#include <linux/capability.h>
#include <linux/ptrace.h>
#include <linux/seq_file.h>
-#include <linux/mutex.h>
+#include <linux/rwsem.h>
#include <linux/nsproxy.h>
#include <linux/mount.h>
+#include <linux/ipc_namespace.h>
#include <asm/uaccess.h>
static const struct file_operations shm_file_operations;
static struct vm_operations_struct shm_vm_ops;
-static struct ipc_ids init_shm_ids;
-
-#define shm_ids(ns) (*((ns)->ids[IPC_SHM_IDS]))
+#define shm_ids(ns) ((ns)->ids[IPC_SHM_IDS])
#define shm_unlock(shp) \
ipc_unlock(&(shp)->shm_perm)
-#define shm_buildid(ns, id, seq) \
- ipc_buildid(&shm_ids(ns), id, seq)
static int newseg(struct ipc_namespace *, struct ipc_params *);
static void shm_open(struct vm_area_struct *vma);
static int sysvipc_shm_proc_show(struct seq_file *s, void *it);
#endif
-static void __shm_init_ns(struct ipc_namespace *ns, struct ipc_ids *ids)
+void shm_init_ns(struct ipc_namespace *ns)
{
- ns->ids[IPC_SHM_IDS] = ids;
ns->shm_ctlmax = SHMMAX;
ns->shm_ctlall = SHMALL;
ns->shm_ctlmni = SHMMNI;
ns->shm_tot = 0;
- ipc_init_ids(ids);
+ ipc_init_ids(&ns->ids[IPC_SHM_IDS]);
}
-static void do_shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *shp)
+/*
+ * Called with shm_ids.rw_mutex (writer) and the shp structure locked.
+ * Only shm_ids.rw_mutex remains locked on exit.
+ */
+static void do_shm_rmid(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
{
+ struct shmid_kernel *shp;
+ shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+
if (shp->shm_nattch){
shp->shm_perm.mode |= SHM_DEST;
/* Do not find it any more */
shm_destroy(ns, shp);
}
-int shm_init_ns(struct ipc_namespace *ns)
-{
- struct ipc_ids *ids;
-
- ids = kmalloc(sizeof(struct ipc_ids), GFP_KERNEL);
- if (ids == NULL)
- return -ENOMEM;
-
- __shm_init_ns(ns, ids);
- return 0;
-}
-
+#ifdef CONFIG_IPC_NS
void shm_exit_ns(struct ipc_namespace *ns)
{
- struct shmid_kernel *shp;
- int next_id;
- int total, in_use;
-
- mutex_lock(&shm_ids(ns).mutex);
-
- in_use = shm_ids(ns).in_use;
-
- for (total = 0, next_id = 0; total < in_use; next_id++) {
- shp = idr_find(&shm_ids(ns).ipcs_idr, next_id);
- if (shp == NULL)
- continue;
- ipc_lock_by_ptr(&shp->shm_perm);
- do_shm_rmid(ns, shp);
- total++;
- }
- mutex_unlock(&shm_ids(ns).mutex);
-
- kfree(ns->ids[IPC_SHM_IDS]);
- ns->ids[IPC_SHM_IDS] = NULL;
+ free_ipcs(ns, &shm_ids(ns), do_shm_rmid);
}
+#endif
void __init shm_init (void)
{
- __shm_init_ns(&init_ipc_ns, &init_shm_ids);
+ shm_init_ns(&init_ipc_ns);
ipc_init_proc_interface("sysvipc/shm",
" key shmid perms size cpid lpid nattch uid gid cuid cgid atime dtime ctime\n",
IPC_SHM_IDS, sysvipc_shm_proc_show);
}
+/*
+ * shm_lock_(check_)down routines are called in the paths where the rw_mutex
+ * is held to protect access to the idr tree.
+ */
+static inline struct shmid_kernel *shm_lock_down(struct ipc_namespace *ns,
+ int id)
+{
+ struct kern_ipc_perm *ipcp = ipc_lock_down(&shm_ids(ns), id);
+
+ if (IS_ERR(ipcp))
+ return (struct shmid_kernel *)ipcp;
+
+ return container_of(ipcp, struct shmid_kernel, shm_perm);
+}
+
+/*
+ * shm_lock_(check_) routines are called in the paths where the rw_mutex
+ * is not held.
+ */
static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id)
{
struct kern_ipc_perm *ipcp = ipc_lock(&shm_ids(ns), id);
+ if (IS_ERR(ipcp))
+ return (struct shmid_kernel *)ipcp;
+
return container_of(ipcp, struct shmid_kernel, shm_perm);
}
{
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);
}
ipc_rmid(&shm_ids(ns), &s->shm_perm);
}
-static inline int shm_addid(struct ipc_namespace *ns, struct shmid_kernel *shp)
-{
- return ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
-}
-
-
/* This is called by fork, once for every shm attach. */
static void shm_open(struct vm_area_struct *vma)
/*
* shm_destroy - free the struct shmid_kernel
*
+ * @ns: namespace
* @shp: struct to free
*
- * It has to be called with shp and shm_ids.mutex locked,
+ * It has to be called with shp and shm_ids.rw_mutex (writer) locked,
* but returns with shp unlocked and freed.
*/
static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
struct shmid_kernel *shp;
struct ipc_namespace *ns = sfd->ns;
- mutex_lock(&shm_ids(ns).mutex);
+ down_write(&shm_ids(ns).rw_mutex);
/* remove from the list of attaches of the shm segment */
- shp = shm_lock(ns, sfd->id);
+ shp = shm_lock_down(ns, sfd->id);
BUG_ON(IS_ERR(shp));
shp->shm_lprid = task_tgid_vnr(current);
shp->shm_dtim = get_seconds();
shm_destroy(ns, shp);
else
shm_unlock(shp);
- mutex_unlock(&shm_ids(ns).mutex);
+ up_write(&shm_ids(ns).rw_mutex);
}
static int shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
pol = sfd->vm_ops->get_policy(vma, addr);
else if (vma->vm_policy)
pol = vma->vm_policy;
- else
- pol = current->mempolicy;
+
return pol;
}
#endif
#endif
};
+/**
+ * newseg - Create a new shared memory segment
+ * @ns: namespace
+ * @params: ptr to the structure that contains key, size and shmflg
+ *
+ * Called with shm_ids.rw_mutex held as a writer.
+ */
+
static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
{
key_t key = params->key;
if (IS_ERR(file))
goto no_file;
- error = -ENOSPC;
- id = shm_addid(ns, shp);
- if(id == -1)
+ id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
+ if (id < 0) {
+ error = id;
goto no_id;
+ }
shp->shm_cprid = task_tgid_vnr(current);
shp->shm_lprid = 0;
shp->shm_ctim = get_seconds();
shp->shm_segsz = size;
shp->shm_nattch = 0;
- shp->shm_perm.id = shm_buildid(ns, id, shp->shm_perm.seq);
shp->shm_file = file;
/*
* shmid gets reported as "inode#" in /proc/pid/maps.
return error;
}
+/*
+ * Called with shm_ids.rw_mutex and ipcp locked.
+ */
static inline int shm_security(struct kern_ipc_perm *ipcp, int shmflg)
{
struct shmid_kernel *shp;
return security_shm_associate(shp, shmflg);
}
+/*
+ * Called with shm_ids.rw_mutex and ipcp locked.
+ */
static inline int shm_more_checks(struct kern_ipc_perm *ipcp,
struct ipc_params *params)
{
}
}
-struct shm_setbuf {
- uid_t uid;
- gid_t gid;
- mode_t mode;
-};
-
-static inline unsigned long copy_shmid_from_user(struct shm_setbuf *out, void __user *buf, int version)
+static inline unsigned long
+copy_shmid_from_user(struct shmid64_ds *out, void __user *buf, int version)
{
switch(version) {
case IPC_64:
- {
- struct shmid64_ds tbuf;
-
- if (copy_from_user(&tbuf, buf, sizeof(tbuf)))
+ if (copy_from_user(out, buf, sizeof(*out)))
return -EFAULT;
-
- out->uid = tbuf.shm_perm.uid;
- out->gid = tbuf.shm_perm.gid;
- out->mode = tbuf.shm_perm.mode;
-
return 0;
- }
case IPC_OLD:
{
struct shmid_ds tbuf_old;
if (copy_from_user(&tbuf_old, buf, sizeof(tbuf_old)))
return -EFAULT;
- out->uid = tbuf_old.shm_perm.uid;
- out->gid = tbuf_old.shm_perm.gid;
- out->mode = tbuf_old.shm_perm.mode;
+ out->shm_perm.uid = tbuf_old.shm_perm.uid;
+ out->shm_perm.gid = tbuf_old.shm_perm.gid;
+ out->shm_perm.mode = tbuf_old.shm_perm.mode;
return 0;
}
}
}
+/*
+ * Called with shm_ids.rw_mutex held as a reader
+ */
static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
unsigned long *swp)
{
struct shmid_kernel *shp;
struct inode *inode;
- /*
- * idr_find() is called via shm_get(), so with shm_ids.mutex
- * locked. Since ipc_addid() is also called with
- * shm_ids.mutex down, there is no need to add read barriers
- * here to gurantee the writes in ipc_addid() are seen in
- * order here (for Alpha).
- * However idr_find() itself does not necessary require
- * ipc_ids.mutex down. So if idr_find() is used by other
- * places without ipc_ids.mutex down, then it needs read
- * read memory barriers as ipc_lock() does.
- */
-
shp = idr_find(&shm_ids(ns).ipcs_idr, next_id);
if (shp == NULL)
continue;
if (is_file_hugepages(shp->shm_file)) {
struct address_space *mapping = inode->i_mapping;
- *rss += (HPAGE_SIZE/PAGE_SIZE)*mapping->nrpages;
+ struct hstate *h = hstate_file(shp->shm_file);
+ *rss += pages_per_huge_page(h) * mapping->nrpages;
} else {
struct shmem_inode_info *info = SHMEM_I(inode);
spin_lock(&info->lock);
}
}
-asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf)
+/*
+ * This function handles some shmctl commands which require the rw_mutex
+ * to be held in write mode.
+ * NOTE: no locks must be held, the rw_mutex is taken inside this function.
+ */
+static int shmctl_down(struct ipc_namespace *ns, int shmid, int cmd,
+ struct shmid_ds __user *buf, int version)
+{
+ struct kern_ipc_perm *ipcp;
+ struct shmid64_ds shmid64;
+ struct shmid_kernel *shp;
+ int err;
+
+ if (cmd == IPC_SET) {
+ if (copy_shmid_from_user(&shmid64, buf, version))
+ return -EFAULT;
+ }
+
+ ipcp = ipcctl_pre_down(&shm_ids(ns), shmid, cmd, &shmid64.shm_perm, 0);
+ if (IS_ERR(ipcp))
+ return PTR_ERR(ipcp);
+
+ shp = container_of(ipcp, struct shmid_kernel, shm_perm);
+
+ err = security_shm_shmctl(shp, cmd);
+ if (err)
+ goto out_unlock;
+ switch (cmd) {
+ case IPC_RMID:
+ do_shm_rmid(ns, ipcp);
+ goto out_up;
+ case IPC_SET:
+ ipc_update_perm(&shmid64.shm_perm, ipcp);
+ shp->shm_ctim = get_seconds();
+ break;
+ default:
+ err = -EINVAL;
+ }
+out_unlock:
+ shm_unlock(shp);
+out_up:
+ up_write(&shm_ids(ns).rw_mutex);
+ return err;
+}
+
+asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf)
{
- struct shm_setbuf setbuf;
struct shmid_kernel *shp;
int err, version;
struct ipc_namespace *ns;
shminfo.shmmin = SHMMIN;
if(copy_shminfo_to_user (buf, &shminfo, version))
return -EFAULT;
- /* reading a integer is always atomic */
+
+ down_read(&shm_ids(ns).rw_mutex);
err = ipc_get_maxid(&shm_ids(ns));
+ up_read(&shm_ids(ns).rw_mutex);
+
if(err<0)
err = 0;
goto out;
return err;
memset(&shm_info,0,sizeof(shm_info));
- mutex_lock(&shm_ids(ns).mutex);
+ down_read(&shm_ids(ns).rw_mutex);
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));
- mutex_unlock(&shm_ids(ns).mutex);
+ up_read(&shm_ids(ns).rw_mutex);
if(copy_to_user (buf, &shm_info, sizeof(shm_info))) {
err = -EFAULT;
goto out;
goto out;
}
case IPC_RMID:
- {
- /*
- * We cannot simply remove the file. The SVID states
- * that the block remains until the last person
- * detaches from it, then is deleted. A shmat() on
- * an RMID segment is legal in older Linux and if
- * we change it apps break...
- *
- * Instead we set a destroyed flag, and then blow
- * the name away when the usage hits zero.
- */
- mutex_lock(&shm_ids(ns).mutex);
- shp = shm_lock_check(ns, shmid);
- if (IS_ERR(shp)) {
- err = PTR_ERR(shp);
- goto out_up;
- }
-
- err = audit_ipc_obj(&(shp->shm_perm));
- if (err)
- goto out_unlock_up;
-
- if (current->euid != shp->shm_perm.uid &&
- current->euid != shp->shm_perm.cuid &&
- !capable(CAP_SYS_ADMIN)) {
- err=-EPERM;
- goto out_unlock_up;
- }
-
- err = security_shm_shmctl(shp, cmd);
- if (err)
- goto out_unlock_up;
-
- do_shm_rmid(ns, shp);
- mutex_unlock(&shm_ids(ns).mutex);
- goto out;
- }
-
case IPC_SET:
- {
- if (!buf) {
- err = -EFAULT;
- goto out;
- }
-
- if (copy_shmid_from_user (&setbuf, buf, version)) {
- err = -EFAULT;
- goto out;
- }
- mutex_lock(&shm_ids(ns).mutex);
- shp = shm_lock_check(ns, shmid);
- if (IS_ERR(shp)) {
- err = PTR_ERR(shp);
- goto out_up;
- }
- err = audit_ipc_obj(&(shp->shm_perm));
- if (err)
- goto out_unlock_up;
- err = audit_ipc_set_perm(0, setbuf.uid, setbuf.gid, setbuf.mode);
- if (err)
- goto out_unlock_up;
- err=-EPERM;
- if (current->euid != shp->shm_perm.uid &&
- current->euid != shp->shm_perm.cuid &&
- !capable(CAP_SYS_ADMIN)) {
- goto out_unlock_up;
- }
-
- err = security_shm_shmctl(shp, cmd);
- if (err)
- goto out_unlock_up;
-
- shp->shm_perm.uid = setbuf.uid;
- shp->shm_perm.gid = setbuf.gid;
- shp->shm_perm.mode = (shp->shm_perm.mode & ~S_IRWXUGO)
- | (setbuf.mode & S_IRWXUGO);
- shp->shm_ctim = get_seconds();
- break;
- }
-
+ err = shmctl_down(ns, shmid, cmd, buf, version);
+ return err;
default:
- err = -EINVAL;
- goto out;
+ return -EINVAL;
}
- err = 0;
-out_unlock_up:
- shm_unlock(shp);
-out_up:
- mutex_unlock(&shm_ids(ns).mutex);
- goto out;
out_unlock:
shm_unlock(shp);
out:
if (!sfd)
goto out_put_dentry;
- err = -ENOMEM;
-
file = alloc_file(path.mnt, path.dentry, f_mode, &shm_file_operations);
if (!file)
goto out_free;
fput(file);
out_nattch:
- mutex_lock(&shm_ids(ns).mutex);
- shp = shm_lock(ns, shmid);
+ down_write(&shm_ids(ns).rw_mutex);
+ shp = shm_lock_down(ns, shmid);
BUG_ON(IS_ERR(shp));
shp->shm_nattch--;
if(shp->shm_nattch == 0 &&
shm_destroy(ns, shp);
else
shm_unlock(shp);
- mutex_unlock(&shm_ids(ns).mutex);
+ up_write(&shm_ids(ns).rw_mutex);
out:
return err;
static int sysvipc_shm_proc_show(struct seq_file *s, void *it)
{
struct shmid_kernel *shp = it;
- char *format;
-#define SMALL_STRING "%10d %10d %4o %10u %5u %5u %5d %5u %5u %5u %5u %10lu %10lu %10lu\n"
-#define BIG_STRING "%10d %10d %4o %21u %5u %5u %5d %5u %5u %5u %5u %10lu %10lu %10lu\n"
+#if BITS_PER_LONG <= 32
+#define SIZE_SPEC "%10lu"
+#else
+#define SIZE_SPEC "%21lu"
+#endif
- if (sizeof(size_t) <= sizeof(int))
- format = SMALL_STRING;
- else
- format = BIG_STRING;
- return seq_printf(s, format,
+ return seq_printf(s,
+ "%10d %10d %4o " SIZE_SPEC " %5u %5u "
+ "%5lu %5u %5u %5u %5u %10lu %10lu %10lu\n",
shp->shm_perm.key,
shp->shm_perm.id,
shp->shm_perm.mode,
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff