diff options
Diffstat (limited to 'fs/proc/base.c')
| -rw-r--r-- | fs/proc/base.c | 4114 |
1 files changed, 2544 insertions, 1570 deletions
diff --git a/fs/proc/base.c b/fs/proc/base.c index a170450aadb..2d696b0c93b 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -49,422 +49,171 @@ #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/task_io_accounting_ops.h> #include <linux/init.h> +#include <linux/capability.h> #include <linux/file.h> +#include <linux/fdtable.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/namei.h> -#include <linux/namespace.h> +#include <linux/mnt_namespace.h> #include <linux/mm.h> -#include <linux/smp_lock.h> +#include <linux/swap.h> #include <linux/rcupdate.h> #include <linux/kallsyms.h> +#include <linux/stacktrace.h> +#include <linux/resource.h> +#include <linux/module.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/ptrace.h> -#include <linux/seccomp.h> +#include <linux/tracehook.h> +#include <linux/printk.h> +#include <linux/cgroup.h> #include <linux/cpuset.h> #include <linux/audit.h> +#include <linux/poll.h> +#include <linux/nsproxy.h> +#include <linux/oom.h> +#include <linux/elf.h> +#include <linux/pid_namespace.h> +#include <linux/user_namespace.h> +#include <linux/fs_struct.h> +#include <linux/slab.h> +#include <linux/flex_array.h> +#include <linux/posix-timers.h> +#ifdef CONFIG_HARDWALL +#include <asm/hardwall.h> +#endif +#include <trace/events/oom.h> #include "internal.h" +#include "fd.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. +/* NOTE: + * Implementing inode permission operations in /proc is almost + * certainly an error. Permission checks need to happen during + * each system call not at open time. The reason is that most of + * what we wish to check for permissions in /proc varies at runtime. + * + * The classic example of a problem is opening file descriptors + * in /proc for a task before it execs a suid executable. */ -#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_NUMA_MAPS, - PROC_TGID_MOUNTS, - PROC_TGID_WCHAN, -#ifdef CONFIG_MMU - PROC_TGID_SMAPS, -#endif -#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_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_NUMA_MAPS, - PROC_TID_MOUNTS, - PROC_TID_WCHAN, -#ifdef CONFIG_MMU - PROC_TID_SMAPS, -#endif -#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_OOM_SCORE, - PROC_TID_OOM_ADJUST, - - /* Add new entries before this */ - PROC_TID_FD_DIR = 0x8000, /* 0x8000-0xffff */ -}; - 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), -#ifdef CONFIG_NUMA - E(PROC_TGID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO), -#endif - 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_MMU - E(PROC_TGID_SMAPS, "smaps", S_IFREG|S_IRUGO), -#endif -#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), -#ifdef CONFIG_NUMA - E(PROC_TID_NUMA_MAPS, "numa_maps", S_IFREG|S_IRUGO), -#endif - 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_MMU - E(PROC_TID_SMAPS, "smaps", S_IFREG|S_IRUGO), -#endif -#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} + int len; + umode_t mode; + const struct inode_operations *iop; + const struct file_operations *fop; + union proc_op op; }; -#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 +#define NOD(NAME, MODE, IOP, FOP, OP) { \ + .name = (NAME), \ + .len = sizeof(NAME) - 1, \ + .mode = MODE, \ + .iop = IOP, \ + .fop = FOP, \ + .op = OP, \ +} -#undef E +#define DIR(NAME, MODE, iops, fops) \ + NOD(NAME, (S_IFDIR|(MODE)), &iops, &fops, {} ) +#define LNK(NAME, get_link) \ + NOD(NAME, (S_IFLNK|S_IRWXUGO), \ + &proc_pid_link_inode_operations, NULL, \ + { .proc_get_link = get_link } ) +#define REG(NAME, MODE, fops) \ + NOD(NAME, (S_IFREG|(MODE)), NULL, &fops, {}) +#define INF(NAME, MODE, read) \ + NOD(NAME, (S_IFREG|(MODE)), \ + NULL, &proc_info_file_operations, \ + { .proc_read = read } ) +#define ONE(NAME, MODE, show) \ + NOD(NAME, (S_IFREG|(MODE)), \ + NULL, &proc_single_file_operations, \ + { .proc_show = show } ) -static int proc_fd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +/* + * Count the number of hardlinks for the pid_entry table, excluding the . + * and .. links. + */ +static unsigned int pid_entry_count_dirs(const struct pid_entry *entries, + unsigned int n) { - struct task_struct *task = proc_task(inode); - struct files_struct *files; - struct file *file; - int fd = proc_type(inode) - PROC_TID_FD_DIR; + unsigned int i; + unsigned int count; - files = get_files_struct(task); - if (files) { - rcu_read_lock(); - file = fcheck_files(files, fd); - if (file) { - *mnt = mntget(file->f_vfsmnt); - *dentry = dget(file->f_dentry); - rcu_read_unlock(); - put_files_struct(files); - return 0; - } - rcu_read_unlock(); - put_files_struct(files); + count = 0; + for (i = 0; i < n; ++i) { + if (S_ISDIR(entries[i].mode)) + ++count; } - return -ENOENT; -} -static struct fs_struct *get_fs_struct(struct task_struct *task) -{ - struct fs_struct *fs; - task_lock(task); - fs = task->fs; - if(fs) - atomic_inc(&fs->count); - task_unlock(task); - return fs; + return count; } -static int proc_cwd_link(struct inode *inode, struct dentry **dentry, struct vfsmount **mnt) +static int get_task_root(struct task_struct *task, struct path *root) { - struct fs_struct *fs = get_fs_struct(proc_task(inode)); int result = -ENOENT; - 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 = get_fs_struct(proc_task(inode)); - int result = -ENOENT; - if (fs) { - read_lock(&fs->lock); - *mnt = mntget(fs->rootmnt); - *dentry = dget(fs->root); - read_unlock(&fs->lock); + task_lock(task); + if (task->fs) { + get_fs_root(task->fs, root); result = 0; - put_fs_struct(fs); } + task_unlock(task); return result; } - -/* Same as proc_root_link, but this addionally tries to get fs from other - * threads in the group */ -static int proc_task_root_link(struct inode *inode, struct dentry **dentry, - struct vfsmount **mnt) +static int proc_cwd_link(struct dentry *dentry, struct path *path) { - struct fs_struct *fs; + struct task_struct *task = get_proc_task(dentry->d_inode); int result = -ENOENT; - struct task_struct *leader = proc_task(inode); - task_lock(leader); - fs = leader->fs; - if (fs) { - atomic_inc(&fs->count); - task_unlock(leader); - } else { - /* Try to get fs from other threads */ - task_unlock(leader); - read_lock(&tasklist_lock); - if (pid_alive(leader)) { - struct task_struct *task = leader; - - while ((task = next_thread(task)) != leader) { - task_lock(task); - fs = task->fs; - if (fs) { - atomic_inc(&fs->count); - task_unlock(task); - break; - } - task_unlock(task); - } + if (task) { + task_lock(task); + if (task->fs) { + get_fs_pwd(task->fs, path); + result = 0; } - read_unlock(&tasklist_lock); - } - - if (fs) { - read_lock(&fs->lock); - *mnt = mntget(fs->rootmnt); - *dentry = dget(fs->root); - read_unlock(&fs->lock); - result = 0; - put_fs_struct(fs); + task_unlock(task); + put_task_struct(task); } 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 proc_pid_environ(struct task_struct *task, char * buffer) +static int proc_root_link(struct dentry *dentry, struct path *path) { - 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 (!ptrace_may_attach(task)) - res = -ESRCH; - mmput(mm); + struct task_struct *task = get_proc_task(dentry->d_inode); + int result = -ENOENT; + + if (task) { + result = get_task_root(task, path); + put_task_struct(task); } - return res; + return result; } -static int proc_pid_cmdline(struct task_struct *task, char * buffer) +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; + return get_cmdline(task, buffer, PAGE_SIZE); } static int proc_pid_auxv(struct task_struct *task, char *buffer) { - int res = 0; - struct mm_struct *mm = get_task_mm(task); - if (mm) { + struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ); + int res = PTR_ERR(mm); + if (mm && !IS_ERR(mm)) { unsigned int nwords = 0; - do + do { nwords += 2; - while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */ + } while (mm->saved_auxv[nwords - 2] != 0); /* AT_NULL */ res = nwords * sizeof(mm->saved_auxv[0]); if (res > PAGE_SIZE) res = PAGE_SIZE; @@ -482,221 +231,371 @@ static int proc_pid_auxv(struct task_struct *task, char *buffer) */ 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]; + unsigned long wchan; + char symname[KSYM_NAME_LEN]; 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); + if (lookup_symbol_name(wchan, symname) < 0) + if (!ptrace_may_access(task, PTRACE_MODE_READ)) + return 0; + else + return sprintf(buffer, "%lu", wchan); + else + return sprintf(buffer, "%s", symname); } #endif /* CONFIG_KALLSYMS */ -#ifdef CONFIG_SCHEDSTATS -/* - * Provides /proc/PID/schedstat - */ -static int proc_pid_schedstat(struct task_struct *task, char *buffer) +static int lock_trace(struct task_struct *task) { - return sprintf(buffer, "%lu %lu %lu\n", - task->sched_info.cpu_time, - task->sched_info.run_delay, - task->sched_info.pcnt); + int err = mutex_lock_killable(&task->signal->cred_guard_mutex); + if (err) + return err; + if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) { + mutex_unlock(&task->signal->cred_guard_mutex); + return -EPERM; + } + return 0; } -#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) +static void unlock_trace(struct task_struct *task) { - unsigned long points; - struct timespec uptime; - - do_posix_clock_monotonic_gettime(&uptime); - points = badness(task, uptime.tv_sec); - return sprintf(buffer, "%lu\n", points); + mutex_unlock(&task->signal->cred_guard_mutex); } -/************************************************************************/ -/* Here the fs part begins */ -/************************************************************************/ +#ifdef CONFIG_STACKTRACE -/* permission checks */ +#define MAX_STACK_TRACE_DEPTH 64 -/* If the process being read is separated by chroot from the reading process, - * don't let the reader access the threads. - */ -static int proc_check_chroot(struct dentry *root, struct vfsmount *vfsmnt) +static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) { - struct dentry *de, *base; - struct vfsmount *our_vfsmnt, *mnt; - int res = 0; - read_lock(¤t->fs->lock); - our_vfsmnt = mntget(current->fs->rootmnt); - base = dget(current->fs->root); - read_unlock(¤t->fs->lock); + struct stack_trace trace; + unsigned long *entries; + int err; + int i; - spin_lock(&vfsmount_lock); - de = root; - mnt = vfsmnt; + entries = kmalloc(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL); + if (!entries) + return -ENOMEM; - while (vfsmnt != our_vfsmnt) { - if (vfsmnt == vfsmnt->mnt_parent) - goto out; - de = vfsmnt->mnt_mountpoint; - vfsmnt = vfsmnt->mnt_parent; - } + trace.nr_entries = 0; + trace.max_entries = MAX_STACK_TRACE_DEPTH; + trace.entries = entries; + trace.skip = 0; - if (!is_subdir(de, base)) - goto out; - spin_unlock(&vfsmount_lock); + err = lock_trace(task); + if (!err) { + save_stack_trace_tsk(task, &trace); -exit: - dput(base); - mntput(our_vfsmnt); - dput(root); - mntput(mnt); - return res; -out: - spin_unlock(&vfsmount_lock); - res = -EACCES; - goto exit; -} - -static int proc_check_root(struct inode *inode) -{ - struct dentry *root; - struct vfsmount *vfsmnt; + for (i = 0; i < trace.nr_entries; i++) { + seq_printf(m, "[<%pK>] %pS\n", + (void *)entries[i], (void *)entries[i]); + } + unlock_trace(task); + } + kfree(entries); - if (proc_root_link(inode, &root, &vfsmnt)) /* Ewww... */ - return -ENOENT; - return proc_check_chroot(root, vfsmnt); + return err; } +#endif -static int proc_permission(struct inode *inode, int mask, struct nameidata *nd) +#ifdef CONFIG_SCHEDSTATS +/* + * Provides /proc/PID/schedstat + */ +static int proc_pid_schedstat(struct task_struct *task, char *buffer) { - if (generic_permission(inode, mask, NULL) != 0) - return -EACCES; - return proc_check_root(inode); + return sprintf(buffer, "%llu %llu %lu\n", + (unsigned long long)task->se.sum_exec_runtime, + (unsigned long long)task->sched_info.run_delay, + task->sched_info.pcount); } +#endif -static int proc_task_permission(struct inode *inode, int mask, struct nameidata *nd) +#ifdef CONFIG_LATENCYTOP +static int lstats_show_proc(struct seq_file *m, void *v) { - struct dentry *root; - struct vfsmount *vfsmnt; + int i; + struct inode *inode = m->private; + struct task_struct *task = get_proc_task(inode); - if (generic_permission(inode, mask, NULL) != 0) - return -EACCES; + if (!task) + return -ESRCH; + seq_puts(m, "Latency Top version : v0.1\n"); + for (i = 0; i < 32; i++) { + struct latency_record *lr = &task->latency_record[i]; + if (lr->backtrace[0]) { + int q; + seq_printf(m, "%i %li %li", + lr->count, lr->time, lr->max); + for (q = 0; q < LT_BACKTRACEDEPTH; q++) { + unsigned long bt = lr->backtrace[q]; + if (!bt) + break; + if (bt == ULONG_MAX) + break; + seq_printf(m, " %ps", (void *)bt); + } + seq_putc(m, '\n'); + } - if (proc_task_root_link(inode, &root, &vfsmnt)) - return -ENOENT; + } + put_task_struct(task); + return 0; +} - return proc_check_chroot(root, vfsmnt); +static int lstats_open(struct inode *inode, struct file *file) +{ + return single_open(file, lstats_show_proc, inode); } -extern struct seq_operations proc_pid_maps_op; -static int maps_open(struct inode *inode, struct file *file) +static ssize_t lstats_write(struct file *file, const char __user *buf, + size_t count, loff_t *offs) { - 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; + struct task_struct *task = get_proc_task(file_inode(file)); + + if (!task) + return -ESRCH; + clear_all_latency_tracing(task); + put_task_struct(task); + + return count; } -static struct file_operations proc_maps_operations = { - .open = maps_open, +static const struct file_operations proc_lstats_operations = { + .open = lstats_open, .read = seq_read, + .write = lstats_write, .llseek = seq_lseek, - .release = seq_release, + .release = single_release, }; -#ifdef CONFIG_NUMA -extern struct seq_operations proc_pid_numa_maps_op; -static int numa_maps_open(struct inode *inode, struct file *file) +#endif + +#ifdef CONFIG_CGROUPS +static int cgroup_open(struct inode *inode, struct file *file) { - struct task_struct *task = proc_task(inode); - int ret = seq_open(file, &proc_pid_numa_maps_op); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = task; - } - return ret; + struct pid *pid = PROC_I(inode)->pid; + return single_open(file, proc_cgroup_show, pid); } -static struct file_operations proc_numa_maps_operations = { - .open = numa_maps_open, +static const struct file_operations proc_cgroup_operations = { + .open = cgroup_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = single_release, }; #endif -#ifdef CONFIG_MMU -extern struct seq_operations proc_pid_smaps_op; -static int smaps_open(struct inode *inode, struct file *file) +#ifdef CONFIG_PROC_PID_CPUSET + +static int cpuset_open(struct inode *inode, struct file *file) { - struct task_struct *task = proc_task(inode); - int ret = seq_open(file, &proc_pid_smaps_op); - if (!ret) { - struct seq_file *m = file->private_data; - m->private = task; - } - return ret; + struct pid *pid = PROC_I(inode)->pid; + return single_open(file, proc_cpuset_show, pid); } -static struct file_operations proc_smaps_operations = { - .open = smaps_open, +static const struct file_operations proc_cpuset_operations = { + .open = cpuset_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release, + .release = single_release, }; #endif -extern struct seq_operations mounts_op; -static int mounts_open(struct inode *inode, struct file *file) +static int proc_oom_score(struct task_struct *task, char *buffer) { - struct task_struct *task = proc_task(inode); - int ret = seq_open(file, &mounts_op); + unsigned long totalpages = totalram_pages + total_swap_pages; + unsigned long points = 0; - 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); + read_lock(&tasklist_lock); + if (pid_alive(task)) + points = oom_badness(task, NULL, NULL, totalpages) * + 1000 / totalpages; + read_unlock(&tasklist_lock); + return sprintf(buffer, "%lu\n", points); +} - if (namespace) - m->private = namespace; - else { - seq_release(inode, file); - ret = -EINVAL; - } +struct limit_names { + char *name; + char *unit; +}; + +static const struct limit_names lnames[RLIM_NLIMITS] = { + [RLIMIT_CPU] = {"Max cpu time", "seconds"}, + [RLIMIT_FSIZE] = {"Max file size", "bytes"}, + [RLIMIT_DATA] = {"Max data size", "bytes"}, + [RLIMIT_STACK] = {"Max stack size", "bytes"}, + [RLIMIT_CORE] = {"Max core file size", "bytes"}, + [RLIMIT_RSS] = {"Max resident set", "bytes"}, + [RLIMIT_NPROC] = {"Max processes", "processes"}, + [RLIMIT_NOFILE] = {"Max open files", "files"}, + [RLIMIT_MEMLOCK] = {"Max locked memory", "bytes"}, + [RLIMIT_AS] = {"Max address space", "bytes"}, + [RLIMIT_LOCKS] = {"Max file locks", "locks"}, + [RLIMIT_SIGPENDING] = {"Max pending signals", "signals"}, + [RLIMIT_MSGQUEUE] = {"Max msgqueue size", "bytes"}, + [RLIMIT_NICE] = {"Max nice priority", NULL}, + [RLIMIT_RTPRIO] = {"Max realtime priority", NULL}, + [RLIMIT_RTTIME] = {"Max realtime timeout", "us"}, +}; + +/* Display limits for a process */ +static int proc_pid_limits(struct task_struct *task, char *buffer) +{ + unsigned int i; + int count = 0; + unsigned long flags; + char *bufptr = buffer; + + struct rlimit rlim[RLIM_NLIMITS]; + + if (!lock_task_sighand(task, &flags)) + return 0; + memcpy(rlim, task->signal->rlim, sizeof(struct rlimit) * RLIM_NLIMITS); + unlock_task_sighand(task, &flags); + + /* + * print the file header + */ + count += sprintf(&bufptr[count], "%-25s %-20s %-20s %-10s\n", + "Limit", "Soft Limit", "Hard Limit", "Units"); + + for (i = 0; i < RLIM_NLIMITS; i++) { + if (rlim[i].rlim_cur == RLIM_INFINITY) + count += sprintf(&bufptr[count], "%-25s %-20s ", + lnames[i].name, "unlimited"); + else + count += sprintf(&bufptr[count], "%-25s %-20lu ", + lnames[i].name, rlim[i].rlim_cur); + + if (rlim[i].rlim_max == RLIM_INFINITY) + count += sprintf(&bufptr[count], "%-20s ", "unlimited"); + else + count += sprintf(&bufptr[count], "%-20lu ", + rlim[i].rlim_max); + + if (lnames[i].unit) + count += sprintf(&bufptr[count], "%-10s\n", + lnames[i].unit); + else + count += sprintf(&bufptr[count], "\n"); } - return ret; + + return count; } -static int mounts_release(struct inode *inode, struct file *file) +#ifdef CONFIG_HAVE_ARCH_TRACEHOOK +static int proc_pid_syscall(struct task_struct *task, char *buffer) { - struct seq_file *m = file->private_data; - struct namespace *namespace = m->private; - put_namespace(namespace); - return seq_release(inode, file); + long nr; + unsigned long args[6], sp, pc; + int res = lock_trace(task); + if (res) + return res; + + if (task_current_syscall(task, &nr, args, 6, &sp, &pc)) + res = sprintf(buffer, "running\n"); + else if (nr < 0) + res = sprintf(buffer, "%ld 0x%lx 0x%lx\n", nr, sp, pc); + else + res = sprintf(buffer, + "%ld 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx 0x%lx\n", + nr, + args[0], args[1], args[2], args[3], args[4], args[5], + sp, pc); + unlock_trace(task); + return res; } +#endif /* CONFIG_HAVE_ARCH_TRACEHOOK */ -static struct file_operations proc_mounts_operations = { - .open = mounts_open, - .read = seq_read, - .llseek = seq_lseek, - .release = mounts_release, +/************************************************************************/ +/* Here the fs part begins */ +/************************************************************************/ + +/* permission checks */ +static int proc_fd_access_allowed(struct inode *inode) +{ + struct task_struct *task; + int allowed = 0; + /* Allow access to a task's file descriptors if it is us or we + * may use ptrace attach to the process and find out that + * information. + */ + task = get_proc_task(inode); + if (task) { + allowed = ptrace_may_access(task, PTRACE_MODE_READ); + put_task_struct(task); + } + return allowed; +} + +int proc_setattr(struct dentry *dentry, struct iattr *attr) +{ + int error; + struct inode *inode = dentry->d_inode; + + if (attr->ia_valid & ATTR_MODE) + return -EPERM; + + error = inode_change_ok(inode, attr); + if (error) + return error; + + setattr_copy(inode, attr); + mark_inode_dirty(inode); + return 0; +} + +/* + * May current process learn task's sched/cmdline info (for hide_pid_min=1) + * or euid/egid (for hide_pid_min=2)? + */ +static bool has_pid_permissions(struct pid_namespace *pid, + struct task_struct *task, + int hide_pid_min) +{ + if (pid->hide_pid < hide_pid_min) + return true; + if (in_group_p(pid->pid_gid)) + return true; + return ptrace_may_access(task, PTRACE_MODE_READ); +} + + +static int proc_pid_permission(struct inode *inode, int mask) +{ + struct pid_namespace *pid = inode->i_sb->s_fs_info; + struct task_struct *task; + bool has_perms; + + task = get_proc_task(inode); + if (!task) + return -ESRCH; + has_perms = has_pid_permissions(pid, task, 1); + put_task_struct(task); + + if (!has_perms) { + if (pid->hide_pid == 2) { + /* + * Let's make getdents(), stat(), and open() + * consistent with each other. If a process + * may not stat() a file, it shouldn't be seen + * in procfs at all. + */ + return -ENOENT; + } + + return -EPERM; + } + return generic_permission(inode, mask); +} + + + +static const struct inode_operations proc_def_inode_operations = { + .setattr = proc_setattr, }; #define PROC_BLOCK_SIZE (3*1024) /* 4K page size but our output routines use some slack for overruns */ @@ -704,140 +603,171 @@ static struct file_operations proc_mounts_operations = { 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; + struct inode * inode = file_inode(file); unsigned long page; ssize_t length; - struct task_struct *task = proc_task(inode); + struct task_struct *task = get_proc_task(inode); + + length = -ESRCH; + if (!task) + goto out_no_task; if (count > PROC_BLOCK_SIZE) count = PROC_BLOCK_SIZE; - if (!(page = __get_free_page(GFP_KERNEL))) - return -ENOMEM; + + length = -ENOMEM; + if (!(page = __get_free_page(GFP_TEMPORARY))) + goto out; 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); +out: + put_task_struct(task); +out_no_task: return length; } -static struct file_operations proc_info_file_operations = { +static const struct file_operations proc_info_file_operations = { .read = proc_info_read, + .llseek = generic_file_llseek, }; -static int mem_open(struct inode* inode, struct file* file) +static int proc_single_show(struct seq_file *m, void *v) { - file->private_data = (void*)((long)current->self_exec_id); - return 0; + struct inode *inode = m->private; + struct pid_namespace *ns; + struct pid *pid; + struct task_struct *task; + int ret; + + ns = inode->i_sb->s_fs_info; + pid = proc_pid(inode); + task = get_pid_task(pid, PIDTYPE_PID); + if (!task) + return -ESRCH; + + ret = PROC_I(inode)->op.proc_show(m, ns, pid, task); + + put_task_struct(task); + return ret; } -static ssize_t mem_read(struct file * file, char __user * buf, - size_t count, loff_t *ppos) +static int proc_single_open(struct inode *inode, struct file *filp) { - struct task_struct *task = proc_task(file->f_dentry->d_inode); - char *page; - unsigned long src = *ppos; - int ret = -ESRCH; + return single_open(filp, proc_single_show, inode); +} + +static const struct file_operations proc_single_file_operations = { + .open = proc_single_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __mem_open(struct inode *inode, struct file *file, unsigned int mode) +{ + struct task_struct *task = get_proc_task(file_inode(file)); struct mm_struct *mm; - if (!MAY_PTRACE(task) || !ptrace_may_attach(task)) - goto out; + if (!task) + return -ESRCH; - ret = -ENOMEM; - page = (char *)__get_free_page(GFP_USER); - if (!page) - goto out; + mm = mm_access(task, mode); + put_task_struct(task); - ret = 0; - - mm = get_task_mm(task); - if (!mm) - goto out_free; + if (IS_ERR(mm)) + return PTR_ERR(mm); - ret = -EIO; - - if (file->private_data != (void*)((long)current->self_exec_id)) - goto out_put; + if (mm) { + /* ensure this mm_struct can't be freed */ + atomic_inc(&mm->mm_count); + /* but do not pin its memory */ + mmput(mm); + } - ret = 0; - - while (count > 0) { - int this_len, retval; + file->private_data = mm; - this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count; - retval = access_process_vm(task, src, page, this_len, 0); - if (!retval || !MAY_PTRACE(task) || !ptrace_may_attach(task)) { - if (!ret) - ret = -EIO; - break; - } + return 0; +} - if (copy_to_user(buf, page, retval)) { - ret = -EFAULT; - break; - } - - ret += retval; - src += retval; - buf += retval; - count -= retval; - } - *ppos = src; +static int mem_open(struct inode *inode, struct file *file) +{ + int ret = __mem_open(inode, file, PTRACE_MODE_ATTACH); + + /* OK to pass negative loff_t, we can catch out-of-range */ + file->f_mode |= FMODE_UNSIGNED_OFFSET; -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) +static ssize_t mem_rw(struct file *file, char __user *buf, + size_t count, loff_t *ppos, int write) { - int copied = 0; + struct mm_struct *mm = file->private_data; + unsigned long addr = *ppos; + ssize_t copied; char *page; - struct task_struct *task = proc_task(file->f_dentry->d_inode); - unsigned long dst = *ppos; - if (!MAY_PTRACE(task) || !ptrace_may_attach(task)) - return -ESRCH; + if (!mm) + return 0; - page = (char *)__get_free_page(GFP_USER); + page = (char *)__get_free_page(GFP_TEMPORARY); if (!page) return -ENOMEM; + copied = 0; + if (!atomic_inc_not_zero(&mm->mm_users)) + goto free; + while (count > 0) { - int this_len, retval; + int this_len = min_t(int, count, PAGE_SIZE); - this_len = (count > PAGE_SIZE) ? PAGE_SIZE : count; - if (copy_from_user(page, buf, this_len)) { + if (write && copy_from_user(page, buf, this_len)) { copied = -EFAULT; break; } - retval = access_process_vm(task, dst, page, this_len, 1); - if (!retval) { + + this_len = access_remote_vm(mm, addr, page, this_len, write); + if (!this_len) { if (!copied) copied = -EIO; break; } - copied += retval; - buf += retval; - dst += retval; - count -= retval; + + if (!write && copy_to_user(buf, page, this_len)) { + copied = -EFAULT; + break; + } + + buf += this_len; + addr += this_len; + copied += this_len; + count -= this_len; } - *ppos = dst; + *ppos = addr; + + mmput(mm); +free: free_page((unsigned long) page); return copied; } -#endif -static loff_t mem_lseek(struct file * file, loff_t offset, int orig) +static ssize_t mem_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + return mem_rw(file, buf, count, ppos, 0); +} + +static ssize_t mem_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + return mem_rw(file, (char __user*)buf, count, ppos, 1); +} + +loff_t mem_lseek(struct file *file, loff_t offset, int orig) { switch (orig) { case 0: @@ -853,65 +783,284 @@ static loff_t mem_lseek(struct file * file, loff_t offset, int orig) return file->f_pos; } -static struct file_operations proc_mem_operations = { +static int mem_release(struct inode *inode, struct file *file) +{ + struct mm_struct *mm = file->private_data; + if (mm) + mmdrop(mm); + return 0; +} + +static const struct file_operations proc_mem_operations = { .llseek = mem_lseek, .read = mem_read, .write = mem_write, .open = mem_open, + .release = mem_release, }; -static ssize_t oom_adjust_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) +static int environ_open(struct inode *inode, struct file *file) { - 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; + return __mem_open(inode, file, PTRACE_MODE_READ); +} - len = sprintf(buffer, "%i\n", oom_adjust); - if (__ppos >= len) +static ssize_t environ_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + char *page; + unsigned long src = *ppos; + int ret = 0; + struct mm_struct *mm = file->private_data; + + if (!mm) return 0; - if (count > len-__ppos) - count = len-__ppos; - if (copy_to_user(buf, buffer + __ppos, count)) - return -EFAULT; - *ppos = __ppos + count; - return count; + + page = (char *)__get_free_page(GFP_TEMPORARY); + if (!page) + return -ENOMEM; + + ret = 0; + if (!atomic_inc_not_zero(&mm->mm_users)) + goto free; + while (count > 0) { + size_t this_len, max_len; + int retval; + + if (src >= (mm->env_end - mm->env_start)) + break; + + this_len = mm->env_end - (mm->env_start + src); + + max_len = min_t(size_t, PAGE_SIZE, count); + this_len = min(max_len, this_len); + + retval = access_remote_vm(mm, (mm->env_start + src), + page, this_len, 0); + + if (retval <= 0) { + ret = retval; + break; + } + + if (copy_to_user(buf, page, retval)) { + ret = -EFAULT; + break; + } + + ret += retval; + src += retval; + buf += retval; + count -= retval; + } + *ppos = src; + mmput(mm); + +free: + free_page((unsigned long) page); + return ret; } -static ssize_t oom_adjust_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static const struct file_operations proc_environ_operations = { + .open = environ_open, + .read = environ_read, + .llseek = generic_file_llseek, + .release = mem_release, +}; + +static ssize_t oom_adj_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], *end; - int oom_adjust; + struct task_struct *task = get_proc_task(file_inode(file)); + char buffer[PROC_NUMBUF]; + int oom_adj = OOM_ADJUST_MIN; + size_t len; + unsigned long flags; - 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) && oom_adjust != OOM_DISABLE) - return -EINVAL; - if (*end == '\n') - end++; - task->oomkilladj = oom_adjust; - if (end - buffer == 0) - return -EIO; - return end - buffer; + if (!task) + return -ESRCH; + if (lock_task_sighand(task, &flags)) { + if (task->signal->oom_score_adj == OOM_SCORE_ADJ_MAX) + oom_adj = OOM_ADJUST_MAX; + else + oom_adj = (task->signal->oom_score_adj * -OOM_DISABLE) / + OOM_SCORE_ADJ_MAX; + unlock_task_sighand(task, &flags); + } + put_task_struct(task); + len = snprintf(buffer, sizeof(buffer), "%d\n", oom_adj); + return simple_read_from_buffer(buf, count, ppos, buffer, len); } -static struct file_operations proc_oom_adjust_operations = { - .read = oom_adjust_read, - .write = oom_adjust_write, +static ssize_t oom_adj_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + char buffer[PROC_NUMBUF]; + int oom_adj; + unsigned long flags; + int err; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out; + } + + err = kstrtoint(strstrip(buffer), 0, &oom_adj); + if (err) + goto out; + if ((oom_adj < OOM_ADJUST_MIN || oom_adj > OOM_ADJUST_MAX) && + oom_adj != OOM_DISABLE) { + err = -EINVAL; + goto out; + } + + task = get_proc_task(file_inode(file)); + if (!task) { + err = -ESRCH; + goto out; + } + + task_lock(task); + if (!task->mm) { + err = -EINVAL; + goto err_task_lock; + } + + if (!lock_task_sighand(task, &flags)) { + err = -ESRCH; + goto err_task_lock; + } + + /* + * Scale /proc/pid/oom_score_adj appropriately ensuring that a maximum + * value is always attainable. + */ + if (oom_adj == OOM_ADJUST_MAX) + oom_adj = OOM_SCORE_ADJ_MAX; + else + oom_adj = (oom_adj * OOM_SCORE_ADJ_MAX) / -OOM_DISABLE; + + if (oom_adj < task->signal->oom_score_adj && + !capable(CAP_SYS_RESOURCE)) { + err = -EACCES; + goto err_sighand; + } + + /* + * /proc/pid/oom_adj is provided for legacy purposes, ask users to use + * /proc/pid/oom_score_adj instead. + */ + pr_warn_once("%s (%d): /proc/%d/oom_adj is deprecated, please use /proc/%d/oom_score_adj instead.\n", + current->comm, task_pid_nr(current), task_pid_nr(task), + task_pid_nr(task)); + + task->signal->oom_score_adj = oom_adj; + trace_oom_score_adj_update(task); +err_sighand: + unlock_task_sighand(task, &flags); +err_task_lock: + task_unlock(task); + put_task_struct(task); +out: + return err < 0 ? err : count; +} + +static const struct file_operations proc_oom_adj_operations = { + .read = oom_adj_read, + .write = oom_adj_write, + .llseek = generic_file_llseek, }; -static struct inode_operations proc_mem_inode_operations = { - .permission = proc_permission, +static ssize_t oom_score_adj_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task = get_proc_task(file_inode(file)); + char buffer[PROC_NUMBUF]; + short oom_score_adj = OOM_SCORE_ADJ_MIN; + unsigned long flags; + size_t len; + + if (!task) + return -ESRCH; + if (lock_task_sighand(task, &flags)) { + oom_score_adj = task->signal->oom_score_adj; + unlock_task_sighand(task, &flags); + } + put_task_struct(task); + len = snprintf(buffer, sizeof(buffer), "%hd\n", oom_score_adj); + return simple_read_from_buffer(buf, count, ppos, buffer, len); +} + +static ssize_t oom_score_adj_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct task_struct *task; + char buffer[PROC_NUMBUF]; + unsigned long flags; + int oom_score_adj; + int err; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) { + err = -EFAULT; + goto out; + } + + err = kstrtoint(strstrip(buffer), 0, &oom_score_adj); + if (err) + goto out; + if (oom_score_adj < OOM_SCORE_ADJ_MIN || + oom_score_adj > OOM_SCORE_ADJ_MAX) { + err = -EINVAL; + goto out; + } + + task = get_proc_task(file_inode(file)); + if (!task) { + err = -ESRCH; + goto out; + } + + task_lock(task); + if (!task->mm) { + err = -EINVAL; + goto err_task_lock; + } + + if (!lock_task_sighand(task, &flags)) { + err = -ESRCH; + goto err_task_lock; + } + + if ((short)oom_score_adj < task->signal->oom_score_adj_min && + !capable(CAP_SYS_RESOURCE)) { + err = -EACCES; + goto err_sighand; + } + + task->signal->oom_score_adj = (short)oom_score_adj; + if (has_capability_noaudit(current, CAP_SYS_RESOURCE)) + task->signal->oom_score_adj_min = (short)oom_score_adj; + trace_oom_score_adj_update(task); + +err_sighand: + unlock_task_sighand(task, &flags); +err_task_lock: + task_unlock(task); + put_task_struct(task); +out: + return err < 0 ? err : count; +} + +static const struct file_operations proc_oom_score_adj_operations = { + .read = oom_score_adj_read, + .write = oom_score_adj_write, + .llseek = default_llseek, }; #ifdef CONFIG_AUDITSYSCALL @@ -919,52 +1068,70 @@ static struct inode_operations proc_mem_inode_operations = { 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); + struct inode * inode = file_inode(file); + struct task_struct *task = get_proc_task(inode); ssize_t length; char tmpbuf[TMPBUFLEN]; + if (!task) + return -ESRCH; length = scnprintf(tmpbuf, TMPBUFLEN, "%u", - audit_get_loginuid(task->audit_context)); + from_kuid(file->f_cred->user_ns, + audit_get_loginuid(task))); + put_task_struct(task); 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; + struct inode * inode = file_inode(file); char *page, *tmp; ssize_t length; - struct task_struct *task = proc_task(inode); uid_t loginuid; + kuid_t kloginuid; - if (!capable(CAP_AUDIT_CONTROL)) - return -EPERM; - - if (current != task) + rcu_read_lock(); + if (current != pid_task(proc_pid(inode), PIDTYPE_PID)) { + rcu_read_unlock(); return -EPERM; + } + rcu_read_unlock(); - if (count > PAGE_SIZE) - count = PAGE_SIZE; + if (count >= PAGE_SIZE) + count = PAGE_SIZE - 1; if (*ppos != 0) { /* No partial writes. */ return -EINVAL; } - page = (char*)__get_free_page(GFP_USER); + page = (char*)__get_free_page(GFP_TEMPORARY); if (!page) return -ENOMEM; length = -EFAULT; if (copy_from_user(page, buf, count)) goto out_free_page; + page[count] = '\0'; loginuid = simple_strtoul(page, &tmp, 10); if (tmp == page) { length = -EINVAL; goto out_free_page; } - length = audit_set_loginuid(task, loginuid); + + /* is userspace tring to explicitly UNSET the loginuid? */ + if (loginuid == AUDIT_UID_UNSET) { + kloginuid = INVALID_UID; + } else { + kloginuid = make_kuid(file->f_cred->user_ns, loginuid); + if (!uid_valid(kloginuid)) { + length = -EINVAL; + goto out_free_page; + } + } + + length = audit_set_loginuid(kloginuid); if (likely(length == 0)) length = count; @@ -973,107 +1140,335 @@ out_free_page: return length; } -static struct file_operations proc_loginuid_operations = { +static const struct file_operations proc_loginuid_operations = { .read = proc_loginuid_read, .write = proc_loginuid_write, + .llseek = generic_file_llseek, +}; + +static ssize_t proc_sessionid_read(struct file * file, char __user * buf, + size_t count, loff_t *ppos) +{ + struct inode * inode = file_inode(file); + struct task_struct *task = get_proc_task(inode); + ssize_t length; + char tmpbuf[TMPBUFLEN]; + + if (!task) + return -ESRCH; + length = scnprintf(tmpbuf, TMPBUFLEN, "%u", + audit_get_sessionid(task)); + put_task_struct(task); + return simple_read_from_buffer(buf, count, ppos, tmpbuf, length); +} + +static const struct file_operations proc_sessionid_operations = { + .read = proc_sessionid_read, + .llseek = generic_file_llseek, }; #endif -#ifdef CONFIG_SECCOMP -static ssize_t seccomp_read(struct file *file, char __user *buf, - size_t count, loff_t *ppos) +#ifdef CONFIG_FAULT_INJECTION +static ssize_t proc_fault_inject_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; + struct task_struct *task = get_proc_task(file_inode(file)); + char buffer[PROC_NUMBUF]; size_t len; + int make_it_fail; - /* 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)) + if (!task) + return -ESRCH; + make_it_fail = task->make_it_fail; + put_task_struct(task); + + len = snprintf(buffer, sizeof(buffer), "%i\n", make_it_fail); + + return simple_read_from_buffer(buf, count, ppos, buffer, len); +} + +static ssize_t proc_fault_inject_write(struct file * file, + const char __user * buf, size_t count, loff_t *ppos) +{ + struct task_struct *task; + char buffer[PROC_NUMBUF], *end; + int make_it_fail; + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) return -EFAULT; - *ppos = __ppos + count; + make_it_fail = simple_strtol(strstrip(buffer), &end, 0); + if (*end) + return -EINVAL; + if (make_it_fail < 0 || make_it_fail > 1) + return -EINVAL; + + task = get_proc_task(file_inode(file)); + if (!task) + return -ESRCH; + task->make_it_fail = make_it_fail; + put_task_struct(task); + return count; } -static ssize_t seccomp_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) +static const struct file_operations proc_fault_inject_operations = { + .read = proc_fault_inject_read, + .write = proc_fault_inject_write, + .llseek = generic_file_llseek, +}; +#endif + + +#ifdef CONFIG_SCHED_DEBUG +/* + * Print out various scheduling related per-task fields: + */ +static int sched_show(struct seq_file *m, void *v) { - struct task_struct *tsk = proc_task(file->f_dentry->d_inode); - char __buf[20], *end; - unsigned int seccomp_mode; + struct inode *inode = m->private; + struct task_struct *p; - /* can set it only once to be even more secure */ - if (unlikely(tsk->seccomp.mode)) - return -EPERM; + p = get_proc_task(inode); + if (!p) + return -ESRCH; + proc_sched_show_task(p, m); + + put_task_struct(p); + + return 0; +} + +static ssize_t +sched_write(struct file *file, const char __user *buf, + size_t count, loff_t *offset) +{ + struct inode *inode = file_inode(file); + struct task_struct *p; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + proc_sched_set_task(p); + + put_task_struct(p); - memset(__buf, 0, sizeof(__buf)); - count = min(count, sizeof(__buf) - 1); - if (copy_from_user(__buf, buf, count)) + return count; +} + +static int sched_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, sched_show, inode); +} + +static const struct file_operations proc_pid_sched_operations = { + .open = sched_open, + .read = seq_read, + .write = sched_write, + .llseek = seq_lseek, + .release = single_release, +}; + +#endif + +#ifdef CONFIG_SCHED_AUTOGROUP +/* + * Print out autogroup related information: + */ +static int sched_autogroup_show(struct seq_file *m, void *v) +{ + struct inode *inode = m->private; + struct task_struct *p; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + proc_sched_autogroup_show_task(p, m); + + put_task_struct(p); + + return 0; +} + +static ssize_t +sched_autogroup_write(struct file *file, const char __user *buf, + size_t count, loff_t *offset) +{ + struct inode *inode = file_inode(file); + struct task_struct *p; + char buffer[PROC_NUMBUF]; + int nice; + int err; + + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, 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; + + err = kstrtoint(strstrip(buffer), 0, &nice); + if (err < 0) + return err; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + + err = proc_sched_autogroup_set_nice(p, nice); + if (err) + count = err; + + put_task_struct(p); + + return count; } -static struct file_operations proc_seccomp_operations = { - .read = seccomp_read, - .write = seccomp_write, +static int sched_autogroup_open(struct inode *inode, struct file *filp) +{ + int ret; + + ret = single_open(filp, sched_autogroup_show, NULL); + if (!ret) { + struct seq_file *m = filp->private_data; + + m->private = inode; + } + return ret; +} + +static const struct file_operations proc_pid_sched_autogroup_operations = { + .open = sched_autogroup_open, + .read = seq_read, + .write = sched_autogroup_write, + .llseek = seq_lseek, + .release = single_release, +}; + +#endif /* CONFIG_SCHED_AUTOGROUP */ + +static ssize_t comm_write(struct file *file, const char __user *buf, + size_t count, loff_t *offset) +{ + struct inode *inode = file_inode(file); + struct task_struct *p; + char buffer[TASK_COMM_LEN]; + const size_t maxlen = sizeof(buffer) - 1; + + memset(buffer, 0, sizeof(buffer)); + if (copy_from_user(buffer, buf, count > maxlen ? maxlen : count)) + return -EFAULT; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + + if (same_thread_group(current, p)) + set_task_comm(p, buffer); + else + count = -EINVAL; + + put_task_struct(p); + + return count; +} + +static int comm_show(struct seq_file *m, void *v) +{ + struct inode *inode = m->private; + struct task_struct *p; + + p = get_proc_task(inode); + if (!p) + return -ESRCH; + + task_lock(p); + seq_printf(m, "%s\n", p->comm); + task_unlock(p); + + put_task_struct(p); + + return 0; +} + +static int comm_open(struct inode *inode, struct file *filp) +{ + return single_open(filp, comm_show, inode); +} + +static const struct file_operations proc_pid_set_comm_operations = { + .open = comm_open, + .read = seq_read, + .write = comm_write, + .llseek = seq_lseek, + .release = single_release, }; -#endif /* CONFIG_SECCOMP */ + +static int proc_exe_link(struct dentry *dentry, struct path *exe_path) +{ + struct task_struct *task; + struct mm_struct *mm; + struct file *exe_file; + + task = get_proc_task(dentry->d_inode); + if (!task) + return -ENOENT; + mm = get_task_mm(task); + put_task_struct(task); + if (!mm) + return -ENOENT; + exe_file = get_mm_exe_file(mm); + mmput(mm); + if (exe_file) { + *exe_path = exe_file->f_path; + path_get(&exe_file->f_path); + fput(exe_file); + return 0; + } else + return -ENOENT; +} static void *proc_pid_follow_link(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; + struct path path; 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)) + /* Are we allowed to snoop on the tasks file descriptors? */ + if (!proc_fd_access_allowed(inode)) goto out; - error = proc_check_root(inode); + + error = PROC_I(inode)->op.proc_get_link(dentry, &path); if (error) goto out; - error = PROC_I(inode)->op.proc_get_link(inode, &nd->dentry, &nd->mnt); - nd->last_type = LAST_BIND; + nd_jump_link(nd, &path); + return NULL; out: return ERR_PTR(error); } -static int do_proc_readlink(struct dentry *dentry, struct vfsmount *mnt, - char __user *buffer, int buflen) +static int do_proc_readlink(struct path *path, char __user *buffer, int buflen) { - struct inode * inode; - char *tmp = (char*)__get_free_page(GFP_KERNEL), *path; + char *tmp = (char*)__get_free_page(GFP_TEMPORARY); + char *pathname; 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)) + + pathname = d_path(path, tmp, PAGE_SIZE); + len = PTR_ERR(pathname); + if (IS_ERR(pathname)) goto out; - len = tmp + PAGE_SIZE - 1 - path; + len = tmp + PAGE_SIZE - 1 - pathname; if (len > buflen) len = buflen; - if (copy_to_user(buffer, path, len)) + if (copy_to_user(buffer, pathname, len)) len = -EFAULT; out: free_page((unsigned long)tmp); @@ -1084,218 +1479,62 @@ static int proc_pid_readlink(struct dentry * dentry, char __user * buffer, int b { int error = -EACCES; struct inode *inode = dentry->d_inode; - struct dentry *de; - struct vfsmount *mnt = NULL; - - lock_kernel(); + struct path path; - if (current->fsuid != inode->i_uid && !capable(CAP_DAC_OVERRIDE)) - goto out; - error = proc_check_root(inode); - if (error) + /* Are we allowed to snoop on the tasks file descriptors? */ + if (!proc_fd_access_allowed(inode)) goto out; - error = PROC_I(inode)->op.proc_get_link(inode, &de, &mnt); + error = PROC_I(inode)->op.proc_get_link(dentry, &path); if (error) goto out; - error = do_proc_readlink(de, mnt, buffer, buflen); - dput(de); - mntput(mnt); + error = do_proc_readlink(&path, buffer, buflen); + path_put(&path); out: - unlock_kernel(); return error; } -static struct inode_operations proc_pid_link_inode_operations = { +const struct inode_operations proc_pid_link_inode_operations = { .readlink = proc_pid_readlink, - .follow_link = proc_pid_follow_link + .follow_link = proc_pid_follow_link, + .setattr = proc_setattr, }; -#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; - struct fdtable *fdt; - - 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; - rcu_read_lock(); - fdt = files_fdtable(files); - for (fd = filp->f_pos-2; - fd < fdt->max_fds; - fd++, filp->f_pos++) { - unsigned int i,j; - - if (!fcheck_files(files, fd)) - continue; - rcu_read_unlock(); - - 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) { - rcu_read_lock(); - break; - } - rcu_read_lock(); - } - rcu_read_unlock(); - 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); - if(dumpable == 1) - return 1; - return 0; -} - - -static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task, int ino) +struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task) { struct inode * inode; struct proc_inode *ei; + const struct cred *cred; /* We need a new inode */ - + inode = new_inode(sb); if (!inode) goto out; /* Common stuff */ ei = PROC_I(inode); - ei->task = NULL; + inode->i_ino = get_next_ino(); 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; + inode->i_op = &proc_def_inode_operations; /* * 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; + ei->pid = get_task_pid(task, PIDTYPE_PID); + if (!ei->pid) + goto out_unlock; + + if (task_dumpable(task)) { + rcu_read_lock(); + cred = __task_cred(task); + inode->i_uid = cred->euid; + inode->i_gid = cred->egid; + rcu_read_unlock(); } security_task_to_inode(task, inode); @@ -1303,11 +1542,43 @@ out: return inode; out_unlock: - ei->pde = NULL; iput(inode); return NULL; } +int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +{ + struct inode *inode = dentry->d_inode; + struct task_struct *task; + const struct cred *cred; + struct pid_namespace *pid = dentry->d_sb->s_fs_info; + + generic_fillattr(inode, stat); + + rcu_read_lock(); + stat->uid = GLOBAL_ROOT_UID; + stat->gid = GLOBAL_ROOT_GID; + task = pid_task(proc_pid(inode), PIDTYPE_PID); + if (task) { + if (!has_pid_permissions(pid, task, 2)) { + rcu_read_unlock(); + /* + * This doesn't prevent learning whether PID exists, + * it only makes getattr() consistent with readdir(). + */ + return -ENOENT; + } + if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || + task_dumpable(task)) { + cred = __task_cred(task); + stat->uid = cred->euid; + stat->gid = cred->egid; + } + } + rcu_read_unlock(); + return 0; +} + /* dentry stuff */ /* @@ -1317,912 +1588,1615 @@ out_unlock: * * Rewrite the inode's ownerships here because the owning task may have * performed a setuid(), etc. + * + * Before the /proc/pid/status file was created the only way to read + * the effective uid of a /process was to stat /proc/pid. Reading + * /proc/pid/status is slow enough that procps and other packages + * kept stating /proc/pid. To keep the rules in /proc simple I have + * made this apply to all per process world readable and executable + * directories. */ -static int pid_revalidate(struct dentry *dentry, struct nameidata *nd) +int pid_revalidate(struct dentry *dentry, unsigned int flags) { - 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; -} + struct inode *inode; + struct task_struct *task; + const struct cred *cred; -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; + if (flags & LOOKUP_RCU) + return -ECHILD; - files = get_files_struct(task); - if (files) { - rcu_read_lock(); - if (fcheck_files(files, fd)) { + inode = dentry->d_inode; + task = get_proc_task(inode); + + if (task) { + if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || + task_dumpable(task)) { + rcu_read_lock(); + cred = __task_cred(task); + inode->i_uid = cred->euid; + inode->i_gid = cred->egid; rcu_read_unlock(); - 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; + } else { + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; } - rcu_read_unlock(); - put_files_struct(files); + inode->i_mode &= ~(S_ISUID | S_ISGID); + security_task_to_inode(task, inode); + put_task_struct(task); + return 1; } d_drop(dentry); return 0; } -static void pid_base_iput(struct dentry *dentry, struct inode *inode) +static inline bool proc_inode_is_dead(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); + return !proc_pid(inode)->tasks[PIDTYPE_PID].first; } -static int pid_delete_dentry(struct dentry * dentry) +int pid_delete_dentry(const 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)); + return proc_inode_is_dead(dentry->d_inode); } -static struct dentry_operations tid_fd_dentry_operations = +const struct dentry_operations pid_dentry_operations = { - .d_revalidate = tid_fd_revalidate, + .d_revalidate = pid_revalidate, .d_delete = pid_delete_dentry, }; -static struct dentry_operations pid_dentry_operations = +/* Lookups */ + +/* + * Fill a directory entry. + * + * If possible create the dcache entry and derive our inode number and + * file type from dcache entry. + * + * Since all of the proc inode numbers are dynamically generated, the inode + * numbers do not exist until the inode is cache. This means creating the + * the dcache entry in readdir is necessary to keep the inode numbers + * reported by readdir in sync with the inode numbers reported + * by stat. + */ +bool proc_fill_cache(struct file *file, struct dir_context *ctx, + const char *name, int len, + instantiate_t instantiate, struct task_struct *task, const void *ptr) { - .d_revalidate = pid_revalidate, - .d_delete = pid_delete_dentry, -}; + struct dentry *child, *dir = file->f_path.dentry; + struct qstr qname = QSTR_INIT(name, len); + struct inode *inode; + unsigned type; + ino_t ino; -static struct dentry_operations pid_base_dentry_operations = + child = d_hash_and_lookup(dir, &qname); + if (!child) { + child = d_alloc(dir, &qname); + if (!child) + goto end_instantiate; + if (instantiate(dir->d_inode, child, task, ptr) < 0) { + dput(child); + goto end_instantiate; + } + } + inode = child->d_inode; + ino = inode->i_ino; + type = inode->i_mode >> 12; + dput(child); + return dir_emit(ctx, name, len, ino, type); + +end_instantiate: + return dir_emit(ctx, name, len, 1, DT_UNKNOWN); +} + +#ifdef CONFIG_CHECKPOINT_RESTORE + +/* + * dname_to_vma_addr - maps a dentry name into two unsigned longs + * which represent vma start and end addresses. + */ +static int dname_to_vma_addr(struct dentry *dentry, + unsigned long *start, unsigned long *end) { - .d_revalidate = pid_revalidate, - .d_iput = pid_base_iput, - .d_delete = pid_delete_dentry, -}; + if (sscanf(dentry->d_name.name, "%lx-%lx", start, end) != 2) + return -EINVAL; -/* Lookups */ + return 0; +} -static unsigned name_to_int(struct dentry *dentry) +static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags) { - const char *name = dentry->d_name.name; - int len = dentry->d_name.len; - unsigned n = 0; + unsigned long vm_start, vm_end; + bool exact_vma_exists = false; + struct mm_struct *mm = NULL; + struct task_struct *task; + const struct cred *cred; + struct inode *inode; + int status = 0; + + if (flags & LOOKUP_RCU) + return -ECHILD; + + if (!capable(CAP_SYS_ADMIN)) { + status = -EPERM; + goto out_notask; + } + + inode = dentry->d_inode; + task = get_proc_task(inode); + if (!task) + goto out_notask; - if (len > 1 && *name == '0') + mm = mm_access(task, PTRACE_MODE_READ); + if (IS_ERR_OR_NULL(mm)) goto out; - while (len-- > 0) { - unsigned c = *name++ - '0'; - if (c > 9) - goto out; - if (n >= (~0U-9)/10) - goto out; - n *= 10; - n += c; - } - return n; + + if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) { + down_read(&mm->mmap_sem); + exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end); + up_read(&mm->mmap_sem); + } + + mmput(mm); + + if (exact_vma_exists) { + if (task_dumpable(task)) { + rcu_read_lock(); + cred = __task_cred(task); + inode->i_uid = cred->euid; + inode->i_gid = cred->egid; + rcu_read_unlock(); + } else { + inode->i_uid = GLOBAL_ROOT_UID; + inode->i_gid = GLOBAL_ROOT_GID; + } + security_task_to_inode(task, inode); + status = 1; + } + out: - return ~0U; + put_task_struct(task); + +out_notask: + if (status <= 0) + d_drop(dentry); + + return status; } -/* SMP-safe */ -static struct dentry *proc_lookupfd(struct inode * dir, struct dentry * dentry, struct nameidata *nd) +static const struct dentry_operations tid_map_files_dentry_operations = { + .d_revalidate = map_files_d_revalidate, + .d_delete = pid_delete_dentry, +}; + +static int proc_map_files_get_link(struct dentry *dentry, struct path *path) { - struct task_struct *task = proc_task(dir); - unsigned fd = name_to_int(dentry); - struct file * file; - struct files_struct * files; - struct inode *inode; - struct proc_inode *ei; + unsigned long vm_start, vm_end; + struct vm_area_struct *vma; + struct task_struct *task; + struct mm_struct *mm; + int rc; - if (fd == ~0U) + rc = -ENOENT; + task = get_proc_task(dentry->d_inode); + if (!task) goto out; - if (!pid_alive(task)) + + mm = get_task_mm(task); + put_task_struct(task); + if (!mm) goto out; - inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_FD_DIR+fd); + rc = dname_to_vma_addr(dentry, &vm_start, &vm_end); + if (rc) + goto out_mmput; + + rc = -ENOENT; + down_read(&mm->mmap_sem); + vma = find_exact_vma(mm, vm_start, vm_end); + if (vma && vma->vm_file) { + *path = vma->vm_file->f_path; + path_get(path); + rc = 0; + } + up_read(&mm->mmap_sem); + +out_mmput: + mmput(mm); +out: + return rc; +} + +struct map_files_info { + fmode_t mode; + unsigned long len; + unsigned char name[4*sizeof(long)+2]; /* max: %lx-%lx\0 */ +}; + +static int +proc_map_files_instantiate(struct inode *dir, struct dentry *dentry, + struct task_struct *task, const void *ptr) +{ + fmode_t mode = (fmode_t)(unsigned long)ptr; + struct proc_inode *ei; + struct inode *inode; + + inode = proc_pid_make_inode(dir->i_sb, task); if (!inode) - goto out; + return -ENOENT; + ei = PROC_I(inode); - files = get_files_struct(task); - if (!files) - goto out_unlock; - inode->i_mode = S_IFLNK; - rcu_read_lock(); - file = fcheck_files(files, fd); - if (!file) - goto out_unlock2; - if (file->f_mode & 1) - inode->i_mode |= S_IRUSR | S_IXUSR; - if (file->f_mode & 2) - inode->i_mode |= S_IWUSR | S_IXUSR; - rcu_read_unlock(); - put_files_struct(files); + ei->op.proc_get_link = proc_map_files_get_link; + inode->i_op = &proc_pid_link_inode_operations; inode->i_size = 64; - ei->op.proc_get_link = proc_fd_link; - dentry->d_op = &tid_fd_dentry_operations; + inode->i_mode = S_IFLNK; + + if (mode & FMODE_READ) + inode->i_mode |= S_IRUSR; + if (mode & FMODE_WRITE) + inode->i_mode |= S_IWUSR; + + d_set_d_op(dentry, &tid_map_files_dentry_operations); d_add(dentry, inode); - return NULL; -out_unlock2: - rcu_read_unlock(); - put_files_struct(files); -out_unlock: - iput(inode); -out: - return ERR_PTR(-ENOENT); + return 0; } -static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir); -static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd); +static struct dentry *proc_map_files_lookup(struct inode *dir, + struct dentry *dentry, unsigned int flags) +{ + unsigned long vm_start, vm_end; + struct vm_area_struct *vma; + struct task_struct *task; + int result; + struct mm_struct *mm; -static struct file_operations proc_fd_operations = { - .read = generic_read_dir, - .readdir = proc_readfd, -}; + result = -EPERM; + if (!capable(CAP_SYS_ADMIN)) + goto out; -static struct file_operations proc_task_operations = { - .read = generic_read_dir, - .readdir = proc_task_readdir, + result = -ENOENT; + task = get_proc_task(dir); + if (!task) + goto out; + + result = -EACCES; + if (!ptrace_may_access(task, PTRACE_MODE_READ)) + goto out_put_task; + + result = -ENOENT; + if (dname_to_vma_addr(dentry, &vm_start, &vm_end)) + goto out_put_task; + + mm = get_task_mm(task); + if (!mm) + goto out_put_task; + + down_read(&mm->mmap_sem); + vma = find_exact_vma(mm, vm_start, vm_end); + if (!vma) + goto out_no_vma; + + if (vma->vm_file) + result = proc_map_files_instantiate(dir, dentry, task, + (void *)(unsigned long)vma->vm_file->f_mode); + +out_no_vma: + up_read(&mm->mmap_sem); + mmput(mm); +out_put_task: + put_task_struct(task); +out: + return ERR_PTR(result); +} + +static const struct inode_operations proc_map_files_inode_operations = { + .lookup = proc_map_files_lookup, + .permission = proc_fd_permission, + .setattr = proc_setattr, }; -/* - * proc directories can do almost nothing.. - */ -static struct inode_operations proc_fd_inode_operations = { - .lookup = proc_lookupfd, - .permission = proc_permission, +static int +proc_map_files_readdir(struct file *file, struct dir_context *ctx) +{ + struct vm_area_struct *vma; + struct task_struct *task; + struct mm_struct *mm; + unsigned long nr_files, pos, i; + struct flex_array *fa = NULL; + struct map_files_info info; + struct map_files_info *p; + int ret; + + ret = -EPERM; + if (!capable(CAP_SYS_ADMIN)) + goto out; + + ret = -ENOENT; + task = get_proc_task(file_inode(file)); + if (!task) + goto out; + + ret = -EACCES; + if (!ptrace_may_access(task, PTRACE_MODE_READ)) + goto out_put_task; + + ret = 0; + if (!dir_emit_dots(file, ctx)) + goto out_put_task; + + mm = get_task_mm(task); + if (!mm) + goto out_put_task; + down_read(&mm->mmap_sem); + + nr_files = 0; + + /* + * We need two passes here: + * + * 1) Collect vmas of mapped files with mmap_sem taken + * 2) Release mmap_sem and instantiate entries + * + * otherwise we get lockdep complained, since filldir() + * routine might require mmap_sem taken in might_fault(). + */ + + for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) { + if (vma->vm_file && ++pos > ctx->pos) + nr_files++; + } + + if (nr_files) { + fa = flex_array_alloc(sizeof(info), nr_files, + GFP_KERNEL); + if (!fa || flex_array_prealloc(fa, 0, nr_files, + GFP_KERNEL)) { + ret = -ENOMEM; + if (fa) + flex_array_free(fa); + up_read(&mm->mmap_sem); + mmput(mm); + goto out_put_task; + } + for (i = 0, vma = mm->mmap, pos = 2; vma; + vma = vma->vm_next) { + if (!vma->vm_file) + continue; + if (++pos <= ctx->pos) + continue; + + info.mode = vma->vm_file->f_mode; + info.len = snprintf(info.name, + sizeof(info.name), "%lx-%lx", + vma->vm_start, vma->vm_end); + if (flex_array_put(fa, i++, &info, GFP_KERNEL)) + BUG(); + } + } + up_read(&mm->mmap_sem); + + for (i = 0; i < nr_files; i++) { + p = flex_array_get(fa, i); + if (!proc_fill_cache(file, ctx, + p->name, p->len, + proc_map_files_instantiate, + task, + (void *)(unsigned long)p->mode)) + break; + ctx->pos++; + } + if (fa) + flex_array_free(fa); + mmput(mm); + +out_put_task: + put_task_struct(task); +out: + return ret; +} + +static const struct file_operations proc_map_files_operations = { + .read = generic_read_dir, + .iterate = proc_map_files_readdir, + .llseek = default_llseek, }; -static struct inode_operations proc_task_inode_operations = { - .lookup = proc_task_lookup, - .permission = proc_task_permission, +struct timers_private { + struct pid *pid; + struct task_struct *task; + struct sighand_struct *sighand; + struct pid_namespace *ns; + unsigned long flags; }; -#ifdef CONFIG_SECURITY -static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, - size_t count, loff_t *ppos) +static void *timers_start(struct seq_file *m, loff_t *pos) { - struct inode * inode = file->f_dentry->d_inode; - unsigned long page; - ssize_t length; - struct task_struct *task = proc_task(inode); + struct timers_private *tp = m->private; - if (count > PAGE_SIZE) - count = PAGE_SIZE; - if (!(page = __get_free_page(GFP_KERNEL))) - return -ENOMEM; + tp->task = get_pid_task(tp->pid, PIDTYPE_PID); + if (!tp->task) + return ERR_PTR(-ESRCH); - length = security_getprocattr(task, - (char*)file->f_dentry->d_name.name, - (void*)page, count); - if (length >= 0) - length = simple_read_from_buffer(buf, count, ppos, (char *)page, length); - free_page(page); - return length; + tp->sighand = lock_task_sighand(tp->task, &tp->flags); + if (!tp->sighand) + return ERR_PTR(-ESRCH); + + return seq_list_start(&tp->task->signal->posix_timers, *pos); } -static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, - size_t count, loff_t *ppos) -{ - struct inode * inode = file->f_dentry->d_inode; - char *page; - ssize_t length; - struct task_struct *task = proc_task(inode); - - if (count > PAGE_SIZE) - count = PAGE_SIZE; - if (*ppos != 0) { - /* No partial writes. */ - return -EINVAL; +static void *timers_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct timers_private *tp = m->private; + return seq_list_next(v, &tp->task->signal->posix_timers, pos); +} + +static void timers_stop(struct seq_file *m, void *v) +{ + struct timers_private *tp = m->private; + + if (tp->sighand) { + unlock_task_sighand(tp->task, &tp->flags); + tp->sighand = NULL; } - page = (char*)__get_free_page(GFP_USER); - if (!page) + + if (tp->task) { + put_task_struct(tp->task); + tp->task = NULL; + } +} + +static int show_timer(struct seq_file *m, void *v) +{ + struct k_itimer *timer; + struct timers_private *tp = m->private; + int notify; + static char *nstr[] = { + [SIGEV_SIGNAL] = "signal", + [SIGEV_NONE] = "none", + [SIGEV_THREAD] = "thread", + }; + + timer = list_entry((struct list_head *)v, struct k_itimer, list); + notify = timer->it_sigev_notify; + + seq_printf(m, "ID: %d\n", timer->it_id); + seq_printf(m, "signal: %d/%p\n", timer->sigq->info.si_signo, + timer->sigq->info.si_value.sival_ptr); + seq_printf(m, "notify: %s/%s.%d\n", + nstr[notify & ~SIGEV_THREAD_ID], + (notify & SIGEV_THREAD_ID) ? "tid" : "pid", + pid_nr_ns(timer->it_pid, tp->ns)); + seq_printf(m, "ClockID: %d\n", timer->it_clock); + + return 0; +} + +static const struct seq_operations proc_timers_seq_ops = { + .start = timers_start, + .next = timers_next, + .stop = timers_stop, + .show = show_timer, +}; + +static int proc_timers_open(struct inode *inode, struct file *file) +{ + struct timers_private *tp; + + tp = __seq_open_private(file, &proc_timers_seq_ops, + sizeof(struct timers_private)); + if (!tp) return -ENOMEM; - length = -EFAULT; - if (copy_from_user(page, buf, count)) - goto out; - length = security_setprocattr(task, - (char*)file->f_dentry->d_name.name, - (void*)page, count); -out: - free_page((unsigned long) page); - return length; -} + tp->pid = proc_pid(inode); + tp->ns = inode->i_sb->s_fs_info; + return 0; +} -static struct file_operations proc_pid_attr_operations = { - .read = proc_pid_attr_read, - .write = proc_pid_attr_write, +static const struct file_operations proc_timers_operations = { + .open = proc_timers_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_private, }; +#endif /* CONFIG_CHECKPOINT_RESTORE */ -static struct file_operations proc_tid_attr_operations; -static struct inode_operations proc_tid_attr_inode_operations; -static struct file_operations proc_tgid_attr_operations; -static struct inode_operations proc_tgid_attr_inode_operations; -#endif +static int proc_pident_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, const void *ptr) +{ + const struct pid_entry *p = ptr; + struct inode *inode; + struct proc_inode *ei; + + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + goto out; -static int get_tid_list(int index, unsigned int *tids, struct inode *dir); + ei = PROC_I(inode); + inode->i_mode = p->mode; + if (S_ISDIR(inode->i_mode)) + set_nlink(inode, 2); /* Use getattr to fix if necessary */ + if (p->iop) + inode->i_op = p->iop; + if (p->fop) + inode->i_fop = p->fop; + ei->op = p->op; + d_set_d_op(dentry, &pid_dentry_operations); + d_add(dentry, inode); + /* Close the race of the process dying before we return the dentry */ + if (pid_revalidate(dentry, 0)) + return 0; +out: + return -ENOENT; +} -/* SMP-safe */ static struct dentry *proc_pident_lookup(struct inode *dir, struct dentry *dentry, - struct pid_entry *ents) + const struct pid_entry *ents, + unsigned int nents) { - struct inode *inode; int error; - struct task_struct *task = proc_task(dir); - struct pid_entry *p; - struct proc_inode *ei; + struct task_struct *task = get_proc_task(dir); + const struct pid_entry *p, *last; error = -ENOENT; - inode = NULL; - if (!pid_alive(task)) - goto out; + if (!task) + goto out_no_task; - for (p = ents; p->name; p++) { + /* + * Yes, it does not scale. And it should not. Don't add + * new entries into /proc/<tgid>/ without very good reasons. + */ + last = &ents[nents - 1]; + for (p = ents; p <= last; p++) { if (p->len != dentry->d_name.len) continue; if (!memcmp(dentry->d_name.name, p->name, p->len)) break; } - if (!p->name) + if (p > last) goto out; - error = -EINVAL; - inode = proc_pid_make_inode(dir->i_sb, task, p->type); - if (!inode) + error = proc_pident_instantiate(dir, dentry, task, p); +out: + put_task_struct(task); +out_no_task: + return ERR_PTR(error); +} + +static int proc_pident_readdir(struct file *file, struct dir_context *ctx, + const struct pid_entry *ents, unsigned int nents) +{ + struct task_struct *task = get_proc_task(file_inode(file)); + const struct pid_entry *p; + + if (!task) + return -ENOENT; + + if (!dir_emit_dots(file, ctx)) goto out; - ei = PROC_I(inode); - inode->i_mode = p->mode; - /* - * Yes, it does not scale. And it should not. Don't add - * new entries into /proc/<tgid>/ without very good reasons. - */ - switch(p->type) { - case PROC_TGID_TASK: - inode->i_nlink = 2 + get_tid_list(2, NULL, dir); - inode->i_op = &proc_task_inode_operations; - inode->i_fop = &proc_task_operations; - break; - case PROC_TID_FD: - case PROC_TGID_FD: - inode->i_nlink = 2; - inode->i_op = &proc_fd_inode_operations; - inode->i_fop = &proc_fd_operations; - break; - case PROC_TID_EXE: - case PROC_TGID_EXE: - inode->i_op = &proc_pid_link_inode_operations; - ei->op.proc_get_link = proc_exe_link; - break; - case PROC_TID_CWD: - case PROC_TGID_CWD: - inode->i_op = &proc_pid_link_inode_operations; - ei->op.proc_get_link = proc_cwd_link; - break; - case PROC_TID_ROOT: - case PROC_TGID_ROOT: - inode->i_op = &proc_pid_link_inode_operations; - ei->op.proc_get_link = proc_root_link; - break; - case PROC_TID_ENVIRON: - case PROC_TGID_ENVIRON: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_environ; - break; - case PROC_TID_AUXV: - case PROC_TGID_AUXV: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_auxv; - break; - case PROC_TID_STATUS: - case PROC_TGID_STATUS: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_status; - break; - case PROC_TID_STAT: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_tid_stat; - break; - case PROC_TGID_STAT: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_tgid_stat; - break; - case PROC_TID_CMDLINE: - case PROC_TGID_CMDLINE: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_cmdline; - break; - case PROC_TID_STATM: - case PROC_TGID_STATM: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_statm; - break; - case PROC_TID_MAPS: - case PROC_TGID_MAPS: - inode->i_fop = &proc_maps_operations; - break; -#ifdef CONFIG_NUMA - case PROC_TID_NUMA_MAPS: - case PROC_TGID_NUMA_MAPS: - inode->i_fop = &proc_numa_maps_operations; - break; -#endif - case PROC_TID_MEM: - case PROC_TGID_MEM: - inode->i_op = &proc_mem_inode_operations; - inode->i_fop = &proc_mem_operations; - break; -#ifdef CONFIG_SECCOMP - case PROC_TID_SECCOMP: - case PROC_TGID_SECCOMP: - inode->i_fop = &proc_seccomp_operations; - break; -#endif /* CONFIG_SECCOMP */ - case PROC_TID_MOUNTS: - case PROC_TGID_MOUNTS: - inode->i_fop = &proc_mounts_operations; - break; -#ifdef CONFIG_MMU - case PROC_TID_SMAPS: - case PROC_TGID_SMAPS: - inode->i_fop = &proc_smaps_operations; - break; -#endif -#ifdef CONFIG_SECURITY - case PROC_TID_ATTR: - inode->i_nlink = 2; - inode->i_op = &proc_tid_attr_inode_operations; - inode->i_fop = &proc_tid_attr_operations; - break; - case PROC_TGID_ATTR: - inode->i_nlink = 2; - inode->i_op = &proc_tgid_attr_inode_operations; - inode->i_fop = &proc_tgid_attr_operations; - break; - case PROC_TID_ATTR_CURRENT: - case PROC_TGID_ATTR_CURRENT: - case PROC_TID_ATTR_PREV: - case PROC_TGID_ATTR_PREV: - case PROC_TID_ATTR_EXEC: - case PROC_TGID_ATTR_EXEC: - case PROC_TID_ATTR_FSCREATE: - case PROC_TGID_ATTR_FSCREATE: - inode->i_fop = &proc_pid_attr_operations; - break; -#endif -#ifdef CONFIG_KALLSYMS - case PROC_TID_WCHAN: - case PROC_TGID_WCHAN: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_wchan; - break; -#endif -#ifdef CONFIG_SCHEDSTATS - case PROC_TID_SCHEDSTAT: - case PROC_TGID_SCHEDSTAT: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_pid_schedstat; - break; -#endif -#ifdef CONFIG_CPUSETS - case PROC_TID_CPUSET: - case PROC_TGID_CPUSET: - inode->i_fop = &proc_cpuset_operations; - break; -#endif - case PROC_TID_OOM_SCORE: - case PROC_TGID_OOM_SCORE: - inode->i_fop = &proc_info_file_operations; - ei->op.proc_read = proc_oom_score; - break; - case PROC_TID_OOM_ADJUST: - case PROC_TGID_OOM_ADJUST: - inode->i_fop = &proc_oom_adjust_operations; - break; -#ifdef CONFIG_AUDITSYSCALL - case PROC_TID_LOGINUID: - case PROC_TGID_LOGINUID: - inode->i_fop = &proc_loginuid_operations; + if (ctx->pos >= nents + 2) + goto out; + + for (p = ents + (ctx->pos - 2); p <= ents + nents - 1; p++) { + if (!proc_fill_cache(file, ctx, p->name, p->len, + proc_pident_instantiate, task, p)) break; -#endif - default: - printk("procfs: impossible type (%d)",p->type); - iput(inode); - return ERR_PTR(-EINVAL); + ctx->pos++; } - dentry->d_op = &pid_dentry_operations; - d_add(dentry, inode); - return NULL; - out: - return ERR_PTR(error); + put_task_struct(task); + return 0; } -static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ - return proc_pident_lookup(dir, dentry, tgid_base_stuff); +#ifdef CONFIG_SECURITY +static ssize_t proc_pid_attr_read(struct file * file, char __user * buf, + size_t count, loff_t *ppos) +{ + struct inode * inode = file_inode(file); + char *p = NULL; + ssize_t length; + struct task_struct *task = get_proc_task(inode); + + if (!task) + return -ESRCH; + + length = security_getprocattr(task, + (char*)file->f_path.dentry->d_name.name, + &p); + put_task_struct(task); + if (length > 0) + length = simple_read_from_buffer(buf, count, ppos, p, length); + kfree(p); + return length; } -static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd){ - return proc_pident_lookup(dir, dentry, tid_base_stuff); +static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf, + size_t count, loff_t *ppos) +{ + struct inode * inode = file_inode(file); + char *page; + ssize_t length; + struct task_struct *task = get_proc_task(inode); + + length = -ESRCH; + if (!task) + goto out_no_task; + if (count > PAGE_SIZE) + count = PAGE_SIZE; + + /* No partial writes. */ + length = -EINVAL; + if (*ppos != 0) + goto out; + + length = -ENOMEM; + page = (char*)__get_free_page(GFP_TEMPORARY); + if (!page) + goto out; + + length = -EFAULT; + if (copy_from_user(page, buf, count)) + goto out_free; + + /* Guard against adverse ptrace interaction */ + length = mutex_lock_interruptible(&task->signal->cred_guard_mutex); + if (length < 0) + goto out_free; + + length = security_setprocattr(task, + (char*)file->f_path.dentry->d_name.name, + (void*)page, count); + mutex_unlock(&task->signal->cred_guard_mutex); +out_free: + free_page((unsigned long) page); +out: + put_task_struct(task); +out_no_task: + return length; } -static struct file_operations proc_tgid_base_operations = { - .read = generic_read_dir, - .readdir = proc_tgid_base_readdir, +static const struct file_operations proc_pid_attr_operations = { + .read = proc_pid_attr_read, + .write = proc_pid_attr_write, + .llseek = generic_file_llseek, }; -static struct file_operations proc_tid_base_operations = { - .read = generic_read_dir, - .readdir = proc_tid_base_readdir, +static const struct pid_entry attr_dir_stuff[] = { + REG("current", S_IRUGO|S_IWUGO, proc_pid_attr_operations), + REG("prev", S_IRUGO, proc_pid_attr_operations), + REG("exec", S_IRUGO|S_IWUGO, proc_pid_attr_operations), + REG("fscreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations), + REG("keycreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations), + REG("sockcreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations), }; -static struct inode_operations proc_tgid_base_inode_operations = { - .lookup = proc_tgid_base_lookup, +static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx) +{ + return proc_pident_readdir(file, ctx, + attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff)); +} + +static const struct file_operations proc_attr_dir_operations = { + .read = generic_read_dir, + .iterate = proc_attr_dir_readdir, + .llseek = default_llseek, }; -static struct inode_operations proc_tid_base_inode_operations = { - .lookup = proc_tid_base_lookup, +static struct dentry *proc_attr_dir_lookup(struct inode *dir, + struct dentry *dentry, unsigned int flags) +{ + return proc_pident_lookup(dir, dentry, + attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff)); +} + +static const struct inode_operations proc_attr_dir_inode_operations = { + .lookup = proc_attr_dir_lookup, + .getattr = pid_getattr, + .setattr = proc_setattr, }; -#ifdef CONFIG_SECURITY -static int proc_tgid_attr_readdir(struct file * filp, - void * dirent, filldir_t filldir) +#endif + +#ifdef CONFIG_ELF_CORE +static ssize_t proc_coredump_filter_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) { - return proc_pident_readdir(filp,dirent,filldir, - tgid_attr_stuff,ARRAY_SIZE(tgid_attr_stuff)); + struct task_struct *task = get_proc_task(file_inode(file)); + struct mm_struct *mm; + char buffer[PROC_NUMBUF]; + size_t len; + int ret; + + if (!task) + return -ESRCH; + + ret = 0; + mm = get_task_mm(task); + if (mm) { + len = snprintf(buffer, sizeof(buffer), "%08lx\n", + ((mm->flags & MMF_DUMP_FILTER_MASK) >> + MMF_DUMP_FILTER_SHIFT)); + mmput(mm); + ret = simple_read_from_buffer(buf, count, ppos, buffer, len); + } + + put_task_struct(task); + + return ret; } -static int proc_tid_attr_readdir(struct file * filp, - void * dirent, filldir_t filldir) +static ssize_t proc_coredump_filter_write(struct file *file, + const char __user *buf, + size_t count, + loff_t *ppos) { - return proc_pident_readdir(filp,dirent,filldir, - tid_attr_stuff,ARRAY_SIZE(tid_attr_stuff)); + struct task_struct *task; + struct mm_struct *mm; + char buffer[PROC_NUMBUF], *end; + unsigned int val; + int ret; + int i; + unsigned long mask; + + ret = -EFAULT; + memset(buffer, 0, sizeof(buffer)); + if (count > sizeof(buffer) - 1) + count = sizeof(buffer) - 1; + if (copy_from_user(buffer, buf, count)) + goto out_no_task; + + ret = -EINVAL; + val = (unsigned int)simple_strtoul(buffer, &end, 0); + if (*end == '\n') + end++; + if (end - buffer == 0) + goto out_no_task; + + ret = -ESRCH; + task = get_proc_task(file_inode(file)); + if (!task) + goto out_no_task; + + ret = end - buffer; + mm = get_task_mm(task); + if (!mm) + goto out_no_mm; + + for (i = 0, mask = 1; i < MMF_DUMP_FILTER_BITS; i++, mask <<= 1) { + if (val & mask) + set_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags); + else + clear_bit(i + MMF_DUMP_FILTER_SHIFT, &mm->flags); + } + + mmput(mm); + out_no_mm: + put_task_struct(task); + out_no_task: + return ret; } -static struct file_operations proc_tgid_attr_operations = { - .read = generic_read_dir, - .readdir = proc_tgid_attr_readdir, +static const struct file_operations proc_coredump_filter_operations = { + .read = proc_coredump_filter_read, + .write = proc_coredump_filter_write, + .llseek = generic_file_llseek, }; +#endif -static struct file_operations proc_tid_attr_operations = { - .read = generic_read_dir, - .readdir = proc_tid_attr_readdir, -}; +#ifdef CONFIG_TASK_IO_ACCOUNTING +static int do_io_accounting(struct task_struct *task, char *buffer, int whole) +{ + struct task_io_accounting acct = task->ioac; + unsigned long flags; + int result; + + result = mutex_lock_killable(&task->signal->cred_guard_mutex); + if (result) + return result; + + if (!ptrace_may_access(task, PTRACE_MODE_READ)) { + result = -EACCES; + goto out_unlock; + } + + if (whole && lock_task_sighand(task, &flags)) { + struct task_struct *t = task; + + task_io_accounting_add(&acct, &task->signal->ioac); + while_each_thread(task, t) + task_io_accounting_add(&acct, &t->ioac); + + unlock_task_sighand(task, &flags); + } + result = sprintf(buffer, + "rchar: %llu\n" + "wchar: %llu\n" + "syscr: %llu\n" + "syscw: %llu\n" + "read_bytes: %llu\n" + "write_bytes: %llu\n" + "cancelled_write_bytes: %llu\n", + (unsigned long long)acct.rchar, + (unsigned long long)acct.wchar, + (unsigned long long)acct.syscr, + (unsigned long long)acct.syscw, + (unsigned long long)acct.read_bytes, + (unsigned long long)acct.write_bytes, + (unsigned long long)acct.cancelled_write_bytes); +out_unlock: + mutex_unlock(&task->signal->cred_guard_mutex); + return result; +} + +static int proc_tid_io_accounting(struct task_struct *task, char *buffer) +{ + return do_io_accounting(task, buffer, 0); +} + +static int proc_tgid_io_accounting(struct task_struct *task, char *buffer) +{ + return do_io_accounting(task, buffer, 1); +} +#endif /* CONFIG_TASK_IO_ACCOUNTING */ + +#ifdef CONFIG_USER_NS +static int proc_id_map_open(struct inode *inode, struct file *file, + struct seq_operations *seq_ops) +{ + struct user_namespace *ns = NULL; + struct task_struct *task; + struct seq_file *seq; + int ret = -EINVAL; + + task = get_proc_task(inode); + if (task) { + rcu_read_lock(); + ns = get_user_ns(task_cred_xxx(task, user_ns)); + rcu_read_unlock(); + put_task_struct(task); + } + if (!ns) + goto err; + + ret = seq_open(file, seq_ops); + if (ret) + goto err_put_ns; + + seq = file->private_data; + seq->private = ns; + + return 0; +err_put_ns: + put_user_ns(ns); +err: + return ret; +} + +static int proc_id_map_release(struct inode *inode, struct file *file) +{ + struct seq_file *seq = file->private_data; + struct user_namespace *ns = seq->private; + put_user_ns(ns); + return seq_release(inode, file); +} + +static int proc_uid_map_open(struct inode *inode, struct file *file) +{ + return proc_id_map_open(inode, file, &proc_uid_seq_operations); +} -static struct dentry *proc_tgid_attr_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) +static int proc_gid_map_open(struct inode *inode, struct file *file) { - return proc_pident_lookup(dir, dentry, tgid_attr_stuff); + return proc_id_map_open(inode, file, &proc_gid_seq_operations); } -static struct dentry *proc_tid_attr_lookup(struct inode *dir, - struct dentry *dentry, struct nameidata *nd) +static int proc_projid_map_open(struct inode *inode, struct file *file) { - return proc_pident_lookup(dir, dentry, tid_attr_stuff); + return proc_id_map_open(inode, file, &proc_projid_seq_operations); } -static struct inode_operations proc_tgid_attr_inode_operations = { - .lookup = proc_tgid_attr_lookup, +static const struct file_operations proc_uid_map_operations = { + .open = proc_uid_map_open, + .write = proc_uid_map_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_id_map_release, }; -static struct inode_operations proc_tid_attr_inode_operations = { - .lookup = proc_tid_attr_lookup, +static const struct file_operations proc_gid_map_operations = { + .open = proc_gid_map_open, + .write = proc_gid_map_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_id_map_release, }; -#endif + +static const struct file_operations proc_projid_map_operations = { + .open = proc_projid_map_open, + .write = proc_projid_map_write, + .read = seq_read, + .llseek = seq_lseek, + .release = proc_id_map_release, +}; +#endif /* CONFIG_USER_NS */ + +static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) +{ + int err = lock_trace(task); + if (!err) { + seq_printf(m, "%08x\n", task->personality); + unlock_trace(task); + } + return err; +} /* - * /proc/self: + * Thread groups */ -static int proc_self_readlink(struct dentry *dentry, char __user *buffer, - int buflen) +static const struct file_operations proc_task_operations; +static const struct inode_operations proc_task_inode_operations; + +static const struct pid_entry tgid_base_stuff[] = { + DIR("task", S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations), + DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), +#ifdef CONFIG_CHECKPOINT_RESTORE + DIR("map_files", S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations), +#endif + DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations), + DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), +#ifdef CONFIG_NET + DIR("net", S_IRUGO|S_IXUGO, proc_net_inode_operations, proc_net_operations), +#endif + REG("environ", S_IRUSR, proc_environ_operations), + INF("auxv", S_IRUSR, proc_pid_auxv), + ONE("status", S_IRUGO, proc_pid_status), + ONE("personality", S_IRUSR, proc_pid_personality), + INF("limits", S_IRUGO, proc_pid_limits), +#ifdef CONFIG_SCHED_DEBUG + REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), +#endif +#ifdef CONFIG_SCHED_AUTOGROUP + REG("autogroup", S_IRUGO|S_IWUSR, proc_pid_sched_autogroup_operations), +#endif + REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), +#ifdef CONFIG_HAVE_ARCH_TRACEHOOK + INF("syscall", S_IRUSR, proc_pid_syscall), +#endif + INF("cmdline", S_IRUGO, proc_pid_cmdline), + ONE("stat", S_IRUGO, proc_tgid_stat), + ONE("statm", S_IRUGO, proc_pid_statm), + REG("maps", S_IRUGO, proc_pid_maps_operations), +#ifdef CONFIG_NUMA + REG("numa_maps", S_IRUGO, proc_pid_numa_maps_operations), +#endif + REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations), + LNK("cwd", proc_cwd_link), + LNK("root", proc_root_link), + LNK("exe", proc_exe_link), + REG("mounts", S_IRUGO, proc_mounts_operations), + REG("mountinfo", S_IRUGO, proc_mountinfo_operations), + REG("mountstats", S_IRUSR, proc_mountstats_operations), +#ifdef CONFIG_PROC_PAGE_MONITOR + REG("clear_refs", S_IWUSR, proc_clear_refs_operations), + REG("smaps", S_IRUGO, proc_pid_smaps_operations), + REG("pagemap", S_IRUSR, proc_pagemap_operations), +#endif +#ifdef CONFIG_SECURITY + DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), +#endif +#ifdef CONFIG_KALLSYMS + INF("wchan", S_IRUGO, proc_pid_wchan), +#endif +#ifdef CONFIG_STACKTRACE + ONE("stack", S_IRUSR, proc_pid_stack), +#endif +#ifdef CONFIG_SCHEDSTATS + INF("schedstat", S_IRUGO, proc_pid_schedstat), +#endif +#ifdef CONFIG_LATENCYTOP + REG("latency", S_IRUGO, proc_lstats_operations), +#endif +#ifdef CONFIG_PROC_PID_CPUSET + REG("cpuset", S_IRUGO, proc_cpuset_operations), +#endif +#ifdef CONFIG_CGROUPS + REG("cgroup", S_IRUGO, proc_cgroup_operations), +#endif + INF("oom_score", S_IRUGO, proc_oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), + REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), +#ifdef CONFIG_AUDITSYSCALL + REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), + REG("sessionid", S_IRUGO, proc_sessionid_operations), +#endif +#ifdef CONFIG_FAULT_INJECTION + REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), +#endif +#ifdef CONFIG_ELF_CORE + REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations), +#endif +#ifdef CONFIG_TASK_IO_ACCOUNTING + INF("io", S_IRUSR, proc_tgid_io_accounting), +#endif +#ifdef CONFIG_HARDWALL + INF("hardwall", S_IRUGO, proc_pid_hardwall), +#endif +#ifdef CONFIG_USER_NS + REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), + REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), + REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), +#endif +#ifdef CONFIG_CHECKPOINT_RESTORE + REG("timers", S_IRUGO, proc_timers_operations), +#endif +}; + +static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) { - char tmp[30]; - sprintf(tmp, "%d", current->tgid); - return vfs_readlink(dentry,buffer,buflen,tmp); + return proc_pident_readdir(file, ctx, + tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); } -static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd) +static const struct file_operations proc_tgid_base_operations = { + .read = generic_read_dir, + .iterate = proc_tgid_base_readdir, + .llseek = default_llseek, +}; + +static struct dentry *proc_tgid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { - char tmp[30]; - sprintf(tmp, "%d", current->tgid); - return ERR_PTR(vfs_follow_link(nd,tmp)); -} + return proc_pident_lookup(dir, dentry, + tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff)); +} -static struct inode_operations proc_self_inode_operations = { - .readlink = proc_self_readlink, - .follow_link = proc_self_follow_link, +static const struct inode_operations proc_tgid_base_inode_operations = { + .lookup = proc_tgid_base_lookup, + .getattr = pid_getattr, + .setattr = proc_setattr, + .permission = proc_pid_permission, }; +static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid) +{ + struct dentry *dentry, *leader, *dir; + char buf[PROC_NUMBUF]; + struct qstr name; + + name.name = buf; + name.len = snprintf(buf, sizeof(buf), "%d", pid); + /* no ->d_hash() rejects on procfs */ + dentry = d_hash_and_lookup(mnt->mnt_root, &name); + if (dentry) { + shrink_dcache_parent(dentry); + d_drop(dentry); + dput(dentry); + } + + name.name = buf; + name.len = snprintf(buf, sizeof(buf), "%d", tgid); + leader = d_hash_and_lookup(mnt->mnt_root, &name); + if (!leader) + goto out; + + name.name = "task"; + name.len = strlen(name.name); + dir = d_hash_and_lookup(leader, &name); + if (!dir) + goto out_put_leader; + + name.name = buf; + name.len = snprintf(buf, sizeof(buf), "%d", pid); + dentry = d_hash_and_lookup(dir, &name); + if (dentry) { + shrink_dcache_parent(dentry); + d_drop(dentry); + dput(dentry); + } + + dput(dir); +out_put_leader: + dput(leader); +out: + return; +} + /** - * proc_pid_unhash - Unhash /proc/@pid entry from the dcache. - * @p: task that should be flushed. + * proc_flush_task - Remove dcache entries for @task from the /proc dcache. + * @task: task that should be flushed. + * + * When flushing dentries from proc, one needs to flush them from global + * proc (proc_mnt) and from all the namespaces' procs this task was seen + * in. This call is supposed to do all of this job. + * + * Looks in the dcache for + * /proc/@pid + * /proc/@tgid/task/@pid + * if either directory is present flushes it and all of it'ts children + * from the dcache. * - * Drops the /proc/@pid dcache entry from the hash chains. + * It is safe and reasonable to cache /proc entries for a task until + * that task exits. After that they just clog up the dcache with + * useless entries, possibly causing useful dcache entries to be + * flushed instead. This routine is proved to flush those useless + * dcache entries at process exit time. * - * Dropping /proc/@pid entries and detach_pid must be synchroneous, - * otherwise e.g. /proc/@pid/exe might point to the wrong executable, - * if the pid value is immediately reused. This is enforced by - * - caller must acquire spin_lock(p->proc_lock) - * - must be called before detach_pid() - * - proc_pid_lookup acquires proc_lock, and checks that - * the target is not dead by looking at the attach count - * of PIDTYPE_PID. + * NOTE: This routine is just an optimization so it does not guarantee + * that no dcache entries will exist at process exit time it + * just makes it very unlikely that any will persist. */ -struct dentry *proc_pid_unhash(struct task_struct *p) +void proc_flush_task(struct task_struct *task) { - struct dentry *proc_dentry; + int i; + struct pid *pid, *tgid; + struct upid *upid; - proc_dentry = p->proc_dentry; - if (proc_dentry != NULL) { + pid = task_pid(task); + tgid = task_tgid(task); - spin_lock(&dcache_lock); - spin_lock(&proc_dentry->d_lock); - if (!d_unhashed(proc_dentry)) { - dget_locked(proc_dentry); - __d_drop(proc_dentry); - spin_unlock(&proc_dentry->d_lock); - } else { - spin_unlock(&proc_dentry->d_lock); - proc_dentry = NULL; - } - spin_unlock(&dcache_lock); + for (i = 0; i <= pid->level; i++) { + upid = &pid->numbers[i]; + proc_flush_task_mnt(upid->ns->proc_mnt, upid->nr, + tgid->numbers[i].nr); } - return proc_dentry; } -/** - * proc_pid_flush - recover memory used by stale /proc/@pid/x entries - * @proc_dentry: directoy to prune. - * - * Shrink the /proc directory that was used by the just killed thread. - */ - -void proc_pid_flush(struct dentry *proc_dentry) +static int proc_pid_instantiate(struct inode *dir, + struct dentry * dentry, + struct task_struct *task, const void *ptr) { - might_sleep(); - if(proc_dentry != NULL) { - shrink_dcache_parent(proc_dentry); - dput(proc_dentry); - } + struct inode *inode; + + inode = proc_pid_make_inode(dir->i_sb, task); + if (!inode) + goto out; + + inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; + inode->i_op = &proc_tgid_base_inode_operations; + inode->i_fop = &proc_tgid_base_operations; + inode->i_flags|=S_IMMUTABLE; + + set_nlink(inode, 2 + pid_entry_count_dirs(tgid_base_stuff, + ARRAY_SIZE(tgid_base_stuff))); + + d_set_d_op(dentry, &pid_dentry_operations); + + d_add(dentry, inode); + /* Close the race of the process dying before we return the dentry */ + if (pid_revalidate(dentry, 0)) + return 0; +out: + return -ENOENT; } -/* SMP-safe */ -struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { + int result = 0; struct task_struct *task; - struct inode *inode; - struct proc_inode *ei; unsigned tgid; - int died; - - if (dentry->d_name.len == 4 && !memcmp(dentry->d_name.name,"self",4)) { - inode = new_inode(dir->i_sb); - if (!inode) - return ERR_PTR(-ENOMEM); - ei = PROC_I(inode); - inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; - inode->i_ino = fake_ino(0, PROC_TGID_INO); - ei->pde = NULL; - inode->i_mode = S_IFLNK|S_IRWXUGO; - inode->i_uid = inode->i_gid = 0; - inode->i_size = 64; - inode->i_op = &proc_self_inode_operations; - d_add(dentry, inode); - return NULL; - } + struct pid_namespace *ns; + tgid = name_to_int(dentry); if (tgid == ~0U) goto out; - read_lock(&tasklist_lock); - task = find_task_by_pid(tgid); + ns = dentry->d_sb->s_fs_info; + rcu_read_lock(); + task = find_task_by_pid_ns(tgid, ns); if (task) get_task_struct(task); - read_unlock(&tasklist_lock); + rcu_read_unlock(); if (!task) goto out; - inode = proc_pid_make_inode(dir->i_sb, task, PROC_TGID_INO); + result = proc_pid_instantiate(dir, dentry, task, NULL); + put_task_struct(task); +out: + return ERR_PTR(result); +} + +/* + * Find the first task with tgid >= tgid + * + */ +struct tgid_iter { + unsigned int tgid; + struct task_struct *task; +}; +static struct tgid_iter next_tgid(struct pid_namespace *ns, struct tgid_iter iter) +{ + struct pid *pid; + if (iter.task) + put_task_struct(iter.task); + rcu_read_lock(); +retry: + iter.task = NULL; + pid = find_ge_pid(iter.tgid, ns); + if (pid) { + iter.tgid = pid_nr_ns(pid, ns); + iter.task = pid_task(pid, PIDTYPE_PID); + /* What we to know is if the pid we have find is the + * pid of a thread_group_leader. Testing for task + * being a thread_group_leader is the obvious thing + * todo but there is a window when it fails, due to + * the pid transfer logic in de_thread. + * + * So we perform the straight forward test of seeing + * if the pid we have found is the pid of a thread + * group leader, and don't worry if the task we have + * found doesn't happen to be a thread group leader. + * As we don't care in the case of readdir. + */ + if (!iter.task || !has_group_leader_pid(iter.task)) { + iter.tgid += 1; + goto retry; + } + get_task_struct(iter.task); + } + rcu_read_unlock(); + return iter; +} - if (!inode) { - put_task_struct(task); - goto out; +#define TGID_OFFSET (FIRST_PROCESS_ENTRY + 1) + +/* for the /proc/ directory itself, after non-process stuff has been done */ +int proc_pid_readdir(struct file *file, struct dir_context *ctx) +{ + struct tgid_iter iter; + struct pid_namespace *ns = file->f_dentry->d_sb->s_fs_info; + loff_t pos = ctx->pos; + + if (pos >= PID_MAX_LIMIT + TGID_OFFSET) + return 0; + + if (pos == TGID_OFFSET - 1) { + struct inode *inode = ns->proc_self->d_inode; + if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK)) + return 0; + iter.tgid = 0; + } else { + iter.tgid = pos - TGID_OFFSET; } - inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; - inode->i_op = &proc_tgid_base_inode_operations; - inode->i_fop = &proc_tgid_base_operations; - inode->i_flags|=S_IMMUTABLE; + iter.task = NULL; + for (iter = next_tgid(ns, iter); + iter.task; + iter.tgid += 1, iter = next_tgid(ns, iter)) { + char name[PROC_NUMBUF]; + int len; + if (!has_pid_permissions(ns, iter.task, 2)) + continue; + + len = snprintf(name, sizeof(name), "%d", iter.tgid); + ctx->pos = iter.tgid + TGID_OFFSET; + if (!proc_fill_cache(file, ctx, name, len, + proc_pid_instantiate, iter.task, NULL)) { + put_task_struct(iter.task); + return 0; + } + } + ctx->pos = PID_MAX_LIMIT + TGID_OFFSET; + return 0; +} + +/* + * Tasks + */ +static const struct pid_entry tid_base_stuff[] = { + DIR("fd", S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations), + DIR("fdinfo", S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations), + DIR("ns", S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations), + REG("environ", S_IRUSR, proc_environ_operations), + INF("auxv", S_IRUSR, proc_pid_auxv), + ONE("status", S_IRUGO, proc_pid_status), + ONE("personality", S_IRUSR, proc_pid_personality), + INF("limits", S_IRUGO, proc_pid_limits), +#ifdef CONFIG_SCHED_DEBUG + REG("sched", S_IRUGO|S_IWUSR, proc_pid_sched_operations), +#endif + REG("comm", S_IRUGO|S_IWUSR, proc_pid_set_comm_operations), +#ifdef CONFIG_HAVE_ARCH_TRACEHOOK + INF("syscall", S_IRUSR, proc_pid_syscall), +#endif + INF("cmdline", S_IRUGO, proc_pid_cmdline), + ONE("stat", S_IRUGO, proc_tid_stat), + ONE("statm", S_IRUGO, proc_pid_statm), + REG("maps", S_IRUGO, proc_tid_maps_operations), +#ifdef CONFIG_CHECKPOINT_RESTORE + REG("children", S_IRUGO, proc_tid_children_operations), +#endif +#ifdef CONFIG_NUMA + REG("numa_maps", S_IRUGO, proc_tid_numa_maps_operations), +#endif + REG("mem", S_IRUSR|S_IWUSR, proc_mem_operations), + LNK("cwd", proc_cwd_link), + LNK("root", proc_root_link), + LNK("exe", proc_exe_link), + REG("mounts", S_IRUGO, proc_mounts_operations), + REG("mountinfo", S_IRUGO, proc_mountinfo_operations), +#ifdef CONFIG_PROC_PAGE_MONITOR + REG("clear_refs", S_IWUSR, proc_clear_refs_operations), + REG("smaps", S_IRUGO, proc_tid_smaps_operations), + REG("pagemap", S_IRUSR, proc_pagemap_operations), +#endif #ifdef CONFIG_SECURITY - inode->i_nlink = 5; -#else - inode->i_nlink = 4; + DIR("attr", S_IRUGO|S_IXUGO, proc_attr_dir_inode_operations, proc_attr_dir_operations), +#endif +#ifdef CONFIG_KALLSYMS + INF("wchan", S_IRUGO, proc_pid_wchan), +#endif +#ifdef CONFIG_STACKTRACE + ONE("stack", S_IRUSR, proc_pid_stack), #endif +#ifdef CONFIG_SCHEDSTATS + INF("schedstat", S_IRUGO, proc_pid_schedstat), +#endif +#ifdef CONFIG_LATENCYTOP + REG("latency", S_IRUGO, proc_lstats_operations), +#endif +#ifdef CONFIG_PROC_PID_CPUSET + REG("cpuset", S_IRUGO, proc_cpuset_operations), +#endif +#ifdef CONFIG_CGROUPS + REG("cgroup", S_IRUGO, proc_cgroup_operations), +#endif + INF("oom_score", S_IRUGO, proc_oom_score), + REG("oom_adj", S_IRUGO|S_IWUSR, proc_oom_adj_operations), + REG("oom_score_adj", S_IRUGO|S_IWUSR, proc_oom_score_adj_operations), +#ifdef CONFIG_AUDITSYSCALL + REG("loginuid", S_IWUSR|S_IRUGO, proc_loginuid_operations), + REG("sessionid", S_IRUGO, proc_sessionid_operations), +#endif +#ifdef CONFIG_FAULT_INJECTION + REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations), +#endif +#ifdef CONFIG_TASK_IO_ACCOUNTING + INF("io", S_IRUSR, proc_tid_io_accounting), +#endif +#ifdef CONFIG_HARDWALL + INF("hardwall", S_IRUGO, proc_pid_hardwall), +#endif +#ifdef CONFIG_USER_NS + REG("uid_map", S_IRUGO|S_IWUSR, proc_uid_map_operations), + REG("gid_map", S_IRUGO|S_IWUSR, proc_gid_map_operations), + REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations), +#endif +}; - dentry->d_op = &pid_base_dentry_operations; +static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx) +{ + return proc_pident_readdir(file, ctx, + tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); +} - died = 0; - d_add(dentry, inode); - spin_lock(&task->proc_lock); - task->proc_dentry = dentry; - if (!pid_alive(task)) { - dentry = proc_pid_unhash(task); - died = 1; - } - spin_unlock(&task->proc_lock); +static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) +{ + return proc_pident_lookup(dir, dentry, + tid_base_stuff, ARRAY_SIZE(tid_base_stuff)); +} - put_task_struct(task); - if (died) { - proc_pid_flush(dentry); +static const struct file_operations proc_tid_base_operations = { + .read = generic_read_dir, + .iterate = proc_tid_base_readdir, + .llseek = default_llseek, +}; + +static const struct inode_operations proc_tid_base_inode_operations = { + .lookup = proc_tid_base_lookup, + .getattr = pid_getattr, + .setattr = proc_setattr, +}; + +static int proc_task_instantiate(struct inode *dir, + struct dentry *dentry, struct task_struct *task, const void *ptr) +{ + struct inode *inode; + inode = proc_pid_make_inode(dir->i_sb, task); + + if (!inode) goto out; - } - return NULL; + inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; + inode->i_op = &proc_tid_base_inode_operations; + inode->i_fop = &proc_tid_base_operations; + inode->i_flags|=S_IMMUTABLE; + + set_nlink(inode, 2 + pid_entry_count_dirs(tid_base_stuff, + ARRAY_SIZE(tid_base_stuff))); + + d_set_d_op(dentry, &pid_dentry_operations); + + d_add(dentry, inode); + /* Close the race of the process dying before we return the dentry */ + if (pid_revalidate(dentry, 0)) + return 0; out: - return ERR_PTR(-ENOENT); + return -ENOENT; } -/* SMP-safe */ -static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) +static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { + int result = -ENOENT; struct task_struct *task; - struct task_struct *leader = proc_task(dir); - struct inode *inode; + struct task_struct *leader = get_proc_task(dir); unsigned tid; + struct pid_namespace *ns; + + if (!leader) + goto out_no_task; tid = name_to_int(dentry); if (tid == ~0U) goto out; - read_lock(&tasklist_lock); - task = find_task_by_pid(tid); + ns = dentry->d_sb->s_fs_info; + rcu_read_lock(); + task = find_task_by_pid_ns(tid, ns); if (task) get_task_struct(task); - read_unlock(&tasklist_lock); + rcu_read_unlock(); if (!task) goto out; - if (leader->tgid != task->tgid) + if (!same_thread_group(leader, task)) goto out_drop_task; - inode = proc_pid_make_inode(dir->i_sb, task, PROC_TID_INO); - - - if (!inode) - goto out_drop_task; - inode->i_mode = S_IFDIR|S_IRUGO|S_IXUGO; - inode->i_op = &proc_tid_base_inode_operations; - inode->i_fop = &proc_tid_base_operations; - inode->i_flags|=S_IMMUTABLE; -#ifdef CONFIG_SECURITY - inode->i_nlink = 4; -#else - inode->i_nlink = 3; -#endif - - dentry->d_op = &pid_base_dentry_operations; - - d_add(dentry, inode); - - put_task_struct(task); - return NULL; + result = proc_task_instantiate(dir, dentry, task, NULL); out_drop_task: put_task_struct(task); out: - return ERR_PTR(-ENOENT); + put_task_struct(leader); +out_no_task: + return ERR_PTR(result); } -#define PROC_NUMBUF 10 -#define PROC_MAXPIDS 20 - /* - * Get a few tgid's to return for filldir - we need to hold the - * tasklist lock while doing this, and we must release it before - * we actually do the filldir itself, so we use a temp buffer.. + * Find the first tid of a thread group to return to user space. + * + * Usually this is just the thread group leader, but if the users + * buffer was too small or there was a seek into the middle of the + * directory we have more work todo. + * + * In the case of a short read we start with find_task_by_pid. + * + * In the case of a seek we start with the leader and walk nr + * threads past it. */ -static int get_tgid_list(int index, unsigned long version, unsigned int *tgids) +static struct task_struct *first_tid(struct pid *pid, int tid, loff_t f_pos, + struct pid_namespace *ns) { - struct task_struct *p; - int nr_tgids = 0; + struct task_struct *pos, *task; + unsigned long nr = f_pos; - index--; - read_lock(&tasklist_lock); - p = NULL; - if (version) { - p = find_task_by_pid(version); - if (p && !thread_group_leader(p)) - p = NULL; - } + if (nr != f_pos) /* 32bit overflow? */ + return NULL; - if (p) - index = 0; - else - p = next_task(&init_task); + rcu_read_lock(); + task = pid_task(pid, PIDTYPE_PID); + if (!task) + goto fail; - for ( ; p != &init_task; p = next_task(p)) { - int tgid = p->pid; - if (!pid_alive(p)) - continue; - if (--index >= 0) - continue; - tgids[nr_tgids] = tgid; - nr_tgids++; - if (nr_tgids >= PROC_MAXPIDS) - break; + /* Attempt to start with the tid of a thread */ + if (tid && nr) { + pos = find_task_by_pid_ns(tid, ns); + if (pos && same_thread_group(pos, task)) + goto found; } - read_unlock(&tasklist_lock); - return nr_tgids; + + /* If nr exceeds the number of threads there is nothing todo */ + if (nr >= get_nr_threads(task)) + goto fail; + + /* If we haven't found our starting place yet start + * with the leader and walk nr threads forward. + */ + pos = task = task->group_leader; + do { + if (!nr--) + goto found; + } while_each_thread(task, pos); +fail: + pos = NULL; + goto out; +found: + get_task_struct(pos); +out: + rcu_read_unlock(); + return pos; } /* - * Get a few tid's to return for filldir - we need to hold the - * tasklist lock while doing this, and we must release it before - * we actually do the filldir itself, so we use a temp buffer.. + * Find the next thread in the thread list. + * Return NULL if there is an error or no next thread. + * + * The reference to the input task_struct is released. */ -static int get_tid_list(int index, unsigned int *tids, struct inode *dir) +static struct task_struct *next_tid(struct task_struct *start) { - struct task_struct *leader_task = proc_task(dir); - struct task_struct *task = leader_task; - int nr_tids = 0; - - index -= 2; - read_lock(&tasklist_lock); - /* - * The starting point task (leader_task) might be an already - * unlinked task, which cannot be used to access the task-list - * via next_thread(). - */ - if (pid_alive(task)) do { - int tid = task->pid; - - if (--index >= 0) - continue; - if (tids != NULL) - tids[nr_tids] = tid; - nr_tids++; - if (nr_tids >= PROC_MAXPIDS) - break; - } while ((task = next_thread(task)) != leader_task); - read_unlock(&tasklist_lock); - return nr_tids; + struct task_struct *pos = NULL; + rcu_read_lock(); + if (pid_alive(start)) { + pos = next_thread(start); + if (thread_group_leader(pos)) + pos = NULL; + else + get_task_struct(pos); + } + rcu_read_unlock(); + put_task_struct(start); + return pos; } -/* for the /proc/ directory itself, after non-process stuff has been done */ -int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir) +/* for the /proc/TGID/task/ directories */ +static int proc_task_readdir(struct file *file, struct dir_context *ctx) { - unsigned int tgid_array[PROC_MAXPIDS]; - char buf[PROC_NUMBUF]; - unsigned int nr = filp->f_pos - FIRST_PROCESS_ENTRY; - unsigned int nr_tgids, i; - int next_tgid; + struct inode *inode = file_inode(file); + struct task_struct *task; + struct pid_namespace *ns; + int tid; - if (!nr) { - ino_t ino = fake_ino(0,PROC_TGID_INO); - if (filldir(dirent, "self", 4, filp->f_pos, ino, DT_LNK) < 0) - return 0; - filp->f_pos++; - nr++; - } + if (proc_inode_is_dead(inode)) + return -ENOENT; + + if (!dir_emit_dots(file, ctx)) + return 0; /* f_version caches the tgid value that the last readdir call couldn't * return. lseek aka telldir automagically resets f_version to 0. */ - next_tgid = filp->f_version; - filp->f_version = 0; - for (;;) { - nr_tgids = get_tgid_list(nr, next_tgid, tgid_array); - if (!nr_tgids) { - /* no more entries ! */ + ns = file->f_dentry->d_sb->s_fs_info; + tid = (int)file->f_version; + file->f_version = 0; + for (task = first_tid(proc_pid(inode), tid, ctx->pos - 2, ns); + task; + task = next_tid(task), ctx->pos++) { + char name[PROC_NUMBUF]; + int len; + tid = task_pid_nr_ns(task, ns); + len = snprintf(name, sizeof(name), "%d", tid); + if (!proc_fill_cache(file, ctx, name, len, + proc_task_instantiate, task, NULL)) { + /* returning this tgid failed, save it as the first + * pid for the next readir call */ + file->f_version = (u64)tid; + put_task_struct(task); break; } - next_tgid = 0; - - /* do not use the last found pid, reserve it for next_tgid */ - if (nr_tgids == PROC_MAXPIDS) { - nr_tgids--; - next_tgid = tgid_array[nr_tgids]; - } - - for (i=0;i<nr_tgids;i++) { - int tgid = tgid_array[i]; - ino_t ino = fake_ino(tgid,PROC_TGID_INO); - unsigned long j = PROC_NUMBUF; - - do - buf[--j] = '0' + (tgid % 10); - while ((tgid /= 10) != 0); - - if (filldir(dirent, buf+j, PROC_NUMBUF-j, filp->f_pos, ino, DT_DIR) < 0) { - /* returning this tgid failed, save it as the first - * pid for the next readir call */ - filp->f_version = tgid_array[i]; - goto out; - } - filp->f_pos++; - nr++; - } } -out: + return 0; } -/* for the /proc/TGID/task/ directories */ -static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir) +static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { - unsigned int tid_array[PROC_MAXPIDS]; - char buf[PROC_NUMBUF]; - unsigned int nr_tids, i; - struct dentry *dentry = filp->f_dentry; struct inode *inode = dentry->d_inode; - int retval = -ENOENT; - ino_t ino; - unsigned long pos = filp->f_pos; /* avoiding "long long" filp->f_pos */ + struct task_struct *p = get_proc_task(inode); + generic_fillattr(inode, stat); - if (!pid_alive(proc_task(inode))) - goto out; - retval = 0; - - switch (pos) { - case 0: - ino = inode->i_ino; - if (filldir(dirent, ".", 1, pos, ino, DT_DIR) < 0) - goto out; - pos++; - /* fall through */ - case 1: - ino = parent_ino(dentry); - if (filldir(dirent, "..", 2, pos, ino, DT_DIR) < 0) - goto out; - pos++; - /* fall through */ + if (p) { + stat->nlink += get_nr_threads(p); + put_task_struct(p); } - nr_tids = get_tid_list(pos, tid_array, inode); - inode->i_nlink = pos + nr_tids; - - for (i = 0; i < nr_tids; i++) { - unsigned long j = PROC_NUMBUF; - int tid = tid_array[i]; - - ino = fake_ino(tid,PROC_TID_INO); + return 0; +} - do - buf[--j] = '0' + (tid % 10); - while ((tid /= 10) != 0); +static const struct inode_operations proc_task_inode_operations = { + .lookup = proc_task_lookup, + .getattr = proc_task_getattr, + .setattr = proc_setattr, + .permission = proc_pid_permission, +}; - if (filldir(dirent, buf+j, PROC_NUMBUF-j, pos, ino, DT_DIR) < 0) - break; - pos++; - } -out: - filp->f_pos = pos; - return retval; -} +static const struct file_operations proc_task_operations = { + .read = generic_read_dir, + .iterate = proc_task_readdir, + .llseek = default_llseek, +}; |