diff options
Diffstat (limited to 'hw/vfio')
| -rw-r--r-- | hw/vfio/common.c | 2 | ||||
| -rw-r--r-- | hw/vfio/spapr.c | 49 | ||||
| -rw-r--r-- | hw/vfio/trace-events | 2 |
3 files changed, 38 insertions, 15 deletions
diff --git a/hw/vfio/common.c b/hw/vfio/common.c index df2b4721bf..4374cc6176 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -729,7 +729,7 @@ static void vfio_listener_release(VFIOContainer *container) } } -static struct vfio_info_cap_header * +struct vfio_info_cap_header * vfio_get_region_info_cap(struct vfio_region_info *info, uint16_t id) { struct vfio_info_cap_header *hdr; diff --git a/hw/vfio/spapr.c b/hw/vfio/spapr.c index becf71a3fc..57fe758e54 100644 --- a/hw/vfio/spapr.c +++ b/hw/vfio/spapr.c @@ -143,19 +143,19 @@ int vfio_spapr_create_window(VFIOContainer *container, MemoryRegionSection *section, hwaddr *pgsize) { - int ret; + int ret = 0; IOMMUMemoryRegion *iommu_mr = IOMMU_MEMORY_REGION(section->mr); uint64_t pagesize = memory_region_iommu_get_min_page_size(iommu_mr); - unsigned entries, pages; + unsigned entries, bits_total, bits_per_level, max_levels; struct vfio_iommu_spapr_tce_create create = { .argsz = sizeof(create) }; - long systempagesize = qemu_getrampagesize(); + long rampagesize = qemu_getrampagesize(); /* * The host might not support the guest supported IOMMU page size, * so we will use smaller physical IOMMU pages to back them. */ - if (pagesize > systempagesize) { - pagesize = systempagesize; + if (pagesize > rampagesize) { + pagesize = rampagesize; } pagesize = 1ULL << (63 - clz64(container->pgsizes & (pagesize | (pagesize - 1)))); @@ -176,16 +176,38 @@ int vfio_spapr_create_window(VFIOContainer *container, create.window_size = int128_get64(section->size); create.page_shift = ctz64(pagesize); /* - * SPAPR host supports multilevel TCE tables, there is some - * heuristic to decide how many levels we want for our table: - * 0..64 = 1; 65..4096 = 2; 4097..262144 = 3; 262145.. = 4 + * SPAPR host supports multilevel TCE tables. We try to guess optimal + * levels number and if this fails (for example due to the host memory + * fragmentation), we increase levels. The DMA address structure is: + * rrrrrrrr rxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx xxxxxxxx iiiiiiii + * where: + * r = reserved (bits >= 55 are reserved in the existing hardware) + * i = IOMMU page offset (64K in this example) + * x = bits to index a TCE which can be split to equal chunks to index + * within the level. + * The aim is to split "x" to smaller possible number of levels. */ entries = create.window_size >> create.page_shift; - pages = MAX((entries * sizeof(uint64_t)) / getpagesize(), 1); - pages = MAX(pow2ceil(pages), 1); /* Round up */ - create.levels = ctz64(pages) / 6 + 1; - - ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create); + /* bits_total is number of "x" needed */ + bits_total = ctz64(entries * sizeof(uint64_t)); + /* + * bits_per_level is a safe guess of how much we can allocate per level: + * 8 is the current minimum for CONFIG_FORCE_MAX_ZONEORDER and MAX_ORDER + * is usually bigger than that. + * Below we look at getpagesize() as TCEs are allocated from system pages. + */ + bits_per_level = ctz64(getpagesize()) + 8; + create.levels = bits_total / bits_per_level; + if (bits_total % bits_per_level) { + ++create.levels; + } + max_levels = (64 - create.page_shift) / ctz64(getpagesize()); + for ( ; create.levels <= max_levels; ++create.levels) { + ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create); + if (!ret) { + break; + } + } if (ret) { error_report("Failed to create a window, ret = %d (%m)", ret); return -errno; @@ -200,6 +222,7 @@ int vfio_spapr_create_window(VFIOContainer *container, return -EINVAL; } trace_vfio_spapr_create_window(create.page_shift, + create.levels, create.window_size, create.start_addr); *pgsize = pagesize; diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index ed2f333ad7..cf1e886818 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -129,6 +129,6 @@ vfio_prereg_listener_region_add_skip(uint64_t start, uint64_t end) "0x%"PRIx64" vfio_prereg_listener_region_del_skip(uint64_t start, uint64_t end) "0x%"PRIx64" - 0x%"PRIx64 vfio_prereg_register(uint64_t va, uint64_t size, int ret) "va=0x%"PRIx64" size=0x%"PRIx64" ret=%d" vfio_prereg_unregister(uint64_t va, uint64_t size, int ret) "va=0x%"PRIx64" size=0x%"PRIx64" ret=%d" -vfio_spapr_create_window(int ps, uint64_t ws, uint64_t off) "pageshift=0x%x winsize=0x%"PRIx64" offset=0x%"PRIx64 +vfio_spapr_create_window(int ps, unsigned int levels, uint64_t ws, uint64_t off) "pageshift=0x%x levels=%u winsize=0x%"PRIx64" offset=0x%"PRIx64 vfio_spapr_remove_window(uint64_t off) "offset=0x%"PRIx64 vfio_spapr_group_attach(int groupfd, int tablefd) "Attached groupfd %d to liobn fd %d" |