[dpdk-dev] [PATCH v4 1/1] vfio: modify spapr iommu support to use static window sizing

[Burakov, Anatoly]

On 15-Oct-20 6:23 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 at linux.vnet.ibm.com>
> ---

These changes are almost exclusively contained to PPC64 code, so with 
below changes,

Acked-by: Anatoly Burakov <anatoly.burakov at intel.com>

> +static uint64_t
> +get_highest_mem_addr(struct spapr_size_walk_param *param)
> +{
> +	/* 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);
> +
> +		if (max == 0) {
> +			RTE_LOG(ERR, EAL, "Failed to find valid \"System RAM\" "
> +				"entry in file %s\n", proc_iomem);
> +			return -1;
> +		}
> +
> +		return rte_align64pow2(max + 1);
> +	} 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);
> +		return rte_align64pow2(param->max_va);
> +	}
> +
> +	RTE_LOG(ERR, EAL, "Unsupported IOVA mode\n");
> +	return 0;

You're returning a uint64_t here, while also returning -1 in some of the 
error cases above, but not here. How about making the address an output 
parameter, and return 0 on success and -1 on error? It makes the code a 
bit messier at the call site, but would probably make more sense than 
returning 0 or -1 depending on which error condition you've hit.

Also, because of this, there's a bug below where you check for return 
value of 0, but not -1.

> +}
> +
> +
> +/*
> + * 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;
> -
> -	/* skip external memory that isn't a heap */
> -	if (msl->external && !msl->heap)
> -		return 0;
> +	struct spapr_size_walk_param param;
>   
> -	/* skip any segments with invalid IOVA addresses */
> -	if (ms->iova == RTE_BAD_IOVA)
> +	/* only create DMA window once */
> +	if (spapr_dma_win_len > 0)
>   		return 0;
>   
> -	if (max > param->window_size) {
> -		param->hugepage_sz = ms->hugepage_sz;
> -		param->window_size = max;
> +	/* 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.is_user_managed)
> +		RTE_LOG(WARNING, EAL, "Detected user managed external memory which may not be managed by the IOMMU\n");
> +
> +	spapr_dma_win_len = get_highest_mem_addr(&param);
> +	if (spapr_dma_win_len == 0)
> +		return -1;

This error check doesn't catch all errors, as indicated above.

> +	RTE_LOG(DEBUG, EAL, "Setting DMA window size to 0x%" PRIx64 "\n",
> +		spapr_dma_win_len);
> +	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));
> +		RTE_LOG(ERR, EAL, "  can't get iommu info, error %i (%s)\n",
> +			errno, strerror(errno));
>   		return -1;
>   	}
>   
> -	/* remove default DMA of 32 bit window */
> +	/* remove default DMA window */
>   	remove.start_addr = info.dma32_window_start;
>   	ret = ioctl(vfio_container_fd, VFIO_IOMMU_SPAPR_TCE_REMOVE, &remove);

If you're never recreating a window, does it need to be removed? Or is 
this some kind of default window that is always present?

> -	if (ret) {
> -		RTE_LOG(ERR, EAL, "  cannot remove default DMA window, "
> -				"error %i (%s)\n", errno, strerror(errno));
> +	if (ret)
>   		return -1;
> -	}
>   
> -	/* create new DMA window */
> -	ret = ioctl(vfio_container_fd, VFIO_IOMMU_SPAPR_TCE_CREATE, create);
> +	/* create a new DMA window (start address is not selectable) */
> +	create.window_size = spapr_dma_win_len;
> +	create.page_shift  = __builtin_ctzll(spapr_dma_win_page_sz);
> +	create.levels = 1;
> +	ret = ioctl(vfio_container_fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create);
>   	if (ret) {
> -#ifdef VFIO_IOMMU_SPAPR_INFO_DDW
> -		/* try possible page_shift and levels for workaround */
> +		/* if at first we don't succeed, try more levels */
>   		uint32_t levels;
>   
> -		for (levels = create->levels + 1;
> +		for (levels = create.levels + 1;
>   			ret && levels <= info.ddw.levels; levels++) {
> -			create->levels = levels;
> +			create.levels = levels;
>   			ret = ioctl(vfio_container_fd,
> -				VFIO_IOMMU_SPAPR_TCE_CREATE, create);
> -		}
> -#endif
> -		if (ret) {
> -			RTE_LOG(ERR, EAL, "  cannot create new DMA window, "
> -					"error %i (%s)\n", errno, strerror(errno));
> -			return -1;
> +				VFIO_IOMMU_SPAPR_TCE_CREATE, &create);
>   		}
>   	}
> -
> -	if (create->start_addr != 0) {
> -		RTE_LOG(ERR, EAL, "  DMA window start address != 0\n");
> +	if (ret) {
> +		RTE_LOG(ERR, EAL, "  cannot create new DMA window, error %i (%s)\n",
> +			errno, strerror(errno));
> +		RTE_LOG(ERR, EAL, "  consider using a larger hugepage size "
> +			"if supported by the system\n");
>   		return -1;
>   	}
>   
> -	return 0;
> +	/* verify the start address  */
> +	if (create.start_addr != 0) {
> +		RTE_LOG(ERR, EAL, "  received unsupported start address 0x%"
> +			PRIx64 "\n", (uint64_t)create.start_addr);
> +		return -1;
> +	}
> +	return ret;
>   }
>   
>   static int
> -vfio_spapr_dma_mem_map(int vfio_container_fd, uint64_t vaddr, uint64_t iova,
> -		uint64_t len, int do_map)
> +vfio_spapr_dma_mem_map(int vfio_container_fd, uint64_t vaddr,
> +	uint64_t iova, uint64_t len, int do_map)

Nitpick, but this bit after newline should have two indents, not one.

-- 
Thanks,
Anatoly