Re: [PATCH 5/5] io_uring: add IORING_OP_WAITID support

[Jens Axboe <axboe@kernel.dk>]

On 7/15/23 8:06?AM, Jens Axboe wrote:
> On 7/15/23 1:12?AM, Arnd Bergmann wrote:
>> On Fri, Jul 14, 2023, at 22:14, Jens Axboe wrote:
>>> On 7/14/23 12:33?PM, Arnd Bergmann wrote:
>>>> On Fri, Jul 14, 2023, at 17:47, Christian Brauner wrote:
>>>>> On Tue, Jul 11, 2023 at 04:18:13PM -0600, Jens Axboe wrote:
>>>>>>>> Does this require argument conversion for compat tasks?
>>>>>>>>
>>>>>>>> Even without the rusage argument, I think the siginfo
>>>>>>>> remains incompatible with 32-bit tasks, unfortunately.
>>>>>>>
>>>>>>> Hmm yes good point, if compat_siginfo and siginfo are different, then it
>>>>>>> does need handling for that. Would be a trivial addition, I'll make that
>>>>>>> change. Thanks Arnd!
>>>>>>
>>>>>> Should be fixed in the current version:
>>>>>>
>>>>>> https://git.kernel.dk/cgit/linux/commit/?h=io_uring-waitid&id=08f3dc9b7cedbd20c0f215f25c9a7814c6c601cc
>>>>>
>>>>> In kernel/signal.c in pidfd_send_signal() we have
>>>>> copy_siginfo_from_user_any() it seems that a similar version
>>>>> copy_siginfo_to_user_any() might be something to consider. We do have
>>>>> copy_siginfo_to_user32() and copy_siginfo_to_user(). But I may lack
>>>>> context why this wouldn't work here.
>>>>
>>>> We could add a copy_siginfo_to_user_any(), but I think open-coding
>>>> it is easier here, since the in_compat_syscall() check does not
>>>> work inside of the io_uring kernel thread, it has to be
>>>> "if (req->ctx->compat)" in order to match the wordsize of the task
>>>> that started the request.
>>>
>>> Yeah, unifying this stuff did cross my mind when adding another one.
>>> Which I think could still be done, you'd just need to pass in a 'compat'
>>> parameter similar to how it's done for iovec importing.
>>>
>>> But if it's ok with everybody I'd rather do that as a cleanup post this.
>>
>> Sure, keeping that separate seem best.
>>
>> Looking at what copy_siginfo_from_user_any() actually does, I don't
>> even think it's worth adapting copy_siginfo_to_user_any() for io_uring,
>> since it's already just a trivial wrapper, and adding another
>> argument would add more complexity overall than it saves.
> 
> Yeah, took a look too this morning, and not sure there's much to reduce
> here that would make it cleaner. I'm going to send out a v2 with this
> unchanged, holler if people disagree.

One thing we could do is the below, but honestly not sure it's worth the
hassle?


diff --git a/io_uring/waitid.c b/io_uring/waitid.c
index 14ffa07e161a..6de1041c4784 100644
--- a/io_uring/waitid.c
+++ b/io_uring/waitid.c
@@ -43,6 +43,8 @@ static bool io_waitid_compat_copy_si(struct io_waitid *iw, int signo)
 	bool ret;
 
 	infop = (struct compat_siginfo __user *) iw->infop;
+	if (!infop)
+		return true;
 
 	if (!user_write_access_begin(infop, sizeof(*infop)))
 		return false;
@@ -66,32 +68,13 @@ static bool io_waitid_compat_copy_si(struct io_waitid *iw, int signo)
 static bool io_waitid_copy_si(struct io_kiocb *req, int signo)
 {
 	struct io_waitid *iw = io_kiocb_to_cmd(req, struct io_waitid);
-	bool ret;
-
-	if (!iw->infop)
-		return true;
 
 #ifdef CONFIG_COMPAT
 	if (req->ctx->compat)
 		return io_waitid_compat_copy_si(iw, signo);
 #endif
 
-	if (!user_write_access_begin(iw->infop, sizeof(*iw->infop)))
-		return false;
-
-	unsafe_put_user(signo, &iw->infop->si_signo, Efault);
-	unsafe_put_user(0, &iw->infop->si_errno, Efault);
-	unsafe_put_user(iw->info.cause, &iw->infop->si_code, Efault);
-	unsafe_put_user(iw->info.pid, &iw->infop->si_pid, Efault);
-	unsafe_put_user(iw->info.uid, &iw->infop->si_uid, Efault);
-	unsafe_put_user(iw->info.status, &iw->infop->si_status, Efault);
-	ret = true;
-done:
-	user_write_access_end();
-	return ret;
-Efault:
-	ret = false;
-	goto done;
+	return siginfo_put_user(iw->infop, &iw->info, signo);
 }
 
 static int io_waitid_finish(struct io_kiocb *req, int ret)
diff --git a/kernel/exit.c b/kernel/exit.c
index 1c9d1cbadcd0..e3a0b6699a23 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -1723,6 +1723,28 @@ static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop,
 	return ret;
 }
 
+bool siginfo_put_user(struct siginfo __user *infop, struct waitid_info *wi,
+		      int signo)
+{
+	if (!infop)
+		return true;
+
+	if (!user_write_access_begin(infop, sizeof(*infop)))
+		return false;
+
+	unsafe_put_user(signo, &infop->si_signo, Efault);
+	unsafe_put_user(0, &infop->si_errno, Efault);
+	unsafe_put_user(wi->cause, &infop->si_code, Efault);
+	unsafe_put_user(wi->pid, &infop->si_pid, Efault);
+	unsafe_put_user(wi->uid, &infop->si_uid, Efault);
+	unsafe_put_user(wi->status, &infop->si_status, Efault);
+	user_write_access_end();
+	return true;
+Efault:
+	user_write_access_end();
+	return false;
+}
+
 SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 		infop, int, options, struct rusage __user *, ru)
 {
@@ -1737,23 +1759,9 @@ SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
 		if (ru && copy_to_user(ru, &r, sizeof(struct rusage)))
 			return -EFAULT;
 	}
-	if (!infop)
-		return err;
-
-	if (!user_write_access_begin(infop, sizeof(*infop)))
+	if (siginfo_put_user(infop, &info, signo))
 		return -EFAULT;
-
-	unsafe_put_user(signo, &infop->si_signo, Efault);
-	unsafe_put_user(0, &infop->si_errno, Efault);
-	unsafe_put_user(info.cause, &infop->si_code, Efault);
-	unsafe_put_user(info.pid, &infop->si_pid, Efault);
-	unsafe_put_user(info.uid, &infop->si_uid, Efault);
-	unsafe_put_user(info.status, &infop->si_status, Efault);
-	user_write_access_end();
 	return err;
-Efault:
-	user_write_access_end();
-	return -EFAULT;
 }
 
 long kernel_wait4(pid_t upid, int __user *stat_addr, int options,
diff --git a/kernel/exit.h b/kernel/exit.h
index f10207ba1341..b7e0e32133fa 100644
--- a/kernel/exit.h
+++ b/kernel/exit.h
@@ -27,4 +27,6 @@ long __do_wait(struct wait_opts *wo);
 int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid,
 			  struct waitid_info *infop, int options,
 			  struct rusage *ru, unsigned int *f_flags);
+bool siginfo_put_user(struct siginfo __user *infop, struct waitid_info *wi,
+		      int signo);
 #endif

-- 
Jens Axboe