Fix PID namespace persistence
PATCH 1/1 Fix PID namespace persistence
From: michael-dev <[email protected]>
After unshare(...) is called, /proc/self/ns/pid does not change.
Instead, only /proc/self/ns/pid_for_children is affected. So bind-mounting /proc/self/ns/pid results in the original namespace getting bind-mounted.
Fix this by instead bind-mounting ns/pid_for_children.
--- sys-utils/unshare.c | 66 ++++++++++++++++++++++++++------------------- 1 file changed, 38 insertions(+), 28 deletions(-)
sys-utils/unshare.c +38 -28
@@ -63,7 +63,7 @@ static struct namespace_file { { .type = CLONE_NEWIPC, .name = "ns/ipc" }, { .type = CLONE_NEWUTS, .name = "ns/uts" }, { .type = CLONE_NEWNET, .name = "ns/net" }, - { .type = CLONE_NEWPID, .name = "ns/pid" }, + { .type = CLONE_NEWPID, .name = "ns/pid_for_children" }, { .type = CLONE_NEWNS, .name = "ns/mnt" }, { .type = CLONE_NEWTIME, .name = "ns/time" }, { .name = NULL }
@@ -361,6 +361,7 @@ int main(int argc, char *argv[])const char *procmnt =NULL ;const char *newroot =NULL ;const char *newdir =NULL ; +pid_t pid_bind =0 ;pid_t pid =0 ;int fds[2 ];int status;
@@ -501,13 +502,37 @@ int main(int argc, char *argv[]) "unsharing of a time namespace (-t)"));if (npersists && (unshare_flags &CLONE_NEWNS )) -bind_ns_files_from_child (&pid, fds); +bind_ns_files_from_child (&pid_bind, fds);if (-1 ==unshare (unshare_flags))err (EXIT_FAILURE ,_ ("unshare failed" )); -if (npersists) { -if (pid && (unshare_flags &CLONE_NEWNS )) { +if (force_boottime) +settime (boottime,CLOCK_BOOTTIME ); + +if (force_monotonic) +settime (monotonic,CLOCK_MONOTONIC ); + +if (forkit) { +// force child forking before mountspace binding +// so pid_for_children is populated + pid =fork (); + +switch (pid) { +case -1 : +err (EXIT_FAILURE ,_ ("fork failed" )); +case 0 :/* child */ +if (pid_bind && (unshare_flags &CLONE_NEWNS )) +close (fds[1 ]); +break ; +default :/* parent */ +break ; + } + } + +if (npersists && (pid || !forkit)) { +// run in parent +if (pid_bind && (unshare_flags &CLONE_NEWNS )) {int rc;char ch =PIPE_SYNC_BYTE ;
@@ -518,7 +543,7 @@ int main(int argc, char *argv[])/* wait for bind_ns_files_from_child() */ do { - rc = waitpid(pid, &status, 0); + rc = waitpid(pid_bind, &status, 0); if (rc < 0) { if (errno == EINTR) continue;
@@ -533,29 +558,14 @@ int main(int argc, char *argv[])bind_ns_files (getpid ()); } -if (force_boottime) -settime (boottime,CLOCK_BOOTTIME ); - -if (force_monotonic) -settime (monotonic,CLOCK_MONOTONIC ); - -if (forkit) { - pid =fork (); - -switch (pid) { -case -1 : -err (EXIT_FAILURE ,_ ("fork failed" )); -case 0 :/* child */ -break ; -default :/* parent */ -if (waitpid (pid, &status,0 ) ==-1 ) -err (EXIT_FAILURE ,_ ("waitpid failed" )); -if (WIFEXITED (status)) -return WEXITSTATUS (status); -else if (WIFSIGNALED (status)) -kill (getpid (),WTERMSIG (status)); -err (EXIT_FAILURE ,_ ("child exit failed" )); - } +if (pid) { +if (waitpid (pid, &status,0 ) ==-1 ) +err (EXIT_FAILURE ,_ ("waitpid failed" )); +if (WIFEXITED (status)) +return WEXITSTATUS (status); +else if (WIFSIGNALED (status)) +kill (getpid (),WTERMSIG (status)); +err (EXIT_FAILURE ,_ ("child exit failed" )); }if (kill_child_signo !=0 &&prctl (PR_SET_PDEATHSIG , kill_child_signo) <0 )
Signature · 1 line
2.17.1
Karel Zak
maintainerEric, can you review this unshare(8) patch? Please.
Karel
Quoted 124 lines · On Wed, Apr 15, 2020 at 11:16:53PM +0200, [email protected] wrote:
From: michael-dev <[email protected]>
After unshare(...) is called,
/proc/self/ns/piddoes not change.
Instead, only/proc/self/ns/pid_for_childrenis affected. So bind-mounting/proc/self/ns/pidresults in the original namespace getting bind-mounted.Fix this by instead bind-mounting ns/pid_for_children.
Signed-off-by Michael Braun <[email protected]>--- sys-utils/unshare.c | 66 ++++++++++++++++++++++++++------------------- 1 file changed, 38 insertions(+), 28 deletions(-)sys-utils/unshare.c +38
-28@@ -63,7 +63,7 @@ static struct namespace_file { { .type = CLONE_NEWIPC, .name = "ns/ipc" }, { .type = CLONE_NEWUTS, .name = "ns/uts" }, { .type = CLONE_NEWNET, .name = "ns/net" }, - { .type = CLONE_NEWPID, .name = "ns/pid" }, + { .type = CLONE_NEWPID, .name = "ns/pid_for_children" }, { .type = CLONE_NEWNS, .name = "ns/mnt" }, { .type = CLONE_NEWTIME, .name = "ns/time" }, { .name = NULL }@@ -361,6 +361,7 @@ int main(int argc, char *argv[])const char *procmnt =NULL ;const char *newroot =NULL ;const char *newdir =NULL ; +pid_t pid_bind =0 ;pid_t pid =0 ;int fds[2 ];int status;@@ -501,13 +502,37 @@ int main(int argc, char *argv[]) "unsharing of a time namespace (-t)"));if (npersists && (unshare_flags &CLONE_NEWNS )) -bind_ns_files_from_child (&pid, fds); +bind_ns_files_from_child (&pid_bind, fds);if (-1 ==unshare (unshare_flags))err (EXIT_FAILURE ,_ ("unshare failed" )); -if (npersists) { -if (pid && (unshare_flags &CLONE_NEWNS )) { +if (force_boottime) +settime (boottime,CLOCK_BOOTTIME ); + +if (force_monotonic) +settime (monotonic,CLOCK_MONOTONIC ); + +if (forkit) { +// force child forking before mountspace binding +// so pid_for_children is populated + pid =fork (); + +switch (pid) { +case -1 : +err (EXIT_FAILURE ,_ ("fork failed" )); +case 0 :/* child */ +if (pid_bind && (unshare_flags &CLONE_NEWNS )) +close (fds[1 ]); +break ; +default :/* parent */ +break ; + } + } + +if (npersists && (pid || !forkit)) { +// run in parent +if (pid_bind && (unshare_flags &CLONE_NEWNS )) {int rc;char ch =PIPE_SYNC_BYTE ;@@ -518,7 +543,7 @@ int main(int argc, char *argv[])/* wait for bind_ns_files_from_child() */ do { - rc = waitpid(pid, &status, 0); + rc = waitpid(pid_bind, &status, 0); if (rc < 0) { if (errno == EINTR) continue;@@ -533,29 +558,14 @@ int main(int argc, char *argv[])bind_ns_files (getpid ()); } -if (force_boottime) -settime (boottime,CLOCK_BOOTTIME ); - -if (force_monotonic) -settime (monotonic,CLOCK_MONOTONIC ); - -if (forkit) { - pid =fork (); - -switch (pid) { -case -1 : -err (EXIT_FAILURE ,_ ("fork failed" )); -case 0 :/* child */ -break ; -default :/* parent */ -if (waitpid (pid, &status,0 ) ==-1 ) -err (EXIT_FAILURE ,_ ("waitpid failed" )); -if (WIFEXITED (status)) -return WEXITSTATUS (status); -else if (WIFSIGNALED (status)) -kill (getpid (),WTERMSIG (status)); -err (EXIT_FAILURE ,_ ("child exit failed" )); - } +if (pid) { +if (waitpid (pid, &status,0 ) ==-1 ) +err (EXIT_FAILURE ,_ ("waitpid failed" )); +if (WIFEXITED (status)) +return WEXITSTATUS (status); +else if (WIFSIGNALED (status)) +kill (getpid (),WTERMSIG (status)); +err (EXIT_FAILURE ,_ ("child exit failed" )); }if (kill_child_signo !=0 &&prctl (PR_SET_PDEATHSIG , kill_child_signo) <0 )Signature · 1 line
2.17.1
Signature · 2 lines
Karel Zak <[email protected]> http://karelzak.blogspot.com
Quoted 6 lines · [email protected] writes:
From: michael-dev <[email protected]>
After unshare(...) is called,
/proc/self/ns/piddoes not change.
Instead, only/proc/self/ns/pid_for_childrenis affected. So bind-mounting/proc/self/ns/pidresults in the original namespace getting bind-mounted.Fix this by instead bind-mounting ns/pid_for_children.
Why all of the extra code motion and change?
Your description sounds like only the first hunk is necessary. Did something else get mixed into this change? Or are all of the hunks necessary?
Eric
Quoted 114 lines
Signed-off-by Michael Braun <[email protected]>--- sys-utils/unshare.c | 66 ++++++++++++++++++++++++++------------------- 1 file changed, 38 insertions(+), 28 deletions(-)sys-utils/unshare.c +38
-28@@ -63,7 +63,7 @@ static struct namespace_file { { .type = CLONE_NEWIPC, .name = "ns/ipc" }, { .type = CLONE_NEWUTS, .name = "ns/uts" }, { .type = CLONE_NEWNET, .name = "ns/net" }, - { .type = CLONE_NEWPID, .name = "ns/pid" }, + { .type = CLONE_NEWPID, .name = "ns/pid_for_children" }, { .type = CLONE_NEWNS, .name = "ns/mnt" }, { .type = CLONE_NEWTIME, .name = "ns/time" }, { .name = NULL }@@ -361,6 +361,7 @@ int main(int argc, char *argv[])const char *procmnt =NULL ;const char *newroot =NULL ;const char *newdir =NULL ; +pid_t pid_bind =0 ;pid_t pid =0 ;int fds[2 ];int status;@@ -501,13 +502,37 @@ int main(int argc, char *argv[]) "unsharing of a time namespace (-t)"));if (npersists && (unshare_flags &CLONE_NEWNS )) -bind_ns_files_from_child (&pid, fds); +bind_ns_files_from_child (&pid_bind, fds);if (-1 ==unshare (unshare_flags))err (EXIT_FAILURE ,_ ("unshare failed" )); -if (npersists) { -if (pid && (unshare_flags &CLONE_NEWNS )) { +if (force_boottime) +settime (boottime,CLOCK_BOOTTIME ); + +if (force_monotonic) +settime (monotonic,CLOCK_MONOTONIC ); + +if (forkit) { +// force child forking before mountspace binding +// so pid_for_children is populated + pid =fork (); + +switch (pid) { +case -1 : +err (EXIT_FAILURE ,_ ("fork failed" )); +case 0 :/* child */ +if (pid_bind && (unshare_flags &CLONE_NEWNS )) +close (fds[1 ]); +break ; +default :/* parent */ +break ; + } + } + +if (npersists && (pid || !forkit)) { +// run in parent +if (pid_bind && (unshare_flags &CLONE_NEWNS )) {int rc;char ch =PIPE_SYNC_BYTE ;@@ -518,7 +543,7 @@ int main(int argc, char *argv[])/* wait for bind_ns_files_from_child() */ do { - rc = waitpid(pid, &status, 0); + rc = waitpid(pid_bind, &status, 0); if (rc < 0) { if (errno == EINTR) continue;@@ -533,29 +558,14 @@ int main(int argc, char *argv[])bind_ns_files (getpid ()); } -if (force_boottime) -settime (boottime,CLOCK_BOOTTIME ); - -if (force_monotonic) -settime (monotonic,CLOCK_MONOTONIC ); - -if (forkit) { - pid =fork (); - -switch (pid) { -case -1 : -err (EXIT_FAILURE ,_ ("fork failed" )); -case 0 :/* child */ -break ; -default :/* parent */ -if (waitpid (pid, &status,0 ) ==-1 ) -err (EXIT_FAILURE ,_ ("waitpid failed" )); -if (WIFEXITED (status)) -return WEXITSTATUS (status); -else if (WIFSIGNALED (status)) -kill (getpid (),WTERMSIG (status)); -err (EXIT_FAILURE ,_ ("child exit failed" )); - } +if (pid) { +if (waitpid (pid, &status,0 ) ==-1 ) +err (EXIT_FAILURE ,_ ("waitpid failed" )); +if (WIFEXITED (status)) +return WEXITSTATUS (status); +else if (WIFSIGNALED (status)) +kill (getpid (),WTERMSIG (status)); +err (EXIT_FAILURE ,_ ("child exit failed" )); }if (kill_child_signo !=0 &&prctl (PR_SET_PDEATHSIG , kill_child_signo) <0 )
Am 16.04.2020 22:49, schrieb [email protected]:
Quoted 5 lines
Why all of the extra code motion and change?
Your description sounds like only the first hunk is necessary. Did something else get mixed into this change? Or are all of the hunks necessary?
Because after unsharing, pid_for_children is a dangling symlink.
So if (forkit) needs to be before /* wait for bind_ns_files_from_child() */.
Moving this results in an overlapping use of the pid variable, so that gets renamed.
Additionally, we cannot wait for the forkit child (bash) to exit before triggering and waiting for the bind-mounting child to bind-mount the persistent namespace. So forking and waiting for the forkit child (bash) needs to become splitted.
Regards,
Michael
Quoted 8 lines · michael-dev
Am 16.04.2020 22:49, schrieb [email protected]:
Quoted 5 lines
Why all of the extra code motion and change?
Your description sounds like only the first hunk is necessary. Did something else get mixed into this change? Or are all of the hunks necessary?
Quoted 9 lines
Because after unsharing,
pid_for_childrenis a dangling symlink. So if (forkit) needs to be before /* wait forbind_ns_files_from_child()*/.
Moving this results in an overlapping use of the pid variable, so that gets renamed.
Additionally, we cannot wait for the forkit child (bash) to exit before triggering and waiting for the bind-mounting child to bind-mount the persistent namespace. So forking and waiting for the forkit child (bash) needs to become splitted.
@Michael: I confim theproblem, and thanks for this fix.
@Zak: an analogous fix is required for time namespaces.
Cheers,
Michael
Signature · 3 lines
Michael Kerrisk Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/ Author of "The Linux Programming Interface", http://blog.man7.org/
Karel Zak
maintainerQuoted 19 lines · Michael Kerrisk
Quoted 8 lines · michael-dev
Am 16.04.2020 22:49, schrieb [email protected]:
Quoted 5 lines
Why all of the extra code motion and change?
Your description sounds like only the first hunk is necessary. Did something else get mixed into this change? Or are all of the hunks necessary?
Quoted 9 lines
Because after unsharing,
pid_for_childrenis a dangling symlink. So if (forkit) needs to be before /* wait forbind_ns_files_from_child()*/.
Moving this results in an overlapping use of the pid variable, so that gets renamed.
Additionally, we cannot wait for the forkit child (bash) to exit before triggering and waiting for the bind-mounting child to bind-mount the persistent namespace. So forking and waiting for the forkit child (bash) needs to become splitted.
Quoted 3 lines
@Michael: I confim theproblem, and thanks for this fix.
@Zak: an analogous fix is required for time namespaces.
OK, I'll play with it later this week. Sorry for the delay, I'm busy with other things.
Karel
Signature · 2 lines
Karel Zak <[email protected]> http://karelzak.blogspot.com
[I should have CCed Adrian, so that he is aware of the issue also, having added Time Namespaces; Adrian, for context, see
https://lore.kernel.org/util-linux/[email protected]/T/#t
]
Quoted 21 lines · Karel Zak
Quoted 19 lines · Michael Kerrisk
Quoted 17 lines · michael-dev
Am 16.04.2020 22:49, schrieb [email protected]:
Quoted 5 lines
Why all of the extra code motion and change?
Your description sounds like only the first hunk is necessary. Did something else get mixed into this change? Or are all of the hunks necessary?
Because after unsharing,
pid_for_childrenis a dangling symlink. So if (forkit) needs to be before /* wait forbind_ns_files_from_child()*/.
Moving this results in an overlapping use of the pid variable, so that gets renamed.
Additionally, we cannot wait for the forkit child (bash) to exit before triggering and waiting for the bind-mounting child to bind-mount the persistent namespace. So forking and waiting for the forkit child (bash) needs to become splitted.
Quoted 6 lines
Quoted 3 lines
@Michael: I confim theproblem, and thanks for this fix.
@Zak: an analogous fix is required for time namespaces.
OK, I'll play with it later this week. Sorry for the delay, I'm busy with other things.
Thanks, Karel!
Signature · 3 lines
Michael Kerrisk Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/ Linux/UNIX System Programming Training: http://man7.org/training/
Quoted 2 lines · On Wed, Apr 15, 2020 at 11:16:53PM +0200, [email protected] wrote:
sys-utils/unshare.c | 66 ++++++++++++++++++++++++++------------------- 1 file changed, 38 insertions(+), 28 deletions(-)
Applied. I did small changes to the patch, see:
https://github.com/karelzak/util-linux/commit/0d5260b66c5581c8a5855a5f49e298e48e8baf82
Quoted 1 line · Michael Kerrisk
@Zak: an analogous fix is required for time namespaces.
A have added ns/time_for_children to the commit.
Thanks guys!
Karel
Signature · 2 lines
Karel Zak <[email protected]> http://karelzak.blogspot.com