#include <linux/seq_file.h>
#include <linux/mutex.h>
#include <linux/nsproxy.h>
+#include <linux/mount.h>
#include <asm/uaccess.h>
#include "util.h"
-static struct file_operations shm_file_operations;
+struct shm_file_data {
+ int id;
+ struct ipc_namespace *ns;
+ struct file *file;
+ const struct vm_operations_struct *vm_ops;
+};
+
+#define shm_file_data(file) (*((struct shm_file_data **)&(file)->private_data))
+
+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_buildid(ns, id, seq) \
ipc_buildid(&shm_ids(ns), id, seq)
-static int newseg (struct ipc_namespace *ns, key_t key,
- int shmflg, size_t size);
-static void shm_open (struct vm_area_struct *shmd);
-static void shm_close (struct vm_area_struct *shmd);
+static int newseg(struct ipc_namespace *, struct ipc_params *);
+static void shm_open(struct vm_area_struct *vma);
+static void shm_close(struct vm_area_struct *vma);
static void shm_destroy (struct ipc_namespace *ns, struct shmid_kernel *shp);
#ifdef CONFIG_PROC_FS
static int sysvipc_shm_proc_show(struct seq_file *s, void *it);
#endif
-static void __ipc_init __shm_init_ns(struct ipc_namespace *ns, struct ipc_ids *ids)
+static void __shm_init_ns(struct ipc_namespace *ns, struct ipc_ids *ids)
{
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, 1);
+ ipc_init_ids(ids);
}
static void do_shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *shp)
shm_destroy(ns, shp);
}
-#ifdef CONFIG_IPC_NS
int shm_init_ns(struct ipc_namespace *ns)
{
struct ipc_ids *ids;
void shm_exit_ns(struct ipc_namespace *ns)
{
- int i;
struct shmid_kernel *shp;
+ int next_id;
+ int total, in_use;
mutex_lock(&shm_ids(ns).mutex);
- for (i = 0; i <= shm_ids(ns).max_id; i++) {
- shp = shm_lock(ns, i);
+
+ 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;
}
-#endif
void __init shm_init (void)
{
return 0;
}
-static inline struct shmid_kernel *shm_rmid(struct ipc_namespace *ns, int id)
+static inline void shm_rmid(struct ipc_namespace *ns, struct shmid_kernel *s)
{
- return (struct shmid_kernel *)ipc_rmid(&shm_ids(ns), id);
+ ipc_rmid(&shm_ids(ns), &s->shm_perm);
}
static inline int shm_addid(struct ipc_namespace *ns, struct shmid_kernel *shp)
-static inline void shm_inc(struct ipc_namespace *ns, int id)
+/* This is called by fork, once for every shm attach. */
+static void shm_open(struct vm_area_struct *vma)
{
+ struct file *file = vma->vm_file;
+ struct shm_file_data *sfd = shm_file_data(file);
struct shmid_kernel *shp;
- shp = shm_lock(ns, id);
+ shp = shm_lock(sfd->ns, sfd->id);
BUG_ON(!shp);
shp->shm_atim = get_seconds();
- shp->shm_lprid = current->tgid;
+ shp->shm_lprid = task_tgid_vnr(current);
shp->shm_nattch++;
shm_unlock(shp);
}
-#define shm_file_ns(file) (*((struct ipc_namespace **)&(file)->private_data))
-
-/* This is called by fork, once for every shm attach. */
-static void shm_open(struct vm_area_struct *shmd)
-{
- shm_inc(shm_file_ns(shmd->vm_file),
- shmd->vm_file->f_dentry->d_inode->i_ino);
-}
-
/*
* shm_destroy - free the struct shmid_kernel
*
static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp)
{
ns->shm_tot -= (shp->shm_segsz + PAGE_SIZE - 1) >> PAGE_SHIFT;
- shm_rmid(ns, shp->id);
+ shm_rmid(ns, shp);
shm_unlock(shp);
if (!is_file_hugepages(shp->shm_file))
shmem_lock(shp->shm_file, 0, shp->mlock_user);
else
- user_shm_unlock(shp->shm_file->f_dentry->d_inode->i_size,
+ user_shm_unlock(shp->shm_file->f_path.dentry->d_inode->i_size,
shp->mlock_user);
fput (shp->shm_file);
security_shm_free(shp);
}
/*
- * remove the attach descriptor shmd.
+ * remove the attach descriptor vma.
* free memory for segment if it is marked destroyed.
* The descriptor has already been removed from the current->mm->mmap list
* and will later be kfree()d.
*/
-static void shm_close (struct vm_area_struct *shmd)
+static void shm_close(struct vm_area_struct *vma)
{
- struct file * file = shmd->vm_file;
- int id = file->f_dentry->d_inode->i_ino;
+ struct file * file = vma->vm_file;
+ struct shm_file_data *sfd = shm_file_data(file);
struct shmid_kernel *shp;
- struct ipc_namespace *ns;
-
- ns = shm_file_ns(file);
+ struct ipc_namespace *ns = sfd->ns;
mutex_lock(&shm_ids(ns).mutex);
/* remove from the list of attaches of the shm segment */
- shp = shm_lock(ns, id);
+ shp = shm_lock(ns, sfd->id);
BUG_ON(!shp);
- shp->shm_lprid = current->tgid;
+ shp->shm_lprid = task_tgid_vnr(current);
shp->shm_dtim = get_seconds();
shp->shm_nattch--;
if(shp->shm_nattch == 0 &&
mutex_unlock(&shm_ids(ns).mutex);
}
+static int shm_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct file *file = vma->vm_file;
+ struct shm_file_data *sfd = shm_file_data(file);
+
+ return sfd->vm_ops->fault(vma, vmf);
+}
+
+#ifdef CONFIG_NUMA
+static int shm_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
+{
+ struct file *file = vma->vm_file;
+ struct shm_file_data *sfd = shm_file_data(file);
+ int err = 0;
+ if (sfd->vm_ops->set_policy)
+ err = sfd->vm_ops->set_policy(vma, new);
+ return err;
+}
+
+static struct mempolicy *shm_get_policy(struct vm_area_struct *vma,
+ unsigned long addr)
+{
+ struct file *file = vma->vm_file;
+ struct shm_file_data *sfd = shm_file_data(file);
+ struct mempolicy *pol = NULL;
+
+ if (sfd->vm_ops->get_policy)
+ pol = sfd->vm_ops->get_policy(vma, addr);
+ else if (vma->vm_policy)
+ pol = vma->vm_policy;
+ else
+ pol = current->mempolicy;
+ return pol;
+}
+#endif
+
static int shm_mmap(struct file * file, struct vm_area_struct * vma)
{
+ struct shm_file_data *sfd = shm_file_data(file);
int ret;
- ret = shmem_mmap(file, vma);
- if (ret == 0) {
- vma->vm_ops = &shm_vm_ops;
- if (!(vma->vm_flags & VM_WRITE))
- vma->vm_flags &= ~VM_MAYWRITE;
- shm_inc(shm_file_ns(file), file->f_dentry->d_inode->i_ino);
- }
+ ret = sfd->file->f_op->mmap(sfd->file, vma);
+ if (ret != 0)
+ return ret;
+ sfd->vm_ops = vma->vm_ops;
+#ifdef CONFIG_MMU
+ BUG_ON(!sfd->vm_ops->fault);
+#endif
+ vma->vm_ops = &shm_vm_ops;
+ shm_open(vma);
return ret;
}
static int shm_release(struct inode *ino, struct file *file)
{
- struct ipc_namespace *ns;
+ struct shm_file_data *sfd = shm_file_data(file);
- ns = shm_file_ns(file);
- put_ipc_ns(ns);
- shm_file_ns(file) = NULL;
+ put_ipc_ns(sfd->ns);
+ shm_file_data(file) = NULL;
+ kfree(sfd);
return 0;
}
-static struct file_operations shm_file_operations = {
+static int shm_fsync(struct file *file, struct dentry *dentry, int datasync)
+{
+ int (*fsync) (struct file *, struct dentry *, int datasync);
+ struct shm_file_data *sfd = shm_file_data(file);
+ int ret = -EINVAL;
+
+ fsync = sfd->file->f_op->fsync;
+ if (fsync)
+ ret = fsync(sfd->file, sfd->file->f_path.dentry, datasync);
+ return ret;
+}
+
+static unsigned long shm_get_unmapped_area(struct file *file,
+ unsigned long addr, unsigned long len, unsigned long pgoff,
+ unsigned long flags)
+{
+ struct shm_file_data *sfd = shm_file_data(file);
+ return get_unmapped_area(sfd->file, addr, len, pgoff, flags);
+}
+
+int is_file_shm_hugepages(struct file *file)
+{
+ int ret = 0;
+
+ if (file->f_op == &shm_file_operations) {
+ struct shm_file_data *sfd;
+ sfd = shm_file_data(file);
+ ret = is_file_hugepages(sfd->file);
+ }
+ return ret;
+}
+
+static const struct file_operations shm_file_operations = {
.mmap = shm_mmap,
+ .fsync = shm_fsync,
.release = shm_release,
-#ifndef CONFIG_MMU
- .get_unmapped_area = shmem_get_unmapped_area,
-#endif
+ .get_unmapped_area = shm_get_unmapped_area,
};
static struct vm_operations_struct shm_vm_ops = {
.open = shm_open, /* callback for a new vm-area open */
.close = shm_close, /* callback for when the vm-area is released */
- .nopage = shmem_nopage,
-#if defined(CONFIG_NUMA) && defined(CONFIG_SHMEM)
- .set_policy = shmem_set_policy,
- .get_policy = shmem_get_policy,
+ .fault = shm_fault,
+#if defined(CONFIG_NUMA)
+ .set_policy = shm_set_policy,
+ .get_policy = shm_get_policy,
#endif
};
-static int newseg (struct ipc_namespace *ns, key_t key, int shmflg, size_t size)
+static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
{
+ key_t key = params->key;
+ int shmflg = params->flg;
+ size_t size = params->u.size;
int error;
struct shmid_kernel *shp;
int numpages = (size + PAGE_SIZE -1) >> PAGE_SHIFT;
if (size < SHMMIN || size > ns->shm_ctlmax)
return -EINVAL;
- if (ns->shm_tot + numpages >= ns->shm_ctlall)
+ if (ns->shm_tot + numpages > ns->shm_ctlall)
return -ENOSPC;
shp = ipc_rcu_alloc(sizeof(*shp));
return error;
}
+ sprintf (name, "SYSV%08x", key);
if (shmflg & SHM_HUGETLB) {
- /* hugetlb_zero_setup takes care of mlock user accounting */
- file = hugetlb_zero_setup(size);
+ /* hugetlb_file_setup takes care of mlock user accounting */
+ file = hugetlb_file_setup(name, size);
shp->mlock_user = current->user;
} else {
int acctflag = VM_ACCOUNT;
if ((shmflg & SHM_NORESERVE) &&
sysctl_overcommit_memory != OVERCOMMIT_NEVER)
acctflag = 0;
- sprintf (name, "SYSV%08x", key);
file = shmem_file_setup(name, size, acctflag);
}
error = PTR_ERR(file);
if(id == -1)
goto no_id;
- shp->shm_cprid = current->tgid;
+ shp->shm_cprid = task_tgid_vnr(current);
shp->shm_lprid = 0;
shp->shm_atim = shp->shm_dtim = 0;
shp->shm_ctim = get_seconds();
shp->shm_segsz = size;
shp->shm_nattch = 0;
- shp->id = shm_buildid(ns, id, shp->shm_perm.seq);
+ shp->shm_perm.id = shm_buildid(ns, id, shp->shm_perm.seq);
shp->shm_file = file;
- file->f_dentry->d_inode->i_ino = shp->id;
-
- shm_file_ns(file) = get_ipc_ns(ns);
-
- /* Hugetlb ops would have already been assigned. */
- if (!(shmflg & SHM_HUGETLB))
- file->f_op = &shm_file_operations;
+ /*
+ * shmid gets reported as "inode#" in /proc/pid/maps.
+ * proc-ps tools use this. Changing this will break them.
+ */
+ file->f_dentry->d_inode->i_ino = shp->shm_perm.id;
ns->shm_tot += numpages;
+ error = shp->shm_perm.id;
shm_unlock(shp);
- return shp->id;
+ return error;
no_id:
fput(file);
return error;
}
+static inline int shm_security(void *shp, int shmflg)
+{
+ return security_shm_associate((struct shmid_kernel *) shp, shmflg);
+}
+
+static inline int shm_more_checks(void *shp, struct ipc_params *params)
+{
+ if (((struct shmid_kernel *)shp)->shm_segsz < params->u.size)
+ return -EINVAL;
+
+ return 0;
+}
+
asmlinkage long sys_shmget (key_t key, size_t size, int shmflg)
{
- struct shmid_kernel *shp;
- int err, id = 0;
struct ipc_namespace *ns;
+ struct ipc_ops shm_ops;
+ struct ipc_params shm_params;
ns = current->nsproxy->ipc_ns;
- mutex_lock(&shm_ids(ns).mutex);
- if (key == IPC_PRIVATE) {
- err = newseg(ns, key, shmflg, size);
- } else if ((id = ipc_findkey(&shm_ids(ns), key)) == -1) {
- if (!(shmflg & IPC_CREAT))
- err = -ENOENT;
- else
- err = newseg(ns, key, shmflg, size);
- } else if ((shmflg & IPC_CREAT) && (shmflg & IPC_EXCL)) {
- err = -EEXIST;
- } else {
- shp = shm_lock(ns, id);
- BUG_ON(shp==NULL);
- if (shp->shm_segsz < size)
- err = -EINVAL;
- else if (ipcperms(&shp->shm_perm, shmflg))
- err = -EACCES;
- else {
- int shmid = shm_buildid(ns, id, shp->shm_perm.seq);
- err = security_shm_associate(shp, shmflg);
- if (!err)
- err = shmid;
- }
- shm_unlock(shp);
- }
- mutex_unlock(&shm_ids(ns).mutex);
+ shm_ops.getnew = newseg;
+ shm_ops.associate = shm_security;
+ shm_ops.more_checks = shm_more_checks;
- return err;
+ shm_params.key = key;
+ shm_params.flg = shmflg;
+ shm_params.u.size = size;
+
+ return ipcget(ns, &shm_ids(ns), &shm_ops, &shm_params);
}
static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_ds *in, int version)
static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
unsigned long *swp)
{
- int i;
+ int next_id;
+ int total, in_use;
*rss = 0;
*swp = 0;
- for (i = 0; i <= shm_ids(ns).max_id; i++) {
+ in_use = shm_ids(ns).in_use;
+
+ for (total = 0, next_id = 0; total < in_use; next_id++) {
struct shmid_kernel *shp;
struct inode *inode;
- shp = shm_get(ns, i);
- if(!shp)
+ shp = shm_get(ns, next_id);
+ if (shp == NULL)
continue;
- inode = shp->shm_file->f_dentry->d_inode;
+ inode = shp->shm_file->f_path.dentry->d_inode;
if (is_file_hugepages(shp->shm_file)) {
struct address_space *mapping = inode->i_mapping;
*swp += info->swapped;
spin_unlock(&info->lock);
}
+
+ total++;
}
}
if(copy_shminfo_to_user (buf, &shminfo, version))
return -EFAULT;
/* reading a integer is always atomic */
- err= shm_ids(ns).max_id;
+ err = ipc_get_maxid(&shm_ids(ns));
if(err<0)
err = 0;
goto out;
shm_info.shm_tot = ns->shm_tot;
shm_info.swap_attempts = 0;
shm_info.swap_successes = 0;
- err = shm_ids(ns).max_id;
+ err = ipc_get_maxid(&shm_ids(ns));
mutex_unlock(&shm_ids(ns).mutex);
if(copy_to_user (buf, &shm_info, sizeof(shm_info))) {
err = -EFAULT;
if(shp==NULL) {
err = -EINVAL;
goto out;
- } else if(cmd==SHM_STAT) {
- err = -EINVAL;
- if (shmid > shm_ids(ns).max_id)
- goto out_unlock;
- result = shm_buildid(ns, shmid, shp->shm_perm.seq);
+ } else if (cmd == SHM_STAT) {
+ result = shp->shm_perm.id;
} else {
err = shm_checkid(ns, shp,shmid);
if(err)
tbuf.shm_ctime = shp->shm_ctim;
tbuf.shm_cpid = shp->shm_cprid;
tbuf.shm_lpid = shp->shm_lprid;
- if (!is_file_hugepages(shp->shm_file))
- tbuf.shm_nattch = shp->shm_nattch;
- else
- tbuf.shm_nattch = file_count(shp->shm_file) - 1;
+ tbuf.shm_nattch = shp->shm_nattch;
shm_unlock(shp);
if(copy_shmid_to_user (buf, &tbuf, version))
err = -EFAULT;
struct user_struct * user = current->user;
if (!is_file_hugepages(shp->shm_file)) {
err = shmem_lock(shp->shm_file, 1, user);
- if (!err) {
+ if (!err && !(shp->shm_perm.mode & SHM_LOCKED)){
shp->shm_perm.mode |= SHM_LOCKED;
shp->mlock_user = user;
}
unsigned long flags;
unsigned long prot;
int acc_mode;
- void *user_addr;
+ unsigned long user_addr;
struct ipc_namespace *ns;
+ struct shm_file_data *sfd;
+ struct path path;
+ mode_t f_mode;
- if (shmid < 0) {
- err = -EINVAL;
+ err = -EINVAL;
+ if (shmid < 0)
goto out;
- } else if ((addr = (ulong)shmaddr)) {
+ else if ((addr = (ulong)shmaddr)) {
if (addr & (SHMLBA-1)) {
if (shmflg & SHM_RND)
addr &= ~(SHMLBA-1); /* round down */
#ifndef __ARCH_FORCE_SHMLBA
if (addr & ~PAGE_MASK)
#endif
- return -EINVAL;
+ goto out;
}
flags = MAP_SHARED | MAP_FIXED;
} else {
if ((shmflg & SHM_REMAP))
- return -EINVAL;
+ goto out;
flags = MAP_SHARED;
}
if (shmflg & SHM_RDONLY) {
prot = PROT_READ;
acc_mode = S_IRUGO;
+ f_mode = FMODE_READ;
} else {
prot = PROT_READ | PROT_WRITE;
acc_mode = S_IRUGO | S_IWUGO;
+ f_mode = FMODE_READ | FMODE_WRITE;
}
if (shmflg & SHM_EXEC) {
prot |= PROT_EXEC;
*/
ns = current->nsproxy->ipc_ns;
shp = shm_lock(ns, shmid);
- if(shp == NULL) {
- err = -EINVAL;
+ if(shp == NULL)
goto out;
- }
+
err = shm_checkid(ns, shp,shmid);
- if (err) {
- shm_unlock(shp);
- goto out;
- }
- if (ipcperms(&shp->shm_perm, acc_mode)) {
- shm_unlock(shp);
- err = -EACCES;
- goto out;
- }
+ if (err)
+ goto out_unlock;
+
+ err = -EACCES;
+ if (ipcperms(&shp->shm_perm, acc_mode))
+ goto out_unlock;
err = security_shm_shmat(shp, shmaddr, shmflg);
- if (err) {
- shm_unlock(shp);
- return err;
- }
-
- file = shp->shm_file;
- size = i_size_read(file->f_dentry->d_inode);
+ if (err)
+ goto out_unlock;
+
+ path.dentry = dget(shp->shm_file->f_path.dentry);
+ path.mnt = shp->shm_file->f_path.mnt;
shp->shm_nattch++;
+ size = i_size_read(path.dentry->d_inode);
shm_unlock(shp);
+ err = -ENOMEM;
+ sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
+ 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;
+
+ file->private_data = sfd;
+ file->f_mapping = shp->shm_file->f_mapping;
+ sfd->id = shp->shm_perm.id;
+ sfd->ns = get_ipc_ns(ns);
+ sfd->file = shp->shm_file;
+ sfd->vm_ops = NULL;
+
down_write(¤t->mm->mmap_sem);
if (addr && !(shmflg & SHM_REMAP)) {
- user_addr = ERR_PTR(-EINVAL);
+ err = -EINVAL;
if (find_vma_intersection(current->mm, addr, addr + size))
goto invalid;
/*
goto invalid;
}
- user_addr = (void*) do_mmap (file, addr, size, prot, flags, 0);
-
+ user_addr = do_mmap (file, addr, size, prot, flags, 0);
+ *raddr = user_addr;
+ err = 0;
+ if (IS_ERR_VALUE(user_addr))
+ err = (long)user_addr;
invalid:
up_write(¤t->mm->mmap_sem);
+ fput(file);
+
+out_nattch:
mutex_lock(&shm_ids(ns).mutex);
shp = shm_lock(ns, shmid);
BUG_ON(!shp);
shm_unlock(shp);
mutex_unlock(&shm_ids(ns).mutex);
- *raddr = (unsigned long) user_addr;
- err = 0;
- if (IS_ERR(user_addr))
- err = PTR_ERR(user_addr);
out:
return err;
+
+out_unlock:
+ shm_unlock(shp);
+ goto out;
+
+out_free:
+ kfree(sfd);
+out_put_dentry:
+ dput(path.dentry);
+ goto out_nattch;
}
asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg)
* a fragment created by mprotect() and/or munmap(), or it
* otherwise it starts at this address with no hassles.
*/
- if ((vma->vm_ops == &shm_vm_ops || is_vm_hugetlb_page(vma)) &&
+ if ((vma->vm_ops == &shm_vm_ops) &&
(vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff) {
- size = vma->vm_file->f_dentry->d_inode->i_size;
+ size = vma->vm_file->f_path.dentry->d_inode->i_size;
do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
/*
* We discovered the size of the shm segment, so
next = vma->vm_next;
/* finding a matching vma now does not alter retval */
- if ((vma->vm_ops == &shm_vm_ops || is_vm_hugetlb_page(vma)) &&
+ if ((vma->vm_ops == &shm_vm_ops) &&
(vma->vm_start - addr)/PAGE_SIZE == vma->vm_pgoff)
do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start);
format = BIG_STRING;
return seq_printf(s, format,
shp->shm_perm.key,
- shp->id,
+ shp->shm_perm.id,
shp->shm_perm.mode,
shp->shm_segsz,
shp->shm_cprid,
shp->shm_lprid,
- is_file_hugepages(shp->shm_file) ? (file_count(shp->shm_file) - 1) : shp->shm_nattch,
+ shp->shm_nattch,
shp->shm_perm.uid,
shp->shm_perm.gid,
shp->shm_perm.cuid,
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff