linux-stable/kernel/pid_namespace.c

467 lines
11 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Pid namespaces
*
* Authors:
* (C) 2007 Pavel Emelyanov <xemul@openvz.org>, OpenVZ, SWsoft Inc.
* (C) 2007 Sukadev Bhattiprolu <sukadev@us.ibm.com>, IBM
* Many thanks to Oleg Nesterov for comments and help
*
*/
#include <linux/pid.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/syscalls.h>
#include <linux/cred.h>
#include <linux/err.h>
#include <linux/acct.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/proc_ns.h>
pidns: add reboot_pid_ns() to handle the reboot syscall In the case of a child pid namespace, rebooting the system does not really makes sense. When the pid namespace is used in conjunction with the other namespaces in order to create a linux container, the reboot syscall leads to some problems. A container can reboot the host. That can be fixed by dropping the sys_reboot capability but we are unable to correctly to poweroff/ halt/reboot a container and the container stays stuck at the shutdown time with the container's init process waiting indefinitively. After several attempts, no solution from userspace was found to reliabily handle the shutdown from a container. This patch propose to make the init process of the child pid namespace to exit with a signal status set to : SIGINT if the child pid namespace called "halt/poweroff" and SIGHUP if the child pid namespace called "reboot". When the reboot syscall is called and we are not in the initial pid namespace, we kill the pid namespace for "HALT", "POWEROFF", "RESTART", and "RESTART2". Otherwise we return EINVAL. Returning EINVAL is also an easy way to check if this feature is supported by the kernel when invoking another 'reboot' option like CAD. By this way the parent process of the child pid namespace knows if it rebooted or not and can take the right decision. Test case: ========== #include <alloca.h> #include <stdio.h> #include <sched.h> #include <unistd.h> #include <signal.h> #include <sys/reboot.h> #include <sys/types.h> #include <sys/wait.h> #include <linux/reboot.h> static int do_reboot(void *arg) { int *cmd = arg; if (reboot(*cmd)) printf("failed to reboot(%d): %m\n", *cmd); } int test_reboot(int cmd, int sig) { long stack_size = 4096; void *stack = alloca(stack_size) + stack_size; int status; pid_t ret; ret = clone(do_reboot, stack, CLONE_NEWPID | SIGCHLD, &cmd); if (ret < 0) { printf("failed to clone: %m\n"); return -1; } if (wait(&status) < 0) { printf("unexpected wait error: %m\n"); return -1; } if (!WIFSIGNALED(status)) { printf("child process exited but was not signaled\n"); return -1; } if (WTERMSIG(status) != sig) { printf("signal termination is not the one expected\n"); return -1; } return 0; } int main(int argc, char *argv[]) { int status; status = test_reboot(LINUX_REBOOT_CMD_RESTART, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_RESTART2, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART2) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_HALT, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_HALT) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_POWER_OFF, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_POWERR_OFF) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_CAD_ON, -1); if (status >= 0) { printf("reboot(LINUX_REBOOT_CMD_CAD_ON) should have failed\n"); return 1; } printf("reboot(LINUX_REBOOT_CMD_CAD_ON) has failed as expected\n"); return 0; } [akpm@linux-foundation.org: tweak and add comments] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr> Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Tested-by: Serge Hallyn <serge.hallyn@canonical.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-28 21:42:51 +00:00
#include <linux/reboot.h>
#include <linux/export.h>
#include <linux/sched/task.h>
#include <linux/sched/signal.h>
pid: replace pid bitmap implementation with IDR API Patch series "Replacing PID bitmap implementation with IDR API", v4. This series replaces kernel bitmap implementation of PID allocation with IDR API. These patches are written to simplify the kernel by replacing custom code with calls to generic code. The following are the stats for pid and pid_namespace object files before and after the replacement. There is a noteworthy change between the IDR and bitmap implementation. Before text data bss dec hex filename 8447 3894 64 12405 3075 kernel/pid.o After text data bss dec hex filename 3397 304 0 3701 e75 kernel/pid.o Before text data bss dec hex filename 5692 1842 192 7726 1e2e kernel/pid_namespace.o After text data bss dec hex filename 2854 216 16 3086 c0e kernel/pid_namespace.o The following are the stats for ps, pstree and calling readdir on /proc for 10,000 processes. ps: With IDR API With bitmap real 0m1.479s 0m2.319s user 0m0.070s 0m0.060s sys 0m0.289s 0m0.516s pstree: With IDR API With bitmap real 0m1.024s 0m1.794s user 0m0.348s 0m0.612s sys 0m0.184s 0m0.264s proc: With IDR API With bitmap real 0m0.059s 0m0.074s user 0m0.000s 0m0.004s sys 0m0.016s 0m0.016s This patch (of 2): Replace the current bitmap implementation for Process ID allocation. Functions that are no longer required, for example, free_pidmap(), alloc_pidmap(), etc. are removed. The rest of the functions are modified to use the IDR API. The change was made to make the PID allocation less complex by replacing custom code with calls to generic API. [gs051095@gmail.com: v6] Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com [avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl] Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Julia Lawall <julia.lawall@lip6.fr> Cc: Ingo Molnar <mingo@kernel.org> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 23:30:30 +00:00
#include <linux/idr.h>
static DEFINE_MUTEX(pid_caches_mutex);
static struct kmem_cache *pid_ns_cachep;
/* Write once array, filled from the beginning. */
static struct kmem_cache *pid_cache[MAX_PID_NS_LEVEL];
/*
* creates the kmem cache to allocate pids from.
* @level: pid namespace level
*/
static struct kmem_cache *create_pid_cachep(unsigned int level)
{
/* Level 0 is init_pid_ns.pid_cachep */
struct kmem_cache **pkc = &pid_cache[level - 1];
struct kmem_cache *kc;
char name[4 + 10 + 1];
unsigned int len;
kc = READ_ONCE(*pkc);
if (kc)
return kc;
snprintf(name, sizeof(name), "pid_%u", level + 1);
len = sizeof(struct pid) + level * sizeof(struct upid);
mutex_lock(&pid_caches_mutex);
/* Name collision forces to do allocation under mutex. */
if (!*pkc)
*pkc = kmem_cache_create(name, len, 0, SLAB_HWCACHE_ALIGN, 0);
mutex_unlock(&pid_caches_mutex);
/* current can fail, but someone else can succeed. */
return READ_ONCE(*pkc);
}
static struct ucounts *inc_pid_namespaces(struct user_namespace *ns)
{
return inc_ucount(ns, current_euid(), UCOUNT_PID_NAMESPACES);
}
static void dec_pid_namespaces(struct ucounts *ucounts)
{
dec_ucount(ucounts, UCOUNT_PID_NAMESPACES);
}
static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns,
struct pid_namespace *parent_pid_ns)
{
struct pid_namespace *ns;
unsigned int level = parent_pid_ns->level + 1;
struct ucounts *ucounts;
pidns: limit the nesting depth of pid namespaces 'struct pid' is a "variable sized struct" - a header with an array of upids at the end. The size of the array depends on a level (depth) of pid namespaces. Now a level of pidns is not limited, so 'struct pid' can be more than one page. Looks reasonable, that it should be less than a page. MAX_PIS_NS_LEVEL is not calculated from PAGE_SIZE, because in this case it depends on architectures, config options and it will be reduced, if someone adds a new fields in struct pid or struct upid. I suggest to set MAX_PIS_NS_LEVEL = 32, because it saves ability to expand "struct pid" and it's more than enough for all known for me use-cases. When someone finds a reasonable use case, we can add a config option or a sysctl parameter. In addition it will reduce the effect of another problem, when we have many nested namespaces and the oldest one starts dying. zap_pid_ns_processe will be called for each namespace and find_vpid will be called for each process in a namespace. find_vpid will be called minimum max_level^2 / 2 times. The reason of that is that when we found a bit in pidmap, we can't determine this pidns is top for this process or it isn't. vpid is a heavy operation, so a fork bomb, which create many nested namespace, can make a system inaccessible for a long time. For example my system becomes inaccessible for a few minutes with 4000 processes. [akpm@linux-foundation.org: return -EINVAL in response to excessive nesting, not -ENOMEM] Signed-off-by: Andrew Vagin <avagin@openvz.org> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-25 20:38:07 +00:00
int err;
err = -EINVAL;
if (!in_userns(parent_pid_ns->user_ns, user_ns))
goto out;
err = -ENOSPC;
if (level > MAX_PID_NS_LEVEL)
goto out;
ucounts = inc_pid_namespaces(user_ns);
if (!ucounts)
pidns: limit the nesting depth of pid namespaces 'struct pid' is a "variable sized struct" - a header with an array of upids at the end. The size of the array depends on a level (depth) of pid namespaces. Now a level of pidns is not limited, so 'struct pid' can be more than one page. Looks reasonable, that it should be less than a page. MAX_PIS_NS_LEVEL is not calculated from PAGE_SIZE, because in this case it depends on architectures, config options and it will be reduced, if someone adds a new fields in struct pid or struct upid. I suggest to set MAX_PIS_NS_LEVEL = 32, because it saves ability to expand "struct pid" and it's more than enough for all known for me use-cases. When someone finds a reasonable use case, we can add a config option or a sysctl parameter. In addition it will reduce the effect of another problem, when we have many nested namespaces and the oldest one starts dying. zap_pid_ns_processe will be called for each namespace and find_vpid will be called for each process in a namespace. find_vpid will be called minimum max_level^2 / 2 times. The reason of that is that when we found a bit in pidmap, we can't determine this pidns is top for this process or it isn't. vpid is a heavy operation, so a fork bomb, which create many nested namespace, can make a system inaccessible for a long time. For example my system becomes inaccessible for a few minutes with 4000 processes. [akpm@linux-foundation.org: return -EINVAL in response to excessive nesting, not -ENOMEM] Signed-off-by: Andrew Vagin <avagin@openvz.org> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-25 20:38:07 +00:00
goto out;
pidns: limit the nesting depth of pid namespaces 'struct pid' is a "variable sized struct" - a header with an array of upids at the end. The size of the array depends on a level (depth) of pid namespaces. Now a level of pidns is not limited, so 'struct pid' can be more than one page. Looks reasonable, that it should be less than a page. MAX_PIS_NS_LEVEL is not calculated from PAGE_SIZE, because in this case it depends on architectures, config options and it will be reduced, if someone adds a new fields in struct pid or struct upid. I suggest to set MAX_PIS_NS_LEVEL = 32, because it saves ability to expand "struct pid" and it's more than enough for all known for me use-cases. When someone finds a reasonable use case, we can add a config option or a sysctl parameter. In addition it will reduce the effect of another problem, when we have many nested namespaces and the oldest one starts dying. zap_pid_ns_processe will be called for each namespace and find_vpid will be called for each process in a namespace. find_vpid will be called minimum max_level^2 / 2 times. The reason of that is that when we found a bit in pidmap, we can't determine this pidns is top for this process or it isn't. vpid is a heavy operation, so a fork bomb, which create many nested namespace, can make a system inaccessible for a long time. For example my system becomes inaccessible for a few minutes with 4000 processes. [akpm@linux-foundation.org: return -EINVAL in response to excessive nesting, not -ENOMEM] Signed-off-by: Andrew Vagin <avagin@openvz.org> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Pavel Emelyanov <xemul@parallels.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-10-25 20:38:07 +00:00
err = -ENOMEM;
ns = kmem_cache_zalloc(pid_ns_cachep, GFP_KERNEL);
if (ns == NULL)
goto out_dec;
pid: replace pid bitmap implementation with IDR API Patch series "Replacing PID bitmap implementation with IDR API", v4. This series replaces kernel bitmap implementation of PID allocation with IDR API. These patches are written to simplify the kernel by replacing custom code with calls to generic code. The following are the stats for pid and pid_namespace object files before and after the replacement. There is a noteworthy change between the IDR and bitmap implementation. Before text data bss dec hex filename 8447 3894 64 12405 3075 kernel/pid.o After text data bss dec hex filename 3397 304 0 3701 e75 kernel/pid.o Before text data bss dec hex filename 5692 1842 192 7726 1e2e kernel/pid_namespace.o After text data bss dec hex filename 2854 216 16 3086 c0e kernel/pid_namespace.o The following are the stats for ps, pstree and calling readdir on /proc for 10,000 processes. ps: With IDR API With bitmap real 0m1.479s 0m2.319s user 0m0.070s 0m0.060s sys 0m0.289s 0m0.516s pstree: With IDR API With bitmap real 0m1.024s 0m1.794s user 0m0.348s 0m0.612s sys 0m0.184s 0m0.264s proc: With IDR API With bitmap real 0m0.059s 0m0.074s user 0m0.000s 0m0.004s sys 0m0.016s 0m0.016s This patch (of 2): Replace the current bitmap implementation for Process ID allocation. Functions that are no longer required, for example, free_pidmap(), alloc_pidmap(), etc. are removed. The rest of the functions are modified to use the IDR API. The change was made to make the PID allocation less complex by replacing custom code with calls to generic API. [gs051095@gmail.com: v6] Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com [avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl] Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Julia Lawall <julia.lawall@lip6.fr> Cc: Ingo Molnar <mingo@kernel.org> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 23:30:30 +00:00
idr_init(&ns->idr);
ns->pid_cachep = create_pid_cachep(level);
if (ns->pid_cachep == NULL)
pid: replace pid bitmap implementation with IDR API Patch series "Replacing PID bitmap implementation with IDR API", v4. This series replaces kernel bitmap implementation of PID allocation with IDR API. These patches are written to simplify the kernel by replacing custom code with calls to generic code. The following are the stats for pid and pid_namespace object files before and after the replacement. There is a noteworthy change between the IDR and bitmap implementation. Before text data bss dec hex filename 8447 3894 64 12405 3075 kernel/pid.o After text data bss dec hex filename 3397 304 0 3701 e75 kernel/pid.o Before text data bss dec hex filename 5692 1842 192 7726 1e2e kernel/pid_namespace.o After text data bss dec hex filename 2854 216 16 3086 c0e kernel/pid_namespace.o The following are the stats for ps, pstree and calling readdir on /proc for 10,000 processes. ps: With IDR API With bitmap real 0m1.479s 0m2.319s user 0m0.070s 0m0.060s sys 0m0.289s 0m0.516s pstree: With IDR API With bitmap real 0m1.024s 0m1.794s user 0m0.348s 0m0.612s sys 0m0.184s 0m0.264s proc: With IDR API With bitmap real 0m0.059s 0m0.074s user 0m0.000s 0m0.004s sys 0m0.016s 0m0.016s This patch (of 2): Replace the current bitmap implementation for Process ID allocation. Functions that are no longer required, for example, free_pidmap(), alloc_pidmap(), etc. are removed. The rest of the functions are modified to use the IDR API. The change was made to make the PID allocation less complex by replacing custom code with calls to generic API. [gs051095@gmail.com: v6] Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com [avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl] Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Julia Lawall <julia.lawall@lip6.fr> Cc: Ingo Molnar <mingo@kernel.org> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 23:30:30 +00:00
goto out_free_idr;
err = ns_alloc_inum(&ns->ns);
if (err)
pid: replace pid bitmap implementation with IDR API Patch series "Replacing PID bitmap implementation with IDR API", v4. This series replaces kernel bitmap implementation of PID allocation with IDR API. These patches are written to simplify the kernel by replacing custom code with calls to generic code. The following are the stats for pid and pid_namespace object files before and after the replacement. There is a noteworthy change between the IDR and bitmap implementation. Before text data bss dec hex filename 8447 3894 64 12405 3075 kernel/pid.o After text data bss dec hex filename 3397 304 0 3701 e75 kernel/pid.o Before text data bss dec hex filename 5692 1842 192 7726 1e2e kernel/pid_namespace.o After text data bss dec hex filename 2854 216 16 3086 c0e kernel/pid_namespace.o The following are the stats for ps, pstree and calling readdir on /proc for 10,000 processes. ps: With IDR API With bitmap real 0m1.479s 0m2.319s user 0m0.070s 0m0.060s sys 0m0.289s 0m0.516s pstree: With IDR API With bitmap real 0m1.024s 0m1.794s user 0m0.348s 0m0.612s sys 0m0.184s 0m0.264s proc: With IDR API With bitmap real 0m0.059s 0m0.074s user 0m0.000s 0m0.004s sys 0m0.016s 0m0.016s This patch (of 2): Replace the current bitmap implementation for Process ID allocation. Functions that are no longer required, for example, free_pidmap(), alloc_pidmap(), etc. are removed. The rest of the functions are modified to use the IDR API. The change was made to make the PID allocation less complex by replacing custom code with calls to generic API. [gs051095@gmail.com: v6] Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com [avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl] Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Julia Lawall <julia.lawall@lip6.fr> Cc: Ingo Molnar <mingo@kernel.org> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 23:30:30 +00:00
goto out_free_idr;
ns->ns.ops = &pidns_operations;
kref_init(&ns->kref);
ns->level = level;
ns->parent = get_pid_ns(parent_pid_ns);
ns->user_ns = get_user_ns(user_ns);
ns->ucounts = ucounts;
ns->pid_allocated = PIDNS_ADDING;
return ns;
pid: replace pid bitmap implementation with IDR API Patch series "Replacing PID bitmap implementation with IDR API", v4. This series replaces kernel bitmap implementation of PID allocation with IDR API. These patches are written to simplify the kernel by replacing custom code with calls to generic code. The following are the stats for pid and pid_namespace object files before and after the replacement. There is a noteworthy change between the IDR and bitmap implementation. Before text data bss dec hex filename 8447 3894 64 12405 3075 kernel/pid.o After text data bss dec hex filename 3397 304 0 3701 e75 kernel/pid.o Before text data bss dec hex filename 5692 1842 192 7726 1e2e kernel/pid_namespace.o After text data bss dec hex filename 2854 216 16 3086 c0e kernel/pid_namespace.o The following are the stats for ps, pstree and calling readdir on /proc for 10,000 processes. ps: With IDR API With bitmap real 0m1.479s 0m2.319s user 0m0.070s 0m0.060s sys 0m0.289s 0m0.516s pstree: With IDR API With bitmap real 0m1.024s 0m1.794s user 0m0.348s 0m0.612s sys 0m0.184s 0m0.264s proc: With IDR API With bitmap real 0m0.059s 0m0.074s user 0m0.000s 0m0.004s sys 0m0.016s 0m0.016s This patch (of 2): Replace the current bitmap implementation for Process ID allocation. Functions that are no longer required, for example, free_pidmap(), alloc_pidmap(), etc. are removed. The rest of the functions are modified to use the IDR API. The change was made to make the PID allocation less complex by replacing custom code with calls to generic API. [gs051095@gmail.com: v6] Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com [avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl] Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Julia Lawall <julia.lawall@lip6.fr> Cc: Ingo Molnar <mingo@kernel.org> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 23:30:30 +00:00
out_free_idr:
idr_destroy(&ns->idr);
kmem_cache_free(pid_ns_cachep, ns);
out_dec:
dec_pid_namespaces(ucounts);
out:
return ERR_PTR(err);
}
static void delayed_free_pidns(struct rcu_head *p)
{
struct pid_namespace *ns = container_of(p, struct pid_namespace, rcu);
dec_pid_namespaces(ns->ucounts);
put_user_ns(ns->user_ns);
kmem_cache_free(pid_ns_cachep, ns);
}
static void destroy_pid_namespace(struct pid_namespace *ns)
{
ns_free_inum(&ns->ns);
pid: replace pid bitmap implementation with IDR API Patch series "Replacing PID bitmap implementation with IDR API", v4. This series replaces kernel bitmap implementation of PID allocation with IDR API. These patches are written to simplify the kernel by replacing custom code with calls to generic code. The following are the stats for pid and pid_namespace object files before and after the replacement. There is a noteworthy change between the IDR and bitmap implementation. Before text data bss dec hex filename 8447 3894 64 12405 3075 kernel/pid.o After text data bss dec hex filename 3397 304 0 3701 e75 kernel/pid.o Before text data bss dec hex filename 5692 1842 192 7726 1e2e kernel/pid_namespace.o After text data bss dec hex filename 2854 216 16 3086 c0e kernel/pid_namespace.o The following are the stats for ps, pstree and calling readdir on /proc for 10,000 processes. ps: With IDR API With bitmap real 0m1.479s 0m2.319s user 0m0.070s 0m0.060s sys 0m0.289s 0m0.516s pstree: With IDR API With bitmap real 0m1.024s 0m1.794s user 0m0.348s 0m0.612s sys 0m0.184s 0m0.264s proc: With IDR API With bitmap real 0m0.059s 0m0.074s user 0m0.000s 0m0.004s sys 0m0.016s 0m0.016s This patch (of 2): Replace the current bitmap implementation for Process ID allocation. Functions that are no longer required, for example, free_pidmap(), alloc_pidmap(), etc. are removed. The rest of the functions are modified to use the IDR API. The change was made to make the PID allocation less complex by replacing custom code with calls to generic API. [gs051095@gmail.com: v6] Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com [avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl] Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Julia Lawall <julia.lawall@lip6.fr> Cc: Ingo Molnar <mingo@kernel.org> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 23:30:30 +00:00
idr_destroy(&ns->idr);
call_rcu(&ns->rcu, delayed_free_pidns);
}
struct pid_namespace *copy_pid_ns(unsigned long flags,
struct user_namespace *user_ns, struct pid_namespace *old_ns)
{
if (!(flags & CLONE_NEWPID))
return get_pid_ns(old_ns);
if (task_active_pid_ns(current) != old_ns)
return ERR_PTR(-EINVAL);
return create_pid_namespace(user_ns, old_ns);
}
static void free_pid_ns(struct kref *kref)
{
struct pid_namespace *ns;
ns = container_of(kref, struct pid_namespace, kref);
destroy_pid_namespace(ns);
}
void put_pid_ns(struct pid_namespace *ns)
{
struct pid_namespace *parent;
while (ns != &init_pid_ns) {
parent = ns->parent;
if (!kref_put(&ns->kref, free_pid_ns))
break;
ns = parent;
}
}
EXPORT_SYMBOL_GPL(put_pid_ns);
void zap_pid_ns_processes(struct pid_namespace *pid_ns)
{
int nr;
int rc;
struct task_struct *task, *me = current;
int init_pids = thread_group_leader(me) ? 1 : 2;
pid: replace pid bitmap implementation with IDR API Patch series "Replacing PID bitmap implementation with IDR API", v4. This series replaces kernel bitmap implementation of PID allocation with IDR API. These patches are written to simplify the kernel by replacing custom code with calls to generic code. The following are the stats for pid and pid_namespace object files before and after the replacement. There is a noteworthy change between the IDR and bitmap implementation. Before text data bss dec hex filename 8447 3894 64 12405 3075 kernel/pid.o After text data bss dec hex filename 3397 304 0 3701 e75 kernel/pid.o Before text data bss dec hex filename 5692 1842 192 7726 1e2e kernel/pid_namespace.o After text data bss dec hex filename 2854 216 16 3086 c0e kernel/pid_namespace.o The following are the stats for ps, pstree and calling readdir on /proc for 10,000 processes. ps: With IDR API With bitmap real 0m1.479s 0m2.319s user 0m0.070s 0m0.060s sys 0m0.289s 0m0.516s pstree: With IDR API With bitmap real 0m1.024s 0m1.794s user 0m0.348s 0m0.612s sys 0m0.184s 0m0.264s proc: With IDR API With bitmap real 0m0.059s 0m0.074s user 0m0.000s 0m0.004s sys 0m0.016s 0m0.016s This patch (of 2): Replace the current bitmap implementation for Process ID allocation. Functions that are no longer required, for example, free_pidmap(), alloc_pidmap(), etc. are removed. The rest of the functions are modified to use the IDR API. The change was made to make the PID allocation less complex by replacing custom code with calls to generic API. [gs051095@gmail.com: v6] Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com [avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl] Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Julia Lawall <julia.lawall@lip6.fr> Cc: Ingo Molnar <mingo@kernel.org> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 23:30:30 +00:00
struct pid *pid;
/* Don't allow any more processes into the pid namespace */
disable_pid_allocation(pid_ns);
/*
* Ignore SIGCHLD causing any terminated children to autoreap.
* This speeds up the namespace shutdown, plus see the comment
* below.
*/
spin_lock_irq(&me->sighand->siglock);
me->sighand->action[SIGCHLD - 1].sa.sa_handler = SIG_IGN;
spin_unlock_irq(&me->sighand->siglock);
/*
* 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.
*
*/
pid: replace pid bitmap implementation with IDR API Patch series "Replacing PID bitmap implementation with IDR API", v4. This series replaces kernel bitmap implementation of PID allocation with IDR API. These patches are written to simplify the kernel by replacing custom code with calls to generic code. The following are the stats for pid and pid_namespace object files before and after the replacement. There is a noteworthy change between the IDR and bitmap implementation. Before text data bss dec hex filename 8447 3894 64 12405 3075 kernel/pid.o After text data bss dec hex filename 3397 304 0 3701 e75 kernel/pid.o Before text data bss dec hex filename 5692 1842 192 7726 1e2e kernel/pid_namespace.o After text data bss dec hex filename 2854 216 16 3086 c0e kernel/pid_namespace.o The following are the stats for ps, pstree and calling readdir on /proc for 10,000 processes. ps: With IDR API With bitmap real 0m1.479s 0m2.319s user 0m0.070s 0m0.060s sys 0m0.289s 0m0.516s pstree: With IDR API With bitmap real 0m1.024s 0m1.794s user 0m0.348s 0m0.612s sys 0m0.184s 0m0.264s proc: With IDR API With bitmap real 0m0.059s 0m0.074s user 0m0.000s 0m0.004s sys 0m0.016s 0m0.016s This patch (of 2): Replace the current bitmap implementation for Process ID allocation. Functions that are no longer required, for example, free_pidmap(), alloc_pidmap(), etc. are removed. The rest of the functions are modified to use the IDR API. The change was made to make the PID allocation less complex by replacing custom code with calls to generic API. [gs051095@gmail.com: v6] Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com [avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl] Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Julia Lawall <julia.lawall@lip6.fr> Cc: Ingo Molnar <mingo@kernel.org> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 23:30:30 +00:00
rcu_read_lock();
read_lock(&tasklist_lock);
pid: replace pid bitmap implementation with IDR API Patch series "Replacing PID bitmap implementation with IDR API", v4. This series replaces kernel bitmap implementation of PID allocation with IDR API. These patches are written to simplify the kernel by replacing custom code with calls to generic code. The following are the stats for pid and pid_namespace object files before and after the replacement. There is a noteworthy change between the IDR and bitmap implementation. Before text data bss dec hex filename 8447 3894 64 12405 3075 kernel/pid.o After text data bss dec hex filename 3397 304 0 3701 e75 kernel/pid.o Before text data bss dec hex filename 5692 1842 192 7726 1e2e kernel/pid_namespace.o After text data bss dec hex filename 2854 216 16 3086 c0e kernel/pid_namespace.o The following are the stats for ps, pstree and calling readdir on /proc for 10,000 processes. ps: With IDR API With bitmap real 0m1.479s 0m2.319s user 0m0.070s 0m0.060s sys 0m0.289s 0m0.516s pstree: With IDR API With bitmap real 0m1.024s 0m1.794s user 0m0.348s 0m0.612s sys 0m0.184s 0m0.264s proc: With IDR API With bitmap real 0m0.059s 0m0.074s user 0m0.000s 0m0.004s sys 0m0.016s 0m0.016s This patch (of 2): Replace the current bitmap implementation for Process ID allocation. Functions that are no longer required, for example, free_pidmap(), alloc_pidmap(), etc. are removed. The rest of the functions are modified to use the IDR API. The change was made to make the PID allocation less complex by replacing custom code with calls to generic API. [gs051095@gmail.com: v6] Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com [avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl] Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Julia Lawall <julia.lawall@lip6.fr> Cc: Ingo Molnar <mingo@kernel.org> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 23:30:30 +00:00
nr = 2;
idr_for_each_entry_continue(&pid_ns->idr, pid, nr) {
task = pid_task(pid, PIDTYPE_PID);
if (task && !__fatal_signal_pending(task))
group_send_sig_info(SIGKILL, SEND_SIG_PRIV, task, PIDTYPE_MAX);
}
read_unlock(&tasklist_lock);
pid: replace pid bitmap implementation with IDR API Patch series "Replacing PID bitmap implementation with IDR API", v4. This series replaces kernel bitmap implementation of PID allocation with IDR API. These patches are written to simplify the kernel by replacing custom code with calls to generic code. The following are the stats for pid and pid_namespace object files before and after the replacement. There is a noteworthy change between the IDR and bitmap implementation. Before text data bss dec hex filename 8447 3894 64 12405 3075 kernel/pid.o After text data bss dec hex filename 3397 304 0 3701 e75 kernel/pid.o Before text data bss dec hex filename 5692 1842 192 7726 1e2e kernel/pid_namespace.o After text data bss dec hex filename 2854 216 16 3086 c0e kernel/pid_namespace.o The following are the stats for ps, pstree and calling readdir on /proc for 10,000 processes. ps: With IDR API With bitmap real 0m1.479s 0m2.319s user 0m0.070s 0m0.060s sys 0m0.289s 0m0.516s pstree: With IDR API With bitmap real 0m1.024s 0m1.794s user 0m0.348s 0m0.612s sys 0m0.184s 0m0.264s proc: With IDR API With bitmap real 0m0.059s 0m0.074s user 0m0.000s 0m0.004s sys 0m0.016s 0m0.016s This patch (of 2): Replace the current bitmap implementation for Process ID allocation. Functions that are no longer required, for example, free_pidmap(), alloc_pidmap(), etc. are removed. The rest of the functions are modified to use the IDR API. The change was made to make the PID allocation less complex by replacing custom code with calls to generic API. [gs051095@gmail.com: v6] Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com [avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl] Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Julia Lawall <julia.lawall@lip6.fr> Cc: Ingo Molnar <mingo@kernel.org> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 23:30:30 +00:00
rcu_read_unlock();
/*
* Reap the EXIT_ZOMBIE children we had before we ignored SIGCHLD.
* kernel_wait4() will also block until our children traced from the
* parent namespace are detached and become EXIT_DEAD.
*/
do {
clear_thread_flag(TIF_SIGPENDING);
rc = kernel_wait4(-1, NULL, __WALL, NULL);
} while (rc != -ECHILD);
pidns: guarantee that the pidns init will be the last pidns process reaped Today we have a twofold bug. Sometimes release_task on pid == 1 in a pid namespace can run before other processes in a pid namespace have had release task called. With the result that pid_ns_release_proc can be called before the last proc_flus_task() is done using upid->ns->proc_mnt, resulting in the use of a stale pointer. This same set of circumstances can lead to waitpid(...) returning for a processes started with clone(CLONE_NEWPID) before the every process in the pid namespace has actually exited. To fix this modify zap_pid_ns_processess wait until all other processes in the pid namespace have exited, even EXIT_DEAD zombies. The delay_group_leader and related tests ensure that the thread gruop leader will be the last thread of a process group to be reaped, or to become EXIT_DEAD and self reap. With the change to zap_pid_ns_processes we get the guarantee that pid == 1 in a pid namespace will be the last task that release_task is called on. With pid == 1 being the last task to pass through release_task pid_ns_release_proc can no longer be called too early nor can wait return before all of the EXIT_DEAD tasks in a pid namespace have exited. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Louis Rilling <louis.rilling@kerlabs.com> Cc: Mike Galbraith <efault@gmx.de> Acked-by: Pavel Emelyanov <xemul@parallels.com> Tested-by: Andrew Wagin <avagin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-20 19:53:03 +00:00
/*
* kernel_wait4() misses EXIT_DEAD children, and EXIT_ZOMBIE
* process whose parents processes are outside of the pid
* namespace. Such processes are created with setns()+fork().
*
* If those EXIT_ZOMBIE processes are not reaped by their
* parents before their parents exit, they will be reparented
* to pid_ns->child_reaper. Thus pidns->child_reaper needs to
* stay valid until they all go away.
*
* The code relies on the the pid_ns->child_reaper ignoring
* SIGCHILD to cause those EXIT_ZOMBIE processes to be
* autoreaped if reparented.
*
* Semantically it is also desirable to wait for EXIT_ZOMBIE
* processes before allowing the child_reaper to be reaped, as
* that gives the invariant that when the init process of a
* pid namespace is reaped all of the processes in the pid
* namespace are gone.
*
* Once all of the other tasks are gone from the pid_namespace
* free_pid() will awaken this task.
pidns: guarantee that the pidns init will be the last pidns process reaped Today we have a twofold bug. Sometimes release_task on pid == 1 in a pid namespace can run before other processes in a pid namespace have had release task called. With the result that pid_ns_release_proc can be called before the last proc_flus_task() is done using upid->ns->proc_mnt, resulting in the use of a stale pointer. This same set of circumstances can lead to waitpid(...) returning for a processes started with clone(CLONE_NEWPID) before the every process in the pid namespace has actually exited. To fix this modify zap_pid_ns_processess wait until all other processes in the pid namespace have exited, even EXIT_DEAD zombies. The delay_group_leader and related tests ensure that the thread gruop leader will be the last thread of a process group to be reaped, or to become EXIT_DEAD and self reap. With the change to zap_pid_ns_processes we get the guarantee that pid == 1 in a pid namespace will be the last task that release_task is called on. With pid == 1 being the last task to pass through release_task pid_ns_release_proc can no longer be called too early nor can wait return before all of the EXIT_DEAD tasks in a pid namespace have exited. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Louis Rilling <louis.rilling@kerlabs.com> Cc: Mike Galbraith <efault@gmx.de> Acked-by: Pavel Emelyanov <xemul@parallels.com> Tested-by: Andrew Wagin <avagin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-20 19:53:03 +00:00
*/
for (;;) {
set_current_state(TASK_INTERRUPTIBLE);
if (pid_ns->pid_allocated == init_pids)
pidns: guarantee that the pidns init will be the last pidns process reaped Today we have a twofold bug. Sometimes release_task on pid == 1 in a pid namespace can run before other processes in a pid namespace have had release task called. With the result that pid_ns_release_proc can be called before the last proc_flus_task() is done using upid->ns->proc_mnt, resulting in the use of a stale pointer. This same set of circumstances can lead to waitpid(...) returning for a processes started with clone(CLONE_NEWPID) before the every process in the pid namespace has actually exited. To fix this modify zap_pid_ns_processess wait until all other processes in the pid namespace have exited, even EXIT_DEAD zombies. The delay_group_leader and related tests ensure that the thread gruop leader will be the last thread of a process group to be reaped, or to become EXIT_DEAD and self reap. With the change to zap_pid_ns_processes we get the guarantee that pid == 1 in a pid namespace will be the last task that release_task is called on. With pid == 1 being the last task to pass through release_task pid_ns_release_proc can no longer be called too early nor can wait return before all of the EXIT_DEAD tasks in a pid namespace have exited. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Louis Rilling <louis.rilling@kerlabs.com> Cc: Mike Galbraith <efault@gmx.de> Acked-by: Pavel Emelyanov <xemul@parallels.com> Tested-by: Andrew Wagin <avagin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-20 19:53:03 +00:00
break;
schedule();
}
__set_current_state(TASK_RUNNING);
pidns: guarantee that the pidns init will be the last pidns process reaped Today we have a twofold bug. Sometimes release_task on pid == 1 in a pid namespace can run before other processes in a pid namespace have had release task called. With the result that pid_ns_release_proc can be called before the last proc_flus_task() is done using upid->ns->proc_mnt, resulting in the use of a stale pointer. This same set of circumstances can lead to waitpid(...) returning for a processes started with clone(CLONE_NEWPID) before the every process in the pid namespace has actually exited. To fix this modify zap_pid_ns_processess wait until all other processes in the pid namespace have exited, even EXIT_DEAD zombies. The delay_group_leader and related tests ensure that the thread gruop leader will be the last thread of a process group to be reaped, or to become EXIT_DEAD and self reap. With the change to zap_pid_ns_processes we get the guarantee that pid == 1 in a pid namespace will be the last task that release_task is called on. With pid == 1 being the last task to pass through release_task pid_ns_release_proc can no longer be called too early nor can wait return before all of the EXIT_DEAD tasks in a pid namespace have exited. Signed-off-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Cc: Louis Rilling <louis.rilling@kerlabs.com> Cc: Mike Galbraith <efault@gmx.de> Acked-by: Pavel Emelyanov <xemul@parallels.com> Tested-by: Andrew Wagin <avagin@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-06-20 19:53:03 +00:00
pidns: add reboot_pid_ns() to handle the reboot syscall In the case of a child pid namespace, rebooting the system does not really makes sense. When the pid namespace is used in conjunction with the other namespaces in order to create a linux container, the reboot syscall leads to some problems. A container can reboot the host. That can be fixed by dropping the sys_reboot capability but we are unable to correctly to poweroff/ halt/reboot a container and the container stays stuck at the shutdown time with the container's init process waiting indefinitively. After several attempts, no solution from userspace was found to reliabily handle the shutdown from a container. This patch propose to make the init process of the child pid namespace to exit with a signal status set to : SIGINT if the child pid namespace called "halt/poweroff" and SIGHUP if the child pid namespace called "reboot". When the reboot syscall is called and we are not in the initial pid namespace, we kill the pid namespace for "HALT", "POWEROFF", "RESTART", and "RESTART2". Otherwise we return EINVAL. Returning EINVAL is also an easy way to check if this feature is supported by the kernel when invoking another 'reboot' option like CAD. By this way the parent process of the child pid namespace knows if it rebooted or not and can take the right decision. Test case: ========== #include <alloca.h> #include <stdio.h> #include <sched.h> #include <unistd.h> #include <signal.h> #include <sys/reboot.h> #include <sys/types.h> #include <sys/wait.h> #include <linux/reboot.h> static int do_reboot(void *arg) { int *cmd = arg; if (reboot(*cmd)) printf("failed to reboot(%d): %m\n", *cmd); } int test_reboot(int cmd, int sig) { long stack_size = 4096; void *stack = alloca(stack_size) + stack_size; int status; pid_t ret; ret = clone(do_reboot, stack, CLONE_NEWPID | SIGCHLD, &cmd); if (ret < 0) { printf("failed to clone: %m\n"); return -1; } if (wait(&status) < 0) { printf("unexpected wait error: %m\n"); return -1; } if (!WIFSIGNALED(status)) { printf("child process exited but was not signaled\n"); return -1; } if (WTERMSIG(status) != sig) { printf("signal termination is not the one expected\n"); return -1; } return 0; } int main(int argc, char *argv[]) { int status; status = test_reboot(LINUX_REBOOT_CMD_RESTART, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_RESTART2, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART2) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_HALT, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_HALT) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_POWER_OFF, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_POWERR_OFF) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_CAD_ON, -1); if (status >= 0) { printf("reboot(LINUX_REBOOT_CMD_CAD_ON) should have failed\n"); return 1; } printf("reboot(LINUX_REBOOT_CMD_CAD_ON) has failed as expected\n"); return 0; } [akpm@linux-foundation.org: tweak and add comments] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr> Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Tested-by: Serge Hallyn <serge.hallyn@canonical.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-28 21:42:51 +00:00
if (pid_ns->reboot)
current->signal->group_exit_code = pid_ns->reboot;
acct_exit_ns(pid_ns);
return;
}
#ifdef CONFIG_CHECKPOINT_RESTORE
static int pid_ns_ctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct pid_namespace *pid_ns = task_active_pid_ns(current);
struct ctl_table tmp = *table;
pid: replace pid bitmap implementation with IDR API Patch series "Replacing PID bitmap implementation with IDR API", v4. This series replaces kernel bitmap implementation of PID allocation with IDR API. These patches are written to simplify the kernel by replacing custom code with calls to generic code. The following are the stats for pid and pid_namespace object files before and after the replacement. There is a noteworthy change between the IDR and bitmap implementation. Before text data bss dec hex filename 8447 3894 64 12405 3075 kernel/pid.o After text data bss dec hex filename 3397 304 0 3701 e75 kernel/pid.o Before text data bss dec hex filename 5692 1842 192 7726 1e2e kernel/pid_namespace.o After text data bss dec hex filename 2854 216 16 3086 c0e kernel/pid_namespace.o The following are the stats for ps, pstree and calling readdir on /proc for 10,000 processes. ps: With IDR API With bitmap real 0m1.479s 0m2.319s user 0m0.070s 0m0.060s sys 0m0.289s 0m0.516s pstree: With IDR API With bitmap real 0m1.024s 0m1.794s user 0m0.348s 0m0.612s sys 0m0.184s 0m0.264s proc: With IDR API With bitmap real 0m0.059s 0m0.074s user 0m0.000s 0m0.004s sys 0m0.016s 0m0.016s This patch (of 2): Replace the current bitmap implementation for Process ID allocation. Functions that are no longer required, for example, free_pidmap(), alloc_pidmap(), etc. are removed. The rest of the functions are modified to use the IDR API. The change was made to make the PID allocation less complex by replacing custom code with calls to generic API. [gs051095@gmail.com: v6] Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com [avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl] Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Julia Lawall <julia.lawall@lip6.fr> Cc: Ingo Molnar <mingo@kernel.org> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 23:30:30 +00:00
int ret, next;
if (write && !ns_capable(pid_ns->user_ns, CAP_SYS_ADMIN))
return -EPERM;
/*
* Writing directly to ns' last_pid field is OK, since this field
* is volatile in a living namespace anyway and a code writing to
* it should synchronize its usage with external means.
*/
pid: replace pid bitmap implementation with IDR API Patch series "Replacing PID bitmap implementation with IDR API", v4. This series replaces kernel bitmap implementation of PID allocation with IDR API. These patches are written to simplify the kernel by replacing custom code with calls to generic code. The following are the stats for pid and pid_namespace object files before and after the replacement. There is a noteworthy change between the IDR and bitmap implementation. Before text data bss dec hex filename 8447 3894 64 12405 3075 kernel/pid.o After text data bss dec hex filename 3397 304 0 3701 e75 kernel/pid.o Before text data bss dec hex filename 5692 1842 192 7726 1e2e kernel/pid_namespace.o After text data bss dec hex filename 2854 216 16 3086 c0e kernel/pid_namespace.o The following are the stats for ps, pstree and calling readdir on /proc for 10,000 processes. ps: With IDR API With bitmap real 0m1.479s 0m2.319s user 0m0.070s 0m0.060s sys 0m0.289s 0m0.516s pstree: With IDR API With bitmap real 0m1.024s 0m1.794s user 0m0.348s 0m0.612s sys 0m0.184s 0m0.264s proc: With IDR API With bitmap real 0m0.059s 0m0.074s user 0m0.000s 0m0.004s sys 0m0.016s 0m0.016s This patch (of 2): Replace the current bitmap implementation for Process ID allocation. Functions that are no longer required, for example, free_pidmap(), alloc_pidmap(), etc. are removed. The rest of the functions are modified to use the IDR API. The change was made to make the PID allocation less complex by replacing custom code with calls to generic API. [gs051095@gmail.com: v6] Link: http://lkml.kernel.org/r/1507760379-21662-2-git-send-email-gs051095@gmail.com [avagin@openvz.org: restore the old behaviour of the ns_last_pid sysctl] Link: http://lkml.kernel.org/r/20171106183144.16368-1-avagin@openvz.org Link: http://lkml.kernel.org/r/1507583624-22146-2-git-send-email-gs051095@gmail.com Signed-off-by: Gargi Sharma <gs051095@gmail.com> Reviewed-by: Rik van Riel <riel@redhat.com> Acked-by: Oleg Nesterov <oleg@redhat.com> Cc: Julia Lawall <julia.lawall@lip6.fr> Cc: Ingo Molnar <mingo@kernel.org> Cc: Pavel Tatashin <pasha.tatashin@oracle.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Christoph Hellwig <hch@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-11-17 23:30:30 +00:00
next = idr_get_cursor(&pid_ns->idr) - 1;
tmp.data = &next;
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
if (!ret && write)
idr_set_cursor(&pid_ns->idr, next + 1);
return ret;
}
extern int pid_max;
static struct ctl_table pid_ns_ctl_table[] = {
{
.procname = "ns_last_pid",
.maxlen = sizeof(int),
.mode = 0666, /* permissions are checked in the handler */
.proc_handler = pid_ns_ctl_handler,
proc/sysctl: add shared variables for range check In the sysctl code the proc_dointvec_minmax() function is often used to validate the user supplied value between an allowed range. This function uses the extra1 and extra2 members from struct ctl_table as minimum and maximum allowed value. On sysctl handler declaration, in every source file there are some readonly variables containing just an integer which address is assigned to the extra1 and extra2 members, so the sysctl range is enforced. The special values 0, 1 and INT_MAX are very often used as range boundary, leading duplication of variables like zero=0, one=1, int_max=INT_MAX in different source files: $ git grep -E '\.extra[12].*&(zero|one|int_max)' |wc -l 248 Add a const int array containing the most commonly used values, some macros to refer more easily to the correct array member, and use them instead of creating a local one for every object file. This is the bloat-o-meter output comparing the old and new binary compiled with the default Fedora config: # scripts/bloat-o-meter -d vmlinux.o.old vmlinux.o add/remove: 2/2 grow/shrink: 0/2 up/down: 24/-188 (-164) Data old new delta sysctl_vals - 12 +12 __kstrtab_sysctl_vals - 12 +12 max 14 10 -4 int_max 16 - -16 one 68 - -68 zero 128 28 -100 Total: Before=20583249, After=20583085, chg -0.00% [mcroce@redhat.com: tipc: remove two unused variables] Link: http://lkml.kernel.org/r/20190530091952.4108-1-mcroce@redhat.com [akpm@linux-foundation.org: fix net/ipv6/sysctl_net_ipv6.c] [arnd@arndb.de: proc/sysctl: make firmware loader table conditional] Link: http://lkml.kernel.org/r/20190617130014.1713870-1-arnd@arndb.de [akpm@linux-foundation.org: fix fs/eventpoll.c] Link: http://lkml.kernel.org/r/20190430180111.10688-1-mcroce@redhat.com Signed-off-by: Matteo Croce <mcroce@redhat.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de> Acked-by: Kees Cook <keescook@chromium.org> Reviewed-by: Aaron Tomlin <atomlin@redhat.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-07-18 22:58:50 +00:00
.extra1 = SYSCTL_ZERO,
.extra2 = &pid_max,
},
{ }
};
static struct ctl_path kern_path[] = { { .procname = "kernel", }, { } };
#endif /* CONFIG_CHECKPOINT_RESTORE */
pidns: add reboot_pid_ns() to handle the reboot syscall In the case of a child pid namespace, rebooting the system does not really makes sense. When the pid namespace is used in conjunction with the other namespaces in order to create a linux container, the reboot syscall leads to some problems. A container can reboot the host. That can be fixed by dropping the sys_reboot capability but we are unable to correctly to poweroff/ halt/reboot a container and the container stays stuck at the shutdown time with the container's init process waiting indefinitively. After several attempts, no solution from userspace was found to reliabily handle the shutdown from a container. This patch propose to make the init process of the child pid namespace to exit with a signal status set to : SIGINT if the child pid namespace called "halt/poweroff" and SIGHUP if the child pid namespace called "reboot". When the reboot syscall is called and we are not in the initial pid namespace, we kill the pid namespace for "HALT", "POWEROFF", "RESTART", and "RESTART2". Otherwise we return EINVAL. Returning EINVAL is also an easy way to check if this feature is supported by the kernel when invoking another 'reboot' option like CAD. By this way the parent process of the child pid namespace knows if it rebooted or not and can take the right decision. Test case: ========== #include <alloca.h> #include <stdio.h> #include <sched.h> #include <unistd.h> #include <signal.h> #include <sys/reboot.h> #include <sys/types.h> #include <sys/wait.h> #include <linux/reboot.h> static int do_reboot(void *arg) { int *cmd = arg; if (reboot(*cmd)) printf("failed to reboot(%d): %m\n", *cmd); } int test_reboot(int cmd, int sig) { long stack_size = 4096; void *stack = alloca(stack_size) + stack_size; int status; pid_t ret; ret = clone(do_reboot, stack, CLONE_NEWPID | SIGCHLD, &cmd); if (ret < 0) { printf("failed to clone: %m\n"); return -1; } if (wait(&status) < 0) { printf("unexpected wait error: %m\n"); return -1; } if (!WIFSIGNALED(status)) { printf("child process exited but was not signaled\n"); return -1; } if (WTERMSIG(status) != sig) { printf("signal termination is not the one expected\n"); return -1; } return 0; } int main(int argc, char *argv[]) { int status; status = test_reboot(LINUX_REBOOT_CMD_RESTART, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_RESTART2, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART2) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_HALT, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_HALT) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_POWER_OFF, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_POWERR_OFF) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_CAD_ON, -1); if (status >= 0) { printf("reboot(LINUX_REBOOT_CMD_CAD_ON) should have failed\n"); return 1; } printf("reboot(LINUX_REBOOT_CMD_CAD_ON) has failed as expected\n"); return 0; } [akpm@linux-foundation.org: tweak and add comments] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr> Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Tested-by: Serge Hallyn <serge.hallyn@canonical.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-28 21:42:51 +00:00
int reboot_pid_ns(struct pid_namespace *pid_ns, int cmd)
{
if (pid_ns == &init_pid_ns)
return 0;
switch (cmd) {
case LINUX_REBOOT_CMD_RESTART2:
case LINUX_REBOOT_CMD_RESTART:
pid_ns->reboot = SIGHUP;
break;
case LINUX_REBOOT_CMD_POWER_OFF:
case LINUX_REBOOT_CMD_HALT:
pid_ns->reboot = SIGINT;
break;
default:
return -EINVAL;
}
read_lock(&tasklist_lock);
send_sig(SIGKILL, pid_ns->child_reaper, 1);
pidns: add reboot_pid_ns() to handle the reboot syscall In the case of a child pid namespace, rebooting the system does not really makes sense. When the pid namespace is used in conjunction with the other namespaces in order to create a linux container, the reboot syscall leads to some problems. A container can reboot the host. That can be fixed by dropping the sys_reboot capability but we are unable to correctly to poweroff/ halt/reboot a container and the container stays stuck at the shutdown time with the container's init process waiting indefinitively. After several attempts, no solution from userspace was found to reliabily handle the shutdown from a container. This patch propose to make the init process of the child pid namespace to exit with a signal status set to : SIGINT if the child pid namespace called "halt/poweroff" and SIGHUP if the child pid namespace called "reboot". When the reboot syscall is called and we are not in the initial pid namespace, we kill the pid namespace for "HALT", "POWEROFF", "RESTART", and "RESTART2". Otherwise we return EINVAL. Returning EINVAL is also an easy way to check if this feature is supported by the kernel when invoking another 'reboot' option like CAD. By this way the parent process of the child pid namespace knows if it rebooted or not and can take the right decision. Test case: ========== #include <alloca.h> #include <stdio.h> #include <sched.h> #include <unistd.h> #include <signal.h> #include <sys/reboot.h> #include <sys/types.h> #include <sys/wait.h> #include <linux/reboot.h> static int do_reboot(void *arg) { int *cmd = arg; if (reboot(*cmd)) printf("failed to reboot(%d): %m\n", *cmd); } int test_reboot(int cmd, int sig) { long stack_size = 4096; void *stack = alloca(stack_size) + stack_size; int status; pid_t ret; ret = clone(do_reboot, stack, CLONE_NEWPID | SIGCHLD, &cmd); if (ret < 0) { printf("failed to clone: %m\n"); return -1; } if (wait(&status) < 0) { printf("unexpected wait error: %m\n"); return -1; } if (!WIFSIGNALED(status)) { printf("child process exited but was not signaled\n"); return -1; } if (WTERMSIG(status) != sig) { printf("signal termination is not the one expected\n"); return -1; } return 0; } int main(int argc, char *argv[]) { int status; status = test_reboot(LINUX_REBOOT_CMD_RESTART, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_RESTART2, SIGHUP); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_RESTART2) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_HALT, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_HALT) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_POWER_OFF, SIGINT); if (status < 0) return 1; printf("reboot(LINUX_REBOOT_CMD_POWERR_OFF) succeed\n"); status = test_reboot(LINUX_REBOOT_CMD_CAD_ON, -1); if (status >= 0) { printf("reboot(LINUX_REBOOT_CMD_CAD_ON) should have failed\n"); return 1; } printf("reboot(LINUX_REBOOT_CMD_CAD_ON) has failed as expected\n"); return 0; } [akpm@linux-foundation.org: tweak and add comments] [akpm@linux-foundation.org: checkpatch fixes] Signed-off-by: Daniel Lezcano <daniel.lezcano@free.fr> Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Tested-by: Serge Hallyn <serge.hallyn@canonical.com> Reviewed-by: Oleg Nesterov <oleg@redhat.com> Cc: Michael Kerrisk <mtk.manpages@gmail.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-28 21:42:51 +00:00
read_unlock(&tasklist_lock);
do_exit(0);
/* Not reached */
return 0;
}
static inline struct pid_namespace *to_pid_ns(struct ns_common *ns)
{
return container_of(ns, struct pid_namespace, ns);
}
static struct ns_common *pidns_get(struct task_struct *task)
{
struct pid_namespace *ns;
rcu_read_lock();
ns = task_active_pid_ns(task);
if (ns)
get_pid_ns(ns);
rcu_read_unlock();
return ns ? &ns->ns : NULL;
}
static struct ns_common *pidns_for_children_get(struct task_struct *task)
{
struct pid_namespace *ns = NULL;
task_lock(task);
if (task->nsproxy) {
ns = task->nsproxy->pid_ns_for_children;
get_pid_ns(ns);
}
task_unlock(task);
if (ns) {
read_lock(&tasklist_lock);
if (!ns->child_reaper) {
put_pid_ns(ns);
ns = NULL;
}
read_unlock(&tasklist_lock);
}
return ns ? &ns->ns : NULL;
}
static void pidns_put(struct ns_common *ns)
{
put_pid_ns(to_pid_ns(ns));
}
static int pidns_install(struct nsproxy *nsproxy, struct ns_common *ns)
{
struct pid_namespace *active = task_active_pid_ns(current);
struct pid_namespace *ancestor, *new = to_pid_ns(ns);
if (!ns_capable(new->user_ns, CAP_SYS_ADMIN) ||
!ns_capable(current_user_ns(), CAP_SYS_ADMIN))
return -EPERM;
/*
* Only allow entering the current active pid namespace
* or a child of the current active pid namespace.
*
* This is required for fork to return a usable pid value and
* this maintains the property that processes and their
* children can not escape their current pid namespace.
*/
if (new->level < active->level)
return -EINVAL;
ancestor = new;
while (ancestor->level > active->level)
ancestor = ancestor->parent;
if (ancestor != active)
return -EINVAL;
put_pid_ns(nsproxy->pid_ns_for_children);
nsproxy->pid_ns_for_children = get_pid_ns(new);
return 0;
}
static struct ns_common *pidns_get_parent(struct ns_common *ns)
{
struct pid_namespace *active = task_active_pid_ns(current);
struct pid_namespace *pid_ns, *p;
/* See if the parent is in the current namespace */
pid_ns = p = to_pid_ns(ns)->parent;
for (;;) {
if (!p)
return ERR_PTR(-EPERM);
if (p == active)
break;
p = p->parent;
}
return &get_pid_ns(pid_ns)->ns;
}
static struct user_namespace *pidns_owner(struct ns_common *ns)
{
return to_pid_ns(ns)->user_ns;
}
const struct proc_ns_operations pidns_operations = {
.name = "pid",
.type = CLONE_NEWPID,
.get = pidns_get,
.put = pidns_put,
.install = pidns_install,
.owner = pidns_owner,
.get_parent = pidns_get_parent,
};
const struct proc_ns_operations pidns_for_children_operations = {
.name = "pid_for_children",
.real_ns_name = "pid",
.type = CLONE_NEWPID,
.get = pidns_for_children_get,
.put = pidns_put,
.install = pidns_install,
.owner = pidns_owner,
.get_parent = pidns_get_parent,
};
static __init int pid_namespaces_init(void)
{
pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
#ifdef CONFIG_CHECKPOINT_RESTORE
register_sysctl_paths(kern_path, pid_ns_ctl_table);
#endif
return 0;
}
__initcall(pid_namespaces_init);