[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [xen staging-4.14] IOMMU/x86: maintain a per-device pseudo domain ID
commit 27b89fdd092907af40d1945ea7b05db398d39565 Author: Jan Beulich <jbeulich@xxxxxxxx> AuthorDate: Tue Apr 5 15:13:43 2022 +0200 Commit: Jan Beulich <jbeulich@xxxxxxxx> CommitDate: Tue Apr 5 15:13:43 2022 +0200 IOMMU/x86: maintain a per-device pseudo domain ID In order to subsequently enable per-device quarantine page tables, we'll need domain-ID-like identifiers to be inserted in the respective device (AMD) or context (Intel) table entries alongside the per-device page table root addresses. Make use of "real" domain IDs occupying only half of the value range coverable by domid_t. Note that in VT-d's iommu_alloc() I didn't want to introduce new memory leaks in case of error, but existing ones don't get plugged - that'll be the subject of a later change. The VT-d changes are slightly asymmetric, but this way we can avoid assigning pseudo domain IDs to devices which would never be mapped while still avoiding to add a new parameter to domain_context_unmap(). Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx> Reviewed-by: Paul Durrant <paul@xxxxxxx> Reviewed-by: Kevin Tian <kevin.tian@xxxxxxxxx> Reviewed-by: Roger Pau Monné <roger.pau@xxxxxxxxxx> master commit: 97af062b89d52c0ecf7af254b53345c97d438e33 master date: 2022-04-05 14:19:10 +0200 --- xen/drivers/passthrough/amd/iommu.h | 1 + xen/drivers/passthrough/amd/iommu_detect.c | 8 ++++ xen/drivers/passthrough/amd/pci_amd_iommu.c | 22 ++++++++- xen/drivers/passthrough/pci.c | 11 +++-- xen/drivers/passthrough/vtd/iommu.c | 69 ++++++++++++++++++++++++----- xen/drivers/passthrough/vtd/iommu.h | 1 + xen/drivers/passthrough/x86/iommu.c | 47 ++++++++++++++++++++ xen/include/asm-x86/iommu.h | 4 ++ xen/include/asm-x86/pci.h | 6 +++ 9 files changed, 153 insertions(+), 16 deletions(-) diff --git a/xen/drivers/passthrough/amd/iommu.h b/xen/drivers/passthrough/amd/iommu.h index b1194ca92f..79c6a5b5b0 100644 --- a/xen/drivers/passthrough/amd/iommu.h +++ b/xen/drivers/passthrough/amd/iommu.h @@ -96,6 +96,7 @@ struct amd_iommu { struct ring_buffer cmd_buffer; struct ring_buffer event_log; struct ring_buffer ppr_log; + unsigned long *domid_map; int exclusion_enable; int exclusion_allow_all; diff --git a/xen/drivers/passthrough/amd/iommu_detect.c b/xen/drivers/passthrough/amd/iommu_detect.c index 8312bb4b6f..a5fa647a18 100644 --- a/xen/drivers/passthrough/amd/iommu_detect.c +++ b/xen/drivers/passthrough/amd/iommu_detect.c @@ -180,6 +180,11 @@ int __init amd_iommu_detect_one_acpi( if ( rt ) goto out; + iommu->domid_map = iommu_init_domid(); + rt = -ENOMEM; + if ( !iommu->domid_map ) + goto out; + rt = pci_ro_device(iommu->seg, bus, PCI_DEVFN(dev, func)); if ( rt ) printk(XENLOG_ERR @@ -191,7 +196,10 @@ int __init amd_iommu_detect_one_acpi( out: if ( rt ) + { + xfree(iommu->domid_map); xfree(iommu); + } return rt; } diff --git a/xen/drivers/passthrough/amd/pci_amd_iommu.c b/xen/drivers/passthrough/amd/pci_amd_iommu.c index e87abbeb74..bd5f61fc3f 100644 --- a/xen/drivers/passthrough/amd/pci_amd_iommu.c +++ b/xen/drivers/passthrough/amd/pci_amd_iommu.c @@ -554,6 +554,8 @@ static int amd_iommu_add_device(u8 devfn, struct pci_dev *pdev) struct amd_iommu *iommu; u16 bdf; struct ivrs_mappings *ivrs_mappings; + bool fresh_domid = false; + int ret; if ( !pdev->domain ) return -EINVAL; @@ -617,7 +619,22 @@ static int amd_iommu_add_device(u8 devfn, struct pci_dev *pdev) spin_unlock_irqrestore(&iommu->lock, flags); } - return amd_iommu_setup_domain_device(pdev->domain, iommu, devfn, pdev); + if ( iommu_quarantine && pdev->arch.pseudo_domid == DOMID_INVALID ) + { + pdev->arch.pseudo_domid = iommu_alloc_domid(iommu->domid_map); + if ( pdev->arch.pseudo_domid == DOMID_INVALID ) + return -ENOSPC; + fresh_domid = true; + } + + ret = amd_iommu_setup_domain_device(pdev->domain, iommu, devfn, pdev); + if ( ret && fresh_domid ) + { + iommu_free_domid(pdev->arch.pseudo_domid, iommu->domid_map); + pdev->arch.pseudo_domid = DOMID_INVALID; + } + + return ret; } static int amd_iommu_remove_device(u8 devfn, struct pci_dev *pdev) @@ -642,6 +659,9 @@ static int amd_iommu_remove_device(u8 devfn, struct pci_dev *pdev) amd_iommu_disable_domain_device(pdev->domain, iommu, devfn, pdev); + iommu_free_domid(pdev->arch.pseudo_domid, iommu->domid_map); + pdev->arch.pseudo_domid = DOMID_INVALID; + ivrs_mappings = get_ivrs_mappings(pdev->seg); bdf = PCI_BDF2(pdev->bus, devfn); if ( amd_iommu_perdev_intremap && diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c index f15af59764..0dfe30e38a 100644 --- a/xen/drivers/passthrough/pci.c +++ b/xen/drivers/passthrough/pci.c @@ -339,6 +339,7 @@ static struct pci_dev *alloc_pdev(struct pci_seg *pseg, u8 bus, u8 devfn) *((u8*) &pdev->bus) = bus; *((u8*) &pdev->devfn) = devfn; pdev->domain = NULL; + pdev->arch.pseudo_domid = DOMID_INVALID; INIT_LIST_HEAD(&pdev->msi_list); pos = pci_find_cap_offset(pseg->nr, bus, PCI_SLOT(devfn), PCI_FUNC(devfn), @@ -1349,9 +1350,13 @@ static int _dump_pci_devices(struct pci_seg *pseg, void *arg) list_for_each_entry ( pdev, &pseg->alldevs_list, alldevs_list ) { - printk("%04x:%02x:%02x.%u - %pd - node %-3d - MSIs < ", - pseg->nr, pdev->bus, - PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn), pdev->domain, + printk("%04x:%02x:%02x.%u - ", pseg->nr, pdev->bus, + PCI_SLOT(pdev->devfn), PCI_FUNC(pdev->devfn)); + if ( pdev->domain == dom_io ) + printk("DomIO:%x", pdev->arch.pseudo_domid); + else + printk("%pd", pdev->domain); + printk(" - node %-3d - MSIs < ", (pdev->node != NUMA_NO_NODE) ? pdev->node : -1); list_for_each_entry ( msi, &pdev->msi_list, list ) printk("%d ", msi->irq); diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c index 82ed48b2a3..52e9ec38e6 100644 --- a/xen/drivers/passthrough/vtd/iommu.c +++ b/xen/drivers/passthrough/vtd/iommu.c @@ -22,6 +22,7 @@ #include <xen/sched.h> #include <xen/xmalloc.h> #include <xen/domain_page.h> +#include <xen/err.h> #include <xen/iocap.h> #include <xen/iommu.h> #include <xen/numa.h> @@ -1195,7 +1196,7 @@ int __init iommu_alloc(struct acpi_drhd_unit *drhd) { struct vtd_iommu *iommu; unsigned long sagaw, nr_dom; - int agaw; + int agaw, rc; if ( nr_iommus >= MAX_IOMMUS ) { @@ -1288,7 +1289,16 @@ int __init iommu_alloc(struct acpi_drhd_unit *drhd) if ( !iommu->domid_map ) return -ENOMEM; + iommu->pseudo_domid_map = iommu_init_domid(); + rc = -ENOMEM; + if ( !iommu->pseudo_domid_map ) + goto free; + return 0; + + free: + iommu_free(drhd); + return rc; } void __init iommu_free(struct acpi_drhd_unit *drhd) @@ -1311,6 +1321,7 @@ void __init iommu_free(struct acpi_drhd_unit *drhd) xfree(iommu->domid_bitmap); xfree(iommu->domid_map); + xfree(iommu->pseudo_domid_map); if ( iommu->msi.irq >= 0 ) destroy_irq(iommu->msi.irq); @@ -1591,8 +1602,8 @@ int domain_context_mapping_one( return rc ?: pdev && prev_dom; } -static int domain_context_unmap(struct domain *d, uint8_t devfn, - struct pci_dev *pdev); +static const struct acpi_drhd_unit *domain_context_unmap( + struct domain *d, uint8_t devfn, struct pci_dev *pdev); static int domain_context_mapping(struct domain *domain, u8 devfn, struct pci_dev *pdev) @@ -1600,6 +1611,7 @@ static int domain_context_mapping(struct domain *domain, u8 devfn, struct acpi_drhd_unit *drhd; const struct acpi_rmrr_unit *rmrr; paddr_t pgd_maddr = dom_iommu(domain)->arch.pgd_maddr; + domid_t orig_domid = pdev->arch.pseudo_domid; int ret = 0; unsigned int i, mode = 0; uint16_t seg = pdev->seg, bdf; @@ -1660,6 +1672,14 @@ static int domain_context_mapping(struct domain *domain, u8 devfn, break; case DEV_TYPE_PCIe_ENDPOINT: + if ( iommu_quarantine && orig_domid == DOMID_INVALID ) + { + pdev->arch.pseudo_domid = + iommu_alloc_domid(drhd->iommu->pseudo_domid_map); + if ( pdev->arch.pseudo_domid == DOMID_INVALID ) + return -ENOSPC; + } + if ( iommu_debug ) printk(VTDPREFIX "d%d:PCIe: map %04x:%02x:%02x.%u\n", domain->domain_id, seg, bus, @@ -1675,6 +1695,14 @@ static int domain_context_mapping(struct domain *domain, u8 devfn, break; case DEV_TYPE_PCI: + if ( iommu_quarantine && orig_domid == DOMID_INVALID ) + { + pdev->arch.pseudo_domid = + iommu_alloc_domid(drhd->iommu->pseudo_domid_map); + if ( pdev->arch.pseudo_domid == DOMID_INVALID ) + return -ENOSPC; + } + if ( iommu_debug ) printk(VTDPREFIX "d%d:PCI: map %04x:%02x:%02x.%u\n", domain->domain_id, seg, bus, @@ -1750,6 +1778,13 @@ static int domain_context_mapping(struct domain *domain, u8 devfn, if ( !ret && devfn == pdev->devfn ) pci_vtd_quirk(pdev); + if ( ret && drhd && orig_domid == DOMID_INVALID ) + { + iommu_free_domid(pdev->arch.pseudo_domid, + drhd->iommu->pseudo_domid_map); + pdev->arch.pseudo_domid = DOMID_INVALID; + } + return ret; } @@ -1832,8 +1867,10 @@ int domain_context_unmap_one( return rc; } -static int domain_context_unmap(struct domain *domain, u8 devfn, - struct pci_dev *pdev) +static const struct acpi_drhd_unit *domain_context_unmap( + struct domain *domain, + uint8_t devfn, + struct pci_dev *pdev) { struct acpi_drhd_unit *drhd; struct vtd_iommu *iommu; @@ -1843,7 +1880,7 @@ static int domain_context_unmap(struct domain *domain, u8 devfn, drhd = acpi_find_matched_drhd_unit(pdev); if ( !drhd ) - return -ENODEV; + return ERR_PTR(-ENODEV); iommu = drhd->iommu; switch ( pdev->type ) @@ -1854,7 +1891,7 @@ static int domain_context_unmap(struct domain *domain, u8 devfn, domain->domain_id, seg, bus, PCI_SLOT(devfn), PCI_FUNC(devfn)); if ( !is_hardware_domain(domain) ) - return -EPERM; + return ERR_PTR(-EPERM); goto out; case DEV_TYPE_PCIe_BRIDGE: @@ -1929,7 +1966,7 @@ static int domain_context_unmap(struct domain *domain, u8 devfn, check_cleanup_domid_map(domain, pdev, iommu); out: - return ret; + return ret ? ERR_PTR(ret) : drhd; } static void iommu_domain_teardown(struct domain *d) @@ -2153,16 +2190,17 @@ static int intel_iommu_enable_device(struct pci_dev *pdev) static int intel_iommu_remove_device(u8 devfn, struct pci_dev *pdev) { + const struct acpi_drhd_unit *drhd; struct acpi_rmrr_unit *rmrr; u16 bdf; - int ret, i; + unsigned int i; if ( !pdev->domain ) return -EINVAL; - ret = domain_context_unmap(pdev->domain, devfn, pdev); - if ( ret ) - return ret; + drhd = domain_context_unmap(pdev->domain, devfn, pdev); + if ( IS_ERR(drhd) ) + return PTR_ERR(drhd); for_each_rmrr_device ( rmrr, bdf, i ) { @@ -2179,6 +2217,13 @@ static int intel_iommu_remove_device(u8 devfn, struct pci_dev *pdev) rmrr->end_address, 0); } + if ( drhd ) + { + iommu_free_domid(pdev->arch.pseudo_domid, + drhd->iommu->pseudo_domid_map); + pdev->arch.pseudo_domid = DOMID_INVALID; + } + return 0; } diff --git a/xen/drivers/passthrough/vtd/iommu.h b/xen/drivers/passthrough/vtd/iommu.h index 503b07ffb7..be44fc017f 100644 --- a/xen/drivers/passthrough/vtd/iommu.h +++ b/xen/drivers/passthrough/vtd/iommu.h @@ -535,6 +535,7 @@ struct vtd_iommu { } flush; struct list_head ats_devices; + unsigned long *pseudo_domid_map; /* "pseudo" domain id bitmap */ unsigned long *domid_bitmap; /* domain id bitmap */ u16 *domid_map; /* domain id mapping array */ uint32_t version; diff --git a/xen/drivers/passthrough/x86/iommu.c b/xen/drivers/passthrough/x86/iommu.c index 2db74e5a54..bf18f2f3a5 100644 --- a/xen/drivers/passthrough/x86/iommu.c +++ b/xen/drivers/passthrough/x86/iommu.c @@ -375,6 +375,53 @@ void __hwdom_init arch_iommu_hwdom_init(struct domain *d) return; } +unsigned long *__init iommu_init_domid(void) +{ + if ( !iommu_quarantine ) + return ZERO_BLOCK_PTR; + + BUILD_BUG_ON(DOMID_MASK * 2U >= UINT16_MAX); + + return xzalloc_array(unsigned long, + BITS_TO_LONGS(UINT16_MAX - DOMID_MASK)); +} + +domid_t iommu_alloc_domid(unsigned long *map) +{ + /* + * This is used uniformly across all IOMMUs, such that on typical + * systems we wouldn't re-use the same ID very quickly (perhaps never). + */ + static unsigned int start; + unsigned int idx = find_next_zero_bit(map, UINT16_MAX - DOMID_MASK, start); + + ASSERT(pcidevs_locked()); + + if ( idx >= UINT16_MAX - DOMID_MASK ) + idx = find_first_zero_bit(map, UINT16_MAX - DOMID_MASK); + if ( idx >= UINT16_MAX - DOMID_MASK ) + return DOMID_INVALID; + + __set_bit(idx, map); + + start = idx + 1; + + return idx | (DOMID_MASK + 1); +} + +void iommu_free_domid(domid_t domid, unsigned long *map) +{ + ASSERT(pcidevs_locked()); + + if ( domid == DOMID_INVALID ) + return; + + ASSERT(domid > DOMID_MASK); + + if ( !__test_and_clear_bit(domid & DOMID_MASK, map) ) + BUG(); +} + /* * Local variables: * mode: C diff --git a/xen/include/asm-x86/iommu.h b/xen/include/asm-x86/iommu.h index aaf9455b8e..389417d198 100644 --- a/xen/include/asm-x86/iommu.h +++ b/xen/include/asm-x86/iommu.h @@ -130,6 +130,10 @@ int pi_update_irte(const struct pi_desc *pi_desc, const struct pirq *pirq, iommu_vcall(ops, sync_cache, addr, size); \ }) +unsigned long *iommu_init_domid(void); +domid_t iommu_alloc_domid(unsigned long *map); +void iommu_free_domid(domid_t domid, unsigned long *map); + #endif /* !__ARCH_X86_IOMMU_H__ */ /* * Local variables: diff --git a/xen/include/asm-x86/pci.h b/xen/include/asm-x86/pci.h index cc05045e9c..70ed48e309 100644 --- a/xen/include/asm-x86/pci.h +++ b/xen/include/asm-x86/pci.h @@ -15,6 +15,12 @@ struct arch_pci_dev { vmask_t used_vectors; + /* + * These fields are (de)initialized under pcidevs-lock. Other uses of + * them don't race (de)initialization and hence don't strictly need any + * locking. + */ + domid_t pseudo_domid; }; int pci_conf_write_intercept(unsigned int seg, unsigned int bdf, -- generated by git-patchbot for /home/xen/git/xen.git#staging-4.14
|
![]() |
Lists.xenproject.org is hosted with RackSpace, monitoring our |