diff mbox series

nfs: callback_proc: fix an incorrect NULL check on list iterator

Message ID 20220327080230.12134-1-xiam0nd.tong@gmail.com (mailing list archive)
State New, archived
Headers show
Series nfs: callback_proc: fix an incorrect NULL check on list iterator | expand

Commit Message

Xiaomeng Tong March 27, 2022, 8:02 a.m. UTC
The bug is here:
	if (!server ||
	server->pnfs_curr_ld->id != dev->cbd_layout_type) {

The list iterator value 'server' will *always* be set and non-NULL
by list_for_each_entry_rcu, so it is incorrect to assume that the
iterator value will be NULL if the list is empty or no element is
found (In fact, it will be a bogus pointer to an invalid struct
object containing the HEAD, which is used for above check at next
outer loop). Otherwise it may bypass the check in theory (iif
server->pnfs_curr_ld->id == dev->cbd_layout_type, 'server' now is
a bogus pointer) and lead to invalid memory access passing the check.

To fix the bug, use a new variable 'iter' as the list iterator,
while use the original variable 'server' as a dedicated pointer to
point to the found element.

Cc: stable@vger.kernel.org
Fixes: 1be5683b03a76 ("pnfs: CB_NOTIFY_DEVICEID")
Signed-off-by: Xiaomeng Tong <xiam0nd.tong@gmail.com>
---
 fs/nfs/callback_proc.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

Comments

Trond Myklebust March 27, 2022, 3:20 p.m. UTC | #1
On Sun, 2022-03-27 at 16:02 +0800, Xiaomeng Tong wrote:
> The bug is here:
>         if (!server ||
>         server->pnfs_curr_ld->id != dev->cbd_layout_type) {
> 
> The list iterator value 'server' will *always* be set and non-NULL
> by list_for_each_entry_rcu, so it is incorrect to assume that the
> iterator value will be NULL if the list is empty or no element is
> found (In fact, it will be a bogus pointer to an invalid struct
> object containing the HEAD, which is used for above check at next
> outer loop). Otherwise it may bypass the check in theory (iif
> server->pnfs_curr_ld->id == dev->cbd_layout_type, 'server' now is
> a bogus pointer) and lead to invalid memory access passing the check.
> 
> To fix the bug, use a new variable 'iter' as the list iterator,
> while use the original variable 'server' as a dedicated pointer to
> point to the found element.
> 
> Cc: stable@vger.kernel.org
> Fixes: 1be5683b03a76 ("pnfs: CB_NOTIFY_DEVICEID")
> Signed-off-by: Xiaomeng Tong <xiam0nd.tong@gmail.com>
> ---
>  fs/nfs/callback_proc.c | 9 +++++----
>  1 file changed, 5 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
> index c343666d9a42..84779785dc8d 100644
> --- a/fs/nfs/callback_proc.c
> +++ b/fs/nfs/callback_proc.c
> @@ -361,7 +361,7 @@ __be32 nfs4_callback_devicenotify(void *argp,
> void *resp,
>         uint32_t i;
>         __be32 res = 0;
>         struct nfs_client *clp = cps->clp;
> -       struct nfs_server *server = NULL;
> +       struct nfs_server *server = NULL, *iter;
>  
>         if (!clp) {
>                 res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
> @@ -374,10 +374,11 @@ __be32 nfs4_callback_devicenotify(void *argp,
> void *resp,
>                 if (!server ||
>                     server->pnfs_curr_ld->id != dev->cbd_layout_type)
> {
>                         rcu_read_lock();
> -                       list_for_each_entry_rcu(server, &clp-
> >cl_superblocks, client_link)
> -                               if (server->pnfs_curr_ld &&
> -                                   server->pnfs_curr_ld->id == dev-
> >cbd_layout_type) {
> +                       list_for_each_entry_rcu(iter, &clp-
> >cl_superblocks, client_link)
> +                               if (iter->pnfs_curr_ld &&
> +                                   iter->pnfs_curr_ld->id == dev-
> >cbd_layout_type) {
>                                         rcu_read_unlock();
> +                                       server = iter;

Hmm... We're not holding any locks on the super block for 'iter' here,
so nothing is preventing it from going away while we're.

Given that we really only want a pointer to the struct
pnfs_layoutdriver_type anyway, why not just convert the code to save a
pointer to that (and do it while holding the rcu_read_lock())?

The struct pnfs_layoutdriver is always expected to be a statically
allocated structure, so it won't go away as long as the pNFS driver
module remains loaded.

>                                         goto found;
>                                 }
>                         rcu_read_unlock();
Xiaomeng Tong March 28, 2022, 1:43 a.m. UTC | #2
On Sun, 27 Mar 2022 15:20:42 +0000, Trond Myklebust wrote:
> On Sun, 2022-03-27 at 16:02 +0800, Xiaomeng Tong wrote:
> > The bug is here:
> >         if (!server ||
> >         server->pnfs_curr_ld->id != dev->cbd_layout_type) {
> > 
> > The list iterator value 'server' will *always* be set and non-NULL
> > by list_for_each_entry_rcu, so it is incorrect to assume that the
> > iterator value will be NULL if the list is empty or no element is
> > found (In fact, it will be a bogus pointer to an invalid struct
> > object containing the HEAD, which is used for above check at next
> > outer loop). Otherwise it may bypass the check in theory (iif
> > server->pnfs_curr_ld->id == dev->cbd_layout_type, 'server' now is
> > a bogus pointer) and lead to invalid memory access passing the check.
> > 
> > To fix the bug, use a new variable 'iter' as the list iterator,
> > while use the original variable 'server' as a dedicated pointer to
> > point to the found element.
> > 
> > Cc: stable@vger.kernel.org
> > Fixes: 1be5683b03a76 ("pnfs: CB_NOTIFY_DEVICEID")
> > Signed-off-by: Xiaomeng Tong <xiam0nd.tong@gmail.com>
> > ---
> >  fs/nfs/callback_proc.c | 9 +++++----
> >  1 file changed, 5 insertions(+), 4 deletions(-)
> > 
> > diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
> > index c343666d9a42..84779785dc8d 100644
> > --- a/fs/nfs/callback_proc.c
> > +++ b/fs/nfs/callback_proc.c
> > @@ -361,7 +361,7 @@ __be32 nfs4_callback_devicenotify(void *argp,
> > void *resp,
> >         uint32_t i;
> >         __be32 res = 0;
> >         struct nfs_client *clp = cps->clp;
> > -       struct nfs_server *server = NULL;
> > +       struct nfs_server *server = NULL, *iter;
> >  
> >         if (!clp) {
> >                 res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
> > @@ -374,10 +374,11 @@ __be32 nfs4_callback_devicenotify(void *argp,
> > void *resp,
> >                 if (!server ||
> >                     server->pnfs_curr_ld->id != dev->cbd_layout_type)
> > {
> >                         rcu_read_lock();
> > -                       list_for_each_entry_rcu(server, &clp-
> > >cl_superblocks, client_link)
> > -                               if (server->pnfs_curr_ld &&
> > -                                   server->pnfs_curr_ld->id == dev-
> > >cbd_layout_type) {
> > +                       list_for_each_entry_rcu(iter, &clp-
> > >cl_superblocks, client_link)
> > +                               if (iter->pnfs_curr_ld &&
> > +                                   iter->pnfs_curr_ld->id == dev-
> > >cbd_layout_type) {
> >                                         rcu_read_unlock();
> > +                                       server = iter;
> 
> Hmm... We're not holding any locks on the super block for 'iter' here,
> so nothing is preventing it from going away while we're.
> 

ok, i am not a 'rcu lock' expert, i will make it hold the rcu_read_lock()
if necessary.

> Given that we really only want a pointer to the struct
> pnfs_layoutdriver_type anyway, why not just convert the code to save a
> pointer to that (and do it while holding the rcu_read_lock())?
> 

Maybe it's not that simple. If you only save a pointer to that and still
use 'server' as the list iterator of list_for_each_entry_rcu, there could
be problem.

I.e., if no element found in list_for_each_entry_rcu in the first outer
'for' loop, and now 'server' is a bogus pointer to an invalid struct, and
continue to go into the second outer 'for' loop, and the check below will
lead to invalid memory access (server->pnfs_curr_ld->id), even can potentialy
be bypassed with crafted data to make the condition false and mistakely run
nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id); with bogus
'server'.

if (!server ||
    server->pnfs_curr_ld->id != dev->cbd_layout_type) {

> The struct pnfs_layoutdriver is always expected to be a statically
> allocated structure, so it won't go away as long as the pNFS driver
> module remains loaded.
>

--
Xiaomeng Tong
Trond Myklebust March 28, 2022, 1:24 p.m. UTC | #3
On Mon, 2022-03-28 at 09:43 +0800, Xiaomeng Tong wrote:
> On Sun, 27 Mar 2022 15:20:42 +0000, Trond Myklebust wrote:
> > On Sun, 2022-03-27 at 16:02 +0800, Xiaomeng Tong wrote:
> > > The bug is here:
> > >         if (!server ||
> > >         server->pnfs_curr_ld->id != dev->cbd_layout_type) {
> > > 
> > > The list iterator value 'server' will *always* be set and non-
> > > NULL
> > > by list_for_each_entry_rcu, so it is incorrect to assume that the
> > > iterator value will be NULL if the list is empty or no element is
> > > found (In fact, it will be a bogus pointer to an invalid struct
> > > object containing the HEAD, which is used for above check at next
> > > outer loop). Otherwise it may bypass the check in theory (iif
> > > server->pnfs_curr_ld->id == dev->cbd_layout_type, 'server' now is
> > > a bogus pointer) and lead to invalid memory access passing the
> > > check.
> > > 
> > > To fix the bug, use a new variable 'iter' as the list iterator,
> > > while use the original variable 'server' as a dedicated pointer
> > > to
> > > point to the found element.
> > > 
> > > Cc: stable@vger.kernel.org
> > > Fixes: 1be5683b03a76 ("pnfs: CB_NOTIFY_DEVICEID")
> > > Signed-off-by: Xiaomeng Tong <xiam0nd.tong@gmail.com>
> > > ---
> > >  fs/nfs/callback_proc.c | 9 +++++----
> > >  1 file changed, 5 insertions(+), 4 deletions(-)
> > > 
> > > diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
> > > index c343666d9a42..84779785dc8d 100644
> > > --- a/fs/nfs/callback_proc.c
> > > +++ b/fs/nfs/callback_proc.c
> > > @@ -361,7 +361,7 @@ __be32 nfs4_callback_devicenotify(void *argp,
> > > void *resp,
> > >         uint32_t i;
> > >         __be32 res = 0;
> > >         struct nfs_client *clp = cps->clp;
> > > -       struct nfs_server *server = NULL;
> > > +       struct nfs_server *server = NULL, *iter;
> > >  
> > >         if (!clp) {
> > >                 res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
> > > @@ -374,10 +374,11 @@ __be32 nfs4_callback_devicenotify(void
> > > *argp,
> > > void *resp,
> > >                 if (!server ||
> > >                     server->pnfs_curr_ld->id != dev-
> > > >cbd_layout_type)
> > > {
> > >                         rcu_read_lock();
> > > -                       list_for_each_entry_rcu(server, &clp-
> > > > cl_superblocks, client_link)
> > > -                               if (server->pnfs_curr_ld &&
> > > -                                   server->pnfs_curr_ld->id ==
> > > dev-
> > > > cbd_layout_type) {
> > > +                       list_for_each_entry_rcu(iter, &clp-
> > > > cl_superblocks, client_link)
> > > +                               if (iter->pnfs_curr_ld &&
> > > +                                   iter->pnfs_curr_ld->id ==
> > > dev-
> > > > cbd_layout_type) {
> > >                                         rcu_read_unlock();
> > > +                                       server = iter;
> > 
> > Hmm... We're not holding any locks on the super block for 'iter'
> > here,
> > so nothing is preventing it from going away while we're.
> > 
> 
> ok, i am not a 'rcu lock' expert, i will make it hold the
> rcu_read_lock()
> if necessary.
> 
> > Given that we really only want a pointer to the struct
> > pnfs_layoutdriver_type anyway, why not just convert the code to
> > save a
> > pointer to that (and do it while holding the rcu_read_lock())?
> > 
> 
> Maybe it's not that simple. If you only save a pointer to that and
> still
> use 'server' as the list iterator of list_for_each_entry_rcu, there
> could
> be problem.
> 
> I.e., if no element found in list_for_each_entry_rcu in the first
> outer
> 'for' loop, and now 'server' is a bogus pointer to an invalid struct,
> and
> continue to go into the second outer 'for' loop, and the check below
> will
> lead to invalid memory access (server->pnfs_curr_ld->id), even can
> potentialy
> be bypassed with crafted data to make the condition false and
> mistakely run
> nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id);
> with bogus
> 'server'.
> 
> if (!server ||
>     server->pnfs_curr_ld->id != dev->cbd_layout_type) {
> 
> > The struct pnfs_layoutdriver is always expected to be a statically
> > allocated structure, so it won't go away as long as the pNFS driver
> > module remains loaded.
> 


Let's just do the following.

8<-----------------------------------------------
From 7c9d845f0612e5bcd23456a2ec43be8ac43458f1 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Mon, 28 Mar 2022 08:36:34 -0400
Subject: [PATCH] NFSv4/pNFS: Fix another issue with a list iterator pointing
 to the head

In nfs4_callback_devicenotify(), if we don't find a matching entry for
the deviceid, we're left with a pointer to 'struct nfs_server' that
actually points to the list of super blocks associated with our struct
nfs_client.
Furthermore, even if we have a valid pointer, nothing pins the super
block, and so the struct nfs_server could end up getting freed while
we're using it.

Since all we want is a pointer to the struct pnfs_layoutdriver_type,
let's skip all the iteration over super blocks, and just use APIs to
find the layout driver directly.

Reported-by: Xiaomeng Tong <xiam0nd.tong@gmail.com>
Fixes: 1be5683b03a7 ("pnfs: CB_NOTIFY_DEVICEID")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/callback_proc.c | 27 +++++++++------------------
 fs/nfs/pnfs.c          | 11 +++++++++++
 fs/nfs/pnfs.h          |  2 ++
 3 files changed, 22 insertions(+), 18 deletions(-)

diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index 39d1ec870d90..c8520284dda7 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -358,12 +358,11 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp,
 				  struct cb_process_state *cps)
 {
 	struct cb_devicenotifyargs *args = argp;
+	const struct pnfs_layoutdriver_type *ld = NULL;
 	uint32_t i;
 	__be32 res = 0;
-	struct nfs_client *clp = cps->clp;
-	struct nfs_server *server = NULL;
 
-	if (!clp) {
+	if (!cps->clp) {
 		res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
 		goto out;
 	}
@@ -371,23 +370,15 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp,
 	for (i = 0; i < args->ndevs; i++) {
 		struct cb_devicenotifyitem *dev = &args->devs[i];
 
-		if (!server ||
-		    server->pnfs_curr_ld->id != dev->cbd_layout_type) {
-			rcu_read_lock();
-			list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
-				if (server->pnfs_curr_ld &&
-				    server->pnfs_curr_ld->id == dev->cbd_layout_type) {
-					rcu_read_unlock();
-					goto found;
-				}
-			rcu_read_unlock();
-			continue;
+		if (!ld || ld->id != dev->cbd_layout_type) {
+			pnfs_put_layoutdriver(ld);
+			ld = pnfs_find_layoutdriver(dev->cbd_layout_type);
+			if (!ld)
+				continue;
 		}
-
-	found:
-		nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id);
+		nfs4_delete_deviceid(ld, cps->clp, &dev->cbd_dev_id);
 	}
-
+	pnfs_put_layoutdriver(ld);
 out:
 	kfree(args->devs);
 	return res;
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index de318bb5d349..856c962273c7 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -92,6 +92,17 @@ find_pnfs_driver(u32 id)
 	return local;
 }
 
+const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id)
+{
+	return find_pnfs_driver(id);
+}
+
+void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld)
+{
+	if (ld)
+		module_put(ld->owner);
+}
+
 void
 unset_pnfs_layoutdriver(struct nfs_server *nfss)
 {
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index f4d7548d67b2..07f11489e4e9 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -234,6 +234,8 @@ struct pnfs_devicelist {
 
 extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *);
 extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
+extern const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id);
+extern void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld);
 
 /* nfs4proc.c */
 extern size_t max_response_pages(struct nfs_server *server);
Greg KH March 28, 2022, 1:43 p.m. UTC | #4
On Mon, Mar 28, 2022 at 01:24:57PM +0000, Trond Myklebust wrote:
> On Mon, 2022-03-28 at 09:43 +0800, Xiaomeng Tong wrote:
> > On Sun, 27 Mar 2022 15:20:42 +0000, Trond Myklebust wrote:
> > > On Sun, 2022-03-27 at 16:02 +0800, Xiaomeng Tong wrote:
> > > > The bug is here:
> > > >         if (!server ||
> > > >         server->pnfs_curr_ld->id != dev->cbd_layout_type) {
> > > > 
> > > > The list iterator value 'server' will *always* be set and non-
> > > > NULL
> > > > by list_for_each_entry_rcu, so it is incorrect to assume that the
> > > > iterator value will be NULL if the list is empty or no element is
> > > > found (In fact, it will be a bogus pointer to an invalid struct
> > > > object containing the HEAD, which is used for above check at next
> > > > outer loop). Otherwise it may bypass the check in theory (iif
> > > > server->pnfs_curr_ld->id == dev->cbd_layout_type, 'server' now is
> > > > a bogus pointer) and lead to invalid memory access passing the
> > > > check.
> > > > 
> > > > To fix the bug, use a new variable 'iter' as the list iterator,
> > > > while use the original variable 'server' as a dedicated pointer
> > > > to
> > > > point to the found element.
> > > > 
> > > > Cc: stable@vger.kernel.org
> > > > Fixes: 1be5683b03a76 ("pnfs: CB_NOTIFY_DEVICEID")
> > > > Signed-off-by: Xiaomeng Tong <xiam0nd.tong@gmail.com>
> > > > ---
> > > >  fs/nfs/callback_proc.c | 9 +++++----
> > > >  1 file changed, 5 insertions(+), 4 deletions(-)
> > > > 
> > > > diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
> > > > index c343666d9a42..84779785dc8d 100644
> > > > --- a/fs/nfs/callback_proc.c
> > > > +++ b/fs/nfs/callback_proc.c
> > > > @@ -361,7 +361,7 @@ __be32 nfs4_callback_devicenotify(void *argp,
> > > > void *resp,
> > > >         uint32_t i;
> > > >         __be32 res = 0;
> > > >         struct nfs_client *clp = cps->clp;
> > > > -       struct nfs_server *server = NULL;
> > > > +       struct nfs_server *server = NULL, *iter;
> > > >  
> > > >         if (!clp) {
> > > >                 res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
> > > > @@ -374,10 +374,11 @@ __be32 nfs4_callback_devicenotify(void
> > > > *argp,
> > > > void *resp,
> > > >                 if (!server ||
> > > >                     server->pnfs_curr_ld->id != dev-
> > > > >cbd_layout_type)
> > > > {
> > > >                         rcu_read_lock();
> > > > -                       list_for_each_entry_rcu(server, &clp-
> > > > > cl_superblocks, client_link)
> > > > -                               if (server->pnfs_curr_ld &&
> > > > -                                   server->pnfs_curr_ld->id ==
> > > > dev-
> > > > > cbd_layout_type) {
> > > > +                       list_for_each_entry_rcu(iter, &clp-
> > > > > cl_superblocks, client_link)
> > > > +                               if (iter->pnfs_curr_ld &&
> > > > +                                   iter->pnfs_curr_ld->id ==
> > > > dev-
> > > > > cbd_layout_type) {
> > > >                                         rcu_read_unlock();
> > > > +                                       server = iter;
> > > 
> > > Hmm... We're not holding any locks on the super block for 'iter'
> > > here,
> > > so nothing is preventing it from going away while we're.
> > > 
> > 
> > ok, i am not a 'rcu lock' expert, i will make it hold the
> > rcu_read_lock()
> > if necessary.
> > 
> > > Given that we really only want a pointer to the struct
> > > pnfs_layoutdriver_type anyway, why not just convert the code to
> > > save a
> > > pointer to that (and do it while holding the rcu_read_lock())?
> > > 
> > 
> > Maybe it's not that simple. If you only save a pointer to that and
> > still
> > use 'server' as the list iterator of list_for_each_entry_rcu, there
> > could
> > be problem.
> > 
> > I.e., if no element found in list_for_each_entry_rcu in the first
> > outer
> > 'for' loop, and now 'server' is a bogus pointer to an invalid struct,
> > and
> > continue to go into the second outer 'for' loop, and the check below
> > will
> > lead to invalid memory access (server->pnfs_curr_ld->id), even can
> > potentialy
> > be bypassed with crafted data to make the condition false and
> > mistakely run
> > nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id);
> > with bogus
> > 'server'.
> > 
> > if (!server ||
> >     server->pnfs_curr_ld->id != dev->cbd_layout_type) {
> > 
> > > The struct pnfs_layoutdriver is always expected to be a statically
> > > allocated structure, so it won't go away as long as the pNFS driver
> > > module remains loaded.
> > 
> 
> 
> Let's just do the following.
> 
> 8<-----------------------------------------------
> From 7c9d845f0612e5bcd23456a2ec43be8ac43458f1 Mon Sep 17 00:00:00 2001
> From: Trond Myklebust <trond.myklebust@hammerspace.com>
> Date: Mon, 28 Mar 2022 08:36:34 -0400
> Subject: [PATCH] NFSv4/pNFS: Fix another issue with a list iterator pointing
>  to the head
> 
> In nfs4_callback_devicenotify(), if we don't find a matching entry for
> the deviceid, we're left with a pointer to 'struct nfs_server' that
> actually points to the list of super blocks associated with our struct
> nfs_client.
> Furthermore, even if we have a valid pointer, nothing pins the super
> block, and so the struct nfs_server could end up getting freed while
> we're using it.
> 
> Since all we want is a pointer to the struct pnfs_layoutdriver_type,
> let's skip all the iteration over super blocks, and just use APIs to
> find the layout driver directly.
> 
> Reported-by: Xiaomeng Tong <xiam0nd.tong@gmail.com>
> Fixes: 1be5683b03a7 ("pnfs: CB_NOTIFY_DEVICEID")
> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
> ---
>  fs/nfs/callback_proc.c | 27 +++++++++------------------
>  fs/nfs/pnfs.c          | 11 +++++++++++
>  fs/nfs/pnfs.h          |  2 ++
>  3 files changed, 22 insertions(+), 18 deletions(-)

<formletter>

This is not the correct way to submit patches for inclusion in the
stable kernel tree.  Please read:
    https://www.kernel.org/doc/html/latest/process/stable-kernel-rules.html
for how to do this properly.

</formletter>
Xiaomeng Tong March 29, 2022, 4 a.m. UTC | #5
On Mon, 28 Mar 2022 13:24:57 +0000, Trond Myklebust wrote:
> Let's just do the following.
> 
> 8<-----------------------------------------------
> From 7c9d845f0612e5bcd23456a2ec43be8ac43458f1 Mon Sep 17 00:00:00 2001
> From: Trond Myklebust <trond.myklebust@hammerspace.com>
> Date: Mon, 28 Mar 2022 08:36:34 -0400
> Subject: [PATCH] NFSv4/pNFS: Fix another issue with a list iterator pointing
>  to the head
> 
> In nfs4_callback_devicenotify(), if we don't find a matching entry for
> the deviceid, we're left with a pointer to 'struct nfs_server' that
> actually points to the list of super blocks associated with our struct
> nfs_client.
> Furthermore, even if we have a valid pointer, nothing pins the super
> block, and so the struct nfs_server could end up getting freed while
> we're using it.
> 
> Since all we want is a pointer to the struct pnfs_layoutdriver_type,
> let's skip all the iteration over super blocks, and just use APIs to
> find the layout driver directly.
> 
> Reported-by: Xiaomeng Tong <xiam0nd.tong@gmail.com>
> Fixes: 1be5683b03a7 ("pnfs: CB_NOTIFY_DEVICEID")
> Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
> ---
>  fs/nfs/callback_proc.c | 27 +++++++++------------------
>  fs/nfs/pnfs.c          | 11 +++++++++++
>  fs/nfs/pnfs.h          |  2 ++
>  3 files changed, 22 insertions(+), 18 deletions(-)
> 
> diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
> index 39d1ec870d90..c8520284dda7 100644
> --- a/fs/nfs/callback_proc.c
> +++ b/fs/nfs/callback_proc.c
> @@ -358,12 +358,11 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp,
>  				  struct cb_process_state *cps)
>  {
>  	struct cb_devicenotifyargs *args = argp;
> +	const struct pnfs_layoutdriver_type *ld = NULL;
>  	uint32_t i;
>  	__be32 res = 0;
> -	struct nfs_client *clp = cps->clp;
> -	struct nfs_server *server = NULL;
>  
> -	if (!clp) {
> +	if (!cps->clp) {
>  		res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
>  		goto out;
>  	}
> @@ -371,23 +370,15 @@ __be32 nfs4_callback_devicenotify(void *argp, void *resp,
>  	for (i = 0; i < args->ndevs; i++) {
>  		struct cb_devicenotifyitem *dev = &args->devs[i];
>  
> -		if (!server ||
> -		    server->pnfs_curr_ld->id != dev->cbd_layout_type) {
> -			rcu_read_lock();
> -			list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
> -				if (server->pnfs_curr_ld &&
> -				    server->pnfs_curr_ld->id == dev->cbd_layout_type) {
> -					rcu_read_unlock();
> -					goto found;
> -				}
> -			rcu_read_unlock();
> -			continue;
> +		if (!ld || ld->id != dev->cbd_layout_type) {
> +			pnfs_put_layoutdriver(ld);
> +			ld = pnfs_find_layoutdriver(dev->cbd_layout_type);
> +			if (!ld)
> +				continue;
>  		}
> -
> -	found:
> -		nfs4_delete_deviceid(server->pnfs_curr_ld, clp, &dev->cbd_dev_id);
> +		nfs4_delete_deviceid(ld, cps->clp, &dev->cbd_dev_id);
>  	}
> -
> +	pnfs_put_layoutdriver(ld);
>  out:
>  	kfree(args->devs);
>  	return res;
> diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
> index de318bb5d349..856c962273c7 100644
> --- a/fs/nfs/pnfs.c
> +++ b/fs/nfs/pnfs.c
> @@ -92,6 +92,17 @@ find_pnfs_driver(u32 id)
>  	return local;
>  }
>  
> +const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id)
> +{
> +	return find_pnfs_driver(id);
> +}
> +
> +void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld)
> +{
> +	if (ld)
> +		module_put(ld->owner);
> +}
> +
>  void
>  unset_pnfs_layoutdriver(struct nfs_server *nfss)
>  {
> diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
> index f4d7548d67b2..07f11489e4e9 100644
> --- a/fs/nfs/pnfs.h
> +++ b/fs/nfs/pnfs.h
> @@ -234,6 +234,8 @@ struct pnfs_devicelist {
>  
>  extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *);
>  extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *);
> +extern const struct pnfs_layoutdriver_type *pnfs_find_layoutdriver(u32 id);
> +extern void pnfs_put_layoutdriver(const struct pnfs_layoutdriver_type *ld);
>  
>  /* nfs4proc.c */
>  extern size_t max_response_pages(struct nfs_server *server);
> -- 

Thank you, i have resend a PATCH v2 with fix as you suggested, and also with
some changes, please check it.

--
Xiaomeng Tong
diff mbox series

Patch

diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index c343666d9a42..84779785dc8d 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -361,7 +361,7 @@  __be32 nfs4_callback_devicenotify(void *argp, void *resp,
 	uint32_t i;
 	__be32 res = 0;
 	struct nfs_client *clp = cps->clp;
-	struct nfs_server *server = NULL;
+	struct nfs_server *server = NULL, *iter;
 
 	if (!clp) {
 		res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
@@ -374,10 +374,11 @@  __be32 nfs4_callback_devicenotify(void *argp, void *resp,
 		if (!server ||
 		    server->pnfs_curr_ld->id != dev->cbd_layout_type) {
 			rcu_read_lock();
-			list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link)
-				if (server->pnfs_curr_ld &&
-				    server->pnfs_curr_ld->id == dev->cbd_layout_type) {
+			list_for_each_entry_rcu(iter, &clp->cl_superblocks, client_link)
+				if (iter->pnfs_curr_ld &&
+				    iter->pnfs_curr_ld->id == dev->cbd_layout_type) {
 					rcu_read_unlock();
+					server = iter;
 					goto found;
 				}
 			rcu_read_unlock();