X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=ipc%2Fshm.c;h=464694e0aa4a19c74b973a2a69f0d88049b9c512;hb=57ecb34febc4c133ca0ccc7817796605a78a01d3;hp=3e4aff982546f96c078f229cee9a3108337b766c;hpb=48dea404ed01869313f1908cca8a15774dcd8ee5;p=safe%2Fjmp%2Flinux-2.6 diff --git a/ipc/shm.c b/ipc/shm.c index 3e4aff9..464694e 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -39,6 +39,7 @@ #include #include #include +#include #include @@ -54,7 +55,7 @@ struct shm_file_data { #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 const struct vm_operations_struct shm_vm_ops; #define shm_ids(ns) ((ns)->ids[IPC_SHM_IDS]) @@ -75,7 +76,7 @@ void shm_init_ns(struct ipc_namespace *ns) ns->shm_ctlall = SHMALL; ns->shm_ctlmni = SHMMNI; ns->shm_tot = 0; - ipc_init_ids(&ns->ids[IPC_SHM_IDS]); + ipc_init_ids(&shm_ids(ns)); } /* @@ -112,35 +113,8 @@ void __init shm_init (void) } /* - * 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); -} - -static inline struct shmid_kernel *shm_lock_check_down( - struct ipc_namespace *ns, - int id) -{ - struct kern_ipc_perm *ipcp = ipc_lock_check_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. + * is not necessarily held. */ static inline struct shmid_kernel *shm_lock(struct ipc_namespace *ns, int id) { @@ -200,7 +174,7 @@ static void shm_destroy(struct ipc_namespace *ns, struct shmid_kernel *shp) shm_unlock(shp); if (!is_file_hugepages(shp->shm_file)) shmem_lock(shp->shm_file, 0, shp->mlock_user); - else + else if (shp->mlock_user) user_shm_unlock(shp->shm_file->f_path.dentry->d_inode->i_size, shp->mlock_user); fput (shp->shm_file); @@ -223,7 +197,7 @@ static void shm_close(struct vm_area_struct *vma) down_write(&shm_ids(ns).rw_mutex); /* remove from the list of attaches of the shm segment */ - shp = shm_lock_down(ns, sfd->id); + shp = shm_lock(ns, sfd->id); BUG_ON(IS_ERR(shp)); shp->shm_lprid = task_tgid_vnr(current); shp->shm_dtim = get_seconds(); @@ -338,7 +312,7 @@ static const struct file_operations shm_file_operations = { .get_unmapped_area = shm_get_unmapped_area, }; -static struct vm_operations_struct shm_vm_ops = { +static const 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 */ .fault = shm_fault, @@ -367,6 +341,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) struct file * file; char name[13]; int id; + int acctflag = 0; if (size < SHMMIN || size > ns->shm_ctlmax) return -EINVAL; @@ -391,18 +366,19 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) sprintf (name, "SYSV%08x", key); if (shmflg & SHM_HUGETLB) { - /* hugetlb_file_setup takes care of mlock user accounting */ - file = hugetlb_file_setup(name, size); - shp->mlock_user = current->user; + /* hugetlb_file_setup applies strict accounting */ + if (shmflg & SHM_NORESERVE) + acctflag = VM_NORESERVE; + file = hugetlb_file_setup(name, size, acctflag, + &shp->mlock_user, HUGETLB_SHMFS_INODE); } else { - int acctflag = VM_ACCOUNT; /* * Do not allow no accounting for OVERCOMMIT_NEVER, even * if it's asked for. */ if ((shmflg & SHM_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER) - acctflag = 0; + acctflag = VM_NORESERVE; file = shmem_file_setup(name, size, acctflag); } error = PTR_ERR(file); @@ -434,6 +410,8 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) return error; no_id: + if (is_file_hugepages(file) && shp->mlock_user) + user_shm_unlock(size, shp->mlock_user); fput(file); no_file: security_shm_free(shp); @@ -467,7 +445,7 @@ static inline int shm_more_checks(struct kern_ipc_perm *ipcp, return 0; } -asmlinkage long sys_shmget (key_t key, size_t size, int shmflg) +SYSCALL_DEFINE3(shmget, key_t, key, size_t, size, int, shmflg) { struct ipc_namespace *ns; struct ipc_ops shm_ops; @@ -511,28 +489,14 @@ static inline unsigned long copy_shmid_to_user(void __user *buf, struct shmid64_ } } -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; @@ -540,9 +504,9 @@ static inline unsigned long copy_shmid_from_user(struct shm_setbuf *out, void __ 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; } @@ -592,33 +556,84 @@ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss, in_use = shm_ids(ns).in_use; for (total = 0, next_id = 0; total < in_use; next_id++) { + struct kern_ipc_perm *ipc; struct shmid_kernel *shp; struct inode *inode; - shp = idr_find(&shm_ids(ns).ipcs_idr, next_id); - if (shp == NULL) + ipc = idr_find(&shm_ids(ns).ipcs_idr, next_id); + if (ipc == NULL) continue; + shp = container_of(ipc, struct shmid_kernel, shm_perm); inode = shp->shm_file->f_path.dentry->d_inode; 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 { +#ifdef CONFIG_SHMEM struct shmem_inode_info *info = SHMEM_I(inode); spin_lock(&info->lock); *rss += inode->i_mapping->nrpages; *swp += info->swapped; spin_unlock(&info->lock); +#else + *rss += inode->i_mapping->nrpages; +#endif } total++; } } -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; +} + +SYSCALL_DEFINE3(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; @@ -640,7 +655,7 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) if (err) return err; - memset(&shminfo,0,sizeof(shminfo)); + memset(&shminfo, 0, sizeof(shminfo)); shminfo.shmmni = shminfo.shmseg = ns->shm_ctlmni; shminfo.shmmax = ns->shm_ctlmax; shminfo.shmall = ns->shm_ctlall; @@ -665,7 +680,7 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) if (err) return err; - memset(&shm_info,0,sizeof(shm_info)); + memset(&shm_info, 0, sizeof(shm_info)); 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); @@ -674,7 +689,7 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) shm_info.swap_successes = 0; err = ipc_get_maxid(&shm_ids(ns)); up_read(&shm_ids(ns).rw_mutex); - if(copy_to_user (buf, &shm_info, sizeof(shm_info))) { + if (copy_to_user(buf, &shm_info, sizeof(shm_info))) { err = -EFAULT; goto out; } @@ -688,11 +703,6 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) struct shmid64_ds tbuf; int result; - if (!buf) { - err = -EFAULT; - goto out; - } - if (cmd == SHM_STAT) { shp = shm_lock(ns, shmid); if (IS_ERR(shp)) { @@ -708,7 +718,7 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) } result = 0; } - err=-EACCES; + err = -EACCES; if (ipcperms (&shp->shm_perm, S_IRUGO)) goto out_unlock; err = security_shm_shmctl(shp, cmd); @@ -733,20 +743,23 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) case SHM_LOCK: case SHM_UNLOCK: { + struct file *uninitialized_var(shm_file); + + lru_add_drain_all(); /* drain pagevecs to lru lists */ + shp = shm_lock_check(ns, shmid); if (IS_ERR(shp)) { err = PTR_ERR(shp); goto out; } - err = audit_ipc_obj(&(shp->shm_perm)); - if (err) - goto out_unlock; + audit_ipc_obj(&(shp->shm_perm)); if (!capable(CAP_IPC_LOCK)) { + uid_t euid = current_euid(); err = -EPERM; - if (current->euid != shp->shm_perm.uid && - current->euid != shp->shm_perm.cuid) + if (euid != shp->shm_perm.uid && + euid != shp->shm_perm.cuid) goto out_unlock; if (cmd == SHM_LOCK && !current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur) @@ -758,7 +771,7 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) goto out_unlock; if(cmd==SHM_LOCK) { - struct user_struct * user = current->user; + struct user_struct *user = current_user(); if (!is_file_hugepages(shp->shm_file)) { err = shmem_lock(shp->shm_file, 1, user); if (!err && !(shp->shm_perm.mode & SHM_LOCKED)){ @@ -775,97 +788,13 @@ asmlinkage long sys_shmctl (int shmid, int cmd, struct shmid_ds __user *buf) 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. - */ - down_write(&shm_ids(ns).rw_mutex); - shp = shm_lock_check_down(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->shm_perm); - up_write(&shm_ids(ns).rw_mutex); - goto out; - } - case IPC_SET: - { - if (!buf) { - err = -EFAULT; - goto out; - } - - if (copy_shmid_from_user (&setbuf, buf, version)) { - err = -EFAULT; - goto out; - } - down_write(&shm_ids(ns).rw_mutex); - shp = shm_lock_check_down(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: - up_write(&shm_ids(ns).rw_mutex); - goto out; out_unlock: shm_unlock(shp); out: @@ -893,7 +822,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr) struct ipc_namespace *ns; struct shm_file_data *sfd; struct path path; - mode_t f_mode; + fmode_t f_mode; err = -EINVAL; if (shmid < 0) @@ -960,11 +889,10 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr) 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; + ima_counts_get(file); file->private_data = sfd; file->f_mapping = shp->shm_file->f_mapping; @@ -999,7 +927,7 @@ invalid: out_nattch: down_write(&shm_ids(ns).rw_mutex); - shp = shm_lock_down(ns, shmid); + shp = shm_lock(ns, shmid); BUG_ON(IS_ERR(shp)); shp->shm_nattch--; if(shp->shm_nattch == 0 && @@ -1023,7 +951,7 @@ out_put_dentry: goto out_nattch; } -asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg) +SYSCALL_DEFINE3(shmat, int, shmid, char __user *, shmaddr, int, shmflg) { unsigned long ret; long err; @@ -1039,13 +967,16 @@ asmlinkage long sys_shmat(int shmid, char __user *shmaddr, int shmflg) * detach and kill segment if marked destroyed. * The work is done in shm_close. */ -asmlinkage long sys_shmdt(char __user *shmaddr) +SYSCALL_DEFINE1(shmdt, char __user *, shmaddr) { struct mm_struct *mm = current->mm; - struct vm_area_struct *vma, *next; + struct vm_area_struct *vma; unsigned long addr = (unsigned long)shmaddr; - loff_t size = 0; int retval = -EINVAL; +#ifdef CONFIG_MMU + loff_t size = 0; + struct vm_area_struct *next; +#endif if (addr & ~PAGE_MASK) return retval; @@ -1074,6 +1005,7 @@ asmlinkage long sys_shmdt(char __user *shmaddr) */ vma = find_vma(mm, addr); +#ifdef CONFIG_MMU while (vma) { next = vma->vm_next; @@ -1118,6 +1050,17 @@ asmlinkage long sys_shmdt(char __user *shmaddr) vma = next; } +#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) { + do_munmap(mm, vma->vm_start, vma->vm_end - vma->vm_start); + retval = 0; + } + +#endif + up_write(&mm->mmap_sem); return retval; } @@ -1126,16 +1069,16 @@ asmlinkage long sys_shmdt(char __user *shmaddr) 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,