| 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
| ||
|
Message-ID: <59A4DADE.5050303@intel.com>
Date: Tue, 29 Aug 2017 11:09:18 +0800
From: Wei Wang <wei.w.wang@...el.com>
To: "Michael S. Tsirkin" <mst@...hat.com>
CC: virtio-dev@...ts.oasis-open.org, linux-kernel@...r.kernel.org,
qemu-devel@...gnu.org, virtualization@...ts.linux-foundation.org,
kvm@...r.kernel.org, linux-mm@...ck.org, mhocko@...nel.org,
akpm@...ux-foundation.org, mawilcox@...rosoft.com,
david@...hat.com, cornelia.huck@...ibm.com,
mgorman@...hsingularity.net, aarcange@...hat.com,
amit.shah@...hat.com, pbonzini@...hat.com, willy@...radead.org,
liliang.opensource@...il.com, yang.zhang.wz@...il.com,
quan.xu@...yun.com
Subject: Re: [PATCH v15 3/5] virtio-balloon: VIRTIO_BALLOON_F_SG
On 08/29/2017 02:03 AM, Michael S. Tsirkin wrote:
> On Mon, Aug 28, 2017 at 06:08:31PM +0800, Wei Wang wrote:
>> Add a new feature, VIRTIO_BALLOON_F_SG, which enables the transfer
>> of balloon (i.e. inflated/deflated) pages using scatter-gather lists
>> to the host.
>>
>> The implementation of the previous virtio-balloon is not very
>> efficient, because the balloon pages are transferred to the
>> host one by one. Here is the breakdown of the time in percentage
>> spent on each step of the balloon inflating process (inflating
>> 7GB of an 8GB idle guest).
>>
>> 1) allocating pages (6.5%)
>> 2) sending PFNs to host (68.3%)
>> 3) address translation (6.1%)
>> 4) madvise (19%)
>>
>> It takes about 4126ms for the inflating process to complete.
>> The above profiling shows that the bottlenecks are stage 2)
>> and stage 4).
>>
>> This patch optimizes step 2) by transferring pages to the host in
>> sgs. An sg describes a chunk of guest physically continuous pages.
>> With this mechanism, step 4) can also be optimized by doing address
>> translation and madvise() in chunks rather than page by page.
>>
>> With this new feature, the above ballooning process takes ~597ms
>> resulting in an improvement of ~86%.
>>
>> TODO: optimize stage 1) by allocating/freeing a chunk of pages
>> instead of a single page each time.
>>
>> Signed-off-by: Wei Wang <wei.w.wang@...el.com>
>> Signed-off-by: Liang Li <liang.z.li@...el.com>
>> Suggested-by: Michael S. Tsirkin <mst@...hat.com>
>> ---
>> drivers/virtio/virtio_balloon.c | 171 ++++++++++++++++++++++++++++++++----
>> include/uapi/linux/virtio_balloon.h | 1 +
>> 2 files changed, 155 insertions(+), 17 deletions(-)
>>
>> diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
>> index f0b3a0b..8ecc1d4 100644
>> --- a/drivers/virtio/virtio_balloon.c
>> +++ b/drivers/virtio/virtio_balloon.c
>> @@ -32,6 +32,8 @@
>> #include <linux/mm.h>
>> #include <linux/mount.h>
>> #include <linux/magic.h>
>> +#include <linux/xbitmap.h>
>> +#include <asm/page.h>
>>
>> /*
>> * Balloon device works in 4K page units. So each page is pointed to by
>> @@ -79,6 +81,9 @@ struct virtio_balloon {
>> /* Synchronize access/update to this struct virtio_balloon elements */
>> struct mutex balloon_lock;
>>
>> + /* The xbitmap used to record balloon pages */
>> + struct xb page_xb;
>> +
>> /* The array of pfns we tell the Host about. */
>> unsigned int num_pfns;
>> __virtio32 pfns[VIRTIO_BALLOON_ARRAY_PFNS_MAX];
>> @@ -141,13 +146,111 @@ static void set_page_pfns(struct virtio_balloon *vb,
>> page_to_balloon_pfn(page) + i);
>> }
>>
>> +static int add_one_sg(struct virtqueue *vq, void *addr, uint32_t size)
>> +{
>> + struct scatterlist sg;
>> +
>> + sg_init_one(&sg, addr, size);
>> + return virtqueue_add_inbuf(vq, &sg, 1, vq, GFP_KERNEL);
>> +}
>> +
>> +static void send_balloon_page_sg(struct virtio_balloon *vb,
>> + struct virtqueue *vq,
>> + void *addr,
>> + uint32_t size,
>> + bool batch)
>> +{
>> + unsigned int len;
>> + int err;
>> +
>> + err = add_one_sg(vq, addr, size);
>> + /* Sanity check: this can't really happen */
>> + WARN_ON(err);
> It might be cleaner to detect that add failed due to
> ring full and kick then. Just an idea, up to you
> whether to do it.
>
>> +
>> + /* If batching is in use, we batch the sgs till the vq is full. */
>> + if (!batch || !vq->num_free) {
>> + virtqueue_kick(vq);
>> + wait_event(vb->acked, virtqueue_get_buf(vq, &len));
>> + /* Release all the entries if there are */
> Meaning
> Account for all used entries if any
> ?
>
>> + while (virtqueue_get_buf(vq, &len))
>> + ;
>
> Above code is reused below. Add a function?
>
>> + }
>> +}
>> +
>> +/*
>> + * Send balloon pages in sgs to host. The balloon pages are recorded in the
>> + * page xbitmap. Each bit in the bitmap corresponds to a page of PAGE_SIZE.
>> + * The page xbitmap is searched for continuous "1" bits, which correspond
>> + * to continuous pages, to chunk into sgs.
>> + *
>> + * @page_xb_start and @page_xb_end form the range of bits in the xbitmap that
>> + * need to be searched.
>> + */
>> +static void tell_host_sgs(struct virtio_balloon *vb,
>> + struct virtqueue *vq,
>> + unsigned long page_xb_start,
>> + unsigned long page_xb_end)
>> +{
>> + unsigned long sg_pfn_start, sg_pfn_end;
>> + void *sg_addr;
>> + uint32_t sg_len, sg_max_len = round_down(UINT_MAX, PAGE_SIZE);
>> +
>> + sg_pfn_start = page_xb_start;
>> + while (sg_pfn_start < page_xb_end) {
>> + sg_pfn_start = xb_find_next_bit(&vb->page_xb, sg_pfn_start,
>> + page_xb_end, 1);
>> + if (sg_pfn_start == page_xb_end + 1)
>> + break;
>> + sg_pfn_end = xb_find_next_bit(&vb->page_xb, sg_pfn_start + 1,
>> + page_xb_end, 0);
>> + sg_addr = (void *)pfn_to_kaddr(sg_pfn_start);
>> + sg_len = (sg_pfn_end - sg_pfn_start) << PAGE_SHIFT;
>> + while (sg_len > sg_max_len) {
>> + send_balloon_page_sg(vb, vq, sg_addr, sg_max_len, 1);
> Last argument should be true, not 1.
>
>> + sg_addr += sg_max_len;
>> + sg_len -= sg_max_len;
>> + }
>> + send_balloon_page_sg(vb, vq, sg_addr, sg_len, 1);
>> + xb_zero(&vb->page_xb, sg_pfn_start, sg_pfn_end);
>> + sg_pfn_start = sg_pfn_end + 1;
>> + }
>> +
>> + /*
>> + * The last few sgs may not reach the batch size, but need a kick to
>> + * notify the device to handle them.
>> + */
>> + if (vq->num_free != virtqueue_get_vring_size(vq)) {
>> + virtqueue_kick(vq);
>> + wait_event(vb->acked, virtqueue_get_buf(vq, &sg_len));
>> + while (virtqueue_get_buf(vq, &sg_len))
>> + ;
> Some entries can get used after a pause. Looks like they will leak then?
> One fix would be to convert above if to a while loop.
> I don't know whether to do it like this in send_balloon_page_sg too.
>
Thanks for the above comments. I've re-written this part of code.
Please have a check below if there is anything more we could improve:
static void kick_and_wait(struct virtqueue *vq, wait_queue_head_t wq_head)
{
unsigned int len;
virtqueue_kick(vq);
wait_event(wq_head, virtqueue_get_buf(vq, &len));
/* Detach all the used buffers from the vq */
while (virtqueue_get_buf(vq, &len))
;
}
static int add_one_sg(struct virtqueue *vq, void *addr, uint32_t size)
{
struct scatterlist sg;
int ret;
sg_init_one(&sg, addr, size);
ret = virtqueue_add_inbuf(vq, &sg, 1, vq, GFP_KERNEL);
if (unlikely(ret == -ENOSPC))
dev_warn(&vq->vdev->dev, "%s: failed due to ring full\n",
__func__);
return ret;
}
static void send_balloon_page_sg(struct virtio_balloon *vb,
struct virtqueue *vq,
void *addr,
uint32_t size,
bool batch)
{
int err;
do {
err = add_one_sg(vq, addr, size);
if (err == -ENOSPC || !batch || !vq->num_free)
kick_and_wait(vq, vb->acked);
} while (err == -ENOSPC);
}
Best,
Wei
Powered by blists - more mailing lists