The patch titled
namespaces: cleanup the code managed with PID_NS option
has been added to the -mm tree. Its filename is
cleanup-the-code-managed-with-pid_ns-option.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: namespaces: cleanup the code managed with PID_NS option
From: Pavel Emelyanov <xemul@xxxxxxxxxx>
Just like with the user namespaces, move the namespace management code into
the separate .c file and mark the (already existing) PID_NS option as "depend
on NAMESPACES"
Signed-off-by: Pavel Emelyanov <xemul@xxxxxxxxxx>
Acked-by: Serge Hallyn <serue@xxxxxxxxxx>
Cc: Cedric Le Goater <clg@xxxxxxxxxx>
Cc: "Eric W. Biederman" <ebiederm@xxxxxxxxxxxx>
Cc: Herbert Poetzl <herbert@xxxxxxxxxxxx>
Cc: Kirill Korotaev <dev@xxxxx>
Cc: Sukadev Bhattiprolu <sukadev@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/pid.h | 2
include/linux/pid_namespace.h | 6
init/Kconfig | 24 +--
kernel/Makefile | 1
kernel/pid.c | 184 -----------------------------
kernel/pid_namespace.c | 197 ++++++++++++++++++++++++++++++++
6 files changed, 220 insertions(+), 194 deletions(-)
diff -puN include/linux/pid.h~cleanup-the-code-managed-with-pid_ns-option include/linux/pid.h
--- a/include/linux/pid.h~cleanup-the-code-managed-with-pid_ns-option
+++ a/include/linux/pid.h
@@ -118,10 +118,10 @@ extern struct pid *find_pid(int nr);
*/
extern struct pid *find_get_pid(int nr);
extern struct pid *find_ge_pid(int nr, struct pid_namespace *);
+int next_pidmap(struct pid_namespace *pid_ns, int last);
extern struct pid *alloc_pid(struct pid_namespace *ns);
extern void FASTCALL(free_pid(struct pid *pid));
-extern void zap_pid_ns_processes(struct pid_namespace *pid_ns);
/*
* the helpers to get the pid's id seen from different namespaces
diff -puN include/linux/pid_namespace.h~cleanup-the-code-managed-with-pid_ns-option include/linux/pid_namespace.h
--- a/include/linux/pid_namespace.h~cleanup-the-code-managed-with-pid_ns-option
+++ a/include/linux/pid_namespace.h
@@ -39,6 +39,7 @@ static inline struct pid_namespace *get_
extern struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *ns);
extern void free_pid_ns(struct kref *kref);
+extern void zap_pid_ns_processes(struct pid_namespace *pid_ns);
static inline void put_pid_ns(struct pid_namespace *ns)
{
@@ -66,6 +67,11 @@ static inline void put_pid_ns(struct pid
{
}
+
+static inline void zap_pid_ns_processes(struct pid_namespace *ns)
+{
+ BUG();
+}
#endif /* CONFIG_PID_NS */
static inline struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
diff -puN init/Kconfig~cleanup-the-code-managed-with-pid_ns-option init/Kconfig
--- a/init/Kconfig~cleanup-the-code-managed-with-pid_ns-option
+++ a/init/Kconfig
@@ -206,18 +206,6 @@ config TASK_IO_ACCOUNTING
Say N if unsure.
-config PID_NS
- bool "PID Namespaces (EXPERIMENTAL)"
- default n
- depends on EXPERIMENTAL
- help
- Suport process id namespaces. This allows having multiple
- process with the same pid as long as they are in different
- pid namespaces. This is a building block of containers.
-
- Unless you want to work with an experimental feature
- say N here.
-
config AUDIT
bool "Auditing support"
depends on NET
@@ -426,6 +414,18 @@ config USER_NS
to provide different user info for different servers.
If unsure, say N.
+config PID_NS
+ bool "PID Namespaces (EXPERIMENTAL)"
+ default n
+ depends on NAMESPACES && EXPERIMENTAL
+ help
+ Suport process id namespaces. This allows having multiple
+ process with the same pid as long as they are in different
+ pid namespaces. This is a building block of containers.
+
+ Unless you want to work with an experimental feature
+ say N here.
+
config BLK_DEV_INITRD
bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
depends on BROKEN || !FRV
diff -puN kernel/Makefile~cleanup-the-code-managed-with-pid_ns-option kernel/Makefile
--- a/kernel/Makefile~cleanup-the-code-managed-with-pid_ns-option
+++ a/kernel/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_AUDIT_TREE) += audit_tree.o
obj-$(CONFIG_KPROBES) += kprobes.o
obj-$(CONFIG_UTS_NS) += utsname.o
obj-$(CONFIG_USER_NS) += user_namespace.o
+obj-$(CONFIG_PID_NS) += pid_namespace.o
obj-$(CONFIG_SYSFS) += ksysfs.o
obj-$(CONFIG_DETECT_SOFTLOCKUP) += softlockup.o
obj-$(CONFIG_GENERIC_HARDIRQS) += irq/
diff -puN kernel/pid.c~cleanup-the-code-managed-with-pid_ns-option kernel/pid.c
--- a/kernel/pid.c~cleanup-the-code-managed-with-pid_ns-option
+++ a/kernel/pid.c
@@ -41,7 +41,6 @@
static struct hlist_head *pid_hash;
static int pidhash_shift;
struct pid init_struct_pid = INIT_STRUCT_PID;
-static struct kmem_cache *pid_ns_cachep;
int pid_max = PID_MAX_DEFAULT;
@@ -181,7 +180,7 @@ static int alloc_pidmap(struct pid_names
return -1;
}
-static int next_pidmap(struct pid_namespace *pid_ns, int last)
+int next_pidmap(struct pid_namespace *pid_ns, int last)
{
int offset;
struct pidmap *map, *end;
@@ -487,180 +486,6 @@ struct pid *find_ge_pid(int nr, struct p
}
EXPORT_SYMBOL_GPL(find_get_pid);
-struct pid_cache {
- int nr_ids;
- char name[16];
- struct kmem_cache *cachep;
- struct list_head list;
-};
-
-static LIST_HEAD(pid_caches_lh);
-static DEFINE_MUTEX(pid_caches_mutex);
-
-/*
- * creates the kmem cache to allocate pids from.
- * @nr_ids: the number of numerical ids this pid will have to carry
- */
-
-static struct kmem_cache *create_pid_cachep(int nr_ids)
-{
- struct pid_cache *pcache;
- struct kmem_cache *cachep;
-
- mutex_lock(&pid_caches_mutex);
- list_for_each_entry (pcache, &pid_caches_lh, list)
- if (pcache->nr_ids == nr_ids)
- goto out;
-
- pcache = kmalloc(sizeof(struct pid_cache), GFP_KERNEL);
- if (pcache == NULL)
- goto err_alloc;
-
- snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids);
- cachep = kmem_cache_create(pcache->name,
- sizeof(struct pid) + (nr_ids - 1) * sizeof(struct upid),
- 0, SLAB_HWCACHE_ALIGN, NULL);
- if (cachep == NULL)
- goto err_cachep;
-
- pcache->nr_ids = nr_ids;
- pcache->cachep = cachep;
- list_add(&pcache->list, &pid_caches_lh);
-out:
- mutex_unlock(&pid_caches_mutex);
- return pcache->cachep;
-
-err_cachep:
- kfree(pcache);
-err_alloc:
- mutex_unlock(&pid_caches_mutex);
- return NULL;
-}
-
-#ifdef CONFIG_PID_NS
-static struct pid_namespace *create_pid_namespace(int level)
-{
- struct pid_namespace *ns;
- int i;
-
- ns = kmem_cache_alloc(pid_ns_cachep, GFP_KERNEL);
- if (ns == NULL)
- goto out;
-
- ns->pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
- if (!ns->pidmap[0].page)
- goto out_free;
-
- ns->pid_cachep = create_pid_cachep(level + 1);
- if (ns->pid_cachep == NULL)
- goto out_free_map;
-
- kref_init(&ns->kref);
- ns->last_pid = 0;
- ns->child_reaper = NULL;
- ns->level = level;
-
- set_bit(0, ns->pidmap[0].page);
- atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
-
- for (i = 1; i < PIDMAP_ENTRIES; i++) {
- ns->pidmap[i].page = 0;
- atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
- }
-
- return ns;
-
-out_free_map:
- kfree(ns->pidmap[0].page);
-out_free:
- kmem_cache_free(pid_ns_cachep, ns);
-out:
- return ERR_PTR(-ENOMEM);
-}
-
-static void destroy_pid_namespace(struct pid_namespace *ns)
-{
- int i;
-
- for (i = 0; i < PIDMAP_ENTRIES; i++)
- kfree(ns->pidmap[i].page);
- kmem_cache_free(pid_ns_cachep, ns);
-}
-
-struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns)
-{
- struct pid_namespace *new_ns;
-
- BUG_ON(!old_ns);
- new_ns = get_pid_ns(old_ns);
- if (!(flags & CLONE_NEWPID))
- goto out;
-
- new_ns = ERR_PTR(-EINVAL);
- if (flags & CLONE_THREAD)
- goto out_put;
-
- new_ns = create_pid_namespace(old_ns->level + 1);
- if (!IS_ERR(new_ns))
- new_ns->parent = get_pid_ns(old_ns);
-
-out_put:
- put_pid_ns(old_ns);
-out:
- return new_ns;
-}
-
-void free_pid_ns(struct kref *kref)
-{
- struct pid_namespace *ns, *parent;
-
- ns = container_of(kref, struct pid_namespace, kref);
-
- parent = ns->parent;
- destroy_pid_namespace(ns);
-
- if (parent != NULL)
- put_pid_ns(parent);
-}
-#endif /* CONFIG_PID_NS */
-
-void zap_pid_ns_processes(struct pid_namespace *pid_ns)
-{
- int nr;
- int rc;
-
- /*
- * The last thread in the cgroup-init thread group is terminating.
- * Find remaining pid_ts in the namespace, signal and wait for them
- * to exit.
- *
- * Note: This signals each threads in the namespace - even those that
- * belong to the same thread group, To avoid this, we would have
- * to walk the entire tasklist looking a processes in this
- * namespace, but that could be unnecessarily expensive if the
- * pid namespace has just a few processes. Or we need to
- * maintain a tasklist for each pid namespace.
- *
- */
- read_lock(&tasklist_lock);
- nr = next_pidmap(pid_ns, 1);
- while (nr > 0) {
- kill_proc_info(SIGKILL, SEND_SIG_PRIV, nr);
- nr = next_pidmap(pid_ns, nr);
- }
- read_unlock(&tasklist_lock);
-
- do {
- clear_thread_flag(TIF_SIGPENDING);
- rc = sys_wait4(-1, NULL, __WALL, NULL);
- } while (rc != -ECHILD);
-
-
- /* Child reaper for the pid namespace is going away */
- pid_ns->child_reaper = NULL;
- return;
-}
-
/*
* The pid hash table is scaled according to the amount of memory in the
* machine. From a minimum of 16 slots up to 4096 slots at one gigabyte or
@@ -693,9 +518,6 @@ void __init pidmap_init(void)
set_bit(0, init_pid_ns.pidmap[0].page);
atomic_dec(&init_pid_ns.pidmap[0].nr_free);
- init_pid_ns.pid_cachep = create_pid_cachep(1);
- if (init_pid_ns.pid_cachep == NULL)
- panic("Can't create pid_1 cachep\n");
-
- pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
+ init_pid_ns.pid_cachep = KMEM_CACHE(pid,
+ SLAB_HWCACHE_ALIGN | SLAB_PANIC);
}
diff -puN /dev/null kernel/pid_namespace.c
--- /dev/null
+++ a/kernel/pid_namespace.c
@@ -0,0 +1,197 @@
+/*
+ * Pid namespaces
+ *
+ * Authors:
+ * (C) 2007 Pavel Emelyanov <xemul@xxxxxxxxxx>, OpenVZ, SWsoft Inc.
+ * (C) 2007 Sukadev Bhattiprolu <sukadev@xxxxxxxxxx>, IBM
+ * Many thanks to Oleg Nesterov for comments and help
+ *
+ */
+
+#include <linux/pid.h>
+#include <linux/pid_namespace.h>
+#include <linux/syscalls.h>
+#include <linux/err.h>
+
+#define BITS_PER_PAGE (PAGE_SIZE*8)
+
+struct pid_cache {
+ int nr_ids;
+ char name[16];
+ struct kmem_cache *cachep;
+ struct list_head list;
+};
+
+static LIST_HEAD(pid_caches_lh);
+static DEFINE_MUTEX(pid_caches_mutex);
+static struct kmem_cache *pid_ns_cachep;
+
+/*
+ * creates the kmem cache to allocate pids from.
+ * @nr_ids: the number of numerical ids this pid will have to carry
+ */
+
+static struct kmem_cache *create_pid_cachep(int nr_ids)
+{
+ struct pid_cache *pcache;
+ struct kmem_cache *cachep;
+
+ mutex_lock(&pid_caches_mutex);
+ list_for_each_entry (pcache, &pid_caches_lh, list)
+ if (pcache->nr_ids == nr_ids)
+ goto out;
+
+ pcache = kmalloc(sizeof(struct pid_cache), GFP_KERNEL);
+ if (pcache == NULL)
+ goto err_alloc;
+
+ snprintf(pcache->name, sizeof(pcache->name), "pid_%d", nr_ids);
+ cachep = kmem_cache_create(pcache->name,
+ sizeof(struct pid) + (nr_ids - 1) * sizeof(struct upid),
+ 0, SLAB_HWCACHE_ALIGN, NULL);
+ if (cachep == NULL)
+ goto err_cachep;
+
+ pcache->nr_ids = nr_ids;
+ pcache->cachep = cachep;
+ list_add(&pcache->list, &pid_caches_lh);
+out:
+ mutex_unlock(&pid_caches_mutex);
+ return pcache->cachep;
+
+err_cachep:
+ kfree(pcache);
+err_alloc:
+ mutex_unlock(&pid_caches_mutex);
+ return NULL;
+}
+
+static struct pid_namespace *create_pid_namespace(int level)
+{
+ struct pid_namespace *ns;
+ int i;
+
+ ns = kmem_cache_alloc(pid_ns_cachep, GFP_KERNEL);
+ if (ns == NULL)
+ goto out;
+
+ ns->pidmap[0].page = kzalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!ns->pidmap[0].page)
+ goto out_free;
+
+ ns->pid_cachep = create_pid_cachep(level + 1);
+ if (ns->pid_cachep == NULL)
+ goto out_free_map;
+
+ kref_init(&ns->kref);
+ ns->last_pid = 0;
+ ns->child_reaper = NULL;
+ ns->level = level;
+
+ set_bit(0, ns->pidmap[0].page);
+ atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
+
+ for (i = 1; i < PIDMAP_ENTRIES; i++) {
+ ns->pidmap[i].page = 0;
+ atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
+ }
+
+ return ns;
+
+out_free_map:
+ kfree(ns->pidmap[0].page);
+out_free:
+ kmem_cache_free(pid_ns_cachep, ns);
+out:
+ return ERR_PTR(-ENOMEM);
+}
+
+static void destroy_pid_namespace(struct pid_namespace *ns)
+{
+ int i;
+
+ for (i = 0; i < PIDMAP_ENTRIES; i++)
+ kfree(ns->pidmap[i].page);
+ kmem_cache_free(pid_ns_cachep, ns);
+}
+
+struct pid_namespace *copy_pid_ns(unsigned long flags, struct pid_namespace *old_ns)
+{
+ struct pid_namespace *new_ns;
+
+ BUG_ON(!old_ns);
+ new_ns = get_pid_ns(old_ns);
+ if (!(flags & CLONE_NEWPID))
+ goto out;
+
+ new_ns = ERR_PTR(-EINVAL);
+ if (flags & CLONE_THREAD)
+ goto out_put;
+
+ new_ns = create_pid_namespace(old_ns->level + 1);
+ if (!IS_ERR(new_ns))
+ new_ns->parent = get_pid_ns(old_ns);
+
+out_put:
+ put_pid_ns(old_ns);
+out:
+ return new_ns;
+}
+
+void free_pid_ns(struct kref *kref)
+{
+ struct pid_namespace *ns, *parent;
+
+ ns = container_of(kref, struct pid_namespace, kref);
+
+ parent = ns->parent;
+ destroy_pid_namespace(ns);
+
+ if (parent != NULL)
+ put_pid_ns(parent);
+}
+
+void zap_pid_ns_processes(struct pid_namespace *pid_ns)
+{
+ int nr;
+ int rc;
+
+ /*
+ * The last thread in the cgroup-init thread group is terminating.
+ * Find remaining pid_ts in the namespace, signal and wait for them
+ * to exit.
+ *
+ * Note: This signals each threads in the namespace - even those that
+ * belong to the same thread group, To avoid this, we would have
+ * to walk the entire tasklist looking a processes in this
+ * namespace, but that could be unnecessarily expensive if the
+ * pid namespace has just a few processes. Or we need to
+ * maintain a tasklist for each pid namespace.
+ *
+ */
+ read_lock(&tasklist_lock);
+ nr = next_pidmap(pid_ns, 1);
+ while (nr > 0) {
+ kill_proc_info(SIGKILL, SEND_SIG_PRIV, nr);
+ nr = next_pidmap(pid_ns, nr);
+ }
+ read_unlock(&tasklist_lock);
+
+ do {
+ clear_thread_flag(TIF_SIGPENDING);
+ rc = sys_wait4(-1, NULL, __WALL, NULL);
+ } while (rc != -ECHILD);
+
+
+ /* Child reaper for the pid namespace is going away */
+ pid_ns->child_reaper = NULL;
+ return;
+}
+
+static __init int pid_namespaces_init(void)
+{
+ pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
+ return 0;
+}
+
+__initcall(pid_namespaces_init);
_
Patches currently in -mm which might be from xemul@xxxxxxxxxx are
origin.patch
git-net.patch
memory-controller-add-documentation.patch
memory-controller-resource-counters-v7.patch
memory-controller-containers-setup-v7.patch
memory-controller-accounting-setup-v7.patch
memory-controller-memory-accounting-v7.patch
memory-controller-task-migration-v7.patch
memory-controller-add-per-container-lru-and-reclaim-v7.patch
memory-controller-add-per-container-lru-and-reclaim-v7-memcgroup-fix-try_to_free-order.patch
memory-controller-improve-user-interface.patch
memory-controller-oom-handling-v7.patch
memory-controller-add-switch-to-control-what-type-of-pages-to-limit-v7.patch
memory-controller-make-page_referenced-container-aware-v7.patch
memory-controller-make-charging-gfp-mask-aware.patch
memcgroup-reinstate-swapoff-mod.patch
bugfix-for-memory-cgroup-controller-charge-refcnt-race-fix.patch
bugfix-for-memory-cgroup-controller-fix-error-handling-path-in-mem_charge_cgroup.patch
bugfix-for-memory-controller-add-helper-function-for-assigning-cgroup-to-page.patch
bugfix-for-memory-cgroup-controller-avoid-pagelru-page-in-mem_cgroup_isolate_pages.patch
bugfix-for-memory-cgroup-controller-avoid-pagelru-page-in-mem_cgroup_isolate_pages-fix.patch
memcgroup-fix-zone-isolation-oom.patch
memcgroup-revert-swap_state-mods.patch
bugfix-for-memory-cgroup-controller-migration-under-memory-controller-fix.patch
memory-cgroup-enhancements-fix-zone-handling-in-try_to_free_mem_cgroup_page.patch
memory-cgroup-enhancements-force_empty-interface-for-dropping-all-account-in-empty-cgroup.patch
memory-cgroup-enhancements-remember-a-page-is-charged-as-page-cache.patch
memory-cgroup-enhancements-remember-a-page-is-on-active-list-of-cgroup-or-not.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup-checkpatch-fixes.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup-fix-1.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup-uninlining.patch
memory-cgroup-enhancements-add-status-accounting-function-for-memory-cgroup-fix-2.patch
memory-cgroup-enhancements-add-memorystat-file.patch
memory-cgroup-enhancements-add-memorystat-file-checkpatch-fixes.patch
memory-cgroup-enhancements-add-memorystat-file-printk-fix.patch
memory-cgroup-enhancements-add-pre_destroy-handler.patch
memory-cgroup-enhancements-implicit-force_empty-at-rmdir.patch
add-the-namespaces-config-option.patch
move-the-uts-namespace-under-uts_ns-option.patch
move-the-ipc-namespace-under-ipc_ns-option.patch
cleanup-the-code-managed-with-the-user_ns-option.patch
cleanup-the-code-managed-with-the-user_ns-option-checkpatch-fixes.patch
cleanup-the-code-managed-with-pid_ns-option.patch
mark-net_ns-with-depends-on-namespaces.patch
reiser4.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
