From a5c57fd2e9bd1c8ea8613a8f94fd0be5eccbf321 Mon Sep 17 00:00:00 2001 From: Gaurav Batra Date: Thu, 15 Feb 2024 16:18:33 -0600 Subject: powerpc/pseries/iommu: DLPAR add doesn't completely initialize pci_controller When a PCI device is dynamically added, the kernel oopses with a NULL pointer dereference: BUG: Kernel NULL pointer dereference on read at 0x00000030 Faulting instruction address: 0xc0000000006bbe5c Oops: Kernel access of bad area, sig: 11 [#1] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries Modules linked in: rpadlpar_io rpaphp rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache netfs xsk_diag bonding nft_compat nf_tables nfnetlink rfkill binfmt_misc dm_multipath rpcrdma sunrpc rdma_ucm ib_srpt ib_isert iscsi_target_mod target_core_mod ib_umad ib_iser libiscsi scsi_transport_iscsi ib_ipoib rdma_cm iw_cm ib_cm mlx5_ib ib_uverbs ib_core pseries_rng drm drm_panel_orientation_quirks xfs libcrc32c mlx5_core mlxfw sd_mod t10_pi sg tls ibmvscsi ibmveth scsi_transport_srp vmx_crypto pseries_wdt psample dm_mirror dm_region_hash dm_log dm_mod fuse CPU: 17 PID: 2685 Comm: drmgr Not tainted 6.7.0-203405+ #66 Hardware name: IBM,9080-HEX POWER10 (raw) 0x800200 0xf000006 of:IBM,FW1060.00 (NH1060_008) hv:phyp pSeries NIP: c0000000006bbe5c LR: c000000000a13e68 CTR: c0000000000579f8 REGS: c00000009924f240 TRAP: 0300 Not tainted (6.7.0-203405+) MSR: 8000000000009033 CR: 24002220 XER: 20040006 CFAR: c000000000a13e64 DAR: 0000000000000030 DSISR: 40000000 IRQMASK: 0 ... NIP sysfs_add_link_to_group+0x34/0x94 LR iommu_device_link+0x5c/0x118 Call Trace: iommu_init_device+0x26c/0x318 (unreliable) iommu_device_link+0x5c/0x118 iommu_init_device+0xa8/0x318 iommu_probe_device+0xc0/0x134 iommu_bus_notifier+0x44/0x104 notifier_call_chain+0xb8/0x19c blocking_notifier_call_chain+0x64/0x98 bus_notify+0x50/0x7c device_add+0x640/0x918 pci_device_add+0x23c/0x298 of_create_pci_dev+0x400/0x884 of_scan_pci_dev+0x124/0x1b0 __of_scan_bus+0x78/0x18c pcibios_scan_phb+0x2a4/0x3b0 init_phb_dynamic+0xb8/0x110 dlpar_add_slot+0x170/0x3b8 [rpadlpar_io] add_slot_store.part.0+0xb4/0x130 [rpadlpar_io] kobj_attr_store+0x2c/0x48 sysfs_kf_write+0x64/0x78 kernfs_fop_write_iter+0x1b0/0x290 vfs_write+0x350/0x4a0 ksys_write+0x84/0x140 system_call_exception+0x124/0x330 system_call_vectored_common+0x15c/0x2ec Commit a940904443e4 ("powerpc/iommu: Add iommu_ops to report capabilities and allow blocking domains") broke DLPAR add of PCI devices. The above added iommu_device structure to pci_controller. During system boot, PCI devices are discovered and this newly added iommu_device structure is initialized by a call to iommu_device_register(). During DLPAR add of a PCI device, a new pci_controller structure is allocated but there are no calls made to iommu_device_register() interface. Fix is to register the iommu device during DLPAR add as well. Fixes: a940904443e4 ("powerpc/iommu: Add iommu_ops to report capabilities and allow blocking domains") Signed-off-by: Gaurav Batra Reviewed-by: Brian King Signed-off-by: Michael Ellerman Link: https://msgid.link/20240215221833.4817-1-gbatra@linux.ibm.com --- arch/powerpc/include/asm/ppc-pci.h | 10 ++++++++++ arch/powerpc/kernel/iommu.c | 23 +++++++++++++++++------ arch/powerpc/platforms/pseries/pci_dlpar.c | 4 ++++ 3 files changed, 31 insertions(+), 6 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/include/asm/ppc-pci.h b/arch/powerpc/include/asm/ppc-pci.h index ce2b1b5eebdd..a8b7e8682f5b 100644 --- a/arch/powerpc/include/asm/ppc-pci.h +++ b/arch/powerpc/include/asm/ppc-pci.h @@ -30,6 +30,16 @@ void *pci_traverse_device_nodes(struct device_node *start, void *data); extern void pci_devs_phb_init_dynamic(struct pci_controller *phb); +#if defined(CONFIG_IOMMU_API) && (defined(CONFIG_PPC_PSERIES) || \ + defined(CONFIG_PPC_POWERNV)) +extern void ppc_iommu_register_device(struct pci_controller *phb); +extern void ppc_iommu_unregister_device(struct pci_controller *phb); +#else +static inline void ppc_iommu_register_device(struct pci_controller *phb) { } +static inline void ppc_iommu_unregister_device(struct pci_controller *phb) { } +#endif + + /* From rtas_pci.h */ extern void init_pci_config_tokens (void); extern unsigned long get_phb_buid (struct device_node *); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index df17b33b89d1..2c0173e7094d 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -1341,7 +1341,7 @@ static struct iommu_device *spapr_tce_iommu_probe_device(struct device *dev) struct pci_controller *hose; if (!dev_is_pci(dev)) - return ERR_PTR(-EPERM); + return ERR_PTR(-ENODEV); pdev = to_pci_dev(dev); hose = pdev->bus->sysdata; @@ -1390,6 +1390,21 @@ static const struct attribute_group *spapr_tce_iommu_groups[] = { NULL, }; +void ppc_iommu_register_device(struct pci_controller *phb) +{ + iommu_device_sysfs_add(&phb->iommu, phb->parent, + spapr_tce_iommu_groups, "iommu-phb%04x", + phb->global_number); + iommu_device_register(&phb->iommu, &spapr_tce_iommu_ops, + phb->parent); +} + +void ppc_iommu_unregister_device(struct pci_controller *phb) +{ + iommu_device_unregister(&phb->iommu); + iommu_device_sysfs_remove(&phb->iommu); +} + /* * This registers IOMMU devices of PHBs. This needs to happen * after core_initcall(iommu_init) + postcore_initcall(pci_driver_init) and @@ -1400,11 +1415,7 @@ static int __init spapr_tce_setup_phb_iommus_initcall(void) struct pci_controller *hose; list_for_each_entry(hose, &hose_list, list_node) { - iommu_device_sysfs_add(&hose->iommu, hose->parent, - spapr_tce_iommu_groups, "iommu-phb%04x", - hose->global_number); - iommu_device_register(&hose->iommu, &spapr_tce_iommu_ops, - hose->parent); + ppc_iommu_register_device(hose); } return 0; } diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c index 4ba824568119..4448386268d9 100644 --- a/arch/powerpc/platforms/pseries/pci_dlpar.c +++ b/arch/powerpc/platforms/pseries/pci_dlpar.c @@ -35,6 +35,8 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn) pseries_msi_allocate_domains(phb); + ppc_iommu_register_device(phb); + /* Create EEH devices for the PHB */ eeh_phb_pe_create(phb); @@ -76,6 +78,8 @@ int remove_phb_dynamic(struct pci_controller *phb) } } + ppc_iommu_unregister_device(phb); + pseries_msi_free_domains(phb); /* Keep a reference so phb isn't freed yet */ -- cgit v1.2.3 From 20c8c4dafe93e82441583e93bd68c0d256d7bed4 Mon Sep 17 00:00:00 2001 From: Amit Machhiwal Date: Wed, 7 Feb 2024 11:15:26 +0530 Subject: KVM: PPC: Book3S HV: Fix L2 guest reboot failure due to empty 'arch_compat' Currently, rebooting a pseries nested qemu-kvm guest (L2) results in below error as L1 qemu sends PVR value 'arch_compat' == 0 via ppc_set_compat ioctl. This triggers a condition failure in kvmppc_set_arch_compat() resulting in an EINVAL. qemu-system-ppc64: Unable to set CPU compatibility mode in KVM: Invalid argument Also, a value of 0 for arch_compat generally refers the default compatibility of the host. But, arch_compat, being a Guest Wide Element in nested API v2, cannot be set to 0 in GSB as PowerVM (L0) expects a non-zero value. A value of 0 triggers a kernel trap during a reboot and consequently causes it to fail: [ 22.106360] reboot: Restarting system KVM: unknown exit, hardware reason ffffffffffffffea NIP 0000000000000100 LR 000000000000fe44 CTR 0000000000000000 XER 0000000020040092 CPU#0 MSR 0000000000001000 HID0 0000000000000000 HF 6c000000 iidx 3 didx 3 TB 00000000 00000000 DECR 0 GPR00 0000000000000000 0000000000000000 c000000002a8c300 000000007fe00000 GPR04 0000000000000000 0000000000000000 0000000000001002 8000000002803033 GPR08 000000000a000000 0000000000000000 0000000000000004 000000002fff0000 GPR12 0000000000000000 c000000002e10000 0000000105639200 0000000000000004 GPR16 0000000000000000 000000010563a090 0000000000000000 0000000000000000 GPR20 0000000105639e20 00000001056399c8 00007fffe54abab0 0000000105639288 GPR24 0000000000000000 0000000000000001 0000000000000001 0000000000000000 GPR28 0000000000000000 0000000000000000 c000000002b30840 0000000000000000 CR 00000000 [ - - - - - - - - ] RES 000@ffffffffffffffff SRR0 0000000000000000 SRR1 0000000000000000 PVR 0000000000800200 VRSAVE 0000000000000000 SPRG0 0000000000000000 SPRG1 0000000000000000 SPRG2 0000000000000000 SPRG3 0000000000000000 SPRG4 0000000000000000 SPRG5 0000000000000000 SPRG6 0000000000000000 SPRG7 0000000000000000 HSRR0 0000000000000000 HSRR1 0000000000000000 CFAR 0000000000000000 LPCR 0000000000020400 PTCR 0000000000000000 DAR 0000000000000000 DSISR 0000000000000000 kernel:trap=0xffffffea | pc=0x100 | msr=0x1000 This patch updates kvmppc_set_arch_compat() to use the host PVR value if 'compat_pvr' == 0 indicating that qemu doesn't want to enforce any specific PVR compat mode. The relevant part of the code might need a rework if PowerVM implements a support for `arch_compat == 0` in nestedv2 API. Fixes: 19d31c5f1157 ("KVM: PPC: Add support for nestedv2 guests") Reviewed-by: "Aneesh Kumar K.V (IBM)" Reviewed-by: Vaibhav Jain Signed-off-by: Amit Machhiwal Signed-off-by: Michael Ellerman Link: https://msgid.link/20240207054526.3720087-1-amachhiw@linux.ibm.com --- arch/powerpc/kvm/book3s_hv.c | 26 ++++++++++++++++++++++++-- arch/powerpc/kvm/book3s_hv_nestedv2.c | 20 ++++++++++++++++++-- 2 files changed, 42 insertions(+), 4 deletions(-) (limited to 'arch') diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 52427fc2a33f..0b921704da45 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -391,6 +391,24 @@ static void kvmppc_set_pvr_hv(struct kvm_vcpu *vcpu, u32 pvr) /* Dummy value used in computing PCR value below */ #define PCR_ARCH_31 (PCR_ARCH_300 << 1) +static inline unsigned long map_pcr_to_cap(unsigned long pcr) +{ + unsigned long cap = 0; + + switch (pcr) { + case PCR_ARCH_300: + cap = H_GUEST_CAP_POWER9; + break; + case PCR_ARCH_31: + cap = H_GUEST_CAP_POWER10; + break; + default: + break; + } + + return cap; +} + static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) { unsigned long host_pcr_bit = 0, guest_pcr_bit = 0, cap = 0; @@ -424,11 +442,9 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) break; case PVR_ARCH_300: guest_pcr_bit = PCR_ARCH_300; - cap = H_GUEST_CAP_POWER9; break; case PVR_ARCH_31: guest_pcr_bit = PCR_ARCH_31; - cap = H_GUEST_CAP_POWER10; break; default: return -EINVAL; @@ -440,6 +456,12 @@ static int kvmppc_set_arch_compat(struct kvm_vcpu *vcpu, u32 arch_compat) return -EINVAL; if (kvmhv_on_pseries() && kvmhv_is_nestedv2()) { + /* + * 'arch_compat == 0' would mean the guest should default to + * L1's compatibility. In this case, the guest would pick + * host's PCR and evaluate the corresponding capabilities. + */ + cap = map_pcr_to_cap(guest_pcr_bit); if (!(cap & nested_capabilities)) return -EINVAL; } diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c index 5378eb40b162..8e6f5355f08b 100644 --- a/arch/powerpc/kvm/book3s_hv_nestedv2.c +++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c @@ -138,6 +138,7 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb, vector128 v; int rc, i; u16 iden; + u32 arch_compat = 0; vcpu = gsm->data; @@ -347,8 +348,23 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb, break; } case KVMPPC_GSID_LOGICAL_PVR: - rc = kvmppc_gse_put_u32(gsb, iden, - vcpu->arch.vcore->arch_compat); + /* + * Though 'arch_compat == 0' would mean the default + * compatibility, arch_compat, being a Guest Wide + * Element, cannot be filled with a value of 0 in GSB + * as this would result into a kernel trap. + * Hence, when `arch_compat == 0`, arch_compat should + * default to L1's PVR. + */ + if (!vcpu->arch.vcore->arch_compat) { + if (cpu_has_feature(CPU_FTR_ARCH_31)) + arch_compat = PVR_ARCH_31; + else if (cpu_has_feature(CPU_FTR_ARCH_300)) + arch_compat = PVR_ARCH_300; + } else { + arch_compat = vcpu->arch.vcore->arch_compat; + } + rc = kvmppc_gse_put_u32(gsb, iden, arch_compat); break; } -- cgit v1.2.3