[dpdk-dev] [PATCH v2 2/2] vhost: cache gpa to hpa translation

[Gavin Hu]

Hi Marvin,

> -----Original Message-----
> From: dev <dev-bounces at dpdk.org> On Behalf Of Marvin Liu
> Sent: Wednesday, April 1, 2020 10:50 PM
> To: maxime.coquelin at redhat.com; xiaolong.ye at intel.com;
> zhihong.wang at intel.com
> Cc: dev at dpdk.org; Marvin Liu <yong.liu at intel.com>
> Subject: [dpdk-dev] [PATCH v2 2/2] vhost: cache gpa to hpa translation
> 
> If Tx zero copy enabled, gpa to hpa mapping table is updated one by
> one. This will harm performance when guest memory backend using 2M
> hugepages. Now add cached mapping table which will sorted by using
> sequence. Address translation will first check cached mapping table,
> then check unsorted mapping table if no match found.
> 
> Signed-off-by: Marvin Liu <yong.liu at intel.com>
> 
> diff --git a/lib/librte_vhost/vhost.h b/lib/librte_vhost/vhost.h
> index 2087d1400..5cb0e83dd 100644
> --- a/lib/librte_vhost/vhost.h
> +++ b/lib/librte_vhost/vhost.h
> @@ -368,7 +368,9 @@ struct virtio_net {
>  	struct vhost_device_ops const *notify_ops;
> 
>  	uint32_t		nr_guest_pages;
> +	uint32_t		nr_cached_guest_pages;
>  	uint32_t		max_guest_pages;
> +	struct guest_page       *cached_guest_pages;
>  	struct guest_page       *guest_pages;
> 
>  	int			slave_req_fd;
> @@ -553,12 +555,25 @@ gpa_to_hpa(struct virtio_net *dev, uint64_t gpa,
> uint64_t size)
>  {
>  	uint32_t i;
>  	struct guest_page *page;
> +	uint32_t cached_pages = dev->nr_cached_guest_pages;
> +
> +	for (i = 0; i < cached_pages; i++) {
> +		page = &dev->cached_guest_pages[i];
> +		if (gpa >= page->guest_phys_addr &&
> +			gpa + size < page->guest_phys_addr + page->size) {
> +			return gpa - page->guest_phys_addr +
> +				page->host_phys_addr;
> +		}
> +	}
Sorry, I did not see any speedup with cached guest pages in comparison to the old code below.
Is it not a simple copy? 
Is it a better idea to use hash instead to speed up the translation? 
/Gavin
> 
>  	for (i = 0; i < dev->nr_guest_pages; i++) {
>  		page = &dev->guest_pages[i];
> 
>  		if (gpa >= page->guest_phys_addr &&
>  		    gpa + size < page->guest_phys_addr + page->size) {
> +			rte_memcpy(&dev-
> >cached_guest_pages[cached_pages],
> +				   page, sizeof(struct guest_page));
> +			dev->nr_cached_guest_pages++;
>  			return gpa - page->guest_phys_addr +
>  			       page->host_phys_addr;
>  		}
> diff --git a/lib/librte_vhost/vhost_user.c b/lib/librte_vhost/vhost_user.c
> index 79fcb9d19..1bae1fddc 100644
> --- a/lib/librte_vhost/vhost_user.c
> +++ b/lib/librte_vhost/vhost_user.c
> @@ -192,7 +192,9 @@ vhost_backend_cleanup(struct virtio_net *dev)
>  	}
> 
>  	rte_free(dev->guest_pages);
> +	rte_free(dev->cached_guest_pages);
>  	dev->guest_pages = NULL;
> +	dev->cached_guest_pages = NULL;
> 
>  	if (dev->log_addr) {
>  		munmap((void *)(uintptr_t)dev->log_addr, dev->log_size);
> @@ -898,7 +900,7 @@ add_one_guest_page(struct virtio_net *dev,
> uint64_t guest_phys_addr,
>  		   uint64_t host_phys_addr, uint64_t size)
>  {
>  	struct guest_page *page, *last_page;
> -	struct guest_page *old_pages;
> +	struct guest_page *old_pages, *old_cached_pages;
> 
>  	if (dev->nr_guest_pages == dev->max_guest_pages) {
>  		dev->max_guest_pages *= 2;
> @@ -906,9 +908,19 @@ add_one_guest_page(struct virtio_net *dev,
> uint64_t guest_phys_addr,
>  		dev->guest_pages = rte_realloc(dev->guest_pages,
>  					dev->max_guest_pages *
> sizeof(*page),
>  					RTE_CACHE_LINE_SIZE);
> -		if (dev->guest_pages == NULL) {
> +		old_cached_pages = dev->cached_guest_pages;
> +		dev->cached_guest_pages = rte_realloc(dev-
> >cached_guest_pages,
> +						dev->max_guest_pages *
> +						sizeof(*page),
> +						RTE_CACHE_LINE_SIZE);
> +		dev->nr_cached_guest_pages = 0;
> +		if (dev->guest_pages == NULL ||
> +				dev->cached_guest_pages == NULL) {
>  			VHOST_LOG_CONFIG(ERR, "cannot realloc
> guest_pages\n");
>  			rte_free(old_pages);
> +			rte_free(old_cached_pages);
> +			dev->guest_pages = NULL;
> +			dev->cached_guest_pages = NULL;
>  			return -1;
>  		}
>  	}
> @@ -1078,6 +1090,20 @@ vhost_user_set_mem_table(struct virtio_net
> **pdev, struct VhostUserMsg *msg,
>  		}
>  	}
> 
> +	if (dev->cached_guest_pages == NULL) {
> +		dev->cached_guest_pages = rte_zmalloc(NULL,
> +						dev->max_guest_pages *
> +						sizeof(struct guest_page),
> +						RTE_CACHE_LINE_SIZE);
> +		if (dev->cached_guest_pages == NULL) {
> +			VHOST_LOG_CONFIG(ERR,
> +				"(%d) failed to allocate memory "
> +				"for dev->cached_guest_pages\n",
> +				dev->vid);
> +			return RTE_VHOST_MSG_RESULT_ERR;
> +		}
> +	}
> +
>  	dev->mem = rte_zmalloc("vhost-mem-table", sizeof(struct
> rte_vhost_memory) +
>  		sizeof(struct rte_vhost_mem_region) * memory->nregions,
> 0);
>  	if (dev->mem == NULL) {
> --
> 2.17.1