diff options
Diffstat (limited to 'fs/proc/base.c')
| -rw-r--r-- | fs/proc/base.c | 2056 |
1 files changed, 2056 insertions, 0 deletions
diff --git a/fs/proc/base.c b/fs/proc/base.c new file mode 100644 index 00000000000..dad8ea4e00a --- /dev/null +++ b/fs/proc/base.c @@ -0,0 +1,2056 @@ +/* + * linux/fs/proc/base.c + * + * Copyright (C) 1991, 1992 Linus Torvalds + * + * proc base directory handling functions + * + * 1999, Al Viro. Rewritten. Now it covers the whole per-process part. + * Instead of using magical inumbers to determine the kind of object + * we allocate and fill in-core inodes upon lookup. They don't even + * go into icache. We cache the reference to task_struct upon lookup too. + * Eventually it should become a filesystem in its own. We don't use the + * rest of procfs anymore. + */ + +#include <asm/uaccess.h> + +#include <linux/config.h> +#include <linux/errno.h> +#include <linux/time.h> +#include <linux/proc_fs.h> +#include <linux/stat.h> +#include <linux/init.h> +#include <linux/file.h> +#include <linux/string.h> +#include <linux/seq_file.h> +#include <linux/namei.h> +#include <linux/namespace.h> +#include <linux/mm.h> +#include <linux/smp_lock.h> +#include <linux/kallsyms.h> +#include <linux/mount.h> +#include <linux/security.h> +#include <linux/ptrace.h> +#include <linux/seccomp.h> +#include <linux/cpuset.h> +#include <linux/audit.h> +#include "internal.h" + +/* + * For hysterical raisins we keep the same inumbers as in the old procfs. + * Feel free to change the macro below - just keep the range distinct from + * inumbers of the rest of procfs (currently those are in 0x0000--0xffff). + * As soon as we'll get a separate superblock we will be able to forget + * about magical ranges too. + */ + +#define fake_ino(pid,ino) (((pid)<<16)|(ino)) + +enum pid_directory_inos { + PROC_TGID_INO = 2, + PROC_TGID_TASK, + PROC_TGID_STATUS, + PROC_TGID_MEM, +#ifdef CONFIG_SECCOMP + PROC_TGID_SECCOMP, +#endif + PROC_TGID_CWD, + PROC_TGID_ROOT, + PROC_TGID_EXE, + PROC_TGID_FD, + PROC_TGID_ENVIRON, + PROC_TGID_AUXV, + PROC_TGID_CMDLINE, + PROC_TGID_STAT, + PROC_TGID_STATM, + PROC_TGID_MAPS, + PROC_TGID_MOUNTS, + PROC_TGID_WCHAN, +#ifdef CONFIG_SCHEDSTATS + PROC_TGID_SCHEDSTAT, +#endif +#ifdef CONFIG_CPUSETS + PROC_TGID_CPUSET, +#endif +#ifdef CONFIG_SECURITY + PROC_TGID_ATTR, + PROC_TGID_ATTR_CURRENT, + PROC_TGID_ATTR_PREV, + PROC_TGID_ATTR_EXEC, + PROC_TGID_ATTR_FSCREATE, +#endif +#ifdef CONFIG_AUDITSYSCALL + PROC_TGID_LOGINUID, +#endif + PROC_TGID_FD_DIR, + PROC_TGID_OOM_SCORE, + PROC_TGID_OOM_ADJUST, + PROC_TID_INO, + PROC_TID_STATUS, + PROC_TID_MEM, +#ifdef CONFIG_SECCOMP + PROC_TID_SECCOMP, +#endif + PROC_TID_CWD, + PROC_TID_ROOT, + PROC_TID_EXE, + PROC_TID_FD, + PROC_TID_ENVIRON, + PROC_TID_AUXV, + PROC_TID_CMDLINE, + PROC_TID_STAT, + PROC_TID_STATM, + PROC_TID_MAPS, + PROC_TID_MOUNTS, + PROC_TID_WCHAN, +#ifdef CONFIG_SCHEDSTATS + PROC_TID_SCHEDSTAT, +#endif +#ifdef CONFIG_CPUSETS + PROC_TID_CPUSET, +#endif +#ifdef CONFIG_SECURITY + PROC_TID_ATTR, + PROC_TID_ATTR_CURRENT, + PROC_TID_ATTR_PREV, + PROC_TID_ATTR_EXEC, + PROC_TID_ATTR_FSCREATE, +#endif +#ifdef CONFIG_AUDITSYSCALL + PROC_TID_LOGINUID, +#endif + PROC_TID_FD_DIR = 0x8000, /* 0x8000-0xffff */ + PROC_TID_OOM_SCORE, + PROC_TID_OOM_ADJUST, +}; + +struct pid_entry { + int type; + int len; + char *name; + mode_t mode; +}; + +#define E(type,name,mode) {(type),sizeof(name)-1,(name),(mode)} + +static struct pid_entry tgid_base_stuff[] = { + E(PROC_TGID_TASK, "task", S_IFDIR|S_IRUGO|S_IXUGO), + E(PROC_TGID_FD, "fd", S_IFDIR|S_IRUSR|S_IXUSR), + E(PROC_TGID_ENVIRON, "environ", S_IFREG|S_IRUSR), + E(PROC_TGID_AUXV, "auxv", S_IFREG|S_IRUSR), + E(PROC_TGID_STATUS, "status", S_IFREG|S_IRUGO), + E(PROC_TGID_CMDLINE, "cmdline", S_IFREG|S_IRUGO), + E(PROC_TGID_STAT, "stat", S_IFREG|S_IRUGO), + E(PROC_TGID_STATM, "statm", S_IFREG|S_IRUGO), + E(PROC_TGID_MAPS, "maps", S_IFREG|S_IRUGO), + E(PROC_TGID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR), +#ifdef CONFIG_SECCOMP + E(PROC_TGID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR), +#endif + E(PROC_TGID_CWD, "cwd", S_IFLNK|S_IRWXUGO), + E(PROC_TGID_ROOT, "root", S_IFLNK|S_IRWXUGO), + E(PROC_TGID_EXE, "exe", S_IFLNK|S_IRWXUGO), + E(PROC_TGID_MOUNTS, "mounts", S_IFREG|S_IRUGO), +#ifdef CONFIG_SECURITY + E(PROC_TGID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), +#endif +#ifdef CONFIG_KALLSYMS + E(PROC_TGID_WCHAN, "wchan", S_IFREG|S_IRUGO), +#endif +#ifdef CONFIG_SCHEDSTATS + E(PROC_TGID_SCHEDSTAT, "schedstat", S_IFREG|S_IRUGO), +#endif +#ifdef CONFIG_CPUSETS + E(PROC_TGID_CPUSET, "cpuset", S_IFREG|S_IRUGO), +#endif + E(PROC_TGID_OOM_SCORE, "oom_score",S_IFREG|S_IRUGO), + E(PROC_TGID_OOM_ADJUST,"oom_adj", S_IFREG|S_IRUGO|S_IWUSR), +#ifdef CONFIG_AUDITSYSCALL + E(PROC_TGID_LOGINUID, "loginuid", S_IFREG|S_IWUSR|S_IRUGO), +#endif + {0,0,NULL,0} +}; +static struct pid_entry tid_base_stuff[] = { + E(PROC_TID_FD, "fd", S_IFDIR|S_IRUSR|S_IXUSR), + E(PROC_TID_ENVIRON, "environ", S_IFREG|S_IRUSR), + E(PROC_TID_AUXV, "auxv", S_IFREG|S_IRUSR), + E(PROC_TID_STATUS, "status", S_IFREG|S_IRUGO), + E(PROC_TID_CMDLINE, "cmdline", S_IFREG|S_IRUGO), + E(PROC_TID_STAT, "stat", S_IFREG|S_IRUGO), + E(PROC_TID_STATM, "statm", S_IFREG|S_IRUGO), + E(PROC_TID_MAPS, "maps", S_IFREG|S_IRUGO), + E(PROC_TID_MEM, "mem", S_IFREG|S_IRUSR|S_IWUSR), +#ifdef CONFIG_SECCOMP + E(PROC_TID_SECCOMP, "seccomp", S_IFREG|S_IRUSR|S_IWUSR), +#endif + E(PROC_TID_CWD, "cwd", S_IFLNK|S_IRWXUGO), + E(PROC_TID_ROOT, "root", S_IFLNK|S_IRWXUGO), + E(PROC_TID_EXE, "exe", S_IFLNK|S_IRWXUGO), + E(PROC_TID_MOUNTS, "mounts", S_IFREG|S_IRUGO), +#ifdef CONFIG_SECURITY + E(PROC_TID_ATTR, "attr", S_IFDIR|S_IRUGO|S_IXUGO), +#endif +#ifdef CONFIG_KALLSYMS + E(PROC_TID_WCHAN, "wchan", S_IFREG|S_IRUGO), +#endif +#ifdef CONFIG_SCHEDSTATS + E(PROC_TID_SCHEDSTAT, "schedstat",S_IFREG|S_IRUGO), +#endif +#ifdef CONFIG_CPUSETS + E(PROC_TID_CPUSET, "cpuset", S_IFREG|S_IRUGO), +#endif + E(PROC_TID_OOM_SCORE, "oom_score",S_IFREG|S_IRUGO), + E(PROC_TID_OOM_ADJUST, "oom_adj", S_IFREG|S_IRUGO|S_IWUSR), +#ifdef CONFIG_AUDITSYSCALL + E(PROC_TID_LOGINUID, "loginuid", S_IFREG|S_IWUSR|S_IRUGO), +#endif + {0,0,NULL,0} +}; + +#ifdef CONFIG_SECURITY +static struct pid_entry tgid_attr_stuff[] = { + E(PROC_TGID_ATTR_CURRENT, "current", S_IFREG|S_IRUGO|S_IWUGO), + E(PROC_TGID_ATTR_PREV, "prev", S_IFREG|S_IRUGO), + E(PROC_TGID_ATTR_EXEC, "exec", S_IFREG|S_IRUGO|S_IWUGO), + E(PROC_TGID_ATTR_FSCREATE, "fscreate", S_IFREG|S_IRUGO|S_IWUGO), + {0,0,NULL,0} +}; +static struct pid_entry tid_attr_stuff[] = { + E(PROC_TID_ATTR_CURRENT, "current", S_IFREG|S_IRUGO|S_IWUGO), + E(PROC_TID_ATTR_PREV, "prev", S_IFREG|S_IRUGO), + E(PROC_TID_ATTR_EXEC, "exec", S_IFREG|S_IRUGO|S_IWUGO), + E(PROC_TID_ATTR_FSCREATE, "fscreate", S_IFREG|S_IRUGO|S_IWUGO), + {0,0,NULL,0} +}; +#endif + +#undef E + +static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +{ + struct task_struct *task = proc_task(inode); + struct files_struct *files; + struct file *file; + int fd = proc_type(inode) - PROC_TID_FD_DIR; + + files = get_files_struct(task); + if (files) { + spin_lock(&files->file_lock); + file = fcheck_files(files, fd); + if (file) { + *mnt = mntget(file->f_vfsmnt); + *dentry = dget(file->f_dentry); + spin_unlock(&files->file_lock); + put_files_struct(files); + return 0; + } + spin_unlock(&files->file_lock); + put_files_struct(files); + } + return -ENOENT; +} + +static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +{ + struct fs_struct *fs; + int result = -ENOENT; + task_lock(proc_task(inode)); + fs = proc_task(inode)->fs; + if(fs) + atomic_inc(&fs->count); + task_unlock(proc_task(inode)); + if (fs) { + read_lock(&fs->lock); + *mnt = mntget(fs->pwdmnt); + *dentry = dget(fs->pwd); + read_unlock(&fs->lock); + result = 0; + put_fs_struct(fs); + } + return result; +} + +static int proc_root_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +{ + struct fs_struct *fs; + int result = -ENOENT; + task_lock(proc_task(inode)); + fs = proc_task(inode)->fs; + if(fs) + atomic_inc(&fs->count); + task_unlock(proc_task(inode)); + if (fs) { + read_lock(&fs->lock); + *mnt = mntget(fs->rootmnt); + *dentry = dget(fs->root); + read_unlock(&fs->lock); + result = 0; + put_fs_struct(fs); + } + return result; +} + +#define MAY_PTRACE(task) \ + (task == current || \ + (task->parent == current && \ + (task->ptrace & PT_PTRACED) && \ + (task->state == TASK_STOPPED || task->state == TASK_TRACED) && \ + security_ptrace(current,task) == 0)) + +static int may_ptrace_attach(struct task_struct *task) +{ + int retval = 0; + + task_lock(task); + + if (!task->mm) + goto out; + if (((current->uid != task->euid) || + (current->uid != task->suid) || + (current->uid != task->uid) || + (current->gid != task->egid) || + (current->gid != task->sgid) || + (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE)) + goto out; + rmb(); + if (!task->mm->dumpable && !capable(CAP_SYS_PTRACE)) + goto out; + if (security_ptrace(current, task)) + goto out; + + retval = 1; +out: + task_unlock(task); + return retval; +} + +static int proc_pid_environ(struct task_struct *task, char * buffer) +{ + int res = 0; + struct mm_struct *mm = get_task_mm(task); + if (mm) { + unsigned int len = mm->env_end - mm->env_start; + if (len > PAGE_SIZE) + len = PAGE_SIZE; + res = access_process_vm(task, mm->env_start, buffer, len, 0); + if (!may_ptrace_attach(task)) + res = -ESRCH; + mmput(mm); + } + return res; +} + +static int proc_pid_cmdline(struct task_struct *task, char * buffer) +{ + int res = 0; + unsigned int len; + struct mm_struct *mm = get_task_mm(task); + if (!mm) + goto out; + if (!mm->arg_end) + goto out_mm; /* Shh! No looking before we're done */ + + len = mm->arg_end - mm->arg_start; + + if (len > PAGE_SIZE) + len = PAGE_SIZE; + + res = access_process_vm(task, mm->arg_start, buffer, len, 0); + + // If the nul at the end of args has been overwritten, then + // assume application is using setproctitle(3). + if (res > 0 && buffer[res-1] != '\0' && len < PAGE_SIZE) { + len = strnlen(buffer, res); + if (len < res) { + res = len; + } else { + len = mm->env_end - mm->env_start; + if (len > PAGE_SIZE - res) + len = PAGE_SIZE - res; + res += access_process_vm(task, mm->env_start, buffer+res, len, 0); + res = strnlen(buffer, res); + } + } +out_mm: + mmput(mm); +out: + return res; +} + +static int proc_pid_auxv(struct task_struct *task, char *buffer) +{ + int res = 0; + struct mm_struct *mm = get_task_mm(task); + if (mm) { + unsigned int nwords = 0; + do + nwords += 2; + while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */ + res = nwords * sizeof(mm->saved_auxv[0]); + if (res > PAGE_SIZE) + res = PAGE_SIZE; + memcpy(buffer, mm->saved_auxv, res); + mmput(mm); + } + return res; +} + + +#ifdef CONFIG_KALLSYMS +/* + * Provides a wchan file via kallsyms in a proper one-value-per-file format. + * Returns the resolved symbol. If that fails, simply return the address. + */ +static int proc_pid_wchan(struct task_struct *task, char *buffer) +{ + char *modname; + const char *sym_name; + unsigned long wchan, size, offset; + char namebuf[KSYM_NAME_LEN+1]; + + wchan = get_wchan(task); + + sym_name = kallsyms_lookup(wchan, &size, &offset, &modname, namebuf); + if (sym_name) + return sprintf(buffer, "%s", sym_name); + return sprintf(buffer, "%lu", wchan); +} +#endif /* CONFIG_KALLSYMS */ + +#ifdef CONFIG_SCHEDSTATS +/* + * Provides /proc/PID/schedstat + */ +static int proc_pid_schedstat(struct task_struct *task, char *buffer) +{ + return sprintf(buffer, "%lu %lu %lu\n", + task->sched_info.cpu_time, + task->sched_info.run_delay, + task->sched_info.pcnt); +} +#endif + +/* The badness from the OOM killer */ +unsigned long badness(struct task_struct *p, unsigned long uptime); +static int proc_oom_score(struct task_struct *task, char *buffer) +{ + unsigned long points; + struct timespec uptime; + + do_posix_clock_monotonic_gettime(&uptime); + points = badness(task, uptime.tv_sec); + return sprintf(buffer, "%lu\n", points); +} + +/************************************************************************/ +/* Here the fs part begins */ +/************************************************************************/ + +/* permission checks */ + +static int proc_check_root(struct inode *inode) +{ + struct dentry *de, *base, *root; + struct vfsmount *our_vfsmnt, *vfsmnt, *mnt; + int res = 0; + + if (proc_root_link(inode, &root, &vfsmnt)) /* Ewww... */ + return -ENOENT; + read_lock(¤t->fs->lock); + our_vfsmnt = mntget(current->fs->rootmnt); + base = dget(current->fs->root); + read_unlock(¤t->fs->lock); + + spin_lock(&vfsmount_lock); + de = root; + mnt = vfsmnt; + + while (vfsmnt != our_vfsmnt) { + if (vfsmnt == vfsmnt->mnt_parent) + goto out; + de = vfsmnt->mnt_mountpoint; + vfsmnt = vfsmnt->mnt_parent; + } + + if (!is_subdir(de, base)) + goto out; + spin_unlock(&vfsmount_lock); + +exit: + dput(base); + mntput(our_vfsmnt); + dput(root); + mntput(mnt); + return res; +out: + spin_unlock(&vfsmount_lock); + res = -EACCES; + goto exit; +} + +static int proc_permission(struct inode *inode, int mask, struct nameidata *nd) +{ + if (generic_permission(inode, mask, NULL) != 0) + return -EACCES; + return proc_check_root(inode); +} + +extern struct seq_operations proc_pid_maps_op; +static int maps_open(struct inode *inode, struct file *file) +{ + struct task_struct *task = proc_task(inode); + int ret = seq_open(file, &proc_pid_maps_op); + if (!ret) { + struct seq_file *m = file->private_data; + m->private = task; + } + return ret; +} + +static struct file_operations proc_maps_operations = { + .open = maps_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, +}; + +extern struct seq_operations mounts_op; +static int mounts_open(struct inode *inode, struct file *file) +{ + struct task_struct *task = proc_task(inode); + int ret = seq_open(file, &mounts_op); + + if (!ret) { + struct seq_file *m = file->private_data; + struct namespace *namespace; + task_lock(task); + namespace = task->namespace; + if (namespace) + get_namespace(namespace); + task_unlock(task); + + if (namespace) + m->private = namespace; + else { + seq_release(inode, file); + ret = -EINVAL; + } + } + return ret; +} + +static int mounts_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + struct namespace *namespace = m->private; + put_namespace(namespace); + return seq_release(inode, file); +} + +static struct file_operations proc_mounts_operations = { + .open = mounts_open, + .read = seq_read, + .llseek = seq_lseek, + .release = mounts_release, +}; + +#define PROC_BLOCK_SIZE (3*1024) /* 4K page size but our output routines use some slack for overruns */ + +static ssize_t proc_info_read(struct file * file, char __user * buf, + size_t count, loff_t *ppos) +{ + struct inode * inode = file->f_dentry->d_inode; + unsigned long page; + ssize_t length; + struct task_struct *task = proc_task(inode); + + if (count > PROC_BLOCK_SIZE) + count = PROC_BLOCK_SIZE; + if (!(page = __get_free_page(GFP_KERNEL))) + return -ENOMEM; + + length = PROC_I(inode)->op.proc_read(task, (char*)page); + + if (length >= 0) + length = simple_read_from_buffer(buf, count, ppos, (char *)page, length); + free_page(page); + return length; +} + +static struct file_operations proc_info_file_operations = { + .read = proc_info_read, +}; + +static int mem_open(struct inode* inode, struct file* file) +{ + file->private_data = (void*)((long)current->self_exec_id); + return 0; +} + +static ssize_t mem_read(struct file * file, char __user * buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task = proc_task(file->f_dentry->d_inode); + char *page; + unsigned long src = *ppos; + int ret = -ESRCH; + struct mm_struct *mm; + + if (!MAY_PTRACE(task) || !may_ptrace_attach(task)) + goto out; + + ret = -ENOMEM; + page = (char *)__get_free_page(GFP_USER); + if (!page) + goto out; + + ret = 0; + + mm = get_task_mm(task); + if (!mm) + goto out_free; + + ret = -EIO; + + if (file->private_data != (void*)((long)current->self_exec_id)) + goto out_put; + + ret = 0; + + while (count > 0) { + int this_len, retval; + + this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count; + retval = access_process_vm(task, src, page, this_len, 0); + if (!retval || !MAY_PTRACE(task) || !may_ptrace_attach(task)) { + if (!ret) + ret = -EIO; + break; + } + + if (copy_to_user(buf, page, retval)) { + ret = -EFAULT; + break; + } + + ret += retval; + src += retval; + buf += retval; + count -= retval; + } + *ppos = src; + +out_put: + mmput(mm); +out_free: + free_page((unsigned long) page); +out: + return ret; +} + +#define mem_write NULL + +#ifndef mem_write +/* This is a security hazard */ +static ssize_t mem_write(struct file * file, const char * buf, + size_t count, loff_t *ppos) +{ + int copied = 0; + char *page; + struct task_struct *task = proc_task(file->f_dentry->d_inode); + unsigned long dst = *ppos; + + if (!MAY_PTRACE(task) || !may_ptrace_attach(task)) + return -ESRCH; + + page = (char *)__get_free_page(GFP_USER); + if (!page) + return -ENOMEM; + + while (count > 0) { + int this_len, retval; + + this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count; + if (copy_from_user(page, buf, this_len)) { + copied = -EFAULT; + break; + } + retval = access_process_vm(task, dst, page, this_len, 1); + if (!retval) { + if (!copied) + copied = -EIO; + break; + } + copied += retval; + buf += retval; + dst += retval; + count -= retval; + } + *ppos = dst; + free_page((unsigned long) page); + return copied; +} +#endif + +static loff_t mem_lseek(struct file * file, loff_t offset, int orig) +{ + switch (orig) { + case 0: + file->f_pos = offset; + break; + case 1: + file->f_pos += offset; + break; + default: + return -EINVAL; + } + force_successful_syscall_return(); + return file->f_pos; +} + +static struct file_operations proc_mem_operations = { + .llseek = mem_lseek, + .read = mem_read, + .write = mem_write, + .open = mem_open, +}; + +static ssize_t oom_adjust_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task = proc_task(file->f_dentry->d_inode); + char buffer[8]; + size_t len; + int oom_adjust = task->oomkilladj; + loff_t __ppos = *ppos; + + len = sprintf(buffer, "%i\n", oom_adjust); + if (__ppos >= len) + return 0; + if (count > len-__ppos) + count = len-__ppos; + if (copy_to_user(buf, buffer + __ppos, count)) + return -EFAULT; + *ppos = __ppos + count; + return count; +} + +static ssize_t oom_adjust_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task = proc_task(file->f_dentry->d_inode); + char buffer[8], *end; + int oom_adjust; + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + memset(buffer, 0, 8); + if (count > 6) + count = 6; + if (copy_from_user(buffer, buf, count)) + return -EFAULT; + oom_adjust = simple_strtol(buffer, &end, 0); + if (oom_adjust < -16 || oom_adjust > 15) + return -EINVAL; + if (*end == '\n') + end++; + task->oomkilladj = oom_adjust; + if (end - buffer == 0) + return -EIO; + return end - buffer; +} + +static struct file_operations proc_oom_adjust_operations = { + .read = oom_adjust_read, + .write = oom_adjust_write, +}; + +static struct inode_operations proc_mem_inode_operations = { + .permission = proc_permission, +}; + +#ifdef CONFIG_AUDITSYSCALL +#define TMPBUFLEN 21 +static ssize_t proc_loginuid_read(struct file * file, char __user * buf, + size_t count, loff_t *ppos) +{ + struct inode * inode = file->f_dentry->d_inode; + struct task_struct *task = proc_task(inode); + ssize_t length; + char tmpbuf[TMPBUFLEN]; + + length = scnprintf(tmpbuf, TMPBUFLEN, "%u", + audit_get_loginuid(task->audit_context)); + return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); +} + +static ssize_t proc_loginuid_write(struct file * file, const char __user * buf, + size_t count, loff_t *ppos) +{ + struct inode * inode = file->f_dentry->d_inode; + char *page, *tmp; + ssize_t length; + struct task_struct *task = proc_task(inode); + uid_t loginuid; + + if (!capable(CAP_AUDIT_CONTROL)) + return -EPERM; + + if (current != task) + return -EPERM; + + if (count > PAGE_SIZE) + count = PAGE_SIZE; + + if (*ppos != 0) { + /* No partial writes. */ + return -EINVAL; + } + page = (char*)__get_free_page(GFP_USER); + if (!page) + return -ENOMEM; + length = -EFAULT; + if (copy_from_user(page, buf, count)) + goto out_free_page; + + loginuid = simple_strtoul(page, &tmp, 10); + if (tmp == page) { + length = -EINVAL; + goto out_free_page; + + } + length = audit_set_loginuid(task->audit_context, loginuid); + if (likely(length == 0)) + length = count; + +out_free_page: + free_page((unsigned long) page); + return length; +} + +static struct file_operations proc_loginuid_operations = { + .read = proc_loginuid_read, + .write = proc_loginuid_write, +}; +#endif + +#ifdef CONFIG_SECCOMP +static ssize_t seccomp_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *tsk = proc_task(file->f_dentry->d_inode); + char __buf[20]; + loff_t __ppos = *ppos; + size_t len; + + /* no need to print the trailing zero, so use only len */ + len = sprintf(__buf, "%u\n", tsk->seccomp.mode); + if (__ppos >= len) + return 0; + if (count > len - __ppos) + count = len - __ppos; + if (copy_to_user(buf, __buf + __ppos, count)) + return -EFAULT; + *ppos = __ppos + count; + return count; +} + +static ssize_t seccomp_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *tsk = proc_task(file->f_dentry->d_inode); + char __buf[20], *end; + unsigned int seccomp_mode; + + /* can set it only once to be even more secure */ + if (unlikely(tsk->seccomp.mode)) + return -EPERM; + + memset(__buf, 0, sizeof(__buf)); + count = min(count, sizeof(__buf) - 1); + if (copy_from_user(__buf, buf, count)) + return -EFAULT; + seccomp_mode = simple_strtoul(__buf, &end, 0); + if (*end == '\n') + end++; + if (seccomp_mode && seccomp_mode <= NR_SECCOMP_MODES) { + tsk->seccomp.mode = seccomp_mode; + set_tsk_thread_flag(tsk, TIF_SECCOMP); + } else + return -EINVAL; + if (unlikely(!(end - __buf))) + return -EIO; + return end - __buf; +} + +static struct file_operations proc_seccomp_operations = { + .read = seccomp_read, + .write = seccomp_write, +}; +#endif /* CONFIG_SECCOMP */ + +static int proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) +{ + struct inode *inode = dentry->d_inode; + int error = -EACCES; + + /* We don't need a base pointer in the /proc filesystem */ + path_release(nd); + + if (current->fsuid != inode->i_uid && !capable(CAP_DAC_OVERRIDE)) + goto out; + error = proc_check_root(inode); + if (error) + goto out; + + error = PROC_I(inode)->op.proc_get_link(inode, &nd->dentry, &nd->mnt); + nd->last_type = LAST_BIND; +out: + return error; +} + +static int do_proc_readlink(struct dentry *dentry, struct vfsmount *mnt, + char __user *buffer, int buflen) +{ + struct inode * inode; + char *tmp = (char*)__get_free_page(GFP_KERNEL), *path; + int len; + + if (!tmp) + return -ENOMEM; + + inode = dentry->d_inode; + path = d_path(dentry, mnt, tmp, PAGE_SIZE); + len = PTR_ERR(path); + if (IS_ERR(path)) + goto out; + len = tmp + PAGE_SIZE - 1 - path; + + if (len > buflen) + len = buflen; + if (copy_to_user(buffer, path, len)) + len = -EFAULT; + out: + free_page((unsigned long)tmp); + return len; +} + +static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int buflen) +{ + int error = -EACCES; + struct inode *inode = dentry->d_inode; + struct dentry *de; + struct vfsmount *mnt = NULL; + + lock_kernel(); + + if (current->fsuid != inode->i_uid && !capable(CAP_DAC_OVERRIDE)) + goto out; + error = proc_check_root(inode); + if (error) + goto out; + + error = PROC_I(inode)->op.proc_get_link(inode, &de, &mnt); + if (error) + goto out; + + error = do_proc_readlink(de, mnt, buffer, buflen); + dput(de); + mntput(mnt); +out: + unlock_kernel(); + return error; +} + +static struct inode_operations proc_pid_link_inode_operations = { + .readlink = proc_pid_readlink, + .follow_link = proc_pid_follow_link +}; + +#define NUMBUF 10 + +static int proc_readfd(struct file * filp, void * dirent, filldir_t filldir) +{ + struct inode *inode = filp->f_dentry->d_inode; + struct task_struct *p = proc_task(inode); + unsigned int fd, tid, ino; + int retval; + char buf[NUMBUF]; + struct files_struct * files; + + retval = -ENOENT; + if (!pid_alive(p)) + goto out; + retval = 0; + tid = p->pid; + + fd = filp->f_pos; + switch (fd) { + case 0: + if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0) + goto out; + filp->f_pos++; + case 1: + ino = fake_ino(tid, PROC_TID_INO); + if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0) + goto out; + filp->f_pos++; + default: + files = get_files_struct(p); + if (!files) + goto out; + spin_lock(&files->file_lock); + for (fd = filp->f_pos-2; + fd < files->max_fds; + fd++, filp->f_pos++) { + unsigned int i,j; + + if (!fcheck_files(files, fd)) + continue; + spin_unlock(&files->file_lock); + + j = NUMBUF; + i = fd; + do { + j--; + buf[j] = '0' + (i % 10); + i /= 10; + } while (i); + + ino = fake_ino(tid, PROC_TID_FD_DIR + fd); + if (filldir(dirent, buf+j, NUMBUF-j, fd+2, ino, DT_LNK) < 0) { + spin_lock(&files->file_lock); + break; + } + spin_lock(&files->file_lock); + } + spin_unlock(&files->file_lock); + put_files_struct(files); + } +out: + return retval; +} + +static int proc_pident_readdir(struct file *filp, + void *dirent, filldir_t filldir, + struct pid_entry *ents, unsigned int nents) +{ + int i; + int pid; + struct dentry *dentry = filp->f_dentry; + struct inode *inode = dentry->d_inode; + struct pid_entry *p; + ino_t ino; + int ret; + + ret = -ENOENT; + if (!pid_alive(proc_task(inode))) + goto out; + + ret = 0; + pid = proc_task(inode)->pid; + i = filp->f_pos; + switch (i) { + case 0: + ino = inode->i_ino; + if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0) + goto out; + i++; + filp->f_pos++; + /* fall through */ + case 1: + ino = parent_ino(dentry); + if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0) + goto out; + i++; + filp->f_pos++; + /* fall through */ + default: + i -= 2; + if (i >= nents) { + ret = 1; + goto out; + } + p = ents + i; + while (p->name) { + if (filldir(dirent, p->name, p->len, filp->f_pos, + fake_ino(pid, p->type), p->mode >> 12) < 0) + goto out; + filp->f_pos++; + p++; + } + } + + ret = 1; +out: + return ret; +} + +static int proc_tgid_base_readdir(struct file * filp, + void * dirent, filldir_t filldir) +{ + return proc_pident_readdir(filp,dirent,filldir, + tgid_base_stuff,ARRAY_SIZE(tgid_base_stuff)); +} + +static int proc_tid_base_readdir(struct file * filp, + void * dirent, filldir_t filldir) +{ + return proc_pident_readdir(filp,dirent,filldir, + tid_base_stuff,ARRAY_SIZE(tid_base_stuff)); +} + +/* building an inode */ + +static int task_dumpable(struct task_struct *task) +{ + int dumpable = 0; + struct mm_struct *mm; + + task_lock(task); + mm = task->mm; + if (mm) + dumpable = mm->dumpable; + task_unlock(task); + return dumpable; +} + + +static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task, int ino) +{ + struct inode * inode; + struct proc_inode *ei; + + /* We need a new inode */ + + inode = new_inode(sb); + if (!inode) + goto out; + + /* Common stuff */ + ei = PROC_I(inode); + ei->task = NULL; + inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; + inode->i_ino = fake_ino(task->pid, ino); + + if (!pid_alive(task)) + goto out_unlock; + + /* + * grab the reference to task. + */ + get_task_struct(task); + ei->task = task; + ei->type = ino; + inode->i_uid = 0; + inode->i_gid = 0; + if (ino == PROC_TGID_INO || ino == PROC_TID_INO || task_dumpable(task)) { + inode->i_uid = task->euid; + inode->i_gid = task->egid; + } + security_task_to_inode(task, inode); + +out: + return inode; + +out_unlock: + ei->pde = NULL; + iput(inode); + return NULL; +} + +/* dentry stuff */ + +/* + * Exceptional case: normally we are not allowed to unhash a busy + * directory. In this case, however, we can do it - no aliasing problems + * due to the way we treat inodes. + * + * Rewrite the inode's ownerships here because the owning task may have + * performed a setuid(), etc. + */ +static int pid_revalidate(struct dentry *dentry, struct nameidata *nd) +{ + struct inode *inode = dentry->d_inode; + struct task_struct *task = proc_task(inode); + if (pid_alive(task)) { + if (proc_type(inode) == PROC_TGID_INO || proc_type(inode) == PROC_TID_INO || task_dumpable(task)) { + inode->i_uid = task->euid; + inode->i_gid = task->egid; + } else { + inode->i_uid = 0; + inode->i_gid = 0; + } + security_task_to_inode(task, inode); + return 1; + } + d_drop(dentry); + return 0; +} + +static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) +{ + struct inode *inode = dentry->d_inode; + struct task_struct *task = proc_task(inode); + int fd = proc_type(inode) - PROC_TID_FD_DIR; + struct files_struct *files; + + files = get_files_struct(task); + if (files) { + spin_lock(&files->file_lock); + if (fcheck_files(files, fd)) { + spin_unlock(&files->file_lock); + put_files_struct(files); + if (task_dumpable(task)) { + inode->i_uid = task->euid; + inode->i_gid = task->egid; + } else { + inode->i_uid = 0; + inode->i_gid = 0; + } + security_task_to_inode(task, inode); + return 1; + } + spin_unlock(&files->file_lock); + put_files_struct(files); + } + d_drop(dentry); + return 0; +} + +static void pid_base_iput(struct dentry *dentry, struct inode *inode) +{ + struct task_struct *task = proc_task(inode); + spin_lock(&task->proc_lock); + if (task->proc_dentry == dentry) + task->proc_dentry = NULL; + spin_unlock(&task->proc_lock); + iput(inode); +} + +static int pid_delete_dentry(struct dentry * dentry) +{ + /* Is the task we represent dead? + * If so, then don't put the dentry on the lru list, + * kill it immediately. + */ + return !pid_alive(proc_task(dentry->d_inode)); +} + +static struct dentry_operations tid_fd_dentry_operations = +{ + .d_revalidate = tid_fd_revalidate, + .d_delete = pid_delete_dentry, +}; + +static struct dentry_operations pid_dentry_operations = +{ + .d_revalidate = pid_revalidate, + .d_delete = pid_delete_dentry, +}; + +static struct dentry_operations pid_base_dentry_operations = +{ + .d_revalidate = pid_revalidate, + .d_iput = pid_base_iput, + .d_delete = pid_delete_dentry, +}; + +/* Lookups */ + +static unsigned name_to_int(struct dentry *dentry) +{ + const char *name = dentry->d_name.name; + int len = dentry->d_name.len; + unsigned n = 0; + + if (len > 1 && *name == '0') |