diff options
Diffstat (limited to 'arch/x86')
280 files changed, 9007 insertions, 5280 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 67745ceab0db..7577c3344930 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -69,6 +69,7 @@ config X86 select ARCH_ENABLE_THP_MIGRATION if X86_64 && TRANSPARENT_HUGEPAGE select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_CACHE_LINE_SIZE + select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE @@ -81,6 +82,7 @@ config X86 select ARCH_HAS_KCOV if X86_64 select ARCH_HAS_MEM_ENCRYPT select ARCH_HAS_MEMBARRIER_SYNC_CORE + select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_PTE_DEVMAP if X86_64 @@ -290,6 +292,8 @@ config X86 select X86_FEATURE_NAMES if PROC_FS select PROC_PID_ARCH_STATUS if PROC_FS select HAVE_ARCH_NODE_DEV_GROUP if X86_SGX + select FUNCTION_ALIGNMENT_16B if X86_64 || X86_ALIGNMENT_16 + select FUNCTION_ALIGNMENT_4B imply IMA_SECURE_AND_OR_TRUSTED_BOOT if EFI select HAVE_DYNAMIC_FTRACE_NO_PATCHABLE @@ -357,11 +361,6 @@ config ARCH_HAS_CPU_RELAX config ARCH_HIBERNATION_POSSIBLE def_bool y -config ARCH_NR_GPIO - int - default 1024 if X86_64 - default 512 - config ARCH_SUSPEND_POSSIBLE def_bool y @@ -462,8 +461,8 @@ config X86_X2APIC Some Intel systems circa 2022 and later are locked into x2APIC mode and can not fall back to the legacy APIC modes if SGX or TDX are - enabled in the BIOS. They will be unable to boot without enabling - this option. + enabled in the BIOS. They will boot with very reduced functionality + without enabling this option. If you don't know what to do here, say N. @@ -1109,7 +1108,6 @@ config X86_LOCAL_APIC def_bool y depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI select IRQ_DOMAIN_HIERARCHY - select PCI_MSI_IRQ_DOMAIN if PCI_MSI config X86_IO_APIC def_bool y @@ -1854,7 +1852,7 @@ config CC_HAS_IBT config X86_KERNEL_IBT prompt "Indirect Branch Tracking" - bool + def_bool y depends on X86_64 && CC_HAS_IBT && HAVE_OBJTOOL # https://github.com/llvm/llvm-project/commit/9d7001eba9c4cb311e03cd8cdc231f9e579f2d0f depends on !LD_IS_LLD || LLD_VERSION >= 140000 @@ -1980,6 +1978,23 @@ config EFI_STUB See Documentation/admin-guide/efi-stub.rst for more information. +config EFI_HANDOVER_PROTOCOL + bool "EFI handover protocol (DEPRECATED)" + depends on EFI_STUB + default y + help + Select this in order to include support for the deprecated EFI + handover protocol, which defines alternative entry points into the + EFI stub. This is a practice that has no basis in the UEFI + specification, and requires a priori knowledge on the part of the + bootloader about Linux/x86 specific ways of passing the command line + and initrd, and where in memory those assets may be loaded. + + If in doubt, say Y. Even though the corresponding support is not + present in upstream GRUB or other bootloaders, most distros build + GRUB with numerous downstream patches applied, and may rely on the + handover protocol as as result. + config EFI_MIXED bool "EFI mixed-mode support" depends on EFI_STUB && X86_64 @@ -1994,6 +2009,37 @@ config EFI_MIXED If unsure, say N. +config EFI_FAKE_MEMMAP + bool "Enable EFI fake memory map" + depends on EFI + help + Saying Y here will enable "efi_fake_mem" boot option. By specifying + this parameter, you can add arbitrary attribute to specific memory + range by updating original (firmware provided) EFI memmap. This is + useful for debugging of EFI memmap related feature, e.g., Address + Range Mirroring feature. + +config EFI_MAX_FAKE_MEM + int "maximum allowable number of ranges in efi_fake_mem boot option" + depends on EFI_FAKE_MEMMAP + range 1 128 + default 8 + help + Maximum allowable number of ranges in efi_fake_mem boot option. + Ranges can be set up to this value using comma-separated list. + The default value is 8. + +config EFI_RUNTIME_MAP + bool "Export EFI runtime maps to sysfs" if EXPERT + depends on EFI + default KEXEC_CORE + help + Export EFI runtime memory regions to /sys/firmware/efi/runtime-map. + That memory map is required by the 2nd kernel to set up EFI virtual + mappings after kexec, but can also be used for debugging purposes. + + See also Documentation/ABI/testing/sysfs-firmware-efi-runtime-map. + source "kernel/Kconfig.hz" config KEXEC @@ -2443,6 +2489,46 @@ config CC_HAS_SLS config CC_HAS_RETURN_THUNK def_bool $(cc-option,-mfunction-return=thunk-extern) +config CC_HAS_ENTRY_PADDING + def_bool $(cc-option,-fpatchable-function-entry=16,16) + +config FUNCTION_PADDING_CFI + int + default 59 if FUNCTION_ALIGNMENT_64B + default 27 if FUNCTION_ALIGNMENT_32B + default 11 if FUNCTION_ALIGNMENT_16B + default 3 if FUNCTION_ALIGNMENT_8B + default 0 + +# Basically: FUNCTION_ALIGNMENT - 5*CFI_CLANG +# except Kconfig can't do arithmetic :/ +config FUNCTION_PADDING_BYTES + int + default FUNCTION_PADDING_CFI if CFI_CLANG + default FUNCTION_ALIGNMENT + +config CALL_PADDING + def_bool n + depends on CC_HAS_ENTRY_PADDING && OBJTOOL + select FUNCTION_ALIGNMENT_16B + +config FINEIBT + def_bool y + depends on X86_KERNEL_IBT && CFI_CLANG && RETPOLINE + select CALL_PADDING + +config HAVE_CALL_THUNKS + def_bool y + depends on CC_HAS_ENTRY_PADDING && RETHUNK && OBJTOOL + +config CALL_THUNKS + def_bool n + select CALL_PADDING + +config PREFIX_SYMBOLS + def_bool y + depends on CALL_PADDING && !CFI_CLANG + menuconfig SPECULATION_MITIGATIONS bool "Mitigations for speculative execution vulnerabilities" default y @@ -2494,6 +2580,37 @@ config CPU_UNRET_ENTRY help Compile the kernel with support for the retbleed=unret mitigation. +config CALL_DEPTH_TRACKING + bool "Mitigate RSB underflow with call depth tracking" + depends on CPU_SUP_INTEL && HAVE_CALL_THUNKS + select HAVE_DYNAMIC_FTRACE_NO_PATCHABLE + select CALL_THUNKS + default y + help + Compile the kernel with call depth tracking to mitigate the Intel + SKL Return-Speculation-Buffer (RSB) underflow issue. The + mitigation is off by default and needs to be enabled on the + kernel command line via the retbleed=stuff option. For + non-affected systems the overhead of this option is marginal as + the call depth tracking is using run-time generated call thunks + in a compiler generated padding area and call patching. This + increases text size by ~5%. For non affected systems this space + is unused. On affected SKL systems this results in a significant + performance gain over the IBRS mitigation. + +config CALL_THUNKS_DEBUG + bool "Enable call thunks and call depth tracking debugging" + depends on CALL_DEPTH_TRACKING + select FUNCTION_ALIGNMENT_32B + default n + help + Enable call/ret counters for imbalance detection and build in + a noisy dmesg about callthunks generation and call patching for + trouble shooting. The debug prints need to be enabled on the + kernel command line with 'debug-callthunks'. + Only enable this, when you are debugging call thunks as this + creates a noticable runtime overhead. If unsure say N. + config CPU_IBPB_ENTRY bool "Enable IBPB on kernel entry" depends on CPU_SUP_AMD && X86_64 diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 415a5d138de4..a3a07df8a609 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -208,6 +208,12 @@ ifdef CONFIG_SLS KBUILD_CFLAGS += -mharden-sls=all endif +ifdef CONFIG_CALL_PADDING +PADDING_CFLAGS := -fpatchable-function-entry=$(CONFIG_FUNCTION_PADDING_BYTES),$(CONFIG_FUNCTION_PADDING_BYTES) +KBUILD_CFLAGS += $(PADDING_CFLAGS) +export PADDING_CFLAGS +endif + KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE) ifdef CONFIG_LTO_CLANG diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index 9860ca5979f8..9e38ffaadb5d 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -83,7 +83,7 @@ cmd_image = $(obj)/tools/build $(obj)/setup.bin $(obj)/vmlinux.bin \ $(obj)/bzImage: $(obj)/setup.bin $(obj)/vmlinux.bin $(obj)/tools/build FORCE $(call if_changed,image) - @$(kecho) 'Kernel: $@ is ready' ' (#'`cat .version`')' + @$(kecho) 'Kernel: $@ is ready' ' (#'$(or $(KBUILD_BUILD_VERSION),`cat .version`)')' OBJCOPYFLAGS_vmlinux.bin := -O binary -R .note -R .comment -S $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 3a261abb6d15..1acff356d97a 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -68,7 +68,7 @@ KBUILD_LDFLAGS += $(call ld-option,--no-ld-generated-unwind-info) # address by the bootloader. LDFLAGS_vmlinux := -pie $(call ld-option, --no-dynamic-linker) ifdef CONFIG_LD_ORPHAN_WARN -LDFLAGS_vmlinux += --orphan-handling=warn +LDFLAGS_vmlinux += --orphan-handling=$(CONFIG_LD_ORPHAN_WARN_LEVEL) endif LDFLAGS_vmlinux += -z noexecstack ifeq ($(CONFIG_LD_IS_BFD),y) @@ -100,7 +100,7 @@ vmlinux-objs-$(CONFIG_RANDOMIZE_BASE) += $(obj)/kaslr.o ifdef CONFIG_X86_64 vmlinux-objs-y += $(obj)/ident_map_64.o vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o - vmlinux-objs-y += $(obj)/mem_encrypt.o + vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/mem_encrypt.o vmlinux-objs-y += $(obj)/pgtable_64.o vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o endif @@ -108,11 +108,11 @@ endif vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o vmlinux-objs-$(CONFIG_INTEL_TDX_GUEST) += $(obj)/tdx.o $(obj)/tdcall.o -vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o -efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o +vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a -$(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE +$(obj)/vmlinux: $(vmlinux-objs-y) FORCE $(call if_changed,ld) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S diff --git a/arch/x86/boot/compressed/efi_mixed.S b/arch/x86/boot/compressed/efi_mixed.S new file mode 100644 index 000000000000..4ca70bf93dc0 --- /dev/null +++ b/arch/x86/boot/compressed/efi_mixed.S @@ -0,0 +1,345 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming + * + * Early support for invoking 32-bit EFI services from a 64-bit kernel. + * + * Because this thunking occurs before ExitBootServices() we have to + * restore the firmware's 32-bit GDT and IDT before we make EFI service + * calls. + * + * On the plus side, we don't have to worry about mangling 64-bit + * addresses into 32-bits because we're executing with an identity + * mapped pagetable and haven't transitioned to 64-bit virtual addresses + * yet. + */ + +#include <linux/linkage.h> +#include <asm/msr.h> +#include <asm/page_types.h> +#include <asm/processor-flags.h> +#include <asm/segment.h> + + .code64 + .text +/* + * When booting in 64-bit mode on 32-bit EFI firmware, startup_64_mixed_mode() + * is the first thing that runs after switching to long mode. Depending on + * whether the EFI handover protocol or the compat entry point was used to + * enter the kernel, it will either branch to the 64-bit EFI handover + * entrypoint at offset 0x390 in the image, or to the 64-bit EFI PE/COFF + * entrypoint efi_pe_entry(). In the former case, the bootloader must provide a + * struct bootparams pointer as the third argument, so the presence of such a + * pointer is used to disambiguate. + * + * +--------------+ + * +------------------+ +------------+ +------>| efi_pe_entry | + * | efi32_pe_entry |---->| | | +-----------+--+ + * +------------------+ | | +------+----------------+ | + * | startup_32 |---->| startup_64_mixed_mode | | + * +------------------+ | | +------+----------------+ V + * | efi32_stub_entry |---->| | | +------------------+ + * +------------------+ +------------+ +---->| efi64_stub_entry | + * +-------------+----+ + * +------------+ +----------+ | + * | startup_64 |<----| efi_main |<--------------+ + * +------------+ +----------+ + */ +SYM_FUNC_START(startup_64_mixed_mode) + lea efi32_boot_args(%rip), %rdx + mov 0(%rdx), %edi + mov 4(%rdx), %esi + mov 8(%rdx), %edx // saved bootparams pointer + test %edx, %edx + jnz efi64_stub_entry + /* + * efi_pe_entry uses MS calling convention, which requires 32 bytes of + * shadow space on the stack even if all arguments are passed in + * registers. We also need an additional 8 bytes for the space that + * would be occupied by the return address, and this also results in + * the correct stack alignment for entry. + */ + sub $40, %rsp + mov %rdi, %rcx // MS calling convention + mov %rsi, %rdx + jmp efi_pe_entry +SYM_FUNC_END(startup_64_mixed_mode) + +SYM_FUNC_START(__efi64_thunk) + push %rbp + push %rbx + + movl %ds, %eax + push %rax + movl %es, %eax + push %rax + movl %ss, %eax + push %rax + + /* Copy args passed on stack */ + movq 0x30(%rsp), %rbp + movq 0x38(%rsp), %rbx + movq 0x40(%rsp), %rax + + /* + * Convert x86-64 ABI params to i386 ABI + */ + subq $64, %rsp + movl %esi, 0x0(%rsp) + movl %edx, 0x4(%rsp) + movl %ecx, 0x8(%rsp) + movl %r8d, 0xc(%rsp) + movl %r9d, 0x10(%rsp) + movl %ebp, 0x14(%rsp) + movl %ebx, 0x18(%rsp) + movl %eax, 0x1c(%rsp) + + leaq 0x20(%rsp), %rbx + sgdt (%rbx) + sidt 16(%rbx) + + leaq 1f(%rip), %rbp + + /* + * Switch to IDT and GDT with 32-bit segments. These are the firmware + * GDT and IDT that were installed when the kernel started executing. + * The pointers were saved by the efi32_entry() routine below. + * + * Pass the saved DS selector to the 32-bit code, and use far return to + * restore the saved CS selector. + */ + lidt efi32_boot_idt(%rip) + lgdt efi32_boot_gdt(%rip) + + movzwl efi32_boot_ds(%rip), %edx + movzwq efi32_boot_cs(%rip), %rax + pushq %rax + leaq efi_enter32(%rip), %rax + pushq %rax + lretq + +1: addq $64, %rsp + movq %rdi, %rax + + pop %rbx + movl %ebx, %ss + pop %rbx + movl %ebx, %es + pop %rbx + movl %ebx, %ds + /* Clear out 32-bit selector from FS and GS */ + xorl %ebx, %ebx + movl %ebx, %fs + movl %ebx, %gs + + pop %rbx + pop %rbp + RET +SYM_FUNC_END(__efi64_thunk) + + .code32 +/* + * EFI service pointer must be in %edi. + * + * The stack should represent the 32-bit calling convention. + */ +SYM_FUNC_START_LOCAL(efi_enter32) + /* Load firmware selector into data and stack segment registers */ + movl %edx, %ds + movl %edx, %es + movl %edx, %fs + movl %edx, %gs + movl %edx, %ss + + /* Reload pgtables */ + movl %cr3, %eax + movl %eax, %cr3 + + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + /* Disable long mode via EFER */ + movl $MSR_EFER, %ecx + rdmsr + btrl $_EFER_LME, %eax + wrmsr + + call *%edi + + /* We must preserve return value */ + movl %eax, %edi + + /* + * Some firmware will return with interrupts enabled. Be sure to + * disable them before we switch GDTs and IDTs. + */ + cli + + lidtl 16(%ebx) + lgdtl (%ebx) + + movl %cr4, %eax + btsl $(X86_CR4_PAE_BIT), %eax + movl %eax, %cr4 + + movl %cr3, %eax + movl %eax, %cr3 + + movl $MSR_EFER, %ecx + rdmsr + btsl $_EFER_LME, %eax + wrmsr + + xorl %eax, %eax + lldt %ax + + pushl $__KERNEL_CS + pushl %ebp + + /* Enable paging */ + movl %cr0, %eax + btsl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + lret +SYM_FUNC_END(efi_enter32) + +/* + * This is the common EFI stub entry point for mixed mode. + * + * Arguments: %ecx image handle + * %edx EFI system table pointer + * %esi struct bootparams pointer (or NULL when not using + * the EFI handover protocol) + * + * Since this is the point of no return for ordinary execution, no registers + * are considered live except for the function parameters. [Note that the EFI + * stub may still exit and return to the firmware using the Exit() EFI boot + * service.] + */ +SYM_FUNC_START(efi32_entry) + call 1f +1: pop %ebx + + /* Save firmware GDTR and code/data selectors */ + sgdtl (efi32_boot_gdt - 1b)(%ebx) + movw %cs, (efi32_boot_cs - 1b)(%ebx) + movw %ds, (efi32_boot_ds - 1b)(%ebx) + + /* Store firmware IDT descriptor */ + sidtl (efi32_boot_idt - 1b)(%ebx) + + /* Store boot arguments */ + leal (efi32_boot_args - 1b)(%ebx), %ebx + movl %ecx, 0(%ebx) + movl %edx, 4(%ebx) + movl %esi, 8(%ebx) + movb $0x0, 12(%ebx) // efi_is64 + + /* Disable paging */ + movl %cr0, %eax + btrl $X86_CR0_PG_BIT, %eax + movl %eax, %cr0 + + jmp startup_32 +SYM_FUNC_END(efi32_entry) + +#define ST32_boottime 60 // offsetof(efi_system_table_32_t, boottime) +#define BS32_handle_protocol 88 // offsetof(efi_boot_services_32_t, handle_protocol) +#define LI32_image_base 32 // offsetof(efi_loaded_image_32_t, image_base) + +/* + * efi_status_t efi32_pe_entry(efi_handle_t image_handle, + * efi_system_table_32_t *sys_table) + */ +SYM_FUNC_START(efi32_pe_entry) + pushl %ebp + movl %esp, %ebp + pushl %eax // dummy push to allocate loaded_image + + pushl %ebx // save callee-save registers + pushl %edi + + call verify_cpu // check for long mode support + testl %eax, %eax + movl $0x80000003, %eax // EFI_UNSUPPORTED + jnz 2f + + call 1f +1: pop %ebx + + /* Get the loaded image protocol pointer from the image handle */ + leal -4(%ebp), %eax + pushl %eax // &loaded_image + leal (loaded_image_proto - 1b)(%ebx), %eax + pushl %eax // pass the GUID address + pushl 8(%ebp) // pass the image handle + + /* + * Note the alignment of the stack frame. + * sys_table + * handle <-- 16-byte aligned on entry by ABI + * return address + * frame pointer + * loaded_image <-- local variable + * saved %ebx <-- 16-byte aligned here + * saved %edi + * &loaded_image + * &loaded_image_proto + * handle <-- 16-byte aligned for call to handle_protocol + */ + + movl 12(%ebp), %eax // sys_table + movl ST32_boottime(%eax), %eax // sys_table->boottime + call *BS32_handle_protocol(%eax) // sys_table->boottime->handle_protocol + addl $12, %esp // restore argument space + testl %eax, %eax + jnz 2f + + movl 8(%ebp), %ecx // image_handle + movl 12(%ebp), %edx // sys_table + movl -4(%ebp), %esi // loaded_image + movl LI32_image_base(%esi), %esi // loaded_image->image_base + leal (startup_32 - 1b)(%ebx), %ebp // runtime address of startup_32 + /* + * We need to set the image_offset variable here since startup_32() will + * use it before we get to the 64-bit efi_pe_entry() in C code. + */ + subl %esi, %ebp // calculate image_offset + movl %ebp, (image_offset - 1b)(%ebx) // save image_offset + xorl %esi, %esi + jmp efi32_entry // pass %ecx, %edx, %esi + // no other registers remain live + +2: popl %edi // restore callee-save registers + popl %ebx + leave + RET +SYM_FUNC_END(efi32_pe_entry) + + .section ".rodata" + /* EFI loaded image protocol GUID */ + .balign 4 +SYM_DATA_START_LOCAL(loaded_image_proto) + .long 0x5b1b31a1 + .word 0x9562, 0x11d2 + .byte 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b +SYM_DATA_END(loaded_image_proto) + + .data + .balign 8 +SYM_DATA_START_LOCAL(efi32_boot_gdt) + .word 0 + .quad 0 +SYM_DATA_END(efi32_boot_gdt) + +SYM_DATA_START_LOCAL(efi32_boot_idt) + .word 0 + .quad 0 +SYM_DATA_END(efi32_boot_idt) + +SYM_DATA_LOCAL(efi32_boot_cs, .word 0) +SYM_DATA_LOCAL(efi32_boot_ds, .word 0) +SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0) +SYM_DATA(efi_is64, .byte 1) diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S deleted file mode 100644 index 67e7edcdfea8..000000000000 --- a/arch/x86/boot/compressed/efi_thunk_64.S +++ /dev/null @@ -1,195 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming - * - * Early support for invoking 32-bit EFI services from a 64-bit kernel. - * - * Because this thunking occurs before ExitBootServices() we have to - * restore the firmware's 32-bit GDT and IDT before we make EFI service - * calls. - * - * On the plus side, we don't have to worry about mangling 64-bit - * addresses into 32-bits because we're executing with an identity - * mapped pagetable and haven't transitioned to 64-bit virtual addresses - * yet. - */ - -#include <linux/linkage.h> -#include <asm/msr.h> -#include <asm/page_types.h> -#include <asm/processor-flags.h> -#include <asm/segment.h> - - .code64 - .text -SYM_FUNC_START(__efi64_thunk) - push %rbp - push %rbx - - movl %ds, %eax - push %rax - movl %es, %eax - push %rax - movl %ss, %eax - push %rax - - /* Copy args passed on stack */ - movq 0x30(%rsp), %rbp - movq 0x38(%rsp), %rbx - movq 0x40(%rsp), %rax - - /* - * Convert x86-64 ABI params to i386 ABI - */ - subq $64, %rsp - movl %esi, 0x0(%rsp) - movl %edx, 0x4(%rsp) - movl %ecx, 0x8(%rsp) - movl %r8d, 0xc(%rsp) - movl %r9d, 0x10(%rsp) - movl %ebp, 0x14(%rsp) - movl %ebx, 0x18(%rsp) - movl %eax, 0x1c(%rsp) - - leaq 0x20(%rsp), %rbx - sgdt (%rbx) - - addq $16, %rbx - sidt (%rbx) - - leaq 1f(%rip), %rbp - - /* - * Switch to IDT and GDT with 32-bit segments. This is the firmware GDT - * and IDT that was installed when the kernel started executing. The - * pointers were saved at the EFI stub entry point in head_64.S. - * - * Pass the saved DS selector to the 32-bit code, and use far return to - * restore the saved CS selector. - */ - leaq efi32_boot_idt(%rip), %rax - lidt (%rax) - leaq efi32_boot_gdt(%rip), %rax - lgdt (%rax) - - movzwl efi32_boot_ds(%rip), %edx - movzwq efi32_boot_cs(%rip), %rax - pushq %rax - leaq efi_enter32(%rip), %rax - pushq %rax - lretq - -1: addq $64, %rsp - movq %rdi, %rax - - pop %rbx - movl %ebx, %ss - pop %rbx - movl %ebx, %es - pop %rbx - movl %ebx, %ds - /* Clear out 32-bit selector from FS and GS */ - xorl %ebx, %ebx - movl %ebx, %fs - movl %ebx, %gs - - /* - * Convert 32-bit status code into 64-bit. - */ - roll $1, %eax - rorq $1, %rax - - pop %rbx - pop %rbp - RET -SYM_FUNC_END(__efi64_thunk) - - .code32 -/* - * EFI service pointer must be in %edi. - * - * The stack should represent the 32-bit calling convention. - */ -SYM_FUNC_START_LOCAL(efi_enter32) - /* Load firmware selector into data and stack segment registers */ - movl %edx, %ds - movl %edx, %es - movl %edx, %fs - movl %edx, %gs - movl %edx, %ss - - /* Reload pgtables */ - movl %cr3, %eax - movl %eax, %cr3 - - /* Disable paging */ - movl %cr0, %eax - btrl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - - /* Disable long mode via EFER */ - movl $MSR_EFER, %ecx - rdmsr - btrl $_EFER_LME, %eax - wrmsr - - call *%edi - - /* We must preserve return value */ - movl %eax, %edi - - /* - * Some firmware will return with interrupts enabled. Be sure to - * disable them before we switch GDTs and IDTs. - */ - cli - - lidtl (%ebx) - subl $16, %ebx - - lgdtl (%ebx) - - movl %cr4, %eax - btsl $(X86_CR4_PAE_BIT), %eax - movl %eax, %cr4 - - movl %cr3, %eax - movl %eax, %cr3 - - movl $MSR_EFER, %ecx - rdmsr - btsl $_EFER_LME, %eax - wrmsr - - xorl %eax, %eax - lldt %ax - - pushl $__KERNEL_CS - pushl %ebp - - /* Enable paging */ - movl %cr0, %eax - btsl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - lret -SYM_FUNC_END(efi_enter32) - - .data - .balign 8 -SYM_DATA_START(efi32_boot_gdt) - .word 0 - .quad 0 -SYM_DATA_END(efi32_boot_gdt) - -SYM_DATA_START(efi32_boot_idt) - .word 0 - .quad 0 -SYM_DATA_END(efi32_boot_idt) - -SYM_DATA_START(efi32_boot_cs) - .word 0 -SYM_DATA_END(efi32_boot_cs) - -SYM_DATA_START(efi32_boot_ds) - .word 0 -SYM_DATA_END(efi32_boot_ds) diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S index 3b354eb9516d..6589ddd4cfaf 100644 --- a/arch/x86/boot/compressed/head_32.S +++ b/arch/x86/boot/compressed/head_32.S @@ -208,10 +208,6 @@ SYM_DATA_START_LOCAL(gdt) .quad 0x00cf92000000ffff /* __KERNEL_DS */ SYM_DATA_END_LABEL(gdt, SYM_L_LOCAL, gdt_end) -#ifdef CONFIG_EFI_STUB -SYM_DATA(image_offset, .long 0) -#endif - /* * Stack and heap for uncompression */ diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S index d33f060900d2..a75712991df3 100644 --- a/arch/x86/boot/compressed/head_64.S +++ b/arch/x86/boot/compressed/head_64.S @@ -38,6 +38,14 @@ #include "pgtable.h" /* + * Fix alignment at 16 bytes. Following CONFIG_FUNCTION_ALIGNMENT will result + * in assembly errors due to trying to move .org backward due to the excessive + * alignment. + */ +#undef __ALIGN +#define __ALIGN .balign 16, 0x90 + +/* * Locally defined symbols should be marked hidden: */ .hidden _bss @@ -118,7 +126,9 @@ SYM_FUNC_START(startup_32) 1: /* Setup Exception handling for SEV-ES */ +#ifdef CONFIG_AMD_MEM_ENCRYPT call startup32_load_idt +#endif /* Make sure cpu supports long mode. */ call verify_cpu @@ -178,12 +188,13 @@ SYM_FUNC_START(startup_32) */ /* * If SEV is active then set the encryption mask in the page tables. - * This will insure that when the kernel is copied and decompressed + * This will ensure that when the kernel is copied and decompressed * it will be done so encrypted. */ - call get_sev_encryption_bit xorl %edx, %edx #ifdef CONFIG_AMD_MEM_ENCRYPT + call get_sev_encryption_bit + xorl %edx, %edx testl %eax, %eax jz 1f subl $32, %eax /* Encryption bit is always above bit 31 */ @@ -249,6 +260,11 @@ SYM_FUNC_START(startup_32) movl $__BOOT_TSS, %eax ltr %ax +#ifdef CONFIG_AMD_MEM_ENCRYPT + /* Check if the C-bit position is correct when SEV is active */ + call startup32_check_sev_cbit +#endif + /* * Setup for the jump to 64bit mode * @@ -261,29 +277,11 @@ SYM_FUNC_START(startup_32) */ leal rva(startup_64)(%ebp), %eax #ifdef CONFIG_EFI_MIXED - movl rva(efi32_boot_args)(%ebp), %edi - testl %edi, %edi - jz 1f - leal rva(efi64_stub_entry)(%ebp), %eax - movl rva(efi32_boot_args+4)(%ebp), %esi - movl rva(efi32_boot_args+8)(%ebp), %edx // saved bootparams pointer - testl %edx, %edx - jnz 1f - /* - * efi_pe_entry uses MS calling convention, which requires 32 bytes of - * shadow space on the stack even if all arguments are passed in - * registers. We also need an additional 8 bytes for the space that - * would be occupied by the return address, and this also results in - * the correct stack alignment for entry. - */ - subl $40, %esp - leal rva(efi_pe_entry)(%ebp), %eax - movl %edi, %ecx // MS calling convention - movl %esi, %edx + cmpb $1, rva(efi_is64)(%ebp) + je 1f + leal rva(startup_64_mixed_mode)(%ebp), %eax 1: #endif - /* Check if the C-bit position is correct when SEV is active */ - call startup32_check_sev_cbit pushl $__KERNEL_CS pushl %eax @@ -296,38 +294,14 @@ SYM_FUNC_START(startup_32) lret SYM_FUNC_END(startup_32) -#ifdef CONFIG_EFI_MIXED +#if IS_ENABLED(CONFIG_EFI_MIXED) && IS_ENABLED(CONFIG_EFI_HANDOVER_PROTOCOL) .org 0x190 SYM_FUNC_START(efi32_stub_entry) add $0x4, %esp /* Discard return address */ popl %ecx popl %edx popl %esi - - call 1f -1: pop %ebp - subl $ rva(1b), %ebp - - movl %esi, rva(efi32_boot_args+8)(%ebp) -SYM_INNER_LABEL(efi32_pe_stub_entry, SYM_L_LOCAL) - movl %ecx, rva(efi32_boot_args)(%ebp) - movl %edx, rva(efi32_boot_args+4)(%ebp) - movb $0, rva(efi_is64)(%ebp) - - /* Save firmware GDTR and code/data selectors */ - sgdtl rva(efi32_boot_gdt)(%ebp) - movw %cs, rva(efi32_boot_cs)(%ebp) - movw %ds, rva(efi32_boot_ds)(%ebp) - - /* Store firmware IDT descriptor */ - sidtl rva(efi32_boot_idt)(%ebp) - - /* Disable paging */ - movl %cr0, %eax - btrl $X86_CR0_PG_BIT, %eax - movl %eax, %cr0 - - jmp startup_32 + jmp efi32_entry SYM_FUNC_END(efi32_stub_entry) #endif @@ -550,7 +524,9 @@ trampoline_return: SYM_CODE_END(startup_64) #ifdef CONFIG_EFI_STUB +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL .org 0x390 +#endif SYM_FUNC_START(efi64_stub_entry) and $~0xf, %rsp /* realign the stack */ movq %rdx, %rbx /* save boot_params pointer */ @@ -713,6 +689,7 @@ SYM_FUNC_START_LOCAL_NOALIGN(.Lno_longmode) jmp 1b SYM_FUNC_END(.Lno_longmode) + .globl verify_cpu #include "../../kernel/verify_cpu.S" .data @@ -744,242 +721,6 @@ SYM_DATA_START(boot_idt) .endr SYM_DATA_END_LABEL(boot_idt, SYM_L_GLOBAL, boot_idt_end) -#ifdef CONFIG_AMD_MEM_ENCRYPT -SYM_DATA_START(boot32_idt_desc) - .word boot32_idt_end - boot32_idt - 1 - .long 0 -SYM_DATA_END(boot32_idt_desc) - .balign 8 -SYM_DATA_START(boot32_idt) - .rept 32 - .quad 0 - .endr -SYM_DATA_END_LABEL(boot32_idt, SYM_L_GLOBAL, boot32_idt_end) -#endif - -#ifdef CONFIG_EFI_STUB -SYM_DATA(image_offset, .long 0) -#endif -#ifdef CONFIG_EFI_MIXED -SYM_DATA_LOCAL(efi32_boot_args, .long 0, 0, 0) -SYM_DATA(efi_is64, .byte 1) - -#define ST32_boottime 60 // offsetof(efi_system_table_32_t, boottime) -#define BS32_handle_protocol 88 // offsetof(efi_boot_services_32_t, handle_protocol) -#define LI32_image_base 32 // offsetof(efi_loaded_image_32_t, image_base) - - __HEAD - .code32 -SYM_FUNC_START(efi32_pe_entry) -/* - * efi_status_t efi32_pe_entry(efi_handle_t image_handle, - * efi_system_table_32_t *sys_table) - */ - - pushl %ebp - movl %esp, %ebp - pushl %eax // dummy push to allocate loaded_image - - pushl %ebx // save callee-save registers - pushl %edi - - call verify_cpu // check for long mode support - testl %eax, %eax - movl $0x80000003, %eax // EFI_UNSUPPORTED - jnz 2f - - call 1f -1: pop %ebx - subl $ rva(1b), %ebx - - /* Get the loaded image protocol pointer from the image handle */ - leal -4(%ebp), %eax - pushl %eax // &loaded_image - leal rva(loaded_image_proto)(%ebx), %eax - pushl %eax // pass the GUID address - pushl 8(%ebp) // pass the image handle - - /* - * Note the alignment of the stack frame. - * sys_table - * handle <-- 16-byte aligned on entry by ABI - * return address - * frame pointer - * loaded_image <-- local variable - * saved %ebx <-- 16-byte aligned here - * saved %edi - * &loaded_image - * &loaded_image_proto - * handle <-- 16-byte aligned for call to handle_protocol - */ - - movl 12(%ebp), %eax // sys_table - movl ST32_boottime(%eax), %eax // sys_table->boottime - call *BS32_handle_protocol(%eax) // sys_table->boottime->handle_protocol - addl $12, %esp // restore argument space - testl %eax, %eax - jnz 2f - - movl 8(%ebp), %ecx // image_handle - movl 12(%ebp), %edx // sys_table - movl -4(%ebp), %esi // loaded_image - movl LI32_image_base(%esi), %esi // loaded_image->image_base - movl %ebx, %ebp // startup_32 for efi32_pe_stub_entry - /* - * We need to set the image_offset variable here since startup_32() will - * use it before we get to the 64-bit efi_pe_entry() in C code. - */ - subl %esi, %ebx - movl %ebx, rva(image_offset)(%ebp) // save image_offset - jmp efi32_pe_stub_entry - -2: popl %edi // restore callee-save registers - popl %ebx - leave - RET -SYM_FUNC_END(efi32_pe_entry) - - .section ".rodata" - /* EFI loaded image protocol GUID */ - .balign 4 -SYM_DATA_START_LOCAL(loaded_image_proto) - .long 0x5b1b31a1 - .word 0x9562, 0x11d2 - .byte 0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b -SYM_DATA_END(loaded_image_proto) -#endif - -#ifdef CONFIG_AMD_MEM_ENCRYPT - __HEAD - .code32 -/* - * Write an IDT entry into boot32_idt - * - * Parameters: - * - * %eax: Handler address - * %edx: Vector number - * - * Physical offset is expected in %ebp - */ -SYM_FUNC_START(startup32_set_idt_entry) - push %ebx - push %ecx - - /* IDT entry address to %ebx */ - leal rva(boot32_idt)(%ebp), %ebx - shl $3, %edx - addl %edx, %ebx - - /* Build IDT entry, lower 4 bytes */ - movl %eax, %edx - andl $0x0000ffff, %edx # Target code segment offset [15:0] - movl $__KERNEL32_CS, %ecx # Target code segment selector - shl $16, %ecx - orl %ecx, %edx - - /* Store lower 4 bytes to IDT */ - movl %edx, (%ebx) - - /* Build IDT entry, upper 4 bytes */ - movl %eax, %edx - andl $0xffff0000, %edx # Target code segment offset [31:16] - orl $0x00008e00, %edx # Present, Type 32-bit Interrupt Gate - - /* Store upper 4 bytes to IDT */ - movl %edx, 4(%ebx) - - pop %ecx - pop %ebx - RET -SYM_FUNC_END(startup32_set_idt_entry) -#endif - -SYM_FUNC_START(startup32_load_idt) -#ifdef CONFIG_AMD_MEM_ENCRYPT - /* #VC handler */ - leal rva(startup32_vc_handler)(%ebp), %eax - movl $X86_TRAP_VC, %edx - call startup32_set_idt_entry - - /* Load IDT */ - leal rva(boot32_idt)(%ebp), %eax - movl %eax, rva(boot32_idt_desc+2)(%ebp) - lidt rva(boot32_idt_desc)(%ebp) -#endif - RET -SYM_FUNC_END(startup32_load_idt) - -/* - * Check for the correct C-bit position when the startup_32 boot-path is used. - * - * The check makes use of the fact that all memory is encrypted when paging is - * disabled. The function creates 64 bits of random data using the RDRAND - * instruction. RDRAND is mandatory for SEV guests, so always available. If the - * hypervisor violates that the kernel will crash right here. - * - * The 64 bits of random data are stored to a memory location and at the same - * time kept in the %eax and %ebx registers. Since encryption is always active - * when paging is off the random data will be stored encrypted in main memory. - * - * Then paging is enabled. When the C-bit position is correct all memory is - * still mapped encrypted and comparing the register values with memory will - * succeed. An incorrect C-bit position will map all memory unencrypted, so that - * the compare will use the encrypted random data and fail. - */ -SYM_FUNC_START(startup32_check_sev_cbit) -#ifdef CONFIG_AMD_MEM_ENCRYPT - pushl %eax - pushl %ebx - pushl %ecx - pushl %edx - - /* Check for non-zero sev_status */ - movl rva(sev_status)(%ebp), %eax - testl %eax, %eax - jz 4f - - /* - * Get two 32-bit random values - Don't bail out if RDRAND fails - * because it is better to prevent forward progress if no random value - * can be gathered. - */ -1: rdrand %eax - jnc 1b -2: rdrand %ebx - jnc 2b - - /* Store to memory and keep it in the registers */ - movl %eax, rva(sev_check_data)(%ebp) - movl %ebx, rva(sev_check_data+4)(%ebp) - - /* Enable paging to see if encryption is active */ - movl %cr0, %edx /* Backup %cr0 in %edx */ - movl $(X86_CR0_PG | X86_CR0_PE), %ecx /* Enable Paging and Protected mode */ - movl %ecx, %cr0 - - cmpl %eax, rva(sev_check_data)(%ebp) - jne 3f - cmpl %ebx, rva(sev_check_data+4)(%ebp) - jne 3f - - movl %edx, %cr0 /* Restore previous %cr0 */ - - jmp 4f - -3: /* Check failed - hlt the machine */ - hlt - jmp 3b - -4: - popl %edx - popl %ecx - popl %ebx - popl %eax -#endif - RET -SYM_FUNC_END(startup32_check_sev_cbit) - /* * Stack and heap for uncompression */ diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index e476bcbd9b42..454757fbdfe5 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -668,7 +668,7 @@ static bool process_mem_region(struct mem_vector *region, } } #endif - return 0; + return false; } #ifdef CONFIG_EFI diff --git a/arch/x86/boot/compressed/mem_encrypt.S b/arch/x86/boot/compressed/mem_encrypt.S index a73e4d783cae..32f7cc8a8625 100644 --- a/arch/x86/boot/compressed/mem_encrypt.S +++ b/arch/x86/boot/compressed/mem_encrypt.S @@ -12,16 +12,13 @@ #include <asm/processor-flags.h> #include <asm/msr.h> #include <asm/asm-offsets.h> +#include <asm/segment.h> +#include <asm/trapnr.h> .text .code32 SYM_FUNC_START(get_sev_encryption_bit) - xor %eax, %eax - -#ifdef CONFIG_AMD_MEM_ENCRYPT push %ebx - push %ecx - push %edx movl $0x80000000, %eax /* CPUID to check the highest leaf */ cpuid @@ -52,12 +49,7 @@ SYM_FUNC_START(get_sev_encryption_bit) xor %eax, %eax .Lsev_exit: - pop %edx - pop %ecx pop %ebx - -#endif /* CONFIG_AMD_MEM_ENCRYPT */ - RET SYM_FUNC_END(get_sev_encryption_bit) @@ -98,7 +90,7 @@ SYM_CODE_START_LOCAL(sev_es_req_cpuid) jmp 1b SYM_CODE_END(sev_es_req_cpuid) -SYM_CODE_START(startup32_vc_handler) +SYM_CODE_START_LOCAL(startup32_vc_handler) pushl %eax pushl %ebx pushl %ecx @@ -184,15 +176,149 @@ SYM_CODE_START(startup32_vc_handler) jmp .Lfail SYM_CODE_END(startup32_vc_handler) +/* + * Write an IDT entry into boot32_idt + * + * Parameters: + * + * %eax: Handler address + * %edx: Vector number + * %ecx: IDT address + */ +SYM_FUNC_START_LOCAL(startup32_set_idt_entry) + /* IDT entry address to %ecx */ + leal (%ecx, %edx, 8), %ecx + + /* Build IDT entry, lower 4 bytes */ + movl %eax, %edx + andl $0x0000ffff, %edx # Target code segment offset [15:0] + orl $(__KERNEL32_CS << 16), %edx # Target code segment selector + + /* Store lower 4 bytes to IDT */ + movl %edx, (%ecx) + + /* Build IDT entry, upper 4 bytes */ + movl %eax, %edx + andl $0xffff0000, %edx # Target code segment offset [31:16] + orl $0x00008e00, %edx # Present, Type 32-bit Interrupt Gate + + /* Store upper 4 bytes to IDT */ + movl %edx, 4(%ecx) + + RET +SYM_FUNC_END(startup32_set_idt_entry) + +SYM_FUNC_START(startup32_load_idt) + push %ebp + push %ebx + + call 1f +1: pop %ebp + + leal (boot32_idt - 1b)(%ebp), %ebx + + /* #VC handler */ + leal (startup32_vc_handler - 1b)(%ebp), %eax + movl $X86_TRAP_VC, %edx + movl %ebx, %ecx + call startup32_set_idt_entry + + /* Load IDT */ + leal (boot32_idt_desc - 1b)(%ebp), %ecx + movl %ebx, 2(%ecx) + lidt (%ecx) + + pop %ebx + pop %ebp + RET +SYM_FUNC_END(startup32_load_idt) + +/* + * Check for the correct C-bit position when the startup_32 boot-path is used. + * + * The check makes use of the fact that all memory is encrypted when paging is + * disabled. The function creates 64 bits of random data using the RDRAND + * instruction. RDRAND is mandatory for SEV guests, so always available. If the + * hypervisor violates that the kernel will crash right here. + * + * The 64 bits of random data are stored to a memory location and at the same + * time kept in the %eax and %ebx registers. Since encryption is always active + * when paging is off the random data will be stored encrypted in main memory. + * + * Then paging is enabled. When the C-bit position is correct all memory is + * still mapped encrypted and comparing the register values with memory will + * succeed. An incorrect C-bit position will map all memory unencrypted, so that + * the compare will use the encrypted random data and fail. + */ +SYM_FUNC_START(startup32_check_sev_cbit) + pushl %ebx + pushl %ebp + + call 0f +0: popl %ebp + + /* Check for non-zero sev_status */ + movl (sev_status - 0b)(%ebp), %eax + testl %eax, %eax + jz 4f + + /* + * Get two 32-bit random values - Don't bail out if RDRAND fails + * because it is better to prevent forward progress if no random value + * can be gathered. + */ +1: rdrand %eax + jnc 1b +2: rdrand %ebx + jnc 2b + + /* Store to memory and keep it in the registers */ + leal (sev_check_data - 0b)(%ebp), %ebp + movl %eax, 0(%ebp) + movl %ebx, 4(%ebp) + + /* Enable paging to see if encryption is active */ + movl %cr0, %edx /* Backup %cr0 in %edx */ + movl $(X86_CR0_PG | X86_CR0_PE), %ecx /* Enable Paging and Protected mode */ + movl %ecx, %cr0 + + cmpl %eax, 0(%ebp) + jne 3f + cmpl %ebx, 4(%ebp) + jne 3f + + movl %edx, %cr0 /* Restore previous %cr0 */ + + jmp 4f + +3: /* Check failed - hlt the machine */ + hlt + jmp 3b + +4: + popl %ebp + popl %ebx + RET +SYM_FUNC_END(startup32_check_sev_cbit) + .code64 #include "../../kernel/sev_verify_cbit.S" .data -#ifdef CONFIG_AMD_MEM_ENCRYPT .balign 8 SYM_DATA(sme_me_mask, .quad 0) SYM_DATA(sev_status, .quad 0) SYM_DATA(sev_check_data, .quad 0) -#endif + +SYM_DATA_START_LOCAL(boot32_idt) + .rept 32 + .quad 0 + .endr +SYM_DATA_END(boot32_idt) + +SYM_DATA_START_LOCAL(boot32_idt_desc) + .word . - boot32_idt - 1 + .long 0 +SYM_DATA_END(boot32_idt_desc) diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c index a83d67ec627d..d75237ba7ce9 100644 --- a/arch/x86/boot/cpuflags.c +++ b/arch/x86/boot/cpuflags.c @@ -64,20 +64,11 @@ int has_eflag(unsigned long mask) return !!((f0^f1) & mask); } -/* Handle x86_32 PIC using ebx. */ -#if defined(__i386__) && defined(__PIC__) -# define EBX_REG "=r" -#else -# define EBX_REG "=b" -#endif - void cpuid_count(u32 id, u32 count, u32 *a, u32 *b, u32 *c, u32 *d) { - asm volatile(".ifnc %%ebx,%3 ; movl %%ebx,%3 ; .endif \n\t" - "cpuid \n\t" - ".ifnc %%ebx,%3 ; xchgl %%ebx,%3 ; .endif \n\t" - : "=a" (*a), "=c" (*c), "=d" (*d), EBX_REG (*b) - : "a" (id), "c" (count) + asm volatile("cpuid" + : "=a" (*a), "=b" (*b), "=c" (*c), "=d" (*d) + : "0" (id), "2" (count) ); } diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index f912d7770130..9338c68e7413 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -80,10 +80,11 @@ bs_die: ljmp $0xf000,$0xfff0 #ifdef CONFIG_EFI_STUB - .org 0x3c + .org 0x38 # # Offset to the PE header. # + .long LINUX_PE_MAGIC .long pe_header #endif /* CONFIG_EFI_STUB */ @@ -406,7 +407,7 @@ xloadflags: # define XLF1 0 #endif -#ifdef CONFIG_EFI_STUB +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL # ifdef CONFIG_EFI_MIXED # define XLF23 (XLF_EFI_HANDOVER_32|XLF_EFI_HANDOVER_64) # else diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 8a3fff9128bb..1c8541ae3b3a 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -350,7 +350,7 @@ static int _kstrtoul(const char *s, unsigned int base, unsigned long *res) } /** - * kstrtoul - convert a string to an unsigned long + * boot_kstrtoul - convert a string to an unsigned long * @s: The start of the string. The string must be null-terminated, and may also * include a single newline before its terminating null. The first character * may also be a plus sign, but not a minus sign. diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index a3725ad46c5a..bd247692b701 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -290,6 +290,7 @@ static void efi_stub_entry_update(void) { unsigned long addr = efi32_stub_entry; +#ifdef CONFIG_EFI_HANDOVER_PROTOCOL #ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */ addr = efi64_stub_entry - 0x200; @@ -299,6 +300,7 @@ static void efi_stub_entry_update(void) if (efi32_stub_entry != addr) die("32-bit and 64-bit EFI entry points do not match\n"); #endif +#endif put_unaligned_le32(addr, &buf[0x264]); } diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index b8998cf0508a..cfd4c95b9f04 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -5,6 +5,8 @@ #define pr_fmt(fmt) "tdx: " fmt #include <linux/cpufeature.h> +#include <linux/export.h> +#include <linux/io.h> #include <asm/coco.h> #include <asm/tdx.h> #include <asm/vmx.h> @@ -15,6 +17,7 @@ /* TDX module Call Leaf IDs */ #define TDX_GET_INFO 1 #define TDX_GET_VEINFO 3 +#define TDX_GET_REPORT 4 #define TDX_ACCEPT_PAGE 6 /* TDX hypercall Leaf IDs */ @@ -36,6 +39,12 @@ #define ATTR_SEPT_VE_DISABLE BIT(28) +/* TDX Module call error codes */ +#define TDCALL_RETURN_CODE(a) ((a) >> 32) +#define TDCALL_INVALID_OPERAND 0xc0000100 + +#define TDREPORT_SUBTYPE_0 0 + /* * Wrapper for standard use of __tdx_hypercall with no output aside from * return code. @@ -100,6 +109,37 @@ static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, panic("TDCALL %lld failed (Buggy TDX module!)\n", fn); } +/** + * tdx_mcall_get_report0() - Wrapper to get TDREPORT0 (a.k.a. TDREPORT + * subtype 0) using TDG.MR.REPORT TDCALL. + * @reportdata: Address of the input buffer which contains user-defined + * REPORTDATA to be included into TDREPORT. + * @tdreport: Address of the output buffer to store TDREPORT. + * + * Refer to section titled "TDG.MR.REPORT leaf" in the TDX Module + * v1.0 specification for more information on TDG.MR.REPORT TDCALL. + * It is used in the TDX guest driver module to get the TDREPORT0. + * + * Return 0 on success, -EINVAL for invalid operands, or -EIO on + * other TDCALL failures. + */ +int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport) +{ + u64 ret; + + ret = __tdx_module_call(TDX_GET_REPORT, virt_to_phys(tdreport), + virt_to_phys(reportdata), TDREPORT_SUBTYPE_0, + 0, NULL); + if (ret) { + if (TDCALL_RETURN_CODE(ret) == TDCALL_INVALID_OPERAND) + return -EINVAL; + return -EIO; + } + + return 0; +} +EXPORT_SYMBOL_GPL(tdx_mcall_get_report0); + static void tdx_parse_tdinfo(u64 *cc_mask) { struct tdx_module_output out; diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 3b1d701a4f6c..3e7a329235bd 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -107,3 +107,6 @@ quiet_cmd_perlasm = PERLASM $@ cmd_perlasm = $(PERL) $< > $@ $(obj)/%.S: $(src)/%.pl FORCE $(call if_changed,perlasm) + +# Disable GCOV in odd or sensitive code +GCOV_PROFILE_curve25519-x86_64.o := n diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S index b48ddebb4748..cdf3215ec272 100644 --- a/arch/x86/crypto/aegis128-aesni-asm.S +++ b/arch/x86/crypto/aegis128-aesni-asm.S @@ -7,6 +7,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/frame.h> #define STATE0 %xmm0 @@ -402,7 +403,7 @@ SYM_FUNC_END(crypto_aegis128_aesni_ad) * void crypto_aegis128_aesni_enc(void *state, unsigned int length, * const void *src, void *dst); */ -SYM_FUNC_START(crypto_aegis128_aesni_enc) +SYM_TYPED_FUNC_START(crypto_aegis128_aesni_enc) FRAME_BEGIN cmp $0x10, LEN @@ -499,7 +500,7 @@ SYM_FUNC_END(crypto_aegis128_aesni_enc) * void crypto_aegis128_aesni_enc_tail(void *state, unsigned int length, * const void *src, void *dst); */ -SYM_FUNC_START(crypto_aegis128_aesni_enc_tail) +SYM_TYPED_FUNC_START(crypto_aegis128_aesni_enc_tail) FRAME_BEGIN /* load the state: */ @@ -556,7 +557,7 @@ SYM_FUNC_END(crypto_aegis128_aesni_enc_tail) * void crypto_aegis128_aesni_dec(void *state, unsigned int length, * const void *src, void *dst); */ -SYM_FUNC_START(crypto_aegis128_aesni_dec) +SYM_TYPED_FUNC_START(crypto_aegis128_aesni_dec) FRAME_BEGIN cmp $0x10, LEN @@ -653,7 +654,7 @@ SYM_FUNC_END(crypto_aegis128_aesni_dec) * void crypto_aegis128_aesni_dec_tail(void *state, unsigned int length, * const void *src, void *dst); */ -SYM_FUNC_START(crypto_aegis128_aesni_dec_tail) +SYM_TYPED_FUNC_START(crypto_aegis128_aesni_dec_tail) FRAME_BEGIN /* load the state: */ diff --git a/arch/x86/crypto/aria-aesni-avx-asm_64.S b/arch/x86/crypto/aria-aesni-avx-asm_64.S index c75fd7d015ed..03ae4cd1d976 100644 --- a/arch/x86/crypto/aria-aesni-avx-asm_64.S +++ b/arch/x86/crypto/aria-aesni-avx-asm_64.S @@ -7,6 +7,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/frame.h> /* struct aria_ctx: */ @@ -913,7 +914,7 @@ SYM_FUNC_START_LOCAL(__aria_aesni_avx_crypt_16way) RET; SYM_FUNC_END(__aria_aesni_avx_crypt_16way) -SYM_FUNC_START(aria_aesni_avx_encrypt_16way) +SYM_TYPED_FUNC_START(aria_aesni_avx_encrypt_16way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -938,7 +939,7 @@ SYM_FUNC_START(aria_aesni_avx_encrypt_16way) RET; SYM_FUNC_END(aria_aesni_avx_encrypt_16way) -SYM_FUNC_START(aria_aesni_avx_decrypt_16way) +SYM_TYPED_FUNC_START(aria_aesni_avx_decrypt_16way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -1039,7 +1040,7 @@ SYM_FUNC_START_LOCAL(__aria_aesni_avx_ctr_gen_keystream_16way) RET; SYM_FUNC_END(__aria_aesni_avx_ctr_gen_keystream_16way) -SYM_FUNC_START(aria_aesni_avx_ctr_crypt_16way) +SYM_TYPED_FUNC_START(aria_aesni_avx_ctr_crypt_16way) /* input: * %rdi: ctx * %rsi: dst @@ -1208,7 +1209,7 @@ SYM_FUNC_START_LOCAL(__aria_aesni_avx_gfni_crypt_16way) RET; SYM_FUNC_END(__aria_aesni_avx_gfni_crypt_16way) -SYM_FUNC_START(aria_aesni_avx_gfni_encrypt_16way) +SYM_TYPED_FUNC_START(aria_aesni_avx_gfni_encrypt_16way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -1233,7 +1234,7 @@ SYM_FUNC_START(aria_aesni_avx_gfni_encrypt_16way) RET; SYM_FUNC_END(aria_aesni_avx_gfni_encrypt_16way) -SYM_FUNC_START(aria_aesni_avx_gfni_decrypt_16way) +SYM_TYPED_FUNC_START(aria_aesni_avx_gfni_decrypt_16way) /* input: * %rdi: ctx, CTX * %rsi: dst @@ -1258,7 +1259,7 @@ SYM_FUNC_START(aria_aesni_avx_gfni_decrypt_16way) RET; SYM_FUNC_END(aria_aesni_avx_gfni_decrypt_16way) -SYM_FUNC_START(aria_aesni_avx_gfni_ctr_crypt_16way) +SYM_TYPED_FUNC_START(aria_aesni_avx_gfni_ctr_crypt_16way) /* input: * %rdi: ctx * %rsi: dst diff --git a/arch/x86/crypto/camellia-aesni-avx-asm_64.S b/arch/x86/crypto/camellia-aesni-avx-asm_64.S index 2e1658ddbe1a..4a30618281ec 100644 --- a/arch/x86/crypto/camellia-aesni-avx-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx-asm_64.S @@ -712,7 +712,6 @@ SYM_FUNC_END(roundsm16_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) .text -.align 8 SYM_FUNC_START_LOCAL(__camellia_enc_blk16) /* input: * %rdi: ctx, CTX @@ -799,7 +798,6 @@ SYM_FUNC_START_LOCAL(__camellia_enc_blk16) jmp .Lenc_done; SYM_FUNC_END(__camellia_enc_blk16) -.align 8 SYM_FUNC_START_LOCAL(__camellia_dec_blk16) /* input: * %rdi: ctx, CTX diff --git a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S index 0e4e9abbf4de..deaf62aa73a6 100644 --- a/arch/x86/crypto/camellia-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/camellia-aesni-avx2-asm_64.S @@ -221,7 +221,6 @@ * Size optimization... with inlined roundsm32 binary would be over 5 times * larger and would only marginally faster. */ -.align 8 SYM_FUNC_START_LOCAL(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd) roundsm32(%ymm0, %ymm1, %ymm2, %ymm3, %ymm4, %ymm5, %ymm6, %ymm7, %ymm8, %ymm9, %ymm10, %ymm11, %ymm12, %ymm13, %ymm14, %ymm15, @@ -229,7 +228,6 @@ SYM_FUNC_START_LOCAL(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_c RET; SYM_FUNC_END(roundsm32_x0_x1_x2_x3_x4_x5_x6_x7_y0_y1_y2_y3_y4_y5_y6_y7_cd) -.align 8 SYM_FUNC_START_LOCAL(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) roundsm32(%ymm4, %ymm5, %ymm6, %ymm7, %ymm0, %ymm1, %ymm2, %ymm3, %ymm12, %ymm13, %ymm14, %ymm15, %ymm8, %ymm9, %ymm10, %ymm11, @@ -748,7 +746,6 @@ SYM_FUNC_END(roundsm32_x4_x5_x6_x7_x0_x1_x2_x3_y4_y5_y6_y7_y0_y1_y2_y3_ab) .text -.align 8 SYM_FUNC_START_LOCAL(__camellia_enc_blk32) /* input: * %rdi: ctx, CTX @@ -835,7 +832,6 @@ SYM_FUNC_START_LOCAL(__camellia_enc_blk32) jmp .Lenc_done; SYM_FUNC_END(__camellia_enc_blk32) -.align 8 SYM_FUNC_START_LOCAL(__camellia_dec_blk32) /* input: * %rdi: ctx, CTX diff --git a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S index b258af420c92..0326a01503c3 100644 --- a/arch/x86/crypto/cast5-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/cast5-avx-x86_64-asm_64.S @@ -208,7 +208,6 @@ .text -.align 16 SYM_FUNC_START_LOCAL(__cast5_enc_blk16) /* input: * %rdi: ctx @@ -282,7 +281,6 @@ SYM_FUNC_START_LOCAL(__cast5_enc_blk16) RET; SYM_FUNC_END(__cast5_enc_blk16) -.align 16 SYM_FUNC_START_LOCAL(__cast5_dec_blk16) /* input: * %rdi: ctx diff --git a/arch/x86/crypto/crct10dif-pcl-asm_64.S b/arch/x86/crypto/crct10dif-pcl-asm_64.S index 721474abfb71..5286db5b8165 100644 --- a/arch/x86/crypto/crct10dif-pcl-asm_64.S +++ b/arch/x86/crypto/crct10dif-pcl-asm_64.S @@ -94,7 +94,6 @@ # # Assumes len >= 16. # -.align 16 SYM_FUNC_START(crc_t10dif_pcl) movdqa .Lbswap_mask(%rip), BSWAP_MASK diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S index 6a0b15e7196a..ef73a3ab8726 100644 --- a/arch/x86/crypto/nh-avx2-x86_64.S +++ b/arch/x86/crypto/nh-avx2-x86_64.S @@ -8,6 +8,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #define PASS0_SUMS %ymm0 #define PASS1_SUMS %ymm1 @@ -65,11 +66,11 @@ /* * void nh_avx2(const u32 *key, const u8 *message, size_t message_len, - * u8 hash[NH_HASH_BYTES]) + * __le64 hash[NH_NUM_PASSES]) * * It's guaranteed that message_len % 16 == 0. */ -SYM_FUNC_START(nh_avx2) +SYM_TYPED_FUNC_START(nh_avx2) vmovdqu 0x00(KEY), K0 vmovdqu 0x10(KEY), K1 diff --git a/arch/x86/crypto/nh-sse2-x86_64.S b/arch/x86/crypto/nh-sse2-x86_64.S index 34c567bbcb4f..75fb994b6d17 100644 --- a/arch/x86/crypto/nh-sse2-x86_64.S +++ b/arch/x86/crypto/nh-sse2-x86_64.S @@ -8,6 +8,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #define PASS0_SUMS %xmm0 #define PASS1_SUMS %xmm1 @@ -67,11 +68,11 @@ /* * void nh_sse2(const u32 *key, const u8 *message, size_t message_len, - * u8 hash[NH_HASH_BYTES]) + * __le64 hash[NH_NUM_PASSES]) * * It's guaranteed that message_len % 16 == 0. */ -SYM_FUNC_START(nh_sse2) +SYM_TYPED_FUNC_START(nh_sse2) movdqu 0x00(KEY), K0 movdqu 0x10(KEY), K1 diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c index 8ea5ab0f1ca7..46b036204ed9 100644 --- a/arch/x86/crypto/nhpoly1305-avx2-glue.c +++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c @@ -14,14 +14,7 @@ #include <asm/simd.h> asmlinkage void nh_avx2(const u32 *key, const u8 *message, size_t message_len, - u8 hash[NH_HASH_BYTES]); - -/* wrapper to avoid indirect call to assembly, which doesn't work with CFI */ -static void _nh_avx2(const u32 *key, const u8 *message, size_t message_len, - __le64 hash[NH_NUM_PASSES]) -{ - nh_avx2(key, message, message_len, (u8 *)hash); -} + __le64 hash[NH_NUM_PASSES]); static int nhpoly1305_avx2_update(struct shash_desc *desc, const u8 *src, unsigned int srclen) @@ -33,7 +26,7 @@ static int nhpoly1305_avx2_update(struct shash_desc *desc, unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); - crypto_nhpoly1305_update_helper(desc, src, n, _nh_avx2); + crypto_nhpoly1305_update_helper(desc, src, n, nh_avx2); kernel_fpu_end(); src += n; srclen -= n; diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c index 2b353d42ed13..4a4970d75107 100644 --- a/arch/x86/crypto/nhpoly1305-sse2-glue.c +++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c @@ -14,14 +14,7 @@ #include <asm/simd.h> asmlinkage void nh_sse2(const u32 *key, const u8 *message, size_t message_len, - u8 hash[NH_HASH_BYTES]); - -/* wrapper to avoid indirect call to assembly, which doesn't work with CFI */ -static void _nh_sse2(const u32 *key, const u8 *message, size_t message_len, - __le64 hash[NH_NUM_PASSES]) -{ - nh_sse2(key, message, message_len, (u8 *)hash); -} + __le64 hash[NH_NUM_PASSES]); static int nhpoly1305_sse2_update(struct shash_desc *desc, const u8 *src, unsigned int srclen) @@ -33,7 +26,7 @@ static int nhpoly1305_sse2_update(struct shash_desc *desc, unsigned int n = min_t(unsigned int, srclen, SZ_4K); kernel_fpu_begin(); - crypto_nhpoly1305_update_helper(desc, src, n, _nh_sse2); + crypto_nhpoly1305_update_helper(desc, src, n, nh_sse2); kernel_fpu_end(); src += n; srclen -= n; diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl index 2077ce7a5647..b9abcd79c1f4 100644 --- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl +++ b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl @@ -108,7 +108,6 @@ if (!$kernel) { sub declare_function() { my ($name, $align, $nargs) = @_; if($kernel) { - $code .= ".align $align\n"; $code .= "SYM_FUNC_START($name)\n"; $code .= ".L$name:\n"; } else { diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S index 82f2313f512b..97e283621851 100644 --- a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S @@ -550,7 +550,6 @@ #define write_blocks(x0, x1, x2, x3, t0, t1, t2) \ transpose_4x4(x0, x1, x2, x3, t0, t1, t2) -.align 8 SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx) /* input: * %rdi: ctx, CTX @@ -604,7 +603,6 @@ SYM_FUNC_START_LOCAL(__serpent_enc_blk8_avx) RET; SYM_FUNC_END(__serpent_enc_blk8_avx) -.align 8 SYM_FUNC_START_LOCAL(__serpent_dec_blk8_avx) /* input: * %rdi: ctx, CTX diff --git a/arch/x86/crypto/serpent-avx2-asm_64.S b/arch/x86/crypto/serpent-avx2-asm_64.S index 8ea34c9b9316..6d60c50593a9 100644 --- a/arch/x86/crypto/serpent-avx2-asm_64.S +++ b/arch/x86/crypto/serpent-avx2-asm_64.S @@ -550,7 +550,6 @@ #define write_blocks(x0, x1, x2, x3, t0, t1, t2) \ transpose_4x4(x0, x1, x2, x3, t0, t1, t2) -.align 8 SYM_FUNC_START_LOCAL(__serpent_enc_blk16) /* input: * %rdi: ctx, CTX @@ -604,7 +603,6 @@ SYM_FUNC_START_LOCAL(__serpent_enc_blk16) RET; SYM_FUNC_END(__serpent_enc_blk16) -.align 8 SYM_FUNC_START_LOCAL(__serpent_dec_blk16) /* input: * %rdi: ctx, CTX diff --git a/arch/x86/crypto/sha1_ni_asm.S b/arch/x86/crypto/sha1_ni_asm.S index 2f94ec0e763b..cade913d4882 100644 --- a/arch/x86/crypto/sha1_ni_asm.S +++ b/arch/x86/crypto/sha1_ni_asm.S @@ -54,6 +54,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #define DIGEST_PTR %rdi /* 1st arg */ #define DATA_PTR %rsi /* 2nd arg */ @@ -92,8 +93,7 @@ * numBlocks: Number of blocks to process */ .text -.align 32 -SYM_FUNC_START(sha1_ni_transform) +SYM_TYPED_FUNC_START(sha1_ni_transform) push %rbp mov %rsp, %rbp sub $FRAME_SIZE, %rsp diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S index 263f916362e0..f54988c80eb4 100644 --- a/arch/x86/crypto/sha1_ssse3_asm.S +++ b/arch/x86/crypto/sha1_ssse3_asm.S @@ -25,6 +25,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #define CTX %rdi // arg1 #define BUF %rsi // arg2 @@ -67,7 +68,7 @@ * param: function's name */ .macro SHA1_VECTOR_ASM name - SYM_FUNC_START(\name) + SYM_TYPED_FUNC_START(\name) push %rbx push %r12 diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S index 3baa1ec39097..5555b5d5215a 100644 --- a/arch/x86/crypto/sha256-avx-asm.S +++ b/arch/x86/crypto/sha256-avx-asm.S @@ -48,6 +48,7 @@ ######################################################################## #include <linux/linkage.h> +#include <linux/cfi_types.h> ## assume buffers not aligned #define VMOVDQ vmovdqu @@ -346,8 +347,7 @@ a = TMP_ ## arg 3 : Num blocks ######################################################################## .text -SYM_FUNC_START(sha256_transform_avx) -.align 32 +SYM_TYPED_FUNC_START(sha256_transform_avx) pushq %rbx pushq %r12 pushq %r13 diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 9bcdbc47b8b4..3eada9416852 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -49,6 +49,7 @@ ######################################################################## #include <linux/linkage.h> +#include <linux/cfi_types.h> ## assume buffers not aligned #define VMOVDQ vmovdqu @@ -523,8 +524,7 @@ STACK_SIZE = _CTX + _CTX_SIZE ## arg 3 : Num blocks ######################################################################## .text -SYM_FUNC_START(sha256_transform_rorx) -.align 32 +SYM_TYPED_FUNC_START(sha256_transform_rorx) pushq %rbx pushq %r12 pushq %r13 diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S index c4a5db612c32..959288eecc68 100644 --- a/arch/x86/crypto/sha256-ssse3-asm.S +++ b/arch/x86/crypto/sha256-ssse3-asm.S @@ -47,6 +47,7 @@ ######################################################################## #include <linux/linkage.h> +#include <linux/cfi_types.h> ## assume buffers not aligned #define MOVDQ movdqu @@ -355,8 +356,7 @@ a = TMP_ ## arg 3 : Num blocks ######################################################################## .text -SYM_FUNC_START(sha256_transform_ssse3) -.align 32 +SYM_TYPED_FUNC_START(sha256_transform_ssse3) pushq %rbx pushq %r12 pushq %r13 diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S index 94d50dd27cb5..537b6dcd7ed8 100644 --- a/arch/x86/crypto/sha256_ni_asm.S +++ b/arch/x86/crypto/sha256_ni_asm.S @@ -54,6 +54,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #define DIGEST_PTR %rdi /* 1st arg */ #define DATA_PTR %rsi /* 2nd arg */ @@ -96,8 +97,7 @@ */ .text -.align 32 -SYM_FUNC_START(sha256_ni_transform) +SYM_TYPED_FUNC_START(sha256_ni_transform) shl $6, NUM_BLKS /* convert to bytes */ jz .Ldone_hash diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S index 1fefe6dd3a9e..b0984f19fdb4 100644 --- a/arch/x86/crypto/sha512-avx-asm.S +++ b/arch/x86/crypto/sha512-avx-asm.S @@ -48,6 +48,7 @@ ######################################################################## #include <linux/linkage.h> +#include <linux/cfi_types.h> .text @@ -273,7 +274,7 @@ frame_size = frame_WK + WK_SIZE # of SHA512 message blocks. # "blocks" is the message length in SHA512 blocks ######################################################################## -SYM_FUNC_START(sha512_transform_avx) +SYM_TYPED_FUNC_START(sha512_transform_avx) test msglen, msglen je nowork diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index 5cdaab7d6901..b1ca99055ef9 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -50,6 +50,7 @@ ######################################################################## #include <linux/linkage.h> +#include <linux/cfi_types.h> .text @@ -565,7 +566,7 @@ frame_size = frame_CTX + CTX_SIZE # of SHA512 message blocks. # "blocks" is the message length in SHA512 blocks ######################################################################## -SYM_FUNC_START(sha512_transform_rorx) +SYM_TYPED_FUNC_START(sha512_transform_rorx) # Save GPRs push %rbx push %r12 diff --git a/arch/x86/crypto/sha512-ssse3-asm.S b/arch/x86/crypto/sha512-ssse3-asm.S index b84c22e06c5f..c06afb5270e5 100644 --- a/arch/x86/crypto/sha512-ssse3-asm.S +++ b/arch/x86/crypto/sha512-ssse3-asm.S @@ -48,6 +48,7 @@ ######################################################################## #include <linux/linkage.h> +#include <linux/cfi_types.h> .text @@ -274,7 +275,7 @@ frame_size = frame_WK + WK_SIZE # of SHA512 message blocks. # "blocks" is the message length in SHA512 blocks. ######################################################################## -SYM_FUNC_START(sha512_transform_ssse3) +SYM_TYPED_FUNC_START(sha512_transform_ssse3) test msglen, msglen je nowork diff --git a/arch/x86/crypto/sm3-avx-asm_64.S b/arch/x86/crypto/sm3-avx-asm_64.S index b12b9efb5ec5..503bab450a91 100644 --- a/arch/x86/crypto/sm3-avx-asm_64.S +++ b/arch/x86/crypto/sm3-avx-asm_64.S @@ -12,6 +12,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/frame.h> /* Context structure */ @@ -327,8 +328,7 @@ * void sm3_transform_avx(struct sm3_state *state, * const u8 *data, int nblocks); */ -.align 16 -SYM_FUNC_START(sm3_transform_avx) +SYM_TYPED_FUNC_START(sm3_transform_avx) /* input: * %rdi: ctx, CTX * %rsi: data (64*nblks bytes) diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S index 4767ab61ff48..e2668d2fe6ce 100644 --- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S @@ -14,6 +14,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/frame.h> #define rRIP (%rip) @@ -139,13 +140,11 @@ .text -.align 16 /* * void sm4_aesni_avx_crypt4(const u32 *rk, u8 *dst, * const u8 *src, int nblocks) */ -.align 8 SYM_FUNC_START(sm4_aesni_avx_crypt4) /* input: * %rdi: round key array, CTX @@ -249,7 +248,6 @@ SYM_FUNC_START(sm4_aesni_avx_crypt4) RET; SYM_FUNC_END(sm4_aesni_avx_crypt4) -.align 8 SYM_FUNC_START_LOCAL(__sm4_crypt_blk8) /* input: * %rdi: round key array, CTX @@ -363,7 +361,6 @@ SYM_FUNC_END(__sm4_crypt_blk8) * void sm4_aesni_avx_crypt8(const u32 *rk, u8 *dst, * const u8 *src, int nblocks) */ -.align 8 SYM_FUNC_START(sm4_aesni_avx_crypt8) /* input: * %rdi: round key array, CTX @@ -419,8 +416,7 @@ SYM_FUNC_END(sm4_aesni_avx_crypt8) * void sm4_aesni_avx_ctr_enc_blk8(const u32 *rk, u8 *dst, * const u8 *src, u8 *iv) */ -.align 8 -SYM_FUNC_START(sm4_aesni_avx_ctr_enc_blk8) +SYM_TYPED_FUNC_START(sm4_aesni_avx_ctr_enc_blk8) /* input: * %rdi: round key array, CTX * %rsi: dst (8 blocks) @@ -494,8 +490,7 @@ SYM_FUNC_END(sm4_aesni_avx_ctr_enc_blk8) * void sm4_aesni_avx_cbc_dec_blk8(const u32 *rk, u8 *dst, * const u8 *src, u8 *iv) */ -.align 8 -SYM_FUNC_START(sm4_aesni_avx_cbc_dec_blk8) +SYM_TYPED_FUNC_START(sm4_aesni_avx_cbc_dec_blk8) /* input: * %rdi: round key array, CTX * %rsi: dst (8 blocks) @@ -544,8 +539,7 @@ SYM_FUNC_END(sm4_aesni_avx_cbc_dec_blk8) * void sm4_aesni_avx_cfb_dec_blk8(const u32 *rk, u8 *dst, * const u8 *src, u8 *iv) */ -.align 8 -SYM_FUNC_START(sm4_aesni_avx_cfb_dec_blk8) +SYM_TYPED_FUNC_START(sm4_aesni_avx_cfb_dec_blk8) /* input: * %rdi: round key array, CTX * %rsi: dst (8 blocks) diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S index 4732fe8bb65b..98ede9459287 100644 --- a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S @@ -14,6 +14,7 @@ */ #include <linux/linkage.h> +#include <linux/cfi_types.h> #include <asm/frame.h> #define rRIP (%rip) @@ -153,9 +154,6 @@ .long 0xdeadbeef, 0xdeadbeef, 0xdeadbeef .text -.align 16 - -.align 8 SYM_FUNC_START_LOCAL(__sm4_crypt_blk16) /* input: * %rdi: round key array, CTX @@ -281,8 +279,7 @@ SYM_FUNC_END(__sm4_crypt_blk16) * void sm4_aesni_avx2_ctr_enc_blk16(const u32 *rk, u8 *dst, * const u8 *src, u8 *iv) */ -.align 8 -SYM_FUNC_START(sm4_aesni_avx2_ctr_enc_blk16) +SYM_TYPED_FUNC_START(sm4_aesni_avx2_ctr_enc_blk16) /* input: * %rdi: round key array, CTX * %rsi: dst (16 blocks) @@ -394,8 +391,7 @@ SYM_FUNC_END(sm4_aesni_avx2_ctr_enc_blk16) * void sm4_aesni_avx2_cbc_dec_blk16(const u32 *rk, u8 *dst, * const u8 *src, u8 *iv) */ -.align 8 -SYM_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16) +SYM_TYPED_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16) /* input: * %rdi: round key array, CTX * %rsi: dst (16 blocks) @@ -448,8 +444,7 @@ SYM_FUNC_END(sm4_aesni_avx2_cbc_dec_blk16) * void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst, * const u8 *src, u8 *iv) */ -.align 8 -SYM_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16) +SYM_TYPED_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16) /* input: * %rdi: round key array, CTX * %rsi: dst (16 blocks) diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S index 31f9b2ec3857..12fde271cd3f 100644 --- a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S +++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S @@ -228,7 +228,6 @@ vpxor x2, wkey, x2; \ vpxor x3, wkey, x3; -.align 8 SYM_FUNC_START_LOCAL(__twofish_enc_blk8) /* input: * %rdi: ctx, CTX @@ -270,7 +269,6 @@ SYM_FUNC_START_LOCAL(__twofish_enc_blk8) RET; SYM_FUNC_END(__twofish_enc_blk8) -.align 8 SYM_FUNC_START_LOCAL(__twofish_dec_blk8) /* input: * %rdi: ctx, CTX diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c index f9c4adc27404..0614beece279 100644 --- a/arch/x86/crypto/twofish_glue.c +++ b/arch/x86/crypto/twofish_glue.c @@ -38,8 +38,8 @@ * Third Edition. */ +#include <crypto/algapi.h> #include <crypto/twofish.h> -#include <linux/crypto.h> #include <linux/init.h> #include <linux/module.h> #include <linux/types.h> diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index e309e7156038..91397f58ac30 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -1181,7 +1181,7 @@ SYM_CODE_START(asm_exc_nmi) * is using the thread stack right now, so it's safe for us to use it. */ movl %esp, %ebx - movl PER_CPU_VAR(cpu_current_top_of_stack), %esp + movl PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %esp call exc_nmi movl %ebx, %esp @@ -1243,7 +1243,7 @@ SYM_CODE_START(rewind_stack_and_make_dead) /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp - movl PER_CPU_VAR(cpu_current_top_of_stack), %esi + movl PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %esi leal -TOP_OF_KERNEL_STACK_PADDING-PTREGS_SIZE(%esi), %esp call make_task_dead diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 9953d966d124..15739a2c0983 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -92,7 +92,7 @@ SYM_CODE_START(entry_SYSCALL_64) /* tss.sp2 is scratch space. */ movq %rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2) SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + movq PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL) ANNOTATE_NOENDBR @@ -252,7 +252,7 @@ SYM_FUNC_START(__switch_to_asm) #ifdef CONFIG_STACKPROTECTOR movq TASK_stack_canary(%rsi), %rbx - movq %rbx, PER_CPU_VAR(fixed_percpu_data) + stack_canary_offset + movq %rbx, PER_CPU_VAR(fixed_percpu_data) + FIXED_stack_canary #endif /* @@ -284,9 +284,11 @@ SYM_FUNC_END(__switch_to_asm) * r12: kernel thread arg */ .pushsection .text, "ax" -SYM_CODE_START(ret_from_fork) + __FUNC_ALIGN +SYM_CODE_START_NOALIGN(ret_from_fork) UNWIND_HINT_EMPTY ANNOTATE_NOENDBR // copy_thread + CALL_DEPTH_ACCOUNT movq %rax, %rdi call schedule_tail /* rdi: 'prev' task parameter */ @@ -326,11 +328,12 @@ SYM_CODE_END(ret_from_fork) #endif .endm -SYM_CODE_START_LOCAL(xen_error_entry) +SYM_CODE_START(xen_error_entry) + ANNOTATE_NOENDBR UNWIND_HINT_FUNC PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 - UNTRAIN_RET + UNTRAIN_RET_FROM_CALL RET SYM_CODE_END(xen_error_entry) @@ -600,13 +603,13 @@ SYM_CODE_END(\asmsym) * shared between 32 and 64 bit and emit the __irqentry_text_* markers * so the stacktrace boundary checks work. */ - .align 16 + __ALIGN .globl __irqentry_text_start __irqentry_text_start: #include <asm/idtentry.h> - .align 16 + __ALIGN .globl __irqentry_text_end __irqentry_text_end: ANNOTATE_NOENDBR @@ -828,7 +831,8 @@ EXPORT_SYMBOL(asm_load_gs_index) * * C calling convention: exc_xen_hypervisor_callback(struct *pt_regs) */ -SYM_CODE_START_LOCAL(exc_xen_hypervisor_callback) + __FUNC_ALIGN +SYM_CODE_START_LOCAL_NOALIGN(exc_xen_hypervisor_callback) /* * Since we don't modify %rdi, evtchn_do_upall(struct *pt_regs) will @@ -856,7 +860,8 @@ SYM_CODE_END(exc_xen_hypervisor_callback) * We distinguish between categories by comparing each saved segment register * with its current contents: any discrepancy means we in category 1. */ -SYM_CODE_START(xen_failsafe_callback) + __FUNC_ALIGN +SYM_CODE_START_NOALIGN(xen_failsafe_callback) UNWIND_HINT_EMPTY ENDBR movl %ds, %ecx @@ -903,7 +908,8 @@ SYM_CODE_END(xen_failsafe_callback) * R14 - old CR3 * R15 - old SPEC_CTRL */ -SYM_CODE_START_LOCAL(paranoid_entry) +SYM_CODE_START(paranoid_entry) + ANNOTATE_NOENDBR UNWIND_HINT_FUNC PUSH_AND_CLEAR_REGS save_ret=1 ENCODE_FRAME_POINTER 8 @@ -972,7 +978,7 @@ SYM_CODE_START_LOCAL(paranoid_entry) * CR3 above, keep the old value in a callee saved register. */ IBRS_ENTER save_reg=%r15 - UNTRAIN_RET + UNTRAIN_RET_FROM_CALL RET SYM_CODE_END(paranoid_entry) @@ -1038,7 +1044,8 @@ SYM_CODE_END(paranoid_exit) /* * Switch GS and CR3 if needed. */ -SYM_CODE_START_LOCAL(error_entry) +SYM_CODE_START(error_entry) + ANNOTATE_NOENDBR UNWIND_HINT_FUNC PUSH_AND_CLEAR_REGS save_ret=1 @@ -1056,14 +1063,11 @@ SYM_CODE_START_LOCAL(error_entry) /* We have user CR3. Change to kernel CR3. */ SWITCH_TO_KERNEL_CR3 scratch_reg=%rax IBRS_ENTER - UNTRAIN_RET + UNTRAIN_RET_FROM_CALL leaq 8(%rsp), %rdi /* arg0 = pt_regs pointer */ -.Lerror_entry_from_usermode_after_swapgs: - /* Put us onto the real thread stack. */ - call sync_regs - RET + jmp sync_regs /* * There are two places in the kernel that can potentially fault with @@ -1094,6 +1098,7 @@ SYM_CODE_START_LOCAL(error_entry) */ .Lerror_entry_done_lfence: FENCE_SWAPGS_KERNEL_ENTRY + CALL_DEPTH_ACCOUNT leaq 8(%rsp), %rax /* return pt_regs pointer */ ANNOTATE_UNRET_END RET @@ -1112,7 +1117,7 @@ SYM_CODE_START_LOCAL(error_entry) FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rax IBRS_ENTER - UNTRAIN_RET + UNTRAIN_RET_FROM_CALL /* * Pretend that the exception came from user mode: set up pt_regs @@ -1121,7 +1126,7 @@ SYM_CODE_START_LOCAL(error_entry) leaq 8(%rsp), %rdi /* arg0 = pt_regs pointer */ call fixup_bad_iret mov %rax, %rdi - jmp .Lerror_entry_from_usermode_after_swapgs + jmp sync_regs SYM_CODE_END(error_entry) SYM_CODE_START_LOCAL(error_return) @@ -1206,7 +1211,7 @@ SYM_CODE_START(asm_exc_nmi) FENCE_SWAPGS_USER_ENTRY SWITCH_TO_KERNEL_CR3 scratch_reg=%rdx movq %rsp, %rdx - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + movq PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp UNWIND_HINT_IRET_REGS base=%rdx offset=8 pushq 5*8(%rdx) /* pt_regs->ss */ pushq 4*8(%rdx) /* pt_regs->rsp */ @@ -1516,12 +1521,13 @@ SYM_CODE_END(ignore_sysret) #endif .pushsection .text, "ax" -SYM_CODE_START(rewind_stack_and_make_dead) + __FUNC_ALIGN +SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead) UNWIND_HINT_FUNC /* Prevent any naive code from trying to unwind to our caller. */ xorl %ebp, %ebp - movq PER_CPU_VAR(cpu_current_top_of_stack), %rax + movq PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rax leaq -PTREGS_SIZE(%rax), %rsp UNWIND_HINT_REGS diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 4dd19819053a..70150298f8bd 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -58,10 +58,10 @@ SYM_CODE_START(entry_SYSENTER_compat) SWITCH_TO_KERNEL_CR3 scratch_reg=%rax popq %rax - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + movq PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp /* Construct struct pt_regs on stack */ - pushq $__USER32_DS /* pt_regs->ss */ + pushq $__USER_DS /* pt_regs->ss */ pushq $0 /* pt_regs->sp = 0 (placeholder) */ /* @@ -128,7 +128,6 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) popfq jmp .Lsysenter_flags_fixed SYM_INNER_LABEL(__end_entry_SYSENTER_compat, SYM_L_GLOBAL) - ANNOTATE_NOENDBR // is_sysenter_singlestep SYM_CODE_END(entry_SYSENTER_compat) /* @@ -191,13 +190,13 @@ SYM_CODE_START(entry_SYSCALL_compat) SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp /* Switch to the kernel stack */ - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + movq PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp SYM_INNER_LABEL(entry_SYSCALL_compat_safe_stack, SYM_L_GLOBAL) ANNOTATE_NOENDBR /* Construct struct pt_regs on stack */ - pushq $__USER32_DS /* pt_regs->ss */ + pushq $__USER_DS /* pt_regs->ss */ pushq %r8 /* pt_regs->sp */ pushq %r11 /* pt_regs->flags */ pushq $__USER32_CS /* pt_regs->cs */ @@ -332,7 +331,7 @@ SYM_CODE_START(entry_INT80_compat) ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV movq %rsp, %rax - movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp + movq PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp pushq 5*8(%rax) /* regs->ss */ pushq 4*8(%rax) /* regs->rsp */ diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index f38b07d2768b..5e37f41e5f14 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -11,7 +11,7 @@ /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ .macro THUNK name, func -SYM_FUNC_START_NOALIGN(\name) +SYM_FUNC_START(\name) pushq %rbp movq %rsp, %rbp @@ -36,7 +36,7 @@ SYM_FUNC_END(\name) EXPORT_SYMBOL(preempt_schedule_thunk) EXPORT_SYMBOL(preempt_schedule_notrace_thunk) -SYM_CODE_START_LOCAL_NOALIGN(__thunk_restore) +SYM_CODE_START_LOCAL(__thunk_restore) popq %r11 popq %r10 popq %r9 diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 3e88b9df8c8f..838613ac15b8 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -33,11 +33,12 @@ vobjs32-y += vdso32/vclock_gettime.o vobjs-$(CONFIG_X86_SGX) += vsgx.o # files to link into kernel -obj-y += vma.o extable.o -KASAN_SANITIZE_vma.o := y -UBSAN_SANITIZE_vma.o := y -KCSAN_SANITIZE_vma.o := y -OBJECT_FILES_NON_STANDARD_vma.o := n +obj-y += vma.o extable.o +KASAN_SANITIZE_vma.o := y +UBSAN_SANITIZE_vma.o := y +KCSAN_SANITIZE_vma.o := y +OBJECT_FILES_NON_STANDARD_vma.o := n +OBJECT_FILES_NON_STANDARD_extable.o := n # vDSO images to build vdso_img-$(VDSO64-y) += 64 @@ -94,7 +95,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),) endif endif -$(vobjs): KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) +$(vobjs): KBUILD_CFLAGS := $(filter-out $(PADDING_CFLAGS) $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL) $(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO # @@ -157,6 +158,7 @@ KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_CFI),$(KBUILD_CFLAGS_32)) +KBUILD_CFLAGS_32 := $(filter-out $(PADDING_CFLAGS),$(KBUILD_CFLAGS_32)) KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic KBUILD_CFLAGS_32 += -fno-stack-protector KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) diff --git a/arch/x86/entry/vdso/vdso.lds.S b/arch/x86/entry/vdso/vdso.lds.S index 4bf48462fca7..e8c60ae7a7c8 100644 --- a/arch/x86/entry/vdso/vdso.lds.S +++ b/arch/x86/entry/vdso/vdso.lds.S @@ -27,7 +27,9 @@ VERSION { __vdso_time; clock_getres; __vdso_clock_getres; +#ifdef CONFIG_X86_SGX __vdso_sgx_enter_enclave; +#endif local: *; }; } diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 311eae30e089..b8f3f9b9e53c 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -98,24 +98,6 @@ static int vdso_mremap(const struct vm_special_mapping *sm, } #ifdef CONFIG_TIME_NS -static struct page *find_timens_vvar_page(struct vm_area_struct *vma) -{ - if (likely(vma->vm_mm == current->mm)) - return current->nsproxy->time_ns->vvar_page; - - /* - * VM_PFNMAP | VM_IO protect .fault() handler from being called - * through interfaces like /proc/$pid/mem or - * process_vm_{readv,writev}() as long as there's no .access() - * in special_mapping_vmops(). - * For more details check_vma_flags() and __access_remote_vm() - */ - - WARN(1, "vvar_page accessed remotely"); - - return NULL; -} - /* * The vvar page layout depends on whether a task belongs to the root or * non-root time namespace. Whenever a task changes its namespace, the VVAR @@ -140,11 +122,6 @@ int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) return 0; } -#else -static inline struct page *find_timens_vvar_page(struct vm_area_struct *vma) -{ - return NULL; -} #endif static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, @@ -210,11 +187,10 @@ static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, pgprot_decrypted(vma->vm_page_prot)); } } else if (sym_offset == image->sym_hvclock_page) { - struct ms_hyperv_tsc_page *tsc_pg = hv_get_tsc_page(); + pfn = hv_get_tsc_pfn(); - if (tsc_pg && vclock_was_used(VDSO_CLOCKMODE_HVCLOCK)) - return vmf_insert_pfn(vma, vmf->address, - virt_to_phys(tsc_pg) >> PAGE_SHIFT); + if (pfn && vclock_was_used(VDSO_CLOCKMODE_HVCLOCK)) + return vmf_insert_pfn(vma, vmf->address, pfn); } else if (sym_offset == image->sym_timens_page) { struct page *timens_page = find_timens_vvar_page(vma); @@ -327,7 +303,7 @@ static unsigned long vdso_addr(unsigned long start, unsigned len) end -= len; if (end > start) { - offset = prandom_u32_max(((end - start) >> PAGE_SHIFT) + 1); + offset = get_random_u32_below(((end - start) >> PAGE_SHIFT) + 1); addr = start + (offset << PAGE_SHIFT); } else { addr = start; diff --git a/arch/x86/events/amd/brs.c b/arch/x86/events/amd/brs.c index f1bff153d945..58461fa18b6f 100644 --- a/arch/x86/events/amd/brs.c +++ b/arch/x86/events/amd/brs.c @@ -384,7 +384,7 @@ static void amd_brs_poison_buffer(void) * On ctxswin, sched_in = true, called after the PMU has started * On ctxswout, sched_in = false, called before the PMU is stopped */ -void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in) +void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 4cb710efbdd9..da3f5ebac4e1 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -631,7 +631,7 @@ static const struct attribute_group *op_attr_update[] = { static struct perf_ibs perf_ibs_fetch = { .pmu = { - .task_ctx_nr = perf_invalid_context, + .task_ctx_nr = perf_hw_context, .event_init = perf_ibs_init, .add = perf_ibs_add, @@ -655,7 +655,7 @@ static struct perf_ibs perf_ibs_fetch = { static struct perf_ibs perf_ibs_op = { .pmu = { - .task_ctx_nr = perf_invalid_context, + .task_ctx_nr = perf_hw_context, .event_init = perf_ibs_init, .add = perf_ibs_add, diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c index 38a75216c12c..eb31f850841a 100644 --- a/arch/x86/events/amd/lbr.c +++ b/arch/x86/events/amd/lbr.c @@ -352,7 +352,7 @@ void amd_pmu_lbr_add(struct perf_event *event) cpuc->br_sel = reg->reg; } - perf_sched_cb_inc(event->ctx->pmu); + perf_sched_cb_inc(event->pmu); if (!cpuc->lbr_users++ && !event->total_time_running) amd_pmu_lbr_reset(); @@ -370,10 +370,10 @@ void amd_pmu_lbr_del(struct perf_event *event) cpuc->lbr_users--; WARN_ON_ONCE(cpuc->lbr_users < 0); - perf_sched_cb_dec(event->ctx->pmu); + perf_sched_cb_dec(event->pmu); } -void amd_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) +void amd_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index b30b8bbcd1e2..85a63a41c471 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -90,6 +90,8 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_swap_task_ctx, *x86_pmu.swap_task_ctx); DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs, *x86_pmu.drain_pebs); DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases); +DEFINE_STATIC_CALL_NULL(x86_pmu_filter, *x86_pmu.filter); + /* * This one is magic, it will get called even when PMU init fails (because * there is no PMU), in which case it should simply return NULL. @@ -2031,6 +2033,7 @@ static void x86_pmu_static_call_update(void) static_call_update(x86_pmu_pebs_aliases, x86_pmu.pebs_aliases); static_call_update(x86_pmu_guest_get_msrs, x86_pmu.guest_get_msrs); + static_call_update(x86_pmu_filter, x86_pmu.filter); } static void _x86_pmu_read(struct perf_event *event) @@ -2052,23 +2055,6 @@ void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed, pr_info("... event mask: %016Lx\n", intel_ctrl); } -/* - * The generic code is not hybrid friendly. The hybrid_pmu->pmu - * of the first registered PMU is unconditionally assigned to - * each possible cpuctx->ctx.pmu. - * Update the correct hybrid PMU to the cpuctx->ctx.pmu. - */ -void x86_pmu_update_cpu_context(struct pmu *pmu, int cpu) -{ - struct perf_cpu_context *cpuctx; - - if (!pmu->pmu_cpu_context) - return; - - cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); - cpuctx->ctx.pmu = pmu; -} - static int __init init_hw_perf_events(void) { struct x86_pmu_quirk *quirk; @@ -2175,13 +2161,9 @@ static int __init init_hw_perf_events(void) if (err) goto out2; } else { - u8 cpu_type = get_this_hybrid_cpu_type(); struct x86_hybrid_pmu *hybrid_pmu; int i, j; - if (!cpu_type && x86_pmu.get_hybrid_cpu_type) - cpu_type = x86_pmu.get_hybrid_cpu_type(); - for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) { hybrid_pmu = &x86_pmu.hybrid_pmu[i]; @@ -2195,9 +2177,6 @@ static int __init init_hw_perf_events(void) (hybrid_pmu->cpu_type == hybrid_big) ? PERF_TYPE_RAW : -1); if (err) break; - - if (cpu_type == hybrid_pmu->cpu_type) - x86_pmu_update_cpu_context(&hybrid_pmu->pmu, raw_smp_processor_id()); } if (i < x86_pmu.num_hybrid_pmus) { @@ -2646,15 +2625,15 @@ static const struct attribute_group *x86_pmu_attr_groups[] = { NULL, }; -static void x86_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) +static void x86_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in) { - static_call_cond(x86_pmu_sched_task)(ctx, sched_in); + static_call_cond(x86_pmu_sched_task)(pmu_ctx, sched_in); } -static void x86_pmu_swap_task_ctx(struct perf_event_context *prev, - struct perf_event_context *next) +static void x86_pmu_swap_task_ctx(struct perf_event_pmu_context *prev_epc, + struct perf_event_pmu_context *next_epc) { - static_call_cond(x86_pmu_swap_task_ctx)(prev, next); + static_call_cond(x86_pmu_swap_task_ctx)(prev_epc, next_epc); } void perf_check_microcode(void) @@ -2689,12 +2668,13 @@ static int x86_pmu_aux_output_match(struct perf_event *event) return 0; } -static int x86_pmu_filter_match(struct perf_event *event) +static bool x86_pmu_filter(struct pmu *pmu, int cpu) { - if (x86_pmu.filter_match) - return x86_pmu.filter_match(event); + bool ret = false; - return 1; + static_call_cond(x86_pmu_filter)(pmu, cpu, &ret); + + return ret; } static struct pmu pmu = { @@ -2725,7 +2705,7 @@ static struct pmu pmu = { .aux_output_match = x86_pmu_aux_output_match, - .filter_match = x86_pmu_filter_match, + .filter = x86_pmu_filter, }; void arch_perf_update_userpage(struct perf_event *event, diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 1b92bf05fd65..dfd2c124cdf8 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4536,8 +4536,6 @@ end: cpumask_set_cpu(cpu, &pmu->supported_cpus); cpuc->pmu = &pmu->pmu; - x86_pmu_update_cpu_context(&pmu->pmu, cpu); - return true; } @@ -4671,17 +4669,17 @@ static void intel_pmu_cpu_dead(int cpu) cpumask_clear_cpu(cpu, &hybrid_pmu(cpuc->pmu)->supported_cpus); } -static void intel_pmu_sched_task(struct perf_event_context *ctx, +static void intel_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in) { - intel_pmu_pebs_sched_task(ctx, sched_in); - intel_pmu_lbr_sched_task(ctx, sched_in); + intel_pmu_pebs_sched_task(pmu_ctx, sched_in); + intel_pmu_lbr_sched_task(pmu_ctx, sched_in); } -static void intel_pmu_swap_task_ctx(struct perf_event_context *prev, - struct perf_event_context *next) +static void intel_pmu_swap_task_ctx(struct perf_event_pmu_context *prev_epc, + struct perf_event_pmu_context *next_epc) { - intel_pmu_lbr_swap_task_ctx(prev, next); + intel_pmu_lbr_swap_task_ctx(prev_epc, next_epc); } static int intel_pmu_check_period(struct perf_event *event, u64 value) @@ -4705,12 +4703,11 @@ static int intel_pmu_aux_output_match(struct perf_event *event) return is_intel_pt_event(event); } -static int intel_pmu_filter_match(struct perf_event *event) +static void intel_pmu_filter(struct pmu *pmu, int cpu, bool *ret) { - struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); - unsigned int cpu = smp_processor_id(); + struct x86_hybrid_pmu *hpmu = hybrid_pmu(pmu); - return cpumask_test_cpu(cpu, &pmu->supported_cpus); + *ret = !cpumask_test_cpu(cpu, &hpmu->supported_cpus); } PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); @@ -6413,7 +6410,7 @@ __init int intel_pmu_init(void) static_call_update(intel_pmu_set_topdown_event_period, &adl_set_topdown_event_period); - x86_pmu.filter_match = intel_pmu_filter_match; + x86_pmu.filter = intel_pmu_filter; x86_pmu.get_event_constraints = adl_get_event_constraints; x86_pmu.hw_config = adl_hw_config; x86_pmu.limit_period = spr_limit_period; diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 446d2833efa7..88e58b6ee73c 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1069,7 +1069,7 @@ static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc) return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs); } -void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in) +void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1177,7 +1177,7 @@ static void pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct perf_event *event, bool add) { - struct pmu *pmu = event->ctx->pmu; + struct pmu *pmu = event->pmu; /* * Make sure we get updated with the first PEBS * event. It will trigger also during removal, but diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 8259d725054d..1f21f576ca77 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -515,21 +515,21 @@ static void __intel_pmu_lbr_save(void *ctx) cpuc->last_log_id = ++task_context_opt(ctx)->log_id; } -void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev, - struct perf_event_context *next) +void intel_pmu_lbr_swap_task_ctx(struct perf_event_pmu_context *prev_epc, + struct perf_event_pmu_context *next_epc) { void *prev_ctx_data, *next_ctx_data; - swap(prev->task_ctx_data, next->task_ctx_data); + swap(prev_epc->task_ctx_data, next_epc->task_ctx_data); /* - * Architecture specific synchronization makes sense in - * case both prev->task_ctx_data and next->task_ctx_data + * Architecture specific synchronization makes sense in case + * both prev_epc->task_ctx_data and next_epc->task_ctx_data * pointers are allocated. */ - prev_ctx_data = next->task_ctx_data; - next_ctx_data = prev->task_ctx_data; + prev_ctx_data = next_epc->task_ctx_data; + next_ctx_data = prev_epc->task_ctx_data; if (!prev_ctx_data || !next_ctx_data) return; @@ -538,7 +538,7 @@ void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev, task_context_opt(next_ctx_data)->lbr_callstack_users); } -void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) +void intel_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); void *task_ctx; @@ -551,7 +551,7 @@ void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in) * the task was scheduled out, restore the stack. Otherwise flush * the LBR stack. */ - task_ctx = ctx ? ctx->task_ctx_data : NULL; + task_ctx = pmu_ctx ? pmu_ctx->task_ctx_data : NULL; if (task_ctx) { if (sched_in) __intel_pmu_lbr_restore(task_ctx); @@ -587,8 +587,8 @@ void intel_pmu_lbr_add(struct perf_event *event) cpuc->br_sel = event->hw.branch_reg.reg; - if (branch_user_callstack(cpuc->br_sel) && event->ctx->task_ctx_data) - task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users++; + if (branch_user_callstack(cpuc->br_sel) && event->pmu_ctx->task_ctx_data) + task_context_opt(event->pmu_ctx->task_ctx_data)->lbr_callstack_users++; /* * Request pmu::sched_task() callback, which will fire inside the @@ -611,7 +611,7 @@ void intel_pmu_lbr_add(struct perf_event *event) */ if (x86_pmu.intel_cap.pebs_baseline && event->attr.precise_ip > 0) cpuc->lbr_pebs_users++; - perf_sched_cb_inc(event->ctx->pmu); + perf_sched_cb_inc(event->pmu); if (!cpuc->lbr_users++ && !event->total_time_running) intel_pmu_lbr_reset(); } @@ -664,8 +664,8 @@ void intel_pmu_lbr_del(struct perf_event *event) return; if (branch_user_callstack(cpuc->br_sel) && - event->ctx->task_ctx_data) - task_context_opt(event->ctx->task_ctx_data)->lbr_callstack_users--; + event->pmu_ctx->task_ctx_data) + task_context_opt(event->pmu_ctx->task_ctx_data)->lbr_callstack_users--; if (event->hw.flags & PERF_X86_EVENT_LBR_SELECT) cpuc->lbr_select = 0; @@ -675,7 +675,7 @@ void intel_pmu_lbr_del(struct perf_event *event) cpuc->lbr_users--; WARN_ON_ONCE(cpuc->lbr_users < 0); WARN_ON_ONCE(cpuc->lbr_pebs_users < 0); - perf_sched_cb_dec(event->ctx->pmu); + perf_sched_cb_dec(event->pmu); } static inline bool vlbr_exclude_host(void) @@ -1603,10 +1603,8 @@ clear_arch_lbr: * x86_perf_get_lbr - get the LBR records information * * @lbr: the caller's memory to store the LBR records information - * - * Returns: 0 indicates the LBR info has been successfully obtained */ -int x86_perf_get_lbr(struct x86_pmu_lbr *lbr) +void x86_perf_get_lbr(struct x86_pmu_lbr *lbr) { int lbr_fmt = x86_pmu.intel_cap.lbr_format; @@ -1614,8 +1612,6 @@ int x86_perf_get_lbr(struct x86_pmu_lbr *lbr) lbr->from = x86_pmu.lbr_from; lbr->to = x86_pmu.lbr_to; lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? x86_pmu.lbr_info : 0; - - return 0; } EXPORT_SYMBOL_GPL(x86_perf_get_lbr); diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c index 03bbcc2fa2ff..35936188db01 100644 --- a/arch/x86/events/intel/p4.c +++ b/arch/x86/events/intel/p4.c @@ -24,7 +24,7 @@ struct p4_event_bind { unsigned int escr_msr[2]; /* ESCR MSR for this event */ unsigned int escr_emask; /* valid ESCR EventMask bits */ unsigned int shared; /* event is shared across threads */ - char cntr[2][P4_CNTR_LIMIT]; /* counter index (offset), -1 on absence */ + signed char cntr[2][P4_CNTR_LIMIT]; /* counter index (offset), -1 on absence */ }; struct p4_pebs_bind { diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index 2adeaf4de4df..e278e2e7c051 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -2,6 +2,7 @@ #include <linux/slab.h> #include <linux/pci.h> #include <asm/apicdef.h> +#include <asm/intel-family.h> #include <linux/io-64-nonatomic-lo-hi.h> #include <linux/perf_event.h> @@ -88,12 +89,12 @@ struct intel_uncore_type { * to identify which platform component each PMON block of that type is * supposed to monitor. */ - struct intel_uncore_topology *topology; + struct intel_uncore_topology **topology; /* * Optional callbacks for managing mapping of Uncore units to PMONs */ int (*get_topology)(struct intel_uncore_type *type); - int (*set_mapping)(struct intel_uncore_type *type); + void (*set_mapping)(struct intel_uncore_type *type); void (*cleanup_mapping)(struct intel_uncore_type *type); }; @@ -178,11 +179,26 @@ struct freerunning_counters { unsigned *box_offsets; }; -struct intel_uncore_topology { - u64 configuration; +struct uncore_iio_topology { + int pci_bus_no; int segment; }; +struct uncore_upi_topology { + int die_to; + int pmu_idx_to; + int enabled; +}; + +struct intel_uncore_topology { + int pmu_idx; + union { + void *untyped; + struct uncore_iio_topology *iio; + struct uncore_upi_topology *upi; + }; +}; + struct pci2phy_map { struct list_head list; int segment; diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 1ef4f7861e2e..1f4869227efb 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -1338,6 +1338,7 @@ static void __uncore_imc_init_box(struct intel_uncore_box *box, /* MCHBAR is disabled */ if (!(mch_bar & BIT(0))) { pr_warn("perf uncore: MCHBAR is disabled. Failed to map IMC free-running counters.\n"); + pci_dev_put(pdev); return; } mch_bar &= ~BIT(0); @@ -1352,6 +1353,8 @@ static void __uncore_imc_init_box(struct intel_uncore_box *box, box->io_addr = ioremap(addr, type->mmio_map_size); if (!box->io_addr) pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name); + + pci_dev_put(pdev); } static void tgl_uncore_imc_freerunning_init_box(struct intel_uncore_box *box) diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index ed869443efb2..44c2f879f708 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -445,6 +445,7 @@ #define ICX_UPI_PCI_PMON_CTR0 0x320 #define ICX_UPI_PCI_PMON_BOX_CTL 0x318 #define ICX_UPI_CTL_UMASK_EXT 0xffffff +#define ICX_UBOX_DID 0x3450 /* ICX M3UPI*/ #define ICX_M3UPI_PCI_PMON_CTL0 0xd8 @@ -457,6 +458,7 @@ /* SPR */ #define SPR_RAW_EVENT_MASK_EXT 0xffffff +#define SPR_UBOX_DID 0x3250 /* SPR CHA */ #define SPR_CHA_PMON_CTL_TID_EN (1 << 16) @@ -1372,6 +1374,28 @@ static struct pci_driver snbep_uncore_pci_driver = { #define NODE_ID_MASK 0x7 +/* Each three bits from 0 to 23 of GIDNIDMAP register correspond Node ID. */ +#define GIDNIDMAP(config, id) (((config) >> (3 * (id))) & 0x7) + +static int upi_nodeid_groupid(struct pci_dev *ubox_dev, int nodeid_loc, int idmap_loc, + int *nodeid, int *groupid) +{ + int ret; + + /* get the Node ID of the local register */ + ret = pci_read_config_dword(ubox_dev, nodeid_loc, nodeid); + if (ret) + goto err; + + *nodeid = *nodeid & NODE_ID_MASK; + /* get the Node ID mapping */ + ret = pci_read_config_dword(ubox_dev, idmap_loc, groupid); + if (ret) + goto err; +err: + return ret; +} + /* * build pci bus to socket mapping */ @@ -1397,13 +1421,8 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool * the topology. */ if (nr_node_ids <= 8) { - /* get the Node ID of the local register */ - err = pci_read_config_dword(ubox_dev, nodeid_loc, &config); - if (err) - break; - nodeid = config & NODE_ID_MASK; - /* get the Node ID mapping */ - err = pci_read_config_dword(ubox_dev, idmap_loc, &config); + err = upi_nodeid_groupid(ubox_dev, nodeid_loc, idmap_loc, + &nodeid, &config); if (err) break; @@ -1421,7 +1440,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool * to a particular node. */ for (i = 0; i < 8; i++) { - if (nodeid == ((config >> (3 * i)) & 0x7)) { + if (nodeid == GIDNIDMAP(config, i)) { if (topology_max_die_per_package() > 1) die_id = i; else @@ -2891,6 +2910,7 @@ static bool hswep_has_limit_sbox(unsigned int device) return false; pci_read_config_dword(dev, HSWEP_PCU_CAPID4_OFFET, &capid4); + pci_dev_put(dev); if (!hswep_get_chop(capid4)) return true; @@ -3699,10 +3719,16 @@ static struct intel_uncore_ops skx_uncore_iio_ops = { .read_counter = uncore_msr_read_counter, }; -static inline u8 skx_iio_stack(struct intel_uncore_pmu *pmu, int die) +static struct intel_uncore_topology *pmu_topology(struct intel_uncore_pmu *pmu, int die) { - return pmu->type->topology[die].configuration >> - (pmu->pmu_idx * BUS_NUM_STRIDE); + int idx; + + for (idx = 0; idx < pmu->type->num_boxes; idx++) { + if (pmu->type->topology[die][idx].pmu_idx == pmu->pmu_idx) + return &pmu->type->topology[die][idx]; + } + + return NULL; } static umode_t @@ -3710,8 +3736,9 @@ pmu_iio_mapping_visible(struct kobject *kobj, struct attribute *attr, int die, int zero_bus_pmu) { struct intel_uncore_pmu *pmu = dev_to_uncore_pmu(kobj_to_dev(kobj)); + struct intel_uncore_topology *pmut = pmu_topology(pmu, die); - return (!skx_iio_stack(pmu, die) && pmu->pmu_idx != zero_bus_pmu) ? 0 : attr->mode; + return (pmut && !pmut->iio->pci_bus_no && pmu->pmu_idx != zero_bus_pmu) ? 0 : attr->mode; } static umode_t @@ -3727,9 +3754,10 @@ static ssize_t skx_iio_mapping_show(struct device *dev, struct intel_uncore_pmu *pmu = dev_to_uncore_pmu(dev); struct dev_ext_attribute *ea = to_dev_ext_attribute(attr); long die = (long)ea->var; + struct intel_uncore_topology *pmut = pmu_topology(pmu, die); - return sprintf(buf, "%04x:%02x\n", pmu->type->topology[die].segment, - skx_iio_stack(pmu, die)); + return sprintf(buf, "%04x:%02x\n", pmut ? pmut->iio->segment : 0, + pmut ? pmut->iio->pci_bus_no : 0); } static int skx_msr_cpu_bus_read(int cpu, u64 *topology) @@ -3764,18 +3792,79 @@ static int die_to_cpu(int die) return res; } -static int skx_iio_get_topology(struct intel_uncore_type *type) +enum { + IIO_TOPOLOGY_TYPE, + UPI_TOPOLOGY_TYPE, + TOPOLOGY_MAX +}; + +static const size_t topology_size[TOPOLOGY_MAX] = { + sizeof(*((struct intel_uncore_topology *)NULL)->iio), + sizeof(*((struct intel_uncore_topology *)NULL)->upi) +}; + +static int pmu_alloc_topology(struct intel_uncore_type *type, int topology_type) { - int die, ret = -EPERM; + int die, idx; + struct intel_uncore_topology **topology; + + if (!type->num_boxes) + return -EPERM; - type->topology = kcalloc(uncore_max_dies(), sizeof(*type->topology), - GFP_KERNEL); - if (!type->topology) - return -ENOMEM; + topology = kcalloc(uncore_max_dies(), sizeof(*topology), GFP_KERNEL); + if (!topology) + goto err; for (die = 0; die < uncore_max_dies(); die++) { - ret = skx_msr_cpu_bus_read(die_to_cpu(die), - &type->topology[die].configuration); + topology[die] = kcalloc(type->num_boxes, sizeof(**topology), GFP_KERNEL); + if (!topology[die]) + goto clear; + for (idx = 0; idx < type->num_boxes; idx++) { + topology[die][idx].untyped = kcalloc(type->num_boxes, + topology_size[topology_type], + GFP_KERNEL); + if (!topology[die][idx].untyped) + goto clear; + } + } + + type->topology = topology; + + return 0; +clear: + for (; die >= 0; die--) { + for (idx = 0; idx < type->num_boxes; idx++) + kfree(topology[die][idx].untyped); + kfree(topology[die]); + } + kfree(topology); +err: + return -ENOMEM; +} + +static void pmu_free_topology(struct intel_uncore_type *type) +{ + int die, idx; + + if (type->topology) { + for (die = 0; die < uncore_max_dies(); die++) { + for (idx = 0; idx < type->num_boxes; idx++) + kfree(type->topology[die][idx].untyped); + kfree(type->topology[die]); + } + kfree(type->topology); + type->topology = NULL; + } +} + +static int skx_pmu_get_topology(struct intel_uncore_type *type, + int (*topology_cb)(struct intel_uncore_type*, int, int, u64)) +{ + int die, ret = -EPERM; + u64 cpu_bus_msr; + + for (die = 0; die < uncore_max_dies(); die++) { + ret = skx_msr_cpu_bus_read(die_to_cpu(die), &cpu_bus_msr); if (ret) break; @@ -3783,15 +3872,33 @@ static int skx_iio_get_topology(struct intel_uncore_type *type) if (ret < 0) break; - type->topology[die].segment = ret; + ret = topology_cb(type, ret, die, cpu_bus_msr); + if (ret) + break; } - if (ret < 0) { - kfree(type->topology); - type->topology = NULL; + return ret; +} + +static int skx_iio_topology_cb(struct intel_uncore_type *type, int segment, + int die, u64 cpu_bus_msr) +{ + int idx; + struct intel_uncore_topology *t; + + for (idx = 0; idx < type->num_boxes; idx++) { + t = &type->topology[die][idx]; + t->pmu_idx = idx; + t->iio->segment = segment; + t->iio->pci_bus_no = (cpu_bus_msr >> (idx * BUS_NUM_STRIDE)) & 0xff; } - return ret; + return 0; +} + +static int skx_iio_get_topology(struct intel_uncore_type *type) +{ + return skx_pmu_get_topology(type, skx_iio_topology_cb); } static struct attribute_group skx_iio_mapping_group = { @@ -3803,8 +3910,25 @@ static const struct attribute_group *skx_iio_attr_update[] = { NULL, }; -static int -pmu_iio_set_mapping(struct intel_uncore_type *type, struct attribute_group *ag) +static void pmu_clear_mapping_attr(const struct attribute_group **groups, + struct attribute_group *ag) +{ + int i; + + for (i = 0; groups[i]; i++) { + if (groups[i] == ag) { + for (i++; groups[i]; i++) + groups[i - 1] = groups[i]; + groups[i - 1] = NULL; + break; + } + } +} + +static void +pmu_set_mapping(struct intel_uncore_type *type, struct attribute_group *ag, + ssize_t (*show)(struct device*, struct device_attribute*, char*), + int topology_type) { char buf[64]; int ret; @@ -3812,11 +3936,13 @@ pmu_iio_set_mapping(struct intel_uncore_type *type, struct attribute_group *ag) struct attribute **attrs = NULL; struct dev_ext_attribute *eas = NULL; - ret = type->get_topology(type); + ret = pmu_alloc_topology(type, topology_type); if (ret < 0) goto clear_attr_update; - ret = -ENOMEM; + ret = type->get_topology(type); + if (ret < 0) + goto clear_topology; /* One more for NULL. */ attrs = kcalloc((uncore_max_dies() + 1), sizeof(*attrs), GFP_KERNEL); @@ -3828,20 +3954,20 @@ pmu_iio_set_mapping(struct intel_uncore_type *type, struct attribute_group *ag) goto clear_attrs; for (die = 0; die < uncore_max_dies(); die++) { - sprintf(buf, "die%ld", die); + snprintf(buf, sizeof(buf), "die%ld", die); sysfs_attr_init(&eas[die].attr.attr); eas[die].attr.attr.name = kstrdup(buf, GFP_KERNEL); if (!eas[die].attr.attr.name) goto err; eas[die].attr.attr.mode = 0444; - eas[die].attr.show = skx_iio_mapping_show; + eas[die].attr.show = show; eas[die].attr.store = NULL; eas[die].var = (void *)die; attrs[die] = &eas[die].attr.attr; } ag->attrs = attrs; - return 0; + return; err: for (; die >= 0; die--) kfree(eas[die].attr.attr.name); @@ -3849,14 +3975,13 @@ err: clear_attrs: kfree(attrs); clear_topology: - kfree(type->topology); + pmu_free_topology(type); clear_attr_update: - type->attr_update = NULL; - return ret; + pmu_clear_mapping_attr(type->attr_update, ag); } static void -pmu_iio_cleanup_mapping(struct intel_uncore_type *type, struct attribute_group *ag) +pmu_cleanup_mapping(struct intel_uncore_type *type, struct attribute_group *ag) { struct attribute **attr = ag->attrs; @@ -3868,17 +3993,23 @@ pmu_iio_cleanup_mapping(struct intel_uncore_type *type, struct attribute_group * kfree(attr_to_ext_attr(*ag->attrs)); kfree(ag->attrs); ag->attrs = NULL; - kfree(type->topology); + pmu_free_topology(type); +} + +static void +pmu_iio_set_mapping(struct intel_uncore_type *type, struct attribute_group *ag) +{ + pmu_set_mapping(type, ag, skx_iio_mapping_show, IIO_TOPOLOGY_TYPE); } -static int skx_iio_set_mapping(struct intel_uncore_type *type) +static void skx_iio_set_mapping(struct intel_uncore_type *type) { - return pmu_iio_set_mapping(type, &skx_iio_mapping_group); + pmu_iio_set_mapping(type, &skx_iio_mapping_group); } static void skx_iio_cleanup_mapping(struct intel_uncore_type *type) { - pmu_iio_cleanup_mapping(type, &skx_iio_mapping_group); + pmu_cleanup_mapping(type, &skx_iio_mapping_group); } static struct intel_uncore_type skx_uncore_iio = { @@ -4139,6 +4270,132 @@ static struct intel_uncore_ops skx_upi_uncore_pci_ops = { .read_counter = snbep_uncore_pci_read_counter, }; +static umode_t +skx_upi_mapping_visible(struct kobject *kobj, struct attribute *attr, int die) +{ + struct intel_uncore_pmu *pmu = dev_to_uncore_pmu(kobj_to_dev(kobj)); + + return pmu->type->topology[die][pmu->pmu_idx].upi->enabled ? attr->mode : 0; +} + +static ssize_t skx_upi_mapping_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct intel_uncore_pmu *pmu = dev_to_uncore_pmu(dev); + struct dev_ext_attribute *ea = to_dev_ext_attribute(attr); + long die = (long)ea->var; + struct uncore_upi_topology *upi = pmu->type->topology[die][pmu->pmu_idx].upi; + + return sysfs_emit(buf, "upi_%d,die_%d\n", upi->pmu_idx_to, upi->die_to); +} + +#define SKX_UPI_REG_DID 0x2058 +#define SKX_UPI_REGS_ADDR_DEVICE_LINK0 0x0e +#define SKX_UPI_REGS_ADDR_FUNCTION 0x00 + +/* + * UPI Link Parameter 0 + * | Bit | Default | Description + * | 19:16 | 0h | base_nodeid - The NodeID of the sending socket. + * | 12:8 | 00h | sending_port - The processor die port number of the sending port. + */ +#define SKX_KTILP0_OFFSET 0x94 + +/* + * UPI Pcode Status. This register is used by PCode to store the link training status. + * | Bit | Default | Description + * | 4 | 0h | ll_status_valid — Bit indicates the valid training status + * logged from PCode to the BIOS. + */ +#define SKX_KTIPCSTS_OFFSET 0x120 + +static int upi_fill_topology(struct pci_dev *dev, struct intel_uncore_topology *tp, + int pmu_idx) +{ + int ret; + u32 upi_conf; + struct uncore_upi_topology *upi = tp->upi; + + tp->pmu_idx = pmu_idx; + ret = pci_read_config_dword(dev, SKX_KTIPCSTS_OFFSET, &upi_conf); + if (ret) { + ret = pcibios_err_to_errno(ret); + goto err; + } + upi->enabled = (upi_conf >> 4) & 1; + if (upi->enabled) { + ret = pci_read_config_dword(dev, SKX_KTILP0_OFFSET, + &upi_conf); + if (ret) { + ret = pcibios_err_to_errno(ret); + goto err; + } + upi->die_to = (upi_conf >> 16) & 0xf; + upi->pmu_idx_to = (upi_conf >> 8) & 0x1f; + } +err: + return ret; +} + +static int skx_upi_topology_cb(struct intel_uncore_type *type, int segment, + int die, u64 cpu_bus_msr) +{ + int idx, ret; + struct intel_uncore_topology *upi; + unsigned int devfn; + struct pci_dev *dev = NULL; + u8 bus = cpu_bus_msr >> (3 * BUS_NUM_STRIDE); + + for (idx = 0; idx < type->num_boxes; idx++) { + upi = &type->topology[die][idx]; + devfn = PCI_DEVFN(SKX_UPI_REGS_ADDR_DEVICE_LINK0 + idx, + SKX_UPI_REGS_ADDR_FUNCTION); + dev = pci_get_domain_bus_and_slot(segment, bus, devfn); + if (dev) { + ret = upi_fill_topology(dev, upi, idx); + if (ret) + break; + } + } + + pci_dev_put(dev); + return ret; +} + +static int skx_upi_get_topology(struct intel_uncore_type *type) +{ + /* CPX case is not supported */ + if (boot_cpu_data.x86_stepping == 11) + return -EPERM; + + return skx_pmu_get_topology(type, skx_upi_topology_cb); +} + +static struct attribute_group skx_upi_mapping_group = { + .is_visible = skx_upi_mapping_visible, +}; + +static const struct attribute_group *skx_upi_attr_update[] = { + &skx_upi_mapping_group, + NULL +}; + +static void +pmu_upi_set_mapping(struct intel_uncore_type *type, struct attribute_group *ag) +{ + pmu_set_mapping(type, ag, skx_upi_mapping_show, UPI_TOPOLOGY_TYPE); +} + +static void skx_upi_set_mapping(struct intel_uncore_type *type) +{ + pmu_upi_set_mapping(type, &skx_upi_mapping_group); +} + +static void skx_upi_cleanup_mapping(struct intel_uncore_type *type) +{ + pmu_cleanup_mapping(type, &skx_upi_mapping_group); +} + static struct intel_uncore_type skx_uncore_upi = { .name = "upi", .num_counters = 4, @@ -4151,6 +4408,10 @@ static struct intel_uncore_type skx_uncore_upi = { .box_ctl = SKX_UPI_PCI_PMON_BOX_CTL, .ops = &skx_upi_uncore_pci_ops, .format_group = &skx_upi_uncore_format_group, + .attr_update = skx_upi_attr_update, + .get_topology = skx_upi_get_topology, + .set_mapping = skx_upi_set_mapping, + .cleanup_mapping = skx_upi_cleanup_mapping, }; static void skx_m2m_uncore_pci_init_box(struct intel_uncore_box *box) @@ -4461,11 +4722,6 @@ static int sad_cfg_iio_topology(struct intel_uncore_type *type, u8 *sad_pmon_map int die, stack_id, ret = -EPERM; struct pci_dev *dev = NULL; - type->topology = kcalloc(uncore_max_dies(), sizeof(*type->topology), - GFP_KERNEL); - if (!type->topology) - return -ENOMEM; - while ((dev = pci_get_device(PCI_VENDOR_ID_INTEL, SNR_ICX_MESH2IIO_MMAP_DID, dev))) { ret = pci_read_config_dword(dev, SNR_ICX_SAD_CONTROL_CFG, &sad_cfg); if (ret) { @@ -4483,14 +4739,12 @@ static int sad_cfg_iio_topology(struct intel_uncore_type *type, u8 *sad_pmon_map /* Convert stack id from SAD_CONTROL to PMON notation. */ stack_id = sad_pmon_mapping[stack_id]; - ((u8 *)&(type->topology[die].configuration))[stack_id] = dev->bus->number; - type->topology[die].segment = pci_domain_nr(dev->bus); + type->topology[die][stack_id].iio->segment = pci_domain_nr(dev->bus); + type->topology[die][stack_id].pmu_idx = stack_id; + type->topology[die][stack_id].iio->pci_bus_no = dev->bus->number; } - if (ret) { - kfree(type->topology); - type->topology = NULL; - } + pci_dev_put(dev); return ret; } @@ -4519,14 +4773,14 @@ static int snr_iio_get_topology(struct intel_uncore_type *type) return sad_cfg_iio_topology(type, snr_sad_pmon_mapping); } -static int snr_iio_set_mapping(struct intel_uncore_type *type) +static void snr_iio_set_mapping(struct intel_uncore_type *type) { - return pmu_iio_set_mapping(type, &snr_iio_mapping_group); + pmu_iio_set_mapping(type, &snr_iio_mapping_group); } static void snr_iio_cleanup_mapping(struct intel_uncore_type *type) { - pmu_iio_cleanup_mapping(type, &snr_iio_mapping_group); + pmu_cleanup_mapping(type, &snr_iio_mapping_group); } static struct event_constraint snr_uncore_iio_constraints[] = { @@ -4857,6 +5111,8 @@ static int snr_uncore_mmio_map(struct intel_uncore_box *box, addr += box_ctl; + pci_dev_put(pdev); + box->io_addr = ioremap(addr, type->mmio_map_size); if (!box->io_addr) { pr_warn("perf uncore: Failed to ioremap for %s.\n", type->name); @@ -5137,14 +5393,19 @@ static int icx_iio_get_topology(struct intel_uncore_type *type) return sad_cfg_iio_topology(type, icx_sad_pmon_mapping); } -static int icx_iio_set_mapping(struct intel_uncore_type *type) +static void icx_iio_set_mapping(struct intel_uncore_type *type) { - return pmu_iio_set_mapping(type, &icx_iio_mapping_group); + /* Detect ICX-D system. This case is not supported */ + if (boot_cpu_data.x86_model == INTEL_FAM6_ICELAKE_D) { + pmu_clear_mapping_attr(type->attr_update, &icx_iio_mapping_group); + return; + } + pmu_iio_set_mapping(type, &icx_iio_mapping_group); } static void icx_iio_cleanup_mapping(struct intel_uncore_type *type) { - pmu_iio_cleanup_mapping(type, &icx_iio_mapping_group); + pmu_cleanup_mapping(type, &icx_iio_mapping_group); } static struct intel_uncore_type icx_uncore_iio = { @@ -5337,6 +5598,76 @@ static const struct attribute_group icx_upi_uncore_format_group = { .attrs = icx_upi_uncore_formats_attr, }; +#define ICX_UPI_REGS_ADDR_DEVICE_LINK0 0x02 +#define ICX_UPI_REGS_ADDR_FUNCTION 0x01 + +static int discover_upi_topology(struct intel_uncore_type *type, int ubox_did, int dev_link0) +{ + struct pci_dev *ubox = NULL; + struct pci_dev *dev = NULL; + u32 nid, gid; + int i, idx, ret = -EPERM; + struct intel_uncore_topology *upi; + unsigned int devfn; + + /* GIDNIDMAP method supports machines which have less than 8 sockets. */ + if (uncore_max_dies() > 8) + goto err; + + while ((ubox = pci_get_device(PCI_VENDOR_ID_INTEL, ubox_did, ubox))) { + ret = upi_nodeid_groupid(ubox, SKX_CPUNODEID, SKX_GIDNIDMAP, &nid, &gid); + if (ret) { + ret = pcibios_err_to_errno(ret); + break; + } + + for (i = 0; i < 8; i++) { + if (nid != GIDNIDMAP(gid, i)) + continue; + for (idx = 0; idx < type->num_boxes; idx++) { + upi = &type->topology[nid][idx]; + devfn = PCI_DEVFN(dev_link0 + idx, ICX_UPI_REGS_ADDR_FUNCTION); + dev = pci_get_domain_bus_and_slot(pci_domain_nr(ubox->bus), + ubox->bus->number, + devfn); + if (dev) { + ret = upi_fill_topology(dev, upi, idx); + if (ret) + goto err; + } + } + } + } +err: + pci_dev_put(ubox); + pci_dev_put(dev); + return ret; +} + +static int icx_upi_get_topology(struct intel_uncore_type *type) +{ + return discover_upi_topology(type, ICX_UBOX_DID, ICX_UPI_REGS_ADDR_DEVICE_LINK0); +} + +static struct attribute_group icx_upi_mapping_group = { + .is_visible = skx_upi_mapping_visible, +}; + +static const struct attribute_group *icx_upi_attr_update[] = { + &icx_upi_mapping_group, + NULL +}; + +static void icx_upi_set_mapping(struct intel_uncore_type *type) +{ + pmu_upi_set_mapping(type, &icx_upi_mapping_group); +} + +static void icx_upi_cleanup_mapping(struct intel_uncore_type *type) +{ + pmu_cleanup_mapping(type, &icx_upi_mapping_group); +} + static struct intel_uncore_type icx_uncore_upi = { .name = "upi", .num_counters = 4, @@ -5349,6 +5680,10 @@ static struct intel_uncore_type icx_uncore_upi = { .box_ctl = ICX_UPI_PCI_PMON_BOX_CTL, .ops = &skx_upi_uncore_pci_ops, .format_group = &icx_upi_uncore_format_group, + .attr_update = icx_upi_attr_update, + .get_topology = icx_upi_get_topology, + .set_mapping = icx_upi_set_mapping, + .cleanup_mapping = icx_upi_cleanup_mapping, }; static struct event_constraint icx_uncore_m3upi_constraints[] = { @@ -5780,9 +6115,43 @@ static struct intel_uncore_type spr_uncore_m2m = { .name = "m2m", }; +static struct attribute_group spr_upi_mapping_group = { + .is_visible = skx_upi_mapping_visible, +}; + +static const struct attribute_group *spr_upi_attr_update[] = { + &uncore_alias_group, + &spr_upi_mapping_group, + NULL +}; + +#define SPR_UPI_REGS_ADDR_DEVICE_LINK0 0x01 + +static void spr_upi_set_mapping(struct intel_uncore_type *type) +{ + pmu_upi_set_mapping(type, &spr_upi_mapping_group); +} + +static void spr_upi_cleanup_mapping(struct intel_uncore_type *type) +{ + pmu_cleanup_mapping(type, &spr_upi_mapping_group); +} + +static int spr_upi_get_topology(struct intel_uncore_type *type) +{ + return discover_upi_topology(type, SPR_UBOX_DID, SPR_UPI_REGS_ADDR_DEVICE_LINK0); +} + static struct intel_uncore_type spr_uncore_upi = { - SPR_UNCORE_PCI_COMMON_FORMAT(), + .event_mask = SNBEP_PMON_RAW_EVENT_MASK, + .event_mask_ext = SPR_RAW_EVENT_MASK_EXT, + .format_group = &spr_uncore_raw_format_group, + .ops = &spr_uncore_pci_ops, .name = "upi", + .attr_update = spr_upi_attr_update, + .get_topology = spr_upi_get_topology, + .set_mapping = spr_upi_set_mapping, + .cleanup_mapping = spr_upi_cleanup_mapping, }; static struct intel_uncore_type spr_uncore_m3upi = { @@ -5986,6 +6355,12 @@ static void uncore_type_customized_copy(struct intel_uncore_type *to_type, to_type->format_group = from_type->format_group; if (from_type->attr_update) to_type->attr_update = from_type->attr_update; + if (from_type->set_mapping) + to_type->set_mapping = from_type->set_mapping; + if (from_type->get_topology) + to_type->get_topology = from_type->get_topology; + if (from_type->cleanup_mapping) + to_type->cleanup_mapping = from_type->cleanup_mapping; } static struct intel_uncore_type ** diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 332d2e6d8ae4..0e849f28a5c1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -811,7 +811,7 @@ struct x86_pmu { void (*cpu_dead)(int cpu); void (*check_microcode)(void); - void (*sched_task)(struct perf_event_context *ctx, + void (*sched_task)(struct perf_event_pmu_context *pmu_ctx, bool sched_in); /* @@ -894,12 +894,12 @@ struct x86_pmu { int num_topdown_events; /* - * perf task context (i.e. struct perf_event_context::task_ctx_data) + * perf task context (i.e. struct perf_event_pmu_context::task_ctx_data) * switch helper to bridge calls from perf/core to perf/x86. * See struct pmu::swap_task_ctx() usage for examples; */ - void (*swap_task_ctx)(struct perf_event_context *prev, - struct perf_event_context *next); + void (*swap_task_ctx)(struct perf_event_pmu_context *prev_epc, + struct perf_event_pmu_context *next_epc); /* * AMD bits @@ -925,7 +925,7 @@ struct x86_pmu { int (*aux_output_match) (struct perf_event *event); - int (*filter_match)(struct perf_event *event); + void (*filter)(struct pmu *pmu, int cpu, bool *ret); /* * Hybrid support * @@ -1180,8 +1180,6 @@ int x86_pmu_handle_irq(struct pt_regs *regs); void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed, u64 intel_ctrl); -void x86_pmu_update_cpu_context(struct pmu *pmu, int cpu); - extern struct event_constraint emptyconstraint; extern struct event_constraint unconstrained; @@ -1306,7 +1304,7 @@ void amd_pmu_lbr_reset(void); void amd_pmu_lbr_read(void); void amd_pmu_lbr_add(struct perf_event *event); void amd_pmu_lbr_del(struct perf_event *event); -void amd_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); +void amd_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in); void amd_pmu_lbr_enable_all(void); void amd_pmu_lbr_disable_all(void); int amd_pmu_lbr_hw_config(struct perf_event *event); @@ -1322,7 +1320,6 @@ void amd_brs_enable_all(void); void amd_brs_disable_all(void); void amd_brs_drain(void); void amd_brs_lopwr_init(void); -void amd_brs_disable_all(void); int amd_brs_hw_config(struct perf_event *event); void amd_brs_reset(void); @@ -1330,7 +1327,7 @@ static inline void amd_pmu_brs_add(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - perf_sched_cb_inc(event->ctx->pmu); + perf_sched_cb_inc(event->pmu); cpuc->lbr_users++; /* * No need to reset BRS because it is reset @@ -1345,10 +1342,10 @@ static inline void amd_pmu_brs_del(struct perf_event *event) cpuc->lbr_users--; WARN_ON_ONCE(cpuc->lbr_users < 0); - perf_sched_cb_dec(event->ctx->pmu); + perf_sched_cb_dec(event->pmu); } -void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in); +void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in); #else static inline int amd_brs_init(void) { @@ -1373,7 +1370,7 @@ static inline void amd_pmu_brs_del(struct perf_event *event) { } -static inline void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in) +static inline void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in) { } @@ -1533,7 +1530,7 @@ void intel_pmu_pebs_enable_all(void); void intel_pmu_pebs_disable_all(void); -void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in); +void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in); void intel_pmu_auto_reload_read(struct perf_event *event); @@ -1541,10 +1538,10 @@ void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr); void intel_ds_init(void); -void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev, - struct perf_event_context *next); +void intel_pmu_lbr_swap_task_ctx(struct perf_event_pmu_context *prev_epc, + struct perf_event_pmu_context *next_epc); -void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); +void intel_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in); u64 lbr_from_signext_quirk_wr(u64 val); diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index f49bc3ec76e6..41ef036ebb7b 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -77,7 +77,7 @@ static int hyperv_init_ghcb(void) static int hv_cpu_init(unsigned int cpu) { union hv_vp_assist_msr_contents msr = { 0 }; - struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()]; + struct hv_vp_assist_page **hvp = &hv_vp_assist_page[cpu]; int ret; ret = hv_common_cpu_init(cpu); @@ -87,34 +87,32 @@ static int hv_cpu_init(unsigned int cpu) if (!hv_vp_assist_page) return 0; - if (!*hvp) { - if (hv_root_partition) { - /* - * For root partition we get the hypervisor provided VP assist - * page, instead of allocating a new page. - */ - rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); - *hvp = memremap(msr.pfn << - HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT, - PAGE_SIZE, MEMREMAP_WB); - } else { - /* - * The VP assist page is an "overlay" page (see Hyper-V TLFS's - * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed - * out to make sure we always write the EOI MSR in - * hv_apic_eoi_write() *after* the EOI optimization is disabled - * in hv_cpu_die(), otherwise a CPU may not be stopped in the - * case of CPU offlining and the VM will hang. - */ + if (hv_root_partition) { + /* + * For root partition we get the hypervisor provided VP assist + * page, instead of allocating a new page. + */ + rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); + *hvp = memremap(msr.pfn << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT, + PAGE_SIZE, MEMREMAP_WB); + } else { + /* + * The VP assist page is an "overlay" page (see Hyper-V TLFS's + * Section 5.2.1 "GPA Overlay Pages"). Here it must be zeroed + * out to make sure we always write the EOI MSR in + * hv_apic_eoi_write() *after* the EOI optimization is disabled + * in hv_cpu_die(), otherwise a CPU may not be stopped in the + * case of CPU offlining and the VM will hang. + */ + if (!*hvp) *hvp = __vmalloc(PAGE_SIZE, GFP_KERNEL | __GFP_ZERO); - if (*hvp) - msr.pfn = vmalloc_to_pfn(*hvp); - } - WARN_ON(!(*hvp)); - if (*hvp) { - msr.enable = 1; - wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); - } + if (*hvp) + msr.pfn = vmalloc_to_pfn(*hvp); + + } + if (!WARN_ON(!(*hvp))) { + msr.enable = 1; + wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64); } return hyperv_init_ghcb(); @@ -464,6 +462,8 @@ void __init hyperv_init(void) BUG_ON(!src); memcpy_to_page(pg, 0, src, HV_HYP_PAGE_SIZE); memunmap(src); + + hv_remap_tsc_clocksource(); } else { hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg); wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); @@ -537,8 +537,6 @@ void hyperv_cleanup(void) union hv_x64_msr_hypercall_contents hypercall_msr; union hv_reference_tsc_msr tsc_msr; - unregister_syscore_ops(&hv_syscore_ops); - /* Reset our OS id */ wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0); hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, 0); diff --git a/arch/x86/ia32/Makefile b/arch/x86/ia32/Makefile index e481056698de..333556a86b2a 100644 --- a/arch/x86/ia32/Makefile +++ b/arch/x86/ia32/Makefile @@ -3,7 +3,5 @@ # Makefile for the ia32 kernel emulation subsystem. # -obj-$(CONFIG_IA32_EMULATION) := ia32_signal.o - audit-class-$(CONFIG_AUDIT) := audit.o obj-$(CONFIG_IA32_EMULATION) += $(audit-class-y) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 9542c582d546..7659217f4d49 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -78,8 +78,43 @@ extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); extern void apply_retpolines(s32 *start, s32 *end); extern void apply_returns(s32 *start, s32 *end); extern void apply_ibt_endbr(s32 *start, s32 *end); +extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine, + s32 *start_cfi, s32 *end_cfi); struct module; +struct paravirt_patch_site; + +struct callthunk_sites { + s32 *call_start, *call_end; + struct paravirt_patch_site *pv_start, *pv_end; +}; + +#ifdef CONFIG_CALL_THUNKS +extern void callthunks_patch_builtin_calls(void); +extern void callthunks_patch_module_calls(struct callthunk_sites *sites, + struct module *mod); +extern void *callthunks_translate_call_dest(void *dest); +extern bool is_callthunk(void *addr); +extern int x86_call_depth_emit_accounting(u8 **pprog, void *func); +#else +static __always_inline void callthunks_patch_builtin_calls(void) {} +static __always_inline void +callthunks_patch_module_calls(struct callthunk_sites *sites, + struct module *mod) {} +static __always_inline void *callthunks_translate_call_dest(void *dest) +{ + return dest; +} +static __always_inline bool is_callthunk(void *addr) +{ + return false; +} +static __always_inline int x86_call_depth_emit_accounting(u8 **pprog, + void *func) +{ + return 0; +} +#endif #ifdef CONFIG_SMP extern void alternatives_smp_module_add(struct module *mod, char *name, @@ -347,6 +382,7 @@ static inline int alternatives_text_reserved(void *start, void *end) #define old_len 141b-140b #define new_len1 144f-143f #define new_len2 145f-144f +#define new_len3 146f-145f /* * gas compatible max based on the idea from: @@ -354,7 +390,8 @@ static inline int alternatives_text_reserved(void *start, void *end) * * The additional "-" is needed because gas uses a "true" value of -1. */ -#define alt_max_short(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) +#define alt_max_2(a, b) ((a) ^ (((a) ^ (b)) & -(-((a) < (b))))) +#define alt_max_3(a, b, c) (alt_max_2(alt_max_2(a, b), c)) /* @@ -366,13 +403,36 @@ static inline int alternatives_text_reserved(void *start, void *end) 140: \oldinstr 141: - .skip -((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \ - (alt_max_short(new_len1, new_len2) - (old_len)),0x90 + .skip -((alt_max_2(new_len1, new_len2) - (old_len)) > 0) * \ + (alt_max_2(new_len1, new_len2) - (old_len)),0x90 +142: + + .pushsection .altinstructions,"a" + altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f + altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f + .popsection + + .pushsection .altinstr_replacement,"ax" +143: + \newinstr1 +144: + \newinstr2 +145: + .popsection +.endm + +.macro ALTERNATIVE_3 oldinstr, newinstr1, feature1, newinstr2, feature2, newinstr3, feature3 +140: + \oldinstr +141: + .skip -((alt_max_3(new_len1, new_len2, new_len3) - (old_len)) > 0) * \ + (alt_max_3(new_len1, new_len2, new_len3) - (old_len)),0x90 142: .pushsection .altinstructions,"a" altinstruction_entry 140b,143f,\feature1,142b-140b,144f-143f altinstruction_entry 140b,144f,\feature2,142b-140b,145f-144f + altinstruction_entry 140b,145f,\feature3,142b-140b,146f-145f .popsection .pushsection .altinstr_replacement,"ax" @@ -381,6 +441,8 @@ static inline int alternatives_text_reserved(void *start, void *end) 144: \newinstr2 145: + \newinstr3 +146: .popsection .endm diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 3415321c8240..3216da7074ba 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -249,7 +249,6 @@ static inline u64 native_x2apic_icr_read(void) extern int x2apic_mode; extern int x2apic_phys; extern void __init x2apic_set_max_apicid(u32 apicid); -extern void __init check_x2apic(void); extern void x2apic_setup(void); static inline int x2apic_enabled(void) { @@ -258,13 +257,13 @@ static inline int x2apic_enabled(void) #define x2apic_supported() (boot_cpu_has(X86_FEATURE_X2APIC)) #else /* !CONFIG_X86_X2APIC */ -static inline void check_x2apic(void) { } static inline void x2apic_setup(void) { } static inline int x2apic_enabled(void) { return 0; } #define x2apic_mode (0) #define x2apic_supported() (0) #endif /* !CONFIG_X86_X2APIC */ +extern void __init check_x2apic(void); struct irq_data; diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h index 86b2e0dcc4bf..ce9685fc78d8 100644 --- a/arch/x86/include/asm/cacheinfo.h +++ b/arch/x86/include/asm/cacheinfo.h @@ -2,7 +2,20 @@ #ifndef _ASM_X86_CACHEINFO_H #define _ASM_X86_CACHEINFO_H +/* Kernel controls MTRR and/or PAT MSRs. */ +extern unsigned int memory_caching_control; +#define CACHE_MTRR 0x01 +#define CACHE_PAT 0x02 + void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu); void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu); +void cache_disable(void); +void cache_enable(void); +void set_cache_aps_delayed_init(bool val); +bool get_cache_aps_delayed_init(void); +void cache_bp_init(void); +void cache_bp_restore(void); +void cache_aps_init(void); + #endif /* _ASM_X86_CACHEINFO_H */ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index b472ef76826a..78796b98a544 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -95,5 +95,7 @@ static inline bool intel_cpu_signatures_match(unsigned int s1, unsigned int p1, } extern u64 x86_read_arch_cap_msr(void); +int intel_find_matching_signature(void *mc, unsigned int csig, int cpf); +int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type); #endif /* _ASM_X86_CPU_H */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index b71f4f2ecdd5..61012476d66e 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -304,10 +304,16 @@ #define X86_FEATURE_UNRET (11*32+15) /* "" AMD BTB untrain return */ #define X86_FEATURE_USE_IBPB_FW (11*32+16) /* "" Use IBPB during runtime firmware calls */ #define X86_FEATURE_RSB_VMEXIT_LITE (11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */ +#define X86_FEATURE_SGX_EDECCSSA (11*32+18) /* "" SGX EDECCSSA user leaf function */ +#define X86_FEATURE_CALL_DEPTH (11*32+19) /* "" Call depth tracking for RSB stuffing */ +#define X86_FEATURE_MSR_TSX_CTRL (11*32+20) /* "" MSR IA32_TSX_CTRL (Intel) implemented */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ +#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ +#define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */ +#define X86_FEATURE_AVX_IFMA (12*32+23) /* "" Support for VPMADD52[H,L]UQ */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h index 70b2db18165e..9bee3e7bf973 100644 --- a/arch/x86/include/asm/cpuid.h +++ b/arch/x86/include/asm/cpuid.h @@ -1,13 +1,132 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* * CPUID-related helpers/definitions - * - * Derived from arch/x86/kvm/cpuid.c */ #ifndef _ASM_X86_CPUID_H #define _ASM_X86_CPUID_H +#include <asm/string.h> + +struct cpuid_regs { + u32 eax, ebx, ecx, edx; +}; + +enum cpuid_regs_idx { + CPUID_EAX = 0, + CPUID_EBX, + CPUID_ECX, + CPUID_EDX, +}; + +#ifdef CONFIG_X86_32 +extern int have_cpuid_p(void); +#else +static inline int have_cpuid_p(void) +{ + return 1; +} +#endif +static inline void native_cpuid(unsigned int *eax, unsigned int *ebx, + unsigned int *ecx, unsigned int *edx) +{ + /* ecx is often an input as well as an output. */ + asm volatile("cpuid" + : "=a" (*eax), + "=b" (*ebx), + "=c" (*ecx), + "=d" (*edx) + : "0" (*eax), "2" (*ecx) + : "memory"); +} + +#define native_cpuid_reg(reg) \ +static inline unsigned int native_cpuid_##reg(unsigned int op) \ +{ \ + unsigned int eax = op, ebx, ecx = 0, edx; \ + \ + native_cpuid(&eax, &ebx, &ecx, &edx); \ + \ + return reg; \ +} + +/* + * Native CPUID functions returning a single datum. + */ +native_cpuid_reg(eax) +native_cpuid_reg(ebx) +native_cpuid_reg(ecx) +native_cpuid_reg(edx) + +#ifdef CONFIG_PARAVIRT_XXL +#include <asm/paravirt.h> +#else +#define __cpuid native_cpuid +#endif + +/* + * Generic CPUID function + * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx + * resulting in stale register contents being returned. + */ +static inline void cpuid(unsigned int op, + unsigned int *eax, unsigned int *ebx, + unsigned int *ecx, unsigned int *edx) +{ + *eax = op; + *ecx = 0; + __cpuid(eax, ebx, ecx, edx); +} + +/* Some CPUID calls want 'count' to be placed in ecx */ +static inline void cpuid_count(unsigned int op, int count, + unsigned int *eax, unsigned int *ebx, + unsigned int *ecx, unsigned int *edx) +{ + *eax = op; + *ecx = count; + __cpuid(eax, ebx, ecx, edx); +} + +/* + * CPUID functions returning a single datum + */ +static inline unsigned int cpuid_eax(unsigned int op) +{ + unsigned int eax, ebx, ecx, edx; + + cpuid(op, &eax, &ebx, &ecx, &edx); + + return eax; +} + +static inline unsigned int cpuid_ebx(unsigned int op) +{ + unsigned int eax, ebx, ecx, edx; + + cpuid(op, &eax, &ebx, &ecx, &edx); + + return ebx; +} + +static inline unsigned int cpuid_ecx(unsigned int op) +{ + unsigned int eax, ebx, ecx, edx; + + cpuid(op, &eax, &ebx, &ecx, &edx); + + return ecx; +} + +static inline unsigned int cpuid_edx(unsigned int op) +{ + unsigned int eax, ebx, ecx, edx; + + cpuid(op, &eax, &ebx, &ecx, &edx); + + return edx; +} + static __always_inline bool cpuid_function_is_indexed(u32 function) { switch (function) { @@ -31,4 +150,22 @@ static __always_inline bool cpuid_function_is_indexed(u32 function) return false; } +#define for_each_possible_hypervisor_cpuid_base(function) \ + for (function = 0x40000000; function < 0x40010000; function += 0x100) + +static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) +{ + uint32_t base, eax, signature[3]; + + for_each_possible_hypervisor_cpuid_base(base) { + cpuid(base, &eax, &signature[0], &signature[1], &signature[2]); + + if (!memcmp(sig, signature, 12) && + (leaves == 0 || ((eax - base) >= leaves))) + return base; + } + + return 0; +} + #endif /* _ASM_X86_CPUID_H */ diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h index 3e204e6140b5..a1168e7b69e5 100644 --- a/arch/x86/include/asm/current.h +++ b/arch/x86/include/asm/current.h @@ -3,16 +3,42 @@ #define _ASM_X86_CURRENT_H #include <linux/compiler.h> -#include <asm/percpu.h> #ifndef __ASSEMBLY__ + +#include <linux/cache.h> +#include <asm/percpu.h> + struct task_struct; -DECLARE_PER_CPU(struct task_struct *, current_task); +struct pcpu_hot { + union { + struct { + struct task_struct *current_task; + int preempt_count; + int cpu_number; +#ifdef CONFIG_CALL_DEPTH_TRACKING + u64 call_depth; +#endif + unsigned long top_of_stack; + void *hardirq_stack_ptr; + u16 softirq_pending; +#ifdef CONFIG_X86_64 + bool hardirq_stack_inuse; +#else + void *softirq_stack_ptr; +#endif + }; + u8 pad[64]; + }; +}; +static_assert(sizeof(struct pcpu_hot) == 64); + +DECLARE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot); static __always_inline struct task_struct *get_current(void) { - return this_cpu_read_stable(current_task); + return this_cpu_read_stable(pcpu_hot.current_task); } #define current get_current() diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index cfdf307ddc01..b049d950612f 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -2,8 +2,8 @@ #ifndef _ASM_X86_DEBUGREG_H #define _ASM_X86_DEBUGREG_H - #include <linux/bug.h> +#include <linux/percpu.h> #include <uapi/asm/debugreg.h> DECLARE_PER_CPU(unsigned long, cpu_dr7); diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 33d2cd04d254..c44b56f7ffba 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -69,6 +69,12 @@ # define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31)) #endif +#ifdef CONFIG_CALL_DEPTH_TRACKING +# define DISABLE_CALL_DEPTH_TRACKING 0 +#else +# define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) +#endif + #ifdef CONFIG_INTEL_IOMMU_SVM # define DISABLE_ENQCMD 0 #else @@ -81,6 +87,12 @@ # define DISABLE_SGX (1 << (X86_FEATURE_SGX & 31)) #endif +#ifdef CONFIG_XEN_PV +# define DISABLE_XENPV 0 +#else +# define DISABLE_XENPV (1 << (X86_FEATURE_XENPV & 31)) +#endif + #ifdef CONFIG_INTEL_TDX_GUEST # define DISABLE_TDX_GUEST 0 #else @@ -98,10 +110,11 @@ #define DISABLED_MASK5 0 #define DISABLED_MASK6 0 #define DISABLED_MASK7 (DISABLE_PTI) -#define DISABLED_MASK8 (DISABLE_TDX_GUEST) +#define DISABLED_MASK8 (DISABLE_XENPV|DISABLE_TDX_GUEST) #define DISABLED_MASK9 (DISABLE_SGX) #define DISABLED_MASK10 0 -#define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET) +#define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ + DISABLE_CALL_DEPTH_TRACKING) #define DISABLED_MASK12 0 #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index 233ae6986d6f..a63154e049d7 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -178,7 +178,7 @@ struct efi_setup_data { extern u64 efi_setup; #ifdef CONFIG_EFI -extern efi_status_t __efi64_thunk(u32, ...); +extern u64 __efi64_thunk(u32, ...); #define efi64_thunk(...) ({ \ u64 __pad[3]; /* must have space for 3 args on the stack */ \ @@ -228,16 +228,15 @@ static inline bool efi_is_native(void) return efi_is_64bit(); } -#define efi_mixed_mode_cast(attr) \ - __builtin_choose_expr( \ - __builtin_types_compatible_p(u32, __typeof__(attr)), \ - (unsigned long)(attr), (attr)) - #define efi_table_attr(inst, attr) \ - (efi_is_native() \ - ? inst->attr \ - : (__typeof__(inst->attr)) \ - efi_mixed_mode_cast(inst->mixed_mode.attr)) + (efi_is_native() ? (inst)->attr \ + : efi_mixed_table_attr((inst), attr)) + +#define efi_mixed_table_attr(inst, attr) \ + (__typeof__(inst->attr)) \ + _Generic(inst->mixed_mode.attr, \ + u32: (unsigned long)(inst->mixed_mode.attr), \ + default: (inst->mixed_mode.attr)) /* * The following macros allow translating arguments if necessary from native to @@ -325,6 +324,17 @@ static inline u32 efi64_convert_status(efi_status_t status) #define __efi64_argmap_set_memory_space_attributes(phys, size, flags) \ (__efi64_split(phys), __efi64_split(size), __efi64_split(flags)) +/* file protocol */ +#define __efi64_argmap_open(prot, newh, fname, mode, attr) \ + ((prot), efi64_zero_upper(newh), (fname), __efi64_split(mode), \ + __efi64_split(attr)) + +#define __efi64_argmap_set_position(pos) (__efi64_split(pos)) + +/* file system protocol */ +#define __efi64_argmap_open_volume(prot, file) \ + ((prot), efi64_zero_upper(file)) + /* * The macros below handle the plumbing for the argument mapping. To add a * mapping for a specific EFI method, simply define a macro @@ -344,31 +354,27 @@ static inline u32 efi64_convert_status(efi_status_t status) #define __efi_eat(...) #define __efi_eval(...) __VA_ARGS__ -/* The three macros below handle dispatching via the thunk if needed */ - -#define efi_call_proto(inst, func, ...) \ - (efi_is_native() \ - ? inst->func(inst, ##__VA_ARGS__) \ - : __efi64_thunk_map(inst, func, inst, ##__VA_ARGS__)) +static inline efi_status_t __efi64_widen_efi_status(u64 status) +{ + /* use rotate to move the value of bit #31 into position #63 */ + return ror64(rol32(status, 1), 1); +} -#define efi_bs_call(func, ...) \ - (efi_is_native() \ - ? efi_system_table->boottime->func(__VA_ARGS__) \ - : __efi64_thunk_map(efi_table_attr(efi_system_table, \ - boottime), \ - func, __VA_ARGS__)) +/* The macro below handles dispatching via the thunk if needed */ -#define efi_rt_call(func, ...) \ - (efi_is_native() \ - ? efi_system_table->runtime->func(__VA_ARGS__) \ - : __efi64_thunk_map(efi_table_attr(efi_system_table, \ - runtime), \ - func, __VA_ARGS__)) +#define efi_fn_call(inst, func, ...) \ + (efi_is_native() ? (inst)->func(__VA_ARGS__) \ + : efi_mixed_call((inst), func, ##__VA_ARGS__)) -#define efi_dxe_call(func, ...) \ - (efi_is_native() \ - ? efi_dxe_table->func(__VA_ARGS__) \ - : __efi64_thunk_map(efi_dxe_table, func, __VA_ARGS__)) +#define efi_mixed_call(inst, func, ...) \ + _Generic(inst->func(__VA_ARGS__), \ + efi_status_t: \ + __efi64_widen_efi_status( \ + __efi64_thunk_map(inst, func, ##__VA_ARGS__)), \ + u64: ({ BUILD_BUG(); ULONG_MAX; }), \ + default: \ + (__typeof__(inst->func(__VA_ARGS__))) \ + __efi64_thunk_map(inst, func, ##__VA_ARGS__)) #else /* CONFIG_EFI_MIXED */ @@ -400,13 +406,52 @@ static inline void efi_reserve_boot_services(void) #ifdef CONFIG_EFI_FAKE_MEMMAP extern void __init efi_fake_memmap_early(void); +extern void __init efi_fake_memmap(void); #else static inline void efi_fake_memmap_early(void) { } + +static inline void efi_fake_memmap(void) +{ +} #endif +extern int __init efi_memmap_alloc(unsigned int num_entries, + struct efi_memory_map_data *data); +extern void __efi_memmap_free(u64 phys, unsigned long size, + unsigned long flags); +#define __efi_memmap_free __efi_memmap_free + +extern int __init efi_memmap_install(struct efi_memory_map_data *data); +extern int __init efi_memmap_split_count(efi_memory_desc_t *md, + struct range *range); +extern void __init efi_memmap_insert(struct efi_memory_map *old_memmap, + void *buf, struct efi_mem_range *mem); + #define arch_ima_efi_boot_mode \ ({ extern struct boot_params boot_params; boot_params.secure_boot; }) +#ifdef CONFIG_EFI_RUNTIME_MAP +int efi_get_runtime_map_size(void); +int efi_get_runtime_map_desc_size(void); +int efi_runtime_map_copy(void *buf, size_t bufsz); +#else +static inline int efi_get_runtime_map_size(void) +{ + return 0; +} + +static inline int efi_get_runtime_map_desc_size(void) +{ + return 0; +} + +static inline int efi_runtime_map_copy(void *buf, size_t bufsz) +{ + return 0; +} + +#endif + #endif /* _ASM_X86_EFI_H */ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index cb0ff1055ab1..18fd06f7936a 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -152,10 +152,6 @@ do { \ (elf_check_arch_ia32(x) || \ (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) -#if __USER32_DS != __USER_DS -# error "The following code assumes __USER32_DS == __USER_DS" -#endif - static inline void elf_common_init(struct thread_struct *t, struct pt_regs *regs, const u16 ds) { @@ -226,7 +222,6 @@ do { \ /* I'm not sure if we can use '-' here */ #define ELF_PLATFORM ("x86_64") extern void set_personality_64bit(void); -extern unsigned int sysctl_vsyscall32; extern int force_personality32; #endif /* !CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h index 674ed46d3ced..117903881fe4 100644 --- a/arch/x86/include/asm/entry-common.h +++ b/arch/x86/include/asm/entry-common.h @@ -24,8 +24,8 @@ static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) /* * For !SMAP hardware we patch out CLAC on entry. */ - if (boot_cpu_has(X86_FEATURE_SMAP) || - (IS_ENABLED(CONFIG_64BIT) && boot_cpu_has(X86_FEATURE_XENPV))) + if (cpu_feature_enabled(X86_FEATURE_SMAP) || + cpu_feature_enabled(X86_FEATURE_XENPV)) mask |= X86_EFLAGS_AC; WARN_ON_ONCE(flags & mask); diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h index e1c9df9102a5..611fa41711af 100644 --- a/arch/x86/include/asm/fpu/signal.h +++ b/arch/x86/include/asm/fpu/signal.h @@ -13,16 +13,9 @@ #ifdef CONFIG_X86_64 # include <uapi/asm/sigcontext.h> # include <asm/user32.h> -struct ksignal; -int ia32_setup_rt_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs); -int ia32_setup_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs); #else # define user_i387_ia32_struct user_i387_struct # define user32_fxsr_struct user_fxsr_struct -# define ia32_setup_frame __setup_frame -# define ia32_setup_rt_frame __setup_rt_frame #endif extern void convert_from_fxsr(struct user_i387_ia32_struct *env, diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h index 908d99b127d3..5061ac98ffa1 100644 --- a/arch/x86/include/asm/ftrace.h +++ b/arch/x86/include/asm/ftrace.h @@ -34,19 +34,6 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; } -/* - * When a ftrace registered caller is tracing a function that is - * also set by a register_ftrace_direct() call, it needs to be - * differentiated in the ftrace_caller trampoline. To do this, we - * place the direct caller in the ORIG_AX part of pt_regs. This - * tells the ftrace_caller that there's a direct caller. - */ -static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) -{ - /* Emulate a call */ - regs->orig_ax = addr; -} - #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS struct ftrace_regs { struct pt_regs regs; @@ -61,9 +48,25 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs) return &fregs->regs; } -#define ftrace_instruction_pointer_set(fregs, _ip) \ +#define ftrace_regs_set_instruction_pointer(fregs, _ip) \ do { (fregs)->regs.ip = (_ip); } while (0) +#define ftrace_regs_get_instruction_pointer(fregs) \ + ((fregs)->regs.ip) + +#define ftrace_regs_get_argument(fregs, n) \ + regs_get_kernel_argument(&(fregs)->regs, n) +#define ftrace_regs_get_stack_pointer(fregs) \ + kernel_stack_pointer(&(fregs)->regs) +#define ftrace_regs_return_value(fregs) \ + regs_return_value(&(fregs)->regs) +#define ftrace_regs_set_return_value(fregs, ret) \ + regs_set_return_value(&(fregs)->regs, ret) +#define ftrace_override_function_with_return(fregs) \ + override_function_with_return(&(fregs)->regs) +#define ftrace_regs_query_register_offset(name) \ + regs_query_register_offset(name) + struct ftrace_ops; #define ftrace_graph_func ftrace_graph_func void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, @@ -72,6 +75,24 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip, #define FTRACE_GRAPH_TRAMP_ADDR FTRACE_GRAPH_ADDR #endif +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS +/* + * When a ftrace registered caller is tracing a function that is + * also set by a register_ftrace_direct() call, it needs to be + * differentiated in the ftrace_caller trampoline. To do this, we + * place the direct caller in the ORIG_AX part of pt_regs. This + * tells the ftrace_caller that there's a direct caller. + */ +static inline void +__arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr) +{ + /* Emulate a call */ + regs->orig_ax = addr; +} +#define arch_ftrace_set_direct_caller(fregs, addr) \ + __arch_ftrace_set_direct_caller(&(fregs)->regs, addr) +#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */ + #ifdef CONFIG_DYNAMIC_FTRACE struct dyn_arch_ftrace { diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 275e7fd20310..66837b8c67f1 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -3,9 +3,9 @@ #define _ASM_X86_HARDIRQ_H #include <linux/threads.h> +#include <asm/current.h> typedef struct { - u16 __softirq_pending; #if IS_ENABLED(CONFIG_KVM_INTEL) u8 kvm_cpu_l1tf_flush_l1d; #endif @@ -60,6 +60,7 @@ extern u64 arch_irq_stat_cpu(unsigned int cpu); extern u64 arch_irq_stat(void); #define arch_irq_stat arch_irq_stat +#define local_softirq_pending_ref pcpu_hot.softirq_pending #if IS_ENABLED(CONFIG_KVM_INTEL) static inline void kvm_set_cpu_l1tf_flush_l1d(void) diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 3089ec352743..08e822bd7aa6 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -61,6 +61,8 @@ #define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE BIT(10) /* Support for debug MSRs available */ #define HV_FEATURE_DEBUG_MSRS_AVAILABLE BIT(11) +/* Support for extended gva ranges for flush hypercalls available */ +#define HV_FEATURE_EXT_GVA_RANGES_FLUSH BIT(14) /* * Support for returning hypercall output block via XMM * registers is available @@ -374,11 +376,20 @@ struct hv_nested_enlightenments_control { struct hv_vp_assist_page { __u32 apic_assist; __u32 reserved1; - __u64 vtl_control[3]; + __u32 vtl_entry_reason; + __u32 vtl_reserved; + __u64 vtl_ret_x64rax; + __u64 vtl_ret_x64rcx; struct hv_nested_enlightenments_control nested_control; __u8 enlighten_vmentry; __u8 reserved2[7]; __u64 current_nested_vmcs; + __u8 synthetic_time_unhalted_timer_expired; + __u8 reserved3[7]; + __u8 virtualization_fault_information[40]; + __u8 reserved4[8]; + __u8 intercept_message[256]; + __u8 vtl_ret_actions[256]; } __packed; struct hv_enlightened_vmcs { @@ -598,6 +609,41 @@ struct hv_enlightened_vmcs { #define HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL 0xFFFF +/* + * Note, Hyper-V isn't actually stealing bit 28 from Intel, just abusing it by + * pairing it with architecturally impossible exit reasons. Bit 28 is set only + * on SMI exits to a SMI transfer monitor (STM) and if and only if a MTF VM-Exit + * is pending. I.e. it will never be set by hardware for non-SMI exits (there + * are only three), nor will it ever be set unless the VMM is an STM. + */ +#define HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH 0x10000031 + +/* + * Hyper-V uses the software reserved 32 bytes in VMCB control area to expose + * SVM enlightenments to guests. + */ +struct hv_vmcb_enlightenments { + struct __packed hv_enlightenments_control { + u32 nested_flush_hypercall:1; + u32 msr_bitmap:1; + u32 enlightened_npt_tlb: 1; + u32 reserved:29; + } __packed hv_enlightenments_control; + u32 hv_vp_id; + u64 hv_vm_id; + u64 partition_assist_page; + u64 reserved; +} __packed; + +/* + * Hyper-V uses the software reserved clean bit in VMCB. + */ +#define HV_VMCB_NESTED_ENLIGHTENMENTS 31 + +/* Synthetic VM-Exit */ +#define HV_SVM_EXITCODE_ENL 0xf0000000 +#define HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH (1) + struct hv_partition_assist_pg { u32 tlb_lock_count; }; diff --git a/arch/x86/include/asm/hyperv_timer.h b/arch/x86/include/asm/hyperv_timer.h new file mode 100644 index 000000000000..388fa81b8f38 --- /dev/null +++ b/arch/x86/include/asm/hyperv_timer.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_HYPERV_TIMER_H +#define _ASM_X86_HYPERV_TIMER_H + +#include <asm/msr.h> + +#define hv_get_raw_timer() rdtsc_ordered() + +#endif diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index 7cc49432187f..7a2ed154a5e1 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -44,10 +44,6 @@ extern int irq_remapping_reenable(int); extern int irq_remap_enable_fault_handling(void); extern void panic_if_irq_remap(const char *msg); -/* Create PCI MSI/MSIx irqdomain, use @parent as the parent irqdomain. */ -extern struct irq_domain * -arch_create_remap_msi_irq_domain(struct irq_domain *par, const char *n, int id); - /* Get parent irqdomain for interrupt remapping irqdomain */ static inline struct irq_domain *arch_get_ir_parent_domain(void) { diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 147cb8fdda92..798183867d78 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -116,7 +116,7 @@ ASM_CALL_ARG2 #define call_on_irqstack(func, asm_call, argconstr...) \ - call_on_stack(__this_cpu_read(hardirq_stack_ptr), \ + call_on_stack(__this_cpu_read(pcpu_hot.hardirq_stack_ptr), \ func, asm_call, argconstr) /* Macros to assert type correctness for run_*_on_irqstack macros */ @@ -135,7 +135,7 @@ * User mode entry and interrupt on the irq stack do not \ * switch stacks. If from user mode the task stack is empty. \ */ \ - if (user_mode(regs) || __this_cpu_read(hardirq_stack_inuse)) { \ + if (user_mode(regs) || __this_cpu_read(pcpu_hot.hardirq_stack_inuse)) { \ irq_enter_rcu(); \ func(c_args); \ irq_exit_rcu(); \ @@ -146,9 +146,9 @@ * places. Invoke the stack switch macro with the call \ * sequence which matches the above direct invocation. \ */ \ - __this_cpu_write(hardirq_stack_inuse, true); \ + __this_cpu_write(pcpu_hot.hardirq_stack_inuse, true); \ call_on_irqstack(func, asm_call, constr); \ - __this_cpu_write(hardirq_stack_inuse, false); \ + __this_cpu_write(pcpu_hot.hardirq_stack_inuse, false); \ } \ } @@ -212,9 +212,9 @@ */ #define do_softirq_own_stack() \ { \ - __this_cpu_write(hardirq_stack_inuse, true); \ + __this_cpu_write(pcpu_hot.hardirq_stack_inuse, true); \ call_on_irqstack(__do_softirq, ASM_CALL_ARG0); \ - __this_cpu_write(hardirq_stack_inuse, false); \ + __this_cpu_write(pcpu_hot.hardirq_stack_inuse, false); \ } #endif diff --git a/arch/x86/include/asm/irqdomain.h b/arch/x86/include/asm/irqdomain.h index 125c23b7bad3..30c325c235c0 100644 --- a/arch/x86/include/asm/irqdomain.h +++ b/arch/x86/include/asm/irqdomain.h @@ -7,9 +7,7 @@ #ifdef CONFIG_X86_LOCAL_APIC enum { - /* Allocate contiguous CPU vectors */ - X86_IRQ_ALLOC_CONTIGUOUS_VECTORS = 0x1, - X86_IRQ_ALLOC_LEGACY = 0x2, + X86_IRQ_ALLOC_LEGACY = 0x1, }; extern int x86_fwspec_is_ioapic(struct irq_fwspec *fwspec); diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 82ba4a564e58..abccd51dcfca 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -110,10 +110,12 @@ KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt) KVM_X86_OP_OPTIONAL(set_hv_timer) KVM_X86_OP_OPTIONAL(cancel_hv_timer) KVM_X86_OP(setup_mce) +#ifdef CONFIG_KVM_SMM KVM_X86_OP(smi_allowed) KVM_X86_OP(enter_smm) KVM_X86_OP(leave_smm) KVM_X86_OP(enable_smi_window) +#endif KVM_X86_OP_OPTIONAL(mem_enc_ioctl) KVM_X86_OP_OPTIONAL(mem_enc_register_region) KVM_X86_OP_OPTIONAL(mem_enc_unregister_region) @@ -123,7 +125,7 @@ KVM_X86_OP_OPTIONAL(guest_memory_reclaimed) KVM_X86_OP(get_msr_feature) KVM_X86_OP(can_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) -KVM_X86_OP_OPTIONAL(enable_direct_tlbflush) +KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush) KVM_X86_OP_OPTIONAL(migrate_timers) KVM_X86_OP(msr_filter_changed) KVM_X86_OP(complete_emulated_msr) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f05ebaa26f0f..f35f1ff4427b 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -25,6 +25,7 @@ #include <linux/clocksource.h> #include <linux/irqbypass.h> #include <linux/hyperv.h> +#include <linux/kfifo.h> #include <asm/apic.h> #include <asm/pvclock-abi.h> @@ -81,7 +82,9 @@ #define KVM_REQ_NMI KVM_ARCH_REQ(9) #define KVM_REQ_PMU KVM_ARCH_REQ(10) #define KVM_REQ_PMI KVM_ARCH_REQ(11) +#ifdef CONFIG_KVM_SMM #define KVM_REQ_SMI KVM_ARCH_REQ(12) +#endif #define KVM_REQ_MASTERCLOCK_UPDATE KVM_ARCH_REQ(13) #define KVM_REQ_MCLOCK_INPROGRESS \ KVM_ARCH_REQ_FLAGS(14, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) @@ -108,6 +111,8 @@ KVM_ARCH_REQ_FLAGS(30, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_MMU_FREE_OBSOLETE_ROOTS \ KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) +#define KVM_REQ_HV_TLB_FLUSH \ + KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define CR0_RESERVED_BITS \ (~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \ @@ -204,6 +209,7 @@ typedef enum exit_fastpath_completion fastpath_t; struct x86_emulate_ctxt; struct x86_exception; +union kvm_smram; enum x86_intercept; enum x86_intercept_stage; @@ -253,16 +259,16 @@ enum x86_intercept_stage; #define PFERR_GUEST_PAGE_BIT 33 #define PFERR_IMPLICIT_ACCESS_BIT 48 -#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT) -#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT) -#define PFERR_USER_MASK (1U << PFERR_USER_BIT) -#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT) -#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT) -#define PFERR_PK_MASK (1U << PFERR_PK_BIT) -#define PFERR_SGX_MASK (1U << PFERR_SGX_BIT) -#define PFERR_GUEST_FINAL_MASK (1ULL << PFERR_GUEST_FINAL_BIT) -#define PFERR_GUEST_PAGE_MASK (1ULL << PFERR_GUEST_PAGE_BIT) -#define PFERR_IMPLICIT_ACCESS (1ULL << PFERR_IMPLICIT_ACCESS_BIT) +#define PFERR_PRESENT_MASK BIT(PFERR_PRESENT_BIT) +#define PFERR_WRITE_MASK BIT(PFERR_WRITE_BIT) +#define PFERR_USER_MASK BIT(PFERR_USER_BIT) +#define PFERR_RSVD_MASK BIT(PFERR_RSVD_BIT) +#define PFERR_FETCH_MASK BIT(PFERR_FETCH_BIT) +#define PFERR_PK_MASK BIT(PFERR_PK_BIT) +#define PFERR_SGX_MASK BIT(PFERR_SGX_BIT) +#define PFERR_GUEST_FINAL_MASK BIT_ULL(PFERR_GUEST_FINAL_BIT) +#define PFERR_GUEST_PAGE_MASK BIT_ULL(PFERR_GUEST_PAGE_BIT) +#define PFERR_IMPLICIT_ACCESS BIT_ULL(PFERR_IMPLICIT_ACCESS_BIT) #define PFERR_NESTED_GUEST_PAGE (PFERR_GUEST_PAGE_MASK | \ PFERR_WRITE_MASK | \ @@ -488,17 +494,19 @@ enum pmc_type { struct kvm_pmc { enum pmc_type type; u8 idx; + bool is_paused; + bool intr; u64 counter; + u64 prev_counter; u64 eventsel; struct perf_event *perf_event; struct kvm_vcpu *vcpu; /* + * only for creating or reusing perf_event, * eventsel value for general purpose counters, * ctrl value for fixed counters. */ u64 current_config; - bool is_paused; - bool intr; }; /* More counters may conflict with other existing Architectural MSRs */ @@ -524,7 +532,16 @@ struct kvm_pmu { struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED]; struct irq_work irq_work; - DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX); + + /* + * Overlay the bitmap with a 64-bit atomic so that all bits can be + * set in a single access, e.g. to reprogram all counters when the PMU + * filter changes. + */ + union { + DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX); + atomic64_t __reprogram_pmi; + }; DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX); DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX); @@ -602,6 +619,29 @@ struct kvm_vcpu_hv_synic { bool dont_zero_synic_pages; }; +/* The maximum number of entries on the TLB flush fifo. */ +#define KVM_HV_TLB_FLUSH_FIFO_SIZE (16) +/* + * Note: the following 'magic' entry is made up by KVM to avoid putting + * anything besides GVA on the TLB flush fifo. It is theoretically possible + * to observe a request to flush 4095 PFNs starting from 0xfffffffffffff000 + * which will look identical. KVM's action to 'flush everything' instead of + * flushing these particular addresses is, however, fully legitimate as + * flushing more than requested is always OK. + */ +#define KVM_HV_TLB_FLUSHALL_ENTRY ((u64)-1) + +enum hv_tlb_flush_fifos { + HV_L1_TLB_FLUSH_FIFO, + HV_L2_TLB_FLUSH_FIFO, + HV_NR_TLB_FLUSH_FIFOS, +}; + +struct kvm_vcpu_hv_tlb_flush_fifo { + spinlock_t write_lock; + DECLARE_KFIFO(entries, u64, KVM_HV_TLB_FLUSH_FIFO_SIZE); +}; + /* Hyper-V per vcpu emulation context */ struct kvm_vcpu_hv { struct kvm_vcpu *vcpu; @@ -623,6 +663,19 @@ struct kvm_vcpu_hv { u32 nested_eax; /* HYPERV_CPUID_NESTED_FEATURES.EAX */ u32 nested_ebx; /* HYPERV_CPUID_NESTED_FEATURES.EBX */ } cpuid_cache; + + struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS]; + + /* Preallocated buffer for handling hypercalls passing sparse vCPU set */ + u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS]; + + struct hv_vp_assist_page vp_assist_page; + + struct { + u64 pa_page_gpa; + u64 vm_id; + u32 vp_id; + } nested; }; /* Xen HVM per vcpu emulation context */ @@ -633,6 +686,7 @@ struct kvm_vcpu_xen { struct gfn_to_pfn_cache vcpu_info_cache; struct gfn_to_pfn_cache vcpu_time_info_cache; struct gfn_to_pfn_cache runstate_cache; + struct gfn_to_pfn_cache runstate2_cache; u64 last_steal; u64 runstate_entry_time; u64 runstate_times[4]; @@ -1059,6 +1113,7 @@ struct msr_bitmap_range { struct kvm_xen { u32 xen_version; bool long_mode; + bool runstate_update_flag; u8 upcall_vector; struct gfn_to_pfn_cache shinfo_cache; struct idr evtchn_ports; @@ -1156,7 +1211,18 @@ struct kvm_arch { struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES]; struct list_head active_mmu_pages; struct list_head zapped_obsolete_pages; - struct list_head lpage_disallowed_mmu_pages; + /* + * A list of kvm_mmu_page structs that, if zapped, could possibly be + * replaced by an NX huge page. A shadow page is on this list if its + * existence disallows an NX huge page (nx_huge_page_disallowed is set) + * and there are no other conditions that prevent a huge page, e.g. + * the backing host page is huge, dirtly logging is not enabled for its + * memslot, etc... Note, zapping shadow pages on this list doesn't + * guarantee an NX huge page will be created in its stead, e.g. if the + * guest attempts to execute from the region then KVM obviously can't + * create an NX huge page (without hanging the guest). + */ + struct list_head possible_nx_huge_pages; struct kvm_page_track_notifier_node mmu_sp_tracker; struct kvm_page_track_notifier_head track_notifier_head; /* @@ -1272,7 +1338,7 @@ struct kvm_arch { bool sgx_provisioning_allowed; struct kvm_pmu_event_filter __rcu *pmu_event_filter; - struct task_struct *nx_lpage_recovery_thread; + struct task_struct *nx_huge_page_recovery_thread; #ifdef CONFIG_X86_64 /* @@ -1284,6 +1350,9 @@ struct kvm_arch { */ bool tdp_mmu_enabled; + /* The number of TDP MMU pages across all roots. */ + atomic64_t tdp_mmu_pages; + /* * List of kvm_mmu_page structs being used as roots. * All kvm_mmu_page structs in the list should have @@ -1305,20 +1374,12 @@ struct kvm_arch { struct list_head tdp_mmu_roots; /* - * List of kvm_mmu_page structs not being used as roots. - * All kvm_mmu_page structs in the list should have - * tdp_mmu_page set and a tdp_mmu_root_count of 0. - */ - struct list_head tdp_mmu_pages; - - /* * Protects accesses to the following fields when the MMU lock * is held in read mode: * - tdp_mmu_roots (above) - * - tdp_mmu_pages (above) * - the link field of kvm_mmu_page structs used by the TDP MMU - * - lpage_disallowed_mmu_pages - * - the lpage_disallowed_link field of kvm_mmu_page structs used + * - possible_nx_huge_pages; + * - the possible_nx_huge_page_link field of kvm_mmu_page structs used * by the TDP MMU * It is acceptable, but not necessary, to acquire this lock when * the thread holds the MMU lock in write mode. @@ -1612,10 +1673,12 @@ struct kvm_x86_ops { void (*setup_mce)(struct kvm_vcpu *vcpu); +#ifdef CONFIG_KVM_SMM int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection); - int (*enter_smm)(struct kvm_vcpu *vcpu, char *smstate); - int (*leave_smm)(struct kvm_vcpu *vcpu, const char *smstate); + int (*enter_smm)(struct kvm_vcpu *vcpu, union kvm_smram *smram); + int (*leave_smm)(struct kvm_vcpu *vcpu, const union kvm_smram *smram); void (*enable_smi_window)(struct kvm_vcpu *vcpu); +#endif int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp); int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp); @@ -1630,7 +1693,7 @@ struct kvm_x86_ops { void *insn, int insn_len); bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu); - int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu); + int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu); void (*migrate_timers)(struct kvm_vcpu *vcpu); void (*msr_filter_changed)(struct kvm_vcpu *vcpu); @@ -1663,6 +1726,7 @@ struct kvm_x86_nested_ops { int (*enable_evmcs)(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); uint16_t (*get_evmcs_version)(struct kvm_vcpu *vcpu); + void (*hv_inject_synthetic_vmexit_post_tlb_flush)(struct kvm_vcpu *vcpu); }; struct kvm_x86_init_ops { @@ -1844,6 +1908,7 @@ int kvm_emulate_ap_reset_hold(struct kvm_vcpu *vcpu); int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); +void kvm_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg); void kvm_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); @@ -1909,8 +1974,6 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu); gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); -gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, - struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception); gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, @@ -1994,14 +2057,18 @@ enum { #define HF_NMI_MASK (1 << 3) #define HF_IRET_MASK (1 << 4) #define HF_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ + +#ifdef CONFIG_KVM_SMM #define HF_SMM_MASK (1 << 6) #define HF_SMM_INSIDE_NMI_MASK (1 << 7) -#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE -#define KVM_ADDRESS_SPACE_NUM 2 - -#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) -#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) +# define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE +# define KVM_ADDRESS_SPACE_NUM 2 +# define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) +# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) +#else +# define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0) +#endif #define KVM_ARCH_WANT_MMU_NOTIFIER @@ -2089,14 +2156,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu) #endif } -#define put_smstate(type, buf, offset, val) \ - *(type *)((buf) + (offset) - 0x7e00) = val - -#define GET_SMSTATE(type, buf, offset) \ - (*(type *)((buf) + (offset) - 0x7e00)) - -int kvm_cpu_dirty_log_size(void); - int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages); #define KVM_CLOCK_VALID_FLAGS \ diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index f484d656d34e..dd9b8118f784 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -12,13 +12,26 @@ #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0))) #endif /* CONFIG_X86_32 */ -#ifdef __ASSEMBLY__ - -#if defined(CONFIG_X86_64) || defined(CONFIG_X86_ALIGNMENT_16) -#define __ALIGN .p2align 4, 0x90 +#define __ALIGN .balign CONFIG_FUNCTION_ALIGNMENT, 0x90; #define __ALIGN_STR __stringify(__ALIGN) + +#if defined(CONFIG_CALL_PADDING) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#define FUNCTION_PADDING .skip CONFIG_FUNCTION_ALIGNMENT, 0x90; +#else +#define FUNCTION_PADDING +#endif + +#if (CONFIG_FUNCTION_ALIGNMENT > 8) && !defined(__DISABLE_EXPORTS) && !defined(BULID_VDSO) +# define __FUNC_ALIGN __ALIGN; FUNCTION_PADDING +#else +# define __FUNC_ALIGN __ALIGN #endif +#define ASM_FUNC_ALIGN __stringify(__FUNC_ALIGN) +#define SYM_F_ALIGN __FUNC_ALIGN + +#ifdef __ASSEMBLY__ + #if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) #define RET jmp __x86_return_thunk #else /* CONFIG_RETPOLINE */ @@ -43,11 +56,45 @@ #endif /* __ASSEMBLY__ */ +/* + * Depending on -fpatchable-function-entry=N,N usage (CONFIG_CALL_PADDING) the + * CFI symbol layout changes. + * + * Without CALL_THUNKS: + * + * .align FUNCTION_ALIGNMENT + * __cfi_##name: + * .skip FUNCTION_PADDING, 0x90 + * .byte 0xb8 + * .long __kcfi_typeid_##name + * name: + * + * With CALL_THUNKS: + * + * .align FUNCTION_ALIGNMENT + * __cfi_##name: + * .byte 0xb8 + * .long __kcfi_typeid_##name + * .skip FUNCTION_PADDING, 0x90 + * name: + * + * In both cases the whole thing is FUNCTION_ALIGNMENT aligned and sized. + */ + +#ifdef CONFIG_CALL_PADDING +#define CFI_PRE_PADDING +#define CFI_POST_PADDING .skip CONFIG_FUNCTION_PADDING_BYTES, 0x90; +#else +#define CFI_PRE_PADDING .skip CONFIG_FUNCTION_PADDING_BYTES, 0x90; +#define CFI_POST_PADDING +#endif + #define __CFI_TYPE(name) \ SYM_START(__cfi_##name, SYM_L_LOCAL, SYM_A_NONE) \ - .fill 11, 1, 0x90 ASM_NL \ + CFI_PRE_PADDING \ .byte 0xb8 ASM_NL \ .long __kcfi_typeid_##name ASM_NL \ + CFI_POST_PADDING \ SYM_FUNC_END(__cfi_##name) /* SYM_TYPED_FUNC_START -- use for indirectly called globals, w/ CFI type */ @@ -57,7 +104,7 @@ /* SYM_FUNC_START -- use for global functions */ #define SYM_FUNC_START(name) \ - SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \ + SYM_START(name, SYM_L_GLOBAL, SYM_F_ALIGN) \ ENDBR /* SYM_FUNC_START_NOALIGN -- use for global functions, w/o alignment */ @@ -67,7 +114,7 @@ /* SYM_FUNC_START_LOCAL -- use for local functions */ #define SYM_FUNC_START_LOCAL(name) \ - SYM_START(name, SYM_L_LOCAL, SYM_A_ALIGN) \ + SYM_START(name, SYM_L_LOCAL, SYM_F_ALIGN) \ ENDBR /* SYM_FUNC_START_LOCAL_NOALIGN -- use for local functions, w/o alignment */ @@ -77,7 +124,7 @@ /* SYM_FUNC_START_WEAK -- use for weak functions */ #define SYM_FUNC_START_WEAK(name) \ - SYM_START(name, SYM_L_WEAK, SYM_A_ALIGN) \ + SYM_START(name, SYM_L_WEAK, SYM_F_ALIGN) \ ENDBR /* SYM_FUNC_START_WEAK_NOALIGN -- use for weak functions, w/o alignment */ diff --git a/arch/x86/include/asm/memtype.h b/arch/x86/include/asm/memtype.h index 9ca760e430b9..113b2fa51849 100644 --- a/arch/x86/include/asm/memtype.h +++ b/arch/x86/include/asm/memtype.h @@ -6,9 +6,8 @@ #include <asm/pgtable_types.h> extern bool pat_enabled(void); -extern void pat_disable(const char *reason); -extern void pat_init(void); -extern void init_cache_modes(void); +extern void pat_bp_init(void); +extern void pat_cpu_init(void); extern int memtype_reserve(u64 start, u64 end, enum page_cache_mode req_pcm, enum page_cache_mode *ret_pcm); diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index 74ecc2bd6cd0..d5a58bde091c 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -33,8 +33,7 @@ enum ucode_state { }; struct microcode_ops { - enum ucode_state (*request_microcode_fw) (int cpu, struct device *, - bool refresh_fw); + enum ucode_state (*request_microcode_fw) (int cpu, struct device *); void (*microcode_fini_cpu) (int cpu); @@ -50,7 +49,6 @@ struct microcode_ops { struct ucode_cpu_info { struct cpu_signature cpu_sig; - int valid; void *mc; }; extern struct ucode_cpu_info ucode_cpu_info[]; diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h index 4c92cea7e4b5..f1fa979e05bf 100644 --- a/arch/x86/include/asm/microcode_intel.h +++ b/arch/x86/include/asm/microcode_intel.h @@ -14,7 +14,8 @@ struct microcode_header_intel { unsigned int pf; unsigned int datasize; unsigned int totalsize; - unsigned int reserved[3]; + unsigned int metasize; + unsigned int reserved[2]; }; struct microcode_intel { @@ -41,6 +42,8 @@ struct extended_sigtable { #define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE) #define EXT_HEADER_SIZE (sizeof(struct extended_sigtable)) #define EXT_SIGNATURE_SIZE (sizeof(struct extended_signature)) +#define MC_HEADER_TYPE_MICROCODE 1 +#define MC_HEADER_TYPE_IFS 2 #define get_totalsize(mc) \ (((struct microcode_intel *)mc)->hdr.datasize ? \ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 61f0c206bff0..6d502f3efb0f 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -19,8 +19,6 @@ typedef int (*hyperv_fill_flush_list_func)( struct hv_guest_mapping_flush_list *flush, void *data); -#define hv_get_raw_timer() rdtsc_ordered() - void hyperv_vector_handler(struct pt_regs *regs); #if IS_ENABLED(CONFIG_HYPERV) diff --git a/arch/x86/include/asm/msi.h b/arch/x86/include/asm/msi.h index d71c7e8b738d..935c6d470341 100644 --- a/arch/x86/include/asm/msi.h +++ b/arch/x86/include/asm/msi.h @@ -62,4 +62,10 @@ typedef struct x86_msi_addr_hi { struct msi_msg; u32 x86_msi_msg_get_destid(struct msi_msg *msg, bool extid); +#define X86_VECTOR_MSI_FLAGS_SUPPORTED \ + (MSI_GENERIC_FLAGS_MASK | MSI_FLAG_PCI_MSIX | MSI_FLAG_PCI_MSIX_ALLOC_DYN) + +#define X86_VECTOR_MSI_FLAGS_REQUIRED \ + (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS) + #endif /* _ASM_X86_MSI_H */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 4a2af82553e4..37ff47552bcb 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -4,12 +4,7 @@ #include <linux/bits.h> -/* - * CPU model specific register (MSR) numbers. - * - * Do not add new entries to this file unless the definitions are shared - * between multiple compilation units. - */ +/* CPU model specific register (MSR) numbers. */ /* x86-64 specific MSRs */ #define MSR_EFER 0xc0000080 /* extended feature register */ @@ -798,6 +793,7 @@ #define ENERGY_PERF_BIAS_PERFORMANCE 0 #define ENERGY_PERF_BIAS_BALANCE_PERFORMANCE 4 #define ENERGY_PERF_BIAS_NORMAL 6 +#define ENERGY_PERF_BIAS_NORMAL_POWERSAVE 7 #define ENERGY_PERF_BIAS_BALANCE_POWERSAVE 8 #define ENERGY_PERF_BIAS_POWERSAVE 15 @@ -1052,6 +1048,20 @@ #define VMX_BASIC_MEM_TYPE_WB 6LLU #define VMX_BASIC_INOUT 0x0040000000000000LLU +/* Resctrl MSRs: */ +/* - Intel: */ +#define MSR_IA32_L3_QOS_CFG 0xc81 +#define MSR_IA32_L2_QOS_CFG 0xc82 +#define MSR_IA32_QM_EVTSEL 0xc8d +#define MSR_IA32_QM_CTR 0xc8e +#define MSR_IA32_PQR_ASSOC 0xc8f +#define MSR_IA32_L3_CBM_BASE 0xc90 +#define MSR_IA32_L2_CBM_BASE 0xd10 +#define MSR_IA32_MBA_THRTL_BASE 0xd50 + +/* - AMD: */ +#define MSR_IA32_MBA_BW_BASE 0xc0000200 + /* MSR_IA32_VMX_MISC bits */ #define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14) #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h index 76d726074c16..f0eeaf6e5f5f 100644 --- a/arch/x86/include/asm/mtrr.h +++ b/arch/x86/include/asm/mtrr.h @@ -25,13 +25,12 @@ #include <uapi/asm/mtrr.h> -void mtrr_bp_init(void); - /* * The following functions are for use by other drivers that cannot use * arch_phys_wc_add and arch_phys_wc_del. */ # ifdef CONFIG_MTRR +void mtrr_bp_init(void); extern u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform); extern void mtrr_save_fixed_ranges(void *); extern void mtrr_save_state(void); @@ -42,12 +41,12 @@ extern int mtrr_add_page(unsigned long base, unsigned long size, extern int mtrr_del(int reg, unsigned long base, unsigned long size); extern int mtrr_del_page(int reg, unsigned long base, unsigned long size); extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi); -extern void mtrr_ap_init(void); -extern void set_mtrr_aps_delayed_init(void); -extern void mtrr_aps_init(void); extern void mtrr_bp_restore(void); extern int mtrr_trim_uncached_memory(unsigned long end_pfn); extern int amd_special_default_mtrr(void); +void mtrr_disable(void); +void mtrr_enable(void); +void mtrr_generic_set_state(void); # else static inline u8 mtrr_type_lookup(u64 addr, u64 end, u8 *uniform) { @@ -83,10 +82,11 @@ static inline int mtrr_trim_uncached_memory(unsigned long end_pfn) static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi) { } -#define mtrr_ap_init() do {} while (0) -#define set_mtrr_aps_delayed_init() do {} while (0) -#define mtrr_aps_init() do {} while (0) +#define mtrr_bp_init() do {} while (0) #define mtrr_bp_restore() do {} while (0) +#define mtrr_disable() do {} while (0) +#define mtrr_enable() do {} while (0) +#define mtrr_generic_set_state() do {} while (0) # endif #ifdef CONFIG_COMPAT diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index c936ce9f0c47..771b0a2b7a34 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -12,8 +12,104 @@ #include <asm/msr-index.h> #include <asm/unwind_hints.h> #include <asm/percpu.h> +#include <asm/current.h> -#define RETPOLINE_THUNK_SIZE 32 +/* + * Call depth tracking for Intel SKL CPUs to address the RSB underflow + * issue in software. + * + * The tracking does not use a counter. It uses uses arithmetic shift + * right on call entry and logical shift left on return. + * + * The depth tracking variable is initialized to 0x8000.... when the call + * depth is zero. The arithmetic shift right sign extends the MSB and + * saturates after the 12th call. The shift count is 5 for both directions + * so the tracking covers 12 nested calls. + * + * Call + * 0: 0x8000000000000000 0x0000000000000000 + * 1: 0xfc00000000000000 0xf000000000000000 + * ... + * 11: 0xfffffffffffffff8 0xfffffffffffffc00 + * 12: 0xffffffffffffffff 0xffffffffffffffe0 + * + * After a return buffer fill the depth is credited 12 calls before the + * next stuffing has to take place. + * + * There is a inaccuracy for situations like this: + * + * 10 calls + * 5 returns + * 3 calls + * 4 returns + * 3 calls + * .... + * + * The shift count might cause this to be off by one in either direction, + * but there is still a cushion vs. the RSB depth. The algorithm does not + * claim to be perfect and it can be speculated around by the CPU, but it + * is considered that it obfuscates the problem enough to make exploitation + * extremly difficult. + */ +#define RET_DEPTH_SHIFT 5 +#define RSB_RET_STUFF_LOOPS 16 +#define RET_DEPTH_INIT 0x8000000000000000ULL +#define RET_DEPTH_INIT_FROM_CALL 0xfc00000000000000ULL +#define RET_DEPTH_CREDIT 0xffffffffffffffffULL + +#ifdef CONFIG_CALL_THUNKS_DEBUG +# define CALL_THUNKS_DEBUG_INC_CALLS \ + incq %gs:__x86_call_count; +# define CALL_THUNKS_DEBUG_INC_RETS \ + incq %gs:__x86_ret_count; +# define CALL_THUNKS_DEBUG_INC_STUFFS \ + incq %gs:__x86_stuffs_count; +# define CALL_THUNKS_DEBUG_INC_CTXSW \ + incq %gs:__x86_ctxsw_count; +#else +# define CALL_THUNKS_DEBUG_INC_CALLS +# define CALL_THUNKS_DEBUG_INC_RETS +# define CALL_THUNKS_DEBUG_INC_STUFFS +# define CALL_THUNKS_DEBUG_INC_CTXSW +#endif + +#if defined(CONFIG_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS) + +#include <asm/asm-offsets.h> + +#define CREDIT_CALL_DEPTH \ + movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth); + +#define ASM_CREDIT_CALL_DEPTH \ + movq $-1, PER_CPU_VAR(pcpu_hot + X86_call_depth); + +#define RESET_CALL_DEPTH \ + mov $0x80, %rax; \ + shl $56, %rax; \ + movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); + +#define RESET_CALL_DEPTH_FROM_CALL \ + mov $0xfc, %rax; \ + shl $56, %rax; \ + movq %rax, PER_CPU_VAR(pcpu_hot + X86_call_depth); \ + CALL_THUNKS_DEBUG_INC_CALLS + +#define INCREMENT_CALL_DEPTH \ + sarq $5, %gs:pcpu_hot + X86_call_depth; \ + CALL_THUNKS_DEBUG_INC_CALLS + +#define ASM_INCREMENT_CALL_DEPTH \ + sarq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth); \ + CALL_THUNKS_DEBUG_INC_CALLS + +#else +#define CREDIT_CALL_DEPTH +#define ASM_CREDIT_CALL_DEPTH +#define RESET_CALL_DEPTH +#define INCREMENT_CALL_DEPTH +#define ASM_INCREMENT_CALL_DEPTH +#define RESET_CALL_DEPTH_FROM_CALL +#endif /* * Fill the CPU return stack buffer. @@ -32,6 +128,7 @@ * from C via asm(".include <asm/nospec-branch.h>") but let's not go there. */ +#define RETPOLINE_THUNK_SIZE 32 #define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */ /* @@ -60,7 +157,9 @@ dec reg; \ jnz 771b; \ /* barrier for jnz misprediction */ \ - lfence; + lfence; \ + ASM_CREDIT_CALL_DEPTH \ + CALL_THUNKS_DEBUG_INC_CTXSW #else /* * i386 doesn't unconditionally have LFENCE, as such it can't @@ -185,11 +284,32 @@ * where we have a stack but before any RET instruction. */ .macro UNTRAIN_RET -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) +#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ + defined(CONFIG_CALL_DEPTH_TRACKING) ANNOTATE_UNRET_END - ALTERNATIVE_2 "", \ - CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ - "call entry_ibpb", X86_FEATURE_ENTRY_IBPB + ALTERNATIVE_3 "", \ + CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ + "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \ + __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH +#endif +.endm + +.macro UNTRAIN_RET_FROM_CALL +#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ + defined(CONFIG_CALL_DEPTH_TRACKING) + ANNOTATE_UNRET_END + ALTERNATIVE_3 "", \ + CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET, \ + "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \ + __stringify(RESET_CALL_DEPTH_FROM_CALL), X86_FEATURE_CALL_DEPTH +#endif +.endm + + +.macro CALL_DEPTH_ACCOUNT +#ifdef CONFIG_CALL_DEPTH_TRACKING + ALTERNATIVE "", \ + __stringify(ASM_INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH #endif .endm @@ -203,11 +323,45 @@ typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; extern retpoline_thunk_t __x86_indirect_thunk_array[]; +extern retpoline_thunk_t __x86_indirect_call_thunk_array[]; +extern retpoline_thunk_t __x86_indirect_jump_thunk_array[]; extern void __x86_return_thunk(void); extern void zen_untrain_ret(void); extern void entry_ibpb(void); +#ifdef CONFIG_CALL_THUNKS +extern void (*x86_return_thunk)(void); +#else +#define x86_return_thunk (&__x86_return_thunk) +#endif + +#ifdef CONFIG_CALL_DEPTH_TRACKING +extern void __x86_return_skl(void); + +static inline void x86_set_skl_return_thunk(void) +{ + x86_return_thunk = &__x86_return_skl; +} + +#define CALL_DEPTH_ACCOUNT \ + ALTERNATIVE("", \ + __stringify(INCREMENT_CALL_DEPTH), \ + X86_FEATURE_CALL_DEPTH) + +#ifdef CONFIG_CALL_THUNKS_DEBUG +DECLARE_PER_CPU(u64, __x86_call_count); +DECLARE_PER_CPU(u64, __x86_ret_count); +DECLARE_PER_CPU(u64, __x86_stuffs_count); +DECLARE_PER_CPU(u64, __x86_ctxsw_count); +#endif +#else +static inline void x86_set_skl_return_thunk(void) {} + +#define CALL_DEPTH_ACCOUNT "" + +#endif + #ifdef CONFIG_RETPOLINE #define GEN(reg) \ @@ -215,6 +369,16 @@ extern void entry_ibpb(void); #include <asm/GEN-for-each-reg.h> #undef GEN +#define GEN(reg) \ + extern retpoline_thunk_t __x86_indirect_call_thunk_ ## reg; +#include <asm/GEN-for-each-reg.h> +#undef GEN + +#define GEN(reg) \ + extern retpoline_thunk_t __x86_indirect_jump_thunk_ ## reg; +#include <asm/GEN-for-each-reg.h> +#undef GEN + #ifdef CONFIG_X86_64 /* @@ -321,7 +485,7 @@ static inline void indirect_branch_prediction_barrier(void) /* The Intel SPEC CTRL MSR base value cache */ extern u64 x86_spec_ctrl_base; DECLARE_PER_CPU(u64, x86_spec_ctrl_current); -extern void write_spec_ctrl_current(u64 val, bool force); +extern void update_spec_ctrl_cond(u64 val); extern u64 spec_ctrl_current(void); /* diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 2a0b8dd4ec33..73e9522db7c1 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -4,13 +4,13 @@ /* Various instructions on x86 need to be replaced for * para-virtualization: those hooks are defined here. */ +#include <asm/paravirt_types.h> + #ifdef CONFIG_PARAVIRT #include <asm/pgtable_types.h> #include <asm/asm.h> #include <asm/nospec-branch.h> -#include <asm/paravirt_types.h> - #ifndef __ASSEMBLY__ #include <linux/bug.h> #include <linux/types.h> @@ -665,6 +665,7 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu); asm(".pushsection " section ", \"ax\";" \ ".globl " PV_THUNK_NAME(func) ";" \ ".type " PV_THUNK_NAME(func) ", @function;" \ + ASM_FUNC_ALIGN \ PV_THUNK_NAME(func) ":" \ ASM_ENDBR \ FRAME_BEGIN \ @@ -730,6 +731,18 @@ static __always_inline unsigned long arch_local_irq_save(void) #undef PVOP_VCALL4 #undef PVOP_CALL4 +#define DEFINE_PARAVIRT_ASM(func, instr, sec) \ + asm (".pushsection " #sec ", \"ax\"\n" \ + ".global " #func "\n\t" \ + ".type " #func ", @function\n\t" \ + ASM_FUNC_ALIGN "\n" \ + #func ":\n\t" \ + ASM_ENDBR \ + instr "\n\t" \ + ASM_RET \ + ".size " #func ", . - " #func "\n\t" \ + ".popsection") + extern void default_banner(void); #else /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index f3d601574730..8c1da419260f 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -2,36 +2,23 @@ #ifndef _ASM_X86_PARAVIRT_TYPES_H #define _ASM_X86_PARAVIRT_TYPES_H -/* Bitmask of what can be clobbered: usually at least eax. */ -#define CLBR_EAX (1 << 0) -#define CLBR_ECX (1 << 1) -#define CLBR_EDX (1 << 2) -#define CLBR_EDI (1 << 3) - -#ifdef CONFIG_X86_32 -/* CLBR_ANY should match all regs platform has. For i386, that's just it */ -#define CLBR_ANY ((1 << 4) - 1) - -#define CLBR_ARG_REGS (CLBR_EAX | CLBR_EDX | CLBR_ECX) -#define CLBR_RET_REG (CLBR_EAX | CLBR_EDX) -#else -#define CLBR_RAX CLBR_EAX -#define CLBR_RCX CLBR_ECX -#define CLBR_RDX CLBR_EDX -#define CLBR_RDI CLBR_EDI -#define CLBR_RSI (1 << 4) -#define CLBR_R8 (1 << 5) -#define CLBR_R9 (1 << 6) -#define CLBR_R10 (1 << 7) -#define CLBR_R11 (1 << 8) - -#define CLBR_ANY ((1 << 9) - 1) +#ifndef __ASSEMBLY__ +/* These all sit in the .parainstructions section to tell us what to patch. */ +struct paravirt_patch_site { + u8 *instr; /* original instructions */ + u8 type; /* type of this instruction */ + u8 len; /* length of original instruction */ +}; -#define CLBR_ARG_REGS (CLBR_RDI | CLBR_RSI | CLBR_RDX | \ - CLBR_RCX | CLBR_R8 | CLBR_R9) -#define CLBR_RET_REG (CLBR_RAX) +/* Lazy mode for batching updates / context switch */ +enum paravirt_lazy_mode { + PARAVIRT_LAZY_NONE, + PARAVIRT_LAZY_MMU, + PARAVIRT_LAZY_CPU, +}; +#endif -#endif /* X86_64 */ +#ifdef CONFIG_PARAVIRT #ifndef __ASSEMBLY__ @@ -279,27 +266,23 @@ extern struct paravirt_patch_template pv_ops; #define paravirt_type(op) \ [paravirt_typenum] "i" (PARAVIRT_PATCH(op)), \ [paravirt_opptr] "m" (pv_ops.op) -#define paravirt_clobber(clobber) \ - [paravirt_clobber] "i" (clobber) - /* * Generate some code, and mark it as patchable by the * apply_paravirt() alternate instruction patcher. */ -#define _paravirt_alt(insn_string, type, clobber) \ +#define _paravirt_alt(insn_string, type) \ "771:\n\t" insn_string "\n" "772:\n" \ ".pushsection .parainstructions,\"a\"\n" \ _ASM_ALIGN "\n" \ _ASM_PTR " 771b\n" \ " .byte " type "\n" \ " .byte 772b-771b\n" \ - " .short " clobber "\n" \ _ASM_ALIGN "\n" \ ".popsection\n" /* Generate patchable code, with the default asm parameters. */ #define paravirt_alt(insn_string) \ - _paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]") + _paravirt_alt(insn_string, "%c[paravirt_typenum]") /* Simple instruction patching code. */ #define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t" @@ -451,20 +434,19 @@ int paravirt_disable_iospace(void); }) -#define ____PVOP_CALL(ret, op, clbr, call_clbr, extra_clbr, ...) \ +#define ____PVOP_CALL(ret, op, call_clbr, extra_clbr, ...) \ ({ \ PVOP_CALL_ARGS; \ PVOP_TEST_NULL(op); \ asm volatile(paravirt_alt(PARAVIRT_CALL) \ : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ - paravirt_clobber(clbr), \ ##__VA_ARGS__ \ : "memory", "cc" extra_clbr); \ ret; \ }) -#define ____PVOP_ALT_CALL(ret, op, alt, cond, clbr, call_clbr, \ +#define ____PVOP_ALT_CALL(ret, op, alt, cond, call_clbr, \ extra_clbr, ...) \ ({ \ PVOP_CALL_ARGS; \ @@ -473,45 +455,44 @@ int paravirt_disable_iospace(void); alt, cond) \ : call_clbr, ASM_CALL_CONSTRAINT \ : paravirt_type(op), \ - paravirt_clobber(clbr), \ ##__VA_ARGS__ \ : "memory", "cc" extra_clbr); \ ret; \ }) #define __PVOP_CALL(rettype, op, ...) \ - ____PVOP_CALL(PVOP_RETVAL(rettype), op, CLBR_ANY, \ + ____PVOP_CALL(PVOP_RETVAL(rettype), op, \ PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, ##__VA_ARGS__) #define __PVOP_ALT_CALL(rettype, op, alt, cond, ...) \ - ____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op, alt, cond, CLBR_ANY,\ + ____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op, alt, cond, \ PVOP_CALL_CLOBBERS, EXTRA_CLOBBERS, \ ##__VA_ARGS__) #define __PVOP_CALLEESAVE(rettype, op, ...) \ - ____PVOP_CALL(PVOP_RETVAL(rettype), op.func, CLBR_RET_REG, \ + ____PVOP_CALL(PVOP_RETVAL(rettype), op.func, \ PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__) #define __PVOP_ALT_CALLEESAVE(rettype, op, alt, cond, ...) \ ____PVOP_ALT_CALL(PVOP_RETVAL(rettype), op.func, alt, cond, \ - CLBR_RET_REG, PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__) + PVOP_CALLEE_CLOBBERS, , ##__VA_ARGS__) #define __PVOP_VCALL(op, ...) \ - (void)____PVOP_CALL(, op, CLBR_ANY, PVOP_VCALL_CLOBBERS, \ + (void)____PVOP_CALL(, op, PVOP_VCALL_CLOBBERS, \ VEXTRA_CLOBBERS, ##__VA_ARGS__) #define __PVOP_ALT_VCALL(op, alt, cond, ...) \ - (void)____PVOP_ALT_CALL(, op, alt, cond, CLBR_ANY, \ + (void)____PVOP_ALT_CALL(, op, alt, cond, \ PVOP_VCALL_CLOBBERS, VEXTRA_CLOBBERS, \ ##__VA_ARGS__) #define __PVOP_VCALLEESAVE(op, ...) \ - (void)____PVOP_CALL(, op.func, CLBR_RET_REG, \ + (void)____PVOP_CALL(, op.func, \ PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__) #define __PVOP_ALT_VCALLEESAVE(op, alt, cond, ...) \ - (void)____PVOP_ALT_CALL(, op.func, alt, cond, CLBR_RET_REG, \ + (void)____PVOP_ALT_CALL(, op.func, alt, cond, \ PVOP_VCALLEE_CLOBBERS, , ##__VA_ARGS__) @@ -571,13 +552,6 @@ int paravirt_disable_iospace(void); __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) -/* Lazy mode for batching updates / context switch */ -enum paravirt_lazy_mode { - PARAVIRT_LAZY_NONE, - PARAVIRT_LAZY_MMU, - PARAVIRT_LAZY_CPU, -}; - enum paravirt_lazy_mode paravirt_get_lazy_mode(void); void paravirt_start_context_switch(struct task_struct *prev); void paravirt_end_context_switch(struct task_struct *next); @@ -593,16 +567,9 @@ unsigned long paravirt_ret0(void); #define paravirt_nop ((void *)_paravirt_nop) -/* These all sit in the .parainstructions section to tell us what to patch. */ -struct paravirt_patch_site { - u8 *instr; /* original instructions */ - u8 type; /* type of this instruction */ - u8 len; /* length of original instruction */ -}; - extern struct paravirt_patch_site __parainstructions[], __parainstructions_end[]; #endif /* __ASSEMBLY__ */ - +#endif /* CONFIG_PARAVIRT */ #endif /* _ASM_X86_PARAVIRT_TYPES_H */ diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 736793d65bcb..b40c462b4af3 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -21,7 +21,7 @@ struct pci_sysdata { #ifdef CONFIG_X86_64 void *iommu; /* IOMMU private data */ #endif -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +#ifdef CONFIG_PCI_MSI void *fwnode; /* IRQ domain for MSI assignment */ #endif #if IS_ENABLED(CONFIG_VMD) @@ -52,7 +52,7 @@ static inline int pci_proc_domain(struct pci_bus *bus) } #endif -#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN +#ifdef CONFIG_PCI_MSI static inline void *_pci_root_bus_fwnode(struct pci_bus *bus) { return to_pci_sysdata(bus)->fwnode; @@ -92,6 +92,7 @@ void pcibios_scan_root(int bus); struct irq_routing_table *pcibios_get_irq_routing_table(void); int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); +bool pci_dev_has_default_msi_parent_domain(struct pci_dev *dev); #define HAVE_PCI_MMAP #define arch_can_pci_mmap_wc() pat_enabled() diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 9ac46dbe57d4..5d0f6891ae61 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -543,12 +543,12 @@ static inline void perf_check_microcode(void) { } #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_INTEL) extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data); -extern int x86_perf_get_lbr(struct x86_pmu_lbr *lbr); +extern void x86_perf_get_lbr(struct x86_pmu_lbr *lbr); #else struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr, void *data); -static inline int x86_perf_get_lbr(struct x86_pmu_lbr *lbr) +static inline void x86_perf_get_lbr(struct x86_pmu_lbr *lbr) { - return -1; + memset(lbr, 0, sizeof(*lbr)); } #endif diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5059799bebe3..0564edd24ffb 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -139,6 +139,7 @@ static inline int pmd_dirty(pmd_t pmd) return pmd_flags(pmd) & _PAGE_DIRTY; } +#define pmd_young pmd_young static inline int pmd_young(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_ACCESSED; @@ -291,7 +292,23 @@ static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { - return pte_flags(pte) & _PAGE_UFFD_WP; + bool wp = pte_flags(pte) & _PAGE_UFFD_WP; + +#ifdef CONFIG_DEBUG_VM + /* + * Having write bit for wr-protect-marked present ptes is fatal, + * because it means the uffd-wp bit will be ignored and write will + * just go through. + * + * Use any chance of pgtable walking to verify this (e.g., when + * page swapped out or being migrated for all purposes). It means + * something is already wrong. Tell the admin even before the + * process crashes. We also nail it with wrong pgtable setup. + */ + WARN_ON_ONCE(wp && pte_write(pte)); +#endif + + return wp; } static inline pte_t pte_mkuffd_wp(pte_t pte) @@ -1438,6 +1455,14 @@ static inline bool arch_has_hw_pte_young(void) return true; } +#ifdef CONFIG_XEN_PV +#define arch_has_hw_nonleaf_pmd_young arch_has_hw_nonleaf_pmd_young +static inline bool arch_has_hw_nonleaf_pmd_young(void) +{ + return !cpu_feature_enabled(X86_FEATURE_XENPV); +} +#endif + #ifdef CONFIG_PAGE_TABLE_CHECK static inline bool pte_user_accessible_page(pte_t pte) { diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h index 7c9c968a42ef..7d4ad8907297 100644 --- a/arch/x86/include/asm/pgtable_32.h +++ b/arch/x86/include/asm/pgtable_32.h @@ -48,15 +48,6 @@ do { \ #endif /* !__ASSEMBLY__ */ /* - * kern_addr_valid() is (1) for FLATMEM and (0) for SPARSEMEM - */ -#ifdef CONFIG_FLATMEM -#define kern_addr_valid(addr) (1) -#else -#define kern_addr_valid(kaddr) (0) -#endif - -/* * This is used to calculate the .brk reservation for initial pagetables. * Enough space is reserved to allocate pagetables sufficient to cover all * of LOWMEM_PAGES, which is an upper bound on the size of the direct map of diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index e479491da8d5..7929327abe00 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -240,7 +240,6 @@ static inline void native_pgd_clear(pgd_t *pgd) #define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val }) #define __swp_entry_to_pmd(x) ((pmd_t) { .pmd = (x).val }) -extern int kern_addr_valid(unsigned long addr); extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 5f6daea1ee24..2d13f25b1bd8 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -4,11 +4,11 @@ #include <asm/rmwcc.h> #include <asm/percpu.h> +#include <asm/current.h> + #include <linux/thread_info.h> #include <linux/static_call_types.h> -DECLARE_PER_CPU(int, __preempt_count); - /* We use the MSB mostly because its available */ #define PREEMPT_NEED_RESCHED 0x80000000 @@ -24,7 +24,7 @@ DECLARE_PER_CPU(int, __preempt_count); */ static __always_inline int preempt_count(void) { - return raw_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED; + return raw_cpu_read_4(pcpu_hot.preempt_count) & ~PREEMPT_NEED_RESCHED; } static __always_inline void preempt_count_set(int pc) @@ -32,10 +32,10 @@ static __always_inline void preempt_count_set(int pc) int old, new; do { - old = raw_cpu_read_4(__preempt_count); + old = raw_cpu_read_4(pcpu_hot.preempt_count); new = (old & PREEMPT_NEED_RESCHED) | (pc & ~PREEMPT_NEED_RESCHED); - } while (raw_cpu_cmpxchg_4(__preempt_count, old, new) != old); + } while (raw_cpu_cmpxchg_4(pcpu_hot.preempt_count, old, new) != old); } /* @@ -44,7 +44,7 @@ static __always_inline void preempt_count_set(int pc) #define init_task_preempt_count(p) do { } while (0) #define init_idle_preempt_count(p, cpu) do { \ - per_cpu(__preempt_count, (cpu)) = PREEMPT_DISABLED; \ + per_cpu(pcpu_hot.preempt_count, (cpu)) = PREEMPT_DISABLED; \ } while (0) /* @@ -58,17 +58,17 @@ static __always_inline void preempt_count_set(int pc) static __always_inline void set_preempt_need_resched(void) { - raw_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED); + raw_cpu_and_4(pcpu_hot.preempt_count, ~PREEMPT_NEED_RESCHED); } static __always_inline void clear_preempt_need_resched(void) { - raw_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED); + raw_cpu_or_4(pcpu_hot.preempt_count, PREEMPT_NEED_RESCHED); } static __always_inline bool test_preempt_need_resched(void) { - return !(raw_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED); + return !(raw_cpu_read_4(pcpu_hot.preempt_count) & PREEMPT_NEED_RESCHED); } /* @@ -77,12 +77,12 @@ static __always_inline bool test_preempt_need_resched(void) static __always_inline void __preempt_count_add(int val) { - raw_cpu_add_4(__preempt_count, val); + raw_cpu_add_4(pcpu_hot.preempt_count, val); } static __always_inline void __preempt_count_sub(int val) { - raw_cpu_add_4(__preempt_count, -val); + raw_cpu_add_4(pcpu_hot.preempt_count, -val); } /* @@ -92,7 +92,8 @@ static __always_inline void __preempt_count_sub(int val) */ static __always_inline bool __preempt_count_dec_and_test(void) { - return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var])); + return GEN_UNARY_RMWcc("decl", pcpu_hot.preempt_count, e, + __percpu_arg([var])); } /* @@ -100,7 +101,7 @@ static __always_inline bool __preempt_count_dec_and_test(void) */ static __always_inline bool should_resched(int preempt_offset) { - return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); + return unlikely(raw_cpu_read_4(pcpu_hot.preempt_count) == preempt_offset); } #ifdef CONFIG_PREEMPTION diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 67c9d73b31fa..4e35c66edeb7 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -16,6 +16,7 @@ struct vm86; #include <uapi/asm/sigcontext.h> #include <asm/current.h> #include <asm/cpufeatures.h> +#include <asm/cpuid.h> #include <asm/page.h> #include <asm/pgtable_types.h> #include <asm/percpu.h> @@ -146,17 +147,6 @@ struct cpuinfo_x86 { unsigned initialized : 1; } __randomize_layout; -struct cpuid_regs { - u32 eax, ebx, ecx, edx; -}; - -enum cpuid_regs_idx { - CPUID_EAX = 0, - CPUID_EBX, - CPUID_ECX, - CPUID_EDX, -}; - #define X86_VENDOR_INTEL 0 #define X86_VENDOR_CYRIX 1 #define X86_VENDOR_AMD 2 @@ -205,45 +195,6 @@ extern void identify_secondary_cpu(struct cpuinfo_x86 *); extern void print_cpu_info(struct cpuinfo_x86 *); void print_cpu_msr(struct cpuinfo_x86 *); -#ifdef CONFIG_X86_32 -extern int have_cpuid_p(void); -#else -static inline int have_cpuid_p(void) -{ - return 1; -} -#endif -static inline void native_cpuid(unsigned int *eax, unsigned int *ebx, - unsigned int *ecx, unsigned int *edx) -{ - /* ecx is often an input as well as an output. */ - asm volatile("cpuid" - : "=a" (*eax), - "=b" (*ebx), - "=c" (*ecx), - "=d" (*edx) - : "0" (*eax), "2" (*ecx) - : "memory"); -} - -#define native_cpuid_reg(reg) \ -static inline unsigned int native_cpuid_##reg(unsigned int op) \ -{ \ - unsigned int eax = op, ebx, ecx = 0, edx; \ - \ - native_cpuid(&eax, &ebx, &ecx, &edx); \ - \ - return reg; \ -} - -/* - * Native CPUID functions returning a single datum. - */ -native_cpuid_reg(eax) -native_cpuid_reg(ebx) -native_cpuid_reg(ecx) -native_cpuid_reg(edx) - /* * Friendlier CR3 helpers. */ @@ -426,8 +377,6 @@ struct irq_stack { char stack[IRQ_STACK_SIZE]; } __aligned(IRQ_STACK_SIZE); -DECLARE_PER_CPU(unsigned long, cpu_current_top_of_stack); - #ifdef CONFIG_X86_64 struct fixed_percpu_data { /* @@ -450,8 +399,6 @@ static inline unsigned long cpu_kernelmode_gs_base(int cpu) return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu); } -DECLARE_PER_CPU(void *, hardirq_stack_ptr); -DECLARE_PER_CPU(bool, hardirq_stack_inuse); extern asmlinkage void ignore_sysret(void); /* Save actual FS/GS selectors and bases to current->thread */ @@ -460,8 +407,6 @@ void current_save_fsgs(void); #ifdef CONFIG_STACKPROTECTOR DECLARE_PER_CPU(unsigned long, __stack_chk_guard); #endif -DECLARE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); -DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr); #endif /* !X86_64 */ struct perf_event; @@ -566,7 +511,7 @@ static __always_inline unsigned long current_top_of_stack(void) * and around vm86 mode and sp0 on x86_64 is special because of the * entry trampoline. */ - return this_cpu_read_stable(cpu_current_top_of_stack); + return this_cpu_read_stable(pcpu_hot.top_of_stack); } static __always_inline bool on_thread_stack(void) @@ -578,7 +523,6 @@ static __always_inline bool on_thread_stack(void) #ifdef CONFIG_PARAVIRT_XXL #include <asm/paravirt.h> #else -#define __cpuid native_cpuid static inline void load_sp0(unsigned long sp0) { @@ -589,69 +533,6 @@ static inline void load_sp0(unsigned long sp0) unsigned long __get_wchan(struct task_struct *p); -/* - * Generic CPUID function - * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx - * resulting in stale register contents being returned. - */ -static inline void cpuid(unsigned int op, - unsigned int *eax, unsigned int *ebx, - unsigned int *ecx, unsigned int *edx) -{ - *eax = op; - *ecx = 0; - __cpuid(eax, ebx, ecx, edx); -} - -/* Some CPUID calls want 'count' to be placed in ecx */ -static inline void cpuid_count(unsigned int op, int count, - unsigned int *eax, unsigned int *ebx, - unsigned int *ecx, unsigned int *edx) -{ - *eax = op; - *ecx = count; - __cpuid(eax, ebx, ecx, edx); -} - -/* - * CPUID functions returning a single datum - */ -static inline unsigned int cpuid_eax(unsigned int op) -{ - unsigned int eax, ebx, ecx, edx; - - cpuid(op, &eax, &ebx, &ecx, &edx); - - return eax; -} - -static inline unsigned int cpuid_ebx(unsigned int op) -{ - unsigned int eax, ebx, ecx, edx; - - cpuid(op, &eax, &ebx, &ecx, &edx); - - return ebx; -} - -static inline unsigned int cpuid_ecx(unsigned int op) -{ - unsigned int eax, ebx, ecx, edx; - - cpuid(op, &eax, &ebx, &ecx, &edx); - - return ecx; -} - -static inline unsigned int cpuid_edx(unsigned int op) -{ - unsigned int eax, ebx, ecx, edx; - - cpuid(op, &eax, &ebx, &ecx, &edx); - - return edx; -} - extern void select_idle_routine(const struct cpuinfo_x86 *c); extern void amd_e400_c1e_apic_setup(void); @@ -667,10 +548,9 @@ extern int sysenter_setup(void); /* Defined in head.S */ extern struct desc_ptr early_gdt_descr; -extern void switch_to_new_gdt(int); +extern void switch_gdt_and_percpu_base(int); extern void load_direct_gdt(int); extern void load_fixmap_gdt(int); -extern void load_percpu_segment(int); extern void cpu_init(void); extern void cpu_init_secondary(void); extern void cpu_init_exception_handling(void); @@ -805,24 +685,6 @@ static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } #endif -#define for_each_possible_hypervisor_cpuid_base(function) \ - for (function = 0x40000000; function < 0x40010000; function += 0x100) - -static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves) -{ - uint32_t base, eax, signature[3]; - - for_each_possible_hypervisor_cpuid_base(base) { - cpuid(base, &eax, &signature[0], &signature[1], &signature[2]); - - if (!memcmp(sig, signature, 12) && - (leaves == 0 || ((eax - base) >= leaves))) - return base; - } - - return 0; -} - extern unsigned long arch_align_stack(unsigned long sp); void free_init_pages(const char *what, unsigned long begin, unsigned long end); extern void free_kernel_image_pages(const char *what, void *begin, void *end); diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index dbb38a6b4dfb..42b17cf10b10 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -14,8 +14,6 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text"); #define __pv_queued_spin_unlock __pv_queued_spin_unlock -#define PV_UNLOCK "__raw_callee_save___pv_queued_spin_unlock" -#define PV_UNLOCK_SLOWPATH "__raw_callee_save___pv_queued_spin_unlock_slowpath" /* * Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock @@ -37,32 +35,27 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text"); * rsi = lockval (second argument) * rdx = internal variable (set to 0) */ -asm (".pushsection .spinlock.text, \"ax\";" - ".globl " PV_UNLOCK ";" - ".type " PV_UNLOCK ", @function;" - ".align 4,0x90;" - PV_UNLOCK ": " - ASM_ENDBR - FRAME_BEGIN - "push %rdx;" - "mov $0x1,%eax;" - "xor %edx,%edx;" - LOCK_PREFIX "cmpxchg %dl,(%rdi);" - "cmp $0x1,%al;" - "jne .slowpath;" - "pop %rdx;" +#define PV_UNLOCK_ASM \ + FRAME_BEGIN \ + "push %rdx\n\t" \ + "mov $0x1,%eax\n\t" \ + "xor %edx,%edx\n\t" \ + LOCK_PREFIX "cmpxchg %dl,(%rdi)\n\t" \ + "cmp $0x1,%al\n\t" \ + "jne .slowpath\n\t" \ + "pop %rdx\n\t" \ + FRAME_END \ + ASM_RET \ + ".slowpath:\n\t" \ + "push %rsi\n\t" \ + "movzbl %al,%esi\n\t" \ + "call __raw_callee_save___pv_queued_spin_unlock_slowpath\n\t" \ + "pop %rsi\n\t" \ + "pop %rdx\n\t" \ FRAME_END - ASM_RET - ".slowpath: " - "push %rsi;" - "movzbl %al,%esi;" - "call " PV_UNLOCK_SLOWPATH ";" - "pop %rsi;" - "pop %rdx;" - FRAME_END - ASM_RET - ".size " PV_UNLOCK ", .-" PV_UNLOCK ";" - ".popsection"); + +DEFINE_PARAVIRT_ASM(__raw_callee_save___pv_queued_spin_unlock, + PV_UNLOCK_ASM, .spinlock.text); #else /* CONFIG_64BIT */ diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h index fd6f6e5b755a..a336feef0af1 100644 --- a/arch/x86/include/asm/realmode.h +++ b/arch/x86/include/asm/realmode.h @@ -91,6 +91,7 @@ static inline void set_real_mode_mem(phys_addr_t mem) void reserve_real_mode(void); void load_trampoline_pgtable(void); +void init_real_mode(void); #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index d24b04ebf950..52788f79786f 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -7,8 +7,6 @@ #include <linux/sched.h> #include <linux/jump_label.h> -#define IA32_PQR_ASSOC 0x0c8f - /** * struct resctrl_pqr_state - State cache for the PQR MSR * @cur_rmid: The cached Resource Monitoring ID @@ -16,8 +14,8 @@ * @default_rmid: The user assigned Resource Monitoring ID * @default_closid: The user assigned cached Class Of Service ID * - * The upper 32 bits of IA32_PQR_ASSOC contain closid and the - * lower 10 bits rmid. The update to IA32_PQR_ASSOC always + * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the + * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always * contains both parts, so we need to cache them. This also * stores the user configured per cpu CLOSID and RMID. * @@ -77,7 +75,7 @@ static void __resctrl_sched_in(void) if (closid != state->cur_closid || rmid != state->cur_rmid) { state->cur_closid = closid; state->cur_rmid = rmid; - wrmsr(IA32_PQR_ASSOC, rmid, closid); + wrmsr(MSR_IA32_PQR_ASSOC, rmid, closid); } } diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h index 2e7890dd58a4..c390a672d560 100644 --- a/arch/x86/include/asm/segment.h +++ b/arch/x86/include/asm/segment.h @@ -135,6 +135,7 @@ #define __KERNEL_DS (GDT_ENTRY_KERNEL_DS*8) #define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8 + 3) #define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) +#define __USER32_CS __USER_CS #define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS*8) /* segment for calling fn: */ @@ -210,7 +211,6 @@ #define __KERNEL_DS (GDT_ENTRY_KERNEL_DS*8) #define __USER32_CS (GDT_ENTRY_DEFAULT_USER32_CS*8 + 3) #define __USER_DS (GDT_ENTRY_DEFAULT_USER_DS*8 + 3) -#define __USER32_DS __USER_DS #define __USER_CS (GDT_ENTRY_DEFAULT_USER_CS*8 + 3) #define __CPUNODE_SEG (GDT_ENTRY_CPUNODE*8 + 3) diff --git a/arch/x86/include/asm/sgx.h b/arch/x86/include/asm/sgx.h index eae20fa52b93..6a0069761508 100644 --- a/arch/x86/include/asm/sgx.h +++ b/arch/x86/include/asm/sgx.h @@ -115,17 +115,36 @@ enum sgx_miscselect { * %SGX_ATTR_EINITTOKENKEY: Allow to use token signing key that is used to * sign cryptographic tokens that can be passed to * EINIT as an authorization to run an enclave. + * %SGX_ATTR_ASYNC_EXIT_NOTIFY: Allow enclaves to be notified after an + * asynchronous exit has occurred. */ enum sgx_attribute { - SGX_ATTR_INIT = BIT(0), - SGX_ATTR_DEBUG = BIT(1), - SGX_ATTR_MODE64BIT = BIT(2), - SGX_ATTR_PROVISIONKEY = BIT(4), - SGX_ATTR_EINITTOKENKEY = BIT(5), - SGX_ATTR_KSS = BIT(7), + SGX_ATTR_INIT = BIT(0), + SGX_ATTR_DEBUG = BIT(1), + SGX_ATTR_MODE64BIT = BIT(2), + /* BIT(3) is reserved */ + SGX_ATTR_PROVISIONKEY = BIT(4), + SGX_ATTR_EINITTOKENKEY = BIT(5), + /* BIT(6) is for CET */ + SGX_ATTR_KSS = BIT(7), + /* BIT(8) is reserved */ + /* BIT(9) is reserved */ + SGX_ATTR_ASYNC_EXIT_NOTIFY = BIT(10), }; -#define SGX_ATTR_RESERVED_MASK (BIT_ULL(3) | BIT_ULL(6) | GENMASK_ULL(63, 8)) +#define SGX_ATTR_RESERVED_MASK (BIT_ULL(3) | \ + BIT_ULL(6) | \ + BIT_ULL(8) | \ + BIT_ULL(9) | \ + GENMASK_ULL(63, 11)) + +#define SGX_ATTR_UNPRIV_MASK (SGX_ATTR_DEBUG | \ + SGX_ATTR_MODE64BIT | \ + SGX_ATTR_KSS | \ + SGX_ATTR_ASYNC_EXIT_NOTIFY) + +#define SGX_ATTR_PRIV_MASK (SGX_ATTR_PROVISIONKEY | \ + SGX_ATTR_EINITTOKENKEY) /** * struct sgx_secs - SGX Enclave Control Structure (SECS) diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h index 65e667279e0f..e770c4fc47f4 100644 --- a/arch/x86/include/asm/sighandling.h +++ b/arch/x86/include/asm/sighandling.h @@ -15,4 +15,13 @@ void signal_fault(struct pt_regs *regs, void __user *frame, char *where); +void __user * +get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, + void __user **fpstate); + +int ia32_setup_frame(struct ksignal *ksig, struct pt_regs *regs); +int ia32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs); +int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs); +int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs); + #endif /* _ASM_X86_SIGHANDLING_H */ diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h index 2dfb5fea13af..4a4043ca6493 100644 --- a/arch/x86/include/asm/signal.h +++ b/arch/x86/include/asm/signal.h @@ -28,11 +28,6 @@ typedef struct { #define SA_IA32_ABI 0x02000000u #define SA_X32_ABI 0x01000000u -#ifndef CONFIG_COMPAT -#define compat_sigset_t compat_sigset_t -typedef sigset_t compat_sigset_t; -#endif - #endif /* __ASSEMBLY__ */ #include <uapi/asm/signal.h> #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index a73bced40e24..b4dbb20dab1a 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -3,10 +3,10 @@ #define _ASM_X86_SMP_H #ifndef __ASSEMBLY__ #include <linux/cpumask.h> -#include <asm/percpu.h> -#include <asm/thread_info.h> #include <asm/cpumask.h> +#include <asm/current.h> +#include <asm/thread_info.h> extern int smp_num_siblings; extern unsigned int num_processors; @@ -19,7 +19,6 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id); -DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid); @@ -150,11 +149,10 @@ __visible void smp_call_function_single_interrupt(struct pt_regs *r); /* * This function is needed by all SMP systems. It must _always_ be valid - * from the initial startup. We map APIC_BASE very early in page_setup(), - * so this is correct in the x86 case. + * from the initial startup. */ -#define raw_smp_processor_id() this_cpu_read(cpu_number) -#define __smp_processor_id() __this_cpu_read(cpu_number) +#define raw_smp_processor_id() this_cpu_read(pcpu_hot.cpu_number) +#define __smp_processor_id() __this_cpu_read(pcpu_hot.cpu_number) #ifdef CONFIG_X86_32 extern int safe_smp_processor_id(void); diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h index 24a8d6c4fb18..00473a650f51 100644 --- a/arch/x86/include/asm/stackprotector.h +++ b/arch/x86/include/asm/stackprotector.h @@ -34,7 +34,6 @@ #include <asm/percpu.h> #include <asm/desc.h> -#include <linux/random.h> #include <linux/sched.h> /* @@ -50,22 +49,11 @@ */ static __always_inline void boot_init_stack_canary(void) { - u64 canary; - u64 tsc; + unsigned long canary = get_random_canary(); #ifdef CONFIG_X86_64 BUILD_BUG_ON(offsetof(struct fixed_percpu_data, stack_canary) != 40); #endif - /* - * We both use the random pool and the current TSC as a source - * of randomness. The TSC only matters for very early init, - * there it already has some randomness on most systems. Later - * on during the bootup the random pool has true entropy too. - */ - get_random_bytes(&canary, sizeof(canary)); - tsc = rdtsc(); - canary += tsc + (tsc << 32UL); - canary &= CANARY_MASK; current->stack_canary = canary; #ifdef CONFIG_X86_64 diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 0361626841bc..cb1ee53ad3b1 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -5,6 +5,8 @@ #include <uapi/asm/svm.h> #include <uapi/asm/kvm.h> +#include <asm/hyperv-tlfs.h> + /* * 32-bit intercept words in the VMCB Control Area, starting * at Byte offset 000h. @@ -161,7 +163,10 @@ struct __attribute__ ((__packed__)) vmcb_control_area { * Offset 0x3e0, 32 bytes reserved * for use by hypervisor/software. */ - u8 reserved_sw[32]; + union { + struct hv_vmcb_enlightenments hv_enlightenments; + u8 reserved_sw[32]; + }; }; @@ -293,12 +298,13 @@ struct vmcb_save_area { struct vmcb_seg ldtr; struct vmcb_seg idtr; struct vmcb_seg tr; - u8 reserved_1[42]; + /* Reserved fields are named following their struct offset */ + u8 reserved_0xa0[42]; u8 vmpl; u8 cpl; - u8 reserved_2[4]; + u8 reserved_0xcc[4]; u64 efer; - u8 reserved_3[112]; + u8 reserved_0xd8[112]; u64 cr4; u64 cr3; u64 cr0; @@ -306,7 +312,7 @@ struct vmcb_save_area { u64 dr6; u64 rflags; u64 rip; - u8 reserved_4[88]; + u8 reserved_0x180[88]; u64 rsp; u64 s_cet; u64 ssp; @@ -321,14 +327,14 @@ struct vmcb_save_area { u64 sysenter_esp; u64 sysenter_eip; u64 cr2; - u8 reserved_5[32]; + u8 reserved_0x248[32]; u64 g_pat; u64 dbgctl; u64 br_from; u64 br_to; u64 last_excp_from; u64 last_excp_to; - u8 reserved_6[72]; + u8 reserved_0x298[72]; u32 spec_ctrl; /* Guest version of SPEC_CTRL at 0x2E0 */ } __packed; @@ -349,12 +355,12 @@ struct sev_es_save_area { u64 vmpl2_ssp; u64 vmpl3_ssp; u64 u_cet; - u8 reserved_1[2]; + u8 reserved_0xc8[2]; u8 vmpl; u8 cpl; - u8 reserved_2[4]; + u8 reserved_0xcc[4]; u64 efer; - u8 reserved_3[104]; + u8 reserved_0xd8[104]; u64 xss; u64 cr4; u64 cr3; @@ -371,7 +377,7 @@ struct sev_es_save_area { u64 dr1_addr_mask; u64 dr2_addr_mask; u64 dr3_addr_mask; - u8 reserved_4[24]; + u8 reserved_0x1c0[24]; u64 rsp; u64 s_cet; u64 ssp; @@ -386,21 +392,21 @@ struct sev_es_save_area { u64 sysenter_esp; u64 sysenter_eip; u64 cr2; - u8 reserved_5[32]; + u8 reserved_0x248[32]; u64 g_pat; u64 dbgctl; u64 br_from; u64 br_to; u64 last_excp_from; u64 last_excp_to; - u8 reserved_7[80]; + u8 reserved_0x298[80]; u32 pkru; - u8 reserved_8[20]; - u64 reserved_9; /* rax already available at 0x01f8 */ + u32 tsc_aux; + u8 reserved_0x2f0[24]; u64 rcx; u64 rdx; u64 rbx; - u64 reserved_10; /* rsp already available at 0x01d8 */ + u64 reserved_0x320; /* rsp already available at 0x01d8 */ u64 rbp; u64 rsi; u64 rdi; @@ -412,7 +418,7 @@ struct sev_es_save_area { u64 r13; u64 r14; u64 r15; - u8 reserved_11[16]; + u8 reserved_0x380[16]; u64 guest_exit_info_1; u64 guest_exit_info_2; u64 guest_exit_int_info; @@ -425,7 +431,7 @@ struct sev_es_save_area { u64 pcpu_id; u64 event_inj; u64 xcr0; - u8 reserved_12[16]; + u8 reserved_0x3f0[16]; /* Floating point area */ u64 x87_dp; @@ -443,23 +449,23 @@ struct sev_es_save_area { } __packed; struct ghcb_save_area { - u8 reserved_1[203]; + u8 reserved_0x0[203]; u8 cpl; - u8 reserved_2[116]; + u8 reserved_0xcc[116]; u64 xss; - u8 reserved_3[24]; + u8 reserved_0x148[24]; u64 dr7; - u8 reserved_4[16]; + u8 reserved_0x168[16]; u64 rip; - u8 reserved_5[88]; + u8 reserved_0x180[88]; u64 rsp; - u8 reserved_6[24]; + u8 reserved_0x1e0[24]; u64 rax; - u8 reserved_7[264]; + u8 reserved_0x200[264]; u64 rcx; u64 rdx; u64 rbx; - u8 reserved_8[8]; + u8 reserved_0x320[8]; u64 rbp; u64 rsi; u64 rdi; @@ -471,12 +477,12 @@ struct ghcb_save_area { u64 r13; u64 r14; u64 r15; - u8 reserved_9[16]; + u8 reserved_0x380[16]; u64 sw_exit_code; u64 sw_exit_info_1; u64 sw_exit_info_2; u64 sw_scratch; - u8 reserved_10[56]; + u8 reserved_0x3b0[56]; u64 xcr0; u8 valid_bitmap[16]; u64 x87_state_gpa; @@ -490,7 +496,7 @@ struct ghcb { u8 shared_buffer[GHCB_SHARED_BUF_SIZE]; - u8 reserved_1[10]; + u8 reserved_0xff0[10]; u16 protocol_version; /* negotiated SEV-ES/GHCB protocol version */ u32 ghcb_usage; } __packed; @@ -502,6 +508,9 @@ struct ghcb { #define EXPECTED_VMCB_CONTROL_AREA_SIZE 1024 #define EXPECTED_GHCB_SIZE PAGE_SIZE +#define BUILD_BUG_RESERVED_OFFSET(x, y) \ + ASSERT_STRUCT_OFFSET(struct x, reserved ## _ ## y, y) + static inline void __unused_size_checks(void) { BUILD_BUG_ON(sizeof(struct vmcb_save_area) != EXPECTED_VMCB_SAVE_AREA_SIZE); @@ -509,6 +518,39 @@ static inline void __unused_size_checks(void) BUILD_BUG_ON(sizeof(struct sev_es_save_area) != EXPECTED_SEV_ES_SAVE_AREA_SIZE); BUILD_BUG_ON(sizeof(struct vmcb_control_area) != EXPECTED_VMCB_CONTROL_AREA_SIZE); BUILD_BUG_ON(sizeof(struct ghcb) != EXPECTED_GHCB_SIZE); + + /* Check offsets of reserved fields */ + + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xa0); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xcc); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0xd8); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x180); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x248); + BUILD_BUG_RESERVED_OFFSET(vmcb_save_area, 0x298); + + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xc8); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xcc); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0xd8); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x1c0); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x248); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x298); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x2f0); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x320); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x380); + BUILD_BUG_RESERVED_OFFSET(sev_es_save_area, 0x3f0); + + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x0); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0xcc); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x148); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x168); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x180); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x1e0); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x200); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x320); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x380); + BUILD_BUG_RESERVED_OFFSET(ghcb_save_area, 0x3b0); + + BUILD_BUG_RESERVED_OFFSET(ghcb, 0xff0); } struct vmcb { diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index c08eb0fdd11f..5c91305d09d2 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -66,13 +66,10 @@ static inline void update_task_stack(struct task_struct *task) { /* sp0 always points to the entry trampoline stack, which is constant: */ #ifdef CONFIG_X86_32 - if (static_cpu_has(X86_FEATURE_XENPV)) - load_sp0(task->thread.sp0); - else - this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0); + this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0); #else /* Xen PV enters the kernel on the thread stack. */ - if (static_cpu_has(X86_FEATURE_XENPV)) + if (cpu_feature_enabled(X86_FEATURE_XENPV)) load_sp0(task_top_of_stack(task)); #endif } diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index 020c81a7c729..28d889c9aa16 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -67,6 +67,8 @@ void tdx_safe_halt(void); bool tdx_early_handle_ve(struct pt_regs *regs); +int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport); + #else static inline void tdx_early_init(void) { }; diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 1cc15528ce29..f4b87f08f5c5 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -45,6 +45,7 @@ extern void *text_poke(void *addr, const void *opcode, size_t len); extern void text_poke_sync(void); extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len); extern void *text_poke_copy(void *addr, const void *opcode, size_t len); +extern void *text_poke_copy_locked(void *addr, const void *opcode, size_t len, bool core_ok); extern void *text_poke_set(void *addr, int c, size_t len); extern int poke_int3_handler(struct pt_regs *regs); extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate); diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index e9170457697e..c1c8c581759d 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -285,6 +285,8 @@ struct x86_hyper_runtime { * possible in x86_early_init_platform_quirks() by * only using the current x86_hardware_subarch * semantics. + * @realmode_reserve: reserve memory for realmode trampoline + * @realmode_init: initialize realmode trampoline * @hyper: x86 hypervisor specific runtime callbacks */ struct x86_platform_ops { @@ -301,6 +303,8 @@ struct x86_platform_ops { void (*apic_post_init)(void); struct x86_legacy_features legacy; void (*set_legacy_features)(void); + void (*realmode_reserve)(void); + void (*realmode_init)(void); struct x86_hyper_runtime hyper; struct x86_guest guest; }; diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 46de10a809ec..e48deab8901d 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -53,14 +53,6 @@ /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 -struct kvm_memory_alias { - __u32 slot; /* this has a different namespace than memory slots */ - __u32 flags; - __u64 guest_phys_addr; - __u64 memory_size; - __u64 target_phys_addr; -}; - /* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */ struct kvm_pic_state { __u8 last_irr; /* edge detection */ @@ -214,6 +206,8 @@ struct kvm_msr_list { struct kvm_msr_filter_range { #define KVM_MSR_FILTER_READ (1 << 0) #define KVM_MSR_FILTER_WRITE (1 << 1) +#define KVM_MSR_FILTER_RANGE_VALID_MASK (KVM_MSR_FILTER_READ | \ + KVM_MSR_FILTER_WRITE) __u32 flags; __u32 nmsrs; /* number of msrs in bitmap */ __u32 base; /* MSR index the bitmap starts at */ @@ -222,8 +216,11 @@ struct kvm_msr_filter_range { #define KVM_MSR_FILTER_MAX_RANGES 16 struct kvm_msr_filter { +#ifndef __KERNEL__ #define KVM_MSR_FILTER_DEFAULT_ALLOW (0 << 0) +#endif #define KVM_MSR_FILTER_DEFAULT_DENY (1 << 0) +#define KVM_MSR_FILTER_VALID_MASK (KVM_MSR_FILTER_DEFAULT_DENY) __u32 flags; struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES]; }; diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index f901658d9f7c..96d51bbc2bd4 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -44,7 +44,7 @@ obj-y += head_$(BITS).o obj-y += head$(BITS).o obj-y += ebda.o obj-y += platform-quirks.o -obj-y += process_$(BITS).o signal.o +obj-y += process_$(BITS).o signal.o signal_$(BITS).o obj-$(CONFIG_COMPAT) += signal_compat.o obj-y += traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o obj-y += time.o ioport.o dumpstack.o nmi.o @@ -54,7 +54,7 @@ obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_IRQ_WORK) += irq_work.o obj-y += probe_roms.o obj-$(CONFIG_X86_32) += sys_ia32.o -obj-$(CONFIG_IA32_EMULATION) += sys_ia32.o +obj-$(CONFIG_IA32_EMULATION) += sys_ia32.o signal_32.o obj-$(CONFIG_X86_64) += sys_x86_64.o obj-$(CONFIG_X86_ESPFIX64) += espfix_64.o obj-$(CONFIG_SYSFS) += ksysfs.o @@ -143,6 +143,8 @@ obj-$(CONFIG_AMD_MEM_ENCRYPT) += sev.o obj-$(CONFIG_CFI_CLANG) += cfi.o +obj-$(CONFIG_CALL_THUNKS) += callthunks.o + ### # 64 bit specific files ifeq ($(CONFIG_X86_64),y) diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 7945eae5b315..401808b47af3 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -52,17 +52,25 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags, if (c->x86_vendor == X86_VENDOR_INTEL && (c->x86 > 0xf || (c->x86 == 6 && c->x86_model >= 0x0f))) flags->bm_control = 0; - /* - * For all recent Centaur CPUs, the ucode will make sure that each - * core can keep cache coherence with each other while entering C3 - * type state. So, set bm_check to 1 to indicate that the kernel - * doesn't need to execute a cache flush operation (WBINVD) when - * entering C3 type state. - */ + if (c->x86_vendor == X86_VENDOR_CENTAUR) { if (c->x86 > 6 || (c->x86 == 6 && c->x86_model == 0x0f && - c->x86_stepping >= 0x0e)) + c->x86_stepping >= 0x0e)) { + /* + * For all recent Centaur CPUs, the ucode will make sure that each + * core can keep cache coherence with each other while entering C3 + * type state. So, set bm_check to 1 to indicate that the kernel + * doesn't need to execute a cache flush operation (WBINVD) when + * entering C3 type state. + */ flags->bm_check = 1; + /* + * For all recent Centaur platforms, ARB_DISABLE is a nop. + * Set bm_control to zero to indicate that ARB_DISABLE is + * not required while entering C3 type state. + */ + flags->bm_control = 0; + } } if (c->x86_vendor == X86_VENDOR_ZHAOXIN) { diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 5cadcea035e0..23cbfa8d34c5 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -116,6 +116,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len) extern s32 __retpoline_sites[], __retpoline_sites_end[]; extern s32 __return_sites[], __return_sites_end[]; +extern s32 __cfi_sites[], __cfi_sites_end[]; extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[]; extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; @@ -377,6 +378,56 @@ static int emit_indirect(int op, int reg, u8 *bytes) return i; } +static inline bool is_jcc32(struct insn *insn) +{ + /* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */ + return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80; +} + +static int emit_call_track_retpoline(void *addr, struct insn *insn, int reg, u8 *bytes) +{ + u8 op = insn->opcode.bytes[0]; + int i = 0; + + /* + * Clang does 'weird' Jcc __x86_indirect_thunk_r11 conditional + * tail-calls. Deal with them. + */ + if (is_jcc32(insn)) { + bytes[i++] = op; + op = insn->opcode.bytes[1]; + goto clang_jcc; + } + + if (insn->length == 6) + bytes[i++] = 0x2e; /* CS-prefix */ + + switch (op) { + case CALL_INSN_OPCODE: + __text_gen_insn(bytes+i, op, addr+i, + __x86_indirect_call_thunk_array[reg], + CALL_INSN_SIZE); + i += CALL_INSN_SIZE; + break; + + case JMP32_INSN_OPCODE: +clang_jcc: + __text_gen_insn(bytes+i, op, addr+i, + __x86_indirect_jump_thunk_array[reg], + JMP32_INSN_SIZE); + i += JMP32_INSN_SIZE; + break; + + default: + WARN(1, "%pS %px %*ph\n", addr, addr, 6, addr); + return -1; + } + + WARN_ON_ONCE(i != insn->length); + + return i; +} + /* * Rewrite the compiler generated retpoline thunk calls. * @@ -409,8 +460,12 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) BUG_ON(reg == 4); if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) && - !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) + !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) { + if (cpu_feature_enabled(X86_FEATURE_CALL_DEPTH)) + return emit_call_track_retpoline(addr, insn, reg, bytes); + return -1; + } op = insn->opcode.bytes[0]; @@ -427,8 +482,7 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) * [ NOP ] * 1: */ - /* Jcc.d32 second opcode byte is in the range: 0x80-0x8f */ - if (op == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80) { + if (is_jcc32(insn)) { cc = insn->opcode.bytes[1] & 0xf; cc ^= 1; /* invert condition */ @@ -518,6 +572,11 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) } #ifdef CONFIG_RETHUNK + +#ifdef CONFIG_CALL_THUNKS +void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk; +#endif + /* * Rewrite the compiler generated return thunk tail-calls. * @@ -533,14 +592,18 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes) { int i = 0; - if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) - return -1; + if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { + if (x86_return_thunk == __x86_return_thunk) + return -1; - bytes[i++] = RET_INSN_OPCODE; + i = JMP32_INSN_SIZE; + __text_gen_insn(bytes, JMP32_INSN_OPCODE, addr, x86_return_thunk, i); + } else { + bytes[i++] = RET_INSN_OPCODE; + } for (; i < insn->length;) bytes[i++] = INT3_INSN_OPCODE; - return i; } @@ -594,6 +657,28 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } #ifdef CONFIG_X86_KERNEL_IBT +static void poison_endbr(void *addr, bool warn) +{ + u32 endbr, poison = gen_endbr_poison(); + + if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr))) + return; + + if (!is_endbr(endbr)) { + WARN_ON_ONCE(warn); + return; + } + + DPRINTK("ENDBR at: %pS (%px)", addr, addr); + + /* + * When we have IBT, the lack of ENDBR will trigger #CP + */ + DUMP_BYTES(((u8*)addr), 4, "%px: orig: ", addr); + DUMP_BYTES(((u8*)&poison), 4, "%px: repl: ", addr); + text_poke_early(addr, &poison, 4); +} + /* * Generated by: objtool --ibt */ @@ -602,31 +687,391 @@ void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end) s32 *s; for (s = start; s < end; s++) { - u32 endbr, poison = gen_endbr_poison(); void *addr = (void *)s + *s; - if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr))) + poison_endbr(addr, true); + if (IS_ENABLED(CONFIG_FINEIBT)) + poison_endbr(addr - 16, false); + } +} + +#else + +void __init_or_module apply_ibt_endbr(s32 *start, s32 *end) { } + +#endif /* CONFIG_X86_KERNEL_IBT */ + +#ifdef CONFIG_FINEIBT + +enum cfi_mode { + CFI_DEFAULT, + CFI_OFF, + CFI_KCFI, + CFI_FINEIBT, +}; + +static enum cfi_mode cfi_mode __ro_after_init = CFI_DEFAULT; +static bool cfi_rand __ro_after_init = true; +static u32 cfi_seed __ro_after_init; + +/* + * Re-hash the CFI hash with a boot-time seed while making sure the result is + * not a valid ENDBR instruction. + */ +static u32 cfi_rehash(u32 hash) +{ + hash ^= cfi_seed; + while (unlikely(is_endbr(hash) || is_endbr(-hash))) { + bool lsb = hash & 1; + hash >>= 1; + if (lsb) + hash ^= 0x80200003; + } + return hash; +} + +static __init int cfi_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + while (str) { + char *next = strchr(str, ','); + if (next) { + *next = 0; + next++; + } + + if (!strcmp(str, "auto")) { + cfi_mode = CFI_DEFAULT; + } else if (!strcmp(str, "off")) { + cfi_mode = CFI_OFF; + cfi_rand = false; + } else if (!strcmp(str, "kcfi")) { + cfi_mode = CFI_KCFI; + } else if (!strcmp(str, "fineibt")) { + cfi_mode = CFI_FINEIBT; + } else if (!strcmp(str, "norand")) { + cfi_rand = false; + } else { + pr_err("Ignoring unknown cfi option (%s).", str); + } + + str = next; + } + + return 0; +} +early_param("cfi", cfi_parse_cmdline); + +/* + * kCFI FineIBT + * + * __cfi_\func: __cfi_\func: + * movl $0x12345678,%eax // 5 endbr64 // 4 + * nop subl $0x12345678,%r10d // 7 + * nop jz 1f // 2 + * nop ud2 // 2 + * nop 1: nop // 1 + * nop + * nop + * nop + * nop + * nop + * nop + * nop + * + * + * caller: caller: + * movl $(-0x12345678),%r10d // 6 movl $0x12345678,%r10d // 6 + * addl $-15(%r11),%r10d // 4 sub $16,%r11 // 4 + * je 1f // 2 nop4 // 4 + * ud2 // 2 + * 1: call __x86_indirect_thunk_r11 // 5 call *%r11; nop2; // 5 + * + */ + +asm( ".pushsection .rodata \n" + "fineibt_preamble_start: \n" + " endbr64 \n" + " subl $0x12345678, %r10d \n" + " je fineibt_preamble_end \n" + " ud2 \n" + " nop \n" + "fineibt_preamble_end: \n" + ".popsection\n" +); + +extern u8 fineibt_preamble_start[]; +extern u8 fineibt_preamble_end[]; + +#define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start) +#define fineibt_preamble_hash 7 + +asm( ".pushsection .rodata \n" + "fineibt_caller_start: \n" + " movl $0x12345678, %r10d \n" + " sub $16, %r11 \n" + ASM_NOP4 + "fineibt_caller_end: \n" + ".popsection \n" +); + +extern u8 fineibt_caller_start[]; +extern u8 fineibt_caller_end[]; + +#define fineibt_caller_size (fineibt_caller_end - fineibt_caller_start) +#define fineibt_caller_hash 2 + +#define fineibt_caller_jmp (fineibt_caller_size - 2) + +static u32 decode_preamble_hash(void *addr) +{ + u8 *p = addr; + + /* b8 78 56 34 12 mov $0x12345678,%eax */ + if (p[0] == 0xb8) + return *(u32 *)(addr + 1); + + return 0; /* invalid hash value */ +} + +static u32 decode_caller_hash(void *addr) +{ + u8 *p = addr; + + /* 41 ba 78 56 34 12 mov $0x12345678,%r10d */ + if (p[0] == 0x41 && p[1] == 0xba) + return -*(u32 *)(addr + 2); + + /* e8 0c 78 56 34 12 jmp.d8 +12 */ + if (p[0] == JMP8_INSN_OPCODE && p[1] == fineibt_caller_jmp) + return -*(u32 *)(addr + 2); + + return 0; /* invalid hash value */ +} + +/* .retpoline_sites */ +static int cfi_disable_callers(s32 *start, s32 *end) +{ + /* + * Disable kCFI by patching in a JMP.d8, this leaves the hash immediate + * in tact for later usage. Also see decode_caller_hash() and + * cfi_rewrite_callers(). + */ + const u8 jmp[] = { JMP8_INSN_OPCODE, fineibt_caller_jmp }; + s32 *s; + + for (s = start; s < end; s++) { + void *addr = (void *)s + *s; + u32 hash; + + addr -= fineibt_caller_size; + hash = decode_caller_hash(addr); + if (!hash) /* nocfi callers */ continue; - if (WARN_ON_ONCE(!is_endbr(endbr))) + text_poke_early(addr, jmp, 2); + } + + return 0; +} + +static int cfi_enable_callers(s32 *start, s32 *end) +{ + /* + * Re-enable kCFI, undo what cfi_disable_callers() did. + */ + const u8 mov[] = { 0x41, 0xba }; + s32 *s; + + for (s = start; s < end; s++) { + void *addr = (void *)s + *s; + u32 hash; + + addr -= fineibt_caller_size; + hash = decode_caller_hash(addr); + if (!hash) /* nocfi callers */ continue; - DPRINTK("ENDBR at: %pS (%px)", addr, addr); + text_poke_early(addr, mov, 2); + } - /* - * When we have IBT, the lack of ENDBR will trigger #CP - */ - DUMP_BYTES(((u8*)addr), 4, "%px: orig: ", addr); - DUMP_BYTES(((u8*)&poison), 4, "%px: repl: ", addr); - text_poke_early(addr, &poison, 4); + return 0; +} + +/* .cfi_sites */ +static int cfi_rand_preamble(s32 *start, s32 *end) +{ + s32 *s; + + for (s = start; s < end; s++) { + void *addr = (void *)s + *s; + u32 hash; + + hash = decode_preamble_hash(addr); + if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n", + addr, addr, 5, addr)) + return -EINVAL; + + hash = cfi_rehash(hash); + text_poke_early(addr + 1, &hash, 4); + } + + return 0; +} + +static int cfi_rewrite_preamble(s32 *start, s32 *end) +{ + s32 *s; + + for (s = start; s < end; s++) { + void *addr = (void *)s + *s; + u32 hash; + + hash = decode_preamble_hash(addr); + if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n", + addr, addr, 5, addr)) + return -EINVAL; + + text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size); + WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678); + text_poke_early(addr + fineibt_preamble_hash, &hash, 4); + } + + return 0; +} + +/* .retpoline_sites */ +static int cfi_rand_callers(s32 *start, s32 *end) +{ + s32 *s; + + for (s = start; s < end; s++) { + void *addr = (void *)s + *s; + u32 hash; + + addr -= fineibt_caller_size; + hash = decode_caller_hash(addr); + if (hash) { + hash = -cfi_rehash(hash); + text_poke_early(addr + 2, &hash, 4); + } + } + + return 0; +} + +static int cfi_rewrite_callers(s32 *start, s32 *end) +{ + s32 *s; + + for (s = start; s < end; s++) { + void *addr = (void *)s + *s; + u32 hash; + + addr -= fineibt_caller_size; + hash = decode_caller_hash(addr); + if (hash) { + text_poke_early(addr, fineibt_caller_start, fineibt_caller_size); + WARN_ON(*(u32 *)(addr + fineibt_caller_hash) != 0x12345678); + text_poke_early(addr + fineibt_caller_hash, &hash, 4); + } + /* rely on apply_retpolines() */ + } + + return 0; +} + +static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, + s32 *start_cfi, s32 *end_cfi, bool builtin) +{ + int ret; + + if (WARN_ONCE(fineibt_preamble_size != 16, + "FineIBT preamble wrong size: %ld", fineibt_preamble_size)) + return; + + if (cfi_mode == CFI_DEFAULT) { + cfi_mode = CFI_KCFI; + if (HAS_KERNEL_IBT && cpu_feature_enabled(X86_FEATURE_IBT)) + cfi_mode = CFI_FINEIBT; + } + + /* + * Rewrite the callers to not use the __cfi_ stubs, such that we might + * rewrite them. This disables all CFI. If this succeeds but any of the + * later stages fails, we're without CFI. + */ + ret = cfi_disable_callers(start_retpoline, end_retpoline); + if (ret) + goto err; + + if (cfi_rand) { + if (builtin) + cfi_seed = get_random_u32(); + + ret = cfi_rand_preamble(start_cfi, end_cfi); + if (ret) + goto err; + + ret = cfi_rand_callers(start_retpoline, end_retpoline); + if (ret) + goto err; + } + + switch (cfi_mode) { + case CFI_OFF: + if (builtin) + pr_info("Disabling CFI\n"); + return; + + case CFI_KCFI: + ret = cfi_enable_callers(start_retpoline, end_retpoline); + if (ret) + goto err; + + if (builtin) + pr_info("Using kCFI\n"); + return; + + case CFI_FINEIBT: + ret = cfi_rewrite_preamble(start_cfi, end_cfi); + if (ret) + goto err; + + ret = cfi_rewrite_callers(start_retpoline, end_retpoline); + if (ret) + goto err; + + if (builtin) + pr_info("Using FineIBT CFI\n"); + return; + + default: + break; } + +err: + pr_err("Something went horribly wrong trying to rewrite the CFI implementation.\n"); } #else -void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end) { } +static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, + s32 *start_cfi, s32 *end_cfi, bool builtin) +{ +} -#endif /* CONFIG_X86_KERNEL_IBT */ +#endif + +void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, + s32 *start_cfi, s32 *end_cfi) +{ + return __apply_fineibt(start_retpoline, end_retpoline, + start_cfi, end_cfi, + /* .builtin = */ false); +} #ifdef CONFIG_SMP static void alternatives_smp_lock(const s32 *start, const s32 *end, @@ -934,6 +1379,9 @@ void __init alternative_instructions(void) */ apply_paravirt(__parainstructions, __parainstructions_end); + __apply_fineibt(__retpoline_sites, __retpoline_sites_end, + __cfi_sites, __cfi_sites_end, true); + /* * Rewrite the retpolines, must be done before alternatives since * those can rewrite the retpoline thunks. @@ -947,6 +1395,12 @@ void __init alternative_instructions(void) */ apply_alternatives(__alt_instructions, __alt_instructions_end); + /* + * Now all calls are established. Apply the call thunks if + * required. + */ + callthunks_patch_builtin_calls(); + apply_ibt_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end); #ifdef CONFIG_SMP @@ -1236,27 +1690,15 @@ void *text_poke_kgdb(void *addr, const void *opcode, size_t len) return __text_poke(text_poke_memcpy, addr, opcode, len); } -/** - * text_poke_copy - Copy instructions into (an unused part of) RX memory - * @addr: address to modify - * @opcode: source of the copy - * @len: length to copy, could be more than 2x PAGE_SIZE - * - * Not safe against concurrent execution; useful for JITs to dump - * new code blocks into unused regions of RX memory. Can be used in - * conjunction with synchronize_rcu_tasks() to wait for existing - * execution to quiesce after having made sure no existing functions - * pointers are live. - */ -void *text_poke_copy(void *addr, const void *opcode, size_t len) +void *text_poke_copy_locked(void *addr, const void *opcode, size_t len, + bool core_ok) { unsigned long start = (unsigned long)addr; size_t patched = 0; - if (WARN_ON_ONCE(core_kernel_text(start))) + if (WARN_ON_ONCE(!core_ok && core_kernel_text(start))) return NULL; - mutex_lock(&text_mutex); while (patched < len) { unsigned long ptr = start + patched; size_t s; @@ -1266,6 +1708,25 @@ void *text_poke_copy(void *addr, const void *opcode, size_t len) __text_poke(text_poke_memcpy, (void *)ptr, opcode + patched, s); patched += s; } + return addr; +} + +/** + * text_poke_copy - Copy instructions into (an unused part of) RX memory + * @addr: address to modify + * @opcode: source of the copy + * @len: length to copy, could be more than 2x PAGE_SIZE + * + * Not safe against concurrent execution; useful for JITs to dump + * new code blocks into unused regions of RX memory. Can be used in + * conjunction with synchronize_rcu_tasks() to wait for existing + * execution to quiesce after having made sure no existing functions + * pointers are live. + */ +void *text_poke_copy(void *addr, const void *opcode, size_t len) +{ + mutex_lock(&text_mutex); + addr = text_poke_copy_locked(addr, opcode, len, false); mutex_unlock(&text_mutex); return addr; } @@ -1608,7 +2069,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr, default: BUG_ON(len != insn.length); - }; + } switch (tp->opcode) { diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index c6876d3ea4b1..20d9a604da7c 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1931,16 +1931,19 @@ void __init check_x2apic(void) } } #else /* CONFIG_X86_X2APIC */ -static int __init validate_x2apic(void) +void __init check_x2apic(void) { if (!apic_is_x2apic_enabled()) - return 0; + return; /* - * Checkme: Can we simply turn off x2apic here instead of panic? + * Checkme: Can we simply turn off x2APIC here instead of disabling the APIC? */ - panic("BIOS has enabled x2apic but kernel doesn't support x2apic, please disable x2apic in BIOS.\n"); + pr_err("Kernel does not support x2APIC, please recompile with CONFIG_X86_X2APIC.\n"); + pr_err("Disabling APIC, expect reduced performance and functionality.\n"); + + disable_apic = 1; + setup_clear_cpu_cap(X86_FEATURE_APIC); } -early_initcall(validate_x2apic); static inline void try_to_enable_x2apic(int remap_mode) { } static inline void __x2apic_enable(void) { } diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 7517eb05bdc1..35d5b8fb18ef 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -142,70 +142,139 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) return ret; } -/* - * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices, - * which implement the MSI or MSI-X Capability Structure. +/** + * pci_dev_has_default_msi_parent_domain - Check whether the device has the default + * MSI parent domain associated + * @dev: Pointer to the PCI device */ -static struct irq_chip pci_msi_controller = { - .name = "PCI-MSI", - .irq_unmask = pci_msi_unmask_irq, - .irq_mask = pci_msi_mask_irq, - .irq_ack = irq_chip_ack_parent, - .irq_retrigger = irq_chip_retrigger_hierarchy, - .irq_set_affinity = msi_set_affinity, - .flags = IRQCHIP_SKIP_SET_WAKE | - IRQCHIP_AFFINITY_PRE_STARTUP, -}; +bool pci_dev_has_default_msi_parent_domain(struct pci_dev *dev) +{ + struct irq_domain *domain = dev_get_msi_domain(&dev->dev); -int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, - msi_alloc_info_t *arg) + if (!domain) + domain = dev_get_msi_domain(&dev->bus->dev); + if (!domain) + return false; + + return domain == x86_vector_domain; +} + +/** + * x86_msi_prepare - Setup of msi_alloc_info_t for allocations + * @domain: The domain for which this setup happens + * @dev: The device for which interrupts are allocated + * @nvec: The number of vectors to allocate + * @alloc: The allocation info structure to initialize + * + * This function is to be used for all types of MSI domains above the x86 + * vector domain and any intermediates. It is always invoked from the + * top level interrupt domain. The domain specific allocation + * functionality is determined via the @domain's bus token which allows to + * map the X86 specific allocation type. + */ +static int x86_msi_prepare(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *alloc) { - init_irq_alloc_info(arg, NULL); - if (to_pci_dev(dev)->msix_enabled) { - arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX; - } else { - arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSI; - arg->flags |= X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; + struct msi_domain_info *info = domain->host_data; + + init_irq_alloc_info(alloc, NULL); + + switch (info->bus_token) { + case DOMAIN_BUS_PCI_DEVICE_MSI: + alloc->type = X86_IRQ_ALLOC_TYPE_PCI_MSI; + return 0; + case DOMAIN_BUS_PCI_DEVICE_MSIX: + case DOMAIN_BUS_PCI_DEVICE_IMS: + alloc->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX; + return 0; + default: + return -EINVAL; } - - return 0; } -EXPORT_SYMBOL_GPL(pci_msi_prepare); -static struct msi_domain_ops pci_msi_domain_ops = { - .msi_prepare = pci_msi_prepare, -}; +/** + * x86_init_dev_msi_info - Domain info setup for MSI domains + * @dev: The device for which the domain should be created + * @domain: The (root) domain providing this callback + * @real_parent: The real parent domain of the to initialize domain + * @info: The domain info for the to initialize domain + * + * This function is to be used for all types of MSI domains above the x86 + * vector domain and any intermediates. The domain specific functionality + * is determined via the @real_parent. + */ +static bool x86_init_dev_msi_info(struct device *dev, struct irq_domain *domain, + struct irq_domain *real_parent, struct msi_domain_info *info) +{ + const struct msi_parent_ops *pops = real_parent->msi_parent_ops; + + /* MSI parent domain specific settings */ + switch (real_parent->bus_token) { + case DOMAIN_BUS_ANY: + /* Only the vector domain can have the ANY token */ + if (WARN_ON_ONCE(domain != real_parent)) + return false; + info->chip->irq_set_affinity = msi_set_affinity; + /* See msi_set_affinity() for the gory details */ + info->flags |= MSI_FLAG_NOMASK_QUIRK; + break; + case DOMAIN_BUS_DMAR: + case DOMAIN_BUS_AMDVI: + break; + default: + WARN_ON_ONCE(1); + return false; + } + + /* Is the target supported? */ + switch(info->bus_token) { + case DOMAIN_BUS_PCI_DEVICE_MSI: + case DOMAIN_BUS_PCI_DEVICE_MSIX: + break; + case DOMAIN_BUS_PCI_DEVICE_IMS: + if (!(pops->supported_flags & MSI_FLAG_PCI_IMS)) + return false; + break; + default: + WARN_ON_ONCE(1); + return false; + } + + /* + * Mask out the domain specific MSI feature flags which are not + * supported by the real parent. + */ + info->flags &= pops->supported_flags; + /* Enforce the required flags */ + info->flags |= X86_VECTOR_MSI_FLAGS_REQUIRED; + + /* This is always invoked from the top level MSI domain! */ + info->ops->msi_prepare = x86_msi_prepare; + + info->chip->irq_ack = irq_chip_ack_parent; + info->chip->irq_retrigger = irq_chip_retrigger_hierarchy; + info->chip->flags |= IRQCHIP_SKIP_SET_WAKE | + IRQCHIP_AFFINITY_PRE_STARTUP; -static struct msi_domain_info pci_msi_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_PCI_MSIX, - .ops = &pci_msi_domain_ops, - .chip = &pci_msi_controller, - .handler = handle_edge_irq, - .handler_name = "edge", + info->handler = handle_edge_irq; + info->handler_name = "edge"; + + return true; +} + +static const struct msi_parent_ops x86_vector_msi_parent_ops = { + .supported_flags = X86_VECTOR_MSI_FLAGS_SUPPORTED, + .init_dev_msi_info = x86_init_dev_msi_info, }; struct irq_domain * __init native_create_pci_msi_domain(void) { - struct fwnode_handle *fn; - struct irq_domain *d; - if (disable_apic) return NULL; - fn = irq_domain_alloc_named_fwnode("PCI-MSI"); - if (!fn) - return NULL; - - d = pci_msi_create_irq_domain(fn, &pci_msi_domain_info, - x86_vector_domain); - if (!d) { - irq_domain_free_fwnode(fn); - pr_warn("Failed to initialize PCI-MSI irqdomain.\n"); - } else { - d->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK; - } - return d; + x86_vector_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT; + x86_vector_domain->msi_parent_ops = &x86_vector_msi_parent_ops; + return x86_vector_domain; } void __init x86_create_pci_msi_domain(void) @@ -213,41 +282,19 @@ void __init x86_create_pci_msi_domain(void) x86_pci_msi_default_domain = x86_init.irqs.create_pci_msi_domain(); } -#ifdef CONFIG_IRQ_REMAP -static struct irq_chip pci_msi_ir_controller = { - .name = "IR-PCI-MSI", - .irq_unmask = pci_msi_unmask_irq, - .irq_mask = pci_msi_mask_irq, - .irq_ack = irq_chip_ack_parent, - .irq_retrigger = irq_chip_retrigger_hierarchy, - .flags = IRQCHIP_SKIP_SET_WAKE | - IRQCHIP_AFFINITY_PRE_STARTUP, -}; - -static struct msi_domain_info pci_msi_ir_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX, - .ops = &pci_msi_domain_ops, - .chip = &pci_msi_ir_controller, - .handler = handle_edge_irq, - .handler_name = "edge", -}; - -struct irq_domain *arch_create_remap_msi_irq_domain(struct irq_domain *parent, - const char *name, int id) +/* Keep around for hyperV */ +int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, + msi_alloc_info_t *arg) { - struct fwnode_handle *fn; - struct irq_domain *d; + init_irq_alloc_info(arg, NULL); - fn = irq_domain_alloc_named_id_fwnode(name, id); - if (!fn) - return NULL; - d = pci_msi_create_irq_domain(fn, &pci_msi_ir_domain_info, parent); - if (!d) - irq_domain_free_fwnode(fn); - return d; + if (to_pci_dev(dev)->msix_enabled) + arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX; + else + arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSI; + return 0; } -#endif +EXPORT_SYMBOL_GPL(pci_msi_prepare); #ifdef CONFIG_DMAR_TABLE /* diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 3e6f6b448f6a..c1efebd27e6c 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -539,10 +539,6 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq, if (disable_apic) return -ENXIO; - /* Currently vector allocator can't guarantee contiguous allocations */ - if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1) - return -ENOSYS; - /* * Catch any attempt to touch the cascade interrupt on a PIC * equipped system. diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 437308004ef2..82c783da16a8 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -107,4 +107,9 @@ static void __used common(void) OFFSET(TSS_sp0, tss_struct, x86_tss.sp0); OFFSET(TSS_sp1, tss_struct, x86_tss.sp1); OFFSET(TSS_sp2, tss_struct, x86_tss.sp2); + OFFSET(X86_top_of_stack, pcpu_hot, top_of_stack); +#ifdef CONFIG_CALL_DEPTH_TRACKING + OFFSET(X86_call_depth, pcpu_hot, call_depth); +#endif + } diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 9b698215d261..bb65371ea9df 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -57,7 +57,7 @@ int main(void) BLANK(); #ifdef CONFIG_STACKPROTECTOR - DEFINE(stack_canary_offset, offsetof(struct fixed_percpu_data, stack_canary)); + OFFSET(FIXED_stack_canary, fixed_percpu_data, stack_canary); BLANK(); #endif return 0; diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c new file mode 100644 index 000000000000..7d2c75ec9a8c --- /dev/null +++ b/arch/x86/kernel/callthunks.c @@ -0,0 +1,388 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#define pr_fmt(fmt) "callthunks: " fmt + +#include <linux/debugfs.h> +#include <linux/kallsyms.h> +#include <linux/memory.h> +#include <linux/moduleloader.h> +#include <linux/static_call.h> + +#include <asm/alternative.h> +#include <asm/asm-offsets.h> +#include <asm/cpu.h> +#include <asm/ftrace.h> +#include <asm/insn.h> +#include <asm/kexec.h> +#include <asm/nospec-branch.h> +#include <asm/paravirt.h> +#include <asm/sections.h> +#include <asm/switch_to.h> +#include <asm/sync_core.h> +#include <asm/text-patching.h> +#include <asm/xen/hypercall.h> + +static int __initdata_or_module debug_callthunks; + +#define prdbg(fmt, args...) \ +do { \ + if (debug_callthunks) \ + printk(KERN_DEBUG pr_fmt(fmt), ##args); \ +} while(0) + +static int __init debug_thunks(char *str) +{ + debug_callthunks = 1; + return 1; +} +__setup("debug-callthunks", debug_thunks); + +#ifdef CONFIG_CALL_THUNKS_DEBUG +DEFINE_PER_CPU(u64, __x86_call_count); +DEFINE_PER_CPU(u64, __x86_ret_count); +DEFINE_PER_CPU(u64, __x86_stuffs_count); +DEFINE_PER_CPU(u64, __x86_ctxsw_count); +EXPORT_SYMBOL_GPL(__x86_ctxsw_count); +EXPORT_SYMBOL_GPL(__x86_call_count); +#endif + +extern s32 __call_sites[], __call_sites_end[]; + +struct thunk_desc { + void *template; + unsigned int template_size; +}; + +struct core_text { + unsigned long base; + unsigned long end; + const char *name; +}; + +static bool thunks_initialized __ro_after_init; + +static const struct core_text builtin_coretext = { + .base = (unsigned long)_text, + .end = (unsigned long)_etext, + .name = "builtin", +}; + +asm ( + ".pushsection .rodata \n" + ".global skl_call_thunk_template \n" + "skl_call_thunk_template: \n" + __stringify(INCREMENT_CALL_DEPTH)" \n" + ".global skl_call_thunk_tail \n" + "skl_call_thunk_tail: \n" + ".popsection \n" +); + +extern u8 skl_call_thunk_template[]; +extern u8 skl_call_thunk_tail[]; + +#define SKL_TMPL_SIZE \ + ((unsigned int)(skl_call_thunk_tail - skl_call_thunk_template)) + +extern void error_entry(void); +extern void xen_error_entry(void); +extern void paranoid_entry(void); + +static inline bool within_coretext(const struct core_text *ct, void *addr) +{ + unsigned long p = (unsigned long)addr; + + return ct->base <= p && p < ct->end; +} + +static inline bool within_module_coretext(void *addr) +{ + bool ret = false; + +#ifdef CONFIG_MODULES + struct module *mod; + + preempt_disable(); + mod = __module_address((unsigned long)addr); + if (mod && within_module_core((unsigned long)addr, mod)) + ret = true; + preempt_enable(); +#endif + return ret; +} + +static bool is_coretext(const struct core_text *ct, void *addr) +{ + if (ct && within_coretext(ct, addr)) + return true; + if (within_coretext(&builtin_coretext, addr)) + return true; + return within_module_coretext(addr); +} + +static __init_or_module bool skip_addr(void *dest) +{ + if (dest == error_entry) + return true; + if (dest == paranoid_entry) + return true; + if (dest == xen_error_entry) + return true; + /* Does FILL_RSB... */ + if (dest == __switch_to_asm) + return true; + /* Accounts directly */ + if (dest == ret_from_fork) + return true; +#ifdef CONFIG_HOTPLUG_CPU + if (dest == start_cpu0) + return true; +#endif +#ifdef CONFIG_FUNCTION_TRACER + if (dest == __fentry__) + return true; +#endif +#ifdef CONFIG_KEXEC_CORE + if (dest >= (void *)relocate_kernel && + dest < (void*)relocate_kernel + KEXEC_CONTROL_CODE_MAX_SIZE) + return true; +#endif +#ifdef CONFIG_XEN + if (dest >= (void *)hypercall_page && + dest < (void*)hypercall_page + PAGE_SIZE) + return true; +#endif + return false; +} + +static __init_or_module void *call_get_dest(void *addr) +{ + struct insn insn; + void *dest; + int ret; + + ret = insn_decode_kernel(&insn, addr); + if (ret) + return ERR_PTR(ret); + + /* Patched out call? */ + if (insn.opcode.bytes[0] != CALL_INSN_OPCODE) + return NULL; + + dest = addr + insn.length + insn.immediate.value; + if (skip_addr(dest)) + return NULL; + return dest; +} + +static const u8 nops[] = { + 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, + 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, + 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, + 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, 0x90, +}; + +static __init_or_module void *patch_dest(void *dest, bool direct) +{ + unsigned int tsize = SKL_TMPL_SIZE; + u8 *pad = dest - tsize; + + /* Already patched? */ + if (!bcmp(pad, skl_call_thunk_template, tsize)) + return pad; + + /* Ensure there are nops */ + if (bcmp(pad, nops, tsize)) { + pr_warn_once("Invalid padding area for %pS\n", dest); + return NULL; + } + + if (direct) + memcpy(pad, skl_call_thunk_template, tsize); + else + text_poke_copy_locked(pad, skl_call_thunk_template, tsize, true); + return pad; +} + +static __init_or_module void patch_call(void *addr, const struct core_text *ct) +{ + void *pad, *dest; + u8 bytes[8]; + + if (!within_coretext(ct, addr)) + return; + + dest = call_get_dest(addr); + if (!dest || WARN_ON_ONCE(IS_ERR(dest))) + return; + + if (!is_coretext(ct, dest)) + return; + + pad = patch_dest(dest, within_coretext(ct, dest)); + if (!pad) + return; + + prdbg("Patch call at: %pS %px to %pS %px -> %px \n", addr, addr, + dest, dest, pad); + __text_gen_insn(bytes, CALL_INSN_OPCODE, addr, pad, CALL_INSN_SIZE); + text_poke_early(addr, bytes, CALL_INSN_SIZE); +} + +static __init_or_module void +patch_call_sites(s32 *start, s32 *end, const struct core_text *ct) +{ + s32 *s; + + for (s = start; s < end; s++) + patch_call((void *)s + *s, ct); +} + +static __init_or_module void +patch_paravirt_call_sites(struct paravirt_patch_site *start, + struct paravirt_patch_site *end, + const struct core_text *ct) +{ + struct paravirt_patch_site *p; + + for (p = start; p < end; p++) + patch_call(p->instr, ct); +} + +static __init_or_module void +callthunks_setup(struct callthunk_sites *cs, const struct core_text *ct) +{ + prdbg("Patching call sites %s\n", ct->name); + patch_call_sites(cs->call_start, cs->call_end, ct); + patch_paravirt_call_sites(cs->pv_start, cs->pv_end, ct); + prdbg("Patching call sites done%s\n", ct->name); +} + +void __init callthunks_patch_builtin_calls(void) +{ + struct callthunk_sites cs = { + .call_start = __call_sites, + .call_end = __call_sites_end, + .pv_start = __parainstructions, + .pv_end = __parainstructions_end + }; + + if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH)) + return; + + pr_info("Setting up call depth tracking\n"); + mutex_lock(&text_mutex); + callthunks_setup(&cs, &builtin_coretext); + static_call_force_reinit(); + thunks_initialized = true; + mutex_unlock(&text_mutex); +} + +void *callthunks_translate_call_dest(void *dest) +{ + void *target; + + lockdep_assert_held(&text_mutex); + + if (!thunks_initialized || skip_addr(dest)) + return dest; + + if (!is_coretext(NULL, dest)) + return dest; + + target = patch_dest(dest, false); + return target ? : dest; +} + +bool is_callthunk(void *addr) +{ + unsigned int tmpl_size = SKL_TMPL_SIZE; + void *tmpl = skl_call_thunk_template; + unsigned long dest; + + dest = roundup((unsigned long)addr, CONFIG_FUNCTION_ALIGNMENT); + if (!thunks_initialized || skip_addr((void *)dest)) + return false; + + return !bcmp((void *)(dest - tmpl_size), tmpl, tmpl_size); +} + +#ifdef CONFIG_BPF_JIT +int x86_call_depth_emit_accounting(u8 **pprog, void *func) +{ + unsigned int tmpl_size = SKL_TMPL_SIZE; + void *tmpl = skl_call_thunk_template; + + if (!thunks_initialized) + return 0; + + /* Is function call target a thunk? */ + if (func && is_callthunk(func)) + return 0; + + memcpy(*pprog, tmpl, tmpl_size); + *pprog += tmpl_size; + return tmpl_size; +} +#endif + +#ifdef CONFIG_MODULES +void noinline callthunks_patch_module_calls(struct callthunk_sites *cs, + struct module *mod) +{ + struct core_text ct = { + .base = (unsigned long)mod->core_layout.base, + .end = (unsigned long)mod->core_layout.base + mod->core_layout.size, + .name = mod->name, + }; + + if (!thunks_initialized) + return; + + mutex_lock(&text_mutex); + callthunks_setup(cs, &ct); + mutex_unlock(&text_mutex); +} +#endif /* CONFIG_MODULES */ + +#if defined(CONFIG_CALL_THUNKS_DEBUG) && defined(CONFIG_DEBUG_FS) +static int callthunks_debug_show(struct seq_file *m, void *p) +{ + unsigned long cpu = (unsigned long)m->private; + + seq_printf(m, "C: %16llu R: %16llu S: %16llu X: %16llu\n,", + per_cpu(__x86_call_count, cpu), + per_cpu(__x86_ret_count, cpu), + per_cpu(__x86_stuffs_count, cpu), + per_cpu(__x86_ctxsw_count, cpu)); + return 0; +} + +static int callthunks_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, callthunks_debug_show, inode->i_private); +} + +static const struct file_operations dfs_ops = { + .open = callthunks_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init callthunks_debugfs_init(void) +{ + struct dentry *dir; + unsigned long cpu; + + dir = debugfs_create_dir("callthunks", NULL); + for_each_possible_cpu(cpu) { + void *arg = (void *)cpu; + char name [10]; + + sprintf(name, "cpu%lu", cpu); + debugfs_create_file(name, 0644, dir, arg, &dfs_ops); + } + return 0; +} +__initcall(callthunks_debugfs_init); +#endif diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index f10a921ee756..d7e3ceaf75c1 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -17,9 +17,6 @@ KMSAN_SANITIZE_common.o := n # As above, instrumenting secondary CPU boot code causes boot hangs. KCSAN_SANITIZE_common.o := n -# Make sure load_percpu_segment has no stackprotector -CFLAGS_common.o := -fno-stack-protector - obj-y := cacheinfo.o scattered.o topology.o obj-y += common.o obj-y += rdrand.o diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index c75d75b9f11a..f769d6d08b43 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -983,7 +983,7 @@ static void init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_3DNOWPREFETCH); /* AMD CPUs don't reset SS attributes on SYSRET, Xen does. */ - if (!cpu_has(c, X86_FEATURE_XENPV)) + if (!cpu_feature_enabled(X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); /* diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 3e3230cccaa7..d970ddb0cc65 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -60,11 +60,18 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); static DEFINE_MUTEX(spec_ctrl_mutex); +/* Update SPEC_CTRL MSR and its cached copy unconditionally */ +static void update_spec_ctrl(u64 val) +{ + this_cpu_write(x86_spec_ctrl_current, val); + wrmsrl(MSR_IA32_SPEC_CTRL, val); +} + /* * Keep track of the SPEC_CTRL MSR value for the current task, which may differ * from x86_spec_ctrl_base due to STIBP/SSB in __speculation_ctrl_update(). */ -void write_spec_ctrl_current(u64 val, bool force) +void update_spec_ctrl_cond(u64 val) { if (this_cpu_read(x86_spec_ctrl_current) == val) return; @@ -75,7 +82,7 @@ void write_spec_ctrl_current(u64 val, bool force) * When KERNEL_IBRS this MSR is written on return-to-user, unless * forced the update can be delayed until that time. */ - if (force || !cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS)) + if (!cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS)) wrmsrl(MSR_IA32_SPEC_CTRL, val); } @@ -780,6 +787,7 @@ enum retbleed_mitigation { RETBLEED_MITIGATION_IBPB, RETBLEED_MITIGATION_IBRS, RETBLEED_MITIGATION_EIBRS, + RETBLEED_MITIGATION_STUFF, }; enum retbleed_mitigation_cmd { @@ -787,6 +795,7 @@ enum retbleed_mitigation_cmd { RETBLEED_CMD_AUTO, RETBLEED_CMD_UNRET, RETBLEED_CMD_IBPB, + RETBLEED_CMD_STUFF, }; static const char * const retbleed_strings[] = { @@ -795,6 +804,7 @@ static const char * const retbleed_strings[] = { [RETBLEED_MITIGATION_IBPB] = "Mitigation: IBPB", [RETBLEED_MITIGATION_IBRS] = "Mitigation: IBRS", [RETBLEED_MITIGATION_EIBRS] = "Mitigation: Enhanced IBRS", + [RETBLEED_MITIGATION_STUFF] = "Mitigation: Stuffing", }; static enum retbleed_mitigation retbleed_mitigation __ro_after_init = @@ -824,8 +834,12 @@ static int __init retbleed_parse_cmdline(char *str) retbleed_cmd = RETBLEED_CMD_UNRET; } else if (!strcmp(str, "ibpb")) { retbleed_cmd = RETBLEED_CMD_IBPB; + } else if (!strcmp(str, "stuff")) { + retbleed_cmd = RETBLEED_CMD_STUFF; } else if (!strcmp(str, "nosmt")) { retbleed_nosmt = true; + } else if (!strcmp(str, "force")) { + setup_force_cpu_bug(X86_BUG_RETBLEED); } else { pr_err("Ignoring unknown retbleed option (%s).", str); } @@ -872,6 +886,21 @@ static void __init retbleed_select_mitigation(void) } break; + case RETBLEED_CMD_STUFF: + if (IS_ENABLED(CONFIG_CALL_DEPTH_TRACKING) && + spectre_v2_enabled == SPECTRE_V2_RETPOLINE) { + retbleed_mitigation = RETBLEED_MITIGATION_STUFF; + + } else { + if (IS_ENABLED(CONFIG_CALL_DEPTH_TRACKING)) + pr_err("WARNING: retbleed=stuff depends on spectre_v2=retpoline\n"); + else + pr_err("WARNING: kernel not compiled with CALL_DEPTH_TRACKING.\n"); + + goto do_cmd_auto; + } + break; + do_cmd_auto: case RETBLEED_CMD_AUTO: default: @@ -909,6 +938,12 @@ do_cmd_auto: mitigate_smt = true; break; + case RETBLEED_MITIGATION_STUFF: + setup_force_cpu_cap(X86_FEATURE_RETHUNK); + setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH); + x86_set_skl_return_thunk(); + break; + default: break; } @@ -919,7 +954,7 @@ do_cmd_auto: /* * Let IBRS trump all on Intel without affecting the effects of the - * retbleed= cmdline option. + * retbleed= cmdline option except for call depth based stuffing */ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { switch (spectre_v2_enabled) { @@ -932,7 +967,8 @@ do_cmd_auto: retbleed_mitigation = RETBLEED_MITIGATION_EIBRS; break; default: - pr_err(RETBLEED_INTEL_MSG); + if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF) + pr_err(RETBLEED_INTEL_MSG); } } @@ -1295,7 +1331,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return SPECTRE_V2_CMD_AUTO; } - if (cmd == SPECTRE_V2_CMD_IBRS && boot_cpu_has(X86_FEATURE_XENPV)) { + if (cmd == SPECTRE_V2_CMD_IBRS && cpu_feature_enabled(X86_FEATURE_XENPV)) { pr_err("%s selected but running as XenPV guest. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; @@ -1328,7 +1364,7 @@ static void __init spec_ctrl_disable_kernel_rrsba(void) if (ia32_cap & ARCH_CAP_RRSBA) { x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; - write_spec_ctrl_current(x86_spec_ctrl_base, true); + update_spec_ctrl(x86_spec_ctrl_base); } } @@ -1406,6 +1442,7 @@ static void __init spectre_v2_select_mitigation(void) if (IS_ENABLED(CONFIG_CPU_IBRS_ENTRY) && boot_cpu_has_bug(X86_BUG_RETBLEED) && retbleed_cmd != RETBLEED_CMD_OFF && + retbleed_cmd != RETBLEED_CMD_STUFF && boot_cpu_has(X86_FEATURE_IBRS) && boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) { mode = SPECTRE_V2_IBRS; @@ -1450,7 +1487,7 @@ static void __init spectre_v2_select_mitigation(void) if (spectre_v2_in_ibrs_mode(mode)) { x86_spec_ctrl_base |= SPEC_CTRL_IBRS; - write_spec_ctrl_current(x86_spec_ctrl_base, true); + update_spec_ctrl(x86_spec_ctrl_base); } switch (mode) { @@ -1564,7 +1601,7 @@ static void __init spectre_v2_select_mitigation(void) static void update_stibp_msr(void * __unused) { u64 val = spec_ctrl_current() | (x86_spec_ctrl_base & SPEC_CTRL_STIBP); - write_spec_ctrl_current(val, true); + update_spec_ctrl(val); } /* Update x86_spec_ctrl_base in case SMT state changed. */ @@ -1797,7 +1834,7 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void) x86_amd_ssb_disable(); } else { x86_spec_ctrl_base |= SPEC_CTRL_SSBD; - write_spec_ctrl_current(x86_spec_ctrl_base, true); + update_spec_ctrl(x86_spec_ctrl_base); } } @@ -2048,7 +2085,7 @@ int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) void x86_spec_ctrl_setup_ap(void) { if (boot_cpu_has(X86_FEATURE_MSR_SPEC_CTRL)) - write_spec_ctrl_current(x86_spec_ctrl_base, true); + update_spec_ctrl(x86_spec_ctrl_base); if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) x86_amd_ssb_disable(); @@ -2199,74 +2236,74 @@ static const char * const l1tf_vmx_states[] = { static ssize_t l1tf_show_state(char *buf) { if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) - return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + return sysfs_emit(buf, "%s\n", L1TF_DEFAULT_MSG); if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED || (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER && sched_smt_active())) { - return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, - l1tf_vmx_states[l1tf_vmx_mitigation]); + return sysfs_emit(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation]); } - return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, - l1tf_vmx_states[l1tf_vmx_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG, + l1tf_vmx_states[l1tf_vmx_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t itlb_multihit_show_state(char *buf) { if (!boot_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) || !boot_cpu_has(X86_FEATURE_VMX)) - return sprintf(buf, "KVM: Mitigation: VMX unsupported\n"); + return sysfs_emit(buf, "KVM: Mitigation: VMX unsupported\n"); else if (!(cr4_read_shadow() & X86_CR4_VMXE)) - return sprintf(buf, "KVM: Mitigation: VMX disabled\n"); + return sysfs_emit(buf, "KVM: Mitigation: VMX disabled\n"); else if (itlb_multihit_kvm_mitigation) - return sprintf(buf, "KVM: Mitigation: Split huge pages\n"); + return sysfs_emit(buf, "KVM: Mitigation: Split huge pages\n"); else - return sprintf(buf, "KVM: Vulnerable\n"); + return sysfs_emit(buf, "KVM: Vulnerable\n"); } #else static ssize_t l1tf_show_state(char *buf) { - return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG); + return sysfs_emit(buf, "%s\n", L1TF_DEFAULT_MSG); } static ssize_t itlb_multihit_show_state(char *buf) { - return sprintf(buf, "Processor vulnerable\n"); + return sysfs_emit(buf, "Processor vulnerable\n"); } #endif static ssize_t mds_show_state(char *buf) { if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { - return sprintf(buf, "%s; SMT Host state unknown\n", - mds_strings[mds_mitigation]); + return sysfs_emit(buf, "%s; SMT Host state unknown\n", + mds_strings[mds_mitigation]); } if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) { - return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], - (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" : - sched_smt_active() ? "mitigated" : "disabled")); + return sysfs_emit(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" : + sched_smt_active() ? "mitigated" : "disabled")); } - return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; SMT %s\n", mds_strings[mds_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t tsx_async_abort_show_state(char *buf) { if ((taa_mitigation == TAA_MITIGATION_TSX_DISABLED) || (taa_mitigation == TAA_MITIGATION_OFF)) - return sprintf(buf, "%s\n", taa_strings[taa_mitigation]); + return sysfs_emit(buf, "%s\n", taa_strings[taa_mitigation]); if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) { - return sprintf(buf, "%s; SMT Host state unknown\n", - taa_strings[taa_mitigation]); + return sysfs_emit(buf, "%s; SMT Host state unknown\n", + taa_strings[taa_mitigation]); } - return sprintf(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], - sched_smt_active() ? "vulnerable" : "disabled"); + return sysfs_emit(buf, "%s; SMT %s\n", taa_strings[taa_mitigation], + sched_smt_active() ? "vulnerable" : "disabled"); } static ssize_t mmio_stale_data_show_state(char *buf) @@ -2334,73 +2371,72 @@ static char *pbrsb_eibrs_state(void) static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) - return sprintf(buf, "Vulnerable: LFENCE\n"); + return sysfs_emit(buf, "Vulnerable: LFENCE\n"); if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled()) - return sprintf(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); + return sysfs_emit(buf, "Vulnerable: eIBRS with unprivileged eBPF\n"); if (sched_smt_active() && unprivileged_ebpf_enabled() && spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) - return sprintf(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); + return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); - return sprintf(buf, "%s%s%s%s%s%s%s\n", - spectre_v2_strings[spectre_v2_enabled], - ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", - stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", - pbrsb_eibrs_state(), - spectre_v2_module_string()); + return sysfs_emit(buf, "%s%s%s%s%s%s%s\n", + spectre_v2_strings[spectre_v2_enabled], + ibpb_state(), + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + stibp_state(), + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + pbrsb_eibrs_state(), + spectre_v2_module_string()); } static ssize_t srbds_show_state(char *buf) { - return sprintf(buf, "%s\n", srbds_strings[srbds_mitigation]); + return sysfs_emit(buf, "%s\n", srbds_strings[srbds_mitigation]); } static ssize_t retbleed_show_state(char *buf) { if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET || retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { - if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && - boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) - return sprintf(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && + boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) + return sysfs_emit(buf, "Vulnerable: untrained return thunk / IBPB on non-AMD based uarch\n"); - return sprintf(buf, "%s; SMT %s\n", - retbleed_strings[retbleed_mitigation], - !sched_smt_active() ? "disabled" : - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || - spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? - "enabled with STIBP protection" : "vulnerable"); + return sysfs_emit(buf, "%s; SMT %s\n", retbleed_strings[retbleed_mitigation], + !sched_smt_active() ? "disabled" : + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT || + spectre_v2_user_stibp == SPECTRE_V2_USER_STRICT_PREFERRED ? + "enabled with STIBP protection" : "vulnerable"); } - return sprintf(buf, "%s\n", retbleed_strings[retbleed_mitigation]); + return sysfs_emit(buf, "%s\n", retbleed_strings[retbleed_mitigation]); } static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr, char *buf, unsigned int bug) { if (!boot_cpu_has_bug(bug)) - return sprintf(buf, "Not affected\n"); + return sysfs_emit(buf, "Not affected\n"); switch (bug) { case X86_BUG_CPU_MELTDOWN: if (boot_cpu_has(X86_FEATURE_PTI)) - return sprintf(buf, "Mitigation: PTI\n"); + return sysfs_emit(buf, "Mitigation: PTI\n"); if (hypervisor_is_type(X86_HYPER_XEN_PV)) - return sprintf(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); + return sysfs_emit(buf, "Unknown (XEN PV detected, hypervisor mitigation required)\n"); break; case X86_BUG_SPECTRE_V1: - return sprintf(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); + return sysfs_emit(buf, "%s\n", spectre_v1_strings[spectre_v1_mitigation]); case X86_BUG_SPECTRE_V2: return spectre_v2_show_state(buf); case X86_BUG_SPEC_STORE_BYPASS: - return sprintf(buf, "%s\n", ssb_strings[ssb_mode]); + return sysfs_emit(buf, "%s\n", ssb_strings[ssb_mode]); case X86_BUG_L1TF: if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV)) @@ -2430,7 +2466,7 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr break; } - return sprintf(buf, "Vulnerable\n"); + return sysfs_emit(buf, "Vulnerable\n"); } ssize_t cpu_show_meltdown(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 66556833d7af..f4e5aa27eec6 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -11,15 +11,19 @@ #include <linux/slab.h> #include <linux/cacheinfo.h> #include <linux/cpu.h> +#include <linux/cpuhotplug.h> #include <linux/sched.h> #include <linux/capability.h> #include <linux/sysfs.h> #include <linux/pci.h> +#include <linux/stop_machine.h> #include <asm/cpufeature.h> #include <asm/cacheinfo.h> #include <asm/amd_nb.h> #include <asm/smp.h> +#include <asm/mtrr.h> +#include <asm/tlbflush.h> #include "cpu.h" @@ -35,6 +39,9 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); /* Shared L2 cache maps */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map); +/* Kernel controls MTRR and/or PAT MSRs. */ +unsigned int memory_caching_control __ro_after_init; + struct _cache_table { unsigned char descriptor; char cache_type; @@ -1040,3 +1047,175 @@ int populate_cache_leaves(unsigned int cpu) return 0; } + +/* + * Disable and enable caches. Needed for changing MTRRs and the PAT MSR. + * + * Since we are disabling the cache don't allow any interrupts, + * they would run extremely slow and would only increase the pain. + * + * The caller must ensure that local interrupts are disabled and + * are reenabled after cache_enable() has been called. + */ +static unsigned long saved_cr4; +static DEFINE_RAW_SPINLOCK(cache_disable_lock); + +void cache_disable(void) __acquires(cache_disable_lock) +{ + unsigned long cr0; + + /* + * Note that this is not ideal + * since the cache is only flushed/disabled for this CPU while the + * MTRRs are changed, but changing this requires more invasive + * changes to the way the kernel boots + */ + + raw_spin_lock(&cache_disable_lock); + + /* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */ + cr0 = read_cr0() | X86_CR0_CD; + write_cr0(cr0); + + /* + * Cache flushing is the most time-consuming step when programming + * the MTRRs. Fortunately, as per the Intel Software Development + * Manual, we can skip it if the processor supports cache self- + * snooping. + */ + if (!static_cpu_has(X86_FEATURE_SELFSNOOP)) + wbinvd(); + + /* Save value of CR4 and clear Page Global Enable (bit 7) */ + if (cpu_feature_enabled(X86_FEATURE_PGE)) { + saved_cr4 = __read_cr4(); + __write_cr4(saved_cr4 & ~X86_CR4_PGE); + } + + /* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */ + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + flush_tlb_local(); + + if (cpu_feature_enabled(X86_FEATURE_MTRR)) + mtrr_disable(); + + /* Again, only flush caches if we have to. */ + if (!static_cpu_has(X86_FEATURE_SELFSNOOP)) + wbinvd(); +} + +void cache_enable(void) __releases(cache_disable_lock) +{ + /* Flush TLBs (no need to flush caches - they are disabled) */ + count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); + flush_tlb_local(); + + if (cpu_feature_enabled(X86_FEATURE_MTRR)) + mtrr_enable(); + + /* Enable caches */ + write_cr0(read_cr0() & ~X86_CR0_CD); + + /* Restore value of CR4 */ + if (cpu_feature_enabled(X86_FEATURE_PGE)) + __write_cr4(saved_cr4); + + raw_spin_unlock(&cache_disable_lock); +} + +static void cache_cpu_init(void) +{ + unsigned long flags; + + local_irq_save(flags); + cache_disable(); + + if (memory_caching_control & CACHE_MTRR) + mtrr_generic_set_state(); + + if (memory_caching_control & CACHE_PAT) + pat_cpu_init(); + + cache_enable(); + local_irq_restore(flags); +} + +static bool cache_aps_delayed_init = true; + +void set_cache_aps_delayed_init(bool val) +{ + cache_aps_delayed_init = val; +} + +bool get_cache_aps_delayed_init(void) +{ + return cache_aps_delayed_init; +} + +static int cache_rendezvous_handler(void *unused) +{ + if (get_cache_aps_delayed_init() || !cpu_online(smp_processor_id())) + cache_cpu_init(); + + return 0; +} + +void __init cache_bp_init(void) +{ + mtrr_bp_init(); + pat_bp_init(); + + if (memory_caching_control) + cache_cpu_init(); +} + +void cache_bp_restore(void) +{ + if (memory_caching_control) + cache_cpu_init(); +} + +static int cache_ap_init(unsigned int cpu) +{ + if (!memory_caching_control || get_cache_aps_delayed_init()) + return 0; + + /* + * Ideally we should hold mtrr_mutex here to avoid MTRR entries + * changed, but this routine will be called in CPU boot time, + * holding the lock breaks it. + * + * This routine is called in two cases: + * + * 1. very early time of software resume, when there absolutely + * isn't MTRR entry changes; + * + * 2. CPU hotadd time. We let mtrr_add/del_page hold cpuhotplug + * lock to prevent MTRR entry changes + */ + stop_machine_from_inactive_cpu(cache_rendezvous_handler, NULL, + cpu_callout_mask); + + return 0; +} + +/* + * Delayed cache initialization for all AP's + */ +void cache_aps_init(void) +{ + if (!memory_caching_control || !get_cache_aps_delayed_init()) + return; + + stop_machine(cache_rendezvous_handler, NULL, cpu_online_mask); + set_cache_aps_delayed_init(false); +} + +static int __init cache_ap_register(void) +{ + cpuhp_setup_state_nocalls(CPUHP_AP_CACHECTRL_STARTING, + "x86/cachectrl:starting", + cache_ap_init, NULL); + return 0; +} +core_initcall(cache_ap_register); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 3e508f239098..9cfca3d7d0e2 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -22,9 +22,9 @@ #include <linux/io.h> #include <linux/syscore_ops.h> #include <linux/pgtable.h> +#include <linux/stackprotector.h> #include <asm/cmdline.h> -#include <asm/stackprotector.h> #include <asm/perf_event.h> #include <asm/mmu_context.h> #include <asm/doublefault.h> @@ -52,6 +52,7 @@ #include <asm/cpu.h> #include <asm/mce.h> #include <asm/msr.h> +#include <asm/cacheinfo.h> #include <asm/memtype.h> #include <asm/microcode.h> #include <asm/microcode_intel.h> @@ -609,6 +610,7 @@ static __always_inline void setup_cet(struct cpuinfo_x86 *c) if (!ibt_selftest()) { pr_err("IBT selftest: Failed!\n"); + wrmsrl(MSR_IA32_S_CET, 0); setup_clear_cpu_cap(X86_FEATURE_IBT); return; } @@ -701,16 +703,6 @@ static const char *table_lookup_model(struct cpuinfo_x86 *c) __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long)); __u32 cpu_caps_set[NCAPINTS + NBUGINTS] __aligned(sizeof(unsigned long)); -void load_percpu_segment(int cpu) -{ -#ifdef CONFIG_X86_32 - loadsegment(fs, __KERNEL_PERCPU); -#else - __loadsegment_simple(gs, 0); - wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu)); -#endif -} - #ifdef CONFIG_X86_32 /* The 32-bit entry code needs to find cpu_entry_area. */ DEFINE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); @@ -738,16 +730,45 @@ void load_fixmap_gdt(int cpu) } EXPORT_SYMBOL_GPL(load_fixmap_gdt); -/* - * Current gdt points %fs at the "master" per-cpu area: after this, - * it's on the real one. +/** + * switch_gdt_and_percpu_base - Switch to direct GDT and runtime per CPU base + * @cpu: The CPU number for which this is invoked + * + * Invoked during early boot to switch from early GDT and early per CPU to + * the direct GDT and the runtime per CPU area. On 32-bit the percpu base + * switch is implicit by loading the direct GDT. On 64bit this requires + * to update GSBASE. */ -void switch_to_new_gdt(int cpu) +void __init switch_gdt_and_percpu_base(int cpu) { - /* Load the original GDT */ load_direct_gdt(cpu); - /* Reload the per-cpu base */ - load_percpu_segment(cpu); + +#ifdef CONFIG_X86_64 + /* + * No need to load %gs. It is already correct. + * + * Writing %gs on 64bit would zero GSBASE which would make any per + * CPU operation up to the point of the wrmsrl() fault. + * + * Set GSBASE to the new offset. Until the wrmsrl() happens the + * early mapping is still valid. That means the GSBASE update will + * lose any prior per CPU data which was not copied over in + * setup_per_cpu_areas(). + * + * This works even with stackprotector enabled because the + * per CPU stack canary is 0 in both per CPU areas. + */ + wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu)); +#else + /* + * %fs is already set to __KERNEL_PERCPU, but after switching GDT + * it is required to load FS again so that the 'hidden' part is + * updated from the new GDT. Up to this point the early per CPU + * translation is active. Any content of the early per CPU data + * which was not copied over in setup_per_cpu_areas() is lost. + */ + loadsegment(fs, __KERNEL_PERCPU); +#endif } static const struct cpu_dev *cpu_devs[X86_VENDOR_NUM] = {}; @@ -1948,7 +1969,6 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_32 enable_sep_cpu(); #endif - mtrr_ap_init(); validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); @@ -1993,27 +2013,18 @@ static __init int setup_clearcpuid(char *arg) } __setup("clearcpuid=", setup_clearcpuid); +DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = { + .current_task = &init_task, + .preempt_count = INIT_PREEMPT_COUNT, + .top_of_stack = TOP_OF_INIT_STACK, +}; +EXPORT_PER_CPU_SYMBOL(pcpu_hot); + #ifdef CONFIG_X86_64 DEFINE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __aligned(PAGE_SIZE) __visible; EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data); -/* - * The following percpu variables are hot. Align current_task to - * cacheline size such that they fall in the same cacheline. - */ -DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned = - &init_task; -EXPORT_PER_CPU_SYMBOL(current_task); - -DEFINE_PER_CPU(void *, hardirq_stack_ptr); -DEFINE_PER_CPU(bool, hardirq_stack_inuse); - -DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; -EXPORT_PER_CPU_SYMBOL(__preempt_count); - -DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) = TOP_OF_INIT_STACK; - static void wrmsrl_cstar(unsigned long val) { /* @@ -2064,20 +2075,6 @@ void syscall_init(void) #else /* CONFIG_X86_64 */ -DEFINE_PER_CPU(struct task_struct *, current_task) = &init_task; -EXPORT_PER_CPU_SYMBOL(current_task); -DEFINE_PER_CPU(int, __preempt_count) = INIT_PREEMPT_COUNT; -EXPORT_PER_CPU_SYMBOL(__preempt_count); - -/* - * On x86_32, vm86 modifies tss.sp0, so sp0 isn't a reliable way to find - * the top of the kernel stack. Use an extra percpu variable to track the - * top of the kernel stack directly. - */ -DEFINE_PER_CPU(unsigned long, cpu_current_top_of_stack) = - (unsigned long)&init_thread_union + THREAD_SIZE; -EXPORT_PER_CPU_SYMBOL(cpu_current_top_of_stack); - #ifdef CONFIG_STACKPROTECTOR DEFINE_PER_CPU(unsigned long, __stack_chk_guard); EXPORT_PER_CPU_SYMBOL(__stack_chk_guard); @@ -2248,12 +2245,6 @@ void cpu_init(void) boot_cpu_has(X86_FEATURE_TSC) || boot_cpu_has(X86_FEATURE_DE)) cr4_clear_bits(X86_CR4_VME|X86_CR4_PVI|X86_CR4_TSD|X86_CR4_DE); - /* - * Initialize the per-CPU GDT with the boot GDT, - * and set up the GDT descriptor: - */ - switch_to_new_gdt(cpu); - if (IS_ENABLED(CONFIG_X86_64)) { loadsegment(fs, 0); memset(cur->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8); diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index c881bcafba7d..d95221117129 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -75,6 +75,7 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_SGX_LC, X86_FEATURE_SGX }, { X86_FEATURE_SGX1, X86_FEATURE_SGX }, { X86_FEATURE_SGX2, X86_FEATURE_SGX1 }, + { X86_FEATURE_SGX_EDECCSSA, X86_FEATURE_SGX1 }, { X86_FEATURE_XFD, X86_FEATURE_XSAVES }, { X86_FEATURE_XFD, X86_FEATURE_XGETBV1 }, { X86_FEATURE_AMX_TILE, X86_FEATURE_XFD }, diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index c393b8773ace..5a2962c492d3 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -339,7 +339,7 @@ static void init_hygon(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_ARAT); /* Hygon CPUs don't reset SS attributes on SYSRET, Xen does. */ - if (!cpu_has(c, X86_FEATURE_XENPV)) + if (!cpu_feature_enabled(X86_FEATURE_XENPV)) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); check_null_seg_clears_base(c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 2d7ea5480ec3..291d4167fab8 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -210,12 +210,154 @@ int intel_cpu_collect_info(struct ucode_cpu_info *uci) csig.rev = intel_get_microcode_revision(); uci->cpu_sig = csig; - uci->valid = 1; return 0; } EXPORT_SYMBOL_GPL(intel_cpu_collect_info); +/* + * Returns 1 if update has been found, 0 otherwise. + */ +int intel_find_matching_signature(void *mc, unsigned int csig, int cpf) +{ + struct microcode_header_intel *mc_hdr = mc; + struct extended_sigtable *ext_hdr; + struct extended_signature *ext_sig; + int i; + + if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf)) + return 1; + + /* Look for ext. headers: */ + if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE) + return 0; + + ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE; + ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE; + + for (i = 0; i < ext_hdr->count; i++) { + if (intel_cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf)) + return 1; + ext_sig++; + } + return 0; +} +EXPORT_SYMBOL_GPL(intel_find_matching_signature); + +/** + * intel_microcode_sanity_check() - Sanity check microcode file. + * @mc: Pointer to the microcode file contents. + * @print_err: Display failure reason if true, silent if false. + * @hdr_type: Type of file, i.e. normal microcode file or In Field Scan file. + * Validate if the microcode header type matches with the type + * specified here. + * + * Validate certain header fields and verify if computed checksum matches + * with the one specified in the header. + * + * Return: 0 if the file passes all the checks, -EINVAL if any of the checks + * fail. + */ +int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type) +{ + unsigned long total_size, data_size, ext_table_size; + struct microcode_header_intel *mc_header = mc; + struct extended_sigtable *ext_header = NULL; + u32 sum, orig_sum, ext_sigcount = 0, i; + struct extended_signature *ext_sig; + + total_size = get_totalsize(mc_header); + data_size = get_datasize(mc_header); + + if (data_size + MC_HEADER_SIZE > total_size) { + if (print_err) + pr_err("Error: bad microcode data file size.\n"); + return -EINVAL; + } + + if (mc_header->ldrver != 1 || mc_header->hdrver != hdr_type) { + if (print_err) + pr_err("Error: invalid/unknown microcode update format. Header type %d\n", + mc_header->hdrver); + return -EINVAL; + } + + ext_table_size = total_size - (MC_HEADER_SIZE + data_size); + if (ext_table_size) { + u32 ext_table_sum = 0; + u32 *ext_tablep; + + if (ext_table_size < EXT_HEADER_SIZE || + ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) { + if (print_err) + pr_err("Error: truncated extended signature table.\n"); + return -EINVAL; + } + + ext_header = mc + MC_HEADER_SIZE + data_size; + if (ext_table_size != exttable_size(ext_header)) { + if (print_err) + pr_err("Error: extended signature table size mismatch.\n"); + return -EFAULT; + } + + ext_sigcount = ext_header->count; + + /* + * Check extended table checksum: the sum of all dwords that + * comprise a valid table must be 0. + */ + ext_tablep = (u32 *)ext_header; + + i = ext_table_size / sizeof(u32); + while (i--) + ext_table_sum += ext_tablep[i]; + + if (ext_table_sum) { + if (print_err) + pr_warn("Bad extended signature table checksum, aborting.\n"); + return -EINVAL; + } + } + + /* + * Calculate the checksum of update data and header. The checksum of + * valid update data and header including the extended signature table + * must be 0. + */ + orig_sum = 0; + i = (MC_HEADER_SIZE + data_size) / sizeof(u32); + while (i--) + orig_sum += ((u32 *)mc)[i]; + + if (orig_sum) { + if (print_err) + pr_err("Bad microcode data checksum, aborting.\n"); + return -EINVAL; + } + + if (!ext_table_size) + return 0; + + /* + * Check extended signature checksum: 0 => valid. + */ + for (i = 0; i < ext_sigcount; i++) { + ext_sig = (void *)ext_header + EXT_HEADER_SIZE + + EXT_SIGNATURE_SIZE * i; + + sum = (mc_header->sig + mc_header->pf + mc_header->cksum) - + (ext_sig->sig + ext_sig->pf + ext_sig->cksum); + if (sum) { + if (print_err) + pr_err("Bad extended signature checksum, aborting.\n"); + return -EINVAL; + } + } + return 0; +} +EXPORT_SYMBOL_GPL(intel_microcode_sanity_check); + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; @@ -1034,8 +1176,32 @@ static const struct { static struct ratelimit_state bld_ratelimit; +static unsigned int sysctl_sld_mitigate = 1; static DEFINE_SEMAPHORE(buslock_sem); +#ifdef CONFIG_PROC_SYSCTL +static struct ctl_table sld_sysctls[] = { + { + .procname = "split_lock_mitigate", + .data = &sysctl_sld_mitigate, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_douintvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + {} +}; + +static int __init sld_mitigate_sysctl_init(void) +{ + register_sysctl_init("kernel", sld_sysctls); + return 0; +} + +late_initcall(sld_mitigate_sysctl_init); +#endif + static inline bool match_option(const char *arg, int arglen, const char *opt) { int len = strlen(opt), ratelimit; @@ -1146,12 +1312,20 @@ static void split_lock_init(void) split_lock_verify_msr(sld_state != sld_off); } -static void __split_lock_reenable(struct work_struct *work) +static void __split_lock_reenable_unlock(struct work_struct *work) { sld_update_msr(true); up(&buslock_sem); } +static DECLARE_DELAYED_WORK(sl_reenable_unlock, __split_lock_reenable_unlock); + +static void __split_lock_reenable(struct work_struct *work) +{ + sld_update_msr(true); +} +static DECLARE_DELAYED_WORK(sl_reenable, __split_lock_reenable); + /* * If a CPU goes offline with pending delayed work to re-enable split lock * detection then the delayed work will be executed on some other CPU. That @@ -1169,10 +1343,9 @@ static int splitlock_cpu_offline(unsigned int cpu) return 0; } -static DECLARE_DELAYED_WORK(split_lock_reenable, __split_lock_reenable); - static void split_lock_warn(unsigned long ip) { + struct delayed_work *work; int cpu; if (!current->reported_split_lock) @@ -1180,14 +1353,26 @@ static void split_lock_warn(unsigned long ip) current->comm, current->pid, ip); current->reported_split_lock = 1; - /* misery factor #1, sleep 10ms before trying to execute split lock */ - if (msleep_interruptible(10) > 0) - return; - /* Misery factor #2, only allow one buslocked disabled core at a time */ - if (down_interruptible(&buslock_sem) == -EINTR) - return; + if (sysctl_sld_mitigate) { + /* + * misery factor #1: + * sleep 10ms before trying to execute split lock. + */ + if (msleep_interruptible(10) > 0) + return; + /* + * Misery factor #2: + * only allow one buslocked disabled core at a time. + */ + if (down_interruptible(&buslock_sem) == -EINTR) + return; + work = &sl_reenable_unlock; + } else { + work = &sl_reenable; + } + cpu = get_cpu(); - schedule_delayed_work_on(cpu, &split_lock_reenable, 2); + schedule_delayed_work_on(cpu, work, 2); /* Disable split lock detection on this CPU to make progress */ sld_update_msr(false); diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c index fbaf12e43f41..3b8476158236 100644 --- a/arch/x86/kernel/cpu/intel_epb.c +++ b/arch/x86/kernel/cpu/intel_epb.c @@ -204,7 +204,12 @@ static int intel_epb_offline(unsigned int cpu) } static const struct x86_cpu_id intel_epb_normal[] = { - X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 7), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, + ENERGY_PERF_BIAS_NORMAL_POWERSAVE), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, + ENERGY_PERF_BIAS_NORMAL_POWERSAVE), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, + ENERGY_PERF_BIAS_NORMAL_POWERSAVE), {} }; diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 1c87501e0fa3..10fb5b5c9efa 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -788,6 +788,24 @@ _log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc) return status & MCI_STATUS_DEFERRED; } +static bool _log_error_deferred(unsigned int bank, u32 misc) +{ + if (!_log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), + mca_msr_reg(bank, MCA_ADDR), misc)) + return false; + + /* + * Non-SMCA systems don't have MCA_DESTAT/MCA_DEADDR registers. + * Return true here to avoid accessing these registers. + */ + if (!mce_flags.smca) + return true; + + /* Clear MCA_DESTAT if the deferred error was logged from MCA_STATUS. */ + wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0); + return true; +} + /* * We have three scenarios for checking for Deferred errors: * @@ -799,19 +817,8 @@ _log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc) */ static void log_error_deferred(unsigned int bank) { - bool defrd; - - defrd = _log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), - mca_msr_reg(bank, MCA_ADDR), 0); - - if (!mce_flags.smca) - return; - - /* Clear MCA_DESTAT if we logged the deferred error from MCA_STATUS. */ - if (defrd) { - wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0); + if (_log_error_deferred(bank, 0)) return; - } /* * Only deferred errors are logged in MCA_DE{STAT,ADDR} so just check @@ -832,7 +839,7 @@ static void amd_deferred_error_interrupt(void) static void log_error_thresholding(unsigned int bank, u64 misc) { - _log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), mca_msr_reg(bank, MCA_ADDR), misc); + _log_error_deferred(bank, misc); } static void log_and_reset_block(struct threshold_block *block) diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index 00483d1c27e4..c4477162c07d 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -203,6 +203,11 @@ static struct severity { BITSET(MCI_STATUS_OVER|MCI_STATUS_UC) ), MCESEV( + PANIC, "Uncorrected in kernel", + BITSET(MCI_STATUS_UC), + KERNEL + ), + MCESEV( UC, "Uncorrected", BITSET(MCI_STATUS_UC) ), @@ -391,9 +396,6 @@ static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, char *msg = s->msg; s->covered = 1; - if (s->sev >= MCE_UC_SEVERITY && ctx == IN_KERNEL) - return MCE_PANIC_SEVERITY; - return s->sev; } } diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index 3a35dec3ec55..56471f750762 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -901,8 +901,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size) * * These might be larger than 2K. */ -static enum ucode_state request_microcode_amd(int cpu, struct device *device, - bool refresh_fw) +static enum ucode_state request_microcode_amd(int cpu, struct device *device) { char fw_name[36] = "amd-ucode/microcode_amd.bin"; struct cpuinfo_x86 *c = &cpu_data(cpu); @@ -911,7 +910,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device, const struct firmware *fw; /* reload ucode container only on the boot cpu */ - if (!refresh_fw || !bsp) + if (!bsp) return UCODE_OK; if (c->x86 >= 0x15) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 6a41cee242f6..712aafff96e0 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -319,60 +319,6 @@ void reload_early_microcode(void) } } -static void collect_cpu_info_local(void *arg) -{ - struct cpu_info_ctx *ctx = arg; - - ctx->err = microcode_ops->collect_cpu_info(smp_processor_id(), - ctx->cpu_sig); -} - -static int collect_cpu_info_on_target(int cpu, struct cpu_signature *cpu_sig) -{ - struct cpu_info_ctx ctx = { .cpu_sig = cpu_sig, .err = 0 }; - int ret; - - ret = smp_call_function_single(cpu, collect_cpu_info_local, &ctx, 1); - if (!ret) - ret = ctx.err; - - return ret; -} - -static int collect_cpu_info(int cpu) -{ - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - int ret; - - memset(uci, 0, sizeof(*uci)); - - ret = collect_cpu_info_on_target(cpu, &uci->cpu_sig); - if (!ret) - uci->valid = 1; - - return ret; -} - -static void apply_microcode_local(void *arg) -{ - enum ucode_state *err = arg; - - *err = microcode_ops->apply_microcode(smp_processor_id()); -} - -static int apply_microcode_on_target(int cpu) -{ - enum ucode_state err; - int ret; - - ret = smp_call_function_single(cpu, apply_microcode_local, &err, 1); - if (!ret) { - if (err == UCODE_ERROR) - ret = 1; - } - return ret; -} - /* fake device for request_firmware */ static struct platform_device *microcode_pdev; @@ -458,7 +404,7 @@ static int __reload_late(void *info) * below. */ if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu) - apply_microcode_local(&err); + err = microcode_ops->apply_microcode(cpu); else goto wait_for_siblings; @@ -480,7 +426,7 @@ wait_for_siblings: * revision. */ if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu) - apply_microcode_local(&err); + err = microcode_ops->apply_microcode(cpu); return ret; } @@ -531,7 +477,7 @@ static ssize_t reload_store(struct device *dev, if (ret) goto put; - tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev, true); + tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev); if (tmp_ret != UCODE_NEW) goto put; @@ -589,91 +535,17 @@ static void microcode_fini_cpu(int cpu) microcode_ops->microcode_fini_cpu(cpu); } -static enum ucode_state microcode_resume_cpu(int cpu) +static enum ucode_state microcode_init_cpu(int cpu) { - if (apply_microcode_on_target(cpu)) - return UCODE_ERROR; - - pr_debug("CPU%d updated upon resume\n", cpu); - - return UCODE_OK; -} - -static enum ucode_state microcode_init_cpu(int cpu, bool refresh_fw) -{ - enum ucode_state ustate; struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - if (uci->valid) - return UCODE_OK; - - if (collect_cpu_info(cpu)) - return UCODE_ERROR; - - /* --dimm. Trigger a delayed update? */ - if (system_state != SYSTEM_RUNNING) - return UCODE_NFOUND; - - ustate = microcode_ops->request_microcode_fw(cpu, µcode_pdev->dev, refresh_fw); - if (ustate == UCODE_NEW) { - pr_debug("CPU%d updated upon init\n", cpu); - apply_microcode_on_target(cpu); - } - - return ustate; -} - -static enum ucode_state microcode_update_cpu(int cpu) -{ - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - - /* Refresh CPU microcode revision after resume. */ - collect_cpu_info(cpu); - - if (uci->valid) - return microcode_resume_cpu(cpu); - - return microcode_init_cpu(cpu, false); -} - -static int mc_device_add(struct device *dev, struct subsys_interface *sif) -{ - int err, cpu = dev->id; - - if (!cpu_online(cpu)) - return 0; - - pr_debug("CPU%d added\n", cpu); - - err = sysfs_create_group(&dev->kobj, &mc_attr_group); - if (err) - return err; + memset(uci, 0, sizeof(*uci)); - if (microcode_init_cpu(cpu, true) == UCODE_ERROR) - return -EINVAL; + microcode_ops->collect_cpu_info(cpu, &uci->cpu_sig); - return err; + return microcode_ops->apply_microcode(cpu); } -static void mc_device_remove(struct device *dev, struct subsys_interface *sif) -{ - int cpu = dev->id; - - if (!cpu_online(cpu)) - return; - - pr_debug("CPU%d removed\n", cpu); - microcode_fini_cpu(cpu); - sysfs_remove_group(&dev->kobj, &mc_attr_group); -} - -static struct subsys_interface mc_cpu_interface = { - .name = "microcode", - .subsys = &cpu_subsys, - .add_dev = mc_device_add, - .remove_dev = mc_device_remove, -}; - /** * microcode_bsp_resume - Update boot CPU microcode during resume. */ @@ -682,21 +554,23 @@ void microcode_bsp_resume(void) int cpu = smp_processor_id(); struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - if (uci->valid && uci->mc) + if (uci->mc) microcode_ops->apply_microcode(cpu); - else if (!uci->mc) + else reload_early_microcode(); } static struct syscore_ops mc_syscore_ops = { - .resume = microcode_bsp_resume, + .resume = microcode_bsp_resume, }; static int mc_cpu_starting(unsigned int cpu) { - microcode_update_cpu(cpu); - pr_debug("CPU%d added\n", cpu); - return 0; + enum ucode_state err = microcode_ops->apply_microcode(cpu); + + pr_debug("%s: CPU%d, err: %d\n", __func__, cpu, err); + + return err == UCODE_ERROR; } static int mc_cpu_online(unsigned int cpu) @@ -713,13 +587,30 @@ static int mc_cpu_down_prep(unsigned int cpu) struct device *dev; dev = get_cpu_device(cpu); + + microcode_fini_cpu(cpu); + /* Suspend is in progress, only remove the interface */ sysfs_remove_group(&dev->kobj, &mc_attr_group); - pr_debug("CPU%d removed\n", cpu); + pr_debug("%s: CPU%d\n", __func__, cpu); return 0; } +static void setup_online_cpu(struct work_struct *work) +{ + int cpu = smp_processor_id(); + enum ucode_state err; + + err = microcode_init_cpu(cpu); + if (err == UCODE_ERROR) { + pr_err("Error applying microcode on CPU%d\n", cpu); + return; + } + + mc_cpu_online(cpu); +} + static struct attribute *cpu_root_microcode_attrs[] = { #ifdef CONFIG_MICROCODE_LATE_LOADING &dev_attr_reload.attr, @@ -750,28 +641,19 @@ static int __init microcode_init(void) if (!microcode_ops) return -ENODEV; - microcode_pdev = platform_device_register_simple("microcode", -1, - NULL, 0); + microcode_pdev = platform_device_register_simple("microcode", -1, NULL, 0); if (IS_ERR(microcode_pdev)) return PTR_ERR(microcode_pdev); - cpus_read_lock(); - mutex_lock(µcode_mutex); - error = subsys_interface_register(&mc_cpu_interface); - mutex_unlock(µcode_mutex); - cpus_read_unlock(); - - if (error) - goto out_pdev; - - error = sysfs_create_group(&cpu_subsys.dev_root->kobj, - &cpu_root_microcode_group); - + error = sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpu_root_microcode_group); if (error) { pr_err("Error creating microcode group!\n"); - goto out_driver; + goto out_pdev; } + /* Do per-CPU setup */ + schedule_on_each_cpu(setup_online_cpu); + register_syscore_ops(&mc_syscore_ops); cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting", mc_cpu_starting, NULL); @@ -782,15 +664,6 @@ static int __init microcode_init(void) return 0; - out_driver: - cpus_read_lock(); - mutex_lock(µcode_mutex); - - subsys_interface_unregister(&mc_cpu_interface); - - mutex_unlock(µcode_mutex); - cpus_read_unlock(); - out_pdev: platform_device_unregister(microcode_pdev); return error; diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 1fcbd671f1df..cac2bdb57f0b 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -48,34 +48,6 @@ static int llc_size_per_core; /* * Returns 1 if update has been found, 0 otherwise. */ -static int find_matching_signature(void *mc, unsigned int csig, int cpf) -{ - struct microcode_header_intel *mc_hdr = mc; - struct extended_sigtable *ext_hdr; - struct extended_signature *ext_sig; - int i; - - if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf)) - return 1; - - /* Look for ext. headers: */ - if (get_totalsize(mc_hdr) <= get_datasize(mc_hdr) + MC_HEADER_SIZE) - return 0; - - ext_hdr = mc + get_datasize(mc_hdr) + MC_HEADER_SIZE; - ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE; - - for (i = 0; i < ext_hdr->count; i++) { - if (intel_cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf)) - return 1; - ext_sig++; - } - return 0; -} - -/* - * Returns 1 if update has been found, 0 otherwise. - */ static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev) { struct microcode_header_intel *mc_hdr = mc; @@ -83,7 +55,7 @@ static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev if (mc_hdr->rev <= new_rev) return 0; - return find_matching_signature(mc, csig, cpf); + return intel_find_matching_signature(mc, csig, cpf); } static struct ucode_patch *memdup_patch(void *data, unsigned int size) @@ -117,7 +89,7 @@ static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigne sig = mc_saved_hdr->sig; pf = mc_saved_hdr->pf; - if (find_matching_signature(data, sig, pf)) { + if (intel_find_matching_signature(data, sig, pf)) { prev_found = true; if (mc_hdr->rev <= mc_saved_hdr->rev) @@ -149,7 +121,7 @@ static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigne if (!p) return; - if (!find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf)) + if (!intel_find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf)) return; /* @@ -163,104 +135,6 @@ static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigne intel_ucode_patch = p->data; } -static int microcode_sanity_check(void *mc, int print_err) -{ - unsigned long total_size, data_size, ext_table_size; - struct microcode_header_intel *mc_header = mc; - struct extended_sigtable *ext_header = NULL; - u32 sum, orig_sum, ext_sigcount = 0, i; - struct extended_signature *ext_sig; - - total_size = get_totalsize(mc_header); - data_size = get_datasize(mc_header); - - if (data_size + MC_HEADER_SIZE > total_size) { - if (print_err) - pr_err("Error: bad microcode data file size.\n"); - return -EINVAL; - } - - if (mc_header->ldrver != 1 || mc_header->hdrver != 1) { - if (print_err) - pr_err("Error: invalid/unknown microcode update format.\n"); - return -EINVAL; - } - - ext_table_size = total_size - (MC_HEADER_SIZE + data_size); - if (ext_table_size) { - u32 ext_table_sum = 0; - u32 *ext_tablep; - - if ((ext_table_size < EXT_HEADER_SIZE) - || ((ext_table_size - EXT_HEADER_SIZE) % EXT_SIGNATURE_SIZE)) { - if (print_err) - pr_err("Error: truncated extended signature table.\n"); - return -EINVAL; - } - - ext_header = mc + MC_HEADER_SIZE + data_size; - if (ext_table_size != exttable_size(ext_header)) { - if (print_err) - pr_err("Error: extended signature table size mismatch.\n"); - return -EFAULT; - } - - ext_sigcount = ext_header->count; - - /* - * Check extended table checksum: the sum of all dwords that - * comprise a valid table must be 0. - */ - ext_tablep = (u32 *)ext_header; - - i = ext_table_size / sizeof(u32); - while (i--) - ext_table_sum += ext_tablep[i]; - - if (ext_table_sum) { - if (print_err) - pr_warn("Bad extended signature table checksum, aborting.\n"); - return -EINVAL; - } - } - - /* - * Calculate the checksum of update data and header. The checksum of - * valid update data and header including the extended signature table - * must be 0. - */ - orig_sum = 0; - i = (MC_HEADER_SIZE + data_size) / sizeof(u32); - while (i--) - orig_sum += ((u32 *)mc)[i]; - - if (orig_sum) { - if (print_err) - pr_err("Bad microcode data checksum, aborting.\n"); - return -EINVAL; - } - - if (!ext_table_size) - return 0; - - /* - * Check extended signature checksum: 0 => valid. - */ - for (i = 0; i < ext_sigcount; i++) { - ext_sig = (void *)ext_header + EXT_HEADER_SIZE + - EXT_SIGNATURE_SIZE * i; - - sum = (mc_header->sig + mc_header->pf + mc_header->cksum) - - (ext_sig->sig + ext_sig->pf + ext_sig->cksum); - if (sum) { - if (print_err) - pr_err("Bad extended signature checksum, aborting.\n"); - return -EINVAL; - } - } - return 0; -} - /* * Get microcode matching with BSP's model. Only CPUs with the same model as * BSP can stay in the platform. @@ -281,13 +155,13 @@ scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save) mc_size = get_totalsize(mc_header); if (!mc_size || mc_size > size || - microcode_sanity_check(data, 0) < 0) + intel_microcode_sanity_check(data, false, MC_HEADER_TYPE_MICROCODE) < 0) break; size -= mc_size; - if (!find_matching_signature(data, uci->cpu_sig.sig, - uci->cpu_sig.pf)) { + if (!intel_find_matching_signature(data, uci->cpu_sig.sig, + uci->cpu_sig.pf)) { data += mc_size; continue; } @@ -621,7 +495,6 @@ void load_ucode_intel_ap(void) else iup = &intel_ucode_patch; -reget: if (!*iup) { patch = __load_ucode_intel(&uci); if (!patch) @@ -632,12 +505,7 @@ reget: uci.mc = *iup; - if (apply_microcode_early(&uci, true)) { - /* Mixed-silicon system? Try to refetch the proper patch: */ - *iup = NULL; - - goto reget; - } + apply_microcode_early(&uci, true); } static struct microcode_intel *find_patch(struct ucode_cpu_info *uci) @@ -652,9 +520,9 @@ static struct microcode_intel *find_patch(struct ucode_cpu_info *uci) if (phdr->rev <= uci->cpu_sig.rev) continue; - if (!find_matching_signature(phdr, - uci->cpu_sig.sig, - uci->cpu_sig.pf)) + if (!intel_find_matching_signature(phdr, + uci->cpu_sig.sig, + uci->cpu_sig.pf)) continue; return iter->data; @@ -680,7 +548,6 @@ void reload_ucode_intel(void) static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) { - static struct cpu_signature prev; struct cpuinfo_x86 *c = &cpu_data(cpu_num); unsigned int val[2]; @@ -696,13 +563,6 @@ static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) csig->rev = c->microcode; - /* No extra locking on prev, races are harmless. */ - if (csig->sig != prev.sig || csig->pf != prev.pf || csig->rev != prev.rev) { - pr_info("sig=0x%x, pf=0x%x, revision=0x%x\n", - csig->sig, csig->pf, csig->rev); - prev = *csig; - } - return 0; } @@ -820,7 +680,7 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter) memcpy(mc, &mc_header, sizeof(mc_header)); data = mc + sizeof(mc_header); if (!copy_from_iter_full(data, data_size, iter) || - microcode_sanity_check(mc, 1) < 0) { + intel_microcode_sanity_check(mc, true, MC_HEADER_TYPE_MICROCODE) < 0) { break; } @@ -885,8 +745,7 @@ static bool is_blacklisted(unsigned int cpu) return false; } -static enum ucode_state request_microcode_fw(int cpu, struct device *device, - bool refresh_fw) +static enum ucode_state request_microcode_fw(int cpu, struct device *device) { struct cpuinfo_x86 *c = &cpu_data(cpu); const struct firmware *firmware; @@ -908,7 +767,7 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device, kvec.iov_base = (void *)firmware->data; kvec.iov_len = firmware->size; - iov_iter_kvec(&iter, WRITE, &kvec, 1, firmware->size); + iov_iter_kvec(&iter, ITER_SOURCE, &kvec, 1, firmware->size); ret = generic_load_microcode(cpu, &iter); release_firmware(firmware); diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 831613959a92..46668e255421 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -475,6 +475,12 @@ static bool __init ms_hyperv_x2apic_available(void) * (logically) generates MSIs directly to the system APIC irq domain. * There is no HPET, and PCI MSI/MSI-X interrupts are remapped by the * pci-hyperv host bridge. + * + * Note: for a Hyper-V root partition, this will always return false. + * The hypervisor doesn't expose these HYPERV_CPUID_VIRT_STACK_* cpuids by + * default, they are implemented as intercepts by the Windows Hyper-V stack. + * Even a nested root partition (L2 root) will not get them because the + * nested (L1) hypervisor filters them out. */ static bool __init ms_hyperv_msi_ext_dest_id(void) { diff --git a/arch/x86/kernel/cpu/mtrr/amd.c b/arch/x86/kernel/cpu/mtrr/amd.c index a65a0272096d..eff6ac62c0ff 100644 --- a/arch/x86/kernel/cpu/mtrr/amd.c +++ b/arch/x86/kernel/cpu/mtrr/amd.c @@ -109,7 +109,7 @@ amd_validate_add_page(unsigned long base, unsigned long size, unsigned int type) return 0; } -static const struct mtrr_ops amd_mtrr_ops = { +const struct mtrr_ops amd_mtrr_ops = { .vendor = X86_VENDOR_AMD, .set = amd_set_mtrr, .get = amd_get_mtrr, @@ -117,9 +117,3 @@ static const struct mtrr_ops amd_mtrr_ops = { .validate_add_page = amd_validate_add_page, .have_wrcomb = positive_have_wrcomb, }; - -int __init amd_init_mtrr(void) -{ - set_mtrr_ops(&amd_mtrr_ops); - return 0; -} diff --git a/arch/x86/kernel/cpu/mtrr/centaur.c b/arch/x86/kernel/cpu/mtrr/centaur.c index f27177816569..b8a74eddde83 100644 --- a/arch/x86/kernel/cpu/mtrr/centaur.c +++ b/arch/x86/kernel/cpu/mtrr/centaur.c @@ -111,7 +111,7 @@ centaur_validate_add_page(unsigned long base, unsigned long size, unsigned int t return 0; } -static const struct mtrr_ops centaur_mtrr_ops = { +const struct mtrr_ops centaur_mtrr_ops = { .vendor = X86_VENDOR_CENTAUR, .set = centaur_set_mcr, .get = centaur_get_mcr, @@ -119,9 +119,3 @@ static const struct mtrr_ops centaur_mtrr_ops = { .validate_add_page = centaur_validate_add_page, .have_wrcomb = positive_have_wrcomb, }; - -int __init centaur_init_mtrr(void) -{ - set_mtrr_ops(¢aur_mtrr_ops); - return 0; -} diff --git a/arch/x86/kernel/cpu/mtrr/cyrix.c b/arch/x86/kernel/cpu/mtrr/cyrix.c index ca670919b561..173b9e01e623 100644 --- a/arch/x86/kernel/cpu/mtrr/cyrix.c +++ b/arch/x86/kernel/cpu/mtrr/cyrix.c @@ -234,51 +234,11 @@ static void cyrix_set_arr(unsigned int reg, unsigned long base, post_set(); } -typedef struct { - unsigned long base; - unsigned long size; - mtrr_type type; -} arr_state_t; - -static arr_state_t arr_state[8] = { - {0UL, 0UL, 0UL}, {0UL, 0UL, 0UL}, {0UL, 0UL, 0UL}, {0UL, 0UL, 0UL}, - {0UL, 0UL, 0UL}, {0UL, 0UL, 0UL}, {0UL, 0UL, 0UL}, {0UL, 0UL, 0UL} -}; - -static unsigned char ccr_state[7] = { 0, 0, 0, 0, 0, 0, 0 }; - -static void cyrix_set_all(void) -{ - int i; - - prepare_set(); - - /* the CCRs are not contiguous */ - for (i = 0; i < 4; i++) - setCx86(CX86_CCR0 + i, ccr_state[i]); - for (; i < 7; i++) - setCx86(CX86_CCR4 + i, ccr_state[i]); - - for (i = 0; i < 8; i++) { - cyrix_set_arr(i, arr_state[i].base, - arr_state[i].size, arr_state[i].type); - } - - post_set(); -} - -static const struct mtrr_ops cyrix_mtrr_ops = { +const struct mtrr_ops cyrix_mtrr_ops = { .vendor = X86_VENDOR_CYRIX, - .set_all = cyrix_set_all, .set = cyrix_set_arr, .get = cyrix_get_arr, .get_free_region = cyrix_get_free_region, .validate_add_page = generic_validate_add_page, .have_wrcomb = positive_have_wrcomb, }; - -int __init cyrix_init_mtrr(void) -{ - set_mtrr_ops(&cyrix_mtrr_ops); - return 0; -} diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 558108296f3c..ee09d359e08f 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -10,6 +10,7 @@ #include <linux/mm.h> #include <asm/processor-flags.h> +#include <asm/cacheinfo.h> #include <asm/cpufeature.h> #include <asm/tlbflush.h> #include <asm/mtrr.h> @@ -396,9 +397,6 @@ print_fixed(unsigned base, unsigned step, const mtrr_type *types) } } -static void prepare_set(void); -static void post_set(void); - static void __init print_mtrr_state(void) { unsigned int i; @@ -444,20 +442,6 @@ static void __init print_mtrr_state(void) pr_debug("TOM2: %016llx aka %lldM\n", mtrr_tom2, mtrr_tom2>>20); } -/* PAT setup for BP. We need to go through sync steps here */ -void __init mtrr_bp_pat_init(void) -{ - unsigned long flags; - - local_irq_save(flags); - prepare_set(); - - pat_init(); - - post_set(); - local_irq_restore(flags); -} - /* Grab all of the MTRR state for this CPU into *state */ bool __init get_mtrr_state(void) { @@ -684,7 +668,10 @@ static u32 deftype_lo, deftype_hi; /** * set_mtrr_state - Set the MTRR state for this CPU. * - * NOTE: The CPU must already be in a safe state for MTRR changes. + * NOTE: The CPU must already be in a safe state for MTRR changes, including + * measures that only a single CPU can be active in set_mtrr_state() in + * order to not be subject to races for usage of deftype_lo. This is + * accomplished by taking cache_disable_lock. * RETURNS: 0 if no changes made, else a mask indicating what was changed. */ static unsigned long set_mtrr_state(void) @@ -715,106 +702,34 @@ static unsigned long set_mtrr_state(void) return change_mask; } - -static unsigned long cr4; -static DEFINE_RAW_SPINLOCK(set_atomicity_lock); - -/* - * Since we are disabling the cache don't allow any interrupts, - * they would run extremely slow and would only increase the pain. - * - * The caller must ensure that local interrupts are disabled and - * are reenabled after post_set() has been called. - */ -static void prepare_set(void) __acquires(set_atomicity_lock) +void mtrr_disable(void) { - unsigned long cr0; - - /* - * Note that this is not ideal - * since the cache is only flushed/disabled for this CPU while the - * MTRRs are changed, but changing this requires more invasive - * changes to the way the kernel boots - */ - - raw_spin_lock(&set_atomicity_lock); - - /* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */ - cr0 = read_cr0() | X86_CR0_CD; - write_cr0(cr0); - - /* - * Cache flushing is the most time-consuming step when programming - * the MTRRs. Fortunately, as per the Intel Software Development - * Manual, we can skip it if the processor supports cache self- - * snooping. - */ - if (!static_cpu_has(X86_FEATURE_SELFSNOOP)) - wbinvd(); - - /* Save value of CR4 and clear Page Global Enable (bit 7) */ - if (boot_cpu_has(X86_FEATURE_PGE)) { - cr4 = __read_cr4(); - __write_cr4(cr4 & ~X86_CR4_PGE); - } - - /* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */ - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - flush_tlb_local(); - /* Save MTRR state */ rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi); /* Disable MTRRs, and set the default type to uncached */ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi); - - /* Again, only flush caches if we have to. */ - if (!static_cpu_has(X86_FEATURE_SELFSNOOP)) - wbinvd(); } -static void post_set(void) __releases(set_atomicity_lock) +void mtrr_enable(void) { - /* Flush TLBs (no need to flush caches - they are disabled) */ - count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL); - flush_tlb_local(); - /* Intel (P6) standard MTRRs */ mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi); - - /* Enable caches */ - write_cr0(read_cr0() & ~X86_CR0_CD); - - /* Restore value of CR4 */ - if (boot_cpu_has(X86_FEATURE_PGE)) - __write_cr4(cr4); - raw_spin_unlock(&set_atomicity_lock); } -static void generic_set_all(void) +void mtrr_generic_set_state(void) { unsigned long mask, count; - unsigned long flags; - - local_irq_save(flags); - prepare_set(); /* Actually set the state */ mask = set_mtrr_state(); - /* also set PAT */ - pat_init(); - - post_set(); - local_irq_restore(flags); - /* Use the atomic bitops to update the global mask */ for (count = 0; count < sizeof(mask) * 8; ++count) { if (mask & 0x01) set_bit(count, &smp_changes_mask); mask >>= 1; } - } /** @@ -836,7 +751,7 @@ static void generic_set_mtrr(unsigned int reg, unsigned long base, vr = &mtrr_state.var_ranges[reg]; local_irq_save(flags); - prepare_set(); + cache_disable(); if (size == 0) { /* @@ -855,7 +770,7 @@ static void generic_set_mtrr(unsigned int reg, unsigned long base, mtrr_wrmsr(MTRRphysMask_MSR(reg), vr->mask_lo, vr->mask_hi); } - post_set(); + cache_enable(); local_irq_restore(flags); } @@ -914,8 +829,6 @@ int positive_have_wrcomb(void) * Generic structure... */ const struct mtrr_ops generic_mtrr_ops = { - .use_intel_if = 1, - .set_all = generic_set_all, .get = generic_get_mtrr, .get_free_region = generic_get_free_region, .set = generic_set_mtrr, diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 2746cac9d8a9..783f3210d582 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -46,6 +46,7 @@ #include <linux/syscore_ops.h> #include <linux/rcupdate.h> +#include <asm/cacheinfo.h> #include <asm/cpufeature.h> #include <asm/e820/api.h> #include <asm/mtrr.h> @@ -58,32 +59,18 @@ #define MTRR_TO_PHYS_WC_OFFSET 1000 u32 num_var_ranges; -static bool __mtrr_enabled; - static bool mtrr_enabled(void) { - return __mtrr_enabled; + return !!mtrr_if; } unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; static DEFINE_MUTEX(mtrr_mutex); u64 size_or_mask, size_and_mask; -static bool mtrr_aps_delayed_init; - -static const struct mtrr_ops *mtrr_ops[X86_VENDOR_NUM] __ro_after_init; const struct mtrr_ops *mtrr_if; -static void set_mtrr(unsigned int reg, unsigned long base, - unsigned long size, mtrr_type type); - -void __init set_mtrr_ops(const struct mtrr_ops *ops) -{ - if (ops->vendor && ops->vendor < X86_VENDOR_NUM) - mtrr_ops[ops->vendor] = ops; -} - /* Returns non-zero if we have the write-combining memory type */ static int have_wrcomb(void) { @@ -119,11 +106,11 @@ static int have_wrcomb(void) } /* This function returns the number of variable MTRRs */ -static void __init set_num_var_ranges(void) +static void __init set_num_var_ranges(bool use_generic) { unsigned long config = 0, dummy; - if (use_intel()) + if (use_generic) rdmsr(MSR_MTRRcap, config, dummy); else if (is_cpu(AMD) || is_cpu(HYGON)) config = 2; @@ -160,25 +147,8 @@ static int mtrr_rendezvous_handler(void *info) { struct set_mtrr_data *data = info; - /* - * We use this same function to initialize the mtrrs during boot, - * resume, runtime cpu online and on an explicit request to set a - * specific MTRR. - * - * During boot or suspend, the state of the boot cpu's mtrrs has been - * saved, and we want to replicate that across all the cpus that come - * online (either at the end of boot or resume or during a runtime cpu - * online). If we're doing that, @reg is set to something special and on - * all the cpu's we do mtrr_if->set_all() (On the logical cpu that - * started the boot/resume sequence, this might be a duplicate - * set_all()). - */ - if (data->smp_reg != ~0U) { - mtrr_if->set(data->smp_reg, data->smp_base, - data->smp_size, data->smp_type); - } else if (mtrr_aps_delayed_init || !cpu_online(smp_processor_id())) { - mtrr_if->set_all(); - } + mtrr_if->set(data->smp_reg, data->smp_base, + data->smp_size, data->smp_type); return 0; } @@ -248,19 +218,6 @@ static void set_mtrr_cpuslocked(unsigned int reg, unsigned long base, stop_machine_cpuslocked(mtrr_rendezvous_handler, &data, cpu_online_mask); } -static void set_mtrr_from_inactive_cpu(unsigned int reg, unsigned long base, - unsigned long size, mtrr_type type) -{ - struct set_mtrr_data data = { .smp_reg = reg, - .smp_base = base, - .smp_size = size, - .smp_type = type - }; - - stop_machine_from_inactive_cpu(mtrr_rendezvous_handler, &data, - cpu_callout_mask); -} - /** * mtrr_add_page - Add a memory type region * @base: Physical base address of region in pages (in units of 4 kB!) @@ -617,20 +574,6 @@ int arch_phys_wc_index(int handle) } EXPORT_SYMBOL_GPL(arch_phys_wc_index); -/* - * HACK ALERT! - * These should be called implicitly, but we can't yet until all the initcall - * stuff is done... - */ -static void __init init_ifs(void) -{ -#ifndef CONFIG_X86_64 - amd_init_mtrr(); - cyrix_init_mtrr(); - centaur_init_mtrr(); -#endif -} - /* The suspend/resume methods are only for CPU without MTRR. CPU using generic * MTRR driver doesn't require this */ @@ -686,10 +629,9 @@ int __initdata changed_by_mtrr_cleanup; */ void __init mtrr_bp_init(void) { + const char *why = "(not available)"; u32 phys_addr; - init_ifs(); - phys_addr = 32; if (boot_cpu_has(X86_FEATURE_MTRR)) { @@ -730,21 +672,21 @@ void __init mtrr_bp_init(void) case X86_VENDOR_AMD: if (cpu_feature_enabled(X86_FEATURE_K6_MTRR)) { /* Pre-Athlon (K6) AMD CPU MTRRs */ - mtrr_if = mtrr_ops[X86_VENDOR_AMD]; + mtrr_if = &amd_mtrr_ops; size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CENTAUR: if (cpu_feature_enabled(X86_FEATURE_CENTAUR_MCR)) { - mtrr_if = mtrr_ops[X86_VENDOR_CENTAUR]; + mtrr_if = ¢aur_mtrr_ops; size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } break; case X86_VENDOR_CYRIX: if (cpu_feature_enabled(X86_FEATURE_CYRIX_ARR)) { - mtrr_if = mtrr_ops[X86_VENDOR_CYRIX]; + mtrr_if = &cyrix_mtrr_ops; size_or_mask = SIZE_OR_MASK_BITS(32); size_and_mask = 0; } @@ -754,58 +696,23 @@ void __init mtrr_bp_init(void) } } - if (mtrr_if) { - __mtrr_enabled = true; - set_num_var_ranges(); + if (mtrr_enabled()) { + set_num_var_ranges(mtrr_if == &generic_mtrr_ops); init_table(); - if (use_intel()) { + if (mtrr_if == &generic_mtrr_ops) { /* BIOS may override */ - __mtrr_enabled = get_mtrr_state(); - - if (mtrr_enabled()) - mtrr_bp_pat_init(); - - if (mtrr_cleanup(phys_addr)) { - changed_by_mtrr_cleanup = 1; - mtrr_if->set_all(); + if (get_mtrr_state()) { + memory_caching_control |= CACHE_MTRR; + changed_by_mtrr_cleanup = mtrr_cleanup(phys_addr); + } else { + mtrr_if = NULL; + why = "by BIOS"; } } } - if (!mtrr_enabled()) { - pr_info("Disabled\n"); - - /* - * PAT initialization relies on MTRR's rendezvous handler. - * Skip PAT init until the handler can initialize both - * features independently. - */ - pat_disable("MTRRs disabled, skipping PAT initialization too."); - } -} - -void mtrr_ap_init(void) -{ if (!mtrr_enabled()) - return; - - if (!use_intel() || mtrr_aps_delayed_init) - return; - - /* - * Ideally we should hold mtrr_mutex here to avoid mtrr entries - * changed, but this routine will be called in cpu boot time, - * holding the lock breaks it. - * - * This routine is called in two cases: - * - * 1. very early time of software resume, when there absolutely - * isn't mtrr entry changes; - * - * 2. cpu hotadd time. We let mtrr_add/del_page hold cpuhotplug - * lock to prevent mtrr entry changes - */ - set_mtrr_from_inactive_cpu(~0U, 0, 0, 0); + pr_info("MTRRs disabled %s\n", why); } /** @@ -823,50 +730,12 @@ void mtrr_save_state(void) smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1); } -void set_mtrr_aps_delayed_init(void) -{ - if (!mtrr_enabled()) - return; - if (!use_intel()) - return; - - mtrr_aps_delayed_init = true; -} - -/* - * Delayed MTRR initialization for all AP's - */ -void mtrr_aps_init(void) -{ - if (!use_intel() || !mtrr_enabled()) - return; - - /* - * Check if someone has requested the delay of AP MTRR initialization, - * by doing set_mtrr_aps_delayed_init(), prior to this point. If not, - * then we are done. - */ - if (!mtrr_aps_delayed_init) - return; - - set_mtrr(~0U, 0, 0, 0); - mtrr_aps_delayed_init = false; -} - -void mtrr_bp_restore(void) -{ - if (!use_intel() || !mtrr_enabled()) - return; - - mtrr_if->set_all(); -} - static int __init mtrr_init_finialize(void) { if (!mtrr_enabled()) return 0; - if (use_intel()) { + if (memory_caching_control & CACHE_MTRR) { if (!changed_by_mtrr_cleanup) mtrr_state_warn(); return 0; diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.h b/arch/x86/kernel/cpu/mtrr/mtrr.h index 2ac99e561181..02eb5871492d 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.h +++ b/arch/x86/kernel/cpu/mtrr/mtrr.h @@ -14,11 +14,8 @@ extern unsigned int mtrr_usage_table[MTRR_MAX_VAR_RANGES]; struct mtrr_ops { u32 vendor; - u32 use_intel_if; void (*set)(unsigned int reg, unsigned long base, unsigned long size, mtrr_type type); - void (*set_all)(void); - void (*get)(unsigned int reg, unsigned long *base, unsigned long *size, mtrr_type *type); int (*get_free_region)(unsigned long base, unsigned long size, @@ -53,15 +50,11 @@ void set_mtrr_prepare_save(struct set_mtrr_context *ctxt); void fill_mtrr_var_range(unsigned int index, u32 base_lo, u32 base_hi, u32 mask_lo, u32 mask_hi); bool get_mtrr_state(void); -void mtrr_bp_pat_init(void); - -extern void __init set_mtrr_ops(const struct mtrr_ops *ops); extern u64 size_or_mask, size_and_mask; extern const struct mtrr_ops *mtrr_if; #define is_cpu(vnd) (mtrr_if && mtrr_if->vendor == X86_VENDOR_##vnd) -#define use_intel() (mtrr_if && mtrr_if->use_intel_if == 1) extern unsigned int num_var_ranges; extern u64 mtrr_tom2; @@ -71,10 +64,10 @@ void mtrr_state_warn(void); const char *mtrr_attrib_to_str(int x); void mtrr_wrmsr(unsigned, unsigned, unsigned); -/* CPU specific mtrr init functions */ -int amd_init_mtrr(void); -int cyrix_init_mtrr(void); -int centaur_init_mtrr(void); +/* CPU specific mtrr_ops vectors. */ +extern const struct mtrr_ops amd_mtrr_ops; +extern const struct mtrr_ops cyrix_mtrr_ops; +extern const struct mtrr_ops centaur_mtrr_ops; extern int changed_by_mtrr_cleanup; extern int mtrr_cleanup(unsigned address_bits); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 3266ea36667c..c98e52ff5f20 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -575,7 +575,7 @@ static void clear_closid_rmid(int cpu) state->default_rmid = 0; state->cur_closid = 0; state->cur_rmid = 0; - wrmsr(IA32_PQR_ASSOC, 0, 0); + wrmsr(MSR_IA32_PQR_ASSOC, 0, 0); } static int resctrl_online_cpu(unsigned int cpu) @@ -828,7 +828,6 @@ static __init void rdt_init_res_defs_intel(void) if (r->rid == RDT_RESOURCE_L3 || r->rid == RDT_RESOURCE_L2) { r->cache.arch_has_sparse_bitmaps = false; - r->cache.arch_has_empty_bitmaps = false; r->cache.arch_has_per_cpu_cfg = false; r->cache.min_cbm_bits = 1; } else if (r->rid == RDT_RESOURCE_MBA) { @@ -849,7 +848,6 @@ static __init void rdt_init_res_defs_amd(void) if (r->rid == RDT_RESOURCE_L3 || r->rid == RDT_RESOURCE_L2) { r->cache.arch_has_sparse_bitmaps = true; - r->cache.arch_has_empty_bitmaps = true; r->cache.arch_has_per_cpu_cfg = true; r->cache.min_cbm_bits = 0; } else if (r->rid == RDT_RESOURCE_MBA) { diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 1dafbdc5ac31..1df0e3262bca 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -105,8 +105,7 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) return false; } - if ((!r->cache.arch_has_empty_bitmaps && val == 0) || - val > r->default_ctrl) { + if ((r->cache.min_cbm_bits > 0 && val == 0) || val > r->default_ctrl) { rdt_last_cmd_puts("Mask out of range\n"); return false; } diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 5f7128686cfd..5ebd28e6aa0c 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -8,16 +8,6 @@ #include <linux/fs_context.h> #include <linux/jump_label.h> -#define MSR_IA32_L3_QOS_CFG 0xc81 -#define MSR_IA32_L2_QOS_CFG 0xc82 -#define MSR_IA32_L3_CBM_BASE 0xc90 -#define MSR_IA32_L2_CBM_BASE 0xd10 -#define MSR_IA32_MBA_THRTL_BASE 0xd50 -#define MSR_IA32_MBA_BW_BASE 0xc0000200 - -#define MSR_IA32_QM_CTR 0x0c8e -#define MSR_IA32_QM_EVTSEL 0x0c8d - #define L3_QOS_CDP_ENABLE 0x01ULL #define L2_QOS_CDP_ENABLE 0x01ULL diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 4e4231a58f38..524f8ff3e69c 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -477,7 +477,7 @@ static int pseudo_lock_fn(void *_rdtgrp) * pseudo-locked followed by reading of kernel memory to load it * into the cache. */ - __wrmsr(IA32_PQR_ASSOC, rmid_p, rdtgrp->closid); + __wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, rdtgrp->closid); /* * Cache was flushed earlier. Now access kernel memory to read it * into cache region associated with just activated plr->closid. @@ -513,7 +513,7 @@ static int pseudo_lock_fn(void *_rdtgrp) * Critical section end: restore closid with capacity bitmask that * does not overlap with pseudo-locked region. */ - __wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p); + __wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, closid_p); /* Re-enable the hardware prefetcher(s) */ wrmsrl(MSR_MISC_FEATURE_CONTROL, saved_msr); diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index fc01f81f6e2a..f53944fb8f7f 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -40,6 +40,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_PER_THREAD_MBA, CPUID_ECX, 0, 0x00000010, 3 }, { X86_FEATURE_SGX1, CPUID_EAX, 0, 0x00000012, 0 }, { X86_FEATURE_SGX2, CPUID_EAX, 1, 0x00000012, 0 }, + { X86_FEATURE_SGX_EDECCSSA, CPUID_EAX, 11, 0x00000012, 0 }, { X86_FEATURE_HW_PSTATE, CPUID_EDX, 7, 0x80000007, 0 }, { X86_FEATURE_CPB, CPUID_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 }, diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 1ec20807de1e..2a0e90fe2abc 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -160,8 +160,8 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, return ret; pginfo.addr = encl_page->desc & PAGE_MASK; - pginfo.contents = (unsigned long)kmap_atomic(b.contents); - pcmd_page = kmap_atomic(b.pcmd); + pginfo.contents = (unsigned long)kmap_local_page(b.contents); + pcmd_page = kmap_local_page(b.pcmd); pginfo.metadata = (unsigned long)pcmd_page + b.pcmd_offset; if (secs_page) @@ -187,8 +187,8 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, */ pcmd_page_empty = !memchr_inv(pcmd_page, 0, PAGE_SIZE); - kunmap_atomic(pcmd_page); - kunmap_atomic((void *)(unsigned long)pginfo.contents); + kunmap_local(pcmd_page); + kunmap_local((void *)(unsigned long)pginfo.contents); get_page(b.pcmd); sgx_encl_put_backing(&b); @@ -197,10 +197,10 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page, if (pcmd_page_empty && !reclaimer_writing_to_pcmd(encl, pcmd_first_page)) { sgx_encl_truncate_backing_page(encl, PFN_DOWN(page_pcmd_off)); - pcmd_page = kmap_atomic(b.pcmd); + pcmd_page = kmap_local_page(b.pcmd); if (memchr_inv(pcmd_page, 0, PAGE_SIZE)) pr_warn("PCMD page not empty after truncate.\n"); - kunmap_atomic(pcmd_page); + kunmap_local(pcmd_page); } put_page(b.pcmd); @@ -268,7 +268,7 @@ static struct sgx_encl_page *sgx_encl_load_page_in_vma(struct sgx_encl *encl, unsigned long addr, unsigned long vm_flags) { - unsigned long vm_prot_bits = vm_flags & (VM_READ | VM_WRITE | VM_EXEC); + unsigned long vm_prot_bits = vm_flags & VM_ACCESS_FLAGS; struct sgx_encl_page *entry; entry = xa_load(&encl->page_array, PFN_DOWN(addr)); @@ -502,7 +502,7 @@ static void sgx_vma_open(struct vm_area_struct *vma) int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start, unsigned long end, unsigned long vm_flags) { - unsigned long vm_prot_bits = vm_flags & (VM_READ | VM_WRITE | VM_EXEC); + unsigned long vm_prot_bits = vm_flags & VM_ACCESS_FLAGS; struct sgx_encl_page *page; unsigned long count = 0; int ret = 0; @@ -680,11 +680,15 @@ const struct vm_operations_struct sgx_vm_ops = { void sgx_encl_release(struct kref *ref) { struct sgx_encl *encl = container_of(ref, struct sgx_encl, refcount); + unsigned long max_page_index = PFN_DOWN(encl->base + encl->size - 1); struct sgx_va_page *va_page; struct sgx_encl_page *entry; - unsigned long index; + unsigned long count = 0; + + XA_STATE(xas, &encl->page_array, PFN_DOWN(encl->base)); - xa_for_each(&encl->page_array, index, entry) { + xas_lock(&xas); + xas_for_each(&xas, entry, max_page_index) { if (entry->epc_page) { /* * The page and its radix tree entry cannot be freed @@ -699,9 +703,20 @@ void sgx_encl_release(struct kref *ref) } kfree(entry); - /* Invoke scheduler to prevent soft lockups. */ - cond_resched(); + /* + * Invoke scheduler on every XA_CHECK_SCHED iteration + * to prevent soft lockups. + */ + if (!(++count % XA_CHECK_SCHED)) { + xas_pause(&xas); + xas_unlock(&xas); + + cond_resched(); + + xas_lock(&xas); + } } + xas_unlock(&xas); xa_destroy(&encl->page_array); diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index da8b8ea6b063..21ca0a831b70 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -111,7 +111,7 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs) encl->base = secs->base; encl->size = secs->size; encl->attributes = secs->attributes; - encl->attributes_mask = SGX_ATTR_DEBUG | SGX_ATTR_MODE64BIT | SGX_ATTR_KSS; + encl->attributes_mask = SGX_ATTR_UNPRIV_MASK; /* Set only after completion, as encl->lock has not been taken. */ set_bit(SGX_ENCL_CREATED, &encl->flags); @@ -221,11 +221,11 @@ static int __sgx_encl_add_page(struct sgx_encl *encl, pginfo.secs = (unsigned long)sgx_get_epc_virt_addr(encl->secs.epc_page); pginfo.addr = encl_page->desc & PAGE_MASK; pginfo.metadata = (unsigned long)secinfo; - pginfo.contents = (unsigned long)kmap_atomic(src_page); + pginfo.contents = (unsigned long)kmap_local_page(src_page); ret = __eadd(&pginfo, sgx_get_epc_virt_addr(epc_page)); - kunmap_atomic((void *)pginfo.contents); + kunmap_local((void *)pginfo.contents); put_page(src_page); return ret ? -EIO : 0; diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 0aad028f04d4..e5a37b6e9aa5 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -165,17 +165,17 @@ static int __sgx_encl_ewb(struct sgx_epc_page *epc_page, void *va_slot, pginfo.addr = 0; pginfo.secs = 0; - pginfo.contents = (unsigned long)kmap_atomic(backing->contents); - pginfo.metadata = (unsigned long)kmap_atomic(backing->pcmd) + + pginfo.contents = (unsigned long)kmap_local_page(backing->contents); + pginfo.metadata = (unsigned long)kmap_local_page(backing->pcmd) + backing->pcmd_offset; ret = __ewb(&pginfo, sgx_get_epc_virt_addr(epc_page), va_slot); set_page_dirty(backing->pcmd); set_page_dirty(backing->contents); - kunmap_atomic((void *)(unsigned long)(pginfo.metadata - + kunmap_local((void *)(unsigned long)(pginfo.metadata - backing->pcmd_offset)); - kunmap_atomic((void *)(unsigned long)pginfo.contents); + kunmap_local((void *)(unsigned long)pginfo.contents); return ret; } diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c index ec7bbac3a9f2..8009c8346d8f 100644 --- a/arch/x86/kernel/cpu/tsx.c +++ b/arch/x86/kernel/cpu/tsx.c @@ -58,24 +58,6 @@ static void tsx_enable(void) wrmsrl(MSR_IA32_TSX_CTRL, tsx); } -static bool tsx_ctrl_is_supported(void) -{ - u64 ia32_cap = x86_read_arch_cap_msr(); - - /* - * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this - * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. - * - * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a - * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES - * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get - * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, - * tsx= cmdline requests will do nothing on CPUs without - * MSR_IA32_TSX_CTRL support. - */ - return !!(ia32_cap & ARCH_CAP_TSX_CTRL_MSR); -} - static enum tsx_ctrl_states x86_get_tsx_auto_mode(void) { if (boot_cpu_has_bug(X86_BUG_TAA)) @@ -135,7 +117,7 @@ static void tsx_clear_cpuid(void) rdmsrl(MSR_TSX_FORCE_ABORT, msr); msr |= MSR_TFA_TSX_CPUID_CLEAR; wrmsrl(MSR_TSX_FORCE_ABORT, msr); - } else if (tsx_ctrl_is_supported()) { + } else if (cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL)) { rdmsrl(MSR_IA32_TSX_CTRL, msr); msr |= TSX_CTRL_CPUID_CLEAR; wrmsrl(MSR_IA32_TSX_CTRL, msr); @@ -158,7 +140,8 @@ static void tsx_dev_mode_disable(void) u64 mcu_opt_ctrl; /* Check if RTM_ALLOW exists */ - if (!boot_cpu_has_bug(X86_BUG_TAA) || !tsx_ctrl_is_supported() || + if (!boot_cpu_has_bug(X86_BUG_TAA) || + !cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL) || !cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL)) return; @@ -191,7 +174,20 @@ void __init tsx_init(void) return; } - if (!tsx_ctrl_is_supported()) { + /* + * TSX is controlled via MSR_IA32_TSX_CTRL. However, support for this + * MSR is enumerated by ARCH_CAP_TSX_MSR bit in MSR_IA32_ARCH_CAPABILITIES. + * + * TSX control (aka MSR_IA32_TSX_CTRL) is only available after a + * microcode update on CPUs that have their MSR_IA32_ARCH_CAPABILITIES + * bit MDS_NO=1. CPUs with MDS_NO=0 are not planned to get + * MSR_IA32_TSX_CTRL support even after a microcode update. Thus, + * tsx= cmdline requests will do nothing on CPUs without + * MSR_IA32_TSX_CTRL support. + */ + if (x86_read_arch_cap_msr() & ARCH_CAP_TSX_CTRL_MSR) { + setup_force_cpu_cap(X86_FEATURE_MSR_TSX_CTRL); + } else { tsx_ctrl_state = TSX_CTRL_NOT_SUPPORTED; return; } diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c index e75bc2f217ff..32d710f7eb84 100644 --- a/arch/x86/kernel/crash_dump_64.c +++ b/arch/x86/kernel/crash_dump_64.c @@ -57,7 +57,7 @@ ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos) struct kvec kvec = { .iov_base = buf, .iov_len = count }; struct iov_iter iter; - iov_iter_kvec(&iter, READ, &kvec, 1, count); + iov_iter_kvec(&iter, ITER_DEST, &kvec, 1, count); return read_from_oldmem(&iter, count, ppos, cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)); diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 5cd51f25f446..28da5dd83fc0 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -31,11 +31,6 @@ char __initdata cmd_line[COMMAND_LINE_SIZE]; int __initdata of_ioapic; -void __init early_init_dt_add_memory_arch(u64 base, u64 size) -{ - BUG(); -} - void __init add_dtb(u64 data) { initial_dtb = data + offsetof(struct setup_data, data); @@ -167,7 +162,14 @@ static void __init dtb_lapic_setup(void) return; } smp_found_config = 1; - pic_mode = 1; + if (of_property_read_bool(dn, "intel,virtual-wire-mode")) { + pr_info("Virtual Wire compatibility mode.\n"); + pic_mode = 0; + } else { + pr_info("IMCR and PIC compatibility mode.\n"); + pic_mode = 1; + } + register_lapic_address(lapic_addr); } @@ -248,7 +250,7 @@ static void __init dtb_add_ioapic(struct device_node *dn) ret = of_address_to_resource(dn, 0, &r); if (ret) { - printk(KERN_ERR "Can't obtain address from device node %pOF.\n", dn); + pr_err("Can't obtain address from device node %pOF.\n", dn); return; } mp_register_ioapic(++ioapic_id, r.start, gsi_top, &cfg); @@ -265,7 +267,7 @@ static void __init dtb_ioapic_setup(void) of_ioapic = 1; return; } - printk(KERN_ERR "Error: No information about IO-APIC in OF.\n"); + pr_err("Error: No information about IO-APIC in OF.\n"); } #else static void __init dtb_ioapic_setup(void) {} diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 722fd712e1cf..b4905d5173fd 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -37,7 +37,7 @@ const char *stack_type_name(enum stack_type type) static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info) { - unsigned long *begin = (unsigned long *)this_cpu_read(hardirq_stack_ptr); + unsigned long *begin = (unsigned long *)this_cpu_read(pcpu_hot.hardirq_stack_ptr); unsigned long *end = begin + (THREAD_SIZE / sizeof(long)); /* @@ -62,7 +62,7 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info) static bool in_softirq_stack(unsigned long *stack, struct stack_info *info) { - unsigned long *begin = (unsigned long *)this_cpu_read(softirq_stack_ptr); + unsigned long *begin = (unsigned long *)this_cpu_read(pcpu_hot.softirq_stack_ptr); unsigned long *end = begin + (THREAD_SIZE / sizeof(long)); /* diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index 6c5defd6569a..f05339fee778 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -134,7 +134,7 @@ static __always_inline bool in_exception_stack(unsigned long *stack, struct stac static __always_inline bool in_irq_stack(unsigned long *stack, struct stack_info *info) { - unsigned long *end = (unsigned long *)this_cpu_read(hardirq_stack_ptr); + unsigned long *end = (unsigned long *)this_cpu_read(pcpu_hot.hardirq_stack_ptr); unsigned long *begin; /* diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 9417d5aa7305..16f9814c9be0 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -94,17 +94,7 @@ static inline unsigned long espfix_base_addr(unsigned int cpu) static void init_espfix_random(void) { - unsigned long rand; - - /* - * This is run before the entropy pools are initialized, - * but this is hopefully better than nothing. - */ - if (!arch_get_random_longs(&rand, 1)) { - /* The constant is an arbitrary large prime */ - rand = rdtsc(); - rand *= 0xc345c6b72fd16123UL; - } + unsigned long rand = get_random_long(); slot_random = rand % ESPFIX_STACKS_PER_PAGE; page_random = (rand / ESPFIX_STACKS_PER_PAGE) diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index d00db56a8868..9baa89a8877d 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -391,8 +391,6 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, { struct fpstate *kstate = gfpu->fpstate; const union fpregs_state *ustate = buf; - struct pkru_state *xpkru; - int ret; if (!cpu_feature_enabled(X86_FEATURE_XSAVE)) { if (ustate->xsave.header.xfeatures & ~XFEATURE_MASK_FPSSE) @@ -406,16 +404,15 @@ int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, if (ustate->xsave.header.xfeatures & ~xcr0) return -EINVAL; - ret = copy_uabi_from_kernel_to_xstate(kstate, ustate); - if (ret) - return ret; + /* + * Nullify @vpkru to preserve its current value if PKRU's bit isn't set + * in the header. KVM's odd ABI is to leave PKRU untouched in this + * case (all other components are eventually re-initialized). + */ + if (!(ustate->xsave.header.xfeatures & XFEATURE_MASK_PKRU)) + vpkru = NULL; - /* Retrieve PKRU if not in init state */ - if (kstate->regs.xsave.header.xfeatures & XFEATURE_MASK_PKRU) { - xpkru = get_xsave_addr(&kstate->regs.xsave, XFEATURE_PKRU); - *vpkru = xpkru->pkru; - } - return 0; + return copy_uabi_from_kernel_to_xstate(kstate, ustate, vpkru); } EXPORT_SYMBOL_GPL(fpu_copy_uabi_to_guest_fpstate); #endif /* CONFIG_KVM */ diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c index 8946f89761cc..851eb13edc01 100644 --- a/arch/x86/kernel/fpu/init.c +++ b/arch/x86/kernel/fpu/init.c @@ -133,9 +133,6 @@ static void __init fpu__init_system_generic(void) fpu__init_system_mxcsr(); } -/* Get alignment of the TYPE. */ -#define TYPE_ALIGN(TYPE) offsetof(struct { char x; TYPE test; }, test) - /* * Enforce that 'MEMBER' is the last field of 'TYPE'. * @@ -143,8 +140,8 @@ static void __init fpu__init_system_generic(void) * because that's how C aligns structs. */ #define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \ - BUILD_BUG_ON(sizeof(TYPE) != ALIGN(offsetofend(TYPE, MEMBER), \ - TYPE_ALIGN(TYPE))) + BUILD_BUG_ON(sizeof(TYPE) != \ + ALIGN(offsetofend(TYPE, MEMBER), _Alignof(TYPE))) /* * We append the 'struct fpu' to the task_struct: diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c index 75ffaef8c299..6d056b68f4ed 100644 --- a/arch/x86/kernel/fpu/regset.c +++ b/arch/x86/kernel/fpu/regset.c @@ -167,7 +167,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset, } fpu_force_restore(fpu); - ret = copy_uabi_from_kernel_to_xstate(fpu->fpstate, kbuf ?: tmpbuf); + ret = copy_uabi_from_kernel_to_xstate(fpu->fpstate, kbuf ?: tmpbuf, &target->thread.pkru); out: vfree(tmpbuf); diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c index 91d4b6de58ab..558076dbde5b 100644 --- a/arch/x86/kernel/fpu/signal.c +++ b/arch/x86/kernel/fpu/signal.c @@ -396,7 +396,7 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx, fpregs = &fpu->fpstate->regs; if (use_xsave() && !fx_only) { - if (copy_sigframe_from_user_to_xstate(fpu->fpstate, buf_fx)) + if (copy_sigframe_from_user_to_xstate(tsk, buf_fx)) return false; } else { if (__copy_from_user(&fpregs->fxsave, buf_fx, diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 59e543b95a3c..714166cc25f2 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -440,8 +440,8 @@ static void __init __xstate_dump_leaves(void) } } -#define XSTATE_WARN_ON(x) do { \ - if (WARN_ONCE(x, "XSAVE consistency problem, dumping leaves")) { \ +#define XSTATE_WARN_ON(x, fmt, ...) do { \ + if (WARN_ONCE(x, "XSAVE consistency problem: " fmt, ##__VA_ARGS__)) { \ __xstate_dump_leaves(); \ } \ } while (0) @@ -554,8 +554,7 @@ static bool __init check_xstate_against_struct(int nr) (nr >= XFEATURE_MAX) || (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) || ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_RSRVD_COMP_16))) { - WARN_ONCE(1, "no structure for xstate: %d\n", nr); - XSTATE_WARN_ON(1); + XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr); return false; } return true; @@ -598,12 +597,13 @@ static bool __init paranoid_xstate_size_valid(unsigned int kernel_size) * XSAVES. */ if (!xsaves && xfeature_is_supervisor(i)) { - XSTATE_WARN_ON(1); + XSTATE_WARN_ON(1, "Got supervisor feature %d, but XSAVES not advertised\n", i); return false; } } size = xstate_calculate_size(fpu_kernel_cfg.max_features, compacted); - XSTATE_WARN_ON(size != kernel_size); + XSTATE_WARN_ON(size != kernel_size, + "size %u != kernel_size %u\n", size, kernel_size); return size == kernel_size; } @@ -1200,8 +1200,36 @@ static int copy_from_buffer(void *dst, unsigned int offset, unsigned int size, } +/** + * copy_uabi_to_xstate - Copy a UABI format buffer to the kernel xstate + * @fpstate: The fpstate buffer to copy to + * @kbuf: The UABI format buffer, if it comes from the kernel + * @ubuf: The UABI format buffer, if it comes from userspace + * @pkru: The location to write the PKRU value to + * + * Converts from the UABI format into the kernel internal hardware + * dependent format. + * + * This function ultimately has three different callers with distinct PKRU + * behavior. + * 1. When called from sigreturn the PKRU register will be restored from + * @fpstate via an XRSTOR. Correctly copying the UABI format buffer to + * @fpstate is sufficient to cover this case, but the caller will also + * pass a pointer to the thread_struct's pkru field in @pkru and updating + * it is harmless. + * 2. When called from ptrace the PKRU register will be restored from the + * thread_struct's pkru field. A pointer to that is passed in @pkru. + * The kernel will restore it manually, so the XRSTOR behavior that resets + * the PKRU register to the hardware init value (0) if the corresponding + * xfeatures bit is not set is emulated here. + * 3. When called from KVM the PKRU register will be restored from the vcpu's + * pkru field. A pointer to that is passed in @pkru. KVM hasn't used + * XRSTOR and hasn't had the PKRU resetting behavior described above. To + * preserve that KVM behavior, it passes NULL for @pkru if the xfeatures + * bit is not set. + */ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf, - const void __user *ubuf) + const void __user *ubuf, u32 *pkru) { struct xregs_state *xsave = &fpstate->regs.xsave; unsigned int offset, size; @@ -1250,6 +1278,20 @@ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf, } } + if (hdr.xfeatures & XFEATURE_MASK_PKRU) { + struct pkru_state *xpkru; + + xpkru = __raw_xsave_addr(xsave, XFEATURE_PKRU); + *pkru = xpkru->pkru; + } else { + /* + * KVM may pass NULL here to indicate that it does not need + * PKRU updated. + */ + if (pkru) + *pkru = 0; + } + /* * The state that came in from userspace was user-state only. * Mask all the user states out of 'xfeatures': @@ -1268,9 +1310,9 @@ static int copy_uabi_to_xstate(struct fpstate *fpstate, const void *kbuf, * Convert from a ptrace standard-format kernel buffer to kernel XSAVE[S] * format and copy to the target thread. Used by ptrace and KVM. */ -int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf) +int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru) { - return copy_uabi_to_xstate(fpstate, kbuf, NULL); + return copy_uabi_to_xstate(fpstate, kbuf, NULL, pkru); } /* @@ -1278,10 +1320,10 @@ int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf) * XSAVE[S] format and copy to the target thread. This is called from the * sigreturn() and rt_sigreturn() system calls. */ -int copy_sigframe_from_user_to_xstate(struct fpstate *fpstate, +int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf) { - return copy_uabi_to_xstate(fpstate, NULL, ubuf); + return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru); } static bool validate_independent_components(u64 mask) diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index 5ad47031383b..a4ecb04d8d64 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -46,8 +46,8 @@ extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, u32 pkru_val, enum xstate_copy_mode copy_mode); extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode mode); -extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf); -extern int copy_sigframe_from_user_to_xstate(struct fpstate *fpstate, const void __user *ubuf); +extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru); +extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void __user *ubuf); extern void fpu__init_cpu_xstate(void); diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index bd165004776d..ae0a8e515e20 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -69,6 +69,10 @@ static const char *ftrace_nop_replace(void) static const char *ftrace_call_replace(unsigned long ip, unsigned long addr) { + /* + * No need to translate into a callthunk. The trampoline does + * the depth accounting itself. + */ return text_gen_insn(CALL_INSN_OPCODE, (void *)ip, (void *)addr); } @@ -217,7 +221,9 @@ void ftrace_replace_code(int enable) ret = ftrace_verify_code(rec->ip, old); if (ret) { + ftrace_expected = old; ftrace_bug(ret, rec); + ftrace_expected = NULL; return; } } @@ -317,7 +323,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) unsigned long size; unsigned long *ptr; void *trampoline; - void *ip; + void *ip, *dest; /* 48 8b 15 <offset> is movq <offset>(%rip), %rdx */ unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 }; unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE }; @@ -359,7 +365,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) ip = trampoline + size; if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) - __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, &__x86_return_thunk, JMP32_INSN_SIZE); + __text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE); else memcpy(ip, retq, sizeof(retq)); @@ -404,17 +410,19 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) /* put in the call to the function */ mutex_lock(&text_mutex); call_offset -= start_offset; + /* + * No need to translate into a callthunk. The trampoline does + * the depth accounting before the call already. + */ + dest = ftrace_ops_get_func(ops); memcpy(trampoline + call_offset, - text_gen_insn(CALL_INSN_OPCODE, - trampoline + call_offset, - ftrace_ops_get_func(ops)), CALL_INSN_SIZE); + text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest), + CALL_INSN_SIZE); mutex_unlock(&text_mutex); /* ALLOC_TRAMP flags lets us know we created it */ ops->flags |= FTRACE_OPS_FL_ALLOC_TRAMP; - set_vm_flush_reset_perms(trampoline); - if (likely(system_state != SYSTEM_BOOTING)) set_memory_ro((unsigned long)trampoline, npages); set_memory_x((unsigned long)trampoline, npages); diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 2a4be92fd144..1265ad519249 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -3,8 +3,9 @@ * Copyright (C) 2014 Steven Rostedt, Red Hat Inc */ -#include <linux/linkage.h> #include <linux/cfi_types.h> +#include <linux/linkage.h> +#include <asm/asm-offsets.h> #include <asm/ptrace.h> #include <asm/ftrace.h> #include <asm/export.h> @@ -131,16 +132,19 @@ .endm SYM_TYPED_FUNC_START(ftrace_stub) + CALL_DEPTH_ACCOUNT RET SYM_FUNC_END(ftrace_stub) SYM_TYPED_FUNC_START(ftrace_stub_graph) + CALL_DEPTH_ACCOUNT RET SYM_FUNC_END(ftrace_stub_graph) #ifdef CONFIG_DYNAMIC_FTRACE SYM_FUNC_START(__fentry__) + CALL_DEPTH_ACCOUNT RET SYM_FUNC_END(__fentry__) EXPORT_SYMBOL(__fentry__) @@ -149,6 +153,8 @@ SYM_FUNC_START(ftrace_caller) /* save_mcount_regs fills in first two parameters */ save_mcount_regs + CALL_DEPTH_ACCOUNT + /* Stack - skipping return address of ftrace_caller */ leaq MCOUNT_REG_SIZE+8(%rsp), %rcx movq %rcx, RSP(%rsp) @@ -164,6 +170,9 @@ SYM_INNER_LABEL(ftrace_caller_op_ptr, SYM_L_GLOBAL) /* Only ops with REGS flag set should have CS register set */ movq $0, CS(%rsp) + /* Account for the function call below */ + CALL_DEPTH_ACCOUNT + SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL) ANNOTATE_NOENDBR call ftrace_stub @@ -193,6 +202,8 @@ SYM_FUNC_START(ftrace_regs_caller) save_mcount_regs 8 /* save_mcount_regs fills in first two parameters */ + CALL_DEPTH_ACCOUNT + SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL) ANNOTATE_NOENDBR /* Load the ftrace_ops into the 3rd parameter */ @@ -223,6 +234,9 @@ SYM_INNER_LABEL(ftrace_regs_caller_op_ptr, SYM_L_GLOBAL) /* regs go into 4th parameter */ leaq (%rsp), %rcx + /* Account for the function call below */ + CALL_DEPTH_ACCOUNT + SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL) ANNOTATE_NOENDBR call ftrace_stub @@ -275,7 +289,20 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL) /* Restore flags */ popfq UNWIND_HINT_FUNC - RET + + /* + * The above left an extra return value on the stack; effectively + * doing a tail-call without using a register. This PUSH;RET + * pattern unbalances the RSB, inject a pointless CALL to rebalance. + */ + ANNOTATE_INTRA_FUNCTION_CALL + CALL .Ldo_rebalance + int3 +.Ldo_rebalance: + add $8, %rsp + ALTERNATIVE __stringify(RET), \ + __stringify(ANNOTATE_UNRET_SAFE; ret; int3), \ + X86_FEATURE_CALL_DEPTH SYM_FUNC_END(ftrace_regs_caller) STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller) @@ -284,6 +311,8 @@ STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller) #else /* ! CONFIG_DYNAMIC_FTRACE */ SYM_FUNC_START(__fentry__) + CALL_DEPTH_ACCOUNT + cmpq $ftrace_stub, ftrace_trace_function jnz trace RET @@ -337,6 +366,8 @@ SYM_CODE_START(return_to_handler) int3 .Ldo_rop: mov %rdi, (%rsp) - RET + ALTERNATIVE __stringify(RET), \ + __stringify(ANNOTATE_UNRET_SAFE; ret; int3), \ + X86_FEATURE_CALL_DEPTH SYM_CODE_END(return_to_handler) #endif diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 9b7acc9c7874..67c8ed99144b 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -261,16 +261,6 @@ SYM_FUNC_START(startup_32_smp) addl $__PAGE_OFFSET, %esp /* - * start system 32-bit setup. We need to re-do some of the things done - * in 16-bit mode for the "real" operations. - */ - movl setup_once_ref,%eax - andl %eax,%eax - jz 1f # Did we do this already? - call *%eax -1: - -/* * Check if it is 486 */ movb $4,X86 # at least 486 @@ -331,18 +321,7 @@ SYM_FUNC_END(startup_32_smp) #include "verify_cpu.S" -/* - * setup_once - * - * The setup work we only want to run on the BSP. - * - * Warning: %esi is live across this function. - */ __INIT -setup_once: - andl $0,setup_once_ref /* Once is enough, thanks */ - RET - SYM_FUNC_START(early_idt_handler_array) # 36(%esp) %eflags # 32(%esp) %cs @@ -458,7 +437,6 @@ SYM_DATA(early_recursion_flag, .long 0) __REFDATA .align 4 SYM_DATA(initial_code, .long i386_start_kernel) -SYM_DATA(setup_once_ref, .long setup_once) #ifdef CONFIG_PAGE_TABLE_ISOLATION #define PGD_ALIGN (2 * PAGE_SIZE) diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index d860d437631b..222efd4a09bc 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -370,6 +370,7 @@ SYM_CODE_END(secondary_startup_64) * start_secondary() via .Ljump_to_C_code. */ SYM_CODE_START(start_cpu0) + ANNOTATE_NOENDBR UNWIND_HINT_EMPTY movq initial_stack(%rip), %rsp jmp .Ljump_to_C_code diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 15aefa3f3e18..3aa5304200c5 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -407,7 +407,7 @@ struct legacy_pic null_legacy_pic = { .make_irq = legacy_pic_uint_noop, }; -struct legacy_pic default_legacy_pic = { +static struct legacy_pic default_legacy_pic = { .nr_legacy_irqs = NR_IRQS_LEGACY, .chip = &i8259A_chip, .mask = mask_8259A_irq, diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c index 01833ebf5e8e..dc1049c01f9b 100644 --- a/arch/x86/kernel/irq_32.c +++ b/arch/x86/kernel/irq_32.c @@ -52,9 +52,6 @@ static inline int check_stack_overflow(void) { return 0; } static inline void print_stack_overflow(void) { } #endif -DEFINE_PER_CPU(struct irq_stack *, hardirq_stack_ptr); -DEFINE_PER_CPU(struct irq_stack *, softirq_stack_ptr); - static void call_on_stack(void *func, void *stack) { asm volatile("xchgl %%ebx,%%esp \n" @@ -77,7 +74,7 @@ static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc) u32 *isp, *prev_esp, arg1; curstk = (struct irq_stack *) current_stack(); - irqstk = __this_cpu_read(hardirq_stack_ptr); + irqstk = __this_cpu_read(pcpu_hot.hardirq_stack_ptr); /* * this is where we switch to the IRQ stack. However, if we are @@ -115,7 +112,7 @@ int irq_init_percpu_irqstack(unsigned int cpu) int node = cpu_to_node(cpu); struct page *ph, *ps; - if (per_cpu(hardirq_stack_ptr, cpu)) + if (per_cpu(pcpu_hot.hardirq_stack_ptr, cpu)) return 0; ph = alloc_pages_node(node, THREADINFO_GFP, THREAD_SIZE_ORDER); @@ -127,8 +124,8 @@ int irq_init_percpu_irqstack(unsigned int cpu) return -ENOMEM; } - per_cpu(hardirq_stack_ptr, cpu) = page_address(ph); - per_cpu(softirq_stack_ptr, cpu) = page_address(ps); + per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = page_address(ph); + per_cpu(pcpu_hot.softirq_stack_ptr, cpu) = page_address(ps); return 0; } @@ -138,7 +135,7 @@ void do_softirq_own_stack(void) struct irq_stack *irqstk; u32 *isp, *prev_esp; - irqstk = __this_cpu_read(softirq_stack_ptr); + irqstk = __this_cpu_read(pcpu_hot.softirq_stack_ptr); /* build the stack frame on the softirq stack */ isp = (u32 *) ((char *)irqstk + sizeof(*irqstk)); diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c index 1c0fb96b9e39..fe0c859873d1 100644 --- a/arch/x86/kernel/irq_64.c +++ b/arch/x86/kernel/irq_64.c @@ -50,7 +50,7 @@ static int map_irq_stack(unsigned int cpu) return -ENOMEM; /* Store actual TOS to avoid adjustment in the hotpath */ - per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8; + per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8; return 0; } #else @@ -63,14 +63,14 @@ static int map_irq_stack(unsigned int cpu) void *va = per_cpu_ptr(&irq_stack_backing_store, cpu); /* Store actual TOS to avoid adjustment in the hotpath */ - per_cpu(hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8; + per_cpu(pcpu_hot.hardirq_stack_ptr, cpu) = va + IRQ_STACK_SIZE - 8; return 0; } #endif int irq_init_percpu_irqstack(unsigned int cpu) { - if (per_cpu(hardirq_stack_ptr, cpu)) + if (per_cpu(pcpu_hot.hardirq_stack_ptr, cpu)) return 0; return map_irq_stack(cpu); } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index eb8bc82846b9..01b8d956aa76 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -414,7 +414,6 @@ void *alloc_insn_page(void) if (!page) return NULL; - set_vm_flush_reset_perms(page); /* * First make the page read-only, and only then make it executable to * prevent it from being W+X in between. diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index d4e48b4a438b..1cceac5984da 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -349,7 +349,7 @@ static notrace void kvm_guest_apic_eoi_write(u32 reg, u32 val) static void kvm_guest_cpu_init(void) { if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) { - u64 pa = slow_virt_to_phys(this_cpu_ptr(&apf_reason)); + u64 pa; WARN_ON_ONCE(!static_branch_likely(&kvm_async_pf_enabled)); @@ -798,19 +798,13 @@ extern bool __raw_callee_save___kvm_vcpu_is_preempted(long); * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and * restoring to/from the stack. */ -asm( -".pushsection .text;" -".global __raw_callee_save___kvm_vcpu_is_preempted;" -".type __raw_callee_save___kvm_vcpu_is_preempted, @function;" -"__raw_callee_save___kvm_vcpu_is_preempted:" -ASM_ENDBR -"movq __per_cpu_offset(,%rdi,8), %rax;" -"cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);" -"setne %al;" -ASM_RET -".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;" -".popsection"); +#define PV_VCPU_PREEMPTED_ASM \ + "movq __per_cpu_offset(,%rdi,8), %rax\n\t" \ + "cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax)\n\t" \ + "setne %al\n\t" +DEFINE_PARAVIRT_ASM(__raw_callee_save___kvm_vcpu_is_preempted, + PV_VCPU_PREEMPTED_ASM, .text); #endif static void __init kvm_guest_init(void) diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index c032edcd3d95..705fb2a41d7d 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -53,7 +53,7 @@ static unsigned long int get_module_load_offset(void) */ if (module_load_offset == 0) module_load_offset = - (prandom_u32_max(1024) + 1) * PAGE_SIZE; + get_random_u32_inclusive(1, 1024) * PAGE_SIZE; mutex_unlock(&module_kaslr_mutex); } return module_load_offset; @@ -74,10 +74,11 @@ void *module_alloc(unsigned long size) return NULL; p = __vmalloc_node_range(size, MODULE_ALIGN, - MODULES_VADDR + get_module_load_offset(), - MODULES_END, gfp_mask, - PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, - __builtin_return_address(0)); + MODULES_VADDR + get_module_load_offset(), + MODULES_END, gfp_mask, PAGE_KERNEL, + VM_FLUSH_RESET_PERMS | VM_DEFER_KMEMLEAK, + NUMA_NO_NODE, __builtin_return_address(0)); + if (p && (kasan_alloc_module_shadow(p, size, gfp_mask) < 0)) { vfree(p); return NULL; @@ -251,14 +252,13 @@ int module_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *me) { - const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL, + const Elf_Shdr *s, *alt = NULL, *locks = NULL, *para = NULL, *orc = NULL, *orc_ip = NULL, - *retpolines = NULL, *returns = NULL, *ibt_endbr = NULL; + *retpolines = NULL, *returns = NULL, *ibt_endbr = NULL, + *calls = NULL, *cfi = NULL; char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) { - if (!strcmp(".text", secstrings + s->sh_name)) - text = s; if (!strcmp(".altinstructions", secstrings + s->sh_name)) alt = s; if (!strcmp(".smp_locks", secstrings + s->sh_name)) @@ -273,6 +273,10 @@ int module_finalize(const Elf_Ehdr *hdr, retpolines = s; if (!strcmp(".return_sites", secstrings + s->sh_name)) returns = s; + if (!strcmp(".call_sites", secstrings + s->sh_name)) + calls = s; + if (!strcmp(".cfi_sites", secstrings + s->sh_name)) + cfi = s; if (!strcmp(".ibt_endbr_seal", secstrings + s->sh_name)) ibt_endbr = s; } @@ -285,6 +289,22 @@ int module_finalize(const Elf_Ehdr *hdr, void *pseg = (void *)para->sh_addr; apply_paravirt(pseg, pseg + para->sh_size); } + if (retpolines || cfi) { + void *rseg = NULL, *cseg = NULL; + unsigned int rsize = 0, csize = 0; + + if (retpolines) { + rseg = (void *)retpolines->sh_addr; + rsize = retpolines->sh_size; + } + + if (cfi) { + cseg = (void *)cfi->sh_addr; + csize = cfi->sh_size; + } + + apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize); + } if (retpolines) { void *rseg = (void *)retpolines->sh_addr; apply_retpolines(rseg, rseg + retpolines->sh_size); @@ -298,16 +318,32 @@ int module_finalize(const Elf_Ehdr *hdr, void *aseg = (void *)alt->sh_addr; apply_alternatives(aseg, aseg + alt->sh_size); } + if (calls || para) { + struct callthunk_sites cs = {}; + + if (calls) { + cs.call_start = (void *)calls->sh_addr; + cs.call_end = (void *)calls->sh_addr + calls->sh_size; + } + + if (para) { + cs.pv_start = (void *)para->sh_addr; + cs.pv_end = (void *)para->sh_addr + para->sh_size; + } + + callthunks_patch_module_calls(&cs, me); + } if (ibt_endbr) { void *iseg = (void *)ibt_endbr->sh_addr; apply_ibt_endbr(iseg, iseg + ibt_endbr->sh_size); } - if (locks && text) { + if (locks) { void *lseg = (void *)locks->sh_addr; - void *tseg = (void *)text->sh_addr; + void *text = me->core_layout.base; + void *text_end = text + me->core_layout.text_size; alternatives_smp_module_add(me, me->name, lseg, lseg + locks->sh_size, - tseg, tseg + text->sh_size); + text, text_end); } if (orc && orc_ip) diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 7ca2d46c08cc..327757afb027 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -37,27 +37,10 @@ * nop stub, which must not clobber anything *including the stack* to * avoid confusing the entry prologues. */ -extern void _paravirt_nop(void); -asm (".pushsection .entry.text, \"ax\"\n" - ".global _paravirt_nop\n" - "_paravirt_nop:\n\t" - ASM_ENDBR - ASM_RET - ".size _paravirt_nop, . - _paravirt_nop\n\t" - ".type _paravirt_nop, @function\n\t" - ".popsection"); +DEFINE_PARAVIRT_ASM(_paravirt_nop, "", .entry.text); /* stub always returning 0. */ -asm (".pushsection .entry.text, \"ax\"\n" - ".global paravirt_ret0\n" - "paravirt_ret0:\n\t" - ASM_ENDBR - "xor %" _ASM_AX ", %" _ASM_AX ";\n\t" - ASM_RET - ".size paravirt_ret0, . - paravirt_ret0\n\t" - ".type paravirt_ret0, @function\n\t" - ".popsection"); - +DEFINE_PARAVIRT_ASM(paravirt_ret0, "xor %eax,%eax", .entry.text); void __init default_banner(void) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index c21b7347a26d..40d156a31676 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -600,7 +600,7 @@ static __always_inline void __speculation_ctrl_update(unsigned long tifp, } if (updmsr) - write_spec_ctrl_current(msr, false); + update_spec_ctrl_cond(msr); } static unsigned long speculation_ctrl_update_tif(struct task_struct *tsk) @@ -965,7 +965,7 @@ early_param("idle", idle_setup); unsigned long arch_align_stack(unsigned long sp) { if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) - sp -= prandom_u32_max(8192); + sp -= get_random_u32_below(8192); return sp & ~0xf; } diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 2f314b170c9f..470c128759ea 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -191,13 +191,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) arch_end_context_switch(next_p); /* - * Reload esp0 and cpu_current_top_of_stack. This changes + * Reload esp0 and pcpu_hot.top_of_stack. This changes * current_thread_info(). Refresh the SYSENTER configuration in * case prev or next is vm86. */ update_task_stack(next_p); refresh_sysenter_cs(next); - this_cpu_write(cpu_current_top_of_stack, + this_cpu_write(pcpu_hot.top_of_stack, (unsigned long)task_stack_page(next_p) + THREAD_SIZE); @@ -207,7 +207,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) if (prev->gs | next->gs) loadsegment(gs, next->gs); - this_cpu_write(current_task, next_p); + raw_cpu_write(pcpu_hot.current_task, next_p); switch_fpu_finish(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 6b3418bff326..4e34b3b68ebd 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -165,7 +165,7 @@ static noinstr unsigned long __rdgsbase_inactive(void) lockdep_assert_irqs_disabled(); - if (!static_cpu_has(X86_FEATURE_XENPV)) { + if (!cpu_feature_enabled(X86_FEATURE_XENPV)) { native_swapgs(); gsbase = rdgsbase(); native_swapgs(); @@ -190,7 +190,7 @@ static noinstr void __wrgsbase_inactive(unsigned long gsbase) { lockdep_assert_irqs_disabled(); - if (!static_cpu_has(X86_FEATURE_XENPV)) { + if (!cpu_feature_enabled(X86_FEATURE_XENPV)) { native_swapgs(); wrgsbase(gsbase); native_swapgs(); @@ -563,7 +563,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) int cpu = smp_processor_id(); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && - this_cpu_read(hardirq_stack_inuse)); + this_cpu_read(pcpu_hot.hardirq_stack_inuse)); if (!test_thread_flag(TIF_NEED_FPU_LOAD)) switch_fpu_prepare(prev_fpu, cpu); @@ -617,8 +617,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) /* * Switch the PDA and FPU contexts. */ - this_cpu_write(current_task, next_p); - this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p)); + raw_cpu_write(pcpu_hot.current_task, next_p); + raw_cpu_write(pcpu_hot.top_of_stack, task_top_of_stack(next_p)); switch_fpu_finish(); diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c index 37c12fb92906..dfaa270a7cc9 100644 --- a/arch/x86/kernel/ptrace.c +++ b/arch/x86/kernel/ptrace.c @@ -44,16 +44,35 @@ #include "tls.h" -enum x86_regset { - REGSET_GENERAL, - REGSET_FP, - REGSET_XFP, - REGSET_IOPERM64 = REGSET_XFP, - REGSET_XSTATE, - REGSET_TLS, - REGSET_IOPERM32, +enum x86_regset_32 { + REGSET32_GENERAL, + REGSET32_FP, + REGSET32_XFP, + REGSET32_XSTATE, + REGSET32_TLS, + REGSET32_IOPERM, }; +enum x86_regset_64 { + REGSET64_GENERAL, + REGSET64_FP, + REGSET64_IOPERM, + REGSET64_XSTATE, +}; + +#define REGSET_GENERAL \ +({ \ + BUILD_BUG_ON((int)REGSET32_GENERAL != (int)REGSET64_GENERAL); \ + REGSET32_GENERAL; \ +}) + +#define REGSET_FP \ +({ \ + BUILD_BUG_ON((int)REGSET32_FP != (int)REGSET64_FP); \ + REGSET32_FP; \ +}) + + struct pt_regs_offset { const char *name; int offset; @@ -788,13 +807,13 @@ long arch_ptrace(struct task_struct *child, long request, #ifdef CONFIG_X86_32 case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ return copy_regset_to_user(child, &user_x86_32_view, - REGSET_XFP, + REGSET32_XFP, 0, sizeof(struct user_fxsr_struct), datap) ? -EIO : 0; case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ return copy_regset_from_user(child, &user_x86_32_view, - REGSET_XFP, + REGSET32_XFP, 0, sizeof(struct user_fxsr_struct), datap) ? -EIO : 0; #endif @@ -1086,13 +1105,13 @@ static long ia32_arch_ptrace(struct task_struct *child, compat_long_t request, case PTRACE_GETFPXREGS: /* Get the child extended FPU state. */ return copy_regset_to_user(child, &user_x86_32_view, - REGSET_XFP, 0, + REGSET32_XFP, 0, sizeof(struct user32_fxsr_struct), datap); case PTRACE_SETFPXREGS: /* Set the child extended FPU state. */ return copy_regset_from_user(child, &user_x86_32_view, - REGSET_XFP, 0, + REGSET32_XFP, 0, sizeof(struct user32_fxsr_struct), datap); @@ -1215,29 +1234,38 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, #ifdef CONFIG_X86_64 static struct user_regset x86_64_regsets[] __ro_after_init = { - [REGSET_GENERAL] = { - .core_note_type = NT_PRSTATUS, - .n = sizeof(struct user_regs_struct) / sizeof(long), - .size = sizeof(long), .align = sizeof(long), - .regset_get = genregs_get, .set = genregs_set + [REGSET64_GENERAL] = { + .core_note_type = NT_PRSTATUS, + .n = sizeof(struct user_regs_struct) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .regset_get = genregs_get, + .set = genregs_set }, - [REGSET_FP] = { - .core_note_type = NT_PRFPREG, - .n = sizeof(struct fxregs_state) / sizeof(long), - .size = sizeof(long), .align = sizeof(long), - .active = regset_xregset_fpregs_active, .regset_get = xfpregs_get, .set = xfpregs_set + [REGSET64_FP] = { + .core_note_type = NT_PRFPREG, + .n = sizeof(struct fxregs_state) / sizeof(long), + .size = sizeof(long), + .align = sizeof(long), + .active = regset_xregset_fpregs_active, + .regset_get = xfpregs_get, + .set = xfpregs_set }, - [REGSET_XSTATE] = { - .core_note_type = NT_X86_XSTATE, - .size = sizeof(u64), .align = sizeof(u64), - .active = xstateregs_active, .regset_get = xstateregs_get, - .set = xstateregs_set + [REGSET64_XSTATE] = { + .core_note_type = NT_X86_XSTATE, + .size = sizeof(u64), + .align = sizeof(u64), + .active = xstateregs_active, + .regset_get = xstateregs_get, + .set = xstateregs_set }, - [REGSET_IOPERM64] = { - .core_note_type = NT_386_IOPERM, - .n = IO_BITMAP_LONGS, - .size = sizeof(long), .align = sizeof(long), - .active = ioperm_active, .regset_get = ioperm_get + [REGSET64_IOPERM] = { + .core_note_type = NT_386_IOPERM, + .n = IO_BITMAP_LONGS, + .size = sizeof(long), + .align = sizeof(long), + .active = ioperm_active, + .regset_get = ioperm_get }, }; @@ -1256,43 +1284,57 @@ static const struct user_regset_view user_x86_64_view = { #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION static struct user_regset x86_32_regsets[] __ro_after_init = { - [REGSET_GENERAL] = { - .core_note_type = NT_PRSTATUS, - .n = sizeof(struct user_regs_struct32) / sizeof(u32), - .size = sizeof(u32), .align = sizeof(u32), - .regset_get = genregs32_get, .set = genregs32_set + [REGSET32_GENERAL] = { + .core_note_type = NT_PRSTATUS, + .n = sizeof(struct user_regs_struct32) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .regset_get = genregs32_get, + .set = genregs32_set }, - [REGSET_FP] = { - .core_note_type = NT_PRFPREG, - .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32), - .size = sizeof(u32), .align = sizeof(u32), - .active = regset_fpregs_active, .regset_get = fpregs_get, .set = fpregs_set + [REGSET32_FP] = { + .core_note_type = NT_PRFPREG, + .n = sizeof(struct user_i387_ia32_struct) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .active = regset_fpregs_active, + .regset_get = fpregs_get, + .set = fpregs_set }, - [REGSET_XFP] = { - .core_note_type = NT_PRXFPREG, - .n = sizeof(struct fxregs_state) / sizeof(u32), - .size = sizeof(u32), .align = sizeof(u32), - .active = regset_xregset_fpregs_active, .regset_get = xfpregs_get, .set = xfpregs_set + [REGSET32_XFP] = { + .core_note_type = NT_PRXFPREG, + .n = sizeof(struct fxregs_state) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .active = regset_xregset_fpregs_active, + .regset_get = xfpregs_get, + .set = xfpregs_set }, - [REGSET_XSTATE] = { - .core_note_type = NT_X86_XSTATE, - .size = sizeof(u64), .align = sizeof(u64), - .active = xstateregs_active, .regset_get = xstateregs_get, - .set = xstateregs_set + [REGSET32_XSTATE] = { + .core_note_type = NT_X86_XSTATE, + .size = sizeof(u64), + .align = sizeof(u64), + .active = xstateregs_active, + .regset_get = xstateregs_get, + .set = xstateregs_set }, - [REGSET_TLS] = { - .core_note_type = NT_386_TLS, - .n = GDT_ENTRY_TLS_ENTRIES, .bias = GDT_ENTRY_TLS_MIN, - .size = sizeof(struct user_desc), - .align = sizeof(struct user_desc), - .active = regset_tls_active, - .regset_get = regset_tls_get, .set = regset_tls_set + [REGSET32_TLS] = { + .core_note_type = NT_386_TLS, + .n = GDT_ENTRY_TLS_ENTRIES, + .bias = GDT_ENTRY_TLS_MIN, + .size = sizeof(struct user_desc), + .align = sizeof(struct user_desc), + .active = regset_tls_active, + .regset_get = regset_tls_get, + .set = regset_tls_set }, - [REGSET_IOPERM32] = { - .core_note_type = NT_386_IOPERM, - .n = IO_BITMAP_BYTES / sizeof(u32), - .size = sizeof(u32), .align = sizeof(u32), - .active = ioperm_active, .regset_get = ioperm_get + [REGSET32_IOPERM] = { + .core_note_type = NT_386_IOPERM, + .n = IO_BITMAP_BYTES / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .active = ioperm_active, + .regset_get = ioperm_get }, }; @@ -1311,10 +1353,10 @@ u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; void __init update_regset_xstate_info(unsigned int size, u64 xstate_mask) { #ifdef CONFIG_X86_64 - x86_64_regsets[REGSET_XSTATE].n = size / sizeof(u64); + x86_64_regsets[REGSET64_XSTATE].n = size / sizeof(u64); #endif #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION - x86_32_regsets[REGSET_XSTATE].n = size / sizeof(u64); + x86_32_regsets[REGSET32_XSTATE].n = size / sizeof(u64); #endif xstate_fx_sw_bytes[USER_XSTATE_XCR0_WORD] = xstate_mask; } diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S index 4809c0dc4eb0..4a73351f87f8 100644 --- a/arch/x86/kernel/relocate_kernel_64.S +++ b/arch/x86/kernel/relocate_kernel_64.S @@ -41,6 +41,7 @@ .text .align PAGE_SIZE .code64 +SYM_CODE_START_NOALIGN(relocate_range) SYM_CODE_START_NOALIGN(relocate_kernel) UNWIND_HINT_EMPTY ANNOTATE_NOENDBR @@ -312,5 +313,5 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages) int3 SYM_CODE_END(swap_pages) - .globl kexec_control_code_size -.set kexec_control_code_size, . - relocate_kernel + .skip KEXEC_CONTROL_CODE_MAX_SIZE - (. - relocate_kernel), 0xcc +SYM_CODE_END(relocate_range); diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c index bba1abd05bfe..79bc8a97a083 100644 --- a/arch/x86/kernel/resource.c +++ b/arch/x86/kernel/resource.c @@ -42,8 +42,16 @@ static void remove_e820_regions(struct resource *avail) resource_clip(avail, e820_start, e820_end); if (orig.start != avail->start || orig.end != avail->end) { - pr_info("clipped %pR to %pR for e820 entry [mem %#010Lx-%#010Lx]\n", - &orig, avail, e820_start, e820_end); + pr_info("resource: avoiding allocation from e820 entry [mem %#010Lx-%#010Lx]\n", + e820_start, e820_end); + if (avail->end > avail->start) + /* + * Use %pa instead of %pR because "avail" + * is typically IORESOURCE_UNSET, so %pR + * shows the size instead of addresses. + */ + pr_info("resource: remaining [mem %pa-%pa] available\n", + &avail->start, &avail->end); orig = *avail; } } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 216fee7144ee..88188549647c 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -31,9 +31,11 @@ #include <xen/xen.h> #include <asm/apic.h> +#include <asm/efi.h> #include <asm/numa.h> #include <asm/bios_ebda.h> #include <asm/bugs.h> +#include <asm/cacheinfo.h> #include <asm/cpu.h> #include <asm/efi.h> #include <asm/gart.h> @@ -1074,24 +1076,13 @@ void __init setup_arch(char **cmdline_p) max_pfn = e820__end_of_ram_pfn(); /* update e820 for memory not covered by WB MTRRs */ - if (IS_ENABLED(CONFIG_MTRR)) - mtrr_bp_init(); - else - pat_disable("PAT support disabled because CONFIG_MTRR is disabled in the kernel."); - + cache_bp_init(); if (mtrr_trim_uncached_memory(max_pfn)) max_pfn = e820__end_of_ram_pfn(); max_possible_pfn = max_pfn; /* - * This call is required when the CPU does not support PAT. If - * mtrr_bp_init() invoked it already via pat_init() the call has no - * effect. - */ - init_cache_modes(); - - /* * Define random base addresses for memory sections after max_pfn is * defined and before each memory section base is used. */ @@ -1175,7 +1166,7 @@ void __init setup_arch(char **cmdline_p) * Moreover, on machines with SandyBridge graphics or in setups that use * crashkernel the entire 1M is reserved anyway. */ - reserve_real_mode(); + x86_platform.realmode_reserve(); init_mem_mapping(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 49325caa7307..c242dc47e9cb 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -11,6 +11,7 @@ #include <linux/smp.h> #include <linux/topology.h> #include <linux/pfn.h> +#include <linux/stackprotector.h> #include <asm/sections.h> #include <asm/processor.h> #include <asm/desc.h> @@ -21,10 +22,6 @@ #include <asm/proto.h> #include <asm/cpumask.h> #include <asm/cpu.h> -#include <asm/stackprotector.h> - -DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number); -EXPORT_PER_CPU_SYMBOL(cpu_number); #ifdef CONFIG_X86_64 #define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load) @@ -172,7 +169,7 @@ void __init setup_per_cpu_areas(void) for_each_possible_cpu(cpu) { per_cpu_offset(cpu) = delta + pcpu_unit_offsets[cpu]; per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu); - per_cpu(cpu_number, cpu) = cpu; + per_cpu(pcpu_hot.cpu_number, cpu) = cpu; setup_percpu_segment(cpu); /* * Copy data used in early init routines from the @@ -211,7 +208,7 @@ void __init setup_per_cpu_areas(void) * area. Reload any changed state for the boot CPU. */ if (!cpu) - switch_to_new_gdt(cpu); + switch_gdt_and_percpu_base(cpu); } /* indicate the early static arrays will soon be gone */ diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 9c7265b524c7..1504eb8d25aa 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -37,180 +37,27 @@ #include <asm/sighandling.h> #include <asm/vm86.h> -#ifdef CONFIG_X86_64 -#include <linux/compat.h> -#include <asm/proto.h> -#include <asm/ia32_unistd.h> -#include <asm/fpu/xstate.h> -#endif /* CONFIG_X86_64 */ - #include <asm/syscall.h> #include <asm/sigframe.h> #include <asm/signal.h> -#ifdef CONFIG_X86_64 -/* - * If regs->ss will cause an IRET fault, change it. Otherwise leave it - * alone. Using this generally makes no sense unless - * user_64bit_mode(regs) would return true. - */ -static void force_valid_ss(struct pt_regs *regs) +static inline int is_ia32_compat_frame(struct ksignal *ksig) { - u32 ar; - asm volatile ("lar %[old_ss], %[ar]\n\t" - "jz 1f\n\t" /* If invalid: */ - "xorl %[ar], %[ar]\n\t" /* set ar = 0 */ - "1:" - : [ar] "=r" (ar) - : [old_ss] "rm" ((u16)regs->ss)); - - /* - * For a valid 64-bit user context, we need DPL 3, type - * read-write data or read-write exp-down data, and S and P - * set. We can't use VERW because VERW doesn't check the - * P bit. - */ - ar &= AR_DPL_MASK | AR_S | AR_P | AR_TYPE_MASK; - if (ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA) && - ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN)) - regs->ss = __USER_DS; + return IS_ENABLED(CONFIG_IA32_EMULATION) && + ksig->ka.sa.sa_flags & SA_IA32_ABI; } -# define CONTEXT_COPY_SIZE offsetof(struct sigcontext, reserved1) -#else -# define CONTEXT_COPY_SIZE sizeof(struct sigcontext) -#endif -static bool restore_sigcontext(struct pt_regs *regs, - struct sigcontext __user *usc, - unsigned long uc_flags) +static inline int is_ia32_frame(struct ksignal *ksig) { - struct sigcontext sc; - - /* Always make any pending restarted system calls return -EINTR */ - current->restart_block.fn = do_no_restart_syscall; - - if (copy_from_user(&sc, usc, CONTEXT_COPY_SIZE)) - return false; - -#ifdef CONFIG_X86_32 - loadsegment(gs, sc.gs); - regs->fs = sc.fs; - regs->es = sc.es; - regs->ds = sc.ds; -#endif /* CONFIG_X86_32 */ - - regs->bx = sc.bx; - regs->cx = sc.cx; - regs->dx = sc.dx; - regs->si = sc.si; - regs->di = sc.di; - regs->bp = sc.bp; - regs->ax = sc.ax; - regs->sp = sc.sp; - regs->ip = sc.ip; - -#ifdef CONFIG_X86_64 - regs->r8 = sc.r8; - regs->r9 = sc.r9; - regs->r10 = sc.r10; - regs->r11 = sc.r11; - regs->r12 = sc.r12; - regs->r13 = sc.r13; - regs->r14 = sc.r14; - regs->r15 = sc.r15; -#endif /* CONFIG_X86_64 */ - - /* Get CS/SS and force CPL3 */ - regs->cs = sc.cs | 0x03; - regs->ss = sc.ss | 0x03; - - regs->flags = (regs->flags & ~FIX_EFLAGS) | (sc.flags & FIX_EFLAGS); - /* disable syscall checks */ - regs->orig_ax = -1; - -#ifdef CONFIG_X86_64 - /* - * Fix up SS if needed for the benefit of old DOSEMU and - * CRIU. - */ - if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs))) - force_valid_ss(regs); -#endif - - return fpu__restore_sig((void __user *)sc.fpstate, - IS_ENABLED(CONFIG_X86_32)); + return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(ksig); } -static __always_inline int -__unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, - struct pt_regs *regs, unsigned long mask) +static inline int is_x32_frame(struct ksignal *ksig) { -#ifdef CONFIG_X86_32 - unsigned int gs; - savesegment(gs, gs); - - unsafe_put_user(gs, (unsigned int __user *)&sc->gs, Efault); - unsafe_put_user(regs->fs, (unsigned int __user *)&sc->fs, Efault); - unsafe_put_user(regs->es, (unsigned int __user *)&sc->es, Efault); - unsafe_put_user(regs->ds, (unsigned int __user *)&sc->ds, Efault); -#endif /* CONFIG_X86_32 */ - - unsafe_put_user(regs->di, &sc->di, Efault); - unsafe_put_user(regs->si, &sc->si, Efault); - unsafe_put_user(regs->bp, &sc->bp, Efault); - unsafe_put_user(regs->sp, &sc->sp, Efault); - unsafe_put_user(regs->bx, &sc->bx, Efault); - unsafe_put_user(regs->dx, &sc->dx, Efault); - unsafe_put_user(regs->cx, &sc->cx, Efault); - unsafe_put_user(regs->ax, &sc->ax, Efault); -#ifdef CONFIG_X86_64 - unsafe_put_user(regs->r8, &sc->r8, Efault); - unsafe_put_user(regs->r9, &sc->r9, Efault); - unsafe_put_user(regs->r10, &sc->r10, Efault); - unsafe_put_user(regs->r11, &sc->r11, Efault); - unsafe_put_user(regs->r12, &sc->r12, Efault); - unsafe_put_user(regs->r13, &sc->r13, Efault); - unsafe_put_user(regs->r14, &sc->r14, Efault); - unsafe_put_user(regs->r15, &sc->r15, Efault); -#endif /* CONFIG_X86_64 */ - - unsafe_put_user(current->thread.trap_nr, &sc->trapno, Efault); - unsafe_put_user(current->thread.error_code, &sc->err, Efault); - unsafe_put_user(regs->ip, &sc->ip, Efault); -#ifdef CONFIG_X86_32 - unsafe_put_user(regs->cs, (unsigned int __user *)&sc->cs, Efault); - unsafe_put_user(regs->flags, &sc->flags, Efault); - unsafe_put_user(regs->sp, &sc->sp_at_signal, Efault); - unsafe_put_user(regs->ss, (unsigned int __user *)&sc->ss, Efault); -#else /* !CONFIG_X86_32 */ - unsafe_put_user(regs->flags, &sc->flags, Efault); - unsafe_put_user(regs->cs, &sc->cs, Efault); - unsafe_put_user(0, &sc->gs, Efault); - unsafe_put_user(0, &sc->fs, Efault); - unsafe_put_user(regs->ss, &sc->ss, Efault); -#endif /* CONFIG_X86_32 */ - - unsafe_put_user(fpstate, (unsigned long __user *)&sc->fpstate, Efault); - - /* non-iBCS2 extensions.. */ - unsafe_put_user(mask, &sc->oldmask, Efault); - unsafe_put_user(current->thread.cr2, &sc->cr2, Efault); - return 0; -Efault: - return -EFAULT; + return IS_ENABLED(CONFIG_X86_X32_ABI) && + ksig->ka.sa.sa_flags & SA_X32_ABI; } -#define unsafe_put_sigcontext(sc, fp, regs, set, label) \ -do { \ - if (__unsafe_setup_sigcontext(sc, fp, regs, set->sig[0])) \ - goto label; \ -} while(0); - -#define unsafe_put_sigmask(set, frame, label) \ - unsafe_put_user(*(__u64 *)(set), \ - (__u64 __user *)&(frame)->uc.uc_sigmask, \ - label) - /* * Set up a signal frame. */ @@ -223,24 +70,12 @@ do { \ /* * Determine which stack to use.. */ -static unsigned long align_sigframe(unsigned long sp) -{ -#ifdef CONFIG_X86_32 - /* - * Align the stack pointer according to the i386 ABI, - * i.e. so that on function entry ((sp + 4) & 15) == 0. - */ - sp = ((sp + 4) & -FRAME_ALIGNMENT) - 4; -#else /* !CONFIG_X86_32 */ - sp = round_down(sp, FRAME_ALIGNMENT) - 8; -#endif - return sp; -} - -static void __user * -get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, +void __user * +get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size, void __user **fpstate) { + struct k_sigaction *ka = &ksig->ka; + int ia32_frame = is_ia32_frame(ksig); /* Default to using normal stack */ bool nested_altstack = on_sig_stack(regs->sp); bool entering_altstack = false; @@ -249,7 +84,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, unsigned long buf_fx = 0; /* redzone */ - if (IS_ENABLED(CONFIG_X86_64)) + if (!ia32_frame) sp -= 128; /* This is the X/Open sanctioned signal stack switching. */ @@ -263,7 +98,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, sp = current->sas_ss_sp + current->sas_ss_size; entering_altstack = true; } - } else if (IS_ENABLED(CONFIG_X86_32) && + } else if (ia32_frame && !nested_altstack && regs->ss != __USER_DS && !(ka->sa.sa_flags & SA_RESTORER) && @@ -273,11 +108,19 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, entering_altstack = true; } - sp = fpu__alloc_mathframe(sp, IS_ENABLED(CONFIG_X86_32), - &buf_fx, &math_size); + sp = fpu__alloc_mathframe(sp, ia32_frame, &buf_fx, &math_size); *fpstate = (void __user *)sp; - sp = align_sigframe(sp - frame_size); + sp -= frame_size; + + if (ia32_frame) + /* + * Align the stack pointer according to the i386 ABI, + * i.e. so that on function entry ((sp + 4) & 15) == 0. + */ + sp = ((sp + 4) & -FRAME_ALIGNMENT) - 4; + else + sp = round_down(sp, FRAME_ALIGNMENT) - 8; /* * If we are on the alternate signal stack and would overflow it, don't. @@ -300,391 +143,6 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size, return (void __user *)sp; } -#ifdef CONFIG_X86_32 -static const struct { - u16 poplmovl; - u32 val; - u16 int80; -} __attribute__((packed)) retcode = { - 0xb858, /* popl %eax; movl $..., %eax */ - __NR_sigreturn, - 0x80cd, /* int $0x80 */ -}; - -static const struct { - u8 movl; - u32 val; - u16 int80; - u8 pad; -} __attribute__((packed)) rt_retcode = { - 0xb8, /* movl $..., %eax */ - __NR_rt_sigreturn, - 0x80cd, /* int $0x80 */ - 0 -}; - -static int -__setup_frame(int sig, struct ksignal *ksig, sigset_t *set, - struct pt_regs *regs) -{ - struct sigframe __user *frame; - void __user *restorer; - void __user *fp = NULL; - - frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp); - - if (!user_access_begin(frame, sizeof(*frame))) - return -EFAULT; - - unsafe_put_user(sig, &frame->sig, Efault); - unsafe_put_sigcontext(&frame->sc, fp, regs, set, Efault); - unsafe_put_user(set->sig[1], &frame->extramask[0], Efault); - if (current->mm->context.vdso) - restorer = current->mm->context.vdso + - vdso_image_32.sym___kernel_sigreturn; - else - restorer = &frame->retcode; - if (ksig->ka.sa.sa_flags & SA_RESTORER) - restorer = ksig->ka.sa.sa_restorer; - - /* Set up to return from userspace. */ - unsafe_put_user(restorer, &frame->pretcode, Efault); - - /* - * This is popl %eax ; movl $__NR_sigreturn, %eax ; int $0x80 - * - * WE DO NOT USE IT ANY MORE! It's only left here for historical - * reasons and because gdb uses it as a signature to notice - * signal handler stack frames. - */ - unsafe_put_user(*((u64 *)&retcode), (u64 *)frame->retcode, Efault); - user_access_end(); - - /* Set up registers for signal handler */ - regs->sp = (unsigned long)frame; - regs->ip = (unsigned long)ksig->ka.sa.sa_handler; - regs->ax = (unsigned long)sig; - regs->dx = 0; - regs->cx = 0; - - regs->ds = __USER_DS; - regs->es = __USER_DS; - regs->ss = __USER_DS; - regs->cs = __USER_CS; - - return 0; - -Efault: - user_access_end(); - return -EFAULT; -} - -static int __setup_rt_frame(int sig, struct ksignal *ksig, - sigset_t *set, struct pt_regs *regs) -{ - struct rt_sigframe __user *frame; - void __user *restorer; - void __user *fp = NULL; - - frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp); - - if (!user_access_begin(frame, sizeof(*frame))) - return -EFAULT; - - unsafe_put_user(sig, &frame->sig, Efault); - unsafe_put_user(&frame->info, &frame->pinfo, Efault); - unsafe_put_user(&frame->uc, &frame->puc, Efault); - - /* Create the ucontext. */ - if (static_cpu_has(X86_FEATURE_XSAVE)) - unsafe_put_user(UC_FP_XSTATE, &frame->uc.uc_flags, Efault); - else - unsafe_put_user(0, &frame->uc.uc_flags, Efault); - unsafe_put_user(0, &frame->uc.uc_link, Efault); - unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); - - /* Set up to return from userspace. */ - restorer = current->mm->context.vdso + - vdso_image_32.sym___kernel_rt_sigreturn; - if (ksig->ka.sa.sa_flags & SA_RESTORER) - restorer = ksig->ka.sa.sa_restorer; - unsafe_put_user(restorer, &frame->pretcode, Efault); - - /* - * This is movl $__NR_rt_sigreturn, %ax ; int $0x80 - * - * WE DO NOT USE IT ANY MORE! It's only left here for historical - * reasons and because gdb uses it as a signature to notice - * signal handler stack frames. - */ - unsafe_put_user(*((u64 *)&rt_retcode), (u64 *)frame->retcode, Efault); - unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); - unsafe_put_sigmask(set, frame, Efault); - user_access_end(); - - if (copy_siginfo_to_user(&frame->info, &ksig->info)) - return -EFAULT; - - /* Set up registers for signal handler */ - regs->sp = (unsigned long)frame; - regs->ip = (unsigned long)ksig->ka.sa.sa_handler; - regs->ax = (unsigned long)sig; - regs->dx = (unsigned long)&frame->info; - regs->cx = (unsigned long)&frame->uc; - - regs->ds = __USER_DS; - regs->es = __USER_DS; - regs->ss = __USER_DS; - regs->cs = __USER_CS; - - return 0; -Efault: - user_access_end(); - return -EFAULT; -} -#else /* !CONFIG_X86_32 */ -static unsigned long frame_uc_flags(struct pt_regs *regs) -{ - unsigned long flags; - - if (boot_cpu_has(X86_FEATURE_XSAVE)) - flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS; - else - flags = UC_SIGCONTEXT_SS; - - if (likely(user_64bit_mode(regs))) - flags |= UC_STRICT_RESTORE_SS; - - return flags; -} - -static int __setup_rt_frame(int sig, struct ksignal *ksig, - sigset_t *set, struct pt_regs *regs) -{ - struct rt_sigframe __user *frame; - void __user *fp = NULL; - unsigned long uc_flags; - - /* x86-64 should always use SA_RESTORER. */ - if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) - return -EFAULT; - - frame = get_sigframe(&ksig->ka, regs, sizeof(struct rt_sigframe), &fp); - uc_flags = frame_uc_flags(regs); - - if (!user_access_begin(frame, sizeof(*frame))) - return -EFAULT; - - /* Create the ucontext. */ - unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); - unsafe_put_user(0, &frame->uc.uc_link, Efault); - unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); - - /* Set up to return from userspace. If provided, use a stub - already in userspace. */ - unsafe_put_user(ksig->ka.sa.sa_restorer, &frame->pretcode, Efault); - unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); - unsafe_put_sigmask(set, frame, Efault); - user_access_end(); - - if (ksig->ka.sa.sa_flags & SA_SIGINFO) { - if (copy_siginfo_to_user(&frame->info, &ksig->info)) - return -EFAULT; - } - - /* Set up registers for signal handler */ - regs->di = sig; - /* In case the signal handler was declared without prototypes */ - regs->ax = 0; - - /* This also works for non SA_SIGINFO handlers because they expect the - next argument after the signal number on the stack. */ - regs->si = (unsigned long)&frame->info; - regs->dx = (unsigned long)&frame->uc; - regs->ip = (unsigned long) ksig->ka.sa.sa_handler; - - regs->sp = (unsigned long)frame; - - /* - * Set up the CS and SS registers to run signal handlers in - * 64-bit mode, even if the handler happens to be interrupting - * 32-bit or 16-bit code. - * - * SS is subtle. In 64-bit mode, we don't need any particular - * SS descriptor, but we do need SS to be valid. It's possible - * that the old SS is entirely bogus -- this can happen if the - * signal we're trying to deliver is #GP or #SS caused by a bad - * SS value. We also have a compatibility issue here: DOSEMU - * relies on the contents of the SS register indicating the - * SS value at the time of the signal, even though that code in - * DOSEMU predates sigreturn's ability to restore SS. (DOSEMU - * avoids relying on sigreturn to restore SS; instead it uses - * a trampoline.) So we do our best: if the old SS was valid, - * we keep it. Otherwise we replace it. - */ - regs->cs = __USER_CS; - - if (unlikely(regs->ss != __USER_DS)) - force_valid_ss(regs); - - return 0; - -Efault: - user_access_end(); - return -EFAULT; -} -#endif /* CONFIG_X86_32 */ - -#ifdef CONFIG_X86_X32_ABI -static int x32_copy_siginfo_to_user(struct compat_siginfo __user *to, - const struct kernel_siginfo *from) -{ - struct compat_siginfo new; - - copy_siginfo_to_external32(&new, from); - if (from->si_signo == SIGCHLD) { - new._sifields._sigchld_x32._utime = from->si_utime; - new._sifields._sigchld_x32._stime = from->si_stime; - } - if (copy_to_user(to, &new, sizeof(struct compat_siginfo))) - return -EFAULT; - return 0; -} - -int copy_siginfo_to_user32(struct compat_siginfo __user *to, - const struct kernel_siginfo *from) -{ - if (in_x32_syscall()) - return x32_copy_siginfo_to_user(to, from); - return __copy_siginfo_to_user32(to, from); -} -#endif /* CONFIG_X86_X32_ABI */ - -static int x32_setup_rt_frame(struct ksignal *ksig, - compat_sigset_t *set, - struct pt_regs *regs) -{ -#ifdef CONFIG_X86_X32_ABI - struct rt_sigframe_x32 __user *frame; - unsigned long uc_flags; - void __user *restorer; - void __user *fp = NULL; - - if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) - return -EFAULT; - - frame = get_sigframe(&ksig->ka, regs, sizeof(*frame), &fp); - - uc_flags = frame_uc_flags(regs); - - if (!user_access_begin(frame, sizeof(*frame))) - return -EFAULT; - - /* Create the ucontext. */ - unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); - unsafe_put_user(0, &frame->uc.uc_link, Efault); - unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); - unsafe_put_user(0, &frame->uc.uc__pad0, Efault); - restorer = ksig->ka.sa.sa_restorer; - unsafe_put_user(restorer, (unsigned long __user *)&frame->pretcode, Efault); - unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); - unsafe_put_sigmask(set, frame, Efault); - user_access_end(); - - if (ksig->ka.sa.sa_flags & SA_SIGINFO) { - if (x32_copy_siginfo_to_user(&frame->info, &ksig->info)) - return -EFAULT; - } - - /* Set up registers for signal handler */ - regs->sp = (unsigned long) frame; - regs->ip = (unsigned long) ksig->ka.sa.sa_handler; - - /* We use the x32 calling convention here... */ - regs->di = ksig->sig; - regs->si = (unsigned long) &frame->info; - regs->dx = (unsigned long) &frame->uc; - - loadsegment(ds, __USER_DS); - loadsegment(es, __USER_DS); - - regs->cs = __USER_CS; - regs->ss = __USER_DS; -#endif /* CONFIG_X86_X32_ABI */ - - return 0; -#ifdef CONFIG_X86_X32_ABI -Efault: - user_access_end(); - return -EFAULT; -#endif -} - -/* - * Do a signal return; undo the signal stack. - */ -#ifdef CONFIG_X86_32 -SYSCALL_DEFINE0(sigreturn) -{ - struct pt_regs *regs = current_pt_regs(); - struct sigframe __user *frame; - sigset_t set; - - frame = (struct sigframe __user *)(regs->sp - 8); - - if (!access_ok(frame, sizeof(*frame))) - goto badframe; - if (__get_user(set.sig[0], &frame->sc.oldmask) || - __get_user(set.sig[1], &frame->extramask[0])) - goto badframe; - - set_current_blocked(&set); - - /* - * x86_32 has no uc_flags bits relevant to restore_sigcontext. - * Save a few cycles by skipping the __get_user. - */ - if (!restore_sigcontext(regs, &frame->sc, 0)) - goto badframe; - return regs->ax; - -badframe: - signal_fault(regs, frame, "sigreturn"); - - return 0; -} -#endif /* CONFIG_X86_32 */ - -SYSCALL_DEFINE0(rt_sigreturn) -{ - struct pt_regs *regs = current_pt_regs(); - struct rt_sigframe __user *frame; - sigset_t set; - unsigned long uc_flags; - - frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long)); - if (!access_ok(frame, sizeof(*frame))) - goto badframe; - if (__get_user(*(__u64 *)&set, (__u64 __user *)&frame->uc.uc_sigmask)) - goto badframe; - if (__get_user(uc_flags, &frame->uc.uc_flags)) - goto badframe; - - set_current_blocked(&set); - - if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) - goto badframe; - - if (restore_altstack(&frame->uc.uc_stack)) - goto badframe; - - return regs->ax; - -badframe: - signal_fault(regs, frame, "rt_sigreturn"); - return 0; -} - /* * There are four different struct types for signal frame: sigframe_ia32, * rt_sigframe_ia32, rt_sigframe_x32, and rt_sigframe. Use the worst case @@ -743,43 +201,22 @@ unsigned long get_sigframe_size(void) return max_frame_size; } -static inline int is_ia32_compat_frame(struct ksignal *ksig) -{ - return IS_ENABLED(CONFIG_IA32_EMULATION) && - ksig->ka.sa.sa_flags & SA_IA32_ABI; -} - -static inline int is_ia32_frame(struct ksignal *ksig) -{ - return IS_ENABLED(CONFIG_X86_32) || is_ia32_compat_frame(ksig); -} - -static inline int is_x32_frame(struct ksignal *ksig) -{ - return IS_ENABLED(CONFIG_X86_X32_ABI) && - ksig->ka.sa.sa_flags & SA_X32_ABI; -} - static int setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { - int usig = ksig->sig; - sigset_t *set = sigmask_to_save(); - compat_sigset_t *cset = (compat_sigset_t *) set; - /* Perform fixup for the pre-signal frame. */ rseq_signal_deliver(ksig, regs); /* Set up the stack frame */ if (is_ia32_frame(ksig)) { if (ksig->ka.sa.sa_flags & SA_SIGINFO) - return ia32_setup_rt_frame(usig, ksig, cset, regs); + return ia32_setup_rt_frame(ksig, regs); else - return ia32_setup_frame(usig, ksig, cset, regs); + return ia32_setup_frame(ksig, regs); } else if (is_x32_frame(ksig)) { - return x32_setup_rt_frame(ksig, cset, regs); + return x32_setup_rt_frame(ksig, regs); } else { - return __setup_rt_frame(ksig->sig, ksig, set, regs); + return x64_setup_rt_frame(ksig, regs); } } @@ -969,36 +406,3 @@ bool sigaltstack_size_valid(size_t ss_size) return true; } #endif /* CONFIG_DYNAMIC_SIGFRAME */ - -#ifdef CONFIG_X86_X32_ABI -COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn) -{ - struct pt_regs *regs = current_pt_regs(); - struct rt_sigframe_x32 __user *frame; - sigset_t set; - unsigned long uc_flags; - - frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); - - if (!access_ok(frame, sizeof(*frame))) - goto badframe; - if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask)) - goto badframe; - if (__get_user(uc_flags, &frame->uc.uc_flags)) - goto badframe; - - set_current_blocked(&set); - - if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) - goto badframe; - - if (compat_restore_altstack(&frame->uc.uc_stack)) - goto badframe; - - return regs->ax; - -badframe: - signal_fault(regs, frame, "x32 rt_sigreturn"); - return 0; -} -#endif diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/kernel/signal_32.c index c9c3859322fa..2553136cf39b 100644 --- a/arch/x86/ia32/ia32_signal.c +++ b/arch/x86/kernel/signal_32.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 /* - * linux/arch/x86_64/ia32/ia32_signal.c - * * Copyright (C) 1991, 1992 Linus Torvalds * * 1997-11-28 Modified for POSIX.1b signals by Richard Henderson @@ -26,7 +24,6 @@ #include <linux/uaccess.h> #include <asm/fpu/signal.h> #include <asm/ptrace.h> -#include <asm/ia32_unistd.h> #include <asm/user32.h> #include <uapi/asm/sigcontext.h> #include <asm/proto.h> @@ -35,6 +32,9 @@ #include <asm/sighandling.h> #include <asm/smap.h> +#ifdef CONFIG_IA32_EMULATION +#include <asm/ia32_unistd.h> + static inline void reload_segments(struct sigcontext_32 *sc) { unsigned int cur; @@ -53,6 +53,21 @@ static inline void reload_segments(struct sigcontext_32 *sc) loadsegment(es, sc->es | 0x03); } +#define sigset32_t compat_sigset_t +#define restore_altstack32 compat_restore_altstack +#define unsafe_save_altstack32 unsafe_compat_save_altstack + +#else + +#define sigset32_t sigset_t +#define __NR_ia32_sigreturn __NR_sigreturn +#define __NR_ia32_rt_sigreturn __NR_rt_sigreturn +#define restore_altstack32 restore_altstack +#define unsafe_save_altstack32 unsafe_save_altstack +#define __copy_siginfo_to_user32 copy_siginfo_to_user + +#endif + /* * Do a signal return; undo the signal stack. */ @@ -86,6 +101,7 @@ static bool ia32_restore_sigcontext(struct pt_regs *regs, /* disable syscall checks */ regs->orig_ax = -1; +#ifdef CONFIG_IA32_EMULATION /* * Reload fs and gs if they have changed in the signal * handler. This does not handle long fs/gs base changes in @@ -93,10 +109,17 @@ static bool ia32_restore_sigcontext(struct pt_regs *regs, * normal case. */ reload_segments(&sc); +#else + loadsegment(gs, sc.gs); + regs->fs = sc.fs; + regs->es = sc.es; + regs->ds = sc.ds; +#endif + return fpu__restore_sig(compat_ptr(sc.fpstate), 1); } -COMPAT_SYSCALL_DEFINE0(sigreturn) +SYSCALL32_DEFINE0(sigreturn) { struct pt_regs *regs = current_pt_regs(); struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8); @@ -119,7 +142,7 @@ badframe: return 0; } -COMPAT_SYSCALL_DEFINE0(rt_sigreturn) +SYSCALL32_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe_ia32 __user *frame; @@ -129,7 +152,7 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn) if (!access_ok(frame, sizeof(*frame))) goto badframe; - if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask)) + if (__get_user(*(__u64 *)&set, (__u64 __user *)&frame->uc.uc_sigmask)) goto badframe; set_current_blocked(&set); @@ -137,7 +160,7 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn) if (!ia32_restore_sigcontext(regs, &frame->uc.uc_mcontext)) goto badframe; - if (compat_restore_altstack(&frame->uc.uc_stack)) + if (restore_altstack32(&frame->uc.uc_stack)) goto badframe; return regs->ax; @@ -159,9 +182,15 @@ __unsafe_setup_sigcontext32(struct sigcontext_32 __user *sc, struct pt_regs *regs, unsigned int mask) { unsafe_put_user(get_user_seg(gs), (unsigned int __user *)&sc->gs, Efault); +#ifdef CONFIG_IA32_EMULATION unsafe_put_user(get_user_seg(fs), (unsigned int __user *)&sc->fs, Efault); unsafe_put_user(get_user_seg(ds), (unsigned int __user *)&sc->ds, Efault); unsafe_put_user(get_user_seg(es), (unsigned int __user *)&sc->es, Efault); +#else + unsafe_put_user(regs->fs, (unsigned int __user *)&sc->fs, Efault); + unsafe_put_user(regs->es, (unsigned int __user *)&sc->es, Efault); + unsafe_put_user(regs->ds, (unsigned int __user *)&sc->ds, Efault); +#endif unsafe_put_user(regs->di, &sc->di, Efault); unsafe_put_user(regs->si, &sc->si, Efault); @@ -196,43 +225,9 @@ do { \ goto label; \ } while(0) -/* - * Determine which stack to use.. - */ -static void __user *get_sigframe(struct ksignal *ksig, struct pt_regs *regs, - size_t frame_size, - void __user **fpstate) -{ - unsigned long sp, fx_aligned, math_size; - - /* Default to using normal stack */ - sp = regs->sp; - - /* This is the X/Open sanctioned signal stack switching. */ - if (ksig->ka.sa.sa_flags & SA_ONSTACK) - sp = sigsp(sp, ksig); - /* This is the legacy signal stack switching. */ - else if (regs->ss != __USER32_DS && - !(ksig->ka.sa.sa_flags & SA_RESTORER) && - ksig->ka.sa.sa_restorer) - sp = (unsigned long) ksig->ka.sa.sa_restorer; - - sp = fpu__alloc_mathframe(sp, 1, &fx_aligned, &math_size); - *fpstate = (struct _fpstate_32 __user *) sp; - if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)fx_aligned, - math_size)) - return (void __user *) -1L; - - sp -= frame_size; - /* Align the stack pointer according to the i386 ABI, - * i.e. so that on function entry ((sp + 4) & 15) == 0. */ - sp = ((sp + 4) & -16ul) - 4; - return (void __user *) sp; -} - -int ia32_setup_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs) +int ia32_setup_frame(struct ksignal *ksig, struct pt_regs *regs) { + sigset32_t *set = (sigset32_t *) sigmask_to_save(); struct sigframe_ia32 __user *frame; void __user *restorer; void __user *fp = NULL; @@ -264,7 +259,7 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; - unsafe_put_user(sig, &frame->sig, Efault); + unsafe_put_user(ksig->sig, &frame->sig, Efault); unsafe_put_sigcontext32(&frame->sc, fp, regs, set, Efault); unsafe_put_user(set->sig[1], &frame->extramask[0], Efault); unsafe_put_user(ptr_to_compat(restorer), &frame->pretcode, Efault); @@ -280,15 +275,20 @@ int ia32_setup_frame(int sig, struct ksignal *ksig, regs->ip = (unsigned long) ksig->ka.sa.sa_handler; /* Make -mregparm=3 work */ - regs->ax = sig; + regs->ax = ksig->sig; regs->dx = 0; regs->cx = 0; - loadsegment(ds, __USER32_DS); - loadsegment(es, __USER32_DS); +#ifdef CONFIG_IA32_EMULATION + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); +#else + regs->ds = __USER_DS; + regs->es = __USER_DS; +#endif regs->cs = __USER32_CS; - regs->ss = __USER32_DS; + regs->ss = __USER_DS; return 0; Efault: @@ -296,9 +296,9 @@ Efault: return -EFAULT; } -int ia32_setup_rt_frame(int sig, struct ksignal *ksig, - compat_sigset_t *set, struct pt_regs *regs) +int ia32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) { + sigset32_t *set = (sigset32_t *) sigmask_to_save(); struct rt_sigframe_ia32 __user *frame; void __user *restorer; void __user *fp = NULL; @@ -321,7 +321,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, if (!user_access_begin(frame, sizeof(*frame))) return -EFAULT; - unsafe_put_user(sig, &frame->sig, Efault); + unsafe_put_user(ksig->sig, &frame->sig, Efault); unsafe_put_user(ptr_to_compat(&frame->info), &frame->pinfo, Efault); unsafe_put_user(ptr_to_compat(&frame->uc), &frame->puc, Efault); @@ -331,7 +331,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, else unsafe_put_user(0, &frame->uc.uc_flags, Efault); unsafe_put_user(0, &frame->uc.uc_link, Efault); - unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); + unsafe_save_altstack32(&frame->uc.uc_stack, regs->sp, Efault); if (ksig->ka.sa.sa_flags & SA_RESTORER) restorer = ksig->ka.sa.sa_restorer; @@ -357,15 +357,20 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig, regs->ip = (unsigned long) ksig->ka.sa.sa_handler; /* Make -mregparm=3 work */ - regs->ax = sig; + regs->ax = ksig->sig; regs->dx = (unsigned long) &frame->info; regs->cx = (unsigned long) &frame->uc; - loadsegment(ds, __USER32_DS); - loadsegment(es, __USER32_DS); +#ifdef CONFIG_IA32_EMULATION + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); +#else + regs->ds = __USER_DS; + regs->es = __USER_DS; +#endif regs->cs = __USER32_CS; - regs->ss = __USER32_DS; + regs->ss = __USER_DS; return 0; Efault: diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c new file mode 100644 index 000000000000..ff9c55064223 --- /dev/null +++ b/arch/x86/kernel/signal_64.c @@ -0,0 +1,383 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen SuSE Labs + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/unistd.h> +#include <linux/uaccess.h> +#include <linux/syscalls.h> + +#include <asm/ucontext.h> +#include <asm/fpu/signal.h> +#include <asm/sighandling.h> + +#include <asm/syscall.h> +#include <asm/sigframe.h> +#include <asm/signal.h> + +/* + * If regs->ss will cause an IRET fault, change it. Otherwise leave it + * alone. Using this generally makes no sense unless + * user_64bit_mode(regs) would return true. + */ +static void force_valid_ss(struct pt_regs *regs) +{ + u32 ar; + asm volatile ("lar %[old_ss], %[ar]\n\t" + "jz 1f\n\t" /* If invalid: */ + "xorl %[ar], %[ar]\n\t" /* set ar = 0 */ + "1:" + : [ar] "=r" (ar) + : [old_ss] "rm" ((u16)regs->ss)); + + /* + * For a valid 64-bit user context, we need DPL 3, type + * read-write data or read-write exp-down data, and S and P + * set. We can't use VERW because VERW doesn't check the + * P bit. + */ + ar &= AR_DPL_MASK | AR_S | AR_P | AR_TYPE_MASK; + if (ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA) && + ar != (AR_DPL3 | AR_S | AR_P | AR_TYPE_RWDATA_EXPDOWN)) + regs->ss = __USER_DS; +} + +static bool restore_sigcontext(struct pt_regs *regs, + struct sigcontext __user *usc, + unsigned long uc_flags) +{ + struct sigcontext sc; + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; + + if (copy_from_user(&sc, usc, offsetof(struct sigcontext, reserved1))) + return false; + + regs->bx = sc.bx; + regs->cx = sc.cx; + regs->dx = sc.dx; + regs->si = sc.si; + regs->di = sc.di; + regs->bp = sc.bp; + regs->ax = sc.ax; + regs->sp = sc.sp; + regs->ip = sc.ip; + regs->r8 = sc.r8; + regs->r9 = sc.r9; + regs->r10 = sc.r10; + regs->r11 = sc.r11; + regs->r12 = sc.r12; + regs->r13 = sc.r13; + regs->r14 = sc.r14; + regs->r15 = sc.r15; + + /* Get CS/SS and force CPL3 */ + regs->cs = sc.cs | 0x03; + regs->ss = sc.ss | 0x03; + + regs->flags = (regs->flags & ~FIX_EFLAGS) | (sc.flags & FIX_EFLAGS); + /* disable syscall checks */ + regs->orig_ax = -1; + + /* + * Fix up SS if needed for the benefit of old DOSEMU and + * CRIU. + */ + if (unlikely(!(uc_flags & UC_STRICT_RESTORE_SS) && user_64bit_mode(regs))) + force_valid_ss(regs); + + return fpu__restore_sig((void __user *)sc.fpstate, 0); +} + +static __always_inline int +__unsafe_setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate, + struct pt_regs *regs, unsigned long mask) +{ + unsafe_put_user(regs->di, &sc->di, Efault); + unsafe_put_user(regs->si, &sc->si, Efault); + unsafe_put_user(regs->bp, &sc->bp, Efault); + unsafe_put_user(regs->sp, &sc->sp, Efault); + unsafe_put_user(regs->bx, &sc->bx, Efault); + unsafe_put_user(regs->dx, &sc->dx, Efault); + unsafe_put_user(regs->cx, &sc->cx, Efault); + unsafe_put_user(regs->ax, &sc->ax, Efault); + unsafe_put_user(regs->r8, &sc->r8, Efault); + unsafe_put_user(regs->r9, &sc->r9, Efault); + unsafe_put_user(regs->r10, &sc->r10, Efault); + unsafe_put_user(regs->r11, &sc->r11, Efault); + unsafe_put_user(regs->r12, &sc->r12, Efault); + unsafe_put_user(regs->r13, &sc->r13, Efault); + unsafe_put_user(regs->r14, &sc->r14, Efault); + unsafe_put_user(regs->r15, &sc->r15, Efault); + + unsafe_put_user(current->thread.trap_nr, &sc->trapno, Efault); + unsafe_put_user(current->thread.error_code, &sc->err, Efault); + unsafe_put_user(regs->ip, &sc->ip, Efault); + unsafe_put_user(regs->flags, &sc->flags, Efault); + unsafe_put_user(regs->cs, &sc->cs, Efault); + unsafe_put_user(0, &sc->gs, Efault); + unsafe_put_user(0, &sc->fs, Efault); + unsafe_put_user(regs->ss, &sc->ss, Efault); + + unsafe_put_user(fpstate, (unsigned long __user *)&sc->fpstate, Efault); + + /* non-iBCS2 extensions.. */ + unsafe_put_user(mask, &sc->oldmask, Efault); + unsafe_put_user(current->thread.cr2, &sc->cr2, Efault); + return 0; +Efault: + return -EFAULT; +} + +#define unsafe_put_sigcontext(sc, fp, regs, set, label) \ +do { \ + if (__unsafe_setup_sigcontext(sc, fp, regs, set->sig[0])) \ + goto label; \ +} while(0); + +#define unsafe_put_sigmask(set, frame, label) \ + unsafe_put_user(*(__u64 *)(set), \ + (__u64 __user *)&(frame)->uc.uc_sigmask, \ + label) + +static unsigned long frame_uc_flags(struct pt_regs *regs) +{ + unsigned long flags; + + if (boot_cpu_has(X86_FEATURE_XSAVE)) + flags = UC_FP_XSTATE | UC_SIGCONTEXT_SS; + else + flags = UC_SIGCONTEXT_SS; + + if (likely(user_64bit_mode(regs))) + flags |= UC_STRICT_RESTORE_SS; + + return flags; +} + +int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) +{ + sigset_t *set = sigmask_to_save(); + struct rt_sigframe __user *frame; + void __user *fp = NULL; + unsigned long uc_flags; + + /* x86-64 should always use SA_RESTORER. */ + if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) + return -EFAULT; + + frame = get_sigframe(ksig, regs, sizeof(struct rt_sigframe), &fp); + uc_flags = frame_uc_flags(regs); + + if (!user_access_begin(frame, sizeof(*frame))) + return -EFAULT; + + /* Create the ucontext. */ + unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); + unsafe_put_user(0, &frame->uc.uc_link, Efault); + unsafe_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); + + /* Set up to return from userspace. If provided, use a stub + already in userspace. */ + unsafe_put_user(ksig->ka.sa.sa_restorer, &frame->pretcode, Efault); + unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); + unsafe_put_sigmask(set, frame, Efault); + user_access_end(); + + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { + if (copy_siginfo_to_user(&frame->info, &ksig->info)) + return -EFAULT; + } + + /* Set up registers for signal handler */ + regs->di = ksig->sig; + /* In case the signal handler was declared without prototypes */ + regs->ax = 0; + + /* This also works for non SA_SIGINFO handlers because they expect the + next argument after the signal number on the stack. */ + regs->si = (unsigned long)&frame->info; + regs->dx = (unsigned long)&frame->uc; + regs->ip = (unsigned long) ksig->ka.sa.sa_handler; + + regs->sp = (unsigned long)frame; + + /* + * Set up the CS and SS registers to run signal handlers in + * 64-bit mode, even if the handler happens to be interrupting + * 32-bit or 16-bit code. + * + * SS is subtle. In 64-bit mode, we don't need any particular + * SS descriptor, but we do need SS to be valid. It's possible + * that the old SS is entirely bogus -- this can happen if the + * signal we're trying to deliver is #GP or #SS caused by a bad + * SS value. We also have a compatibility issue here: DOSEMU + * relies on the contents of the SS register indicating the + * SS value at the time of the signal, even though that code in + * DOSEMU predates sigreturn's ability to restore SS. (DOSEMU + * avoids relying on sigreturn to restore SS; instead it uses + * a trampoline.) So we do our best: if the old SS was valid, + * we keep it. Otherwise we replace it. + */ + regs->cs = __USER_CS; + + if (unlikely(regs->ss != __USER_DS)) + force_valid_ss(regs); + + return 0; + +Efault: + user_access_end(); + return -EFAULT; +} + +/* + * Do a signal return; undo the signal stack. + */ +SYSCALL_DEFINE0(rt_sigreturn) +{ + struct pt_regs *regs = current_pt_regs(); + struct rt_sigframe __user *frame; + sigset_t set; + unsigned long uc_flags; + + frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long)); + if (!access_ok(frame, sizeof(*frame))) + goto badframe; + if (__get_user(*(__u64 *)&set, (__u64 __user *)&frame->uc.uc_sigmask)) + goto badframe; + if (__get_user(uc_flags, &frame->uc.uc_flags)) + goto badframe; + + set_current_blocked(&set); + + if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) + goto badframe; + + if (restore_altstack(&frame->uc.uc_stack)) + goto badframe; + + return regs->ax; + +badframe: + signal_fault(regs, frame, "rt_sigreturn"); + return 0; +} + +#ifdef CONFIG_X86_X32_ABI +static int x32_copy_siginfo_to_user(struct compat_siginfo __user *to, + const struct kernel_siginfo *from) +{ + struct compat_siginfo new; + + copy_siginfo_to_external32(&new, from); + if (from->si_signo == SIGCHLD) { + new._sifields._sigchld_x32._utime = from->si_utime; + new._sifields._sigchld_x32._stime = from->si_stime; + } + if (copy_to_user(to, &new, sizeof(struct compat_siginfo))) + return -EFAULT; + return 0; +} + +int copy_siginfo_to_user32(struct compat_siginfo __user *to, + const struct kernel_siginfo *from) +{ + if (in_x32_syscall()) + return x32_copy_siginfo_to_user(to, from); + return __copy_siginfo_to_user32(to, from); +} + +int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs) +{ + compat_sigset_t *set = (compat_sigset_t *) sigmask_to_save(); + struct rt_sigframe_x32 __user *frame; + unsigned long uc_flags; + void __user *restorer; + void __user *fp = NULL; + + if (!(ksig->ka.sa.sa_flags & SA_RESTORER)) + return -EFAULT; + + frame = get_sigframe(ksig, regs, sizeof(*frame), &fp); + + uc_flags = frame_uc_flags(regs); + + if (!user_access_begin(frame, sizeof(*frame))) + return -EFAULT; + + /* Create the ucontext. */ + unsafe_put_user(uc_flags, &frame->uc.uc_flags, Efault); + unsafe_put_user(0, &frame->uc.uc_link, Efault); + unsafe_compat_save_altstack(&frame->uc.uc_stack, regs->sp, Efault); + unsafe_put_user(0, &frame->uc.uc__pad0, Efault); + restorer = ksig->ka.sa.sa_restorer; + unsafe_put_user(restorer, (unsigned long __user *)&frame->pretcode, Efault); + unsafe_put_sigcontext(&frame->uc.uc_mcontext, fp, regs, set, Efault); + unsafe_put_sigmask(set, frame, Efault); + user_access_end(); + + if (ksig->ka.sa.sa_flags & SA_SIGINFO) { + if (x32_copy_siginfo_to_user(&frame->info, &ksig->info)) + return -EFAULT; + } + + /* Set up registers for signal handler */ + regs->sp = (unsigned long) frame; + regs->ip = (unsigned long) ksig->ka.sa.sa_handler; + + /* We use the x32 calling convention here... */ + regs->di = ksig->sig; + regs->si = (unsigned long) &frame->info; + regs->dx = (unsigned long) &frame->uc; + + loadsegment(ds, __USER_DS); + loadsegment(es, __USER_DS); + + regs->cs = __USER_CS; + regs->ss = __USER_DS; + + return 0; + +Efault: + user_access_end(); + return -EFAULT; +} + +COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn) +{ + struct pt_regs *regs = current_pt_regs(); + struct rt_sigframe_x32 __user *frame; + sigset_t set; + unsigned long uc_flags; + + frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8); + + if (!access_ok(frame, sizeof(*frame))) + goto badframe; + if (__get_user(set.sig[0], (__u64 __user *)&frame->uc.uc_sigmask)) + goto badframe; + if (__get_user(uc_flags, &frame->uc.uc_flags)) + goto badframe; + + set_current_blocked(&set); + + if (!restore_sigcontext(regs, &frame->uc.uc_mcontext, uc_flags)) + goto badframe; + + if (compat_restore_altstack(&frame->uc.uc_stack)) + goto badframe; + + return regs->ax; + +badframe: + signal_fault(regs, frame, "x32 rt_sigreturn"); + return 0; +} +#endif /* CONFIG_X86_X32_ABI */ diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 3f3ea0287f69..55cad72715d9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -56,8 +56,10 @@ #include <linux/numa.h> #include <linux/pgtable.h> #include <linux/overflow.h> +#include <linux/stackprotector.h> #include <asm/acpi.h> +#include <asm/cacheinfo.h> #include <asm/desc.h> #include <asm/nmi.h> #include <asm/irq.h> @@ -1046,7 +1048,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle) /* Just in case we booted with a single CPU. */ alternatives_enable_smp(); - per_cpu(current_task, cpu) = idle; + per_cpu(pcpu_hot.current_task, cpu) = idle; cpu_init_stack_canary(cpu, idle); /* Initialize the interrupt stack(s) */ @@ -1056,7 +1058,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle) #ifdef CONFIG_X86_32 /* Stack for startup_32 can be just as for start_secondary onwards */ - per_cpu(cpu_current_top_of_stack, cpu) = task_top_of_stack(idle); + per_cpu(pcpu_hot.top_of_stack, cpu) = task_top_of_stack(idle); #else initial_gs = per_cpu_offset(cpu); #endif @@ -1428,8 +1430,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) uv_system_init(); - set_mtrr_aps_delayed_init(); - smp_quirk_init_udelay(); speculative_store_bypass_ht_init(); @@ -1439,12 +1439,12 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) void arch_thaw_secondary_cpus_begin(void) { - set_mtrr_aps_delayed_init(); + set_cache_aps_delayed_init(true); } void arch_thaw_secondary_cpus_end(void) { - mtrr_aps_init(); + cache_aps_init(); } /* @@ -1453,7 +1453,11 @@ void arch_thaw_secondary_cpus_end(void) void __init native_smp_prepare_boot_cpu(void) { int me = smp_processor_id(); - switch_to_new_gdt(me); + + /* SMP handles this from setup_per_cpu_areas() */ + if (!IS_ENABLED(CONFIG_SMP)) + switch_gdt_and_percpu_base(me); + /* already set me in cpu_online_mask in boot_cpu_init() */ cpumask_set_cpu(me, cpu_callout_mask); cpu_set_state_online(me); @@ -1487,7 +1491,7 @@ void __init native_smp_cpus_done(unsigned int max_cpus) nmi_selftest(); impress_friends(); - mtrr_aps_init(); + cache_aps_init(); } static int __initdata setup_possible_cpus = -1; diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index aaaba85d6d7f..2ebc338980bc 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -34,6 +34,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, switch (type) { case CALL: + func = callthunks_translate_call_dest(func); code = text_gen_insn(CALL_INSN_OPCODE, insn, func); if (func == &__static_call_return0) { emulate = code; @@ -52,7 +53,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type, case RET: if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) - code = text_gen_insn(JMP32_INSN_OPCODE, insn, &__x86_return_thunk); + code = text_gen_insn(JMP32_INSN_OPCODE, insn, x86_return_thunk); else code = &retinsn; break; diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index 8617d1ed9d31..1b83377274b8 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -106,7 +106,7 @@ int arch_register_cpu(int num) * Xen PV guests don't support CPU0 hotplug at all. */ if (c->x86_vendor != X86_VENDOR_INTEL || - boot_cpu_has(X86_FEATURE_XENPV)) + cpu_feature_enabled(X86_FEATURE_XENPV)) cpu0_hotpluggable = 0; /* diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index d3fdec706f1d..d317dc3d06a3 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -68,13 +68,13 @@ #ifdef CONFIG_X86_64 #include <asm/x86_init.h> -#include <asm/proto.h> #else #include <asm/processor-flags.h> #include <asm/setup.h> -#include <asm/proto.h> #endif +#include <asm/proto.h> + DECLARE_BITMAP(system_vectors, NR_VECTORS); static inline void cond_local_irq_enable(struct pt_regs *regs) @@ -858,7 +858,7 @@ DEFINE_IDTENTRY_RAW(exc_int3) */ asmlinkage __visible noinstr struct pt_regs *sync_regs(struct pt_regs *eregs) { - struct pt_regs *regs = (struct pt_regs *)this_cpu_read(cpu_current_top_of_stack) - 1; + struct pt_regs *regs = (struct pt_regs *)this_cpu_read(pcpu_hot.top_of_stack) - 1; if (regs != eregs) *regs = *eregs; return regs; @@ -876,7 +876,7 @@ asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *r * trust it and switch to the current kernel stack */ if (ip_within_syscall_gap(regs)) { - sp = this_cpu_read(cpu_current_top_of_stack); + sp = this_cpu_read(pcpu_hot.top_of_stack); goto sync; } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index cafacb2e58cc..a78e73da4a74 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -51,7 +51,7 @@ int tsc_clocksource_reliable; static u32 art_to_tsc_numerator; static u32 art_to_tsc_denominator; static u64 art_to_tsc_offset; -struct clocksource *art_related_clocksource; +static struct clocksource *art_related_clocksource; struct cyc2ns { struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */ diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index c059820dfaea..cdf6c6060170 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -136,6 +136,21 @@ static struct orc_entry null_orc_entry = { .type = UNWIND_HINT_TYPE_CALL }; +#ifdef CONFIG_CALL_THUNKS +static struct orc_entry *orc_callthunk_find(unsigned long ip) +{ + if (!is_callthunk((void *)ip)) + return NULL; + + return &null_orc_entry; +} +#else +static struct orc_entry *orc_callthunk_find(unsigned long ip) +{ + return NULL; +} +#endif + /* Fake frame pointer entry -- used as a fallback for generated code */ static struct orc_entry orc_fp_entry = { .type = UNWIND_HINT_TYPE_CALL, @@ -189,7 +204,11 @@ static struct orc_entry *orc_find(unsigned long ip) if (orc) return orc; - return orc_ftrace_find(ip); + orc = orc_ftrace_find(ip); + if (orc) + return orc; + + return orc_callthunk_find(ip); } #ifdef CONFIG_MODULES diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index b63cf8f7745e..6c07f6daaa22 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -722,8 +722,9 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) switch (opc1) { case 0xeb: /* jmp 8 */ case 0xe9: /* jmp 32 */ - case 0x90: /* prefix* + nop; same as jmp with .offs = 0 */ break; + case 0x90: /* prefix* + nop; same as jmp with .offs = 0 */ + goto setup; case 0xe8: /* call relative */ branch_clear_offset(auprobe, insn); @@ -753,6 +754,7 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) return -ENOTSUPP; } +setup: auprobe->branch.opc1 = opc1; auprobe->branch.ilen = insn->length; auprobe->branch.offs = insn->immediate.value; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 15f29053cec4..2e0ee14229bf 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -132,18 +132,19 @@ SECTIONS CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT - ALIGN_ENTRY_TEXT_BEGIN - ENTRY_TEXT - ALIGN_ENTRY_TEXT_END SOFTIRQENTRY_TEXT - STATIC_CALL_TEXT - *(.gnu.warning) - #ifdef CONFIG_RETPOLINE __indirect_thunk_start = .; *(.text.__x86.*) __indirect_thunk_end = .; #endif + STATIC_CALL_TEXT + + ALIGN_ENTRY_TEXT_BEGIN + ENTRY_TEXT + ALIGN_ENTRY_TEXT_END + *(.gnu.warning) + } :text =0xcccc /* End of text section, which should occupy whole number of pages */ @@ -290,6 +291,13 @@ SECTIONS *(.return_sites) __return_sites_end = .; } + + . = ALIGN(8); + .call_sites : AT(ADDR(.call_sites) - LOAD_OFFSET) { + __call_sites = .; + *(.call_sites) + __call_sites_end = .; + } #endif #ifdef CONFIG_X86_KERNEL_IBT @@ -301,6 +309,15 @@ SECTIONS } #endif +#ifdef CONFIG_FINEIBT + . = ALIGN(8); + .cfi_sites : AT(ADDR(.cfi_sites) - LOAD_OFFSET) { + __cfi_sites = .; + *(.cfi_sites) + __cfi_sites_end = .; + } +#endif + /* * struct alt_inst entries. From the header (alternative.h): * "Alternative instructions for different CPU types or capabilities" @@ -493,11 +510,3 @@ INIT_PER_CPU(irq_stack_backing_store); #endif #endif /* CONFIG_X86_64 */ - -#ifdef CONFIG_KEXEC_CORE -#include <asm/kexec.h> - -. = ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE, - "kexec control code size is too big"); -#endif - diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 57353519bc11..ef80d361b463 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -25,6 +25,7 @@ #include <asm/iommu.h> #include <asm/mach_traps.h> #include <asm/irqdomain.h> +#include <asm/realmode.h> void x86_init_noop(void) { } void __init x86_init_uint_noop(unsigned int unused) { } @@ -145,6 +146,8 @@ struct x86_platform_ops x86_platform __ro_after_init = { .get_nmi_reason = default_get_nmi_reason, .save_sched_clock_state = tsc_save_sched_clock_state, .restore_sched_clock_state = tsc_restore_sched_clock_state, + .realmode_reserve = reserve_real_mode, + .realmode_init = init_real_mode, .hyper.pin_vcpu = x86_op_int_noop, .guest = { diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 67be7f217e37..fbeaa9ddef59 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -118,6 +118,17 @@ config KVM_AMD_SEV Provides support for launching Encrypted VMs (SEV) and Encrypted VMs with Encrypted State (SEV-ES) on AMD processors. +config KVM_SMM + bool "System Management Mode emulation" + default y + depends on KVM + help + Provides support for KVM to emulate System Management Mode (SMM) + in virtual machines. This can be used by the virtual machine + firmware to implement UEFI secure boot. + + If unsure, say Y. + config KVM_XEN bool "Support for Xen hypercall interface" depends on KVM diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index f453a0f96e24..80e3fe184d17 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -20,12 +20,14 @@ endif kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o kvm-$(CONFIG_KVM_XEN) += xen.o +kvm-$(CONFIG_KVM_SMM) += smm.o kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \ - vmx/evmcs.o vmx/nested.o vmx/posted_intr.o + vmx/hyperv.o vmx/nested.o vmx/posted_intr.o kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o -kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o svm/sev.o +kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \ + svm/sev.o svm/hyperv.o ifdef CONFIG_HYPERV kvm-amd-y += svm/svm_onhyperv.o diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 62bc7a01cecc..b14653b61470 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -62,10 +62,16 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) * This one is tied to SSB in the user API, and not * visible in /proc/cpuinfo. */ -#define KVM_X86_FEATURE_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ +#define KVM_X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ #define F feature_bit -#define SF(name) (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0) + +/* Scattered Flag - For features that are scattered by cpufeatures.h. */ +#define SF(name) \ +({ \ + BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \ + (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0); \ +}) /* * Magic value used by KVM when querying userspace-provided CPUID entries and @@ -543,9 +549,9 @@ static __always_inline void __kvm_cpu_cap_mask(unsigned int leaf) } static __always_inline -void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask) +void kvm_cpu_cap_init_kvm_defined(enum kvm_only_cpuid_leafs leaf, u32 mask) { - /* Use kvm_cpu_cap_mask for non-scattered leafs. */ + /* Use kvm_cpu_cap_mask for leafs that aren't KVM-only. */ BUILD_BUG_ON(leaf < NCAPINTS); kvm_cpu_caps[leaf] = mask; @@ -555,7 +561,7 @@ void kvm_cpu_cap_init_scattered(enum kvm_only_cpuid_leafs leaf, u32 mask) static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) { - /* Use kvm_cpu_cap_init_scattered for scattered leafs. */ + /* Use kvm_cpu_cap_init_kvm_defined for KVM-only leafs. */ BUILD_BUG_ON(leaf >= NCAPINTS); kvm_cpu_caps[leaf] &= mask; @@ -657,15 +663,20 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); kvm_cpu_cap_mask(CPUID_7_1_EAX, - F(AVX_VNNI) | F(AVX512_BF16) + F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | F(AMX_FP16) | + F(AVX_IFMA) + ); + + kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, + F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(PREFETCHITI) ); kvm_cpu_cap_mask(CPUID_D_1_EAX, F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd ); - kvm_cpu_cap_init_scattered(CPUID_12_EAX, - SF(SGX1) | SF(SGX2) + kvm_cpu_cap_init_kvm_defined(CPUID_12_EAX, + SF(SGX1) | SF(SGX2) | SF(SGX_EDECCSSA) ); kvm_cpu_cap_mask(CPUID_8000_0001_ECX, @@ -694,7 +705,7 @@ void kvm_set_cpu_caps(void) F(CLZERO) | F(XSAVEERPTR) | F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) | - __feature_bit(KVM_X86_FEATURE_PSFD) + __feature_bit(KVM_X86_FEATURE_AMD_PSFD) ); /* @@ -913,9 +924,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) goto out; cpuid_entry_override(entry, CPUID_7_1_EAX); + cpuid_entry_override(entry, CPUID_7_1_EDX); entry->ebx = 0; entry->ecx = 0; - entry->edx = 0; } break; case 0xa: { /* Architectural Performance Monitoring */ @@ -1047,9 +1058,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * userspace. ATTRIBUTES.XFRM is not adjusted as userspace is * expected to derive it from supported XCR0. */ - entry->eax &= SGX_ATTR_DEBUG | SGX_ATTR_MODE64BIT | - SGX_ATTR_PROVISIONKEY | SGX_ATTR_EINITTOKENKEY | - SGX_ATTR_KSS; + entry->eax &= SGX_ATTR_PRIV_MASK | SGX_ATTR_UNPRIV_MASK; entry->ebx &= 0; break; /* Intel PT */ @@ -1222,8 +1231,12 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * Other defined bits are for MSRs that KVM does not expose: * EAX 3 SPCL, SMM page configuration lock * EAX 13 PCMSR, Prefetch control MSR + * + * KVM doesn't support SMM_CTL. + * EAX 9 SMM_CTL MSR is not supported */ entry->eax &= BIT(0) | BIT(2) | BIT(6); + entry->eax |= BIT(9); if (static_cpu_has(X86_FEATURE_LFENCE_RDTSC)) entry->eax |= BIT(2); if (!static_cpu_has_bug(X86_BUG_NULL_SEG)) diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 4a43261d25a2..5cc3efa0e21c 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -242,37 +242,6 @@ enum x86_transfer_type { X86_TRANSFER_TASK_SWITCH, }; -static ulong reg_read(struct x86_emulate_ctxt *ctxt, unsigned nr) -{ - if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt)) - nr &= NR_EMULATOR_GPRS - 1; - - if (!(ctxt->regs_valid & (1 << nr))) { - ctxt->regs_valid |= 1 << nr; - ctxt->_regs[nr] = ctxt->ops->read_gpr(ctxt, nr); - } - return ctxt->_regs[nr]; -} - -static ulong *reg_write(struct x86_emulate_ctxt *ctxt, unsigned nr) -{ - if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt)) - nr &= NR_EMULATOR_GPRS - 1; - - BUILD_BUG_ON(sizeof(ctxt->regs_dirty) * BITS_PER_BYTE < NR_EMULATOR_GPRS); - BUILD_BUG_ON(sizeof(ctxt->regs_valid) * BITS_PER_BYTE < NR_EMULATOR_GPRS); - - ctxt->regs_valid |= 1 << nr; - ctxt->regs_dirty |= 1 << nr; - return &ctxt->_regs[nr]; -} - -static ulong *reg_rmw(struct x86_emulate_ctxt *ctxt, unsigned nr) -{ - reg_read(ctxt, nr); - return reg_write(ctxt, nr); -} - static void writeback_registers(struct x86_emulate_ctxt *ctxt) { unsigned long dirty = ctxt->regs_dirty; @@ -2338,335 +2307,15 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt) return rc; } -static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt) -{ -#ifdef CONFIG_X86_64 - return ctxt->ops->guest_has_long_mode(ctxt); -#else - return false; -#endif -} - -static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags) -{ - desc->g = (flags >> 23) & 1; - desc->d = (flags >> 22) & 1; - desc->l = (flags >> 21) & 1; - desc->avl = (flags >> 20) & 1; - desc->p = (flags >> 15) & 1; - desc->dpl = (flags >> 13) & 3; - desc->s = (flags >> 12) & 1; - desc->type = (flags >> 8) & 15; -} - -static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate, - int n) -{ - struct desc_struct desc; - int offset; - u16 selector; - - selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4); - - if (n < 3) - offset = 0x7f84 + n * 12; - else - offset = 0x7f2c + (n - 3) * 12; - - set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8)); - set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4)); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset)); - ctxt->ops->set_segment(ctxt, selector, &desc, 0, n); - return X86EMUL_CONTINUE; -} - -#ifdef CONFIG_X86_64 -static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate, - int n) -{ - struct desc_struct desc; - int offset; - u16 selector; - u32 base3; - - offset = 0x7e00 + n * 16; - - selector = GET_SMSTATE(u16, smstate, offset); - rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8); - set_desc_limit(&desc, GET_SMSTATE(u32, smstate, offset + 4)); - set_desc_base(&desc, GET_SMSTATE(u32, smstate, offset + 8)); - base3 = GET_SMSTATE(u32, smstate, offset + 12); - - ctxt->ops->set_segment(ctxt, selector, &desc, base3, n); - return X86EMUL_CONTINUE; -} -#endif - -static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt, - u64 cr0, u64 cr3, u64 cr4) -{ - int bad; - u64 pcid; - - /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */ - pcid = 0; - if (cr4 & X86_CR4_PCIDE) { - pcid = cr3 & 0xfff; - cr3 &= ~0xfff; - } - - bad = ctxt->ops->set_cr(ctxt, 3, cr3); - if (bad) - return X86EMUL_UNHANDLEABLE; - - /* - * First enable PAE, long mode needs it before CR0.PG = 1 is set. - * Then enable protected mode. However, PCID cannot be enabled - * if EFER.LMA=0, so set it separately. - */ - bad = ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); - if (bad) - return X86EMUL_UNHANDLEABLE; - - bad = ctxt->ops->set_cr(ctxt, 0, cr0); - if (bad) - return X86EMUL_UNHANDLEABLE; - - if (cr4 & X86_CR4_PCIDE) { - bad = ctxt->ops->set_cr(ctxt, 4, cr4); - if (bad) - return X86EMUL_UNHANDLEABLE; - if (pcid) { - bad = ctxt->ops->set_cr(ctxt, 3, cr3 | pcid); - if (bad) - return X86EMUL_UNHANDLEABLE; - } - - } - - return X86EMUL_CONTINUE; -} - -static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, - const char *smstate) -{ - struct desc_struct desc; - struct desc_ptr dt; - u16 selector; - u32 val, cr0, cr3, cr4; - int i; - - cr0 = GET_SMSTATE(u32, smstate, 0x7ffc); - cr3 = GET_SMSTATE(u32, smstate, 0x7ff8); - ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED; - ctxt->_eip = GET_SMSTATE(u32, smstate, 0x7ff0); - - for (i = 0; i < 8; i++) - *reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4); - - val = GET_SMSTATE(u32, smstate, 0x7fcc); - - if (ctxt->ops->set_dr(ctxt, 6, val)) - return X86EMUL_UNHANDLEABLE; - - val = GET_SMSTATE(u32, smstate, 0x7fc8); - - if (ctxt->ops->set_dr(ctxt, 7, val)) - return X86EMUL_UNHANDLEABLE; - - selector = GET_SMSTATE(u32, smstate, 0x7fc4); - set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f64)); - set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f60)); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f5c)); - ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR); - - selector = GET_SMSTATE(u32, smstate, 0x7fc0); - set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7f80)); - set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7f7c)); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7f78)); - ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR); - - dt.address = GET_SMSTATE(u32, smstate, 0x7f74); - dt.size = GET_SMSTATE(u32, smstate, 0x7f70); - ctxt->ops->set_gdt(ctxt, &dt); - - dt.address = GET_SMSTATE(u32, smstate, 0x7f58); - dt.size = GET_SMSTATE(u32, smstate, 0x7f54); - ctxt->ops->set_idt(ctxt, &dt); - - for (i = 0; i < 6; i++) { - int r = rsm_load_seg_32(ctxt, smstate, i); - if (r != X86EMUL_CONTINUE) - return r; - } - - cr4 = GET_SMSTATE(u32, smstate, 0x7f14); - - ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8)); - - return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); -} - -#ifdef CONFIG_X86_64 -static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, - const char *smstate) -{ - struct desc_struct desc; - struct desc_ptr dt; - u64 val, cr0, cr3, cr4; - u32 base3; - u16 selector; - int i, r; - - for (i = 0; i < 16; i++) - *reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8); - - ctxt->_eip = GET_SMSTATE(u64, smstate, 0x7f78); - ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED; - - val = GET_SMSTATE(u64, smstate, 0x7f68); - - if (ctxt->ops->set_dr(ctxt, 6, val)) - return X86EMUL_UNHANDLEABLE; - - val = GET_SMSTATE(u64, smstate, 0x7f60); - - if (ctxt->ops->set_dr(ctxt, 7, val)) - return X86EMUL_UNHANDLEABLE; - - cr0 = GET_SMSTATE(u64, smstate, 0x7f58); - cr3 = GET_SMSTATE(u64, smstate, 0x7f50); - cr4 = GET_SMSTATE(u64, smstate, 0x7f48); - ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00)); - val = GET_SMSTATE(u64, smstate, 0x7ed0); - - if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA)) - return X86EMUL_UNHANDLEABLE; - - selector = GET_SMSTATE(u32, smstate, 0x7e90); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e92) << 8); - set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e94)); - set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e98)); - base3 = GET_SMSTATE(u32, smstate, 0x7e9c); - ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR); - - dt.size = GET_SMSTATE(u32, smstate, 0x7e84); - dt.address = GET_SMSTATE(u64, smstate, 0x7e88); - ctxt->ops->set_idt(ctxt, &dt); - - selector = GET_SMSTATE(u32, smstate, 0x7e70); - rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, 0x7e72) << 8); - set_desc_limit(&desc, GET_SMSTATE(u32, smstate, 0x7e74)); - set_desc_base(&desc, GET_SMSTATE(u32, smstate, 0x7e78)); - base3 = GET_SMSTATE(u32, smstate, 0x7e7c); - ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR); - - dt.size = GET_SMSTATE(u32, smstate, 0x7e64); - dt.address = GET_SMSTATE(u64, smstate, 0x7e68); - ctxt->ops->set_gdt(ctxt, &dt); - - r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4); - if (r != X86EMUL_CONTINUE) - return r; - - for (i = 0; i < 6; i++) { - r = rsm_load_seg_64(ctxt, smstate, i); - if (r != X86EMUL_CONTINUE) - return r; - } - - return X86EMUL_CONTINUE; -} -#endif - static int em_rsm(struct x86_emulate_ctxt *ctxt) { - unsigned long cr0, cr4, efer; - char buf[512]; - u64 smbase; - int ret; - if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0) return emulate_ud(ctxt); - smbase = ctxt->ops->get_smbase(ctxt); - - ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf)); - if (ret != X86EMUL_CONTINUE) - return X86EMUL_UNHANDLEABLE; - - if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_INSIDE_NMI_MASK) == 0) - ctxt->ops->set_nmi_mask(ctxt, false); - - ctxt->ops->exiting_smm(ctxt); - - /* - * Get back to real mode, to prepare a safe state in which to load - * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU - * supports long mode. - */ - if (emulator_has_longmode(ctxt)) { - struct desc_struct cs_desc; - - /* Zero CR4.PCIDE before CR0.PG. */ - cr4 = ctxt->ops->get_cr(ctxt, 4); - if (cr4 & X86_CR4_PCIDE) - ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE); - - /* A 32-bit code segment is required to clear EFER.LMA. */ - memset(&cs_desc, 0, sizeof(cs_desc)); - cs_desc.type = 0xb; - cs_desc.s = cs_desc.g = cs_desc.p = 1; - ctxt->ops->set_segment(ctxt, 0, &cs_desc, 0, VCPU_SREG_CS); - } - - /* For the 64-bit case, this will clear EFER.LMA. */ - cr0 = ctxt->ops->get_cr(ctxt, 0); - if (cr0 & X86_CR0_PE) - ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); - - if (emulator_has_longmode(ctxt)) { - /* Clear CR4.PAE before clearing EFER.LME. */ - cr4 = ctxt->ops->get_cr(ctxt, 4); - if (cr4 & X86_CR4_PAE) - ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE); - - /* And finally go back to 32-bit mode. */ - efer = 0; - ctxt->ops->set_msr(ctxt, MSR_EFER, efer); - } - - /* - * Give leave_smm() a chance to make ISA-specific changes to the vCPU - * state (e.g. enter guest mode) before loading state from the SMM - * state-save area. - */ - if (ctxt->ops->leave_smm(ctxt, buf)) - goto emulate_shutdown; - -#ifdef CONFIG_X86_64 - if (emulator_has_longmode(ctxt)) - ret = rsm_load_state_64(ctxt, buf); - else -#endif - ret = rsm_load_state_32(ctxt, buf); - - if (ret != X86EMUL_CONTINUE) - goto emulate_shutdown; + if (ctxt->ops->leave_smm(ctxt)) + ctxt->ops->triple_fault(ctxt); - /* - * Note, the ctxt->ops callbacks are responsible for handling side - * effects when writing MSRs and CRs, e.g. MMU context resets, CPUID - * runtime updates, etc... If that changes, e.g. this flow is moved - * out of the emulator to make it look more like enter_smm(), then - * those side effects need to be explicitly handled for both success - * and shutdown. - */ return emulator_recalc_and_set_mode(ctxt); - -emulate_shutdown: - ctxt->ops->triple_fault(ctxt); - return X86EMUL_CONTINUE; } static void diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 0adf4a437e85..2c7f2a26421e 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -23,22 +23,25 @@ #include "ioapic.h" #include "cpuid.h" #include "hyperv.h" +#include "mmu.h" #include "xen.h" #include <linux/cpu.h> #include <linux/kvm_host.h> #include <linux/highmem.h> #include <linux/sched/cputime.h> +#include <linux/spinlock.h> #include <linux/eventfd.h> #include <asm/apicdef.h> +#include <asm/mshyperv.h> #include <trace/events/kvm.h> #include "trace.h" #include "irq.h" #include "fpu.h" -#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, 64) +#define KVM_HV_MAX_SPARSE_VCPU_SET_BITS DIV_ROUND_UP(KVM_MAX_VCPUS, HV_VCPUS_PER_SPARSE_BANK) static void stimer_mark_pending(struct kvm_vcpu_hv_stimer *stimer, bool vcpu_kick); @@ -897,13 +900,15 @@ bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_hv_assist_page_enabled); -bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu, - struct hv_vp_assist_page *assist_page) +int kvm_hv_get_assist_page(struct kvm_vcpu *vcpu) { - if (!kvm_hv_assist_page_enabled(vcpu)) - return false; - return !kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, - assist_page, sizeof(*assist_page)); + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + if (!hv_vcpu || !kvm_hv_assist_page_enabled(vcpu)) + return -EFAULT; + + return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.pv_eoi.data, + &hv_vcpu->vp_assist_page, sizeof(struct hv_vp_assist_page)); } EXPORT_SYMBOL_GPL(kvm_hv_get_assist_page); @@ -954,6 +959,11 @@ int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) hv_vcpu->vp_index = vcpu->vcpu_idx; + for (i = 0; i < HV_NR_TLB_FLUSH_FIFOS; i++) { + INIT_KFIFO(hv_vcpu->tlb_flush_fifo[i].entries); + spin_lock_init(&hv_vcpu->tlb_flush_fifo[i].write_lock); + } + return 0; } @@ -1736,6 +1746,28 @@ static void sparse_set_to_vcpu_mask(struct kvm *kvm, u64 *sparse_banks, } } +static bool hv_is_vp_in_sparse_set(u32 vp_id, u64 valid_bank_mask, u64 sparse_banks[]) +{ + int valid_bit_nr = vp_id / HV_VCPUS_PER_SPARSE_BANK; + unsigned long sbank; + + if (!test_bit(valid_bit_nr, (unsigned long *)&valid_bank_mask)) + return false; + + /* + * The index into the sparse bank is the number of preceding bits in + * the valid mask. Optimize for VMs with <64 vCPUs by skipping the + * fancy math if there can't possibly be preceding bits. + */ + if (valid_bit_nr) + sbank = hweight64(valid_bank_mask & GENMASK_ULL(valid_bit_nr - 1, 0)); + else + sbank = 0; + + return test_bit(vp_id % HV_VCPUS_PER_SPARSE_BANK, + (unsigned long *)&sparse_banks[sbank]); +} + struct kvm_hv_hcall { u64 param; u64 ingpa; @@ -1749,57 +1781,173 @@ struct kvm_hv_hcall { sse128_t xmm[HV_HYPERCALL_MAX_XMM_REGISTERS]; }; -static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc, - int consumed_xmm_halves, - u64 *sparse_banks, gpa_t offset) -{ - u16 var_cnt; - int i; - - if (hc->var_cnt > 64) - return -EINVAL; - /* Ignore banks that cannot possibly contain a legal VP index. */ - var_cnt = min_t(u16, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS); +static int kvm_hv_get_hc_data(struct kvm *kvm, struct kvm_hv_hcall *hc, + u16 orig_cnt, u16 cnt_cap, u64 *data, + int consumed_xmm_halves, gpa_t offset) +{ + /* + * Preserve the original count when ignoring entries via a "cap", KVM + * still needs to validate the guest input (though the non-XMM path + * punts on the checks). + */ + u16 cnt = min(orig_cnt, cnt_cap); + int i, j; if (hc->fast) { /* * Each XMM holds two sparse banks, but do not count halves that * have already been consumed for hypercall parameters. */ - if (hc->var_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves) + if (orig_cnt > 2 * HV_HYPERCALL_MAX_XMM_REGISTERS - consumed_xmm_halves) return HV_STATUS_INVALID_HYPERCALL_INPUT; - for (i = 0; i < var_cnt; i++) { - int j = i + consumed_xmm_halves; + + for (i = 0; i < cnt; i++) { + j = i + consumed_xmm_halves; if (j % 2) - sparse_banks[i] = sse128_hi(hc->xmm[j / 2]); + data[i] = sse128_hi(hc->xmm[j / 2]); else - sparse_banks[i] = sse128_lo(hc->xmm[j / 2]); + data[i] = sse128_lo(hc->xmm[j / 2]); } return 0; } - return kvm_read_guest(kvm, hc->ingpa + offset, sparse_banks, - var_cnt * sizeof(*sparse_banks)); + return kvm_read_guest(kvm, hc->ingpa + offset, data, + cnt * sizeof(*data)); +} + +static u64 kvm_get_sparse_vp_set(struct kvm *kvm, struct kvm_hv_hcall *hc, + u64 *sparse_banks, int consumed_xmm_halves, + gpa_t offset) +{ + if (hc->var_cnt > HV_MAX_SPARSE_VCPU_BANKS) + return -EINVAL; + + /* Cap var_cnt to ignore banks that cannot contain a legal VP index. */ + return kvm_hv_get_hc_data(kvm, hc, hc->var_cnt, KVM_HV_MAX_SPARSE_VCPU_SET_BITS, + sparse_banks, consumed_xmm_halves, offset); +} + +static int kvm_hv_get_tlb_flush_entries(struct kvm *kvm, struct kvm_hv_hcall *hc, u64 entries[], + int consumed_xmm_halves, gpa_t offset) +{ + return kvm_hv_get_hc_data(kvm, hc, hc->rep_cnt, hc->rep_cnt, + entries, consumed_xmm_halves, offset); +} + +static void hv_tlb_flush_enqueue(struct kvm_vcpu *vcpu, + struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo, + u64 *entries, int count) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + u64 flush_all_entry = KVM_HV_TLB_FLUSHALL_ENTRY; + + if (!hv_vcpu) + return; + + spin_lock(&tlb_flush_fifo->write_lock); + + /* + * All entries should fit on the fifo leaving one free for 'flush all' + * entry in case another request comes in. In case there's not enough + * space, just put 'flush all' entry there. + */ + if (count && entries && count < kfifo_avail(&tlb_flush_fifo->entries)) { + WARN_ON(kfifo_in(&tlb_flush_fifo->entries, entries, count) != count); + goto out_unlock; + } + + /* + * Note: full fifo always contains 'flush all' entry, no need to check the + * return value. + */ + kfifo_in(&tlb_flush_fifo->entries, &flush_all_entry, 1); + +out_unlock: + spin_unlock(&tlb_flush_fifo->write_lock); +} + +int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + u64 entries[KVM_HV_TLB_FLUSH_FIFO_SIZE]; + int i, j, count; + gva_t gva; + + if (!tdp_enabled || !hv_vcpu) + return -EINVAL; + + tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(vcpu, is_guest_mode(vcpu)); + + count = kfifo_out(&tlb_flush_fifo->entries, entries, KVM_HV_TLB_FLUSH_FIFO_SIZE); + + for (i = 0; i < count; i++) { + if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY) + goto out_flush_all; + + /* + * Lower 12 bits of 'address' encode the number of additional + * pages to flush. + */ + gva = entries[i] & PAGE_MASK; + for (j = 0; j < (entries[i] & ~PAGE_MASK) + 1; j++) + static_call(kvm_x86_flush_tlb_gva)(vcpu, gva + j * PAGE_SIZE); + + ++vcpu->stat.tlb_flush; + } + return 0; + +out_flush_all: + kfifo_reset_out(&tlb_flush_fifo->entries); + + /* Fall back to full flush. */ + return -ENOSPC; } static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + u64 *sparse_banks = hv_vcpu->sparse_banks; struct kvm *kvm = vcpu->kvm; struct hv_tlb_flush_ex flush_ex; struct hv_tlb_flush flush; DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); + struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo; + /* + * Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE' + * entries on the TLB flush fifo. The last entry, however, needs to be + * always left free for 'flush all' entry which gets placed when + * there is not enough space to put all the requested entries. + */ + u64 __tlb_flush_entries[KVM_HV_TLB_FLUSH_FIFO_SIZE - 1]; + u64 *tlb_flush_entries; u64 valid_bank_mask; - u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; + struct kvm_vcpu *v; + unsigned long i; bool all_cpus; + int consumed_xmm_halves = 0; + gpa_t data_offset; /* - * The Hyper-V TLFS doesn't allow more than 64 sparse banks, e.g. the - * valid mask is a u64. Fail the build if KVM's max allowed number of - * vCPUs (>4096) would exceed this limit, KVM will additional changes - * for Hyper-V support to avoid setting the guest up to fail. + * The Hyper-V TLFS doesn't allow more than HV_MAX_SPARSE_VCPU_BANKS + * sparse banks. Fail the build if KVM's max allowed number of + * vCPUs (>4096) exceeds this limit. */ - BUILD_BUG_ON(KVM_HV_MAX_SPARSE_VCPU_SET_BITS > 64); + BUILD_BUG_ON(KVM_HV_MAX_SPARSE_VCPU_SET_BITS > HV_MAX_SPARSE_VCPU_BANKS); + + /* + * 'Slow' hypercall's first parameter is the address in guest's memory + * where hypercall parameters are placed. This is either a GPA or a + * nested GPA when KVM is handling the call from L2 ('direct' TLB + * flush). Translate the address here so the memory can be uniformly + * read with kvm_read_guest(). + */ + if (!hc->fast && is_guest_mode(vcpu)) { + hc->ingpa = translate_nested_gpa(vcpu, hc->ingpa, 0, NULL); + if (unlikely(hc->ingpa == INVALID_GPA)) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST || hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE) { @@ -1807,14 +1955,17 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) flush.address_space = hc->ingpa; flush.flags = hc->outgpa; flush.processor_mask = sse128_lo(hc->xmm[0]); + consumed_xmm_halves = 1; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush, sizeof(flush)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; + data_offset = sizeof(flush); } trace_kvm_hv_flush_tlb(flush.processor_mask, - flush.address_space, flush.flags); + flush.address_space, flush.flags, + is_guest_mode(vcpu)); valid_bank_mask = BIT_ULL(0); sparse_banks[0] = flush.processor_mask; @@ -1834,16 +1985,18 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) flush_ex.flags = hc->outgpa; memcpy(&flush_ex.hv_vp_set, &hc->xmm[0], sizeof(hc->xmm[0])); + consumed_xmm_halves = 2; } else { if (unlikely(kvm_read_guest(kvm, hc->ingpa, &flush_ex, sizeof(flush_ex)))) return HV_STATUS_INVALID_HYPERCALL_INPUT; + data_offset = sizeof(flush_ex); } trace_kvm_hv_flush_tlb_ex(flush_ex.hv_vp_set.valid_bank_mask, flush_ex.hv_vp_set.format, flush_ex.address_space, - flush_ex.flags); + flush_ex.flags, is_guest_mode(vcpu)); valid_bank_mask = flush_ex.hv_vp_set.valid_bank_mask; all_cpus = flush_ex.hv_vp_set.format != @@ -1852,29 +2005,95 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) if (hc->var_cnt != hweight64(valid_bank_mask)) return HV_STATUS_INVALID_HYPERCALL_INPUT; - if (all_cpus) - goto do_flush; + if (!all_cpus) { + if (!hc->var_cnt) + goto ret_success; - if (!hc->var_cnt) - goto ret_success; + if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, + consumed_xmm_halves, data_offset)) + return HV_STATUS_INVALID_HYPERCALL_INPUT; + } - if (kvm_get_sparse_vp_set(kvm, hc, 2, sparse_banks, - offsetof(struct hv_tlb_flush_ex, - hv_vp_set.bank_contents))) + /* + * Hyper-V TLFS doesn't explicitly forbid non-empty sparse vCPU + * banks (and, thus, non-zero 'var_cnt') for the 'all vCPUs' + * case (HV_GENERIC_SET_ALL). Always adjust data_offset and + * consumed_xmm_halves to make sure TLB flush entries are read + * from the correct offset. + */ + data_offset += hc->var_cnt * sizeof(sparse_banks[0]); + consumed_xmm_halves += hc->var_cnt; + } + + if (hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE || + hc->code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX || + hc->rep_cnt > ARRAY_SIZE(__tlb_flush_entries)) { + tlb_flush_entries = NULL; + } else { + if (kvm_hv_get_tlb_flush_entries(kvm, hc, __tlb_flush_entries, + consumed_xmm_halves, data_offset)) return HV_STATUS_INVALID_HYPERCALL_INPUT; + tlb_flush_entries = __tlb_flush_entries; } -do_flush: /* * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't * analyze it here, flush TLB regardless of the specified address space. */ - if (all_cpus) { - kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH_GUEST); - } else { + if (all_cpus && !is_guest_mode(vcpu)) { + kvm_for_each_vcpu(i, v, kvm) { + tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, false); + hv_tlb_flush_enqueue(v, tlb_flush_fifo, + tlb_flush_entries, hc->rep_cnt); + } + + kvm_make_all_cpus_request(kvm, KVM_REQ_HV_TLB_FLUSH); + } else if (!is_guest_mode(vcpu)) { sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, vcpu_mask); - kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST, vcpu_mask); + for_each_set_bit(i, vcpu_mask, KVM_MAX_VCPUS) { + v = kvm_get_vcpu(kvm, i); + if (!v) + continue; + tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, false); + hv_tlb_flush_enqueue(v, tlb_flush_fifo, + tlb_flush_entries, hc->rep_cnt); + } + + kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, vcpu_mask); + } else { + struct kvm_vcpu_hv *hv_v; + + bitmap_zero(vcpu_mask, KVM_MAX_VCPUS); + + kvm_for_each_vcpu(i, v, kvm) { + hv_v = to_hv_vcpu(v); + + /* + * The following check races with nested vCPUs entering/exiting + * and/or migrating between L1's vCPUs, however the only case when + * KVM *must* flush the TLB is when the target L2 vCPU keeps + * running on the same L1 vCPU from the moment of the request until + * kvm_hv_flush_tlb() returns. TLB is fully flushed in all other + * cases, e.g. when the target L2 vCPU migrates to a different L1 + * vCPU or when the corresponding L1 vCPU temporary switches to a + * different L2 vCPU while the request is being processed. + */ + if (!hv_v || hv_v->nested.vm_id != hv_vcpu->nested.vm_id) + continue; + + if (!all_cpus && + !hv_is_vp_in_sparse_set(hv_v->nested.vp_id, valid_bank_mask, + sparse_banks)) + continue; + + __set_bit(i, vcpu_mask); + tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(v, true); + hv_tlb_flush_enqueue(v, tlb_flush_fifo, + tlb_flush_entries, hc->rep_cnt); + } + + kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH, vcpu_mask); } ret_success: @@ -1883,8 +2102,8 @@ ret_success: ((u64)hc->rep_cnt << HV_HYPERCALL_REP_COMP_OFFSET); } -static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, - unsigned long *vcpu_bitmap) +static void kvm_hv_send_ipi_to_many(struct kvm *kvm, u32 vector, + u64 *sparse_banks, u64 valid_bank_mask) { struct kvm_lapic_irq irq = { .delivery_mode = APIC_DM_FIXED, @@ -1894,7 +2113,9 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, unsigned long i; kvm_for_each_vcpu(i, vcpu, kvm) { - if (vcpu_bitmap && !test_bit(i, vcpu_bitmap)) + if (sparse_banks && + !hv_is_vp_in_sparse_set(kvm_hv_get_vpindex(vcpu), + valid_bank_mask, sparse_banks)) continue; /* We fail only when APIC is disabled */ @@ -1904,12 +2125,12 @@ static void kvm_send_ipi_to_many(struct kvm *kvm, u32 vector, static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + u64 *sparse_banks = hv_vcpu->sparse_banks; struct kvm *kvm = vcpu->kvm; struct hv_send_ipi_ex send_ipi_ex; struct hv_send_ipi send_ipi; - DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS); u64 valid_bank_mask; - u64 sparse_banks[KVM_HV_MAX_SPARSE_VCPU_SET_BITS]; u32 vector; bool all_cpus; @@ -1959,7 +2180,7 @@ static u64 kvm_hv_send_ipi(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc) if (!hc->var_cnt) goto ret_success; - if (kvm_get_sparse_vp_set(kvm, hc, 1, sparse_banks, + if (kvm_get_sparse_vp_set(kvm, hc, sparse_banks, 1, offsetof(struct hv_send_ipi_ex, vp_set.bank_contents))) return HV_STATUS_INVALID_HYPERCALL_INPUT; @@ -1969,13 +2190,10 @@ check_and_send_ipi: if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) return HV_STATUS_INVALID_HYPERCALL_INPUT; - if (all_cpus) { - kvm_send_ipi_to_many(kvm, vector, NULL); - } else { - sparse_set_to_vcpu_mask(kvm, sparse_banks, valid_bank_mask, vcpu_mask); - - kvm_send_ipi_to_many(kvm, vector, vcpu_mask); - } + if (all_cpus) + kvm_hv_send_ipi_to_many(kvm, vector, NULL, 0); + else + kvm_hv_send_ipi_to_many(kvm, vector, sparse_banks, valid_bank_mask); ret_success: return HV_STATUS_SUCCESS; @@ -2062,10 +2280,25 @@ static void kvm_hv_hypercall_set_result(struct kvm_vcpu *vcpu, u64 result) static int kvm_hv_hypercall_complete(struct kvm_vcpu *vcpu, u64 result) { + u32 tlb_lock_count = 0; + int ret; + + if (hv_result_success(result) && is_guest_mode(vcpu) && + kvm_hv_is_tlb_flush_hcall(vcpu) && + kvm_read_guest(vcpu->kvm, to_hv_vcpu(vcpu)->nested.pa_page_gpa, + &tlb_lock_count, sizeof(tlb_lock_count))) + result = HV_STATUS_INVALID_HYPERCALL_INPUT; + trace_kvm_hv_hypercall_done(result); kvm_hv_hypercall_set_result(vcpu, result); ++vcpu->stat.hypercalls; - return kvm_skip_emulated_instruction(vcpu); + + ret = kvm_skip_emulated_instruction(vcpu); + + if (tlb_lock_count) + kvm_x86_ops.nested_ops->hv_inject_synthetic_vmexit_post_tlb_flush(vcpu); + + return ret; } static int kvm_hv_hypercall_complete_userspace(struct kvm_vcpu *vcpu) @@ -2502,6 +2735,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, ent->ebx |= HV_DEBUGGING; ent->edx |= HV_X64_GUEST_DEBUGGING_AVAILABLE; ent->edx |= HV_FEATURE_DEBUG_MSRS_AVAILABLE; + ent->edx |= HV_FEATURE_EXT_GVA_RANGES_FLUSH; /* * Direct Synthetic timers only make sense with in-kernel @@ -2545,6 +2779,7 @@ int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, case HYPERV_CPUID_NESTED_FEATURES: ent->eax = evmcs_ver; + ent->eax |= HV_X64_NESTED_DIRECT_FLUSH; ent->eax |= HV_X64_NESTED_MSR_BITMAP; ent->ebx |= HV_X64_NESTED_EVMCS1_PERF_GLOBAL_CTRL; break; diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index 1030b1b50552..9f96414a31c5 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -22,6 +22,7 @@ #define __ARCH_X86_KVM_HYPERV_H__ #include <linux/kvm_host.h> +#include "x86.h" /* "Hv#1" signature */ #define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 @@ -107,8 +108,7 @@ int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages); void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu); bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu); -bool kvm_hv_get_assist_page(struct kvm_vcpu *vcpu, - struct hv_vp_assist_page *assist_page); +int kvm_hv_get_assist_page(struct kvm_vcpu *vcpu); static inline struct kvm_vcpu_hv_stimer *to_hv_stimer(struct kvm_vcpu *vcpu, int timer_index) @@ -151,4 +151,64 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args); int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 __user *entries); +static inline struct kvm_vcpu_hv_tlb_flush_fifo *kvm_hv_get_tlb_flush_fifo(struct kvm_vcpu *vcpu, + bool is_guest_mode) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + int i = is_guest_mode ? HV_L2_TLB_FLUSH_FIFO : + HV_L1_TLB_FLUSH_FIFO; + + return &hv_vcpu->tlb_flush_fifo[i]; +} + +static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo; + + if (!to_hv_vcpu(vcpu) || !kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu)) + return; + + tlb_flush_fifo = kvm_hv_get_tlb_flush_fifo(vcpu, is_guest_mode(vcpu)); + + kfifo_reset_out(&tlb_flush_fifo->entries); +} + +static inline bool guest_hv_cpuid_has_l2_tlb_flush(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + return hv_vcpu && + (hv_vcpu->cpuid_cache.nested_eax & HV_X64_NESTED_DIRECT_FLUSH); +} + +static inline bool kvm_hv_is_tlb_flush_hcall(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + u16 code; + + if (!hv_vcpu) + return false; + + code = is_64_bit_hypercall(vcpu) ? kvm_rcx_read(vcpu) : + kvm_rax_read(vcpu); + + return (code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE || + code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST || + code == HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX || + code == HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX); +} + +static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu) +{ + if (!to_hv_vcpu(vcpu)) + return 0; + + if (!kvm_hv_assist_page_enabled(vcpu)) + return 0; + + return kvm_hv_get_assist_page(vcpu); +} + +int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu); + #endif diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index f371f1292ca3..a70952eca905 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -31,7 +31,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu) return r; } -EXPORT_SYMBOL(kvm_cpu_has_pending_timer); /* * check if there is a pending userspace external interrupt @@ -150,7 +149,6 @@ void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) if (kvm_xen_timer_enabled(vcpu)) kvm_xen_inject_timer_irqs(vcpu); } -EXPORT_SYMBOL_GPL(kvm_inject_pending_timer_irqs); void __kvm_migrate_timers(struct kvm_vcpu *vcpu) { @@ -165,3 +163,8 @@ bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args) return resample ? irqchip_kernel(kvm) : irqchip_in_kernel(kvm); } + +bool kvm_arch_irqchip_in_kernel(struct kvm *kvm) +{ + return irqchip_in_kernel(kvm); +} diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 3febc342360c..c09174f73a34 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -200,9 +200,4 @@ static inline bool is_guest_mode(struct kvm_vcpu *vcpu) return vcpu->arch.hflags & HF_GUEST_MASK; } -static inline bool is_smm(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.hflags & HF_SMM_MASK; -} - #endif diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 89246446d6aa..2d9662be8333 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -117,16 +117,6 @@ struct x86_emulate_ops { struct x86_exception *fault, bool system); /* - * read_phys: Read bytes of standard (non-emulated/special) memory. - * Used for descriptor reading. - * @addr: [IN ] Physical address from which to read. - * @val: [OUT] Value read from memory. - * @bytes: [IN ] Number of bytes to read from memory. - */ - int (*read_phys)(struct x86_emulate_ctxt *ctxt, unsigned long addr, - void *val, unsigned int bytes); - - /* * write_std: Write bytes of standard (non-emulated/special) memory. * Used for descriptor writing. * @addr: [IN ] Linear address to which to write. @@ -209,11 +199,8 @@ struct x86_emulate_ops { int (*cpl)(struct x86_emulate_ctxt *ctxt); void (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); - u64 (*get_smbase)(struct x86_emulate_ctxt *ctxt); - void (*set_smbase)(struct x86_emulate_ctxt *ctxt, u64 smbase); int (*set_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data); int (*get_msr_with_filter)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); - int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data); int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc); int (*read_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata); @@ -234,8 +221,7 @@ struct x86_emulate_ops { void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked); unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt); - void (*exiting_smm)(struct x86_emulate_ctxt *ctxt); - int (*leave_smm)(struct x86_emulate_ctxt *ctxt, const char *smstate); + int (*leave_smm)(struct x86_emulate_ctxt *ctxt); void (*triple_fault)(struct x86_emulate_ctxt *ctxt); int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr); }; @@ -292,7 +278,6 @@ enum x86emul_mode { /* These match some of the HF_* flags defined in kvm_host.h */ #define X86EMUL_GUEST_MASK (1 << 5) /* VCPU is in guest-mode */ #define X86EMUL_SMM_MASK (1 << 6) -#define X86EMUL_SMM_INSIDE_NMI_MASK (1 << 7) /* * fastop functions are declared as taking a never-defined fastop parameter, @@ -526,4 +511,35 @@ void emulator_invalidate_register_cache(struct x86_emulate_ctxt *ctxt); void emulator_writeback_register_cache(struct x86_emulate_ctxt *ctxt); bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt); +static inline ulong reg_read(struct x86_emulate_ctxt *ctxt, unsigned nr) +{ + if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt)) + nr &= NR_EMULATOR_GPRS - 1; + + if (!(ctxt->regs_valid & (1 << nr))) { + ctxt->regs_valid |= 1 << nr; + ctxt->_regs[nr] = ctxt->ops->read_gpr(ctxt, nr); + } + return ctxt->_regs[nr]; +} + +static inline ulong *reg_write(struct x86_emulate_ctxt *ctxt, unsigned nr) +{ + if (KVM_EMULATOR_BUG_ON(nr >= NR_EMULATOR_GPRS, ctxt)) + nr &= NR_EMULATOR_GPRS - 1; + + BUILD_BUG_ON(sizeof(ctxt->regs_dirty) * BITS_PER_BYTE < NR_EMULATOR_GPRS); + BUILD_BUG_ON(sizeof(ctxt->regs_valid) * BITS_PER_BYTE < NR_EMULATOR_GPRS); + + ctxt->regs_valid |= 1 << nr; + ctxt->regs_dirty |= 1 << nr; + return &ctxt->_regs[nr]; +} + +static inline ulong *reg_rmw(struct x86_emulate_ctxt *ctxt, unsigned nr) +{ + reg_read(ctxt, nr); + return reg_write(ctxt, nr); +} + #endif /* _ASM_X86_KVM_X86_EMULATE_H */ diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index d7639d126e6c..4efdb4a4d72c 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -42,6 +42,7 @@ #include "x86.h" #include "cpuid.h" #include "hyperv.h" +#include "smm.h" #ifndef CONFIG_X86_64 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y)) @@ -159,7 +160,6 @@ bool kvm_can_use_hv_timer(struct kvm_vcpu *vcpu) && !(kvm_mwait_in_guest(vcpu->kvm) || kvm_can_post_timer_interrupt(vcpu)); } -EXPORT_SYMBOL_GPL(kvm_can_use_hv_timer); static bool kvm_use_posted_timer_interrupt(struct kvm_vcpu *vcpu) { @@ -1170,9 +1170,10 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode, break; case APIC_DM_SMI: - result = 1; - kvm_make_request(KVM_REQ_SMI, vcpu); - kvm_vcpu_kick(vcpu); + if (!kvm_inject_smi(vcpu)) { + kvm_vcpu_kick(vcpu); + result = 1; + } break; case APIC_DM_NMI: @@ -1912,7 +1913,6 @@ bool kvm_lapic_hv_timer_in_use(struct kvm_vcpu *vcpu) return vcpu->arch.apic->lapic_timer.hv_timer_in_use; } -EXPORT_SYMBOL_GPL(kvm_lapic_hv_timer_in_use); static void cancel_hv_timer(struct kvm_lapic *apic) { @@ -2430,7 +2430,6 @@ void kvm_apic_update_apicv(struct kvm_vcpu *vcpu) apic->isr_count = count_vectors(apic->regs + APIC_ISR); } } -EXPORT_SYMBOL_GPL(kvm_apic_update_apicv); void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) { @@ -2722,8 +2721,6 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu, icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR); __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32); } - } else { - kvm_lapic_xapic_id_updated(vcpu->arch.apic); } return 0; @@ -2759,6 +2756,9 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) } memcpy(vcpu->arch.apic->regs, s->regs, sizeof(*s)); + if (!apic_x2apic_mode(apic)) + kvm_lapic_xapic_id_updated(apic); + atomic_set_release(&apic->vcpu->kvm->arch.apic_map_dirty, DIRTY); kvm_recalculate_apic_map(vcpu->kvm); kvm_apic_set_version(vcpu); diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index a5ac4a5a5179..28e3769066e2 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -7,7 +7,7 @@ #include <linux/kvm_host.h> #include "hyperv.h" -#include "kvm_cache_regs.h" +#include "smm.h" #define KVM_APIC_INIT 0 #define KVM_APIC_SIPI 1 diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 1ccb769f62af..835426254e76 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -22,6 +22,7 @@ #include "tdp_mmu.h" #include "x86.h" #include "kvm_cache_regs.h" +#include "smm.h" #include "kvm_emulate.h" #include "cpuid.h" #include "spte.h" @@ -802,15 +803,31 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_flush_remote_tlbs_with_address(kvm, gfn, 1); } -void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) { - if (sp->lpage_disallowed) + /* + * If it's possible to replace the shadow page with an NX huge page, + * i.e. if the shadow page is the only thing currently preventing KVM + * from using a huge page, add the shadow page to the list of "to be + * zapped for NX recovery" pages. Note, the shadow page can already be + * on the list if KVM is reusing an existing shadow page, i.e. if KVM + * links a shadow page at multiple points. + */ + if (!list_empty(&sp->possible_nx_huge_page_link)) return; ++kvm->stat.nx_lpage_splits; - list_add_tail(&sp->lpage_disallowed_link, - &kvm->arch.lpage_disallowed_mmu_pages); - sp->lpage_disallowed = true; + list_add_tail(&sp->possible_nx_huge_page_link, + &kvm->arch.possible_nx_huge_pages); +} + +static void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp, + bool nx_huge_page_possible) +{ + sp->nx_huge_page_disallowed = true; + + if (nx_huge_page_possible) + track_possible_nx_huge_page(kvm, sp); } static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) @@ -830,11 +847,20 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_allow_lpage(slot, gfn); } -void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp) +void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) { + if (list_empty(&sp->possible_nx_huge_page_link)) + return; + --kvm->stat.nx_lpage_splits; - sp->lpage_disallowed = false; - list_del(&sp->lpage_disallowed_link); + list_del_init(&sp->possible_nx_huge_page_link); +} + +static void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) +{ + sp->nx_huge_page_disallowed = false; + + untrack_possible_nx_huge_page(kvm, sp); } static struct kvm_memory_slot * @@ -1645,7 +1671,7 @@ static int is_empty_shadow_page(u64 *spt) u64 *pos; u64 *end; - for (pos = spt, end = pos + PAGE_SIZE / sizeof(u64); pos != end; pos++) + for (pos = spt, end = pos + SPTE_ENT_PER_PAGE; pos != end; pos++) if (is_shadow_present_pte(*pos)) { printk(KERN_ERR "%s: %p %llx\n", __func__, pos, *pos); @@ -1793,7 +1819,7 @@ static int __mmu_unsync_walk(struct kvm_mmu_page *sp, continue; } - child = to_shadow_page(ent & SPTE_BASE_ADDR_MASK); + child = spte_to_child_sp(ent); if (child->unsync_children) { if (mmu_pages_add(pvec, child, i)) @@ -1894,7 +1920,7 @@ static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp) if (sp->role.invalid) return true; - /* TDP MMU pages due not use the MMU generation. */ + /* TDP MMU pages do not use the MMU generation. */ return !sp->tdp_mmu_page && unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen); } @@ -2129,6 +2155,8 @@ static struct kvm_mmu_page *kvm_mmu_alloc_shadow_page(struct kvm *kvm, set_page_private(virt_to_page(sp->spt), (unsigned long)sp); + INIT_LIST_HEAD(&sp->possible_nx_huge_page_link); + /* * active_mmu_pages must be a FIFO list, as kvm_zap_obsolete_pages() * depends on valid pages being added to the head of the list. See @@ -2350,7 +2378,7 @@ static void validate_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, * so we should update the spte at this point to get * a new sp with the correct access. */ - child = to_shadow_page(*sptep & SPTE_BASE_ADDR_MASK); + child = spte_to_child_sp(*sptep); if (child->role.access == direct_access) return; @@ -2371,7 +2399,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp, if (is_last_spte(pte, sp->role.level)) { drop_spte(kvm, spte); } else { - child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK); + child = spte_to_child_sp(pte); drop_parent_pte(child, spte); /* @@ -2443,6 +2471,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, { bool list_unstable, zapped_root = false; + lockdep_assert_held_write(&kvm->mmu_lock); trace_kvm_mmu_prepare_zap_page(sp); ++kvm->stat.mmu_shadow_zapped; *nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list); @@ -2486,8 +2515,8 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, zapped_root = !is_obsolete_sp(kvm, sp); } - if (sp->lpage_disallowed) - unaccount_huge_nx_page(kvm, sp); + if (sp->nx_huge_page_disallowed) + unaccount_nx_huge_page(kvm, sp); sp->role.invalid = 1; @@ -2810,7 +2839,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot, struct kvm_mmu_page *child; u64 pte = *sptep; - child = to_shadow_page(pte & SPTE_BASE_ADDR_MASK); + child = spte_to_child_sp(pte); drop_parent_pte(child, sptep); flush = true; } else if (pfn != spte_to_pfn(*sptep)) { @@ -3084,7 +3113,8 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_ if (cur_level > PG_LEVEL_4K && cur_level == fault->goal_level && is_shadow_present_pte(spte) && - !is_large_pte(spte)) { + !is_large_pte(spte) && + spte_to_child_sp(spte)->nx_huge_page_disallowed) { /* * A small SPTE exists for this pfn, but FNAME(fetch) * and __direct_map would like to create a large PTE @@ -3126,9 +3156,9 @@ static int __direct_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) continue; link_shadow_page(vcpu, it.sptep, sp); - if (fault->is_tdp && fault->huge_page_disallowed && - fault->req_level >= it.level) - account_huge_nx_page(vcpu->kvm, sp); + if (fault->huge_page_disallowed) + account_nx_huge_page(vcpu->kvm, sp, + fault->req_level >= it.level); } if (WARN_ON_ONCE(it.level != fault->goal_level)) @@ -3148,8 +3178,13 @@ static void kvm_send_hwpoison_signal(unsigned long address, struct task_struct * send_sig_mceerr(BUS_MCEERR_AR, (void __user *)address, PAGE_SHIFT, tsk); } -static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) +static int kvm_handle_error_pfn(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn) { + if (is_sigpending_pfn(pfn)) { + kvm_handle_signal_exit(vcpu); + return -EINTR; + } + /* * Do not cache the mmio info caused by writing the readonly gfn * into the spte otherwise read access on readonly gfn also can @@ -3171,7 +3206,7 @@ static int handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fau { /* The pfn is invalid, report the error! */ if (unlikely(is_error_pfn(fault->pfn))) - return kvm_handle_bad_page(vcpu, fault->gfn, fault->pfn); + return kvm_handle_error_pfn(vcpu, fault->gfn, fault->pfn); if (unlikely(!fault->slot)) { gva_t gva = fault->is_tdp ? 0 : fault->addr; @@ -3422,7 +3457,11 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, if (!VALID_PAGE(*root_hpa)) return; - sp = to_shadow_page(*root_hpa & SPTE_BASE_ADDR_MASK); + /* + * The "root" may be a special root, e.g. a PAE entry, treat it as a + * SPTE to ensure any non-PA bits are dropped. + */ + sp = spte_to_child_sp(*root_hpa); if (WARN_ON(!sp)) return; @@ -3907,8 +3946,7 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) hpa_t root = vcpu->arch.mmu->pae_root[i]; if (IS_VALID_PAE_ROOT(root)) { - root &= SPTE_BASE_ADDR_MASK; - sp = to_shadow_page(root); + sp = spte_to_child_sp(root); mmu_sync_children(vcpu, sp, true); } } @@ -4169,7 +4207,7 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) } async = false; - fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async, + fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, fault->write, &fault->map_writable, &fault->hva); if (!async) @@ -4186,7 +4224,12 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) } } - fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, NULL, + /* + * Allow gup to bail on pending non-fatal signals when it's also allowed + * to wait for IO. Note, gup always bails if it is unable to quickly + * get a page and a fatal signal, i.e. SIGKILL, is pending. + */ + fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, true, NULL, fault->write, &fault->map_writable, &fault->hva); return RET_PF_CONTINUE; @@ -4262,14 +4305,14 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (is_page_fault_stale(vcpu, fault, mmu_seq)) goto out_unlock; - r = make_mmu_pages_available(vcpu); - if (r) - goto out_unlock; - - if (is_tdp_mmu_fault) + if (is_tdp_mmu_fault) { r = kvm_tdp_mmu_map(vcpu, fault); - else + } else { + r = make_mmu_pages_available(vcpu); + if (r) + goto out_unlock; r = __direct_map(vcpu, fault); + } out_unlock: if (is_tdp_mmu_fault) @@ -5971,7 +6014,7 @@ int kvm_mmu_init_vm(struct kvm *kvm) INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages); - INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages); + INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); r = kvm_mmu_init_tdp_mmu(kvm); @@ -6656,7 +6699,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) kvm_mmu_zap_all_fast(kvm); mutex_unlock(&kvm->slots_lock); - wake_up_process(kvm->arch.nx_lpage_recovery_thread); + wake_up_process(kvm->arch.nx_huge_page_recovery_thread); } mutex_unlock(&kvm_lock); } @@ -6788,7 +6831,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) - wake_up_process(kvm->arch.nx_lpage_recovery_thread); + wake_up_process(kvm->arch.nx_huge_page_recovery_thread); mutex_unlock(&kvm_lock); } @@ -6796,9 +6839,10 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel return err; } -static void kvm_recover_nx_lpages(struct kvm *kvm) +static void kvm_recover_nx_huge_pages(struct kvm *kvm) { unsigned long nx_lpage_splits = kvm->stat.nx_lpage_splits; + struct kvm_memory_slot *slot; int rcu_idx; struct kvm_mmu_page *sp; unsigned int ratio; @@ -6819,24 +6863,55 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) ratio = READ_ONCE(nx_huge_pages_recovery_ratio); to_zap = ratio ? DIV_ROUND_UP(nx_lpage_splits, ratio) : 0; for ( ; to_zap; --to_zap) { - if (list_empty(&kvm->arch.lpage_disallowed_mmu_pages)) + if (list_empty(&kvm->arch.possible_nx_huge_pages)) break; /* * We use a separate list instead of just using active_mmu_pages - * because the number of lpage_disallowed pages is expected to - * be relatively small compared to the total. + * because the number of shadow pages that be replaced with an + * NX huge page is expected to be relatively small compared to + * the total number of shadow pages. And because the TDP MMU + * doesn't use active_mmu_pages. */ - sp = list_first_entry(&kvm->arch.lpage_disallowed_mmu_pages, + sp = list_first_entry(&kvm->arch.possible_nx_huge_pages, struct kvm_mmu_page, - lpage_disallowed_link); - WARN_ON_ONCE(!sp->lpage_disallowed); - if (is_tdp_mmu_page(sp)) { + possible_nx_huge_page_link); + WARN_ON_ONCE(!sp->nx_huge_page_disallowed); + WARN_ON_ONCE(!sp->role.direct); + + /* + * Unaccount and do not attempt to recover any NX Huge Pages + * that are being dirty tracked, as they would just be faulted + * back in as 4KiB pages. The NX Huge Pages in this slot will be + * recovered, along with all the other huge pages in the slot, + * when dirty logging is disabled. + * + * Since gfn_to_memslot() is relatively expensive, it helps to + * skip it if it the test cannot possibly return true. On the + * other hand, if any memslot has logging enabled, chances are + * good that all of them do, in which case unaccount_nx_huge_page() + * is much cheaper than zapping the page. + * + * If a memslot update is in progress, reading an incorrect value + * of kvm->nr_memslots_dirty_logging is not a problem: if it is + * becoming zero, gfn_to_memslot() will be done unnecessarily; if + * it is becoming nonzero, the page will be zapped unnecessarily. + * Either way, this only affects efficiency in racy situations, + * and not correctness. + */ + slot = NULL; + if (atomic_read(&kvm->nr_memslots_dirty_logging)) { + slot = gfn_to_memslot(kvm, sp->gfn); + WARN_ON_ONCE(!slot); + } + + if (slot && kvm_slot_dirty_track_enabled(slot)) + unaccount_nx_huge_page(kvm, sp); + else if (is_tdp_mmu_page(sp)) flush |= kvm_tdp_mmu_zap_sp(kvm, sp); - } else { + else kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); - WARN_ON_ONCE(sp->lpage_disallowed); - } + WARN_ON_ONCE(sp->nx_huge_page_disallowed); if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); @@ -6856,7 +6931,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) srcu_read_unlock(&kvm->srcu, rcu_idx); } -static long get_nx_lpage_recovery_timeout(u64 start_time) +static long get_nx_huge_page_recovery_timeout(u64 start_time) { bool enabled; uint period; @@ -6867,19 +6942,19 @@ static long get_nx_lpage_recovery_timeout(u64 start_time) : MAX_SCHEDULE_TIMEOUT; } -static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) +static int kvm_nx_huge_page_recovery_worker(struct kvm *kvm, uintptr_t data) { u64 start_time; long remaining_time; while (true) { start_time = get_jiffies_64(); - remaining_time = get_nx_lpage_recovery_timeout(start_time); + remaining_time = get_nx_huge_page_recovery_timeout(start_time); set_current_state(TASK_INTERRUPTIBLE); while (!kthread_should_stop() && remaining_time > 0) { schedule_timeout(remaining_time); - remaining_time = get_nx_lpage_recovery_timeout(start_time); + remaining_time = get_nx_huge_page_recovery_timeout(start_time); set_current_state(TASK_INTERRUPTIBLE); } @@ -6888,7 +6963,7 @@ static int kvm_nx_lpage_recovery_worker(struct kvm *kvm, uintptr_t data) if (kthread_should_stop()) return 0; - kvm_recover_nx_lpages(kvm); + kvm_recover_nx_huge_pages(kvm); } } @@ -6896,17 +6971,17 @@ int kvm_mmu_post_init_vm(struct kvm *kvm) { int err; - err = kvm_vm_create_worker_thread(kvm, kvm_nx_lpage_recovery_worker, 0, + err = kvm_vm_create_worker_thread(kvm, kvm_nx_huge_page_recovery_worker, 0, "kvm-nx-lpage-recovery", - &kvm->arch.nx_lpage_recovery_thread); + &kvm->arch.nx_huge_page_recovery_thread); if (!err) - kthread_unpark(kvm->arch.nx_lpage_recovery_thread); + kthread_unpark(kvm->arch.nx_huge_page_recovery_thread); return err; } void kvm_mmu_pre_destroy_vm(struct kvm *kvm) { - if (kvm->arch.nx_lpage_recovery_thread) - kthread_stop(kvm->arch.nx_lpage_recovery_thread); + if (kvm->arch.nx_huge_page_recovery_thread) + kthread_stop(kvm->arch.nx_huge_page_recovery_thread); } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 582def531d4d..dbaf6755c5a7 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -57,7 +57,13 @@ struct kvm_mmu_page { bool tdp_mmu_page; bool unsync; u8 mmu_valid_gen; - bool lpage_disallowed; /* Can't be replaced by an equiv large page */ + + /* + * The shadow page can't be replaced by an equivalent huge page + * because it is being used to map an executable page in the guest + * and the NX huge page mitigation is enabled. + */ + bool nx_huge_page_disallowed; /* * The following two entries are used to key the shadow page in the @@ -100,7 +106,14 @@ struct kvm_mmu_page { }; }; - struct list_head lpage_disallowed_link; + /* + * Tracks shadow pages that, if zapped, would allow KVM to create an NX + * huge page. A shadow page will have nx_huge_page_disallowed set but + * not be on the list if a huge page is disallowed for other reasons, + * e.g. because KVM is shadowing a PTE at the same gfn, the memslot + * isn't properly aligned, etc... + */ + struct list_head possible_nx_huge_page_link; #ifdef CONFIG_X86_32 /* * Used out of the mmu-lock to avoid reading spte values while an @@ -120,18 +133,6 @@ struct kvm_mmu_page { extern struct kmem_cache *mmu_page_header_cache; -static inline struct kvm_mmu_page *to_shadow_page(hpa_t shadow_page) -{ - struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT); - - return (struct kvm_mmu_page *)page_private(page); -} - -static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep) -{ - return to_shadow_page(__pa(sptep)); -} - static inline int kvm_mmu_role_as_id(union kvm_mmu_page_role role) { return role.smm ? 1 : 0; @@ -315,7 +316,7 @@ void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_ void *mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc); -void account_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp); -void unaccount_huge_nx_page(struct kvm *kvm, struct kvm_mmu_page *sp); +void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp); +void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp); #endif /* __KVM_X86_MMU_INTERNAL_H */ diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 5ab5f94dcb6f..0f6455072055 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -713,9 +713,9 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, continue; link_shadow_page(vcpu, it.sptep, sp); - if (fault->huge_page_disallowed && - fault->req_level >= it.level) - account_huge_nx_page(vcpu->kvm, sp); + if (fault->huge_page_disallowed) + account_nx_huge_page(vcpu->kvm, sp, + fault->req_level >= it.level); } if (WARN_ON_ONCE(it.level != fault->goal_level)) diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index 2e08b2a45361..c0fd7e049b4e 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -161,6 +161,18 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, if (!prefetch) spte |= spte_shadow_accessed_mask(spte); + /* + * For simplicity, enforce the NX huge page mitigation even if not + * strictly necessary. KVM could ignore the mitigation if paging is + * disabled in the guest, as the guest doesn't have an page tables to + * abuse. But to safely ignore the mitigation, KVM would have to + * ensure a new MMU is loaded (or all shadow pages zapped) when CR0.PG + * is toggled on, and that's a net negative for performance when TDP is + * enabled. When TDP is disabled, KVM will always switch to a new MMU + * when CR0.PG is toggled, but leveraging that to ignore the mitigation + * would tie make_spte() further to vCPU/MMU state, and add complexity + * just to optimize a mode that is anything but performance critical. + */ if (level > PG_LEVEL_4K && (pte_access & ACC_EXEC_MASK) && is_nx_huge_page_enabled(vcpu->kvm)) { pte_access &= ~ACC_EXEC_MASK; diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index 7670c13ce251..1f03701b943a 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -188,7 +188,7 @@ extern u64 __read_mostly shadow_nonpresent_or_rsvd_mask; * should not modify the SPTE. * * Use a semi-arbitrary value that doesn't set RWX bits, i.e. is not-present on - * bot AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF + * both AMD and Intel CPUs, and doesn't set PFN bits, i.e. doesn't create a L1TF * vulnerability. Use only low bits to avoid 64-bit immediates. * * Only used by the TDP MMU. @@ -219,6 +219,23 @@ static inline int spte_index(u64 *sptep) */ extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask; +static inline struct kvm_mmu_page *to_shadow_page(hpa_t shadow_page) +{ + struct page *page = pfn_to_page((shadow_page) >> PAGE_SHIFT); + + return (struct kvm_mmu_page *)page_private(page); +} + +static inline struct kvm_mmu_page *spte_to_child_sp(u64 spte) +{ + return to_shadow_page(spte & SPTE_BASE_ADDR_MASK); +} + +static inline struct kvm_mmu_page *sptep_to_sp(u64 *sptep) +{ + return to_shadow_page(__pa(sptep)); +} + static inline bool is_mmio_spte(u64 spte) { return (spte & shadow_mmio_mask) == shadow_mmio_value && diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 672f0432d777..771210ce5181 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -29,7 +29,6 @@ int kvm_mmu_init_tdp_mmu(struct kvm *kvm) kvm->arch.tdp_mmu_enabled = true; INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots); spin_lock_init(&kvm->arch.tdp_mmu_pages_lock); - INIT_LIST_HEAD(&kvm->arch.tdp_mmu_pages); kvm->arch.tdp_mmu_zap_wq = wq; return 1; } @@ -54,7 +53,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) /* Also waits for any queued work items. */ destroy_workqueue(kvm->arch.tdp_mmu_zap_wq); - WARN_ON(!list_empty(&kvm->arch.tdp_mmu_pages)); + WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); /* @@ -284,6 +283,8 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu) static void tdp_mmu_init_sp(struct kvm_mmu_page *sp, tdp_ptep_t sptep, gfn_t gfn, union kvm_mmu_page_role role) { + INIT_LIST_HEAD(&sp->possible_nx_huge_page_link); + set_page_private(virt_to_page(sp->spt), (unsigned long)sp); sp->role = role; @@ -375,11 +376,13 @@ static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { kvm_account_pgtable_pages((void *)sp->spt, +1); + atomic64_inc(&kvm->arch.tdp_mmu_pages); } static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { kvm_account_pgtable_pages((void *)sp->spt, -1); + atomic64_dec(&kvm->arch.tdp_mmu_pages); } /** @@ -395,14 +398,17 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp, bool shared) { tdp_unaccount_mmu_page(kvm, sp); + + if (!sp->nx_huge_page_disallowed) + return; + if (shared) spin_lock(&kvm->arch.tdp_mmu_pages_lock); else lockdep_assert_held_write(&kvm->mmu_lock); - list_del(&sp->link); - if (sp->lpage_disallowed) - unaccount_huge_nx_page(kvm, sp); + sp->nx_huge_page_disallowed = false; + untrack_possible_nx_huge_page(kvm, sp); if (shared) spin_unlock(&kvm->arch.tdp_mmu_pages_lock); @@ -1116,16 +1122,13 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu, * @kvm: kvm instance * @iter: a tdp_iter instance currently on the SPTE that should be set * @sp: The new TDP page table to install. - * @account_nx: True if this page table is being installed to split a - * non-executable huge page. * @shared: This operation is running under the MMU lock in read mode. * * Returns: 0 if the new page table was installed. Non-0 if the page table * could not be installed (e.g. the atomic compare-exchange failed). */ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter, - struct kvm_mmu_page *sp, bool account_nx, - bool shared) + struct kvm_mmu_page *sp, bool shared) { u64 spte = make_nonleaf_spte(sp->spt, !kvm_ad_enabled()); int ret = 0; @@ -1138,16 +1141,14 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter, tdp_mmu_set_spte(kvm, iter, spte); } - spin_lock(&kvm->arch.tdp_mmu_pages_lock); - list_add(&sp->link, &kvm->arch.tdp_mmu_pages); - if (account_nx) - account_huge_nx_page(kvm, sp); - spin_unlock(&kvm->arch.tdp_mmu_pages_lock); tdp_account_mmu_page(kvm, sp); return 0; } +static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, + struct kvm_mmu_page *sp, bool shared); + /* * Handle a TDP page fault (NPT/EPT violation/misconfiguration) by installing * page tables and SPTEs to translate the faulting guest physical address. @@ -1155,9 +1156,10 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter, int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_mmu *mmu = vcpu->arch.mmu; + struct kvm *kvm = vcpu->kvm; struct tdp_iter iter; struct kvm_mmu_page *sp; - int ret; + int ret = RET_PF_RETRY; kvm_mmu_hugepage_adjust(vcpu, fault); @@ -1166,6 +1168,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) rcu_read_lock(); tdp_mmu_for_each_pte(iter, mmu, fault->gfn, fault->gfn + 1) { + int r; + if (fault->nx_huge_page_workaround_enabled) disallowed_hugepage_adjust(fault, iter.old_spte, iter.level); @@ -1173,57 +1177,52 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) break; /* - * If there is an SPTE mapping a large page at a higher level - * than the target, that SPTE must be cleared and replaced - * with a non-leaf SPTE. + * If SPTE has been frozen by another thread, just give up and + * retry, avoiding unnecessary page table allocation and free. */ - if (is_shadow_present_pte(iter.old_spte) && - is_large_pte(iter.old_spte)) { - if (tdp_mmu_zap_spte_atomic(vcpu->kvm, &iter)) - break; + if (is_removed_spte(iter.old_spte)) + goto retry; - /* - * The iter must explicitly re-read the spte here - * because the new value informs the !present - * path below. - */ - iter.old_spte = kvm_tdp_mmu_read_spte(iter.sptep); - } + /* Step down into the lower level page table if it exists. */ + if (is_shadow_present_pte(iter.old_spte) && + !is_large_pte(iter.old_spte)) + continue; - if (!is_shadow_present_pte(iter.old_spte)) { - bool account_nx = fault->huge_page_disallowed && - fault->req_level >= iter.level; + /* + * The SPTE is either non-present or points to a huge page that + * needs to be split. + */ + sp = tdp_mmu_alloc_sp(vcpu); + tdp_mmu_init_child_sp(sp, &iter); - /* - * If SPTE has been frozen by another thread, just - * give up and retry, avoiding unnecessary page table - * allocation and free. - */ - if (is_removed_spte(iter.old_spte)) - break; + sp->nx_huge_page_disallowed = fault->huge_page_disallowed; - sp = tdp_mmu_alloc_sp(vcpu); - tdp_mmu_init_child_sp(sp, &iter); + if (is_shadow_present_pte(iter.old_spte)) + r = tdp_mmu_split_huge_page(kvm, &iter, sp, true); + else + r = tdp_mmu_link_sp(kvm, &iter, sp, true); - if (tdp_mmu_link_sp(vcpu->kvm, &iter, sp, account_nx, true)) { - tdp_mmu_free_sp(sp); - break; - } + /* + * Also force the guest to retry the access if the upper level SPTEs + * aren't in place. + */ + if (r) { + tdp_mmu_free_sp(sp); + goto retry; } - } - /* - * Force the guest to retry the access if the upper level SPTEs aren't - * in place, or if the target leaf SPTE is frozen by another CPU. - */ - if (iter.level != fault->goal_level || is_removed_spte(iter.old_spte)) { - rcu_read_unlock(); - return RET_PF_RETRY; + if (fault->huge_page_disallowed && + fault->req_level >= iter.level) { + spin_lock(&kvm->arch.tdp_mmu_pages_lock); + track_possible_nx_huge_page(kvm, sp); + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); + } } ret = tdp_mmu_map_handle_target_level(vcpu, fault, &iter); - rcu_read_unlock(); +retry: + rcu_read_unlock(); return ret; } @@ -1472,6 +1471,7 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm, return sp; } +/* Note, the caller is responsible for initializing @sp. */ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, struct kvm_mmu_page *sp, bool shared) { @@ -1479,8 +1479,6 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, const int level = iter->level; int ret, i; - tdp_mmu_init_child_sp(sp, iter); - /* * No need for atomics when writing to sp->spt since the page table has * not been linked in yet and thus is not reachable from any other CPU. @@ -1496,7 +1494,7 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, * correctness standpoint since the translation will be the same either * way. */ - ret = tdp_mmu_link_sp(kvm, iter, sp, false, shared); + ret = tdp_mmu_link_sp(kvm, iter, sp, shared); if (ret) goto out; @@ -1556,6 +1554,8 @@ retry: continue; } + tdp_mmu_init_child_sp(sp, &iter); + if (tdp_mmu_split_huge_page(kvm, &iter, sp, shared)) goto retry; diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index c163f7cc23ca..d3714200b932 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -5,6 +5,8 @@ #include <linux/kvm_host.h> +#include "spte.h" + hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index de1fd7369736..684393c22105 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -101,10 +101,6 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) struct kvm_pmu *pmu = pmc_to_pmu(pmc); bool skip_pmi = false; - /* Ignore counters that have been reprogrammed already. */ - if (test_and_set_bit(pmc->idx, pmu->reprogram_pmi)) - return; - if (pmc->perf_event && pmc->perf_event->attr.precise_ip) { if (!in_pmi) { /* @@ -122,7 +118,6 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) } else { __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); } - kvm_make_request(KVM_REQ_PMU, pmc->vcpu); if (!pmc->intr || skip_pmi) return; @@ -147,12 +142,22 @@ static void kvm_perf_overflow(struct perf_event *perf_event, { struct kvm_pmc *pmc = perf_event->overflow_handler_context; + /* + * Ignore overflow events for counters that are scheduled to be + * reprogrammed, e.g. if a PMI for the previous event races with KVM's + * handling of a related guest WRMSR. + */ + if (test_and_set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi)) + return; + __kvm_perf_overflow(pmc, true); + + kvm_make_request(KVM_REQ_PMU, pmc->vcpu); } -static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, - u64 config, bool exclude_user, - bool exclude_kernel, bool intr) +static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, + bool exclude_user, bool exclude_kernel, + bool intr) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); struct perf_event *event; @@ -204,14 +209,14 @@ static void pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, if (IS_ERR(event)) { pr_debug_ratelimited("kvm_pmu: event creation failed %ld for pmc->idx = %d\n", PTR_ERR(event), pmc->idx); - return; + return PTR_ERR(event); } pmc->perf_event = event; pmc_to_pmu(pmc)->event_count++; - clear_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi); pmc->is_paused = false; pmc->intr = intr || pebs; + return 0; } static void pmc_pause_counter(struct kvm_pmc *pmc) @@ -245,7 +250,6 @@ static bool pmc_resume_counter(struct kvm_pmc *pmc) perf_event_enable(pmc->perf_event); pmc->is_paused = false; - clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi); return true; } @@ -293,7 +297,7 @@ out: return allow_event; } -void reprogram_counter(struct kvm_pmc *pmc) +static void reprogram_counter(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); u64 eventsel = pmc->eventsel; @@ -303,10 +307,13 @@ void reprogram_counter(struct kvm_pmc *pmc) pmc_pause_counter(pmc); if (!pmc_speculative_in_use(pmc) || !pmc_is_enabled(pmc)) - return; + goto reprogram_complete; if (!check_pmu_event_filter(pmc)) - return; + goto reprogram_complete; + + if (pmc->counter < pmc->prev_counter) + __kvm_perf_overflow(pmc, false); if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL) printk_once("kvm pmu: pin control bit is ignored\n"); @@ -324,18 +331,29 @@ void reprogram_counter(struct kvm_pmc *pmc) } if (pmc->current_config == new_config && pmc_resume_counter(pmc)) - return; + goto reprogram_complete; pmc_release_perf_event(pmc); pmc->current_config = new_config; - pmc_reprogram_counter(pmc, PERF_TYPE_RAW, - (eventsel & pmu->raw_event_mask), - !(eventsel & ARCH_PERFMON_EVENTSEL_USR), - !(eventsel & ARCH_PERFMON_EVENTSEL_OS), - eventsel & ARCH_PERFMON_EVENTSEL_INT); + + /* + * If reprogramming fails, e.g. due to contention, leave the counter's + * regprogram bit set, i.e. opportunistically try again on the next PMU + * refresh. Don't make a new request as doing so can stall the guest + * if reprogramming repeatedly fails. + */ + if (pmc_reprogram_counter(pmc, PERF_TYPE_RAW, + (eventsel & pmu->raw_event_mask), + !(eventsel & ARCH_PERFMON_EVENTSEL_USR), + !(eventsel & ARCH_PERFMON_EVENTSEL_OS), + eventsel & ARCH_PERFMON_EVENTSEL_INT)) + return; + +reprogram_complete: + clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi); + pmc->prev_counter = 0; } -EXPORT_SYMBOL_GPL(reprogram_counter); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) { @@ -345,10 +363,11 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) for_each_set_bit(bit, pmu->reprogram_pmi, X86_PMC_IDX_MAX) { struct kvm_pmc *pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, bit); - if (unlikely(!pmc || !pmc->perf_event)) { + if (unlikely(!pmc)) { clear_bit(bit, pmu->reprogram_pmi); continue; } + reprogram_counter(pmc); } @@ -522,14 +541,9 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu) static void kvm_pmu_incr_counter(struct kvm_pmc *pmc) { - u64 prev_count; - - prev_count = pmc->counter; + pmc->prev_counter = pmc->counter; pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc); - - reprogram_counter(pmc); - if (pmc->counter < prev_count) - __kvm_perf_overflow(pmc, false); + kvm_pmu_request_counter_reprogam(pmc); } static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc, @@ -542,12 +556,15 @@ static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc, static inline bool cpl_is_matched(struct kvm_pmc *pmc) { bool select_os, select_user; - u64 config = pmc->current_config; + u64 config; if (pmc_is_gp(pmc)) { + config = pmc->eventsel; select_os = config & ARCH_PERFMON_EVENTSEL_OS; select_user = config & ARCH_PERFMON_EVENTSEL_USR; } else { + config = fixed_ctrl_field(pmc_to_pmu(pmc)->fixed_ctr_ctrl, + pmc->idx - INTEL_PMC_IDX_FIXED); select_os = config & 0x1; select_user = config & 0x2; } @@ -577,6 +594,8 @@ EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event); int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) { struct kvm_pmu_event_filter tmp, *filter; + struct kvm_vcpu *vcpu; + unsigned long i; size_t size; int r; @@ -613,9 +632,18 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp) mutex_lock(&kvm->lock); filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter, mutex_is_locked(&kvm->lock)); + synchronize_srcu_expedited(&kvm->srcu); + + BUILD_BUG_ON(sizeof(((struct kvm_pmu *)0)->reprogram_pmi) > + sizeof(((struct kvm_pmu *)0)->__reprogram_pmi)); + + kvm_for_each_vcpu(i, vcpu, kvm) + atomic64_set(&vcpu_to_pmu(vcpu)->__reprogram_pmi, -1ull); + + kvm_make_all_cpus_request(kvm, KVM_REQ_PMU); + mutex_unlock(&kvm->lock); - synchronize_srcu_expedited(&kvm->srcu); r = 0; cleanup: kfree(filter); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 5cc5721f260b..85ff3c0588ba 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -183,7 +183,11 @@ static inline void kvm_init_pmu_capability(void) KVM_PMC_MAX_FIXED); } -void reprogram_counter(struct kvm_pmc *pmc); +static inline void kvm_pmu_request_counter_reprogam(struct kvm_pmc *pmc) +{ + set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi); + kvm_make_request(KVM_REQ_PMU, pmc->vcpu); +} void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index a19d473d0184..042d0aca3c92 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -7,22 +7,41 @@ #include <asm/cpufeatures.h> /* - * Hardware-defined CPUID leafs that are scattered in the kernel, but need to - * be directly used by KVM. Note, these word values conflict with the kernel's - * "bug" caps, but KVM doesn't use those. + * Hardware-defined CPUID leafs that are either scattered by the kernel or are + * unknown to the kernel, but need to be directly used by KVM. Note, these + * word values conflict with the kernel's "bug" caps, but KVM doesn't use those. */ enum kvm_only_cpuid_leafs { CPUID_12_EAX = NCAPINTS, + CPUID_7_1_EDX, NR_KVM_CPU_CAPS, NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, }; +/* + * Define a KVM-only feature flag. + * + * For features that are scattered by cpufeatures.h, __feature_translate() also + * needs to be updated to translate the kernel-defined feature into the + * KVM-defined feature. + * + * For features that are 100% KVM-only, i.e. not defined by cpufeatures.h, + * forego the intermediate KVM_X86_FEATURE and directly define X86_FEATURE_* so + * that X86_FEATURE_* can be used in KVM. No __feature_translate() handling is + * needed in this case. + */ #define KVM_X86_FEATURE(w, f) ((w)*32 + (f)) /* Intel-defined SGX sub-features, CPUID level 0x12 (EAX). */ #define KVM_X86_FEATURE_SGX1 KVM_X86_FEATURE(CPUID_12_EAX, 0) #define KVM_X86_FEATURE_SGX2 KVM_X86_FEATURE(CPUID_12_EAX, 1) +#define KVM_X86_FEATURE_SGX_EDECCSSA KVM_X86_FEATURE(CPUID_12_EAX, 11) + +/* Intel-defined sub-features, CPUID level 0x00000007:1 (EDX) */ +#define X86_FEATURE_AVX_VNNI_INT8 KVM_X86_FEATURE(CPUID_7_1_EDX, 4) +#define X86_FEATURE_AVX_NE_CONVERT KVM_X86_FEATURE(CPUID_7_1_EDX, 5) +#define X86_FEATURE_PREFETCHITI KVM_X86_FEATURE(CPUID_7_1_EDX, 14) struct cpuid_reg { u32 function; @@ -48,6 +67,7 @@ static const struct cpuid_reg reverse_cpuid[] = { [CPUID_7_1_EAX] = { 7, 1, CPUID_EAX}, [CPUID_12_EAX] = {0x00000012, 0, CPUID_EAX}, [CPUID_8000_001F_EAX] = {0x8000001f, 0, CPUID_EAX}, + [CPUID_7_1_EDX] = { 7, 1, CPUID_EDX}, }; /* @@ -78,6 +98,8 @@ static __always_inline u32 __feature_translate(int x86_feature) return KVM_X86_FEATURE_SGX1; else if (x86_feature == X86_FEATURE_SGX2) return KVM_X86_FEATURE_SGX2; + else if (x86_feature == X86_FEATURE_SGX_EDECCSSA) + return KVM_X86_FEATURE_SGX_EDECCSSA; return x86_feature; } diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c new file mode 100644 index 000000000000..a9c1c2af8d94 --- /dev/null +++ b/arch/x86/kvm/smm.c @@ -0,0 +1,649 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/kvm_host.h> +#include "x86.h" +#include "kvm_cache_regs.h" +#include "kvm_emulate.h" +#include "smm.h" +#include "cpuid.h" +#include "trace.h" + +#define CHECK_SMRAM32_OFFSET(field, offset) \ + ASSERT_STRUCT_OFFSET(struct kvm_smram_state_32, field, offset - 0xFE00) + +#define CHECK_SMRAM64_OFFSET(field, offset) \ + ASSERT_STRUCT_OFFSET(struct kvm_smram_state_64, field, offset - 0xFE00) + +static void check_smram_offsets(void) +{ + /* 32 bit SMRAM image */ + CHECK_SMRAM32_OFFSET(reserved1, 0xFE00); + CHECK_SMRAM32_OFFSET(smbase, 0xFEF8); + CHECK_SMRAM32_OFFSET(smm_revision, 0xFEFC); + CHECK_SMRAM32_OFFSET(io_inst_restart, 0xFF00); + CHECK_SMRAM32_OFFSET(auto_hlt_restart, 0xFF02); + CHECK_SMRAM32_OFFSET(io_restart_rdi, 0xFF04); + CHECK_SMRAM32_OFFSET(io_restart_rcx, 0xFF08); + CHECK_SMRAM32_OFFSET(io_restart_rsi, 0xFF0C); + CHECK_SMRAM32_OFFSET(io_restart_rip, 0xFF10); + CHECK_SMRAM32_OFFSET(cr4, 0xFF14); + CHECK_SMRAM32_OFFSET(reserved2, 0xFF18); + CHECK_SMRAM32_OFFSET(int_shadow, 0xFF1A); + CHECK_SMRAM32_OFFSET(reserved3, 0xFF1B); + CHECK_SMRAM32_OFFSET(ds, 0xFF2C); + CHECK_SMRAM32_OFFSET(fs, 0xFF38); + CHECK_SMRAM32_OFFSET(gs, 0xFF44); + CHECK_SMRAM32_OFFSET(idtr, 0xFF50); + CHECK_SMRAM32_OFFSET(tr, 0xFF5C); + CHECK_SMRAM32_OFFSET(gdtr, 0xFF6C); + CHECK_SMRAM32_OFFSET(ldtr, 0xFF78); + CHECK_SMRAM32_OFFSET(es, 0xFF84); + CHECK_SMRAM32_OFFSET(cs, 0xFF90); + CHECK_SMRAM32_OFFSET(ss, 0xFF9C); + CHECK_SMRAM32_OFFSET(es_sel, 0xFFA8); + CHECK_SMRAM32_OFFSET(cs_sel, 0xFFAC); + CHECK_SMRAM32_OFFSET(ss_sel, 0xFFB0); + CHECK_SMRAM32_OFFSET(ds_sel, 0xFFB4); + CHECK_SMRAM32_OFFSET(fs_sel, 0xFFB8); + CHECK_SMRAM32_OFFSET(gs_sel, 0xFFBC); + CHECK_SMRAM32_OFFSET(ldtr_sel, 0xFFC0); + CHECK_SMRAM32_OFFSET(tr_sel, 0xFFC4); + CHECK_SMRAM32_OFFSET(dr7, 0xFFC8); + CHECK_SMRAM32_OFFSET(dr6, 0xFFCC); + CHECK_SMRAM32_OFFSET(gprs, 0xFFD0); + CHECK_SMRAM32_OFFSET(eip, 0xFFF0); + CHECK_SMRAM32_OFFSET(eflags, 0xFFF4); + CHECK_SMRAM32_OFFSET(cr3, 0xFFF8); + CHECK_SMRAM32_OFFSET(cr0, 0xFFFC); + + /* 64 bit SMRAM image */ + CHECK_SMRAM64_OFFSET(es, 0xFE00); + CHECK_SMRAM64_OFFSET(cs, 0xFE10); + CHECK_SMRAM64_OFFSET(ss, 0xFE20); + CHECK_SMRAM64_OFFSET(ds, 0xFE30); + CHECK_SMRAM64_OFFSET(fs, 0xFE40); + CHECK_SMRAM64_OFFSET(gs, 0xFE50); + CHECK_SMRAM64_OFFSET(gdtr, 0xFE60); + CHECK_SMRAM64_OFFSET(ldtr, 0xFE70); + CHECK_SMRAM64_OFFSET(idtr, 0xFE80); + CHECK_SMRAM64_OFFSET(tr, 0xFE90); + CHECK_SMRAM64_OFFSET(io_restart_rip, 0xFEA0); + CHECK_SMRAM64_OFFSET(io_restart_rcx, 0xFEA8); + CHECK_SMRAM64_OFFSET(io_restart_rsi, 0xFEB0); + CHECK_SMRAM64_OFFSET(io_restart_rdi, 0xFEB8); + CHECK_SMRAM64_OFFSET(io_restart_dword, 0xFEC0); + CHECK_SMRAM64_OFFSET(reserved1, 0xFEC4); + CHECK_SMRAM64_OFFSET(io_inst_restart, 0xFEC8); + CHECK_SMRAM64_OFFSET(auto_hlt_restart, 0xFEC9); + CHECK_SMRAM64_OFFSET(amd_nmi_mask, 0xFECA); + CHECK_SMRAM64_OFFSET(int_shadow, 0xFECB); + CHECK_SMRAM64_OFFSET(reserved2, 0xFECC); + CHECK_SMRAM64_OFFSET(efer, 0xFED0); + CHECK_SMRAM64_OFFSET(svm_guest_flag, 0xFED8); + CHECK_SMRAM64_OFFSET(svm_guest_vmcb_gpa, 0xFEE0); + CHECK_SMRAM64_OFFSET(svm_guest_virtual_int, 0xFEE8); + CHECK_SMRAM64_OFFSET(reserved3, 0xFEF0); + CHECK_SMRAM64_OFFSET(smm_revison, 0xFEFC); + CHECK_SMRAM64_OFFSET(smbase, 0xFF00); + CHECK_SMRAM64_OFFSET(reserved4, 0xFF04); + CHECK_SMRAM64_OFFSET(ssp, 0xFF18); + CHECK_SMRAM64_OFFSET(svm_guest_pat, 0xFF20); + CHECK_SMRAM64_OFFSET(svm_host_efer, 0xFF28); + CHECK_SMRAM64_OFFSET(svm_host_cr4, 0xFF30); + CHECK_SMRAM64_OFFSET(svm_host_cr3, 0xFF38); + CHECK_SMRAM64_OFFSET(svm_host_cr0, 0xFF40); + CHECK_SMRAM64_OFFSET(cr4, 0xFF48); + CHECK_SMRAM64_OFFSET(cr3, 0xFF50); + CHECK_SMRAM64_OFFSET(cr0, 0xFF58); + CHECK_SMRAM64_OFFSET(dr7, 0xFF60); + CHECK_SMRAM64_OFFSET(dr6, 0xFF68); + CHECK_SMRAM64_OFFSET(rflags, 0xFF70); + CHECK_SMRAM64_OFFSET(rip, 0xFF78); + CHECK_SMRAM64_OFFSET(gprs, 0xFF80); + + BUILD_BUG_ON(sizeof(union kvm_smram) != 512); +} + +#undef CHECK_SMRAM64_OFFSET +#undef CHECK_SMRAM32_OFFSET + + +void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) +{ + BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); + + trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm); + + if (entering_smm) { + vcpu->arch.hflags |= HF_SMM_MASK; + } else { + vcpu->arch.hflags &= ~(HF_SMM_MASK | HF_SMM_INSIDE_NMI_MASK); + + /* Process a latched INIT or SMI, if any. */ + kvm_make_request(KVM_REQ_EVENT, vcpu); + + /* + * Even if KVM_SET_SREGS2 loaded PDPTRs out of band, + * on SMM exit we still need to reload them from + * guest memory + */ + vcpu->arch.pdptrs_from_userspace = false; + } + + kvm_mmu_reset_context(vcpu); +} + +void process_smi(struct kvm_vcpu *vcpu) +{ + vcpu->arch.smi_pending = true; + kvm_make_request(KVM_REQ_EVENT, vcpu); +} + +static u32 enter_smm_get_segment_flags(struct kvm_segment *seg) +{ + u32 flags = 0; + flags |= seg->g << 23; + flags |= seg->db << 22; + flags |= seg->l << 21; + flags |= seg->avl << 20; + flags |= seg->present << 15; + flags |= seg->dpl << 13; + flags |= seg->s << 12; + flags |= seg->type << 8; + return flags; +} + +static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, + struct kvm_smm_seg_state_32 *state, + u32 *selector, int n) +{ + struct kvm_segment seg; + + kvm_get_segment(vcpu, &seg, n); + *selector = seg.selector; + state->base = seg.base; + state->limit = seg.limit; + state->flags = enter_smm_get_segment_flags(&seg); +} + +#ifdef CONFIG_X86_64 +static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, + struct kvm_smm_seg_state_64 *state, + int n) +{ + struct kvm_segment seg; + + kvm_get_segment(vcpu, &seg, n); + state->selector = seg.selector; + state->attributes = enter_smm_get_segment_flags(&seg) >> 8; + state->limit = seg.limit; + state->base = seg.base; +} +#endif + +static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, + struct kvm_smram_state_32 *smram) +{ + struct desc_ptr dt; + unsigned long val; + int i; + + smram->cr0 = kvm_read_cr0(vcpu); + smram->cr3 = kvm_read_cr3(vcpu); + smram->eflags = kvm_get_rflags(vcpu); + smram->eip = kvm_rip_read(vcpu); + + for (i = 0; i < 8; i++) + smram->gprs[i] = kvm_register_read_raw(vcpu, i); + + kvm_get_dr(vcpu, 6, &val); + smram->dr6 = (u32)val; + kvm_get_dr(vcpu, 7, &val); + smram->dr7 = (u32)val; + + enter_smm_save_seg_32(vcpu, &smram->tr, &smram->tr_sel, VCPU_SREG_TR); + enter_smm_save_seg_32(vcpu, &smram->ldtr, &smram->ldtr_sel, VCPU_SREG_LDTR); + + static_call(kvm_x86_get_gdt)(vcpu, &dt); + smram->gdtr.base = dt.address; + smram->gdtr.limit = dt.size; + + static_call(kvm_x86_get_idt)(vcpu, &dt); + smram->idtr.base = dt.address; + smram->idtr.limit = dt.size; + + enter_smm_save_seg_32(vcpu, &smram->es, &smram->es_sel, VCPU_SREG_ES); + enter_smm_save_seg_32(vcpu, &smram->cs, &smram->cs_sel, VCPU_SREG_CS); + enter_smm_save_seg_32(vcpu, &smram->ss, &smram->ss_sel, VCPU_SREG_SS); + + enter_smm_save_seg_32(vcpu, &smram->ds, &smram->ds_sel, VCPU_SREG_DS); + enter_smm_save_seg_32(vcpu, &smram->fs, &smram->fs_sel, VCPU_SREG_FS); + enter_smm_save_seg_32(vcpu, &smram->gs, &smram->gs_sel, VCPU_SREG_GS); + + smram->cr4 = kvm_read_cr4(vcpu); + smram->smm_revision = 0x00020000; + smram->smbase = vcpu->arch.smbase; + + smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); +} + +#ifdef CONFIG_X86_64 +static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, + struct kvm_smram_state_64 *smram) +{ + struct desc_ptr dt; + unsigned long val; + int i; + + for (i = 0; i < 16; i++) + smram->gprs[15 - i] = kvm_register_read_raw(vcpu, i); + + smram->rip = kvm_rip_read(vcpu); + smram->rflags = kvm_get_rflags(vcpu); + + + kvm_get_dr(vcpu, 6, &val); + smram->dr6 = val; + kvm_get_dr(vcpu, 7, &val); + smram->dr7 = val; + + smram->cr0 = kvm_read_cr0(vcpu); + smram->cr3 = kvm_read_cr3(vcpu); + smram->cr4 = kvm_read_cr4(vcpu); + + smram->smbase = vcpu->arch.smbase; + smram->smm_revison = 0x00020064; + + smram->efer = vcpu->arch.efer; + + enter_smm_save_seg_64(vcpu, &smram->tr, VCPU_SREG_TR); + + static_call(kvm_x86_get_idt)(vcpu, &dt); + smram->idtr.limit = dt.size; + smram->idtr.base = dt.address; + + enter_smm_save_seg_64(vcpu, &smram->ldtr, VCPU_SREG_LDTR); + + static_call(kvm_x86_get_gdt)(vcpu, &dt); + smram->gdtr.limit = dt.size; + smram->gdtr.base = dt.address; + + enter_smm_save_seg_64(vcpu, &smram->es, VCPU_SREG_ES); + enter_smm_save_seg_64(vcpu, &smram->cs, VCPU_SREG_CS); + enter_smm_save_seg_64(vcpu, &smram->ss, VCPU_SREG_SS); + enter_smm_save_seg_64(vcpu, &smram->ds, VCPU_SREG_DS); + enter_smm_save_seg_64(vcpu, &smram->fs, VCPU_SREG_FS); + enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS); + + smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); +} +#endif + +void enter_smm(struct kvm_vcpu *vcpu) +{ + struct kvm_segment cs, ds; + struct desc_ptr dt; + unsigned long cr0; + union kvm_smram smram; + + check_smram_offsets(); + + memset(smram.bytes, 0, sizeof(smram.bytes)); + +#ifdef CONFIG_X86_64 + if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) + enter_smm_save_state_64(vcpu, &smram.smram64); + else +#endif + enter_smm_save_state_32(vcpu, &smram.smram32); + + /* + * Give enter_smm() a chance to make ISA-specific changes to the vCPU + * state (e.g. leave guest mode) after we've saved the state into the + * SMM state-save area. + * + * Kill the VM in the unlikely case of failure, because the VM + * can be in undefined state in this case. + */ + if (static_call(kvm_x86_enter_smm)(vcpu, &smram)) + goto error; + + kvm_smm_changed(vcpu, true); + + if (kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, &smram, sizeof(smram))) + goto error; + + if (static_call(kvm_x86_get_nmi_mask)(vcpu)) + vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; + else + static_call(kvm_x86_set_nmi_mask)(vcpu, true); + + kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); + kvm_rip_write(vcpu, 0x8000); + + static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0); + + cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); + static_call(kvm_x86_set_cr0)(vcpu, cr0); + vcpu->arch.cr0 = cr0; + + static_call(kvm_x86_set_cr4)(vcpu, 0); + + /* Undocumented: IDT limit is set to zero on entry to SMM. */ + dt.address = dt.size = 0; + static_call(kvm_x86_set_idt)(vcpu, &dt); + + if (WARN_ON_ONCE(kvm_set_dr(vcpu, 7, DR7_FIXED_1))) + goto error; + + cs.selector = (vcpu->arch.smbase >> 4) & 0xffff; + cs.base = vcpu->arch.smbase; + + ds.selector = 0; + ds.base = 0; + + cs.limit = ds.limit = 0xffffffff; + cs.type = ds.type = 0x3; + cs.dpl = ds.dpl = 0; + cs.db = ds.db = 0; + cs.s = ds.s = 1; + cs.l = ds.l = 0; + cs.g = ds.g = 1; + cs.avl = ds.avl = 0; + cs.present = ds.present = 1; + cs.unusable = ds.unusable = 0; + cs.padding = ds.padding = 0; + + kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_DS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_ES); + kvm_set_segment(vcpu, &ds, VCPU_SREG_FS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_GS); + kvm_set_segment(vcpu, &ds, VCPU_SREG_SS); + +#ifdef CONFIG_X86_64 + if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (static_call(kvm_x86_set_efer)(vcpu, 0)) + goto error; +#endif + + kvm_update_cpuid_runtime(vcpu); + kvm_mmu_reset_context(vcpu); + return; +error: + kvm_vm_dead(vcpu->kvm); +} + +static void rsm_set_desc_flags(struct kvm_segment *desc, u32 flags) +{ + desc->g = (flags >> 23) & 1; + desc->db = (flags >> 22) & 1; + desc->l = (flags >> 21) & 1; + desc->avl = (flags >> 20) & 1; + desc->present = (flags >> 15) & 1; + desc->dpl = (flags >> 13) & 3; + desc->s = (flags >> 12) & 1; + desc->type = (flags >> 8) & 15; + + desc->unusable = !desc->present; + desc->padding = 0; +} + +static int rsm_load_seg_32(struct kvm_vcpu *vcpu, + const struct kvm_smm_seg_state_32 *state, + u16 selector, int n) +{ + struct kvm_segment desc; + + desc.selector = selector; + desc.base = state->base; + desc.limit = state->limit; + rsm_set_desc_flags(&desc, state->flags); + kvm_set_segment(vcpu, &desc, n); + return X86EMUL_CONTINUE; +} + +#ifdef CONFIG_X86_64 + +static int rsm_load_seg_64(struct kvm_vcpu *vcpu, + const struct kvm_smm_seg_state_64 *state, + int n) +{ + struct kvm_segment desc; + + desc.selector = state->selector; + rsm_set_desc_flags(&desc, state->attributes << 8); + desc.limit = state->limit; + desc.base = state->base; + kvm_set_segment(vcpu, &desc, n); + return X86EMUL_CONTINUE; +} +#endif + +static int rsm_enter_protected_mode(struct kvm_vcpu *vcpu, + u64 cr0, u64 cr3, u64 cr4) +{ + int bad; + u64 pcid; + + /* In order to later set CR4.PCIDE, CR3[11:0] must be zero. */ + pcid = 0; + if (cr4 & X86_CR4_PCIDE) { + pcid = cr3 & 0xfff; + cr3 &= ~0xfff; + } + + bad = kvm_set_cr3(vcpu, cr3); + if (bad) + return X86EMUL_UNHANDLEABLE; + + /* + * First enable PAE, long mode needs it before CR0.PG = 1 is set. + * Then enable protected mode. However, PCID cannot be enabled + * if EFER.LMA=0, so set it separately. + */ + bad = kvm_set_cr4(vcpu, cr4 & ~X86_CR4_PCIDE); + if (bad) + return X86EMUL_UNHANDLEABLE; + + bad = kvm_set_cr0(vcpu, cr0); + if (bad) + return X86EMUL_UNHANDLEABLE; + + if (cr4 & X86_CR4_PCIDE) { + bad = kvm_set_cr4(vcpu, cr4); + if (bad) + return X86EMUL_UNHANDLEABLE; + if (pcid) { + bad = kvm_set_cr3(vcpu, cr3 | pcid); + if (bad) + return X86EMUL_UNHANDLEABLE; + } + + } + + return X86EMUL_CONTINUE; +} + +static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, + const struct kvm_smram_state_32 *smstate) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + struct desc_ptr dt; + int i, r; + + ctxt->eflags = smstate->eflags | X86_EFLAGS_FIXED; + ctxt->_eip = smstate->eip; + + for (i = 0; i < 8; i++) + *reg_write(ctxt, i) = smstate->gprs[i]; + + if (kvm_set_dr(vcpu, 6, smstate->dr6)) + return X86EMUL_UNHANDLEABLE; + if (kvm_set_dr(vcpu, 7, smstate->dr7)) + return X86EMUL_UNHANDLEABLE; + + rsm_load_seg_32(vcpu, &smstate->tr, smstate->tr_sel, VCPU_SREG_TR); + rsm_load_seg_32(vcpu, &smstate->ldtr, smstate->ldtr_sel, VCPU_SREG_LDTR); + + dt.address = smstate->gdtr.base; + dt.size = smstate->gdtr.limit; + static_call(kvm_x86_set_gdt)(vcpu, &dt); + + dt.address = smstate->idtr.base; + dt.size = smstate->idtr.limit; + static_call(kvm_x86_set_idt)(vcpu, &dt); + + rsm_load_seg_32(vcpu, &smstate->es, smstate->es_sel, VCPU_SREG_ES); + rsm_load_seg_32(vcpu, &smstate->cs, smstate->cs_sel, VCPU_SREG_CS); + rsm_load_seg_32(vcpu, &smstate->ss, smstate->ss_sel, VCPU_SREG_SS); + + rsm_load_seg_32(vcpu, &smstate->ds, smstate->ds_sel, VCPU_SREG_DS); + rsm_load_seg_32(vcpu, &smstate->fs, smstate->fs_sel, VCPU_SREG_FS); + rsm_load_seg_32(vcpu, &smstate->gs, smstate->gs_sel, VCPU_SREG_GS); + + vcpu->arch.smbase = smstate->smbase; + + r = rsm_enter_protected_mode(vcpu, smstate->cr0, + smstate->cr3, smstate->cr4); + + if (r != X86EMUL_CONTINUE) + return r; + + static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0); + ctxt->interruptibility = (u8)smstate->int_shadow; + + return r; +} + +#ifdef CONFIG_X86_64 +static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, + const struct kvm_smram_state_64 *smstate) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + struct desc_ptr dt; + int i, r; + + for (i = 0; i < 16; i++) + *reg_write(ctxt, i) = smstate->gprs[15 - i]; + + ctxt->_eip = smstate->rip; + ctxt->eflags = smstate->rflags | X86_EFLAGS_FIXED; + + if (kvm_set_dr(vcpu, 6, smstate->dr6)) + return X86EMUL_UNHANDLEABLE; + if (kvm_set_dr(vcpu, 7, smstate->dr7)) + return X86EMUL_UNHANDLEABLE; + + vcpu->arch.smbase = smstate->smbase; + + if (kvm_set_msr(vcpu, MSR_EFER, smstate->efer & ~EFER_LMA)) + return X86EMUL_UNHANDLEABLE; + + rsm_load_seg_64(vcpu, &smstate->tr, VCPU_SREG_TR); + + dt.size = smstate->idtr.limit; + dt.address = smstate->idtr.base; + static_call(kvm_x86_set_idt)(vcpu, &dt); + + rsm_load_seg_64(vcpu, &smstate->ldtr, VCPU_SREG_LDTR); + + dt.size = smstate->gdtr.limit; + dt.address = smstate->gdtr.base; + static_call(kvm_x86_set_gdt)(vcpu, &dt); + + r = rsm_enter_protected_mode(vcpu, smstate->cr0, smstate->cr3, smstate->cr4); + if (r != X86EMUL_CONTINUE) + return r; + + rsm_load_seg_64(vcpu, &smstate->es, VCPU_SREG_ES); + rsm_load_seg_64(vcpu, &smstate->cs, VCPU_SREG_CS); + rsm_load_seg_64(vcpu, &smstate->ss, VCPU_SREG_SS); + rsm_load_seg_64(vcpu, &smstate->ds, VCPU_SREG_DS); + rsm_load_seg_64(vcpu, &smstate->fs, VCPU_SREG_FS); + rsm_load_seg_64(vcpu, &smstate->gs, VCPU_SREG_GS); + + static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0); + ctxt->interruptibility = (u8)smstate->int_shadow; + + return X86EMUL_CONTINUE; +} +#endif + +int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) +{ + struct kvm_vcpu *vcpu = ctxt->vcpu; + unsigned long cr0; + union kvm_smram smram; + u64 smbase; + int ret; + + smbase = vcpu->arch.smbase; + + ret = kvm_vcpu_read_guest(vcpu, smbase + 0xfe00, smram.bytes, sizeof(smram)); + if (ret < 0) + return X86EMUL_UNHANDLEABLE; + + if ((vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK) == 0) + static_call(kvm_x86_set_nmi_mask)(vcpu, false); + + kvm_smm_changed(vcpu, false); + + /* + * Get back to real mode, to prepare a safe state in which to load + * CR0/CR3/CR4/EFER. It's all a bit more complicated if the vCPU + * supports long mode. + */ +#ifdef CONFIG_X86_64 + if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { + struct kvm_segment cs_desc; + unsigned long cr4; + + /* Zero CR4.PCIDE before CR0.PG. */ + cr4 = kvm_read_cr4(vcpu); + if (cr4 & X86_CR4_PCIDE) + kvm_set_cr4(vcpu, cr4 & ~X86_CR4_PCIDE); + + /* A 32-bit code segment is required to clear EFER.LMA. */ + memset(&cs_desc, 0, sizeof(cs_desc)); + cs_desc.type = 0xb; + cs_desc.s = cs_desc.g = cs_desc.present = 1; + kvm_set_segment(vcpu, &cs_desc, VCPU_SREG_CS); + } +#endif + + /* For the 64-bit case, this will clear EFER.LMA. */ + cr0 = kvm_read_cr0(vcpu); + if (cr0 & X86_CR0_PE) + kvm_set_cr0(vcpu, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); + +#ifdef CONFIG_X86_64 + if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { + unsigned long cr4, efer; + + /* Clear CR4.PAE before clearing EFER.LME. */ + cr4 = kvm_read_cr4(vcpu); + if (cr4 & X86_CR4_PAE) + kvm_set_cr4(vcpu, cr4 & ~X86_CR4_PAE); + + /* And finally go back to 32-bit mode. */ + efer = 0; + kvm_set_msr(vcpu, MSR_EFER, efer); + } +#endif + + /* + * Give leave_smm() a chance to make ISA-specific changes to the vCPU + * state (e.g. enter guest mode) before loading state from the SMM + * state-save area. + */ + if (static_call(kvm_x86_leave_smm)(vcpu, &smram)) + return X86EMUL_UNHANDLEABLE; + +#ifdef CONFIG_X86_64 + if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) + return rsm_load_state_64(ctxt, &smram.smram64); + else +#endif + return rsm_load_state_32(ctxt, &smram.smram32); +} diff --git a/arch/x86/kvm/smm.h b/arch/x86/kvm/smm.h new file mode 100644 index 000000000000..a1cf2ac5bd78 --- /dev/null +++ b/arch/x86/kvm/smm.h @@ -0,0 +1,168 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ASM_KVM_SMM_H +#define ASM_KVM_SMM_H + +#include <linux/build_bug.h> + +#ifdef CONFIG_KVM_SMM + + +/* + * 32 bit KVM's emulated SMM layout. Based on Intel P6 layout + * (https://www.sandpile.org/x86/smm.htm). + */ + +struct kvm_smm_seg_state_32 { + u32 flags; + u32 limit; + u32 base; +} __packed; + +struct kvm_smram_state_32 { + u32 reserved1[62]; + u32 smbase; + u32 smm_revision; + u16 io_inst_restart; + u16 auto_hlt_restart; + u32 io_restart_rdi; + u32 io_restart_rcx; + u32 io_restart_rsi; + u32 io_restart_rip; + u32 cr4; + + /* A20M#, CPL, shutdown and other reserved/undocumented fields */ + u16 reserved2; + u8 int_shadow; /* KVM extension */ + u8 reserved3[17]; + + struct kvm_smm_seg_state_32 ds; + struct kvm_smm_seg_state_32 fs; + struct kvm_smm_seg_state_32 gs; + struct kvm_smm_seg_state_32 idtr; /* IDTR has only base and limit */ + struct kvm_smm_seg_state_32 tr; + u32 reserved; + struct kvm_smm_seg_state_32 gdtr; /* GDTR has only base and limit */ + struct kvm_smm_seg_state_32 ldtr; + struct kvm_smm_seg_state_32 es; + struct kvm_smm_seg_state_32 cs; + struct kvm_smm_seg_state_32 ss; + + u32 es_sel; + u32 cs_sel; + u32 ss_sel; + u32 ds_sel; + u32 fs_sel; + u32 gs_sel; + u32 ldtr_sel; + u32 tr_sel; + + u32 dr7; + u32 dr6; + u32 gprs[8]; /* GPRS in the "natural" X86 order (EAX/ECX/EDX.../EDI) */ + u32 eip; + u32 eflags; + u32 cr3; + u32 cr0; +} __packed; + + +/* 64 bit KVM's emulated SMM layout. Based on AMD64 layout */ + +struct kvm_smm_seg_state_64 { + u16 selector; + u16 attributes; + u32 limit; + u64 base; +}; + +struct kvm_smram_state_64 { + + struct kvm_smm_seg_state_64 es; + struct kvm_smm_seg_state_64 cs; + struct kvm_smm_seg_state_64 ss; + struct kvm_smm_seg_state_64 ds; + struct kvm_smm_seg_state_64 fs; + struct kvm_smm_seg_state_64 gs; + struct kvm_smm_seg_state_64 gdtr; /* GDTR has only base and limit*/ + struct kvm_smm_seg_state_64 ldtr; + struct kvm_smm_seg_state_64 idtr; /* IDTR has only base and limit*/ + struct kvm_smm_seg_state_64 tr; + + /* I/O restart and auto halt restart are not implemented by KVM */ + u64 io_restart_rip; + u64 io_restart_rcx; + u64 io_restart_rsi; + u64 io_restart_rdi; + u32 io_restart_dword; + u32 reserved1; + u8 io_inst_restart; + u8 auto_hlt_restart; + u8 amd_nmi_mask; /* Documented in AMD BKDG as NMI mask, not used by KVM */ + u8 int_shadow; + u32 reserved2; + + u64 efer; + + /* + * Two fields below are implemented on AMD only, to store + * SVM guest vmcb address if the #SMI was received while in the guest mode. + */ + u64 svm_guest_flag; + u64 svm_guest_vmcb_gpa; + u64 svm_guest_virtual_int; /* unknown purpose, not implemented */ + + u32 reserved3[3]; + u32 smm_revison; + u32 smbase; + u32 reserved4[5]; + + /* ssp and svm_* fields below are not implemented by KVM */ + u64 ssp; + u64 svm_guest_pat; + u64 svm_host_efer; + u64 svm_host_cr4; + u64 svm_host_cr3; + u64 svm_host_cr0; + + u64 cr4; + u64 cr3; + u64 cr0; + u64 dr7; + u64 dr6; + u64 rflags; + u64 rip; + u64 gprs[16]; /* GPRS in a reversed "natural" X86 order (R15/R14/../RCX/RAX.) */ +}; + +union kvm_smram { + struct kvm_smram_state_64 smram64; + struct kvm_smram_state_32 smram32; + u8 bytes[512]; +}; + +static inline int kvm_inject_smi(struct kvm_vcpu *vcpu) +{ + kvm_make_request(KVM_REQ_SMI, vcpu); + return 0; +} + +static inline bool is_smm(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.hflags & HF_SMM_MASK; +} + +void kvm_smm_changed(struct kvm_vcpu *vcpu, bool in_smm); +void enter_smm(struct kvm_vcpu *vcpu); +int emulator_leave_smm(struct x86_emulate_ctxt *ctxt); +void process_smi(struct kvm_vcpu *vcpu); +#else +static inline int kvm_inject_smi(struct kvm_vcpu *vcpu) { return -ENOTTY; } +static inline bool is_smm(struct kvm_vcpu *vcpu) { return false; } + +/* + * emulator_leave_smm is used as a function pointer, so the + * stub is defined in x86.c. + */ +#endif + +#endif diff --git a/arch/x86/kvm/svm/hyperv.c b/arch/x86/kvm/svm/hyperv.c new file mode 100644 index 000000000000..088f6429b24c --- /dev/null +++ b/arch/x86/kvm/svm/hyperv.c @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AMD SVM specific code for Hyper-V on KVM. + * + * Copyright 2022 Red Hat, Inc. and/or its affiliates. + */ +#include "hyperv.h" + +void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + svm->vmcb->control.exit_code = HV_SVM_EXITCODE_ENL; + svm->vmcb->control.exit_code_hi = 0; + svm->vmcb->control.exit_info_1 = HV_SVM_ENL_EXITCODE_TRAP_AFTER_FLUSH; + svm->vmcb->control.exit_info_2 = 0; + nested_svm_vmexit(svm); +} diff --git a/arch/x86/kvm/svm/hyperv.h b/arch/x86/kvm/svm/hyperv.h index 7d6d97968fb9..02f4784b5d44 100644 --- a/arch/x86/kvm/svm/hyperv.h +++ b/arch/x86/kvm/svm/hyperv.h @@ -9,27 +9,37 @@ #include <asm/mshyperv.h> #include "../hyperv.h" +#include "svm.h" -/* - * Hyper-V uses the software reserved 32 bytes in VMCB - * control area to expose SVM enlightenments to guests. - */ -struct hv_enlightenments { - struct __packed hv_enlightenments_control { - u32 nested_flush_hypercall:1; - u32 msr_bitmap:1; - u32 enlightened_npt_tlb: 1; - u32 reserved:29; - } __packed hv_enlightenments_control; - u32 hv_vp_id; - u64 hv_vm_id; - u64 partition_assist_page; - u64 reserved; -} __packed; +static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); -/* - * Hyper-V uses the software reserved clean bit in VMCB - */ -#define VMCB_HV_NESTED_ENLIGHTENMENTS VMCB_SW + if (!hv_vcpu) + return; + + hv_vcpu->nested.pa_page_gpa = hve->partition_assist_page; + hv_vcpu->nested.vm_id = hve->hv_vm_id; + hv_vcpu->nested.vp_id = hve->hv_vp_id; +} + +static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + + if (!hv_vcpu) + return false; + + if (!hve->hv_enlightenments_control.nested_flush_hypercall) + return false; + + return hv_vcpu->vp_assist_page.nested_control.features.directhypercall; +} + +void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); #endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */ diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 4c620999d230..bc9cd7086fa9 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -25,6 +25,7 @@ #include "trace.h" #include "mmu.h" #include "x86.h" +#include "smm.h" #include "cpuid.h" #include "lapic.h" #include "svm.h" @@ -149,8 +150,12 @@ void recalc_intercepts(struct vcpu_svm *svm) vmcb_clr_intercept(c, INTERCEPT_VINTR); } - /* We don't want to see VMMCALLs from a nested guest */ - vmcb_clr_intercept(c, INTERCEPT_VMMCALL); + /* + * We want to see VMMCALLs from a nested guest only when Hyper-V L2 TLB + * flush feature is enabled. + */ + if (!nested_svm_l2_tlb_flush_enabled(&svm->vcpu)) + vmcb_clr_intercept(c, INTERCEPT_VMMCALL); for (i = 0; i < MAX_INTERCEPT; i++) c->intercepts[i] |= g->intercepts[i]; @@ -179,8 +184,7 @@ void recalc_intercepts(struct vcpu_svm *svm) */ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { - struct hv_enlightenments *hve = - (struct hv_enlightenments *)svm->nested.ctl.reserved_sw; + struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; int i; /* @@ -194,7 +198,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) if (!svm->nested.force_msr_bitmap_recalc && kvm_hv_hypercall_enabled(&svm->vcpu) && hve->hv_enlightenments_control.msr_bitmap && - (svm->nested.ctl.clean & BIT(VMCB_HV_NESTED_ENLIGHTENMENTS))) + (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS))) goto set_msrpm_base_pa; if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) @@ -369,8 +373,8 @@ void __nested_copy_vmcb_control_to_cache(struct kvm_vcpu *vcpu, /* Hyper-V extensions (Enlightened VMCB) */ if (kvm_hv_hypercall_enabled(vcpu)) { to->clean = from->clean; - memcpy(to->reserved_sw, from->reserved_sw, - sizeof(struct hv_enlightenments)); + memcpy(&to->hv_enlightenments, &from->hv_enlightenments, + sizeof(to->hv_enlightenments)); } } @@ -474,6 +478,15 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm, static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu) { /* + * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or + * L2's VP_ID upon request from the guest. Make sure we check for + * pending entries in the right FIFO upon L1/L2 transition as these + * requests are put by other vCPUs asynchronously. + */ + if (to_hv_vcpu(vcpu) && npt_enabled) + kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); + + /* * TODO: optimize unconditional TLB flush/MMU sync. A partial list of * things to fix before this can be conditional: * @@ -800,6 +813,8 @@ int enter_svm_guest_mode(struct kvm_vcpu *vcpu, u64 vmcb12_gpa, if (kvm_vcpu_apicv_active(vcpu)) kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + nested_svm_hv_update_vm_vp_ids(vcpu); + return 0; } @@ -822,6 +837,13 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu) return 1; } + /* This fails when VP assist page is enabled but the supplied GPA is bogus */ + ret = kvm_hv_verify_vp_assist(vcpu); + if (ret) { + kvm_inject_gp(vcpu, 0); + return ret; + } + vmcb12_gpa = svm->vmcb->save.rax; ret = kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map); if (ret == -EINVAL) { @@ -1091,6 +1113,12 @@ int nested_svm_vmexit(struct vcpu_svm *svm) static void nested_svm_triple_fault(struct kvm_vcpu *vcpu) { + struct vcpu_svm *svm = to_svm(vcpu); + + if (!vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_SHUTDOWN)) + return; + + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); nested_svm_simple_vmexit(to_svm(vcpu), SVM_EXIT_SHUTDOWN); } @@ -1125,6 +1153,9 @@ void svm_free_nested(struct vcpu_svm *svm) if (!svm->nested.initialized) return; + if (WARN_ON_ONCE(svm->vmcb != svm->vmcb01.ptr)) + svm_switch_vmcb(svm, &svm->vmcb01); + svm_vcpu_free_msrpm(svm->nested.msrpm); svm->nested.msrpm = NULL; @@ -1143,9 +1174,6 @@ void svm_free_nested(struct vcpu_svm *svm) svm->nested.initialized = false; } -/* - * Forcibly leave nested mode in order to be able to reset the VCPU later on. - */ void svm_leave_nested(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1377,6 +1405,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu) return 0; } +#ifdef CONFIG_KVM_SMM if (vcpu->arch.smi_pending && !svm_smi_blocked(vcpu)) { if (block_nested_events) return -EBUSY; @@ -1385,6 +1414,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu) nested_svm_simple_vmexit(svm, SVM_EXIT_SMI); return 0; } +#endif if (vcpu->arch.nmi_pending && !svm_nmi_blocked(vcpu)) { if (block_nested_events) @@ -1411,6 +1441,7 @@ static int svm_check_nested_events(struct kvm_vcpu *vcpu) int nested_svm_exit_special(struct vcpu_svm *svm) { u32 exit_code = svm->vmcb->control.exit_code; + struct kvm_vcpu *vcpu = &svm->vcpu; switch (exit_code) { case SVM_EXIT_INTR: @@ -1429,6 +1460,13 @@ int nested_svm_exit_special(struct vcpu_svm *svm) return NESTED_EXIT_HOST; break; } + case SVM_EXIT_VMMCALL: + /* Hyper-V L2 TLB flush hypercall is handled by L0 */ + if (guest_hv_cpuid_has_l2_tlb_flush(vcpu) && + nested_svm_l2_tlb_flush_enabled(vcpu) && + kvm_hv_is_tlb_flush_hcall(vcpu)) + return NESTED_EXIT_HOST; + break; default: break; } @@ -1479,7 +1517,7 @@ static void nested_copy_vmcb_cache_to_control(struct vmcb_control_area *dst, dst->virt_ext = from->virt_ext; dst->pause_filter_count = from->pause_filter_count; dst->pause_filter_thresh = from->pause_filter_thresh; - /* 'clean' and 'reserved_sw' are not changed by KVM */ + /* 'clean' and 'hv_enlightenments' are not changed by KVM */ } static int svm_get_nested_state(struct kvm_vcpu *vcpu, @@ -1709,6 +1747,9 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu) return false; } + if (kvm_hv_verify_vp_assist(vcpu)) + return false; + return true; } @@ -1720,4 +1761,5 @@ struct kvm_x86_nested_ops svm_nested_ops = { .get_nested_state_pages = svm_get_nested_state_pages, .get_state = svm_get_nested_state, .set_state = svm_set_nested_state, + .hv_inject_synthetic_vmexit_post_tlb_flush = svm_hv_inject_synthetic_vmexit_post_tlb_flush, }; diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 9d65cd095691..0e313fbae055 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -159,7 +159,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) data &= ~pmu->reserved_bits; if (data != pmc->eventsel) { pmc->eventsel = data; - reprogram_counter(pmc); + kvm_pmu_request_counter_reprogam(pmc); } return 0; } @@ -212,7 +212,7 @@ static void amd_pmu_reset(struct kvm_vcpu *vcpu) struct kvm_pmc *pmc = &pmu->gp_counters[i]; pmc_stop_counter(pmc); - pmc->counter = pmc->eventsel = 0; + pmc->counter = pmc->prev_counter = pmc->eventsel = 0; } } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index efaaef2b7ae1..86d6897f4806 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -465,9 +465,9 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages) return; for (i = 0; i < npages; i++) { - page_virtual = kmap_atomic(pages[i]); + page_virtual = kmap_local_page(pages[i]); clflush_cache_range(page_virtual, PAGE_SIZE); - kunmap_atomic(page_virtual); + kunmap_local(page_virtual); cond_resched(); } } @@ -2648,7 +2648,7 @@ static int setup_vmgexit_scratch(struct vcpu_svm *svm, bool sync, u64 len) ghcb_scratch_beg = control->ghcb_gpa + offsetof(struct ghcb, shared_buffer); ghcb_scratch_end = control->ghcb_gpa + - offsetof(struct ghcb, reserved_1); + offsetof(struct ghcb, reserved_0xff0); /* * If the scratch area begins within the GHCB, it must be diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 4b6d2b050e57..9a194aa1a75a 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -6,6 +6,7 @@ #include "mmu.h" #include "kvm_cache_regs.h" #include "x86.h" +#include "smm.h" #include "cpuid.h" #include "pmu.h" @@ -346,12 +347,6 @@ int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer) return 0; } -static int is_external_interrupt(u32 info) -{ - info &= SVM_EVTINJ_TYPE_MASK | SVM_EVTINJ_VALID; - return info == (SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR); -} - static u32 svm_get_interrupt_shadow(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1438,6 +1433,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) */ svm_clear_current_vmcb(svm->vmcb); + svm_leave_nested(vcpu); svm_free_nested(svm); sev_free_vcpu(vcpu); @@ -2713,8 +2709,6 @@ static int svm_get_msr_feature(struct kvm_msr_entry *msr) if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) msr->data |= MSR_AMD64_DE_CFG_LFENCE_SERIALIZE; break; - case MSR_IA32_PERF_CAPABILITIES: - return 0; default: return KVM_MSR_RET_INVALID; } @@ -3425,15 +3419,6 @@ static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 0; } - if (is_external_interrupt(svm->vmcb->control.exit_int_info) && - exit_code != SVM_EXIT_EXCP_BASE + PF_VECTOR && - exit_code != SVM_EXIT_NPF && exit_code != SVM_EXIT_TASK_SWITCH && - exit_code != SVM_EXIT_INTR && exit_code != SVM_EXIT_NMI) - printk(KERN_ERR "%s: unexpected exit_int_info 0x%x " - "exit_code 0x%x\n", - __func__, svm->vmcb->control.exit_int_info, - exit_code); - if (exit_fastpath != EXIT_FASTPATH_NONE) return 1; @@ -3738,6 +3723,13 @@ static void svm_flush_tlb_current(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); /* + * Unlike VMX, SVM doesn't provide a way to flush only NPT TLB entries. + * A TLB flush for the current ASID flushes both "host" and "guest" TLB + * entries, and thus is a superset of Hyper-V's fine grained flushing. + */ + kvm_hv_vcpu_purge_flush_tlb(vcpu); + + /* * Flush only the current ASID even if the TLB flush was invoked via * kvm_flush_remote_tlbs(). Although flushing remote TLBs requires all * ASIDs to be flushed, KVM uses a single ASID for L1 and L2, and @@ -3903,8 +3895,14 @@ static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu) static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { - if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && - to_svm(vcpu)->vmcb->control.exit_info_1) + struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control; + + /* + * Note, the next RIP must be provided as SRCU isn't held, i.e. KVM + * can't read guest memory (dereference memslots) to decode the WRMSR. + */ + if (control->exit_code == SVM_EXIT_MSR && control->exit_info_1 && + nrips && control->next_rip) return handle_fastpath_set_msr_irqoff(vcpu); return EXIT_FASTPATH_NONE; @@ -4116,6 +4114,8 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index) case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: return false; case MSR_IA32_SMBASE: + if (!IS_ENABLED(CONFIG_KVM_SMM)) + return false; /* SEV-ES guests do not support SMM, so report false */ if (kvm && sev_es_guest(kvm)) return false; @@ -4372,6 +4372,7 @@ static void svm_setup_mce(struct kvm_vcpu *vcpu) vcpu->arch.mcg_cap &= 0x1ff; } +#ifdef CONFIG_KVM_SMM bool svm_smi_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -4399,7 +4400,7 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return 1; } -static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) +static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_host_map map_save; @@ -4408,10 +4409,16 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) if (!is_guest_mode(vcpu)) return 0; - /* FED8h - SVM Guest */ - put_smstate(u64, smstate, 0x7ed8, 1); - /* FEE0h - SVM Guest VMCB Physical Address */ - put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa); + /* + * 32-bit SMRAM format doesn't preserve EFER and SVM state. Userspace is + * responsible for ensuring nested SVM and SMIs are mutually exclusive. + */ + + if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + return 1; + + smram->smram64.svm_guest_flag = 1; + smram->smram64.svm_guest_vmcb_gpa = svm->nested.vmcb12_gpa; svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; @@ -4433,8 +4440,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) * that, see svm_prepare_switch_to_guest()) which must be * preserved. */ - if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), - &map_save) == -EINVAL) + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save)) return 1; BUILD_BUG_ON(offsetof(struct vmcb, save) != 0x400); @@ -4446,34 +4452,33 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) +static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) { struct vcpu_svm *svm = to_svm(vcpu); struct kvm_host_map map, map_save; - u64 saved_efer, vmcb12_gpa; struct vmcb *vmcb12; int ret; + const struct kvm_smram_state_64 *smram64 = &smram->smram64; + if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) return 0; /* Non-zero if SMI arrived while vCPU was in guest mode. */ - if (!GET_SMSTATE(u64, smstate, 0x7ed8)) + if (!smram64->svm_guest_flag) return 0; if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) return 1; - saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0); - if (!(saved_efer & EFER_SVME)) + if (!(smram64->efer & EFER_SVME)) return 1; - vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0); - if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL) + if (kvm_vcpu_map(vcpu, gpa_to_gfn(smram64->svm_guest_vmcb_gpa), &map)) return 1; ret = 1; - if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save) == -EINVAL) + if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->nested.hsave_msr), &map_save)) goto unmap_map; if (svm_allocate_nested(svm)) @@ -4495,7 +4500,7 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) vmcb12 = map.hva; nested_copy_vmcb_control_to_cache(svm, &vmcb12->control); nested_copy_vmcb_save_to_cache(svm, &vmcb12->save); - ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false); + ret = enter_svm_guest_mode(vcpu, smram64->svm_guest_vmcb_gpa, vmcb12, false); if (ret) goto unmap_save; @@ -4521,6 +4526,7 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) /* We must be in SMM; RSM will cause a vmexit anyway. */ } } +#endif static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len) @@ -4796,10 +4802,12 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .pi_update_irte = avic_pi_update_irte, .setup_mce = svm_setup_mce, +#ifdef CONFIG_KVM_SMM .smi_allowed = svm_smi_allowed, .enter_smm = svm_enter_smm, .leave_smm = svm_leave_smm, .enable_smi_window = svm_enable_smi_window, +#endif .mem_enc_ioctl = sev_mem_enc_ioctl, .mem_enc_register_region = sev_mem_enc_register_region, @@ -4865,6 +4873,7 @@ static __init void svm_set_cpu_caps(void) { kvm_set_cpu_caps(); + kvm_caps.supported_perf_cap = 0; kvm_caps.supported_xss = 0; /* CPUID 0x80000001 and 0x8000000A (SVM features) */ diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 199a2ecef1ce..4826e6cc611b 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -151,7 +151,10 @@ struct vmcb_ctrl_area_cached { u64 nested_cr3; u64 virt_ext; u32 clean; - u8 reserved_sw[32]; + union { + struct hv_vmcb_enlightenments hv_enlightenments; + u8 reserved_sw[32]; + }; }; struct svm_nested_state { diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c index 8cdc62c74a96..26a89d0da93e 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.c +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -14,9 +14,9 @@ #include "kvm_onhyperv.h" #include "svm_onhyperv.h" -int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) +int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { - struct hv_enlightenments *hve; + struct hv_vmcb_enlightenments *hve; struct hv_partition_assist_pg **p_hv_pa_pg = &to_kvm_hv(vcpu->kvm)->hv_pa_pg; @@ -26,13 +26,13 @@ int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) if (!*p_hv_pa_pg) return -ENOMEM; - hve = (struct hv_enlightenments *)to_svm(vcpu)->vmcb->control.reserved_sw; + hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments; hve->partition_assist_page = __pa(*p_hv_pa_pg); hve->hv_vm_id = (unsigned long)vcpu->kvm; if (!hve->hv_enlightenments_control.nested_flush_hypercall) { hve->hv_enlightenments_control.nested_flush_hypercall = 1; - vmcb_mark_dirty(to_svm(vcpu)->vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); + vmcb_mark_dirty(to_svm(vcpu)->vmcb, HV_VMCB_NESTED_ENLIGHTENMENTS); } return 0; diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index e2fc59380465..45faf84476ce 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -13,12 +13,14 @@ static struct kvm_x86_ops svm_x86_ops; -int svm_hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu); +int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu); static inline void svm_hv_init_vmcb(struct vmcb *vmcb) { - struct hv_enlightenments *hve = - (struct hv_enlightenments *)vmcb->control.reserved_sw; + struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments; + + BUILD_BUG_ON(sizeof(vmcb->control.hv_enlightenments) != + sizeof(vmcb->control.reserved_sw)); if (npt_enabled && ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) @@ -51,8 +53,8 @@ static inline void svm_hv_hardware_setup(void) vp_ap->nested_control.features.directhypercall = 1; } - svm_x86_ops.enable_direct_tlbflush = - svm_hv_enable_direct_tlbflush; + svm_x86_ops.enable_l2_tlb_flush = + svm_hv_enable_l2_tlb_flush; } } @@ -60,23 +62,20 @@ static inline void svm_hv_vmcb_dirty_nested_enlightenments( struct kvm_vcpu *vcpu) { struct vmcb *vmcb = to_svm(vcpu)->vmcb; - struct hv_enlightenments *hve = - (struct hv_enlightenments *)vmcb->control.reserved_sw; + struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments; if (hve->hv_enlightenments_control.msr_bitmap) - vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); + vmcb_mark_dirty(vmcb, HV_VMCB_NESTED_ENLIGHTENMENTS); } -static inline void svm_hv_update_vp_id(struct vmcb *vmcb, - struct kvm_vcpu *vcpu) +static inline void svm_hv_update_vp_id(struct vmcb *vmcb, struct kvm_vcpu *vcpu) { - struct hv_enlightenments *hve = - (struct hv_enlightenments *)vmcb->control.reserved_sw; + struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments; u32 vp_index = kvm_hv_get_vpindex(vcpu); if (hve->hv_vp_id != vp_index) { hve->hv_vp_id = vp_index; - vmcb_mark_dirty(vmcb, VMCB_HV_NESTED_ENLIGHTENMENTS); + vmcb_mark_dirty(vmcb, HV_VMCB_NESTED_ENLIGHTENMENTS); } } #else diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 34367dc203f2..8e8295e774f0 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> #include <asm/asm.h> +#include <asm/asm-offsets.h> #include <asm/bitsperlong.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index bc25589ad588..83843379813e 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -113,12 +113,13 @@ TRACE_EVENT(kvm_hv_hypercall_done, * Tracepoint for Xen hypercall. */ TRACE_EVENT(kvm_xen_hypercall, - TP_PROTO(unsigned long nr, unsigned long a0, unsigned long a1, - unsigned long a2, unsigned long a3, unsigned long a4, - unsigned long a5), - TP_ARGS(nr, a0, a1, a2, a3, a4, a5), + TP_PROTO(u8 cpl, unsigned long nr, + unsigned long a0, unsigned long a1, unsigned long a2, + unsigned long a3, unsigned long a4, unsigned long a5), + TP_ARGS(cpl, nr, a0, a1, a2, a3, a4, a5), TP_STRUCT__entry( + __field(u8, cpl) __field(unsigned long, nr) __field(unsigned long, a0) __field(unsigned long, a1) @@ -129,6 +130,7 @@ TRACE_EVENT(kvm_xen_hypercall, ), TP_fast_assign( + __entry->cpl = cpl; __entry->nr = nr; __entry->a0 = a0; __entry->a1 = a1; @@ -138,8 +140,9 @@ TRACE_EVENT(kvm_xen_hypercall, __entry->a4 = a5; ), - TP_printk("nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx a4 0x%lx a5 %lx", - __entry->nr, __entry->a0, __entry->a1, __entry->a2, + TP_printk("cpl %d nr 0x%lx a0 0x%lx a1 0x%lx a2 0x%lx a3 0x%lx a4 0x%lx a5 %lx", + __entry->cpl, __entry->nr, + __entry->a0, __entry->a1, __entry->a2, __entry->a3, __entry->a4, __entry->a5) ); @@ -1547,38 +1550,41 @@ TRACE_EVENT(kvm_hv_timer_state, * Tracepoint for kvm_hv_flush_tlb. */ TRACE_EVENT(kvm_hv_flush_tlb, - TP_PROTO(u64 processor_mask, u64 address_space, u64 flags), - TP_ARGS(processor_mask, address_space, flags), + TP_PROTO(u64 processor_mask, u64 address_space, u64 flags, bool guest_mode), + TP_ARGS(processor_mask, address_space, flags, guest_mode), TP_STRUCT__entry( __field(u64, processor_mask) __field(u64, address_space) __field(u64, flags) + __field(bool, guest_mode) ), TP_fast_assign( __entry->processor_mask = processor_mask; __entry->address_space = address_space; __entry->flags = flags; + __entry->guest_mode = guest_mode; ), - TP_printk("processor_mask 0x%llx address_space 0x%llx flags 0x%llx", + TP_printk("processor_mask 0x%llx address_space 0x%llx flags 0x%llx %s", __entry->processor_mask, __entry->address_space, - __entry->flags) + __entry->flags, __entry->guest_mode ? "(L2)" : "") ); /* * Tracepoint for kvm_hv_flush_tlb_ex. */ TRACE_EVENT(kvm_hv_flush_tlb_ex, - TP_PROTO(u64 valid_bank_mask, u64 format, u64 address_space, u64 flags), - TP_ARGS(valid_bank_mask, format, address_space, flags), + TP_PROTO(u64 valid_bank_mask, u64 format, u64 address_space, u64 flags, bool guest_mode), + TP_ARGS(valid_bank_mask, format, address_space, flags, guest_mode), TP_STRUCT__entry( __field(u64, valid_bank_mask) __field(u64, format) __field(u64, address_space) __field(u64, flags) + __field(bool, guest_mode) ), TP_fast_assign( @@ -1586,12 +1592,14 @@ TRACE_EVENT(kvm_hv_flush_tlb_ex, __entry->format = format; __entry->address_space = address_space; __entry->flags = flags; + __entry->guest_mode = guest_mode; ), TP_printk("valid_bank_mask 0x%llx format 0x%llx " - "address_space 0x%llx flags 0x%llx", + "address_space 0x%llx flags 0x%llx %s", __entry->valid_bank_mask, __entry->format, - __entry->address_space, __entry->flags) + __entry->address_space, __entry->flags, + __entry->guest_mode ? "(L2)" : "") ); /* diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h index 07254314f3dd..cd2ac9536c99 100644 --- a/arch/x86/kvm/vmx/capabilities.h +++ b/arch/x86/kvm/vmx/capabilities.h @@ -395,30 +395,6 @@ static inline bool vmx_pebs_supported(void) return boot_cpu_has(X86_FEATURE_PEBS) && kvm_pmu_cap.pebs_ept; } -static inline u64 vmx_get_perf_capabilities(void) -{ - u64 perf_cap = PMU_CAP_FW_WRITES; - struct x86_pmu_lbr lbr; - u64 host_perf_cap = 0; - - if (!enable_pmu) - return 0; - - if (boot_cpu_has(X86_FEATURE_PDCM)) - rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); - - if (x86_perf_get_lbr(&lbr) >= 0 && lbr.nr) - perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; - - if (vmx_pebs_supported()) { - perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; - if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4) - perf_cap &= ~PERF_CAP_PEBS_BASELINE; - } - - return perf_cap; -} - static inline bool cpu_has_notify_vmexit(void) { return vmcs_config.cpu_based_2nd_exec_ctrl & diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/hyperv.c index d8b23c96d627..ae03d1fe0355 100644 --- a/arch/x86/kvm/vmx/evmcs.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -3,9 +3,9 @@ #include <linux/errno.h> #include <linux/smp.h> -#include "../hyperv.h" #include "../cpuid.h" -#include "evmcs.h" +#include "hyperv.h" +#include "nested.h" #include "vmcs.h" #include "vmx.h" #include "trace.h" @@ -322,24 +322,17 @@ const struct evmcs_field vmcs_field_to_evmcs_1[] = { }; const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); -bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa) +u64 nested_get_evmptr(struct kvm_vcpu *vcpu) { - struct hv_vp_assist_page assist_page; - - *evmcs_gpa = -1ull; - - if (unlikely(!kvm_hv_get_assist_page(vcpu, &assist_page))) - return false; - - if (unlikely(!assist_page.enlighten_vmentry)) - return false; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); - if (unlikely(!evmptr_is_valid(assist_page.current_nested_vmcs))) - return false; + if (unlikely(kvm_hv_get_assist_page(vcpu))) + return EVMPTR_INVALID; - *evmcs_gpa = assist_page.current_nested_vmcs; + if (unlikely(!hv_vcpu->vp_assist_page.enlighten_vmentry)) + return EVMPTR_INVALID; - return true; + return hv_vcpu->vp_assist_page.current_nested_vmcs; } uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu) @@ -507,3 +500,23 @@ int nested_enable_evmcs(struct kvm_vcpu *vcpu, return 0; } + +bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu) +{ + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); + struct vcpu_vmx *vmx = to_vmx(vcpu); + struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; + + if (!hv_vcpu || !evmcs) + return false; + + if (!evmcs->hv_enlightenments_control.nested_flush_hypercall) + return false; + + return hv_vcpu->vp_assist_page.nested_control.features.directhypercall; +} + +void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu) +{ + nested_vmx_vmexit(vcpu, HV_VMX_SYNTHETIC_EXIT_REASON_TRAP_AFTER_FLUSH, 0, 0); +} diff --git a/arch/x86/kvm/vmx/evmcs.h b/arch/x86/kvm/vmx/hyperv.h index 6f746ef3c038..571e7929d14e 100644 --- a/arch/x86/kvm/vmx/evmcs.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __KVM_X86_VMX_EVMCS_H -#define __KVM_X86_VMX_EVMCS_H +#ifndef __KVM_X86_VMX_HYPERV_H +#define __KVM_X86_VMX_HYPERV_H #include <linux/jump_label.h> @@ -8,6 +8,8 @@ #include <asm/mshyperv.h> #include <asm/vmx.h> +#include "../hyperv.h" + #include "capabilities.h" #include "vmcs.h" #include "vmcs12.h" @@ -235,11 +237,13 @@ enum nested_evmptrld_status { EVMPTRLD_ERROR, }; -bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa); +u64 nested_get_evmptr(struct kvm_vcpu *vcpu); uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version); void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); int nested_evmcs_check_controls(struct vmcs12 *vmcs12); +bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu); +void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); -#endif /* __KVM_X86_VMX_EVMCS_H */ +#endif /* __KVM_X86_VMX_HYPERV_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 0c62352dda6a..b6f4411b613e 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -7,7 +7,6 @@ #include <asm/mmu_context.h> #include "cpuid.h" -#include "evmcs.h" #include "hyperv.h" #include "mmu.h" #include "nested.h" @@ -16,6 +15,7 @@ #include "trace.h" #include "vmx.h" #include "x86.h" +#include "smm.h" static bool __read_mostly enable_shadow_vmcs = 1; module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO); @@ -225,6 +225,7 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) { + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { @@ -233,6 +234,12 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) } vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; + + if (hv_vcpu) { + hv_vcpu->nested.pa_page_gpa = INVALID_GPA; + hv_vcpu->nested.vm_id = 0; + hv_vcpu->nested.vp_id = 0; + } } static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, @@ -1126,6 +1133,15 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx = to_vmx(vcpu); /* + * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or + * L2's VP_ID upon request from the guest. Make sure we check for + * pending entries in the right FIFO upon L1/L2 transition as these + * requests are put by other vCPUs asynchronously. + */ + if (to_hv_vcpu(vcpu) && enable_ept) + kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); + + /* * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings * for *all* contexts to be flushed on VM-Enter/VM-Exit, i.e. it's a * full TLB flush from the guest's perspective. This is required even @@ -1557,12 +1573,20 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields { struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; + struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu); /* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */ vmcs12->tpr_threshold = evmcs->tpr_threshold; vmcs12->guest_rip = evmcs->guest_rip; if (unlikely(!(hv_clean_fields & + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ENLIGHTENMENTSCONTROL))) { + hv_vcpu->nested.pa_page_gpa = evmcs->partition_assist_page; + hv_vcpu->nested.vm_id = evmcs->hv_vm_id; + hv_vcpu->nested.vp_id = evmcs->hv_vp_id; + } + + if (unlikely(!(hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC))) { vmcs12->guest_rsp = evmcs->guest_rsp; vmcs12->guest_rflags = evmcs->guest_rflags; @@ -1977,7 +2001,8 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( if (likely(!guest_cpuid_has_evmcs(vcpu))) return EVMPTRLD_DISABLED; - if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa)) { + evmcs_gpa = nested_get_evmptr(vcpu); + if (!evmptr_is_valid(evmcs_gpa)) { nested_release_evmcs(vcpu); return EVMPTRLD_DISABLED; } @@ -2563,12 +2588,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, nested_ept_init_mmu_context(vcpu); /* - * This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those - * bits which we consider mandatory enabled. - * The CR0_READ_SHADOW is what L2 should have expected to read given - * the specifications by L1; It's not enough to take - * vmcs12->cr0_read_shadow because on our cr0_guest_host_mask we - * have more bits than L1 expected. + * Override the CR0/CR4 read shadows after setting the effective guest + * CR0/CR4. The common helpers also set the shadows, but they don't + * account for vmcs12's cr0/4_guest_host_mask. */ vmx_set_cr0(vcpu, vmcs12->guest_cr0); vmcs_writel(CR0_READ_SHADOW, nested_read_cr0(vmcs12)); @@ -3251,6 +3273,12 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) { + /* + * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy + * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory + * to make nested_evmcs_l2_tlb_flush_enabled() work correctly post + * migration. + */ if (!nested_get_evmcs_page(vcpu)) { pr_debug_ratelimited("%s: enlightened vmptrld failed\n", __func__); @@ -4767,6 +4795,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, vmx_switch_vmcs(vcpu, &vmx->vmcs01); + /* + * If IBRS is advertised to the vCPU, KVM must flush the indirect + * branch predictors when transitioning from L2 to L1, as L1 expects + * hardware (KVM in this case) to provide separate predictor modes. + * Bare metal isolates VMX root (host) from VMX non-root (guest), but + * doesn't isolate different VMCSs, i.e. in this case, doesn't provide + * separate modes for L2 vs L1. + */ + if (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + indirect_branch_prediction_barrier(); + /* Update any VMCS fields that might have changed while L2 ran */ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr); vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr); @@ -4854,6 +4893,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, static void nested_vmx_triple_fault(struct kvm_vcpu *vcpu) { + kvm_clear_request(KVM_REQ_TRIPLE_FAULT, vcpu); nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0); } @@ -5099,24 +5139,35 @@ static int handle_vmxon(struct kvm_vcpu *vcpu) | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; /* - * Note, KVM cannot rely on hardware to perform the CR0/CR4 #UD checks - * that have higher priority than VM-Exit (see Intel SDM's pseudocode - * for VMXON), as KVM must load valid CR0/CR4 values into hardware while - * running the guest, i.e. KVM needs to check the _guest_ values. + * Manually check CR4.VMXE checks, KVM must force CR4.VMXE=1 to enter + * the guest and so cannot rely on hardware to perform the check, + * which has higher priority than VM-Exit (see Intel SDM's pseudocode + * for VMXON). * - * Rely on hardware for the other two pre-VM-Exit checks, !VM86 and - * !COMPATIBILITY modes. KVM may run the guest in VM86 to emulate Real - * Mode, but KVM will never take the guest out of those modes. + * Rely on hardware for the other pre-VM-Exit checks, CR0.PE=1, !VM86 + * and !COMPATIBILITY modes. For an unrestricted guest, KVM doesn't + * force any of the relevant guest state. For a restricted guest, KVM + * does force CR0.PE=1, but only to also force VM86 in order to emulate + * Real Mode, and so there's no need to check CR0.PE manually. */ - if (!nested_host_cr0_valid(vcpu, kvm_read_cr0(vcpu)) || - !nested_host_cr4_valid(vcpu, kvm_read_cr4(vcpu))) { + if (!kvm_read_cr4_bits(vcpu, X86_CR4_VMXE)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } /* - * CPL=0 and all other checks that are lower priority than VM-Exit must - * be checked manually. + * The CPL is checked for "not in VMX operation" and for "in VMX root", + * and has higher priority than the VM-Fail due to being post-VMXON, + * i.e. VMXON #GPs outside of VMX non-root if CPL!=0. In VMX non-root, + * VMXON causes VM-Exit and KVM unconditionally forwards VMXON VM-Exits + * from L2 to L1, i.e. there's no need to check for the vCPU being in + * VMX non-root. + * + * Forwarding the VM-Exit unconditionally, i.e. without performing the + * #UD checks (see above), is functionally ok because KVM doesn't allow + * L1 to run L2 without CR4.VMXE=0, and because KVM never modifies L2's + * CR0 or CR4, i.e. it's L2's responsibility to emulate #UDs that are + * missed by hardware due to shadowing CR0 and/or CR4. */ if (vmx_get_cpl(vcpu)) { kvm_inject_gp(vcpu, 0); @@ -5126,6 +5177,17 @@ static int handle_vmxon(struct kvm_vcpu *vcpu) if (vmx->nested.vmxon) return nested_vmx_fail(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); + /* + * Invalid CR0/CR4 generates #GP. These checks are performed if and + * only if the vCPU isn't already in VMX operation, i.e. effectively + * have lower priority than the VM-Fail above. + */ + if (!nested_host_cr0_valid(vcpu, kvm_read_cr0(vcpu)) || + !nested_host_cr4_valid(vcpu, kvm_read_cr4(vcpu))) { + kvm_inject_gp(vcpu, 0); + return 1; + } + if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES) != VMXON_NEEDED_FEATURES) { kvm_inject_gp(vcpu, 0); @@ -5205,7 +5267,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); u32 zero = 0; gpa_t vmptr; - u64 evmcs_gpa; int r; if (!nested_vmx_check_permission(vcpu)) @@ -5231,7 +5292,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) * vmx->nested.hv_evmcs but this shouldn't be a problem. */ if (likely(!guest_cpuid_has_evmcs(vcpu) || - !nested_enlightened_vmentry(vcpu, &evmcs_gpa))) { + !evmptr_is_valid(nested_get_evmptr(vcpu)))) { if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); @@ -6128,6 +6189,11 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, * Handle L2's bus locks in L0 directly. */ return true; + case EXIT_REASON_VMCALL: + /* Hyper-V L2 TLB flush hypercall is handled by L0 */ + return guest_hv_cpuid_has_l2_tlb_flush(vcpu) && + nested_evmcs_l2_tlb_flush_enabled(vcpu) && + kvm_hv_is_tlb_flush_hcall(vcpu); default: break; } @@ -6440,9 +6506,6 @@ out: return kvm_state.size; } -/* - * Forcibly leave nested mode in order to be able to reset the VCPU later on. - */ void vmx_leave_nested(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu)) { @@ -6982,4 +7045,5 @@ struct kvm_x86_nested_ops vmx_nested_ops = { .write_log_dirty = nested_vmx_write_pml_buffer, .enable_evmcs = nested_enable_evmcs, .get_evmcs_version = nested_get_evmcs_version, + .hv_inject_synthetic_vmexit_post_tlb_flush = vmx_hv_inject_synthetic_vmexit_post_tlb_flush, }; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index 6312c9541c3c..96952263b029 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -79,9 +79,10 @@ static inline bool nested_ept_ad_enabled(struct kvm_vcpu *vcpu) } /* - * Return the cr0 value that a nested guest would read. This is a combination - * of the real cr0 used to run the guest (guest_cr0), and the bits shadowed by - * its hypervisor (cr0_read_shadow). + * Return the cr0/4 value that a nested guest would read. This is a combination + * of L1's "real" cr0 used to run the guest (guest_cr0), and the bits shadowed + * by the L1 hypervisor (cr0_read_shadow). KVM must emulate CPU behavior as + * the value+mask loaded into vmcs02 may not match the vmcs12 fields. */ static inline unsigned long nested_read_cr0(struct vmcs12 *fields) { diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 10b33da9bd05..e5cec07ca8d9 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -52,7 +52,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i); __set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use); - reprogram_counter(pmc); + kvm_pmu_request_counter_reprogam(pmc); } } @@ -76,7 +76,7 @@ static void reprogram_counters(struct kvm_pmu *pmu, u64 diff) for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) { pmc = intel_pmc_idx_to_pmc(pmu, bit); if (pmc) - reprogram_counter(pmc); + kvm_pmu_request_counter_reprogam(pmc); } } @@ -477,7 +477,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) reserved_bits ^= HSW_IN_TX_CHECKPOINTED; if (!(data & reserved_bits)) { pmc->eventsel = data; - reprogram_counter(pmc); + kvm_pmu_request_counter_reprogam(pmc); return 0; } } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false)) @@ -631,7 +631,6 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) pmu->fixed_counters[i].current_config = 0; } - vcpu->arch.perf_capabilities = vmx_get_perf_capabilities(); lbr_desc->records.nr = 0; lbr_desc->event = NULL; lbr_desc->msr_passthrough = false; @@ -647,14 +646,14 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu) pmc = &pmu->gp_counters[i]; pmc_stop_counter(pmc); - pmc->counter = pmc->eventsel = 0; + pmc->counter = pmc->prev_counter = pmc->eventsel = 0; } for (i = 0; i < KVM_PMC_MAX_FIXED; i++) { pmc = &pmu->fixed_counters[i]; pmc_stop_counter(pmc); - pmc->counter = 0; + pmc->counter = pmc->prev_counter = 0; } pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status = 0; diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 8f95c7c01433..b12da2a6dec9 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -182,8 +182,10 @@ static int __handle_encls_ecreate(struct kvm_vcpu *vcpu, /* Enforce CPUID restriction on max enclave size. */ max_size_log2 = (attributes & SGX_ATTR_MODE64BIT) ? sgx_12_0->edx >> 8 : sgx_12_0->edx; - if (size >= BIT_ULL(max_size_log2)) + if (size >= BIT_ULL(max_size_log2)) { kvm_inject_gp(vcpu, 0); + return 1; + } /* * sgx_virt_ecreate() returns: diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h index 746129ddd5ae..01936013428b 100644 --- a/arch/x86/kvm/vmx/vmcs12.h +++ b/arch/x86/kvm/vmx/vmcs12.h @@ -208,9 +208,8 @@ struct __packed vmcs12 { /* * For save/restore compatibility, the vmcs12 field offsets must not change. */ -#define CHECK_OFFSET(field, loc) \ - BUILD_BUG_ON_MSG(offsetof(struct vmcs12, field) != (loc), \ - "Offset of " #field " in struct vmcs12 has changed.") +#define CHECK_OFFSET(field, loc) \ + ASSERT_STRUCT_OFFSET(struct vmcs12, field, loc) static inline void vmx_check_vmcs12_offsets(void) { diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 0b5db4de4d09..766c6b3ef5ed 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -269,6 +269,7 @@ SYM_FUNC_END(__vmx_vcpu_run) .section .text, "ax" +#ifndef CONFIG_CC_HAS_ASM_GOTO_OUTPUT /** * vmread_error_trampoline - Trampoline from inline asm to vmread_error() * @field: VMCS field encoding that failed @@ -317,6 +318,7 @@ SYM_FUNC_START(vmread_error_trampoline) RET SYM_FUNC_END(vmread_error_trampoline) +#endif SYM_FUNC_START(vmx_do_interrupt_nmi_irqoff) /* diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 63247c57c72c..fe5615fd8295 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -51,7 +51,6 @@ #include "capabilities.h" #include "cpuid.h" -#include "evmcs.h" #include "hyperv.h" #include "kvm_onhyperv.h" #include "irq.h" @@ -66,6 +65,7 @@ #include "vmcs12.h" #include "vmx.h" #include "x86.h" +#include "smm.h" MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); @@ -526,7 +526,7 @@ static unsigned long host_idt_base; static bool __read_mostly enlightened_vmcs = true; module_param(enlightened_vmcs, bool, 0444); -static int hv_enable_direct_tlbflush(struct kvm_vcpu *vcpu) +static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { struct hv_enlightened_vmcs *evmcs; struct hv_partition_assist_pg **p_hv_pa_pg = @@ -858,7 +858,7 @@ unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx) * to change it directly without causing a vmexit. In that case read * it after vmexit and store it in vmx->spec_ctrl. */ - if (unlikely(!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))) + if (!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL)) flags |= VMX_RUN_SAVE_SPEC_CTRL; return flags; @@ -1348,8 +1348,10 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu, /* * No indirect branch prediction barrier needed when switching - * the active VMCS within a guest, e.g. on nested VM-Enter. - * The L1 VMM can protect itself with retpolines, IBPB or IBRS. + * the active VMCS within a vCPU, unless IBRS is advertised to + * the vCPU. To minimize the number of IBPBs executed, KVM + * performs IBPB on nested VM-Exit (a single nested transition + * may switch the active VMCS multiple times). */ if (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)) indirect_branch_prediction_barrier(); @@ -1834,12 +1836,42 @@ bool nested_vmx_allowed(struct kvm_vcpu *vcpu) return nested && guest_cpuid_has(vcpu, X86_FEATURE_VMX); } -static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu, - uint64_t val) +/* + * Userspace is allowed to set any supported IA32_FEATURE_CONTROL regardless of + * guest CPUID. Note, KVM allows userspace to set "VMX in SMX" to maintain + * backwards compatibility even though KVM doesn't support emulating SMX. And + * because userspace set "VMX in SMX", the guest must also be allowed to set it, + * e.g. if the MSR is left unlocked and the guest does a RMW operation. + */ +#define KVM_SUPPORTED_FEATURE_CONTROL (FEAT_CTL_LOCKED | \ + FEAT_CTL_VMX_ENABLED_INSIDE_SMX | \ + FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX | \ + FEAT_CTL_SGX_LC_ENABLED | \ + FEAT_CTL_SGX_ENABLED | \ + FEAT_CTL_LMCE_ENABLED) + +static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, + struct msr_data *msr) { - uint64_t valid_bits = to_vmx(vcpu)->msr_ia32_feature_control_valid_bits; + uint64_t valid_bits; + + /* + * Ensure KVM_SUPPORTED_FEATURE_CONTROL is updated when new bits are + * exposed to the guest. + */ + WARN_ON_ONCE(vmx->msr_ia32_feature_control_valid_bits & + ~KVM_SUPPORTED_FEATURE_CONTROL); + + if (!msr->host_initiated && + (vmx->msr_ia32_feature_control & FEAT_CTL_LOCKED)) + return false; + + if (msr->host_initiated) + valid_bits = KVM_SUPPORTED_FEATURE_CONTROL; + else + valid_bits = vmx->msr_ia32_feature_control_valid_bits; - return !(val & ~valid_bits); + return !(msr->data & ~valid_bits); } static int vmx_get_msr_feature(struct kvm_msr_entry *msr) @@ -1849,9 +1881,6 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr) if (!nested) return 1; return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data); - case MSR_IA32_PERF_CAPABILITIES: - msr->data = vmx_get_perf_capabilities(); - return 0; default: return KVM_MSR_RET_INVALID; } @@ -2029,7 +2058,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; - if ((vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) && + if ((kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT) && (host_initiated || intel_pmu_lbr_is_enabled(vcpu))) debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI; @@ -2241,10 +2270,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.mcg_ext_ctl = data; break; case MSR_IA32_FEAT_CTL: - if (!vmx_feature_control_msr_valid(vcpu, data) || - (to_vmx(vcpu)->msr_ia32_feature_control & - FEAT_CTL_LOCKED && !msr_info->host_initiated)) + if (!is_vmx_feature_control_msr_valid(vmx, msr_info)) return 1; + vmx->msr_ia32_feature_control = data; if (msr_info->host_initiated && data == 0) vmx_leave_nested(vcpu); @@ -2342,14 +2370,14 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; if (data & PMU_CAP_LBR_FMT) { if ((data & PMU_CAP_LBR_FMT) != - (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)) + (kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT)) return 1; if (!cpuid_model_is_consistent(vcpu)) return 1; } if (data & PERF_CAP_PEBS_FORMAT) { if ((data & PERF_CAP_PEBS_MASK) != - (vmx_get_perf_capabilities() & PERF_CAP_PEBS_MASK)) + (kvm_caps.supported_perf_cap & PERF_CAP_PEBS_MASK)) return 1; if (!guest_cpuid_has(vcpu, X86_FEATURE_DS)) return 1; @@ -6844,6 +6872,8 @@ static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_SMBASE: + if (!IS_ENABLED(CONFIG_KVM_SMM)) + return false; /* * We cannot do SMM unless we can run the guest in big * real mode. @@ -7669,6 +7699,31 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_update_exception_bitmap(vcpu); } +static u64 vmx_get_perf_capabilities(void) +{ + u64 perf_cap = PMU_CAP_FW_WRITES; + struct x86_pmu_lbr lbr; + u64 host_perf_cap = 0; + + if (!enable_pmu) + return 0; + + if (boot_cpu_has(X86_FEATURE_PDCM)) + rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); + + x86_perf_get_lbr(&lbr); + if (lbr.nr) + perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; + + if (vmx_pebs_supported()) { + perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; + if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4) + perf_cap &= ~PERF_CAP_PEBS_BASELINE; + } + + return perf_cap; +} + static __init void vmx_set_cpu_caps(void) { kvm_set_cpu_caps(); @@ -7691,6 +7746,7 @@ static __init void vmx_set_cpu_caps(void) if (!enable_pmu) kvm_cpu_cap_clear(X86_FEATURE_PDCM); + kvm_caps.supported_perf_cap = vmx_get_perf_capabilities(); if (!enable_sgx) { kvm_cpu_cap_clear(X86_FEATURE_SGX); @@ -7906,6 +7962,7 @@ static void vmx_setup_mce(struct kvm_vcpu *vcpu) ~FEAT_CTL_LMCE_ENABLED; } +#ifdef CONFIG_KVM_SMM static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) { /* we need a nested vmexit to enter SMM, postpone if run is pending */ @@ -7914,7 +7971,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !is_smm(vcpu); } -static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate) +static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7935,7 +7992,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate) return 0; } -static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate) +static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) { struct vcpu_vmx *vmx = to_vmx(vcpu); int ret; @@ -7960,6 +8017,7 @@ static void vmx_enable_smi_window(struct kvm_vcpu *vcpu) { /* RSM will cause a vmexit anyway. */ } +#endif static bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu) { @@ -8127,10 +8185,12 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .setup_mce = vmx_setup_mce, +#ifdef CONFIG_KVM_SMM .smi_allowed = vmx_smi_allowed, .enter_smm = vmx_enter_smm, .leave_smm = vmx_leave_smm, .enable_smi_window = vmx_enable_smi_window, +#endif .can_emulate_instruction = vmx_can_emulate_instruction, .apic_init_signal_blocked = vmx_apic_init_signal_blocked, @@ -8490,8 +8550,8 @@ static int __init vmx_init(void) } if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) - vmx_x86_ops.enable_direct_tlbflush - = hv_enable_direct_tlbflush; + vmx_x86_ops.enable_l2_tlb_flush + = hv_enable_l2_tlb_flush; } else { enlightened_vmcs = false; diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index ec268df83ed6..842dc898c972 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -6,19 +6,33 @@ #include <asm/vmx.h> -#include "evmcs.h" +#include "hyperv.h" #include "vmcs.h" #include "../x86.h" void vmread_error(unsigned long field, bool fault); -__attribute__((regparm(0))) void vmread_error_trampoline(unsigned long field, - bool fault); void vmwrite_error(unsigned long field, unsigned long value); void vmclear_error(struct vmcs *vmcs, u64 phys_addr); void vmptrld_error(struct vmcs *vmcs, u64 phys_addr); void invvpid_error(unsigned long ext, u16 vpid, gva_t gva); void invept_error(unsigned long ext, u64 eptp, gpa_t gpa); +#ifndef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +/* + * The VMREAD error trampoline _always_ uses the stack to pass parameters, even + * for 64-bit targets. Preserving all registers allows the VMREAD inline asm + * blob to avoid clobbering GPRs, which in turn allows the compiler to better + * optimize sequences of VMREADs. + * + * Declare the trampoline as an opaque label as it's not safe to call from C + * code; there is no way to tell the compiler to pass params on the stack for + * 64-bit targets. + * + * void vmread_error_trampoline(unsigned long field, bool fault); + */ +extern unsigned long vmread_error_trampoline; +#endif + static __always_inline void vmcs_check16(unsigned long field) { BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6001) == 0x2000, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 490ec23c8450..312aea1854ae 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -30,6 +30,7 @@ #include "hyperv.h" #include "lapic.h" #include "xen.h" +#include "smm.h" #include <linux/clocksource.h> #include <linux/interrupt.h> @@ -119,8 +120,6 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; static void update_cr8_intercept(struct kvm_vcpu *vcpu); static void process_nmi(struct kvm_vcpu *vcpu); -static void process_smi(struct kvm_vcpu *vcpu); -static void enter_smm(struct kvm_vcpu *vcpu); static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags); static void store_regs(struct kvm_vcpu *vcpu); static int sync_regs(struct kvm_vcpu *vcpu); @@ -464,7 +463,6 @@ u64 kvm_get_apic_base(struct kvm_vcpu *vcpu) { return vcpu->arch.apic_base; } -EXPORT_SYMBOL_GPL(kvm_get_apic_base); enum lapic_mode kvm_get_apic_mode(struct kvm_vcpu *vcpu) { @@ -492,7 +490,6 @@ int kvm_set_apic_base(struct kvm_vcpu *vcpu, struct msr_data *msr_info) kvm_recalculate_apic_map(vcpu->kvm); return 0; } -EXPORT_SYMBOL_GPL(kvm_set_apic_base); /* * Handle a fault on a hardware virtualization (VMX or SVM) instruction. @@ -628,6 +625,12 @@ static void kvm_queue_exception_vmexit(struct kvm_vcpu *vcpu, unsigned int vecto ex->payload = payload; } +/* Forcibly leave the nested mode in cases like a vCPU reset */ +static void kvm_leave_nested(struct kvm_vcpu *vcpu) +{ + kvm_x86_ops.nested_ops->leave_nested(vcpu); +} + static void kvm_multiple_exception(struct kvm_vcpu *vcpu, unsigned nr, bool has_error, u32 error_code, bool has_payload, unsigned long payload, bool reinject) @@ -777,7 +780,6 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) kvm_queue_exception_e_p(vcpu, PF_VECTOR, fault->error_code, fault->address); } -EXPORT_SYMBOL_GPL(kvm_inject_page_fault); void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault) @@ -806,7 +808,6 @@ void kvm_inject_nmi(struct kvm_vcpu *vcpu) atomic_inc(&vcpu->arch.nmi_queued); kvm_make_request(KVM_REQ_NMI, vcpu); } -EXPORT_SYMBOL_GPL(kvm_inject_nmi); void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code) { @@ -831,7 +832,6 @@ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) kvm_queue_exception_e(vcpu, GP_VECTOR, 0); return false; } -EXPORT_SYMBOL_GPL(kvm_require_cpl); bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr) { @@ -1648,6 +1648,9 @@ static int kvm_get_msr_feature(struct kvm_msr_entry *msr) case MSR_IA32_ARCH_CAPABILITIES: msr->data = kvm_get_arch_capabilities(); break; + case MSR_IA32_PERF_CAPABILITIES: + msr->data = kvm_caps.supported_perf_cap; + break; case MSR_IA32_UCODE_REV: rdmsrl_safe(msr->index, &msr->data); break; @@ -2061,7 +2064,6 @@ int kvm_emulate_as_nop(struct kvm_vcpu *vcpu) { return kvm_skip_emulated_instruction(vcpu); } -EXPORT_SYMBOL_GPL(kvm_emulate_as_nop); int kvm_emulate_invd(struct kvm_vcpu *vcpu) { @@ -2309,13 +2311,11 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time, kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu); /* we verify if the enable bit is set... */ - if (system_time & 1) { - kvm_gpc_activate(vcpu->kvm, &vcpu->arch.pv_time, vcpu, - KVM_HOST_USES_PFN, system_time & ~1ULL, + if (system_time & 1) + kvm_gpc_activate(&vcpu->arch.pv_time, system_time & ~1ULL, sizeof(struct pvclock_vcpu_time_info)); - } else { - kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time); - } + else + kvm_gpc_deactivate(&vcpu->arch.pv_time); return; } @@ -2507,7 +2507,6 @@ u64 kvm_scale_tsc(u64 tsc, u64 ratio) return _tsc; } -EXPORT_SYMBOL_GPL(kvm_scale_tsc); static u64 kvm_compute_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) { @@ -2966,6 +2965,22 @@ static void kvm_update_masterclock(struct kvm *kvm) kvm_end_pvclock_update(kvm); } +/* + * Use the kernel's tsc_khz directly if the TSC is constant, otherwise use KVM's + * per-CPU value (which may be zero if a CPU is going offline). Note, tsc_khz + * can change during boot even if the TSC is constant, as it's possible for KVM + * to be loaded before TSC calibration completes. Ideally, KVM would get a + * notification when calibration completes, but practically speaking calibration + * will complete before userspace is alive enough to create VMs. + */ +static unsigned long get_cpu_tsc_khz(void) +{ + if (static_cpu_has(X86_FEATURE_CONSTANT_TSC)) + return tsc_khz; + else + return __this_cpu_read(cpu_tsc_khz); +} + /* Called within read_seqcount_begin/retry for kvm->pvclock_sc. */ static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) { @@ -2976,7 +2991,8 @@ static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) get_cpu(); data->flags = 0; - if (ka->use_master_clock && __this_cpu_read(cpu_tsc_khz)) { + if (ka->use_master_clock && + (static_cpu_has(X86_FEATURE_CONSTANT_TSC) || __this_cpu_read(cpu_tsc_khz))) { #ifdef CONFIG_X86_64 struct timespec64 ts; @@ -2990,7 +3006,7 @@ static void __get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) data->flags |= KVM_CLOCK_TSC_STABLE; hv_clock.tsc_timestamp = ka->master_cycle_now; hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; - kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL, + kvm_get_time_scale(NSEC_PER_SEC, get_cpu_tsc_khz() * 1000LL, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); data->clock = __pvclock_read_cycles(&hv_clock, data->host_tsc); @@ -3029,12 +3045,10 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, unsigned long flags; read_lock_irqsave(&gpc->lock, flags); - while (!kvm_gfn_to_pfn_cache_check(v->kvm, gpc, gpc->gpa, - offset + sizeof(*guest_hv_clock))) { + while (!kvm_gpc_check(gpc, offset + sizeof(*guest_hv_clock))) { read_unlock_irqrestore(&gpc->lock, flags); - if (kvm_gfn_to_pfn_cache_refresh(v->kvm, gpc, gpc->gpa, - offset + sizeof(*guest_hv_clock))) + if (kvm_gpc_refresh(gpc, offset + sizeof(*guest_hv_clock))) return; read_lock_irqsave(&gpc->lock, flags); @@ -3100,7 +3114,7 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) /* Keep irq disabled to prevent changes to the clock */ local_irq_save(flags); - tgt_tsc_khz = __this_cpu_read(cpu_tsc_khz); + tgt_tsc_khz = get_cpu_tsc_khz(); if (unlikely(tgt_tsc_khz == 0)) { local_irq_restore(flags); kvm_make_request(KVM_REQ_CLOCK_UPDATE, v); @@ -3383,7 +3397,7 @@ static int kvm_pv_enable_async_pf_int(struct kvm_vcpu *vcpu, u64 data) static void kvmclock_reset(struct kvm_vcpu *vcpu) { - kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.pv_time); + kvm_gpc_deactivate(&vcpu->arch.pv_time); vcpu->arch.time = 0; } @@ -3391,6 +3405,9 @@ static void kvm_vcpu_flush_tlb_all(struct kvm_vcpu *vcpu) { ++vcpu->stat.tlb_flush; static_call(kvm_x86_flush_tlb_all)(vcpu); + + /* Flushing all ASIDs flushes the current ASID... */ + kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); } static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) @@ -3409,6 +3426,12 @@ static void kvm_vcpu_flush_tlb_guest(struct kvm_vcpu *vcpu) } static_call(kvm_x86_flush_tlb_guest)(vcpu); + + /* + * Flushing all "guest" TLB is always a superset of Hyper-V's fine + * grained flushing. + */ + kvm_hv_vcpu_purge_flush_tlb(vcpu); } @@ -3560,20 +3583,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; vcpu->arch.arch_capabilities = data; break; - case MSR_IA32_PERF_CAPABILITIES: { - struct kvm_msr_entry msr_ent = {.index = msr, .data = 0}; - + case MSR_IA32_PERF_CAPABILITIES: if (!msr_info->host_initiated) return 1; - if (kvm_get_msr_feature(&msr_ent)) - return 1; - if (data & ~msr_ent.data) + if (data & ~kvm_caps.supported_perf_cap) return 1; vcpu->arch.perf_capabilities = data; kvm_pmu_refresh(vcpu); return 0; - } case MSR_EFER: return set_efer(vcpu, msr_info); case MSR_K7_HWCR: @@ -3645,7 +3663,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; } case MSR_IA32_SMBASE: - if (!msr_info->host_initiated) + if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated) return 1; vcpu->arch.smbase = data; break; @@ -4061,7 +4079,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.ia32_misc_enable_msr; break; case MSR_IA32_SMBASE: - if (!msr_info->host_initiated) + if (!IS_ENABLED(CONFIG_KVM_SMM) || !msr_info->host_initiated) return 1; msr_info->data = vcpu->arch.smbase; break; @@ -4419,7 +4437,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | KVM_XEN_HVM_CONFIG_EVTCHN_SEND; if (sched_info_on()) - r |= KVM_XEN_HVM_CONFIG_RUNSTATE; + r |= KVM_XEN_HVM_CONFIG_RUNSTATE | + KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG; break; #endif case KVM_CAP_SYNC_REGS: @@ -4435,6 +4454,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r |= KVM_X86_DISABLE_EXITS_MWAIT; break; case KVM_CAP_X86_SMM: + if (!IS_ENABLED(CONFIG_KVM_SMM)) + break; + /* SMBASE is usually relocated above 1M on modern chipsets, * and SMM handlers might indeed rely on 4G segment limits, * so do not report SMM to be available if real mode is @@ -4475,7 +4497,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0; break; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: - r = kvm_x86_ops.enable_direct_tlbflush != NULL; + r = kvm_x86_ops.enable_l2_tlb_flush != NULL; break; case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: r = kvm_x86_ops.nested_ops->enable_evmcs != NULL; @@ -4891,13 +4913,6 @@ static int kvm_vcpu_ioctl_nmi(struct kvm_vcpu *vcpu) return 0; } -static int kvm_vcpu_ioctl_smi(struct kvm_vcpu *vcpu) -{ - kvm_make_request(KVM_REQ_SMI, vcpu); - - return 0; -} - static int vcpu_ioctl_tpr_access_reporting(struct kvm_vcpu *vcpu, struct kvm_tpr_access_ctl *tac) { @@ -5033,8 +5048,10 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, process_nmi(vcpu); +#ifdef CONFIG_KVM_SMM if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); +#endif /* * KVM's ABI only allows for one exception to be migrated. Luckily, @@ -5062,16 +5079,15 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, ex->pending && ex->has_payload) kvm_deliver_exception_payload(vcpu, ex); + memset(events, 0, sizeof(*events)); + /* * The API doesn't provide the instruction length for software * exceptions, so don't report them. As long as the guest RIP * isn't advanced, we should expect to encounter the exception * again. */ - if (kvm_exception_is_soft(ex->vector)) { - events->exception.injected = 0; - events->exception.pending = 0; - } else { + if (!kvm_exception_is_soft(ex->vector)) { events->exception.injected = ex->injected; events->exception.pending = ex->pending; /* @@ -5091,20 +5107,20 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->interrupt.injected = vcpu->arch.interrupt.injected && !vcpu->arch.interrupt.soft; events->interrupt.nr = vcpu->arch.interrupt.nr; - events->interrupt.soft = 0; events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; events->nmi.pending = vcpu->arch.nmi_pending != 0; events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu); - events->nmi.pad = 0; - events->sipi_vector = 0; /* never valid when reporting to user space */ + /* events->sipi_vector is never valid when reporting to user space */ +#ifdef CONFIG_KVM_SMM events->smi.smm = is_smm(vcpu); events->smi.pending = vcpu->arch.smi_pending; events->smi.smm_inside_nmi = !!(vcpu->arch.hflags & HF_SMM_INSIDE_NMI_MASK); +#endif events->smi.latched_init = kvm_lapic_latched_init(vcpu); events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING @@ -5116,12 +5132,8 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->triple_fault.pending = kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu); events->flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT; } - - memset(&events->reserved, 0, sizeof(events->reserved)); } -static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm); - static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events) { @@ -5194,8 +5206,9 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.apic->sipi_vector = events->sipi_vector; if (events->flags & KVM_VCPUEVENT_VALID_SMM) { +#ifdef CONFIG_KVM_SMM if (!!(vcpu->arch.hflags & HF_SMM_MASK) != events->smi.smm) { - kvm_x86_ops.nested_ops->leave_nested(vcpu); + kvm_leave_nested(vcpu); kvm_smm_changed(vcpu, events->smi.smm); } @@ -5208,6 +5221,12 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, vcpu->arch.hflags &= ~HF_SMM_INSIDE_NMI_MASK; } +#else + if (events->smi.smm || events->smi.pending || + events->smi.smm_inside_nmi) + return -EINVAL; +#endif + if (lapic_in_kernel(vcpu)) { if (events->smi.latched_init) set_bit(KVM_APIC_INIT, &vcpu->arch.apic->pending_events); @@ -5491,10 +5510,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, } return r; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: - if (!kvm_x86_ops.enable_direct_tlbflush) + if (!kvm_x86_ops.enable_l2_tlb_flush) return -ENOTTY; - return static_call(kvm_x86_enable_direct_tlbflush)(vcpu); + return static_call(kvm_x86_enable_l2_tlb_flush)(vcpu); case KVM_CAP_HYPERV_ENFORCE_CPUID: return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); @@ -5574,7 +5593,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp, break; } case KVM_SMI: { - r = kvm_vcpu_ioctl_smi(vcpu); + r = kvm_inject_smi(vcpu); break; } case KVM_SET_CPUID: { @@ -6233,9 +6252,7 @@ split_irqchip_unlock: break; case KVM_CAP_X86_USER_SPACE_MSR: r = -EINVAL; - if (cap->args[0] & ~(KVM_MSR_EXIT_REASON_INVAL | - KVM_MSR_EXIT_REASON_UNKNOWN | - KVM_MSR_EXIT_REASON_FILTER)) + if (cap->args[0] & ~KVM_MSR_EXIT_REASON_VALID_MASK) break; kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; @@ -6412,7 +6429,7 @@ static int kvm_add_msr_filter(struct kvm_x86_msr_filter *msr_filter, if (!user_range->nmsrs) return 0; - if (user_range->flags & ~(KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE)) + if (user_range->flags & ~KVM_MSR_FILTER_RANGE_VALID_MASK) return -EINVAL; if (!user_range->flags) @@ -6446,7 +6463,7 @@ static int kvm_vm_ioctl_set_msr_filter(struct kvm *kvm, int r = 0; u32 i; - if (filter->flags & ~KVM_MSR_FILTER_DEFAULT_DENY) + if (filter->flags & ~KVM_MSR_FILTER_VALID_MASK) return -EINVAL; for (i = 0; i < ARRAY_SIZE(filter->ranges); i++) @@ -7119,8 +7136,8 @@ static int vcpu_mmio_read(struct kvm_vcpu *vcpu, gpa_t addr, int len, void *v) return handled; } -static void kvm_set_segment(struct kvm_vcpu *vcpu, - struct kvm_segment *var, int seg) +void kvm_set_segment(struct kvm_vcpu *vcpu, + struct kvm_segment *var, int seg) { static_call(kvm_x86_set_segment)(vcpu, var, seg); } @@ -7156,16 +7173,6 @@ gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, } EXPORT_SYMBOL_GPL(kvm_mmu_gva_to_gpa_read); - gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, - struct x86_exception *exception) -{ - struct kvm_mmu *mmu = vcpu->arch.walk_mmu; - - u64 access = (static_call(kvm_x86_get_cpl)(vcpu) == 3) ? PFERR_USER_MASK : 0; - access |= PFERR_FETCH_MASK; - return mmu->gva_to_gpa(vcpu, mmu, gva, access, exception); -} - gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, struct x86_exception *exception) { @@ -7278,15 +7285,6 @@ static int emulator_read_std(struct x86_emulate_ctxt *ctxt, return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception); } -static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt, - unsigned long addr, void *val, unsigned int bytes) -{ - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - int r = kvm_vcpu_read_guest(vcpu, addr, val, bytes); - - return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE; -} - static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes, struct kvm_vcpu *vcpu, u64 access, struct x86_exception *exception) @@ -8078,26 +8076,6 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); } -static int emulator_set_msr(struct x86_emulate_ctxt *ctxt, - u32 msr_index, u64 data) -{ - return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data); -} - -static u64 emulator_get_smbase(struct x86_emulate_ctxt *ctxt) -{ - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - - return vcpu->arch.smbase; -} - -static void emulator_set_smbase(struct x86_emulate_ctxt *ctxt, u64 smbase) -{ - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - - vcpu->arch.smbase = smbase; -} - static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, u32 pmc) { @@ -8172,18 +8150,13 @@ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt) return emul_to_vcpu(ctxt)->arch.hflags; } -static void emulator_exiting_smm(struct x86_emulate_ctxt *ctxt) +#ifndef CONFIG_KVM_SMM +static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) { - struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); - - kvm_smm_changed(vcpu, false); -} - -static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt, - const char *smstate) -{ - return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smstate); + WARN_ON_ONCE(1); + return X86EMUL_UNHANDLEABLE; } +#endif static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt) { @@ -8209,7 +8182,6 @@ static const struct x86_emulate_ops emulate_ops = { .write_gpr = emulator_write_gpr, .read_std = emulator_read_std, .write_std = emulator_write_std, - .read_phys = kvm_read_guest_phys_system, .fetch = kvm_fetch_guest_virt, .read_emulated = emulator_read_emulated, .write_emulated = emulator_write_emulated, @@ -8229,11 +8201,8 @@ static const struct x86_emulate_ops emulate_ops = { .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, - .get_smbase = emulator_get_smbase, - .set_smbase = emulator_set_smbase, .set_msr_with_filter = emulator_set_msr_with_filter, .get_msr_with_filter = emulator_get_msr_with_filter, - .set_msr = emulator_set_msr, .get_msr = emulator_get_msr, .check_pmc = emulator_check_pmc, .read_pmc = emulator_read_pmc, @@ -8248,7 +8217,6 @@ static const struct x86_emulate_ops emulate_ops = { .guest_has_rdpid = emulator_guest_has_rdpid, .set_nmi_mask = emulator_set_nmi_mask, .get_hflags = emulator_get_hflags, - .exiting_smm = emulator_exiting_smm, .leave_smm = emulator_leave_smm, .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, @@ -8321,8 +8289,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK); - BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK); - BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK); ctxt->interruptibility = 0; ctxt->have_exception = false; @@ -8581,29 +8547,6 @@ static bool retry_instruction(struct x86_emulate_ctxt *ctxt, static int complete_emulated_mmio(struct kvm_vcpu *vcpu); static int complete_emulated_pio(struct kvm_vcpu *vcpu); -static void kvm_smm_changed(struct kvm_vcpu *vcpu, bool entering_smm) -{ - trace_kvm_smm_transition(vcpu->vcpu_id, vcpu->arch.smbase, entering_smm); - - if (entering_smm) { - vcpu->arch.hflags |= HF_SMM_MASK; - } else { - vcpu->arch.hflags &= ~(HF_SMM_MASK | HF_SMM_INSIDE_NMI_MASK); - - /* Process a latched INIT or SMI, if any. */ - kvm_make_request(KVM_REQ_EVENT, vcpu); - - /* - * Even if KVM_SET_SREGS2 loaded PDPTRs out of band, - * on SMM exit we still need to reload them from - * guest memory - */ - vcpu->arch.pdptrs_from_userspace = false; - } - - kvm_mmu_reset_context(vcpu); -} - static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7, unsigned long *db) { @@ -8835,7 +8778,9 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, write_fault_to_spt, emulation_type)) return 1; - if (ctxt->have_exception) { + + if (ctxt->have_exception && + !(emulation_type & EMULTYPE_SKIP)) { /* * #UD should result in just EMULATION_FAILED, and trap-like * exception should not be encountered during decode. @@ -9099,9 +9044,11 @@ static void tsc_khz_changed(void *data) struct cpufreq_freqs *freq = data; unsigned long khz = 0; + WARN_ON_ONCE(boot_cpu_has(X86_FEATURE_CONSTANT_TSC)); + if (data) khz = freq->new; - else if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + else khz = cpufreq_quick_get(raw_smp_processor_id()); if (!khz) khz = tsc_khz; @@ -9122,8 +9069,10 @@ static void kvm_hyperv_tsc_notifier(void) hyperv_stop_tsc_emulation(); /* TSC frequency always matches when on Hyper-V */ - for_each_present_cpu(cpu) - per_cpu(cpu_tsc_khz, cpu) = tsc_khz; + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + for_each_present_cpu(cpu) + per_cpu(cpu_tsc_khz, cpu) = tsc_khz; + } kvm_caps.max_guest_tsc_khz = tsc_khz; list_for_each_entry(kvm, &vm_list, vm_list) { @@ -9260,10 +9209,10 @@ static void kvm_timer_init(void) } cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); - } - cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online", - kvmclock_cpu_online, kvmclock_cpu_down_prep); + cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "x86/kvm/clk:online", + kvmclock_cpu_online, kvmclock_cpu_down_prep); + } } #ifdef CONFIG_X86_64 @@ -9423,10 +9372,11 @@ void kvm_arch_exit(void) #endif kvm_lapic_exit(); - if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) + if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block, CPUFREQ_TRANSITION_NOTIFIER); - cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); + cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE); + } #ifdef CONFIG_X86_64 pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier); irq_work_sync(&pvclock_irq_work); @@ -9805,7 +9755,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu) int kvm_check_nested_events(struct kvm_vcpu *vcpu) { - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { kvm_x86_ops.nested_ops->triple_fault(vcpu); return 1; } @@ -9993,6 +9943,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, * in order to make progress and get back here for another iteration. * The kvm_x86_ops hooks communicate this by returning -EBUSY. */ +#ifdef CONFIG_KVM_SMM if (vcpu->arch.smi_pending) { r = can_inject ? static_call(kvm_x86_smi_allowed)(vcpu, true) : -EBUSY; if (r < 0) @@ -10005,6 +9956,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, } else static_call(kvm_x86_enable_smi_window)(vcpu); } +#endif if (vcpu->arch.nmi_pending) { r = can_inject ? static_call(kvm_x86_nmi_allowed)(vcpu, true) : -EBUSY; @@ -10080,246 +10032,6 @@ static void process_nmi(struct kvm_vcpu *vcpu) kvm_make_request(KVM_REQ_EVENT, vcpu); } -static u32 enter_smm_get_segment_flags(struct kvm_segment *seg) -{ - u32 flags = 0; - flags |= seg->g << 23; - flags |= seg->db << 22; - flags |= seg->l << 21; - flags |= seg->avl << 20; - flags |= seg->present << 15; - flags |= seg->dpl << 13; - flags |= seg->s << 12; - flags |= seg->type << 8; - return flags; -} - -static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n) -{ - struct kvm_segment seg; - int offset; - - kvm_get_segment(vcpu, &seg, n); - put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector); - - if (n < 3) - offset = 0x7f84 + n * 12; - else - offset = 0x7f2c + (n - 3) * 12; - - put_smstate(u32, buf, offset + 8, seg.base); - put_smstate(u32, buf, offset + 4, seg.limit); - put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg)); -} - -#ifdef CONFIG_X86_64 -static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n) -{ - struct kvm_segment seg; - int offset; - u16 flags; - - kvm_get_segment(vcpu, &seg, n); - offset = 0x7e00 + n * 16; - - flags = enter_smm_get_segment_flags(&seg) >> 8; - put_smstate(u16, buf, offset, seg.selector); - put_smstate(u16, buf, offset + 2, flags); - put_smstate(u32, buf, offset + 4, seg.limit); - put_smstate(u64, buf, offset + 8, seg.base); -} -#endif - -static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf) -{ - struct desc_ptr dt; - struct kvm_segment seg; - unsigned long val; - int i; - - put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu)); - put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu)); - put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu)); - put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu)); - - for (i = 0; i < 8; i++) - put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read_raw(vcpu, i)); - - kvm_get_dr(vcpu, 6, &val); - put_smstate(u32, buf, 0x7fcc, (u32)val); - kvm_get_dr(vcpu, 7, &val); - put_smstate(u32, buf, 0x7fc8, (u32)val); - - kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); - put_smstate(u32, buf, 0x7fc4, seg.selector); - put_smstate(u32, buf, 0x7f64, seg.base); - put_smstate(u32, buf, 0x7f60, seg.limit); - put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg)); - - kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); - put_smstate(u32, buf, 0x7fc0, seg.selector); - put_smstate(u32, buf, 0x7f80, seg.base); - put_smstate(u32, buf, 0x7f7c, seg.limit); - put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg)); - - static_call(kvm_x86_get_gdt)(vcpu, &dt); - put_smstate(u32, buf, 0x7f74, dt.address); - put_smstate(u32, buf, 0x7f70, dt.size); - - static_call(kvm_x86_get_idt)(vcpu, &dt); - put_smstate(u32, buf, 0x7f58, dt.address); - put_smstate(u32, buf, 0x7f54, dt.size); - - for (i = 0; i < 6; i++) - enter_smm_save_seg_32(vcpu, buf, i); - - put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu)); - - /* revision id */ - put_smstate(u32, buf, 0x7efc, 0x00020000); - put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase); -} - -#ifdef CONFIG_X86_64 -static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf) -{ - struct desc_ptr dt; - struct kvm_segment seg; - unsigned long val; - int i; - - for (i = 0; i < 16; i++) - put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read_raw(vcpu, i)); - - put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu)); - put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu)); - - kvm_get_dr(vcpu, 6, &val); - put_smstate(u64, buf, 0x7f68, val); - kvm_get_dr(vcpu, 7, &val); - put_smstate(u64, buf, 0x7f60, val); - - put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu)); - put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu)); - put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu)); - - put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase); - - /* revision id */ - put_smstate(u32, buf, 0x7efc, 0x00020064); - - put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer); - - kvm_get_segment(vcpu, &seg, VCPU_SREG_TR); - put_smstate(u16, buf, 0x7e90, seg.selector); - put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8); - put_smstate(u32, buf, 0x7e94, seg.limit); - put_smstate(u64, buf, 0x7e98, seg.base); - - static_call(kvm_x86_get_idt)(vcpu, &dt); - put_smstate(u32, buf, 0x7e84, dt.size); - put_smstate(u64, buf, 0x7e88, dt.address); - - kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR); - put_smstate(u16, buf, 0x7e70, seg.selector); - put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8); - put_smstate(u32, buf, 0x7e74, seg.limit); - put_smstate(u64, buf, 0x7e78, seg.base); - - static_call(kvm_x86_get_gdt)(vcpu, &dt); - put_smstate(u32, buf, 0x7e64, dt.size); - put_smstate(u64, buf, 0x7e68, dt.address); - - for (i = 0; i < 6; i++) - enter_smm_save_seg_64(vcpu, buf, i); -} -#endif - -static void enter_smm(struct kvm_vcpu *vcpu) -{ - struct kvm_segment cs, ds; - struct desc_ptr dt; - unsigned long cr0; - char buf[512]; - - memset(buf, 0, 512); -#ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - enter_smm_save_state_64(vcpu, buf); - else -#endif - enter_smm_save_state_32(vcpu, buf); - - /* - * Give enter_smm() a chance to make ISA-specific changes to the vCPU - * state (e.g. leave guest mode) after we've saved the state into the - * SMM state-save area. - */ - static_call(kvm_x86_enter_smm)(vcpu, buf); - - kvm_smm_changed(vcpu, true); - kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf)); - - if (static_call(kvm_x86_get_nmi_mask)(vcpu)) - vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK; - else - static_call(kvm_x86_set_nmi_mask)(vcpu, true); - - kvm_set_rflags(vcpu, X86_EFLAGS_FIXED); - kvm_rip_write(vcpu, 0x8000); - - cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); - static_call(kvm_x86_set_cr0)(vcpu, cr0); - vcpu->arch.cr0 = cr0; - - static_call(kvm_x86_set_cr4)(vcpu, 0); - - /* Undocumented: IDT limit is set to zero on entry to SMM. */ - dt.address = dt.size = 0; - static_call(kvm_x86_set_idt)(vcpu, &dt); - - kvm_set_dr(vcpu, 7, DR7_FIXED_1); - - cs.selector = (vcpu->arch.smbase >> 4) & 0xffff; - cs.base = vcpu->arch.smbase; - - ds.selector = 0; - ds.base = 0; - - cs.limit = ds.limit = 0xffffffff; - cs.type = ds.type = 0x3; - cs.dpl = ds.dpl = 0; - cs.db = ds.db = 0; - cs.s = ds.s = 1; - cs.l = ds.l = 0; - cs.g = ds.g = 1; - cs.avl = ds.avl = 0; - cs.present = ds.present = 1; - cs.unusable = ds.unusable = 0; - cs.padding = ds.padding = 0; - - kvm_set_segment(vcpu, &cs, VCPU_SREG_CS); - kvm_set_segment(vcpu, &ds, VCPU_SREG_DS); - kvm_set_segment(vcpu, &ds, VCPU_SREG_ES); - kvm_set_segment(vcpu, &ds, VCPU_SREG_FS); - kvm_set_segment(vcpu, &ds, VCPU_SREG_GS); - kvm_set_segment(vcpu, &ds, VCPU_SREG_SS); - -#ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) - static_call(kvm_x86_set_efer)(vcpu, 0); -#endif - - kvm_update_cpuid_runtime(vcpu); - kvm_mmu_reset_context(vcpu); -} - -static void process_smi(struct kvm_vcpu *vcpu) -{ - vcpu->arch.smi_pending = true; - kvm_make_request(KVM_REQ_EVENT, vcpu); -} - void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, unsigned long *vcpu_bitmap) { @@ -10510,20 +10222,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) bool req_immediate_exit = false; - /* Forbid vmenter if vcpu dirty ring is soft-full */ - if (unlikely(vcpu->kvm->dirty_ring_size && - kvm_dirty_ring_soft_full(&vcpu->dirty_ring))) { - vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL; - trace_kvm_dirty_ring_exit(vcpu); - r = 0; - goto out; - } - if (kvm_request_pending(vcpu)) { if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) { r = -EIO; goto out; } + + if (kvm_dirty_ring_check_request(vcpu)) { + r = 0; + goto out; + } + if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) { r = 0; @@ -10547,23 +10256,37 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_mmu_sync_roots(vcpu); if (kvm_check_request(KVM_REQ_LOAD_MMU_PGD, vcpu)) kvm_mmu_load_pgd(vcpu); - if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) { + + /* + * Note, the order matters here, as flushing "all" TLB entries + * also flushes the "current" TLB entries, i.e. servicing the + * flush "all" will clear any request to flush "current". + */ + if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu)) kvm_vcpu_flush_tlb_all(vcpu); - /* Flushing all ASIDs flushes the current ASID... */ - kvm_clear_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu); - } kvm_service_local_tlb_flush_requests(vcpu); + /* + * Fall back to a "full" guest flush if Hyper-V's precise + * flushing fails. Note, Hyper-V's flushing is per-vCPU, but + * the flushes are considered "remote" and not "local" because + * the requests can be initiated from other vCPUs. + */ + if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) && + kvm_hv_vcpu_flush_tlb(vcpu)) + kvm_vcpu_flush_tlb_guest(vcpu); + if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; r = 0; goto out; } - if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { - if (is_guest_mode(vcpu)) { + if (kvm_test_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { + if (is_guest_mode(vcpu)) kvm_x86_ops.nested_ops->triple_fault(vcpu); - } else { + + if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; vcpu->mmio_needed = 0; r = 0; @@ -10578,8 +10301,10 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); +#ifdef CONFIG_KVM_SMM if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); +#endif if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); if (kvm_check_request(KVM_REQ_PMU, vcpu)) @@ -11827,7 +11552,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail = ~0; vcpu->arch.regs_dirty = ~0; - kvm_gpc_init(&vcpu->arch.pv_time); + kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm, vcpu, KVM_HOST_USES_PFN); if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -11893,6 +11618,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT; kvm_async_pf_hash_reset(vcpu); + + vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap; kvm_pmu_init(vcpu); vcpu->arch.pending_external_vector = -1; @@ -11997,8 +11724,18 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) WARN_ON_ONCE(!init_event && (old_cr0 || kvm_read_cr3(vcpu) || kvm_read_cr4(vcpu))); + /* + * SVM doesn't unconditionally VM-Exit on INIT and SHUTDOWN, thus it's + * possible to INIT the vCPU while L2 is active. Force the vCPU back + * into L1 as EFER.SVME is cleared on INIT (along with all other EFER + * bits), i.e. virtualization is disabled. + */ + if (is_guest_mode(vcpu)) + kvm_leave_nested(vcpu); + kvm_lapic_reset(vcpu, init_event); + WARN_ON_ONCE(is_guest_mode(vcpu) || is_smm(vcpu)); vcpu->arch.hflags = 0; vcpu->arch.smi_pending = 0; @@ -12317,7 +12054,6 @@ bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu) { return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id; } -EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp); bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) { @@ -12892,10 +12628,12 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) static_call(kvm_x86_nmi_allowed)(vcpu, false))) return true; +#ifdef CONFIG_KVM_SMM if (kvm_test_request(KVM_REQ_SMI, vcpu) || (vcpu->arch.smi_pending && static_call(kvm_x86_smi_allowed)(vcpu, false))) return true; +#endif if (kvm_arch_interrupt_allowed(vcpu) && (kvm_cpu_has_interrupt(vcpu) || @@ -12936,7 +12674,9 @@ bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) return true; if (kvm_test_request(KVM_REQ_NMI, vcpu) || +#ifdef CONFIG_KVM_SMM kvm_test_request(KVM_REQ_SMI, vcpu) || +#endif kvm_test_request(KVM_REQ_EVENT, vcpu)) return true; diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 829d3134c1eb..9de72586f406 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -27,6 +27,7 @@ struct kvm_caps { u64 supported_mce_cap; u64 supported_xcr0; u64 supported_xss; + u64 supported_perf_cap; }; void kvm_spurious_fault(void); diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 2dae413bd62a..d7af40240248 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -42,13 +42,12 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) int idx = srcu_read_lock(&kvm->srcu); if (gfn == GPA_INVALID) { - kvm_gpc_deactivate(kvm, gpc); + kvm_gpc_deactivate(gpc); goto out; } do { - ret = kvm_gpc_activate(kvm, gpc, NULL, KVM_HOST_USES_PFN, gpa, - PAGE_SIZE); + ret = kvm_gpc_activate(gpc, gpa, PAGE_SIZE); if (ret) goto out; @@ -170,112 +169,45 @@ static void kvm_xen_init_timer(struct kvm_vcpu *vcpu) vcpu->arch.xen.timer.function = xen_timer_callback; } -static void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) +static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) { struct kvm_vcpu_xen *vx = &v->arch.xen; - u64 now = get_kvmclock_ns(v->kvm); - u64 delta_ns = now - vx->runstate_entry_time; - u64 run_delay = current->sched_info.run_delay; - - if (unlikely(!vx->runstate_entry_time)) - vx->current_runstate = RUNSTATE_offline; - - /* - * Time waiting for the scheduler isn't "stolen" if the - * vCPU wasn't running anyway. - */ - if (vx->current_runstate == RUNSTATE_running) { - u64 steal_ns = run_delay - vx->last_steal; - - delta_ns -= steal_ns; - - vx->runstate_times[RUNSTATE_runnable] += steal_ns; - } - vx->last_steal = run_delay; - - vx->runstate_times[vx->current_runstate] += delta_ns; - vx->current_runstate = state; - vx->runstate_entry_time = now; -} - -void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) -{ - struct kvm_vcpu_xen *vx = &v->arch.xen; - struct gfn_to_pfn_cache *gpc = &vx->runstate_cache; - uint64_t *user_times; + struct gfn_to_pfn_cache *gpc1 = &vx->runstate_cache; + struct gfn_to_pfn_cache *gpc2 = &vx->runstate2_cache; + size_t user_len, user_len1, user_len2; + struct vcpu_runstate_info rs; unsigned long flags; - size_t user_len; - int *user_state; - - kvm_xen_update_runstate(v, state); - - if (!vx->runstate_cache.active) - return; - - if (IS_ENABLED(CONFIG_64BIT) && v->kvm->arch.xen.long_mode) - user_len = sizeof(struct vcpu_runstate_info); - else - user_len = sizeof(struct compat_vcpu_runstate_info); - - read_lock_irqsave(&gpc->lock, flags); - while (!kvm_gfn_to_pfn_cache_check(v->kvm, gpc, gpc->gpa, - user_len)) { - read_unlock_irqrestore(&gpc->lock, flags); - - /* When invoked from kvm_sched_out() we cannot sleep */ - if (state == RUNSTATE_runnable) - return; - - if (kvm_gfn_to_pfn_cache_refresh(v->kvm, gpc, gpc->gpa, user_len)) - return; - - read_lock_irqsave(&gpc->lock, flags); - } + size_t times_ofs; + uint8_t *update_bit = NULL; + uint64_t entry_time; + uint64_t *rs_times; + int *rs_state; /* * The only difference between 32-bit and 64-bit versions of the - * runstate struct us the alignment of uint64_t in 32-bit, which + * runstate struct is the alignment of uint64_t in 32-bit, which * means that the 64-bit version has an additional 4 bytes of - * padding after the first field 'state'. - * - * So we use 'int __user *user_state' to point to the state field, - * and 'uint64_t __user *user_times' for runstate_entry_time. So - * the actual array of time[] in each state starts at user_times[1]. + * padding after the first field 'state'. Let's be really really + * paranoid about that, and matching it with our internal data + * structures that we memcpy into it... */ BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != 0); BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state) != 0); BUILD_BUG_ON(sizeof(struct compat_vcpu_runstate_info) != 0x2c); #ifdef CONFIG_X86_64 + /* + * The 64-bit structure has 4 bytes of padding before 'state_entry_time' + * so each subsequent field is shifted by 4, and it's 4 bytes longer. + */ BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) != offsetof(struct compat_vcpu_runstate_info, state_entry_time) + 4); BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, time) != offsetof(struct compat_vcpu_runstate_info, time) + 4); + BUILD_BUG_ON(sizeof(struct vcpu_runstate_info) != 0x2c + 4); #endif - - user_state = gpc->khva; - - if (IS_ENABLED(CONFIG_64BIT) && v->kvm->arch.xen.long_mode) - user_times = gpc->khva + offsetof(struct vcpu_runstate_info, - state_entry_time); - else - user_times = gpc->khva + offsetof(struct compat_vcpu_runstate_info, - state_entry_time); - /* - * First write the updated state_entry_time at the appropriate - * location determined by 'offset'. - */ - BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state_entry_time) != - sizeof(user_times[0])); - BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) != - sizeof(user_times[0])); - - user_times[0] = vx->runstate_entry_time | XEN_RUNSTATE_UPDATE; - smp_wmb(); - - /* - * Next, write the new runstate. This is in the *same* place - * for 32-bit and 64-bit guests, asserted here for paranoia. + * The state field is in the same place at the start of both structs, + * and is the same size (int) as vx->current_runstate. */ BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state) != offsetof(struct compat_vcpu_runstate_info, state)); @@ -284,34 +216,238 @@ void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, int state) BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state) != sizeof(vx->current_runstate)); - *user_state = vx->current_runstate; + /* + * The state_entry_time field is 64 bits in both versions, and the + * XEN_RUNSTATE_UPDATE flag is in the top bit, which given that x86 + * is little-endian means that it's in the last *byte* of the word. + * That detail is important later. + */ + BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, state_entry_time) != + sizeof(uint64_t)); + BUILD_BUG_ON(sizeof_field(struct compat_vcpu_runstate_info, state_entry_time) != + sizeof(uint64_t)); + BUILD_BUG_ON((XEN_RUNSTATE_UPDATE >> 56) != 0x80); /* - * Write the actual runstate times immediately after the - * runstate_entry_time. + * The time array is four 64-bit quantities in both versions, matching + * the vx->runstate_times and immediately following state_entry_time. */ BUILD_BUG_ON(offsetof(struct vcpu_runstate_info, state_entry_time) != - offsetof(struct vcpu_runstate_info, time) - sizeof(u64)); + offsetof(struct vcpu_runstate_info, time) - sizeof(uint64_t)); BUILD_BUG_ON(offsetof(struct compat_vcpu_runstate_info, state_entry_time) != - offsetof(struct compat_vcpu_runstate_info, time) - sizeof(u64)); + offsetof(struct compat_vcpu_runstate_info, time) - sizeof(uint64_t)); BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) != sizeof_field(struct compat_vcpu_runstate_info, time)); BUILD_BUG_ON(sizeof_field(struct vcpu_runstate_info, time) != sizeof(vx->runstate_times)); - memcpy(user_times + 1, vx->runstate_times, sizeof(vx->runstate_times)); - smp_wmb(); + if (IS_ENABLED(CONFIG_64BIT) && v->kvm->arch.xen.long_mode) { + user_len = sizeof(struct vcpu_runstate_info); + times_ofs = offsetof(struct vcpu_runstate_info, + state_entry_time); + } else { + user_len = sizeof(struct compat_vcpu_runstate_info); + times_ofs = offsetof(struct compat_vcpu_runstate_info, + state_entry_time); + } + + /* + * There are basically no alignment constraints. The guest can set it + * up so it crosses from one page to the next, and at arbitrary byte + * alignment (and the 32-bit ABI doesn't align the 64-bit integers + * anyway, even if the overall struct had been 64-bit aligned). + */ + if ((gpc1->gpa & ~PAGE_MASK) + user_len >= PAGE_SIZE) { + user_len1 = PAGE_SIZE - (gpc1->gpa & ~PAGE_MASK); + user_len2 = user_len - user_len1; + } else { + user_len1 = user_len; + user_len2 = 0; + } + BUG_ON(user_len1 + user_len2 != user_len); + + retry: + /* + * Attempt to obtain the GPC lock on *both* (if there are two) + * gfn_to_pfn caches that cover the region. + */ + read_lock_irqsave(&gpc1->lock, flags); + while (!kvm_gpc_check(gpc1, user_len1)) { + read_unlock_irqrestore(&gpc1->lock, flags); + + /* When invoked from kvm_sched_out() we cannot sleep */ + if (atomic) + return; + + if (kvm_gpc_refresh(gpc1, user_len1)) + return; + + read_lock_irqsave(&gpc1->lock, flags); + } + + if (likely(!user_len2)) { + /* + * Set up three pointers directly to the runstate_info + * struct in the guest (via the GPC). + * + * • @rs_state → state field + * • @rs_times → state_entry_time field. + * • @update_bit → last byte of state_entry_time, which + * contains the XEN_RUNSTATE_UPDATE bit. + */ + rs_state = gpc1->khva; + rs_times = gpc1->khva + times_ofs; + if (v->kvm->arch.xen.runstate_update_flag) + update_bit = ((void *)(&rs_times[1])) - 1; + } else { + /* + * The guest's runstate_info is split across two pages and we + * need to hold and validate both GPCs simultaneously. We can + * declare a lock ordering GPC1 > GPC2 because nothing else + * takes them more than one at a time. + */ + read_lock(&gpc2->lock); + + if (!kvm_gpc_check(gpc2, user_len2)) { + read_unlock(&gpc2->lock); + read_unlock_irqrestore(&gpc1->lock, flags); + + /* When invoked from kvm_sched_out() we cannot sleep */ + if (atomic) + return; + + /* + * Use kvm_gpc_activate() here because if the runstate + * area was configured in 32-bit mode and only extends + * to the second page now because the guest changed to + * 64-bit mode, the second GPC won't have been set up. + */ + if (kvm_gpc_activate(gpc2, gpc1->gpa + user_len1, + user_len2)) + return; + + /* + * We dropped the lock on GPC1 so we have to go all the + * way back and revalidate that too. + */ + goto retry; + } + + /* + * In this case, the runstate_info struct will be assembled on + * the kernel stack (compat or not as appropriate) and will + * be copied to GPC1/GPC2 with a dual memcpy. Set up the three + * rs pointers accordingly. + */ + rs_times = &rs.state_entry_time; + + /* + * The rs_state pointer points to the start of what we'll + * copy to the guest, which in the case of a compat guest + * is the 32-bit field that the compiler thinks is padding. + */ + rs_state = ((void *)rs_times) - times_ofs; + + /* + * The update_bit is still directly in the guest memory, + * via one GPC or the other. + */ + if (v->kvm->arch.xen.runstate_update_flag) { + if (user_len1 >= times_ofs + sizeof(uint64_t)) + update_bit = gpc1->khva + times_ofs + + sizeof(uint64_t) - 1; + else + update_bit = gpc2->khva + times_ofs + + sizeof(uint64_t) - 1 - user_len1; + } + +#ifdef CONFIG_X86_64 + /* + * Don't leak kernel memory through the padding in the 64-bit + * version of the struct. + */ + memset(&rs, 0, offsetof(struct vcpu_runstate_info, state_entry_time)); +#endif + } + + /* + * First, set the XEN_RUNSTATE_UPDATE bit in the top bit of the + * state_entry_time field, directly in the guest. We need to set + * that (and write-barrier) before writing to the rest of the + * structure, and clear it last. Just as Xen does, we address the + * single *byte* in which it resides because it might be in a + * different cache line to the rest of the 64-bit word, due to + * the (lack of) alignment constraints. + */ + entry_time = vx->runstate_entry_time; + if (update_bit) { + entry_time |= XEN_RUNSTATE_UPDATE; + *update_bit = (vx->runstate_entry_time | XEN_RUNSTATE_UPDATE) >> 56; + smp_wmb(); + } /* - * Finally, clear the XEN_RUNSTATE_UPDATE bit in the guest's - * runstate_entry_time field. + * Now assemble the actual structure, either on our kernel stack + * or directly in the guest according to how the rs_state and + * rs_times pointers were set up above. */ - user_times[0] &= ~XEN_RUNSTATE_UPDATE; + *rs_state = vx->current_runstate; + rs_times[0] = entry_time; + memcpy(rs_times + 1, vx->runstate_times, sizeof(vx->runstate_times)); + + /* For the split case, we have to then copy it to the guest. */ + if (user_len2) { + memcpy(gpc1->khva, rs_state, user_len1); + memcpy(gpc2->khva, ((void *)rs_state) + user_len1, user_len2); + } smp_wmb(); - read_unlock_irqrestore(&gpc->lock, flags); + /* Finally, clear the XEN_RUNSTATE_UPDATE bit. */ + if (update_bit) { + entry_time &= ~XEN_RUNSTATE_UPDATE; + *update_bit = entry_time >> 56; + smp_wmb(); + } - mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT); + if (user_len2) + read_unlock(&gpc2->lock); + + read_unlock_irqrestore(&gpc1->lock, flags); + + mark_page_dirty_in_slot(v->kvm, gpc1->memslot, gpc1->gpa >> PAGE_SHIFT); + if (user_len2) + mark_page_dirty_in_slot(v->kvm, gpc2->memslot, gpc2->gpa >> PAGE_SHIFT); +} + +void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) +{ + struct kvm_vcpu_xen *vx = &v->arch.xen; + u64 now = get_kvmclock_ns(v->kvm); + u64 delta_ns = now - vx->runstate_entry_time; + u64 run_delay = current->sched_info.run_delay; + + if (unlikely(!vx->runstate_entry_time)) + vx->current_runstate = RUNSTATE_offline; + + /* + * Time waiting for the scheduler isn't "stolen" if the + * vCPU wasn't running anyway. + */ + if (vx->current_runstate == RUNSTATE_running) { + u64 steal_ns = run_delay - vx->last_steal; + + delta_ns -= steal_ns; + + vx->runstate_times[RUNSTATE_runnable] += steal_ns; + } + vx->last_steal = run_delay; + + vx->runstate_times[vx->current_runstate] += delta_ns; + vx->current_runstate = state; + vx->runstate_entry_time = now; + + if (vx->runstate_cache.active) + kvm_xen_update_runstate_guest(v, state == RUNSTATE_runnable); } static void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) @@ -352,12 +488,10 @@ void kvm_xen_inject_pending_events(struct kvm_vcpu *v) * little more honest about it. */ read_lock_irqsave(&gpc->lock, flags); - while (!kvm_gfn_to_pfn_cache_check(v->kvm, gpc, gpc->gpa, - sizeof(struct vcpu_info))) { + while (!kvm_gpc_check(gpc, sizeof(struct vcpu_info))) { read_unlock_irqrestore(&gpc->lock, flags); - if (kvm_gfn_to_pfn_cache_refresh(v->kvm, gpc, gpc->gpa, - sizeof(struct vcpu_info))) + if (kvm_gpc_refresh(gpc, sizeof(struct vcpu_info))) return; read_lock_irqsave(&gpc->lock, flags); @@ -417,8 +551,7 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) sizeof_field(struct compat_vcpu_info, evtchn_upcall_pending)); read_lock_irqsave(&gpc->lock, flags); - while (!kvm_gfn_to_pfn_cache_check(v->kvm, gpc, gpc->gpa, - sizeof(struct vcpu_info))) { + while (!kvm_gpc_check(gpc, sizeof(struct vcpu_info))) { read_unlock_irqrestore(&gpc->lock, flags); /* @@ -432,8 +565,7 @@ int __kvm_xen_has_interrupt(struct kvm_vcpu *v) if (in_atomic() || !task_is_running(current)) return 1; - if (kvm_gfn_to_pfn_cache_refresh(v->kvm, gpc, gpc->gpa, - sizeof(struct vcpu_info))) { + if (kvm_gpc_refresh(gpc, sizeof(struct vcpu_info))) { /* * If this failed, userspace has screwed up the * vcpu_info mapping. No interrupts for you. @@ -493,6 +625,17 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) r = 0; break; + case KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + mutex_lock(&kvm->lock); + kvm->arch.xen.runstate_update_flag = !!data->u.runstate_update_flag; + mutex_unlock(&kvm->lock); + r = 0; + break; + default: break; } @@ -530,6 +673,15 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) r = 0; break; + case KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + data->u.runstate_update_flag = kvm->arch.xen.runstate_update_flag; + r = 0; + break; + default: break; } @@ -554,15 +706,13 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) offsetof(struct compat_vcpu_info, time)); if (data->u.gpa == GPA_INVALID) { - kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache); + kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache); r = 0; break; } - r = kvm_gpc_activate(vcpu->kvm, - &vcpu->arch.xen.vcpu_info_cache, NULL, - KVM_HOST_USES_PFN, data->u.gpa, - sizeof(struct vcpu_info)); + r = kvm_gpc_activate(&vcpu->arch.xen.vcpu_info_cache, + data->u.gpa, sizeof(struct vcpu_info)); if (!r) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); @@ -570,37 +720,65 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: if (data->u.gpa == GPA_INVALID) { - kvm_gpc_deactivate(vcpu->kvm, - &vcpu->arch.xen.vcpu_time_info_cache); + kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_time_info_cache); r = 0; break; } - r = kvm_gpc_activate(vcpu->kvm, - &vcpu->arch.xen.vcpu_time_info_cache, - NULL, KVM_HOST_USES_PFN, data->u.gpa, + r = kvm_gpc_activate(&vcpu->arch.xen.vcpu_time_info_cache, + data->u.gpa, sizeof(struct pvclock_vcpu_time_info)); if (!r) kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu); break; - case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR: + case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR: { + size_t sz, sz1, sz2; + if (!sched_info_on()) { r = -EOPNOTSUPP; break; } if (data->u.gpa == GPA_INVALID) { - kvm_gpc_deactivate(vcpu->kvm, - &vcpu->arch.xen.runstate_cache); r = 0; + deactivate_out: + kvm_gpc_deactivate(&vcpu->arch.xen.runstate_cache); + kvm_gpc_deactivate(&vcpu->arch.xen.runstate2_cache); break; } - r = kvm_gpc_activate(vcpu->kvm, &vcpu->arch.xen.runstate_cache, - NULL, KVM_HOST_USES_PFN, data->u.gpa, - sizeof(struct vcpu_runstate_info)); - break; + /* + * If the guest switches to 64-bit mode after setting the runstate + * address, that's actually OK. kvm_xen_update_runstate_guest() + * will cope. + */ + if (IS_ENABLED(CONFIG_64BIT) && vcpu->kvm->arch.xen.long_mode) + sz = sizeof(struct vcpu_runstate_info); + else + sz = sizeof(struct compat_vcpu_runstate_info); + + /* How much fits in the (first) page? */ + sz1 = PAGE_SIZE - (data->u.gpa & ~PAGE_MASK); + r = kvm_gpc_activate(&vcpu->arch.xen.runstate_cache, + data->u.gpa, sz1); + if (r) + goto deactivate_out; + + /* Either map the second page, or deactivate the second GPC */ + if (sz1 >= sz) { + kvm_gpc_deactivate(&vcpu->arch.xen.runstate2_cache); + } else { + sz2 = sz - sz1; + BUG_ON((data->u.gpa + sz1) & ~PAGE_MASK); + r = kvm_gpc_activate(&vcpu->arch.xen.runstate2_cache, + data->u.gpa + sz1, sz2); + if (r) + goto deactivate_out; + } + kvm_xen_update_runstate_guest(vcpu, false); + break; + } case KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT: if (!sched_info_on()) { r = -EOPNOTSUPP; @@ -693,6 +871,8 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) if (data->u.runstate.state <= RUNSTATE_offline) kvm_xen_update_runstate(vcpu, data->u.runstate.state); + else if (vcpu->arch.xen.runstate_cache.active) + kvm_xen_update_runstate_guest(vcpu, false); r = 0; break; @@ -954,6 +1134,14 @@ static int kvm_xen_hypercall_complete_userspace(struct kvm_vcpu *vcpu) return kvm_xen_hypercall_set_result(vcpu, run->xen.u.hcall.result); } +static inline int max_evtchn_port(struct kvm *kvm) +{ + if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) + return EVTCHN_2L_NR_CHANNELS; + else + return COMPAT_EVTCHN_2L_NR_CHANNELS; +} + static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports, evtchn_port_t *ports) { @@ -964,9 +1152,9 @@ static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports, bool ret = true; int idx, i; - read_lock_irqsave(&gpc->lock, flags); idx = srcu_read_lock(&kvm->srcu); - if (!kvm_gfn_to_pfn_cache_check(kvm, gpc, gpc->gpa, PAGE_SIZE)) + read_lock_irqsave(&gpc->lock, flags); + if (!kvm_gpc_check(gpc, PAGE_SIZE)) goto out_rcu; ret = false; @@ -986,8 +1174,8 @@ static bool wait_pending_event(struct kvm_vcpu *vcpu, int nr_ports, } out_rcu: - srcu_read_unlock(&kvm->srcu, idx); read_unlock_irqrestore(&gpc->lock, flags); + srcu_read_unlock(&kvm->srcu, idx); return ret; } @@ -1000,20 +1188,45 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, evtchn_port_t port, *ports; gpa_t gpa; - if (!longmode || !lapic_in_kernel(vcpu) || + if (!lapic_in_kernel(vcpu) || !(vcpu->kvm->arch.xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_EVTCHN_SEND)) return false; idx = srcu_read_lock(&vcpu->kvm->srcu); gpa = kvm_mmu_gva_to_gpa_system(vcpu, param, NULL); srcu_read_unlock(&vcpu->kvm->srcu, idx); - - if (!gpa || kvm_vcpu_read_guest(vcpu, gpa, &sched_poll, - sizeof(sched_poll))) { + if (!gpa) { *r = -EFAULT; return true; } + if (IS_ENABLED(CONFIG_64BIT) && !longmode) { + struct compat_sched_poll sp32; + + /* Sanity check that the compat struct definition is correct */ + BUILD_BUG_ON(sizeof(sp32) != 16); + + if (kvm_vcpu_read_guest(vcpu, gpa, &sp32, sizeof(sp32))) { + *r = -EFAULT; + return true; + } + + /* + * This is a 32-bit pointer to an array of evtchn_port_t which + * are uint32_t, so once it's converted no further compat + * handling is needed. + */ + sched_poll.ports = (void *)(unsigned long)(sp32.ports); + sched_poll.nr_ports = sp32.nr_ports; + sched_poll.timeout = sp32.timeout; + } else { + if (kvm_vcpu_read_guest(vcpu, gpa, &sched_poll, + sizeof(sched_poll))) { + *r = -EFAULT; + return true; + } + } + if (unlikely(sched_poll.nr_ports > 1)) { /* Xen (unofficially) limits number of pollers to 128 */ if (sched_poll.nr_ports > 128) { @@ -1042,6 +1255,10 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode, *r = -EFAULT; goto out; } + if (ports[i] >= max_evtchn_port(vcpu->kvm)) { + *r = -EINVAL; + goto out; + } } if (sched_poll.nr_ports == 1) @@ -1215,6 +1432,7 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) bool longmode; u64 input, params[6], r = -ENOSYS; bool handled = false; + u8 cpl; input = (u64)kvm_register_read(vcpu, VCPU_REGS_RAX); @@ -1242,9 +1460,17 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) params[5] = (u64)kvm_r9_read(vcpu); } #endif - trace_kvm_xen_hypercall(input, params[0], params[1], params[2], + cpl = static_call(kvm_x86_get_cpl)(vcpu); + trace_kvm_xen_hypercall(cpl, input, params[0], params[1], params[2], params[3], params[4], params[5]); + /* + * Only allow hypercall acceleration for CPL0. The rare hypercalls that + * are permitted in guest userspace can be handled by the VMM. + */ + if (unlikely(cpl > 0)) + goto handle_in_userspace; + switch (input) { case __HYPERVISOR_xen_version: if (params[0] == XENVER_version && vcpu->kvm->arch.xen.xen_version) { @@ -1279,10 +1505,11 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) if (handled) return kvm_xen_hypercall_set_result(vcpu, r); +handle_in_userspace: vcpu->run->exit_reason = KVM_EXIT_XEN; vcpu->run->xen.type = KVM_EXIT_XEN_HCALL; vcpu->run->xen.u.hcall.longmode = longmode; - vcpu->run->xen.u.hcall.cpl = static_call(kvm_x86_get_cpl)(vcpu); + vcpu->run->xen.u.hcall.cpl = cpl; vcpu->run->xen.u.hcall.input = input; vcpu->run->xen.u.hcall.params[0] = params[0]; vcpu->run->xen.u.hcall.params[1] = params[1]; @@ -1297,14 +1524,6 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu) return 0; } -static inline int max_evtchn_port(struct kvm *kvm) -{ - if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) - return EVTCHN_2L_NR_CHANNELS; - else - return COMPAT_EVTCHN_2L_NR_CHANNELS; -} - static void kvm_xen_check_poller(struct kvm_vcpu *vcpu, int port) { int poll_evtchn = vcpu->arch.xen.poll_evtchn; @@ -1357,7 +1576,7 @@ int kvm_xen_set_evtchn_fast(struct kvm_xen_evtchn *xe, struct kvm *kvm) idx = srcu_read_lock(&kvm->srcu); read_lock_irqsave(&gpc->lock, flags); - if (!kvm_gfn_to_pfn_cache_check(kvm, gpc, gpc->gpa, PAGE_SIZE)) + if (!kvm_gpc_check(gpc, PAGE_SIZE)) goto out_rcu; if (IS_ENABLED(CONFIG_64BIT) && kvm->arch.xen.long_mode) { @@ -1391,7 +1610,7 @@ int kvm_xen_set_evtchn_fast(struct kvm_xen_evtchn *xe, struct kvm *kvm) gpc = &vcpu->arch.xen.vcpu_info_cache; read_lock_irqsave(&gpc->lock, flags); - if (!kvm_gfn_to_pfn_cache_check(kvm, gpc, gpc->gpa, sizeof(struct vcpu_info))) { + if (!kvm_gpc_check(gpc, sizeof(struct vcpu_info))) { /* * Could not access the vcpu_info. Set the bit in-kernel * and prod the vCPU to deliver it for itself. @@ -1489,7 +1708,7 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm) break; idx = srcu_read_lock(&kvm->srcu); - rc = kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpc->gpa, PAGE_SIZE); + rc = kvm_gpc_refresh(gpc, PAGE_SIZE); srcu_read_unlock(&kvm->srcu, idx); } while(!rc); @@ -1819,9 +2038,14 @@ void kvm_xen_init_vcpu(struct kvm_vcpu *vcpu) timer_setup(&vcpu->arch.xen.poll_timer, cancel_evtchn_poll, 0); - kvm_gpc_init(&vcpu->arch.xen.runstate_cache); - kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache); - kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache); + kvm_gpc_init(&vcpu->arch.xen.runstate_cache, vcpu->kvm, NULL, + KVM_HOST_USES_PFN); + kvm_gpc_init(&vcpu->arch.xen.runstate2_cache, vcpu->kvm, NULL, + KVM_HOST_USES_PFN); + kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache, vcpu->kvm, NULL, + KVM_HOST_USES_PFN); + kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache, vcpu->kvm, NULL, + KVM_HOST_USES_PFN); } void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) @@ -1829,9 +2053,10 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) if (kvm_xen_timer_enabled(vcpu)) kvm_xen_stop_timer(vcpu); - kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.runstate_cache); - kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_info_cache); - kvm_gpc_deactivate(vcpu->kvm, &vcpu->arch.xen.vcpu_time_info_cache); + kvm_gpc_deactivate(&vcpu->arch.xen.runstate_cache); + kvm_gpc_deactivate(&vcpu->arch.xen.runstate2_cache); + kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache); + kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_time_info_cache); del_timer_sync(&vcpu->arch.xen.poll_timer); } @@ -1839,7 +2064,7 @@ void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) void kvm_xen_init_vm(struct kvm *kvm) { idr_init(&kvm->arch.xen.evtchn_ports); - kvm_gpc_init(&kvm->arch.xen.shinfo_cache); + kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN); } void kvm_xen_destroy_vm(struct kvm *kvm) @@ -1847,7 +2072,7 @@ void kvm_xen_destroy_vm(struct kvm *kvm) struct evtchnfd *evtchnfd; int i; - kvm_gpc_deactivate(kvm, &kvm->arch.xen.shinfo_cache); + kvm_gpc_deactivate(&kvm->arch.xen.shinfo_cache); idr_for_each_entry(&kvm->arch.xen.evtchn_ports, evtchnfd, i) { if (!evtchnfd->deliver.port.port) diff --git a/arch/x86/kvm/xen.h b/arch/x86/kvm/xen.h index 532a535a9e99..ea33d80a0c51 100644 --- a/arch/x86/kvm/xen.h +++ b/arch/x86/kvm/xen.h @@ -143,11 +143,11 @@ int kvm_xen_hypercall(struct kvm_vcpu *vcpu); #include <asm/xen/interface.h> #include <xen/interface/vcpu.h> -void kvm_xen_update_runstate_guest(struct kvm_vcpu *vcpu, int state); +void kvm_xen_update_runstate(struct kvm_vcpu *vcpu, int state); static inline void kvm_xen_runstate_set_running(struct kvm_vcpu *vcpu) { - kvm_xen_update_runstate_guest(vcpu, RUNSTATE_running); + kvm_xen_update_runstate(vcpu, RUNSTATE_running); } static inline void kvm_xen_runstate_set_preempted(struct kvm_vcpu *vcpu) @@ -162,7 +162,7 @@ static inline void kvm_xen_runstate_set_preempted(struct kvm_vcpu *vcpu) if (WARN_ON_ONCE(!vcpu->preempted)) return; - kvm_xen_update_runstate_guest(vcpu, RUNSTATE_runnable); + kvm_xen_update_runstate(vcpu, RUNSTATE_runnable); } /* 32-bit compatibility definitions, also used natively in 32-bit build */ @@ -207,4 +207,11 @@ struct compat_vcpu_runstate_info { uint64_t time[4]; } __attribute__((packed)); +struct compat_sched_poll { + /* This is actually a guest virtual address which points to ports. */ + uint32_t ports; + unsigned int nr_ports; + uint64_t timeout; +}; + #endif /* __ARCH_X86_KVM_XEN_H__ */ diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index 7ba5f61d7273..4f1a40a86534 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -60,6 +60,7 @@ ifeq ($(CONFIG_X86_32),y) lib-y += checksum_32.o lib-y += strstr_32.o lib-y += string_32.o + lib-y += memmove_32.o ifneq ($(CONFIG_X86_CMPXCHG64),y) lib-y += cmpxchg8b_emu.o atomic64_386_32.o endif diff --git a/arch/x86/lib/error-inject.c b/arch/x86/lib/error-inject.c index 1e3de0769b81..b5a6d83106bc 100644 --- a/arch/x86/lib/error-inject.c +++ b/arch/x86/lib/error-inject.c @@ -11,6 +11,7 @@ asm( ".text\n" ".type just_return_func, @function\n" ".globl just_return_func\n" + ASM_FUNC_ALIGN "just_return_func:\n" ANNOTATE_NOENDBR ASM_RET diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c index ef3af7ff2c8a..a29b64befb93 100644 --- a/arch/x86/lib/memcpy_32.c +++ b/arch/x86/lib/memcpy_32.c @@ -17,190 +17,3 @@ __visible void *memset(void *s, int c, size_t count) return __memset(s, c, count); } EXPORT_SYMBOL(memset); - -__visible void *memmove(void *dest, const void *src, size_t n) -{ - int d0,d1,d2,d3,d4,d5; - char *ret = dest; - - __asm__ __volatile__( - /* Handle more 16 bytes in loop */ - "cmp $0x10, %0\n\t" - "jb 1f\n\t" - - /* Decide forward/backward copy mode */ - "cmp %2, %1\n\t" - "jb 2f\n\t" - - /* - * movs instruction have many startup latency - * so we handle small size by general register. - */ - "cmp $680, %0\n\t" - "jb 3f\n\t" - /* - * movs instruction is only good for aligned case. - */ - "mov %1, %3\n\t" - "xor %2, %3\n\t" - "and $0xff, %3\n\t" - "jz 4f\n\t" - "3:\n\t" - "sub $0x10, %0\n\t" - - /* - * We gobble 16 bytes forward in each loop. - */ - "3:\n\t" - "sub $0x10, %0\n\t" - "mov 0*4(%1), %3\n\t" - "mov 1*4(%1), %4\n\t" - "mov %3, 0*4(%2)\n\t" - "mov %4, 1*4(%2)\n\t" - "mov 2*4(%1), %3\n\t" - "mov 3*4(%1), %4\n\t" - "mov %3, 2*4(%2)\n\t" - "mov %4, 3*4(%2)\n\t" - "lea 0x10(%1), %1\n\t" - "lea 0x10(%2), %2\n\t" - "jae 3b\n\t" - "add $0x10, %0\n\t" - "jmp 1f\n\t" - - /* - * Handle data forward by movs. - */ - ".p2align 4\n\t" - "4:\n\t" - "mov -4(%1, %0), %3\n\t" - "lea -4(%2, %0), %4\n\t" - "shr $2, %0\n\t" - "rep movsl\n\t" - "mov %3, (%4)\n\t" - "jmp 11f\n\t" - /* - * Handle data backward by movs. - */ - ".p2align 4\n\t" - "6:\n\t" - "mov (%1), %3\n\t" - "mov %2, %4\n\t" - "lea -4(%1, %0), %1\n\t" - "lea -4(%2, %0), %2\n\t" - "shr $2, %0\n\t" - "std\n\t" - "rep movsl\n\t" - "mov %3,(%4)\n\t" - "cld\n\t" - "jmp 11f\n\t" - - /* - * Start to prepare for backward copy. - */ - ".p2align 4\n\t" - "2:\n\t" - "cmp $680, %0\n\t" - "jb 5f\n\t" - "mov %1, %3\n\t" - "xor %2, %3\n\t" - "and $0xff, %3\n\t" - "jz 6b\n\t" - - /* - * Calculate copy position to tail. - */ - "5:\n\t" - "add %0, %1\n\t" - "add %0, %2\n\t" - "sub $0x10, %0\n\t" - - /* - * We gobble 16 bytes backward in each loop. - */ - "7:\n\t" - "sub $0x10, %0\n\t" - - "mov -1*4(%1), %3\n\t" - "mov -2*4(%1), %4\n\t" - "mov %3, -1*4(%2)\n\t" - "mov %4, -2*4(%2)\n\t" - "mov -3*4(%1), %3\n\t" - "mov -4*4(%1), %4\n\t" - "mov %3, -3*4(%2)\n\t" - "mov %4, -4*4(%2)\n\t" - "lea -0x10(%1), %1\n\t" - "lea -0x10(%2), %2\n\t" - "jae 7b\n\t" - /* - * Calculate copy position to head. - */ - "add $0x10, %0\n\t" - "sub %0, %1\n\t" - "sub %0, %2\n\t" - - /* - * Move data from 8 bytes to 15 bytes. - */ - ".p2align 4\n\t" - "1:\n\t" - "cmp $8, %0\n\t" - "jb 8f\n\t" - "mov 0*4(%1), %3\n\t" - "mov 1*4(%1), %4\n\t" - "mov -2*4(%1, %0), %5\n\t" - "mov -1*4(%1, %0), %1\n\t" - - "mov %3, 0*4(%2)\n\t" - "mov %4, 1*4(%2)\n\t" - "mov %5, -2*4(%2, %0)\n\t" - "mov %1, -1*4(%2, %0)\n\t" - "jmp 11f\n\t" - - /* - * Move data from 4 bytes to 7 bytes. - */ - ".p2align 4\n\t" - "8:\n\t" - "cmp $4, %0\n\t" - "jb 9f\n\t" - "mov 0*4(%1), %3\n\t" - "mov -1*4(%1, %0), %4\n\t" - "mov %3, 0*4(%2)\n\t" - "mov %4, -1*4(%2, %0)\n\t" - "jmp 11f\n\t" - - /* - * Move data from 2 bytes to 3 bytes. - */ - ".p2align 4\n\t" - "9:\n\t" - "cmp $2, %0\n\t" - "jb 10f\n\t" - "movw 0*2(%1), %%dx\n\t" - "movw -1*2(%1, %0), %%bx\n\t" - "movw %%dx, 0*2(%2)\n\t" - "movw %%bx, -1*2(%2, %0)\n\t" - "jmp 11f\n\t" - - /* - * Move data for 1 byte. - */ - ".p2align 4\n\t" - "10:\n\t" - "cmp $1, %0\n\t" - "jb 11f\n\t" - "movb (%1), %%cl\n\t" - "movb %%cl, (%2)\n\t" - ".p2align 4\n\t" - "11:" - : "=&c" (d0), "=&S" (d1), "=&D" (d2), - "=r" (d3),"=r" (d4), "=r"(d5) - :"0" (n), - "1" (src), - "2" (dest) - :"memory"); - - return ret; - -} -EXPORT_SYMBOL(memmove); diff --git a/arch/x86/lib/memmove_32.S b/arch/x86/lib/memmove_32.S new file mode 100644 index 000000000000..0588b2c0fc95 --- /dev/null +++ b/arch/x86/lib/memmove_32.S @@ -0,0 +1,200 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#include <linux/linkage.h> +#include <asm/export.h> + +SYM_FUNC_START(memmove) +/* + * void *memmove(void *dest_in, const void *src_in, size_t n) + * -mregparm=3 passes these in registers: + * dest_in: %eax + * src_in: %edx + * n: %ecx + * See also: arch/x86/entry/calling.h for description of the calling convention. + * + * n can remain in %ecx, but for `rep movsl`, we'll need dest in %edi and src + * in %esi. + */ +.set dest_in, %eax +.set dest, %edi +.set src_in, %edx +.set src, %esi +.set n, %ecx +.set tmp0, %edx +.set tmp0w, %dx +.set tmp1, %ebx +.set tmp1w, %bx +.set tmp2, %eax +.set tmp3b, %cl + +/* + * Save all callee-saved registers, because this function is going to clobber + * all of them: + */ + pushl %ebp + movl %esp, %ebp // set standard frame pointer + + pushl %ebx + pushl %edi + pushl %esi + pushl %eax // save 'dest_in' parameter [eax] as the return value + + movl src_in, src + movl dest_in, dest + + /* Handle more 16 bytes in loop */ + cmpl $0x10, n + jb .Lmove_16B + + /* Decide forward/backward copy mode */ + cmpl dest, src + jb .Lbackwards_header + + /* + * movs instruction have many startup latency + * so we handle small size by general register. + */ + cmpl $680, n + jb .Ltoo_small_forwards + /* movs instruction is only good for aligned case. */ + movl src, tmp0 + xorl dest, tmp0 + andl $0xff, tmp0 + jz .Lforward_movs +.Ltoo_small_forwards: + subl $0x10, n + + /* We gobble 16 bytes forward in each loop. */ +.Lmove_16B_forwards_loop: + subl $0x10, n + movl 0*4(src), tmp0 + movl 1*4(src), tmp1 + movl tmp0, 0*4(dest) + movl tmp1, 1*4(dest) + movl 2*4(src), tmp0 + movl 3*4(src), tmp1 + movl tmp0, 2*4(dest) + movl tmp1, 3*4(dest) + leal 0x10(src), src + leal 0x10(dest), dest + jae .Lmove_16B_forwards_loop + addl $0x10, n + jmp .Lmove_16B + + /* Handle data forward by movs. */ +.p2align 4 +.Lforward_movs: + movl -4(src, n), tmp0 + leal -4(dest, n), tmp1 + shrl $2, n + rep movsl + movl tmp0, (tmp1) + jmp .Ldone + + /* Handle data backward by movs. */ +.p2align 4 +.Lbackwards_movs: + movl (src), tmp0 + movl dest, tmp1 + leal -4(src, n), src + leal -4(dest, n), dest + shrl $2, n + std + rep movsl + movl tmp0,(tmp1) + cld + jmp .Ldone + + /* Start to prepare for backward copy. */ +.p2align 4 +.Lbackwards_header: + cmpl $680, n + jb .Ltoo_small_backwards + movl src, tmp0 + xorl dest, tmp0 + andl $0xff, tmp0 + jz .Lbackwards_movs + + /* Calculate copy position to tail. */ +.Ltoo_small_backwards: + addl n, src + addl n, dest + subl $0x10, n + + /* We gobble 16 bytes backward in each loop. */ +.Lmove_16B_backwards_loop: + subl $0x10, n + + movl -1*4(src), tmp0 + movl -2*4(src), tmp1 + movl tmp0, -1*4(dest) + movl tmp1, -2*4(dest) + movl -3*4(src), tmp0 + movl -4*4(src), tmp1 + movl tmp0, -3*4(dest) + movl tmp1, -4*4(dest) + leal -0x10(src), src + leal -0x10(dest), dest + jae .Lmove_16B_backwards_loop + /* Calculate copy position to head. */ + addl $0x10, n + subl n, src + subl n, dest + + /* Move data from 8 bytes to 15 bytes. */ +.p2align 4 +.Lmove_16B: + cmpl $8, n + jb .Lmove_8B + movl 0*4(src), tmp0 + movl 1*4(src), tmp1 + movl -2*4(src, n), tmp2 + movl -1*4(src, n), src + + movl tmp0, 0*4(dest) + movl tmp1, 1*4(dest) + movl tmp2, -2*4(dest, n) + movl src, -1*4(dest, n) + jmp .Ldone + + /* Move data from 4 bytes to 7 bytes. */ +.p2align 4 +.Lmove_8B: + cmpl $4, n + jb .Lmove_4B + movl 0*4(src), tmp0 + movl -1*4(src, n), tmp1 + movl tmp0, 0*4(dest) + movl tmp1, -1*4(dest, n) + jmp .Ldone + + /* Move data from 2 bytes to 3 bytes. */ +.p2align 4 +.Lmove_4B: + cmpl $2, n + jb .Lmove_1B + movw 0*2(src), tmp0w + movw -1*2(src, n), tmp1w + movw tmp0w, 0*2(dest) + movw tmp1w, -1*2(dest, n) + jmp .Ldone + + /* Move data for 1 byte. */ +.p2align 4 +.Lmove_1B: + cmpl $1, n + jb .Ldone + movb (src), tmp3b + movb tmp3b, (dest) +.p2align 4 +.Ldone: + popl dest_in // restore 'dest_in' [eax] as the return value + /* Restore all callee-saved registers: */ + popl %esi + popl %edi + popl %ebx + popl %ebp + + RET +SYM_FUNC_END(memmove) +EXPORT_SYMBOL(memmove) diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index b7dfd60243b7..32125224fcca 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -47,8 +47,6 @@ SYM_FUNC_START(__put_user_1) LOAD_TASK_SIZE_MINUS_N(0) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user -SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL) - ENDBR ASM_STAC 1: movb %al,(%_ASM_CX) xor %ecx,%ecx @@ -56,54 +54,87 @@ SYM_INNER_LABEL(__put_user_nocheck_1, SYM_L_GLOBAL) RET SYM_FUNC_END(__put_user_1) EXPORT_SYMBOL(__put_user_1) + +SYM_FUNC_START(__put_user_nocheck_1) + ENDBR + ASM_STAC +2: movb %al,(%_ASM_CX) + xor %ecx,%ecx + ASM_CLAC + RET +SYM_FUNC_END(__put_user_nocheck_1) EXPORT_SYMBOL(__put_user_nocheck_1) SYM_FUNC_START(__put_user_2) LOAD_TASK_SIZE_MINUS_N(1) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user -SYM_INNER_LABEL(__put_user_nocheck_2, SYM_L_GLOBAL) - ENDBR ASM_STAC -2: movw %ax,(%_ASM_CX) +3: movw %ax,(%_ASM_CX) xor %ecx,%ecx ASM_CLAC RET SYM_FUNC_END(__put_user_2) EXPORT_SYMBOL(__put_user_2) + +SYM_FUNC_START(__put_user_nocheck_2) + ENDBR + ASM_STAC +4: movw %ax,(%_ASM_CX) + xor %ecx,%ecx + ASM_CLAC + RET +SYM_FUNC_END(__put_user_nocheck_2) EXPORT_SYMBOL(__put_user_nocheck_2) SYM_FUNC_START(__put_user_4) LOAD_TASK_SIZE_MINUS_N(3) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user -SYM_INNER_LABEL(__put_user_nocheck_4, SYM_L_GLOBAL) - ENDBR ASM_STAC -3: movl %eax,(%_ASM_CX) +5: movl %eax,(%_ASM_CX) xor %ecx,%ecx ASM_CLAC RET SYM_FUNC_END(__put_user_4) EXPORT_SYMBOL(__put_user_4) + +SYM_FUNC_START(__put_user_nocheck_4) + ENDBR + ASM_STAC +6: movl %eax,(%_ASM_CX) + xor %ecx,%ecx + ASM_CLAC + RET +SYM_FUNC_END(__put_user_nocheck_4) EXPORT_SYMBOL(__put_user_nocheck_4) SYM_FUNC_START(__put_user_8) LOAD_TASK_SIZE_MINUS_N(7) cmp %_ASM_BX,%_ASM_CX jae .Lbad_put_user -SYM_INNER_LABEL(__put_user_nocheck_8, SYM_L_GLOBAL) - ENDBR ASM_STAC -4: mov %_ASM_AX,(%_ASM_CX) +7: mov %_ASM_AX,(%_ASM_CX) #ifdef CONFIG_X86_32 -5: movl %edx,4(%_ASM_CX) +8: movl %edx,4(%_ASM_CX) #endif xor %ecx,%ecx ASM_CLAC RET SYM_FUNC_END(__put_user_8) EXPORT_SYMBOL(__put_user_8) + +SYM_FUNC_START(__put_user_nocheck_8) + ENDBR + ASM_STAC +9: mov %_ASM_AX,(%_ASM_CX) +#ifdef CONFIG_X86_32 +10: movl %edx,4(%_ASM_CX) +#endif + xor %ecx,%ecx + ASM_CLAC + RET +SYM_FUNC_END(__put_user_nocheck_8) EXPORT_SYMBOL(__put_user_nocheck_8) SYM_CODE_START_LOCAL(.Lbad_put_user_clac) @@ -117,6 +148,11 @@ SYM_CODE_END(.Lbad_put_user_clac) _ASM_EXTABLE_UA(2b, .Lbad_put_user_clac) _ASM_EXTABLE_UA(3b, .Lbad_put_user_clac) _ASM_EXTABLE_UA(4b, .Lbad_put_user_clac) -#ifdef CONFIG_X86_32 _ASM_EXTABLE_UA(5b, .Lbad_put_user_clac) + _ASM_EXTABLE_UA(6b, .Lbad_put_user_clac) + _ASM_EXTABLE_UA(7b, .Lbad_put_user_clac) + _ASM_EXTABLE_UA(9b, .Lbad_put_user_clac) +#ifdef CONFIG_X86_32 + _ASM_EXTABLE_UA(8b, .Lbad_put_user_clac) + _ASM_EXTABLE_UA(10b, .Lbad_put_user_clac) #endif diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 073289a55f84..5f61c65322be 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -5,24 +5,27 @@ #include <asm/dwarf2.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> +#include <asm/asm-offsets.h> #include <asm/export.h> #include <asm/nospec-branch.h> #include <asm/unwind_hints.h> +#include <asm/percpu.h> #include <asm/frame.h> .section .text.__x86.indirect_thunk -.macro RETPOLINE reg + +.macro POLINE reg ANNOTATE_INTRA_FUNCTION_CALL call .Ldo_rop_\@ -.Lspec_trap_\@: - UNWIND_HINT_EMPTY - pause - lfence - jmp .Lspec_trap_\@ + int3 .Ldo_rop_\@: mov %\reg, (%_ASM_SP) UNWIND_HINT_FUNC +.endm + +.macro RETPOLINE reg + POLINE \reg RET .endm @@ -52,7 +55,6 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL) */ #define __EXPORT_THUNK(sym) _ASM_NOKPROBE(sym); EXPORT_SYMBOL(sym) -#define EXPORT_THUNK(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg) .align RETPOLINE_THUNK_SIZE SYM_CODE_START(__x86_indirect_thunk_array) @@ -64,10 +66,65 @@ SYM_CODE_START(__x86_indirect_thunk_array) .align RETPOLINE_THUNK_SIZE SYM_CODE_END(__x86_indirect_thunk_array) -#define GEN(reg) EXPORT_THUNK(reg) +#define GEN(reg) __EXPORT_THUNK(__x86_indirect_thunk_ ## reg) +#include <asm/GEN-for-each-reg.h> +#undef GEN + +#ifdef CONFIG_CALL_DEPTH_TRACKING +.macro CALL_THUNK reg + .align RETPOLINE_THUNK_SIZE + +SYM_INNER_LABEL(__x86_indirect_call_thunk_\reg, SYM_L_GLOBAL) + UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR + + CALL_DEPTH_ACCOUNT + POLINE \reg + ANNOTATE_UNRET_SAFE + ret + int3 +.endm + + .align RETPOLINE_THUNK_SIZE +SYM_CODE_START(__x86_indirect_call_thunk_array) + +#define GEN(reg) CALL_THUNK reg #include <asm/GEN-for-each-reg.h> #undef GEN + .align RETPOLINE_THUNK_SIZE +SYM_CODE_END(__x86_indirect_call_thunk_array) + +#define GEN(reg) __EXPORT_THUNK(__x86_indirect_call_thunk_ ## reg) +#include <asm/GEN-for-each-reg.h> +#undef GEN + +.macro JUMP_THUNK reg + .align RETPOLINE_THUNK_SIZE + +SYM_INNER_LABEL(__x86_indirect_jump_thunk_\reg, SYM_L_GLOBAL) + UNWIND_HINT_EMPTY + ANNOTATE_NOENDBR + POLINE \reg + ANNOTATE_UNRET_SAFE + ret + int3 +.endm + + .align RETPOLINE_THUNK_SIZE +SYM_CODE_START(__x86_indirect_jump_thunk_array) + +#define GEN(reg) JUMP_THUNK reg +#include <asm/GEN-for-each-reg.h> +#undef GEN + + .align RETPOLINE_THUNK_SIZE +SYM_CODE_END(__x86_indirect_jump_thunk_array) + +#define GEN(reg) __EXPORT_THUNK(__x86_indirect_jump_thunk_ ## reg) +#include <asm/GEN-for-each-reg.h> +#undef GEN +#endif /* * This function name is magical and is used by -mfunction-return=thunk-extern * for the compiler to generate JMPs to it. @@ -140,3 +197,37 @@ __EXPORT_THUNK(zen_untrain_ret) EXPORT_SYMBOL(__x86_return_thunk) #endif /* CONFIG_RETHUNK */ + +#ifdef CONFIG_CALL_DEPTH_TRACKING + + .align 64 +SYM_FUNC_START(__x86_return_skl) + ANNOTATE_NOENDBR + /* + * Keep the hotpath in a 16byte I-fetch for the non-debug + * case. + */ + CALL_THUNKS_DEBUG_INC_RETS + shlq $5, PER_CPU_VAR(pcpu_hot + X86_call_depth) + jz 1f + ANNOTATE_UNRET_SAFE + ret + int3 +1: + CALL_THUNKS_DEBUG_INC_STUFFS + .rept 16 + ANNOTATE_INTRA_FUNCTION_CALL + call 2f + int3 +2: + .endr + add $(8*16), %rsp + + CREDIT_CALL_DEPTH + + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_FUNC_END(__x86_return_skl) + +#endif /* CONFIG_CALL_DEPTH_TRACKING */ diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c index 6c2f1b76a0b6..42cd96e7d733 100644 --- a/arch/x86/mm/cpu_entry_area.c +++ b/arch/x86/mm/cpu_entry_area.c @@ -138,17 +138,13 @@ static void __init setup_cpu_entry_area(unsigned int cpu) pgprot_t tss_prot = PAGE_KERNEL_RO; #else /* - * On native 32-bit systems, the GDT cannot be read-only because + * On 32-bit systems, the GDT cannot be read-only because * our double fault handler uses a task gate, and entering through * a task gate needs to change an available TSS to busy. If the * GDT is read-only, that will triple fault. The TSS cannot be * read-only because the CPU writes to it on task switches. - * - * On Xen PV, the GDT must be read-only because the hypervisor - * requires it. */ - pgprot_t gdt_prot = boot_cpu_has(X86_FEATURE_XENPV) ? - PAGE_KERNEL_RO : PAGE_KERNEL; + pgprot_t gdt_prot = PAGE_KERNEL; pgprot_t tss_prot = PAGE_KERNEL; #endif diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 3f040c6e5d13..a190aae8ceaf 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1416,47 +1416,6 @@ void mark_rodata_ro(void) debug_checkwx(); } -int kern_addr_valid(unsigned long addr) -{ - unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT; - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - pte_t *pte; - - if (above != 0 && above != -1UL) - return 0; - - pgd = pgd_offset_k(addr); - if (pgd_none(*pgd)) - return 0; - - p4d = p4d_offset(pgd, addr); - if (!p4d_present(*p4d)) - return 0; - - pud = pud_offset(p4d, addr); - if (!pud_present(*pud)) - return 0; - - if (pud_large(*pud)) - return pfn_valid(pud_pfn(*pud)); - - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) - return 0; - - if (pmd_large(*pmd)) - return pfn_valid(pmd_pfn(*pmd)); - - pte = pte_offset_kernel(pmd, addr); - if (pte_none(*pte)) - return 0; - - return pfn_valid(pte_pfn(*pte)); -} - /* * Block size is the minimum amount of memory which can be hotplugged or * hotremoved. It must be power of two and must be equal or larger than @@ -1533,72 +1492,44 @@ static long __meminitdata addr_start, addr_end; static void __meminitdata *p_start, *p_end; static int __meminitdata node_start; -static int __meminit vmemmap_populate_hugepages(unsigned long start, - unsigned long end, int node, struct vmem_altmap *altmap) +void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node, + unsigned long addr, unsigned long next) { - unsigned long addr; - unsigned long next; - pgd_t *pgd; - p4d_t *p4d; - pud_t *pud; - pmd_t *pmd; - - for (addr = start; addr < end; addr = next) { - next = pmd_addr_end(addr, end); - - pgd = vmemmap_pgd_populate(addr, node); - if (!pgd) - return -ENOMEM; - - p4d = vmemmap_p4d_populate(pgd, addr, node); - if (!p4d) - return -ENOMEM; - - pud = vmemmap_pud_populate(p4d, addr, node); - if (!pud) - return -ENOMEM; - - pmd = pmd_offset(pud, addr); - if (pmd_none(*pmd)) { - void *p; - - p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap); - if (p) { - pte_t entry; - - entry = pfn_pte(__pa(p) >> PAGE_SHIFT, - PAGE_KERNEL_LARGE); - set_pmd(pmd, __pmd(pte_val(entry))); + pte_t entry; + + entry = pfn_pte(__pa(p) >> PAGE_SHIFT, + PAGE_KERNEL_LARGE); + set_pmd(pmd, __pmd(pte_val(entry))); + + /* check to see if we have contiguous blocks */ + if (p_end != p || node_start != node) { + if (p_start) + pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", + addr_start, addr_end-1, p_start, p_end-1, node_start); + addr_start = addr; + node_start = node; + p_start = p; + } - /* check to see if we have contiguous blocks */ - if (p_end != p || node_start != node) { - if (p_start) - pr_debug(" [%lx-%lx] PMD -> [%p-%p] on node %d\n", - addr_start, addr_end-1, p_start, p_end-1, node_start); - addr_start = addr; - node_start = node; - p_start = p; - } + addr_end = addr + PMD_SIZE; + p_end = p + PMD_SIZE; - addr_end = addr + PMD_SIZE; - p_end = p + PMD_SIZE; + if (!IS_ALIGNED(addr, PMD_SIZE) || + !IS_ALIGNED(next, PMD_SIZE)) + vmemmap_use_new_sub_pmd(addr, next); +} - if (!IS_ALIGNED(addr, PMD_SIZE) || - !IS_ALIGNED(next, PMD_SIZE)) - vmemmap_use_new_sub_pmd(addr, next); +int __meminit vmemmap_check_pmd(pmd_t *pmd, int node, + unsigned long addr, unsigned long next) +{ + int large = pmd_large(*pmd); - continue; - } else if (altmap) - return -ENOMEM; /* no fallback */ - } else if (pmd_large(*pmd)) { - vmemmap_verify((pte_t *)pmd, node, addr, next); - vmemmap_use_sub_pmd(addr, next); - continue; - } - if (vmemmap_populate_basepages(addr, next, node, NULL)) - return -ENOMEM; + if (pmd_large(*pmd)) { + vmemmap_verify((pte_t *)pmd, node, addr, next); + vmemmap_use_sub_pmd(addr, next); } - return 0; + + return large; } int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 78c5bc654cff..6453fbaedb08 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -217,9 +217,15 @@ __ioremap_caller(resource_size_t phys_addr, unsigned long size, * Mappings have to be page-aligned */ offset = phys_addr & ~PAGE_MASK; - phys_addr &= PHYSICAL_PAGE_MASK; + phys_addr &= PAGE_MASK; size = PAGE_ALIGN(last_addr+1) - phys_addr; + /* + * Mask out any bits not part of the actual physical + * address, like memory encryption bits. + */ + phys_addr &= PHYSICAL_PAGE_MASK; + retval = memtype_reserve(phys_addr, (u64)phys_addr + size, pcm, &new_pcm); if (retval) { diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c index d3efbc5b3449..9f82019179e1 100644 --- a/arch/x86/mm/kmmio.c +++ b/arch/x86/mm/kmmio.c @@ -62,7 +62,13 @@ struct kmmio_context { int active; }; -static DEFINE_SPINLOCK(kmmio_lock); +/* + * The kmmio_lock is taken in int3 context, which is treated as NMI context. + * This causes lockdep to complain about it bein in both NMI and normal + * context. Hide it from lockdep, as it should not have any other locks + * taken under it, and this is only enabled for debugging mmio anyway. + */ +static arch_spinlock_t kmmio_lock = __ARCH_SPIN_LOCK_UNLOCKED; /* Protected by kmmio_lock */ unsigned int kmmio_count; @@ -240,15 +246,14 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) page_base &= page_level_mask(l); /* - * Preemption is now disabled to prevent process switch during - * single stepping. We can only handle one active kmmio trace + * Hold the RCU read lock over single stepping to avoid looking + * up the probe and kmmio_fault_page again. The rcu_read_lock_sched() + * also disables preemption and prevents process switch during + * the single stepping. We can only handle one active kmmio trace * per cpu, so ensure that we finish it before something else - * gets to run. We also hold the RCU read lock over single - * stepping to avoid looking up the probe and kmmio_fault_page - * again. + * gets to run. */ - preempt_disable(); - rcu_read_lock(); + rcu_read_lock_sched_notrace(); faultpage = get_kmmio_fault_page(page_base); if (!faultpage) { @@ -317,8 +322,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr) return 1; /* fault handled */ no_kmmio: - rcu_read_unlock(); - preempt_enable_no_resched(); + rcu_read_unlock_sched_notrace(); return ret; } @@ -346,10 +350,10 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs) ctx->probe->post_handler(ctx->probe, condition, regs); /* Prevent racing against release_kmmio_fault_page(). */ - spin_lock(&kmmio_lock); + arch_spin_lock(&kmmio_lock); if (ctx->fpage->count) arm_kmmio_fault_page(ctx->fpage); - spin_unlock(&kmmio_lock); + arch_spin_unlock(&kmmio_lock); regs->flags &= ~X86_EFLAGS_TF; regs->flags |= ctx->saved_flags; @@ -357,8 +361,7 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs) /* These were acquired in kmmio_handler(). */ ctx->active--; BUG_ON(ctx->active); - rcu_read_unlock(); - preempt_enable_no_resched(); + rcu_read_unlock_sched_notrace(); /* * if somebody else is singlestepping across a probe point, flags @@ -440,7 +443,8 @@ int register_kmmio_probe(struct kmmio_probe *p) unsigned int l; pte_t *pte; - spin_lock_irqsave(&kmmio_lock, flags); + local_irq_save(flags); + arch_spin_lock(&kmmio_lock); if (get_kmmio_probe(addr)) { ret = -EEXIST; goto out; @@ -460,7 +464,9 @@ int register_kmmio_probe(struct kmmio_probe *p) size += page_level_size(l); } out: - spin_unlock_irqrestore(&kmmio_lock, flags); + arch_spin_unlock(&kmmio_lock); + local_irq_restore(flags); + /* * XXX: What should I do here? * Here was a call to global_flush_tlb(), but it does not exist @@ -494,7 +500,8 @@ static void remove_kmmio_fault_pages(struct rcu_head *head) struct kmmio_fault_page **prevp = &dr->release_list; unsigned long flags; - spin_lock_irqsave(&kmmio_lock, flags); + local_irq_save(flags); + arch_spin_lock(&kmmio_lock); while (f) { if (!f->count) { list_del_rcu(&f->list); @@ -506,7 +513,8 @@ static void remove_kmmio_fault_pages(struct rcu_head *head) } f = *prevp; } - spin_unlock_irqrestore(&kmmio_lock, flags); + arch_spin_unlock(&kmmio_lock); + local_irq_restore(flags); /* This is the real RCU destroy call. */ call_rcu(&dr->rcu, rcu_free_kmmio_fault_pages); @@ -540,14 +548,16 @@ void unregister_kmmio_probe(struct kmmio_probe *p) if (!pte) return; - spin_lock_irqsave(&kmmio_lock, flags); + local_irq_save(flags); + arch_spin_lock(&kmmio_lock); while (size < size_lim) { release_kmmio_fault_page(addr + size, &release_list); size += page_level_size(l); } list_del_rcu(&p->list); kmmio_count--; - spin_unlock_irqrestore(&kmmio_lock, flags); + arch_spin_unlock(&kmmio_lock); + local_irq_restore(flags); if (!release_list) return; diff --git a/arch/x86/mm/pat/cpa-test.c b/arch/x86/mm/pat/cpa-test.c index 423b21e80929..3d2f7f0a6ed1 100644 --- a/arch/x86/mm/pat/cpa-test.c +++ b/arch/x86/mm/pat/cpa-test.c @@ -136,10 +136,10 @@ static int pageattr_test(void) failed += print_split(&sa); for (i = 0; i < NTEST; i++) { - unsigned long pfn = prandom_u32_max(max_pfn_mapped); + unsigned long pfn = get_random_u32_below(max_pfn_mapped); addr[i] = (unsigned long)__va(pfn << PAGE_SHIFT); - len[i] = prandom_u32_max(NPAGES); + len[i] = get_random_u32_below(NPAGES); len[i] = min_t(unsigned long, len[i], max_pfn_mapped - pfn - 1); if (len[i] == 0) diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 66a209f7eb86..46de9cf5c91d 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -43,6 +43,7 @@ #include <linux/rbtree.h> #include <asm/cacheflush.h> +#include <asm/cacheinfo.h> #include <asm/processor.h> #include <asm/tlbflush.h> #include <asm/x86_init.h> @@ -60,41 +61,34 @@ #undef pr_fmt #define pr_fmt(fmt) "" fmt -static bool __read_mostly pat_bp_initialized; static bool __read_mostly pat_disabled = !IS_ENABLED(CONFIG_X86_PAT); -static bool __initdata pat_force_disabled = !IS_ENABLED(CONFIG_X86_PAT); -static bool __read_mostly pat_bp_enabled; -static bool __read_mostly pat_cm_initialized; +static u64 __ro_after_init pat_msr_val; /* * PAT support is enabled by default, but can be disabled for * various user-requested or hardware-forced reasons: */ -void pat_disable(const char *msg_reason) +static void __init pat_disable(const char *msg_reason) { if (pat_disabled) return; - if (pat_bp_initialized) { - WARN_ONCE(1, "x86/PAT: PAT cannot be disabled after initialization\n"); - return; - } - pat_disabled = true; pr_info("x86/PAT: %s\n", msg_reason); + + memory_caching_control &= ~CACHE_PAT; } static int __init nopat(char *str) { pat_disable("PAT support disabled via boot option."); - pat_force_disabled = true; return 0; } early_param("nopat", nopat); bool pat_enabled(void) { - return pat_bp_enabled; + return !pat_disabled; } EXPORT_SYMBOL_GPL(pat_enabled); @@ -192,7 +186,8 @@ enum { #define CM(c) (_PAGE_CACHE_MODE_ ## c) -static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) +static enum page_cache_mode __init pat_get_cache_mode(unsigned int pat_val, + char *msg) { enum page_cache_mode cache; char *cache_mode; @@ -219,14 +214,12 @@ static enum page_cache_mode pat_get_cache_mode(unsigned pat_val, char *msg) * configuration. * Using lower indices is preferred, so we start with highest index. */ -static void __init_cache_modes(u64 pat) +static void __init init_cache_modes(u64 pat) { enum page_cache_mode cache; char pat_msg[33]; int i; - WARN_ON_ONCE(pat_cm_initialized); - pat_msg[32] = 0; for (i = 7; i >= 0; i--) { cache = pat_get_cache_mode((pat >> (i * 8)) & 7, @@ -234,34 +227,9 @@ static void __init_cache_modes(u64 pat) update_cache_mode_entry(i, cache); } pr_info("x86/PAT: Configuration [0-7]: %s\n", pat_msg); - - pat_cm_initialized = true; } -#define PAT(x, y) ((u64)PAT_ ## y << ((x)*8)) - -static void pat_bp_init(u64 pat) -{ - u64 tmp_pat; - - if (!boot_cpu_has(X86_FEATURE_PAT)) { - pat_disable("PAT not supported by the CPU."); - return; - } - - rdmsrl(MSR_IA32_CR_PAT, tmp_pat); - if (!tmp_pat) { - pat_disable("PAT support disabled by the firmware."); - return; - } - - wrmsrl(MSR_IA32_CR_PAT, pat); - pat_bp_enabled = true; - - __init_cache_modes(pat); -} - -static void pat_ap_init(u64 pat) +void pat_cpu_init(void) { if (!boot_cpu_has(X86_FEATURE_PAT)) { /* @@ -271,30 +239,39 @@ static void pat_ap_init(u64 pat) panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n"); } - wrmsrl(MSR_IA32_CR_PAT, pat); + wrmsrl(MSR_IA32_CR_PAT, pat_msr_val); } -void __init init_cache_modes(void) +/** + * pat_bp_init - Initialize the PAT MSR value and PAT table + * + * This function initializes PAT MSR value and PAT table with an OS-defined + * value to enable additional cache attributes, WC, WT and WP. + * + * This function prepares the calls of pat_cpu_init() via cache_cpu_init() + * on all CPUs. + */ +void __init pat_bp_init(void) { - u64 pat = 0; + struct cpuinfo_x86 *c = &boot_cpu_data; +#define PAT(p0, p1, p2, p3, p4, p5, p6, p7) \ + (((u64)PAT_ ## p0) | ((u64)PAT_ ## p1 << 8) | \ + ((u64)PAT_ ## p2 << 16) | ((u64)PAT_ ## p3 << 24) | \ + ((u64)PAT_ ## p4 << 32) | ((u64)PAT_ ## p5 << 40) | \ + ((u64)PAT_ ## p6 << 48) | ((u64)PAT_ ## p7 << 56)) - if (pat_cm_initialized) - return; - if (boot_cpu_has(X86_FEATURE_PAT)) { - /* - * CPU supports PAT. Set PAT table to be consistent with - * PAT MSR. This case supports "nopat" boot option, and - * virtual machine environments which support PAT without - * MTRRs. In specific, Xen has unique setup to PAT MSR. - * - * If PAT MSR returns 0, it is considered invalid and emulates - * as No PAT. - */ - rdmsrl(MSR_IA32_CR_PAT, pat); - } + if (!IS_ENABLED(CONFIG_X86_PAT)) + pr_info_once("x86/PAT: PAT support disabled because CONFIG_X86_PAT is disabled in the kernel.\n"); + + if (!cpu_feature_enabled(X86_FEATURE_PAT)) + pat_disable("PAT not supported by the CPU."); + else + rdmsrl(MSR_IA32_CR_PAT, pat_msr_val); + + if (!pat_msr_val) { + pat_disable("PAT support disabled by the firmware."); - if (!pat) { /* * No PAT. Emulate the PAT table that corresponds to the two * cache bits, PWT (Write Through) and PCD (Cache Disable). @@ -313,40 +290,22 @@ void __init init_cache_modes(void) * NOTE: When WC or WP is used, it is redirected to UC- per * the default setup in __cachemode2pte_tbl[]. */ - pat = PAT(0, WB) | PAT(1, WT) | PAT(2, UC_MINUS) | PAT(3, UC) | - PAT(4, WB) | PAT(5, WT) | PAT(6, UC_MINUS) | PAT(7, UC); - } else if (!pat_force_disabled && cpu_feature_enabled(X86_FEATURE_HYPERVISOR)) { - /* - * Clearly PAT is enabled underneath. Allow pat_enabled() to - * reflect this. - */ - pat_bp_enabled = true; + pat_msr_val = PAT(WB, WT, UC_MINUS, UC, WB, WT, UC_MINUS, UC); } - __init_cache_modes(pat); -} - -/** - * pat_init - Initialize the PAT MSR and PAT table on the current CPU - * - * This function initializes PAT MSR and PAT table with an OS-defined value - * to enable additional cache attributes, WC, WT and WP. - * - * This function must be called on all CPUs using the specific sequence of - * operations defined in Intel SDM. mtrr_rendezvous_handler() provides this - * procedure for PAT. - */ -void pat_init(void) -{ - u64 pat; - struct cpuinfo_x86 *c = &boot_cpu_data; - -#ifndef CONFIG_X86_PAT - pr_info_once("x86/PAT: PAT support disabled because CONFIG_X86_PAT is disabled in the kernel.\n"); -#endif - - if (pat_disabled) + /* + * Xen PV doesn't allow to set PAT MSR, but all cache modes are + * supported. + * When running as TDX guest setting the PAT MSR won't work either + * due to the requirement to set CR0.CD when doing so. Rely on + * firmware to have set the PAT MSR correctly. + */ + if (pat_disabled || + cpu_feature_enabled(X86_FEATURE_XENPV) || + cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { + init_cache_modes(pat_msr_val); return; + } if ((c->x86_vendor == X86_VENDOR_INTEL) && (((c->x86 == 0x6) && (c->x86_model <= 0xd)) || @@ -371,8 +330,7 @@ void pat_init(void) * NOTE: When WT or WP is used, it is redirected to UC- per * the default setup in __cachemode2pte_tbl[]. */ - pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | - PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC); + pat_msr_val = PAT(WB, WC, UC_MINUS, UC, WB, WC, UC_MINUS, UC); } else { /* * Full PAT support. We put WT in slot 7 to improve @@ -400,19 +358,14 @@ void pat_init(void) * The reserved slots are unused, but mapped to their * corresponding types in the presence of PAT errata. */ - pat = PAT(0, WB) | PAT(1, WC) | PAT(2, UC_MINUS) | PAT(3, UC) | - PAT(4, WB) | PAT(5, WP) | PAT(6, UC_MINUS) | PAT(7, WT); + pat_msr_val = PAT(WB, WC, UC_MINUS, UC, WB, WP, UC_MINUS, WT); } - if (!pat_bp_initialized) { - pat_bp_init(pat); - pat_bp_initialized = true; - } else { - pat_ap_init(pat); - } -} + memory_caching_control |= CACHE_PAT; + init_cache_modes(pat_msr_val); #undef PAT +} static DEFINE_SPINLOCK(memtype_lock); /* protects memtype accesses */ diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index 2e5a045731de..ef34ba21aa92 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -20,6 +20,7 @@ #include <linux/kernel.h> #include <linux/cc_platform.h> #include <linux/set_memory.h> +#include <linux/memregion.h> #include <asm/e820/api.h> #include <asm/processor.h> @@ -330,6 +331,23 @@ void arch_invalidate_pmem(void *addr, size_t size) EXPORT_SYMBOL_GPL(arch_invalidate_pmem); #endif +#ifdef CONFIG_ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION +bool cpu_cache_has_invalidate_memregion(void) +{ + return !cpu_feature_enabled(X86_FEATURE_HYPERVISOR); +} +EXPORT_SYMBOL_NS_GPL(cpu_cache_has_invalidate_memregion, DEVMEM); + +int cpu_cache_invalidate_memregion(int res_desc) +{ + if (WARN_ON_ONCE(!cpu_cache_has_invalidate_memregion())) + return -ENXIO; + wbinvd_on_all_cpus(); + return 0; +} +EXPORT_SYMBOL_NS_GPL(cpu_cache_invalidate_memregion, DEVMEM); +#endif + static void __cpa_flush_all(void *arg) { unsigned long cache = (unsigned long)arg; diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 8525f2876fb4..e4f499eb0f29 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -299,9 +299,6 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) pud_t *pud; int i; - if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */ - return; - p4d = p4d_offset(pgd, 0); pud = pud_offset(p4d, 0); @@ -434,10 +431,12 @@ pgd_t *pgd_alloc(struct mm_struct *mm) mm->pgd = pgd; - if (preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0) + if (sizeof(pmds) != 0 && + preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0) goto out_free_pgd; - if (preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0) + if (sizeof(u_pmds) != 0 && + preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0) goto out_free_pmds; if (paravirt_pgd_alloc(mm) != 0) @@ -451,17 +450,22 @@ pgd_t *pgd_alloc(struct mm_struct *mm) spin_lock(&pgd_lock); pgd_ctor(mm, pgd); - pgd_prepopulate_pmd(mm, pgd, pmds); - pgd_prepopulate_user_pmd(mm, pgd, u_pmds); + if (sizeof(pmds) != 0) + pgd_prepopulate_pmd(mm, pgd, pmds); + + if (sizeof(u_pmds) != 0) + pgd_prepopulate_user_pmd(mm, pgd, u_pmds); spin_unlock(&pgd_lock); return pgd; out_free_user_pmds: - free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS); + if (sizeof(u_pmds) != 0) + free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS); out_free_pmds: - free_pmds(mm, pmds, PREALLOCATED_PMDS); + if (sizeof(pmds) != 0) + free_pmds(mm, pmds, PREALLOCATED_PMDS); out_free_pgd: _pgd_free(pgd); out: diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 99620428ad78..b808be77635e 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -12,6 +12,7 @@ #include <linux/memory.h> #include <linux/sort.h> #include <asm/extable.h> +#include <asm/ftrace.h> #include <asm/set_memory.h> #include <asm/nospec-branch.h> #include <asm/text-patching.h> @@ -340,6 +341,13 @@ static int emit_call(u8 **pprog, void *func, void *ip) return emit_patch(pprog, func, ip, 0xE8); } +static int emit_rsb_call(u8 **pprog, void *func, void *ip) +{ + OPTIMIZER_HIDE_VAR(func); + x86_call_depth_emit_accounting(pprog, func); + return emit_patch(pprog, func, ip, 0xE8); +} + static int emit_jump(u8 **pprog, void *func, void *ip) { return emit_patch(pprog, func, ip, 0xE9); @@ -417,7 +425,10 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) EMIT2(0xFF, 0xE0 + reg); } else if (cpu_feature_enabled(X86_FEATURE_RETPOLINE)) { OPTIMIZER_HIDE_VAR(reg); - emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); + if (cpu_feature_enabled(X86_FEATURE_CALL_DEPTH)) + emit_jump(&prog, &__x86_indirect_jump_thunk_array[reg], ip); + else + emit_jump(&prog, &__x86_indirect_thunk_array[reg], ip); } else { EMIT2(0xFF, 0xE0 + reg); /* jmp *%\reg */ if (IS_ENABLED(CONFIG_RETPOLINE) || IS_ENABLED(CONFIG_SLS)) @@ -432,7 +443,7 @@ static void emit_return(u8 **pprog, u8 *ip) u8 *prog = *pprog; if (cpu_feature_enabled(X86_FEATURE_RETHUNK)) { - emit_jump(&prog, &__x86_return_thunk, ip); + emit_jump(&prog, x86_return_thunk, ip); } else { EMIT1(0xC3); /* ret */ if (IS_ENABLED(CONFIG_SLS)) @@ -891,6 +902,65 @@ static void emit_nops(u8 **pprog, int len) *pprog = prog; } +/* emit the 3-byte VEX prefix + * + * r: same as rex.r, extra bit for ModRM reg field + * x: same as rex.x, extra bit for SIB index field + * b: same as rex.b, extra bit for ModRM r/m, or SIB base + * m: opcode map select, encoding escape bytes e.g. 0x0f38 + * w: same as rex.w (32 bit or 64 bit) or opcode specific + * src_reg2: additional source reg (encoded as BPF reg) + * l: vector length (128 bit or 256 bit) or reserved + * pp: opcode prefix (none, 0x66, 0xf2 or 0xf3) + */ +static void emit_3vex(u8 **pprog, bool r, bool x, bool b, u8 m, + bool w, u8 src_reg2, bool l, u8 pp) +{ + u8 *prog = *pprog; + const u8 b0 = 0xc4; /* first byte of 3-byte VEX prefix */ + u8 b1, b2; + u8 vvvv = reg2hex[src_reg2]; + + /* reg2hex gives only the lower 3 bit of vvvv */ + if (is_ereg(src_reg2)) + vvvv |= 1 << 3; + + /* + * 2nd byte of 3-byte VEX prefix + * ~ means bit inverted encoding + * + * 7 0 + * +---+---+---+---+---+---+---+---+ + * |~R |~X |~B | m | + * +---+---+---+---+---+---+---+---+ + */ + b1 = (!r << 7) | (!x << 6) | (!b << 5) | (m & 0x1f); + /* + * 3rd byte of 3-byte VEX prefix + * + * 7 0 + * +---+---+---+---+---+---+---+---+ + * | W | ~vvvv | L | pp | + * +---+---+---+---+---+---+---+---+ + */ + b2 = (w << 7) | ((~vvvv & 0xf) << 3) | (l << 2) | (pp & 3); + + EMIT3(b0, b1, b2); + *pprog = prog; +} + +/* emit BMI2 shift instruction */ +static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op) +{ + u8 *prog = *pprog; + bool r = is_ereg(dst_reg); + u8 m = 2; /* escape code 0f38 */ + + emit_3vex(&prog, r, false, r, m, is64, src_reg, false, op); + EMIT2(0xf7, add_2reg(0xC0, dst_reg, dst_reg)); + *pprog = prog; +} + #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp))) static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, @@ -1137,17 +1207,38 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image case BPF_ALU64 | BPF_LSH | BPF_X: case BPF_ALU64 | BPF_RSH | BPF_X: case BPF_ALU64 | BPF_ARSH | BPF_X: + /* BMI2 shifts aren't better when shift count is already in rcx */ + if (boot_cpu_has(X86_FEATURE_BMI2) && src_reg != BPF_REG_4) { + /* shrx/sarx/shlx dst_reg, dst_reg, src_reg */ + bool w = (BPF_CLASS(insn->code) == BPF_ALU64); + u8 op; + + switch (BPF_OP(insn->code)) { + case BPF_LSH: + op = 1; /* prefix 0x66 */ + break; + case BPF_RSH: + op = 3; /* prefix 0xf2 */ + break; + case BPF_ARSH: + op = 2; /* prefix 0xf3 */ + break; + } - /* Check for bad case when dst_reg == rcx */ - if (dst_reg == BPF_REG_4) { - /* mov r11, dst_reg */ - EMIT_mov(AUX_REG, dst_reg); - dst_reg = AUX_REG; + emit_shiftx(&prog, dst_reg, src_reg, w, op); + + break; } if (src_reg != BPF_REG_4) { /* common case */ - EMIT1(0x51); /* push rcx */ - + /* Check for bad case when dst_reg == rcx */ + if (dst_reg == BPF_REG_4) { + /* mov r11, dst_reg */ + EMIT_mov(AUX_REG, dst_reg); + dst_reg = AUX_REG; + } else { + EMIT1(0x51); /* push rcx */ + } /* mov rcx, src_reg */ EMIT_mov(BPF_REG_4, src_reg); } @@ -1159,12 +1250,14 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image b3 = simple_alu_opcodes[BPF_OP(insn->code)]; EMIT2(0xD3, add_1reg(b3, dst_reg)); - if (src_reg != BPF_REG_4) - EMIT1(0x59); /* pop rcx */ + if (src_reg != BPF_REG_4) { + if (insn->dst_reg == BPF_REG_4) + /* mov dst_reg, r11 */ + EMIT_mov(insn->dst_reg, AUX_REG); + else + EMIT1(0x59); /* pop rcx */ + } - if (insn->dst_reg == BPF_REG_4) - /* mov dst_reg, r11 */ - EMIT_mov(insn->dst_reg, AUX_REG); break; case BPF_ALU | BPF_END | BPF_FROM_BE: @@ -1226,8 +1319,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image /* speculation barrier */ case BPF_ST | BPF_NOSPEC: - if (boot_cpu_has(X86_FEATURE_XMM2)) - EMIT_LFENCE(); + EMIT_LFENCE(); break; /* ST: *(u8*)(dst_reg + off) = imm */ @@ -1433,19 +1525,26 @@ st: if (is_imm8(insn->off)) break; /* call */ - case BPF_JMP | BPF_CALL: + case BPF_JMP | BPF_CALL: { + int offs; + func = (u8 *) __bpf_call_base + imm32; if (tail_call_reachable) { /* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ EMIT3_off32(0x48, 0x8B, 0x85, -round_up(bpf_prog->aux->stack_depth, 8) - 8); - if (!imm32 || emit_call(&prog, func, image + addrs[i - 1] + 7)) + if (!imm32) return -EINVAL; + offs = 7 + x86_call_depth_emit_accounting(&prog, func); } else { - if (!imm32 || emit_call(&prog, func, image + addrs[i - 1])) + if (!imm32) return -EINVAL; + offs = x86_call_depth_emit_accounting(&prog, func); } + if (emit_call(&prog, func, image + addrs[i - 1] + offs)) + return -EINVAL; break; + } case BPF_JMP | BPF_TAIL_CALL: if (imm32) @@ -1813,10 +1912,6 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_link *l, int stack_size, int run_ctx_off, bool save_ret) { - void (*exit)(struct bpf_prog *prog, u64 start, - struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_exit; - u64 (*enter)(struct bpf_prog *prog, - struct bpf_tramp_run_ctx *run_ctx) = __bpf_prog_enter; u8 *prog = *pprog; u8 *jmp_insn; int ctx_cookie_off = offsetof(struct bpf_tramp_run_ctx, bpf_cookie); @@ -1835,23 +1930,12 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_1, -run_ctx_off + ctx_cookie_off); - if (p->aux->sleepable) { - enter = __bpf_prog_enter_sleepable; - exit = __bpf_prog_exit_sleepable; - } else if (p->type == BPF_PROG_TYPE_STRUCT_OPS) { - enter = __bpf_prog_enter_struct_ops; - exit = __bpf_prog_exit_struct_ops; - } else if (p->expected_attach_type == BPF_LSM_CGROUP) { - enter = __bpf_prog_enter_lsm_cgroup; - exit = __bpf_prog_exit_lsm_cgroup; - } - /* arg1: mov rdi, progs[i] */ emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32, (u32) (long) p); /* arg2: lea rsi, [rbp - ctx_cookie_off] */ EMIT4(0x48, 0x8D, 0x75, -run_ctx_off); - if (emit_call(&prog, enter, prog)) + if (emit_rsb_call(&prog, bpf_trampoline_enter(p), prog)) return -EINVAL; /* remember prog start time returned by __bpf_prog_enter */ emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); @@ -1872,7 +1956,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, (long) p->insnsi >> 32, (u32) (long) p->insnsi); /* call JITed bpf program or interpreter */ - if (emit_call(&prog, p->bpf_func, prog)) + if (emit_rsb_call(&prog, p->bpf_func, prog)) return -EINVAL; /* @@ -1896,7 +1980,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, emit_mov_reg(&prog, true, BPF_REG_2, BPF_REG_6); /* arg3: lea rdx, [rbp - run_ctx_off] */ EMIT4(0x48, 0x8D, 0x55, -run_ctx_off); - if (emit_call(&prog, exit, prog)) + if (emit_rsb_call(&prog, bpf_trampoline_exit(p), prog)) return -EINVAL; *pprog = prog; @@ -2118,6 +2202,11 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i prog = image; EMIT_ENDBR(); + /* + * This is the direct-call trampoline, as such it needs accounting + * for the __fentry__ call. + */ + x86_call_depth_emit_accounting(&prog, NULL); EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */ @@ -2144,7 +2233,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (flags & BPF_TRAMP_F_CALL_ORIG) { /* arg1: mov rdi, im */ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); - if (emit_call(&prog, __bpf_tramp_enter, prog)) { + if (emit_rsb_call(&prog, __bpf_tramp_enter, prog)) { ret = -EINVAL; goto cleanup; } @@ -2176,7 +2265,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i EMIT2(0xff, 0xd0); /* call *rax */ } else { /* call original function */ - if (emit_call(&prog, orig_call, prog)) { + if (emit_rsb_call(&prog, orig_call, prog)) { ret = -EINVAL; goto cleanup; } @@ -2220,7 +2309,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i im->ip_epilogue = prog; /* arg1: mov rdi, im */ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); - if (emit_call(&prog, __bpf_tramp_exit, prog)) { + if (emit_rsb_call(&prog, __bpf_tramp_exit, prog)) { ret = -EINVAL; goto cleanup; } diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 2f82480fd430..ea2eb2ec90e2 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -1,4 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 + +#define pr_fmt(fmt) "PCI: " fmt + #include <linux/pci.h> #include <linux/acpi.h> #include <linux/init.h> @@ -37,15 +40,15 @@ static int __init set_nouse_crs(const struct dmi_system_id *id) static int __init set_ignore_seg(const struct dmi_system_id *id) { - printk(KERN_INFO "PCI: %s detected: ignoring ACPI _SEG\n", id->ident); + pr_info("%s detected: ignoring ACPI _SEG\n", id->ident); pci_ignore_seg = true; return 0; } static int __init set_no_e820(const struct dmi_system_id *id) { - printk(KERN_INFO "PCI: %s detected: not clipping E820 regions from _CRS\n", - id->ident); + pr_info("%s detected: not clipping E820 regions from _CRS\n", + id->ident); pci_use_e820 = false; return 0; } @@ -231,10 +234,9 @@ void __init pci_acpi_crs_quirks(void) else if (pci_probe & PCI_USE__CRS) pci_use_crs = true; - printk(KERN_INFO "PCI: %s host bridge windows from ACPI; " - "if necessary, use \"pci=%s\" and report a bug\n", - pci_use_crs ? "Using" : "Ignoring", - pci_use_crs ? "nocrs" : "use_crs"); + pr_info("%s host bridge windows from ACPI; if necessary, use \"pci=%s\" and report a bug\n", + pci_use_crs ? "Using" : "Ignoring", + pci_use_crs ? "nocrs" : "use_crs"); /* "pci=use_e820"/"pci=no_e820" on the kernel cmdline takes precedence */ if (pci_probe & PCI_NO_E820) @@ -242,19 +244,17 @@ void __init pci_acpi_crs_quirks(void) else if (pci_probe & PCI_USE_E820) pci_use_e820 = true; - printk(KERN_INFO "PCI: %s E820 reservations for host bridge windows\n", - pci_use_e820 ? "Using" : "Ignoring"); + pr_info("%s E820 reservations for host bridge windows\n", + pci_use_e820 ? "Using" : "Ignoring"); if (pci_probe & (PCI_NO_E820 | PCI_USE_E820)) - printk(KERN_INFO "PCI: Please notify linux-pci@vger.kernel.org so future kernels can this automatically\n"); + pr_info("Please notify linux-pci@vger.kernel.org so future kernels can do this automatically\n"); } #ifdef CONFIG_PCI_MMCONFIG static int check_segment(u16 seg, struct device *dev, char *estr) { if (seg) { - dev_err(dev, - "%s can't access PCI configuration " - "space under this host bridge.\n", + dev_err(dev, "%s can't access configuration space under this host bridge\n", estr); return -EIO; } @@ -264,9 +264,7 @@ static int check_segment(u16 seg, struct device *dev, char *estr) * just can't access extended configuration space of * devices under this host bridge. */ - dev_warn(dev, - "%s can't access extended PCI configuration " - "space under this bridge.\n", + dev_warn(dev, "%s can't access extended configuration space under this bridge\n", estr); return 0; @@ -421,9 +419,8 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) root->segment = domain = 0; if (domain && !pci_domains_supported) { - printk(KERN_WARNING "pci_bus %04x:%02x: " - "ignored (multiple domains not supported)\n", - domain, busnum); + pr_warn("pci_bus %04x:%02x: ignored (multiple domains not supported)\n", + domain, busnum); return NULL; } @@ -491,7 +488,7 @@ int __init pci_acpi_init(void) if (acpi_noirq) return -ENODEV; - printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n"); + pr_info("Using ACPI for IRQ routing\n"); acpi_irq_penalty_init(); pcibios_enable_irq = acpi_pci_irq_enable; pcibios_disable_irq = acpi_pci_irq_disable; @@ -503,7 +500,7 @@ int __init pci_acpi_init(void) * also do it here in case there are still broken drivers that * don't use pci_enable_device(). */ - printk(KERN_INFO "PCI: Routing PCI interrupts for all devices because \"pci=routeirq\" specified\n"); + pr_info("Routing PCI interrupts for all devices because \"pci=routeirq\" specified\n"); for_each_pci_dev(dev) acpi_pci_irq_enable(dev); } diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile index a50245157685..543df9a1379d 100644 --- a/arch/x86/platform/efi/Makefile +++ b/arch/x86/platform/efi/Makefile @@ -2,5 +2,8 @@ KASAN_SANITIZE := n GCOV_PROFILE := n -obj-$(CONFIG_EFI) += quirks.o efi.o efi_$(BITS).o efi_stub_$(BITS).o +obj-$(CONFIG_EFI) += memmap.o quirks.o efi.o efi_$(BITS).o \ + efi_stub_$(BITS).o obj-$(CONFIG_EFI_MIXED) += efi_thunk_$(BITS).o +obj-$(CONFIG_EFI_FAKE_MEMMAP) += fake_mem.o +obj-$(CONFIG_EFI_RUNTIME_MAP) += runtime-map.o diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index ebc98a68c400..55d9caf66401 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -214,9 +214,11 @@ int __init efi_memblock_x86_reserve_range(void) data.desc_size = e->efi_memdesc_size; data.desc_version = e->efi_memdesc_version; - rv = efi_memmap_init_early(&data); - if (rv) - return rv; + if (!efi_enabled(EFI_PARAVIRT)) { + rv = efi_memmap_init_early(&data); + if (rv) + return rv; + } if (add_efi_memmap || do_efi_soft_reserve()) do_add_efi_memmap(); @@ -303,6 +305,50 @@ static void __init efi_clean_memmap(void) } } +/* + * Firmware can use EfiMemoryMappedIO to request that MMIO regions be + * mapped by the OS so they can be accessed by EFI runtime services, but + * should have no other significance to the OS (UEFI r2.10, sec 7.2). + * However, most bootloaders and EFI stubs convert EfiMemoryMappedIO + * regions to E820_TYPE_RESERVED entries, which prevent Linux from + * allocating space from them (see remove_e820_regions()). + * + * Some platforms use EfiMemoryMappedIO entries for PCI MMCONFIG space and + * PCI host bridge windows, which means Linux can't allocate BAR space for + * hot-added devices. + * + * Remove large EfiMemoryMappedIO regions from the E820 map to avoid this + * problem. + * + * Retain small EfiMemoryMappedIO regions because on some platforms, these + * describe non-window space that's included in host bridge _CRS. If we + * assign that space to PCI devices, they don't work. + */ +static void __init efi_remove_e820_mmio(void) +{ + efi_memory_desc_t *md; + u64 size, start, end; + int i = 0; + + for_each_efi_memory_desc(md) { + if (md->type == EFI_MEMORY_MAPPED_IO) { + size = md->num_pages << EFI_PAGE_SHIFT; + start = md->phys_addr; + end = start + size - 1; + if (size >= 256*1024) { + pr_info("Remove mem%02u: MMIO range=[0x%08llx-0x%08llx] (%lluMB) from e820 map\n", + i, start, end, size >> 20); + e820__range_remove(start, size, + E820_TYPE_RESERVED, 1); + } else { + pr_info("Not removing mem%02u: MMIO range=[0x%08llx-0x%08llx] (%lluKB) from e820 map\n", + i, start, end, size >> 10); + } + } + i++; + } +} + void __init efi_print_memmap(void) { efi_memory_desc_t *md; @@ -474,6 +520,8 @@ void __init efi_init(void) set_bit(EFI_RUNTIME_SERVICES, &efi.flags); efi_clean_memmap(); + efi_remove_e820_mmio(); + if (efi_enabled(EFI_DBG)) efi_print_memmap(); } diff --git a/arch/x86/platform/efi/fake_mem.c b/arch/x86/platform/efi/fake_mem.c new file mode 100644 index 000000000000..41d57cad3d84 --- /dev/null +++ b/arch/x86/platform/efi/fake_mem.c @@ -0,0 +1,197 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * fake_mem.c + * + * Copyright (C) 2015 FUJITSU LIMITED + * Author: Taku Izumi <izumi.taku@jp.fujitsu.com> + * + * This code introduces new boot option named "efi_fake_mem" + * By specifying this parameter, you can add arbitrary attribute to + * specific memory range by updating original (firmware provided) EFI + * memmap. + */ + +#include <linux/kernel.h> +#include <linux/efi.h> +#include <linux/init.h> +#include <linux/memblock.h> +#include <linux/types.h> +#include <linux/sort.h> +#include <asm/e820/api.h> +#include <asm/efi.h> + +#define EFI_MAX_FAKEMEM CONFIG_EFI_MAX_FAKE_MEM + +static struct efi_mem_range efi_fake_mems[EFI_MAX_FAKEMEM]; +static int nr_fake_mem; + +static int __init cmp_fake_mem(const void *x1, const void *x2) +{ + const struct efi_mem_range *m1 = x1; + const struct efi_mem_range *m2 = x2; + + if (m1->range.start < m2->range.start) + return -1; + if (m1->range.start > m2->range.start) + return 1; + return 0; +} + +static void __init efi_fake_range(struct efi_mem_range *efi_range) +{ + struct efi_memory_map_data data = { 0 }; + int new_nr_map = efi.memmap.nr_map; + efi_memory_desc_t *md; + void *new_memmap; + + /* count up the number of EFI memory descriptor */ + for_each_efi_memory_desc(md) + new_nr_map += efi_memmap_split_count(md, &efi_range->range); + + /* allocate memory for new EFI memmap */ + if (efi_memmap_alloc(new_nr_map, &data) != 0) + return; + + /* create new EFI memmap */ + new_memmap = early_memremap(data.phys_map, data.size); + if (!new_memmap) { + __efi_memmap_free(data.phys_map, data.size, data.flags); + return; + } + + efi_memmap_insert(&efi.memmap, new_memmap, efi_range); + + /* swap into new EFI memmap */ + early_memunmap(new_memmap, data.size); + + efi_memmap_install(&data); +} + +void __init efi_fake_memmap(void) +{ + int i; + + if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem) + return; + + for (i = 0; i < nr_fake_mem; i++) + efi_fake_range(&efi_fake_mems[i]); + + /* print new EFI memmap */ + efi_print_memmap(); +} + +static int __init setup_fake_mem(char *p) +{ + u64 start = 0, mem_size = 0, attribute = 0; + int i; + + if (!p) + return -EINVAL; + + while (*p != '\0') { + mem_size = memparse(p, &p); + if (*p == '@') + start = memparse(p+1, &p); + else + break; + + if (*p == ':') + attribute = simple_strtoull(p+1, &p, 0); + else + break; + + if (nr_fake_mem >= EFI_MAX_FAKEMEM) + break; + + efi_fake_mems[nr_fake_mem].range.start = start; + efi_fake_mems[nr_fake_mem].range.end = start + mem_size - 1; + efi_fake_mems[nr_fake_mem].attribute = attribute; + nr_fake_mem++; + + if (*p == ',') + p++; + } + + sort(efi_fake_mems, nr_fake_mem, sizeof(struct efi_mem_range), + cmp_fake_mem, NULL); + + for (i = 0; i < nr_fake_mem; i++) + pr_info("efi_fake_mem: add attr=0x%016llx to [mem 0x%016llx-0x%016llx]", + efi_fake_mems[i].attribute, efi_fake_mems[i].range.start, + efi_fake_mems[i].range.end); + + return *p == '\0' ? 0 : -EINVAL; +} + +early_param("efi_fake_mem", setup_fake_mem); + +void __init efi_fake_memmap_early(void) +{ + int i; + + /* + * The late efi_fake_mem() call can handle all requests if + * EFI_MEMORY_SP support is disabled. + */ + if (!efi_soft_reserve_enabled()) + return; + + if (!efi_enabled(EFI_MEMMAP) || !nr_fake_mem) + return; + + /* + * Given that efi_fake_memmap() needs to perform memblock + * allocations it needs to run after e820__memblock_setup(). + * However, if efi_fake_mem specifies EFI_MEMORY_SP for a given + * address range that potentially needs to mark the memory as + * reserved prior to e820__memblock_setup(). Update e820 + * directly if EFI_MEMORY_SP is specified for an + * EFI_CONVENTIONAL_MEMORY descriptor. + */ + for (i = 0; i < nr_fake_mem; i++) { + struct efi_mem_range *mem = &efi_fake_mems[i]; + efi_memory_desc_t *md; + u64 m_start, m_end; + + if ((mem->attribute & EFI_MEMORY_SP) == 0) + continue; + + m_start = mem->range.start; + m_end = mem->range.end; + for_each_efi_memory_desc(md) { + u64 start, end, size; + + if (md->type != EFI_CONVENTIONAL_MEMORY) + continue; + + start = md->phys_addr; + end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1; + + if (m_start <= end && m_end >= start) + /* fake range overlaps descriptor */; + else + continue; + + /* + * Trim the boundary of the e820 update to the + * descriptor in case the fake range overlaps + * !EFI_CONVENTIONAL_MEMORY + */ + start = max(start, m_start); + end = min(end, m_end); + size = end - start + 1; + + if (end <= start) + continue; + + /* + * Ensure each efi_fake_mem instance results in + * a unique e820 resource + */ + e820__range_remove(start, size, E820_TYPE_RAM, 1); + e820__range_add(start, size, E820_TYPE_SOFT_RESERVED); + e820__update_table(e820_table); + } + } +} diff --git a/arch/x86/platform/efi/memmap.c b/arch/x86/platform/efi/memmap.c new file mode 100644 index 000000000000..c69f8471e6d0 --- /dev/null +++ b/arch/x86/platform/efi/memmap.c @@ -0,0 +1,239 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Common EFI memory map functions. + */ + +#define pr_fmt(fmt) "efi: " fmt + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/efi.h> +#include <linux/io.h> +#include <asm/early_ioremap.h> +#include <asm/efi.h> +#include <linux/memblock.h> +#include <linux/slab.h> + +static phys_addr_t __init __efi_memmap_alloc_early(unsigned long size) +{ + return memblock_phys_alloc(size, SMP_CACHE_BYTES); +} + +static phys_addr_t __init __efi_memmap_alloc_late(unsigned long size) +{ + unsigned int order = get_order(size); + struct page *p = alloc_pages(GFP_KERNEL, order); + + if (!p) + return 0; + + return PFN_PHYS(page_to_pfn(p)); +} + +void __init __efi_memmap_free(u64 phys, unsigned long size, unsigned long flags) +{ + if (flags & EFI_MEMMAP_MEMBLOCK) { + if (slab_is_available()) + memblock_free_late(phys, size); + else + memblock_phys_free(phys, size); + } else if (flags & EFI_MEMMAP_SLAB) { + struct page *p = pfn_to_page(PHYS_PFN(phys)); + unsigned int order = get_order(size); + + free_pages((unsigned long) page_address(p), order); + } +} + +/** + * efi_memmap_alloc - Allocate memory for the EFI memory map + * @num_entries: Number of entries in the allocated map. + * @data: efi memmap installation parameters + * + * Depending on whether mm_init() has already been invoked or not, + * either memblock or "normal" page allocation is used. + * + * Returns zero on success, a negative error code on failure. + */ +int __init efi_memmap_alloc(unsigned int num_entries, + struct efi_memory_map_data *data) +{ + /* Expect allocation parameters are zero initialized */ + WARN_ON(data->phys_map || data->size); + + data->size = num_entries * efi.memmap.desc_size; + data->desc_version = efi.memmap.desc_version; + data->desc_size = efi.memmap.desc_size; + data->flags &= ~(EFI_MEMMAP_SLAB | EFI_MEMMAP_MEMBLOCK); + data->flags |= efi.memmap.flags & EFI_MEMMAP_LATE; + + if (slab_is_available()) { + data->flags |= EFI_MEMMAP_SLAB; + data->phys_map = __efi_memmap_alloc_late(data->size); + } else { + data->flags |= EFI_MEMMAP_MEMBLOCK; + data->phys_map = __efi_memmap_alloc_early(data->size); + } + + if (!data->phys_map) + return -ENOMEM; + return 0; +} + +/** + * efi_memmap_install - Install a new EFI memory map in efi.memmap + * @ctx: map allocation parameters (address, size, flags) + * + * Unlike efi_memmap_init_*(), this function does not allow the caller + * to switch from early to late mappings. It simply uses the existing + * mapping function and installs the new memmap. + * + * Returns zero on success, a negative error code on failure. + */ +int __init efi_memmap_install(struct efi_memory_map_data *data) +{ + efi_memmap_unmap(); + + if (efi_enabled(EFI_PARAVIRT)) + return 0; + + return __efi_memmap_init(data); +} + +/** + * efi_memmap_split_count - Count number of additional EFI memmap entries + * @md: EFI memory descriptor to split + * @range: Address range (start, end) to split around + * + * Returns the number of additional EFI memmap entries required to + * accommodate @range. + */ +int __init efi_memmap_split_count(efi_memory_desc_t *md, struct range *range) +{ + u64 m_start, m_end; + u64 start, end; + int count = 0; + + start = md->phys_addr; + end = start + (md->num_pages << EFI_PAGE_SHIFT) - 1; + + /* modifying range */ + m_start = range->start; + m_end = range->end; + + if (m_start <= start) { + /* split into 2 parts */ + if (start < m_end && m_end < end) + count++; + } + + if (start < m_start && m_start < end) { + /* split into 3 parts */ + if (m_end < end) + count += 2; + /* split into 2 parts */ + if (end <= m_end) + count++; + } + + return count; +} + +/** + * efi_memmap_insert - Insert a memory region in an EFI memmap + * @old_memmap: The existing EFI memory map structure + * @buf: Address of buffer to store new map + * @mem: Memory map entry to insert + * + * It is suggested that you call efi_memmap_split_count() first + * to see how large @buf needs to be. + */ +void __init efi_memmap_insert(struct efi_memory_map *old_memmap, void *buf, + struct efi_mem_range *mem) +{ + u64 m_start, m_end, m_attr; + efi_memory_desc_t *md; + u64 start, end; + void *old, *new; + + /* modifying range */ + m_start = mem->range.start; + m_end = mem->range.end; + m_attr = mem->attribute; + + /* + * The EFI memory map deals with regions in EFI_PAGE_SIZE + * units. Ensure that the region described by 'mem' is aligned + * correctly. + */ + if (!IS_ALIGNED(m_start, EFI_PAGE_SIZE) || + !IS_ALIGNED(m_end + 1, EFI_PAGE_SIZE)) { + WARN_ON(1); + return; + } + + for (old = old_memmap->map, new = buf; + old < old_memmap->map_end; + old += old_memmap->desc_size, new += old_memmap->desc_size) { + + /* copy original EFI memory descriptor */ + memcpy(new, old, old_memmap->desc_size); + md = new; + start = md->phys_addr; + end = md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT) - 1; + + if (m_start <= start && end <= m_end) + md->attribute |= m_attr; + + if (m_start <= start && + (start < m_end && m_end < end)) { + /* first part */ + md->attribute |= m_attr; + md->num_pages = (m_end - md->phys_addr + 1) >> + EFI_PAGE_SHIFT; + /* latter part */ + new += old_memmap->desc_size; + memcpy(new, old, old_memmap->desc_size); + md = new; + md->phys_addr = m_end + 1; + md->num_pages = (end - md->phys_addr + 1) >> + EFI_PAGE_SHIFT; + } + + if ((start < m_start && m_start < end) && m_end < end) { + /* first part */ + md->num_pages = (m_start - md->phys_addr) >> + EFI_PAGE_SHIFT; + /* middle part */ + new += old_memmap->desc_size; + memcpy(new, old, old_memmap->desc_size); + md = new; + md->attribute |= m_attr; + md->phys_addr = m_start; + md->num_pages = (m_end - m_start + 1) >> + EFI_PAGE_SHIFT; + /* last part */ + new += old_memmap->desc_size; + memcpy(new, old, old_memmap->desc_size); + md = new; + md->phys_addr = m_end + 1; + md->num_pages = (end - m_end) >> + EFI_PAGE_SHIFT; + } + + if ((start < m_start && m_start < end) && + (end <= m_end)) { + /* first part */ + md->num_pages = (m_start - md->phys_addr) >> + EFI_PAGE_SHIFT; + /* latter part */ + new += old_memmap->desc_size; + memcpy(new, old, old_memmap->desc_size); + md = new; + md->phys_addr = m_start; + md->num_pages = (end - md->phys_addr + 1) >> + EFI_PAGE_SHIFT; + md->attribute |= m_attr; + } + } +} diff --git a/arch/x86/platform/efi/runtime-map.c b/arch/x86/platform/efi/runtime-map.c new file mode 100644 index 000000000000..bbee682ef8cd --- /dev/null +++ b/arch/x86/platform/efi/runtime-map.c @@ -0,0 +1,194 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2013 Red Hat, Inc., Dave Young <dyoung@redhat.com> + */ + +#include <linux/string.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/types.h> +#include <linux/efi.h> +#include <linux/slab.h> + +#include <asm/efi.h> +#include <asm/setup.h> + +struct efi_runtime_map_entry { + efi_memory_desc_t md; + struct kobject kobj; /* kobject for each entry */ +}; + +static struct efi_runtime_map_entry **map_entries; + +struct map_attribute { + struct attribute attr; + ssize_t (*show)(struct efi_runtime_map_entry *entry, char *buf); +}; + +static inline struct map_attribute *to_map_attr(struct attribute *attr) +{ + return container_of(attr, struct map_attribute, attr); +} + +static ssize_t type_show(struct efi_runtime_map_entry *entry, char *buf) +{ + return snprintf(buf, PAGE_SIZE, "0x%x\n", entry->md.type); +} + +#define EFI_RUNTIME_FIELD(var) entry->md.var + +#define EFI_RUNTIME_U64_ATTR_SHOW(name) \ +static ssize_t name##_show(struct efi_runtime_map_entry *entry, char *buf) \ +{ \ + return snprintf(buf, PAGE_SIZE, "0x%llx\n", EFI_RUNTIME_FIELD(name)); \ +} + +EFI_RUNTIME_U64_ATTR_SHOW(phys_addr); +EFI_RUNTIME_U64_ATTR_SHOW(virt_addr); +EFI_RUNTIME_U64_ATTR_SHOW(num_pages); +EFI_RUNTIME_U64_ATTR_SHOW(attribute); + +static inline struct efi_runtime_map_entry *to_map_entry(struct kobject *kobj) +{ + return container_of(kobj, struct efi_runtime_map_entry, kobj); +} + +static ssize_t map_attr_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + struct efi_runtime_map_entry *entry = to_map_entry(kobj); + struct map_attribute *map_attr = to_map_attr(attr); + + return map_attr->show(entry, buf); +} + +static struct map_attribute map_type_attr = __ATTR_RO_MODE(type, 0400); +static struct map_attribute map_phys_addr_attr = __ATTR_RO_MODE(phys_addr, 0400); +static struct map_attribute map_virt_addr_attr = __ATTR_RO_MODE(virt_addr, 0400); +static struct map_attribute map_num_pages_attr = __ATTR_RO_MODE(num_pages, 0400); +static struct map_attribute map_attribute_attr = __ATTR_RO_MODE(attribute, 0400); + +/* + * These are default attributes that are added for every memmap entry. + */ +static struct attribute *def_attrs[] = { + &map_type_attr.attr, + &map_phys_addr_attr.attr, + &map_virt_addr_attr.attr, + &map_num_pages_attr.attr, + &map_attribute_attr.attr, + NULL +}; +ATTRIBUTE_GROUPS(def); + +static const struct sysfs_ops map_attr_ops = { + .show = map_attr_show, +}; + +static void map_release(struct kobject *kobj) +{ + struct efi_runtime_map_entry *entry; + + entry = to_map_entry(kobj); + kfree(entry); +} + +static struct kobj_type __refdata map_ktype = { + .sysfs_ops = &map_attr_ops, + .default_groups = def_groups, + .release = map_release, +}; + +static struct kset *map_kset; + +static struct efi_runtime_map_entry * +add_sysfs_runtime_map_entry(struct kobject *kobj, int nr, + efi_memory_desc_t *md) +{ + int ret; + struct efi_runtime_map_entry *entry; + + if (!map_kset) { + map_kset = kset_create_and_add("runtime-map", NULL, kobj); + if (!map_kset) + return ERR_PTR(-ENOMEM); + } + + entry = kzalloc(sizeof(*entry), GFP_KERNEL); + if (!entry) { + kset_unregister(map_kset); + map_kset = NULL; + return ERR_PTR(-ENOMEM); + } + + memcpy(&entry->md, md, sizeof(efi_memory_desc_t)); + + kobject_init(&entry->kobj, &map_ktype); + entry->kobj.kset = map_kset; + ret = kobject_add(&entry->kobj, NULL, "%d", nr); + if (ret) { + kobject_put(&entry->kobj); + kset_unregister(map_kset); + map_kset = NULL; + return ERR_PTR(ret); + } + + return entry; +} + +int efi_get_runtime_map_size(void) +{ + return efi.memmap.nr_map * efi.memmap.desc_size; +} + +int efi_get_runtime_map_desc_size(void) +{ + return efi.memmap.desc_size; +} + +int efi_runtime_map_copy(void *buf, size_t bufsz) +{ + size_t sz = efi_get_runtime_map_size(); + + if (sz > bufsz) + sz = bufsz; + + memcpy(buf, efi.memmap.map, sz); + return 0; +} + +static int __init efi_runtime_map_init(void) +{ + int i, j, ret = 0; + struct efi_runtime_map_entry *entry; + efi_memory_desc_t *md; + + if (!efi_enabled(EFI_MEMMAP) || !efi_kobj) + return 0; + + map_entries = kcalloc(efi.memmap.nr_map, sizeof(entry), GFP_KERNEL); + if (!map_entries) { + ret = -ENOMEM; + goto out; + } + + i = 0; + for_each_efi_memory_desc(md) { + entry = add_sysfs_runtime_map_entry(efi_kobj, i, md); + if (IS_ERR(entry)) { + ret = PTR_ERR(entry); + goto out_add_entry; + } + *(map_entries + i++) = entry; + } + + return 0; +out_add_entry: + for (j = i - 1; j >= 0; j--) { + entry = *(map_entries + j); + kobject_put(&entry->kobj); + } +out: + return ret; +} +subsys_initcall_sync(efi_runtime_map_init); diff --git a/arch/x86/platform/olpc/olpc-xo15-sci.c b/arch/x86/platform/olpc/olpc-xo15-sci.c index 994a229cb79f..68244a3422d1 100644 --- a/arch/x86/platform/olpc/olpc-xo15-sci.c +++ b/arch/x86/platform/olpc/olpc-xo15-sci.c @@ -183,13 +183,12 @@ err_sysfs: return r; } -static int xo15_sci_remove(struct acpi_device *device) +static void xo15_sci_remove(struct acpi_device *device) { acpi_disable_gpe(NULL, xo15_sci_gpe); acpi_remove_gpe_handler(NULL, xo15_sci_gpe, xo15_sci_gpe_handler); cancel_work_sync(&sci_work); sysfs_remove_file(&device->dev.kobj, &lid_wake_on_close_attr.attr); - return 0; } #ifdef CONFIG_PM_SLEEP diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c index 4cd39f304e20..236447ee9beb 100644 --- a/arch/x86/power/cpu.c +++ b/arch/x86/power/cpu.c @@ -23,6 +23,7 @@ #include <asm/fpu/api.h> #include <asm/debugreg.h> #include <asm/cpu.h> +#include <asm/cacheinfo.h> #include <asm/mmu_context.h> #include <asm/cpu_device_id.h> #include <asm/microcode.h> @@ -261,7 +262,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt) do_fpu_end(); tsc_verify_tsc_adjust(true); x86_platform.restore_sched_clock_state(); - mtrr_bp_restore(); + cache_bp_restore(); perf_restore_debug_store(); c = &cpu_data(smp_processor_id()); @@ -513,16 +514,23 @@ static int pm_cpu_check(const struct x86_cpu_id *c) static void pm_save_spec_msr(void) { - u32 spec_msr_id[] = { - MSR_IA32_SPEC_CTRL, - MSR_IA32_TSX_CTRL, - MSR_TSX_FORCE_ABORT, - MSR_IA32_MCU_OPT_CTRL, - MSR_AMD64_LS_CFG, - MSR_AMD64_DE_CFG, + struct msr_enumeration { + u32 msr_no; + u32 feature; + } msr_enum[] = { + { MSR_IA32_SPEC_CTRL, X86_FEATURE_MSR_SPEC_CTRL }, + { MSR_IA32_TSX_CTRL, X86_FEATURE_MSR_TSX_CTRL }, + { MSR_TSX_FORCE_ABORT, X86_FEATURE_TSX_FORCE_ABORT }, + { MSR_IA32_MCU_OPT_CTRL, X86_FEATURE_SRBDS_CTRL }, + { MSR_AMD64_LS_CFG, X86_FEATURE_LS_CFG_SSBD }, + { MSR_AMD64_DE_CFG, X86_FEATURE_LFENCE_RDTSC }, }; + int i; - msr_build_context(spec_msr_id, ARRAY_SIZE(spec_msr_id)); + for (i = 0; i < ARRAY_SIZE(msr_enum); i++) { + if (boot_cpu_has(msr_enum[i].feature)) + msr_build_context(&msr_enum[i].msr_no, 1); + } } static int pm_check_save_msr(void) diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c index e94e0050a583..6f955eb1e163 100644 --- a/arch/x86/power/hibernate.c +++ b/arch/x86/power/hibernate.c @@ -159,7 +159,7 @@ int relocate_restore_code(void) if (!relocated_restore_code) return -ENOMEM; - memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE); + __memcpy((void *)relocated_restore_code, core_restore_code, PAGE_SIZE); /* Make the page containing the relocated code executable */ pgd = (pgd_t *)__va(read_cr3_pa()) + diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 41d7669a97ad..af565816d2ba 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -200,14 +200,18 @@ static void __init set_real_mode_permissions(void) set_memory_x((unsigned long) text_start, text_size >> PAGE_SHIFT); } -static int __init init_real_mode(void) +void __init init_real_mode(void) { if (!real_mode_header) panic("Real mode trampoline was not allocated"); setup_real_mode(); set_real_mode_permissions(); +} +static int __init do_init_real_mode(void) +{ + x86_platform.realmode_init(); return 0; } -early_initcall(init_real_mode); +early_initcall(do_init_real_mode); diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h index dcaf3b38a9e0..6523eb7c3bd1 100644 --- a/arch/x86/um/asm/elf.h +++ b/arch/x86/um/asm/elf.h @@ -201,10 +201,6 @@ typedef struct user_i387_struct elf_fpregset_t; struct task_struct; -extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu); - -#define ELF_CORE_COPY_FPREGS(t, fpu) elf_core_copy_fpregs(t, fpu) - #define ELF_EXEC_PAGESIZE 4096 #define ELF_ET_DYN_BASE (TASK_SIZE / 3 * 2) diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index 038da45f057a..5b1379662877 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -33,6 +33,7 @@ #include <linux/edd.h> #include <linux/reboot.h> #include <linux/virtio_anchor.h> +#include <linux/stackprotector.h> #include <xen/xen.h> #include <xen/events.h> @@ -65,7 +66,6 @@ #include <asm/pgalloc.h> #include <asm/tlbflush.h> #include <asm/reboot.h> -#include <asm/stackprotector.h> #include <asm/hypervisor.h> #include <asm/mach_traps.h> #include <asm/mwait.h> @@ -1210,7 +1210,7 @@ static void __init xen_setup_gdt(int cpu) pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry_boot; pv_ops.cpu.load_gdt = xen_load_gdt_boot; - switch_to_new_gdt(cpu); + switch_gdt_and_percpu_base(cpu); pv_ops.cpu.write_gdt_entry = xen_write_gdt_entry; pv_ops.cpu.load_gdt = xen_load_gdt; @@ -1266,6 +1266,8 @@ asmlinkage __visible void __init xen_start_kernel(struct start_info *si) xen_vcpu_info_reset(0); x86_platform.get_nmi_reason = xen_get_nmi_reason; + x86_platform.realmode_reserve = x86_init_noop; + x86_platform.realmode_init = x86_init_noop; x86_init.resources.memory_setup = xen_memory_setup; x86_init.irqs.intr_mode_select = x86_init_noop; diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index c3e1f9a7d43a..4b0d6fff88de 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -32,30 +32,30 @@ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id) void xen_smp_intr_free(unsigned int cpu) { + kfree(per_cpu(xen_resched_irq, cpu).name); + per_cpu(xen_resched_irq, cpu).name = NULL; if (per_cpu(xen_resched_irq, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu).irq, NULL); per_cpu(xen_resched_irq, cpu).irq = -1; - kfree(per_cpu(xen_resched_irq, cpu).name); - per_cpu(xen_resched_irq, cpu).name = NULL; } + kfree(per_cpu(xen_callfunc_irq, cpu).name); + per_cpu(xen_callfunc_irq, cpu).name = NULL; if (per_cpu(xen_callfunc_irq, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu).irq, NULL); per_cpu(xen_callfunc_irq, cpu).irq = -1; - kfree(per_cpu(xen_callfunc_irq, cpu).name); - per_cpu(xen_callfunc_irq, cpu).name = NULL; } + kfree(per_cpu(xen_debug_irq, cpu).name); + per_cpu(xen_debug_irq, cpu).name = NULL; if (per_cpu(xen_debug_irq, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu).irq, NULL); per_cpu(xen_debug_irq, cpu).irq = -1; - kfree(per_cpu(xen_debug_irq, cpu).name); - per_cpu(xen_debug_irq, cpu).name = NULL; } + kfree(per_cpu(xen_callfuncsingle_irq, cpu).name); + per_cpu(xen_callfuncsingle_irq, cpu).name = NULL; if (per_cpu(xen_callfuncsingle_irq, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu).irq, NULL); per_cpu(xen_callfuncsingle_irq, cpu).irq = -1; - kfree(per_cpu(xen_callfuncsingle_irq, cpu).name); - per_cpu(xen_callfuncsingle_irq, cpu).name = NULL; } } @@ -65,6 +65,7 @@ int xen_smp_intr_init(unsigned int cpu) char *resched_name, *callfunc_name, *debug_name; resched_name = kasprintf(GFP_KERNEL, "resched%d", cpu); + per_cpu(xen_resched_irq, cpu).name = resched_name; rc = bind_ipi_to_irqhandler(XEN_RESCHEDULE_VECTOR, cpu, xen_reschedule_interrupt, @@ -74,9 +75,9 @@ int xen_smp_intr_init(unsigned int cpu) if (rc < 0) goto fail; per_cpu(xen_resched_irq, cpu).irq = rc; - per_cpu(xen_resched_irq, cpu).name = resched_name; callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu); + per_cpu(xen_callfunc_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR, cpu, xen_call_function_interrupt, @@ -86,10 +87,10 @@ int xen_smp_intr_init(unsigned int cpu) if (rc < 0) goto fail; per_cpu(xen_callfunc_irq, cpu).irq = rc; - per_cpu(xen_callfunc_irq, cpu).name = callfunc_name; if (!xen_fifo_events) { debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu); + per_cpu(xen_debug_irq, cpu).name = debug_name; rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt, IRQF_PERCPU | IRQF_NOBALANCING, @@ -97,10 +98,10 @@ int xen_smp_intr_init(unsigned int cpu) if (rc < 0) goto fail; per_cpu(xen_debug_irq, cpu).irq = rc; - per_cpu(xen_debug_irq, cpu).name = debug_name; } callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu); + per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR, cpu, xen_call_function_single_interrupt, @@ -110,7 +111,6 @@ int xen_smp_intr_init(unsigned int cpu) if (rc < 0) goto fail; per_cpu(xen_callfuncsingle_irq, cpu).irq = rc; - per_cpu(xen_callfuncsingle_irq, cpu).name = callfunc_name; return 0; diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 480be82e9b7b..6175f2c5c822 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -97,18 +97,18 @@ asmlinkage __visible void cpu_bringup_and_idle(void) void xen_smp_intr_free_pv(unsigned int cpu) { + kfree(per_cpu(xen_irq_work, cpu).name); + per_cpu(xen_irq_work, cpu).name = NULL; if (per_cpu(xen_irq_work, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_irq_work, cpu).irq, NULL); per_cpu(xen_irq_work, cpu).irq = -1; - kfree(per_cpu(xen_irq_work, cpu).name); - per_cpu(xen_irq_work, cpu).name = NULL; } + kfree(per_cpu(xen_pmu_irq, cpu).name); + per_cpu(xen_pmu_irq, cpu).name = NULL; if (per_cpu(xen_pmu_irq, cpu).irq >= 0) { unbind_from_irqhandler(per_cpu(xen_pmu_irq, cpu).irq, NULL); per_cpu(xen_pmu_irq, cpu).irq = -1; - kfree(per_cpu(xen_pmu_irq, cpu).name); - per_cpu(xen_pmu_irq, cpu).name = NULL; } } @@ -118,6 +118,7 @@ int xen_smp_intr_init_pv(unsigned int cpu) char *callfunc_name, *pmu_name; callfunc_name = kasprintf(GFP_KERNEL, "irqwork%d", cpu); + per_cpu(xen_irq_work, cpu).name = callfunc_name; rc = bind_ipi_to_irqhandler(XEN_IRQ_WORK_VECTOR, cpu, xen_irq_work_interrupt, @@ -127,10 +128,10 @@ int xen_smp_intr_init_pv(unsigned int cpu) if (rc < 0) goto fail; per_cpu(xen_irq_work, cpu).irq = rc; - per_cpu(xen_irq_work, cpu).name = callfunc_name; if (is_xen_pmu) { pmu_name = kasprintf(GFP_KERNEL, "pmu%d", cpu); + per_cpu(xen_pmu_irq, cpu).name = pmu_name; rc = bind_virq_to_irqhandler(VIRQ_XENPMU, cpu, xen_pmu_irq_handler, IRQF_PERCPU|IRQF_NOBALANCING, @@ -138,7 +139,6 @@ int xen_smp_intr_init_pv(unsigned int cpu) if (rc < 0) goto fail; per_cpu(xen_pmu_irq, cpu).irq = rc; - per_cpu(xen_pmu_irq, cpu).name = pmu_name; } return 0; diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c index 043c73dfd2c9..5c6fc16e4b92 100644 --- a/arch/x86/xen/spinlock.c +++ b/arch/x86/xen/spinlock.c @@ -75,6 +75,7 @@ void xen_init_lock_cpu(int cpu) cpu, per_cpu(lock_kicker_irq, cpu)); name = kasprintf(GFP_KERNEL, "spinlock%d", cpu); + per_cpu(irq_name, cpu) = name; irq = bind_ipi_to_irqhandler(XEN_SPIN_UNLOCK_VECTOR, cpu, dummy_handler, @@ -85,7 +86,6 @@ void xen_init_lock_cpu(int cpu) if (irq >= 0) { disable_irq(irq); /* make sure it's never delivered */ per_cpu(lock_kicker_irq, cpu) = irq; - per_cpu(irq_name, cpu) = name; } printk("cpu %d spinlock event irq %d\n", cpu, irq); @@ -98,6 +98,8 @@ void xen_uninit_lock_cpu(int cpu) if (!xen_pvspin) return; + kfree(per_cpu(irq_name, cpu)); + per_cpu(irq_name, cpu) = NULL; /* * When booting the kernel with 'mitigations=auto,nosmt', the secondary * CPUs are not activated, and lock_kicker_irq is not initialized. @@ -108,8 +110,6 @@ void xen_uninit_lock_cpu(int cpu) unbind_from_irqhandler(irq, NULL); per_cpu(lock_kicker_irq, cpu) = -1; - kfree(per_cpu(irq_name, cpu)); - per_cpu(irq_name, cpu) = NULL; } PV_CALLEE_SAVE_REGS_THUNK(xen_vcpu_stolen); diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 6b4fdf6b9542..4a184f6e4e4d 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -262,10 +262,10 @@ SYM_CODE_START(xen_entry_SYSCALL_compat) /* * Neither Xen nor the kernel really knows what the old SS and - * CS were. The kernel expects __USER32_DS and __USER32_CS, so + * CS were. The kernel expects __USER_DS and __USER32_CS, so * report those values even though Xen will guess its own values. */ - movq $__USER32_DS, 4*8(%rsp) + movq $__USER_DS, 4*8(%rsp) movq $__USER32_CS, 1*8(%rsp) jmp entry_SYSCALL_compat_after_hwframe @@ -284,10 +284,10 @@ SYM_CODE_START(xen_entry_SYSENTER_compat) /* * Neither Xen nor the kernel really knows what the old SS and - * CS were. The kernel expects __USER32_DS and __USER32_CS, so + * CS were. The kernel expects __USER_DS and __USER32_CS, so * report those values even though Xen will guess its own values. */ - movq $__USER32_DS, 4*8(%rsp) + movq $__USER_DS, 4*8(%rsp) movq $__USER32_CS, 1*8(%rsp) jmp entry_SYSENTER_compat_after_hwframe |