linux/kernel/user.c

266 lines
6.3 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* The "user cache".
*
* (C) Copyright 1991-2000 Linus Torvalds
*
* We have a per-user structure to keep track of how many
* processes, files etc the user has claimed, in order to be
* able to have per-user limits for system resources.
*/
#include <linux/init.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/bitops.h>
#include <linux/key.h>
#include <linux/sched/user.h>
#include <linux/interrupt.h>
#include <linux/export.h>
#include <linux/user_namespace.h>
binfmt_misc: enable sandboxed mounts Enable unprivileged sandboxes to create their own binfmt_misc mounts. This is based on Laurent's work in [1] but has been significantly reworked to fix various issues we identified in earlier versions. While binfmt_misc can currently only be mounted in the initial user namespace, binary types registered in this binfmt_misc instance are available to all sandboxes (Either by having them installed in the sandbox or by registering the binary type with the F flag causing the interpreter to be opened right away). So binfmt_misc binary types are already delegated to sandboxes implicitly. However, while a sandbox has access to all registered binary types in binfmt_misc a sandbox cannot currently register its own binary types in binfmt_misc. This has prevented various use-cases some of which were already outlined in [1] but we have a range of issues associated with this (cf. [3]-[5] below which are just a small sample). Extend binfmt_misc to be mountable in non-initial user namespaces. Similar to other filesystem such as nfsd, mqueue, and sunrpc we use keyed superblock management. The key determines whether we need to create a new superblock or can reuse an already existing one. We use the user namespace of the mount as key. This means a new binfmt_misc superblock is created once per user namespace creation. Subsequent mounts of binfmt_misc in the same user namespace will mount the same binfmt_misc instance. We explicitly do not create a new binfmt_misc superblock on every binfmt_misc mount as the semantics for load_misc_binary() line up with the keying model. This also allows us to retrieve the relevant binfmt_misc instance based on the caller's user namespace which can be done in a simple (bounded to 32 levels) loop. Similar to the current binfmt_misc semantics allowing access to the binary types in the initial binfmt_misc instance we do allow sandboxes access to their parent's binfmt_misc mounts if they do not have created a separate binfmt_misc instance. Overall, this will unblock the use-cases mentioned below and in general will also allow to support and harden execution of another architecture's binaries in tight sandboxes. For instance, using the unshare binary it possible to start a chroot of another architecture and configure the binfmt_misc interpreter without being root to run the binaries in this chroot and without requiring the host to modify its binary type handlers. Henning had already posted a few experiments in the cover letter at [1]. But here's an additional example where an unprivileged container registers qemu-user-static binary handlers for various binary types in its separate binfmt_misc mount and is then seamlessly able to start containers with a different architecture without affecting the host: root [lxc monitor] /var/snap/lxd/common/lxd/containers f1 1000000 \_ /sbin/init 1000000 \_ /lib/systemd/systemd-journald 1000000 \_ /lib/systemd/systemd-udevd 1000100 \_ /lib/systemd/systemd-networkd 1000101 \_ /lib/systemd/systemd-resolved 1000000 \_ /usr/sbin/cron -f 1000103 \_ /usr/bin/dbus-daemon --system --address=systemd: --nofork --nopidfile --systemd-activation --syslog-only 1000000 \_ /usr/bin/python3 /usr/bin/networkd-dispatcher --run-startup-triggers 1000104 \_ /usr/sbin/rsyslogd -n -iNONE 1000000 \_ /lib/systemd/systemd-logind 1000000 \_ /sbin/agetty -o -p -- \u --noclear --keep-baud console 115200,38400,9600 vt220 1000107 \_ dnsmasq --conf-file=/dev/null -u lxc-dnsmasq --strict-order --bind-interfaces --pid-file=/run/lxc/dnsmasq.pid --liste 1000000 \_ [lxc monitor] /var/lib/lxc f1-s390x 1100000 \_ /usr/bin/qemu-s390x-static /sbin/init 1100000 \_ /usr/bin/qemu-s390x-static /lib/systemd/systemd-journald 1100000 \_ /usr/bin/qemu-s390x-static /usr/sbin/cron -f 1100103 \_ /usr/bin/qemu-s390x-static /usr/bin/dbus-daemon --system --address=systemd: --nofork --nopidfile --systemd-ac 1100000 \_ /usr/bin/qemu-s390x-static /usr/bin/python3 /usr/bin/networkd-dispatcher --run-startup-triggers 1100104 \_ /usr/bin/qemu-s390x-static /usr/sbin/rsyslogd -n -iNONE 1100000 \_ /usr/bin/qemu-s390x-static /lib/systemd/systemd-logind 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud console 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud pts/0 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud pts/1 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud pts/2 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud pts/3 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /lib/systemd/systemd-udevd [1]: https://lore.kernel.org/all/20191216091220.465626-1-laurent@vivier.eu [2]: https://discuss.linuxcontainers.org/t/binfmt-misc-permission-denied [3]: https://discuss.linuxcontainers.org/t/lxd-binfmt-support-for-qemu-static-interpreters [4]: https://discuss.linuxcontainers.org/t/3-1-0-binfmt-support-service-in-unprivileged-guest-requires-write-access-on-hosts-proc-sys-fs-binfmt-misc [5]: https://discuss.linuxcontainers.org/t/qemu-user-static-not-working-4-11 Link: https://lore.kernel.org/r/20191216091220.465626-2-laurent@vivier.eu (origin) Link: https://lore.kernel.org/r/20211028103114.2849140-2-brauner@kernel.org (v1) Cc: Sargun Dhillon <sargun@sargun.me> Cc: Serge Hallyn <serge@hallyn.com> Cc: Jann Horn <jannh@google.com> Cc: Henning Schild <henning.schild@siemens.com> Cc: Andrei Vagin <avagin@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Laurent Vivier <laurent@vivier.eu> Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Laurent Vivier <laurent@vivier.eu> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Kees Cook <keescook@chromium.org> --- /* v2 */ - Serge Hallyn <serge@hallyn.com>: - Use GFP_KERNEL_ACCOUNT for userspace triggered allocations when a new binary type handler is registered. - Christian Brauner <christian.brauner@ubuntu.com>: - Switch authorship to me. I refused to do that earlier even though Laurent said I should do so because I think it's genuinely bad form. But by now I have changed so many things that it'd be unfair to blame Laurent for any potential bugs in here. - Add more comments that explain what's going on. - Rename functions while changing them to better reflect what they are doing to make the code easier to understand. - In the first version when a specific binary type handler was removed either through a write to the entry's file or all binary type handlers were removed by a write to the binfmt_misc mount's status file all cleanup work happened during inode eviction. That includes removal of the relevant entries from entry list. While that works fine I disliked that model after thinking about it for a bit. Because it means that there was a window were someone has already removed a or all binary handlers but they could still be safely reached from load_misc_binary() when it has managed to take the read_lock() on the entries list while inode eviction was already happening. Again, that perfectly benign but it's cleaner to remove the binary handler from the list immediately meaning that ones the write to then entry's file or the binfmt_misc status file returns the binary type cannot be executed anymore. That gives stronger guarantees to the user.
2021-10-28 10:31:14 +00:00
#include <linux/binfmts.h>
#include <linux/proc_ns.h>
binfmt_misc: enable sandboxed mounts Enable unprivileged sandboxes to create their own binfmt_misc mounts. This is based on Laurent's work in [1] but has been significantly reworked to fix various issues we identified in earlier versions. While binfmt_misc can currently only be mounted in the initial user namespace, binary types registered in this binfmt_misc instance are available to all sandboxes (Either by having them installed in the sandbox or by registering the binary type with the F flag causing the interpreter to be opened right away). So binfmt_misc binary types are already delegated to sandboxes implicitly. However, while a sandbox has access to all registered binary types in binfmt_misc a sandbox cannot currently register its own binary types in binfmt_misc. This has prevented various use-cases some of which were already outlined in [1] but we have a range of issues associated with this (cf. [3]-[5] below which are just a small sample). Extend binfmt_misc to be mountable in non-initial user namespaces. Similar to other filesystem such as nfsd, mqueue, and sunrpc we use keyed superblock management. The key determines whether we need to create a new superblock or can reuse an already existing one. We use the user namespace of the mount as key. This means a new binfmt_misc superblock is created once per user namespace creation. Subsequent mounts of binfmt_misc in the same user namespace will mount the same binfmt_misc instance. We explicitly do not create a new binfmt_misc superblock on every binfmt_misc mount as the semantics for load_misc_binary() line up with the keying model. This also allows us to retrieve the relevant binfmt_misc instance based on the caller's user namespace which can be done in a simple (bounded to 32 levels) loop. Similar to the current binfmt_misc semantics allowing access to the binary types in the initial binfmt_misc instance we do allow sandboxes access to their parent's binfmt_misc mounts if they do not have created a separate binfmt_misc instance. Overall, this will unblock the use-cases mentioned below and in general will also allow to support and harden execution of another architecture's binaries in tight sandboxes. For instance, using the unshare binary it possible to start a chroot of another architecture and configure the binfmt_misc interpreter without being root to run the binaries in this chroot and without requiring the host to modify its binary type handlers. Henning had already posted a few experiments in the cover letter at [1]. But here's an additional example where an unprivileged container registers qemu-user-static binary handlers for various binary types in its separate binfmt_misc mount and is then seamlessly able to start containers with a different architecture without affecting the host: root [lxc monitor] /var/snap/lxd/common/lxd/containers f1 1000000 \_ /sbin/init 1000000 \_ /lib/systemd/systemd-journald 1000000 \_ /lib/systemd/systemd-udevd 1000100 \_ /lib/systemd/systemd-networkd 1000101 \_ /lib/systemd/systemd-resolved 1000000 \_ /usr/sbin/cron -f 1000103 \_ /usr/bin/dbus-daemon --system --address=systemd: --nofork --nopidfile --systemd-activation --syslog-only 1000000 \_ /usr/bin/python3 /usr/bin/networkd-dispatcher --run-startup-triggers 1000104 \_ /usr/sbin/rsyslogd -n -iNONE 1000000 \_ /lib/systemd/systemd-logind 1000000 \_ /sbin/agetty -o -p -- \u --noclear --keep-baud console 115200,38400,9600 vt220 1000107 \_ dnsmasq --conf-file=/dev/null -u lxc-dnsmasq --strict-order --bind-interfaces --pid-file=/run/lxc/dnsmasq.pid --liste 1000000 \_ [lxc monitor] /var/lib/lxc f1-s390x 1100000 \_ /usr/bin/qemu-s390x-static /sbin/init 1100000 \_ /usr/bin/qemu-s390x-static /lib/systemd/systemd-journald 1100000 \_ /usr/bin/qemu-s390x-static /usr/sbin/cron -f 1100103 \_ /usr/bin/qemu-s390x-static /usr/bin/dbus-daemon --system --address=systemd: --nofork --nopidfile --systemd-ac 1100000 \_ /usr/bin/qemu-s390x-static /usr/bin/python3 /usr/bin/networkd-dispatcher --run-startup-triggers 1100104 \_ /usr/bin/qemu-s390x-static /usr/sbin/rsyslogd -n -iNONE 1100000 \_ /usr/bin/qemu-s390x-static /lib/systemd/systemd-logind 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud console 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud pts/0 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud pts/1 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud pts/2 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud pts/3 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /lib/systemd/systemd-udevd [1]: https://lore.kernel.org/all/20191216091220.465626-1-laurent@vivier.eu [2]: https://discuss.linuxcontainers.org/t/binfmt-misc-permission-denied [3]: https://discuss.linuxcontainers.org/t/lxd-binfmt-support-for-qemu-static-interpreters [4]: https://discuss.linuxcontainers.org/t/3-1-0-binfmt-support-service-in-unprivileged-guest-requires-write-access-on-hosts-proc-sys-fs-binfmt-misc [5]: https://discuss.linuxcontainers.org/t/qemu-user-static-not-working-4-11 Link: https://lore.kernel.org/r/20191216091220.465626-2-laurent@vivier.eu (origin) Link: https://lore.kernel.org/r/20211028103114.2849140-2-brauner@kernel.org (v1) Cc: Sargun Dhillon <sargun@sargun.me> Cc: Serge Hallyn <serge@hallyn.com> Cc: Jann Horn <jannh@google.com> Cc: Henning Schild <henning.schild@siemens.com> Cc: Andrei Vagin <avagin@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Laurent Vivier <laurent@vivier.eu> Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Laurent Vivier <laurent@vivier.eu> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Kees Cook <keescook@chromium.org> --- /* v2 */ - Serge Hallyn <serge@hallyn.com>: - Use GFP_KERNEL_ACCOUNT for userspace triggered allocations when a new binary type handler is registered. - Christian Brauner <christian.brauner@ubuntu.com>: - Switch authorship to me. I refused to do that earlier even though Laurent said I should do so because I think it's genuinely bad form. But by now I have changed so many things that it'd be unfair to blame Laurent for any potential bugs in here. - Add more comments that explain what's going on. - Rename functions while changing them to better reflect what they are doing to make the code easier to understand. - In the first version when a specific binary type handler was removed either through a write to the entry's file or all binary type handlers were removed by a write to the binfmt_misc mount's status file all cleanup work happened during inode eviction. That includes removal of the relevant entries from entry list. While that works fine I disliked that model after thinking about it for a bit. Because it means that there was a window were someone has already removed a or all binary handlers but they could still be safely reached from load_misc_binary() when it has managed to take the read_lock() on the entries list while inode eviction was already happening. Again, that perfectly benign but it's cleaner to remove the binary handler from the list immediately meaning that ones the write to then entry's file or the binfmt_misc status file returns the binary type cannot be executed anymore. That gives stronger guarantees to the user.
2021-10-28 10:31:14 +00:00
#if IS_ENABLED(CONFIG_BINFMT_MISC)
struct binfmt_misc init_binfmt_misc = {
.entries = LIST_HEAD_INIT(init_binfmt_misc.entries),
.enabled = true,
.entries_lock = __RW_LOCK_UNLOCKED(init_binfmt_misc.entries_lock),
};
EXPORT_SYMBOL_GPL(init_binfmt_misc);
#endif
userns: add a user_namespace as creator/owner of uts_namespace The expected course of development for user namespaces targeted capabilities is laid out at https://wiki.ubuntu.com/UserNamespace. Goals: - Make it safe for an unprivileged user to unshare namespaces. They will be privileged with respect to the new namespace, but this should only include resources which the unprivileged user already owns. - Provide separate limits and accounting for userids in different namespaces. Status: Currently (as of 2.6.38) you can clone with the CLONE_NEWUSER flag to get a new user namespace if you have the CAP_SYS_ADMIN, CAP_SETUID, and CAP_SETGID capabilities. What this gets you is a whole new set of userids, meaning that user 500 will have a different 'struct user' in your namespace than in other namespaces. So any accounting information stored in struct user will be unique to your namespace. However, throughout the kernel there are checks which - simply check for a capability. Since root in a child namespace has all capabilities, this means that a child namespace is not constrained. - simply compare uid1 == uid2. Since these are the integer uids, uid 500 in namespace 1 will be said to be equal to uid 500 in namespace 2. As a result, the lxc implementation at lxc.sf.net does not use user namespaces. This is actually helpful because it leaves us free to develop user namespaces in such a way that, for some time, user namespaces may be unuseful. Bugs aside, this patchset is supposed to not at all affect systems which are not actively using user namespaces, and only restrict what tasks in child user namespace can do. They begin to limit privilege to a user namespace, so that root in a container cannot kill or ptrace tasks in the parent user namespace, and can only get world access rights to files. Since all files currently belong to the initila user namespace, that means that child user namespaces can only get world access rights to *all* files. While this temporarily makes user namespaces bad for system containers, it starts to get useful for some sandboxing. I've run the 'runltplite.sh' with and without this patchset and found no difference. This patch: copy_process() handles CLONE_NEWUSER before the rest of the namespaces. So in the case of clone(CLONE_NEWUSER|CLONE_NEWUTS) the new uts namespace will have the new user namespace as its owner. That is what we want, since we want root in that new userns to be able to have privilege over it. Changelog: Feb 15: don't set uts_ns->user_ns if we didn't create a new uts_ns. Feb 23: Move extern init_user_ns declaration from init/version.c to utsname.h. Signed-off-by: Serge E. Hallyn <serge.hallyn@canonical.com> Acked-by: "Eric W. Biederman" <ebiederm@xmission.com> Acked-by: Daniel Lezcano <daniel.lezcano@free.fr> Acked-by: David Howells <dhowells@redhat.com> Cc: James Morris <jmorris@namei.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 23:43:16 +00:00
/*
* userns count is 1 for root user, 1 for init_uts_ns,
* and 1 for... ?
*/
struct user_namespace init_user_ns = {
userns: Rework the user_namespace adding uid/gid mapping support - Convert the old uid mapping functions into compatibility wrappers - Add a uid/gid mapping layer from user space uid and gids to kernel internal uids and gids that is extent based for simplicty and speed. * Working with number space after mapping uids/gids into their kernel internal version adds only mapping complexity over what we have today, leaving the kernel code easy to understand and test. - Add proc files /proc/self/uid_map /proc/self/gid_map These files display the mapping and allow a mapping to be added if a mapping does not exist. - Allow entering the user namespace without a uid or gid mapping. Since we are starting with an existing user our uids and gids still have global mappings so are still valid and useful they just don't have local mappings. The requirement for things to work are global uid and gid so it is odd but perfectly fine not to have a local uid and gid mapping. Not requiring global uid and gid mappings greatly simplifies the logic of setting up the uid and gid mappings by allowing the mappings to be set after the namespace is created which makes the slight weirdness worth it. - Make the mappings in the initial user namespace to the global uid/gid space explicit. Today it is an identity mapping but in the future we may want to twist this for debugging, similar to what we do with jiffies. - Document the memory ordering requirements of setting the uid and gid mappings. We only allow the mappings to be set once and there are no pointers involved so the requirments are trivial but a little atypical. Performance: In this scheme for the permission checks the performance is expected to stay the same as the actuall machine instructions should remain the same. The worst case I could think of is ls -l on a large directory where all of the stat results need to be translated with from kuids and kgids to uids and gids. So I benchmarked that case on my laptop with a dual core hyperthread Intel i5-2520M cpu with 3M of cpu cache. My benchmark consisted of going to single user mode where nothing else was running. On an ext4 filesystem opening 1,000,000 files and looping through all of the files 1000 times and calling fstat on the individuals files. This was to ensure I was benchmarking stat times where the inodes were in the kernels cache, but the inode values were not in the processors cache. My results: v3.4-rc1: ~= 156ns (unmodified v3.4-rc1 with user namespace support disabled) v3.4-rc1-userns-: ~= 155ns (v3.4-rc1 with my user namespace patches and user namespace support disabled) v3.4-rc1-userns+: ~= 164ns (v3.4-rc1 with my user namespace patches and user namespace support enabled) All of the configurations ran in roughly 120ns when I performed tests that ran in the cpu cache. So in summary the performance impact is: 1ns improvement in the worst case with user namespace support compiled out. 8ns aka 5% slowdown in the worst case with user namespace support compiled in. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2011-11-17 08:11:58 +00:00
.uid_map = {
.nr_extents = 1,
{
.extent[0] = {
.first = 0,
.lower_first = 0,
.count = 4294967295U,
},
userns: Rework the user_namespace adding uid/gid mapping support - Convert the old uid mapping functions into compatibility wrappers - Add a uid/gid mapping layer from user space uid and gids to kernel internal uids and gids that is extent based for simplicty and speed. * Working with number space after mapping uids/gids into their kernel internal version adds only mapping complexity over what we have today, leaving the kernel code easy to understand and test. - Add proc files /proc/self/uid_map /proc/self/gid_map These files display the mapping and allow a mapping to be added if a mapping does not exist. - Allow entering the user namespace without a uid or gid mapping. Since we are starting with an existing user our uids and gids still have global mappings so are still valid and useful they just don't have local mappings. The requirement for things to work are global uid and gid so it is odd but perfectly fine not to have a local uid and gid mapping. Not requiring global uid and gid mappings greatly simplifies the logic of setting up the uid and gid mappings by allowing the mappings to be set after the namespace is created which makes the slight weirdness worth it. - Make the mappings in the initial user namespace to the global uid/gid space explicit. Today it is an identity mapping but in the future we may want to twist this for debugging, similar to what we do with jiffies. - Document the memory ordering requirements of setting the uid and gid mappings. We only allow the mappings to be set once and there are no pointers involved so the requirments are trivial but a little atypical. Performance: In this scheme for the permission checks the performance is expected to stay the same as the actuall machine instructions should remain the same. The worst case I could think of is ls -l on a large directory where all of the stat results need to be translated with from kuids and kgids to uids and gids. So I benchmarked that case on my laptop with a dual core hyperthread Intel i5-2520M cpu with 3M of cpu cache. My benchmark consisted of going to single user mode where nothing else was running. On an ext4 filesystem opening 1,000,000 files and looping through all of the files 1000 times and calling fstat on the individuals files. This was to ensure I was benchmarking stat times where the inodes were in the kernels cache, but the inode values were not in the processors cache. My results: v3.4-rc1: ~= 156ns (unmodified v3.4-rc1 with user namespace support disabled) v3.4-rc1-userns-: ~= 155ns (v3.4-rc1 with my user namespace patches and user namespace support disabled) v3.4-rc1-userns+: ~= 164ns (v3.4-rc1 with my user namespace patches and user namespace support enabled) All of the configurations ran in roughly 120ns when I performed tests that ran in the cpu cache. So in summary the performance impact is: 1ns improvement in the worst case with user namespace support compiled out. 8ns aka 5% slowdown in the worst case with user namespace support compiled in. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2011-11-17 08:11:58 +00:00
},
},
.gid_map = {
.nr_extents = 1,
{
.extent[0] = {
.first = 0,
.lower_first = 0,
.count = 4294967295U,
},
userns: Rework the user_namespace adding uid/gid mapping support - Convert the old uid mapping functions into compatibility wrappers - Add a uid/gid mapping layer from user space uid and gids to kernel internal uids and gids that is extent based for simplicty and speed. * Working with number space after mapping uids/gids into their kernel internal version adds only mapping complexity over what we have today, leaving the kernel code easy to understand and test. - Add proc files /proc/self/uid_map /proc/self/gid_map These files display the mapping and allow a mapping to be added if a mapping does not exist. - Allow entering the user namespace without a uid or gid mapping. Since we are starting with an existing user our uids and gids still have global mappings so are still valid and useful they just don't have local mappings. The requirement for things to work are global uid and gid so it is odd but perfectly fine not to have a local uid and gid mapping. Not requiring global uid and gid mappings greatly simplifies the logic of setting up the uid and gid mappings by allowing the mappings to be set after the namespace is created which makes the slight weirdness worth it. - Make the mappings in the initial user namespace to the global uid/gid space explicit. Today it is an identity mapping but in the future we may want to twist this for debugging, similar to what we do with jiffies. - Document the memory ordering requirements of setting the uid and gid mappings. We only allow the mappings to be set once and there are no pointers involved so the requirments are trivial but a little atypical. Performance: In this scheme for the permission checks the performance is expected to stay the same as the actuall machine instructions should remain the same. The worst case I could think of is ls -l on a large directory where all of the stat results need to be translated with from kuids and kgids to uids and gids. So I benchmarked that case on my laptop with a dual core hyperthread Intel i5-2520M cpu with 3M of cpu cache. My benchmark consisted of going to single user mode where nothing else was running. On an ext4 filesystem opening 1,000,000 files and looping through all of the files 1000 times and calling fstat on the individuals files. This was to ensure I was benchmarking stat times where the inodes were in the kernels cache, but the inode values were not in the processors cache. My results: v3.4-rc1: ~= 156ns (unmodified v3.4-rc1 with user namespace support disabled) v3.4-rc1-userns-: ~= 155ns (v3.4-rc1 with my user namespace patches and user namespace support disabled) v3.4-rc1-userns+: ~= 164ns (v3.4-rc1 with my user namespace patches and user namespace support enabled) All of the configurations ran in roughly 120ns when I performed tests that ran in the cpu cache. So in summary the performance impact is: 1ns improvement in the worst case with user namespace support compiled out. 8ns aka 5% slowdown in the worst case with user namespace support compiled in. Acked-by: Serge Hallyn <serge.hallyn@canonical.com> Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2011-11-17 08:11:58 +00:00
},
},
.projid_map = {
.nr_extents = 1,
{
.extent[0] = {
.first = 0,
.lower_first = 0,
.count = 4294967295U,
},
},
},
user: Use generic ns_common::count Switch over user namespaces to use the newly introduced common lifetime counter. Currently every namespace type has its own lifetime counter which is stored in the specific namespace struct. The lifetime counters are used identically for all namespaces types. Namespaces may of course have additional unrelated counters and these are not altered. This introduces a common lifetime counter into struct ns_common. The ns_common struct encompasses information that all namespaces share. That should include the lifetime counter since its common for all of them. It also allows us to unify the type of the counters across all namespaces. Most of them use refcount_t but one uses atomic_t and at least one uses kref. Especially the last one doesn't make much sense since it's just a wrapper around refcount_t since 2016 and actually complicates cleanup operations by having to use container_of() to cast the correct namespace struct out of struct ns_common. Having the lifetime counter for the namespaces in one place reduces maintenance cost. Not just because after switching all namespaces over we will have removed more code than we added but also because the logic is more easily understandable and we indicate to the user that the basic lifetime requirements for all namespaces are currently identical. Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com> Reviewed-by: Kees Cook <keescook@chromium.org> Acked-by: Christian Brauner <christian.brauner@ubuntu.com> Link: https://lore.kernel.org/r/159644979754.604812.601625186726406922.stgit@localhost.localdomain Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>
2020-08-03 10:16:37 +00:00
.ns.count = REFCOUNT_INIT(3),
.owner = GLOBAL_ROOT_UID,
.group = GLOBAL_ROOT_GID,
.ns.inum = PROC_USER_INIT_INO,
#ifdef CONFIG_USER_NS
.ns.ops = &userns_operations,
#endif
2014-12-02 18:27:26 +00:00
.flags = USERNS_INIT_FLAGS,
#ifdef CONFIG_KEYS
.keyring_name_list = LIST_HEAD_INIT(init_user_ns.keyring_name_list),
.keyring_sem = __RWSEM_INITIALIZER(init_user_ns.keyring_sem),
KEYS: Add per-user_namespace registers for persistent per-UID kerberos caches Add support for per-user_namespace registers of persistent per-UID kerberos caches held within the kernel. This allows the kerberos cache to be retained beyond the life of all a user's processes so that the user's cron jobs can work. The kerberos cache is envisioned as a keyring/key tree looking something like: struct user_namespace \___ .krb_cache keyring - The register \___ _krb.0 keyring - Root's Kerberos cache \___ _krb.5000 keyring - User 5000's Kerberos cache \___ _krb.5001 keyring - User 5001's Kerberos cache \___ tkt785 big_key - A ccache blob \___ tkt12345 big_key - Another ccache blob Or possibly: struct user_namespace \___ .krb_cache keyring - The register \___ _krb.0 keyring - Root's Kerberos cache \___ _krb.5000 keyring - User 5000's Kerberos cache \___ _krb.5001 keyring - User 5001's Kerberos cache \___ tkt785 keyring - A ccache \___ krbtgt/REDHAT.COM@REDHAT.COM big_key \___ http/REDHAT.COM@REDHAT.COM user \___ afs/REDHAT.COM@REDHAT.COM user \___ nfs/REDHAT.COM@REDHAT.COM user \___ krbtgt/KERNEL.ORG@KERNEL.ORG big_key \___ http/KERNEL.ORG@KERNEL.ORG big_key What goes into a particular Kerberos cache is entirely up to userspace. Kernel support is limited to giving you the Kerberos cache keyring that you want. The user asks for their Kerberos cache by: krb_cache = keyctl_get_krbcache(uid, dest_keyring); The uid is -1 or the user's own UID for the user's own cache or the uid of some other user's cache (requires CAP_SETUID). This permits rpc.gssd or whatever to mess with the cache. The cache returned is a keyring named "_krb.<uid>" that the possessor can read, search, clear, invalidate, unlink from and add links to. Active LSMs get a chance to rule on whether the caller is permitted to make a link. Each uid's cache keyring is created when it first accessed and is given a timeout that is extended each time this function is called so that the keyring goes away after a while. The timeout is configurable by sysctl but defaults to three days. Each user_namespace struct gets a lazily-created keyring that serves as the register. The cache keyrings are added to it. This means that standard key search and garbage collection facilities are available. The user_namespace struct's register goes away when it does and anything left in it is then automatically gc'd. Signed-off-by: David Howells <dhowells@redhat.com> Tested-by: Simo Sorce <simo@redhat.com> cc: Serge E. Hallyn <serge.hallyn@ubuntu.com> cc: Eric W. Biederman <ebiederm@xmission.com>
2013-09-24 09:35:19 +00:00
#endif
binfmt_misc: enable sandboxed mounts Enable unprivileged sandboxes to create their own binfmt_misc mounts. This is based on Laurent's work in [1] but has been significantly reworked to fix various issues we identified in earlier versions. While binfmt_misc can currently only be mounted in the initial user namespace, binary types registered in this binfmt_misc instance are available to all sandboxes (Either by having them installed in the sandbox or by registering the binary type with the F flag causing the interpreter to be opened right away). So binfmt_misc binary types are already delegated to sandboxes implicitly. However, while a sandbox has access to all registered binary types in binfmt_misc a sandbox cannot currently register its own binary types in binfmt_misc. This has prevented various use-cases some of which were already outlined in [1] but we have a range of issues associated with this (cf. [3]-[5] below which are just a small sample). Extend binfmt_misc to be mountable in non-initial user namespaces. Similar to other filesystem such as nfsd, mqueue, and sunrpc we use keyed superblock management. The key determines whether we need to create a new superblock or can reuse an already existing one. We use the user namespace of the mount as key. This means a new binfmt_misc superblock is created once per user namespace creation. Subsequent mounts of binfmt_misc in the same user namespace will mount the same binfmt_misc instance. We explicitly do not create a new binfmt_misc superblock on every binfmt_misc mount as the semantics for load_misc_binary() line up with the keying model. This also allows us to retrieve the relevant binfmt_misc instance based on the caller's user namespace which can be done in a simple (bounded to 32 levels) loop. Similar to the current binfmt_misc semantics allowing access to the binary types in the initial binfmt_misc instance we do allow sandboxes access to their parent's binfmt_misc mounts if they do not have created a separate binfmt_misc instance. Overall, this will unblock the use-cases mentioned below and in general will also allow to support and harden execution of another architecture's binaries in tight sandboxes. For instance, using the unshare binary it possible to start a chroot of another architecture and configure the binfmt_misc interpreter without being root to run the binaries in this chroot and without requiring the host to modify its binary type handlers. Henning had already posted a few experiments in the cover letter at [1]. But here's an additional example where an unprivileged container registers qemu-user-static binary handlers for various binary types in its separate binfmt_misc mount and is then seamlessly able to start containers with a different architecture without affecting the host: root [lxc monitor] /var/snap/lxd/common/lxd/containers f1 1000000 \_ /sbin/init 1000000 \_ /lib/systemd/systemd-journald 1000000 \_ /lib/systemd/systemd-udevd 1000100 \_ /lib/systemd/systemd-networkd 1000101 \_ /lib/systemd/systemd-resolved 1000000 \_ /usr/sbin/cron -f 1000103 \_ /usr/bin/dbus-daemon --system --address=systemd: --nofork --nopidfile --systemd-activation --syslog-only 1000000 \_ /usr/bin/python3 /usr/bin/networkd-dispatcher --run-startup-triggers 1000104 \_ /usr/sbin/rsyslogd -n -iNONE 1000000 \_ /lib/systemd/systemd-logind 1000000 \_ /sbin/agetty -o -p -- \u --noclear --keep-baud console 115200,38400,9600 vt220 1000107 \_ dnsmasq --conf-file=/dev/null -u lxc-dnsmasq --strict-order --bind-interfaces --pid-file=/run/lxc/dnsmasq.pid --liste 1000000 \_ [lxc monitor] /var/lib/lxc f1-s390x 1100000 \_ /usr/bin/qemu-s390x-static /sbin/init 1100000 \_ /usr/bin/qemu-s390x-static /lib/systemd/systemd-journald 1100000 \_ /usr/bin/qemu-s390x-static /usr/sbin/cron -f 1100103 \_ /usr/bin/qemu-s390x-static /usr/bin/dbus-daemon --system --address=systemd: --nofork --nopidfile --systemd-ac 1100000 \_ /usr/bin/qemu-s390x-static /usr/bin/python3 /usr/bin/networkd-dispatcher --run-startup-triggers 1100104 \_ /usr/bin/qemu-s390x-static /usr/sbin/rsyslogd -n -iNONE 1100000 \_ /usr/bin/qemu-s390x-static /lib/systemd/systemd-logind 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud console 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud pts/0 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud pts/1 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud pts/2 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /sbin/agetty -o -p -- \u --noclear --keep-baud pts/3 115200,38400,9600 vt220 1100000 \_ /usr/bin/qemu-s390x-static /lib/systemd/systemd-udevd [1]: https://lore.kernel.org/all/20191216091220.465626-1-laurent@vivier.eu [2]: https://discuss.linuxcontainers.org/t/binfmt-misc-permission-denied [3]: https://discuss.linuxcontainers.org/t/lxd-binfmt-support-for-qemu-static-interpreters [4]: https://discuss.linuxcontainers.org/t/3-1-0-binfmt-support-service-in-unprivileged-guest-requires-write-access-on-hosts-proc-sys-fs-binfmt-misc [5]: https://discuss.linuxcontainers.org/t/qemu-user-static-not-working-4-11 Link: https://lore.kernel.org/r/20191216091220.465626-2-laurent@vivier.eu (origin) Link: https://lore.kernel.org/r/20211028103114.2849140-2-brauner@kernel.org (v1) Cc: Sargun Dhillon <sargun@sargun.me> Cc: Serge Hallyn <serge@hallyn.com> Cc: Jann Horn <jannh@google.com> Cc: Henning Schild <henning.schild@siemens.com> Cc: Andrei Vagin <avagin@gmail.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Laurent Vivier <laurent@vivier.eu> Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Laurent Vivier <laurent@vivier.eu> Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com> Signed-off-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Kees Cook <keescook@chromium.org> --- /* v2 */ - Serge Hallyn <serge@hallyn.com>: - Use GFP_KERNEL_ACCOUNT for userspace triggered allocations when a new binary type handler is registered. - Christian Brauner <christian.brauner@ubuntu.com>: - Switch authorship to me. I refused to do that earlier even though Laurent said I should do so because I think it's genuinely bad form. But by now I have changed so many things that it'd be unfair to blame Laurent for any potential bugs in here. - Add more comments that explain what's going on. - Rename functions while changing them to better reflect what they are doing to make the code easier to understand. - In the first version when a specific binary type handler was removed either through a write to the entry's file or all binary type handlers were removed by a write to the binfmt_misc mount's status file all cleanup work happened during inode eviction. That includes removal of the relevant entries from entry list. While that works fine I disliked that model after thinking about it for a bit. Because it means that there was a window were someone has already removed a or all binary handlers but they could still be safely reached from load_misc_binary() when it has managed to take the read_lock() on the entries list while inode eviction was already happening. Again, that perfectly benign but it's cleaner to remove the binary handler from the list immediately meaning that ones the write to then entry's file or the binfmt_misc status file returns the binary type cannot be executed anymore. That gives stronger guarantees to the user.
2021-10-28 10:31:14 +00:00
#if IS_ENABLED(CONFIG_BINFMT_MISC)
.binfmt_misc = &init_binfmt_misc,
#endif
};
EXPORT_SYMBOL_GPL(init_user_ns);
/*
* UID task count cache, to get fast user lookup in "alloc_uid"
* when changing user ID's (ie setuid() and friends).
*/
#define UIDHASH_BITS (IS_ENABLED(CONFIG_BASE_SMALL) ? 3 : 7)
#define UIDHASH_SZ (1 << UIDHASH_BITS)
#define UIDHASH_MASK (UIDHASH_SZ - 1)
#define __uidhashfn(uid) (((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK)
#define uidhashentry(uid) (uidhash_table + __uidhashfn((__kuid_val(uid))))
static struct kmem_cache *uid_cachep;
static struct hlist_head uidhash_table[UIDHASH_SZ];
/*
* The uidhash_lock is mostly taken from process context, but it is
* occasionally also taken from softirq/tasklet context, when
* task-structs get RCU-freed. Hence all locking must be softirq-safe.
* But free_uid() is also called with local interrupts disabled, and running
* local_bh_enable() with local interrupts disabled is an error - we'll run
* softirq callbacks, and they can unconditionally enable interrupts, and
* the caller of free_uid() didn't expect that..
*/
static DEFINE_SPINLOCK(uidhash_lock);
/* root_user.__count is 1, for init task cred */
struct user_struct root_user = {
.__count = REFCOUNT_INIT(1),
.uid = GLOBAL_ROOT_UID,
.ratelimit = RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0),
};
/*
* These routines must be called with the uidhash spinlock held!
*/
static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent)
{
hlist_add_head(&up->uidhash_node, hashent);
}
static void uid_hash_remove(struct user_struct *up)
{
hlist_del_init(&up->uidhash_node);
}
static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent)
{
struct user_struct *user;
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 01:06:00 +00:00
hlist_for_each_entry(user, hashent, uidhash_node) {
if (uid_eq(user->uid, uid)) {
refcount_inc(&user->__count);
return user;
}
}
return NULL;
}
static int user_epoll_alloc(struct user_struct *up)
{
#ifdef CONFIG_EPOLL
return percpu_counter_init(&up->epoll_watches, 0, GFP_KERNEL);
#else
return 0;
#endif
}
static void user_epoll_free(struct user_struct *up)
{
#ifdef CONFIG_EPOLL
percpu_counter_destroy(&up->epoll_watches);
#endif
}
/* IRQs are disabled and uidhash_lock is held upon function entry.
* IRQ state (as stored in flags) is restored and uidhash_lock released
* upon function exit.
*/
User namespaces: set of cleanups (v2) The user_ns is moved from nsproxy to user_struct, so that a struct cred by itself is sufficient to determine access (which it otherwise would not be). Corresponding ecryptfs fixes (by David Howells) are here as well. Fix refcounting. The following rules now apply: 1. The task pins the user struct. 2. The user struct pins its user namespace. 3. The user namespace pins the struct user which created it. User namespaces are cloned during copy_creds(). Unsharing a new user_ns is no longer possible. (We could re-add that, but it'll cause code duplication and doesn't seem useful if PAM doesn't need to clone user namespaces). When a user namespace is created, its first user (uid 0) gets empty keyrings and a clean group_info. This incorporates a previous patch by David Howells. Here is his original patch description: >I suggest adding the attached incremental patch. It makes the following >changes: > > (1) Provides a current_user_ns() macro to wrap accesses to current's user > namespace. > > (2) Fixes eCryptFS. > > (3) Renames create_new_userns() to create_user_ns() to be more consistent > with the other associated functions and because the 'new' in the name is > superfluous. > > (4) Moves the argument and permission checks made for CLONE_NEWUSER to the > beginning of do_fork() so that they're done prior to making any attempts > at allocation. > > (5) Calls create_user_ns() after prepare_creds(), and gives it the new creds > to fill in rather than have it return the new root user. I don't imagine > the new root user being used for anything other than filling in a cred > struct. > > This also permits me to get rid of a get_uid() and a free_uid(), as the > reference the creds were holding on the old user_struct can just be > transferred to the new namespace's creator pointer. > > (6) Makes create_user_ns() reset the UIDs and GIDs of the creds under > preparation rather than doing it in copy_creds(). > >David >Signed-off-by: David Howells <dhowells@redhat.com> Changelog: Oct 20: integrate dhowells comments 1. leave thread_keyring alone 2. use current_user_ns() in set_user() Signed-off-by: Serge Hallyn <serue@us.ibm.com>
2008-10-15 21:38:45 +00:00
static void free_user(struct user_struct *up, unsigned long flags)
__releases(&uidhash_lock)
{
uid_hash_remove(up);
spin_unlock_irqrestore(&uidhash_lock, flags);
user_epoll_free(up);
kmem_cache_free(uid_cachep, up);
}
/*
* Locate the user_struct for the passed UID. If found, take a ref on it. The
* caller must undo that ref with free_uid().
*
* If the user_struct could not be found, return NULL.
*/
struct user_struct *find_user(kuid_t uid)
{
struct user_struct *ret;
unsigned long flags;
spin_lock_irqsave(&uidhash_lock, flags);
ret = uid_hash_find(uid, uidhashentry(uid));
spin_unlock_irqrestore(&uidhash_lock, flags);
return ret;
}
void free_uid(struct user_struct *up)
{
unsigned long flags;
if (!up)
return;
if (refcount_dec_and_lock_irqsave(&up->__count, &uidhash_lock, &flags))
free_user(up, flags);
}
EXPORT_SYMBOL_GPL(free_uid);
struct user_struct *alloc_uid(kuid_t uid)
{
struct hlist_head *hashent = uidhashentry(uid);
struct user_struct *up, *new;
spin_lock_irq(&uidhash_lock);
up = uid_hash_find(uid, hashent);
spin_unlock_irq(&uidhash_lock);
if (!up) {
new = kmem_cache_zalloc(uid_cachep, GFP_KERNEL);
if (!new)
return NULL;
new->uid = uid;
refcount_set(&new->__count, 1);
if (user_epoll_alloc(new)) {
kmem_cache_free(uid_cachep, new);
return NULL;
}
ratelimit_state_init(&new->ratelimit, HZ, 100);
ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE);
/*
* Before adding this, check whether we raced
* on adding the same user already..
*/
spin_lock_irq(&uidhash_lock);
up = uid_hash_find(uid, hashent);
if (up) {
user_epoll_free(new);
kmem_cache_free(uid_cachep, new);
} else {
uid_hash_insert(new, hashent);
up = new;
}
spin_unlock_irq(&uidhash_lock);
}
return up;
}
static int __init uid_cache_init(void)
{
int n;
uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct),
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
for(n = 0; n < UIDHASH_SZ; ++n)
INIT_HLIST_HEAD(uidhash_table + n);
if (user_epoll_alloc(&root_user))
panic("root_user epoll percpu counter alloc failed");
/* Insert the root user immediately (init already runs as root) */
spin_lock_irq(&uidhash_lock);
uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID));
spin_unlock_irq(&uidhash_lock);
return 0;
}
2014-04-03 21:48:35 +00:00
subsys_initcall(uid_cache_init);