diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-08-05 00:59:54 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-08-05 00:59:54 +0300 |
commit | 7c5c3a6177fa9646884114fc7f2e970b0bc50dc9 (patch) | |
tree | 956857522574ae7cb07d2227dc16e53d7e9e00e7 /arch/s390/kvm/pv.c | |
parent | f0a892f599c46af673e47418c47c15e69a7b67f4 (diff) | |
parent | 281106f938d3daaea6f8b6723a8217a2a1ef6936 (diff) | |
download | linux-7c5c3a6177fa9646884114fc7f2e970b0bc50dc9.tar.xz |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm
Pull kvm updates from Paolo Bonzini:
"Quite a large pull request due to a selftest API overhaul and some
patches that had come in too late for 5.19.
ARM:
- Unwinder implementations for both nVHE modes (classic and
protected), complete with an overflow stack
- Rework of the sysreg access from userspace, with a complete rewrite
of the vgic-v3 view to allign with the rest of the infrastructure
- Disagregation of the vcpu flags in separate sets to better track
their use model.
- A fix for the GICv2-on-v3 selftest
- A small set of cosmetic fixes
RISC-V:
- Track ISA extensions used by Guest using bitmap
- Added system instruction emulation framework
- Added CSR emulation framework
- Added gfp_custom flag in struct kvm_mmu_memory_cache
- Added G-stage ioremap() and iounmap() functions
- Added support for Svpbmt inside Guest
s390:
- add an interface to provide a hypervisor dump for secure guests
- improve selftests to use TAP interface
- enable interpretive execution of zPCI instructions (for PCI
passthrough)
- First part of deferred teardown
- CPU Topology
- PV attestation
- Minor fixes
x86:
- Permit guests to ignore single-bit ECC errors
- Intel IPI virtualization
- Allow getting/setting pending triple fault with
KVM_GET/SET_VCPU_EVENTS
- PEBS virtualization
- Simplify PMU emulation by just using PERF_TYPE_RAW events
- More accurate event reinjection on SVM (avoid retrying
instructions)
- Allow getting/setting the state of the speaker port data bit
- Refuse starting the kvm-intel module if VM-Entry/VM-Exit controls
are inconsistent
- "Notify" VM exit (detect microarchitectural hangs) for Intel
- Use try_cmpxchg64 instead of cmpxchg64
- Ignore benign host accesses to PMU MSRs when PMU is disabled
- Allow disabling KVM's "MONITOR/MWAIT are NOPs!" behavior
- Allow NX huge page mitigation to be disabled on a per-vm basis
- Port eager page splitting to shadow MMU as well
- Enable CMCI capability by default and handle injected UCNA errors
- Expose pid of vcpu threads in debugfs
- x2AVIC support for AMD
- cleanup PIO emulation
- Fixes for LLDT/LTR emulation
- Don't require refcounted "struct page" to create huge SPTEs
- Miscellaneous cleanups:
- MCE MSR emulation
- Use separate namespaces for guest PTEs and shadow PTEs bitmasks
- PIO emulation
- Reorganize rmap API, mostly around rmap destruction
- Do not workaround very old KVM bugs for L0 that runs with nesting enabled
- new selftests API for CPUID
Generic:
- Fix races in gfn->pfn cache refresh; do not pin pages tracked by
the cache
- new selftests API using struct kvm_vcpu instead of a (vm, id)
tuple"
* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (606 commits)
selftests: kvm: set rax before vmcall
selftests: KVM: Add exponent check for boolean stats
selftests: KVM: Provide descriptive assertions in kvm_binary_stats_test
selftests: KVM: Check stat name before other fields
KVM: x86/mmu: remove unused variable
RISC-V: KVM: Add support for Svpbmt inside Guest/VM
RISC-V: KVM: Use PAGE_KERNEL_IO in kvm_riscv_gstage_ioremap()
RISC-V: KVM: Add G-stage ioremap() and iounmap() functions
KVM: Add gfp_custom flag in struct kvm_mmu_memory_cache
RISC-V: KVM: Add extensible CSR emulation framework
RISC-V: KVM: Add extensible system instruction emulation framework
RISC-V: KVM: Factor-out instruction emulation into separate sources
RISC-V: KVM: move preempt_disable() call in kvm_arch_vcpu_ioctl_run
RISC-V: KVM: Make kvm_riscv_guest_timer_init a void function
RISC-V: KVM: Fix variable spelling mistake
RISC-V: KVM: Improve ISA extension by using a bitmap
KVM, x86/mmu: Fix the comment around kvm_tdp_mmu_zap_leafs()
KVM: SVM: Dump Virtual Machine Save Area (VMSA) to klog
KVM: x86/mmu: Treat NX as a valid SPTE bit for NPT
KVM: x86: Do not block APIC write for non ICR registers
...
Diffstat (limited to 'arch/s390/kvm/pv.c')
-rw-r--r-- | arch/s390/kvm/pv.c | 269 |
1 files changed, 257 insertions, 12 deletions
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index cc7c9599f43e..7cb7799a0acb 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -7,13 +7,25 @@ */ #include <linux/kvm.h> #include <linux/kvm_host.h> +#include <linux/minmax.h> #include <linux/pagemap.h> #include <linux/sched/signal.h> #include <asm/gmap.h> #include <asm/uv.h> #include <asm/mman.h> +#include <linux/pagewalk.h> +#include <linux/sched/mm.h> +#include <linux/mmu_notifier.h> #include "kvm-s390.h" +static void kvm_s390_clear_pv_state(struct kvm *kvm) +{ + kvm->arch.pv.handle = 0; + kvm->arch.pv.guest_len = 0; + kvm->arch.pv.stor_base = 0; + kvm->arch.pv.stor_var = NULL; +} + int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc) { int cc; @@ -108,7 +120,7 @@ static void kvm_s390_pv_dealloc_vm(struct kvm *kvm) vfree(kvm->arch.pv.stor_var); free_pages(kvm->arch.pv.stor_base, get_order(uv_info.guest_base_stor_len)); - memset(&kvm->arch.pv, 0, sizeof(kvm->arch.pv)); + kvm_s390_clear_pv_state(kvm); } static int kvm_s390_pv_alloc_vm(struct kvm *kvm) @@ -152,21 +164,51 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) { int cc; - /* make all pages accessible before destroying the guest */ - s390_reset_acc(kvm->mm); - cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), UVC_CMD_DESTROY_SEC_CONF, rc, rrc); WRITE_ONCE(kvm->arch.gmap->guest_handle, 0); - atomic_set(&kvm->mm->context.is_protected, 0); + /* + * if the mm still has a mapping, make all its pages accessible + * before destroying the guest + */ + if (mmget_not_zero(kvm->mm)) { + s390_uv_destroy_range(kvm->mm, 0, TASK_SIZE); + mmput(kvm->mm); + } + + if (!cc) { + atomic_dec(&kvm->mm->context.protected_count); + kvm_s390_pv_dealloc_vm(kvm); + } else { + /* Intended memory leak on "impossible" error */ + s390_replace_asce(kvm->arch.gmap); + } KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM: rc %x rrc %x", *rc, *rrc); WARN_ONCE(cc, "protvirt destroy vm failed rc %x rrc %x", *rc, *rrc); - /* Inteded memory leak on "impossible" error */ - if (!cc) - kvm_s390_pv_dealloc_vm(kvm); + return cc ? -EIO : 0; } +static void kvm_s390_pv_mmu_notifier_release(struct mmu_notifier *subscription, + struct mm_struct *mm) +{ + struct kvm *kvm = container_of(subscription, struct kvm, arch.pv.mmu_notifier); + u16 dummy; + + /* + * No locking is needed since this is the last thread of the last user of this + * struct mm. + * When the struct kvm gets deinitialized, this notifier is also + * unregistered. This means that if this notifier runs, then the + * struct kvm is still valid. + */ + kvm_s390_cpus_from_pv(kvm, &dummy, &dummy); +} + +static const struct mmu_notifier_ops kvm_s390_pv_mmu_notifier_ops = { + .release = kvm_s390_pv_mmu_notifier_release, +}; + int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) { struct uv_cb_cgc uvcb = { @@ -197,14 +239,22 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc) /* Outputs */ kvm->arch.pv.handle = uvcb.guest_handle; + atomic_inc(&kvm->mm->context.protected_count); if (cc) { - if (uvcb.header.rc & UVC_RC_NEED_DESTROY) + if (uvcb.header.rc & UVC_RC_NEED_DESTROY) { kvm_s390_pv_deinit_vm(kvm, &dummy, &dummy); - else + } else { + atomic_dec(&kvm->mm->context.protected_count); kvm_s390_pv_dealloc_vm(kvm); + } return -EIO; } kvm->arch.gmap->guest_handle = uvcb.guest_handle; + /* Add the notifier only once. No races because we hold kvm->lock */ + if (kvm->arch.pv.mmu_notifier.ops != &kvm_s390_pv_mmu_notifier_ops) { + kvm->arch.pv.mmu_notifier.ops = &kvm_s390_pv_mmu_notifier_ops; + mmu_notifier_register(&kvm->arch.pv.mmu_notifier, kvm->mm); + } return 0; } @@ -224,8 +274,6 @@ int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, *rrc = uvcb.header.rrc; KVM_UV_EVENT(kvm, 3, "PROTVIRT VM SET PARMS: rc %x rrc %x", *rc, *rrc); - if (!cc) - atomic_set(&kvm->mm->context.is_protected, 1); return cc ? -EINVAL : 0; } @@ -298,3 +346,200 @@ int kvm_s390_pv_set_cpu_state(struct kvm_vcpu *vcpu, u8 state) return -EINVAL; return 0; } + +int kvm_s390_pv_dump_cpu(struct kvm_vcpu *vcpu, void *buff, u16 *rc, u16 *rrc) +{ + struct uv_cb_dump_cpu uvcb = { + .header.cmd = UVC_CMD_DUMP_CPU, + .header.len = sizeof(uvcb), + .cpu_handle = vcpu->arch.pv.handle, + .dump_area_origin = (u64)buff, + }; + int cc; + + cc = uv_call_sched(0, (u64)&uvcb); + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + return cc; +} + +/* Size of the cache for the storage state dump data. 1MB for now */ +#define DUMP_BUFF_LEN HPAGE_SIZE + +/** + * kvm_s390_pv_dump_stor_state + * + * @kvm: pointer to the guest's KVM struct + * @buff_user: Userspace pointer where we will write the results to + * @gaddr: Starting absolute guest address for which the storage state + * is requested. + * @buff_user_len: Length of the buff_user buffer + * @rc: Pointer to where the uvcb return code is stored + * @rrc: Pointer to where the uvcb return reason code is stored + * + * Stores buff_len bytes of tweak component values to buff_user + * starting with the 1MB block specified by the absolute guest address + * (gaddr). The gaddr pointer will be updated with the last address + * for which data was written when returning to userspace. buff_user + * might be written to even if an error rc is returned. For instance + * if we encounter a fault after writing the first page of data. + * + * Context: kvm->lock needs to be held + * + * Return: + * 0 on success + * -ENOMEM if allocating the cache fails + * -EINVAL if gaddr is not aligned to 1MB + * -EINVAL if buff_user_len is not aligned to uv_info.conf_dump_storage_state_len + * -EINVAL if the UV call fails, rc and rrc will be set in this case + * -EFAULT if copying the result to buff_user failed + */ +int kvm_s390_pv_dump_stor_state(struct kvm *kvm, void __user *buff_user, + u64 *gaddr, u64 buff_user_len, u16 *rc, u16 *rrc) +{ + struct uv_cb_dump_stor_state uvcb = { + .header.cmd = UVC_CMD_DUMP_CONF_STOR_STATE, + .header.len = sizeof(uvcb), + .config_handle = kvm->arch.pv.handle, + .gaddr = *gaddr, + .dump_area_origin = 0, + }; + const u64 increment_len = uv_info.conf_dump_storage_state_len; + size_t buff_kvm_size; + size_t size_done = 0; + u8 *buff_kvm = NULL; + int cc, ret; + + ret = -EINVAL; + /* UV call processes 1MB guest storage chunks at a time */ + if (!IS_ALIGNED(*gaddr, HPAGE_SIZE)) + goto out; + + /* + * We provide the storage state for 1MB chunks of guest + * storage. The buffer will need to be aligned to + * conf_dump_storage_state_len so we don't end on a partial + * chunk. + */ + if (!buff_user_len || + !IS_ALIGNED(buff_user_len, increment_len)) + goto out; + + /* + * Allocate a buffer from which we will later copy to the user + * process. We don't want userspace to dictate our buffer size + * so we limit it to DUMP_BUFF_LEN. + */ + ret = -ENOMEM; + buff_kvm_size = min_t(u64, buff_user_len, DUMP_BUFF_LEN); + buff_kvm = vzalloc(buff_kvm_size); + if (!buff_kvm) + goto out; + + ret = 0; + uvcb.dump_area_origin = (u64)buff_kvm; + /* We will loop until the user buffer is filled or an error occurs */ + do { + /* Get 1MB worth of guest storage state data */ + cc = uv_call_sched(0, (u64)&uvcb); + + /* All or nothing */ + if (cc) { + ret = -EINVAL; + break; + } + + size_done += increment_len; + uvcb.dump_area_origin += increment_len; + buff_user_len -= increment_len; + uvcb.gaddr += HPAGE_SIZE; + + /* KVM Buffer full, time to copy to the process */ + if (!buff_user_len || size_done == DUMP_BUFF_LEN) { + if (copy_to_user(buff_user, buff_kvm, size_done)) { + ret = -EFAULT; + break; + } + + buff_user += size_done; + size_done = 0; + uvcb.dump_area_origin = (u64)buff_kvm; + } + } while (buff_user_len); + + /* Report back where we ended dumping */ + *gaddr = uvcb.gaddr; + + /* Lets only log errors, we don't want to spam */ +out: + if (ret) + KVM_UV_EVENT(kvm, 3, + "PROTVIRT DUMP STORAGE STATE: addr %llx ret %d, uvcb rc %x rrc %x", + uvcb.gaddr, ret, uvcb.header.rc, uvcb.header.rrc); + *rc = uvcb.header.rc; + *rrc = uvcb.header.rrc; + vfree(buff_kvm); + + return ret; +} + +/** + * kvm_s390_pv_dump_complete + * + * @kvm: pointer to the guest's KVM struct + * @buff_user: Userspace pointer where we will write the results to + * @rc: Pointer to where the uvcb return code is stored + * @rrc: Pointer to where the uvcb return reason code is stored + * + * Completes the dumping operation and writes the completion data to + * user space. + * + * Context: kvm->lock needs to be held + * + * Return: + * 0 on success + * -ENOMEM if allocating the completion buffer fails + * -EINVAL if the UV call fails, rc and rrc will be set in this case + * -EFAULT if copying the result to buff_user failed + */ +int kvm_s390_pv_dump_complete(struct kvm *kvm, void __user *buff_user, + u16 *rc, u16 *rrc) +{ + struct uv_cb_dump_complete complete = { + .header.len = sizeof(complete), + .header.cmd = UVC_CMD_DUMP_COMPLETE, + .config_handle = kvm_s390_pv_get_handle(kvm), + }; + u64 *compl_data; + int ret; + + /* Allocate dump area */ + compl_data = vzalloc(uv_info.conf_dump_finalize_len); + if (!compl_data) + return -ENOMEM; + complete.dump_area_origin = (u64)compl_data; + + ret = uv_call_sched(0, (u64)&complete); + *rc = complete.header.rc; + *rrc = complete.header.rrc; + KVM_UV_EVENT(kvm, 3, "PROTVIRT DUMP COMPLETE: rc %x rrc %x", + complete.header.rc, complete.header.rrc); + + if (!ret) { + /* + * kvm_s390_pv_dealloc_vm() will also (mem)set + * this to false on a reboot or other destroy + * operation for this vm. + */ + kvm->arch.pv.dumping = false; + kvm_s390_vcpu_unblock_all(kvm); + ret = copy_to_user(buff_user, compl_data, uv_info.conf_dump_finalize_len); + if (ret) + ret = -EFAULT; + } + vfree(compl_data); + /* If the UVC returned an error, translate it to -EINVAL */ + if (ret > 0) + ret = -EINVAL; + return ret; +} |