// SPDX-License-Identifier: GPL-2.0/* * linux/fs/proc/base.c * * Copyright (C) 1991, 1992 Linus Torvalds * * proc base directory handling functions * * 1999, Al Viro. Rewritten. Now it covers the whole per-process part. * Instead of using magical inumbers to determine the kind of object * we allocate and fill in-core inodes upon lookup. They don't even * go into icache. We cache the reference to task_struct upon lookup too. * Eventually it should become a filesystem in its own. We don't use the * rest of procfs anymore. * * * Changelog: * 17-Jan-2005 * Allan Bezerra * Bruna Moreira <bruna.moreira@indt.org.br> * Edjard Mota <edjard.mota@indt.org.br> * Ilias Biris <ilias.biris@indt.org.br> * Mauricio Lin <mauricio.lin@indt.org.br> * * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT * * A new process specific entry (smaps) included in /proc. It shows the * size of rss for each memory area. The maps entry lacks information * about physical memory size (rss) for each mapped file, i.e., * rss information for executables and library files. * This additional information is useful for any tools that need to know * about physical memory consumption for a process specific library. * * Changelog: * 21-Feb-2005 * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT * Pud inclusion in the page table walking. * * ChangeLog: * 10-Mar-2005 * 10LE Instituto Nokia de Tecnologia - INdT: * A better way to walks through the page table as suggested by Hugh Dickins. * * Simo Piiroinen <simo.piiroinen@nokia.com>: * Smaps information related to shared, private, clean and dirty pages. * * Paul Mundt <paul.mundt@nokia.com>: * Overall revision about smaps. */ #include <linux/uaccess.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/generic-radix-tree.h>#include <linux/string.h>#include <linux/seq_file.h>#include <linux/namei.h>#include <linux/mnt_namespace.h>#include <linux/mm.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/printk.h>#include <linux/cache.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_parser.h>#include <linux/fs_struct.h>#include <linux/slab.h>#include <linux/sched/autogroup.h>#include <linux/sched/mm.h>#include <linux/sched/coredump.h>#include <linux/sched/debug.h>#include <linux/sched/exec_state.h>#include <linux/sched/stat.h>#include <linux/posix-timers.h>#include <linux/time_namespace.h>#include <linux/resctrl.h>#include <linux/cn_proc.h>#include <linux/ksm.h>#include <uapi/linux/lsm.h>#include <trace/events/oom.h>#include "internal.h"#include "fd.h" #include "../../lib/kstrtox.h" /* 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. */ static u8 nlink_tid __ro_after_init;static u8 nlink_tgid __ro_after_init; enum proc_mem_force { PROC_MEM_FORCE_ALWAYS, PROC_MEM_FORCE_PTRACE, PROC_MEM_FORCE_NEVER}; static enum proc_mem_force proc_mem_force_override __ro_after_init = IS_ENABLED(CONFIG_PROC_MEM_NO_FORCE) ? PROC_MEM_FORCE_NEVER : IS_ENABLED(CONFIG_PROC_MEM_FORCE_PTRACE) ? PROC_MEM_FORCE_PTRACE : PROC_MEM_FORCE_ALWAYS; static const struct constant_table proc_mem_force_table[] __initconst = { { "always", PROC_MEM_FORCE_ALWAYS }, { "ptrace", PROC_MEM_FORCE_PTRACE }, { "never", PROC_MEM_FORCE_NEVER }, { }}; static int __init early_proc_mem_force_override(char *buf){ if (!buf) return -EINVAL; /* * lookup_constant() defaults to proc_mem_force_override to preseve * the initial Kconfig choice in case an invalid param gets passed. */ proc_mem_force_override = lookup_constant(proc_mem_force_table, buf, proc_mem_force_override); return 0;}early_param("proc_mem.force_override", early_proc_mem_force_override); struct pid_entry { const char *name; unsigned int len; umode_t mode; const struct inode_operations *iop; const struct file_operations *fop; union proc_op op;}; #define NOD(NAME, MODE, IOP, FOP, OP) { \ .name = (NAME), \ .len = sizeof(NAME) - 1, \ .mode = MODE, \ .iop = IOP, \ .fop = FOP, \ .op = OP, \} #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 ONE(NAME, MODE, show) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_single_file_operations, \ { .proc_show = show } )#define ATTR(LSMID, NAME, MODE) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_pid_attr_operations, \ { .lsmid = LSMID }) /* * Count the number of hardlinks for the pid_entry table, excluding the . * and .. links. */static unsigned int __init pid_entry_nlink(const struct pid_entry *entries, unsigned int n){ unsigned int i; unsigned int count; count = 2; for (i = 0; i < n; ++i) { if (S_ISDIR(entries[i].mode)) ++count; } return count;} static int get_task_root(struct task_struct *task, struct path *root){ int result = -ENOENT; task_lock(task); if (task->real_fs) { get_fs_root(task->real_fs, root); result = 0; } task_unlock(task); return result;} static int proc_cwd_link(struct dentry *dentry, struct path *path, struct task_struct *task){ int result = -ENOENT; task_lock(task); if (task->real_fs) { get_fs_pwd(task->real_fs, path); result = 0; } task_unlock(task); return result;} static int proc_root_link(struct dentry *dentry, struct path *path, struct task_struct *task){ return get_task_root(task, path);} /* * If the user used setproctitle(), we just get the string from * user space at arg_start, and limit it to a maximum of one page. */static ssize_t get_mm_proctitle(struct mm_struct *mm, char __user *buf, size_t count, unsigned long pos, unsigned long arg_start){ char *page; int ret, got; if (pos >= PAGE_SIZE) return 0; page = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!page) return -ENOMEM; ret = 0; got = access_remote_vm(mm, arg_start, page, PAGE_SIZE, FOLL_ANON); if (got > 0) { int len = strnlen(page, got); /* Include the NUL character if it was found */ if (len < got) len++; if (len > pos) { len -= pos; if (len > count) len = count; len -= copy_to_user(buf, page+pos, len); if (!len) len = -EFAULT; ret = len; } } kfree(page); return ret;} static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf, size_t count, loff_t *ppos){ unsigned long arg_start, arg_end, env_start, env_end; unsigned long pos, len; char *page, c; /* Check if process spawned far enough to have cmdline. */ if (!mm->env_end) return 0; spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); if (arg_start >= arg_end) return 0; /* * We allow setproctitle() to overwrite the argument * strings, and overflow past the original end. But * only when it overflows into the environment area. */ if (env_start != arg_end || env_end < env_start) env_start = env_end = arg_end; len = env_end - arg_start; /* We're not going to care if "*ppos" has high bits set */ pos = *ppos; if (pos >= len) return 0; if (count > len - pos) count = len - pos; if (!count) return 0; /* * Magical special case: if the argv[] end byte is not * zero, the user has overwritten it with setproctitle(3). * * Possible future enhancement: do this only once when * pos is 0, and set a flag in the 'struct file'. */ if (access_remote_vm(mm, arg_end-1, &c, 1, FOLL_ANON) == 1 && c) return get_mm_proctitle(mm, buf, count, pos, arg_start); /* * For the non-setproctitle() case we limit things strictly * to the [arg_start, arg_end[ range. */ pos += arg_start; if (pos < arg_start || pos >= arg_end) return 0; if (count > arg_end - pos) count = arg_end - pos; page = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!page) return -ENOMEM; len = 0; while (count) { int got; size_t size = min_t(size_t, PAGE_SIZE, count); got = access_remote_vm(mm, pos, page, size, FOLL_ANON); if (got <= 0) break; got -= copy_to_user(buf, page, got); if (unlikely(!got)) { if (!len) len = -EFAULT; break; } pos += got; buf += got; len += got; count -= got; } kfree(page); return len;} static ssize_t get_task_cmdline(struct task_struct *tsk, char __user *buf, size_t count, loff_t *pos){ struct mm_struct *mm; ssize_t ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = get_mm_cmdline(mm, buf, count, pos); mmput(mm); return ret;} static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, size_t count, loff_t *pos){ struct task_struct *tsk; ssize_t ret; BUG_ON(*pos < 0); tsk = get_proc_task(file_inode(file)); if (!tsk) return -ESRCH; ret = get_task_cmdline(tsk, buf, count, pos); put_task_struct(tsk); if (ret > 0) *pos += ret; return ret;} static const struct file_operations proc_pid_cmdline_ops = { .read = proc_pid_cmdline_read, .llseek = generic_file_llseek,}; #ifdef CONFIG_KALLSYMS/* * Provides a wchan file via kallsyms in a proper one-value-per-file format. * Returns the resolved symbol to user space. */static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task){ unsigned long wchan; char symname[KSYM_NAME_LEN]; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto print0; wchan = get_wchan(task); if (wchan && !lookup_symbol_name(wchan, symname)) { seq_puts(m, symname); up_read(&task->signal->exec_update_lock); return 0; } print0: seq_putc(m, '0'); up_read(&task->signal->exec_update_lock); return 0;}#endif /* CONFIG_KALLSYMS */ static int lock_trace(struct task_struct *task){ int err = down_read_killable(&task->signal->exec_update_lock); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { up_read(&task->signal->exec_update_lock); return -EPERM; } return 0;} static void unlock_trace(struct task_struct *task){ up_read(&task->signal->exec_update_lock);} #ifdef CONFIG_STACKTRACE #define MAX_STACK_TRACE_DEPTH 64 static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task){ unsigned long *entries; int err; /* * The ability to racily run the kernel stack unwinder on a running task * and then observe the unwinder output is scary; while it is useful for * debugging kernel issues, it can also allow an attacker to leak kernel * stack contents. * Doing this in a manner that is at least safe from races would require * some work to ensure that the remote task can not be scheduled; and * even then, this would still expose the unwinder as local attack * surface. * Therefore, this interface is restricted to root. */ if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) return -EACCES; entries = kmalloc_array(MAX_STACK_TRACE_DEPTH, sizeof(*entries), GFP_KERNEL); if (!entries) return -ENOMEM; err = lock_trace(task); if (!err) { unsigned int i, nr_entries; nr_entries = stack_trace_save_tsk(task, entries, MAX_STACK_TRACE_DEPTH, 0); for (i = 0; i < nr_entries; i++) { seq_printf(m, "[<0>] %pB\n", (void *)entries[i]); } unlock_trace(task); } kfree(entries); Lines 1–500 of 3990. Load more
// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/proc/base.c * * Copyright (C) 1991, 1992 Linus Torvalds * * proc base directory handling functions * * 1999, Al Viro. Rewritten. Now it covers the whole per-process part. * Instead of using magical inumbers to determine the kind of object * we allocate and fill in-core inodes upon lookup. They don't even * go into icache. We cache the reference to task_struct upon lookup too. * Eventually it should become a filesystem in its own. We don't use the * rest of procfs anymore. * * * Changelog: * 17-Jan-2005 * Allan Bezerra * Bruna Moreira <bruna.moreira@indt.org.br> * Edjard Mota <edjard.mota@indt.org.br> * Ilias Biris <ilias.biris@indt.org.br> * Mauricio Lin <mauricio.lin@indt.org.br> * * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT * * A new process specific entry (smaps) included in /proc. It shows the * size of rss for each memory area. The maps entry lacks information * about physical memory size (rss) for each mapped file, i.e., * rss information for executables and library files. * This additional information is useful for any tools that need to know * about physical memory consumption for a process specific library. * * Changelog: * 21-Feb-2005 * Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT * Pud inclusion in the page table walking. * * ChangeLog: * 10-Mar-2005 * 10LE Instituto Nokia de Tecnologia - INdT: * A better way to walks through the page table as suggested by Hugh Dickins. * * Simo Piiroinen <simo.piiroinen@nokia.com>: * Smaps information related to shared, private, clean and dirty pages. * * Paul Mundt <paul.mundt@nokia.com>: * Overall revision about smaps. */ #include <linux/uaccess.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/generic-radix-tree.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/namei.h> #include <linux/mnt_namespace.h> #include <linux/mm.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/printk.h> #include <linux/cache.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_parser.h> #include <linux/fs_struct.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/debug.h> #include <linux/sched/exec_state.h> #include <linux/sched/stat.h> #include <linux/posix-timers.h> #include <linux/time_namespace.h> #include <linux/resctrl.h> #include <linux/cn_proc.h> #include <linux/ksm.h> #include <uapi/linux/lsm.h> #include <trace/events/oom.h> #include "internal.h" #include "fd.h" #include "../../lib/kstrtox.h" /* 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. */ static u8 nlink_tid __ro_after_init; static u8 nlink_tgid __ro_after_init; enum proc_mem_force { PROC_MEM_FORCE_ALWAYS, PROC_MEM_FORCE_PTRACE, PROC_MEM_FORCE_NEVER }; static enum proc_mem_force proc_mem_force_override __ro_after_init = IS_ENABLED(CONFIG_PROC_MEM_NO_FORCE) ? PROC_MEM_FORCE_NEVER : IS_ENABLED(CONFIG_PROC_MEM_FORCE_PTRACE) ? PROC_MEM_FORCE_PTRACE : PROC_MEM_FORCE_ALWAYS; static const struct constant_table proc_mem_force_table[] __initconst = { { "always", PROC_MEM_FORCE_ALWAYS }, { "ptrace", PROC_MEM_FORCE_PTRACE }, { "never", PROC_MEM_FORCE_NEVER }, { } }; static int __init early_proc_mem_force_override(char *buf) { if (!buf) return -EINVAL; /* * lookup_constant() defaults to proc_mem_force_override to preseve * the initial Kconfig choice in case an invalid param gets passed. */ proc_mem_force_override = lookup_constant(proc_mem_force_table, buf, proc_mem_force_override); return 0; } early_param("proc_mem.force_override", early_proc_mem_force_override); struct pid_entry { const char *name; unsigned int len; umode_t mode; const struct inode_operations *iop; const struct file_operations *fop; union proc_op op; }; #define NOD(NAME, MODE, IOP, FOP, OP) { \ .name = (NAME), \ .len = sizeof(NAME) - 1, \ .mode = MODE, \ .iop = IOP, \ .fop = FOP, \ .op = OP, \ } #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 ONE(NAME, MODE, show) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_single_file_operations, \ { .proc_show = show } ) #define ATTR(LSMID, NAME, MODE) \ NOD(NAME, (S_IFREG|(MODE)), \ NULL, &proc_pid_attr_operations, \ { .lsmid = LSMID }) /* * Count the number of hardlinks for the pid_entry table, excluding the . * and .. links. */ static unsigned int __init pid_entry_nlink(const struct pid_entry *entries, unsigned int n) { unsigned int i; unsigned int count; count = 2; for (i = 0; i < n; ++i) { if (S_ISDIR(entries[i].mode)) ++count; } return count; } static int get_task_root(struct task_struct *task, struct path *root) { int result = -ENOENT; task_lock(task); if (task->real_fs) { get_fs_root(task->real_fs, root); result = 0; } task_unlock(task); return result; } static int proc_cwd_link(struct dentry *dentry, struct path *path, struct task_struct *task) { int result = -ENOENT; task_lock(task); if (task->real_fs) { get_fs_pwd(task->real_fs, path); result = 0; } task_unlock(task); return result; } static int proc_root_link(struct dentry *dentry, struct path *path, struct task_struct *task) { return get_task_root(task, path); } /* * If the user used setproctitle(), we just get the string from * user space at arg_start, and limit it to a maximum of one page. */ static ssize_t get_mm_proctitle(struct mm_struct *mm, char __user *buf, size_t count, unsigned long pos, unsigned long arg_start) { char *page; int ret, got; if (pos >= PAGE_SIZE) return 0; page = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!page) return -ENOMEM; ret = 0; got = access_remote_vm(mm, arg_start, page, PAGE_SIZE, FOLL_ANON); if (got > 0) { int len = strnlen(page, got); /* Include the NUL character if it was found */ if (len < got) len++; if (len > pos) { len -= pos; if (len > count) len = count; len -= copy_to_user(buf, page+pos, len); if (!len) len = -EFAULT; ret = len; } } kfree(page); return ret; } static ssize_t get_mm_cmdline(struct mm_struct *mm, char __user *buf, size_t count, loff_t *ppos) { unsigned long arg_start, arg_end, env_start, env_end; unsigned long pos, len; char *page, c; /* Check if process spawned far enough to have cmdline. */ if (!mm->env_end) return 0; spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); if (arg_start >= arg_end) return 0; /* * We allow setproctitle() to overwrite the argument * strings, and overflow past the original end. But * only when it overflows into the environment area. */ if (env_start != arg_end || env_end < env_start) env_start = env_end = arg_end; len = env_end - arg_start; /* We're not going to care if "*ppos" has high bits set */ pos = *ppos; if (pos >= len) return 0; if (count > len - pos) count = len - pos; if (!count) return 0; /* * Magical special case: if the argv[] end byte is not * zero, the user has overwritten it with setproctitle(3). * * Possible future enhancement: do this only once when * pos is 0, and set a flag in the 'struct file'. */ if (access_remote_vm(mm, arg_end-1, &c, 1, FOLL_ANON) == 1 && c) return get_mm_proctitle(mm, buf, count, pos, arg_start); /* * For the non-setproctitle() case we limit things strictly * to the [arg_start, arg_end[ range. */ pos += arg_start; if (pos < arg_start || pos >= arg_end) return 0; if (count > arg_end - pos) count = arg_end - pos; page = kmalloc(PAGE_SIZE, GFP_KERNEL); if (!page) return -ENOMEM; len = 0; while (count) { int got; size_t size = min_t(size_t, PAGE_SIZE, count); got = access_remote_vm(mm, pos, page, size, FOLL_ANON); if (got <= 0) break; got -= copy_to_user(buf, page, got); if (unlikely(!got)) { if (!len) len = -EFAULT; break; } pos += got; buf += got; len += got; count -= got; } kfree(page); return len; } static ssize_t get_task_cmdline(struct task_struct *tsk, char __user *buf, size_t count, loff_t *pos) { struct mm_struct *mm; ssize_t ret; mm = get_task_mm(tsk); if (!mm) return 0; ret = get_mm_cmdline(mm, buf, count, pos); mmput(mm); return ret; } static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, size_t count, loff_t *pos) { struct task_struct *tsk; ssize_t ret; BUG_ON(*pos < 0); tsk = get_proc_task(file_inode(file)); if (!tsk) return -ESRCH; ret = get_task_cmdline(tsk, buf, count, pos); put_task_struct(tsk); if (ret > 0) *pos += ret; return ret; } static const struct file_operations proc_pid_cmdline_ops = { .read = proc_pid_cmdline_read, .llseek = generic_file_llseek, }; #ifdef CONFIG_KALLSYMS /* * Provides a wchan file via kallsyms in a proper one-value-per-file format. * Returns the resolved symbol to user space. */ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long wchan; char symname[KSYM_NAME_LEN]; int err; err = down_read_killable(&task->signal->exec_update_lock); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) goto print0; wchan = get_wchan(task); if (wchan && !lookup_symbol_name(wchan, symname)) { seq_puts(m, symname); up_read(&task->signal->exec_update_lock); return 0; } print0: seq_putc(m, '0'); up_read(&task->signal->exec_update_lock); return 0; } #endif /* CONFIG_KALLSYMS */ static int lock_trace(struct task_struct *task) { int err = down_read_killable(&task->signal->exec_update_lock); if (err) return err; if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) { up_read(&task->signal->exec_update_lock); return -EPERM; } return 0; } static void unlock_trace(struct task_struct *task) { up_read(&task->signal->exec_update_lock); } #ifdef CONFIG_STACKTRACE #define MAX_STACK_TRACE_DEPTH 64 static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task) { unsigned long *entries; int err; /* * The ability to racily run the kernel stack unwinder on a running task * and then observe the unwinder output is scary; while it is useful for * debugging kernel issues, it can also allow an attacker to leak kernel * stack contents. * Doing this in a manner that is at least safe from races would require * some work to ensure that the remote task can not be scheduled; and * even then, this would still expose the unwinder as local attack * surface. * Therefore, this interface is restricted to root. */ if (!file_ns_capable(m->file, &init_user_ns, CAP_SYS_ADMIN)) return -EACCES; entries = kmalloc_array(MAX_STACK_TRACE_DEPTH, sizeof(*entries), GFP_KERNEL); if (!entries) return -ENOMEM; err = lock_trace(task); if (!err) { unsigned int i, nr_entries; nr_entries = stack_trace_save_tsk(task, entries, MAX_STACK_TRACE_DEPTH, 0); for (i = 0; i < nr_entries; i++) { seq_printf(m, "[<0>] %pB\n", (void *)entries[i]); } unlock_trace(task); } kfree(entries);