Re: [PATCH 1/6] mm: change locked_vm's type from unsigned long to atomic64_t

[Mark Rutland <mark.rutland@xxxxxxx>]

On Thu, Apr 11, 2019 at 02:22:23PM +1000, Alexey Kardashevskiy wrote:
> On 03/04/2019 07:41, Daniel Jordan wrote:

> > -	dev_dbg(dev, "[%d] RLIMIT_MEMLOCK %c%ld %ld/%ld%s\n", current->pid,
> > +	dev_dbg(dev, "[%d] RLIMIT_MEMLOCK %c%ld %lld/%lu%s\n", current->pid,
> >  		incr ? '+' : '-', npages << PAGE_SHIFT,
> > -		current->mm->locked_vm << PAGE_SHIFT, rlimit(RLIMIT_MEMLOCK),
> > -		ret ? "- exceeded" : "");
> > +		(s64)atomic64_read(&current->mm->locked_vm) << PAGE_SHIFT,
> > +		rlimit(RLIMIT_MEMLOCK), ret ? "- exceeded" : "");
> 
> 
> 
> atomic64_read() returns "long" which matches "%ld", why this change (and
> similar below)? You did not do this in the two pr_debug()s above anyway.

Unfortunately, architectures return inconsistent types for atomic64 ops.

Some return long (e..g. powerpc), some return long long (e.g. arc), and
some return s64 (e.g. x86).

I'm currently trying to clean things up so that all use s64 [1], but in
the mean time it's necessary for generic code use a cast or temporarly
variable to ensure a consistent type. Once that's cleaned up, we can
remove the redundant casts.

Thanks,
Mark.

[1] https://git.kernel.org/pub/scm/linux/kernel/git/mark/linux.git/log/?h=atomics/type-cleanup