diff options
| author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-08-07 13:11:40 +0000 |
|---|---|---|
| committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-08-07 13:11:40 +0000 |
| commit | 8b0a8165cdad0f4133837d753649ef4682e42c3b (patch) | |
| tree | 5c58f869f31ddb1f7bd6e8bdea269b680b36c5b6 /arch/x86 | |
| parent | Releasing progress-linux version 6.8.12-1~progress7.99u1. (diff) | |
| download | linux-8b0a8165cdad0f4133837d753649ef4682e42c3b.tar.xz linux-8b0a8165cdad0f4133837d753649ef4682e42c3b.zip | |
Merging upstream version 6.9.7.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'arch/x86')
332 files changed, 8400 insertions, 4385 deletions
diff --git a/arch/x86/Kbuild b/arch/x86/Kbuild index 5a83da703e..cf0ad89f56 100644 --- a/arch/x86/Kbuild +++ b/arch/x86/Kbuild @@ -28,5 +28,7 @@ obj-y += net/ obj-$(CONFIG_KEXEC_FILE) += purgatory/ +obj-y += virt/ + # for cleaning subdir- += boot tools diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index bfccf12138..f5b3d14ff3 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -101,7 +101,7 @@ config X86 select ARCH_HAS_STRICT_MODULE_RWX select ARCH_HAS_SYNC_CORE_BEFORE_USERMODE select ARCH_HAS_SYSCALL_WRAPPER - select ARCH_HAS_UBSAN_SANITIZE_ALL + select ARCH_HAS_UBSAN select ARCH_HAS_DEBUG_WX select ARCH_HAS_ZONE_DMA_SET if EXPERT select ARCH_HAVE_NMI_SAFE_CMPXCHG @@ -148,6 +148,7 @@ config X86 select EDAC_ATOMIC_SCRUB select EDAC_SUPPORT select GENERIC_CLOCKEVENTS_BROADCAST if X86_64 || (X86_32 && X86_LOCAL_APIC) + select GENERIC_CLOCKEVENTS_BROADCAST_IDLE if GENERIC_CLOCKEVENTS_BROADCAST select GENERIC_CLOCKEVENTS_MIN_ADJUST select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE @@ -245,7 +246,6 @@ config X86 select HAVE_FUNCTION_ERROR_INJECTION select HAVE_KRETPROBES select HAVE_RETHOOK - select HAVE_KVM select HAVE_LIVEPATCH if X86_64 select HAVE_MIXED_BREAKPOINTS_REGS select HAVE_MOD_ARCH_SPECIFIC @@ -256,6 +256,7 @@ config X86 select HAVE_NOINSTR_VALIDATION if HAVE_OBJTOOL select HAVE_OBJTOOL if X86_64 select HAVE_OPTPROBES + select HAVE_PAGE_SIZE_4KB select HAVE_PCSPKR_PLATFORM select HAVE_PERF_EVENTS select HAVE_PERF_EVENTS_NMI @@ -472,10 +473,6 @@ config X86_MPPARSE For old smp systems that do not have proper acpi support. Newer systems (esp with 64bit cpus) with acpi support, MADT and DSDT will override it -config GOLDFISH - def_bool y - depends on X86_GOLDFISH - config X86_CPU_RESCTRL bool "x86 CPU resource control support" depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD) @@ -497,6 +494,15 @@ config X86_CPU_RESCTRL Say N if unsure. +config X86_FRED + bool "Flexible Return and Event Delivery" + depends on X86_64 + help + When enabled, try to use Flexible Return and Event Delivery + instead of the legacy SYSCALL/SYSENTER/IDT architecture for + ring transitions and exception/interrupt handling if the + system supports it. + if X86_32 config X86_BIGSMP bool "Support for big SMP systems with more than 8 CPUs" @@ -1055,8 +1061,9 @@ config SCHED_MC config SCHED_MC_PRIO bool "CPU core priorities scheduler support" - depends on SCHED_MC && CPU_SUP_INTEL - select X86_INTEL_PSTATE + depends on SCHED_MC + select X86_INTEL_PSTATE if CPU_SUP_INTEL + select X86_AMD_PSTATE if CPU_SUP_AMD && ACPI select CPU_FREQ default y help @@ -2094,7 +2101,7 @@ config ARCH_SUPPORTS_CRASH_HOTPLUG def_bool y config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION - def_bool CRASH_CORE + def_bool CRASH_RESERVE config PHYSICAL_START hex "Physical address where the kernel is loaded" if (EXPERT || CRASH_DUMP) @@ -2102,11 +2109,11 @@ config PHYSICAL_START help This gives the physical address where the kernel is loaded. - If kernel is a not relocatable (CONFIG_RELOCATABLE=n) then - bzImage will decompress itself to above physical address and - run from there. Otherwise, bzImage will run from the address where - it has been loaded by the boot loader and will ignore above physical - address. + If the kernel is not relocatable (CONFIG_RELOCATABLE=n) then bzImage + will decompress itself to above physical address and run from there. + Otherwise, bzImage will run from the address where it has been loaded + by the boot loader. The only exception is if it is loaded below the + above physical address, in which case it will relocate itself there. In normal kdump cases one does not have to set/change this option as now bzImage can be compiled as a completely relocatable image @@ -2422,6 +2429,20 @@ source "kernel/livepatch/Kconfig" endmenu +config CC_HAS_NAMED_AS + def_bool CC_IS_GCC && GCC_VERSION >= 120100 + +config USE_X86_SEG_SUPPORT + def_bool y + depends on CC_HAS_NAMED_AS + # + # -fsanitize=kernel-address (KASAN) is at the moment incompatible + # with named address spaces - see GCC PR sanitizer/111736. + # + depends on !KASAN + # -fsanitize=thread (KCSAN) is also incompatible. + depends on !KCSAN + config CC_HAS_SLS def_bool $(cc-option,-mharden-sls=all) @@ -2453,12 +2474,12 @@ config CALL_PADDING config FINEIBT def_bool y - depends on X86_KERNEL_IBT && CFI_CLANG && RETPOLINE + depends on X86_KERNEL_IBT && CFI_CLANG && MITIGATION_RETPOLINE select CALL_PADDING config HAVE_CALL_THUNKS def_bool y - depends on CC_HAS_ENTRY_PADDING && RETHUNK && OBJTOOL + depends on CC_HAS_ENTRY_PADDING && MITIGATION_RETHUNK && OBJTOOL config CALL_THUNKS def_bool n @@ -2484,7 +2505,7 @@ menuconfig CPU_MITIGATIONS if CPU_MITIGATIONS -config PAGE_TABLE_ISOLATION +config MITIGATION_PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" default y depends on (X86_64 || X86_PAE) @@ -2495,7 +2516,7 @@ config PAGE_TABLE_ISOLATION See Documentation/arch/x86/pti.rst for more details. -config RETPOLINE +config MITIGATION_RETPOLINE bool "Avoid speculative indirect branches in kernel" select OBJTOOL if HAVE_OBJTOOL default y @@ -2505,9 +2526,9 @@ config RETPOLINE branches. Requires a compiler with -mindirect-branch=thunk-extern support for full protection. The kernel may run slower. -config RETHUNK +config MITIGATION_RETHUNK bool "Enable return-thunks" - depends on RETPOLINE && CC_HAS_RETURN_THUNK + depends on MITIGATION_RETPOLINE && CC_HAS_RETURN_THUNK select OBJTOOL if HAVE_OBJTOOL default y if X86_64 help @@ -2516,14 +2537,14 @@ config RETHUNK Requires a compiler with -mfunction-return=thunk-extern support for full protection. The kernel may run slower. -config CPU_UNRET_ENTRY +config MITIGATION_UNRET_ENTRY bool "Enable UNRET on kernel entry" - depends on CPU_SUP_AMD && RETHUNK && X86_64 + depends on CPU_SUP_AMD && MITIGATION_RETHUNK && X86_64 default y help Compile the kernel with support for the retbleed=unret mitigation. -config CALL_DEPTH_TRACKING +config MITIGATION_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 @@ -2543,7 +2564,7 @@ config CALL_DEPTH_TRACKING config CALL_THUNKS_DEBUG bool "Enable call thunks and call depth tracking debugging" - depends on CALL_DEPTH_TRACKING + depends on MITIGATION_CALL_DEPTH_TRACKING select FUNCTION_ALIGNMENT_32B default n help @@ -2554,14 +2575,14 @@ config CALL_THUNKS_DEBUG Only enable this when you are debugging call thunks as this creates a noticeable runtime overhead. If unsure say N. -config CPU_IBPB_ENTRY +config MITIGATION_IBPB_ENTRY bool "Enable IBPB on kernel entry" depends on CPU_SUP_AMD && X86_64 default y help Compile the kernel with support for the retbleed=ibpb mitigation. -config CPU_IBRS_ENTRY +config MITIGATION_IBRS_ENTRY bool "Enable IBRS on kernel entry" depends on CPU_SUP_INTEL && X86_64 default y @@ -2570,14 +2591,14 @@ config CPU_IBRS_ENTRY This mitigates both spectre_v2 and retbleed at great cost to performance. -config CPU_SRSO +config MITIGATION_SRSO bool "Mitigate speculative RAS overflow on AMD" - depends on CPU_SUP_AMD && X86_64 && RETHUNK + depends on CPU_SUP_AMD && X86_64 && MITIGATION_RETHUNK default y help Enable the SRSO mitigation needed on AMD Zen1-4 machines. -config SLS +config MITIGATION_SLS bool "Mitigate Straight-Line-Speculation" depends on CC_HAS_SLS && X86_64 select OBJTOOL if HAVE_OBJTOOL @@ -2587,7 +2608,7 @@ config SLS against straight line speculation. The kernel image might be slightly larger. -config GDS_FORCE_MITIGATION +config MITIGATION_GDS_FORCE bool "Force GDS Mitigation" depends on CPU_SUP_INTEL default n diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug index c5d614d28a..74777a97e3 100644 --- a/arch/x86/Kconfig.debug +++ b/arch/x86/Kconfig.debug @@ -248,6 +248,7 @@ config UNWINDER_ORC config UNWINDER_FRAME_POINTER bool "Frame pointer unwinder" + select ARCH_WANT_FRAME_POINTERS select FRAME_POINTER help This option enables the frame pointer unwinder for unwinding kernel @@ -271,7 +272,3 @@ config UNWINDER_GUESS overhead. endchoice - -config FRAME_POINTER - depends on !UNWINDER_ORC && !UNWINDER_GUESS - bool diff --git a/arch/x86/Makefile b/arch/x86/Makefile index da8f3caf27..5ab93fcdd6 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -22,7 +22,7 @@ RETPOLINE_VDSO_CFLAGS := -mretpoline endif RETPOLINE_CFLAGS += $(call cc-option,-mindirect-branch-cs-prefix) -ifdef CONFIG_RETHUNK +ifdef CONFIG_MITIGATION_RETHUNK RETHUNK_CFLAGS := -mfunction-return=thunk-extern RETPOLINE_CFLAGS += $(RETHUNK_CFLAGS) endif @@ -53,6 +53,9 @@ REALMODE_CFLAGS += -fno-stack-protector REALMODE_CFLAGS += -Wno-address-of-packed-member REALMODE_CFLAGS += $(cc_stack_align4) REALMODE_CFLAGS += $(CLANG_FLAGS) +ifdef CONFIG_CC_IS_CLANG +REALMODE_CFLAGS += -Wno-gnu +endif export REALMODE_CFLAGS # BITS is used as extension for files which are available in a 32 bit @@ -68,6 +71,7 @@ export BITS # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53383 # KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx +KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2 ifeq ($(CONFIG_X86_KERNEL_IBT),y) @@ -192,7 +196,7 @@ KBUILD_CFLAGS += -Wno-sign-compare KBUILD_CFLAGS += -fno-asynchronous-unwind-tables # Avoid indirect branches in kernel to deal with Spectre -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE KBUILD_CFLAGS += $(RETPOLINE_CFLAGS) # Additionally, avoid generating expensive indirect jumps which # are subject to retpolines for small number of switch cases. @@ -205,7 +209,7 @@ ifdef CONFIG_RETPOLINE endif endif -ifdef CONFIG_SLS +ifdef CONFIG_MITIGATION_SLS KBUILD_CFLAGS += -mharden-sls=all endif @@ -217,12 +221,6 @@ endif KBUILD_LDFLAGS += -m elf_$(UTS_MACHINE) -ifdef CONFIG_LTO_CLANG -ifeq ($(call test-lt, $(CONFIG_LLD_VERSION), 130000),y) -KBUILD_LDFLAGS += -plugin-opt=-stack-alignment=$(if $(CONFIG_X86_32),4,8) -endif -endif - ifdef CONFIG_X86_NEED_RELOCS LDFLAGS_vmlinux := --emit-relocs --discard-none else @@ -253,8 +251,6 @@ archheaders: libs-y += arch/x86/lib/ -core-y += arch/x86/virt/ - # drivers-y are linked after core-y drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/ drivers-$(CONFIG_PCI) += arch/x86/pci/ @@ -296,12 +292,11 @@ install: vdso-install-$(CONFIG_X86_64) += arch/x86/entry/vdso/vdso64.so.dbg vdso-install-$(CONFIG_X86_X32_ABI) += arch/x86/entry/vdso/vdsox32.so.dbg -vdso-install-$(CONFIG_X86_32) += arch/x86/entry/vdso/vdso32.so.dbg -vdso-install-$(CONFIG_IA32_EMULATION) += arch/x86/entry/vdso/vdso32.so.dbg +vdso-install-$(CONFIG_COMPAT_32) += arch/x86/entry/vdso/vdso32.so.dbg archprepare: checkbin checkbin: -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE ifeq ($(RETPOLINE_CFLAGS),) @echo "You are building kernel with non-retpoline compiler." >&2 @echo "Please update your compiler." >&2 diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index e9522c6893..8da3466775 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -116,9 +116,9 @@ vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_mixed.o -vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a +vmlinux-libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a -$(obj)/vmlinux: $(vmlinux-objs-y) FORCE +$(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE $(call if_changed,ld) OBJCOPYFLAGS_vmlinux.bin := -R .comment -S diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 18d15d1ce8..f196b1d1dd 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -5,6 +5,8 @@ #include "../string.h" #include "efi.h" +#include <asm/bootparam.h> + #include <linux/numa.h> /* diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index c1bb180973..e162d7f59c 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 #include "misc.h" +#include <asm/bootparam.h> + static unsigned long fs; static inline void set_fs(unsigned long seg) { diff --git a/arch/x86/boot/compressed/efi.c b/arch/x86/boot/compressed/efi.c index 6edd034b0b..f2e50f9758 100644 --- a/arch/x86/boot/compressed/efi.c +++ b/arch/x86/boot/compressed/efi.c @@ -7,6 +7,8 @@ #include "misc.h" +#include <asm/bootparam.h> + /** * efi_get_type - Given a pointer to boot_params, determine the type of EFI environment. * diff --git a/arch/x86/boot/compressed/efi.h b/arch/x86/boot/compressed/efi.h index 866c0af8b5..b22300970f 100644 --- a/arch/x86/boot/compressed/efi.h +++ b/arch/x86/boot/compressed/efi.h @@ -97,15 +97,6 @@ typedef struct { u32 tables; } efi_system_table_32_t; -/* kexec external ABI */ -struct efi_setup_data { - u64 fw_vendor; - u64 __unused; - u64 tables; - u64 smbios; - u64 reserved[8]; -}; - struct efi_unaccepted_memory { u32 version; u32 unit_size; diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index d040080d7e..dfb9c2deb7 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -8,8 +8,8 @@ * Copyright (C) 2016 Kees Cook */ -/* No PAGE_TABLE_ISOLATION support needed either: */ -#undef CONFIG_PAGE_TABLE_ISOLATION +/* No MITIGATION_PAGE_TABLE_ISOLATION support needed either: */ +#undef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION #include "error.h" #include "misc.h" @@ -284,7 +284,7 @@ static int set_clr_page_flags(struct x86_mapping_info *info, pudp = pud_offset(p4dp, address); pmdp = pmd_offset(pudp, address); - if (pmd_large(*pmdp)) + if (pmd_leaf(*pmdp)) ptep = split_large_pmd(info, pmdp, address); else ptep = pte_offset_kernel(pmdp, address); @@ -389,5 +389,5 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code) { - /* Empty handler to ignore NMI during early boot */ + spurious_nmi_count++; } diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index ee0fac468e..b70e4a21c1 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -52,6 +52,7 @@ struct port_io_ops pio_ops; memptr free_mem_ptr; memptr free_mem_end_ptr; +int spurious_nmi_count; static char *vidmem; static int vidport; @@ -164,21 +165,34 @@ void __putstr(const char *s) outb(0xff & (pos >> 1), vidport+1); } -void __puthex(unsigned long value) +static noinline void __putnum(unsigned long value, unsigned int base, + int mindig) { - char alpha[2] = "0"; - int bits; + char buf[8*sizeof(value)+1]; + char *p; - for (bits = sizeof(value) * 8 - 4; bits >= 0; bits -= 4) { - unsigned long digit = (value >> bits) & 0xf; + p = buf + sizeof(buf); + *--p = '\0'; - if (digit < 0xA) - alpha[0] = '0' + digit; - else - alpha[0] = 'a' + (digit - 0xA); + while (mindig-- > 0 || value) { + unsigned char digit = value % base; + digit += (digit >= 10) ? ('a'-10) : '0'; + *--p = digit; - __putstr(alpha); + value /= base; } + + __putstr(p); +} + +void __puthex(unsigned long value) +{ + __putnum(value, 16, sizeof(value)*2); +} + +void __putdec(unsigned long value) +{ + __putnum(value, 10, 1); } #ifdef CONFIG_X86_NEED_RELOCS @@ -509,10 +523,16 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) /* Disable exception handling before booting the kernel */ cleanup_exception_handling(); + if (spurious_nmi_count) { + error_putstr("Spurious early NMIs ignored: "); + error_putdec(spurious_nmi_count); + error_putstr("\n"); + } + return output + entry_offset; } -void fortify_panic(const char *name) +void __fortify_panic(const u8 reason, size_t avail, size_t size) { error("detected buffer overflow"); } diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index bc2f0f17fb..b353a7be38 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -59,12 +59,15 @@ extern char _head[], _end[]; /* misc.c */ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; +extern int spurious_nmi_count; void *malloc(int size); void free(void *where); void __putstr(const char *s); void __puthex(unsigned long value); +void __putdec(unsigned long value); #define error_putstr(__x) __putstr(__x) #define error_puthex(__x) __puthex(__x) +#define error_putdec(__x) __putdec(__x) #ifdef CONFIG_X86_VERBOSE_BOOTUP diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 51f957b24b..c882e1f67a 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include "misc.h" +#include <asm/bootparam.h> #include <asm/e820/types.h> #include <asm/processor.h> #include "pgtable.h" diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 4c9b752814..ec71846d28 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -12,6 +12,7 @@ */ #include "misc.h" +#include <asm/bootparam.h> #include <asm/pgtable_types.h> #include <asm/sev.h> #include <asm/trapnr.h> @@ -307,6 +308,10 @@ void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code) if (result != ES_OK) goto finish; + result = vc_check_opcode_bytes(&ctxt, exit_code); + if (result != ES_OK) + goto finish; + switch (exit_code) { case SVM_EXIT_RDTSC: case SVM_EXIT_RDTSCP: @@ -368,7 +373,7 @@ static void enforce_vmpl0(void) MSR_AMD64_SNP_VMPL_SSS | \ MSR_AMD64_SNP_SECURE_TSC | \ MSR_AMD64_SNP_VMGEXIT_PARAM | \ - MSR_AMD64_SNP_VMSA_REG_PROTECTION | \ + MSR_AMD64_SNP_VMSA_REG_PROT | \ MSR_AMD64_SNP_RESERVED_BIT13 | \ MSR_AMD64_SNP_RESERVED_BIT15 | \ MSR_AMD64_SNP_RESERVED_MASK) diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index a1bbedd989..b5c79f4335 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -111,11 +111,7 @@ extra_header_fields: .long salign # SizeOfHeaders .long 0 # CheckSum .word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application) -#ifdef CONFIG_EFI_DXE_MEM_ATTRIBUTES .word IMAGE_DLL_CHARACTERISTICS_NX_COMPAT # DllCharacteristics -#else - .word 0 # DllCharacteristics -#endif #ifdef CONFIG_X86_32 .long 0 # SizeOfStackReserve .long 0 # SizeOfStackCommit diff --git a/arch/x86/boot/main.c b/arch/x86/boot/main.c index c4ea5258ab..9049f390d8 100644 --- a/arch/x86/boot/main.c +++ b/arch/x86/boot/main.c @@ -119,8 +119,8 @@ static void init_heap(void) char *stack_end; if (boot_params.hdr.loadflags & CAN_USE_HEAP) { - asm("leal %P1(%%esp),%0" - : "=r" (stack_end) : "i" (-STACK_SIZE)); + asm("leal %n1(%%esp),%0" + : "=r" (stack_end) : "i" (STACK_SIZE)); heap_end = (char *) ((size_t)boot_params.hdr.heap_end_ptr + 0x200); diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index ddd4efdc79..b31ef2424d 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -20,6 +20,11 @@ enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE; u64 cc_mask __ro_after_init; +static struct cc_attr_flags { + __u64 host_sev_snp : 1, + __resv : 63; +} cc_flags; + static bool noinstr intel_cc_platform_has(enum cc_attr attr) { switch (attr) { @@ -93,6 +98,9 @@ static bool noinstr amd_cc_platform_has(enum cc_attr attr) case CC_ATTR_GUEST_SEV_SNP: return sev_status & MSR_AMD64_SEV_SNP_ENABLED; + case CC_ATTR_HOST_SEV_SNP: + return cc_flags.host_sev_snp; + default: return false; } @@ -153,6 +161,50 @@ u64 cc_mkdec(u64 val) } EXPORT_SYMBOL_GPL(cc_mkdec); +static void amd_cc_platform_clear(enum cc_attr attr) +{ + switch (attr) { + case CC_ATTR_HOST_SEV_SNP: + cc_flags.host_sev_snp = 0; + break; + default: + break; + } +} + +void cc_platform_clear(enum cc_attr attr) +{ + switch (cc_vendor) { + case CC_VENDOR_AMD: + amd_cc_platform_clear(attr); + break; + default: + break; + } +} + +static void amd_cc_platform_set(enum cc_attr attr) +{ + switch (attr) { + case CC_ATTR_HOST_SEV_SNP: + cc_flags.host_sev_snp = 1; + break; + default: + break; + } +} + +void cc_platform_set(enum cc_attr attr) +{ + switch (cc_vendor) { + case CC_VENDOR_AMD: + amd_cc_platform_set(attr); + break; + default: + break; + } +} + __init void cc_random_init(void) { /* diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 73abbbdd26..91801138b1 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -42,7 +42,7 @@ CONFIG_EFI_STUB=y CONFIG_HZ_1000=y CONFIG_KEXEC=y CONFIG_CRASH_DUMP=y -# CONFIG_RETHUNK is not set +# CONFIG_MITIGATION_RETHUNK is not set CONFIG_HIBERNATION=y CONFIG_PM_DEBUG=y CONFIG_PM_TRACE_RTC=y diff --git a/arch/x86/configs/tiny.config b/arch/x86/configs/tiny.config index 66c9e2aab1..be3ee42949 100644 --- a/arch/x86/configs/tiny.config +++ b/arch/x86/configs/tiny.config @@ -1,5 +1,6 @@ CONFIG_NOHIGHMEM=y # CONFIG_HIGHMEM4G is not set # CONFIG_HIGHMEM64G is not set +# CONFIG_UNWINDER_ORC is not set CONFIG_UNWINDER_GUESS=y # CONFIG_UNWINDER_FRAME_POINTER is not set diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile index ca2fe18699..c93e7f5c2a 100644 --- a/arch/x86/entry/Makefile +++ b/arch/x86/entry/Makefile @@ -18,6 +18,9 @@ obj-y += vdso/ obj-y += vsyscall/ obj-$(CONFIG_PREEMPTION) += thunk_$(BITS).o +CFLAGS_entry_fred.o += -fno-stack-protector +CFLAGS_REMOVE_entry_fred.o += -pg $(CC_FLAGS_FTRACE) +obj-$(CONFIG_X86_FRED) += entry_64_fred.o entry_fred.o + obj-$(CONFIG_IA32_EMULATION) += entry_64_compat.o syscall_32.o obj-$(CONFIG_X86_X32_ABI) += syscall_x32.o - diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index 9f1d94790a..ea81770629 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -65,7 +65,7 @@ For 32-bit we have the following conventions - kernel is built with * for assembly code: */ -.macro PUSH_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 +.macro PUSH_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 unwind_hint=1 .if \save_ret pushq %rsi /* pt_regs->si */ movq 8(%rsp), %rsi /* temporarily store the return address in %rsi */ @@ -87,14 +87,17 @@ For 32-bit we have the following conventions - kernel is built with pushq %r13 /* pt_regs->r13 */ pushq %r14 /* pt_regs->r14 */ pushq %r15 /* pt_regs->r15 */ + + .if \unwind_hint UNWIND_HINT_REGS + .endif .if \save_ret pushq %rsi /* return address on top of stack */ .endif .endm -.macro CLEAR_REGS +.macro CLEAR_REGS clear_bp=1 /* * Sanitize registers of values that a speculation attack might * otherwise want to exploit. The lower registers are likely clobbered @@ -109,7 +112,9 @@ For 32-bit we have the following conventions - kernel is built with xorl %r10d, %r10d /* nospec r10 */ xorl %r11d, %r11d /* nospec r11 */ xorl %ebx, %ebx /* nospec rbx */ + .if \clear_bp xorl %ebp, %ebp /* nospec rbp */ + .endif xorl %r12d, %r12d /* nospec r12 */ xorl %r13d, %r13d /* nospec r13 */ xorl %r14d, %r14d /* nospec r14 */ @@ -117,9 +122,9 @@ For 32-bit we have the following conventions - kernel is built with .endm -.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 - PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret - CLEAR_REGS +.macro PUSH_AND_CLEAR_REGS rdx=%rdx rcx=%rcx rax=%rax save_ret=0 clear_bp=1 unwind_hint=1 + PUSH_REGS rdx=\rdx, rcx=\rcx, rax=\rax, save_ret=\save_ret unwind_hint=\unwind_hint + CLEAR_REGS clear_bp=\clear_bp .endm .macro POP_REGS pop_rdi=1 @@ -142,10 +147,10 @@ For 32-bit we have the following conventions - kernel is built with .endif .endm -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* - * PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two + * MITIGATION_PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two * halves: */ #define PTI_USER_PGTABLE_BIT PAGE_SHIFT @@ -160,7 +165,7 @@ For 32-bit we have the following conventions - kernel is built with .macro ADJUST_KERNEL_CR3 reg:req ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID - /* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */ + /* Clear PCID and "MITIGATION_PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */ andq $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg .endm @@ -173,7 +178,7 @@ For 32-bit we have the following conventions - kernel is built with .endm #define THIS_CPU_user_pcid_flush_mask \ - PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask + PER_CPU_VAR(cpu_tlbstate + TLB_STATE_user_pcid_flush_mask) .macro SWITCH_TO_USER_CR3 scratch_reg:req scratch_reg2:req mov %cr3, \scratch_reg @@ -239,17 +244,19 @@ For 32-bit we have the following conventions - kernel is built with .Ldone_\@: .endm -.macro RESTORE_CR3 scratch_reg:req save_reg:req +/* Restore CR3 from a kernel context. May restore a user CR3 value. */ +.macro PARANOID_RESTORE_CR3 scratch_reg:req save_reg:req ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI - ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID - /* - * KERNEL pages can always resume with NOFLUSH as we do - * explicit flushes. + * If CR3 contained the kernel page tables at the paranoid exception + * entry, then there is nothing to restore as CR3 is not modified while + * handling the exception. */ bt $PTI_USER_PGTABLE_BIT, \save_reg - jnc .Lnoflush_\@ + jnc .Lend_\@ + + ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID /* * Check if there's a pending flush for the user ASID we're @@ -257,25 +264,17 @@ For 32-bit we have the following conventions - kernel is built with */ movq \save_reg, \scratch_reg andq $(0x7FF), \scratch_reg - bt \scratch_reg, THIS_CPU_user_pcid_flush_mask - jnc .Lnoflush_\@ - btr \scratch_reg, THIS_CPU_user_pcid_flush_mask - jmp .Lwrcr3_\@ + jc .Lwrcr3_\@ -.Lnoflush_\@: SET_NOFLUSH_BIT \save_reg .Lwrcr3_\@: - /* - * The CR3 write could be avoided when not changing its value, - * but would require a CR3 read *and* a scratch register. - */ movq \save_reg, %cr3 .Lend_\@: .endm -#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */ +#else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION=n: */ .macro SWITCH_TO_KERNEL_CR3 scratch_reg:req .endm @@ -285,7 +284,7 @@ For 32-bit we have the following conventions - kernel is built with .endm .macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req .endm -.macro RESTORE_CR3 scratch_reg:req save_reg:req +.macro PARANOID_RESTORE_CR3 scratch_reg:req save_reg:req .endm #endif @@ -303,7 +302,7 @@ For 32-bit we have the following conventions - kernel is built with * Assumes x86_spec_ctrl_{base,current} to have SPEC_CTRL_IBRS set. */ .macro IBRS_ENTER save_reg -#ifdef CONFIG_CPU_IBRS_ENTRY +#ifdef CONFIG_MITIGATION_IBRS_ENTRY ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS movl $MSR_IA32_SPEC_CTRL, %ecx @@ -332,7 +331,7 @@ For 32-bit we have the following conventions - kernel is built with * regs. Must be called after the last RET. */ .macro IBRS_EXIT save_reg -#ifdef CONFIG_CPU_IBRS_ENTRY +#ifdef CONFIG_MITIGATION_IBRS_ENTRY ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS movl $MSR_IA32_SPEC_CTRL, %ecx @@ -426,3 +425,63 @@ For 32-bit we have the following conventions - kernel is built with .endm #endif /* CONFIG_SMP */ + +#ifdef CONFIG_X86_64 + +/* rdi: arg1 ... normal C conventions. rax is saved/restored. */ +.macro THUNK name, func +SYM_FUNC_START(\name) + pushq %rbp + movq %rsp, %rbp + + pushq %rdi + pushq %rsi + pushq %rdx + pushq %rcx + pushq %rax + pushq %r8 + pushq %r9 + pushq %r10 + pushq %r11 + + call \func + + popq %r11 + popq %r10 + popq %r9 + popq %r8 + popq %rax + popq %rcx + popq %rdx + popq %rsi + popq %rdi + popq %rbp + RET +SYM_FUNC_END(\name) + _ASM_NOKPROBE(\name) +.endm + +#else /* CONFIG_X86_32 */ + +/* put return address in eax (arg1) */ +.macro THUNK name, func, put_ret_addr_in_eax=0 +SYM_CODE_START_NOALIGN(\name) + pushl %eax + pushl %ecx + pushl %edx + + .if \put_ret_addr_in_eax + /* Place EIP in the arg1 */ + movl 3*4(%esp), %eax + .endif + + call \func + popl %edx + popl %ecx + popl %eax + RET + _ASM_NOKPROBE(\name) +SYM_CODE_END(\name) + .endm + +#endif diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 6de50b8070..51cc9c7cb9 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -255,6 +255,71 @@ __visible noinstr void do_int80_emulation(struct pt_regs *regs) instrumentation_end(); syscall_exit_to_user_mode(regs); } + +#ifdef CONFIG_X86_FRED +/* + * A FRED-specific INT80 handler is warranted for the follwing reasons: + * + * 1) As INT instructions and hardware interrupts are separate event + * types, FRED does not preclude the use of vector 0x80 for external + * interrupts. As a result, the FRED setup code does not reserve + * vector 0x80 and calling int80_is_external() is not merely + * suboptimal but actively incorrect: it could cause a system call + * to be incorrectly ignored. + * + * 2) It is called only for handling vector 0x80 of event type + * EVENT_TYPE_SWINT and will never be called to handle any external + * interrupt (event type EVENT_TYPE_EXTINT). + * + * 3) FRED has separate entry flows depending on if the event came from + * user space or kernel space, and because the kernel does not use + * INT insns, the FRED kernel entry handler fred_entry_from_kernel() + * falls through to fred_bad_type() if the event type is + * EVENT_TYPE_SWINT, i.e., INT insns. So if the kernel is handling + * an INT insn, it can only be from a user level. + * + * 4) int80_emulation() does a CLEAR_BRANCH_HISTORY. While FRED will + * likely take a different approach if it is ever needed: it + * probably belongs in either fred_intx()/ fred_other() or + * asm_fred_entrypoint_user(), depending on if this ought to be done + * for all entries from userspace or only system + * calls. + * + * 5) INT $0x80 is the fast path for 32-bit system calls under FRED. + */ +DEFINE_FREDENTRY_RAW(int80_emulation) +{ + int nr; + + enter_from_user_mode(regs); + + instrumentation_begin(); + add_random_kstack_offset(); + + /* + * FRED pushed 0 into regs::orig_ax and regs::ax contains the + * syscall number. + * + * User tracing code (ptrace or signal handlers) might assume + * that the regs::orig_ax contains a 32-bit number on invoking + * a 32-bit syscall. + * + * Establish the syscall convention by saving the 32bit truncated + * syscall number in regs::orig_ax and by invalidating regs::ax. + */ + regs->orig_ax = regs->ax & GENMASK(31, 0); + regs->ax = -ENOSYS; + + nr = syscall_32_enter(regs); + + local_irq_enable(); + nr = syscall_enter_from_user_mode_work(regs, nr); + do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); + syscall_exit_to_user_mode(regs); +} +#endif #else /* CONFIG_IA32_EMULATION */ /* Handles int $0x80 on a 32bit kernel */ diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index 0033790499..d9feadffa9 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -10,6 +10,8 @@ #include <asm/segment.h> #include <asm/cache.h> +#include "calling.h" + .pushsection .noinstr.text, "ax" SYM_FUNC_START(entry_ibpb) @@ -43,3 +45,4 @@ EXPORT_SYMBOL_GPL(mds_verw_sel); .popsection +THUNK warn_thunk_thunk, __warn_thunk diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index fba4276468..d3a814efbf 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -305,7 +305,7 @@ .macro CHECK_AND_APPLY_ESPFIX #ifdef CONFIG_X86_ESPFIX32 #define GDT_ESPFIX_OFFSET (GDT_ENTRY_ESPFIX_SS * 8) -#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + GDT_ESPFIX_OFFSET +#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page + GDT_ESPFIX_OFFSET) ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_ESPFIX @@ -649,10 +649,6 @@ SYM_CODE_START_LOCAL(asm_\cfunc) SYM_CODE_END(asm_\cfunc) .endm -.macro idtentry_sysvec vector cfunc - idtentry \vector asm_\cfunc \cfunc has_error_code=0 -.endm - /* * Include the defines which emit the idt entries which are shared * shared between 32 and 64 bit and emit the __irqentry_text_* markers diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index e986331b14..1b5be07f86 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -192,7 +192,7 @@ SYM_FUNC_START(__switch_to_asm) #ifdef CONFIG_STACKPROTECTOR movq TASK_stack_canary(%rsi), %rbx - movq %rbx, PER_CPU_VAR(fixed_percpu_data) + FIXED_stack_canary + movq %rbx, PER_CPU_VAR(fixed_percpu_data + FIXED_stack_canary) #endif /* @@ -249,7 +249,13 @@ SYM_CODE_START(ret_from_fork_asm) * and unwind should work normally. */ UNWIND_HINT_REGS + +#ifdef CONFIG_X86_FRED + ALTERNATIVE "jmp swapgs_restore_regs_and_return_to_usermode", \ + "jmp asm_fred_exit_user", X86_FEATURE_FRED +#else jmp swapgs_restore_regs_and_return_to_usermode +#endif SYM_CODE_END(ret_from_fork_asm) .popsection @@ -372,14 +378,6 @@ SYM_CODE_END(\asmsym) idtentry \vector asm_\cfunc \cfunc has_error_code=1 .endm -/* - * System vectors which invoke their handlers directly and are not - * going through the regular common device interrupt handling code. - */ -.macro idtentry_sysvec vector cfunc - idtentry \vector asm_\cfunc \cfunc has_error_code=0 -.endm - /** * idtentry_mce_db - Macro to generate entry stubs for #MC and #DB * @vector: Vector number @@ -564,7 +562,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) #ifdef CONFIG_XEN_PV ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV #endif -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION ALTERNATIVE "", "jmp .Lpti_restore_regs_and_return_to_usermode", X86_FEATURE_PTI #endif @@ -581,7 +579,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) jnz .Lnative_iret ud2 -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION .Lpti_restore_regs_and_return_to_usermode: POP_REGS pop_rdi=0 @@ -973,14 +971,14 @@ SYM_CODE_START_LOCAL(paranoid_exit) IBRS_EXIT save_reg=%r15 /* - * The order of operations is important. RESTORE_CR3 requires + * The order of operations is important. PARANOID_RESTORE_CR3 requires * kernel GSBASE. * * NB to anyone to try to optimize this code: this code does * not execute at all for exceptions from user mode. Those * exceptions go through error_return instead. */ - RESTORE_CR3 scratch_reg=%rax save_reg=%r14 + PARANOID_RESTORE_CR3 scratch_reg=%rax save_reg=%r14 /* Handle the three GSBASE cases */ ALTERNATIVE "jmp .Lparanoid_exit_checkgs", "", X86_FEATURE_FSGSBASE @@ -1101,7 +1099,7 @@ SYM_CODE_END(error_return) * * Registers: * %r14: Used to save/restore the CR3 of the interrupted context - * when PAGE_TABLE_ISOLATION is in use. Do not clobber. + * when MITIGATION_PAGE_TABLE_ISOLATION is in use. Do not clobber. */ SYM_CODE_START(asm_exc_nmi) UNWIND_HINT_IRET_ENTRY @@ -1409,8 +1407,7 @@ end_repeat_nmi: /* Always restore stashed SPEC_CTRL value (see paranoid_entry) */ IBRS_EXIT save_reg=%r15 - /* Always restore stashed CR3 value (see paranoid_entry) */ - RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 + PARANOID_RESTORE_CR3 scratch_reg=%r15 save_reg=%r14 /* * The above invocation of paranoid_entry stored the GSBASE diff --git a/arch/x86/entry/entry_64_fred.S b/arch/x86/entry/entry_64_fred.S new file mode 100644 index 0000000000..a02bc6f3d2 --- /dev/null +++ b/arch/x86/entry/entry_64_fred.S @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * The actual FRED entry points. + */ + +#include <linux/export.h> + +#include <asm/asm.h> +#include <asm/fred.h> +#include <asm/segment.h> + +#include "calling.h" + + .code64 + .section .noinstr.text, "ax" + +.macro FRED_ENTER + UNWIND_HINT_END_OF_STACK + ENDBR + PUSH_AND_CLEAR_REGS + movq %rsp, %rdi /* %rdi -> pt_regs */ +.endm + +.macro FRED_EXIT + UNWIND_HINT_REGS + POP_REGS +.endm + +/* + * The new RIP value that FRED event delivery establishes is + * IA32_FRED_CONFIG & ~FFFH for events that occur in ring 3. + * Thus the FRED ring 3 entry point must be 4K page aligned. + */ + .align 4096 + +SYM_CODE_START_NOALIGN(asm_fred_entrypoint_user) + FRED_ENTER + call fred_entry_from_user +SYM_INNER_LABEL(asm_fred_exit_user, SYM_L_GLOBAL) + FRED_EXIT +1: ERETU + + _ASM_EXTABLE_TYPE(1b, asm_fred_entrypoint_user, EX_TYPE_ERETU) +SYM_CODE_END(asm_fred_entrypoint_user) + +/* + * The new RIP value that FRED event delivery establishes is + * (IA32_FRED_CONFIG & ~FFFH) + 256 for events that occur in + * ring 0, i.e., asm_fred_entrypoint_user + 256. + */ + .org asm_fred_entrypoint_user + 256, 0xcc +SYM_CODE_START_NOALIGN(asm_fred_entrypoint_kernel) + FRED_ENTER + call fred_entry_from_kernel + FRED_EXIT + ERETS +SYM_CODE_END(asm_fred_entrypoint_kernel) + +#if IS_ENABLED(CONFIG_KVM_INTEL) +SYM_FUNC_START(asm_fred_entry_from_kvm) + push %rbp + mov %rsp, %rbp + + UNWIND_HINT_SAVE + + /* + * Both IRQ and NMI from VMX can be handled on current task stack + * because there is no need to protect from reentrancy and the call + * stack leading to this helper is effectively constant and shallow + * (relatively speaking). Do the same when FRED is active, i.e., no + * need to check current stack level for a stack switch. + * + * Emulate the FRED-defined redzone and stack alignment. + */ + sub $(FRED_CONFIG_REDZONE_AMOUNT << 6), %rsp + and $FRED_STACK_FRAME_RSP_MASK, %rsp + + /* + * Start to push a FRED stack frame, which is always 64 bytes: + * + * +--------+-----------------+ + * | Bytes | Usage | + * +--------+-----------------+ + * | 63:56 | Reserved | + * | 55:48 | Event Data | + * | 47:40 | SS + Event Info | + * | 39:32 | RSP | + * | 31:24 | RFLAGS | + * | 23:16 | CS + Aux Info | + * | 15:8 | RIP | + * | 7:0 | Error Code | + * +--------+-----------------+ + */ + push $0 /* Reserved, must be 0 */ + push $0 /* Event data, 0 for IRQ/NMI */ + push %rdi /* fred_ss handed in by the caller */ + push %rbp + pushf + mov $__KERNEL_CS, %rax + push %rax + + /* + * Unlike the IDT event delivery, FRED _always_ pushes an error code + * after pushing the return RIP, thus the CALL instruction CANNOT be + * used here to push the return RIP, otherwise there is no chance to + * push an error code before invoking the IRQ/NMI handler. + * + * Use LEA to get the return RIP and push it, then push an error code. + */ + lea 1f(%rip), %rax + push %rax /* Return RIP */ + push $0 /* Error code, 0 for IRQ/NMI */ + + PUSH_AND_CLEAR_REGS clear_bp=0 unwind_hint=0 + movq %rsp, %rdi /* %rdi -> pt_regs */ + call __fred_entry_from_kvm /* Call the C entry point */ + POP_REGS + ERETS +1: + /* + * Objtool doesn't understand what ERETS does, this hint tells it that + * yes, we'll reach here and with what stack state. A save/restore pair + * isn't strictly needed, but it's the simplest form. + */ + UNWIND_HINT_RESTORE + pop %rbp + RET + +SYM_FUNC_END(asm_fred_entry_from_kvm) +EXPORT_SYMBOL_GPL(asm_fred_entry_from_kvm); +#endif diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c new file mode 100644 index 0000000000..89c1476fcd --- /dev/null +++ b/arch/x86/entry/entry_fred.c @@ -0,0 +1,294 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * The FRED specific kernel/user entry functions which are invoked from + * assembly code and dispatch to the associated handlers. + */ +#include <linux/kernel.h> +#include <linux/kdebug.h> +#include <linux/nospec.h> + +#include <asm/desc.h> +#include <asm/fred.h> +#include <asm/idtentry.h> +#include <asm/syscall.h> +#include <asm/trapnr.h> +#include <asm/traps.h> + +/* FRED EVENT_TYPE_OTHER vector numbers */ +#define FRED_SYSCALL 1 +#define FRED_SYSENTER 2 + +static noinstr void fred_bad_type(struct pt_regs *regs, unsigned long error_code) +{ + irqentry_state_t irq_state = irqentry_nmi_enter(regs); + + instrumentation_begin(); + + /* Panic on events from a high stack level */ + if (regs->fred_cs.sl > 0) { + pr_emerg("PANIC: invalid or fatal FRED event; event type %u " + "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n", + regs->fred_ss.type, regs->fred_ss.vector, error_code, + fred_event_data(regs), regs->cs, regs->ip); + die("invalid or fatal FRED event", regs, error_code); + panic("invalid or fatal FRED event"); + } else { + unsigned long flags = oops_begin(); + int sig = SIGKILL; + + pr_alert("BUG: invalid or fatal FRED event; event type %u " + "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n", + regs->fred_ss.type, regs->fred_ss.vector, error_code, + fred_event_data(regs), regs->cs, regs->ip); + + if (__die("Invalid or fatal FRED event", regs, error_code)) + sig = 0; + + oops_end(flags, regs, sig); + } + + instrumentation_end(); + irqentry_nmi_exit(regs, irq_state); +} + +static noinstr void fred_intx(struct pt_regs *regs) +{ + switch (regs->fred_ss.vector) { + /* Opcode 0xcd, 0x3, NOT INT3 (opcode 0xcc) */ + case X86_TRAP_BP: + return exc_int3(regs); + + /* Opcode 0xcd, 0x4, NOT INTO (opcode 0xce) */ + case X86_TRAP_OF: + return exc_overflow(regs); + +#ifdef CONFIG_IA32_EMULATION + /* INT80 */ + case IA32_SYSCALL_VECTOR: + if (ia32_enabled()) + return fred_int80_emulation(regs); + fallthrough; +#endif + + default: + return exc_general_protection(regs, 0); + } +} + +static __always_inline void fred_other(struct pt_regs *regs) +{ + /* The compiler can fold these conditions into a single test */ + if (likely(regs->fred_ss.vector == FRED_SYSCALL && regs->fred_ss.lm)) { + regs->orig_ax = regs->ax; + regs->ax = -ENOSYS; + do_syscall_64(regs, regs->orig_ax); + return; + } else if (ia32_enabled() && + likely(regs->fred_ss.vector == FRED_SYSENTER && !regs->fred_ss.lm)) { + regs->orig_ax = regs->ax; + regs->ax = -ENOSYS; + do_fast_syscall_32(regs); + return; + } else { + exc_invalid_op(regs); + return; + } +} + +#define SYSVEC(_vector, _function) [_vector - FIRST_SYSTEM_VECTOR] = fred_sysvec_##_function + +static idtentry_t sysvec_table[NR_SYSTEM_VECTORS] __ro_after_init = { + SYSVEC(ERROR_APIC_VECTOR, error_interrupt), + SYSVEC(SPURIOUS_APIC_VECTOR, spurious_apic_interrupt), + SYSVEC(LOCAL_TIMER_VECTOR, apic_timer_interrupt), + SYSVEC(X86_PLATFORM_IPI_VECTOR, x86_platform_ipi), + + SYSVEC(RESCHEDULE_VECTOR, reschedule_ipi), + SYSVEC(CALL_FUNCTION_SINGLE_VECTOR, call_function_single), + SYSVEC(CALL_FUNCTION_VECTOR, call_function), + SYSVEC(REBOOT_VECTOR, reboot), + + SYSVEC(THRESHOLD_APIC_VECTOR, threshold), + SYSVEC(DEFERRED_ERROR_VECTOR, deferred_error), + SYSVEC(THERMAL_APIC_VECTOR, thermal), + + SYSVEC(IRQ_WORK_VECTOR, irq_work), + + SYSVEC(POSTED_INTR_VECTOR, kvm_posted_intr_ipi), + SYSVEC(POSTED_INTR_WAKEUP_VECTOR, kvm_posted_intr_wakeup_ipi), + SYSVEC(POSTED_INTR_NESTED_VECTOR, kvm_posted_intr_nested_ipi), +}; + +static bool fred_setup_done __initdata; + +void __init fred_install_sysvec(unsigned int sysvec, idtentry_t handler) +{ + if (WARN_ON_ONCE(sysvec < FIRST_SYSTEM_VECTOR)) + return; + + if (WARN_ON_ONCE(fred_setup_done)) + return; + + if (!WARN_ON_ONCE(sysvec_table[sysvec - FIRST_SYSTEM_VECTOR])) + sysvec_table[sysvec - FIRST_SYSTEM_VECTOR] = handler; +} + +static noinstr void fred_handle_spurious_interrupt(struct pt_regs *regs) +{ + spurious_interrupt(regs, regs->fred_ss.vector); +} + +void __init fred_complete_exception_setup(void) +{ + unsigned int vector; + + for (vector = 0; vector < FIRST_EXTERNAL_VECTOR; vector++) + set_bit(vector, system_vectors); + + for (vector = 0; vector < NR_SYSTEM_VECTORS; vector++) { + if (sysvec_table[vector]) + set_bit(vector + FIRST_SYSTEM_VECTOR, system_vectors); + else + sysvec_table[vector] = fred_handle_spurious_interrupt; + } + fred_setup_done = true; +} + +static noinstr void fred_extint(struct pt_regs *regs) +{ + unsigned int vector = regs->fred_ss.vector; + unsigned int index = array_index_nospec(vector - FIRST_SYSTEM_VECTOR, + NR_SYSTEM_VECTORS); + + if (WARN_ON_ONCE(vector < FIRST_EXTERNAL_VECTOR)) + return; + + if (likely(vector >= FIRST_SYSTEM_VECTOR)) { + irqentry_state_t state = irqentry_enter(regs); + + instrumentation_begin(); + sysvec_table[index](regs); + instrumentation_end(); + irqentry_exit(regs, state); + } else { + common_interrupt(regs, vector); + } +} + +static noinstr void fred_hwexc(struct pt_regs *regs, unsigned long error_code) +{ + /* Optimize for #PF. That's the only exception which matters performance wise */ + if (likely(regs->fred_ss.vector == X86_TRAP_PF)) + return exc_page_fault(regs, error_code); + + switch (regs->fred_ss.vector) { + case X86_TRAP_DE: return exc_divide_error(regs); + case X86_TRAP_DB: return fred_exc_debug(regs); + case X86_TRAP_BR: return exc_bounds(regs); + case X86_TRAP_UD: return exc_invalid_op(regs); + case X86_TRAP_NM: return exc_device_not_available(regs); + case X86_TRAP_DF: return exc_double_fault(regs, error_code); + case X86_TRAP_TS: return exc_invalid_tss(regs, error_code); + case X86_TRAP_NP: return exc_segment_not_present(regs, error_code); + case X86_TRAP_SS: return exc_stack_segment(regs, error_code); + case X86_TRAP_GP: return exc_general_protection(regs, error_code); + case X86_TRAP_MF: return exc_coprocessor_error(regs); + case X86_TRAP_AC: return exc_alignment_check(regs, error_code); + case X86_TRAP_XF: return exc_simd_coprocessor_error(regs); + +#ifdef CONFIG_X86_MCE + case X86_TRAP_MC: return fred_exc_machine_check(regs); +#endif +#ifdef CONFIG_INTEL_TDX_GUEST + case X86_TRAP_VE: return exc_virtualization_exception(regs); +#endif +#ifdef CONFIG_X86_CET + case X86_TRAP_CP: return exc_control_protection(regs, error_code); +#endif + default: return fred_bad_type(regs, error_code); + } + +} + +static noinstr void fred_swexc(struct pt_regs *regs, unsigned long error_code) +{ + switch (regs->fred_ss.vector) { + case X86_TRAP_BP: return exc_int3(regs); + case X86_TRAP_OF: return exc_overflow(regs); + default: return fred_bad_type(regs, error_code); + } +} + +__visible noinstr void fred_entry_from_user(struct pt_regs *regs) +{ + unsigned long error_code = regs->orig_ax; + + /* Invalidate orig_ax so that syscall_get_nr() works correctly */ + regs->orig_ax = -1; + + switch (regs->fred_ss.type) { + case EVENT_TYPE_EXTINT: + return fred_extint(regs); + case EVENT_TYPE_NMI: + if (likely(regs->fred_ss.vector == X86_TRAP_NMI)) + return fred_exc_nmi(regs); + break; + case EVENT_TYPE_HWEXC: + return fred_hwexc(regs, error_code); + case EVENT_TYPE_SWINT: + return fred_intx(regs); + case EVENT_TYPE_PRIV_SWEXC: + if (likely(regs->fred_ss.vector == X86_TRAP_DB)) + return fred_exc_debug(regs); + break; + case EVENT_TYPE_SWEXC: + return fred_swexc(regs, error_code); + case EVENT_TYPE_OTHER: + return fred_other(regs); + default: break; + } + + return fred_bad_type(regs, error_code); +} + +__visible noinstr void fred_entry_from_kernel(struct pt_regs *regs) +{ + unsigned long error_code = regs->orig_ax; + + /* Invalidate orig_ax so that syscall_get_nr() works correctly */ + regs->orig_ax = -1; + + switch (regs->fred_ss.type) { + case EVENT_TYPE_EXTINT: + return fred_extint(regs); + case EVENT_TYPE_NMI: + if (likely(regs->fred_ss.vector == X86_TRAP_NMI)) + return fred_exc_nmi(regs); + break; + case EVENT_TYPE_HWEXC: + return fred_hwexc(regs, error_code); + case EVENT_TYPE_PRIV_SWEXC: + if (likely(regs->fred_ss.vector == X86_TRAP_DB)) + return fred_exc_debug(regs); + break; + case EVENT_TYPE_SWEXC: + return fred_swexc(regs, error_code); + default: break; + } + + return fred_bad_type(regs, error_code); +} + +#if IS_ENABLED(CONFIG_KVM_INTEL) +__visible noinstr void __fred_entry_from_kvm(struct pt_regs *regs) +{ + switch (regs->fred_ss.type) { + case EVENT_TYPE_EXTINT: + return fred_extint(regs); + case EVENT_TYPE_NMI: + return fred_exc_nmi(regs); + default: + WARN_ON_ONCE(1); + } +} +#endif diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S index 0103e103a6..da37f42f45 100644 --- a/arch/x86/entry/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -4,33 +4,15 @@ * Copyright 2008 by Steven Rostedt, Red Hat, Inc * (inspired by Andi Kleen's thunk_64.S) */ - #include <linux/export.h> - #include <linux/linkage.h> - #include <asm/asm.h> - /* put return address in eax (arg1) */ - .macro THUNK name, func, put_ret_addr_in_eax=0 -SYM_CODE_START_NOALIGN(\name) - pushl %eax - pushl %ecx - pushl %edx +#include <linux/export.h> +#include <linux/linkage.h> +#include <asm/asm.h> - .if \put_ret_addr_in_eax - /* Place EIP in the arg1 */ - movl 3*4(%esp), %eax - .endif +#include "calling.h" - call \func - popl %edx - popl %ecx - popl %eax - RET - _ASM_NOKPROBE(\name) -SYM_CODE_END(\name) - .endm - - THUNK preempt_schedule_thunk, preempt_schedule - THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace - EXPORT_SYMBOL(preempt_schedule_thunk) - EXPORT_SYMBOL(preempt_schedule_notrace_thunk) +THUNK preempt_schedule_thunk, preempt_schedule +THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace +EXPORT_SYMBOL(preempt_schedule_thunk) +EXPORT_SYMBOL(preempt_schedule_notrace_thunk) diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index 416b400f39..119ebdc3d3 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -9,39 +9,6 @@ #include "calling.h" #include <asm/asm.h> - /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ - .macro THUNK name, func -SYM_FUNC_START(\name) - pushq %rbp - movq %rsp, %rbp - - pushq %rdi - pushq %rsi - pushq %rdx - pushq %rcx - pushq %rax - pushq %r8 - pushq %r9 - pushq %r10 - pushq %r11 - - call \func - - popq %r11 - popq %r10 - popq %r9 - popq %r8 - popq %rax - popq %rcx - popq %rdx - popq %rsi - popq %rdi - popq %rbp - RET -SYM_FUNC_END(\name) - _ASM_NOKPROBE(\name) - .endm - THUNK preempt_schedule_thunk, preempt_schedule THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace EXPORT_SYMBOL(preempt_schedule_thunk) diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 73ac5adb0b..3d64bcc403 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -3,13 +3,15 @@ # Building vDSO images for x86. # -# Include the generic Makefile to check the built vdso. +# Include the generic Makefile to check the built vDSO: include $(srctree)/lib/vdso/Makefile # Sanitizer runtimes are unavailable and cannot be linked here. KASAN_SANITIZE := n KMSAN_SANITIZE_vclock_gettime.o := n +KMSAN_SANITIZE_vdso32/vclock_gettime.o := n KMSAN_SANITIZE_vgetcpu.o := n +KMSAN_SANITIZE_vdso32/vgetcpu.o := n UBSAN_SANITIZE := n KCSAN_SANITIZE := n @@ -18,52 +20,40 @@ OBJECT_FILES_NON_STANDARD := y # Prevents link failures: __sanitizer_cov_trace_pc() is not linked in. KCOV_INSTRUMENT := n -VDSO64-$(CONFIG_X86_64) := y -VDSOX32-$(CONFIG_X86_X32_ABI) := y -VDSO32-$(CONFIG_X86_32) := y -VDSO32-$(CONFIG_IA32_EMULATION) := y - -# files to link into the vdso +# Files to link into the vDSO: vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o vobjs32-y := vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o vobjs32-y += vdso32/vclock_gettime.o vdso32/vgetcpu.o vobjs-$(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 +# Files to link into the 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_extable.o := n -OBJECT_FILES_NON_STANDARD_vdso-image-32.o := n -OBJECT_FILES_NON_STANDARD_vdso-image-x32.o := n -OBJECT_FILES_NON_STANDARD_vdso-image-64.o := n -OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n OBJECT_FILES_NON_STANDARD_vma.o := n +OBJECT_FILES_NON_STANDARD_extable.o := n -# vDSO images to build -vdso_img-$(VDSO64-y) += 64 -vdso_img-$(VDSOX32-y) += x32 -vdso_img-$(VDSO32-y) += 32 +# vDSO images to build: +obj-$(CONFIG_X86_64) += vdso-image-64.o +obj-$(CONFIG_X86_X32_ABI) += vdso-image-x32.o +obj-$(CONFIG_COMPAT_32) += vdso-image-32.o vdso32-setup.o -obj-$(VDSO32-y) += vdso32-setup.o +OBJECT_FILES_NON_STANDARD_vdso-image-32.o := n +OBJECT_FILES_NON_STANDARD_vdso-image-x32.o := n +OBJECT_FILES_NON_STANDARD_vdso-image-64.o := n +OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n -vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) -vobjs32 := $(foreach F,$(vobjs32-y),$(obj)/$F) +vobjs := $(addprefix $(obj)/, $(vobjs-y)) +vobjs32 := $(addprefix $(obj)/, $(vobjs32-y)) $(obj)/vdso.o: $(obj)/vdso.so targets += vdso.lds $(vobjs-y) targets += vdso32/vdso32.lds $(vobjs32-y) -# Build the vDSO image C files and link them in. -vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o) -vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c) -vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg) -obj-y += $(vdso_img_objs) -targets += $(vdso_img_cfiles) -targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so) +targets += $(foreach x, 64 x32 32, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg) CPPFLAGS_vdso.lds += -P -C @@ -91,7 +81,7 @@ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \ -fno-omit-frame-pointer -foptimize-sibling-calls \ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE ifneq ($(RETPOLINE_VDSO_CFLAGS),) CFL += $(RETPOLINE_VDSO_CFLAGS) endif @@ -127,7 +117,7 @@ VDSO_LDFLAGS_vdsox32.lds = -m elf32_x86_64 -soname linux-vdso.so.1 \ vobjx32s-y := $(vobjs-y:.o=-x32.o) # same thing, but in the output directory -vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F) +vobjx32s := $(addprefix $(obj)/, $(vobjx32s-y)) # Convert 64bit object file to x32 for x32 vDSO. quiet_cmd_x32 = X32 $@ @@ -168,7 +158,7 @@ KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls) KBUILD_CFLAGS_32 += -fno-omit-frame-pointer KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE ifneq ($(RETPOLINE_VDSO_CFLAGS),) KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS) endif @@ -194,5 +184,3 @@ GCOV_PROFILE := n quiet_cmd_vdso_and_check = VDSO $@ cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check) - -clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so* diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c index 7645730dc2..6d83ceb7f1 100644 --- a/arch/x86/entry/vdso/vma.c +++ b/arch/x86/entry/vdso/vma.c @@ -274,59 +274,6 @@ up_fail: return ret; } -#ifdef CONFIG_X86_64 -/* - * Put the vdso above the (randomized) stack with another randomized - * offset. This way there is no hole in the middle of address space. - * To save memory make sure it is still in the same PTE as the stack - * top. This doesn't give that many random bits. - * - * Note that this algorithm is imperfect: the distribution of the vdso - * start address within a PMD is biased toward the end. - * - * Only used for the 64-bit and x32 vdsos. - */ -static unsigned long vdso_addr(unsigned long start, unsigned len) -{ - unsigned long addr, end; - unsigned offset; - - /* - * Round up the start address. It can start out unaligned as a result - * of stack start randomization. - */ - start = PAGE_ALIGN(start); - - /* Round the lowest possible end address up to a PMD boundary. */ - end = (start + len + PMD_SIZE - 1) & PMD_MASK; - if (end >= DEFAULT_MAP_WINDOW) - end = DEFAULT_MAP_WINDOW; - end -= len; - - if (end > start) { - offset = get_random_u32_below(((end - start) >> PAGE_SHIFT) + 1); - addr = start + (offset << PAGE_SHIFT); - } else { - addr = start; - } - - /* - * Forcibly align the final address in case we have a hardware - * issue that requires alignment for performance reasons. - */ - addr = align_vdso_addr(addr); - - return addr; -} - -static int map_vdso_randomized(const struct vdso_image *image) -{ - unsigned long addr = vdso_addr(current->mm->start_stack, image->size-image->sym_vvar_start); - - return map_vdso(image, addr); -} -#endif - int map_vdso_once(const struct vdso_image *image, unsigned long addr) { struct mm_struct *mm = current->mm; @@ -369,7 +316,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) if (!vdso64_enabled) return 0; - return map_vdso_randomized(&vdso_image_64); + return map_vdso(&vdso_image_64, 0); } #ifdef CONFIG_COMPAT @@ -380,7 +327,7 @@ int compat_arch_setup_additional_pages(struct linux_binprm *bprm, if (x32) { if (!vdso64_enabled) return 0; - return map_vdso_randomized(&vdso_image_x32); + return map_vdso(&vdso_image_x32, 0); } #endif #ifdef CONFIG_IA32_EMULATION diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index 1245000a87..2fb7d53cf3 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -76,7 +76,7 @@ static void warn_bad_vsyscall(const char *level, struct pt_regs *regs, if (!show_unhandled_signals) return; - printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n", + printk_ratelimited("%s%s[%d] %s ip:%lx cs:%x sp:%lx ax:%lx si:%lx di:%lx\n", level, current->comm, task_pid_nr(current), message, regs->ip, regs->cs, regs->sp, regs->ax, regs->si, regs->di); diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index eb5c8539d6..985ef3b479 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -273,8 +273,23 @@ static const u64 amd_zen2_perfmon_event_map[PERF_COUNT_HW_MAX] = [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a9, }; +static const u64 amd_zen4_perfmon_event_map[PERF_COUNT_HW_MAX] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_CACHE_MISSES] = 0x0964, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a9, + [PERF_COUNT_HW_REF_CPU_CYCLES] = 0x100000120, +}; + static u64 amd_pmu_event_map(int hw_event) { + if (cpu_feature_enabled(X86_FEATURE_ZEN4) || boot_cpu_data.x86 >= 0x1a) + return amd_zen4_perfmon_event_map[hw_event]; + if (cpu_feature_enabled(X86_FEATURE_ZEN2) || boot_cpu_data.x86 >= 0x19) return amd_zen2_perfmon_event_map[hw_event]; @@ -593,7 +608,7 @@ static void amd_pmu_cpu_starting(int cpu) if (!x86_pmu.amd_nb_constraints) return; - nb_id = topology_die_id(cpu); + nb_id = topology_amd_node_id(cpu); WARN_ON_ONCE(nb_id == BAD_APICID); for_each_online_cpu(i) { @@ -918,8 +933,8 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) if (!status) goto done; - /* Read branch records before unfreezing */ - if (status & GLOBAL_STATUS_LBRS_FROZEN) { + /* Read branch records */ + if (x86_pmu.lbr_nr) { amd_pmu_lbr_read(); status &= ~GLOBAL_STATUS_LBRS_FROZEN; } diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c index 4a1e600314..5149830c7c 100644 --- a/arch/x86/events/amd/lbr.c +++ b/arch/x86/events/amd/lbr.c @@ -402,10 +402,12 @@ void amd_pmu_lbr_enable_all(void) wrmsrl(MSR_AMD64_LBR_SELECT, lbr_select); } - rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); - rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); + if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) { + rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); + wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + } - wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN); } @@ -418,10 +420,12 @@ void amd_pmu_lbr_disable_all(void) return; rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg); - rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); - wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN); - wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + + if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) { + rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl); + wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI); + } } __init int amd_pmu_lbr_init(void) diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 5bf03c5758..4ccb8fa483 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -71,7 +71,7 @@ union amd_uncore_info { }; struct amd_uncore { - union amd_uncore_info * __percpu info; + union amd_uncore_info __percpu *info; struct amd_uncore_pmu *pmus; unsigned int num_pmus; bool init_done; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 3804f21ab0..768d141489 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -17,6 +17,7 @@ #include <linux/kvm_host.h> #include <asm/cpufeature.h> +#include <asm/debugreg.h> #include <asm/hardirq.h> #include <asm/intel-family.h> #include <asm/intel_pt.h> diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 4b50a3a981..326c8cd5aa 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -834,7 +834,7 @@ static int __init cstate_init(void) } if (has_cstate_pkg) { - if (topology_max_die_per_package() > 1) { + if (topology_max_dies_per_package() > 1) { err = perf_pmu_register(&cstate_pkg_pmu, "cstate_die", -1); } else { diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 807de7b596..e010bfed84 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -5,6 +5,7 @@ #include <linux/sched/clock.h> #include <asm/cpu_entry_area.h> +#include <asm/debugreg.h> #include <asm/perf_event.h> #include <asm/tlbflush.h> #include <asm/insn.h> diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 78cd508410..4367aa77cb 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1693,6 +1693,7 @@ void x86_perf_get_lbr(struct x86_pmu_lbr *lbr) lbr->from = x86_pmu.lbr_from; lbr->to = x86_pmu.lbr_to; lbr->info = x86_pmu.lbr_info; + lbr->has_callstack = x86_pmu_has_lbr_callstack(); } EXPORT_SYMBOL_GPL(x86_perf_get_lbr); diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 7927c0b832..258e2cdf28 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1893,7 +1893,7 @@ static int __init intel_uncore_init(void) return -ENODEV; __uncore_max_dies = - topology_max_packages() * topology_max_die_per_package(); + topology_max_packages() * topology_max_dies_per_package(); id = x86_match_cpu(intel_uncore_match); if (!id) { diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c index 56eea2c66c..92da8aaa59 100644 --- a/arch/x86/events/intel/uncore_nhmex.c +++ b/arch/x86/events/intel/uncore_nhmex.c @@ -1221,8 +1221,8 @@ void nhmex_uncore_cpu_init(void) uncore_nhmex = true; else nhmex_uncore_mbox.event_descs = wsmex_uncore_mbox_events; - if (nhmex_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - nhmex_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (nhmex_uncore_cbox.num_boxes > topology_num_cores_per_package()) + nhmex_uncore_cbox.num_boxes = topology_num_cores_per_package(); uncore_msr_uncores = nhmex_msr_uncores; } /* end of Nehalem-EX uncore support */ diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c index 7fd4334e12..9462fd9f3b 100644 --- a/arch/x86/events/intel/uncore_snb.c +++ b/arch/x86/events/intel/uncore_snb.c @@ -364,8 +364,8 @@ static struct intel_uncore_type *snb_msr_uncores[] = { void snb_uncore_cpu_init(void) { uncore_msr_uncores = snb_msr_uncores; - if (snb_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - snb_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (snb_uncore_cbox.num_boxes > topology_num_cores_per_package()) + snb_uncore_cbox.num_boxes = topology_num_cores_per_package(); } static void skl_uncore_msr_init_box(struct intel_uncore_box *box) @@ -428,8 +428,8 @@ static struct intel_uncore_type *skl_msr_uncores[] = { void skl_uncore_cpu_init(void) { uncore_msr_uncores = skl_msr_uncores; - if (skl_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - skl_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (skl_uncore_cbox.num_boxes > topology_num_cores_per_package()) + skl_uncore_cbox.num_boxes = topology_num_cores_per_package(); snb_uncore_arb.ops = &skl_uncore_msr_ops; } diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index a96496bef6..2eaf0f3398 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1172,8 +1172,8 @@ static struct intel_uncore_type *snbep_msr_uncores[] = { void snbep_uncore_cpu_init(void) { - if (snbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - snbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (snbep_uncore_cbox.num_boxes > topology_num_cores_per_package()) + snbep_uncore_cbox.num_boxes = topology_num_cores_per_package(); uncore_msr_uncores = snbep_msr_uncores; } @@ -1406,7 +1406,7 @@ static int topology_gidnid_map(int nodeid, u32 gidnid) */ for (i = 0; i < 8; i++) { if (nodeid == GIDNIDMAP(gidnid, i)) { - if (topology_max_die_per_package() > 1) + if (topology_max_dies_per_package() > 1) die_id = i; else die_id = topology_phys_to_logical_pkg(i); @@ -1845,8 +1845,8 @@ static struct intel_uncore_type *ivbep_msr_uncores[] = { void ivbep_uncore_cpu_init(void) { - if (ivbep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - ivbep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (ivbep_uncore_cbox.num_boxes > topology_num_cores_per_package()) + ivbep_uncore_cbox.num_boxes = topology_num_cores_per_package(); uncore_msr_uncores = ivbep_msr_uncores; } @@ -2917,8 +2917,8 @@ static bool hswep_has_limit_sbox(unsigned int device) void hswep_uncore_cpu_init(void) { - if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (hswep_uncore_cbox.num_boxes > topology_num_cores_per_package()) + hswep_uncore_cbox.num_boxes = topology_num_cores_per_package(); /* Detect 6-8 core systems with only two SBOXes */ if (hswep_has_limit_sbox(HSWEP_PCU_DID)) @@ -3280,8 +3280,8 @@ static struct event_constraint bdx_uncore_pcu_constraints[] = { void bdx_uncore_cpu_init(void) { - if (bdx_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores) - bdx_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores; + if (bdx_uncore_cbox.num_boxes > topology_num_cores_per_package()) + bdx_uncore_cbox.num_boxes = topology_num_cores_per_package(); uncore_msr_uncores = bdx_msr_uncores; /* Detect systems with no SBOXes */ diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 8d98d468b9..fb2b1961e5 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -674,7 +674,7 @@ static const struct attribute_group *rapl_attr_update[] = { static int __init init_rapl_pmus(void) { - int maxdie = topology_max_packages() * topology_max_die_per_package(); + int maxdie = topology_max_packages() * topology_max_dies_per_package(); size_t size; size = sizeof(*rapl_pmus) + maxdie * sizeof(struct rapl_pmu *); diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 5fc45543e9..0569f57933 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -105,7 +105,7 @@ static bool cpu_is_self(int cpu) * IPI implementation on Hyper-V. */ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, - bool exclude_self) + bool exclude_self) { struct hv_send_ipi_ex *ipi_arg; unsigned long flags; @@ -132,8 +132,8 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, if (!cpumask_equal(mask, cpu_present_mask) || exclude_self) { ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K; - nr_bank = cpumask_to_vpset_skip(&(ipi_arg->vp_set), mask, - exclude_self ? cpu_is_self : NULL); + nr_bank = cpumask_to_vpset_skip(&ipi_arg->vp_set, mask, + exclude_self ? cpu_is_self : NULL); /* * 'nr_bank <= 0' means some CPUs in cpumask can't be @@ -147,7 +147,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, } status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank, - ipi_arg, NULL); + ipi_arg, NULL); ipi_mask_ex_done: local_irq_restore(flags); @@ -155,7 +155,7 @@ ipi_mask_ex_done: } static bool __send_ipi_mask(const struct cpumask *mask, int vector, - bool exclude_self) + bool exclude_self) { int cur_cpu, vcpu, this_cpu = smp_processor_id(); struct hv_send_ipi ipi_arg; @@ -181,7 +181,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector, return false; } - if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) + if (vector < HV_IPI_LOW_VECTOR || vector > HV_IPI_HIGH_VECTOR) return false; /* @@ -218,7 +218,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector, } status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector, - ipi_arg.cpu_mask); + ipi_arg.cpu_mask); return hv_result_success(status); do_ex_hypercall: @@ -241,7 +241,7 @@ static bool __send_ipi_one(int cpu, int vector) return false; } - if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) + if (vector < HV_IPI_LOW_VECTOR || vector > HV_IPI_HIGH_VECTOR) return false; if (vp >= 64) diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 8f3a4d16bb..17a71e92a3 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -667,14 +667,14 @@ void hyperv_cleanup(void) hv_hypercall_pg = NULL; /* Reset the hypercall page */ - hypercall_msr.as_uint64 = hv_get_register(HV_X64_MSR_HYPERCALL); + hypercall_msr.as_uint64 = hv_get_msr(HV_X64_MSR_HYPERCALL); hypercall_msr.enable = 0; - hv_set_register(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); + hv_set_msr(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64); /* Reset the TSC page */ - tsc_msr.as_uint64 = hv_get_register(HV_X64_MSR_REFERENCE_TSC); + tsc_msr.as_uint64 = hv_get_msr(HV_X64_MSR_REFERENCE_TSC); tsc_msr.enable = 0; - hv_set_register(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64); + hv_set_msr(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64); } void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die) diff --git a/arch/x86/hyperv/hv_proc.c b/arch/x86/hyperv/hv_proc.c index 68a0843d47..3fa1f2ee7b 100644 --- a/arch/x86/hyperv/hv_proc.c +++ b/arch/x86/hyperv/hv_proc.c @@ -3,7 +3,6 @@ #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/clockchips.h> -#include <linux/acpi.h> #include <linux/hyperv.h> #include <linux/slab.h> #include <linux/cpuhotplug.h> @@ -116,12 +115,11 @@ free_buf: int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id) { - struct hv_add_logical_processor_in *input; - struct hv_add_logical_processor_out *output; + struct hv_input_add_logical_processor *input; + struct hv_output_add_logical_processor *output; u64 status; unsigned long flags; int ret = HV_STATUS_SUCCESS; - int pxm = node_to_pxm(node); /* * When adding a logical processor, the hypervisor may return @@ -137,11 +135,7 @@ int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id) input->lp_index = lp_index; input->apic_id = apic_id; - input->flags = 0; - input->proximity_domain_info.domain_id = pxm; - input->proximity_domain_info.flags.reserved = 0; - input->proximity_domain_info.flags.proximity_info_valid = 1; - input->proximity_domain_info.flags.proximity_preferred = 1; + input->proximity_domain_info = hv_numa_node_to_pxm_info(node); status = hv_do_hypercall(HVCALL_ADD_LOGICAL_PROCESSOR, input, output); local_irq_restore(flags); @@ -166,7 +160,6 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags) u64 status; unsigned long irq_flags; int ret = HV_STATUS_SUCCESS; - int pxm = node_to_pxm(node); /* Root VPs don't seem to need pages deposited */ if (partition_id != hv_current_partition_id) { @@ -185,14 +178,7 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags) input->vp_index = vp_index; input->flags = flags; input->subnode_type = HvSubnodeAny; - if (node != NUMA_NO_NODE) { - input->proximity_domain_info.domain_id = pxm; - input->proximity_domain_info.flags.reserved = 0; - input->proximity_domain_info.flags.proximity_info_valid = 1; - input->proximity_domain_info.flags.proximity_preferred = 1; - } else { - input->proximity_domain_info.as_uint64 = 0; - } + input->proximity_domain_info = hv_numa_node_to_pxm_info(node); status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL); local_irq_restore(irq_flags); diff --git a/arch/x86/hyperv/hv_spinlock.c b/arch/x86/hyperv/hv_spinlock.c index 737d6f7a61..151e851bef 100644 --- a/arch/x86/hyperv/hv_spinlock.c +++ b/arch/x86/hyperv/hv_spinlock.c @@ -16,7 +16,7 @@ #include <asm/paravirt.h> #include <asm/apic.h> -static bool __initdata hv_pvspin = true; +static bool hv_pvspin __initdata = true; static void hv_qlock_kick(int cpu) { @@ -64,6 +64,7 @@ __visible bool hv_vcpu_is_preempted(int vcpu) { return false; } + PV_CALLEE_SAVE_REGS_THUNK(hv_vcpu_is_preempted); void __init hv_init_spinlocks(void) diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index c8062975a5..5c7de79423 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -32,8 +32,9 @@ void __init hv_vtl_init_platform(void) x86_init.timers.timer_init = x86_init_noop; /* Avoid searching for BIOS MP tables */ - x86_init.mpparse.find_smp_config = x86_init_noop; - x86_init.mpparse.get_smp_config = x86_init_uint_noop; + x86_init.mpparse.find_mptable = x86_init_noop; + x86_init.mpparse.early_parse_smp_cfg = x86_init_noop; + x86_init.mpparse.parse_smp_cfg = x86_init_noop; x86_platform.get_wallclock = get_rtc_noop; x86_platform.set_wallclock = set_rtc_noop; diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index fcd20c6dc7..0cb2396de0 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -117,7 +117,7 @@ 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 int x86_call_depth_emit_accounting(u8 **pprog, void *func); +extern int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip); #else static __always_inline void callthunks_patch_builtin_calls(void) {} static __always_inline void @@ -128,7 +128,7 @@ static __always_inline void *callthunks_translate_call_dest(void *dest) return dest; } static __always_inline int x86_call_depth_emit_accounting(u8 **pprog, - void *func) + void *func, void *ip) { return 0; } @@ -294,10 +294,10 @@ static inline int alternatives_text_reserved(void *start, void *end) * Otherwise, if CPU has feature1, newinstr1 is used. * Otherwise, oldinstr is used. */ -#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2, \ - ft_flags2, input...) \ - asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, \ - newinstr2, ft_flags2) \ +#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2, \ + ft_flags2, input...) \ + asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, \ + newinstr2, ft_flags2) \ : : "i" (0), ## input) /* Like alternative_input, but with a single output argument */ @@ -307,7 +307,7 @@ static inline int alternatives_text_reserved(void *start, void *end) /* Like alternative_io, but for replacing a direct call with another one. */ #define alternative_call(oldfunc, newfunc, ft_flags, output, input...) \ - asm_inline volatile (ALTERNATIVE("call %P[old]", "call %P[new]", ft_flags) \ + asm_inline volatile (ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags) \ : output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input) /* @@ -316,12 +316,12 @@ static inline int alternatives_text_reserved(void *start, void *end) * Otherwise, if CPU has feature1, function1 is used. * Otherwise, old function is used. */ -#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \ - output, input...) \ - asm_inline volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", ft_flags1,\ - "call %P[new2]", ft_flags2) \ - : output, ASM_CALL_CONSTRAINT \ - : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ +#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \ + output, input...) \ + asm_inline volatile (ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1, \ + "call %c[new2]", ft_flags2) \ + : output, ASM_CALL_CONSTRAINT \ + : [old] "i" (oldfunc), [new1] "i" (newfunc1), \ [new2] "i" (newfunc2), ## input) /* diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index dddd3fc195..e6ab0cf15e 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -47,6 +47,10 @@ extern void x86_32_probe_apic(void); static inline void x86_32_probe_apic(void) { } #endif +extern u32 cpuid_to_apicid[]; + +#define CPU_ACPIID_INVALID U32_MAX + #ifdef CONFIG_X86_LOCAL_APIC extern int apic_verbosity; @@ -55,8 +59,6 @@ extern int local_apic_timer_c2_ok; extern bool apic_is_disabled; extern unsigned int lapic_timer_period; -extern u32 cpuid_to_apicid[]; - extern enum apic_intr_mode_id apic_intr_mode; enum apic_intr_mode_id { APIC_PIC, @@ -170,6 +172,14 @@ extern bool apic_needs_pit(void); extern void apic_send_IPI_allbutself(unsigned int vector); +extern void topology_register_apic(u32 apic_id, u32 acpi_id, bool present); +extern void topology_register_boot_apic(u32 apic_id); +extern int topology_hotplug_apic(u32 apic_id, u32 acpi_id); +extern void topology_hotunplug_apic(unsigned int cpu); +extern void topology_apply_cmdline_limits_early(void); +extern void topology_init_possible_cpus(void); +extern void topology_reset_possible_cpus_up(void); + #else /* !CONFIG_X86_LOCAL_APIC */ static inline void lapic_shutdown(void) { } #define local_apic_timer_c2_ok 1 @@ -184,6 +194,8 @@ static inline void apic_intr_mode_init(void) { } static inline void lapic_assign_system_vectors(void) { } static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { } static inline bool apic_needs_pit(void) { return true; } +static inline void topology_apply_cmdline_limits_early(void) { } +static inline void topology_init_possible_cpus(void) { } #endif /* !CONFIG_X86_LOCAL_APIC */ #ifdef CONFIG_X86_X2APIC @@ -290,16 +302,11 @@ struct apic { /* Probe, setup and smpboot functions */ int (*probe)(void); int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id); - bool (*apic_id_registered)(void); - bool (*check_apicid_used)(physid_mask_t *map, u32 apicid); void (*init_apic_ldr)(void); - void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap); u32 (*cpu_present_to_apicid)(int mps_cpu); - u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb); u32 (*get_apic_id)(u32 id); - u32 (*set_apic_id)(u32 apicid); /* wakeup_secondary_cpu */ int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip); @@ -528,7 +535,6 @@ extern int default_apic_id_valid(u32 apicid); extern u32 apic_default_calc_apicid(unsigned int cpu); extern u32 apic_flat_calc_apicid(unsigned int cpu); -extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap); extern u32 default_cpu_present_to_apicid(int mps_cpu); void apic_send_nmi_to_offline_cpu(unsigned int cpu); diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h index 0e82074517..25466c4d21 100644 --- a/arch/x86/include/asm/asm-prototypes.h +++ b/arch/x86/include/asm/asm-prototypes.h @@ -12,6 +12,7 @@ #include <asm/special_insns.h> #include <asm/preempt.h> #include <asm/asm.h> +#include <asm/fred.h> #include <asm/gsseg.h> #include <asm/nospec-branch.h> diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h index 3486d91b85..d510405e4e 100644 --- a/arch/x86/include/asm/atomic64_32.h +++ b/arch/x86/include/asm/atomic64_32.h @@ -24,7 +24,7 @@ typedef struct { #ifdef CONFIG_X86_CMPXCHG64 #define __alternative_atomic64(f, g, out, in...) \ - asm volatile("call %P[func]" \ + asm volatile("call %c[func]" \ : out : [func] "i" (atomic64_##g##_cx8), ## in) #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8) diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index d0795b5fab..63bdc6b852 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -33,7 +33,7 @@ * Returns: * 0 - (index < size) */ -static inline unsigned long array_index_mask_nospec(unsigned long index, +static __always_inline unsigned long array_index_mask_nospec(unsigned long index, unsigned long size) { unsigned long mask; diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h index a368afce37..aa6c8f8ca9 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -14,6 +14,7 @@ enum cc_vendor { #ifdef CONFIG_ARCH_HAS_CC_PLATFORM extern enum cc_vendor cc_vendor; extern u64 cc_mask; + static inline void cc_set_mask(u64 mask) { RIP_REL_REF(cc_mask) = mask; diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index f8f9a9b793..aa30fd8cad 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -9,18 +9,10 @@ #include <linux/percpu.h> #include <asm/ibt.h> -#ifdef CONFIG_SMP - -extern void prefill_possible_map(void); - -#else /* CONFIG_SMP */ - -static inline void prefill_possible_map(void) {} - +#ifndef CONFIG_SMP #define cpu_physical_id(cpu) boot_cpu_physical_apicid #define cpu_acpi_id(cpu) 0 #define safe_smp_processor_id() 0 - #endif /* CONFIG_SMP */ #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h index eb8fcede9e..e8e3dbe7f1 100644 --- a/arch/x86/include/asm/cpu_device_id.h +++ b/arch/x86/include/asm/cpu_device_id.h @@ -3,6 +3,39 @@ #define _ASM_X86_CPU_DEVICE_ID /* + * Can't use <linux/bitfield.h> because it generates expressions that + * cannot be used in structure initializers. Bitfield construction + * here must match the union in struct cpuinfo_86: + * union { + * struct { + * __u8 x86_model; + * __u8 x86; + * __u8 x86_vendor; + * __u8 x86_reserved; + * }; + * __u32 x86_vfm; + * }; + */ +#define VFM_MODEL_BIT 0 +#define VFM_FAMILY_BIT 8 +#define VFM_VENDOR_BIT 16 +#define VFM_RSVD_BIT 24 + +#define VFM_MODEL_MASK GENMASK(VFM_FAMILY_BIT - 1, VFM_MODEL_BIT) +#define VFM_FAMILY_MASK GENMASK(VFM_VENDOR_BIT - 1, VFM_FAMILY_BIT) +#define VFM_VENDOR_MASK GENMASK(VFM_RSVD_BIT - 1, VFM_VENDOR_BIT) + +#define VFM_MODEL(vfm) (((vfm) & VFM_MODEL_MASK) >> VFM_MODEL_BIT) +#define VFM_FAMILY(vfm) (((vfm) & VFM_FAMILY_MASK) >> VFM_FAMILY_BIT) +#define VFM_VENDOR(vfm) (((vfm) & VFM_VENDOR_MASK) >> VFM_VENDOR_BIT) + +#define VFM_MAKE(_vendor, _family, _model) ( \ + ((_model) << VFM_MODEL_BIT) | \ + ((_family) << VFM_FAMILY_BIT) | \ + ((_vendor) << VFM_VENDOR_BIT) \ +) + +/* * Declare drivers belonging to specific x86 CPUs * Similar in spirit to pci_device_id and related PCI functions * @@ -20,6 +53,9 @@ #define X86_CENTAUR_FAM6_C7_D 0xd #define X86_CENTAUR_FAM6_NANO 0xf +/* x86_cpu_id::flags */ +#define X86_CPU_ID_FLAG_ENTRY_VALID BIT(0) + #define X86_STEPPINGS(mins, maxs) GENMASK(maxs, mins) /** * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching @@ -46,6 +82,18 @@ .model = _model, \ .steppings = _steppings, \ .feature = _feature, \ + .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \ + .driver_data = (unsigned long) _data \ +} + +#define X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \ + _steppings, _feature, _data) { \ + .vendor = _vendor, \ + .family = _family, \ + .model = _model, \ + .steppings = _steppings, \ + .feature = _feature, \ + .flags = X86_CPU_ID_FLAG_ENTRY_VALID, \ .driver_data = (unsigned long) _data \ } @@ -164,6 +212,56 @@ X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, INTEL_FAM6_##model, \ steppings, X86_FEATURE_ANY, data) +/** + * X86_MATCH_VFM - Match encoded vendor/family/model + * @vfm: Encoded 8-bits each for vendor, family, model + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + * + * Stepping and feature are set to wildcards + */ +#define X86_MATCH_VFM(vfm, data) \ + X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ + VFM_VENDOR(vfm), \ + VFM_FAMILY(vfm), \ + VFM_MODEL(vfm), \ + X86_STEPPING_ANY, X86_FEATURE_ANY, data) + +/** + * X86_MATCH_VFM_STEPPINGS - Match encoded vendor/family/model/stepping + * @vfm: Encoded 8-bits each for vendor, family, model + * @steppings: Bitmask of steppings to match + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + * + * feature is set to wildcard + */ +#define X86_MATCH_VFM_STEPPINGS(vfm, steppings, data) \ + X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ + VFM_VENDOR(vfm), \ + VFM_FAMILY(vfm), \ + VFM_MODEL(vfm), \ + steppings, X86_FEATURE_ANY, data) + +/** + * X86_MATCH_VFM_FEATURE - Match encoded vendor/family/model/feature + * @vfm: Encoded 8-bits each for vendor, family, model + * @feature: A X86_FEATURE bit + * @data: Driver specific data or NULL. The internal storage + * format is unsigned long. The supplied value, pointer + * etc. is cast to unsigned long internally. + * + * Steppings is set to wildcard + */ +#define X86_MATCH_VFM_FEATURE(vfm, feature, data) \ + X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE( \ + VFM_VENDOR(vfm), \ + VFM_FAMILY(vfm), \ + VFM_MODEL(vfm), \ + X86_STEPPING_ANY, feature, data) + /* * Match specific microcode revisions. * diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 686e92d266..3508f3fc92 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -173,7 +173,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit); static __always_inline bool _static_cpu_has(u16 bit) { asm goto( - ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]") + ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]") ".pushsection .altinstr_aux,\"ax\"\n" "6:\n" " testb %[bitnum]," _ASM_RIP(%P[cap_byte]) "\n" diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 76b3b00ff1..3c74343296 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -324,7 +324,9 @@ #define X86_FEATURE_FZRM (12*32+10) /* "" Fast zero-length REP MOVSB */ #define X86_FEATURE_FSRS (12*32+11) /* "" Fast short REP STOSB */ #define X86_FEATURE_FSRC (12*32+12) /* "" Fast short REP {CMPSB,SCASB} */ +#define X86_FEATURE_FRED (12*32+17) /* Flexible Return and Event Delivery */ #define X86_FEATURE_LKGS (12*32+18) /* "" Load "kernel" (userspace) GS */ +#define X86_FEATURE_WRMSRNS (12*32+19) /* "" Non-serializing WRMSR */ #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 */ #define X86_FEATURE_LAM (12*32+26) /* Linear Address Masking */ @@ -440,6 +442,7 @@ #define X86_FEATURE_SEV (19*32+ 1) /* AMD Secure Encrypted Virtualization */ #define X86_FEATURE_VM_PAGE_FLUSH (19*32+ 2) /* "" VM Page Flush MSR is supported */ #define X86_FEATURE_SEV_ES (19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */ +#define X86_FEATURE_SEV_SNP (19*32+ 4) /* AMD Secure Encrypted Virtualization - Secure Nested Paging */ #define X86_FEATURE_V_TSC_AUX (19*32+ 9) /* "" Virtual TSC_AUX */ #define X86_FEATURE_SME_COHERENT (19*32+10) /* "" AMD hardware-enforced cache coherency */ #define X86_FEATURE_DEBUG_SWAP (19*32+14) /* AMD SEV-ES full debug state swap support */ @@ -462,6 +465,7 @@ * * Reuse free bits when adding new feature flags! */ +#define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ #define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ #define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ #define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h index 9bee3e7bf9..6b122a31da 100644 --- a/arch/x86/include/asm/cpuid.h +++ b/arch/x86/include/asm/cpuid.h @@ -127,6 +127,42 @@ static inline unsigned int cpuid_edx(unsigned int op) return edx; } +static inline void __cpuid_read(unsigned int leaf, unsigned int subleaf, u32 *regs) +{ + regs[CPUID_EAX] = leaf; + regs[CPUID_ECX] = subleaf; + __cpuid(regs + CPUID_EAX, regs + CPUID_EBX, regs + CPUID_ECX, regs + CPUID_EDX); +} + +#define cpuid_subleaf(leaf, subleaf, regs) { \ + static_assert(sizeof(*(regs)) == 16); \ + __cpuid_read(leaf, subleaf, (u32 *)(regs)); \ +} + +#define cpuid_leaf(leaf, regs) { \ + static_assert(sizeof(*(regs)) == 16); \ + __cpuid_read(leaf, 0, (u32 *)(regs)); \ +} + +static inline void __cpuid_read_reg(unsigned int leaf, unsigned int subleaf, + enum cpuid_regs_idx regidx, u32 *reg) +{ + u32 regs[4]; + + __cpuid_read(leaf, subleaf, regs); + *reg = regs[regidx]; +} + +#define cpuid_subleaf_reg(leaf, subleaf, regidx, reg) { \ + static_assert(sizeof(*(reg)) == 4); \ + __cpuid_read_reg(leaf, subleaf, regidx, (u32 *)(reg)); \ +} + +#define cpuid_leaf_reg(leaf, regidx, reg) { \ + static_assert(sizeof(*(reg)) == 4); \ + __cpuid_read_reg(leaf, 0, regidx, (u32 *)(reg)); \ +} + static __always_inline bool cpuid_function_is_indexed(u32 function) { switch (function) { diff --git a/arch/x86/include/asm/crash_core.h b/arch/x86/include/asm/crash_reserve.h index 041020da8d..7835b2cdff 100644 --- a/arch/x86/include/asm/crash_core.h +++ b/arch/x86/include/asm/crash_reserve.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _X86_CRASH_CORE_H -#define _X86_CRASH_CORE_H +#ifndef _X86_CRASH_RESERVE_H +#define _X86_CRASH_RESERVE_H /* 16M alignment for crash kernel regions */ #define CRASH_ALIGN SZ_16M @@ -41,4 +41,4 @@ static inline unsigned long crash_low_size_default(void) #define HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY -#endif /* _X86_CRASH_CORE_H */ +#endif /* _X86_CRASH_RESERVE_H */ diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h index dd4b67101b..bf5953883e 100644 --- a/arch/x86/include/asm/current.h +++ b/arch/x86/include/asm/current.h @@ -18,7 +18,7 @@ struct pcpu_hot { struct task_struct *current_task; int preempt_count; int cpu_number; -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING u64 call_depth; #endif unsigned long top_of_stack; @@ -37,8 +37,15 @@ static_assert(sizeof(struct pcpu_hot) == 64); DECLARE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot); +/* const-qualified alias to pcpu_hot, aliased by linker. */ +DECLARE_PER_CPU_ALIGNED(const struct pcpu_hot __percpu_seg_override, + const_pcpu_hot); + static __always_inline struct task_struct *get_current(void) { + if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT)) + return this_cpu_read_const(const_pcpu_hot.current_task); + return this_cpu_read_stable(pcpu_hot.current_task); } diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 0cec92c430..fdbbbfec74 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -5,7 +5,9 @@ #include <linux/bug.h> #include <linux/percpu.h> #include <uapi/asm/debugreg.h> + #include <asm/cpufeature.h> +#include <asm/msr.h> DECLARE_PER_CPU(unsigned long, cpu_dr7); @@ -159,4 +161,26 @@ static inline unsigned long amd_get_dr_addr_mask(unsigned int dr) } #endif +static inline unsigned long get_debugctlmsr(void) +{ + unsigned long debugctlmsr = 0; + +#ifndef CONFIG_X86_DEBUGCTLMSR + if (boot_cpu_data.x86 < 6) + return 0; +#endif + rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); + + return debugctlmsr; +} + +static inline void update_debugctlmsr(unsigned long debugctlmsr) +{ +#ifndef CONFIG_X86_DEBUGCTLMSR + if (boot_cpu_data.x86 < 6) + return; +#endif + wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); +} + #endif /* _ASM_X86_DEBUGREG_H */ diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h index ab97b22ac0..62dc9f59ea 100644 --- a/arch/x86/include/asm/desc.h +++ b/arch/x86/include/asm/desc.h @@ -46,6 +46,7 @@ struct gdt_page { } __attribute__((aligned(PAGE_SIZE))); DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page); +DECLARE_INIT_PER_CPU(gdt_page); /* Provide the original GDT */ static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu) @@ -402,8 +403,6 @@ static inline void set_desc_limit(struct desc_struct *desc, unsigned long limit) desc->limit1 = (limit >> 16) & 0xf; } -void alloc_intr_gate(unsigned int n, const void *addr); - static inline void init_idt_data(struct idt_data *data, unsigned int n, const void *addr) { diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 88fcf08458..c492bdc97b 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -44,32 +44,32 @@ # define DISABLE_LA57 (1<<(X86_FEATURE_LA57 & 31)) #endif -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION # define DISABLE_PTI 0 #else # define DISABLE_PTI (1 << (X86_FEATURE_PTI & 31)) #endif -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE # define DISABLE_RETPOLINE 0 #else # define DISABLE_RETPOLINE ((1 << (X86_FEATURE_RETPOLINE & 31)) | \ (1 << (X86_FEATURE_RETPOLINE_LFENCE & 31))) #endif -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK # define DISABLE_RETHUNK 0 #else # define DISABLE_RETHUNK (1 << (X86_FEATURE_RETHUNK & 31)) #endif -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY # define DISABLE_UNRET 0 #else # define DISABLE_UNRET (1 << (X86_FEATURE_UNRET & 31)) #endif -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING # define DISABLE_CALL_DEPTH_TRACKING 0 #else # define DISABLE_CALL_DEPTH_TRACKING (1 << (X86_FEATURE_CALL_DEPTH & 31)) @@ -117,6 +117,18 @@ #define DISABLE_IBT (1 << (X86_FEATURE_IBT & 31)) #endif +#ifdef CONFIG_X86_FRED +# define DISABLE_FRED 0 +#else +# define DISABLE_FRED (1 << (X86_FEATURE_FRED & 31)) +#endif + +#ifdef CONFIG_KVM_AMD_SEV +#define DISABLE_SEV_SNP 0 +#else +#define DISABLE_SEV_SNP (1 << (X86_FEATURE_SEV_SNP & 31)) +#endif + /* * Make sure to add features to the correct mask */ @@ -133,7 +145,7 @@ #define DISABLED_MASK10 0 #define DISABLED_MASK11 (DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \ DISABLE_CALL_DEPTH_TRACKING|DISABLE_USER_SHSTK) -#define DISABLED_MASK12 (DISABLE_LAM) +#define DISABLED_MASK12 (DISABLE_FRED|DISABLE_LAM) #define DISABLED_MASK13 0 #define DISABLED_MASK14 0 #define DISABLED_MASK15 0 @@ -141,7 +153,7 @@ DISABLE_ENQCMD) #define DISABLED_MASK17 0 #define DISABLED_MASK18 (DISABLE_IBT) -#define DISABLED_MASK19 0 +#define DISABLED_MASK19 (DISABLE_SEV_SNP) #define DISABLED_MASK20 0 #define DISABLED_MASK21 0 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h index e8f58ddd06..2e74a7f0e9 100644 --- a/arch/x86/include/asm/e820/api.h +++ b/arch/x86/include/asm/e820/api.h @@ -17,6 +17,7 @@ extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type); extern void e820__range_add (u64 start, u64 size, enum e820_type type); extern u64 e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type); extern u64 e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type); +extern u64 e820__range_update_table(struct e820_table *t, u64 start, u64 size, enum e820_type old_type, enum e820_type new_type); extern void e820__print_table(char *who); extern int e820__update_table(struct e820_table *table); diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h index c4555b269a..4810961775 100644 --- a/arch/x86/include/asm/efi.h +++ b/arch/x86/include/asm/efi.h @@ -143,15 +143,6 @@ extern void efi_free_boot_services(void); void arch_efi_call_virt_setup(void); void arch_efi_call_virt_teardown(void); -/* kexec external ABI */ -struct efi_setup_data { - u64 fw_vendor; - u64 __unused; - u64 tables; - u64 smbios; - u64 reserved[8]; -}; - extern u64 efi_setup; #ifdef CONFIG_EFI @@ -410,7 +401,6 @@ 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, @@ -418,8 +408,9 @@ extern int __init efi_memmap_split_count(efi_memory_desc_t *md, 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; }) +extern enum efi_secureboot_mode __x86_ima_efi_boot_mode(void); + +#define arch_ima_efi_boot_mode __x86_ima_efi_boot_mode() #ifdef CONFIG_EFI_RUNTIME_MAP int efi_get_runtime_map_size(void); diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 1e16bd5ac7..1fb83d4771 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -392,5 +392,4 @@ struct va_alignment { } ____cacheline_aligned; extern struct va_alignment va_align; -extern unsigned long align_vdso_addr(unsigned long); #endif /* _ASM_X86_ELF_H */ diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h index fe63120450..7acf0383be 100644 --- a/arch/x86/include/asm/extable_fixup_types.h +++ b/arch/x86/include/asm/extable_fixup_types.h @@ -64,6 +64,8 @@ #define EX_TYPE_UCOPY_LEN4 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4)) #define EX_TYPE_UCOPY_LEN8 (EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8)) -#define EX_TYPE_ZEROPAD 20 /* longword load with zeropad on fault */ +#define EX_TYPE_ZEROPAD 20 /* longword load with zeropad on fault */ + +#define EX_TYPE_ERETU 21 #endif diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h index ca6e5e5f16..c485f1944c 100644 --- a/arch/x86/include/asm/fpu/sched.h +++ b/arch/x86/include/asm/fpu/sched.h @@ -37,10 +37,12 @@ extern void fpu_flush_thread(void); * The FPU context is only stored/restored for a user task and * PF_KTHREAD is used to distinguish between kernel and user threads. */ -static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) +static inline void switch_fpu_prepare(struct task_struct *old, int cpu) { if (cpu_feature_enabled(X86_FEATURE_FPU) && - !(current->flags & (PF_KTHREAD | PF_USER_WORKER))) { + !(old->flags & (PF_KTHREAD | PF_USER_WORKER))) { + struct fpu *old_fpu = &old->thread.fpu; + save_fpregs_to_fpstate(old_fpu); /* * The save operation preserved register state, so the @@ -60,10 +62,10 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu) * Delay loading of the complete FPU state until the return to userland. * PKRU is handled separately. */ -static inline void switch_fpu_finish(void) +static inline void switch_fpu_finish(struct task_struct *new) { if (cpu_feature_enabled(X86_FEATURE_FPU)) - set_thread_flag(TIF_NEED_FPU_LOAD); + set_tsk_thread_flag(new, TIF_NEED_FPU_LOAD); } #endif /* _ASM_X86_FPU_SCHED_H */ diff --git a/arch/x86/include/asm/fred.h b/arch/x86/include/asm/fred.h new file mode 100644 index 0000000000..e86c7ba324 --- /dev/null +++ b/arch/x86/include/asm/fred.h @@ -0,0 +1,97 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Macros for Flexible Return and Event Delivery (FRED) + */ + +#ifndef ASM_X86_FRED_H +#define ASM_X86_FRED_H + +#include <linux/const.h> + +#include <asm/asm.h> +#include <asm/trapnr.h> + +/* + * FRED event return instruction opcodes for ERET{S,U}; supported in + * binutils >= 2.41. + */ +#define ERETS _ASM_BYTES(0xf2,0x0f,0x01,0xca) +#define ERETU _ASM_BYTES(0xf3,0x0f,0x01,0xca) + +/* + * RSP is aligned to a 64-byte boundary before used to push a new stack frame + */ +#define FRED_STACK_FRAME_RSP_MASK _AT(unsigned long, (~0x3f)) + +/* + * Used for the return address for call emulation during code patching, + * and measured in 64-byte cache lines. + */ +#define FRED_CONFIG_REDZONE_AMOUNT 1 +#define FRED_CONFIG_REDZONE (_AT(unsigned long, FRED_CONFIG_REDZONE_AMOUNT) << 6) +#define FRED_CONFIG_INT_STKLVL(l) (_AT(unsigned long, l) << 9) +#define FRED_CONFIG_ENTRYPOINT(p) _AT(unsigned long, (p)) + +#ifndef __ASSEMBLY__ + +#ifdef CONFIG_X86_FRED +#include <linux/kernel.h> + +#include <asm/ptrace.h> + +struct fred_info { + /* Event data: CR2, DR6, ... */ + unsigned long edata; + unsigned long resv; +}; + +/* Full format of the FRED stack frame */ +struct fred_frame { + struct pt_regs regs; + struct fred_info info; +}; + +static __always_inline struct fred_info *fred_info(struct pt_regs *regs) +{ + return &container_of(regs, struct fred_frame, regs)->info; +} + +static __always_inline unsigned long fred_event_data(struct pt_regs *regs) +{ + return fred_info(regs)->edata; +} + +void asm_fred_entrypoint_user(void); +void asm_fred_entrypoint_kernel(void); +void asm_fred_entry_from_kvm(struct fred_ss); + +__visible void fred_entry_from_user(struct pt_regs *regs); +__visible void fred_entry_from_kernel(struct pt_regs *regs); +__visible void __fred_entry_from_kvm(struct pt_regs *regs); + +/* Can be called from noinstr code, thus __always_inline */ +static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) +{ + struct fred_ss ss = { + .ss =__KERNEL_DS, + .type = type, + .vector = vector, + .nmi = type == EVENT_TYPE_NMI, + .lm = 1, + }; + + asm_fred_entry_from_kvm(ss); +} + +void cpu_init_fred_exceptions(void); +void fred_complete_exception_setup(void); + +#else /* CONFIG_X86_FRED */ +static __always_inline unsigned long fred_event_data(struct pt_regs *regs) { return 0; } +static inline void cpu_init_fred_exceptions(void) { } +static inline void fred_complete_exception_setup(void) { } +static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { } +#endif /* CONFIG_X86_FRED */ +#endif /* !__ASSEMBLY__ */ + +#endif /* ASM_X86_FRED_H */ diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h index 35cff5f2be..9e7e8ca8e2 100644 --- a/arch/x86/include/asm/fsgsbase.h +++ b/arch/x86/include/asm/fsgsbase.h @@ -6,7 +6,7 @@ #ifdef CONFIG_X86_64 -#include <asm/msr-index.h> +#include <asm/msr.h> /* * Read/write a task's FSBASE or GSBASE. This returns the value that diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 66837b8c67..fbc7722b87 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -15,7 +15,7 @@ typedef struct { unsigned int irq_spurious_count; unsigned int icr_read_retry_count; #endif -#ifdef CONFIG_HAVE_KVM +#if IS_ENABLED(CONFIG_KVM) unsigned int kvm_posted_intr_ipis; unsigned int kvm_posted_intr_wakeup_ipis; unsigned int kvm_posted_intr_nested_ipis; diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index b02c3cd3c0..edebf1020e 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -16,8 +16,6 @@ #include <asm/irq_vectors.h> -#define IRQ_MATRIX_BITS NR_VECTORS - #ifndef __ASSEMBLY__ #include <linux/percpu.h> diff --git a/arch/x86/include/asm/hyperv-tlfs.h b/arch/x86/include/asm/hyperv-tlfs.h index 2ff26f53cd..3787d26810 100644 --- a/arch/x86/include/asm/hyperv-tlfs.h +++ b/arch/x86/include/asm/hyperv-tlfs.h @@ -182,7 +182,7 @@ enum hv_isolation_type { #define HV_X64_MSR_HYPERCALL 0x40000001 /* MSR used to provide vcpu index */ -#define HV_REGISTER_VP_INDEX 0x40000002 +#define HV_X64_MSR_VP_INDEX 0x40000002 /* MSR used to reset the guest OS. */ #define HV_X64_MSR_RESET 0x40000003 @@ -191,10 +191,10 @@ enum hv_isolation_type { #define HV_X64_MSR_VP_RUNTIME 0x40000010 /* MSR used to read the per-partition time reference counter */ -#define HV_REGISTER_TIME_REF_COUNT 0x40000020 +#define HV_X64_MSR_TIME_REF_COUNT 0x40000020 /* A partition's reference time stamp counter (TSC) page */ -#define HV_REGISTER_REFERENCE_TSC 0x40000021 +#define HV_X64_MSR_REFERENCE_TSC 0x40000021 /* MSR used to retrieve the TSC frequency */ #define HV_X64_MSR_TSC_FREQUENCY 0x40000022 @@ -209,61 +209,61 @@ enum hv_isolation_type { #define HV_X64_MSR_VP_ASSIST_PAGE 0x40000073 /* Define synthetic interrupt controller model specific registers. */ -#define HV_REGISTER_SCONTROL 0x40000080 -#define HV_REGISTER_SVERSION 0x40000081 -#define HV_REGISTER_SIEFP 0x40000082 -#define HV_REGISTER_SIMP 0x40000083 -#define HV_REGISTER_EOM 0x40000084 -#define HV_REGISTER_SINT0 0x40000090 -#define HV_REGISTER_SINT1 0x40000091 -#define HV_REGISTER_SINT2 0x40000092 -#define HV_REGISTER_SINT3 0x40000093 -#define HV_REGISTER_SINT4 0x40000094 -#define HV_REGISTER_SINT5 0x40000095 -#define HV_REGISTER_SINT6 0x40000096 -#define HV_REGISTER_SINT7 0x40000097 -#define HV_REGISTER_SINT8 0x40000098 -#define HV_REGISTER_SINT9 0x40000099 -#define HV_REGISTER_SINT10 0x4000009A -#define HV_REGISTER_SINT11 0x4000009B -#define HV_REGISTER_SINT12 0x4000009C -#define HV_REGISTER_SINT13 0x4000009D -#define HV_REGISTER_SINT14 0x4000009E -#define HV_REGISTER_SINT15 0x4000009F +#define HV_X64_MSR_SCONTROL 0x40000080 +#define HV_X64_MSR_SVERSION 0x40000081 +#define HV_X64_MSR_SIEFP 0x40000082 +#define HV_X64_MSR_SIMP 0x40000083 +#define HV_X64_MSR_EOM 0x40000084 +#define HV_X64_MSR_SINT0 0x40000090 +#define HV_X64_MSR_SINT1 0x40000091 +#define HV_X64_MSR_SINT2 0x40000092 +#define HV_X64_MSR_SINT3 0x40000093 +#define HV_X64_MSR_SINT4 0x40000094 +#define HV_X64_MSR_SINT5 0x40000095 +#define HV_X64_MSR_SINT6 0x40000096 +#define HV_X64_MSR_SINT7 0x40000097 +#define HV_X64_MSR_SINT8 0x40000098 +#define HV_X64_MSR_SINT9 0x40000099 +#define HV_X64_MSR_SINT10 0x4000009A +#define HV_X64_MSR_SINT11 0x4000009B +#define HV_X64_MSR_SINT12 0x4000009C +#define HV_X64_MSR_SINT13 0x4000009D +#define HV_X64_MSR_SINT14 0x4000009E +#define HV_X64_MSR_SINT15 0x4000009F /* * Define synthetic interrupt controller model specific registers for * nested hypervisor. */ -#define HV_REGISTER_NESTED_SCONTROL 0x40001080 -#define HV_REGISTER_NESTED_SVERSION 0x40001081 -#define HV_REGISTER_NESTED_SIEFP 0x40001082 -#define HV_REGISTER_NESTED_SIMP 0x40001083 -#define HV_REGISTER_NESTED_EOM 0x40001084 -#define HV_REGISTER_NESTED_SINT0 0x40001090 +#define HV_X64_MSR_NESTED_SCONTROL 0x40001080 +#define HV_X64_MSR_NESTED_SVERSION 0x40001081 +#define HV_X64_MSR_NESTED_SIEFP 0x40001082 +#define HV_X64_MSR_NESTED_SIMP 0x40001083 +#define HV_X64_MSR_NESTED_EOM 0x40001084 +#define HV_X64_MSR_NESTED_SINT0 0x40001090 /* * Synthetic Timer MSRs. Four timers per vcpu. */ -#define HV_REGISTER_STIMER0_CONFIG 0x400000B0 -#define HV_REGISTER_STIMER0_COUNT 0x400000B1 -#define HV_REGISTER_STIMER1_CONFIG 0x400000B2 -#define HV_REGISTER_STIMER1_COUNT 0x400000B3 -#define HV_REGISTER_STIMER2_CONFIG 0x400000B4 -#define HV_REGISTER_STIMER2_COUNT 0x400000B5 -#define HV_REGISTER_STIMER3_CONFIG 0x400000B6 -#define HV_REGISTER_STIMER3_COUNT 0x400000B7 +#define HV_X64_MSR_STIMER0_CONFIG 0x400000B0 +#define HV_X64_MSR_STIMER0_COUNT 0x400000B1 +#define HV_X64_MSR_STIMER1_CONFIG 0x400000B2 +#define HV_X64_MSR_STIMER1_COUNT 0x400000B3 +#define HV_X64_MSR_STIMER2_CONFIG 0x400000B4 +#define HV_X64_MSR_STIMER2_COUNT 0x400000B5 +#define HV_X64_MSR_STIMER3_CONFIG 0x400000B6 +#define HV_X64_MSR_STIMER3_COUNT 0x400000B7 /* Hyper-V guest idle MSR */ #define HV_X64_MSR_GUEST_IDLE 0x400000F0 /* Hyper-V guest crash notification MSR's */ -#define HV_REGISTER_CRASH_P0 0x40000100 -#define HV_REGISTER_CRASH_P1 0x40000101 -#define HV_REGISTER_CRASH_P2 0x40000102 -#define HV_REGISTER_CRASH_P3 0x40000103 -#define HV_REGISTER_CRASH_P4 0x40000104 -#define HV_REGISTER_CRASH_CTL 0x40000105 +#define HV_X64_MSR_CRASH_P0 0x40000100 +#define HV_X64_MSR_CRASH_P1 0x40000101 +#define HV_X64_MSR_CRASH_P2 0x40000102 +#define HV_X64_MSR_CRASH_P3 0x40000103 +#define HV_X64_MSR_CRASH_P4 0x40000104 +#define HV_X64_MSR_CRASH_CTL 0x40000105 /* TSC emulation after migration */ #define HV_X64_MSR_REENLIGHTENMENT_CONTROL 0x40000106 @@ -276,31 +276,38 @@ enum hv_isolation_type { /* HV_X64_MSR_TSC_INVARIANT_CONTROL bits */ #define HV_EXPOSE_INVARIANT_TSC BIT_ULL(0) -/* Register name aliases for temporary compatibility */ -#define HV_X64_MSR_STIMER0_COUNT HV_REGISTER_STIMER0_COUNT -#define HV_X64_MSR_STIMER0_CONFIG HV_REGISTER_STIMER0_CONFIG -#define HV_X64_MSR_STIMER1_COUNT HV_REGISTER_STIMER1_COUNT -#define HV_X64_MSR_STIMER1_CONFIG HV_REGISTER_STIMER1_CONFIG -#define HV_X64_MSR_STIMER2_COUNT HV_REGISTER_STIMER2_COUNT -#define HV_X64_MSR_STIMER2_CONFIG HV_REGISTER_STIMER2_CONFIG -#define HV_X64_MSR_STIMER3_COUNT HV_REGISTER_STIMER3_COUNT -#define HV_X64_MSR_STIMER3_CONFIG HV_REGISTER_STIMER3_CONFIG -#define HV_X64_MSR_SCONTROL HV_REGISTER_SCONTROL -#define HV_X64_MSR_SVERSION HV_REGISTER_SVERSION -#define HV_X64_MSR_SIMP HV_REGISTER_SIMP -#define HV_X64_MSR_SIEFP HV_REGISTER_SIEFP -#define HV_X64_MSR_VP_INDEX HV_REGISTER_VP_INDEX -#define HV_X64_MSR_EOM HV_REGISTER_EOM -#define HV_X64_MSR_SINT0 HV_REGISTER_SINT0 -#define HV_X64_MSR_SINT15 HV_REGISTER_SINT15 -#define HV_X64_MSR_CRASH_P0 HV_REGISTER_CRASH_P0 -#define HV_X64_MSR_CRASH_P1 HV_REGISTER_CRASH_P1 -#define HV_X64_MSR_CRASH_P2 HV_REGISTER_CRASH_P2 -#define HV_X64_MSR_CRASH_P3 HV_REGISTER_CRASH_P3 -#define HV_X64_MSR_CRASH_P4 HV_REGISTER_CRASH_P4 -#define HV_X64_MSR_CRASH_CTL HV_REGISTER_CRASH_CTL -#define HV_X64_MSR_TIME_REF_COUNT HV_REGISTER_TIME_REF_COUNT -#define HV_X64_MSR_REFERENCE_TSC HV_REGISTER_REFERENCE_TSC +/* + * To support arch-generic code calling hv_set/get_register: + * - On x86, HV_MSR_ indicates an MSR accessed via rdmsrl/wrmsrl + * - On ARM, HV_MSR_ indicates a VP register accessed via hypercall + */ +#define HV_MSR_CRASH_P0 (HV_X64_MSR_CRASH_P0) +#define HV_MSR_CRASH_P1 (HV_X64_MSR_CRASH_P1) +#define HV_MSR_CRASH_P2 (HV_X64_MSR_CRASH_P2) +#define HV_MSR_CRASH_P3 (HV_X64_MSR_CRASH_P3) +#define HV_MSR_CRASH_P4 (HV_X64_MSR_CRASH_P4) +#define HV_MSR_CRASH_CTL (HV_X64_MSR_CRASH_CTL) + +#define HV_MSR_VP_INDEX (HV_X64_MSR_VP_INDEX) +#define HV_MSR_TIME_REF_COUNT (HV_X64_MSR_TIME_REF_COUNT) +#define HV_MSR_REFERENCE_TSC (HV_X64_MSR_REFERENCE_TSC) + +#define HV_MSR_SINT0 (HV_X64_MSR_SINT0) +#define HV_MSR_SVERSION (HV_X64_MSR_SVERSION) +#define HV_MSR_SCONTROL (HV_X64_MSR_SCONTROL) +#define HV_MSR_SIEFP (HV_X64_MSR_SIEFP) +#define HV_MSR_SIMP (HV_X64_MSR_SIMP) +#define HV_MSR_EOM (HV_X64_MSR_EOM) + +#define HV_MSR_NESTED_SCONTROL (HV_X64_MSR_NESTED_SCONTROL) +#define HV_MSR_NESTED_SVERSION (HV_X64_MSR_NESTED_SVERSION) +#define HV_MSR_NESTED_SIEFP (HV_X64_MSR_NESTED_SIEFP) +#define HV_MSR_NESTED_SIMP (HV_X64_MSR_NESTED_SIMP) +#define HV_MSR_NESTED_EOM (HV_X64_MSR_NESTED_EOM) +#define HV_MSR_NESTED_SINT0 (HV_X64_MSR_NESTED_SINT0) + +#define HV_MSR_STIMER0_CONFIG (HV_X64_MSR_STIMER0_CONFIG) +#define HV_MSR_STIMER0_COUNT (HV_X64_MSR_STIMER0_COUNT) /* * Registers are only accessible via HVCALL_GET_VP_REGISTERS hvcall and diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index c7ef6ea2fa..4212c00c97 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -69,7 +69,7 @@ extern void ia32_pick_mmap_layout(struct mm_struct *mm); extern bool __ia32_enabled; -static inline bool ia32_enabled(void) +static __always_inline bool ia32_enabled(void) { return __ia32_enabled; } @@ -81,7 +81,7 @@ static inline void ia32_disable(void) #else /* !CONFIG_IA32_EMULATION */ -static inline bool ia32_enabled(void) +static __always_inline bool ia32_enabled(void) { return IS_ENABLED(CONFIG_X86_32); } diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 13639e57e1..749c7411d2 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -13,15 +13,18 @@ #include <asm/irq_stack.h> +typedef void (*idtentry_t)(struct pt_regs *regs); + /** * DECLARE_IDTENTRY - Declare functions for simple IDT entry points * No error code pushed by hardware * @vector: Vector number (ignored for C) * @func: Function name of the entry point * - * Declares three functions: + * Declares four functions: * - The ASM entry point: asm_##func * - The XEN PV trap entry point: xen_##func (maybe unused) + * - The C handler called from the FRED event dispatcher (maybe unused) * - The C handler called from the ASM entry point * * Note: This is the C variant of DECLARE_IDTENTRY(). As the name says it @@ -31,6 +34,7 @@ #define DECLARE_IDTENTRY(vector, func) \ asmlinkage void asm_##func(void); \ asmlinkage void xen_asm_##func(void); \ + void fred_##func(struct pt_regs *regs); \ __visible void func(struct pt_regs *regs) /** @@ -138,6 +142,17 @@ static __always_inline void __##func(struct pt_regs *regs, \ __visible noinstr void func(struct pt_regs *regs) /** + * DEFINE_FREDENTRY_RAW - Emit code for raw FRED entry points + * @func: Function name of the entry point + * + * @func is called from the FRED event dispatcher with interrupts disabled. + * + * See @DEFINE_IDTENTRY_RAW for further details. + */ +#define DEFINE_FREDENTRY_RAW(func) \ +noinstr void fred_##func(struct pt_regs *regs) + +/** * DECLARE_IDTENTRY_RAW_ERRORCODE - Declare functions for raw IDT entry points * Error code pushed by hardware * @vector: Vector number (ignored for C) @@ -233,17 +248,27 @@ static noinline void __##func(struct pt_regs *regs, u32 vector) #define DEFINE_IDTENTRY_SYSVEC(func) \ static void __##func(struct pt_regs *regs); \ \ +static __always_inline void instr_##func(struct pt_regs *regs) \ +{ \ + kvm_set_cpu_l1tf_flush_l1d(); \ + run_sysvec_on_irqstack_cond(__##func, regs); \ +} \ + \ __visible noinstr void func(struct pt_regs *regs) \ { \ irqentry_state_t state = irqentry_enter(regs); \ \ instrumentation_begin(); \ - kvm_set_cpu_l1tf_flush_l1d(); \ - run_sysvec_on_irqstack_cond(__##func, regs); \ + instr_##func (regs); \ instrumentation_end(); \ irqentry_exit(regs, state); \ } \ \ +void fred_##func(struct pt_regs *regs) \ +{ \ + instr_##func (regs); \ +} \ + \ static noinline void __##func(struct pt_regs *regs) /** @@ -260,19 +285,29 @@ static noinline void __##func(struct pt_regs *regs) #define DEFINE_IDTENTRY_SYSVEC_SIMPLE(func) \ static __always_inline void __##func(struct pt_regs *regs); \ \ -__visible noinstr void func(struct pt_regs *regs) \ +static __always_inline void instr_##func(struct pt_regs *regs) \ { \ - irqentry_state_t state = irqentry_enter(regs); \ - \ - instrumentation_begin(); \ __irq_enter_raw(); \ kvm_set_cpu_l1tf_flush_l1d(); \ __##func (regs); \ __irq_exit_raw(); \ +} \ + \ +__visible noinstr void func(struct pt_regs *regs) \ +{ \ + irqentry_state_t state = irqentry_enter(regs); \ + \ + instrumentation_begin(); \ + instr_##func (regs); \ instrumentation_end(); \ irqentry_exit(regs, state); \ } \ \ +void fred_##func(struct pt_regs *regs) \ +{ \ + instr_##func (regs); \ +} \ + \ static __always_inline void __##func(struct pt_regs *regs) /** @@ -410,17 +445,35 @@ __visible noinstr void func(struct pt_regs *regs, \ /* C-Code mapping */ #define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_RAW #define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_RAW +#define DEFINE_FREDENTRY_NMI DEFINE_FREDENTRY_RAW #ifdef CONFIG_X86_64 #define DECLARE_IDTENTRY_MCE DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE_USER DEFINE_IDTENTRY_NOIST +#define DEFINE_FREDENTRY_MCE DEFINE_FREDENTRY_RAW #define DECLARE_IDTENTRY_DEBUG DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG_USER DEFINE_IDTENTRY_NOIST +#define DEFINE_FREDENTRY_DEBUG DEFINE_FREDENTRY_RAW +#endif + +void idt_install_sysvec(unsigned int n, const void *function); + +#ifdef CONFIG_X86_FRED +void fred_install_sysvec(unsigned int vector, const idtentry_t function); +#else +static inline void fred_install_sysvec(unsigned int vector, const idtentry_t function) { } #endif +#define sysvec_install(vector, function) { \ + if (cpu_feature_enabled(X86_FEATURE_FRED)) \ + fred_install_sysvec(vector, function); \ + else \ + idt_install_sysvec(vector, asm_##function); \ +} + #else /* !__ASSEMBLY__ */ /* @@ -447,7 +500,7 @@ __visible noinstr void func(struct pt_regs *regs, \ /* System vector entries */ #define DECLARE_IDTENTRY_SYSVEC(vector, func) \ - idtentry_sysvec vector func + DECLARE_IDTENTRY(vector, func) #ifdef CONFIG_X86_64 # define DECLARE_IDTENTRY_MCE(vector, func) \ @@ -655,36 +708,53 @@ DECLARE_IDTENTRY(RESCHEDULE_VECTOR, sysvec_reschedule_ipi); DECLARE_IDTENTRY_SYSVEC(REBOOT_VECTOR, sysvec_reboot); DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_SINGLE_VECTOR, sysvec_call_function_single); DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_VECTOR, sysvec_call_function); +#else +# define fred_sysvec_reschedule_ipi NULL +# define fred_sysvec_reboot NULL +# define fred_sysvec_call_function_single NULL +# define fred_sysvec_call_function NULL #endif #ifdef CONFIG_X86_LOCAL_APIC # ifdef CONFIG_X86_MCE_THRESHOLD DECLARE_IDTENTRY_SYSVEC(THRESHOLD_APIC_VECTOR, sysvec_threshold); +# else +# define fred_sysvec_threshold NULL # endif # ifdef CONFIG_X86_MCE_AMD DECLARE_IDTENTRY_SYSVEC(DEFERRED_ERROR_VECTOR, sysvec_deferred_error); +# else +# define fred_sysvec_deferred_error NULL # endif # ifdef CONFIG_X86_THERMAL_VECTOR DECLARE_IDTENTRY_SYSVEC(THERMAL_APIC_VECTOR, sysvec_thermal); +# else +# define fred_sysvec_thermal NULL # endif # ifdef CONFIG_IRQ_WORK DECLARE_IDTENTRY_SYSVEC(IRQ_WORK_VECTOR, sysvec_irq_work); +# else +# define fred_sysvec_irq_work NULL # endif #endif -#ifdef CONFIG_HAVE_KVM +#if IS_ENABLED(CONFIG_KVM) DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_VECTOR, sysvec_kvm_posted_intr_ipi); DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_WAKEUP_VECTOR, sysvec_kvm_posted_intr_wakeup_ipi); DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR, sysvec_kvm_posted_intr_nested_ipi); +#else +# define fred_sysvec_kvm_posted_intr_ipi NULL +# define fred_sysvec_kvm_posted_intr_wakeup_ipi NULL +# define fred_sysvec_kvm_posted_intr_nested_ipi NULL #endif #if IS_ENABLED(CONFIG_HYPERV) DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback); DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment); -DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0); +DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0); #endif #if IS_ENABLED(CONFIG_ACRN_GUEST) diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index b65e9c46b9..d0941f4c27 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -127,6 +127,7 @@ #define INTEL_FAM6_ARROWLAKE_H 0xC5 #define INTEL_FAM6_ARROWLAKE 0xC6 +#define INTEL_FAM6_ARROWLAKE_U 0xB5 #define INTEL_FAM6_LUNARLAKE_M 0xBD diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 51c782600e..0d806513c4 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -140,7 +140,6 @@ extern void mask_ioapic_entries(void); extern int restore_ioapic_entries(void); extern void setup_ioapic_ids_from_mpc(void); -extern void setup_ioapic_ids_from_mpc_nocheck(void); extern int mp_find_ioapic(u32 gsi); extern int mp_find_ioapic_pin(int ioapic, u32 gsi); diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h index 2fd52b65de..3be2451e7b 100644 --- a/arch/x86/include/asm/iommu.h +++ b/arch/x86/include/asm/iommu.h @@ -10,6 +10,7 @@ extern int force_iommu, no_iommu; extern int iommu_detected; extern int iommu_merge; extern int panic_on_overflow; +extern bool amd_iommu_snp_en; #ifdef CONFIG_SWIOTLB extern bool x86_swiotlb_enable; diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h index 836c170d30..194dfff84c 100644 --- a/arch/x86/include/asm/irq.h +++ b/arch/x86/include/asm/irq.h @@ -29,7 +29,7 @@ struct irq_desc; extern void fixup_irqs(void); -#ifdef CONFIG_HAVE_KVM +#if IS_ENABLED(CONFIG_KVM) extern void kvm_set_posted_intr_wakeup_handler(void (*handler)(void)); #endif diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h index 798183867d..b71ad173f8 100644 --- a/arch/x86/include/asm/irq_stack.h +++ b/arch/x86/include/asm/irq_stack.h @@ -100,7 +100,7 @@ } #define ASM_CALL_ARG0 \ - "call %P[__func] \n" \ + "call %c[__func] \n" \ ASM_REACHABLE #define ASM_CALL_ARG1 \ diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 3a19904c2d..d18bfb238f 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -84,11 +84,9 @@ #define HYPERVISOR_CALLBACK_VECTOR 0xf3 /* Vector for KVM to deliver posted interrupt IPI */ -#ifdef CONFIG_HAVE_KVM #define POSTED_INTR_VECTOR 0xf2 #define POSTED_INTR_WAKEUP_VECTOR 0xf1 #define POSTED_INTR_NESTED_VECTOR 0xf0 -#endif #define MANAGED_IRQ_SHUTDOWN_VECTOR 0xef diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h index c9f6a6c5de..91ca9a9ee3 100644 --- a/arch/x86/include/asm/kexec.h +++ b/arch/x86/include/asm/kexec.h @@ -25,7 +25,6 @@ #include <asm/page.h> #include <asm/ptrace.h> -#include <asm/bootparam.h> struct kimage; diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 378ed944b8..110d7f29ca 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -103,7 +103,6 @@ KVM_X86_OP(write_tsc_multiplier) KVM_X86_OP(get_exit_info) KVM_X86_OP(check_intercept) KVM_X86_OP(handle_exit_irqoff) -KVM_X86_OP(request_immediate_exit) KVM_X86_OP(sched_in) KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging) KVM_X86_OP_OPTIONAL(vcpu_blocking) @@ -138,6 +137,7 @@ KVM_X86_OP(complete_emulated_msr) KVM_X86_OP(vcpu_deliver_sipi_vector) KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons); KVM_X86_OP_OPTIONAL(get_untagged_addr) +KVM_X86_OP_OPTIONAL(alloc_apic_backing_page) #undef KVM_X86_OP #undef KVM_X86_OP_OPTIONAL diff --git a/arch/x86/include/asm/kvm-x86-pmu-ops.h b/arch/x86/include/asm/kvm-x86-pmu-ops.h index 058bc63635..f852b13aee 100644 --- a/arch/x86/include/asm/kvm-x86-pmu-ops.h +++ b/arch/x86/include/asm/kvm-x86-pmu-ops.h @@ -12,11 +12,9 @@ BUILD_BUG_ON(1) * a NULL definition, for example if "static_call_cond()" will be used * at the call sites. */ -KVM_X86_PMU_OP(hw_event_available) -KVM_X86_PMU_OP(pmc_idx_to_pmc) KVM_X86_PMU_OP(rdpmc_ecx_to_pmc) KVM_X86_PMU_OP(msr_idx_to_pmc) -KVM_X86_PMU_OP(is_valid_rdpmc_ecx) +KVM_X86_PMU_OP_OPTIONAL(check_rdpmc_early) KVM_X86_PMU_OP(is_valid_msr) KVM_X86_PMU_OP(get_msr) KVM_X86_PMU_OP(set_msr) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index b7a539ea29..6efd1497b0 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -536,6 +536,7 @@ struct kvm_pmc { #define KVM_PMC_MAX_FIXED 3 #define MSR_ARCH_PERFMON_FIXED_CTR_MAX (MSR_ARCH_PERFMON_FIXED_CTR0 + KVM_PMC_MAX_FIXED - 1) #define KVM_AMD_PMC_MAX_GENERIC 6 + struct kvm_pmu { u8 version; unsigned nr_arch_gp_counters; @@ -1469,6 +1470,15 @@ struct kvm_arch { */ bool shadow_root_allocated; +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING + /* + * If set, the VM has (or had) an external write tracking user, and + * thus all write tracking metadata has been allocated, even if KVM + * itself isn't using write tracking. + */ + bool external_write_tracking_enabled; +#endif + #if IS_ENABLED(CONFIG_HYPERV) hpa_t hv_root_tdp; spinlock_t hv_root_tdp_lock; @@ -1666,7 +1676,8 @@ struct kvm_x86_ops { void (*flush_tlb_guest)(struct kvm_vcpu *vcpu); int (*vcpu_pre_run)(struct kvm_vcpu *vcpu); - enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu); + enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu, + bool force_immediate_exit); int (*handle_exit)(struct kvm_vcpu *vcpu, enum exit_fastpath_completion exit_fastpath); int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu); @@ -1734,8 +1745,6 @@ struct kvm_x86_ops { struct x86_exception *exception); void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu); - void (*request_immediate_exit)(struct kvm_vcpu *vcpu); - void (*sched_in)(struct kvm_vcpu *vcpu, int cpu); /* @@ -1797,6 +1806,7 @@ struct kvm_x86_ops { unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu); gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); + void *(*alloc_apic_backing_page)(struct kvm_vcpu *vcpu); }; struct kvm_x86_nested_ops { @@ -1882,8 +1892,16 @@ static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, } #endif /* CONFIG_HYPERV */ +enum kvm_intr_type { + /* Values are arbitrary, but must be non-zero. */ + KVM_HANDLING_IRQ = 1, + KVM_HANDLING_NMI, +}; + +/* Enable perf NMI and timer modes to work, and minimise false positives. */ #define kvm_arch_pmi_in_guest(vcpu) \ - ((vcpu) && (vcpu)->arch.handling_intr_from_guest) + ((vcpu) && (vcpu)->arch.handling_intr_from_guest && \ + (!!in_nmi() == ((vcpu)->arch.handling_intr_from_guest == KVM_HANDLING_NMI))) void __init kvm_mmu_x86_module_init(void); int kvm_mmu_vendor_module_init(void); @@ -2048,7 +2066,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8); int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val); -void kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val); +unsigned long kvm_get_dr(struct kvm_vcpu *vcpu, int dr); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu); @@ -2241,7 +2259,6 @@ extern bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu); int kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err); -void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu); void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size); diff --git a/arch/x86/include/asm/kvmclock.h b/arch/x86/include/asm/kvmclock.h index 511b350691..f163176d6f 100644 --- a/arch/x86/include/asm/kvmclock.h +++ b/arch/x86/include/asm/kvmclock.h @@ -4,8 +4,6 @@ #include <linux/percpu.h> -extern struct clocksource kvm_clock; - DECLARE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu); static __always_inline struct pvclock_vcpu_time_info *this_cpu_pvti(void) diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h index 571fe4d2d2..dc31b13b87 100644 --- a/arch/x86/include/asm/linkage.h +++ b/arch/x86/include/asm/linkage.h @@ -40,27 +40,27 @@ #ifdef __ASSEMBLY__ -#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) #define RET jmp __x86_return_thunk -#else /* CONFIG_RETPOLINE */ -#ifdef CONFIG_SLS +#else /* CONFIG_MITIGATION_RETPOLINE */ +#ifdef CONFIG_MITIGATION_SLS #define RET ret; int3 #else #define RET ret #endif -#endif /* CONFIG_RETPOLINE */ +#endif /* CONFIG_MITIGATION_RETPOLINE */ #else /* __ASSEMBLY__ */ -#if defined(CONFIG_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) +#if defined(CONFIG_MITIGATION_RETHUNK) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO) #define ASM_RET "jmp __x86_return_thunk\n\t" -#else /* CONFIG_RETPOLINE */ -#ifdef CONFIG_SLS +#else /* CONFIG_MITIGATION_RETPOLINE */ +#ifdef CONFIG_MITIGATION_SLS #define ASM_RET "ret; int3\n\t" #else #define ASM_RET "ret\n\t" #endif -#endif /* CONFIG_RETPOLINE */ +#endif /* CONFIG_MITIGATION_RETPOLINE */ #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index 73dba8b944..59aa966dc2 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -131,8 +131,20 @@ static inline bool local_try_cmpxchg(local_t *l, long *old, long new) (typeof(l->a.counter) *) old, new); } -/* Always has a lock prefix */ -#define local_xchg(l, n) (xchg(&((l)->a.counter), (n))) +/* + * Implement local_xchg using CMPXCHG instruction without the LOCK prefix. + * XCHG is expensive due to the implied LOCK prefix. The processor + * cannot prefetch cachelines if XCHG is used. + */ +static __always_inline long +local_xchg(local_t *l, long n) +{ + long c = local_read(l); + + do { } while (!local_try_cmpxchg(l, &c, n)); + + return c; +} /** * local_add_unless - add unless the number is already a given value diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h index 0da5c227f4..ce4677b8b7 100644 --- a/arch/x86/include/asm/mmu.h +++ b/arch/x86/include/asm/mmu.h @@ -75,7 +75,7 @@ typedef struct { .lock = __MUTEX_INITIALIZER(mm.context.lock), \ } -void leave_mm(int cpu); +void leave_mm(void); #define leave_mm leave_mm #endif /* _ASM_X86_MMU_H */ diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index 4b0f98a8d3..c72c7ff78f 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_MPSPEC_H #define _ASM_X86_MPSPEC_H +#include <linux/types.h> #include <asm/mpspec_def.h> #include <asm/x86_init.h> @@ -46,70 +47,31 @@ extern int smp_found_config; # define smp_found_config 0 #endif -static inline void get_smp_config(void) -{ - x86_init.mpparse.get_smp_config(0); -} - -static inline void early_get_smp_config(void) -{ - x86_init.mpparse.get_smp_config(1); -} - -static inline void find_smp_config(void) -{ - x86_init.mpparse.find_smp_config(); -} - #ifdef CONFIG_X86_MPPARSE extern void e820__memblock_alloc_reserved_mpc_new(void); extern int enable_update_mptable; -extern void default_find_smp_config(void); -extern void default_get_smp_config(unsigned int early); +extern void mpparse_find_mptable(void); +extern void mpparse_parse_early_smp_config(void); +extern void mpparse_parse_smp_config(void); #else static inline void e820__memblock_alloc_reserved_mpc_new(void) { } -#define enable_update_mptable 0 -#define default_find_smp_config x86_init_noop -#define default_get_smp_config x86_init_uint_noop +#define enable_update_mptable 0 +#define mpparse_find_mptable x86_init_noop +#define mpparse_parse_early_smp_config x86_init_noop +#define mpparse_parse_smp_config x86_init_noop #endif -int generic_processor_info(int apicid); +extern DECLARE_BITMAP(phys_cpu_present_map, MAX_LOCAL_APIC); -#define PHYSID_ARRAY_SIZE BITS_TO_LONGS(MAX_LOCAL_APIC) - -struct physid_mask { - unsigned long mask[PHYSID_ARRAY_SIZE]; -}; - -typedef struct physid_mask physid_mask_t; - -#define physid_set(physid, map) set_bit(physid, (map).mask) -#define physid_isset(physid, map) test_bit(physid, (map).mask) - -#define physids_or(dst, src1, src2) \ - bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_LOCAL_APIC) - -#define physids_clear(map) \ - bitmap_zero((map).mask, MAX_LOCAL_APIC) - -#define physids_empty(map) \ - bitmap_empty((map).mask, MAX_LOCAL_APIC) - -static inline void physids_promote(unsigned long physids, physid_mask_t *map) +static inline void reset_phys_cpu_present_map(u32 apicid) { - physids_clear(*map); - map->mask[0] = physids; + bitmap_zero(phys_cpu_present_map, MAX_LOCAL_APIC); + set_bit(apicid, phys_cpu_present_map); } -static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map) +static inline void copy_phys_cpu_present_map(unsigned long *dst) { - physids_clear(*map); - physid_set(physid, *map); + bitmap_copy(dst, phys_cpu_present_map, MAX_LOCAL_APIC); } -#define PHYSID_MASK_ALL { {[0 ... PHYSID_ARRAY_SIZE-1] = ~0UL} } -#define PHYSID_MASK_NONE { {[0 ... PHYSID_ARRAY_SIZE-1] = 0UL} } - -extern physid_mask_t phys_cpu_present_map; - #endif /* _ASM_X86_MPSPEC_H */ diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index ce4ce8720d..390c4d1395 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -293,24 +293,24 @@ static inline void hv_ivm_msr_write(u64 msr, u64 value) {} static inline void hv_ivm_msr_read(u64 msr, u64 *value) {} #endif -static inline bool hv_is_synic_reg(unsigned int reg) +static inline bool hv_is_synic_msr(unsigned int reg) { - return (reg >= HV_REGISTER_SCONTROL) && - (reg <= HV_REGISTER_SINT15); + return (reg >= HV_X64_MSR_SCONTROL) && + (reg <= HV_X64_MSR_SINT15); } -static inline bool hv_is_sint_reg(unsigned int reg) +static inline bool hv_is_sint_msr(unsigned int reg) { - return (reg >= HV_REGISTER_SINT0) && - (reg <= HV_REGISTER_SINT15); + return (reg >= HV_X64_MSR_SINT0) && + (reg <= HV_X64_MSR_SINT15); } -u64 hv_get_register(unsigned int reg); -void hv_set_register(unsigned int reg, u64 value); -u64 hv_get_non_nested_register(unsigned int reg); -void hv_set_non_nested_register(unsigned int reg, u64 value); +u64 hv_get_msr(unsigned int reg); +void hv_set_msr(unsigned int reg, u64 value); +u64 hv_get_non_nested_msr(unsigned int reg); +void hv_set_non_nested_msr(unsigned int reg, u64 value); -static __always_inline u64 hv_raw_get_register(unsigned int reg) +static __always_inline u64 hv_raw_get_msr(unsigned int reg) { return __rdmsr(reg); } @@ -331,10 +331,10 @@ static inline int hyperv_flush_guest_mapping_range(u64 as, { return -1; } -static inline void hv_set_register(unsigned int reg, u64 value) { } -static inline u64 hv_get_register(unsigned int reg) { return 0; } -static inline void hv_set_non_nested_register(unsigned int reg, u64 value) { } -static inline u64 hv_get_non_nested_register(unsigned int reg) { return 0; } +static inline void hv_set_msr(unsigned int reg, u64 value) { } +static inline u64 hv_get_msr(unsigned int reg) { return 0; } +static inline void hv_set_non_nested_msr(unsigned int reg, u64 value) { } +static inline u64 hv_get_non_nested_msr(unsigned int reg) { return 0; } #endif /* CONFIG_HYPERV */ diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index d65f8ce6b7..e72c2b8729 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -36,8 +36,19 @@ #define EFER_FFXSR (1<<_EFER_FFXSR) #define EFER_AUTOIBRS (1<<_EFER_AUTOIBRS) -/* Intel MSRs. Some also available on other CPUs */ +/* FRED MSRs */ +#define MSR_IA32_FRED_RSP0 0x1cc /* Level 0 stack pointer */ +#define MSR_IA32_FRED_RSP1 0x1cd /* Level 1 stack pointer */ +#define MSR_IA32_FRED_RSP2 0x1ce /* Level 2 stack pointer */ +#define MSR_IA32_FRED_RSP3 0x1cf /* Level 3 stack pointer */ +#define MSR_IA32_FRED_STKLVLS 0x1d0 /* Exception stack levels */ +#define MSR_IA32_FRED_SSP0 MSR_IA32_PL0_SSP /* Level 0 shadow stack pointer */ +#define MSR_IA32_FRED_SSP1 0x1d1 /* Level 1 shadow stack pointer */ +#define MSR_IA32_FRED_SSP2 0x1d2 /* Level 2 shadow stack pointer */ +#define MSR_IA32_FRED_SSP3 0x1d3 /* Level 3 shadow stack pointer */ +#define MSR_IA32_FRED_CONFIG 0x1d4 /* Entrypoint and interrupt stack level */ +/* Intel MSRs. Some also available on other CPUs */ #define MSR_TEST_CTRL 0x00000033 #define MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT 29 #define MSR_TEST_CTRL_SPLIT_LOCK_DETECT BIT(MSR_TEST_CTRL_SPLIT_LOCK_DETECT_BIT) @@ -609,34 +620,47 @@ #define MSR_AMD64_SEV_ES_GHCB 0xc0010130 #define MSR_AMD64_SEV 0xc0010131 #define MSR_AMD64_SEV_ENABLED_BIT 0 -#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 -#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_ENABLED BIT_ULL(MSR_AMD64_SEV_ENABLED_BIT) +#define MSR_AMD64_SEV_ES_ENABLED_BIT 1 #define MSR_AMD64_SEV_ES_ENABLED BIT_ULL(MSR_AMD64_SEV_ES_ENABLED_BIT) +#define MSR_AMD64_SEV_SNP_ENABLED_BIT 2 #define MSR_AMD64_SEV_SNP_ENABLED BIT_ULL(MSR_AMD64_SEV_SNP_ENABLED_BIT) - -/* SNP feature bits enabled by the hypervisor */ -#define MSR_AMD64_SNP_VTOM BIT_ULL(3) -#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(4) -#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(5) -#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(6) -#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(7) -#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(8) -#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(9) -#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(10) -#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(11) -#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(12) -#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(14) -#define MSR_AMD64_SNP_VMSA_REG_PROTECTION BIT_ULL(16) -#define MSR_AMD64_SNP_SMT_PROTECTION BIT_ULL(17) - -/* SNP feature bits reserved for future use. */ -#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) -#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) -#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, 18) +#define MSR_AMD64_SNP_VTOM_BIT 3 +#define MSR_AMD64_SNP_VTOM BIT_ULL(MSR_AMD64_SNP_VTOM_BIT) +#define MSR_AMD64_SNP_REFLECT_VC_BIT 4 +#define MSR_AMD64_SNP_REFLECT_VC BIT_ULL(MSR_AMD64_SNP_REFLECT_VC_BIT) +#define MSR_AMD64_SNP_RESTRICTED_INJ_BIT 5 +#define MSR_AMD64_SNP_RESTRICTED_INJ BIT_ULL(MSR_AMD64_SNP_RESTRICTED_INJ_BIT) +#define MSR_AMD64_SNP_ALT_INJ_BIT 6 +#define MSR_AMD64_SNP_ALT_INJ BIT_ULL(MSR_AMD64_SNP_ALT_INJ_BIT) +#define MSR_AMD64_SNP_DEBUG_SWAP_BIT 7 +#define MSR_AMD64_SNP_DEBUG_SWAP BIT_ULL(MSR_AMD64_SNP_DEBUG_SWAP_BIT) +#define MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT 8 +#define MSR_AMD64_SNP_PREVENT_HOST_IBS BIT_ULL(MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT) +#define MSR_AMD64_SNP_BTB_ISOLATION_BIT 9 +#define MSR_AMD64_SNP_BTB_ISOLATION BIT_ULL(MSR_AMD64_SNP_BTB_ISOLATION_BIT) +#define MSR_AMD64_SNP_VMPL_SSS_BIT 10 +#define MSR_AMD64_SNP_VMPL_SSS BIT_ULL(MSR_AMD64_SNP_VMPL_SSS_BIT) +#define MSR_AMD64_SNP_SECURE_TSC_BIT 11 +#define MSR_AMD64_SNP_SECURE_TSC BIT_ULL(MSR_AMD64_SNP_SECURE_TSC_BIT) +#define MSR_AMD64_SNP_VMGEXIT_PARAM_BIT 12 +#define MSR_AMD64_SNP_VMGEXIT_PARAM BIT_ULL(MSR_AMD64_SNP_VMGEXIT_PARAM_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT13 BIT_ULL(13) +#define MSR_AMD64_SNP_IBS_VIRT_BIT 14 +#define MSR_AMD64_SNP_IBS_VIRT BIT_ULL(MSR_AMD64_SNP_IBS_VIRT_BIT) +#define MSR_AMD64_SNP_RESERVED_BIT15 BIT_ULL(15) +#define MSR_AMD64_SNP_VMSA_REG_PROT_BIT 16 +#define MSR_AMD64_SNP_VMSA_REG_PROT BIT_ULL(MSR_AMD64_SNP_VMSA_REG_PROT_BIT) +#define MSR_AMD64_SNP_SMT_PROT_BIT 17 +#define MSR_AMD64_SNP_SMT_PROT BIT_ULL(MSR_AMD64_SNP_SMT_PROT_BIT) +#define MSR_AMD64_SNP_RESV_BIT 18 +#define MSR_AMD64_SNP_RESERVED_MASK GENMASK_ULL(63, MSR_AMD64_SNP_RESV_BIT) #define MSR_AMD64_VIRT_SPEC_CTRL 0xc001011f +#define MSR_AMD64_RMP_BASE 0xc0010132 +#define MSR_AMD64_RMP_END 0xc0010133 + /* AMD Collaborative Processor Performance Control MSRs */ #define MSR_AMD_CPPC_CAP1 0xc00102b0 #define MSR_AMD_CPPC_ENABLE 0xc00102b1 @@ -723,8 +747,15 @@ #define MSR_K8_TOP_MEM1 0xc001001a #define MSR_K8_TOP_MEM2 0xc001001d #define MSR_AMD64_SYSCFG 0xc0010010 -#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 +#define MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT 23 #define MSR_AMD64_SYSCFG_MEM_ENCRYPT BIT_ULL(MSR_AMD64_SYSCFG_MEM_ENCRYPT_BIT) +#define MSR_AMD64_SYSCFG_SNP_EN_BIT 24 +#define MSR_AMD64_SYSCFG_SNP_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_EN_BIT) +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT 25 +#define MSR_AMD64_SYSCFG_SNP_VMPL_EN BIT_ULL(MSR_AMD64_SYSCFG_SNP_VMPL_EN_BIT) +#define MSR_AMD64_SYSCFG_MFDM_BIT 19 +#define MSR_AMD64_SYSCFG_MFDM BIT_ULL(MSR_AMD64_SYSCFG_MFDM_BIT) + #define MSR_K8_INT_PENDING_MSG 0xc0010055 /* C1E active bits in int pending message */ #define K8_INTP_C1E_ACTIVE_MASK 0x18000000 diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index 65ec1965cd..d642037f9e 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -12,11 +12,13 @@ #include <uapi/asm/msr.h> #include <asm/shared/msr.h> +#include <linux/percpu.h> + struct msr_info { - u32 msr_no; - struct msr reg; - struct msr *msrs; - int err; + u32 msr_no; + struct msr reg; + struct msr __percpu *msrs; + int err; }; struct msr_regs_info { @@ -97,6 +99,19 @@ static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high) : : "c" (msr), "a"(low), "d" (high) : "memory"); } +/* + * WRMSRNS behaves exactly like WRMSR with the only difference being + * that it is not a serializing instruction by default. + */ +static __always_inline void __wrmsrns(u32 msr, u32 low, u32 high) +{ + /* Instruction opcode for WRMSRNS; supported in binutils >= 2.40. */ + asm volatile("1: .byte 0x0f,0x01,0xc6\n" + "2:\n" + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR) + : : "c" (msr), "a"(low), "d" (high)); +} + #define native_rdmsr(msr, val1, val2) \ do { \ u64 __val = __rdmsr((msr)); \ @@ -297,6 +312,11 @@ do { \ #endif /* !CONFIG_PARAVIRT_XXL */ +static __always_inline void wrmsrns(u32 msr, u64 val) +{ + __wrmsrns(msr, val, val >> 32); +} + /* * 64-bit version of wrmsr_safe(): */ @@ -305,8 +325,8 @@ static inline int wrmsrl_safe(u32 msr, u64 val) return wrmsr_safe(msr, (u32)val, (u32)(val >> 32)); } -struct msr *msrs_alloc(void); -void msrs_free(struct msr *msrs); +struct msr __percpu *msrs_alloc(void); +void msrs_free(struct msr __percpu *msrs); int msr_set_bit(u32 msr, u8 bit); int msr_clear_bit(u32 msr, u8 bit); @@ -315,8 +335,8 @@ int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q); -void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); -void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs); +void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs); +void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs); int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h); int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h); int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q); @@ -345,14 +365,14 @@ static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q) return 0; } static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no, - struct msr *msrs) + struct msr __percpu *msrs) { - rdmsr_on_cpu(0, msr_no, &(msrs[0].l), &(msrs[0].h)); + rdmsr_on_cpu(0, msr_no, raw_cpu_ptr(&msrs->l), raw_cpu_ptr(&msrs->h)); } static inline void wrmsr_on_cpus(const struct cpumask *m, u32 msr_no, - struct msr *msrs) + struct msr __percpu *msrs) { - wrmsr_on_cpu(0, msr_no, msrs[0].l, msrs[0].h); + wrmsr_on_cpu(0, msr_no, raw_cpu_read(msrs->l), raw_cpu_read(msrs->h)); } static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 5c5f1e56c4..41a0ebb699 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -14,9 +14,6 @@ extern void release_perfctr_nmi(unsigned int); extern int reserve_evntsel_nmi(unsigned int); extern void release_evntsel_nmi(unsigned int); -struct ctl_table; -extern int proc_nmi_enabled(struct ctl_table *, int , - void __user *, size_t *, loff_t *); extern int unknown_nmi_panic; #endif /* CONFIG_X86_LOCAL_APIC */ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 3ff081a74a..ff5f1ecc7d 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -59,13 +59,13 @@ #ifdef CONFIG_CALL_THUNKS_DEBUG # define CALL_THUNKS_DEBUG_INC_CALLS \ - incq %gs:__x86_call_count; + incq PER_CPU_VAR(__x86_call_count); # define CALL_THUNKS_DEBUG_INC_RETS \ - incq %gs:__x86_ret_count; + incq PER_CPU_VAR(__x86_ret_count); # define CALL_THUNKS_DEBUG_INC_STUFFS \ - incq %gs:__x86_stuffs_count; + incq PER_CPU_VAR(__x86_stuffs_count); # define CALL_THUNKS_DEBUG_INC_CTXSW \ - incq %gs:__x86_ctxsw_count; + incq PER_CPU_VAR(__x86_ctxsw_count); #else # define CALL_THUNKS_DEBUG_INC_CALLS # define CALL_THUNKS_DEBUG_INC_RETS @@ -73,16 +73,13 @@ # define CALL_THUNKS_DEBUG_INC_CTXSW #endif -#if defined(CONFIG_CALL_DEPTH_TRACKING) && !defined(COMPILE_OFFSETS) +#if defined(CONFIG_MITIGATION_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 \ xor %eax, %eax; \ bts $63, %rax; \ @@ -95,20 +92,14 @@ 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 +#define INCREMENT_CALL_DEPTH #endif /* @@ -158,7 +149,7 @@ jnz 771b; \ /* barrier for jnz misprediction */ \ lfence; \ - ASM_CREDIT_CALL_DEPTH \ + CREDIT_CALL_DEPTH \ CALL_THUNKS_DEBUG_INC_CTXSW #else /* @@ -212,7 +203,7 @@ */ .macro VALIDATE_UNRET_END #if defined(CONFIG_NOINSTR_VALIDATION) && \ - (defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO)) + (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) ANNOTATE_RETPOLINE_SAFE nop #endif @@ -241,7 +232,7 @@ * instruction irrespective of kCFI. */ .macro JMP_NOSPEC reg:req -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE __CS_PREFIX \reg jmp __x86_indirect_thunk_\reg #else @@ -251,7 +242,7 @@ .endm .macro CALL_NOSPEC reg:req -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE __CS_PREFIX \reg call __x86_indirect_thunk_\reg #else @@ -280,7 +271,7 @@ * kernel can support nested alternatives with arbitrary nesting. */ .macro CALL_UNTRAIN_RET -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) +#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO) ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \ "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS #endif @@ -298,7 +289,7 @@ * where we have a stack but before any RET instruction. */ .macro __UNTRAIN_RET ibpb_feature, call_depth_insns -#if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_IBPB_ENTRY) +#if defined(CONFIG_MITIGATION_RETHUNK) || defined(CONFIG_MITIGATION_IBPB_ENTRY) VALIDATE_UNRET_END CALL_UNTRAIN_RET ALTERNATIVE_2 "", \ @@ -318,9 +309,9 @@ .macro CALL_DEPTH_ACCOUNT -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING ALTERNATIVE "", \ - __stringify(ASM_INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH + __stringify(INCREMENT_CALL_DEPTH), X86_FEATURE_CALL_DEPTH #endif .endm @@ -361,13 +352,13 @@ 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[]; -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK extern void __x86_return_thunk(void); #else static inline void __x86_return_thunk(void) {} #endif -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY extern void retbleed_return_thunk(void); #else static inline void retbleed_return_thunk(void) {} @@ -375,7 +366,7 @@ static inline void retbleed_return_thunk(void) {} extern void srso_alias_untrain_ret(void); -#ifdef CONFIG_CPU_SRSO +#ifdef CONFIG_MITIGATION_SRSO extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); #else @@ -396,7 +387,9 @@ extern void clear_bhb_loop(void); extern void (*x86_return_thunk)(void); -#ifdef CONFIG_CALL_DEPTH_TRACKING +extern void __warn_thunk(void); + +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING extern void call_depth_return_thunk(void); #define CALL_DEPTH_ACCOUNT \ @@ -410,14 +403,14 @@ DECLARE_PER_CPU(u64, __x86_ret_count); DECLARE_PER_CPU(u64, __x86_stuffs_count); DECLARE_PER_CPU(u64, __x86_ctxsw_count); #endif -#else /* !CONFIG_CALL_DEPTH_TRACKING */ +#else /* !CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ static inline void call_depth_return_thunk(void) {} #define CALL_DEPTH_ACCOUNT "" -#endif /* CONFIG_CALL_DEPTH_TRACKING */ +#endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE #define GEN(reg) \ extern retpoline_thunk_t __x86_indirect_thunk_ ## reg; @@ -438,7 +431,7 @@ static inline void call_depth_return_thunk(void) {} /* * Inline asm uses the %V modifier which is only in newer GCC - * which is ensured when CONFIG_RETPOLINE is defined. + * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined. */ # define CALL_NOSPEC \ ALTERNATIVE_2( \ diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h index 86bd4311da..9da9c8a2f1 100644 --- a/arch/x86/include/asm/page_types.h +++ b/arch/x86/include/asm/page_types.h @@ -7,7 +7,7 @@ #include <linux/mem_encrypt.h> /* PAGE_SHIFT determines the page size */ -#define PAGE_SHIFT 12 +#define PAGE_SHIFT CONFIG_PAGE_SHIFT #define PAGE_SIZE (_AC(1,UL) << PAGE_SHIFT) #define PAGE_MASK (~(PAGE_SIZE-1)) diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index b40c462b4a..b3ab80a033 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -10,7 +10,6 @@ #include <linux/numa.h> #include <asm/io.h> #include <asm/memtype.h> -#include <asm/x86_init.h> struct pci_sysdata { int domain; /* PCI domain */ @@ -124,16 +123,4 @@ cpumask_of_pcibus(const struct pci_bus *bus) } #endif -struct pci_setup_rom { - struct setup_data data; - uint16_t vendor; - uint16_t devid; - uint64_t pcilen; - unsigned long segment; - unsigned long bus; - unsigned long device; - unsigned long function; - uint8_t romdata[]; -}; - #endif /* _ASM_X86_PCI_H */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 5e01883eb5..ce5111cec3 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -4,17 +4,21 @@ #ifdef CONFIG_X86_64 #define __percpu_seg gs +#define __percpu_rel (%rip) #else #define __percpu_seg fs +#define __percpu_rel #endif #ifdef __ASSEMBLY__ #ifdef CONFIG_SMP -#define PER_CPU_VAR(var) %__percpu_seg:var -#else /* ! SMP */ -#define PER_CPU_VAR(var) var -#endif /* SMP */ +#define __percpu %__percpu_seg: +#else +#define __percpu +#endif + +#define PER_CPU_VAR(var) __percpu(var)__percpu_rel #ifdef CONFIG_X86_64_SMP #define INIT_PER_CPU_VAR(var) init_per_cpu__##var @@ -24,30 +28,78 @@ #else /* ...!ASSEMBLY */ +#include <linux/build_bug.h> #include <linux/stringify.h> #include <asm/asm.h> #ifdef CONFIG_SMP + +#ifdef CONFIG_CC_HAS_NAMED_AS + +#ifdef __CHECKER__ +#define __seg_gs __attribute__((address_space(__seg_gs))) +#define __seg_fs __attribute__((address_space(__seg_fs))) +#endif + +#ifdef CONFIG_X86_64 +#define __percpu_seg_override __seg_gs +#else +#define __percpu_seg_override __seg_fs +#endif + +#define __percpu_prefix "" + +#else /* CONFIG_CC_HAS_NAMED_AS */ + +#define __percpu_seg_override #define __percpu_prefix "%%"__stringify(__percpu_seg)":" + +#endif /* CONFIG_CC_HAS_NAMED_AS */ + +#define __force_percpu_prefix "%%"__stringify(__percpu_seg)":" #define __my_cpu_offset this_cpu_read(this_cpu_off) +#ifdef CONFIG_X86_64 +#define __raw_my_cpu_offset raw_cpu_read_8(this_cpu_off); +#else +#define __raw_my_cpu_offset raw_cpu_read_4(this_cpu_off); +#endif + /* * Compared to the generic __my_cpu_offset version, the following * saves one instruction and avoids clobbering a temp register. + * + * arch_raw_cpu_ptr should not be used in 32-bit VDSO for a 64-bit + * kernel, because games are played with CONFIG_X86_64 there and + * sizeof(this_cpu_off) becames 4. */ -#define arch_raw_cpu_ptr(ptr) \ -({ \ - unsigned long tcp_ptr__; \ - asm ("add " __percpu_arg(1) ", %0" \ - : "=r" (tcp_ptr__) \ - : "m" (this_cpu_off), "0" (ptr)); \ - (typeof(*(ptr)) __kernel __force *)tcp_ptr__; \ +#ifndef BUILD_VDSO32_64 +#define arch_raw_cpu_ptr(_ptr) \ +({ \ + unsigned long tcp_ptr__ = __raw_my_cpu_offset; \ + tcp_ptr__ += (__force unsigned long)(_ptr); \ + (typeof(*(_ptr)) __kernel __force *)tcp_ptr__; \ }) #else -#define __percpu_prefix "" +#define arch_raw_cpu_ptr(_ptr) ({ BUILD_BUG(); (typeof(_ptr))0; }) #endif +#define PER_CPU_VAR(var) %__percpu_seg:(var)__percpu_rel + +#else /* CONFIG_SMP */ +#define __percpu_seg_override +#define __percpu_prefix "" +#define __force_percpu_prefix "" + +#define PER_CPU_VAR(var) (var)__percpu_rel + +#endif /* CONFIG_SMP */ + +#define __my_cpu_type(var) typeof(var) __percpu_seg_override +#define __my_cpu_ptr(ptr) (__my_cpu_type(*ptr)*)(__force uintptr_t)(ptr) +#define __my_cpu_var(var) (*__my_cpu_ptr(&(var))) #define __percpu_arg(x) __percpu_prefix "%" #x +#define __force_percpu_arg(x) __force_percpu_prefix "%" #x /* * Initialized pointers to per-cpu variables needed for the boot @@ -107,14 +159,14 @@ do { \ (void)pto_tmp__; \ } \ asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var])) \ - : [var] "+m" (_var) \ + : [var] "+m" (__my_cpu_var(_var)) \ : [val] __pcpu_reg_imm_##size(pto_val__)); \ } while (0) #define percpu_unary_op(size, qual, op, _var) \ ({ \ asm qual (__pcpu_op1_##size(op, __percpu_arg([var])) \ - : [var] "+m" (_var)); \ + : [var] "+m" (__my_cpu_var(_var))); \ }) /* @@ -144,16 +196,16 @@ do { \ __pcpu_type_##size pfo_val__; \ asm qual (__pcpu_op2_##size(op, __percpu_arg([var]), "%[val]") \ : [val] __pcpu_reg_##size("=", pfo_val__) \ - : [var] "m" (_var)); \ + : [var] "m" (__my_cpu_var(_var))); \ (typeof(_var))(unsigned long) pfo_val__; \ }) #define percpu_stable_op(size, op, _var) \ ({ \ __pcpu_type_##size pfo_val__; \ - asm(__pcpu_op2_##size(op, __percpu_arg(P[var]), "%[val]") \ + asm(__pcpu_op2_##size(op, __force_percpu_arg(a[var]), "%[val]") \ : [val] __pcpu_reg_##size("=", pfo_val__) \ - : [var] "p" (&(_var))); \ + : [var] "i" (&(_var))); \ (typeof(_var))(unsigned long) pfo_val__; \ }) @@ -166,7 +218,7 @@ do { \ asm qual (__pcpu_op2_##size("xadd", "%[tmp]", \ __percpu_arg([var])) \ : [tmp] __pcpu_reg_##size("+", paro_tmp__), \ - [var] "+m" (_var) \ + [var] "+m" (__my_cpu_var(_var)) \ : : "memory"); \ (typeof(_var))(unsigned long) (paro_tmp__ + _val); \ }) @@ -187,7 +239,7 @@ do { \ __percpu_arg([var])) \ "\n\tjnz 1b" \ : [oval] "=&a" (pxo_old__), \ - [var] "+m" (_var) \ + [var] "+m" (__my_cpu_var(_var)) \ : [nval] __pcpu_reg_##size(, pxo_new__) \ : "memory"); \ (typeof(_var))(unsigned long) pxo_old__; \ @@ -204,7 +256,7 @@ do { \ asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]", \ __percpu_arg([var])) \ : [oval] "+a" (pco_old__), \ - [var] "+m" (_var) \ + [var] "+m" (__my_cpu_var(_var)) \ : [nval] __pcpu_reg_##size(, pco_new__) \ : "memory"); \ (typeof(_var))(unsigned long) pco_old__; \ @@ -221,7 +273,7 @@ do { \ CC_SET(z) \ : CC_OUT(z) (success), \ [oval] "+a" (pco_old__), \ - [var] "+m" (_var) \ + [var] "+m" (__my_cpu_var(_var)) \ : [nval] __pcpu_reg_##size(, pco_new__) \ : "memory"); \ if (unlikely(!success)) \ @@ -244,7 +296,7 @@ do { \ \ asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \ "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \ - : [var] "+m" (_var), \ + : [var] "+m" (__my_cpu_var(_var)), \ "+a" (old__.low), \ "+d" (old__.high) \ : "b" (new__.low), \ @@ -276,7 +328,7 @@ do { \ "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \ CC_SET(z) \ : CC_OUT(z) (success), \ - [var] "+m" (_var), \ + [var] "+m" (__my_cpu_var(_var)), \ "+a" (old__.low), \ "+d" (old__.high) \ : "b" (new__.low), \ @@ -313,7 +365,7 @@ do { \ \ asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \ "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \ - : [var] "+m" (_var), \ + : [var] "+m" (__my_cpu_var(_var)), \ "+a" (old__.low), \ "+d" (old__.high) \ : "b" (new__.low), \ @@ -345,7 +397,7 @@ do { \ "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \ CC_SET(z) \ : CC_OUT(z) (success), \ - [var] "+m" (_var), \ + [var] "+m" (__my_cpu_var(_var)), \ "+a" (old__.low), \ "+d" (old__.high) \ : "b" (new__.low), \ @@ -366,9 +418,9 @@ do { \ * accessed while this_cpu_read_stable() allows the value to be cached. * this_cpu_read_stable() is more efficient and can be used if its value * is guaranteed to be valid across cpus. The current users include - * get_current() and get_thread_info() both of which are actually - * per-thread variables implemented as per-cpu variables and thus - * stable for the duration of the respective task. + * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are + * actually per-thread variables implemented as per-CPU variables and + * thus stable for the duration of the respective task. */ #define this_cpu_read_stable_1(pcp) percpu_stable_op(1, "mov", pcp) #define this_cpu_read_stable_2(pcp) percpu_stable_op(2, "mov", pcp) @@ -376,13 +428,72 @@ do { \ #define this_cpu_read_stable_8(pcp) percpu_stable_op(8, "mov", pcp) #define this_cpu_read_stable(pcp) __pcpu_size_call_return(this_cpu_read_stable_, pcp) +#ifdef CONFIG_USE_X86_SEG_SUPPORT + +#define __raw_cpu_read(qual, pcp) \ +({ \ + *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)); \ +}) + +#define __raw_cpu_write(qual, pcp, val) \ +do { \ + *(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)) = (val); \ +} while (0) + +#define raw_cpu_read_1(pcp) __raw_cpu_read(, pcp) +#define raw_cpu_read_2(pcp) __raw_cpu_read(, pcp) +#define raw_cpu_read_4(pcp) __raw_cpu_read(, pcp) +#define raw_cpu_write_1(pcp, val) __raw_cpu_write(, pcp, val) +#define raw_cpu_write_2(pcp, val) __raw_cpu_write(, pcp, val) +#define raw_cpu_write_4(pcp, val) __raw_cpu_write(, pcp, val) + +#define this_cpu_read_1(pcp) __raw_cpu_read(volatile, pcp) +#define this_cpu_read_2(pcp) __raw_cpu_read(volatile, pcp) +#define this_cpu_read_4(pcp) __raw_cpu_read(volatile, pcp) +#define this_cpu_write_1(pcp, val) __raw_cpu_write(volatile, pcp, val) +#define this_cpu_write_2(pcp, val) __raw_cpu_write(volatile, pcp, val) +#define this_cpu_write_4(pcp, val) __raw_cpu_write(volatile, pcp, val) + +#ifdef CONFIG_X86_64 +#define raw_cpu_read_8(pcp) __raw_cpu_read(, pcp) +#define raw_cpu_write_8(pcp, val) __raw_cpu_write(, pcp, val) + +#define this_cpu_read_8(pcp) __raw_cpu_read(volatile, pcp) +#define this_cpu_write_8(pcp, val) __raw_cpu_write(volatile, pcp, val) +#endif + +#define this_cpu_read_const(pcp) __raw_cpu_read(, pcp) +#else /* CONFIG_USE_X86_SEG_SUPPORT */ + #define raw_cpu_read_1(pcp) percpu_from_op(1, , "mov", pcp) #define raw_cpu_read_2(pcp) percpu_from_op(2, , "mov", pcp) #define raw_cpu_read_4(pcp) percpu_from_op(4, , "mov", pcp) - #define raw_cpu_write_1(pcp, val) percpu_to_op(1, , "mov", (pcp), val) #define raw_cpu_write_2(pcp, val) percpu_to_op(2, , "mov", (pcp), val) #define raw_cpu_write_4(pcp, val) percpu_to_op(4, , "mov", (pcp), val) + +#define this_cpu_read_1(pcp) percpu_from_op(1, volatile, "mov", pcp) +#define this_cpu_read_2(pcp) percpu_from_op(2, volatile, "mov", pcp) +#define this_cpu_read_4(pcp) percpu_from_op(4, volatile, "mov", pcp) +#define this_cpu_write_1(pcp, val) percpu_to_op(1, volatile, "mov", (pcp), val) +#define this_cpu_write_2(pcp, val) percpu_to_op(2, volatile, "mov", (pcp), val) +#define this_cpu_write_4(pcp, val) percpu_to_op(4, volatile, "mov", (pcp), val) + +#ifdef CONFIG_X86_64 +#define raw_cpu_read_8(pcp) percpu_from_op(8, , "mov", pcp) +#define raw_cpu_write_8(pcp, val) percpu_to_op(8, , "mov", (pcp), val) + +#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp) +#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val) +#endif + +/* + * The generic per-cpu infrastrucutre is not suitable for + * reading const-qualified variables. + */ +#define this_cpu_read_const(pcp) ({ BUILD_BUG(); (typeof(pcp))0; }) +#endif /* CONFIG_USE_X86_SEG_SUPPORT */ + #define raw_cpu_add_1(pcp, val) percpu_add_op(1, , (pcp), val) #define raw_cpu_add_2(pcp, val) percpu_add_op(2, , (pcp), val) #define raw_cpu_add_4(pcp, val) percpu_add_op(4, , (pcp), val) @@ -408,12 +519,6 @@ do { \ #define raw_cpu_xchg_2(pcp, val) raw_percpu_xchg_op(pcp, val) #define raw_cpu_xchg_4(pcp, val) raw_percpu_xchg_op(pcp, val) -#define this_cpu_read_1(pcp) percpu_from_op(1, volatile, "mov", pcp) -#define this_cpu_read_2(pcp) percpu_from_op(2, volatile, "mov", pcp) -#define this_cpu_read_4(pcp) percpu_from_op(4, volatile, "mov", pcp) -#define this_cpu_write_1(pcp, val) percpu_to_op(1, volatile, "mov", (pcp), val) -#define this_cpu_write_2(pcp, val) percpu_to_op(2, volatile, "mov", (pcp), val) -#define this_cpu_write_4(pcp, val) percpu_to_op(4, volatile, "mov", (pcp), val) #define this_cpu_add_1(pcp, val) percpu_add_op(1, volatile, (pcp), val) #define this_cpu_add_2(pcp, val) percpu_add_op(2, volatile, (pcp), val) #define this_cpu_add_4(pcp, val) percpu_add_op(4, volatile, (pcp), val) @@ -452,8 +557,6 @@ do { \ * 32 bit must fall back to generic operations. */ #ifdef CONFIG_X86_64 -#define raw_cpu_read_8(pcp) percpu_from_op(8, , "mov", pcp) -#define raw_cpu_write_8(pcp, val) percpu_to_op(8, , "mov", (pcp), val) #define raw_cpu_add_8(pcp, val) percpu_add_op(8, , (pcp), val) #define raw_cpu_and_8(pcp, val) percpu_to_op(8, , "and", (pcp), val) #define raw_cpu_or_8(pcp, val) percpu_to_op(8, , "or", (pcp), val) @@ -462,8 +565,6 @@ do { \ #define raw_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval) #define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, , pcp, ovalp, nval) -#define this_cpu_read_8(pcp) percpu_from_op(8, volatile, "mov", pcp) -#define this_cpu_write_8(pcp, val) percpu_to_op(8, volatile, "mov", (pcp), val) #define this_cpu_add_8(pcp, val) percpu_add_op(8, volatile, (pcp), val) #define this_cpu_and_8(pcp, val) percpu_to_op(8, volatile, "and", (pcp), val) #define this_cpu_or_8(pcp, val) percpu_to_op(8, volatile, "or", (pcp), val) @@ -494,7 +595,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr, asm volatile("btl "__percpu_arg(2)",%1" CC_SET(c) : CC_OUT(c) (oldbit) - : "m" (*(unsigned long __percpu *)addr), "Ir" (nr)); + : "m" (*__my_cpu_ptr((unsigned long __percpu *)(addr))), "Ir" (nr)); return oldbit; } diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 3736b8a46c..7f1e172505 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -555,6 +555,7 @@ struct x86_pmu_lbr { unsigned int from; unsigned int to; unsigned int info; + bool has_callstack; }; extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap); diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index 94de1a05ae..d65e338b6a 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -181,7 +181,7 @@ static inline u64 p4_clear_ht_bit(u64 config) static inline int p4_ht_active(void) { #ifdef CONFIG_SMP - return smp_num_siblings > 1; + return __max_threads_per_core > 1; #endif return 0; } @@ -189,7 +189,7 @@ static inline int p4_ht_active(void) static inline int p4_ht_thread(int cpu) { #ifdef CONFIG_SMP - if (smp_num_siblings == 2) + if (__max_threads_per_core == 2) return cpu != cpumask_first(this_cpu_cpumask_var_ptr(cpu_sibling_map)); #endif return 0; diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h index c7ec5bb883..dcd836b59b 100644 --- a/arch/x86/include/asm/pgalloc.h +++ b/arch/x86/include/asm/pgalloc.h @@ -34,7 +34,7 @@ static inline void paravirt_release_p4d(unsigned long pfn) {} */ extern gfp_t __userpte_alloc_gfp; -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * Instead of one PGD, we acquire two PGDs. Being order-1, it is * both 8k in size and 8k-aligned. That lets us just flip bit 12 diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h index 9e7c0b719c..dabafba957 100644 --- a/arch/x86/include/asm/pgtable-3level.h +++ b/arch/x86/include/asm/pgtable-3level.h @@ -52,7 +52,7 @@ static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) static inline void native_set_pud(pud_t *pudp, pud_t pud) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd); #endif pxx_xchg64(pud, pudp, native_pud_val(pud)); diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 9d077bca6a..315535ffb2 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -31,7 +31,8 @@ struct seq_file; void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm); void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, bool user); -void ptdump_walk_pgd_level_checkwx(void); +bool ptdump_walk_pgd_level_checkwx(void); +#define ptdump_check_wx ptdump_walk_pgd_level_checkwx void ptdump_walk_user_pgd_level_checkwx(void); /* @@ -41,10 +42,8 @@ void ptdump_walk_user_pgd_level_checkwx(void); #define pgprot_decrypted(prot) __pgprot(cc_mkdec(pgprot_val(prot))) #ifdef CONFIG_DEBUG_WX -#define debug_checkwx() ptdump_walk_pgd_level_checkwx() #define debug_checkwx_user() ptdump_walk_user_pgd_level_checkwx() #else -#define debug_checkwx() do { } while (0) #define debug_checkwx_user() do { } while (0) #endif @@ -252,8 +251,8 @@ static inline unsigned long pgd_pfn(pgd_t pgd) return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT; } -#define p4d_leaf p4d_large -static inline int p4d_large(p4d_t p4d) +#define p4d_leaf p4d_leaf +static inline bool p4d_leaf(p4d_t p4d) { /* No 512 GiB pages yet */ return 0; @@ -261,14 +260,14 @@ static inline int p4d_large(p4d_t p4d) #define pte_page(pte) pfn_to_page(pte_pfn(pte)) -#define pmd_leaf pmd_large -static inline int pmd_large(pmd_t pte) +#define pmd_leaf pmd_leaf +static inline bool pmd_leaf(pmd_t pte) { return pmd_flags(pte) & _PAGE_PSE; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE -/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_large */ +/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_leaf */ static inline int pmd_trans_huge(pmd_t pmd) { return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE; @@ -909,7 +908,7 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size, pmd_t *populate_extra_pmd(unsigned long vaddr); pte_t *populate_extra_pte(unsigned long vaddr); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd); /* @@ -923,12 +922,12 @@ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) return pgd; return __pti_set_user_pgtbl(pgdp, pgd); } -#else /* CONFIG_PAGE_TABLE_ISOLATION */ +#else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { return pgd; } -#endif /* CONFIG_PAGE_TABLE_ISOLATION */ +#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ #endif /* __ASSEMBLY__ */ @@ -956,13 +955,13 @@ static inline int pte_same(pte_t a, pte_t b) return a.pte == b.pte; } -static inline pte_t pte_next_pfn(pte_t pte) +static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) { if (__pte_needs_invert(pte_val(pte))) - return __pte(pte_val(pte) - (1UL << PFN_PTE_SHIFT)); - return __pte(pte_val(pte) + (1UL << PFN_PTE_SHIFT)); + return __pte(pte_val(pte) - (nr << PFN_PTE_SHIFT)); + return __pte(pte_val(pte) + (nr << PFN_PTE_SHIFT)); } -#define pte_next_pfn pte_next_pfn +#define pte_advance_pfn pte_advance_pfn static inline int pte_present(pte_t a) { @@ -1086,8 +1085,8 @@ static inline pmd_t *pud_pgtable(pud_t pud) */ #define pud_page(pud) pfn_to_page(pud_pfn(pud)) -#define pud_leaf pud_large -static inline int pud_large(pud_t pud) +#define pud_leaf pud_leaf +static inline bool pud_leaf(pud_t pud) { return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) == (_PAGE_PSE | _PAGE_PRESENT); @@ -1097,12 +1096,6 @@ static inline int pud_bad(pud_t pud) { return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0; } -#else -#define pud_leaf pud_large -static inline int pud_large(pud_t pud) -{ - return 0; -} #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 @@ -1131,7 +1124,7 @@ static inline int p4d_bad(p4d_t p4d) { unsigned long ignore_flags = _KERNPG_TABLE | _PAGE_USER; - if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (p4d_flags(p4d) & ~ignore_flags) != 0; @@ -1177,7 +1170,7 @@ static inline int pgd_bad(pgd_t pgd) if (!pgtable_l5_enabled()) return 0; - if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + if (IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) ignore_flags |= _PAGE_NX; return (pgd_flags(pgd) & ~ignore_flags) != _KERNPG_TABLE; @@ -1419,12 +1412,12 @@ static inline bool pgdp_maps_userspace(void *__ptr) return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START); } -#define pgd_leaf pgd_large -static inline int pgd_large(pgd_t pgd) { return 0; } +#define pgd_leaf pgd_leaf +static inline bool pgd_leaf(pgd_t pgd) { return false; } -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* - * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages + * All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages * (8k-aligned and 8k in size). The kernel one is at the beginning 4k and * the user one is in the last 4k. To switch between them, you * just need to flip the 12th bit in their addresses. @@ -1469,7 +1462,7 @@ static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) { return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT); } -#endif /* CONFIG_PAGE_TABLE_ISOLATION */ +#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ /* * clone_pgd_range(pgd_t *dst, pgd_t *src, int count); @@ -1484,7 +1477,7 @@ static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp) static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count) { memcpy(dst, src, count * sizeof(pgd_t)); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!static_cpu_has(X86_FEATURE_PTI)) return; /* Clone the user space pgd as well */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 24af25b155..7e9db77231 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -143,7 +143,8 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { pgd_t pgd; - if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { + if (pgtable_l5_enabled() || + !IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) { WRITE_ONCE(*p4dp, p4d); return; } diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 38b54b992f..9053dfe9fa 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -21,9 +21,9 @@ typedef unsigned long pgprotval_t; typedef struct { pteval_t pte; } pte_t; typedef struct { pmdval_t pmd; } pmd_t; -#ifdef CONFIG_X86_5LEVEL extern unsigned int __pgtable_l5_enabled; +#ifdef CONFIG_X86_5LEVEL #ifdef USE_EARLY_PGTABLE_L5 /* * cpu_feature_enabled() is not available in early boot code. diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index af77235fde..919909d8cb 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -91,7 +91,7 @@ static __always_inline void __preempt_count_sub(int val) */ static __always_inline bool __preempt_count_dec_and_test(void) { - return GEN_UNARY_RMWcc("decl", pcpu_hot.preempt_count, e, + return GEN_UNARY_RMWcc("decl", __my_cpu_var(pcpu_hot.preempt_count), e, __percpu_arg([var])); } diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h index d8cccadc83..e5f204b9b3 100644 --- a/arch/x86/include/asm/processor-flags.h +++ b/arch/x86/include/asm/processor-flags.h @@ -51,7 +51,7 @@ #define CR3_NOFLUSH 0 #endif -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION # define X86_CR3_PTI_PCID_USER_BIT 11 #endif diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 5636ad6973..78e51b0d64 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -20,7 +20,6 @@ struct vm86; #include <asm/page.h> #include <asm/pgtable_types.h> #include <asm/percpu.h> -#include <asm/msr.h> #include <asm/desc_defs.h> #include <asm/nops.h> #include <asm/special_insns.h> @@ -100,6 +99,9 @@ struct cpuinfo_topology { u32 logical_pkg_id; u32 logical_die_id; + // AMD Node ID and Nodes per Package info + u32 amd_node_id; + // Cache level topology IDs u32 llc_id; u32 l2c_id; @@ -119,8 +121,6 @@ struct cpuinfo_x86 { #endif __u8 x86_virt_bits; __u8 x86_phys_bits; - /* CPUID returned core id bits: */ - __u8 x86_coreid_bits; /* Max extended CPUID function supported: */ __u32 extended_cpuid_level; /* Maximum supported CPUID level, -1=no CPUID: */ @@ -148,8 +148,6 @@ struct cpuinfo_x86 { unsigned long loops_per_jiffy; /* protected processor identification number */ u64 ppin; - /* cpuid returned max cores value: */ - u16 x86_max_cores; u16 x86_clflush_size; /* number of cores as seen by the OS: */ u16 booted_cores; @@ -186,13 +184,8 @@ extern struct cpuinfo_x86 new_cpu_data; extern __u32 cpu_caps_cleared[NCAPINTS + NBUGINTS]; extern __u32 cpu_caps_set[NCAPINTS + NBUGINTS]; -#ifdef CONFIG_SMP DECLARE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); #define cpu_data(cpu) per_cpu(cpu_info, cpu) -#else -#define cpu_info boot_cpu_data -#define cpu_data(cpu) boot_cpu_data -#endif extern const struct seq_operations cpuinfo_op; @@ -532,6 +525,9 @@ 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. */ + if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT)) + return this_cpu_read_const(const_pcpu_hot.top_of_stack); + return this_cpu_read_stable(pcpu_hot.top_of_stack); } @@ -554,7 +550,7 @@ static inline void load_sp0(unsigned long sp0) unsigned long __get_wchan(struct task_struct *p); -extern void select_idle_routine(const struct cpuinfo_x86 *c); +extern void select_idle_routine(void); extern void amd_e400_c1e_apic_setup(void); extern unsigned long boot_option_idle_override; @@ -575,28 +571,6 @@ extern void cpu_init(void); extern void cpu_init_exception_handling(void); extern void cr4_init(void); -static inline unsigned long get_debugctlmsr(void) -{ - unsigned long debugctlmsr = 0; - -#ifndef CONFIG_X86_DEBUGCTLMSR - if (boot_cpu_data.x86 < 6) - return 0; -#endif - rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); - - return debugctlmsr; -} - -static inline void update_debugctlmsr(unsigned long debugctlmsr) -{ -#ifndef CONFIG_X86_DEBUGCTLMSR - if (boot_cpu_data.x86 < 6) - return; -#endif - wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr); -} - extern void set_task_blockstep(struct task_struct *task, bool on); /* Boot loader type from the setup header: */ @@ -663,8 +637,10 @@ static __always_inline void prefetchw(const void *x) #else extern unsigned long __end_init_task[]; -#define INIT_THREAD { \ - .sp = (unsigned long)&__end_init_task - sizeof(struct pt_regs), \ +#define INIT_THREAD { \ + .sp = (unsigned long)&__end_init_task - \ + TOP_OF_KERNEL_STACK_PADDING - \ + sizeof(struct pt_regs), \ } extern unsigned long KSTK_ESP(struct task_struct *task); @@ -703,12 +679,10 @@ static inline u32 per_cpu_l2c_id(unsigned int cpu) } #ifdef CONFIG_CPU_SUP_AMD -extern u32 amd_get_nodes_per_socket(void); extern u32 amd_get_highest_perf(void); extern void amd_clear_divider(void); extern void amd_check_microcode(void); #else -static inline u32 amd_get_nodes_per_socket(void) { return 0; } static inline u32 amd_get_highest_perf(void) { return 0; } static inline void amd_clear_divider(void) { } static inline void amd_check_microcode(void) { } diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h index 65dee24206..043758a2e6 100644 --- a/arch/x86/include/asm/prom.h +++ b/arch/x86/include/asm/prom.h @@ -23,11 +23,11 @@ extern int of_ioapic; extern u64 initial_dtb; extern void add_dtb(u64 data); void x86_of_pci_init(void); -void x86_dtb_init(void); +void x86_dtb_parse_smp_config(void); #else static inline void add_dtb(u64 data) { } static inline void x86_of_pci_init(void) { } -static inline void x86_dtb_init(void) { } +static inline void x86_dtb_parse_smp_config(void) { } #define of_ioapic 0 #endif diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h index 07375b476c..ab167c96b9 100644 --- a/arch/x86/include/asm/pti.h +++ b/arch/x86/include/asm/pti.h @@ -3,7 +3,7 @@ #define _ASM_X86_PTI_H #ifndef __ASSEMBLY__ -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION extern void pti_init(void); extern void pti_check_boottime_disable(void); extern void pti_finalize(void); diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h index f4db78b09c..5a83fbd9bc 100644 --- a/arch/x86/include/asm/ptrace.h +++ b/arch/x86/include/asm/ptrace.h @@ -56,18 +56,64 @@ struct pt_regs { #else /* __i386__ */ +struct fred_cs { + /* CS selector */ + u64 cs : 16, + /* Stack level at event time */ + sl : 2, + /* IBT in WAIT_FOR_ENDBRANCH state */ + wfe : 1, + : 45; +}; + +struct fred_ss { + /* SS selector */ + u64 ss : 16, + /* STI state */ + sti : 1, + /* Set if syscall, sysenter or INT n */ + swevent : 1, + /* Event is NMI type */ + nmi : 1, + : 13, + /* Event vector */ + vector : 8, + : 8, + /* Event type */ + type : 4, + : 4, + /* Event was incident to enclave execution */ + enclave : 1, + /* CPU was in long mode */ + lm : 1, + /* + * Nested exception during FRED delivery, not set + * for #DF. + */ + nested : 1, + : 1, + /* + * The length of the instruction causing the event. + * Only set for INTO, INT1, INT3, INT n, SYSCALL + * and SYSENTER. 0 otherwise. + */ + insnlen : 4; +}; + struct pt_regs { -/* - * C ABI says these regs are callee-preserved. They aren't saved on kernel entry - * unless syscall needs a complete, fully filled "struct pt_regs". - */ + /* + * C ABI says these regs are callee-preserved. They aren't saved on + * kernel entry unless syscall needs a complete, fully filled + * "struct pt_regs". + */ unsigned long r15; unsigned long r14; unsigned long r13; unsigned long r12; unsigned long bp; unsigned long bx; -/* These regs are callee-clobbered. Always saved on kernel entry. */ + + /* These regs are callee-clobbered. Always saved on kernel entry. */ unsigned long r11; unsigned long r10; unsigned long r9; @@ -77,18 +123,50 @@ struct pt_regs { unsigned long dx; unsigned long si; unsigned long di; -/* - * On syscall entry, this is syscall#. On CPU exception, this is error code. - * On hw interrupt, it's IRQ number: - */ + + /* + * orig_ax is used on entry for: + * - the syscall number (syscall, sysenter, int80) + * - error_code stored by the CPU on traps and exceptions + * - the interrupt number for device interrupts + * + * A FRED stack frame starts here: + * 1) It _always_ includes an error code; + * + * 2) The return frame for ERET[US] starts here, but + * the content of orig_ax is ignored. + */ unsigned long orig_ax; -/* Return frame for iretq */ + + /* The IRETQ return frame starts here */ unsigned long ip; - unsigned long cs; + + union { + /* CS selector */ + u16 cs; + /* The extended 64-bit data slot containing CS */ + u64 csx; + /* The FRED CS extension */ + struct fred_cs fred_cs; + }; + unsigned long flags; unsigned long sp; - unsigned long ss; -/* top of stack page */ + + union { + /* SS selector */ + u16 ss; + /* The extended 64-bit data slot containing SS */ + u64 ssx; + /* The FRED SS extension */ + struct fred_ss fred_ss; + }; + + /* + * Top of stack on IDT systems, while FRED systems have extra fields + * defined above for storing exception related information, e.g. CR2 or + * DR6. + */ }; #endif /* !__i386__ */ diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h index 255a78d9d9..12dbd2588c 100644 --- a/arch/x86/include/asm/resctrl.h +++ b/arch/x86/include/asm/resctrl.h @@ -7,6 +7,13 @@ #include <linux/sched.h> #include <linux/jump_label.h> +/* + * This value can never be a valid CLOSID, and is used when mapping a + * (closid, rmid) pair to an index and back. On x86 only the RMID is + * needed. The index is a software defined value. + */ +#define X86_RESCTRL_EMPTY_CLOSID ((u32)~0) + /** * struct resctrl_pqr_state - State cache for the PQR MSR * @cur_rmid: The cached Resource Monitoring ID @@ -31,10 +38,47 @@ struct resctrl_pqr_state { DECLARE_PER_CPU(struct resctrl_pqr_state, pqr_state); +extern bool rdt_alloc_capable; +extern bool rdt_mon_capable; + DECLARE_STATIC_KEY_FALSE(rdt_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); +static inline bool resctrl_arch_alloc_capable(void) +{ + return rdt_alloc_capable; +} + +static inline void resctrl_arch_enable_alloc(void) +{ + static_branch_enable_cpuslocked(&rdt_alloc_enable_key); + static_branch_inc_cpuslocked(&rdt_enable_key); +} + +static inline void resctrl_arch_disable_alloc(void) +{ + static_branch_disable_cpuslocked(&rdt_alloc_enable_key); + static_branch_dec_cpuslocked(&rdt_enable_key); +} + +static inline bool resctrl_arch_mon_capable(void) +{ + return rdt_mon_capable; +} + +static inline void resctrl_arch_enable_mon(void) +{ + static_branch_enable_cpuslocked(&rdt_mon_enable_key); + static_branch_inc_cpuslocked(&rdt_enable_key); +} + +static inline void resctrl_arch_disable_mon(void) +{ + static_branch_disable_cpuslocked(&rdt_mon_enable_key); + static_branch_dec_cpuslocked(&rdt_enable_key); +} + /* * __resctrl_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR * @@ -88,12 +132,58 @@ static inline unsigned int resctrl_arch_round_mon_val(unsigned int val) return val * scale; } +static inline void resctrl_arch_set_closid_rmid(struct task_struct *tsk, + u32 closid, u32 rmid) +{ + WRITE_ONCE(tsk->closid, closid); + WRITE_ONCE(tsk->rmid, rmid); +} + +static inline bool resctrl_arch_match_closid(struct task_struct *tsk, u32 closid) +{ + return READ_ONCE(tsk->closid) == closid; +} + +static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored, + u32 rmid) +{ + return READ_ONCE(tsk->rmid) == rmid; +} + static inline void resctrl_sched_in(struct task_struct *tsk) { if (static_branch_likely(&rdt_enable_key)) __resctrl_sched_in(tsk); } +static inline u32 resctrl_arch_system_num_rmid_idx(void) +{ + /* RMID are independent numbers for x86. num_rmid_idx == num_rmid */ + return boot_cpu_data.x86_cache_max_rmid + 1; +} + +static inline void resctrl_arch_rmid_idx_decode(u32 idx, u32 *closid, u32 *rmid) +{ + *rmid = idx; + *closid = X86_RESCTRL_EMPTY_CLOSID; +} + +static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid) +{ + return rmid; +} + +/* x86 can always read an rmid, nothing needs allocating */ +struct rdt_resource; +static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid) +{ + might_sleep(); + return NULL; +}; + +static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid, + void *ctx) { }; + void resctrl_cpu_detect(struct cpuinfo_x86 *c); #else diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 5c83729c8e..e61e68d71c 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -48,7 +48,7 @@ extern unsigned long saved_video_mode; extern void reserve_standard_io_resources(void); extern void i386_reserve_resources(void); extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp); -extern void startup_64_setup_env(unsigned long physbase); +extern void startup_64_setup_gdt_idt(void); extern void early_setup_idt(void); extern void __init do_early_exception(struct pt_regs *regs, int trapnr); diff --git a/arch/x86/include/asm/setup_data.h b/arch/x86/include/asm/setup_data.h new file mode 100644 index 0000000000..77c51111a8 --- /dev/null +++ b/arch/x86/include/asm/setup_data.h @@ -0,0 +1,32 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _ASM_X86_SETUP_DATA_H +#define _ASM_X86_SETUP_DATA_H + +#include <uapi/asm/setup_data.h> + +#ifndef __ASSEMBLY__ + +struct pci_setup_rom { + struct setup_data data; + uint16_t vendor; + uint16_t devid; + uint64_t pcilen; + unsigned long segment; + unsigned long bus; + unsigned long device; + unsigned long function; + uint8_t romdata[]; +}; + +/* kexec external ABI */ +struct efi_setup_data { + u64 fw_vendor; + u64 __unused; + u64 tables; + u64 smbios; + u64 reserved[8]; +}; + +#endif /* __ASSEMBLY__ */ + +#endif /* _ASM_X86_SETUP_DATA_H */ diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 75a5388d40..93ed60080c 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -13,7 +13,6 @@ #include <asm/insn.h> #include <asm/sev-common.h> -#include <asm/bootparam.h> #include <asm/coco.h> #define GHCB_PROTOCOL_MIN 1ULL @@ -22,6 +21,8 @@ #define VMGEXIT() { asm volatile("rep; vmmcall\n\r"); } +struct boot_params; + enum es_result { ES_OK, /* All good */ ES_UNSUPPORTED, /* Requested operation not supported */ @@ -87,9 +88,23 @@ extern bool handle_vc_boot_ghcb(struct pt_regs *regs); /* Software defined (when rFlags.CF = 1) */ #define PVALIDATE_FAIL_NOUPDATE 255 +/* RMUPDATE detected 4K page and 2MB page overlap. */ +#define RMPUPDATE_FAIL_OVERLAP 4 + /* RMP page size */ #define RMP_PG_SIZE_4K 0 #define RMP_PG_SIZE_2M 1 +#define RMP_TO_PG_LEVEL(level) (((level) == RMP_PG_SIZE_4K) ? PG_LEVEL_4K : PG_LEVEL_2M) +#define PG_LEVEL_TO_RMP(level) (((level) == PG_LEVEL_4K) ? RMP_PG_SIZE_4K : RMP_PG_SIZE_2M) + +struct rmp_state { + u64 gpa; + u8 assigned; + u8 pagesize; + u8 immutable; + u8 rsvd; + u32 asid; +} __packed; #define RMPADJUST_VMSA_PAGE_BIT BIT(16) @@ -213,6 +228,7 @@ int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct sn void snp_accept_memory(phys_addr_t start, phys_addr_t end); u64 snp_get_unsupported_features(u64 status); u64 sev_get_status(void); +void sev_show_status(void); #else static inline void sev_es_ist_enter(struct pt_regs *regs) { } static inline void sev_es_ist_exit(void) { } @@ -241,6 +257,33 @@ static inline int snp_issue_guest_request(u64 exit_code, struct snp_req_data *in static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { } static inline u64 snp_get_unsupported_features(u64 status) { return 0; } static inline u64 sev_get_status(void) { return 0; } +static inline void sev_show_status(void) { } +#endif + +#ifdef CONFIG_KVM_AMD_SEV +bool snp_probe_rmptable_info(void); +int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level); +void snp_dump_hva_rmpentry(unsigned long address); +int psmash(u64 pfn); +int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable); +int rmp_make_shared(u64 pfn, enum pg_level level); +void snp_leak_pages(u64 pfn, unsigned int npages); +void kdump_sev_callback(void); +void snp_fixup_e820_tables(void); +#else +static inline bool snp_probe_rmptable_info(void) { return false; } +static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } +static inline void snp_dump_hva_rmpentry(unsigned long address) {} +static inline int psmash(u64 pfn) { return -ENODEV; } +static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, + bool immutable) +{ + return -ENODEV; +} +static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; } +static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} +static inline void kdump_sev_callback(void) { } +static inline void snp_fixup_e820_tables(void) {} #endif #endif diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 4fab2ed454..a35936b512 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -8,9 +8,6 @@ #include <asm/current.h> #include <asm/thread_info.h> -extern int smp_num_siblings; -extern unsigned int num_processors; - DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map); @@ -59,11 +56,6 @@ static inline void stop_other_cpus(void) smp_ops.stop_other_cpus(1); } -static inline void smp_prepare_boot_cpu(void) -{ - smp_ops.smp_prepare_boot_cpu(); -} - static inline void smp_prepare_cpus(unsigned int max_cpus) { smp_ops.smp_prepare_cpus(max_cpus); @@ -110,7 +102,6 @@ void cpu_disable_common(void); void native_smp_prepare_boot_cpu(void); void smp_prepare_cpus_common(void); void native_smp_prepare_cpus(unsigned int max_cpus); -void calculate_max_logical_packages(void); void native_smp_cpus_done(unsigned int max_cpus); int common_cpu_up(unsigned int cpunum, struct task_struct *tidle); int native_kick_ap(unsigned int cpu, struct task_struct *tidle); @@ -174,8 +165,6 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu) } #endif /* CONFIG_SMP */ -extern unsigned disabled_cpus; - #ifdef CONFIG_DEBUG_NMI_SELFTEST extern void nmi_selftest(void); #else diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h index c648502e45..658b690b2c 100644 --- a/arch/x86/include/asm/spec-ctrl.h +++ b/arch/x86/include/asm/spec-ctrl.h @@ -96,4 +96,6 @@ static inline void speculative_store_bypass_ht_init(void) { } extern void speculation_ctrl_update(unsigned long tif); extern void speculation_ctrl_update_current(void); +extern bool itlb_multihit_kvm_mitigation; + #endif diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 09a5461d72..2e9fc5c400 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -2,11 +2,11 @@ #ifndef _ASM_X86_SPECIAL_INSNS_H #define _ASM_X86_SPECIAL_INSNS_H - #ifdef __KERNEL__ - #include <asm/nops.h> #include <asm/processor-flags.h> + +#include <linux/errno.h> #include <linux/irqflags.h> #include <linux/jump_label.h> diff --git a/arch/x86/include/asm/static_call.h b/arch/x86/include/asm/static_call.h index 343b722cca..125c407e2a 100644 --- a/arch/x86/include/asm/static_call.h +++ b/arch/x86/include/asm/static_call.h @@ -46,7 +46,7 @@ #define ARCH_DEFINE_STATIC_CALL_TRAMP(name, func) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, ".byte 0xe9; .long " #func " - (. + 4)") -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK #define ARCH_DEFINE_STATIC_CALL_NULL_TRAMP(name) \ __ARCH_DEFINE_STATIC_CALL_TRAMP(name, "jmp __x86_return_thunk") #else diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 87a7b917d3..728c98175b 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -358,10 +358,10 @@ struct sev_es_save_area { struct vmcb_seg ldtr; struct vmcb_seg idtr; struct vmcb_seg tr; - u64 vmpl0_ssp; - u64 vmpl1_ssp; - u64 vmpl2_ssp; - u64 vmpl3_ssp; + u64 pl0_ssp; + u64 pl1_ssp; + u64 pl2_ssp; + u64 pl3_ssp; u64 u_cet; u8 reserved_0xc8[2]; u8 vmpl; diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index f42dbf17f5..c3bd0c0758 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -70,9 +70,13 @@ static inline void update_task_stack(struct task_struct *task) #ifdef CONFIG_X86_32 this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0); #else - /* Xen PV enters the kernel on the thread stack. */ - if (cpu_feature_enabled(X86_FEATURE_XENPV)) + if (cpu_feature_enabled(X86_FEATURE_FRED)) { + /* WRMSRNS is a baseline feature for FRED. */ + wrmsrns(MSR_IA32_FRED_RSP0, (unsigned long)task_stack_page(task) + THREAD_SIZE); + } else if (cpu_feature_enabled(X86_FEATURE_XENPV)) { + /* Xen PV enters the kernel on the thread stack. */ load_sp0(task_top_of_stack(task)); + } #endif } diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 0b70653a98..345aafbc19 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -15,6 +15,8 @@ extern void text_poke_early(void *addr, const void *opcode, size_t len); +extern void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len); + /* * Clear and restore the kernel write-protection flag on the local CPU. * Allows the kernel to edit read-only pages. diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index d63b029407..12da7dfd5e 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -31,7 +31,9 @@ * In vm86 mode, the hardware frame is much longer still, so add 16 * bytes to make room for the real-mode segments. * - * x86_64 has a fixed-length stack frame. + * x86-64 has a fixed-length stack frame, but it depends on whether + * or not FRED is enabled. Future versions of FRED might make this + * dynamic, but for now it is always 2 words longer. */ #ifdef CONFIG_X86_32 # ifdef CONFIG_VM86 @@ -39,8 +41,12 @@ # else # define TOP_OF_KERNEL_STACK_PADDING 8 # endif -#else -# define TOP_OF_KERNEL_STACK_PADDING 0 +#else /* x86-64 */ +# ifdef CONFIG_X86_FRED +# define TOP_OF_KERNEL_STACK_PADDING (2 * 8) +# else +# define TOP_OF_KERNEL_STACK_PADDING 0 +# endif #endif /* diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 5f87f6b9b0..abe3a8f22c 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -102,6 +102,35 @@ static inline void setup_node_to_cpumask_map(void) { } #include <asm-generic/topology.h> +/* Topology information */ +enum x86_topology_domains { + TOPO_SMT_DOMAIN, + TOPO_CORE_DOMAIN, + TOPO_MODULE_DOMAIN, + TOPO_TILE_DOMAIN, + TOPO_DIE_DOMAIN, + TOPO_DIEGRP_DOMAIN, + TOPO_PKG_DOMAIN, + TOPO_MAX_DOMAIN, +}; + +struct x86_topology_system { + unsigned int dom_shifts[TOPO_MAX_DOMAIN]; + unsigned int dom_size[TOPO_MAX_DOMAIN]; +}; + +extern struct x86_topology_system x86_topo_system; + +static inline unsigned int topology_get_domain_size(enum x86_topology_domains dom) +{ + return x86_topo_system.dom_size[dom]; +} + +static inline unsigned int topology_get_domain_shift(enum x86_topology_domains dom) +{ + return dom == TOPO_SMT_DOMAIN ? 0 : x86_topo_system.dom_shifts[dom - 1]; +} + extern const struct cpumask *cpu_coregroup_mask(int cpu); extern const struct cpumask *cpu_clustergroup_mask(int cpu); @@ -112,7 +141,42 @@ extern const struct cpumask *cpu_clustergroup_mask(int cpu); #define topology_core_id(cpu) (cpu_data(cpu).topo.core_id) #define topology_ppin(cpu) (cpu_data(cpu).ppin) -extern unsigned int __max_die_per_package; +#define topology_amd_node_id(cpu) (cpu_data(cpu).topo.amd_node_id) + +extern unsigned int __max_dies_per_package; +extern unsigned int __max_logical_packages; +extern unsigned int __max_threads_per_core; +extern unsigned int __num_threads_per_package; +extern unsigned int __num_cores_per_package; + +static inline unsigned int topology_max_packages(void) +{ + return __max_logical_packages; +} + +static inline unsigned int topology_max_dies_per_package(void) +{ + return __max_dies_per_package; +} + +static inline unsigned int topology_num_cores_per_package(void) +{ + return __num_cores_per_package; +} + +static inline unsigned int topology_num_threads_per_package(void) +{ + return __num_threads_per_package; +} + +#ifdef CONFIG_X86_LOCAL_APIC +int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level); +#else +static inline int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level) +{ + return 0; +} +#endif #ifdef CONFIG_SMP #define topology_cluster_id(cpu) (cpu_data(cpu).topo.l2c_id) @@ -121,12 +185,11 @@ extern unsigned int __max_die_per_package; #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) #define topology_sibling_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu)) -extern unsigned int __max_logical_packages; -#define topology_max_packages() (__max_logical_packages) -static inline int topology_max_die_per_package(void) +static inline int topology_phys_to_logical_pkg(unsigned int pkg) { - return __max_die_per_package; + return topology_get_logical_id(pkg << x86_topo_system.dom_shifts[TOPO_PKG_DOMAIN], + TOPO_PKG_DOMAIN); } extern int __max_smt_threads; @@ -138,9 +201,12 @@ static inline int topology_max_smt_threads(void) #include <linux/cpu_smt.h> -int topology_update_package_map(unsigned int apicid, unsigned int cpu); -int topology_update_die_map(unsigned int dieid, unsigned int cpu); -int topology_phys_to_logical_pkg(unsigned int pkg); +extern unsigned int __amd_nodes_per_pkg; + +static inline unsigned int topology_amd_nodes_per_pkg(void) +{ + return __amd_nodes_per_pkg; +} extern struct cpumask __cpu_primary_thread_mask; #define cpu_primary_thread_mask ((const struct cpumask *)&__cpu_primary_thread_mask) @@ -153,16 +219,12 @@ static inline bool topology_is_primary_thread(unsigned int cpu) { return cpumask_test_cpu(cpu, cpu_primary_thread_mask); } + #else /* CONFIG_SMP */ -#define topology_max_packages() (1) -static inline int -topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; } -static inline int -topology_update_die_map(unsigned int dieid, unsigned int cpu) { return 0; } static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; } -static inline int topology_max_die_per_package(void) { return 1; } static inline int topology_max_smt_threads(void) { return 1; } static inline bool topology_is_primary_thread(unsigned int cpu) { return true; } +static inline unsigned int topology_amd_nodes_per_pkg(void) { return 1; } #endif /* !CONFIG_SMP */ static inline void arch_fix_phys_package_id(int num, u32 slot) diff --git a/arch/x86/include/asm/trap_pf.h b/arch/x86/include/asm/trap_pf.h index afa524325e..a23a7b707b 100644 --- a/arch/x86/include/asm/trap_pf.h +++ b/arch/x86/include/asm/trap_pf.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_TRAP_PF_H #define _ASM_X86_TRAP_PF_H +#include <linux/bits.h> + /* * Page fault error code bits: * @@ -13,16 +15,18 @@ * bit 5 == 1: protection keys block access * bit 6 == 1: shadow stack access fault * bit 15 == 1: SGX MMU page-fault + * bit 31 == 1: fault was due to RMP violation */ enum x86_pf_error_code { - X86_PF_PROT = 1 << 0, - X86_PF_WRITE = 1 << 1, - X86_PF_USER = 1 << 2, - X86_PF_RSVD = 1 << 3, - X86_PF_INSTR = 1 << 4, - X86_PF_PK = 1 << 5, - X86_PF_SHSTK = 1 << 6, - X86_PF_SGX = 1 << 15, + X86_PF_PROT = BIT(0), + X86_PF_WRITE = BIT(1), + X86_PF_USER = BIT(2), + X86_PF_RSVD = BIT(3), + X86_PF_INSTR = BIT(4), + X86_PF_PK = BIT(5), + X86_PF_SHSTK = BIT(6), + X86_PF_SGX = BIT(15), + X86_PF_RMP = BIT(31), }; #endif /* _ASM_X86_TRAP_PF_H */ diff --git a/arch/x86/include/asm/trapnr.h b/arch/x86/include/asm/trapnr.h index f5d2325aa0..8d1154cdf7 100644 --- a/arch/x86/include/asm/trapnr.h +++ b/arch/x86/include/asm/trapnr.h @@ -2,6 +2,18 @@ #ifndef _ASM_X86_TRAPNR_H #define _ASM_X86_TRAPNR_H +/* + * Event type codes used by FRED, Intel VT-x and AMD SVM + */ +#define EVENT_TYPE_EXTINT 0 // External interrupt +#define EVENT_TYPE_RESERVED 1 +#define EVENT_TYPE_NMI 2 // NMI +#define EVENT_TYPE_HWEXC 3 // Hardware originated traps, exceptions +#define EVENT_TYPE_SWINT 4 // INT n +#define EVENT_TYPE_PRIV_SWEXC 5 // INT1 +#define EVENT_TYPE_SWEXC 6 // INTO, INT3 +#define EVENT_TYPE_OTHER 7 // FRED SYSCALL/SYSENTER, VT-x MTF + /* Interrupts/Exceptions */ #define X86_TRAP_DE 0 /* Divide-by-zero */ diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h index 594fce0ca7..405efb3e49 100644 --- a/arch/x86/include/asm/tsc.h +++ b/arch/x86/include/asm/tsc.h @@ -5,8 +5,9 @@ #ifndef _ASM_X86_TSC_H #define _ASM_X86_TSC_H -#include <asm/processor.h> #include <asm/cpufeature.h> +#include <asm/processor.h> +#include <asm/msr.h> /* * Standard way to access the cycle counter. diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 237dc8cdd1..3a7755c1a4 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -78,10 +78,10 @@ extern int __get_user_bad(void); int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ - asm volatile("call __" #fn "_%P4" \ + asm volatile("call __" #fn "_%c[size]" \ : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ - : "0" (ptr), "i" (sizeof(*(ptr)))); \ + : "0" (ptr), [size] "i" (sizeof(*(ptr)))); \ instrument_get_user(__val_gu); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ @@ -177,7 +177,7 @@ extern void __put_user_nocheck_8(void); __chk_user_ptr(__ptr); \ __ptr_pu = __ptr; \ __val_pu = __x; \ - asm volatile("call __" #fn "_%P[size]" \ + asm volatile("call __" #fn "_%c[size]" \ : "=c" (__ret_pu), \ ASM_CALL_CONSTRAINT \ : "0" (__ptr_pu), \ diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h index f2c02e4469..04789f45ab 100644 --- a/arch/x86/include/asm/uaccess_64.h +++ b/arch/x86/include/asm/uaccess_64.h @@ -11,6 +11,7 @@ #include <asm/alternative.h> #include <asm/cpufeatures.h> #include <asm/page.h> +#include <asm/percpu.h> #ifdef CONFIG_ADDRESS_MASKING /* @@ -18,14 +19,10 @@ */ static inline unsigned long __untagged_addr(unsigned long addr) { - /* - * Refer tlbstate_untag_mask directly to avoid RIP-relative relocation - * in alternative instructions. The relocation gets wrong when gets - * copied to the target place. - */ asm (ALTERNATIVE("", - "and %%gs:tlbstate_untag_mask, %[addr]\n\t", X86_FEATURE_LAM) - : [addr] "+r" (addr) : "m" (tlbstate_untag_mask)); + "and " __percpu_arg([mask]) ", %[addr]", X86_FEATURE_LAM) + : [addr] "+r" (addr) + : [mask] "m" (__my_cpu_var(tlbstate_untag_mask))); return addr; } @@ -54,7 +51,7 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm, * half and a user half. When cast to a signed type, user pointers * are positive and kernel pointers are negative. */ -#define valid_user_address(x) ((long)(x) >= 0) +#define valid_user_address(x) ((__force long)(x) >= 0) /* * User pointers can have tag bits on x86-64. This scheme tolerates @@ -87,8 +84,9 @@ static inline bool __access_ok(const void __user *ptr, unsigned long size) if (__builtin_constant_p(size <= PAGE_SIZE) && size <= PAGE_SIZE) { return valid_user_address(ptr); } else { - unsigned long sum = size + (unsigned long)ptr; - return valid_user_address(sum) && sum >= (unsigned long)ptr; + unsigned long sum = size + (__force unsigned long)ptr; + + return valid_user_address(sum) && sum >= (__force unsigned long)ptr; } } #define __access_ok __access_ok diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 0e73616b82..4dba173630 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -17,6 +17,7 @@ #include <linux/types.h> #include <uapi/asm/vmx.h> +#include <asm/trapnr.h> #include <asm/vmxfeatures.h> #define VMCS_CONTROL_BIT(x) BIT(VMX_FEATURE_##x & 0x1f) @@ -374,14 +375,14 @@ enum vmcs_field { #define VECTORING_INFO_DELIVER_CODE_MASK INTR_INFO_DELIVER_CODE_MASK #define VECTORING_INFO_VALID_MASK INTR_INFO_VALID_MASK -#define INTR_TYPE_EXT_INTR (0 << 8) /* external interrupt */ -#define INTR_TYPE_RESERVED (1 << 8) /* reserved */ -#define INTR_TYPE_NMI_INTR (2 << 8) /* NMI */ -#define INTR_TYPE_HARD_EXCEPTION (3 << 8) /* processor exception */ -#define INTR_TYPE_SOFT_INTR (4 << 8) /* software interrupt */ -#define INTR_TYPE_PRIV_SW_EXCEPTION (5 << 8) /* ICE breakpoint - undocumented */ -#define INTR_TYPE_SOFT_EXCEPTION (6 << 8) /* software exception */ -#define INTR_TYPE_OTHER_EVENT (7 << 8) /* other event */ +#define INTR_TYPE_EXT_INTR (EVENT_TYPE_EXTINT << 8) /* external interrupt */ +#define INTR_TYPE_RESERVED (EVENT_TYPE_RESERVED << 8) /* reserved */ +#define INTR_TYPE_NMI_INTR (EVENT_TYPE_NMI << 8) /* NMI */ +#define INTR_TYPE_HARD_EXCEPTION (EVENT_TYPE_HWEXC << 8) /* processor exception */ +#define INTR_TYPE_SOFT_INTR (EVENT_TYPE_SWINT << 8) /* software interrupt */ +#define INTR_TYPE_PRIV_SW_EXCEPTION (EVENT_TYPE_PRIV_SWEXC << 8) /* ICE breakpoint */ +#define INTR_TYPE_SOFT_EXCEPTION (EVENT_TYPE_SWEXC << 8) /* software exception */ +#define INTR_TYPE_OTHER_EVENT (EVENT_TYPE_OTHER << 8) /* other event */ /* GUEST_INTERRUPTIBILITY_INFO flags. */ #define GUEST_INTR_STATE_STI 0x00000001 diff --git a/arch/x86/include/asm/vmxfeatures.h b/arch/x86/include/asm/vmxfeatures.h index c6a7eed039..266daf5b5b 100644 --- a/arch/x86/include/asm/vmxfeatures.h +++ b/arch/x86/include/asm/vmxfeatures.h @@ -25,6 +25,7 @@ #define VMX_FEATURE_EPT_EXECUTE_ONLY ( 0*32+ 17) /* "ept_x_only" EPT entries can be execute only */ #define VMX_FEATURE_EPT_AD ( 0*32+ 18) /* EPT Accessed/Dirty bits */ #define VMX_FEATURE_EPT_1GB ( 0*32+ 19) /* 1GB EPT pages */ +#define VMX_FEATURE_EPT_5LEVEL ( 0*32+ 20) /* 5-level EPT paging */ /* Aggregated APIC features 24-27 */ #define VMX_FEATURE_FLEXPRIORITY ( 0*32+ 24) /* TPR shadow + virt APIC */ diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h index 46b4f1f7f3..e8d7d4941c 100644 --- a/arch/x86/include/asm/word-at-a-time.h +++ b/arch/x86/include/asm/word-at-a-time.h @@ -2,7 +2,8 @@ #ifndef _ASM_WORD_AT_A_TIME_H #define _ASM_WORD_AT_A_TIME_H -#include <linux/kernel.h> +#include <linux/bitops.h> +#include <linux/wordpart.h> /* * This is largely generic for little-endian machines, but the diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 550dcbbbb1..6149eabe20 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -2,8 +2,6 @@ #ifndef _ASM_X86_PLATFORM_H #define _ASM_X86_PLATFORM_H -#include <asm/bootparam.h> - struct ghcb; struct mpc_bus; struct mpc_cpu; @@ -15,13 +13,15 @@ struct irq_domain; /** * struct x86_init_mpparse - platform specific mpparse ops * @setup_ioapic_ids: platform specific ioapic id override - * @find_smp_config: find the smp configuration - * @get_smp_config: get the smp configuration + * @find_mptable: Find MPTABLE early to reserve the memory region + * @early_parse_smp_cfg: Parse the SMP configuration data early before initmem_init() + * @parse_smp_cfg: Parse the SMP configuration data */ struct x86_init_mpparse { void (*setup_ioapic_ids)(void); - void (*find_smp_config)(void); - void (*get_smp_config)(unsigned int early); + void (*find_mptable)(void); + void (*early_parse_smp_cfg)(void); + void (*parse_smp_cfg)(void); }; /** diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index eeea058cf6..9b82eebd7a 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -2,21 +2,7 @@ #ifndef _ASM_X86_BOOTPARAM_H #define _ASM_X86_BOOTPARAM_H -/* setup_data/setup_indirect types */ -#define SETUP_NONE 0 -#define SETUP_E820_EXT 1 -#define SETUP_DTB 2 -#define SETUP_PCI 3 -#define SETUP_EFI 4 -#define SETUP_APPLE_PROPERTIES 5 -#define SETUP_JAILHOUSE 6 -#define SETUP_CC_BLOB 7 -#define SETUP_IMA 8 -#define SETUP_RNG_SEED 9 -#define SETUP_ENUM_MAX SETUP_RNG_SEED - -#define SETUP_INDIRECT (1<<31) -#define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT) +#include <asm/setup_data.h> /* ram_size flags */ #define RAMDISK_IMAGE_START_MASK 0x07FF @@ -49,22 +35,6 @@ #include <asm/ist.h> #include <video/edid.h> -/* extensible setup data list node */ -struct setup_data { - __u64 next; - __u32 type; - __u32 len; - __u8 data[]; -}; - -/* extensible setup indirect data node */ -struct setup_indirect { - __u32 type; - __u32 reserved; /* Reserved, must be set to zero. */ - __u64 len; - __u64 addr; -}; - struct setup_header { __u8 setup_sects; __u16 root_flags; @@ -138,50 +108,10 @@ struct efi_info { #define E820_MAX_ENTRIES_ZEROPAGE 128 /* - * The E820 memory region entry of the boot protocol ABI: - */ -struct boot_e820_entry { - __u64 addr; - __u64 size; - __u32 type; -} __attribute__((packed)); - -/* * Smallest compatible version of jailhouse_setup_data required by this kernel. */ #define JAILHOUSE_SETUP_REQUIRED_VERSION 1 -/* - * The boot loader is passing platform information via this Jailhouse-specific - * setup data structure. - */ -struct jailhouse_setup_data { - struct { - __u16 version; - __u16 compatible_version; - } __attribute__((packed)) hdr; - struct { - __u16 pm_timer_address; - __u16 num_cpus; - __u64 pci_mmconfig_base; - __u32 tsc_khz; - __u32 apic_khz; - __u8 standard_ioapic; - __u8 cpu_ids[255]; - } __attribute__((packed)) v1; - struct { - __u32 flags; - } __attribute__((packed)) v2; -} __attribute__((packed)); - -/* - * IMA buffer setup data information from the previous kernel during kexec - */ -struct ima_setup_data { - __u64 addr; - __u64 size; -} __attribute__((packed)); - /* The so-called "zeropage" */ struct boot_params { struct screen_info screen_info; /* 0x000 */ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index a448d0964f..ef11aa4cab 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -7,6 +7,8 @@ * */ +#include <linux/const.h> +#include <linux/bits.h> #include <linux/types.h> #include <linux/ioctl.h> #include <linux/stddef.h> @@ -40,7 +42,6 @@ #define __KVM_HAVE_IRQ_LINE #define __KVM_HAVE_MSI #define __KVM_HAVE_USER_NMI -#define __KVM_HAVE_GUEST_DEBUG #define __KVM_HAVE_MSIX #define __KVM_HAVE_MCE #define __KVM_HAVE_PIT_STATE2 @@ -49,7 +50,6 @@ #define __KVM_HAVE_DEBUGREGS #define __KVM_HAVE_XSAVE #define __KVM_HAVE_XCRS -#define __KVM_HAVE_READONLY_MEM /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -526,9 +526,301 @@ struct kvm_pmu_event_filter { #define KVM_PMU_EVENT_ALLOW 0 #define KVM_PMU_EVENT_DENY 1 -#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS BIT(0) +#define KVM_PMU_EVENT_FLAG_MASKED_EVENTS _BITUL(0) #define KVM_PMU_EVENT_FLAGS_VALID_MASK (KVM_PMU_EVENT_FLAG_MASKED_EVENTS) +/* for KVM_CAP_MCE */ +struct kvm_x86_mce { + __u64 status; + __u64 addr; + __u64 misc; + __u64 mcg_status; + __u8 bank; + __u8 pad1[7]; + __u64 pad2[3]; +}; + +/* for KVM_CAP_XEN_HVM */ +#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) +#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) +#define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) +#define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) +#define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) +#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) +#define KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE (1 << 7) +#define KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA (1 << 8) + +struct kvm_xen_hvm_config { + __u32 flags; + __u32 msr; + __u64 blob_addr_32; + __u64 blob_addr_64; + __u8 blob_size_32; + __u8 blob_size_64; + __u8 pad2[30]; +}; + +struct kvm_xen_hvm_attr { + __u16 type; + __u16 pad[3]; + union { + __u8 long_mode; + __u8 vector; + __u8 runstate_update_flag; + union { + __u64 gfn; +#define KVM_XEN_INVALID_GFN ((__u64)-1) + __u64 hva; + } shared_info; + struct { + __u32 send_port; + __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */ + __u32 flags; +#define KVM_XEN_EVTCHN_DEASSIGN (1 << 0) +#define KVM_XEN_EVTCHN_UPDATE (1 << 1) +#define KVM_XEN_EVTCHN_RESET (1 << 2) + /* + * Events sent by the guest are either looped back to + * the guest itself (potentially on a different port#) + * or signalled via an eventfd. + */ + union { + struct { + __u32 port; + __u32 vcpu; + __u32 priority; + } port; + struct { + __u32 port; /* Zero for eventfd */ + __s32 fd; + } eventfd; + __u32 padding[4]; + } deliver; + } evtchn; + __u32 xen_version; + __u64 pad[8]; + } u; +}; + + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_ATTR_TYPE_LONG_MODE 0x0 +#define KVM_XEN_ATTR_TYPE_SHARED_INFO 0x1 +#define KVM_XEN_ATTR_TYPE_UPCALL_VECTOR 0x2 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 +#define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ +#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */ +#define KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA 0x6 + +struct kvm_xen_vcpu_attr { + __u16 type; + __u16 pad[3]; + union { + __u64 gpa; +#define KVM_XEN_INVALID_GPA ((__u64)-1) + __u64 hva; + __u64 pad[8]; + struct { + __u64 state; + __u64 state_entry_time; + __u64 time_running; + __u64 time_runnable; + __u64 time_blocked; + __u64 time_offline; + } runstate; + __u32 vcpu_id; + struct { + __u32 port; + __u32 priority; + __u64 expires_ns; + } timer; + __u8 vector; + } u; +}; + +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO 0x0 +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO 0x1 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADDR 0x2 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_CURRENT 0x3 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_DATA 0x4 +#define KVM_XEN_VCPU_ATTR_TYPE_RUNSTATE_ADJUST 0x5 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID 0x6 +#define KVM_XEN_VCPU_ATTR_TYPE_TIMER 0x7 +#define KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR 0x8 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA */ +#define KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA 0x9 + +/* Secure Encrypted Virtualization command */ +enum sev_cmd_id { + /* Guest initialization commands */ + KVM_SEV_INIT = 0, + KVM_SEV_ES_INIT, + /* Guest launch commands */ + KVM_SEV_LAUNCH_START, + KVM_SEV_LAUNCH_UPDATE_DATA, + KVM_SEV_LAUNCH_UPDATE_VMSA, + KVM_SEV_LAUNCH_SECRET, + KVM_SEV_LAUNCH_MEASURE, + KVM_SEV_LAUNCH_FINISH, + /* Guest migration commands (outgoing) */ + KVM_SEV_SEND_START, + KVM_SEV_SEND_UPDATE_DATA, + KVM_SEV_SEND_UPDATE_VMSA, + KVM_SEV_SEND_FINISH, + /* Guest migration commands (incoming) */ + KVM_SEV_RECEIVE_START, + KVM_SEV_RECEIVE_UPDATE_DATA, + KVM_SEV_RECEIVE_UPDATE_VMSA, + KVM_SEV_RECEIVE_FINISH, + /* Guest status and debug commands */ + KVM_SEV_GUEST_STATUS, + KVM_SEV_DBG_DECRYPT, + KVM_SEV_DBG_ENCRYPT, + /* Guest certificates commands */ + KVM_SEV_CERT_EXPORT, + /* Attestation report */ + KVM_SEV_GET_ATTESTATION_REPORT, + /* Guest Migration Extension */ + KVM_SEV_SEND_CANCEL, + + KVM_SEV_NR_MAX, +}; + +struct kvm_sev_cmd { + __u32 id; + __u32 pad0; + __u64 data; + __u32 error; + __u32 sev_fd; +}; + +struct kvm_sev_launch_start { + __u32 handle; + __u32 policy; + __u64 dh_uaddr; + __u32 dh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_launch_update_data { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + + +struct kvm_sev_launch_secret { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_launch_measure { + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_guest_status { + __u32 handle; + __u32 policy; + __u32 state; +}; + +struct kvm_sev_dbg { + __u64 src_uaddr; + __u64 dst_uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_attestation_report { + __u8 mnonce[16]; + __u64 uaddr; + __u32 len; + __u32 pad0; +}; + +struct kvm_sev_send_start { + __u32 policy; + __u32 pad0; + __u64 pdh_cert_uaddr; + __u32 pdh_cert_len; + __u32 pad1; + __u64 plat_certs_uaddr; + __u32 plat_certs_len; + __u32 pad2; + __u64 amd_certs_uaddr; + __u32 amd_certs_len; + __u32 pad3; + __u64 session_uaddr; + __u32 session_len; + __u32 pad4; +}; + +struct kvm_sev_send_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +struct kvm_sev_receive_start { + __u32 handle; + __u32 policy; + __u64 pdh_uaddr; + __u32 pdh_len; + __u32 pad0; + __u64 session_uaddr; + __u32 session_len; + __u32 pad1; +}; + +struct kvm_sev_receive_update_data { + __u64 hdr_uaddr; + __u32 hdr_len; + __u32 pad0; + __u64 guest_uaddr; + __u32 guest_len; + __u32 pad1; + __u64 trans_uaddr; + __u32 trans_len; + __u32 pad2; +}; + +#define KVM_X2APIC_API_USE_32BIT_IDS (1ULL << 0) +#define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK (1ULL << 1) + +struct kvm_hyperv_eventfd { + __u32 conn_id; + __s32 fd; + __u32 flags; + __u32 padding[3]; +}; + +#define KVM_HYPERV_CONN_ID_MASK 0x00ffffff +#define KVM_HYPERV_EVENTFD_DEASSIGN (1 << 0) + /* * Masked event layout. * Bits Description @@ -549,10 +841,10 @@ struct kvm_pmu_event_filter { ((__u64)(!!(exclude)) << 55)) #define KVM_PMU_MASKED_ENTRY_EVENT_SELECT \ - (GENMASK_ULL(7, 0) | GENMASK_ULL(35, 32)) -#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (GENMASK_ULL(63, 56)) -#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (GENMASK_ULL(15, 8)) -#define KVM_PMU_MASKED_ENTRY_EXCLUDE (BIT_ULL(55)) + (__GENMASK_ULL(7, 0) | __GENMASK_ULL(35, 32)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MASK (__GENMASK_ULL(63, 56)) +#define KVM_PMU_MASKED_ENTRY_UMASK_MATCH (__GENMASK_ULL(15, 8)) +#define KVM_PMU_MASKED_ENTRY_EXCLUDE (_BITULL(55)) #define KVM_PMU_MASKED_ENTRY_UMASK_MASK_SHIFT (56) /* for KVM_{GET,SET,HAS}_DEVICE_ATTR */ @@ -560,7 +852,7 @@ struct kvm_pmu_event_filter { #define KVM_VCPU_TSC_OFFSET 0 /* attribute for the TSC offset */ /* x86-specific KVM_EXIT_HYPERCALL flags. */ -#define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) +#define KVM_EXIT_HYPERCALL_LONG_MODE _BITULL(0) #define KVM_X86_DEFAULT_VM 0 #define KVM_X86_SW_PROTECTED_VM 1 diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h index 6e64b27b2c..a1efa7907a 100644 --- a/arch/x86/include/uapi/asm/kvm_para.h +++ b/arch/x86/include/uapi/asm/kvm_para.h @@ -92,7 +92,7 @@ struct kvm_clock_pairing { #define KVM_ASYNC_PF_DELIVERY_AS_INT (1 << 3) /* MSR_KVM_ASYNC_PF_INT */ -#define KVM_ASYNC_PF_VEC_MASK GENMASK(7, 0) +#define KVM_ASYNC_PF_VEC_MASK __GENMASK(7, 0) /* MSR_KVM_MIGRATION_CONTROL */ #define KVM_MIGRATION_READY (1 << 0) @@ -142,7 +142,6 @@ struct kvm_vcpu_pv_apf_data { __u32 token; __u8 pad[56]; - __u32 enabled; }; #define KVM_PV_EOI_BIT 0 diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h index d898432947..f1a4adc782 100644 --- a/arch/x86/include/uapi/asm/processor-flags.h +++ b/arch/x86/include/uapi/asm/processor-flags.h @@ -139,6 +139,13 @@ #define X86_CR4_LAM_SUP_BIT 28 /* LAM for supervisor pointers */ #define X86_CR4_LAM_SUP _BITUL(X86_CR4_LAM_SUP_BIT) +#ifdef __x86_64__ +#define X86_CR4_FRED_BIT 32 /* enable FRED kernel entry */ +#define X86_CR4_FRED _BITUL(X86_CR4_FRED_BIT) +#else +#define X86_CR4_FRED (0) +#endif + /* * x86-64 Task Priority Register, CR8 */ diff --git a/arch/x86/include/uapi/asm/setup_data.h b/arch/x86/include/uapi/asm/setup_data.h new file mode 100644 index 0000000000..b111b0c185 --- /dev/null +++ b/arch/x86/include/uapi/asm/setup_data.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _UAPI_ASM_X86_SETUP_DATA_H +#define _UAPI_ASM_X86_SETUP_DATA_H + +/* setup_data/setup_indirect types */ +#define SETUP_NONE 0 +#define SETUP_E820_EXT 1 +#define SETUP_DTB 2 +#define SETUP_PCI 3 +#define SETUP_EFI 4 +#define SETUP_APPLE_PROPERTIES 5 +#define SETUP_JAILHOUSE 6 +#define SETUP_CC_BLOB 7 +#define SETUP_IMA 8 +#define SETUP_RNG_SEED 9 +#define SETUP_ENUM_MAX SETUP_RNG_SEED + +#define SETUP_INDIRECT (1<<31) +#define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT) + +#ifndef __ASSEMBLY__ + +#include <linux/types.h> + +/* extensible setup data list node */ +struct setup_data { + __u64 next; + __u32 type; + __u32 len; + __u8 data[]; +}; + +/* extensible setup indirect data node */ +struct setup_indirect { + __u32 type; + __u32 reserved; /* Reserved, must be set to zero. */ + __u64 len; + __u64 addr; +}; + +/* + * The E820 memory region entry of the boot protocol ABI: + */ +struct boot_e820_entry { + __u64 addr; + __u64 size; + __u32 type; +} __attribute__((packed)); + +/* + * The boot loader is passing platform information via this Jailhouse-specific + * setup data structure. + */ +struct jailhouse_setup_data { + struct { + __u16 version; + __u16 compatible_version; + } __attribute__((packed)) hdr; + struct { + __u16 pm_timer_address; + __u16 num_cpus; + __u64 pci_mmconfig_base; + __u32 tsc_khz; + __u32 apic_khz; + __u8 standard_ioapic; + __u8 cpu_ids[255]; + } __attribute__((packed)) v1; + struct { + __u32 flags; + } __attribute__((packed)) v2; +} __attribute__((packed)); + +/* + * IMA buffer setup data information from the previous kernel during kexec + */ +struct ima_setup_data { + __u64 addr; + __u64 size; +} __attribute__((packed)); + +#endif /* __ASSEMBLY__ */ + +#endif /* _UAPI_ASM_X86_SETUP_DATA_H */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 0000325ab9..74077694da 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -33,6 +33,7 @@ KASAN_SANITIZE_sev.o := n KCSAN_SANITIZE := n KMSAN_SANITIZE_head$(BITS).o := n KMSAN_SANITIZE_nmi.o := n +KMSAN_SANITIZE_sev.o := n # If instrumentation of the following files is enabled, boot hangs during # first second. @@ -48,6 +49,7 @@ obj-y += platform-quirks.o obj-y += process_$(BITS).o signal.o signal_$(BITS).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 +obj-$(CONFIG_X86_FRED) += fred.o obj-$(CONFIG_MODIFY_LDT_SYSCALL) += ldt.o obj-$(CONFIG_X86_KERNEL_IBT) += ibt_selftest.o obj-y += setup.o x86_init.o i8259.o irqinit.o @@ -98,11 +100,11 @@ obj-$(CONFIG_FTRACE_SYSCALLS) += ftrace.o obj-$(CONFIG_X86_TSC) += trace_clock.o obj-$(CONFIG_TRACING) += trace.o obj-$(CONFIG_RETHOOK) += rethook.o -obj-$(CONFIG_CRASH_CORE) += crash_core_$(BITS).o +obj-$(CONFIG_VMCORE_INFO) += vmcore_info_$(BITS).o obj-$(CONFIG_KEXEC_CORE) += machine_kexec_$(BITS).o -obj-$(CONFIG_KEXEC_CORE) += relocate_kernel_$(BITS).o crash.o +obj-$(CONFIG_KEXEC_CORE) += relocate_kernel_$(BITS).o obj-$(CONFIG_KEXEC_FILE) += kexec-bzimage64.o -obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o +obj-$(CONFIG_CRASH_DUMP) += crash_dump_$(BITS).o crash.o obj-y += kprobes/ obj-$(CONFIG_MODULES) += module.o obj-$(CONFIG_X86_32) += doublefault_32.o diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 85a3ce2a36..4bf82dbd2a 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -164,35 +164,6 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) return 0; } -/** - * acpi_register_lapic - register a local apic and generates a logic cpu number - * @id: local apic id to register - * @acpiid: ACPI id to register - * @enabled: this cpu is enabled or not - * - * Returns the logic cpu number which maps to the local apic - */ -static int acpi_register_lapic(int id, u32 acpiid, u8 enabled) -{ - int cpu; - - if (id >= MAX_LOCAL_APIC) { - pr_info("skipped apicid that is too big\n"); - return -EINVAL; - } - - if (!enabled) { - ++disabled_cpus; - return -EINVAL; - } - - cpu = generic_processor_info(id); - if (cpu >= 0) - early_per_cpu(x86_cpu_to_acpiid, cpu) = acpiid; - - return cpu; -} - static bool __init acpi_is_processor_usable(u32 lapic_flags) { if (lapic_flags & ACPI_MADT_ENABLED) @@ -254,7 +225,7 @@ acpi_parse_x2apic(union acpi_subtable_headers *header, const unsigned long end) return 0; } - acpi_register_lapic(apic_id, processor->uid, enabled); + topology_register_apic(apic_id, processor->uid, enabled); #else pr_warn("x2apic entry ignored\n"); #endif @@ -289,9 +260,9 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) * to not preallocating memory for all NR_CPUS * when we use CPU hotplug. */ - acpi_register_lapic(processor->id, /* APIC ID */ - processor->processor_id, /* ACPI ID */ - processor->lapic_flags & ACPI_MADT_ENABLED); + topology_register_apic(processor->id, /* APIC ID */ + processor->processor_id, /* ACPI ID */ + processor->lapic_flags & ACPI_MADT_ENABLED); has_lapic_cpus = true; return 0; @@ -309,9 +280,9 @@ acpi_parse_sapic(union acpi_subtable_headers *header, const unsigned long end) acpi_table_print_madt_entry(&header->common); - acpi_register_lapic((processor->id << 8) | processor->eid,/* APIC ID */ - processor->processor_id, /* ACPI ID */ - processor->lapic_flags & ACPI_MADT_ENABLED); + topology_register_apic((processor->id << 8) | processor->eid,/* APIC ID */ + processor->processor_id, /* ACPI ID */ + processor->lapic_flags & ACPI_MADT_ENABLED); return 0; } @@ -844,12 +815,10 @@ static int acpi_map_cpu2node(acpi_handle handle, int cpu, int physid) return 0; } -int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, - int *pcpu) +int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id, int *pcpu) { - int cpu; + int cpu = topology_hotplug_apic(physid, acpi_id); - cpu = acpi_register_lapic(physid, acpi_id, ACPI_MADT_ENABLED); if (cpu < 0) { pr_info("Unable to map lapic to logical cpu number\n"); return cpu; @@ -868,15 +837,11 @@ int acpi_unmap_cpu(int cpu) #ifdef CONFIG_ACPI_NUMA set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE); #endif - - per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; - set_cpu_present(cpu, false); - num_processors--; - - return (0); + topology_hotunplug_apic(cpu); + return 0; } EXPORT_SYMBOL(acpi_unmap_cpu); -#endif /* CONFIG_ACPI_HOTPLUG_CPU */ +#endif /* CONFIG_ACPI_HOTPLUG_CPU */ int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base) { diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c index 401808b47a..f3ffd0a3a0 100644 --- a/arch/x86/kernel/acpi/cstate.c +++ b/arch/x86/kernel/acpi/cstate.c @@ -131,8 +131,8 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx) cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); /* Check whether this particular cx_type (in CST) is supported or not */ - cstate_type = ((cx->address >> MWAIT_SUBSTATE_SIZE) & - MWAIT_CSTATE_MASK) + 1; + cstate_type = (((cx->address >> MWAIT_SUBSTATE_SIZE) & + MWAIT_CSTATE_MASK) + 1) & MWAIT_CSTATE_MASK; edx_part = edx >> (cstate_type * MWAIT_SUBSTATE_SIZE); num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK; diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S index d5d8a352ea..94ff83f3d3 100644 --- a/arch/x86/kernel/acpi/wakeup_64.S +++ b/arch/x86/kernel/acpi/wakeup_64.S @@ -17,7 +17,7 @@ * Hooray, we are in Long 64-bit mode (but still running in low memory) */ SYM_FUNC_START(wakeup_long64) - movq saved_magic, %rax + movq saved_magic(%rip), %rax movq $0x123456789abcdef0, %rdx cmpq %rdx, %rax je 2f @@ -33,14 +33,14 @@ SYM_FUNC_START(wakeup_long64) movw %ax, %es movw %ax, %fs movw %ax, %gs - movq saved_rsp, %rsp + movq saved_rsp(%rip), %rsp - movq saved_rbx, %rbx - movq saved_rdi, %rdi - movq saved_rsi, %rsi - movq saved_rbp, %rbp + movq saved_rbx(%rip), %rbx + movq saved_rdi(%rip), %rdi + movq saved_rsi(%rip), %rsi + movq saved_rbp(%rip), %rbp - movq saved_rip, %rax + movq saved_rip(%rip), %rax ANNOTATE_RETPOLINE_SAFE jmp *%rax SYM_FUNC_END(wakeup_long64) @@ -72,11 +72,11 @@ SYM_FUNC_START(do_suspend_lowlevel) movq $.Lresume_point, saved_rip(%rip) - movq %rsp, saved_rsp - movq %rbp, saved_rbp - movq %rbx, saved_rbx - movq %rdi, saved_rdi - movq %rsi, saved_rsi + movq %rsp, saved_rsp(%rip) + movq %rbp, saved_rbp(%rip) + movq %rbx, saved_rbx(%rip) + movq %rdi, saved_rdi(%rip) + movq %rsi, saved_rsi(%rip) addq $8, %rsp movl $3, %edi diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 1d85cb7071..45a280f216 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -45,7 +45,7 @@ EXPORT_SYMBOL_GPL(alternatives_patched); #define DA_ENDBR 0x08 #define DA_SMP 0x10 -static unsigned int __initdata_or_module debug_alternative; +static unsigned int debug_alternative; static int __init debug_alt(char *str) { @@ -133,7 +133,7 @@ const unsigned char * const x86_nops[ASM_NOP_MAX+1] = * each single-byte NOPs). If @len to fill out is > ASM_NOP_MAX, pad with INT3 and * *jump* over instead of executing long and daft NOPs. */ -static void __init_or_module add_nop(u8 *instr, unsigned int len) +static void add_nop(u8 *instr, unsigned int len) { u8 *target = instr + len; @@ -206,7 +206,7 @@ static int skip_nops(u8 *instr, int offset, int len) * Optimize a sequence of NOPs, possibly preceded by an unconditional jump * to the end of the NOP sequence into a single NOP. */ -static bool __init_or_module +static bool __optimize_nops(u8 *instr, size_t len, struct insn *insn, int *next, int *prev, int *target) { int i = *next - insn->length; @@ -335,8 +335,7 @@ bool need_reloc(unsigned long offset, u8 *src, size_t src_len) return (target < src || target > src + src_len); } -static void __init_or_module noinline -apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) +void apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) { int prev, target = 0; @@ -545,7 +544,7 @@ static inline bool is_jcc32(struct insn *insn) return insn->opcode.bytes[0] == 0x0f && (insn->opcode.bytes[1] & 0xf0) == 0x80; } -#if defined(CONFIG_RETPOLINE) && defined(CONFIG_OBJTOOL) +#if defined(CONFIG_MITIGATION_RETPOLINE) && defined(CONFIG_OBJTOOL) /* * CALL/JMP *%\reg @@ -709,8 +708,8 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes) /* * The compiler is supposed to EMIT an INT3 after every unconditional * JMP instruction due to AMD BTC. However, if the compiler is too old - * or SLS isn't enabled, we still need an INT3 after indirect JMPs - * even on Intel. + * or MITIGATION_SLS isn't enabled, we still need an INT3 after + * indirect JMPs even on Intel. */ if (op == JMP32_INSN_OPCODE && i < insn->length) bytes[i++] = INT3_INSN_OPCODE; @@ -770,7 +769,7 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) } } -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK /* * Rewrite the compiler generated return thunk tail-calls. @@ -843,14 +842,14 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) } #else void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } -#endif /* CONFIG_RETHUNK */ +#endif /* CONFIG_MITIGATION_RETHUNK */ -#else /* !CONFIG_RETPOLINE || !CONFIG_OBJTOOL */ +#else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { } void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } -#endif /* CONFIG_RETPOLINE && CONFIG_OBJTOOL */ +#endif /* CONFIG_MITIGATION_RETPOLINE && CONFIG_OBJTOOL */ #ifdef CONFIG_X86_KERNEL_IBT @@ -1805,7 +1804,7 @@ static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm) * restoring the previous mm. */ if (this_cpu_read(cpu_tlbstate_shared.is_lazy)) - leave_mm(smp_processor_id()); + leave_mm(); temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm); switch_mm_irqs_off(NULL, mm, current); diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 053f6dcc6b..027a8c7a2c 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -95,6 +95,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F3) }, {} @@ -214,7 +215,14 @@ out: int amd_smn_read(u16 node, u32 address, u32 *value) { - return __amd_smn_rw(node, address, value, false); + int err = __amd_smn_rw(node, address, value, false); + + if (PCI_POSSIBLE_ERROR(*value)) { + err = -ENODEV; + *value = 0; + } + + return err; } EXPORT_SYMBOL_GPL(amd_smn_read); @@ -386,7 +394,7 @@ struct resource *amd_get_mmconfig_range(struct resource *res) int amd_get_subcaches(int cpu) { - struct pci_dev *link = node_to_amd_nb(topology_die_id(cpu))->link; + struct pci_dev *link = node_to_amd_nb(topology_amd_node_id(cpu))->link; unsigned int mask; if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING)) @@ -400,7 +408,7 @@ int amd_get_subcaches(int cpu) int amd_set_subcaches(int cpu, unsigned long mask) { static unsigned int reset, ban; - struct amd_northbridge *nb = node_to_amd_nb(topology_die_id(cpu)); + struct amd_northbridge *nb = node_to_amd_nb(topology_amd_node_id(cpu)); unsigned int reg; int cuid; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index a04a5163e5..803dcfb0e3 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -19,6 +19,7 @@ #include <linux/kernel_stat.h> #include <linux/mc146818rtc.h> #include <linux/acpi_pmtmr.h> +#include <linux/bitmap.h> #include <linux/clockchips.h> #include <linux/interrupt.h> #include <linux/memblock.h> @@ -67,10 +68,6 @@ #include "local.h" -unsigned int num_processors; - -unsigned disabled_cpus; - /* Processor that is doing the boot up */ u32 boot_cpu_physical_apicid __ro_after_init = BAD_APICID; EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid); @@ -78,18 +75,6 @@ EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid); u8 boot_cpu_apic_version __ro_after_init; /* - * Bitmask of physically existing CPUs: - */ -physid_mask_t phys_cpu_present_map; - -/* - * Processor to be disabled specified by kernel parameter - * disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to - * avoid undefined behaviour caused by sending INIT from AP to BSP. - */ -static u32 disabled_cpu_apicid __ro_after_init = BAD_APICID; - -/* * This variable controls which CPUs receive external NMIs. By default, * external NMIs are delivered only to the BSP. */ @@ -108,14 +93,6 @@ static inline bool apic_accessible(void) return x2apic_mode || apic_mmio_base; } -/* - * Map cpu index to physical APIC ID - */ -DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid, BAD_APICID); -DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid, U32_MAX); -EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid); -EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid); - #ifdef CONFIG_X86_32 /* Local APIC was disabled by the BIOS and enabled by the kernel */ static int enabled_via_apicbase __ro_after_init; @@ -261,16 +238,6 @@ u64 native_apic_icr_read(void) return icr1 | ((u64)icr2 << 32); } -#ifdef CONFIG_X86_32 -/** - * get_physical_broadcast - Get number of physical broadcast IDs - */ -int get_physical_broadcast(void) -{ - return modern_apic() ? 0xff : 0xf; -} -#endif - /** * lapic_get_maxlvt - get the maximum number of local vector table entries */ @@ -1549,9 +1516,6 @@ static void setup_local_APIC(void) apic_write(APIC_ESR, 0); } #endif - /* Validate that the APIC is registered if required */ - BUG_ON(apic->apic_id_registered && !apic->apic_id_registered()); - /* * Intel recommends to set DFR, LDR and TPR before enabling * an APIC. See e.g. "AP-388 82489DX User's Manual" (Intel @@ -1690,8 +1654,6 @@ void apic_ap_setup(void) end_local_APIC_setup(); } -static __init void cpu_set_boot_apic(void); - static __init void apic_read_boot_cpu_id(bool x2apic) { /* @@ -1706,7 +1668,8 @@ static __init void apic_read_boot_cpu_id(bool x2apic) boot_cpu_physical_apicid = read_apic_id(); boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR)); } - cpu_set_boot_apic(); + topology_register_boot_apic(boot_cpu_physical_apicid); + x86_32_probe_bigsmp_early(); } #ifdef CONFIG_X86_X2APIC @@ -2096,7 +2059,6 @@ void __init init_apic_mappings(void) pr_info("APIC: disable apic facility\n"); apic_disable(); } - num_processors = 1; } } @@ -2311,155 +2273,6 @@ void disconnect_bsp_APIC(int virt_wire_setup) apic_write(APIC_LVT1, value); } -/* - * The number of allocated logical CPU IDs. Since logical CPU IDs are allocated - * contiguously, it equals to current allocated max logical CPU ID plus 1. - * All allocated CPU IDs should be in the [0, nr_logical_cpuids) range, - * so the maximum of nr_logical_cpuids is nr_cpu_ids. - * - * NOTE: Reserve 0 for BSP. - */ -static int nr_logical_cpuids = 1; - -/* - * Used to store mapping between logical CPU IDs and APIC IDs. - */ -u32 cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = BAD_APICID, }; - -bool arch_match_cpu_phys_id(int cpu, u64 phys_id) -{ - return phys_id == (u64)cpuid_to_apicid[cpu]; -} - -#ifdef CONFIG_SMP -static void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) -{ - /* Isolate the SMT bit(s) in the APICID and check for 0 */ - u32 mask = (1U << (fls(smp_num_siblings) - 1)) - 1; - - if (smp_num_siblings == 1 || !(apicid & mask)) - cpumask_set_cpu(cpu, &__cpu_primary_thread_mask); -} - -/* - * Due to the utter mess of CPUID evaluation smp_num_siblings is not valid - * during early boot. Initialize the primary thread mask before SMP - * bringup. - */ -static int __init smp_init_primary_thread_mask(void) -{ - unsigned int cpu; - - /* - * XEN/PV provides either none or useless topology information. - * Pretend that all vCPUs are primary threads. - */ - if (xen_pv_domain()) { - cpumask_copy(&__cpu_primary_thread_mask, cpu_possible_mask); - return 0; - } - - for (cpu = 0; cpu < nr_logical_cpuids; cpu++) - cpu_mark_primary_thread(cpu, cpuid_to_apicid[cpu]); - return 0; -} -early_initcall(smp_init_primary_thread_mask); -#else -static inline void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) { } -#endif - -/* - * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids - * and cpuid_to_apicid[] synchronized. - */ -static int allocate_logical_cpuid(int apicid) -{ - int i; - - /* - * cpuid <-> apicid mapping is persistent, so when a cpu is up, - * check if the kernel has allocated a cpuid for it. - */ - for (i = 0; i < nr_logical_cpuids; i++) { - if (cpuid_to_apicid[i] == apicid) - return i; - } - - /* Allocate a new cpuid. */ - if (nr_logical_cpuids >= nr_cpu_ids) { - WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %u reached. " - "Processor %d/0x%x and the rest are ignored.\n", - nr_cpu_ids, nr_logical_cpuids, apicid); - return -EINVAL; - } - - cpuid_to_apicid[nr_logical_cpuids] = apicid; - return nr_logical_cpuids++; -} - -static void cpu_update_apic(int cpu, u32 apicid) -{ -#if defined(CONFIG_SMP) || defined(CONFIG_X86_64) - early_per_cpu(x86_cpu_to_apicid, cpu) = apicid; -#endif - set_cpu_possible(cpu, true); - physid_set(apicid, phys_cpu_present_map); - set_cpu_present(cpu, true); - num_processors++; - - if (system_state != SYSTEM_BOOTING) - cpu_mark_primary_thread(cpu, apicid); -} - -static __init void cpu_set_boot_apic(void) -{ - cpuid_to_apicid[0] = boot_cpu_physical_apicid; - cpu_update_apic(0, boot_cpu_physical_apicid); - x86_32_probe_bigsmp_early(); -} - -int generic_processor_info(int apicid) -{ - int cpu, max = nr_cpu_ids; - - /* The boot CPU must be set before MADT/MPTABLE parsing happens */ - if (cpuid_to_apicid[0] == BAD_APICID) - panic("Boot CPU APIC not registered yet\n"); - - if (apicid == boot_cpu_physical_apicid) - return 0; - - if (disabled_cpu_apicid == apicid) { - int thiscpu = num_processors + disabled_cpus; - - pr_warn("APIC: Disabling requested cpu. Processor %d/0x%x ignored.\n", - thiscpu, apicid); - - disabled_cpus++; - return -ENODEV; - } - - if (num_processors >= nr_cpu_ids) { - int thiscpu = max + disabled_cpus; - - pr_warn("APIC: NR_CPUS/possible_cpus limit of %i reached. " - "Processor %d/0x%x ignored.\n", max, thiscpu, apicid); - - disabled_cpus++; - return -EINVAL; - } - - cpu = allocate_logical_cpuid(apicid); - if (cpu < 0) { - disabled_cpus++; - return -EINVAL; - } - - cpu_update_apic(cpu, apicid); - return cpu; -} - - void __irq_msi_compose_msg(struct irq_cfg *cfg, struct msi_msg *msg, bool dmar) { @@ -2502,10 +2315,7 @@ EXPORT_SYMBOL_GPL(x86_msi_msg_get_destid); static void __init apic_bsp_up_setup(void) { -#ifdef CONFIG_X86_64 - apic_write(APIC_ID, apic->set_apic_id(boot_cpu_physical_apicid)); -#endif - physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); + reset_phys_cpu_present_map(boot_cpu_physical_apicid); } /** @@ -2851,15 +2661,6 @@ static int __init lapic_insert_resource(void) */ late_initcall(lapic_insert_resource); -static int __init apic_set_disabled_cpu_apicid(char *arg) -{ - if (!arg || !get_option(&arg, &disabled_cpu_apicid)) - return -EINVAL; - - return 0; -} -early_param("disable_cpu_apicid", apic_set_disabled_cpu_apicid); - static int __init apic_set_extnmi(char *arg) { if (!arg) diff --git a/arch/x86/kernel/apic/apic_common.c b/arch/x86/kernel/apic/apic_common.c index 8a00141073..9ef3be8668 100644 --- a/arch/x86/kernel/apic/apic_common.c +++ b/arch/x86/kernel/apic/apic_common.c @@ -18,16 +18,6 @@ u32 apic_flat_calc_apicid(unsigned int cpu) return 1U << cpu; } -bool default_check_apicid_used(physid_mask_t *map, u32 apicid) -{ - return physid_isset(apicid, *map); -} - -void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) -{ - *retmap = *phys_map; -} - u32 default_cpu_present_to_apicid(int mps_cpu) { if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu)) @@ -37,11 +27,6 @@ u32 default_cpu_present_to_apicid(int mps_cpu) } EXPORT_SYMBOL_GPL(default_cpu_present_to_apicid); -bool default_apic_id_registered(void) -{ - return physid_isset(read_apic_id(), phys_cpu_present_map); -} - /* * Set up the logical destination ID when the APIC operates in logical * destination mode. diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index b295a056a4..f37ad3392f 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -61,16 +61,6 @@ static u32 flat_get_apic_id(u32 x) return (x >> 24) & 0xFF; } -static u32 set_apic_id(u32 id) -{ - return (id & 0xFF) << 24; -} - -static u32 flat_phys_pkg_id(u32 initial_apic_id, int index_msb) -{ - return initial_apic_id >> index_msb; -} - static int flat_probe(void) { return 1; @@ -80,7 +70,6 @@ static struct apic apic_flat __ro_after_init = { .name = "flat", .probe = flat_probe, .acpi_madt_oem_check = flat_acpi_madt_oem_check, - .apic_id_registered = default_apic_id_registered, .dest_mode_logical = true, @@ -88,11 +77,9 @@ static struct apic apic_flat __ro_after_init = { .init_apic_ldr = default_init_apic_ldr, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = flat_phys_pkg_id, .max_apic_id = 0xFE, .get_apic_id = flat_get_apic_id, - .set_apic_id = set_apic_id, .calc_dest_apicid = apic_flat_calc_apicid, @@ -151,18 +138,15 @@ static struct apic apic_physflat __ro_after_init = { .name = "physical flat", .probe = physflat_probe, .acpi_madt_oem_check = physflat_acpi_madt_oem_check, - .apic_id_registered = default_apic_id_registered, .dest_mode_logical = false, .disable_esr = 0, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = flat_phys_pkg_id, .max_apic_id = 0xFE, .get_apic_id = flat_get_apic_id, - .set_apic_id = set_apic_id, .calc_dest_apicid = apic_default_calc_apicid, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 9f1d553eb4..b5bb7a2e83 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -29,7 +29,6 @@ static void noop_send_IPI_self(int vector) { } static void noop_apic_icr_write(u32 low, u32 id) { } static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { return -1; } static u64 noop_apic_icr_read(void) { return 0; } -static u32 noop_phys_pkg_id(u32 cpuid_apic, int index_msb) { return 0; } static u32 noop_get_apic_id(u32 apicid) { return 0; } static void noop_apic_eoi(void) { } @@ -51,12 +50,8 @@ struct apic apic_noop __ro_after_init = { .disable_esr = 0, - .check_apicid_used = default_check_apicid_used, - .ioapic_phys_id_map = default_ioapic_phys_id_map, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = noop_phys_pkg_id, - .max_apic_id = 0xFE, .get_apic_id = noop_get_apic_id, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 7d0c51b9d3..16410f087b 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -38,11 +38,6 @@ static u32 numachip1_get_apic_id(u32 x) return id; } -static u32 numachip1_set_apic_id(u32 id) -{ - return (id & 0xff) << 24; -} - static u32 numachip2_get_apic_id(u32 x) { u64 mcfg; @@ -51,16 +46,6 @@ static u32 numachip2_get_apic_id(u32 x) return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24); } -static u32 numachip2_set_apic_id(u32 id) -{ - return id << 24; -} - -static u32 numachip_phys_pkg_id(u32 initial_apic_id, int index_msb) -{ - return initial_apic_id >> index_msb; -} - static void numachip1_apic_icr_write(int apicid, unsigned int val) { write_lcsr(CSR_G3_EXT_IRQ_GEN, (apicid << 16) | val); @@ -227,11 +212,9 @@ static const struct apic apic_numachip1 __refconst = { .disable_esr = 0, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = numachip_phys_pkg_id, .max_apic_id = UINT_MAX, .get_apic_id = numachip1_get_apic_id, - .set_apic_id = numachip1_set_apic_id, .calc_dest_apicid = apic_default_calc_apicid, @@ -263,11 +246,9 @@ static const struct apic apic_numachip2 __refconst = { .disable_esr = 0, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = numachip_phys_pkg_id, .max_apic_id = UINT_MAX, .get_apic_id = numachip2_get_apic_id, - .set_apic_id = numachip2_set_apic_id, .calc_dest_apicid = apic_default_calc_apicid, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 5a0d60b38e..9285d500d5 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -18,22 +18,6 @@ static u32 bigsmp_get_apic_id(u32 x) return (x >> 24) & 0xFF; } -static bool bigsmp_check_apicid_used(physid_mask_t *map, u32 apicid) -{ - return false; -} - -static void bigsmp_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) -{ - /* For clustered we don't have a good way to do this yet - hack */ - physids_promote(0xFFL, retmap); -} - -static u32 bigsmp_phys_pkg_id(u32 cpuid_apic, int index_msb) -{ - return cpuid_apic >> index_msb; -} - static void bigsmp_send_IPI_allbutself(int vector) { default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector); @@ -84,14 +68,10 @@ static struct apic apic_bigsmp __ro_after_init = { .disable_esr = 1, - .check_apicid_used = bigsmp_check_apicid_used, - .ioapic_phys_id_map = bigsmp_ioapic_phys_id_map, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = bigsmp_phys_pkg_id, .max_apic_id = 0xFE, .get_apic_id = bigsmp_get_apic_id, - .set_apic_id = NULL, .calc_dest_apicid = apic_default_calc_apicid, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 40c7cf180c..477b740b2f 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -1458,20 +1458,20 @@ void restore_boot_irq_mode(void) * * by Matt Domsch <Matt_Domsch@dell.com> Tue Dec 21 12:25:05 CST 1999 */ -void __init setup_ioapic_ids_from_mpc_nocheck(void) +static void __init setup_ioapic_ids_from_mpc_nocheck(void) { + DECLARE_BITMAP(phys_id_present_map, MAX_LOCAL_APIC); + const u32 broadcast_id = 0xF; union IO_APIC_reg_00 reg_00; - physid_mask_t phys_id_present_map; - int ioapic_idx; - int i; unsigned char old_id; unsigned long flags; + int ioapic_idx, i; /* * This is broken; anything with a real cpu count has to * circumvent this idiocy regardless. */ - apic->ioapic_phys_id_map(&phys_cpu_present_map, &phys_id_present_map); + copy_phys_cpu_present_map(phys_id_present_map); /* * Set the IOAPIC ID to the value stored in the MPC table. @@ -1484,11 +1484,10 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) old_id = mpc_ioapic_id(ioapic_idx); - if (mpc_ioapic_id(ioapic_idx) >= get_physical_broadcast()) { - printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n", - ioapic_idx, mpc_ioapic_id(ioapic_idx)); - printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", - reg_00.bits.ID); + if (mpc_ioapic_id(ioapic_idx) >= broadcast_id) { + pr_err(FW_BUG "IO-APIC#%d ID is %d in the MPC table!...\n", + ioapic_idx, mpc_ioapic_id(ioapic_idx)); + pr_err("... fixing up to %d. (tell your hw vendor)\n", reg_00.bits.ID); ioapics[ioapic_idx].mp_config.apicid = reg_00.bits.ID; } @@ -1497,23 +1496,21 @@ void __init setup_ioapic_ids_from_mpc_nocheck(void) * system must have a unique ID or we get lots of nice * 'stuck on smp_invalidate_needed IPI wait' messages. */ - if (apic->check_apicid_used(&phys_id_present_map, - mpc_ioapic_id(ioapic_idx))) { - printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n", - ioapic_idx, mpc_ioapic_id(ioapic_idx)); - for (i = 0; i < get_physical_broadcast(); i++) - if (!physid_isset(i, phys_id_present_map)) + if (test_bit(mpc_ioapic_id(ioapic_idx), phys_id_present_map)) { + pr_err(FW_BUG "IO-APIC#%d ID %d is already used!...\n", + ioapic_idx, mpc_ioapic_id(ioapic_idx)); + for (i = 0; i < broadcast_id; i++) + if (!test_bit(i, phys_id_present_map)) break; - if (i >= get_physical_broadcast()) + if (i >= broadcast_id) panic("Max APIC ID exceeded!\n"); - printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n", - i); - physid_set(i, phys_id_present_map); + pr_err("... fixing up to %d. (tell your hw vendor)\n", i); + set_bit(i, phys_id_present_map); ioapics[ioapic_idx].mp_config.apicid = i; } else { apic_printk(APIC_VERBOSE, "Setting %d in the phys_id_present_map\n", mpc_ioapic_id(ioapic_idx)); - physid_set(mpc_ioapic_id(ioapic_idx), phys_id_present_map); + set_bit(mpc_ioapic_id(ioapic_idx), phys_id_present_map); } /* @@ -2209,7 +2206,7 @@ static inline void __init check_timer(void) * 8259A. */ if (pin1 == -1) { - panic_if_irq_remap("BIOS bug: timer not connected to IO-APIC"); + panic_if_irq_remap(FW_BUG "Timer not connected to IO-APIC"); pin1 = pin2; apic1 = apic2; no_pin1 = 1; @@ -2354,7 +2351,7 @@ static int mp_irqdomain_create(int ioapic) fwspec.param_count = 1; fwspec.param[0] = mpc_ioapic_id(ioapic); - parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_ANY); + parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_GENERIC_MSI); if (!parent) { if (!cfg->dev) irq_domain_free_fwnode(fn); @@ -2494,56 +2491,41 @@ unsigned int arch_dynirq_lower_bound(unsigned int from) #ifdef CONFIG_X86_32 static int io_apic_get_unique_id(int ioapic, int apic_id) { + static DECLARE_BITMAP(apic_id_map, MAX_LOCAL_APIC); + const u32 broadcast_id = 0xF; union IO_APIC_reg_00 reg_00; - static physid_mask_t apic_id_map = PHYSID_MASK_NONE; - physid_mask_t tmp; unsigned long flags; int i = 0; - /* - * The P4 platform supports up to 256 APIC IDs on two separate APIC - * buses (one for LAPICs, one for IOAPICs), where predecessors only - * supports up to 16 on one shared APIC bus. - * - * TBD: Expand LAPIC/IOAPIC support on P4-class systems to take full - * advantage of new APIC bus architecture. - */ - - if (physids_empty(apic_id_map)) - apic->ioapic_phys_id_map(&phys_cpu_present_map, &apic_id_map); + /* Initialize the ID map */ + if (bitmap_empty(apic_id_map, MAX_LOCAL_APIC)) + copy_phys_cpu_present_map(apic_id_map); raw_spin_lock_irqsave(&ioapic_lock, flags); reg_00.raw = io_apic_read(ioapic, 0); raw_spin_unlock_irqrestore(&ioapic_lock, flags); - if (apic_id >= get_physical_broadcast()) { - printk(KERN_WARNING "IOAPIC[%d]: Invalid apic_id %d, trying " - "%d\n", ioapic, apic_id, reg_00.bits.ID); + if (apic_id >= broadcast_id) { + pr_warn("IOAPIC[%d]: Invalid apic_id %d, trying %d\n", + ioapic, apic_id, reg_00.bits.ID); apic_id = reg_00.bits.ID; } - /* - * Every APIC in a system must have a unique ID or we get lots of nice - * 'stuck on smp_invalidate_needed IPI wait' messages. - */ - if (apic->check_apicid_used(&apic_id_map, apic_id)) { - - for (i = 0; i < get_physical_broadcast(); i++) { - if (!apic->check_apicid_used(&apic_id_map, i)) + /* Every APIC in a system must have a unique ID */ + if (test_bit(apic_id, apic_id_map)) { + for (i = 0; i < broadcast_id; i++) { + if (!test_bit(i, apic_id_map)) break; } - if (i == get_physical_broadcast()) + if (i == broadcast_id) panic("Max apic_id exceeded!\n"); - printk(KERN_WARNING "IOAPIC[%d]: apic_id %d already used, " - "trying %d\n", ioapic, apic_id, i); - + pr_warn("IOAPIC[%d]: apic_id %d already used, trying %d\n", ioapic, apic_id, i); apic_id = i; } - physid_set_mask_of_physid(apic_id, &tmp); - physids_or(apic_id_map, apic_id_map, tmp); + set_bit(apic_id, apic_id_map); if (reg_00.bits.ID != apic_id) { reg_00.bits.ID = apic_id; @@ -2569,11 +2551,9 @@ static int io_apic_get_unique_id(int ioapic, int apic_id) static u8 io_apic_unique_id(int idx, u8 id) { - if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && - !APIC_XAPIC(boot_cpu_apic_version)) + if ((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && !APIC_XAPIC(boot_cpu_apic_version)) return io_apic_get_unique_id(idx, id); - else - return id; + return id; } #else static u8 io_apic_unique_id(int idx, u8 id) diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h index 9ea6186ea8..842fe28496 100644 --- a/arch/x86/kernel/apic/local.h +++ b/arch/x86/kernel/apic/local.h @@ -16,8 +16,6 @@ /* X2APIC */ void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest); u32 x2apic_get_apic_id(u32 id); -u32 x2apic_set_apic_id(u32 id); -u32 x2apic_phys_pkg_id(u32 initial_apicid, int index_msb); void x2apic_send_IPI_all(int vector); void x2apic_send_IPI_allbutself(int vector); @@ -63,9 +61,6 @@ void default_send_IPI_allbutself(int vector); void default_send_IPI_all(int vector); void default_send_IPI_self(int vector); -bool default_apic_id_registered(void); -bool default_check_apicid_used(physid_mask_t *map, u32 apicid); - #ifdef CONFIG_X86_32 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, int vector); void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, int vector); diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index c0f78059f0..f75ee345c0 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -18,11 +18,6 @@ #include "local.h" -static u32 default_phys_pkg_id(u32 cpuid_apic, int index_msb) -{ - return cpuid_apic >> index_msb; -} - static u32 default_get_apic_id(u32 x) { unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR)); @@ -43,17 +38,13 @@ static struct apic apic_default __ro_after_init = { .name = "default", .probe = probe_default, - .apic_id_registered = default_apic_id_registered, .dest_mode_logical = true, .disable_esr = 0, - .check_apicid_used = default_check_apicid_used, .init_apic_ldr = default_init_apic_ldr, - .ioapic_phys_id_map = default_ioapic_phys_id_map, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = default_phys_pkg_id, .max_apic_id = 0xFE, .get_apic_id = default_get_apic_id, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 185738c727..29cd0543fc 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -1036,7 +1036,8 @@ static void __vector_schedule_cleanup(struct apic_chip_data *apicd) add_timer_on(&cl->timer, cpu); } } else { - apicd->prev_vector = 0; + pr_warn("IRQ %u schedule cleanup for offline CPU %u\n", apicd->irq, cpu); + free_moved_vector(apicd); } raw_spin_unlock(&vector_lock); } @@ -1073,6 +1074,7 @@ void irq_complete_move(struct irq_cfg *cfg) */ void irq_force_complete_move(struct irq_desc *desc) { + unsigned int cpu = smp_processor_id(); struct apic_chip_data *apicd; struct irq_data *irqd; unsigned int vector; @@ -1097,10 +1099,11 @@ void irq_force_complete_move(struct irq_desc *desc) goto unlock; /* - * If prev_vector is empty, no action required. + * If prev_vector is empty or the descriptor is neither currently + * nor previously on the outgoing CPU no action required. */ vector = apicd->prev_vector; - if (!vector) + if (!vector || (apicd->cpu != cpu && apicd->prev_cpu != cpu)) goto unlock; /* diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index 28a7d3f231..567dbd2fe4 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -231,16 +231,12 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .disable_esr = 0, - .check_apicid_used = NULL, .init_apic_ldr = init_x2apic_ldr, - .ioapic_phys_id_map = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = x2apic_phys_pkg_id, .max_apic_id = UINT_MAX, .x2apic_set_max_apicid = true, .get_apic_id = x2apic_get_apic_id, - .set_apic_id = x2apic_set_apic_id, .calc_dest_apicid = x2apic_calc_apicid, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 409815a406..12d4c35547 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -129,16 +129,6 @@ u32 x2apic_get_apic_id(u32 id) return id; } -u32 x2apic_set_apic_id(u32 id) -{ - return id; -} - -u32 x2apic_phys_pkg_id(u32 initial_apicid, int index_msb) -{ - return initial_apicid >> index_msb; -} - static struct apic apic_x2apic_phys __ro_after_init = { .name = "physical x2apic", @@ -150,12 +140,10 @@ static struct apic apic_x2apic_phys __ro_after_init = { .disable_esr = 0, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = x2apic_phys_pkg_id, .max_apic_id = UINT_MAX, .x2apic_set_max_apicid = true, .get_apic_id = x2apic_get_apic_id, - .set_apic_id = x2apic_set_apic_id, .calc_dest_apicid = apic_default_calc_apicid, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index f1766b18dc..7fef504ca5 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -241,54 +241,20 @@ static void __init uv_tsc_check_sync(void) is_uv(UV3) ? sname.s3.field : \ undef) -/* [Copied from arch/x86/kernel/cpu/topology.c:detect_extended_topology()] */ - -#define SMT_LEVEL 0 /* Leaf 0xb SMT level */ -#define INVALID_TYPE 0 /* Leaf 0xb sub-leaf types */ -#define SMT_TYPE 1 -#define CORE_TYPE 2 -#define LEAFB_SUBTYPE(ecx) (((ecx) >> 8) & 0xff) -#define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) - -static void set_x2apic_bits(void) -{ - unsigned int eax, ebx, ecx, edx, sub_index; - unsigned int sid_shift; - - cpuid(0, &eax, &ebx, &ecx, &edx); - if (eax < 0xb) { - pr_info("UV: CPU does not have CPUID.11\n"); - return; - } - - cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx); - if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) { - pr_info("UV: CPUID.11 not implemented\n"); - return; - } - - sid_shift = BITS_SHIFT_NEXT_LEVEL(eax); - sub_index = 1; - do { - cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx); - if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) { - sid_shift = BITS_SHIFT_NEXT_LEVEL(eax); - break; - } - sub_index++; - } while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE); - - uv_cpuid.apicid_shift = 0; - uv_cpuid.apicid_mask = (~(-1 << sid_shift)); - uv_cpuid.socketid_shift = sid_shift; -} - static void __init early_get_apic_socketid_shift(void) { + unsigned int sid_shift = topology_get_domain_shift(TOPO_PKG_DOMAIN); + if (is_uv2_hub() || is_uv3_hub()) uvh_apicid.v = uv_early_read_mmr(UVH_APICID); - set_x2apic_bits(); + if (sid_shift) { + uv_cpuid.apicid_shift = 0; + uv_cpuid.apicid_mask = (~(-1 << sid_shift)); + uv_cpuid.socketid_shift = sid_shift; + } else { + pr_info("UV: CPU does not have valid CPUID.11\n"); + } pr_info("UV: apicid_shift:%d apicid_mask:0x%x\n", uv_cpuid.apicid_shift, uv_cpuid.apicid_mask); pr_info("UV: socketid_shift:%d pnode_mask:0x%x\n", uv_cpuid.socketid_shift, uv_cpuid.pnode_mask); @@ -779,21 +745,6 @@ static void uv_send_IPI_all(int vector) uv_send_IPI_mask(cpu_online_mask, vector); } -static u32 set_apic_id(u32 id) -{ - return id; -} - -static unsigned int uv_read_apic_id(void) -{ - return x2apic_get_apic_id(apic_read(APIC_ID)); -} - -static u32 uv_phys_pkg_id(u32 initial_apicid, int index_msb) -{ - return uv_read_apic_id() >> index_msb; -} - static int uv_probe(void) { return apic == &apic_x2apic_uv_x; @@ -810,11 +761,9 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .disable_esr = 0, .cpu_present_to_apicid = default_cpu_present_to_apicid, - .phys_pkg_id = uv_phys_pkg_id, .max_apic_id = UINT_MAX, .get_apic_id = x2apic_get_apic_id, - .set_apic_id = set_apic_id, .calc_dest_apicid = apic_default_calc_apicid, diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 76a5ced278..b37ab10957 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -1055,35 +1055,6 @@ static int apm_get_power_status(u_short *status, u_short *bat, u_short *life) return APM_SUCCESS; } -#if 0 -static int apm_get_battery_status(u_short which, u_short *status, - u_short *bat, u_short *life, u_short *nbat) -{ - u32 eax; - u32 ebx; - u32 ecx; - u32 edx; - u32 esi; - - if (apm_info.connection_version < 0x0102) { - /* pretend we only have one battery. */ - if (which != 1) - return APM_BAD_DEVICE; - *nbat = 1; - return apm_get_power_status(status, bat, life); - } - - if (apm_bios_call(APM_FUNC_GET_STATUS, (0x8000 | (which)), 0, &eax, - &ebx, &ecx, &edx, &esi)) - return (eax >> 8) & 0xff; - *status = ebx; - *bat = ecx; - *life = edx; - *nbat = esi; - return APM_SUCCESS; -} -#endif - /** * apm_engage_power_management - enable PM on a device * @device: identity of device diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index 6913b372cc..a98020bf31 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -109,7 +109,7 @@ static void __used common(void) OFFSET(TSS_sp2, tss_struct, x86_tss.sp2); OFFSET(X86_top_of_stack, pcpu_hot, top_of_stack); OFFSET(X86_current_task, pcpu_hot, current_task); -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING OFFSET(X86_call_depth, pcpu_hot, call_depth); #endif #if IS_ENABLED(CONFIG_CRYPTO_ARIA_AESNI_AVX_X86_64) diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index 64ad2ddea1..e92ff0c11d 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -24,6 +24,8 @@ static int __initdata_or_module debug_callthunks; +#define MAX_PATCH_LEN (255-1) + #define prdbg(fmt, args...) \ do { \ if (debug_callthunks) \ @@ -42,8 +44,8 @@ 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); +EXPORT_PER_CPU_SYMBOL_GPL(__x86_ctxsw_count); +EXPORT_PER_CPU_SYMBOL_GPL(__x86_call_count); #endif extern s32 __call_sites[], __call_sites_end[]; @@ -179,10 +181,15 @@ static const u8 nops[] = { static void *patch_dest(void *dest, bool direct) { unsigned int tsize = SKL_TMPL_SIZE; + u8 insn_buff[MAX_PATCH_LEN]; u8 *pad = dest - tsize; + memcpy(insn_buff, skl_call_thunk_template, tsize); + apply_relocation(insn_buff, tsize, pad, + skl_call_thunk_template, tsize); + /* Already patched? */ - if (!bcmp(pad, skl_call_thunk_template, tsize)) + if (!bcmp(pad, insn_buff, tsize)) return pad; /* Ensure there are nops */ @@ -192,9 +199,9 @@ static void *patch_dest(void *dest, bool direct) } if (direct) - memcpy(pad, skl_call_thunk_template, tsize); + memcpy(pad, insn_buff, tsize); else - text_poke_copy_locked(pad, skl_call_thunk_template, tsize, true); + text_poke_copy_locked(pad, insn_buff, tsize, true); return pad; } @@ -290,20 +297,27 @@ void *callthunks_translate_call_dest(void *dest) static bool is_callthunk(void *addr) { unsigned int tmpl_size = SKL_TMPL_SIZE; - void *tmpl = skl_call_thunk_template; + u8 insn_buff[MAX_PATCH_LEN]; unsigned long dest; + u8 *pad; 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); + pad = (void *)(dest - tmpl_size); + + memcpy(insn_buff, skl_call_thunk_template, tmpl_size); + apply_relocation(insn_buff, tmpl_size, pad, + skl_call_thunk_template, tmpl_size); + + return !bcmp(pad, insn_buff, tmpl_size); } -int x86_call_depth_emit_accounting(u8 **pprog, void *func) +int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip) { unsigned int tmpl_size = SKL_TMPL_SIZE; - void *tmpl = skl_call_thunk_template; + u8 insn_buff[MAX_PATCH_LEN]; if (!thunks_initialized) return 0; @@ -312,7 +326,11 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func) if (func && is_callthunk(func)) return 0; - memcpy(*pprog, tmpl, tmpl_size); + memcpy(insn_buff, skl_call_thunk_template, tmpl_size); + apply_relocation(insn_buff, tmpl_size, ip, + skl_call_thunk_template, tmpl_size); + + memcpy(*pprog, insn_buff, tmpl_size); *pprog += tmpl_size; return tmpl_size; } diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 93eabf5440..eb4dbcdf41 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -17,7 +17,8 @@ KMSAN_SANITIZE_common.o := n # As above, instrumenting secondary CPU boot code causes boot hangs. KCSAN_SANITIZE_common.o := n -obj-y := cacheinfo.o scattered.o topology.o +obj-y := cacheinfo.o scattered.o +obj-y += topology_common.o topology_ext.o topology_amd.o obj-y += common.o obj-y += rdrand.o obj-y += match.o @@ -25,14 +26,16 @@ obj-y += bugs.o obj-y += aperfmperf.o obj-y += cpuid-deps.o obj-y += umwait.o +obj-y += capflags.o powerflags.o -obj-$(CONFIG_PROC_FS) += proc.o -obj-y += capflags.o powerflags.o +obj-$(CONFIG_X86_LOCAL_APIC) += topology.o -obj-$(CONFIG_IA32_FEAT_CTL) += feat_ctl.o +obj-$(CONFIG_PROC_FS) += proc.o + +obj-$(CONFIG_IA32_FEAT_CTL) += feat_ctl.o ifdef CONFIG_CPU_SUP_INTEL -obj-y += intel.o intel_pconfig.o tsx.o -obj-$(CONFIG_PM) += intel_epb.o +obj-y += intel.o intel_pconfig.o tsx.o +obj-$(CONFIG_PM) += intel_epb.o endif obj-$(CONFIG_CPU_SUP_AMD) += amd.o obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o diff --git a/arch/x86/kernel/cpu/acrn.c b/arch/x86/kernel/cpu/acrn.c index bfeb18fad6..2c5b51aad9 100644 --- a/arch/x86/kernel/cpu/acrn.c +++ b/arch/x86/kernel/cpu/acrn.c @@ -26,8 +26,8 @@ static u32 __init acrn_detect(void) static void __init acrn_init_platform(void) { - /* Setup the IDT for ACRN hypervisor callback */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_acrn_hv_callback); + /* Install system interrupt handler for ACRN hypervisor callback */ + sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_acrn_hv_callback); x86_platform.calibrate_tsc = acrn_get_tsc_khz; x86_platform.calibrate_cpu = acrn_get_tsc_khz; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 0838ea579e..307302af0a 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -20,6 +20,7 @@ #include <asm/delay.h> #include <asm/debugreg.h> #include <asm/resctrl.h> +#include <asm/sev.h> #ifdef CONFIG_X86_64 # include <asm/mmconfig.h> @@ -27,13 +28,6 @@ #include "cpu.h" -/* - * nodes_per_socket: Stores the number of nodes per socket. - * Refer to Fam15h Models 00-0fh BKDG - CPUID Fn8000_001E_ECX - * Node Identifiers[10:8] - */ -static u32 nodes_per_socket = 1; - static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { u32 gprs[8] = { 0 }; @@ -300,97 +294,6 @@ static int nearby_node(int apicid) } #endif -/* - * Fix up topo::core_id for pre-F17h systems to be in the - * [0 .. cores_per_node - 1] range. Not really needed but - * kept so as not to break existing setups. - */ -static void legacy_fixup_core_id(struct cpuinfo_x86 *c) -{ - u32 cus_per_node; - - if (c->x86 >= 0x17) - return; - - cus_per_node = c->x86_max_cores / nodes_per_socket; - c->topo.core_id %= cus_per_node; -} - -/* - * Fixup core topology information for - * (1) AMD multi-node processors - * Assumption: Number of cores in each internal node is the same. - * (2) AMD processors supporting compute units - */ -static void amd_get_topology(struct cpuinfo_x86 *c) -{ - /* get information required for multi-node processors */ - if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - int err; - u32 eax, ebx, ecx, edx; - - cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - - c->topo.die_id = ecx & 0xff; - - if (c->x86 == 0x15) - c->topo.cu_id = ebx & 0xff; - - if (c->x86 >= 0x17) { - c->topo.core_id = ebx & 0xff; - - if (smp_num_siblings > 1) - c->x86_max_cores /= smp_num_siblings; - } - - /* - * In case leaf B is available, use it to derive - * topology information. - */ - err = detect_extended_topology(c); - if (!err) - c->x86_coreid_bits = get_count_order(c->x86_max_cores); - - cacheinfo_amd_init_llc_id(c); - - } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { - u64 value; - - rdmsrl(MSR_FAM10H_NODE_ID, value); - c->topo.die_id = value & 7; - c->topo.llc_id = c->topo.die_id; - } else - return; - - if (nodes_per_socket > 1) { - set_cpu_cap(c, X86_FEATURE_AMD_DCM); - legacy_fixup_core_id(c); - } -} - -/* - * On a AMD dual core setup the lower bits of the APIC id distinguish the cores. - * Assumes number of cores is a power of two. - */ -static void amd_detect_cmp(struct cpuinfo_x86 *c) -{ - unsigned bits; - - bits = c->x86_coreid_bits; - /* Low order bits define the core id (index of core in socket) */ - c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1); - /* Convert the initial APIC ID into the socket ID */ - c->topo.pkg_id = c->topo.initial_apicid >> bits; - /* use socket ID also for last level cache */ - c->topo.llc_id = c->topo.die_id = c->topo.pkg_id; -} - -u32 amd_get_nodes_per_socket(void) -{ - return nodes_per_socket; -} -EXPORT_SYMBOL_GPL(amd_get_nodes_per_socket); - static void srat_detect_node(struct cpuinfo_x86 *c) { #ifdef CONFIG_NUMA @@ -442,29 +345,25 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -static void early_init_amd_mc(struct cpuinfo_x86 *c) +static void bsp_determine_snp(struct cpuinfo_x86 *c) { -#ifdef CONFIG_SMP - unsigned bits, ecx; - - /* Multi core CPU? */ - if (c->extended_cpuid_level < 0x80000008) - return; +#ifdef CONFIG_ARCH_HAS_CC_PLATFORM + cc_vendor = CC_VENDOR_AMD; - ecx = cpuid_ecx(0x80000008); - - c->x86_max_cores = (ecx & 0xff) + 1; - - /* CPU telling us the core id bits shift? */ - bits = (ecx >> 12) & 0xF; - - /* Otherwise recompute */ - if (bits == 0) { - while ((1 << bits) < c->x86_max_cores) - bits++; + if (cpu_has(c, X86_FEATURE_SEV_SNP)) { + /* + * RMP table entry format is not architectural and is defined by the + * per-processor PPR. Restrict SNP support on the known CPU models + * for which the RMP table entry format is currently defined for. + */ + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && + c->x86 >= 0x19 && snp_probe_rmptable_info()) { + cc_platform_set(CC_ATTR_HOST_SEV_SNP); + } else { + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); + } } - - c->x86_coreid_bits = bits; #endif } @@ -500,18 +399,6 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_MWAITX)) use_mwaitx_delay(); - if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - u32 ecx; - - ecx = cpuid_ecx(0x8000001e); - __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1; - } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { - u64 value; - - rdmsrl(MSR_FAM10H_NODE_ID, value); - __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1; - } - if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && !boot_cpu_has(X86_FEATURE_VIRT_SSBD) && c->x86 >= 0x15 && c->x86 <= 0x17) { @@ -586,6 +473,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) break; } + bsp_determine_snp(c); return; warn: @@ -604,8 +492,8 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) * SME feature (set in scattered.c). * If the kernel has not enabled SME via any means then * don't advertise the SME feature. - * For SEV: If BIOS has not enabled SEV then don't advertise the - * SEV and SEV_ES feature (set in scattered.c). + * For SEV: If BIOS has not enabled SEV then don't advertise SEV and + * any additional functionality based on it. * * In all cases, since support for SME and SEV requires long mode, * don't advertise the feature under CONFIG_X86_32. @@ -640,16 +528,14 @@ clear_all: clear_sev: setup_clear_cpu_cap(X86_FEATURE_SEV); setup_clear_cpu_cap(X86_FEATURE_SEV_ES); + setup_clear_cpu_cap(X86_FEATURE_SEV_SNP); } } static void early_init_amd(struct cpuinfo_x86 *c) { - u64 value; u32 dummy; - early_init_amd_mc(c); - if (c->x86 >= 0xf) set_cpu_cap(c, X86_FEATURE_K8); @@ -715,23 +601,6 @@ static void early_init_amd(struct cpuinfo_x86 *c) early_detect_mem_encrypt(c); - /* Re-enable TopologyExtensions if switched off by BIOS */ - if (c->x86 == 0x15 && - (c->x86_model >= 0x10 && c->x86_model <= 0x6f) && - !cpu_has(c, X86_FEATURE_TOPOEXT)) { - - if (msr_set_bit(0xc0011005, 54) > 0) { - rdmsrl(0xc0011005, value); - if (value & BIT_64(54)) { - set_cpu_cap(c, X86_FEATURE_TOPOEXT); - pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); - } - } - } - - if (cpu_has(c, X86_FEATURE_TOPOEXT)) - smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) { if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB)) setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); @@ -940,7 +809,7 @@ static void fix_erratum_1386(struct cpuinfo_x86 *c) void init_spectral_chicken(struct cpuinfo_x86 *c) { -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY u64 value; /* @@ -968,7 +837,6 @@ static void init_amd_zen_common(void) static void init_amd_zen1(struct cpuinfo_x86 *c) { - init_amd_zen_common(); fix_erratum_1386(c); /* Fix up CPUID bits, but only if not virtualised. */ @@ -1022,7 +890,6 @@ static void zen2_zenbleed_check(struct cpuinfo_x86 *c) static void init_amd_zen2(struct cpuinfo_x86 *c) { - init_amd_zen_common(); init_spectral_chicken(c); fix_erratum_1386(c); zen2_zenbleed_check(c); @@ -1030,8 +897,6 @@ static void init_amd_zen2(struct cpuinfo_x86 *c) static void init_amd_zen3(struct cpuinfo_x86 *c) { - init_amd_zen_common(); - if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { /* * Zen3 (Fam19 model < 0x10) parts are not susceptible to @@ -1045,15 +910,12 @@ static void init_amd_zen3(struct cpuinfo_x86 *c) static void init_amd_zen4(struct cpuinfo_x86 *c) { - init_amd_zen_common(); - if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); } static void init_amd_zen5(struct cpuinfo_x86 *c) { - init_amd_zen_common(); } static void init_amd(struct cpuinfo_x86 *c) @@ -1075,9 +937,6 @@ static void init_amd(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_FSRM)) set_cpu_cap(c, X86_FEATURE_FSRS); - /* get apicid instead of initial apic id from cpuid */ - c->topo.apicid = read_apic_id(); - /* K6s reports MCEs but don't actually have all the MSRs */ if (c->x86 < 6) clear_cpu_cap(c, X86_FEATURE_MCE); @@ -1093,6 +952,13 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x16: init_amd_jg(c); break; } + /* + * Save up on some future enablement work and do common Zen + * settings. + */ + if (c->x86 >= 0x17) + init_amd_zen_common(); + if (boot_cpu_has(X86_FEATURE_ZEN1)) init_amd_zen1(c); else if (boot_cpu_has(X86_FEATURE_ZEN2)) @@ -1113,8 +979,6 @@ static void init_amd(struct cpuinfo_x86 *c) cpu_detect_cache_sizes(c); - amd_detect_cmp(c); - amd_get_topology(c); srat_detect_node(c); init_amd_cacheinfo(c); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index e7ceee008b..ab18185894 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -56,7 +56,7 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_base); /* The current value of the SPEC_CTRL MSR with task-specific bits set */ DEFINE_PER_CPU(u64, x86_spec_ctrl_current); -EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); +EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current); u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; EXPORT_SYMBOL_GPL(x86_pred_cmd); @@ -731,7 +731,7 @@ enum gds_mitigations { GDS_MITIGATION_HYPERVISOR, }; -#if IS_ENABLED(CONFIG_GDS_FORCE_MITIGATION) +#if IS_ENABLED(CONFIG_MITIGATION_GDS_FORCE) static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FORCE; #else static enum gds_mitigations gds_mitigation __ro_after_init = GDS_MITIGATION_FULL; @@ -1042,10 +1042,10 @@ static void __init retbleed_select_mitigation(void) return; case RETBLEED_CMD_UNRET: - if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) { + if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) { retbleed_mitigation = RETBLEED_MITIGATION_UNRET; } else { - pr_err("WARNING: kernel not compiled with CPU_UNRET_ENTRY.\n"); + pr_err("WARNING: kernel not compiled with MITIGATION_UNRET_ENTRY.\n"); goto do_cmd_auto; } break; @@ -1054,24 +1054,24 @@ static void __init retbleed_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_IBPB)) { pr_err("WARNING: CPU does not support IBPB.\n"); goto do_cmd_auto; - } else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) { + } else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) { retbleed_mitigation = RETBLEED_MITIGATION_IBPB; } else { - pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); + pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n"); goto do_cmd_auto; } break; case RETBLEED_CMD_STUFF: - if (IS_ENABLED(CONFIG_CALL_DEPTH_TRACKING) && + if (IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) && spectre_v2_enabled == SPECTRE_V2_RETPOLINE) { retbleed_mitigation = RETBLEED_MITIGATION_STUFF; } else { - if (IS_ENABLED(CONFIG_CALL_DEPTH_TRACKING)) + if (IS_ENABLED(CONFIG_MITIGATION_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"); + pr_err("WARNING: kernel not compiled with MITIGATION_CALL_DEPTH_TRACKING.\n"); goto do_cmd_auto; } @@ -1081,9 +1081,10 @@ do_cmd_auto: case RETBLEED_CMD_AUTO: if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { - if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) + if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) retbleed_mitigation = RETBLEED_MITIGATION_UNRET; - else if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY) && boot_cpu_has(X86_FEATURE_IBPB)) + else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY) && + boot_cpu_has(X86_FEATURE_IBPB)) retbleed_mitigation = RETBLEED_MITIGATION_IBPB; } @@ -1162,7 +1163,7 @@ static enum spectre_v2_user_mitigation spectre_v2_user_stibp __ro_after_init = static enum spectre_v2_user_mitigation spectre_v2_user_ibpb __ro_after_init = SPECTRE_V2_USER_NONE; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE static bool spectre_v2_bad_module; bool retpoline_module_ok(bool has_retpoline) @@ -1475,7 +1476,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) cmd == SPECTRE_V2_CMD_RETPOLINE_GENERIC || cmd == SPECTRE_V2_CMD_EIBRS_LFENCE || cmd == SPECTRE_V2_CMD_EIBRS_RETPOLINE) && - !IS_ENABLED(CONFIG_RETPOLINE)) { + !IS_ENABLED(CONFIG_MITIGATION_RETPOLINE)) { pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; @@ -1498,7 +1499,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) return SPECTRE_V2_CMD_AUTO; } - if (cmd == SPECTRE_V2_CMD_IBRS && !IS_ENABLED(CONFIG_CPU_IBRS_ENTRY)) { + if (cmd == SPECTRE_V2_CMD_IBRS && !IS_ENABLED(CONFIG_MITIGATION_IBRS_ENTRY)) { pr_err("%s selected but not compiled in. Switching to AUTO select\n", mitigation_options[i].option); return SPECTRE_V2_CMD_AUTO; @@ -1529,7 +1530,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void) static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) { - if (!IS_ENABLED(CONFIG_RETPOLINE)) { + if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE)) { pr_err("Kernel not compiled with retpoline; no mitigation available!"); return SPECTRE_V2_NONE; } @@ -1697,7 +1698,7 @@ static void __init spectre_v2_select_mitigation(void) break; } - if (IS_ENABLED(CONFIG_CPU_IBRS_ENTRY) && + if (IS_ENABLED(CONFIG_MITIGATION_IBRS_ENTRY) && boot_cpu_has_bug(X86_BUG_RETBLEED) && retbleed_cmd != RETBLEED_CMD_OFF && retbleed_cmd != RETBLEED_CMD_STUFF && @@ -2591,7 +2592,7 @@ static void __init srso_select_mitigation(void) break; case SRSO_CMD_SAFE_RET: - if (IS_ENABLED(CONFIG_CPU_SRSO)) { + if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) { /* * Enable the return thunk for generated code * like ftrace, static_call, etc. @@ -2611,29 +2612,29 @@ static void __init srso_select_mitigation(void) else srso_mitigation = SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED; } else { - pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n"); } break; case SRSO_CMD_IBPB: - if (IS_ENABLED(CONFIG_CPU_IBPB_ENTRY)) { + if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) { if (has_microcode) { setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); srso_mitigation = SRSO_MITIGATION_IBPB; } } else { - pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); + pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n"); } break; case SRSO_CMD_IBPB_ON_VMEXIT: - if (IS_ENABLED(CONFIG_CPU_SRSO)) { + if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) { if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; } } else { - pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); + pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n"); } break; } @@ -3016,3 +3017,8 @@ ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attrib return cpu_show_common(dev, attr, buf, X86_BUG_RFDS); } #endif + +void __warn_thunk(void) +{ + WARN_ONCE(1, "Unpatched return thunk in use. This should not happen!\n"); +} diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index c131c412db..392d09c936 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -301,7 +301,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax, eax->split.type = types[leaf]; eax->split.level = levels[leaf]; eax->split.num_threads_sharing = 0; - eax->split.num_cores_on_die = __this_cpu_read(cpu_info.x86_max_cores) - 1; + eax->split.num_cores_on_die = topology_num_cores_per_package(); if (assoc == 0xffff) @@ -595,7 +595,7 @@ static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index) if (index < 3) return; - node = topology_die_id(smp_processor_id()); + node = topology_amd_node_id(smp_processor_id()); this_leaf->nb = node_to_amd_nb(node); if (this_leaf->nb && !this_leaf->nb->l3_cache.indices) amd_calc_l3_indices(this_leaf->nb); @@ -661,7 +661,7 @@ static int find_num_cache_leaves(struct cpuinfo_x86 *c) return i; } -void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c) +void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id) { /* * We may have multiple LLCs if L3 caches exist, so check if we @@ -672,7 +672,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c) if (c->x86 < 0x17) { /* LLC is at the node level. */ - c->topo.llc_id = c->topo.die_id; + c->topo.llc_id = die_id; } else if (c->x86 == 0x17 && c->x86_model <= 0x1F) { /* * LLC is at the core complex level. @@ -1118,15 +1118,16 @@ static void cache_cpu_init(void) unsigned long flags; local_irq_save(flags); - cache_disable(); - if (memory_caching_control & CACHE_MTRR) + if (memory_caching_control & CACHE_MTRR) { + cache_disable(); mtrr_generic_set_state(); + cache_enable(); + } if (memory_caching_control & CACHE_PAT) pat_cpu_init(); - cache_enable(); local_irq_restore(flags); } diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c index 345f7d905d..a3b55db35c 100644 --- a/arch/x86/kernel/cpu/centaur.c +++ b/arch/x86/kernel/cpu/centaur.c @@ -128,10 +128,6 @@ static void init_centaur(struct cpuinfo_x86 *c) #endif early_init_centaur(c); init_intel_cacheinfo(c); - detect_num_cpu_cores(c); -#ifdef CONFIG_X86_32 - detect_ht(c); -#endif if (c->cpuid_level > 9) { unsigned int eax = cpuid_eax(10); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 46603c6e40..1982007828 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -61,6 +61,7 @@ #include <asm/microcode.h> #include <asm/intel-family.h> #include <asm/cpu_device_id.h> +#include <asm/fred.h> #include <asm/uv/uv.h> #include <asm/ia32.h> #include <asm/set_memory.h> @@ -70,11 +71,26 @@ #include "cpu.h" +DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); +EXPORT_PER_CPU_SYMBOL(cpu_info); + u32 elf_hwcap2 __read_mostly; /* Number of siblings per CPU package */ -int smp_num_siblings = 1; -EXPORT_SYMBOL(smp_num_siblings); +unsigned int __max_threads_per_core __ro_after_init = 1; +EXPORT_SYMBOL(__max_threads_per_core); + +unsigned int __max_dies_per_package __ro_after_init = 1; +EXPORT_SYMBOL(__max_dies_per_package); + +unsigned int __max_logical_packages __ro_after_init = 1; +EXPORT_SYMBOL(__max_logical_packages); + +unsigned int __num_cores_per_package __ro_after_init = 1; +EXPORT_SYMBOL(__num_cores_per_package); + +unsigned int __num_threads_per_package __ro_after_init = 1; +EXPORT_SYMBOL(__num_threads_per_package); static struct ppin_info { int feature; @@ -382,9 +398,8 @@ out: } /* These bits should not change their value after CPU init is finished. */ -static const unsigned long cr4_pinned_mask = - X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | - X86_CR4_FSGSBASE | X86_CR4_CET; +static const unsigned long cr4_pinned_mask = X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_UMIP | + X86_CR4_FSGSBASE | X86_CR4_CET | X86_CR4_FRED; static DEFINE_STATIC_KEY_FALSE_RO(cr_pinning); static unsigned long cr4_pinned_bits __ro_after_init; @@ -790,19 +805,6 @@ static void get_model_name(struct cpuinfo_x86 *c) *(s + 1) = '\0'; } -void detect_num_cpu_cores(struct cpuinfo_x86 *c) -{ - unsigned int eax, ebx, ecx, edx; - - c->x86_max_cores = 1; - if (!IS_ENABLED(CONFIG_SMP) || c->cpuid_level < 4) - return; - - cpuid_count(4, 0, &eax, &ebx, &ecx, &edx); - if (eax & 0x1f) - c->x86_max_cores = (eax >> 26) + 1; -} - void cpu_detect_cache_sizes(struct cpuinfo_x86 *c) { unsigned int n, dummy, ebx, ecx, edx, l2size; @@ -864,51 +866,6 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c) tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]); } -int detect_ht_early(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - u32 eax, ebx, ecx, edx; - - if (!cpu_has(c, X86_FEATURE_HT)) - return -1; - - if (cpu_has(c, X86_FEATURE_CMP_LEGACY)) - return -1; - - if (cpu_has(c, X86_FEATURE_XTOPOLOGY)) - return -1; - - cpuid(1, &eax, &ebx, &ecx, &edx); - - smp_num_siblings = (ebx & 0xff0000) >> 16; - if (smp_num_siblings == 1) - pr_info_once("CPU0: Hyper-Threading is disabled\n"); -#endif - return 0; -} - -void detect_ht(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - int index_msb, core_bits; - - if (detect_ht_early(c) < 0) - return; - - index_msb = get_count_order(smp_num_siblings); - c->topo.pkg_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb); - - smp_num_siblings = smp_num_siblings / c->x86_max_cores; - - index_msb = get_count_order(smp_num_siblings); - - core_bits = get_count_order(c->x86_max_cores); - - c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb) & - ((1 << core_bits) - 1); -#endif -} - static void get_cpu_vendor(struct cpuinfo_x86 *c) { char *v = c->x86_vendor_id; @@ -1096,18 +1053,9 @@ void get_cpu_cap(struct cpuinfo_x86 *c) void get_cpu_address_sizes(struct cpuinfo_x86 *c) { u32 eax, ebx, ecx, edx; - bool vp_bits_from_cpuid = true; if (!cpu_has(c, X86_FEATURE_CPUID) || - (c->extended_cpuid_level < 0x80000008)) - vp_bits_from_cpuid = false; - - if (vp_bits_from_cpuid) { - cpuid(0x80000008, &eax, &ebx, &ecx, &edx); - - c->x86_virt_bits = (eax >> 8) & 0xff; - c->x86_phys_bits = eax & 0xff; - } else { + (c->extended_cpuid_level < 0x80000008)) { if (IS_ENABLED(CONFIG_X86_64)) { c->x86_clflush_size = 64; c->x86_phys_bits = 36; @@ -1121,7 +1069,17 @@ void get_cpu_address_sizes(struct cpuinfo_x86 *c) cpu_has(c, X86_FEATURE_PSE36)) c->x86_phys_bits = 36; } + } else { + cpuid(0x80000008, &eax, &ebx, &ecx, &edx); + + c->x86_virt_bits = (eax >> 8) & 0xff; + c->x86_phys_bits = eax & 0xff; + + /* Provide a sane default if not enumerated: */ + if (!c->x86_clflush_size) + c->x86_clflush_size = 32; } + c->x86_cache_bits = c->x86_phys_bits; c->x86_cache_alignment = c->x86_clflush_size; } @@ -1385,8 +1343,13 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) /* * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature * flag and protect from vendor-specific bugs via the whitelist. + * + * Don't use AutoIBRS when SNP is enabled because it degrades host + * userspace indirect branch performance. */ - if ((x86_arch_cap_msr & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { + if ((x86_arch_cap_msr & ARCH_CAP_IBRS_ALL) || + (cpu_has(c, X86_FEATURE_AUTOIBRS) && + !cpu_feature_enabled(X86_FEATURE_SEV_SNP))) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && !(x86_arch_cap_msr & ARCH_CAP_PBRSB_NO)) @@ -1627,11 +1590,14 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) if (have_cpuid_p()) { cpu_detect(c); get_cpu_vendor(c); + intel_unlock_cpuid_leafs(c); get_cpu_cap(c); setup_force_cpu_cap(X86_FEATURE_CPUID); get_cpu_address_sizes(c); cpu_parse_early_param(); + cpu_init_topology(c); + if (this_cpu->c_early_init) this_cpu->c_early_init(c); @@ -1643,6 +1609,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) } else { setup_clear_cpu_cap(X86_FEATURE_CPUID); get_cpu_address_sizes(c); + cpu_init_topology(c); } setup_force_cpu_cap(X86_FEATURE_ALWAYS); @@ -1783,23 +1750,11 @@ static void generic_identify(struct cpuinfo_x86 *c) cpu_detect(c); get_cpu_vendor(c); - + intel_unlock_cpuid_leafs(c); get_cpu_cap(c); get_cpu_address_sizes(c); - if (c->cpuid_level >= 0x00000001) { - c->topo.initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF; -#ifdef CONFIG_X86_32 -# ifdef CONFIG_SMP - c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0); -# else - c->topo.apicid = c->topo.initial_apicid; -# endif -#endif - c->topo.pkg_id = c->topo.initial_apicid; - } - get_model_name(c); /* Default name */ /* @@ -1821,29 +1776,6 @@ static void generic_identify(struct cpuinfo_x86 *c) } /* - * Validate that ACPI/mptables have the same information about the - * effective APIC id and update the package map. - */ -static void validate_apic_and_package_id(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - unsigned int cpu = smp_processor_id(); - u32 apicid; - - apicid = apic->cpu_present_to_apicid(cpu); - - if (apicid != c->topo.apicid) { - pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n", - cpu, apicid, c->topo.initial_apicid); - } - BUG_ON(topology_update_package_map(c->topo.pkg_id, cpu)); - BUG_ON(topology_update_die_map(c->topo.die_id, cpu)); -#else - c->topo.logical_pkg_id = 0; -#endif -} - -/* * This does the hard work of actually picking apart the CPU stuff... */ static void identify_cpu(struct cpuinfo_x86 *c) @@ -1856,11 +1788,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->x86_model = c->x86_stepping = 0; /* So far unknown... */ c->x86_vendor_id[0] = '\0'; /* Unset */ c->x86_model_id[0] = '\0'; /* Unset */ - c->x86_max_cores = 1; - c->x86_coreid_bits = 0; - c->topo.cu_id = 0xff; - c->topo.llc_id = BAD_APICID; - c->topo.l2c_id = BAD_APICID; #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; c->x86_phys_bits = 36; @@ -1879,17 +1806,14 @@ static void identify_cpu(struct cpuinfo_x86 *c) generic_identify(c); + cpu_parse_topology(c); + if (this_cpu->c_identify) this_cpu->c_identify(c); /* Clear/Set all flags overridden by options, after probe */ apply_forced_caps(c); -#ifdef CONFIG_X86_64 - c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0); -#endif - - /* * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and * Hygon will clear it in ->c_init() below. @@ -1943,10 +1867,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->x86, c->x86_model); } -#ifdef CONFIG_X86_64 - detect_ht(c); -#endif - x86_init_rdrand(c); setup_pku(c); setup_cet(c); @@ -1978,8 +1898,6 @@ static void identify_cpu(struct cpuinfo_x86 *c) /* Init Machine Check Exception if available. */ mcheck_cpu_init(c); - select_idle_routine(c); - #ifdef CONFIG_NUMA numa_add_cpu(smp_processor_id()); #endif @@ -2038,7 +1956,6 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c) #ifdef CONFIG_X86_32 enable_sep_cpu(); #endif - validate_apic_and_package_id(c); x86_spec_ctrl_setup_ap(); update_srbds_msr(); if (boot_cpu_has_bug(X86_BUG_GDS)) @@ -2090,6 +2007,7 @@ DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = { .top_of_stack = TOP_OF_INIT_STACK, }; EXPORT_PER_CPU_SYMBOL(pcpu_hot); +EXPORT_PER_CPU_SYMBOL(const_pcpu_hot); #ifdef CONFIG_X86_64 DEFINE_PER_CPU_FIRST(struct fixed_percpu_data, @@ -2107,10 +2025,8 @@ static void wrmsrl_cstar(unsigned long val) wrmsrl(MSR_CSTAR, val); } -/* May not be marked __init: used by software suspend */ -void syscall_init(void) +static inline void idt_syscall_init(void) { - wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); if (ia32_enabled()) { @@ -2144,6 +2060,23 @@ void syscall_init(void) X86_EFLAGS_AC|X86_EFLAGS_ID); } +/* May not be marked __init: used by software suspend */ +void syscall_init(void) +{ + /* The default user and kernel segments */ + wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); + + /* + * Except the IA32_STAR MSR, there is NO need to setup SYSCALL and + * SYSENTER MSRs for FRED, because FRED uses the ring 3 FRED + * entrypoint for SYSCALL and SYSENTER, and ERETU is the only legit + * instruction to return to ring 3 (both sysexit and sysret cause + * #UD when FRED is enabled). + */ + if (!cpu_feature_enabled(X86_FEATURE_FRED)) + idt_syscall_init(); +} + #else /* CONFIG_X86_64 */ #ifdef CONFIG_STACKPROTECTOR @@ -2247,8 +2180,9 @@ void cpu_init_exception_handling(void) /* paranoid_entry() gets the CPU number from the GDT */ setup_getcpu(cpu); - /* IST vectors need TSS to be set up. */ - tss_setup_ist(tss); + /* For IDT mode, IST vectors need to be set in TSS. */ + if (!cpu_feature_enabled(X86_FEATURE_FRED)) + tss_setup_ist(tss); tss_setup_io_bitmap(tss); set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss); @@ -2257,8 +2191,10 @@ void cpu_init_exception_handling(void) /* GHCB needs to be setup to handle #VC. */ setup_ghcb(); - /* Finally load the IDT */ - load_current_idt(); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + cpu_init_fred_exceptions(); + else + load_current_idt(); } /* @@ -2381,13 +2317,17 @@ void arch_smt_update(void) void __init arch_cpu_finalize_init(void) { + struct cpuinfo_x86 *c = this_cpu_ptr(&cpu_info); + identify_boot_cpu(); + select_idle_routine(); + /* * identify_boot_cpu() initialized SMT support information, let the * core code know. */ - cpu_smt_set_num_threads(smp_num_siblings, smp_num_siblings); + cpu_smt_set_num_threads(__max_threads_per_core, __max_threads_per_core); if (!IS_ENABLED(CONFIG_SMP)) { pr_info("CPU: "); @@ -2417,6 +2357,13 @@ void __init arch_cpu_finalize_init(void) fpu__init_system(); fpu__init_cpu(); + /* + * Ensure that access to the per CPU representation has the initial + * boot CPU configuration. + */ + *c = boot_cpu_data; + c->initialized = true; + alternative_instructions(); if (IS_ENABLED(CONFIG_X86_64)) { diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 885281ae79..1beccefbaf 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -2,6 +2,11 @@ #ifndef ARCH_X86_CPU_H #define ARCH_X86_CPU_H +#include <asm/cpu.h> +#include <asm/topology.h> + +#include "topology.h" + /* attempt to consolidate cpu attributes */ struct cpu_dev { const char *c_vendor; @@ -56,9 +61,11 @@ extern __ro_after_init enum tsx_ctrl_states tsx_ctrl_state; extern void __init tsx_init(void); void tsx_ap_init(void); +void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c); #else static inline void tsx_init(void) { } static inline void tsx_ap_init(void) { } +static inline void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c) { } #endif /* CONFIG_CPU_SUP_INTEL */ extern void init_spectral_chicken(struct cpuinfo_x86 *c); @@ -71,14 +78,9 @@ extern void init_intel_cacheinfo(struct cpuinfo_x86 *c); extern void init_amd_cacheinfo(struct cpuinfo_x86 *c); extern void init_hygon_cacheinfo(struct cpuinfo_x86 *c); -extern void detect_num_cpu_cores(struct cpuinfo_x86 *c); -extern int detect_extended_topology_early(struct cpuinfo_x86 *c); -extern int detect_extended_topology(struct cpuinfo_x86 *c); -extern int detect_ht_early(struct cpuinfo_x86 *c); -extern void detect_ht(struct cpuinfo_x86 *c); extern void check_null_seg_clears_base(struct cpuinfo_x86 *c); -void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c); +void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id); void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c); unsigned int aperfmperf_get_khz(int cpu); @@ -96,4 +98,5 @@ static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) mode == SPECTRE_V2_EIBRS_RETPOLINE || mode == SPECTRE_V2_EIBRS_LFENCE; } + #endif /* ARCH_X86_CPU_H */ diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index 6fb6d8a57c..946813d816 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -82,6 +82,8 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_XFD, X86_FEATURE_XGETBV1 }, { X86_FEATURE_AMX_TILE, X86_FEATURE_XFD }, { X86_FEATURE_SHSTK, X86_FEATURE_XSAVES }, + { X86_FEATURE_FRED, X86_FEATURE_LKGS }, + { X86_FEATURE_FRED, X86_FEATURE_WRMSRNS }, {} }; diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c index 0c179d684b..3baf3e4358 100644 --- a/arch/x86/kernel/cpu/debugfs.c +++ b/arch/x86/kernel/cpu/debugfs.c @@ -5,6 +5,8 @@ #include <asm/apic.h> #include <asm/processor.h> +#include "cpu.h" + static int cpu_debug_show(struct seq_file *m, void *p) { unsigned long cpu = (unsigned long)m->private; @@ -24,9 +26,12 @@ static int cpu_debug_show(struct seq_file *m, void *p) seq_printf(m, "logical_die_id: %u\n", c->topo.logical_die_id); seq_printf(m, "llc_id: %u\n", c->topo.llc_id); seq_printf(m, "l2c_id: %u\n", c->topo.l2c_id); - seq_printf(m, "max_cores: %u\n", c->x86_max_cores); - seq_printf(m, "max_die_per_pkg: %u\n", __max_die_per_package); - seq_printf(m, "smp_num_siblings: %u\n", smp_num_siblings); + seq_printf(m, "amd_node_id: %u\n", c->topo.amd_node_id); + seq_printf(m, "amd_nodes_per_pkg: %u\n", topology_amd_nodes_per_pkg()); + seq_printf(m, "num_threads: %u\n", __num_threads_per_package); + seq_printf(m, "num_cores: %u\n", __num_cores_per_package); + seq_printf(m, "max_dies_per_pkg: %u\n", __max_dies_per_package); + seq_printf(m, "max_threads_per_core:%u\n", __max_threads_per_core); return 0; } @@ -42,12 +47,48 @@ static const struct file_operations dfs_cpu_ops = { .release = single_release, }; +static int dom_debug_show(struct seq_file *m, void *p) +{ + static const char *domain_names[TOPO_MAX_DOMAIN] = { + [TOPO_SMT_DOMAIN] = "Thread", + [TOPO_CORE_DOMAIN] = "Core", + [TOPO_MODULE_DOMAIN] = "Module", + [TOPO_TILE_DOMAIN] = "Tile", + [TOPO_DIE_DOMAIN] = "Die", + [TOPO_DIEGRP_DOMAIN] = "DieGrp", + [TOPO_PKG_DOMAIN] = "Package", + }; + unsigned int dom, nthreads = 1; + + for (dom = 0; dom < TOPO_MAX_DOMAIN; dom++) { + nthreads *= x86_topo_system.dom_size[dom]; + seq_printf(m, "domain: %-10s shift: %u dom_size: %5u max_threads: %5u\n", + domain_names[dom], x86_topo_system.dom_shifts[dom], + x86_topo_system.dom_size[dom], nthreads); + } + return 0; +} + +static int dom_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, dom_debug_show, inode->i_private); +} + +static const struct file_operations dfs_dom_ops = { + .open = dom_debug_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + static __init int cpu_init_debugfs(void) { struct dentry *dir, *base = debugfs_create_dir("topo", arch_debugfs_dir); unsigned long id; char name[24]; + debugfs_create_file("domains", 0444, base, NULL, &dfs_dom_ops); + dir = debugfs_create_dir("cpus", base); for_each_possible_cpu(id) { sprintf(name, "%lu", id); diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c index 03851240c3..1640ae7654 100644 --- a/arch/x86/kernel/cpu/feat_ctl.c +++ b/arch/x86/kernel/cpu/feat_ctl.c @@ -72,6 +72,8 @@ static void init_vmx_capabilities(struct cpuinfo_x86 *c) c->vmx_capability[MISC_FEATURES] |= VMX_F(EPT_AD); if (ept & VMX_EPT_1GB_PAGE_BIT) c->vmx_capability[MISC_FEATURES] |= VMX_F(EPT_1GB); + if (ept & VMX_EPT_PAGE_WALK_5_BIT) + c->vmx_capability[MISC_FEATURES] |= VMX_F(EPT_5LEVEL); /* Synthetic APIC features that are aggregates of multiple features. */ if ((c->vmx_capability[PRIMARY_CTLS] & VMX_F(VIRTUAL_TPR)) && diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index f0cd95502f..c5191b06f9 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -18,14 +18,6 @@ #include "cpu.h" -#define APICID_SOCKET_ID_BIT 6 - -/* - * nodes_per_socket: Stores the number of nodes per socket. - * Refer to CPUID Fn8000_001E_ECX Node Identifiers[10:8] - */ -static u32 nodes_per_socket = 1; - #ifdef CONFIG_NUMA /* * To workaround broken NUMA config. Read the comment in @@ -49,80 +41,6 @@ static int nearby_node(int apicid) } #endif -static void hygon_get_topology_early(struct cpuinfo_x86 *c) -{ - if (cpu_has(c, X86_FEATURE_TOPOEXT)) - smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1; -} - -/* - * Fixup core topology information for - * (1) Hygon multi-node processors - * Assumption: Number of cores in each internal node is the same. - * (2) Hygon processors supporting compute units - */ -static void hygon_get_topology(struct cpuinfo_x86 *c) -{ - /* get information required for multi-node processors */ - if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - int err; - u32 eax, ebx, ecx, edx; - - cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - - c->topo.die_id = ecx & 0xff; - - c->topo.core_id = ebx & 0xff; - - if (smp_num_siblings > 1) - c->x86_max_cores /= smp_num_siblings; - - /* - * In case leaf B is available, use it to derive - * topology information. - */ - err = detect_extended_topology(c); - if (!err) - c->x86_coreid_bits = get_count_order(c->x86_max_cores); - - /* - * Socket ID is ApicId[6] for the processors with model <= 0x3 - * when running on host. - */ - if (!boot_cpu_has(X86_FEATURE_HYPERVISOR) && c->x86_model <= 0x3) - c->topo.pkg_id = c->topo.apicid >> APICID_SOCKET_ID_BIT; - - cacheinfo_hygon_init_llc_id(c); - } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { - u64 value; - - rdmsrl(MSR_FAM10H_NODE_ID, value); - c->topo.die_id = value & 7; - c->topo.llc_id = c->topo.die_id; - } else - return; - - if (nodes_per_socket > 1) - set_cpu_cap(c, X86_FEATURE_AMD_DCM); -} - -/* - * On Hygon setup the lower bits of the APIC id distinguish the cores. - * Assumes number of cores is a power of two. - */ -static void hygon_detect_cmp(struct cpuinfo_x86 *c) -{ - unsigned int bits; - - bits = c->x86_coreid_bits; - /* Low order bits define the core id (index of core in socket) */ - c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1); - /* Convert the initial APIC ID into the socket ID */ - c->topo.pkg_id = c->topo.initial_apicid >> bits; - /* Use package ID also for last level cache */ - c->topo.llc_id = c->topo.die_id = c->topo.pkg_id; -} - static void srat_detect_node(struct cpuinfo_x86 *c) { #ifdef CONFIG_NUMA @@ -173,32 +91,6 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #endif } -static void early_init_hygon_mc(struct cpuinfo_x86 *c) -{ -#ifdef CONFIG_SMP - unsigned int bits, ecx; - - /* Multi core CPU? */ - if (c->extended_cpuid_level < 0x80000008) - return; - - ecx = cpuid_ecx(0x80000008); - - c->x86_max_cores = (ecx & 0xff) + 1; - - /* CPU telling us the core id bits shift? */ - bits = (ecx >> 12) & 0xF; - - /* Otherwise recompute */ - if (bits == 0) { - while ((1 << bits) < c->x86_max_cores) - bits++; - } - - c->x86_coreid_bits = bits; -#endif -} - static void bsp_init_hygon(struct cpuinfo_x86 *c) { if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) { @@ -212,18 +104,6 @@ static void bsp_init_hygon(struct cpuinfo_x86 *c) if (cpu_has(c, X86_FEATURE_MWAITX)) use_mwaitx_delay(); - if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { - u32 ecx; - - ecx = cpuid_ecx(0x8000001e); - __max_die_per_package = nodes_per_socket = ((ecx >> 8) & 7) + 1; - } else if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { - u64 value; - - rdmsrl(MSR_FAM10H_NODE_ID, value); - __max_die_per_package = nodes_per_socket = ((value >> 3) & 7) + 1; - } - if (!boot_cpu_has(X86_FEATURE_AMD_SSBD) && !boot_cpu_has(X86_FEATURE_VIRT_SSBD)) { /* @@ -242,8 +122,6 @@ static void early_init_hygon(struct cpuinfo_x86 *c) { u32 dummy; - early_init_hygon_mc(c); - set_cpu_cap(c, X86_FEATURE_K8); rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); @@ -284,8 +162,6 @@ static void early_init_hygon(struct cpuinfo_x86 *c) * we can set it unconditionally. */ set_cpu_cap(c, X86_FEATURE_VMMCALL); - - hygon_get_topology_early(c); } static void init_hygon(struct cpuinfo_x86 *c) @@ -302,9 +178,6 @@ static void init_hygon(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_REP_GOOD); - /* get apicid instead of initial apic id from cpuid */ - c->topo.apicid = read_apic_id(); - /* * XXX someone from Hygon needs to confirm this DTRT * @@ -316,8 +189,6 @@ static void init_hygon(struct cpuinfo_x86 *c) cpu_detect_cache_sizes(c); - hygon_detect_cmp(c); - hygon_get_topology(c); srat_detect_node(c); init_hygon_cacheinfo(c); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 40dec9b56f..93efd9edc7 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -268,19 +268,26 @@ detect_keyid_bits: c->x86_phys_bits -= keyid_bits; } +void intel_unlock_cpuid_leafs(struct cpuinfo_x86 *c) +{ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return; + + if (c->x86 < 6 || (c->x86 == 6 && c->x86_model < 0xd)) + return; + + /* + * The BIOS can have limited CPUID to leaf 2, which breaks feature + * enumeration. Unlock it and update the maximum leaf info. + */ + if (msr_clear_bit(MSR_IA32_MISC_ENABLE, MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) + c->cpuid_level = cpuid_eax(0); +} + static void early_init_intel(struct cpuinfo_x86 *c) { u64 misc_enable; - /* Unmask CPUID levels if masked: */ - if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) { - if (msr_clear_bit(MSR_IA32_MISC_ENABLE, - MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) { - c->cpuid_level = cpuid_eax(0); - get_cpu_cap(c); - } - } - if ((c->x86 == 0xf && c->x86_model >= 0x03) || (c->x86 == 0x6 && c->x86_model >= 0x0e)) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); @@ -401,13 +408,6 @@ static void early_init_intel(struct cpuinfo_x86 *c) check_memory_type_self_snoop_errata(c); /* - * Get the number of SMT siblings early from the extended topology - * leaf, if available. Otherwise try the legacy SMT detection. - */ - if (detect_extended_topology_early(c) < 0) - detect_ht_early(c); - - /* * Adjust the number of physical bits early because it affects the * valid bits of the MTRR mask registers. */ @@ -610,24 +610,6 @@ static void init_intel(struct cpuinfo_x86 *c) intel_workarounds(c); - /* - * Detect the extended topology information if available. This - * will reinitialise the initial_apicid which will be used - * in init_intel_cacheinfo() - */ - detect_extended_topology(c); - - if (!cpu_has(c, X86_FEATURE_XTOPOLOGY)) { - /* - * let's use the legacy cpuid vector 0x1 and 0x4 for topology - * detection. - */ - detect_num_cpu_cores(c); -#ifdef CONFIG_X86_32 - detect_ht(c); -#endif - } - init_intel_cacheinfo(c); if (c->cpuid_level > 9) { diff --git a/arch/x86/kernel/cpu/intel_pconfig.c b/arch/x86/kernel/cpu/intel_pconfig.c index 0771a905b2..5be2b17902 100644 --- a/arch/x86/kernel/cpu/intel_pconfig.c +++ b/arch/x86/kernel/cpu/intel_pconfig.c @@ -7,6 +7,8 @@ * Author: * Kirill A. Shutemov <kirill.shutemov@linux.intel.com> */ +#include <linux/bug.h> +#include <linux/limits.h> #include <asm/cpufeature.h> #include <asm/intel_pconfig.h> diff --git a/arch/x86/kernel/cpu/match.c b/arch/x86/kernel/cpu/match.c index ad6776081e..ae71b8ef90 100644 --- a/arch/x86/kernel/cpu/match.c +++ b/arch/x86/kernel/cpu/match.c @@ -39,9 +39,7 @@ const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match) const struct x86_cpu_id *m; struct cpuinfo_x86 *c = &boot_cpu_data; - for (m = match; - m->vendor | m->family | m->model | m->steppings | m->feature; - m++) { + for (m = match; m->flags & X86_CPU_ID_FLAG_ENTRY_VALID; m++) { if (m->vendor != X86_VENDOR_ANY && c->x86_vendor != m->vendor) continue; if (m->family != X86_FAMILY_ANY && c->x86 != m->family) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 2b46eb0fdf..9a0133ef7e 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -1231,7 +1231,7 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, return -ENODEV; if (is_shared_bank(bank)) { - nb = node_to_amd_nb(topology_die_id(cpu)); + nb = node_to_amd_nb(topology_amd_node_id(cpu)); /* threshold descriptor already initialized on this node? */ if (nb && nb->bank4) { @@ -1335,7 +1335,7 @@ static void threshold_remove_bank(struct threshold_bank *bank) * The last CPU on this node using the shared bank is going * away, remove that bank now. */ - nb = node_to_amd_nb(topology_die_id(smp_processor_id())); + nb = node_to_amd_nb(topology_amd_node_id(smp_processor_id())); nb->bank4 = NULL; } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index c17f9403cf..84d41be6d0 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -46,6 +46,7 @@ #include <linux/hardirq.h> #include <linux/kexec.h> +#include <asm/fred.h> #include <asm/intel-family.h> #include <asm/processor.h> #include <asm/traps.h> @@ -2166,6 +2167,31 @@ DEFINE_IDTENTRY_MCE_USER(exc_machine_check) exc_machine_check_user(regs); local_db_restore(dr7); } + +#ifdef CONFIG_X86_FRED +/* + * When occurred on different ring level, i.e., from user or kernel + * context, #MCE needs to be handled on different stack: User #MCE + * on current task stack, while kernel #MCE on a dedicated stack. + * + * This is exactly how FRED event delivery invokes an exception + * handler: ring 3 event on level 0 stack, i.e., current task stack; + * ring 0 event on the #MCE dedicated stack specified in the + * IA32_FRED_STKLVLS MSR. So unlike IDT, the FRED machine check entry + * stub doesn't do stack switch. + */ +DEFINE_FREDENTRY_MCE(exc_machine_check) +{ + unsigned long dr7; + + dr7 = local_db_save(); + if (user_mode(regs)) + exc_machine_check_user(regs); + else + exc_machine_check_kernel(regs); + local_db_restore(dr7); +} +#endif #else /* 32bit unified entry point */ DEFINE_IDTENTRY_RAW(exc_machine_check) @@ -2431,7 +2457,7 @@ static void mce_enable_ce(void *all) __mcheck_cpu_init_timer(); } -static struct bus_type mce_subsys = { +static const struct bus_type mce_subsys = { .name = "machinecheck", .dev_name = "machinecheck", }; diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 72f0695c3d..94953d7494 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -430,11 +430,9 @@ static void trigger_thr_int(void *info) static u32 get_nbc_for_node(int node_id) { - struct cpuinfo_x86 *c = &boot_cpu_data; u32 cores_per_node; - cores_per_node = (c->x86_max_cores * smp_num_siblings) / amd_get_nodes_per_socket(); - + cores_per_node = topology_num_threads_per_package() / topology_amd_nodes_per_pkg(); return cores_per_node * node_id; } @@ -543,8 +541,8 @@ static void do_inject(void) if (boot_cpu_has(X86_FEATURE_AMD_DCM) && b == 4 && boot_cpu_data.x86 < 0x17) { - toggle_nb_mca_mst_cpu(topology_die_id(cpu)); - cpu = get_nbc_for_node(topology_die_id(cpu)); + toggle_nb_mca_mst_cpu(topology_amd_node_id(cpu)); + cpu = get_nbc_for_node(topology_amd_node_id(cpu)); } cpus_read_lock(); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 857e608af6..5f0414452b 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -641,7 +641,7 @@ static __init void calc_llc_size_per_core(struct cpuinfo_x86 *c) { u64 llc_size = c->x86_cache_size * 1024ULL; - do_div(llc_size, c->x86_max_cores); + do_div(llc_size, topology_num_cores_per_package()); llc_size_per_core = (unsigned int)llc_size; } diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 01fa06dd06..e0fd57a8ba 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -45,70 +45,70 @@ bool hyperv_paravisor_present __ro_after_init; EXPORT_SYMBOL_GPL(hyperv_paravisor_present); #if IS_ENABLED(CONFIG_HYPERV) -static inline unsigned int hv_get_nested_reg(unsigned int reg) +static inline unsigned int hv_get_nested_msr(unsigned int reg) { - if (hv_is_sint_reg(reg)) - return reg - HV_REGISTER_SINT0 + HV_REGISTER_NESTED_SINT0; + if (hv_is_sint_msr(reg)) + return reg - HV_X64_MSR_SINT0 + HV_X64_MSR_NESTED_SINT0; switch (reg) { - case HV_REGISTER_SIMP: - return HV_REGISTER_NESTED_SIMP; - case HV_REGISTER_SIEFP: - return HV_REGISTER_NESTED_SIEFP; - case HV_REGISTER_SVERSION: - return HV_REGISTER_NESTED_SVERSION; - case HV_REGISTER_SCONTROL: - return HV_REGISTER_NESTED_SCONTROL; - case HV_REGISTER_EOM: - return HV_REGISTER_NESTED_EOM; + case HV_X64_MSR_SIMP: + return HV_X64_MSR_NESTED_SIMP; + case HV_X64_MSR_SIEFP: + return HV_X64_MSR_NESTED_SIEFP; + case HV_X64_MSR_SVERSION: + return HV_X64_MSR_NESTED_SVERSION; + case HV_X64_MSR_SCONTROL: + return HV_X64_MSR_NESTED_SCONTROL; + case HV_X64_MSR_EOM: + return HV_X64_MSR_NESTED_EOM; default: return reg; } } -u64 hv_get_non_nested_register(unsigned int reg) +u64 hv_get_non_nested_msr(unsigned int reg) { u64 value; - if (hv_is_synic_reg(reg) && ms_hyperv.paravisor_present) + if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present) hv_ivm_msr_read(reg, &value); else rdmsrl(reg, value); return value; } -EXPORT_SYMBOL_GPL(hv_get_non_nested_register); +EXPORT_SYMBOL_GPL(hv_get_non_nested_msr); -void hv_set_non_nested_register(unsigned int reg, u64 value) +void hv_set_non_nested_msr(unsigned int reg, u64 value) { - if (hv_is_synic_reg(reg) && ms_hyperv.paravisor_present) { + if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present) { hv_ivm_msr_write(reg, value); /* Write proxy bit via wrmsl instruction */ - if (hv_is_sint_reg(reg)) + if (hv_is_sint_msr(reg)) wrmsrl(reg, value | 1 << 20); } else { wrmsrl(reg, value); } } -EXPORT_SYMBOL_GPL(hv_set_non_nested_register); +EXPORT_SYMBOL_GPL(hv_set_non_nested_msr); -u64 hv_get_register(unsigned int reg) +u64 hv_get_msr(unsigned int reg) { if (hv_nested) - reg = hv_get_nested_reg(reg); + reg = hv_get_nested_msr(reg); - return hv_get_non_nested_register(reg); + return hv_get_non_nested_msr(reg); } -EXPORT_SYMBOL_GPL(hv_get_register); +EXPORT_SYMBOL_GPL(hv_get_msr); -void hv_set_register(unsigned int reg, u64 value) +void hv_set_msr(unsigned int reg, u64 value) { if (hv_nested) - reg = hv_get_nested_reg(reg); + reg = hv_get_nested_msr(reg); - hv_set_non_nested_register(reg, value); + hv_set_non_nested_msr(reg, value); } -EXPORT_SYMBOL_GPL(hv_set_register); +EXPORT_SYMBOL_GPL(hv_set_msr); static void (*vmbus_handler)(void); static void (*hv_stimer0_handler)(void); @@ -209,7 +209,9 @@ static void hv_machine_shutdown(void) if (kexec_in_progress) hyperv_cleanup(); } +#endif /* CONFIG_KEXEC_CORE */ +#ifdef CONFIG_CRASH_DUMP static void hv_machine_crash_shutdown(struct pt_regs *regs) { if (hv_crash_handler) @@ -221,7 +223,7 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs) /* Disable the hypercall page when there is only 1 active CPU. */ hyperv_cleanup(); } -#endif /* CONFIG_KEXEC_CORE */ +#endif /* CONFIG_CRASH_DUMP */ #endif /* CONFIG_HYPERV */ static uint32_t __init ms_hyperv_platform(void) @@ -350,13 +352,24 @@ static void __init reduced_hw_init(void) x86_init.irqs.pre_vector_init = x86_init_noop; } +int hv_get_hypervisor_version(union hv_hypervisor_version_info *info) +{ + unsigned int hv_max_functions; + + hv_max_functions = cpuid_eax(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS); + if (hv_max_functions < HYPERV_CPUID_VERSION) { + pr_err("%s: Could not detect Hyper-V version\n", __func__); + return -ENODEV; + } + + cpuid(HYPERV_CPUID_VERSION, &info->eax, &info->ebx, &info->ecx, &info->edx); + + return 0; +} + static void __init ms_hyperv_init_platform(void) { int hv_max_functions_eax; - int hv_host_info_eax; - int hv_host_info_ebx; - int hv_host_info_ecx; - int hv_host_info_edx; #ifdef CONFIG_PARAVIRT pv_info.name = "Hyper-V"; @@ -407,21 +420,6 @@ static void __init ms_hyperv_init_platform(void) pr_info("Hyper-V: running on a nested hypervisor\n"); } - /* - * Extract host information. - */ - if (hv_max_functions_eax >= HYPERV_CPUID_VERSION) { - hv_host_info_eax = cpuid_eax(HYPERV_CPUID_VERSION); - hv_host_info_ebx = cpuid_ebx(HYPERV_CPUID_VERSION); - hv_host_info_ecx = cpuid_ecx(HYPERV_CPUID_VERSION); - hv_host_info_edx = cpuid_edx(HYPERV_CPUID_VERSION); - - pr_info("Hyper-V: Host Build %d.%d.%d.%d-%d-%d\n", - hv_host_info_ebx >> 16, hv_host_info_ebx & 0xFFFF, - hv_host_info_eax, hv_host_info_edx & 0xFFFFFF, - hv_host_info_ecx, hv_host_info_edx >> 24); - } - if (ms_hyperv.features & HV_ACCESS_FREQUENCY_MSRS && ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { x86_platform.calibrate_tsc = hv_get_tsc_khz; @@ -454,7 +452,7 @@ static void __init ms_hyperv_init_platform(void) /* To be supported: more work is required. */ ms_hyperv.features &= ~HV_MSR_REFERENCE_TSC_AVAILABLE; - /* HV_REGISTER_CRASH_CTL is unsupported. */ + /* HV_MSR_CRASH_CTL is unsupported. */ ms_hyperv.misc_features &= ~HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE; /* Don't trust Hyper-V's TLB-flushing hypercalls. */ @@ -495,10 +493,14 @@ static void __init ms_hyperv_init_platform(void) no_timer_check = 1; #endif -#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE) +#if IS_ENABLED(CONFIG_HYPERV) +#if defined(CONFIG_KEXEC_CORE) machine_ops.shutdown = hv_machine_shutdown; +#endif +#if defined(CONFIG_CRASH_DUMP) machine_ops.crash_shutdown = hv_machine_crash_shutdown; #endif +#endif if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) { /* * Writing to synthetic MSR 0x40000118 updates/changes the @@ -539,19 +541,18 @@ static void __init ms_hyperv_init_platform(void) */ x86_platform.apic_post_init = hyperv_init; hyperv_setup_mmu_ops(); - /* Setup the IDT for hypervisor callback */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_hyperv_callback); - /* Setup the IDT for reenlightenment notifications */ + /* Install system interrupt handler for hypervisor callback */ + sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback); + + /* Install system interrupt handler for reenlightenment notifications */ if (ms_hyperv.features & HV_ACCESS_REENLIGHTENMENT) { - alloc_intr_gate(HYPERV_REENLIGHTENMENT_VECTOR, - asm_sysvec_hyperv_reenlightenment); + sysvec_install(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment); } - /* Setup the IDT for stimer0 */ + /* Install system interrupt handler for stimer0 */ if (ms_hyperv.misc_features & HV_STIMER_DIRECT_MODE_AVAILABLE) { - alloc_intr_gate(HYPERV_STIMER0_VECTOR, - asm_sysvec_hyperv_stimer0); + sysvec_install(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0); } # ifdef CONFIG_SMP @@ -643,6 +644,7 @@ const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = { .init.x2apic_available = ms_hyperv_x2apic_available, .init.msi_ext_dest_id = ms_hyperv_msi_ext_dest_id, .init.init_platform = ms_hyperv_init_platform, + .init.guest_late_init = ms_hyperv_late_init, #ifdef CONFIG_AMD_MEM_ENCRYPT .runtime.sev_es_hcall_prepare = hv_sev_es_hcall_prepare, .runtime.sev_es_hcall_finish = hv_sev_es_hcall_finish, diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index d3524778a5..7b29ebda02 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -108,6 +108,9 @@ static inline void k8_check_syscfg_dram_mod_en(void) (boot_cpu_data.x86 >= 0x0f))) return; + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return; + rdmsr(MSR_AMD64_SYSCFG, lo, hi); if (lo & K8_MTRRFIXRANGE_DRAM_MODIFY) { pr_err(FW_WARN "MTRR: CPU %u: SYSCFG[MtrrFixDramModEn]" diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c index 26a427fa84..eeac00d209 100644 --- a/arch/x86/kernel/cpu/rdrand.c +++ b/arch/x86/kernel/cpu/rdrand.c @@ -6,6 +6,7 @@ * Authors: Fenghua Yu <fenghua.yu@intel.com>, * H. Peter Anvin <hpa@linux.intel.com> */ +#include <linux/printk.h> #include <asm/processor.h> #include <asm/archrandom.h> diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index d04371e851..83e4034158 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -16,6 +16,7 @@ #define pr_fmt(fmt) "resctrl: " fmt +#include <linux/cpu.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/cacheinfo.h> @@ -25,8 +26,15 @@ #include <asm/resctrl.h> #include "internal.h" -/* Mutex to protect rdtgroup access. */ -DEFINE_MUTEX(rdtgroup_mutex); +/* + * rdt_domain structures are kfree()d when their last CPU goes offline, + * and allocated when the first CPU in a new domain comes online. + * The rdt_resource's domain list is updated when this happens. Readers of + * the domain list must either take cpus_read_lock(), or rely on an RCU + * read-side critical section, to avoid observing concurrent modification. + * All writers take this mutex: + */ +static DEFINE_MUTEX(domain_list_lock); /* * The cached resctrl_pqr_state is strictly per CPU and can never be @@ -136,15 +144,15 @@ static inline void cache_alloc_hsw_probe(void) { struct rdt_hw_resource *hw_res = &rdt_resources_all[RDT_RESOURCE_L3]; struct rdt_resource *r = &hw_res->r_resctrl; - u32 l, h, max_cbm = BIT_MASK(20) - 1; + u64 max_cbm = BIT_ULL_MASK(20) - 1, l3_cbm_0; - if (wrmsr_safe(MSR_IA32_L3_CBM_BASE, max_cbm, 0)) + if (wrmsrl_safe(MSR_IA32_L3_CBM_BASE, max_cbm)) return; - rdmsr(MSR_IA32_L3_CBM_BASE, l, h); + rdmsrl(MSR_IA32_L3_CBM_BASE, l3_cbm_0); /* If all the bits were set in MSR, return success */ - if (l != max_cbm) + if (l3_cbm_0 != max_cbm) return; hw_res->num_closid = 4; @@ -510,6 +518,8 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) struct rdt_domain *d; int err; + lockdep_assert_held(&domain_list_lock); + d = rdt_find_domain(r, id, &add_pos); if (IS_ERR(d)) { pr_warn("Couldn't find cache id for CPU %d\n", cpu); @@ -543,11 +553,12 @@ static void domain_add_cpu(int cpu, struct rdt_resource *r) return; } - list_add_tail(&d->list, add_pos); + list_add_tail_rcu(&d->list, add_pos); err = resctrl_online_domain(r, d); if (err) { - list_del(&d->list); + list_del_rcu(&d->list); + synchronize_rcu(); domain_free(hw_dom); } } @@ -558,6 +569,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) struct rdt_hw_domain *hw_dom; struct rdt_domain *d; + lockdep_assert_held(&domain_list_lock); + d = rdt_find_domain(r, id, NULL); if (IS_ERR_OR_NULL(d)) { pr_warn("Couldn't find cache id for CPU %d\n", cpu); @@ -568,7 +581,8 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) cpumask_clear_cpu(cpu, &d->cpu_mask); if (cpumask_empty(&d->cpu_mask)) { resctrl_offline_domain(r, d); - list_del(&d->list); + list_del_rcu(&d->list); + synchronize_rcu(); /* * rdt_domain "d" is going to be freed below, so clear @@ -580,73 +594,47 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r) return; } - - if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) { - if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { - cancel_delayed_work(&d->mbm_over); - mbm_setup_overflow_handler(d, 0); - } - if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && - has_busy_rmid(r, d)) { - cancel_delayed_work(&d->cqm_limbo); - cqm_setup_limbo_handler(d, 0); - } - } } static void clear_closid_rmid(int cpu) { struct resctrl_pqr_state *state = this_cpu_ptr(&pqr_state); - state->default_closid = 0; - state->default_rmid = 0; - state->cur_closid = 0; - state->cur_rmid = 0; - wrmsr(MSR_IA32_PQR_ASSOC, 0, 0); + state->default_closid = RESCTRL_RESERVED_CLOSID; + state->default_rmid = RESCTRL_RESERVED_RMID; + state->cur_closid = RESCTRL_RESERVED_CLOSID; + state->cur_rmid = RESCTRL_RESERVED_RMID; + wrmsr(MSR_IA32_PQR_ASSOC, RESCTRL_RESERVED_RMID, + RESCTRL_RESERVED_CLOSID); } -static int resctrl_online_cpu(unsigned int cpu) +static int resctrl_arch_online_cpu(unsigned int cpu) { struct rdt_resource *r; - mutex_lock(&rdtgroup_mutex); + mutex_lock(&domain_list_lock); for_each_capable_rdt_resource(r) domain_add_cpu(cpu, r); - /* The cpu is set in default rdtgroup after online. */ - cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); + mutex_unlock(&domain_list_lock); + clear_closid_rmid(cpu); - mutex_unlock(&rdtgroup_mutex); + resctrl_online_cpu(cpu); return 0; } -static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) +static int resctrl_arch_offline_cpu(unsigned int cpu) { - struct rdtgroup *cr; - - list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) { - if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) { - break; - } - } -} - -static int resctrl_offline_cpu(unsigned int cpu) -{ - struct rdtgroup *rdtgrp; struct rdt_resource *r; - mutex_lock(&rdtgroup_mutex); + resctrl_offline_cpu(cpu); + + mutex_lock(&domain_list_lock); for_each_capable_rdt_resource(r) domain_remove_cpu(cpu, r); - list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { - if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) { - clear_childcpus(rdtgrp, cpu); - break; - } - } + mutex_unlock(&domain_list_lock); + clear_closid_rmid(cpu); - mutex_unlock(&rdtgroup_mutex); return 0; } @@ -966,7 +954,8 @@ static int __init resctrl_late_init(void) state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/resctrl/cat:online:", - resctrl_online_cpu, resctrl_offline_cpu); + resctrl_arch_online_cpu, + resctrl_arch_offline_cpu); if (state < 0) return state; @@ -990,8 +979,14 @@ late_initcall(resctrl_late_init); static void __exit resctrl_exit(void) { + struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + cpuhp_remove_state(rdt_online); + rdtgroup_exit(); + + if (r->mon_capable) + rdt_put_mon_l3_config(); } __exitcall(resctrl_exit); diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index beccb0e87b..7997b47743 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -19,6 +19,8 @@ #include <linux/kernfs.h> #include <linux/seq_file.h> #include <linux/slab.h> +#include <linux/tick.h> + #include "internal.h" /* @@ -210,6 +212,9 @@ static int parse_line(char *line, struct resctrl_schema *s, struct rdt_domain *d; unsigned long dom_id; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP && (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) { rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n"); @@ -314,6 +319,9 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid) struct rdt_domain *d; u32 idx; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; @@ -379,11 +387,9 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, return -EINVAL; buf[nbytes - 1] = '\0'; - cpus_read_lock(); rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { rdtgroup_kn_unlock(of->kn); - cpus_read_unlock(); return -ENOENT; } rdt_last_cmd_clear(); @@ -445,7 +451,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of, out: rdt_staged_configs_clear(); rdtgroup_kn_unlock(of->kn); - cpus_read_unlock(); return ret ?: nbytes; } @@ -465,6 +470,9 @@ static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int clo bool sep = false; u32 ctrl_val; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + seq_printf(s, "%*s:", max_name_width, schema->name); list_for_each_entry(dom, &r->domains, list) { if (sep) @@ -522,12 +530,24 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of, return ret; } +static int smp_mon_event_count(void *arg) +{ + mon_event_count(arg); + + return 0; +} + void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_domain *d, struct rdtgroup *rdtgrp, int evtid, int first) { + int cpu; + + /* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + /* - * setup the parameters to send to the IPI to read the data. + * Setup the parameters to pass to mon_event_count() to read the data. */ rr->rgrp = rdtgrp; rr->evtid = evtid; @@ -535,8 +555,26 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, rr->d = d; rr->val = 0; rr->first = first; + rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid); + if (IS_ERR(rr->arch_mon_ctx)) { + rr->err = -EINVAL; + return; + } + + cpu = cpumask_any_housekeeping(&d->cpu_mask, RESCTRL_PICK_ANY_CPU); + + /* + * cpumask_any_housekeeping() prefers housekeeping CPUs, but + * are all the CPUs nohz_full? If yes, pick a CPU to IPI. + * MPAM's resctrl_arch_rmid_read() is unable to read the + * counters on some platforms if its called in IRQ context. + */ + if (tick_nohz_full_cpu(cpu)) + smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1); + else + smp_call_on_cpu(cpu, smp_mon_event_count, rr, false); - smp_call_function_any(&d->cpu_mask, mon_event_count, rr, 1); + resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx); } int rdtgroup_mondata_show(struct seq_file *m, void *arg) diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 52e7e7deee..1a8687f807 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -7,6 +7,9 @@ #include <linux/kernfs.h> #include <linux/fs_context.h> #include <linux/jump_label.h> +#include <linux/tick.h> + +#include <asm/resctrl.h> #define L3_QOS_CDP_ENABLE 0x01ULL @@ -53,6 +56,47 @@ /* Max event bits supported */ #define MAX_EVT_CONFIG_BITS GENMASK(6, 0) +/** + * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that + * aren't marked nohz_full + * @mask: The mask to pick a CPU from. + * @exclude_cpu:The CPU to avoid picking. + * + * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping + * CPUs that don't use nohz_full, these are preferred. Pass + * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs. + * + * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available. + */ +static inline unsigned int +cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu) +{ + unsigned int cpu, hk_cpu; + + if (exclude_cpu == RESCTRL_PICK_ANY_CPU) + cpu = cpumask_any(mask); + else + cpu = cpumask_any_but(mask, exclude_cpu); + + /* Only continue if tick_nohz_full_mask has been initialized. */ + if (!tick_nohz_full_enabled()) + return cpu; + + /* If the CPU picked isn't marked nohz_full nothing more needs doing. */ + if (cpu < nr_cpu_ids && !tick_nohz_full_cpu(cpu)) + return cpu; + + /* Try to find a CPU that isn't nohz_full to use in preference */ + hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask); + if (hk_cpu == exclude_cpu) + hk_cpu = cpumask_nth_andnot(1, mask, tick_nohz_full_mask); + + if (hk_cpu < nr_cpu_ids) + cpu = hk_cpu; + + return cpu; +} + struct rdt_fs_context { struct kernfs_fs_context kfc; bool enable_cdpl2; @@ -68,9 +112,6 @@ static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) return container_of(kfc, struct rdt_fs_context, kfc); } -DECLARE_STATIC_KEY_FALSE(rdt_enable_key); -DECLARE_STATIC_KEY_FALSE(rdt_mon_enable_key); - /** * struct mon_evt - Entry in the event list of a resource * @evtid: event id @@ -111,12 +152,12 @@ struct rmid_read { bool first; int err; u64 val; + void *arch_mon_ctx; }; -extern bool rdt_alloc_capable; -extern bool rdt_mon_capable; extern unsigned int rdt_mon_features; extern struct list_head resctrl_schema_all; +extern bool resctrl_mounted; enum rdt_group_type { RDTCTRL_GROUP = 0, @@ -424,8 +465,6 @@ extern struct mutex rdtgroup_mutex; extern struct rdt_hw_resource rdt_resources_all[]; extern struct rdtgroup rdtgroup_default; -DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key); - extern struct dentry *debugfs_resctrl; enum resctrl_res_level { @@ -541,9 +580,10 @@ void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp); struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r); int closids_supported(void); void closid_free(int closid); -int alloc_rmid(void); -void free_rmid(u32 rmid); +int alloc_rmid(u32 closid); +void free_rmid(u32 closid, u32 rmid); int rdt_get_mon_l3_config(struct rdt_resource *r); +void __exit rdt_put_mon_l3_config(void); bool __init rdt_cpu_has(int flag); void mon_event_count(void *info); int rdtgroup_mondata_show(struct seq_file *m, void *arg); @@ -551,17 +591,21 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r, struct rdt_domain *d, struct rdtgroup *rdtgrp, int evtid, int first); void mbm_setup_overflow_handler(struct rdt_domain *dom, - unsigned long delay_ms); + unsigned long delay_ms, + int exclude_cpu); void mbm_handle_overflow(struct work_struct *work); void __init intel_rdt_mbm_apply_quirk(void); bool is_mba_sc(struct rdt_resource *r); -void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms); +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms, + int exclude_cpu); void cqm_handle_limbo(struct work_struct *work); -bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d); +bool has_busy_rmid(struct rdt_domain *d); void __check_limbo(struct rdt_domain *d, bool force_free); void rdt_domain_reconfigure_cdp(struct rdt_resource *r); void __init thread_throttle_mode_init(void); void __init mbm_config_rftype_init(const char *config); void rdt_staged_configs_clear(void); +bool closid_allocated(unsigned int closid); +int resctrl_find_cleanest_closid(void); #endif /* _ASM_X86_RESCTRL_INTERNAL_H */ diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index 3a6c069614..2ce5f4913c 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -15,6 +15,7 @@ * Software Developer Manual June 2016, volume 3, section 17.17. */ +#include <linux/cpu.h> #include <linux/module.h> #include <linux/sizes.h> #include <linux/slab.h> @@ -24,7 +25,20 @@ #include "internal.h" +/** + * struct rmid_entry - dirty tracking for all RMID. + * @closid: The CLOSID for this entry. + * @rmid: The RMID for this entry. + * @busy: The number of domains with cached data using this RMID. + * @list: Member of the rmid_free_lru list when busy == 0. + * + * Depending on the architecture the correct monitor is accessed using + * both @closid and @rmid, or @rmid only. + * + * Take the rdtgroup_mutex when accessing. + */ struct rmid_entry { + u32 closid; u32 rmid; int busy; struct list_head list; @@ -38,6 +52,13 @@ struct rmid_entry { static LIST_HEAD(rmid_free_lru); /* + * @closid_num_dirty_rmid The number of dirty RMID each CLOSID has. + * Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined. + * Indexed by CLOSID. Protected by rdtgroup_mutex. + */ +static u32 *closid_num_dirty_rmid; + +/* * @rmid_limbo_count - count of currently unused but (potentially) * dirty RMIDs. * This counts RMIDs that no one is currently using but that @@ -136,12 +157,29 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val) return val; } -static inline struct rmid_entry *__rmid_entry(u32 rmid) +/* + * x86 and arm64 differ in their handling of monitoring. + * x86's RMID are independent numbers, there is only one source of traffic + * with an RMID value of '1'. + * arm64's PMG extends the PARTID/CLOSID space, there are multiple sources of + * traffic with a PMG value of '1', one for each CLOSID, meaning the RMID + * value is no longer unique. + * To account for this, resctrl uses an index. On x86 this is just the RMID, + * on arm64 it encodes the CLOSID and RMID. This gives a unique number. + * + * The domain's rmid_busy_llc and rmid_ptrs[] are sized by index. The arch code + * must accept an attempt to read every index. + */ +static inline struct rmid_entry *__rmid_entry(u32 idx) { struct rmid_entry *entry; + u32 closid, rmid; + + entry = &rmid_ptrs[idx]; + resctrl_arch_rmid_idx_decode(idx, &closid, &rmid); - entry = &rmid_ptrs[rmid]; - WARN_ON(entry->rmid != rmid); + WARN_ON_ONCE(entry->closid != closid); + WARN_ON_ONCE(entry->rmid != rmid); return entry; } @@ -190,7 +228,8 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_domain *hw_dom, } void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d, - u32 rmid, enum resctrl_event_id eventid) + u32 unused, u32 rmid, + enum resctrl_event_id eventid) { struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); struct arch_mbm_state *am; @@ -230,7 +269,8 @@ static u64 mbm_overflow_count(u64 prev_msr, u64 cur_msr, unsigned int width) } int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, - u32 rmid, enum resctrl_event_id eventid, u64 *val) + u32 unused, u32 rmid, enum resctrl_event_id eventid, + u64 *val, void *ignored) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); struct rdt_hw_domain *hw_dom = resctrl_to_arch_dom(d); @@ -238,6 +278,8 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, u64 msr_val, chunks; int ret; + resctrl_arch_rmid_read_context_check(); + if (!cpumask_test_cpu(smp_processor_id(), &d->cpu_mask)) return -EINVAL; @@ -260,6 +302,17 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, return 0; } +static void limbo_release_entry(struct rmid_entry *entry) +{ + lockdep_assert_held(&rdtgroup_mutex); + + rmid_limbo_count--; + list_add_tail(&entry->list, &rmid_free_lru); + + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + closid_num_dirty_rmid[entry->closid]--; +} + /* * Check the RMIDs that are marked as busy for this domain. If the * reported LLC occupancy is below the threshold clear the busy bit and @@ -269,11 +322,20 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_domain *d, void __check_limbo(struct rdt_domain *d, bool force_free) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); struct rmid_entry *entry; - u32 crmid = 1, nrmid; + u32 idx, cur_idx = 1; + void *arch_mon_ctx; bool rmid_dirty; u64 val = 0; + arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID); + if (IS_ERR(arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(arch_mon_ctx)); + return; + } + /* * Skip RMID 0 and start from RMID 1 and check all the RMIDs that * are marked as busy for occupancy < threshold. If the occupancy @@ -281,53 +343,125 @@ void __check_limbo(struct rdt_domain *d, bool force_free) * RMID and move it to the free list when the counter reaches 0. */ for (;;) { - nrmid = find_next_bit(d->rmid_busy_llc, r->num_rmid, crmid); - if (nrmid >= r->num_rmid) + idx = find_next_bit(d->rmid_busy_llc, idx_limit, cur_idx); + if (idx >= idx_limit) break; - entry = __rmid_entry(nrmid); - - if (resctrl_arch_rmid_read(r, d, entry->rmid, - QOS_L3_OCCUP_EVENT_ID, &val)) { + entry = __rmid_entry(idx); + if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid, + QOS_L3_OCCUP_EVENT_ID, &val, + arch_mon_ctx)) { rmid_dirty = true; } else { rmid_dirty = (val >= resctrl_rmid_realloc_threshold); } if (force_free || !rmid_dirty) { - clear_bit(entry->rmid, d->rmid_busy_llc); - if (!--entry->busy) { - rmid_limbo_count--; - list_add_tail(&entry->list, &rmid_free_lru); - } + clear_bit(idx, d->rmid_busy_llc); + if (!--entry->busy) + limbo_release_entry(entry); } - crmid = nrmid + 1; + cur_idx = idx + 1; + } + + resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx); +} + +bool has_busy_rmid(struct rdt_domain *d) +{ + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); + + return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit; +} + +static struct rmid_entry *resctrl_find_free_rmid(u32 closid) +{ + struct rmid_entry *itr; + u32 itr_idx, cmp_idx; + + if (list_empty(&rmid_free_lru)) + return rmid_limbo_count ? ERR_PTR(-EBUSY) : ERR_PTR(-ENOSPC); + + list_for_each_entry(itr, &rmid_free_lru, list) { + /* + * Get the index of this free RMID, and the index it would need + * to be if it were used with this CLOSID. + * If the CLOSID is irrelevant on this architecture, the two + * index values are always the same on every entry and thus the + * very first entry will be returned. + */ + itr_idx = resctrl_arch_rmid_idx_encode(itr->closid, itr->rmid); + cmp_idx = resctrl_arch_rmid_idx_encode(closid, itr->rmid); + + if (itr_idx == cmp_idx) + return itr; } + + return ERR_PTR(-ENOSPC); } -bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d) +/** + * resctrl_find_cleanest_closid() - Find a CLOSID where all the associated + * RMID are clean, or the CLOSID that has + * the most clean RMID. + * + * MPAM's equivalent of RMID are per-CLOSID, meaning a freshly allocated CLOSID + * may not be able to allocate clean RMID. To avoid this the allocator will + * choose the CLOSID with the most clean RMID. + * + * When the CLOSID and RMID are independent numbers, the first free CLOSID will + * be returned. + */ +int resctrl_find_cleanest_closid(void) { - return find_first_bit(d->rmid_busy_llc, r->num_rmid) != r->num_rmid; + u32 cleanest_closid = ~0; + int i = 0; + + lockdep_assert_held(&rdtgroup_mutex); + + if (!IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + return -EIO; + + for (i = 0; i < closids_supported(); i++) { + int num_dirty; + + if (closid_allocated(i)) + continue; + + num_dirty = closid_num_dirty_rmid[i]; + if (num_dirty == 0) + return i; + + if (cleanest_closid == ~0) + cleanest_closid = i; + + if (num_dirty < closid_num_dirty_rmid[cleanest_closid]) + cleanest_closid = i; + } + + if (cleanest_closid == ~0) + return -ENOSPC; + + return cleanest_closid; } /* - * As of now the RMIDs allocation is global. - * However we keep track of which packages the RMIDs - * are used to optimize the limbo list management. + * For MPAM the RMID value is not unique, and has to be considered with + * the CLOSID. The (CLOSID, RMID) pair is allocated on all domains, which + * allows all domains to be managed by a single free list. + * Each domain also has a rmid_busy_llc to reduce the work of the limbo handler. */ -int alloc_rmid(void) +int alloc_rmid(u32 closid) { struct rmid_entry *entry; lockdep_assert_held(&rdtgroup_mutex); - if (list_empty(&rmid_free_lru)) - return rmid_limbo_count ? -EBUSY : -ENOSPC; + entry = resctrl_find_free_rmid(closid); + if (IS_ERR(entry)) + return PTR_ERR(entry); - entry = list_first_entry(&rmid_free_lru, - struct rmid_entry, list); list_del(&entry->list); - return entry->rmid; } @@ -335,47 +469,51 @@ static void add_rmid_to_limbo(struct rmid_entry *entry) { struct rdt_resource *r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; struct rdt_domain *d; - int cpu, err; - u64 val = 0; + u32 idx; + + lockdep_assert_held(&rdtgroup_mutex); + + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + + idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid); entry->busy = 0; - cpu = get_cpu(); list_for_each_entry(d, &r->domains, list) { - if (cpumask_test_cpu(cpu, &d->cpu_mask)) { - err = resctrl_arch_rmid_read(r, d, entry->rmid, - QOS_L3_OCCUP_EVENT_ID, - &val); - if (err || val <= resctrl_rmid_realloc_threshold) - continue; - } - /* * For the first limbo RMID in the domain, * setup up the limbo worker. */ - if (!has_busy_rmid(r, d)) - cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL); - set_bit(entry->rmid, d->rmid_busy_llc); + if (!has_busy_rmid(d)) + cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL, + RESCTRL_PICK_ANY_CPU); + set_bit(idx, d->rmid_busy_llc); entry->busy++; } - put_cpu(); - if (entry->busy) - rmid_limbo_count++; - else - list_add_tail(&entry->list, &rmid_free_lru); + rmid_limbo_count++; + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) + closid_num_dirty_rmid[entry->closid]++; } -void free_rmid(u32 rmid) +void free_rmid(u32 closid, u32 rmid) { + u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); struct rmid_entry *entry; - if (!rmid) - return; - lockdep_assert_held(&rdtgroup_mutex); - entry = __rmid_entry(rmid); + /* + * Do not allow the default rmid to be free'd. Comparing by index + * allows architectures that ignore the closid parameter to avoid an + * unnecessary check. + */ + if (!resctrl_arch_mon_capable() || + idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, + RESCTRL_RESERVED_RMID)) + return; + + entry = __rmid_entry(idx); if (is_llc_occupancy_enabled()) add_rmid_to_limbo(entry); @@ -383,33 +521,36 @@ void free_rmid(u32 rmid) list_add_tail(&entry->list, &rmid_free_lru); } -static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 rmid, - enum resctrl_event_id evtid) +static struct mbm_state *get_mbm_state(struct rdt_domain *d, u32 closid, + u32 rmid, enum resctrl_event_id evtid) { + u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); + switch (evtid) { case QOS_L3_MBM_TOTAL_EVENT_ID: - return &d->mbm_total[rmid]; + return &d->mbm_total[idx]; case QOS_L3_MBM_LOCAL_EVENT_ID: - return &d->mbm_local[rmid]; + return &d->mbm_local[idx]; default: return NULL; } } -static int __mon_event_count(u32 rmid, struct rmid_read *rr) +static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr) { struct mbm_state *m; u64 tval = 0; if (rr->first) { - resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid); - m = get_mbm_state(rr->d, rmid, rr->evtid); + resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid); + m = get_mbm_state(rr->d, closid, rmid, rr->evtid); if (m) memset(m, 0, sizeof(struct mbm_state)); return 0; } - rr->err = resctrl_arch_rmid_read(rr->r, rr->d, rmid, rr->evtid, &tval); + rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid, rr->evtid, + &tval, rr->arch_mon_ctx); if (rr->err) return rr->err; @@ -421,6 +562,7 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) /* * mbm_bw_count() - Update bw count from values previously read by * __mon_event_count(). + * @closid: The closid used to identify the cached mbm_state. * @rmid: The rmid used to identify the cached mbm_state. * @rr: The struct rmid_read populated by __mon_event_count(). * @@ -429,9 +571,10 @@ static int __mon_event_count(u32 rmid, struct rmid_read *rr) * __mon_event_count() is compared with the chunks value from the previous * invocation. This must be called once per second to maintain values in MBps. */ -static void mbm_bw_count(u32 rmid, struct rmid_read *rr) +static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr) { - struct mbm_state *m = &rr->d->mbm_local[rmid]; + u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid); + struct mbm_state *m = &rr->d->mbm_local[idx]; u64 cur_bw, bytes, cur_bytes; cur_bytes = rr->val; @@ -444,7 +587,7 @@ static void mbm_bw_count(u32 rmid, struct rmid_read *rr) } /* - * This is called via IPI to read the CQM/MBM counters + * This is scheduled by mon_event_read() to read the CQM/MBM counters * on a domain. */ void mon_event_count(void *info) @@ -456,7 +599,7 @@ void mon_event_count(void *info) rdtgrp = rr->rgrp; - ret = __mon_event_count(rdtgrp->mon.rmid, rr); + ret = __mon_event_count(rdtgrp->closid, rdtgrp->mon.rmid, rr); /* * For Ctrl groups read data from child monitor groups and @@ -467,7 +610,8 @@ void mon_event_count(void *info) if (rdtgrp->type == RDTCTRL_GROUP) { list_for_each_entry(entry, head, mon.crdtgrp_list) { - if (__mon_event_count(entry->mon.rmid, rr) == 0) + if (__mon_event_count(entry->closid, entry->mon.rmid, + rr) == 0) ret = 0; } } @@ -519,9 +663,9 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) struct mbm_state *pmbm_data, *cmbm_data; struct rdt_resource *r_mba; struct rdt_domain *dom_mba; + u32 cur_bw, user_bw, idx; struct list_head *head; struct rdtgroup *entry; - u32 cur_bw, user_bw; if (!is_mbm_local_enabled()) return; @@ -530,7 +674,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) closid = rgrp->closid; rmid = rgrp->mon.rmid; - pmbm_data = &dom_mbm->mbm_local[rmid]; + idx = resctrl_arch_rmid_idx_encode(closid, rmid); + pmbm_data = &dom_mbm->mbm_local[idx]; dom_mba = get_domain_from_cpu(smp_processor_id(), r_mba); if (!dom_mba) { @@ -578,7 +723,8 @@ static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_domain *dom_mbm) resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val); } -static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) +static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, + u32 closid, u32 rmid) { struct rmid_read rr; @@ -593,12 +739,28 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) if (is_mbm_total_enabled()) { rr.evtid = QOS_L3_MBM_TOTAL_EVENT_ID; rr.val = 0; - __mon_event_count(rmid, &rr); + rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); + if (IS_ERR(rr.arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(rr.arch_mon_ctx)); + return; + } + + __mon_event_count(closid, rmid, &rr); + + resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); } if (is_mbm_local_enabled()) { rr.evtid = QOS_L3_MBM_LOCAL_EVENT_ID; rr.val = 0; - __mon_event_count(rmid, &rr); + rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid); + if (IS_ERR(rr.arch_mon_ctx)) { + pr_warn_ratelimited("Failed to allocate monitor context: %ld", + PTR_ERR(rr.arch_mon_ctx)); + return; + } + + __mon_event_count(closid, rmid, &rr); /* * Call the MBA software controller only for the @@ -606,7 +768,9 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) * the software controller explicitly. */ if (is_mba_sc(NULL)) - mbm_bw_count(rmid, &rr); + mbm_bw_count(closid, rmid, &rr); + + resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx); } } @@ -617,106 +781,193 @@ static void mbm_update(struct rdt_resource *r, struct rdt_domain *d, int rmid) void cqm_handle_limbo(struct work_struct *work) { unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL); - int cpu = smp_processor_id(); - struct rdt_resource *r; struct rdt_domain *d; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); - r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; d = container_of(work, struct rdt_domain, cqm_limbo.work); __check_limbo(d, false); - if (has_busy_rmid(r, d)) - schedule_delayed_work_on(cpu, &d->cqm_limbo, delay); + if (has_busy_rmid(d)) { + d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask, + RESCTRL_PICK_ANY_CPU); + schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo, + delay); + } mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); } -void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms) +/** + * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this + * domain. + * @dom: The domain the limbo handler should run for. + * @delay_ms: How far in the future the handler should run. + * @exclude_cpu: Which CPU the handler should not run on, + * RESCTRL_PICK_ANY_CPU to pick any CPU. + */ +void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms, + int exclude_cpu) { unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - cpu = cpumask_any(&dom->cpu_mask); + cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu); dom->cqm_work_cpu = cpu; - schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay); + if (cpu < nr_cpu_ids) + schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay); } void mbm_handle_overflow(struct work_struct *work) { unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL); struct rdtgroup *prgrp, *crgrp; - int cpu = smp_processor_id(); struct list_head *head; struct rdt_resource *r; struct rdt_domain *d; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); - if (!static_branch_likely(&rdt_mon_enable_key)) + /* + * If the filesystem has been unmounted this work no longer needs to + * run. + */ + if (!resctrl_mounted || !resctrl_arch_mon_capable()) goto out_unlock; r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; d = container_of(work, struct rdt_domain, mbm_over.work); list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) { - mbm_update(r, d, prgrp->mon.rmid); + mbm_update(r, d, prgrp->closid, prgrp->mon.rmid); head = &prgrp->mon.crdtgrp_list; list_for_each_entry(crgrp, head, mon.crdtgrp_list) - mbm_update(r, d, crgrp->mon.rmid); + mbm_update(r, d, crgrp->closid, crgrp->mon.rmid); if (is_mba_sc(NULL)) update_mba_bw(prgrp, d); } - schedule_delayed_work_on(cpu, &d->mbm_over, delay); + /* + * Re-check for housekeeping CPUs. This allows the overflow handler to + * move off a nohz_full CPU quickly. + */ + d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask, + RESCTRL_PICK_ANY_CPU); + schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay); out_unlock: mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); } -void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms) +/** + * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this + * domain. + * @dom: The domain the overflow handler should run for. + * @delay_ms: How far in the future the handler should run. + * @exclude_cpu: Which CPU the handler should not run on, + * RESCTRL_PICK_ANY_CPU to pick any CPU. + */ +void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms, + int exclude_cpu) { unsigned long delay = msecs_to_jiffies(delay_ms); int cpu; - if (!static_branch_likely(&rdt_mon_enable_key)) + /* + * When a domain comes online there is no guarantee the filesystem is + * mounted. If not, there is no need to catch counter overflow. + */ + if (!resctrl_mounted || !resctrl_arch_mon_capable()) return; - cpu = cpumask_any(&dom->cpu_mask); + cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu); dom->mbm_work_cpu = cpu; - schedule_delayed_work_on(cpu, &dom->mbm_over, delay); + + if (cpu < nr_cpu_ids) + schedule_delayed_work_on(cpu, &dom->mbm_over, delay); } static int dom_data_init(struct rdt_resource *r) { + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); + u32 num_closid = resctrl_arch_get_num_closid(r); struct rmid_entry *entry = NULL; - int i, nr_rmids; + int err = 0, i; + u32 idx; + + mutex_lock(&rdtgroup_mutex); + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + u32 *tmp; + + /* + * If the architecture hasn't provided a sanitised value here, + * this may result in larger arrays than necessary. Resctrl will + * use a smaller system wide value based on the resources in + * use. + */ + tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL); + if (!tmp) { + err = -ENOMEM; + goto out_unlock; + } - nr_rmids = r->num_rmid; - rmid_ptrs = kcalloc(nr_rmids, sizeof(struct rmid_entry), GFP_KERNEL); - if (!rmid_ptrs) - return -ENOMEM; + closid_num_dirty_rmid = tmp; + } - for (i = 0; i < nr_rmids; i++) { + rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL); + if (!rmid_ptrs) { + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + kfree(closid_num_dirty_rmid); + closid_num_dirty_rmid = NULL; + } + err = -ENOMEM; + goto out_unlock; + } + + for (i = 0; i < idx_limit; i++) { entry = &rmid_ptrs[i]; INIT_LIST_HEAD(&entry->list); - entry->rmid = i; + resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid); list_add_tail(&entry->list, &rmid_free_lru); } /* - * RMID 0 is special and is always allocated. It's used for all - * tasks that are not monitored. + * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and + * are always allocated. These are used for the rdtgroup_default + * control group, which will be setup later in rdtgroup_init(). */ - entry = __rmid_entry(0); + idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID, + RESCTRL_RESERVED_RMID); + entry = __rmid_entry(idx); list_del(&entry->list); - return 0; +out_unlock: + mutex_unlock(&rdtgroup_mutex); + + return err; +} + +static void __exit dom_data_exit(void) +{ + mutex_lock(&rdtgroup_mutex); + + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + kfree(closid_num_dirty_rmid); + closid_num_dirty_rmid = NULL; + } + + kfree(rmid_ptrs); + rmid_ptrs = NULL; + + mutex_unlock(&rdtgroup_mutex); } static struct mon_evt llc_occupancy_event = { @@ -814,6 +1065,11 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r) return 0; } +void __exit rdt_put_mon_l3_config(void) +{ + dom_data_exit(); +} + void __init intel_rdt_mbm_apply_quirk(void) { int cf_index; diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c index 8f559eeae0..884b88e251 100644 --- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c +++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c @@ -581,7 +581,7 @@ static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp) if (ret) goto err_cpus; - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups"); if (ret) goto err_cpus_list; @@ -628,7 +628,7 @@ static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp) if (ret) goto err_cpus; - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777); if (ret) goto err_cpus_list; @@ -752,7 +752,7 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp) * anymore when this group would be used for pseudo-locking. This * is safe to call on platforms not capable of monitoring. */ - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); ret = 0; goto out; @@ -776,8 +776,8 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) { int ret; - if (rdt_mon_capable) { - ret = alloc_rmid(); + if (resctrl_arch_mon_capable()) { + ret = alloc_rmid(rdtgrp->closid); if (ret < 0) { rdt_last_cmd_puts("Out of RMIDs\n"); return ret; @@ -787,7 +787,7 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp) ret = rdtgroup_locksetup_user_restore(rdtgrp); if (ret) { - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); return ret; } @@ -844,6 +844,9 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d) struct rdt_domain *d_i; bool ret = false; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL)) return true; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 2b69e560b0..011e17efb1 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -35,6 +35,10 @@ DEFINE_STATIC_KEY_FALSE(rdt_enable_key); DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key); DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key); + +/* Mutex to protect rdtgroup access. */ +DEFINE_MUTEX(rdtgroup_mutex); + static struct kernfs_root *rdt_root; struct rdtgroup rdtgroup_default; LIST_HEAD(rdt_all_groups); @@ -42,6 +46,9 @@ LIST_HEAD(rdt_all_groups); /* list of entries for the schemata file */ LIST_HEAD(resctrl_schema_all); +/* The filesystem can only be mounted once. */ +bool resctrl_mounted; + /* Kernel fs node for "info" directory under root */ static struct kernfs_node *kn_info; @@ -102,7 +109,7 @@ void rdt_staged_configs_clear(void) * * Using a global CLOSID across all resources has some advantages and * some drawbacks: - * + We can simply set "current->closid" to assign a task to a resource + * + We can simply set current's closid to assign a task to a resource * group. * + Context switch code can avoid extra memory references deciding which * CLOSID to load into the PQR_ASSOC MSR @@ -111,7 +118,7 @@ void rdt_staged_configs_clear(void) * - Our choices on how to configure each resource become progressively more * limited as the number of resources grows. */ -static int closid_free_map; +static unsigned long closid_free_map; static int closid_free_map_len; int closids_supported(void) @@ -130,26 +137,39 @@ static void closid_init(void) closid_free_map = BIT_MASK(rdt_min_closid) - 1; - /* CLOSID 0 is always reserved for the default group */ - closid_free_map &= ~1; + /* RESCTRL_RESERVED_CLOSID is always reserved for the default group */ + __clear_bit(RESCTRL_RESERVED_CLOSID, &closid_free_map); closid_free_map_len = rdt_min_closid; } static int closid_alloc(void) { - u32 closid = ffs(closid_free_map); + int cleanest_closid; + u32 closid; - if (closid == 0) - return -ENOSPC; - closid--; - closid_free_map &= ~(1 << closid); + lockdep_assert_held(&rdtgroup_mutex); + + if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) { + cleanest_closid = resctrl_find_cleanest_closid(); + if (cleanest_closid < 0) + return cleanest_closid; + closid = cleanest_closid; + } else { + closid = ffs(closid_free_map); + if (closid == 0) + return -ENOSPC; + closid--; + } + __clear_bit(closid, &closid_free_map); return closid; } void closid_free(int closid) { - closid_free_map |= 1 << closid; + lockdep_assert_held(&rdtgroup_mutex); + + __set_bit(closid, &closid_free_map); } /** @@ -159,9 +179,11 @@ void closid_free(int closid) * Return: true if @closid is currently associated with a resource group, * false if @closid is free */ -static bool closid_allocated(unsigned int closid) +bool closid_allocated(unsigned int closid) { - return (closid_free_map & (1 << closid)) == 0; + lockdep_assert_held(&rdtgroup_mutex); + + return !test_bit(closid, &closid_free_map); } /** @@ -559,14 +581,26 @@ static void update_task_closid_rmid(struct task_struct *t) _update_task_closid_rmid(t); } +static bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp) +{ + u32 closid, rmid = rdtgrp->mon.rmid; + + if (rdtgrp->type == RDTCTRL_GROUP) + closid = rdtgrp->closid; + else if (rdtgrp->type == RDTMON_GROUP) + closid = rdtgrp->mon.parent->closid; + else + return false; + + return resctrl_arch_match_closid(tsk, closid) && + resctrl_arch_match_rmid(tsk, closid, rmid); +} + static int __rdtgroup_move_task(struct task_struct *tsk, struct rdtgroup *rdtgrp) { /* If the task is already in rdtgrp, no need to move the task. */ - if ((rdtgrp->type == RDTCTRL_GROUP && tsk->closid == rdtgrp->closid && - tsk->rmid == rdtgrp->mon.rmid) || - (rdtgrp->type == RDTMON_GROUP && tsk->rmid == rdtgrp->mon.rmid && - tsk->closid == rdtgrp->mon.parent->closid)) + if (task_in_rdtgroup(tsk, rdtgrp)) return 0; /* @@ -577,19 +611,19 @@ static int __rdtgroup_move_task(struct task_struct *tsk, * For monitor groups, can move the tasks only from * their parent CTRL group. */ - - if (rdtgrp->type == RDTCTRL_GROUP) { - WRITE_ONCE(tsk->closid, rdtgrp->closid); - WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); - } else if (rdtgrp->type == RDTMON_GROUP) { - if (rdtgrp->mon.parent->closid == tsk->closid) { - WRITE_ONCE(tsk->rmid, rdtgrp->mon.rmid); - } else { - rdt_last_cmd_puts("Can't move task to different control group\n"); - return -EINVAL; - } + if (rdtgrp->type == RDTMON_GROUP && + !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) { + rdt_last_cmd_puts("Can't move task to different control group\n"); + return -EINVAL; } + if (rdtgrp->type == RDTMON_GROUP) + resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid, + rdtgrp->mon.rmid); + else + resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid, + rdtgrp->mon.rmid); + /* * Ensure the task's closid and rmid are written before determining if * the task is current that will decide if it will be interrupted. @@ -611,14 +645,15 @@ static int __rdtgroup_move_task(struct task_struct *tsk, static bool is_closid_match(struct task_struct *t, struct rdtgroup *r) { - return (rdt_alloc_capable && - (r->type == RDTCTRL_GROUP) && (t->closid == r->closid)); + return (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) && + resctrl_arch_match_closid(t, r->closid)); } static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r) { - return (rdt_mon_capable && - (r->type == RDTMON_GROUP) && (t->rmid == r->mon.rmid)); + return (resctrl_arch_mon_capable() && (r->type == RDTMON_GROUP) && + resctrl_arch_match_rmid(t, r->mon.parent->closid, + r->mon.rmid)); } /** @@ -853,7 +888,7 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, mutex_lock(&rdtgroup_mutex); /* Return empty if resctrl has not been mounted. */ - if (!static_branch_unlikely(&rdt_enable_key)) { + if (!resctrl_mounted) { seq_puts(s, "res:\nmon:\n"); goto unlock; } @@ -869,7 +904,7 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, rdtg->mode != RDT_MODE_EXCLUSIVE) continue; - if (rdtg->closid != tsk->closid) + if (!resctrl_arch_match_closid(tsk, rdtg->closid)) continue; seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "", @@ -877,7 +912,8 @@ int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns, seq_puts(s, "mon:"); list_for_each_entry(crg, &rdtg->mon.crdtgrp_list, mon.crdtgrp_list) { - if (tsk->rmid != crg->mon.rmid) + if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid, + crg->mon.rmid)) continue; seq_printf(s, "%s", crg->kn->name); break; @@ -982,6 +1018,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, bool sep = false; u32 ctrl_val; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); hw_shareable = r->cache.shareable_bits; list_for_each_entry(dom, &r->domains, list) { @@ -1042,6 +1079,7 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of, } seq_putc(seq, '\n'); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return 0; } @@ -1297,6 +1335,9 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) struct rdt_domain *d; u32 ctrl; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA) @@ -1561,6 +1602,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid struct rdt_domain *dom; bool sep = false; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); list_for_each_entry(dom, &r->domains, list) { @@ -1577,6 +1619,7 @@ static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid seq_puts(s, "\n"); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return 0; } @@ -1614,11 +1657,10 @@ static void mon_event_config_write(void *info) wrmsr(MSR_IA32_EVT_CFG_BASE + index, mon_info->mon_config, 0); } -static int mbm_config_write_domain(struct rdt_resource *r, - struct rdt_domain *d, u32 evtid, u32 val) +static void mbm_config_write_domain(struct rdt_resource *r, + struct rdt_domain *d, u32 evtid, u32 val) { struct mon_config_info mon_info = {0}; - int ret = 0; /* * Read the current config value first. If both are the same then @@ -1627,7 +1669,7 @@ static int mbm_config_write_domain(struct rdt_resource *r, mon_info.evtid = evtid; mondata_config_read(d, &mon_info); if (mon_info.mon_config == val) - goto out; + return; mon_info.mon_config = val; @@ -1650,9 +1692,6 @@ static int mbm_config_write_domain(struct rdt_resource *r, * mbm_local and mbm_total counts for all the RMIDs. */ resctrl_arch_reset_rmid_all(r, d); - -out: - return ret; } static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) @@ -1661,7 +1700,9 @@ static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid) char *dom_str = NULL, *id_str; unsigned long dom_id, val; struct rdt_domain *d; - int ret = 0; + + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); next: if (!tok || tok[0] == '\0') @@ -1690,9 +1731,7 @@ next: list_for_each_entry(d, &r->domains, list) { if (d->id == dom_id) { - ret = mbm_config_write_domain(r, d, evtid, val); - if (ret) - return -EINVAL; + mbm_config_write_domain(r, d, evtid, val); goto next; } } @@ -1711,6 +1750,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of, if (nbytes == 0 || buf[nbytes - 1] != '\n') return -EINVAL; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); rdt_last_cmd_clear(); @@ -1720,6 +1760,7 @@ static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of, ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return ret ?: nbytes; } @@ -1735,6 +1776,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of, if (nbytes == 0 || buf[nbytes - 1] != '\n') return -EINVAL; + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); rdt_last_cmd_clear(); @@ -1744,6 +1786,7 @@ static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of, ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID); mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); return ret ?: nbytes; } @@ -2220,6 +2263,9 @@ static int set_cache_qos_cfg(int level, bool enable) struct rdt_domain *d; int cpu; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (level == RDT_RESOURCE_L3) update = l3_qos_cfg_update; else if (level == RDT_RESOURCE_L2) @@ -2419,6 +2465,7 @@ struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn) rdtgroup_kn_get(rdtgrp, kn); + cpus_read_lock(); mutex_lock(&rdtgroup_mutex); /* Was this group deleted while we waited? */ @@ -2436,6 +2483,8 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn) return; mutex_unlock(&rdtgroup_mutex); + cpus_read_unlock(); + rdtgroup_kn_put(rdtgrp, kn); } @@ -2586,7 +2635,7 @@ static int rdt_get_tree(struct fs_context *fc) /* * resctrl file system can only be mounted once. */ - if (static_branch_unlikely(&rdt_enable_key)) { + if (resctrl_mounted) { ret = -EBUSY; goto out; } @@ -2607,7 +2656,7 @@ static int rdt_get_tree(struct fs_context *fc) closid_init(); - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) flags |= RFTYPE_MON; ret = rdtgroup_add_files(rdtgroup_default.kn, flags); @@ -2620,7 +2669,7 @@ static int rdt_get_tree(struct fs_context *fc) if (ret < 0) goto out_schemata_free; - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { ret = mongroup_create_dir(rdtgroup_default.kn, &rdtgroup_default, "mon_groups", &kn_mongrp); @@ -2642,18 +2691,19 @@ static int rdt_get_tree(struct fs_context *fc) if (ret < 0) goto out_psl; - if (rdt_alloc_capable) - static_branch_enable_cpuslocked(&rdt_alloc_enable_key); - if (rdt_mon_capable) - static_branch_enable_cpuslocked(&rdt_mon_enable_key); + if (resctrl_arch_alloc_capable()) + resctrl_arch_enable_alloc(); + if (resctrl_arch_mon_capable()) + resctrl_arch_enable_mon(); - if (rdt_alloc_capable || rdt_mon_capable) - static_branch_enable_cpuslocked(&rdt_enable_key); + if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable()) + resctrl_mounted = true; if (is_mbm_enabled()) { r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; list_for_each_entry(dom, &r->domains, list) - mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL); + mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL, + RESCTRL_PICK_ANY_CPU); } goto out; @@ -2661,10 +2711,10 @@ static int rdt_get_tree(struct fs_context *fc) out_psl: rdt_pseudo_lock_release(); out_mondata: - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) kernfs_remove(kn_mondata); out_mongrp: - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) kernfs_remove(kn_mongrp); out_info: kernfs_remove(kn_info); @@ -2767,6 +2817,9 @@ static int reset_all_ctrls(struct rdt_resource *r) struct rdt_domain *d; int i; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + if (!zalloc_cpumask_var(&cpu_mask, GFP_KERNEL)) return -ENOMEM; @@ -2812,8 +2865,8 @@ static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to, for_each_process_thread(p, t) { if (!from || is_closid_match(t, from) || is_rmid_match(t, from)) { - WRITE_ONCE(t->closid, to->closid); - WRITE_ONCE(t->rmid, to->mon.rmid); + resctrl_arch_set_closid_rmid(t, to->closid, + to->mon.rmid); /* * Order the closid/rmid stores above before the loads @@ -2844,7 +2897,7 @@ static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp) head = &rdtgrp->mon.crdtgrp_list; list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) { - free_rmid(sentry->mon.rmid); + free_rmid(sentry->closid, sentry->mon.rmid); list_del(&sentry->mon.crdtgrp_list); if (atomic_read(&sentry->waitcount) != 0) @@ -2884,7 +2937,7 @@ static void rmdir_all_sub(void) cpumask_or(&rdtgroup_default.cpu_mask, &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask); - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); kernfs_remove(rdtgrp->kn); list_del(&rdtgrp->rdtgroup_list); @@ -2919,9 +2972,11 @@ static void rdt_kill_sb(struct super_block *sb) rdtgroup_default.mode = RDT_MODE_SHAREABLE; schemata_list_destroy(); rdtgroup_destroy_root(); - static_branch_disable_cpuslocked(&rdt_alloc_enable_key); - static_branch_disable_cpuslocked(&rdt_mon_enable_key); - static_branch_disable_cpuslocked(&rdt_enable_key); + if (resctrl_arch_alloc_capable()) + resctrl_arch_disable_alloc(); + if (resctrl_arch_mon_capable()) + resctrl_arch_disable_mon(); + resctrl_mounted = false; kernfs_kill_sb(sb); mutex_unlock(&rdtgroup_mutex); cpus_read_unlock(); @@ -3049,6 +3104,9 @@ static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn, struct rdt_domain *dom; int ret; + /* Walking r->domains, ensure it can't race with cpuhp */ + lockdep_assert_cpus_held(); + list_for_each_entry(dom, &r->domains, list) { ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp); if (ret) @@ -3295,6 +3353,36 @@ out: return ret; } +static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp) +{ + int ret; + + if (!resctrl_arch_mon_capable()) + return 0; + + ret = alloc_rmid(rdtgrp->closid); + if (ret < 0) { + rdt_last_cmd_puts("Out of RMIDs\n"); + return ret; + } + rdtgrp->mon.rmid = ret; + + ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn); + if (ret) { + rdt_last_cmd_puts("kernfs subdir error\n"); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); + return ret; + } + + return 0; +} + +static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp) +{ + if (resctrl_arch_mon_capable()) + free_rmid(rgrp->closid, rgrp->mon.rmid); +} + static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, const char *name, umode_t mode, enum rdt_group_type rtype, struct rdtgroup **r) @@ -3355,7 +3443,7 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, if (rtype == RDTCTRL_GROUP) { files = RFTYPE_BASE | RFTYPE_CTRL; - if (rdt_mon_capable) + if (resctrl_arch_mon_capable()) files |= RFTYPE_MON; } else { files = RFTYPE_BASE | RFTYPE_MON; @@ -3367,29 +3455,11 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, goto out_destroy; } - if (rdt_mon_capable) { - ret = alloc_rmid(); - if (ret < 0) { - rdt_last_cmd_puts("Out of RMIDs\n"); - goto out_destroy; - } - rdtgrp->mon.rmid = ret; - - ret = mkdir_mondata_all(kn, rdtgrp, &rdtgrp->mon.mon_data_kn); - if (ret) { - rdt_last_cmd_puts("kernfs subdir error\n"); - goto out_idfree; - } - } - kernfs_activate(kn); - /* * The caller unlocks the parent_kn upon success. */ return 0; -out_idfree: - free_rmid(rdtgrp->mon.rmid); out_destroy: kernfs_put(rdtgrp->kn); kernfs_remove(rdtgrp->kn); @@ -3403,7 +3473,6 @@ out_unlock: static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp) { kernfs_remove(rgrp->kn); - free_rmid(rgrp->mon.rmid); rdtgroup_remove(rgrp); } @@ -3425,12 +3494,21 @@ static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn, prgrp = rdtgrp->mon.parent; rdtgrp->closid = prgrp->closid; + ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp); + if (ret) { + mkdir_rdt_prepare_clean(rdtgrp); + goto out_unlock; + } + + kernfs_activate(rdtgrp->kn); + /* * Add the rdtgrp to the list of rdtgrps the parent * ctrl_mon group has to track. */ list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list); +out_unlock: rdtgroup_kn_unlock(parent_kn); return ret; } @@ -3461,13 +3539,20 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, ret = 0; rdtgrp->closid = closid; + + ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp); + if (ret) + goto out_closid_free; + + kernfs_activate(rdtgrp->kn); + ret = rdtgroup_init_alloc(rdtgrp); if (ret < 0) - goto out_id_free; + goto out_rmid_free; list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups); - if (rdt_mon_capable) { + if (resctrl_arch_mon_capable()) { /* * Create an empty mon_groups directory to hold the subset * of tasks and cpus to monitor. @@ -3483,7 +3568,9 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn, out_del_list: list_del(&rdtgrp->rdtgroup_list); -out_id_free: +out_rmid_free: + mkdir_rdt_prepare_rmid_free(rdtgrp); +out_closid_free: closid_free(closid); out_common_fail: mkdir_rdt_prepare_clean(rdtgrp); @@ -3520,14 +3607,14 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name, * allocation is supported, add a control and monitoring * subdirectory */ - if (rdt_alloc_capable && parent_kn == rdtgroup_default.kn) + if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn) return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode); /* * If RDT monitoring is supported and the parent directory is a valid * "mon_groups" directory, add a monitoring subdirectory. */ - if (rdt_mon_capable && is_mon_groups(parent_kn, name)) + if (resctrl_arch_mon_capable() && is_mon_groups(parent_kn, name)) return rdtgroup_mkdir_mon(parent_kn, name, mode); return -EPERM; @@ -3552,7 +3639,7 @@ static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) update_closid_rmid(tmpmask, NULL); rdtgrp->flags = RDT_DELETED; - free_rmid(rdtgrp->mon.rmid); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); /* * Remove the rdtgrp from the parent ctrl_mon group's list @@ -3598,8 +3685,8 @@ static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask) cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask); update_closid_rmid(tmpmask, NULL); + free_rmid(rdtgrp->closid, rdtgrp->mon.rmid); closid_free(rdtgrp->closid); - free_rmid(rdtgrp->mon.rmid); rdtgroup_ctrl_remove(rdtgrp); @@ -3831,8 +3918,8 @@ static void __init rdtgroup_setup_default(void) { mutex_lock(&rdtgroup_mutex); - rdtgroup_default.closid = 0; - rdtgroup_default.mon.rmid = 0; + rdtgroup_default.closid = RESCTRL_RESERVED_CLOSID; + rdtgroup_default.mon.rmid = RESCTRL_RESERVED_RMID; rdtgroup_default.type = RDTCTRL_GROUP; INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list); @@ -3850,24 +3937,24 @@ static void domain_destroy_mon_state(struct rdt_domain *d) void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) { - lockdep_assert_held(&rdtgroup_mutex); + mutex_lock(&rdtgroup_mutex); if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) mba_sc_domain_destroy(r, d); if (!r->mon_capable) - return; + goto out_unlock; /* * If resctrl is mounted, remove all the * per domain monitor data directories. */ - if (static_branch_unlikely(&rdt_mon_enable_key)) + if (resctrl_mounted && resctrl_arch_mon_capable()) rmdir_mondata_subdir_allrdtgrp(r, d->id); if (is_mbm_enabled()) cancel_delayed_work(&d->mbm_over); - if (is_llc_occupancy_enabled() && has_busy_rmid(r, d)) { + if (is_llc_occupancy_enabled() && has_busy_rmid(d)) { /* * When a package is going down, forcefully * decrement rmid->ebusy. There is no way to know @@ -3881,20 +3968,24 @@ void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d) } domain_destroy_mon_state(d); + +out_unlock: + mutex_unlock(&rdtgroup_mutex); } static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) { + u32 idx_limit = resctrl_arch_system_num_rmid_idx(); size_t tsize; if (is_llc_occupancy_enabled()) { - d->rmid_busy_llc = bitmap_zalloc(r->num_rmid, GFP_KERNEL); + d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL); if (!d->rmid_busy_llc) return -ENOMEM; } if (is_mbm_total_enabled()) { tsize = sizeof(*d->mbm_total); - d->mbm_total = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL); if (!d->mbm_total) { bitmap_free(d->rmid_busy_llc); return -ENOMEM; @@ -3902,7 +3993,7 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) } if (is_mbm_local_enabled()) { tsize = sizeof(*d->mbm_local); - d->mbm_local = kcalloc(r->num_rmid, tsize, GFP_KERNEL); + d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL); if (!d->mbm_local) { bitmap_free(d->rmid_busy_llc); kfree(d->mbm_total); @@ -3915,34 +4006,97 @@ static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_domain *d) int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d) { - int err; + int err = 0; - lockdep_assert_held(&rdtgroup_mutex); + mutex_lock(&rdtgroup_mutex); - if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) + if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) { /* RDT_RESOURCE_MBA is never mon_capable */ - return mba_sc_domain_allocate(r, d); + err = mba_sc_domain_allocate(r, d); + goto out_unlock; + } if (!r->mon_capable) - return 0; + goto out_unlock; err = domain_setup_mon_state(r, d); if (err) - return err; + goto out_unlock; if (is_mbm_enabled()) { INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow); - mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL); + mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL, + RESCTRL_PICK_ANY_CPU); } if (is_llc_occupancy_enabled()) INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo); - /* If resctrl is mounted, add per domain monitor data directories. */ - if (static_branch_unlikely(&rdt_mon_enable_key)) + /* + * If the filesystem is not mounted then only the default resource group + * exists. Creation of its directories is deferred until mount time + * by rdt_get_tree() calling mkdir_mondata_all(). + * If resctrl is mounted, add per domain monitor data directories. + */ + if (resctrl_mounted && resctrl_arch_mon_capable()) mkdir_mondata_subdir_allrdtgrp(r, d); - return 0; +out_unlock: + mutex_unlock(&rdtgroup_mutex); + + return err; +} + +void resctrl_online_cpu(unsigned int cpu) +{ + mutex_lock(&rdtgroup_mutex); + /* The CPU is set in default rdtgroup after online. */ + cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask); + mutex_unlock(&rdtgroup_mutex); +} + +static void clear_childcpus(struct rdtgroup *r, unsigned int cpu) +{ + struct rdtgroup *cr; + + list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) { + if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) + break; + } +} + +void resctrl_offline_cpu(unsigned int cpu) +{ + struct rdt_resource *l3 = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl; + struct rdtgroup *rdtgrp; + struct rdt_domain *d; + + mutex_lock(&rdtgroup_mutex); + list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) { + if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) { + clear_childcpus(rdtgrp, cpu); + break; + } + } + + if (!l3->mon_capable) + goto out_unlock; + + d = get_domain_from_cpu(cpu, l3); + if (d) { + if (is_mbm_enabled() && cpu == d->mbm_work_cpu) { + cancel_delayed_work(&d->mbm_over); + mbm_setup_overflow_handler(d, 0, cpu); + } + if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu && + has_busy_rmid(d)) { + cancel_delayed_work(&d->cqm_limbo); + cqm_setup_limbo_handler(d, 0, cpu); + } + } + +out_unlock: + mutex_unlock(&rdtgroup_mutex); } /* diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index 0ebca40dfd..af5aa2c754 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -50,6 +50,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 }, { X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 }, { X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 }, + { X86_FEATURE_AMD_LBR_PMC_FREEZE, CPUID_EAX, 2, 0x80000022, 0 }, { 0, 0, 0, 0, 0 } }; diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index dc13670356..621a151ccf 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -1,167 +1,571 @@ -// SPDX-License-Identifier: GPL-2.0 +// SPDX-License-Identifier: GPL-2.0-only /* - * Check for extended topology enumeration cpuid leaf 0xb and if it - * exists, use it for populating initial_apicid and cpu topology - * detection. + * CPU/APIC topology + * + * The APIC IDs describe the system topology in multiple domain levels. + * The CPUID topology parser provides the information which part of the + * APIC ID is associated to the individual levels: + * + * [PACKAGE][DIEGRP][DIE][TILE][MODULE][CORE][THREAD] + * + * The root space contains the package (socket) IDs. + * + * Not enumerated levels consume 0 bits space, but conceptually they are + * always represented. If e.g. only CORE and THREAD levels are enumerated + * then the DIE, MODULE and TILE have the same physical ID as the PACKAGE. + * + * If SMT is not supported, then the THREAD domain is still used. It then + * has the same physical ID as the CORE domain and is the only child of + * the core domain. + * + * This allows a unified view on the system independent of the enumerated + * domain levels without requiring any conditionals in the code. */ - +#define pr_fmt(fmt) "CPU topo: " fmt #include <linux/cpu.h> + +#include <xen/xen.h> + #include <asm/apic.h> -#include <asm/memtype.h> -#include <asm/processor.h> +#include <asm/hypervisor.h> +#include <asm/io_apic.h> +#include <asm/mpspec.h> +#include <asm/smp.h> #include "cpu.h" -/* leaf 0xb SMT level */ -#define SMT_LEVEL 0 +/* + * Map cpu index to physical APIC ID + */ +DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid, BAD_APICID); +DEFINE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid, CPU_ACPIID_INVALID); +EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid); +EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_acpiid); -/* extended topology sub-leaf types */ -#define INVALID_TYPE 0 -#define SMT_TYPE 1 -#define CORE_TYPE 2 -#define DIE_TYPE 5 +/* Bitmap of physically present CPUs. */ +DECLARE_BITMAP(phys_cpu_present_map, MAX_LOCAL_APIC) __read_mostly; -#define LEAFB_SUBTYPE(ecx) (((ecx) >> 8) & 0xff) -#define BITS_SHIFT_NEXT_LEVEL(eax) ((eax) & 0x1f) -#define LEVEL_MAX_SIBLINGS(ebx) ((ebx) & 0xffff) +/* Used for CPU number allocation and parallel CPU bringup */ +u32 cpuid_to_apicid[] __ro_after_init = { [0 ... NR_CPUS - 1] = BAD_APICID, }; -unsigned int __max_die_per_package __read_mostly = 1; -EXPORT_SYMBOL(__max_die_per_package); +/* Bitmaps to mark registered APICs at each topology domain */ +static struct { DECLARE_BITMAP(map, MAX_LOCAL_APIC); } apic_maps[TOPO_MAX_DOMAIN] __ro_after_init; -#ifdef CONFIG_SMP /* - * Check if given CPUID extended topology "leaf" is implemented + * Keep track of assigned, disabled and rejected CPUs. Present assigned + * with 1 as CPU #0 is reserved for the boot CPU. */ -static int check_extended_topology_leaf(int leaf) -{ - unsigned int eax, ebx, ecx, edx; +static struct { + unsigned int nr_assigned_cpus; + unsigned int nr_disabled_cpus; + unsigned int nr_rejected_cpus; + u32 boot_cpu_apic_id; + u32 real_bsp_apic_id; +} topo_info __ro_after_init = { + .nr_assigned_cpus = 1, + .boot_cpu_apic_id = BAD_APICID, + .real_bsp_apic_id = BAD_APICID, +}; - cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); +#define domain_weight(_dom) bitmap_weight(apic_maps[_dom].map, MAX_LOCAL_APIC) - if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE)) - return -1; +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == (u64)cpuid_to_apicid[cpu]; +} - return 0; +#ifdef CONFIG_SMP +static void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) +{ + if (!(apicid & (__max_threads_per_core - 1))) + cpumask_set_cpu(cpu, &__cpu_primary_thread_mask); } +#else +static inline void cpu_mark_primary_thread(unsigned int cpu, unsigned int apicid) { } +#endif + /* - * Return best CPUID Extended Topology Leaf supported + * Convert the APIC ID to a domain level ID by masking out the low bits + * below the domain level @dom. */ -static int detect_extended_topology_leaf(struct cpuinfo_x86 *c) +static inline u32 topo_apicid(u32 apicid, enum x86_topology_domains dom) { - if (c->cpuid_level >= 0x1f) { - if (check_extended_topology_leaf(0x1f) == 0) - return 0x1f; - } + if (dom == TOPO_SMT_DOMAIN) + return apicid; + return apicid & (UINT_MAX << x86_topo_system.dom_shifts[dom - 1]); +} - if (c->cpuid_level >= 0xb) { - if (check_extended_topology_leaf(0xb) == 0) - return 0xb; - } +static int topo_lookup_cpuid(u32 apic_id) +{ + int i; - return -1; + /* CPU# to APICID mapping is persistent once it is established */ + for (i = 0; i < topo_info.nr_assigned_cpus; i++) { + if (cpuid_to_apicid[i] == apic_id) + return i; + } + return -ENODEV; } -#endif -int detect_extended_topology_early(struct cpuinfo_x86 *c) +static __init int topo_get_cpunr(u32 apic_id) { -#ifdef CONFIG_SMP - unsigned int eax, ebx, ecx, edx; - int leaf; + int cpu = topo_lookup_cpuid(apic_id); - leaf = detect_extended_topology_leaf(c); - if (leaf < 0) - return -1; + if (cpu >= 0) + return cpu; - set_cpu_cap(c, X86_FEATURE_XTOPOLOGY); + return topo_info.nr_assigned_cpus++; +} - cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); - /* - * initial apic id, which also represents 32-bit extended x2apic id. - */ - c->topo.initial_apicid = edx; - smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); +static void topo_set_cpuids(unsigned int cpu, u32 apic_id, u32 acpi_id) +{ +#if defined(CONFIG_SMP) || defined(CONFIG_X86_64) + early_per_cpu(x86_cpu_to_apicid, cpu) = apic_id; + early_per_cpu(x86_cpu_to_acpiid, cpu) = acpi_id; #endif - return 0; + set_cpu_present(cpu, true); } -/* - * Check for extended topology enumeration cpuid leaf, and if it - * exists, use it for populating initial_apicid and cpu topology - * detection. - */ -int detect_extended_topology(struct cpuinfo_x86 *c) +static __init bool check_for_real_bsp(u32 apic_id) { -#ifdef CONFIG_SMP - unsigned int eax, ebx, ecx, edx, sub_index; - unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width; - unsigned int core_select_mask, core_level_siblings; - unsigned int die_select_mask, die_level_siblings; - unsigned int pkg_mask_width; - bool die_level_present = false; - int leaf; - - leaf = detect_extended_topology_leaf(c); - if (leaf < 0) - return -1; + bool is_bsp = false, has_apic_base = boot_cpu_data.x86 >= 6; + u64 msr; /* - * Populate HT related information from sub-leaf level 0. + * There is no real good way to detect whether this a kdump() + * kernel, but except on the Voyager SMP monstrosity which is not + * longer supported, the real BSP APIC ID is the first one which is + * enumerated by firmware. That allows to detect whether the boot + * CPU is the real BSP. If it is not, then do not register the APIC + * because sending INIT to the real BSP would reset the whole + * system. + * + * The first APIC ID which is enumerated by firmware is detectable + * because the boot CPU APIC ID is registered before that without + * invoking this code. */ - cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); - c->topo.initial_apicid = edx; - core_level_siblings = LEVEL_MAX_SIBLINGS(ebx); - smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); - core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); - die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); - pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); - - sub_index = 1; - while (true) { - cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx); + if (topo_info.real_bsp_apic_id != BAD_APICID) + return false; + /* + * Check whether the enumeration order is broken by evaluating the + * BSP bit in the APICBASE MSR. If the CPU does not have the + * APICBASE MSR then the BSP detection is not possible and the + * kernel must rely on the firmware enumeration order. + */ + if (has_apic_base) { + rdmsrl(MSR_IA32_APICBASE, msr); + is_bsp = !!(msr & MSR_IA32_APICBASE_BSP); + } + + if (apic_id == topo_info.boot_cpu_apic_id) { /* - * Check for the Core type in the implemented sub leaves. + * If the boot CPU has the APIC BSP bit set then the + * firmware enumeration is agreeing. If the CPU does not + * have the APICBASE MSR then the only choice is to trust + * the enumeration order. */ - if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) { - core_level_siblings = LEVEL_MAX_SIBLINGS(ebx); - core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); - die_level_siblings = core_level_siblings; - die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); - } - if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) { - die_level_present = true; - die_level_siblings = LEVEL_MAX_SIBLINGS(ebx); - die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); + if (is_bsp || !has_apic_base) { + topo_info.real_bsp_apic_id = apic_id; + return false; } + /* + * If the boot APIC is enumerated first, but the APICBASE + * MSR does not have the BSP bit set, then there is no way + * to discover the real BSP here. Assume a crash kernel and + * limit the number of CPUs to 1 as an INIT to the real BSP + * would reset the machine. + */ + pr_warn("Enumerated BSP APIC %x is not marked in APICBASE MSR\n", apic_id); + pr_warn("Assuming crash kernel. Limiting to one CPU to prevent machine INIT\n"); + set_nr_cpu_ids(1); + goto fwbug; + } - if (LEAFB_SUBTYPE(ecx) != INVALID_TYPE) - pkg_mask_width = BITS_SHIFT_NEXT_LEVEL(eax); - else - break; + pr_warn("Boot CPU APIC ID not the first enumerated APIC ID: %x != %x\n", + topo_info.boot_cpu_apic_id, apic_id); - sub_index++; + if (is_bsp) { + /* + * The boot CPU has the APIC BSP bit set. Use it and complain + * about the broken firmware enumeration. + */ + topo_info.real_bsp_apic_id = topo_info.boot_cpu_apic_id; + goto fwbug; } - core_select_mask = (~(-1 << pkg_mask_width)) >> ht_mask_width; - die_select_mask = (~(-1 << die_plus_mask_width)) >> - core_plus_mask_width; + pr_warn("Crash kernel detected. Disabling real BSP to prevent machine INIT\n"); + + topo_info.real_bsp_apic_id = apic_id; + return true; + +fwbug: + pr_warn(FW_BUG "APIC enumeration order not specification compliant\n"); + return false; +} + +static unsigned int topo_unit_count(u32 lvlid, enum x86_topology_domains at_level, + unsigned long *map) +{ + unsigned int id, end, cnt = 0; + + /* Calculate the exclusive end */ + end = lvlid + (1U << x86_topo_system.dom_shifts[at_level]); + + /* Unfortunately there is no bitmap_weight_range() */ + for (id = find_next_bit(map, end, lvlid); id < end; id = find_next_bit(map, end, ++id)) + cnt++; + return cnt; +} + +static __init void topo_register_apic(u32 apic_id, u32 acpi_id, bool present) +{ + int cpu, dom; + + if (present) { + set_bit(apic_id, phys_cpu_present_map); + + /* + * Double registration is valid in case of the boot CPU + * APIC because that is registered before the enumeration + * of the APICs via firmware parsers or VM guest + * mechanisms. + */ + if (apic_id == topo_info.boot_cpu_apic_id) + cpu = 0; + else + cpu = topo_get_cpunr(apic_id); + + cpuid_to_apicid[cpu] = apic_id; + topo_set_cpuids(cpu, apic_id, acpi_id); + } else { + u32 pkgid = topo_apicid(apic_id, TOPO_PKG_DOMAIN); - c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid, - ht_mask_width) & core_select_mask; + /* + * Check for present APICs in the same package when running + * on bare metal. Allow the bogosity in a guest. + */ + if (hypervisor_is_type(X86_HYPER_NATIVE) && + topo_unit_count(pkgid, TOPO_PKG_DOMAIN, phys_cpu_present_map)) { + pr_info_once("Ignoring hot-pluggable APIC ID %x in present package.\n", + apic_id); + topo_info.nr_rejected_cpus++; + return; + } - if (die_level_present) { - c->topo.die_id = apic->phys_pkg_id(c->topo.initial_apicid, - core_plus_mask_width) & die_select_mask; + topo_info.nr_disabled_cpus++; } - c->topo.pkg_id = apic->phys_pkg_id(c->topo.initial_apicid, pkg_mask_width); /* - * Reinit the apicid, now that we have extended initial_apicid. + * Register present and possible CPUs in the domain + * maps. cpu_possible_map will be updated in + * topology_init_possible_cpus() after enumeration is done. */ - c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0); + for (dom = TOPO_SMT_DOMAIN; dom < TOPO_MAX_DOMAIN; dom++) + set_bit(topo_apicid(apic_id, dom), apic_maps[dom].map); +} + +/** + * topology_register_apic - Register an APIC in early topology maps + * @apic_id: The APIC ID to set up + * @acpi_id: The ACPI ID associated to the APIC + * @present: True if the corresponding CPU is present + */ +void __init topology_register_apic(u32 apic_id, u32 acpi_id, bool present) +{ + if (apic_id >= MAX_LOCAL_APIC) { + pr_err_once("APIC ID %x exceeds kernel limit of: %x\n", apic_id, MAX_LOCAL_APIC - 1); + topo_info.nr_rejected_cpus++; + return; + } + + if (check_for_real_bsp(apic_id)) { + topo_info.nr_rejected_cpus++; + return; + } + + /* CPU numbers exhausted? */ + if (apic_id != topo_info.boot_cpu_apic_id && topo_info.nr_assigned_cpus >= nr_cpu_ids) { + pr_warn_once("CPU limit of %d reached. Ignoring further CPUs\n", nr_cpu_ids); + topo_info.nr_rejected_cpus++; + return; + } + + topo_register_apic(apic_id, acpi_id, present); +} + +/** + * topology_register_boot_apic - Register the boot CPU APIC + * @apic_id: The APIC ID to set up + * + * Separate so CPU #0 can be assigned + */ +void __init topology_register_boot_apic(u32 apic_id) +{ + WARN_ON_ONCE(topo_info.boot_cpu_apic_id != BAD_APICID); + + topo_info.boot_cpu_apic_id = apic_id; + topo_register_apic(apic_id, CPU_ACPIID_INVALID, true); +} - c->x86_max_cores = (core_level_siblings / smp_num_siblings); - __max_die_per_package = (die_level_siblings / core_level_siblings); +/** + * topology_get_logical_id - Retrieve the logical ID at a given topology domain level + * @apicid: The APIC ID for which to lookup the logical ID + * @at_level: The topology domain level to use + * + * @apicid must be a full APIC ID, not the normalized variant. It's valid to have + * all bits below the domain level specified by @at_level to be clear. So both + * real APIC IDs and backshifted normalized APIC IDs work correctly. + * + * Returns: + * - >= 0: The requested logical ID + * - -ERANGE: @apicid is out of range + * - -ENODEV: @apicid is not registered + */ +int topology_get_logical_id(u32 apicid, enum x86_topology_domains at_level) +{ + /* Remove the bits below @at_level to get the proper level ID of @apicid */ + unsigned int lvlid = topo_apicid(apicid, at_level); + + if (lvlid >= MAX_LOCAL_APIC) + return -ERANGE; + if (!test_bit(lvlid, apic_maps[at_level].map)) + return -ENODEV; + /* Get the number of set bits before @lvlid. */ + return bitmap_weight(apic_maps[at_level].map, lvlid); +} +EXPORT_SYMBOL_GPL(topology_get_logical_id); + +/** + * topology_unit_count - Retrieve the count of specified units at a given topology domain level + * @apicid: The APIC ID which specifies the search range + * @which_units: The domain level specifying the units to count + * @at_level: The domain level at which @which_units have to be counted + * + * This returns the number of possible units according to the enumerated + * information. + * + * E.g. topology_count_units(apicid, TOPO_CORE_DOMAIN, TOPO_PKG_DOMAIN) + * counts the number of possible cores in the package to which @apicid + * belongs. + * + * @at_level must obviously be greater than @which_level to produce useful + * results. If @at_level is equal to @which_units the result is + * unsurprisingly 1. If @at_level is less than @which_units the results + * is by definition undefined and the function returns 0. + */ +unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units, + enum x86_topology_domains at_level) +{ + /* Remove the bits below @at_level to get the proper level ID of @apicid */ + unsigned int lvlid = topo_apicid(apicid, at_level); + + if (lvlid >= MAX_LOCAL_APIC) + return 0; + if (!test_bit(lvlid, apic_maps[at_level].map)) + return 0; + if (which_units > at_level) + return 0; + if (which_units == at_level) + return 1; + return topo_unit_count(lvlid, at_level, apic_maps[which_units].map); +} + +#ifdef CONFIG_ACPI_HOTPLUG_CPU +/** + * topology_hotplug_apic - Handle a physical hotplugged APIC after boot + * @apic_id: The APIC ID to set up + * @acpi_id: The ACPI ID associated to the APIC + */ +int topology_hotplug_apic(u32 apic_id, u32 acpi_id) +{ + int cpu; + + if (apic_id >= MAX_LOCAL_APIC) + return -EINVAL; + + /* Reject if the APIC ID was not registered during enumeration. */ + if (!test_bit(apic_id, apic_maps[TOPO_SMT_DOMAIN].map)) + return -ENODEV; + + cpu = topo_lookup_cpuid(apic_id); + if (cpu < 0) + return -ENOSPC; + + set_bit(apic_id, phys_cpu_present_map); + topo_set_cpuids(cpu, apic_id, acpi_id); + cpu_mark_primary_thread(cpu, apic_id); + return cpu; +} + +/** + * topology_hotunplug_apic - Remove a physical hotplugged APIC after boot + * @cpu: The CPU number for which the APIC ID is removed + */ +void topology_hotunplug_apic(unsigned int cpu) +{ + u32 apic_id = cpuid_to_apicid[cpu]; + + if (apic_id == BAD_APICID) + return; + + per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; + clear_bit(apic_id, phys_cpu_present_map); + set_cpu_present(cpu, false); +} #endif + +#ifdef CONFIG_X86_LOCAL_APIC +static unsigned int max_possible_cpus __initdata = NR_CPUS; + +/** + * topology_apply_cmdline_limits_early - Apply topology command line limits early + * + * Ensure that command line limits are in effect before firmware parsing + * takes place. + */ +void __init topology_apply_cmdline_limits_early(void) +{ + unsigned int possible = nr_cpu_ids; + + /* 'maxcpus=0' 'nosmp' 'nolapic' 'disableapic' 'noapic' */ + if (!setup_max_cpus || ioapic_is_disabled || apic_is_disabled) + possible = 1; + + /* 'possible_cpus=N' */ + possible = min_t(unsigned int, max_possible_cpus, possible); + + if (possible < nr_cpu_ids) { + pr_info("Limiting to %u possible CPUs\n", possible); + set_nr_cpu_ids(possible); + } +} + +static __init bool restrict_to_up(void) +{ + if (!smp_found_config || ioapic_is_disabled) + return true; + /* + * XEN PV is special as it does not advertise the local APIC + * properly, but provides a fake topology for it so that the + * infrastructure works. So don't apply the restrictions vs. APIC + * here. + */ + if (xen_pv_domain()) + return false; + + return apic_is_disabled; +} + +void __init topology_init_possible_cpus(void) +{ + unsigned int assigned = topo_info.nr_assigned_cpus; + unsigned int disabled = topo_info.nr_disabled_cpus; + unsigned int cnta, cntb, cpu, allowed = 1; + unsigned int total = assigned + disabled; + u32 apicid, firstid; + + /* + * If there was no APIC registered, then fake one so that the + * topology bitmap is populated. That ensures that the code below + * is valid and the various query interfaces can be used + * unconditionally. This does not affect the actual APIC code in + * any way because either the local APIC address has not been + * registered or the local APIC was disabled on the command line. + */ + if (topo_info.boot_cpu_apic_id == BAD_APICID) + topology_register_boot_apic(0); + + if (!restrict_to_up()) { + if (WARN_ON_ONCE(assigned > nr_cpu_ids)) { + disabled += assigned - nr_cpu_ids; + assigned = nr_cpu_ids; + } + allowed = min_t(unsigned int, total, nr_cpu_ids); + } + + if (total > allowed) + pr_warn("%u possible CPUs exceed the limit of %u\n", total, allowed); + + assigned = min_t(unsigned int, allowed, assigned); + disabled = allowed - assigned; + + topo_info.nr_assigned_cpus = assigned; + topo_info.nr_disabled_cpus = disabled; + + total_cpus = allowed; + set_nr_cpu_ids(allowed); + + cnta = domain_weight(TOPO_PKG_DOMAIN); + cntb = domain_weight(TOPO_DIE_DOMAIN); + __max_logical_packages = cnta; + __max_dies_per_package = 1U << (get_count_order(cntb) - get_count_order(cnta)); + + pr_info("Max. logical packages: %3u\n", cnta); + pr_info("Max. logical dies: %3u\n", cntb); + pr_info("Max. dies per package: %3u\n", __max_dies_per_package); + + cnta = domain_weight(TOPO_CORE_DOMAIN); + cntb = domain_weight(TOPO_SMT_DOMAIN); + /* + * Can't use order delta here as order(cnta) can be equal + * order(cntb) even if cnta != cntb. + */ + __max_threads_per_core = DIV_ROUND_UP(cntb, cnta); + pr_info("Max. threads per core: %3u\n", __max_threads_per_core); + + firstid = find_first_bit(apic_maps[TOPO_SMT_DOMAIN].map, MAX_LOCAL_APIC); + __num_cores_per_package = topology_unit_count(firstid, TOPO_CORE_DOMAIN, TOPO_PKG_DOMAIN); + pr_info("Num. cores per package: %3u\n", __num_cores_per_package); + __num_threads_per_package = topology_unit_count(firstid, TOPO_SMT_DOMAIN, TOPO_PKG_DOMAIN); + pr_info("Num. threads per package: %3u\n", __num_threads_per_package); + + pr_info("Allowing %u present CPUs plus %u hotplug CPUs\n", assigned, disabled); + if (topo_info.nr_rejected_cpus) + pr_info("Rejected CPUs %u\n", topo_info.nr_rejected_cpus); + + init_cpu_present(cpumask_of(0)); + init_cpu_possible(cpumask_of(0)); + + /* Assign CPU numbers to non-present CPUs */ + for (apicid = 0; disabled; disabled--, apicid++) { + apicid = find_next_andnot_bit(apic_maps[TOPO_SMT_DOMAIN].map, phys_cpu_present_map, + MAX_LOCAL_APIC, apicid); + if (apicid >= MAX_LOCAL_APIC) + break; + cpuid_to_apicid[topo_info.nr_assigned_cpus++] = apicid; + } + + for (cpu = 0; cpu < allowed; cpu++) { + apicid = cpuid_to_apicid[cpu]; + + set_cpu_possible(cpu, true); + + if (apicid == BAD_APICID) + continue; + + cpu_mark_primary_thread(cpu, apicid); + set_cpu_present(cpu, test_bit(apicid, phys_cpu_present_map)); + } +} + +/* + * Late SMP disable after sizing CPU masks when APIC/IOAPIC setup failed. + */ +void __init topology_reset_possible_cpus_up(void) +{ + init_cpu_present(cpumask_of(0)); + init_cpu_possible(cpumask_of(0)); + + bitmap_zero(phys_cpu_present_map, MAX_LOCAL_APIC); + if (topo_info.boot_cpu_apic_id != BAD_APICID) + set_bit(topo_info.boot_cpu_apic_id, phys_cpu_present_map); +} + +static int __init setup_possible_cpus(char *str) +{ + get_option(&str, &max_possible_cpus); return 0; } +early_param("possible_cpus", setup_possible_cpus); +#endif diff --git a/arch/x86/kernel/cpu/topology.h b/arch/x86/kernel/cpu/topology.h new file mode 100644 index 0000000000..37326297f8 --- /dev/null +++ b/arch/x86/kernel/cpu/topology.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef ARCH_X86_TOPOLOGY_H +#define ARCH_X86_TOPOLOGY_H + +struct topo_scan { + struct cpuinfo_x86 *c; + unsigned int dom_shifts[TOPO_MAX_DOMAIN]; + unsigned int dom_ncpus[TOPO_MAX_DOMAIN]; + + /* Legacy CPUID[1]:EBX[23:16] number of logical processors */ + unsigned int ebx1_nproc_shift; + + /* AMD specific node ID which cannot be mapped into APIC space. */ + u16 amd_nodes_per_pkg; + u16 amd_node_id; +}; + +void cpu_init_topology(struct cpuinfo_x86 *c); +void cpu_parse_topology(struct cpuinfo_x86 *c); +void topology_set_dom(struct topo_scan *tscan, enum x86_topology_domains dom, + unsigned int shift, unsigned int ncpus); +bool cpu_parse_topology_ext(struct topo_scan *tscan); +void cpu_parse_topology_amd(struct topo_scan *tscan); +void cpu_topology_fixup_amd(struct topo_scan *tscan); + +static inline u32 topo_shift_apicid(u32 apicid, enum x86_topology_domains dom) +{ + if (dom == TOPO_SMT_DOMAIN) + return apicid; + return apicid >> x86_topo_system.dom_shifts[dom - 1]; +} + +static inline u32 topo_relative_domain_id(u32 apicid, enum x86_topology_domains dom) +{ + if (dom != TOPO_SMT_DOMAIN) + apicid >>= x86_topo_system.dom_shifts[dom - 1]; + return apicid & (x86_topo_system.dom_size[dom] - 1); +} + +static inline u32 topo_domain_mask(enum x86_topology_domains dom) +{ + return (1U << x86_topo_system.dom_shifts[dom]) - 1; +} + +/* + * Update a domain level after the fact without propagating. Used to fixup + * broken CPUID enumerations. + */ +static inline void topology_update_dom(struct topo_scan *tscan, enum x86_topology_domains dom, + unsigned int shift, unsigned int ncpus) +{ + tscan->dom_shifts[dom] = shift; + tscan->dom_ncpus[dom] = ncpus; +} + +#ifdef CONFIG_X86_LOCAL_APIC +unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units, + enum x86_topology_domains at_level); +#else +static inline unsigned int topology_unit_count(u32 apicid, enum x86_topology_domains which_units, + enum x86_topology_domains at_level) +{ + return 1; +} +#endif + +#endif /* ARCH_X86_TOPOLOGY_H */ diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c new file mode 100644 index 0000000000..5ee6373d4d --- /dev/null +++ b/arch/x86/kernel/cpu/topology_amd.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/cpu.h> + +#include <asm/apic.h> +#include <asm/memtype.h> +#include <asm/processor.h> + +#include "cpu.h" + +static bool parse_8000_0008(struct topo_scan *tscan) +{ + struct { + // ecx + u32 cpu_nthreads : 8, // Number of physical threads - 1 + : 4, // Reserved + apicid_coreid_len : 4, // Number of thread core ID bits (shift) in APIC ID + perf_tsc_len : 2, // Performance time-stamp counter size + : 14; // Reserved + } ecx; + unsigned int sft; + + if (tscan->c->extended_cpuid_level < 0x80000008) + return false; + + cpuid_leaf_reg(0x80000008, CPUID_ECX, &ecx); + + /* If the thread bits are 0, then get the shift value from ecx.cpu_nthreads */ + sft = ecx.apicid_coreid_len; + if (!sft) + sft = get_count_order(ecx.cpu_nthreads + 1); + + /* + * cpu_nthreads describes the number of threads in the package + * sft is the number of APIC ID bits per package + * + * As the number of actual threads per core is not described in + * this leaf, just set the CORE domain shift and let the later + * parsers set SMT shift. Assume one thread per core by default + * which is correct if there are no other CPUID leafs to parse. + */ + topology_update_dom(tscan, TOPO_SMT_DOMAIN, 0, 1); + topology_set_dom(tscan, TOPO_CORE_DOMAIN, sft, ecx.cpu_nthreads + 1); + return true; +} + +static void store_node(struct topo_scan *tscan, u16 nr_nodes, u16 node_id) +{ + /* + * Starting with Fam 17h the DIE domain could probably be used to + * retrieve the node info on AMD/HYGON. Analysis of CPUID dumps + * suggests it's the topmost bit(s) of the CPU cores area, but + * that's guess work and neither enumerated nor documented. + * + * Up to Fam 16h this does not work at all and the legacy node ID + * has to be used. + */ + tscan->amd_nodes_per_pkg = nr_nodes; + tscan->amd_node_id = node_id; +} + +static bool parse_8000_001e(struct topo_scan *tscan, bool has_0xb) +{ + struct { + // eax + u32 ext_apic_id : 32; // Extended APIC ID + // ebx + u32 core_id : 8, // Unique per-socket logical core unit ID + core_nthreads : 8, // #Threads per core (zero-based) + : 16; // Reserved + // ecx + u32 node_id : 8, // Node (die) ID of invoking logical CPU + nnodes_per_socket : 3, // #nodes in invoking logical CPU's package/socket + : 21; // Reserved + // edx + u32 : 32; // Reserved + } leaf; + + if (!boot_cpu_has(X86_FEATURE_TOPOEXT)) + return false; + + cpuid_leaf(0x8000001e, &leaf); + + tscan->c->topo.initial_apicid = leaf.ext_apic_id; + + /* + * If leaf 0xb is available, then the domain shifts are set + * already and nothing to do here. Only valid for family >= 0x17. + */ + if (!has_0xb && tscan->c->x86 >= 0x17) { + /* + * Leaf 0x80000008 set the CORE domain shift already. + * Update the SMT domain, but do not propagate it. + */ + unsigned int nthreads = leaf.core_nthreads + 1; + + topology_update_dom(tscan, TOPO_SMT_DOMAIN, get_count_order(nthreads), nthreads); + } + + store_node(tscan, leaf.nnodes_per_socket + 1, leaf.node_id); + + if (tscan->c->x86_vendor == X86_VENDOR_AMD) { + if (tscan->c->x86 == 0x15) + tscan->c->topo.cu_id = leaf.core_id; + + cacheinfo_amd_init_llc_id(tscan->c, leaf.node_id); + } else { + /* + * Package ID is ApicId[6..] on certain Hygon CPUs. See + * commit e0ceeae708ce for explanation. The topology info + * is screwed up: The package shift is always 6 and the + * node ID is bit [4:5]. + */ + if (!boot_cpu_has(X86_FEATURE_HYPERVISOR) && tscan->c->x86_model <= 0x3) { + topology_set_dom(tscan, TOPO_CORE_DOMAIN, 6, + tscan->dom_ncpus[TOPO_CORE_DOMAIN]); + } + cacheinfo_hygon_init_llc_id(tscan->c); + } + return true; +} + +static void parse_fam10h_node_id(struct topo_scan *tscan) +{ + union { + struct { + u64 node_id : 3, + nodes_per_pkg : 3, + unused : 58; + }; + u64 msr; + } nid; + + if (!boot_cpu_has(X86_FEATURE_NODEID_MSR)) + return; + + rdmsrl(MSR_FAM10H_NODE_ID, nid.msr); + store_node(tscan, nid.nodes_per_pkg + 1, nid.node_id); + tscan->c->topo.llc_id = nid.node_id; +} + +static void legacy_set_llc(struct topo_scan *tscan) +{ + unsigned int apicid = tscan->c->topo.initial_apicid; + + /* If none of the parsers set LLC ID then use the die ID for it. */ + if (tscan->c->topo.llc_id == BAD_APICID) + tscan->c->topo.llc_id = apicid >> tscan->dom_shifts[TOPO_CORE_DOMAIN]; +} + +static void topoext_fixup(struct topo_scan *tscan) +{ + struct cpuinfo_x86 *c = tscan->c; + u64 msrval; + + /* Try to re-enable TopologyExtensions if switched off by BIOS */ + if (cpu_has(c, X86_FEATURE_TOPOEXT) || c->x86_vendor != X86_VENDOR_AMD || + c->x86 != 0x15 || c->x86_model < 0x10 || c->x86_model > 0x6f) + return; + + if (msr_set_bit(0xc0011005, 54) <= 0) + return; + + rdmsrl(0xc0011005, msrval); + if (msrval & BIT_64(54)) { + set_cpu_cap(c, X86_FEATURE_TOPOEXT); + pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); + } +} + +static void parse_topology_amd(struct topo_scan *tscan) +{ + bool has_0xb = false; + + /* + * If the extended topology leaf 0x8000_001e is available + * try to get SMT and CORE shift from leaf 0xb first, then + * try to get the CORE shift from leaf 0x8000_0008. + */ + if (cpu_feature_enabled(X86_FEATURE_TOPOEXT)) + has_0xb = cpu_parse_topology_ext(tscan); + + if (!has_0xb && !parse_8000_0008(tscan)) + return; + + /* Prefer leaf 0x8000001e if available */ + if (parse_8000_001e(tscan, has_0xb)) + return; + + /* Try the NODEID MSR */ + parse_fam10h_node_id(tscan); +} + +void cpu_parse_topology_amd(struct topo_scan *tscan) +{ + tscan->amd_nodes_per_pkg = 1; + topoext_fixup(tscan); + parse_topology_amd(tscan); + legacy_set_llc(tscan); + + if (tscan->amd_nodes_per_pkg > 1) + set_cpu_cap(tscan->c, X86_FEATURE_AMD_DCM); +} + +void cpu_topology_fixup_amd(struct topo_scan *tscan) +{ + struct cpuinfo_x86 *c = tscan->c; + + /* + * Adjust the core_id relative to the node when there is more than + * one node. + */ + if (tscan->c->x86 < 0x17 && tscan->amd_nodes_per_pkg > 1) + c->topo.core_id %= tscan->dom_ncpus[TOPO_CORE_DOMAIN] / tscan->amd_nodes_per_pkg; +} diff --git a/arch/x86/kernel/cpu/topology_common.c b/arch/x86/kernel/cpu/topology_common.c new file mode 100644 index 0000000000..9a6069e713 --- /dev/null +++ b/arch/x86/kernel/cpu/topology_common.c @@ -0,0 +1,220 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/cpu.h> + +#include <xen/xen.h> + +#include <asm/apic.h> +#include <asm/processor.h> +#include <asm/smp.h> + +#include "cpu.h" + +struct x86_topology_system x86_topo_system __ro_after_init; +EXPORT_SYMBOL_GPL(x86_topo_system); + +unsigned int __amd_nodes_per_pkg __ro_after_init; +EXPORT_SYMBOL_GPL(__amd_nodes_per_pkg); + +void topology_set_dom(struct topo_scan *tscan, enum x86_topology_domains dom, + unsigned int shift, unsigned int ncpus) +{ + topology_update_dom(tscan, dom, shift, ncpus); + + /* Propagate to the upper levels */ + for (dom++; dom < TOPO_MAX_DOMAIN; dom++) { + tscan->dom_shifts[dom] = tscan->dom_shifts[dom - 1]; + tscan->dom_ncpus[dom] = tscan->dom_ncpus[dom - 1]; + } +} + +static unsigned int __maybe_unused parse_num_cores_legacy(struct cpuinfo_x86 *c) +{ + struct { + u32 cache_type : 5, + unused : 21, + ncores : 6; + } eax; + + if (c->cpuid_level < 4) + return 1; + + cpuid_subleaf_reg(4, 0, CPUID_EAX, &eax); + if (!eax.cache_type) + return 1; + + return eax.ncores + 1; +} + +static void parse_legacy(struct topo_scan *tscan) +{ + unsigned int cores, core_shift, smt_shift = 0; + struct cpuinfo_x86 *c = tscan->c; + + cores = parse_num_cores_legacy(c); + core_shift = get_count_order(cores); + + if (cpu_has(c, X86_FEATURE_HT)) { + if (!WARN_ON_ONCE(tscan->ebx1_nproc_shift < core_shift)) + smt_shift = tscan->ebx1_nproc_shift - core_shift; + /* + * The parser expects leaf 0xb/0x1f format, which means + * the number of logical processors at core level is + * counting threads. + */ + core_shift += smt_shift; + cores <<= smt_shift; + } + + topology_set_dom(tscan, TOPO_SMT_DOMAIN, smt_shift, 1U << smt_shift); + topology_set_dom(tscan, TOPO_CORE_DOMAIN, core_shift, cores); +} + +static bool fake_topology(struct topo_scan *tscan) +{ + /* + * Preset the CORE level shift for CPUID less systems and XEN_PV, + * which has useless CPUID information. + */ + topology_set_dom(tscan, TOPO_SMT_DOMAIN, 0, 1); + topology_set_dom(tscan, TOPO_CORE_DOMAIN, 0, 1); + + return tscan->c->cpuid_level < 1; +} + +static void parse_topology(struct topo_scan *tscan, bool early) +{ + const struct cpuinfo_topology topo_defaults = { + .cu_id = 0xff, + .llc_id = BAD_APICID, + .l2c_id = BAD_APICID, + }; + struct cpuinfo_x86 *c = tscan->c; + struct { + u32 unused0 : 16, + nproc : 8, + apicid : 8; + } ebx; + + c->topo = topo_defaults; + + if (fake_topology(tscan)) + return; + + /* Preset Initial APIC ID from CPUID leaf 1 */ + cpuid_leaf_reg(1, CPUID_EBX, &ebx); + c->topo.initial_apicid = ebx.apicid; + + /* + * The initial invocation from early_identify_cpu() happens before + * the APIC is mapped or X2APIC enabled. For establishing the + * topology, that's not required. Use the initial APIC ID. + */ + if (early) + c->topo.apicid = c->topo.initial_apicid; + else + c->topo.apicid = read_apic_id(); + + /* The above is sufficient for UP */ + if (!IS_ENABLED(CONFIG_SMP)) + return; + + tscan->ebx1_nproc_shift = get_count_order(ebx.nproc); + + switch (c->x86_vendor) { + case X86_VENDOR_AMD: + if (IS_ENABLED(CONFIG_CPU_SUP_AMD)) + cpu_parse_topology_amd(tscan); + break; + case X86_VENDOR_CENTAUR: + case X86_VENDOR_ZHAOXIN: + parse_legacy(tscan); + break; + case X86_VENDOR_INTEL: + if (!IS_ENABLED(CONFIG_CPU_SUP_INTEL) || !cpu_parse_topology_ext(tscan)) + parse_legacy(tscan); + break; + case X86_VENDOR_HYGON: + if (IS_ENABLED(CONFIG_CPU_SUP_HYGON)) + cpu_parse_topology_amd(tscan); + break; + } +} + +static void topo_set_ids(struct topo_scan *tscan, bool early) +{ + struct cpuinfo_x86 *c = tscan->c; + u32 apicid = c->topo.apicid; + + c->topo.pkg_id = topo_shift_apicid(apicid, TOPO_PKG_DOMAIN); + c->topo.die_id = topo_shift_apicid(apicid, TOPO_DIE_DOMAIN); + + if (!early) { + c->topo.logical_pkg_id = topology_get_logical_id(apicid, TOPO_PKG_DOMAIN); + c->topo.logical_die_id = topology_get_logical_id(apicid, TOPO_DIE_DOMAIN); + } + + /* Package relative core ID */ + c->topo.core_id = (apicid & topo_domain_mask(TOPO_PKG_DOMAIN)) >> + x86_topo_system.dom_shifts[TOPO_SMT_DOMAIN]; + + c->topo.amd_node_id = tscan->amd_node_id; + + if (c->x86_vendor == X86_VENDOR_AMD) + cpu_topology_fixup_amd(tscan); +} + +void cpu_parse_topology(struct cpuinfo_x86 *c) +{ + unsigned int dom, cpu = smp_processor_id(); + struct topo_scan tscan = { .c = c, }; + + parse_topology(&tscan, false); + + if (IS_ENABLED(CONFIG_X86_LOCAL_APIC)) { + if (c->topo.initial_apicid != c->topo.apicid) { + pr_err(FW_BUG "CPU%4u: APIC ID mismatch. CPUID: 0x%04x APIC: 0x%04x\n", + cpu, c->topo.initial_apicid, c->topo.apicid); + } + + if (c->topo.apicid != cpuid_to_apicid[cpu]) { + pr_err(FW_BUG "CPU%4u: APIC ID mismatch. Firmware: 0x%04x APIC: 0x%04x\n", + cpu, cpuid_to_apicid[cpu], c->topo.apicid); + } + } + + for (dom = TOPO_SMT_DOMAIN; dom < TOPO_MAX_DOMAIN; dom++) { + if (tscan.dom_shifts[dom] == x86_topo_system.dom_shifts[dom]) + continue; + pr_err(FW_BUG "CPU%d: Topology domain %u shift %u != %u\n", cpu, dom, + tscan.dom_shifts[dom], x86_topo_system.dom_shifts[dom]); + } + + topo_set_ids(&tscan, false); +} + +void __init cpu_init_topology(struct cpuinfo_x86 *c) +{ + struct topo_scan tscan = { .c = c, }; + unsigned int dom, sft; + + parse_topology(&tscan, true); + + /* Copy the shift values and calculate the unit sizes. */ + memcpy(x86_topo_system.dom_shifts, tscan.dom_shifts, sizeof(x86_topo_system.dom_shifts)); + + dom = TOPO_SMT_DOMAIN; + x86_topo_system.dom_size[dom] = 1U << x86_topo_system.dom_shifts[dom]; + + for (dom++; dom < TOPO_MAX_DOMAIN; dom++) { + sft = x86_topo_system.dom_shifts[dom] - x86_topo_system.dom_shifts[dom - 1]; + x86_topo_system.dom_size[dom] = 1U << sft; + } + + topo_set_ids(&tscan, true); + + /* + * AMD systems have Nodes per package which cannot be mapped to + * APIC ID. + */ + __amd_nodes_per_pkg = tscan.amd_nodes_per_pkg; +} diff --git a/arch/x86/kernel/cpu/topology_ext.c b/arch/x86/kernel/cpu/topology_ext.c new file mode 100644 index 0000000000..e477228cd5 --- /dev/null +++ b/arch/x86/kernel/cpu/topology_ext.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/cpu.h> + +#include <asm/apic.h> +#include <asm/memtype.h> +#include <asm/processor.h> + +#include "cpu.h" + +enum topo_types { + INVALID_TYPE = 0, + SMT_TYPE = 1, + CORE_TYPE = 2, + MAX_TYPE_0B = 3, + MODULE_TYPE = 3, + TILE_TYPE = 4, + DIE_TYPE = 5, + DIEGRP_TYPE = 6, + MAX_TYPE_1F = 7, +}; + +/* + * Use a lookup table for the case that there are future types > 6 which + * describe an intermediate domain level which does not exist today. + */ +static const unsigned int topo_domain_map_0b_1f[MAX_TYPE_1F] = { + [SMT_TYPE] = TOPO_SMT_DOMAIN, + [CORE_TYPE] = TOPO_CORE_DOMAIN, + [MODULE_TYPE] = TOPO_MODULE_DOMAIN, + [TILE_TYPE] = TOPO_TILE_DOMAIN, + [DIE_TYPE] = TOPO_DIE_DOMAIN, + [DIEGRP_TYPE] = TOPO_DIEGRP_DOMAIN, +}; + +static inline bool topo_subleaf(struct topo_scan *tscan, u32 leaf, u32 subleaf, + unsigned int *last_dom) +{ + unsigned int dom, maxtype; + const unsigned int *map; + struct { + // eax + u32 x2apic_shift : 5, // Number of bits to shift APIC ID right + // for the topology ID at the next level + : 27; // Reserved + // ebx + u32 num_processors : 16, // Number of processors at current level + : 16; // Reserved + // ecx + u32 level : 8, // Current topology level. Same as sub leaf number + type : 8, // Level type. If 0, invalid + : 16; // Reserved + // edx + u32 x2apic_id : 32; // X2APIC ID of the current logical processor + } sl; + + switch (leaf) { + case 0x0b: maxtype = MAX_TYPE_0B; map = topo_domain_map_0b_1f; break; + case 0x1f: maxtype = MAX_TYPE_1F; map = topo_domain_map_0b_1f; break; + default: return false; + } + + cpuid_subleaf(leaf, subleaf, &sl); + + if (!sl.num_processors || sl.type == INVALID_TYPE) + return false; + + if (sl.type >= maxtype) { + pr_err_once("Topology: leaf 0x%x:%d Unknown domain type %u\n", + leaf, subleaf, sl.type); + /* + * It really would have been too obvious to make the domain + * type space sparse and leave a few reserved types between + * the points which might change instead of following the + * usual "this can be fixed in software" principle. + */ + dom = *last_dom + 1; + } else { + dom = map[sl.type]; + *last_dom = dom; + } + + if (!dom) { + tscan->c->topo.initial_apicid = sl.x2apic_id; + } else if (tscan->c->topo.initial_apicid != sl.x2apic_id) { + pr_warn_once(FW_BUG "CPUID leaf 0x%x subleaf %d APIC ID mismatch %x != %x\n", + leaf, subleaf, tscan->c->topo.initial_apicid, sl.x2apic_id); + } + + topology_set_dom(tscan, dom, sl.x2apic_shift, sl.num_processors); + return true; +} + +static bool parse_topology_leaf(struct topo_scan *tscan, u32 leaf) +{ + unsigned int last_dom; + u32 subleaf; + + /* Read all available subleafs and populate the levels */ + for (subleaf = 0, last_dom = 0; topo_subleaf(tscan, leaf, subleaf, &last_dom); subleaf++); + + /* If subleaf 0 failed to parse, give up */ + if (!subleaf) + return false; + + /* + * There are machines in the wild which have shift 0 in the subleaf + * 0, but advertise 2 logical processors at that level. They are + * truly SMT. + */ + if (!tscan->dom_shifts[TOPO_SMT_DOMAIN] && tscan->dom_ncpus[TOPO_SMT_DOMAIN] > 1) { + unsigned int sft = get_count_order(tscan->dom_ncpus[TOPO_SMT_DOMAIN]); + + pr_warn_once(FW_BUG "CPUID leaf 0x%x subleaf 0 has shift level 0 but %u CPUs. Fixing it up.\n", + leaf, tscan->dom_ncpus[TOPO_SMT_DOMAIN]); + topology_update_dom(tscan, TOPO_SMT_DOMAIN, sft, tscan->dom_ncpus[TOPO_SMT_DOMAIN]); + } + + set_cpu_cap(tscan->c, X86_FEATURE_XTOPOLOGY); + return true; +} + +bool cpu_parse_topology_ext(struct topo_scan *tscan) +{ + /* Intel: Try leaf 0x1F first. */ + if (tscan->c->cpuid_level >= 0x1f && parse_topology_leaf(tscan, 0x1f)) + return true; + + /* Intel/AMD: Fall back to leaf 0xB if available */ + return tscan->c->cpuid_level >= 0x0b && parse_topology_leaf(tscan, 0x0b); +} diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c index 415564a652..90eba7eb53 100644 --- a/arch/x86/kernel/cpu/zhaoxin.c +++ b/arch/x86/kernel/cpu/zhaoxin.c @@ -71,10 +71,6 @@ static void init_zhaoxin(struct cpuinfo_x86 *c) { early_init_zhaoxin(c); init_intel_cacheinfo(c); - detect_num_cpu_cores(c); -#ifdef CONFIG_X86_32 - detect_ht(c); -#endif if (c->cpuid_level > 9) { unsigned int eax = cpuid_eax(10); diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index b6b044356f..e74d0c4286 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -26,6 +26,7 @@ #include <linux/vmalloc.h> #include <linux/memblock.h> +#include <asm/bootparam.h> #include <asm/processor.h> #include <asm/hardirq.h> #include <asm/nmi.h> @@ -40,6 +41,7 @@ #include <asm/intel_pt.h> #include <asm/crash.h> #include <asm/cmdline.h> +#include <asm/sev.h> /* Used while preparing memory map entries for second kernel */ struct crash_memmap_data { @@ -59,6 +61,8 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs) */ cpu_emergency_stop_pt(); + kdump_sev_callback(); + disable_local_APIC(); } diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index afd0992409..003e0298f4 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -136,7 +136,7 @@ static void __init dtb_cpu_setup(void) pr_warn("%pOF: missing local APIC ID\n", dn); continue; } - generic_processor_info(apic_id); + topology_register_apic(apic_id, CPU_ACPIID_INVALID, true); } } @@ -283,26 +283,28 @@ void __init x86_flattree_get_config(void) u32 size, map_len; void *dt; - if (!initial_dtb) - return; + if (initial_dtb) { + map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128); - map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128); + dt = early_memremap(initial_dtb, map_len); + size = fdt_totalsize(dt); + if (map_len < size) { + early_memunmap(dt, map_len); + dt = early_memremap(initial_dtb, size); + map_len = size; + } - dt = early_memremap(initial_dtb, map_len); - size = fdt_totalsize(dt); - if (map_len < size) { - early_memunmap(dt, map_len); - dt = early_memremap(initial_dtb, size); - map_len = size; + early_init_dt_verify(dt); } - early_init_dt_verify(dt); unflatten_and_copy_device_tree(); - early_memunmap(dt, map_len); + + if (initial_dtb) + early_memunmap(dt, map_len); } #endif -void __init x86_dtb_init(void) +void __init x86_dtb_parse_smp_config(void) { if (!of_have_populated_dt()) return; diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index f18ca44c90..44a91ef5a2 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -410,7 +410,7 @@ static void __die_header(const char *str, struct pt_regs *regs, long err) IS_ENABLED(CONFIG_SMP) ? " SMP" : "", debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "", IS_ENABLED(CONFIG_KASAN) ? " KASAN" : "", - IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION) ? + IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION) ? (boot_cpu_has(X86_FEATURE_PTI) ? " PTI" : " NOPTI") : ""); } NOKPROBE_SYMBOL(__die_header); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index b66f540de0..68b09f718f 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -532,9 +532,10 @@ u64 __init e820__range_update(u64 start, u64 size, enum e820_type old_type, enum return __e820__range_update(e820_table, start, size, old_type, new_type); } -static u64 __init e820__range_update_kexec(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type) +u64 __init e820__range_update_table(struct e820_table *t, u64 start, u64 size, + enum e820_type old_type, enum e820_type new_type) { - return __e820__range_update(e820_table_kexec, start, size, old_type, new_type); + return __e820__range_update(t, start, size, old_type, new_type); } /* Remove a range of memory from the E820 table: */ @@ -806,7 +807,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) addr = memblock_phys_alloc(size, align); if (addr) { - e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__range_update_table(e820_table_kexec, addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n"); e820__update_table_kexec(); } @@ -1016,17 +1017,6 @@ void __init e820__reserve_setup_data(void) e820__range_update(pa_data, sizeof(*data)+data->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - /* - * SETUP_EFI, SETUP_IMA and SETUP_RNG_SEED are supplied by - * kexec and do not need to be reserved. - */ - if (data->type != SETUP_EFI && - data->type != SETUP_IMA && - data->type != SETUP_RNG_SEED) - e820__range_update_kexec(pa_data, - sizeof(*data) + data->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - if (data->type == SETUP_INDIRECT) { len += data->len; early_memunmap(data, sizeof(*data)); @@ -1038,12 +1028,9 @@ void __init e820__reserve_setup_data(void) indirect = (struct setup_indirect *)data->data; - if (indirect->type != SETUP_INDIRECT) { + if (indirect->type != SETUP_INDIRECT) e820__range_update(indirect->addr, indirect->len, E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - e820__range_update_kexec(indirect->addr, indirect->len, - E820_TYPE_RAM, E820_TYPE_RESERVED_KERN); - } } pa_data = pa_next; @@ -1051,7 +1038,6 @@ void __init e820__reserve_setup_data(void) } e820__update_table(e820_table); - e820__update_table(e820_table_kexec); pr_info("extended physical RAM map:\n"); e820__print_table("reserve setup_data"); diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c index 16f9814c9b..6726e0473d 100644 --- a/arch/x86/kernel/espfix_64.c +++ b/arch/x86/kernel/espfix_64.c @@ -106,6 +106,10 @@ void __init init_espfix_bsp(void) pgd_t *pgd; p4d_t *p4d; + /* FRED systems always restore the full value of %rsp */ + if (cpu_feature_enabled(X86_FEATURE_FRED)) + return; + /* Install the espfix pud into the kernel page directory */ pgd = &init_top_pgt[pgd_index(ESPFIX_BASE_ADDR)]; p4d = p4d_alloc(&init_mm, pgd, ESPFIX_BASE_ADDR); @@ -129,6 +133,10 @@ void init_espfix_ap(int cpu) void *stack_page; pteval_t ptemask; + /* FRED systems always restore the full value of %rsp */ + if (cpu_feature_enabled(X86_FEATURE_FRED)) + return; + /* We only have to do this once... */ if (likely(per_cpu(espfix_stack, cpu))) return; /* Already initialized */ diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c index a06b876bbf..edbafc5940 100644 --- a/arch/x86/kernel/fpu/bugs.c +++ b/arch/x86/kernel/fpu/bugs.c @@ -2,6 +2,8 @@ /* * x86 FPU bug checks: */ +#include <linux/printk.h> + #include <asm/cpufeature.h> #include <asm/fpu/api.h> diff --git a/arch/x86/kernel/fred.c b/arch/x86/kernel/fred.c new file mode 100644 index 0000000000..4bcd8791ad --- /dev/null +++ b/arch/x86/kernel/fred.c @@ -0,0 +1,59 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/kernel.h> + +#include <asm/desc.h> +#include <asm/fred.h> +#include <asm/tlbflush.h> +#include <asm/traps.h> + +/* #DB in the kernel would imply the use of a kernel debugger. */ +#define FRED_DB_STACK_LEVEL 1UL +#define FRED_NMI_STACK_LEVEL 2UL +#define FRED_MC_STACK_LEVEL 2UL +/* + * #DF is the highest level because a #DF means "something went wrong + * *while delivering an exception*." The number of cases for which that + * can happen with FRED is drastically reduced and basically amounts to + * "the stack you pointed me to is broken." Thus, always change stacks + * on #DF, which means it should be at the highest level. + */ +#define FRED_DF_STACK_LEVEL 3UL + +#define FRED_STKLVL(vector, lvl) ((lvl) << (2 * (vector))) + +void cpu_init_fred_exceptions(void) +{ + /* When FRED is enabled by default, remove this log message */ + pr_info("Initialize FRED on CPU%d\n", smp_processor_id()); + + wrmsrl(MSR_IA32_FRED_CONFIG, + /* Reserve for CALL emulation */ + FRED_CONFIG_REDZONE | + FRED_CONFIG_INT_STKLVL(0) | + FRED_CONFIG_ENTRYPOINT(asm_fred_entrypoint_user)); + + /* + * The purpose of separate stacks for NMI, #DB and #MC *in the kernel* + * (remember that user space faults are always taken on stack level 0) + * is to avoid overflowing the kernel stack. + */ + wrmsrl(MSR_IA32_FRED_STKLVLS, + FRED_STKLVL(X86_TRAP_DB, FRED_DB_STACK_LEVEL) | + FRED_STKLVL(X86_TRAP_NMI, FRED_NMI_STACK_LEVEL) | + FRED_STKLVL(X86_TRAP_MC, FRED_MC_STACK_LEVEL) | + FRED_STKLVL(X86_TRAP_DF, FRED_DF_STACK_LEVEL)); + + /* The FRED equivalents to IST stacks... */ + wrmsrl(MSR_IA32_FRED_RSP1, __this_cpu_ist_top_va(DB)); + wrmsrl(MSR_IA32_FRED_RSP2, __this_cpu_ist_top_va(NMI)); + wrmsrl(MSR_IA32_FRED_RSP3, __this_cpu_ist_top_va(DF)); + + /* Enable FRED */ + cr4_set_bits(X86_CR4_FRED); + /* Any further IDT use is a bug */ + idt_invalidate(); + + /* Use int $0x80 for 32-bit system calls in FRED mode */ + setup_clear_cpu_cap(X86_FEATURE_SYSENTER32); + setup_clear_cpu_cap(X86_FEATURE_SYSCALL32); +} diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c index 12df54ff0e..70139d9d2e 100644 --- a/arch/x86/kernel/ftrace.c +++ b/arch/x86/kernel/ftrace.c @@ -307,7 +307,8 @@ union ftrace_op_code_union { } __attribute__((packed)); }; -#define RET_SIZE (IS_ENABLED(CONFIG_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_SLS)) +#define RET_SIZE \ + (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) ? 5 : 1 + IS_ENABLED(CONFIG_MITIGATION_SLS)) static unsigned long create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size) diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index dc09560679..a817ed0724 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -22,6 +22,8 @@ #include <linux/cc_platform.h> #include <linux/pgtable.h> +#include <asm/asm.h> +#include <asm/page_64.h> #include <asm/processor.h> #include <asm/proto.h> #include <asm/smp.h> @@ -67,42 +69,11 @@ unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4; EXPORT_SYMBOL(vmemmap_base); #endif -/* - * GDT used on the boot CPU before switching to virtual addresses. - */ -static struct desc_struct startup_gdt[GDT_ENTRIES] __initdata = { - [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff), - [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(DESC_CODE64, 0, 0xfffff), - [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(DESC_DATA64, 0, 0xfffff), -}; - -/* - * Address needs to be set at runtime because it references the startup_gdt - * while the kernel still uses a direct mapping. - */ -static struct desc_ptr startup_gdt_descr __initdata = { - .size = sizeof(startup_gdt)-1, - .address = 0, -}; - -static void __head *fixup_pointer(void *ptr, unsigned long physaddr) -{ - return ptr - (void *)_text + (void *)physaddr; -} - -static unsigned long __head *fixup_long(void *ptr, unsigned long physaddr) +static inline bool check_la57_support(void) { - return fixup_pointer(ptr, physaddr); -} - -#ifdef CONFIG_X86_5LEVEL -static unsigned int __head *fixup_int(void *ptr, unsigned long physaddr) -{ - return fixup_pointer(ptr, physaddr); -} + if (!IS_ENABLED(CONFIG_X86_5LEVEL)) + return false; -static bool __head check_la57_support(unsigned long physaddr) -{ /* * 5-level paging is detected and enabled at kernel decompression * stage. Only check if it has been enabled there. @@ -110,21 +81,15 @@ static bool __head check_la57_support(unsigned long physaddr) if (!(native_read_cr4() & X86_CR4_LA57)) return false; - *fixup_int(&__pgtable_l5_enabled, physaddr) = 1; - *fixup_int(&pgdir_shift, physaddr) = 48; - *fixup_int(&ptrs_per_p4d, physaddr) = 512; - *fixup_long(&page_offset_base, physaddr) = __PAGE_OFFSET_BASE_L5; - *fixup_long(&vmalloc_base, physaddr) = __VMALLOC_BASE_L5; - *fixup_long(&vmemmap_base, physaddr) = __VMEMMAP_BASE_L5; + RIP_REL_REF(__pgtable_l5_enabled) = 1; + RIP_REL_REF(pgdir_shift) = 48; + RIP_REL_REF(ptrs_per_p4d) = 512; + RIP_REL_REF(page_offset_base) = __PAGE_OFFSET_BASE_L5; + RIP_REL_REF(vmalloc_base) = __VMALLOC_BASE_L5; + RIP_REL_REF(vmemmap_base) = __VMEMMAP_BASE_L5; return true; } -#else -static bool __head check_la57_support(unsigned long physaddr) -{ - return false; -} -#endif static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdval_t *pmd) { @@ -173,23 +138,22 @@ static unsigned long __head sme_postprocess_startup(struct boot_params *bp, pmdv * doesn't have to generate PC-relative relocations when accessing globals from * that function. Clang actually does not generate them, which leads to * boot-time crashes. To work around this problem, every global pointer must - * be adjusted using fixup_pointer(). + * be accessed using RIP_REL_REF(). */ unsigned long __head __startup_64(unsigned long physaddr, struct boot_params *bp) { - unsigned long load_delta, *p; + pmd_t (*early_pgts)[PTRS_PER_PMD] = RIP_REL_REF(early_dynamic_pgts); unsigned long pgtable_flags; + unsigned long load_delta; pgdval_t *pgd; p4dval_t *p4d; pudval_t *pud; pmdval_t *pmd, pmd_entry; - pteval_t *mask_ptr; bool la57; int i; - unsigned int *next_pgt_ptr; - la57 = check_la57_support(physaddr); + la57 = check_la57_support(); /* Is the address too large? */ if (physaddr >> MAX_PHYSMEM_BITS) @@ -200,6 +164,7 @@ unsigned long __head __startup_64(unsigned long physaddr, * and the address I am actually running at. */ load_delta = physaddr - (unsigned long)(_text - __START_KERNEL_map); + RIP_REL_REF(phys_base) = load_delta; /* Is the address not 2M aligned? */ if (load_delta & ~PMD_MASK) @@ -210,26 +175,21 @@ unsigned long __head __startup_64(unsigned long physaddr, /* Fixup the physical addresses in the page table */ - pgd = fixup_pointer(early_top_pgt, physaddr); - p = pgd + pgd_index(__START_KERNEL_map); - if (la57) - *p = (unsigned long)level4_kernel_pgt; - else - *p = (unsigned long)level3_kernel_pgt; - *p += _PAGE_TABLE_NOENC - __START_KERNEL_map + load_delta; + pgd = &RIP_REL_REF(early_top_pgt)->pgd; + pgd[pgd_index(__START_KERNEL_map)] += load_delta; if (la57) { - p4d = fixup_pointer(level4_kernel_pgt, physaddr); - p4d[511] += load_delta; + p4d = (p4dval_t *)&RIP_REL_REF(level4_kernel_pgt); + p4d[MAX_PTRS_PER_P4D - 1] += load_delta; + + pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE; } - pud = fixup_pointer(level3_kernel_pgt, physaddr); - pud[510] += load_delta; - pud[511] += load_delta; + RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 2].pud += load_delta; + RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 1].pud += load_delta; - pmd = fixup_pointer(level2_fixmap_pgt, physaddr); for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--) - pmd[i] += load_delta; + RIP_REL_REF(level2_fixmap_pgt)[i].pmd += load_delta; /* * Set up the identity mapping for the switchover. These @@ -238,15 +198,14 @@ unsigned long __head __startup_64(unsigned long physaddr, * it avoids problems around wraparound. */ - next_pgt_ptr = fixup_pointer(&next_early_pgt, physaddr); - pud = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); - pmd = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], physaddr); + pud = &early_pgts[0]->pmd; + pmd = &early_pgts[1]->pmd; + RIP_REL_REF(next_early_pgt) = 2; pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask(); if (la57) { - p4d = fixup_pointer(early_dynamic_pgts[(*next_pgt_ptr)++], - physaddr); + p4d = &early_pgts[RIP_REL_REF(next_early_pgt)++]->pmd; i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD; pgd[i + 0] = (pgdval_t)p4d + pgtable_flags; @@ -267,8 +226,7 @@ unsigned long __head __startup_64(unsigned long physaddr, pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL; /* Filter out unsupported __PAGE_KERNEL_* bits: */ - mask_ptr = fixup_pointer(&__supported_pte_mask, physaddr); - pmd_entry &= *mask_ptr; + pmd_entry &= RIP_REL_REF(__supported_pte_mask); pmd_entry += sme_get_me_mask(); pmd_entry += physaddr; @@ -294,7 +252,7 @@ unsigned long __head __startup_64(unsigned long physaddr, * error, causing the BIOS to halt the system. */ - pmd = fixup_pointer(level2_kernel_pgt, physaddr); + pmd = &RIP_REL_REF(level2_kernel_pgt)->pmd; /* invalidate pages before the kernel image */ for (i = 0; i < pmd_index((unsigned long)_text); i++) @@ -309,12 +267,6 @@ unsigned long __head __startup_64(unsigned long physaddr, for (; i < PTRS_PER_PMD; i++) pmd[i] &= ~_PAGE_PRESENT; - /* - * Fixup phys_base - remove the memory encryption mask to obtain - * the true physical address. - */ - *fixup_long(&phys_base, physaddr) += load_delta - sme_get_me_mask(); - return sme_postprocess_startup(bp, pmd); } @@ -569,62 +521,52 @@ void __init __noreturn x86_64_start_reservations(char *real_mode_data) */ static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data; -static struct desc_ptr bringup_idt_descr = { - .size = (NUM_EXCEPTION_VECTORS * sizeof(gate_desc)) - 1, - .address = 0, /* Set at runtime */ -}; - -static void set_bringup_idt_handler(gate_desc *idt, int n, void *handler) +/* This may run while still in the direct mapping */ +static void __head startup_64_load_idt(void *vc_handler) { -#ifdef CONFIG_AMD_MEM_ENCRYPT + struct desc_ptr desc = { + .address = (unsigned long)&RIP_REL_REF(bringup_idt_table), + .size = sizeof(bringup_idt_table) - 1, + }; struct idt_data data; - gate_desc desc; - - init_idt_data(&data, n, handler); - idt_init_desc(&desc, &data); - native_write_idt_entry(idt, n, &desc); -#endif -} + gate_desc idt_desc; -/* This runs while still in the direct mapping */ -static void __head startup_64_load_idt(unsigned long physbase) -{ - struct desc_ptr *desc = fixup_pointer(&bringup_idt_descr, physbase); - gate_desc *idt = fixup_pointer(bringup_idt_table, physbase); - - - if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { - void *handler; - - /* VMM Communication Exception */ - handler = fixup_pointer(vc_no_ghcb, physbase); - set_bringup_idt_handler(idt, X86_TRAP_VC, handler); + /* @vc_handler is set only for a VMM Communication Exception */ + if (vc_handler) { + init_idt_data(&data, X86_TRAP_VC, vc_handler); + idt_init_desc(&idt_desc, &data); + native_write_idt_entry((gate_desc *)desc.address, X86_TRAP_VC, &idt_desc); } - desc->address = (unsigned long)idt; - native_load_idt(desc); + native_load_idt(&desc); } /* This is used when running on kernel addresses */ void early_setup_idt(void) { - /* VMM Communication Exception */ + void *handler = NULL; + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) { setup_ghcb(); - set_bringup_idt_handler(bringup_idt_table, X86_TRAP_VC, vc_boot_ghcb); + handler = vc_boot_ghcb; } - bringup_idt_descr.address = (unsigned long)bringup_idt_table; - native_load_idt(&bringup_idt_descr); + startup_64_load_idt(handler); } /* * Setup boot CPU state needed before kernel switches to virtual addresses. */ -void __head startup_64_setup_env(unsigned long physbase) +void __head startup_64_setup_gdt_idt(void) { + void *handler = NULL; + + struct desc_ptr startup_gdt_descr = { + .address = (unsigned long)&RIP_REL_REF(init_per_cpu_var(gdt_page.gdt)), + .size = GDT_SIZE - 1, + }; + /* Load GDT */ - startup_gdt_descr.address = (unsigned long)fixup_pointer(startup_gdt, physbase); native_load_gdt(&startup_gdt_descr); /* New GDT is live - reload data segment registers */ @@ -632,5 +574,8 @@ void __head startup_64_setup_env(unsigned long physbase) "movl %%eax, %%ss\n" "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory"); - startup_64_load_idt(physbase); + if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT)) + handler = &RIP_REL_REF(vc_no_ghcb); + + startup_64_load_idt(handler); } diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index 487ac57e2c..b50f3641c4 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -414,7 +414,7 @@ __REFDATA .align 4 SYM_DATA(initial_code, .long i386_start_kernel) -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION #define PGD_ALIGN (2 * PAGE_SIZE) #define PTI_USER_PGD_FILL 1024 #else @@ -474,7 +474,7 @@ SYM_DATA_START(initial_page_table) # endif .align PAGE_SIZE /* needs to be page-sized too */ -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * PTI needs another page so sync_initial_pagetable() works correctly * and does not scribble over the data which is placed behind the diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index d4918d03ef..d8198fbd70 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -26,6 +26,7 @@ #include <asm/apicdef.h> #include <asm/fixmap.h> #include <asm/smp.h> +#include <asm/thread_info.h> /* * We are not able to switch in one step to the final KERNEL ADDRESS SPACE @@ -39,7 +40,6 @@ L4_START_KERNEL = l4_index(__START_KERNEL_map) L3_START_KERNEL = pud_index(__START_KERNEL_map) - .text __HEAD .code64 SYM_CODE_START_NOALIGN(startup_64) @@ -66,9 +66,7 @@ SYM_CODE_START_NOALIGN(startup_64) mov %rsi, %r15 /* Set up the stack for verify_cpu() */ - leaq (__end_init_task - PTREGS_SIZE)(%rip), %rsp - - leaq _text(%rip), %rdi + leaq (__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp /* Setup GSBASE to allow stack canary access for C code */ movl $MSR_GS_BASE, %ecx @@ -77,7 +75,7 @@ SYM_CODE_START_NOALIGN(startup_64) shrq $32, %rdx wrmsr - call startup_64_setup_env + call startup_64_setup_gdt_idt /* Now switch to __KERNEL_CS so IRET works reliably */ pushq $__KERNEL_CS @@ -113,13 +111,11 @@ SYM_CODE_START_NOALIGN(startup_64) call __startup_64 /* Form the CR3 value being sure to include the CR3 modifier */ - addq $(early_top_pgt - __START_KERNEL_map), %rax + leaq early_top_pgt(%rip), %rcx + addq %rcx, %rax #ifdef CONFIG_AMD_MEM_ENCRYPT mov %rax, %rdi - mov %rax, %r14 - - addq phys_base(%rip), %rdi /* * For SEV guests: Verify that the C-bit is correct. A malicious @@ -128,17 +124,23 @@ SYM_CODE_START_NOALIGN(startup_64) * the next RET instruction. */ call sev_verify_cbit +#endif /* - * Restore CR3 value without the phys_base which will be added - * below, before writing %cr3. + * Switch to early_top_pgt which still has the identity mappings + * present. */ - mov %r14, %rax -#endif + movq %rax, %cr3 - jmp 1f + /* Branch to the common startup code at its kernel virtual address */ + ANNOTATE_RETPOLINE_SAFE + jmp *0f(%rip) SYM_CODE_END(startup_64) + __INITRODATA +0: .quad common_startup_64 + + .text SYM_CODE_START(secondary_startup_64) UNWIND_HINT_END_OF_STACK ANNOTATE_NOENDBR @@ -171,22 +173,39 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) ANNOTATE_NOENDBR /* Clear %R15 which holds the boot_params pointer on the boot CPU */ - xorq %r15, %r15 + xorl %r15d, %r15d + + /* Derive the runtime physical address of init_top_pgt[] */ + movq phys_base(%rip), %rax + addq $(init_top_pgt - __START_KERNEL_map), %rax /* * Retrieve the modifier (SME encryption mask if SME is active) to be * added to the initial pgdir entry that will be programmed into CR3. */ #ifdef CONFIG_AMD_MEM_ENCRYPT - movq sme_me_mask, %rax -#else - xorq %rax, %rax + addq sme_me_mask(%rip), %rax #endif + /* + * Switch to the init_top_pgt here, away from the trampoline_pgd and + * unmap the identity mapped ranges. + */ + movq %rax, %cr3 - /* Form the CR3 value being sure to include the CR3 modifier */ - addq $(init_top_pgt - __START_KERNEL_map), %rax -1: +SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL) + UNWIND_HINT_END_OF_STACK + ANNOTATE_NOENDBR + /* + * Create a mask of CR4 bits to preserve. Omit PGE in order to flush + * global 1:1 translations from the TLBs. + * + * From the SDM: + * "If CR4.PGE is changing from 0 to 1, there were no global TLB + * entries before the execution; if CR4.PGE is changing from 1 to 0, + * there will be no global TLB entries after the execution." + */ + movl $(X86_CR4_PAE | X86_CR4_LA57), %edx #ifdef CONFIG_X86_MCE /* * Preserve CR4.MCE if the kernel will enable #MC support. @@ -195,52 +214,20 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) * configured will crash the system regardless of the CR4.MCE value set * here. */ - movq %cr4, %rcx - andl $X86_CR4_MCE, %ecx -#else - movl $0, %ecx + orl $X86_CR4_MCE, %edx #endif + movq %cr4, %rcx + andl %edx, %ecx - /* Enable PAE mode, PSE, PGE and LA57 */ - orl $(X86_CR4_PAE | X86_CR4_PSE | X86_CR4_PGE), %ecx -#ifdef CONFIG_X86_5LEVEL - testb $1, __pgtable_l5_enabled(%rip) - jz 1f - orl $X86_CR4_LA57, %ecx -1: -#endif + /* Even if ignored in long mode, set PSE uniformly on all logical CPUs. */ + btsl $X86_CR4_PSE_BIT, %ecx movq %rcx, %cr4 - /* Setup early boot stage 4-/5-level pagetables. */ - addq phys_base(%rip), %rax - /* - * Switch to new page-table - * - * For the boot CPU this switches to early_top_pgt which still has the - * identity mappings present. The secondary CPUs will switch to the - * init_top_pgt here, away from the trampoline_pgd and unmap the - * identity mapped ranges. + * Set CR4.PGE to re-enable global translations. */ - movq %rax, %cr3 - - /* - * Do a global TLB flush after the CR3 switch to make sure the TLB - * entries from the identity mapping are flushed. - */ - movq %cr4, %rcx - movq %rcx, %rax - xorq $X86_CR4_PGE, %rcx + btsl $X86_CR4_PGE_BIT, %ecx movq %rcx, %cr4 - movq %rax, %cr4 - - /* Ensure I am executing from virtual addresses */ - movq $1f, %rax - ANNOTATE_RETPOLINE_SAFE - jmp *%rax -1: - UNWIND_HINT_END_OF_STACK - ANNOTATE_NOENDBR // above #ifdef CONFIG_SMP /* @@ -297,7 +284,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) .Llookup_AP: /* EAX contains the APIC ID of the current CPU */ - xorq %rcx, %rcx + xorl %ecx, %ecx leaq cpuid_to_apicid(%rip), %rbx .Lfind_cpunr: @@ -428,39 +415,10 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) movq %r15, %rdi .Ljump_to_C_code: - /* - * Jump to run C code and to be on a real kernel address. - * Since we are running on identity-mapped space we have to jump - * to the full 64bit address, this is only possible as indirect - * jump. In addition we need to ensure %cs is set so we make this - * a far return. - * - * Note: do not change to far jump indirect with 64bit offset. - * - * AMD does not support far jump indirect with 64bit offset. - * AMD64 Architecture Programmer's Manual, Volume 3: states only - * JMP FAR mem16:16 FF /5 Far jump indirect, - * with the target specified by a far pointer in memory. - * JMP FAR mem16:32 FF /5 Far jump indirect, - * with the target specified by a far pointer in memory. - * - * Intel64 does support 64bit offset. - * Software Developer Manual Vol 2: states: - * FF /5 JMP m16:16 Jump far, absolute indirect, - * address given in m16:16 - * FF /5 JMP m16:32 Jump far, absolute indirect, - * address given in m16:32. - * REX.W + FF /5 JMP m16:64 Jump far, absolute indirect, - * address given in m16:64. - */ - pushq $.Lafter_lret # put return address on stack for unwinder xorl %ebp, %ebp # clear frame pointer - movq initial_code(%rip), %rax - pushq $__KERNEL_CS # set correct cs - pushq %rax # target address in negative space - lretq -.Lafter_lret: - ANNOTATE_NOENDBR + ANNOTATE_RETPOLINE_SAFE + callq *initial_code(%rip) + ud2 SYM_CODE_END(secondary_startup_64) #include "verify_cpu.S" @@ -477,7 +435,7 @@ SYM_CODE_START(soft_restart_cpu) UNWIND_HINT_END_OF_STACK /* Find the idle task stack */ - movq PER_CPU_VAR(pcpu_hot) + X86_current_task, %rcx + movq PER_CPU_VAR(pcpu_hot + X86_current_task), %rcx movq TASK_threadsp(%rcx), %rsp jmp .Ljump_to_C_code @@ -622,7 +580,7 @@ SYM_CODE_END(vc_no_ghcb) #define SYM_DATA_START_PAGE_ALIGNED(name) \ SYM_START(name, SYM_L_GLOBAL, .balign PAGE_SIZE) -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * Each PGD needs to be 8k long and 8k aligned. We do not * ever go out to userspace with these, so we do not @@ -655,7 +613,8 @@ SYM_CODE_END(vc_no_ghcb) .balign 4 SYM_DATA_START_PTI_ALIGNED(early_top_pgt) - .fill 512,8,0 + .fill 511,8,0 + .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC .fill PTI_USER_PGD_FILL,8,0 SYM_DATA_END(early_top_pgt) diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index a38d0c93a6..c96ae8fee9 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -568,7 +568,7 @@ static struct irq_domain *hpet_create_irq_domain(int hpet_id) fwspec.param_count = 1; fwspec.param[0] = hpet_id; - parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_ANY); + parent = irq_find_matching_fwspec(&fwspec, DOMAIN_BUS_GENERIC_MSI); if (!parent) { irq_domain_free_fwnode(fn); kfree(domain_info); diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 660b601f1d..fc37c8d83d 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -153,7 +153,7 @@ static const __initconst struct idt_data apic_idts[] = { #ifdef CONFIG_X86_LOCAL_APIC INTG(LOCAL_TIMER_VECTOR, asm_sysvec_apic_timer_interrupt), INTG(X86_PLATFORM_IPI_VECTOR, asm_sysvec_x86_platform_ipi), -# ifdef CONFIG_HAVE_KVM +# if IS_ENABLED(CONFIG_KVM) INTG(POSTED_INTR_VECTOR, asm_sysvec_kvm_posted_intr_ipi), INTG(POSTED_INTR_WAKEUP_VECTOR, asm_sysvec_kvm_posted_intr_wakeup_ipi), INTG(POSTED_INTR_NESTED_VECTOR, asm_sysvec_kvm_posted_intr_nested_ipi), @@ -337,7 +337,7 @@ void idt_invalidate(void) load_idt(&idt); } -void __init alloc_intr_gate(unsigned int n, const void *addr) +void __init idt_install_sysvec(unsigned int n, const void *function) { if (WARN_ON(n < FIRST_SYSTEM_VECTOR)) return; @@ -346,5 +346,5 @@ void __init alloc_intr_gate(unsigned int n, const void *addr) return; if (!WARN_ON(test_and_set_bit(n, system_vectors))) - set_intr_gate(n, addr); + set_intr_gate(n, function); } diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 11761c1245..35fde01079 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -164,7 +164,7 @@ int arch_show_interrupts(struct seq_file *p, int prec) #if defined(CONFIG_X86_IO_APIC) seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count)); #endif -#ifdef CONFIG_HAVE_KVM +#if IS_ENABLED(CONFIG_KVM) seq_printf(p, "%*s: ", prec, "PIN"); for_each_online_cpu(j) seq_printf(p, "%10u ", irq_stats(j)->kvm_posted_intr_ipis); @@ -290,7 +290,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_x86_platform_ipi) } #endif -#ifdef CONFIG_HAVE_KVM +#if IS_ENABLED(CONFIG_KVM) static void dummy_handler(void) {} static void (*kvm_posted_intr_wakeup_handler)(void) = dummy_handler; diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c index c683666876..f79c5edc0b 100644 --- a/arch/x86/kernel/irqinit.c +++ b/arch/x86/kernel/irqinit.c @@ -28,6 +28,7 @@ #include <asm/setup.h> #include <asm/i8259.h> #include <asm/traps.h> +#include <asm/fred.h> #include <asm/prom.h> /* @@ -96,7 +97,11 @@ void __init native_init_IRQ(void) /* Execute any quirks before the call gates are initialised: */ x86_init.irqs.pre_vector_init(); - idt_setup_apic_and_irq_gates(); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + fred_complete_exception_setup(); + else + idt_setup_apic_and_irq_gates(); + lapic_assign_system_vectors(); if (!acpi_ioapic && !of_ioapic && nr_legacy_irqs()) { diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c index 578d16fc04..df33786061 100644 --- a/arch/x86/kernel/jailhouse.c +++ b/arch/x86/kernel/jailhouse.c @@ -89,7 +89,7 @@ static void __init jailhouse_x2apic_init(void) #endif } -static void __init jailhouse_get_smp_config(unsigned int early) +static void __init jailhouse_parse_smp_config(void) { struct ioapic_domain_cfg ioapic_cfg = { .type = IOAPIC_DOMAIN_STRICT, @@ -102,7 +102,7 @@ static void __init jailhouse_get_smp_config(unsigned int early) register_lapic_address(0xfee00000); for (cpu = 0; cpu < setup_data.v1.num_cpus; cpu++) - generic_processor_info(setup_data.v1.cpu_ids[cpu]); + topology_register_apic(setup_data.v1.cpu_ids[cpu], CPU_ACPIID_INVALID, true); smp_found_config = 1; @@ -201,21 +201,23 @@ static void __init jailhouse_init_platform(void) struct setup_data header; void *mapping; - x86_init.irqs.pre_vector_init = x86_init_noop; - x86_init.timers.timer_init = jailhouse_timer_init; - x86_init.mpparse.get_smp_config = jailhouse_get_smp_config; - x86_init.pci.arch_init = jailhouse_pci_arch_init; + x86_init.irqs.pre_vector_init = x86_init_noop; + x86_init.timers.timer_init = jailhouse_timer_init; + x86_init.mpparse.find_mptable = x86_init_noop; + x86_init.mpparse.early_parse_smp_cfg = x86_init_noop; + x86_init.mpparse.parse_smp_cfg = jailhouse_parse_smp_config; + x86_init.pci.arch_init = jailhouse_pci_arch_init; - x86_platform.calibrate_cpu = jailhouse_get_tsc; - x86_platform.calibrate_tsc = jailhouse_get_tsc; - x86_platform.get_wallclock = jailhouse_get_wallclock; - x86_platform.legacy.rtc = 0; - x86_platform.legacy.warm_reset = 0; - x86_platform.legacy.i8042 = X86_LEGACY_I8042_PLATFORM_ABSENT; + x86_platform.calibrate_cpu = jailhouse_get_tsc; + x86_platform.calibrate_tsc = jailhouse_get_tsc; + x86_platform.get_wallclock = jailhouse_get_wallclock; + x86_platform.legacy.rtc = 0; + x86_platform.legacy.warm_reset = 0; + x86_platform.legacy.i8042 = X86_LEGACY_I8042_PLATFORM_ABSENT; - legacy_pic = &null_legacy_pic; + legacy_pic = &null_legacy_pic; - machine_ops.emergency_restart = jailhouse_no_restart; + machine_ops.emergency_restart = jailhouse_no_restart; while (pa_data) { mapping = early_memremap(pa_data, sizeof(header)); diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 2a422e00ed..68530fad05 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -263,11 +263,13 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, memset(¶ms->hd0_info, 0, sizeof(params->hd0_info)); memset(¶ms->hd1_info, 0, sizeof(params->hd1_info)); +#ifdef CONFIG_CRASH_DUMP if (image->type == KEXEC_TYPE_CRASH) { ret = crash_setup_memmap_entries(image, params); if (ret) return ret; } else +#endif setup_e820_entries(params); nr_e820_entries = params->e820_entries; @@ -433,12 +435,14 @@ static void *bzImage64_load(struct kimage *image, char *kernel, return ERR_PTR(-EINVAL); } +#ifdef CONFIG_CRASH_DUMP /* Allocate and load backup region */ if (image->type == KEXEC_TYPE_CRASH) { ret = crash_load_segments(image); if (ret) return ERR_PTR(ret); } +#endif /* * Load purgatory. For 64bit entry point, purgatory code can be @@ -503,7 +507,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel, kbuf.bufsz = kernel_len - kern16_size; kbuf.memsz = PAGE_ALIGN(header->init_size); kbuf.buf_align = header->kernel_alignment; - kbuf.buf_min = MIN_KERNEL_LOAD_ADDR; + if (header->pref_address < MIN_KERNEL_LOAD_ADDR) + kbuf.buf_min = MIN_KERNEL_LOAD_ADDR; + else + kbuf.buf_min = header->pref_address; kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; ret = kexec_add_buffer(&kbuf); if (ret) diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h index c993521d49..e772276f5a 100644 --- a/arch/x86/kernel/kprobes/common.h +++ b/arch/x86/kernel/kprobes/common.h @@ -78,7 +78,7 @@ #endif /* Ensure if the instruction can be boostable */ -extern int can_boost(struct insn *insn, void *orig_addr); +extern bool can_boost(struct insn *insn, void *orig_addr); /* Recover instruction if given address is probed */ extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr); diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index a6a3475e1d..d0e49bd7c6 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -137,14 +137,14 @@ NOKPROBE_SYMBOL(synthesize_relcall); * Returns non-zero if INSN is boostable. * RIP relative instructions are adjusted at copying time in 64 bits mode */ -int can_boost(struct insn *insn, void *addr) +bool can_boost(struct insn *insn, void *addr) { kprobe_opcode_t opcode; insn_byte_t prefix; int i; if (search_exception_tables((unsigned long)addr)) - return 0; /* Page fault may occur on this address. */ + return false; /* Page fault may occur on this address. */ /* 2nd-byte opcode */ if (insn->opcode.nbytes == 2) @@ -152,7 +152,7 @@ int can_boost(struct insn *insn, void *addr) (unsigned long *)twobyte_is_boostable); if (insn->opcode.nbytes != 1) - return 0; + return false; for_each_insn_prefix(insn, i, prefix) { insn_attr_t attr; @@ -160,7 +160,7 @@ int can_boost(struct insn *insn, void *addr) attr = inat_get_opcode_attribute(prefix); /* Can't boost Address-size override prefix and CS override prefix */ if (prefix == 0x2e || inat_is_address_size_prefix(attr)) - return 0; + return false; } opcode = insn->opcode.bytes[0]; @@ -169,24 +169,35 @@ int can_boost(struct insn *insn, void *addr) case 0x62: /* bound */ case 0x70 ... 0x7f: /* Conditional jumps */ case 0x9a: /* Call far */ - case 0xc0 ... 0xc1: /* Grp2 */ case 0xcc ... 0xce: /* software exceptions */ - case 0xd0 ... 0xd3: /* Grp2 */ case 0xd6: /* (UD) */ case 0xd8 ... 0xdf: /* ESC */ case 0xe0 ... 0xe3: /* LOOP*, JCXZ */ case 0xe8 ... 0xe9: /* near Call, JMP */ case 0xeb: /* Short JMP */ case 0xf0 ... 0xf4: /* LOCK/REP, HLT */ + /* ... are not boostable */ + return false; + case 0xc0 ... 0xc1: /* Grp2 */ + case 0xd0 ... 0xd3: /* Grp2 */ + /* + * AMD uses nnn == 110 as SHL/SAL, but Intel makes it reserved. + */ + return X86_MODRM_REG(insn->modrm.bytes[0]) != 0b110; case 0xf6 ... 0xf7: /* Grp3 */ + /* AMD uses nnn == 001 as TEST, but Intel makes it reserved. */ + return X86_MODRM_REG(insn->modrm.bytes[0]) != 0b001; case 0xfe: /* Grp4 */ - /* ... are not boostable */ - return 0; + /* Only INC and DEC are boostable */ + return X86_MODRM_REG(insn->modrm.bytes[0]) == 0b000 || + X86_MODRM_REG(insn->modrm.bytes[0]) == 0b001; case 0xff: /* Grp5 */ - /* Only indirect jmp is boostable */ - return X86_MODRM_REG(insn->modrm.bytes[0]) == 4; + /* Only INC, DEC, and indirect JMP are boostable */ + return X86_MODRM_REG(insn->modrm.bytes[0]) == 0b000 || + X86_MODRM_REG(insn->modrm.bytes[0]) == 0b001 || + X86_MODRM_REG(insn->modrm.bytes[0]) == 0b100; default: - return 1; + return true; } } @@ -252,21 +263,40 @@ unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long add return __recover_probed_insn(buf, addr); } -/* Check if paddr is at an instruction boundary */ -static int can_probe(unsigned long paddr) +/* Check if insn is INT or UD */ +static inline bool is_exception_insn(struct insn *insn) +{ + /* UD uses 0f escape */ + if (insn->opcode.bytes[0] == 0x0f) { + /* UD0 / UD1 / UD2 */ + return insn->opcode.bytes[1] == 0xff || + insn->opcode.bytes[1] == 0xb9 || + insn->opcode.bytes[1] == 0x0b; + } + + /* INT3 / INT n / INTO / INT1 */ + return insn->opcode.bytes[0] == 0xcc || + insn->opcode.bytes[0] == 0xcd || + insn->opcode.bytes[0] == 0xce || + insn->opcode.bytes[0] == 0xf1; +} + +/* + * Check if paddr is at an instruction boundary and that instruction can + * be probed + */ +static bool can_probe(unsigned long paddr) { unsigned long addr, __addr, offset = 0; struct insn insn; kprobe_opcode_t buf[MAX_INSN_SIZE]; if (!kallsyms_lookup_size_offset(paddr, NULL, &offset)) - return 0; + return false; /* Decode instructions */ addr = paddr - offset; while (addr < paddr) { - int ret; - /* * Check if the instruction has been modified by another * kprobe, in which case we replace the breakpoint by the @@ -277,11 +307,10 @@ static int can_probe(unsigned long paddr) */ __addr = recover_probed_instruction(buf, addr); if (!__addr) - return 0; + return false; - ret = insn_decode_kernel(&insn, (void *)__addr); - if (ret < 0) - return 0; + if (insn_decode_kernel(&insn, (void *)__addr) < 0) + return false; #ifdef CONFIG_KGDB /* @@ -290,10 +319,26 @@ static int can_probe(unsigned long paddr) */ if (insn.opcode.bytes[0] == INT3_INSN_OPCODE && kgdb_has_hit_break(addr)) - return 0; + return false; #endif addr += insn.length; } + + /* Check if paddr is at an instruction boundary */ + if (addr != paddr) + return false; + + __addr = recover_probed_instruction(buf, addr); + if (!__addr) + return false; + + if (insn_decode_kernel(&insn, (void *)__addr) < 0) + return false; + + /* INT and UD are special and should not be kprobed */ + if (is_exception_insn(&insn)) + return false; + if (IS_ENABLED(CONFIG_CFI_CLANG)) { /* * The compiler generates the following instruction sequence @@ -308,13 +353,6 @@ static int can_probe(unsigned long paddr) * Also, these movl and addl are used for showing expected * type. So those must not be touched. */ - __addr = recover_probed_instruction(buf, addr); - if (!__addr) - return 0; - - if (insn_decode_kernel(&insn, (void *)__addr) < 0) - return 0; - if (insn.opcode.value == 0xBA) offset = 12; else if (insn.opcode.value == 0x3) @@ -324,11 +362,11 @@ static int can_probe(unsigned long paddr) /* This movl/addl is used for decoding CFI. */ if (is_cfi_trap(addr + offset)) - return 0; + return false; } out: - return (addr == paddr); + return true; } /* If x86 supports IBT (ENDBR) it must be skipped. */ diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c index dd2ec14adb..15af7e98e1 100644 --- a/arch/x86/kernel/kprobes/ftrace.c +++ b/arch/x86/kernel/kprobes/ftrace.c @@ -21,6 +21,9 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip, struct kprobe_ctlblk *kcb; int bit; + if (unlikely(kprobe_ftrace_disabled)) + return; + bit = ftrace_test_recursion_trylock(ip, parent_ip); if (bit < 0) return; diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c index 517821b483..36d6809c6c 100644 --- a/arch/x86/kernel/kprobes/opt.c +++ b/arch/x86/kernel/kprobes/opt.c @@ -324,7 +324,7 @@ static int can_optimize(unsigned long paddr) * However, the kernel built with retpolines or IBT has jump * tables disabled so the check can be skipped altogether. */ - if (!IS_ENABLED(CONFIG_RETPOLINE) && + if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && !IS_ENABLED(CONFIG_X86_KERNEL_IBT) && insn_is_indirect_jump(&insn)) return 0; diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 428ee74002..7f0732bc0c 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -65,6 +65,7 @@ static int __init parse_no_stealacc(char *arg) early_param("no-steal-acc", parse_no_stealacc); +static DEFINE_PER_CPU_READ_MOSTLY(bool, async_pf_enabled); static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64); DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64) __visible; static int has_steal_clock = 0; @@ -244,7 +245,7 @@ noinstr u32 kvm_read_and_reset_apf_flags(void) { u32 flags = 0; - if (__this_cpu_read(apf_reason.enabled)) { + if (__this_cpu_read(async_pf_enabled)) { flags = __this_cpu_read(apf_reason.flags); __this_cpu_write(apf_reason.flags, 0); } @@ -295,7 +296,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt) inc_irq_stat(irq_hv_callback_count); - if (__this_cpu_read(apf_reason.enabled)) { + if (__this_cpu_read(async_pf_enabled)) { token = __this_cpu_read(apf_reason.token); kvm_async_pf_task_wake(token); __this_cpu_write(apf_reason.token, 0); @@ -362,7 +363,7 @@ static void kvm_guest_cpu_init(void) wrmsrl(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR); wrmsrl(MSR_KVM_ASYNC_PF_EN, pa); - __this_cpu_write(apf_reason.enabled, 1); + __this_cpu_write(async_pf_enabled, true); pr_debug("setup async PF for cpu %d\n", smp_processor_id()); } @@ -383,11 +384,11 @@ static void kvm_guest_cpu_init(void) static void kvm_pv_disable_apf(void) { - if (!__this_cpu_read(apf_reason.enabled)) + if (!__this_cpu_read(async_pf_enabled)) return; wrmsrl(MSR_KVM_ASYNC_PF_EN, 0); - __this_cpu_write(apf_reason.enabled, 0); + __this_cpu_write(async_pf_enabled, false); pr_debug("disable async PF for cpu %d\n", smp_processor_id()); } @@ -770,7 +771,7 @@ static struct notifier_block kvm_pv_reboot_nb = { * won't be valid. In cases like kexec, in which you install a new kernel, this * means a random memory location will be kept being written. */ -#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_CRASH_DUMP static void kvm_crash_shutdown(struct pt_regs *regs) { kvm_guest_cpu_offline(true); @@ -830,7 +831,7 @@ static void __init kvm_guest_init(void) if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_INT) && kvmapf) { static_branch_enable(&kvm_async_pf_enabled); - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, asm_sysvec_kvm_asyncpf_interrupt); + sysvec_install(HYPERVISOR_CALLBACK_VECTOR, sysvec_kvm_asyncpf_interrupt); } #ifdef CONFIG_SMP @@ -853,7 +854,7 @@ static void __init kvm_guest_init(void) kvm_guest_cpu_init(); #endif -#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_CRASH_DUMP machine_ops.crash_shutdown = kvm_crash_shutdown; #endif diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index 5bb395551c..5b2c15214a 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -154,15 +154,15 @@ static int kvm_cs_enable(struct clocksource *cs) return 0; } -struct clocksource kvm_clock = { +static struct clocksource kvm_clock = { .name = "kvm-clock", .read = kvm_clock_get_cycles, .rating = 400, .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS, + .id = CSID_X86_KVM_CLK, .enable = kvm_cs_enable, }; -EXPORT_SYMBOL_GPL(kvm_clock); static void kvm_register_clock(char *txt) { diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 7a814b4140..0f19ef355f 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -184,7 +184,7 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries) return new_ldt; } -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void do_sanity_check(struct mm_struct *mm, bool had_kernel_mapping, @@ -377,7 +377,7 @@ static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) flush_tlb_mm_range(mm, va, va + nr_pages * PAGE_SIZE, PAGE_SHIFT, false); } -#else /* !CONFIG_PAGE_TABLE_ISOLATION */ +#else /* !CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static int map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) @@ -388,11 +388,11 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) static void unmap_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt) { } -#endif /* CONFIG_PAGE_TABLE_ISOLATION */ +#endif /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION */ static void free_ldt_pgtables(struct mm_struct *mm) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION struct mmu_gather tlb; unsigned long start = LDT_BASE_ADDR; unsigned long end = LDT_END_ADDR; diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index bc0a5348b4..cc0f7f70b1 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -295,8 +295,15 @@ void machine_kexec_cleanup(struct kimage *image) void machine_kexec(struct kimage *image) { unsigned long page_list[PAGES_NR]; - void *control_page; + unsigned int host_mem_enc_active; int save_ftrace_enabled; + void *control_page; + + /* + * This must be done before load_segments() since if call depth tracking + * is used then GS must be valid to make any function calls. + */ + host_mem_enc_active = cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -358,7 +365,7 @@ void machine_kexec(struct kimage *image) (unsigned long)page_list, image->start, image->preserve_context, - cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)); + host_mem_enc_active); #ifdef CONFIG_KEXEC_JUMP if (image->preserve_context) @@ -508,6 +515,8 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image) } #endif /* CONFIG_KEXEC_FILE */ +#ifdef CONFIG_CRASH_DUMP + static int kexec_mark_range(unsigned long start, unsigned long end, bool protect) { @@ -552,6 +561,7 @@ void arch_kexec_unprotect_crashkres(void) { kexec_mark_crashkres(false); } +#endif /* * During a traditional boot under SME, SME will encrypt the kernel, diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index b223922248..e89171b034 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -36,6 +36,8 @@ * Checksum an MP configuration block. */ +static unsigned int num_procs __initdata; + static int __init mpf_checksum(unsigned char *mp, int len) { int sum = 0; @@ -50,16 +52,15 @@ static void __init MP_processor_info(struct mpc_cpu *m) { char *bootup_cpu = ""; - if (!(m->cpuflag & CPU_ENABLED)) { - disabled_cpus++; + topology_register_apic(m->apicid, CPU_ACPIID_INVALID, m->cpuflag & CPU_ENABLED); + if (!(m->cpuflag & CPU_ENABLED)) return; - } if (m->cpuflag & CPU_BOOTPROCESSOR) bootup_cpu = " (Bootup-CPU)"; pr_info("Processor #%d%s\n", m->apicid, bootup_cpu); - generic_processor_info(m->apicid); + num_procs++; } #ifdef CONFIG_X86_IO_APIC @@ -196,12 +197,12 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) if (!smp_check_mpc(mpc, oem, str)) return 0; - /* Initialize the lapic mapping */ - if (!acpi_lapic) - register_lapic_address(mpc->lapic); - - if (early) + if (early) { + /* Initialize the lapic mapping */ + if (!acpi_lapic) + register_lapic_address(mpc->lapic); return 1; + } /* Now process the configuration blocks. */ while (count < mpc->length) { @@ -236,9 +237,9 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) } } - if (!num_processors) + if (!num_procs && !acpi_lapic) pr_err("MPTABLE: no processors registered!\n"); - return num_processors; + return num_procs || acpi_lapic; } #ifdef CONFIG_X86_IO_APIC @@ -473,7 +474,7 @@ static int __init check_physptr(struct mpf_intel *mpf, unsigned int early) /* * Scan the memory blocks for an SMP configuration block. */ -void __init default_get_smp_config(unsigned int early) +static __init void mpparse_get_smp_config(unsigned int early) { struct mpf_intel *mpf; @@ -529,8 +530,8 @@ void __init default_get_smp_config(unsigned int early) } else BUG(); - if (!early) - pr_info("Processors: %d\n", num_processors); + if (!early && !acpi_lapic) + pr_info("Processors: %d\n", num_procs); /* * Only use the first configuration found. */ @@ -538,6 +539,16 @@ out: early_memunmap(mpf, sizeof(*mpf)); } +void __init mpparse_parse_early_smp_config(void) +{ + mpparse_get_smp_config(true); +} + +void __init mpparse_parse_smp_config(void) +{ + mpparse_get_smp_config(false); +} + static void __init smp_reserve_memory(struct mpf_intel *mpf) { memblock_reserve(mpf->physptr, get_mpc_size(mpf->physptr)); @@ -587,7 +598,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length) return ret; } -void __init default_find_smp_config(void) +void __init mpparse_find_mptable(void) { unsigned int address; diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index 6da2cfa23c..ed163c8c86 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -35,6 +35,7 @@ #include <asm/nospec-branch.h> #include <asm/microcode.h> #include <asm/sev.h> +#include <asm/fred.h> #define CREATE_TRACE_POINTS #include <trace/events/nmi.h> @@ -303,13 +304,13 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs) __this_cpu_add(nmi_stats.unknown, 1); - pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", - reason, smp_processor_id()); + pr_emerg_ratelimited("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n", + reason, smp_processor_id()); if (unknown_nmi_panic || panic_on_unrecovered_nmi) nmi_panic(regs, "NMI: Not continuing"); - pr_emerg("Dazed and confused, but trying to continue\n"); + pr_emerg_ratelimited("Dazed and confused, but trying to continue\n"); } NOKPROBE_SYMBOL(unknown_nmi_error); @@ -502,7 +503,7 @@ DEFINE_IDTENTRY_RAW(exc_nmi) if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) raw_atomic_long_inc(&nsp->idt_calls); - if (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) { + if (arch_cpu_is_offline(smp_processor_id())) { if (microcode_nmi_handler_enabled()) microcode_offline_nmi_handler(); return; @@ -579,7 +580,7 @@ EXPORT_SYMBOL_GPL(asm_exc_nmi_kvm_vmx); static char *nmi_check_stall_msg[] = { /* */ -/* +--------- nsp->idt_seq_snap & 0x1: CPU is in NMI handler. */ +/* +--------- nmi_seq & 0x1: CPU is currently in NMI handler. */ /* | +------ cpu_is_offline(cpu) */ /* | | +--- nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls): */ /* | | | NMI handler has been invoked. */ @@ -627,27 +628,72 @@ void nmi_backtrace_stall_check(const struct cpumask *btp) nmi_seq = READ_ONCE(nsp->idt_nmi_seq); if (nsp->idt_nmi_seq_snap + 1 == nmi_seq && (nmi_seq & 0x1)) { msgp = "CPU entered NMI handler function, but has not exited"; - } else if ((nsp->idt_nmi_seq_snap & 0x1) != (nmi_seq & 0x1)) { - msgp = "CPU is handling NMIs"; - } else { - idx = ((nsp->idt_seq_snap & 0x1) << 2) | + } else if (nsp->idt_nmi_seq_snap == nmi_seq || + nsp->idt_nmi_seq_snap + 1 == nmi_seq) { + idx = ((nmi_seq & 0x1) << 2) | (cpu_is_offline(cpu) << 1) | (nsp->idt_calls_snap != atomic_long_read(&nsp->idt_calls)); msgp = nmi_check_stall_msg[idx]; if (nsp->idt_ignored_snap != READ_ONCE(nsp->idt_ignored) && (idx & 0x1)) modp = ", but OK because ignore_nmis was set"; - if (nmi_seq & 0x1) - msghp = " (CPU currently in NMI handler function)"; - else if (nsp->idt_nmi_seq_snap + 1 == nmi_seq) + if (nsp->idt_nmi_seq_snap + 1 == nmi_seq) msghp = " (CPU exited one NMI handler function)"; + else if (nmi_seq & 0x1) + msghp = " (CPU currently in NMI handler function)"; + else + msghp = " (CPU was never in an NMI handler function)"; + } else { + msgp = "CPU is handling NMIs"; } - pr_alert("%s: CPU %d: %s%s%s, last activity: %lu jiffies ago.\n", - __func__, cpu, msgp, modp, msghp, j - READ_ONCE(nsp->recv_jiffies)); + pr_alert("%s: CPU %d: %s%s%s\n", __func__, cpu, msgp, modp, msghp); + pr_alert("%s: last activity: %lu jiffies ago.\n", + __func__, j - READ_ONCE(nsp->recv_jiffies)); } } #endif +#ifdef CONFIG_X86_FRED +/* + * With FRED, CR2/DR6 is pushed to #PF/#DB stack frame during FRED + * event delivery, i.e., there is no problem of transient states. + * And NMI unblocking only happens when the stack frame indicates + * that so should happen. + * + * Thus, the NMI entry stub for FRED is really straightforward and + * as simple as most exception handlers. As such, #DB is allowed + * during NMI handling. + */ +DEFINE_FREDENTRY_NMI(exc_nmi) +{ + irqentry_state_t irq_state; + + if (arch_cpu_is_offline(smp_processor_id())) { + if (microcode_nmi_handler_enabled()) + microcode_offline_nmi_handler(); + return; + } + + /* + * Save CR2 for eventual restore to cover the case where the NMI + * hits the VMENTER/VMEXIT region where guest CR2 is life. This + * prevents guest state corruption in case that the NMI handler + * takes a page fault. + */ + this_cpu_write(nmi_cr2, read_cr2()); + + irq_state = irqentry_nmi_enter(regs); + + inc_irq_stat(__nmi_count); + default_do_nmi(regs); + + irqentry_nmi_exit(regs, irq_state); + + if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) + write_cr2(this_cpu_read(nmi_cr2)); +} +#endif + void stop_nmi(void) { ignore_nmis++; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ab49ade31b..b8441147eb 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -846,31 +846,6 @@ void __noreturn stop_this_cpu(void *dummy) } /* - * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power - * states (local apic timer and TSC stop). - * - * XXX this function is completely buggered vs RCU and tracing. - */ -static void amd_e400_idle(void) -{ - /* - * We cannot use static_cpu_has_bug() here because X86_BUG_AMD_APIC_C1E - * gets set after static_cpu_has() places have been converted via - * alternatives. - */ - if (!boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) { - default_idle(); - return; - } - - tick_broadcast_enter(); - - default_idle(); - - tick_broadcast_exit(); -} - -/* * Prefer MWAIT over HALT if MWAIT is supported, MWAIT_CPUID leaf * exists and whenever MONITOR/MWAIT extensions are present there is at * least one C1 substate. @@ -878,21 +853,22 @@ static void amd_e400_idle(void) * Do not prefer MWAIT if MONITOR instruction has a bug or idle=nomwait * is passed to kernel commandline parameter. */ -static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) +static __init bool prefer_mwait_c1_over_halt(void) { + const struct cpuinfo_x86 *c = &boot_cpu_data; u32 eax, ebx, ecx, edx; - /* User has disallowed the use of MWAIT. Fallback to HALT */ - if (boot_option_idle_override == IDLE_NOMWAIT) - return 0; + /* If override is enforced on the command line, fall back to HALT. */ + if (boot_option_idle_override != IDLE_NO_OVERRIDE) + return false; /* MWAIT is not supported on this platform. Fallback to HALT */ if (!cpu_has(c, X86_FEATURE_MWAIT)) - return 0; + return false; - /* Monitor has a bug. Fallback to HALT */ - if (boot_cpu_has_bug(X86_BUG_MONITOR)) - return 0; + /* Monitor has a bug or APIC stops in C1E. Fallback to HALT */ + if (boot_cpu_has_bug(X86_BUG_MONITOR) || boot_cpu_has_bug(X86_BUG_AMD_APIC_C1E)) + return false; cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx); @@ -901,13 +877,13 @@ static int prefer_mwait_c1_over_halt(const struct cpuinfo_x86 *c) * with EAX=0, ECX=0. */ if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) - return 1; + return true; /* * If MWAIT extensions are available, there should be at least one * MWAIT C1 substate present. */ - return (edx & MWAIT_C1_SUBSTATE_MASK); + return !!(edx & MWAIT_C1_SUBSTATE_MASK); } /* @@ -933,26 +909,27 @@ static __cpuidle void mwait_idle(void) __current_clr_polling(); } -void select_idle_routine(const struct cpuinfo_x86 *c) +void __init select_idle_routine(void) { -#ifdef CONFIG_SMP - if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1) - pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); -#endif - if (x86_idle_set() || boot_option_idle_override == IDLE_POLL) + if (boot_option_idle_override == IDLE_POLL) { + if (IS_ENABLED(CONFIG_SMP) && __max_threads_per_core > 1) + pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); + return; + } + + /* Required to guard against xen_set_default_idle() */ + if (x86_idle_set()) return; - if (boot_cpu_has_bug(X86_BUG_AMD_E400)) { - pr_info("using AMD E400 aware idle routine\n"); - static_call_update(x86_idle, amd_e400_idle); - } else if (prefer_mwait_c1_over_halt(c)) { + if (prefer_mwait_c1_over_halt()) { pr_info("using mwait in idle threads\n"); static_call_update(x86_idle, mwait_idle); } else if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { pr_info("using TDX aware idle routine\n"); static_call_update(x86_idle, tdx_safe_halt); - } else + } else { static_call_update(x86_idle, default_idle); + } } void amd_e400_c1e_apic_setup(void) @@ -985,7 +962,10 @@ void __init arch_post_acpi_subsys_init(void) if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC)) mark_tsc_unstable("TSC halt in AMD C1E"); - pr_info("System has AMD C1E enabled\n"); + + if (IS_ENABLED(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST_IDLE)) + static_branch_enable(&arch_needs_tick_broadcast); + pr_info("System has AMD C1E erratum E400. Workaround enabled.\n"); } static int __init idle_setup(char *str) @@ -998,24 +978,14 @@ static int __init idle_setup(char *str) boot_option_idle_override = IDLE_POLL; cpu_idle_poll_ctrl(true); } else if (!strcmp(str, "halt")) { - /* - * When the boot option of idle=halt is added, halt is - * forced to be used for CPU idle. In such case CPU C2/C3 - * won't be used again. - * To continue to load the CPU idle driver, don't touch - * the boot_option_idle_override. - */ - static_call_update(x86_idle, default_idle); + /* 'idle=halt' HALT for idle. C-states are disabled. */ boot_option_idle_override = IDLE_HALT; } else if (!strcmp(str, "nomwait")) { - /* - * If the boot option of "idle=nomwait" is added, - * it means that mwait will be disabled for CPU C1/C2/C3 - * states. - */ + /* 'idle=nomwait' disables MWAIT for idle */ boot_option_idle_override = IDLE_NOMWAIT; - } else - return -1; + } else { + return -EINVAL; + } return 0; } @@ -1030,7 +1000,10 @@ unsigned long arch_align_stack(unsigned long sp) unsigned long arch_randomize_brk(struct mm_struct *mm) { - return randomize_page(mm->brk, 0x02000000); + if (mmap_is_ia32()) + return randomize_page(mm->brk, SZ_32M); + + return randomize_page(mm->brk, SZ_1G); } /* diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 708c87b88c..0917c7f257 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -156,13 +156,12 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread, *next = &next_p->thread; - struct fpu *prev_fpu = &prev->fpu; int cpu = smp_processor_id(); /* never put a printk in __switch_to... printk() calls wake_up*() indirectly */ - if (!test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_prepare(prev_fpu, cpu); + if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD)) + switch_fpu_prepare(prev_p, cpu); /* * Save away %gs. No need to save %fs, as it was saved on the @@ -209,7 +208,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) raw_cpu_write(pcpu_hot.current_task, next_p); - switch_fpu_finish(); + switch_fpu_finish(next_p); /* Load the Intel cache allocation PQR MSR. */ resctrl_sched_in(next_p); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 4989095ab7..6d3d20e3e4 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -56,6 +56,7 @@ #include <asm/resctrl.h> #include <asm/unistd.h> #include <asm/fsgsbase.h> +#include <asm/fred.h> #ifdef CONFIG_IA32_EMULATION /* Not included via unistd.h */ #include <asm/unistd_32_ia32.h> @@ -117,7 +118,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, printk("%sFS: %016lx(%04x) GS:%016lx(%04x) knlGS:%016lx\n", log_lvl, fs, fsindex, gs, gsindex, shadowgs); - printk("%sCS: %04lx DS: %04x ES: %04x CR0: %016lx\n", + printk("%sCS: %04x DS: %04x ES: %04x CR0: %016lx\n", log_lvl, regs->cs, ds, es, cr0); printk("%sCR2: %016lx CR3: %016lx CR4: %016lx\n", log_lvl, cr2, cr3, cr4); @@ -166,7 +167,29 @@ static noinstr unsigned long __rdgsbase_inactive(void) lockdep_assert_irqs_disabled(); - if (!cpu_feature_enabled(X86_FEATURE_XENPV)) { + /* + * SWAPGS is no longer needed thus NOT allowed with FRED because + * FRED transitions ensure that an operating system can _always_ + * operate with its own GS base address: + * - For events that occur in ring 3, FRED event delivery swaps + * the GS base address with the IA32_KERNEL_GS_BASE MSR. + * - ERETU (the FRED transition that returns to ring 3) also swaps + * the GS base address with the IA32_KERNEL_GS_BASE MSR. + * + * And the operating system can still setup the GS segment for a + * user thread without the need of loading a user thread GS with: + * - Using LKGS, available with FRED, to modify other attributes + * of the GS segment without compromising its ability always to + * operate with its own GS base address. + * - Accessing the GS segment base address for a user thread as + * before using RDMSR or WRMSR on the IA32_KERNEL_GS_BASE MSR. + * + * Note, LKGS loads the GS base address into the IA32_KERNEL_GS_BASE + * MSR instead of the GS segment’s descriptor cache. As such, the + * operating system never changes its runtime GS base address. + */ + if (!cpu_feature_enabled(X86_FEATURE_FRED) && + !cpu_feature_enabled(X86_FEATURE_XENPV)) { native_swapgs(); gsbase = rdgsbase(); native_swapgs(); @@ -191,7 +214,8 @@ static noinstr void __wrgsbase_inactive(unsigned long gsbase) { lockdep_assert_irqs_disabled(); - if (!cpu_feature_enabled(X86_FEATURE_XENPV)) { + if (!cpu_feature_enabled(X86_FEATURE_FRED) && + !cpu_feature_enabled(X86_FEATURE_XENPV)) { native_swapgs(); wrgsbase(gsbase); native_swapgs(); @@ -505,7 +529,7 @@ void x86_gsbase_write_task(struct task_struct *task, unsigned long gsbase) static void start_thread_common(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp, - unsigned int _cs, unsigned int _ss, unsigned int _ds) + u16 _cs, u16 _ss, u16 _ds) { WARN_ON_ONCE(regs != current_pt_regs()); @@ -522,11 +546,36 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip, loadsegment(ds, _ds); load_gs_index(0); - regs->ip = new_ip; - regs->sp = new_sp; - regs->cs = _cs; - regs->ss = _ss; - regs->flags = X86_EFLAGS_IF; + regs->ip = new_ip; + regs->sp = new_sp; + regs->csx = _cs; + regs->ssx = _ss; + /* + * Allow single-step trap and NMI when starting a new task, thus + * once the new task enters user space, single-step trap and NMI + * are both enabled immediately. + * + * Entering a new task is logically speaking a return from a + * system call (exec, fork, clone, etc.). As such, if ptrace + * enables single stepping a single step exception should be + * allowed to trigger immediately upon entering user space. + * This is not optional. + * + * NMI should *never* be disabled in user space. As such, this + * is an optional, opportunistic way to catch errors. + * + * Paranoia: High-order 48 bits above the lowest 16 bit SS are + * discarded by the legacy IRET instruction on all Intel, AMD, + * and Cyrix/Centaur/VIA CPUs, thus can be set unconditionally, + * even when FRED is not enabled. But we choose the safer side + * to use these bits only when FRED is enabled. + */ + if (cpu_feature_enabled(X86_FEATURE_FRED)) { + regs->fred_ss.swevent = true; + regs->fred_ss.nmi = true; + } + + regs->flags = X86_EFLAGS_IF | X86_EFLAGS_FIXED; } void @@ -562,14 +611,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p) { struct thread_struct *prev = &prev_p->thread; struct thread_struct *next = &next_p->thread; - struct fpu *prev_fpu = &prev->fpu; int cpu = smp_processor_id(); WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) && this_cpu_read(pcpu_hot.hardirq_stack_inuse)); - if (!test_thread_flag(TIF_NEED_FPU_LOAD)) - switch_fpu_prepare(prev_fpu, cpu); + if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD)) + switch_fpu_prepare(prev_p, cpu); /* We must save %fs and %gs before load_TLS() because * %fs and %gs may be cleared by load_TLS(). @@ -623,7 +671,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *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(); + switch_fpu_finish(next_p); /* Reload sp0. */ update_task_stack(next_p); diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index 830425e6d3..f3130f7627 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -796,7 +796,7 @@ struct machine_ops machine_ops __ro_after_init = { .emergency_restart = native_machine_emergency_restart, .restart = native_machine_restart, .halt = native_machine_halt, -#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_CRASH_DUMP .crash_shutdown = native_machine_crash_shutdown, #endif }; @@ -826,7 +826,7 @@ void machine_halt(void) machine_ops.halt(); } -#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_CRASH_DUMP void machine_crash_shutdown(struct pt_regs *regs) { machine_ops.crash_shutdown(regs); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 3998109195..e125e059e2 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -471,7 +471,7 @@ static void __init arch_reserve_crashkernel(void) bool high = false; int ret; - if (!IS_ENABLED(CONFIG_KEXEC_CORE)) + if (!IS_ENABLED(CONFIG_CRASH_RESERVE)) return; ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), @@ -970,10 +970,8 @@ void __init setup_arch(char **cmdline_p) high_memory = (void *)__va(max_pfn * PAGE_SIZE - 1) + 1; #endif - /* - * Find and reserve possible boot-time SMP configuration: - */ - find_smp_config(); + /* Find and reserve MPTABLE area */ + x86_init.mpparse.find_mptable(); early_alloc_pgt_buf(); @@ -1091,7 +1089,9 @@ void __init setup_arch(char **cmdline_p) early_platform_quirks(); + /* Some platforms need the APIC registered for NUMA configuration */ early_acpi_boot_init(); + x86_init.mpparse.early_parse_smp_cfg(); x86_flattree_get_config(); @@ -1132,24 +1132,19 @@ void __init setup_arch(char **cmdline_p) early_quirks(); - /* - * Read APIC and some other early information from ACPI tables. - */ - acpi_boot_init(); - x86_dtb_init(); + topology_apply_cmdline_limits_early(); /* - * get boot-time SMP configuration: + * Parse SMP configuration. Try ACPI first and then the platform + * specific parser. */ - get_smp_config(); + acpi_boot_init(); + x86_init.mpparse.parse_smp_cfg(); - /* - * Systems w/o ACPI and mptables might not have it mapped the local - * APIC yet, but prefill_possible_map() might need to access it. - */ + /* Last opportunity to detect and map the local APIC */ init_apic_mappings(); - prefill_possible_map(); + topology_init_possible_cpus(); init_cpu_to_node(); init_gi_nodes(); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index be2fa2fc02..b4f8fa0f72 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -9,12 +9,18 @@ * and is included directly into both code-bases. */ +#include <asm/setup_data.h> + #ifndef __BOOT_COMPRESSED -#define error(v) pr_err(v) -#define has_cpuflag(f) boot_cpu_has(f) +#define error(v) pr_err(v) +#define has_cpuflag(f) boot_cpu_has(f) +#define sev_printk(fmt, ...) printk(fmt, ##__VA_ARGS__) +#define sev_printk_rtl(fmt, ...) printk_ratelimited(fmt, ##__VA_ARGS__) #else #undef WARN #define WARN(condition, format...) (!!(condition)) +#define sev_printk(fmt, ...) +#define sev_printk_rtl(fmt, ...) #endif /* I/O parameters for CPUID-related helpers */ @@ -570,6 +576,7 @@ void __head do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) { unsigned int subfn = lower_bits(regs->cx, 32); unsigned int fn = lower_bits(regs->ax, 32); + u16 opcode = *(unsigned short *)regs->ip; struct cpuid_leaf leaf; int ret; @@ -577,6 +584,10 @@ void __head do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) if (exit_code != SVM_EXIT_CPUID) goto fail; + /* Is it really a CPUID insn? */ + if (opcode != 0xa20f) + goto fail; + leaf.fn = fn; leaf.subfn = subfn; @@ -1167,3 +1178,94 @@ static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc) out: return ret; } + +static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt, + unsigned long exit_code) +{ + unsigned int opcode = (unsigned int)ctxt->insn.opcode.value; + u8 modrm = ctxt->insn.modrm.value; + + switch (exit_code) { + + case SVM_EXIT_IOIO: + case SVM_EXIT_NPF: + /* handled separately */ + return ES_OK; + + case SVM_EXIT_CPUID: + if (opcode == 0xa20f) + return ES_OK; + break; + + case SVM_EXIT_INVD: + if (opcode == 0x080f) + return ES_OK; + break; + + case SVM_EXIT_MONITOR: + /* MONITOR and MONITORX instructions generate the same error code */ + if (opcode == 0x010f && (modrm == 0xc8 || modrm == 0xfa)) + return ES_OK; + break; + + case SVM_EXIT_MWAIT: + /* MWAIT and MWAITX instructions generate the same error code */ + if (opcode == 0x010f && (modrm == 0xc9 || modrm == 0xfb)) + return ES_OK; + break; + + case SVM_EXIT_MSR: + /* RDMSR */ + if (opcode == 0x320f || + /* WRMSR */ + opcode == 0x300f) + return ES_OK; + break; + + case SVM_EXIT_RDPMC: + if (opcode == 0x330f) + return ES_OK; + break; + + case SVM_EXIT_RDTSC: + if (opcode == 0x310f) + return ES_OK; + break; + + case SVM_EXIT_RDTSCP: + if (opcode == 0x010f && modrm == 0xf9) + return ES_OK; + break; + + case SVM_EXIT_READ_DR7: + if (opcode == 0x210f && + X86_MODRM_REG(ctxt->insn.modrm.value) == 7) + return ES_OK; + break; + + case SVM_EXIT_VMMCALL: + if (opcode == 0x010f && modrm == 0xd9) + return ES_OK; + + break; + + case SVM_EXIT_WRITE_DR7: + if (opcode == 0x230f && + X86_MODRM_REG(ctxt->insn.modrm.value) == 7) + return ES_OK; + break; + + case SVM_EXIT_WBINVD: + if (opcode == 0x90f) + return ES_OK; + break; + + default: + break; + } + + sev_printk(KERN_ERR "Wrong/unhandled opcode bytes: 0x%x, exit_code: 0x%lx, rIP: 0x%lx\n", + opcode, exit_code, ctxt->regs->ip); + + return ES_UNSUPPORTED; +} diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index eb2873b5eb..38ad066179 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -61,6 +61,25 @@ #define AP_INIT_CR0_DEFAULT 0x60000010 #define AP_INIT_MXCSR_DEFAULT 0x1f80 +static const char * const sev_status_feat_names[] = { + [MSR_AMD64_SEV_ENABLED_BIT] = "SEV", + [MSR_AMD64_SEV_ES_ENABLED_BIT] = "SEV-ES", + [MSR_AMD64_SEV_SNP_ENABLED_BIT] = "SEV-SNP", + [MSR_AMD64_SNP_VTOM_BIT] = "vTom", + [MSR_AMD64_SNP_REFLECT_VC_BIT] = "ReflectVC", + [MSR_AMD64_SNP_RESTRICTED_INJ_BIT] = "RI", + [MSR_AMD64_SNP_ALT_INJ_BIT] = "AI", + [MSR_AMD64_SNP_DEBUG_SWAP_BIT] = "DebugSwap", + [MSR_AMD64_SNP_PREVENT_HOST_IBS_BIT] = "NoHostIBS", + [MSR_AMD64_SNP_BTB_ISOLATION_BIT] = "BTBIsol", + [MSR_AMD64_SNP_VMPL_SSS_BIT] = "VmplSSS", + [MSR_AMD64_SNP_SECURE_TSC_BIT] = "SecureTSC", + [MSR_AMD64_SNP_VMGEXIT_PARAM_BIT] = "VMGExitParam", + [MSR_AMD64_SNP_IBS_VIRT_BIT] = "IBSVirt", + [MSR_AMD64_SNP_VMSA_REG_PROT_BIT] = "VMSARegProt", + [MSR_AMD64_SNP_SMT_PROT_BIT] = "SMTProt", +}; + /* For early boot hypervisor communication in SEV-ES enabled guests */ static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE); @@ -1740,7 +1759,10 @@ static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt, struct ghcb *ghcb, unsigned long exit_code) { - enum es_result result; + enum es_result result = vc_check_opcode_bytes(ctxt, exit_code); + + if (result != ES_OK) + return result; switch (exit_code) { case SVM_EXIT_READ_DR7: @@ -2261,3 +2283,19 @@ static int __init snp_init_platform_device(void) return 0; } device_initcall(snp_init_platform_device); + +void sev_show_status(void) +{ + int i; + + pr_info("Status: "); + for (i = 0; i < MSR_AMD64_SNP_RESV_BIT; i++) { + if (sev_status & BIT_ULL(i)) { + if (!sev_status_feat_names[i]) + continue; + + pr_cont("%s ", sev_status_feat_names[i]); + } + } + pr_cont("\n"); +} diff --git a/arch/x86/kernel/sev_verify_cbit.S b/arch/x86/kernel/sev_verify_cbit.S index 3355e27c69..1ab65f6c6a 100644 --- a/arch/x86/kernel/sev_verify_cbit.S +++ b/arch/x86/kernel/sev_verify_cbit.S @@ -77,7 +77,7 @@ SYM_FUNC_START(sev_verify_cbit) * The check failed, prevent any forward progress to prevent ROP * attacks, invalidate the stack and go into a hlt loop. */ - xorq %rsp, %rsp + xorl %esp, %esp subq $0x1000, %rsp 2: hlt jmp 2b diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 96a771f9f9..18266cc3d9 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -148,14 +148,16 @@ static int register_stop_handler(void) static void native_stop_other_cpus(int wait) { - unsigned int cpu = smp_processor_id(); + unsigned int old_cpu, this_cpu; unsigned long flags, timeout; if (reboot_force) return; /* Only proceed if this is the first CPU to reach this code */ - if (atomic_cmpxchg(&stopping_cpu, -1, cpu) != -1) + old_cpu = -1; + this_cpu = smp_processor_id(); + if (!atomic_try_cmpxchg(&stopping_cpu, &old_cpu, this_cpu)) return; /* For kexec, ensure that offline CPUs are out of MWAIT and in HLT */ @@ -186,7 +188,7 @@ static void native_stop_other_cpus(int wait) * NMIs. */ cpumask_copy(&cpus_stop_mask, cpu_online_mask); - cpumask_clear_cpu(cpu, &cpus_stop_mask); + cpumask_clear_cpu(this_cpu, &cpus_stop_mask); if (!cpumask_empty(&cpus_stop_mask)) { apic_send_IPI_allbutself(REBOOT_VECTOR); @@ -210,6 +212,8 @@ static void native_stop_other_cpus(int wait) * CPUs to stop. */ if (!smp_no_nmi_ipi && !register_stop_handler()) { + unsigned int cpu; + pr_emerg("Shutting down cpus with NMI\n"); for_each_cpu(cpu, &cpus_stop_mask) @@ -282,7 +286,7 @@ struct smp_ops smp_ops = { .smp_cpus_done = native_smp_cpus_done, .stop_other_cpus = native_stop_other_cpus, -#if defined(CONFIG_KEXEC_CORE) +#if defined(CONFIG_CRASH_DUMP) .crash_stop_other_cpus = kdump_nmi_shootdown_cpus, #endif .smp_send_reschedule = native_smp_send_reschedule, diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 3f57ce68a3..76bb65045c 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -101,10 +101,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_core_map); DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map); EXPORT_PER_CPU_SYMBOL(cpu_die_map); -/* Per CPU bogomips and other parameters */ -DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info); -EXPORT_PER_CPU_SYMBOL(cpu_info); - /* CPUs which are the primary SMT threads */ struct cpumask __cpu_primary_thread_mask __read_mostly; @@ -125,25 +121,6 @@ struct mwait_cpu_dead { */ static DEFINE_PER_CPU_ALIGNED(struct mwait_cpu_dead, mwait_cpu_dead); -/* Logical package management. */ -struct logical_maps { - u32 phys_pkg_id; - u32 phys_die_id; - u32 logical_pkg_id; - u32 logical_die_id; -}; - -/* Temporary workaround until the full topology mechanics is in place */ -static DEFINE_PER_CPU_READ_MOSTLY(struct logical_maps, logical_maps) = { - .phys_pkg_id = U32_MAX, - .phys_die_id = U32_MAX, -}; - -unsigned int __max_logical_packages __read_mostly; -EXPORT_SYMBOL(__max_logical_packages); -static unsigned int logical_packages __read_mostly; -static unsigned int logical_die __read_mostly; - /* Maximum number of SMT threads on any online core */ int __read_mostly __max_smt_threads = 1; @@ -336,106 +313,6 @@ static void notrace start_secondary(void *unused) cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); } -/** - * topology_phys_to_logical_pkg - Map a physical package id to a logical - * @phys_pkg: The physical package id to map - * - * Returns logical package id or -1 if not found - */ -int topology_phys_to_logical_pkg(unsigned int phys_pkg) -{ - int cpu; - - for_each_possible_cpu(cpu) { - if (per_cpu(logical_maps.phys_pkg_id, cpu) == phys_pkg) - return per_cpu(logical_maps.logical_pkg_id, cpu); - } - return -1; -} -EXPORT_SYMBOL(topology_phys_to_logical_pkg); - -/** - * topology_phys_to_logical_die - Map a physical die id to logical - * @die_id: The physical die id to map - * @cur_cpu: The CPU for which the mapping is done - * - * Returns logical die id or -1 if not found - */ -static int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu) -{ - int cpu, proc_id = cpu_data(cur_cpu).topo.pkg_id; - - for_each_possible_cpu(cpu) { - if (per_cpu(logical_maps.phys_pkg_id, cpu) == proc_id && - per_cpu(logical_maps.phys_die_id, cpu) == die_id) - return per_cpu(logical_maps.logical_die_id, cpu); - } - return -1; -} - -/** - * topology_update_package_map - Update the physical to logical package map - * @pkg: The physical package id as retrieved via CPUID - * @cpu: The cpu for which this is updated - */ -int topology_update_package_map(unsigned int pkg, unsigned int cpu) -{ - int new; - - /* Already available somewhere? */ - new = topology_phys_to_logical_pkg(pkg); - if (new >= 0) - goto found; - - new = logical_packages++; - if (new != pkg) { - pr_info("CPU %u Converting physical %u to logical package %u\n", - cpu, pkg, new); - } -found: - per_cpu(logical_maps.phys_pkg_id, cpu) = pkg; - per_cpu(logical_maps.logical_pkg_id, cpu) = new; - cpu_data(cpu).topo.logical_pkg_id = new; - return 0; -} -/** - * topology_update_die_map - Update the physical to logical die map - * @die: The die id as retrieved via CPUID - * @cpu: The cpu for which this is updated - */ -int topology_update_die_map(unsigned int die, unsigned int cpu) -{ - int new; - - /* Already available somewhere? */ - new = topology_phys_to_logical_die(die, cpu); - if (new >= 0) - goto found; - - new = logical_die++; - if (new != die) { - pr_info("CPU %u Converting physical %u to logical die %u\n", - cpu, die, new); - } -found: - per_cpu(logical_maps.phys_die_id, cpu) = die; - per_cpu(logical_maps.logical_die_id, cpu) = new; - cpu_data(cpu).topo.logical_die_id = new; - return 0; -} - -static void __init smp_store_boot_cpu_info(void) -{ - int id = 0; /* CPU 0 */ - struct cpuinfo_x86 *c = &cpu_data(id); - - *c = boot_cpu_data; - c->cpu_index = id; - topology_update_package_map(c->topo.pkg_id, id); - topology_update_die_map(c->topo.die_id, id); - c->initialized = true; -} - /* * The bootstrap kernel entry code has set these up. Save them for * a given CPU @@ -488,6 +365,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) if (c->topo.pkg_id == o->topo.pkg_id && c->topo.die_id == o->topo.die_id && + c->topo.amd_node_id == o->topo.amd_node_id && per_cpu_llc_id(cpu1) == per_cpu_llc_id(cpu2)) { if (c->topo.core_id == o->topo.core_id) return topology_sane(c, o, "smt"); @@ -509,10 +387,13 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) static bool match_die(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (c->topo.pkg_id == o->topo.pkg_id && - c->topo.die_id == o->topo.die_id) - return true; - return false; + if (c->topo.pkg_id != o->topo.pkg_id || c->topo.die_id != o->topo.die_id) + return false; + + if (cpu_feature_enabled(X86_FEATURE_TOPOEXT) && topology_amd_nodes_per_pkg() > 1) + return c->topo.amd_node_id == o->topo.amd_node_id; + + return true; } static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) @@ -670,8 +551,8 @@ static void __init build_sched_topology(void) void set_cpu_sibling_map(int cpu) { - bool has_smt = smp_num_siblings > 1; - bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1; + bool has_smt = __max_threads_per_core > 1; + bool has_mp = has_smt || topology_num_cores_per_package() > 1; struct cpuinfo_x86 *c = &cpu_data(cpu); struct cpuinfo_x86 *o; int i, threads; @@ -1068,9 +949,13 @@ int native_kick_ap(unsigned int cpu, struct task_struct *tidle) pr_debug("++++++++++++++++++++=_---CPU UP %u\n", cpu); - if (apicid == BAD_APICID || !physid_isset(apicid, phys_cpu_present_map) || - !apic_id_valid(apicid)) { - pr_err("%s: bad cpu %d\n", __func__, cpu); + if (apicid == BAD_APICID || !apic_id_valid(apicid)) { + pr_err("CPU %u has invalid APIC ID %x. Aborting bringup\n", cpu, apicid); + return -EINVAL; + } + + if (!test_bit(apicid, phys_cpu_present_map)) { + pr_err("CPU %u APIC ID %x is not present. Aborting bringup\n", cpu, apicid); return -EINVAL; } @@ -1139,42 +1024,22 @@ static __init void disable_smp(void) pr_info("SMP disabled\n"); disable_ioapic_support(); + topology_reset_possible_cpus_up(); - init_cpu_present(cpumask_of(0)); - init_cpu_possible(cpumask_of(0)); - - if (smp_found_config) - physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map); - else - physid_set_mask_of_physid(0, &phys_cpu_present_map); cpumask_set_cpu(0, topology_sibling_cpumask(0)); cpumask_set_cpu(0, topology_core_cpumask(0)); cpumask_set_cpu(0, topology_die_cpumask(0)); } -static void __init smp_cpu_index_default(void) -{ - int i; - struct cpuinfo_x86 *c; - - for_each_possible_cpu(i) { - c = &cpu_data(i); - /* mark all to hotplug */ - c->cpu_index = nr_cpu_ids; - } -} - void __init smp_prepare_cpus_common(void) { unsigned int i; - smp_cpu_index_default(); - - /* - * Setup boot CPU information - */ - smp_store_boot_cpu_info(); /* Final full version of the data */ - mb(); + /* Mark all except the boot CPU as hotpluggable */ + for_each_possible_cpu(i) { + if (i) + per_cpu(cpu_info.cpu_index, i) = nr_cpu_ids; + } for_each_possible_cpu(i) { zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL); @@ -1187,6 +1052,11 @@ void __init smp_prepare_cpus_common(void) set_cpu_sibling_map(0); } +void __init smp_prepare_boot_cpu(void) +{ + smp_ops.smp_prepare_boot_cpu(); +} + #ifdef CONFIG_X86_64 /* Establish whether parallel bringup can be supported. */ bool __init arch_cpuhp_init_parallel_bringup(void) @@ -1265,102 +1135,16 @@ void __init native_smp_prepare_boot_cpu(void) native_pv_lock_init(); } -void __init calculate_max_logical_packages(void) -{ - int ncpus; - - /* - * Today neither Intel nor AMD support heterogeneous systems so - * extrapolate the boot cpu's data to all packages. - */ - ncpus = cpu_data(0).booted_cores * topology_max_smt_threads(); - __max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus); - pr_info("Max logical packages: %u\n", __max_logical_packages); -} - void __init native_smp_cpus_done(unsigned int max_cpus) { pr_debug("Boot done\n"); - calculate_max_logical_packages(); build_sched_topology(); nmi_selftest(); impress_friends(); cache_aps_init(); } -static int __initdata setup_possible_cpus = -1; -static int __init _setup_possible_cpus(char *str) -{ - get_option(&str, &setup_possible_cpus); - return 0; -} -early_param("possible_cpus", _setup_possible_cpus); - - -/* - * cpu_possible_mask should be static, it cannot change as cpu's - * are onlined, or offlined. The reason is per-cpu data-structures - * are allocated by some modules at init time, and don't expect to - * do this dynamically on cpu arrival/departure. - * cpu_present_mask on the other hand can change dynamically. - * In case when cpu_hotplug is not compiled, then we resort to current - * behaviour, which is cpu_possible == cpu_present. - * - Ashok Raj - * - * Three ways to find out the number of additional hotplug CPUs: - * - If the BIOS specified disabled CPUs in ACPI/mptables use that. - * - The user can overwrite it with possible_cpus=NUM - * - Otherwise don't reserve additional CPUs. - * We do this because additional CPUs waste a lot of memory. - * -AK - */ -__init void prefill_possible_map(void) -{ - int i, possible; - - i = setup_max_cpus ?: 1; - if (setup_possible_cpus == -1) { - possible = num_processors; -#ifdef CONFIG_HOTPLUG_CPU - if (setup_max_cpus) - possible += disabled_cpus; -#else - if (possible > i) - possible = i; -#endif - } else - possible = setup_possible_cpus; - - total_cpus = max_t(int, possible, num_processors + disabled_cpus); - - /* nr_cpu_ids could be reduced via nr_cpus= */ - if (possible > nr_cpu_ids) { - pr_warn("%d Processors exceeds NR_CPUS limit of %u\n", - possible, nr_cpu_ids); - possible = nr_cpu_ids; - } - -#ifdef CONFIG_HOTPLUG_CPU - if (!setup_max_cpus) -#endif - if (possible > i) { - pr_warn("%d Processors exceeds max_cpus limit of %u\n", - possible, setup_max_cpus); - possible = i; - } - - set_nr_cpu_ids(possible); - - pr_info("Allowing %d CPUs, %d hotplug CPUs\n", - possible, max_t(int, possible - num_processors, 0)); - - reset_cpu_possible_mask(); - - for (i = 0; i < possible; i++) - set_cpu_possible(i, true); -} - /* correctly size the local cpu masks */ void __init setup_cpu_local_masks(void) { diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c index 77a9316da4..4eefaac64c 100644 --- a/arch/x86/kernel/static_call.c +++ b/arch/x86/kernel/static_call.c @@ -172,7 +172,7 @@ void arch_static_call_transform(void *site, void *tramp, void *func, bool tail) } EXPORT_SYMBOL_GPL(arch_static_call_transform); -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK /* * This is called by apply_returns() to fix up static call trampolines, * specifically ARCH_DEFINE_STATIC_CALL_NULL_TRAMP which is recorded as diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c index 8e2b2552b5..3e2952679b 100644 --- a/arch/x86/kernel/step.c +++ b/arch/x86/kernel/step.c @@ -6,7 +6,9 @@ #include <linux/sched/task_stack.h> #include <linux/mm.h> #include <linux/ptrace.h> + #include <asm/desc.h> +#include <asm/debugreg.h> #include <asm/mmu_context.h> unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs) diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c index c783aeb37d..cb9fa1d5c6 100644 --- a/arch/x86/kernel/sys_x86_64.c +++ b/arch/x86/kernel/sys_x86_64.c @@ -52,13 +52,6 @@ static unsigned long get_align_bits(void) return va_align.bits & get_align_mask(); } -unsigned long align_vdso_addr(unsigned long addr) -{ - unsigned long align_mask = get_align_mask(); - addr = (addr + align_mask) & ~align_mask; - return addr | get_align_bits(); -} - static int __init control_va_addr_alignment(char *str) { /* guard against enabling this on other CPU families */ diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c3b2f863ac..4fa0b17e50 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -51,6 +51,7 @@ #include <asm/ftrace.h> #include <asm/traps.h> #include <asm/desc.h> +#include <asm/fred.h> #include <asm/fpu/api.h> #include <asm/cpu.h> #include <asm/cpu_entry_area.h> @@ -773,7 +774,7 @@ 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(pcpu_hot.top_of_stack) - 1; + struct pt_regs *regs = (struct pt_regs *)current_top_of_stack() - 1; if (regs != eregs) *regs = *eregs; return regs; @@ -791,7 +792,7 @@ 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(pcpu_hot.top_of_stack); + sp = current_top_of_stack(); goto sync; } @@ -935,8 +936,7 @@ static bool notify_debug(struct pt_regs *regs, unsigned long *dr6) return false; } -static __always_inline void exc_debug_kernel(struct pt_regs *regs, - unsigned long dr6) +static noinstr void exc_debug_kernel(struct pt_regs *regs, unsigned long dr6) { /* * Disable breakpoints during exception handling; recursive exceptions @@ -948,6 +948,11 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, * * Entry text is excluded for HW_BP_X and cpu_entry_area, which * includes the entry stack is excluded for everything. + * + * For FRED, nested #DB should just work fine. But when a watchpoint or + * breakpoint is set in the code path which is executed by #DB handler, + * it results in an endless recursion and stack overflow. Thus we stay + * with the IDT approach, i.e., save DR7 and disable #DB. */ unsigned long dr7 = local_db_save(); irqentry_state_t irq_state = irqentry_nmi_enter(regs); @@ -977,7 +982,8 @@ static __always_inline void exc_debug_kernel(struct pt_regs *regs, * Catch SYSENTER with TF set and clear DR_STEP. If this hit a * watchpoint at the same time then that will still be handled. */ - if ((dr6 & DR_STEP) && is_sysenter_singlestep(regs)) + if (!cpu_feature_enabled(X86_FEATURE_FRED) && + (dr6 & DR_STEP) && is_sysenter_singlestep(regs)) dr6 &= ~DR_STEP; /* @@ -1009,8 +1015,7 @@ out: local_db_restore(dr7); } -static __always_inline void exc_debug_user(struct pt_regs *regs, - unsigned long dr6) +static noinstr void exc_debug_user(struct pt_regs *regs, unsigned long dr6) { bool icebp; @@ -1094,6 +1099,34 @@ DEFINE_IDTENTRY_DEBUG_USER(exc_debug) { exc_debug_user(regs, debug_read_clear_dr6()); } + +#ifdef CONFIG_X86_FRED +/* + * When occurred on different ring level, i.e., from user or kernel + * context, #DB needs to be handled on different stack: User #DB on + * current task stack, while kernel #DB on a dedicated stack. + * + * This is exactly how FRED event delivery invokes an exception + * handler: ring 3 event on level 0 stack, i.e., current task stack; + * ring 0 event on the #DB dedicated stack specified in the + * IA32_FRED_STKLVLS MSR. So unlike IDT, the FRED debug exception + * entry stub doesn't do stack switch. + */ +DEFINE_FREDENTRY_DEBUG(exc_debug) +{ + /* + * FRED #DB stores DR6 on the stack in the format which + * debug_read_clear_dr6() returns for the IDT entry points. + */ + unsigned long dr6 = fred_event_data(regs); + + if (user_mode(regs)) + exc_debug_user(regs, dr6); + else + exc_debug_kernel(regs, dr6); +} +#endif /* CONFIG_X86_FRED */ + #else /* 32 bit does not have separate entry points. */ DEFINE_IDTENTRY_RAW(exc_debug) @@ -1369,8 +1402,34 @@ DEFINE_IDTENTRY_SW(iret_error) } #endif +/* Do not enable FRED by default yet. */ +static bool enable_fred __ro_after_init = false; + +#ifdef CONFIG_X86_FRED +static int __init fred_setup(char *str) +{ + if (!str) + return -EINVAL; + + if (!cpu_feature_enabled(X86_FEATURE_FRED)) + return 0; + + if (!strcmp(str, "on")) + enable_fred = true; + else if (!strcmp(str, "off")) + enable_fred = false; + else + pr_warn("invalid FRED option: 'fred=%s'\n", str); + return 0; +} +early_param("fred", fred_setup); +#endif + void __init trap_init(void) { + if (cpu_feature_enabled(X86_FEATURE_FRED) && !enable_fred) + setup_clear_cpu_cap(X86_FEATURE_FRED); + /* Init cpu_entry_area before IST entries are set up */ setup_cpu_entry_areas(); @@ -1379,7 +1438,10 @@ void __init trap_init(void) /* Initialize TSS before setting up traps so ISTs work */ cpu_init_exception_handling(); + /* Setup traps as cpu_init() might #GP */ - idt_setup_traps(); + if (!cpu_feature_enabled(X86_FEATURE_FRED)) + idt_setup_traps(); + cpu_init(); } diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 15f97c0abc..5a69a49acc 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -53,7 +53,7 @@ static int __read_mostly tsc_force_recalibrate; static u32 art_to_tsc_numerator; static u32 art_to_tsc_denominator; static u64 art_to_tsc_offset; -static struct clocksource *art_related_clocksource; +static bool have_art; struct cyc2ns { struct cyc2ns_data data[2]; /* 0 + 2*16 = 32 */ @@ -652,7 +652,7 @@ success: } /** - * native_calibrate_tsc + * native_calibrate_tsc - determine TSC frequency * Determine TSC frequency via CPUID, else return 0. */ unsigned long native_calibrate_tsc(void) @@ -1168,6 +1168,7 @@ static struct clocksource clocksource_tsc_early = { .mask = CLOCKSOURCE_MASK(64), .flags = CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_MUST_VERIFY, + .id = CSID_X86_TSC_EARLY, .vdso_clock_mode = VDSO_CLOCKMODE_TSC, .enable = tsc_cs_enable, .resume = tsc_resume, @@ -1190,6 +1191,7 @@ static struct clocksource clocksource_tsc = { CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_MUST_VERIFY | CLOCK_SOURCE_VERIFY_PERCPU, + .id = CSID_X86_TSC, .vdso_clock_mode = VDSO_CLOCKMODE_TSC, .enable = tsc_cs_enable, .resume = tsc_resume, @@ -1309,8 +1311,10 @@ struct system_counterval_t convert_art_to_tsc(u64 art) do_div(tmp, art_to_tsc_denominator); res += tmp + art_to_tsc_offset; - return (struct system_counterval_t) {.cs = art_related_clocksource, - .cycles = res}; + return (struct system_counterval_t) { + .cs_id = have_art ? CSID_X86_TSC : CSID_GENERIC, + .cycles = res, + }; } EXPORT_SYMBOL(convert_art_to_tsc); @@ -1327,12 +1331,10 @@ EXPORT_SYMBOL(convert_art_to_tsc); * that this flag is set before conversion to TSC is attempted. * * Return: - * struct system_counterval_t - system counter value with the pointer to the - * corresponding clocksource - * @cycles: System counter value - * @cs: Clocksource corresponding to system counter value. Used - * by timekeeping code to verify comparability of two cycle - * values. + * struct system_counterval_t - system counter value with the ID of the + * corresponding clocksource: + * cycles: System counter value + * cs_id: The clocksource ID for validating comparability */ struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns) @@ -1347,8 +1349,10 @@ struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns) do_div(tmp, USEC_PER_SEC); res += tmp; - return (struct system_counterval_t) { .cs = art_related_clocksource, - .cycles = res}; + return (struct system_counterval_t) { + .cs_id = have_art ? CSID_X86_TSC : CSID_GENERIC, + .cycles = res, + }; } EXPORT_SYMBOL(convert_art_ns_to_tsc); @@ -1357,7 +1361,7 @@ static void tsc_refine_calibration_work(struct work_struct *work); static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work); /** * tsc_refine_calibration_work - Further refine tsc freq calibration - * @work - ignored. + * @work: ignored. * * This functions uses delayed work over a period of a * second to further refine the TSC freq value. Since this is @@ -1455,7 +1459,7 @@ out: goto unreg; if (boot_cpu_has(X86_FEATURE_ART)) - art_related_clocksource = &clocksource_tsc; + have_art = true; clocksource_register_khz(&clocksource_tsc, tsc_khz); unreg: clocksource_unregister(&clocksource_tsc_early); @@ -1481,7 +1485,7 @@ static int __init init_tsc_clocksource(void) */ if (boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) { if (boot_cpu_has(X86_FEATURE_ART)) - art_related_clocksource = &clocksource_tsc; + have_art = true; clocksource_register_khz(&clocksource_tsc, tsc_khz); clocksource_unregister(&clocksource_tsc_early); diff --git a/arch/x86/kernel/crash_core_32.c b/arch/x86/kernel/vmcore_info_32.c index 8a89c109e2..5995a74928 100644 --- a/arch/x86/kernel/crash_core_32.c +++ b/arch/x86/kernel/vmcore_info_32.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only -#include <linux/crash_core.h> +#include <linux/vmcore_info.h> #include <linux/pgtable.h> #include <asm/setup.h> diff --git a/arch/x86/kernel/crash_core_64.c b/arch/x86/kernel/vmcore_info_64.c index 7d255f882a..0dec7d8687 100644 --- a/arch/x86/kernel/crash_core_64.c +++ b/arch/x86/kernel/vmcore_info_64.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only -#include <linux/crash_core.h> +#include <linux/vmcore_info.h> #include <linux/pgtable.h> #include <asm/setup.h> diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index a349dbfc6d..56451fd209 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -46,6 +46,7 @@ ENTRY(phys_startup_64) #endif jiffies = jiffies_64; +const_pcpu_hot = pcpu_hot; #if defined(CONFIG_X86_64) /* @@ -132,7 +133,7 @@ SECTIONS LOCK_TEXT KPROBES_TEXT SOFTIRQENTRY_TEXT -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE *(.text..__x86.indirect_thunk) *(.text..__x86.return_thunk) #endif @@ -142,7 +143,7 @@ SECTIONS *(.text..__x86.rethunk_untrain) ENTRY_TEXT -#ifdef CONFIG_CPU_SRSO +#ifdef CONFIG_MITIGATION_SRSO /* * See the comment above srso_alias_untrain_ret()'s * definition. @@ -267,7 +268,7 @@ SECTIONS } #endif -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* * List of instructions that call/jmp/jcc to retpoline thunks * __x86_indirect_thunk_*(). These instructions can be patched along @@ -504,11 +505,11 @@ INIT_PER_CPU(irq_stack_backing_store); "fixed_percpu_data is not at start of per-cpu area"); #endif -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY . = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned"); #endif -#ifdef CONFIG_CPU_SRSO +#ifdef CONFIG_MITIGATION_SRSO . = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); /* * GNU ld cannot do XOR until 2.41. diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index d3fc017705..73511332bb 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -127,25 +127,12 @@ static void __init vsmp_cap_cpus(void) #endif } -static u32 apicid_phys_pkg_id(u32 initial_apic_id, int index_msb) -{ - return read_apic_id() >> index_msb; -} - -static void vsmp_apic_post_init(void) -{ - /* need to update phys_pkg_id */ - apic->phys_pkg_id = apicid_phys_pkg_id; -} - void __init vsmp_init(void) { detect_vsmp_box(); if (!is_vsmp_box()) return; - x86_platform.apic_post_init = vsmp_apic_post_init; - vsmp_cap_cpus(); set_vsmp_ctl(); diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c index 3f0718b4a7..d5dc5a9263 100644 --- a/arch/x86/kernel/x86_init.c +++ b/arch/x86/kernel/x86_init.c @@ -72,8 +72,9 @@ struct x86_init_ops x86_init __initdata = { .mpparse = { .setup_ioapic_ids = x86_init_noop, - .find_smp_config = default_find_smp_config, - .get_smp_config = default_get_smp_config, + .find_mptable = mpparse_find_mptable, + .early_parse_smp_cfg = mpparse_parse_early_smp_config, + .parse_smp_cfg = mpparse_parse_smp_config, }, .irqs = { diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 65ed14b654..0ebdd088f2 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -7,7 +7,6 @@ source "virt/kvm/Kconfig" menuconfig VIRTUALIZATION bool "Virtualization" - depends on HAVE_KVM || X86 default y help Say Y here to get to see options for using your Linux host to run other @@ -20,7 +19,6 @@ if VIRTUALIZATION config KVM tristate "Kernel-based Virtual Machine (KVM) support" - depends on HAVE_KVM depends on HIGH_RES_TIMERS depends on X86_LOCAL_APIC select KVM_COMMON @@ -29,9 +27,9 @@ config KVM select HAVE_KVM_PFNCACHE select HAVE_KVM_DIRTY_RING_TSO select HAVE_KVM_DIRTY_RING_ACQ_REL - select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING + select HAVE_KVM_READONLY_MEM select KVM_ASYNC_PF select USER_RETURN_NOTIFIER select KVM_MMIO @@ -120,10 +118,11 @@ config KVM_AMD will be called kvm-amd. config KVM_AMD_SEV - def_bool y bool "AMD Secure Encrypted Virtualization (SEV) support" + default y depends on KVM_AMD && X86_64 depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) + select ARCH_HAS_CC_PLATFORM help Provides support for launching Encrypted VMs (SEV) and Encrypted VMs with Encrypted State (SEV-ES) on AMD processors. diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 475b5fa917..addc44fc71 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -3,10 +3,6 @@ ccflags-y += -I $(srctree)/arch/x86/kvm ccflags-$(CONFIG_KVM_WERROR) += -Werror -ifeq ($(CONFIG_FRAME_POINTER),y) -OBJECT_FILES_NON_STANDARD_vmenter.o := y -endif - include $(srctree)/virt/kvm/Makefile.kvm kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 3a02276899..b1002b7988 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -189,15 +189,15 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 return 0; } -static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, - const char *sig) +static struct kvm_hypervisor_cpuid __kvm_get_hypervisor_cpuid(struct kvm_cpuid_entry2 *entries, + int nent, const char *sig) { struct kvm_hypervisor_cpuid cpuid = {}; struct kvm_cpuid_entry2 *entry; u32 base; for_each_possible_hypervisor_cpuid_base(base) { - entry = kvm_find_cpuid_entry(vcpu, base); + entry = cpuid_entry2_find(entries, nent, base, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (entry) { u32 signature[3]; @@ -217,22 +217,29 @@ static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcp return cpuid; } -static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu, - struct kvm_cpuid_entry2 *entries, int nent) +static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, + const char *sig) { - u32 base = vcpu->arch.kvm_cpuid.base; - - if (!base) - return NULL; + return __kvm_get_hypervisor_cpuid(vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent, sig); +} - return cpuid_entry2_find(entries, nent, base | KVM_CPUID_FEATURES, +static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_cpuid_entry2 *entries, + int nent, u32 kvm_cpuid_base) +{ + return cpuid_entry2_find(entries, nent, kvm_cpuid_base | KVM_CPUID_FEATURES, KVM_CPUID_INDEX_NOT_SIGNIFICANT); } static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) { - return __kvm_find_kvm_cpuid_features(vcpu, vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent); + u32 base = vcpu->arch.kvm_cpuid.base; + + if (!base) + return NULL; + + return __kvm_find_kvm_cpuid_features(vcpu->arch.cpuid_entries, + vcpu->arch.cpuid_nent, base); } void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) @@ -266,6 +273,7 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e int nent) { struct kvm_cpuid_entry2 *best; + struct kvm_hypervisor_cpuid kvm_cpuid; best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); if (best) { @@ -292,10 +300,12 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e cpuid_entry_has(best, X86_FEATURE_XSAVEC))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - best = __kvm_find_kvm_cpuid_features(vcpu, entries, nent); - if (kvm_hlt_in_guest(vcpu->kvm) && best && - (best->eax & (1 << KVM_FEATURE_PV_UNHALT))) - best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); + kvm_cpuid = __kvm_get_hypervisor_cpuid(entries, nent, KVM_SIGNATURE); + if (kvm_cpuid.base) { + best = __kvm_find_kvm_cpuid_features(entries, nent, kvm_cpuid.base); + if (kvm_hlt_in_guest(vcpu->kvm) && best) + best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); + } if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { best = cpuid_entry2_find(entries, nent, 0x1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); @@ -1222,9 +1232,8 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = 0; break; case 0x80000008: { - unsigned g_phys_as = (entry->eax >> 16) & 0xff; - unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); - unsigned phys_as = entry->eax & 0xff; + unsigned int virt_as = max((entry->eax >> 8) & 0xff, 48U); + unsigned int phys_as; /* * If TDP (NPT) is disabled use the adjusted host MAXPHYADDR as @@ -1232,16 +1241,16 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) * reductions in MAXPHYADDR for memory encryption affect shadow * paging, too. * - * If TDP is enabled but an explicit guest MAXPHYADDR is not - * provided, use the raw bare metal MAXPHYADDR as reductions to - * the HPAs do not affect GPAs. + * If TDP is enabled, use the raw bare metal MAXPHYADDR as + * reductions to the HPAs do not affect GPAs. */ - if (!tdp_enabled) - g_phys_as = boot_cpu_data.x86_phys_bits; - else if (!g_phys_as) - g_phys_as = phys_as; + if (!tdp_enabled) { + phys_as = boot_cpu_data.x86_phys_bits; + } else { + phys_as = entry->eax & 0xff; + } - entry->eax = g_phys_as | (virt_as << 8); + entry->eax = phys_as | (virt_as << 8); entry->ecx &= ~(GENMASK(31, 16) | GENMASK(11, 8)); entry->edx = 0; cpuid_entry_override(entry, CPUID_8000_0008_EBX); diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index 95ea1a1f74..999227fc7c 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -189,9 +189,8 @@ static const struct file_operations mmu_rmaps_stat_fops = { .release = kvm_mmu_rmaps_stat_release, }; -int kvm_arch_create_vm_debugfs(struct kvm *kvm) +void kvm_arch_create_vm_debugfs(struct kvm *kvm) { debugfs_create_file("mmu_rmaps_stat", 0644, kvm->debugfs_dentry, kvm, &mmu_rmaps_stat_fops); - return 0; } diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index e223043ef5..5d4c861334 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1820,22 +1820,22 @@ static int writeback(struct x86_emulate_ctxt *ctxt, struct operand *op) return X86EMUL_CONTINUE; } -static int push(struct x86_emulate_ctxt *ctxt, void *data, int bytes) +static int emulate_push(struct x86_emulate_ctxt *ctxt, const void *data, int len) { struct segmented_address addr; - rsp_increment(ctxt, -bytes); + rsp_increment(ctxt, -len); addr.ea = reg_read(ctxt, VCPU_REGS_RSP) & stack_mask(ctxt); addr.seg = VCPU_SREG_SS; - return segmented_write(ctxt, addr, data, bytes); + return segmented_write(ctxt, addr, data, len); } static int em_push(struct x86_emulate_ctxt *ctxt) { /* Disable writeback. */ ctxt->dst.type = OP_NONE; - return push(ctxt, &ctxt->src.val, ctxt->op_bytes); + return emulate_push(ctxt, &ctxt->src.val, ctxt->op_bytes); } static int emulate_pop(struct x86_emulate_ctxt *ctxt, @@ -1863,7 +1863,8 @@ static int emulate_popf(struct x86_emulate_ctxt *ctxt, void *dest, int len) { int rc; - unsigned long val, change_mask; + unsigned long val = 0; + unsigned long change_mask; int iopl = (ctxt->eflags & X86_EFLAGS_IOPL) >> X86_EFLAGS_IOPL_BIT; int cpl = ctxt->ops->cpl(ctxt); @@ -1920,7 +1921,7 @@ static int em_enter(struct x86_emulate_ctxt *ctxt) return X86EMUL_UNHANDLEABLE; rbp = reg_read(ctxt, VCPU_REGS_RBP); - rc = push(ctxt, &rbp, stack_size(ctxt)); + rc = emulate_push(ctxt, &rbp, stack_size(ctxt)); if (rc != X86EMUL_CONTINUE) return rc; assign_masked(reg_rmw(ctxt, VCPU_REGS_RBP), reg_read(ctxt, VCPU_REGS_RSP), @@ -1954,7 +1955,7 @@ static int em_push_sreg(struct x86_emulate_ctxt *ctxt) static int em_pop_sreg(struct x86_emulate_ctxt *ctxt) { int seg = ctxt->src2.val; - unsigned long selector; + unsigned long selector = 0; int rc; rc = emulate_pop(ctxt, &selector, 2); @@ -2000,7 +2001,7 @@ static int em_popa(struct x86_emulate_ctxt *ctxt) { int rc = X86EMUL_CONTINUE; int reg = VCPU_REGS_RDI; - u32 val; + u32 val = 0; while (reg >= VCPU_REGS_RAX) { if (reg == VCPU_REGS_RSP) { @@ -2229,7 +2230,7 @@ static int em_cmpxchg8b(struct x86_emulate_ctxt *ctxt) static int em_ret(struct x86_emulate_ctxt *ctxt) { int rc; - unsigned long eip; + unsigned long eip = 0; rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) @@ -2241,7 +2242,8 @@ static int em_ret(struct x86_emulate_ctxt *ctxt) static int em_ret_far(struct x86_emulate_ctxt *ctxt) { int rc; - unsigned long eip, cs; + unsigned long eip = 0; + unsigned long cs = 0; int cpl = ctxt->ops->cpl(ctxt); struct desc_struct new_desc; @@ -3011,7 +3013,7 @@ static int emulator_do_task_switch(struct x86_emulate_ctxt *ctxt, ret = em_push(ctxt); } - ops->get_dr(ctxt, 7, &dr7); + dr7 = ops->get_dr(ctxt, 7); ops->set_dr(ctxt, 7, dr7 & ~(DR_LOCAL_ENABLE_MASK | DR_LOCAL_SLOWDOWN)); return ret; @@ -3184,7 +3186,7 @@ fail: static int em_ret_near_imm(struct x86_emulate_ctxt *ctxt) { int rc; - unsigned long eip; + unsigned long eip = 0; rc = emulate_pop(ctxt, &eip, ctxt->op_bytes); if (rc != X86EMUL_CONTINUE) @@ -3866,15 +3868,6 @@ static int check_cr_access(struct x86_emulate_ctxt *ctxt) return X86EMUL_CONTINUE; } -static int check_dr7_gd(struct x86_emulate_ctxt *ctxt) -{ - unsigned long dr7; - - ctxt->ops->get_dr(ctxt, 7, &dr7); - - return dr7 & DR7_GD; -} - static int check_dr_read(struct x86_emulate_ctxt *ctxt) { int dr = ctxt->modrm_reg; @@ -3887,10 +3880,10 @@ static int check_dr_read(struct x86_emulate_ctxt *ctxt) if ((cr4 & X86_CR4_DE) && (dr == 4 || dr == 5)) return emulate_ud(ctxt); - if (check_dr7_gd(ctxt)) { + if (ctxt->ops->get_dr(ctxt, 7) & DR7_GD) { ulong dr6; - ctxt->ops->get_dr(ctxt, 6, &dr6); + dr6 = ctxt->ops->get_dr(ctxt, 6); dr6 &= ~DR_TRAP_BITS; dr6 |= DR6_BD | DR6_ACTIVE_LOW; ctxt->ops->set_dr(ctxt, 6, dr6); @@ -3962,7 +3955,7 @@ static int check_rdpmc(struct x86_emulate_ctxt *ctxt) * protected mode. */ if ((!(cr4 & X86_CR4_PCE) && ctxt->ops->cpl(ctxt)) || - ctxt->ops->check_pmc(ctxt, rcx)) + ctxt->ops->check_rdpmc_early(ctxt, rcx)) return emulate_gp(ctxt, 0); return X86EMUL_CONTINUE; @@ -4505,11 +4498,11 @@ static const struct instr_dual instr_dual_0f_38_f1 = { }; static const struct gprefix three_byte_0f_38_f0 = { - ID(0, &instr_dual_0f_38_f0), N, N, N + ID(0, &instr_dual_0f_38_f0), ID(0, &instr_dual_0f_38_f0), N, N }; static const struct gprefix three_byte_0f_38_f1 = { - ID(0, &instr_dual_0f_38_f1), N, N, N + ID(0, &instr_dual_0f_38_f1), ID(0, &instr_dual_0f_38_f1), N, N }; /* @@ -5449,7 +5442,7 @@ twobyte_insn: ctxt->dst.val = ops->get_cr(ctxt, ctxt->modrm_reg); break; case 0x21: /* mov from dr to reg */ - ops->get_dr(ctxt, ctxt->modrm_reg, &ctxt->dst.val); + ctxt->dst.val = ops->get_dr(ctxt, ctxt->modrm_reg); break; case 0x40 ... 0x4f: /* cmov */ if (test_cc(ctxt->b, ctxt->eflags)) diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index e6d1498251..5382646162 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -203,12 +203,12 @@ struct x86_emulate_ops { ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr); int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val); int (*cpl)(struct x86_emulate_ctxt *ctxt); - void (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); + ulong (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr); int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); 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 (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata); - int (*check_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc); + int (*check_rdpmc_early)(struct x86_emulate_ctxt *ctxt, u32 pmc); int (*read_pmc)(struct x86_emulate_ctxt *ctxt, u32 pmc, u64 *pdata); void (*halt)(struct x86_emulate_ctxt *ctxt); void (*wbinvd)(struct x86_emulate_ctxt *ctxt); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 76fcee92b0..ebf41023be 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -125,6 +125,9 @@ static inline int __apic_test_and_clear_vector(int vec, void *bitmap) return __test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec)); } +__read_mostly DEFINE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu); +EXPORT_SYMBOL_GPL(kvm_has_noapic_vcpu); + __read_mostly DEFINE_STATIC_KEY_DEFERRED_FALSE(apic_hw_disabled, HZ); __read_mostly DEFINE_STATIC_KEY_DEFERRED_FALSE(apic_sw_disabled, HZ); @@ -2469,8 +2472,10 @@ void kvm_free_lapic(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; - if (!vcpu->arch.apic) + if (!vcpu->arch.apic) { + static_branch_dec(&kvm_has_noapic_vcpu); return; + } hrtimer_cancel(&apic->lapic_timer.timer); @@ -2813,13 +2818,21 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) ASSERT(vcpu != NULL); + if (!irqchip_in_kernel(vcpu->kvm)) { + static_branch_inc(&kvm_has_noapic_vcpu); + return 0; + } + apic = kzalloc(sizeof(*apic), GFP_KERNEL_ACCOUNT); if (!apic) goto nomem; vcpu->arch.apic = apic; - apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); + if (kvm_x86_ops.alloc_apic_backing_page) + apic->regs = static_call(kvm_x86_alloc_apic_backing_page)(vcpu); + else + apic->regs = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!apic->regs) { printk(KERN_ERR "malloc apic regs error for vcpu %x\n", vcpu->vcpu_id); @@ -2848,6 +2861,21 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns) static_branch_inc(&apic_sw_disabled.key); /* sw disabled at reset */ kvm_iodevice_init(&apic->dev, &apic_mmio_ops); + /* + * Defer evaluating inhibits until the vCPU is first run, as this vCPU + * will not get notified of any changes until this vCPU is visible to + * other vCPUs (marked online and added to the set of vCPUs). + * + * Opportunistically mark APICv active as VMX in particularly is highly + * unlikely to have inhibits. Ignore the current per-VM APICv state so + * that vCPU creation is guaranteed to run with a deterministic value, + * the request will ensure the vCPU gets the correct state before VM-Entry. + */ + if (enable_apicv) { + apic->apicv_active = true; + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); + } + return 0; nomem_free_apic: kfree(apic); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 982cf41e14..db007a4dff 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -47,18 +47,18 @@ #include <linux/kern_levels.h> #include <linux/kstrtox.h> #include <linux/kthread.h> +#include <linux/wordpart.h> #include <asm/page.h> #include <asm/memtype.h> #include <asm/cmpxchg.h> #include <asm/io.h> #include <asm/set_memory.h> +#include <asm/spec-ctrl.h> #include <asm/vmx.h> #include "trace.h" -extern bool itlb_multihit_kvm_mitigation; - static bool nx_hugepage_mitigation_hard_disabled; int __read_mostly nx_huge_pages = -1; @@ -263,7 +263,7 @@ static unsigned long get_guest_cr3(struct kvm_vcpu *vcpu) static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) { - if (IS_ENABLED(CONFIG_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) return kvm_read_cr3(vcpu); return mmu->get_guest_pgd(vcpu); @@ -3110,7 +3110,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, /* * Read each entry once. As above, a non-leaf entry can be promoted to * a huge page _during_ this walk. Re-reading the entry could send the - * walk into the weeks, e.g. p*d_large() returns false (sees the old + * walk into the weeks, e.g. p*d_leaf() returns false (sees the old * value) and then p*d_offset() walks into the target huge page instead * of the old page table (sees the new value). */ @@ -3135,7 +3135,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, if (pmd_none(pmd) || !pmd_present(pmd)) goto out; - if (pmd_large(pmd)) + if (pmd_leaf(pmd)) level = PG_LEVEL_2M; out: @@ -3575,10 +3575,14 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, if (WARN_ON_ONCE(!sp)) return; - if (is_tdp_mmu_page(sp)) + if (is_tdp_mmu_page(sp)) { + lockdep_assert_held_read(&kvm->mmu_lock); kvm_tdp_mmu_put_root(kvm, sp); - else if (!--sp->root_count && sp->role.invalid) - kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); + } else { + lockdep_assert_held_write(&kvm->mmu_lock); + if (!--sp->root_count && sp->role.invalid) + kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); + } *root_hpa = INVALID_PAGE; } @@ -3587,6 +3591,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, ulong roots_to_free) { + bool is_tdp_mmu = tdp_mmu_enabled && mmu->root_role.direct; int i; LIST_HEAD(invalid_list); bool free_active_root; @@ -3609,7 +3614,10 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, return; } - write_lock(&kvm->mmu_lock); + if (is_tdp_mmu) + read_lock(&kvm->mmu_lock); + else + write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if (roots_to_free & KVM_MMU_ROOT_PREVIOUS(i)) @@ -3635,8 +3643,13 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, mmu->root.pgd = 0; } - kvm_mmu_commit_zap_page(kvm, &invalid_list); - write_unlock(&kvm->mmu_lock); + if (is_tdp_mmu) { + read_unlock(&kvm->mmu_lock); + WARN_ON_ONCE(!list_empty(&invalid_list)); + } else { + kvm_mmu_commit_zap_page(kvm, &invalid_list); + write_unlock(&kvm->mmu_lock); + } } EXPORT_SYMBOL_GPL(kvm_mmu_free_roots); @@ -3693,15 +3706,15 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) unsigned i; int r; + if (tdp_mmu_enabled) + return kvm_tdp_mmu_alloc_root(vcpu); + write_lock(&vcpu->kvm->mmu_lock); r = make_mmu_pages_available(vcpu); if (r < 0) goto out_unlock; - if (tdp_mmu_enabled) { - root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu); - mmu->root.hpa = root; - } else if (shadow_root_level >= PT64_ROOT_4LEVEL) { + if (shadow_root_level >= PT64_ROOT_4LEVEL) { root = mmu_alloc_root(vcpu, 0, 0, shadow_root_level); mmu->root.hpa = root; } else if (shadow_root_level == PT32E_ROOT_LEVEL) { @@ -5563,9 +5576,9 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) * that problem is swept under the rug; KVM's CPUID API is horrific and * it's all but impossible to solve it without introducing a new API. */ - vcpu->arch.root_mmu.root_role.word = 0; - vcpu->arch.guest_mmu.root_role.word = 0; - vcpu->arch.nested_mmu.root_role.word = 0; + vcpu->arch.root_mmu.root_role.invalid = 1; + vcpu->arch.guest_mmu.root_role.invalid = 1; + vcpu->arch.nested_mmu.root_role.invalid = 1; vcpu->arch.root_mmu.cpu_role.ext.valid = 0; vcpu->arch.guest_mmu.cpu_role.ext.valid = 0; vcpu->arch.nested_mmu.cpu_role.ext.valid = 0; @@ -7039,9 +7052,7 @@ int kvm_mmu_vendor_module_init(void) kvm_mmu_reset_all_pte_masks(); - pte_list_desc_cache = kmem_cache_create("pte_list_desc", - sizeof(struct pte_list_desc), - 0, SLAB_ACCOUNT, NULL); + pte_list_desc_cache = KMEM_CACHE(pte_list_desc, SLAB_ACCOUNT); if (!pte_list_desc_cache) goto out; diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 0669a8a668..5390a591a5 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -315,7 +315,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, if (!prefetch) vcpu->stat.pf_taken++; - if (IS_ENABLED(CONFIG_RETPOLINE) && fault.is_tdp) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && fault.is_tdp) r = kvm_tdp_page_fault(vcpu, &fault); else r = vcpu->arch.mmu->page_fault(vcpu, &fault); diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index c87da11f3a..f6448284c1 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -20,10 +20,23 @@ #include "mmu_internal.h" #include "page_track.h" +static bool kvm_external_write_tracking_enabled(struct kvm *kvm) +{ +#ifdef CONFIG_KVM_EXTERNAL_WRITE_TRACKING + /* + * Read external_write_tracking_enabled before related pointers. Pairs + * with the smp_store_release in kvm_page_track_write_tracking_enable(). + */ + return smp_load_acquire(&kvm->arch.external_write_tracking_enabled); +#else + return false; +#endif +} + bool kvm_page_track_write_tracking_enabled(struct kvm *kvm) { - return IS_ENABLED(CONFIG_KVM_EXTERNAL_WRITE_TRACKING) || - !tdp_enabled || kvm_shadow_root_allocated(kvm); + return kvm_external_write_tracking_enabled(kvm) || + kvm_shadow_root_allocated(kvm) || !tdp_enabled; } void kvm_page_track_free_memslot(struct kvm_memory_slot *slot) @@ -153,6 +166,50 @@ int kvm_page_track_init(struct kvm *kvm) return init_srcu_struct(&head->track_srcu); } +static int kvm_enable_external_write_tracking(struct kvm *kvm) +{ + struct kvm_memslots *slots; + struct kvm_memory_slot *slot; + int r = 0, i, bkt; + + mutex_lock(&kvm->slots_arch_lock); + + /* + * Check for *any* write tracking user (not just external users) under + * lock. This avoids unnecessary work, e.g. if KVM itself is using + * write tracking, or if two external users raced when registering. + */ + if (kvm_page_track_write_tracking_enabled(kvm)) + goto out_success; + + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + slots = __kvm_memslots(kvm, i); + kvm_for_each_memslot(slot, bkt, slots) { + /* + * Intentionally do NOT free allocations on failure to + * avoid having to track which allocations were made + * now versus when the memslot was created. The + * metadata is guaranteed to be freed when the slot is + * freed, and will be kept/used if userspace retries + * the failed ioctl() instead of killing the VM. + */ + r = kvm_page_track_write_tracking_alloc(slot); + if (r) + goto out_unlock; + } + } + +out_success: + /* + * Ensure that external_write_tracking_enabled becomes true strictly + * after all the related pointers are set. + */ + smp_store_release(&kvm->arch.external_write_tracking_enabled, true); +out_unlock: + mutex_unlock(&kvm->slots_arch_lock); + return r; +} + /* * register the notifier so that event interception for the tracked guest * pages can be received. @@ -161,10 +218,17 @@ int kvm_page_track_register_notifier(struct kvm *kvm, struct kvm_page_track_notifier_node *n) { struct kvm_page_track_notifier_head *head; + int r; if (!kvm || kvm->mm != current->mm) return -ESRCH; + if (!kvm_external_write_tracking_enabled(kvm)) { + r = kvm_enable_external_write_tracking(kvm); + if (r) + return r; + } + kvm_get_kvm(kvm); head = &kvm->arch.track_notifier_head; diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 953082bf96..04c1f0957f 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -149,11 +149,11 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * If shared is set, this function is operating under the MMU lock in read * mode. */ -#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid)\ - for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid); \ - ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _only_valid)) \ - if (kvm_mmu_page_as_id(_root) != _as_id) { \ +#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid); \ + ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ + _root = tdp_mmu_next_root(_kvm, _root, _only_valid)) \ + if (_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) { \ } else #define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ @@ -171,12 +171,19 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * Holding mmu_lock for write obviates the need for RCU protection as the list * is guaranteed to be stable. */ -#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \ - list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) \ - if (kvm_lockdep_assert_mmu_lock_held(_kvm, false) && \ - kvm_mmu_page_as_id(_root) != _as_id) { \ +#define __for_each_tdp_mmu_root(_kvm, _root, _as_id, _only_valid) \ + list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) \ + if (kvm_lockdep_assert_mmu_lock_held(_kvm, false) && \ + ((_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) || \ + ((_only_valid) && (_root)->role.invalid))) { \ } else +#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \ + __for_each_tdp_mmu_root(_kvm, _root, _as_id, false) + +#define for_each_valid_tdp_mmu_root(_kvm, _root, _as_id) \ + __for_each_tdp_mmu_root(_kvm, _root, _as_id, true) + static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu) { struct kvm_mmu_page *sp; @@ -216,22 +223,41 @@ static void tdp_mmu_init_child_sp(struct kvm_mmu_page *child_sp, tdp_mmu_init_sp(child_sp, iter->sptep, iter->gfn, role); } -hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) +int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu) { - union kvm_mmu_page_role role = vcpu->arch.mmu->root_role; + struct kvm_mmu *mmu = vcpu->arch.mmu; + union kvm_mmu_page_role role = mmu->root_role; + int as_id = kvm_mmu_role_as_id(role); struct kvm *kvm = vcpu->kvm; struct kvm_mmu_page *root; - lockdep_assert_held_write(&kvm->mmu_lock); + /* + * Check for an existing root before acquiring the pages lock to avoid + * unnecessary serialization if multiple vCPUs are loading a new root. + * E.g. when bringing up secondary vCPUs, KVM will already have created + * a valid root on behalf of the primary vCPU. + */ + read_lock(&kvm->mmu_lock); + + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, as_id) { + if (root->role.word == role.word) + goto out_read_unlock; + } + + spin_lock(&kvm->arch.tdp_mmu_pages_lock); /* - * Check for an existing root before allocating a new one. Note, the - * role check prevents consuming an invalid root. + * Recheck for an existing root after acquiring the pages lock, another + * vCPU may have raced ahead and created a new usable root. Manually + * walk the list of roots as the standard macros assume that the pages + * lock is *not* held. WARN if grabbing a reference to a usable root + * fails, as the last reference to a root can only be put *after* the + * root has been invalidated, which requires holding mmu_lock for write. */ - for_each_tdp_mmu_root(kvm, root, kvm_mmu_role_as_id(role)) { + list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { if (root->role.word == role.word && - kvm_tdp_mmu_get_root(root)) - goto out; + !WARN_ON_ONCE(!kvm_tdp_mmu_get_root(root))) + goto out_spin_unlock; } root = tdp_mmu_alloc_sp(vcpu); @@ -245,13 +271,20 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu) * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots(). */ refcount_set(&root->tdp_mmu_root_count, 2); - - spin_lock(&kvm->arch.tdp_mmu_pages_lock); list_add_rcu(&root->link, &kvm->arch.tdp_mmu_roots); - spin_unlock(&kvm->arch.tdp_mmu_pages_lock); -out: - return __pa(root->spt); +out_spin_unlock: + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); +out_read_unlock: + read_unlock(&kvm->mmu_lock); + /* + * Note, KVM_REQ_MMU_FREE_OBSOLETE_ROOTS will prevent entering the guest + * and actually consuming the root if it's invalidated after dropping + * mmu_lock, and the root can't be freed as this vCPU holds a reference. + */ + mmu->root.hpa = __pa(root->spt); + mmu->root.pgd = 0; + return 0; } static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, @@ -734,15 +767,26 @@ static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); /* - * To avoid RCU stalls due to recursively removing huge swaths of SPs, - * split the zap into two passes. On the first pass, zap at the 1gb - * level, and then zap top-level SPs on the second pass. "1gb" is not - * arbitrary, as KVM must be able to zap a 1gb shadow page without - * inducing a stall to allow in-place replacement with a 1gb hugepage. + * Zap roots in multiple passes of decreasing granularity, i.e. zap at + * 4KiB=>2MiB=>1GiB=>root, in order to better honor need_resched() (all + * preempt models) or mmu_lock contention (full or real-time models). + * Zapping at finer granularity marginally increases the total time of + * the zap, but in most cases the zap itself isn't latency sensitive. * - * Because zapping a SP recurses on its children, stepping down to - * PG_LEVEL_4K in the iterator itself is unnecessary. + * If KVM is configured to prove the MMU, skip the 4KiB and 2MiB zaps + * in order to mimic the page fault path, which can replace a 1GiB page + * table with an equivalent 1GiB hugepage, i.e. can get saddled with + * zapping a 1GiB region that's fully populated with 4KiB SPTEs. This + * allows verifying that KVM can safely zap 1GiB regions, e.g. without + * inducing RCU stalls, without relying on a relatively rare event + * (zapping roots is orders of magnitude more common). Note, because + * zapping a SP recurses on its children, stepping down to PG_LEVEL_4K + * in the iterator itself is unnecessary. */ + if (!IS_ENABLED(CONFIG_KVM_PROVE_MMU)) { + __tdp_mmu_zap_root(kvm, root, shared, PG_LEVEL_4K); + __tdp_mmu_zap_root(kvm, root, shared, PG_LEVEL_2M); + } __tdp_mmu_zap_root(kvm, root, shared, PG_LEVEL_1G); __tdp_mmu_zap_root(kvm, root, shared, root->role.level); @@ -800,7 +844,13 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, continue; tdp_mmu_iter_set_spte(kvm, &iter, 0); - flush = true; + + /* + * Zappings SPTEs in invalid roots doesn't require a TLB flush, + * see kvm_tdp_mmu_zap_invalidated_roots() for details. + */ + if (!root->role.invalid) + flush = true; } rcu_read_unlock(); @@ -813,16 +863,16 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, } /* - * Zap leaf SPTEs for the range of gfns, [start, end), for all roots. Returns - * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or - * more SPTEs were zapped since the MMU lock was last acquired. + * Zap leaf SPTEs for the range of gfns, [start, end), for all *VALID** roots. + * Returns true if a TLB flush is needed before releasing the MMU lock, i.e. if + * one or more SPTEs were zapped since the MMU lock was last acquired. */ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush) { struct kvm_mmu_page *root; lockdep_assert_held_write(&kvm->mmu_lock); - for_each_tdp_mmu_root_yield_safe(kvm, root) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, -1) flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush); return flush; @@ -896,7 +946,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) * the VM is being destroyed). * * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference. - * See kvm_tdp_mmu_get_vcpu_root_hpa(). + * See kvm_tdp_mmu_alloc_root(). */ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) { @@ -1508,13 +1558,6 @@ static bool tdp_mmu_need_write_protect(struct kvm_mmu_page *sp) return kvm_mmu_page_ad_need_write_protect(sp) || !kvm_ad_enabled(); } -/* - * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If - * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. - * If AD bits are not enabled, this will require clearing the writable bit on - * each SPTE. Returns true if an SPTE has been changed and the TLBs need to - * be flushed. - */ static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end) { @@ -1551,11 +1594,9 @@ retry: } /* - * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If - * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. - * If AD bits are not enabled, this will require clearing the writable bit on - * each SPTE. Returns true if an SPTE has been changed and the TLBs need to - * be flushed. + * Clear the dirty status (D-bit or W-bit) of all the SPTEs mapping GFNs in the + * memslot. Returns true if an SPTE has been changed and the TLBs need to be + * flushed. */ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, const struct kvm_memory_slot *slot) @@ -1571,13 +1612,6 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, return spte_set; } -/* - * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is - * set in mask, starting at gfn. The given memslot is expected to contain all - * the GFNs represented by set bits in the mask. If AD bits are enabled, - * clearing the dirty status will involve clearing the dirty bit on each SPTE - * or, if AD bits are not enabled, clearing the writable bit on each SPTE. - */ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t gfn, unsigned long mask, bool wrprot) { @@ -1620,11 +1654,9 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, } /* - * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is - * set in mask, starting at gfn. The given memslot is expected to contain all - * the GFNs represented by set bits in the mask. If AD bits are enabled, - * clearing the dirty status will involve clearing the dirty bit on each SPTE - * or, if AD bits are not enabled, clearing the writable bit on each SPTE. + * Clear the dirty status (D-bit or W-bit) of all the 4k SPTEs mapping GFNs for + * which a bit is set in mask, starting at gfn. The given memslot is expected to + * contain all the GFNs represented by set bits in the mask. */ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, @@ -1633,7 +1665,7 @@ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, { struct kvm_mmu_page *root; - for_each_tdp_mmu_root(kvm, root, slot->as_id) + for_each_valid_tdp_mmu_root(kvm, root, slot->as_id) clear_dirty_pt_masked(kvm, root, gfn, mask, wrprot); } @@ -1751,7 +1783,7 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, bool spte_set = false; lockdep_assert_held_write(&kvm->mmu_lock); - for_each_tdp_mmu_root(kvm, root, slot->as_id) + for_each_valid_tdp_mmu_root(kvm, root, slot->as_id) spte_set |= write_protect_gfn(kvm, root, gfn, min_level); return spte_set; diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 20d97aa46c..6e1ea04ca8 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -10,7 +10,7 @@ void kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); -hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu); +int kvm_tdp_mmu_alloc_root(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 2ab2d5213f..a593b03c9a 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -29,6 +29,9 @@ struct x86_pmu_capability __read_mostly kvm_pmu_cap; EXPORT_SYMBOL_GPL(kvm_pmu_cap); +struct kvm_pmu_emulated_event_selectors __read_mostly kvm_pmu_eventsel; +EXPORT_SYMBOL_GPL(kvm_pmu_eventsel); + /* Precise Distribution of Instructions Retired (PDIR) */ static const struct x86_cpu_id vmx_pebs_pdir_cpu[] = { X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D, NULL), @@ -67,7 +70,7 @@ static const struct x86_cpu_id vmx_pebs_pdist_cpu[] = { * all perf counters (both gp and fixed). The mapping relationship * between pmc and perf counters is as the following: * * Intel: [0 .. KVM_INTEL_PMC_MAX_GENERIC-1] <=> gp counters - * [INTEL_PMC_IDX_FIXED .. INTEL_PMC_IDX_FIXED + 2] <=> fixed + * [KVM_FIXED_PMC_BASE_IDX .. KVM_FIXED_PMC_BASE_IDX + 2] <=> fixed * * AMD: [0 .. AMD64_NUM_COUNTERS-1] and, for families 15H * and later, [0 .. AMD64_NUM_COUNTERS_CORE-1] <=> gp counters */ @@ -411,7 +414,7 @@ static bool is_gp_event_allowed(struct kvm_x86_pmu_event_filter *f, static bool is_fixed_event_allowed(struct kvm_x86_pmu_event_filter *filter, int idx) { - int fixed_idx = idx - INTEL_PMC_IDX_FIXED; + int fixed_idx = idx - KVM_FIXED_PMC_BASE_IDX; if (filter->action == KVM_PMU_EVENT_DENY && test_bit(fixed_idx, (ulong *)&filter->fixed_counter_bitmap)) @@ -441,11 +444,10 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc) static bool pmc_event_is_allowed(struct kvm_pmc *pmc) { return pmc_is_globally_enabled(pmc) && pmc_speculative_in_use(pmc) && - static_call(kvm_x86_pmu_hw_event_available)(pmc) && check_pmu_event_filter(pmc); } -static void reprogram_counter(struct kvm_pmc *pmc) +static int reprogram_counter(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); u64 eventsel = pmc->eventsel; @@ -456,7 +458,7 @@ static void reprogram_counter(struct kvm_pmc *pmc) emulate_overflow = pmc_pause_counter(pmc); if (!pmc_event_is_allowed(pmc)) - goto reprogram_complete; + return 0; if (emulate_overflow) __kvm_perf_overflow(pmc, false); @@ -466,7 +468,7 @@ static void reprogram_counter(struct kvm_pmc *pmc) if (pmc_is_fixed(pmc)) { fixed_ctr_ctrl = fixed_ctrl_field(pmu->fixed_ctr_ctrl, - pmc->idx - INTEL_PMC_IDX_FIXED); + pmc->idx - KVM_FIXED_PMC_BASE_IDX); if (fixed_ctr_ctrl & 0x1) eventsel |= ARCH_PERFMON_EVENTSEL_OS; if (fixed_ctr_ctrl & 0x2) @@ -477,43 +479,45 @@ static void reprogram_counter(struct kvm_pmc *pmc) } if (pmc->current_config == new_config && pmc_resume_counter(pmc)) - goto reprogram_complete; + return 0; pmc_release_perf_event(pmc); pmc->current_config = new_config; - /* - * 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); + return 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); } void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) { + DECLARE_BITMAP(bitmap, X86_PMC_IDX_MAX); struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + struct kvm_pmc *pmc; int bit; - 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); + bitmap_copy(bitmap, pmu->reprogram_pmi, X86_PMC_IDX_MAX); - if (unlikely(!pmc)) { - clear_bit(bit, pmu->reprogram_pmi); - continue; - } + /* + * The reprogramming bitmap can be written asynchronously by something + * other than the task that holds vcpu->mutex, take care to clear only + * the bits that will actually processed. + */ + BUILD_BUG_ON(sizeof(bitmap) != sizeof(atomic64_t)); + atomic64_andnot(*(s64 *)bitmap, &pmu->__reprogram_pmi); - reprogram_counter(pmc); + kvm_for_each_pmc(pmu, pmc, bit, bitmap) { + /* + * If reprogramming fails, e.g. due to contention, re-set the + * 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 (reprogram_counter(pmc)) + set_bit(pmc->idx, pmu->reprogram_pmi); } /* @@ -525,10 +529,20 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) kvm_pmu_cleanup(vcpu); } -/* check if idx is a valid index to access PMU */ -bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +int kvm_pmu_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx) { - return static_call(kvm_x86_pmu_is_valid_rdpmc_ecx)(vcpu, idx); + /* + * On Intel, VMX interception has priority over RDPMC exceptions that + * aren't already handled by the emulator, i.e. there are no additional + * check needed for Intel PMUs. + * + * On AMD, _all_ exceptions on RDPMC have priority over SVM intercepts, + * i.e. an invalid PMC results in a #GP, not #VMEXIT. + */ + if (!kvm_pmu_ops.check_rdpmc_early) + return 0; + + return static_call(kvm_x86_pmu_check_rdpmc_early)(vcpu, idx); } bool is_vmware_backdoor_pmc(u32 pmc_idx) @@ -567,10 +581,9 @@ static int kvm_pmu_rdpmc_vmware(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) { - bool fast_mode = idx & (1u << 31); struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *pmc; - u64 mask = fast_mode ? ~0u : ~0ull; + u64 mask = ~0ull; if (!pmu->version) return 1; @@ -716,11 +729,7 @@ static void kvm_pmu_reset(struct kvm_vcpu *vcpu) bitmap_zero(pmu->reprogram_pmi, X86_PMC_IDX_MAX); - for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) { - pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i); - if (!pmc) - continue; - + kvm_for_each_pmc(pmu, pmc, i, pmu->all_valid_pmc_idx) { pmc_stop_counter(pmc); pmc->counter = 0; pmc->emulated_counter = 0; @@ -804,10 +813,8 @@ void kvm_pmu_cleanup(struct kvm_vcpu *vcpu) bitmap_andnot(bitmask, pmu->all_valid_pmc_idx, pmu->pmc_in_use, X86_PMC_IDX_MAX); - for_each_set_bit(i, bitmask, X86_PMC_IDX_MAX) { - pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i); - - if (pmc && pmc->perf_event && !pmc_speculative_in_use(pmc)) + kvm_for_each_pmc(pmu, pmc, i, bitmask) { + if (pmc->perf_event && !pmc_speculative_in_use(pmc)) pmc_stop_counter(pmc); } @@ -827,13 +834,6 @@ static void kvm_pmu_incr_counter(struct kvm_pmc *pmc) kvm_pmu_request_counter_reprogram(pmc); } -static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc, - unsigned int perf_hw_id) -{ - return !((pmc->eventsel ^ perf_get_hw_event_config(perf_hw_id)) & - AMD64_RAW_EVENT_MASK_NB); -} - static inline bool cpl_is_matched(struct kvm_pmc *pmc) { bool select_os, select_user; @@ -845,29 +845,56 @@ static inline bool cpl_is_matched(struct kvm_pmc *pmc) 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); + pmc->idx - KVM_FIXED_PMC_BASE_IDX); select_os = config & 0x1; select_user = config & 0x2; } + /* + * Skip the CPL lookup, which isn't free on Intel, if the result will + * be the same regardless of the CPL. + */ + if (select_os == select_user) + return select_os; + return (static_call(kvm_x86_get_cpl)(pmc->vcpu) == 0) ? select_os : select_user; } -void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id) +void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 eventsel) { + DECLARE_BITMAP(bitmap, X86_PMC_IDX_MAX); struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *pmc; int i; - for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) { - pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i); + BUILD_BUG_ON(sizeof(pmu->global_ctrl) * BITS_PER_BYTE != X86_PMC_IDX_MAX); - if (!pmc || !pmc_event_is_allowed(pmc)) + if (!kvm_pmu_has_perf_global_ctrl(pmu)) + bitmap_copy(bitmap, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX); + else if (!bitmap_and(bitmap, pmu->all_valid_pmc_idx, + (unsigned long *)&pmu->global_ctrl, X86_PMC_IDX_MAX)) + return; + + kvm_for_each_pmc(pmu, pmc, i, bitmap) { + /* + * Ignore checks for edge detect (all events currently emulated + * but KVM are always rising edges), pin control (unsupported + * by modern CPUs), and counter mask and its invert flag (KVM + * doesn't emulate multiple events in a single clock cycle). + * + * Note, the uppermost nibble of AMD's mask overlaps Intel's + * IN_TX (bit 32) and IN_TXCP (bit 33), as well as two reserved + * bits (bits 35:34). Checking the "in HLE/RTM transaction" + * flags is correct as the vCPU can't be in a transaction if + * KVM is emulating an instruction. Checking the reserved bits + * might be wrong if they are defined in the future, but so + * could ignoring them, so do the simple thing for now. + */ + if (((pmc->eventsel ^ eventsel) & AMD64_RAW_EVENT_MASK_NB) || + !pmc_event_is_allowed(pmc) || !cpl_is_matched(pmc)) continue; - /* Ignore checks for edge detect, pin control, invert and CMASK bits */ - if (eventsel_match_perf_hw_id(pmc, perf_hw_id) && cpl_is_matched(pmc)) - kvm_pmu_incr_counter(pmc); + kvm_pmu_incr_counter(pmc); } } EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 7caeb3d8d4..4d52b0b539 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -4,6 +4,8 @@ #include <linux/nospec.h> +#include <asm/kvm_host.h> + #define vcpu_to_pmu(vcpu) (&(vcpu)->arch.pmu) #define pmu_to_vcpu(pmu) (container_of((pmu), struct kvm_vcpu, arch.pmu)) #define pmc_to_pmu(pmc) (&(pmc)->vcpu->arch.pmu) @@ -18,13 +20,18 @@ #define VMWARE_BACKDOOR_PMC_REAL_TIME 0x10001 #define VMWARE_BACKDOOR_PMC_APPARENT_TIME 0x10002 +#define KVM_FIXED_PMC_BASE_IDX INTEL_PMC_IDX_FIXED + +struct kvm_pmu_emulated_event_selectors { + u64 INSTRUCTIONS_RETIRED; + u64 BRANCH_INSTRUCTIONS_RETIRED; +}; + struct kvm_pmu_ops { - bool (*hw_event_available)(struct kvm_pmc *pmc); - struct kvm_pmc *(*pmc_idx_to_pmc)(struct kvm_pmu *pmu, int pmc_idx); struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu, unsigned int idx, u64 *mask); struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr); - bool (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx); + int (*check_rdpmc_early)(struct kvm_vcpu *vcpu, unsigned int idx); bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr); int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info); @@ -55,6 +62,38 @@ static inline bool kvm_pmu_has_perf_global_ctrl(struct kvm_pmu *pmu) return pmu->version > 1; } +/* + * KVM tracks all counters in 64-bit bitmaps, with general purpose counters + * mapped to bits 31:0 and fixed counters mapped to 63:32, e.g. fixed counter 0 + * is tracked internally via index 32. On Intel, (AMD doesn't support fixed + * counters), this mirrors how fixed counters are mapped to PERF_GLOBAL_CTRL + * and similar MSRs, i.e. tracking fixed counters at base index 32 reduces the + * amounter of boilerplate needed to iterate over PMCs *and* simplifies common + * enabling/disable/reset operations. + * + * WARNING! This helper is only for lookups that are initiated by KVM, it is + * NOT safe for guest lookups, e.g. will do the wrong thing if passed a raw + * ECX value from RDPMC (fixed counters are accessed by setting bit 30 in ECX + * for RDPMC, not by adding 32 to the fixed counter index). + */ +static inline struct kvm_pmc *kvm_pmc_idx_to_pmc(struct kvm_pmu *pmu, int idx) +{ + if (idx < pmu->nr_arch_gp_counters) + return &pmu->gp_counters[idx]; + + idx -= KVM_FIXED_PMC_BASE_IDX; + if (idx >= 0 && idx < pmu->nr_arch_fixed_counters) + return &pmu->fixed_counters[idx]; + + return NULL; +} + +#define kvm_for_each_pmc(pmu, pmc, i, bitmap) \ + for_each_set_bit(i, bitmap, X86_PMC_IDX_MAX) \ + if (!(pmc = kvm_pmc_idx_to_pmc(pmu, i))) \ + continue; \ + else \ + static inline u64 pmc_bitmask(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -131,12 +170,13 @@ static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc) if (pmc_is_fixed(pmc)) return fixed_ctrl_field(pmu->fixed_ctr_ctrl, - pmc->idx - INTEL_PMC_IDX_FIXED) & 0x3; + pmc->idx - KVM_FIXED_PMC_BASE_IDX) & 0x3; return pmc->eventsel & ARCH_PERFMON_EVENTSEL_ENABLE; } extern struct x86_pmu_capability kvm_pmu_cap; +extern struct kvm_pmu_emulated_event_selectors kvm_pmu_eventsel; static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops) { @@ -178,6 +218,11 @@ static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops) pmu_ops->MAX_NR_GP_COUNTERS); kvm_pmu_cap.num_counters_fixed = min(kvm_pmu_cap.num_counters_fixed, KVM_PMC_MAX_FIXED); + + kvm_pmu_eventsel.INSTRUCTIONS_RETIRED = + perf_get_hw_event_config(PERF_COUNT_HW_INSTRUCTIONS); + kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED = + perf_get_hw_event_config(PERF_COUNT_HW_BRANCH_INSTRUCTIONS); } static inline void kvm_pmu_request_counter_reprogram(struct kvm_pmc *pmc) @@ -216,7 +261,7 @@ static inline bool pmc_is_globally_enabled(struct kvm_pmc *pmc) void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu); void kvm_pmu_handle_event(struct kvm_vcpu *vcpu); int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data); -bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx); +int kvm_pmu_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx); bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); @@ -225,7 +270,7 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu); void kvm_pmu_cleanup(struct kvm_vcpu *vcpu); void kvm_pmu_destroy(struct kvm_vcpu *vcpu); int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp); -void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id); +void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 eventsel); bool is_vmware_backdoor_pmc(u32 pmc_idx); diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index dc3d95fdca..d06d43d8d2 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -184,7 +184,6 @@ 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); @@ -195,10 +194,8 @@ static void enter_smm_save_state_32(struct kvm_vcpu *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; + smram->dr6 = (u32)vcpu->arch.dr6; + smram->dr7 = (u32)vcpu->arch.dr7; 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); @@ -231,7 +228,6 @@ 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++) @@ -240,11 +236,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, 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->dr6 = vcpu->arch.dr6; + smram->dr7 = vcpu->arch.dr7; smram->cr0 = kvm_read_cr0(vcpu); smram->cr3 = kvm_read_cr3(vcpu); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index dee62362a3..55b9a6d96b 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1181,7 +1181,7 @@ int svm_allocate_nested(struct vcpu_svm *svm) if (svm->nested.initialized) return 0; - vmcb02_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + vmcb02_page = snp_safe_alloc_page(&svm->vcpu); if (!vmcb02_page) return -ENOMEM; svm->nested.vmcb02.ptr = page_address(vmcb02_page); diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index b6a7ad4d69..dfcc38bd97 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -25,7 +25,7 @@ enum pmu_type { PMU_TYPE_EVNTSEL, }; -static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) +static struct kvm_pmc *amd_pmu_get_pmc(struct kvm_pmu *pmu, int pmc_idx) { unsigned int num_counters = pmu->nr_arch_gp_counters; @@ -70,28 +70,24 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, return NULL; } - return amd_pmc_idx_to_pmc(pmu, idx); + return amd_pmu_get_pmc(pmu, idx); } -static bool amd_hw_event_available(struct kvm_pmc *pmc) -{ - return true; -} - -static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) +static int amd_check_rdpmc_early(struct kvm_vcpu *vcpu, unsigned int idx) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - idx &= ~(3u << 30); + if (idx >= pmu->nr_arch_gp_counters) + return -EINVAL; - return idx < pmu->nr_arch_gp_counters; + return 0; } /* idx is the ECX register of RDPMC instruction */ static struct kvm_pmc *amd_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, unsigned int idx, u64 *mask) { - return amd_pmc_idx_to_pmc(vcpu_to_pmu(vcpu), idx & ~(3u << 30)); + return amd_pmu_get_pmc(vcpu_to_pmu(vcpu), idx); } static struct kvm_pmc *amd_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr) @@ -233,11 +229,9 @@ static void amd_pmu_init(struct kvm_vcpu *vcpu) } struct kvm_pmu_ops amd_pmu_ops __initdata = { - .hw_event_available = amd_hw_event_available, - .pmc_idx_to_pmc = amd_pmc_idx_to_pmc, .rdpmc_ecx_to_pmc = amd_rdpmc_ecx_to_pmc, .msr_idx_to_pmc = amd_msr_idx_to_pmc, - .is_valid_rdpmc_ecx = amd_is_valid_rdpmc_ecx, + .check_rdpmc_early = amd_check_rdpmc_early, .is_valid_msr = amd_is_valid_msr, .get_msr = amd_pmu_get_msr, .set_msr = amd_pmu_set_msr, diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 86088d1250..4471b4e08d 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -186,7 +186,8 @@ again: mutex_unlock(&sev_bitmap_lock); - return asid; + sev->asid = asid; + return 0; e_uncharge: sev_misc_cg_uncharge(sev); put_misc_cg(sev->misc_cg); @@ -253,23 +254,23 @@ static void sev_unbind_asid(struct kvm *kvm, unsigned int handle) static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; - int asid, ret; + struct sev_platform_init_args init_args = {0}; + int ret; if (kvm->created_vcpus) return -EINVAL; - ret = -EBUSY; if (unlikely(sev->active)) - return ret; + return -EINVAL; sev->active = true; sev->es_active = argp->id == KVM_SEV_ES_INIT; - asid = sev_asid_new(sev); - if (asid < 0) + ret = sev_asid_new(sev); + if (ret) goto e_no_asid; - sev->asid = asid; - ret = sev_platform_init(&argp->error); + init_args.probe = false; + ret = sev_platform_init(&init_args); if (ret) goto e_free; @@ -281,6 +282,7 @@ static int sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp) return 0; e_free: + argp->error = init_args.error; sev_asid_free(sev); sev->asid = 0; e_no_asid: @@ -432,7 +434,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, /* Avoid using vmalloc for smaller buffers. */ size = npages * sizeof(struct page *); if (size > PAGE_SIZE) - pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); + pages = __vmalloc(size, GFP_KERNEL_ACCOUNT); else pages = kmalloc(size, GFP_KERNEL_ACCOUNT); @@ -664,6 +666,14 @@ static int __sev_launch_update_vmsa(struct kvm *kvm, struct kvm_vcpu *vcpu, return ret; vcpu->arch.guest_state_protected = true; + + /* + * SEV-ES guest mandates LBR Virtualization to be _always_ ON. Enable it + * only after setting guest_state_protected because KVM_SET_MSRS allows + * dynamic toggling of LBRV (for performance reason) on write access to + * MSR_IA32_DEBUGCTLMSR when guest_state_protected is not set. + */ + svm_enable_lbrv(vcpu); return 0; } @@ -2267,6 +2277,12 @@ void __init sev_hardware_setup(void) if (!boot_cpu_has(X86_FEATURE_SEV_ES)) goto out; + if (!lbrv) { + WARN_ONCE(!boot_cpu_has(X86_FEATURE_LBRV), + "LBRV must be present for SEV-ES support"); + goto out; + } + /* Has the system been allocated ASIDs for SEV-ES? */ if (min_sev_asid == 1) goto out; @@ -3032,7 +3048,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE; - svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK; /* * An SEV-ES guest requires a VMSA area that is a separate from the @@ -3084,10 +3099,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm) /* Clear intercepts on selected MSRs */ set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); } void sev_init_vmcb(struct vcpu_svm *svm) @@ -3176,3 +3187,35 @@ void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector) ghcb_set_sw_exit_info_2(svm->sev_es.ghcb, 1); } + +struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu) +{ + unsigned long pfn; + struct page *p; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + + /* + * Allocate an SNP-safe page to workaround the SNP erratum where + * the CPU will incorrectly signal an RMP violation #PF if a + * hugepage (2MB or 1GB) collides with the RMP entry of a + * 2MB-aligned VMCB, VMSA, or AVIC backing page. + * + * Allocate one extra page, choose a page which is not + * 2MB-aligned, and free the other. + */ + p = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO, 1); + if (!p) + return NULL; + + split_page(p, 1); + + pfn = page_to_pfn(p); + if (IS_ALIGNED(pfn, PTRS_PER_PMD)) + __free_page(p++); + else + __free_page(p + 1); + + return p; +} diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index e90b429c84..4650153afa 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -99,6 +99,7 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_SPEC_CTRL, .always = false }, { .index = MSR_IA32_PRED_CMD, .always = false }, { .index = MSR_IA32_FLUSH_CMD, .always = false }, + { .index = MSR_IA32_DEBUGCTLMSR, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -215,7 +216,7 @@ int vgif = true; module_param(vgif, int, 0444); /* enable/disable LBR virtualization */ -static int lbrv = true; +int lbrv = true; module_param(lbrv, int, 0444); static int tsc_scaling = true; @@ -703,7 +704,7 @@ static int svm_cpu_init(int cpu) int ret = -ENOMEM; memset(sd, 0, sizeof(struct svm_cpu_data)); - sd->save_area = alloc_page(GFP_KERNEL | __GFP_ZERO); + sd->save_area = snp_safe_alloc_page(NULL); if (!sd->save_area) return ret; @@ -990,7 +991,7 @@ void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb) vmcb_mark_dirty(to_vmcb, VMCB_LBR); } -static void svm_enable_lbrv(struct kvm_vcpu *vcpu) +void svm_enable_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1000,6 +1001,9 @@ static void svm_enable_lbrv(struct kvm_vcpu *vcpu) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1); + if (sev_es_guest(vcpu->kvm)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1); + /* Move the LBR msrs to the vmcb02 so that the guest can see them. */ if (is_guest_mode(vcpu)) svm_copy_lbrs(svm->vmcb, svm->vmcb01.ptr); @@ -1009,6 +1013,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); + KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm); + svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK; set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0); set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0); @@ -1421,7 +1427,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu) svm = to_svm(vcpu); err = -ENOMEM; - vmcb01_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + vmcb01_page = snp_safe_alloc_page(vcpu); if (!vmcb01_page) goto out; @@ -1430,7 +1436,7 @@ static int svm_vcpu_create(struct kvm_vcpu *vcpu) * SEV-ES guests require a separate VMSA page used to contain * the encrypted register state of the guest. */ - vmsa_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); + vmsa_page = snp_safe_alloc_page(vcpu); if (!vmsa_page) goto error_free_vmcb_page; @@ -1503,6 +1509,11 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); } +static struct sev_es_save_area *sev_es_host_save_area(struct svm_cpu_data *sd) +{ + return page_address(sd->save_area) + 0x400; +} + static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1519,12 +1530,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) * or subsequent vmload of host save area. */ vmsave(sd->save_area_pa); - if (sev_es_guest(vcpu->kvm)) { - struct sev_es_save_area *hostsa; - hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); - - sev_es_prepare_switch_to_guest(hostsa); - } + if (sev_es_guest(vcpu->kvm)) + sev_es_prepare_switch_to_guest(sev_es_host_save_area(sd)); if (tsc_scaling) __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); @@ -2735,7 +2742,6 @@ static int dr_interception(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); int reg, dr; - unsigned long val; int err = 0; /* @@ -2763,11 +2769,9 @@ static int dr_interception(struct kvm_vcpu *vcpu) dr = svm->vmcb->control.exit_code - SVM_EXIT_READ_DR0; if (dr >= 16) { /* mov to DRn */ dr -= 16; - val = kvm_register_read(vcpu, reg); - err = kvm_set_dr(vcpu, dr, val); + err = kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg)); } else { - kvm_get_dr(vcpu, dr, &val); - kvm_register_write(vcpu, reg, val); + kvm_register_write(vcpu, reg, kvm_get_dr(vcpu, dr)); } return kvm_complete_insn_gp(vcpu, err); @@ -3455,7 +3459,7 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code) if (!svm_check_exit_valid(exit_code)) return svm_handle_invalid_exit(vcpu, exit_code); -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE if (exit_code == SVM_EXIT_MSR) return msr_interception(vcpu); else if (exit_code == SVM_EXIT_VINTR) @@ -3845,16 +3849,27 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); /* - * KVM should never request an NMI window when vNMI is enabled, as KVM - * allows at most one to-be-injected NMI and one pending NMI, i.e. if - * two NMIs arrive simultaneously, KVM will inject one and set - * V_NMI_PENDING for the other. WARN, but continue with the standard - * single-step approach to try and salvage the pending NMI. + * If NMIs are outright masked, i.e. the vCPU is already handling an + * NMI, and KVM has not yet intercepted an IRET, then there is nothing + * more to do at this time as KVM has already enabled IRET intercepts. + * If KVM has already intercepted IRET, then single-step over the IRET, + * as NMIs aren't architecturally unmasked until the IRET completes. + * + * If vNMI is enabled, KVM should never request an NMI window if NMIs + * are masked, as KVM allows at most one to-be-injected NMI and one + * pending NMI. If two NMIs arrive simultaneously, KVM will inject one + * NMI and set V_NMI_PENDING for the other, but if and only if NMIs are + * unmasked. KVM _will_ request an NMI window in some situations, e.g. + * if the vCPU is in an STI shadow or if GIF=0, KVM can't immediately + * inject the NMI. In those situations, KVM needs to single-step over + * the STI shadow or intercept STGI. */ - WARN_ON_ONCE(is_vnmi_enabled(svm)); + if (svm_get_nmi_mask(vcpu)) { + WARN_ON_ONCE(is_vnmi_enabled(svm)); - if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion) - return; /* IRET will cause a vm exit */ + if (!svm->awaiting_iret_completion) + return; /* IRET will cause a vm exit */ + } /* * SEV-ES guests are responsible for signaling when a vCPU is ready to @@ -4092,6 +4107,9 @@ static int svm_vcpu_pre_run(struct kvm_vcpu *vcpu) static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) { + if (is_guest_mode(vcpu)) + return EXIT_FASTPATH_NONE; + if (to_svm(vcpu)->vmcb->control.exit_code == SVM_EXIT_MSR && to_svm(vcpu)->vmcb->control.exit_info_1) return handle_fastpath_set_msr_irqoff(vcpu); @@ -4101,6 +4119,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_intercepted) { + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); struct vcpu_svm *svm = to_svm(vcpu); guest_state_enter_irqoff(); @@ -4108,19 +4127,21 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in amd_clear_divider(); if (sev_es_guest(vcpu->kvm)) - __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted); + __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted, + sev_es_host_save_area(sd)); else __svm_vcpu_run(svm, spec_ctrl_intercepted); guest_state_exit_irqoff(); } -static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) +static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, + bool force_immediate_exit) { struct vcpu_svm *svm = to_svm(vcpu); bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL); - trace_kvm_entry(vcpu); + trace_kvm_entry(vcpu, force_immediate_exit); svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX]; svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP]; @@ -4139,9 +4160,12 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) * is enough to force an immediate vmexit. */ disable_nmi_singlestep(svm); - smp_send_reschedule(vcpu->cpu); + force_immediate_exit = true; } + if (force_immediate_exit) + smp_send_reschedule(vcpu->cpu); + pre_svm_run(vcpu); sync_lapic_to_cr8(vcpu); @@ -4237,9 +4261,6 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu) svm_complete_interrupts(vcpu); - if (is_guest_mode(vcpu)) - return EXIT_FASTPATH_NONE; - return svm_exit_handlers_fastpath(vcpu); } @@ -4900,6 +4921,16 @@ static int svm_vm_init(struct kvm *kvm) return 0; } +static void *svm_alloc_apic_backing_page(struct kvm_vcpu *vcpu) +{ + struct page *page = snp_safe_alloc_page(vcpu); + + if (!page) + return NULL; + + return page_address(page); +} + static struct kvm_x86_ops svm_x86_ops __initdata = { .name = KBUILD_MODNAME, @@ -4997,8 +5028,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .check_intercept = svm_check_intercept, .handle_exit_irqoff = svm_handle_exit_irqoff, - .request_immediate_exit = __kvm_request_immediate_exit, - .sched_in = svm_sched_in, .nested_ops = &svm_nested_ops, @@ -5031,6 +5060,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector, .vcpu_get_apicv_inhibit_reasons = avic_vcpu_get_apicv_inhibit_reasons, + .alloc_apic_backing_page = svm_alloc_apic_backing_page, }; /* @@ -5236,6 +5266,12 @@ static __init int svm_hardware_setup(void) nrips = nrips && boot_cpu_has(X86_FEATURE_NRIPS); + if (lbrv) { + if (!boot_cpu_has(X86_FEATURE_LBRV)) + lbrv = false; + else + pr_info("LBR virtualization supported\n"); + } /* * Note, SEV setup consumes npt_enabled and enable_mmio_caching (which * may be modified by svm_adjust_mmio_mask()), as well as nrips. @@ -5289,14 +5325,6 @@ static __init int svm_hardware_setup(void) svm_x86_ops.set_vnmi_pending = NULL; } - - if (lbrv) { - if (!boot_cpu_has(X86_FEATURE_LBRV)) - lbrv = false; - else - pr_info("LBR virtualization supported\n"); - } - if (!enable_pmu) pr_info("PMU virtualization is disabled\n"); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 8ef95139cd..2ed3015e03 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -30,7 +30,7 @@ #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 -#define MAX_DIRECT_ACCESS_MSRS 47 +#define MAX_DIRECT_ACCESS_MSRS 48 #define MSRPM_OFFSETS 32 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; @@ -39,6 +39,7 @@ extern int vgif; extern bool intercept_smi; extern bool x2avic_enabled; extern bool vnmi; +extern int lbrv; /* * Clean bits in VMCB. @@ -543,6 +544,7 @@ u32 *svm_vcpu_alloc_msrpm(void); void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm); void svm_vcpu_free_msrpm(u32 *msrpm); void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb); +void svm_enable_lbrv(struct kvm_vcpu *vcpu); void svm_update_lbrv(struct kvm_vcpu *vcpu); int svm_set_efer(struct kvm_vcpu *vcpu, u64 efer); @@ -694,10 +696,12 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm); void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector); void sev_es_prepare_switch_to_guest(struct sev_es_save_area *hostsa); void sev_es_unmap_ghcb(struct vcpu_svm *svm); +struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu); /* vmenter.S */ -void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); +void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted, + struct sev_es_save_area *hostsa); void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); #define DEFINE_KVM_GHCB_ACCESSORS(field) \ diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 9499f9c6b0..a0c8eb37d3 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -3,6 +3,7 @@ #include <asm/asm.h> #include <asm/asm-offsets.h> #include <asm/bitsperlong.h> +#include <asm/frame.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> #include "kvm-asm-offsets.h" @@ -67,7 +68,7 @@ "", X86_FEATURE_V_SPEC_CTRL 901: .endm -.macro RESTORE_HOST_SPEC_CTRL_BODY +.macro RESTORE_HOST_SPEC_CTRL_BODY spec_ctrl_intercepted:req 900: /* Same for after vmexit. */ mov $MSR_IA32_SPEC_CTRL, %ecx @@ -76,7 +77,7 @@ * Load the value that the guest had written into MSR_IA32_SPEC_CTRL, * if it was not intercepted during guest execution. */ - cmpb $0, (%_ASM_SP) + cmpb $0, \spec_ctrl_intercepted jnz 998f rdmsr movl %eax, SVM_spec_ctrl(%_ASM_DI) @@ -99,6 +100,7 @@ */ SYM_FUNC_START(__svm_vcpu_run) push %_ASM_BP + mov %_ASM_SP, %_ASM_BP #ifdef CONFIG_X86_64 push %r15 push %r14 @@ -207,7 +209,7 @@ SYM_FUNC_START(__svm_vcpu_run) 7: vmload %_ASM_AX 8: -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif @@ -268,7 +270,7 @@ SYM_FUNC_START(__svm_vcpu_run) RET RESTORE_GUEST_SPEC_CTRL_BODY - RESTORE_HOST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY (%_ASM_SP) 10: cmpb $0, _ASM_RIP(kvm_rebooting) jne 2b @@ -290,66 +292,68 @@ SYM_FUNC_START(__svm_vcpu_run) SYM_FUNC_END(__svm_vcpu_run) +#ifdef CONFIG_KVM_AMD_SEV + + +#ifdef CONFIG_X86_64 +#define SEV_ES_GPRS_BASE 0x300 +#define SEV_ES_RBX (SEV_ES_GPRS_BASE + __VCPU_REGS_RBX * WORD_SIZE) +#define SEV_ES_RBP (SEV_ES_GPRS_BASE + __VCPU_REGS_RBP * WORD_SIZE) +#define SEV_ES_RSI (SEV_ES_GPRS_BASE + __VCPU_REGS_RSI * WORD_SIZE) +#define SEV_ES_RDI (SEV_ES_GPRS_BASE + __VCPU_REGS_RDI * WORD_SIZE) +#define SEV_ES_R12 (SEV_ES_GPRS_BASE + __VCPU_REGS_R12 * WORD_SIZE) +#define SEV_ES_R13 (SEV_ES_GPRS_BASE + __VCPU_REGS_R13 * WORD_SIZE) +#define SEV_ES_R14 (SEV_ES_GPRS_BASE + __VCPU_REGS_R14 * WORD_SIZE) +#define SEV_ES_R15 (SEV_ES_GPRS_BASE + __VCPU_REGS_R15 * WORD_SIZE) +#endif + /** * __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode * @svm: struct vcpu_svm * * @spec_ctrl_intercepted: bool */ SYM_FUNC_START(__svm_sev_es_vcpu_run) - push %_ASM_BP -#ifdef CONFIG_X86_64 - push %r15 - push %r14 - push %r13 - push %r12 -#else - push %edi - push %esi -#endif - push %_ASM_BX + FRAME_BEGIN /* - * Save variables needed after vmexit on the stack, in inverse - * order compared to when they are needed. + * Save non-volatile (callee-saved) registers to the host save area. + * Except for RAX and RSP, all GPRs are restored on #VMEXIT, but not + * saved on VMRUN. */ + mov %rbp, SEV_ES_RBP (%rdx) + mov %r15, SEV_ES_R15 (%rdx) + mov %r14, SEV_ES_R14 (%rdx) + mov %r13, SEV_ES_R13 (%rdx) + mov %r12, SEV_ES_R12 (%rdx) + mov %rbx, SEV_ES_RBX (%rdx) - /* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */ - push %_ASM_ARG2 - - /* Save @svm. */ - push %_ASM_ARG1 - -.ifnc _ASM_ARG1, _ASM_DI /* - * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX - * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL. + * Save volatile registers that hold arguments that are needed after + * #VMEXIT (RDI=@svm and RSI=@spec_ctrl_intercepted). */ - mov %_ASM_ARG1, %_ASM_DI -.endif + mov %rdi, SEV_ES_RDI (%rdx) + mov %rsi, SEV_ES_RSI (%rdx) - /* Clobbers RAX, RCX, RDX. */ + /* Clobbers RAX, RCX, RDX (@hostsa). */ RESTORE_GUEST_SPEC_CTRL /* Get svm->current_vmcb->pa into RAX. */ - mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX - mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX + mov SVM_current_vmcb(%rdi), %rax + mov KVM_VMCB_pa(%rax), %rax /* Enter guest mode */ sti -1: vmrun %_ASM_AX +1: vmrun %rax 2: cli - /* Pop @svm to RDI, guest registers have been saved already. */ - pop %_ASM_DI - -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif - /* Clobbers RAX, RCX, RDX. */ + /* Clobbers RAX, RCX, RDX, consumes RDI (@svm) and RSI (@spec_ctrl_intercepted). */ RESTORE_HOST_SPEC_CTRL /* @@ -361,30 +365,17 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) */ UNTRAIN_RET_VM - /* "Pop" @spec_ctrl_intercepted. */ - pop %_ASM_BX - - pop %_ASM_BX - -#ifdef CONFIG_X86_64 - pop %r12 - pop %r13 - pop %r14 - pop %r15 -#else - pop %esi - pop %edi -#endif - pop %_ASM_BP + FRAME_END RET RESTORE_GUEST_SPEC_CTRL_BODY - RESTORE_HOST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY %sil -3: cmpb $0, _ASM_RIP(kvm_rebooting) +3: cmpb $0, kvm_rebooting(%rip) jne 2b ud2 _ASM_EXTABLE(1b, 3b) SYM_FUNC_END(__svm_sev_es_vcpu_run) +#endif /* CONFIG_KVM_AMD_SEV */ diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index b82e6ed4f0..c6b4b17280 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -15,20 +15,23 @@ * Tracepoint for guest mode entry. */ TRACE_EVENT(kvm_entry, - TP_PROTO(struct kvm_vcpu *vcpu), - TP_ARGS(vcpu), + TP_PROTO(struct kvm_vcpu *vcpu, bool force_immediate_exit), + TP_ARGS(vcpu, force_immediate_exit), TP_STRUCT__entry( __field( unsigned int, vcpu_id ) __field( unsigned long, rip ) + __field( bool, immediate_exit ) ), TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; __entry->rip = kvm_rip_read(vcpu); + __entry->immediate_exit = force_immediate_exit; ), - TP_printk("vcpu %u, rip 0x%lx", __entry->vcpu_id, __entry->rip) + TP_printk("vcpu %u, rip 0x%lx%s", __entry->vcpu_id, __entry->rip, + __entry->immediate_exit ? "[immediate exit]" : "") ); /* diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 6329a30685..d05ddf7514 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3606,7 +3606,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) return 1; } - kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); + kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED); if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) return nested_vmx_failInvalid(vcpu); @@ -4433,7 +4433,7 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) (vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE); if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS) - kvm_get_dr(vcpu, 7, (unsigned long *)&vmcs12->guest_dr7); + vmcs12->guest_dr7 = vcpu->arch.dr7; if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_IA32_EFER) vmcs12->guest_ia32_efer = vcpu->arch.efer; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 600a021ae9..be40474de6 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -20,53 +20,19 @@ #include "nested.h" #include "pmu.h" -#define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0) - -enum intel_pmu_architectural_events { - /* - * The order of the architectural events matters as support for each - * event is enumerated via CPUID using the index of the event. - */ - INTEL_ARCH_CPU_CYCLES, - INTEL_ARCH_INSTRUCTIONS_RETIRED, - INTEL_ARCH_REFERENCE_CYCLES, - INTEL_ARCH_LLC_REFERENCES, - INTEL_ARCH_LLC_MISSES, - INTEL_ARCH_BRANCHES_RETIRED, - INTEL_ARCH_BRANCHES_MISPREDICTED, - - NR_REAL_INTEL_ARCH_EVENTS, - - /* - * Pseudo-architectural event used to implement IA32_FIXED_CTR2, a.k.a. - * TSC reference cycles. The architectural reference cycles event may - * or may not actually use the TSC as the reference, e.g. might use the - * core crystal clock or the bus clock (yeah, "architectural"). - */ - PSEUDO_ARCH_REFERENCE_CYCLES = NR_REAL_INTEL_ARCH_EVENTS, - NR_INTEL_ARCH_EVENTS, -}; +/* + * Perf's "BASE" is wildly misleading, architectural PMUs use bits 31:16 of ECX + * to encode the "type" of counter to read, i.e. this is not a "base". And to + * further confuse things, non-architectural PMUs use bit 31 as a flag for + * "fast" reads, whereas the "type" is an explicit value. + */ +#define INTEL_RDPMC_GP 0 +#define INTEL_RDPMC_FIXED INTEL_PMC_FIXED_RDPMC_BASE -static struct { - u8 eventsel; - u8 unit_mask; -} const intel_arch_events[] = { - [INTEL_ARCH_CPU_CYCLES] = { 0x3c, 0x00 }, - [INTEL_ARCH_INSTRUCTIONS_RETIRED] = { 0xc0, 0x00 }, - [INTEL_ARCH_REFERENCE_CYCLES] = { 0x3c, 0x01 }, - [INTEL_ARCH_LLC_REFERENCES] = { 0x2e, 0x4f }, - [INTEL_ARCH_LLC_MISSES] = { 0x2e, 0x41 }, - [INTEL_ARCH_BRANCHES_RETIRED] = { 0xc4, 0x00 }, - [INTEL_ARCH_BRANCHES_MISPREDICTED] = { 0xc5, 0x00 }, - [PSEUDO_ARCH_REFERENCE_CYCLES] = { 0x00, 0x03 }, -}; +#define INTEL_RDPMC_TYPE_MASK GENMASK(31, 16) +#define INTEL_RDPMC_INDEX_MASK GENMASK(15, 0) -/* mapping between fixed pmc index and intel_arch_events array */ -static int fixed_pmc_events[] = { - [0] = INTEL_ARCH_INSTRUCTIONS_RETIRED, - [1] = INTEL_ARCH_CPU_CYCLES, - [2] = PSEUDO_ARCH_REFERENCE_CYCLES, -}; +#define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0) static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) { @@ -84,77 +50,61 @@ 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); + __set_bit(KVM_FIXED_PMC_BASE_IDX + i, pmu->pmc_in_use); kvm_pmu_request_counter_reprogram(pmc); } } -static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) -{ - if (pmc_idx < INTEL_PMC_IDX_FIXED) { - return get_gp_pmc(pmu, MSR_P6_EVNTSEL0 + pmc_idx, - MSR_P6_EVNTSEL0); - } else { - u32 idx = pmc_idx - INTEL_PMC_IDX_FIXED; - - return get_fixed_pmc(pmu, idx + MSR_CORE_PERF_FIXED_CTR0); - } -} - -static bool intel_hw_event_available(struct kvm_pmc *pmc) -{ - struct kvm_pmu *pmu = pmc_to_pmu(pmc); - u8 event_select = pmc->eventsel & ARCH_PERFMON_EVENTSEL_EVENT; - u8 unit_mask = (pmc->eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8; - int i; - - BUILD_BUG_ON(ARRAY_SIZE(intel_arch_events) != NR_INTEL_ARCH_EVENTS); - - /* - * Disallow events reported as unavailable in guest CPUID. Note, this - * doesn't apply to pseudo-architectural events. - */ - for (i = 0; i < NR_REAL_INTEL_ARCH_EVENTS; i++) { - if (intel_arch_events[i].eventsel != event_select || - intel_arch_events[i].unit_mask != unit_mask) - continue; - - return pmu->available_event_types & BIT(i); - } - - return true; -} - -static bool intel_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx) -{ - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - bool fixed = idx & (1u << 30); - - idx &= ~(3u << 30); - - return fixed ? idx < pmu->nr_arch_fixed_counters - : idx < pmu->nr_arch_gp_counters; -} - static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, unsigned int idx, u64 *mask) { + unsigned int type = idx & INTEL_RDPMC_TYPE_MASK; struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - bool fixed = idx & (1u << 30); struct kvm_pmc *counters; unsigned int num_counters; + u64 bitmask; + + /* + * The encoding of ECX for RDPMC is different for architectural versus + * non-architecturals PMUs (PMUs with version '0'). For architectural + * PMUs, bits 31:16 specify the PMC type and bits 15:0 specify the PMC + * index. For non-architectural PMUs, bit 31 is a "fast" flag, and + * bits 30:0 specify the PMC index. + * + * Yell and reject attempts to read PMCs for a non-architectural PMU, + * as KVM doesn't support such PMUs. + */ + if (WARN_ON_ONCE(!pmu->version)) + return NULL; - idx &= ~(3u << 30); - if (fixed) { + /* + * General Purpose (GP) PMCs are supported on all PMUs, and fixed PMCs + * are supported on all architectural PMUs, i.e. on all virtual PMUs + * supported by KVM. Note, KVM only emulates fixed PMCs for PMU v2+, + * but the type itself is still valid, i.e. let RDPMC fail due to + * accessing a non-existent counter. Reject attempts to read all other + * types, which are unknown/unsupported. + */ + switch (type) { + case INTEL_RDPMC_FIXED: counters = pmu->fixed_counters; num_counters = pmu->nr_arch_fixed_counters; - } else { + bitmask = pmu->counter_bitmask[KVM_PMC_FIXED]; + break; + case INTEL_RDPMC_GP: counters = pmu->gp_counters; num_counters = pmu->nr_arch_gp_counters; + bitmask = pmu->counter_bitmask[KVM_PMC_GP]; + break; + default: + return NULL; } + + idx &= INTEL_RDPMC_INDEX_MASK; if (idx >= num_counters) return NULL; - *mask &= pmu->counter_bitmask[fixed ? KVM_PMC_FIXED : KVM_PMC_GP]; + + *mask &= bitmask; return &counters[array_index_nospec(idx, num_counters)]; } @@ -464,20 +414,38 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } -static void setup_fixed_pmc_eventsel(struct kvm_pmu *pmu) +/* + * Map fixed counter events to architectural general purpose event encodings. + * Perf doesn't provide APIs to allow KVM to directly program a fixed counter, + * and so KVM instead programs the architectural event to effectively request + * the fixed counter. Perf isn't guaranteed to use a fixed counter and may + * instead program the encoding into a general purpose counter, e.g. if a + * different perf_event is already utilizing the requested counter, but the end + * result is the same (ignoring the fact that using a general purpose counter + * will likely exacerbate counter contention). + * + * Forcibly inlined to allow asserting on @index at build time, and there should + * never be more than one user. + */ +static __always_inline u64 intel_get_fixed_pmc_eventsel(unsigned int index) { - int i; - - BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_events) != KVM_PMC_MAX_FIXED); + const enum perf_hw_id fixed_pmc_perf_ids[] = { + [0] = PERF_COUNT_HW_INSTRUCTIONS, + [1] = PERF_COUNT_HW_CPU_CYCLES, + [2] = PERF_COUNT_HW_REF_CPU_CYCLES, + }; + u64 eventsel; - for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { - int index = array_index_nospec(i, KVM_PMC_MAX_FIXED); - struct kvm_pmc *pmc = &pmu->fixed_counters[index]; - u32 event = fixed_pmc_events[index]; + BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_perf_ids) != KVM_PMC_MAX_FIXED); + BUILD_BUG_ON(index >= KVM_PMC_MAX_FIXED); - pmc->eventsel = (intel_arch_events[event].unit_mask << 8) | - intel_arch_events[event].eventsel; - } + /* + * Yell if perf reports support for a fixed counter but perf doesn't + * have a known encoding for the associated general purpose event. + */ + eventsel = perf_get_hw_event_config(fixed_pmc_perf_ids[index]); + WARN_ON_ONCE(!eventsel && index < kvm_pmu_cap.num_counters_fixed); + return eventsel; } static void intel_pmu_refresh(struct kvm_vcpu *vcpu) @@ -531,13 +499,12 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) kvm_pmu_cap.bit_width_fixed); pmu->counter_bitmask[KVM_PMC_FIXED] = ((u64)1 << edx.split.bit_width_fixed) - 1; - setup_fixed_pmc_eventsel(pmu); } for (i = 0; i < pmu->nr_arch_fixed_counters; i++) pmu->fixed_ctr_ctrl_mask &= ~(0xbull << (i * 4)); counter_mask = ~(((1ull << pmu->nr_arch_gp_counters) - 1) | - (((1ull << pmu->nr_arch_fixed_counters) - 1) << INTEL_PMC_IDX_FIXED)); + (((1ull << pmu->nr_arch_fixed_counters) - 1) << KVM_FIXED_PMC_BASE_IDX)); pmu->global_ctrl_mask = counter_mask; /* @@ -568,7 +535,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) perf_capabilities = vcpu_get_perf_capabilities(vcpu); if (cpuid_model_is_consistent(vcpu) && (perf_capabilities & PMU_CAP_LBR_FMT)) - x86_perf_get_lbr(&lbr_desc->records); + memcpy(&lbr_desc->records, &vmx_lbr_caps, sizeof(vmx_lbr_caps)); else lbr_desc->records.nr = 0; @@ -581,7 +548,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->reserved_bits &= ~ICL_EVENTSEL_ADAPTIVE; for (i = 0; i < pmu->nr_arch_fixed_counters; i++) { pmu->fixed_ctr_ctrl_mask &= - ~(1ULL << (INTEL_PMC_IDX_FIXED + i * 4)); + ~(1ULL << (KVM_FIXED_PMC_BASE_IDX + i * 4)); } pmu->pebs_data_cfg_mask = ~0xff00000full; } else { @@ -607,8 +574,9 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu) for (i = 0; i < KVM_PMC_MAX_FIXED; i++) { pmu->fixed_counters[i].type = KVM_PMC_FIXED; pmu->fixed_counters[i].vcpu = vcpu; - pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED; + pmu->fixed_counters[i].idx = i + KVM_FIXED_PMC_BASE_IDX; pmu->fixed_counters[i].current_config = 0; + pmu->fixed_counters[i].eventsel = intel_get_fixed_pmc_eventsel(i); } lbr_desc->records.nr = 0; @@ -736,11 +704,8 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu) struct kvm_pmc *pmc = NULL; int bit, hw_idx; - for_each_set_bit(bit, (unsigned long *)&pmu->global_ctrl, - X86_PMC_IDX_MAX) { - pmc = intel_pmc_idx_to_pmc(pmu, bit); - - if (!pmc || !pmc_speculative_in_use(pmc) || + kvm_for_each_pmc(pmu, pmc, bit, (unsigned long *)&pmu->global_ctrl) { + if (!pmc_speculative_in_use(pmc) || !pmc_is_globally_enabled(pmc) || !pmc->perf_event) continue; @@ -755,11 +720,8 @@ void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu) } struct kvm_pmu_ops intel_pmu_ops __initdata = { - .hw_event_available = intel_hw_event_available, - .pmc_idx_to_pmc = intel_pmc_idx_to_pmc, .rdpmc_ecx_to_pmc = intel_rdpmc_ecx_to_pmc, .msr_idx_to_pmc = intel_msr_idx_to_pmc, - .is_valid_rdpmc_ecx = intel_is_valid_rdpmc_ecx, .is_valid_msr = intel_is_valid_msr, .get_msr = intel_pmu_get_msr, .set_msr = intel_pmu_set_msr, diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 784f2ecca5..22411f4aff 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -38,6 +38,7 @@ #include <asm/desc.h> #include <asm/fpu/api.h> #include <asm/fpu/xstate.h> +#include <asm/fred.h> #include <asm/idtentry.h> #include <asm/io.h> #include <asm/irq_remapping.h> @@ -49,6 +50,8 @@ #include <asm/spec-ctrl.h> #include <asm/vmx.h> +#include <trace/events/ipi.h> + #include "capabilities.h" #include "cpuid.h" #include "hyperv.h" @@ -159,7 +162,7 @@ module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); /* * List of MSRs that can be directly passed to the guest. - * In addition to these x2apic and PT MSRs are handled specially. + * In addition to these x2apic, PT and LBR MSRs are handled specially. */ static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = { MSR_IA32_SPEC_CTRL, @@ -215,6 +218,8 @@ module_param(ple_window_max, uint, 0444); int __read_mostly pt_mode = PT_MODE_SYSTEM; module_param(pt_mode, int, S_IRUGO); +struct x86_pmu_lbr __ro_after_init vmx_lbr_caps; + static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); static DEFINE_MUTEX(vmx_l1d_flush_mutex); @@ -667,25 +672,14 @@ static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu) return flexpriority_enabled && lapic_in_kernel(vcpu); } -static int possible_passthrough_msr_slot(u32 msr) -{ - u32 i; - - for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) - if (vmx_possible_passthrough_msrs[i] == msr) - return i; - - return -ENOENT; -} - -static bool is_valid_passthrough_msr(u32 msr) +static int vmx_get_passthrough_msr_slot(u32 msr) { - bool r; + int i; switch (msr) { case 0x800 ... 0x8ff: /* x2APIC MSRs. These are handled in vmx_update_msr_bitmap_x2apic() */ - return true; + return -ENOENT; case MSR_IA32_RTIT_STATUS: case MSR_IA32_RTIT_OUTPUT_BASE: case MSR_IA32_RTIT_OUTPUT_MASK: @@ -700,14 +694,16 @@ static bool is_valid_passthrough_msr(u32 msr) case MSR_LBR_CORE_FROM ... MSR_LBR_CORE_FROM + 8: case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8: /* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */ - return true; + return -ENOENT; } - r = possible_passthrough_msr_slot(msr) != -ENOENT; - - WARN(!r, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr); + for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) { + if (vmx_possible_passthrough_msrs[i] == msr) + return i; + } - return r; + WARN(1, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr); + return -ENOENT; } struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr) @@ -1290,8 +1286,6 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu) u16 fs_sel, gs_sel; int i; - vmx->req_immediate_exit = false; - /* * Note that guest MSRs to be saved/restored can also be changed * when guest state is loaded. This happens when guest transitions @@ -3963,6 +3957,7 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + int idx; if (!cpu_has_vmx_msr_bitmap()) return; @@ -3972,16 +3967,13 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) /* * Mark the desired intercept state in shadow bitmap, this is needed * for resync when the MSR filters change. - */ - if (is_valid_passthrough_msr(msr)) { - int idx = possible_passthrough_msr_slot(msr); - - if (idx != -ENOENT) { - if (type & MSR_TYPE_R) - clear_bit(idx, vmx->shadow_msr_intercept.read); - if (type & MSR_TYPE_W) - clear_bit(idx, vmx->shadow_msr_intercept.write); - } + */ + idx = vmx_get_passthrough_msr_slot(msr); + if (idx >= 0) { + if (type & MSR_TYPE_R) + clear_bit(idx, vmx->shadow_msr_intercept.read); + if (type & MSR_TYPE_W) + clear_bit(idx, vmx->shadow_msr_intercept.write); } if ((type & MSR_TYPE_R) && @@ -4007,6 +3999,7 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap; + int idx; if (!cpu_has_vmx_msr_bitmap()) return; @@ -4016,16 +4009,13 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type) /* * Mark the desired intercept state in shadow bitmap, this is needed * for resync when the MSR filter changes. - */ - if (is_valid_passthrough_msr(msr)) { - int idx = possible_passthrough_msr_slot(msr); - - if (idx != -ENOENT) { - if (type & MSR_TYPE_R) - set_bit(idx, vmx->shadow_msr_intercept.read); - if (type & MSR_TYPE_W) - set_bit(idx, vmx->shadow_msr_intercept.write); - } + */ + idx = vmx_get_passthrough_msr_slot(msr); + if (idx >= 0) { + if (type & MSR_TYPE_R) + set_bit(idx, vmx->shadow_msr_intercept.read); + if (type & MSR_TYPE_W) + set_bit(idx, vmx->shadow_msr_intercept.write); } if (type & MSR_TYPE_R) @@ -4136,6 +4126,9 @@ static void vmx_msr_filter_changed(struct kvm_vcpu *vcpu) struct vcpu_vmx *vmx = to_vmx(vcpu); u32 i; + if (!cpu_has_vmx_msr_bitmap()) + return; + /* * Redo intercept permissions for MSRs that KVM is passing through to * the guest. Disabling interception will check the new MSR filter and @@ -5575,10 +5568,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) reg = DEBUG_REG_ACCESS_REG(exit_qualification); if (exit_qualification & TYPE_MOV_FROM_DR) { - unsigned long val; - - kvm_get_dr(vcpu, dr, &val); - kvm_register_write(vcpu, reg, val); + kvm_register_write(vcpu, reg, kvm_get_dr(vcpu, dr)); err = 0; } else { err = kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg)); @@ -6000,22 +5990,46 @@ static int handle_pml_full(struct kvm_vcpu *vcpu) return 1; } -static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu) +static fastpath_t handle_fastpath_preemption_timer(struct kvm_vcpu *vcpu, + bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!vmx->req_immediate_exit && - !unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) { - kvm_lapic_expired_hv_timer(vcpu); + /* + * In the *extremely* unlikely scenario that this is a spurious VM-Exit + * due to the timer expiring while it was "soft" disabled, just eat the + * exit and re-enter the guest. + */ + if (unlikely(vmx->loaded_vmcs->hv_timer_soft_disabled)) return EXIT_FASTPATH_REENTER_GUEST; - } - return EXIT_FASTPATH_NONE; + /* + * If the timer expired because KVM used it to force an immediate exit, + * then mission accomplished. + */ + if (force_immediate_exit) + return EXIT_FASTPATH_EXIT_HANDLED; + + /* + * If L2 is active, go down the slow path as emulating the guest timer + * expiration likely requires synthesizing a nested VM-Exit. + */ + if (is_guest_mode(vcpu)) + return EXIT_FASTPATH_NONE; + + kvm_lapic_expired_hv_timer(vcpu); + return EXIT_FASTPATH_REENTER_GUEST; } static int handle_preemption_timer(struct kvm_vcpu *vcpu) { - handle_fastpath_preemption_timer(vcpu); + /* + * This non-fastpath handler is reached if and only if the preemption + * timer was being used to emulate a guest timer while L2 is active. + * All other scenarios are supposed to be handled in the fastpath. + */ + WARN_ON_ONCE(!is_guest_mode(vcpu)); + kvm_lapic_expired_hv_timer(vcpu); return 1; } @@ -6518,7 +6532,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; vcpu->run->internal.data[0] = vectoring_info; vcpu->run->internal.data[1] = exit_reason.full; - vcpu->run->internal.data[2] = vcpu->arch.exit_qualification; + vcpu->run->internal.data[2] = vmx_get_exit_qual(vcpu); if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { vcpu->run->internal.data[ndata++] = vmcs_read64(GUEST_PHYSICAL_ADDRESS); @@ -6552,7 +6566,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) if (exit_reason.basic >= kvm_vmx_max_exit_handlers) goto unexpected_vmexit; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE if (exit_reason.basic == EXIT_REASON_MSR_WRITE) return kvm_emulate_wrmsr(vcpu); else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER) @@ -6969,14 +6983,16 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu) { u32 intr_info = vmx_get_intr_info(vcpu); unsigned int vector = intr_info & INTR_INFO_VECTOR_MASK; - gate_desc *desc = (gate_desc *)host_idt_base + vector; if (KVM_BUG(!is_external_intr(intr_info), vcpu->kvm, "unexpected VM-Exit interrupt info: 0x%x", intr_info)) return; kvm_before_interrupt(vcpu, KVM_HANDLING_IRQ); - vmx_do_interrupt_irqoff(gate_offset(desc)); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + fred_entry_from_kvm(EVENT_TYPE_EXTINT, vector); + else + vmx_do_interrupt_irqoff(gate_offset((gate_desc *)host_idt_base + vector)); kvm_after_interrupt(vcpu); vcpu->arch.at_instruction_boundary = true; @@ -7155,13 +7171,13 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx) msrs[i].host, false); } -static void vmx_update_hv_timer(struct kvm_vcpu *vcpu) +static void vmx_update_hv_timer(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); u64 tscl; u32 delta_tsc; - if (vmx->req_immediate_exit) { + if (force_immediate_exit) { vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, 0); vmx->loaded_vmcs->hv_timer_soft_disabled = false; } else if (vmx->hv_deadline_tsc != -1) { @@ -7214,13 +7230,22 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx, barrier_nospec(); } -static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu) +static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu, + bool force_immediate_exit) { + /* + * If L2 is active, some VMX preemption timer exits can be handled in + * the fastpath even, all other exits must use the slow path. + */ + if (is_guest_mode(vcpu) && + to_vmx(vcpu)->exit_reason.basic != EXIT_REASON_PREEMPTION_TIMER) + return EXIT_FASTPATH_NONE; + switch (to_vmx(vcpu)->exit_reason.basic) { case EXIT_REASON_MSR_WRITE: return handle_fastpath_set_msr_irqoff(vcpu); case EXIT_REASON_PREEMPTION_TIMER: - return handle_fastpath_preemption_timer(vcpu); + return handle_fastpath_preemption_timer(vcpu, force_immediate_exit); default: return EXIT_FASTPATH_NONE; } @@ -7272,7 +7297,10 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu, if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI && is_nmi(vmx_get_intr_info(vcpu))) { kvm_before_interrupt(vcpu, KVM_HANDLING_NMI); - vmx_do_nmi_irqoff(); + if (cpu_feature_enabled(X86_FEATURE_FRED)) + fred_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR); + else + vmx_do_nmi_irqoff(); kvm_after_interrupt(vcpu); } @@ -7280,7 +7308,7 @@ out: guest_state_exit_irqoff(); } -static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) +static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit) { struct vcpu_vmx *vmx = to_vmx(vcpu); unsigned long cr3, cr4; @@ -7307,7 +7335,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) return EXIT_FASTPATH_NONE; } - trace_kvm_entry(vcpu); + trace_kvm_entry(vcpu, force_immediate_exit); if (vmx->ple_window_dirty) { vmx->ple_window_dirty = false; @@ -7366,7 +7394,9 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_passthrough_lbr_msrs(vcpu); if (enable_preemption_timer) - vmx_update_hv_timer(vcpu); + vmx_update_hv_timer(vcpu, force_immediate_exit); + else if (force_immediate_exit) + smp_send_reschedule(vcpu->cpu); kvm_wait_lapic_expire(vcpu); @@ -7430,10 +7460,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_recover_nmi_blocking(vmx); vmx_complete_interrupts(vmx); - if (is_guest_mode(vcpu)) - return EXIT_FASTPATH_NONE; - - return vmx_exit_handlers_fastpath(vcpu); + return vmx_exit_handlers_fastpath(vcpu, force_immediate_exit); } static void vmx_vcpu_free(struct kvm_vcpu *vcpu) @@ -7837,10 +7864,9 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_update_exception_bitmap(vcpu); } -static u64 vmx_get_perf_capabilities(void) +static __init 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) @@ -7850,8 +7876,16 @@ static u64 vmx_get_perf_capabilities(void) rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) { - x86_perf_get_lbr(&lbr); - if (lbr.nr) + x86_perf_get_lbr(&vmx_lbr_caps); + + /* + * KVM requires LBR callstack support, as the overhead due to + * context switching LBRs without said support is too high. + * See intel_pmu_create_guest_lbr_event() for more info. + */ + if (!vmx_lbr_caps.has_callstack) + memset(&vmx_lbr_caps, 0, sizeof(vmx_lbr_caps)); + else if (vmx_lbr_caps.nr) perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; } @@ -7933,11 +7967,6 @@ static __init void vmx_set_cpu_caps(void) kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG); } -static void vmx_request_immediate_exit(struct kvm_vcpu *vcpu) -{ - to_vmx(vcpu)->req_immediate_exit = true; -} - static int vmx_check_intercept_io(struct kvm_vcpu *vcpu, struct x86_instruction_info *info) { @@ -8390,8 +8419,6 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .check_intercept = vmx_check_intercept, .handle_exit_irqoff = vmx_handle_exit_irqoff, - .request_immediate_exit = vmx_request_immediate_exit, - .sched_in = vmx_sched_in, .cpu_dirty_log_size = PML_ENTITY_NUM, @@ -8651,7 +8678,6 @@ static __init int hardware_setup(void) if (!enable_preemption_timer) { vmx_x86_ops.set_hv_timer = NULL; vmx_x86_ops.cancel_hv_timer = NULL; - vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit; } kvm_caps.supported_mce_cap |= MCG_LMCE_P; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index e3b0985bb7..90f9e44346 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -15,6 +15,7 @@ #include "vmx_ops.h" #include "../cpuid.h" #include "run_flags.h" +#include "../mmu.h" #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 @@ -109,6 +110,8 @@ struct lbr_desc { bool msr_passthrough; }; +extern struct x86_pmu_lbr vmx_lbr_caps; + /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -332,8 +335,6 @@ struct vcpu_vmx { unsigned int ple_window; bool ple_window_dirty; - bool req_immediate_exit; - /* Support for PML */ #define PML_ENTITY_NUM 512 struct page *pml_pg; @@ -721,7 +722,8 @@ static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu) if (!enable_ept) return true; - return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; + return allow_smaller_maxphyaddr && + cpuid_maxphyaddr(vcpu) < kvm_get_shadow_phys_bits(); } static inline bool is_unrestricted_guest(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c84927216f..4dbd9d99f9 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1399,22 +1399,19 @@ int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val) } EXPORT_SYMBOL_GPL(kvm_set_dr); -void kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val) +unsigned long kvm_get_dr(struct kvm_vcpu *vcpu, int dr) { size_t size = ARRAY_SIZE(vcpu->arch.db); switch (dr) { case 0 ... 3: - *val = vcpu->arch.db[array_index_nospec(dr, size)]; - break; + return vcpu->arch.db[array_index_nospec(dr, size)]; case 4: case 6: - *val = vcpu->arch.dr6; - break; + return vcpu->arch.dr6; case 5: default: /* 7 */ - *val = vcpu->arch.dr7; - break; + return vcpu->arch.dr7; } } EXPORT_SYMBOL_GPL(kvm_get_dr); @@ -2860,7 +2857,11 @@ static inline u64 vgettsc(struct pvclock_clock *clock, u64 *tsc_timestamp, return v * clock->mult; } -static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp) +/* + * As with get_kvmclock_base_ns(), this counts from boot time, at the + * frequency of CLOCK_MONOTONIC_RAW (hence adding gtos->offs_boot). + */ +static int do_kvmclock_base(s64 *t, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; unsigned long seq; @@ -2879,6 +2880,29 @@ static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp) return mode; } +/* + * This calculates CLOCK_MONOTONIC at the time of the TSC snapshot, with + * no boot time offset. + */ +static int do_monotonic(s64 *t, u64 *tsc_timestamp) +{ + struct pvclock_gtod_data *gtod = &pvclock_gtod_data; + unsigned long seq; + int mode; + u64 ns; + + do { + seq = read_seqcount_begin(>od->seq); + ns = gtod->clock.base_cycles; + ns += vgettsc(>od->clock, tsc_timestamp, &mode); + ns >>= gtod->clock.shift; + ns += ktime_to_ns(gtod->clock.offset); + } while (unlikely(read_seqcount_retry(>od->seq, seq))); + *t = ns; + + return mode; +} + static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) { struct pvclock_gtod_data *gtod = &pvclock_gtod_data; @@ -2900,18 +2924,42 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) return mode; } -/* returns true if host is using TSC based clocksource */ +/* + * Calculates the kvmclock_base_ns (CLOCK_MONOTONIC_RAW + boot time) and + * reports the TSC value from which it do so. Returns true if host is + * using TSC based clocksource. + */ static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) { /* checked again under seqlock below */ if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) return false; - return gtod_is_based_on_tsc(do_monotonic_raw(kernel_ns, - tsc_timestamp)); + return gtod_is_based_on_tsc(do_kvmclock_base(kernel_ns, + tsc_timestamp)); +} + +/* + * Calculates CLOCK_MONOTONIC and reports the TSC value from which it did + * so. Returns true if host is using TSC based clocksource. + */ +bool kvm_get_monotonic_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp) +{ + /* checked again under seqlock below */ + if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode)) + return false; + + return gtod_is_based_on_tsc(do_monotonic(kernel_ns, + tsc_timestamp)); } -/* returns true if host is using TSC based clocksource */ +/* + * Calculates CLOCK_REALTIME and reports the TSC value from which it did + * so. Returns true if host is using TSC based clocksource. + * + * DO NOT USE this for anything related to migration. You want CLOCK_TAI + * for that. + */ static bool kvm_get_walltime_and_clockread(struct timespec64 *ts, u64 *tsc_timestamp) { @@ -3158,7 +3206,7 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, guest_hv_clock->version = ++vcpu->hv_clock.version; - mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT); + kvm_gpc_mark_dirty_in_slot(gpc); read_unlock_irqrestore(&gpc->lock, flags); trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock); @@ -4680,7 +4728,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) KVM_XEN_HVM_CONFIG_SHARED_INFO | KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | KVM_XEN_HVM_CONFIG_EVTCHN_SEND | - KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE | + KVM_XEN_HVM_CONFIG_SHARED_INFO_HVA; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE | KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG; @@ -5064,8 +5113,7 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu) int idx; if (vcpu->preempted) { - if (!vcpu->arch.guest_state_protected) - vcpu->arch.preempted_in_kernel = !static_call(kvm_x86_get_cpl)(vcpu); + vcpu->arch.preempted_in_kernel = kvm_arch_vcpu_in_kernel(vcpu); /* * Take the srcu lock as memslots will be accessed to check the gfn @@ -5512,18 +5560,23 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, struct kvm_debugregs *dbgregs) { - unsigned long val; + unsigned int i; memset(dbgregs, 0, sizeof(*dbgregs)); - memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); - kvm_get_dr(vcpu, 6, &val); - dbgregs->dr6 = val; + + BUILD_BUG_ON(ARRAY_SIZE(vcpu->arch.db) != ARRAY_SIZE(dbgregs->db)); + for (i = 0; i < ARRAY_SIZE(vcpu->arch.db); i++) + dbgregs->db[i] = vcpu->arch.db[i]; + + dbgregs->dr6 = vcpu->arch.dr6; dbgregs->dr7 = vcpu->arch.dr7; } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, struct kvm_debugregs *dbgregs) { + unsigned int i; + if (dbgregs->flags) return -EINVAL; @@ -5532,7 +5585,9 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, if (!kvm_dr7_valid(dbgregs->dr7)) return -EINVAL; - memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db)); + for (i = 0; i < ARRAY_SIZE(vcpu->arch.db); i++) + vcpu->arch.db[i] = dbgregs->db[i]; + kvm_update_dr0123(vcpu); vcpu->arch.dr6 = dbgregs->dr6; vcpu->arch.dr7 = dbgregs->dr7; @@ -8180,10 +8235,9 @@ static void emulator_wbinvd(struct x86_emulate_ctxt *ctxt) kvm_emulate_wbinvd_noskip(emul_to_vcpu(ctxt)); } -static void emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, - unsigned long *dest) +static unsigned long emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr) { - kvm_get_dr(emul_to_vcpu(ctxt), dr, dest); + return kvm_get_dr(emul_to_vcpu(ctxt), dr); } static int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, @@ -8405,12 +8459,9 @@ static int emulator_get_msr(struct x86_emulate_ctxt *ctxt, return kvm_get_msr(emul_to_vcpu(ctxt), msr_index, pdata); } -static int emulator_check_pmc(struct x86_emulate_ctxt *ctxt, - u32 pmc) +static int emulator_check_rdpmc_early(struct x86_emulate_ctxt *ctxt, u32 pmc) { - if (kvm_pmu_is_valid_rdpmc_ecx(emul_to_vcpu(ctxt), pmc)) - return 0; - return -EINVAL; + return kvm_pmu_check_rdpmc_early(emul_to_vcpu(ctxt), pmc); } static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt, @@ -8542,7 +8593,7 @@ static const struct x86_emulate_ops emulate_ops = { .set_msr_with_filter = emulator_set_msr_with_filter, .get_msr_with_filter = emulator_get_msr_with_filter, .get_msr = emulator_get_msr, - .check_pmc = emulator_check_pmc, + .check_rdpmc_early = emulator_check_rdpmc_early, .read_pmc = emulator_read_pmc, .halt = emulator_halt, .wbinvd = emulator_wbinvd, @@ -8803,31 +8854,24 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, kvm_release_pfn_clean(pfn); - /* The instructions are well-emulated on direct mmu. */ - if (vcpu->arch.mmu->root_role.direct) { - unsigned int indirect_shadow_pages; - - write_lock(&vcpu->kvm->mmu_lock); - indirect_shadow_pages = vcpu->kvm->arch.indirect_shadow_pages; - write_unlock(&vcpu->kvm->mmu_lock); - - if (indirect_shadow_pages) - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); - - return true; - } - /* - * if emulation was due to access to shadowed page table - * and it failed try to unshadow page and re-enter the - * guest to let CPU execute the instruction. + * If emulation may have been triggered by a write to a shadowed page + * table, unprotect the gfn (zap any relevant SPTEs) and re-enter the + * guest to let the CPU re-execute the instruction in the hope that the + * CPU can cleanly execute the instruction that KVM failed to emulate. */ - kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); + if (vcpu->kvm->arch.indirect_shadow_pages) + kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa)); /* - * If the access faults on its page table, it can not - * be fixed by unprotecting shadow page and it should - * be reported to userspace. + * If the failed instruction faulted on an access to page tables that + * are used to translate any part of the instruction, KVM can't resolve + * the issue by unprotecting the gfn, as zapping the shadow page will + * result in the instruction taking a !PRESENT page fault and thus put + * the vCPU into an infinite loop of page faults. E.g. KVM will create + * a SPTE and write-protect the gfn to resolve the !PRESENT fault, and + * then zap the SPTE to unprotect the gfn, and then do it all over + * again. Report the error to userspace. */ return !(emulation_type & EMULTYPE_WRITE_PF_TO_SP); } @@ -8922,7 +8966,7 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu) if (unlikely(!r)) return 0; - kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS); + kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.INSTRUCTIONS_RETIRED); /* * rflags is the old, "raw" value of the flags. The new value has @@ -9235,9 +9279,9 @@ writeback: */ if (!ctxt->have_exception || exception_type(ctxt->exception.vector) == EXCPT_TRAP) { - kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_INSTRUCTIONS); + kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.INSTRUCTIONS_RETIRED); if (ctxt->is_branch) - kvm_pmu_trigger_event(vcpu, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); + kvm_pmu_trigger_event(vcpu, kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED); kvm_rip_write(vcpu, ctxt->eip); if (r && (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP))) r = kvm_vcpu_do_singlestep(vcpu); @@ -9648,11 +9692,13 @@ static void kvm_x86_check_cpu_compat(void *ret) *(int *)ret = kvm_x86_check_processor_compatibility(); } -static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) +int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) { u64 host_pat; int r, cpu; + guard(mutex)(&vendor_module_lock); + if (kvm_x86_ops.hardware_enable) { pr_err("already loaded vendor module '%s'\n", kvm_x86_ops.name); return -EEXIST; @@ -9782,17 +9828,6 @@ out_free_x86_emulator_cache: kmem_cache_destroy(x86_emulator_cache); return r; } - -int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) -{ - int r; - - mutex_lock(&vendor_module_lock); - r = __kvm_x86_vendor_init(ops); - mutex_unlock(&vendor_module_lock); - - return r; -} EXPORT_SYMBOL_GPL(kvm_x86_vendor_init); void kvm_x86_vendor_exit(void) @@ -10642,13 +10677,12 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256); + static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); + if (irqchip_split(vcpu->kvm)) kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors); - else { - static_call_cond(kvm_x86_sync_pir_to_irr)(vcpu); - if (ioapic_in_kernel(vcpu->kvm)) - kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); - } + else if (ioapic_in_kernel(vcpu->kvm)) + kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors); if (is_guest_mode(vcpu)) vcpu->arch.load_eoi_exitmap_pending = true; @@ -10689,12 +10723,6 @@ static void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) static_call_cond(kvm_x86_set_apic_access_page_addr)(vcpu); } -void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu) -{ - smp_send_reschedule(vcpu->cpu); -} -EXPORT_SYMBOL_GPL(__kvm_request_immediate_exit); - /* * Called within kvm->srcu read side. * Returns 1 to let vcpu_run() continue the guest execution loop without @@ -10944,10 +10972,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) goto cancel_injection; } - if (req_immediate_exit) { + if (req_immediate_exit) kvm_make_request(KVM_REQ_EVENT, vcpu); - static_call(kvm_x86_request_immediate_exit)(vcpu); - } fpregs_assert_state_consistent(); if (test_thread_flag(TIF_NEED_FPU_LOAD)) @@ -10978,7 +11004,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) && (kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED)); - exit_fastpath = static_call(kvm_x86_vcpu_run)(vcpu); + exit_fastpath = static_call(kvm_x86_vcpu_run)(vcpu, req_immediate_exit); if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST)) break; @@ -12065,7 +12091,7 @@ 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, vcpu->kvm, vcpu, KVM_HOST_USES_PFN); + kvm_gpc_init(&vcpu->arch.pv_time, vcpu->kvm); if (!irqchip_in_kernel(vcpu->kvm) || kvm_vcpu_is_reset_bsp(vcpu)) vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE; @@ -12076,27 +12102,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) if (r < 0) return r; - if (irqchip_in_kernel(vcpu->kvm)) { - r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); - if (r < 0) - goto fail_mmu_destroy; - - /* - * Defer evaluating inhibits until the vCPU is first run, as - * this vCPU will not get notified of any changes until this - * vCPU is visible to other vCPUs (marked online and added to - * the set of vCPUs). Opportunistically mark APICv active as - * VMX in particularly is highly unlikely to have inhibits. - * Ignore the current per-VM APICv state so that vCPU creation - * is guaranteed to run with a deterministic value, the request - * will ensure the vCPU gets the correct state before VM-Entry. - */ - if (enable_apicv) { - vcpu->arch.apic->apicv_active = true; - kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); - } - } else - static_branch_inc(&kvm_has_noapic_vcpu); + r = kvm_create_lapic(vcpu, lapic_timer_advance_ns); + if (r < 0) + goto fail_mmu_destroy; r = -ENOMEM; @@ -12217,8 +12225,6 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu) srcu_read_unlock(&vcpu->kvm->srcu, idx); free_page((unsigned long)vcpu->arch.pio_data); kvfree(vcpu->arch.cpuid_entries); - if (!lapic_in_kernel(vcpu)) - static_branch_dec(&kvm_has_noapic_vcpu); } void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) @@ -12495,9 +12501,6 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu) return (vcpu->arch.apic_base & MSR_IA32_APICBASE_BSP) != 0; } -__read_mostly DEFINE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu); -EXPORT_SYMBOL_GPL(kvm_has_noapic_vcpu); - void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); @@ -13100,11 +13103,13 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu) bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) { - if (kvm_vcpu_apicv_active(vcpu) && - static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu)) - return true; + return kvm_vcpu_apicv_active(vcpu) && + static_call(kvm_x86_dy_apicv_has_pending_interrupt)(vcpu); +} - return false; +bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.preempted_in_kernel; } bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) @@ -13127,9 +13132,6 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) if (vcpu->arch.guest_state_protected) return true; - if (vcpu != kvm_get_running_vcpu()) - return vcpu->arch.preempted_in_kernel; - return static_call(kvm_x86_get_cpl)(vcpu) == 0; } @@ -13924,9 +13926,6 @@ module_init(kvm_x86_init); static void __exit kvm_x86_exit(void) { - /* - * If module_init() is implemented, module_exit() must also be - * implemented to allow module unload. - */ + WARN_ON_ONCE(static_branch_unlikely(&kvm_has_noapic_vcpu)); } module_exit(kvm_x86_exit); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 2f7e191666..a8b7180377 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -294,6 +294,7 @@ void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip); u64 get_kvmclock_ns(struct kvm *kvm); uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm); +bool kvm_get_monotonic_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp); int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, @@ -431,12 +432,6 @@ static inline bool kvm_notify_vmexit_enabled(struct kvm *kvm) return kvm->arch.notify_vmexit_flags & KVM_X86_NOTIFY_VMEXIT_ENABLED; } -enum kvm_intr_type { - /* Values are arbitrary, but must be non-zero. */ - KVM_HANDLING_IRQ = 1, - KVM_HANDLING_NMI, -}; - static __always_inline void kvm_before_interrupt(struct kvm_vcpu *vcpu, enum kvm_intr_type intr) { diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index b0212ba2d8..f65b35a05d 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -10,7 +10,7 @@ #include "x86.h" #include "xen.h" #include "hyperv.h" -#include "lapic.h" +#include "irq.h" #include <linux/eventfd.h> #include <linux/kvm_host.h> @@ -24,6 +24,7 @@ #include <xen/interface/sched.h> #include <asm/xen/cpuid.h> +#include <asm/pvclock.h> #include "cpuid.h" #include "trace.h" @@ -34,41 +35,32 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r); DEFINE_STATIC_KEY_DEFERRED_FALSE(kvm_xen_enabled, HZ); -static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) +static int kvm_xen_shared_info_init(struct kvm *kvm) { struct gfn_to_pfn_cache *gpc = &kvm->arch.xen.shinfo_cache; struct pvclock_wall_clock *wc; - gpa_t gpa = gfn_to_gpa(gfn); u32 *wc_sec_hi; u32 wc_version; u64 wall_nsec; int ret = 0; int idx = srcu_read_lock(&kvm->srcu); - if (gfn == KVM_XEN_INVALID_GFN) { - kvm_gpc_deactivate(gpc); - goto out; - } + read_lock_irq(&gpc->lock); + while (!kvm_gpc_check(gpc, PAGE_SIZE)) { + read_unlock_irq(&gpc->lock); - do { - ret = kvm_gpc_activate(gpc, gpa, PAGE_SIZE); + ret = kvm_gpc_refresh(gpc, PAGE_SIZE); if (ret) goto out; - /* - * This code mirrors kvm_write_wall_clock() except that it writes - * directly through the pfn cache and doesn't mark the page dirty. - */ - wall_nsec = kvm_get_wall_clock_epoch(kvm); - - /* It could be invalid again already, so we need to check */ read_lock_irq(&gpc->lock); + } - if (gpc->valid) - break; - - read_unlock_irq(&gpc->lock); - } while (1); + /* + * This code mirrors kvm_write_wall_clock() except that it writes + * directly through the pfn cache and doesn't mark the page dirty. + */ + wall_nsec = kvm_get_wall_clock_epoch(kvm); /* Paranoia checks on the 32-bit struct layout */ BUILD_BUG_ON(offsetof(struct compat_shared_info, wc) != 0x900); @@ -158,8 +150,93 @@ static enum hrtimer_restart xen_timer_callback(struct hrtimer *timer) return HRTIMER_NORESTART; } -static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs, s64 delta_ns) +static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs, + bool linux_wa) { + int64_t kernel_now, delta; + uint64_t guest_now; + + /* + * The guest provides the requested timeout in absolute nanoseconds + * of the KVM clock — as *it* sees it, based on the scaled TSC and + * the pvclock information provided by KVM. + * + * The kernel doesn't support hrtimers based on CLOCK_MONOTONIC_RAW + * so use CLOCK_MONOTONIC. In the timescales covered by timers, the + * difference won't matter much as there is no cumulative effect. + * + * Calculate the time for some arbitrary point in time around "now" + * in terms of both kvmclock and CLOCK_MONOTONIC. Calculate the + * delta between the kvmclock "now" value and the guest's requested + * timeout, apply the "Linux workaround" described below, and add + * the resulting delta to the CLOCK_MONOTONIC "now" value, to get + * the absolute CLOCK_MONOTONIC time at which the timer should + * fire. + */ + if (vcpu->arch.hv_clock.version && vcpu->kvm->arch.use_master_clock && + static_cpu_has(X86_FEATURE_CONSTANT_TSC)) { + uint64_t host_tsc, guest_tsc; + + if (!IS_ENABLED(CONFIG_64BIT) || + !kvm_get_monotonic_and_clockread(&kernel_now, &host_tsc)) { + /* + * Don't fall back to get_kvmclock_ns() because it's + * broken; it has a systemic error in its results + * because it scales directly from host TSC to + * nanoseconds, and doesn't scale first to guest TSC + * and *then* to nanoseconds as the guest does. + * + * There is a small error introduced here because time + * continues to elapse between the ktime_get() and the + * subsequent rdtsc(). But not the systemic drift due + * to get_kvmclock_ns(). + */ + kernel_now = ktime_get(); /* This is CLOCK_MONOTONIC */ + host_tsc = rdtsc(); + } + + /* Calculate the guest kvmclock as the guest would do it. */ + guest_tsc = kvm_read_l1_tsc(vcpu, host_tsc); + guest_now = __pvclock_read_cycles(&vcpu->arch.hv_clock, + guest_tsc); + } else { + /* + * Without CONSTANT_TSC, get_kvmclock_ns() is the only option. + * + * Also if the guest PV clock hasn't been set up yet, as is + * likely to be the case during migration when the vCPU has + * not been run yet. It would be possible to calculate the + * scaling factors properly in that case but there's not much + * point in doing so. The get_kvmclock_ns() drift accumulates + * over time, so it's OK to use it at startup. Besides, on + * migration there's going to be a little bit of skew in the + * precise moment at which timers fire anyway. Often they'll + * be in the "past" by the time the VM is running again after + * migration. + */ + guest_now = get_kvmclock_ns(vcpu->kvm); + kernel_now = ktime_get(); + } + + delta = guest_abs - guest_now; + + /* + * Xen has a 'Linux workaround' in do_set_timer_op() which checks for + * negative absolute timeout values (caused by integer overflow), and + * for values about 13 days in the future (2^50ns) which would be + * caused by jiffies overflow. For those cases, Xen sets the timeout + * 100ms in the future (not *too* soon, since if a guest really did + * set a long timeout on purpose we don't want to keep churning CPU + * time by waking it up). Emulate Xen's workaround when starting the + * timer in response to __HYPERVISOR_set_timer_op. + */ + if (linux_wa && + unlikely((int64_t)guest_abs < 0 || + (delta > 0 && (uint32_t) (delta >> 50) != 0))) { + delta = 100 * NSEC_PER_MSEC; + guest_abs = guest_now + delta; + } + /* * Avoid races with the old timer firing. Checking timer_expires * to avoid calling hrtimer_cancel() will only have false positives @@ -171,14 +248,12 @@ static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs, s64 delta_ atomic_set(&vcpu->arch.xen.timer_pending, 0); vcpu->arch.xen.timer_expires = guest_abs; - if (delta_ns <= 0) { + if (delta <= 0) xen_timer_callback(&vcpu->arch.xen.timer); - } else { - ktime_t ktime_now = ktime_get(); + else hrtimer_start(&vcpu->arch.xen.timer, - ktime_add_ns(ktime_now, delta_ns), + ktime_add_ns(kernel_now, delta), HRTIMER_MODE_ABS_HARD); - } } static void kvm_xen_stop_timer(struct kvm_vcpu *vcpu) @@ -452,14 +527,13 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) smp_wmb(); } - if (user_len2) + if (user_len2) { + kvm_gpc_mark_dirty_in_slot(gpc2); read_unlock(&gpc2->lock); + } + kvm_gpc_mark_dirty_in_slot(gpc1); 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) @@ -496,7 +570,6 @@ void kvm_xen_update_runstate(struct kvm_vcpu *v, int state) void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) { struct kvm_lapic_irq irq = { }; - int r; irq.dest_id = v->vcpu_id; irq.vector = v->arch.xen.upcall_vector; @@ -505,8 +578,7 @@ void kvm_xen_inject_vcpu_vector(struct kvm_vcpu *v) irq.delivery_mode = APIC_DM_FIXED; irq.level = 1; - /* The fast version will always work for physical unicast */ - WARN_ON_ONCE(!kvm_irq_delivery_to_apic_fast(v->kvm, NULL, &irq, &r, NULL)); + kvm_irq_delivery_to_apic(v->kvm, NULL, &irq, NULL); } /* @@ -565,13 +637,13 @@ void kvm_xen_inject_pending_events(struct kvm_vcpu *v) : "0" (evtchn_pending_sel32)); WRITE_ONCE(vi->evtchn_upcall_pending, 1); } + + kvm_gpc_mark_dirty_in_slot(gpc); read_unlock_irqrestore(&gpc->lock, flags); /* For the per-vCPU lapic vector, deliver it as MSI. */ if (v->arch.xen.upcall_vector) kvm_xen_inject_vcpu_vector(v); - - mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT); } int __kvm_xen_has_interrupt(struct kvm_vcpu *v) @@ -635,17 +707,59 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) } else { mutex_lock(&kvm->arch.xen.xen_lock); kvm->arch.xen.long_mode = !!data->u.long_mode; + + /* + * Re-initialize shared_info to put the wallclock in the + * correct place. Whilst it's not necessary to do this + * unless the mode is actually changed, it does no harm + * to make the call anyway. + */ + r = kvm->arch.xen.shinfo_cache.active ? + kvm_xen_shared_info_init(kvm) : 0; mutex_unlock(&kvm->arch.xen.xen_lock); - r = 0; } break; case KVM_XEN_ATTR_TYPE_SHARED_INFO: + case KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA: { + int idx; + mutex_lock(&kvm->arch.xen.xen_lock); - r = kvm_xen_shared_info_init(kvm, data->u.shared_info.gfn); + + idx = srcu_read_lock(&kvm->srcu); + + if (data->type == KVM_XEN_ATTR_TYPE_SHARED_INFO) { + gfn_t gfn = data->u.shared_info.gfn; + + if (gfn == KVM_XEN_INVALID_GFN) { + kvm_gpc_deactivate(&kvm->arch.xen.shinfo_cache); + r = 0; + } else { + r = kvm_gpc_activate(&kvm->arch.xen.shinfo_cache, + gfn_to_gpa(gfn), PAGE_SIZE); + } + } else { + void __user * hva = u64_to_user_ptr(data->u.shared_info.hva); + + if (!PAGE_ALIGNED(hva) || !access_ok(hva, PAGE_SIZE)) { + r = -EINVAL; + } else if (!hva) { + kvm_gpc_deactivate(&kvm->arch.xen.shinfo_cache); + r = 0; + } else { + r = kvm_gpc_activate_hva(&kvm->arch.xen.shinfo_cache, + (unsigned long)hva, PAGE_SIZE); + } + } + + srcu_read_unlock(&kvm->srcu, idx); + + if (!r && kvm->arch.xen.shinfo_cache.active) + r = kvm_xen_shared_info_init(kvm); + mutex_unlock(&kvm->arch.xen.xen_lock); break; - + } case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: if (data->u.vector && data->u.vector < 0x10) r = -EINVAL; @@ -699,13 +813,21 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) break; case KVM_XEN_ATTR_TYPE_SHARED_INFO: - if (kvm->arch.xen.shinfo_cache.active) + if (kvm_gpc_is_gpa_active(&kvm->arch.xen.shinfo_cache)) data->u.shared_info.gfn = gpa_to_gfn(kvm->arch.xen.shinfo_cache.gpa); else data->u.shared_info.gfn = KVM_XEN_INVALID_GFN; r = 0; break; + case KVM_XEN_ATTR_TYPE_SHARED_INFO_HVA: + if (kvm_gpc_is_hva_active(&kvm->arch.xen.shinfo_cache)) + data->u.shared_info.hva = kvm->arch.xen.shinfo_cache.uhva; + else + data->u.shared_info.hva = 0; + r = 0; + break; + case KVM_XEN_ATTR_TYPE_UPCALL_VECTOR: data->u.vector = kvm->arch.xen.upcall_vector; r = 0; @@ -742,20 +864,33 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) switch (data->type) { case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO: + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA: /* No compat necessary here. */ BUILD_BUG_ON(sizeof(struct vcpu_info) != sizeof(struct compat_vcpu_info)); BUILD_BUG_ON(offsetof(struct vcpu_info, time) != offsetof(struct compat_vcpu_info, time)); - if (data->u.gpa == KVM_XEN_INVALID_GPA) { - kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache); - r = 0; - break; + if (data->type == KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO) { + if (data->u.gpa == KVM_XEN_INVALID_GPA) { + kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache); + r = 0; + break; + } + + r = kvm_gpc_activate(&vcpu->arch.xen.vcpu_info_cache, + data->u.gpa, sizeof(struct vcpu_info)); + } else { + if (data->u.hva == 0) { + kvm_gpc_deactivate(&vcpu->arch.xen.vcpu_info_cache); + r = 0; + break; + } + + r = kvm_gpc_activate_hva(&vcpu->arch.xen.vcpu_info_cache, + data->u.hva, 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); @@ -944,9 +1079,7 @@ int kvm_xen_vcpu_set_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) /* Start the timer if the new value has a valid vector+expiry. */ if (data->u.timer.port && data->u.timer.expires_ns) - kvm_xen_start_timer(vcpu, data->u.timer.expires_ns, - data->u.timer.expires_ns - - get_kvmclock_ns(vcpu->kvm)); + kvm_xen_start_timer(vcpu, data->u.timer.expires_ns, false); r = 0; break; @@ -977,13 +1110,21 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) switch (data->type) { case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO: - if (vcpu->arch.xen.vcpu_info_cache.active) + if (kvm_gpc_is_gpa_active(&vcpu->arch.xen.vcpu_info_cache)) data->u.gpa = vcpu->arch.xen.vcpu_info_cache.gpa; else data->u.gpa = KVM_XEN_INVALID_GPA; r = 0; break; + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_INFO_HVA: + if (kvm_gpc_is_hva_active(&vcpu->arch.xen.vcpu_info_cache)) + data->u.hva = vcpu->arch.xen.vcpu_info_cache.uhva; + else + data->u.hva = 0; + r = 0; + break; + case KVM_XEN_VCPU_ATTR_TYPE_VCPU_TIME_INFO: if (vcpu->arch.xen.vcpu_time_info_cache.active) data->u.gpa = vcpu->arch.xen.vcpu_time_info_cache.gpa; @@ -1093,9 +1234,24 @@ int kvm_xen_write_hypercall_page(struct kvm_vcpu *vcpu, u64 data) u32 page_num = data & ~PAGE_MASK; u64 page_addr = data & PAGE_MASK; bool lm = is_long_mode(vcpu); + int r = 0; + + mutex_lock(&kvm->arch.xen.xen_lock); + if (kvm->arch.xen.long_mode != lm) { + kvm->arch.xen.long_mode = lm; + + /* + * Re-initialize shared_info to put the wallclock in the + * correct place. + */ + if (kvm->arch.xen.shinfo_cache.active && + kvm_xen_shared_info_init(kvm)) + r = 1; + } + mutex_unlock(&kvm->arch.xen.xen_lock); - /* Latch long_mode for shared_info pages etc. */ - vcpu->kvm->arch.xen.long_mode = lm; + if (r) + return r; /* * If Xen hypercall intercept is enabled, fill the hypercall @@ -1396,7 +1552,6 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, { struct vcpu_set_singleshot_timer oneshot; struct x86_exception e; - s64 delta; if (!kvm_xen_timer_enabled(vcpu)) return false; @@ -1430,9 +1585,7 @@ static bool kvm_xen_hcall_vcpu_op(struct kvm_vcpu *vcpu, bool longmode, int cmd, return true; } - /* A delta <= 0 results in an immediate callback, which is what we want */ - delta = oneshot.timeout_abs_ns - get_kvmclock_ns(vcpu->kvm); - kvm_xen_start_timer(vcpu, oneshot.timeout_abs_ns, delta); + kvm_xen_start_timer(vcpu, oneshot.timeout_abs_ns, false); *r = 0; return true; @@ -1455,29 +1608,10 @@ static bool kvm_xen_hcall_set_timer_op(struct kvm_vcpu *vcpu, uint64_t timeout, if (!kvm_xen_timer_enabled(vcpu)) return false; - if (timeout) { - uint64_t guest_now = get_kvmclock_ns(vcpu->kvm); - int64_t delta = timeout - guest_now; - - /* Xen has a 'Linux workaround' in do_set_timer_op() which - * checks for negative absolute timeout values (caused by - * integer overflow), and for values about 13 days in the - * future (2^50ns) which would be caused by jiffies - * overflow. For those cases, it sets the timeout 100ms in - * the future (not *too* soon, since if a guest really did - * set a long timeout on purpose we don't want to keep - * churning CPU time by waking it up). - */ - if (unlikely((int64_t)timeout < 0 || - (delta > 0 && (uint32_t) (delta >> 50) != 0))) { - delta = 100 * NSEC_PER_MSEC; - timeout = guest_now + delta; - } - - kvm_xen_start_timer(vcpu, timeout, delta); - } else { + if (timeout) + kvm_xen_start_timer(vcpu, timeout, true); + else kvm_xen_stop_timer(vcpu); - } *r = 0; return true; @@ -1621,9 +1755,6 @@ int kvm_xen_set_evtchn_fast(struct kvm_xen_evtchn *xe, struct kvm *kvm) WRITE_ONCE(xe->vcpu_idx, vcpu->vcpu_idx); } - if (!vcpu->arch.xen.vcpu_info_cache.active) - return -EINVAL; - if (xe->port >= max_evtchn_port(kvm)) return -EINVAL; @@ -1731,8 +1862,6 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm) mm_borrowed = true; } - mutex_lock(&kvm->arch.xen.xen_lock); - /* * It is theoretically possible for the page to be unmapped * and the MMU notifier to invalidate the shared_info before @@ -1760,8 +1889,6 @@ static int kvm_xen_set_evtchn(struct kvm_xen_evtchn *xe, struct kvm *kvm) srcu_read_unlock(&kvm->srcu, idx); } while(!rc); - mutex_unlock(&kvm->arch.xen.xen_lock); - if (mm_borrowed) kthread_unuse_mm(kvm->mm); @@ -2109,14 +2236,10 @@ 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, 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); + kvm_gpc_init(&vcpu->arch.xen.runstate_cache, vcpu->kvm); + kvm_gpc_init(&vcpu->arch.xen.runstate2_cache, vcpu->kvm); + kvm_gpc_init(&vcpu->arch.xen.vcpu_info_cache, vcpu->kvm); + kvm_gpc_init(&vcpu->arch.xen.vcpu_time_info_cache, vcpu->kvm); } void kvm_xen_destroy_vcpu(struct kvm_vcpu *vcpu) @@ -2159,7 +2282,7 @@ void kvm_xen_init_vm(struct kvm *kvm) { mutex_init(&kvm->arch.xen.xen_lock); idr_init(&kvm->arch.xen.evtchn_ports); - kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm, NULL, KVM_HOST_USES_PFN); + kvm_gpc_init(&kvm->arch.xen.shinfo_cache, kvm); } void kvm_xen_destroy_vm(struct kvm *kvm) diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index f0dae4fb6d..6da73513f0 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -36,7 +36,7 @@ lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc.o copy_mc_64.o lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o insn-eval.o lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o -lib-$(CONFIG_RETPOLINE) += retpoline.o +lib-$(CONFIG_MITIGATION_RETPOLINE) += retpoline.o obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o obj-y += iomem.o diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S index 6962df3157..4fb44894ad 100644 --- a/arch/x86/lib/cmpxchg16b_emu.S +++ b/arch/x86/lib/cmpxchg16b_emu.S @@ -23,14 +23,14 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu) cli /* if (*ptr == old) */ - cmpq PER_CPU_VAR(0(%rsi)), %rax + cmpq __percpu (%rsi), %rax jne .Lnot_same - cmpq PER_CPU_VAR(8(%rsi)), %rdx + cmpq __percpu 8(%rsi), %rdx jne .Lnot_same /* *ptr = new */ - movq %rbx, PER_CPU_VAR(0(%rsi)) - movq %rcx, PER_CPU_VAR(8(%rsi)) + movq %rbx, __percpu (%rsi) + movq %rcx, __percpu 8(%rsi) /* set ZF in EFLAGS to indicate success */ orl $X86_EFLAGS_ZF, (%rsp) @@ -42,8 +42,8 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu) /* *ptr != old */ /* old = *ptr */ - movq PER_CPU_VAR(0(%rsi)), %rax - movq PER_CPU_VAR(8(%rsi)), %rdx + movq __percpu (%rsi), %rax + movq __percpu 8(%rsi), %rdx /* clear ZF in EFLAGS to indicate failure */ andl $(~X86_EFLAGS_ZF), (%rsp) diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S index 873e4ef23e..1c96be769a 100644 --- a/arch/x86/lib/cmpxchg8b_emu.S +++ b/arch/x86/lib/cmpxchg8b_emu.S @@ -24,12 +24,12 @@ SYM_FUNC_START(cmpxchg8b_emu) pushfl cli - cmpl 0(%esi), %eax + cmpl (%esi), %eax jne .Lnot_same cmpl 4(%esi), %edx jne .Lnot_same - movl %ebx, 0(%esi) + movl %ebx, (%esi) movl %ecx, 4(%esi) orl $X86_EFLAGS_ZF, (%esp) @@ -38,7 +38,7 @@ SYM_FUNC_START(cmpxchg8b_emu) RET .Lnot_same: - movl 0(%esi), %eax + movl (%esi), %eax movl 4(%esi), %edx andl $(~X86_EFLAGS_ZF), (%esp) @@ -53,18 +53,30 @@ EXPORT_SYMBOL(cmpxchg8b_emu) #ifndef CONFIG_UML +/* + * Emulate 'cmpxchg8b %fs:(%rsi)' + * + * Inputs: + * %esi : memory location to compare + * %eax : low 32 bits of old value + * %edx : high 32 bits of old value + * %ebx : low 32 bits of new value + * %ecx : high 32 bits of new value + * + * Notably this is not LOCK prefixed and is not safe against NMIs + */ SYM_FUNC_START(this_cpu_cmpxchg8b_emu) pushfl cli - cmpl PER_CPU_VAR(0(%esi)), %eax + cmpl __percpu (%esi), %eax jne .Lnot_same2 - cmpl PER_CPU_VAR(4(%esi)), %edx + cmpl __percpu 4(%esi), %edx jne .Lnot_same2 - movl %ebx, PER_CPU_VAR(0(%esi)) - movl %ecx, PER_CPU_VAR(4(%esi)) + movl %ebx, __percpu (%esi) + movl %ecx, __percpu 4(%esi) orl $X86_EFLAGS_ZF, (%esp) @@ -72,8 +84,8 @@ SYM_FUNC_START(this_cpu_cmpxchg8b_emu) RET .Lnot_same2: - movl PER_CPU_VAR(0(%esi)), %eax - movl PER_CPU_VAR(4(%esi)), %edx + movl __percpu (%esi), %eax + movl __percpu 4(%esi), %edx andl $(~X86_EFLAGS_ZF), (%esp) diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 10d5ed8b59..a1cb3a4e67 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -44,7 +44,11 @@ or %rdx, %rax .else cmp $TASK_SIZE_MAX-\size+1, %eax +.if \size != 8 jae .Lbad_get_user +.else + jae .Lbad_get_user_8 +.endif sbb %edx, %edx /* array_index_mask_nospec() */ and %edx, %eax .endif @@ -154,7 +158,7 @@ SYM_CODE_END(__get_user_handle_exception) #ifdef CONFIG_X86_32 SYM_CODE_START_LOCAL(__get_user_8_handle_exception) ASM_CLAC -bad_get_user_8: +.Lbad_get_user_8: xor %edx,%edx xor %ecx,%ecx mov $(-EFAULT),%_ASM_AX diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c index 558a605929..98631c0e7a 100644 --- a/arch/x86/lib/insn-eval.c +++ b/arch/x86/lib/insn-eval.c @@ -1129,15 +1129,15 @@ static int get_eff_addr_modrm_16(struct insn *insn, struct pt_regs *regs, * get_eff_addr_sib() - Obtain referenced effective address via SIB * @insn: Instruction. Must be valid. * @regs: Register values as seen when entering kernel mode - * @regoff: Obtained operand offset, in pt_regs, associated with segment + * @base_offset: Obtained operand offset, in pt_regs, associated with segment * @eff_addr: Obtained effective address * * Obtain the effective address referenced by the SIB byte of @insn. After * identifying the registers involved in the indexed, register-indirect memory * reference, its value is obtained from the operands in @regs. The computed * address is stored @eff_addr. Also, the register operand that indicates the - * associated segment is stored in @regoff, this parameter can later be used to - * determine such segment. + * associated segment is stored in @base_offset; this parameter can later be + * used to determine such segment. * * Returns: * diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c index 55e371cc69..1bb155a095 100644 --- a/arch/x86/lib/insn.c +++ b/arch/x86/lib/insn.c @@ -71,7 +71,7 @@ void insn_init(struct insn *insn, const void *kaddr, int buf_len, int x86_64) insn->kaddr = kaddr; insn->end_kaddr = kaddr + buf_len; insn->next_byte = kaddr; - insn->x86_64 = x86_64 ? 1 : 0; + insn->x86_64 = x86_64; insn->opnd_bytes = 4; if (x86_64) insn->addr_bytes = 8; @@ -268,11 +268,9 @@ int insn_get_opcode(struct insn *insn) if (opcode->got) return 0; - if (!insn->prefixes.got) { - ret = insn_get_prefixes(insn); - if (ret) - return ret; - } + ret = insn_get_prefixes(insn); + if (ret) + return ret; /* Get first opcode */ op = get_next(insn_byte_t, insn); @@ -339,11 +337,9 @@ int insn_get_modrm(struct insn *insn) if (modrm->got) return 0; - if (!insn->opcode.got) { - ret = insn_get_opcode(insn); - if (ret) - return ret; - } + ret = insn_get_opcode(insn); + if (ret) + return ret; if (inat_has_modrm(insn->attr)) { mod = get_next(insn_byte_t, insn); @@ -386,11 +382,9 @@ int insn_rip_relative(struct insn *insn) if (!insn->x86_64) return 0; - if (!modrm->got) { - ret = insn_get_modrm(insn); - if (ret) - return 0; - } + ret = insn_get_modrm(insn); + if (ret) + return 0; /* * For rip-relative instructions, the mod field (top 2 bits) * is zero and the r/m field (bottom 3 bits) is 0x5. @@ -417,11 +411,9 @@ int insn_get_sib(struct insn *insn) if (insn->sib.got) return 0; - if (!insn->modrm.got) { - ret = insn_get_modrm(insn); - if (ret) - return ret; - } + ret = insn_get_modrm(insn); + if (ret) + return ret; if (insn->modrm.nbytes) { modrm = insn->modrm.bytes[0]; @@ -460,11 +452,9 @@ int insn_get_displacement(struct insn *insn) if (insn->displacement.got) return 0; - if (!insn->sib.got) { - ret = insn_get_sib(insn); - if (ret) - return ret; - } + ret = insn_get_sib(insn); + if (ret) + return ret; if (insn->modrm.nbytes) { /* @@ -628,11 +618,9 @@ int insn_get_immediate(struct insn *insn) if (insn->immediate.got) return 0; - if (!insn->displacement.got) { - ret = insn_get_displacement(insn); - if (ret) - return ret; - } + ret = insn_get_displacement(insn); + if (ret) + return ret; if (inat_has_moffset(insn->attr)) { if (!__get_moffset(insn)) @@ -703,11 +691,9 @@ int insn_get_length(struct insn *insn) if (insn->length) return 0; - if (!insn->immediate.got) { - ret = insn_get_immediate(insn); - if (ret) - return ret; - } + ret = insn_get_immediate(insn); + if (ret) + return ret; insn->length = (unsigned char)((unsigned long)insn->next_byte - (unsigned long)insn->kaddr); diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c index 40bbe56bde..acd463d887 100644 --- a/arch/x86/lib/msr-smp.c +++ b/arch/x86/lib/msr-smp.c @@ -9,10 +9,9 @@ static void __rdmsr_on_cpu(void *info) { struct msr_info *rv = info; struct msr *reg; - int this_cpu = raw_smp_processor_id(); if (rv->msrs) - reg = per_cpu_ptr(rv->msrs, this_cpu); + reg = this_cpu_ptr(rv->msrs); else reg = &rv->reg; @@ -23,10 +22,9 @@ static void __wrmsr_on_cpu(void *info) { struct msr_info *rv = info; struct msr *reg; - int this_cpu = raw_smp_processor_id(); if (rv->msrs) - reg = per_cpu_ptr(rv->msrs, this_cpu); + reg = this_cpu_ptr(rv->msrs); else reg = &rv->reg; @@ -97,7 +95,7 @@ int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q) EXPORT_SYMBOL(wrmsrl_on_cpu); static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, - struct msr *msrs, + struct msr __percpu *msrs, void (*msr_func) (void *info)) { struct msr_info rv; @@ -124,7 +122,7 @@ static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no, * @msrs: array of MSR values * */ -void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) +void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs) { __rwmsr_on_cpus(mask, msr_no, msrs, __rdmsr_on_cpu); } @@ -138,7 +136,7 @@ EXPORT_SYMBOL(rdmsr_on_cpus); * @msrs: array of MSR values * */ -void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs) +void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs) { __rwmsr_on_cpus(mask, msr_no, msrs, __wrmsr_on_cpu); } diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c index 47fd9bd6b9..4bf4fad5b1 100644 --- a/arch/x86/lib/msr.c +++ b/arch/x86/lib/msr.c @@ -6,9 +6,9 @@ #define CREATE_TRACE_POINTS #include <asm/msr-trace.h> -struct msr *msrs_alloc(void) +struct msr __percpu *msrs_alloc(void) { - struct msr *msrs = NULL; + struct msr __percpu *msrs = NULL; msrs = alloc_percpu(struct msr); if (!msrs) { @@ -20,7 +20,7 @@ struct msr *msrs_alloc(void) } EXPORT_SYMBOL(msrs_alloc); -void msrs_free(struct msr *msrs) +void msrs_free(struct msr __percpu *msrs) { free_percpu(msrs); } diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 5b26a952e2..391059b2c6 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -71,7 +71,7 @@ SYM_CODE_END(__x86_indirect_thunk_array) #include <asm/GEN-for-each-reg.h> #undef GEN -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING .macro CALL_THUNK reg .align RETPOLINE_THUNK_SIZE @@ -127,7 +127,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) #undef GEN #endif -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_MITIGATION_RETHUNK /* * Be careful here: that label cannot really be removed because in @@ -138,7 +138,7 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) */ .section .text..__x86.return_thunk -#ifdef CONFIG_CPU_SRSO +#ifdef CONFIG_MITIGATION_SRSO /* * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at @@ -225,8 +225,7 @@ SYM_CODE_START(srso_return_thunk) SYM_CODE_END(srso_return_thunk) #define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret" -#else /* !CONFIG_CPU_SRSO */ -#define JMP_SRSO_UNTRAIN_RET "ud2" +#else /* !CONFIG_MITIGATION_SRSO */ /* Dummy for the alternative in CALL_UNTRAIN_RET. */ SYM_CODE_START(srso_alias_untrain_ret) ANNOTATE_UNRET_SAFE @@ -235,9 +234,10 @@ SYM_CODE_START(srso_alias_untrain_ret) int3 SYM_FUNC_END(srso_alias_untrain_ret) __EXPORT_THUNK(srso_alias_untrain_ret) -#endif /* CONFIG_CPU_SRSO */ +#define JMP_SRSO_UNTRAIN_RET "ud2" +#endif /* CONFIG_MITIGATION_SRSO */ -#ifdef CONFIG_CPU_UNRET_ENTRY +#ifdef CONFIG_MITIGATION_UNRET_ENTRY /* * Some generic notes on the untraining sequences: @@ -319,20 +319,20 @@ SYM_CODE_END(retbleed_return_thunk) SYM_FUNC_END(retbleed_untrain_ret) #define JMP_RETBLEED_UNTRAIN_RET "jmp retbleed_untrain_ret" -#else /* !CONFIG_CPU_UNRET_ENTRY */ +#else /* !CONFIG_MITIGATION_UNRET_ENTRY */ #define JMP_RETBLEED_UNTRAIN_RET "ud2" -#endif /* CONFIG_CPU_UNRET_ENTRY */ +#endif /* CONFIG_MITIGATION_UNRET_ENTRY */ -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) +#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO) SYM_FUNC_START(entry_untrain_ret) ALTERNATIVE JMP_RETBLEED_UNTRAIN_RET, JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) -#endif /* CONFIG_CPU_UNRET_ENTRY || CONFIG_CPU_SRSO */ +#endif /* CONFIG_MITIGATION_UNRET_ENTRY || CONFIG_MITIGATION_SRSO */ -#ifdef CONFIG_CALL_DEPTH_TRACKING +#ifdef CONFIG_MITIGATION_CALL_DEPTH_TRACKING .align 64 SYM_FUNC_START(call_depth_return_thunk) @@ -364,7 +364,7 @@ SYM_FUNC_START(call_depth_return_thunk) int3 SYM_FUNC_END(call_depth_return_thunk) -#endif /* CONFIG_CALL_DEPTH_TRACKING */ +#endif /* CONFIG_MITIGATION_CALL_DEPTH_TRACKING */ /* * This function name is magical and is used by -mfunction-return=thunk-extern @@ -374,21 +374,25 @@ SYM_FUNC_END(call_depth_return_thunk) * 'JMP __x86_return_thunk' sites are changed to something else by * apply_returns(). * - * This should be converted eventually to call a warning function which - * should scream loudly when the default return thunk is called after - * alternatives have been applied. - * - * That warning function cannot BUG() because the bug splat cannot be - * displayed in all possible configurations, leading to users not really - * knowing why the machine froze. + * The ALTERNATIVE below adds a really loud warning to catch the case + * where the insufficient default return thunk ends up getting used for + * whatever reason like miscompilation or failure of + * objtool/alternatives/etc to patch all the return sites. */ SYM_CODE_START(__x86_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR +#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || \ + defined(CONFIG_MITIGATION_SRSO) || \ + defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) + ALTERNATIVE __stringify(ANNOTATE_UNRET_SAFE; ret), \ + "jmp warn_thunk_thunk", X86_FEATURE_ALWAYS +#else ANNOTATE_UNRET_SAFE ret +#endif int3 SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) -#endif /* CONFIG_RETHUNK */ +#endif /* CONFIG_MITIGATION_RETHUNK */ diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt index d1ccd06c53..da9347552b 100644 --- a/arch/x86/lib/x86-opcode-map.txt +++ b/arch/x86/lib/x86-opcode-map.txt @@ -1051,8 +1051,8 @@ GrpTable: Grp6 EndTable GrpTable: Grp7 -0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) -1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) +0: SGDT Ms | VMCALL (001),(11B) | VMLAUNCH (010),(11B) | VMRESUME (011),(11B) | VMXOFF (100),(11B) | PCONFIG (101),(11B) | ENCLV (000),(11B) | WRMSRNS (110),(11B) +1: SIDT Ms | MONITOR (000),(11B) | MWAIT (001),(11B) | CLAC (010),(11B) | STAC (011),(11B) | ENCLS (111),(11B) | ERETU (F3),(010),(11B) | ERETS (F2),(010),(11B) 2: LGDT Ms | XGETBV (000),(11B) | XSETBV (001),(11B) | VMFUNC (100),(11B) | XEND (101)(11B) | XTEST (110)(11B) | ENCLU (111),(11B) 3: LIDT Ms 4: SMSW Mw/Rv diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index c80febc44c..428048e73b 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -16,6 +16,7 @@ KASAN_SANITIZE_pgprot.o := n KCSAN_SANITIZE := n # Avoid recursion by not calling KMSAN hooks for CEA code. KMSAN_SANITIZE_cpu_entry_area.o := n +KMSAN_SANITIZE_mem_encrypt_identity.o := n ifdef CONFIG_FUNCTION_TRACER CFLAGS_REMOVE_mem_encrypt.o = -pg @@ -60,7 +61,7 @@ obj-$(CONFIG_NUMA_EMU) += numa_emulation.o obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS) += pkeys.o obj-$(CONFIG_RANDOMIZE_MEMORY) += kaslr.o -obj-$(CONFIG_PAGE_TABLE_ISOLATION) += pti.o +obj-$(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION) += pti.o obj-$(CONFIG_X86_MEM_ENCRYPT) += mem_encrypt.o obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_amd.o diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index b3ca7d23e4..9332b36a10 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -54,13 +54,11 @@ static __init int find_northbridge(void) int __init amd_numa_init(void) { - u64 start = PFN_PHYS(0); + unsigned int numnodes, cores, apicid; + u64 prevbase, start = PFN_PHYS(0); u64 end = PFN_PHYS(max_pfn); - unsigned numnodes; - u64 prevbase; - int i, j, nb; u32 nodeid, reg; - unsigned int bits, cores, apicid_base; + int i, j, nb; if (!early_pci_allowed()) return -EINVAL; @@ -158,26 +156,18 @@ int __init amd_numa_init(void) return -ENOENT; /* - * We seem to have valid NUMA configuration. Map apicids to nodes - * using the coreid bits from early_identify_cpu. + * We seem to have valid NUMA configuration. Map apicids to nodes + * using the size of the core domain in the APIC space. */ - bits = boot_cpu_data.x86_coreid_bits; - cores = 1 << bits; - apicid_base = 0; + cores = topology_get_domain_size(TOPO_CORE_DOMAIN); - /* - * get boot-time SMP configuration: - */ - early_get_smp_config(); + apicid = boot_cpu_physical_apicid; + if (apicid > 0) + pr_info("BSP APIC ID: %02x\n", apicid); - if (boot_cpu_physical_apicid > 0) { - pr_info("BSP APIC ID: %02x\n", boot_cpu_physical_apicid); - apicid_base = boot_cpu_physical_apicid; + for_each_node_mask(i, numa_nodes_parsed) { + for (j = 0; j < cores; j++, apicid++) + set_apicid_to_node(apicid, i); } - - for_each_node_mask(i, numa_nodes_parsed) - for (j = apicid_base; j < cores + apicid_base; j++) - set_apicid_to_node((i << bits) + j, i); - return 0; } diff --git a/arch/x86/mm/debug_pagetables.c b/arch/x86/mm/debug_pagetables.c index b43301cb2a..ae5c213a1c 100644 --- a/arch/x86/mm/debug_pagetables.c +++ b/arch/x86/mm/debug_pagetables.c @@ -22,7 +22,7 @@ static int ptdump_curknl_show(struct seq_file *m, void *v) DEFINE_SHOW_ATTRIBUTE(ptdump_curknl); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static int ptdump_curusr_show(struct seq_file *m, void *v) { if (current->mm->pgd) @@ -54,7 +54,7 @@ static int __init pt_dump_debug_init(void) debugfs_create_file("current_kernel", 0400, dir, NULL, &ptdump_curknl_fops); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION debugfs_create_file("current_user", 0400, dir, NULL, &ptdump_curusr_fops); #endif diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c index e1b599ecbb..89079ea73e 100644 --- a/arch/x86/mm/dump_pagetables.c +++ b/arch/x86/mm/dump_pagetables.c @@ -362,9 +362,9 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, } } -static void ptdump_walk_pgd_level_core(struct seq_file *m, - struct mm_struct *mm, pgd_t *pgd, - bool checkwx, bool dmesg) +bool ptdump_walk_pgd_level_core(struct seq_file *m, + struct mm_struct *mm, pgd_t *pgd, + bool checkwx, bool dmesg) { const struct ptdump_range ptdump_ranges[] = { #ifdef CONFIG_X86_64 @@ -391,12 +391,17 @@ static void ptdump_walk_pgd_level_core(struct seq_file *m, ptdump_walk_pgd(&st.ptdump, mm, pgd); if (!checkwx) - return; - if (st.wx_pages) + return true; + if (st.wx_pages) { pr_info("x86/mm: Checked W+X mappings: FAILED, %lu W+X pages found.\n", st.wx_pages); - else + + return false; + } else { pr_info("x86/mm: Checked W+X mappings: passed, no W+X pages found.\n"); + + return true; + } } void ptdump_walk_pgd_level(struct seq_file *m, struct mm_struct *mm) @@ -408,7 +413,7 @@ void ptdump_walk_pgd_level_debugfs(struct seq_file *m, struct mm_struct *mm, bool user) { pgd_t *pgd = mm->pgd; -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (user && boot_cpu_has(X86_FEATURE_PTI)) pgd = kernel_to_user_pgdp(pgd); #endif @@ -418,7 +423,7 @@ EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs); void ptdump_walk_user_pgd_level_checkwx(void) { -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION pgd_t *pgd = INIT_PGD; if (!(__supported_pte_mask & _PAGE_NX) || @@ -431,9 +436,12 @@ void ptdump_walk_user_pgd_level_checkwx(void) #endif } -void ptdump_walk_pgd_level_checkwx(void) +bool ptdump_walk_pgd_level_checkwx(void) { - ptdump_walk_pgd_level_core(NULL, &init_mm, INIT_PGD, true, false); + if (!(__supported_pte_mask & _PAGE_NX)) + return true; + + return ptdump_walk_pgd_level_core(NULL, &init_mm, INIT_PGD, true, false); } static int __init pt_dump_init(void) diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c index 271dcb2dea..b522933bfa 100644 --- a/arch/x86/mm/extable.c +++ b/arch/x86/mm/extable.c @@ -6,6 +6,7 @@ #include <xen/xen.h> #include <asm/fpu/api.h> +#include <asm/fred.h> #include <asm/sev.h> #include <asm/traps.h> #include <asm/kdebug.h> @@ -223,6 +224,79 @@ static bool ex_handler_ucopy_len(const struct exception_table_entry *fixup, return ex_handler_uaccess(fixup, regs, trapnr, fault_address); } +#ifdef CONFIG_X86_FRED +static bool ex_handler_eretu(const struct exception_table_entry *fixup, + struct pt_regs *regs, unsigned long error_code) +{ + struct pt_regs *uregs = (struct pt_regs *)(regs->sp - offsetof(struct pt_regs, orig_ax)); + unsigned short ss = uregs->ss; + unsigned short cs = uregs->cs; + + /* + * Move the NMI bit from the invalid stack frame, which caused ERETU + * to fault, to the fault handler's stack frame, thus to unblock NMI + * with the fault handler's ERETS instruction ASAP if NMI is blocked. + */ + regs->fred_ss.nmi = uregs->fred_ss.nmi; + + /* + * Sync event information to uregs, i.e., the ERETU return frame, but + * is it safe to write to the ERETU return frame which is just above + * current event stack frame? + * + * The RSP used by FRED to push a stack frame is not the value in %rsp, + * it is calculated from %rsp with the following 2 steps: + * 1) RSP = %rsp - (IA32_FRED_CONFIG & 0x1c0) // Reserve N*64 bytes + * 2) RSP = RSP & ~0x3f // Align to a 64-byte cache line + * when an event delivery doesn't trigger a stack level change. + * + * Here is an example with N*64 (N=1) bytes reserved: + * + * 64-byte cache line ==> ______________ + * |___Reserved___| + * |__Event_data__| + * |_____SS_______| + * |_____RSP______| + * |_____FLAGS____| + * |_____CS_______| + * |_____IP_______| + * 64-byte cache line ==> |__Error_code__| <== ERETU return frame + * |______________| + * |______________| + * |______________| + * |______________| + * |______________| + * |______________| + * |______________| + * 64-byte cache line ==> |______________| <== RSP after step 1) and 2) + * |___Reserved___| + * |__Event_data__| + * |_____SS_______| + * |_____RSP______| + * |_____FLAGS____| + * |_____CS_______| + * |_____IP_______| + * 64-byte cache line ==> |__Error_code__| <== ERETS return frame + * + * Thus a new FRED stack frame will always be pushed below a previous + * FRED stack frame ((N*64) bytes may be reserved between), and it is + * safe to write to a previous FRED stack frame as they never overlap. + */ + fred_info(uregs)->edata = fred_event_data(regs); + uregs->ssx = regs->ssx; + uregs->fred_ss.ss = ss; + /* The NMI bit was moved away above */ + uregs->fred_ss.nmi = 0; + uregs->csx = regs->csx; + uregs->fred_cs.sl = 0; + uregs->fred_cs.wfe = 0; + uregs->cs = cs; + uregs->orig_ax = error_code; + + return ex_handler_default(fixup, regs); +} +#endif + int ex_get_fixup_type(unsigned long ip) { const struct exception_table_entry *e = search_exception_tables(ip); @@ -300,6 +374,10 @@ int fixup_exception(struct pt_regs *regs, int trapnr, unsigned long error_code, return ex_handler_ucopy_len(e, regs, trapnr, fault_addr, reg, imm); case EX_TYPE_ZEROPAD: return ex_handler_zeropad(e, regs, fault_addr); +#ifdef CONFIG_X86_FRED + case EX_TYPE_ERETU: + return ex_handler_eretu(e, regs, error_code); +#endif } BUG(); } diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index e604d2d6cc..bba4e020dd 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -34,6 +34,8 @@ #include <asm/kvm_para.h> /* kvm_handle_async_pf */ #include <asm/vdso.h> /* fixup_vdso_exception() */ #include <asm/irq_stack.h> +#include <asm/fred.h> +#include <asm/sev.h> /* snp_dump_hva_rmpentry() */ #define CREATE_TRACE_POINTS #include <asm/trace/exceptions.h> @@ -250,7 +252,7 @@ static noinline int vmalloc_fault(unsigned long address) if (!pmd_k) return -1; - if (pmd_large(*pmd_k)) + if (pmd_leaf(*pmd_k)) return 0; pte_k = pte_offset_kernel(pmd_k, address); @@ -319,7 +321,7 @@ static void dump_pagetable(unsigned long address) * And let's rather not kmap-atomic the pte, just in case * it's allocated already: */ - if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_large(*pmd)) + if (!low_pfn(pmd_pfn(*pmd)) || !pmd_present(*pmd) || pmd_leaf(*pmd)) goto out; pte = pte_offset_kernel(pmd, address); @@ -368,7 +370,7 @@ static void dump_pagetable(unsigned long address) goto bad; pr_cont("P4D %lx ", p4d_val(*p4d)); - if (!p4d_present(*p4d) || p4d_large(*p4d)) + if (!p4d_present(*p4d) || p4d_leaf(*p4d)) goto out; pud = pud_offset(p4d, address); @@ -384,7 +386,7 @@ static void dump_pagetable(unsigned long address) goto bad; pr_cont("PMD %lx ", pmd_val(*pmd)); - if (!pmd_present(*pmd) || pmd_large(*pmd)) + if (!pmd_present(*pmd) || pmd_leaf(*pmd)) goto out; pte = pte_offset_kernel(pmd, address); @@ -547,6 +549,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad !(error_code & X86_PF_PROT) ? "not-present page" : (error_code & X86_PF_RSVD) ? "reserved bit violation" : (error_code & X86_PF_PK) ? "protection keys violation" : + (error_code & X86_PF_RMP) ? "RMP violation" : "permissions violation"); if (!(error_code & X86_PF_USER) && user_mode(regs)) { @@ -579,6 +582,9 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code, unsigned long ad } dump_pagetable(address); + + if (error_code & X86_PF_RMP) + snp_dump_hva_rmpentry(address); } static noinline void @@ -999,7 +1005,7 @@ spurious_kernel_fault(unsigned long error_code, unsigned long address) if (!p4d_present(*p4d)) return 0; - if (p4d_large(*p4d)) + if (p4d_leaf(*p4d)) return spurious_kernel_fault_check(error_code, (pte_t *) p4d); pud = pud_offset(p4d, address); @@ -1013,7 +1019,7 @@ spurious_kernel_fault(unsigned long error_code, unsigned long address) if (!pmd_present(*pmd)) return 0; - if (pmd_large(*pmd)) + if (pmd_leaf(*pmd)) return spurious_kernel_fault_check(error_code, (pte_t *) pmd); pte = pte_offset_kernel(pmd, address); @@ -1262,21 +1268,14 @@ void do_user_addr_fault(struct pt_regs *regs, return; } - /* - * It's safe to allow irq's after cr2 has been saved and the - * vmalloc fault has been handled. - * - * User-mode registers count as a user access even for any - * potential system fault or CPU buglet: - */ - if (user_mode(regs)) { - local_irq_enable(); - flags |= FAULT_FLAG_USER; - } else { - if (regs->flags & X86_EFLAGS_IF) - local_irq_enable(); + /* Legacy check - remove this after verifying that it doesn't trigger */ + if (WARN_ON_ONCE(!(regs->flags & X86_EFLAGS_IF))) { + bad_area_nosemaphore(regs, error_code, address); + return; } + local_irq_enable(); + perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address); /* @@ -1292,6 +1291,14 @@ void do_user_addr_fault(struct pt_regs *regs, if (error_code & X86_PF_INSTR) flags |= FAULT_FLAG_INSTRUCTION; + /* + * We set FAULT_FLAG_USER based on the register state, not + * based on X86_PF_USER. User space accesses that cause + * system page faults are still user accesses. + */ + if (user_mode(regs)) + flags |= FAULT_FLAG_USER; + #ifdef CONFIG_X86_64 /* * Faults in the vsyscall page might need emulation. The @@ -1478,8 +1485,10 @@ handle_page_fault(struct pt_regs *regs, unsigned long error_code, DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault) { - unsigned long address = read_cr2(); irqentry_state_t state; + unsigned long address; + + address = cpu_feature_enabled(X86_FEATURE_FRED) ? fred_event_data(regs) : read_cr2(); prefetchw(¤t->mm->mmap_lock); diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index b63403d717..ac41b1e094 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -463,7 +463,7 @@ void __init native_pagetable_init(void) break; /* should not be large page here */ - if (pmd_large(*pmd)) { + if (pmd_leaf(*pmd)) { pr_warn("try to clear pte for ram above max_low_pfn: pfn: %lx pmd: %p pmd phys: %lx, but pmd is big page and is not using pte !\n", pfn, pmd, __pa(pmd)); BUG_ON(1); @@ -800,6 +800,4 @@ void mark_rodata_ro(void) set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT); #endif mark_nxdata_nx(); - if (__supported_pte_mask & _PAGE_NX) - debug_checkwx(); } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 534436c9d3..7e177856ee 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -530,7 +530,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long paddr, unsigned long paddr_end, } if (!pmd_none(*pmd)) { - if (!pmd_large(*pmd)) { + if (!pmd_leaf(*pmd)) { spin_lock(&init_mm.page_table_lock); pte = (pte_t *)pmd_page_vaddr(*pmd); paddr_last = phys_pte_init(pte, paddr, @@ -1114,7 +1114,7 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end, if (!pmd_present(*pmd)) continue; - if (pmd_large(*pmd)) { + if (pmd_leaf(*pmd)) { if (IS_ALIGNED(addr, PMD_SIZE) && IS_ALIGNED(next, PMD_SIZE)) { if (!direct) @@ -1197,7 +1197,7 @@ remove_p4d_table(p4d_t *p4d_start, unsigned long addr, unsigned long end, if (!p4d_present(*p4d)) continue; - BUILD_BUG_ON(p4d_large(*p4d)); + BUILD_BUG_ON(p4d_leaf(*p4d)); pud_base = pud_offset(p4d, 0); remove_pud_table(pud_base, addr, next, altmap, direct); @@ -1412,8 +1412,6 @@ void mark_rodata_ro(void) (void *)text_end, (void *)rodata_start); free_kernel_image_pages("unused kernel image (rodata/data gap)", (void *)rodata_end, (void *)_sdata); - - debug_checkwx(); } /* @@ -1522,9 +1520,9 @@ void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node, int __meminit vmemmap_check_pmd(pmd_t *pmd, int node, unsigned long addr, unsigned long next) { - int large = pmd_large(*pmd); + int large = pmd_leaf(*pmd); - if (pmd_large(*pmd)) { + if (pmd_leaf(*pmd)) { vmemmap_verify((pte_t *)pmd, node, addr, next); vmemmap_use_sub_pmd(addr, next); } diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index fcf508c52b..9dddf19a55 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -95,7 +95,7 @@ static void __init kasan_populate_pud(pud_t *pud, unsigned long addr, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); - if (!pmd_large(*pmd)) + if (!pmd_leaf(*pmd)) kasan_populate_pmd(pmd, addr, next, nid); } while (pmd++, addr = next, addr != end); } diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index c290c55b63..0a120d85d7 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -14,6 +14,8 @@ #include <linux/mem_encrypt.h> #include <linux/virtio_anchor.h> +#include <asm/sev.h> + /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) { @@ -42,38 +44,45 @@ bool force_dma_unencrypted(struct device *dev) static void print_mem_encrypt_feature_info(void) { - pr_info("Memory Encryption Features active:"); - - if (cpu_feature_enabled(X86_FEATURE_TDX_GUEST)) { - pr_cont(" Intel TDX\n"); - return; - } + pr_info("Memory Encryption Features active: "); - pr_cont(" AMD"); + switch (cc_vendor) { + case CC_VENDOR_INTEL: + pr_cont("Intel TDX\n"); + break; + case CC_VENDOR_AMD: + pr_cont("AMD"); - /* Secure Memory Encryption */ - if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { + /* Secure Memory Encryption */ + if (cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT)) { /* * SME is mutually exclusive with any of the SEV * features below. - */ - pr_cont(" SME\n"); - return; - } + */ + pr_cont(" SME\n"); + return; + } - /* Secure Encrypted Virtualization */ - if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) - pr_cont(" SEV"); + /* Secure Encrypted Virtualization */ + if (cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + pr_cont(" SEV"); + + /* Encrypted Register State */ + if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) + pr_cont(" SEV-ES"); - /* Encrypted Register State */ - if (cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) - pr_cont(" SEV-ES"); + /* Secure Nested Paging */ + if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) + pr_cont(" SEV-SNP"); - /* Secure Nested Paging */ - if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) - pr_cont(" SEV-SNP"); + pr_cont("\n"); - pr_cont("\n"); + sev_show_status(); + + break; + default: + pr_cont("Unknown\n"); + } } /* Architecture __weak replacement functions */ @@ -93,6 +102,13 @@ void __init mem_encrypt_setup_arch(void) phys_addr_t total_mem = memblock_phys_mem_size(); unsigned long size; + /* + * Do RMP table fixups after the e820 tables have been setup by + * e820__memory_setup(). + */ + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + snp_fixup_e820_tables(); + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) return; diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 94cd06d4b0..422602f603 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -498,7 +498,7 @@ void __init sme_early_init(void) * as this memory is not pre-validated and would thus cause a crash. */ if (sev_status & MSR_AMD64_SEV_SNP_ENABLED) { - x86_init.mpparse.find_smp_config = x86_init_noop; + x86_init.mpparse.find_mptable = x86_init_noop; x86_init.pci.init_irq = x86_init_noop; x86_init.resources.probe_roms = x86_init_noop; diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index cc47a818a6..ac33b2263a 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -157,7 +157,7 @@ static void __head sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) return; pmd = pmd_offset(pud, ppd->vaddr); - if (pmd_large(*pmd)) + if (pmd_leaf(*pmd)) return; set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags)); @@ -181,7 +181,7 @@ static void __head sme_populate_pgd(struct sme_populate_pgd_data *ppd) set_pmd(pmd, __pmd(PMD_FLAGS | __pa(pte))); } - if (pmd_large(*pmd)) + if (pmd_leaf(*pmd)) return; pte = pte_offset_kernel(pmd, ppd->vaddr); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index ce84ba86e6..6ce10e3c62 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -493,7 +493,7 @@ static void __init numa_clear_kernel_node_hotplug(void) for_each_reserved_mem_region(mb_region) { int nid = memblock_get_region_node(mb_region); - if (nid != MAX_NUMNODES) + if (nid != NUMA_NO_NODE) node_set(nid, reserved_nodemask); } @@ -614,9 +614,9 @@ static int __init numa_init(int (*init_func)(void)) nodes_clear(node_online_map); memset(&numa_meminfo, 0, sizeof(numa_meminfo)); WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.memory, - MAX_NUMNODES)); + NUMA_NO_NODE)); WARN_ON(memblock_set_node(0, ULLONG_MAX, &memblock.reserved, - MAX_NUMNODES)); + NUMA_NO_NODE)); /* In case that parsing SRAT failed. */ WARN_ON(memblock_clear_hotplug(0, ULLONG_MAX)); numa_reset_distance(); diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index 104544359d..025fd7ea5d 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -24,6 +24,7 @@ #include <linux/memblock.h> #include <linux/init.h> +#include <asm/pgtable_areas.h> #include "numa_internal.h" diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index 37d51cfd77..36b603d0cd 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -240,6 +240,8 @@ void pat_cpu_init(void) } wrmsrl(MSR_IA32_CR_PAT, pat_msr_val); + + __flush_tlb_all(); } /** @@ -296,13 +298,8 @@ void __init pat_bp_init(void) /* * 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)) { + if (pat_disabled || cpu_feature_enabled(X86_FEATURE_XENPV)) { init_cache_modes(pat_msr_val); return; } diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index b4073fb452..19fdfbb171 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -687,7 +687,7 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, return NULL; *level = PG_LEVEL_512G; - if (p4d_large(*p4d) || !p4d_present(*p4d)) + if (p4d_leaf(*p4d) || !p4d_present(*p4d)) return (pte_t *)p4d; *nx |= p4d_flags(*p4d) & _PAGE_NX; @@ -709,7 +709,7 @@ pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address, return NULL; *level = PG_LEVEL_2M; - if (pmd_large(*pmd) || !pmd_present(*pmd)) + if (pmd_leaf(*pmd) || !pmd_present(*pmd)) return (pte_t *)pmd; *nx |= pmd_flags(*pmd) & _PAGE_NX; @@ -774,7 +774,7 @@ pmd_t *lookup_pmd_address(unsigned long address) return NULL; p4d = p4d_offset(pgd, address); - if (p4d_none(*p4d) || p4d_large(*p4d) || !p4d_present(*p4d)) + if (p4d_none(*p4d) || p4d_leaf(*p4d) || !p4d_present(*p4d)) return NULL; pud = pud_offset(p4d, address); @@ -1271,7 +1271,7 @@ static void unmap_pmd_range(pud_t *pud, unsigned long start, unsigned long end) * Try to unmap in 2M chunks. */ while (end - start >= PMD_SIZE) { - if (pmd_large(*pmd)) + if (pmd_leaf(*pmd)) pmd_clear(pmd); else __unmap_pmd_range(pud, pmd, start, start + PMD_SIZE); @@ -2197,7 +2197,7 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc) /* Notify hypervisor that we are about to set/clr encryption attribute. */ if (!x86_platform.guest.enc_status_change_prepare(addr, numpages, enc)) - return -EIO; + goto vmm_fail; ret = __change_page_attr_set_clr(&cpa, 1); @@ -2210,13 +2210,20 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc) */ cpa_flush(&cpa, 0); + if (ret) + return ret; + /* Notify hypervisor that we have successfully set/clr encryption attribute. */ - if (!ret) { - if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc)) - ret = -EIO; - } + if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc)) + goto vmm_fail; - return ret; + return 0; + +vmm_fail: + WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s.\n", + (void *)addr, numpages, enc ? "private" : "shared"); + + return -EIO; } static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc) diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index a67bb8f982..103cbccf1d 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -293,7 +293,7 @@ static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp) for (i = 0; i < PREALLOCATED_PMDS; i++) mop_up_one_pmd(mm, &pgdp[i]); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION if (!boot_cpu_has(X86_FEATURE_PTI)) return; @@ -325,7 +325,7 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[]) } } -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION static void pgd_prepopulate_user_pmd(struct mm_struct *mm, pgd_t *k_pgd, pmd_t *pmds[]) { @@ -631,6 +631,8 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { + VM_WARN_ON_ONCE(!pmd_present(*pmdp)); + /* * No flush is necessary. Once an invalid PTE is established, the PTE's * access and dirty bits cannot be updated. @@ -792,7 +794,7 @@ int pud_clear_huge(pud_t *pud) */ int pmd_clear_huge(pmd_t *pmd) { - if (pmd_large(*pmd)) { + if (pmd_leaf(*pmd)) { pmd_clear(pmd); return 1; } diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 912b1da7ed..2e69abf4f8 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -185,7 +185,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address) set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page))); } - BUILD_BUG_ON(pgd_large(*pgd) != 0); + BUILD_BUG_ON(pgd_leaf(*pgd) != 0); return p4d_offset(pgd, address); } @@ -206,7 +206,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) if (!p4d) return NULL; - BUILD_BUG_ON(p4d_large(*p4d) != 0); + BUILD_BUG_ON(p4d_leaf(*p4d) != 0); if (p4d_none(*p4d)) { unsigned long new_pud_page = __get_free_page(gfp); if (WARN_ON_ONCE(!new_pud_page)) @@ -252,7 +252,7 @@ static pte_t *pti_user_pagetable_walk_pte(unsigned long address) return NULL; /* We can't do anything sensible if we hit a large mapping. */ - if (pmd_large(*pmd)) { + if (pmd_leaf(*pmd)) { WARN_ON(1); return NULL; } @@ -341,7 +341,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end, continue; } - if (pmd_large(*pmd) || level == PTI_CLONE_PMD) { + if (pmd_leaf(*pmd) || level == PTI_CLONE_PMD) { target_pmd = pti_user_pagetable_walk_pmd(addr); if (WARN_ON(!target_pmd)) return; diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 5768d386ef..44ac64f3a0 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -89,10 +89,10 @@ #define CR3_HW_ASID_BITS 12 /* - * When enabled, PAGE_TABLE_ISOLATION consumes a single bit for + * When enabled, MITIGATION_PAGE_TABLE_ISOLATION consumes a single bit for * user/kernel switches */ -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION # define PTI_CONSUMED_PCID_BITS 1 #else # define PTI_CONSUMED_PCID_BITS 0 @@ -114,7 +114,7 @@ static inline u16 kern_pcid(u16 asid) { VM_WARN_ON_ONCE(asid > MAX_ASID_AVAILABLE); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION /* * Make sure that the dynamic ASID space does not conflict with the * bit we are using to switch between user and kernel ASIDs. @@ -149,7 +149,7 @@ static inline u16 kern_pcid(u16 asid) static inline u16 user_pcid(u16 asid) { u16 ret = kern_pcid(asid); -#ifdef CONFIG_PAGE_TABLE_ISOLATION +#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION ret |= 1 << X86_CR3_PTI_PCID_USER_BIT; #endif return ret; @@ -262,7 +262,7 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen, static inline void invalidate_user_asid(u16 asid) { /* There is no user ASID if address space separation is off */ - if (!IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) + if (!IS_ENABLED(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION)) return; /* @@ -299,7 +299,7 @@ static void load_new_mm_cr3(pgd_t *pgdir, u16 new_asid, unsigned long lam, write_cr3(new_mm_cr3); } -void leave_mm(int cpu) +void leave_mm(void) { struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm); @@ -327,7 +327,7 @@ void switch_mm(struct mm_struct *prev, struct mm_struct *next, unsigned long flags; local_irq_save(flags); - switch_mm_irqs_off(prev, next, tsk); + switch_mm_irqs_off(NULL, next, tsk); local_irq_restore(flags); } @@ -492,10 +492,16 @@ void cr4_update_pce(void *ignored) static inline void cr4_update_pce_mm(struct mm_struct *mm) { } #endif -void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, +/* + * This optimizes when not actually switching mm's. Some architectures use the + * 'unused' argument for this optimization, but x86 must use + * 'cpu_tlbstate.loaded_mm' instead because it does not always keep + * 'current->active_mm' up to date. + */ +void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next, struct task_struct *tsk) { - struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm); + struct mm_struct *prev = this_cpu_read(cpu_tlbstate.loaded_mm); u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid); unsigned long new_lam = mm_lam_cr3_mask(next); bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy); @@ -504,15 +510,6 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, bool need_flush; u16 new_asid; - /* - * NB: The scheduler will call us with prev == next when switching - * from lazy TLB mode to normal mode if active_mm isn't changing. - * When this happens, we don't assume that CR3 (and hence - * cpu_tlbstate.loaded_mm) matches next. - * - * NB: leave_mm() calls us with prev == NULL and tsk == NULL. - */ - /* We don't want flush_tlb_func() to run concurrently with us. */ if (IS_ENABLED(CONFIG_PROVE_LOCKING)) WARN_ON_ONCE(!irqs_disabled()); @@ -527,7 +524,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * isn't free. */ #ifdef CONFIG_DEBUG_VM - if (WARN_ON_ONCE(__read_cr3() != build_cr3(real_prev->pgd, prev_asid, + if (WARN_ON_ONCE(__read_cr3() != build_cr3(prev->pgd, prev_asid, tlbstate_lam_cr3_mask()))) { /* * If we were to BUG here, we'd be very likely to kill @@ -559,7 +556,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * provides that full memory barrier and core serializing * instruction. */ - if (real_prev == next) { + if (prev == next) { /* Not actually switching mm's */ VM_WARN_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) != next->context.ctx_id); @@ -574,7 +571,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * mm_cpumask. The TLB shootdown code can figure out from * cpu_tlbstate_shared.is_lazy whether or not to send an IPI. */ - if (WARN_ON_ONCE(real_prev != &init_mm && + if (WARN_ON_ONCE(prev != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))) cpumask_set_cpu(cpu, mm_cpumask(next)); @@ -616,10 +613,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, * Skip kernel threads; we never send init_mm TLB flushing IPIs, * but the bitmap manipulation can cause cache line contention. */ - if (real_prev != &init_mm) { + if (prev != &init_mm) { VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, - mm_cpumask(real_prev))); - cpumask_clear_cpu(cpu, mm_cpumask(real_prev)); + mm_cpumask(prev))); + cpumask_clear_cpu(cpu, mm_cpumask(prev)); } /* @@ -656,9 +653,9 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next, this_cpu_write(cpu_tlbstate.loaded_mm, next); this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid); - if (next != real_prev) { + if (next != prev) { cr4_update_pce_mm(next); - switch_ldt(real_prev, next); + switch_ldt(prev, next); } } diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index f415c2cf53..59cbc94b6e 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -113,6 +113,7 @@ static int bpf_size_to_x86_bytes(int bpf_size) /* Pick a register outside of BPF range for JIT internal work */ #define AUX_REG (MAX_BPF_JIT_REG + 1) #define X86_REG_R9 (MAX_BPF_JIT_REG + 2) +#define X86_REG_R12 (MAX_BPF_JIT_REG + 3) /* * The following table maps BPF registers to x86-64 registers. @@ -139,6 +140,7 @@ static const int reg2hex[] = { [BPF_REG_AX] = 2, /* R10 temp register */ [AUX_REG] = 3, /* R11 temp register */ [X86_REG_R9] = 1, /* R9 register, 6th function argument */ + [X86_REG_R12] = 4, /* R12 callee saved */ }; static const int reg2pt_regs[] = { @@ -167,6 +169,7 @@ static bool is_ereg(u32 reg) BIT(BPF_REG_8) | BIT(BPF_REG_9) | BIT(X86_REG_R9) | + BIT(X86_REG_R12) | BIT(BPF_REG_AX)); } @@ -205,6 +208,17 @@ static u8 add_2mod(u8 byte, u32 r1, u32 r2) return byte; } +static u8 add_3mod(u8 byte, u32 r1, u32 r2, u32 index) +{ + if (is_ereg(r1)) + byte |= 1; + if (is_ereg(index)) + byte |= 2; + if (is_ereg(r2)) + byte |= 4; + return byte; +} + /* Encode 'dst_reg' register into x86-64 opcode 'byte' */ static u8 add_1reg(u8 byte, u32 dst_reg) { @@ -466,7 +480,7 @@ static int emit_call(u8 **pprog, void *func, void *ip) static int emit_rsb_call(u8 **pprog, void *func, void *ip) { OPTIMIZER_HIDE_VAR(func); - ip += x86_call_depth_emit_accounting(pprog, func); + ip += x86_call_depth_emit_accounting(pprog, func, ip); return emit_patch(pprog, func, ip, 0xE8); } @@ -553,7 +567,7 @@ static void emit_indirect_jump(u8 **pprog, int reg, u8 *ip) 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)) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) || IS_ENABLED(CONFIG_MITIGATION_SLS)) EMIT1(0xCC); /* int3 */ } @@ -568,7 +582,7 @@ static void emit_return(u8 **pprog, u8 *ip) emit_jump(&prog, x86_return_thunk, ip); } else { EMIT1(0xC3); /* ret */ - if (IS_ENABLED(CONFIG_SLS)) + if (IS_ENABLED(CONFIG_MITIGATION_SLS)) EMIT1(0xCC); /* int3 */ } @@ -645,6 +659,8 @@ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog, pop_r12(&prog); } else { pop_callee_regs(&prog, callee_regs_used); + if (bpf_arena_get_kern_vm_start(bpf_prog->aux->arena)) + pop_r12(&prog); } EMIT1(0x58); /* pop rax */ @@ -704,6 +720,8 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog, pop_r12(&prog); } else { pop_callee_regs(&prog, callee_regs_used); + if (bpf_arena_get_kern_vm_start(bpf_prog->aux->arena)) + pop_r12(&prog); } EMIT1(0x58); /* pop rax */ @@ -887,6 +905,18 @@ static void emit_insn_suffix(u8 **pprog, u32 ptr_reg, u32 val_reg, int off) *pprog = prog; } +static void emit_insn_suffix_SIB(u8 **pprog, u32 ptr_reg, u32 val_reg, u32 index_reg, int off) +{ + u8 *prog = *pprog; + + if (is_imm8(off)) { + EMIT3(add_2reg(0x44, BPF_REG_0, val_reg), add_2reg(0, ptr_reg, index_reg) /* SIB */, off); + } else { + EMIT2_off32(add_2reg(0x84, BPF_REG_0, val_reg), add_2reg(0, ptr_reg, index_reg) /* SIB */, off); + } + *pprog = prog; +} + /* * Emit a REX byte if it will be necessary to address these registers */ @@ -968,6 +998,37 @@ static void emit_ldsx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) *pprog = prog; } +static void emit_ldx_index(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, u32 index_reg, int off) +{ + u8 *prog = *pprog; + + switch (size) { + case BPF_B: + /* movzx rax, byte ptr [rax + r12 + off] */ + EMIT3(add_3mod(0x40, src_reg, dst_reg, index_reg), 0x0F, 0xB6); + break; + case BPF_H: + /* movzx rax, word ptr [rax + r12 + off] */ + EMIT3(add_3mod(0x40, src_reg, dst_reg, index_reg), 0x0F, 0xB7); + break; + case BPF_W: + /* mov eax, dword ptr [rax + r12 + off] */ + EMIT2(add_3mod(0x40, src_reg, dst_reg, index_reg), 0x8B); + break; + case BPF_DW: + /* mov rax, qword ptr [rax + r12 + off] */ + EMIT2(add_3mod(0x48, src_reg, dst_reg, index_reg), 0x8B); + break; + } + emit_insn_suffix_SIB(&prog, src_reg, dst_reg, index_reg, off); + *pprog = prog; +} + +static void emit_ldx_r12(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) +{ + emit_ldx_index(pprog, size, dst_reg, src_reg, X86_REG_R12, off); +} + /* STX: *(u8*)(dst_reg + off) = src_reg */ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) { @@ -1002,6 +1063,71 @@ static void emit_stx(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) *pprog = prog; } +/* STX: *(u8*)(dst_reg + index_reg + off) = src_reg */ +static void emit_stx_index(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, u32 index_reg, int off) +{ + u8 *prog = *pprog; + + switch (size) { + case BPF_B: + /* mov byte ptr [rax + r12 + off], al */ + EMIT2(add_3mod(0x40, dst_reg, src_reg, index_reg), 0x88); + break; + case BPF_H: + /* mov word ptr [rax + r12 + off], ax */ + EMIT3(0x66, add_3mod(0x40, dst_reg, src_reg, index_reg), 0x89); + break; + case BPF_W: + /* mov dword ptr [rax + r12 + 1], eax */ + EMIT2(add_3mod(0x40, dst_reg, src_reg, index_reg), 0x89); + break; + case BPF_DW: + /* mov qword ptr [rax + r12 + 1], rax */ + EMIT2(add_3mod(0x48, dst_reg, src_reg, index_reg), 0x89); + break; + } + emit_insn_suffix_SIB(&prog, dst_reg, src_reg, index_reg, off); + *pprog = prog; +} + +static void emit_stx_r12(u8 **pprog, u32 size, u32 dst_reg, u32 src_reg, int off) +{ + emit_stx_index(pprog, size, dst_reg, src_reg, X86_REG_R12, off); +} + +/* ST: *(u8*)(dst_reg + index_reg + off) = imm32 */ +static void emit_st_index(u8 **pprog, u32 size, u32 dst_reg, u32 index_reg, int off, int imm) +{ + u8 *prog = *pprog; + + switch (size) { + case BPF_B: + /* mov byte ptr [rax + r12 + off], imm8 */ + EMIT2(add_3mod(0x40, dst_reg, 0, index_reg), 0xC6); + break; + case BPF_H: + /* mov word ptr [rax + r12 + off], imm16 */ + EMIT3(0x66, add_3mod(0x40, dst_reg, 0, index_reg), 0xC7); + break; + case BPF_W: + /* mov dword ptr [rax + r12 + 1], imm32 */ + EMIT2(add_3mod(0x40, dst_reg, 0, index_reg), 0xC7); + break; + case BPF_DW: + /* mov qword ptr [rax + r12 + 1], imm32 */ + EMIT2(add_3mod(0x48, dst_reg, 0, index_reg), 0xC7); + break; + } + emit_insn_suffix_SIB(&prog, dst_reg, 0, index_reg, off); + EMIT(imm, bpf_size_to_x86_bytes(size)); + *pprog = prog; +} + +static void emit_st_r12(u8 **pprog, u32 size, u32 dst_reg, int off, int imm) +{ + emit_st_index(pprog, size, dst_reg, X86_REG_R12, off, imm); +} + static int emit_atomic(u8 **pprog, u8 atomic_op, u32 dst_reg, u32 src_reg, s16 off, u8 bpf_size) { @@ -1043,12 +1169,15 @@ static int emit_atomic(u8 **pprog, u8 atomic_op, return 0; } +#define DONT_CLEAR 1 + bool ex_handler_bpf(const struct exception_table_entry *x, struct pt_regs *regs) { u32 reg = x->fixup >> 8; /* jump over faulting load and clear dest register */ - *(unsigned long *)((void *)regs + reg) = 0; + if (reg != DONT_CLEAR) + *(unsigned long *)((void *)regs + reg) = 0; regs->ip += x->fixup & 0xff; return true; } @@ -1147,11 +1276,15 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image bool tail_call_seen = false; bool seen_exit = false; u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; + u64 arena_vm_start, user_vm_start; int i, excnt = 0; int ilen, proglen = 0; u8 *prog = temp; int err; + arena_vm_start = bpf_arena_get_kern_vm_start(bpf_prog->aux->arena); + user_vm_start = bpf_arena_get_user_vm_start(bpf_prog->aux->arena); + detect_reg_usage(insn, insn_cnt, callee_regs_used, &tail_call_seen); @@ -1172,8 +1305,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image push_r12(&prog); push_callee_regs(&prog, all_callee_regs_used); } else { + if (arena_vm_start) + push_r12(&prog); push_callee_regs(&prog, callee_regs_used); } + if (arena_vm_start) + emit_mov_imm64(&prog, X86_REG_R12, + arena_vm_start >> 32, (u32) arena_vm_start); ilen = prog - temp; if (rw_image) @@ -1213,6 +1351,40 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image break; case BPF_ALU64 | BPF_MOV | BPF_X: + if (insn->off == BPF_ADDR_SPACE_CAST && + insn->imm == 1U << 16) { + if (dst_reg != src_reg) + /* 32-bit mov */ + emit_mov_reg(&prog, false, dst_reg, src_reg); + /* shl dst_reg, 32 */ + maybe_emit_1mod(&prog, dst_reg, true); + EMIT3(0xC1, add_1reg(0xE0, dst_reg), 32); + + /* or dst_reg, user_vm_start */ + maybe_emit_1mod(&prog, dst_reg, true); + if (is_axreg(dst_reg)) + EMIT1_off32(0x0D, user_vm_start >> 32); + else + EMIT2_off32(0x81, add_1reg(0xC8, dst_reg), user_vm_start >> 32); + + /* rol dst_reg, 32 */ + maybe_emit_1mod(&prog, dst_reg, true); + EMIT3(0xC1, add_1reg(0xC0, dst_reg), 32); + + /* xor r11, r11 */ + EMIT3(0x4D, 0x31, 0xDB); + + /* test dst_reg32, dst_reg32; check if lower 32-bit are zero */ + maybe_emit_mod(&prog, dst_reg, dst_reg, false); + EMIT2(0x85, add_2reg(0xC0, dst_reg, dst_reg)); + + /* cmove r11, dst_reg; if so, set dst_reg to zero */ + /* WARNING: Intel swapped src/dst register encoding in CMOVcc !!! */ + maybe_emit_mod(&prog, AUX_REG, dst_reg, true); + EMIT3(0x0F, 0x44, add_2reg(0xC0, AUX_REG, dst_reg)); + break; + } + fallthrough; case BPF_ALU | BPF_MOV | BPF_X: if (insn->off == 0) emit_mov_reg(&prog, @@ -1564,6 +1736,56 @@ st: if (is_imm8(insn->off)) emit_stx(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); break; + case BPF_ST | BPF_PROBE_MEM32 | BPF_B: + case BPF_ST | BPF_PROBE_MEM32 | BPF_H: + case BPF_ST | BPF_PROBE_MEM32 | BPF_W: + case BPF_ST | BPF_PROBE_MEM32 | BPF_DW: + start_of_ldx = prog; + emit_st_r12(&prog, BPF_SIZE(insn->code), dst_reg, insn->off, insn->imm); + goto populate_extable; + + /* LDX: dst_reg = *(u8*)(src_reg + r12 + off) */ + case BPF_LDX | BPF_PROBE_MEM32 | BPF_B: + case BPF_LDX | BPF_PROBE_MEM32 | BPF_H: + case BPF_LDX | BPF_PROBE_MEM32 | BPF_W: + case BPF_LDX | BPF_PROBE_MEM32 | BPF_DW: + case BPF_STX | BPF_PROBE_MEM32 | BPF_B: + case BPF_STX | BPF_PROBE_MEM32 | BPF_H: + case BPF_STX | BPF_PROBE_MEM32 | BPF_W: + case BPF_STX | BPF_PROBE_MEM32 | BPF_DW: + start_of_ldx = prog; + if (BPF_CLASS(insn->code) == BPF_LDX) + emit_ldx_r12(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); + else + emit_stx_r12(&prog, BPF_SIZE(insn->code), dst_reg, src_reg, insn->off); +populate_extable: + { + struct exception_table_entry *ex; + u8 *_insn = image + proglen + (start_of_ldx - temp); + s64 delta; + + if (!bpf_prog->aux->extable) + break; + + if (excnt >= bpf_prog->aux->num_exentries) { + pr_err("mem32 extable bug\n"); + return -EFAULT; + } + ex = &bpf_prog->aux->extable[excnt++]; + + delta = _insn - (u8 *)&ex->insn; + /* switch ex to rw buffer for writes */ + ex = (void *)rw_image + ((void *)ex - (void *)image); + + ex->insn = delta; + + ex->data = EX_TYPE_BPF; + + ex->fixup = (prog - start_of_ldx) | + ((BPF_CLASS(insn->code) == BPF_LDX ? reg2pt_regs[dst_reg] : DONT_CLEAR) << 8); + } + break; + /* LDX: dst_reg = *(u8*)(src_reg + off) */ case BPF_LDX | BPF_MEM | BPF_B: case BPF_LDX | BPF_PROBE_MEM | BPF_B: @@ -1743,20 +1965,17 @@ st: if (is_imm8(insn->off)) /* call */ case BPF_JMP | BPF_CALL: { - int offs; + u8 *ip = image + addrs[i - 1]; func = (u8 *) __bpf_call_base + imm32; if (tail_call_reachable) { RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth); - if (!imm32) - return -EINVAL; - offs = 7 + x86_call_depth_emit_accounting(&prog, func); - } else { - if (!imm32) - return -EINVAL; - offs = x86_call_depth_emit_accounting(&prog, func); + ip += 7; } - if (emit_call(&prog, func, image + addrs[i - 1] + offs)) + if (!imm32) + return -EINVAL; + ip += x86_call_depth_emit_accounting(&prog, func, ip); + if (emit_call(&prog, func, ip)) return -EINVAL; break; } @@ -2029,6 +2248,8 @@ emit_jmp: pop_r12(&prog); } else { pop_callee_regs(&prog, callee_regs_used); + if (arena_vm_start) + pop_r12(&prog); } EMIT1(0xC9); /* leave */ emit_return(&prog, image + addrs[i - 1] + (prog - temp)); @@ -2604,7 +2825,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im * Direct-call fentry stub, as such it needs accounting for the * __fentry__ call. */ - x86_call_depth_emit_accounting(&prog, NULL); + x86_call_depth_emit_accounting(&prog, NULL, image); } EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ @@ -3235,3 +3456,19 @@ void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, BUG_ON(ret < 0); } } + +bool bpf_jit_supports_arena(void) +{ + return true; +} + +bool bpf_jit_supports_ptr_xchg(void) +{ + return true; +} + +/* x86-64 JIT emits its own code to filter user addresses so return 0 here */ +u64 bpf_arch_uaddress_limit(void) +{ + return 0; +} diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index b18ce19981..c10083a8e6 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1273,7 +1273,7 @@ static int emit_jmp_edx(u8 **pprog, u8 *ip) u8 *prog = *pprog; int cnt = 0; -#ifdef CONFIG_RETPOLINE +#ifdef CONFIG_MITIGATION_RETPOLINE EMIT1_off32(0xE9, (u8 *)__x86_indirect_thunk_edx - (ip + 5)); #else EMIT2(0xFF, 0xE2); diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index 0cc9520666..39255f0eb1 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -518,7 +518,34 @@ static bool __ref pci_mmcfg_reserved(struct device *dev, { struct resource *conflict; - if (!early && !acpi_disabled) { + if (early) { + + /* + * Don't try to do this check unless configuration type 1 + * is available. How about type 2? + */ + + /* + * 946f2ee5c731 ("Check that MCFG points to an e820 + * reserved area") added this E820 check in 2006 to work + * around BIOS defects. + * + * Per PCI Firmware r3.3, sec 4.1.2, ECAM space must be + * reserved by a PNP0C02 resource, but it need not be + * mentioned in E820. Before the ACPI interpreter is + * available, we can't check for PNP0C02 resources, so + * there's no reliable way to verify the region in this + * early check. Keep it only for the old machines that + * motivated 946f2ee5c731. + */ + if (dmi_get_bios_year() < 2016 && raw_pci_ops) + return is_mmconf_reserved(e820__mapped_all, cfg, dev, + "E820 entry"); + + return true; + } + + if (!acpi_disabled) { if (is_mmconf_reserved(is_acpi_reserved, cfg, dev, "ACPI motherboard resource")) return true; @@ -551,16 +578,7 @@ static bool __ref pci_mmcfg_reserved(struct device *dev, * For MCFG information constructed from hotpluggable host bridge's * _CBA method, just assume it's reserved. */ - if (pci_mmcfg_running_state) - return true; - - /* Don't try to do this check unless configuration - type 1 is available. how about type 2 ?*/ - if (raw_pci_ops) - return is_mmconf_reserved(e820__mapped_all, cfg, dev, - "E820 entry"); - - return false; + return pci_mmcfg_running_state; } static void __init pci_mmcfg_reject_broken(int early) diff --git a/arch/x86/platform/atom/punit_atom_debug.c b/arch/x86/platform/atom/punit_atom_debug.c index f8ed5f66cd..6b9c6deca8 100644 --- a/arch/x86/platform/atom/punit_atom_debug.c +++ b/arch/x86/platform/atom/punit_atom_debug.c @@ -7,6 +7,9 @@ * Copyright (c) 2015, Intel Corporation. */ +#define pr_fmt(fmt) "punit_atom: " fmt + +#include <linux/acpi.h> #include <linux/module.h> #include <linux/init.h> #include <linux/device.h> @@ -117,6 +120,51 @@ static void punit_dbgfs_unregister(void) debugfs_remove_recursive(punit_dbg_file); } +#if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND) +static const struct punit_device *punit_dev; + +static void punit_s2idle_check(void) +{ + const struct punit_device *punit_devp; + u32 punit_pwr_status, dstate; + int status; + + for (punit_devp = punit_dev; punit_devp->name; punit_devp++) { + /* Skip MIO, it is on till the very last moment */ + if (punit_devp->reg == MIO_SS_PM) + continue; + + status = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ, + punit_devp->reg, &punit_pwr_status); + if (status) { + pr_err("%s read failed\n", punit_devp->name); + } else { + dstate = (punit_pwr_status >> punit_devp->sss_pos) & 3; + if (!dstate) + pr_err("%s is in D0 prior to s2idle\n", punit_devp->name); + } + } +} + +static struct acpi_s2idle_dev_ops punit_s2idle_ops = { + .check = punit_s2idle_check, +}; + +static void punit_s2idle_check_register(struct punit_device *punit_device) +{ + punit_dev = punit_device; + acpi_register_lps0_dev(&punit_s2idle_ops); +} + +static void punit_s2idle_check_unregister(void) +{ + acpi_unregister_lps0_dev(&punit_s2idle_ops); +} +#else +static void punit_s2idle_check_register(struct punit_device *punit_device) {} +static void punit_s2idle_check_unregister(void) {} +#endif + #define X86_MATCH(model, data) \ X86_MATCH_VENDOR_FAM_MODEL_FEATURE(INTEL, 6, INTEL_FAM6_##model, \ X86_FEATURE_MWAIT, data) @@ -131,19 +179,23 @@ MODULE_DEVICE_TABLE(x86cpu, intel_punit_cpu_ids); static int __init punit_atom_debug_init(void) { + struct punit_device *punit_device; const struct x86_cpu_id *id; id = x86_match_cpu(intel_punit_cpu_ids); if (!id) return -ENODEV; - punit_dbgfs_register((struct punit_device *)id->driver_data); + punit_device = (struct punit_device *)id->driver_data; + punit_dbgfs_register(punit_device); + punit_s2idle_check_register(punit_device); return 0; } static void __exit punit_atom_debug_exit(void) { + punit_s2idle_check_unregister(); punit_dbgfs_unregister(); } diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c index 40745664d9..f32451bdcf 100644 --- a/arch/x86/platform/ce4100/ce4100.c +++ b/arch/x86/platform/ce4100/ce4100.c @@ -135,13 +135,13 @@ static void sdv_pci_init(void) */ void __init x86_ce4100_early_setup(void) { - x86_init.oem.arch_setup = sdv_arch_setup; - x86_init.resources.probe_roms = x86_init_noop; - x86_init.mpparse.get_smp_config = x86_init_uint_noop; - x86_init.mpparse.find_smp_config = x86_init_noop; - x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc_nocheck; - x86_init.pci.init = ce4100_pci_init; - x86_init.pci.init_irq = sdv_pci_init; + x86_init.oem.arch_setup = sdv_arch_setup; + x86_init.resources.probe_roms = x86_init_noop; + x86_init.mpparse.find_mptable = x86_init_noop; + x86_init.mpparse.early_parse_smp_cfg = x86_init_noop; + x86_init.mpparse.parse_smp_cfg = x86_dtb_parse_smp_config; + x86_init.pci.init = ce4100_pci_init; + x86_init.pci.init_irq = sdv_pci_init; /* * By default, the reboot method is ACPI which is supported by the diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index e9f99c56f3..f090ec972d 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -950,3 +950,8 @@ umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n) } return attr->mode; } + +enum efi_secureboot_mode __x86_ima_efi_boot_mode(void) +{ + return boot_params.secure_boot; +} diff --git a/arch/x86/platform/efi/memmap.c b/arch/x86/platform/efi/memmap.c index 4ef20b49eb..6ed1935504 100644 --- a/arch/x86/platform/efi/memmap.c +++ b/arch/x86/platform/efi/memmap.c @@ -92,12 +92,22 @@ int __init efi_memmap_alloc(unsigned int num_entries, */ int __init efi_memmap_install(struct efi_memory_map_data *data) { + unsigned long size = efi.memmap.desc_size * efi.memmap.nr_map; + unsigned long flags = efi.memmap.flags; + u64 phys = efi.memmap.phys_map; + int ret; + efi_memmap_unmap(); if (efi_enabled(EFI_PARAVIRT)) return 0; - return __efi_memmap_init(data); + ret = __efi_memmap_init(data); + if (ret) + return ret; + + __efi_memmap_free(phys, size, flags); + return 0; } /** diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c index f4592dc7a1..7be71c2cdc 100644 --- a/arch/x86/platform/intel-mid/intel-mid.c +++ b/arch/x86/platform/intel-mid/intel-mid.c @@ -118,7 +118,8 @@ void __init x86_intel_mid_early_setup(void) machine_ops.emergency_restart = intel_mid_reboot; /* Avoid searching for BIOS MP tables */ - x86_init.mpparse.find_smp_config = x86_init_noop; - x86_init.mpparse.get_smp_config = x86_init_uint_noop; + x86_init.mpparse.find_mptable = x86_init_noop; + x86_init.mpparse.early_parse_smp_cfg = x86_init_noop; + x86_init.mpparse.parse_smp_cfg = x86_init_noop; set_bit(MP_BUS_ISA, mp_bus_not_pci); } diff --git a/arch/x86/platform/pvh/enlighten.c b/arch/x86/platform/pvh/enlighten.c index a12117f3d4..8c2d4b8de2 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -3,6 +3,7 @@ #include <xen/hvc-console.h> +#include <asm/bootparam.h> #include <asm/io_apic.h> #include <asm/hypervisor.h> #include <asm/e820/api.h> diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile index 379777572b..e0cd7afd53 100644 --- a/arch/x86/power/Makefile +++ b/arch/x86/power/Makefile @@ -5,7 +5,7 @@ CFLAGS_cpu.o := -fno-stack-protector # Clang may incorrectly inline functions with stack protector enabled into -# __restore_processor_state(): https://bugs.llvm.org/show_bug.cgi?id=47479 +# __restore_processor_state(): https://llvm.org/pr47479 CFLAGS_REMOVE_cpu.o := $(CC_FLAGS_LTO) obj-$(CONFIG_PM_SLEEP) += cpu.o diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c index d8af46e677..5b81d19cd1 100644 --- a/arch/x86/power/hibernate.c +++ b/arch/x86/power/hibernate.c @@ -165,7 +165,7 @@ int relocate_restore_code(void) pgd = (pgd_t *)__va(read_cr3_pa()) + pgd_index(relocated_restore_code); p4d = p4d_offset(pgd, relocated_restore_code); - if (p4d_large(*p4d)) { + if (p4d_leaf(*p4d)) { set_p4d(p4d, __p4d(p4d_val(*p4d) & ~_PAGE_NX)); goto out; } @@ -175,7 +175,7 @@ int relocate_restore_code(void) goto out; } pmd = pmd_offset(pud, relocated_restore_code); - if (pmd_large(*pmd)) { + if (pmd_leaf(*pmd)) { set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX)); goto out; } diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile index 8d1c82795e..a18591f6e6 100644 --- a/arch/x86/purgatory/Makefile +++ b/arch/x86/purgatory/Makefile @@ -62,7 +62,7 @@ ifdef CONFIG_STACKPROTECTOR_STRONG PURGATORY_CFLAGS_REMOVE += -fstack-protector-strong endif -ifdef CONFIG_RETPOLINE +ifdef CONFIG_MITIGATION_RETPOLINE PURGATORY_CFLAGS_REMOVE += $(RETPOLINE_CFLAGS) endif diff --git a/arch/x86/realmode/rm/trampoline_64.S b/arch/x86/realmode/rm/trampoline_64.S index c9f76fae90..14d9c7daf9 100644 --- a/arch/x86/realmode/rm/trampoline_64.S +++ b/arch/x86/realmode/rm/trampoline_64.S @@ -37,13 +37,15 @@ .text .code16 -.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0 +.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0 lock_rip=0 /* * Make sure only one CPU fiddles with the realmode stack */ .Llock_rm\@: .if \lock_pa lock btsl $0, pa_tr_lock + .elseif \lock_rip + lock btsl $0, tr_lock(%rip) .else lock btsl $0, tr_lock .endif @@ -220,6 +222,35 @@ SYM_CODE_START(trampoline_start64) lidt tr_idt(%rip) lgdt tr_gdt64(%rip) + /* Check if paging mode has to be changed */ + movq %cr4, %rax + xorl tr_cr4(%rip), %eax + testl $X86_CR4_LA57, %eax + jnz .L_switch_paging + + /* Paging mode is correct proceed in 64-bit mode */ + + LOCK_AND_LOAD_REALMODE_ESP lock_rip=1 + + movw $__KERNEL_DS, %dx + movl %edx, %ss + addl $pa_real_mode_base, %esp + movl %edx, %ds + movl %edx, %es + movl %edx, %fs + movl %edx, %gs + + movl $pa_trampoline_pgd, %eax + movq %rax, %cr3 + + pushq $__KERNEL_CS + pushq tr_start(%rip) + lretq +.L_switch_paging: + /* + * To switch between 4- and 5-level paging modes, it is necessary + * to disable paging. This must be done in the compatibility mode. + */ ljmpl *tr_compat(%rip) SYM_CODE_END(trampoline_start64) diff --git a/arch/x86/um/shared/sysdep/archsetjmp.h b/arch/x86/um/shared/sysdep/archsetjmp.h index 166cedbab9..8c81d1a604 100644 --- a/arch/x86/um/shared/sysdep/archsetjmp.h +++ b/arch/x86/um/shared/sysdep/archsetjmp.h @@ -1,6 +1,13 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_UM_SYSDEP_ARCHSETJMP_H +#define __X86_UM_SYSDEP_ARCHSETJMP_H + #ifdef __i386__ #include "archsetjmp_32.h" #else #include "archsetjmp_64.h" #endif + +unsigned long get_thread_reg(int reg, jmp_buf *buf); + +#endif /* __X86_UM_SYSDEP_ARCHSETJMP_H */ diff --git a/arch/x86/virt/Makefile b/arch/x86/virt/Makefile index 1e36502cd7..ea343fc392 100644 --- a/arch/x86/virt/Makefile +++ b/arch/x86/virt/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y += vmx/ +obj-y += svm/ vmx/ diff --git a/arch/x86/virt/svm/Makefile b/arch/x86/virt/svm/Makefile new file mode 100644 index 0000000000..ef2a31bdcc --- /dev/null +++ b/arch/x86/virt/svm/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 + +obj-$(CONFIG_KVM_AMD_SEV) += sev.o diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c new file mode 100644 index 0000000000..0ae10535c6 --- /dev/null +++ b/arch/x86/virt/svm/sev.c @@ -0,0 +1,606 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * AMD SVM-SEV Host Support. + * + * Copyright (C) 2023 Advanced Micro Devices, Inc. + * + * Author: Ashish Kalra <ashish.kalra@amd.com> + * + */ + +#include <linux/cc_platform.h> +#include <linux/printk.h> +#include <linux/mm_types.h> +#include <linux/set_memory.h> +#include <linux/memblock.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/cpumask.h> +#include <linux/iommu.h> +#include <linux/amd-iommu.h> + +#include <asm/sev.h> +#include <asm/processor.h> +#include <asm/setup.h> +#include <asm/svm.h> +#include <asm/smp.h> +#include <asm/cpu.h> +#include <asm/apic.h> +#include <asm/cpuid.h> +#include <asm/cmdline.h> +#include <asm/iommu.h> + +/* + * The RMP entry format is not architectural. The format is defined in PPR + * Family 19h Model 01h, Rev B1 processor. + */ +struct rmpentry { + union { + struct { + u64 assigned : 1, + pagesize : 1, + immutable : 1, + rsvd1 : 9, + gpa : 39, + asid : 10, + vmsa : 1, + validated : 1, + rsvd2 : 1; + }; + u64 lo; + }; + u64 hi; +} __packed; + +/* + * The first 16KB from the RMP_BASE is used by the processor for the + * bookkeeping, the range needs to be added during the RMP entry lookup. + */ +#define RMPTABLE_CPU_BOOKKEEPING_SZ 0x4000 + +/* Mask to apply to a PFN to get the first PFN of a 2MB page */ +#define PFN_PMD_MASK GENMASK_ULL(63, PMD_SHIFT - PAGE_SHIFT) + +static u64 probed_rmp_base, probed_rmp_size; +static struct rmpentry *rmptable __ro_after_init; +static u64 rmptable_max_pfn __ro_after_init; + +static LIST_HEAD(snp_leaked_pages_list); +static DEFINE_SPINLOCK(snp_leaked_pages_list_lock); + +static unsigned long snp_nr_leaked_pages; + +#undef pr_fmt +#define pr_fmt(fmt) "SEV-SNP: " fmt + +static int __mfd_enable(unsigned int cpu) +{ + u64 val; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return 0; + + rdmsrl(MSR_AMD64_SYSCFG, val); + + val |= MSR_AMD64_SYSCFG_MFDM; + + wrmsrl(MSR_AMD64_SYSCFG, val); + + return 0; +} + +static __init void mfd_enable(void *arg) +{ + __mfd_enable(smp_processor_id()); +} + +static int __snp_enable(unsigned int cpu) +{ + u64 val; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return 0; + + rdmsrl(MSR_AMD64_SYSCFG, val); + + val |= MSR_AMD64_SYSCFG_SNP_EN; + val |= MSR_AMD64_SYSCFG_SNP_VMPL_EN; + + wrmsrl(MSR_AMD64_SYSCFG, val); + + return 0; +} + +static __init void snp_enable(void *arg) +{ + __snp_enable(smp_processor_id()); +} + +#define RMP_ADDR_MASK GENMASK_ULL(51, 13) + +bool snp_probe_rmptable_info(void) +{ + u64 max_rmp_pfn, calc_rmp_sz, rmp_sz, rmp_base, rmp_end; + + rdmsrl(MSR_AMD64_RMP_BASE, rmp_base); + rdmsrl(MSR_AMD64_RMP_END, rmp_end); + + if (!(rmp_base & RMP_ADDR_MASK) || !(rmp_end & RMP_ADDR_MASK)) { + pr_err("Memory for the RMP table has not been reserved by BIOS\n"); + return false; + } + + if (rmp_base > rmp_end) { + pr_err("RMP configuration not valid: base=%#llx, end=%#llx\n", rmp_base, rmp_end); + return false; + } + + rmp_sz = rmp_end - rmp_base + 1; + + /* + * Calculate the amount the memory that must be reserved by the BIOS to + * address the whole RAM, including the bookkeeping area. The RMP itself + * must also be covered. + */ + max_rmp_pfn = max_pfn; + if (PHYS_PFN(rmp_end) > max_pfn) + max_rmp_pfn = PHYS_PFN(rmp_end); + + calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ; + + if (calc_rmp_sz > rmp_sz) { + pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n", + calc_rmp_sz, rmp_sz); + return false; + } + + probed_rmp_base = rmp_base; + probed_rmp_size = rmp_sz; + + pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n", + probed_rmp_base, probed_rmp_base + probed_rmp_size - 1); + + return true; +} + +static void __init __snp_fixup_e820_tables(u64 pa) +{ + if (IS_ALIGNED(pa, PMD_SIZE)) + return; + + /* + * Handle cases where the RMP table placement by the BIOS is not + * 2M aligned and the kexec kernel could try to allocate + * from within that chunk which then causes a fatal RMP fault. + * + * The e820_table needs to be updated as it is converted to + * kernel memory resources and used by KEXEC_FILE_LOAD syscall + * to load kexec segments. + * + * The e820_table_firmware needs to be updated as it is exposed + * to sysfs and used by the KEXEC_LOAD syscall to load kexec + * segments. + * + * The e820_table_kexec needs to be updated as it passed to + * the kexec-ed kernel. + */ + pa = ALIGN_DOWN(pa, PMD_SIZE); + if (e820__mapped_any(pa, pa + PMD_SIZE, E820_TYPE_RAM)) { + pr_info("Reserving start/end of RMP table on a 2MB boundary [0x%016llx]\n", pa); + e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__range_update_table(e820_table_kexec, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__range_update_table(e820_table_firmware, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); + } +} + +void __init snp_fixup_e820_tables(void) +{ + __snp_fixup_e820_tables(probed_rmp_base); + __snp_fixup_e820_tables(probed_rmp_base + probed_rmp_size); +} + +/* + * Do the necessary preparations which are verified by the firmware as + * described in the SNP_INIT_EX firmware command description in the SNP + * firmware ABI spec. + */ +static int __init snp_rmptable_init(void) +{ + void *rmptable_start; + u64 rmptable_size; + u64 val; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return 0; + + if (!amd_iommu_snp_en) + goto nosnp; + + if (!probed_rmp_size) + goto nosnp; + + rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB); + if (!rmptable_start) { + pr_err("Failed to map RMP table\n"); + return 1; + } + + /* + * Check if SEV-SNP is already enabled, this can happen in case of + * kexec boot. + */ + rdmsrl(MSR_AMD64_SYSCFG, val); + if (val & MSR_AMD64_SYSCFG_SNP_EN) + goto skip_enable; + + memset(rmptable_start, 0, probed_rmp_size); + + /* Flush the caches to ensure that data is written before SNP is enabled. */ + wbinvd_on_all_cpus(); + + /* MtrrFixDramModEn must be enabled on all the CPUs prior to enabling SNP. */ + on_each_cpu(mfd_enable, NULL, 1); + + on_each_cpu(snp_enable, NULL, 1); + +skip_enable: + rmptable_start += RMPTABLE_CPU_BOOKKEEPING_SZ; + rmptable_size = probed_rmp_size - RMPTABLE_CPU_BOOKKEEPING_SZ; + + rmptable = (struct rmpentry *)rmptable_start; + rmptable_max_pfn = rmptable_size / sizeof(struct rmpentry) - 1; + + cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/rmptable_init:online", __snp_enable, NULL); + + /* + * Setting crash_kexec_post_notifiers to 'true' to ensure that SNP panic + * notifier is invoked to do SNP IOMMU shutdown before kdump. + */ + crash_kexec_post_notifiers = true; + + return 0; + +nosnp: + cc_platform_clear(CC_ATTR_HOST_SEV_SNP); + return -ENOSYS; +} + +/* + * This must be called after the IOMMU has been initialized. + */ +device_initcall(snp_rmptable_init); + +static struct rmpentry *get_rmpentry(u64 pfn) +{ + if (WARN_ON_ONCE(pfn > rmptable_max_pfn)) + return ERR_PTR(-EFAULT); + + return &rmptable[pfn]; +} + +static struct rmpentry *__snp_lookup_rmpentry(u64 pfn, int *level) +{ + struct rmpentry *large_entry, *entry; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return ERR_PTR(-ENODEV); + + entry = get_rmpentry(pfn); + if (IS_ERR(entry)) + return entry; + + /* + * Find the authoritative RMP entry for a PFN. This can be either a 4K + * RMP entry or a special large RMP entry that is authoritative for a + * whole 2M area. + */ + large_entry = get_rmpentry(pfn & PFN_PMD_MASK); + if (IS_ERR(large_entry)) + return large_entry; + + *level = RMP_TO_PG_LEVEL(large_entry->pagesize); + + return entry; +} + +int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) +{ + struct rmpentry *e; + + e = __snp_lookup_rmpentry(pfn, level); + if (IS_ERR(e)) + return PTR_ERR(e); + + *assigned = !!e->assigned; + return 0; +} +EXPORT_SYMBOL_GPL(snp_lookup_rmpentry); + +/* + * Dump the raw RMP entry for a particular PFN. These bits are documented in the + * PPR for a particular CPU model and provide useful information about how a + * particular PFN is being utilized by the kernel/firmware at the time certain + * unexpected events occur, such as RMP faults. + */ +static void dump_rmpentry(u64 pfn) +{ + u64 pfn_i, pfn_end; + struct rmpentry *e; + int level; + + e = __snp_lookup_rmpentry(pfn, &level); + if (IS_ERR(e)) { + pr_err("Failed to read RMP entry for PFN 0x%llx, error %ld\n", + pfn, PTR_ERR(e)); + return; + } + + if (e->assigned) { + pr_info("PFN 0x%llx, RMP entry: [0x%016llx - 0x%016llx]\n", + pfn, e->lo, e->hi); + return; + } + + /* + * If the RMP entry for a particular PFN is not in an assigned state, + * then it is sometimes useful to get an idea of whether or not any RMP + * entries for other PFNs within the same 2MB region are assigned, since + * those too can affect the ability to access a particular PFN in + * certain situations, such as when the PFN is being accessed via a 2MB + * mapping in the host page table. + */ + pfn_i = ALIGN_DOWN(pfn, PTRS_PER_PMD); + pfn_end = pfn_i + PTRS_PER_PMD; + + pr_info("PFN 0x%llx unassigned, dumping non-zero entries in 2M PFN region: [0x%llx - 0x%llx]\n", + pfn, pfn_i, pfn_end); + + while (pfn_i < pfn_end) { + e = __snp_lookup_rmpentry(pfn_i, &level); + if (IS_ERR(e)) { + pr_err("Error %ld reading RMP entry for PFN 0x%llx\n", + PTR_ERR(e), pfn_i); + pfn_i++; + continue; + } + + if (e->lo || e->hi) + pr_info("PFN: 0x%llx, [0x%016llx - 0x%016llx]\n", pfn_i, e->lo, e->hi); + pfn_i++; + } +} + +void snp_dump_hva_rmpentry(unsigned long hva) +{ + unsigned long paddr; + unsigned int level; + pgd_t *pgd; + pte_t *pte; + + pgd = __va(read_cr3_pa()); + pgd += pgd_index(hva); + pte = lookup_address_in_pgd(pgd, hva, &level); + + if (!pte) { + pr_err("Can't dump RMP entry for HVA %lx: no PTE/PFN found\n", hva); + return; + } + + paddr = PFN_PHYS(pte_pfn(*pte)) | (hva & ~page_level_mask(level)); + dump_rmpentry(PHYS_PFN(paddr)); +} + +/* + * PSMASH a 2MB aligned page into 4K pages in the RMP table while preserving the + * Validated bit. + */ +int psmash(u64 pfn) +{ + unsigned long paddr = pfn << PAGE_SHIFT; + int ret; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return -ENODEV; + + if (!pfn_valid(pfn)) + return -EINVAL; + + /* Binutils version 2.36 supports the PSMASH mnemonic. */ + asm volatile(".byte 0xF3, 0x0F, 0x01, 0xFF" + : "=a" (ret) + : "a" (paddr) + : "memory", "cc"); + + return ret; +} +EXPORT_SYMBOL_GPL(psmash); + +/* + * If the kernel uses a 2MB or larger directmap mapping to write to an address, + * and that mapping contains any 4KB pages that are set to private in the RMP + * table, an RMP #PF will trigger and cause a host crash. Hypervisor code that + * owns the PFNs being transitioned will never attempt such a write, but other + * kernel tasks writing to other PFNs in the range may trigger these checks + * inadvertently due a large directmap mapping that happens to overlap such a + * PFN. + * + * Prevent this by splitting any 2MB+ mappings that might end up containing a + * mix of private/shared PFNs as a result of a subsequent RMPUPDATE for the + * PFN/rmp_level passed in. + * + * Note that there is no attempt here to scan all the RMP entries for the 2MB + * physical range, since it would only be worthwhile in determining if a + * subsequent RMPUPDATE for a 4KB PFN would result in all the entries being of + * the same shared/private state, thus avoiding the need to split the mapping. + * But that would mean the entries are currently in a mixed state, and so the + * mapping would have already been split as a result of prior transitions. + * And since the 4K split is only done if the mapping is 2MB+, and there isn't + * currently a mechanism in place to restore 2MB+ mappings, such a check would + * not provide any usable benefit. + * + * More specifics on how these checks are carried out can be found in APM + * Volume 2, "RMP and VMPL Access Checks". + */ +static int adjust_direct_map(u64 pfn, int rmp_level) +{ + unsigned long vaddr; + unsigned int level; + int npages, ret; + pte_t *pte; + + /* + * pfn_to_kaddr() will return a vaddr only within the direct + * map range. + */ + vaddr = (unsigned long)pfn_to_kaddr(pfn); + + /* Only 4KB/2MB RMP entries are supported by current hardware. */ + if (WARN_ON_ONCE(rmp_level > PG_LEVEL_2M)) + return -EINVAL; + + if (!pfn_valid(pfn)) + return -EINVAL; + + if (rmp_level == PG_LEVEL_2M && + (!IS_ALIGNED(pfn, PTRS_PER_PMD) || !pfn_valid(pfn + PTRS_PER_PMD - 1))) + return -EINVAL; + + /* + * If an entire 2MB physical range is being transitioned, then there is + * no risk of RMP #PFs due to write accesses from overlapping mappings, + * since even accesses from 1GB mappings will be treated as 2MB accesses + * as far as RMP table checks are concerned. + */ + if (rmp_level == PG_LEVEL_2M) + return 0; + + pte = lookup_address(vaddr, &level); + if (!pte || pte_none(*pte)) + return 0; + + if (level == PG_LEVEL_4K) + return 0; + + npages = page_level_size(rmp_level) / PAGE_SIZE; + ret = set_memory_4k(vaddr, npages); + if (ret) + pr_warn("Failed to split direct map for PFN 0x%llx, ret: %d\n", + pfn, ret); + + return ret; +} + +/* + * It is expected that those operations are seldom enough so that no mutual + * exclusion of updaters is needed and thus the overlap error condition below + * should happen very rarely and would get resolved relatively quickly by + * the firmware. + * + * If not, one could consider introducing a mutex or so here to sync concurrent + * RMP updates and thus diminish the amount of cases where firmware needs to + * lock 2M ranges to protect against concurrent updates. + * + * The optimal solution would be range locking to avoid locking disjoint + * regions unnecessarily but there's no support for that yet. + */ +static int rmpupdate(u64 pfn, struct rmp_state *state) +{ + unsigned long paddr = pfn << PAGE_SHIFT; + int ret, level; + + if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + return -ENODEV; + + level = RMP_TO_PG_LEVEL(state->pagesize); + + if (adjust_direct_map(pfn, level)) + return -EFAULT; + + do { + /* Binutils version 2.36 supports the RMPUPDATE mnemonic. */ + asm volatile(".byte 0xF2, 0x0F, 0x01, 0xFE" + : "=a" (ret) + : "a" (paddr), "c" ((unsigned long)state) + : "memory", "cc"); + } while (ret == RMPUPDATE_FAIL_OVERLAP); + + if (ret) { + pr_err("RMPUPDATE failed for PFN %llx, pg_level: %d, ret: %d\n", + pfn, level, ret); + dump_rmpentry(pfn); + dump_stack(); + return -EFAULT; + } + + return 0; +} + +/* Transition a page to guest-owned/private state in the RMP table. */ +int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immutable) +{ + struct rmp_state state; + + memset(&state, 0, sizeof(state)); + state.assigned = 1; + state.asid = asid; + state.immutable = immutable; + state.gpa = gpa; + state.pagesize = PG_LEVEL_TO_RMP(level); + + return rmpupdate(pfn, &state); +} +EXPORT_SYMBOL_GPL(rmp_make_private); + +/* Transition a page to hypervisor-owned/shared state in the RMP table. */ +int rmp_make_shared(u64 pfn, enum pg_level level) +{ + struct rmp_state state; + + memset(&state, 0, sizeof(state)); + state.pagesize = PG_LEVEL_TO_RMP(level); + + return rmpupdate(pfn, &state); +} +EXPORT_SYMBOL_GPL(rmp_make_shared); + +void snp_leak_pages(u64 pfn, unsigned int npages) +{ + struct page *page = pfn_to_page(pfn); + + pr_warn("Leaking PFN range 0x%llx-0x%llx\n", pfn, pfn + npages); + + spin_lock(&snp_leaked_pages_list_lock); + while (npages--) { + + /* + * Reuse the page's buddy list for chaining into the leaked + * pages list. This page should not be on a free list currently + * and is also unsafe to be added to a free list. + */ + if (likely(!PageCompound(page)) || + + /* + * Skip inserting tail pages of compound page as + * page->buddy_list of tail pages is not usable. + */ + (PageHead(page) && compound_nr(page) <= npages)) + list_add_tail(&page->buddy_list, &snp_leaked_pages_list); + + dump_rmpentry(pfn); + snp_nr_leaked_pages++; + pfn++; + page++; + } + spin_unlock(&snp_leaked_pages_list_lock); +} +EXPORT_SYMBOL_GPL(snp_leak_pages); + +void kdump_sev_callback(void) +{ + /* + * Do wbinvd() on remote CPUs when SNP is enabled in order to + * safely do SNP_SHUTDOWN on the local CPU. + */ + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + wbinvd(); +} diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index a65fc2ae15..77e788e928 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -81,7 +81,6 @@ config XEN_PVH bool "Xen PVH guest support" depends on XEN && XEN_PVHVM && ACPI select PVH - def_bool n help Support for running as a Xen PVH guest. diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index 9dd5490b33..8b045dd251 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -33,12 +33,6 @@ static unsigned int xen_io_apic_read(unsigned apic, unsigned reg) return 0xfd; } -static u32 xen_set_apic_id(u32 x) -{ - WARN_ON(1); - return x; -} - static u32 xen_get_apic_id(u32 x) { return ((x)>>24) & 0xFFu; @@ -49,20 +43,20 @@ static u32 xen_apic_read(u32 reg) struct xen_platform_op op = { .cmd = XENPF_get_cpuinfo, .interface_version = XENPF_INTERFACE_VERSION, - .u.pcpu_info.xen_cpuid = 0, }; - int ret; - - /* Shouldn't need this as APIC is turned off for PV, and we only - * get called on the bootup processor. But just in case. */ - if (!xen_initial_domain() || smp_processor_id()) - return 0; + int ret, cpu; if (reg == APIC_LVR) return 0x14; if (reg != APIC_ID) return 0; + cpu = smp_processor_id(); + if (!xen_initial_domain()) + return cpu ? cpuid_to_apicid[cpu] << 24 : 0; + + op.u.pcpu_info.xen_cpuid = cpu; + ret = HYPERVISOR_platform_op(&op); if (ret) op.u.pcpu_info.apic_id = BAD_APICID; @@ -110,11 +104,6 @@ static int xen_madt_oem_check(char *oem_id, char *oem_table_id) return xen_pv_domain(); } -static u32 xen_phys_pkg_id(u32 initial_apic_id, int index_msb) -{ - return initial_apic_id >> index_msb; -} - static u32 xen_cpu_present_to_apicid(int cpu) { if (cpu_present(cpu)) @@ -133,11 +122,9 @@ static struct apic xen_pv_apic __ro_after_init = { .disable_esr = 0, .cpu_present_to_apicid = xen_cpu_present_to_apicid, - .phys_pkg_id = xen_phys_pkg_id, /* detect_ht */ .max_apic_id = UINT_MAX, .get_apic_id = xen_get_apic_id, - .set_apic_id = xen_set_apic_id, .calc_dest_apicid = apic_flat_calc_apicid, diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index a01ca255b0..b88722dfc4 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -382,3 +382,36 @@ void __init xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns) memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); } + +#ifdef CONFIG_XEN_UNPOPULATED_ALLOC +int __init arch_xen_unpopulated_init(struct resource **res) +{ + unsigned int i; + + if (!xen_domain()) + return -ENODEV; + + /* Must be set strictly before calling xen_free_unpopulated_pages(). */ + *res = &iomem_resource; + + /* + * Initialize with pages from the extra memory regions (see + * arch/x86/xen/setup.c). + */ + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + unsigned int j; + + for (j = 0; j < xen_extra_mem[i].n_pfns; j++) { + struct page *pg = + pfn_to_page(xen_extra_mem[i].start_pfn + j); + + xen_free_unpopulated_pages(1, &pg); + } + + /* Zero so region is not also added to the balloon driver. */ + xen_extra_mem[i].n_pfns = 0; + } + + return 0; +} +#endif diff --git a/arch/x86/xen/enlighten_hvm.c b/arch/x86/xen/enlighten_hvm.c index 3f8c34707c..c001a22965 100644 --- a/arch/x86/xen/enlighten_hvm.c +++ b/arch/x86/xen/enlighten_hvm.c @@ -148,7 +148,9 @@ static void xen_hvm_shutdown(void) if (kexec_in_progress) xen_reboot(SHUTDOWN_soft_reset); } +#endif +#ifdef CONFIG_CRASH_DUMP static void xen_hvm_crash_shutdown(struct pt_regs *regs) { native_machine_crash_shutdown(regs); @@ -168,7 +170,7 @@ static int xen_cpu_up_prepare_hvm(unsigned int cpu) */ xen_uninit_lock_cpu(cpu); - if (cpu_acpi_id(cpu) != U32_MAX) + if (cpu_acpi_id(cpu) != CPU_ACPIID_INVALID) per_cpu(xen_vcpu_id, cpu) = cpu_acpi_id(cpu); else per_cpu(xen_vcpu_id, cpu) = cpu; @@ -236,6 +238,8 @@ static void __init xen_hvm_guest_init(void) #ifdef CONFIG_KEXEC_CORE machine_ops.shutdown = xen_hvm_shutdown; +#endif +#ifdef CONFIG_CRASH_DUMP machine_ops.crash_shutdown = xen_hvm_crash_shutdown; #endif } diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index aeb33e0a3f..9ba53814ed 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -200,6 +200,9 @@ static void __init xen_pv_init_platform(void) xen_set_mtrr_data(); else mtrr_overwrite_state(NULL, 0, MTRR_TYPE_WRBACK); + + /* Adjust nr_cpu_ids before "enumeration" happens */ + xen_smp_count_cpus(); } static void __init xen_pv_guest_late_init(void) @@ -216,13 +219,21 @@ static __read_mostly unsigned int cpuid_leaf5_edx_val; static void xen_cpuid(unsigned int *ax, unsigned int *bx, unsigned int *cx, unsigned int *dx) { - unsigned maskebx = ~0; + unsigned int maskebx = ~0; + unsigned int or_ebx = 0; /* * Mask out inconvenient features, to try and disable as many * unsupported kernel subsystems as possible. */ switch (*ax) { + case 0x1: + /* Replace initial APIC ID in bits 24-31 of EBX. */ + /* See xen_pv_smp_config() for related topology preparations. */ + maskebx = 0x00ffffff; + or_ebx = smp_processor_id() << 24; + break; + case CPUID_MWAIT_LEAF: /* Synthesize the values.. */ *ax = 0; @@ -245,6 +256,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, : "0" (*ax), "2" (*cx)); *bx &= maskebx; + *bx |= or_ebx; } static bool __init xen_check_mwait(void) diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index c28f073c1d..27a2a02ef8 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -5,6 +5,7 @@ #include <xen/hvc-console.h> +#include <asm/bootparam.h> #include <asm/io_apic.h> #include <asm/hypervisor.h> #include <asm/e820/api.h> diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 994aef4473..54e0d311dc 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -913,7 +913,7 @@ static void drop_mm_ref_this_cpu(void *info) struct mm_struct *mm = info; if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm) - leave_mm(smp_processor_id()); + leave_mm(); /* * If this cpu still has a stale cr3 reference, then make sure @@ -1059,7 +1059,7 @@ static void __init xen_cleanmfnmap_pmd(pmd_t *pmd, bool unpin) pte_t *pte_tbl; int i; - if (pmd_large(*pmd)) { + if (pmd_leaf(*pmd)) { pa = pmd_val(*pmd) & PHYSICAL_PAGE_MASK; xen_free_ro_pages(pa, PMD_SIZE); return; @@ -1104,7 +1104,7 @@ static void __init xen_cleanmfnmap_p4d(p4d_t *p4d, bool unpin) pud_t *pud_tbl; int i; - if (p4d_large(*p4d)) { + if (p4d_leaf(*p4d)) { pa = p4d_val(*p4d) & PHYSICAL_PAGE_MASK; xen_free_ro_pages(pa, P4D_SIZE); return; @@ -1871,7 +1871,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) if (!pmd_present(pmd)) return 0; pa = pmd_val(pmd) & PTE_PFN_MASK; - if (pmd_large(pmd)) + if (pmd_leaf(pmd)) return pa + (vaddr & ~PMD_MASK); pte = native_make_pte(xen_read_phys_ulong(pa + pte_index(vaddr) * @@ -2520,7 +2520,7 @@ out: } EXPORT_SYMBOL_GPL(xen_remap_pfn); -#ifdef CONFIG_KEXEC_CORE +#ifdef CONFIG_VMCORE_INFO phys_addr_t paddr_vmcoreinfo_note(void) { if (xen_pv_domain()) diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index 1fb9a1644d..935771726f 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -135,8 +135,6 @@ void __init xen_smp_cpus_done(unsigned int max_cpus) { if (xen_hvm_domain()) native_smp_cpus_done(max_cpus); - else - calculate_max_logical_packages(); } void xen_smp_send_reschedule(int cpu) diff --git a/arch/x86/xen/smp.h b/arch/x86/xen/smp.h index c20cbb14c8..b8efdbc693 100644 --- a/arch/x86/xen/smp.h +++ b/arch/x86/xen/smp.h @@ -19,6 +19,7 @@ extern void xen_smp_intr_free(unsigned int cpu); int xen_smp_intr_init_pv(unsigned int cpu); void xen_smp_intr_free_pv(unsigned int cpu); +void xen_smp_count_cpus(void); void xen_smp_cpus_done(unsigned int max_cpus); void xen_smp_send_reschedule(int cpu); @@ -44,6 +45,7 @@ static inline int xen_smp_intr_init_pv(unsigned int cpu) return 0; } static inline void xen_smp_intr_free_pv(unsigned int cpu) {} +static inline void xen_smp_count_cpus(void) { } #endif /* CONFIG_SMP */ #endif diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index a0f07bbfcd..ac41d83b38 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -29,6 +29,7 @@ #include <asm/idtentry.h> #include <asm/desc.h> #include <asm/cpu.h> +#include <asm/apic.h> #include <asm/io_apic.h> #include <xen/interface/xen.h> @@ -73,7 +74,6 @@ static void cpu_bringup(void) } cpu = smp_processor_id(); smp_store_cpu_info(cpu); - cpu_data(cpu).x86_max_cores = 1; set_cpu_sibling_map(cpu); speculative_store_bypass_ht_init(); @@ -149,39 +149,16 @@ int xen_smp_intr_init_pv(unsigned int cpu) return rc; } -static void __init _get_smp_config(unsigned int early) +static void __init xen_pv_smp_config(void) { - int i, rc; - unsigned int subtract = 0; - - if (early) - return; - - num_processors = 0; - disabled_cpus = 0; - for (i = 0; i < nr_cpu_ids; i++) { - rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL); - if (rc >= 0) { - num_processors++; - set_cpu_possible(i, true); - } else { - set_cpu_possible(i, false); - set_cpu_present(i, false); - subtract++; - } - } -#ifdef CONFIG_HOTPLUG_CPU - /* This is akin to using 'nr_cpus' on the Linux command line. - * Which is OK as when we use 'dom0_max_vcpus=X' we can only - * have up to X, while nr_cpu_ids is greater than X. This - * normally is not a problem, except when CPU hotplugging - * is involved and then there might be more than X CPUs - * in the guest - which will not work as there is no - * hypercall to expand the max number of VCPUs an already - * running guest has. So cap it up to X. */ - if (subtract) - set_nr_cpu_ids(nr_cpu_ids - subtract); -#endif + u32 apicid = 0; + int i; + + topology_register_boot_apic(apicid); + + for (i = 0; i < nr_cpu_ids; i++) + topology_register_apic(apicid++, CPU_ACPIID_INVALID, true); + /* Pretend to be a proper enumerated system */ smp_found_config = 1; } @@ -224,8 +201,6 @@ static void __init xen_pv_smp_prepare_cpus(unsigned int max_cpus) smp_prepare_cpus_common(); - cpu_data(0).x86_max_cores = 1; - speculative_store_bypass_ht_init(); xen_pmu_init(0); @@ -434,6 +409,20 @@ static irqreturn_t xen_irq_work_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } +void __init xen_smp_count_cpus(void) +{ + unsigned int cpus; + + for (cpus = 0; cpus < nr_cpu_ids; cpus++) { + if (HYPERVISOR_vcpu_op(VCPUOP_is_up, cpus, NULL) < 0) + break; + } + + pr_info("Xen PV: Detected %u vCPUS\n", cpus); + if (cpus < nr_cpu_ids) + set_nr_cpu_ids(cpus); +} + static const struct smp_ops xen_smp_ops __initconst = { .smp_prepare_boot_cpu = xen_pv_smp_prepare_boot_cpu, .smp_prepare_cpus = xen_pv_smp_prepare_cpus, @@ -458,6 +447,12 @@ void __init xen_smp_init(void) smp_ops = xen_smp_ops; /* Avoid searching for BIOS MP tables */ - x86_init.mpparse.find_smp_config = x86_init_noop; - x86_init.mpparse.get_smp_config = _get_smp_config; + x86_init.mpparse.find_mptable = x86_init_noop; + x86_init.mpparse.early_parse_smp_cfg = x86_init_noop; + + /* XEN/PV Dom0 has halfways sane topology information via CPUID/MADT */ + if (xen_initial_domain()) + x86_init.mpparse.parse_smp_cfg = x86_init_noop; + else + x86_init.mpparse.parse_smp_cfg = xen_pv_smp_config; } diff --git a/arch/x86/xen/vga.c b/arch/x86/xen/vga.c index d97adab842..f7547807b0 100644 --- a/arch/x86/xen/vga.c +++ b/arch/x86/xen/vga.c @@ -2,7 +2,6 @@ #include <linux/screen_info.h> #include <linux/init.h> -#include <asm/bootparam.h> #include <asm/setup.h> #include <xen/interface/xen.h> diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 1a9cd18dfb..83189cf5cd 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -28,7 +28,7 @@ * non-zero. */ SYM_FUNC_START(xen_irq_disable_direct) - movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + movb $1, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask) RET SYM_FUNC_END(xen_irq_disable_direct) @@ -69,7 +69,7 @@ SYM_FUNC_END(check_events) SYM_FUNC_START(xen_irq_enable_direct) FRAME_BEGIN /* Unmask events */ - movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + movb $0, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask) /* * Preempt here doesn't matter because that will deal with any @@ -78,7 +78,7 @@ SYM_FUNC_START(xen_irq_enable_direct) */ /* Test for pending */ - testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending + testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_pending) jz 1f call check_events @@ -97,7 +97,7 @@ SYM_FUNC_END(xen_irq_enable_direct) * x86 use opposite senses (mask vs enable). */ SYM_FUNC_START(xen_save_fl_direct) - testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask + testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask) setz %ah addb %ah, %ah RET @@ -113,7 +113,7 @@ SYM_FUNC_END(xen_read_cr2); SYM_FUNC_START(xen_read_cr2_direct) FRAME_BEGIN - _ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX + _ASM_MOV PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_arch_cr2), %_ASM_AX FRAME_END RET SYM_FUNC_END(xen_read_cr2_direct); diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S index a0ea285878..04101b984f 100644 --- a/arch/x86/xen/xen-head.S +++ b/arch/x86/xen/xen-head.S @@ -49,7 +49,7 @@ SYM_CODE_START(startup_xen) ANNOTATE_NOENDBR cld - leaq (__end_init_task - PTREGS_SIZE)(%rip), %rsp + leaq (__end_init_task - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE)(%rip), %rsp /* Set up %gs. * |