID);
+ 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;
next prev parent reply other threads:[~2013-02-04 0:16 UTC|newest]
Thread overview: 128+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-02-03 1:20 [PATCHSET] idr: implement idr_alloc() and convert existing users Tejun Heo
2013-02-03 1:20 ` [PATCH 01/62] idr: cosmetic updates to struct / initializer definitions Tejun Heo
2013-02-03 1:20 ` [PATCH 02/62] idr: relocate idr_for_each_entry() and reorganize id[r|a]_get_new() Tejun Heo
2013-02-03 1:20 ` [PATCH 03/62] idr: remove _idr_rc_to_errno() hack Tejun Heo
2013-02-03 1:20 ` [PATCH 04/62] idr: refactor idr_get_new_above() Tejun Heo
2013-02-03 1:20 ` [PATCH 05/62] idr: implement idr_preload[_end]() and idr_alloc() Tejun Heo
2013-02-04 18:32 ` [PATCH v2 " Tejun Heo
2013-02-03 1:20 ` [PATCH 06/62] block: fix synchronization and limit check in blk_alloc_devt() Tejun Heo
2013-02-06 11:00 ` Jens Axboe
2013-02-03 1:20 ` [PATCH 07/62] block: convert to idr_alloc() Tejun Heo
2013-02-04 13:10 ` Jens Axboe
2013-02-03 1:20 ` [PATCH 08/62] block/loop: " Tejun Heo
2013-02-04 13:11 ` Jens Axboe
2013-02-03 1:20 ` [PATCH 09/62] atm/nicstar: " Tejun Heo
2013-02-04 14:04 ` chas williams - CONTRACTOR
2013-02-04 17:06 ` Tejun Heo
2013-02-04 18:06 ` chas williams - CONTRACTOR
2013-02-04 18:37 ` [PATCH v3 " Tejun Heo
2013-02-03 1:20 ` [PATCH 10/62] drbd: " Tejun Heo
2013-02-03 1:20 ` [PATCH 11/62] dca: " Tejun Heo
2013-02-03 1:20 ` [PATCH 12/62] dmaengine: " Tejun Heo
2013-02-03 1:20 ` [PATCH 13/62] firewire: " Tejun Heo
2013-02-03 11:03 ` Stefan Richter
2013-02-03 11:18 ` Stefan Richter
2013-02-04 16:57 ` [PATCH 12.5/62] firewire: add minor number range check to fw_device_init() Tejun Heo
2013-02-04 18:15 ` Stefan Richter
2013-02-04 16:58 ` [PATCH v2 13/62] firewire: convert to idr_alloc() Tejun Heo
2013-02-04 18:16 ` Stefan Richter
2013-02-03 1:20 ` [PATCH 14/62] gpio: " Tejun Heo
2013-02-04 20:40 ` Linus Walleij
2013-02-03 1:20 ` [PATCH 15/62] drm: " Tejun Heo
2013-02-03 1:20 ` [PATCH 16/62] drm/exynos: " Tejun Heo
2013-02-03 1:20 ` [PATCH 17/62] drm/i915: " Tejun Heo
2013-02-04 14:53 ` Daniel Vetter
2013-02-03 1:20 ` [PATCH 18/62] drm/sis: " Tejun Heo
2013-02-03 1:20 ` [PATCH 19/62] drm/via: " Tejun Heo
2013-02-03 1:20 ` [PATCH 20/62] drm/vmwgfx: " Tejun Heo
2013-02-03 1:20 ` [PATCH 21/62] i2c: " Tejun Heo
2013-02-03 1:20 ` [PATCH 22/62] infiniband/core: " Tejun Heo
2013-02-04 16:43 ` [PATCH v2 " Tejun Heo
2013-02-05 0:07 ` Hefty, Sean
2013-02-03 1:20 ` [PATCH 23/62] infiniband/amso1100: " Tejun Heo
2013-02-03 14:36 ` Steve Wise
2013-02-03 1:20 ` [PATCH 24/62] infiniband/cxgb3: " Tejun Heo
2013-02-03 14:37 ` Steve Wise
2013-02-03 1:20 ` [PATCH 25/62] infiniband/cxgb4: " Tejun Heo
2013-02-03 14:18 ` Steve Wise
2013-02-03 14:28 ` Tejun Heo
2013-02-04 15:32 ` Steve Wise
2013-02-03 1:20 ` [PATCH 26/62] infiniband/ehca: " Tejun Heo
2013-02-03 1:20 ` [PATCH 27/62] infiniband/ipath: " Tejun Heo
2013-02-04 16:15 ` Marciniszyn, Mike
2013-02-04 16:18 ` Tejun Heo
2013-02-03 1:20 ` [PATCH 28/62] infiniband/mlx4: " Tejun Heo
2013-02-03 1:20 ` [PATCH 29/62] infiniband/ocrdma: " Tejun Heo
2013-02-03 1:20 ` [PATCH 30/62] infiniband/qib: " Tejun Heo
2013-02-03 1:20 ` [PATCH 31/62] dm: " Tejun Heo
2013-02-03 1:20 ` [PATCH 32/62] memstick: " Tejun Heo
2013-02-03 1:20 ` [PATCH 33/62] mfd: " Tejun Heo
2013-02-03 22:32 ` Samuel Ortiz
2013-02-03 1:20 ` [PATCH 34/62] misc/c2port: " Tejun Heo
2013-02-03 1:20 ` [PATCH 35/62] misc/tifm_core: " Tejun Heo
2013-02-03 1:20 ` [PATCH 36/62] mmc: " Tejun Heo
2013-02-03 1:20 ` [PATCH 37/62] mtd: " Tejun Heo
2013-02-04 13:09 ` Ezequiel Garcia
2013-02-03 1:20 ` [PATCH 38/62] i2c: " Tejun Heo
2013-02-03 1:25 ` [PATCH UPDATED 38/62] macvtap: " Tejun Heo
2013-02-03 1:20 ` [PATCH 39/62] ppp: " Tejun Heo
2013-02-03 1:20 ` [PATCH 40/62] power: " Tejun Heo
2013-02-03 3:46 ` Anton Vorontsov
2013-02-03 1:20 ` [PATCH 41/62] pps: " Tejun Heo
2013-02-03 1:20 ` [PATCH 42/62] remoteproc: " Tejun Heo
2013-02-03 1:20 ` [PATCH 43/62] rpmsg: " Tejun Heo
2013-02-03 1:20 ` [PATCH 44/62] scsi/bfa: " Tejun Heo
2013-02-03 1:20 ` [PATCH 45/62] scsi: " Tejun Heo
2013-02-03 1:20 ` [PATCH 46/62] target/iscsi: " Tejun Heo
2013-02-03 1:20 ` [PATCH 47/62] scsi/lpfc: " Tejun Heo
2013-02-11 22:46 ` James Smart
2013-02-03 1:20 ` [PATCH 48/62] thermal: " Tejun Heo
2013-02-03 1:20 ` [PATCH 49/62] uio: " Tejun Heo
2013-02-03 7:05 ` Greg Kroah-Hartman
2013-02-03 1:20 ` [PATCH 50/62] vfio: " Tejun Heo
2013-02-04 16:06 ` Alex Williamson
2013-02-04 16:48 ` [PATCH v2 " Tejun Heo
2013-02-03 1:20 ` [PATCH 51/62] dlm: " Tejun Heo
2013-02-03 1:20 ` [PATCH 52/62] inotify: " Tejun Heo
2013-02-03 1:20 ` [PATCH 53/62] ocfs2: " Tejun Heo
2013-02-03 1:20 ` [PATCH 54/62] ipc: " Tejun Heo
2013-02-03 1:20 ` [PATCH 55/62] cgroup: " Tejun Heo
2013-02-04 2:49 ` Li Zefan
2013-02-03 1:20 ` [PATCH 56/62] events: " Tejun Heo
2013-02-03 1:20 ` [PATCH 57/62] posix-timers: " Tejun Heo
2013-02-03 1:20 ` [PATCH 58/62] net/9p: " Tejun Heo
2013-02-03 1:21 ` [PATCH 59/62] mac80211: " Tejun Heo
2013-02-04 17:40 ` Johannes Berg
2013-02-04 17:42 ` Tejun Heo
2013-02-03 1:21 ` [PATCH 60/62] sctp: " Tejun Heo
2013-02-03 16:55 ` Neil Horman
2013-02-04 16:22 ` Vlad Yasevich
2013-02-04 16:37 ` Tejun Heo
2013-02-04 16:42 ` [PATCH v2 " Tejun Heo
2013-02-05 15:22 ` Neil Horman
2013-02-03 1:21 ` [PATCH 61/62] nfs4client: " Tejun Heo
2013-02-03 1:21 ` [PATCH 62/62] idr: deprecate idr_pre_get() and idr_get_new[_above]() Tejun Heo
2013-02-03 13:41 ` [PATCHSET] idr: implement idr_alloc() and convert existing users Eric W. Biederman
2013-02-03 14:13 ` Tejun Heo
2013-02-03 15:24 ` Eric W. Biederman
2013-02-03 15:47 ` Tejun Heo
2013-02-03 17:02 ` J. Bruce Fields
2013-02-04 0:15 ` J. Bruce Fields [this message]
2013-02-04 17:10 ` Tejun Heo
2013-02-04 17:11 ` Tejun Heo
2013-02-04 18:15 ` J. Bruce Fields
2013-03-21 14:06 ` J. Bruce Fields
2013-03-21 18:35 ` Tejun Heo
2013-03-26 15:19 ` Jeff Layton
2013-03-26 15:26 ` Tejun Heo
2013-03-26 16:30 ` J. Bruce Fields
2013-03-26 16:33 ` Tejun Heo
2013-03-26 16:36 ` Tejun Heo
2013-03-26 16:52 ` Jeff Layton
2013-02-04 17:16 ` J. Bruce Fields
2013-02-04 19:17 ` Tejun Heo
2013-02-04 19:54 ` Marciniszyn, Mike
2013-02-04 21:42 ` Tejun Heo
2013-02-04 22:25 ` Marciniszyn, Mike
2013-02-04 20:08 ` Marciniszyn, Mike
2013-02-04 21:43 ` Tejun Heo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20130204001557.GB24778@fieldses.org \
--to=bfields@fieldses.org \
--cc=akpm@linux-foundation.org \
--cc=axboe@kernel.dk \
--cc=ebiederm@xmission.com \
--cc=jmorris@namei.org \
--cc=linux-kernel@vger.kernel.org \
--cc=rusty@rustcorp.com.au \
--cc=skinsbursky@parallels.com \
--cc=tj@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).