aboutsummaryrefslogtreecommitdiff
path: root/ipc/shm.c
diff options
context:
space:
mode:
Diffstat (limited to 'ipc/shm.c')
-rw-r--r--ipc/shm.c255
1 files changed, 148 insertions, 107 deletions
diff --git a/ipc/shm.c b/ipc/shm.c
index c6b4ad5ce3b7..2821cdf93adb 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -19,6 +19,9 @@
* namespaces support
* OpenVZ, SWsoft Inc.
* Pavel Emelianov <xemul@openvz.org>
+ *
+ * Better ipc lock (kern_ipc_perm.lock) handling
+ * Davidlohr Bueso <davidlohr.bueso@hp.com>, June 2013.
*/
#include <linux/slab.h>
@@ -80,8 +83,8 @@ void shm_init_ns(struct ipc_namespace *ns)
}
/*
- * Called with shm_ids.rw_mutex (writer) and the shp structure locked.
- * Only shm_ids.rw_mutex remains locked on exit.
+ * Called with shm_ids.rwsem (writer) and the shp structure locked.
+ * Only shm_ids.rwsem remains locked on exit.
*/
static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
@@ -124,8 +127,28 @@ void __init shm_init (void)
IPC_SHM_IDS, sysvipc_shm_proc_show);
}
+static inline struct shmid_kernel *shm_obtain_object(struct ipc_namespace *ns, int id)
+{
+ struct kern_ipc_perm *ipcp = ipc_obtain_object(&shm_ids(ns), id);
+
+ if (IS_ERR(ipcp))
+ return ERR_CAST(ipcp);
+
+ return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
+static inline struct shmid_kernel *shm_obtain_object_check(struct ipc_namespace *ns, int id)
+{
+ struct kern_ipc_perm *ipcp = ipc_obtain_object_check(&shm_ids(ns), id);
+
+ if (IS_ERR(ipcp))
+ return ERR_CAST(ipcp);
+
+ return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
/*
- * shm_lock_(check_) routines are called in the paths where the rw_mutex
+ * shm_lock_(check_) routines are called in the paths where the rwsem
* is not necessarily held.
*/
static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
@@ -144,17 +167,6 @@ static inline void shm_lock_by_ptr(struct shmid_kernel *ipcp)
ipc_lock_object(&ipcp->shm_perm);
}
-static inline struct shmid_kernel *shm_lock_check(struct ipc_namespace *ns,
- int id)
-{
- struct kern_ipc_perm *ipcp = ipc_lock_check(&shm_ids(ns), id);
-
- if (IS_ERR(ipcp))
- return (struct shmid_kernel *)ipcp;
-
- return container_of(ipcp, struct shmid_kernel, shm_perm);
-}
-
static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
{
ipc_rmid(&shm_ids(ns), &s->shm_perm);
@@ -182,7 +194,7 @@ static void shm_open(struct vm_area_struct *vma)
* @ns: namespace
* @shp: struct to free
*
- * It has to be called with shp and shm_ids.rw_mutex (writer) locked,
+ * It has to be called with shp and shm_ids.rwsem (writer) locked,
* but returns with shp unlocked and freed.
*/
static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
@@ -230,7 +242,7 @@ static void shm_close(struct vm_area_struct *vma)
struct shmid_kernel *shp;
struct ipc_namespace *ns = sfd->ns;
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
/* remove from the list of attaches of the shm segment */
shp = shm_lock(ns, sfd->id);
BUG_ON(IS_ERR(shp));
@@ -241,10 +253,10 @@ static void shm_close(struct vm_area_struct *vma)
shm_destroy(ns, shp);
else
shm_unlock(shp);
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
}
-/* Called with ns->shm_ids(ns).rw_mutex locked */
+/* Called with ns->shm_ids(ns).rwsem locked */
static int shm_try_destroy_current(int id, void *p, void *data)
{
struct ipc_namespace *ns = data;
@@ -275,7 +287,7 @@ static int shm_try_destroy_current(int id, void *p, void *data)
return 0;
}
-/* Called with ns->shm_ids(ns).rw_mutex locked */
+/* Called with ns->shm_ids(ns).rwsem locked */
static int shm_try_destroy_orphaned(int id, void *p, void *data)
{
struct ipc_namespace *ns = data;
@@ -286,7 +298,7 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data)
* We want to destroy segments without users and with already
* exit'ed originating process.
*
- * As shp->* are changed under rw_mutex, it's safe to skip shp locking.
+ * As shp->* are changed under rwsem, it's safe to skip shp locking.
*/
if (shp->shm_creator != NULL)
return 0;
@@ -300,10 +312,10 @@ static int shm_try_destroy_orphaned(int id, void *p, void *data)
void shm_destroy_orphaned(struct ipc_namespace *ns)
{
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
if (shm_ids(ns).in_use)
idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_orphaned, ns);
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
}
@@ -315,10 +327,10 @@ void exit_shm(struct task_struct *task)
return;
/* Destroy all already created segments, but not mapped yet */
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
if (shm_ids(ns).in_use)
idr_for_each(&shm_ids(ns).ipcs_idr, &shm_try_destroy_current, ns);
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
}
static int shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
@@ -452,7 +464,7 @@ static const struct vm_operations_struct shm_vm_ops = {
* @ns: namespace
* @params: ptr to the structure that contains key, size and shmflg
*
- * Called with shm_ids.rw_mutex held as a writer.
+ * Called with shm_ids.rwsem held as a writer.
*/
static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
@@ -560,7 +572,7 @@ no_file:
}
/*
- * Called with shm_ids.rw_mutex and ipcp locked.
+ * Called with shm_ids.rwsem and ipcp locked.
*/
static inline int shm_security(struct kern_ipc_perm *ipcp, int shmflg)
{
@@ -571,7 +583,7 @@ static inline int shm_security(struct kern_ipc_perm *ipcp, int shmflg)
}
/*
- * Called with shm_ids.rw_mutex and ipcp locked.
+ * Called with shm_ids.rwsem and ipcp locked.
*/
static inline int shm_more_checks(struct kern_ipc_perm *ipcp,
struct ipc_params *params)
@@ -684,7 +696,7 @@ static inline unsigned long copy_shminfo_to_user(void __user *buf, struct shminf
/*
* Calculate and add used RSS and swap pages of a shm.
- * Called with shm_ids.rw_mutex held as a reader
+ * Called with shm_ids.rwsem held as a reader
*/
static void shm_add_rss_swap(struct shmid_kernel *shp,
unsigned long *rss_add, unsigned long *swp_add)
@@ -711,7 +723,7 @@ static void shm_add_rss_swap(struct shmid_kernel *shp,
}
/*
- * Called with shm_ids.rw_mutex held as a reader
+ * Called with shm_ids.rwsem held as a reader
*/
static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
unsigned long *swp)
@@ -740,9 +752,9 @@ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
}
/*
- * This function handles some shmctl commands which require the rw_mutex
+ * This function handles some shmctl commands which require the rwsem
* to be held in write mode.
- * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ * NOTE: no locks must be held, the rwsem is taken inside this function.
*/
static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
struct shmid_ds __user *buf, int version)
@@ -757,14 +769,13 @@ static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
return -EFAULT;
}
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
rcu_read_lock();
- ipcp = ipcctl_pre_down(ns, &shm_ids(ns), shmid, cmd,
- &shmid64.shm_perm, 0);
+ ipcp = ipcctl_pre_down_nolock(ns, &shm_ids(ns), shmid, cmd,
+ &shmid64.shm_perm, 0);
if (IS_ERR(ipcp)) {
err = PTR_ERR(ipcp);
- /* the ipc lock is not held upon failure */
goto out_unlock1;
}
@@ -772,14 +783,16 @@ static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
err = security_shm_shmctl(shp, cmd);
if (err)
- goto out_unlock0;
+ goto out_unlock1;
switch (cmd) {
case IPC_RMID:
+ ipc_lock_object(&shp->shm_perm);
/* do_shm_rmid unlocks the ipc object and rcu */
do_shm_rmid(ns, ipcp);
goto out_up;
case IPC_SET:
+ ipc_lock_object(&shp->shm_perm);
err = ipc_update_perm(&shmid64.shm_perm, ipcp);
if (err)
goto out_unlock0;
@@ -787,6 +800,7 @@ static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
break;
default:
err = -EINVAL;
+ goto out_unlock1;
}
out_unlock0:
@@ -794,33 +808,28 @@ out_unlock0:
out_unlock1:
rcu_read_unlock();
out_up:
- up_write(&shm_ids(ns).rw_mutex);
+ up_write(&shm_ids(ns).rwsem);
return err;
}
-SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+static int shmctl_nolock(struct ipc_namespace *ns, int shmid,
+ int cmd, int version, void __user *buf)
{
+ int err;
struct shmid_kernel *shp;
- int err, version;
- struct ipc_namespace *ns;
- if (cmd < 0 || shmid < 0) {
- err = -EINVAL;
- goto out;
+ /* preliminary security checks for *_INFO */
+ if (cmd == IPC_INFO || cmd == SHM_INFO) {
+ err = security_shm_shmctl(NULL, cmd);
+ if (err)
+ return err;
}
- version = ipc_parse_version(&cmd);
- ns = current->nsproxy->ipc_ns;
-
- switch (cmd) { /* replace with proc interface ? */
+ switch (cmd) {
case IPC_INFO:
{
struct shminfo64 shminfo;
- err = security_shm_shmctl(NULL, cmd);
- if (err)
- return err;
-
memset(&shminfo, 0, sizeof(shminfo));
shminfo.shmmni = shminfo.shmseg = ns->shm_ctlmni;
shminfo.shmmax = ns->shm_ctlmax;
@@ -830,9 +839,9 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
if(copy_shminfo_to_user (buf, &shminfo, version))
return -EFAULT;
- down_read(&shm_ids(ns).rw_mutex);
+ down_read(&shm_ids(ns).rwsem);
err = ipc_get_maxid(&shm_ids(ns));
- up_read(&shm_ids(ns).rw_mutex);
+ up_read(&shm_ids(ns).rwsem);
if(err<0)
err = 0;
@@ -842,19 +851,15 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
{
struct shm_info shm_info;
- err = security_shm_shmctl(NULL, cmd);
- if (err)
- return err;
-
memset(&shm_info, 0, sizeof(shm_info));
- down_read(&shm_ids(ns).rw_mutex);
+ down_read(&shm_ids(ns).rwsem);
shm_info.used_ids = shm_ids(ns).in_use;
shm_get_stat (ns, &shm_info.shm_rss, &shm_info.shm_swp);
shm_info.shm_tot = ns->shm_tot;
shm_info.swap_attempts = 0;
shm_info.swap_successes = 0;
err = ipc_get_maxid(&shm_ids(ns));
- up_read(&shm_ids(ns).rw_mutex);
+ up_read(&shm_ids(ns).rwsem);
if (copy_to_user(buf, &shm_info, sizeof(shm_info))) {
err = -EFAULT;
goto out;
@@ -869,27 +874,31 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
struct shmid64_ds tbuf;
int result;
+ rcu_read_lock();
if (cmd == SHM_STAT) {
- shp = shm_lock(ns, shmid);
+ shp = shm_obtain_object(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
result = shp->shm_perm.id;
} else {
- shp = shm_lock_check(ns, shmid);
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
result = 0;
}
+
err = -EACCES;
if (ipcperms(ns, &shp->shm_perm, S_IRUGO))
goto out_unlock;
+
err = security_shm_shmctl(shp, cmd);
if (err)
goto out_unlock;
+
memset(&tbuf, 0, sizeof(tbuf));
kernel_to_ipc64_perm(&shp->shm_perm, &tbuf.shm_perm);
tbuf.shm_segsz = shp->shm_segsz;
@@ -899,43 +908,76 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
tbuf.shm_cpid = shp->shm_cprid;
tbuf.shm_lpid = shp->shm_lprid;
tbuf.shm_nattch = shp->shm_nattch;
- shm_unlock(shp);
- if(copy_shmid_to_user (buf, &tbuf, version))
+ rcu_read_unlock();
+
+ if (copy_shmid_to_user(buf, &tbuf, version))
err = -EFAULT;
else
err = result;
goto out;
}
+ default:
+ return -EINVAL;
+ }
+
+out_unlock:
+ rcu_read_unlock();
+out:
+ return err;
+}
+
+SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
+{
+ struct shmid_kernel *shp;
+ int err, version;
+ struct ipc_namespace *ns;
+
+ if (cmd < 0 || shmid < 0)
+ return -EINVAL;
+
+ version = ipc_parse_version(&cmd);
+ ns = current->nsproxy->ipc_ns;
+
+ switch (cmd) {
+ case IPC_INFO:
+ case SHM_INFO:
+ case SHM_STAT:
+ case IPC_STAT:
+ return shmctl_nolock(ns, shmid, cmd, version, buf);
+ case IPC_RMID:
+ case IPC_SET:
+ return shmctl_down(ns, shmid, cmd, buf, version);
case SHM_LOCK:
case SHM_UNLOCK:
{
struct file *shm_file;
- shp = shm_lock_check(ns, shmid);
+ rcu_read_lock();
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock1;
}
audit_ipc_obj(&(shp->shm_perm));
+ err = security_shm_shmctl(shp, cmd);
+ if (err)
+ goto out_unlock1;
+ ipc_lock_object(&shp->shm_perm);
if (!ns_capable(ns->user_ns, CAP_IPC_LOCK)) {
kuid_t euid = current_euid();
err = -EPERM;
if (!uid_eq(euid, shp->shm_perm.uid) &&
!uid_eq(euid, shp->shm_perm.cuid))
- goto out_unlock;
+ goto out_unlock0;
if (cmd == SHM_LOCK && !rlimit(RLIMIT_MEMLOCK))
- goto out_unlock;
+ goto out_unlock0;
}
- err = security_shm_shmctl(shp, cmd);
- if (err)
- goto out_unlock;
-
shm_file = shp->shm_file;
if (is_file_hugepages(shm_file))
- goto out_unlock;
+ goto out_unlock0;
if (cmd == SHM_LOCK) {
struct user_struct *user = current_user();
@@ -944,32 +986,31 @@ SYSCALL_DEFINE3(shmctl, int, shmid, int, cmd, struct shmid_ds __user *, buf)
shp->shm_perm.mode |= SHM_LOCKED;
shp->mlock_user = user;
}
- goto out_unlock;
+ goto out_unlock0;
}
/* SHM_UNLOCK */
if (!(shp->shm_perm.mode & SHM_LOCKED))
- goto out_unlock;
+ goto out_unlock0;
shmem_lock(shm_file, 0, shp->mlock_user);
shp->shm_perm.mode &= ~SHM_LOCKED;
shp->mlock_user = NULL;
get_file(shm_file);
- shm_unlock(shp);
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
shmem_unlock_mapping(shm_file->f_mapping);
+
fput(shm_file);
- goto out;
- }
- case IPC_RMID:
- case IPC_SET:
- err = shmctl_down(ns, shmid, cmd, buf, version);
return err;
+ }
default:
return -EINVAL;
}
-out_unlock:
- shm_unlock(shp);
-out:
+out_unlock0:
+ ipc_unlock_object(&shp->shm_perm);
+out_unlock1:
+ rcu_read_unlock();
return err;
}
@@ -1037,10 +1078,11 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
* additional creator id...
*/
ns = current->nsproxy->ipc_ns;
- shp = shm_lock_check(ns, shmid);
+ rcu_read_lock();
+ shp = shm_obtain_object_check(ns, shmid);
if (IS_ERR(shp)) {
err = PTR_ERR(shp);
- goto out;
+ goto out_unlock;
}
err = -EACCES;
@@ -1051,24 +1093,31 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
if (err)
goto out_unlock;
+ ipc_lock_object(&shp->shm_perm);
path = shp->shm_file->f_path;
path_get(&path);
shp->shm_nattch++;
size = i_size_read(path.dentry->d_inode);
- shm_unlock(shp);
+ ipc_unlock_object(&shp->shm_perm);
+ rcu_read_unlock();
err = -ENOMEM;
sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
- if (!sfd)
- goto out_put_dentry;
+ if (!sfd) {
+ path_put(&path);
+ goto out_nattch;
+ }
file = alloc_file(&path, f_mode,
is_file_hugepages(shp->shm_file) ?
&shm_file_operations_huge :
&shm_file_operations);
err = PTR_ERR(file);
- if (IS_ERR(file))
- goto out_free;
+ if (IS_ERR(file)) {
+ kfree(sfd);
+ path_put(&path);
+ goto out_nattch;
+ }
file->private_data = sfd;
file->f_mapping = shp->shm_file->f_mapping;
@@ -1094,7 +1143,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr,
addr > current->mm->start_stack - size - PAGE_SIZE * 5)
goto invalid;
}
-
+
addr = do_mmap_pgoff(file, addr, size, prot, flags, 0, &populate);
*raddr = addr;
err = 0;
@@ -1109,7 +1158,7 @@ out_fput:
fput(file);
out_nattch:
- down_write(&shm_ids(ns).rw_mutex);
+ down_write(&shm_ids(ns).rwsem);
shp = shm_lock(ns, shmid);
BUG_ON(IS_ERR(shp));
shp->shm_nattch--;
@@ -1117,20 +1166,13 @@ out_nattch:
shm_destroy(ns, shp);
else
shm_unlock(shp);
- up_write(&shm_ids(ns).rw_mutex);
-
-out:
+ up_write(&shm_ids(ns).rwsem);
return err;
out_unlock:
- shm_unlock(shp);
- goto out;
-
-out_free:
- kfree(sfd);
-out_put_dentry:
- path_put(&path);
- goto out_nattch;
+ rcu_read_unlock();
+out:
+ return err;
}
SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg)
@@ -1235,8 +1277,7 @@ SYSCALL_DEFINE1(shmdt, char __user *, shmaddr)
#else /* CONFIG_MMU */
/* under NOMMU conditions, the exact address to be destroyed must be
* given */
- retval = -EINVAL;
- if (vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
+ if (vma && vma->vm_start == addr && vma->vm_ops == &shm_vm_ops) {
do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
retval = 0;
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-02 09:12:50 +0000