diff --git a/.gitlab-ci.d/buildtest.yml b/.gitlab-ci.d/buildtest.yml index 1931b77b49..6c05c46397 100644 --- a/.gitlab-ci.d/buildtest.yml +++ b/.gitlab-ci.d/buildtest.yml @@ -41,8 +41,7 @@ build-system-ubuntu: job: amd64-ubuntu2004-container variables: IMAGE: ubuntu2004 - CONFIGURE_ARGS: --enable-docs --enable-fdt=system --enable-slirp=system - --enable-capstone + CONFIGURE_ARGS: --enable-docs --enable-fdt=system --enable-capstone TARGETS: aarch64-softmmu alpha-softmmu cris-softmmu hppa-softmmu microblazeel-softmmu mips64el-softmmu MAKE_CHECK_ARGS: check-build @@ -120,7 +119,7 @@ build-system-fedora: variables: IMAGE: fedora CONFIGURE_ARGS: --disable-gcrypt --enable-nettle --enable-docs - --enable-fdt=system --enable-slirp=system --enable-capstone + --enable-fdt=system --enable-slirp --enable-capstone TARGETS: tricore-softmmu microblaze-softmmu mips-softmmu xtensa-softmmu m68k-softmmu riscv32-softmmu ppc-softmmu sparc64-softmmu MAKE_CHECK_ARGS: check-build @@ -339,10 +338,8 @@ clang-user: # On gitlab runners, default value sometimes end up calling 2 lds concurrently and # triggers an Out-Of-Memory error # -# Since slirp callbacks are used in QEMU Timers, slirp needs to be compiled together -# with QEMU and linked as a static library to avoid false positives in CFI checks. -# This can be accomplished by using -enable-slirp=git, which avoids the use of -# a system-wide version of the library +# Since slirp callbacks are used in QEMU Timers, we cannot use libslirp with +# CFI builds, and thus have to disable it here. # # Split in three sets of build/check/avocado to limit the execution time of each # job @@ -355,7 +352,7 @@ build-cfi-aarch64: AR: llvm-ar IMAGE: fedora CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug - --enable-safe-stack --enable-slirp=git + --enable-safe-stack --disable-slirp TARGETS: aarch64-softmmu MAKE_CHECK_ARGS: check-build # FIXME: This job is often failing, likely due to out-of-memory problems in @@ -395,7 +392,7 @@ build-cfi-ppc64-s390x: AR: llvm-ar IMAGE: fedora CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug - --enable-safe-stack --enable-slirp=git + --enable-safe-stack --disable-slirp TARGETS: ppc64-softmmu s390x-softmmu MAKE_CHECK_ARGS: check-build # FIXME: This job is often failing, likely due to out-of-memory problems in @@ -435,7 +432,7 @@ build-cfi-x86_64: AR: llvm-ar IMAGE: fedora CONFIGURE_ARGS: --cc=clang --cxx=clang++ --enable-cfi --enable-cfi-debug - --enable-safe-stack --enable-slirp=git + --enable-safe-stack --disable-slirp TARGETS: x86_64-softmmu MAKE_CHECK_ARGS: check-build timeout: 70m @@ -469,7 +466,7 @@ tsan-build: variables: IMAGE: ubuntu2004 CONFIGURE_ARGS: --enable-tsan --cc=clang-10 --cxx=clang++-10 - --enable-trace-backends=ust --enable-fdt=system --enable-slirp=system + --enable-trace-backends=ust --enable-fdt=system --disable-slirp TARGETS: x86_64-softmmu ppc64-softmmu riscv64-softmmu x86_64-linux-user MAKE_CHECK_ARGS: bench V=1 @@ -571,7 +568,6 @@ build-without-default-features: --disable-capstone --disable-pie --disable-qom-cast-debug - --disable-slirp --disable-strip TARGETS: avr-softmmu i386-softmmu mips64-softmmu s390x-softmmu sh4-softmmu sparc64-softmmu hexagon-linux-user i386-linux-user s390x-linux-user diff --git a/.gitmodules b/.gitmodules index aedd9a03d4..24cffa87d4 100644 --- a/.gitmodules +++ b/.gitmodules @@ -46,9 +46,6 @@ [submodule "roms/edk2"] path = roms/edk2 url = https://gitlab.com/qemu-project/edk2.git -[submodule "slirp"] - path = slirp - url = https://gitlab.com/qemu-project/libslirp.git [submodule "roms/opensbi"] path = roms/opensbi url = https://gitlab.com/qemu-project/opensbi.git diff --git a/MAINTAINERS b/MAINTAINERS index 269e07cf47..789172b2a8 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2985,7 +2985,6 @@ F: include/hw/registerfields.h SLIRP M: Samuel Thibault S: Maintained -F: slirp/ F: net/slirp.c F: include/net/slirp.h T: git https://people.debian.org/~sthibault/qemu.git slirp diff --git a/configure b/configure index cc4ecd6008..dc53e4df03 100755 --- a/configure +++ b/configure @@ -319,11 +319,6 @@ vfio_user_server="disabled" # are included in the automatically generated help message) # 1. Track which submodules are needed -if test "$default_feature" = no ; then - slirp="disabled" -else - slirp="auto" -fi fdt="auto" # 2. Automatically enable/disable other options @@ -827,14 +822,6 @@ for opt do ;; --disable-tsan) tsan="no" ;; - --disable-slirp) slirp="disabled" - ;; - --enable-slirp) slirp="enabled" - ;; - --enable-slirp=git) slirp="internal" - ;; - --enable-slirp=*) slirp="$optarg" - ;; --disable-tcg) tcg="disabled" plugins="no" ;; @@ -1253,6 +1240,7 @@ add_to nowarn_flags -Wno-string-plus-int add_to nowarn_flags -Wno-typedef-redefinition add_to nowarn_flags -Wno-tautological-type-limit-compare add_to nowarn_flags -Wno-psabi +add_to nowarn_flags -Wno-gnu-variable-sized-type-not-at-end gcc_flags="$warn_flags $nowarn_flags" @@ -1817,16 +1805,6 @@ EOF fi fi -########################################## -# check for slirp - -case "$slirp" in - auto | enabled | internal) - # Simpler to always update submodule, even if not needed. - git_submodules="${git_submodules} slirp" - ;; -esac - ########################################## # functions to probe cross compilers @@ -2734,7 +2712,6 @@ if test "$skip_meson" = no; then test "$fdt" != auto && meson_option_add "-Dfdt=$fdt" test -n "${LIB_FUZZING_ENGINE+xxx}" && meson_option_add "-Dfuzzing_engine=$LIB_FUZZING_ENGINE" test "$qemu_suffix" != qemu && meson_option_add "-Dqemu_suffix=$qemu_suffix" - test "$slirp" != auto && meson_option_add "-Dslirp=$slirp" test "$smbd" != '' && meson_option_add "-Dsmbd=$smbd" test "$tcg" != enabled && meson_option_add "-Dtcg=$tcg" test "$vfio_user_server" != auto && meson_option_add "-Dvfio_user_server=$vfio_user_server" diff --git a/hw/s390x/meson.build b/hw/s390x/meson.build index feefe0717e..f291016fee 100644 --- a/hw/s390x/meson.build +++ b/hw/s390x/meson.build @@ -23,6 +23,7 @@ s390x_ss.add(when: 'CONFIG_KVM', if_true: files( 's390-skeys-kvm.c', 's390-stattrib-kvm.c', 'pv.c', + 's390-pci-kvm.c', )) s390x_ss.add(when: 'CONFIG_TCG', if_true: files( 'tod-tcg.c', diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c index 4b2bdd94b3..977e7daa15 100644 --- a/hw/s390x/s390-pci-bus.c +++ b/hw/s390x/s390-pci-bus.c @@ -16,6 +16,7 @@ #include "qapi/visitor.h" #include "hw/s390x/s390-pci-bus.h" #include "hw/s390x/s390-pci-inst.h" +#include "hw/s390x/s390-pci-kvm.h" #include "hw/s390x/s390-pci-vfio.h" #include "hw/pci/pci_bus.h" #include "hw/qdev-properties.h" @@ -189,7 +190,10 @@ void s390_pci_sclp_deconfigure(SCCB *sccb) rc = SCLP_RC_NO_ACTION_REQUIRED; break; default: - if (pbdev->summary_ind) { + if (pbdev->interp && (pbdev->fh & FH_MASK_ENABLE)) { + /* Interpreted devices were using interrupt forwarding */ + s390_pci_kvm_aif_disable(pbdev); + } else if (pbdev->summary_ind) { pci_dereg_irqs(pbdev); } if (pbdev->iommu->enabled) { @@ -744,13 +748,14 @@ static void s390_pci_iommu_free(S390pciState *s, PCIBus *bus, int32_t devfn) object_unref(OBJECT(iommu)); } -S390PCIGroup *s390_group_create(int id) +S390PCIGroup *s390_group_create(int id, int host_id) { S390PCIGroup *group; S390pciState *s = s390_get_phb(); group = g_new0(S390PCIGroup, 1); group->id = id; + group->host_id = host_id; QTAILQ_INSERT_TAIL(&s->zpci_groups, group, link); return group; } @@ -768,12 +773,25 @@ S390PCIGroup *s390_group_find(int id) return NULL; } +S390PCIGroup *s390_group_find_host_sim(int host_id) +{ + S390PCIGroup *group; + S390pciState *s = s390_get_phb(); + + QTAILQ_FOREACH(group, &s->zpci_groups, link) { + if (group->id >= ZPCI_SIM_GRP_START && group->host_id == host_id) { + return group; + } + } + return NULL; +} + static void s390_pci_init_default_group(void) { S390PCIGroup *group; ClpRspQueryPciGrp *resgrp; - group = s390_group_create(ZPCI_DEFAULT_FN_GRP); + group = s390_group_create(ZPCI_DEFAULT_FN_GRP, ZPCI_DEFAULT_FN_GRP); resgrp = &group->zpci_group; resgrp->fr = 1; resgrp->dasm = 0; @@ -821,6 +839,7 @@ static void s390_pcihost_realize(DeviceState *dev, Error **errp) NULL, g_free); s->zpci_table = g_hash_table_new_full(g_int_hash, g_int_equal, NULL, NULL); s->bus_no = 0; + s->next_sim_grp = ZPCI_SIM_GRP_START; QTAILQ_INIT(&s->pending_sei); QTAILQ_INIT(&s->zpci_devs); QTAILQ_INIT(&s->zpci_dma_limit); @@ -880,6 +899,10 @@ static int s390_pci_msix_init(S390PCIBusDevice *pbdev) static void s390_pci_msix_free(S390PCIBusDevice *pbdev) { + if (pbdev->msix.entries == 0) { + return; + } + memory_region_del_subregion(&pbdev->iommu->mr, &pbdev->msix_notify_mr); object_unparent(OBJECT(&pbdev->msix_notify_mr)); } @@ -971,12 +994,51 @@ static void s390_pci_update_subordinate(PCIDevice *dev, uint32_t nr) } } +static int s390_pci_interp_plug(S390pciState *s, S390PCIBusDevice *pbdev) +{ + uint32_t idx, fh; + + if (!s390_pci_get_host_fh(pbdev, &fh)) { + return -EPERM; + } + + /* + * The host device is already in an enabled state, but we always present + * the initial device state to the guest as disabled (ZPCI_FS_DISABLED). + * Therefore, mask off the enable bit from the passthrough handle until + * the guest issues a CLP SET PCI FN later to enable the device. + */ + pbdev->fh = fh & ~FH_MASK_ENABLE; + + /* Next, see if the idx is already in-use */ + idx = pbdev->fh & FH_MASK_INDEX; + if (pbdev->idx != idx) { + if (s390_pci_find_dev_by_idx(s, idx)) { + return -EINVAL; + } + /* + * Update the idx entry with the passed through idx + * If the relinquished idx is lower than next_idx, use it + * to replace next_idx + */ + g_hash_table_remove(s->zpci_table, &pbdev->idx); + if (idx < s->next_idx) { + s->next_idx = idx; + } + pbdev->idx = idx; + g_hash_table_insert(s->zpci_table, &pbdev->idx, pbdev); + } + + return 0; +} + static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { S390pciState *s = S390_PCI_HOST_BRIDGE(hotplug_dev); PCIDevice *pdev = NULL; S390PCIBusDevice *pbdev = NULL; + int rc; if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) { PCIBridge *pb = PCI_BRIDGE(dev); @@ -1022,15 +1084,41 @@ static void s390_pcihost_plug(HotplugHandler *hotplug_dev, DeviceState *dev, set_pbdev_info(pbdev); if (object_dynamic_cast(OBJECT(dev), "vfio-pci")) { - pbdev->fh |= FH_SHM_VFIO; + /* + * By default, interpretation is always requested; if the available + * facilities indicate it is not available, fallback to the + * interception model. + */ + if (pbdev->interp) { + if (s390_pci_kvm_interp_allowed()) { + rc = s390_pci_interp_plug(s, pbdev); + if (rc) { + error_setg(errp, "Plug failed for zPCI device in " + "interpretation mode: %d", rc); + return; + } + } else { + DPRINTF("zPCI interpretation facilities missing.\n"); + pbdev->interp = false; + pbdev->forwarding_assist = false; + } + } pbdev->iommu->dma_limit = s390_pci_start_dma_count(s, pbdev); /* Fill in CLP information passed via the vfio region */ s390_pci_get_clp_info(pbdev); + if (!pbdev->interp) { + /* Do vfio passthrough but intercept for I/O */ + pbdev->fh |= FH_SHM_VFIO; + pbdev->forwarding_assist = false; + } } else { pbdev->fh |= FH_SHM_EMUL; + /* Always intercept emulated devices */ + pbdev->interp = false; + pbdev->forwarding_assist = false; } - if (s390_pci_msix_init(pbdev)) { + if (s390_pci_msix_init(pbdev) && !pbdev->interp) { error_setg(errp, "MSI-X support is mandatory " "in the S390 architecture"); return; @@ -1177,7 +1265,10 @@ static void s390_pcihost_reset(DeviceState *dev) /* Process all pending unplug requests */ QTAILQ_FOREACH_SAFE(pbdev, &s->zpci_devs, link, next) { if (pbdev->unplug_requested) { - if (pbdev->summary_ind) { + if (pbdev->interp && (pbdev->fh & FH_MASK_ENABLE)) { + /* Interpreted devices were using interrupt forwarding */ + s390_pci_kvm_aif_disable(pbdev); + } else if (pbdev->summary_ind) { pci_dereg_irqs(pbdev); } if (pbdev->iommu->enabled) { @@ -1315,7 +1406,10 @@ static void s390_pci_device_reset(DeviceState *dev) break; } - if (pbdev->summary_ind) { + if (pbdev->interp && (pbdev->fh & FH_MASK_ENABLE)) { + /* Interpreted devices were using interrupt forwarding */ + s390_pci_kvm_aif_disable(pbdev); + } else if (pbdev->summary_ind) { pci_dereg_irqs(pbdev); } if (pbdev->iommu->enabled) { @@ -1360,6 +1454,9 @@ static Property s390_pci_device_properties[] = { DEFINE_PROP_UINT16("uid", S390PCIBusDevice, uid, UID_UNDEFINED), DEFINE_PROP_S390_PCI_FID("fid", S390PCIBusDevice, fid), DEFINE_PROP_STRING("target", S390PCIBusDevice, target), + DEFINE_PROP_BOOL("interpret", S390PCIBusDevice, interp, true), + DEFINE_PROP_BOOL("forwarding-assist", S390PCIBusDevice, forwarding_assist, + true), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c index 6d400d4147..20a9bcc7af 100644 --- a/hw/s390x/s390-pci-inst.c +++ b/hw/s390x/s390-pci-inst.c @@ -18,6 +18,8 @@ #include "sysemu/hw_accel.h" #include "hw/s390x/s390-pci-inst.h" #include "hw/s390x/s390-pci-bus.h" +#include "hw/s390x/s390-pci-kvm.h" +#include "hw/s390x/s390-pci-vfio.h" #include "hw/s390x/tod.h" #ifndef DEBUG_S390PCI_INST @@ -246,6 +248,20 @@ int clp_service_call(S390CPU *cpu, uint8_t r2, uintptr_t ra) goto out; } + /* + * Take this opportunity to make sure we still have an accurate + * host fh. It's possible part of the handle changed while the + * device was disabled to the guest (e.g. vfio hot reset for + * ISM during plug) + */ + if (pbdev->interp) { + /* Take this opportunity to make sure we are sync'd with host */ + if (!s390_pci_get_host_fh(pbdev, &pbdev->fh) || + !(pbdev->fh & FH_MASK_ENABLE)) { + stw_p(&ressetpci->hdr.rsp, CLP_RC_SETPCIFN_FH); + goto out; + } + } pbdev->fh |= FH_MASK_ENABLE; pbdev->state = ZPCI_FS_ENABLED; stl_p(&ressetpci->fh, pbdev->fh); @@ -1050,6 +1066,32 @@ static void fmb_update(void *opaque) timer_mod(pbdev->fmb_timer, t + pbdev->pci_group->zpci_group.mui); } +static int mpcifc_reg_int_interp(S390PCIBusDevice *pbdev, ZpciFib *fib) +{ + int rc; + + rc = s390_pci_kvm_aif_enable(pbdev, fib, pbdev->forwarding_assist); + if (rc) { + DPRINTF("Failed to enable interrupt forwarding\n"); + return rc; + } + + return 0; +} + +static int mpcifc_dereg_int_interp(S390PCIBusDevice *pbdev, ZpciFib *fib) +{ + int rc; + + rc = s390_pci_kvm_aif_disable(pbdev); + if (rc) { + DPRINTF("Failed to disable interrupt forwarding\n"); + return rc; + } + + return 0; +} + int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar, uintptr_t ra) { @@ -1104,7 +1146,12 @@ int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar, switch (oc) { case ZPCI_MOD_FC_REG_INT: - if (pbdev->summary_ind) { + if (pbdev->interp) { + if (mpcifc_reg_int_interp(pbdev, &fib)) { + cc = ZPCI_PCI_LS_ERR; + s390_set_status_code(env, r1, ZPCI_MOD_ST_SEQUENCE); + } + } else if (pbdev->summary_ind) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_SEQUENCE); } else if (reg_irqs(env, pbdev, fib)) { @@ -1113,7 +1160,12 @@ int mpcifc_service_call(S390CPU *cpu, uint8_t r1, uint64_t fiba, uint8_t ar, } break; case ZPCI_MOD_FC_DEREG_INT: - if (!pbdev->summary_ind) { + if (pbdev->interp) { + if (mpcifc_dereg_int_interp(pbdev, &fib)) { + cc = ZPCI_PCI_LS_ERR; + s390_set_status_code(env, r1, ZPCI_MOD_ST_SEQUENCE); + } + } else if (!pbdev->summary_ind) { cc = ZPCI_PCI_LS_ERR; s390_set_status_code(env, r1, ZPCI_MOD_ST_SEQUENCE); } else { diff --git a/hw/s390x/s390-pci-kvm.c b/hw/s390x/s390-pci-kvm.c new file mode 100644 index 0000000000..5eb7fd12e2 --- /dev/null +++ b/hw/s390x/s390-pci-kvm.c @@ -0,0 +1,54 @@ +/* + * s390 zPCI KVM interfaces + * + * Copyright 2022 IBM Corp. + * Author(s): Matthew Rosato + * + * This work is licensed under the terms of the GNU GPL, version 2 or (at + * your option) any later version. See the COPYING file in the top-level + * directory. + */ + +#include "qemu/osdep.h" + +#include + +#include "kvm/kvm_s390x.h" +#include "hw/s390x/pv.h" +#include "hw/s390x/s390-pci-bus.h" +#include "hw/s390x/s390-pci-kvm.h" +#include "hw/s390x/s390-pci-inst.h" +#include "cpu_models.h" + +bool s390_pci_kvm_interp_allowed(void) +{ + return (kvm_s390_get_zpci_op() && !s390_is_pv() && + !object_property_get_bool(OBJECT(qdev_get_machine()), + "zpcii-disable", NULL)); +} + +int s390_pci_kvm_aif_enable(S390PCIBusDevice *pbdev, ZpciFib *fib, bool assist) +{ + struct kvm_s390_zpci_op args = { + .fh = pbdev->fh, + .op = KVM_S390_ZPCIOP_REG_AEN, + .u.reg_aen.ibv = fib->aibv, + .u.reg_aen.sb = fib->aisb, + .u.reg_aen.noi = FIB_DATA_NOI(fib->data), + .u.reg_aen.isc = FIB_DATA_ISC(fib->data), + .u.reg_aen.sbo = FIB_DATA_AISBO(fib->data), + .u.reg_aen.flags = (assist) ? 0 : KVM_S390_ZPCIOP_REGAEN_HOST + }; + + return kvm_vm_ioctl(kvm_state, KVM_S390_ZPCI_OP, &args); +} + +int s390_pci_kvm_aif_disable(S390PCIBusDevice *pbdev) +{ + struct kvm_s390_zpci_op args = { + .fh = pbdev->fh, + .op = KVM_S390_ZPCIOP_DEREG_AEN + }; + + return kvm_vm_ioctl(kvm_state, KVM_S390_ZPCI_OP, &args); +} diff --git a/hw/s390x/s390-pci-vfio.c b/hw/s390x/s390-pci-vfio.c index 6f80a47e29..2aefa508a0 100644 --- a/hw/s390x/s390-pci-vfio.c +++ b/hw/s390x/s390-pci-vfio.c @@ -124,18 +124,44 @@ static void s390_pci_read_base(S390PCIBusDevice *pbdev, pbdev->zpci_fn.pft = 0; } +static bool get_host_fh(S390PCIBusDevice *pbdev, struct vfio_device_info *info, + uint32_t *fh) +{ + struct vfio_info_cap_header *hdr; + struct vfio_device_info_cap_zpci_base *cap; + VFIOPCIDevice *vpci = container_of(pbdev->pdev, VFIOPCIDevice, pdev); + + hdr = vfio_get_device_info_cap(info, VFIO_DEVICE_INFO_CAP_ZPCI_BASE); + + /* Can only get the host fh with version 2 or greater */ + if (hdr == NULL || hdr->version < 2) { + trace_s390_pci_clp_cap(vpci->vbasedev.name, + VFIO_DEVICE_INFO_CAP_ZPCI_BASE); + return false; + } + cap = (void *) hdr; + + *fh = cap->fh; + return true; +} + static void s390_pci_read_group(S390PCIBusDevice *pbdev, struct vfio_device_info *info) { struct vfio_info_cap_header *hdr; struct vfio_device_info_cap_zpci_group *cap; + S390pciState *s = s390_get_phb(); ClpRspQueryPciGrp *resgrp; VFIOPCIDevice *vpci = container_of(pbdev->pdev, VFIOPCIDevice, pdev); + uint8_t start_gid = pbdev->zpci_fn.pfgid; hdr = vfio_get_device_info_cap(info, VFIO_DEVICE_INFO_CAP_ZPCI_GROUP); - /* If capability not provided, just use the default group */ - if (hdr == NULL) { + /* + * If capability not provided or the underlying hostdev is simulated, just + * use the default group. + */ + if (hdr == NULL || pbdev->zpci_fn.pfgid >= ZPCI_SIM_GRP_START) { trace_s390_pci_clp_cap(vpci->vbasedev.name, VFIO_DEVICE_INFO_CAP_ZPCI_GROUP); pbdev->zpci_fn.pfgid = ZPCI_DEFAULT_FN_GRP; @@ -144,11 +170,40 @@ static void s390_pci_read_group(S390PCIBusDevice *pbdev, } cap = (void *) hdr; + /* + * For an intercept device, let's use an existing simulated group if one + * one was already created for other intercept devices in this group. + * If not, create a new simulated group if any are still available. + * If all else fails, just fall back on the default group. + */ + if (!pbdev->interp) { + pbdev->pci_group = s390_group_find_host_sim(pbdev->zpci_fn.pfgid); + if (pbdev->pci_group) { + /* Use existing simulated group */ + pbdev->zpci_fn.pfgid = pbdev->pci_group->id; + return; + } else { + if (s->next_sim_grp == ZPCI_DEFAULT_FN_GRP) { + /* All out of simulated groups, use default */ + trace_s390_pci_clp_cap(vpci->vbasedev.name, + VFIO_DEVICE_INFO_CAP_ZPCI_GROUP); + pbdev->zpci_fn.pfgid = ZPCI_DEFAULT_FN_GRP; + pbdev->pci_group = s390_group_find(ZPCI_DEFAULT_FN_GRP); + return; + } else { + /* We can assign a new simulated group */ + pbdev->zpci_fn.pfgid = s->next_sim_grp; + s->next_sim_grp++; + /* Fall through to create the new sim group using CLP info */ + } + } + } + /* See if the PCI group is already defined, create if not */ pbdev->pci_group = s390_group_find(pbdev->zpci_fn.pfgid); if (!pbdev->pci_group) { - pbdev->pci_group = s390_group_create(pbdev->zpci_fn.pfgid); + pbdev->pci_group = s390_group_create(pbdev->zpci_fn.pfgid, start_gid); resgrp = &pbdev->pci_group->zpci_group; if (cap->flags & VFIO_DEVICE_INFO_ZPCI_FLAG_REFRESH) { @@ -158,7 +213,11 @@ static void s390_pci_read_group(S390PCIBusDevice *pbdev, resgrp->msia = cap->msi_addr; resgrp->mui = cap->mui; resgrp->i = cap->noi; - resgrp->maxstbl = cap->maxstbl; + if (pbdev->interp && hdr->version >= 2) { + resgrp->maxstbl = cap->imaxstbl; + } else { + resgrp->maxstbl = cap->maxstbl; + } resgrp->version = cap->version; resgrp->dtsm = ZPCI_DTSM; } @@ -217,25 +276,13 @@ static void s390_pci_read_pfip(S390PCIBusDevice *pbdev, memcpy(pbdev->zpci_fn.pfip, cap->pfip, CLP_PFIP_NR_SEGMENTS); } -/* - * This function will issue the VFIO_DEVICE_GET_INFO ioctl and look for - * capabilities that contain information about CLP features provided by the - * underlying host. - * On entry, defaults have already been placed into the guest CLP response - * buffers. On exit, defaults will have been overwritten for any CLP features - * found in the capability chain; defaults will remain for any CLP features not - * found in the chain. - */ -void s390_pci_get_clp_info(S390PCIBusDevice *pbdev) +static struct vfio_device_info *get_device_info(S390PCIBusDevice *pbdev, + uint32_t argsz) { - g_autofree struct vfio_device_info *info = NULL; + struct vfio_device_info *info = g_malloc0(argsz); VFIOPCIDevice *vfio_pci; - uint32_t argsz; int fd; - argsz = sizeof(*info); - info = g_malloc0(argsz); - vfio_pci = container_of(pbdev->pdev, VFIOPCIDevice, pdev); fd = vfio_pci->vbasedev.fd; @@ -250,7 +297,8 @@ retry: if (ioctl(fd, VFIO_DEVICE_GET_INFO, info)) { trace_s390_pci_clp_dev_info(vfio_pci->vbasedev.name); - return; + g_free(info); + return NULL; } if (info->argsz > argsz) { @@ -259,6 +307,47 @@ retry: goto retry; } + return info; +} + +/* + * Get the host function handle from the vfio CLP capabilities chain. Returns + * true if a fh value was placed into the provided buffer. Returns false + * if a fh could not be obtained (ioctl failed or capabilitiy version does + * not include the fh) + */ +bool s390_pci_get_host_fh(S390PCIBusDevice *pbdev, uint32_t *fh) +{ + g_autofree struct vfio_device_info *info = NULL; + + assert(fh); + + info = get_device_info(pbdev, sizeof(*info)); + if (!info) { + return false; + } + + return get_host_fh(pbdev, info, fh); +} + +/* + * This function will issue the VFIO_DEVICE_GET_INFO ioctl and look for + * capabilities that contain information about CLP features provided by the + * underlying host. + * On entry, defaults have already been placed into the guest CLP response + * buffers. On exit, defaults will have been overwritten for any CLP features + * found in the capability chain; defaults will remain for any CLP features not + * found in the chain. + */ +void s390_pci_get_clp_info(S390PCIBusDevice *pbdev) +{ + g_autofree struct vfio_device_info *info = NULL; + + info = get_device_info(pbdev, sizeof(*info)); + if (!info) { + return; + } + /* * Find the CLP features provided and fill in the guest CLP responses. * Always call s390_pci_read_base first as information from this could diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index 9a2467c889..03855c7231 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -645,6 +645,21 @@ static inline void machine_set_dea_key_wrap(Object *obj, bool value, ms->dea_key_wrap = value; } +static inline bool machine_get_zpcii_disable(Object *obj, Error **errp) +{ + S390CcwMachineState *ms = S390_CCW_MACHINE(obj); + + return ms->zpcii_disable; +} + +static inline void machine_set_zpcii_disable(Object *obj, bool value, + Error **errp) +{ + S390CcwMachineState *ms = S390_CCW_MACHINE(obj); + + ms->zpcii_disable = value; +} + static S390CcwMachineClass *current_mc; /* @@ -740,6 +755,13 @@ static inline void s390_machine_initfn(Object *obj) "Up to 8 chars in set of [A-Za-z0-9. ] (lower case chars converted" " to upper case) to pass to machine loader, boot manager," " and guest kernel"); + + object_property_add_bool(obj, "zpcii-disable", + machine_get_zpcii_disable, + machine_set_zpcii_disable); + object_property_set_description(obj, "zpcii-disable", + "disable zPCI interpretation facilties"); + object_property_set_bool(obj, "zpcii-disable", false, NULL); } static const TypeInfo ccw_machine_info = { @@ -803,8 +825,13 @@ DEFINE_CCW_MACHINE(7_2, "7.2", true); static void ccw_machine_7_1_instance_options(MachineState *machine) { + static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V7_1 }; + S390CcwMachineState *ms = S390_CCW_MACHINE(machine); + ccw_machine_7_2_instance_options(machine); s390_cpudef_featoff_greater(16, 1, S390_FEAT_PAIE); + s390_set_qemu_cpu_model(0x8561, 15, 1, qemu_cpu_feat); + ms->zpcii_disable = true; } static void ccw_machine_7_1_class_options(MachineClass *mc) diff --git a/include/hw/s390x/s390-pci-bus.h b/include/hw/s390x/s390-pci-bus.h index da3cde2bb4..0605fcea24 100644 --- a/include/hw/s390x/s390-pci-bus.h +++ b/include/hw/s390x/s390-pci-bus.h @@ -315,13 +315,16 @@ typedef struct ZpciFmb { QEMU_BUILD_BUG_MSG(offsetof(ZpciFmb, fmt0) != 48, "padding in ZpciFmb"); #define ZPCI_DEFAULT_FN_GRP 0xFF +#define ZPCI_SIM_GRP_START 0xF0 typedef struct S390PCIGroup { ClpRspQueryPciGrp zpci_group; int id; + int host_id; QTAILQ_ENTRY(S390PCIGroup) link; } S390PCIGroup; -S390PCIGroup *s390_group_create(int id); +S390PCIGroup *s390_group_create(int id, int host_id); S390PCIGroup *s390_group_find(int id); +S390PCIGroup *s390_group_find_host_sim(int host_id); struct S390PCIBusDevice { DeviceState qdev; @@ -350,6 +353,8 @@ struct S390PCIBusDevice { IndAddr *indicator; bool pci_unplug_request_processed; bool unplug_requested; + bool interp; + bool forwarding_assist; QTAILQ_ENTRY(S390PCIBusDevice) link; }; @@ -368,6 +373,7 @@ struct S390pciState { QTAILQ_HEAD(, S390PCIBusDevice) zpci_devs; QTAILQ_HEAD(, S390PCIDMACount) zpci_dma_limit; QTAILQ_HEAD(, S390PCIGroup) zpci_groups; + uint8_t next_sim_grp; }; S390pciState *s390_get_phb(void); diff --git a/include/hw/s390x/s390-pci-kvm.h b/include/hw/s390x/s390-pci-kvm.h new file mode 100644 index 0000000000..933814a402 --- /dev/null +++ b/include/hw/s390x/s390-pci-kvm.h @@ -0,0 +1,38 @@ +/* + * s390 PCI KVM interfaces + * + * Copyright 2022 IBM Corp. + * Author(s): Matthew Rosato + * + * This work is licensed under the terms of the GNU GPL, version 2 or (at + * your option) any later version. See the COPYING file in the top-level + * directory. + */ + +#ifndef HW_S390_PCI_KVM_H +#define HW_S390_PCI_KVM_H + +#include "hw/s390x/s390-pci-bus.h" +#include "hw/s390x/s390-pci-inst.h" + +#ifdef CONFIG_KVM +bool s390_pci_kvm_interp_allowed(void); +int s390_pci_kvm_aif_enable(S390PCIBusDevice *pbdev, ZpciFib *fib, bool assist); +int s390_pci_kvm_aif_disable(S390PCIBusDevice *pbdev); +#else +static inline bool s390_pci_kvm_interp_allowed(void) +{ + return false; +} +static inline int s390_pci_kvm_aif_enable(S390PCIBusDevice *pbdev, ZpciFib *fib, + bool assist) +{ + return -EINVAL; +} +static inline int s390_pci_kvm_aif_disable(S390PCIBusDevice *pbdev) +{ + return -EINVAL; +} +#endif + +#endif diff --git a/include/hw/s390x/s390-pci-vfio.h b/include/hw/s390x/s390-pci-vfio.h index ff708aef50..ae1b126ff7 100644 --- a/include/hw/s390x/s390-pci-vfio.h +++ b/include/hw/s390x/s390-pci-vfio.h @@ -20,6 +20,7 @@ bool s390_pci_update_dma_avail(int fd, unsigned int *avail); S390PCIDMACount *s390_pci_start_dma_count(S390pciState *s, S390PCIBusDevice *pbdev); void s390_pci_end_dma_count(S390pciState *s, S390PCIDMACount *cnt); +bool s390_pci_get_host_fh(S390PCIBusDevice *pbdev, uint32_t *fh); void s390_pci_get_clp_info(S390PCIBusDevice *pbdev); #else static inline bool s390_pci_update_dma_avail(int fd, unsigned int *avail) @@ -33,6 +34,10 @@ static inline S390PCIDMACount *s390_pci_start_dma_count(S390pciState *s, } static inline void s390_pci_end_dma_count(S390pciState *s, S390PCIDMACount *cnt) { } +static inline bool s390_pci_get_host_fh(S390PCIBusDevice *pbdev, uint32_t *fh) +{ + return false; +} static inline void s390_pci_get_clp_info(S390PCIBusDevice *pbdev) { } #endif diff --git a/include/hw/s390x/s390-virtio-ccw.h b/include/hw/s390x/s390-virtio-ccw.h index 3331990e02..8a0090a071 100644 --- a/include/hw/s390x/s390-virtio-ccw.h +++ b/include/hw/s390x/s390-virtio-ccw.h @@ -27,6 +27,7 @@ struct S390CcwMachineState { bool aes_key_wrap; bool dea_key_wrap; bool pv; + bool zpcii_disable; uint8_t loadparm[8]; }; diff --git a/include/standard-headers/asm-x86/bootparam.h b/include/standard-headers/asm-x86/bootparam.h index b2aaad10e5..0b06d2bff1 100644 --- a/include/standard-headers/asm-x86/bootparam.h +++ b/include/standard-headers/asm-x86/bootparam.h @@ -10,12 +10,13 @@ #define SETUP_EFI 4 #define SETUP_APPLE_PROPERTIES 5 #define SETUP_JAILHOUSE 6 +#define SETUP_CC_BLOB 7 +#define SETUP_IMA 8 #define SETUP_RNG_SEED 9 +#define SETUP_ENUM_MAX SETUP_RNG_SEED #define SETUP_INDIRECT (1<<31) - -/* SETUP_INDIRECT | max(SETUP_*) */ -#define SETUP_TYPE_MAX (SETUP_INDIRECT | SETUP_JAILHOUSE) +#define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT) /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF diff --git a/include/standard-headers/drm/drm_fourcc.h b/include/standard-headers/drm/drm_fourcc.h index 4888f85f69..48b620cbef 100644 --- a/include/standard-headers/drm/drm_fourcc.h +++ b/include/standard-headers/drm/drm_fourcc.h @@ -558,7 +558,7 @@ extern "C" { * * The main surface is Y-tiled and is at plane index 0 whereas CCS is linear * and at index 1. The clear color is stored at index 2, and the pitch should - * be ignored. The clear color structure is 256 bits. The first 128 bits + * be 64 bytes aligned. The clear color structure is 256 bits. The first 128 bits * represents Raw Clear Color Red, Green, Blue and Alpha color each represented * by 32 bits. The raw clear color is consumed by the 3d engine and generates * the converted clear color of size 64 bits. The first 32 bits store the Lower @@ -571,6 +571,53 @@ extern "C" { */ #define I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC fourcc_mod_code(INTEL, 8) +/* + * Intel Tile 4 layout + * + * This is a tiled layout using 4KB tiles in a row-major layout. It has the same + * shape as Tile Y at two granularities: 4KB (128B x 32) and 64B (16B x 4). It + * only differs from Tile Y at the 256B granularity in between. At this + * granularity, Tile Y has a shape of 16B x 32 rows, but this tiling has a shape + * of 64B x 8 rows. + */ +#define I915_FORMAT_MOD_4_TILED fourcc_mod_code(INTEL, 9) + +/* + * Intel color control surfaces (CCS) for DG2 render compression. + * + * The main surface is Tile 4 and at plane index 0. The CCS data is stored + * outside of the GEM object in a reserved memory area dedicated for the + * storage of the CCS data for all RC/RC_CC/MC compressible GEM objects. The + * main surface pitch is required to be a multiple of four Tile 4 widths. + */ +#define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS fourcc_mod_code(INTEL, 10) + +/* + * Intel color control surfaces (CCS) for DG2 media compression. + * + * The main surface is Tile 4 and at plane index 0. For semi-planar formats + * like NV12, the Y and UV planes are Tile 4 and are located at plane indices + * 0 and 1, respectively. The CCS for all planes are stored outside of the + * GEM object in a reserved memory area dedicated for the storage of the + * CCS data for all RC/RC_CC/MC compressible GEM objects. The main surface + * pitch is required to be a multiple of four Tile 4 widths. + */ +#define I915_FORMAT_MOD_4_TILED_DG2_MC_CCS fourcc_mod_code(INTEL, 11) + +/* + * Intel Color Control Surface with Clear Color (CCS) for DG2 render compression. + * + * The main surface is Tile 4 and at plane index 0. The CCS data is stored + * outside of the GEM object in a reserved memory area dedicated for the + * storage of the CCS data for all RC/RC_CC/MC compressible GEM objects. The + * main surface pitch is required to be a multiple of four Tile 4 widths. The + * clear color is stored at plane index 1 and the pitch should be 64 bytes + * aligned. The format of the 256 bits of clear color data matches the one used + * for the I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC modifier, see its description + * for details. + */ +#define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC fourcc_mod_code(INTEL, 12) + /* * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks * @@ -608,6 +655,28 @@ extern "C" { */ #define DRM_FORMAT_MOD_QCOM_COMPRESSED fourcc_mod_code(QCOM, 1) +/* + * Qualcomm Tiled Format + * + * Similar to DRM_FORMAT_MOD_QCOM_COMPRESSED but not compressed. + * Implementation may be platform and base-format specific. + * + * Each macrotile consists of m x n (mostly 4 x 4) tiles. + * Pixel data pitch/stride is aligned with macrotile width. + * Pixel data height is aligned with macrotile height. + * Entire pixel data buffer is aligned with 4k(bytes). + */ +#define DRM_FORMAT_MOD_QCOM_TILED3 fourcc_mod_code(QCOM, 3) + +/* + * Qualcomm Alternate Tiled Format + * + * Alternate tiled format typically only used within GMEM. + * Implementation may be platform and base-format specific. + */ +#define DRM_FORMAT_MOD_QCOM_TILED2 fourcc_mod_code(QCOM, 2) + + /* Vivante framebuffer modifiers */ /* @@ -1293,6 +1362,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier) #define AMD_FMT_MOD_TILE_VER_GFX9 1 #define AMD_FMT_MOD_TILE_VER_GFX10 2 #define AMD_FMT_MOD_TILE_VER_GFX10_RBPLUS 3 +#define AMD_FMT_MOD_TILE_VER_GFX11 4 /* * 64K_S is the same for GFX9/GFX10/GFX10_RBPLUS and hence has GFX9 as canonical @@ -1308,6 +1378,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(uint64_t modifier) #define AMD_FMT_MOD_TILE_GFX9_64K_S_X 25 #define AMD_FMT_MOD_TILE_GFX9_64K_D_X 26 #define AMD_FMT_MOD_TILE_GFX9_64K_R_X 27 +#define AMD_FMT_MOD_TILE_GFX11_256K_R_X 31 #define AMD_FMT_MOD_DCC_BLOCK_64B 0 #define AMD_FMT_MOD_DCC_BLOCK_128B 1 diff --git a/include/standard-headers/linux/ethtool.h b/include/standard-headers/linux/ethtool.h index 38d5a4cd6e..4537da20cc 100644 --- a/include/standard-headers/linux/ethtool.h +++ b/include/standard-headers/linux/ethtool.h @@ -257,7 +257,7 @@ struct ethtool_tunable { uint32_t id; uint32_t type_id; uint32_t len; - void *data[0]; + void *data[]; }; #define DOWNSHIFT_DEV_DEFAULT_COUNT 0xff @@ -322,7 +322,7 @@ struct ethtool_regs { uint32_t cmd; uint32_t version; uint32_t len; - uint8_t data[0]; + uint8_t data[]; }; /** @@ -348,7 +348,7 @@ struct ethtool_eeprom { uint32_t magic; uint32_t offset; uint32_t len; - uint8_t data[0]; + uint8_t data[]; }; /** @@ -752,7 +752,7 @@ struct ethtool_gstrings { uint32_t cmd; uint32_t string_set; uint32_t len; - uint8_t data[0]; + uint8_t data[]; }; /** @@ -777,7 +777,7 @@ struct ethtool_sset_info { uint32_t cmd; uint32_t reserved; uint64_t sset_mask; - uint32_t data[0]; + uint32_t data[]; }; /** @@ -817,7 +817,7 @@ struct ethtool_test { uint32_t flags; uint32_t reserved; uint32_t len; - uint64_t data[0]; + uint64_t data[]; }; /** @@ -834,7 +834,7 @@ struct ethtool_test { struct ethtool_stats { uint32_t cmd; uint32_t n_stats; - uint64_t data[0]; + uint64_t data[]; }; /** @@ -851,7 +851,7 @@ struct ethtool_stats { struct ethtool_perm_addr { uint32_t cmd; uint32_t size; - uint8_t data[0]; + uint8_t data[]; }; /* boolean flags controlling per-interface behavior characteristics. @@ -1160,7 +1160,7 @@ struct ethtool_rxnfc { struct ethtool_rxfh_indir { uint32_t cmd; uint32_t size; - uint32_t ring_index[0]; + uint32_t ring_index[]; }; /** @@ -1201,7 +1201,7 @@ struct ethtool_rxfh { uint8_t hfunc; uint8_t rsvd8[3]; uint32_t rsvd32; - uint32_t rss_config[0]; + uint32_t rss_config[]; }; #define ETH_RXFH_CONTEXT_ALLOC 0xffffffff #define ETH_RXFH_INDIR_NO_CHANGE 0xffffffff @@ -1286,7 +1286,7 @@ struct ethtool_dump { uint32_t version; uint32_t flag; uint32_t len; - uint8_t data[0]; + uint8_t data[]; }; #define ETH_FW_DUMP_DISABLE 0 @@ -1318,7 +1318,7 @@ struct ethtool_get_features_block { struct ethtool_gfeatures { uint32_t cmd; uint32_t size; - struct ethtool_get_features_block features[0]; + struct ethtool_get_features_block features[]; }; /** @@ -1340,7 +1340,7 @@ struct ethtool_set_features_block { struct ethtool_sfeatures { uint32_t cmd; uint32_t size; - struct ethtool_set_features_block features[0]; + struct ethtool_set_features_block features[]; }; /** @@ -1691,6 +1691,7 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT = 89, ETHTOOL_LINK_MODE_100baseFX_Half_BIT = 90, ETHTOOL_LINK_MODE_100baseFX_Full_BIT = 91, + ETHTOOL_LINK_MODE_10baseT1L_Full_BIT = 92, /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS }; @@ -2086,7 +2087,7 @@ struct ethtool_link_settings { uint8_t master_slave_state; uint8_t reserved1[1]; uint32_t reserved[7]; - uint32_t link_mode_masks[0]; + uint32_t link_mode_masks[]; /* layout of link_mode_masks fields: * uint32_t map_supported[link_mode_masks_nwords]; * uint32_t map_advertising[link_mode_masks_nwords]; diff --git a/include/standard-headers/linux/input.h b/include/standard-headers/linux/input.h index 7822c24178..942ea6aaa9 100644 --- a/include/standard-headers/linux/input.h +++ b/include/standard-headers/linux/input.h @@ -75,10 +75,13 @@ struct input_id { * Note that input core does not clamp reported values to the * [minimum, maximum] limits, such task is left to userspace. * - * The default resolution for main axes (ABS_X, ABS_Y, ABS_Z) - * is reported in units per millimeter (units/mm), resolution - * for rotational axes (ABS_RX, ABS_RY, ABS_RZ) is reported - * in units per radian. + * The default resolution for main axes (ABS_X, ABS_Y, ABS_Z, + * ABS_MT_POSITION_X, ABS_MT_POSITION_Y) is reported in units + * per millimeter (units/mm), resolution for rotational axes + * (ABS_RX, ABS_RY, ABS_RZ) is reported in units per radian. + * The resolution for the size axes (ABS_MT_TOUCH_MAJOR, + * ABS_MT_TOUCH_MINOR, ABS_MT_WIDTH_MAJOR, ABS_MT_WIDTH_MINOR) + * is reported in units per millimeter (units/mm). * When INPUT_PROP_ACCELEROMETER is set the resolution changes. * The main axes (ABS_X, ABS_Y, ABS_Z) are then reported in * units per g (units/g) and in units per degree per second @@ -268,6 +271,7 @@ struct input_mask { #define BUS_RMI 0x1D #define BUS_CEC 0x1E #define BUS_INTEL_ISHTP 0x1F +#define BUS_AMD_SFH 0x20 /* * MT_TOOL types diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h index bee1a9ed6e..57b8e2ffb1 100644 --- a/include/standard-headers/linux/pci_regs.h +++ b/include/standard-headers/linux/pci_regs.h @@ -616,6 +616,7 @@ #define PCI_EXP_SLTCTL_PWR_OFF 0x0400 /* Power Off */ #define PCI_EXP_SLTCTL_EIC 0x0800 /* Electromechanical Interlock Control */ #define PCI_EXP_SLTCTL_DLLSCE 0x1000 /* Data Link Layer State Changed Enable */ +#define PCI_EXP_SLTCTL_ASPL_DISABLE 0x2000 /* Auto Slot Power Limit Disable */ #define PCI_EXP_SLTCTL_IBPD_DISABLE 0x4000 /* In-band PD disable */ #define PCI_EXP_SLTSTA 0x1a /* Slot Status */ #define PCI_EXP_SLTSTA_ABP 0x0001 /* Attention Button Pressed */ @@ -736,7 +737,8 @@ #define PCI_EXT_CAP_ID_DVSEC 0x23 /* Designated Vendor-Specific */ #define PCI_EXT_CAP_ID_DLF 0x25 /* Data Link Feature */ #define PCI_EXT_CAP_ID_PL_16GT 0x26 /* Physical Layer 16.0 GT/s */ -#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PL_16GT +#define PCI_EXT_CAP_ID_DOE 0x2E /* Data Object Exchange */ +#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_DOE #define PCI_EXT_CAP_DSN_SIZEOF 12 #define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40 @@ -1102,4 +1104,30 @@ #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_MASK 0x000000F0 #define PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_SHIFT 4 +/* Data Object Exchange */ +#define PCI_DOE_CAP 0x04 /* DOE Capabilities Register */ +#define PCI_DOE_CAP_INT_SUP 0x00000001 /* Interrupt Support */ +#define PCI_DOE_CAP_INT_MSG_NUM 0x00000ffe /* Interrupt Message Number */ +#define PCI_DOE_CTRL 0x08 /* DOE Control Register */ +#define PCI_DOE_CTRL_ABORT 0x00000001 /* DOE Abort */ +#define PCI_DOE_CTRL_INT_EN 0x00000002 /* DOE Interrupt Enable */ +#define PCI_DOE_CTRL_GO 0x80000000 /* DOE Go */ +#define PCI_DOE_STATUS 0x0c /* DOE Status Register */ +#define PCI_DOE_STATUS_BUSY 0x00000001 /* DOE Busy */ +#define PCI_DOE_STATUS_INT_STATUS 0x00000002 /* DOE Interrupt Status */ +#define PCI_DOE_STATUS_ERROR 0x00000004 /* DOE Error */ +#define PCI_DOE_STATUS_DATA_OBJECT_READY 0x80000000 /* Data Object Ready */ +#define PCI_DOE_WRITE 0x10 /* DOE Write Data Mailbox Register */ +#define PCI_DOE_READ 0x14 /* DOE Read Data Mailbox Register */ + +/* DOE Data Object - note not actually registers */ +#define PCI_DOE_DATA_OBJECT_HEADER_1_VID 0x0000ffff +#define PCI_DOE_DATA_OBJECT_HEADER_1_TYPE 0x00ff0000 +#define PCI_DOE_DATA_OBJECT_HEADER_2_LENGTH 0x0003ffff + +#define PCI_DOE_DATA_OBJECT_DISC_REQ_3_INDEX 0x000000ff +#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_VID 0x0000ffff +#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_PROTOCOL 0x00ff0000 +#define PCI_DOE_DATA_OBJECT_DISC_RSP_3_NEXT_INDEX 0xff000000 + #endif /* LINUX_PCI_REGS_H */ diff --git a/include/standard-headers/linux/vhost_types.h b/include/standard-headers/linux/vhost_types.h index 0bd2684a2a..c41a73fe36 100644 --- a/include/standard-headers/linux/vhost_types.h +++ b/include/standard-headers/linux/vhost_types.h @@ -87,7 +87,7 @@ struct vhost_msg { struct vhost_msg_v2 { uint32_t type; - uint32_t reserved; + uint32_t asid; union { struct vhost_iotlb_msg iotlb; uint8_t padding[64]; @@ -107,7 +107,7 @@ struct vhost_memory_region { struct vhost_memory { uint32_t nregions; uint32_t padding; - struct vhost_memory_region regions[0]; + struct vhost_memory_region regions[]; }; /* VHOST_SCSI specific definitions */ @@ -135,7 +135,7 @@ struct vhost_scsi_target { struct vhost_vdpa_config { uint32_t off; uint32_t len; - uint8_t buf[0]; + uint8_t buf[]; }; /* vhost vdpa IOVA range @@ -153,4 +153,15 @@ struct vhost_vdpa_iova_range { /* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */ #define VHOST_NET_F_VIRTIO_NET_HDR 27 +/* Use message type V2 */ +#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 +/* IOTLB can accept batching hints */ +#define VHOST_BACKEND_F_IOTLB_BATCH 0x2 +/* IOTLB can accept address space identifier through V2 type of IOTLB + * message + */ +#define VHOST_BACKEND_F_IOTLB_ASID 0x3 +/* Device can be suspended */ +#define VHOST_BACKEND_F_SUSPEND 0x4 + #endif diff --git a/include/standard-headers/linux/virtio_9p.h b/include/standard-headers/linux/virtio_9p.h index f5604fc5fb..da61dee98c 100644 --- a/include/standard-headers/linux/virtio_9p.h +++ b/include/standard-headers/linux/virtio_9p.h @@ -38,7 +38,7 @@ struct virtio_9p_config { /* length of the tag name */ __virtio16 tag_len; /* non-NULL terminated tag name */ - uint8_t tag[0]; + uint8_t tag[]; } QEMU_PACKED; #endif /* _LINUX_VIRTIO_9P_H */ diff --git a/include/standard-headers/linux/virtio_config.h b/include/standard-headers/linux/virtio_config.h index 7acd8d4abc..965ee6ae23 100644 --- a/include/standard-headers/linux/virtio_config.h +++ b/include/standard-headers/linux/virtio_config.h @@ -52,7 +52,7 @@ * rest are per-device feature bits. */ #define VIRTIO_TRANSPORT_F_START 28 -#define VIRTIO_TRANSPORT_F_END 38 +#define VIRTIO_TRANSPORT_F_END 41 #ifndef VIRTIO_CONFIG_NO_LEGACY /* Do we get callbacks when the ring is completely used, even if we've @@ -96,4 +96,9 @@ * Does the device support Single Root I/O Virtualization? */ #define VIRTIO_F_SR_IOV 37 + +/* + * This feature indicates that the driver can reset a queue individually. + */ +#define VIRTIO_F_RING_RESET 40 #endif /* _LINUX_VIRTIO_CONFIG_H */ diff --git a/include/standard-headers/linux/virtio_ids.h b/include/standard-headers/linux/virtio_ids.h index 80d76b75bc..7aa2eb7662 100644 --- a/include/standard-headers/linux/virtio_ids.h +++ b/include/standard-headers/linux/virtio_ids.h @@ -73,12 +73,12 @@ * Virtio Transitional IDs */ -#define VIRTIO_TRANS_ID_NET 1000 /* transitional virtio net */ -#define VIRTIO_TRANS_ID_BLOCK 1001 /* transitional virtio block */ -#define VIRTIO_TRANS_ID_BALLOON 1002 /* transitional virtio balloon */ -#define VIRTIO_TRANS_ID_CONSOLE 1003 /* transitional virtio console */ -#define VIRTIO_TRANS_ID_SCSI 1004 /* transitional virtio SCSI */ -#define VIRTIO_TRANS_ID_RNG 1005 /* transitional virtio rng */ -#define VIRTIO_TRANS_ID_9P 1009 /* transitional virtio 9p console */ +#define VIRTIO_TRANS_ID_NET 0x1000 /* transitional virtio net */ +#define VIRTIO_TRANS_ID_BLOCK 0x1001 /* transitional virtio block */ +#define VIRTIO_TRANS_ID_BALLOON 0x1002 /* transitional virtio balloon */ +#define VIRTIO_TRANS_ID_CONSOLE 0x1003 /* transitional virtio console */ +#define VIRTIO_TRANS_ID_SCSI 0x1004 /* transitional virtio SCSI */ +#define VIRTIO_TRANS_ID_RNG 0x1005 /* transitional virtio rng */ +#define VIRTIO_TRANS_ID_9P 0x1009 /* transitional virtio 9p console */ #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/include/standard-headers/linux/virtio_net.h b/include/standard-headers/linux/virtio_net.h index e0a070518f..42c68caf71 100644 --- a/include/standard-headers/linux/virtio_net.h +++ b/include/standard-headers/linux/virtio_net.h @@ -56,7 +56,7 @@ #define VIRTIO_NET_F_MQ 22 /* Device supports Receive Flow * Steering */ #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ - +#define VIRTIO_NET_F_NOTF_COAL 53 /* Device supports notifications coalescing */ #define VIRTIO_NET_F_HASH_REPORT 57 /* Supports hash report */ #define VIRTIO_NET_F_RSS 60 /* Supports RSS RX steering */ #define VIRTIO_NET_F_RSC_EXT 61 /* extended coalescing info */ @@ -355,4 +355,36 @@ struct virtio_net_hash_config { #define VIRTIO_NET_CTRL_GUEST_OFFLOADS 5 #define VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET 0 +/* + * Control notifications coalescing. + * + * Request the device to change the notifications coalescing parameters. + * + * Available with the VIRTIO_NET_F_NOTF_COAL feature bit. + */ +#define VIRTIO_NET_CTRL_NOTF_COAL 6 +/* + * Set the tx-usecs/tx-max-packets parameters. + */ +struct virtio_net_ctrl_coal_tx { + /* Maximum number of packets to send before a TX notification */ + uint32_t tx_max_packets; + /* Maximum number of usecs to delay a TX notification */ + uint32_t tx_usecs; +}; + +#define VIRTIO_NET_CTRL_NOTF_COAL_TX_SET 0 + +/* + * Set the rx-usecs/rx-max-packets parameters. + */ +struct virtio_net_ctrl_coal_rx { + /* Maximum number of packets to receive before a RX notification */ + uint32_t rx_max_packets; + /* Maximum number of usecs to delay a RX notification */ + uint32_t rx_usecs; +}; + +#define VIRTIO_NET_CTRL_NOTF_COAL_RX_SET 1 + #endif /* _LINUX_VIRTIO_NET_H */ diff --git a/include/standard-headers/linux/virtio_pci.h b/include/standard-headers/linux/virtio_pci.h index db7a8e2fcb..be912cfc95 100644 --- a/include/standard-headers/linux/virtio_pci.h +++ b/include/standard-headers/linux/virtio_pci.h @@ -202,6 +202,8 @@ struct virtio_pci_cfg_cap { #define VIRTIO_PCI_COMMON_Q_AVAILHI 44 #define VIRTIO_PCI_COMMON_Q_USEDLO 48 #define VIRTIO_PCI_COMMON_Q_USEDHI 52 +#define VIRTIO_PCI_COMMON_Q_NDATA 56 +#define VIRTIO_PCI_COMMON_Q_RESET 58 #endif /* VIRTIO_PCI_NO_MODERN */ diff --git a/include/standard-headers/linux/virtio_ring.h b/include/standard-headers/linux/virtio_ring.h index 0fa0e1067f..22f6eb8ca7 100644 --- a/include/standard-headers/linux/virtio_ring.h +++ b/include/standard-headers/linux/virtio_ring.h @@ -91,15 +91,21 @@ #define VRING_USED_ALIGN_SIZE 4 #define VRING_DESC_ALIGN_SIZE 16 -/* Virtio ring descriptors: 16 bytes. These can chain together via "next". */ +/** + * struct vring_desc - Virtio ring descriptors, + * 16 bytes long. These can chain together via @next. + * + * @addr: buffer address (guest-physical) + * @len: buffer length + * @flags: descriptor flags + * @next: index of the next descriptor in the chain, + * if the VRING_DESC_F_NEXT flag is set. We chain unused + * descriptors via this, too. + */ struct vring_desc { - /* Address (guest-physical). */ __virtio64 addr; - /* Length. */ __virtio32 len; - /* The flags as indicated above. */ __virtio16 flags; - /* We chain unused descriptors via this, too */ __virtio16 next; }; diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h index 5c28a9737a..4bf2d7246e 100644 --- a/linux-headers/asm-arm64/kvm.h +++ b/linux-headers/asm-arm64/kvm.h @@ -75,9 +75,11 @@ struct kvm_regs { /* KVM_ARM_SET_DEVICE_ADDR ioctl id encoding */ #define KVM_ARM_DEVICE_TYPE_SHIFT 0 -#define KVM_ARM_DEVICE_TYPE_MASK (0xffff << KVM_ARM_DEVICE_TYPE_SHIFT) +#define KVM_ARM_DEVICE_TYPE_MASK GENMASK(KVM_ARM_DEVICE_TYPE_SHIFT + 15, \ + KVM_ARM_DEVICE_TYPE_SHIFT) #define KVM_ARM_DEVICE_ID_SHIFT 16 -#define KVM_ARM_DEVICE_ID_MASK (0xffff << KVM_ARM_DEVICE_ID_SHIFT) +#define KVM_ARM_DEVICE_ID_MASK GENMASK(KVM_ARM_DEVICE_ID_SHIFT + 15, \ + KVM_ARM_DEVICE_ID_SHIFT) /* Supported device IDs */ #define KVM_ARM_DEVICE_VGIC_V2 0 @@ -139,8 +141,10 @@ struct kvm_guest_debug_arch { __u64 dbg_wvr[KVM_ARM_MAX_DBG_REGS]; }; +#define KVM_DEBUG_ARCH_HSR_HIGH_VALID (1 << 0) struct kvm_debug_exit_arch { __u32 hsr; + __u32 hsr_high; /* ESR_EL2[61:32] */ __u64 far; /* used for watchpoints */ }; @@ -332,6 +336,31 @@ struct kvm_arm_copy_mte_tags { #define KVM_ARM64_SVE_VLS_WORDS \ ((KVM_ARM64_SVE_VQ_MAX - KVM_ARM64_SVE_VQ_MIN) / 64 + 1) +/* Bitmap feature firmware registers */ +#define KVM_REG_ARM_FW_FEAT_BMAP (0x0016 << KVM_REG_ARM_COPROC_SHIFT) +#define KVM_REG_ARM_FW_FEAT_BMAP_REG(r) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ + KVM_REG_ARM_FW_FEAT_BMAP | \ + ((r) & 0xffff)) + +#define KVM_REG_ARM_STD_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(0) + +enum { + KVM_REG_ARM_STD_BIT_TRNG_V1_0 = 0, +}; + +#define KVM_REG_ARM_STD_HYP_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(1) + +enum { + KVM_REG_ARM_STD_HYP_BIT_PV_TIME = 0, +}; + +#define KVM_REG_ARM_VENDOR_HYP_BMAP KVM_REG_ARM_FW_FEAT_BMAP_REG(2) + +enum { + KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT = 0, + KVM_REG_ARM_VENDOR_HYP_BIT_PTP = 1, +}; + /* Device Control API: ARM VGIC */ #define KVM_DEV_ARM_VGIC_GRP_ADDR 0 #define KVM_DEV_ARM_VGIC_GRP_DIST_REGS 1 diff --git a/linux-headers/asm-generic/unistd.h b/linux-headers/asm-generic/unistd.h index 1c48b0ae3b..45fa180cc5 100644 --- a/linux-headers/asm-generic/unistd.h +++ b/linux-headers/asm-generic/unistd.h @@ -383,7 +383,7 @@ __SYSCALL(__NR_syslog, sys_syslog) /* kernel/ptrace.c */ #define __NR_ptrace 117 -__SYSCALL(__NR_ptrace, sys_ptrace) +__SC_COMP(__NR_ptrace, sys_ptrace, compat_sys_ptrace) /* kernel/sched/core.c */ #define __NR_sched_setparam 118 @@ -779,7 +779,7 @@ __SYSCALL(__NR_rseq, sys_rseq) #define __NR_kexec_file_load 294 __SYSCALL(__NR_kexec_file_load, sys_kexec_file_load) /* 295 through 402 are unassigned to sync up with generic numbers, don't use */ -#if __BITS_PER_LONG == 32 +#if defined(__SYSCALL_COMPAT) || __BITS_PER_LONG == 32 #define __NR_clock_gettime64 403 __SYSCALL(__NR_clock_gettime64, sys_clock_gettime) #define __NR_clock_settime64 404 diff --git a/linux-headers/asm-riscv/kvm.h b/linux-headers/asm-riscv/kvm.h index f808ad1ce5..7351417afd 100644 --- a/linux-headers/asm-riscv/kvm.h +++ b/linux-headers/asm-riscv/kvm.h @@ -82,6 +82,25 @@ struct kvm_riscv_timer { __u64 state; }; +/* + * ISA extension IDs specific to KVM. This is not the same as the host ISA + * extension IDs as that is internal to the host and should not be exposed + * to the guest. This should always be contiguous to keep the mapping simple + * in KVM implementation. + */ +enum KVM_RISCV_ISA_EXT_ID { + KVM_RISCV_ISA_EXT_A = 0, + KVM_RISCV_ISA_EXT_C, + KVM_RISCV_ISA_EXT_D, + KVM_RISCV_ISA_EXT_F, + KVM_RISCV_ISA_EXT_H, + KVM_RISCV_ISA_EXT_I, + KVM_RISCV_ISA_EXT_M, + KVM_RISCV_ISA_EXT_SVPBMT, + KVM_RISCV_ISA_EXT_SSTC, + KVM_RISCV_ISA_EXT_MAX, +}; + /* Possible states for kvm_riscv_timer */ #define KVM_RISCV_TIMER_STATE_OFF 0 #define KVM_RISCV_TIMER_STATE_ON 1 @@ -123,6 +142,9 @@ struct kvm_riscv_timer { #define KVM_REG_RISCV_FP_D_REG(name) \ (offsetof(struct __riscv_d_ext_state, name) / sizeof(__u64)) +/* ISA Extension registers are mapped as type 7 */ +#define KVM_REG_RISCV_ISA_EXT (0x07 << KVM_REG_RISCV_TYPE_SHIFT) + #endif #endif /* __LINUX_KVM_RISCV_H */ diff --git a/linux-headers/asm-riscv/unistd.h b/linux-headers/asm-riscv/unistd.h index 8062996c2d..73d7cdd2ec 100644 --- a/linux-headers/asm-riscv/unistd.h +++ b/linux-headers/asm-riscv/unistd.h @@ -15,12 +15,13 @@ * along with this program. If not, see . */ -#ifdef __LP64__ +#if defined(__LP64__) && !defined(__SYSCALL_COMPAT) #define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SET_GET_RLIMIT #endif /* __LP64__ */ #define __ARCH_WANT_SYS_CLONE3 +#define __ARCH_WANT_MEMFD_SECRET #include diff --git a/linux-headers/asm-s390/kvm.h b/linux-headers/asm-s390/kvm.h index f053b8304a..e2afd95420 100644 --- a/linux-headers/asm-s390/kvm.h +++ b/linux-headers/asm-s390/kvm.h @@ -74,6 +74,7 @@ struct kvm_s390_io_adapter_req { #define KVM_S390_VM_CRYPTO 2 #define KVM_S390_VM_CPU_MODEL 3 #define KVM_S390_VM_MIGRATION 4 +#define KVM_S390_VM_CPU_TOPOLOGY 5 /* kvm attributes for mem_ctrl */ #define KVM_S390_VM_MEM_ENABLE_CMMA 0 diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h index bf6e96011d..46de10a809 100644 --- a/linux-headers/asm-x86/kvm.h +++ b/linux-headers/asm-x86/kvm.h @@ -198,13 +198,13 @@ struct kvm_msrs { __u32 nmsrs; /* number of msrs in entries */ __u32 pad; - struct kvm_msr_entry entries[0]; + struct kvm_msr_entry entries[]; }; /* for KVM_GET_MSR_INDEX_LIST */ struct kvm_msr_list { __u32 nmsrs; /* number of msrs in entries */ - __u32 indices[0]; + __u32 indices[]; }; /* Maximum size of any access bitmap in bytes */ @@ -241,7 +241,7 @@ struct kvm_cpuid_entry { struct kvm_cpuid { __u32 nent; __u32 padding; - struct kvm_cpuid_entry entries[0]; + struct kvm_cpuid_entry entries[]; }; struct kvm_cpuid_entry2 { @@ -263,7 +263,7 @@ struct kvm_cpuid_entry2 { struct kvm_cpuid2 { __u32 nent; __u32 padding; - struct kvm_cpuid_entry2 entries[0]; + struct kvm_cpuid_entry2 entries[]; }; /* for KVM_GET_PIT and KVM_SET_PIT */ @@ -306,7 +306,8 @@ struct kvm_pit_state { struct kvm_pit_channel_state channels[3]; }; -#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001 +#define KVM_PIT_FLAGS_HPET_LEGACY 0x00000001 +#define KVM_PIT_FLAGS_SPEAKER_DATA_ON 0x00000002 struct kvm_pit_state2 { struct kvm_pit_channel_state channels[3]; @@ -325,6 +326,7 @@ struct kvm_reinject_control { #define KVM_VCPUEVENT_VALID_SHADOW 0x00000004 #define KVM_VCPUEVENT_VALID_SMM 0x00000008 #define KVM_VCPUEVENT_VALID_PAYLOAD 0x00000010 +#define KVM_VCPUEVENT_VALID_TRIPLE_FAULT 0x00000020 /* Interrupt shadow states */ #define KVM_X86_SHADOW_INT_MOV_SS 0x01 @@ -359,7 +361,10 @@ struct kvm_vcpu_events { __u8 smm_inside_nmi; __u8 latched_init; } smi; - __u8 reserved[27]; + struct { + __u8 pending; + } triple_fault; + __u8 reserved[26]; __u8 exception_has_payload; __u64 exception_payload; }; @@ -389,7 +394,7 @@ struct kvm_xsave { * the contents of CPUID leaf 0xD on the host. */ __u32 region[1024]; - __u32 extra[0]; + __u32 extra[]; }; #define KVM_MAX_XCRS 16 @@ -428,11 +433,13 @@ struct kvm_sync_regs { struct kvm_vcpu_events events; }; -#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) -#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) -#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) -#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) -#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) +#define KVM_X86_QUIRK_LINT0_REENABLED (1 << 0) +#define KVM_X86_QUIRK_CD_NW_CLEARED (1 << 1) +#define KVM_X86_QUIRK_LAPIC_MMIO_HOLE (1 << 2) +#define KVM_X86_QUIRK_OUT_7E_INC_RIP (1 << 3) +#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4) +#define KVM_X86_QUIRK_FIX_HYPERCALL_INSN (1 << 5) +#define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6) #define KVM_STATE_NESTED_FORMAT_VMX 0 #define KVM_STATE_NESTED_FORMAT_SVM 1 @@ -515,7 +522,7 @@ struct kvm_pmu_event_filter { __u32 fixed_counter_bitmap; __u32 flags; __u32 pad[4]; - __u64 events[0]; + __u64 events[]; }; #define KVM_PMU_EVENT_ALLOW 0 diff --git a/linux-headers/asm-x86/mman.h b/linux-headers/asm-x86/mman.h index d4a8d0424b..775dbd3aff 100644 --- a/linux-headers/asm-x86/mman.h +++ b/linux-headers/asm-x86/mman.h @@ -5,20 +5,6 @@ #define MAP_32BIT 0x40 /* only give out 32bit addresses */ #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS -/* - * Take the 4 protection key bits out of the vma->vm_flags - * value and turn them in to the bits that we can put in - * to a pte. - * - * Only override these if Protection Keys are available - * (which is only on 64-bit). - */ -#define arch_vm_get_page_prot(vm_flags) __pgprot( \ - ((vm_flags) & VM_PKEY_BIT0 ? _PAGE_PKEY_BIT0 : 0) | \ - ((vm_flags) & VM_PKEY_BIT1 ? _PAGE_PKEY_BIT1 : 0) | \ - ((vm_flags) & VM_PKEY_BIT2 ? _PAGE_PKEY_BIT2 : 0) | \ - ((vm_flags) & VM_PKEY_BIT3 ? _PAGE_PKEY_BIT3 : 0)) - #define arch_calc_vm_prot_bits(prot, key) ( \ ((key) & 0x1 ? VM_PKEY_BIT0 : 0) | \ ((key) & 0x2 ? VM_PKEY_BIT1 : 0) | \ diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index f089349149..ebdafa576d 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -270,6 +270,8 @@ struct kvm_xen_exit { #define KVM_EXIT_X86_BUS_LOCK 33 #define KVM_EXIT_XEN 34 #define KVM_EXIT_RISCV_SBI 35 +#define KVM_EXIT_RISCV_CSR 36 +#define KVM_EXIT_NOTIFY 37 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -444,6 +446,9 @@ struct kvm_run { #define KVM_SYSTEM_EVENT_SHUTDOWN 1 #define KVM_SYSTEM_EVENT_RESET 2 #define KVM_SYSTEM_EVENT_CRASH 3 +#define KVM_SYSTEM_EVENT_WAKEUP 4 +#define KVM_SYSTEM_EVENT_SUSPEND 5 +#define KVM_SYSTEM_EVENT_SEV_TERM 6 __u32 type; __u32 ndata; union { @@ -491,6 +496,18 @@ struct kvm_run { unsigned long args[6]; unsigned long ret[2]; } riscv_sbi; + /* KVM_EXIT_RISCV_CSR */ + struct { + unsigned long csr_num; + unsigned long new_value; + unsigned long write_mask; + unsigned long ret_value; + } riscv_csr; + /* KVM_EXIT_NOTIFY */ + struct { +#define KVM_NOTIFY_CONTEXT_INVALID (1 << 0) + __u32 flags; + } notify; /* Fix the size of the union. */ char padding[256]; }; @@ -537,7 +554,7 @@ struct kvm_coalesced_mmio { struct kvm_coalesced_mmio_ring { __u32 first, last; - struct kvm_coalesced_mmio coalesced_mmio[0]; + struct kvm_coalesced_mmio coalesced_mmio[]; }; #define KVM_COALESCED_MMIO_MAX \ @@ -616,7 +633,7 @@ struct kvm_clear_dirty_log { /* for KVM_SET_SIGNAL_MASK */ struct kvm_signal_mask { __u32 len; - __u8 sigset[0]; + __u8 sigset[]; }; /* for KVM_TPR_ACCESS_REPORTING */ @@ -644,6 +661,7 @@ struct kvm_vapic_addr { #define KVM_MP_STATE_OPERATING 7 #define KVM_MP_STATE_LOAD 8 #define KVM_MP_STATE_AP_RESET_HOLD 9 +#define KVM_MP_STATE_SUSPENDED 10 struct kvm_mp_state { __u32 mp_state; @@ -1148,8 +1166,15 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_MEM_OP_EXTENSION 211 #define KVM_CAP_PMU_CAPABILITY 212 #define KVM_CAP_DISABLE_QUIRKS2 213 -/* #define KVM_CAP_VM_TSC_CONTROL 214 */ +#define KVM_CAP_VM_TSC_CONTROL 214 #define KVM_CAP_SYSTEM_EVENT_DATA 215 +#define KVM_CAP_ARM_SYSTEM_SUSPEND 216 +#define KVM_CAP_S390_PROTECTED_DUMP 217 +#define KVM_CAP_X86_TRIPLE_FAULT_EVENT 218 +#define KVM_CAP_X86_NOTIFY_VMEXIT 219 +#define KVM_CAP_VM_DISABLE_NX_HUGE_PAGES 220 +#define KVM_CAP_S390_ZPCI_OP 221 +#define KVM_CAP_S390_CPU_TOPOLOGY 222 #ifdef KVM_CAP_IRQ_ROUTING @@ -1214,7 +1239,7 @@ struct kvm_irq_routing_entry { struct kvm_irq_routing { __u32 nr; __u32 flags; - struct kvm_irq_routing_entry entries[0]; + struct kvm_irq_routing_entry entries[]; }; #endif @@ -1238,6 +1263,7 @@ struct kvm_x86_mce { #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) +#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) struct kvm_xen_hvm_config { __u32 flags; @@ -1333,7 +1359,7 @@ struct kvm_dirty_tlb { struct kvm_reg_list { __u64 n; /* number of regs */ - __u64 reg[0]; + __u64 reg[]; }; struct kvm_one_reg { @@ -1476,7 +1502,8 @@ struct kvm_s390_ucas_mapping { #define KVM_SET_PIT2 _IOW(KVMIO, 0xa0, struct kvm_pit_state2) /* Available with KVM_CAP_PPC_GET_PVINFO */ #define KVM_PPC_GET_PVINFO _IOW(KVMIO, 0xa1, struct kvm_ppc_pvinfo) -/* Available with KVM_CAP_TSC_CONTROL */ +/* Available with KVM_CAP_TSC_CONTROL for a vCPU, or with +* KVM_CAP_VM_TSC_CONTROL to set defaults for a VM */ #define KVM_SET_TSC_KHZ _IO(KVMIO, 0xa2) #define KVM_GET_TSC_KHZ _IO(KVMIO, 0xa3) /* Available with KVM_CAP_PCI_2_3 */ @@ -1651,6 +1678,55 @@ struct kvm_s390_pv_unp { __u64 tweak; }; +enum pv_cmd_dmp_id { + KVM_PV_DUMP_INIT, + KVM_PV_DUMP_CONFIG_STOR_STATE, + KVM_PV_DUMP_COMPLETE, + KVM_PV_DUMP_CPU, +}; + +struct kvm_s390_pv_dmp { + __u64 subcmd; + __u64 buff_addr; + __u64 buff_len; + __u64 gaddr; /* For dump storage state */ + __u64 reserved[4]; +}; + +enum pv_cmd_info_id { + KVM_PV_INFO_VM, + KVM_PV_INFO_DUMP, +}; + +struct kvm_s390_pv_info_dump { + __u64 dump_cpu_buffer_len; + __u64 dump_config_mem_buffer_per_1m; + __u64 dump_config_finalize_len; +}; + +struct kvm_s390_pv_info_vm { + __u64 inst_calls_list[4]; + __u64 max_cpus; + __u64 max_guests; + __u64 max_guest_addr; + __u64 feature_indication; +}; + +struct kvm_s390_pv_info_header { + __u32 id; + __u32 len_max; + __u32 len_written; + __u32 reserved; +}; + +struct kvm_s390_pv_info { + struct kvm_s390_pv_info_header header; + union { + struct kvm_s390_pv_info_dump dump; + struct kvm_s390_pv_info_vm vm; + }; +}; + enum pv_cmd_id { KVM_PV_ENABLE, KVM_PV_DISABLE, @@ -1659,6 +1735,8 @@ enum pv_cmd_id { KVM_PV_VERIFY, KVM_PV_PREP_RESET, KVM_PV_UNSHARE_ALL, + KVM_PV_INFO, + KVM_PV_DUMP, }; struct kvm_pv_cmd { @@ -1692,6 +1770,32 @@ struct kvm_xen_hvm_attr { struct { __u64 gfn; } shared_info; + struct { + __u32 send_port; + __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ + __u32 flags; +#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) +#define KVM_XEN_EVTCHN_UPDATE (1 << 1) +#define KVM_XEN_EVTCHN_RESET (1 << 2) + /* + * Events sent by the guest are either looped back to + * the guest itself (potentially on a different port#) + * or signalled via an eventfd. + */ + union { + struct { + __u32 port; + __u32 vcpu; + __u32 priority; + } port; + struct { + __u32 port; /* Zero for eventfd */ + __s32 fd; + } eventfd; + __u32 padding[4]; + } deliver; + } evtchn; + __u32 xen_version; __u64 pad[8]; } u; }; @@ -1700,11 +1804,17 @@ struct kvm_xen_hvm_attr { #define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 #define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 #define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 +#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) #define KVM_XEN_VCPU_SET_ATTR _IOW(KVMIO, 0xcb, struct kvm_xen_vcpu_attr) +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_HVM_EVTCHN_SEND _IOW(KVMIO, 0xd0, struct kvm_irq_routing_xen_evtchn) + #define KVM_GET_SREGS2 _IOR(KVMIO, 0xcc, struct kvm_sregs2) #define KVM_SET_SREGS2 _IOW(KVMIO, 0xcd, struct kvm_sregs2) @@ -1722,6 +1832,13 @@ struct kvm_xen_vcpu_attr { __u64 time_blocked; __u64 time_offline; } runstate; + __u32 vcpu_id; + struct { + __u32 port; + __u32 priority; + __u64 expires_ns; + } timer; + __u8 vector; } u; }; @@ -1732,6 +1849,10 @@ struct kvm_xen_vcpu_attr { #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 #define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 +#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 +#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 /* Secure Encrypted Virtualization command */ enum sev_cmd_id { @@ -2032,7 +2153,7 @@ struct kvm_stats_header { #define KVM_STATS_UNIT_SECONDS (0x2 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_CYCLES (0x3 << KVM_STATS_UNIT_SHIFT) #define KVM_STATS_UNIT_BOOLEAN (0x4 << KVM_STATS_UNIT_SHIFT) -#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_CYCLES +#define KVM_STATS_UNIT_MAX KVM_STATS_UNIT_BOOLEAN #define KVM_STATS_BASE_SHIFT 8 #define KVM_STATS_BASE_MASK (0xF << KVM_STATS_BASE_SHIFT) @@ -2067,4 +2188,41 @@ struct kvm_stats_desc { /* Available with KVM_CAP_XSAVE2 */ #define KVM_GET_XSAVE2 _IOR(KVMIO, 0xcf, struct kvm_xsave) +/* Available with KVM_CAP_S390_PROTECTED_DUMP */ +#define KVM_S390_PV_CPU_COMMAND _IOWR(KVMIO, 0xd0, struct kvm_pv_cmd) + +/* Available with KVM_CAP_X86_NOTIFY_VMEXIT */ +#define KVM_X86_NOTIFY_VMEXIT_ENABLED (1ULL << 0) +#define KVM_X86_NOTIFY_VMEXIT_USER (1ULL << 1) + +/* Available with KVM_CAP_S390_ZPCI_OP */ +#define KVM_S390_ZPCI_OP _IOW(KVMIO, 0xd1, struct kvm_s390_zpci_op) + +struct kvm_s390_zpci_op { + /* in */ + __u32 fh; /* target device */ + __u8 op; /* operation to perform */ + __u8 pad[3]; + union { + /* for KVM_S390_ZPCIOP_REG_AEN */ + struct { + __u64 ibv; /* Guest addr of interrupt bit vector */ + __u64 sb; /* Guest addr of summary bit */ + __u32 flags; + __u32 noi; /* Number of interrupts */ + __u8 isc; /* Guest interrupt subclass */ + __u8 sbo; /* Offset of guest summary bit vector */ + __u16 pad; + } reg_aen; + __u64 reserved[8]; + } u; +}; + +/* types for kvm_s390_zpci_op->op */ +#define KVM_S390_ZPCIOP_REG_AEN 0 +#define KVM_S390_ZPCIOP_DEREG_AEN 1 + +/* flags for kvm_s390_zpci_op->u.reg_aen.flags */ +#define KVM_S390_ZPCIOP_REGAEN_HOST (1 << 0) + #endif /* __LINUX_KVM_H */ diff --git a/linux-headers/linux/userfaultfd.h b/linux-headers/linux/userfaultfd.h index 769b8379e4..a3a377cd44 100644 --- a/linux-headers/linux/userfaultfd.h +++ b/linux-headers/linux/userfaultfd.h @@ -33,7 +33,8 @@ UFFD_FEATURE_THREAD_ID | \ UFFD_FEATURE_MINOR_HUGETLBFS | \ UFFD_FEATURE_MINOR_SHMEM | \ - UFFD_FEATURE_EXACT_ADDRESS) + UFFD_FEATURE_EXACT_ADDRESS | \ + UFFD_FEATURE_WP_HUGETLBFS_SHMEM) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -47,7 +48,8 @@ #define UFFD_API_RANGE_IOCTLS_BASIC \ ((__u64)1 << _UFFDIO_WAKE | \ (__u64)1 << _UFFDIO_COPY | \ - (__u64)1 << _UFFDIO_CONTINUE) + (__u64)1 << _UFFDIO_CONTINUE | \ + (__u64)1 << _UFFDIO_WRITEPROTECT) /* * Valid ioctl command number range with this API is from 0x00 to @@ -194,6 +196,9 @@ struct uffdio_api { * UFFD_FEATURE_EXACT_ADDRESS indicates that the exact address of page * faults would be provided and the offset within the page would not be * masked. + * + * UFFD_FEATURE_WP_HUGETLBFS_SHMEM indicates that userfaultfd + * write-protection mode is supported on both shmem and hugetlbfs. */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) @@ -207,6 +212,7 @@ struct uffdio_api { #define UFFD_FEATURE_MINOR_HUGETLBFS (1<<9) #define UFFD_FEATURE_MINOR_SHMEM (1<<10) #define UFFD_FEATURE_EXACT_ADDRESS (1<<11) +#define UFFD_FEATURE_WP_HUGETLBFS_SHMEM (1<<12) __u64 features; __u64 ioctls; diff --git a/linux-headers/linux/vduse.h b/linux-headers/linux/vduse.h index d47b004ce6..6d2ca064b5 100644 --- a/linux-headers/linux/vduse.h +++ b/linux-headers/linux/vduse.h @@ -210,6 +210,53 @@ struct vduse_vq_eventfd { */ #define VDUSE_VQ_INJECT_IRQ _IOW(VDUSE_BASE, 0x17, __u32) +/** + * struct vduse_iova_umem - userspace memory configuration for one IOVA region + * @uaddr: start address of userspace memory, it must be aligned to page size + * @iova: start of the IOVA region + * @size: size of the IOVA region + * @reserved: for future use, needs to be initialized to zero + * + * Structure used by VDUSE_IOTLB_REG_UMEM and VDUSE_IOTLB_DEREG_UMEM + * ioctls to register/de-register userspace memory for IOVA regions + */ +struct vduse_iova_umem { + __u64 uaddr; + __u64 iova; + __u64 size; + __u64 reserved[3]; +}; + +/* Register userspace memory for IOVA regions */ +#define VDUSE_IOTLB_REG_UMEM _IOW(VDUSE_BASE, 0x18, struct vduse_iova_umem) + +/* De-register the userspace memory. Caller should set iova and size field. */ +#define VDUSE_IOTLB_DEREG_UMEM _IOW(VDUSE_BASE, 0x19, struct vduse_iova_umem) + +/** + * struct vduse_iova_info - information of one IOVA region + * @start: start of the IOVA region + * @last: last of the IOVA region + * @capability: capability of the IOVA regsion + * @reserved: for future use, needs to be initialized to zero + * + * Structure used by VDUSE_IOTLB_GET_INFO ioctl to get information of + * one IOVA region. + */ +struct vduse_iova_info { + __u64 start; + __u64 last; +#define VDUSE_IOVA_CAP_UMEM (1 << 0) + __u64 capability; + __u64 reserved[3]; +}; + +/* + * Find the first IOVA region that overlaps with the range [start, last] + * and return some information on it. Caller should set start and last fields. + */ +#define VDUSE_IOTLB_GET_INFO _IOWR(VDUSE_BASE, 0x1a, struct vduse_iova_info) + /* The control messages definition for read(2)/write(2) on /dev/vduse/$NAME */ /** diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h index e9f7795c39..ede44b5572 100644 --- a/linux-headers/linux/vfio.h +++ b/linux-headers/linux/vfio.h @@ -643,7 +643,7 @@ enum { }; /** - * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IORW(VFIO_TYPE, VFIO_BASE + 12, + * VFIO_DEVICE_GET_PCI_HOT_RESET_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 12, * struct vfio_pci_hot_reset_info) * * Return: 0 on success, -errno on failure: @@ -770,7 +770,7 @@ struct vfio_device_ioeventfd { #define VFIO_DEVICE_IOEVENTFD _IO(VFIO_TYPE, VFIO_BASE + 16) /** - * VFIO_DEVICE_FEATURE - _IORW(VFIO_TYPE, VFIO_BASE + 17, + * VFIO_DEVICE_FEATURE - _IOWR(VFIO_TYPE, VFIO_BASE + 17, * struct vfio_device_feature) * * Get, set, or probe feature data of the device. The feature is selected diff --git a/linux-headers/linux/vfio_zdev.h b/linux-headers/linux/vfio_zdev.h index b4309397b6..77f2aff1f2 100644 --- a/linux-headers/linux/vfio_zdev.h +++ b/linux-headers/linux/vfio_zdev.h @@ -29,6 +29,9 @@ struct vfio_device_info_cap_zpci_base { __u16 fmb_length; /* Measurement Block Length (in bytes) */ __u8 pft; /* PCI Function Type */ __u8 gid; /* PCI function group ID */ + /* End of version 1 */ + __u32 fh; /* PCI function handle */ + /* End of version 2 */ }; /** @@ -47,6 +50,10 @@ struct vfio_device_info_cap_zpci_group { __u16 noi; /* Maximum number of MSIs */ __u16 maxstbl; /* Maximum Store Block Length */ __u8 version; /* Supported PCI Version */ + /* End of version 1 */ + __u8 reserved; + __u16 imaxstbl; /* Maximum Interpreted Store Block Length */ + /* End of version 2 */ }; /** diff --git a/linux-headers/linux/vhost.h b/linux-headers/linux/vhost.h index 5d99e7c242..f9f115a7c7 100644 --- a/linux-headers/linux/vhost.h +++ b/linux-headers/linux/vhost.h @@ -89,11 +89,6 @@ /* Set or get vhost backend capability */ -/* Use message type V2 */ -#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1 -/* IOTLB can accept batching hints */ -#define VHOST_BACKEND_F_IOTLB_BATCH 0x2 - #define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64) #define VHOST_GET_BACKEND_FEATURES _IOR(VHOST_VIRTIO, 0x26, __u64) @@ -150,11 +145,39 @@ /* Get the valid iova range */ #define VHOST_VDPA_GET_IOVA_RANGE _IOR(VHOST_VIRTIO, 0x78, \ struct vhost_vdpa_iova_range) - /* Get the config size */ #define VHOST_VDPA_GET_CONFIG_SIZE _IOR(VHOST_VIRTIO, 0x79, __u32) /* Get the count of all virtqueues */ #define VHOST_VDPA_GET_VQS_COUNT _IOR(VHOST_VIRTIO, 0x80, __u32) +/* Get the number of virtqueue groups. */ +#define VHOST_VDPA_GET_GROUP_NUM _IOR(VHOST_VIRTIO, 0x81, __u32) + +/* Get the number of address spaces. */ +#define VHOST_VDPA_GET_AS_NUM _IOR(VHOST_VIRTIO, 0x7A, unsigned int) + +/* Get the group for a virtqueue: read index, write group in num, + * The virtqueue index is stored in the index field of + * vhost_vring_state. The group for this specific virtqueue is + * returned via num field of vhost_vring_state. + */ +#define VHOST_VDPA_GET_VRING_GROUP _IOWR(VHOST_VIRTIO, 0x7B, \ + struct vhost_vring_state) +/* Set the ASID for a virtqueue group. The group index is stored in + * the index field of vhost_vring_state, the ASID associated with this + * group is stored at num field of vhost_vring_state. + */ +#define VHOST_VDPA_SET_GROUP_ASID _IOW(VHOST_VIRTIO, 0x7C, \ + struct vhost_vring_state) + +/* Suspend a device so it does not process virtqueue requests anymore + * + * After the return of ioctl the device must preserve all the necessary state + * (the virtqueue vring base plus the possible device specific states) that is + * required for restoring in the future. The device must not change its + * configuration after that point. + */ +#define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D) + #endif diff --git a/linux-user/include/host/s390/host-signal.h b/linux-user/include/host/s390/host-signal.h index 25fefa00bd..e6d3ec26dc 100644 --- a/linux-user/include/host/s390/host-signal.h +++ b/linux-user/include/host/s390/host-signal.h @@ -87,6 +87,31 @@ static inline bool host_signal_write(siginfo_t *info, host_sigcontext *uc) return true; } break; + case 0xe6: + switch (pinsn[2] & 0xff) { + case 0x09: /* VSTEBRH */ + case 0x0a: /* VSTEBRG */ + case 0x0b: /* VSTEBRF */ + case 0x0e: /* VSTBR */ + case 0x0f: /* VSTER */ + case 0x3f: /* VSTRLR */ + return true; + } + break; + case 0xe7: + switch (pinsn[2] & 0xff) { + case 0x08: /* VSTEB */ + case 0x09: /* VSTEH */ + case 0x0a: /* VSTEG */ + case 0x0b: /* VSTEF */ + case 0x0e: /* VST */ + case 0x1a: /* VSCEG */ + case 0x1b: /* VSCEF */ + case 0x3e: /* VSTM */ + case 0x3f: /* VSTL */ + return true; + } + break; case 0xeb: /* RSY format insns */ switch (pinsn[2] & 0xff) { case 0x14: /* CSY */ diff --git a/meson.build b/meson.build index 13db89c65a..8dc661363f 100644 --- a/meson.build +++ b/meson.build @@ -637,6 +637,26 @@ else method: 'pkg-config', kwargs: static_kwargs) endif +slirp = not_found +if not get_option('slirp').auto() or have_system + slirp = dependency('slirp', required: get_option('slirp'), + method: 'pkg-config', kwargs: static_kwargs) + # slirp < 4.7 is incompatible with CFI support in QEMU. This is because + # it passes function pointers within libslirp as callbacks for timers. + # When using a system-wide shared libslirp, the type information for the + # callback is missing and the timer call produces a false positive with CFI. + # Do not use the "version" keyword argument to produce a better error. + # with control-flow integrity. + if get_option('cfi') and slirp.found() and slirp.version().version_compare('<4.7') + if get_option('slirp').enabled() + error('Control-Flow Integrity requires libslirp 4.7.') + else + warning('Cannot use libslirp since Control-Flow Integrity requires libslirp >= 4.7.') + slirp = not_found + endif + endif +endif + vde = not_found if not get_option('vde').auto() or have_system or have_tools vde = cc.find_library('vdeplug', has_headers: ['libvdeplug.h'], @@ -2617,103 +2637,6 @@ if not get_option('capstone').auto() or have_system or have_user endif endif -slirp = not_found -slirp_opt = 'disabled' -if have_system - slirp_opt = get_option('slirp') - if slirp_opt in ['enabled', 'auto', 'system'] - have_internal = fs.exists(meson.current_source_dir() / 'slirp/meson.build') - slirp_dep_required = (slirp_opt == 'system' or - slirp_opt == 'enabled' and not have_internal) - slirp = dependency('slirp', kwargs: static_kwargs, - method: 'pkg-config', version: '>=4.1.0', - required: slirp_dep_required) - # slirp <4.7 is incompatible with CFI support in QEMU. This is because - # it passes function pointers within libslirp as callbacks for timers. - # When using a system-wide shared libslirp, the type information for the - # callback is missing and the timer call produces a false positive with CFI. - # Do not use the "version" keyword argument to produce a better error. - # with control-flow integrity. - if get_option('cfi') and slirp.found() and slirp.version().version_compare('<4.7') - if slirp_dep_required - error('Control-Flow Integrity requires libslirp 4.7.') - else - warning('Control-Flow Integrity requires libslirp 4.7, not using system-wide libslirp.') - slirp = not_found - endif - endif - if slirp.found() - slirp_opt = 'system' - elif have_internal - slirp_opt = 'internal' - else - slirp_opt = 'disabled' - endif - endif - if slirp_opt == 'internal' - slirp_deps = [] - if targetos == 'windows' - slirp_deps = cc.find_library('iphlpapi') - elif targetos == 'darwin' - slirp_deps = cc.find_library('resolv') - endif - slirp_conf = configuration_data() - slirp_conf.set('SLIRP_MAJOR_VERSION', meson.project_version().split('.')[0]) - slirp_conf.set('SLIRP_MINOR_VERSION', meson.project_version().split('.')[1]) - slirp_conf.set('SLIRP_MICRO_VERSION', meson.project_version().split('.')[2]) - slirp_conf.set_quoted('SLIRP_VERSION_STRING', meson.project_version()) - slirp_cargs = ['-DG_LOG_DOMAIN="Slirp"'] - slirp_files = [ - 'slirp/src/arp_table.c', - 'slirp/src/bootp.c', - 'slirp/src/cksum.c', - 'slirp/src/dhcpv6.c', - 'slirp/src/dnssearch.c', - 'slirp/src/if.c', - 'slirp/src/ip6_icmp.c', - 'slirp/src/ip6_input.c', - 'slirp/src/ip6_output.c', - 'slirp/src/ip_icmp.c', - 'slirp/src/ip_input.c', - 'slirp/src/ip_output.c', - 'slirp/src/mbuf.c', - 'slirp/src/misc.c', - 'slirp/src/ncsi.c', - 'slirp/src/ndp_table.c', - 'slirp/src/sbuf.c', - 'slirp/src/slirp.c', - 'slirp/src/socket.c', - 'slirp/src/state.c', - 'slirp/src/stream.c', - 'slirp/src/tcp_input.c', - 'slirp/src/tcp_output.c', - 'slirp/src/tcp_subr.c', - 'slirp/src/tcp_timer.c', - 'slirp/src/tftp.c', - 'slirp/src/udp.c', - 'slirp/src/udp6.c', - 'slirp/src/util.c', - 'slirp/src/version.c', - 'slirp/src/vmstate.c', - ] - - configure_file( - input : 'slirp/src/libslirp-version.h.in', - output : 'libslirp-version.h', - configuration: slirp_conf) - - slirp_inc = include_directories('slirp', 'slirp/src') - libslirp = static_library('slirp', - build_by_default: false, - sources: slirp_files, - c_args: slirp_cargs, - include_directories: slirp_inc) - slirp = declare_dependency(link_with: libslirp, - dependencies: slirp_deps, - include_directories: slirp_inc) - endif -endif - libvfio_user_dep = not_found if have_system and vfio_user_server_allowed have_internal = fs.exists(meson.current_source_dir() / 'subprojects/libvfio-user/meson.build') @@ -3718,7 +3641,7 @@ summary_info += {'genisoimage': config_host['GENISOIMAGE']} if targetos == 'windows' and have_ga summary_info += {'wixl': wixl} endif -if slirp_opt != 'disabled' and have_system +if slirp.found() and have_system summary_info += {'smbd': have_slirp_smbd ? smbd_path : false} endif summary(summary_info, bool_yn: true, section: 'Host binaries') @@ -3912,7 +3835,7 @@ summary_info += {'SDL image support': sdl_image} summary_info += {'GTK support': gtk} summary_info += {'pixman': pixman} summary_info += {'VTE support': vte} -summary_info += {'slirp support': slirp_opt == 'internal' ? slirp_opt : slirp} +summary_info += {'slirp support': slirp} summary_info += {'libtasn1': tasn1} summary_info += {'PAM': pam} summary_info += {'iconv support': iconv} diff --git a/meson_options.txt b/meson_options.txt index 9df9e86d7d..79c6af18d5 100644 --- a/meson_options.txt +++ b/meson_options.txt @@ -199,6 +199,8 @@ option('l2tpv3', type : 'feature', value : 'auto', description: 'l2tpv3 network backend support') option('netmap', type : 'feature', value : 'auto', description: 'netmap network backend support') +option('slirp', type: 'feature', value: 'auto', + description: 'libslirp user mode network backend support') option('vde', type : 'feature', value : 'auto', description: 'vde network backend support') option('vmnet', type : 'feature', value : 'auto', @@ -266,9 +268,6 @@ option('vduse_blk_export', type: 'feature', value: 'auto', option('capstone', type: 'feature', value: 'auto', description: 'Whether and how to find the capstone library') -option('slirp', type: 'combo', value: 'auto', - choices: ['disabled', 'enabled', 'auto', 'system', 'internal'], - description: 'Whether and how to find the slirp library') option('fdt', type: 'combo', value: 'auto', choices: ['disabled', 'enabled', 'auto', 'system', 'internal'], description: 'Whether and how to find the libfdt library') diff --git a/qemu-options.hx b/qemu-options.hx index 2ff06884f4..913c71e38f 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -37,7 +37,8 @@ DEF("machine", HAS_ARG, QEMU_OPTION_machine, \ " memory-encryption=@var{} memory encryption object to use (default=none)\n" " hmat=on|off controls ACPI HMAT support (default=off)\n" " memory-backend='backend-id' specifies explicitly provided backend for main RAM (default=none)\n" - " cxl-fmw.0.targets.0=firsttarget,cxl-fmw.0.targets.1=secondtarget,cxl-fmw.0.size=size[,cxl-fmw.0.interleave-granularity=granularity]\n", + " cxl-fmw.0.targets.0=firsttarget,cxl-fmw.0.targets.1=secondtarget,cxl-fmw.0.size=size[,cxl-fmw.0.interleave-granularity=granularity]\n" + " zpcii-disable=on|off disables zPCI interpretation facilities (default=off)\n", QEMU_ARCH_ALL) SRST ``-machine [type=]name[,prop=value[,...]]`` @@ -157,6 +158,11 @@ SRST :: -machine cxl-fmw.0.targets.0=cxl.0,cxl-fmw.0.targets.1=cxl.1,cxl-fmw.0.size=128G,cxl-fmw.0.interleave-granularity=512k + + ``zpcii-disable=on|off`` + Disables zPCI interpretation facilties on s390-ccw hosts. + This feature can be used to disable hardware virtual assists + related to zPCI devices. The default is off. ERST DEF("M", HAS_ARG, QEMU_OPTION_M, diff --git a/scripts/archive-source.sh b/scripts/archive-source.sh index c6169db69f..23e042dacd 100755 --- a/scripts/archive-source.sh +++ b/scripts/archive-source.sh @@ -26,7 +26,7 @@ sub_file="${sub_tdir}/submodule.tar" # independent of what the developer currently has initialized # in their checkout, because the build environment is completely # different to the host OS. -submodules="dtc slirp meson ui/keycodemapdb" +submodules="dtc meson ui/keycodemapdb" submodules="$submodules tests/fp/berkeley-softfloat-3 tests/fp/berkeley-testfloat-3" sub_deinit="" diff --git a/scripts/meson-buildoptions.sh b/scripts/meson-buildoptions.sh index f08e3a8a7e..eb3267bef5 100644 --- a/scripts/meson-buildoptions.sh +++ b/scripts/meson-buildoptions.sh @@ -35,8 +35,6 @@ meson_options_help() { printf "%s\n" ' --enable-qom-cast-debug cast debugging support' printf "%s\n" ' --enable-rng-none dummy RNG, avoid using /dev/(u)random and' printf "%s\n" ' getrandom()' - printf "%s\n" ' --enable-slirp[=CHOICE] Whether and how to find the slirp library' - printf "%s\n" ' (choices: auto/disabled/enabled/internal/system)' printf "%s\n" ' --enable-strip Strip targets on install' printf "%s\n" ' --enable-tcg-interpreter TCG with bytecode interpreter (slow)' printf "%s\n" ' --enable-trace-backends=CHOICES' @@ -141,6 +139,7 @@ meson_options_help() { printf "%s\n" ' sdl-image SDL Image support for icons' printf "%s\n" ' seccomp seccomp support' printf "%s\n" ' selinux SELinux support in qemu-nbd' + printf "%s\n" ' slirp libslirp user mode network backend support' printf "%s\n" ' slirp-smbd use smbd (at path --smbd=*) in slirp networking' printf "%s\n" ' smartcard CA smartcard emulation support' printf "%s\n" ' snappy snappy compression support' @@ -387,7 +386,6 @@ _meson_option_parse() { --disable-selinux) printf "%s" -Dselinux=disabled ;; --enable-slirp) printf "%s" -Dslirp=enabled ;; --disable-slirp) printf "%s" -Dslirp=disabled ;; - --enable-slirp=*) quote_sh "-Dslirp=$2" ;; --enable-slirp-smbd) printf "%s" -Dslirp_smbd=enabled ;; --disable-slirp-smbd) printf "%s" -Dslirp_smbd=disabled ;; --enable-smartcard) printf "%s" -Dsmartcard=enabled ;; diff --git a/slirp b/slirp deleted file mode 160000 index 9d59bb775d..0000000000 --- a/slirp +++ /dev/null @@ -1 +0,0 @@ -Subproject commit 9d59bb775d6294c8b447a88512f7bb43f12a25a8 diff --git a/target/s390x/gen-features.c b/target/s390x/gen-features.c index 1558c52626..1e3b7c0dc9 100644 --- a/target/s390x/gen-features.c +++ b/target/s390x/gen-features.c @@ -744,13 +744,20 @@ static uint16_t qemu_V7_0[] = { S390_FEAT_MISC_INSTRUCTION_EXT3, }; +static uint16_t qemu_V7_1[] = { + S390_FEAT_VECTOR_ENH2, +}; + /* * Features for the "qemu" CPU model of the latest QEMU machine and the "max" * CPU model under TCG. Don't include features that are not part of the full * feature set of the current "max" CPU model generation. */ static uint16_t qemu_MAX[] = { - S390_FEAT_VECTOR_ENH2, + S390_FEAT_MSA_EXT_5, + S390_FEAT_KIMD_SHA_512, + S390_FEAT_KLMD_SHA_512, + S390_FEAT_PRNO_TRNG, }; /****** END FEATURE DEFS ******/ @@ -873,6 +880,7 @@ static FeatGroupDefSpec QemuFeatDef[] = { QEMU_FEAT_INITIALIZER(V6_0), QEMU_FEAT_INITIALIZER(V6_2), QEMU_FEAT_INITIALIZER(V7_0), + QEMU_FEAT_INITIALIZER(V7_1), QEMU_FEAT_INITIALIZER(MAX), }; diff --git a/target/s390x/kvm/kvm.c b/target/s390x/kvm/kvm.c index 7bd8db0e7b..6a8dbadf7e 100644 --- a/target/s390x/kvm/kvm.c +++ b/target/s390x/kvm/kvm.c @@ -157,6 +157,7 @@ static int cap_ri; static int cap_hpage_1m; static int cap_vcpu_resets; static int cap_protected; +static int cap_zpci_op; static bool mem_op_storage_key_support; @@ -362,6 +363,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s) cap_s390_irq = kvm_check_extension(s, KVM_CAP_S390_INJECT_IRQ); cap_vcpu_resets = kvm_check_extension(s, KVM_CAP_S390_VCPU_RESETS); cap_protected = kvm_check_extension(s, KVM_CAP_S390_PROTECTED); + cap_zpci_op = kvm_check_extension(s, KVM_CAP_S390_ZPCI_OP); kvm_vm_enable_cap(s, KVM_CAP_S390_USER_SIGP, 0); kvm_vm_enable_cap(s, KVM_CAP_S390_VECTOR_REGISTERS, 0); @@ -2574,3 +2576,8 @@ bool kvm_arch_cpu_check_are_resettable(void) { return true; } + +int kvm_s390_get_zpci_op(void) +{ + return cap_zpci_op; +} diff --git a/target/s390x/kvm/kvm_s390x.h b/target/s390x/kvm/kvm_s390x.h index 05a5e1e6f4..aaae8570de 100644 --- a/target/s390x/kvm/kvm_s390x.h +++ b/target/s390x/kvm/kvm_s390x.h @@ -27,6 +27,7 @@ void kvm_s390_vcpu_interrupt_pre_save(S390CPU *cpu); int kvm_s390_vcpu_interrupt_post_load(S390CPU *cpu); int kvm_s390_get_hpage_1m(void); int kvm_s390_get_ri(void); +int kvm_s390_get_zpci_op(void); int kvm_s390_get_clock(uint8_t *tod_high, uint64_t *tod_clock); int kvm_s390_get_clock_ext(uint8_t *tod_high, uint64_t *tod_clock); int kvm_s390_set_clock(uint8_t tod_high, uint64_t tod_clock); diff --git a/target/s390x/tcg/crypto_helper.c b/target/s390x/tcg/crypto_helper.c index 138d9e7ad9..762b277884 100644 --- a/target/s390x/tcg/crypto_helper.c +++ b/target/s390x/tcg/crypto_helper.c @@ -1,10 +1,12 @@ /* * s390x crypto helpers * + * Copyright (C) 2022 Jason A. Donenfeld . All Rights Reserved. * Copyright (c) 2017 Red Hat Inc * * Authors: * David Hildenbrand + * Jason A. Donenfeld * * This work is licensed under the terms of the GNU GPL, version 2 or later. * See the COPYING file in the top-level directory. @@ -12,12 +14,262 @@ #include "qemu/osdep.h" #include "qemu/main-loop.h" +#include "qemu/guest-random.h" #include "s390x-internal.h" #include "tcg_s390x.h" #include "exec/helper-proto.h" #include "exec/exec-all.h" #include "exec/cpu_ldst.h" +static uint64_t R(uint64_t x, int c) +{ + return (x >> c) | (x << (64 - c)); +} +static uint64_t Ch(uint64_t x, uint64_t y, uint64_t z) +{ + return (x & y) ^ (~x & z); +} +static uint64_t Maj(uint64_t x, uint64_t y, uint64_t z) +{ + return (x & y) ^ (x & z) ^ (y & z); +} +static uint64_t Sigma0(uint64_t x) +{ + return R(x, 28) ^ R(x, 34) ^ R(x, 39); +} +static uint64_t Sigma1(uint64_t x) +{ + return R(x, 14) ^ R(x, 18) ^ R(x, 41); +} +static uint64_t sigma0(uint64_t x) +{ + return R(x, 1) ^ R(x, 8) ^ (x >> 7); +} +static uint64_t sigma1(uint64_t x) +{ + return R(x, 19) ^ R(x, 61) ^ (x >> 6); +} + +static const uint64_t K[80] = { + 0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL, 0xb5c0fbcfec4d3b2fULL, + 0xe9b5dba58189dbbcULL, 0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL, + 0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL, 0xd807aa98a3030242ULL, + 0x12835b0145706fbeULL, 0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL, + 0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL, 0x9bdc06a725c71235ULL, + 0xc19bf174cf692694ULL, 0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL, + 0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL, 0x2de92c6f592b0275ULL, + 0x4a7484aa6ea6e483ULL, 0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL, + 0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL, 0xb00327c898fb213fULL, + 0xbf597fc7beef0ee4ULL, 0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL, + 0x06ca6351e003826fULL, 0x142929670a0e6e70ULL, 0x27b70a8546d22ffcULL, + 0x2e1b21385c26c926ULL, 0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL, + 0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL, 0x81c2c92e47edaee6ULL, + 0x92722c851482353bULL, 0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL, + 0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL, 0xd192e819d6ef5218ULL, + 0xd69906245565a910ULL, 0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL, + 0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL, 0x2748774cdf8eeb99ULL, + 0x34b0bcb5e19b48a8ULL, 0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL, + 0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL, 0x748f82ee5defb2fcULL, + 0x78a5636f43172f60ULL, 0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL, + 0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL, 0xbef9a3f7b2c67915ULL, + 0xc67178f2e372532bULL, 0xca273eceea26619cULL, 0xd186b8c721c0c207ULL, + 0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL, 0x06f067aa72176fbaULL, + 0x0a637dc5a2c898a6ULL, 0x113f9804bef90daeULL, 0x1b710b35131c471bULL, + 0x28db77f523047d84ULL, 0x32caab7b40c72493ULL, 0x3c9ebe0a15c9bebcULL, + 0x431d67c49c100d4cULL, 0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL, + 0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL +}; + +/* a is icv/ocv, w is a single message block. w will get reused internally. */ +static void sha512_bda(uint64_t a[8], uint64_t w[16]) +{ + uint64_t t, z[8], b[8]; + int i, j; + + memcpy(z, a, sizeof(z)); + for (i = 0; i < 80; i++) { + memcpy(b, a, sizeof(b)); + + t = a[7] + Sigma1(a[4]) + Ch(a[4], a[5], a[6]) + K[i] + w[i % 16]; + b[7] = t + Sigma0(a[0]) + Maj(a[0], a[1], a[2]); + b[3] += t; + for (j = 0; j < 8; ++j) { + a[(j + 1) % 8] = b[j]; + } + if (i % 16 == 15) { + for (j = 0; j < 16; ++j) { + w[j] += w[(j + 9) % 16] + sigma0(w[(j + 1) % 16]) + + sigma1(w[(j + 14) % 16]); + } + } + } + + for (i = 0; i < 8; i++) { + a[i] += z[i]; + } +} + +/* a is icv/ocv, w is a single message block that needs be64 conversion. */ +static void sha512_bda_be64(uint64_t a[8], uint64_t w[16]) +{ + uint64_t t[16]; + int i; + + for (i = 0; i < 16; i++) { + t[i] = be64_to_cpu(w[i]); + } + sha512_bda(a, t); +} + +static void sha512_read_icv(CPUS390XState *env, uint64_t addr, + uint64_t a[8], uintptr_t ra) +{ + int i; + + for (i = 0; i < 8; i++, addr += 8) { + addr = wrap_address(env, addr); + a[i] = cpu_ldq_be_data_ra(env, addr, ra); + } +} + +static void sha512_write_ocv(CPUS390XState *env, uint64_t addr, + uint64_t a[8], uintptr_t ra) +{ + int i; + + for (i = 0; i < 8; i++, addr += 8) { + addr = wrap_address(env, addr); + cpu_stq_be_data_ra(env, addr, a[i], ra); + } +} + +static void sha512_read_block(CPUS390XState *env, uint64_t addr, + uint64_t a[16], uintptr_t ra) +{ + int i; + + for (i = 0; i < 16; i++, addr += 8) { + addr = wrap_address(env, addr); + a[i] = cpu_ldq_be_data_ra(env, addr, ra); + } +} + +static void sha512_read_mbl_be64(CPUS390XState *env, uint64_t addr, + uint8_t a[16], uintptr_t ra) +{ + int i; + + for (i = 0; i < 16; i++, addr += 1) { + addr = wrap_address(env, addr); + a[i] = cpu_ldub_data_ra(env, addr, ra); + } +} + +static int cpacf_sha512(CPUS390XState *env, uintptr_t ra, uint64_t param_addr, + uint64_t *message_reg, uint64_t *len_reg, uint32_t type) +{ + enum { MAX_BLOCKS_PER_RUN = 64 }; /* Arbitrary: keep interactivity. */ + uint64_t len = *len_reg, a[8], processed = 0; + int i, message_reg_len = 64; + + g_assert(type == S390_FEAT_TYPE_KIMD || type == S390_FEAT_TYPE_KLMD); + + if (!(env->psw.mask & PSW_MASK_64)) { + len = (uint32_t)len; + message_reg_len = (env->psw.mask & PSW_MASK_32) ? 32 : 24; + } + + /* KIMD: length has to be properly aligned. */ + if (type == S390_FEAT_TYPE_KIMD && !QEMU_IS_ALIGNED(len, 128)) { + tcg_s390_program_interrupt(env, PGM_SPECIFICATION, ra); + } + + sha512_read_icv(env, param_addr, a, ra); + + /* Process full blocks first. */ + for (; len >= 128; len -= 128, processed += 128) { + uint64_t w[16]; + + if (processed >= MAX_BLOCKS_PER_RUN * 128) { + break; + } + + sha512_read_block(env, *message_reg + processed, w, ra); + sha512_bda(a, w); + } + + /* KLMD: Process partial/empty block last. */ + if (type == S390_FEAT_TYPE_KLMD && len < 128) { + uint8_t x[128]; + + /* Read the remainder of the message byte-per-byte. */ + for (i = 0; i < len; i++) { + uint64_t addr = wrap_address(env, *message_reg + processed + i); + + x[i] = cpu_ldub_data_ra(env, addr, ra); + } + /* Pad the remainder with zero and set the top bit. */ + memset(x + len, 0, 128 - len); + x[len] = 128; + + /* + * Place the MBL either into this block (if there is space left), + * or use an additional one. + */ + if (len < 112) { + sha512_read_mbl_be64(env, param_addr + 64, x + 112, ra); + } + sha512_bda_be64(a, (uint64_t *)x); + + if (len >= 112) { + memset(x, 0, 112); + sha512_read_mbl_be64(env, param_addr + 64, x + 112, ra); + sha512_bda_be64(a, (uint64_t *)x); + } + + processed += len; + len = 0; + } + + /* + * Modify memory after we read all inputs and modify registers only after + * writing memory succeeded. + * + * TODO: if writing fails halfway through (e.g., when crossing page + * boundaries), we're in trouble. We'd need something like access_prepare(). + */ + sha512_write_ocv(env, param_addr, a, ra); + *message_reg = deposit64(*message_reg, 0, message_reg_len, + *message_reg + processed); + *len_reg -= processed; + return !len ? 0 : 3; +} + +static void fill_buf_random(CPUS390XState *env, uintptr_t ra, + uint64_t *buf_reg, uint64_t *len_reg) +{ + uint8_t tmp[256]; + uint64_t len = *len_reg; + int buf_reg_len = 64; + + if (!(env->psw.mask & PSW_MASK_64)) { + len = (uint32_t)len; + buf_reg_len = (env->psw.mask & PSW_MASK_32) ? 32 : 24; + } + + while (len) { + size_t block = MIN(len, sizeof(tmp)); + + qemu_guest_getrandom_nofail(tmp, block); + for (size_t i = 0; i < block; ++i) { + cpu_stb_data_ra(env, wrap_address(env, *buf_reg), tmp[i], ra); + *buf_reg = deposit64(*buf_reg, 0, buf_reg_len, *buf_reg + 1); + --*len_reg; + } + len -= block; + } +} + uint32_t HELPER(msa)(CPUS390XState *env, uint32_t r1, uint32_t r2, uint32_t r3, uint32_t type) { @@ -52,6 +304,13 @@ uint32_t HELPER(msa)(CPUS390XState *env, uint32_t r1, uint32_t r2, uint32_t r3, cpu_stb_data_ra(env, param_addr, subfunc[i], ra); } break; + case 3: /* CPACF_*_SHA_512 */ + return cpacf_sha512(env, ra, env->regs[1], &env->regs[r2], + &env->regs[r2 + 1], type); + case 114: /* CPACF_PRNO_TRNG */ + fill_buf_random(env, ra, &env->regs[r1], &env->regs[r1 + 1]); + fill_buf_random(env, ra, &env->regs[r2], &env->regs[r2 + 1]); + break; default: /* we don't implement any other subfunction yet */ g_assert_not_reached(); diff --git a/target/s390x/tcg/insn-data.def b/target/s390x/tcg/insn-data.def index 6d2cfe5fa2..6382ceabfc 100644 --- a/target/s390x/tcg/insn-data.def +++ b/target/s390x/tcg/insn-data.def @@ -466,7 +466,7 @@ C(0xe39f, LAT, RXY_a, LAT, 0, m2_32u, r1, 0, lat, 0) C(0xe385, LGAT, RXY_a, LAT, 0, a2, r1, 0, lgat, 0) /* LOAD AND ZERO RIGHTMOST BYTE */ - C(0xe3eb, LZRF, RXY_a, LZRB, 0, m2_32u, new, r1_32, lzrb, 0) + C(0xe33b, LZRF, RXY_a, LZRB, 0, m2_32u, new, r1_32, lzrb, 0) C(0xe32a, LZRG, RXY_a, LZRB, 0, m2_64, r1, 0, lzrb, 0) /* LOAD LOGICAL AND ZERO RIGHTMOST BYTE */ C(0xe33a, LLZRGF, RXY_a, LZRB, 0, m2_32u, r1, 0, lzrb, 0) diff --git a/tests/avocado/machine_s390_ccw_virtio.py b/tests/avocado/machine_s390_ccw_virtio.py index 438a6f4321..78152f2ad1 100644 --- a/tests/avocado/machine_s390_ccw_virtio.py +++ b/tests/avocado/machine_s390_ccw_virtio.py @@ -66,6 +66,7 @@ class S390CCWVirtioMachine(QemuSystemTest): '-kernel', kernel_path, '-initrd', initrd_path, '-append', kernel_command_line, + '-cpu', 'max,prno-trng=off', '-device', 'virtio-net-ccw,devno=fe.1.1111', '-device', 'virtio-rng-ccw,devno=fe.2.0000,max_revision=0,id=rn1', diff --git a/util/qemu-config.c b/util/qemu-config.c index 433488aa56..5325f6bf80 100644 --- a/util/qemu-config.c +++ b/util/qemu-config.c @@ -236,6 +236,10 @@ static QemuOptsList machine_opts = { .help = "Up to 8 chars in set of [A-Za-z0-9. ](lower case chars" " converted to upper case) to pass to machine" " loader, boot manager, and guest kernel", + },{ + .name = "zpcii-disable", + .type = QEMU_OPT_BOOL, + .help = "disable zPCI interpretation facilities", }, { /* End of list */ } }