mm/madvise: support both pid and pidfd for process_madvise

There is a demand[1] to support pid as well pidfd for process_madvise
to reduce unnecessary syscall to get pidfd if the user has control of
the target process (ie, they could guarantee the process is not gone or
pid is not reused).

This patch aims for supporting both options like waitid(2).  So, the
syscall is currently,

        int process_madvise(idtype_t idtype, id_t id, void *addr,
                size_t length, int advice, unsigned long flags);

@which is actually idtype_t for userspace library and currently, it
supports P_PID and P_PIDFD.

[1]  https://lore.kernel.org/linux-mm/9d849087-3359-c4ab-fbec-859e8186c509@virtuozzo.com/.

Change-Id: I06249a7621685e120e548a94098e6cce8d32d38d
Link: http://lkml.kernel.org/r/20200302193630.68771-6-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Suggested-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Christian Brauner <christian@brauner.io>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Daniel Colascione <dancol@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Joel Fernandes <joel@joelfernandes.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Dias <joaodias@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oleksandr Natalenko <oleksandr@redhat.com>
Cc: Sandeep Patil <sspatil@google.com>
Cc: SeongJae Park <sj38.park@gmail.com>
Cc: SeongJae Park <sjpark@amazon.de>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Sonny Rao <sonnyrao@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Christian Brauner <christian.brauner@ubuntu.com>
Cc: <linux-man@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Git-Commit: 6c7663468de1b093e8ef5c0ef1df42c890f612bf
Git-Repo: git://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git
Signed-off-by: Charan Teja Reddy <charante@codeaurora.org>
This commit is contained in:
Minchan Kim 2020-05-22 14:28:20 +10:00 • committed by Charan Teja Reddy
commit 306d0c3e29
2 changed files with 24 additions and 13 deletions

View file

@ -874,7 +874,8 @@ asmlinkage long sys_munlockall(void);
asmlinkage long sys_mincore(unsigned long start, size_t len,
unsigned char __user * vec);
asmlinkage long sys_madvise(unsigned long start, size_t len, int behavior);
asmlinkage long sys_process_madvise(int pidfd, unsigned long start,
asmlinkage long sys_process_madvise(int which, pid_t pid, unsigned long start,
size_t len, int behavior, unsigned long flags);
asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
unsigned long prot, unsigned long pgoff,

View file

@ -1208,11 +1208,10 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
return do_madvise(current, current->mm, start, len_in, behavior);
}
SYSCALL_DEFINE5(process_madvise, int, pidfd, unsigned long, start,
SYSCALL_DEFINE6(process_madvise, int, which, pid_t, upid, unsigned long, start,
size_t, len_in, int, behavior, unsigned long, flags)
{
int ret;
struct fd f;
struct pid *pid;
struct task_struct *task;
struct mm_struct *mm;
@ -1223,20 +1222,31 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, unsigned long, start,
if (!process_madvise_behavior_valid(behavior))
return -EINVAL;
f = fdget(pidfd);
if (!f.file)
return -EBADF;
switch (which) {
case P_PID:
if (upid <= 0)
return -EINVAL;
pid = pidfd_pid(f.file);
if (IS_ERR(pid)) {
ret = PTR_ERR(pid);
goto fdput;
pid = find_get_pid(upid);
if (!pid)
return -ESRCH;
break;
case P_PIDFD:
if (upid < 0)
return -EINVAL;
pid = pidfd_get_pid(upid);
if (IS_ERR(pid))
return PTR_ERR(pid);
break;
default:
return -EINVAL;
}
task = get_pid_task(pid, PIDTYPE_PID);
if (!task) {
ret = -ESRCH;
goto fdput;
goto put_pid;
}
mm = mm_access(task, PTRACE_MODE_ATTACH_FSCREDS);
@ -1249,7 +1259,7 @@ SYSCALL_DEFINE5(process_madvise, int, pidfd, unsigned long, start,
mmput(mm);
release_task:
put_task_struct(task);
fdput:
fdput(f);
put_pid:
put_pid(pid);
return ret;
}