Re: [dpdk-dev] [PATCH v3 1/1] vfio: modify spapr iommu support to use static window sizing

["Burakov, Anatoly" <anatoly.burakov@intel.com>]

On 10-Aug-20 10:07 PM, David Christensen wrote:
> The SPAPR IOMMU requires that a DMA window size be defined before memory
> can be mapped for DMA. Current code dynamically modifies the DMA window
> size in response to every new memory allocation which is potentially
> dangerous because all existing mappings need to be unmapped/remapped in
> order to resize the DMA window, leaving hardware holding IOVA addresses
> that are temporarily unmapped.  The new SPAPR code statically assigns
> the DMA window size on first use, using the largest physical memory
> memory address when IOVA=PA and the highest existing memseg virtual
> address when IOVA=VA.
> 
> Signed-off-by: David Christensen <drc@linux.vnet.ibm.com>
> ---

<snip>

> +struct spapr_size_walk_param {
> +	uint64_t max_va;
> +	uint64_t page_sz;
> +	int external;
> +};
> +
> +/*
> + * In order to set the DMA window size required for the SPAPR IOMMU
> + * we need to walk the existing virtual memory allocations as well as
> + * find the hugepage size used.
> + */
>   static int
> -vfio_spapr_unmap_walk(const struct rte_memseg_list *msl,
> -		const struct rte_memseg *ms, void *arg)
> +vfio_spapr_size_walk(const struct rte_memseg_list *msl, void *arg)
>   {
> -	int *vfio_container_fd = arg;
> +	struct spapr_size_walk_param *param = arg;
> +	uint64_t max = (uint64_t) msl->base_va + (uint64_t) msl->len;
>   
> -	/* skip external memory that isn't a heap */
> -	if (msl->external && !msl->heap)
> -		return 0;
> +	if (msl->external) {
> +		param->external++;
> +		if (!msl->heap)
> +			return 0;
> +	}

It would be nice to have some comments in the code explaining what we're 
skipping and why.

Also, seems that you're using param->external as bool? This is a 
non-public API so using stdbool is not an issue here, perhaps replace it 
with bool param->has_external?

>   
> -	/* skip any segments with invalid IOVA addresses */
> -	if (ms->iova == RTE_BAD_IOVA)
> -		return 0;
> +	if (max > param->max_va) {
> +		param->page_sz = msl->page_sz;
> +		param->max_va = max;
> +	}
>   
> -	return vfio_spapr_dma_do_map(*vfio_container_fd, ms->addr_64, ms->iova,
> -			ms->len, 0);
> +	return 0;
>   }
>   
> -struct spapr_walk_param {
> -	uint64_t window_size;
> -	uint64_t hugepage_sz;
> -};
> -
> +/*
> + * The SPAPRv2 IOMMU supports 2 DMA windows with starting
> + * address at 0 or 1<<59.  By default, a DMA window is set
> + * at address 0, 2GB long, with a 4KB page.  For DPDK we
> + * must remove the default window and setup a new DMA window
> + * based on the hugepage size and memory requirements of
> + * the application before we can map memory for DMA.
> + */
>   static int
> -vfio_spapr_window_size_walk(const struct rte_memseg_list *msl,
> -		const struct rte_memseg *ms, void *arg)
> +spapr_dma_win_size(void)
>   {
> -	struct spapr_walk_param *param = arg;
> -	uint64_t max = ms->iova + ms->len;
> +	struct spapr_size_walk_param param;
>   
> -	/* skip external memory that isn't a heap */
> -	if (msl->external && !msl->heap)
> +	/* only create DMA window once */
> +	if (spapr_dma_win_len > 0)
>   		return 0;
>   
> -	/* skip any segments with invalid IOVA addresses */
> -	if (ms->iova == RTE_BAD_IOVA)
> -		return 0;
> +	/* walk the memseg list to find the page size/max VA address */
> +	memset(&param, 0, sizeof(param));
> +	if (rte_memseg_list_walk(vfio_spapr_size_walk, &param) < 0) {
> +		RTE_LOG(ERR, EAL, "Failed to walk memseg list for DMA "
> +			"window size\n");
> +		return -1;
> +	}
> +
> +	/* We can't be sure if DMA window covers external memory */
> +	if (param.external > 0)
> +		RTE_LOG(WARNING, EAL, "Detected external memory which may "
> +			"not be managed by the IOMMU\n");
> +
> +	/* find the maximum IOVA address for setting the DMA window size */
> +	if (rte_eal_iova_mode() == RTE_IOVA_PA) {
> +		static const char proc_iomem[] = "/proc/iomem";
> +		static const char str_sysram[] = "System RAM";
> +		uint64_t start, end, max = 0;
> +		char *line = NULL;
> +		char *dash, *space;
> +		size_t line_len;
> +
> +		/*
> +		 * Example "System RAM" in /proc/iomem:
> +		 * 00000000-1fffffffff : System RAM
> +		 * 200000000000-201fffffffff : System RAM
> +		 */
> +		FILE *fd = fopen(proc_iomem, "r");
> +		if (fd == NULL) {
> +			RTE_LOG(ERR, EAL, "Cannot open %s\n", proc_iomem);
> +			return -1;
> +		}
> +		/* Scan /proc/iomem for the highest PA in the system */
> +		while (getline(&line, &line_len, fd) != -1) {
> +			if (strstr(line, str_sysram) == NULL)
> +				continue;
> +
> +			space = strstr(line, " ");
> +			dash = strstr(line, "-");
> +
> +			/* Validate the format of the memory string */
> +			if (space == NULL || dash == NULL || space < dash) {
> +				RTE_LOG(ERR, EAL, "Can't parse line \"%s\" in "
> +					"file %s\n", line, proc_iomem);
> +				continue;
> +			}
> +
> +			start = strtoull(line, NULL, 16);
> +			end   = strtoull(dash + 1, NULL, 16);
> +			RTE_LOG(DEBUG, EAL, "Found system RAM from 0x%"
> +				PRIx64 " to 0x%" PRIx64 "\n", start, end);
> +			if (end > max)
> +				max = end;
> +		}
> +		free(line);
> +		fclose(fd);

I would've put all of this file reading business into a separate 
function, as otherwise it's a bit hard to follow the mix of file ops and 
using the results. Something like

value = get_value_from_iomem();
if (value > ...)
...

is much easier on the eyes :)

>   
> -	if (max > param->window_size) {
> -		param->hugepage_sz = ms->hugepage_sz;
> -		param->window_size = max;
> +		if (max == 0) {
> +			RTE_LOG(ERR, EAL, "Failed to find valid \"System RAM\" "
> +				"entry in file %s\n", proc_iomem);
> +			return -1;
> +		}
> +
> +		spapr_dma_win_len = rte_align64pow2(max + 1);
> +		RTE_LOG(DEBUG, EAL, "Setting DMA window size to 0x%"
> +			PRIx64 "\n", spapr_dma_win_len);
> +	} else if (rte_eal_iova_mode() == RTE_IOVA_VA) {
> +		RTE_LOG(DEBUG, EAL, "Highest VA address in memseg list is 0x%"
> +			PRIx64 "\n", param.max_va);
> +		spapr_dma_win_len = rte_align64pow2(param.max_va);
> +		RTE_LOG(DEBUG, EAL, "Setting DMA window size to 0x%"
> +			PRIx64 "\n", spapr_dma_win_len);
> +	} else {
> +		RTE_LOG(ERR, EAL, "Unsupported IOVA mode\n");
> +		return -1;
>   	}
>   
> +	spapr_dma_win_page_sz = param.page_sz;
> +	rte_mem_set_dma_mask(__builtin_ctzll(spapr_dma_win_len));
>   	return 0;
>   }
>   
>   static int
> -vfio_spapr_create_new_dma_window(int vfio_container_fd,
> -		struct vfio_iommu_spapr_tce_create *create) {
> +vfio_spapr_create_dma_window(int vfio_container_fd)
> +{
> +	struct vfio_iommu_spapr_tce_create create = {
> +		.argsz = sizeof(create), };
>   	struct vfio_iommu_spapr_tce_remove remove = {
> -		.argsz = sizeof(remove),
> -	};
> +		.argsz = sizeof(remove), };
>   	struct vfio_iommu_spapr_tce_info info = {
> -		.argsz = sizeof(info),
> -	};
> +		.argsz = sizeof(info), };
>   	int ret;
>   
> -	/* query spapr iommu info */
> +	ret = spapr_dma_win_size();
> +	if (ret < 0)
> +		return ret;
> +
>   	ret = ioctl(vfio_container_fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info);
>   	if (ret) {
> -		RTE_LOG(ERR, EAL, "  cannot get iommu info, "
> -				"error %i (%s)\n", errno, strerror(errno));

Here and in other similar places, no need to split strings into multiline.

Overall, since these changes are confined to PPC64 i can't really test 
these, but with the above changes:

Reviewed-by: Anatoly Burakov <anatoly.burakov@intel.com>

-- 
Thanks,
Anatoly