1
linux/ipc/util.h

195 lines
6.1 KiB
C
Raw Normal View History

/*
* linux/ipc/util.h
* Copyright (C) 1999 Christoph Rohland
*
* ipc helper functions (c) 1999 Manfred Spraul <manfred@colorfullife.com>
* namespaces support. 2006 OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
*/
#ifndef _IPC_UTIL_H
#define _IPC_UTIL_H
#include <linux/unistd.h>
#include <linux/err.h>
#define SEQ_MULTIPLIER (IPCMNI)
void sem_init(void);
void msg_init(void);
void shm_init(void);
namespaces: move the IPC namespace under IPC_NS option Currently the IPC namespace management code is spread over the ipc/*.c files. I moved this code into ipc/namespace.c file which is compiled out when needed. The linux/ipc_namespace.h file is used to store the prototypes of the functions in namespace.c and the stubs for NAMESPACES=n case. This is done so, because the stub for copy_ipc_namespace requires the knowledge of the CLONE_NEWIPC flag, which is in sched.h. But the linux/ipc.h file itself in included into many many .c files via the sys.h->sem.h sequence so adding the sched.h into it will make all these .c depend on sched.h which is not that good. On the other hand the knowledge about the namespaces stuff is required in 4 .c files only. Besides, this patch compiles out some auxiliary functions from ipc/sem.c, msg.c and shm.c files. It turned out that moving these functions into namespaces.c is not that easy because they use many other calls and macros from the original file. Moving them would make this patch complicated. On the other hand all these functions can be consolidated, so I will send a separate patch doing this a bit later. Signed-off-by: Pavel Emelyanov <xemul@openvz.org> Acked-by: Serge Hallyn <serue@us.ibm.com> Cc: Cedric Le Goater <clg@fr.ibm.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Herbert Poetzl <herbert@13thfloor.at> Cc: Kirill Korotaev <dev@sw.ru> Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 05:18:22 -07:00
struct ipc_namespace;
#ifdef CONFIG_POSIX_MQUEUE
namespaces: ipc namespaces: implement support for posix msqueues Implement multiple mounts of the mqueue file system, and link it to usage of CLONE_NEWIPC. Each ipc ns has a corresponding mqueuefs superblock. When a user does clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an internal mount of a new mqueuefs sb linked to the new ipc ns. When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the mqueuefs superblock. Posix message queues can be worked with both through the mq_* system calls (see mq_overview(7)), and through the VFS through the mqueue mount. Any usage of mq_open() and friends will work with the acting task's ipc namespace. Any actions through the VFS will work with the mqueuefs in which the file was created. So if a user doesn't remount mqueuefs after unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls /dev/mqueue". If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns, ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1) ipc_ns:1 will be freed, (2) it's superblock will live on until task b umounts the corresponding mqueuefs, and vfs actions will continue to succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to the deceased ipc_ns:1. To make this happen, we must protect the ipc reference count when a) a task exits and drops its ipcns->count, since it might be dropping it to 0 and freeing the ipcns b) a task accesses the ipcns through its mqueuefs interface, since it bumps the ipcns refcount and might race with the last task in the ipcns exiting. So the kref is changed to an atomic_t so we can use atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns through ns = mqueuefs_sb->s_fs_info is protected by the same lock. Signed-off-by: Cedric Le Goater <clg@fr.ibm.com> Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 19:01:10 -07:00
extern void mq_clear_sbinfo(struct ipc_namespace *ns);
extern void mq_put_mnt(struct ipc_namespace *ns);
#else
namespaces: ipc namespaces: implement support for posix msqueues Implement multiple mounts of the mqueue file system, and link it to usage of CLONE_NEWIPC. Each ipc ns has a corresponding mqueuefs superblock. When a user does clone(CLONE_NEWIPC) or unshare(CLONE_NEWIPC), the unshare will cause an internal mount of a new mqueuefs sb linked to the new ipc ns. When a user does 'mount -t mqueue mqueue /dev/mqueue', he mounts the mqueuefs superblock. Posix message queues can be worked with both through the mq_* system calls (see mq_overview(7)), and through the VFS through the mqueue mount. Any usage of mq_open() and friends will work with the acting task's ipc namespace. Any actions through the VFS will work with the mqueuefs in which the file was created. So if a user doesn't remount mqueuefs after unshare(CLONE_NEWIPC), mq_open("/ab") will not be reflected in "ls /dev/mqueue". If task a mounts mqueue for ipc_ns:1, then clones task b with a new ipcns, ipcns:2, and then task a is the last task in ipc_ns:1 to exit, then (1) ipc_ns:1 will be freed, (2) it's superblock will live on until task b umounts the corresponding mqueuefs, and vfs actions will continue to succeed, but (3) sb->s_fs_info will be NULL for the sb corresponding to the deceased ipc_ns:1. To make this happen, we must protect the ipc reference count when a) a task exits and drops its ipcns->count, since it might be dropping it to 0 and freeing the ipcns b) a task accesses the ipcns through its mqueuefs interface, since it bumps the ipcns refcount and might race with the last task in the ipcns exiting. So the kref is changed to an atomic_t so we can use atomic_dec_and_lock(&ns->count,mq_lock), and every access to the ipcns through ns = mqueuefs_sb->s_fs_info is protected by the same lock. Signed-off-by: Cedric Le Goater <clg@fr.ibm.com> Signed-off-by: Serge E. Hallyn <serue@us.ibm.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-06 19:01:10 -07:00
static inline void mq_clear_sbinfo(struct ipc_namespace *ns) { }
static inline void mq_put_mnt(struct ipc_namespace *ns) { }
#endif
#ifdef CONFIG_SYSVIPC
void sem_init_ns(struct ipc_namespace *ns);
void msg_init_ns(struct ipc_namespace *ns);
void shm_init_ns(struct ipc_namespace *ns);
void sem_exit_ns(struct ipc_namespace *ns);
void msg_exit_ns(struct ipc_namespace *ns);
void shm_exit_ns(struct ipc_namespace *ns);
#else
static inline void sem_init_ns(struct ipc_namespace *ns) { }
static inline void msg_init_ns(struct ipc_namespace *ns) { }
static inline void shm_init_ns(struct ipc_namespace *ns) { }
static inline void sem_exit_ns(struct ipc_namespace *ns) { }
static inline void msg_exit_ns(struct ipc_namespace *ns) { }
static inline void shm_exit_ns(struct ipc_namespace *ns) { }
#endif
/*
* Structure that holds the parameters needed by the ipc operations
* (see after)
*/
struct ipc_params {
key_t key;
int flg;
union {
size_t size; /* for shared memories */
int nsems; /* for semaphores */
} u; /* holds the getnew() specific param */
};
/*
* Structure that holds some ipc operations. This structure is used to unify
* the calls to sys_msgget(), sys_semget(), sys_shmget()
* . routine to call to create a new ipc object. Can be one of newque,
* newary, newseg
* . routine to call to check permissions for a new ipc object.
* Can be one of security_msg_associate, security_sem_associate,
* security_shm_associate
* . routine to call for an extra check if needed
*/
struct ipc_ops {
int (*getnew)(struct ipc_namespace *, struct ipc_params *);
int (*associate)(struct kern_ipc_perm *, int);
int (*more_checks)(struct kern_ipc_perm *, struct ipc_params *);
};
struct seq_file;
struct ipc_ids;
void ipc_init_ids(struct ipc_ids *);
#ifdef CONFIG_PROC_FS
void __init ipc_init_proc_interface(const char *path, const char *header,
int ids, int (*show)(struct seq_file *, void *));
#else
#define ipc_init_proc_interface(path, header, ids, show) do {} while (0)
#endif
#define IPC_SEM_IDS 0
#define IPC_MSG_IDS 1
#define IPC_SHM_IDS 2
#define ipcid_to_idx(id) ((id) % SEQ_MULTIPLIER)
#define ipcid_to_seqx(id) ((id) / SEQ_MULTIPLIER)
#define IPCID_SEQ_MAX min_t(int, INT_MAX/SEQ_MULTIPLIER, USHRT_MAX)
/* must be called with ids->rwsem acquired for writing */
int ipc_addid(struct ipc_ids *, struct kern_ipc_perm *, int);
/* must be called with ids->rwsem acquired for reading */
int ipc_get_maxid(struct ipc_ids *);
/* must be called with both locks acquired. */
void ipc_rmid(struct ipc_ids *, struct kern_ipc_perm *);
/* must be called with ipcp locked */
int ipcperms(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp, short flg);
/*
* For allocation that need to be freed by RCU.
* Objects are reference counted, they start with reference count 1.
* getref increases the refcount, the putref call that reduces the recount
* to 0 schedules the rcu destruction. Caller must guarantee locking.
*
* refcount is initialized by ipc_addid(), before that point call_rcu()
* must be used.
*/
int ipc_rcu_getref(struct kern_ipc_perm *ptr);
void ipc_rcu_putref(struct kern_ipc_perm *ptr,
void (*func)(struct rcu_head *head));
struct kern_ipc_perm *ipc_lock(struct ipc_ids *, int);
struct kern_ipc_perm *ipc_obtain_object_idr(struct ipc_ids *ids, int id);
void kernel_to_ipc64_perm(struct kern_ipc_perm *in, struct ipc64_perm *out);
void ipc64_perm_to_ipc_perm(struct ipc64_perm *in, struct ipc_perm *out);
int ipc_update_perm(struct ipc64_perm *in, struct kern_ipc_perm *out);
struct kern_ipc_perm *ipcctl_pre_down_nolock(struct ipc_namespace *ns,
struct ipc_ids *ids, int id, int cmd,
struct ipc64_perm *perm, int extra_perm);
#ifndef CONFIG_ARCH_WANT_IPC_PARSE_VERSION
/* On IA-64, we always use the "64-bit version" of the IPC structures. */
# define ipc_parse_version(cmd) IPC_64
#else
int ipc_parse_version(int *cmd);
#endif
extern void free_msg(struct msg_msg *msg);
ipc, msg: fix message length check for negative values On 64 bit systems the test for negative message sizes is bogus as the size, which may be positive when evaluated as a long, will get truncated to an int when passed to load_msg(). So a long might very well contain a positive value but when truncated to an int it would become negative. That in combination with a small negative value of msg_ctlmax (which will be promoted to an unsigned type for the comparison against msgsz, making it a big positive value and therefore make it pass the check) will lead to two problems: 1/ The kmalloc() call in alloc_msg() will allocate a too small buffer as the addition of alen is effectively a subtraction. 2/ The copy_from_user() call in load_msg() will first overflow the buffer with userland data and then, when the userland access generates an access violation, the fixup handler copy_user_handle_tail() will try to fill the remainder with zeros -- roughly 4GB. That almost instantly results in a system crash or reset. ,-[ Reproducer (needs to be run as root) ]-- | #include <sys/stat.h> | #include <sys/msg.h> | #include <unistd.h> | #include <fcntl.h> | | int main(void) { | long msg = 1; | int fd; | | fd = open("/proc/sys/kernel/msgmax", O_WRONLY); | write(fd, "-1", 2); | close(fd); | | msgsnd(0, &msg, 0xfffffff0, IPC_NOWAIT); | | return 0; | } '--- Fix the issue by preventing msgsz from getting truncated by consistently using size_t for the message length. This way the size checks in do_msgsnd() could still be passed with a negative value for msg_ctlmax but we would fail on the buffer allocation in that case and error out. Also change the type of m_ts from int to size_t to avoid similar nastiness in other code paths -- it is used in similar constructs, i.e. signed vs. unsigned checks. It should never become negative under normal circumstances, though. Setting msg_ctlmax to a negative value is an odd configuration and should be prevented. As that might break existing userland, it will be handled in a separate commit so it could easily be reverted and reworked without reintroducing the above described bug. Hardening mechanisms for user copy operations would have catched that bug early -- e.g. checking slab object sizes on user copy operations as the usercopy feature of the PaX patch does. Or, for that matter, detect the long vs. int sign change due to truncation, as the size overflow plugin of the very same patch does. [akpm@linux-foundation.org: fix i386 min() warnings] Signed-off-by: Mathias Krause <minipli@googlemail.com> Cc: Pax Team <pageexec@freemail.hu> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Brad Spengler <spender@grsecurity.net> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: <stable@vger.kernel.org> [ v2.3.27+ -- yes, that old ;) ] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-12 16:11:47 -07:00
extern struct msg_msg *load_msg(const void __user *src, size_t len);
extern struct msg_msg *copy_msg(struct msg_msg *src, struct msg_msg *dst);
ipc, msg: fix message length check for negative values On 64 bit systems the test for negative message sizes is bogus as the size, which may be positive when evaluated as a long, will get truncated to an int when passed to load_msg(). So a long might very well contain a positive value but when truncated to an int it would become negative. That in combination with a small negative value of msg_ctlmax (which will be promoted to an unsigned type for the comparison against msgsz, making it a big positive value and therefore make it pass the check) will lead to two problems: 1/ The kmalloc() call in alloc_msg() will allocate a too small buffer as the addition of alen is effectively a subtraction. 2/ The copy_from_user() call in load_msg() will first overflow the buffer with userland data and then, when the userland access generates an access violation, the fixup handler copy_user_handle_tail() will try to fill the remainder with zeros -- roughly 4GB. That almost instantly results in a system crash or reset. ,-[ Reproducer (needs to be run as root) ]-- | #include <sys/stat.h> | #include <sys/msg.h> | #include <unistd.h> | #include <fcntl.h> | | int main(void) { | long msg = 1; | int fd; | | fd = open("/proc/sys/kernel/msgmax", O_WRONLY); | write(fd, "-1", 2); | close(fd); | | msgsnd(0, &msg, 0xfffffff0, IPC_NOWAIT); | | return 0; | } '--- Fix the issue by preventing msgsz from getting truncated by consistently using size_t for the message length. This way the size checks in do_msgsnd() could still be passed with a negative value for msg_ctlmax but we would fail on the buffer allocation in that case and error out. Also change the type of m_ts from int to size_t to avoid similar nastiness in other code paths -- it is used in similar constructs, i.e. signed vs. unsigned checks. It should never become negative under normal circumstances, though. Setting msg_ctlmax to a negative value is an odd configuration and should be prevented. As that might break existing userland, it will be handled in a separate commit so it could easily be reverted and reworked without reintroducing the above described bug. Hardening mechanisms for user copy operations would have catched that bug early -- e.g. checking slab object sizes on user copy operations as the usercopy feature of the PaX patch does. Or, for that matter, detect the long vs. int sign change due to truncation, as the size overflow plugin of the very same patch does. [akpm@linux-foundation.org: fix i386 min() warnings] Signed-off-by: Mathias Krause <minipli@googlemail.com> Cc: Pax Team <pageexec@freemail.hu> Cc: Davidlohr Bueso <davidlohr@hp.com> Cc: Brad Spengler <spender@grsecurity.net> Cc: Manfred Spraul <manfred@colorfullife.com> Cc: <stable@vger.kernel.org> [ v2.3.27+ -- yes, that old ;) ] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-12 16:11:47 -07:00
extern int store_msg(void __user *dest, struct msg_msg *msg, size_t len);
static inline int ipc_buildid(int id, int seq)
{
return SEQ_MULTIPLIER * seq + id;
}
static inline int ipc_checkid(struct kern_ipc_perm *ipcp, int uid)
{
ipc: remove bogus lock comment for ipc_checkid This series makes the sysv semaphore code more scalable, by reducing the time the semaphore lock is held, and making the locking more scalable for semaphore arrays with multiple semaphores. The first four patches were written by Davidlohr Buesso, and reduce the hold time of the semaphore lock. The last three patches change the sysv semaphore code locking to be more fine grained, providing a performance boost when multiple semaphores in a semaphore array are being manipulated simultaneously. On a 24 CPU system, performance numbers with the semop-multi test with N threads and N semaphores, look like this: vanilla Davidlohr's Davidlohr's + Davidlohr's + threads patches rwlock patches v3 patches 10 610652 726325 1783589 2142206 20 341570 365699 1520453 1977878 30 288102 307037 1498167 2037995 40 290714 305955 1612665 2256484 50 288620 312890 1733453 2650292 60 289987 306043 1649360 2388008 70 291298 306347 1723167 2717486 80 290948 305662 1729545 2763582 90 290996 306680 1736021 2757524 100 292243 306700 1773700 3059159 This patch: There is no reason to be holding the ipc lock while reading ipcp->seq, hence remove misleading comment. Also simplify the return value for the function. Signed-off-by: Davidlohr Bueso <davidlohr.bueso@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Cc: Chegu Vinod <chegu_vinod@hp.com> Cc: Emmanuel Benisty <benisty.e@gmail.com> Cc: Jason Low <jason.low2@hp.com> Cc: Michel Lespinasse <walken@google.com> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Stanislav Kinsbursky <skinsbursky@parallels.com> Tested-by: Sedat Dilek <sedat.dilek@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 19:15:14 -07:00
return uid / SEQ_MULTIPLIER != ipcp->seq;
}
static inline void ipc_lock_object(struct kern_ipc_perm *perm)
{
spin_lock(&perm->lock);
}
static inline void ipc_unlock_object(struct kern_ipc_perm *perm)
{
spin_unlock(&perm->lock);
}
static inline void ipc_assert_locked_object(struct kern_ipc_perm *perm)
ipc,sem: do not hold ipc lock more than necessary Instead of holding the ipc lock for permissions and security checks, among others, only acquire it when necessary. Some numbers.... 1) With Rik's semop-multi.c microbenchmark we can see the following results: Baseline (3.9-rc1): cpus 4, threads: 256, semaphores: 128, test duration: 30 secs total operations: 151452270, ops/sec 5048409 + 59.40% a.out [kernel.kallsyms] [k] _raw_spin_lock + 6.14% a.out [kernel.kallsyms] [k] sys_semtimedop + 3.84% a.out [kernel.kallsyms] [k] avc_has_perm_flags + 3.64% a.out [kernel.kallsyms] [k] __audit_syscall_exit + 2.06% a.out [kernel.kallsyms] [k] copy_user_enhanced_fast_string + 1.86% a.out [kernel.kallsyms] [k] ipc_lock With this patchset: cpus 4, threads: 256, semaphores: 128, test duration: 30 secs total operations: 273156400, ops/sec 9105213 + 18.54% a.out [kernel.kallsyms] [k] _raw_spin_lock + 11.72% a.out [kernel.kallsyms] [k] sys_semtimedop + 7.70% a.out [kernel.kallsyms] [k] ipc_has_perm.isra.21 + 6.58% a.out [kernel.kallsyms] [k] avc_has_perm_flags + 6.54% a.out [kernel.kallsyms] [k] __audit_syscall_exit + 4.71% a.out [kernel.kallsyms] [k] ipc_obtain_object_check 2) While on an Oracle swingbench DSS (data mining) workload the improvements are not as exciting as with Rik's benchmark, we can see some positive numbers. For an 8 socket machine the following are the percentages of %sys time incurred in the ipc lock: Baseline (3.9-rc1): 100 swingbench users: 8,74% 400 swingbench users: 21,86% 800 swingbench users: 84,35% With this patchset: 100 swingbench users: 8,11% 400 swingbench users: 19,93% 800 swingbench users: 77,69% [riel@redhat.com: fix two locking bugs] [sasha.levin@oracle.com: prevent releasing RCU read lock twice in semctl_main] [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Davidlohr Bueso <davidlohr.bueso@hp.com> Signed-off-by: Rik van Riel <riel@redhat.com> Reviewed-by: Chegu Vinod <chegu_vinod@hp.com> Acked-by: Michel Lespinasse <walken@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Jason Low <jason.low2@hp.com> Cc: Emmanuel Benisty <benisty.e@gmail.com> Cc: Peter Hurley <peter@hurleysoftware.com> Cc: Stanislav Kinsbursky <skinsbursky@parallels.com> Tested-by: Sedat Dilek <sedat.dilek@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-04-30 19:15:29 -07:00
{
assert_spin_locked(&perm->lock);
}
static inline void ipc_unlock(struct kern_ipc_perm *perm)
{
ipc_unlock_object(perm);
rcu_read_unlock();
}
/*
* ipc_valid_object() - helper to sort out IPC_RMID races for codepaths
* where the respective ipc_ids.rwsem is not being held down.
* Checks whether the ipc object is still around or if it's gone already, as
* ipc_rmid() may have already freed the ID while the ipc lock was spinning.
* Needs to be called with kern_ipc_perm.lock held -- exception made for one
* checkpoint case at sys_semtimedop() as noted in code commentary.
*/
static inline bool ipc_valid_object(struct kern_ipc_perm *perm)
{
return !perm->deleted;
}
struct kern_ipc_perm *ipc_obtain_object_check(struct ipc_ids *ids, int id);
int ipcget(struct ipc_namespace *ns, struct ipc_ids *ids,
const struct ipc_ops *ops, struct ipc_params *params);
void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids,
void (*free)(struct ipc_namespace *, struct kern_ipc_perm *));
#endif