linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Peter Oskolkov <posk@posk.io>
Cc: Ingo Molnar <mingo@redhat.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	linux-kernel@vger.kernel.org, linux-api@vger.kernel.org,
	Paul Turner <pjt@google.com>, Ben Segall <bsegall@google.com>,
	Peter Oskolkov <posk@google.com>,
	Joel Fernandes <joel@joelfernandes.org>,
	Andrei Vagin <avagin@google.com>,
	Jim Newsome <jnewsome@torproject.org>,
	Jann Horn <jannh@google.com>
Subject: Re: [RFC PATCH 2/3 v0.2] sched/umcg: RFC: add userspace atomic helpers
Date: Fri, 9 Jul 2021 10:01:56 +0200	[thread overview]
Message-ID: <YOgCdMWE9OXvqczk@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20210708194638.128950-3-posk@google.com>

On Thu, Jul 08, 2021 at 12:46:37PM -0700, Peter Oskolkov wrote:

> +static inline int umcg_atomic_cmpxchg_64(u64 *uval, u64 __user *uaddr,
> +						u64 oldval, u64 newval)
> +{
> +	int ret = 0;
> +
> +	if (!user_access_begin(uaddr, sizeof(u64)))
> +		return -EFAULT;
> +	asm volatile("\n"
> +		"1:\t" LOCK_PREFIX "cmpxchgq %4, %2\n"
> +		"2:\n"
> +		"\t.section .fixup, \"ax\"\n"
> +		"3:\tmov     %3, %0\n"
> +		"\tjmp     2b\n"
> +		"\t.previous\n"
> +		_ASM_EXTABLE_UA(1b, 3b)
> +		: "+r" (ret), "=a" (oldval), "+m" (*uaddr)
> +		: "i" (-EFAULT), "r" (newval), "1" (oldval)
> +		: "memory"
> +	);
> +	user_access_end();
> +	*uval = oldval;
> +	return ret;
> +}

> +static inline int fix_pagefault(unsigned long uaddr, bool write_fault)
> +{
> +	struct mm_struct *mm = current->mm;
> +	int ret;
> +
> +	mmap_read_lock(mm);
> +	ret = fixup_user_fault(mm, uaddr, write_fault ? FAULT_FLAG_WRITE : 0,
> +			NULL);
> +	mmap_read_unlock(mm);
> +
> +	return ret < 0 ? ret : 0;
> +}

> +static inline int umcg_cmpxchg_64_user(u64 __user *uaddr, u64 *prev, u64 val)
> +{
> +	while (true) {
> +		int ret;
> +		u64 expected = *prev;
> +
> +		pagefault_disable();
> +		ret = umcg_atomic_cmpxchg_64(prev, uaddr, expected, val);
> +		pagefault_enable();
> +
> +		if (!ret)
> +			return *prev == expected ? 0 : -EAGAIN;
> +
> +		if (WARN_ONCE(ret != -EFAULT, "Unexpected error"))
> +			return -EFAULT;
> +
> +		ret = fix_pagefault((unsigned long)uaddr, true);
> +		if (ret)
> +			return -EFAULT;
> +	}
> +}
> +
> +/**
> + * atomic_stack_push_user - push a node onto the stack
> + * @head - a pointer to the head of the stack;
> + * @node - a pointer to the node to push.
> + *
> + * Push a node onto a single-linked list (stack). Atomicity/correctness
> + * is guaranteed by locking the head via settings its first bit (assuming
> + * the pointer is aligned).
> + *
> + * Return: 0 on success, -EFAULT on error.
> + */
> +static inline int atomic_stack_push_user(u64 __user *head, u64 __user *node)
> +{
> +	while (true) {
> +		int ret;
> +		u64 first;
> +
> +		smp_mb();  /* Make the read below clean. */
> +		if (get_user(first, head))
> +			return -EFAULT;
> +
> +		if (first & 1UL) {
> +			cpu_relax();
> +			continue;  /* first is being deleted. */
> +		}
> +
> +		if (put_user(first, node))
> +			return -EFAULT;
> +		smp_mb();  /* Make the write above visible. */
> +
> +		ret = umcg_cmpxchg_64_user(head, &first, (u64)node);
> +		if (!ret)
> +			return 0;
> +
> +		if (ret == -EAGAIN) {
> +			cpu_relax();
> +			continue;
> +		}
> +
> +		if (WARN_ONCE(ret != -EFAULT, "unexpected umcg_cmpxchg result"))
> +			return -EFAULT;
> +
> +		return -EFAULT;
> +	}
> +}


This is horrible... Jann is absolutely right, you do not, *ever* do
userspace spinlocks. What's wrong with the trivial lockless single
linked list approach?

On top of that, you really want to avoid all that endless stac/clac
nonsense and only have that once, at the outer edges of things.

Something like the *completely* untested below (except it needs lots of
extra gunk to support compilers without asm-goto-output, and more widths
and ...


#define __try_cmpxchg_user_size(ptr, oldp, new, size, label)		\
({									\
	_Bool __success;						\
	__chk_user_ptr(ptr);						\
	__typeof__(ptr) _old = (__typeof__(ptr))(oldp);			\
	__typeof__(*(ptr)) __old = *_old;				\
	__typeof__(*(ptr)) __new = (new);				\
	switch (size) {							\
	case 8:								\
		volatile u64 *__ptr = (volatile u64 *)(ptr);		\
		asm_volatile_goto("1: " LOCK_PREFIX "cmpxchgq %[new], %[ptr]" \
				  CC_SET(z)				\
				  _ASM_EXTABLE_UA(1b, %l[label])	\
				  : CC_OUT(x) (__success),		\
				    [ptr] "+m" (*__ptr),		\
				    [old] "+a" (__old),			\
				  : [new] "r" (__new)			\
				  : "memory"				\
				  : label);				\
		break;							\
	}								\
	if (unlikely(!success))						\
		*_old = __old;						\
	__success;							\
})

#define unsafe_try_cmpxchg_user(ptr, oldp, new, label)			\
	__try_cmpxchg_user_size((ptr), (oldp), (new), sizeof(*(ptr)), label);

int user_llist_add(u64 __user *new, u64 __user *head)
{
	u64 first;
	int ret;

	if (unlikely(!access_ok(new, sizeof(*new)) ||
		     !access_ok(head, sizeof(*head))))
		return -EFAULT;

again:
	__uaccess_begin_nospec();

	unsafe_get_user(first, head, Efault_head);
	do {
		unsafe_put_user(first, new, Efault_new);
	} while (!unsafe_try_cmpxchg_user(head, &first, new, Efault_head));

	user_access_end();

	return 0;

Efault_new:
	user_access_end();

	ret = fixup_fault(new);
	if (ret < 0)
		return ret;

	goto again;

Efault_head:
	user_access_end();

	ret = fixup_fault(head);
	if (ret < 0)
		return ret;

	goto again;
}

  parent reply	other threads:[~2021-07-09  8:02 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-08 19:46 [RFC PATCH 0/3 v0.2] RFC: sched/UMCG Peter Oskolkov
2021-07-08 19:46 ` [RFC PATCH 1/3 v0.2] sched: add WF_CURRENT_CPU and externise ttwu Peter Oskolkov
2021-07-08 19:46 ` [RFC PATCH 2/3 v0.2] sched/umcg: RFC: add userspace atomic helpers Peter Oskolkov
2021-07-08 21:12   ` Jann Horn
2021-07-09  4:01     ` Peter Oskolkov
2021-07-09  8:01   ` Peter Zijlstra [this message]
2021-07-09 16:57     ` Peter Oskolkov
2021-07-09 17:33       ` Peter Oskolkov
2021-07-13 16:10       ` Peter Zijlstra
2021-07-13 17:14         ` Peter Oskolkov
2021-07-08 19:46 ` [RFC PATCH 3/3 v0.2] sched/umcg: RFC: implement UMCG syscalls Peter Oskolkov
2021-07-11 16:35   ` Peter Oskolkov
2021-07-11 18:29   ` Thierry Delisle
2021-07-12 15:40     ` Peter Oskolkov
2021-07-12 21:44       ` Thierry Delisle
2021-07-12 23:31         ` Peter Oskolkov
2021-07-13 14:02           ` Peter Zijlstra

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=YOgCdMWE9OXvqczk@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=avagin@google.com \
    --cc=bsegall@google.com \
    --cc=jannh@google.com \
    --cc=jnewsome@torproject.org \
    --cc=joel@joelfernandes.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=pjt@google.com \
    --cc=posk@google.com \
    --cc=posk@posk.io \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).