diff options
Diffstat (limited to 'arch/x86')
51 files changed, 630 insertions, 326 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index d9830e7e1060..6ce906815bb2 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1256,7 +1256,8 @@ config TOSHIBA config I8K tristate "Dell i8k legacy laptop support" - select HWMON + depends on HWMON + depends on PROC_FS select SENSORS_DELL_SMM help This option enables legacy /proc/i8k userspace interface in hwmon @@ -1518,6 +1519,7 @@ config AMD_MEM_ENCRYPT select ARCH_HAS_FORCE_DMA_UNENCRYPTED select INSTRUCTION_DECODER select ARCH_HAS_RESTRICTED_VIRTIO_MEMORY_ACCESS + select ARCH_HAS_CC_PLATFORM help Say yes to enable support for the encryption of system memory. This requires an AMD processor that supports Secure Memory diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 0fc961bef299..e09f4672dd38 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -866,7 +866,7 @@ static int xts_crypt(struct skcipher_request *req, bool encrypt) req = &subreq; err = skcipher_walk_virt(&walk, req, false); - if (err) + if (!walk.nbytes) return err; } else { tail = 0; diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 1b40b9297083..fd2ee9408e91 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -226,7 +226,8 @@ bool emulate_vsyscall(unsigned long error_code, if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) { warn_bad_vsyscall(KERN_DEBUG, regs, "seccomp tried to change syscall nr or ip"); - do_exit(SIGSYS); + force_exit_sig(SIGSYS); + return true; } regs->orig_ax = -1; if (tmp) diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 9a044438072b..c7f1cc433a6a 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -243,7 +243,8 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = { static struct event_constraint intel_icl_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ - FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* old INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x0100, 0), /* INST_RETIRED.PREC_DIST */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */ @@ -288,7 +289,7 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = { static struct event_constraint intel_spr_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ - FIXED_EVENT_CONSTRAINT(0x01c0, 0), /* INST_RETIRED.PREC_DIST */ + FIXED_EVENT_CONSTRAINT(0x0100, 0), /* INST_RETIRED.PREC_DIST */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */ @@ -2998,8 +2999,10 @@ intel_vlbr_constraints(struct perf_event *event) { struct event_constraint *c = &vlbr_constraint; - if (unlikely(constraint_match(c, event->hw.config))) + if (unlikely(constraint_match(c, event->hw.config))) { + event->hw.flags |= c->flags; return c; + } return NULL; } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8647713276a7..4dbb55a43dad 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -923,7 +923,8 @@ struct event_constraint intel_skl_pebs_event_constraints[] = { }; struct event_constraint intel_icl_pebs_event_constraints[] = { - INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x100000000ULL), /* old INST_RETIRED.PREC_DIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x0100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ @@ -943,7 +944,7 @@ struct event_constraint intel_icl_pebs_event_constraints[] = { }; struct event_constraint intel_spr_pebs_event_constraints[] = { - INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), + INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe), diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h index 7280c8a3c831..6d735611c281 100644 --- a/arch/x86/events/intel/uncore_discovery.h +++ b/arch/x86/events/intel/uncore_discovery.h @@ -30,7 +30,7 @@ #define uncore_discovery_invalid_unit(unit) \ - (!unit.table1 || !unit.ctl || !unit.table3 || \ + (!unit.table1 || !unit.ctl || \ unit.table1 == -1ULL || unit.ctl == -1ULL || \ unit.table3 == -1ULL) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 5ddc0f30db6f..3660f698fb2a 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -452,7 +452,7 @@ #define ICX_M3UPI_PCI_PMON_BOX_CTL 0xa0 /* ICX IMC */ -#define ICX_NUMBER_IMC_CHN 2 +#define ICX_NUMBER_IMC_CHN 3 #define ICX_IMC_MEM_STRIDE 0x4 /* SPR */ @@ -3608,6 +3608,9 @@ static int skx_cha_hw_config(struct intel_uncore_box *box, struct perf_event *ev struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; struct extra_reg *er; int idx = 0; + /* Any of the CHA events may be filtered by Thread/Core-ID.*/ + if (event->hw.config & SNBEP_CBO_PMON_CTL_TID_EN) + idx = SKX_CHA_MSR_PMON_BOX_FILTER_TID; for (er = skx_uncore_cha_extra_regs; er->msr; er++) { if (er->event != (event->hw.config & er->config_mask)) @@ -3675,6 +3678,7 @@ static struct event_constraint skx_uncore_iio_constraints[] = { UNCORE_EVENT_CONSTRAINT(0xc0, 0xc), UNCORE_EVENT_CONSTRAINT(0xc5, 0xc), UNCORE_EVENT_CONSTRAINT(0xd4, 0xc), + UNCORE_EVENT_CONSTRAINT(0xd5, 0xc), EVENT_CONSTRAINT_END }; @@ -4525,6 +4529,13 @@ static void snr_iio_cleanup_mapping(struct intel_uncore_type *type) pmu_iio_cleanup_mapping(type, &snr_iio_mapping_group); } +static struct event_constraint snr_uncore_iio_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x83, 0x3), + UNCORE_EVENT_CONSTRAINT(0xc0, 0xc), + UNCORE_EVENT_CONSTRAINT(0xd5, 0xc), + EVENT_CONSTRAINT_END +}; + static struct intel_uncore_type snr_uncore_iio = { .name = "iio", .num_counters = 4, @@ -4536,6 +4547,7 @@ static struct intel_uncore_type snr_uncore_iio = { .event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT, .box_ctl = SNR_IIO_MSR_PMON_BOX_CTL, .msr_offset = SNR_IIO_MSR_OFFSET, + .constraints = snr_uncore_iio_constraints, .ops = &ivbep_uncore_msr_ops, .format_group = &snr_uncore_iio_format_group, .attr_update = snr_iio_attr_update, @@ -5076,8 +5088,10 @@ static struct event_constraint icx_uncore_iio_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x02, 0x3), UNCORE_EVENT_CONSTRAINT(0x03, 0x3), UNCORE_EVENT_CONSTRAINT(0x83, 0x3), + UNCORE_EVENT_CONSTRAINT(0x88, 0xc), UNCORE_EVENT_CONSTRAINT(0xc0, 0xc), UNCORE_EVENT_CONSTRAINT(0xc5, 0xc), + UNCORE_EVENT_CONSTRAINT(0xd5, 0xc), EVENT_CONSTRAINT_END }; @@ -5463,7 +5477,7 @@ static struct intel_uncore_ops icx_uncore_mmio_ops = { static struct intel_uncore_type icx_uncore_imc = { .name = "imc", .num_counters = 4, - .num_boxes = 8, + .num_boxes = 12, .perf_ctr_bits = 48, .fixed_ctr_bits = 48, .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, @@ -5647,6 +5661,7 @@ static struct intel_uncore_type spr_uncore_chabox = { .event_mask = SPR_CHA_PMON_EVENT_MASK, .event_mask_ext = SPR_RAW_EVENT_MASK_EXT, .num_shared_regs = 1, + .constraints = skx_uncore_chabox_constraints, .ops = &spr_uncore_chabox_ops, .format_group = &spr_uncore_chabox_format_group, .attr_update = uncore_alias_groups, @@ -5658,6 +5673,7 @@ static struct intel_uncore_type spr_uncore_iio = { .event_mask_ext = SNR_IIO_PMON_RAW_EVENT_MASK_EXT, .format_group = &snr_uncore_iio_format_group, .attr_update = uncore_alias_groups, + .constraints = icx_uncore_iio_constraints, }; static struct attribute *spr_uncore_raw_formats_attr[] = { @@ -5686,9 +5702,16 @@ static struct intel_uncore_type spr_uncore_irp = { }; +static struct event_constraint spr_uncore_m2pcie_constraints[] = { + UNCORE_EVENT_CONSTRAINT(0x14, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + EVENT_CONSTRAINT_END +}; + static struct intel_uncore_type spr_uncore_m2pcie = { SPR_UNCORE_COMMON_FORMAT(), .name = "m2pcie", + .constraints = spr_uncore_m2pcie_constraints, }; static struct intel_uncore_type spr_uncore_pcu = { @@ -5765,6 +5788,7 @@ static struct intel_uncore_type spr_uncore_upi = { static struct intel_uncore_type spr_uncore_m3upi = { SPR_UNCORE_PCI_COMMON_FORMAT(), .name = "m3upi", + .constraints = icx_uncore_m3upi_constraints, }; static struct intel_uncore_type spr_uncore_mdf = { diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 708a2712a516..d20eef3d452a 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -139,7 +139,6 @@ void set_hv_tscchange_cb(void (*cb)(void)) struct hv_reenlightenment_control re_ctrl = { .vector = HYPERV_REENLIGHTENMENT_VECTOR, .enabled = 1, - .target_vp = hv_vp_index[smp_processor_id()] }; struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1}; @@ -148,13 +147,20 @@ void set_hv_tscchange_cb(void (*cb)(void)) return; } + if (!hv_vp_index) + return; + hv_reenlightenment_cb = cb; /* Make sure callback is registered before we write to MSRs */ wmb(); + re_ctrl.target_vp = hv_vp_index[get_cpu()]; + wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl)); wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl)); + + put_cpu(); } EXPORT_SYMBOL_GPL(set_hv_tscchange_cb); diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h index 3d52b094850a..dd5ea1bdf04c 100644 --- a/arch/x86/include/asm/cpu_entry_area.h +++ b/arch/x86/include/asm/cpu_entry_area.h @@ -10,6 +10,12 @@ #ifdef CONFIG_X86_64 +#ifdef CONFIG_AMD_MEM_ENCRYPT +#define VC_EXCEPTION_STKSZ EXCEPTION_STKSZ +#else +#define VC_EXCEPTION_STKSZ 0 +#endif + /* Macro to enforce the same ordering and stack sizes */ #define ESTACKS_MEMBERS(guardsize, optional_stack_size) \ char DF_stack_guard[guardsize]; \ @@ -28,7 +34,7 @@ /* The exception stacks' physical storage. No guard pages required */ struct exception_stacks { - ESTACKS_MEMBERS(0, 0) + ESTACKS_MEMBERS(0, VC_EXCEPTION_STKSZ) }; /* The effective cpu entry area mapping with guard pages. */ diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h index 91d7182ad2d6..4ec3613551e3 100644 --- a/arch/x86/include/asm/insn-eval.h +++ b/arch/x86/include/asm/insn-eval.h @@ -21,6 +21,7 @@ int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs); int insn_get_modrm_reg_off(struct insn *insn, struct pt_regs *regs); unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx); int insn_get_code_seg_params(struct pt_regs *regs); +int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip); int insn_fetch_from_user(struct pt_regs *regs, unsigned char buf[MAX_INSN_SIZE]); int insn_fetch_from_user_inatomic(struct pt_regs *regs, diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 562854c60808..8d55bd11848c 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -77,11 +77,11 @@ * Function calls can clobber anything except the callee-saved * registers. Tell the compiler. */ -#define call_on_irqstack(func, asm_call, argconstr...) \ +#define call_on_stack(stack, func, asm_call, argconstr...) \ { \ register void *tos asm("r11"); \ \ - tos = ((void *)__this_cpu_read(hardirq_stack_ptr)); \ + tos = ((void *)(stack)); \ \ asm_inline volatile( \ "movq %%rsp, (%[tos]) \n" \ @@ -98,6 +98,25 @@ ); \ } +#define ASM_CALL_ARG0 \ + "call %P[__func] \n" + +#define ASM_CALL_ARG1 \ + "movq %[arg1], %%rdi \n" \ + ASM_CALL_ARG0 + +#define ASM_CALL_ARG2 \ + "movq %[arg2], %%rsi \n" \ + ASM_CALL_ARG1 + +#define ASM_CALL_ARG3 \ + "movq %[arg3], %%rdx \n" \ + ASM_CALL_ARG2 + +#define call_on_irqstack(func, asm_call, argconstr...) \ + call_on_stack(__this_cpu_read(hardirq_stack_ptr), \ + func, asm_call, argconstr) + /* Macros to assert type correctness for run_*_on_irqstack macros */ #define assert_function_type(func, proto) \ static_assert(__builtin_types_compatible_p(typeof(&func), proto)) @@ -147,8 +166,7 @@ */ #define ASM_CALL_SYSVEC \ "call irq_enter_rcu \n" \ - "movq %[arg1], %%rdi \n" \ - "call %P[__func] \n" \ + ASM_CALL_ARG1 \ "call irq_exit_rcu \n" #define SYSVEC_CONSTRAINTS , [arg1] "r" (regs) @@ -168,12 +186,10 @@ */ #define ASM_CALL_IRQ \ "call irq_enter_rcu \n" \ - "movq %[arg1], %%rdi \n" \ - "movl %[arg2], %%esi \n" \ - "call %P[__func] \n" \ + ASM_CALL_ARG2 \ "call irq_exit_rcu \n" -#define IRQ_CONSTRAINTS , [arg1] "r" (regs), [arg2] "r" (vector) +#define IRQ_CONSTRAINTS , [arg1] "r" (regs), [arg2] "r" ((unsigned long)vector) #define run_irq_on_irqstack_cond(func, regs, vector) \ { \ @@ -185,9 +201,6 @@ IRQ_CONSTRAINTS, regs, vector); \ } -#define ASM_CALL_SOFTIRQ \ - "call %P[__func] \n" - /* * Macro to invoke __do_softirq on the irq stack. This is only called from * task context when bottom halves are about to be reenabled and soft @@ -197,7 +210,7 @@ #define do_softirq_own_stack() \ { \ __this_cpu_write(hardirq_stack_inuse, true); \ - call_on_irqstack(__do_softirq, ASM_CALL_SOFTIRQ); \ + call_on_irqstack(__do_softirq, ASM_CALL_ARG0); \ __this_cpu_write(hardirq_stack_inuse, false); \ } diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 13f64654dfff..fa24fd4d138d 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -364,6 +364,7 @@ union kvm_mmu_extended_role { unsigned int cr4_smap:1; unsigned int cr4_smep:1; unsigned int cr4_la57:1; + unsigned int efer_lma:1; }; }; @@ -751,7 +752,7 @@ struct kvm_vcpu_arch { u8 preempted; u64 msr_val; u64 last_steal; - struct gfn_to_pfn_cache cache; + struct gfn_to_hva_cache cache; } st; u64 l1_tsc_offset; diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 9c80c68d75b5..3fb9f5ebefa4 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -13,6 +13,7 @@ #ifndef __ASSEMBLY__ #include <linux/init.h> +#include <linux/cc_platform.h> #include <asm/bootparam.h> diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index a8d4ad856568..e9e2c3ba5923 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -15,7 +15,7 @@ #define THREAD_SIZE_ORDER (2 + KASAN_STACK_ORDER) #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) -#define EXCEPTION_STACK_ORDER (0 + KASAN_STACK_ORDER) +#define EXCEPTION_STACK_ORDER (1 + KASAN_STACK_ORDER) #define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER) #define IRQ_STACK_ORDER (2 + KASAN_STACK_ORDER) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 9ad2acaaae9b..577f342dbfb2 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -518,6 +518,7 @@ struct thread_struct { */ unsigned long iopl_emul; + unsigned int iopl_warn:1; unsigned int sig_on_uaccess_err:1; /* diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index f248eb2ac2d4..3881b5333eb8 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -38,6 +38,16 @@ int get_stack_info(unsigned long *stack, struct task_struct *task, bool get_stack_info_noinstr(unsigned long *stack, struct task_struct *task, struct stack_info *info); +static __always_inline +bool get_stack_guard_info(unsigned long *stack, struct stack_info *info) +{ + /* make sure it's not in the stack proper */ + if (get_stack_info_noinstr(stack, current, info)) + return false; + /* but if it is in the page below it, we hit a guard */ + return get_stack_info_noinstr((void *)stack + PAGE_SIZE, current, info); +} + const char *stack_type_name(enum stack_type type); static inline bool on_stack(struct stack_info *info, void *addr, size_t len) diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 7f7200021bd1..6221be7cafc3 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -40,9 +40,9 @@ void math_emulate(struct math_emu_info *); bool fault_in_kernel_space(unsigned long address); #ifdef CONFIG_VMAP_STACK -void __noreturn handle_stack_overflow(const char *message, - struct pt_regs *regs, - unsigned long fault_address); +void __noreturn handle_stack_overflow(struct pt_regs *regs, + unsigned long fault_address, + struct stack_info *info); #endif #endif /* _ASM_X86_TRAPS_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 8f4e8fa6ed75..2ff3e600f426 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -21,6 +21,7 @@ CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg CFLAGS_REMOVE_sev.o = -pg +CFLAGS_REMOVE_cc_platform.o = -pg endif KASAN_SANITIZE_head$(BITS).o := n @@ -29,6 +30,7 @@ KASAN_SANITIZE_dumpstack_$(BITS).o := n KASAN_SANITIZE_stacktrace.o := n KASAN_SANITIZE_paravirt.o := n KASAN_SANITIZE_sev.o := n +KASAN_SANITIZE_cc_platform.o := n # With some compiler versions the generated code results in boot hangs, caused # by several compilation units. To be safe, disable all instrumentation. @@ -47,6 +49,7 @@ endif KCOV_INSTRUMENT := n CFLAGS_head$(BITS).o += -fno-stack-protector +CFLAGS_cc_platform.o += -fno-stack-protector CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace @@ -147,6 +150,9 @@ obj-$(CONFIG_UNWINDER_FRAME_POINTER) += unwind_frame.o obj-$(CONFIG_UNWINDER_GUESS) += unwind_guess.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o + +obj-$(CONFIG_ARCH_HAS_CC_PLATFORM) += cc_platform.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/cc_platform.c b/arch/x86/kernel/cc_platform.c new file mode 100644 index 000000000000..03bb2f343ddb --- /dev/null +++ b/arch/x86/kernel/cc_platform.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Confidential Computing Platform Capability checks + * + * Copyright (C) 2021 Advanced Micro Devices, Inc. + * + * Author: Tom Lendacky <thomas.lendacky@amd.com> + */ + +#include <linux/export.h> +#include <linux/cc_platform.h> +#include <linux/mem_encrypt.h> + +#include <asm/processor.h> + +static bool __maybe_unused intel_cc_platform_has(enum cc_attr attr) +{ +#ifdef CONFIG_INTEL_TDX_GUEST + return false; +#else + return false; +#endif +} + +/* + * SME and SEV are very similar but they are not the same, so there are + * times that the kernel will need to distinguish between SME and SEV. The + * cc_platform_has() function is used for this. When a distinction isn't + * needed, the CC_ATTR_MEM_ENCRYPT attribute can be used. + * + * The trampoline code is a good example for this requirement. Before + * paging is activated, SME will access all memory as decrypted, but SEV + * will access all memory as encrypted. So, when APs are being brought + * up under SME the trampoline area cannot be encrypted, whereas under SEV + * the trampoline area must be encrypted. + */ +static bool amd_cc_platform_has(enum cc_attr attr) +{ +#ifdef CONFIG_AMD_MEM_ENCRYPT + switch (attr) { + case CC_ATTR_MEM_ENCRYPT: + return sme_me_mask; + + case CC_ATTR_HOST_MEM_ENCRYPT: + return sme_me_mask && !(sev_status & MSR_AMD64_SEV_ENABLED); + + case CC_ATTR_GUEST_MEM_ENCRYPT: + return sev_status & MSR_AMD64_SEV_ENABLED; + + case CC_ATTR_GUEST_STATE_ENCRYPT: + return sev_status & MSR_AMD64_SEV_ES_ENABLED; + + default: + return false; + } +#else + return false; +#endif +} + + +bool cc_platform_has(enum cc_attr attr) +{ + if (sme_me_mask) + return amd_cc_platform_has(attr); + + return false; +} +EXPORT_SYMBOL_GPL(cc_platform_has); diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 2131af9f2fa2..4edb6f0f628c 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -989,6 +989,8 @@ static void init_amd(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_IRPERF) && !cpu_has_amd_erratum(c, amd_erratum_1054)) msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); + + check_null_seg_clears_base(c); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b3410f1ac217..58b1416c05da 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1396,9 +1396,8 @@ void __init early_cpu_init(void) early_identify_cpu(&boot_cpu_data); } -static void detect_null_seg_behavior(struct cpuinfo_x86 *c) +static bool detect_null_seg_behavior(void) { -#ifdef CONFIG_X86_64 /* * Empirically, writing zero to a segment selector on AMD does * not clear the base, whereas writing zero to a segment @@ -1419,10 +1418,43 @@ static void detect_null_seg_behavior(struct cpuinfo_x86 *c) wrmsrl(MSR_FS_BASE, 1); loadsegment(fs, 0); rdmsrl(MSR_FS_BASE, tmp); - if (tmp != 0) - set_cpu_bug(c, X86_BUG_NULL_SEG); wrmsrl(MSR_FS_BASE, old_base); -#endif + return tmp == 0; +} + +void check_null_seg_clears_base(struct cpuinfo_x86 *c) +{ + /* BUG_NULL_SEG is only relevant with 64bit userspace */ + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + /* Zen3 CPUs advertise Null Selector Clears Base in CPUID. */ + if (c->extended_cpuid_level >= 0x80000021 && + cpuid_eax(0x80000021) & BIT(6)) + return; + + /* + * CPUID bit above wasn't set. If this kernel is still running + * as a HV guest, then the HV has decided not to advertize + * that CPUID bit for whatever reason. For example, one + * member of the migration pool might be vulnerable. Which + * means, the bug is present: set the BUG flag and return. + */ + if (cpu_has(c, X86_FEATURE_HYPERVISOR)) { + set_cpu_bug(c, X86_BUG_NULL_SEG); + return; + } + + /* + * Zen2 CPUs also have this behaviour, but no CPUID bit. + * 0x18 is the respective family for Hygon. + */ + if ((c->x86 == 0x17 || c->x86 == 0x18) && + detect_null_seg_behavior()) + return; + + /* All the remaining ones are affected */ + set_cpu_bug(c, X86_BUG_NULL_SEG); } static void generic_identify(struct cpuinfo_x86 *c) @@ -1458,8 +1490,6 @@ static void generic_identify(struct cpuinfo_x86 *c) get_model_name(c); /* Default name */ - detect_null_seg_behavior(c); - /* * ESPFIX is a strange bug. All real CPUs have it. Paravirt * systems that run Linux at CPL > 0 may or may not have the diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 95521302630d..ee6f23f7587d 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -75,6 +75,7 @@ extern int detect_extended_topology_early(struct cpuinfo_x86 *c); extern int detect_extended_topology(struct cpuinfo_x86 *c); extern int detect_ht_early(struct cpuinfo_x86 *c); extern void detect_ht(struct cpuinfo_x86 *c); +extern void check_null_seg_clears_base(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index 6d50136f7ab9..3fcdda4c1e11 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -335,6 +335,8 @@ static void init_hygon(struct cpuinfo_x86 *c) /* Hygon CPUs don't reset SS attributes on SYSRET, Xen does. */ if (!cpu_has(c, X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); + + check_null_seg_clears_base(c); } static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index acfd5d9f93c6..bb9a46a804bf 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -547,12 +547,13 @@ bool intel_filter_mce(struct mce *m) { struct cpuinfo_x86 *c = &boot_cpu_data; - /* MCE errata HSD131, HSM142, HSW131, BDM48, and HSM142 */ + /* MCE errata HSD131, HSM142, HSW131, BDM48, HSM142 and SKX37 */ if ((c->x86 == 6) && ((c->x86_model == INTEL_FAM6_HASWELL) || (c->x86_model == INTEL_FAM6_HASWELL_L) || (c->x86_model == INTEL_FAM6_BROADWELL) || - (c->x86_model == INTEL_FAM6_HASWELL_G)) && + (c->x86_model == INTEL_FAM6_HASWELL_G) || + (c->x86_model == INTEL_FAM6_SKYLAKE_X)) && (m->bank == 0) && ((m->status & 0xa0000000ffffffff) == 0x80000000000f0005)) return true; diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 63d3de02bbcc..8471a8b9b48e 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -28,8 +28,7 @@ static DECLARE_WAIT_QUEUE_HEAD(ksgxd_waitq); static LIST_HEAD(sgx_active_page_list); static DEFINE_SPINLOCK(sgx_reclaimer_lock); -/* The free page list lock protected variables prepend the lock. */ -static unsigned long sgx_nr_free_pages; +static atomic_long_t sgx_nr_free_pages = ATOMIC_LONG_INIT(0); /* Nodes with one or more EPC sections. */ static nodemask_t sgx_numa_mask; @@ -403,14 +402,15 @@ skip: spin_lock(&node->lock); list_add_tail(&epc_page->list, &node->free_page_list); - sgx_nr_free_pages++; spin_unlock(&node->lock); + atomic_long_inc(&sgx_nr_free_pages); } } static bool sgx_should_reclaim(unsigned long watermark) { - return sgx_nr_free_pages < watermark && !list_empty(&sgx_active_page_list); + return atomic_long_read(&sgx_nr_free_pages) < watermark && + !list_empty(&sgx_active_page_list); } static int ksgxd(void *p) @@ -471,9 +471,9 @@ static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid) page = list_first_entry(&node->free_page_list, struct sgx_epc_page, list); list_del_init(&page->list); - sgx_nr_free_pages--; spin_unlock(&node->lock); + atomic_long_dec(&sgx_nr_free_pages); return page; } @@ -625,9 +625,9 @@ void sgx_free_epc_page(struct sgx_epc_page *page) spin_lock(&node->lock); list_add_tail(&page->list, &node->free_page_list); - sgx_nr_free_pages++; spin_unlock(&node->lock); + atomic_long_inc(&sgx_nr_free_pages); } static bool __init sgx_setup_epc_section(u64 phys_addr, u64 size, diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 5601b95944fa..6c5defd6569a 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -32,9 +32,15 @@ const char *stack_type_name(enum stack_type type) { BUILD_BUG_ON(N_EXCEPTION_STACKS != 6); + if (type == STACK_TYPE_TASK) + return "TASK"; + if (type == STACK_TYPE_IRQ) return "IRQ"; + if (type == STACK_TYPE_SOFTIRQ) + return "SOFTIRQ"; + if (type == STACK_TYPE_ENTRY) { /* * On 64-bit, we have a generic entry stack that we diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index e28f6a5d14f1..766ffe3ba313 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -291,8 +291,10 @@ void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)) { if (handler) kvm_posted_intr_wakeup_handler = handler; - else + else { kvm_posted_intr_wakeup_handler = dummy_handler; + synchronize_rcu(); + } } EXPORT_SYMBOL_GPL(kvm_set_posted_intr_wakeup_handler); diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 1d9463e3096b..f2f733bcb2b9 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -132,6 +132,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg, frame->ret_addr = (unsigned long) ret_from_fork; p->thread.sp = (unsigned long) fork_frame; p->thread.io_bitmap = NULL; + p->thread.iopl_warn = 0; memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps)); #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 40ed44ead063..d71267081153 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -742,6 +742,28 @@ dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p) return 0; } +static char *prepare_command_line(void) +{ +#ifdef CONFIG_CMDLINE_BOOL +#ifdef CONFIG_CMDLINE_OVERRIDE + strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); +#else + if (builtin_cmdline[0]) { + /* append boot loader cmdline to builtin */ + strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); + strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); + strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); + } +#endif +#endif + + strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); + + parse_early_param(); + + return command_line; +} + /* * Determine if we were loaded by an EFI loader. If so, then we have also been * passed the efi memmap, systab, etc., so we should use these data structures @@ -831,6 +853,23 @@ void __init setup_arch(char **cmdline_p) x86_init.oem.arch_setup(); /* + * x86_configure_nx() is called before parse_early_param() (called by + * prepare_command_line()) to detect whether hardware doesn't support + * NX (so that the early EHCI debug console setup can safely call + * set_fixmap()). It may then be called again from within noexec_setup() + * during parsing early parameters to honor the respective command line + * option. + */ + x86_configure_nx(); + + /* + * This parses early params and it needs to run before + * early_reserve_memory() because latter relies on such settings + * supplied as early params. + */ + *cmdline_p = prepare_command_line(); + + /* * Do some memory reservations *before* memory is added to memblock, so * memblock allocations won't overwrite it. * @@ -863,33 +902,6 @@ void __init setup_arch(char **cmdline_p) bss_resource.start = __pa_symbol(__bss_start); bss_resource.end = __pa_symbol(__bss_stop)-1; -#ifdef CONFIG_CMDLINE_BOOL -#ifdef CONFIG_CMDLINE_OVERRIDE - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); -#else - if (builtin_cmdline[0]) { - /* append boot loader cmdline to builtin */ - strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE); - strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE); - strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE); - } -#endif -#endif - - strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE); - *cmdline_p = command_line; - - /* - * x86_configure_nx() is called before parse_early_param() to detect - * whether hardware doesn't support NX (so that the early EHCI debug - * console setup can safely call set_fixmap()). It may then be called - * again from within noexec_setup() during parsing early parameters - * to honor the respective command line option. - */ - x86_configure_nx(); - - parse_early_param(); - #ifdef CONFIG_MEMORY_HOTPLUG /* * Memory used by the kernel cannot be hot-removed because Linux diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index a6895e440bc3..88401675dabb 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -46,16 +46,6 @@ static struct ghcb __initdata *boot_ghcb; struct sev_es_runtime_data { struct ghcb ghcb_page; - /* Physical storage for the per-CPU IST stack of the #VC handler */ - char ist_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE); - - /* - * Physical storage for the per-CPU fall-back stack of the #VC handler. - * The fall-back stack is used when it is not safe to switch back to the - * interrupted stack in the #VC entry code. - */ - char fallback_stack[EXCEPTION_STKSZ] __aligned(PAGE_SIZE); - /* * Reserve one page per CPU as backup storage for the unencrypted GHCB. * It is needed when an NMI happens while the #VC handler uses the real @@ -99,27 +89,6 @@ DEFINE_STATIC_KEY_FALSE(sev_es_enable_key); /* Needed in vc_early_forward_exception */ void do_early_exception(struct pt_regs *regs, int trapnr); -static void __init setup_vc_stacks(int cpu) -{ - struct sev_es_runtime_data *data; - struct cpu_entry_area *cea; - unsigned long vaddr; - phys_addr_t pa; - - data = per_cpu(runtime_data, cpu); - cea = get_cpu_entry_area(cpu); - - /* Map #VC IST stack */ - vaddr = CEA_ESTACK_BOT(&cea->estacks, VC); - pa = __pa(data->ist_stack); - cea_set_pte((void *)vaddr, pa, PAGE_KERNEL); - - /* Map VC fall-back stack */ - vaddr = CEA_ESTACK_BOT(&cea->estacks, VC2); - pa = __pa(data->fallback_stack); - cea_set_pte((void *)vaddr, pa, PAGE_KERNEL); -} - static __always_inline bool on_vc_stack(struct pt_regs *regs) { unsigned long sp = regs->sp; @@ -787,7 +756,6 @@ void __init sev_es_init_vc_handling(void) for_each_possible_cpu(cpu) { alloc_runtime_data(cpu); init_ghcb(cpu); - setup_vc_stacks(cpu); } sev_es_setup_play_dead(); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index a58800973aed..5b1984d46822 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -313,17 +313,19 @@ out: } #ifdef CONFIG_VMAP_STACK -__visible void __noreturn handle_stack_overflow(const char *message, - struct pt_regs *regs, - unsigned long fault_address) +__visible void __noreturn handle_stack_overflow(struct pt_regs *regs, + unsigned long fault_address, + struct stack_info *info) { - printk(KERN_EMERG "BUG: stack guard page was hit at %p (stack is %p..%p)\n", - (void *)fault_address, current->stack, - (char *)current->stack + THREAD_SIZE - 1); - die(message, regs, 0); + const char *name = stack_type_name(info->type); + + printk(KERN_EMERG "BUG: %s stack guard page was hit at %p (stack is %p..%p)\n", + name, (void *)fault_address, info->begin, info->end); + + die("stack guard page", regs, 0); /* Be absolutely certain we don't return. */ - panic("%s", message); + panic("%s stack guard hit", name); } #endif @@ -353,6 +355,7 @@ DEFINE_IDTENTRY_DF(exc_double_fault) #ifdef CONFIG_VMAP_STACK unsigned long address = read_cr2(); + struct stack_info info; #endif #ifdef CONFIG_X86_ESPFIX64 @@ -455,10 +458,8 @@ DEFINE_IDTENTRY_DF(exc_double_fault) * stack even if the actual trigger for the double fault was * something else. */ - if ((unsigned long)task_stack_page(tsk) - 1 - address < PAGE_SIZE) { - handle_stack_overflow("kernel stack overflow (double-fault)", - regs, address); - } + if (get_stack_guard_info((void *)address, &info)) + handle_stack_overflow(regs, address, &info); #endif pr_emerg("PANIC: double fault, error_code: 0x%lx\n", error_code); @@ -528,6 +529,36 @@ static enum kernel_gp_hint get_kernel_gp_address(struct pt_regs *regs, #define GPFSTR "general protection fault" +static bool fixup_iopl_exception(struct pt_regs *regs) +{ + struct thread_struct *t = ¤t->thread; + unsigned char byte; + unsigned long ip; + + if (!IS_ENABLED(CONFIG_X86_IOPL_IOPERM) || t->iopl_emul != 3) + return false; + + if (insn_get_effective_ip(regs, &ip)) + return false; + + if (get_user(byte, (const char __user *)ip)) + return false; + + if (byte != 0xfa && byte != 0xfb) + return false; + + if (!t->iopl_warn && printk_ratelimit()) { + pr_err("%s[%d] attempts to use CLI/STI, pretending it's a NOP, ip:%lx", + current->comm, task_pid_nr(current), ip); + print_vma_addr(KERN_CONT " in ", ip); + pr_cont("\n"); + t->iopl_warn = 1; + } + + regs->ip += 1; + return true; +} + DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) { char desc[sizeof(GPFSTR) + 50 + 2*sizeof(unsigned long) + 1] = GPFSTR; @@ -553,6 +584,9 @@ DEFINE_IDTENTRY_ERRORCODE(exc_general_protection) tsk = current; if (user_mode(regs)) { + if (fixup_iopl_exception(regs)) + goto exit; + tsk->thread.error_code = error_code; tsk->thread.trap_nr = X86_TRAP_GP; @@ -709,7 +743,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r stack = (unsigned long *)sp; if (!get_stack_info_noinstr(stack, current, &info) || info.type == STACK_TYPE_ENTRY || - info.type >= STACK_TYPE_EXCEPTION_LAST) + info.type > STACK_TYPE_EXCEPTION_LAST) sp = __this_cpu_ist_top_va(VC2); sync: diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index e5a7a10a0164..17d58740891e 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -142,6 +142,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval) user_access_end(); +exit_vm86: preempt_disable(); tsk->thread.sp0 = vm86->saved_sp0; tsk->thread.sysenter_cs = __KERNEL_CS; @@ -161,7 +162,8 @@ Efault_end: user_access_end(); Efault: pr_alert("could not access userspace vm86 info\n"); - do_exit(SIGSEGV); + force_exit_sig(SIGSEGV); + goto exit_vm86; } static int do_vm86_irq_handling(int subfunction, int irqnumber); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 751aa85a3001..f666fd79d8ad 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -232,6 +232,25 @@ u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu) return rsvd_bits(cpuid_maxphyaddr(vcpu), 63); } +static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, + int nent) +{ + int r; + + r = kvm_check_cpuid(e2, nent); + if (r) + return r; + + kvfree(vcpu->arch.cpuid_entries); + vcpu->arch.cpuid_entries = e2; + vcpu->arch.cpuid_nent = nent; + + kvm_update_cpuid_runtime(vcpu); + kvm_vcpu_after_set_cpuid(vcpu); + + return 0; +} + /* when an old userspace process fills a new kernel module */ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid *cpuid, @@ -268,18 +287,9 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, e2[i].padding[2] = 0; } - r = kvm_check_cpuid(e2, cpuid->nent); - if (r) { + r = kvm_set_cpuid(vcpu, e2, cpuid->nent); + if (r) kvfree(e2); - goto out_free_cpuid; - } - - kvfree(vcpu->arch.cpuid_entries); - vcpu->arch.cpuid_entries = e2; - vcpu->arch.cpuid_nent = cpuid->nent; - - kvm_update_cpuid_runtime(vcpu); - kvm_vcpu_after_set_cpuid(vcpu); out_free_cpuid: kvfree(e); @@ -303,20 +313,11 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, return PTR_ERR(e2); } - r = kvm_check_cpuid(e2, cpuid->nent); - if (r) { + r = kvm_set_cpuid(vcpu, e2, cpuid->nent); + if (r) kvfree(e2); - return r; - } - kvfree(vcpu->arch.cpuid_entries); - vcpu->arch.cpuid_entries = e2; - vcpu->arch.cpuid_nent = cpuid->nent; - - kvm_update_cpuid_runtime(vcpu); - kvm_vcpu_after_set_cpuid(vcpu); - - return 0; + return r; } int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index d5124b520f76..b9a13dc211d5 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2022,7 +2022,7 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) { bool longmode; - longmode = is_64_bit_mode(vcpu); + longmode = is_64_bit_hypercall(vcpu); if (longmode) kvm_rax_write(vcpu, result); else { @@ -2171,7 +2171,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu) } #ifdef CONFIG_X86_64 - if (is_64_bit_mode(vcpu)) { + if (is_64_bit_hypercall(vcpu)) { hc.param = kvm_rcx_read(vcpu); hc.ingpa = kvm_rdx_read(vcpu); hc.outgpa = kvm_r8_read(vcpu); diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c index 8c065da73f8e..4e0f52660842 100644 --- a/arch/x86/kvm/ioapic.c +++ b/arch/x86/kvm/ioapic.c @@ -96,7 +96,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic, static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic) { ioapic->rtc_status.pending_eoi = 0; - bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID + 1); + bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID); } static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index bbd4a5d18b5d..27e61ff3ac3e 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -39,13 +39,13 @@ struct kvm_vcpu; struct dest_map { /* vcpu bitmap where IRQ has been sent */ - DECLARE_BITMAP(map, KVM_MAX_VCPU_ID + 1); + DECLARE_BITMAP(map, KVM_MAX_VCPU_ID); /* * Vector sent to a given vcpu, only valid when * the vcpu's bit in map is set */ - u8 vectors[KVM_MAX_VCPU_ID + 1]; + u8 vectors[KVM_MAX_VCPU_ID]; }; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 0cc58901bf7a..0e0f960a0bf8 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4679,6 +4679,7 @@ static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu, /* PKEY and LA57 are active iff long mode is active. */ ext.cr4_pke = ____is_efer_lma(regs) && ____is_cr4_pke(regs); ext.cr4_la57 = ____is_efer_lma(regs) && ____is_cr4_la57(regs); + ext.efer_lma = ____is_efer_lma(regs); } ext.valid = 1; @@ -5758,13 +5759,11 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, gfn_start, gfn_end, flush); - if (flush) - kvm_flush_remote_tlbs_with_address(kvm, gfn_start, - gfn_end - gfn_start); } if (flush) - kvm_flush_remote_tlbs_with_address(kvm, gfn_start, gfn_end); + kvm_flush_remote_tlbs_with_address(kvm, gfn_start, + gfn_end - gfn_start); kvm_dec_notifier_count(kvm, gfn_start, gfn_end); diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index eb7b227fc6cf..31d6456d8ac3 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -310,12 +310,7 @@ static inline bool __is_bad_mt_xwr(struct rsvd_bits_validate *rsvd_check, static __always_inline bool is_rsvd_spte(struct rsvd_bits_validate *rsvd_check, u64 spte, int level) { - /* - * Use a bitwise-OR instead of a logical-OR to aggregate the reserved - * bits and EPT's invalid memtype/XWR checks to avoid an extra Jcc - * (this is extremely unlikely to be short-circuited as true). - */ - return __is_bad_mt_xwr(rsvd_check, spte) | + return __is_bad_mt_xwr(rsvd_check, spte) || __is_rsvd_bits_set(rsvd_check, spte, level); } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 7e34d7163ada..ff19ce0780fe 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1787,7 +1787,12 @@ int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd) mutex_unlock(&source_kvm->lock); mutex_lock(&kvm->lock); - if (sev_guest(kvm)) { + /* + * Disallow out-of-band SEV/SEV-ES init if the target is already an + * SEV guest, or if vCPUs have been created. KVM relies on vCPUs being + * created after SEV/SEV-ES initialization, e.g. to init intercepts. + */ + if (sev_guest(kvm) || kvm->created_vcpus) { ret = -EINVAL; goto e_mirror_unlock; } diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index eedcebf58004..8936d8383b2e 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -524,29 +524,6 @@ static int nested_vmx_check_tpr_shadow_controls(struct kvm_vcpu *vcpu, } /* - * Check if MSR is intercepted for L01 MSR bitmap. - */ -static bool msr_write_intercepted_l01(struct kvm_vcpu *vcpu, u32 msr) -{ - unsigned long *msr_bitmap; - int f = sizeof(unsigned long); - - if (!cpu_has_vmx_msr_bitmap()) - return true; - - msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap; - - if (msr <= 0x1fff) { - return !!test_bit(msr, msr_bitmap + 0x800 / f); - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - return !!test_bit(msr, msr_bitmap + 0xc00 / f); - } - - return true; -} - -/* * If a msr is allowed by L0, we should check whether it is allowed by L1. * The corresponding bit will be cleared unless both of L0 and L1 allow it. */ @@ -599,6 +576,34 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) } } +#define BUILD_NVMX_MSR_INTERCEPT_HELPER(rw) \ +static inline \ +void nested_vmx_set_msr_##rw##_intercept(struct vcpu_vmx *vmx, \ + unsigned long *msr_bitmap_l1, \ + unsigned long *msr_bitmap_l0, u32 msr) \ +{ \ + if (vmx_test_msr_bitmap_##rw(vmx->vmcs01.msr_bitmap, msr) || \ + vmx_test_msr_bitmap_##rw(msr_bitmap_l1, msr)) \ + vmx_set_msr_bitmap_##rw(msr_bitmap_l0, msr); \ + else \ + vmx_clear_msr_bitmap_##rw(msr_bitmap_l0, msr); \ +} +BUILD_NVMX_MSR_INTERCEPT_HELPER(read) +BUILD_NVMX_MSR_INTERCEPT_HELPER(write) + +static inline void nested_vmx_set_intercept_for_msr(struct vcpu_vmx *vmx, + unsigned long *msr_bitmap_l1, + unsigned long *msr_bitmap_l0, + u32 msr, int types) +{ + if (types & MSR_TYPE_R) + nested_vmx_set_msr_read_intercept(vmx, msr_bitmap_l1, + msr_bitmap_l0, msr); + if (types & MSR_TYPE_W) + nested_vmx_set_msr_write_intercept(vmx, msr_bitmap_l1, + msr_bitmap_l0, msr); +} + /* * Merge L0's and L1's MSR bitmap, return false to indicate that * we do not use the hardware. @@ -606,10 +611,11 @@ static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { + struct vcpu_vmx *vmx = to_vmx(vcpu); int msr; unsigned long *msr_bitmap_l1; - unsigned long *msr_bitmap_l0 = to_vmx(vcpu)->nested.vmcs02.msr_bitmap; - struct kvm_host_map *map = &to_vmx(vcpu)->nested.msr_bitmap_map; + unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; + struct kvm_host_map *map = &vmx->nested.msr_bitmap_map; /* Nothing to do if the MSR bitmap is not in use. */ if (!cpu_has_vmx_msr_bitmap() || @@ -660,44 +666,27 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, } } - /* KVM unconditionally exposes the FS/GS base MSRs to L1. */ + /* + * Always check vmcs01's bitmap to honor userspace MSR filters and any + * other runtime changes to vmcs01's bitmap, e.g. dynamic pass-through. + */ #ifdef CONFIG_X86_64 - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_FS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_FS_BASE, MSR_TYPE_RW); - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_GS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_GS_BASE, MSR_TYPE_RW); - nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0, - MSR_KERNEL_GS_BASE, MSR_TYPE_RW); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_KERNEL_GS_BASE, MSR_TYPE_RW); #endif + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_SPEC_CTRL, MSR_TYPE_RW); - /* - * Checking the L0->L1 bitmap is trying to verify two things: - * - * 1. L0 gave a permission to L1 to actually passthrough the MSR. This - * ensures that we do not accidentally generate an L02 MSR bitmap - * from the L12 MSR bitmap that is too permissive. - * 2. That L1 or L2s have actually used the MSR. This avoids - * unnecessarily merging of the bitmap if the MSR is unused. This - * works properly because we only update the L01 MSR bitmap lazily. - * So even if L0 should pass L1 these MSRs, the L01 bitmap is only - * updated to reflect this when L1 (or its L2s) actually write to - * the MSR. - */ - if (!msr_write_intercepted_l01(vcpu, MSR_IA32_SPEC_CTRL)) - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - MSR_IA32_SPEC_CTRL, - MSR_TYPE_R | MSR_TYPE_W); - - if (!msr_write_intercepted_l01(vcpu, MSR_IA32_PRED_CMD)) - nested_vmx_disable_intercept_for_msr( - msr_bitmap_l1, msr_bitmap_l0, - MSR_IA32_PRED_CMD, - MSR_TYPE_W); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_PRED_CMD, MSR_TYPE_W); - kvm_vcpu_unmap(vcpu, &to_vmx(vcpu)->nested.msr_bitmap_map, false); + kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); return true; } @@ -2865,6 +2854,17 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, return 0; } +static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu, + struct vmcs12 *vmcs12) +{ +#ifdef CONFIG_X86_64 + if (CC(!!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) != + !!(vcpu->arch.efer & EFER_LMA))) + return -EINVAL; +#endif + return 0; +} + static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { @@ -2889,18 +2889,16 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, return -EINVAL; #ifdef CONFIG_X86_64 - ia32e = !!(vcpu->arch.efer & EFER_LMA); + ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE); #else ia32e = false; #endif if (ia32e) { - if (CC(!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)) || - CC(!(vmcs12->host_cr4 & X86_CR4_PAE))) + if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE))) return -EINVAL; } else { - if (CC(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) || - CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) || + if (CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) || CC(vmcs12->host_cr4 & X86_CR4_PCIDE) || CC((vmcs12->host_rip) >> 32)) return -EINVAL; @@ -3570,6 +3568,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (nested_vmx_check_controls(vcpu, vmcs12)) return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD); + if (nested_vmx_check_address_space_size(vcpu, vmcs12)) + return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); + if (nested_vmx_check_host_state(vcpu, vmcs12)) return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 7d595effb66f..671ff4150fcb 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -769,24 +769,13 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu) /* * Check if MSR is intercepted for currently loaded MSR bitmap. */ -static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr) +static bool msr_write_intercepted(struct vcpu_vmx *vmx, u32 msr) { - unsigned long *msr_bitmap; - int f = sizeof(unsigned long); - - if (!cpu_has_vmx_msr_bitmap()) + if (!(exec_controls_get(vmx) & CPU_BASED_USE_MSR_BITMAPS)) return true; - msr_bitmap = to_vmx(vcpu)->loaded_vmcs->msr_bitmap; - - if (msr <= 0x1fff) { - return !!test_bit(msr, msr_bitmap + 0x800 / f); - } else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) { - msr &= 0x1fff; - return !!test_bit(msr, msr_bitmap + 0xc00 / f); - } - - return true; + return vmx_test_msr_bitmap_write(vmx->loaded_vmcs->msr_bitmap, + MSR_IA32_SPEC_CTRL); } static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx, @@ -3695,46 +3684,6 @@ void free_vpid(int vpid) spin_unlock(&vmx_vpid_lock); } -static void vmx_clear_msr_bitmap_read(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __clear_bit(msr, msr_bitmap + 0x000 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __clear_bit(msr & 0x1fff, msr_bitmap + 0x400 / f); -} - -static void vmx_clear_msr_bitmap_write(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __clear_bit(msr, msr_bitmap + 0x800 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __clear_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); -} - -static void vmx_set_msr_bitmap_read(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __set_bit(msr, msr_bitmap + 0x000 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __set_bit(msr & 0x1fff, msr_bitmap + 0x400 / f); -} - -static void vmx_set_msr_bitmap_write(ulong *msr_bitmap, u32 msr) -{ - int f = sizeof(unsigned long); - - if (msr <= 0x1fff) - __set_bit(msr, msr_bitmap + 0x800 / f); - else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) - __set_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); -} - void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -6720,7 +6669,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) * If the L02 MSR bitmap does not intercept the MSR, then we need to * save it. */ - if (unlikely(!msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL))) + if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) vmx->spec_ctrl = native_read_msr(MSR_IA32_SPEC_CTRL); x86_spec_ctrl_restore_host(vmx->spec_ctrl, 0); @@ -7551,6 +7500,8 @@ static void vmx_migrate_timers(struct kvm_vcpu *vcpu) static void hardware_unsetup(void) { + kvm_set_posted_intr_wakeup_handler(NULL); + if (nested) nested_vmx_hardware_unsetup(); @@ -7879,8 +7830,6 @@ static __init int hardware_setup(void) vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit; } - kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler); - kvm_mce_cap_supported |= MCG_LMCE_P; if (pt_mode != PT_MODE_SYSTEM && pt_mode != PT_MODE_HOST_GUEST) @@ -7904,6 +7853,9 @@ static __init int hardware_setup(void) r = alloc_kvm_area(); if (r) nested_vmx_hardware_unsetup(); + + kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler); + return r; } diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 592217fd7d92..3f9c8548625d 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -400,6 +400,69 @@ static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu); +static inline bool vmx_test_msr_bitmap_read(ulong *msr_bitmap, u32 msr) +{ + int f = sizeof(unsigned long); + + if (msr <= 0x1fff) + return test_bit(msr, msr_bitmap + 0x000 / f); + else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) + return test_bit(msr & 0x1fff, msr_bitmap + 0x400 / f); + return true; +} + +static inline bool vmx_test_msr_bitmap_write(ulong *msr_bitmap, u32 msr) +{ + int f = sizeof(unsigned long); + + if (msr <= 0x1fff) + return test_bit(msr, msr_bitmap + 0x800 / f); + else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) + return test_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); + return true; +} + +static inline void vmx_clear_msr_bitmap_read(ulong *msr_bitmap, u32 msr) +{ + int f = sizeof(unsigned long); + + if (msr <= 0x1fff) + __clear_bit(msr, msr_bitmap + 0x000 / f); + else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) + __clear_bit(msr & 0x1fff, msr_bitmap + 0x400 / f); +} + +static inline void vmx_clear_msr_bitmap_write(ulong *msr_bitmap, u32 msr) +{ + int f = sizeof(unsigned long); + + if (msr <= 0x1fff) + __clear_bit(msr, msr_bitmap + 0x800 / f); + else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) + __clear_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); +} + +static inline void vmx_set_msr_bitmap_read(ulong *msr_bitmap, u32 msr) +{ + int f = sizeof(unsigned long); + + if (msr <= 0x1fff) + __set_bit(msr, msr_bitmap + 0x000 / f); + else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) + __set_bit(msr & 0x1fff, msr_bitmap + 0x400 / f); +} + +static inline void vmx_set_msr_bitmap_write(ulong *msr_bitmap, u32 msr) +{ + int f = sizeof(unsigned long); + + if (msr <= 0x1fff) + __set_bit(msr, msr_bitmap + 0x800 / f); + else if ((msr >= 0xc0000000) && (msr <= 0xc0001fff)) + __set_bit(msr & 0x1fff, msr_bitmap + 0xc00 / f); +} + + static inline u8 vmx_get_rvi(void) { return vmcs_read16(GUEST_INTR_STATUS) & 0xff; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index bfe0de3008a6..16c7465619f7 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -3195,8 +3195,11 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) static void record_steal_time(struct kvm_vcpu *vcpu) { - struct kvm_host_map map; - struct kvm_steal_time *st; + struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; + struct kvm_steal_time __user *st; + struct kvm_memslots *slots; + u64 steal; + u32 version; if (kvm_xen_msr_enabled(vcpu->kvm)) { kvm_xen_runstate_set_running(vcpu); @@ -3206,47 +3209,86 @@ static void record_steal_time(struct kvm_vcpu *vcpu) if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; - /* -EAGAIN is returned in atomic context so we can just return. */ - if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, - &map, &vcpu->arch.st.cache, false)) + if (WARN_ON_ONCE(current->mm != vcpu->kvm->mm)) return; - st = map.hva + - offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + slots = kvm_memslots(vcpu->kvm); + + if (unlikely(slots->generation != ghc->generation || + kvm_is_error_hva(ghc->hva) || !ghc->memslot)) { + gfn_t gfn = vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS; + + /* We rely on the fact that it fits in a single page. */ + BUILD_BUG_ON((sizeof(*st) - 1) & KVM_STEAL_VALID_BITS); + + if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gfn, sizeof(*st)) || + kvm_is_error_hva(ghc->hva) || !ghc->memslot) + return; + } + st = (struct kvm_steal_time __user *)ghc->hva; /* * Doing a TLB flush here, on the guest's behalf, can avoid * expensive IPIs. */ if (guest_pv_has(vcpu, KVM_FEATURE_PV_TLB_FLUSH)) { - u8 st_preempted = xchg(&st->preempted, 0); + u8 st_preempted = 0; + int err = -EFAULT; + + if (!user_access_begin(st, sizeof(*st))) + return; + + asm volatile("1: xchgb %0, %2\n" + "xor %1, %1\n" + "2:\n" + _ASM_EXTABLE_UA(1b, 2b) + : "+q" (st_preempted), + "+&r" (err), + "+m" (st->preempted)); + if (err) + goto out; + + user_access_end(); + + vcpu->arch.st.preempted = 0; trace_kvm_pv_tlb_flush(vcpu->vcpu_id, st_preempted & KVM_VCPU_FLUSH_TLB); if (st_preempted & KVM_VCPU_FLUSH_TLB) kvm_vcpu_flush_tlb_guest(vcpu); + + if (!user_access_begin(st, sizeof(*st))) + goto dirty; } else { - st->preempted = 0; - } + if (!user_access_begin(st, sizeof(*st))) + return; - vcpu->arch.st.preempted = 0; + unsafe_put_user(0, &st->preempted, out); + vcpu->arch.st.preempted = 0; + } - if (st->version & 1) - st->version += 1; /* first time write, random junk */ + unsafe_get_user(version, &st->version, out); + if (version & 1) + version += 1; /* first time write, random junk */ - st->version += 1; + version += 1; + unsafe_put_user(version, &st->version, out); smp_wmb(); - st->steal += current->sched_info.run_delay - + unsafe_get_user(steal, &st->steal, out); + steal += current->sched_info.run_delay - vcpu->arch.st.last_steal; vcpu->arch.st.last_steal = current->sched_info.run_delay; + unsafe_put_user(steal, &st->steal, out); - smp_wmb(); - - st->version += 1; + version += 1; + unsafe_put_user(version, &st->version, out); - kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, false); + out: + user_access_end(); + dirty: + mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -4285,8 +4327,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) { - struct kvm_host_map map; - struct kvm_steal_time *st; + struct gfn_to_hva_cache *ghc = &vcpu->arch.st.cache; + struct kvm_steal_time __user *st; + struct kvm_memslots *slots; + static const u8 preempted = KVM_VCPU_PREEMPTED; if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED)) return; @@ -4294,16 +4338,23 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu) if (vcpu->arch.st.preempted) return; - if (kvm_map_gfn(vcpu, vcpu->arch.st.msr_val >> PAGE_SHIFT, &map, - &vcpu->arch.st.cache, true)) + /* This happens on process exit */ + if (unlikely(current->mm != vcpu->kvm->mm)) + return; + + slots = kvm_memslots(vcpu->kvm); + + if (unlikely(slots->generation != ghc->generation || + kvm_is_error_hva(ghc->hva) || !ghc->memslot)) return; - st = map.hva + - offset_in_page(vcpu->arch.st.msr_val & KVM_STEAL_VALID_BITS); + st = (struct kvm_steal_time __user *)ghc->hva; + BUILD_BUG_ON(sizeof(st->preempted) != sizeof(preempted)); - st->preempted = vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; + if (!copy_to_user_nofault(&st->preempted, &preempted, sizeof(preempted))) + vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED; - kvm_unmap_gfn(vcpu, &map, &vcpu->arch.st.cache, true, true); + mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa)); } void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) @@ -8686,7 +8737,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) trace_kvm_hypercall(nr, a0, a1, a2, a3); - op_64_bit = is_64_bit_mode(vcpu); + op_64_bit = is_64_bit_hypercall(vcpu); if (!op_64_bit) { nr &= 0xFFFFFFFF; a0 &= 0xFFFFFFFF; @@ -9378,12 +9429,16 @@ static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; - if (to_hv_vcpu(vcpu)) + if (to_hv_vcpu(vcpu)) { bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, to_hv_synic(vcpu)->vec_bitmap, 256); + static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); + return; + } - static_call(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); + static_call(kvm_x86_load_eoi_exitmap)( + vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, @@ -10817,11 +10872,8 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) { - struct gfn_to_pfn_cache *cache = &vcpu->arch.st.cache; int idx; - kvm_release_pfn(cache->pfn, cache->dirty, cache); - kvmclock_reset(vcpu); static_call(kvm_x86_vcpu_free)(vcpu); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 7d66d63dc55a..9776a1db8ea8 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -153,12 +153,24 @@ static inline bool is_64_bit_mode(struct kvm_vcpu *vcpu) { int cs_db, cs_l; + WARN_ON_ONCE(vcpu->arch.guest_state_protected); + if (!is_long_mode(vcpu)) return false; static_call(kvm_x86_get_cs_db_l_bits)(vcpu, &cs_db, &cs_l); return cs_l; } +static inline bool is_64_bit_hypercall(struct kvm_vcpu *vcpu) +{ + /* + * If running with protected guest state, the CS register is not + * accessible. The hypercall register values will have had to been + * provided in 64-bit mode, so assume the guest is in 64-bit. + */ + return vcpu->arch.guest_state_protected || is_64_bit_mode(vcpu); +} + static inline bool x86_exception_has_error_code(unsigned int vector) { static u32 exception_has_error_code = BIT(DF_VECTOR) | BIT(TS_VECTOR) | diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 8f62baebd028..0787d6645573 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -299,7 +299,7 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; case KVM_XEN_ATTR_TYPE_SHARED_INFO: - data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_gfn); + data->u.shared_info.gfn = kvm->arch.xen.shinfo_gfn; r = 0; break; @@ -698,7 +698,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) kvm_hv_hypercall_enabled(vcpu)) return kvm_hv_hypercall(vcpu); - longmode = is_64_bit_mode(vcpu); + longmode = is_64_bit_hypercall(vcpu); if (!longmode) { params[0] = (u32)kvm_rbx_read(vcpu); params[1] = (u32)kvm_rcx_read(vcpu); diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index a1d24fdc07cf..eb3ccffb9b9d 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -1417,7 +1417,7 @@ void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs) } } -static int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip) +int insn_get_effective_ip(struct pt_regs *regs, unsigned long *ip) { unsigned long seg_base = 0; diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index c565def611e2..55e371cc69fd 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -13,6 +13,7 @@ #endif #include <asm/inat.h> /*__ignore_sync_check__ */ #include <asm/insn.h> /* __ignore_sync_check__ */ +#include <asm/unaligned.h> /* __ignore_sync_check__ */ #include <linux/errno.h> #include <linux/kconfig.h> @@ -37,10 +38,10 @@ ((insn)->next_byte + sizeof(t) + n <= (insn)->end_kaddr) #define __get_next(t, insn) \ - ({ t r; memcpy(&r, insn->next_byte, sizeof(t)); insn->next_byte += sizeof(t); leXX_to_cpu(t, r); }) + ({ t r = get_unaligned((t *)(insn)->next_byte); (insn)->next_byte += sizeof(t); leXX_to_cpu(t, r); }) #define __peek_nbyte_next(t, insn, n) \ - ({ t r; memcpy(&r, (insn)->next_byte + n, sizeof(t)); leXX_to_cpu(t, r); }) + ({ t r = get_unaligned((t *)(insn)->next_byte + n); leXX_to_cpu(t, r); }) #define get_next(t, insn) \ ({ if (unlikely(!validate_next(t, insn, 0))) goto err_out; __get_next(t, insn); }) diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index f5e1e60c9095..6c2f1b76a0b6 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -110,6 +110,13 @@ static void __init percpu_setup_exception_stacks(unsigned int cpu) cea_map_stack(NMI); cea_map_stack(DB); cea_map_stack(MCE); + + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { + if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) { + cea_map_stack(VC); + cea_map_stack(VC2); + } + } } #else static inline void percpu_setup_exception_stacks(unsigned int cpu) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 84a2c8c4af73..4bfed53e210e 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -32,6 +32,7 @@ #include <asm/pgtable_areas.h> /* VMALLOC_START, ... */ #include <asm/kvm_para.h> /* kvm_handle_async_pf */ #include <asm/vdso.h> /* fixup_vdso_exception() */ +#include <asm/irq_stack.h> #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -631,6 +632,9 @@ static noinline void page_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long address) { +#ifdef CONFIG_VMAP_STACK + struct stack_info info; +#endif unsigned long flags; int sig; @@ -649,9 +653,7 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code, * that we're in vmalloc space to avoid this. */ if (is_vmalloc_addr((void *)address) && - (((unsigned long)current->stack - 1 - address < PAGE_SIZE) || - address - ((unsigned long)current->stack + THREAD_SIZE) < PAGE_SIZE)) { - unsigned long stack = __this_cpu_ist_top_va(DF) - sizeof(void *); + get_stack_guard_info((void *)address, &info)) { /* * We're likely to be running with very little stack space * left. It's plausible that we'd hit this condition but @@ -662,13 +664,11 @@ page_fault_oops(struct pt_regs *regs, unsigned long error_code, * and then double-fault, though, because we're likely to * break the console driver and lose most of the stack dump. */ - asm volatile ("movq %[stack], %%rsp\n\t" - "call handle_stack_overflow\n\t" - "1: jmp 1b" - : ASM_CALL_CONSTRAINT - : "D" ("kernel stack overflow (page fault)"), - "S" (regs), "d" (address), - [stack] "rm" (stack)); + call_on_stack(__this_cpu_ist_top_va(DF) - sizeof(void*), + handle_stack_overflow, + ASM_CALL_ARG3, + , [arg1] "r" (regs), [arg2] "r" (address), [arg3] "r" (&info)); + unreachable(); } #endif diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index ff08dc463634..e29b1418d00c 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -20,6 +20,7 @@ #include <linux/bitops.h> #include <linux/dma-mapping.h> #include <linux/virtio_config.h> +#include <linux/cc_platform.h> #include <asm/tlbflush.h> #include <asm/fixmap.h> diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index 470b20208430..700ce8fdea87 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -27,6 +27,15 @@ #undef CONFIG_PARAVIRT_XXL #undef CONFIG_PARAVIRT_SPINLOCKS +/* + * This code runs before CPU feature bits are set. By default, the + * pgtable_l5_enabled() function uses bit X86_FEATURE_LA57 to determine if + * 5-level paging is active, so that won't work here. USE_EARLY_PGTABLE_L5 + * is provided to handle this situation and, instead, use a variable that + * has been set by the early boot code. + */ +#define USE_EARLY_PGTABLE_L5 + #include <linux/kernel.h> #include <linux/mm.h> #include <linux/mem_encrypt.h> |