summaryrefslogtreecommitdiff
path: root/kernel/sys.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sys.c')
-rw-r--r--kernel/sys.c215
1 files changed, 125 insertions, 90 deletions
diff --git a/kernel/sys.c b/kernel/sys.c
index a03d9cd23ed7..259fda25eb6b 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -92,10 +92,10 @@
# define SET_TSC_CTL(a) (-EINVAL)
#endif
#ifndef MPX_ENABLE_MANAGEMENT
-# define MPX_ENABLE_MANAGEMENT(a) (-EINVAL)
+# define MPX_ENABLE_MANAGEMENT() (-EINVAL)
#endif
#ifndef MPX_DISABLE_MANAGEMENT
-# define MPX_DISABLE_MANAGEMENT(a) (-EINVAL)
+# define MPX_DISABLE_MANAGEMENT() (-EINVAL)
#endif
#ifndef GET_FP_MODE
# define GET_FP_MODE(a) (-EINVAL)
@@ -325,6 +325,7 @@ out_unlock:
* SMP: There are not races, the GIDs are checked only by filesystem
* operations (as far as semantic preservation is concerned).
*/
+#ifdef CONFIG_MULTIUSER
SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid)
{
struct user_namespace *ns = current_user_ns();
@@ -815,6 +816,7 @@ change_okay:
commit_creds(new);
return old_fsgid;
}
+#endif /* CONFIG_MULTIUSER */
/**
* sys_getpid - return the thread group id of the current process
@@ -1647,14 +1649,13 @@ SYSCALL_DEFINE1(umask, int, mask)
return mask;
}
-static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd)
+static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd)
{
struct fd exe;
+ struct file *old_exe, *exe_file;
struct inode *inode;
int err;
- VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
-
exe = fdget(fd);
if (!exe.file)
return -EBADF;
@@ -1678,15 +1679,22 @@ static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd)
/*
* Forbid mm->exe_file change if old file still mapped.
*/
+ exe_file = get_mm_exe_file(mm);
err = -EBUSY;
- if (mm->exe_file) {
+ if (exe_file) {
struct vm_area_struct *vma;
- for (vma = mm->mmap; vma; vma = vma->vm_next)
- if (vma->vm_file &&
- path_equal(&vma->vm_file->f_path,
- &mm->exe_file->f_path))
- goto exit;
+ down_read(&mm->mmap_sem);
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (!vma->vm_file)
+ continue;
+ if (path_equal(&vma->vm_file->f_path,
+ &exe_file->f_path))
+ goto exit_err;
+ }
+
+ up_read(&mm->mmap_sem);
+ fput(exe_file);
}
/*
@@ -1700,13 +1708,20 @@ static int prctl_set_mm_exe_file_locked(struct mm_struct *mm, unsigned int fd)
goto exit;
err = 0;
- set_mm_exe_file(mm, exe.file); /* this grabs a reference to exe.file */
+ /* set the new file, lockless */
+ get_file(exe.file);
+ old_exe = xchg(&mm->exe_file, exe.file);
+ if (old_exe)
+ fput(old_exe);
exit:
fdput(exe);
return err;
+exit_err:
+ up_read(&mm->mmap_sem);
+ fput(exe_file);
+ goto exit;
}
-#ifdef CONFIG_CHECKPOINT_RESTORE
/*
* WARNING: we don't require any capability here so be very careful
* in what is allowed for modification from userspace.
@@ -1802,6 +1817,7 @@ out:
return error;
}
+#ifdef CONFIG_CHECKPOINT_RESTORE
static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size)
{
struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, };
@@ -1838,10 +1854,9 @@ static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data
user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL;
}
- down_write(&mm->mmap_sem);
if (prctl_map.exe_fd != (u32)-1)
- error = prctl_set_mm_exe_file_locked(mm, prctl_map.exe_fd);
- downgrade_write(&mm->mmap_sem);
+ error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd);
+ down_read(&mm->mmap_sem);
if (error)
goto out;
@@ -1887,10 +1902,41 @@ out:
}
#endif /* CONFIG_CHECKPOINT_RESTORE */
+static int prctl_set_auxv(struct mm_struct *mm, unsigned long addr,
+ unsigned long len)
+{
+ /*
+ * This doesn't move the auxiliary vector itself since it's pinned to
+ * mm_struct, but it permits filling the vector with new values. It's
+ * up to the caller to provide sane values here, otherwise userspace
+ * tools which use this vector might be unhappy.
+ */
+ unsigned long user_auxv[AT_VECTOR_SIZE];
+
+ if (len > sizeof(user_auxv))
+ return -EINVAL;
+
+ if (copy_from_user(user_auxv, (const void __user *)addr, len))
+ return -EFAULT;
+
+ /* Make sure the last entry is always AT_NULL */
+ user_auxv[AT_VECTOR_SIZE - 2] = 0;
+ user_auxv[AT_VECTOR_SIZE - 1] = 0;
+
+ BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv));
+
+ task_lock(current);
+ memcpy(mm->saved_auxv, user_auxv, len);
+ task_unlock(current);
+
+ return 0;
+}
+
static int prctl_set_mm(int opt, unsigned long addr,
unsigned long arg4, unsigned long arg5)
{
struct mm_struct *mm = current->mm;
+ struct prctl_mm_map prctl_map;
struct vm_area_struct *vma;
int error;
@@ -1907,12 +1953,11 @@ static int prctl_set_mm(int opt, unsigned long addr,
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
- if (opt == PR_SET_MM_EXE_FILE) {
- down_write(&mm->mmap_sem);
- error = prctl_set_mm_exe_file_locked(mm, (unsigned int)addr);
- up_write(&mm->mmap_sem);
- return error;
- }
+ if (opt == PR_SET_MM_EXE_FILE)
+ return prctl_set_mm_exe_file(mm, (unsigned int)addr);
+
+ if (opt == PR_SET_MM_AUXV)
+ return prctl_set_auxv(mm, addr, arg4);
if (addr >= TASK_SIZE || addr < mmap_min_addr)
return -EINVAL;
@@ -1922,42 +1967,64 @@ static int prctl_set_mm(int opt, unsigned long addr,
down_read(&mm->mmap_sem);
vma = find_vma(mm, addr);
+ prctl_map.start_code = mm->start_code;
+ prctl_map.end_code = mm->end_code;
+ prctl_map.start_data = mm->start_data;
+ prctl_map.end_data = mm->end_data;
+ prctl_map.start_brk = mm->start_brk;
+ prctl_map.brk = mm->brk;
+ prctl_map.start_stack = mm->start_stack;
+ prctl_map.arg_start = mm->arg_start;
+ prctl_map.arg_end = mm->arg_end;
+ prctl_map.env_start = mm->env_start;
+ prctl_map.env_end = mm->env_end;
+ prctl_map.auxv = NULL;
+ prctl_map.auxv_size = 0;
+ prctl_map.exe_fd = -1;
+
switch (opt) {
case PR_SET_MM_START_CODE:
- mm->start_code = addr;
+ prctl_map.start_code = addr;
break;
case PR_SET_MM_END_CODE:
- mm->end_code = addr;
+ prctl_map.end_code = addr;
break;
case PR_SET_MM_START_DATA:
- mm->start_data = addr;
+ prctl_map.start_data = addr;
break;
case PR_SET_MM_END_DATA:
- mm->end_data = addr;
+ prctl_map.end_data = addr;
+ break;
+ case PR_SET_MM_START_STACK:
+ prctl_map.start_stack = addr;
break;
-
case PR_SET_MM_START_BRK:
- if (addr <= mm->end_data)
- goto out;
-
- if (check_data_rlimit(rlimit(RLIMIT_DATA), mm->brk, addr,
- mm->end_data, mm->start_data))
- goto out;
-
- mm->start_brk = addr;
+ prctl_map.start_brk = addr;
break;
-
case PR_SET_MM_BRK:
- if (addr <= mm->end_data)
- goto out;
-
- if (check_data_rlimit(rlimit(RLIMIT_DATA), addr, mm->start_brk,
- mm->end_data, mm->start_data))
- goto out;
-
- mm->brk = addr;
+ prctl_map.brk = addr;
break;
+ case PR_SET_MM_ARG_START:
+ prctl_map.arg_start = addr;
+ break;
+ case PR_SET_MM_ARG_END:
+ prctl_map.arg_end = addr;
+ break;
+ case PR_SET_MM_ENV_START:
+ prctl_map.env_start = addr;
+ break;
+ case PR_SET_MM_ENV_END:
+ prctl_map.env_end = addr;
+ break;
+ default:
+ goto out;
+ }
+ error = validate_prctl_map(&prctl_map);
+ if (error)
+ goto out;
+
+ switch (opt) {
/*
* If command line arguments and environment
* are placed somewhere else on stack, we can
@@ -1974,52 +2041,20 @@ static int prctl_set_mm(int opt, unsigned long addr,
error = -EFAULT;
goto out;
}
- if (opt == PR_SET_MM_START_STACK)
- mm->start_stack = addr;
- else if (opt == PR_SET_MM_ARG_START)
- mm->arg_start = addr;
- else if (opt == PR_SET_MM_ARG_END)
- mm->arg_end = addr;
- else if (opt == PR_SET_MM_ENV_START)
- mm->env_start = addr;
- else if (opt == PR_SET_MM_ENV_END)
- mm->env_end = addr;
- break;
-
- /*
- * This doesn't move auxiliary vector itself
- * since it's pinned to mm_struct, but allow
- * to fill vector with new values. It's up
- * to a caller to provide sane values here
- * otherwise user space tools which use this
- * vector might be unhappy.
- */
- case PR_SET_MM_AUXV: {
- unsigned long user_auxv[AT_VECTOR_SIZE];
-
- if (arg4 > sizeof(user_auxv))
- goto out;
- up_read(&mm->mmap_sem);
-
- if (copy_from_user(user_auxv, (const void __user *)addr, arg4))
- return -EFAULT;
-
- /* Make sure the last entry is always AT_NULL */
- user_auxv[AT_VECTOR_SIZE - 2] = 0;
- user_auxv[AT_VECTOR_SIZE - 1] = 0;
-
- BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv));
-
- task_lock(current);
- memcpy(mm->saved_auxv, user_auxv, arg4);
- task_unlock(current);
-
- return 0;
- }
- default:
- goto out;
}
+ mm->start_code = prctl_map.start_code;
+ mm->end_code = prctl_map.end_code;
+ mm->start_data = prctl_map.start_data;
+ mm->end_data = prctl_map.end_data;
+ mm->start_brk = prctl_map.start_brk;
+ mm->brk = prctl_map.brk;
+ mm->start_stack = prctl_map.start_stack;
+ mm->arg_start = prctl_map.arg_start;
+ mm->arg_end = prctl_map.arg_end;
+ mm->env_start = prctl_map.env_start;
+ mm->env_end = prctl_map.env_end;
+
error = 0;
out:
up_read(&mm->mmap_sem);
@@ -2219,12 +2254,12 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
case PR_MPX_ENABLE_MANAGEMENT:
if (arg2 || arg3 || arg4 || arg5)
return -EINVAL;
- error = MPX_ENABLE_MANAGEMENT(me);
+ error = MPX_ENABLE_MANAGEMENT();
break;
case PR_MPX_DISABLE_MANAGEMENT:
if (arg2 || arg3 || arg4 || arg5)
return -EINVAL;
- error = MPX_DISABLE_MANAGEMENT(me);
+ error = MPX_DISABLE_MANAGEMENT();
break;
case PR_SET_FP_MODE:
error = SET_FP_MODE(me, arg2);
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-16 19:43:53 +0000