diff options
Diffstat (limited to 'hw/vfio')
| -rw-r--r-- | hw/vfio/Makefile.objs | 1 | ||||
| -rw-r--r-- | hw/vfio/common.c | 170 | ||||
| -rw-r--r-- | hw/vfio/spapr.c | 210 | ||||
| -rw-r--r-- | hw/vfio/trace-events | 8 |
4 files changed, 359 insertions, 30 deletions
diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs index ceddbb8f99..c25e32b029 100644 --- a/hw/vfio/Makefile.objs +++ b/hw/vfio/Makefile.objs @@ -4,4 +4,5 @@ obj-$(CONFIG_PCI) += pci.o pci-quirks.o obj-$(CONFIG_SOFTMMU) += platform.o obj-$(CONFIG_SOFTMMU) += calxeda-xgmac.o obj-$(CONFIG_SOFTMMU) += amd-xgbe.o +obj-$(CONFIG_SOFTMMU) += spapr.o endif diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 7be638e0e3..f3c0522e7e 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -28,6 +28,7 @@ #include "exec/memory.h" #include "hw/hw.h" #include "qemu/error-report.h" +#include "qemu/range.h" #include "sysemu/kvm.h" #ifdef CONFIG_KVM #include "linux/kvm.h" @@ -241,6 +242,44 @@ static int vfio_dma_map(VFIOContainer *container, hwaddr iova, return -errno; } +static void vfio_host_win_add(VFIOContainer *container, + hwaddr min_iova, hwaddr max_iova, + uint64_t iova_pgsizes) +{ + VFIOHostDMAWindow *hostwin; + + QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { + if (ranges_overlap(hostwin->min_iova, + hostwin->max_iova - hostwin->min_iova + 1, + min_iova, + max_iova - min_iova + 1)) { + hw_error("%s: Overlapped IOMMU are not enabled", __func__); + } + } + + hostwin = g_malloc0(sizeof(*hostwin)); + + hostwin->min_iova = min_iova; + hostwin->max_iova = max_iova; + hostwin->iova_pgsizes = iova_pgsizes; + QLIST_INSERT_HEAD(&container->hostwin_list, hostwin, hostwin_next); +} + +static int vfio_host_win_del(VFIOContainer *container, hwaddr min_iova, + hwaddr max_iova) +{ + VFIOHostDMAWindow *hostwin; + + QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { + if (hostwin->min_iova == min_iova && hostwin->max_iova == max_iova) { + QLIST_REMOVE(hostwin, hostwin_next); + return 0; + } + } + + return -1; +} + static bool vfio_listener_skipped_section(MemoryRegionSection *section) { return (!memory_region_is_ram(section->mr) && @@ -329,6 +368,8 @@ static void vfio_listener_region_add(MemoryListener *listener, Int128 llend, llsize; void *vaddr; int ret; + VFIOHostDMAWindow *hostwin; + bool hostwin_found; if (vfio_listener_skipped_section(section)) { trace_vfio_listener_region_add_skip( @@ -354,7 +395,40 @@ static void vfio_listener_region_add(MemoryListener *listener, } end = int128_get64(int128_sub(llend, int128_one())); - if ((iova < container->min_iova) || (end > container->max_iova)) { + if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { + VFIOHostDMAWindow *hostwin; + hwaddr pgsize = 0; + + /* For now intersections are not allowed, we may relax this later */ + QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { + if (ranges_overlap(hostwin->min_iova, + hostwin->max_iova - hostwin->min_iova + 1, + section->offset_within_address_space, + int128_get64(section->size))) { + ret = -1; + goto fail; + } + } + + ret = vfio_spapr_create_window(container, section, &pgsize); + if (ret) { + goto fail; + } + + vfio_host_win_add(container, section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1, pgsize); + } + + hostwin_found = false; + QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { + if (hostwin->min_iova <= iova && end <= hostwin->max_iova) { + hostwin_found = true; + break; + } + } + + if (!hostwin_found) { error_report("vfio: IOMMU container %p can't map guest IOVA region" " 0x%"HWADDR_PRIx"..0x%"HWADDR_PRIx, container, iova, end); @@ -369,10 +443,6 @@ static void vfio_listener_region_add(MemoryListener *listener, trace_vfio_listener_region_add_iommu(iova, end); /* - * FIXME: We should do some checking to see if the - * capabilities of the host VFIO IOMMU are adequate to model - * the guest IOMMU - * * FIXME: For VFIO iommu types which have KVM acceleration to * avoid bouncing all map/unmaps through qemu this way, this * would be the right place to wire that up (tell the KVM @@ -493,6 +563,18 @@ static void vfio_listener_region_del(MemoryListener *listener, "0x%"HWADDR_PRIx") = %d (%m)", container, iova, int128_get64(llsize), ret); } + + if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { + vfio_spapr_remove_window(container, + section->offset_within_address_space); + if (vfio_host_win_del(container, + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(section->size) - 1) < 0) { + hw_error("%s: Cannot delete missing window at %"HWADDR_PRIx, + __func__, section->offset_within_address_space); + } + } } static const MemoryListener vfio_memory_listener = { @@ -503,6 +585,9 @@ static const MemoryListener vfio_memory_listener = { static void vfio_listener_release(VFIOContainer *container) { memory_listener_unregister(&container->listener); + if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { + memory_listener_unregister(&container->prereg_listener); + } } static struct vfio_info_cap_header * @@ -861,8 +946,8 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) goto free_container_exit; } - ret = ioctl(fd, VFIO_SET_IOMMU, - v2 ? VFIO_TYPE1v2_IOMMU : VFIO_TYPE1_IOMMU); + container->iommu_type = v2 ? VFIO_TYPE1v2_IOMMU : VFIO_TYPE1_IOMMU; + ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type); if (ret) { error_report("vfio: failed to set iommu for container: %m"); ret = -errno; @@ -876,19 +961,18 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) * existing Type1 IOMMUs generally support any IOVA we're * going to actually try in practice. */ - container->min_iova = 0; - container->max_iova = (hwaddr)-1; - - /* Assume just 4K IOVA page size */ - container->iova_pgsizes = 0x1000; info.argsz = sizeof(info); ret = ioctl(fd, VFIO_IOMMU_GET_INFO, &info); /* Ignore errors */ - if ((ret == 0) && (info.flags & VFIO_IOMMU_INFO_PGSIZES)) { - container->iova_pgsizes = info.iova_pgsizes; + if (ret || !(info.flags & VFIO_IOMMU_INFO_PGSIZES)) { + /* Assume 4k IOVA page size */ + info.iova_pgsizes = 4096; } - } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU)) { + vfio_host_win_add(container, 0, (hwaddr)-1, info.iova_pgsizes); + } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU) || + ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU)) { struct vfio_iommu_spapr_tce_info info; + bool v2 = !!ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_v2_IOMMU); ret = ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &fd); if (ret) { @@ -896,7 +980,9 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) ret = -errno; goto free_container_exit; } - ret = ioctl(fd, VFIO_SET_IOMMU, VFIO_SPAPR_TCE_IOMMU); + container->iommu_type = + v2 ? VFIO_SPAPR_TCE_v2_IOMMU : VFIO_SPAPR_TCE_IOMMU; + ret = ioctl(fd, VFIO_SET_IOMMU, container->iommu_type); if (ret) { error_report("vfio: failed to set iommu for container: %m"); ret = -errno; @@ -908,30 +994,54 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) * when container fd is closed so we do not call it explicitly * in this file. */ - ret = ioctl(fd, VFIO_IOMMU_ENABLE); - if (ret) { - error_report("vfio: failed to enable container: %m"); - ret = -errno; - goto free_container_exit; + if (!v2) { + ret = ioctl(fd, VFIO_IOMMU_ENABLE); + if (ret) { + error_report("vfio: failed to enable container: %m"); + ret = -errno; + goto free_container_exit; + } + } else { + container->prereg_listener = vfio_prereg_listener; + + memory_listener_register(&container->prereg_listener, + &address_space_memory); + if (container->error) { + memory_listener_unregister(&container->prereg_listener); + error_report("vfio: RAM memory listener initialization failed for container"); + goto free_container_exit; + } } - /* - * This only considers the host IOMMU's 32-bit window. At - * some point we need to add support for the optional 64-bit - * window and dynamic windows - */ info.argsz = sizeof(info); ret = ioctl(fd, VFIO_IOMMU_SPAPR_TCE_GET_INFO, &info); if (ret) { error_report("vfio: VFIO_IOMMU_SPAPR_TCE_GET_INFO failed: %m"); ret = -errno; + if (v2) { + memory_listener_unregister(&container->prereg_listener); + } goto free_container_exit; } - container->min_iova = info.dma32_window_start; - container->max_iova = container->min_iova + info.dma32_window_size - 1; - /* Assume just 4K IOVA pages for now */ - container->iova_pgsizes = 0x1000; + if (v2) { + /* + * There is a default window in just created container. + * To make region_add/del simpler, we better remove this + * window now and let those iommu_listener callbacks + * create/remove them when needed. + */ + ret = vfio_spapr_remove_window(container, info.dma32_window_start); + if (ret) { + goto free_container_exit; + } + } else { + /* The default table uses 4K pages */ + vfio_host_win_add(container, info.dma32_window_start, + info.dma32_window_start + + info.dma32_window_size - 1, + 0x1000); + } } else { error_report("vfio: No available IOMMU models"); ret = -EINVAL; diff --git a/hw/vfio/spapr.c b/hw/vfio/spapr.c new file mode 100644 index 0000000000..0af342332c --- /dev/null +++ b/hw/vfio/spapr.c @@ -0,0 +1,210 @@ +/* + * DMA memory preregistration + * + * Authors: + * Alexey Kardashevskiy <aik@ozlabs.ru> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "cpu.h" +#include <sys/ioctl.h> +#include <linux/vfio.h> + +#include "hw/vfio/vfio-common.h" +#include "hw/hw.h" +#include "qemu/error-report.h" +#include "trace.h" + +static bool vfio_prereg_listener_skipped_section(MemoryRegionSection *section) +{ + if (memory_region_is_iommu(section->mr)) { + hw_error("Cannot possibly preregister IOMMU memory"); + } + + return !memory_region_is_ram(section->mr) || + memory_region_is_skip_dump(section->mr); +} + +static void *vfio_prereg_gpa_to_vaddr(MemoryRegionSection *section, hwaddr gpa) +{ + return memory_region_get_ram_ptr(section->mr) + + section->offset_within_region + + (gpa - section->offset_within_address_space); +} + +static void vfio_prereg_listener_region_add(MemoryListener *listener, + MemoryRegionSection *section) +{ + VFIOContainer *container = container_of(listener, VFIOContainer, + prereg_listener); + const hwaddr gpa = section->offset_within_address_space; + hwaddr end; + int ret; + hwaddr page_mask = qemu_real_host_page_mask; + struct vfio_iommu_spapr_register_memory reg = { + .argsz = sizeof(reg), + .flags = 0, + }; + + if (vfio_prereg_listener_skipped_section(section)) { + trace_vfio_prereg_listener_region_add_skip( + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(int128_sub(section->size, int128_one()))); + return; + } + + if (unlikely((section->offset_within_address_space & ~page_mask) || + (section->offset_within_region & ~page_mask) || + (int128_get64(section->size) & ~page_mask))) { + error_report("%s received unaligned region", __func__); + return; + } + + end = section->offset_within_address_space + int128_get64(section->size); + if (gpa >= end) { + return; + } + + memory_region_ref(section->mr); + + reg.vaddr = (uintptr_t) vfio_prereg_gpa_to_vaddr(section, gpa); + reg.size = end - gpa; + + ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_REGISTER_MEMORY, ®); + trace_vfio_prereg_register(reg.vaddr, reg.size, ret ? -errno : 0); + if (ret) { + /* + * On the initfn path, store the first error in the container so we + * can gracefully fail. Runtime, there's not much we can do other + * than throw a hardware error. + */ + if (!container->initialized) { + if (!container->error) { + container->error = ret; + } + } else { + hw_error("vfio: Memory registering failed, unable to continue"); + } + } +} + +static void vfio_prereg_listener_region_del(MemoryListener *listener, + MemoryRegionSection *section) +{ + VFIOContainer *container = container_of(listener, VFIOContainer, + prereg_listener); + const hwaddr gpa = section->offset_within_address_space; + hwaddr end; + int ret; + hwaddr page_mask = qemu_real_host_page_mask; + struct vfio_iommu_spapr_register_memory reg = { + .argsz = sizeof(reg), + .flags = 0, + }; + + if (vfio_prereg_listener_skipped_section(section)) { + trace_vfio_prereg_listener_region_del_skip( + section->offset_within_address_space, + section->offset_within_address_space + + int128_get64(int128_sub(section->size, int128_one()))); + return; + } + + if (unlikely((section->offset_within_address_space & ~page_mask) || + (section->offset_within_region & ~page_mask) || + (int128_get64(section->size) & ~page_mask))) { + error_report("%s received unaligned region", __func__); + return; + } + + end = section->offset_within_address_space + int128_get64(section->size); + if (gpa >= end) { + return; + } + + reg.vaddr = (uintptr_t) vfio_prereg_gpa_to_vaddr(section, gpa); + reg.size = end - gpa; + + ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_UNREGISTER_MEMORY, ®); + trace_vfio_prereg_unregister(reg.vaddr, reg.size, ret ? -errno : 0); +} + +const MemoryListener vfio_prereg_listener = { + .region_add = vfio_prereg_listener_region_add, + .region_del = vfio_prereg_listener_region_del, +}; + +int vfio_spapr_create_window(VFIOContainer *container, + MemoryRegionSection *section, + hwaddr *pgsize) +{ + int ret; + unsigned pagesize = memory_region_iommu_get_min_page_size(section->mr); + unsigned entries, pages; + struct vfio_iommu_spapr_tce_create create = { .argsz = sizeof(create) }; + + /* + * FIXME: For VFIO iommu types which have KVM acceleration to + * avoid bouncing all map/unmaps through qemu this way, this + * would be the right place to wire that up (tell the KVM + * device emulation the VFIO iommu handles to use). + */ + 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 + */ + entries = create.window_size >> create.page_shift; + pages = MAX((entries * sizeof(uint64_t)) / getpagesize(), 1); + pages = MAX(pow2ceil(pages) - 1, 1); /* Round up */ + create.levels = ctz64(pages) / 6 + 1; + + ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create); + if (ret) { + error_report("Failed to create a window, ret = %d (%m)", ret); + return -errno; + } + + if (create.start_addr != section->offset_within_address_space) { + vfio_spapr_remove_window(container, create.start_addr); + + error_report("Host doesn't support DMA window at %"HWADDR_PRIx", must be %"PRIx64, + section->offset_within_address_space, + (uint64_t)create.start_addr); + ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_REMOVE, &remove); + return -EINVAL; + } + trace_vfio_spapr_create_window(create.page_shift, + create.window_size, + create.start_addr); + *pgsize = pagesize; + + return 0; +} + +int vfio_spapr_remove_window(VFIOContainer *container, + hwaddr offset_within_address_space) +{ + struct vfio_iommu_spapr_tce_remove remove = { + .argsz = sizeof(remove), + .start_addr = offset_within_address_space, + }; + int ret; + + ret = ioctl(container->fd, VFIO_IOMMU_SPAPR_TCE_REMOVE, &remove); + if (ret) { + error_report("Failed to remove window at %"PRIx64, + (uint64_t)remove.start_addr); + return -errno; + } + + trace_vfio_spapr_remove_window(offset_within_address_space); + + return 0; +} diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index a768fb54ec..4bb7690c46 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -115,3 +115,11 @@ vfio_platform_populate_interrupts(int pin, int count, int flags) "- IRQ index %d vfio_intp_interrupt_set_pending(int index) "irq %d is set PENDING" vfio_platform_start_level_irqfd_injection(int index, int fd, int resamplefd) "IRQ index=%d, fd = %d, resamplefd = %d" vfio_platform_start_edge_irqfd_injection(int index, int fd) "IRQ index=%d, fd = %d" + +# hw/vfio/spapr.c +vfio_prereg_listener_region_add_skip(uint64_t start, uint64_t end) "%"PRIx64" - %"PRIx64 +vfio_prereg_listener_region_del_skip(uint64_t start, uint64_t end) "%"PRIx64" - %"PRIx64 +vfio_prereg_register(uint64_t va, uint64_t size, int ret) "va=%"PRIx64" size=%"PRIx64" ret=%d" +vfio_prereg_unregister(uint64_t va, uint64_t size, int ret) "va=%"PRIx64" size=%"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_remove_window(uint64_t off) "offset=%"PRIx64 |