aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/sys.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sys.c')
-rw-r--r--kernel/sys.c240
1 files changed, 168 insertions, 72 deletions
diff --git a/kernel/sys.c b/kernel/sys.c
index 8fdac0d90504..5fd54bf0e886 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -7,6 +7,7 @@
#include <linux/export.h>
#include <linux/mm.h>
+#include <linux/mm_inline.h>
#include <linux/utsname.h>
#include <linux/mman.h>
#include <linux/reboot.h>
@@ -24,6 +25,7 @@
#include <linux/times.h>
#include <linux/posix-timers.h>
#include <linux/security.h>
+#include <linux/random.h>
#include <linux/suspend.h>
#include <linux/tty.h>
#include <linux/signal.h>
@@ -116,6 +118,12 @@
#ifndef SVE_GET_VL
# define SVE_GET_VL() (-EINVAL)
#endif
+#ifndef SME_SET_VL
+# define SME_SET_VL(a) (-EINVAL)
+#endif
+#ifndef SME_GET_VL
+# define SME_GET_VL() (-EINVAL)
+#endif
#ifndef PAC_RESET_KEYS
# define PAC_RESET_KEYS(a, b) (-EINVAL)
#endif
@@ -220,7 +228,6 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
niceval = MAX_NICE;
rcu_read_lock();
- read_lock(&tasklist_lock);
switch (which) {
case PRIO_PROCESS:
if (who)
@@ -235,9 +242,11 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
pgrp = find_vpid(who);
else
pgrp = task_pgrp(current);
+ read_lock(&tasklist_lock);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
error = set_one_prio(p, niceval, error);
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+ read_unlock(&tasklist_lock);
break;
case PRIO_USER:
uid = make_kuid(cred->user_ns, who);
@@ -249,16 +258,15 @@ SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval)
if (!user)
goto out_unlock; /* No processes for this user */
}
- do_each_thread(g, p) {
+ for_each_process_thread(g, p) {
if (uid_eq(task_uid(p), uid) && task_pid_vnr(p))
error = set_one_prio(p, niceval, error);
- } while_each_thread(g, p);
+ }
if (!uid_eq(uid, cred->uid))
free_uid(user); /* For find_user() */
break;
}
out_unlock:
- read_unlock(&tasklist_lock);
rcu_read_unlock();
out:
return error;
@@ -283,7 +291,6 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
return -EINVAL;
rcu_read_lock();
- read_lock(&tasklist_lock);
switch (which) {
case PRIO_PROCESS:
if (who)
@@ -301,11 +308,13 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
pgrp = find_vpid(who);
else
pgrp = task_pgrp(current);
+ read_lock(&tasklist_lock);
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) {
niceval = nice_to_rlimit(task_nice(p));
if (niceval > retval)
retval = niceval;
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p);
+ read_unlock(&tasklist_lock);
break;
case PRIO_USER:
uid = make_kuid(cred->user_ns, who);
@@ -317,19 +326,18 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who)
if (!user)
goto out_unlock; /* No processes for this user */
}
- do_each_thread(g, p) {
+ for_each_process_thread(g, p) {
if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) {
niceval = nice_to_rlimit(task_nice(p));
if (niceval > retval)
retval = niceval;
}
- } while_each_thread(g, p);
+ }
if (!uid_eq(uid, cred->uid))
free_uid(user); /* for find_user() */
break;
}
out_unlock:
- read_unlock(&tasklist_lock);
rcu_read_unlock();
return retval;
@@ -472,6 +480,16 @@ static int set_user(struct cred *new)
if (!new_user)
return -EAGAIN;
+ free_uid(new->user);
+ new->user = new_user;
+ return 0;
+}
+
+static void flag_nproc_exceeded(struct cred *new)
+{
+ if (new->ucounts == current_ucounts())
+ return;
+
/*
* We don't fail in case of NPROC limit excess here because too many
* poorly written programs don't check set*uid() return code, assuming
@@ -479,16 +497,11 @@ static int set_user(struct cred *new)
* for programs doing set*uid()+execve() by harmlessly deferring the
* failure to the execve() stage.
*/
- if (is_ucounts_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) &&
- new_user != INIT_USER &&
- !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN))
+ if (is_rlimit_overlimit(new->ucounts, UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC)) &&
+ new->user != INIT_USER)
current->flags |= PF_NPROC_EXCEEDED;
else
current->flags &= ~PF_NPROC_EXCEEDED;
-
- free_uid(new->user);
- new->user = new_user;
- return 0;
}
/*
@@ -563,6 +576,7 @@ long __sys_setreuid(uid_t ruid, uid_t euid)
if (retval < 0)
goto error;
+ flag_nproc_exceeded(new);
return commit_creds(new);
error:
@@ -625,6 +639,7 @@ long __sys_setuid(uid_t uid)
if (retval < 0)
goto error;
+ flag_nproc_exceeded(new);
return commit_creds(new);
error:
@@ -704,6 +719,7 @@ long __sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
if (retval < 0)
goto error;
+ flag_nproc_exceeded(new);
return commit_creds(new);
error:
@@ -1351,6 +1367,7 @@ SYSCALL_DEFINE2(sethostname, char __user *, name, int, len)
if (!copy_from_user(tmp, name, len)) {
struct new_utsname *u;
+ add_device_randomness(tmp, len);
down_write(&uts_sem);
u = utsname();
memcpy(u->nodename, tmp, len);
@@ -1404,6 +1421,7 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
if (!copy_from_user(tmp, name, len)) {
struct new_utsname *u;
+ add_device_randomness(tmp, len);
down_write(&uts_sem);
u = utsname();
memcpy(u->domainname, tmp, len);
@@ -1415,6 +1433,68 @@ SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len)
return errno;
}
+/* make sure you are allowed to change @tsk limits before calling this */
+static int do_prlimit(struct task_struct *tsk, unsigned int resource,
+ struct rlimit *new_rlim, struct rlimit *old_rlim)
+{
+ struct rlimit *rlim;
+ int retval = 0;
+
+ if (resource >= RLIM_NLIMITS)
+ return -EINVAL;
+ if (new_rlim) {
+ if (new_rlim->rlim_cur > new_rlim->rlim_max)
+ return -EINVAL;
+ if (resource == RLIMIT_NOFILE &&
+ new_rlim->rlim_max > sysctl_nr_open)
+ return -EPERM;
+ }
+
+ /* Holding a refcount on tsk protects tsk->signal from disappearing. */
+ rlim = tsk->signal->rlim + resource;
+ task_lock(tsk->group_leader);
+ if (new_rlim) {
+ /*
+ * Keep the capable check against init_user_ns until cgroups can
+ * contain all limits.
+ */
+ if (new_rlim->rlim_max > rlim->rlim_max &&
+ !capable(CAP_SYS_RESOURCE))
+ retval = -EPERM;
+ if (!retval)
+ retval = security_task_setrlimit(tsk, resource, new_rlim);
+ }
+ if (!retval) {
+ if (old_rlim)
+ *old_rlim = *rlim;
+ if (new_rlim)
+ *rlim = *new_rlim;
+ }
+ task_unlock(tsk->group_leader);
+
+ /*
+ * RLIMIT_CPU handling. Arm the posix CPU timer if the limit is not
+ * infinite. In case of RLIM_INFINITY the posix CPU timer code
+ * ignores the rlimit.
+ */
+ if (!retval && new_rlim && resource == RLIMIT_CPU &&
+ new_rlim->rlim_cur != RLIM_INFINITY &&
+ IS_ENABLED(CONFIG_POSIX_TIMERS)) {
+ /*
+ * update_rlimit_cpu can fail if the task is exiting, but there
+ * may be other tasks in the thread group that are not exiting,
+ * and they need their cpu timers adjusted.
+ *
+ * The group_leader is the last task to be released, so if we
+ * cannot update_rlimit_cpu on it, then the entire process is
+ * exiting and we do not need to update at all.
+ */
+ update_rlimit_cpu(tsk->group_leader, new_rlim->rlim_cur);
+ }
+
+ return retval;
+}
+
SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim)
{
struct rlimit value;
@@ -1558,63 +1638,6 @@ static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim)
rlim->rlim_max = (unsigned long)rlim64->rlim_max;
}
-/* make sure you are allowed to change @tsk limits before calling this */
-int do_prlimit(struct task_struct *tsk, unsigned int resource,
- struct rlimit *new_rlim, struct rlimit *old_rlim)
-{
- struct rlimit *rlim;
- int retval = 0;
-
- if (resource >= RLIM_NLIMITS)
- return -EINVAL;
- if (new_rlim) {
- if (new_rlim->rlim_cur > new_rlim->rlim_max)
- return -EINVAL;
- if (resource == RLIMIT_NOFILE &&
- new_rlim->rlim_max > sysctl_nr_open)
- return -EPERM;
- }
-
- /* protect tsk->signal and tsk->sighand from disappearing */
- read_lock(&tasklist_lock);
- if (!tsk->sighand) {
- retval = -ESRCH;
- goto out;
- }
-
- rlim = tsk->signal->rlim + resource;
- task_lock(tsk->group_leader);
- if (new_rlim) {
- /* Keep the capable check against init_user_ns until
- cgroups can contain all limits */
- if (new_rlim->rlim_max > rlim->rlim_max &&
- !capable(CAP_SYS_RESOURCE))
- retval = -EPERM;
- if (!retval)
- retval = security_task_setrlimit(tsk, resource, new_rlim);
- }
- if (!retval) {
- if (old_rlim)
- *old_rlim = *rlim;
- if (new_rlim)
- *rlim = *new_rlim;
- }
- task_unlock(tsk->group_leader);
-
- /*
- * RLIMIT_CPU handling. Arm the posix CPU timer if the limit is not
- * infinite. In case of RLIM_INFINITY the posix CPU timer code
- * ignores the rlimit.
- */
- if (!retval && new_rlim && resource == RLIMIT_CPU &&
- new_rlim->rlim_cur != RLIM_INFINITY &&
- IS_ENABLED(CONFIG_POSIX_TIMERS))
- update_rlimit_cpu(tsk, new_rlim->rlim_cur);
-out:
- read_unlock(&tasklist_lock);
- return retval;
-}
-
/* rcu lock must be held */
static int check_prlimit_permission(struct task_struct *task,
unsigned int flags)
@@ -2261,6 +2284,70 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
#define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE)
+#ifdef CONFIG_ANON_VMA_NAME
+
+#define ANON_VMA_NAME_MAX_LEN 80
+#define ANON_VMA_NAME_INVALID_CHARS "\\`$[]"
+
+static inline bool is_valid_name_char(char ch)
+{
+ /* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */
+ return ch > 0x1f && ch < 0x7f &&
+ !strchr(ANON_VMA_NAME_INVALID_CHARS, ch);
+}
+
+static int prctl_set_vma(unsigned long opt, unsigned long addr,
+ unsigned long size, unsigned long arg)
+{
+ struct mm_struct *mm = current->mm;
+ const char __user *uname;
+ struct anon_vma_name *anon_name = NULL;
+ int error;
+
+ switch (opt) {
+ case PR_SET_VMA_ANON_NAME:
+ uname = (const char __user *)arg;
+ if (uname) {
+ char *name, *pch;
+
+ name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN);
+ if (IS_ERR(name))
+ return PTR_ERR(name);
+
+ for (pch = name; *pch != '\0'; pch++) {
+ if (!is_valid_name_char(*pch)) {
+ kfree(name);
+ return -EINVAL;
+ }
+ }
+ /* anon_vma has its own copy */
+ anon_name = anon_vma_name_alloc(name);
+ kfree(name);
+ if (!anon_name)
+ return -ENOMEM;
+
+ }
+
+ mmap_write_lock(mm);
+ error = madvise_set_anon_name(mm, addr, size, anon_name);
+ mmap_write_unlock(mm);
+ anon_vma_name_put(anon_name);
+ break;
+ default:
+ error = -EINVAL;
+ }
+
+ return error;
+}
+
+#else /* CONFIG_ANON_VMA_NAME */
+static int prctl_set_vma(unsigned long opt, unsigned long start,
+ unsigned long size, unsigned long arg)
+{
+ return -EINVAL;
+}
+#endif /* CONFIG_ANON_VMA_NAME */
+
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
@@ -2463,6 +2550,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
case PR_SVE_GET_VL:
error = SVE_GET_VL();
break;
+ case PR_SME_SET_VL:
+ error = SME_SET_VL(arg2);
+ break;
+ case PR_SME_GET_VL:
+ error = SME_GET_VL();
+ break;
case PR_GET_SPECULATION_CTRL:
if (arg3 || arg4 || arg5)
return -EINVAL;
@@ -2530,6 +2623,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
error = sched_core_share_pid(arg2, arg3, arg4, arg5);
break;
#endif
+ case PR_SET_VMA:
+ error = prctl_set_vma(arg2, arg3, arg4, arg5);
+ break;
default:
error = -EINVAL;
break;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.