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..46381e6242 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -503,6 +503,9 @@ 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 +864,8 @@ 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; @@ -887,8 +890,10 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) if ((ret == 0) && (info.flags & VFIO_IOMMU_INFO_PGSIZES)) { container->iova_pgsizes = info.iova_pgsizes; } - } else if (ioctl(fd, VFIO_CHECK_EXTENSION, VFIO_SPAPR_TCE_IOMMU)) { + } 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 +901,9 @@ 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; @@ -908,11 +915,23 @@ 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; + } } /* @@ -925,6 +944,9 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as) 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; diff --git a/hw/vfio/spapr.c b/hw/vfio/spapr.c new file mode 100644 index 0000000000..7d64443b7f --- /dev/null +++ b/hw/vfio/spapr.c @@ -0,0 +1,139 @@ +/* + * DMA memory preregistration + * + * Authors: + * Alexey Kardashevskiy + * + * 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 +#include + +#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, +}; diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index a768fb54ec..0b02a3bd54 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -115,3 +115,9 @@ 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" diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 0610377789..405c3b29d6 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -73,6 +73,8 @@ typedef struct VFIOContainer { VFIOAddressSpace *space; int fd; /* /dev/vfio/vfio, empowered by the attached groups */ MemoryListener listener; + MemoryListener prereg_listener; + unsigned iommu_type; int error; bool initialized; /* @@ -158,4 +160,6 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index, int vfio_get_dev_region_info(VFIODevice *vbasedev, uint32_t type, uint32_t subtype, struct vfio_region_info **info); #endif +extern const MemoryListener vfio_prereg_listener; + #endif /* !HW_VFIO_VFIO_COMMON_H */