diff options
-rw-r--r-- | hw/vfio/common.c | 57 | ||||
-rw-r--r-- | hw/vfio/container-base.c | 12 | ||||
-rw-r--r-- | hw/vfio/container.c | 2 | ||||
-rw-r--r-- | hw/vfio/igd.c | 262 | ||||
-rw-r--r-- | include/hw/vfio/vfio-common.h | 6 | ||||
-rw-r--r-- | include/hw/vfio/vfio-container-base.h | 1 | ||||
-rw-r--r-- | include/migration/misc.h | 2 | ||||
-rw-r--r-- | migration/migration.c | 23 | ||||
-rw-r--r-- | system/dirtylimit.c | 3 |
9 files changed, 214 insertions, 154 deletions
diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 598272f..f7499a9 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -170,11 +170,32 @@ bool vfio_device_state_is_precopy(VFIODevice *vbasedev) migration->device_state == VFIO_DEVICE_STATE_PRE_COPY_P2P; } -static bool vfio_devices_all_dirty_tracking(VFIOContainerBase *bcontainer) +static bool vfio_devices_all_device_dirty_tracking_started( + const VFIOContainerBase *bcontainer) { VFIODevice *vbasedev; - if (!migration_is_active() && !migration_is_device()) { + QLIST_FOREACH(vbasedev, &bcontainer->device_list, container_next) { + if (!vbasedev->dirty_tracking) { + return false; + } + } + + return true; +} + +bool vfio_devices_all_dirty_tracking_started( + const VFIOContainerBase *bcontainer) +{ + return vfio_devices_all_device_dirty_tracking_started(bcontainer) || + bcontainer->dirty_pages_started; +} + +static bool vfio_log_sync_needed(const VFIOContainerBase *bcontainer) +{ + VFIODevice *vbasedev; + + if (!vfio_devices_all_dirty_tracking_started(bcontainer)) { return false; } @@ -210,36 +231,6 @@ bool vfio_devices_all_device_dirty_tracking(const VFIOContainerBase *bcontainer) 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. - */ -bool -vfio_devices_all_running_and_mig_active(const VFIOContainerBase *bcontainer) -{ - VFIODevice *vbasedev; - - if (!migration_is_active()) { - return false; - } - - QLIST_FOREACH(vbasedev, &bcontainer->device_list, container_next) { - VFIOMigration *migration = vbasedev->migration; - - if (!migration) { - return false; - } - - if (vfio_device_state_is_running(vbasedev) || - vfio_device_state_is_precopy(vbasedev)) { - continue; - } else { - return false; - } - } - return true; -} - static bool vfio_listener_skipped_section(MemoryRegionSection *section) { return (!memory_region_is_ram(section->mr) && @@ -1373,7 +1364,7 @@ static void vfio_listener_log_sync(MemoryListener *listener, return; } - if (vfio_devices_all_dirty_tracking(bcontainer)) { + if (vfio_log_sync_needed(bcontainer)) { ret = vfio_sync_dirty_bitmap(bcontainer, section, &local_err); if (ret) { error_report_err(local_err); diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c index 6f86c37..749a3fd 100644 --- a/hw/vfio/container-base.c +++ b/hw/vfio/container-base.c @@ -64,13 +64,23 @@ int vfio_container_set_dirty_page_tracking(VFIOContainerBase *bcontainer, bool start, Error **errp) { VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer); + int ret; if (!bcontainer->dirty_pages_supported) { return 0; } g_assert(vioc->set_dirty_page_tracking); - return vioc->set_dirty_page_tracking(bcontainer, start, errp); + if (bcontainer->dirty_pages_started == start) { + return 0; + } + + ret = vioc->set_dirty_page_tracking(bcontainer, start, errp); + if (!ret) { + bcontainer->dirty_pages_started = start; + } + + return ret; } int vfio_container_query_dirty_bitmap(const VFIOContainerBase *bcontainer, diff --git a/hw/vfio/container.c b/hw/vfio/container.c index 78a3c2d..4ebb526 100644 --- a/hw/vfio/container.c +++ b/hw/vfio/container.c @@ -131,7 +131,7 @@ static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer, int ret; Error *local_err = NULL; - if (iotlb && vfio_devices_all_running_and_mig_active(bcontainer)) { + if (iotlb && vfio_devices_all_dirty_tracking_started(bcontainer)) { if (!vfio_devices_all_device_dirty_tracking(bcontainer) && bcontainer->dirty_pages_supported) { return vfio_dma_unmap_bitmap(container, iova, size, iotlb); diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c index 4047f4f..0740a5d 100644 --- a/hw/vfio/igd.c +++ b/hw/vfio/igd.c @@ -14,6 +14,7 @@ #include "qemu/units.h" #include "qemu/error-report.h" #include "qapi/error.h" +#include "qapi/qmp/qerror.h" #include "hw/hw.h" #include "hw/nvram/fw_cfg.h" #include "pci.h" @@ -59,43 +60,41 @@ */ static int igd_gen(VFIOPCIDevice *vdev) { - if ((vdev->device_id & 0xfff) == 0xa84) { - return 8; /* Broxton */ + /* + * Device IDs for Broxton/Apollo Lake are 0x0a84, 0x1a84, 0x1a85, 0x5a84 + * and 0x5a85, match bit 11:1 here + * Prefix 0x0a is taken by Haswell, this rule should be matched first. + */ + if ((vdev->device_id & 0xffe) == 0xa84) { + return 9; } switch (vdev->device_id & 0xff00) { - /* Old, untested, unavailable, unknown */ - case 0x0000: - case 0x2500: - case 0x2700: - case 0x2900: - case 0x2a00: - case 0x2e00: - case 0x3500: - case 0xa000: - return -1; - /* SandyBridge, IvyBridge, ValleyView, Haswell */ - case 0x0100: - case 0x0400: - case 0x0a00: - case 0x0c00: - case 0x0d00: - case 0x0f00: + case 0x0100: /* SandyBridge, IvyBridge */ return 6; - /* BroadWell, CherryView, SkyLake, KabyLake */ - case 0x1600: - case 0x1900: - case 0x2200: - case 0x5900: + case 0x0400: /* Haswell */ + case 0x0a00: /* Haswell */ + case 0x0c00: /* Haswell */ + case 0x0d00: /* Haswell */ + case 0x0f00: /* Valleyview/Bay Trail */ + return 7; + case 0x1600: /* Broadwell */ + case 0x2200: /* Cherryview */ return 8; - /* CoffeeLake */ - case 0x3e00: + case 0x1900: /* Skylake */ + case 0x3100: /* Gemini Lake */ + case 0x5900: /* Kaby Lake */ + case 0x3e00: /* Coffee Lake */ + case 0x9B00: /* Comet Lake */ return 9; - /* ElkhartLake */ - case 0x4500: + case 0x8A00: /* Ice Lake */ + case 0x4500: /* Elkhart Lake */ + case 0x4E00: /* Jasper Lake */ return 11; - /* TigerLake */ - case 0x9A00: + case 0x9A00: /* Tiger Lake */ + case 0x4C00: /* Rocket Lake */ + case 0x4600: /* Alder Lake */ + case 0xA700: /* Raptor Lake */ return 12; } @@ -116,6 +115,53 @@ typedef struct VFIOIGDQuirk { #define IGD_BDSM 0x5c /* Base Data of Stolen Memory */ #define IGD_BDSM_GEN11 0xc0 /* Base Data of Stolen Memory of gen 11 and later */ +#define IGD_GMCH_GEN6_GMS_SHIFT 3 /* SNB_GMCH in i915 */ +#define IGD_GMCH_GEN6_GMS_MASK 0x1f +#define IGD_GMCH_GEN6_GGMS_SHIFT 8 +#define IGD_GMCH_GEN6_GGMS_MASK 0x3 +#define IGD_GMCH_GEN8_GMS_SHIFT 8 /* BDW_GMCH in i915 */ +#define IGD_GMCH_GEN8_GMS_MASK 0xff +#define IGD_GMCH_GEN8_GGMS_SHIFT 6 +#define IGD_GMCH_GEN8_GGMS_MASK 0x3 + +static uint64_t igd_gtt_memory_size(int gen, uint16_t gmch) +{ + uint64_t ggms; + + if (gen < 8) { + ggms = (gmch >> IGD_GMCH_GEN6_GGMS_SHIFT) & IGD_GMCH_GEN6_GGMS_MASK; + } else { + ggms = (gmch >> IGD_GMCH_GEN8_GGMS_SHIFT) & IGD_GMCH_GEN8_GGMS_MASK; + if (ggms != 0) { + ggms = 1 << ggms; + } + } + + return ggms * MiB; +} + +static uint64_t igd_stolen_memory_size(int gen, uint32_t gmch) +{ + uint64_t gms; + + if (gen < 8) { + gms = (gmch >> IGD_GMCH_GEN6_GMS_SHIFT) & IGD_GMCH_GEN6_GMS_MASK; + } else { + gms = (gmch >> IGD_GMCH_GEN8_GMS_SHIFT) & IGD_GMCH_GEN8_GMS_MASK; + } + + if (gen < 9) { + return gms * 32 * MiB; + } else { + if (gms < 0xf0) { + return gms * 32 * MiB; + } else { + return (gms - 0xf0 + 1) * 4 * MiB; + } + } + + return 0; +} /* * The rather short list of registers that we copy from the host devices. @@ -264,17 +310,10 @@ static int vfio_pci_igd_lpc_init(VFIOPCIDevice *vdev, static int vfio_igd_gtt_max(VFIOPCIDevice *vdev) { uint32_t gmch = vfio_pci_read_config(&vdev->pdev, IGD_GMCH, sizeof(gmch)); - int ggms, gen = igd_gen(vdev); - - gmch = vfio_pci_read_config(&vdev->pdev, IGD_GMCH, sizeof(gmch)); - ggms = (gmch >> (gen < 8 ? 8 : 6)) & 0x3; - if (gen > 6) { - ggms = 1 << ggms; - } - - ggms *= MiB; + int gen = igd_gen(vdev); + uint64_t ggms_size = igd_gtt_memory_size(gen, gmch); - return (ggms / (4 * KiB)) * (gen < 8 ? 4 : 8); + return (ggms_size / (4 * KiB)) * (gen < 8 ? 4 : 8); } /* @@ -383,16 +422,9 @@ static const MemoryRegionOps vfio_igd_index_quirk = { .endianness = DEVICE_LITTLE_ENDIAN, }; -#define IGD_BDSM_MMIO_OFFSET 0x1080C0 - -static uint64_t vfio_igd_quirk_bdsm_read(void *opaque, - hwaddr addr, unsigned size) +static uint64_t vfio_igd_pci_config_read(VFIOPCIDevice *vdev, uint64_t offset, + unsigned size) { - VFIOPCIDevice *vdev = opaque; - uint64_t offset; - - offset = IGD_BDSM_GEN11 + addr; - switch (size) { case 1: return pci_get_byte(vdev->pdev.config + offset); @@ -403,21 +435,17 @@ static uint64_t vfio_igd_quirk_bdsm_read(void *opaque, case 8: return pci_get_quad(vdev->pdev.config + offset); default: - hw_error("igd: unsupported read size, %u bytes", size); + hw_error("igd: unsupported pci config read at %"PRIx64", size %u", + offset, size); break; } return 0; } -static void vfio_igd_quirk_bdsm_write(void *opaque, hwaddr addr, - uint64_t data, unsigned size) +static void vfio_igd_pci_config_write(VFIOPCIDevice *vdev, uint64_t offset, + uint64_t data, unsigned size) { - VFIOPCIDevice *vdev = opaque; - uint64_t offset; - - offset = IGD_BDSM_GEN11 + addr; - switch (size) { case 1: pci_set_byte(vdev->pdev.config + offset, data); @@ -432,17 +460,42 @@ static void vfio_igd_quirk_bdsm_write(void *opaque, hwaddr addr, pci_set_quad(vdev->pdev.config + offset, data); break; default: - hw_error("igd: unsupported read size, %u bytes", size); + hw_error("igd: unsupported pci config write at %"PRIx64", size %u", + offset, size); break; } } -static const MemoryRegionOps vfio_igd_bdsm_quirk = { - .read = vfio_igd_quirk_bdsm_read, - .write = vfio_igd_quirk_bdsm_write, - .endianness = DEVICE_LITTLE_ENDIAN, +#define VFIO_IGD_QUIRK_MIRROR_REG(reg, name) \ +static uint64_t vfio_igd_quirk_read_##name(void *opaque, \ + hwaddr addr, unsigned size) \ +{ \ + VFIOPCIDevice *vdev = opaque; \ + \ + return vfio_igd_pci_config_read(vdev, reg + addr, size); \ +} \ + \ +static void vfio_igd_quirk_write_##name(void *opaque, hwaddr addr, \ + uint64_t data, unsigned size) \ +{ \ + VFIOPCIDevice *vdev = opaque; \ + \ + vfio_igd_pci_config_write(vdev, reg + addr, data, size); \ +} \ + \ +static const MemoryRegionOps vfio_igd_quirk_mirror_##name = { \ + .read = vfio_igd_quirk_read_##name, \ + .write = vfio_igd_quirk_write_##name, \ + .endianness = DEVICE_LITTLE_ENDIAN, \ }; +VFIO_IGD_QUIRK_MIRROR_REG(IGD_GMCH, ggc) +VFIO_IGD_QUIRK_MIRROR_REG(IGD_BDSM, bdsm) +VFIO_IGD_QUIRK_MIRROR_REG(IGD_BDSM_GEN11, bdsm64) + +#define IGD_GGC_MMIO_OFFSET 0x108040 +#define IGD_BDSM_MMIO_OFFSET 0x1080C0 + void vfio_probe_igd_bar0_quirk(VFIOPCIDevice *vdev, int nr) { VFIOQuirk *quirk; @@ -465,44 +518,37 @@ void vfio_probe_igd_bar0_quirk(VFIOPCIDevice *vdev, int nr) * into MMIO space and read from MMIO space by the Windows driver. */ gen = igd_gen(vdev); - if (gen < 11) { + if (gen < 6) { return; } - quirk = vfio_quirk_alloc(1); + quirk = vfio_quirk_alloc(2); quirk->data = vdev; - memory_region_init_io(&quirk->mem[0], OBJECT(vdev), &vfio_igd_bdsm_quirk, - vdev, "vfio-igd-bdsm-quirk", 8); + memory_region_init_io(&quirk->mem[0], OBJECT(vdev), + &vfio_igd_quirk_mirror_ggc, vdev, + "vfio-igd-ggc-quirk", 2); memory_region_add_subregion_overlap(vdev->bars[0].region.mem, - IGD_BDSM_MMIO_OFFSET, &quirk->mem[0], + IGD_GGC_MMIO_OFFSET, &quirk->mem[0], 1); - QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next); -} - -static int igd_get_stolen_mb(int gen, uint32_t gmch) -{ - int gms; - - if (gen < 8) { - gms = (gmch >> 3) & 0x1f; + if (gen < 11) { + memory_region_init_io(&quirk->mem[1], OBJECT(vdev), + &vfio_igd_quirk_mirror_bdsm, vdev, + "vfio-igd-bdsm-quirk", 4); + memory_region_add_subregion_overlap(vdev->bars[0].region.mem, + IGD_BDSM_MMIO_OFFSET, + &quirk->mem[1], 1); } else { - gms = (gmch >> 8) & 0xff; + memory_region_init_io(&quirk->mem[1], OBJECT(vdev), + &vfio_igd_quirk_mirror_bdsm64, vdev, + "vfio-igd-bdsm-quirk", 8); + memory_region_add_subregion_overlap(vdev->bars[0].region.mem, + IGD_BDSM_MMIO_OFFSET, + &quirk->mem[1], 1); } - if (gen < 9) { - if (gms > 0x10) { - error_report("Unsupported IGD GMS value 0x%x", gms); - return 0; - } - return gms * 32; - } else { - if (gms < 0xf0) - return gms * 32; - else - return (gms - 0xf0) * 4 + 4; - } + QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next); } void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr) @@ -514,7 +560,8 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr) VFIOQuirk *quirk; VFIOIGDQuirk *igd; PCIDevice *lpc_bridge; - int i, ret, ggms_mb, gms_mb = 0, gen; + int i, ret, gen; + uint64_t ggms_size, gms_size; uint64_t *bdsm_size; uint32_t gmch; uint16_t cmd_orig, cmd; @@ -676,13 +723,33 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr) QLIST_INSERT_HEAD(&vdev->bars[nr].quirks, quirk, next); - /* Determine the size of stolen memory needed for GTT */ - ggms_mb = (gmch >> (gen < 8 ? 8 : 6)) & 0x3; - if (gen > 6) { - ggms_mb = 1 << ggms_mb; + /* + * Allow user to override dsm size using x-igd-gms option, in multiples of + * 32MiB. This option should only be used when the desired size cannot be + * set from DVMT Pre-Allocated option in host BIOS. + */ + if (vdev->igd_gms) { + if (gen < 8) { + if (vdev->igd_gms <= 0x10) { + gmch &= ~(IGD_GMCH_GEN6_GMS_MASK << IGD_GMCH_GEN6_GMS_SHIFT); + gmch |= vdev->igd_gms << IGD_GMCH_GEN6_GMS_SHIFT; + } else { + error_report(QERR_INVALID_PARAMETER_VALUE, + "x-igd-gms", "0~0x10"); + } + } else { + if (vdev->igd_gms <= 0x40) { + gmch &= ~(IGD_GMCH_GEN8_GMS_MASK << IGD_GMCH_GEN8_GMS_SHIFT); + gmch |= vdev->igd_gms << IGD_GMCH_GEN8_GMS_SHIFT; + } else { + error_report(QERR_INVALID_PARAMETER_VALUE, + "x-igd-gms", "0~0x40"); + } + } } - gms_mb = igd_get_stolen_mb(gen, gmch); + ggms_size = igd_gtt_memory_size(gen, gmch); + gms_size = igd_stolen_memory_size(gen, gmch); /* * Request reserved memory for stolen memory via fw_cfg. VM firmware @@ -693,7 +760,7 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr) * config offset 0x5C. */ bdsm_size = g_malloc(sizeof(*bdsm_size)); - *bdsm_size = cpu_to_le64((ggms_mb + gms_mb) * MiB); + *bdsm_size = cpu_to_le64(ggms_size + gms_size); fw_cfg_add_file(fw_cfg_find(), "etc/igd-bdsm-size", bdsm_size, sizeof(*bdsm_size)); @@ -744,5 +811,6 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr) vdev->vbasedev.name); } - trace_vfio_pci_igd_bdsm_enabled(vdev->vbasedev.name, ggms_mb + gms_mb); + trace_vfio_pci_igd_bdsm_enabled(vdev->vbasedev.name, + (ggms_size + gms_size) / MiB); } diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index d571118..0c60be5 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -143,7 +143,7 @@ typedef struct VFIODevice { OnOffAuto pre_copy_dirty_page_tracking; OnOffAuto device_dirty_page_tracking; bool dirty_pages_supported; - bool dirty_tracking; + bool dirty_tracking; /* Protected by BQL */ bool iommu_dirty_tracking; HostIOMMUDevice *hiod; int devid; @@ -296,8 +296,8 @@ bool vfio_migration_realize(VFIODevice *vbasedev, Error **errp); void vfio_migration_exit(VFIODevice *vbasedev); int vfio_bitmap_alloc(VFIOBitmap *vbmap, hwaddr size); -bool -vfio_devices_all_running_and_mig_active(const VFIOContainerBase *bcontainer); +bool vfio_devices_all_dirty_tracking_started( + const VFIOContainerBase *bcontainer); bool vfio_devices_all_device_dirty_tracking(const VFIOContainerBase *bcontainer); int vfio_devices_query_dirty_bitmap(const VFIOContainerBase *bcontainer, diff --git a/include/hw/vfio/vfio-container-base.h b/include/hw/vfio/vfio-container-base.h index 62a8b60..4cff994 100644 --- a/include/hw/vfio/vfio-container-base.h +++ b/include/hw/vfio/vfio-container-base.h @@ -44,6 +44,7 @@ typedef struct VFIOContainerBase { unsigned long pgsizes; unsigned int dma_max_mappings; bool dirty_pages_supported; + bool dirty_pages_started; /* Protected by BQL */ QLIST_HEAD(, VFIOGuestIOMMU) giommu_list; QLIST_HEAD(, VFIORamDiscardListener) vrdl_list; QLIST_ENTRY(VFIOContainerBase) next; diff --git a/include/migration/misc.h b/include/migration/misc.h index 804eb23..c0e23fd 100644 --- a/include/migration/misc.h +++ b/include/migration/misc.h @@ -53,8 +53,6 @@ void dump_vmstate_json_to_file(FILE *out_fp); void migration_object_init(void); void migration_shutdown(void); -bool migration_is_active(void); -bool migration_is_device(void); bool migration_is_running(void); bool migration_thread_is_self(void); diff --git a/migration/migration.c b/migration/migration.c index 056a90d..df61ca4 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -1139,6 +1139,14 @@ bool migration_is_running(void) } } +static bool migration_is_active(void) +{ + MigrationState *s = current_migration; + + return (s->state == MIGRATION_STATUS_ACTIVE || + s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE); +} + static bool migrate_show_downtime(MigrationState *s) { return (s->state == MIGRATION_STATUS_COMPLETED) || migration_in_postcopy(); @@ -1637,21 +1645,6 @@ bool migration_in_bg_snapshot(void) return migrate_background_snapshot() && migration_is_running(); } -bool migration_is_active(void) -{ - MigrationState *s = current_migration; - - return (s->state == MIGRATION_STATUS_ACTIVE || - s->state == MIGRATION_STATUS_POSTCOPY_ACTIVE); -} - -bool migration_is_device(void) -{ - MigrationState *s = current_migration; - - return s->state == MIGRATION_STATUS_DEVICE; -} - bool migration_thread_is_self(void) { MigrationState *s = current_migration; diff --git a/system/dirtylimit.c b/system/dirtylimit.c index d94b994..7c07124 100644 --- a/system/dirtylimit.c +++ b/system/dirtylimit.c @@ -80,8 +80,7 @@ static void vcpu_dirty_rate_stat_collect(void) int i = 0; int64_t period = DIRTYLIMIT_CALC_TIME_MS; - if (migrate_dirty_limit() && - migration_is_active()) { + if (migrate_dirty_limit() && migration_is_running()) { period = migrate_vcpu_dirty_limit_period(); } |