From 3e2413a6520e5b6d8360395b6b423332abfb3362 Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Tue, 7 Mar 2023 12:54:36 +0000 Subject: vfio/common: Fix error reporting in vfio_get_dirty_bitmap() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Return -errno instead of -1 if VFIO_IOMMU_DIRTY_PAGES ioctl fails in vfio_get_dirty_bitmap(). Signed-off-by: Avihai Horon Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20230307125450.62409-2-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 1 + 1 file changed, 1 insertion(+) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index bab83c0e55..9fc305448f 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -1335,6 +1335,7 @@ static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap); if (ret) { + ret = -errno; error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64 " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova, (uint64_t)range->size, errno); -- cgit v1.2.3 From db9b829b15999b47f3e4f6fbede743b6f8686110 Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Tue, 7 Mar 2023 12:54:37 +0000 Subject: vfio/common: Fix wrong %m usages MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are several places where the %m conversion is used if one of vfio_dma_map(), vfio_dma_unmap() or vfio_get_dirty_bitmap() fail. The %m usage in these places is wrong since %m relies on errno value while the above functions don't report errors via errno. Fix it by using strerror() with the returned value instead. Signed-off-by: Avihai Horon Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20230307125450.62409-3-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 29 ++++++++++++++++------------- 1 file changed, 16 insertions(+), 13 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 9fc305448f..4d26e9cccf 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -703,17 +703,17 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) read_only); if (ret) { error_report("vfio_dma_map(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx", %p) = %d (%m)", + "0x%"HWADDR_PRIx", %p) = %d (%s)", container, iova, - iotlb->addr_mask + 1, vaddr, ret); + iotlb->addr_mask + 1, vaddr, ret, strerror(-ret)); } } else { ret = vfio_dma_unmap(container, iova, iotlb->addr_mask + 1, iotlb); if (ret) { error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx") = %d (%m)", + "0x%"HWADDR_PRIx") = %d (%s)", container, iova, - iotlb->addr_mask + 1, ret); + iotlb->addr_mask + 1, ret, strerror(-ret)); } } out: @@ -1095,8 +1095,9 @@ static void vfio_listener_region_add(MemoryListener *listener, vaddr, section->readonly); if (ret) { error_setg(&err, "vfio_dma_map(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx", %p) = %d (%m)", - container, iova, int128_get64(llsize), vaddr, ret); + "0x%"HWADDR_PRIx", %p) = %d (%s)", + container, iova, int128_get64(llsize), vaddr, ret, + strerror(-ret)); if (memory_region_is_ram_device(section->mr)) { /* Allow unexpected mappings not to be fatal for RAM devices */ error_report_err(err); @@ -1228,16 +1229,18 @@ static void vfio_listener_region_del(MemoryListener *listener, ret = vfio_dma_unmap(container, iova, int128_get64(llsize), NULL); if (ret) { error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx") = %d (%m)", - container, iova, int128_get64(llsize), ret); + "0x%"HWADDR_PRIx") = %d (%s)", + container, iova, int128_get64(llsize), ret, + strerror(-ret)); } iova += int128_get64(llsize); } ret = vfio_dma_unmap(container, iova, int128_get64(llsize), NULL); if (ret) { error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx") = %d (%m)", - container, iova, int128_get64(llsize), ret); + "0x%"HWADDR_PRIx") = %d (%s)", + container, iova, int128_get64(llsize), ret, + strerror(-ret)); } } @@ -1384,9 +1387,9 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) translated_addr); if (ret) { error_report("vfio_iommu_map_dirty_notify(%p, 0x%"HWADDR_PRIx", " - "0x%"HWADDR_PRIx") = %d (%m)", - container, iova, - iotlb->addr_mask + 1, ret); + "0x%"HWADDR_PRIx") = %d (%s)", + container, iova, iotlb->addr_mask + 1, ret, + strerror(-ret)); } } rcu_read_unlock(); -- cgit v1.2.3 From 236e0a45f507f1e4130fce9c8edb615bf5e0b00e Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Tue, 7 Mar 2023 12:54:38 +0000 Subject: vfio/common: Abort migration if dirty log start/stop/sync fails MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If VFIO dirty pages log start/stop/sync fails during migration, migration should be aborted as pages dirtied by VFIO devices might not be reported properly. This is not the case today, where in such scenario only an error is printed. Fix it by aborting migration in the above scenario. Fixes: 758b96b61d5c ("vfio/migrate: Move switch of dirty tracking into vfio_memory_listener") Fixes: b6dd6504e303 ("vfio: Add vfio_listener_log_sync to mark dirty pages") Fixes: 9e7b0442f23a ("vfio: Add ioctl to get dirty pages bitmap during dma unmap") Signed-off-by: Avihai Horon Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20230307125450.62409-4-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 53 +++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 45 insertions(+), 8 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 4d26e9cccf..4c80151313 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -42,6 +42,7 @@ #include "migration/migration.h" #include "migration/misc.h" #include "migration/blocker.h" +#include "migration/qemu-file.h" #include "sysemu/tpm.h" VFIOGroupList vfio_group_list = @@ -390,6 +391,19 @@ void vfio_unblock_multiple_devices_migration(void) multiple_devices_migration_blocker = NULL; } +static void vfio_set_migration_error(int err) +{ + MigrationState *ms = migrate_get_current(); + + if (migration_is_setup_or_active(ms->state)) { + WITH_QEMU_LOCK_GUARD(&ms->qemu_file_lock) { + if (ms->to_dst_file) { + qemu_file_set_error(ms->to_dst_file, err); + } + } + } +} + static bool vfio_devices_all_dirty_tracking(VFIOContainer *container) { VFIOGroup *group; @@ -680,6 +694,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) if (iotlb->target_as != &address_space_memory) { error_report("Wrong target AS \"%s\", only system memory is allowed", iotlb->target_as->name ? iotlb->target_as->name : "none"); + vfio_set_migration_error(-EINVAL); return; } @@ -714,6 +729,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) "0x%"HWADDR_PRIx") = %d (%s)", container, iova, iotlb->addr_mask + 1, ret, strerror(-ret)); + vfio_set_migration_error(ret); } } out: @@ -1259,7 +1275,7 @@ static void vfio_listener_region_del(MemoryListener *listener, } } -static void vfio_set_dirty_page_tracking(VFIOContainer *container, bool start) +static int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start) { int ret; struct vfio_iommu_type1_dirty_bitmap dirty = { @@ -1267,7 +1283,7 @@ static void vfio_set_dirty_page_tracking(VFIOContainer *container, bool start) }; if (!container->dirty_pages_supported) { - return; + return 0; } if (start) { @@ -1278,23 +1294,34 @@ static void vfio_set_dirty_page_tracking(VFIOContainer *container, bool start) ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, &dirty); if (ret) { + ret = -errno; error_report("Failed to set dirty tracking flag 0x%x errno: %d", dirty.flags, errno); } + + return ret; } static void vfio_listener_log_global_start(MemoryListener *listener) { VFIOContainer *container = container_of(listener, VFIOContainer, listener); + int ret; - vfio_set_dirty_page_tracking(container, true); + ret = vfio_set_dirty_page_tracking(container, true); + if (ret) { + vfio_set_migration_error(ret); + } } static void vfio_listener_log_global_stop(MemoryListener *listener) { VFIOContainer *container = container_of(listener, VFIOContainer, listener); + int ret; - vfio_set_dirty_page_tracking(container, false); + ret = vfio_set_dirty_page_tracking(container, false); + if (ret) { + vfio_set_migration_error(ret); + } } static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, @@ -1370,19 +1397,18 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) VFIOContainer *container = giommu->container; hwaddr iova = iotlb->iova + giommu->iommu_offset; ram_addr_t translated_addr; + int ret = -EINVAL; trace_vfio_iommu_map_dirty_notify(iova, iova + iotlb->addr_mask); if (iotlb->target_as != &address_space_memory) { error_report("Wrong target AS \"%s\", only system memory is allowed", iotlb->target_as->name ? iotlb->target_as->name : "none"); - return; + goto out; } rcu_read_lock(); if (vfio_get_xlat_addr(iotlb, NULL, &translated_addr, NULL)) { - int ret; - ret = vfio_get_dirty_bitmap(container, iova, iotlb->addr_mask + 1, translated_addr); if (ret) { @@ -1393,6 +1419,11 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) } } rcu_read_unlock(); + +out: + if (ret) { + vfio_set_migration_error(ret); + } } static int vfio_ram_discard_get_dirty_bitmap(MemoryRegionSection *section, @@ -1485,13 +1516,19 @@ static void vfio_listener_log_sync(MemoryListener *listener, MemoryRegionSection *section) { VFIOContainer *container = container_of(listener, VFIOContainer, listener); + int ret; if (vfio_listener_skipped_section(section)) { return; } if (vfio_devices_all_dirty_tracking(container)) { - vfio_sync_dirty_bitmap(container, section); + ret = vfio_sync_dirty_bitmap(container, section); + if (ret) { + error_report("vfio: Failed to sync dirty bitmap, err: %d (%s)", ret, + strerror(-ret)); + vfio_set_migration_error(ret); + } } } -- cgit v1.2.3 From 725ccd7e419d640ebee4c3869235efea070764de Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Tue, 7 Mar 2023 12:54:39 +0000 Subject: vfio/common: Add VFIOBitmap and alloc function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are already two places where dirty page bitmap allocation and calculations are done in open code. To avoid code duplication, introduce VFIOBitmap struct and corresponding alloc function and use them where applicable. Signed-off-by: Avihai Horon Signed-off-by: Joao Martins Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20230307125450.62409-5-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 73 ++++++++++++++++++++++++++++++++++---------------------- 1 file changed, 44 insertions(+), 29 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 4c80151313..cec3de08d2 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -320,6 +320,25 @@ const MemoryRegionOps vfio_region_ops = { * Device state interfaces */ +typedef struct { + unsigned long *bitmap; + hwaddr size; + hwaddr pages; +} VFIOBitmap; + +static int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size) +{ + vbmap->pages = REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size(); + vbmap->size = ROUND_UP(vbmap->pages, sizeof(__u64) * BITS_PER_BYTE) / + BITS_PER_BYTE; + vbmap->bitmap = g_try_malloc0(vbmap->size); + if (!vbmap->bitmap) { + return -ENOMEM; + } + + return 0; +} + bool vfio_mig_active(void) { VFIOGroup *group; @@ -468,9 +487,14 @@ static int vfio_dma_unmap_bitmap(VFIOContainer *container, { struct vfio_iommu_type1_dma_unmap *unmap; struct vfio_bitmap *bitmap; - uint64_t pages = REAL_HOST_PAGE_ALIGN(size) / qemu_real_host_page_size(); + VFIOBitmap vbmap; int ret; + ret = vfio_bitmap_alloc(&vbmap, size); + if (ret) { + return ret; + } + unmap = g_malloc0(sizeof(*unmap) + sizeof(*bitmap)); unmap->argsz = sizeof(*unmap) + sizeof(*bitmap); @@ -484,35 +508,28 @@ static int vfio_dma_unmap_bitmap(VFIOContainer *container, * qemu_real_host_page_size to mark those dirty. Hence set bitmap_pgsize * to qemu_real_host_page_size. */ - bitmap->pgsize = qemu_real_host_page_size(); - bitmap->size = ROUND_UP(pages, sizeof(__u64) * BITS_PER_BYTE) / - BITS_PER_BYTE; + bitmap->size = vbmap.size; + bitmap->data = (__u64 *)vbmap.bitmap; - if (bitmap->size > container->max_dirty_bitmap_size) { - error_report("UNMAP: Size of bitmap too big 0x%"PRIx64, - (uint64_t)bitmap->size); + if (vbmap.size > container->max_dirty_bitmap_size) { + error_report("UNMAP: Size of bitmap too big 0x%"PRIx64, vbmap.size); ret = -E2BIG; goto unmap_exit; } - bitmap->data = g_try_malloc0(bitmap->size); - if (!bitmap->data) { - ret = -ENOMEM; - goto unmap_exit; - } - ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap); if (!ret) { - cpu_physical_memory_set_dirty_lebitmap((unsigned long *)bitmap->data, - iotlb->translated_addr, pages); + cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap, + iotlb->translated_addr, vbmap.pages); } else { error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %m"); } - g_free(bitmap->data); unmap_exit: g_free(unmap); + g_free(vbmap.bitmap); + return ret; } @@ -1329,7 +1346,7 @@ static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, { struct vfio_iommu_type1_dirty_bitmap *dbitmap; struct vfio_iommu_type1_dirty_bitmap_get *range; - uint64_t pages; + VFIOBitmap vbmap; int ret; if (!container->dirty_pages_supported) { @@ -1339,6 +1356,11 @@ static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, return 0; } + ret = vfio_bitmap_alloc(&vbmap, size); + if (ret) { + return ret; + } + dbitmap = g_malloc0(sizeof(*dbitmap) + sizeof(*range)); dbitmap->argsz = sizeof(*dbitmap) + sizeof(*range); @@ -1353,15 +1375,8 @@ static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, * to qemu_real_host_page_size. */ range->bitmap.pgsize = qemu_real_host_page_size(); - - pages = REAL_HOST_PAGE_ALIGN(range->size) / qemu_real_host_page_size(); - range->bitmap.size = ROUND_UP(pages, sizeof(__u64) * BITS_PER_BYTE) / - BITS_PER_BYTE; - range->bitmap.data = g_try_malloc0(range->bitmap.size); - if (!range->bitmap.data) { - ret = -ENOMEM; - goto err_out; - } + range->bitmap.size = vbmap.size; + range->bitmap.data = (__u64 *)vbmap.bitmap; ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap); if (ret) { @@ -1372,14 +1387,14 @@ static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, goto err_out; } - cpu_physical_memory_set_dirty_lebitmap((unsigned long *)range->bitmap.data, - ram_addr, pages); + cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap, ram_addr, + vbmap.pages); trace_vfio_get_dirty_bitmap(container->fd, range->iova, range->size, range->bitmap.size, ram_addr); err_out: - g_free(range->bitmap.data); g_free(dbitmap); + g_free(vbmap.bitmap); return ret; } -- cgit v1.2.3 From fbc6c92134048cef7a9317119da4b6beea03138e Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 7 Mar 2023 12:54:40 +0000 Subject: vfio/common: Add helper to validate iova/end against hostwin MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Move the code that finds the container host DMA window against a iova range. This avoids duplication on the common checks across listener callbacks. Signed-off-by: Joao Martins Reviewed-by: Cédric Le Goater Reviewed-by: Avihai Horon Link: https://lore.kernel.org/r/20230307125450.62409-6-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index cec3de08d2..99acb998eb 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -901,6 +901,22 @@ static void vfio_unregister_ram_discard_listener(VFIOContainer *container, g_free(vrdl); } +static VFIOHostDMAWindow *vfio_find_hostwin(VFIOContainer *container, + hwaddr iova, hwaddr end) +{ + VFIOHostDMAWindow *hostwin; + bool hostwin_found = false; + + QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { + if (hostwin->min_iova <= iova && end <= hostwin->max_iova) { + hostwin_found = true; + break; + } + } + + return hostwin_found ? hostwin : NULL; +} + static bool vfio_known_safe_misalignment(MemoryRegionSection *section) { MemoryRegion *mr = section->mr; @@ -926,7 +942,6 @@ static void vfio_listener_region_add(MemoryListener *listener, void *vaddr; int ret; VFIOHostDMAWindow *hostwin; - bool hostwin_found; Error *err = NULL; if (vfio_listener_skipped_section(section)) { @@ -1027,15 +1042,8 @@ static void vfio_listener_region_add(MemoryListener *listener, #endif } - 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) { + hostwin = vfio_find_hostwin(container, iova, end); + if (!hostwin) { error_setg(&err, "Container %p can't map guest IOVA region" " 0x%"HWADDR_PRIx"..0x%"HWADDR_PRIx, container, iova, end); goto fail; @@ -1237,15 +1245,9 @@ static void vfio_listener_region_del(MemoryListener *listener, if (memory_region_is_ram_device(section->mr)) { hwaddr pgmask; VFIOHostDMAWindow *hostwin; - bool hostwin_found = false; - QLIST_FOREACH(hostwin, &container->hostwin_list, hostwin_next) { - if (hostwin->min_iova <= iova && end <= hostwin->max_iova) { - hostwin_found = true; - break; - } - } - assert(hostwin_found); /* or region_add() would have failed */ + hostwin = vfio_find_hostwin(container, iova, end); + assert(hostwin); /* or region_add() would have failed */ pgmask = (1ULL << ctz64(hostwin->iova_pgsizes)) - 1; try_unmap = !((iova & pgmask) || (int128_get64(llsize) & pgmask)); -- cgit v1.2.3 From 1cd7fa7adc157c5ec8050a6fe31670bdf3f6c2a5 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 7 Mar 2023 12:54:41 +0000 Subject: vfio/common: Use a single tracepoint for skipped sections MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to turn more of the memory listener checks into common functions, one of the affected places is how we trace when sections are skipped. Right now there is one for each. Change it into one single tracepoint `vfio_listener_region_skip` which receives a name which refers to the callback i.e. region_add and region_del. Suggested-by: Avihai Horon Signed-off-by: Joao Martins Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20230307125450.62409-7-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 4 ++-- hw/vfio/trace-events | 3 +-- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 99acb998eb..1cb62efa97 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -945,7 +945,7 @@ static void vfio_listener_region_add(MemoryListener *listener, Error *err = NULL; if (vfio_listener_skipped_section(section)) { - trace_vfio_listener_region_add_skip( + trace_vfio_listener_region_skip("region_add", section->offset_within_address_space, section->offset_within_address_space + int128_get64(int128_sub(section->size, int128_one()))); @@ -1183,7 +1183,7 @@ static void vfio_listener_region_del(MemoryListener *listener, bool try_unmap = true; if (vfio_listener_skipped_section(section)) { - trace_vfio_listener_region_del_skip( + trace_vfio_listener_region_skip("region_del", section->offset_within_address_space, section->offset_within_address_space + int128_get64(int128_sub(section->size, int128_one()))); diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 669d9fe07c..7173e6a5c7 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -96,13 +96,12 @@ vfio_pci_igd_lpc_bridge_enabled(const char *name) "%s" vfio_region_write(const char *name, int index, uint64_t addr, uint64_t data, unsigned size) " (%s:region%d+0x%"PRIx64", 0x%"PRIx64 ", %d)" vfio_region_read(char *name, int index, uint64_t addr, unsigned size, uint64_t data) " (%s:region%d+0x%"PRIx64", %d) = 0x%"PRIx64 vfio_iommu_map_notify(const char *op, uint64_t iova_start, uint64_t iova_end) "iommu %s @ 0x%"PRIx64" - 0x%"PRIx64 -vfio_listener_region_add_skip(uint64_t start, uint64_t end) "SKIPPING region_add 0x%"PRIx64" - 0x%"PRIx64 +vfio_listener_region_skip(const char *name, uint64_t start, uint64_t end) "SKIPPING %s 0x%"PRIx64" - 0x%"PRIx64 vfio_spapr_group_attach(int groupfd, int tablefd) "Attached groupfd %d to liobn fd %d" vfio_listener_region_add_iommu(uint64_t start, uint64_t end) "region_add [iommu] 0x%"PRIx64" - 0x%"PRIx64 vfio_listener_region_add_ram(uint64_t iova_start, uint64_t iova_end, void *vaddr) "region_add [ram] 0x%"PRIx64" - 0x%"PRIx64" [%p]" vfio_known_safe_misalignment(const char *name, uint64_t iova, uint64_t offset_within_region, uintptr_t page_size) "Region \"%s\" iova=0x%"PRIx64" offset_within_region=0x%"PRIx64" qemu_real_host_page_size=0x%"PRIxPTR vfio_listener_region_add_no_dma_map(const char *name, uint64_t iova, uint64_t size, uint64_t page_size) "Region \"%s\" 0x%"PRIx64" size=0x%"PRIx64" is not aligned to 0x%"PRIx64" and cannot be mapped for DMA" -vfio_listener_region_del_skip(uint64_t start, uint64_t end) "SKIPPING region_del 0x%"PRIx64" - 0x%"PRIx64 vfio_listener_region_del(uint64_t start, uint64_t end) "region_del 0x%"PRIx64" - 0x%"PRIx64 vfio_disconnect_container(int fd) "close container->fd=%d" vfio_put_group(int fd) "close group->fd=%d" -- cgit v1.2.3 From b92f237635054189ae10c0c98aeec9f982f1335f Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 7 Mar 2023 12:54:42 +0000 Subject: vfio/common: Consolidate skip/invalid section into helper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The checks are replicated against region_add and region_del and will be soon added in another memory listener dedicated for dirty tracking. Move these into a new helper for avoid duplication. Signed-off-by: Joao Martins Reviewed-by: Cédric Le Goater Reviewed-by: Avihai Horon Link: https://lore.kernel.org/r/20230307125450.62409-8-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 55 +++++++++++++++++++++++-------------------------------- 1 file changed, 23 insertions(+), 32 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 1cb62efa97..d38b7c1969 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -933,23 +933,15 @@ static bool vfio_known_safe_misalignment(MemoryRegionSection *section) return true; } -static void vfio_listener_region_add(MemoryListener *listener, - MemoryRegionSection *section) +static bool vfio_listener_valid_section(MemoryRegionSection *section, + const char *name) { - VFIOContainer *container = container_of(listener, VFIOContainer, listener); - hwaddr iova, end; - Int128 llend, llsize; - void *vaddr; - int ret; - VFIOHostDMAWindow *hostwin; - Error *err = NULL; - if (vfio_listener_skipped_section(section)) { - trace_vfio_listener_region_skip("region_add", + trace_vfio_listener_region_skip(name, section->offset_within_address_space, section->offset_within_address_space + int128_get64(int128_sub(section->size, int128_one()))); - return; + return false; } if (unlikely((section->offset_within_address_space & @@ -964,6 +956,24 @@ static void vfio_listener_region_add(MemoryListener *listener, section->offset_within_region, qemu_real_host_page_size()); } + return false; + } + + return true; +} + +static void vfio_listener_region_add(MemoryListener *listener, + MemoryRegionSection *section) +{ + VFIOContainer *container = container_of(listener, VFIOContainer, listener); + hwaddr iova, end; + Int128 llend, llsize; + void *vaddr; + int ret; + VFIOHostDMAWindow *hostwin; + Error *err = NULL; + + if (!vfio_listener_valid_section(section, "region_add")) { return; } @@ -1182,26 +1192,7 @@ static void vfio_listener_region_del(MemoryListener *listener, int ret; bool try_unmap = true; - if (vfio_listener_skipped_section(section)) { - trace_vfio_listener_region_skip("region_del", - 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 & - ~qemu_real_host_page_mask()) != - (section->offset_within_region & ~qemu_real_host_page_mask()))) { - if (!vfio_known_safe_misalignment(section)) { - error_report("%s received unaligned region %s iova=0x%"PRIx64 - " offset_within_region=0x%"PRIx64 - " qemu_real_host_page_size=0x%"PRIxPTR, - __func__, memory_region_name(section->mr), - section->offset_within_address_space, - section->offset_within_region, - qemu_real_host_page_size()); - } + if (!vfio_listener_valid_section(section, "region_del")) { return; } -- cgit v1.2.3 From 4ead830848e1f2571ca759ee6734bccd6e2ba3a6 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 7 Mar 2023 12:54:43 +0000 Subject: vfio/common: Add helper to consolidate iova/end calculation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In preparation to be used in device dirty tracking, move the code that calculate a iova/end range from the container/section. This avoids duplication on the common checks across listener callbacks. Signed-off-by: Joao Martins Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20230307125450.62409-9-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 41 +++++++++++++++++++++++++++-------------- 1 file changed, 27 insertions(+), 14 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index d38b7c1969..63831eab78 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -962,6 +962,31 @@ static bool vfio_listener_valid_section(MemoryRegionSection *section, return true; } +static bool vfio_get_section_iova_range(VFIOContainer *container, + MemoryRegionSection *section, + hwaddr *out_iova, hwaddr *out_end, + Int128 *out_llend) +{ + Int128 llend; + hwaddr iova; + + iova = REAL_HOST_PAGE_ALIGN(section->offset_within_address_space); + llend = int128_make64(section->offset_within_address_space); + llend = int128_add(llend, section->size); + llend = int128_and(llend, int128_exts64(qemu_real_host_page_mask())); + + if (int128_ge(int128_make64(iova), llend)) { + return false; + } + + *out_iova = iova; + *out_end = int128_get64(int128_sub(llend, int128_one())); + if (out_llend) { + *out_llend = llend; + } + return true; +} + static void vfio_listener_region_add(MemoryListener *listener, MemoryRegionSection *section) { @@ -977,12 +1002,7 @@ static void vfio_listener_region_add(MemoryListener *listener, return; } - iova = REAL_HOST_PAGE_ALIGN(section->offset_within_address_space); - llend = int128_make64(section->offset_within_address_space); - llend = int128_add(llend, section->size); - llend = int128_and(llend, int128_exts64(qemu_real_host_page_mask())); - - if (int128_ge(int128_make64(iova), llend)) { + if (!vfio_get_section_iova_range(container, section, &iova, &end, &llend)) { if (memory_region_is_ram_device(section->mr)) { trace_vfio_listener_region_add_no_dma_map( memory_region_name(section->mr), @@ -992,7 +1012,6 @@ static void vfio_listener_region_add(MemoryListener *listener, } return; } - end = int128_get64(int128_sub(llend, int128_one())); if (container->iommu_type == VFIO_SPAPR_TCE_v2_IOMMU) { hwaddr pgsize = 0; @@ -1219,15 +1238,9 @@ static void vfio_listener_region_del(MemoryListener *listener, */ } - iova = REAL_HOST_PAGE_ALIGN(section->offset_within_address_space); - llend = int128_make64(section->offset_within_address_space); - llend = int128_add(llend, section->size); - llend = int128_and(llend, int128_exts64(qemu_real_host_page_mask())); - - if (int128_ge(int128_make64(iova), llend)) { + if (!vfio_get_section_iova_range(container, section, &iova, &end, &llend)) { return; } - end = int128_get64(int128_sub(llend, int128_one())); llsize = int128_sub(llend, int128_make64(iova)); -- cgit v1.2.3 From 62c1b0024b3a4ac95deded14541c428f8fc662fa Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 7 Mar 2023 12:54:44 +0000 Subject: vfio/common: Record DMA mapped IOVA ranges MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit According to the device DMA logging uAPI, IOVA ranges to be logged by the device must be provided all at once upon DMA logging start. As preparation for the following patches which will add device dirty page tracking, keep a record of all DMA mapped IOVA ranges so later they can be used for DMA logging start. Signed-off-by: Avihai Horon Signed-off-by: Joao Martins Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20230307125450.62409-10-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++++++++ hw/vfio/trace-events | 1 + 2 files changed, 86 insertions(+) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 63831eab78..811502dbc9 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -1325,11 +1325,96 @@ static int vfio_set_dirty_page_tracking(VFIOContainer *container, bool start) return ret; } +typedef struct VFIODirtyRanges { + hwaddr min32; + hwaddr max32; + hwaddr min64; + hwaddr max64; +} VFIODirtyRanges; + +typedef struct VFIODirtyRangesListener { + VFIOContainer *container; + VFIODirtyRanges ranges; + MemoryListener listener; +} VFIODirtyRangesListener; + +static void vfio_dirty_tracking_update(MemoryListener *listener, + MemoryRegionSection *section) +{ + VFIODirtyRangesListener *dirty = container_of(listener, + VFIODirtyRangesListener, + listener); + VFIODirtyRanges *range = &dirty->ranges; + hwaddr iova, end, *min, *max; + + if (!vfio_listener_valid_section(section, "tracking_update") || + !vfio_get_section_iova_range(dirty->container, section, + &iova, &end, NULL)) { + return; + } + + /* + * The address space passed to the dirty tracker is reduced to two ranges: + * one for 32-bit DMA ranges, and another one for 64-bit DMA ranges. + * The underlying reports of dirty will query a sub-interval of each of + * these ranges. + * + * The purpose of the dual range handling is to handle known cases of big + * holes in the address space, like the x86 AMD 1T hole. The alternative + * would be an IOVATree but that has a much bigger runtime overhead and + * unnecessary complexity. + */ + min = (end <= UINT32_MAX) ? &range->min32 : &range->min64; + max = (end <= UINT32_MAX) ? &range->max32 : &range->max64; + + if (*min > iova) { + *min = iova; + } + if (*max < end) { + *max = end; + } + + trace_vfio_device_dirty_tracking_update(iova, end, *min, *max); + return; +} + +static const MemoryListener vfio_dirty_tracking_listener = { + .name = "vfio-tracking", + .region_add = vfio_dirty_tracking_update, +}; + +static void vfio_dirty_tracking_init(VFIOContainer *container, + VFIODirtyRanges *ranges) +{ + VFIODirtyRangesListener dirty; + + memset(&dirty, 0, sizeof(dirty)); + dirty.ranges.min32 = UINT32_MAX; + dirty.ranges.min64 = UINT64_MAX; + dirty.listener = vfio_dirty_tracking_listener; + dirty.container = container; + + memory_listener_register(&dirty.listener, + container->space->as); + + *ranges = dirty.ranges; + + /* + * The memory listener is synchronous, and used to calculate the range + * to dirty tracking. Unregister it after we are done as we are not + * interested in any follow-up updates. + */ + memory_listener_unregister(&dirty.listener); +} + static void vfio_listener_log_global_start(MemoryListener *listener) { VFIOContainer *container = container_of(listener, VFIOContainer, listener); + VFIODirtyRanges ranges; int ret; + vfio_dirty_tracking_init(container, &ranges); + ret = vfio_set_dirty_page_tracking(container, true); if (ret) { vfio_set_migration_error(ret); diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index 7173e6a5c7..dd9fd7b9bd 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -103,6 +103,7 @@ vfio_listener_region_add_ram(uint64_t iova_start, uint64_t iova_end, void *vaddr vfio_known_safe_misalignment(const char *name, uint64_t iova, uint64_t offset_within_region, uintptr_t page_size) "Region \"%s\" iova=0x%"PRIx64" offset_within_region=0x%"PRIx64" qemu_real_host_page_size=0x%"PRIxPTR vfio_listener_region_add_no_dma_map(const char *name, uint64_t iova, uint64_t size, uint64_t page_size) "Region \"%s\" 0x%"PRIx64" size=0x%"PRIx64" is not aligned to 0x%"PRIx64" and cannot be mapped for DMA" vfio_listener_region_del(uint64_t start, uint64_t end) "region_del 0x%"PRIx64" - 0x%"PRIx64 +vfio_device_dirty_tracking_update(uint64_t start, uint64_t end, uint64_t min, uint64_t max) "section 0x%"PRIx64" - 0x%"PRIx64" -> update [0x%"PRIx64" - 0x%"PRIx64"]" vfio_disconnect_container(int fd) "close container->fd=%d" vfio_put_group(int fd) "close group->fd=%d" vfio_get_device(const char * name, unsigned int flags, unsigned int num_regions, unsigned int num_irqs) "Device %s flags: %u, regions: %u, irqs: %u" -- cgit v1.2.3 From 5255bbf4ec16bb352265d9ce131076212730a621 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 7 Mar 2023 12:54:45 +0000 Subject: vfio/common: Add device dirty page tracking start/stop Add device dirty page tracking start/stop functionality. This uses the device DMA logging uAPI to start and stop dirty page tracking by device. Device dirty page tracking is used only if all devices within a container support device dirty page tracking. Signed-off-by: Avihai Horon Signed-off-by: Joao Martins Link: https://lore.kernel.org/r/20230307125450.62409-11-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 173 ++++++++++++++++++++++++++++++++++++++++-- hw/vfio/trace-events | 1 + include/hw/vfio/vfio-common.h | 2 + 3 files changed, 171 insertions(+), 5 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 811502dbc9..55498afeb2 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -450,6 +450,22 @@ static bool vfio_devices_all_dirty_tracking(VFIOContainer *container) return true; } +static bool vfio_devices_all_device_dirty_tracking(VFIOContainer *container) +{ + VFIOGroup *group; + VFIODevice *vbasedev; + + QLIST_FOREACH(group, &container->group_list, container_next) { + QLIST_FOREACH(vbasedev, &group->device_list, next) { + if (!vbasedev->dirty_pages_supported) { + return false; + } + } + } + + return true; +} + /* * Check if all VFIO devices are running and migration is active, which is * essentially equivalent to the migration being in pre-copy phase. @@ -1407,16 +1423,156 @@ static void vfio_dirty_tracking_init(VFIOContainer *container, memory_listener_unregister(&dirty.listener); } +static void vfio_devices_dma_logging_stop(VFIOContainer *container) +{ + uint64_t buf[DIV_ROUND_UP(sizeof(struct vfio_device_feature), + sizeof(uint64_t))] = {}; + struct vfio_device_feature *feature = (struct vfio_device_feature *)buf; + VFIODevice *vbasedev; + VFIOGroup *group; + + feature->argsz = sizeof(buf); + feature->flags = VFIO_DEVICE_FEATURE_SET | + VFIO_DEVICE_FEATURE_DMA_LOGGING_STOP; + + QLIST_FOREACH(group, &container->group_list, container_next) { + QLIST_FOREACH(vbasedev, &group->device_list, next) { + if (!vbasedev->dirty_tracking) { + continue; + } + + if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) { + warn_report("%s: Failed to stop DMA logging, err %d (%s)", + vbasedev->name, -errno, strerror(errno)); + } + vbasedev->dirty_tracking = false; + } + } +} + +static struct vfio_device_feature * +vfio_device_feature_dma_logging_start_create(VFIOContainer *container, + VFIODirtyRanges *tracking) +{ + struct vfio_device_feature *feature; + size_t feature_size; + struct vfio_device_feature_dma_logging_control *control; + struct vfio_device_feature_dma_logging_range *ranges; + + feature_size = sizeof(struct vfio_device_feature) + + sizeof(struct vfio_device_feature_dma_logging_control); + feature = g_try_malloc0(feature_size); + if (!feature) { + errno = ENOMEM; + return NULL; + } + feature->argsz = feature_size; + feature->flags = VFIO_DEVICE_FEATURE_SET | + VFIO_DEVICE_FEATURE_DMA_LOGGING_START; + + control = (struct vfio_device_feature_dma_logging_control *)feature->data; + control->page_size = qemu_real_host_page_size(); + + /* + * DMA logging uAPI guarantees to support at least a number of ranges that + * fits into a single host kernel base page. + */ + control->num_ranges = !!tracking->max32 + !!tracking->max64; + ranges = g_try_new0(struct vfio_device_feature_dma_logging_range, + control->num_ranges); + if (!ranges) { + g_free(feature); + errno = ENOMEM; + + return NULL; + } + + control->ranges = (__u64)(uintptr_t)ranges; + if (tracking->max32) { + ranges->iova = tracking->min32; + ranges->length = (tracking->max32 - tracking->min32) + 1; + ranges++; + } + if (tracking->max64) { + ranges->iova = tracking->min64; + ranges->length = (tracking->max64 - tracking->min64) + 1; + } + + trace_vfio_device_dirty_tracking_start(control->num_ranges, + tracking->min32, tracking->max32, + tracking->min64, tracking->max64); + + return feature; +} + +static void vfio_device_feature_dma_logging_start_destroy( + struct vfio_device_feature *feature) +{ + struct vfio_device_feature_dma_logging_control *control = + (struct vfio_device_feature_dma_logging_control *)feature->data; + struct vfio_device_feature_dma_logging_range *ranges = + (struct vfio_device_feature_dma_logging_range *)(uintptr_t)control->ranges; + + g_free(ranges); + g_free(feature); +} + +static int vfio_devices_dma_logging_start(VFIOContainer *container) +{ + struct vfio_device_feature *feature; + VFIODirtyRanges ranges; + VFIODevice *vbasedev; + VFIOGroup *group; + int ret = 0; + + vfio_dirty_tracking_init(container, &ranges); + feature = vfio_device_feature_dma_logging_start_create(container, + &ranges); + if (!feature) { + return -errno; + } + + QLIST_FOREACH(group, &container->group_list, container_next) { + QLIST_FOREACH(vbasedev, &group->device_list, next) { + if (vbasedev->dirty_tracking) { + continue; + } + + ret = ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature); + if (ret) { + ret = -errno; + error_report("%s: Failed to start DMA logging, err %d (%s)", + vbasedev->name, ret, strerror(errno)); + goto out; + } + vbasedev->dirty_tracking = true; + } + } + +out: + if (ret) { + vfio_devices_dma_logging_stop(container); + } + + vfio_device_feature_dma_logging_start_destroy(feature); + + return ret; +} + static void vfio_listener_log_global_start(MemoryListener *listener) { VFIOContainer *container = container_of(listener, VFIOContainer, listener); - VFIODirtyRanges ranges; int ret; - vfio_dirty_tracking_init(container, &ranges); + if (vfio_devices_all_device_dirty_tracking(container)) { + ret = vfio_devices_dma_logging_start(container); + } else { + ret = vfio_set_dirty_page_tracking(container, true); + } - ret = vfio_set_dirty_page_tracking(container, true); if (ret) { + error_report("vfio: Could not start dirty page tracking, err: %d (%s)", + ret, strerror(-ret)); vfio_set_migration_error(ret); } } @@ -1424,10 +1580,17 @@ static void vfio_listener_log_global_start(MemoryListener *listener) static void vfio_listener_log_global_stop(MemoryListener *listener) { VFIOContainer *container = container_of(listener, VFIOContainer, listener); - int ret; + int ret = 0; + + if (vfio_devices_all_device_dirty_tracking(container)) { + vfio_devices_dma_logging_stop(container); + } else { + ret = vfio_set_dirty_page_tracking(container, false); + } - ret = vfio_set_dirty_page_tracking(container, false); if (ret) { + error_report("vfio: Could not stop dirty page tracking, err: %d (%s)", + ret, strerror(-ret)); vfio_set_migration_error(ret); } } diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index dd9fd7b9bd..bee95dbd97 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -104,6 +104,7 @@ vfio_known_safe_misalignment(const char *name, uint64_t iova, uint64_t offset_wi vfio_listener_region_add_no_dma_map(const char *name, uint64_t iova, uint64_t size, uint64_t page_size) "Region \"%s\" 0x%"PRIx64" size=0x%"PRIx64" is not aligned to 0x%"PRIx64" and cannot be mapped for DMA" vfio_listener_region_del(uint64_t start, uint64_t end) "region_del 0x%"PRIx64" - 0x%"PRIx64 vfio_device_dirty_tracking_update(uint64_t start, uint64_t end, uint64_t min, uint64_t max) "section 0x%"PRIx64" - 0x%"PRIx64" -> update [0x%"PRIx64" - 0x%"PRIx64"]" +vfio_device_dirty_tracking_start(int nr_ranges, uint64_t min32, uint64_t max32, uint64_t min64, uint64_t max64) "nr_ranges %d 32:[0x%"PRIx64" - 0x%"PRIx64"], 64:[0x%"PRIx64" - 0x%"PRIx64"]" vfio_disconnect_container(int fd) "close container->fd=%d" vfio_put_group(int fd) "close group->fd=%d" vfio_get_device(const char * name, unsigned int flags, unsigned int num_regions, unsigned int num_irqs) "Device %s flags: %u, regions: %u, irqs: %u" diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 87524c64a4..9551d2d430 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -143,6 +143,8 @@ typedef struct VFIODevice { VFIOMigration *migration; Error *migration_blocker; OnOffAuto pre_copy_dirty_page_tracking; + bool dirty_pages_supported; + bool dirty_tracking; } VFIODevice; struct VFIODeviceOps { -- cgit v1.2.3 From 6607109f0508f4fe218159e6cf083ec58ed6fbff Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Tue, 7 Mar 2023 12:54:46 +0000 Subject: vfio/common: Extract code from vfio_get_dirty_bitmap() to new function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Extract the VFIO_IOMMU_DIRTY_PAGES ioctl code in vfio_get_dirty_bitmap() to its own function. This will help the code to be more readable after next patch will add device dirty page bitmap sync functionality. Signed-off-by: Avihai Horon Signed-off-by: Joao Martins Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20230307125450.62409-12-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 57 ++++++++++++++++++++++++++++++++++---------------------- 1 file changed, 35 insertions(+), 22 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 55498afeb2..ae81af6d32 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -1595,26 +1595,13 @@ static void vfio_listener_log_global_stop(MemoryListener *listener) } } -static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, - uint64_t size, ram_addr_t ram_addr) +static int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap, + hwaddr iova, hwaddr size) { struct vfio_iommu_type1_dirty_bitmap *dbitmap; struct vfio_iommu_type1_dirty_bitmap_get *range; - VFIOBitmap vbmap; int ret; - if (!container->dirty_pages_supported) { - cpu_physical_memory_set_dirty_range(ram_addr, size, - tcg_enabled() ? DIRTY_CLIENTS_ALL : - DIRTY_CLIENTS_NOCODE); - return 0; - } - - ret = vfio_bitmap_alloc(&vbmap, size); - if (ret) { - return ret; - } - dbitmap = g_malloc0(sizeof(*dbitmap) + sizeof(*range)); dbitmap->argsz = sizeof(*dbitmap) + sizeof(*range); @@ -1629,8 +1616,8 @@ static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, * to qemu_real_host_page_size. */ range->bitmap.pgsize = qemu_real_host_page_size(); - range->bitmap.size = vbmap.size; - range->bitmap.data = (__u64 *)vbmap.bitmap; + range->bitmap.size = vbmap->size; + range->bitmap.data = (__u64 *)vbmap->bitmap; ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap); if (ret) { @@ -1638,16 +1625,42 @@ static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64 " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova, (uint64_t)range->size, errno); - goto err_out; + } + + g_free(dbitmap); + + return ret; +} + +static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, + uint64_t size, ram_addr_t ram_addr) +{ + VFIOBitmap vbmap; + int ret; + + if (!container->dirty_pages_supported) { + cpu_physical_memory_set_dirty_range(ram_addr, size, + tcg_enabled() ? DIRTY_CLIENTS_ALL : + DIRTY_CLIENTS_NOCODE); + return 0; + } + + ret = vfio_bitmap_alloc(&vbmap, size); + if (ret) { + return ret; + } + + ret = vfio_query_dirty_bitmap(container, &vbmap, iova, size); + if (ret) { + goto out; } cpu_physical_memory_set_dirty_lebitmap(vbmap.bitmap, ram_addr, vbmap.pages); - trace_vfio_get_dirty_bitmap(container->fd, range->iova, range->size, - range->bitmap.size, ram_addr); -err_out: - g_free(dbitmap); + trace_vfio_get_dirty_bitmap(container->fd, iova, size, vbmap.size, + ram_addr); +out: g_free(vbmap.bitmap); return ret; -- cgit v1.2.3 From b153402a8941c2193e91ac50ed9720c7da6ee8db Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 7 Mar 2023 12:54:47 +0000 Subject: vfio/common: Add device dirty page bitmap sync MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add device dirty page bitmap sync functionality. This uses the device DMA logging uAPI to sync dirty page bitmap from the device. Device dirty page bitmap sync is used only if all devices within a container support device dirty page tracking. Signed-off-by: Avihai Horon Signed-off-by: Joao Martins Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20230307125450.62409-13-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 79 insertions(+), 9 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index ae81af6d32..334c625858 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -339,6 +339,9 @@ static int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size) return 0; } +static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, + uint64_t size, ram_addr_t ram_addr); + bool vfio_mig_active(void) { VFIOGroup *group; @@ -562,10 +565,16 @@ static int vfio_dma_unmap(VFIOContainer *container, .iova = iova, .size = size, }; + bool need_dirty_sync = false; + int ret; + + if (iotlb && vfio_devices_all_running_and_mig_active(container)) { + if (!vfio_devices_all_device_dirty_tracking(container) && + container->dirty_pages_supported) { + return vfio_dma_unmap_bitmap(container, iova, size, iotlb); + } - if (iotlb && container->dirty_pages_supported && - vfio_devices_all_running_and_mig_active(container)) { - return vfio_dma_unmap_bitmap(container, iova, size, iotlb); + need_dirty_sync = true; } while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) { @@ -591,10 +600,12 @@ static int vfio_dma_unmap(VFIOContainer *container, return -errno; } - if (iotlb && vfio_devices_all_running_and_mig_active(container)) { - cpu_physical_memory_set_dirty_range(iotlb->translated_addr, size, - tcg_enabled() ? DIRTY_CLIENTS_ALL : - DIRTY_CLIENTS_NOCODE); + if (need_dirty_sync) { + ret = vfio_get_dirty_bitmap(container, iova, size, + iotlb->translated_addr); + if (ret) { + return ret; + } } return 0; @@ -1595,6 +1606,58 @@ static void vfio_listener_log_global_stop(MemoryListener *listener) } } +static int vfio_device_dma_logging_report(VFIODevice *vbasedev, hwaddr iova, + hwaddr size, void *bitmap) +{ + uint64_t buf[DIV_ROUND_UP(sizeof(struct vfio_device_feature) + + sizeof(struct vfio_device_feature_dma_logging_report), + sizeof(__u64))] = {}; + struct vfio_device_feature *feature = (struct vfio_device_feature *)buf; + struct vfio_device_feature_dma_logging_report *report = + (struct vfio_device_feature_dma_logging_report *)feature->data; + + report->iova = iova; + report->length = size; + report->page_size = qemu_real_host_page_size(); + report->bitmap = (__u64)(uintptr_t)bitmap; + + feature->argsz = sizeof(buf); + feature->flags = VFIO_DEVICE_FEATURE_GET | + VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT; + + if (ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature)) { + return -errno; + } + + return 0; +} + +static int vfio_devices_query_dirty_bitmap(VFIOContainer *container, + VFIOBitmap *vbmap, hwaddr iova, + hwaddr size) +{ + VFIODevice *vbasedev; + VFIOGroup *group; + int ret; + + QLIST_FOREACH(group, &container->group_list, container_next) { + QLIST_FOREACH(vbasedev, &group->device_list, next) { + ret = vfio_device_dma_logging_report(vbasedev, iova, size, + vbmap->bitmap); + if (ret) { + error_report("%s: Failed to get DMA logging report, iova: " + "0x%" HWADDR_PRIx ", size: 0x%" HWADDR_PRIx + ", err: %d (%s)", + vbasedev->name, iova, size, ret, strerror(-ret)); + + return ret; + } + } + } + + return 0; +} + static int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap, hwaddr iova, hwaddr size) { @@ -1635,10 +1698,12 @@ static int vfio_query_dirty_bitmap(VFIOContainer *container, VFIOBitmap *vbmap, static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, uint64_t size, ram_addr_t ram_addr) { + bool all_device_dirty_tracking = + vfio_devices_all_device_dirty_tracking(container); VFIOBitmap vbmap; int ret; - if (!container->dirty_pages_supported) { + if (!container->dirty_pages_supported && !all_device_dirty_tracking) { cpu_physical_memory_set_dirty_range(ram_addr, size, tcg_enabled() ? DIRTY_CLIENTS_ALL : DIRTY_CLIENTS_NOCODE); @@ -1650,7 +1715,12 @@ static int vfio_get_dirty_bitmap(VFIOContainer *container, uint64_t iova, return ret; } - ret = vfio_query_dirty_bitmap(container, &vbmap, iova, size); + if (all_device_dirty_tracking) { + ret = vfio_devices_query_dirty_bitmap(container, &vbmap, iova, size); + } else { + ret = vfio_query_dirty_bitmap(container, &vbmap, iova, size); + } + if (ret) { goto out; } -- cgit v1.2.3 From e46883204c384f992088f8c3ea713f7e1c2d5a6d Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 7 Mar 2023 12:54:48 +0000 Subject: vfio/migration: Block migration with vIOMMU MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Migrating with vIOMMU will require either tracking maximum IOMMU supported address space (e.g. 39/48 address width on Intel) or range-track current mappings and dirty track the new ones post starting dirty tracking. This will be done as a separate series, so add a live migration blocker until that is fixed. Signed-off-by: Joao Martins Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20230307125450.62409-14-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/common.c | 46 +++++++++++++++++++++++++++++++++++++++++++ hw/vfio/migration.c | 5 +++++ hw/vfio/pci.c | 1 + include/hw/vfio/vfio-common.h | 2 ++ 4 files changed, 54 insertions(+) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 334c625858..539246e332 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -362,6 +362,7 @@ bool vfio_mig_active(void) } static Error *multiple_devices_migration_blocker; +static Error *giommu_migration_blocker; static unsigned int vfio_migratable_device_num(void) { @@ -413,6 +414,51 @@ void vfio_unblock_multiple_devices_migration(void) multiple_devices_migration_blocker = NULL; } +static bool vfio_viommu_preset(void) +{ + VFIOAddressSpace *space; + + QLIST_FOREACH(space, &vfio_address_spaces, list) { + if (space->as != &address_space_memory) { + return true; + } + } + + return false; +} + +int vfio_block_giommu_migration(Error **errp) +{ + int ret; + + if (giommu_migration_blocker || + !vfio_viommu_preset()) { + return 0; + } + + error_setg(&giommu_migration_blocker, + "Migration is currently not supported with vIOMMU enabled"); + ret = migrate_add_blocker(giommu_migration_blocker, errp); + if (ret < 0) { + error_free(giommu_migration_blocker); + giommu_migration_blocker = NULL; + } + + return ret; +} + +void vfio_unblock_giommu_migration(void) +{ + if (!giommu_migration_blocker || + vfio_viommu_preset()) { + return; + } + + migrate_del_blocker(giommu_migration_blocker); + error_free(giommu_migration_blocker); + giommu_migration_blocker = NULL; +} + static void vfio_set_migration_error(int err) { MigrationState *ms = migrate_get_current(); diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c index a2c3d9bade..776fd2d7cd 100644 --- a/hw/vfio/migration.c +++ b/hw/vfio/migration.c @@ -634,6 +634,11 @@ int vfio_migration_probe(VFIODevice *vbasedev, Error **errp) return ret; } + ret = vfio_block_giommu_migration(errp); + if (ret) { + return ret; + } + trace_vfio_migration_probe(vbasedev->name); return 0; diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 939dcc3d4a..30a271eab3 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -3185,6 +3185,7 @@ static void vfio_instance_finalize(Object *obj) */ vfio_put_device(vdev); vfio_put_group(group); + vfio_unblock_giommu_migration(); } static void vfio_exitfn(PCIDevice *pdev) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 9551d2d430..009bec34c4 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -222,6 +222,8 @@ extern VFIOGroupList vfio_group_list; bool vfio_mig_active(void); int vfio_block_multiple_devices_migration(Error **errp); void vfio_unblock_multiple_devices_migration(void); +int vfio_block_giommu_migration(Error **errp); +void vfio_unblock_giommu_migration(void); int64_t vfio_mig_bytes_transferred(void); #ifdef CONFIG_LINUX -- cgit v1.2.3 From 95b29658b60786a4b0631d82698e13483b2c2b94 Mon Sep 17 00:00:00 2001 From: Joao Martins Date: Tue, 7 Mar 2023 12:54:49 +0000 Subject: vfio/migration: Query device dirty page tracking support MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Now that everything has been set up for device dirty page tracking, query the device for device dirty page tracking support. Signed-off-by: Avihai Horon Signed-off-by: Joao Martins Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20230307125450.62409-15-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- hw/vfio/migration.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c index 776fd2d7cd..5d1e66f691 100644 --- a/hw/vfio/migration.c +++ b/hw/vfio/migration.c @@ -555,6 +555,19 @@ static int vfio_migration_query_flags(VFIODevice *vbasedev, uint64_t *mig_flags) return 0; } +static bool vfio_dma_logging_supported(VFIODevice *vbasedev) +{ + uint64_t buf[DIV_ROUND_UP(sizeof(struct vfio_device_feature), + sizeof(uint64_t))] = {}; + struct vfio_device_feature *feature = (struct vfio_device_feature *)buf; + + feature->argsz = sizeof(buf); + feature->flags = VFIO_DEVICE_FEATURE_PROBE | + VFIO_DEVICE_FEATURE_DMA_LOGGING_START; + + return !ioctl(vbasedev->fd, VFIO_DEVICE_FEATURE, feature); +} + static int vfio_migration_init(VFIODevice *vbasedev) { int ret; @@ -589,6 +602,8 @@ static int vfio_migration_init(VFIODevice *vbasedev) migration->device_state = VFIO_DEVICE_STATE_RUNNING; migration->data_fd = -1; + vbasedev->dirty_pages_supported = vfio_dma_logging_supported(vbasedev); + oid = vmstate_if_get_id(VMSTATE_IF(DEVICE(obj))); if (oid) { path = g_strdup_printf("%s/vfio", oid); -- cgit v1.2.3 From 333f988d19878f6b96388a1a797c4e90e7ea0a69 Mon Sep 17 00:00:00 2001 From: Avihai Horon Date: Tue, 7 Mar 2023 12:54:50 +0000 Subject: docs/devel: Document VFIO device dirty page tracking MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adjust the VFIO dirty page tracking documentation and add a section to describe device dirty page tracking. Signed-off-by: Avihai Horon Signed-off-by: Joao Martins Reviewed-by: Cédric Le Goater Link: https://lore.kernel.org/r/20230307125450.62409-16-joao.m.martins@oracle.com Signed-off-by: Alex Williamson --- docs/devel/vfio-migration.rst | 46 +++++++++++++++++++++++++++++-------------- 1 file changed, 31 insertions(+), 15 deletions(-) diff --git a/docs/devel/vfio-migration.rst b/docs/devel/vfio-migration.rst index c214c73e28..1b68ccf115 100644 --- a/docs/devel/vfio-migration.rst +++ b/docs/devel/vfio-migration.rst @@ -59,22 +59,37 @@ System memory dirty pages tracking ---------------------------------- A ``log_global_start`` and ``log_global_stop`` memory listener callback informs -the VFIO IOMMU module to start and stop dirty page tracking. A ``log_sync`` -memory listener callback marks those system memory pages as dirty which are -used for DMA by the VFIO device. The dirty pages bitmap is queried per -container. All pages pinned by the vendor driver through external APIs have to -be marked as dirty during migration. When there are CPU writes, CPU dirty page -tracking can identify dirtied pages, but any page pinned by the vendor driver -can also be written by the device. There is currently no device or IOMMU -support for dirty page tracking in hardware. +the VFIO dirty tracking module to start and stop dirty page tracking. A +``log_sync`` memory listener callback queries the dirty page bitmap from the +dirty tracking module and marks system memory pages which were DMA-ed by the +VFIO device as dirty. The dirty page bitmap is queried per container. + +Currently there are two ways dirty page tracking can be done: +(1) Device dirty tracking: +In this method the device is responsible to log and report its DMAs. This +method can be used only if the device is capable of tracking its DMAs. +Discovering device capability, starting and stopping dirty tracking, and +syncing the dirty bitmaps from the device are done using the DMA logging uAPI. +More info about the uAPI can be found in the comments of the +``vfio_device_feature_dma_logging_control`` and +``vfio_device_feature_dma_logging_report`` structures in the header file +linux-headers/linux/vfio.h. + +(2) VFIO IOMMU module: +In this method dirty tracking is done by IOMMU. However, there is currently no +IOMMU support for dirty page tracking. For this reason, all pages are +perpetually marked dirty, unless the device driver pins pages through external +APIs in which case only those pinned pages are perpetually marked dirty. + +If the above two methods are not supported, all pages are perpetually marked +dirty by QEMU. By default, dirty pages are tracked during pre-copy as well as stop-and-copy -phase. So, a page pinned by the vendor driver will be copied to the destination -in both phases. Copying dirty pages in pre-copy phase helps QEMU to predict if -it can achieve its downtime tolerances. If QEMU during pre-copy phase keeps -finding dirty pages continuously, then it understands that even in stop-and-copy -phase, it is likely to find dirty pages and can predict the downtime -accordingly. +phase. So, a page marked as dirty will be copied to the destination in both +phases. Copying dirty pages in pre-copy phase helps QEMU to predict if it can +achieve its downtime tolerances. If QEMU during pre-copy phase keeps finding +dirty pages continuously, then it understands that even in stop-and-copy phase, +it is likely to find dirty pages and can predict the downtime accordingly. QEMU also provides a per device opt-out option ``pre-copy-dirty-page-tracking`` which disables querying the dirty bitmap during pre-copy phase. If it is set to @@ -89,7 +104,8 @@ phase of migration. In that case, the unmap ioctl returns any dirty pages in that range and QEMU reports corresponding guest physical pages dirty. During stop-and-copy phase, an IOMMU notifier is used to get a callback for mapped pages and then dirty pages bitmap is fetched from VFIO IOMMU modules for those -mapped ranges. +mapped ranges. If device dirty tracking is enabled with vIOMMU, live migration +will be blocked. Flow of state changes during Live migration =========================================== -- cgit v1.2.3 From 8249cffc626d0661d6c109aa0653cd9bb67cd676 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 7 Mar 2023 09:53:46 -0700 Subject: vfio/migration: Rename entry points MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Pick names that align with the section drivers should use them from, avoiding the confusion of calling a _finalize() function from _exit() and generalizing the actual _finalize() to handle removing the viommu blocker. Reviewed-by: Cédric Le Goater Reviewed-by: Joao Martins Link: https://lore.kernel.org/r/167820912978.606734.12740287349119694623.stgit@omen Signed-off-by: Alex Williamson --- hw/vfio/common.c | 2 +- hw/vfio/migration.c | 8 ++++---- hw/vfio/pci.c | 6 +++--- include/hw/vfio/vfio-common.h | 6 +++--- 4 files changed, 11 insertions(+), 11 deletions(-) diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 539246e332..4d01ea3515 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -447,7 +447,7 @@ int vfio_block_giommu_migration(Error **errp) return ret; } -void vfio_unblock_giommu_migration(void) +void vfio_migration_finalize(void) { if (!giommu_migration_blocker || vfio_viommu_preset()) { diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c index 5d1e66f691..1a1a8659c8 100644 --- a/hw/vfio/migration.c +++ b/hw/vfio/migration.c @@ -521,7 +521,7 @@ static void vfio_migration_state_notifier(Notifier *notifier, void *data) } } -static void vfio_migration_exit(VFIODevice *vbasedev) +static void vfio_migration_free(VFIODevice *vbasedev) { g_free(vbasedev->migration); vbasedev->migration = NULL; @@ -631,7 +631,7 @@ int64_t vfio_mig_bytes_transferred(void) return bytes_transferred; } -int vfio_migration_probe(VFIODevice *vbasedev, Error **errp) +int vfio_migration_realize(VFIODevice *vbasedev, Error **errp) { int ret = -ENOTSUP; @@ -669,7 +669,7 @@ add_blocker: return ret; } -void vfio_migration_finalize(VFIODevice *vbasedev) +void vfio_migration_exit(VFIODevice *vbasedev) { if (vbasedev->migration) { VFIOMigration *migration = vbasedev->migration; @@ -677,7 +677,7 @@ void vfio_migration_finalize(VFIODevice *vbasedev) remove_migration_state_change_notifier(&migration->migration_state); qemu_del_vm_change_state_handler(migration->vm_state); unregister_savevm(VMSTATE_IF(vbasedev->dev), "vfio", vbasedev); - vfio_migration_exit(vbasedev); + vfio_migration_free(vbasedev); vfio_unblock_multiple_devices_migration(); } diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 30a271eab3..ec9a854361 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -3145,7 +3145,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) } if (!pdev->failover_pair_id) { - ret = vfio_migration_probe(vbasedev, errp); + ret = vfio_migration_realize(vbasedev, errp); if (ret) { error_report("%s: Migration disabled", vbasedev->name); } @@ -3185,7 +3185,7 @@ static void vfio_instance_finalize(Object *obj) */ vfio_put_device(vdev); vfio_put_group(group); - vfio_unblock_giommu_migration(); + vfio_migration_finalize(); } static void vfio_exitfn(PCIDevice *pdev) @@ -3204,7 +3204,7 @@ static void vfio_exitfn(PCIDevice *pdev) } vfio_teardown_msi(vdev); vfio_bars_exit(vdev); - vfio_migration_finalize(&vdev->vbasedev); + vfio_migration_exit(&vdev->vbasedev); } static void vfio_pci_reset(DeviceState *dev) diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index 009bec34c4..eed244f25f 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -223,7 +223,6 @@ bool vfio_mig_active(void); int vfio_block_multiple_devices_migration(Error **errp); void vfio_unblock_multiple_devices_migration(void); int vfio_block_giommu_migration(Error **errp); -void vfio_unblock_giommu_migration(void); int64_t vfio_mig_bytes_transferred(void); #ifdef CONFIG_LINUX @@ -247,7 +246,8 @@ int vfio_spapr_create_window(VFIOContainer *container, int vfio_spapr_remove_window(VFIOContainer *container, hwaddr offset_within_address_space); -int vfio_migration_probe(VFIODevice *vbasedev, Error **errp); -void vfio_migration_finalize(VFIODevice *vbasedev); +int vfio_migration_realize(VFIODevice *vbasedev, Error **errp); +void vfio_migration_exit(VFIODevice *vbasedev); +void vfio_migration_finalize(void); #endif /* HW_VFIO_VFIO_COMMON_H */ -- cgit v1.2.3 From 969dae5448eaa2914be5b974f9e0311b3f95ee2c Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?C=C3=A9dric=20Le=20Goater?= Date: Fri, 3 Mar 2023 08:43:30 +0100 Subject: vfio: Fix vfio_get_dev_region() trace event MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Simply transpose 'x8' to fix the typo and remove the ending '8' Fixes: e61a424f05 ("vfio: Create device specific region info helper") Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1526 Signed-off-by: Cédric Le Goater Reviewed-by: Philippe Mathieu-Daudé Link: https://lore.kernel.org/r/20230303074330.2609377-1-clg@kaod.org [aw: commit log s/revert/transpose/] Signed-off-by: Alex Williamson --- hw/vfio/trace-events | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index bee95dbd97..646e42fd27 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -118,7 +118,7 @@ vfio_region_mmaps_set_enabled(const char *name, bool enabled) "Region %s mmaps e vfio_region_unmap(const char *name, unsigned long offset, unsigned long end) "Region %s unmap [0x%lx - 0x%lx]" vfio_region_sparse_mmap_header(const char *name, int index, int nr_areas) "Device %s region %d: %d sparse mmap entries" vfio_region_sparse_mmap_entry(int i, unsigned long start, unsigned long end) "sparse entry %d [0x%lx - 0x%lx]" -vfio_get_dev_region(const char *name, int index, uint32_t type, uint32_t subtype) "%s index %d, %08x/%0x8" +vfio_get_dev_region(const char *name, int index, uint32_t type, uint32_t subtype) "%s index %d, %08x/%08x" vfio_dma_unmap_overflow_workaround(void) "" vfio_get_dirty_bitmap(int fd, uint64_t iova, uint64_t size, uint64_t bitmap_size, uint64_t start) "container fd=%d, iova=0x%"PRIx64" size= 0x%"PRIx64" bitmap_size=0x%"PRIx64" start=0x%"PRIx64 vfio_iommu_map_dirty_notify(uint64_t iova_start, uint64_t iova_end) "iommu dirty @ 0x%"PRIx64" - 0x%"PRIx64 -- cgit v1.2.3