Note that the partial device tree should avoid using the phandle 65000
which is reserved by the toolstack.
+=item B<passthrough="STRING">
+
+Specify whether IOMMU mappings are enabled for the domain and hence whether
+it will be enabled for passthrough hardware. Valid values for this option
+are:
+
+=over 4
+
+=item B<disabled>
+
+IOMMU mappings are disabled for the domain and so hardware may not be
+passed through.
+
+This option is the default if no passthrough hardware is specified in the
+domain's configuration.
+
+=item B<enabled>
+
+This option enables IOMMU mappings and selects an appropriate default
+operating mode (see below for details of the operating modes). For HVM/PVH
+domains running on platforms where the option is available, this is
+equivalent to B<share_pt>. Otherwise, and also for PV domains, this
+option is equivalent to B<sync_pt>.
+
+This option is the default if passthrough hardware is specified in the
+domain's configuration.
+
+=item B<sync_pt>
+
+This option means that IOMMU mappings will be synchronized with the
+domain's P2M table as follows:
+
+For a PV domain, all writable pages assigned to the domain are identity
+mapped by MFN in the IOMMU page table. Thus a device driver running in the
+domain may program passthrough hardware for DMA using MFN values
+(i.e. host/machine frame numbers) looked up in its P2M.
+
+For an HVM/PVH domain, all non-foreign RAM pages present in its P2M will be
+mapped by GFN in the IOMMU page table. Thus a device driver running in the
+domain may program passthrough hardware using GFN values (i.e. guest
+physical frame numbers) without any further translation.
+
+This option is not currently available on Arm.
+
+=item B<share_pt>
+
+This option is unavailable for a PV domain. For an HVM/PVH domain, this
+option means that the IOMMU will be programmed to directly reference the
+domain's P2M table as its page table. From the point of view of a device
+driver running in the domain this is functionally equivalent to B<sync_pt>
+but places less load on the hypervisor and so should generally be selected
+in preference. However, the availability of this option is hardware
+specific. If B<xl info> reports B<virt_caps> containing
+B<iommu_hap_pt_share> then this option may be used.
+
+=back
+
=back
=head2 Devices
*/
#define LIBXL_HAVE_BUILDINFO_IOMMU_MEMKB 1
+/*
+ * LIBXL_HAVE_CREATEINFO_PASSTHROUGH indicates that
+ * libxl_domain_create_info has a passthrough field (which is a
+ * libxl_passthrough enumeration) that indicates whether device pass-
+ * through is enabled for the domain and, if so, whether the IOMMU and
+ * HAP page tables may be shared or not.
+ */
+#define LIBXL_HAVE_CREATEINFO_PASSTHROUGH 1
+
/*
* libxl ABI compatibility
*
int libxl__domain_create_info_setdefault(libxl__gc *gc,
libxl_domain_create_info *c_info)
{
+ libxl_physinfo info;
+ int rc;
+
+ rc = libxl_get_physinfo(CTX, &info);
+ if (rc)
+ return rc;
+
if (!c_info->type) {
LOG(ERROR, "domain type unspecified");
return ERROR_INVAL;
libxl__arch_domain_create_info_setdefault(gc, c_info);
if (c_info->type != LIBXL_DOMAIN_TYPE_PV) {
- libxl_physinfo info;
- int rc = libxl_get_physinfo(CTX, &info);
-
- if (rc)
- return rc;
-
if (info.cap_hap)
libxl_defbool_setdefault(&c_info->hap, true);
else if (info.cap_shadow)
if (!c_info->ssidref)
c_info->ssidref = SECINITSID_DOMU;
+ if (info.cap_hvm_directio &&
+ (c_info->passthrough == LIBXL_PASSTHROUGH_ENABLED)) {
+ c_info->passthrough = ((c_info->type == LIBXL_DOMAIN_TYPE_PV) ||
+ !info.cap_iommu_hap_pt_share) ?
+ LIBXL_PASSTHROUGH_SYNC_PT : LIBXL_PASSTHROUGH_SHARE_PT;
+ }
+
return 0;
}
libxl_defbool_val(info->oos) ? 0 : XEN_DOMCTL_CDF_oos_off;
}
+ assert(info->passthrough != LIBXL_PASSTHROUGH_ENABLED);
+ LOG(DETAIL, "passthrough: %s",
+ libxl_passthrough_to_string(info->passthrough));
+
+ if (info->passthrough != LIBXL_PASSTHROUGH_DISABLED)
+ create.flags |= XEN_DOMCTL_CDF_iommu;
+
+ if (info->passthrough == LIBXL_PASSTHROUGH_SYNC_PT)
+ create.iommu_opts |= XEN_DOMCTL_IOMMU_no_sharept;
+
/* Ultimately, handle is an array of 16 uint8_t, same as uuid */
libxl_uuid_copy(ctx, (libxl_uuid *)&create.handle, &info->uuid);
(2, "LINUX")
])
+libxl_passthrough = Enumeration("passthrough", [
+ (0, "enabled"),
+ (1, "disabled"),
+ (2, "sync_pt"),
+ (3, "share_pt"),
+ ])
+
#
# Complex libxl types
#
("pool_name", string),
("run_hotplug_scripts",libxl_defbool),
("driver_domain",libxl_defbool),
+ ("passthrough", libxl_passthrough),
], dir=DIR_IN)
libxl_domain_restore_params = Struct("domain_restore_params", [
| CDF_XS_DOMAIN
| CDF_IOMMU
+type domain_create_iommu_opts =
+ | IOMMU_NO_SHAREPT
+
type domctl_create_config =
{
ssidref: int32;
handle: string;
flags: domain_create_flag list;
+ iommu_opts: domain_create_iommu_opts list;
max_vcpus: int;
max_evtchn_port: int;
max_grant_frames: int;
| CDF_OOS_OFF
| CDF_XS_DOMAIN
| CDF_IOMMU
+
+type domain_create_iommu_opts =
+ | IOMMU_NO_SHAREPT
+
type domctl_create_config = {
ssidref: int32;
handle: string;
flags: domain_create_flag list;
+ iommu_opts: domain_create_iommu_opts list;
max_vcpus: int;
max_evtchn_port: int;
max_grant_frames: int;
#define VAL_SSIDREF Field(config, 0)
#define VAL_HANDLE Field(config, 1)
#define VAL_FLAGS Field(config, 2)
-#define VAL_MAX_VCPUS Field(config, 3)
-#define VAL_MAX_EVTCHN_PORT Field(config, 4)
-#define VAL_MAX_GRANT_FRAMES Field(config, 5)
-#define VAL_MAX_MAPTRACK_FRAMES Field(config, 6)
-#define VAL_ARCH Field(config, 7)
+#define VAL_IOMMU_OPTS Field(config, 3)
+#define VAL_MAX_VCPUS Field(config, 4)
+#define VAL_MAX_EVTCHN_PORT Field(config, 5)
+#define VAL_MAX_GRANT_FRAMES Field(config, 6)
+#define VAL_MAX_MAPTRACK_FRAMES Field(config, 7)
+#define VAL_ARCH Field(config, 8)
uint32_t domid = 0;
int result;
/* ! XEN_DOMCTL_CDF_ XEN_DOMCTL_CDF_MAX max */
(VAL_FLAGS);
+ cfg.iommu_opts = ocaml_list_to_c_bitmap
+ /* ! domain_create_iommu_opts IOMMU_ lc */
+ /* ! XEN_DOMCTL_IOMMU_ XEN_DOMCTL_IOMMU_MAX max */
+ (VAL_IOMMU_OPTS);
+
arch_domconfig = Field(VAL_ARCH, 0);
switch ( Tag_val(VAL_ARCH) )
{
#undef VAL_MAX_GRANT_FRAMES
#undef VAL_MAX_EVTCHN_PORT
#undef VAL_MAX_VCPUS
+#undef VAL_IOMMU_OPTS
#undef VAL_FLAGS
#undef VAL_HANDLE
#undef VAL_SSIDREF
exit(1);
}
+ if (!xlu_cfg_get_list (config, "pci", &pcis, 0, 0)) {
+ d_config->num_pcidevs = 0;
+ d_config->pcidevs = NULL;
+ for(i = 0; (buf = xlu_cfg_get_listitem (pcis, i)) != NULL; i++) {
+ libxl_device_pci *pcidev;
+
+ pcidev = ARRAY_EXTEND_INIT_NODEVID(d_config->pcidevs,
+ d_config->num_pcidevs,
+ libxl_device_pci_init);
+ pcidev->msitranslate = pci_msitranslate;
+ pcidev->power_mgmt = pci_power_mgmt;
+ pcidev->permissive = pci_permissive;
+ pcidev->seize = pci_seize;
+ /*
+ * Like other pci option, the per-device policy always follows
+ * the global policy by default.
+ */
+ pcidev->rdm_policy = b_info->u.hvm.rdm.policy;
+ e = xlu_pci_parse_bdf(config, pcidev, buf);
+ if (e) {
+ fprintf(stderr,
+ "unable to parse PCI BDF `%s' for passthrough\n",
+ buf);
+ exit(-e);
+ }
+ }
+ if (d_config->num_pcidevs && c_info->type == LIBXL_DOMAIN_TYPE_PV)
+ libxl_defbool_set(&b_info->u.pv.e820_host, true);
+ }
+
+ if (!xlu_cfg_get_list (config, "dtdev", &dtdevs, 0, 0)) {
+ d_config->num_dtdevs = 0;
+ d_config->dtdevs = NULL;
+ for (i = 0; (buf = xlu_cfg_get_listitem(dtdevs, i)) != NULL; i++) {
+ libxl_device_dtdev *dtdev;
+
+ dtdev = ARRAY_EXTEND_INIT_NODEVID(d_config->dtdevs,
+ d_config->num_dtdevs,
+ libxl_device_dtdev_init);
+
+ dtdev->path = strdup(buf);
+ if (dtdev->path == NULL) {
+ fprintf(stderr, "unable to duplicate string for dtdevs\n");
+ exit(-1);
+ }
+ }
+ }
+
+ if (xlu_cfg_get_string(config, "passthrough", &buf, 0)) {
+ c_info->passthrough =
+ (d_config->num_pcidevs || d_config->num_dtdevs)
+ ? LIBXL_PASSTHROUGH_ENABLED : LIBXL_PASSTHROUGH_DISABLED;
+ } else {
+ libxl_passthrough o;
+
+ e = libxl_passthrough_from_string(buf, &o);
+ if (e) {
+ fprintf(stderr,
+ "ERROR: unknown passthrough option '%s'\n",
+ buf);
+ exit(-ERROR_FAIL);
+ }
+
+ c_info->passthrough = o;
+ }
+
+ switch (c_info->passthrough) {
+ case LIBXL_PASSTHROUGH_ENABLED:
+ /*
+ * Choose a suitable default. libxl would also do this but
+ * choosing here allows the code calculating 'iommu_memkb'
+ * below make an informed decision.
+ */
+ c_info->passthrough =
+ (c_info->type == LIBXL_DOMAIN_TYPE_PV) || !iommu_hap_pt_share
+ ? LIBXL_PASSTHROUGH_SYNC_PT : LIBXL_PASSTHROUGH_SHARE_PT;
+ break;
+
+ case LIBXL_PASSTHROUGH_DISABLED:
+ if (d_config->num_pcidevs || d_config->num_dtdevs) {
+ fprintf(stderr,
+ "ERROR: passthrough disabled but devices are specified\n");
+ exit(-ERROR_FAIL);
+ }
+ break;
+ case LIBXL_PASSTHROUGH_SHARE_PT:
+ if (c_info->type == LIBXL_DOMAIN_TYPE_PV) {
+ fprintf(stderr,
+ "ERROR: passthrough=\"share_pt\" not valid for PV domain\n");
+ exit(-ERROR_FAIL);
+ } else if (!iommu_hap_pt_share) {
+ fprintf(stderr,
+ "ERROR: passthrough=\"share_pt\" not supported on this platform\n");
+ exit(-ERROR_FAIL);
+ }
+ break;
+ case LIBXL_PASSTHROUGH_SYNC_PT:
+ break;
+ }
+
+ if ((c_info->passthrough != LIBXL_PASSTHROUGH_DISABLED) &&
+ !iommu_enabled) {
+ fprintf(stderr,
+ "ERROR: passthrough not supported on this platform\n");
+ exit(-ERROR_FAIL);
+ }
+
/* libxl_get_required_shadow_memory() and
* libxl_get_required_iommu_memory() must be called after final values
* (default or specified) for vcpus and memory are set, because the
: libxl_get_required_shadow_memory(b_info->max_memkb,
b_info->max_vcpus);
- /* No IOMMU reservation is needed if either the IOMMU is disabled or it
- * can share the P2M. */
- b_info->iommu_memkb = (!iommu_enabled || iommu_hap_pt_share)
- ? 0
- : libxl_get_required_iommu_memory(b_info->max_memkb);
+ /* No IOMMU reservation is needed if passthrough mode is not 'sync_pt' */
+ b_info->iommu_memkb = (c_info->passthrough == LIBXL_PASSTHROUGH_SYNC_PT)
+ ? libxl_get_required_iommu_memory(b_info->max_memkb)
+ : 0;
xlu_cfg_get_defbool(config, "nomigrate", &b_info->disable_migrate, 0);
}
}
- if (!xlu_cfg_get_list (config, "pci", &pcis, 0, 0)) {
- d_config->num_pcidevs = 0;
- d_config->pcidevs = NULL;
- for(i = 0; (buf = xlu_cfg_get_listitem (pcis, i)) != NULL; i++) {
- libxl_device_pci *pcidev;
-
- pcidev = ARRAY_EXTEND_INIT_NODEVID(d_config->pcidevs,
- d_config->num_pcidevs,
- libxl_device_pci_init);
- pcidev->msitranslate = pci_msitranslate;
- pcidev->power_mgmt = pci_power_mgmt;
- pcidev->permissive = pci_permissive;
- pcidev->seize = pci_seize;
- /*
- * Like other pci option, the per-device policy always follows
- * the global policy by default.
- */
- pcidev->rdm_policy = b_info->u.hvm.rdm.policy;
- e = xlu_pci_parse_bdf(config, pcidev, buf);
- if (e) {
- fprintf(stderr,
- "unable to parse PCI BDF `%s' for passthrough\n",
- buf);
- exit(-e);
- }
- }
- if (d_config->num_pcidevs && c_info->type == LIBXL_DOMAIN_TYPE_PV)
- libxl_defbool_set(&b_info->u.pv.e820_host, true);
- }
-
- if (!xlu_cfg_get_list (config, "dtdev", &dtdevs, 0, 0)) {
- d_config->num_dtdevs = 0;
- d_config->dtdevs = NULL;
- for (i = 0; (buf = xlu_cfg_get_listitem(dtdevs, i)) != NULL; i++) {
- libxl_device_dtdev *dtdev;
-
- dtdev = ARRAY_EXTEND_INIT_NODEVID(d_config->dtdevs,
- d_config->num_dtdevs,
- libxl_device_dtdev_init);
-
- dtdev->path = strdup(buf);
- if (dtdev->path == NULL) {
- fprintf(stderr, "unable to duplicate string for dtdevs\n");
- exit(-1);
- }
- }
- }
-
if (!xlu_cfg_get_list(config, "usbctrl", &usbctrls, 0, 0)) {
d_config->num_usbctrls = 0;
d_config->usbctrls = NULL;
return -EINVAL;
}
+ /* The P2M table must always be shared between the CPU and the IOMMU */
+ if ( config->iommu_opts & XEN_DOMCTL_IOMMU_no_sharept )
+ {
+ dprintk(XENLOG_INFO,
+ "Unsupported iommu option: XEN_DOMCTL_IOMMU_no_sharept\n");
+ return -EINVAL;
+ }
+
/* Fill in the native GIC version, passed back to the toolstack. */
if ( config->arch.gic_version == XEN_DOMCTL_CONFIG_GIC_NATIVE )
{
ASSERT(config != NULL);
/* p2m_init relies on some value initialized by the IOMMU subsystem */
- if ( (rc = iommu_domain_init(d)) != 0 )
+ if ( (rc = iommu_domain_init(d, config->iommu_opts)) != 0 )
goto fail;
if ( (rc = p2m_init(d)) != 0 )
if ( (rc = init_domain_irq_mapping(d)) != 0 )
goto fail;
- if ( (rc = iommu_domain_init(d)) != 0 )
+ if ( (rc = iommu_domain_init(d, config->iommu_opts)) != 0 )
goto fail;
psr_domain_init(d);
return -EINVAL;
}
+ if ( !(config->flags & XEN_DOMCTL_CDF_iommu) && config->iommu_opts )
+ {
+ dprintk(XENLOG_INFO,
+ "IOMMU options specified but IOMMU not enabled\n");
+ return -EINVAL;
+ }
+
if ( config->max_vcpus < 1 )
{
dprintk(XENLOG_INFO, "No vCPUS\n");
rover = dom;
}
- /*
- * For now, make sure the createdomain IOMMU flag is set if the
- * IOMMU is enabled. When the flag comes under toolstack control
- * this can go away.
- */
- if ( op->u.createdomain.flags & XEN_DOMCTL_CDF_iommu )
- {
- ASSERT_UNREACHABLE();
- return -EINVAL;
- }
- if ( iommu_enabled )
- op->u.createdomain.flags |= XEN_DOMCTL_CDF_iommu;
-
d = domain_create(dom, &op->u.createdomain, false);
if ( IS_ERR(d) )
{
iommu_hwdom_strict = true;
}
-int iommu_domain_init(struct domain *d)
+int iommu_domain_init(struct domain *d, unsigned int opts)
{
struct domain_iommu *hd = dom_iommu(d);
int ret = 0;
if ( is_hardware_domain(d) )
check_hwdom_reqs(d); /* may modify iommu_hwdom_strict */
+ /*
+ * Use shared page tables for HAP and IOMMU if the global option
+ * is enabled (from which we can infer the h/w is capable) and
+ * the domain options do not disallow it. HAP must, of course, also
+ * be enabled.
+ */
+ hd->hap_pt_share = hap_enabled(d) && iommu_hap_pt_share &&
+ !(opts & XEN_DOMCTL_IOMMU_no_sharept);
+
/*
* NB: 'relaxed' h/w domains don't need the IOMMU mappings to be kept
* in-sync with their assigned pages because all host RAM will be
if ( !is_hardware_domain(d) || iommu_hwdom_strict )
hd->need_sync = !iommu_use_hap_pt(d);
+ ASSERT(!(hd->need_sync && hd->hap_pt_share));
+
return 0;
}
#include "hvm/save.h"
#include "memory.h"
-#define XEN_DOMCTL_INTERFACE_VERSION 0x00000011
+#define XEN_DOMCTL_INTERFACE_VERSION 0x00000012
/*
* NB. xen_domctl.domain is an IN/OUT parameter for this operation.
uint32_t flags;
+#define _XEN_DOMCTL_IOMMU_no_sharept 0
+#define XEN_DOMCTL_IOMMU_no_sharept (1U << _XEN_DOMCTL_IOMMU_no_sharept)
+
+/* Max XEN_DOMCTL_IOMMU_* constant. Used for ABI checking. */
+#define XEN_DOMCTL_IOMMU_MAX XEN_DOMCTL_IOMMU_no_sharept
+
+ uint32_t iommu_opts;
+
/*
* Various domain limits, which impact the quantity of resources (global
* mapping space, xenheap, etc) a guest may consume.
int iommu_setup(void);
int iommu_hardware_setup(void);
-int iommu_domain_init(struct domain *d);
+int iommu_domain_init(struct domain *d, unsigned int opts);
void iommu_hwdom_init(struct domain *d);
void iommu_domain_destroy(struct domain *d);
/* Features supported by the IOMMU */
DECLARE_BITMAP(features, IOMMU_FEAT_count);
+ /* Does the guest share HAP mapping with the IOMMU? */
+ bool hap_pt_share;
+
/*
- * Does the guest reqire mappings to be synchonized, to maintain
- * the default dfn == pfn map. (See comment on dfn at the top of
- * include/xen/mm.h).
+ * Does the guest require mappings to be synchronized, to maintain
+ * the default dfn == pfn map? (See comment on dfn at the top of
+ * include/xen/mm.h). Note that hap_pt_share == false does not
+ * necessarily imply this is true.
*/
bool need_sync;
};
#define iommu_clear_feature(d, f) clear_bit(f, dom_iommu(d)->features)
/* Are we using the domain P2M table as its IOMMU pagetable? */
-#define iommu_use_hap_pt(d) \
- (hap_enabled(d) && is_iommu_enabled(d) && iommu_hap_pt_share)
+#define iommu_use_hap_pt(d) (dom_iommu(d)->hap_pt_share)
/* Does the IOMMU pagetable need to be kept synchronized with the P2M */
#ifdef CONFIG_HAS_PASSTHROUGH
projects / xen.git / commitdiff