vfio-user: introduce vfio-user protocol specification
RFC v5 1/23 vfio-user: introduce vfio-user protocol specification
In reply to a message not in the archiveFrom: Thanos Makatos <[email protected]>
This patch introduces the vfio-user protocol specification (formerly known as VFIO-over-socket), which is designed to allow devices to be emulated outside QEMU, in a separate process. vfio-user reuses the existing VFIO defines, structs and concepts.
It has been earlier discussed as an RFC in:
"RFC: use VFIO over a UNIX domain socket to implement device offloading"
--- docs/devel/index-internals.rst | 1 + docs/devel/vfio-user.rst | 1453 ++++++++++++++++++++++++++++++++++++++++ MAINTAINERS | 6 + 3 files changed, 1460 insertions(+) create mode 100644 docs/devel/vfio-user.rst
docs/devel/index-internals.rst +1 -0
@@ -17,4 +17,5 @@ Details about QEMU's various subsystems including how to add features to them. s390-dasd-ipl tracing vfio-migration + vfio-user writing-monitor-commands
docs/devel/vfio-user.rst new file +1453 -0
1,453 lines not on this page · raw message
MAINTAINERS +6 -0
@@ -1955,6 +1955,12 @@ F: hw/vfio/ap.c F: docs/system/s390x/vfio-ap.rst L: [email protected] +vfio-user +M: John G Johnson <[email protected]> +M: Thanos Makatos <[email protected]> +S: Supported +F: docs/devel/vfio-user.rst + vhost M: Michael S. Tsirkin <[email protected]> S: Supported
Signature · 1 line
1.8.3.1
RFC v5 9/23 vfio-user: define socket send functions
In reply to a message not in the archiveAlso negotiate protocol version with remote server
--- hw/vfio/pci.h | 1 + hw/vfio/user-protocol.h | 41 +++++ hw/vfio/user.h | 2 + hw/vfio/pci.c | 16 ++ hw/vfio/user.c | 414 +++++++++++++++++++++++++++++++++++++++++++++++- 5 files changed, 473 insertions(+), 1 deletion(-)
hw/vfio/pci.h +1 -0
@@ -193,6 +193,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(VFIOUserPCIDevice, VFIO_USER_PCI)struct VFIOUserPCIDevice {VFIOPCIDevice device;char *sock_name; +bool send_queued;/* all sends are queued */ };/* Use uin32_t for vendor & device so PCI_ANY_ID expands and cannot match hw */
hw/vfio/user-protocol.h +41 -0
45 lines not on this page · raw message
hw/vfio/user.h +2 -0
@@ -76,11 +76,13 @@ typedef struct VFIOProxy {/* VFIOProxy flags */ #define VFIO_PROXY_CLIENT 0x1 +#define VFIO_PROXY_FORCE_QUEUED 0x4VFIOProxy *vfio_user_connect_dev (SocketAddress *addr,Error **errp);void vfio_user_disconnect (VFIOProxy *proxy);void vfio_user_set_handler (VFIODevice *vbasedev,void (*handler)(void *opaque,VFIOUserMsg *msg),void *reqarg); +int vfio_user_validate_version (VFIODevice *vbasedev,Error **errp);#endif /* VFIO_USER_H */
hw/vfio/pci.c +16 -0
@@ -3440,12 +3440,27 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp) vbasedev->proxy = proxy;vfio_user_set_handler (vbasedev, vfio_user_pci_process_req, vdev); +if (udev->send_queued) { + proxy->flags |=VFIO_PROXY_FORCE_QUEUED ; + } + +vfio_user_validate_version (vbasedev, &err); +if (err !=NULL ) { +error_propagate (errp, err); + goto error; + } + vbasedev->name =g_strdup_printf ("VFIO user <%s>" , udev->sock_name); vbasedev->dev =DEVICE (vdev); vbasedev->fd =-1 ; vbasedev->type =VFIO_DEVICE_TYPE_PCI ; vbasedev->ops = &vfio_user_pci_ops; +return ; + +error: +vfio_user_disconnect (proxy); +error_prepend (errp,VFIO_MSG_PREFIX , vdev->vbasedev.name); }static void vfio_user_instance_finalize (Object *obj)
@@ -3462,6 +3477,7 @@ static void vfio_user_instance_finalize(Object *obj)static Property vfio_user_pci_dev_properties[] = {DEFINE_PROP_STRING ("socket" , VFIOUserPCIDevice, sock_name), +DEFINE_PROP_BOOL ("x-send-queued" , VFIOUserPCIDevice, send_queued, false),DEFINE_PROP_END_OF_LIST (), };
hw/vfio/user.c +413 -1
455 lines not on this page · raw message
Signature · 1 line
1.8.3.1
RFC v5 18/23 vfio-user: secure DMA support
In reply to a message not in the archiveSecure DMA forces the remote process to use DMA r/w messages instead of directly mapping guest memeory.
--- hw/vfio/pci.h | 1 + hw/vfio/user.h | 1 + hw/vfio/pci.c | 4 ++++ hw/vfio/user.c | 2 +- 4 files changed, 7 insertions(+), 1 deletion(-)
hw/vfio/pci.h +1 -0
@@ -194,6 +194,7 @@ OBJECT_DECLARE_SIMPLE_TYPE(VFIOUserPCIDevice, VFIO_USER_PCI)struct VFIOUserPCIDevice {VFIOPCIDevice device;char *sock_name; +bool secure_dma;/* disable shared mem for DMA */ bool send_queued;/* all sends are queued */ bool no_post;/* all regions write are sync */ };
hw/vfio/user.h +1 -0
@@ -76,6 +76,7 @@ typedef struct VFIOProxy {/* VFIOProxy flags */ #define VFIO_PROXY_CLIENT 0x1 +#define VFIO_PROXY_SECURE 0x2#define VFIO_PROXY_FORCE_QUEUED 0x4#define VFIO_PROXY_NO_POST 0x8
hw/vfio/pci.c +4 -0
@@ -3589,6 +3589,9 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp) vbasedev->proxy = proxy;vfio_user_set_handler (vbasedev, vfio_user_pci_process_req, vdev); +if (udev->secure_dma) { + proxy->flags |=VFIO_PROXY_SECURE ; + }if (udev->send_queued) { proxy->flags |=VFIO_PROXY_FORCE_QUEUED ; }
@@ -3720,6 +3723,7 @@ static void vfio_user_instance_finalize(Object *obj)static Property vfio_user_pci_dev_properties[] = {DEFINE_PROP_STRING ("socket" , VFIOUserPCIDevice, sock_name), +DEFINE_PROP_BOOL ("secure-dma" , VFIOUserPCIDevice, secure_dma, false),DEFINE_PROP_BOOL ("x-send-queued" , VFIOUserPCIDevice, send_queued, false),DEFINE_PROP_BOOL ("x-no-posted-writes" , VFIOUserPCIDevice, no_post, false),DEFINE_PROP_END_OF_LIST (),
hw/vfio/user.c +1 -1
@@ -1528,7 +1528,7 @@ static int vfio_user_io_dma_map(VFIOContainer *container, MemoryRegion *mr,* map->vaddr enters as a QEMU process address * make it either a file offset for mapped areas or 0 */ -if (fd !=-1 ) { +if (fd !=-1 && (container->proxy->flags &VFIO_PROXY_SECURE ) ==0 ) {void *addr = (void *)(uintptr_t )map->vaddr; map->vaddr =qemu_ram_block_host_offset (mr->ram_block, addr);
Signature · 1 line
1.8.3.1
RFC v5 8/23 vfio-user: define socket receive functions
In reply to a message not in the archiveAdd infrastructure needed to receive incoming messages
--- hw/vfio/user-protocol.h | 54 +++++++ hw/vfio/user.h | 8 + hw/vfio/pci.c | 6 + hw/vfio/user.c | 404 ++++++++++++++++++++++++++++++++++++++++++++++++ MAINTAINERS | 1 + 5 files changed, 473 insertions(+) create mode 100644 hw/vfio/user-protocol.h
hw/vfio/user-protocol.h new file +54 -0
@@ -0,0 +1,54 @@ +#ifndef VFIO_USER_PROTOCOL_H +#define VFIO_USER_PROTOCOL_H + +/* +* vfio protocol over a UNIX socket. +* +* Copyright © 2018, 2021 Oracle and/or its affiliates. +* +* This work is licensed under the terms of the GNU GPL, version 2. See +* the COPYING file in the top-level directory. +* +* Each message has a standard header that describes the command +* being sent, which is almost always a VFIO ioctl(). +* +* The header may be followed by command-specific data, such as the +* region and offset info for read and write commands. +*/ + +typedef struct { +uint16_t id; +uint16_t command; +uint32_t size; +uint32_t flags; +uint32_t error_reply; +}VFIOUserHdr ; + +/* VFIOUserHdr commands */ +enum vfio_user_command { +VFIO_USER_VERSION =1 , +VFIO_USER_DMA_MAP =2 , +VFIO_USER_DMA_UNMAP =3 , +VFIO_USER_DEVICE_GET_INFO =4 , +VFIO_USER_DEVICE_GET_REGION_INFO =5 , +VFIO_USER_DEVICE_GET_REGION_IO_FDS =6 , +VFIO_USER_DEVICE_GET_IRQ_INFO =7 , +VFIO_USER_DEVICE_SET_IRQS =8 , +VFIO_USER_REGION_READ =9 , +VFIO_USER_REGION_WRITE =10 , +VFIO_USER_DMA_READ =11 , +VFIO_USER_DMA_WRITE =12 , +VFIO_USER_DEVICE_RESET =13 , +VFIO_USER_DIRTY_PAGES =14 , +VFIO_USER_MAX , +}; + +/* VFIOUserHdr flags */ +#define VFIO_USER_REQUEST 0x0 +#define VFIO_USER_REPLY 0x1 +#define VFIO_USER_TYPE 0xF + +#define VFIO_USER_NO_REPLY 0x10 +#define VFIO_USER_ERROR 0x20 + +#endif /* VFIO_USER_PROTOCOL_H */
hw/vfio/user.h +8 -0
@@ -11,6 +11,8 @@* */ +#include "user-protocol.h" + typedef struct { int send_fds; int recv_fds;
@@ -27,6 +29,7 @@ enum msg_type { typedef struct VFIOUserMsg { QTAILQ_ENTRY(VFIOUserMsg) next; + VFIOUserHdr *hdr; VFIOUserFDs *fds; uint32_t rsize; uint32_t id;
@@ -66,6 +69,8 @@ typedef struct VFIOProxy {VFIOUserMsgQ incoming;VFIOUserMsgQ outgoing;VFIOUserMsg *last_nowait; +VFIOUserMsg *part_recv; +size_t recv_left;enum proxy_state state; } VFIOProxy;
@@ -74,5 +79,8 @@ typedef struct VFIOProxy {VFIOProxy *vfio_user_connect_dev (SocketAddress *addr,Error **errp);void vfio_user_disconnect (VFIOProxy *proxy); +void vfio_user_set_handler (VFIODevice *vbasedev, +void (*handler)(void *opaque,VFIOUserMsg *msg), +void *reqarg);#endif /* VFIO_USER_H */
hw/vfio/pci.c +6 -0
@@ -3387,6 +3387,11 @@ type_init(register_vfio_pci_dev_type)* vfio-user routines. */ +static void vfio_user_pci_process_req (void *opaque,VFIOUserMsg *msg) +{ + +} +/* * Emulated devices don't use host hot reset */
@@ -3433,6 +3438,7 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)return ; } vbasedev->proxy = proxy; +vfio_user_set_handler (vbasedev, vfio_user_pci_process_req, vdev); vbasedev->name =g_strdup_printf ("VFIO user <%s>" , udev->sock_name); vbasedev->dev =DEVICE (vdev);
hw/vfio/user.c +404 -0
448 lines not on this page · raw message
MAINTAINERS +1 -0
@@ -1964,6 +1964,7 @@ S: Supported F: docs/devel/vfio-user.rst F: hw/vfio/user.c F: hw/vfio/user.h +F: hw/vfio/user-protocol.h vhost M: Michael S. Tsirkin <[email protected]>
Signature · 1 line
1.8.3.1
RFC v5 15/23 vfio-user: get and set IRQs
In reply to a message not in the archive--- hw/vfio/user-protocol.h | 25 +++++++++ hw/vfio/pci.c | 9 +++- hw/vfio/user.c | 131 ++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 163 insertions(+), 2 deletions(-)
hw/vfio/user-protocol.h +25 -0
@@ -121,6 +121,31 @@ typedef struct { } VFIOUserRegionInfo;/* +* VFIO_USER_DEVICE_GET_IRQ_INFO +* imported from struct vfio_irq_info +*/ +typedef struct { +VFIOUserHdr hdr; +uint32_t argsz; +uint32_t flags; +uint32_t index; +uint32_t count; +}VFIOUserIRQInfo ; + +/* +* VFIO_USER_DEVICE_SET_IRQS +* imported from struct vfio_irq_set +*/ +typedef struct { +VFIOUserHdr hdr; +uint32_t argsz; +uint32_t flags; +uint32_t index; +uint32_t start; +uint32_t count; +}VFIOUserIRQSet ; + +/* * VFIO_USER_REGION_READ * VFIO_USER_REGION_WRITE */
hw/vfio/pci.c +7 -2
@@ -517,7 +517,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, vdev->nr_vectors = nr +1 ; ret =vfio_enable_vectors (vdev, true);if (ret) { -error_report ("vfio: failed to enable vectors, %d" , ret); +error_report ("vfio: failed to enable vectors, %s" ,strerror (-ret)); } }else {Error *err =NULL ;
@@ -662,7 +662,8 @@ retry: ret =vfio_enable_vectors (vdev, false);if (ret) {if (ret <0 ) { -error_report ("vfio: Error: Failed to setup MSI fds: %m" ); +error_report ("vfio: Error: Failed to setup MSI fds: %s" , +strerror (-ret)); }else if (ret != vdev->nr_vectors) {error_report ("vfio: Error: Failed to enable %d " "MSI vectors, retry with %d" , vdev->nr_vectors, ret);
@@ -2669,6 +2670,7 @@ static void vfio_populate_device(VFIOPCIDevice *vdev, Error **errp) irq_info.index =VFIO_PCI_ERR_IRQ_INDEX ; ret =VDEV_GET_IRQ_INFO (vbasedev, &irq_info); +if (ret) {/* This can fail for an old kernel or legacy PCI dev */ trace_vfio_populate_device_get_irq_info_failure (strerror (errno));
@@ -3662,6 +3664,9 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp) goto out_teardown; } +vfio_register_err_notifier (vdev); +vfio_register_req_notifier (vdev); +return ; out_teardown:
hw/vfio/user.c +131 -0
149 lines not on this page · raw message
Signature · 1 line
1.8.3.1
RFC v5 4/23 vfio-user: add region cache
In reply to a message not in the archivecache VFIO_DEVICE_GET_REGION_INFO results to reduce memory alloc/free cycles and as prep work for vfio-user
--- include/hw/vfio/vfio-common.h | 2 ++ hw/vfio/ccw.c | 5 ----- hw/vfio/common.c | 41 +++++++++++++++++++++++++++++++++++------ hw/vfio/igd.c | 23 +++++++++-------------- hw/vfio/migration.c | 2 -- hw/vfio/pci-quirks.c | 19 +++++-------------- hw/vfio/pci.c | 8 -------- 7 files changed, 51 insertions(+), 49 deletions(-)
include/hw/vfio/vfio-common.h +2 -0
@@ -145,6 +145,7 @@ typedef struct VFIODevice {VFIOMigration *migration;Error *migration_blocker;OnOffAuto pre_copy_dirty_page_tracking; +struct vfio_region_info **regions; } VFIODevice;struct VFIODeviceOps {
@@ -258,6 +259,7 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index, struct vfio_region_info **info);int vfio_get_dev_region_info (VFIODevice *vbasedev,uint32_t type,uint32_t subtype,struct vfio_region_info **info); +void vfio_get_all_regions (VFIODevice *vbasedev);bool vfio_has_region_cap (VFIODevice *vbasedev,int region,uint16_t cap_type);struct vfio_info_cap_header *vfio_get_region_info_cap (struct vfio_region_info *info,uint16_t id);
hw/vfio/ccw.c +0 -5
@@ -517,7 +517,6 @@ static void vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp) vcdev->io_region_offset = info->offset; vcdev->io_region =g_malloc0 (info->size); -g_free (info);/* check for the optional async command region */ ret = vfio_get_dev_region_info(vdev, VFIO_REGION_TYPE_CCW,
@@ -530,7 +529,6 @@ static void vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp) } vcdev->async_cmd_region_offset = info->offset; vcdev->async_cmd_region =g_malloc0 (info->size); -g_free (info); } ret = vfio_get_dev_region_info(vdev, VFIO_REGION_TYPE_CCW,
@@ -543,7 +541,6 @@ static void vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp) } vcdev->schib_region_offset = info->offset; vcdev->schib_region =g_malloc (info->size); -g_free (info); } ret = vfio_get_dev_region_info(vdev, VFIO_REGION_TYPE_CCW,
@@ -557,7 +554,6 @@ static void vfio_ccw_get_region(VFIOCCWDevice *vcdev, Error **errp) } vcdev->crw_region_offset = info->offset; vcdev->crw_region =g_malloc (info->size); -g_free (info); }return ;
@@ -567,7 +563,6 @@ out_err:g_free (vcdev->schib_region);g_free (vcdev->async_cmd_region);g_free (vcdev->io_region); -g_free (info);return ; }
hw/vfio/common.c +35 -6
95 lines not on this page · raw message
hw/vfio/igd.c +9 -14
@@ -425,7 +425,7 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr)if ((ret || !rom->size) && !vdev->pdev.romfile) {error_report ("IGD device %s has no ROM, legacy mode disabled" , vdev->vbasedev.name); - goto out; +return ; }/*
@@ -436,7 +436,7 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr)error_report ("IGD device %s hotplugged, ROM disabled, " "legacy mode disabled" , vdev->vbasedev.name); vdev->rom_read_failed = true; - goto out; +return ; }/*
@@ -449,7 +449,7 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr)if (ret) {error_report ("IGD device %s does not support OpRegion access," "legacy mode disabled" , vdev->vbasedev.name); - goto out; +return ; } ret = vfio_get_dev_region_info(&vdev->vbasedev,
@@ -458,7 +458,7 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr)if (ret) {error_report ("IGD device %s does not support host bridge access," "legacy mode disabled" , vdev->vbasedev.name); - goto out; +return ; } ret = vfio_get_dev_region_info(&vdev->vbasedev,
@@ -467,7 +467,7 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr)if (ret) {error_report ("IGD device %s does not support LPC bridge access," "legacy mode disabled" , vdev->vbasedev.name); - goto out; +return ; } gmch =vfio_pci_read_config (&vdev->pdev,IGD_GMCH ,4 );
@@ -481,7 +481,7 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr)error_reportf_err (err,VFIO_MSG_PREFIX , vdev->vbasedev.name);error_report ("IGD device %s failed to enable VGA access, " "legacy mode disabled" , vdev->vbasedev.name); - goto out; +return ; }/* Create our LPC/ISA bridge */
@@ -489,7 +489,7 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr)if (ret) {error_report ("IGD device %s failed to create LPC bridge, " "legacy mode disabled" , vdev->vbasedev.name); - goto out; +return ; }/* Stuff some host values into the VM PCI host bridge */
@@ -497,7 +497,7 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr)if (ret) {error_report ("IGD device %s failed to modify host bridge, " "legacy mode disabled" , vdev->vbasedev.name); - goto out; +return ; }/* Setup OpRegion access */
@@ -505,7 +505,7 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr)if (ret) {error_append_hint (&err,"IGD legacy mode disabled\n" );error_reportf_err (err,VFIO_MSG_PREFIX , vdev->vbasedev.name); - goto out; +return ; }/* Setup our quirk to munge GTT addresses to the VM allocated buffer */
@@ -608,9 +608,4 @@ void vfio_probe_igd_bar4_quirk(VFIOPCIDevice *vdev, int nr)trace_vfio_pci_igd_bdsm_enabled (vdev->vbasedev.name, ggms_mb + gms_mb); -out: -g_free (rom); -g_free (opregion); -g_free (host); -g_free (lpc); }
hw/vfio/migration.c +0 -2
@@ -876,13 +876,11 @@ int vfio_migration_probe(VFIODevice *vbasedev, Error **errp) }trace_vfio_migration_probe (vbasedev->name, info->index); -g_free (info);return 0 ; add_blocker:error_setg (&vbasedev->migration_blocker,"VFIO device doesn't support migration" ); -g_free (info); ret =migrate_add_blocker (vbasedev->migration_blocker, errp);if (ret <0 ) {
hw/vfio/pci-quirks.c +5 -14
@@ -1601,16 +1601,14 @@ int vfio_pci_nvidia_v100_ram_init(VFIOPCIDevice *vdev, Error **errp) hdr =vfio_get_region_info_cap (nv2reg,VFIO_REGION_INFO_CAP_NVLINK2_SSATGT );if (!hdr) { - ret = -ENODEV ; - goto free_exit; +return -ENODEV ; } cap = (void *) hdr; p =mmap (NULL , nv2reg->size,PROT_READ |PROT_WRITE ,MAP_SHARED , vdev->vbasedev.fd, nv2reg->offset);if (p ==MAP_FAILED ) { - ret = -errno; - goto free_exit; +return -errno; } quirk =vfio_quirk_alloc (1 );
@@ -1623,8 +1621,6 @@ int vfio_pci_nvidia_v100_ram_init(VFIOPCIDevice *vdev, Error **errp) (void *) (uintptr_t) cap->tgt);trace_vfio_pci_nvidia_gpu_setup_quirk (vdev->vbasedev.name, cap->tgt, nv2reg->size); -free_exit: -g_free (nv2reg);return ret; }
@@ -1651,16 +1647,14 @@ int vfio_pci_nvlink2_init(VFIOPCIDevice *vdev, Error **errp) hdr =vfio_get_region_info_cap (atsdreg,VFIO_REGION_INFO_CAP_NVLINK2_SSATGT );if (!hdr) { - ret = -ENODEV ; - goto free_exit; +return -ENODEV ; } captgt = (void *) hdr; hdr =vfio_get_region_info_cap (atsdreg,VFIO_REGION_INFO_CAP_NVLINK2_LNKSPD );if (!hdr) { - ret = -ENODEV ; - goto free_exit; +return -ENODEV ; } capspeed = (void *) hdr;
@@ -1669,8 +1663,7 @@ int vfio_pci_nvlink2_init(VFIOPCIDevice *vdev, Error **errp) p =mmap (NULL , atsdreg->size,PROT_READ |PROT_WRITE ,MAP_SHARED , vdev->vbasedev.fd, atsdreg->offset);if (p ==MAP_FAILED ) { - ret = -errno; - goto free_exit; +return -errno; } quirk =vfio_quirk_alloc (1 );
@@ -1690,8 +1683,6 @@ int vfio_pci_nvlink2_init(VFIOPCIDevice *vdev, Error **errp) (void *) (uintptr_t) capspeed->link_speed);trace_vfio_pci_nvlink2_setup_quirk_lnkspd (vdev->vbasedev.name, capspeed->link_speed); -free_exit: -g_free (atsdreg);return ret; }
hw/vfio/pci.c +0 -8
@@ -793,8 +793,6 @@ static void vfio_pci_load_rom(VFIOPCIDevice *vdev) vdev->rom_size = size = reg_info->size; vdev->rom_offset = reg_info->offset; -g_free (reg_info); -if (!vdev->rom_size) { vdev->rom_read_failed = true; error_report("vfio-pci: Cannot read device rom at "
@@ -2521,7 +2519,6 @@ int vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp)error_setg (errp,"unexpected VGA info, flags 0x%lx, size 0x%lx" , (unsigned long )reg_info->flags, (unsigned long )reg_info->size); -g_free (reg_info);return -EINVAL ; }
@@ -2530,8 +2527,6 @@ int vfio_populate_vga(VFIOPCIDevice *vdev, Error **errp) vdev->vga->fd_offset = reg_info->offset; vdev->vga->fd = vdev->vbasedev.fd; -g_free (reg_info); - vdev->vga->region[QEMU_PCI_VGA_MEM ].offset =QEMU_PCI_VGA_MEM_BASE ; vdev->vga->region[QEMU_PCI_VGA_MEM ].nr =QEMU_PCI_VGA_MEM ;QLIST_INIT (&vdev->vga->region[QEMU_PCI_VGA_MEM ].quirks);
@@ -2626,8 +2621,6 @@ static void vfio_populate_device(VFIOPCIDevice *vdev, Error **errp) } vdev->config_offset = reg_info->offset; -g_free (reg_info); -if (vdev->features &VFIO_FEATURE_ENABLE_VGA ) { ret =vfio_populate_vga (vdev, errp);if (ret) {
@@ -3035,7 +3028,6 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) } ret =vfio_pci_igd_opregion_init (vdev, opregion, errp); -g_free (opregion);if (ret) { goto out_teardown; }
Signature · 1 line
1.8.3.1
RFC v5 7/23 vfio-user: connect vfio proxy to remote server
In reply to a message not in the archiveadd user.c & user.h files for vfio-user code add proxy struct to handle comms with remote server
--- hw/vfio/user.h | 78 +++++++++++++++++++ include/hw/vfio/vfio-common.h | 2 + hw/vfio/pci.c | 19 +++++ hw/vfio/user.c | 170 ++++++++++++++++++++++++++++++++++++++++++ MAINTAINERS | 4 + hw/vfio/meson.build | 1 + 6 files changed, 274 insertions(+) create mode 100644 hw/vfio/user.h create mode 100644 hw/vfio/user.c
hw/vfio/user.h new file +78 -0
@@ -0,0 +1,78 @@ +#ifndef VFIO_USER_H +#define VFIO_USER_H + +/* +* vfio protocol over a UNIX socket. +* +* Copyright © 2018, 2021 Oracle and/or its affiliates. +* +* This work is licensed under the terms of the GNU GPL, version 2. See +* the COPYING file in the top-level directory. +* +*/ + +typedef struct { +int send_fds; +int recv_fds; +int *fds; +}VFIOUserFDs ; + +enum msg_type { +VFIO_MSG_NONE , +VFIO_MSG_ASYNC , +VFIO_MSG_WAIT , +VFIO_MSG_NOWAIT , +VFIO_MSG_REQ , +}; + +typedef struct VFIOUserMsg { +QTAILQ_ENTRY (VFIOUserMsg) next; +VFIOUserFDs *fds; +uint32_t rsize; +uint32_t id; +QemuCond cv; +bool complete; +enum msg_type type; +}VFIOUserMsg ; + + +enum proxy_state { +VFIO_PROXY_CONNECTED =1 , +VFIO_PROXY_ERROR =2 , +VFIO_PROXY_CLOSING =3 , +VFIO_PROXY_CLOSED =4 , +}; + +typedef QTAILQ_HEAD(VFIOUserMsgQ, VFIOUserMsg) VFIOUserMsgQ; + +typedef struct VFIOProxy { +QLIST_ENTRY (VFIOProxy) next; +char *sockname; +struct QIOChannel *ioc; +void (*request)(void *opaque,VFIOUserMsg *msg); +void *req_arg; +int flags; +QemuCond close_cv; +AioContext *ctx; +QEMUBH *req_bh; + +/* +* above only changed when BQL is held +* below are protected by per-proxy lock +*/ +QemuMutex lock; +VFIOUserMsgQ free; +VFIOUserMsgQ pending; +VFIOUserMsgQ incoming; +VFIOUserMsgQ outgoing; +VFIOUserMsg *last_nowait; +enum proxy_state state; +}VFIOProxy ; + +/* VFIOProxy flags */ +#define VFIO_PROXY_CLIENT 0x1 + +VFIOProxy *vfio_user_connect_dev (SocketAddress *addr,Error **errp); +void vfio_user_disconnect (VFIOProxy *proxy); + +#endif /* VFIO_USER_H */
include/hw/vfio/vfio-common.h +2 -0
@@ -76,6 +76,7 @@ typedef struct VFIOAddressSpace {struct VFIOGroup ;typedef struct VFIOContIO VFIOContIO ; +typedef struct VFIOProxy VFIOProxy ; typedef struct VFIOContainer { VFIOAddressSpace *space;
@@ -147,6 +148,7 @@ typedef struct VFIODevice {VFIOMigration *migration;Error *migration_blocker;OnOffAuto pre_copy_dirty_page_tracking; +VFIOProxy *proxy;struct vfio_region_info **regions; } VFIODevice;
hw/vfio/pci.c +19 -0
@@ -43,6 +43,7 @@#include "qapi/error.h" #include "migration/blocker.h" #include "migration/qemu-file.h" +#include "hw/vfio/user.h" /* convenience macros for PCI config space */ #define VDEV_CONFIG_READ (vbasedev, off, size, data) \
@@ -3408,6 +3409,9 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)VFIOUserPCIDevice *udev =VFIO_USER_PCI (pdev);VFIOPCIDevice *vdev =VFIO_PCI_BASE (pdev);VFIODevice *vbasedev = &vdev->vbasedev; +SocketAddress addr; +VFIOProxy *proxy; +Error *err =NULL ;/* * TODO: make option parser understand SocketAddress
@@ -3420,6 +3424,16 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)return ; } +memset (&addr,0 ,sizeof (addr)); + addr.type =SOCKET_ADDRESS_TYPE_UNIX ; + addr.u.q_unix.path = udev->sock_name; + proxy =vfio_user_connect_dev (&addr, &err); +if (!proxy) { +error_setg (errp,"Remote proxy not found" ); +return ; + } + vbasedev->proxy = proxy; + vbasedev->name =g_strdup_printf ("VFIO user <%s>" , udev->sock_name); vbasedev->dev =DEVICE (vdev); vbasedev->fd =-1 ;
@@ -3431,8 +3445,13 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)static void vfio_user_instance_finalize (Object *obj) {VFIOPCIDevice *vdev =VFIO_PCI_BASE (obj); +VFIODevice *vbasedev = &vdev->vbasedev;vfio_put_device (vdev); + +if (vbasedev->proxy !=NULL ) { +vfio_user_disconnect (vbasedev->proxy); + } }static Property vfio_user_pci_dev_properties[] = {
hw/vfio/user.c new file +170 -0
170 lines not on this page · raw message
MAINTAINERS +4 -0
@@ -1958,8 +1958,12 @@ L: [email protected] vfio-user M: John G Johnson <[email protected]> M: Thanos Makatos <[email protected]> +M: Elena Ufimtseva <[email protected]> +M: Jagannathan Raman <[email protected]> S: Supported F: docs/devel/vfio-user.rst +F: hw/vfio/user.c +F: hw/vfio/user.h vhost M: Michael S. Tsirkin <[email protected]>
hw/vfio/meson.build +1 -0
@@ -9,6 +9,7 @@ vfio_ss.add(when: 'CONFIG_VFIO_PCI', if_true: files( 'pci-quirks.c', 'pci.c', )) +vfio_ss.add(when: 'CONFIG_VFIO_USER', if_true: files('user.c')) vfio_ss.add(when: 'CONFIG_VFIO_CCW', if_true: files('ccw.c')) vfio_ss.add(when: 'CONFIG_VFIO_PLATFORM', if_true: files('platform.c')) vfio_ss.add(when: 'CONFIG_VFIO_XGMAC', if_true: files('calxeda-xgmac.c'))
Signature · 1 line
1.8.3.1
RFC v5 12/23 vfio-user: region read/write
In reply to a message not in the archiveAdd support for posted writes on remote devices
--- hw/vfio/pci.h | 1 + hw/vfio/user-protocol.h | 12 +++++ hw/vfio/user.h | 1 + include/hw/vfio/vfio-common.h | 7 +-- hw/vfio/common.c | 10 +++- hw/vfio/pci.c | 9 +++- hw/vfio/user.c | 109 ++++++++++++++++++++++++++++++++++++++++++ 7 files changed, 143 insertions(+), 6 deletions(-)
hw/vfio/pci.h +1 -0
@@ -194,6 +194,7 @@ struct VFIOUserPCIDevice {VFIOPCIDevice device;char *sock_name;bool send_queued;/* all sends are queued */ +bool no_post;/* all regions write are sync */ };/* Use uin32_t for vendor & device so PCI_ANY_ID expands and cannot match hw */
hw/vfio/user-protocol.h +12 -0
@@ -120,4 +120,16 @@ typedef struct { uint64_t offset; } VFIOUserRegionInfo; +/* +* VFIO_USER_REGION_READ +* VFIO_USER_REGION_WRITE +*/ +typedef struct { +VFIOUserHdr hdr; +uint64_t offset; +uint32_t region; +uint32_t count; +char data[]; +}VFIOUserRegionRW ; +#endif /* VFIO_USER_PROTOCOL_H */
hw/vfio/user.h +1 -0
@@ -77,6 +77,7 @@ typedef struct VFIOProxy {/* VFIOProxy flags */ #define VFIO_PROXY_CLIENT 0x1#define VFIO_PROXY_FORCE_QUEUED 0x4 +#define VFIO_PROXY_NO_POST 0x8VFIOProxy *vfio_user_connect_dev (SocketAddress *addr,Error **errp);void vfio_user_disconnect (VFIOProxy *proxy);
include/hw/vfio/vfio-common.h +4 -3
@@ -57,6 +57,7 @@ typedef struct VFIORegion {VFIOMmap *mmaps;uint8_t nr;/* cache the region number for debug */ int fd;/* fd to mmap() region */ +bool post_wr;/* writes can be posted */ } VFIORegion; typedef struct VFIOMigration {
@@ -180,7 +181,7 @@ struct VFIODevIO {int (*region_read)(VFIODevice *vdev,uint8_t nr,off_t off,uint32_t size,void *data);int (*region_write)(VFIODevice *vdev,uint8_t nr,off_t off,uint32_t size, -void *data); +void *data,bool post); };#define VDEV_GET_INFO (vdev, info) \
@@ -193,8 +194,8 @@ struct VFIODevIO { ((vdev)->io_ops->set_irqs((vdev), (irqs)))#define VDEV_REGION_READ (vdev, nr, off, size, data) \ ((vdev)->io_ops->region_read((vdev), (nr), (off), (size), (data))) -#define VDEV_REGION_WRITE (vdev, nr, off, size, data) \ - ((vdev)->io_ops->region_write((vdev), (nr), (off), (size), (data))) +#define VDEV_REGION_WRITE (vdev, nr, off, size, data, post) \ + ((vdev)->io_ops->region_write((vdev), (nr), (off), (size), (data), (post)))struct VFIOContIO { int (*dma_map)(VFIOContainer *container,
hw/vfio/common.c +8 -2
@@ -213,6 +213,7 @@ void vfio_region_write(void *opaque, hwaddr addr,uint32_t dword;uint64_t qword; } buf; +bool post = region->post_wr;int ret;switch (size) {
@@ -233,7 +234,11 @@ void vfio_region_write(void *opaque, hwaddr addr,break ; } - ret =VDEV_REGION_WRITE (vbasedev, region->nr, addr, size, &buf); +/* read-after-write hazard if guest can directly access region */ +if (region->nr_mmaps) { + post = false; + } + ret =VDEV_REGION_WRITE (vbasedev, region->nr, addr, size, &buf, post);if (ret != size) {const char *err = ret <0 ?strerror (-ret) :"short write" ;
@@ -1555,6 +1560,7 @@ int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region, region->size = info->size; region->fd_offset = info->offset; region->nr = index; + region->post_wr = false;if (vbasedev->regfds !=NULL ) { region->fd = vbasedev->regfds[index]; }else {
@@ -2689,7 +2695,7 @@ static int vfio_io_region_read(VFIODevice *vbasedev, uint8_t index, off_t off, }static int vfio_io_region_write (VFIODevice *vbasedev,uint8_t index,off_t off, -uint32_t size,void *data) +uint32_t size,void *data,bool post) {struct vfio_region_info *info = vbasedev->regions[index];int ret;
hw/vfio/pci.c +8 -1
@@ -51,7 +51,7 @@ (size), (data))#define VDEV_CONFIG_WRITE (vbasedev, off, size, data) \ VDEV_REGION_WRITE((vbasedev), VFIO_PCI_CONFIG_REGION_INDEX, (off), \ - (size), (data)) + (size), (data), false)#define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug"
@@ -1661,6 +1661,9 @@ static void vfio_bar_prepare(VFIOPCIDevice *vdev, int nr) bar->type = pci_bar & (bar->ioport ? ~PCI_BASE_ADDRESS_IO_MASK : ~PCI_BASE_ADDRESS_MEM_MASK ); bar->size = bar->region.size; + +/* IO regions are sync, memory can be async */ + bar->region.post_wr = (bar->ioport ==0 ); }static void vfio_bars_prepare (VFIOPCIDevice *vdev)
@@ -3445,6 +3448,9 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)if (udev->send_queued) { proxy->flags |=VFIO_PROXY_FORCE_QUEUED ; } +if (udev->no_post) { + proxy->flags |=VFIO_PROXY_NO_POST ; + }vfio_user_validate_version (vbasedev, &err);if (err !=NULL ) {
@@ -3504,6 +3510,7 @@ static void vfio_user_instance_finalize(Object *obj)static Property vfio_user_pci_dev_properties[] = {DEFINE_PROP_STRING ("socket" , VFIOUserPCIDevice, sock_name),DEFINE_PROP_BOOL ("x-send-queued" , VFIOUserPCIDevice, send_queued, false), +DEFINE_PROP_BOOL ("x-no-posted-writes" , VFIOUserPCIDevice, no_post, false),DEFINE_PROP_END_OF_LIST (), };
hw/vfio/user.c +109 -0
135 lines not on this page · raw message
Signature · 1 line
1.8.3.1
RFC v5 5/23 vfio-user: add device IO ops vector
In reply to a message not in the archiveUsed for communication with VFIO driver
(prep work for vfio-user, which will communicate over a socket)
--- include/hw/vfio/vfio-common.h | 27 ++++++++ hw/vfio/common.c | 107 +++++++++++++++++++++++++++----- hw/vfio/pci.c | 140 ++++++++++++++++++++++++++---------------- 3 files changed, 206 insertions(+), 68 deletions(-)
include/hw/vfio/vfio-common.h +27 -0
@@ -124,6 +124,7 @@ typedef struct VFIOHostDMAWindow { } VFIOHostDMAWindow;typedef struct VFIODeviceOps VFIODeviceOps ; +typedef struct VFIODevIO VFIODevIO ; typedef struct VFIODevice { QLIST_ENTRY(VFIODevice) next;
@@ -139,6 +140,7 @@ typedef struct VFIODevice {bool ram_block_discard_allowed;bool enable_migration;VFIODeviceOps *ops; +VFIODevIO *io_ops;unsigned int num_irqs;unsigned int num_regions;unsigned int flags;
@@ -165,6 +167,30 @@ struct VFIODeviceOps {* through ioctl() to the kernel VFIO driver, but vfio-user * can use a socket to a remote process. */ +struct VFIODevIO { +int (*get_info)(VFIODevice *vdev,struct vfio_device_info *info); +int (*get_region_info)(VFIODevice *vdev, +struct vfio_region_info *info); +int (*get_irq_info)(VFIODevice *vdev,struct vfio_irq_info *irq); +int (*set_irqs)(VFIODevice *vdev,struct vfio_irq_set *irqs); +int (*region_read)(VFIODevice *vdev,uint8_t nr,off_t off,uint32_t size, +void *data); +int (*region_write)(VFIODevice *vdev,uint8_t nr,off_t off,uint32_t size, +void *data); +}; + +#define VDEV_GET_INFO (vdev, info) \ + ((vdev)->io_ops->get_info((vdev), (info))) +#define VDEV_GET_REGION_INFO (vdev, info) \ + ((vdev)->io_ops->get_region_info((vdev), (info))) +#define VDEV_GET_IRQ_INFO (vdev, irq) \ + ((vdev)->io_ops->get_irq_info((vdev), (irq))) +#define VDEV_SET_IRQS (vdev, irqs) \ + ((vdev)->io_ops->set_irqs((vdev), (irqs))) +#define VDEV_REGION_READ (vdev, nr, off, size, data) \ + ((vdev)->io_ops->region_read((vdev), (nr), (off), (size), (data))) +#define VDEV_REGION_WRITE (vdev, nr, off, size, data) \ + ((vdev)->io_ops->region_write((vdev), (nr), (off), (size), (data)))struct VFIOContIO { int (*dma_map)(VFIOContainer *container,
@@ -184,6 +210,7 @@ struct VFIOContIO {#define CONT_DIRTY_BITMAP (cont, bitmap, range) \ ((cont)->io_ops->dirty_bitmap((cont), (bitmap), (range))) +extern VFIODevIO vfio_dev_io_ioctl;extern VFIOContIO vfio_cont_io_ioctl;#endif /* CONFIG_LINUX */
hw/vfio/common.c +92 -15
176 lines not on this page · raw message
hw/vfio/pci.c +87 -53
289 lines not on this page · raw message
Signature · 1 line
1.8.3.1
RFC v5 13/23 vfio-user: pci_user_realize PCI setup
In reply to a message not in the archivePCI BARs read from remote device
PCI config reads/writes sent to remote server
--- hw/vfio/pci.c | 275 ++++++++++++++++++++++++++++++++++++---------------------- 1 file changed, 172 insertions(+), 103 deletions(-)
hw/vfio/pci.c +172 -103
@@ -2831,6 +2831,132 @@ static void vfio_unregister_req_notifier(VFIOPCIDevice *vdev) vdev->req_enabled = false; } +static void vfio_pci_config_setup (VFIOPCIDevice *vdev,Error **errp) +{ +PCIDevice *pdev = &vdev->pdev; +Error *err =NULL ; + +/* vfio emulates a lot for us, but some bits need extra love */ + vdev->emulated_config_bits =g_malloc0 (vdev->config_size); + +/* QEMU can choose to expose the ROM or not */ +memset (vdev->emulated_config_bits +PCI_ROM_ADDRESS ,0xff ,4 ); +/* QEMU can also add or extend BARs */ +memset (vdev->emulated_config_bits +PCI_BASE_ADDRESS_0 ,0xff ,6 *4 ); + +/* +* The PCI spec reserves vendor ID 0xffff as an invalid value. The +* device ID is managed by the vendor and need only be a 16-bit value. +* Allow any 16-bit value for subsystem so they can be hidden or changed. +*/ +if (vdev->vendor_id !=PCI_ANY_ID ) { +if (vdev->vendor_id >=0xffff ) { +error_setg (errp,"invalid PCI vendor ID provided" ); +return ; + } +vfio_add_emulated_word (vdev,PCI_VENDOR_ID , vdev->vendor_id, ~0 ); +trace_vfio_pci_emulated_vendor_id (vdev->vbasedev.name, vdev->vendor_id); + }else { + vdev->vendor_id =pci_get_word (pdev->config +PCI_VENDOR_ID ); + } + +if (vdev->device_id !=PCI_ANY_ID ) { +if (vdev->device_id >0xffff ) { +error_setg (errp,"invalid PCI device ID provided" ); +return ; + } +vfio_add_emulated_word (vdev,PCI_DEVICE_ID , vdev->device_id, ~0 ); +trace_vfio_pci_emulated_device_id (vdev->vbasedev.name, vdev->device_id); + }else { + vdev->device_id =pci_get_word (pdev->config +PCI_DEVICE_ID ); + } + +if (vdev->sub_vendor_id !=PCI_ANY_ID ) { +if (vdev->sub_vendor_id >0xffff ) { +error_setg (errp,"invalid PCI subsystem vendor ID provided" ); +return ; + } +vfio_add_emulated_word (vdev,PCI_SUBSYSTEM_VENDOR_ID , + vdev->sub_vendor_id, ~0 ); +trace_vfio_pci_emulated_sub_vendor_id (vdev->vbasedev.name, + vdev->sub_vendor_id); + } + +if (vdev->sub_device_id !=PCI_ANY_ID ) { +if (vdev->sub_device_id >0xffff ) { +error_setg (errp,"invalid PCI subsystem device ID provided" ); +return ; + } +vfio_add_emulated_word (vdev,PCI_SUBSYSTEM_ID , vdev->sub_device_id, ~0 ); +trace_vfio_pci_emulated_sub_device_id (vdev->vbasedev.name, + vdev->sub_device_id); + } + +/* QEMU can change multi-function devices to single function, or reverse */ + vdev->emulated_config_bits[PCI_HEADER_TYPE ] = +PCI_HEADER_TYPE_MULTI_FUNCTION ; + +/* Restore or clear multifunction, this is always controlled by QEMU */ +if (vdev->pdev.cap_present &QEMU_PCI_CAP_MULTIFUNCTION ) { + vdev->pdev.config[PCI_HEADER_TYPE ] |=PCI_HEADER_TYPE_MULTI_FUNCTION ; + }else { + vdev->pdev.config[PCI_HEADER_TYPE ] &= ~PCI_HEADER_TYPE_MULTI_FUNCTION ; + } + +/* +* Clear host resource mapping info. If we choose not to register a +* BAR, such as might be the case with the option ROM, we can get +* confusing, unwritable, residual addresses from the host here. +*/ +memset (&vdev->pdev.config[PCI_BASE_ADDRESS_0 ],0 ,24 ); +memset (&vdev->pdev.config[PCI_ROM_ADDRESS ],0 ,4 ); + +vfio_pci_size_rom (vdev); + +vfio_bars_prepare (vdev); + +vfio_msix_early_setup (vdev, &err); +if (err) { +error_propagate (errp, err); +return ; + } + +vfio_bars_register (vdev); +} + +static int vfio_interrupt_setup (VFIOPCIDevice *vdev,Error **errp) +{ +PCIDevice *pdev = &vdev->pdev; +int ret; + +/* QEMU emulates all of MSI & MSIX */ +if (pdev->cap_present &QEMU_PCI_CAP_MSIX ) { +memset (vdev->emulated_config_bits + pdev->msix_cap,0xff , +MSIX_CAP_LENGTH ); + } + +if (pdev->cap_present &QEMU_PCI_CAP_MSI ) { +memset (vdev->emulated_config_bits + pdev->msi_cap,0xff , + vdev->msi_cap_size); + } + +if (vfio_pci_read_config (&vdev->pdev,PCI_INTERRUPT_PIN ,1 )) { + vdev->intx.mmap_timer =timer_new_ms (QEMU_CLOCK_VIRTUAL , + vfio_intx_mmap_enable, vdev); +pci_device_set_intx_routing_notifier (&vdev->pdev, + vfio_intx_routing_notifier); + vdev->irqchip_change_notifier.notify = vfio_irqchip_change; +kvm_irqchip_add_change_notifier (&vdev->irqchip_change_notifier); + ret =vfio_intx_enable (vdev, errp); +if (ret) { +pci_device_set_intx_routing_notifier (&vdev->pdev,NULL ); +kvm_irqchip_remove_change_notifier (&vdev->irqchip_change_notifier); +return ret; + } + } +return 0 ; +} +static void vfio_realize (PCIDevice *pdev,Error **errp) {VFIOPCIDevice *vdev =VFIO_PCI_BASE (pdev);
@@ -2946,92 +3072,16 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) goto error; } -/* vfio emulates a lot for us, but some bits need extra love */ - vdev->emulated_config_bits =g_malloc0 (vdev->config_size); - -/* QEMU can choose to expose the ROM or not */ -memset (vdev->emulated_config_bits +PCI_ROM_ADDRESS ,0xff ,4 ); -/* QEMU can also add or extend BARs */ -memset (vdev->emulated_config_bits +PCI_BASE_ADDRESS_0 ,0xff ,6 *4 ); - -/* -* The PCI spec reserves vendor ID 0xffff as an invalid value. The -* device ID is managed by the vendor and need only be a 16-bit value. -* Allow any 16-bit value for subsystem so they can be hidden or changed. -*/ -if (vdev->vendor_id !=PCI_ANY_ID ) { -if (vdev->vendor_id >=0xffff ) { -error_setg (errp,"invalid PCI vendor ID provided" ); - goto error; - } -vfio_add_emulated_word (vdev,PCI_VENDOR_ID , vdev->vendor_id, ~0 ); -trace_vfio_pci_emulated_vendor_id (vdev->vbasedev.name, vdev->vendor_id); - }else { - vdev->vendor_id =pci_get_word (pdev->config +PCI_VENDOR_ID ); - } - -if (vdev->device_id !=PCI_ANY_ID ) { -if (vdev->device_id >0xffff ) { -error_setg (errp,"invalid PCI device ID provided" ); - goto error; - } -vfio_add_emulated_word (vdev,PCI_DEVICE_ID , vdev->device_id, ~0 ); -trace_vfio_pci_emulated_device_id (vdev->vbasedev.name, vdev->device_id); - }else { - vdev->device_id =pci_get_word (pdev->config +PCI_DEVICE_ID ); - } - -if (vdev->sub_vendor_id !=PCI_ANY_ID ) { -if (vdev->sub_vendor_id >0xffff ) { -error_setg (errp,"invalid PCI subsystem vendor ID provided" ); - goto error; - } -vfio_add_emulated_word (vdev,PCI_SUBSYSTEM_VENDOR_ID , - vdev->sub_vendor_id, ~0 ); -trace_vfio_pci_emulated_sub_vendor_id (vdev->vbasedev.name, - vdev->sub_vendor_id); - } - -if (vdev->sub_device_id !=PCI_ANY_ID ) { -if (vdev->sub_device_id >0xffff ) { -error_setg (errp,"invalid PCI subsystem device ID provided" ); - goto error; - } -vfio_add_emulated_word (vdev,PCI_SUBSYSTEM_ID , vdev->sub_device_id, ~0 ); -trace_vfio_pci_emulated_sub_device_id (vdev->vbasedev.name, - vdev->sub_device_id); - } - -/* QEMU can change multi-function devices to single function, or reverse */ - vdev->emulated_config_bits[PCI_HEADER_TYPE ] = -PCI_HEADER_TYPE_MULTI_FUNCTION ; - -/* Restore or clear multifunction, this is always controlled by QEMU */ -if (vdev->pdev.cap_present &QEMU_PCI_CAP_MULTIFUNCTION ) { - vdev->pdev.config[PCI_HEADER_TYPE ] |=PCI_HEADER_TYPE_MULTI_FUNCTION ; - }else { - vdev->pdev.config[PCI_HEADER_TYPE ] &= ~PCI_HEADER_TYPE_MULTI_FUNCTION ; - } - -/* -* Clear host resource mapping info. If we choose not to register a -* BAR, such as might be the case with the option ROM, we can get -* confusing, unwritable, residual addresses from the host here. -*/ -memset (&vdev->pdev.config[PCI_BASE_ADDRESS_0 ],0 ,24 ); -memset (&vdev->pdev.config[PCI_ROM_ADDRESS ],0 ,4 ); - -vfio_pci_size_rom (vdev); - -vfio_bars_prepare (vdev); - -vfio_msix_early_setup (vdev, &err); +vfio_pci_config_setup (vdev, &err);if (err) { -error_propagate (errp, err); goto error; } -vfio_bars_register (vdev); +/* +* vfio_pci_config_setup will have registered the device's BARs +* and setup any MSIX BARs, so errors after it succeeds must +* use out_teardown +*/ ret =vfio_add_capabilities (vdev, errp);if (ret) {
@@ -3072,29 +3122,15 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) } } -/* QEMU emulates all of MSI & MSIX */ -if (pdev->cap_present &QEMU_PCI_CAP_MSIX ) { -memset (vdev->emulated_config_bits + pdev->msix_cap,0xff , -MSIX_CAP_LENGTH ); - } - -if (pdev->cap_present &QEMU_PCI_CAP_MSI ) { -memset (vdev->emulated_config_bits + pdev->msi_cap,0xff , - vdev->msi_cap_size); + ret =vfio_interrupt_setup (vdev, errp); +if (ret) { + goto out_teardown; } -if (vfio_pci_read_config (&vdev->pdev,PCI_INTERRUPT_PIN ,1 )) { - vdev->intx.mmap_timer =timer_new_ms (QEMU_CLOCK_VIRTUAL , - vfio_intx_mmap_enable, vdev); -pci_device_set_intx_routing_notifier (&vdev->pdev, - vfio_intx_routing_notifier); - vdev->irqchip_change_notifier.notify = vfio_irqchip_change; -kvm_irqchip_add_change_notifier (&vdev->irqchip_change_notifier); - ret =vfio_intx_enable (vdev, errp); -if (ret) { - goto out_deregister; - } - } +/* +* vfio_interrupt_setup will have setup INTx's KVM routing +* so errors after it succeeds must use out_deregister +*/ if (vdev->display !=ON_OFF_AUTO_OFF ) { ret =vfio_display_probe (vdev, errp);
@@ -3488,8 +3524,41 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp) goto error; } +/* Get a copy of config space */ + ret =VDEV_REGION_READ (vbasedev,VFIO_PCI_CONFIG_REGION_INDEX ,0 , +MIN (pci_config_size (pdev), vdev->config_size), + pdev->config); +if (ret < (int )MIN (pci_config_size (&vdev->pdev), vdev->config_size)) { +error_setg_errno (errp, -ret,"failed to read device config space" ); + goto error; + } + +vfio_pci_config_setup (vdev, &err); +if (err) { + goto error; + } + +/* +* vfio_pci_config_setup will have registered the device's BARs +* and setup any MSIX BARs, so errors after it succeeds must +* use out_teardown +*/ + + ret =vfio_add_capabilities (vdev, errp); +if (ret) { + goto out_teardown; + } + + ret =vfio_interrupt_setup (vdev, errp); +if (ret) { + goto out_teardown; + } +return ; +out_teardown: +vfio_teardown_msi (vdev); +vfio_bars_exit (vdev); error:vfio_user_disconnect (proxy);error_prepend (errp,VFIO_MSG_PREFIX , vdev->vbasedev.name);
Signature · 1 line
1.8.3.1
RFC v5 14/23 vfio-user: forward msix BAR accesses to server
In reply to a message not in the archiveServer holds device current device pending state
--- hw/vfio/pci.h | 1 + hw/vfio/pci.c | 112 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 113 insertions(+)
hw/vfio/pci.h +1 -0
@@ -112,6 +112,7 @@ typedef struct VFIOMSIXInfo {uint32_t table_offset;uint32_t pba_offset;unsigned long *pending; +MemoryRegion *msix_regions; } VFIOMSIXInfo;/*
hw/vfio/pci.c +112 -0
130 lines not on this page · raw message
Signature · 1 line
1.8.3.1
RFC v5 21/23 vfio-user: add 'x-msg-timeout' option that specifies msg wait times
In reply to a message not in the archive--- hw/vfio/pci.h | 1 + hw/vfio/user.h | 1 + hw/vfio/pci.c | 4 ++++ hw/vfio/user.c | 7 ++++--- 4 files changed, 10 insertions(+), 3 deletions(-)
hw/vfio/pci.h +1 -0
@@ -197,6 +197,7 @@ struct VFIOUserPCIDevice {bool secure_dma;/* disable shared mem for DMA */ bool send_queued;/* all sends are queued */ bool no_post;/* all regions write are sync */ +uint32_t wait_time;/* timeout for message replies */ };/* Use uin32_t for vendor & device so PCI_ANY_ID expands and cannot match hw */
hw/vfio/user.h +1 -0
@@ -55,6 +55,7 @@ typedef struct VFIOProxy {void (*request)(void *opaque,VFIOUserMsg *msg);void *req_arg;int flags; +uint32_t wait_time;QemuCond close_cv;AioContext *ctx;QEMUBH *req_bh;
hw/vfio/pci.c +4 -0
@@ -3698,6 +3698,9 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)if (udev->no_post) { proxy->flags |=VFIO_PROXY_NO_POST ; } +if (udev->wait_time) { + proxy->wait_time = udev->wait_time; + }vfio_user_validate_version (vbasedev, &err);if (err !=NULL ) {
@@ -3840,6 +3843,7 @@ static Property vfio_user_pci_dev_properties[] = {DEFINE_PROP_BOOL ("secure-dma" , VFIOUserPCIDevice, secure_dma, false),DEFINE_PROP_BOOL ("x-send-queued" , VFIOUserPCIDevice, send_queued, false),DEFINE_PROP_BOOL ("x-no-posted-writes" , VFIOUserPCIDevice, no_post, false), +DEFINE_PROP_UINT32 ("x-msg-timeout" , VFIOUserPCIDevice, wait_time,0 ), DEFINE_PROP_END_OF_LIST(), };
hw/vfio/user.c +4 -3
@@ -39,7 +39,7 @@static uint64_t max_xfer_size =VFIO_USER_DEF_MAX_XFER ;static uint64_t max_send_fds =VFIO_USER_DEF_MAX_FDS ; -static int wait_time =1000 ;/* wait 1 sec for replies */ +static uint32_t wait_time =1000 ;/* wait 1 sec for replies */ static IOThread *vfio_user_iothread;static void vfio_user_shutdown (VFIOProxy *proxy);
@@ -718,7 +718,7 @@ static void vfio_user_send_wait(VFIOProxy *proxy, VFIOUserHdr *hdr,if (ret ==0 ) {while (!msg->complete) { -if (!qemu_cond_timedwait (&msg->cv, &proxy->lock, wait_time)) { +if (!qemu_cond_timedwait (&msg->cv, &proxy->lock, proxy->wait_time)) {QTAILQ_REMOVE (&proxy->pending, msg, next);vfio_user_set_error (hdr,ETIMEDOUT );break ;
@@ -757,7 +757,7 @@ static void vfio_user_wait_reqs(VFIOProxy *proxy) msg = proxy->last_nowait; msg->type =VFIO_MSG_WAIT ;while (!msg->complete) { -if (!qemu_cond_timedwait (&msg->cv, &proxy->lock, wait_time)) { +if (!qemu_cond_timedwait (&msg->cv, &proxy->lock, proxy->wait_time)) {QTAILQ_REMOVE (&proxy->pending, msg, next);error_printf ("vfio_wait_reqs - timed out\n" );break ;
@@ -867,6 +867,7 @@ VFIOProxy *vfio_user_connect_dev(SocketAddress *addr, Error **errp) proxy->ioc = ioc; proxy->flags =VFIO_PROXY_CLIENT ; proxy->state =VFIO_PROXY_CONNECTED ; + proxy->wait_time = wait_time;qemu_mutex_init (&proxy->lock);qemu_cond_init (&proxy->close_cv);
Signature · 1 line
1.8.3.1
RFC v5 11/23 vfio-user: get region info
In reply to a message not in the archiveAdd per-region FD to support mmap() of remote device regions
--- hw/vfio/user-protocol.h | 14 ++++++++++ include/hw/vfio/vfio-common.h | 8 +++--- hw/vfio/common.c | 32 ++++++++++++++++++++--- hw/vfio/user.c | 59 +++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 107 insertions(+), 6 deletions(-)
hw/vfio/user-protocol.h +14 -0
@@ -106,4 +106,18 @@ typedef struct { uint32_t cap_offset; } VFIOUserDeviceInfo; +/* +* VFIO_USER_DEVICE_GET_REGION_INFO +* imported from struct_vfio_region_info +*/ +typedef struct { +VFIOUserHdr hdr; +uint32_t argsz; +uint32_t flags; +uint32_t index; +uint32_t cap_offset; +uint64_t size; +uint64_t offset; +}VFIOUserRegionInfo ; +#endif /* VFIO_USER_PROTOCOL_H */
include/hw/vfio/vfio-common.h +5 -3
@@ -56,6 +56,7 @@ typedef struct VFIORegion {uint32_t nr_mmaps;VFIOMmap *mmaps;uint8_t nr;/* cache the region number for debug */ +int fd;/* fd to mmap() region */ } VFIORegion; typedef struct VFIOMigration {
@@ -150,6 +151,7 @@ typedef struct VFIODevice {OnOffAuto pre_copy_dirty_page_tracking;VFIOProxy *proxy;struct vfio_region_info **regions; +int *regfds; } VFIODevice;struct VFIODeviceOps {
@@ -172,7 +174,7 @@ struct VFIODeviceOps {struct VFIODevIO {int (*get_info)(VFIODevice *vdev,struct vfio_device_info *info);int (*get_region_info)(VFIODevice *vdev, -struct vfio_region_info *info); +struct vfio_region_info *info,int *fd);int (*get_irq_info)(VFIODevice *vdev,struct vfio_irq_info *irq);int (*set_irqs)(VFIODevice *vdev,struct vfio_irq_set *irqs); int (*region_read)(VFIODevice *vdev, uint8_t nr, off_t off, uint32_t size,
@@ -183,8 +185,8 @@ struct VFIODevIO {#define VDEV_GET_INFO (vdev, info) \ ((vdev)->io_ops->get_info((vdev), (info))) -#define VDEV_GET_REGION_INFO (vdev, info) \ - ((vdev)->io_ops->get_region_info((vdev), (info))) +#define VDEV_GET_REGION_INFO (vdev, info, fd) \ + ((vdev)->io_ops->get_region_info((vdev), (info), (fd)))#define VDEV_GET_IRQ_INFO (vdev, irq) \ ((vdev)->io_ops->get_irq_info((vdev), (irq)))#define VDEV_SET_IRQS (vdev, irqs) \
hw/vfio/common.c +29 -3
@@ -40,6 +40,7 @@#include "trace.h" #include "qapi/error.h" #include "migration/migration.h" +#include "hw/vfio/user.h" VFIOGroupList vfio_group_list =QLIST_HEAD_INITIALIZER (vfio_group_list);
@@ -1554,6 +1555,11 @@ int vfio_region_setup(Object *obj, VFIODevice *vbasedev, VFIORegion *region, region->size = info->size; region->fd_offset = info->offset; region->nr = index; +if (vbasedev->regfds !=NULL ) { + region->fd = vbasedev->regfds[index]; + }else { + region->fd = vbasedev->fd; + }if (region->size) { region->mem =g_new0 (MemoryRegion,1 );
@@ -1605,7 +1611,7 @@ int vfio_region_mmap(VFIORegion *region)for (i =0 ; i < region->nr_mmaps; i++) { region->mmaps[i].mmap =mmap (NULL , region->mmaps[i].size, prot, -MAP_SHARED , region->vbasedev->fd, +MAP_SHARED , region->fd, region->fd_offset + region->mmaps[i].offset);if (region->mmaps[i].mmap ==MAP_FAILED ) {
@@ -2410,10 +2416,17 @@ void vfio_put_base_device(VFIODevice *vbasedev)int i;for (i =0 ; i < vbasedev->num_regions; i++) { +if (vbasedev->regfds !=NULL && vbasedev->regfds[i] !=-1 ) { +close (vbasedev->regfds[i]); + }g_free (vbasedev->regions[i]); }g_free (vbasedev->regions); vbasedev->regions =NULL ; +if (vbasedev->regfds !=NULL ) { +g_free (vbasedev->regfds); + vbasedev->regfds =NULL ; + } }if (!vbasedev->group) {
@@ -2429,12 +2442,16 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index, struct vfio_region_info **info) {size_t argsz =sizeof (struct vfio_region_info ); +int fd =-1 ;int ret;/* create region cache */ if (vbasedev->regions ==NULL ) { vbasedev->regions = g_new0(struct vfio_region_info *, vbasedev->num_regions); +if (vbasedev->proxy !=NULL ) { + vbasedev->regfds =g_new0 (int, vbasedev->num_regions); + } }/* check cache */ if (vbasedev->regions[index] !=NULL ) {
@@ -2448,7 +2465,7 @@ int vfio_get_region_info(VFIODevice *vbasedev, int index, retry: (*info)->argsz = argsz; - ret =VDEV_GET_REGION_INFO (vbasedev, *info); + ret =VDEV_GET_REGION_INFO (vbasedev, *info, &fd);if (ret !=0 ) {g_free (*info); *info =NULL ;
@@ -2458,12 +2475,19 @@ retry:if ((*info)->argsz > argsz) { argsz = (*info)->argsz; *info =g_realloc (*info, argsz); +if (fd !=-1 ) { +close (fd); + fd =-1 ; + } goto retry; }/* fill cache */ vbasedev->regions[index] = *info; +if (vbasedev->regfds !=NULL ) { + vbasedev->regfds[index] = fd; + }return 0 ; }
@@ -2623,10 +2647,12 @@ static int vfio_io_get_info(VFIODevice *vbasedev, struct vfio_device_info *info) }static int vfio_io_get_region_info (VFIODevice *vbasedev, -struct vfio_region_info *info) +struct vfio_region_info *info, +int *fd) {int ret; + *fd =-1 ; ret =ioctl (vbasedev->fd,VFIO_DEVICE_GET_REGION_INFO , info);return ret <0 ? -errno : ret;
hw/vfio/user.c +59 -0
72 lines not on this page · raw message
Signature · 1 line
1.8.3.1
RFC v5 3/23 vfio-user: add container IO ops vector
In reply to a message not in the archiveUsed for communication with VFIO driver
(prep work for vfio-user, which will communicate over a socket)
--- include/hw/vfio/vfio-common.h | 33 +++++++++++ hw/vfio/common.c | 126 ++++++++++++++++++++++++++++-------------- 2 files changed, 117 insertions(+), 42 deletions(-)
include/hw/vfio/vfio-common.h +33 -0
@@ -75,6 +75,7 @@ typedef struct VFIOAddressSpace { } VFIOAddressSpace;struct VFIOGroup ; +typedef struct VFIOContIO VFIOContIO ; typedef struct VFIOContainer { VFIOAddressSpace *space;
@@ -83,6 +84,7 @@ typedef struct VFIOContainer {MemoryListener prereg_listener;unsigned iommu_type;Error *error; +VFIOContIO *io_ops;bool initialized;bool dirty_pages_supported;uint64_t dirty_pgsizes;
@@ -154,6 +156,37 @@ struct VFIODeviceOps {int (*vfio_load_config)(VFIODevice *vdev,QEMUFile *f); }; +#ifdef CONFIG_LINUX + +/* +* The next 2 ops vectors are how Devices and Containers +* communicate with the server. The default option is +* through ioctl() to the kernel VFIO driver, but vfio-user +* can use a socket to a remote process. +*/ + +struct VFIOContIO { +int (*dma_map)(VFIOContainer *container, +struct vfio_iommu_type1_dma_map *map); +int (*dma_unmap)(VFIOContainer *container, +struct vfio_iommu_type1_dma_unmap *unmap, +struct vfio_bitmap *bitmap); +int (*dirty_bitmap)(VFIOContainer *container, +struct vfio_iommu_type1_dirty_bitmap *bitmap, +struct vfio_iommu_type1_dirty_bitmap_get *range); +}; + +#define CONT_DMA_MAP (cont, map) \ + ((cont)->io_ops->dma_map((cont), (map))) +#define CONT_DMA_UNMAP (cont, unmap, bitmap) \ + ((cont)->io_ops->dma_unmap((cont), (unmap), (bitmap))) +#define CONT_DIRTY_BITMAP (cont, bitmap, range) \ + ((cont)->io_ops->dirty_bitmap((cont), (bitmap), (range))) + +extern VFIOContIO vfio_cont_io_ioctl; + +#endif /* CONFIG_LINUX */ + typedef struct VFIOGroup { int fd; int groupid;
hw/vfio/common.c +84 -42
180 lines not on this page · raw message
Signature · 1 line
1.8.3.1
RFC v5 10/23 vfio-user: get device info
In reply to a message not in the archive--- hw/vfio/user-protocol.h | 14 +++++++++++++ hw/vfio/user.h | 2 ++ hw/vfio/pci.c | 26 ++++++++++++++++++++++++ hw/vfio/user.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 96 insertions(+)
hw/vfio/user-protocol.h +14 -0
@@ -92,4 +92,18 @@ typedef struct {#define VFIO_USER_DEF_MAX_XFER (1024 * 1024)#define VFIO_USER_MAX_MAX_XFER (64 * 1024 * 1024) + +/* +* VFIO_USER_DEVICE_GET_INFO +* imported from struct_device_info +*/ +typedef struct { +VFIOUserHdr hdr; +uint32_t argsz; +uint32_t flags; +uint32_t num_regions; +uint32_t num_irqs; +uint32_t cap_offset; +}VFIOUserDeviceInfo ; +#endif /* VFIO_USER_PROTOCOL_H */
hw/vfio/user.h +2 -0
@@ -85,4 +85,6 @@ void vfio_user_set_handler(VFIODevice *vbasedev, void *reqarg);int vfio_user_validate_version (VFIODevice *vbasedev,Error **errp); +extern VFIODevIO vfio_dev_io_sock; +#endif /* VFIO_USER_H */
hw/vfio/pci.c +26 -0
@@ -3416,6 +3416,8 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)VFIODevice *vbasedev = &vdev->vbasedev;SocketAddress addr;VFIOProxy *proxy; +struct vfio_device_info info; +int ret;Error *err =NULL ;/*
@@ -3455,6 +3457,30 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp) vbasedev->fd =-1 ; vbasedev->type =VFIO_DEVICE_TYPE_PCI ; vbasedev->ops = &vfio_user_pci_ops; + vbasedev->io_ops = &vfio_dev_io_sock; + + ret =VDEV_GET_INFO (vbasedev, &info); +if (ret) { +error_setg_errno (errp, -ret,"get info failure" ); + goto error; + } +/* must be PCI */ +if ((info.flags &VFIO_DEVICE_FLAGS_PCI ) ==0 ) { +error_setg (errp,"remote device not PCI" ); + goto error; + } + + vbasedev->num_irqs = info.num_irqs; + vbasedev->num_regions = info.num_regions; + vbasedev->flags = info.flags; + vbasedev->reset_works = !!(info.flags &VFIO_DEVICE_FLAGS_RESET ); + +vfio_get_all_regions (vbasedev); +vfio_populate_device (vdev, &err); +if (err) { +error_propagate (errp, err); + goto error; + }return ;
hw/vfio/user.c +54 -0
63 lines not on this page · raw message
Signature · 1 line
1.8.3.1
RFC v5 22/23 vfio-user: add tracing to send/recv paths
In reply to a message not in the archive--- hw/vfio/user.c | 8 ++++++++ hw/vfio/trace-events | 5 +++++ 2 files changed, 13 insertions(+)
hw/vfio/user.c +8 -0
@@ -29,6 +29,8 @@#include "qapi/qmp/qstring.h" #include "qapi/qmp/qnum.h" #include "user.h" +#include "trace.h" +/* * These are to defend against a malign server trying
@@ -111,6 +113,8 @@ static int vfio_user_send_qio(VFIOProxy *proxy, VFIOUserMsg *msg)vfio_user_shutdown (proxy);error_report_err (local_err); } +trace_vfio_user_send_write (msg->hdr->id, ret); +return ret; }
@@ -227,6 +231,7 @@ static int vfio_user_complete(VFIOProxy *proxy, Error **errp) }return ret; } +trace_vfio_user_recv_read (msg->hdr->id, ret); msgleft -= ret; data += ret;
@@ -334,6 +339,8 @@ static int vfio_user_recv_one(VFIOProxy *proxy)error_setg (&local_err,"unknown message type" ); goto fatal; } +trace_vfio_user_recv_hdr (proxy->sockname, hdr.id, hdr.command, hdr.size, + hdr.flags);/* * For replies, find the matching pending request.
@@ -410,6 +417,7 @@ static int vfio_user_recv_one(VFIOProxy *proxy)if (ret <=0 ) { goto fatal; } +trace_vfio_user_recv_read (hdr.id, ret); msgleft -= ret; data += ret;
hw/vfio/trace-events +5 -0
@@ -165,3 +165,8 @@ vfio_load_state_device_data(const char *name, uint64_t data_offset, uint64_t dat vfio_load_cleanup(const char *name) " (%s)" 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 + +# user.c +vfio_user_recv_hdr(const char *name, uint16_t id, uint16_t cmd, uint32_t size, uint32_t flags) " (%s) id %x cmd %x size %x flags %x" +vfio_user_recv_read(uint16_t id, int read) " id %x read %x" +vfio_user_send_write(uint16_t id, int wrote) " id %x wrote %x"
Signature · 1 line
1.8.3.1
RFC v5 23/23 vfio-user: add dirty_bitmap stub until it support migration
In reply to a message not in the archive--- hw/vfio/user.c | 10 ++++++++++ 1 file changed, 10 insertions(+)
hw/vfio/user.c +10 -0
@@ -1626,6 +1626,15 @@ static int vfio_user_io_dma_unmap(VFIOContainer *container, container->async_ops); } +static int vfio_user_io_dirty_bitmap (VFIOContainer *container, +struct vfio_iommu_type1_dirty_bitmap *bitmap, +struct vfio_iommu_type1_dirty_bitmap_get *range) +{ + +/* vfio-user doesn't support migration */ +return -EINVAL ; +} +static void vfio_user_io_wait_commit (VFIOContainer *container) {vfio_user_wait_reqs (container->proxy);
@@ -1634,5 +1643,6 @@ static void vfio_user_io_wait_commit(VFIOContainer *container)VFIOContIO vfio_cont_io_sock = { .dma_map = vfio_user_io_dma_map, .dma_unmap = vfio_user_io_dma_unmap, + .dirty_bitmap = vfio_user_io_dirty_bitmap, .wait_commit = vfio_user_io_wait_commit, };
Signature · 1 line
1.8.3.1
RFC v5 17/23 vfio-user: dma map/unmap operations
In reply to a message not in the archiveAdd ability to do async operations during memory transactions
--- hw/vfio/user-protocol.h | 32 +++++++ include/hw/vfio/vfio-common.h | 9 +- hw/vfio/common.c | 63 +++++++++--- hw/vfio/user.c | 217 ++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 305 insertions(+), 16 deletions(-)
hw/vfio/user-protocol.h +32 -0
@@ -94,6 +94,31 @@ typedef struct {/* +* VFIO_USER_DMA_MAP +* imported from struct vfio_iommu_type1_dma_map +*/ +typedef struct { +VFIOUserHdr hdr; +uint32_t argsz; +uint32_t flags; +uint64_t offset;/* FD offset */ +uint64_t iova; +uint64_t size; +}VFIOUserDMAMap ; + +/* +* VFIO_USER_DMA_UNMAP +* imported from struct vfio_iommu_type1_dma_unmap +*/ +typedef struct { +VFIOUserHdr hdr; +uint32_t argsz; +uint32_t flags; +uint64_t iova; +uint64_t size; +}VFIOUserDMAUnmap ; + +/* * VFIO_USER_DEVICE_GET_INFO * imported from struct_device_info */
@@ -157,4 +182,11 @@ typedef struct { char data[]; } VFIOUserRegionRW; +/*imported from struct vfio_bitmap */ +typedef struct { +uint64_t pgsize; +uint64_t size; +char data[]; +}VFIOUserBitmap ; +#endif /* VFIO_USER_PROTOCOL_H */
include/hw/vfio/vfio-common.h +6 -3
@@ -90,6 +90,7 @@ typedef struct VFIOContainer {VFIOContIO *io_ops;bool initialized;bool dirty_pages_supported; +bool async_ops;uint64_t dirty_pgsizes;uint64_t max_dirty_bitmap_size;unsigned long pgsizes;
@@ -199,7 +200,7 @@ struct VFIODevIO { ((vdev)->io_ops->region_write((vdev), (nr), (off), (size), (data), (post)))struct VFIOContIO { -int (*dma_map)(VFIOContainer *container, +int (*dma_map)(VFIOContainer *container,MemoryRegion *mr,struct vfio_iommu_type1_dma_map *map); int (*dma_unmap)(VFIOContainer *container, struct vfio_iommu_type1_dma_unmap *unmap,
@@ -207,14 +208,16 @@ struct VFIOContIO {int (*dirty_bitmap)(VFIOContainer *container,struct vfio_iommu_type1_dirty_bitmap *bitmap,struct vfio_iommu_type1_dirty_bitmap_get *range); +void (*wait_commit)(VFIOContainer *container); }; -#define CONT_DMA_MAP (cont, map) \ - ((cont)->io_ops->dma_map((cont), (map))) +#define CONT_DMA_MAP (cont, mr, map) \ + ((cont)->io_ops->dma_map((cont), (mr), (map)))#define CONT_DMA_UNMAP (cont, unmap, bitmap) \ ((cont)->io_ops->dma_unmap((cont), (unmap), (bitmap)))#define CONT_DIRTY_BITMAP (cont, bitmap, range) \ ((cont)->io_ops->dirty_bitmap((cont), (bitmap), (range))) +#define CONT_WAIT_COMMIT (cont) ((cont)->io_ops->wait_commit(cont))extern VFIODevIO vfio_dev_io_ioctl;extern VFIOContIO vfio_cont_io_ioctl;
hw/vfio/common.c +50 -13
157 lines not on this page · raw message
hw/vfio/user.c +217 -0
248 lines not on this page · raw message
Signature · 1 line
1.8.3.1
RFC v5 2/23 vfio-user: add VFIO base abstract class
In reply to a message not in the archiveAdd an abstract base class both the kernel driver and user socket implementations can use to share code.
--- hw/vfio/pci.h | 16 +++++++-- hw/vfio/pci.c | 106 +++++++++++++++++++++++++++++++++++----------------------- 2 files changed, 78 insertions(+), 44 deletions(-)
hw/vfio/pci.h +14 -2
@@ -114,8 +114,13 @@ typedef struct VFIOMSIXInfo {unsigned long *pending; } VFIOMSIXInfo; -#define TYPE_VFIO_PCI "vfio-pci" -OBJECT_DECLARE_SIMPLE_TYPE(VFIOPCIDevice, VFIO_PCI) +/* +* TYPE_VFIO_PCI_BASE is an abstract type used to share code +* between VFIO implementations that use a kernel driver +* with those that use user sockets. +*/ +#define TYPE_VFIO_PCI_BASE "vfio-pci-base" +OBJECT_DECLARE_SIMPLE_TYPE(VFIOPCIDevice, VFIO_PCI_BASE)struct VFIOPCIDevice {PCIDevice pdev;
@@ -175,6 +180,13 @@ struct VFIOPCIDevice {Notifier irqchip_change_notifier; }; +#define TYPE_VFIO_PCI "vfio-pci" +OBJECT_DECLARE_SIMPLE_TYPE(VFIOKernPCIDevice, VFIO_PCI) + +struct VFIOKernPCIDevice { +VFIOPCIDevice device; +}; +/* Use uin32_t for vendor & device so PCI_ANY_ID expands and cannot match hw */ static inline bool vfio_pci_is (VFIOPCIDevice *vdev,uint32_t vendor,uint32_t device) {
hw/vfio/pci.c +64 -42
229 lines not on this page · raw message
Signature · 1 line
1.8.3.1
RFC v5 19/23 vfio-user: dma read/write operations
In reply to a message not in the archiveMessages from server to client that peform device DMA.
--- hw/vfio/user-protocol.h | 11 ++++++ hw/vfio/user.h | 4 ++ hw/vfio/pci.c | 100 ++++++++++++++++++++++++++++++++++++++++++++++++ hw/vfio/user.c | 60 ++++++++++++++++++++++++++++- 4 files changed, 174 insertions(+), 1 deletion(-)
hw/vfio/user-protocol.h +11 -0
@@ -182,6 +182,17 @@ typedef struct {char data[]; } VFIOUserRegionRW; +/* +* VFIO_USER_DMA_READ +* VFIO_USER_DMA_WRITE +*/ +typedef struct { +VFIOUserHdr hdr; +uint64_t offset; +uint32_t count; +char data[]; +}VFIOUserDMARW ; +/*imported from struct vfio_bitmap */ typedef struct { uint64_t pgsize;
hw/vfio/user.h +4 -0
@@ -82,9 +82,13 @@ typedef struct VFIOProxy {VFIOProxy *vfio_user_connect_dev (SocketAddress *addr,Error **errp);void vfio_user_disconnect (VFIOProxy *proxy); +uint64_t vfio_user_max_xfer (void );void vfio_user_set_handler (VFIODevice *vbasedev,void (*handler)(void *opaque,VFIOUserMsg *msg),void *reqarg); +void vfio_user_send_reply (VFIOProxy *proxy,VFIOUserHdr *hdr,int size); +void vfio_user_send_error (VFIOProxy *proxy,VFIOUserHdr *hdr,int error); +void vfio_user_putfds (VFIOUserMsg *msg);int vfio_user_validate_version (VFIODevice *vbasedev,Error **errp);extern VFIODevIO vfio_dev_io_sock;
hw/vfio/pci.c +100 -0
115 lines not on this page · raw message
hw/vfio/user.c +59 -1
78 lines not on this page · raw message
Signature · 1 line
1.8.3.1
RFC v5 20/23 vfio-user: pci reset
In reply to a message not in the archiveMessage to tell the server to reset the device.
--- hw/vfio/user.h | 1 + hw/vfio/pci.c | 15 +++++++++++++++ hw/vfio/user.c | 12 ++++++++++++ 3 files changed, 28 insertions(+)
hw/vfio/user.h +1 -0
@@ -90,6 +90,7 @@ void vfio_user_send_reply(VFIOProxy *proxy, VFIOUserHdr *hdr, int size);void vfio_user_send_error (VFIOProxy *proxy,VFIOUserHdr *hdr,int error);void vfio_user_putfds (VFIOUserMsg *msg);int vfio_user_validate_version (VFIODevice *vbasedev,Error **errp); +void vfio_user_reset (VFIOProxy *proxy);extern VFIODevIO vfio_dev_io_sock;extern VFIOContIO vfio_cont_io_sock;
hw/vfio/pci.c +15 -0
@@ -3821,6 +3821,20 @@ static void vfio_user_instance_finalize(Object *obj) } } +static void vfio_user_pci_reset (DeviceState *dev) +{ +VFIOPCIDevice *vdev =VFIO_PCI_BASE (dev); +VFIODevice *vbasedev = &vdev->vbasedev; + +vfio_pci_pre_reset (vdev); + +if (vbasedev->reset_works) { +vfio_user_reset (vbasedev->proxy); + } + +vfio_pci_post_reset (vdev); +} +static Property vfio_user_pci_dev_properties[] = {DEFINE_PROP_STRING ("socket" , VFIOUserPCIDevice, sock_name),DEFINE_PROP_BOOL ("secure-dma" , VFIOUserPCIDevice, secure_dma, false),
@@ -3834,6 +3848,7 @@ static void vfio_user_pci_dev_class_init(ObjectClass *klass, void *data)DeviceClass *dc =DEVICE_CLASS (klass);PCIDeviceClass *pdc =PCI_DEVICE_CLASS (klass); + dc->reset = vfio_user_pci_reset;device_class_set_props (dc, vfio_user_pci_dev_properties); dc->desc ="VFIO over socket PCI device assignment" ; pdc->realize = vfio_user_pci_realize;
hw/vfio/user.c +12 -0
@@ -1482,6 +1482,18 @@ static int vfio_user_region_write(VFIOProxy *proxy, uint8_t index, off_t offset,return ret; } +void vfio_user_reset (VFIOProxy *proxy) +{ +VFIOUserHdr msg; + +vfio_user_request_msg (&msg,VFIO_USER_DEVICE_RESET ,sizeof (msg),0 ); + +vfio_user_send_wait (proxy, &msg,NULL ,0 , false); +if (msg.flags &VFIO_USER_ERROR ) { +error_printf ("reset reply error %d\n" , msg.error_reply); + } +} +/* * Socket-based io_ops
Signature · 1 line
1.8.3.1
RFC v5 16/23 vfio-user: proxy container connect/disconnect
In reply to a message not in the archive--- hw/vfio/user.h | 1 + include/hw/vfio/vfio-common.h | 3 ++ hw/vfio/common.c | 105 ++++++++++++++++++++++++++++++++++++++++++ hw/vfio/pci.c | 25 ++++++++++ hw/vfio/user.c | 3 ++ 5 files changed, 137 insertions(+)
hw/vfio/user.h +1 -0
@@ -87,5 +87,6 @@ void vfio_user_set_handler(VFIODevice *vbasedev,int vfio_user_validate_version (VFIODevice *vbasedev,Error **errp);extern VFIODevIO vfio_dev_io_sock; +extern VFIOContIO vfio_cont_io_sock;#endif /* VFIO_USER_H */
include/hw/vfio/vfio-common.h +3 -0
@@ -94,6 +94,7 @@ typedef struct VFIOContainer {uint64_t max_dirty_bitmap_size;unsigned long pgsizes;unsigned int dma_max_mappings; +VFIOProxy *proxy; QLIST_HEAD(, VFIOGuestIOMMU) giommu_list; QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list; QLIST_HEAD(, VFIOGroup) group_list;
@@ -278,6 +279,8 @@ VFIOGroup *vfio_get_group(int groupid, AddressSpace *as, Error **errp);void vfio_put_group (VFIOGroup *group);int vfio_get_device (VFIOGroup *group,const char *name,VFIODevice *vbasedev,Error **errp); +void vfio_connect_proxy (VFIOProxy *proxy,VFIOGroup *group,AddressSpace *as); +void vfio_disconnect_proxy (VFIOGroup *group);extern const MemoryRegionOps vfio_region_ops; typedef QLIST_HEAD(VFIOGroupList, VFIOGroup) VFIOGroupList;
hw/vfio/common.c +105 -0
123 lines not on this page · raw message
hw/vfio/pci.c +25 -0
@@ -3562,6 +3562,7 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp)VFIODevice *vbasedev = &vdev->vbasedev;SocketAddress addr;VFIOProxy *proxy; +VFIOGroup *group =NULL ;struct vfio_device_info info;int ret;Error *err =NULL ;
@@ -3608,6 +3609,19 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error **errp) vbasedev->ops = &vfio_user_pci_ops; vbasedev->io_ops = &vfio_dev_io_sock; +/* +* each device gets its own group and container +* make them unrelated to any host IOMMU groupings +*/ + group =g_malloc0 (sizeof (*group)); + group->fd =-1 ; + group->groupid =-1 ; +QLIST_INIT (&group->device_list); +QLIST_INSERT_HEAD (&group->device_list, vbasedev, next); + vbasedev->group = group; + +vfio_connect_proxy (proxy, group,pci_device_iommu_address_space (pdev)); + ret =VDEV_GET_INFO (vbasedev, &info);if (ret) {error_setg_errno (errp, -ret,"get info failure" );
@@ -3673,6 +3687,10 @@ out_teardown:vfio_teardown_msi (vdev);vfio_bars_exit (vdev); error: +if (group !=NULL ) { +vfio_disconnect_proxy (group); +g_free (group); + }vfio_user_disconnect (proxy);error_prepend (errp,VFIO_MSG_PREFIX , vdev->vbasedev.name); }
@@ -3681,6 +3699,13 @@ static void vfio_user_instance_finalize(Object *obj) {VFIOPCIDevice *vdev =VFIO_PCI_BASE (obj);VFIODevice *vbasedev = &vdev->vbasedev; +VFIOGroup *group = vbasedev->group; + +if (group !=NULL ) { +vfio_disconnect_proxy (group); +g_free (group); + vbasedev->group =NULL ; + }if (vdev->msix !=NULL ) {vfio_user_msix_teardown (vdev);
hw/vfio/user.c +3 -0
@@ -1337,3 +1337,6 @@ VFIODevIO vfio_dev_io_sock = { .region_write = vfio_user_io_region_write, }; + +VFIOContIO vfio_cont_io_sock = { +};
Signature · 1 line
1.8.3.1
RFC v5 6/23 vfio-user: Define type vfio_user_pci_dev_info
In reply to a message not in the archiveNew class for vfio-user with its class and instance constructors and destructors, and its pci ops.
--- hw/vfio/pci.h | 8 +++++ hw/vfio/common.c | 5 ++++ hw/vfio/pci.c | 90 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ hw/vfio/Kconfig | 10 +++++++ 4 files changed, 113 insertions(+)
hw/vfio/pci.h +8 -0
@@ -187,6 +187,14 @@ struct VFIOKernPCIDevice {VFIOPCIDevice device; }; +#define TYPE_VFIO_USER_PCI "vfio-user-pci" +OBJECT_DECLARE_SIMPLE_TYPE(VFIOUserPCIDevice, VFIO_USER_PCI) + +struct VFIOUserPCIDevice { +VFIOPCIDevice device; +char *sock_name; +}; +/* Use uin32_t for vendor & device so PCI_ANY_ID expands and cannot match hw */ static inline bool vfio_pci_is (VFIOPCIDevice *vdev,uint32_t vendor,uint32_t device) {
hw/vfio/common.c +5 -0
@@ -1742,6 +1742,11 @@ void vfio_reset_handler(void *opaque) QLIST_FOREACH(group, &vfio_group_list, next) { QLIST_FOREACH(vbasedev, &group->device_list, next) {if (vbasedev->dev->realized && vbasedev->needs_reset) { +if (vbasedev->ops->vfio_hot_reset_multi ==NULL ) { +error_printf ("%s: No hot reset handler specified\n" , + vbasedev->name); +continue ; + } vbasedev->ops->vfio_hot_reset_multi (vbasedev); } }
hw/vfio/pci.c +90 -0
99 lines not on this page · raw message
hw/vfio/Kconfig +10 -0
@@ -2,6 +2,10 @@ config VFIO bool depends on LINUX +config VFIO_USER + bool + depends on VFIO + config VFIO_PCI bool default y
@@ -9,6 +13,12 @@ config VFIO_PCI select EDID depends on LINUX && PCI +config VFIO_USER_PCI + bool + default y + select VFIO_USER + depends on VFIO_PCI + config VFIO_CCW bool default y
Signature · 1 line
1.8.3.1