diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-08-04 14:59:54 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-08-04 14:59:54 -0700 |
commit | 7c5c3a6177fa9646884114fc7f2e970b0bc50dc9 (patch) | |
tree | 956857522574ae7cb07d2227dc16e53d7e9e00e7 /arch/arm64/kvm/hyp/nvhe | |
parent | drm/amd/amdgpu: fix build failure due to implicit declaration (diff) | |
parent | selftests: kvm: set rax before vmcall (diff) | |
download | linux-dev-7c5c3a6177fa9646884114fc7f2e970b0bc50dc9.tar.xz linux-dev-7c5c3a6177fa9646884114fc7f2e970b0bc50dc9.zip |
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/arm64/kvm/hyp/nvhe')
-rw-r--r-- | arch/arm64/kvm/hyp/nvhe/Makefile | 14 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/nvhe/debug-sr.c | 8 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/nvhe/host.S | 9 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/nvhe/stacktrace.c | 160 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/nvhe/switch.c | 14 | ||||
-rw-r--r-- | arch/arm64/kvm/hyp/nvhe/sys_regs.c | 4 |
6 files changed, 184 insertions, 25 deletions
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile index f9fe4dc21b1f..ed5d222e2826 100644 --- a/arch/arm64/kvm/hyp/nvhe/Makefile +++ b/arch/arm64/kvm/hyp/nvhe/Makefile @@ -12,13 +12,13 @@ HOST_EXTRACFLAGS += -I$(objtree)/include lib-objs := clear_page.o copy_page.o memcpy.o memset.o lib-objs := $(addprefix ../../../lib/, $(lib-objs)) -obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \ +hyp-obj-y := timer-sr.o sysreg-sr.o debug-sr.o switch.o tlb.o hyp-init.o host.o \ hyp-main.o hyp-smp.o psci-relay.o early_alloc.o page_alloc.o \ - cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o -obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ + cache.o setup.o mm.o mem_protect.o sys_regs.o pkvm.o stacktrace.o +hyp-obj-y += ../vgic-v3-sr.o ../aarch32.o ../vgic-v2-cpuif-proxy.o ../entry.o \ ../fpsimd.o ../hyp-entry.o ../exception.o ../pgtable.o -obj-$(CONFIG_DEBUG_LIST) += list_debug.o -obj-y += $(lib-objs) +hyp-obj-$(CONFIG_DEBUG_LIST) += list_debug.o +hyp-obj-y += $(lib-objs) ## ## Build rules for compiling nVHE hyp code @@ -26,9 +26,9 @@ obj-y += $(lib-objs) ## file containing all nVHE hyp code and data. ## -hyp-obj := $(patsubst %.o,%.nvhe.o,$(obj-y)) +hyp-obj := $(patsubst %.o,%.nvhe.o,$(hyp-obj-y)) obj-y := kvm_nvhe.o -extra-y := $(hyp-obj) kvm_nvhe.tmp.o kvm_nvhe.rel.o hyp.lds hyp-reloc.S hyp-reloc.o +targets += $(hyp-obj) kvm_nvhe.tmp.o kvm_nvhe.rel.o hyp.lds hyp-reloc.S hyp-reloc.o # 1) Compile all source files to `.nvhe.o` object files. The file extension # avoids file name clashes for files shared with VHE. diff --git a/arch/arm64/kvm/hyp/nvhe/debug-sr.c b/arch/arm64/kvm/hyp/nvhe/debug-sr.c index df361d839902..e17455773b98 100644 --- a/arch/arm64/kvm/hyp/nvhe/debug-sr.c +++ b/arch/arm64/kvm/hyp/nvhe/debug-sr.c @@ -84,10 +84,10 @@ static void __debug_restore_trace(u64 trfcr_el1) void __debug_save_host_buffers_nvhe(struct kvm_vcpu *vcpu) { /* Disable and flush SPE data generation */ - if (vcpu->arch.flags & KVM_ARM64_DEBUG_STATE_SAVE_SPE) + if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_SPE)) __debug_save_spe(&vcpu->arch.host_debug_state.pmscr_el1); /* Disable and flush Self-Hosted Trace generation */ - if (vcpu->arch.flags & KVM_ARM64_DEBUG_STATE_SAVE_TRBE) + if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_TRBE)) __debug_save_trace(&vcpu->arch.host_debug_state.trfcr_el1); } @@ -98,9 +98,9 @@ void __debug_switch_to_guest(struct kvm_vcpu *vcpu) void __debug_restore_host_buffers_nvhe(struct kvm_vcpu *vcpu) { - if (vcpu->arch.flags & KVM_ARM64_DEBUG_STATE_SAVE_SPE) + if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_SPE)) __debug_restore_spe(vcpu->arch.host_debug_state.pmscr_el1); - if (vcpu->arch.flags & KVM_ARM64_DEBUG_STATE_SAVE_TRBE) + if (vcpu_get_flag(vcpu, DEBUG_STATE_SAVE_TRBE)) __debug_restore_trace(vcpu->arch.host_debug_state.trfcr_el1); } diff --git a/arch/arm64/kvm/hyp/nvhe/host.S b/arch/arm64/kvm/hyp/nvhe/host.S index ea6a397b64a6..b6c0188c4b35 100644 --- a/arch/arm64/kvm/hyp/nvhe/host.S +++ b/arch/arm64/kvm/hyp/nvhe/host.S @@ -177,13 +177,8 @@ SYM_FUNC_END(__host_hvc) b hyp_panic .L__hyp_sp_overflow\@: - /* - * Reset SP to the top of the stack, to allow handling the hyp_panic. - * This corrupts the stack but is ok, since we won't be attempting - * any unwinding here. - */ - ldr_this_cpu x0, kvm_init_params + NVHE_INIT_STACK_HYP_VA, x1 - mov sp, x0 + /* Switch to the overflow stack */ + adr_this_cpu sp, overflow_stack + OVERFLOW_STACK_SIZE, x0 b hyp_panic_bad_stack ASM_BUG() diff --git a/arch/arm64/kvm/hyp/nvhe/stacktrace.c b/arch/arm64/kvm/hyp/nvhe/stacktrace.c new file mode 100644 index 000000000000..58f645ad66bc --- /dev/null +++ b/arch/arm64/kvm/hyp/nvhe/stacktrace.c @@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * KVM nVHE hypervisor stack tracing support. + * + * Copyright (C) 2022 Google LLC + */ +#include <asm/kvm_asm.h> +#include <asm/kvm_hyp.h> +#include <asm/memory.h> +#include <asm/percpu.h> + +DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack) + __aligned(16); + +DEFINE_PER_CPU(struct kvm_nvhe_stacktrace_info, kvm_stacktrace_info); + +/* + * hyp_prepare_backtrace - Prepare non-protected nVHE backtrace. + * + * @fp : frame pointer at which to start the unwinding. + * @pc : program counter at which to start the unwinding. + * + * Save the information needed by the host to unwind the non-protected + * nVHE hypervisor stack in EL1. + */ +static void hyp_prepare_backtrace(unsigned long fp, unsigned long pc) +{ + struct kvm_nvhe_stacktrace_info *stacktrace_info = this_cpu_ptr(&kvm_stacktrace_info); + struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params); + + stacktrace_info->stack_base = (unsigned long)(params->stack_hyp_va - PAGE_SIZE); + stacktrace_info->overflow_stack_base = (unsigned long)this_cpu_ptr(overflow_stack); + stacktrace_info->fp = fp; + stacktrace_info->pc = pc; +} + +#ifdef CONFIG_PROTECTED_NVHE_STACKTRACE +#include <asm/stacktrace/nvhe.h> + +DEFINE_PER_CPU(unsigned long [NVHE_STACKTRACE_SIZE/sizeof(long)], pkvm_stacktrace); + +static bool on_overflow_stack(unsigned long sp, unsigned long size, + struct stack_info *info) +{ + unsigned long low = (unsigned long)this_cpu_ptr(overflow_stack); + unsigned long high = low + OVERFLOW_STACK_SIZE; + + return on_stack(sp, size, low, high, STACK_TYPE_OVERFLOW, info); +} + +static bool on_hyp_stack(unsigned long sp, unsigned long size, + struct stack_info *info) +{ + struct kvm_nvhe_init_params *params = this_cpu_ptr(&kvm_init_params); + unsigned long high = params->stack_hyp_va; + unsigned long low = high - PAGE_SIZE; + + return on_stack(sp, size, low, high, STACK_TYPE_HYP, info); +} + +static bool on_accessible_stack(const struct task_struct *tsk, + unsigned long sp, unsigned long size, + struct stack_info *info) +{ + if (info) + info->type = STACK_TYPE_UNKNOWN; + + return (on_overflow_stack(sp, size, info) || + on_hyp_stack(sp, size, info)); +} + +static int unwind_next(struct unwind_state *state) +{ + struct stack_info info; + + return unwind_next_common(state, &info, on_accessible_stack, NULL); +} + +static void notrace unwind(struct unwind_state *state, + stack_trace_consume_fn consume_entry, + void *cookie) +{ + while (1) { + int ret; + + if (!consume_entry(cookie, state->pc)) + break; + ret = unwind_next(state); + if (ret < 0) + break; + } +} + +/* + * pkvm_save_backtrace_entry - Saves a protected nVHE HYP stacktrace entry + * + * @arg : index of the entry in the stacktrace buffer + * @where : the program counter corresponding to the stack frame + * + * Save the return address of a stack frame to the shared stacktrace buffer. + * The host can access this shared buffer from EL1 to dump the backtrace. + */ +static bool pkvm_save_backtrace_entry(void *arg, unsigned long where) +{ + unsigned long *stacktrace = this_cpu_ptr(pkvm_stacktrace); + int *idx = (int *)arg; + + /* + * Need 2 free slots: 1 for current entry and 1 for the + * delimiter. + */ + if (*idx > ARRAY_SIZE(pkvm_stacktrace) - 2) + return false; + + stacktrace[*idx] = where; + stacktrace[++*idx] = 0UL; + + return true; +} + +/* + * pkvm_save_backtrace - Saves the protected nVHE HYP stacktrace + * + * @fp : frame pointer at which to start the unwinding. + * @pc : program counter at which to start the unwinding. + * + * Save the unwinded stack addresses to the shared stacktrace buffer. + * The host can access this shared buffer from EL1 to dump the backtrace. + */ +static void pkvm_save_backtrace(unsigned long fp, unsigned long pc) +{ + struct unwind_state state; + int idx = 0; + + kvm_nvhe_unwind_init(&state, fp, pc); + + unwind(&state, pkvm_save_backtrace_entry, &idx); +} +#else /* !CONFIG_PROTECTED_NVHE_STACKTRACE */ +static void pkvm_save_backtrace(unsigned long fp, unsigned long pc) +{ +} +#endif /* CONFIG_PROTECTED_NVHE_STACKTRACE */ + +/* + * kvm_nvhe_prepare_backtrace - prepare to dump the nVHE backtrace + * + * @fp : frame pointer at which to start the unwinding. + * @pc : program counter at which to start the unwinding. + * + * Saves the information needed by the host to dump the nVHE hypervisor + * backtrace. + */ +void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc) +{ + if (is_protected_kvm_enabled()) + pkvm_save_backtrace(fp, pc); + else + hyp_prepare_backtrace(fp, pc); +} diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index 6db801db8f27..9f6385702061 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -34,6 +34,8 @@ DEFINE_PER_CPU(struct kvm_host_data, kvm_host_data); DEFINE_PER_CPU(struct kvm_cpu_context, kvm_hyp_ctxt); DEFINE_PER_CPU(unsigned long, kvm_hyp_vector); +extern void kvm_nvhe_prepare_backtrace(unsigned long fp, unsigned long pc); + static void __activate_traps(struct kvm_vcpu *vcpu) { u64 val; @@ -43,7 +45,7 @@ static void __activate_traps(struct kvm_vcpu *vcpu) val = vcpu->arch.cptr_el2; val |= CPTR_EL2_TTA | CPTR_EL2_TAM; - if (!update_fp_enabled(vcpu)) { + if (!guest_owns_fp_regs(vcpu)) { val |= CPTR_EL2_TFP | CPTR_EL2_TZ; __activate_traps_fpsimd32(vcpu); } @@ -123,7 +125,7 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) } cptr = CPTR_EL2_DEFAULT; - if (vcpu_has_sve(vcpu) && (vcpu->arch.flags & KVM_ARM64_FP_ENABLED)) + if (vcpu_has_sve(vcpu) && (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED)) cptr |= CPTR_EL2_TZ; if (cpus_have_final_cap(ARM64_SME)) cptr &= ~CPTR_EL2_TSM; @@ -335,7 +337,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) __sysreg_restore_state_nvhe(host_ctxt); - if (vcpu->arch.flags & KVM_ARM64_FP_ENABLED) + if (vcpu->arch.fp_state == FP_STATE_GUEST_OWNED) __fpsimd_save_fpexc32(vcpu); __debug_switch_to_host(vcpu); @@ -375,6 +377,10 @@ asmlinkage void __noreturn hyp_panic(void) __sysreg_restore_state_nvhe(host_ctxt); } + /* Prepare to dump kvm nvhe hyp stacktrace */ + kvm_nvhe_prepare_backtrace((unsigned long)__builtin_frame_address(0), + _THIS_IP_); + __hyp_do_panic(host_ctxt, spsr, elr, par); unreachable(); } @@ -386,5 +392,5 @@ asmlinkage void __noreturn hyp_panic_bad_stack(void) asmlinkage void kvm_unexpected_el2_exception(void) { - return __kvm_unexpected_el2_exception(); + __kvm_unexpected_el2_exception(); } diff --git a/arch/arm64/kvm/hyp/nvhe/sys_regs.c b/arch/arm64/kvm/hyp/nvhe/sys_regs.c index 6b94c3e6ff26..e20fa4475dac 100644 --- a/arch/arm64/kvm/hyp/nvhe/sys_regs.c +++ b/arch/arm64/kvm/hyp/nvhe/sys_regs.c @@ -38,9 +38,7 @@ static void inject_undef64(struct kvm_vcpu *vcpu) *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); *vcpu_cpsr(vcpu) = read_sysreg_el2(SYS_SPSR); - vcpu->arch.flags |= (KVM_ARM64_EXCEPT_AA64_EL1 | - KVM_ARM64_EXCEPT_AA64_ELx_SYNC | - KVM_ARM64_PENDING_EXCEPTION); + kvm_pend_exception(vcpu, EXCEPT_AA64_EL1_SYNC); __kvm_adjust_pc(vcpu); |