netdev - Re: [PATCH bpf-next 1/6] bpf: implement BPF ring buffer and verifier support for it

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20200514165045.sk6zjlhsfzxbo6mb@bsd-mbp>
Date:   Thu, 14 May 2020 09:50:45 -0700
From:   Jonathan Lemon <bsd@...com>
To:     Andrii Nakryiko <andriin@...com>
Cc:     bpf@...r.kernel.org, netdev@...r.kernel.org, ast@...com,
        daniel@...earbox.net, andrii.nakryiko@...il.com,
        kernel-team@...com, "Paul E . McKenney" <paulmck@...nel.org>,
        Jonathan Lemon <jonathan.lemon@...il.com>
Subject: Re: [PATCH bpf-next 1/6] bpf: implement BPF ring buffer and verifier
 support for it

On Wed, May 13, 2020 at 12:25:27PM -0700, Andrii Nakryiko wrote:
> +static struct bpf_ringbuf *bpf_ringbuf_restore_from_rec(void *meta_ptr)
> +{
> +	unsigned long addr = (unsigned long)meta_ptr;
> +	unsigned long off = *(u32 *)(meta_ptr + 4) << PAGE_SHIFT;
> +
> +	return (void*)((addr & PAGE_MASK) - off);
> +}
> +
> +static void *__bpf_ringbuf_reserve(struct bpf_ringbuf *rb, u64 size)
> +{
> +	unsigned long cons_pos, prod_pos, new_prod_pos, flags;
> +	u32 len, pg_off;
> +	void *meta_ptr;
> +
> +	if (unlikely(size > UINT_MAX))
> +		return NULL;

Size should be 30 bits, not UINT_MAX, since 2 bits are reserved.

> +
> +	len = round_up(size + RINGBUF_META_SZ, 8);
> +	cons_pos = READ_ONCE(rb->consumer_pos);
> +
> +	if (in_nmi()) {
> +		if (!spin_trylock_irqsave(&rb->spinlock, flags))
> +			return NULL;
> +	} else {
> +		spin_lock_irqsave(&rb->spinlock, flags);
> +	}
> +
> +	prod_pos = rb->producer_pos;
> +	new_prod_pos = prod_pos + len;
> +
> +	/* check for out of ringbuf space by ensuring producer position
> +	 * doesn't advance more than (ringbuf_size - 1) ahead
> +	 */
> +	if (new_prod_pos - cons_pos > rb->mask) {
> +		spin_unlock_irqrestore(&rb->spinlock, flags);
> +		return NULL;
> +	}
> +
> +	meta_ptr = rb->data + (prod_pos & rb->mask);
> +	pg_off = bpf_ringbuf_rec_pg_off(rb, meta_ptr);
> +
> +	WRITE_ONCE(*(u32 *)meta_ptr, RINGBUF_BUSY_BIT | size);
> +	WRITE_ONCE(*(u32 *)(meta_ptr + 4), pg_off);

Or define a 64bit word in the structure and use:

        WRITE_ONCE(*(u64 *)meta_ptr, rec.header);


> +
> +	/* ensure length prefix is written before updating producer positions */
> +	smp_wmb();
> +	WRITE_ONCE(rb->producer_pos, new_prod_pos);
> +
> +	spin_unlock_irqrestore(&rb->spinlock, flags);
> +
> +	return meta_ptr + RINGBUF_META_SZ;
> +}
> +
> +BPF_CALL_3(bpf_ringbuf_reserve, struct bpf_map *, map, u64, size, u64, flags)
> +{
> +	struct bpf_ringbuf_map *rb_map;
> +
> +	if (unlikely(flags))
> +		return -EINVAL;
> +
> +	rb_map = container_of(map, struct bpf_ringbuf_map, map);
> +	return (unsigned long)__bpf_ringbuf_reserve(rb_map->rb, size);
> +}
> +

--
Jonathan