| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <5463413E.6000800@nod.at>
Date: Wed, 12 Nov 2014 12:15:10 +0100
From: Richard Weinberger <richard@....at>
To: Chen Hanxiao <chenhanxiao@...fujitsu.com>,
"Eric W. Biederman" <ebiederm@...ssion.com>,
Serge Hallyn <serge.hallyn@...ntu.com>,
Oleg Nesterov <oleg@...hat.com>
CC: containers@...ts.linux-foundation.org,
linux-kernel@...r.kernel.org, David Howells <dhowells@...hat.com>,
Richard Weinberger <richard.weinberger@...il.com>,
Pavel Emelyanov <xemul@...allels.com>,
Vasiliy Kulikov <segooon@...il.com>,
Mateusz Guzik <mguzik@...hat.com>
Subject: Re: [PATCH v7 1/2] procfs: show hierarchy of pid namespace
Am 12.11.2014 um 11:08 schrieb Chen Hanxiao:
> We lack of pid hierarchy information, and this will lead to:
> a) we don't know pids' relationship, who is whose child:
> /proc/PID/ns/pid only tell us whether two pids live in different ns
> b) bring trouble to nested lxc container check/restore/migration
> c) bring trouble to pid translation between containers;
>
> This patch will show the hierarchy of pid namespace
> by pidns_hierarchy like:
>
> <init_PID> <parent_of_init_PID> <relative PID level>
>
> Ex:
> [root@...alhost ~]#cat /proc/pidns_hierarchy
> 18060 1 1
> 18102 18060 2
> 1534 18102 3
> 1600 18102 3
> 1550 1 1
> *Note: numbers represent the pid 1 in different ns
>
> It shows the pid hierarchy below:
>
> init_pid_ns 1
> │
> ┌────────────┐
> ns1 ns2
> │ │
> 1550 18060
> │
> │
> ns3
> │
> 18102
> │
> ┌──────────┐
> ns4 ns5
> │ │
> 1534 1600
>
> Every pid printed in pidns_hierarchy
> is the init pid of that pid ns level.
>
> Signed-off-by: Chen Hanxiao <chenhanxiao@...fujitsu.com>
> ---
> v7: change stype to be consistent with current interface like
> <init_PID> <parent_of_init_PID> <relative PID level>
> remove EXPERT dependent in Kconfig
> v6: fix a get_pid leak and do some cleanups;
> v5: collect pid by find_ge_pid;
> use local list inside nslist_proc_show;
> use get_pid, remove mutex lock.
> v4: simplify pid collection and some performance optimizamtion
> fix another race issue.
> v3: fix a race issue and memory leak issue
> v2: use a procfs text file instead of dirs under /proc
>
> fs/proc/Kconfig | 6 +
> fs/proc/Makefile | 1 +
> fs/proc/pidns_hierarchy.c | 280 ++++++++++++++++++++++++++++++++++++++++++++++
> 3 files changed, 287 insertions(+)
> create mode 100644 fs/proc/pidns_hierarchy.c
>
> diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
> index 2183fcf..82dda55 100644
> --- a/fs/proc/Kconfig
> +++ b/fs/proc/Kconfig
> @@ -71,3 +71,9 @@ config PROC_PAGE_MONITOR
> /proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap,
> /proc/kpagecount, and /proc/kpageflags. Disabling these
> interfaces will reduce the size of the kernel by approximately 4kb.
> +
> +config PROC_PID_HIERARCHY
> + bool "Enable /proc/pidns_hierarchy support"
> + depends on PROC_FS
> + help
> + Show pid namespace hierarchy information
> diff --git a/fs/proc/Makefile b/fs/proc/Makefile
> index 7151ea4..33e384b 100644
> --- a/fs/proc/Makefile
> +++ b/fs/proc/Makefile
> @@ -30,3 +30,4 @@ proc-$(CONFIG_PROC_KCORE) += kcore.o
> proc-$(CONFIG_PROC_VMCORE) += vmcore.o
> proc-$(CONFIG_PRINTK) += kmsg.o
> proc-$(CONFIG_PROC_PAGE_MONITOR) += page.o
> +proc-$(CONFIG_PROC_PID_HIERARCHY) += pidns_hierarchy.o
> diff --git a/fs/proc/pidns_hierarchy.c b/fs/proc/pidns_hierarchy.c
> new file mode 100644
> index 0000000..4629bfd
> --- /dev/null
> +++ b/fs/proc/pidns_hierarchy.c
> @@ -0,0 +1,280 @@
> +#include <linux/init.h>
> +#include <linux/errno.h>
> +#include <linux/proc_fs.h>
> +#include <linux/module.h>
> +#include <linux/list.h>
> +#include <linux/slab.h>
> +#include <linux/pid_namespace.h>
> +#include <linux/seq_file.h>
> +
> +/*
> + * /proc/pidns_hierarchy
> + *
> + * show the hierarchy of pid namespace in:
> + * <init_PID> <parent_of_init_PID> <relative PID level>
> + *
> + * init_PID: child reaper in ns
> + * parent_of_init_PID: init_PID's parent, also child reaper
> + * relative PID level: pid level relative to caller's ns
> + */
> +
> +#define NS_HIERARCHY "pidns_hierarchy"
> +#define MAX(a, b) ((a) > (b) ? (a) : (b))
Please use max() from kernel.h, there is no need to reinvent the wheel.
> +
> +/* list for host pid collection */
> +struct pidns_list {
> + struct list_head list;
> + struct pid *pid;
> + int show_level;
s/show_level/level, to keep it easy. :-)
> +};
> +
> +static void free_pidns_list(struct list_head *head)
> +{
> + struct pidns_list *tmp, *pos;
> +
> + list_for_each_entry_safe(pos, tmp, head, list) {
> + list_del(&pos->list);
> + put_pid(pos->pid);
> + kfree(pos);
> + }
> +}
> +
> +static int
> +pidns_list_add(struct pid *pid, struct list_head *list_head,
> + int show_level)
> +{
> + struct pidns_list *ent;
> +
> + ent = kmalloc(sizeof(*ent), GFP_KERNEL);
> + if (!ent)
> + return -ENOMEM;
> +
> + ent->pid = pid;
> + ent->show_level = show_level;
> + list_add_tail(&ent->list, list_head);
> +
> + return 0;
> +}
> +
> +static int
> +pidns_list_filter(struct list_head *pidns_pid_list,
> + struct list_head *pidns_pid_tree)
> +{
> + struct pidns_list *pos, *pos_t;
> + struct pid_namespace *ns0, *ns1;
> + struct pid *pid0, *pid1;
> + int rc, flag = 0;
> +
> + /*
> + * screen pids with relationship
> + * in pidns_pid_list, we may add pids like:
> + * ns0 ns1 ns2
> + * pid1->pid2->pid3
> + * we should screen pid1, pid2 and keep pid3
> + */
> + list_for_each_entry(pos, pidns_pid_list, list) {
> + list_for_each_entry(pos_t, pidns_pid_list, list) {
> + flag = 0;
> + pid0 = pos->pid;
> + pid1 = pos_t->pid;
> + ns0 = pid0->numbers[pid0->level].ns;
> + ns1 = pid1->numbers[pid1->level].ns;
> + if (pos->pid->level < pos_t->pid->level)
> + for (; ns1 != NULL; ns1 = ns1->parent)
> + if (ns0 == ns1) {
> + flag = 1;
> + break;
> + }
> + /* a redundant pid found */
> + if (flag == 1)
> + break;
> + }
> +
> + if (flag == 0) {
> + get_pid(pos->pid);
> + rc = pidns_list_add(pos->pid, pidns_pid_tree, 0);
> + if (rc) {
> + put_pid(pos->pid);
> + goto cleanup;
> + }
> + }
> + }
> +
> + /*
> + * Now all useful stuffs are in pidns_pid_tree,
> + * free pidns_pid_list
> + */
> + free_pidns_list(pidns_pid_list);
> +
> + return 0;
> +
> +cleanup:
> + free_pidns_list(pidns_pid_tree);
> + return rc;
> +}
> +
> +static void
> +pidns_list_set_show_level(struct list_head *pidns_list_in,
> + struct pid_namespace *curr_ns)
> +{
> + struct pidns_list *pos, *pos_t;
> + struct pid *pid0, *pid1;
> + int i;
> +
> + /*
> + * From the pid hierarchy point of view,
> + * we already had a list of pids who are not
> + * the subset of each other.
> + * But part of them may be same.
> + * We need to set the show_level of each pids:
> + * pid0: A->B->C pid1: A->B->D
> + * show_level 2 0
> + * We use show_level to identify
> + * the public part of each pids.
> + */
> + list_for_each_entry(pos, pidns_list_in, list) {
> + list_for_each_entry(pos_t, pidns_list_in, list) {
> + pid0 = pos->pid;
> + pid1 = pos_t->pid;
> + if (pid0 == pid1)
> + continue;
> + if (pos_t->show_level > 0)
> + continue;
> + for (i = curr_ns->level + 1; i <= pid0->level; i++) {
> + /* skip the public parts */
> + if (pid0->numbers[i].ns ==
> + pid1->numbers[i].ns)
> + continue;
> + else
> + break;
> + }
> + pos->show_level = i - 1;
> + }
> + }
> +}
> +
> +/*
> + * collect pids and stored in pidns_pid_list,
s/stored/store
> + * then remove duplicated ones,
> + * add the rest to pidns_pid_tree
> + */
This comment is a bit confusing.
What about "proc_pidns_list_refresh - Finds all init pids, places them into pidns_pid_list
and then stores the hirarchy into pidns_pid_tree."?
Beside of my minor comments I like the patch. :-)
Thanks a lot for doing this work!
Thanks,
//richard
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists