summaryrefslogtreecommitdiff
path: root/fs/proc/base.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc/base.c')
-rw-r--r--fs/proc/base.c211
1 files changed, 200 insertions, 11 deletions
diff --git a/fs/proc/base.c b/fs/proc/base.c
index d2b8c754f627..b31c27d304eb 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -87,6 +87,7 @@
#include <linux/slab.h>
#include <linux/flex_array.h>
#include <linux/posix-timers.h>
+#include <linux/cpufreq_times.h>
#ifdef CONFIG_HARDWALL
#include <asm/hardwall.h>
#endif
@@ -94,6 +95,8 @@
#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
@@ -252,7 +255,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
* Inherently racy -- command line shares address space
* with code and data.
*/
- rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0);
+ rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON);
if (rv <= 0)
goto out_free_page;
@@ -270,7 +273,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
int nr_read;
_count = min3(count, len, PAGE_SIZE);
- nr_read = access_remote_vm(mm, p, page, _count, 0);
+ nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
if (nr_read < 0)
rv = nr_read;
if (nr_read <= 0)
@@ -305,7 +308,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
bool final;
_count = min3(count, len, PAGE_SIZE);
- nr_read = access_remote_vm(mm, p, page, _count, 0);
+ nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
if (nr_read < 0)
rv = nr_read;
if (nr_read <= 0)
@@ -354,7 +357,7 @@ skip_argv:
bool final;
_count = min3(count, len, PAGE_SIZE);
- nr_read = access_remote_vm(mm, p, page, _count, 0);
+ nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON);
if (nr_read < 0)
rv = nr_read;
if (nr_read <= 0)
@@ -469,6 +472,20 @@ static int proc_pid_stack(struct seq_file *m, struct pid_namespace *ns,
int err;
int i;
+ /*
+ * 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(MAX_STACK_TRACE_DEPTH * sizeof(*entries), GFP_KERNEL);
if (!entries)
return -ENOMEM;
@@ -852,6 +869,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
unsigned long addr = *ppos;
ssize_t copied;
char *page;
+ unsigned int flags;
if (!mm)
return 0;
@@ -864,6 +882,11 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
if (!atomic_inc_not_zero(&mm->mm_users))
goto free;
+ /* Maybe we should limit FOLL_FORCE to actual ptrace users? */
+ flags = FOLL_FORCE;
+ if (write)
+ flags |= FOLL_WRITE;
+
while (count > 0) {
int this_len = min_t(int, count, PAGE_SIZE);
@@ -872,7 +895,7 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
break;
}
- this_len = access_remote_vm(mm, addr, page, this_len, write);
+ this_len = access_remote_vm(mm, addr, page, this_len, flags);
if (!this_len) {
if (!copied)
copied = -EIO;
@@ -953,6 +976,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
unsigned long src = *ppos;
int ret = 0;
struct mm_struct *mm = file->private_data;
+ unsigned long env_start, env_end;
/* Ensure the process spawned far enough to have an environment. */
if (!mm || !mm->env_end)
@@ -965,20 +989,25 @@ static ssize_t environ_read(struct file *file, char __user *buf,
ret = 0;
if (!atomic_inc_not_zero(&mm->mm_users))
goto free;
+
+ down_read(&mm->mmap_sem);
+ env_start = mm->env_start;
+ env_end = mm->env_end;
+ up_read(&mm->mmap_sem);
+
while (count > 0) {
size_t this_len, max_len;
int retval;
- if (src >= (mm->env_end - mm->env_start))
+ if (src >= (env_end - env_start))
break;
- this_len = mm->env_end - (mm->env_start + src);
+ this_len = env_end - (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);
+ retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON);
if (retval <= 0) {
ret = retval;
@@ -1829,8 +1858,33 @@ end_instantiate:
static int dname_to_vma_addr(struct dentry *dentry,
unsigned long *start, unsigned long *end)
{
- if (sscanf(dentry->d_name.name, "%lx-%lx", start, end) != 2)
+ const char *str = dentry->d_name.name;
+ unsigned long long sval, eval;
+ unsigned int len;
+
+ len = _parse_integer(str, 16, &sval);
+ if (len & KSTRTOX_OVERFLOW)
+ return -EINVAL;
+ if (sval != (unsigned long)sval)
return -EINVAL;
+ str += len;
+
+ if (*str != '-')
+ return -EINVAL;
+ str++;
+
+ len = _parse_integer(str, 16, &eval);
+ if (len & KSTRTOX_OVERFLOW)
+ return -EINVAL;
+ if (eval != (unsigned long)eval)
+ return -EINVAL;
+ str += len;
+
+ if (*str != '\0')
+ return -EINVAL;
+
+ *start = sval;
+ *end = eval;
return 0;
}
@@ -2240,6 +2294,92 @@ static const struct file_operations proc_timers_operations = {
.release = seq_release_private,
};
+static ssize_t timerslack_ns_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *offset)
+{
+ struct inode *inode = file_inode(file);
+ struct task_struct *p;
+ u64 slack_ns;
+ int err;
+
+ err = kstrtoull_from_user(buf, count, 10, &slack_ns);
+ if (err < 0)
+ return err;
+
+ p = get_proc_task(inode);
+ if (!p)
+ return -ESRCH;
+
+ if (p != current) {
+ if (!capable(CAP_SYS_NICE)) {
+ count = -EPERM;
+ goto out;
+ }
+
+ err = security_task_setscheduler(p);
+ if (err) {
+ count = err;
+ goto out;
+ }
+ }
+
+ task_lock(p);
+ if (slack_ns == 0)
+ p->timer_slack_ns = p->default_timer_slack_ns;
+ else
+ p->timer_slack_ns = slack_ns;
+ task_unlock(p);
+
+out:
+ put_task_struct(p);
+
+ return count;
+}
+
+static int timerslack_ns_show(struct seq_file *m, void *v)
+{
+ struct inode *inode = m->private;
+ struct task_struct *p;
+ int err = 0;
+
+ p = get_proc_task(inode);
+ if (!p)
+ return -ESRCH;
+
+ if (p != current) {
+
+ if (!capable(CAP_SYS_NICE)) {
+ err = -EPERM;
+ goto out;
+ }
+ err = security_task_getscheduler(p);
+ if (err)
+ goto out;
+ }
+
+ task_lock(p);
+ seq_printf(m, "%llu\n", p->timer_slack_ns);
+ task_unlock(p);
+
+out:
+ put_task_struct(p);
+
+ return err;
+}
+
+static int timerslack_ns_open(struct inode *inode, struct file *filp)
+{
+ return single_open(filp, timerslack_ns_show, inode);
+}
+
+static const struct file_operations proc_pid_set_timerslack_ns_operations = {
+ .open = timerslack_ns_open,
+ .read = seq_read,
+ .write = timerslack_ns_write,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
static int proc_pident_instantiate(struct inode *dir,
struct dentry *dentry, struct task_struct *task, const void *ptr)
{
@@ -2817,6 +2957,10 @@ static const struct pid_entry tgid_base_stuff[] = {
#ifdef CONFIG_CHECKPOINT_RESTORE
REG("timers", S_IRUGO, proc_timers_operations),
#endif
+ REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations),
+#ifdef CONFIG_CPU_FREQ_TIMES
+ ONE("time_in_state", 0444, proc_time_in_state_show),
+#endif
};
static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
@@ -3058,6 +3202,8 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
iter.tgid += 1, iter = next_tgid(ns, iter)) {
char name[PROC_NUMBUF];
int len;
+
+ cond_resched();
if (!has_pid_permissions(ns, iter.task, 2))
continue;
@@ -3074,6 +3220,44 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
}
/*
+ * proc_tid_comm_permission is a special permission function exclusively
+ * used for the node /proc/<pid>/task/<tid>/comm.
+ * It bypasses generic permission checks in the case where a task of the same
+ * task group attempts to access the node.
+ * The rationale behind this is that glibc and bionic access this node for
+ * cross thread naming (pthread_set/getname_np(!self)). However, if
+ * PR_SET_DUMPABLE gets set to 0 this node among others becomes uid=0 gid=0,
+ * which locks out the cross thread naming implementation.
+ * This function makes sure that the node is always accessible for members of
+ * same thread group.
+ */
+static int proc_tid_comm_permission(struct inode *inode, int mask)
+{
+ bool is_same_tgroup;
+ struct task_struct *task;
+
+ task = get_proc_task(inode);
+ if (!task)
+ return -ESRCH;
+ is_same_tgroup = same_thread_group(current, task);
+ put_task_struct(task);
+
+ if (likely(is_same_tgroup && !(mask & MAY_EXEC))) {
+ /* This file (/proc/<pid>/task/<tid>/comm) can always be
+ * read or written by the members of the corresponding
+ * thread group.
+ */
+ return 0;
+ }
+
+ return generic_permission(inode, mask);
+}
+
+static const struct inode_operations proc_tid_comm_inode_operations = {
+ .permission = proc_tid_comm_permission,
+};
+
+/*
* Tasks
*/
static const struct pid_entry tid_base_stuff[] = {
@@ -3091,7 +3275,9 @@ static const struct pid_entry tid_base_stuff[] = {
#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),
+ NOD("comm", S_IFREG|S_IRUGO|S_IWUSR,
+ &proc_tid_comm_inode_operations,
+ &proc_pid_set_comm_operations, {}),
#ifdef CONFIG_HAVE_ARCH_TRACEHOOK
ONE("syscall", S_IRUSR, proc_pid_syscall),
#endif
@@ -3159,6 +3345,9 @@ static const struct pid_entry tid_base_stuff[] = {
REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
REG("setgroups", S_IRUGO|S_IWUSR, proc_setgroups_operations),
#endif
+#ifdef CONFIG_CPU_FREQ_TIMES
+ ONE("time_in_state", 0444, proc_time_in_state_show),
+#endif
};
static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx)
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-24 16:44:40 +0000