This patch adds support for shm_rmid_forced sysctl. If set to 1, all
shared memory objects in current ipc namespace will be automatically
forced to use IPC_RMID. POSIX way of handling shmem allows to create
shm objects and call shmdt() leaving shm object associated with no
process, thus consuming memory not counted via rlimits. With
shm_rmid_forced=1 the shared memory object is counted at least for one
process, so OOM killer may effectively kill the fat process holding
the shared memory.
It obviously breaks POSIX, some programs relying on the feature would
stop working. So, set shm_rmid_forced=1 only if you're sure nobody uses
"orphaned" memory. shm_rmid_forced=0 by default for compatability
reasons.
The feature was previously impemented in -ow as a configure option.
Signed-off-by: Vasiliy Kulikov <[email protected]>
---
Documentation/sysctl/kernel.txt | 22 ++++++++++
include/linux/ipc_namespace.h | 3 +
include/linux/shm.h | 5 ++
ipc/ipc_sysctl.c | 33 +++++++++++++++
ipc/shm.c | 87 +++++++++++++++++++++++++++++++++++++--
kernel/exit.c | 1 +
6 files changed, 147 insertions(+), 4 deletions(-)
---
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index 5e7cb39..7a0ecfd 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -62,6 +62,7 @@ show up in /proc/sys/kernel:
- shmall
- shmmax [ sysv ipc ]
- shmmni
+- shm_rmid_forced
- stop-a [ SPARC only ]
- sysrq ==> Documentation/sysrq.txt
- tainted
@@ -475,6 +476,27 @@ kernel. This value defaults to SHMMAX.
==============================================================
+shm_rmid_forced:
+
+Linux lets you set resource limits, including on how much memory one
+process can consume, via setrlimit(2). Unfortunately, shared memory
+segments are allowed to exist without association with any process, and
+thus might not be counted against any resource limits. If enabled,
+shared memory segments are automatically destroyed when their attach
+count becomes zero after a detach or a process termination. It will
+also destroy segments that were created, but never attached to, on exit
+from the process. The only use left for IPC_RMID is to immediately
+destroy an unattached segment. Of course, this breaks the way things are
+defined, so some applications might stop working. Note that this
+feature will do you no good unless you also configure your resource
+limits (in particular, RLIMIT_AS and RLIMIT_NPROC). Most systems don't
+need this.
+
+Note that if you change this from 0 to 1, already created segments
+without users and with a dead originative process will be destroyed.
+
+==============================================================
+
softlockup_thresh:
This value can be used to lower the softlockup tolerance threshold. The
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index a6d1655..1647795 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -44,6 +44,7 @@ struct ipc_namespace {
size_t shm_ctlall;
int shm_ctlmni;
int shm_tot;
+ int shm_rmid_forced;
struct notifier_block ipcns_nb;
@@ -72,6 +73,7 @@ extern int register_ipcns_notifier(struct ipc_namespace *);
extern int cond_register_ipcns_notifier(struct ipc_namespace *);
extern void unregister_ipcns_notifier(struct ipc_namespace *);
extern int ipcns_notify(unsigned long);
+extern void shm_destroy_orphaned(struct ipc_namespace *ns);
#else /* CONFIG_SYSVIPC */
static inline int register_ipcns_notifier(struct ipc_namespace *ns)
{ return 0; }
@@ -79,6 +81,7 @@ static inline int cond_register_ipcns_notifier(struct ipc_namespace *ns)
{ return 0; }
static inline void unregister_ipcns_notifier(struct ipc_namespace *ns) { }
static inline int ipcns_notify(unsigned long l) { return 0; }
+static inline void shm_destroy_orphaned(struct ipc_namespace *ns) {}
#endif /* CONFIG_SYSVIPC */
#ifdef CONFIG_POSIX_MQUEUE
diff --git a/include/linux/shm.h b/include/linux/shm.h
index eca6235..b030a4e 100644
--- a/include/linux/shm.h
+++ b/include/linux/shm.h
@@ -106,6 +106,7 @@ struct shmid_kernel /* private to the kernel */
#ifdef CONFIG_SYSVIPC
long do_shmat(int shmid, char __user *shmaddr, int shmflg, unsigned long *addr);
extern int is_file_shm_hugepages(struct file *file);
+extern void exit_shm(struct task_struct *task);
#else
static inline long do_shmat(int shmid, char __user *shmaddr,
int shmflg, unsigned long *addr)
@@ -116,6 +117,10 @@ static inline int is_file_shm_hugepages(struct file *file)
{
return 0;
}
+static inline void exit_shm(struct task_struct *task)
+{
+ return 0;
+}
#endif
#endif /* __KERNEL__ */
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 56410fa..1d36879 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -37,6 +37,28 @@ static int proc_ipc_dointvec(ctl_table *table, int write,
return proc_dointvec(&ipc_table, write, buffer, lenp, ppos);
}
+static int proc_ipc_dointvec_minmax(ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table ipc_table;
+ memcpy(&ipc_table, table, sizeof(ipc_table));
+ ipc_table.data = get_ipc(table);
+
+ return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
+}
+
+static int proc_ipc_dointvec_minmax_orphans(ctl_table *table, int write,
+ void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+ struct ipc_namespace *ns = current->nsproxy->ipc_ns;
+ int err = proc_ipc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ if (err < 0)
+ return err;
+ if (ns->shm_rmid_forced)
+ shm_destroy_orphaned(ns);
+ return err;
+}
+
static int proc_ipc_callback_dointvec(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
@@ -125,6 +147,8 @@ static int proc_ipcauto_dointvec_minmax(ctl_table *table, int write,
#else
#define proc_ipc_doulongvec_minmax NULL
#define proc_ipc_dointvec NULL
+#define proc_ipc_dointvec_minmax NULL
+#define proc_ipc_dointvec_minmax_orphans NULL
#define proc_ipc_callback_dointvec NULL
#define proc_ipcauto_dointvec_minmax NULL
#endif
@@ -155,6 +179,15 @@ static struct ctl_table ipc_kern_table[] = {
.proc_handler = proc_ipc_dointvec,
},
{
+ .procname = "shm_rmid_forced",
+ .data = &init_ipc_ns.shm_rmid_forced,
+ .maxlen = sizeof(init_ipc_ns.shm_rmid_forced),
+ .mode = 0644,
+ .proc_handler = proc_ipc_dointvec_minmax_orphans,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+ {
.procname = "msgmax",
.data = &init_ipc_ns.msg_ctlmax,
.maxlen = sizeof (init_ipc_ns.msg_ctlmax),
diff --git a/ipc/shm.c b/ipc/shm.c
index ab3385a..91b3026 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -74,6 +74,7 @@ void shm_init_ns(struct ipc_namespace *ns)
ns->shm_ctlmax = SHMMAX;
ns->shm_ctlall = SHMALL;
ns->shm_ctlmni = SHMMNI;
+ ns->shm_rmid_forced = 0;
ns->shm_tot = 0;
ipc_init_ids(&shm_ids(ns));
}
@@ -186,6 +187,13 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
ipc_rcu_putref(shp);
}
+static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
+{
+ return (shp->shm_nattch == 0) &&
+ (ns->shm_rmid_forced ||
+ (shp->shm_perm.mode & SHM_DEST));
+}
+
/*
* remove the attach descriptor vma.
* free memory for segment if it is marked destroyed.
@@ -206,11 +214,83 @@ static void shm_close(struct vm_area_struct *vma)
shp->shm_lprid = task_tgid_vnr(current);
shp->shm_dtim = get_seconds();
shp->shm_nattch--;
- if(shp->shm_nattch == 0 &&
- shp->shm_perm.mode & SHM_DEST)
+ if (shm_may_destroy(ns, shp))
+ shm_destroy(ns, shp);
+ else
+ shm_unlock(shp);
+ up_write(&shm_ids(ns).rw_mutex);
+}
+
+static int shm_try_destroy_current(int id, void *p, void *data)
+{
+ struct ipc_namespace *ns = data;
+ struct shmid_kernel *shp = shm_lock(ns, id);
+
+ if (IS_ERR(shp))
+ return 0;
+
+ if (shp->shm_cprid != task_tgid_vnr(current)) {
+ shm_unlock(shp);
+ return 0;
+ }
+
+ if (shm_may_destroy(ns, shp))
shm_destroy(ns, shp);
else
shm_unlock(shp);
+ return 0;
+}
+
+static int shm_try_destroy_orphaned(int id, void *p, void *data)
+{
+ struct ipc_namespace *ns = data;
+ struct shmid_kernel *shp = shm_lock(ns, id);
+ struct task_struct *task;
+
+ if (IS_ERR(shp))
+ return 0;
+
+ /*
+ * We want to destroy segments without users and with already
+ * exit'ed originating process.
+ *
+ * XXX: the originating process may exist in another pid namespace.
+ */
+ task = find_task_by_vpid(shp->shm_cprid);
+ if (task != NULL) {
+ shm_unlock(shp);
+ return 0;
+ }
+
+ if (shm_may_destroy(ns, shp))
+ shm_destroy(ns, shp);
+ else
+ shm_unlock(shp);
+ return 0;
+}
+
+void shm_destroy_orphaned(struct ipc_namespace *ns)
+{
+ down_write(&shm_ids(ns).rw_mutex);
+ idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns);
+ up_write(&shm_ids(ns).rw_mutex);
+}
+
+
+void exit_shm(struct task_struct *task)
+{
+ struct nsproxy *nsp = task->nsproxy;
+ struct ipc_namespace *ns;
+
+ if (!nsp)
+ return;
+ ns = nsp->ipc_ns;
+ if (!ns || !ns->shm_rmid_forced)
+ return;
+
+ /* Destroy all already created segments, but not mapped yet */
+ down_write(&shm_ids(ns).rw_mutex);
+ idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_current, ns);
up_write(&shm_ids(ns).rw_mutex);
}
@@ -950,8 +1030,7 @@ out_nattch:
shp = shm_lock(ns, shmid);
BUG_ON(IS_ERR(shp));
shp->shm_nattch--;
- if(shp->shm_nattch == 0 &&
- shp->shm_perm.mode & SHM_DEST)
+ if (shm_may_destroy(ns, shp))
shm_destroy(ns, shp);
else
shm_unlock(shp);
diff --git a/kernel/exit.c b/kernel/exit.c
index 20a4064..816c610 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -991,6 +991,7 @@ NORET_TYPE void do_exit(long code)
trace_sched_process_exit(tsk);
exit_sem(tsk);
+ exit_shm(tsk);
exit_files(tsk);
exit_fs(tsk);
check_stack_usage();
---
On Wed, 22 Jun 2011 19:25:14 +0400 Vasiliy Kulikov wrote:
> Signed-off-by: Vasiliy Kulikov <[email protected]>
> ---
>
> Documentation/sysctl/kernel.txt | 22 ++++++++++
> include/linux/ipc_namespace.h | 3 +
> include/linux/shm.h | 5 ++
> ipc/ipc_sysctl.c | 33 +++++++++++++++
> ipc/shm.c | 87 +++++++++++++++++++++++++++++++++++++--
> kernel/exit.c | 1 +
> 6 files changed, 147 insertions(+), 4 deletions(-)
>
> ---
> diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
> index 5e7cb39..7a0ecfd 100644
> --- a/Documentation/sysctl/kernel.txt
> +++ b/Documentation/sysctl/kernel.txt
> @@ -62,6 +62,7 @@ show up in /proc/sys/kernel:
> - shmall
> - shmmax [ sysv ipc ]
> - shmmni
> +- shm_rmid_forced
> - stop-a [ SPARC only ]
> - sysrq ==> Documentation/sysrq.txt
> - tainted
> @@ -475,6 +476,27 @@ kernel. This value defaults to SHMMAX.
>
> ==============================================================
>
> +shm_rmid_forced:
> +
> +Linux lets you set resource limits, including on how much memory one
including how much memory one
> +process can consume, via setrlimit(2). Unfortunately, shared memory
> +segments are allowed to exist without association with any process, and
> +thus might not be counted against any resource limits. If enabled,
> +shared memory segments are automatically destroyed when their attach
> +count becomes zero after a detach or a process termination. It will
> +also destroy segments that were created, but never attached to, on exit
> +from the process. The only use left for IPC_RMID is to immediately
> +destroy an unattached segment. Of course, this breaks the way things are
> +defined, so some applications might stop working. Note that this
> +feature will do you no good unless you also configure your resource
> +limits (in particular, RLIMIT_AS and RLIMIT_NPROC). Most systems don't
> +need this.
> +
> +Note that if you change this from 0 to 1, already created segments
> +without users and with a dead originative process will be destroyed.
originating (?)
> +
> +==============================================================
> +
> softlockup_thresh:
>
> This value can be used to lower the softlockup tolerance threshold. The
---
~Randy
*** Remember to use Documentation/SubmitChecklist when testing your code ***
On Wed, 22 Jun 2011 19:25:14 +0400
Vasiliy Kulikov <[email protected]> wrote:
> This patch adds support for shm_rmid_forced sysctl. If set to 1, all
> shared memory objects in current ipc namespace will be automatically
> forced to use IPC_RMID. POSIX way of handling shmem allows to create
> shm objects and call shmdt() leaving shm object associated with no
> process, thus consuming memory not counted via rlimits. With
> shm_rmid_forced=1 the shared memory object is counted at least for one
> process, so OOM killer may effectively kill the fat process holding
> the shared memory.
>
> It obviously breaks POSIX, some programs relying on the feature would
> stop working. So, set shm_rmid_forced=1 only if you're sure nobody uses
> "orphaned" memory. shm_rmid_forced=0 by default for compatability
> reasons.
>
> The feature was previously impemented in -ow as a configure option.
>
What a horrid patch. But given the POSIX (mis?)feature I don't see a
better way, and the feature seems desirable. Sigh.
What sort of users would want to turn this on, and why?
> --- a/include/linux/ipc_namespace.h
> +++ b/include/linux/ipc_namespace.h
> @@ -44,6 +44,7 @@ struct ipc_namespace {
> size_t shm_ctlall;
> int shm_ctlmni;
> int shm_tot;
> + int shm_rmid_forced;
>
> struct notifier_block ipcns_nb;
Please send a patch which adds a nice comment to this field.
Perhaps shm_rmid_forced should have had bool type.
> --- a/ipc/shm.c
> +++ b/ipc/shm.c
> @@ -74,6 +74,7 @@ void shm_init_ns(struct ipc_namespace *ns)
> ns->shm_ctlmax = SHMMAX;
> ns->shm_ctlall = SHMALL;
> ns->shm_ctlmni = SHMMNI;
> + ns->shm_rmid_forced = 0;
> ns->shm_tot = 0;
> ipc_init_ids(&shm_ids(ns));
> }
The problem is that nobody will test your feature. So for testing
purposes, let's enable the feature by default. I assume this:
--- a/ipc/shm.c~ipc-introduce-shm_rmid_forced-sysctl-ipc-introduce-shm_rmid_forced-sysctl-testing
+++ a/ipc/shm.c
@@ -74,7 +74,7 @@ void shm_init_ns(struct ipc_namespace *n
ns->shm_ctlmax = SHMMAX;
ns->shm_ctlall = SHMALL;
ns->shm_ctlmni = SHMMNI;
- ns->shm_rmid_forced = 0;
+ ns->shm_rmid_forced = 1;
ns->shm_tot = 0;
ipc_init_ids(&shm_ids(ns));
}
will do that?
> +static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
> +{
> + return (shp->shm_nattch == 0) &&
> + (ns->shm_rmid_forced ||
> + (shp->shm_perm.mode & SHM_DEST));
> +}
Just because the existing code is crappily documented doesn't mean that
we have to copy that ;)
On Wed, Jun 29, 2011 at 15:14 -0700, Andrew Morton wrote:
> What a horrid patch. But given the POSIX (mis?)feature I don't see a
> better way, and the feature seems desirable. Sigh.
>
> What sort of users would want to turn this on, and why?
A shared environment, e.g. a shared web hosting. With multiple ipc
namespaces (on a VPS) each namespace can steal a few megabytes of memory
without any per user accounting. Even if all user's processes are
killed, the orphaned shm is still kept in RAM. It doesn't lead to OOM,
but it prevents from creating new segments and just annoys.
> > --- a/include/linux/ipc_namespace.h
> > +++ b/include/linux/ipc_namespace.h
> > @@ -44,6 +44,7 @@ struct ipc_namespace {
> > size_t shm_ctlall;
> > int shm_ctlmni;
> > int shm_tot;
> > + int shm_rmid_forced;
> >
> > struct notifier_block ipcns_nb;
>
> Please send a patch which adds a nice comment to this field.
OK.
> Perhaps shm_rmid_forced should have had bool type.
OK. The sysctl handler should parse it OK if feed it with sizeof(bool).
> > --- a/ipc/shm.c
> > +++ b/ipc/shm.c
> > @@ -74,6 +74,7 @@ void shm_init_ns(struct ipc_namespace *ns)
> > ns->shm_ctlmax = SHMMAX;
> > ns->shm_ctlall = SHMALL;
> > ns->shm_ctlmni = SHMMNI;
> > + ns->shm_rmid_forced = 0;
> > ns->shm_tot = 0;
> > ipc_init_ids(&shm_ids(ns));
> > }
>
> The problem is that nobody will test your feature. So for testing
> purposes, let's enable the feature by default. I assume this:
>
> --- a/ipc/shm.c~ipc-introduce-shm_rmid_forced-sysctl-ipc-introduce-shm_rmid_forced-sysctl-testing
> +++ a/ipc/shm.c
> @@ -74,7 +74,7 @@ void shm_init_ns(struct ipc_namespace *n
> ns->shm_ctlmax = SHMMAX;
> ns->shm_ctlall = SHMALL;
> ns->shm_ctlmni = SHMMNI;
> - ns->shm_rmid_forced = 0;
> + ns->shm_rmid_forced = 1;
> ns->shm_tot = 0;
> ipc_init_ids(&shm_ids(ns));
> }
>
> will do that?
Sure if it helps testing :)
> > +static bool shm_may_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
> > +{
> > + return (shp->shm_nattch == 0) &&
> > + (ns->shm_rmid_forced ||
> > + (shp->shm_perm.mode & SHM_DEST));
> > +}
>
> Just because the existing code is crappily documented doesn't mean that
> we have to copy that ;)
OK ;)
Thank you!
--
Vasiliy Kulikov
http://www.openwall.com - bringing security into open computing environments
On Thu, Jun 30, 2011 at 13:21 +0400, Vasiliy Kulikov wrote:
> > Perhaps shm_rmid_forced should have had bool type.
>
> OK. The sysctl handler should parse it OK if feed it with sizeof(bool).
I was wrong, maxlen must not be less than sizeof(int), it makes sense
for arrays only. So, it is kept being int.
--
Vasiliy Kulikov
http://www.openwall.com - bringing security into open computing environments