diff options
Diffstat (limited to 'arch/x86')
233 files changed, 5374 insertions, 3978 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 66bfabae8814..3762f41bb092 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -28,7 +28,6 @@ config X86_64 select ARCH_HAS_GIGANTIC_PAGE select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 select ARCH_SUPPORTS_PER_VMA_LOCK - select ARCH_USE_CMPXCHG_LOCKREF select HAVE_ARCH_SOFT_DIRTY select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE @@ -118,6 +117,7 @@ config X86 select ARCH_SUPPORTS_LTO_CLANG select ARCH_SUPPORTS_LTO_CLANG_THIN select ARCH_USE_BUILTIN_BSWAP + select ARCH_USE_CMPXCHG_LOCKREF if X86_CMPXCHG64 select ARCH_USE_MEMTEST select ARCH_USE_QUEUED_RWLOCKS select ARCH_USE_QUEUED_SPINLOCKS @@ -1313,16 +1313,41 @@ config MICROCODE def_bool y depends on CPU_SUP_AMD || CPU_SUP_INTEL +config MICROCODE_INITRD32 + def_bool y + depends on MICROCODE && X86_32 && BLK_DEV_INITRD + config MICROCODE_LATE_LOADING bool "Late microcode loading (DANGEROUS)" default n - depends on MICROCODE + depends on MICROCODE && SMP help Loading microcode late, when the system is up and executing instructions is a tricky business and should be avoided if possible. Just the sequence of synchronizing all cores and SMT threads is one fragile dance which does not guarantee that cores might not softlock after the loading. Therefore, - use this at your own risk. Late loading taints the kernel too. + use this at your own risk. Late loading taints the kernel unless the + microcode header indicates that it is safe for late loading via the + minimal revision check. This minimal revision check can be enforced on + the kernel command line with "microcode.minrev=Y". + +config MICROCODE_LATE_FORCE_MINREV + bool "Enforce late microcode loading minimal revision check" + default n + depends on MICROCODE_LATE_LOADING + help + To prevent that users load microcode late which modifies already + in use features, newer microcode patches have a minimum revision field + in the microcode header, which tells the kernel which minimum + revision must be active in the CPU to safely load that new microcode + late into the running system. If disabled the check will not + be enforced but the kernel will be tainted when the minimal + revision check fails. + + This minimal revision check can also be controlled via the + "microcode.minrev" parameter on the kernel command line. + + If unsure say Y. config X86_MSR tristate "/dev/cpu/*/msr - Model-specific register support" @@ -1534,6 +1559,7 @@ config NUMA depends on X86_64 || (X86_32 && HIGHMEM64G && X86_BIGSMP) default y if X86_BIGSMP select USE_PERCPU_NUMA_NODE_ID + select OF_NUMA if OF help Enable NUMA (Non-Uniform Memory Access) support. @@ -1939,6 +1965,18 @@ config X86_USER_SHADOW_STACK If unsure, say N. +config INTEL_TDX_HOST + bool "Intel Trust Domain Extensions (TDX) host support" + depends on CPU_SUP_INTEL + depends on X86_64 + depends on KVM_INTEL + help + Intel Trust Domain Extensions (TDX) protects guest VMs from malicious + host and certain physical attacks. This option enables necessary TDX + support in the host kernel to run confidential VMs. + + If unsure, say N. + config EFI bool "EFI runtime service support" depends on ACPI @@ -2062,6 +2100,9 @@ config ARCH_SUPPORTS_CRASH_DUMP config ARCH_SUPPORTS_CRASH_HOTPLUG def_bool y +config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION + def_bool CRASH_CORE + config PHYSICAL_START hex "Physical address where the kernel is loaded" if (EXPERT || CRASH_DUMP) default "0x1000000" @@ -2954,6 +2995,15 @@ config IA32_EMULATION 64-bit kernel. You should likely turn this on, unless you're 100% sure that you don't have any 32-bit programs left. +config IA32_EMULATION_DEFAULT_DISABLED + bool "IA32 emulation disabled by default" + default n + depends on IA32_EMULATION + help + Make IA32 emulation disabled by default. This prevents loading 32-bit + processes and access to 32-bit syscalls. If unsure, leave it to its + default value. + config X86_X32_ABI bool "x32 ABI for 64-bit mode" depends on X86_64 diff --git a/arch/x86/Makefile b/arch/x86/Makefile index 5bfe5caaa444..1a068de12a56 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -43,7 +43,7 @@ endif # How to compile the 16-bit code. Note we always compile for -march=i386; # that way we can complain to the user if the CPU is insufficient. -REALMODE_CFLAGS := -m16 -g -Os -DDISABLE_BRANCH_PROFILING -D__DISABLE_EXPORTS \ +REALMODE_CFLAGS := -std=gnu11 -m16 -g -Os -DDISABLE_BRANCH_PROFILING -D__DISABLE_EXPORTS \ -Wall -Wstrict-prototypes -march=i386 -mregparm=3 \ -fno-strict-aliasing -fomit-frame-pointer -fno-pic \ -mno-mmx -mno-sse $(call cc-option,-fcf-protection=none) @@ -81,6 +81,7 @@ ifeq ($(CONFIG_X86_KERNEL_IBT),y) # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104816 # KBUILD_CFLAGS += $(call cc-option,-fcf-protection=branch -fno-jump-tables) +KBUILD_RUSTFLAGS += -Zcf-protection=branch -Zno-jump-tables else KBUILD_CFLAGS += $(call cc-option,-fcf-protection=none) endif @@ -252,6 +253,8 @@ archheaders: libs-y += arch/x86/lib/ +core-y += arch/x86/virt/ + # drivers-y are linked after core-y drivers-$(CONFIG_MATH_EMULATION) += arch/x86/math-emu/ drivers-$(CONFIG_PCI) += arch/x86/pci/ @@ -291,9 +294,10 @@ PHONY += install install: $(call cmd,install) -PHONY += vdso_install -vdso_install: - $(Q)$(MAKE) $(build)=arch/x86/entry/vdso $@ +vdso-install-$(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-$(CONFIG_IA32_EMULATION) += arch/x86/entry/vdso/vdso32.so.dbg archprepare: checkbin checkbin: diff --git a/arch/x86/Makefile.postlink b/arch/x86/Makefile.postlink index 936093d29160..fef2e977cc7d 100644 --- a/arch/x86/Makefile.postlink +++ b/arch/x86/Makefile.postlink @@ -34,9 +34,6 @@ ifeq ($(CONFIG_X86_NEED_RELOCS),y) $(call cmd,strip_relocs) endif -%.ko: FORCE - @true - clean: @rm -f $(OUT_RELOCS)/vmlinux.relocs diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile index f33e45ed1437..3cece19b7473 100644 --- a/arch/x86/boot/Makefile +++ b/arch/x86/boot/Makefile @@ -89,7 +89,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE SETUP_OBJS = $(addprefix $(obj)/,$(setup-y)) -sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|efi32_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|z_.*\)$$/\#define ZO_\2 0x\1/p' +sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_e\?data\|z_.*\)$$/\#define ZO_\2 0x\1/p' quiet_cmd_zoffset = ZOFFSET $@ cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@ diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 9caf89063e77..55c98fdd67d2 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -30,13 +30,13 @@ __efi_get_rsdp_addr(unsigned long cfg_tbl_pa, unsigned int cfg_tbl_len) * Search EFI system tables for RSDP. Preferred is ACPI_20_TABLE_GUID to * ACPI_TABLE_GUID because it has more features. */ - rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + rsdp_addr = efi_find_vendor_table(boot_params_ptr, cfg_tbl_pa, cfg_tbl_len, ACPI_20_TABLE_GUID); if (rsdp_addr) return (acpi_physical_address)rsdp_addr; /* No ACPI_20_TABLE_GUID found, fallback to ACPI_TABLE_GUID. */ - rsdp_addr = efi_find_vendor_table(boot_params, cfg_tbl_pa, cfg_tbl_len, + rsdp_addr = efi_find_vendor_table(boot_params_ptr, cfg_tbl_pa, cfg_tbl_len, ACPI_TABLE_GUID); if (rsdp_addr) return (acpi_physical_address)rsdp_addr; @@ -56,15 +56,15 @@ static acpi_physical_address efi_get_rsdp_addr(void) enum efi_type et; int ret; - et = efi_get_type(boot_params); + et = efi_get_type(boot_params_ptr); if (et == EFI_TYPE_NONE) return 0; - systab_pa = efi_get_system_table(boot_params); + systab_pa = efi_get_system_table(boot_params_ptr); if (!systab_pa) error("EFI support advertised, but unable to locate system table."); - ret = efi_get_conf_table(boot_params, &cfg_tbl_pa, &cfg_tbl_len); + ret = efi_get_conf_table(boot_params_ptr, &cfg_tbl_pa, &cfg_tbl_len); if (ret || !cfg_tbl_pa) error("EFI config table not found."); @@ -156,7 +156,7 @@ acpi_physical_address get_rsdp_addr(void) { acpi_physical_address pa; - pa = boot_params->acpi_rsdp_addr; + pa = boot_params_ptr->acpi_rsdp_addr; if (!pa) pa = efi_get_rsdp_addr(); @@ -210,7 +210,7 @@ static unsigned long get_acpi_srat_table(void) rsdp = (struct acpi_table_rsdp *)get_cmdline_acpi_rsdp(); if (!rsdp) rsdp = (struct acpi_table_rsdp *)(long) - boot_params->acpi_rsdp_addr; + boot_params_ptr->acpi_rsdp_addr; if (!rsdp) return 0; diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c index f1add5d85da9..c1bb180973ea 100644 --- a/arch/x86/boot/compressed/cmdline.c +++ b/arch/x86/boot/compressed/cmdline.c @@ -14,9 +14,9 @@ static inline char rdfs8(addr_t addr) #include "../cmdline.c" unsigned long get_cmd_line_ptr(void) { - unsigned long cmd_line_ptr = boot_params->hdr.cmd_line_ptr; + unsigned long cmd_line_ptr = boot_params_ptr->hdr.cmd_line_ptr; - cmd_line_ptr |= (u64)boot_params->ext_cmd_line_ptr << 32; + cmd_line_ptr |= (u64)boot_params_ptr->ext_cmd_line_ptr << 32; return cmd_line_ptr; } diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 08f93b0401bb..473ba59b82a8 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -159,8 +159,9 @@ void initialize_identity_maps(void *rmode) * or does not touch all the pages covering them. */ kernel_add_identity_map((unsigned long)_head, (unsigned long)_end); - boot_params = rmode; - kernel_add_identity_map((unsigned long)boot_params, (unsigned long)(boot_params + 1)); + boot_params_ptr = rmode; + kernel_add_identity_map((unsigned long)boot_params_ptr, + (unsigned long)(boot_params_ptr + 1)); cmdline = get_cmd_line_ptr(); kernel_add_identity_map(cmdline, cmdline + COMMAND_LINE_SIZE); @@ -168,7 +169,7 @@ void initialize_identity_maps(void *rmode) * Also map the setup_data entries passed via boot_params in case they * need to be accessed by uncompressed kernel via the identity mapping. */ - sd = (struct setup_data *)boot_params->hdr.setup_data; + sd = (struct setup_data *)boot_params_ptr->hdr.setup_data; while (sd) { unsigned long sd_addr = (unsigned long)sd; diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c index 9193acf0e9cd..dec961c6d16a 100644 --- a/arch/x86/boot/compressed/kaslr.c +++ b/arch/x86/boot/compressed/kaslr.c @@ -63,7 +63,7 @@ static unsigned long get_boot_seed(void) unsigned long hash = 0; hash = rotate_xor(hash, build_str, sizeof(build_str)); - hash = rotate_xor(hash, boot_params, sizeof(*boot_params)); + hash = rotate_xor(hash, boot_params_ptr, sizeof(*boot_params_ptr)); return hash; } @@ -383,7 +383,7 @@ static void handle_mem_options(void) static void mem_avoid_init(unsigned long input, unsigned long input_size, unsigned long output) { - unsigned long init_size = boot_params->hdr.init_size; + unsigned long init_size = boot_params_ptr->hdr.init_size; u64 initrd_start, initrd_size; unsigned long cmd_line, cmd_line_size; @@ -395,10 +395,10 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, mem_avoid[MEM_AVOID_ZO_RANGE].size = (output + init_size) - input; /* Avoid initrd. */ - initrd_start = (u64)boot_params->ext_ramdisk_image << 32; - initrd_start |= boot_params->hdr.ramdisk_image; - initrd_size = (u64)boot_params->ext_ramdisk_size << 32; - initrd_size |= boot_params->hdr.ramdisk_size; + initrd_start = (u64)boot_params_ptr->ext_ramdisk_image << 32; + initrd_start |= boot_params_ptr->hdr.ramdisk_image; + initrd_size = (u64)boot_params_ptr->ext_ramdisk_size << 32; + initrd_size |= boot_params_ptr->hdr.ramdisk_size; mem_avoid[MEM_AVOID_INITRD].start = initrd_start; mem_avoid[MEM_AVOID_INITRD].size = initrd_size; /* No need to set mapping for initrd, it will be handled in VO. */ @@ -413,8 +413,8 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size, } /* Avoid boot parameters. */ - mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params; - mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params); + mem_avoid[MEM_AVOID_BOOTPARAMS].start = (unsigned long)boot_params_ptr; + mem_avoid[MEM_AVOID_BOOTPARAMS].size = sizeof(*boot_params_ptr); /* We don't need to set a mapping for setup_data. */ @@ -447,7 +447,7 @@ static bool mem_avoid_overlap(struct mem_vector *img, } /* Avoid all entries in the setup_data linked list. */ - ptr = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data; + ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data; while (ptr) { struct mem_vector avoid; @@ -706,7 +706,7 @@ static inline bool memory_type_is_free(efi_memory_desc_t *md) static bool process_efi_entries(unsigned long minimum, unsigned long image_size) { - struct efi_info *e = &boot_params->efi_info; + struct efi_info *e = &boot_params_ptr->efi_info; bool efi_mirror_found = false; struct mem_vector region; efi_memory_desc_t *md; @@ -777,8 +777,8 @@ static void process_e820_entries(unsigned long minimum, struct boot_e820_entry *entry; /* Verify potential e820 positions, appending to slots list. */ - for (i = 0; i < boot_params->e820_entries; i++) { - entry = &boot_params->e820_table[i]; + for (i = 0; i < boot_params_ptr->e820_entries; i++) { + entry = &boot_params_ptr->e820_table[i]; /* Skip non-RAM entries. */ if (entry->type != E820_TYPE_RAM) continue; @@ -852,7 +852,7 @@ void choose_random_location(unsigned long input, return; } - boot_params->hdr.loadflags |= KASLR_FLAG; + boot_params_ptr->hdr.loadflags |= KASLR_FLAG; if (IS_ENABLED(CONFIG_X86_32)) mem_limit = KERNEL_IMAGE_SIZE; diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c index 3c1609245f2a..b3c3a4be7471 100644 --- a/arch/x86/boot/compressed/mem.c +++ b/arch/x86/boot/compressed/mem.c @@ -54,17 +54,17 @@ bool init_unaccepted_memory(void) enum efi_type et; int ret; - et = efi_get_type(boot_params); + et = efi_get_type(boot_params_ptr); if (et == EFI_TYPE_NONE) return false; - ret = efi_get_conf_table(boot_params, &cfg_table_pa, &cfg_table_len); + ret = efi_get_conf_table(boot_params_ptr, &cfg_table_pa, &cfg_table_len); if (ret) { warn("EFI config table not found."); return false; } - table = (void *)efi_find_vendor_table(boot_params, cfg_table_pa, + table = (void *)efi_find_vendor_table(boot_params_ptr, cfg_table_pa, cfg_table_len, guid); if (!table) return false; diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c index f711f2a85862..b99e08e6815b 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -46,7 +46,7 @@ void *memmove(void *dest, const void *src, size_t n); /* * This is set up by the setup-routine at boot-time */ -struct boot_params *boot_params; +struct boot_params *boot_params_ptr; struct port_io_ops pio_ops; @@ -132,8 +132,8 @@ void __putstr(const char *s) if (lines == 0 || cols == 0) return; - x = boot_params->screen_info.orig_x; - y = boot_params->screen_info.orig_y; + x = boot_params_ptr->screen_info.orig_x; + y = boot_params_ptr->screen_info.orig_y; while ((c = *s++) != '\0') { if (c == '\n') { @@ -154,8 +154,8 @@ void __putstr(const char *s) } } - boot_params->screen_info.orig_x = x; - boot_params->screen_info.orig_y = y; + boot_params_ptr->screen_info.orig_x = x; + boot_params_ptr->screen_info.orig_y = y; pos = (x + cols * y) * 2; /* Update cursor position */ outb(14, vidport); @@ -382,14 +382,14 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) size_t entry_offset; /* Retain x86 boot parameters pointer passed from startup_32/64. */ - boot_params = rmode; + boot_params_ptr = rmode; /* Clear flags intended for solely in-kernel use. */ - boot_params->hdr.loadflags &= ~KASLR_FLAG; + boot_params_ptr->hdr.loadflags &= ~KASLR_FLAG; - sanitize_boot_params(boot_params); + sanitize_boot_params(boot_params_ptr); - if (boot_params->screen_info.orig_video_mode == 7) { + if (boot_params_ptr->screen_info.orig_video_mode == 7) { vidmem = (char *) 0xb0000; vidport = 0x3b4; } else { @@ -397,8 +397,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) vidport = 0x3d4; } - lines = boot_params->screen_info.orig_video_lines; - cols = boot_params->screen_info.orig_video_cols; + lines = boot_params_ptr->screen_info.orig_video_lines; + cols = boot_params_ptr->screen_info.orig_video_cols; init_default_io_ops(); @@ -417,7 +417,7 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) * so that early debugging output from the RSDP parsing code can be * collected. */ - boot_params->acpi_rsdp_addr = get_rsdp_addr(); + boot_params_ptr->acpi_rsdp_addr = get_rsdp_addr(); debug_putstr("early console in extract_kernel\n"); diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index cc70d3fb9049..c0d502bd8716 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -61,7 +61,6 @@ extern memptr free_mem_ptr; extern memptr free_mem_end_ptr; void *malloc(int size); void free(void *where); -extern struct boot_params *boot_params; void __putstr(const char *s); void __puthex(unsigned long value); #define error_putstr(__x) __putstr(__x) diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c index 7939eb6e6ce9..51f957b24ba7 100644 --- a/arch/x86/boot/compressed/pgtable_64.c +++ b/arch/x86/boot/compressed/pgtable_64.c @@ -28,7 +28,6 @@ static char trampoline_save[TRAMPOLINE_32BIT_SIZE]; */ unsigned long *trampoline_32bit __section(".data"); -extern struct boot_params *boot_params; int cmdline_find_option_bool(const char *option); static unsigned long find_trampoline_placement(void) @@ -49,7 +48,7 @@ static unsigned long find_trampoline_placement(void) * * Only look for values in the legacy ROM for non-EFI system. */ - signature = (char *)&boot_params->efi_info.efi_loader_signature; + signature = (char *)&boot_params_ptr->efi_info.efi_loader_signature; if (strncmp(signature, EFI32_LOADER_SIGNATURE, 4) && strncmp(signature, EFI64_LOADER_SIGNATURE, 4)) { ebda_start = *(unsigned short *)0x40e << 4; @@ -65,10 +64,10 @@ static unsigned long find_trampoline_placement(void) bios_start = round_down(bios_start, PAGE_SIZE); /* Find the first usable memory region under bios_start. */ - for (i = boot_params->e820_entries - 1; i >= 0; i--) { + for (i = boot_params_ptr->e820_entries - 1; i >= 0; i--) { unsigned long new = bios_start; - entry = &boot_params->e820_table[i]; + entry = &boot_params_ptr->e820_table[i]; /* Skip all entries above bios_start. */ if (bios_start <= entry->addr) @@ -107,7 +106,7 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable) bool l5_required = false; /* Initialize boot_params. Required for cmdline_find_option_bool(). */ - boot_params = bp; + boot_params_ptr = bp; /* * Check if LA57 is desired and supported. diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index dc8c876fbd8f..454acd7a2daf 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -25,7 +25,7 @@ #include "error.h" #include "../msr.h" -struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); +static struct ghcb boot_ghcb_page __aligned(PAGE_SIZE); struct ghcb *boot_ghcb; /* @@ -103,6 +103,16 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, return ES_OK; } +static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size) +{ + return ES_OK; +} + +static bool fault_in_kernel_space(unsigned long address) +{ + return false; +} + #undef __init #define __init @@ -605,7 +615,7 @@ void sev_prep_identity_maps(unsigned long top_level_pgt) * accessed after switchover. */ if (sev_snp_enabled()) { - unsigned long cc_info_pa = boot_params->cc_blob_address; + unsigned long cc_info_pa = boot_params_ptr->cc_blob_address; struct cc_blob_sev_info *cc_info; kernel_add_identity_map(cc_info_pa, cc_info_pa + sizeof(*cc_info)); diff --git a/arch/x86/boot/compressed/tdx.c b/arch/x86/boot/compressed/tdx.c index 8841b945a1e2..8451d6a1030c 100644 --- a/arch/x86/boot/compressed/tdx.c +++ b/arch/x86/boot/compressed/tdx.c @@ -18,7 +18,7 @@ void __tdx_hypercall_failed(void) static inline unsigned int tdx_io_in(int size, u16 port) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, .r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION), .r12 = size, @@ -26,7 +26,7 @@ static inline unsigned int tdx_io_in(int size, u16 port) .r14 = port, }; - if (__tdx_hypercall_ret(&args)) + if (__tdx_hypercall(&args)) return UINT_MAX; return args.r11; @@ -34,7 +34,7 @@ static inline unsigned int tdx_io_in(int size, u16 port) static inline void tdx_io_out(int size, u16 port, u32 value) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, .r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION), .r12 = size, diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S index b22f34b8684a..083ec6d7722a 100644 --- a/arch/x86/boot/compressed/vmlinux.lds.S +++ b/arch/x86/boot/compressed/vmlinux.lds.S @@ -43,11 +43,13 @@ SECTIONS *(.rodata.*) _erodata = . ; } - .data : { + .data : ALIGN(0x1000) { _data = . ; *(.data) *(.data.*) - *(.bss.efistub) + + /* Add 4 bytes of extra space for a CRC-32 checksum */ + . = ALIGN(. + 4, 0x200); _edata = . ; } . = ALIGN(L1_CACHE_BYTES); diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S index b04ca8e2b213..b2771710ed98 100644 --- a/arch/x86/boot/header.S +++ b/arch/x86/boot/header.S @@ -36,66 +36,20 @@ SYSSEG = 0x1000 /* historical load address >> 4 */ #define ROOT_RDONLY 1 #endif + .set salign, 0x1000 + .set falign, 0x200 + .code16 .section ".bstext", "ax" - - .global bootsect_start -bootsect_start: #ifdef CONFIG_EFI_STUB # "MZ", MS-DOS header .word MZ_MAGIC -#endif - - # Normalize the start address - ljmp $BOOTSEG, $start2 - -start2: - movw %cs, %ax - movw %ax, %ds - movw %ax, %es - movw %ax, %ss - xorw %sp, %sp - sti - cld - - movw $bugger_off_msg, %si - -msg_loop: - lodsb - andb %al, %al - jz bs_die - movb $0xe, %ah - movw $7, %bx - int $0x10 - jmp msg_loop - -bs_die: - # Allow the user to press a key, then reboot - xorw %ax, %ax - int $0x16 - int $0x19 - - # int 0x19 should never return. In case it does anyway, - # invoke the BIOS reset code... - ljmp $0xf000,$0xfff0 - -#ifdef CONFIG_EFI_STUB .org 0x38 # # Offset to the PE header. # .long LINUX_PE_MAGIC .long pe_header -#endif /* CONFIG_EFI_STUB */ - - .section ".bsdata", "a" -bugger_off_msg: - .ascii "Use a boot loader.\r\n" - .ascii "\n" - .ascii "Remove disk and press any key to reboot...\r\n" - .byte 0 - -#ifdef CONFIG_EFI_STUB pe_header: .long PE_MAGIC @@ -124,30 +78,26 @@ optional_header: .byte 0x02 # MajorLinkerVersion .byte 0x14 # MinorLinkerVersion - # Filled in by build.c - .long 0 # SizeOfCode + .long ZO__data # SizeOfCode - .long 0 # SizeOfInitializedData + .long ZO__end - ZO__data # SizeOfInitializedData .long 0 # SizeOfUninitializedData - # Filled in by build.c - .long 0x0000 # AddressOfEntryPoint + .long setup_size + ZO_efi_pe_entry # AddressOfEntryPoint - .long 0x0200 # BaseOfCode + .long setup_size # BaseOfCode #ifdef CONFIG_X86_32 .long 0 # data #endif extra_header_fields: - # PE specification requires ImageBase to be 64k aligned - .set image_base, (LOAD_PHYSICAL_ADDR + 0xffff) & ~0xffff #ifdef CONFIG_X86_32 - .long image_base # ImageBase + .long 0 # ImageBase #else - .quad image_base # ImageBase + .quad 0 # ImageBase #endif - .long 0x20 # SectionAlignment - .long 0x20 # FileAlignment + .long salign # SectionAlignment + .long falign # FileAlignment .word 0 # MajorOperatingSystemVersion .word 0 # MinorOperatingSystemVersion .word LINUX_EFISTUB_MAJOR_VERSION # MajorImageVersion @@ -156,12 +106,10 @@ extra_header_fields: .word 0 # MinorSubsystemVersion .long 0 # Win32VersionValue - # - # The size of the bzImage is written in tools/build.c - # - .long 0 # SizeOfImage + .long setup_size + ZO__end + pecompat_vsize + # SizeOfImage - .long 0x200 # SizeOfHeaders + .long salign # SizeOfHeaders .long 0 # CheckSum .word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application) #ifdef CONFIG_EFI_DXE_MEM_ATTRIBUTES @@ -192,87 +140,78 @@ extra_header_fields: # Section table section_table: - # - # The offset & size fields are filled in by build.c. - # .ascii ".setup" .byte 0 .byte 0 - .long 0 - .long 0x0 # startup_{32,64} - .long 0 # Size of initialized data - # on disk - .long 0x0 # startup_{32,64} - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers - .long IMAGE_SCN_CNT_CODE | \ - IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_EXECUTE | \ - IMAGE_SCN_ALIGN_16BYTES # Characteristics + .long setup_size - salign # VirtualSize + .long salign # VirtualAddress + .long pecompat_fstart - salign # SizeOfRawData + .long salign # PointerToRawData - # - # The EFI application loader requires a relocation section - # because EFI applications must be relocatable. The .reloc - # offset & size fields are filled in by build.c. - # - .ascii ".reloc" - .byte 0 - .byte 0 - .long 0 - .long 0 - .long 0 # SizeOfRawData - .long 0 # PointerToRawData - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers + .long 0, 0, 0 .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_DISCARDABLE | \ - IMAGE_SCN_ALIGN_1BYTES # Characteristics + IMAGE_SCN_MEM_DISCARDABLE # Characteristics #ifdef CONFIG_EFI_MIXED - # - # The offset & size fields are filled in by build.c. - # .asciz ".compat" - .long 0 - .long 0x0 - .long 0 # Size of initialized data - # on disk - .long 0x0 - .long 0 # PointerToRelocations - .long 0 # PointerToLineNumbers - .word 0 # NumberOfRelocations - .word 0 # NumberOfLineNumbers + + .long 8 # VirtualSize + .long setup_size + ZO__end # VirtualAddress + .long pecompat_fsize # SizeOfRawData + .long pecompat_fstart # PointerToRawData + + .long 0, 0, 0 .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_DISCARDABLE | \ - IMAGE_SCN_ALIGN_1BYTES # Characteristics + IMAGE_SCN_MEM_DISCARDABLE # Characteristics + + /* + * Put the IA-32 machine type and the associated entry point address in + * the .compat section, so loaders can figure out which other execution + * modes this image supports. + */ + .pushsection ".pecompat", "a", @progbits + .balign falign + .set pecompat_vsize, salign + .globl pecompat_fstart +pecompat_fstart: + .byte 0x1 # Version + .byte 8 # Size + .word IMAGE_FILE_MACHINE_I386 # PE machine type + .long setup_size + ZO_efi32_pe_entry # Entrypoint + .popsection +#else + .set pecompat_vsize, 0 + .set pecompat_fstart, setup_size #endif - - # - # The offset & size fields are filled in by build.c. - # .ascii ".text" .byte 0 .byte 0 .byte 0 - .long 0 - .long 0x0 # startup_{32,64} - .long 0 # Size of initialized data + .long ZO__data + .long setup_size + .long ZO__data # Size of initialized data # on disk - .long 0x0 # startup_{32,64} + .long setup_size .long 0 # PointerToRelocations .long 0 # PointerToLineNumbers .word 0 # NumberOfRelocations .word 0 # NumberOfLineNumbers .long IMAGE_SCN_CNT_CODE | \ IMAGE_SCN_MEM_READ | \ - IMAGE_SCN_MEM_EXECUTE | \ - IMAGE_SCN_ALIGN_16BYTES # Characteristics + IMAGE_SCN_MEM_EXECUTE # Characteristics + + .ascii ".data\0\0\0" + .long ZO__end - ZO__data # VirtualSize + .long setup_size + ZO__data # VirtualAddress + .long ZO__edata - ZO__data # SizeOfRawData + .long setup_size + ZO__data # PointerToRawData + + .long 0, 0, 0 + .long IMAGE_SCN_CNT_INITIALIZED_DATA | \ + IMAGE_SCN_MEM_READ | \ + IMAGE_SCN_MEM_WRITE # Characteristics .set section_count, (. - section_table) / 40 #endif /* CONFIG_EFI_STUB */ @@ -286,12 +225,12 @@ sentinel: .byte 0xff, 0xff /* Used to detect broken loaders */ .globl hdr hdr: -setup_sects: .byte 0 /* Filled in by build.c */ + .byte setup_sects - 1 root_flags: .word ROOT_RDONLY -syssize: .long 0 /* Filled in by build.c */ +syssize: .long ZO__edata / 16 ram_size: .word 0 /* Obsolete */ vid_mode: .word SVGA_MODE -root_dev: .word 0 /* Filled in by build.c */ +root_dev: .word 0 /* Default to major/minor 0/0 */ boot_flag: .word 0xAA55 # offset 512, entry point @@ -579,9 +518,25 @@ pref_address: .quad LOAD_PHYSICAL_ADDR # preferred load addr # define INIT_SIZE VO_INIT_SIZE #endif + .macro __handover_offset +#ifndef CONFIG_EFI_HANDOVER_PROTOCOL + .long 0 +#elif !defined(CONFIG_X86_64) + .long ZO_efi32_stub_entry +#else + /* Yes, this is really how we defined it :( */ + .long ZO_efi64_stub_entry - 0x200 +#ifdef CONFIG_EFI_MIXED + .if ZO_efi32_stub_entry != ZO_efi64_stub_entry - 0x200 + .error "32-bit and 64-bit EFI entry points do not match" + .endif +#endif +#endif + .endm + init_size: .long INIT_SIZE # kernel initialization size -handover_offset: .long 0 # Filled in by build.c -kernel_info_offset: .long 0 # Filled in by build.c +handover_offset: __handover_offset +kernel_info_offset: .long ZO_kernel_info # End of setup header ##################################################### diff --git a/arch/x86/boot/setup.ld b/arch/x86/boot/setup.ld index 49546c247ae2..83bb7efad8ae 100644 --- a/arch/x86/boot/setup.ld +++ b/arch/x86/boot/setup.ld @@ -10,10 +10,11 @@ ENTRY(_start) SECTIONS { . = 0; - .bstext : { *(.bstext) } - .bsdata : { *(.bsdata) } + .bstext : { + *(.bstext) + . = 495; + } =0xffffffff - . = 495; .header : { *(.header) } .entrytext : { *(.entrytext) } .inittext : { *(.inittext) } @@ -35,11 +36,16 @@ SECTIONS . = ALIGN(16); .data : { *(.data*) } + .pecompat : { *(.pecompat) } + PROVIDE(pecompat_fsize = setup_size - pecompat_fstart); + .signature : { setup_sig = .; LONG(0x5a5aaa55) - } + setup_size = ALIGN(ABSOLUTE(.), 4096); + setup_sects = ABSOLUTE(setup_size / 512); + } . = ALIGN(16); .bss : diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c index bd247692b701..10311d77c67f 100644 --- a/arch/x86/boot/tools/build.c +++ b/arch/x86/boot/tools/build.c @@ -40,10 +40,6 @@ typedef unsigned char u8; typedef unsigned short u16; typedef unsigned int u32; -#define DEFAULT_MAJOR_ROOT 0 -#define DEFAULT_MINOR_ROOT 0 -#define DEFAULT_ROOT_DEV (DEFAULT_MAJOR_ROOT << 8 | DEFAULT_MINOR_ROOT) - /* Minimal number of setup sectors */ #define SETUP_SECT_MIN 5 #define SETUP_SECT_MAX 64 @@ -51,22 +47,7 @@ typedef unsigned int u32; /* This must be large enough to hold the entire setup */ u8 buf[SETUP_SECT_MAX*512]; -#define PECOFF_RELOC_RESERVE 0x20 - -#ifdef CONFIG_EFI_MIXED -#define PECOFF_COMPAT_RESERVE 0x20 -#else -#define PECOFF_COMPAT_RESERVE 0x0 -#endif - -static unsigned long efi32_stub_entry; -static unsigned long efi64_stub_entry; -static unsigned long efi_pe_entry; -static unsigned long efi32_pe_entry; -static unsigned long kernel_info; -static unsigned long startup_64; -static unsigned long _ehead; -static unsigned long _end; +static unsigned long _edata; /*----------------------------------------------------------------------*/ @@ -152,180 +133,6 @@ static void usage(void) die("Usage: build setup system zoffset.h image"); } -#ifdef CONFIG_EFI_STUB - -static void update_pecoff_section_header_fields(char *section_name, u32 vma, u32 size, u32 datasz, u32 offset) -{ - unsigned int pe_header; - unsigned short num_sections; - u8 *section; - - pe_header = get_unaligned_le32(&buf[0x3c]); - num_sections = get_unaligned_le16(&buf[pe_header + 6]); - -#ifdef CONFIG_X86_32 - section = &buf[pe_header + 0xa8]; -#else - section = &buf[pe_header + 0xb8]; -#endif - - while (num_sections > 0) { - if (strncmp((char*)section, section_name, 8) == 0) { - /* section header size field */ - put_unaligned_le32(size, section + 0x8); - - /* section header vma field */ - put_unaligned_le32(vma, section + 0xc); - - /* section header 'size of initialised data' field */ - put_unaligned_le32(datasz, section + 0x10); - - /* section header 'file offset' field */ - put_unaligned_le32(offset, section + 0x14); - - break; - } - section += 0x28; - num_sections--; - } -} - -static void update_pecoff_section_header(char *section_name, u32 offset, u32 size) -{ - update_pecoff_section_header_fields(section_name, offset, size, size, offset); -} - -static void update_pecoff_setup_and_reloc(unsigned int size) -{ - u32 setup_offset = 0x200; - u32 reloc_offset = size - PECOFF_RELOC_RESERVE - PECOFF_COMPAT_RESERVE; -#ifdef CONFIG_EFI_MIXED - u32 compat_offset = reloc_offset + PECOFF_RELOC_RESERVE; -#endif - u32 setup_size = reloc_offset - setup_offset; - - update_pecoff_section_header(".setup", setup_offset, setup_size); - update_pecoff_section_header(".reloc", reloc_offset, PECOFF_RELOC_RESERVE); - - /* - * Modify .reloc section contents with a single entry. The - * relocation is applied to offset 10 of the relocation section. - */ - put_unaligned_le32(reloc_offset + 10, &buf[reloc_offset]); - put_unaligned_le32(10, &buf[reloc_offset + 4]); - -#ifdef CONFIG_EFI_MIXED - update_pecoff_section_header(".compat", compat_offset, PECOFF_COMPAT_RESERVE); - - /* - * Put the IA-32 machine type (0x14c) and the associated entry point - * address in the .compat section, so loaders can figure out which other - * execution modes this image supports. - */ - buf[compat_offset] = 0x1; - buf[compat_offset + 1] = 0x8; - put_unaligned_le16(0x14c, &buf[compat_offset + 2]); - put_unaligned_le32(efi32_pe_entry + size, &buf[compat_offset + 4]); -#endif -} - -static void update_pecoff_text(unsigned int text_start, unsigned int file_sz, - unsigned int init_sz) -{ - unsigned int pe_header; - unsigned int text_sz = file_sz - text_start; - unsigned int bss_sz = init_sz - file_sz; - - pe_header = get_unaligned_le32(&buf[0x3c]); - - /* - * The PE/COFF loader may load the image at an address which is - * misaligned with respect to the kernel_alignment field in the setup - * header. - * - * In order to avoid relocating the kernel to correct the misalignment, - * add slack to allow the buffer to be aligned within the declared size - * of the image. - */ - bss_sz += CONFIG_PHYSICAL_ALIGN; - init_sz += CONFIG_PHYSICAL_ALIGN; - - /* - * Size of code: Subtract the size of the first sector (512 bytes) - * which includes the header. - */ - put_unaligned_le32(file_sz - 512 + bss_sz, &buf[pe_header + 0x1c]); - - /* Size of image */ - put_unaligned_le32(init_sz, &buf[pe_header + 0x50]); - - /* - * Address of entry point for PE/COFF executable - */ - put_unaligned_le32(text_start + efi_pe_entry, &buf[pe_header + 0x28]); - - update_pecoff_section_header_fields(".text", text_start, text_sz + bss_sz, - text_sz, text_start); -} - -static int reserve_pecoff_reloc_section(int c) -{ - /* Reserve 0x20 bytes for .reloc section */ - memset(buf+c, 0, PECOFF_RELOC_RESERVE); - return PECOFF_RELOC_RESERVE; -} - -static void efi_stub_defaults(void) -{ - /* Defaults for old kernel */ -#ifdef CONFIG_X86_32 - efi_pe_entry = 0x10; -#else - efi_pe_entry = 0x210; - startup_64 = 0x200; -#endif -} - -static void efi_stub_entry_update(void) -{ - unsigned long addr = efi32_stub_entry; - -#ifdef CONFIG_EFI_HANDOVER_PROTOCOL -#ifdef CONFIG_X86_64 - /* Yes, this is really how we defined it :( */ - addr = efi64_stub_entry - 0x200; -#endif - -#ifdef CONFIG_EFI_MIXED - if (efi32_stub_entry != addr) - die("32-bit and 64-bit EFI entry points do not match\n"); -#endif -#endif - put_unaligned_le32(addr, &buf[0x264]); -} - -#else - -static inline void update_pecoff_setup_and_reloc(unsigned int size) {} -static inline void update_pecoff_text(unsigned int text_start, - unsigned int file_sz, - unsigned int init_sz) {} -static inline void efi_stub_defaults(void) {} -static inline void efi_stub_entry_update(void) {} - -static inline int reserve_pecoff_reloc_section(int c) -{ - return 0; -} -#endif /* CONFIG_EFI_STUB */ - -static int reserve_pecoff_compat_section(int c) -{ - /* Reserve 0x20 bytes for .compat section */ - memset(buf+c, 0, PECOFF_COMPAT_RESERVE); - return PECOFF_COMPAT_RESERVE; -} - /* * Parse zoffset.h and find the entry points. We could just #include zoffset.h * but that would mean tools/build would have to be rebuilt every time. It's @@ -354,14 +161,7 @@ static void parse_zoffset(char *fname) p = (char *)buf; while (p && *p) { - PARSE_ZOFS(p, efi32_stub_entry); - PARSE_ZOFS(p, efi64_stub_entry); - PARSE_ZOFS(p, efi_pe_entry); - PARSE_ZOFS(p, efi32_pe_entry); - PARSE_ZOFS(p, kernel_info); - PARSE_ZOFS(p, startup_64); - PARSE_ZOFS(p, _ehead); - PARSE_ZOFS(p, _end); + PARSE_ZOFS(p, _edata); p = strchr(p, '\n'); while (p && (*p == '\r' || *p == '\n')) @@ -371,17 +171,14 @@ static void parse_zoffset(char *fname) int main(int argc, char ** argv) { - unsigned int i, sz, setup_sectors, init_sz; + unsigned int i, sz, setup_sectors; int c; - u32 sys_size; struct stat sb; FILE *file, *dest; int fd; void *kernel; u32 crc = 0xffffffffUL; - efi_stub_defaults(); - if (argc != 5) usage(); parse_zoffset(argv[3]); @@ -403,72 +200,27 @@ int main(int argc, char ** argv) die("Boot block hasn't got boot flag (0xAA55)"); fclose(file); - c += reserve_pecoff_compat_section(c); - c += reserve_pecoff_reloc_section(c); - /* Pad unused space with zeros */ - setup_sectors = (c + 511) / 512; + setup_sectors = (c + 4095) / 4096; + setup_sectors *= 8; if (setup_sectors < SETUP_SECT_MIN) setup_sectors = SETUP_SECT_MIN; i = setup_sectors*512; memset(buf+c, 0, i-c); - update_pecoff_setup_and_reloc(i); - - /* Set the default root device */ - put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]); - /* Open and stat the kernel file */ fd = open(argv[2], O_RDONLY); if (fd < 0) die("Unable to open `%s': %m", argv[2]); if (fstat(fd, &sb)) die("Unable to stat `%s': %m", argv[2]); - sz = sb.st_size; + if (_edata != sb.st_size) + die("Unexpected file size `%s': %u != %u", argv[2], _edata, + sb.st_size); + sz = _edata - 4; kernel = mmap(NULL, sz, PROT_READ, MAP_SHARED, fd, 0); if (kernel == MAP_FAILED) die("Unable to mmap '%s': %m", argv[2]); - /* Number of 16-byte paragraphs, including space for a 4-byte CRC */ - sys_size = (sz + 15 + 4) / 16; -#ifdef CONFIG_EFI_STUB - /* - * COFF requires minimum 32-byte alignment of sections, and - * adding a signature is problematic without that alignment. - */ - sys_size = (sys_size + 1) & ~1; -#endif - - /* Patch the setup code with the appropriate size parameters */ - buf[0x1f1] = setup_sectors-1; - put_unaligned_le32(sys_size, &buf[0x1f4]); - - init_sz = get_unaligned_le32(&buf[0x260]); -#ifdef CONFIG_EFI_STUB - /* - * The decompression buffer will start at ImageBase. When relocating - * the compressed kernel to its end, we must ensure that the head - * section does not get overwritten. The head section occupies - * [i, i + _ehead), and the destination is [init_sz - _end, init_sz). - * - * At present these should never overlap, because 'i' is at most 32k - * because of SETUP_SECT_MAX, '_ehead' is less than 1k, and the - * calculation of INIT_SIZE in boot/header.S ensures that - * 'init_sz - _end' is at least 64k. - * - * For future-proofing, increase init_sz if necessary. - */ - - if (init_sz - _end < i + _ehead) { - init_sz = (i + _ehead + _end + 4095) & ~4095; - put_unaligned_le32(init_sz, &buf[0x260]); - } -#endif - update_pecoff_text(setup_sectors * 512, i + (sys_size * 16), init_sz); - - efi_stub_entry_update(); - - /* Update kernel_info offset. */ - put_unaligned_le32(kernel_info, &buf[0x268]); crc = partial_crc32(buf, i, crc); if (fwrite(buf, 1, i, dest) != i) @@ -479,13 +231,6 @@ int main(int argc, char ** argv) if (fwrite(kernel, 1, sz, dest) != sz) die("Writing kernel failed"); - /* Add padding leaving 4 bytes for the checksum */ - while (sz++ < (sys_size*16) - 4) { - crc = partial_crc32_one('\0', crc); - if (fwrite("\0", 1, 1, dest) != 1) - die("Writing padding failed"); - } - /* Write the CRC */ put_unaligned_le32(crc, buf); if (fwrite(buf, 1, 4, dest) != 4) diff --git a/arch/x86/coco/tdx/tdcall.S b/arch/x86/coco/tdx/tdcall.S index b193c0a1d8db..52d9786da308 100644 --- a/arch/x86/coco/tdx/tdcall.S +++ b/arch/x86/coco/tdx/tdcall.S @@ -1,239 +1,63 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <asm/asm-offsets.h> #include <asm/asm.h> -#include <asm/frame.h> -#include <asm/unwind_hints.h> #include <linux/linkage.h> -#include <linux/bits.h> #include <linux/errno.h> #include "../../virt/vmx/tdx/tdxcall.S" -/* - * Bitmasks of exposed registers (with VMM). - */ -#define TDX_RDX BIT(2) -#define TDX_RBX BIT(3) -#define TDX_RSI BIT(6) -#define TDX_RDI BIT(7) -#define TDX_R8 BIT(8) -#define TDX_R9 BIT(9) -#define TDX_R10 BIT(10) -#define TDX_R11 BIT(11) -#define TDX_R12 BIT(12) -#define TDX_R13 BIT(13) -#define TDX_R14 BIT(14) -#define TDX_R15 BIT(15) - -/* - * These registers are clobbered to hold arguments for each - * TDVMCALL. They are safe to expose to the VMM. - * Each bit in this mask represents a register ID. Bit field - * details can be found in TDX GHCI specification, section - * titled "TDCALL [TDG.VP.VMCALL] leaf". - */ -#define TDVMCALL_EXPOSE_REGS_MASK \ - ( TDX_RDX | TDX_RBX | TDX_RSI | TDX_RDI | TDX_R8 | TDX_R9 | \ - TDX_R10 | TDX_R11 | TDX_R12 | TDX_R13 | TDX_R14 | TDX_R15 ) - .section .noinstr.text, "ax" /* - * __tdx_module_call() - Used by TDX guests to request services from - * the TDX module (does not include VMM services) using TDCALL instruction. - * - * Transforms function call register arguments into the TDCALL register ABI. - * After TDCALL operation, TDX module output is saved in @out (if it is - * provided by the user). - * - *------------------------------------------------------------------------- - * TDCALL ABI: - *------------------------------------------------------------------------- - * Input Registers: - * - * RAX - TDCALL Leaf number. - * RCX,RDX,R8-R9 - TDCALL Leaf specific input registers. - * - * Output Registers: + * __tdcall() - Used by TDX guests to request services from the TDX + * module (does not include VMM services) using TDCALL instruction. * - * RAX - TDCALL instruction error code. - * RCX,RDX,R8-R11 - TDCALL Leaf specific output registers. + * __tdcall() function ABI: * - *------------------------------------------------------------------------- + * @fn (RDI) - TDCALL Leaf ID, moved to RAX + * @args (RSI) - struct tdx_module_args for input * - * __tdx_module_call() function ABI: - * - * @fn (RDI) - TDCALL Leaf ID, moved to RAX - * @rcx (RSI) - Input parameter 1, moved to RCX - * @rdx (RDX) - Input parameter 2, moved to RDX - * @r8 (RCX) - Input parameter 3, moved to R8 - * @r9 (R8) - Input parameter 4, moved to R9 - * - * @out (R9) - struct tdx_module_output pointer - * stored temporarily in R12 (not - * shared with the TDX module). It - * can be NULL. + * Only RCX/RDX/R8-R11 are used as input registers. * * Return status of TDCALL via RAX. */ -SYM_FUNC_START(__tdx_module_call) - FRAME_BEGIN +SYM_FUNC_START(__tdcall) TDX_MODULE_CALL host=0 - FRAME_END - RET -SYM_FUNC_END(__tdx_module_call) +SYM_FUNC_END(__tdcall) /* - * TDX_HYPERCALL - Make hypercalls to a TDX VMM using TDVMCALL leaf of TDCALL - * instruction - * - * Transforms values in function call argument struct tdx_hypercall_args @args - * into the TDCALL register ABI. After TDCALL operation, VMM output is saved - * back in @args, if \ret is 1. - * - *------------------------------------------------------------------------- - * TD VMCALL ABI: - *------------------------------------------------------------------------- - * - * Input Registers: + * __tdcall_ret() - Used by TDX guests to request services from the TDX + * module (does not include VMM services) using TDCALL instruction, with + * saving output registers to the 'struct tdx_module_args' used as input. * - * RAX - TDCALL instruction leaf number (0 - TDG.VP.VMCALL) - * RCX - BITMAP which controls which part of TD Guest GPR - * is passed as-is to the VMM and back. - * R10 - Set 0 to indicate TDCALL follows standard TDX ABI - * specification. Non zero value indicates vendor - * specific ABI. - * R11 - VMCALL sub function number - * RBX, RDX, RDI, RSI - Used to pass VMCALL sub function specific arguments. - * R8-R9, R12-R15 - Same as above. + * __tdcall_ret() function ABI: * - * Output Registers: + * @fn (RDI) - TDCALL Leaf ID, moved to RAX + * @args (RSI) - struct tdx_module_args for input and output * - * RAX - TDCALL instruction status (Not related to hypercall - * output). - * RBX, RDX, RDI, RSI - Hypercall sub function specific output values. - * R8-R15 - Same as above. + * Only RCX/RDX/R8-R11 are used as input/output registers. * + * Return status of TDCALL via RAX. */ -.macro TDX_HYPERCALL ret:req - FRAME_BEGIN - - /* Save callee-saved GPRs as mandated by the x86_64 ABI */ - push %r15 - push %r14 - push %r13 - push %r12 - push %rbx - - /* Free RDI to be used as TDVMCALL arguments */ - movq %rdi, %rax - - /* Copy hypercall registers from arg struct: */ - movq TDX_HYPERCALL_r8(%rax), %r8 - movq TDX_HYPERCALL_r9(%rax), %r9 - movq TDX_HYPERCALL_r10(%rax), %r10 - movq TDX_HYPERCALL_r11(%rax), %r11 - movq TDX_HYPERCALL_r12(%rax), %r12 - movq TDX_HYPERCALL_r13(%rax), %r13 - movq TDX_HYPERCALL_r14(%rax), %r14 - movq TDX_HYPERCALL_r15(%rax), %r15 - movq TDX_HYPERCALL_rdi(%rax), %rdi - movq TDX_HYPERCALL_rsi(%rax), %rsi - movq TDX_HYPERCALL_rbx(%rax), %rbx - movq TDX_HYPERCALL_rdx(%rax), %rdx - - push %rax - - /* Mangle function call ABI into TDCALL ABI: */ - /* Set TDCALL leaf ID (TDVMCALL (0)) in RAX */ - xor %eax, %eax - - movl $TDVMCALL_EXPOSE_REGS_MASK, %ecx - - tdcall - - /* - * RAX!=0 indicates a failure of the TDVMCALL mechanism itself and that - * something has gone horribly wrong with the TDX module. - * - * The return status of the hypercall operation is in a separate - * register (in R10). Hypercall errors are a part of normal operation - * and are handled by callers. - */ - testq %rax, %rax - jne .Lpanic\@ - - pop %rax - - .if \ret - movq %r8, TDX_HYPERCALL_r8(%rax) - movq %r9, TDX_HYPERCALL_r9(%rax) - movq %r10, TDX_HYPERCALL_r10(%rax) - movq %r11, TDX_HYPERCALL_r11(%rax) - movq %r12, TDX_HYPERCALL_r12(%rax) - movq %r13, TDX_HYPERCALL_r13(%rax) - movq %r14, TDX_HYPERCALL_r14(%rax) - movq %r15, TDX_HYPERCALL_r15(%rax) - movq %rdi, TDX_HYPERCALL_rdi(%rax) - movq %rsi, TDX_HYPERCALL_rsi(%rax) - movq %rbx, TDX_HYPERCALL_rbx(%rax) - movq %rdx, TDX_HYPERCALL_rdx(%rax) - .endif - - /* TDVMCALL leaf return code is in R10 */ - movq %r10, %rax - - /* - * Zero out registers exposed to the VMM to avoid speculative execution - * with VMM-controlled values. This needs to include all registers - * present in TDVMCALL_EXPOSE_REGS_MASK, except RBX, and R12-R15 which - * will be restored. - */ - xor %r8d, %r8d - xor %r9d, %r9d - xor %r10d, %r10d - xor %r11d, %r11d - xor %rdi, %rdi - xor %rdx, %rdx - - /* Restore callee-saved GPRs as mandated by the x86_64 ABI */ - pop %rbx - pop %r12 - pop %r13 - pop %r14 - pop %r15 - - FRAME_END - - RET -.Lpanic\@: - call __tdx_hypercall_failed - /* __tdx_hypercall_failed never returns */ - REACHABLE - jmp .Lpanic\@ -.endm +SYM_FUNC_START(__tdcall_ret) + TDX_MODULE_CALL host=0 ret=1 +SYM_FUNC_END(__tdcall_ret) /* + * __tdcall_saved_ret() - Used by TDX guests to request services from the + * TDX module (including VMM services) using TDCALL instruction, with + * saving output registers to the 'struct tdx_module_args' used as input. * - * __tdx_hypercall() function ABI: - * - * @args (RDI) - struct tdx_hypercall_args for input - * - * On successful completion, return the hypercall error code. - */ -SYM_FUNC_START(__tdx_hypercall) - TDX_HYPERCALL ret=0 -SYM_FUNC_END(__tdx_hypercall) - -/* + * __tdcall_saved_ret() function ABI: * - * __tdx_hypercall_ret() function ABI: + * @fn (RDI) - TDCALL leaf ID, moved to RAX + * @args (RSI) - struct tdx_module_args for input/output * - * @args (RDI) - struct tdx_hypercall_args for input and output + * All registers in @args are used as input/output registers. * * On successful completion, return the hypercall error code. */ -SYM_FUNC_START(__tdx_hypercall_ret) - TDX_HYPERCALL ret=1 -SYM_FUNC_END(__tdx_hypercall_ret) +SYM_FUNC_START(__tdcall_saved_ret) + TDX_MODULE_CALL host=0 ret=1 saved=1 +SYM_FUNC_END(__tdcall_saved_ret) diff --git a/arch/x86/coco/tdx/tdx-shared.c b/arch/x86/coco/tdx/tdx-shared.c index ef20ddc37b58..78e413269791 100644 --- a/arch/x86/coco/tdx/tdx-shared.c +++ b/arch/x86/coco/tdx/tdx-shared.c @@ -5,7 +5,7 @@ static unsigned long try_accept_one(phys_addr_t start, unsigned long len, enum pg_level pg_level) { unsigned long accept_size = page_level_size(pg_level); - u64 tdcall_rcx; + struct tdx_module_args args = {}; u8 page_size; if (!IS_ALIGNED(start, accept_size)) @@ -34,8 +34,8 @@ static unsigned long try_accept_one(phys_addr_t start, unsigned long len, return 0; } - tdcall_rcx = start | page_size; - if (__tdx_module_call(TDX_ACCEPT_PAGE, tdcall_rcx, 0, 0, 0, NULL)) + args.rcx = start | page_size; + if (__tdcall(TDG_MEM_PAGE_ACCEPT, &args)) return 0; return accept_size; @@ -45,7 +45,7 @@ bool tdx_accept_memory(phys_addr_t start, phys_addr_t end) { /* * For shared->private conversion, accept the page using - * TDX_ACCEPT_PAGE TDX module call. + * TDG_MEM_PAGE_ACCEPT TDX module call. */ while (start < end) { unsigned long len = end - start; @@ -69,3 +69,23 @@ bool tdx_accept_memory(phys_addr_t start, phys_addr_t end) return true; } + +noinstr u64 __tdx_hypercall(struct tdx_module_args *args) +{ + /* + * For TDVMCALL explicitly set RCX to the bitmap of shared registers. + * The caller isn't expected to set @args->rcx anyway. + */ + args->rcx = TDVMCALL_EXPOSE_REGS_MASK; + + /* + * Failure of __tdcall_saved_ret() indicates a failure of the TDVMCALL + * mechanism itself and that something has gone horribly wrong with + * the TDX module. __tdx_hypercall_failed() never returns. + */ + if (__tdcall_saved_ret(TDG_VP_VMCALL, args)) + __tdx_hypercall_failed(); + + /* TDVMCALL leaf return code is in R10 */ + return args->r10; +} diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 752867b1d11b..1b5d17a9f70d 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -38,7 +38,7 @@ #define TDREPORT_SUBTYPE_0 0 /* Called from __tdx_hypercall() for unrecoverable failure */ -noinstr void __tdx_hypercall_failed(void) +noinstr void __noreturn __tdx_hypercall_failed(void) { instrumentation_begin(); panic("TDVMCALL failed. TDX module bug?"); @@ -48,7 +48,7 @@ noinstr void __tdx_hypercall_failed(void) long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, unsigned long p2, unsigned long p3, unsigned long p4) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = nr, .r11 = p1, .r12 = p2, @@ -66,10 +66,9 @@ EXPORT_SYMBOL_GPL(tdx_kvm_hypercall); * should only be used for calls that have no legitimate reason to fail * or where the kernel can not survive the call failing. */ -static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, - struct tdx_module_output *out) +static inline void tdcall(u64 fn, struct tdx_module_args *args) { - if (__tdx_module_call(fn, rcx, rdx, r8, r9, out)) + if (__tdcall_ret(fn, args)) panic("TDCALL %lld failed (Buggy TDX module!)\n", fn); } @@ -89,11 +88,14 @@ static inline void tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, */ int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport) { + struct tdx_module_args args = { + .rcx = virt_to_phys(tdreport), + .rdx = virt_to_phys(reportdata), + .r8 = TDREPORT_SUBTYPE_0, + }; u64 ret; - ret = __tdx_module_call(TDX_GET_REPORT, virt_to_phys(tdreport), - virt_to_phys(reportdata), TDREPORT_SUBTYPE_0, - 0, NULL); + ret = __tdcall(TDG_MR_REPORT, &args); if (ret) { if (TDCALL_RETURN_CODE(ret) == TDCALL_INVALID_OPERAND) return -EINVAL; @@ -127,7 +129,7 @@ EXPORT_SYMBOL_GPL(tdx_hcall_get_quote); static void __noreturn tdx_panic(const char *msg) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, .r11 = TDVMCALL_REPORT_FATAL_ERROR, .r12 = 0, /* Error code: 0 is Panic */ @@ -140,7 +142,7 @@ static void __noreturn tdx_panic(const char *msg) } message; /* VMM assumes '\0' in byte 65, if the message took all 64 bytes */ - strncpy(message.str, msg, 64); + strtomem_pad(message.str, msg, '\0'); args.r8 = message.r8; args.r9 = message.r9; @@ -162,7 +164,7 @@ static void __noreturn tdx_panic(const char *msg) static void tdx_parse_tdinfo(u64 *cc_mask) { - struct tdx_module_output out; + struct tdx_module_args args = {}; unsigned int gpa_width; u64 td_attr; @@ -173,7 +175,7 @@ static void tdx_parse_tdinfo(u64 *cc_mask) * Guest-Host-Communication Interface (GHCI), section 2.4.2 TDCALL * [TDG.VP.INFO]. */ - tdx_module_call(TDX_GET_INFO, 0, 0, 0, 0, &out); + tdcall(TDG_VP_INFO, &args); /* * The highest bit of a guest physical address is the "sharing" bit. @@ -182,7 +184,7 @@ static void tdx_parse_tdinfo(u64 *cc_mask) * The GPA width that comes out of this call is critical. TDX guests * can not meaningfully run without it. */ - gpa_width = out.rcx & GENMASK(5, 0); + gpa_width = args.rcx & GENMASK(5, 0); *cc_mask = BIT_ULL(gpa_width - 1); /* @@ -190,7 +192,7 @@ static void tdx_parse_tdinfo(u64 *cc_mask) * memory. Ensure that no #VE will be delivered for accesses to * TD-private memory. Only VMM-shared memory (MMIO) will #VE. */ - td_attr = out.rdx; + td_attr = args.rdx; if (!(td_attr & ATTR_SEPT_VE_DISABLE)) { const char *msg = "TD misconfiguration: SEPT_VE_DISABLE attribute must be set."; @@ -249,7 +251,7 @@ static int ve_instr_len(struct ve_info *ve) static u64 __cpuidle __halt(const bool irq_disabled) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, .r11 = hcall_func(EXIT_REASON_HLT), .r12 = irq_disabled, @@ -293,7 +295,7 @@ void __cpuidle tdx_safe_halt(void) static int read_msr(struct pt_regs *regs, struct ve_info *ve) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, .r11 = hcall_func(EXIT_REASON_MSR_READ), .r12 = regs->cx, @@ -304,7 +306,7 @@ static int read_msr(struct pt_regs *regs, struct ve_info *ve) * can be found in TDX Guest-Host-Communication Interface * (GHCI), section titled "TDG.VP.VMCALL<Instruction.RDMSR>". */ - if (__tdx_hypercall_ret(&args)) + if (__tdx_hypercall(&args)) return -EIO; regs->ax = lower_32_bits(args.r11); @@ -314,7 +316,7 @@ static int read_msr(struct pt_regs *regs, struct ve_info *ve) static int write_msr(struct pt_regs *regs, struct ve_info *ve) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, .r11 = hcall_func(EXIT_REASON_MSR_WRITE), .r12 = regs->cx, @@ -334,7 +336,7 @@ static int write_msr(struct pt_regs *regs, struct ve_info *ve) static int handle_cpuid(struct pt_regs *regs, struct ve_info *ve) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, .r11 = hcall_func(EXIT_REASON_CPUID), .r12 = regs->ax, @@ -358,7 +360,7 @@ static int handle_cpuid(struct pt_regs *regs, struct ve_info *ve) * ABI can be found in TDX Guest-Host-Communication Interface * (GHCI), section titled "VP.VMCALL<Instruction.CPUID>". */ - if (__tdx_hypercall_ret(&args)) + if (__tdx_hypercall(&args)) return -EIO; /* @@ -376,7 +378,7 @@ static int handle_cpuid(struct pt_regs *regs, struct ve_info *ve) static bool mmio_read(int size, unsigned long addr, unsigned long *val) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, .r11 = hcall_func(EXIT_REASON_EPT_VIOLATION), .r12 = size, @@ -385,8 +387,9 @@ static bool mmio_read(int size, unsigned long addr, unsigned long *val) .r15 = *val, }; - if (__tdx_hypercall_ret(&args)) + if (__tdx_hypercall(&args)) return false; + *val = args.r11; return true; } @@ -504,7 +507,7 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) static bool handle_in(struct pt_regs *regs, int size, int port) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, .r11 = hcall_func(EXIT_REASON_IO_INSTRUCTION), .r12 = size, @@ -519,7 +522,7 @@ static bool handle_in(struct pt_regs *regs, int size, int port) * in TDX Guest-Host-Communication Interface (GHCI) section titled * "TDG.VP.VMCALL<Instruction.IO>". */ - success = !__tdx_hypercall_ret(&args); + success = !__tdx_hypercall(&args); /* Update part of the register affected by the emulated instruction */ regs->ax &= ~mask; @@ -598,7 +601,7 @@ __init bool tdx_early_handle_ve(struct pt_regs *regs) void tdx_get_ve_info(struct ve_info *ve) { - struct tdx_module_output out; + struct tdx_module_args args = {}; /* * Called during #VE handling to retrieve the #VE info from the @@ -615,15 +618,15 @@ void tdx_get_ve_info(struct ve_info *ve) * Note, the TDX module treats virtual NMIs as inhibited if the #VE * valid flag is set. It means that NMI=>#VE will not result in a #DF. */ - tdx_module_call(TDX_GET_VEINFO, 0, 0, 0, 0, &out); + tdcall(TDG_VP_VEINFO_GET, &args); /* Transfer the output parameters */ - ve->exit_reason = out.rcx; - ve->exit_qual = out.rdx; - ve->gla = out.r8; - ve->gpa = out.r9; - ve->instr_len = lower_32_bits(out.r10); - ve->instr_info = upper_32_bits(out.r10); + ve->exit_reason = args.rcx; + ve->exit_qual = args.rdx; + ve->gla = args.r8; + ve->gpa = args.r9; + ve->instr_len = lower_32_bits(args.r10); + ve->instr_info = upper_32_bits(args.r10); } /* @@ -724,14 +727,15 @@ static bool tdx_cache_flush_required(void) } /* - * Inform the VMM of the guest's intent for this physical page: shared with - * the VMM or private to the guest. The VMM is expected to change its mapping - * of the page in response. + * Notify the VMM about page mapping conversion. More info about ABI + * can be found in TDX Guest-Host-Communication Interface (GHCI), + * section "TDG.VP.VMCALL<MapGPA>". */ -static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc) +static bool tdx_map_gpa(phys_addr_t start, phys_addr_t end, bool enc) { - phys_addr_t start = __pa(vaddr); - phys_addr_t end = __pa(vaddr + numpages * PAGE_SIZE); + /* Retrying the hypercall a second time should succeed; use 3 just in case */ + const int max_retries_per_page = 3; + int retry_count = 0; if (!enc) { /* Set the shared (decrypted) bits: */ @@ -739,12 +743,51 @@ static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc) end |= cc_mkdec(0); } - /* - * Notify the VMM about page mapping conversion. More info about ABI - * can be found in TDX Guest-Host-Communication Interface (GHCI), - * section "TDG.VP.VMCALL<MapGPA>" - */ - if (_tdx_hypercall(TDVMCALL_MAP_GPA, start, end - start, 0, 0)) + while (retry_count < max_retries_per_page) { + struct tdx_module_args args = { + .r10 = TDX_HYPERCALL_STANDARD, + .r11 = TDVMCALL_MAP_GPA, + .r12 = start, + .r13 = end - start }; + + u64 map_fail_paddr; + u64 ret = __tdx_hypercall(&args); + + if (ret != TDVMCALL_STATUS_RETRY) + return !ret; + /* + * The guest must retry the operation for the pages in the + * region starting at the GPA specified in R11. R11 comes + * from the untrusted VMM. Sanity check it. + */ + map_fail_paddr = args.r11; + if (map_fail_paddr < start || map_fail_paddr >= end) + return false; + + /* "Consume" a retry without forward progress */ + if (map_fail_paddr == start) { + retry_count++; + continue; + } + + start = map_fail_paddr; + retry_count = 0; + } + + return false; +} + +/* + * Inform the VMM of the guest's intent for this physical page: shared with + * the VMM or private to the guest. The VMM is expected to change its mapping + * of the page in response. + */ +static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc) +{ + phys_addr_t start = __pa(vaddr); + phys_addr_t end = __pa(vaddr + numpages * PAGE_SIZE); + + if (!tdx_map_gpa(start, end, enc)) return false; /* shared->private conversion requires memory to be accepted before use */ @@ -780,6 +823,10 @@ static bool tdx_enc_status_change_finish(unsigned long vaddr, int numpages, void __init tdx_early_init(void) { + struct tdx_module_args args = { + .rdx = TDCS_NOTIFY_ENABLES, + .r9 = -1ULL, + }; u64 cc_mask; u32 eax, sig[3]; @@ -790,12 +837,15 @@ void __init tdx_early_init(void) setup_force_cpu_cap(X86_FEATURE_TDX_GUEST); + /* TSC is the only reliable clock in TDX guest */ + setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE); + cc_vendor = CC_VENDOR_INTEL; tdx_parse_tdinfo(&cc_mask); cc_set_mask(cc_mask); /* Kernel does not use NOTIFY_ENABLES and does not need random #VEs */ - tdx_module_call(TDX_WR, 0, TDCS_NOTIFY_ENABLES, 0, -1ULL, NULL); + tdcall(TDG_VM_WR, &args); /* * All bits above GPA width are reserved and kernel treats shared bit diff --git a/arch/x86/configs/hardening.config b/arch/x86/configs/hardening.config new file mode 100644 index 000000000000..7b497f3b7bc3 --- /dev/null +++ b/arch/x86/configs/hardening.config @@ -0,0 +1,14 @@ +# Basic kernel hardening options (specific to x86) + +# Modern libc no longer needs a fixed-position mapping in userspace, remove +# it as a possible target. +CONFIG_LEGACY_VSYSCALL_NONE=y + +# Enable chip-specific IOMMU support. +CONFIG_INTEL_IOMMU=y +CONFIG_INTEL_IOMMU_DEFAULT_ON=y +CONFIG_INTEL_IOMMU_SVM=y +CONFIG_AMD_IOMMU=y + +# Enable CET Shadow Stack for userspace. +CONFIG_X86_USER_SHADOW_STACK=y diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 1b411bbf3cb0..73abbbdd26f8 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -281,4 +281,5 @@ CONFIG_PROVIDE_OHCI1394_DMA_INIT=y CONFIG_EARLY_PRINTK_DBGP=y CONFIG_DEBUG_BOOT_PARAMS=y CONFIG_UNWINDER_FRAME_POINTER=y +CONFIG_DEBUG_ENTRY=y # CONFIG_64BIT is not set diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 409e9182bd29..61e25f6209ed 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -276,3 +276,4 @@ CONFIG_BLK_DEV_IO_TRACE=y CONFIG_PROVIDE_OHCI1394_DMA_INIT=y CONFIG_EARLY_PRINTK_DBGP=y CONFIG_DEBUG_BOOT_PARAMS=y +CONFIG_DEBUG_ENTRY=y diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 3ac7487ecad2..187f913cc239 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -672,7 +672,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff add %r13, %r10 # Set r10 to be the amount of data left in CYPH_PLAIN_IN after filling sub $16, %r10 - # Determine if if partial block is not being filled and + # Determine if partial block is not being filled and # shift mask accordingly jge .L_no_extra_mask_1_\@ sub %r10, %r12 @@ -708,7 +708,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff add %r13, %r10 # Set r10 to be the amount of data left in CYPH_PLAIN_IN after filling sub $16, %r10 - # Determine if if partial block is not being filled and + # Determine if partial block is not being filled and # shift mask accordingly jge .L_no_extra_mask_2_\@ sub %r10, %r12 diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index 46cddd78857b..74dd230973cf 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -753,7 +753,7 @@ VARIABLE_OFFSET = 16*8 add %r13, %r10 # Set r10 to be the amount of data left in CYPH_PLAIN_IN after filling sub $16, %r10 - # Determine if if partial block is not being filled and + # Determine if partial block is not being filled and # shift mask accordingly jge .L_no_extra_mask_1_\@ sub %r10, %r12 @@ -789,7 +789,7 @@ VARIABLE_OFFSET = 16*8 add %r13, %r10 # Set r10 to be the amount of data left in CYPH_PLAIN_IN after filling sub $16, %r10 - # Determine if if partial block is not being filled and + # Determine if partial block is not being filled and # shift mask accordingly jge .L_no_extra_mask_2_\@ sub %r10, %r12 diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index 39d6a62ac627..b1d90c25975a 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -61,8 +61,8 @@ struct generic_gcmaes_ctx { }; struct aesni_xts_ctx { - u8 raw_tweak_ctx[sizeof(struct crypto_aes_ctx)] AESNI_ALIGN_ATTR; - u8 raw_crypt_ctx[sizeof(struct crypto_aes_ctx)] AESNI_ALIGN_ATTR; + struct crypto_aes_ctx tweak_ctx AESNI_ALIGN_ATTR; + struct crypto_aes_ctx crypt_ctx AESNI_ALIGN_ATTR; }; #define GCM_BLOCK_LEN 16 @@ -80,6 +80,13 @@ struct gcm_context_data { u8 hash_keys[GCM_BLOCK_LEN * 16]; }; +static inline void *aes_align_addr(void *addr) +{ + if (crypto_tfm_ctx_alignment() >= AESNI_ALIGN) + return addr; + return PTR_ALIGN(addr, AESNI_ALIGN); +} + asmlinkage int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, unsigned int key_len); asmlinkage void aesni_enc(const void *ctx, u8 *out, const u8 *in); @@ -201,32 +208,24 @@ static __ro_after_init DEFINE_STATIC_KEY_FALSE(gcm_use_avx2); static inline struct aesni_rfc4106_gcm_ctx *aesni_rfc4106_gcm_ctx_get(struct crypto_aead *tfm) { - unsigned long align = AESNI_ALIGN; - - if (align <= crypto_tfm_ctx_alignment()) - align = 1; - return PTR_ALIGN(crypto_aead_ctx(tfm), align); + return aes_align_addr(crypto_aead_ctx(tfm)); } static inline struct generic_gcmaes_ctx *generic_gcmaes_ctx_get(struct crypto_aead *tfm) { - unsigned long align = AESNI_ALIGN; - - if (align <= crypto_tfm_ctx_alignment()) - align = 1; - return PTR_ALIGN(crypto_aead_ctx(tfm), align); + return aes_align_addr(crypto_aead_ctx(tfm)); } #endif static inline struct crypto_aes_ctx *aes_ctx(void *raw_ctx) { - unsigned long addr = (unsigned long)raw_ctx; - unsigned long align = AESNI_ALIGN; + return aes_align_addr(raw_ctx); +} - if (align <= crypto_tfm_ctx_alignment()) - align = 1; - return (struct crypto_aes_ctx *)ALIGN(addr, align); +static inline struct aesni_xts_ctx *aes_xts_ctx(struct crypto_skcipher *tfm) +{ + return aes_align_addr(crypto_skcipher_ctx(tfm)); } static int aes_set_key_common(struct crypto_aes_ctx *ctx, @@ -881,7 +880,7 @@ static int helper_rfc4106_decrypt(struct aead_request *req) static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { - struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm); + struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm); int err; err = xts_verify_key(tfm, key, keylen); @@ -891,19 +890,18 @@ static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key, keylen /= 2; /* first half of xts-key is for crypt */ - err = aes_set_key_common(aes_ctx(ctx->raw_crypt_ctx), key, keylen); + err = aes_set_key_common(&ctx->crypt_ctx, key, keylen); if (err) return err; /* second half of xts-key is for tweak */ - return aes_set_key_common(aes_ctx(ctx->raw_tweak_ctx), key + keylen, - keylen); + return aes_set_key_common(&ctx->tweak_ctx, key + keylen, keylen); } static int xts_crypt(struct skcipher_request *req, bool encrypt) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct aesni_xts_ctx *ctx = crypto_skcipher_ctx(tfm); + struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm); int tail = req->cryptlen % AES_BLOCK_SIZE; struct skcipher_request subreq; struct skcipher_walk walk; @@ -939,7 +937,7 @@ static int xts_crypt(struct skcipher_request *req, bool encrypt) kernel_fpu_begin(); /* calculate first value of T */ - aesni_enc(aes_ctx(ctx->raw_tweak_ctx), walk.iv, walk.iv); + aesni_enc(&ctx->tweak_ctx, walk.iv, walk.iv); while (walk.nbytes > 0) { int nbytes = walk.nbytes; @@ -948,11 +946,11 @@ static int xts_crypt(struct skcipher_request *req, bool encrypt) nbytes &= ~(AES_BLOCK_SIZE - 1); if (encrypt) - aesni_xts_encrypt(aes_ctx(ctx->raw_crypt_ctx), + aesni_xts_encrypt(&ctx->crypt_ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes, walk.iv); else - aesni_xts_decrypt(aes_ctx(ctx->raw_crypt_ctx), + aesni_xts_decrypt(&ctx->crypt_ctx, walk.dst.virt.addr, walk.src.virt.addr, nbytes, walk.iv); kernel_fpu_end(); @@ -980,11 +978,11 @@ static int xts_crypt(struct skcipher_request *req, bool encrypt) kernel_fpu_begin(); if (encrypt) - aesni_xts_encrypt(aes_ctx(ctx->raw_crypt_ctx), + aesni_xts_encrypt(&ctx->crypt_ctx, walk.dst.virt.addr, walk.src.virt.addr, walk.nbytes, walk.iv); else - aesni_xts_decrypt(aes_ctx(ctx->raw_crypt_ctx), + aesni_xts_decrypt(&ctx->crypt_ctx, walk.dst.virt.addr, walk.src.virt.addr, walk.nbytes, walk.iv); kernel_fpu_end(); diff --git a/arch/x86/crypto/nhpoly1305-avx2-glue.c b/arch/x86/crypto/nhpoly1305-avx2-glue.c index 46b036204ed9..c3a872f4d6a7 100644 --- a/arch/x86/crypto/nhpoly1305-avx2-glue.c +++ b/arch/x86/crypto/nhpoly1305-avx2-glue.c @@ -34,6 +34,14 @@ static int nhpoly1305_avx2_update(struct shash_desc *desc, return 0; } +static int nhpoly1305_avx2_digest(struct shash_desc *desc, + const u8 *src, unsigned int srclen, u8 *out) +{ + return crypto_nhpoly1305_init(desc) ?: + nhpoly1305_avx2_update(desc, src, srclen) ?: + crypto_nhpoly1305_final(desc, out); +} + static struct shash_alg nhpoly1305_alg = { .base.cra_name = "nhpoly1305", .base.cra_driver_name = "nhpoly1305-avx2", @@ -44,6 +52,7 @@ static struct shash_alg nhpoly1305_alg = { .init = crypto_nhpoly1305_init, .update = nhpoly1305_avx2_update, .final = crypto_nhpoly1305_final, + .digest = nhpoly1305_avx2_digest, .setkey = crypto_nhpoly1305_setkey, .descsize = sizeof(struct nhpoly1305_state), }; diff --git a/arch/x86/crypto/nhpoly1305-sse2-glue.c b/arch/x86/crypto/nhpoly1305-sse2-glue.c index 4a4970d75107..a268a8439a5c 100644 --- a/arch/x86/crypto/nhpoly1305-sse2-glue.c +++ b/arch/x86/crypto/nhpoly1305-sse2-glue.c @@ -34,6 +34,14 @@ static int nhpoly1305_sse2_update(struct shash_desc *desc, return 0; } +static int nhpoly1305_sse2_digest(struct shash_desc *desc, + const u8 *src, unsigned int srclen, u8 *out) +{ + return crypto_nhpoly1305_init(desc) ?: + nhpoly1305_sse2_update(desc, src, srclen) ?: + crypto_nhpoly1305_final(desc, out); +} + static struct shash_alg nhpoly1305_alg = { .base.cra_name = "nhpoly1305", .base.cra_driver_name = "nhpoly1305-sse2", @@ -44,6 +52,7 @@ static struct shash_alg nhpoly1305_alg = { .init = crypto_nhpoly1305_init, .update = nhpoly1305_sse2_update, .final = crypto_nhpoly1305_final, + .digest = nhpoly1305_sse2_digest, .setkey = crypto_nhpoly1305_setkey, .descsize = sizeof(struct nhpoly1305_state), }; diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 44340a1139e0..959afa705e95 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -24,8 +24,17 @@ #include <linux/types.h> #include <crypto/sha1.h> #include <crypto/sha1_base.h> +#include <asm/cpu_device_id.h> #include <asm/simd.h> +static const struct x86_cpu_id module_cpu_ids[] = { + X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), + X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), + X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids); + static int sha1_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha1_block_fn *sha1_xform) { @@ -301,6 +310,9 @@ static inline void unregister_sha1_ni(void) { } static int __init sha1_ssse3_mod_init(void) { + if (!x86_match_cpu(module_cpu_ids)) + return -ENODEV; + if (register_sha1_ssse3()) goto fail; diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index 3a5f6be7dbba..4c0383a90e11 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -38,11 +38,20 @@ #include <crypto/sha2.h> #include <crypto/sha256_base.h> #include <linux/string.h> +#include <asm/cpu_device_id.h> #include <asm/simd.h> asmlinkage void sha256_transform_ssse3(struct sha256_state *state, const u8 *data, int blocks); +static const struct x86_cpu_id module_cpu_ids[] = { + X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), + X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), + X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids); + static int _sha256_update(struct shash_desc *desc, const u8 *data, unsigned int len, sha256_block_fn *sha256_xform) { @@ -98,12 +107,20 @@ static int sha256_ssse3_final(struct shash_desc *desc, u8 *out) return sha256_ssse3_finup(desc, NULL, 0, out); } +static int sha256_ssse3_digest(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha256_base_init(desc) ?: + sha256_ssse3_finup(desc, data, len, out); +} + static struct shash_alg sha256_ssse3_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_ssse3_update, .final = sha256_ssse3_final, .finup = sha256_ssse3_finup, + .digest = sha256_ssse3_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", @@ -163,12 +180,20 @@ static int sha256_avx_final(struct shash_desc *desc, u8 *out) return sha256_avx_finup(desc, NULL, 0, out); } +static int sha256_avx_digest(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha256_base_init(desc) ?: + sha256_avx_finup(desc, data, len, out); +} + static struct shash_alg sha256_avx_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_avx_update, .final = sha256_avx_final, .finup = sha256_avx_finup, + .digest = sha256_avx_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", @@ -239,12 +264,20 @@ static int sha256_avx2_final(struct shash_desc *desc, u8 *out) return sha256_avx2_finup(desc, NULL, 0, out); } +static int sha256_avx2_digest(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha256_base_init(desc) ?: + sha256_avx2_finup(desc, data, len, out); +} + static struct shash_alg sha256_avx2_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_avx2_update, .final = sha256_avx2_final, .finup = sha256_avx2_finup, + .digest = sha256_avx2_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", @@ -314,12 +347,20 @@ static int sha256_ni_final(struct shash_desc *desc, u8 *out) return sha256_ni_finup(desc, NULL, 0, out); } +static int sha256_ni_digest(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return sha256_base_init(desc) ?: + sha256_ni_finup(desc, data, len, out); +} + static struct shash_alg sha256_ni_algs[] = { { .digestsize = SHA256_DIGEST_SIZE, .init = sha256_base_init, .update = sha256_ni_update, .final = sha256_ni_final, .finup = sha256_ni_finup, + .digest = sha256_ni_digest, .descsize = sizeof(struct sha256_state), .base = { .cra_name = "sha256", @@ -366,6 +407,9 @@ static inline void unregister_sha256_ni(void) { } static int __init sha256_ssse3_mod_init(void) { + if (!x86_match_cpu(module_cpu_ids)) + return -ENODEV; + if (register_sha256_ssse3()) goto fail; diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 93c60c0c9d4a..d813160b14d8 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -19,6 +19,7 @@ #include <linux/nospec.h> #include <linux/syscalls.h> #include <linux/uaccess.h> +#include <linux/init.h> #ifdef CONFIG_XEN_PV #include <xen/xen-ops.h> @@ -70,7 +71,8 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr) return false; } -__visible noinstr void do_syscall_64(struct pt_regs *regs, int nr) +/* Returns true to return using SYSRET, or false to use IRET */ +__visible noinstr bool do_syscall_64(struct pt_regs *regs, int nr) { add_random_kstack_offset(); nr = syscall_enter_from_user_mode(regs, nr); @@ -84,6 +86,46 @@ __visible noinstr void do_syscall_64(struct pt_regs *regs, int nr) instrumentation_end(); syscall_exit_to_user_mode(regs); + + /* + * Check that the register state is valid for using SYSRET to exit + * to userspace. Otherwise use the slower but fully capable IRET + * exit path. + */ + + /* XEN PV guests always use the IRET path */ + if (cpu_feature_enabled(X86_FEATURE_XENPV)) + return false; + + /* SYSRET requires RCX == RIP and R11 == EFLAGS */ + if (unlikely(regs->cx != regs->ip || regs->r11 != regs->flags)) + return false; + + /* CS and SS must match the values set in MSR_STAR */ + if (unlikely(regs->cs != __USER_CS || regs->ss != __USER_DS)) + return false; + + /* + * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP + * in kernel space. This essentially lets the user take over + * the kernel, since userspace controls RSP. + * + * TASK_SIZE_MAX covers all user-accessible addresses other than + * the deprecated vsyscall page. + */ + if (unlikely(regs->ip >= TASK_SIZE_MAX)) + return false; + + /* + * SYSRET cannot restore RF. It can restore TF, but unlike IRET, + * restoring TF results in a trap from userspace immediately after + * SYSRET. + */ + if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF))) + return false; + + /* Use SYSRET to exit to userspace */ + return true; } #endif @@ -96,6 +138,16 @@ static __always_inline int syscall_32_enter(struct pt_regs *regs) return (int)regs->orig_ax; } +#ifdef CONFIG_IA32_EMULATION +bool __ia32_enabled __ro_after_init = !IS_ENABLED(CONFIG_IA32_EMULATION_DEFAULT_DISABLED); + +static int ia32_emulation_override_cmdline(char *arg) +{ + return kstrtobool(arg, &__ia32_enabled); +} +early_param("ia32_emulation", ia32_emulation_override_cmdline); +#endif + /* * Invoke a 32-bit syscall. Called with IRQs on in CONTEXT_KERNEL. */ @@ -182,8 +234,8 @@ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) return true; } -/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */ -__visible noinstr long do_fast_syscall_32(struct pt_regs *regs) +/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */ +__visible noinstr bool do_fast_syscall_32(struct pt_regs *regs) { /* * Called using the internal vDSO SYSENTER/SYSCALL32 calling @@ -201,41 +253,36 @@ __visible noinstr long do_fast_syscall_32(struct pt_regs *regs) /* Invoke the syscall. If it failed, keep it simple: use IRET. */ if (!__do_fast_syscall_32(regs)) - return 0; + return false; -#ifdef CONFIG_X86_64 /* - * Opportunistic SYSRETL: if possible, try to return using SYSRETL. - * SYSRETL is available on all 64-bit CPUs, so we don't need to - * bother with SYSEXIT. - * - * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP, - * because the ECX fixup above will ensure that this is essentially - * never the case. - */ - return regs->cs == __USER32_CS && regs->ss == __USER_DS && - regs->ip == landing_pad && - (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF)) == 0; -#else - /* - * Opportunistic SYSEXIT: if possible, try to return using SYSEXIT. - * - * Unlike 64-bit opportunistic SYSRET, we can't check that CX == IP, - * because the ECX fixup above will ensure that this is essentially - * never the case. - * - * We don't allow syscalls at all from VM86 mode, but we still - * need to check VM, because we might be returning from sys_vm86. + * Check that the register state is valid for using SYSRETL/SYSEXIT + * to exit to userspace. Otherwise use the slower but fully capable + * IRET exit path. */ - return static_cpu_has(X86_FEATURE_SEP) && - regs->cs == __USER_CS && regs->ss == __USER_DS && - regs->ip == landing_pad && - (regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM)) == 0; -#endif + + /* XEN PV guests always use the IRET path */ + if (cpu_feature_enabled(X86_FEATURE_XENPV)) + return false; + + /* EIP must point to the VDSO landing pad */ + if (unlikely(regs->ip != landing_pad)) + return false; + + /* CS and SS must match the values set in MSR_STAR */ + if (unlikely(regs->cs != __USER32_CS || regs->ss != __USER_DS)) + return false; + + /* If the TF, RF, or VM flags are set, use IRET */ + if (unlikely(regs->flags & (X86_EFLAGS_RF | X86_EFLAGS_TF | X86_EFLAGS_VM))) + return false; + + /* Use SYSRETL/SYSEXIT to exit to userspace */ + return true; } -/* Returns 0 to return using IRET or 1 to return using SYSEXIT/SYSRETL. */ -__visible noinstr long do_SYSENTER_32(struct pt_regs *regs) +/* Returns true to return using SYSEXIT/SYSRETL, or false to use IRET */ +__visible noinstr bool do_SYSENTER_32(struct pt_regs *regs) { /* SYSENTER loses RSP, but the vDSO saved it in RBP. */ regs->sp = regs->bp; diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index bfb7bcb362bc..8c8d38f0cb1d 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -3,8 +3,8 @@ * Common place for both 32- and 64-bit entry routines. */ +#include <linux/export.h> #include <linux/linkage.h> -#include <asm/export.h> #include <asm/msr-index.h> .pushsection .noinstr.text, "ax" diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 6e6af42e044a..c73047bf9f4b 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -837,7 +837,7 @@ SYM_FUNC_START(entry_SYSENTER_32) movl %esp, %eax call do_SYSENTER_32 - testl %eax, %eax + testb %al, %al jz .Lsyscall_32_done STACKLEAK_ERASE diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 43606de22511..de6469dffe3a 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -18,6 +18,7 @@ * - SYM_FUNC_START/END:Define functions in the symbol table. * - idtentry: Define exception entry points. */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/segment.h> #include <asm/cache.h> @@ -34,7 +35,6 @@ #include <asm/asm.h> #include <asm/smap.h> #include <asm/pgtable_types.h> -#include <asm/export.h> #include <asm/frame.h> #include <asm/trapnr.h> #include <asm/nospec-branch.h> @@ -126,70 +126,8 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) * In the Xen PV case we must use iret anyway. */ - ALTERNATIVE "", "jmp swapgs_restore_regs_and_return_to_usermode", \ - X86_FEATURE_XENPV - - movq RCX(%rsp), %rcx - movq RIP(%rsp), %r11 - - cmpq %rcx, %r11 /* SYSRET requires RCX == RIP */ - jne swapgs_restore_regs_and_return_to_usermode - - /* - * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP - * in kernel space. This essentially lets the user take over - * the kernel, since userspace controls RSP. - * - * If width of "canonical tail" ever becomes variable, this will need - * to be updated to remain correct on both old and new CPUs. - * - * Change top bits to match most significant bit (47th or 56th bit - * depending on paging mode) in the address. - */ -#ifdef CONFIG_X86_5LEVEL - ALTERNATIVE "shl $(64 - 48), %rcx; sar $(64 - 48), %rcx", \ - "shl $(64 - 57), %rcx; sar $(64 - 57), %rcx", X86_FEATURE_LA57 -#else - shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx - sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx -#endif - - /* If this changed %rcx, it was not canonical */ - cmpq %rcx, %r11 - jne swapgs_restore_regs_and_return_to_usermode - - cmpq $__USER_CS, CS(%rsp) /* CS must match SYSRET */ - jne swapgs_restore_regs_and_return_to_usermode - - movq R11(%rsp), %r11 - cmpq %r11, EFLAGS(%rsp) /* R11 == RFLAGS */ - jne swapgs_restore_regs_and_return_to_usermode - - /* - * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot - * restore RF properly. If the slowpath sets it for whatever reason, we - * need to restore it correctly. - * - * SYSRET can restore TF, but unlike IRET, restoring TF results in a - * trap from userspace immediately after SYSRET. This would cause an - * infinite loop whenever #DB happens with register state that satisfies - * the opportunistic SYSRET conditions. For example, single-stepping - * this user code: - * - * movq $stuck_here, %rcx - * pushfq - * popq %r11 - * stuck_here: - * - * would never get past 'stuck_here'. - */ - testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 - jnz swapgs_restore_regs_and_return_to_usermode - - /* nothing to check for RSP */ - - cmpq $__USER_DS, SS(%rsp) /* SS must match SYSRET */ - jne swapgs_restore_regs_and_return_to_usermode + ALTERNATIVE "testb %al, %al; jz swapgs_restore_regs_and_return_to_usermode", \ + "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV /* * We win! This label is here just for ease of understanding @@ -1163,8 +1101,8 @@ SYM_CODE_START(asm_exc_nmi) * anyway. * * To handle this case we do the following: - * Check the a special location on the stack that contains - * a variable that is set when NMIs are executing. + * Check a special location on the stack that contains a + * variable that is set when NMIs are executing. * The interrupted task's stack is also checked to see if it * is an NMI stack. * If the variable is not set and the stack is not the NMI @@ -1237,7 +1175,6 @@ SYM_CODE_START(asm_exc_nmi) */ movq %rsp, %rdi - movq $-1, %rsi call exc_nmi /* @@ -1295,8 +1232,8 @@ SYM_CODE_START(asm_exc_nmi) * end_repeat_nmi, then we are a nested NMI. We must not * modify the "iret" frame because it's being written by * the outer NMI. That's okay; the outer NMI handler is - * about to about to call exc_nmi() anyway, so we can just - * resume the outer NMI. + * about to call exc_nmi() anyway, so we can just resume + * the outer NMI. */ movq $repeat_nmi, %rdx @@ -1451,7 +1388,6 @@ end_repeat_nmi: UNWIND_HINT_REGS movq %rsp, %rdi - movq $-1, %rsi call exc_nmi /* Always restore stashed SPEC_CTRL value (see paranoid_entry) */ @@ -1511,18 +1447,16 @@ nmi_restore: iretq SYM_CODE_END(asm_exc_nmi) -#ifndef CONFIG_IA32_EMULATION /* * This handles SYSCALL from 32-bit code. There is no way to program * MSRs to fully disable 32-bit SYSCALL. */ -SYM_CODE_START(ignore_sysret) +SYM_CODE_START(entry_SYSCALL32_ignore) UNWIND_HINT_END_OF_STACK ENDBR mov $-ENOSYS, %eax sysretl -SYM_CODE_END(ignore_sysret) -#endif +SYM_CODE_END(entry_SYSCALL32_ignore) .pushsection .text, "ax" __FUNC_ALIGN diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 70150298f8bd..27c05d08558a 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -118,9 +118,6 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) movq %rsp, %rdi call do_SYSENTER_32 - /* XEN PV guests always use IRET path */ - ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \ - "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV jmp sysret32_from_system_call .Lsysenter_fix_flags: @@ -212,13 +209,15 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) movq %rsp, %rdi call do_fast_syscall_32 + +sysret32_from_system_call: /* XEN PV guests always use IRET path */ - ALTERNATIVE "testl %eax, %eax; jz swapgs_restore_regs_and_return_to_usermode", \ + ALTERNATIVE "testb %al, %al; jz swapgs_restore_regs_and_return_to_usermode", \ "jmp swapgs_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV - /* Opportunistic SYSRET */ -sysret32_from_system_call: /* + * Opportunistic SYSRET + * * We are not going to return to userspace from the trampoline * stack. So let's erase the thread stack right now. */ diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 2d0b1bd866ea..c8fac5205803 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -264,7 +264,7 @@ 250 i386 fadvise64 sys_ia32_fadvise64 # 251 is available for reuse (was briefly sys_set_zone_reclaim) 252 i386 exit_group sys_exit_group -253 i386 lookup_dcookie sys_lookup_dcookie compat_sys_lookup_dcookie +253 i386 lookup_dcookie 254 i386 epoll_create sys_epoll_create 255 i386 epoll_ctl sys_epoll_ctl 256 i386 epoll_wait sys_epoll_wait @@ -457,3 +457,7 @@ 450 i386 set_mempolicy_home_node sys_set_mempolicy_home_node 451 i386 cachestat sys_cachestat 452 i386 fchmodat2 sys_fchmodat2 +453 i386 map_shadow_stack sys_map_shadow_stack +454 i386 futex_wake sys_futex_wake +455 i386 futex_wait sys_futex_wait +456 i386 futex_requeue sys_futex_requeue diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 1d6eee30eceb..8cb8bf68721c 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -220,7 +220,7 @@ 209 64 io_submit sys_io_submit 210 common io_cancel sys_io_cancel 211 64 get_thread_area -212 common lookup_dcookie sys_lookup_dcookie +212 common lookup_dcookie 213 common epoll_create sys_epoll_create 214 64 epoll_ctl_old 215 64 epoll_wait_old @@ -375,6 +375,9 @@ 451 common cachestat sys_cachestat 452 common fchmodat2 sys_fchmodat2 453 64 map_shadow_stack sys_map_shadow_stack +454 common futex_wake sys_futex_wake +455 common futex_wait sys_futex_wait +456 common futex_requeue sys_futex_requeue # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S index ff6e7003da97..0103e103a657 100644 --- a/arch/x86/entry/thunk_32.S +++ b/arch/x86/entry/thunk_32.S @@ -4,9 +4,9 @@ * 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> - #include <asm/export.h> /* put return address in eax (arg1) */ .macro THUNK name, func, put_ret_addr_in_eax=0 diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S index 27b5da2111ac..416b400f39db 100644 --- a/arch/x86/entry/thunk_64.S +++ b/arch/x86/entry/thunk_64.S @@ -4,10 +4,10 @@ * disturbance of register allocation in some inline assembly constructs. * Copyright 2001,2002 by Andi Kleen, SuSE Labs. */ +#include <linux/export.h> #include <linux/linkage.h> #include "calling.h" #include <asm/asm.h> -#include <asm/export.h> /* rdi: arg1 ... normal C conventions. rax is saved/restored. */ .macro THUNK name, func diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile index 6a1821bd7d5e..b1b8dd1608f7 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -42,7 +42,8 @@ vdso_img-$(VDSO64-y) += 64 vdso_img-$(VDSOX32-y) += x32 vdso_img-$(VDSO32-y) += 32 -obj-$(VDSO32-y) += vdso32-setup.o +obj-$(VDSO32-y) += vdso32-setup.o +OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) vobjs32 := $(foreach F,$(vobjs32-y),$(obj)/$F) @@ -190,31 +191,4 @@ GCOV_PROFILE := n quiet_cmd_vdso_and_check = VDSO $@ cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check) -# -# Install the unstripped copies of vdso*.so. If our toolchain supports -# build-id, install .build-id links as well. -# -quiet_cmd_vdso_install = INSTALL $(@:install_%=%) -define cmd_vdso_install - cp $< "$(MODLIB)/vdso/$(@:install_%=%)"; \ - if readelf -n $< |grep -q 'Build ID'; then \ - buildid=`readelf -n $< |grep 'Build ID' |sed -e 's/^.*Build ID: \(.*\)$$/\1/'`; \ - first=`echo $$buildid | cut -b-2`; \ - last=`echo $$buildid | cut -b3-`; \ - mkdir -p "$(MODLIB)/vdso/.build-id/$$first"; \ - ln -sf "../../$(@:install_%=%)" "$(MODLIB)/vdso/.build-id/$$first/$$last.debug"; \ - fi -endef - -vdso_img_insttargets := $(vdso_img_sodbg:%.dbg=install_%) - -$(MODLIB)/vdso: FORCE - @mkdir -p $(MODLIB)/vdso - -$(vdso_img_insttargets): install_%: $(obj)/%.dbg $(MODLIB)/vdso - $(call cmd,vdso_install) - -PHONY += vdso_install $(vdso_img_insttargets) -vdso_install: $(vdso_img_insttargets) - clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so* diff --git a/arch/x86/entry/vdso/vdso32-setup.c b/arch/x86/entry/vdso/vdso32-setup.c index f3b3cacbcbb0..76e4e74f35b5 100644 --- a/arch/x86/entry/vdso/vdso32-setup.c +++ b/arch/x86/entry/vdso/vdso32-setup.c @@ -67,7 +67,6 @@ static struct ctl_table abi_table2[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - {} }; static __init int ia32_binfmt_init(void) diff --git a/arch/x86/entry/vdso/vsgx.S b/arch/x86/entry/vdso/vsgx.S index d77d278ee9dd..37a3d4c02366 100644 --- a/arch/x86/entry/vdso/vsgx.S +++ b/arch/x86/entry/vdso/vsgx.S @@ -1,7 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> -#include <asm/export.h> #include <asm/errno.h> #include <asm/enclu.h> diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index abadd5f23425..e24976593a29 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -534,8 +534,12 @@ static void amd_pmu_cpu_reset(int cpu) /* Clear enable bits i.e. PerfCntrGlobalCtl.PerfCntrEn */ wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0); - /* Clear overflow bits i.e. PerfCntrGLobalStatus.PerfCntrOvfl */ - wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, amd_pmu_global_cntr_mask); + /* + * Clear freeze and overflow bits i.e. PerfCntrGLobalStatus.LbrFreeze + * and PerfCntrGLobalStatus.PerfCntrOvfl + */ + wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, + GLOBAL_STATUS_LBRS_FROZEN | amd_pmu_global_cntr_mask); } static int amd_pmu_cpu_prepare(int cpu) @@ -570,6 +574,7 @@ static void amd_pmu_cpu_starting(int cpu) int i, nb_id; cpuc->perf_ctr_virt_mask = AMD64_EVENTSEL_HOSTONLY; + amd_pmu_cpu_reset(cpu); if (!x86_pmu.amd_nb_constraints) return; @@ -591,8 +596,6 @@ static void amd_pmu_cpu_starting(int cpu) cpuc->amd_nb->nb_id = nb_id; cpuc->amd_nb->refcnt++; - - amd_pmu_cpu_reset(cpu); } static void amd_pmu_cpu_dead(int cpu) @@ -601,6 +604,7 @@ static void amd_pmu_cpu_dead(int cpu) kfree(cpuhw->lbr_sel); cpuhw->lbr_sel = NULL; + amd_pmu_cpu_reset(cpu); if (!x86_pmu.amd_nb_constraints) return; @@ -613,8 +617,6 @@ static void amd_pmu_cpu_dead(int cpu) cpuhw->amd_nb = NULL; } - - amd_pmu_cpu_reset(cpu); } static inline void amd_pmu_set_global_ctl(u64 ctl) @@ -884,7 +886,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) struct hw_perf_event *hwc; struct perf_event *event; int handled = 0, idx; - u64 status, mask; + u64 reserved, status, mask; bool pmu_enabled; /* @@ -909,6 +911,14 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) status &= ~GLOBAL_STATUS_LBRS_FROZEN; } + reserved = status & ~amd_pmu_global_cntr_mask; + if (reserved) + pr_warn_once("Reserved PerfCntrGlobalStatus bits are set (0x%llx), please consider updating microcode\n", + reserved); + + /* Clear any reserved bits set by buggy microcode */ + status &= amd_pmu_global_cntr_mask; + for (idx = 0; idx < x86_pmu.num_counters; idx++) { if (!test_bit(idx, cpuc->active_mask)) continue; diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c index 83f15fe411b3..5bf03c575812 100644 --- a/arch/x86/events/amd/uncore.c +++ b/arch/x86/events/amd/uncore.c @@ -26,57 +26,66 @@ #define RDPMC_BASE_LLC 10 #define COUNTER_SHIFT 16 +#define UNCORE_NAME_LEN 16 +#define UNCORE_GROUP_MAX 256 #undef pr_fmt #define pr_fmt(fmt) "amd_uncore: " fmt static int pmu_version; -static int num_counters_llc; -static int num_counters_nb; -static bool l3_mask; -static HLIST_HEAD(uncore_unused_list); - -struct amd_uncore { - int id; +struct amd_uncore_ctx { int refcnt; int cpu; + struct perf_event **events; + struct hlist_node node; +}; + +struct amd_uncore_pmu { + char name[UNCORE_NAME_LEN]; int num_counters; int rdpmc_base; u32 msr_base; - cpumask_t *active_mask; - struct pmu *pmu; - struct perf_event **events; - struct hlist_node node; + int group; + cpumask_t active_mask; + struct pmu pmu; + struct amd_uncore_ctx * __percpu *ctx; }; -static struct amd_uncore * __percpu *amd_uncore_nb; -static struct amd_uncore * __percpu *amd_uncore_llc; +enum { + UNCORE_TYPE_DF, + UNCORE_TYPE_L3, + UNCORE_TYPE_UMC, -static struct pmu amd_nb_pmu; -static struct pmu amd_llc_pmu; + UNCORE_TYPE_MAX +}; -static cpumask_t amd_nb_active_mask; -static cpumask_t amd_llc_active_mask; +union amd_uncore_info { + struct { + u64 aux_data:32; /* auxiliary data */ + u64 num_pmcs:8; /* number of counters */ + u64 gid:8; /* group id */ + u64 cid:8; /* context id */ + } split; + u64 full; +}; -static bool is_nb_event(struct perf_event *event) -{ - return event->pmu->type == amd_nb_pmu.type; -} +struct amd_uncore { + union amd_uncore_info * __percpu info; + struct amd_uncore_pmu *pmus; + unsigned int num_pmus; + bool init_done; + void (*scan)(struct amd_uncore *uncore, unsigned int cpu); + int (*init)(struct amd_uncore *uncore, unsigned int cpu); + void (*move)(struct amd_uncore *uncore, unsigned int cpu); + void (*free)(struct amd_uncore *uncore, unsigned int cpu); +}; -static bool is_llc_event(struct perf_event *event) -{ - return event->pmu->type == amd_llc_pmu.type; -} +static struct amd_uncore uncores[UNCORE_TYPE_MAX]; -static struct amd_uncore *event_to_amd_uncore(struct perf_event *event) +static struct amd_uncore_pmu *event_to_amd_uncore_pmu(struct perf_event *event) { - if (is_nb_event(event) && amd_uncore_nb) - return *per_cpu_ptr(amd_uncore_nb, event->cpu); - else if (is_llc_event(event) && amd_uncore_llc) - return *per_cpu_ptr(amd_uncore_llc, event->cpu); - - return NULL; + return container_of(event->pmu, struct amd_uncore_pmu, pmu); } static void amd_uncore_read(struct perf_event *event) @@ -91,7 +100,16 @@ static void amd_uncore_read(struct perf_event *event) */ prev = local64_read(&hwc->prev_count); - rdpmcl(hwc->event_base_rdpmc, new); + + /* + * Some uncore PMUs do not have RDPMC assignments. In such cases, + * read counts directly from the corresponding PERF_CTR. + */ + if (hwc->event_base_rdpmc < 0) + rdmsrl(hwc->event_base, new); + else + rdpmcl(hwc->event_base_rdpmc, new); + local64_set(&hwc->prev_count, new); delta = (new << COUNTER_SHIFT) - (prev << COUNTER_SHIFT); delta >>= COUNTER_SHIFT; @@ -118,7 +136,7 @@ static void amd_uncore_stop(struct perf_event *event, int flags) hwc->state |= PERF_HES_STOPPED; if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { - amd_uncore_read(event); + event->pmu->read(event); hwc->state |= PERF_HES_UPTODATE; } } @@ -126,15 +144,16 @@ static void amd_uncore_stop(struct perf_event *event, int flags) static int amd_uncore_add(struct perf_event *event, int flags) { int i; - struct amd_uncore *uncore = event_to_amd_uncore(event); + struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event); + struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu); struct hw_perf_event *hwc = &event->hw; /* are we already assigned? */ - if (hwc->idx != -1 && uncore->events[hwc->idx] == event) + if (hwc->idx != -1 && ctx->events[hwc->idx] == event) goto out; - for (i = 0; i < uncore->num_counters; i++) { - if (uncore->events[i] == event) { + for (i = 0; i < pmu->num_counters; i++) { + if (ctx->events[i] == event) { hwc->idx = i; goto out; } @@ -142,8 +161,8 @@ static int amd_uncore_add(struct perf_event *event, int flags) /* if not, take the first available counter */ hwc->idx = -1; - for (i = 0; i < uncore->num_counters; i++) { - if (cmpxchg(&uncore->events[i], NULL, event) == NULL) { + for (i = 0; i < pmu->num_counters; i++) { + if (cmpxchg(&ctx->events[i], NULL, event) == NULL) { hwc->idx = i; break; } @@ -153,23 +172,16 @@ out: if (hwc->idx == -1) return -EBUSY; - hwc->config_base = uncore->msr_base + (2 * hwc->idx); - hwc->event_base = uncore->msr_base + 1 + (2 * hwc->idx); - hwc->event_base_rdpmc = uncore->rdpmc_base + hwc->idx; + hwc->config_base = pmu->msr_base + (2 * hwc->idx); + hwc->event_base = pmu->msr_base + 1 + (2 * hwc->idx); + hwc->event_base_rdpmc = pmu->rdpmc_base + hwc->idx; hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; - /* - * The first four DF counters are accessible via RDPMC index 6 to 9 - * followed by the L3 counters from index 10 to 15. For processors - * with more than four DF counters, the DF RDPMC assignments become - * discontiguous as the additional counters are accessible starting - * from index 16. - */ - if (is_nb_event(event) && hwc->idx >= NUM_COUNTERS_NB) - hwc->event_base_rdpmc += NUM_COUNTERS_L3; + if (pmu->rdpmc_base < 0) + hwc->event_base_rdpmc = -1; if (flags & PERF_EF_START) - amd_uncore_start(event, PERF_EF_RELOAD); + event->pmu->start(event, PERF_EF_RELOAD); return 0; } @@ -177,55 +189,36 @@ out: static void amd_uncore_del(struct perf_event *event, int flags) { int i; - struct amd_uncore *uncore = event_to_amd_uncore(event); + struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event); + struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu); struct hw_perf_event *hwc = &event->hw; - amd_uncore_stop(event, PERF_EF_UPDATE); + event->pmu->stop(event, PERF_EF_UPDATE); - for (i = 0; i < uncore->num_counters; i++) { - if (cmpxchg(&uncore->events[i], event, NULL) == event) + for (i = 0; i < pmu->num_counters; i++) { + if (cmpxchg(&ctx->events[i], event, NULL) == event) break; } hwc->idx = -1; } -/* - * Return a full thread and slice mask unless user - * has provided them - */ -static u64 l3_thread_slice_mask(u64 config) -{ - if (boot_cpu_data.x86 <= 0x18) - return ((config & AMD64_L3_SLICE_MASK) ? : AMD64_L3_SLICE_MASK) | - ((config & AMD64_L3_THREAD_MASK) ? : AMD64_L3_THREAD_MASK); - - /* - * If the user doesn't specify a threadmask, they're not trying to - * count core 0, so we enable all cores & threads. - * We'll also assume that they want to count slice 0 if they specify - * a threadmask and leave sliceid and enallslices unpopulated. - */ - if (!(config & AMD64_L3_F19H_THREAD_MASK)) - return AMD64_L3_F19H_THREAD_MASK | AMD64_L3_EN_ALL_SLICES | - AMD64_L3_EN_ALL_CORES; - - return config & (AMD64_L3_F19H_THREAD_MASK | AMD64_L3_SLICEID_MASK | - AMD64_L3_EN_ALL_CORES | AMD64_L3_EN_ALL_SLICES | - AMD64_L3_COREID_MASK); -} - static int amd_uncore_event_init(struct perf_event *event) { - struct amd_uncore *uncore; + struct amd_uncore_pmu *pmu; + struct amd_uncore_ctx *ctx; struct hw_perf_event *hwc = &event->hw; - u64 event_mask = AMD64_RAW_EVENT_MASK_NB; if (event->attr.type != event->pmu->type) return -ENOENT; - if (pmu_version >= 2 && is_nb_event(event)) - event_mask = AMD64_PERFMON_V2_RAW_EVENT_MASK_NB; + if (event->cpu < 0) + return -EINVAL; + + pmu = event_to_amd_uncore_pmu(event); + ctx = *per_cpu_ptr(pmu->ctx, event->cpu); + if (!ctx) + return -ENODEV; /* * NB and Last level cache counters (MSRs) are shared across all cores @@ -235,28 +228,14 @@ static int amd_uncore_event_init(struct perf_event *event) * out. So we do not support sampling and per-thread events via * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts: */ - hwc->config = event->attr.config & event_mask; + hwc->config = event->attr.config; hwc->idx = -1; - if (event->cpu < 0) - return -EINVAL; - - /* - * SliceMask and ThreadMask need to be set for certain L3 events. - * For other events, the two fields do not affect the count. - */ - if (l3_mask && is_llc_event(event)) - hwc->config |= l3_thread_slice_mask(event->attr.config); - - uncore = event_to_amd_uncore(event); - if (!uncore) - return -ENODEV; - /* * since request can come in to any of the shared cores, we will remap * to a single common cpu. */ - event->cpu = uncore->cpu; + event->cpu = ctx->cpu; return 0; } @@ -278,17 +257,10 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev, struct device_attribute *attr, char *buf) { - cpumask_t *active_mask; - struct pmu *pmu = dev_get_drvdata(dev); + struct pmu *ptr = dev_get_drvdata(dev); + struct amd_uncore_pmu *pmu = container_of(ptr, struct amd_uncore_pmu, pmu); - if (pmu->type == amd_nb_pmu.type) - active_mask = &amd_nb_active_mask; - else if (pmu->type == amd_llc_pmu.type) - active_mask = &amd_llc_active_mask; - else - return 0; - - return cpumap_print_to_pagebuf(true, buf, active_mask); + return cpumap_print_to_pagebuf(true, buf, &pmu->active_mask); } static DEVICE_ATTR(cpumask, S_IRUGO, amd_uncore_attr_show_cpumask, NULL); @@ -315,7 +287,7 @@ static struct device_attribute format_attr_##_var = \ DEFINE_UNCORE_FORMAT_ATTR(event12, event, "config:0-7,32-35"); DEFINE_UNCORE_FORMAT_ATTR(event14, event, "config:0-7,32-35,59-60"); /* F17h+ DF */ DEFINE_UNCORE_FORMAT_ATTR(event14v2, event, "config:0-7,32-37"); /* PerfMonV2 DF */ -DEFINE_UNCORE_FORMAT_ATTR(event8, event, "config:0-7"); /* F17h+ L3 */ +DEFINE_UNCORE_FORMAT_ATTR(event8, event, "config:0-7"); /* F17h+ L3, PerfMonV2 UMC */ DEFINE_UNCORE_FORMAT_ATTR(umask8, umask, "config:8-15"); DEFINE_UNCORE_FORMAT_ATTR(umask12, umask, "config:8-15,24-27"); /* PerfMonV2 DF */ DEFINE_UNCORE_FORMAT_ATTR(coreid, coreid, "config:42-44"); /* F19h L3 */ @@ -325,6 +297,7 @@ DEFINE_UNCORE_FORMAT_ATTR(threadmask2, threadmask, "config:56-57"); /* F19h L DEFINE_UNCORE_FORMAT_ATTR(enallslices, enallslices, "config:46"); /* F19h L3 */ DEFINE_UNCORE_FORMAT_ATTR(enallcores, enallcores, "config:47"); /* F19h L3 */ DEFINE_UNCORE_FORMAT_ATTR(sliceid, sliceid, "config:48-50"); /* F19h L3 */ +DEFINE_UNCORE_FORMAT_ATTR(rdwrmask, rdwrmask, "config:8-9"); /* PerfMonV2 UMC */ /* Common DF and NB attributes */ static struct attribute *amd_uncore_df_format_attr[] = { @@ -341,6 +314,13 @@ static struct attribute *amd_uncore_l3_format_attr[] = { NULL, }; +/* Common UMC attributes */ +static struct attribute *amd_uncore_umc_format_attr[] = { + &format_attr_event8.attr, /* event */ + &format_attr_rdwrmask.attr, /* rdwrmask */ + NULL, +}; + /* F17h unique L3 attributes */ static struct attribute *amd_f17h_uncore_l3_format_attr[] = { &format_attr_slicemask.attr, /* slicemask */ @@ -378,6 +358,11 @@ static struct attribute_group amd_f19h_uncore_l3_format_group = { .is_visible = amd_f19h_uncore_is_visible, }; +static struct attribute_group amd_uncore_umc_format_group = { + .name = "format", + .attrs = amd_uncore_umc_format_attr, +}; + static const struct attribute_group *amd_uncore_df_attr_groups[] = { &amd_uncore_attr_group, &amd_uncore_df_format_group, @@ -396,259 +381,636 @@ static const struct attribute_group *amd_uncore_l3_attr_update[] = { NULL, }; -static struct pmu amd_nb_pmu = { - .task_ctx_nr = perf_invalid_context, - .attr_groups = amd_uncore_df_attr_groups, - .name = "amd_nb", - .event_init = amd_uncore_event_init, - .add = amd_uncore_add, - .del = amd_uncore_del, - .start = amd_uncore_start, - .stop = amd_uncore_stop, - .read = amd_uncore_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, - .module = THIS_MODULE, +static const struct attribute_group *amd_uncore_umc_attr_groups[] = { + &amd_uncore_attr_group, + &amd_uncore_umc_format_group, + NULL, }; -static struct pmu amd_llc_pmu = { - .task_ctx_nr = perf_invalid_context, - .attr_groups = amd_uncore_l3_attr_groups, - .attr_update = amd_uncore_l3_attr_update, - .name = "amd_l2", - .event_init = amd_uncore_event_init, - .add = amd_uncore_add, - .del = amd_uncore_del, - .start = amd_uncore_start, - .stop = amd_uncore_stop, - .read = amd_uncore_read, - .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, - .module = THIS_MODULE, -}; +static __always_inline +int amd_uncore_ctx_cid(struct amd_uncore *uncore, unsigned int cpu) +{ + union amd_uncore_info *info = per_cpu_ptr(uncore->info, cpu); + return info->split.cid; +} -static struct amd_uncore *amd_uncore_alloc(unsigned int cpu) +static __always_inline +int amd_uncore_ctx_gid(struct amd_uncore *uncore, unsigned int cpu) { - return kzalloc_node(sizeof(struct amd_uncore), GFP_KERNEL, - cpu_to_node(cpu)); + union amd_uncore_info *info = per_cpu_ptr(uncore->info, cpu); + return info->split.gid; } -static inline struct perf_event ** -amd_uncore_events_alloc(unsigned int num, unsigned int cpu) +static __always_inline +int amd_uncore_ctx_num_pmcs(struct amd_uncore *uncore, unsigned int cpu) { - return kzalloc_node(sizeof(struct perf_event *) * num, GFP_KERNEL, - cpu_to_node(cpu)); + union amd_uncore_info *info = per_cpu_ptr(uncore->info, cpu); + return info->split.num_pmcs; } -static int amd_uncore_cpu_up_prepare(unsigned int cpu) +static void amd_uncore_ctx_free(struct amd_uncore *uncore, unsigned int cpu) { - struct amd_uncore *uncore_nb = NULL, *uncore_llc = NULL; + struct amd_uncore_pmu *pmu; + struct amd_uncore_ctx *ctx; + int i; - if (amd_uncore_nb) { - *per_cpu_ptr(amd_uncore_nb, cpu) = NULL; - uncore_nb = amd_uncore_alloc(cpu); - if (!uncore_nb) - goto fail; - uncore_nb->cpu = cpu; - uncore_nb->num_counters = num_counters_nb; - uncore_nb->rdpmc_base = RDPMC_BASE_NB; - uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL; - uncore_nb->active_mask = &amd_nb_active_mask; - uncore_nb->pmu = &amd_nb_pmu; - uncore_nb->events = amd_uncore_events_alloc(num_counters_nb, cpu); - if (!uncore_nb->events) - goto fail; - uncore_nb->id = -1; - *per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb; + if (!uncore->init_done) + return; + + for (i = 0; i < uncore->num_pmus; i++) { + pmu = &uncore->pmus[i]; + ctx = *per_cpu_ptr(pmu->ctx, cpu); + if (!ctx) + continue; + + if (cpu == ctx->cpu) + cpumask_clear_cpu(cpu, &pmu->active_mask); + + if (!--ctx->refcnt) { + kfree(ctx->events); + kfree(ctx); + } + + *per_cpu_ptr(pmu->ctx, cpu) = NULL; } +} - if (amd_uncore_llc) { - *per_cpu_ptr(amd_uncore_llc, cpu) = NULL; - uncore_llc = amd_uncore_alloc(cpu); - if (!uncore_llc) - goto fail; - uncore_llc->cpu = cpu; - uncore_llc->num_counters = num_counters_llc; - uncore_llc->rdpmc_base = RDPMC_BASE_LLC; - uncore_llc->msr_base = MSR_F16H_L2I_PERF_CTL; - uncore_llc->active_mask = &amd_llc_active_mask; - uncore_llc->pmu = &amd_llc_pmu; - uncore_llc->events = amd_uncore_events_alloc(num_counters_llc, cpu); - if (!uncore_llc->events) - goto fail; - uncore_llc->id = -1; - *per_cpu_ptr(amd_uncore_llc, cpu) = uncore_llc; +static int amd_uncore_ctx_init(struct amd_uncore *uncore, unsigned int cpu) +{ + struct amd_uncore_ctx *curr, *prev; + struct amd_uncore_pmu *pmu; + int node, cid, gid, i, j; + + if (!uncore->init_done || !uncore->num_pmus) + return 0; + + cid = amd_uncore_ctx_cid(uncore, cpu); + gid = amd_uncore_ctx_gid(uncore, cpu); + + for (i = 0; i < uncore->num_pmus; i++) { + pmu = &uncore->pmus[i]; + *per_cpu_ptr(pmu->ctx, cpu) = NULL; + curr = NULL; + + /* Check for group exclusivity */ + if (gid != pmu->group) + continue; + + /* Find a sibling context */ + for_each_online_cpu(j) { + if (cpu == j) + continue; + + prev = *per_cpu_ptr(pmu->ctx, j); + if (!prev) + continue; + + if (cid == amd_uncore_ctx_cid(uncore, j)) { + curr = prev; + break; + } + } + + /* Allocate context if sibling does not exist */ + if (!curr) { + node = cpu_to_node(cpu); + curr = kzalloc_node(sizeof(*curr), GFP_KERNEL, node); + if (!curr) + goto fail; + + curr->cpu = cpu; + curr->events = kzalloc_node(sizeof(*curr->events) * + pmu->num_counters, + GFP_KERNEL, node); + if (!curr->events) { + kfree(curr); + goto fail; + } + + cpumask_set_cpu(cpu, &pmu->active_mask); + } + + curr->refcnt++; + *per_cpu_ptr(pmu->ctx, cpu) = curr; } return 0; fail: - if (uncore_nb) { - kfree(uncore_nb->events); - kfree(uncore_nb); - } - - if (uncore_llc) { - kfree(uncore_llc->events); - kfree(uncore_llc); - } + amd_uncore_ctx_free(uncore, cpu); return -ENOMEM; } -static struct amd_uncore * -amd_uncore_find_online_sibling(struct amd_uncore *this, - struct amd_uncore * __percpu *uncores) +static void amd_uncore_ctx_move(struct amd_uncore *uncore, unsigned int cpu) { - unsigned int cpu; - struct amd_uncore *that; - - for_each_online_cpu(cpu) { - that = *per_cpu_ptr(uncores, cpu); + struct amd_uncore_ctx *curr, *next; + struct amd_uncore_pmu *pmu; + int i, j; - if (!that) - continue; + if (!uncore->init_done) + return; - if (this == that) + for (i = 0; i < uncore->num_pmus; i++) { + pmu = &uncore->pmus[i]; + curr = *per_cpu_ptr(pmu->ctx, cpu); + if (!curr) continue; - if (this->id == that->id) { - hlist_add_head(&this->node, &uncore_unused_list); - this = that; - break; + /* Migrate to a shared sibling if possible */ + for_each_online_cpu(j) { + next = *per_cpu_ptr(pmu->ctx, j); + if (!next || cpu == j) + continue; + + if (curr == next) { + perf_pmu_migrate_context(&pmu->pmu, cpu, j); + cpumask_clear_cpu(cpu, &pmu->active_mask); + cpumask_set_cpu(j, &pmu->active_mask); + next->cpu = j; + break; + } } } - - this->refcnt++; - return this; } static int amd_uncore_cpu_starting(unsigned int cpu) { - unsigned int eax, ebx, ecx, edx; struct amd_uncore *uncore; + int i; + + for (i = 0; i < UNCORE_TYPE_MAX; i++) { + uncore = &uncores[i]; + uncore->scan(uncore, cpu); + } + + return 0; +} - if (amd_uncore_nb) { - uncore = *per_cpu_ptr(amd_uncore_nb, cpu); - cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - uncore->id = ecx & 0xff; +static int amd_uncore_cpu_online(unsigned int cpu) +{ + struct amd_uncore *uncore; + int i; - uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_nb); - *per_cpu_ptr(amd_uncore_nb, cpu) = uncore; + for (i = 0; i < UNCORE_TYPE_MAX; i++) { + uncore = &uncores[i]; + if (uncore->init(uncore, cpu)) + break; } - if (amd_uncore_llc) { - uncore = *per_cpu_ptr(amd_uncore_llc, cpu); - uncore->id = get_llc_id(cpu); + return 0; +} - uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc); - *per_cpu_ptr(amd_uncore_llc, cpu) = uncore; +static int amd_uncore_cpu_down_prepare(unsigned int cpu) +{ + struct amd_uncore *uncore; + int i; + + for (i = 0; i < UNCORE_TYPE_MAX; i++) { + uncore = &uncores[i]; + uncore->move(uncore, cpu); } return 0; } -static void uncore_clean_online(void) +static int amd_uncore_cpu_dead(unsigned int cpu) { struct amd_uncore *uncore; - struct hlist_node *n; + int i; - hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) { - hlist_del(&uncore->node); - kfree(uncore->events); - kfree(uncore); + for (i = 0; i < UNCORE_TYPE_MAX; i++) { + uncore = &uncores[i]; + uncore->free(uncore, cpu); } + + return 0; } -static void uncore_online(unsigned int cpu, - struct amd_uncore * __percpu *uncores) +static int amd_uncore_df_event_init(struct perf_event *event) { - struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu); + struct hw_perf_event *hwc = &event->hw; + int ret = amd_uncore_event_init(event); - uncore_clean_online(); + if (ret || pmu_version < 2) + return ret; - if (cpu == uncore->cpu) - cpumask_set_cpu(cpu, uncore->active_mask); + hwc->config = event->attr.config & + (pmu_version >= 2 ? AMD64_PERFMON_V2_RAW_EVENT_MASK_NB : + AMD64_RAW_EVENT_MASK_NB); + + return 0; } -static int amd_uncore_cpu_online(unsigned int cpu) +static int amd_uncore_df_add(struct perf_event *event, int flags) { - if (amd_uncore_nb) - uncore_online(cpu, amd_uncore_nb); + int ret = amd_uncore_add(event, flags & ~PERF_EF_START); + struct hw_perf_event *hwc = &event->hw; + + if (ret) + return ret; + + /* + * The first four DF counters are accessible via RDPMC index 6 to 9 + * followed by the L3 counters from index 10 to 15. For processors + * with more than four DF counters, the DF RDPMC assignments become + * discontiguous as the additional counters are accessible starting + * from index 16. + */ + if (hwc->idx >= NUM_COUNTERS_NB) + hwc->event_base_rdpmc += NUM_COUNTERS_L3; - if (amd_uncore_llc) - uncore_online(cpu, amd_uncore_llc); + /* Delayed start after rdpmc base update */ + if (flags & PERF_EF_START) + amd_uncore_start(event, PERF_EF_RELOAD); return 0; } -static void uncore_down_prepare(unsigned int cpu, - struct amd_uncore * __percpu *uncores) +static +void amd_uncore_df_ctx_scan(struct amd_uncore *uncore, unsigned int cpu) { - unsigned int i; - struct amd_uncore *this = *per_cpu_ptr(uncores, cpu); + union cpuid_0x80000022_ebx ebx; + union amd_uncore_info info; - if (this->cpu != cpu) + if (!boot_cpu_has(X86_FEATURE_PERFCTR_NB)) return; - /* this cpu is going down, migrate to a shared sibling if possible */ - for_each_online_cpu(i) { - struct amd_uncore *that = *per_cpu_ptr(uncores, i); + info.split.aux_data = 0; + info.split.num_pmcs = NUM_COUNTERS_NB; + info.split.gid = 0; + info.split.cid = topology_die_id(cpu); - if (cpu == i) - continue; + if (pmu_version >= 2) { + ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES); + info.split.num_pmcs = ebx.split.num_df_pmc; + } - if (this == that) { - perf_pmu_migrate_context(this->pmu, cpu, i); - cpumask_clear_cpu(cpu, that->active_mask); - cpumask_set_cpu(i, that->active_mask); - that->cpu = i; - break; - } + *per_cpu_ptr(uncore->info, cpu) = info; +} + +static +int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu) +{ + struct attribute **df_attr = amd_uncore_df_format_attr; + struct amd_uncore_pmu *pmu; + + /* Run just once */ + if (uncore->init_done) + return amd_uncore_ctx_init(uncore, cpu); + + /* No grouping, single instance for a system */ + uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL); + if (!uncore->pmus) { + uncore->num_pmus = 0; + goto done; } + + /* + * For Family 17h and above, the Northbridge counters are repurposed + * as Data Fabric counters. The PMUs are exported based on family as + * either NB or DF. + */ + pmu = &uncore->pmus[0]; + strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_df" : "amd_nb", + sizeof(pmu->name)); + pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu); + pmu->msr_base = MSR_F15H_NB_PERF_CTL; + pmu->rdpmc_base = RDPMC_BASE_NB; + pmu->group = amd_uncore_ctx_gid(uncore, cpu); + + if (pmu_version >= 2) { + *df_attr++ = &format_attr_event14v2.attr; + *df_attr++ = &format_attr_umask12.attr; + } else if (boot_cpu_data.x86 >= 0x17) { + *df_attr = &format_attr_event14.attr; + } + + pmu->ctx = alloc_percpu(struct amd_uncore_ctx *); + if (!pmu->ctx) + goto done; + + pmu->pmu = (struct pmu) { + .task_ctx_nr = perf_invalid_context, + .attr_groups = amd_uncore_df_attr_groups, + .name = pmu->name, + .event_init = amd_uncore_df_event_init, + .add = amd_uncore_df_add, + .del = amd_uncore_del, + .start = amd_uncore_start, + .stop = amd_uncore_stop, + .read = amd_uncore_read, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, + .module = THIS_MODULE, + }; + + if (perf_pmu_register(&pmu->pmu, pmu->pmu.name, -1)) { + free_percpu(pmu->ctx); + pmu->ctx = NULL; + goto done; + } + + pr_info("%d %s%s counters detected\n", pmu->num_counters, + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ? "HYGON " : "", + pmu->pmu.name); + + uncore->num_pmus = 1; + +done: + uncore->init_done = true; + + return amd_uncore_ctx_init(uncore, cpu); } -static int amd_uncore_cpu_down_prepare(unsigned int cpu) +static int amd_uncore_l3_event_init(struct perf_event *event) { - if (amd_uncore_nb) - uncore_down_prepare(cpu, amd_uncore_nb); + int ret = amd_uncore_event_init(event); + struct hw_perf_event *hwc = &event->hw; + u64 config = event->attr.config; + u64 mask; - if (amd_uncore_llc) - uncore_down_prepare(cpu, amd_uncore_llc); + hwc->config = config & AMD64_RAW_EVENT_MASK_NB; + + /* + * SliceMask and ThreadMask need to be set for certain L3 events. + * For other events, the two fields do not affect the count. + */ + if (ret || boot_cpu_data.x86 < 0x17) + return ret; + + mask = config & (AMD64_L3_F19H_THREAD_MASK | AMD64_L3_SLICEID_MASK | + AMD64_L3_EN_ALL_CORES | AMD64_L3_EN_ALL_SLICES | + AMD64_L3_COREID_MASK); + + if (boot_cpu_data.x86 <= 0x18) + mask = ((config & AMD64_L3_SLICE_MASK) ? : AMD64_L3_SLICE_MASK) | + ((config & AMD64_L3_THREAD_MASK) ? : AMD64_L3_THREAD_MASK); + + /* + * If the user doesn't specify a ThreadMask, they're not trying to + * count core 0, so we enable all cores & threads. + * We'll also assume that they want to count slice 0 if they specify + * a ThreadMask and leave SliceId and EnAllSlices unpopulated. + */ + else if (!(config & AMD64_L3_F19H_THREAD_MASK)) + mask = AMD64_L3_F19H_THREAD_MASK | AMD64_L3_EN_ALL_SLICES | + AMD64_L3_EN_ALL_CORES; + + hwc->config |= mask; return 0; } -static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores) +static +void amd_uncore_l3_ctx_scan(struct amd_uncore *uncore, unsigned int cpu) { - struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu); + union amd_uncore_info info; - if (cpu == uncore->cpu) - cpumask_clear_cpu(cpu, uncore->active_mask); + if (!boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) + return; + + info.split.aux_data = 0; + info.split.num_pmcs = NUM_COUNTERS_L2; + info.split.gid = 0; + info.split.cid = per_cpu_llc_id(cpu); - if (!--uncore->refcnt) { - kfree(uncore->events); - kfree(uncore); + if (boot_cpu_data.x86 >= 0x17) + info.split.num_pmcs = NUM_COUNTERS_L3; + + *per_cpu_ptr(uncore->info, cpu) = info; +} + +static +int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu) +{ + struct attribute **l3_attr = amd_uncore_l3_format_attr; + struct amd_uncore_pmu *pmu; + + /* Run just once */ + if (uncore->init_done) + return amd_uncore_ctx_init(uncore, cpu); + + /* No grouping, single instance for a system */ + uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL); + if (!uncore->pmus) { + uncore->num_pmus = 0; + goto done; } - *per_cpu_ptr(uncores, cpu) = NULL; + /* + * For Family 17h and above, L3 cache counters are available instead + * of L2 cache counters. The PMUs are exported based on family as + * either L2 or L3. + */ + pmu = &uncore->pmus[0]; + strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_l3" : "amd_l2", + sizeof(pmu->name)); + pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu); + pmu->msr_base = MSR_F16H_L2I_PERF_CTL; + pmu->rdpmc_base = RDPMC_BASE_LLC; + pmu->group = amd_uncore_ctx_gid(uncore, cpu); + + if (boot_cpu_data.x86 >= 0x17) { + *l3_attr++ = &format_attr_event8.attr; + *l3_attr++ = &format_attr_umask8.attr; + *l3_attr++ = boot_cpu_data.x86 >= 0x19 ? + &format_attr_threadmask2.attr : + &format_attr_threadmask8.attr; + } + + pmu->ctx = alloc_percpu(struct amd_uncore_ctx *); + if (!pmu->ctx) + goto done; + + pmu->pmu = (struct pmu) { + .task_ctx_nr = perf_invalid_context, + .attr_groups = amd_uncore_l3_attr_groups, + .attr_update = amd_uncore_l3_attr_update, + .name = pmu->name, + .event_init = amd_uncore_l3_event_init, + .add = amd_uncore_add, + .del = amd_uncore_del, + .start = amd_uncore_start, + .stop = amd_uncore_stop, + .read = amd_uncore_read, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, + .module = THIS_MODULE, + }; + + if (perf_pmu_register(&pmu->pmu, pmu->pmu.name, -1)) { + free_percpu(pmu->ctx); + pmu->ctx = NULL; + goto done; + } + + pr_info("%d %s%s counters detected\n", pmu->num_counters, + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ? "HYGON " : "", + pmu->pmu.name); + + uncore->num_pmus = 1; + +done: + uncore->init_done = true; + + return amd_uncore_ctx_init(uncore, cpu); } -static int amd_uncore_cpu_dead(unsigned int cpu) +static int amd_uncore_umc_event_init(struct perf_event *event) { - if (amd_uncore_nb) - uncore_dead(cpu, amd_uncore_nb); + struct hw_perf_event *hwc = &event->hw; + int ret = amd_uncore_event_init(event); + + if (ret) + return ret; - if (amd_uncore_llc) - uncore_dead(cpu, amd_uncore_llc); + hwc->config = event->attr.config & AMD64_PERFMON_V2_RAW_EVENT_MASK_UMC; return 0; } -static int __init amd_uncore_init(void) +static void amd_uncore_umc_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + + if (flags & PERF_EF_RELOAD) + wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count)); + + hwc->state = 0; + wrmsrl(hwc->config_base, (hwc->config | AMD64_PERFMON_V2_ENABLE_UMC)); + perf_event_update_userpage(event); +} + +static +void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu) { - struct attribute **df_attr = amd_uncore_df_format_attr; - struct attribute **l3_attr = amd_uncore_l3_format_attr; union cpuid_0x80000022_ebx ebx; + union amd_uncore_info info; + unsigned int eax, ecx, edx; + + if (pmu_version < 2) + return; + + cpuid(EXT_PERFMON_DEBUG_FEATURES, &eax, &ebx.full, &ecx, &edx); + info.split.aux_data = ecx; /* stash active mask */ + info.split.num_pmcs = ebx.split.num_umc_pmc; + info.split.gid = topology_die_id(cpu); + info.split.cid = topology_die_id(cpu); + *per_cpu_ptr(uncore->info, cpu) = info; +} + +static +int amd_uncore_umc_ctx_init(struct amd_uncore *uncore, unsigned int cpu) +{ + DECLARE_BITMAP(gmask, UNCORE_GROUP_MAX) = { 0 }; + u8 group_num_pmus[UNCORE_GROUP_MAX] = { 0 }; + u8 group_num_pmcs[UNCORE_GROUP_MAX] = { 0 }; + union amd_uncore_info info; + struct amd_uncore_pmu *pmu; + int index = 0, gid, i; + + if (pmu_version < 2) + return 0; + + /* Run just once */ + if (uncore->init_done) + return amd_uncore_ctx_init(uncore, cpu); + + /* Find unique groups */ + for_each_online_cpu(i) { + info = *per_cpu_ptr(uncore->info, i); + gid = info.split.gid; + if (test_bit(gid, gmask)) + continue; + + __set_bit(gid, gmask); + group_num_pmus[gid] = hweight32(info.split.aux_data); + group_num_pmcs[gid] = info.split.num_pmcs; + uncore->num_pmus += group_num_pmus[gid]; + } + + uncore->pmus = kzalloc(sizeof(*uncore->pmus) * uncore->num_pmus, + GFP_KERNEL); + if (!uncore->pmus) { + uncore->num_pmus = 0; + goto done; + } + + for_each_set_bit(gid, gmask, UNCORE_GROUP_MAX) { + for (i = 0; i < group_num_pmus[gid]; i++) { + pmu = &uncore->pmus[index]; + snprintf(pmu->name, sizeof(pmu->name), "amd_umc_%d", index); + pmu->num_counters = group_num_pmcs[gid] / group_num_pmus[gid]; + pmu->msr_base = MSR_F19H_UMC_PERF_CTL + i * pmu->num_counters * 2; + pmu->rdpmc_base = -1; + pmu->group = gid; + + pmu->ctx = alloc_percpu(struct amd_uncore_ctx *); + if (!pmu->ctx) + goto done; + + pmu->pmu = (struct pmu) { + .task_ctx_nr = perf_invalid_context, + .attr_groups = amd_uncore_umc_attr_groups, + .name = pmu->name, + .event_init = amd_uncore_umc_event_init, + .add = amd_uncore_add, + .del = amd_uncore_del, + .start = amd_uncore_umc_start, + .stop = amd_uncore_stop, + .read = amd_uncore_read, + .capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT, + .module = THIS_MODULE, + }; + + if (perf_pmu_register(&pmu->pmu, pmu->pmu.name, -1)) { + free_percpu(pmu->ctx); + pmu->ctx = NULL; + goto done; + } + + pr_info("%d %s counters detected\n", pmu->num_counters, + pmu->pmu.name); + + index++; + } + } + +done: + uncore->num_pmus = index; + uncore->init_done = true; + + return amd_uncore_ctx_init(uncore, cpu); +} + +static struct amd_uncore uncores[UNCORE_TYPE_MAX] = { + /* UNCORE_TYPE_DF */ + { + .scan = amd_uncore_df_ctx_scan, + .init = amd_uncore_df_ctx_init, + .move = amd_uncore_ctx_move, + .free = amd_uncore_ctx_free, + }, + /* UNCORE_TYPE_L3 */ + { + .scan = amd_uncore_l3_ctx_scan, + .init = amd_uncore_l3_ctx_init, + .move = amd_uncore_ctx_move, + .free = amd_uncore_ctx_free, + }, + /* UNCORE_TYPE_UMC */ + { + .scan = amd_uncore_umc_ctx_scan, + .init = amd_uncore_umc_ctx_init, + .move = amd_uncore_ctx_move, + .free = amd_uncore_ctx_free, + }, +}; + +static int __init amd_uncore_init(void) +{ + struct amd_uncore *uncore; int ret = -ENODEV; + int i; if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) @@ -660,125 +1022,91 @@ static int __init amd_uncore_init(void) if (boot_cpu_has(X86_FEATURE_PERFMON_V2)) pmu_version = 2; - num_counters_nb = NUM_COUNTERS_NB; - num_counters_llc = NUM_COUNTERS_L2; - if (boot_cpu_data.x86 >= 0x17) { - /* - * For F17h and above, the Northbridge counters are - * repurposed as Data Fabric counters. Also, L3 - * counters are supported too. The PMUs are exported - * based on family as either L2 or L3 and NB or DF. - */ - num_counters_llc = NUM_COUNTERS_L3; - amd_nb_pmu.name = "amd_df"; - amd_llc_pmu.name = "amd_l3"; - l3_mask = true; - } + for (i = 0; i < UNCORE_TYPE_MAX; i++) { + uncore = &uncores[i]; - if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) { - if (pmu_version >= 2) { - *df_attr++ = &format_attr_event14v2.attr; - *df_attr++ = &format_attr_umask12.attr; - } else if (boot_cpu_data.x86 >= 0x17) { - *df_attr = &format_attr_event14.attr; - } + BUG_ON(!uncore->scan); + BUG_ON(!uncore->init); + BUG_ON(!uncore->move); + BUG_ON(!uncore->free); - amd_uncore_nb = alloc_percpu(struct amd_uncore *); - if (!amd_uncore_nb) { + uncore->info = alloc_percpu(union amd_uncore_info); + if (!uncore->info) { ret = -ENOMEM; - goto fail_nb; - } - ret = perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1); - if (ret) - goto fail_nb; - - if (pmu_version >= 2) { - ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES); - num_counters_nb = ebx.split.num_df_pmc; - } - - pr_info("%d %s %s counters detected\n", num_counters_nb, - boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ? "HYGON" : "", - amd_nb_pmu.name); - - ret = 0; - } - - if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) { - if (boot_cpu_data.x86 >= 0x19) { - *l3_attr++ = &format_attr_event8.attr; - *l3_attr++ = &format_attr_umask8.attr; - *l3_attr++ = &format_attr_threadmask2.attr; - } else if (boot_cpu_data.x86 >= 0x17) { - *l3_attr++ = &format_attr_event8.attr; - *l3_attr++ = &format_attr_umask8.attr; - *l3_attr++ = &format_attr_threadmask8.attr; - } - - amd_uncore_llc = alloc_percpu(struct amd_uncore *); - if (!amd_uncore_llc) { - ret = -ENOMEM; - goto fail_llc; + goto fail; } - ret = perf_pmu_register(&amd_llc_pmu, amd_llc_pmu.name, -1); - if (ret) - goto fail_llc; - - pr_info("%d %s %s counters detected\n", num_counters_llc, - boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ? "HYGON" : "", - amd_llc_pmu.name); - ret = 0; - } + }; /* * Install callbacks. Core will call them for each online cpu. */ - if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP, - "perf/x86/amd/uncore:prepare", - amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead)) - goto fail_llc; - - if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, - "perf/x86/amd/uncore:starting", - amd_uncore_cpu_starting, NULL)) + ret = cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP, + "perf/x86/amd/uncore:prepare", + NULL, amd_uncore_cpu_dead); + if (ret) + goto fail; + + ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING, + "perf/x86/amd/uncore:starting", + amd_uncore_cpu_starting, NULL); + if (ret) goto fail_prep; - if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE, - "perf/x86/amd/uncore:online", - amd_uncore_cpu_online, - amd_uncore_cpu_down_prepare)) + + ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE, + "perf/x86/amd/uncore:online", + amd_uncore_cpu_online, + amd_uncore_cpu_down_prepare); + if (ret) goto fail_start; + return 0; fail_start: cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING); fail_prep: cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP); -fail_llc: - if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) - perf_pmu_unregister(&amd_nb_pmu); - free_percpu(amd_uncore_llc); -fail_nb: - free_percpu(amd_uncore_nb); +fail: + for (i = 0; i < UNCORE_TYPE_MAX; i++) { + uncore = &uncores[i]; + if (uncore->info) { + free_percpu(uncore->info); + uncore->info = NULL; + } + } return ret; } static void __exit amd_uncore_exit(void) { + struct amd_uncore *uncore; + struct amd_uncore_pmu *pmu; + int i, j; + cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE); cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING); cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP); - if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) { - perf_pmu_unregister(&amd_llc_pmu); - free_percpu(amd_uncore_llc); - amd_uncore_llc = NULL; - } + for (i = 0; i < UNCORE_TYPE_MAX; i++) { + uncore = &uncores[i]; + if (!uncore->info) + continue; + + free_percpu(uncore->info); + uncore->info = NULL; + + for (j = 0; j < uncore->num_pmus; j++) { + pmu = &uncore->pmus[j]; + if (!pmu->ctx) + continue; + + perf_pmu_unregister(&pmu->pmu); + free_percpu(pmu->ctx); + pmu->ctx = NULL; + } - if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) { - perf_pmu_unregister(&amd_nb_pmu); - free_percpu(amd_uncore_nb); - amd_uncore_nb = NULL; + kfree(uncore->pmus); + uncore->pmus = NULL; } } diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 185f902e5f28..40ad1425ffa2 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1887,9 +1887,9 @@ ssize_t events_hybrid_sysfs_show(struct device *dev, str = pmu_attr->event_str; for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) { - if (!(x86_pmu.hybrid_pmu[i].cpu_type & pmu_attr->pmu_type)) + if (!(x86_pmu.hybrid_pmu[i].pmu_type & pmu_attr->pmu_type)) continue; - if (x86_pmu.hybrid_pmu[i].cpu_type & pmu->cpu_type) { + if (x86_pmu.hybrid_pmu[i].pmu_type & pmu->pmu_type) { next_str = strchr(str, ';'); if (next_str) return snprintf(page, next_str - str + 1, "%s", str); @@ -2169,7 +2169,7 @@ static int __init init_hw_perf_events(void) hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_EXTENDED_HW_TYPE; err = perf_pmu_register(&hybrid_pmu->pmu, hybrid_pmu->name, - (hybrid_pmu->cpu_type == hybrid_big) ? PERF_TYPE_RAW : -1); + (hybrid_pmu->pmu_type == hybrid_big) ? PERF_TYPE_RAW : -1); if (err) break; } diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index fa355d3658a6..a08f794a0e79 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -211,6 +211,14 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly = EVENT_CONSTRAINT_END }; +static struct event_constraint intel_grt_event_constraints[] __read_mostly = { + FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ + FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ + FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF_TSC_P */ + EVENT_CONSTRAINT_END +}; + static struct event_constraint intel_skl_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ @@ -299,7 +307,7 @@ static struct extra_reg intel_icl_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; -static struct extra_reg intel_spr_extra_regs[] __read_mostly = { +static struct extra_reg intel_glc_extra_regs[] __read_mostly = { INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), @@ -309,11 +317,12 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = { EVENT_EXTRA_END }; -static struct event_constraint intel_spr_event_constraints[] = { +static struct event_constraint intel_glc_event_constraints[] = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x0100, 0), /* INST_RETIRED.PREC_DIST */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF_TSC_P */ FIXED_EVENT_CONSTRAINT(0x0400, 3), /* SLOTS */ METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0), METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1), @@ -349,7 +358,7 @@ static struct event_constraint intel_spr_event_constraints[] = { EVENT_CONSTRAINT_END }; -static struct extra_reg intel_gnr_extra_regs[] __read_mostly = { +static struct extra_reg intel_rwc_extra_regs[] __read_mostly = { INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), @@ -473,7 +482,7 @@ static u64 intel_pmu_event_map(int hw_event) return intel_perfmon_event_map[hw_event]; } -static __initconst const u64 spr_hw_cache_event_ids +static __initconst const u64 glc_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -552,7 +561,7 @@ static __initconst const u64 spr_hw_cache_event_ids }, }; -static __initconst const u64 spr_hw_cache_extra_regs +static __initconst const u64 glc_hw_cache_extra_regs [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -2556,16 +2565,6 @@ static int icl_set_topdown_event_period(struct perf_event *event) return 0; } -static int adl_set_topdown_event_period(struct perf_event *event) -{ - struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); - - if (pmu->cpu_type != hybrid_big) - return 0; - - return icl_set_topdown_event_period(event); -} - DEFINE_STATIC_CALL(intel_pmu_set_topdown_event_period, x86_perf_event_set_period); static inline u64 icl_get_metrics_event_value(u64 metric, u64 slots, int idx) @@ -2708,16 +2707,6 @@ static u64 icl_update_topdown_event(struct perf_event *event) x86_pmu.num_topdown_events - 1); } -static u64 adl_update_topdown_event(struct perf_event *event) -{ - struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); - - if (pmu->cpu_type != hybrid_big) - return 0; - - return icl_update_topdown_event(event); -} - DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, x86_perf_event_update); static void intel_pmu_read_topdown_event(struct perf_event *event) @@ -3869,7 +3858,7 @@ static inline bool require_mem_loads_aux_event(struct perf_event *event) return false; if (is_hybrid()) - return hybrid_pmu(event->pmu)->cpu_type == hybrid_big; + return hybrid_pmu(event->pmu)->pmu_type == hybrid_big; return true; } @@ -4273,7 +4262,7 @@ icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx, } static struct event_constraint * -spr_get_event_constraints(struct cpu_hw_events *cpuc, int idx, +glc_get_event_constraints(struct cpu_hw_events *cpuc, int idx, struct perf_event *event) { struct event_constraint *c; @@ -4361,9 +4350,9 @@ adl_get_event_constraints(struct cpu_hw_events *cpuc, int idx, { struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); - if (pmu->cpu_type == hybrid_big) - return spr_get_event_constraints(cpuc, idx, event); - else if (pmu->cpu_type == hybrid_small) + if (pmu->pmu_type == hybrid_big) + return glc_get_event_constraints(cpuc, idx, event); + else if (pmu->pmu_type == hybrid_small) return tnt_get_event_constraints(cpuc, idx, event); WARN_ON(1); @@ -4409,7 +4398,7 @@ rwc_get_event_constraints(struct cpu_hw_events *cpuc, int idx, { struct event_constraint *c; - c = spr_get_event_constraints(cpuc, idx, event); + c = glc_get_event_constraints(cpuc, idx, event); /* The Retire Latency is not supported by the fixed counter 0. */ if (event->attr.precise_ip && @@ -4433,9 +4422,9 @@ mtl_get_event_constraints(struct cpu_hw_events *cpuc, int idx, { struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); - if (pmu->cpu_type == hybrid_big) + if (pmu->pmu_type == hybrid_big) return rwc_get_event_constraints(cpuc, idx, event); - if (pmu->cpu_type == hybrid_small) + if (pmu->pmu_type == hybrid_small) return cmt_get_event_constraints(cpuc, idx, event); WARN_ON(1); @@ -4446,18 +4435,18 @@ static int adl_hw_config(struct perf_event *event) { struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); - if (pmu->cpu_type == hybrid_big) + if (pmu->pmu_type == hybrid_big) return hsw_hw_config(event); - else if (pmu->cpu_type == hybrid_small) + else if (pmu->pmu_type == hybrid_small) return intel_pmu_hw_config(event); WARN_ON(1); return -EOPNOTSUPP; } -static u8 adl_get_hybrid_cpu_type(void) +static enum hybrid_cpu_type adl_get_hybrid_cpu_type(void) { - return hybrid_big; + return HYBRID_INTEL_CORE; } /* @@ -4490,7 +4479,7 @@ static void nhm_limit_period(struct perf_event *event, s64 *left) *left = max(*left, 32LL); } -static void spr_limit_period(struct perf_event *event, s64 *left) +static void glc_limit_period(struct perf_event *event, s64 *left) { if (event->attr.precise_ip == 3) *left = max(*left, 128LL); @@ -4618,6 +4607,23 @@ static void intel_pmu_check_num_counters(int *num_counters, int *num_counters_fixed, u64 *intel_ctrl, u64 fixed_mask); +static void intel_pmu_check_event_constraints(struct event_constraint *event_constraints, + int num_counters, + int num_counters_fixed, + u64 intel_ctrl); + +static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs); + +static inline bool intel_pmu_broken_perf_cap(void) +{ + /* The Perf Metric (Bit 15) is always cleared */ + if ((boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE) || + (boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE_L)) + return true; + + return false; +} + static void update_pmu_cap(struct x86_hybrid_pmu *pmu) { unsigned int sub_bitmaps = cpuid_eax(ARCH_PERFMON_EXT_LEAF); @@ -4628,27 +4634,83 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu) &eax, &ebx, &ecx, &edx); pmu->num_counters = fls(eax); pmu->num_counters_fixed = fls(ebx); - intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed, - &pmu->intel_ctrl, ebx); + } + + + if (!intel_pmu_broken_perf_cap()) { + /* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */ + rdmsrl(MSR_IA32_PERF_CAPABILITIES, pmu->intel_cap.capabilities); } } -static bool init_hybrid_pmu(int cpu) +static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu) +{ + intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed, + &pmu->intel_ctrl, (1ULL << pmu->num_counters_fixed) - 1); + pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters); + pmu->unconstrained = (struct event_constraint) + __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1, + 0, pmu->num_counters, 0, 0); + + if (pmu->intel_cap.perf_metrics) + pmu->intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS; + else + pmu->intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS); + + if (pmu->intel_cap.pebs_output_pt_available) + pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT; + else + pmu->pmu.capabilities |= ~PERF_PMU_CAP_AUX_OUTPUT; + + intel_pmu_check_event_constraints(pmu->event_constraints, + pmu->num_counters, + pmu->num_counters_fixed, + pmu->intel_ctrl); + + intel_pmu_check_extra_regs(pmu->extra_regs); +} + +static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void) { - struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); u8 cpu_type = get_this_hybrid_cpu_type(); - struct x86_hybrid_pmu *pmu = NULL; int i; - if (!cpu_type && x86_pmu.get_hybrid_cpu_type) - cpu_type = x86_pmu.get_hybrid_cpu_type(); + /* + * This is running on a CPU model that is known to have hybrid + * configurations. But the CPU told us it is not hybrid, shame + * on it. There should be a fixup function provided for these + * troublesome CPUs (->get_hybrid_cpu_type). + */ + if (cpu_type == HYBRID_INTEL_NONE) { + if (x86_pmu.get_hybrid_cpu_type) + cpu_type = x86_pmu.get_hybrid_cpu_type(); + else + return NULL; + } + /* + * This essentially just maps between the 'hybrid_cpu_type' + * and 'hybrid_pmu_type' enums: + */ for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) { - if (x86_pmu.hybrid_pmu[i].cpu_type == cpu_type) { - pmu = &x86_pmu.hybrid_pmu[i]; - break; - } + enum hybrid_pmu_type pmu_type = x86_pmu.hybrid_pmu[i].pmu_type; + + if (cpu_type == HYBRID_INTEL_CORE && + pmu_type == hybrid_big) + return &x86_pmu.hybrid_pmu[i]; + if (cpu_type == HYBRID_INTEL_ATOM && + pmu_type == hybrid_small) + return &x86_pmu.hybrid_pmu[i]; } + + return NULL; +} + +static bool init_hybrid_pmu(int cpu) +{ + struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu); + struct x86_hybrid_pmu *pmu = find_hybrid_pmu_for_cpu(); + if (WARN_ON_ONCE(!pmu || (pmu->pmu.type == -1))) { cpuc->pmu = NULL; return false; @@ -4661,6 +4723,8 @@ static bool init_hybrid_pmu(int cpu) if (this_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT)) update_pmu_cap(pmu); + intel_pmu_check_hybrid_pmus(pmu); + if (!check_hw_exists(&pmu->pmu, pmu->num_counters, pmu->num_counters_fixed)) return false; @@ -5337,14 +5401,14 @@ static struct attribute *icl_tsx_events_attrs[] = { EVENT_ATTR_STR(mem-stores, mem_st_spr, "event=0xcd,umask=0x2"); EVENT_ATTR_STR(mem-loads-aux, mem_ld_aux, "event=0x03,umask=0x82"); -static struct attribute *spr_events_attrs[] = { +static struct attribute *glc_events_attrs[] = { EVENT_PTR(mem_ld_hsw), EVENT_PTR(mem_st_spr), EVENT_PTR(mem_ld_aux), NULL, }; -static struct attribute *spr_td_events_attrs[] = { +static struct attribute *glc_td_events_attrs[] = { EVENT_PTR(slots), EVENT_PTR(td_retiring), EVENT_PTR(td_bad_spec), @@ -5357,7 +5421,7 @@ static struct attribute *spr_td_events_attrs[] = { NULL, }; -static struct attribute *spr_tsx_events_attrs[] = { +static struct attribute *glc_tsx_events_attrs[] = { EVENT_PTR(tx_start), EVENT_PTR(tx_abort), EVENT_PTR(tx_commit), @@ -5699,7 +5763,7 @@ static bool is_attr_for_this_pmu(struct kobject *kobj, struct attribute *attr) struct perf_pmu_events_hybrid_attr *pmu_attr = container_of(attr, struct perf_pmu_events_hybrid_attr, attr.attr); - return pmu->cpu_type & pmu_attr->pmu_type; + return pmu->pmu_type & pmu_attr->pmu_type; } static umode_t hybrid_events_is_visible(struct kobject *kobj, @@ -5736,7 +5800,7 @@ static umode_t hybrid_format_is_visible(struct kobject *kobj, container_of(attr, struct perf_pmu_format_hybrid_attr, attr.attr); int cpu = hybrid_find_supported_cpu(pmu); - return (cpu >= 0) && (pmu->cpu_type & pmu_attr->pmu_type) ? attr->mode : 0; + return (cpu >= 0) && (pmu->pmu_type & pmu_attr->pmu_type) ? attr->mode : 0; } static struct attribute_group hybrid_group_events_td = { @@ -5880,40 +5944,105 @@ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs) } } -static void intel_pmu_check_hybrid_pmus(u64 fixed_mask) +static const struct { enum hybrid_pmu_type id; char *name; } intel_hybrid_pmu_type_map[] __initconst = { + { hybrid_small, "cpu_atom" }, + { hybrid_big, "cpu_core" }, +}; + +static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus) { + unsigned long pmus_mask = pmus; struct x86_hybrid_pmu *pmu; - int i; + int idx = 0, bit; - for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) { - pmu = &x86_pmu.hybrid_pmu[i]; + x86_pmu.num_hybrid_pmus = hweight_long(pmus_mask); + x86_pmu.hybrid_pmu = kcalloc(x86_pmu.num_hybrid_pmus, + sizeof(struct x86_hybrid_pmu), + GFP_KERNEL); + if (!x86_pmu.hybrid_pmu) + return -ENOMEM; - intel_pmu_check_num_counters(&pmu->num_counters, - &pmu->num_counters_fixed, - &pmu->intel_ctrl, - fixed_mask); + static_branch_enable(&perf_is_hybrid); + x86_pmu.filter = intel_pmu_filter; - if (pmu->intel_cap.perf_metrics) { - pmu->intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS; - pmu->intel_ctrl |= INTEL_PMC_MSK_FIXED_SLOTS; + for_each_set_bit(bit, &pmus_mask, ARRAY_SIZE(intel_hybrid_pmu_type_map)) { + pmu = &x86_pmu.hybrid_pmu[idx++]; + pmu->pmu_type = intel_hybrid_pmu_type_map[bit].id; + pmu->name = intel_hybrid_pmu_type_map[bit].name; + + pmu->num_counters = x86_pmu.num_counters; + pmu->num_counters_fixed = x86_pmu.num_counters_fixed; + pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters); + pmu->unconstrained = (struct event_constraint) + __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1, + 0, pmu->num_counters, 0, 0); + + pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities; + if (pmu->pmu_type & hybrid_small) { + pmu->intel_cap.perf_metrics = 0; + pmu->intel_cap.pebs_output_pt_available = 1; + pmu->mid_ack = true; + } else if (pmu->pmu_type & hybrid_big) { + pmu->intel_cap.perf_metrics = 1; + pmu->intel_cap.pebs_output_pt_available = 0; + pmu->late_ack = true; } + } - if (pmu->intel_cap.pebs_output_pt_available) - pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT; + return 0; +} - intel_pmu_check_event_constraints(pmu->event_constraints, - pmu->num_counters, - pmu->num_counters_fixed, - pmu->intel_ctrl); +static __always_inline void intel_pmu_ref_cycles_ext(void) +{ + if (!(x86_pmu.events_maskl & (INTEL_PMC_MSK_FIXED_REF_CYCLES >> INTEL_PMC_IDX_FIXED))) + intel_perfmon_event_map[PERF_COUNT_HW_REF_CPU_CYCLES] = 0x013c; +} - intel_pmu_check_extra_regs(pmu->extra_regs); - } +static __always_inline void intel_pmu_init_glc(struct pmu *pmu) +{ + x86_pmu.late_ack = true; + x86_pmu.limit_period = glc_limit_period; + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.pebs_block = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_NO_HT_SHARING; + x86_pmu.flags |= PMU_FL_INSTR_LATENCY; + x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04); + x86_pmu.lbr_pt_coexist = true; + x86_pmu.num_topdown_events = 8; + static_call_update(intel_pmu_update_topdown_event, + &icl_update_topdown_event); + static_call_update(intel_pmu_set_topdown_event_period, + &icl_set_topdown_event_period); + + memcpy(hybrid_var(pmu, hw_cache_event_ids), glc_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hybrid_var(pmu, hw_cache_extra_regs), glc_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + hybrid(pmu, event_constraints) = intel_glc_event_constraints; + hybrid(pmu, pebs_constraints) = intel_glc_pebs_event_constraints; + + intel_pmu_ref_cycles_ext(); } -static __always_inline bool is_mtl(u8 x86_model) +static __always_inline void intel_pmu_init_grt(struct pmu *pmu) { - return (x86_model == INTEL_FAM6_METEORLAKE) || - (x86_model == INTEL_FAM6_METEORLAKE_L); + x86_pmu.mid_ack = true; + x86_pmu.limit_period = glc_limit_period; + x86_pmu.pebs_aliases = NULL; + x86_pmu.pebs_prec_dist = true; + x86_pmu.pebs_block = true; + x86_pmu.lbr_pt_coexist = true; + x86_pmu.flags |= PMU_FL_HAS_RSP_1; + x86_pmu.flags |= PMU_FL_INSTR_LATENCY; + + memcpy(hybrid_var(pmu, hw_cache_event_ids), glp_hw_cache_event_ids, sizeof(hw_cache_event_ids)); + memcpy(hybrid_var(pmu, hw_cache_extra_regs), tnt_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); + hybrid_var(pmu, hw_cache_event_ids)[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; + hybrid(pmu, event_constraints) = intel_grt_event_constraints; + hybrid(pmu, pebs_constraints) = intel_grt_pebs_event_constraints; + hybrid(pmu, extra_regs) = intel_grt_extra_regs; + + intel_pmu_ref_cycles_ext(); } __init int intel_pmu_init(void) @@ -6194,28 +6323,10 @@ __init int intel_pmu_init(void) break; case INTEL_FAM6_ATOM_GRACEMONT: - x86_pmu.mid_ack = true; - memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, - sizeof(hw_cache_event_ids)); - memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs, - sizeof(hw_cache_extra_regs)); - hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; - - x86_pmu.event_constraints = intel_slm_event_constraints; - x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints; - x86_pmu.extra_regs = intel_grt_extra_regs; - - x86_pmu.pebs_aliases = NULL; - x86_pmu.pebs_prec_dist = true; - x86_pmu.pebs_block = true; - x86_pmu.lbr_pt_coexist = true; - x86_pmu.flags |= PMU_FL_HAS_RSP_1; - x86_pmu.flags |= PMU_FL_INSTR_LATENCY; - + intel_pmu_init_grt(NULL); intel_pmu_pebs_data_source_grt(); x86_pmu.pebs_latency_data = adl_latency_data_small; x86_pmu.get_event_constraints = tnt_get_event_constraints; - x86_pmu.limit_period = spr_limit_period; td_attr = tnt_events_attrs; mem_attr = grt_mem_attrs; extra_attr = nhm_format_attr; @@ -6225,28 +6336,11 @@ __init int intel_pmu_init(void) case INTEL_FAM6_ATOM_CRESTMONT: case INTEL_FAM6_ATOM_CRESTMONT_X: - x86_pmu.mid_ack = true; - memcpy(hw_cache_event_ids, glp_hw_cache_event_ids, - sizeof(hw_cache_event_ids)); - memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs, - sizeof(hw_cache_extra_regs)); - hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; - - x86_pmu.event_constraints = intel_slm_event_constraints; - x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints; + intel_pmu_init_grt(NULL); x86_pmu.extra_regs = intel_cmt_extra_regs; - - x86_pmu.pebs_aliases = NULL; - x86_pmu.pebs_prec_dist = true; - x86_pmu.lbr_pt_coexist = true; - x86_pmu.pebs_block = true; - x86_pmu.flags |= PMU_FL_HAS_RSP_1; - x86_pmu.flags |= PMU_FL_INSTR_LATENCY; - intel_pmu_pebs_data_source_cmt(); x86_pmu.pebs_latency_data = mtl_latency_data_small; x86_pmu.get_event_constraints = cmt_get_event_constraints; - x86_pmu.limit_period = spr_limit_period; td_attr = cmt_events_attrs; mem_attr = grt_mem_attrs; extra_attr = cmt_format_attr; @@ -6563,44 +6657,23 @@ __init int intel_pmu_init(void) case INTEL_FAM6_SAPPHIRERAPIDS_X: case INTEL_FAM6_EMERALDRAPIDS_X: x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; - x86_pmu.extra_regs = intel_spr_extra_regs; + x86_pmu.extra_regs = intel_glc_extra_regs; fallthrough; case INTEL_FAM6_GRANITERAPIDS_X: case INTEL_FAM6_GRANITERAPIDS_D: - pmem = true; - x86_pmu.late_ack = true; - memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids)); - memcpy(hw_cache_extra_regs, spr_hw_cache_extra_regs, sizeof(hw_cache_extra_regs)); - - x86_pmu.event_constraints = intel_spr_event_constraints; - x86_pmu.pebs_constraints = intel_spr_pebs_event_constraints; + intel_pmu_init_glc(NULL); if (!x86_pmu.extra_regs) - x86_pmu.extra_regs = intel_gnr_extra_regs; - x86_pmu.limit_period = spr_limit_period; + x86_pmu.extra_regs = intel_rwc_extra_regs; x86_pmu.pebs_ept = 1; - x86_pmu.pebs_aliases = NULL; - x86_pmu.pebs_prec_dist = true; - x86_pmu.pebs_block = true; - x86_pmu.flags |= PMU_FL_HAS_RSP_1; - x86_pmu.flags |= PMU_FL_NO_HT_SHARING; - x86_pmu.flags |= PMU_FL_INSTR_LATENCY; - x86_pmu.hw_config = hsw_hw_config; - x86_pmu.get_event_constraints = spr_get_event_constraints; + x86_pmu.get_event_constraints = glc_get_event_constraints; extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? hsw_format_attr : nhm_format_attr; extra_skl_attr = skl_format_attr; - mem_attr = spr_events_attrs; - td_attr = spr_td_events_attrs; - tsx_attr = spr_tsx_events_attrs; - x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04); - x86_pmu.lbr_pt_coexist = true; - intel_pmu_pebs_data_source_skl(pmem); - x86_pmu.num_topdown_events = 8; - static_call_update(intel_pmu_update_topdown_event, - &icl_update_topdown_event); - static_call_update(intel_pmu_set_topdown_event_period, - &icl_set_topdown_event_period); + mem_attr = glc_events_attrs; + td_attr = glc_td_events_attrs; + tsx_attr = glc_tsx_events_attrs; + intel_pmu_pebs_data_source_skl(true); pr_cont("Sapphire Rapids events, "); name = "sapphire_rapids"; break; @@ -6610,47 +6683,17 @@ __init int intel_pmu_init(void) case INTEL_FAM6_RAPTORLAKE: case INTEL_FAM6_RAPTORLAKE_P: case INTEL_FAM6_RAPTORLAKE_S: - case INTEL_FAM6_METEORLAKE: - case INTEL_FAM6_METEORLAKE_L: /* * Alder Lake has 2 types of CPU, core and atom. * * Initialize the common PerfMon capabilities here. */ - x86_pmu.hybrid_pmu = kcalloc(X86_HYBRID_NUM_PMUS, - sizeof(struct x86_hybrid_pmu), - GFP_KERNEL); - if (!x86_pmu.hybrid_pmu) - return -ENOMEM; - static_branch_enable(&perf_is_hybrid); - x86_pmu.num_hybrid_pmus = X86_HYBRID_NUM_PMUS; + intel_pmu_init_hybrid(hybrid_big_small); - x86_pmu.pebs_aliases = NULL; - x86_pmu.pebs_prec_dist = true; - x86_pmu.pebs_block = true; - x86_pmu.flags |= PMU_FL_HAS_RSP_1; - x86_pmu.flags |= PMU_FL_NO_HT_SHARING; - x86_pmu.flags |= PMU_FL_INSTR_LATENCY; - x86_pmu.lbr_pt_coexist = true; x86_pmu.pebs_latency_data = adl_latency_data_small; - x86_pmu.num_topdown_events = 8; - static_call_update(intel_pmu_update_topdown_event, - &adl_update_topdown_event); - static_call_update(intel_pmu_set_topdown_event_period, - &adl_set_topdown_event_period); - - x86_pmu.filter = intel_pmu_filter; x86_pmu.get_event_constraints = adl_get_event_constraints; x86_pmu.hw_config = adl_hw_config; - x86_pmu.limit_period = spr_limit_period; x86_pmu.get_hybrid_cpu_type = adl_get_hybrid_cpu_type; - /* - * The rtm_abort_event is used to check whether to enable GPRs - * for the RTM abort event. Atom doesn't have the RTM abort - * event. There is no harmful to set it in the common - * x86_pmu.rtm_abort_event. - */ - x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04); td_attr = adl_hybrid_events_attrs; mem_attr = adl_hybrid_mem_attrs; @@ -6660,9 +6703,7 @@ __init int intel_pmu_init(void) /* Initialize big core specific PerfMon capabilities.*/ pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX]; - pmu->name = "cpu_core"; - pmu->cpu_type = hybrid_big; - pmu->late_ack = true; + intel_pmu_init_glc(&pmu->pmu); if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) { pmu->num_counters = x86_pmu.num_counters + 2; pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1; @@ -6687,54 +6728,45 @@ __init int intel_pmu_init(void) pmu->unconstrained = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1, 0, pmu->num_counters, 0, 0); - pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities; - pmu->intel_cap.perf_metrics = 1; - pmu->intel_cap.pebs_output_pt_available = 0; + pmu->extra_regs = intel_glc_extra_regs; + + /* Initialize Atom core specific PerfMon capabilities.*/ + pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX]; + intel_pmu_init_grt(&pmu->pmu); + + x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; + intel_pmu_pebs_data_source_adl(); + pr_cont("Alderlake Hybrid events, "); + name = "alderlake_hybrid"; + break; + + case INTEL_FAM6_METEORLAKE: + case INTEL_FAM6_METEORLAKE_L: + intel_pmu_init_hybrid(hybrid_big_small); - memcpy(pmu->hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(pmu->hw_cache_event_ids)); - memcpy(pmu->hw_cache_extra_regs, spr_hw_cache_extra_regs, sizeof(pmu->hw_cache_extra_regs)); - pmu->event_constraints = intel_spr_event_constraints; - pmu->pebs_constraints = intel_spr_pebs_event_constraints; - pmu->extra_regs = intel_spr_extra_regs; + x86_pmu.pebs_latency_data = mtl_latency_data_small; + x86_pmu.get_event_constraints = mtl_get_event_constraints; + x86_pmu.hw_config = adl_hw_config; + + td_attr = adl_hybrid_events_attrs; + mem_attr = mtl_hybrid_mem_attrs; + tsx_attr = adl_hybrid_tsx_attrs; + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr; + + /* Initialize big core specific PerfMon capabilities.*/ + pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX]; + intel_pmu_init_glc(&pmu->pmu); + pmu->extra_regs = intel_rwc_extra_regs; /* Initialize Atom core specific PerfMon capabilities.*/ pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX]; - pmu->name = "cpu_atom"; - pmu->cpu_type = hybrid_small; - pmu->mid_ack = true; - pmu->num_counters = x86_pmu.num_counters; - pmu->num_counters_fixed = x86_pmu.num_counters_fixed; - pmu->max_pebs_events = x86_pmu.max_pebs_events; - pmu->unconstrained = (struct event_constraint) - __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1, - 0, pmu->num_counters, 0, 0); - pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities; - pmu->intel_cap.perf_metrics = 0; - pmu->intel_cap.pebs_output_pt_available = 1; - - memcpy(pmu->hw_cache_event_ids, glp_hw_cache_event_ids, sizeof(pmu->hw_cache_event_ids)); - memcpy(pmu->hw_cache_extra_regs, tnt_hw_cache_extra_regs, sizeof(pmu->hw_cache_extra_regs)); - pmu->hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1; - pmu->event_constraints = intel_slm_event_constraints; - pmu->pebs_constraints = intel_grt_pebs_event_constraints; - pmu->extra_regs = intel_grt_extra_regs; - if (is_mtl(boot_cpu_data.x86_model)) { - x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].extra_regs = intel_gnr_extra_regs; - x86_pmu.pebs_latency_data = mtl_latency_data_small; - extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? - mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr; - mem_attr = mtl_hybrid_mem_attrs; - intel_pmu_pebs_data_source_mtl(); - x86_pmu.get_event_constraints = mtl_get_event_constraints; - pmu->extra_regs = intel_cmt_extra_regs; - pr_cont("Meteorlake Hybrid events, "); - name = "meteorlake_hybrid"; - } else { - x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX; - intel_pmu_pebs_data_source_adl(); - pr_cont("Alderlake Hybrid events, "); - name = "alderlake_hybrid"; - } + intel_pmu_init_grt(&pmu->pmu); + pmu->extra_regs = intel_cmt_extra_regs; + + intel_pmu_pebs_data_source_mtl(); + pr_cont("Meteorlake Hybrid events, "); + name = "meteorlake_hybrid"; break; default: @@ -6846,9 +6878,6 @@ __init int intel_pmu_init(void) if (!is_hybrid() && x86_pmu.intel_cap.perf_metrics) x86_pmu.intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS; - if (is_hybrid()) - intel_pmu_check_hybrid_pmus((u64)fixed_mask); - if (x86_pmu.intel_cap.pebs_timing_info) x86_pmu.flags |= PMU_FL_RETIRE_LATENCY; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 96fffb2d521d..cbeb6d2bf5b4 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -336,6 +336,9 @@ static int cstate_pmu_event_init(struct perf_event *event) cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX); if (!(pkg_msr_mask & (1 << cfg))) return -EINVAL; + + event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG; + event->hw.event_base = pkg_msr[cfg].msr; cpu = cpumask_any_and(&cstate_pkg_cpu_mask, topology_die_cpumask(event->cpu)); diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index eb8dd8b8a1e8..bf97ab904d40 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -261,7 +261,7 @@ static u64 __adl_latency_data_small(struct perf_event *event, u64 status, { u64 val; - WARN_ON_ONCE(hybrid_pmu(event->pmu)->cpu_type == hybrid_big); + WARN_ON_ONCE(hybrid_pmu(event->pmu)->pmu_type == hybrid_big); dse &= PERF_PEBS_DATA_SOURCE_MASK; val = hybrid_var(event->pmu, pebs_data_source)[dse]; @@ -1058,7 +1058,7 @@ struct event_constraint intel_icl_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -struct event_constraint intel_spr_pebs_event_constraints[] = { +struct event_constraint intel_glc_pebs_event_constraints[] = { INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 42a55794004a..8e2a12235e62 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -736,6 +736,7 @@ static bool topa_table_full(struct topa *topa) /** * topa_insert_pages() - create a list of ToPA tables * @buf: PT buffer being initialized. + * @cpu: CPU on which to allocate. * @gfp: Allocation flags. * * This initializes a list of ToPA tables with entries from @@ -1207,8 +1208,11 @@ static void pt_buffer_fini_topa(struct pt_buffer *buf) /** * pt_buffer_init_topa() - initialize ToPA table for pt buffer * @buf: PT buffer. - * @size: Total size of all regions within this ToPA. + * @cpu: CPU on which to allocate. + * @nr_pages: No. of pages to allocate. * @gfp: Allocation flags. + * + * Return: 0 on success or error code. */ static int pt_buffer_init_topa(struct pt_buffer *buf, int cpu, unsigned long nr_pages, gfp_t gfp) @@ -1281,7 +1285,7 @@ out: /** * pt_buffer_setup_aux() - set up topa tables for a PT buffer - * @cpu: Cpu on which to allocate, -1 means current. + * @event: Performance event * @pages: Array of pointers to buffer pages passed from perf core. * @nr_pages: Number of pages in the buffer. * @snapshot: If this is a snapshot/overwrite counter. diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 69043e02e8a7..01023aa5125b 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -74,7 +74,7 @@ int uncore_device_to_die(struct pci_dev *dev) struct cpuinfo_x86 *c = &cpu_data(cpu); if (c->initialized && cpu_to_node(cpu) == node) - return c->logical_die_id; + return c->topo.logical_die_id; } return -1; diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index c8ba2be7585d..53dd5d495ba6 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -652,10 +652,29 @@ enum { #define PERF_PEBS_DATA_SOURCE_MAX 0x10 #define PERF_PEBS_DATA_SOURCE_MASK (PERF_PEBS_DATA_SOURCE_MAX - 1) +enum hybrid_cpu_type { + HYBRID_INTEL_NONE, + HYBRID_INTEL_ATOM = 0x20, + HYBRID_INTEL_CORE = 0x40, +}; + +enum hybrid_pmu_type { + not_hybrid, + hybrid_small = BIT(0), + hybrid_big = BIT(1), + + hybrid_big_small = hybrid_big | hybrid_small, /* only used for matching */ +}; + +#define X86_HYBRID_PMU_ATOM_IDX 0 +#define X86_HYBRID_PMU_CORE_IDX 1 + +#define X86_HYBRID_NUM_PMUS 2 + struct x86_hybrid_pmu { struct pmu pmu; const char *name; - u8 cpu_type; + enum hybrid_pmu_type pmu_type; cpumask_t supported_cpus; union perf_capabilities intel_cap; u64 intel_ctrl; @@ -721,18 +740,6 @@ extern struct static_key_false perf_is_hybrid; __Fp; \ }) -enum hybrid_pmu_type { - hybrid_big = 0x40, - hybrid_small = 0x20, - - hybrid_big_small = hybrid_big | hybrid_small, -}; - -#define X86_HYBRID_PMU_ATOM_IDX 0 -#define X86_HYBRID_PMU_CORE_IDX 1 - -#define X86_HYBRID_NUM_PMUS 2 - /* * struct x86_pmu - generic x86 pmu */ @@ -940,7 +947,7 @@ struct x86_pmu { */ int num_hybrid_pmus; struct x86_hybrid_pmu *hybrid_pmu; - u8 (*get_hybrid_cpu_type) (void); + enum hybrid_cpu_type (*get_hybrid_cpu_type) (void); }; struct x86_perf_task_context_opt { @@ -1521,7 +1528,7 @@ extern struct event_constraint intel_skl_pebs_event_constraints[]; extern struct event_constraint intel_icl_pebs_event_constraints[]; -extern struct event_constraint intel_spr_pebs_event_constraints[]; +extern struct event_constraint intel_glc_pebs_event_constraints[]; struct event_constraint *intel_pebs_constraints(struct perf_event *event); diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c index 1579429846cc..8d98d468b976 100644 --- a/arch/x86/events/rapl.c +++ b/arch/x86/events/rapl.c @@ -115,7 +115,7 @@ struct rapl_pmu { struct rapl_pmus { struct pmu pmu; unsigned int maxdie; - struct rapl_pmu *pmus[]; + struct rapl_pmu *pmus[] __counted_by(maxdie); }; enum rapl_unit_quirk { @@ -179,15 +179,11 @@ static u64 rapl_event_update(struct perf_event *event) s64 delta, sdelta; int shift = RAPL_CNTR_WIDTH; -again: prev_raw_count = local64_read(&hwc->prev_count); - rdmsrl(event->hw.event_base, new_raw_count); - - if (local64_cmpxchg(&hwc->prev_count, prev_raw_count, - new_raw_count) != prev_raw_count) { - cpu_relax(); - goto again; - } + do { + rdmsrl(event->hw.event_base, new_raw_count); + } while (!local64_try_cmpxchg(&hwc->prev_count, + &prev_raw_count, new_raw_count)); /* * Now we have the new raw value and have updated the prev @@ -537,11 +533,11 @@ static struct perf_msr intel_rapl_spr_msrs[] = { * - want to use same event codes across both architectures */ static struct perf_msr amd_rapl_msrs[] = { - [PERF_RAPL_PP0] = { 0, &rapl_events_cores_group, 0, false, 0 }, + [PERF_RAPL_PP0] = { 0, &rapl_events_cores_group, NULL, false, 0 }, [PERF_RAPL_PKG] = { MSR_AMD_PKG_ENERGY_STATUS, &rapl_events_pkg_group, test_msr, false, RAPL_MSR_MASK }, - [PERF_RAPL_RAM] = { 0, &rapl_events_ram_group, 0, false, 0 }, - [PERF_RAPL_PP1] = { 0, &rapl_events_gpu_group, 0, false, 0 }, - [PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group, 0, false, 0 }, + [PERF_RAPL_RAM] = { 0, &rapl_events_ram_group, NULL, false, 0 }, + [PERF_RAPL_PP1] = { 0, &rapl_events_gpu_group, NULL, false, 0 }, + [PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group, NULL, false, 0 }, }; static int rapl_cpu_offline(unsigned int cpu) diff --git a/arch/x86/events/utils.c b/arch/x86/events/utils.c index 76b1f8bb0fd5..dab4ed199227 100644 --- a/arch/x86/events/utils.c +++ b/arch/x86/events/utils.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <asm/insn.h> +#include <linux/mm.h> #include "perf_event.h" @@ -132,9 +133,9 @@ static int get_branch_type(unsigned long from, unsigned long to, int abort, * The LBR logs any address in the IP, even if the IP just * faulted. This means userspace can control the from address. * Ensure we don't blindly read any address by validating it is - * a known text address. + * a known text address and not a vsyscall address. */ - if (kernel_text_address(from)) { + if (kernel_text_address(from) && !in_gate_area_no_mm(from)) { addr = (void *)from; /* * Assume we can get the maximum possible size diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c index 783ed339f341..21556ad87f4b 100644 --- a/arch/x86/hyperv/hv_init.c +++ b/arch/x86/hyperv/hv_init.c @@ -7,6 +7,8 @@ * Author : K. Y. Srinivasan <kys@microsoft.com> */ +#define pr_fmt(fmt) "Hyper-V: " fmt + #include <linux/efi.h> #include <linux/types.h> #include <linux/bitfield.h> @@ -191,7 +193,7 @@ void set_hv_tscchange_cb(void (*cb)(void)) struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1}; if (!hv_reenlightenment_available()) { - pr_warn("Hyper-V: reenlightenment support is unavailable\n"); + pr_warn("reenlightenment support is unavailable\n"); return; } @@ -394,6 +396,7 @@ static void __init hv_get_partition_id(void) local_irq_restore(flags); } +#if IS_ENABLED(CONFIG_HYPERV_VTL_MODE) static u8 __init get_vtl(void) { u64 control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_REGISTERS; @@ -416,13 +419,16 @@ static u8 __init get_vtl(void) if (hv_result_success(ret)) { ret = output->as64.low & HV_X64_VTL_MASK; } else { - pr_err("Failed to get VTL(%lld) and set VTL to zero by default.\n", ret); - ret = 0; + pr_err("Failed to get VTL(error: %lld) exiting...\n", ret); + BUG(); } local_irq_restore(flags); return ret; } +#else +static inline u8 get_vtl(void) { return 0; } +#endif /* * This function is to be invoked early in the boot sequence after the @@ -564,7 +570,7 @@ skip_hypercall_pg_init: if (cpu_feature_enabled(X86_FEATURE_IBT) && *(u32 *)hv_hypercall_pg != gen_endbr()) { setup_clear_cpu_cap(X86_FEATURE_IBT); - pr_warn("Hyper-V: Disabling IBT because of Hyper-V bug\n"); + pr_warn("Disabling IBT because of Hyper-V bug\n"); } #endif @@ -604,8 +610,10 @@ skip_hypercall_pg_init: hv_query_ext_cap(0); /* Find the VTL */ - if (!ms_hyperv.paravisor_present && hv_isolation_type_snp()) - ms_hyperv.vtl = get_vtl(); + ms_hyperv.vtl = get_vtl(); + + if (ms_hyperv.vtl > 0) /* non default VTL */ + hv_vtl_early_init(); return; diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c index 36a562218010..96e6c51515f5 100644 --- a/arch/x86/hyperv/hv_vtl.c +++ b/arch/x86/hyperv/hv_vtl.c @@ -196,7 +196,7 @@ static int hv_vtl_apicid_to_vp_id(u32 apic_id) return ret; } -static int hv_vtl_wakeup_secondary_cpu(int apicid, unsigned long start_eip) +static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { int vp_id; @@ -215,7 +215,7 @@ static int hv_vtl_wakeup_secondary_cpu(int apicid, unsigned long start_eip) return hv_vtl_bringup_vcpu(vp_id, start_eip); } -static int __init hv_vtl_early_init(void) +int __init hv_vtl_early_init(void) { /* * `boot_cpu_has` returns the runtime feature support, @@ -230,4 +230,3 @@ static int __init hv_vtl_early_init(void) return 0; } -early_initcall(hv_vtl_early_init); diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 8c6bf07f7d2b..02e55237d919 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -288,7 +288,7 @@ static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa) free_page((unsigned long)vmsa); } -int hv_snp_boot_ap(int cpu, unsigned long start_ip) +int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) { struct sev_es_save_area *vmsa = (struct sev_es_save_area *) __get_free_page(GFP_KERNEL | __GFP_ZERO); @@ -384,7 +384,7 @@ static inline void hv_ghcb_msr_read(u64 msr, u64 *value) {} #ifdef CONFIG_INTEL_TDX_GUEST static void hv_tdx_msr_write(u64 msr, u64 val) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, .r11 = EXIT_REASON_MSR_WRITE, .r12 = msr, @@ -398,13 +398,13 @@ static void hv_tdx_msr_write(u64 msr, u64 val) static void hv_tdx_msr_read(u64 msr, u64 *val) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, .r11 = EXIT_REASON_MSR_READ, .r12 = msr, }; - u64 ret = __tdx_hypercall_ret(&args); + u64 ret = __tdx_hypercall(&args); if (WARN_ONCE(ret, "Failed to emulate MSR read: %lld\n", ret)) *val = 0; @@ -414,13 +414,13 @@ static void hv_tdx_msr_read(u64 msr, u64 *val) u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2) { - struct tdx_hypercall_args args = { }; + struct tdx_module_args args = { }; args.r10 = control; args.rdx = param1; args.r8 = param2; - (void)__tdx_hypercall_ret(&args); + (void)__tdx_hypercall(&args); return args.r11; } diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild index 4f1ce5fc4e19..a192bdea69e2 100644 --- a/arch/x86/include/asm/Kbuild +++ b/arch/x86/include/asm/Kbuild @@ -10,5 +10,4 @@ generated-y += unistd_64_x32.h generated-y += xen-hypercalls.h generic-y += early_ioremap.h -generic-y += export.h generic-y += mcs_spinlock.h diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 9c4da699e11a..65f79092c9d9 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -58,7 +58,7 @@ #define ANNOTATE_IGNORE_ALTERNATIVE \ "999:\n\t" \ ".pushsection .discard.ignore_alts\n\t" \ - ".long 999b - .\n\t" \ + ".long 999b\n\t" \ ".popsection\n\t" /* @@ -352,7 +352,7 @@ static inline int alternatives_text_reserved(void *start, void *end) .macro ANNOTATE_IGNORE_ALTERNATIVE .Lannotate_\@: .pushsection .discard.ignore_alts - .long .Lannotate_\@ - . + .long .Lannotate_\@ .popsection .endm diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 5af4ec1a0f71..d21f48f1c242 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -54,7 +54,7 @@ extern int local_apic_timer_c2_ok; extern bool apic_is_disabled; extern unsigned int lapic_timer_period; -extern int cpuid_to_apicid[]; +extern u32 cpuid_to_apicid[]; extern enum apic_intr_mode_id apic_intr_mode; enum apic_intr_mode_id { @@ -276,7 +276,8 @@ struct apic { u32 disable_esr : 1, dest_mode_logical : 1, - x2apic_set_max_apicid : 1; + x2apic_set_max_apicid : 1, + nmi_to_offline_cpu : 1; u32 (*calc_dest_apicid)(unsigned int cpu); @@ -292,19 +293,19 @@ struct apic { 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, int apicid); + 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); - int (*cpu_present_to_apicid)(int mps_cpu); - int (*phys_pkg_id)(int cpuid_apic, int index_msb); + u32 (*cpu_present_to_apicid)(int mps_cpu); + u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb); - u32 (*get_apic_id)(unsigned long x); - u32 (*set_apic_id)(unsigned int id); + u32 (*get_apic_id)(u32 id); + u32 (*set_apic_id)(u32 apicid); /* wakeup_secondary_cpu */ - int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); + int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip); /* wakeup secondary CPU using 64-bit wakeup point */ - int (*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip); + int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip); char *name; }; @@ -322,8 +323,8 @@ struct apic_override { void (*send_IPI_self)(int vector); u64 (*icr_read)(void); void (*icr_write)(u32 low, u32 high); - int (*wakeup_secondary_cpu)(int apicid, unsigned long start_eip); - int (*wakeup_secondary_cpu_64)(int apicid, unsigned long start_eip); + int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip); + int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip); }; /* @@ -493,16 +494,6 @@ static inline bool lapic_vector_set_in_irr(unsigned int vector) return !!(irr & (1U << (vector % 32))); } -static inline unsigned default_get_apic_id(unsigned long x) -{ - unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR)); - - if (APIC_XAPIC(ver) || boot_cpu_has(X86_FEATURE_EXTD_APICID)) - return (x >> 24) & 0xFF; - else - return (x >> 24) & 0x0F; -} - /* * Warm reset vector position: */ @@ -517,9 +508,9 @@ extern void generic_bigsmp_probe(void); extern struct apic apic_noop; -static inline unsigned int read_apic_id(void) +static inline u32 read_apic_id(void) { - unsigned int reg = apic_read(APIC_ID); + u32 reg = apic_read(APIC_ID); return apic->get_apic_id(reg); } @@ -538,13 +529,14 @@ 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 bool default_check_apicid_used(physid_mask_t *map, int apicid); extern void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap); -extern int default_cpu_present_to_apicid(int mps_cpu); +extern u32 default_cpu_present_to_apicid(int mps_cpu); + +void apic_send_nmi_to_offline_cpu(unsigned int cpu); #else /* CONFIG_X86_LOCAL_APIC */ -static inline unsigned int read_apic_id(void) { return 0; } +static inline u32 read_apic_id(void) { return 0; } #endif /* !CONFIG_X86_LOCAL_APIC */ diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 2edf68475fec..990eb686ca67 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -94,18 +94,17 @@ arch___clear_bit(unsigned long nr, volatile unsigned long *addr) asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } -static __always_inline bool -arch_clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) +static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask, + volatile unsigned long *addr) { bool negative; - asm volatile(LOCK_PREFIX "andb %2,%1" + asm volatile(LOCK_PREFIX "xorb %2,%1" CC_SET(s) : CC_OUT(s) (negative), WBYTE_ADDR(addr) - : "ir" ((char) ~(1 << nr)) : "memory"); + : "iq" ((char)mask) : "memory"); return negative; } -#define arch_clear_bit_unlock_is_negative_byte \ - arch_clear_bit_unlock_is_negative_byte +#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte static __always_inline void arch___clear_bit_unlock(long nr, volatile unsigned long *addr) @@ -293,6 +292,9 @@ static __always_inline unsigned long variable_ffz(unsigned long word) */ static __always_inline unsigned long __fls(unsigned long word) { + if (__builtin_constant_p(word)) + return BITS_PER_LONG - 1 - __builtin_clzl(word); + asm("bsr %1,%0" : "=r" (word) : "rm" (word)); @@ -360,6 +362,9 @@ static __always_inline int fls(unsigned int x) { int r; + if (__builtin_constant_p(x)) + return x ? 32 - __builtin_clz(x) : 0; + #ifdef CONFIG_X86_64 /* * AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the @@ -401,6 +406,9 @@ static __always_inline int fls(unsigned int x) static __always_inline int fls64(__u64 x) { int bitpos = -1; + + if (__builtin_constant_p(x)) + return x ? 64 - __builtin_clzll(x) : 0; /* * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the * dest reg is undefined if x==0, but their CPU architect says its diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index b3a7cfb0d99e..a38cc0afc90a 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -85,6 +85,8 @@ extern const unsigned long kernel_total_size; unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, void (*error)(char *x)); + +extern struct boot_params *boot_params_ptr; #endif #endif /* _ASM_X86_BOOT_H */ diff --git a/arch/x86/include/asm/cacheinfo.h b/arch/x86/include/asm/cacheinfo.h index ce9685fc78d8..5aa061199866 100644 --- a/arch/x86/include/asm/cacheinfo.h +++ b/arch/x86/include/asm/cacheinfo.h @@ -7,9 +7,6 @@ extern unsigned int memory_caching_control; #define CACHE_MTRR 0x01 #define CACHE_PAT 0x02 -void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu); -void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu); - void cache_disable(void); void cache_enable(void); void set_cache_aps_delayed_init(bool val); diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h index d53636506134..5612648b0202 100644 --- a/arch/x86/include/asm/cmpxchg.h +++ b/arch/x86/include/asm/cmpxchg.h @@ -221,12 +221,18 @@ extern void __add_wrong_size(void) #define __try_cmpxchg(ptr, pold, new, size) \ __raw_try_cmpxchg((ptr), (pold), (new), (size), LOCK_PREFIX) +#define __sync_try_cmpxchg(ptr, pold, new, size) \ + __raw_try_cmpxchg((ptr), (pold), (new), (size), "lock; ") + #define __try_cmpxchg_local(ptr, pold, new, size) \ __raw_try_cmpxchg((ptr), (pold), (new), (size), "") #define arch_try_cmpxchg(ptr, pold, new) \ __try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr))) +#define arch_sync_try_cmpxchg(ptr, pold, new) \ + __sync_try_cmpxchg((ptr), (pold), (new), sizeof(*(ptr))) + #define arch_try_cmpxchg_local(ptr, pold, new) \ __try_cmpxchg_local((ptr), (pold), (new), sizeof(*(ptr))) diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 3a233ebff712..fecc4fe1d68a 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -28,8 +28,6 @@ struct x86_cpu { }; #ifdef CONFIG_HOTPLUG_CPU -extern int arch_register_cpu(int num); -extern void arch_unregister_cpu(int); extern void soft_restart_cpu(void); #endif @@ -73,26 +71,12 @@ static inline void init_ia32_feat_ctl(struct cpuinfo_x86 *c) {} extern __noendbr void cet_disable(void); -struct ucode_cpu_info; +struct cpu_signature; -int intel_cpu_collect_info(struct ucode_cpu_info *uci); - -static inline bool intel_cpu_signatures_match(unsigned int s1, unsigned int p1, - unsigned int s2, unsigned int p2) -{ - if (s1 != s2) - return false; - - /* Processor flags are either both 0 ... */ - if (!p1 && !p2) - return true; - - /* ... or they intersect. */ - return p1 & p2; -} +void intel_collect_cpu_info(struct cpu_signature *sig); extern u64 x86_read_arch_cap_msr(void); -int intel_find_matching_signature(void *mc, unsigned int csig, int cpf); +bool intel_find_matching_signature(void *mc, struct cpu_signature *sig); int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type); extern struct cpumask cpus_stop_mask; diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 58cb9495e40f..4af140cf5719 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -443,6 +443,7 @@ /* AMD-defined Extended Feature 2 EAX, CPUID level 0x80000021 (EAX), word 20 */ #define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* "" No Nested Data Breakpoints */ +#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* "" WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */ #define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* "" LFENCE always serializing / synchronizes RDTSC */ #define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* "" Null Selector Clears Base */ #define X86_FEATURE_AUTOIBRS (20*32+ 8) /* "" Automatic IBRS */ diff --git a/arch/x86/include/asm/crash_core.h b/arch/x86/include/asm/crash_core.h new file mode 100644 index 000000000000..76af98f4e801 --- /dev/null +++ b/arch/x86/include/asm/crash_core.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_CRASH_CORE_H +#define _X86_CRASH_CORE_H + +/* 16M alignment for crash kernel regions */ +#define CRASH_ALIGN SZ_16M + +/* + * Keep the crash kernel below this limit. + * + * Earlier 32-bits kernels would limit the kernel to the low 512 MB range + * due to mapping restrictions. + * + * 64-bit kdump kernels need to be restricted to be under 64 TB, which is + * the upper limit of system RAM in 4-level paging mode. Since the kdump + * jump could be from 5-level paging to 4-level paging, the jump will fail if + * the kernel is put above 64 TB, and during the 1st kernel bootup there's + * no good way to detect the paging mode of the target kernel which will be + * loaded for dumping. + */ +extern unsigned long swiotlb_size_or_default(void); + +#ifdef CONFIG_X86_32 +# define CRASH_ADDR_LOW_MAX SZ_512M +# define CRASH_ADDR_HIGH_MAX SZ_512M +#else +# define CRASH_ADDR_LOW_MAX SZ_4G +# define CRASH_ADDR_HIGH_MAX SZ_64T +#endif + +# define DEFAULT_CRASH_KERNEL_LOW_SIZE crash_low_size_default() + +static inline unsigned long crash_low_size_default(void) +{ +#ifdef CONFIG_X86_64 + return max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20); +#else + return 0; +#endif +} + +#endif /* _X86_CRASH_CORE_H */ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index 18fd06f7936a..a0234dfd1031 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -7,6 +7,7 @@ */ #include <linux/thread_info.h> +#include <asm/ia32.h> #include <asm/ptrace.h> #include <asm/user.h> #include <asm/auxvec.h> @@ -149,7 +150,7 @@ do { \ ((x)->e_machine == EM_X86_64) #define compat_elf_check_arch(x) \ - (elf_check_arch_ia32(x) || \ + ((elf_check_arch_ia32(x) && ia32_enabled()) || \ (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) static inline void elf_common_init(struct thread_struct *t, diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h index 23873da8fb77..c3b9582de7ef 100644 --- a/arch/x86/include/asm/fb.h +++ b/arch/x86/include/asm/fb.h @@ -2,12 +2,14 @@ #ifndef _ASM_X86_FB_H #define _ASM_X86_FB_H +#include <asm/page.h> + struct fb_info; -struct file; -struct vm_area_struct; -void fb_pgprotect(struct file *file, struct vm_area_struct *vma, unsigned long off); -#define fb_pgprotect fb_pgprotect +pgprot_t pgprot_framebuffer(pgprot_t prot, + unsigned long vm_start, unsigned long vm_end, + unsigned long offset); +#define pgprot_framebuffer pgprot_framebuffer int fb_is_primary_device(struct fb_info *info); #define fb_is_primary_device fb_is_primary_device diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 31089b851c4f..a2be3aefff9f 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -157,7 +157,8 @@ static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { static inline void fpu_sync_guest_vmexit_xfd_state(void) { } #endif -extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u32 pkru); +extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, + unsigned int size, u64 xfeatures, u32 pkru); extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru); static inline void fpstate_set_confidential(struct fpu_guest *gfpu) diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index 551829884734..b02c3cd3c0f6 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -28,7 +28,7 @@ #include <asm/irq.h> #include <asm/sections.h> -#ifdef CONFIG_X86_LOCAL_APIC +#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY struct irq_data; struct pci_dev; struct msi_desc; @@ -105,10 +105,10 @@ static inline void irq_complete_move(struct irq_cfg *c) { } #endif extern void apic_ack_edge(struct irq_data *data); -#else /* CONFIG_X86_LOCAL_APIC */ +#else /* CONFIG_IRQ_DOMAIN_HIERARCHY */ static inline void lock_vector_lock(void) {} static inline void unlock_vector_lock(void) {} -#endif /* CONFIG_X86_LOCAL_APIC */ +#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ /* Statistics */ extern atomic_t irq_err_count; diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h index 637fa1df3512..c715097e92fd 100644 --- a/arch/x86/include/asm/i8259.h +++ b/arch/x86/include/asm/i8259.h @@ -69,6 +69,8 @@ struct legacy_pic { void (*make_irq)(unsigned int irq); }; +void legacy_pic_pcat_compat(void); + extern struct legacy_pic *legacy_pic; extern struct legacy_pic null_legacy_pic; diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index fada857f0a1e..5a2ae24b1204 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -68,6 +68,20 @@ extern void ia32_pick_mmap_layout(struct mm_struct *mm); #endif -#endif /* CONFIG_IA32_EMULATION */ +extern bool __ia32_enabled; + +static inline bool ia32_enabled(void) +{ + return __ia32_enabled; +} + +#else /* !CONFIG_IA32_EMULATION */ + +static inline bool ia32_enabled(void) +{ + return IS_ENABLED(CONFIG_X86_32); +} + +#endif #endif /* _ASM_X86_IA32_H */ diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h index 5f1d3c421f68..cc9ccf61b6bd 100644 --- a/arch/x86/include/asm/init.h +++ b/arch/x86/include/asm/init.h @@ -2,6 +2,8 @@ #ifndef _ASM_X86_INIT_H #define _ASM_X86_INIT_H +#define __head __section(".head.text") + struct x86_mapping_info { void *(*alloc_pgt_page)(void *); /* allocate buf for page table */ void *context; /* context for alloc_pgt_page */ diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h index 5fcd85fd64fd..197316121f04 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -27,6 +27,7 @@ * _X - regular server parts * _D - micro server parts * _N,_P - other mobile parts + * _H - premium mobile parts * _S - other client parts * * Historical OPTDIFFs: @@ -124,6 +125,7 @@ #define INTEL_FAM6_METEORLAKE 0xAC #define INTEL_FAM6_METEORLAKE_L 0xAA +#define INTEL_FAM6_ARROWLAKE_H 0xC5 #define INTEL_FAM6_ARROWLAKE 0xC6 #define INTEL_FAM6_LUNARLAKE_M 0xBD diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index e3054e3e46d5..26b628d84594 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -108,6 +108,7 @@ KVM_X86_OP_OPTIONAL(vcpu_blocking) KVM_X86_OP_OPTIONAL(vcpu_unblocking) KVM_X86_OP_OPTIONAL(pi_update_irte) KVM_X86_OP_OPTIONAL(pi_start_assignment) +KVM_X86_OP_OPTIONAL(apicv_pre_state_restore) KVM_X86_OP_OPTIONAL(apicv_post_state_restore) KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt) KVM_X86_OP_OPTIONAL(set_hv_timer) @@ -126,7 +127,7 @@ KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from) KVM_X86_OP_OPTIONAL(vm_move_enc_context_from) KVM_X86_OP_OPTIONAL(guest_memory_reclaimed) KVM_X86_OP(get_msr_feature) -KVM_X86_OP(can_emulate_instruction) +KVM_X86_OP(check_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush) KVM_X86_OP_OPTIONAL(migrate_timers) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 17715cb8731d..d7036982332e 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -39,7 +39,15 @@ #define __KVM_HAVE_ARCH_VCPU_DEBUGFS +/* + * CONFIG_KVM_MAX_NR_VCPUS is defined iff CONFIG_KVM!=n, provide a dummy max if + * KVM is disabled (arbitrarily use the default from CONFIG_KVM_MAX_NR_VCPUS). + */ +#ifdef CONFIG_KVM_MAX_NR_VCPUS +#define KVM_MAX_VCPUS CONFIG_KVM_MAX_NR_VCPUS +#else #define KVM_MAX_VCPUS 1024 +#endif /* * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs @@ -528,7 +536,6 @@ struct kvm_pmu { u64 raw_event_mask; struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED]; - struct irq_work irq_work; /* * Overlay the bitmap with a 64-bit atomic so that all bits can be @@ -680,6 +687,7 @@ struct kvm_hypervisor_cpuid { u32 limit; }; +#ifdef CONFIG_KVM_XEN /* Xen HVM per vcpu emulation context */ struct kvm_vcpu_xen { u64 hypercall_rip; @@ -702,6 +710,7 @@ struct kvm_vcpu_xen { struct timer_list poll_timer; struct kvm_hypervisor_cpuid cpuid; }; +#endif struct kvm_queued_exception { bool pending; @@ -930,8 +939,9 @@ struct kvm_vcpu_arch { bool hyperv_enabled; struct kvm_vcpu_hv *hyperv; +#ifdef CONFIG_KVM_XEN struct kvm_vcpu_xen xen; - +#endif cpumask_var_t wbinvd_dirty_mask; unsigned long last_retry_eip; @@ -1276,7 +1286,6 @@ struct kvm_arch { */ spinlock_t mmu_unsync_pages_lock; - struct list_head assigned_dev_head; struct iommu_domain *iommu_domain; bool iommu_noncoherent; #define __KVM_HAVE_ARCH_NONCOHERENT_DMA @@ -1324,6 +1333,7 @@ struct kvm_arch { int nr_vcpus_matched_tsc; u32 default_tsc_khz; + bool user_set_tsc; seqcount_raw_spinlock_t pvclock_sc; bool use_master_clock; @@ -1692,7 +1702,7 @@ struct kvm_x86_ops { void (*request_immediate_exit)(struct kvm_vcpu *vcpu); - void (*sched_in)(struct kvm_vcpu *kvm, int cpu); + void (*sched_in)(struct kvm_vcpu *vcpu, int cpu); /* * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer. A zero @@ -1709,6 +1719,7 @@ struct kvm_x86_ops { int (*pi_update_irte)(struct kvm *kvm, unsigned int host_irq, uint32_t guest_irq, bool set); void (*pi_start_assignment)(struct kvm *kvm); + void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu); void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu); bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu); @@ -1734,8 +1745,8 @@ struct kvm_x86_ops { int (*get_msr_feature)(struct kvm_msr_entry *entry); - bool (*can_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len); + int (*check_emulate_instruction)(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len); bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu); int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h index 635132a12778..73dba8b94443 100644 --- a/arch/x86/include/asm/local.h +++ b/arch/x86/include/asm/local.h @@ -135,28 +135,27 @@ static inline bool local_try_cmpxchg(local_t *l, long *old, long new) #define local_xchg(l, n) (xchg(&((l)->a.counter), (n))) /** - * local_add_unless - add unless the number is a given value + * local_add_unless - add unless the number is already a given value * @l: pointer of type local_t * @a: the amount to add to l... * @u: ...unless l is equal to u. * - * Atomically adds @a to @l, so long as it was not @u. - * Returns non-zero if @l was not @u, and zero otherwise. + * Atomically adds @a to @l, if @v was not already @u. + * Returns true if the addition was done. */ -#define local_add_unless(l, a, u) \ -({ \ - long c, old; \ - c = local_read((l)); \ - for (;;) { \ - if (unlikely(c == (u))) \ - break; \ - old = local_cmpxchg((l), c, c + (a)); \ - if (likely(old == c)) \ - break; \ - c = old; \ - } \ - c != (u); \ -}) +static __always_inline bool +local_add_unless(local_t *l, long a, long u) +{ + long c = local_read(l); + + do { + if (unlikely(c == u)) + return false; + } while (!local_try_cmpxchg(l, &c, c + a)); + + return true; +} + #define local_inc_not_zero(l) local_add_unless((l), 1, 0) /* On x86_32, these are no better than the atomic variants. diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 180b1cbfcc4e..6de6e1d95952 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -245,7 +245,7 @@ static inline void cmci_recheck(void) {} int mce_available(struct cpuinfo_x86 *c); bool mce_is_memory_error(struct mce *m); bool mce_is_correctable(struct mce *m); -int mce_usable_address(struct mce *m); +bool mce_usable_address(struct mce *m); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 473b16d73b47..359ada486fa9 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -19,8 +19,10 @@ #ifdef CONFIG_X86_MEM_ENCRYPT void __init mem_encrypt_init(void); +void __init mem_encrypt_setup_arch(void); #else static inline void mem_encrypt_init(void) { } +static inline void __init mem_encrypt_setup_arch(void) { } #endif #ifdef CONFIG_AMD_MEM_ENCRYPT @@ -43,7 +45,6 @@ void __init sme_map_bootdata(char *real_mode_data); void __init sme_unmap_bootdata(char *real_mode_data); void __init sme_early_init(void); -void __init sev_setup_arch(void); void __init sme_encrypt_kernel(struct boot_params *bp); void __init sme_enable(struct boot_params *bp); @@ -73,7 +74,6 @@ static inline void __init sme_map_bootdata(char *real_mode_data) { } static inline void __init sme_unmap_bootdata(char *real_mode_data) { } static inline void __init sme_early_init(void) { } -static inline void __init sev_setup_arch(void) { } static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } static inline void __init sme_enable(struct boot_params *bp) { } diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index bbbe9d744977..695e569159c1 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -23,6 +23,8 @@ static inline void load_ucode_ap(void) { } static inline void microcode_bsp_resume(void) { } #endif +extern unsigned long initrd_start_early; + #ifdef CONFIG_CPU_SUP_INTEL /* Intel specific microcode defines. Public for IFS */ struct microcode_header_intel { @@ -36,7 +38,8 @@ struct microcode_header_intel { unsigned int datasize; unsigned int totalsize; unsigned int metasize; - unsigned int reserved[2]; + unsigned int min_req_ver; + unsigned int reserved; }; struct microcode_intel { @@ -68,11 +71,19 @@ static inline u32 intel_get_microcode_revision(void) return rev; } +#endif /* !CONFIG_CPU_SUP_INTEL */ -void show_ucode_info_early(void); +bool microcode_nmi_handler(void); +void microcode_offline_nmi_handler(void); -#else /* CONFIG_CPU_SUP_INTEL */ -static inline void show_ucode_info_early(void) { } -#endif /* !CONFIG_CPU_SUP_INTEL */ +#ifdef CONFIG_MICROCODE_LATE_LOADING +DECLARE_STATIC_KEY_FALSE(microcode_nmi_handler_enable); +static __always_inline bool microcode_nmi_handler_enabled(void) +{ + return static_branch_unlikely(µcode_nmi_handler_enable); +} +#else +static __always_inline bool microcode_nmi_handler_enabled(void) { return false; } +#endif #endif /* _ASM_X86_MICROCODE_H */ diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h index f46df8349e86..4b0f98a8d338 100644 --- a/arch/x86/include/asm/mpspec.h +++ b/arch/x86/include/asm/mpspec.h @@ -37,7 +37,7 @@ extern int mp_bus_id_to_type[MAX_MP_BUSSES]; extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES); -extern unsigned int boot_cpu_physical_apicid; +extern u32 boot_cpu_physical_apicid; extern u8 boot_cpu_apic_version; #ifdef CONFIG_X86_LOCAL_APIC diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h index 033b53f993c6..ce4ce8720d55 100644 --- a/arch/x86/include/asm/mshyperv.h +++ b/arch/x86/include/asm/mshyperv.h @@ -276,11 +276,11 @@ int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry); #ifdef CONFIG_AMD_MEM_ENCRYPT bool hv_ghcb_negotiate_protocol(void); void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason); -int hv_snp_boot_ap(int cpu, unsigned long start_ip); +int hv_snp_boot_ap(u32 cpu, unsigned long start_ip); #else static inline bool hv_ghcb_negotiate_protocol(void) { return false; } static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {} -static inline int hv_snp_boot_ap(int cpu, unsigned long start_ip) { return 0; } +static inline int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) { return 0; } #endif #if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST) @@ -340,8 +340,10 @@ static inline u64 hv_get_non_nested_register(unsigned int reg) { return 0; } #ifdef CONFIG_HYPERV_VTL_MODE void __init hv_vtl_init_platform(void); +int __init hv_vtl_early_init(void); #else static inline void __init hv_vtl_init_platform(void) {} +static inline int __init hv_vtl_early_init(void) { return 0; } #endif #include <asm-generic/mshyperv.h> diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 1d111350197f..1d51e1850ed0 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -222,6 +222,7 @@ #define MSR_INTEGRITY_CAPS_ARRAY_BIST BIT(MSR_INTEGRITY_CAPS_ARRAY_BIST_BIT) #define MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT 4 #define MSR_INTEGRITY_CAPS_PERIODIC_BIST BIT(MSR_INTEGRITY_CAPS_PERIODIC_BIST_BIT) +#define MSR_INTEGRITY_CAPS_SAF_GEN_MASK GENMASK_ULL(10, 9) #define MSR_LBR_NHM_FROM 0x00000680 #define MSR_LBR_NHM_TO 0x000006c0 @@ -553,6 +554,7 @@ #define MSR_AMD64_CPUID_FN_1 0xc0011004 #define MSR_AMD64_LS_CFG 0xc0011020 #define MSR_AMD64_DC_CFG 0xc0011022 +#define MSR_AMD64_TW_CFG 0xc0011023 #define MSR_AMD64_DE_CFG 0xc0011029 #define MSR_AMD64_DE_CFG_LFENCE_SERIALIZE_BIT 1 @@ -637,12 +639,21 @@ /* AMD Last Branch Record MSRs */ #define MSR_AMD64_LBR_SELECT 0xc000010e +/* Zen4 */ +#define MSR_ZEN4_BP_CFG 0xc001102e +#define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5 + +/* Fam 19h MSRs */ +#define MSR_F19H_UMC_PERF_CTL 0xc0010800 +#define MSR_F19H_UMC_PERF_CTR 0xc0010801 + +/* Zen 2 */ +#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3 +#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1) + /* Fam 17h MSRs */ #define MSR_F17H_IRPERF 0xc00000e9 -#define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3 -#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1) - /* Fam 16h MSRs */ #define MSR_F16H_L2I_PERF_CTL 0xc0010230 #define MSR_F16H_L2I_PERF_CTR 0xc0010231 @@ -1112,12 +1123,16 @@ #define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14) #define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29) #define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F -/* AMD-V MSRs */ +/* AMD-V MSRs */ #define MSR_VM_CR 0xc0010114 #define MSR_VM_IGNNE 0xc0010115 #define MSR_VM_HSAVE_PA 0xc0010117 +#define SVM_VM_CR_VALID_MASK 0x001fULL +#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL +#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL + /* Hardware Feedback Interface */ #define MSR_IA32_HW_FEEDBACK_PTR 0x17d0 #define MSR_IA32_HW_FEEDBACK_CONFIG 0x17d1 diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index c55cc243592e..f93e9b96927a 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -196,7 +196,7 @@ .macro ANNOTATE_RETPOLINE_SAFE .Lhere_\@: .pushsection .discard.retpoline_safe - .long .Lhere_\@ - . + .long .Lhere_\@ .popsection .endm @@ -271,7 +271,7 @@ .Lskip_rsb_\@: .endm -#ifdef CONFIG_CPU_UNRET_ENTRY +#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) #define CALL_UNTRAIN_RET "call entry_untrain_ret" #else #define CALL_UNTRAIN_RET "" @@ -288,38 +288,24 @@ * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point * where we have a stack but before any RET instruction. */ -.macro UNTRAIN_RET -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ - defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO) +.macro __UNTRAIN_RET ibpb_feature, call_depth_insns +#if defined(CONFIG_RETHUNK) || defined(CONFIG_CPU_IBPB_ENTRY) VALIDATE_UNRET_END ALTERNATIVE_3 "", \ CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ - "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \ - __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH + "call entry_ibpb", \ibpb_feature, \ + __stringify(\call_depth_insns), X86_FEATURE_CALL_DEPTH #endif .endm -.macro UNTRAIN_RET_VM -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ - defined(CONFIG_CALL_DEPTH_TRACKING) || defined(CONFIG_CPU_SRSO) - VALIDATE_UNRET_END - ALTERNATIVE_3 "", \ - CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ - "call entry_ibpb", X86_FEATURE_IBPB_ON_VMEXIT, \ - __stringify(RESET_CALL_DEPTH), X86_FEATURE_CALL_DEPTH -#endif -.endm +#define UNTRAIN_RET \ + __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH) -.macro UNTRAIN_RET_FROM_CALL -#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \ - defined(CONFIG_CALL_DEPTH_TRACKING) - VALIDATE_UNRET_END - ALTERNATIVE_3 "", \ - CALL_UNTRAIN_RET, X86_FEATURE_UNRET, \ - "call entry_ibpb", X86_FEATURE_ENTRY_IBPB, \ - __stringify(RESET_CALL_DEPTH_FROM_CALL), X86_FEATURE_CALL_DEPTH -#endif -.endm +#define UNTRAIN_RET_VM \ + __UNTRAIN_RET X86_FEATURE_IBPB_ON_VMEXIT, __stringify(RESET_CALL_DEPTH) + +#define UNTRAIN_RET_FROM_CALL \ + __UNTRAIN_RET X86_FEATURE_ENTRY_IBPB, __stringify(RESET_CALL_DEPTH_FROM_CALL) .macro CALL_DEPTH_ACCOUNT @@ -334,7 +320,7 @@ #define ANNOTATE_RETPOLINE_SAFE \ "999:\n\t" \ ".pushsection .discard.retpoline_safe\n\t" \ - ".long 999b - .\n\t" \ + ".long 999b\n\t" \ ".popsection\n\t" typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE]; @@ -348,13 +334,23 @@ extern void __x86_return_thunk(void); static inline void __x86_return_thunk(void) {} #endif +#ifdef CONFIG_CPU_UNRET_ENTRY extern void retbleed_return_thunk(void); +#else +static inline void retbleed_return_thunk(void) {} +#endif + +#ifdef CONFIG_CPU_SRSO extern void srso_return_thunk(void); extern void srso_alias_return_thunk(void); +#else +static inline void srso_return_thunk(void) {} +static inline void srso_alias_return_thunk(void) {} +#endif -extern void retbleed_untrain_ret(void); -extern void srso_untrain_ret(void); -extern void srso_alias_untrain_ret(void); +extern void retbleed_return_thunk(void); +extern void srso_return_thunk(void); +extern void srso_alias_return_thunk(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); @@ -362,12 +358,7 @@ extern void entry_ibpb(void); extern void (*x86_return_thunk)(void); #ifdef CONFIG_CALL_DEPTH_TRACKING -extern void __x86_return_skl(void); - -static inline void x86_set_skl_return_thunk(void) -{ - x86_return_thunk = &__x86_return_skl; -} +extern void call_depth_return_thunk(void); #define CALL_DEPTH_ACCOUNT \ ALTERNATIVE("", \ @@ -380,12 +371,12 @@ DECLARE_PER_CPU(u64, __x86_ret_count); DECLARE_PER_CPU(u64, __x86_stuffs_count); DECLARE_PER_CPU(u64, __x86_ctxsw_count); #endif -#else -static inline void x86_set_skl_return_thunk(void) {} +#else /* !CONFIG_CALL_DEPTH_TRACKING */ +static inline void call_depth_return_thunk(void) {} #define CALL_DEPTH_ACCOUNT "" -#endif +#endif /* CONFIG_CALL_DEPTH_TRACKING */ #ifdef CONFIG_RETPOLINE diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index e3bae2b60a0d..ef2844d69173 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -12,13 +12,6 @@ #define NR_NODE_MEMBLKS (MAX_NUMNODES*2) -/* - * Too small node sizes may confuse the VM badly. Usually they - * result from BIOS bugs. So dont recognize nodes as standalone - * NUMA entities that have less than this amount of RAM listed: - */ -#define NODE_MIN_SIZE (4*1024*1024) - extern int numa_off; /* diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 34734d730463..20624b80f890 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -210,6 +210,25 @@ do { \ (typeof(_var))(unsigned long) pco_old__; \ }) +#define percpu_try_cmpxchg_op(size, qual, _var, _ovalp, _nval) \ +({ \ + bool success; \ + __pcpu_type_##size *pco_oval__ = (__pcpu_type_##size *)(_ovalp); \ + __pcpu_type_##size pco_old__ = *pco_oval__; \ + __pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval); \ + asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]", \ + __percpu_arg([var])) \ + CC_SET(z) \ + : CC_OUT(z) (success), \ + [oval] "+a" (pco_old__), \ + [var] "+m" (_var) \ + : [nval] __pcpu_reg_##size(, pco_new__) \ + : "memory"); \ + if (unlikely(!success)) \ + *pco_oval__ = pco_old__; \ + likely(success); \ +}) + #if defined(CONFIG_X86_32) && !defined(CONFIG_UML) #define percpu_cmpxchg64_op(size, qual, _var, _oval, _nval) \ ({ \ @@ -223,26 +242,63 @@ do { \ old__.var = _oval; \ new__.var = _nval; \ \ - asm qual (ALTERNATIVE("leal %P[var], %%esi; call this_cpu_cmpxchg8b_emu", \ + asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \ "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \ : [var] "+m" (_var), \ "+a" (old__.low), \ "+d" (old__.high) \ : "b" (new__.low), \ - "c" (new__.high) \ - : "memory", "esi"); \ + "c" (new__.high), \ + "S" (&(_var)) \ + : "memory"); \ \ old__.var; \ }) #define raw_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg64_op(8, , pcp, oval, nval) #define this_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg64_op(8, volatile, pcp, oval, nval) + +#define percpu_try_cmpxchg64_op(size, qual, _var, _ovalp, _nval) \ +({ \ + bool success; \ + u64 *_oval = (u64 *)(_ovalp); \ + union { \ + u64 var; \ + struct { \ + u32 low, high; \ + }; \ + } old__, new__; \ + \ + old__.var = *_oval; \ + new__.var = _nval; \ + \ + asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu", \ + "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \ + CC_SET(z) \ + : CC_OUT(z) (success), \ + [var] "+m" (_var), \ + "+a" (old__.low), \ + "+d" (old__.high) \ + : "b" (new__.low), \ + "c" (new__.high), \ + "S" (&(_var)) \ + : "memory"); \ + if (unlikely(!success)) \ + *_oval = old__.var; \ + likely(success); \ +}) + +#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg64_op(8, , pcp, ovalp, nval) +#define this_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg64_op(8, volatile, pcp, ovalp, nval) #endif #ifdef CONFIG_X86_64 #define raw_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg_op(8, , pcp, oval, nval); #define this_cpu_cmpxchg64(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval); +#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, , pcp, ovalp, nval); +#define this_cpu_try_cmpxchg64(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval); + #define percpu_cmpxchg128_op(size, qual, _var, _oval, _nval) \ ({ \ union { \ @@ -255,20 +311,54 @@ do { \ old__.var = _oval; \ new__.var = _nval; \ \ - asm qual (ALTERNATIVE("leaq %P[var], %%rsi; call this_cpu_cmpxchg16b_emu", \ + asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \ "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \ : [var] "+m" (_var), \ "+a" (old__.low), \ "+d" (old__.high) \ : "b" (new__.low), \ - "c" (new__.high) \ - : "memory", "rsi"); \ + "c" (new__.high), \ + "S" (&(_var)) \ + : "memory"); \ \ old__.var; \ }) #define raw_cpu_cmpxchg128(pcp, oval, nval) percpu_cmpxchg128_op(16, , pcp, oval, nval) #define this_cpu_cmpxchg128(pcp, oval, nval) percpu_cmpxchg128_op(16, volatile, pcp, oval, nval) + +#define percpu_try_cmpxchg128_op(size, qual, _var, _ovalp, _nval) \ +({ \ + bool success; \ + u128 *_oval = (u128 *)(_ovalp); \ + union { \ + u128 var; \ + struct { \ + u64 low, high; \ + }; \ + } old__, new__; \ + \ + old__.var = *_oval; \ + new__.var = _nval; \ + \ + asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu", \ + "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \ + CC_SET(z) \ + : CC_OUT(z) (success), \ + [var] "+m" (_var), \ + "+a" (old__.low), \ + "+d" (old__.high) \ + : "b" (new__.low), \ + "c" (new__.high), \ + "S" (&(_var)) \ + : "memory"); \ + if (unlikely(!success)) \ + *_oval = old__.var; \ + likely(success); \ +}) + +#define raw_cpu_try_cmpxchg128(pcp, ovalp, nval) percpu_try_cmpxchg128_op(16, , pcp, ovalp, nval) +#define this_cpu_try_cmpxchg128(pcp, ovalp, nval) percpu_try_cmpxchg128_op(16, volatile, pcp, ovalp, nval) #endif /* @@ -343,6 +433,9 @@ do { \ #define raw_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, , pcp, oval, nval) #define raw_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, , pcp, oval, nval) #define raw_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, , pcp, oval, nval) +#define raw_cpu_try_cmpxchg_1(pcp, ovalp, nval) percpu_try_cmpxchg_op(1, , pcp, ovalp, nval) +#define raw_cpu_try_cmpxchg_2(pcp, ovalp, nval) percpu_try_cmpxchg_op(2, , pcp, ovalp, nval) +#define raw_cpu_try_cmpxchg_4(pcp, ovalp, nval) percpu_try_cmpxchg_op(4, , pcp, ovalp, nval) #define this_cpu_add_return_1(pcp, val) percpu_add_return_op(1, volatile, pcp, val) #define this_cpu_add_return_2(pcp, val) percpu_add_return_op(2, volatile, pcp, val) @@ -350,6 +443,9 @@ do { \ #define this_cpu_cmpxchg_1(pcp, oval, nval) percpu_cmpxchg_op(1, volatile, pcp, oval, nval) #define this_cpu_cmpxchg_2(pcp, oval, nval) percpu_cmpxchg_op(2, volatile, pcp, oval, nval) #define this_cpu_cmpxchg_4(pcp, oval, nval) percpu_cmpxchg_op(4, volatile, pcp, oval, nval) +#define this_cpu_try_cmpxchg_1(pcp, ovalp, nval) percpu_try_cmpxchg_op(1, volatile, pcp, ovalp, nval) +#define this_cpu_try_cmpxchg_2(pcp, ovalp, nval) percpu_try_cmpxchg_op(2, volatile, pcp, ovalp, nval) +#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval) percpu_try_cmpxchg_op(4, volatile, pcp, ovalp, nval) /* * Per cpu atomic 64 bit operations are only available under 64 bit. @@ -364,6 +460,7 @@ do { \ #define raw_cpu_add_return_8(pcp, val) percpu_add_return_op(8, , pcp, val) #define raw_cpu_xchg_8(pcp, nval) raw_percpu_xchg_op(pcp, nval) #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) @@ -373,6 +470,7 @@ do { \ #define this_cpu_add_return_8(pcp, val) percpu_add_return_op(8, volatile, pcp, val) #define this_cpu_xchg_8(pcp, nval) percpu_xchg_op(8, volatile, pcp, nval) #define this_cpu_cmpxchg_8(pcp, oval, nval) percpu_cmpxchg_op(8, volatile, pcp, oval, nval) +#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval) percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval) #endif static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr, diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 85a9fd5a3ec3..2618ec7c3d1d 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -112,6 +112,13 @@ (AMD64_PERFMON_V2_EVENTSEL_EVENT_NB | \ AMD64_PERFMON_V2_EVENTSEL_UMASK_NB) +#define AMD64_PERFMON_V2_ENABLE_UMC BIT_ULL(31) +#define AMD64_PERFMON_V2_EVENTSEL_EVENT_UMC GENMASK_ULL(7, 0) +#define AMD64_PERFMON_V2_EVENTSEL_RDWRMASK_UMC GENMASK_ULL(9, 8) +#define AMD64_PERFMON_V2_RAW_EVENT_MASK_UMC \ + (AMD64_PERFMON_V2_EVENTSEL_EVENT_UMC | \ + AMD64_PERFMON_V2_EVENTSEL_RDWRMASK_UMC) + #define AMD64_NUM_COUNTERS 4 #define AMD64_NUM_COUNTERS_CORE 6 #define AMD64_NUM_COUNTERS_NB 4 @@ -232,6 +239,8 @@ union cpuid_0x80000022_ebx { unsigned int lbr_v2_stack_sz:6; /* Number of Data Fabric Counters */ unsigned int num_df_pmc:6; + /* Number of Unified Memory Controller Counters */ + unsigned int num_umc_pmc:6; } split; unsigned int full; }; diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index d6ad98ca1288..57bab91bbf50 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -955,6 +955,14 @@ 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) +{ + 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)); +} +#define pte_next_pfn pte_next_pfn + static inline int pte_present(pte_t a) { return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); @@ -1708,6 +1716,14 @@ static inline bool pud_user_accessible_page(pud_t pud) } #endif +#ifdef CONFIG_X86_SGX +int arch_memory_failure(unsigned long pfn, int flags); +#define arch_memory_failure arch_memory_failure + +bool arch_is_platform_page(u64 paddr); +#define arch_is_platform_page arch_is_platform_page +#endif + #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_H */ diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 2d13f25b1bd8..4527e1430c6d 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -31,11 +31,11 @@ static __always_inline void preempt_count_set(int pc) { int old, new; + old = raw_cpu_read_4(pcpu_hot.preempt_count); do { - old = raw_cpu_read_4(pcpu_hot.preempt_count); new = (old & PREEMPT_NEED_RESCHED) | (pc & ~PREEMPT_NEED_RESCHED); - } while (raw_cpu_cmpxchg_4(pcpu_hot.preempt_count, old, new) != old); + } while (!raw_cpu_try_cmpxchg_4(pcpu_hot.preempt_count, &old, new)); } /* diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index a3669a7774ed..ae81a7191c1c 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -75,11 +75,36 @@ extern u16 __read_mostly tlb_lld_4m[NR_INFO]; extern u16 __read_mostly tlb_lld_1g[NR_INFO]; /* - * CPU type and hardware bug flags. Kept separately for each CPU. - * Members of this structure are referenced in head_32.S, so think twice - * before touching them. [mj] + * CPU type and hardware bug flags. Kept separately for each CPU. */ +struct cpuinfo_topology { + // Real APIC ID read from the local APIC + u32 apicid; + // The initial APIC ID provided by CPUID + u32 initial_apicid; + + // Physical package ID + u32 pkg_id; + + // Physical die ID on AMD, Relative on Intel + u32 die_id; + + // Compute unit ID - AMD specific + u32 cu_id; + + // Core ID relative to the package + u32 core_id; + + // Logical ID mappings + u32 logical_pkg_id; + u32 logical_die_id; + + // Cache level topology IDs + u32 llc_id; + u32 l2c_id; +}; + struct cpuinfo_x86 { __u8 x86; /* CPU family */ __u8 x86_vendor; /* CPU vendor */ @@ -96,7 +121,6 @@ struct cpuinfo_x86 { __u8 x86_phys_bits; /* CPUID returned core id bits: */ __u8 x86_coreid_bits; - __u8 cu_id; /* Max extended CPUID function supported: */ __u32 extended_cpuid_level; /* Maximum supported CPUID level, -1=no CPUID: */ @@ -112,6 +136,7 @@ struct cpuinfo_x86 { }; char x86_vendor_id[16]; char x86_model_id[64]; + struct cpuinfo_topology topo; /* in KB - valid for CPUS which support this call: */ unsigned int x86_cache_size; int x86_cache_alignment; /* In bytes */ @@ -125,19 +150,9 @@ struct cpuinfo_x86 { u64 ppin; /* cpuid returned max cores value: */ u16 x86_max_cores; - u16 apicid; - u16 initial_apicid; u16 x86_clflush_size; /* number of cores as seen by the OS: */ u16 booted_cores; - /* Physical processor id: */ - u16 phys_proc_id; - /* Logical processor id: */ - u16 logical_proc_id; - /* Core id: */ - u16 cpu_core_id; - u16 cpu_die_id; - u16 logical_die_id; /* Index into per_cpu list: */ u16 cpu_index; /* Is SMT active on this core? */ @@ -399,7 +414,7 @@ static inline unsigned long cpu_kernelmode_gs_base(int cpu) return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu); } -extern asmlinkage void ignore_sysret(void); +extern asmlinkage void entry_SYSCALL32_ignore(void); /* Save actual FS/GS selectors and bases to current->thread */ void current_save_fsgs(void); @@ -678,7 +693,15 @@ extern int set_tsc_mode(unsigned int val); DECLARE_PER_CPU(u64, msr_misc_features_shadow); -extern u16 get_llc_id(unsigned int cpu); +static inline u32 per_cpu_llc_id(unsigned int cpu) +{ + return per_cpu(cpu_info.topo.llc_id, cpu); +} + +static inline u32 per_cpu_l2c_id(unsigned int cpu) +{ + return per_cpu(cpu_info.topo.l2c_id, cpu); +} #ifdef CONFIG_CPU_SUP_AMD extern u32 amd_get_nodes_per_socket(void); @@ -724,14 +747,6 @@ enum mds_mitigations { MDS_MITIGATION_VMWERV, }; -#ifdef CONFIG_X86_SGX -int arch_memory_failure(unsigned long pfn, int flags); -#define arch_memory_failure arch_memory_failure - -bool arch_is_platform_page(u64 paddr); -#define arch_is_platform_page arch_is_platform_page -#endif - extern bool gds_ucode_mitigated(void); #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h index b716d291d0d4..65dee2420624 100644 --- a/arch/x86/include/asm/prom.h +++ b/arch/x86/include/asm/prom.h @@ -31,6 +31,11 @@ static inline void x86_dtb_init(void) { } #define of_ioapic 0 #endif +#ifdef CONFIG_OF_EARLY_FLATTREE +void x86_flattree_get_config(void); +#else +static inline void x86_flattree_get_config(void) { } +#endif extern char cmd_line[COMMAND_LINE_SIZE]; #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 12ef86b19910..4d84122bd643 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -36,6 +36,9 @@ void entry_INT80_compat(void); #ifdef CONFIG_XEN_PV void xen_entry_INT80_compat(void); #endif +#else /* !CONFIG_IA32_EMULATION */ +#define entry_SYSCALL_compat NULL +#define entry_SYSENTER_compat NULL #endif void x86_configure_nx(void); diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index f3495623ac99..bf483fcb4e57 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -126,6 +126,7 @@ void clear_bss(void); #ifdef __i386__ asmlinkage void __init __noreturn i386_start_kernel(void); +void __init mk_early_pgtbl_32(void); #else asmlinkage void __init __noreturn x86_64_start_kernel(char *real_mode); diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index 9eab19950f39..ccce7ebd8677 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -11,11 +11,12 @@ #define TDX_IDENT "IntelTDX " /* TDX module Call Leaf IDs */ -#define TDX_GET_INFO 1 -#define TDX_GET_VEINFO 3 -#define TDX_GET_REPORT 4 -#define TDX_ACCEPT_PAGE 6 -#define TDX_WR 8 +#define TDG_VP_VMCALL 0 +#define TDG_VP_INFO 1 +#define TDG_VP_VEINFO_GET 3 +#define TDG_MR_REPORT 4 +#define TDG_MEM_PAGE_ACCEPT 6 +#define TDG_VM_WR 8 /* TDCS fields. To be used by TDG.VM.WR and TDG.VM.RD module calls */ #define TDCS_NOTIFY_ENABLES 0x9100000000000010 @@ -25,32 +26,70 @@ #define TDVMCALL_GET_QUOTE 0x10002 #define TDVMCALL_REPORT_FATAL_ERROR 0x10003 +#define TDVMCALL_STATUS_RETRY 1 + +/* + * Bitmasks of exposed registers (with VMM). + */ +#define TDX_RDX BIT(2) +#define TDX_RBX BIT(3) +#define TDX_RSI BIT(6) +#define TDX_RDI BIT(7) +#define TDX_R8 BIT(8) +#define TDX_R9 BIT(9) +#define TDX_R10 BIT(10) +#define TDX_R11 BIT(11) +#define TDX_R12 BIT(12) +#define TDX_R13 BIT(13) +#define TDX_R14 BIT(14) +#define TDX_R15 BIT(15) + +/* + * These registers are clobbered to hold arguments for each + * TDVMCALL. They are safe to expose to the VMM. + * Each bit in this mask represents a register ID. Bit field + * details can be found in TDX GHCI specification, section + * titled "TDCALL [TDG.VP.VMCALL] leaf". + */ +#define TDVMCALL_EXPOSE_REGS_MASK \ + (TDX_RDX | TDX_RBX | TDX_RSI | TDX_RDI | TDX_R8 | TDX_R9 | \ + TDX_R10 | TDX_R11 | TDX_R12 | TDX_R13 | TDX_R14 | TDX_R15) + #ifndef __ASSEMBLY__ +#include <linux/compiler_attributes.h> + /* - * Used in __tdx_hypercall() to pass down and get back registers' values of - * the TDCALL instruction when requesting services from the VMM. - * - * This is a software only structure and not part of the TDX module/VMM ABI. + * Used in __tdcall*() to gather the input/output registers' values of the + * TDCALL instruction when requesting services from the TDX module. This is a + * software only structure and not part of the TDX module/VMM ABI */ -struct tdx_hypercall_args { +struct tdx_module_args { + /* callee-clobbered */ + u64 rcx; + u64 rdx; u64 r8; u64 r9; + /* extra callee-clobbered */ u64 r10; u64 r11; + /* callee-saved + rdi/rsi */ u64 r12; u64 r13; u64 r14; u64 r15; + u64 rbx; u64 rdi; u64 rsi; - u64 rbx; - u64 rdx; }; +/* Used to communicate with the TDX module */ +u64 __tdcall(u64 fn, struct tdx_module_args *args); +u64 __tdcall_ret(u64 fn, struct tdx_module_args *args); +u64 __tdcall_saved_ret(u64 fn, struct tdx_module_args *args); + /* Used to request services from the VMM */ -u64 __tdx_hypercall(struct tdx_hypercall_args *args); -u64 __tdx_hypercall_ret(struct tdx_hypercall_args *args); +u64 __tdx_hypercall(struct tdx_module_args *args); /* * Wrapper for standard use of __tdx_hypercall with no output aside from @@ -58,7 +97,7 @@ u64 __tdx_hypercall_ret(struct tdx_hypercall_args *args); */ static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15) { - struct tdx_hypercall_args args = { + struct tdx_module_args args = { .r10 = TDX_HYPERCALL_STANDARD, .r11 = fn, .r12 = r12, @@ -72,25 +111,7 @@ static inline u64 _tdx_hypercall(u64 fn, u64 r12, u64 r13, u64 r14, u64 r15) /* Called from __tdx_hypercall() for unrecoverable failure */ -void __tdx_hypercall_failed(void); - -/* - * Used in __tdx_module_call() to gather the output registers' values of the - * TDCALL instruction when requesting services from the TDX module. This is a - * software only structure and not part of the TDX module/VMM ABI - */ -struct tdx_module_output { - u64 rcx; - u64 rdx; - u64 r8; - u64 r9; - u64 r10; - u64 r11; -}; - -/* Used to communicate with the TDX module */ -u64 __tdx_module_call(u64 fn, u64 rcx, u64 rdx, u64 r8, u64 r9, - struct tdx_module_output *out); +void __noreturn __tdx_hypercall_failed(void); bool tdx_accept_memory(phys_addr_t start, phys_addr_t end); diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index ad98dd1d9cfb..4fab2ed454f3 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -17,10 +17,8 @@ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_die_map); /* cpus sharing the last level cache: */ DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map); DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_l2c_shared_map); -DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id); -DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id); -DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid); +DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_apicid); DECLARE_EARLY_PER_CPU_READ_MOSTLY(u32, x86_cpu_to_acpiid); struct task_struct; @@ -129,7 +127,6 @@ void native_smp_send_reschedule(int cpu); void native_send_call_func_ipi(const struct cpumask *mask); void native_send_call_func_single_ipi(int cpu); -bool smp_park_other_cpus_in_init(void); void smp_store_cpu_info(int id); asmlinkage __visible void smp_reboot_interrupt(void); diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h index 64df897c0ee3..1be13b2dfe8b 100644 --- a/arch/x86/include/asm/sparsemem.h +++ b/arch/x86/include/asm/sparsemem.h @@ -37,6 +37,8 @@ extern int phys_to_target_node(phys_addr_t start); #define phys_to_target_node phys_to_target_node extern int memory_add_physaddr_to_nid(u64 start); #define memory_add_physaddr_to_nid memory_add_physaddr_to_nid +extern int numa_fill_memblks(u64 start, u64 end); +#define numa_fill_memblks numa_fill_memblks #endif #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h index cb0386fc4dc3..c648502e4535 100644 --- a/arch/x86/include/asm/spec-ctrl.h +++ b/arch/x86/include/asm/spec-ctrl.h @@ -4,6 +4,7 @@ #include <linux/thread_info.h> #include <asm/nospec-branch.h> +#include <asm/msr.h> /* * On VMENTER we must preserve whatever view of the SPEC_CTRL MSR @@ -76,6 +77,16 @@ static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn) return (tifn & _TIF_SSBD) ? x86_amd_ls_cfg_ssbd_mask : 0ULL; } +/* + * This can be used in noinstr functions & should only be called in bare + * metal context. + */ +static __always_inline void __update_spec_ctrl(u64 val) +{ + __this_cpu_write(x86_spec_ctrl_current, val); + native_wrmsrl(MSR_IA32_SPEC_CTRL, val); +} + #ifdef CONFIG_SMP extern void speculative_store_bypass_ht_init(void); #else diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 19bf955b67e0..87a7b917d30e 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -229,10 +229,6 @@ struct __attribute__ ((__packed__)) vmcb_control_area { #define SVM_IOIO_SIZE_MASK (7 << SVM_IOIO_SIZE_SHIFT) #define SVM_IOIO_ASIZE_MASK (7 << SVM_IOIO_ASIZE_SHIFT) -#define SVM_VM_CR_VALID_MASK 0x001fULL -#define SVM_VM_CR_SVM_LOCK_MASK 0x0008ULL -#define SVM_VM_CR_SVM_DIS_MASK 0x0010ULL - #define SVM_NESTED_CTL_NP_ENABLE BIT(0) #define SVM_NESTED_CTL_SEV_ENABLE BIT(1) #define SVM_NESTED_CTL_SEV_ES_ENABLE BIT(2) @@ -268,6 +264,7 @@ enum avic_ipi_failure_cause { AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, AVIC_IPI_FAILURE_INVALID_TARGET, AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, + AVIC_IPI_FAILURE_INVALID_IPI_VECTOR, }; #define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(8, 0) @@ -571,8 +568,6 @@ struct vmcb { #define SVM_CPUID_FUNC 0x8000000a -#define SVM_VM_CR_SVM_DISABLE 4 - #define SVM_SELECTOR_S_SHIFT 4 #define SVM_SELECTOR_DPL_SHIFT 5 #define SVM_SELECTOR_P_SHIFT 7 diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 4fb36fba4b5a..f44e2f9ab65d 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -126,12 +126,12 @@ static inline int syscall_get_arch(struct task_struct *task) ? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64; } -void do_syscall_64(struct pt_regs *regs, int nr); +bool do_syscall_64(struct pt_regs *regs, int nr); #endif /* CONFIG_X86_32 */ void do_int80_syscall_32(struct pt_regs *regs); -long do_fast_syscall_32(struct pt_regs *regs); -long do_SYSENTER_32(struct pt_regs *regs); +bool do_fast_syscall_32(struct pt_regs *regs); +bool do_SYSENTER_32(struct pt_regs *regs); #endif /* _ASM_X86_SYSCALL_H */ diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index ebd1cda4875f..f3d5305a60fc 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -8,6 +8,7 @@ #include <asm/errno.h> #include <asm/ptrace.h> +#include <asm/trapnr.h> #include <asm/shared/tdx.h> /* @@ -20,6 +21,9 @@ #define TDX_SW_ERROR (TDX_ERROR | GENMASK_ULL(47, 40)) #define TDX_SEAMCALL_VMFAILINVALID (TDX_SW_ERROR | _UL(0xFFFF0000)) +#define TDX_SEAMCALL_GP (TDX_SW_ERROR | X86_TRAP_GP) +#define TDX_SEAMCALL_UD (TDX_SW_ERROR | X86_TRAP_UD) + #ifndef __ASSEMBLY__ /* @@ -74,5 +78,12 @@ static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, return -ENODEV; } #endif /* CONFIG_INTEL_TDX_GUEST && CONFIG_KVM_GUEST */ + +#ifdef CONFIG_INTEL_TDX_HOST +u64 __seamcall(u64 fn, struct tdx_module_args *args); +u64 __seamcall_ret(u64 fn, struct tdx_module_args *args); +u64 __seamcall_saved_ret(u64 fn, struct tdx_module_args *args); +#endif /* CONFIG_INTEL_TDX_HOST */ + #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_TDX_H */ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 3235ba1e5b06..5f87f6b9b09e 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -105,17 +105,17 @@ static inline void setup_node_to_cpumask_map(void) { } extern const struct cpumask *cpu_coregroup_mask(int cpu); extern const struct cpumask *cpu_clustergroup_mask(int cpu); -#define topology_logical_package_id(cpu) (cpu_data(cpu).logical_proc_id) -#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id) -#define topology_logical_die_id(cpu) (cpu_data(cpu).logical_die_id) -#define topology_die_id(cpu) (cpu_data(cpu).cpu_die_id) -#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id) +#define topology_logical_package_id(cpu) (cpu_data(cpu).topo.logical_pkg_id) +#define topology_physical_package_id(cpu) (cpu_data(cpu).topo.pkg_id) +#define topology_logical_die_id(cpu) (cpu_data(cpu).topo.logical_die_id) +#define topology_die_id(cpu) (cpu_data(cpu).topo.die_id) +#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; #ifdef CONFIG_SMP -#define topology_cluster_id(cpu) (per_cpu(cpu_l2c_id, cpu)) +#define topology_cluster_id(cpu) (cpu_data(cpu).topo.l2c_id) #define topology_die_cpumask(cpu) (per_cpu(cpu_die_map, cpu)) #define topology_cluster_cpumask(cpu) (cpu_clustergroup_mask(cpu)) #define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu)) diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index 8bae40a66282..5c367c1290c3 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -496,7 +496,7 @@ copy_mc_to_kernel(void *to, const void *from, unsigned len); #define copy_mc_to_kernel copy_mc_to_kernel unsigned long __must_check -copy_mc_to_user(void *to, const void *from, unsigned len); +copy_mc_to_user(void __user *to, const void *from, unsigned len); #endif /* diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h index 5240d88db52a..c878616a18b8 100644 --- a/arch/x86/include/asm/x86_init.h +++ b/arch/x86/include/asm/x86_init.h @@ -177,7 +177,7 @@ struct x86_init_ops { * struct x86_cpuinit_ops - platform specific cpu hotplug setups * @setup_percpu_clockev: set up the per cpu clock event device * @early_percpu_clock_init: early init of the per cpu clock event device - * @fixup_cpu_id: fixup function for cpuinfo_x86::phys_proc_id + * @fixup_cpu_id: fixup function for cpuinfo_x86::topo.pkg_id * @parallel_bringup: Parallel bringup control */ struct x86_cpuinit_ops { diff --git a/arch/x86/include/uapi/asm/amd_hsmp.h b/arch/x86/include/uapi/asm/amd_hsmp.h index 769b939444ae..fce22686c834 100644 --- a/arch/x86/include/uapi/asm/amd_hsmp.h +++ b/arch/x86/include/uapi/asm/amd_hsmp.h @@ -47,6 +47,9 @@ enum hsmp_message_ids { HSMP_SET_PCI_RATE, /* 20h Control link rate on PCIe devices */ HSMP_SET_POWER_MODE, /* 21h Select power efficiency profile policy */ HSMP_SET_PSTATE_MAX_MIN, /* 22h Set the max and min DF P-State */ + HSMP_GET_METRIC_TABLE_VER, /* 23h Get metrics table version */ + HSMP_GET_METRIC_TABLE, /* 24h Get metrics table */ + HSMP_GET_METRIC_TABLE_DRAM_ADDR,/* 25h Get metrics table dram address */ HSMP_MSG_ID_MAX, }; @@ -64,6 +67,14 @@ enum hsmp_msg_type { HSMP_GET = 1, }; +enum hsmp_proto_versions { + HSMP_PROTO_VER2 = 2, + HSMP_PROTO_VER3, + HSMP_PROTO_VER4, + HSMP_PROTO_VER5, + HSMP_PROTO_VER6 +}; + struct hsmp_msg_desc { int num_args; int response_sz; @@ -295,6 +306,104 @@ static const struct hsmp_msg_desc hsmp_msg_desc_table[] = { * input: args[0] = min df pstate[15:8] + max df pstate[7:0] */ {1, 0, HSMP_SET}, + + /* + * HSMP_GET_METRIC_TABLE_VER, num_args = 0, response_sz = 1 + * output: args[0] = metrics table version + */ + {0, 1, HSMP_GET}, + + /* + * HSMP_GET_METRIC_TABLE, num_args = 0, response_sz = 0 + */ + {0, 0, HSMP_GET}, + + /* + * HSMP_GET_METRIC_TABLE_DRAM_ADDR, num_args = 0, response_sz = 2 + * output: args[0] = lower 32 bits of the address + * output: args[1] = upper 32 bits of the address + */ + {0, 2, HSMP_GET}, +}; + +/* Metrics table (supported only with proto version 6) */ +struct hsmp_metric_table { + __u32 accumulation_counter; + + /* TEMPERATURE */ + __u32 max_socket_temperature; + __u32 max_vr_temperature; + __u32 max_hbm_temperature; + __u64 max_socket_temperature_acc; + __u64 max_vr_temperature_acc; + __u64 max_hbm_temperature_acc; + + /* POWER */ + __u32 socket_power_limit; + __u32 max_socket_power_limit; + __u32 socket_power; + + /* ENERGY */ + __u64 timestamp; + __u64 socket_energy_acc; + __u64 ccd_energy_acc; + __u64 xcd_energy_acc; + __u64 aid_energy_acc; + __u64 hbm_energy_acc; + + /* FREQUENCY */ + __u32 cclk_frequency_limit; + __u32 gfxclk_frequency_limit; + __u32 fclk_frequency; + __u32 uclk_frequency; + __u32 socclk_frequency[4]; + __u32 vclk_frequency[4]; + __u32 dclk_frequency[4]; + __u32 lclk_frequency[4]; + __u64 gfxclk_frequency_acc[8]; + __u64 cclk_frequency_acc[96]; + + /* FREQUENCY RANGE */ + __u32 max_cclk_frequency; + __u32 min_cclk_frequency; + __u32 max_gfxclk_frequency; + __u32 min_gfxclk_frequency; + __u32 fclk_frequency_table[4]; + __u32 uclk_frequency_table[4]; + __u32 socclk_frequency_table[4]; + __u32 vclk_frequency_table[4]; + __u32 dclk_frequency_table[4]; + __u32 lclk_frequency_table[4]; + __u32 max_lclk_dpm_range; + __u32 min_lclk_dpm_range; + + /* XGMI */ + __u32 xgmi_width; + __u32 xgmi_bitrate; + __u64 xgmi_read_bandwidth_acc[8]; + __u64 xgmi_write_bandwidth_acc[8]; + + /* ACTIVITY */ + __u32 socket_c0_residency; + __u32 socket_gfx_busy; + __u32 dram_bandwidth_utilization; + __u64 socket_c0_residency_acc; + __u64 socket_gfx_busy_acc; + __u64 dram_bandwidth_acc; + __u32 max_dram_bandwidth; + __u64 dram_bandwidth_utilization_acc; + __u64 pcie_bandwidth_acc[4]; + + /* THROTTLERS */ + __u32 prochot_residency_acc; + __u32 ppt_residency_acc; + __u32 socket_thm_residency_acc; + __u32 vr_thm_residency_acc; + __u32 hbm_thm_residency_acc; + __u32 spare; + + /* New items at the end to maintain driver compatibility */ + __u32 gfxclk_frequency[8]; }; /* Reset to default packing */ diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile index 3269a0e23d3a..0000325ab98f 100644 --- a/arch/x86/kernel/Makefile +++ b/arch/x86/kernel/Makefile @@ -16,6 +16,7 @@ CFLAGS_REMOVE_kvmclock.o = -pg CFLAGS_REMOVE_ftrace.o = -pg CFLAGS_REMOVE_early_printk.o = -pg CFLAGS_REMOVE_head64.o = -pg +CFLAGS_REMOVE_head32.o = -pg CFLAGS_REMOVE_sev.o = -pg CFLAGS_REMOVE_rethook.o = -pg endif diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 2a0ea38955df..d0918a75cb00 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -148,6 +148,9 @@ static int __init acpi_parse_madt(struct acpi_table_header *table) pr_debug("Local APIC address 0x%08x\n", madt->address); } + if (madt->flags & ACPI_MADT_PCAT_COMPAT) + legacy_pic_pcat_compat(); + /* ACPI 6.3 and newer support the online capable bit. */ if (acpi_gbl_FADT.header.revision > 6 || (acpi_gbl_FADT.header.revision == 6 && @@ -359,7 +362,7 @@ acpi_parse_lapic_nmi(union acpi_subtable_headers * header, const unsigned long e } #ifdef CONFIG_X86_64 -static int acpi_wakeup_cpu(int apicid, unsigned long start_ip) +static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip) { /* * Remap mailbox memory only for the first call to acpi_wakeup_cpu(). @@ -856,7 +859,7 @@ int acpi_unmap_cpu(int cpu) set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE); #endif - per_cpu(x86_cpu_to_apicid, cpu) = -1; + per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID; set_cpu_present(cpu, false); num_processors--; diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 517ee01503be..73be3931e4f0 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -403,6 +403,17 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, u8 insn_buff[MAX_PATCH_LEN]; DPRINTK(ALT, "alt table %px, -> %px", start, end); + + /* + * In the case CONFIG_X86_5LEVEL=y, KASAN_SHADOW_START is defined using + * cpu_feature_enabled(X86_FEATURE_LA57) and is therefore patched here. + * During the process, KASAN becomes confused seeing partial LA57 + * conversion and triggers a false-positive out-of-bound report. + * + * Disable KASAN until the patching is complete. + */ + kasan_disable_current(); + /* * The scan order should be from start to end. A later scanned * alternative code can overwrite previously scanned alternative code. @@ -452,6 +463,8 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, text_poke_early(instr, insn_buff, insn_buff_sz); } + + kasan_enable_current(); } static inline bool is_jcc32(struct insn *insn) diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 356de955e78d..053f6dcc6b2c 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -27,6 +27,7 @@ #define PCI_DEVICE_ID_AMD_1AH_M00H_ROOT 0x153a #define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507 #define PCI_DEVICE_ID_AMD_MI200_ROOT 0x14bb +#define PCI_DEVICE_ID_AMD_MI300_ROOT 0x14f8 #define PCI_DEVICE_ID_AMD_17H_DF_F4 0x1464 #define PCI_DEVICE_ID_AMD_17H_M10H_DF_F4 0x15ec @@ -43,6 +44,7 @@ #define PCI_DEVICE_ID_AMD_19H_M78H_DF_F4 0x12fc #define PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4 0x12c4 #define PCI_DEVICE_ID_AMD_MI200_DF_F4 0x14d4 +#define PCI_DEVICE_ID_AMD_MI300_DF_F4 0x152c /* Protect the PCI config register pairs used for SMN. */ static DEFINE_MUTEX(smn_mutex); @@ -62,6 +64,7 @@ static const struct pci_device_id amd_root_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_ROOT) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_ROOT) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_ROOT) }, {} }; @@ -93,6 +96,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { 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_MI200_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F3) }, {} }; @@ -112,9 +116,13 @@ static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M10H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M40H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M50H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M60H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M70H_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CNB17H_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F4) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F4) }, {} }; @@ -386,7 +394,7 @@ int amd_get_subcaches(int cpu) pci_read_config_dword(link, 0x1d4, &mask); - return (mask >> (4 * cpu_data(cpu).cpu_core_id)) & 0xf; + return (mask >> (4 * cpu_data(cpu).topo.core_id)) & 0xf; } int amd_set_subcaches(int cpu, unsigned long mask) @@ -412,7 +420,7 @@ int amd_set_subcaches(int cpu, unsigned long mask) pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000); } - cuid = cpu_data(cpu).cpu_core_id; + cuid = cpu_data(cpu).topo.core_id; mask <<= 4 * cuid; mask |= (0xf ^ (1 << cuid)) << 26; diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 760adac3d1a8..41093cf20acd 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -36,6 +36,8 @@ #include <linux/smp.h> #include <linux/mm.h> +#include <xen/xen.h> + #include <asm/trace/irq_vectors.h> #include <asm/irq_remapping.h> #include <asm/pc-conf-reg.h> @@ -70,7 +72,7 @@ unsigned int num_processors; unsigned disabled_cpus; /* Processor that is doing the boot up */ -unsigned int boot_cpu_physical_apicid __ro_after_init = -1U; +u32 boot_cpu_physical_apicid __ro_after_init = BAD_APICID; EXPORT_SYMBOL_GPL(boot_cpu_physical_apicid); u8 boot_cpu_apic_version __ro_after_init; @@ -85,7 +87,7 @@ physid_mask_t phys_cpu_present_map; * disable_cpu_apicid=<int>, mostly used for the kdump 2nd kernel to * avoid undefined behaviour caused by sending INIT from AP to BSP. */ -static unsigned int disabled_cpu_apicid __ro_after_init = BAD_APICID; +static u32 disabled_cpu_apicid __ro_after_init = BAD_APICID; /* * This variable controls which CPUs receive external NMIs. By default, @@ -109,7 +111,7 @@ static inline bool apic_accessible(void) /* * Map cpu index to physical APIC ID */ -DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID); +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); @@ -1763,7 +1765,7 @@ static void __x2apic_enable(void) static int __init setup_nox2apic(char *str) { if (x2apic_enabled()) { - int apicid = native_apic_msr_read(APIC_ID); + u32 apicid = native_apic_msr_read(APIC_ID); if (apicid >= 255) { pr_warn("Apicid: %08x, cannot enforce nox2apic\n", @@ -2316,13 +2318,11 @@ static int nr_logical_cpuids = 1; /* * Used to store mapping between logical CPU IDs and APIC IDs. */ -int cpuid_to_apicid[] = { - [0 ... NR_CPUS - 1] = -1, -}; +u32 cpuid_to_apicid[] = { [0 ... NR_CPUS - 1] = BAD_APICID, }; bool arch_match_cpu_phys_id(int cpu, u64 phys_id) { - return phys_id == cpuid_to_apicid[cpu]; + return phys_id == (u64)cpuid_to_apicid[cpu]; } #ifdef CONFIG_SMP @@ -2344,6 +2344,15 @@ 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; @@ -2382,7 +2391,7 @@ static int allocate_logical_cpuid(int apicid) return nr_logical_cpuids++; } -static void cpu_update_apic(int cpu, int apicid) +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; @@ -2535,7 +2544,7 @@ static struct { */ int active; /* r/w apic fields */ - unsigned int apic_id; + u32 apic_id; unsigned int apic_taskpri; unsigned int apic_ldr; unsigned int apic_dfr; diff --git a/arch/x86/kernel/apic/apic_common.c b/arch/x86/kernel/apic/apic_common.c index 7bc5d9bf59cd..8a00141073ea 100644 --- a/arch/x86/kernel/apic/apic_common.c +++ b/arch/x86/kernel/apic/apic_common.c @@ -18,7 +18,7 @@ u32 apic_flat_calc_apicid(unsigned int cpu) return 1U << cpu; } -bool default_check_apicid_used(physid_mask_t *map, int apicid) +bool default_check_apicid_used(physid_mask_t *map, u32 apicid) { return physid_isset(apicid, *map); } @@ -28,7 +28,7 @@ void default_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *retmap) *retmap = *phys_map; } -int default_cpu_present_to_apicid(int mps_cpu) +u32 default_cpu_present_to_apicid(int mps_cpu) { if (mps_cpu < nr_cpu_ids && cpu_present(mps_cpu)) return (int)per_cpu(x86_cpu_to_apicid, mps_cpu); diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 032a84e2c3cc..7139867d69cd 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -56,17 +56,17 @@ flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) _flat_send_IPI_mask(mask, vector); } -static unsigned int flat_get_apic_id(unsigned long x) +static u32 flat_get_apic_id(u32 x) { return (x >> 24) & 0xFF; } -static u32 set_apic_id(unsigned int id) +static u32 set_apic_id(u32 id) { return (id & 0xFF) << 24; } -static int flat_phys_pkg_id(int initial_apic_id, int index_msb) +static u32 flat_phys_pkg_id(u32 initial_apic_id, int index_msb) { return initial_apic_id >> index_msb; } @@ -103,6 +103,7 @@ static struct apic apic_flat __ro_after_init = { .send_IPI_allbutself = default_send_IPI_allbutself, .send_IPI_all = default_send_IPI_all, .send_IPI_self = default_send_IPI_self, + .nmi_to_offline_cpu = true, .read = native_apic_mem_read, .write = native_apic_mem_write, @@ -158,8 +159,6 @@ static struct apic apic_physflat __ro_after_init = { .disable_esr = 0, - .check_apicid_used = NULL, - .ioapic_phys_id_map = NULL, .cpu_present_to_apicid = default_cpu_present_to_apicid, .phys_pkg_id = flat_phys_pkg_id, @@ -175,6 +174,7 @@ static struct apic apic_physflat __ro_after_init = { .send_IPI_allbutself = default_send_IPI_allbutself, .send_IPI_all = default_send_IPI_all, .send_IPI_self = default_send_IPI_self, + .nmi_to_offline_cpu = true, .read = native_apic_mem_read, .write = native_apic_mem_write, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index 966d7cf10b95..b00d52ae84fa 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -18,6 +18,8 @@ #include <asm/apic.h> +#include "local.h" + static void noop_send_IPI(int cpu, int vector) { } static void noop_send_IPI_mask(const struct cpumask *cpumask, int vector) { } static void noop_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector) { } @@ -25,10 +27,10 @@ static void noop_send_IPI_allbutself(int vector) { } static void noop_send_IPI_all(int vector) { } static void noop_send_IPI_self(int vector) { } static void noop_apic_icr_write(u32 low, u32 id) { } -static int noop_wakeup_secondary_cpu(int apicid, unsigned long start_eip) { return -1; } +static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { return -1; } static u64 noop_apic_icr_read(void) { return 0; } -static int noop_phys_pkg_id(int cpuid_apic, int index_msb) { return 0; } -static unsigned int noop_get_apic_id(unsigned long x) { 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) { } static u32 noop_apic_read(u32 reg) diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 63f3d7be9dc7..456a14c44f67 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -25,7 +25,7 @@ static const struct apic apic_numachip1; static const struct apic apic_numachip2; static void (*numachip_apic_icr_write)(int apicid, unsigned int val) __read_mostly; -static unsigned int numachip1_get_apic_id(unsigned long x) +static u32 numachip1_get_apic_id(u32 x) { unsigned long value; unsigned int id = (x >> 24) & 0xff; @@ -38,12 +38,12 @@ static unsigned int numachip1_get_apic_id(unsigned long x) return id; } -static u32 numachip1_set_apic_id(unsigned int id) +static u32 numachip1_set_apic_id(u32 id) { return (id & 0xff) << 24; } -static unsigned int numachip2_get_apic_id(unsigned long x) +static u32 numachip2_get_apic_id(u32 x) { u64 mcfg; @@ -51,12 +51,12 @@ static unsigned int numachip2_get_apic_id(unsigned long x) return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24); } -static u32 numachip2_set_apic_id(unsigned int id) +static u32 numachip2_set_apic_id(u32 id) { return id << 24; } -static int numachip_phys_pkg_id(int initial_apic_id, int index_msb) +static u32 numachip_phys_pkg_id(u32 initial_apic_id, int index_msb) { return initial_apic_id >> index_msb; } @@ -71,7 +71,7 @@ static void numachip2_apic_icr_write(int apicid, unsigned int val) numachip2_write32_lcsr(NUMACHIP2_APIC_ICR, (apicid << 12) | val); } -static int numachip_wakeup_secondary(int phys_apicid, unsigned long start_rip) +static int numachip_wakeup_secondary(u32 phys_apicid, unsigned long start_rip) { numachip_apic_icr_write(phys_apicid, APIC_DM_INIT); numachip_apic_icr_write(phys_apicid, APIC_DM_STARTUP | @@ -161,7 +161,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) u64 val; u32 nodes = 1; - this_cpu_write(cpu_llc_id, node); + c->topo.llc_id = node; /* Account for nodes per socket in multi-core-module processors */ if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) { @@ -169,7 +169,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node) nodes = ((val >> 3) & 7) + 1; } - c->phys_proc_id = node / nodes; + c->topo.pkg_id = node / nodes; } static int __init numachip_system_init(void) diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 0e5535add4b5..7ee3c486cb33 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -13,12 +13,12 @@ #include "local.h" -static unsigned bigsmp_get_apic_id(unsigned long x) +static u32 bigsmp_get_apic_id(u32 x) { return (x >> 24) & 0xFF; } -static bool bigsmp_check_apicid_used(physid_mask_t *map, int apicid) +static bool bigsmp_check_apicid_used(physid_mask_t *map, u32 apicid) { return false; } @@ -29,7 +29,7 @@ static void bigsmp_ioapic_phys_id_map(physid_mask_t *phys_map, physid_mask_t *re physids_promote(0xFFL, retmap); } -static int bigsmp_phys_pkg_id(int cpuid_apic, int index_msb) +static u32 bigsmp_phys_pkg_id(u32 cpuid_apic, int index_msb) { return cpuid_apic >> index_msb; } diff --git a/arch/x86/kernel/apic/ipi.c b/arch/x86/kernel/apic/ipi.c index a44ba7209ef3..5da693d633b7 100644 --- a/arch/x86/kernel/apic/ipi.c +++ b/arch/x86/kernel/apic/ipi.c @@ -97,6 +97,14 @@ sendmask: __apic_send_IPI_mask(mask, CALL_FUNCTION_VECTOR); } +void apic_send_nmi_to_offline_cpu(unsigned int cpu) +{ + if (WARN_ON_ONCE(!apic->nmi_to_offline_cpu)) + return; + if (WARN_ON_ONCE(!cpumask_test_cpu(cpu, &cpus_booted_once_mask))) + return; + apic->send_IPI(cpu, NMI_VECTOR); +} #endif /* CONFIG_SMP */ static inline int __prepare_ICR2(unsigned int mask) @@ -281,7 +289,7 @@ void default_send_IPI_mask_logical(const struct cpumask *cpumask, int vector) } #ifdef CONFIG_SMP -static int convert_apicid_to_cpu(int apic_id) +static int convert_apicid_to_cpu(u32 apic_id) { int i; @@ -294,7 +302,8 @@ static int convert_apicid_to_cpu(int apic_id) int safe_smp_processor_id(void) { - int apicid, cpuid; + u32 apicid; + int cpuid; if (!boot_cpu_has(X86_FEATURE_APIC)) return 0; diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h index ec219c659c7d..9ea6186ea88c 100644 --- a/arch/x86/kernel/apic/local.h +++ b/arch/x86/kernel/apic/local.h @@ -15,9 +15,9 @@ /* X2APIC */ void __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest); -unsigned int x2apic_get_apic_id(unsigned long id); -u32 x2apic_set_apic_id(unsigned int id); -int x2apic_phys_pkg_id(int initial_apicid, int index_msb); +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); @@ -64,6 +64,7 @@ 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); diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c index 6b6b711678fe..d9651f15ae4f 100644 --- a/arch/x86/kernel/apic/msi.c +++ b/arch/x86/kernel/apic/msi.c @@ -55,14 +55,14 @@ msi_set_affinity(struct irq_data *irqd, const struct cpumask *mask, bool force) * caused by the non-atomic update of the address/data pair. * * Direct update is possible when: - * - The MSI is maskable (remapped MSI does not use this code path)). - * The quirk bit is not set in this case. + * - The MSI is maskable (remapped MSI does not use this code path). + * The reservation mode bit is set in this case. * - The new vector is the same as the old vector * - The old vector is MANAGED_IRQ_SHUTDOWN_VECTOR (interrupt starts up) * - The interrupt is not yet started up * - The new destination CPU is the same as the old destination CPU */ - if (!irqd_msi_nomask_quirk(irqd) || + if (!irqd_can_reserve(irqd) || cfg->vector == old_cfg.vector || old_cfg.vector == MANAGED_IRQ_SHUTDOWN_VECTOR || !irqd_is_started(irqd) || @@ -215,8 +215,6 @@ static bool x86_init_dev_msi_info(struct device *dev, struct irq_domain *domain, if (WARN_ON_ONCE(domain != real_parent)) return false; info->chip->irq_set_affinity = msi_set_affinity; - /* See msi_set_affinity() for the gory details */ - info->flags |= MSI_FLAG_NOMASK_QUIRK; break; case DOMAIN_BUS_DMAR: case DOMAIN_BUS_AMDVI: diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 9a06df6cdd68..5eb3fbe472da 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -18,11 +18,21 @@ #include "local.h" -static int default_phys_pkg_id(int cpuid_apic, int index_msb) +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)); + + if (APIC_XAPIC(ver) || boot_cpu_has(X86_FEATURE_EXTD_APICID)) + return (x >> 24) & 0xFF; + else + return (x >> 24) & 0x0F; +} + /* should be called last. */ static int probe_default(void) { diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index affbff65e497..a8306089c91b 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -251,6 +251,7 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .send_IPI_allbutself = x2apic_send_IPI_allbutself, .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, + .nmi_to_offline_cpu = true, .read = native_apic_msr_read, .write = native_apic_msr_write, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 788cdb4ee394..558a4a8824f4 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -124,17 +124,17 @@ static int x2apic_phys_probe(void) return apic == &apic_x2apic_phys; } -unsigned int x2apic_get_apic_id(unsigned long id) +u32 x2apic_get_apic_id(u32 id) { return id; } -u32 x2apic_set_apic_id(unsigned int id) +u32 x2apic_set_apic_id(u32 id) { return id; } -int x2apic_phys_pkg_id(int initial_apicid, int index_msb) +u32 x2apic_phys_pkg_id(u32 initial_apicid, int index_msb) { return initial_apicid >> index_msb; } @@ -166,6 +166,7 @@ static struct apic apic_x2apic_phys __ro_after_init = { .send_IPI_allbutself = x2apic_send_IPI_allbutself, .send_IPI_all = x2apic_send_IPI_all, .send_IPI_self = x2apic_send_IPI_self, + .nmi_to_offline_cpu = true, .read = native_apic_msr_read, .write = native_apic_msr_write, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 205cee567629..1b0d7336a28f 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -110,7 +110,7 @@ static void __init early_get_pnodeid(void) } else if (UVH_RH_GAM_ADDR_MAP_CONFIG) { union uvh_rh_gam_addr_map_config_u m_n_config; - m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_ADDR_MAP_CONFIG); + m_n_config.v = uv_early_read_mmr(UVH_RH_GAM_ADDR_MAP_CONFIG); uv_cpuid.n_skt = m_n_config.s.n_skt; if (is_uv(UV3)) uv_cpuid.m_skt = m_n_config.s3.m_skt; @@ -701,7 +701,7 @@ static __init void build_uv_gr_table(void) } } -static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip) +static int uv_wakeup_secondary(u32 phys_apicid, unsigned long start_rip) { unsigned long val; int pnode; @@ -779,7 +779,7 @@ static void uv_send_IPI_all(int vector) uv_send_IPI_mask(cpu_online_mask, vector); } -static u32 set_apic_id(unsigned int id) +static u32 set_apic_id(u32 id) { return id; } @@ -789,7 +789,7 @@ static unsigned int uv_read_apic_id(void) return x2apic_get_apic_id(apic_read(APIC_ID)); } -static int uv_phys_pkg_id(int initial_apicid, int index_msb) +static u32 uv_phys_pkg_id(u32 initial_apicid, int index_msb) { return uv_read_apic_id() >> index_msb; } diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c index dc3576303f1a..6913b372ccf7 100644 --- a/arch/x86/kernel/asm-offsets.c +++ b/arch/x86/kernel/asm-offsets.c @@ -68,26 +68,19 @@ static void __used common(void) #endif BLANK(); - OFFSET(TDX_MODULE_rcx, tdx_module_output, rcx); - OFFSET(TDX_MODULE_rdx, tdx_module_output, rdx); - OFFSET(TDX_MODULE_r8, tdx_module_output, r8); - OFFSET(TDX_MODULE_r9, tdx_module_output, r9); - OFFSET(TDX_MODULE_r10, tdx_module_output, r10); - OFFSET(TDX_MODULE_r11, tdx_module_output, r11); - - BLANK(); - OFFSET(TDX_HYPERCALL_r8, tdx_hypercall_args, r8); - OFFSET(TDX_HYPERCALL_r9, tdx_hypercall_args, r9); - OFFSET(TDX_HYPERCALL_r10, tdx_hypercall_args, r10); - OFFSET(TDX_HYPERCALL_r11, tdx_hypercall_args, r11); - OFFSET(TDX_HYPERCALL_r12, tdx_hypercall_args, r12); - OFFSET(TDX_HYPERCALL_r13, tdx_hypercall_args, r13); - OFFSET(TDX_HYPERCALL_r14, tdx_hypercall_args, r14); - OFFSET(TDX_HYPERCALL_r15, tdx_hypercall_args, r15); - OFFSET(TDX_HYPERCALL_rdi, tdx_hypercall_args, rdi); - OFFSET(TDX_HYPERCALL_rsi, tdx_hypercall_args, rsi); - OFFSET(TDX_HYPERCALL_rbx, tdx_hypercall_args, rbx); - OFFSET(TDX_HYPERCALL_rdx, tdx_hypercall_args, rdx); + OFFSET(TDX_MODULE_rcx, tdx_module_args, rcx); + OFFSET(TDX_MODULE_rdx, tdx_module_args, rdx); + OFFSET(TDX_MODULE_r8, tdx_module_args, r8); + OFFSET(TDX_MODULE_r9, tdx_module_args, r9); + OFFSET(TDX_MODULE_r10, tdx_module_args, r10); + OFFSET(TDX_MODULE_r11, tdx_module_args, r11); + OFFSET(TDX_MODULE_r12, tdx_module_args, r12); + OFFSET(TDX_MODULE_r13, tdx_module_args, r13); + OFFSET(TDX_MODULE_r14, tdx_module_args, r14); + OFFSET(TDX_MODULE_r15, tdx_module_args, r15); + OFFSET(TDX_MODULE_rbx, tdx_module_args, rbx); + OFFSET(TDX_MODULE_rdi, tdx_module_args, rdi); + OFFSET(TDX_MODULE_rsi, tdx_module_args, rsi); BLANK(); OFFSET(BP_scratch, boot_params, scratch); diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index faa9f2299848..e9ad518a5003 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -48,11 +48,6 @@ EXPORT_SYMBOL_GPL(__x86_call_count); extern s32 __call_sites[], __call_sites_end[]; -struct thunk_desc { - void *template; - unsigned int template_size; -}; - struct core_text { unsigned long base; unsigned long end; diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index 4350f6bfc064..93eabf544031 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -54,6 +54,8 @@ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o obj-$(CONFIG_HYPERVISOR_GUEST) += vmware.o hypervisor.o mshyperv.o obj-$(CONFIG_ACRN_GUEST) += acrn.o +obj-$(CONFIG_DEBUG_FS) += debugfs.o + quiet_cmd_mkcapflags = MKCAP $@ cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $@ $^ diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 03ef962a6992..a7eab05e5f29 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -80,6 +80,10 @@ static const int amd_div0[] = AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf), AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf)); +static const int amd_erratum_1485[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf), + AMD_MODEL_RANGE(0x19, 0x60, 0x0, 0xaf, 0xf)); + static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { int osvw_id = *erratum++; @@ -378,7 +382,7 @@ static int nearby_node(int apicid) #endif /* - * Fix up cpu_core_id for pre-F17h systems to be in the + * 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. */ @@ -390,7 +394,7 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c) return; cus_per_node = c->x86_max_cores / nodes_per_socket; - c->cpu_core_id %= cus_per_node; + c->topo.core_id %= cus_per_node; } /* @@ -401,8 +405,6 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c) */ static void amd_get_topology(struct cpuinfo_x86 *c) { - int cpu = smp_processor_id(); - /* get information required for multi-node processors */ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { int err; @@ -410,13 +412,13 @@ static void amd_get_topology(struct cpuinfo_x86 *c) cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - c->cpu_die_id = ecx & 0xff; + c->topo.die_id = ecx & 0xff; if (c->x86 == 0x15) - c->cu_id = ebx & 0xff; + c->topo.cu_id = ebx & 0xff; if (c->x86 >= 0x17) { - c->cpu_core_id = ebx & 0xff; + c->topo.core_id = ebx & 0xff; if (smp_num_siblings > 1) c->x86_max_cores /= smp_num_siblings; @@ -430,15 +432,14 @@ static void amd_get_topology(struct cpuinfo_x86 *c) if (!err) c->x86_coreid_bits = get_count_order(c->x86_max_cores); - cacheinfo_amd_init_llc_id(c, cpu); + cacheinfo_amd_init_llc_id(c); } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - c->cpu_die_id = value & 7; - - per_cpu(cpu_llc_id, cpu) = c->cpu_die_id; + c->topo.die_id = value & 7; + c->topo.llc_id = c->topo.die_id; } else return; @@ -455,15 +456,14 @@ static void amd_get_topology(struct cpuinfo_x86 *c) static void amd_detect_cmp(struct cpuinfo_x86 *c) { unsigned bits; - int cpu = smp_processor_id(); bits = c->x86_coreid_bits; /* Low order bits define the core id (index of core in socket) */ - c->cpu_core_id = c->initial_apicid & ((1 << bits)-1); + c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1); /* Convert the initial APIC ID into the socket ID */ - c->phys_proc_id = c->initial_apicid >> bits; + c->topo.pkg_id = c->topo.initial_apicid >> bits; /* use socket ID also for last level cache */ - per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_id; + c->topo.llc_id = c->topo.die_id = c->topo.pkg_id; } u32 amd_get_nodes_per_socket(void) @@ -477,11 +477,11 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #ifdef CONFIG_NUMA int cpu = smp_processor_id(); int node; - unsigned apicid = c->apicid; + unsigned apicid = c->topo.apicid; node = numa_cpu_node(cpu); if (node == NUMA_NO_NODE) - node = get_llc_id(cpu); + node = per_cpu_llc_id(cpu); /* * On multi-fabric platform (e.g. Numascale NumaChip) a @@ -511,7 +511,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c) * through CPU mapping may alter the outcome, directly * access __apicid_to_node[]. */ - int ht_nodeid = c->initial_apicid; + int ht_nodeid = c->topo.initial_apicid; if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE) node = __apicid_to_node[ht_nodeid]; @@ -1010,7 +1010,6 @@ static bool cpu_has_zenbleed_microcode(void) default: return false; - break; } if (boot_cpu_data.microcode < good_rev) @@ -1040,6 +1039,8 @@ static void zenbleed_check(struct cpuinfo_x86 *c) static void init_amd(struct cpuinfo_x86 *c) { + u64 vm_cr; + early_init_amd(c); /* @@ -1056,7 +1057,7 @@ static void init_amd(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_FSRS); /* get apicid instead of initial apic id from cpuid */ - c->apicid = read_apic_id(); + c->topo.apicid = read_apic_id(); /* K6s reports MCEs but don't actually have all the MSRs */ if (c->x86 < 6) @@ -1091,6 +1092,14 @@ static void init_amd(struct cpuinfo_x86 *c) init_amd_cacheinfo(c); + if (cpu_has(c, X86_FEATURE_SVM)) { + rdmsrl(MSR_VM_CR, vm_cr); + if (vm_cr & SVM_VM_CR_SVM_DIS_MASK) { + pr_notice_once("SVM disabled (by BIOS) in MSR_VM_CR\n"); + clear_cpu_cap(c, X86_FEATURE_SVM); + } + } + if (!cpu_has(c, X86_FEATURE_LFENCE_RDTSC) && cpu_has(c, X86_FEATURE_XMM2)) { /* * Use LFENCE for execution serialization. On families which @@ -1149,6 +1158,10 @@ static void init_amd(struct cpuinfo_x86 *c) pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); setup_force_cpu_bug(X86_BUG_DIV0); } + + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && + cpu_has_amd_erratum(c, amd_erratum_1485)) + msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 10499bcd4e39..bb0ab8466b91 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -63,7 +63,7 @@ EXPORT_SYMBOL_GPL(x86_pred_cmd); static DEFINE_MUTEX(spec_ctrl_mutex); -void (*x86_return_thunk)(void) __ro_after_init = &__x86_return_thunk; +void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; /* Update SPEC_CTRL MSR and its cached copy unconditionally */ static void update_spec_ctrl(u64 val) @@ -717,7 +717,7 @@ void update_gds_msr(void) case GDS_MITIGATION_UCODE_NEEDED: case GDS_MITIGATION_HYPERVISOR: return; - }; + } wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl); @@ -1019,7 +1019,6 @@ static void __init retbleed_select_mitigation(void) do_cmd_auto: case RETBLEED_CMD_AUTO: - default: if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) { if (IS_ENABLED(CONFIG_CPU_UNRET_ENTRY)) @@ -1042,8 +1041,7 @@ do_cmd_auto: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_UNRET); - if (IS_ENABLED(CONFIG_RETHUNK)) - x86_return_thunk = retbleed_return_thunk; + x86_return_thunk = retbleed_return_thunk; if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD && boot_cpu_data.x86_vendor != X86_VENDOR_HYGON) @@ -1061,7 +1059,8 @@ do_cmd_auto: case RETBLEED_MITIGATION_STUFF: setup_force_cpu_cap(X86_FEATURE_RETHUNK); setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH); - x86_set_skl_return_thunk(); + + x86_return_thunk = call_depth_return_thunk; break; default: @@ -1290,6 +1289,8 @@ spectre_v2_user_select_mitigation(void) spectre_v2_user_ibpb = mode; switch (cmd) { + case SPECTRE_V2_USER_CMD_NONE: + break; case SPECTRE_V2_USER_CMD_FORCE: case SPECTRE_V2_USER_CMD_PRCTL_IBPB: case SPECTRE_V2_USER_CMD_SECCOMP_IBPB: @@ -1301,8 +1302,6 @@ spectre_v2_user_select_mitigation(void) case SPECTRE_V2_USER_CMD_SECCOMP: static_branch_enable(&switch_mm_cond_ibpb); break; - default: - break; } pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n", @@ -2160,6 +2159,10 @@ static int l1d_flush_prctl_get(struct task_struct *task) static int ssb_prctl_get(struct task_struct *task) { switch (ssb_mode) { + case SPEC_STORE_BYPASS_NONE: + if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) + return PR_SPEC_ENABLE; + return PR_SPEC_NOT_AFFECTED; case SPEC_STORE_BYPASS_DISABLE: return PR_SPEC_DISABLE; case SPEC_STORE_BYPASS_SECCOMP: @@ -2171,11 +2174,8 @@ static int ssb_prctl_get(struct task_struct *task) if (task_spec_ssb_disable(task)) return PR_SPEC_PRCTL | PR_SPEC_DISABLE; return PR_SPEC_PRCTL | PR_SPEC_ENABLE; - default: - if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS)) - return PR_SPEC_ENABLE; - return PR_SPEC_NOT_AFFECTED; } + BUG(); } static int ib_prctl_get(struct task_struct *task) @@ -2353,6 +2353,8 @@ early_param("l1tf", l1tf_cmdline); enum srso_mitigation { SRSO_MITIGATION_NONE, + SRSO_MITIGATION_UCODE_NEEDED, + SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED, SRSO_MITIGATION_MICROCODE, SRSO_MITIGATION_SAFE_RET, SRSO_MITIGATION_IBPB, @@ -2368,11 +2370,13 @@ enum srso_mitigation_cmd { }; static const char * const srso_strings[] = { - [SRSO_MITIGATION_NONE] = "Vulnerable", - [SRSO_MITIGATION_MICROCODE] = "Mitigation: microcode", - [SRSO_MITIGATION_SAFE_RET] = "Mitigation: safe RET", - [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", - [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only" + [SRSO_MITIGATION_NONE] = "Vulnerable", + [SRSO_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode", + [SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED] = "Vulnerable: Safe RET, no microcode", + [SRSO_MITIGATION_MICROCODE] = "Vulnerable: Microcode, no safe RET", + [SRSO_MITIGATION_SAFE_RET] = "Mitigation: Safe RET", + [SRSO_MITIGATION_IBPB] = "Mitigation: IBPB", + [SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only" }; static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE; @@ -2406,34 +2410,44 @@ static void __init srso_select_mitigation(void) { bool has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE); - if (!boot_cpu_has_bug(X86_BUG_SRSO) || cpu_mitigations_off()) - goto pred_cmd; + if (cpu_mitigations_off()) + return; - if (!has_microcode) { - pr_warn("IBPB-extending microcode not applied!\n"); - pr_warn(SRSO_NOTICE); - } else { + if (!boot_cpu_has_bug(X86_BUG_SRSO)) { + if (boot_cpu_has(X86_FEATURE_SBPB)) + x86_pred_cmd = PRED_CMD_SBPB; + return; + } + + if (has_microcode) { /* * Zen1/2 with SMT off aren't vulnerable after the right * IBPB microcode has been applied. + * + * Zen1/2 don't have SBPB, no need to try to enable it here. */ if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) { setup_force_cpu_cap(X86_FEATURE_SRSO_NO); return; } - } - if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { - if (has_microcode) { - pr_err("Retbleed IBPB mitigation enabled, using same for SRSO\n"); + if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) { srso_mitigation = SRSO_MITIGATION_IBPB; - goto pred_cmd; + goto out; } + } else { + pr_warn("IBPB-extending microcode not applied!\n"); + pr_warn(SRSO_NOTICE); + + /* may be overwritten by SRSO_CMD_SAFE_RET below */ + srso_mitigation = SRSO_MITIGATION_UCODE_NEEDED; } switch (srso_cmd) { case SRSO_CMD_OFF: - goto pred_cmd; + if (boot_cpu_has(X86_FEATURE_SBPB)) + x86_pred_cmd = PRED_CMD_SBPB; + return; case SRSO_CMD_MICROCODE: if (has_microcode) { @@ -2458,10 +2472,12 @@ static void __init srso_select_mitigation(void) setup_force_cpu_cap(X86_FEATURE_SRSO); x86_return_thunk = srso_return_thunk; } - srso_mitigation = SRSO_MITIGATION_SAFE_RET; + if (has_microcode) + srso_mitigation = SRSO_MITIGATION_SAFE_RET; + else + srso_mitigation = SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED; } else { pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); - goto pred_cmd; } break; @@ -2473,7 +2489,6 @@ static void __init srso_select_mitigation(void) } } else { pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); - goto pred_cmd; } break; @@ -2485,20 +2500,12 @@ static void __init srso_select_mitigation(void) } } else { pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); - goto pred_cmd; } break; - - default: - break; } - pr_info("%s%s\n", srso_strings[srso_mitigation], (has_microcode ? "" : ", no microcode")); - -pred_cmd: - if ((boot_cpu_has(X86_FEATURE_SRSO_NO) || srso_cmd == SRSO_CMD_OFF) && - boot_cpu_has(X86_FEATURE_SBPB)) - x86_pred_cmd = PRED_CMD_SBPB; +out: + pr_info("%s\n", srso_strings[srso_mitigation]); } #undef pr_fmt @@ -2704,9 +2711,7 @@ static ssize_t srso_show_state(char *buf) if (boot_cpu_has(X86_FEATURE_SRSO_NO)) return sysfs_emit(buf, "Mitigation: SMT disabled\n"); - return sysfs_emit(buf, "%s%s\n", - srso_strings[srso_mitigation], - boot_cpu_has(X86_FEATURE_IBPB_BRTYPE) ? "" : ", no microcode"); + return sysfs_emit(buf, "%s\n", srso_strings[srso_mitigation]); } static ssize_t gds_show_state(char *buf) diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c index 8f86eacf69f7..c131c412db89 100644 --- a/arch/x86/kernel/cpu/cacheinfo.c +++ b/arch/x86/kernel/cpu/cacheinfo.c @@ -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, int cpu) +void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c) { /* * We may have multiple LLCs if L3 caches exist, so check if we @@ -672,13 +672,13 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu) if (c->x86 < 0x17) { /* LLC is at the node level. */ - per_cpu(cpu_llc_id, cpu) = c->cpu_die_id; + c->topo.llc_id = c->topo.die_id; } else if (c->x86 == 0x17 && c->x86_model <= 0x1F) { /* * LLC is at the core complex level. * Core complex ID is ApicId[3] for these processors. */ - per_cpu(cpu_llc_id, cpu) = c->apicid >> 3; + c->topo.llc_id = c->topo.apicid >> 3; } else { /* * LLC ID is calculated from the number of threads sharing the @@ -694,12 +694,12 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu) if (num_sharing_cache) { int bits = get_count_order(num_sharing_cache); - per_cpu(cpu_llc_id, cpu) = c->apicid >> bits; + c->topo.llc_id = c->topo.apicid >> bits; } } } -void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu) +void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c) { /* * We may have multiple LLCs if L3 caches exist, so check if we @@ -712,7 +712,7 @@ void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c, int cpu) * LLC is at the core complex level. * Core complex ID is ApicId[3] for these processors. */ - per_cpu(cpu_llc_id, cpu) = c->apicid >> 3; + c->topo.llc_id = c->topo.apicid >> 3; } void init_amd_cacheinfo(struct cpuinfo_x86 *c) @@ -740,9 +740,6 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c) unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */ unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */ unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb; -#ifdef CONFIG_SMP - unsigned int cpu = c->cpu_index; -#endif if (c->cpuid_level > 3) { static int is_initialized; @@ -776,13 +773,13 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c) new_l2 = this_leaf.size/1024; num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; index_msb = get_count_order(num_threads_sharing); - l2_id = c->apicid & ~((1 << index_msb) - 1); + l2_id = c->topo.apicid & ~((1 << index_msb) - 1); break; case 3: new_l3 = this_leaf.size/1024; num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; index_msb = get_count_order(num_threads_sharing); - l3_id = c->apicid & ~((1 << index_msb) - 1); + l3_id = c->topo.apicid & ~((1 << index_msb) - 1); break; default: break; @@ -856,30 +853,24 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c) if (new_l2) { l2 = new_l2; -#ifdef CONFIG_SMP - per_cpu(cpu_llc_id, cpu) = l2_id; - per_cpu(cpu_l2c_id, cpu) = l2_id; -#endif + c->topo.llc_id = l2_id; + c->topo.l2c_id = l2_id; } if (new_l3) { l3 = new_l3; -#ifdef CONFIG_SMP - per_cpu(cpu_llc_id, cpu) = l3_id; -#endif + c->topo.llc_id = l3_id; } -#ifdef CONFIG_SMP /* - * If cpu_llc_id is not yet set, this means cpuid_level < 4 which in + * If llc_id is not yet set, this means cpuid_level < 4 which in * turns means that the only possibility is SMT (as indicated in * cpuid1). Since cpuid2 doesn't specify shared caches, and we know * that SMT shares all caches, we can unconditionally set cpu_llc_id to - * c->phys_proc_id. + * c->topo.pkg_id. */ - if (per_cpu(cpu_llc_id, cpu) == BAD_APICID) - per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; -#endif + if (c->topo.llc_id == BAD_APICID) + c->topo.llc_id = c->topo.pkg_id; c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d)); @@ -915,7 +906,7 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, unsigned int apicid, nshared, first, last; nshared = base->eax.split.num_threads_sharing + 1; - apicid = cpu_data(cpu).apicid; + apicid = cpu_data(cpu).topo.apicid; first = apicid - (apicid % nshared); last = first + nshared - 1; @@ -924,14 +915,14 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index, if (!this_cpu_ci->info_list) continue; - apicid = cpu_data(i).apicid; + apicid = cpu_data(i).topo.apicid; if ((apicid < first) || (apicid > last)) continue; this_leaf = this_cpu_ci->info_list + index; for_each_online_cpu(sibling) { - apicid = cpu_data(sibling).apicid; + apicid = cpu_data(sibling).topo.apicid; if ((apicid < first) || (apicid > last)) continue; cpumask_set_cpu(sibling, @@ -969,7 +960,7 @@ static void __cache_cpumap_setup(unsigned int cpu, int index, index_msb = get_count_order(num_threads_sharing); for_each_online_cpu(i) - if (cpu_data(i).apicid >> index_msb == c->apicid >> index_msb) { + if (cpu_data(i).topo.apicid >> index_msb == c->topo.apicid >> index_msb) { struct cpu_cacheinfo *sib_cpu_ci = get_cpu_cacheinfo(i); if (i == cpu || !sib_cpu_ci->info_list) @@ -1024,7 +1015,7 @@ static void get_cache_id(int cpu, struct _cpuid4_info_regs *id4_regs) num_threads_sharing = 1 + id4_regs->eax.split.num_threads_sharing; index_msb = get_count_order(num_threads_sharing); - id4_regs->id = c->apicid >> index_msb; + id4_regs->id = c->topo.apicid >> index_msb; } int populate_cache_leaves(unsigned int cpu) diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 382d4e6b848d..b14fc8c1c953 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -62,6 +62,7 @@ #include <asm/intel-family.h> #include <asm/cpu_device_id.h> #include <asm/uv/uv.h> +#include <asm/ia32.h> #include <asm/set_memory.h> #include <asm/traps.h> #include <asm/sev.h> @@ -74,18 +75,6 @@ u32 elf_hwcap2 __read_mostly; int smp_num_siblings = 1; EXPORT_SYMBOL(smp_num_siblings); -/* Last level cache ID of each logical CPU */ -DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID; - -u16 get_llc_id(unsigned int cpu) -{ - return per_cpu(cpu_llc_id, cpu); -} -EXPORT_SYMBOL_GPL(get_llc_id); - -/* L2 cache ID of each logical CPU */ -DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_l2c_id) = BAD_APICID; - static struct ppin_info { int feature; int msr_ppin_ctl; @@ -914,7 +903,7 @@ void detect_ht(struct cpuinfo_x86 *c) return; index_msb = get_count_order(smp_num_siblings); - c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb); + c->topo.pkg_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb); smp_num_siblings = smp_num_siblings / c->x86_max_cores; @@ -922,8 +911,8 @@ void detect_ht(struct cpuinfo_x86 *c) core_bits = get_count_order(c->x86_max_cores); - c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) & - ((1 << core_bits) - 1); + c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid, index_msb) & + ((1 << core_bits) - 1); #endif } @@ -1114,18 +1103,34 @@ 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 (c->extended_cpuid_level >= 0x80000008) { + 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 { + if (IS_ENABLED(CONFIG_X86_64)) { + c->x86_clflush_size = 64; + c->x86_phys_bits = 36; + c->x86_virt_bits = 48; + } else { + c->x86_clflush_size = 32; + c->x86_virt_bits = 32; + c->x86_phys_bits = 32; + + if (cpu_has(c, X86_FEATURE_PAE) || + cpu_has(c, X86_FEATURE_PSE36)) + c->x86_phys_bits = 36; + } } -#ifdef CONFIG_X86_32 - else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) - c->x86_phys_bits = 36; -#endif c->x86_cache_bits = c->x86_phys_bits; + c->x86_cache_alignment = c->x86_clflush_size; } static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) @@ -1303,7 +1308,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = { VULNBL_AMD(0x15, RETBLEED), VULNBL_AMD(0x16, RETBLEED), VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO), - VULNBL_HYGON(0x18, RETBLEED | SMT_RSB), + VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO), VULNBL_AMD(0x19, SRSO), {} }; @@ -1579,17 +1584,6 @@ static void __init cpu_parse_early_param(void) */ static void __init early_identify_cpu(struct cpuinfo_x86 *c) { -#ifdef CONFIG_X86_64 - c->x86_clflush_size = 64; - c->x86_phys_bits = 36; - c->x86_virt_bits = 48; -#else - c->x86_clflush_size = 32; - c->x86_phys_bits = 32; - c->x86_virt_bits = 32; -#endif - c->x86_cache_alignment = c->x86_clflush_size; - memset(&c->x86_capability, 0, sizeof(c->x86_capability)); c->extended_cpuid_level = 0; @@ -1601,7 +1595,6 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) cpu_detect(c); get_cpu_vendor(c); get_cpu_cap(c); - get_cpu_address_sizes(c); setup_force_cpu_cap(X86_FEATURE_CPUID); cpu_parse_early_param(); @@ -1617,6 +1610,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_CPUID); } + get_cpu_address_sizes(c); + setup_force_cpu_cap(X86_FEATURE_ALWAYS); cpu_set_bug_bits(c); @@ -1761,15 +1756,15 @@ static void generic_identify(struct cpuinfo_x86 *c) get_cpu_address_sizes(c); if (c->cpuid_level >= 0x00000001) { - c->initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF; + c->topo.initial_apicid = (cpuid_ebx(1) >> 24) & 0xFF; #ifdef CONFIG_X86_32 # ifdef CONFIG_SMP - c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); + c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0); # else - c->apicid = c->initial_apicid; + c->topo.apicid = c->topo.initial_apicid; # endif #endif - c->phys_proc_id = c->initial_apicid; + c->topo.pkg_id = c->topo.initial_apicid; } get_model_name(c); /* Default name */ @@ -1799,18 +1794,19 @@ static void generic_identify(struct cpuinfo_x86 *c) static void validate_apic_and_package_id(struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP - unsigned int apicid, cpu = smp_processor_id(); + unsigned int cpu = smp_processor_id(); + u32 apicid; apicid = apic->cpu_present_to_apicid(cpu); - if (apicid != c->apicid) { + if (apicid != c->topo.apicid) { pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x APIC: %x\n", - cpu, apicid, c->initial_apicid); + cpu, apicid, c->topo.initial_apicid); } - BUG_ON(topology_update_package_map(c->phys_proc_id, cpu)); - BUG_ON(topology_update_die_map(c->cpu_die_id, cpu)); + BUG_ON(topology_update_package_map(c->topo.pkg_id, cpu)); + BUG_ON(topology_update_die_map(c->topo.die_id, cpu)); #else - c->logical_proc_id = 0; + c->topo.logical_pkg_id = 0; #endif } @@ -1829,7 +1825,9 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->x86_model_id[0] = '\0'; /* Unset */ c->x86_max_cores = 1; c->x86_coreid_bits = 0; - c->cu_id = 0xff; + 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; @@ -1855,7 +1853,7 @@ static void identify_cpu(struct cpuinfo_x86 *c) apply_forced_caps(c); #ifdef CONFIG_X86_64 - c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); + c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0); #endif /* @@ -2074,24 +2072,24 @@ void syscall_init(void) wrmsr(MSR_STAR, 0, (__USER32_CS << 16) | __KERNEL_CS); wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64); -#ifdef CONFIG_IA32_EMULATION - wrmsrl_cstar((unsigned long)entry_SYSCALL_compat); - /* - * This only works on Intel CPUs. - * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP. - * This does not cause SYSENTER to jump to the wrong location, because - * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit). - */ - wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, - (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1)); - wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); -#else - wrmsrl_cstar((unsigned long)ignore_sysret); - wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG); - wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); - wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL); -#endif + if (ia32_enabled()) { + wrmsrl_cstar((unsigned long)entry_SYSCALL_compat); + /* + * This only works on Intel CPUs. + * On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP. + * This does not cause SYSENTER to jump to the wrong location, because + * AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit). + */ + wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, + (unsigned long)(cpu_entry_stack(smp_processor_id()) + 1)); + wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat); + } else { + wrmsrl_cstar((unsigned long)entry_SYSCALL32_ignore); + wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG); + wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL); + wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL); + } /* * Flags to clear on syscall; clear as much as possible @@ -2166,8 +2164,6 @@ static inline void setup_getcpu(int cpu) } #ifdef CONFIG_X86_64 -static inline void ucode_cpu_init(int cpu) { } - static inline void tss_setup_ist(struct tss_struct *tss) { /* Set up the per-CPU TSS IST stacks */ @@ -2178,16 +2174,8 @@ static inline void tss_setup_ist(struct tss_struct *tss) /* Only mapped when SEV-ES is active */ tss->x86_tss.ist[IST_INDEX_VC] = __this_cpu_ist_top_va(VC); } - #else /* CONFIG_X86_64 */ - -static inline void ucode_cpu_init(int cpu) -{ - show_ucode_info_early(); -} - static inline void tss_setup_ist(struct tss_struct *tss) { } - #endif /* !CONFIG_X86_64 */ static inline void tss_setup_io_bitmap(struct tss_struct *tss) @@ -2243,8 +2231,6 @@ void cpu_init(void) struct task_struct *cur = current; int cpu = raw_smp_processor_id(); - ucode_cpu_init(cpu); - #ifdef CONFIG_NUMA if (this_cpu_read(numa_node) == 0 && early_cpu_to_node(cpu) != NUMA_NO_NODE) diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h index 1dcd7d4e38ef..885281ae79a5 100644 --- a/arch/x86/kernel/cpu/cpu.h +++ b/arch/x86/kernel/cpu/cpu.h @@ -78,6 +78,9 @@ 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_hygon_init_llc_id(struct cpuinfo_x86 *c); + unsigned int aperfmperf_get_khz(int cpu); void cpu_select_mitigations(void); diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c new file mode 100644 index 000000000000..0c179d684b3b --- /dev/null +++ b/arch/x86/kernel/cpu/debugfs.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/debugfs.h> + +#include <asm/apic.h> +#include <asm/processor.h> + +static int cpu_debug_show(struct seq_file *m, void *p) +{ + unsigned long cpu = (unsigned long)m->private; + struct cpuinfo_x86 *c = per_cpu_ptr(&cpu_info, cpu); + + seq_printf(m, "online: %d\n", cpu_online(cpu)); + if (!c->initialized) + return 0; + + seq_printf(m, "initial_apicid: %x\n", c->topo.initial_apicid); + seq_printf(m, "apicid: %x\n", c->topo.apicid); + seq_printf(m, "pkg_id: %u\n", c->topo.pkg_id); + seq_printf(m, "die_id: %u\n", c->topo.die_id); + seq_printf(m, "cu_id: %u\n", c->topo.cu_id); + seq_printf(m, "core_id: %u\n", c->topo.core_id); + seq_printf(m, "logical_pkg_id: %u\n", c->topo.logical_pkg_id); + 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); + return 0; +} + +static int cpu_debug_open(struct inode *inode, struct file *file) +{ + return single_open(file, cpu_debug_show, inode->i_private); +} + +static const struct file_operations dfs_cpu_ops = { + .open = cpu_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]; + + dir = debugfs_create_dir("cpus", base); + for_each_possible_cpu(id) { + sprintf(name, "%lu", id); + debugfs_create_file(name, 0444, dir, (void *)id, &dfs_cpu_ops); + } + return 0; +} +late_initcall(cpu_init_debugfs); diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index defdc594be14..6f247d66758d 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -63,8 +63,6 @@ static void hygon_get_topology_early(struct cpuinfo_x86 *c) */ static void hygon_get_topology(struct cpuinfo_x86 *c) { - int cpu = smp_processor_id(); - /* get information required for multi-node processors */ if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { int err; @@ -72,9 +70,9 @@ static void hygon_get_topology(struct cpuinfo_x86 *c) cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); - c->cpu_die_id = ecx & 0xff; + c->topo.die_id = ecx & 0xff; - c->cpu_core_id = ebx & 0xff; + c->topo.core_id = ebx & 0xff; if (smp_num_siblings > 1) c->x86_max_cores /= smp_num_siblings; @@ -87,17 +85,20 @@ static void hygon_get_topology(struct cpuinfo_x86 *c) if (!err) c->x86_coreid_bits = get_count_order(c->x86_max_cores); - /* Socket ID is ApicId[6] for these processors. */ - c->phys_proc_id = c->apicid >> APICID_SOCKET_ID_BIT; + /* + * 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, cpu); + cacheinfo_hygon_init_llc_id(c); } else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) { u64 value; rdmsrl(MSR_FAM10H_NODE_ID, value); - c->cpu_die_id = value & 7; - - per_cpu(cpu_llc_id, cpu) = c->cpu_die_id; + c->topo.die_id = value & 7; + c->topo.llc_id = c->topo.die_id; } else return; @@ -112,15 +113,14 @@ static void hygon_get_topology(struct cpuinfo_x86 *c) static void hygon_detect_cmp(struct cpuinfo_x86 *c) { unsigned int bits; - int cpu = smp_processor_id(); bits = c->x86_coreid_bits; /* Low order bits define the core id (index of core in socket) */ - c->cpu_core_id = c->initial_apicid & ((1 << bits)-1); + c->topo.core_id = c->topo.initial_apicid & ((1 << bits)-1); /* Convert the initial APIC ID into the socket ID */ - c->phys_proc_id = c->initial_apicid >> bits; - /* use socket ID also for last level cache */ - per_cpu(cpu_llc_id, cpu) = c->cpu_die_id = c->phys_proc_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) @@ -128,11 +128,11 @@ static void srat_detect_node(struct cpuinfo_x86 *c) #ifdef CONFIG_NUMA int cpu = smp_processor_id(); int node; - unsigned int apicid = c->apicid; + unsigned int apicid = c->topo.apicid; node = numa_cpu_node(cpu); if (node == NUMA_NO_NODE) - node = per_cpu(cpu_llc_id, cpu); + node = c->topo.llc_id; /* * On multi-fabric platform (e.g. Numascale NumaChip) a @@ -161,7 +161,7 @@ static void srat_detect_node(struct cpuinfo_x86 *c) * through CPU mapping may alter the outcome, directly * access __apicid_to_node[]. */ - int ht_nodeid = c->initial_apicid; + int ht_nodeid = c->topo.initial_apicid; if (__apicid_to_node[ht_nodeid] != NUMA_NO_NODE) node = __apicid_to_node[ht_nodeid]; @@ -290,6 +290,8 @@ static void early_init_hygon(struct cpuinfo_x86 *c) static void init_hygon(struct cpuinfo_x86 *c) { + u64 vm_cr; + early_init_hygon(c); /* @@ -301,7 +303,7 @@ 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->apicid = read_apic_id(); + c->topo.apicid = read_apic_id(); /* * XXX someone from Hygon needs to confirm this DTRT @@ -320,6 +322,14 @@ static void init_hygon(struct cpuinfo_x86 *c) init_hygon_cacheinfo(c); + if (cpu_has(c, X86_FEATURE_SVM)) { + rdmsrl(MSR_VM_CR, vm_cr); + if (vm_cr & SVM_VM_CR_SVM_DIS_MASK) { + pr_notice_once("SVM disabled (by BIOS) in MSR_VM_CR\n"); + clear_cpu_cap(c, X86_FEATURE_SVM); + } + } + if (cpu_has(c, X86_FEATURE_XMM2)) { /* * Use LFENCE for execution serialization. On families which diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index be4045628fd3..a927a8fc9624 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -314,19 +314,6 @@ static void early_init_intel(struct cpuinfo_x86 *c) setup_clear_cpu_cap(X86_FEATURE_PGE); } - if (c->cpuid_level >= 0x00000001) { - u32 eax, ebx, ecx, edx; - - cpuid(0x00000001, &eax, &ebx, &ecx, &edx); - /* - * If HTT (EDX[28]) is set EBX[16:23] contain the number of - * apicids which are reserved per package. Store the resulting - * shift value for the package management code. - */ - if (edx & (1U << 28)) - c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff); - } - check_memory_type_self_snoop_errata(c); /* @@ -1016,7 +1003,6 @@ static struct ctl_table sld_sysctls[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - {} }; static int __init sld_mitigate_sysctl_init(void) diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index c267f43de39e..f3517b8a8e91 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -713,17 +713,75 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) deferred_error_interrupt_enable(c); } -bool amd_mce_is_memory_error(struct mce *m) +/* + * DRAM ECC errors are reported in the Northbridge (bank 4) with + * Extended Error Code 8. + */ +static bool legacy_mce_is_memory_error(struct mce *m) +{ + return m->bank == 4 && XEC(m->status, 0x1f) == 8; +} + +/* + * DRAM ECC errors are reported in Unified Memory Controllers with + * Extended Error Code 0. + */ +static bool smca_mce_is_memory_error(struct mce *m) { enum smca_bank_types bank_type; - /* ErrCodeExt[20:16] */ - u8 xec = (m->status >> 16) & 0x1f; + + if (XEC(m->status, 0x3f)) + return false; bank_type = smca_get_bank_type(m->extcpu, m->bank); + + return bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2; +} + +bool amd_mce_is_memory_error(struct mce *m) +{ if (mce_flags.smca) - return (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) && xec == 0x0; + return smca_mce_is_memory_error(m); + else + return legacy_mce_is_memory_error(m); +} + +/* + * AMD systems do not have an explicit indicator that the value in MCA_ADDR is + * a system physical address. Therefore, individual cases need to be detected. + * Future cases and checks will be added as needed. + * + * 1) General case + * a) Assume address is not usable. + * 2) Poison errors + * a) Indicated by MCA_STATUS[43]: poison. Defined for all banks except legacy + * northbridge (bank 4). + * b) Refers to poison consumption in the core. Does not include "no action", + * "action optional", or "deferred" error severities. + * c) Will include a usable address so that immediate action can be taken. + * 3) Northbridge DRAM ECC errors + * a) Reported in legacy bank 4 with extended error code (XEC) 8. + * b) MCA_STATUS[43] is *not* defined as poison in legacy bank 4. Therefore, + * this bit should not be checked. + * + * NOTE: SMCA UMC memory errors fall into case #1. + */ +bool amd_mce_usable_address(struct mce *m) +{ + /* Check special northbridge case 3) first. */ + if (!mce_flags.smca) { + if (legacy_mce_is_memory_error(m)) + return true; + else if (m->bank == 4) + return false; + } - return m->bank == 4 && xec == 0x8; + /* Check poison bit for all other bank types. */ + if (m->status & MCI_STATUS_POISON) + return true; + + /* Assume address is not usable for all others. */ + return false; } static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c index 8ed341714686..7f7309ff67d0 100644 --- a/arch/x86/kernel/cpu/mce/apei.c +++ b/arch/x86/kernel/cpu/mce/apei.c @@ -103,9 +103,9 @@ int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id) m.socketid = -1; for_each_possible_cpu(cpu) { - if (cpu_data(cpu).initial_apicid == lapic_id) { + if (cpu_data(cpu).topo.initial_apicid == lapic_id) { m.extcpu = cpu; - m.socketid = cpu_data(m.extcpu).phys_proc_id; + m.socketid = cpu_data(m.extcpu).topo.pkg_id; break; } } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 6f35f724cc14..7b397370b4d6 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -123,8 +123,8 @@ void mce_setup(struct mce *m) m->time = __ktime_get_real_seconds(); m->cpuvendor = boot_cpu_data.x86_vendor; m->cpuid = cpuid_eax(1); - m->socketid = cpu_data(m->extcpu).phys_proc_id; - m->apicid = cpu_data(m->extcpu).initial_apicid; + m->socketid = cpu_data(m->extcpu).topo.pkg_id; + m->apicid = cpu_data(m->extcpu).topo.initial_apicid; m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP); m->ppin = cpu_data(m->extcpu).ppin; m->microcode = boot_cpu_data.microcode; @@ -453,32 +453,22 @@ static void mce_irq_work_cb(struct irq_work *entry) mce_schedule_work(); } -/* - * Check if the address reported by the CPU is in a format we can parse. - * It would be possible to add code for most other cases, but all would - * be somewhat complicated (e.g. segment offset would require an instruction - * parser). So only support physical addresses up to page granularity for now. - */ -int mce_usable_address(struct mce *m) +bool mce_usable_address(struct mce *m) { if (!(m->status & MCI_STATUS_ADDRV)) - return 0; - - /* Checks after this one are Intel/Zhaoxin-specific: */ - if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && - boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) - return 1; - - if (!(m->status & MCI_STATUS_MISCV)) - return 0; + return false; - if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) - return 0; + switch (m->cpuvendor) { + case X86_VENDOR_AMD: + return amd_mce_usable_address(m); - if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) - return 0; + case X86_VENDOR_INTEL: + case X86_VENDOR_ZHAOXIN: + return intel_mce_usable_address(m); - return 1; + default: + return true; + } } EXPORT_SYMBOL_GPL(mce_usable_address); diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index f5323551c1a9..52bce533ddcc 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -536,3 +536,23 @@ bool intel_filter_mce(struct mce *m) return false; } + +/* + * Check if the address reported by the CPU is in a format we can parse. + * It would be possible to add code for most other cases, but all would + * be somewhat complicated (e.g. segment offset would require an instruction + * parser). So only support physical addresses up to page granularity for now. + */ +bool intel_mce_usable_address(struct mce *m) +{ + if (!(m->status & MCI_STATUS_MISCV)) + return false; + + if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) + return false; + + if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) + return false; + + return true; +} diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index bcf1b3c66c9c..e13a26c9c0ac 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -49,6 +49,7 @@ void intel_init_cmci(void); void intel_init_lmce(void); void intel_clear_lmce(void); bool intel_filter_mce(struct mce *m); +bool intel_mce_usable_address(struct mce *m); #else # define cmci_intel_adjust_timer mce_adjust_timer_default static inline bool mce_intel_cmci_poll(void) { return false; } @@ -58,6 +59,7 @@ static inline void intel_init_cmci(void) { } static inline void intel_init_lmce(void) { } static inline void intel_clear_lmce(void) { } static inline bool intel_filter_mce(struct mce *m) { return false; } +static inline bool intel_mce_usable_address(struct mce *m) { return false; } #endif void mce_timer_kick(unsigned long interval); @@ -210,6 +212,7 @@ extern bool filter_mce(struct mce *m); #ifdef CONFIG_X86_MCE_AMD extern bool amd_filter_mce(struct mce *m); +bool amd_mce_usable_address(struct mce *m); /* * If MCA_CONFIG[McaLsbInStatusSupported] is set, extract ErrAddr in bits @@ -237,6 +240,7 @@ static __always_inline void smca_extract_err_addr(struct mce *m) #else static inline bool amd_filter_mce(struct mce *m) { return false; } +static inline bool amd_mce_usable_address(struct mce *m) { return false; } static inline void smca_extract_err_addr(struct mce *m) { } #endif diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c index bbd1dc38ea03..9373ec01c5ae 100644 --- a/arch/x86/kernel/cpu/microcode/amd.c +++ b/arch/x86/kernel/cpu/microcode/amd.c @@ -37,6 +37,16 @@ #include "internal.h" +struct ucode_patch { + struct list_head plist; + void *data; + unsigned int size; + u32 patch_id; + u16 equiv_cpu; +}; + +static LIST_HEAD(microcode_cache); + #define UCODE_MAGIC 0x00414d44 #define UCODE_EQUIV_CPU_TABLE_TYPE 0x00000000 #define UCODE_UCODE_TYPE 0x00000001 @@ -121,24 +131,20 @@ static u16 find_equiv_id(struct equiv_cpu_table *et, u32 sig) /* * Check whether there is a valid microcode container file at the beginning - * of @buf of size @buf_size. Set @early to use this function in the early path. + * of @buf of size @buf_size. */ -static bool verify_container(const u8 *buf, size_t buf_size, bool early) +static bool verify_container(const u8 *buf, size_t buf_size) { u32 cont_magic; if (buf_size <= CONTAINER_HDR_SZ) { - if (!early) - pr_debug("Truncated microcode container header.\n"); - + pr_debug("Truncated microcode container header.\n"); return false; } cont_magic = *(const u32 *)buf; if (cont_magic != UCODE_MAGIC) { - if (!early) - pr_debug("Invalid magic value (0x%08x).\n", cont_magic); - + pr_debug("Invalid magic value (0x%08x).\n", cont_magic); return false; } @@ -147,23 +153,20 @@ static bool verify_container(const u8 *buf, size_t buf_size, bool early) /* * Check whether there is a valid, non-truncated CPU equivalence table at the - * beginning of @buf of size @buf_size. Set @early to use this function in the - * early path. + * beginning of @buf of size @buf_size. */ -static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early) +static bool verify_equivalence_table(const u8 *buf, size_t buf_size) { const u32 *hdr = (const u32 *)buf; u32 cont_type, equiv_tbl_len; - if (!verify_container(buf, buf_size, early)) + if (!verify_container(buf, buf_size)) return false; cont_type = hdr[1]; if (cont_type != UCODE_EQUIV_CPU_TABLE_TYPE) { - if (!early) - pr_debug("Wrong microcode container equivalence table type: %u.\n", - cont_type); - + pr_debug("Wrong microcode container equivalence table type: %u.\n", + cont_type); return false; } @@ -172,9 +175,7 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early) equiv_tbl_len = hdr[2]; if (equiv_tbl_len < sizeof(struct equiv_cpu_entry) || buf_size < equiv_tbl_len) { - if (!early) - pr_debug("Truncated equivalence table.\n"); - + pr_debug("Truncated equivalence table.\n"); return false; } @@ -183,22 +184,19 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size, bool early) /* * Check whether there is a valid, non-truncated microcode patch section at the - * beginning of @buf of size @buf_size. Set @early to use this function in the - * early path. + * beginning of @buf of size @buf_size. * * On success, @sh_psize returns the patch size according to the section header, * to the caller. */ static bool -__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early) +__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize) { u32 p_type, p_size; const u32 *hdr; if (buf_size < SECTION_HDR_SIZE) { - if (!early) - pr_debug("Truncated patch section.\n"); - + pr_debug("Truncated patch section.\n"); return false; } @@ -207,17 +205,13 @@ __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize, bool early p_size = hdr[1]; if (p_type != UCODE_UCODE_TYPE) { - if (!early) - pr_debug("Invalid type field (0x%x) in container file section header.\n", - p_type); - + pr_debug("Invalid type field (0x%x) in container file section header.\n", + p_type); return false; } if (p_size < sizeof(struct microcode_header_amd)) { - if (!early) - pr_debug("Patch of size %u too short.\n", p_size); - + pr_debug("Patch of size %u too short.\n", p_size); return false; } @@ -269,7 +263,7 @@ static unsigned int __verify_patch_size(u8 family, u32 sh_psize, size_t buf_size * 0: success */ static int -verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool early) +verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size) { struct microcode_header_amd *mc_hdr; unsigned int ret; @@ -277,7 +271,7 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea u16 proc_id; u8 patch_fam; - if (!__verify_patch_section(buf, buf_size, &sh_psize, early)) + if (!__verify_patch_section(buf, buf_size, &sh_psize)) return -1; /* @@ -292,16 +286,13 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea * size sh_psize, as the section claims. */ if (buf_size < sh_psize) { - if (!early) - pr_debug("Patch of size %u truncated.\n", sh_psize); - + pr_debug("Patch of size %u truncated.\n", sh_psize); return -1; } ret = __verify_patch_size(family, sh_psize, buf_size); if (!ret) { - if (!early) - pr_debug("Per-family patch size mismatch.\n"); + pr_debug("Per-family patch size mismatch.\n"); return -1; } @@ -309,8 +300,7 @@ verify_patch(u8 family, const u8 *buf, size_t buf_size, u32 *patch_size, bool ea mc_hdr = (struct microcode_header_amd *)(buf + SECTION_HDR_SIZE); if (mc_hdr->nb_dev_id || mc_hdr->sb_dev_id) { - if (!early) - pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", mc_hdr->patch_id); + pr_err("Patch-ID 0x%08x: chipset-specific code unsupported.\n", mc_hdr->patch_id); return -1; } @@ -337,7 +327,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc) u16 eq_id; u8 *buf; - if (!verify_equivalence_table(ucode, size, true)) + if (!verify_equivalence_table(ucode, size)) return 0; buf = ucode; @@ -364,7 +354,7 @@ static size_t parse_container(u8 *ucode, size_t size, struct cont_desc *desc) u32 patch_size; int ret; - ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size, true); + ret = verify_patch(x86_family(desc->cpuid_1_eax), buf, size, &patch_size); if (ret < 0) { /* * Patch verification failed, skip to the next container, if @@ -456,14 +446,8 @@ static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size) { struct cont_desc desc = { 0 }; struct microcode_amd *mc; - u32 rev, dummy, *new_rev; bool ret = false; - -#ifdef CONFIG_X86_32 - new_rev = (u32 *)__pa_nodebug(&ucode_new_rev); -#else - new_rev = &ucode_new_rev; -#endif + u32 rev, dummy; desc.cpuid_1_eax = cpuid_1_eax; @@ -484,8 +468,8 @@ static bool early_apply_microcode(u32 cpuid_1_eax, void *ucode, size_t size) return ret; if (!__apply_microcode_amd(mc)) { - *new_rev = mc->hdr.patch_id; - ret = true; + ucode_new_rev = mc->hdr.patch_id; + ret = true; } return ret; @@ -501,7 +485,7 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) if (family >= 0x15) snprintf(fw_name, sizeof(fw_name), - "amd-ucode/microcode_amd_fam%.2xh.bin", family); + "amd-ucode/microcode_amd_fam%02hhxh.bin", family); if (firmware_request_builtin(&fw, fw_name)) { cp->size = fw.size; @@ -512,36 +496,23 @@ static bool get_builtin_microcode(struct cpio_data *cp, unsigned int family) return false; } -static void find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret) +static void __init find_blobs_in_containers(unsigned int cpuid_1_eax, struct cpio_data *ret) { - struct ucode_cpu_info *uci; struct cpio_data cp; - const char *path; - bool use_pa; - - if (IS_ENABLED(CONFIG_X86_32)) { - uci = (struct ucode_cpu_info *)__pa_nodebug(ucode_cpu_info); - path = (const char *)__pa_nodebug(ucode_path); - use_pa = true; - } else { - uci = ucode_cpu_info; - path = ucode_path; - use_pa = false; - } if (!get_builtin_microcode(&cp, x86_family(cpuid_1_eax))) - cp = find_microcode_in_initrd(path, use_pa); - - /* Needed in load_microcode_amd() */ - uci->cpu_sig.sig = cpuid_1_eax; + cp = find_microcode_in_initrd(ucode_path); *ret = cp; } -static void apply_ucode_from_containers(unsigned int cpuid_1_eax) +void __init load_ucode_amd_bsp(unsigned int cpuid_1_eax) { struct cpio_data cp = { }; + /* Needed in load_microcode_amd() */ + ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax; + find_blobs_in_containers(cpuid_1_eax, &cp); if (!(cp.data && cp.size)) return; @@ -549,20 +520,20 @@ static void apply_ucode_from_containers(unsigned int cpuid_1_eax) early_apply_microcode(cpuid_1_eax, cp.data, cp.size); } -void load_ucode_amd_early(unsigned int cpuid_1_eax) -{ - return apply_ucode_from_containers(cpuid_1_eax); -} - static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t size); -int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) +static int __init save_microcode_in_initrd(void) { + unsigned int cpuid_1_eax = native_cpuid_eax(1); + struct cpuinfo_x86 *c = &boot_cpu_data; struct cont_desc desc = { 0 }; enum ucode_state ret; struct cpio_data cp; - cp = find_microcode_in_initrd(ucode_path, false); + if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) + return 0; + + find_blobs_in_containers(cpuid_1_eax, &cp); if (!(cp.data && cp.size)) return -EINVAL; @@ -578,6 +549,7 @@ int __init save_microcode_in_initrd_amd(unsigned int cpuid_1_eax) return 0; } +early_initcall(save_microcode_in_initrd); /* * a small, trivial cache of per-family ucode patches @@ -631,7 +603,6 @@ static struct ucode_patch *find_patch(unsigned int cpu) struct ucode_cpu_info *uci = ucode_cpu_info + cpu; u16 equiv_id; - equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig); if (!equiv_id) return NULL; @@ -733,12 +704,20 @@ out: return ret; } +void load_ucode_amd_ap(unsigned int cpuid_1_eax) +{ + unsigned int cpu = smp_processor_id(); + + ucode_cpu_info[cpu].cpu_sig.sig = cpuid_1_eax; + apply_microcode_amd(cpu); +} + static size_t install_equiv_cpu_table(const u8 *buf, size_t buf_size) { u32 equiv_tbl_len; const u32 *hdr; - if (!verify_equivalence_table(buf, buf_size, false)) + if (!verify_equivalence_table(buf, buf_size)) return 0; hdr = (const u32 *)buf; @@ -784,7 +763,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover, u16 proc_id; int ret; - ret = verify_patch(family, fw, leftover, patch_size, false); + ret = verify_patch(family, fw, leftover, patch_size); if (ret) return ret; @@ -909,6 +888,9 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device) enum ucode_state ret = UCODE_NFOUND; const struct firmware *fw; + if (force_minrev) + return UCODE_NFOUND; + if (c->x86 >= 0x15) snprintf(fw_name, sizeof(fw_name), "amd-ucode/microcode_amd_fam%.2xh.bin", c->x86); @@ -918,7 +900,7 @@ static enum ucode_state request_microcode_amd(int cpu, struct device *device) } ret = UCODE_ERROR; - if (!verify_container(fw->data, fw->size, false)) + if (!verify_container(fw->data, fw->size)) goto fw_release; ret = load_microcode_amd(c->x86, fw->data, fw->size); @@ -938,10 +920,11 @@ static void microcode_fini_cpu_amd(int cpu) } static struct microcode_ops microcode_amd_ops = { - .request_microcode_fw = request_microcode_amd, - .collect_cpu_info = collect_cpu_info_amd, - .apply_microcode = apply_microcode_amd, - .microcode_fini_cpu = microcode_fini_cpu_amd, + .request_microcode_fw = request_microcode_amd, + .collect_cpu_info = collect_cpu_info_amd, + .apply_microcode = apply_microcode_amd, + .microcode_fini_cpu = microcode_fini_cpu_amd, + .nmi_safe = true, }; struct microcode_ops * __init init_amd_microcode(void) diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 6cc7a2c181da..666d25bbc5ad 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -23,6 +23,7 @@ #include <linux/miscdevice.h> #include <linux/capability.h> #include <linux/firmware.h> +#include <linux/cpumask.h> #include <linux/kernel.h> #include <linux/delay.h> #include <linux/mutex.h> @@ -31,6 +32,7 @@ #include <linux/fs.h> #include <linux/mm.h> +#include <asm/apic.h> #include <asm/cpu_device_id.h> #include <asm/perf_event.h> #include <asm/processor.h> @@ -42,11 +44,10 @@ #define DRIVER_VERSION "2.2" static struct microcode_ops *microcode_ops; -static bool dis_ucode_ldr = true; +bool dis_ucode_ldr = true; -bool initrd_gone; - -LIST_HEAD(microcode_cache); +bool force_minrev = IS_ENABLED(CONFIG_MICROCODE_LATE_FORCE_MINREV); +module_param(force_minrev, bool, S_IRUSR | S_IWUSR); /* * Synchronization. @@ -90,10 +91,7 @@ static bool amd_check_current_patch_level(void) native_rdmsr(MSR_AMD64_PATCH_LEVEL, lvl, dummy); - if (IS_ENABLED(CONFIG_X86_32)) - levels = (u32 *)__pa_nodebug(&final_levels); - else - levels = final_levels; + levels = final_levels; for (i = 0; levels[i]; i++) { if (lvl == levels[i]) @@ -105,17 +103,8 @@ static bool amd_check_current_patch_level(void) static bool __init check_loader_disabled_bsp(void) { static const char *__dis_opt_str = "dis_ucode_ldr"; - -#ifdef CONFIG_X86_32 - const char *cmdline = (const char *)__pa_nodebug(boot_command_line); - const char *option = (const char *)__pa_nodebug(__dis_opt_str); - bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr); - -#else /* CONFIG_X86_64 */ const char *cmdline = boot_command_line; const char *option = __dis_opt_str; - bool *res = &dis_ucode_ldr; -#endif /* * CPUID(1).ECX[31]: reserved for hypervisor use. This is still not @@ -123,17 +112,17 @@ static bool __init check_loader_disabled_bsp(void) * that's good enough as they don't land on the BSP path anyway. */ if (native_cpuid_ecx(1) & BIT(31)) - return *res; + return true; if (x86_cpuid_vendor() == X86_VENDOR_AMD) { if (amd_check_current_patch_level()) - return *res; + return true; } if (cmdline_find_option_bool(cmdline, option) <= 0) - *res = false; + dis_ucode_ldr = false; - return *res; + return dis_ucode_ldr; } void __init load_ucode_bsp(void) @@ -168,23 +157,14 @@ void __init load_ucode_bsp(void) if (intel) load_ucode_intel_bsp(); else - load_ucode_amd_early(cpuid_1_eax); -} - -static bool check_loader_disabled_ap(void) -{ -#ifdef CONFIG_X86_32 - return *((bool *)__pa_nodebug(&dis_ucode_ldr)); -#else - return dis_ucode_ldr; -#endif + load_ucode_amd_bsp(cpuid_1_eax); } void load_ucode_ap(void) { unsigned int cpuid_1_eax; - if (check_loader_disabled_ap()) + if (dis_ucode_ldr) return; cpuid_1_eax = native_cpuid_eax(1); @@ -196,97 +176,44 @@ void load_ucode_ap(void) break; case X86_VENDOR_AMD: if (x86_family(cpuid_1_eax) >= 0x10) - load_ucode_amd_early(cpuid_1_eax); - break; - default: - break; - } -} - -static int __init save_microcode_in_initrd(void) -{ - struct cpuinfo_x86 *c = &boot_cpu_data; - int ret = -EINVAL; - - switch (c->x86_vendor) { - case X86_VENDOR_INTEL: - if (c->x86 >= 6) - ret = save_microcode_in_initrd_intel(); - break; - case X86_VENDOR_AMD: - if (c->x86 >= 0x10) - ret = save_microcode_in_initrd_amd(cpuid_eax(1)); + load_ucode_amd_ap(cpuid_1_eax); break; default: break; } - - initrd_gone = true; - - return ret; } -struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa) +struct cpio_data __init find_microcode_in_initrd(const char *path) { #ifdef CONFIG_BLK_DEV_INITRD unsigned long start = 0; size_t size; #ifdef CONFIG_X86_32 - struct boot_params *params; - - if (use_pa) - params = (struct boot_params *)__pa_nodebug(&boot_params); - else - params = &boot_params; - - size = params->hdr.ramdisk_size; - - /* - * Set start only if we have an initrd image. We cannot use initrd_start - * because it is not set that early yet. - */ + size = boot_params.hdr.ramdisk_size; + /* Early load on BSP has a temporary mapping. */ if (size) - start = params->hdr.ramdisk_image; + start = initrd_start_early; -# else /* CONFIG_X86_64 */ +#else /* CONFIG_X86_64 */ size = (unsigned long)boot_params.ext_ramdisk_size << 32; size |= boot_params.hdr.ramdisk_size; if (size) { start = (unsigned long)boot_params.ext_ramdisk_image << 32; start |= boot_params.hdr.ramdisk_image; - start += PAGE_OFFSET; } -# endif +#endif /* * Fixup the start address: after reserve_initrd() runs, initrd_start * has the virtual address of the beginning of the initrd. It also * possibly relocates the ramdisk. In either case, initrd_start contains * the updated address so use that instead. - * - * initrd_gone is for the hotplug case where we've thrown out initrd - * already. */ - if (!use_pa) { - if (initrd_gone) - return (struct cpio_data){ NULL, 0, "" }; - if (initrd_start) - start = initrd_start; - } else { - /* - * The picture with physical addresses is a bit different: we - * need to get the *physical* address to which the ramdisk was - * relocated, i.e., relocated_ramdisk (not initrd_start) and - * since we're running from physical addresses, we need to access - * relocated_ramdisk through its *physical* address too. - */ - u64 *rr = (u64 *)__pa_nodebug(&relocated_ramdisk); - if (*rr) - start = *rr; - } + if (initrd_start) + start = initrd_start; return find_cpio_data(path, (void *)start, size, NULL); #else /* !CONFIG_BLK_DEV_INITRD */ @@ -330,117 +257,298 @@ static struct platform_device *microcode_pdev; * requirement can be relaxed in the future. Right now, this is conservative * and good. */ -#define SPINUNIT 100 /* 100 nsec */ +enum sibling_ctrl { + /* Spinwait with timeout */ + SCTRL_WAIT, + /* Invoke the microcode_apply() callback */ + SCTRL_APPLY, + /* Proceed without invoking the microcode_apply() callback */ + SCTRL_DONE, +}; + +struct microcode_ctrl { + enum sibling_ctrl ctrl; + enum ucode_state result; + unsigned int ctrl_cpu; + bool nmi_enabled; +}; -static int check_online_cpus(void) +DEFINE_STATIC_KEY_FALSE(microcode_nmi_handler_enable); +static DEFINE_PER_CPU(struct microcode_ctrl, ucode_ctrl); +static atomic_t late_cpus_in, offline_in_nmi; +static unsigned int loops_per_usec; +static cpumask_t cpu_offline_mask; + +static noinstr bool wait_for_cpus(atomic_t *cnt) { - unsigned int cpu; + unsigned int timeout, loops; - /* - * Make sure all CPUs are online. It's fine for SMT to be disabled if - * all the primary threads are still online. - */ - for_each_present_cpu(cpu) { - if (topology_is_primary_thread(cpu) && !cpu_online(cpu)) { - pr_err("Not all CPUs online, aborting microcode update.\n"); - return -EINVAL; + WARN_ON_ONCE(raw_atomic_dec_return(cnt) < 0); + + for (timeout = 0; timeout < USEC_PER_SEC; timeout++) { + if (!raw_atomic_read(cnt)) + return true; + + for (loops = 0; loops < loops_per_usec; loops++) + cpu_relax(); + + /* If invoked directly, tickle the NMI watchdog */ + if (!microcode_ops->use_nmi && !(timeout % USEC_PER_MSEC)) { + instrumentation_begin(); + touch_nmi_watchdog(); + instrumentation_end(); } } - - return 0; + /* Prevent the late comers from making progress and let them time out */ + raw_atomic_inc(cnt); + return false; } -static atomic_t late_cpus_in; -static atomic_t late_cpus_out; - -static int __wait_for_cpus(atomic_t *t, long long timeout) +static noinstr bool wait_for_ctrl(void) { - int all_cpus = num_online_cpus(); - - atomic_inc(t); + unsigned int timeout, loops; - while (atomic_read(t) < all_cpus) { - if (timeout < SPINUNIT) { - pr_err("Timeout while waiting for CPUs rendezvous, remaining: %d\n", - all_cpus - atomic_read(t)); - return 1; - } + for (timeout = 0; timeout < USEC_PER_SEC; timeout++) { + if (raw_cpu_read(ucode_ctrl.ctrl) != SCTRL_WAIT) + return true; - ndelay(SPINUNIT); - timeout -= SPINUNIT; + for (loops = 0; loops < loops_per_usec; loops++) + cpu_relax(); - touch_nmi_watchdog(); + /* If invoked directly, tickle the NMI watchdog */ + if (!microcode_ops->use_nmi && !(timeout % USEC_PER_MSEC)) { + instrumentation_begin(); + touch_nmi_watchdog(); + instrumentation_end(); + } } - return 0; + return false; } /* - * Returns: - * < 0 - on error - * 0 - success (no update done or microcode was updated) + * Protected against instrumentation up to the point where the primary + * thread completed the update. See microcode_nmi_handler() for details. */ -static int __reload_late(void *info) +static noinstr bool load_secondary_wait(unsigned int ctrl_cpu) { - int cpu = smp_processor_id(); - enum ucode_state err; - int ret = 0; + /* Initial rendezvous to ensure that all CPUs have arrived */ + if (!wait_for_cpus(&late_cpus_in)) { + raw_cpu_write(ucode_ctrl.result, UCODE_TIMEOUT); + return false; + } /* - * Wait for all CPUs to arrive. A load will not be attempted unless all - * CPUs show up. - * */ - if (__wait_for_cpus(&late_cpus_in, NSEC_PER_SEC)) - return -1; + * Wait for primary threads to complete. If one of them hangs due + * to the update, there is no way out. This is non-recoverable + * because the CPU might hold locks or resources and confuse the + * scheduler, watchdogs etc. There is no way to safely evacuate the + * machine. + */ + if (wait_for_ctrl()) + return true; + instrumentation_begin(); + panic("Microcode load: Primary CPU %d timed out\n", ctrl_cpu); + instrumentation_end(); +} + +/* + * Protected against instrumentation up to the point where the primary + * thread completed the update. See microcode_nmi_handler() for details. + */ +static noinstr void load_secondary(unsigned int cpu) +{ + unsigned int ctrl_cpu = raw_cpu_read(ucode_ctrl.ctrl_cpu); + enum ucode_state ret; + + if (!load_secondary_wait(ctrl_cpu)) { + instrumentation_begin(); + pr_err_once("load: %d CPUs timed out\n", + atomic_read(&late_cpus_in) - 1); + instrumentation_end(); + return; + } + + /* Primary thread completed. Allow to invoke instrumentable code */ + instrumentation_begin(); /* - * On an SMT system, it suffices to load the microcode on one sibling of - * the core because the microcode engine is shared between the threads. - * Synchronization still needs to take place so that no concurrent - * loading attempts happen on multiple threads of an SMT core. See - * below. + * If the primary succeeded then invoke the apply() callback, + * otherwise copy the state from the primary thread. */ - if (cpumask_first(topology_sibling_cpumask(cpu)) == cpu) - err = microcode_ops->apply_microcode(cpu); + if (this_cpu_read(ucode_ctrl.ctrl) == SCTRL_APPLY) + ret = microcode_ops->apply_microcode(cpu); else - goto wait_for_siblings; + ret = per_cpu(ucode_ctrl.result, ctrl_cpu); - if (err >= UCODE_NFOUND) { - if (err == UCODE_ERROR) { - pr_warn("Error reloading microcode on CPU %d\n", cpu); - ret = -1; - } + this_cpu_write(ucode_ctrl.result, ret); + this_cpu_write(ucode_ctrl.ctrl, SCTRL_DONE); + instrumentation_end(); +} + +static void __load_primary(unsigned int cpu) +{ + struct cpumask *secondaries = topology_sibling_cpumask(cpu); + enum sibling_ctrl ctrl; + enum ucode_state ret; + unsigned int sibling; + + /* Initial rendezvous to ensure that all CPUs have arrived */ + if (!wait_for_cpus(&late_cpus_in)) { + this_cpu_write(ucode_ctrl.result, UCODE_TIMEOUT); + pr_err_once("load: %d CPUs timed out\n", atomic_read(&late_cpus_in) - 1); + return; } -wait_for_siblings: - if (__wait_for_cpus(&late_cpus_out, NSEC_PER_SEC)) - panic("Timeout during microcode update!\n"); + ret = microcode_ops->apply_microcode(cpu); + this_cpu_write(ucode_ctrl.result, ret); + this_cpu_write(ucode_ctrl.ctrl, SCTRL_DONE); /* - * At least one thread has completed update on each core. - * For others, simply call the update to make sure the - * per-cpu cpuinfo can be updated with right microcode - * revision. + * If the update was successful, let the siblings run the apply() + * callback. If not, tell them it's done. This also covers the + * case where the CPU has uniform loading at package or system + * scope implemented but does not advertise it. */ - if (cpumask_first(topology_sibling_cpumask(cpu)) != cpu) - err = microcode_ops->apply_microcode(cpu); + if (ret == UCODE_UPDATED || ret == UCODE_OK) + ctrl = SCTRL_APPLY; + else + ctrl = SCTRL_DONE; + + for_each_cpu(sibling, secondaries) { + if (sibling != cpu) + per_cpu(ucode_ctrl.ctrl, sibling) = ctrl; + } +} + +static bool kick_offline_cpus(unsigned int nr_offl) +{ + unsigned int cpu, timeout; + + for_each_cpu(cpu, &cpu_offline_mask) { + /* Enable the rendezvous handler and send NMI */ + per_cpu(ucode_ctrl.nmi_enabled, cpu) = true; + apic_send_nmi_to_offline_cpu(cpu); + } + + /* Wait for them to arrive */ + for (timeout = 0; timeout < (USEC_PER_SEC / 2); timeout++) { + if (atomic_read(&offline_in_nmi) == nr_offl) + return true; + udelay(1); + } + /* Let the others time out */ + return false; +} + +static void release_offline_cpus(void) +{ + unsigned int cpu; + + for_each_cpu(cpu, &cpu_offline_mask) + per_cpu(ucode_ctrl.ctrl, cpu) = SCTRL_DONE; +} + +static void load_primary(unsigned int cpu) +{ + unsigned int nr_offl = cpumask_weight(&cpu_offline_mask); + bool proceed = true; + + /* Kick soft-offlined SMT siblings if required */ + if (!cpu && nr_offl) + proceed = kick_offline_cpus(nr_offl); + + /* If the soft-offlined CPUs did not respond, abort */ + if (proceed) + __load_primary(cpu); - return ret; + /* Unconditionally release soft-offlined SMT siblings if required */ + if (!cpu && nr_offl) + release_offline_cpus(); } /* - * Reload microcode late on all CPUs. Wait for a sec until they - * all gather together. + * Minimal stub rendezvous handler for soft-offlined CPUs which participate + * in the NMI rendezvous to protect against a concurrent NMI on affected + * CPUs. */ -static int microcode_reload_late(void) +void noinstr microcode_offline_nmi_handler(void) { - int old = boot_cpu_data.microcode, ret; + if (!raw_cpu_read(ucode_ctrl.nmi_enabled)) + return; + raw_cpu_write(ucode_ctrl.nmi_enabled, false); + raw_cpu_write(ucode_ctrl.result, UCODE_OFFLINE); + raw_atomic_inc(&offline_in_nmi); + wait_for_ctrl(); +} + +static noinstr bool microcode_update_handler(void) +{ + unsigned int cpu = raw_smp_processor_id(); + + if (raw_cpu_read(ucode_ctrl.ctrl_cpu) == cpu) { + instrumentation_begin(); + load_primary(cpu); + instrumentation_end(); + } else { + load_secondary(cpu); + } + + instrumentation_begin(); + touch_nmi_watchdog(); + instrumentation_end(); + + return true; +} + +/* + * Protection against instrumentation is required for CPUs which are not + * safe against an NMI which is delivered to the secondary SMT sibling + * while the primary thread updates the microcode. Instrumentation can end + * up in #INT3, #DB and #PF. The IRET from those exceptions reenables NMI + * which is the opposite of what the NMI rendezvous is trying to achieve. + * + * The primary thread is safe versus instrumentation as the actual + * microcode update handles this correctly. It's only the sibling code + * path which must be NMI safe until the primary thread completed the + * update. + */ +bool noinstr microcode_nmi_handler(void) +{ + if (!raw_cpu_read(ucode_ctrl.nmi_enabled)) + return false; + + raw_cpu_write(ucode_ctrl.nmi_enabled, false); + return microcode_update_handler(); +} + +static int load_cpus_stopped(void *unused) +{ + if (microcode_ops->use_nmi) { + /* Enable the NMI handler and raise NMI */ + this_cpu_write(ucode_ctrl.nmi_enabled, true); + apic->send_IPI(smp_processor_id(), NMI_VECTOR); + } else { + /* Just invoke the handler directly */ + microcode_update_handler(); + } + return 0; +} + +static int load_late_stop_cpus(bool is_safe) +{ + unsigned int cpu, updated = 0, failed = 0, timedout = 0, siblings = 0; + unsigned int nr_offl, offline = 0; + int old_rev = boot_cpu_data.microcode; struct cpuinfo_x86 prev_info; - pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n"); - pr_err("You should switch to early loading, if possible.\n"); + if (!is_safe) { + pr_err("Late microcode loading without minimal revision check.\n"); + pr_err("You should switch to early loading, if possible.\n"); + } - atomic_set(&late_cpus_in, 0); - atomic_set(&late_cpus_out, 0); + atomic_set(&late_cpus_in, num_online_cpus()); + atomic_set(&offline_in_nmi, 0); + loops_per_usec = loops_per_jiffy / (TICK_NSEC / 1000); /* * Take a snapshot before the microcode update in order to compare and @@ -448,52 +556,162 @@ static int microcode_reload_late(void) */ store_cpu_caps(&prev_info); - ret = stop_machine_cpuslocked(__reload_late, NULL, cpu_online_mask); - if (!ret) { - pr_info("Reload succeeded, microcode revision: 0x%x -> 0x%x\n", - old, boot_cpu_data.microcode); - microcode_check(&prev_info); - } else { - pr_info("Reload failed, current microcode revision: 0x%x\n", - boot_cpu_data.microcode); + if (microcode_ops->use_nmi) + static_branch_enable_cpuslocked(µcode_nmi_handler_enable); + + stop_machine_cpuslocked(load_cpus_stopped, NULL, cpu_online_mask); + + if (microcode_ops->use_nmi) + static_branch_disable_cpuslocked(µcode_nmi_handler_enable); + + /* Analyze the results */ + for_each_cpu_and(cpu, cpu_present_mask, &cpus_booted_once_mask) { + switch (per_cpu(ucode_ctrl.result, cpu)) { + case UCODE_UPDATED: updated++; break; + case UCODE_TIMEOUT: timedout++; break; + case UCODE_OK: siblings++; break; + case UCODE_OFFLINE: offline++; break; + default: failed++; break; + } + } + + if (microcode_ops->finalize_late_load) + microcode_ops->finalize_late_load(!updated); + + if (!updated) { + /* Nothing changed. */ + if (!failed && !timedout) + return 0; + + nr_offl = cpumask_weight(&cpu_offline_mask); + if (offline < nr_offl) { + pr_warn("%u offline siblings did not respond.\n", + nr_offl - atomic_read(&offline_in_nmi)); + return -EIO; + } + pr_err("update failed: %u CPUs failed %u CPUs timed out\n", + failed, timedout); + return -EIO; + } + + if (!is_safe || failed || timedout) + add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); + + pr_info("load: updated on %u primary CPUs with %u siblings\n", updated, siblings); + if (failed || timedout) { + pr_err("load incomplete. %u CPUs timed out or failed\n", + num_online_cpus() - (updated + siblings)); + } + pr_info("revision: 0x%x -> 0x%x\n", old_rev, boot_cpu_data.microcode); + microcode_check(&prev_info); + + return updated + siblings == num_online_cpus() ? 0 : -EIO; +} + +/* + * This function does two things: + * + * 1) Ensure that all required CPUs which are present and have been booted + * once are online. + * + * To pass this check, all primary threads must be online. + * + * If the microcode load is not safe against NMI then all SMT threads + * must be online as well because they still react to NMIs when they are + * soft-offlined and parked in one of the play_dead() variants. So if a + * NMI hits while the primary thread updates the microcode the resulting + * behaviour is undefined. The default play_dead() implementation on + * modern CPUs uses MWAIT, which is also not guaranteed to be safe + * against a microcode update which affects MWAIT. + * + * As soft-offlined CPUs still react on NMIs, the SMT sibling + * restriction can be lifted when the vendor driver signals to use NMI + * for rendezvous and the APIC provides a mechanism to send an NMI to a + * soft-offlined CPU. The soft-offlined CPUs are then able to + * participate in the rendezvous in a trivial stub handler. + * + * 2) Initialize the per CPU control structure and create a cpumask + * which contains "offline"; secondary threads, so they can be handled + * correctly by a control CPU. + */ +static bool setup_cpus(void) +{ + struct microcode_ctrl ctrl = { .ctrl = SCTRL_WAIT, .result = -1, }; + bool allow_smt_offline; + unsigned int cpu; + + allow_smt_offline = microcode_ops->nmi_safe || + (microcode_ops->use_nmi && apic->nmi_to_offline_cpu); + + cpumask_clear(&cpu_offline_mask); + + for_each_cpu_and(cpu, cpu_present_mask, &cpus_booted_once_mask) { + /* + * Offline CPUs sit in one of the play_dead() functions + * with interrupts disabled, but they still react on NMIs + * and execute arbitrary code. Also MWAIT being updated + * while the offline CPU sits there is not necessarily safe + * on all CPU variants. + * + * Mark them in the offline_cpus mask which will be handled + * by CPU0 later in the update process. + * + * Ensure that the primary thread is online so that it is + * guaranteed that all cores are updated. + */ + if (!cpu_online(cpu)) { + if (topology_is_primary_thread(cpu) || !allow_smt_offline) { + pr_err("CPU %u not online, loading aborted\n", cpu); + return false; + } + cpumask_set_cpu(cpu, &cpu_offline_mask); + per_cpu(ucode_ctrl, cpu) = ctrl; + continue; + } + + /* + * Initialize the per CPU state. This is core scope for now, + * but prepared to take package or system scope into account. + */ + ctrl.ctrl_cpu = cpumask_first(topology_sibling_cpumask(cpu)); + per_cpu(ucode_ctrl, cpu) = ctrl; } + return true; +} - return ret; +static int load_late_locked(void) +{ + if (!setup_cpus()) + return -EBUSY; + + switch (microcode_ops->request_microcode_fw(0, µcode_pdev->dev)) { + case UCODE_NEW: + return load_late_stop_cpus(false); + case UCODE_NEW_SAFE: + return load_late_stop_cpus(true); + case UCODE_NFOUND: + return -ENOENT; + default: + return -EBADFD; + } } static ssize_t reload_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t size) { - enum ucode_state tmp_ret = UCODE_OK; - int bsp = boot_cpu_data.cpu_index; unsigned long val; - ssize_t ret = 0; + ssize_t ret; ret = kstrtoul(buf, 0, &val); if (ret || val != 1) return -EINVAL; cpus_read_lock(); - - ret = check_online_cpus(); - if (ret) - goto put; - - tmp_ret = microcode_ops->request_microcode_fw(bsp, µcode_pdev->dev); - if (tmp_ret != UCODE_NEW) - goto put; - - ret = microcode_reload_late(); -put: + ret = load_late_locked(); cpus_read_unlock(); - if (ret == 0) - ret = size; - - add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK); - - return ret; + return ret ? : size; } static DEVICE_ATTR_WO(reload); @@ -535,17 +753,6 @@ static void microcode_fini_cpu(int cpu) microcode_ops->microcode_fini_cpu(cpu); } -static enum ucode_state microcode_init_cpu(int cpu) -{ - struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - - memset(uci, 0, sizeof(*uci)); - - microcode_ops->collect_cpu_info(cpu, &uci->cpu_sig); - - return microcode_ops->apply_microcode(cpu); -} - /** * microcode_bsp_resume - Update boot CPU microcode during resume. */ @@ -564,19 +771,18 @@ static struct syscore_ops mc_syscore_ops = { .resume = microcode_bsp_resume, }; -static int mc_cpu_starting(unsigned int cpu) -{ - enum ucode_state err = microcode_ops->apply_microcode(cpu); - - pr_debug("%s: CPU%d, err: %d\n", __func__, cpu, err); - - return err == UCODE_ERROR; -} - static int mc_cpu_online(unsigned int cpu) { + struct ucode_cpu_info *uci = ucode_cpu_info + cpu; struct device *dev = get_cpu_device(cpu); + memset(uci, 0, sizeof(*uci)); + + microcode_ops->collect_cpu_info(cpu, &uci->cpu_sig); + cpu_data(cpu).microcode = uci->cpu_sig.rev; + if (!cpu) + boot_cpu_data.microcode = uci->cpu_sig.rev; + if (sysfs_create_group(&dev->kobj, &mc_attr_group)) pr_err("Failed to create group for CPU%d\n", cpu); return 0; @@ -584,33 +790,13 @@ static int mc_cpu_online(unsigned int cpu) static int mc_cpu_down_prep(unsigned int cpu) { - struct device *dev; - - dev = get_cpu_device(cpu); + struct device *dev = get_cpu_device(cpu); microcode_fini_cpu(cpu); - - /* Suspend is in progress, only remove the interface */ sysfs_remove_group(&dev->kobj, &mc_attr_group); - pr_debug("%s: CPU%d\n", __func__, cpu); - return 0; } -static void setup_online_cpu(struct work_struct *work) -{ - int cpu = smp_processor_id(); - enum ucode_state err; - - err = microcode_init_cpu(cpu); - if (err == UCODE_ERROR) { - pr_err("Error applying microcode on CPU%d\n", cpu); - return; - } - - mc_cpu_online(cpu); -} - static struct attribute *cpu_root_microcode_attrs[] = { #ifdef CONFIG_MICROCODE_LATE_LOADING &dev_attr_reload.attr, @@ -656,14 +842,9 @@ static int __init microcode_init(void) } } - /* Do per-CPU setup */ - schedule_on_each_cpu(setup_online_cpu); - register_syscore_ops(&mc_syscore_ops); - cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting", - mc_cpu_starting, NULL); - cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online", - mc_cpu_online, mc_cpu_down_prep); + cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/microcode:online", + mc_cpu_online, mc_cpu_down_prep); pr_info("Microcode Update Driver: v%s.", DRIVER_VERSION); @@ -674,5 +855,4 @@ static int __init microcode_init(void) return error; } -fs_initcall(save_microcode_in_initrd); late_initcall(microcode_init); diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 94dd6af9c963..6024feb98d29 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -14,7 +14,6 @@ #include <linux/earlycpio.h> #include <linux/firmware.h> #include <linux/uaccess.h> -#include <linux/vmalloc.h> #include <linux/initrd.h> #include <linux/kernel.h> #include <linux/slab.h> @@ -32,11 +31,14 @@ static const char ucode_path[] = "kernel/x86/microcode/GenuineIntel.bin"; +#define UCODE_BSP_LOADED ((struct microcode_intel *)0x1UL) + /* Current microcode patch used in early patching on the APs. */ -static struct microcode_intel *intel_ucode_patch; +static struct microcode_intel *ucode_patch_va __read_mostly; +static struct microcode_intel *ucode_patch_late __read_mostly; /* last level cache size per core */ -static int llc_size_per_core; +static unsigned int llc_size_per_core __ro_after_init; /* microcode format is extended from prescott processors */ struct extended_signature { @@ -66,60 +68,52 @@ static inline unsigned int exttable_size(struct extended_sigtable *et) return et->count * EXT_SIGNATURE_SIZE + EXT_HEADER_SIZE; } -int intel_cpu_collect_info(struct ucode_cpu_info *uci) +void intel_collect_cpu_info(struct cpu_signature *sig) { - unsigned int val[2]; - unsigned int family, model; - struct cpu_signature csig = { 0 }; - unsigned int eax, ebx, ecx, edx; - - memset(uci, 0, sizeof(*uci)); - - eax = 0x00000001; - ecx = 0; - native_cpuid(&eax, &ebx, &ecx, &edx); - csig.sig = eax; + sig->sig = cpuid_eax(1); + sig->pf = 0; + sig->rev = intel_get_microcode_revision(); - family = x86_family(eax); - model = x86_model(eax); + if (x86_model(sig->sig) >= 5 || x86_family(sig->sig) > 6) { + unsigned int val[2]; - if (model >= 5 || family > 6) { /* get processor flags from MSR 0x17 */ native_rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); - csig.pf = 1 << ((val[1] >> 18) & 7); + sig->pf = 1 << ((val[1] >> 18) & 7); } +} +EXPORT_SYMBOL_GPL(intel_collect_cpu_info); - csig.rev = intel_get_microcode_revision(); - - uci->cpu_sig = csig; +static inline bool cpu_signatures_match(struct cpu_signature *s1, unsigned int sig2, + unsigned int pf2) +{ + if (s1->sig != sig2) + return false; - return 0; + /* Processor flags are either both 0 or they intersect. */ + return ((!s1->pf && !pf2) || (s1->pf & pf2)); } -EXPORT_SYMBOL_GPL(intel_cpu_collect_info); -/* - * Returns 1 if update has been found, 0 otherwise. - */ -int intel_find_matching_signature(void *mc, unsigned int csig, int cpf) +bool intel_find_matching_signature(void *mc, struct cpu_signature *sig) { struct microcode_header_intel *mc_hdr = mc; - struct extended_sigtable *ext_hdr; struct extended_signature *ext_sig; + struct extended_sigtable *ext_hdr; int i; - if (intel_cpu_signatures_match(csig, cpf, mc_hdr->sig, mc_hdr->pf)) - return 1; + if (cpu_signatures_match(sig, mc_hdr->sig, mc_hdr->pf)) + return true; /* Look for ext. headers: */ if (get_totalsize(mc_hdr) <= intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE) - return 0; + return false; ext_hdr = mc + intel_microcode_get_datasize(mc_hdr) + MC_HEADER_SIZE; ext_sig = (void *)ext_hdr + EXT_HEADER_SIZE; for (i = 0; i < ext_hdr->count; i++) { - if (intel_cpu_signatures_match(csig, cpf, ext_sig->sig, ext_sig->pf)) - return 1; + if (cpu_signatures_match(sig, ext_sig->sig, ext_sig->pf)) + return true; ext_sig++; } return 0; @@ -240,264 +234,91 @@ int intel_microcode_sanity_check(void *mc, bool print_err, int hdr_type) } EXPORT_SYMBOL_GPL(intel_microcode_sanity_check); -/* - * Returns 1 if update has been found, 0 otherwise. - */ -static int has_newer_microcode(void *mc, unsigned int csig, int cpf, int new_rev) +static void update_ucode_pointer(struct microcode_intel *mc) { - struct microcode_header_intel *mc_hdr = mc; - - if (mc_hdr->rev <= new_rev) - return 0; - - return intel_find_matching_signature(mc, csig, cpf); -} - -static struct ucode_patch *memdup_patch(void *data, unsigned int size) -{ - struct ucode_patch *p; - - p = kzalloc(sizeof(struct ucode_patch), GFP_KERNEL); - if (!p) - return NULL; - - p->data = kmemdup(data, size, GFP_KERNEL); - if (!p->data) { - kfree(p); - return NULL; - } - - return p; -} - -static void save_microcode_patch(struct ucode_cpu_info *uci, void *data, unsigned int size) -{ - struct microcode_header_intel *mc_hdr, *mc_saved_hdr; - struct ucode_patch *iter, *tmp, *p = NULL; - bool prev_found = false; - unsigned int sig, pf; - - mc_hdr = (struct microcode_header_intel *)data; - - list_for_each_entry_safe(iter, tmp, µcode_cache, plist) { - mc_saved_hdr = (struct microcode_header_intel *)iter->data; - sig = mc_saved_hdr->sig; - pf = mc_saved_hdr->pf; - - if (intel_find_matching_signature(data, sig, pf)) { - prev_found = true; - - if (mc_hdr->rev <= mc_saved_hdr->rev) - continue; - - p = memdup_patch(data, size); - if (!p) - pr_err("Error allocating buffer %p\n", data); - else { - list_replace(&iter->plist, &p->plist); - kfree(iter->data); - kfree(iter); - } - } - } + kvfree(ucode_patch_va); /* - * There weren't any previous patches found in the list cache; save the - * newly found. + * Save the virtual address for early loading and for eventual free + * on late loading. */ - if (!prev_found) { - p = memdup_patch(data, size); - if (!p) - pr_err("Error allocating buffer for %p\n", data); - else - list_add_tail(&p->plist, µcode_cache); - } - - if (!p) - return; + ucode_patch_va = mc; +} - if (!intel_find_matching_signature(p->data, uci->cpu_sig.sig, uci->cpu_sig.pf)) - return; +static void save_microcode_patch(struct microcode_intel *patch) +{ + unsigned int size = get_totalsize(&patch->hdr); + struct microcode_intel *mc; - /* - * Save for early loading. On 32-bit, that needs to be a physical - * address as the APs are running from physical addresses, before - * paging has been enabled. - */ - if (IS_ENABLED(CONFIG_X86_32)) - intel_ucode_patch = (struct microcode_intel *)__pa_nodebug(p->data); + mc = kvmemdup(patch, size, GFP_KERNEL); + if (mc) + update_ucode_pointer(mc); else - intel_ucode_patch = p->data; + pr_err("Unable to allocate microcode memory size: %u\n", size); } -/* - * Get microcode matching with BSP's model. Only CPUs with the same model as - * BSP can stay in the platform. - */ -static struct microcode_intel * -scan_microcode(void *data, size_t size, struct ucode_cpu_info *uci, bool save) +/* Scan blob for microcode matching the boot CPUs family, model, stepping */ +static __init struct microcode_intel *scan_microcode(void *data, size_t size, + struct ucode_cpu_info *uci, + bool save) { struct microcode_header_intel *mc_header; struct microcode_intel *patch = NULL; + u32 cur_rev = uci->cpu_sig.rev; unsigned int mc_size; - while (size) { - if (size < sizeof(struct microcode_header_intel)) - break; - + for (; size >= sizeof(struct microcode_header_intel); size -= mc_size, data += mc_size) { mc_header = (struct microcode_header_intel *)data; mc_size = get_totalsize(mc_header); - if (!mc_size || - mc_size > size || + if (!mc_size || mc_size > size || intel_microcode_sanity_check(data, false, MC_HEADER_TYPE_MICROCODE) < 0) break; - size -= mc_size; - - if (!intel_find_matching_signature(data, uci->cpu_sig.sig, - uci->cpu_sig.pf)) { - data += mc_size; + if (!intel_find_matching_signature(data, &uci->cpu_sig)) continue; - } + /* + * For saving the early microcode, find the matching revision which + * was loaded on the BSP. + * + * On the BSP during early boot, find a newer revision than + * actually loaded in the CPU. + */ if (save) { - save_microcode_patch(uci, data, mc_size); - goto next; - } - - - if (!patch) { - if (!has_newer_microcode(data, - uci->cpu_sig.sig, - uci->cpu_sig.pf, - uci->cpu_sig.rev)) - goto next; - - } else { - struct microcode_header_intel *phdr = &patch->hdr; - - if (!has_newer_microcode(data, - phdr->sig, - phdr->pf, - phdr->rev)) - goto next; + if (cur_rev != mc_header->rev) + continue; + } else if (cur_rev >= mc_header->rev) { + continue; } - /* We have a newer patch, save it. */ patch = data; - -next: - data += mc_size; - } - - if (size) - return NULL; - - return patch; -} - -static bool load_builtin_intel_microcode(struct cpio_data *cp) -{ - unsigned int eax = 1, ebx, ecx = 0, edx; - struct firmware fw; - char name[30]; - - if (IS_ENABLED(CONFIG_X86_32)) - return false; - - native_cpuid(&eax, &ebx, &ecx, &edx); - - sprintf(name, "intel-ucode/%02x-%02x-%02x", - x86_family(eax), x86_model(eax), x86_stepping(eax)); - - if (firmware_request_builtin(&fw, name)) { - cp->size = fw.size; - cp->data = (void *)fw.data; - return true; - } - - return false; -} - -static void print_ucode_info(int old_rev, int new_rev, unsigned int date) -{ - pr_info_once("updated early: 0x%x -> 0x%x, date = %04x-%02x-%02x\n", - old_rev, - new_rev, - date & 0xffff, - date >> 24, - (date >> 16) & 0xff); -} - -#ifdef CONFIG_X86_32 - -static int delay_ucode_info; -static int current_mc_date; -static int early_old_rev; - -/* - * Print early updated ucode info after printk works. This is delayed info dump. - */ -void show_ucode_info_early(void) -{ - struct ucode_cpu_info uci; - - if (delay_ucode_info) { - intel_cpu_collect_info(&uci); - print_ucode_info(early_old_rev, uci.cpu_sig.rev, current_mc_date); - delay_ucode_info = 0; + cur_rev = mc_header->rev; } -} - -/* - * At this point, we can not call printk() yet. Delay printing microcode info in - * show_ucode_info_early() until printk() works. - */ -static void print_ucode(int old_rev, int new_rev, int date) -{ - int *delay_ucode_info_p; - int *current_mc_date_p; - int *early_old_rev_p; - - delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info); - current_mc_date_p = (int *)__pa_nodebug(¤t_mc_date); - early_old_rev_p = (int *)__pa_nodebug(&early_old_rev); - - *delay_ucode_info_p = 1; - *current_mc_date_p = date; - *early_old_rev_p = old_rev; -} -#else -static inline void print_ucode(int old_rev, int new_rev, int date) -{ - print_ucode_info(old_rev, new_rev, date); + return size ? NULL : patch; } -#endif -static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) +static enum ucode_state __apply_microcode(struct ucode_cpu_info *uci, + struct microcode_intel *mc, + u32 *cur_rev) { - struct microcode_intel *mc; - u32 rev, old_rev; + u32 rev; - mc = uci->mc; if (!mc) - return 0; + return UCODE_NFOUND; /* * Save us the MSR write below - which is a particular expensive * operation - when the other hyperthread has updated the microcode * already. */ - rev = intel_get_microcode_revision(); - if (rev >= mc->hdr.rev) { - uci->cpu_sig.rev = rev; + *cur_rev = intel_get_microcode_revision(); + if (*cur_rev >= mc->hdr.rev) { + uci->cpu_sig.rev = *cur_rev; return UCODE_OK; } - old_rev = rev; - /* * Writeback and invalidate caches before updating microcode to avoid * internal issues depending on what the microcode is updating. @@ -509,247 +330,182 @@ static int apply_microcode_early(struct ucode_cpu_info *uci, bool early) rev = intel_get_microcode_revision(); if (rev != mc->hdr.rev) - return -1; + return UCODE_ERROR; uci->cpu_sig.rev = rev; + return UCODE_UPDATED; +} - if (early) - print_ucode(old_rev, uci->cpu_sig.rev, mc->hdr.date); - else - print_ucode_info(old_rev, uci->cpu_sig.rev, mc->hdr.date); +static enum ucode_state apply_microcode_early(struct ucode_cpu_info *uci) +{ + struct microcode_intel *mc = uci->mc; + enum ucode_state ret; + u32 cur_rev, date; - return 0; + ret = __apply_microcode(uci, mc, &cur_rev); + if (ret == UCODE_UPDATED) { + date = mc->hdr.date; + pr_info_once("updated early: 0x%x -> 0x%x, date = %04x-%02x-%02x\n", + cur_rev, mc->hdr.rev, date & 0xffff, date >> 24, (date >> 16) & 0xff); + } + return ret; } -int __init save_microcode_in_initrd_intel(void) +static __init bool load_builtin_intel_microcode(struct cpio_data *cp) { - struct ucode_cpu_info uci; - struct cpio_data cp; - - /* - * initrd is going away, clear patch ptr. We will scan the microcode one - * last time before jettisoning and save a patch, if found. Then we will - * update that pointer too, with a stable patch address to use when - * resuming the cores. - */ - intel_ucode_patch = NULL; + unsigned int eax = 1, ebx, ecx = 0, edx; + struct firmware fw; + char name[30]; - if (!load_builtin_intel_microcode(&cp)) - cp = find_microcode_in_initrd(ucode_path, false); + if (IS_ENABLED(CONFIG_X86_32)) + return false; - if (!(cp.data && cp.size)) - return 0; + native_cpuid(&eax, &ebx, &ecx, &edx); - intel_cpu_collect_info(&uci); + sprintf(name, "intel-ucode/%02x-%02x-%02x", + x86_family(eax), x86_model(eax), x86_stepping(eax)); - scan_microcode(cp.data, cp.size, &uci, true); - return 0; + if (firmware_request_builtin(&fw, name)) { + cp->size = fw.size; + cp->data = (void *)fw.data; + return true; + } + return false; } -/* - * @res_patch, output: a pointer to the patch we found. - */ -static struct microcode_intel *__load_ucode_intel(struct ucode_cpu_info *uci) +static __init struct microcode_intel *get_microcode_blob(struct ucode_cpu_info *uci, bool save) { - static const char *path; struct cpio_data cp; - bool use_pa; - - if (IS_ENABLED(CONFIG_X86_32)) { - path = (const char *)__pa_nodebug(ucode_path); - use_pa = true; - } else { - path = ucode_path; - use_pa = false; - } - /* try built-in microcode first */ if (!load_builtin_intel_microcode(&cp)) - cp = find_microcode_in_initrd(path, use_pa); + cp = find_microcode_in_initrd(ucode_path); if (!(cp.data && cp.size)) return NULL; - intel_cpu_collect_info(uci); + intel_collect_cpu_info(&uci->cpu_sig); - return scan_microcode(cp.data, cp.size, uci, false); + return scan_microcode(cp.data, cp.size, uci, save); } -void __init load_ucode_intel_bsp(void) +/* + * Invoked from an early init call to save the microcode blob which was + * selected during early boot when mm was not usable. The microcode must be + * saved because initrd is going away. It's an early init call so the APs + * just can use the pointer and do not have to scan initrd/builtin firmware + * again. + */ +static int __init save_builtin_microcode(void) { - struct microcode_intel *patch; struct ucode_cpu_info uci; - patch = __load_ucode_intel(&uci); - if (!patch) - return; + if (xchg(&ucode_patch_va, NULL) != UCODE_BSP_LOADED) + return 0; - uci.mc = patch; + if (dis_ucode_ldr || boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) + return 0; - apply_microcode_early(&uci, true); + uci.mc = get_microcode_blob(&uci, true); + if (uci.mc) + save_microcode_patch(uci.mc); + return 0; } +early_initcall(save_builtin_microcode); -void load_ucode_intel_ap(void) +/* Load microcode on BSP from initrd or builtin blobs */ +void __init load_ucode_intel_bsp(void) { - struct microcode_intel *patch, **iup; struct ucode_cpu_info uci; - if (IS_ENABLED(CONFIG_X86_32)) - iup = (struct microcode_intel **) __pa_nodebug(&intel_ucode_patch); - else - iup = &intel_ucode_patch; - - if (!*iup) { - patch = __load_ucode_intel(&uci); - if (!patch) - return; - - *iup = patch; - } - - uci.mc = *iup; - - apply_microcode_early(&uci, true); + uci.mc = get_microcode_blob(&uci, false); + if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED) + ucode_patch_va = UCODE_BSP_LOADED; } -static struct microcode_intel *find_patch(struct ucode_cpu_info *uci) +void load_ucode_intel_ap(void) { - struct microcode_header_intel *phdr; - struct ucode_patch *iter, *tmp; - - list_for_each_entry_safe(iter, tmp, µcode_cache, plist) { - - phdr = (struct microcode_header_intel *)iter->data; - - if (phdr->rev <= uci->cpu_sig.rev) - continue; - - if (!intel_find_matching_signature(phdr, - uci->cpu_sig.sig, - uci->cpu_sig.pf)) - continue; + struct ucode_cpu_info uci; - return iter->data; - } - return NULL; + uci.mc = ucode_patch_va; + if (uci.mc) + apply_microcode_early(&uci); } +/* Reload microcode on resume */ void reload_ucode_intel(void) { - struct microcode_intel *p; - struct ucode_cpu_info uci; - - intel_cpu_collect_info(&uci); - - p = find_patch(&uci); - if (!p) - return; - - uci.mc = p; + struct ucode_cpu_info uci = { .mc = ucode_patch_va, }; - apply_microcode_early(&uci, false); + if (uci.mc) + apply_microcode_early(&uci); } static int collect_cpu_info(int cpu_num, struct cpu_signature *csig) { - struct cpuinfo_x86 *c = &cpu_data(cpu_num); - unsigned int val[2]; - - memset(csig, 0, sizeof(*csig)); - - csig->sig = cpuid_eax(0x00000001); - - if ((c->x86_model >= 5) || (c->x86 > 6)) { - /* get processor flags from MSR 0x17 */ - rdmsr(MSR_IA32_PLATFORM_ID, val[0], val[1]); - csig->pf = 1 << ((val[1] >> 18) & 7); - } - - csig->rev = c->microcode; - + intel_collect_cpu_info(csig); return 0; } -static enum ucode_state apply_microcode_intel(int cpu) +static enum ucode_state apply_microcode_late(int cpu) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - struct cpuinfo_x86 *c = &cpu_data(cpu); - bool bsp = c->cpu_index == boot_cpu_data.cpu_index; - struct microcode_intel *mc; + struct microcode_intel *mc = ucode_patch_late; enum ucode_state ret; - static int prev_rev; - u32 rev; + u32 cur_rev; - /* We should bind the task to the CPU */ - if (WARN_ON(raw_smp_processor_id() != cpu)) + if (WARN_ON_ONCE(smp_processor_id() != cpu)) return UCODE_ERROR; - /* Look for a newer patch in our cache: */ - mc = find_patch(uci); - if (!mc) { - mc = uci->mc; - if (!mc) - return UCODE_NFOUND; - } + ret = __apply_microcode(uci, mc, &cur_rev); + if (ret != UCODE_UPDATED && ret != UCODE_OK) + return ret; - /* - * Save us the MSR write below - which is a particular expensive - * operation - when the other hyperthread has updated the microcode - * already. - */ - rev = intel_get_microcode_revision(); - if (rev >= mc->hdr.rev) { - ret = UCODE_OK; - goto out; + if (!cpu && uci->cpu_sig.rev != cur_rev) { + pr_info("Updated to revision 0x%x, date = %04x-%02x-%02x\n", + uci->cpu_sig.rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24, + (mc->hdr.date >> 16) & 0xff); } - /* - * Writeback and invalidate caches before updating microcode to avoid - * internal issues depending on what the microcode is updating. - */ - native_wbinvd(); + cpu_data(cpu).microcode = uci->cpu_sig.rev; + if (!cpu) + boot_cpu_data.microcode = uci->cpu_sig.rev; - /* write microcode via MSR 0x79 */ - wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits); + return ret; +} - rev = intel_get_microcode_revision(); +static bool ucode_validate_minrev(struct microcode_header_intel *mc_header) +{ + int cur_rev = boot_cpu_data.microcode; - if (rev != mc->hdr.rev) { - pr_err("CPU%d update to revision 0x%x failed\n", - cpu, mc->hdr.rev); - return UCODE_ERROR; + /* + * When late-loading, ensure the header declares a minimum revision + * required to perform a late-load. The previously reserved field + * is 0 in older microcode blobs. + */ + if (!mc_header->min_req_ver) { + pr_info("Unsafe microcode update: Microcode header does not specify a required min version\n"); + return false; } - if (bsp && rev != prev_rev) { - pr_info("updated to revision 0x%x, date = %04x-%02x-%02x\n", - rev, - mc->hdr.date & 0xffff, - mc->hdr.date >> 24, - (mc->hdr.date >> 16) & 0xff); - prev_rev = rev; + /* + * Check whether the current revision is either greater or equal to + * to the minimum revision specified in the header. + */ + if (cur_rev < mc_header->min_req_ver) { + pr_info("Unsafe microcode update: Current revision 0x%x too old\n", cur_rev); + pr_info("Current should be at 0x%x or higher. Use early loading instead\n", mc_header->min_req_ver); + return false; } - - ret = UCODE_UPDATED; - -out: - uci->cpu_sig.rev = rev; - c->microcode = rev; - - /* Update boot_cpu_data's revision too, if we're on the BSP: */ - if (bsp) - boot_cpu_data.microcode = rev; - - return ret; + return true; } -static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter) +static enum ucode_state parse_microcode_blobs(int cpu, struct iov_iter *iter) { struct ucode_cpu_info *uci = ucode_cpu_info + cpu; - unsigned int curr_mc_size = 0, new_mc_size = 0; - enum ucode_state ret = UCODE_OK; - int new_rev = uci->cpu_sig.rev; + bool is_safe, new_is_safe = false; + int cur_rev = uci->cpu_sig.rev; + unsigned int curr_mc_size = 0; u8 *new_mc = NULL, *mc = NULL; - unsigned int csig, cpf; while (iov_iter_count(iter)) { struct microcode_header_intel mc_header; @@ -758,68 +514,66 @@ static enum ucode_state generic_load_microcode(int cpu, struct iov_iter *iter) if (!copy_from_iter_full(&mc_header, sizeof(mc_header), iter)) { pr_err("error! Truncated or inaccessible header in microcode data file\n"); - break; + goto fail; } mc_size = get_totalsize(&mc_header); if (mc_size < sizeof(mc_header)) { pr_err("error! Bad data in microcode data file (totalsize too small)\n"); - break; + goto fail; } data_size = mc_size - sizeof(mc_header); if (data_size > iov_iter_count(iter)) { pr_err("error! Bad data in microcode data file (truncated file?)\n"); - break; + goto fail; } /* For performance reasons, reuse mc area when possible */ if (!mc || mc_size > curr_mc_size) { - vfree(mc); - mc = vmalloc(mc_size); + kvfree(mc); + mc = kvmalloc(mc_size, GFP_KERNEL); if (!mc) - break; + goto fail; curr_mc_size = mc_size; } memcpy(mc, &mc_header, sizeof(mc_header)); data = mc + sizeof(mc_header); if (!copy_from_iter_full(data, data_size, iter) || - intel_microcode_sanity_check(mc, true, MC_HEADER_TYPE_MICROCODE) < 0) { - break; - } + intel_microcode_sanity_check(mc, true, MC_HEADER_TYPE_MICROCODE) < 0) + goto fail; - csig = uci->cpu_sig.sig; - cpf = uci->cpu_sig.pf; - if (has_newer_microcode(mc, csig, cpf, new_rev)) { - vfree(new_mc); - new_rev = mc_header.rev; - new_mc = mc; - new_mc_size = mc_size; - mc = NULL; /* trigger new vmalloc */ - ret = UCODE_NEW; - } - } + if (cur_rev >= mc_header.rev) + continue; - vfree(mc); + if (!intel_find_matching_signature(mc, &uci->cpu_sig)) + continue; - if (iov_iter_count(iter)) { - vfree(new_mc); - return UCODE_ERROR; + is_safe = ucode_validate_minrev(&mc_header); + if (force_minrev && !is_safe) + continue; + + kvfree(new_mc); + cur_rev = mc_header.rev; + new_mc = mc; + new_is_safe = is_safe; + mc = NULL; } + if (iov_iter_count(iter)) + goto fail; + + kvfree(mc); if (!new_mc) return UCODE_NFOUND; - vfree(uci->mc); - uci->mc = (struct microcode_intel *)new_mc; - - /* Save for CPU hotplug */ - save_microcode_patch(uci, new_mc, new_mc_size); + ucode_patch_late = (struct microcode_intel *)new_mc; + return new_is_safe ? UCODE_NEW_SAFE : UCODE_NEW; - pr_debug("CPU%d found a matching microcode update with version 0x%x (current=0x%x)\n", - cpu, new_rev, uci->cpu_sig.rev); - - return ret; +fail: + kvfree(mc); + kvfree(new_mc); + return UCODE_ERROR; } static bool is_blacklisted(unsigned int cpu) @@ -868,26 +622,36 @@ static enum ucode_state request_microcode_fw(int cpu, struct device *device) kvec.iov_base = (void *)firmware->data; kvec.iov_len = firmware->size; iov_iter_kvec(&iter, ITER_SOURCE, &kvec, 1, firmware->size); - ret = generic_load_microcode(cpu, &iter); + ret = parse_microcode_blobs(cpu, &iter); release_firmware(firmware); return ret; } +static void finalize_late_load(int result) +{ + if (!result) + update_ucode_pointer(ucode_patch_late); + else + kvfree(ucode_patch_late); + ucode_patch_late = NULL; +} + static struct microcode_ops microcode_intel_ops = { - .request_microcode_fw = request_microcode_fw, - .collect_cpu_info = collect_cpu_info, - .apply_microcode = apply_microcode_intel, + .request_microcode_fw = request_microcode_fw, + .collect_cpu_info = collect_cpu_info, + .apply_microcode = apply_microcode_late, + .finalize_late_load = finalize_late_load, + .use_nmi = IS_ENABLED(CONFIG_X86_64), }; -static int __init calc_llc_size_per_core(struct cpuinfo_x86 *c) +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); - - return (int)llc_size; + llc_size_per_core = (unsigned int)llc_size; } struct microcode_ops * __init init_intel_microcode(void) @@ -900,7 +664,7 @@ struct microcode_ops * __init init_intel_microcode(void) return NULL; } - llc_size_per_core = calc_llc_size_per_core(c); + calc_llc_size_per_core(c); return µcode_intel_ops; } diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h index bf883aa71233..f8047b12329a 100644 --- a/arch/x86/kernel/cpu/microcode/internal.h +++ b/arch/x86/kernel/cpu/microcode/internal.h @@ -8,43 +8,37 @@ #include <asm/cpu.h> #include <asm/microcode.h> -struct ucode_patch { - struct list_head plist; - void *data; /* Intel uses only this one */ - unsigned int size; - u32 patch_id; - u16 equiv_cpu; -}; - -extern struct list_head microcode_cache; - struct device; enum ucode_state { UCODE_OK = 0, UCODE_NEW, + UCODE_NEW_SAFE, UCODE_UPDATED, UCODE_NFOUND, UCODE_ERROR, + UCODE_TIMEOUT, + UCODE_OFFLINE, }; struct microcode_ops { enum ucode_state (*request_microcode_fw)(int cpu, struct device *dev); - void (*microcode_fini_cpu)(int cpu); /* - * The generic 'microcode_core' part guarantees that - * the callbacks below run on a target cpu when they - * are being called. + * The generic 'microcode_core' part guarantees that the callbacks + * below run on a target CPU when they are being called. * See also the "Synchronization" section in microcode_core.c. */ - enum ucode_state (*apply_microcode)(int cpu); - int (*collect_cpu_info)(int cpu, struct cpu_signature *csig); + enum ucode_state (*apply_microcode)(int cpu); + int (*collect_cpu_info)(int cpu, struct cpu_signature *csig); + void (*finalize_late_load)(int result); + unsigned int nmi_safe : 1, + use_nmi : 1; }; extern struct ucode_cpu_info ucode_cpu_info[]; -struct cpio_data find_microcode_in_initrd(const char *path, bool use_pa); +struct cpio_data find_microcode_in_initrd(const char *path); #define MAX_UCODE_COUNT 128 @@ -94,12 +88,12 @@ static inline unsigned int x86_cpuid_family(void) return x86_family(eax); } -extern bool initrd_gone; +extern bool dis_ucode_ldr; +extern bool force_minrev; #ifdef CONFIG_CPU_SUP_AMD void load_ucode_amd_bsp(unsigned int family); void load_ucode_amd_ap(unsigned int family); -void load_ucode_amd_early(unsigned int cpuid_1_eax); int save_microcode_in_initrd_amd(unsigned int family); void reload_ucode_amd(unsigned int cpu); struct microcode_ops *init_amd_microcode(void); @@ -107,7 +101,6 @@ void exit_amd_microcode(void); #else /* CONFIG_CPU_SUP_AMD */ static inline void load_ucode_amd_bsp(unsigned int family) { } static inline void load_ucode_amd_ap(unsigned int family) { } -static inline void load_ucode_amd_early(unsigned int family) { } static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; } static inline void reload_ucode_amd(unsigned int cpu) { } static inline struct microcode_ops *init_amd_microcode(void) { return NULL; } @@ -117,13 +110,11 @@ static inline void exit_amd_microcode(void) { } #ifdef CONFIG_CPU_SUP_INTEL void load_ucode_intel_bsp(void); void load_ucode_intel_ap(void); -int save_microcode_in_initrd_intel(void); void reload_ucode_intel(void); struct microcode_ops *init_intel_microcode(void); #else /* CONFIG_CPU_SUP_INTEL */ static inline void load_ucode_intel_bsp(void) { } static inline void load_ucode_intel_ap(void) { } -static inline int save_microcode_in_initrd_intel(void) { return -EINVAL; } static inline void reload_ucode_intel(void) { } static inline struct microcode_ops *init_intel_microcode(void) { return NULL; } #endif /* !CONFIG_CPU_SUP_INTEL */ diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index 31c0e68f6227..e65fae63660e 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -20,13 +20,13 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c, unsigned int cpu) { #ifdef CONFIG_SMP - seq_printf(m, "physical id\t: %d\n", c->phys_proc_id); + seq_printf(m, "physical id\t: %d\n", c->topo.pkg_id); seq_printf(m, "siblings\t: %d\n", cpumask_weight(topology_core_cpumask(cpu))); - seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id); + seq_printf(m, "core id\t\t: %d\n", c->topo.core_id); seq_printf(m, "cpu cores\t: %d\n", c->booted_cores); - seq_printf(m, "apicid\t\t: %d\n", c->apicid); - seq_printf(m, "initial apicid\t: %d\n", c->initial_apicid); + seq_printf(m, "apicid\t\t: %d\n", c->topo.apicid); + seq_printf(m, "initial apicid\t: %d\n", c->topo.initial_apicid); #endif } diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 030d3b409768..19e0681f0435 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -152,6 +152,7 @@ static inline void cache_alloc_hsw_probe(void) r->cache.cbm_len = 20; r->cache.shareable_bits = 0xc0000; r->cache.min_cbm_bits = 2; + r->cache.arch_has_sparse_bitmasks = false; r->alloc_capable = true; rdt_alloc_capable = true; @@ -267,15 +268,18 @@ static void rdt_get_cache_alloc_cfg(int idx, struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_1_eax eax; + union cpuid_0x10_x_ecx ecx; union cpuid_0x10_x_edx edx; - u32 ebx, ecx; + u32 ebx; - cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx, &edx.full); + cpuid_count(0x00000010, idx, &eax.full, &ebx, &ecx.full, &edx.full); hw_res->num_closid = edx.split.cos_max + 1; r->cache.cbm_len = eax.split.cbm_len + 1; r->default_ctrl = BIT_MASK(eax.split.cbm_len + 1) - 1; r->cache.shareable_bits = ebx & r->default_ctrl; r->data_width = (r->cache.cbm_len + 3) / 4; + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + r->cache.arch_has_sparse_bitmasks = ecx.split.noncont; r->alloc_capable = true; } @@ -872,7 +876,6 @@ static __init void rdt_init_res_defs_intel(void) if (r->rid == RDT_RESOURCE_L3 || r->rid == RDT_RESOURCE_L2) { - r->cache.arch_has_sparse_bitmaps = false; r->cache.arch_has_per_cpu_cfg = false; r->cache.min_cbm_bits = 1; } else if (r->rid == RDT_RESOURCE_MBA) { @@ -892,7 +895,7 @@ static __init void rdt_init_res_defs_amd(void) if (r->rid == RDT_RESOURCE_L3 || r->rid == RDT_RESOURCE_L2) { - r->cache.arch_has_sparse_bitmaps = true; + r->cache.arch_has_sparse_bitmasks = true; r->cache.arch_has_per_cpu_cfg = true; r->cache.min_cbm_bits = 0; } else if (r->rid == RDT_RESOURCE_MBA) { diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index b44c487727d4..beccb0e87ba7 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -87,10 +87,12 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, /* * Check whether a cache bit mask is valid. - * For Intel the SDM says: - * Please note that all (and only) contiguous '1' combinations - * are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.). - * Additionally Haswell requires at least two bits set. + * On Intel CPUs, non-contiguous 1s value support is indicated by CPUID: + * - CPUID.0x10.1:ECX[3]: L3 non-contiguous 1s value supported if 1 + * - CPUID.0x10.2:ECX[3]: L2 non-contiguous 1s value supported if 1 + * + * Haswell does not support a non-contiguous 1s value and additionally + * requires at least two bits set. * AMD allows non-contiguous bitmasks. */ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) @@ -113,8 +115,8 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r) first_bit = find_first_bit(&val, cbm_len); zero_bit = find_next_zero_bit(&val, cbm_len, first_bit); - /* Are non-contiguous bitmaps allowed? */ - if (!r->cache.arch_has_sparse_bitmaps && + /* Are non-contiguous bitmasks allowed? */ + if (!r->cache.arch_has_sparse_bitmasks && (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) { rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val); return false; diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h index 85ceaf9a31ac..a4f1aa15f0a2 100644 --- a/arch/x86/kernel/cpu/resctrl/internal.h +++ b/arch/x86/kernel/cpu/resctrl/internal.h @@ -59,6 +59,7 @@ struct rdt_fs_context { bool enable_cdpl2; bool enable_cdpl3; bool enable_mba_mbps; + bool enable_debug; }; static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc) @@ -243,18 +244,17 @@ struct rdtgroup { */ #define RFTYPE_INFO BIT(0) #define RFTYPE_BASE BIT(1) -#define RF_CTRLSHIFT 4 -#define RF_MONSHIFT 5 -#define RF_TOPSHIFT 6 -#define RFTYPE_CTRL BIT(RF_CTRLSHIFT) -#define RFTYPE_MON BIT(RF_MONSHIFT) -#define RFTYPE_TOP BIT(RF_TOPSHIFT) +#define RFTYPE_CTRL BIT(4) +#define RFTYPE_MON BIT(5) +#define RFTYPE_TOP BIT(6) #define RFTYPE_RES_CACHE BIT(8) #define RFTYPE_RES_MB BIT(9) -#define RF_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) -#define RF_MON_INFO (RFTYPE_INFO | RFTYPE_MON) -#define RF_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP) -#define RF_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL) +#define RFTYPE_DEBUG BIT(10) +#define RFTYPE_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL) +#define RFTYPE_MON_INFO (RFTYPE_INFO | RFTYPE_MON) +#define RFTYPE_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP) +#define RFTYPE_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL) +#define RFTYPE_MON_BASE (RFTYPE_BASE | RFTYPE_MON) /* List of all resource groups */ extern struct list_head rdt_all_groups; @@ -270,7 +270,7 @@ void __exit rdtgroup_exit(void); * @mode: Access mode * @kf_ops: File operations * @flags: File specific RFTYPE_FLAGS_* flags - * @fflags: File specific RF_* or RFTYPE_* flags + * @fflags: File specific RFTYPE_* flags * @seq_show: Show content of the file * @write: Write to the file */ @@ -492,6 +492,15 @@ union cpuid_0x10_3_eax { unsigned int full; }; +/* CPUID.(EAX=10H, ECX=ResID).ECX */ +union cpuid_0x10_x_ecx { + struct { + unsigned int reserved:3; + unsigned int noncont:1; + } split; + unsigned int full; +}; + /* CPUID.(EAX=10H, ECX=ResID).EDX */ union cpuid_0x10_x_edx { struct { diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index ded1fc7cb7cb..f136ac046851 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -30,15 +30,15 @@ struct rmid_entry { struct list_head list; }; -/** - * @rmid_free_lru A least recently used list of free RMIDs +/* + * @rmid_free_lru - A least recently used list of free RMIDs * These RMIDs are guaranteed to have an occupancy less than the * threshold occupancy */ static LIST_HEAD(rmid_free_lru); -/** - * @rmid_limbo_count count of currently unused but (potentially) +/* + * @rmid_limbo_count - count of currently unused but (potentially) * dirty RMIDs. * This counts RMIDs that no one is currently using but that * may have a occupancy value > resctrl_rmid_realloc_threshold. User can @@ -46,7 +46,7 @@ static LIST_HEAD(rmid_free_lru); */ static unsigned int rmid_limbo_count; -/** +/* * @rmid_entry - The entry in the limbo and free lists. */ static struct rmid_entry *rmid_ptrs; diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c index 725344048f85..69a1de92384a 100644 --- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c +++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c @@ -54,8 +54,13 @@ static struct kernfs_node *kn_mondata; static struct seq_buf last_cmd_status; static char last_cmd_status_buf[512]; +static int rdtgroup_setup_root(struct rdt_fs_context *ctx); +static void rdtgroup_destroy_root(void); + struct dentry *debugfs_resctrl; +static bool resctrl_debug; + void rdt_last_cmd_clear(void) { lockdep_assert_held(&rdtgroup_mutex); @@ -696,11 +701,10 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct rdtgroup *rdtgrp; + char *pid_str; int ret = 0; pid_t pid; - if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) - return -EINVAL; rdtgrp = rdtgroup_kn_lock_live(of->kn); if (!rdtgrp) { rdtgroup_kn_unlock(of->kn); @@ -715,7 +719,27 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of, goto unlock; } - ret = rdtgroup_move_task(pid, rdtgrp, of); + while (buf && buf[0] != '\0' && buf[0] != '\n') { + pid_str = strim(strsep(&buf, ",")); + + if (kstrtoint(pid_str, 0, &pid)) { + rdt_last_cmd_printf("Task list parsing error pid %s\n", pid_str); + ret = -EINVAL; + break; + } + + if (pid < 0) { + rdt_last_cmd_printf("Invalid pid %d\n", pid); + ret = -EINVAL; + break; + } + + ret = rdtgroup_move_task(pid, rdtgrp, of); + if (ret) { + rdt_last_cmd_printf("Error while processing task %d\n", pid); + break; + } + } unlock: rdtgroup_kn_unlock(of->kn); @@ -755,6 +779,38 @@ static int rdtgroup_tasks_show(struct kernfs_open_file *of, return ret; } +static int rdtgroup_closid_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (rdtgrp) + seq_printf(s, "%u\n", rdtgrp->closid); + else + ret = -ENOENT; + rdtgroup_kn_unlock(of->kn); + + return ret; +} + +static int rdtgroup_rmid_show(struct kernfs_open_file *of, + struct seq_file *s, void *v) +{ + struct rdtgroup *rdtgrp; + int ret = 0; + + rdtgrp = rdtgroup_kn_lock_live(of->kn); + if (rdtgrp) + seq_printf(s, "%u\n", rdtgrp->mon.rmid); + else + ret = -ENOENT; + rdtgroup_kn_unlock(of->kn); + + return ret; +} + #ifdef CONFIG_PROC_CPU_RESCTRL /* @@ -895,7 +951,7 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of, return 0; } -/** +/* * rdt_bit_usage_show - Display current usage of resources * * A domain is a shared resource that can now be allocated differently. Here @@ -1117,12 +1173,24 @@ static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type) } } +static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of, + struct seq_file *seq, void *v) +{ + struct resctrl_schema *s = of->kn->parent->priv; + struct rdt_resource *r = s->res; + + seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks); + + return 0; +} + /** * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other * @r: Resource to which domain instance @d belongs. * @d: The domain instance for which @closid is being tested. * @cbm: Capacity bitmask being tested. * @closid: Intended closid for @cbm. + * @type: CDP type of @r. * @exclusive: Only check if overlaps with exclusive resource groups * * Checks if provided @cbm intended to be used for @closid on domain @@ -1209,6 +1277,7 @@ bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d, /** * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive + * @rdtgrp: Resource group identified through its closid. * * An exclusive resource group implies that there should be no sharing of * its allocated resources. At the time this group is considered to be @@ -1251,9 +1320,8 @@ static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp) return true; } -/** +/* * rdtgroup_mode_write - Modify the resource group's mode - * */ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) @@ -1357,12 +1425,11 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, return size; } -/** +/* * rdtgroup_size_show - Display size in bytes of allocated regions * * The "size" file mirrors the layout of the "schemata" file, printing the * size in bytes of each region instead of the capacity bitmask. - * */ static int rdtgroup_size_show(struct kernfs_open_file *of, struct seq_file *s, void *v) @@ -1686,77 +1753,77 @@ static struct rftype res_common_files[] = { .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_last_cmd_status_show, - .fflags = RF_TOP_INFO, + .fflags = RFTYPE_TOP_INFO, }, { .name = "num_closids", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_num_closids_show, - .fflags = RF_CTRL_INFO, + .fflags = RFTYPE_CTRL_INFO, }, { .name = "mon_features", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_mon_features_show, - .fflags = RF_MON_INFO, + .fflags = RFTYPE_MON_INFO, }, { .name = "num_rmids", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_num_rmids_show, - .fflags = RF_MON_INFO, + .fflags = RFTYPE_MON_INFO, }, { .name = "cbm_mask", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_default_ctrl_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "min_cbm_bits", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_min_cbm_bits_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "shareable_bits", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_shareable_bits_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "bit_usage", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_bit_usage_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_CACHE, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, }, { .name = "min_bandwidth", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_min_bw_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB, }, { .name = "bandwidth_gran", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_bw_gran_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB, }, { .name = "delay_linear", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdt_delay_linear_show, - .fflags = RF_CTRL_INFO | RFTYPE_RES_MB, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB, }, /* * Platform specific which (if any) capabilities are provided by @@ -1775,7 +1842,7 @@ static struct rftype res_common_files[] = { .kf_ops = &rdtgroup_kf_single_ops, .write = max_threshold_occ_write, .seq_show = max_threshold_occ_show, - .fflags = RF_MON_INFO | RFTYPE_RES_CACHE, + .fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE, }, { .name = "mbm_total_bytes_config", @@ -1817,12 +1884,19 @@ static struct rftype res_common_files[] = { .fflags = RFTYPE_BASE, }, { + .name = "mon_hw_id", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdtgroup_rmid_show, + .fflags = RFTYPE_MON_BASE | RFTYPE_DEBUG, + }, + { .name = "schemata", .mode = 0644, .kf_ops = &rdtgroup_kf_single_ops, .write = rdtgroup_schemata_write, .seq_show = rdtgroup_schemata_show, - .fflags = RF_CTRL_BASE, + .fflags = RFTYPE_CTRL_BASE, }, { .name = "mode", @@ -1830,14 +1904,28 @@ static struct rftype res_common_files[] = { .kf_ops = &rdtgroup_kf_single_ops, .write = rdtgroup_mode_write, .seq_show = rdtgroup_mode_show, - .fflags = RF_CTRL_BASE, + .fflags = RFTYPE_CTRL_BASE, }, { .name = "size", .mode = 0444, .kf_ops = &rdtgroup_kf_single_ops, .seq_show = rdtgroup_size_show, - .fflags = RF_CTRL_BASE, + .fflags = RFTYPE_CTRL_BASE, + }, + { + .name = "sparse_masks", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdt_has_sparse_bitmasks_show, + .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE, + }, + { + .name = "ctrl_hw_id", + .mode = 0444, + .kf_ops = &rdtgroup_kf_single_ops, + .seq_show = rdtgroup_closid_show, + .fflags = RFTYPE_CTRL_BASE | RFTYPE_DEBUG, }, }; @@ -1852,6 +1940,9 @@ static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags) lockdep_assert_held(&rdtgroup_mutex); + if (resctrl_debug) + fflags |= RFTYPE_DEBUG; + for (rft = rfts; rft < rfts + len; rft++) { if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) { ret = rdtgroup_add_file(kn, rft); @@ -1894,7 +1985,7 @@ void __init thread_throttle_mode_init(void) if (!rft) return; - rft->fflags = RF_CTRL_INFO | RFTYPE_RES_MB; + rft->fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB; } void __init mbm_config_rftype_init(const char *config) @@ -1903,7 +1994,7 @@ void __init mbm_config_rftype_init(const char *config) rft = rdtgroup_get_rftype_by_name(config); if (rft) - rft->fflags = RF_MON_INFO | RFTYPE_RES_CACHE; + rft->fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE; } /** @@ -2038,21 +2129,21 @@ static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn) if (IS_ERR(kn_info)) return PTR_ERR(kn_info); - ret = rdtgroup_add_files(kn_info, RF_TOP_INFO); + ret = rdtgroup_add_files(kn_info, RFTYPE_TOP_INFO); if (ret) goto out_destroy; /* loop over enabled controls, these are all alloc_capable */ list_for_each_entry(s, &resctrl_schema_all, list) { r = s->res; - fflags = r->fflags | RF_CTRL_INFO; + fflags = r->fflags | RFTYPE_CTRL_INFO; ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags); if (ret) goto out_destroy; } for_each_mon_capable_rdt_resource(r) { - fflags = r->fflags | RF_MON_INFO; + fflags = r->fflags | RFTYPE_MON_INFO; sprintf(name, "%s_MON", r->name); ret = rdtgroup_mkdir_info_resdir(r, name, fflags); if (ret) @@ -2271,14 +2362,6 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable) return 0; } -static void cdp_disable_all(void) -{ - if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3)) - resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); - if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) - resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); -} - /* * We don't allow rdtgroup directories to be created anywhere * except the root directory. Thus when looking for the rdtgroup @@ -2358,19 +2441,47 @@ static int mkdir_mondata_all(struct kernfs_node *parent_kn, struct rdtgroup *prgrp, struct kernfs_node **mon_data_kn); +static void rdt_disable_ctx(void) +{ + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); + set_mba_sc(false); + + resctrl_debug = false; +} + static int rdt_enable_ctx(struct rdt_fs_context *ctx) { int ret = 0; - if (ctx->enable_cdpl2) + if (ctx->enable_cdpl2) { ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true); + if (ret) + goto out_done; + } - if (!ret && ctx->enable_cdpl3) + if (ctx->enable_cdpl3) { ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true); + if (ret) + goto out_cdpl2; + } - if (!ret && ctx->enable_mba_mbps) + if (ctx->enable_mba_mbps) { ret = set_mba_sc(true); + if (ret) + goto out_cdpl3; + } + + if (ctx->enable_debug) + resctrl_debug = true; + return 0; + +out_cdpl3: + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false); +out_cdpl2: + resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false); +out_done: return ret; } @@ -2463,6 +2574,7 @@ static void schemata_list_destroy(void) static int rdt_get_tree(struct fs_context *fc) { struct rdt_fs_context *ctx = rdt_fc2context(fc); + unsigned long flags = RFTYPE_CTRL_BASE; struct rdt_domain *dom; struct rdt_resource *r; int ret; @@ -2477,18 +2589,31 @@ static int rdt_get_tree(struct fs_context *fc) goto out; } + ret = rdtgroup_setup_root(ctx); + if (ret) + goto out; + ret = rdt_enable_ctx(ctx); - if (ret < 0) - goto out_cdp; + if (ret) + goto out_root; ret = schemata_list_create(); if (ret) { schemata_list_destroy(); - goto out_mba; + goto out_ctx; } closid_init(); + if (rdt_mon_capable) + flags |= RFTYPE_MON; + + ret = rdtgroup_add_files(rdtgroup_default.kn, flags); + if (ret) + goto out_schemata_free; + + kernfs_activate(rdtgroup_default.kn); + ret = rdtgroup_create_info_dir(rdtgroup_default.kn); if (ret < 0) goto out_schemata_free; @@ -2543,11 +2668,10 @@ out_info: kernfs_remove(kn_info); out_schemata_free: schemata_list_destroy(); -out_mba: - if (ctx->enable_mba_mbps) - set_mba_sc(false); -out_cdp: - cdp_disable_all(); +out_ctx: + rdt_disable_ctx(); +out_root: + rdtgroup_destroy_root(); out: rdt_last_cmd_clear(); mutex_unlock(&rdtgroup_mutex); @@ -2559,6 +2683,7 @@ enum rdt_param { Opt_cdp, Opt_cdpl2, Opt_mba_mbps, + Opt_debug, nr__rdt_params }; @@ -2566,6 +2691,7 @@ static const struct fs_parameter_spec rdt_fs_parameters[] = { fsparam_flag("cdp", Opt_cdp), fsparam_flag("cdpl2", Opt_cdpl2), fsparam_flag("mba_MBps", Opt_mba_mbps), + fsparam_flag("debug", Opt_debug), {} }; @@ -2591,6 +2717,9 @@ static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param) return -EINVAL; ctx->enable_mba_mbps = true; return 0; + case Opt_debug: + ctx->enable_debug = true; + return 0; } return -EINVAL; @@ -2618,7 +2747,6 @@ static int rdt_init_fs_context(struct fs_context *fc) if (!ctx) return -ENOMEM; - ctx->kfc.root = rdt_root; ctx->kfc.magic = RDTGROUP_SUPER_MAGIC; fc->fs_private = &ctx->kfc; fc->ops = &rdt_fs_context_ops; @@ -2779,16 +2907,16 @@ static void rdt_kill_sb(struct super_block *sb) cpus_read_lock(); mutex_lock(&rdtgroup_mutex); - set_mba_sc(false); + rdt_disable_ctx(); /*Put everything back to default values. */ for_each_alloc_capable_rdt_resource(r) reset_all_ctrls(r); - cdp_disable_all(); rmdir_all_sub(); rdt_pseudo_lock_release(); 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); @@ -3170,8 +3298,8 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, enum rdt_group_type rtype, struct rdtgroup **r) { struct rdtgroup *prdtgrp, *rdtgrp; + unsigned long files = 0; struct kernfs_node *kn; - uint files = 0; int ret; prdtgrp = rdtgroup_kn_lock_live(parent_kn); @@ -3223,7 +3351,14 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn, goto out_destroy; } - files = RFTYPE_BASE | BIT(RF_CTRLSHIFT + rtype); + if (rtype == RDTCTRL_GROUP) { + files = RFTYPE_BASE | RFTYPE_CTRL; + if (rdt_mon_capable) + files |= RFTYPE_MON; + } else { + files = RFTYPE_BASE | RFTYPE_MON; + } + ret = rdtgroup_add_files(kn, files); if (ret) { rdt_last_cmd_puts("kernfs fill error\n"); @@ -3656,6 +3791,9 @@ static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf) if (is_mba_sc(&rdt_resources_all[RDT_RESOURCE_MBA].r_resctrl)) seq_puts(seq, ",mba_MBps"); + if (resctrl_debug) + seq_puts(seq, ",debug"); + return 0; } @@ -3666,10 +3804,8 @@ static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = { .show_options = rdtgroup_show_options, }; -static int __init rdtgroup_setup_root(void) +static int rdtgroup_setup_root(struct rdt_fs_context *ctx) { - int ret; - rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops, KERNFS_ROOT_CREATE_DEACTIVATED | KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK, @@ -3677,6 +3813,20 @@ static int __init rdtgroup_setup_root(void) if (IS_ERR(rdt_root)) return PTR_ERR(rdt_root); + ctx->kfc.root = rdt_root; + rdtgroup_default.kn = kernfs_root_to_node(rdt_root); + + return 0; +} + +static void rdtgroup_destroy_root(void) +{ + kernfs_destroy_root(rdt_root); + rdtgroup_default.kn = NULL; +} + +static void __init rdtgroup_setup_default(void) +{ mutex_lock(&rdtgroup_mutex); rdtgroup_default.closid = 0; @@ -3686,19 +3836,7 @@ static int __init rdtgroup_setup_root(void) list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups); - ret = rdtgroup_add_files(kernfs_root_to_node(rdt_root), RF_CTRL_BASE); - if (ret) { - kernfs_destroy_root(rdt_root); - goto out; - } - - rdtgroup_default.kn = kernfs_root_to_node(rdt_root); - kernfs_activate(rdtgroup_default.kn); - -out: mutex_unlock(&rdtgroup_mutex); - - return ret; } static void domain_destroy_mon_state(struct rdt_domain *d) @@ -3820,13 +3958,11 @@ int __init rdtgroup_init(void) seq_buf_init(&last_cmd_status, last_cmd_status_buf, sizeof(last_cmd_status_buf)); - ret = rdtgroup_setup_root(); - if (ret) - return ret; + rdtgroup_setup_default(); ret = sysfs_create_mount_point(fs_kobj, "resctrl"); if (ret) - goto cleanup_root; + return ret; ret = register_filesystem(&rdt_fs_type); if (ret) @@ -3859,8 +3995,6 @@ int __init rdtgroup_init(void) cleanup_mountpoint: sysfs_remove_mount_point(fs_kobj, "resctrl"); -cleanup_root: - kernfs_destroy_root(rdt_root); return ret; } @@ -3870,5 +4004,4 @@ void __exit rdtgroup_exit(void) debugfs_remove_recursive(debugfs_resctrl); unregister_filesystem(&rdt_fs_type); sysfs_remove_mount_point(fs_kobj, "resctrl"); - kernfs_destroy_root(rdt_root); } diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c index 91fa70e51004..279148e72459 100644 --- a/arch/x86/kernel/cpu/sgx/encl.c +++ b/arch/x86/kernel/cpu/sgx/encl.c @@ -235,6 +235,21 @@ static struct sgx_epc_page *sgx_encl_eldu(struct sgx_encl_page *encl_page, return epc_page; } +/* + * Ensure the SECS page is not swapped out. Must be called with encl->lock + * to protect the enclave states including SECS and ensure the SECS page is + * not swapped out again while being used. + */ +static struct sgx_epc_page *sgx_encl_load_secs(struct sgx_encl *encl) +{ + struct sgx_epc_page *epc_page = encl->secs.epc_page; + + if (!epc_page) + epc_page = sgx_encl_eldu(&encl->secs, NULL); + + return epc_page; +} + static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl, struct sgx_encl_page *entry) { @@ -248,11 +263,9 @@ static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl, return entry; } - if (!(encl->secs.epc_page)) { - epc_page = sgx_encl_eldu(&encl->secs, NULL); - if (IS_ERR(epc_page)) - return ERR_CAST(epc_page); - } + epc_page = sgx_encl_load_secs(encl); + if (IS_ERR(epc_page)) + return ERR_CAST(epc_page); epc_page = sgx_encl_eldu(entry, encl->secs.epc_page); if (IS_ERR(epc_page)) @@ -339,6 +352,13 @@ static vm_fault_t sgx_encl_eaug_page(struct vm_area_struct *vma, mutex_lock(&encl->lock); + epc_page = sgx_encl_load_secs(encl); + if (IS_ERR(epc_page)) { + if (PTR_ERR(epc_page) == -EBUSY) + vmret = VM_FAULT_NOPAGE; + goto err_out_unlock; + } + epc_page = sgx_alloc_epc_page(encl_page, false); if (IS_ERR(epc_page)) { if (PTR_ERR(epc_page) == -EBUSY) diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index 0270925fe013..dc136703566f 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -78,7 +78,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c) /* * initial apic id, which also represents 32-bit extended x2apic id. */ - c->initial_apicid = edx; + c->topo.initial_apicid = edx; smp_num_siblings = max_t(int, smp_num_siblings, LEVEL_MAX_SIBLINGS(ebx)); #endif return 0; @@ -108,7 +108,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c) * Populate HT related information from sub-leaf level 0. */ cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx); - c->initial_apicid = 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); @@ -146,20 +146,19 @@ int detect_extended_topology(struct cpuinfo_x86 *c) die_select_mask = (~(-1 << die_plus_mask_width)) >> core_plus_mask_width; - c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, + c->topo.core_id = apic->phys_pkg_id(c->topo.initial_apicid, ht_mask_width) & core_select_mask; if (die_level_present) { - c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid, + c->topo.die_id = apic->phys_pkg_id(c->topo.initial_apicid, core_plus_mask_width) & die_select_mask; } - c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, - pkg_mask_width); + 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. */ - c->apicid = apic->phys_pkg_id(c->initial_apicid, 0); + c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0); c->x86_max_cores = (core_level_siblings / smp_num_siblings); __max_die_per_package = (die_level_siblings / core_level_siblings); diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c index 05fa4ef63490..415564a6523b 100644 --- a/arch/x86/kernel/cpu/zhaoxin.c +++ b/arch/x86/kernel/cpu/zhaoxin.c @@ -65,20 +65,6 @@ static void early_init_zhaoxin(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC); set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC); } - - if (c->cpuid_level >= 0x00000001) { - u32 eax, ebx, ecx, edx; - - cpuid(0x00000001, &eax, &ebx, &ecx, &edx); - /* - * If HTT (EDX[28]) is set EBX[16:23] contain the number of - * apicids which are reserved per package. Store the resulting - * shift value for the package management code. - */ - if (edx & (1U << 28)) - c->x86_coreid_bits = get_count_order((ebx >> 16) & 0xff); - } - } static void init_zhaoxin(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 87d38f17ff5c..afd09924094e 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -278,7 +278,7 @@ static void __init dtb_apic_setup(void) } #ifdef CONFIG_OF_EARLY_FLATTREE -static void __init x86_flattree_get_config(void) +void __init x86_flattree_get_config(void) { u32 size, map_len; void *dt; @@ -300,14 +300,10 @@ static void __init x86_flattree_get_config(void) unflatten_and_copy_device_tree(); early_memunmap(dt, map_len); } -#else -static inline void x86_flattree_get_config(void) { } #endif void __init x86_dtb_init(void) { - x86_flattree_get_config(); - if (!of_have_populated_dt()) return; diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index a86d37052a64..a21a4d0ecc34 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -369,14 +369,15 @@ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest) EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate); void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, - unsigned int size, u32 pkru) + unsigned int size, u64 xfeatures, u32 pkru) { struct fpstate *kstate = gfpu->fpstate; union fpregs_state *ustate = buf; struct membuf mb = { .p = buf, .left = size }; if (cpu_feature_enabled(X86_FEATURE_XSAVE)) { - __copy_xstate_to_uabi_buf(mb, kstate, pkru, XSTATE_COPY_XSAVE); + __copy_xstate_to_uabi_buf(mb, kstate, xfeatures, pkru, + XSTATE_COPY_XSAVE); } else { memcpy(&ustate->fxsave, &kstate->regs.fxsave, sizeof(ustate->fxsave)); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index cadf68737e6b..117e74c44e75 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1049,6 +1049,7 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer * @to: membuf descriptor * @fpstate: The fpstate buffer from which to copy + * @xfeatures: The mask of xfeatures to save (XSAVE mode only) * @pkru_val: The PKRU value to store in the PKRU component * @copy_mode: The requested copy mode * @@ -1059,7 +1060,8 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, * It supports partial copy but @to.pos always starts from zero. */ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, - u32 pkru_val, enum xstate_copy_mode copy_mode) + u64 xfeatures, u32 pkru_val, + enum xstate_copy_mode copy_mode) { const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr); struct xregs_state *xinit = &init_fpstate.regs.xsave; @@ -1083,7 +1085,7 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, break; case XSTATE_COPY_XSAVE: - header.xfeatures &= fpstate->user_xfeatures; + header.xfeatures &= fpstate->user_xfeatures & xfeatures; break; } @@ -1185,6 +1187,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode copy_mode) { __copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate, + tsk->thread.fpu.fpstate->user_xfeatures, tsk->thread.pkru, copy_mode); } @@ -1536,10 +1539,7 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize, fpregs_restore_userregs(); newfps->xfeatures = curfps->xfeatures | xfeatures; - - if (!guest_fpu) - newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; - + newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; newfps->xfd = curfps->xfd & ~xfeatures; /* Do the final updates within the locked region */ @@ -1736,7 +1736,6 @@ EXPORT_SYMBOL_GPL(xstate_get_guest_group_perm); /** * fpu_xstate_prctl - xstate permission operations - * @tsk: Redundant pointer to current * @option: A subfunction of arch_prctl() * @arg2: option argument * Return: 0 if successful; otherwise, an error code diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index a4ecb04d8d64..3518fb26d06b 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -43,7 +43,8 @@ enum xstate_copy_mode { struct membuf; extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, - u32 pkru_val, enum xstate_copy_mode copy_mode); + u64 xfeatures, u32 pkru_val, + enum xstate_copy_mode copy_mode); extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode mode); extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru); diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S index 24c1175a47e2..58d9ed50fe61 100644 --- a/arch/x86/kernel/ftrace_32.S +++ b/arch/x86/kernel/ftrace_32.S @@ -3,10 +3,10 @@ * Copyright (C) 2017 Steven Rostedt, VMware Inc. */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/page_types.h> #include <asm/segment.h> -#include <asm/export.h> #include <asm/ftrace.h> #include <asm/nospec-branch.h> #include <asm/frame.h> diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S index 945cfa5f7239..214f30e9f0c0 100644 --- a/arch/x86/kernel/ftrace_64.S +++ b/arch/x86/kernel/ftrace_64.S @@ -3,12 +3,12 @@ * Copyright (C) 2014 Steven Rostedt, Red Hat Inc */ +#include <linux/export.h> #include <linux/cfi_types.h> #include <linux/linkage.h> #include <asm/asm-offsets.h> #include <asm/ptrace.h> #include <asm/ftrace.h> -#include <asm/export.h> #include <asm/nospec-branch.h> #include <asm/unwind_hints.h> #include <asm/frame.h> diff --git a/arch/x86/kernel/head32.c b/arch/x86/kernel/head32.c index 246a609f889b..de001b2146ab 100644 --- a/arch/x86/kernel/head32.c +++ b/arch/x86/kernel/head32.c @@ -19,6 +19,7 @@ #include <asm/apic.h> #include <asm/io_apic.h> #include <asm/bios_ebda.h> +#include <asm/microcode.h> #include <asm/tlbflush.h> #include <asm/bootparam_utils.h> @@ -29,11 +30,33 @@ static void __init i386_default_early_setup(void) x86_init.mpparse.setup_ioapic_ids = setup_ioapic_ids_from_mpc; } +#ifdef CONFIG_MICROCODE_INITRD32 +unsigned long __initdata initrd_start_early; +static pte_t __initdata *initrd_pl2p_start, *initrd_pl2p_end; + +static void zap_early_initrd_mapping(void) +{ + pte_t *pl2p = initrd_pl2p_start; + + for (; pl2p < initrd_pl2p_end; pl2p++) { + *pl2p = (pte_t){ .pte = 0 }; + + if (!IS_ENABLED(CONFIG_X86_PAE)) + *(pl2p + ((PAGE_OFFSET >> PGDIR_SHIFT))) = (pte_t) {.pte = 0}; + } +} +#else +static inline void zap_early_initrd_mapping(void) { } +#endif + asmlinkage __visible void __init __noreturn i386_start_kernel(void) { /* Make sure IDT is set up before any exception happens */ idt_setup_early_handler(); + load_ucode_bsp(); + zap_early_initrd_mapping(); + cr4_init_shadow(); sanitize_boot_params(&boot_params); @@ -69,52 +92,83 @@ asmlinkage __visible void __init __noreturn i386_start_kernel(void) * to the first kernel PMD. Note the upper half of each PMD or PTE are * always zero at this stage. */ -void __init mk_early_pgtbl_32(void); -void __init mk_early_pgtbl_32(void) -{ -#ifdef __pa -#undef __pa -#endif -#define __pa(x) ((unsigned long)(x) - PAGE_OFFSET) - pte_t pte, *ptep; - int i; - unsigned long *ptr; - /* Enough space to fit pagetables for the low memory linear map */ - const unsigned long limit = __pa(_end) + - (PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT); #ifdef CONFIG_X86_PAE - pmd_t pl2, *pl2p = (pmd_t *)__pa(initial_pg_pmd); -#define SET_PL2(pl2, val) { (pl2).pmd = (val); } +typedef pmd_t pl2_t; +#define pl2_base initial_pg_pmd +#define SET_PL2(val) { .pmd = (val), } #else - pgd_t pl2, *pl2p = (pgd_t *)__pa(initial_page_table); -#define SET_PL2(pl2, val) { (pl2).pgd = (val); } +typedef pgd_t pl2_t; +#define pl2_base initial_page_table +#define SET_PL2(val) { .pgd = (val), } #endif - ptep = (pte_t *)__pa(__brk_base); - pte.pte = PTE_IDENT_ATTR; - +static __init __no_stack_protector pte_t init_map(pte_t pte, pte_t **ptep, pl2_t **pl2p, + const unsigned long limit) +{ while ((pte.pte & PTE_PFN_MASK) < limit) { + pl2_t pl2 = SET_PL2((unsigned long)*ptep | PDE_IDENT_ATTR); + int i; + + **pl2p = pl2; + if (!IS_ENABLED(CONFIG_X86_PAE)) { + /* Kernel PDE entry */ + *(*pl2p + ((PAGE_OFFSET >> PGDIR_SHIFT))) = pl2; + } - SET_PL2(pl2, (unsigned long)ptep | PDE_IDENT_ATTR); - *pl2p = pl2; -#ifndef CONFIG_X86_PAE - /* Kernel PDE entry */ - *(pl2p + ((PAGE_OFFSET >> PGDIR_SHIFT))) = pl2; -#endif for (i = 0; i < PTRS_PER_PTE; i++) { - *ptep = pte; + **ptep = pte; pte.pte += PAGE_SIZE; - ptep++; + (*ptep)++; } - - pl2p++; + (*pl2p)++; } + return pte; +} + +void __init __no_stack_protector mk_early_pgtbl_32(void) +{ + /* Enough space to fit pagetables for the low memory linear map */ + unsigned long limit = __pa_nodebug(_end) + (PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT); + pte_t pte, *ptep = (pte_t *)__pa_nodebug(__brk_base); + struct boot_params __maybe_unused *params; + pl2_t *pl2p = (pl2_t *)__pa_nodebug(pl2_base); + unsigned long *ptr; + + pte.pte = PTE_IDENT_ATTR; + pte = init_map(pte, &ptep, &pl2p, limit); - ptr = (unsigned long *)__pa(&max_pfn_mapped); + ptr = (unsigned long *)__pa_nodebug(&max_pfn_mapped); /* Can't use pte_pfn() since it's a call with CONFIG_PARAVIRT */ *ptr = (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT; - ptr = (unsigned long *)__pa(&_brk_end); + ptr = (unsigned long *)__pa_nodebug(&_brk_end); *ptr = (unsigned long)ptep + PAGE_OFFSET; -} +#ifdef CONFIG_MICROCODE_INITRD32 + /* Running on a hypervisor? */ + if (native_cpuid_ecx(1) & BIT(31)) + return; + + params = (struct boot_params *)__pa_nodebug(&boot_params); + if (!params->hdr.ramdisk_size || !params->hdr.ramdisk_image) + return; + + /* Save the virtual start address */ + ptr = (unsigned long *)__pa_nodebug(&initrd_start_early); + *ptr = (pte.pte & PTE_PFN_MASK) + PAGE_OFFSET; + *ptr += ((unsigned long)params->hdr.ramdisk_image) & ~PAGE_MASK; + + /* Save PLP2 for cleanup */ + ptr = (unsigned long *)__pa_nodebug(&initrd_pl2p_start); + *ptr = (unsigned long)pl2p + PAGE_OFFSET; + + limit = (unsigned long)params->hdr.ramdisk_image; + pte.pte = PTE_IDENT_ATTR | PFN_ALIGN(limit); + limit = (unsigned long)params->hdr.ramdisk_image + params->hdr.ramdisk_size; + + init_map(pte, &ptep, &pl2p, limit); + + ptr = (unsigned long *)__pa_nodebug(&initrd_pl2p_end); + *ptr = (unsigned long)pl2p + PAGE_OFFSET; +#endif +} diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 49f7629b17f7..05a110c97111 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -41,6 +41,7 @@ #include <asm/trapnr.h> #include <asm/sev.h> #include <asm/tdx.h> +#include <asm/init.h> /* * Manage page tables very early on. @@ -69,7 +70,7 @@ EXPORT_SYMBOL(vmemmap_base); /* * GDT used on the boot CPU before switching to virtual addresses. */ -static struct desc_struct startup_gdt[GDT_ENTRIES] = { +static struct desc_struct startup_gdt[GDT_ENTRIES] __initdata = { [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff), [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff), [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc093, 0, 0xfffff), @@ -79,13 +80,11 @@ static struct desc_struct startup_gdt[GDT_ENTRIES] = { * 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 = { - .size = sizeof(startup_gdt), +static struct desc_ptr startup_gdt_descr __initdata = { + .size = sizeof(startup_gdt)-1, .address = 0, }; -#define __head __section(".head.text") - static void __head *fixup_pointer(void *ptr, unsigned long physaddr) { return ptr - (void *)_text + (void *)physaddr; @@ -211,7 +210,7 @@ unsigned long __head __startup_64(unsigned long physaddr, /* Fixup the physical addresses in the page table */ - pgd = fixup_pointer(&early_top_pgt, physaddr); + pgd = fixup_pointer(early_top_pgt, physaddr); p = pgd + pgd_index(__START_KERNEL_map); if (la57) *p = (unsigned long)level4_kernel_pgt; @@ -220,11 +219,11 @@ unsigned long __head __startup_64(unsigned long physaddr, *p += _PAGE_TABLE_NOENC - __START_KERNEL_map + load_delta; if (la57) { - p4d = fixup_pointer(&level4_kernel_pgt, physaddr); + p4d = fixup_pointer(level4_kernel_pgt, physaddr); p4d[511] += load_delta; } - pud = fixup_pointer(&level3_kernel_pgt, physaddr); + pud = fixup_pointer(level3_kernel_pgt, physaddr); pud[510] += load_delta; pud[511] += load_delta; @@ -588,7 +587,7 @@ static void set_bringup_idt_handler(gate_desc *idt, int n, void *handler) } /* This runs while still in the direct mapping */ -static void startup_64_load_idt(unsigned long physbase) +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); diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S index c9318993f959..487ac57e2c81 100644 --- a/arch/x86/kernel/head_32.S +++ b/arch/x86/kernel/head_32.S @@ -8,6 +8,7 @@ */ .text +#include <linux/export.h> #include <linux/threads.h> #include <linux/init.h> #include <linux/linkage.h> @@ -25,7 +26,6 @@ #include <asm/nops.h> #include <asm/nospec-branch.h> #include <asm/bootparam.h> -#include <asm/export.h> #include <asm/pgtable_32.h> /* Physical address */ @@ -118,11 +118,6 @@ SYM_CODE_START(startup_32) movl %eax, pa(olpc_ofw_pgd) #endif -#ifdef CONFIG_MICROCODE - /* Early load ucode on BSP. */ - call load_ucode_bsp -#endif - /* Create early pagetables. */ call mk_early_pgtbl_32 @@ -157,11 +152,6 @@ SYM_FUNC_START(startup_32_smp) movl %eax,%ss leal -__PAGE_OFFSET(%ecx),%esp -#ifdef CONFIG_MICROCODE - /* Early load ucode on AP. */ - call load_ucode_ap -#endif - .Ldefault_entry: movl $(CR0_STATE & ~X86_CR0_PG),%eax movl %eax,%cr0 diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index ea6995920b7a..086a2c3aaaa0 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -9,7 +9,7 @@ * Copyright (C) 2005 Eric Biederman <ebiederm@xmission.com> */ - +#include <linux/export.h> #include <linux/linkage.h> #include <linux/threads.h> #include <linux/init.h> @@ -22,7 +22,6 @@ #include <asm/percpu.h> #include <asm/nops.h> #include "../entry/calling.h" -#include <asm/export.h> #include <asm/nospec-branch.h> #include <asm/apicdef.h> #include <asm/fixmap.h> @@ -180,8 +179,8 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) movl $0, %ecx #endif - /* Enable PAE mode, PGE and LA57 */ - orl $(X86_CR4_PAE | X86_CR4_PGE), %ecx + /* Enable PAE mode, PSE, PGE and LA57 */ + orl $(X86_CR4_PAE | X86_CR4_PSE | X86_CR4_PGE), %ecx #ifdef CONFIG_X86_5LEVEL testl $1, __pgtable_l5_enabled(%rip) jz 1f diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 1648aa0204d9..41eecf180b7f 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -52,7 +52,7 @@ unsigned long hpet_address; u8 hpet_blockid; /* OS timer block num */ bool hpet_msi_disable; -#ifdef CONFIG_GENERIC_MSI_IRQ +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_GENERIC_MSI_IRQ) static DEFINE_PER_CPU(struct hpet_channel *, cpu_hpet_channel); static struct irq_domain *hpet_domain; #endif @@ -469,7 +469,7 @@ static void __init hpet_legacy_clockevent_register(struct hpet_channel *hc) /* * HPET MSI Support */ -#ifdef CONFIG_GENERIC_MSI_IRQ +#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_GENERIC_MSI_IRQ) static void hpet_msi_unmask(struct irq_data *data) { struct hpet_channel *hc = irq_data_get_irq_handler_data(data); diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c index 30a55207c000..c20d1832c481 100644 --- a/arch/x86/kernel/i8259.c +++ b/arch/x86/kernel/i8259.c @@ -32,6 +32,7 @@ */ static void init_8259A(int auto_eoi); +static bool pcat_compat __ro_after_init; static int i8259A_auto_eoi; DEFINE_RAW_SPINLOCK(i8259A_lock); @@ -299,15 +300,32 @@ static void unmask_8259A(void) static int probe_8259A(void) { + unsigned char new_val, probe_val = ~(1 << PIC_CASCADE_IR); unsigned long flags; - unsigned char probe_val = ~(1 << PIC_CASCADE_IR); - unsigned char new_val; + + /* + * If MADT has the PCAT_COMPAT flag set, then do not bother probing + * for the PIC. Some BIOSes leave the PIC uninitialized and probing + * fails. + * + * Right now this causes problems as quite some code depends on + * nr_legacy_irqs() > 0 or has_legacy_pic() == true. This is silly + * when the system has an IO/APIC because then PIC is not required + * at all, except for really old machines where the timer interrupt + * must be routed through the PIC. So just pretend that the PIC is + * there and let legacy_pic->init() initialize it for nothing. + * + * Alternatively this could just try to initialize the PIC and + * repeat the probe, but for cases where there is no PIC that's + * just pointless. + */ + if (pcat_compat) + return nr_legacy_irqs(); + /* - * Check to see if we have a PIC. - * Mask all except the cascade and read - * back the value we just wrote. If we don't - * have a PIC, we will read 0xff as opposed to the - * value we wrote. + * Check to see if we have a PIC. Mask all except the cascade and + * read back the value we just wrote. If we don't have a PIC, we + * will read 0xff as opposed to the value we wrote. */ raw_spin_lock_irqsave(&i8259A_lock, flags); @@ -429,5 +447,9 @@ static int __init i8259A_init_ops(void) return 0; } - device_initcall(i8259A_init_ops); + +void __init legacy_pic_pcat_compat(void) +{ + pcat_compat = true; +} diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index b786d48f5a0f..8857abc706e4 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -10,6 +10,7 @@ #include <asm/proto.h> #include <asm/desc.h> #include <asm/hw_irq.h> +#include <asm/ia32.h> #include <asm/idtentry.h> #define DPL0 0x0 @@ -116,6 +117,9 @@ static const __initconst struct idt_data def_idts[] = { #endif SYSG(X86_TRAP_OF, asm_exc_overflow), +}; + +static const struct idt_data ia32_idt[] __initconst = { #if defined(CONFIG_IA32_EMULATION) SYSG(IA32_SYSCALL_VECTOR, entry_INT80_compat), #elif defined(CONFIG_X86_32) @@ -225,6 +229,9 @@ void __init idt_setup_early_traps(void) void __init idt_setup_traps(void) { idt_setup_from_table(idt_table, def_idts, ARRAY_SIZE(def_idts), true); + + if (ia32_enabled()) + idt_setup_from_table(idt_table, ia32_idt, ARRAY_SIZE(ia32_idt), true); } #ifdef CONFIG_X86_64 diff --git a/arch/x86/kernel/irqflags.S b/arch/x86/kernel/irqflags.S index aaf9e776f323..7f542a7799cb 100644 --- a/arch/x86/kernel/irqflags.S +++ b/arch/x86/kernel/irqflags.S @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <asm/asm.h> -#include <asm/export.h> +#include <linux/export.h> #include <linux/linkage.h> /* diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c index ee4fe8cdb857..9a7c03d47861 100644 --- a/arch/x86/kernel/itmt.c +++ b/arch/x86/kernel/itmt.c @@ -74,7 +74,6 @@ static struct ctl_table itmt_kern_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, - {} }; static struct ctl_table_header *itmt_sysctl_header; diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c index 3a43a2dee658..9c9faa1634fb 100644 --- a/arch/x86/kernel/kgdb.c +++ b/arch/x86/kernel/kgdb.c @@ -695,7 +695,6 @@ void kgdb_arch_exit(void) } /** - * * kgdb_skipexception - Bail out of KGDB when we've been triggered. * @exception: Exception vector number * @regs: Current &struct pt_regs. diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b8ab9ee5896c..0ddb3bd0f1aa 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -500,13 +500,13 @@ static bool pv_sched_yield_supported(void) static void __send_ipi_mask(const struct cpumask *mask, int vector) { unsigned long flags; - int cpu, apic_id, icr; - int min = 0, max = 0; + int cpu, min = 0, max = 0; #ifdef CONFIG_X86_64 __uint128_t ipi_bitmap = 0; #else u64 ipi_bitmap = 0; #endif + u32 apic_id, icr; long ret; if (cpumask_empty(mask)) @@ -1028,8 +1028,8 @@ arch_initcall(activate_jump_labels); /* Kick a cpu by its apicid. Used to wake up a halted vcpu */ static void kvm_kick_cpu(int cpu) { - int apicid; unsigned long flags = 0; + u32 apicid; apicid = per_cpu(x86_cpu_to_apicid, cpu); kvm_hypercall2(KVM_HC_KICK_CPU, flags, apicid); diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c index a0c551846b35..17e955ab69fe 100644 --- a/arch/x86/kernel/nmi.c +++ b/arch/x86/kernel/nmi.c @@ -33,6 +33,7 @@ #include <asm/reboot.h> #include <asm/cache.h> #include <asm/nospec-branch.h> +#include <asm/microcode.h> #include <asm/sev.h> #define CREATE_TRACE_POINTS @@ -343,6 +344,9 @@ static noinstr void default_do_nmi(struct pt_regs *regs) instrumentation_begin(); + if (microcode_nmi_handler_enabled() && microcode_nmi_handler()) + goto out; + handled = nmi_handle(NMI_LOCAL, regs); __this_cpu_add(nmi_stats.normal, handled); if (handled) { @@ -498,8 +502,11 @@ 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 (IS_ENABLED(CONFIG_SMP) && arch_cpu_is_offline(smp_processor_id())) { + if (microcode_nmi_handler_enabled()) + microcode_offline_nmi_handler(); return; + } if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) { this_cpu_write(nmi_state, NMI_LATCHED); @@ -507,12 +514,13 @@ DEFINE_IDTENTRY_RAW(exc_nmi) } this_cpu_write(nmi_state, NMI_EXECUTING); this_cpu_write(nmi_cr2, read_cr2()); + +nmi_restart: if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) { WRITE_ONCE(nsp->idt_seq, nsp->idt_seq + 1); WARN_ON_ONCE(!(nsp->idt_seq & 0x1)); WRITE_ONCE(nsp->recv_jiffies, jiffies); } -nmi_restart: /* * Needs to happen before DR7 is accessed, because the hypervisor can @@ -548,16 +556,16 @@ nmi_restart: if (unlikely(this_cpu_read(nmi_cr2) != read_cr2())) write_cr2(this_cpu_read(nmi_cr2)); - if (this_cpu_dec_return(nmi_state)) - goto nmi_restart; - - if (user_mode(regs)) - mds_user_clear_cpu_buffers(); if (IS_ENABLED(CONFIG_NMI_CHECK_CPU)) { WRITE_ONCE(nsp->idt_seq, nsp->idt_seq + 1); WARN_ON_ONCE(nsp->idt_seq & 0x1); WRITE_ONCE(nsp->recv_jiffies, jiffies); } + if (this_cpu_dec_return(nmi_state)) + goto nmi_restart; + + if (user_mode(regs)) + mds_user_clear_cpu_buffers(); } #if IS_ENABLED(CONFIG_KVM_INTEL) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b098b1fa2470..1526747bedf2 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -466,154 +466,29 @@ static void __init memblock_x86_reserve_range_setup_data(void) } } -/* - * --------- Crashkernel reservation ------------------------------ - */ - -/* 16M alignment for crash kernel regions */ -#define CRASH_ALIGN SZ_16M - -/* - * Keep the crash kernel below this limit. - * - * Earlier 32-bits kernels would limit the kernel to the low 512 MB range - * due to mapping restrictions. - * - * 64-bit kdump kernels need to be restricted to be under 64 TB, which is - * the upper limit of system RAM in 4-level paging mode. Since the kdump - * jump could be from 5-level paging to 4-level paging, the jump will fail if - * the kernel is put above 64 TB, and during the 1st kernel bootup there's - * no good way to detect the paging mode of the target kernel which will be - * loaded for dumping. - */ -#ifdef CONFIG_X86_32 -# define CRASH_ADDR_LOW_MAX SZ_512M -# define CRASH_ADDR_HIGH_MAX SZ_512M -#else -# define CRASH_ADDR_LOW_MAX SZ_4G -# define CRASH_ADDR_HIGH_MAX SZ_64T -#endif - -static int __init reserve_crashkernel_low(void) -{ -#ifdef CONFIG_X86_64 - unsigned long long base, low_base = 0, low_size = 0; - unsigned long low_mem_limit; - int ret; - - low_mem_limit = min(memblock_phys_mem_size(), CRASH_ADDR_LOW_MAX); - - /* crashkernel=Y,low */ - ret = parse_crashkernel_low(boot_command_line, low_mem_limit, &low_size, &base); - if (ret) { - /* - * two parts from kernel/dma/swiotlb.c: - * -swiotlb size: user-specified with swiotlb= or default. - * - * -swiotlb overflow buffer: now hardcoded to 32k. We round it - * to 8M for other buffers that may need to stay low too. Also - * make sure we allocate enough extra low memory so that we - * don't run out of DMA buffers for 32-bit devices. - */ - low_size = max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20); - } else { - /* passed with crashkernel=0,low ? */ - if (!low_size) - return 0; - } - - low_base = memblock_phys_alloc_range(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX); - if (!low_base) { - pr_err("Cannot reserve %ldMB crashkernel low memory, please try smaller size.\n", - (unsigned long)(low_size >> 20)); - return -ENOMEM; - } - - pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (low RAM limit: %ldMB)\n", - (unsigned long)(low_size >> 20), - (unsigned long)(low_base >> 20), - (unsigned long)(low_mem_limit >> 20)); - - crashk_low_res.start = low_base; - crashk_low_res.end = low_base + low_size - 1; - insert_resource(&iomem_resource, &crashk_low_res); -#endif - return 0; -} - -static void __init reserve_crashkernel(void) +static void __init arch_reserve_crashkernel(void) { - unsigned long long crash_size, crash_base, total_mem; + unsigned long long crash_base, crash_size, low_size = 0; + char *cmdline = boot_command_line; bool high = false; int ret; if (!IS_ENABLED(CONFIG_KEXEC_CORE)) return; - total_mem = memblock_phys_mem_size(); - - /* crashkernel=XM */ - ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); - if (ret != 0 || crash_size <= 0) { - /* crashkernel=X,high */ - ret = parse_crashkernel_high(boot_command_line, total_mem, - &crash_size, &crash_base); - if (ret != 0 || crash_size <= 0) - return; - high = true; - } + ret = parse_crashkernel(cmdline, memblock_phys_mem_size(), + &crash_size, &crash_base, + &low_size, &high); + if (ret) + return; if (xen_pv_domain()) { pr_info("Ignoring crashkernel for a Xen PV domain\n"); return; } - /* 0 means: find the address automatically */ - if (!crash_base) { - /* - * Set CRASH_ADDR_LOW_MAX upper bound for crash memory, - * crashkernel=x,high reserves memory over 4G, also allocates - * 256M extra low memory for DMA buffers and swiotlb. - * But the extra memory is not required for all machines. - * So try low memory first and fall back to high memory - * unless "crashkernel=size[KMG],high" is specified. - */ - if (!high) - crash_base = memblock_phys_alloc_range(crash_size, - CRASH_ALIGN, CRASH_ALIGN, - CRASH_ADDR_LOW_MAX); - if (!crash_base) - crash_base = memblock_phys_alloc_range(crash_size, - CRASH_ALIGN, CRASH_ALIGN, - CRASH_ADDR_HIGH_MAX); - if (!crash_base) { - pr_info("crashkernel reservation failed - No suitable area found.\n"); - return; - } - } else { - unsigned long long start; - - start = memblock_phys_alloc_range(crash_size, SZ_1M, crash_base, - crash_base + crash_size); - if (start != crash_base) { - pr_info("crashkernel reservation failed - memory is in use.\n"); - return; - } - } - - if (crash_base >= (1ULL << 32) && reserve_crashkernel_low()) { - memblock_phys_free(crash_base, crash_size); - return; - } - - pr_info("Reserving %ldMB of memory at %ldMB for crashkernel (System RAM: %ldMB)\n", - (unsigned long)(crash_size >> 20), - (unsigned long)(crash_base >> 20), - (unsigned long)(total_mem >> 20)); - - crashk_res.start = crash_base; - crashk_res.end = crash_base + crash_size - 1; - insert_resource(&iomem_resource, &crashk_res); + reserve_crashkernel_generic(cmdline, crash_size, crash_base, + low_size, high); } static struct resource standard_io_resources[] = { @@ -1120,7 +995,7 @@ void __init setup_arch(char **cmdline_p) * Needs to run after memblock setup because it needs the physical * memory size. */ - sev_setup_arch(); + mem_encrypt_setup_arch(); efi_fake_memmap(); efi_find_mirror(); @@ -1217,6 +1092,8 @@ void __init setup_arch(char **cmdline_p) early_acpi_boot_init(); + x86_flattree_get_config(); + initmem_init(); dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); @@ -1227,7 +1104,7 @@ void __init setup_arch(char **cmdline_p) * Reserve memory for crash kernel after SRAT is parsed so that it * won't consume hotpluggable memory. */ - reserve_crashkernel(); + arch_reserve_crashkernel(); memblock_find_dma_reserve(); @@ -1290,7 +1167,7 @@ void __init setup_arch(char **cmdline_p) #ifdef CONFIG_VT #if defined(CONFIG_VGA_CONSOLE) if (!efi_enabled(EFI_BOOT) || (efi_mem_type(0xa0000) != EFI_CONVENTIONAL_MEMORY)) - conswitchp = &vga_con; + vgacon_register_screen(&screen_info); #endif #endif x86_init.oem.banner(); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 2eabccde94fb..ccb0915e84e1 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -256,7 +256,7 @@ static int __sev_cpuid_hv(u32 fn, int reg_idx, u32 *reg) return 0; } -static int sev_cpuid_hv(struct cpuid_leaf *leaf) +static int __sev_cpuid_hv_msr(struct cpuid_leaf *leaf) { int ret; @@ -279,6 +279,45 @@ static int sev_cpuid_hv(struct cpuid_leaf *leaf) return ret; } +static int __sev_cpuid_hv_ghcb(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) +{ + u32 cr4 = native_read_cr4(); + int ret; + + ghcb_set_rax(ghcb, leaf->fn); + ghcb_set_rcx(ghcb, leaf->subfn); + + if (cr4 & X86_CR4_OSXSAVE) + /* Safe to read xcr0 */ + ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK)); + else + /* xgetbv will cause #UD - use reset value for xcr0 */ + ghcb_set_xcr0(ghcb, 1); + + ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0); + if (ret != ES_OK) + return ret; + + if (!(ghcb_rax_is_valid(ghcb) && + ghcb_rbx_is_valid(ghcb) && + ghcb_rcx_is_valid(ghcb) && + ghcb_rdx_is_valid(ghcb))) + return ES_VMM_ERROR; + + leaf->eax = ghcb->save.rax; + leaf->ebx = ghcb->save.rbx; + leaf->ecx = ghcb->save.rcx; + leaf->edx = ghcb->save.rdx; + + return ES_OK; +} + +static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) +{ + return ghcb ? __sev_cpuid_hv_ghcb(ghcb, ctxt, leaf) + : __sev_cpuid_hv_msr(leaf); +} + /* * This may be called early while still running on the initial identity * mapping. Use RIP-relative addressing to obtain the correct address @@ -388,19 +427,20 @@ snp_cpuid_get_validated_func(struct cpuid_leaf *leaf) return false; } -static void snp_cpuid_hv(struct cpuid_leaf *leaf) +static void snp_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) { - if (sev_cpuid_hv(leaf)) + if (sev_cpuid_hv(ghcb, ctxt, leaf)) sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_CPUID_HV); } -static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) +static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt, + struct cpuid_leaf *leaf) { struct cpuid_leaf leaf_hv = *leaf; switch (leaf->fn) { case 0x1: - snp_cpuid_hv(&leaf_hv); + snp_cpuid_hv(ghcb, ctxt, &leaf_hv); /* initial APIC ID */ leaf->ebx = (leaf_hv.ebx & GENMASK(31, 24)) | (leaf->ebx & GENMASK(23, 0)); @@ -419,7 +459,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) break; case 0xB: leaf_hv.subfn = 0; - snp_cpuid_hv(&leaf_hv); + snp_cpuid_hv(ghcb, ctxt, &leaf_hv); /* extended APIC ID */ leaf->edx = leaf_hv.edx; @@ -467,7 +507,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) } break; case 0x8000001E: - snp_cpuid_hv(&leaf_hv); + snp_cpuid_hv(ghcb, ctxt, &leaf_hv); /* extended APIC ID */ leaf->eax = leaf_hv.eax; @@ -488,7 +528,7 @@ static int snp_cpuid_postprocess(struct cpuid_leaf *leaf) * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value * should be treated as fatal by caller. */ -static int snp_cpuid(struct cpuid_leaf *leaf) +static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -522,7 +562,7 @@ static int snp_cpuid(struct cpuid_leaf *leaf) return 0; } - return snp_cpuid_postprocess(leaf); + return snp_cpuid_postprocess(ghcb, ctxt, leaf); } /* @@ -544,14 +584,14 @@ void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) leaf.fn = fn; leaf.subfn = subfn; - ret = snp_cpuid(&leaf); + ret = snp_cpuid(NULL, NULL, &leaf); if (!ret) goto cpuid_done; if (ret != -EOPNOTSUPP) goto fail; - if (sev_cpuid_hv(&leaf)) + if (__sev_cpuid_hv_msr(&leaf)) goto fail; cpuid_done: @@ -592,6 +632,23 @@ fail: sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); } +static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt, + unsigned long address, + bool write) +{ + if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) { + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.error_code = X86_PF_USER; + ctxt->fi.cr2 = address; + if (write) + ctxt->fi.error_code |= X86_PF_WRITE; + + return ES_EXCEPTION; + } + + return ES_OK; +} + static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, void *src, char *buf, unsigned int data_size, @@ -599,7 +656,12 @@ static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, bool backwards) { int i, b = backwards ? -1 : 1; - enum es_result ret = ES_OK; + unsigned long address = (unsigned long)src; + enum es_result ret; + + ret = vc_insn_string_check(ctxt, address, false); + if (ret != ES_OK) + return ret; for (i = 0; i < count; i++) { void *s = src + (i * data_size * b); @@ -620,7 +682,12 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt, bool backwards) { int i, s = backwards ? -1 : 1; - enum es_result ret = ES_OK; + unsigned long address = (unsigned long)dst; + enum es_result ret; + + ret = vc_insn_string_check(ctxt, address, true); + if (ret != ES_OK) + return ret; for (i = 0; i < count; i++) { void *d = dst + (i * data_size * s); @@ -656,6 +723,9 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt, static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) { struct insn *insn = &ctxt->insn; + size_t size; + u64 port; + *exitinfo = 0; switch (insn->opcode.bytes[0]) { @@ -664,7 +734,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0x6d: *exitinfo |= IOIO_TYPE_INS; *exitinfo |= IOIO_SEG_ES; - *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + port = ctxt->regs->dx & 0xffff; break; /* OUTS opcodes */ @@ -672,41 +742,43 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0x6f: *exitinfo |= IOIO_TYPE_OUTS; *exitinfo |= IOIO_SEG_DS; - *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + port = ctxt->regs->dx & 0xffff; break; /* IN immediate opcodes */ case 0xe4: case 0xe5: *exitinfo |= IOIO_TYPE_IN; - *exitinfo |= (u8)insn->immediate.value << 16; + port = (u8)insn->immediate.value & 0xffff; break; /* OUT immediate opcodes */ case 0xe6: case 0xe7: *exitinfo |= IOIO_TYPE_OUT; - *exitinfo |= (u8)insn->immediate.value << 16; + port = (u8)insn->immediate.value & 0xffff; break; /* IN register opcodes */ case 0xec: case 0xed: *exitinfo |= IOIO_TYPE_IN; - *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + port = ctxt->regs->dx & 0xffff; break; /* OUT register opcodes */ case 0xee: case 0xef: *exitinfo |= IOIO_TYPE_OUT; - *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + port = ctxt->regs->dx & 0xffff; break; default: return ES_DECODE_FAILED; } + *exitinfo |= port << 16; + switch (insn->opcode.bytes[0]) { case 0x6c: case 0x6e: @@ -716,12 +788,15 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0xee: /* Single byte opcodes */ *exitinfo |= IOIO_DATA_8; + size = 1; break; default: /* Length determined by instruction parsing */ *exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16 : IOIO_DATA_32; + size = (insn->opnd_bytes == 2) ? 2 : 4; } + switch (insn->addr_bytes) { case 2: *exitinfo |= IOIO_ADDR_16; @@ -737,7 +812,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) if (insn_has_rep_prefix(insn)) *exitinfo |= IOIO_REP; - return ES_OK; + return vc_ioio_check(ctxt, (u16)port, size); } static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) @@ -848,14 +923,15 @@ static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ret; } -static int vc_handle_cpuid_snp(struct pt_regs *regs) +static int vc_handle_cpuid_snp(struct ghcb *ghcb, struct es_em_ctxt *ctxt) { + struct pt_regs *regs = ctxt->regs; struct cpuid_leaf leaf; int ret; leaf.fn = regs->ax; leaf.subfn = regs->cx; - ret = snp_cpuid(&leaf); + ret = snp_cpuid(ghcb, ctxt, &leaf); if (!ret) { regs->ax = leaf.eax; regs->bx = leaf.ebx; @@ -874,7 +950,7 @@ static enum es_result vc_handle_cpuid(struct ghcb *ghcb, enum es_result ret; int snp_cpuid_ret; - snp_cpuid_ret = vc_handle_cpuid_snp(regs); + snp_cpuid_ret = vc_handle_cpuid_snp(ghcb, ctxt); if (!snp_cpuid_ret) return ES_OK; if (snp_cpuid_ret != -EOPNOTSUPP) diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 2787826d9f60..70472eebe719 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -524,6 +524,33 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt return ES_OK; } +static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size) +{ + BUG_ON(size > 4); + + if (user_mode(ctxt->regs)) { + struct thread_struct *t = ¤t->thread; + struct io_bitmap *iobm = t->io_bitmap; + size_t idx; + + if (!iobm) + goto fault; + + for (idx = port; idx < port + size; ++idx) { + if (test_bit(idx, iobm->bitmap)) + goto fault; + } + } + + return ES_OK; + +fault: + ctxt->fi.vector = X86_TRAP_GP; + ctxt->fi.error_code = 0; + + return ES_EXCEPTION; +} + /* Include code shared with pre-decompression boot stage */ #include "sev-shared.c" @@ -868,8 +895,7 @@ void snp_set_memory_private(unsigned long vaddr, unsigned long npages) void snp_accept_memory(phys_addr_t start, phys_addr_t end) { - unsigned long vaddr; - unsigned int npages; + unsigned long vaddr, npages; if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP)) return; @@ -940,7 +966,7 @@ static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa) free_page((unsigned long)vmsa); } -static int wakeup_cpu_via_vmgexit(int apic_id, unsigned long start_ip) +static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip) { struct sev_es_save_area *cur_vmsa, *vmsa; struct ghcb_state state; @@ -1509,6 +1535,9 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ES_DECODE_FAILED; } + if (user_mode(ctxt->regs)) + return ES_UNSUPPORTED; + switch (mmio) { case INSN_MMIO_WRITE: memcpy(ghcb->shared_buffer, reg_data, bytes); diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 6eb06d001bcc..96a771f9f930 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -131,7 +131,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) } /* - * Disable virtualization, APIC etc. and park the CPU in a HLT loop + * this function calls the 'stop' function on all other CPUs in the system. */ DEFINE_IDTENTRY_SYSVEC(sysvec_reboot) { @@ -172,17 +172,13 @@ static void native_stop_other_cpus(int wait) * 2) Wait for all other CPUs to report that they reached the * HLT loop in stop_this_cpu() * - * 3) If the system uses INIT/STARTUP for CPU bringup, then - * send all present CPUs an INIT vector, which brings them - * completely out of the way. + * 3) If #2 timed out send an NMI to the CPUs which did not + * yet report * - * 4) If #3 is not possible and #2 timed out send an NMI to the - * CPUs which did not yet report - * - * 5) Wait for all other CPUs to report that they reached the + * 4) Wait for all other CPUs to report that they reached the * HLT loop in stop_this_cpu() * - * #4 can obviously race against a CPU reaching the HLT loop late. + * #3 can obviously race against a CPU reaching the HLT loop late. * That CPU will have reported already and the "have all CPUs * reached HLT" condition will be true despite the fact that the * other CPU is still handling the NMI. Again, there is no @@ -198,7 +194,7 @@ static void native_stop_other_cpus(int wait) /* * Don't wait longer than a second for IPI completion. The * wait request is not checked here because that would - * prevent an NMI/INIT shutdown in case that not all + * prevent an NMI shutdown attempt in case that not all * CPUs reach shutdown state. */ timeout = USEC_PER_SEC; @@ -206,27 +202,7 @@ static void native_stop_other_cpus(int wait) udelay(1); } - /* - * Park all other CPUs in INIT including "offline" CPUs, if - * possible. That's a safe place where they can't resume execution - * of HLT and then execute the HLT loop from overwritten text or - * page tables. - * - * The only downside is a broadcast MCE, but up to the point where - * the kexec() kernel brought all APs online again an MCE will just - * make HLT resume and handle the MCE. The machine crashes and burns - * due to overwritten text, page tables and data. So there is a - * choice between fire and frying pan. The result is pretty much - * the same. Chose frying pan until x86 provides a sane mechanism - * to park a CPU. - */ - if (smp_park_other_cpus_in_init()) - goto done; - - /* - * If park with INIT was not possible and the REBOOT_VECTOR didn't - * take all secondary CPUs offline, try with the NMI. - */ + /* if the REBOOT_VECTOR didn't work, try with the NMI */ if (!cpumask_empty(&cpus_stop_mask)) { /* * If NMI IPI is enabled, try to register the stop handler @@ -249,7 +225,6 @@ static void native_stop_other_cpus(int wait) udelay(1); } -done: local_irq_save(flags); disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 48e040618731..2cc2aa120b4b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -87,6 +87,7 @@ #include <asm/hw_irq.h> #include <asm/stackprotector.h> #include <asm/sev.h> +#include <asm/spec-ctrl.h> /* representing HT siblings of each logical CPU */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); @@ -124,7 +125,20 @@ struct mwait_cpu_dead { */ static DEFINE_PER_CPU_ALIGNED(struct mwait_cpu_dead, mwait_cpu_dead); -/* Logical package management. We might want to allocate that dynamically */ +/* 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; @@ -258,12 +272,9 @@ static void notrace start_secondary(void *unused) cpu_init_exception_handling(); /* - * 32-bit systems load the microcode from the ASM startup code for - * historical reasons. - * - * On 64-bit systems load it before reaching the AP alive - * synchronization point below so it is not part of the full per - * CPU serialized bringup part when "parallel" bringup is enabled. + * Load the microcode before reaching the AP alive synchronization + * point below so it is not part of the full per CPU serialized + * bringup part when "parallel" bringup is enabled. * * That's even safe when hyperthreading is enabled in the CPU as * the core code starts the primary threads first and leaves the @@ -276,8 +287,7 @@ static void notrace start_secondary(void *unused) * CPUID, MSRs etc. must be strictly serialized to maintain * software state correctness. */ - if (IS_ENABLED(CONFIG_X86_64)) - load_ucode_ap(); + load_ucode_ap(); /* * Synchronization point with the hotplug core. Sets this CPUs @@ -288,7 +298,7 @@ static void notrace start_secondary(void *unused) cpu_init(); fpu__init_cpu(); - rcu_cpu_starting(raw_smp_processor_id()); + rcutree_report_cpu_starting(raw_smp_processor_id()); x86_cpuinit.early_percpu_clock_init(); ap_starting(); @@ -337,10 +347,8 @@ int topology_phys_to_logical_pkg(unsigned int phys_pkg) int cpu; for_each_possible_cpu(cpu) { - struct cpuinfo_x86 *c = &cpu_data(cpu); - - if (c->initialized && c->phys_proc_id == phys_pkg) - return c->logical_proc_id; + if (per_cpu(logical_maps.phys_pkg_id, cpu) == phys_pkg) + return per_cpu(logical_maps.logical_pkg_id, cpu); } return -1; } @@ -355,14 +363,12 @@ EXPORT_SYMBOL(topology_phys_to_logical_pkg); */ static int topology_phys_to_logical_die(unsigned int die_id, unsigned int cur_cpu) { - int cpu, proc_id = cpu_data(cur_cpu).phys_proc_id; + int cpu, proc_id = cpu_data(cur_cpu).topo.pkg_id; for_each_possible_cpu(cpu) { - struct cpuinfo_x86 *c = &cpu_data(cpu); - - if (c->initialized && c->cpu_die_id == die_id && - c->phys_proc_id == proc_id) - return c->logical_die_id; + 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; } @@ -387,7 +393,9 @@ int topology_update_package_map(unsigned int pkg, unsigned int cpu) cpu, pkg, new); } found: - cpu_data(cpu).logical_proc_id = new; + 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; } /** @@ -410,7 +418,9 @@ int topology_update_die_map(unsigned int die, unsigned int cpu) cpu, die, new); } found: - cpu_data(cpu).logical_die_id = new; + 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; } @@ -421,8 +431,8 @@ static void __init smp_store_boot_cpu_info(void) *c = boot_cpu_data; c->cpu_index = id; - topology_update_package_map(c->phys_proc_id, id); - topology_update_die_map(c->cpu_die_id, id); + topology_update_package_map(c->topo.pkg_id, id); + topology_update_die_map(c->topo.die_id, id); c->initialized = true; } @@ -476,21 +486,21 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) if (boot_cpu_has(X86_FEATURE_TOPOEXT)) { int cpu1 = c->cpu_index, cpu2 = o->cpu_index; - if (c->phys_proc_id == o->phys_proc_id && - c->cpu_die_id == o->cpu_die_id && - per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) { - if (c->cpu_core_id == o->cpu_core_id) + if (c->topo.pkg_id == o->topo.pkg_id && + c->topo.die_id == o->topo.die_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"); - if ((c->cu_id != 0xff) && - (o->cu_id != 0xff) && - (c->cu_id == o->cu_id)) + if ((c->topo.cu_id != 0xff) && + (o->topo.cu_id != 0xff) && + (c->topo.cu_id == o->topo.cu_id)) return topology_sane(c, o, "smt"); } - } else if (c->phys_proc_id == o->phys_proc_id && - c->cpu_die_id == o->cpu_die_id && - c->cpu_core_id == o->cpu_core_id) { + } else if (c->topo.pkg_id == o->topo.pkg_id && + c->topo.die_id == o->topo.die_id && + c->topo.core_id == o->topo.core_id) { return topology_sane(c, o, "smt"); } @@ -499,8 +509,8 @@ 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->phys_proc_id == o->phys_proc_id && - c->cpu_die_id == o->cpu_die_id) + if (c->topo.pkg_id == o->topo.pkg_id && + c->topo.die_id == o->topo.die_id) return true; return false; } @@ -510,11 +520,11 @@ static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) int cpu1 = c->cpu_index, cpu2 = o->cpu_index; /* If the arch didn't set up l2c_id, fall back to SMT */ - if (per_cpu(cpu_l2c_id, cpu1) == BAD_APICID) + if (per_cpu_l2c_id(cpu1) == BAD_APICID) return match_smt(c, o); /* Do not match if L2 cache id does not match: */ - if (per_cpu(cpu_l2c_id, cpu1) != per_cpu(cpu_l2c_id, cpu2)) + if (per_cpu_l2c_id(cpu1) != per_cpu_l2c_id(cpu2)) return false; return topology_sane(c, o, "l2c"); @@ -527,7 +537,7 @@ static bool match_l2c(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) */ static bool match_pkg(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) { - if (c->phys_proc_id == o->phys_proc_id) + if (c->topo.pkg_id == o->topo.pkg_id) return true; return false; } @@ -560,11 +570,11 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o) bool intel_snc = id && id->driver_data; /* Do not match if we do not have a valid APICID for cpu: */ - if (per_cpu(cpu_llc_id, cpu1) == BAD_APICID) + if (per_cpu_llc_id(cpu1) == BAD_APICID) return false; /* Do not match if LLC id does not match: */ - if (per_cpu(cpu_llc_id, cpu1) != per_cpu(cpu_llc_id, cpu2)) + if (per_cpu_llc_id(cpu1) != per_cpu_llc_id(cpu2)) return false; /* @@ -640,13 +650,13 @@ static void __init build_sched_topology(void) }; #endif /* - * When there is NUMA topology inside the package skip the DIE domain + * When there is NUMA topology inside the package skip the PKG domain * since the NUMA domains will auto-magically create the right spanning * domains based on the SLIT. */ if (!x86_has_numa_in_package) { x86_topology[i++] = (struct sched_domain_topology_level){ - cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(DIE) + cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(PKG) }; } @@ -809,7 +819,7 @@ static void __init smp_quirk_init_udelay(void) /* * Wake up AP by INIT, INIT, STARTUP sequence. */ -static void send_init_sequence(int phys_apicid) +static void send_init_sequence(u32 phys_apicid) { int maxlvt = lapic_get_maxlvt(); @@ -835,7 +845,7 @@ static void send_init_sequence(int phys_apicid) /* * Wake up AP by INIT, INIT, STARTUP sequence. */ -static int wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip) +static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip) { unsigned long send_status = 0, accept_status = 0; int num_starts, j, maxlvt; @@ -982,7 +992,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle) * Returns zero if startup was successfully sent, else error code from * ->wakeup_secondary_cpu. */ -static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) +static int do_boot_cpu(u32 apicid, int cpu, struct task_struct *idle) { unsigned long start_ip = real_mode_header->trampoline_start; int ret; @@ -1050,7 +1060,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle) int native_kick_ap(unsigned int cpu, struct task_struct *tidle) { - int apicid = apic->cpu_present_to_apicid(cpu); + u32 apicid = apic->cpu_present_to_apicid(cpu); int err; lockdep_assert_irqs_enabled(); @@ -1240,33 +1250,6 @@ void arch_thaw_secondary_cpus_end(void) cache_aps_init(); } -bool smp_park_other_cpus_in_init(void) -{ - unsigned int cpu, this_cpu = smp_processor_id(); - unsigned int apicid; - - if (apic->wakeup_secondary_cpu_64 || apic->wakeup_secondary_cpu) - return false; - - /* - * If this is a crash stop which does not execute on the boot CPU, - * then this cannot use the INIT mechanism because INIT to the boot - * CPU will reset the machine. - */ - if (this_cpu) - return false; - - for_each_cpu_and(cpu, &cpus_booted_once_mask, cpu_present_mask) { - if (cpu == this_cpu) - continue; - apicid = apic->cpu_present_to_apicid(cpu); - if (apicid == BAD_APICID) - continue; - send_init_sequence(apicid); - } - return true; -} - /* * Early setup to make printk work. */ @@ -1432,7 +1415,7 @@ static void remove_siblinginfo(int cpu) cpumask_clear(topology_sibling_cpumask(cpu)); cpumask_clear(topology_core_cpumask(cpu)); cpumask_clear(topology_die_cpumask(cpu)); - c->cpu_core_id = 0; + c->topo.core_id = 0; c->booted_cores = 0; cpumask_clear_cpu(cpu, cpu_sibling_setup_mask); recompute_smt_state(); @@ -1623,8 +1606,15 @@ void __noreturn hlt_play_dead(void) native_halt(); } +/* + * native_play_dead() is essentially a __noreturn function, but it can't + * be marked as such as the compiler may complain about it. + */ void native_play_dead(void) { + if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS)) + __update_spec_ctrl(0); + play_dead_common(); tboot_shutdown(TB_SHUTDOWN_WFS); diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index ca004e2e4469..0bab03130033 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -54,7 +54,7 @@ void arch_unregister_cpu(int num) EXPORT_SYMBOL(arch_unregister_cpu); #else /* CONFIG_HOTPLUG_CPU */ -static int __init arch_register_cpu(int num) +int __init arch_register_cpu(int num) { return register_cpu(&per_cpu(cpu_devices, num).cpu, num); } diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c index bbc440c93e08..1123ef3ccf90 100644 --- a/arch/x86/kernel/tsc_sync.c +++ b/arch/x86/kernel/tsc_sync.c @@ -15,6 +15,7 @@ * ( The serial nature of the boot logic and the CPU hotplug lock * protects against more than 2 CPUs entering this code. ) */ +#include <linux/workqueue.h> #include <linux/topology.h> #include <linux/spinlock.h> #include <linux/kernel.h> @@ -342,6 +343,13 @@ static inline unsigned int loop_timeout(int cpu) return (cpumask_weight(topology_core_cpumask(cpu)) > 1) ? 2 : 20; } +static void tsc_sync_mark_tsc_unstable(struct work_struct *work) +{ + mark_tsc_unstable("check_tsc_sync_source failed"); +} + +static DECLARE_WORK(tsc_sync_work, tsc_sync_mark_tsc_unstable); + /* * The freshly booted CPU initiates this via an async SMP function call. */ @@ -395,7 +403,7 @@ retry: "turning off TSC clock.\n", max_warp); if (random_warps) pr_warn("TSC warped randomly between CPUs\n"); - mark_tsc_unstable("check_tsc_sync_source failed"); + schedule_work(&tsc_sync_work); } /* diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 7e574cf3bf8a..d00c28aaa5be 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -85,7 +85,7 @@ static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table, { int *first = ip_table; int *last = ip_table + num_entries - 1; - int *mid = first, *found = first; + int *mid, *found = first; if (!num_entries) return NULL; diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index f15fb71f280e..54a5596adaa6 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -139,10 +139,7 @@ SECTIONS STATIC_CALL_TEXT ALIGN_ENTRY_TEXT_BEGIN -#ifdef CONFIG_CPU_SRSO *(.text..__x86.rethunk_untrain) -#endif - ENTRY_TEXT #ifdef CONFIG_CPU_SRSO @@ -520,12 +517,12 @@ INIT_PER_CPU(irq_stack_backing_store); "fixed_percpu_data is not at start of per-cpu area"); #endif -#ifdef CONFIG_RETHUNK +#ifdef CONFIG_CPU_UNRET_ENTRY . = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned"); -. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); #endif #ifdef CONFIG_CPU_SRSO +. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); /* * GNU ld cannot do XOR until 2.41. * https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=f6f78318fca803c4907fb8d7f6ded8295f1947b1 diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c index 65e96b76c423..d3fc01770558 100644 --- a/arch/x86/kernel/vsmp_64.c +++ b/arch/x86/kernel/vsmp_64.c @@ -127,7 +127,7 @@ static void __init vsmp_cap_cpus(void) #endif } -static int apicid_phys_pkg_id(int initial_apic_id, int index_msb) +static u32 apicid_phys_pkg_id(u32 initial_apic_id, int index_msb) { return read_apic_id() >> index_msb; } diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index ed90f148140d..950c12868d30 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -154,4 +154,15 @@ config KVM_PROVE_MMU config KVM_EXTERNAL_WRITE_TRACKING bool +config KVM_MAX_NR_VCPUS + int "Maximum number of vCPUs per KVM guest" + depends on KVM + range 1024 4096 + default 4096 if MAXSMP + default 1024 + help + Set the maximum number of vCPUs per KVM guest. Larger values will increase + the memory footprint of each KVM guest, regardless of how many vCPUs are + created for a given VM. + endif # VIRTUALIZATION diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0544e30b4946..dda6fc4cfae8 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -360,14 +360,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); - /* - * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if - * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't - * supported by the host. - */ - vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 | - XFEATURE_MASK_FPSSE; - kvm_update_pv_runtime(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); @@ -456,7 +448,9 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, vcpu->arch.cpuid_nent = nent; vcpu->arch.kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); +#ifdef CONFIG_KVM_XEN vcpu->arch.xen.cpuid = kvm_get_hypervisor_cpuid(vcpu, XEN_SIGNATURE); +#endif kvm_vcpu_after_set_cpuid(vcpu); return 0; @@ -761,11 +755,13 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_8000_0021_EAX, F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC) | 0 /* SmmPgCfgLock */ | - F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ + F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ | + F(WRMSR_XX_BASE_NS) ); - if (cpu_feature_enabled(X86_FEATURE_SRSO_NO)) - kvm_cpu_cap_set(X86_FEATURE_SRSO_NO); + kvm_cpu_cap_check_and_set(X86_FEATURE_SBPB); + kvm_cpu_cap_check_and_set(X86_FEATURE_IBPB_BRTYPE); + kvm_cpu_cap_check_and_set(X86_FEATURE_SRSO_NO); kvm_cpu_cap_init_kvm_defined(CPUID_8000_0022_EAX, F(PERFMON_V2) diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 284fa4704553..0b90532b6e26 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -174,7 +174,8 @@ static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu) static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu) { return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || - guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)); + guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB) || + guest_cpuid_has(vcpu, X86_FEATURE_SBPB)); } static inline bool supports_cpuid_fault(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 7c2dac6824e2..238afd7335e4 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -727,10 +727,12 @@ static int stimer_set_count(struct kvm_vcpu_hv_stimer *stimer, u64 count, stimer_cleanup(stimer); stimer->count = count; - if (stimer->count == 0) - stimer->config.enable = 0; - else if (stimer->config.auto_enable) - stimer->config.enable = 1; + if (!host) { + if (stimer->count == 0) + stimer->config.enable = 0; + else if (stimer->config.auto_enable) + stimer->config.enable = 1; + } if (stimer->config.enable) stimer_mark_pending(stimer, false); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index dcd60b39e794..245b20973cae 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2444,22 +2444,22 @@ EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) { struct kvm_lapic *apic = vcpu->arch.apic; - u64 val; /* - * ICR is a single 64-bit register when x2APIC is enabled. For legacy - * xAPIC, ICR writes need to go down the common (slightly slower) path - * to get the upper half from ICR2. + * ICR is a single 64-bit register when x2APIC is enabled, all others + * registers hold 32-bit values. For legacy xAPIC, ICR writes need to + * go down the common path to get the upper half from ICR2. + * + * Note, using the write helpers may incur an unnecessary write to the + * virtual APIC state, but KVM needs to conditionally modify the value + * in certain cases, e.g. to clear the ICR busy bit. The cost of extra + * conditional branches is likely a wash relative to the cost of the + * maybe-unecessary write, and both are in the noise anyways. */ - if (apic_x2apic_mode(apic) && offset == APIC_ICR) { - val = kvm_lapic_get_reg64(apic, APIC_ICR); - kvm_apic_send_ipi(apic, (u32)val, (u32)(val >> 32)); - trace_kvm_apic_write(APIC_ICR, val); - } else { - /* TODO: optimize to just emulate side effect w/o one more write */ - val = kvm_lapic_get_reg(apic, offset); - kvm_lapic_reg_write(apic, offset, (u32)val); - } + if (apic_x2apic_mode(apic) && offset == APIC_ICR) + kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR)); + else + kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); } EXPORT_SYMBOL_GPL(kvm_apic_write_nodecode); @@ -2670,6 +2670,8 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) u64 msr_val; int i; + static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu); + if (!init_event) { msr_val = APIC_DEFAULT_PHYS_BASE | MSR_IA32_APICBASE_ENABLE; if (kvm_vcpu_is_reset_bsp(vcpu)) @@ -2759,13 +2761,17 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) { u32 reg = kvm_lapic_get_reg(apic, lvt_type); int vector, mode, trig_mode; + int r; if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) { vector = reg & APIC_VECTOR_MASK; mode = reg & APIC_MODE_MASK; trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; - return __apic_accept_irq(apic, mode, vector, 1, trig_mode, - NULL); + + r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); + if (r && lvt_type == APIC_LVTPC) + kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); + return r; } return 0; } @@ -2977,6 +2983,8 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) struct kvm_lapic *apic = vcpu->arch.apic; int r; + static_call_cond(kvm_x86_apicv_pre_state_restore)(vcpu); + kvm_lapic_set_base(vcpu, vcpu->arch.apic_base); /* set SPIV separately to get count of SW disabled APICs right */ apic_set_spiv(apic, *((u32 *)(s->regs + APIC_SPIV))); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 253fb2093d5d..bb8c86eefac0 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -237,6 +237,13 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, return -(u32)fault & errcode; } +bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma); + +static inline bool kvm_mmu_honors_guest_mtrrs(struct kvm *kvm) +{ + return __kvm_mmu_honors_guest_mtrrs(kvm_arch_has_noncoherent_dma(kvm)); +} + void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end); int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index f7901cb4d2fa..c57e181bba21 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3425,8 +3425,8 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_mmu_page *sp; int ret = RET_PF_INVALID; - u64 spte = 0ull; - u64 *sptep = NULL; + u64 spte; + u64 *sptep; uint retry_count = 0; if (!page_fault_can_be_fast(fault)) @@ -3442,6 +3442,14 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) else sptep = fast_pf_get_last_sptep(vcpu, fault->addr, &spte); + /* + * It's entirely possible for the mapping to have been zapped + * by a different task, but the root page should always be + * available as the vCPU holds a reference to its root(s). + */ + if (WARN_ON_ONCE(!sptep)) + spte = REMOVED_SPTE; + if (!is_shadow_present_pte(spte)) break; @@ -4479,21 +4487,28 @@ out_unlock: } #endif -int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +bool __kvm_mmu_honors_guest_mtrrs(bool vm_has_noncoherent_dma) { /* - * If the guest's MTRRs may be used to compute the "real" memtype, - * restrict the mapping level to ensure KVM uses a consistent memtype - * across the entire mapping. If the host MTRRs are ignored by TDP - * (shadow_memtype_mask is non-zero), and the VM has non-coherent DMA - * (DMA doesn't snoop CPU caches), KVM's ABI is to honor the memtype - * from the guest's MTRRs so that guest accesses to memory that is - * DMA'd aren't cached against the guest's wishes. + * If host MTRRs are ignored (shadow_memtype_mask is non-zero), and the + * VM has non-coherent DMA (DMA doesn't snoop CPU caches), KVM's ABI is + * to honor the memtype from the guest's MTRRs so that guest accesses + * to memory that is DMA'd aren't cached against the guest's wishes. * * Note, KVM may still ultimately ignore guest MTRRs for certain PFNs, * e.g. KVM will force UC memtype for host MMIO. */ - if (shadow_memtype_mask && kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + return vm_has_noncoherent_dma && shadow_memtype_mask; +} + +int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) +{ + /* + * If the guest's MTRRs may be used to compute the "real" memtype, + * restrict the mapping level to ensure KVM uses a consistent memtype + * across the entire mapping. + */ + if (kvm_mmu_honors_guest_mtrrs(vcpu->kvm)) { for ( ; fault->max_level > PG_LEVEL_4K; --fault->max_level) { int page_num = KVM_PAGES_PER_HPAGE(fault->max_level); gfn_t base = gfn_round_for_level(fault->gfn, @@ -6785,11 +6800,7 @@ static unsigned long mmu_shrink_count(struct shrinker *shrink, return percpu_counter_read_positive(&kvm_total_used_mmu_pages); } -static struct shrinker mmu_shrinker = { - .count_objects = mmu_shrink_count, - .scan_objects = mmu_shrink_scan, - .seeks = DEFAULT_SEEKS * 10, -}; +static struct shrinker *mmu_shrinker; static void mmu_destroy_caches(void) { @@ -6922,10 +6933,16 @@ int kvm_mmu_vendor_module_init(void) if (percpu_counter_init(&kvm_total_used_mmu_pages, 0, GFP_KERNEL)) goto out; - ret = register_shrinker(&mmu_shrinker, "x86-mmu"); - if (ret) + mmu_shrinker = shrinker_alloc(0, "x86-mmu"); + if (!mmu_shrinker) goto out_shrinker; + mmu_shrinker->count_objects = mmu_shrink_count; + mmu_shrinker->scan_objects = mmu_shrink_scan; + mmu_shrinker->seeks = DEFAULT_SEEKS * 10; + + shrinker_register(mmu_shrinker); + return 0; out_shrinker: @@ -6947,7 +6964,7 @@ void kvm_mmu_vendor_module_exit(void) { mmu_destroy_caches(); percpu_counter_destroy(&kvm_total_used_mmu_pages); - unregister_shrinker(&mmu_shrinker); + shrinker_free(mmu_shrinker); } /* diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c index 3eb6e7f47e96..a67c28a56417 100644 --- a/arch/x86/kvm/mtrr.c +++ b/arch/x86/kvm/mtrr.c @@ -320,7 +320,7 @@ static void update_mtrr(struct kvm_vcpu *vcpu, u32 msr) struct kvm_mtrr *mtrr_state = &vcpu->arch.mtrr_state; gfn_t start, end; - if (!tdp_enabled || !kvm_arch_has_noncoherent_dma(vcpu->kvm)) + if (!kvm_mmu_honors_guest_mtrrs(vcpu->kvm)) return; if (!mtrr_is_enabled(mtrr_state) && msr != MSR_MTRRdefType) diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index edb89b51b383..9ae07db6f0f6 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -93,14 +93,6 @@ void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops) #undef __KVM_X86_PMU_OP } -static void kvm_pmi_trigger_fn(struct irq_work *irq_work) -{ - struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work); - struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); - - kvm_pmu_deliver_pmi(vcpu); -} - static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -124,20 +116,7 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); } - if (!pmc->intr || skip_pmi) - return; - - /* - * Inject PMI. If vcpu was in a guest mode during NMI PMI - * can be ejected on a guest mode re-entry. Otherwise we can't - * be sure that vcpu wasn't executing hlt instruction at the - * time of vmexit and is not going to re-enter guest mode until - * woken up. So we should wake it, but this is impossible from - * NMI context. Do it from irq work instead. - */ - if (in_pmi && !kvm_handling_nmi_from_guest(pmc->vcpu)) - irq_work_queue(&pmc_to_pmu(pmc)->irq_work); - else + if (pmc->intr && !skip_pmi) kvm_make_request(KVM_REQ_PMI, pmc->vcpu); } @@ -675,9 +654,6 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) void kvm_pmu_reset(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - - irq_work_sync(&pmu->irq_work); static_call(kvm_x86_pmu_reset)(vcpu); } @@ -687,7 +663,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) memset(pmu, 0, sizeof(*pmu)); static_call(kvm_x86_pmu_init)(vcpu); - init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); pmu->event_count = 0; pmu->need_cleanup = false; kvm_pmu_refresh(vcpu); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 7d9ba301c090..1d64113de488 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -74,6 +74,12 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) return counter & pmc_bitmask(pmc); } +static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val) +{ + pmc->counter += val - pmc_read_counter(pmc); + pmc->counter &= pmc_bitmask(pmc); +} + static inline void pmc_release_perf_event(struct kvm_pmc *pmc) { if (pmc->perf_event) { diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index b42111a24cc2..dc3d95fdca7d 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -324,7 +324,6 @@ void enter_smm(struct kvm_vcpu *vcpu) cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG); static_call(kvm_x86_set_cr0)(vcpu, cr0); - vcpu->arch.cr0 = cr0; static_call(kvm_x86_set_cr4)(vcpu, 0); diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 2092db892d7d..4b74ea91f4e6 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -529,8 +529,11 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); break; + case AVIC_IPI_FAILURE_INVALID_IPI_VECTOR: + /* Invalid IPI with vector < 16 */ + break; default: - pr_err("Unknown IPI interception\n"); + vcpu_unimpl(vcpu, "Unknown avic incomplete IPI interception\n"); } return 1; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index dd496c9e5f91..3fea8c47679e 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1253,6 +1253,9 @@ void svm_leave_nested(struct kvm_vcpu *vcpu) nested_svm_uninit_mmu_context(vcpu); vmcb_mark_all_dirty(svm->vmcb); + + if (kvm_apicv_activated(vcpu->kvm)) + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); } kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index cef5a3d0abd0..373ff6a6687b 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -160,7 +160,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* MSR_PERFCTRn */ pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { - pmc->counter += data - pmc_read_counter(pmc); + pmc_write_counter(pmc, data); pmc_update_sample_period(pmc); return 0; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9507df93f410..712146312358 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -199,7 +199,7 @@ module_param_named(npt, npt_enabled, bool, 0444); /* allow nested virtualization in KVM/SVM */ static int nested = true; -module_param(nested, int, S_IRUGO); +module_param(nested, int, 0444); /* enable/disable Next RIP Save */ int nrips = true; @@ -364,8 +364,6 @@ static void svm_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask) svm->vmcb->control.int_state |= SVM_INTERRUPT_SHADOW_MASK; } -static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len); static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, bool commit_side_effects) @@ -386,14 +384,6 @@ static int __svm_skip_emulated_instruction(struct kvm_vcpu *vcpu, } if (!svm->next_rip) { - /* - * FIXME: Drop this when kvm_emulate_instruction() does the - * right thing and treats "can't emulate" as outright failure - * for EMULTYPE_SKIP. - */ - if (!svm_can_emulate_instruction(vcpu, EMULTYPE_SKIP, NULL, 0)) - return 0; - if (unlikely(!commit_side_effects)) old_rflags = svm->vmcb->save.rflags; @@ -531,8 +521,6 @@ static bool __kvm_is_svm_supported(void) int cpu = smp_processor_id(); struct cpuinfo_x86 *c = &cpu_data(cpu); - u64 vm_cr; - if (c->x86_vendor != X86_VENDOR_AMD && c->x86_vendor != X86_VENDOR_HYGON) { pr_err("CPU %d isn't AMD or Hygon\n", cpu); @@ -549,12 +537,6 @@ static bool __kvm_is_svm_supported(void) return false; } - rdmsrl(MSR_VM_CR, vm_cr); - if (vm_cr & (1 << SVM_VM_CR_SVM_DISABLE)) { - pr_err("SVM disabled (by BIOS) in MSR_VM_CR on CPU %d\n", cpu); - return false; - } - return true; } @@ -691,7 +673,7 @@ static int svm_hardware_enable(void) */ if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { struct sev_es_save_area *hostsa; - u32 msr_hi; + u32 __maybe_unused msr_hi; hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); @@ -913,8 +895,7 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) if (intercept == svm->x2avic_msrs_intercepted) return; - if (!x2avic_enabled || - !apic_x2apic_mode(svm->vcpu.arch.apic)) + if (!x2avic_enabled) return; for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) { @@ -2203,12 +2184,6 @@ static int shutdown_interception(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; struct vcpu_svm *svm = to_svm(vcpu); - /* - * The VM save area has already been encrypted so it - * cannot be reinitialized - just terminate. - */ - if (sev_es_guest(vcpu->kvm)) - return -EINVAL; /* * VMCB is undefined after a SHUTDOWN intercept. INIT the vCPU to put @@ -2217,9 +2192,14 @@ static int shutdown_interception(struct kvm_vcpu *vcpu) * userspace. At a platform view, INIT is acceptable behavior as * there exist bare metal platforms that automatically INIT the CPU * in response to shutdown. + * + * The VM save area for SEV-ES guests has already been encrypted so it + * cannot be reinitialized, i.e. synthesizing INIT is futile. */ - clear_page(svm->vmcb); - kvm_vcpu_reset(vcpu, true); + if (!sev_es_guest(vcpu->kvm)) { + clear_page(svm->vmcb); + kvm_vcpu_reset(vcpu, true); + } kvm_run->exit_reason = KVM_EXIT_SHUTDOWN; return 0; @@ -4728,15 +4708,15 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) } #endif -static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { bool smep, smap, is_user; u64 error_code; /* Emulation is always possible when KVM has access to all guest state. */ if (!sev_guest(vcpu->kvm)) - return true; + return X86EMUL_CONTINUE; /* #UD and #GP should never be intercepted for SEV guests. */ WARN_ON_ONCE(emul_type & (EMULTYPE_TRAP_UD | @@ -4748,14 +4728,14 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * to guest register state. */ if (sev_es_guest(vcpu->kvm)) - return false; + return X86EMUL_RETRY_INSTR; /* * Emulation is possible if the instruction is already decoded, e.g. * when completing I/O after returning from userspace. */ if (emul_type & EMULTYPE_NO_DECODE) - return true; + return X86EMUL_CONTINUE; /* * Emulation is possible for SEV guests if and only if a prefilled @@ -4781,9 +4761,11 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * success (and in practice it will work the vast majority of the time). */ if (unlikely(!insn)) { - if (!(emul_type & EMULTYPE_SKIP)) - kvm_queue_exception(vcpu, UD_VECTOR); - return false; + if (emul_type & EMULTYPE_SKIP) + return X86EMUL_UNHANDLEABLE; + + kvm_queue_exception(vcpu, UD_VECTOR); + return X86EMUL_PROPAGATE_FAULT; } /* @@ -4794,7 +4776,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * table used to translate CS:RIP resides in emulated MMIO. */ if (likely(insn_len)) - return true; + return X86EMUL_CONTINUE; /* * Detect and workaround Errata 1096 Fam_17h_00_0Fh. @@ -4852,6 +4834,7 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, kvm_inject_gp(vcpu, 0); else kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); + return X86EMUL_PROPAGATE_FAULT; } resume_guest: @@ -4869,7 +4852,7 @@ resume_guest: * doesn't explicitly define "ignored", i.e. doing nothing and letting * the guest spin is technically "ignoring" the access. */ - return false; + return X86EMUL_RETRY_INSTR; } static bool svm_apic_init_signal_blocked(struct kvm_vcpu *vcpu) @@ -5029,7 +5012,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .vm_copy_enc_context_from = sev_vm_copy_enc_context_from, .vm_move_enc_context_from = sev_vm_move_enc_context_from, - .can_emulate_instruction = svm_can_emulate_instruction, + .check_emulate_instruction = svm_check_emulate_instruction, .apic_init_signal_blocked = svm_apic_init_signal_blocked, diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index f2efa0bf7ae8..820d3e1f6b4f 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -436,11 +436,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; - pmc->counter += data - pmc_read_counter(pmc); + pmc_write_counter(pmc, data); pmc_update_sample_period(pmc); break; } else if ((pmc = get_fixed_pmc(pmu, msr))) { - pmc->counter += data - pmc_read_counter(pmc); + pmc_write_counter(pmc, data); pmc_update_sample_period(pmc); break; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 72e3943f3693..be20a60047b1 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -82,28 +82,28 @@ bool __read_mostly enable_vpid = 1; module_param_named(vpid, enable_vpid, bool, 0444); static bool __read_mostly enable_vnmi = 1; -module_param_named(vnmi, enable_vnmi, bool, S_IRUGO); +module_param_named(vnmi, enable_vnmi, bool, 0444); bool __read_mostly flexpriority_enabled = 1; -module_param_named(flexpriority, flexpriority_enabled, bool, S_IRUGO); +module_param_named(flexpriority, flexpriority_enabled, bool, 0444); bool __read_mostly enable_ept = 1; -module_param_named(ept, enable_ept, bool, S_IRUGO); +module_param_named(ept, enable_ept, bool, 0444); bool __read_mostly enable_unrestricted_guest = 1; module_param_named(unrestricted_guest, - enable_unrestricted_guest, bool, S_IRUGO); + enable_unrestricted_guest, bool, 0444); bool __read_mostly enable_ept_ad_bits = 1; -module_param_named(eptad, enable_ept_ad_bits, bool, S_IRUGO); +module_param_named(eptad, enable_ept_ad_bits, bool, 0444); static bool __read_mostly emulate_invalid_guest_state = true; -module_param(emulate_invalid_guest_state, bool, S_IRUGO); +module_param(emulate_invalid_guest_state, bool, 0444); static bool __read_mostly fasteoi = 1; -module_param(fasteoi, bool, S_IRUGO); +module_param(fasteoi, bool, 0444); -module_param(enable_apicv, bool, S_IRUGO); +module_param(enable_apicv, bool, 0444); bool __read_mostly enable_ipiv = true; module_param(enable_ipiv, bool, 0444); @@ -114,10 +114,10 @@ module_param(enable_ipiv, bool, 0444); * use VMX instructions. */ static bool __read_mostly nested = 1; -module_param(nested, bool, S_IRUGO); +module_param(nested, bool, 0444); bool __read_mostly enable_pml = 1; -module_param_named(pml, enable_pml, bool, S_IRUGO); +module_param_named(pml, enable_pml, bool, 0444); static bool __read_mostly error_on_inconsistent_vmcs_config = true; module_param(error_on_inconsistent_vmcs_config, bool, 0444); @@ -1657,8 +1657,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) return 0; } -static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { /* * Emulation of instructions in SGX enclaves is impossible as RIP does @@ -1669,9 +1669,9 @@ static bool vmx_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, */ if (to_vmx(vcpu)->exit_reason.enclave_mode) { kvm_queue_exception(vcpu, UD_VECTOR); - return false; + return X86EMUL_PROPAGATE_FAULT; } - return true; + return X86EMUL_CONTINUE; } static int skip_emulated_instruction(struct kvm_vcpu *vcpu) @@ -5792,7 +5792,7 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) { gpa_t gpa; - if (!vmx_can_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) + if (vmx_check_emulate_instruction(vcpu, EMULTYPE_PF, NULL, 0)) return 1; /* @@ -6912,7 +6912,7 @@ static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap) vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]); } -static void vmx_apicv_post_state_restore(struct kvm_vcpu *vcpu) +static void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7579,8 +7579,6 @@ static int vmx_vm_init(struct kvm *kvm) static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) { - u8 cache; - /* We wanted to honor guest CD/MTRR/PAT, but doing so could result in * memory aliases with conflicting memory types and sometimes MCEs. * We have to be careful as to what are honored and when. @@ -7607,11 +7605,10 @@ static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) if (kvm_read_cr0_bits(vcpu, X86_CR0_CD)) { if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) - cache = MTRR_TYPE_WRBACK; + return MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT; else - cache = MTRR_TYPE_UNCACHABLE; - - return (cache << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; + return (MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT) | + VMX_EPT_IPAT_BIT; } return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT; @@ -8286,7 +8283,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .set_apic_access_page_addr = vmx_set_apic_access_page_addr, .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl, .load_eoi_exitmap = vmx_load_eoi_exitmap, - .apicv_post_state_restore = vmx_apicv_post_state_restore, + .apicv_pre_state_restore = vmx_apicv_pre_state_restore, .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, @@ -8341,7 +8338,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .enable_smi_window = vmx_enable_smi_window, #endif - .can_emulate_instruction = vmx_can_emulate_instruction, + .check_emulate_instruction = vmx_check_emulate_instruction, .apic_init_signal_blocked = vmx_apic_init_signal_blocked, .migrate_timers = vmx_migrate_timers, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9f18b06bbda6..2c924075f6f1 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -145,21 +145,21 @@ EXPORT_STATIC_CALL_GPL(kvm_x86_get_cs_db_l_bits); EXPORT_STATIC_CALL_GPL(kvm_x86_cache_reg); static bool __read_mostly ignore_msrs = 0; -module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR); +module_param(ignore_msrs, bool, 0644); bool __read_mostly report_ignored_msrs = true; -module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR); +module_param(report_ignored_msrs, bool, 0644); EXPORT_SYMBOL_GPL(report_ignored_msrs); unsigned int min_timer_period_us = 200; -module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR); +module_param(min_timer_period_us, uint, 0644); static bool __read_mostly kvmclock_periodic_sync = true; -module_param(kvmclock_periodic_sync, bool, S_IRUGO); +module_param(kvmclock_periodic_sync, bool, 0444); /* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */ static u32 __read_mostly tsc_tolerance_ppm = 250; -module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); +module_param(tsc_tolerance_ppm, uint, 0644); /* * lapic timer advance (tscdeadline mode only) in nanoseconds. '-1' enables @@ -168,13 +168,13 @@ module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); * tuning, i.e. allows privileged userspace to set an exact advancement time. */ static int __read_mostly lapic_timer_advance_ns = -1; -module_param(lapic_timer_advance_ns, int, S_IRUGO | S_IWUSR); +module_param(lapic_timer_advance_ns, int, 0644); static bool __read_mostly vector_hashing = true; -module_param(vector_hashing, bool, S_IRUGO); +module_param(vector_hashing, bool, 0444); bool __read_mostly enable_vmware_backdoor = false; -module_param(enable_vmware_backdoor, bool, S_IRUGO); +module_param(enable_vmware_backdoor, bool, 0444); EXPORT_SYMBOL_GPL(enable_vmware_backdoor); /* @@ -186,7 +186,7 @@ static int __read_mostly force_emulation_prefix; module_param(force_emulation_prefix, int, 0644); int __read_mostly pi_inject_timer = -1; -module_param(pi_inject_timer, bint, S_IRUGO | S_IWUSR); +module_param(pi_inject_timer, bint, 0644); /* Enable/disable PMU virtualization */ bool __read_mostly enable_pmu = true; @@ -962,7 +962,7 @@ void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned lon kvm_mmu_reset_context(vcpu); if (((cr0 ^ old_cr0) & X86_CR0_CD) && - kvm_arch_has_noncoherent_dma(vcpu->kvm) && + kvm_mmu_honors_guest_mtrrs(vcpu->kvm) && !kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) kvm_zap_gfn_range(vcpu->kvm, 0, ~0ULL); } @@ -2331,14 +2331,9 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock, int sec_hi_o if (kvm_write_guest(kvm, wall_clock, &version, sizeof(version))) return; - /* - * The guest calculates current wall clock time by adding - * system time (updated by kvm_guest_time_update below) to the - * wall clock specified here. We do the reverse here. - */ - wall_nsec = ktime_get_real_ns() - get_kvmclock_ns(kvm); + wall_nsec = kvm_get_wall_clock_epoch(kvm); - wc.nsec = do_div(wall_nsec, 1000000000); + wc.nsec = do_div(wall_nsec, NSEC_PER_SEC); wc.sec = (u32)wall_nsec; /* overflow in 2106 guest time */ wc.version = version; @@ -2714,8 +2709,9 @@ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, kvm_track_tsc_matching(vcpu); } -static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) +static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value) { + u64 data = user_value ? *user_value : 0; struct kvm *kvm = vcpu->kvm; u64 offset, ns, elapsed; unsigned long flags; @@ -2730,25 +2726,37 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data) if (vcpu->arch.virtual_tsc_khz) { if (data == 0) { /* - * detection of vcpu initialization -- need to sync - * with other vCPUs. This particularly helps to keep - * kvm_clock stable after CPU hotplug + * Force synchronization when creating a vCPU, or when + * userspace explicitly writes a zero value. */ synchronizing = true; - } else { + } else if (kvm->arch.user_set_tsc) { u64 tsc_exp = kvm->arch.last_tsc_write + nsec_to_cycles(vcpu, elapsed); u64 tsc_hz = vcpu->arch.virtual_tsc_khz * 1000LL; /* - * Special case: TSC write with a small delta (1 second) - * of virtual cycle time against real time is - * interpreted as an attempt to synchronize the CPU. + * Here lies UAPI baggage: when a user-initiated TSC write has + * a small delta (1 second) of virtual cycle time against the + * previously set vCPU, we assume that they were intended to be + * in sync and the delta was only due to the racy nature of the + * legacy API. + * + * This trick falls down when restoring a guest which genuinely + * has been running for less time than the 1 second of imprecision + * which we allow for in the legacy API. In this case, the first + * value written by userspace (on any vCPU) should not be subject + * to this 'correction' to make it sync up with values that only + * come from the kernel's default vCPU creation. Make the 1-second + * slop hack only trigger if the user_set_tsc flag is already set. */ synchronizing = data < tsc_exp + tsc_hz && data + tsc_hz > tsc_exp; } } + if (user_value) + kvm->arch.user_set_tsc = true; + /* * For a reliable TSC, we can match TSC offsets, and for an unstable * TSC, we add elapsed time in this computation. We could let the @@ -3232,16 +3240,94 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) if (vcpu->pv_time.active) kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0); +#ifdef CONFIG_KVM_XEN if (vcpu->xen.vcpu_info_cache.active) kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache, offsetof(struct compat_vcpu_info, time)); if (vcpu->xen.vcpu_time_info_cache.active) kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0); +#endif kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; } /* + * The pvclock_wall_clock ABI tells the guest the wall clock time at + * which it started (i.e. its epoch, when its kvmclock was zero). + * + * In fact those clocks are subtly different; wall clock frequency is + * adjusted by NTP and has leap seconds, while the kvmclock is a + * simple function of the TSC without any such adjustment. + * + * Perhaps the ABI should have exposed CLOCK_TAI and a ratio between + * that and kvmclock, but even that would be subject to change over + * time. + * + * Attempt to calculate the epoch at a given moment using the *same* + * TSC reading via kvm_get_walltime_and_clockread() to obtain both + * wallclock and kvmclock times, and subtracting one from the other. + * + * Fall back to using their values at slightly different moments by + * calling ktime_get_real_ns() and get_kvmclock_ns() separately. + */ +uint64_t kvm_get_wall_clock_epoch(struct kvm *kvm) +{ +#ifdef CONFIG_X86_64 + struct pvclock_vcpu_time_info hv_clock; + struct kvm_arch *ka = &kvm->arch; + unsigned long seq, local_tsc_khz; + struct timespec64 ts; + uint64_t host_tsc; + + do { + seq = read_seqcount_begin(&ka->pvclock_sc); + + local_tsc_khz = 0; + if (!ka->use_master_clock) + break; + + /* + * The TSC read and the call to get_cpu_tsc_khz() must happen + * on the same CPU. + */ + get_cpu(); + + local_tsc_khz = get_cpu_tsc_khz(); + + if (local_tsc_khz && + !kvm_get_walltime_and_clockread(&ts, &host_tsc)) + local_tsc_khz = 0; /* Fall back to old method */ + + put_cpu(); + + /* + * These values must be snapshotted within the seqcount loop. + * After that, it's just mathematics which can happen on any + * CPU at any time. + */ + hv_clock.tsc_timestamp = ka->master_cycle_now; + hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset; + + } while (read_seqcount_retry(&ka->pvclock_sc, seq)); + + /* + * If the conditions were right, and obtaining the wallclock+TSC was + * successful, calculate the KVM clock at the corresponding time and + * subtract one from the other to get the guest's epoch in nanoseconds + * since 1970-01-01. + */ + if (local_tsc_khz) { + kvm_get_time_scale(NSEC_PER_SEC, local_tsc_khz * NSEC_PER_USEC, + &hv_clock.tsc_shift, + &hv_clock.tsc_to_system_mul); + return ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec - + __pvclock_read_cycles(&hv_clock, host_tsc); + } +#endif + return ktime_get_real_ns() - get_kvmclock_ns(kvm); +} + +/* * kvmclock updates which are isolated to a given vcpu, such as * vcpu->cpu migration, should not allow system_timestamp from * the rest of the vcpus to remain static. Otherwise ntp frequency @@ -3290,9 +3376,6 @@ static void kvmclock_sync_fn(struct work_struct *work) kvmclock_sync_work); struct kvm *kvm = container_of(ka, struct kvm, arch); - if (!kvmclock_periodic_sync) - return; - schedule_delayed_work(&kvm->arch.kvmclock_update_work, 0); schedule_delayed_work(&kvm->arch.kvmclock_sync_work, KVMCLOCK_SYNC_PERIOD); @@ -3641,6 +3724,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_PATCH_LOADER: case MSR_AMD64_BU_CFG2: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: break; @@ -3670,17 +3754,36 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vcpu->arch.perf_capabilities = data; kvm_pmu_refresh(vcpu); break; - case MSR_IA32_PRED_CMD: - if (!msr_info->host_initiated && !guest_has_pred_cmd_msr(vcpu)) - return 1; + case MSR_IA32_PRED_CMD: { + u64 reserved_bits = ~(PRED_CMD_IBPB | PRED_CMD_SBPB); + + if (!msr_info->host_initiated) { + if ((!guest_has_pred_cmd_msr(vcpu))) + return 1; + + if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)) + reserved_bits |= PRED_CMD_IBPB; - if (!boot_cpu_has(X86_FEATURE_IBPB) || (data & ~PRED_CMD_IBPB)) + if (!guest_cpuid_has(vcpu, X86_FEATURE_SBPB)) + reserved_bits |= PRED_CMD_SBPB; + } + + if (!boot_cpu_has(X86_FEATURE_IBPB)) + reserved_bits |= PRED_CMD_IBPB; + + if (!boot_cpu_has(X86_FEATURE_SBPB)) + reserved_bits |= PRED_CMD_SBPB; + + if (data & reserved_bits) return 1; + if (!data) break; - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + wrmsrl(MSR_IA32_PRED_CMD, data); break; + } case MSR_IA32_FLUSH_CMD: if (!msr_info->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)) @@ -3700,13 +3803,16 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) data &= ~(u64)0x100; /* ignore ignne emulation enable */ data &= ~(u64)0x8; /* ignore TLB cache disable */ - /* Handle McStatusWrEn */ - if (data == BIT_ULL(18)) { - vcpu->arch.msr_hwcr = data; - } else if (data != 0) { + /* + * Allow McStatusWrEn and TscFreqSel. (Linux guests from v3.2 + * through at least v6.6 whine if TscFreqSel is clear, + * depending on F/M/S. + */ + if (data & ~(BIT_ULL(18) | BIT_ULL(24))) { kvm_pr_unimpl_wrmsr(vcpu, msr, data); return 1; } + vcpu->arch.msr_hwcr = data; break; case MSR_FAM10H_MMIO_CONF_BASE: if (data != 0) { @@ -3777,7 +3883,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_TSC: if (msr_info->host_initiated) { - kvm_synchronize_tsc(vcpu, data); + kvm_synchronize_tsc(vcpu, &data); } else { u64 adj = kvm_compute_l1_tsc_offset(vcpu, data) - vcpu->arch.l1_tsc_offset; adjust_tsc_offset_guest(vcpu, adj); @@ -4065,6 +4171,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_AMD64_BU_CFG2: case MSR_IA32_PERF_CTL: case MSR_AMD64_DC_CFG: + case MSR_AMD64_TW_CFG: case MSR_F15H_EX_CFG: /* * Intel Sandy Bridge CPUs must support the RAPL (running average power @@ -5382,26 +5489,37 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, return 0; } -static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, - struct kvm_xsave *guest_xsave) -{ - if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return; - - fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, - guest_xsave->region, - sizeof(guest_xsave->region), - vcpu->arch.pkru); -} static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, u8 *state, unsigned int size) { + /* + * Only copy state for features that are enabled for the guest. The + * state itself isn't problematic, but setting bits in the header for + * features that are supported in *this* host but not exposed to the + * guest can result in KVM_SET_XSAVE failing when live migrating to a + * compatible host without the features that are NOT exposed to the + * guest. + * + * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if + * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't + * supported by the host. + */ + u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 | + XFEATURE_MASK_FPSSE; + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return; - fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, - state, size, vcpu->arch.pkru); + fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size, + supported_xcr0, vcpu->arch.pkru); +} + +static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) +{ + return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, + sizeof(guest_xsave->region)); } static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, @@ -5536,6 +5654,7 @@ static int kvm_arch_tsc_set_attr(struct kvm_vcpu *vcpu, tsc = kvm_scale_tsc(rdtsc(), vcpu->arch.l1_tsc_scaling_ratio) + offset; ns = get_kvmclock_base_ns(); + kvm->arch.user_set_tsc = true; __kvm_synchronize_tsc(vcpu, offset, tsc, ns, matched); raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags); @@ -6248,6 +6367,9 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot) struct kvm_vcpu *vcpu; unsigned long i; + if (!kvm_x86_ops.cpu_dirty_log_size) + return; + kvm_for_each_vcpu(i, vcpu, kvm) kvm_vcpu_kick(vcpu); } @@ -7474,11 +7596,11 @@ int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val, } EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system); -static int kvm_can_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, - void *insn, int insn_len) +static int kvm_check_emulate_insn(struct kvm_vcpu *vcpu, int emul_type, + void *insn, int insn_len) { - return static_call(kvm_x86_can_emulate_instruction)(vcpu, emul_type, - insn, insn_len); + return static_call(kvm_x86_check_emulate_instruction)(vcpu, emul_type, + insn, insn_len); } int handle_ud(struct kvm_vcpu *vcpu) @@ -7488,8 +7610,10 @@ int handle_ud(struct kvm_vcpu *vcpu) int emul_type = EMULTYPE_TRAP_UD; char sig[5]; /* ud2; .ascii "kvm" */ struct x86_exception e; + int r; - if (unlikely(!kvm_can_emulate_insn(vcpu, emul_type, NULL, 0))) + r = kvm_check_emulate_insn(vcpu, emul_type, NULL, 0); + if (r != X86EMUL_CONTINUE) return 1; if (fep_flags && @@ -8871,8 +8995,14 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; - if (unlikely(!kvm_can_emulate_insn(vcpu, emulation_type, insn, insn_len))) - return 1; + r = kvm_check_emulate_insn(vcpu, emulation_type, insn, insn_len); + if (r != X86EMUL_CONTINUE) { + if (r == X86EMUL_RETRY_INSTR || r == X86EMUL_PROPAGATE_FAULT) + return 1; + + WARN_ON_ONCE(r != X86EMUL_UNHANDLEABLE); + return handle_emulation_failure(vcpu, emulation_type); + } vcpu->arch.l1tf_flush_l1d = true; @@ -10576,16 +10706,16 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) } if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu)) record_steal_time(vcpu); + if (kvm_check_request(KVM_REQ_PMU, vcpu)) + kvm_pmu_handle_event(vcpu); + if (kvm_check_request(KVM_REQ_PMI, vcpu)) + kvm_pmu_deliver_pmi(vcpu); #ifdef CONFIG_KVM_SMM if (kvm_check_request(KVM_REQ_SMI, vcpu)) process_smi(vcpu); #endif if (kvm_check_request(KVM_REQ_NMI, vcpu)) process_nmi(vcpu); - if (kvm_check_request(KVM_REQ_PMU, vcpu)) - kvm_pmu_handle_event(vcpu); - if (kvm_check_request(KVM_REQ_PMI, vcpu)) - kvm_pmu_deliver_pmi(vcpu); if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) { BUG_ON(vcpu->arch.pending_ioapic_eoi > 255); if (test_bit(vcpu->arch.pending_ioapic_eoi, @@ -11521,7 +11651,6 @@ static int __set_sregs_common(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs, *mmu_reset_needed |= kvm_read_cr0(vcpu) != sregs->cr0; static_call(kvm_x86_set_cr0)(vcpu, sregs->cr0); - vcpu->arch.cr0 = sregs->cr0; *mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4; static_call(kvm_x86_set_cr4)(vcpu, sregs->cr4); @@ -11565,8 +11694,10 @@ static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) if (ret) return ret; - if (mmu_reset_needed) + if (mmu_reset_needed) { kvm_mmu_reset_context(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + } max_bits = KVM_NR_INTERRUPTS; pending_vec = find_first_bit( @@ -11607,8 +11738,10 @@ static int __set_sregs2(struct kvm_vcpu *vcpu, struct kvm_sregs2 *sregs2) mmu_reset_needed = 1; vcpu->arch.pdptrs_from_userspace = true; } - if (mmu_reset_needed) + if (mmu_reset_needed) { kvm_mmu_reset_context(vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); + } return 0; } @@ -11959,7 +12092,7 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) if (mutex_lock_killable(&vcpu->mutex)) return; vcpu_load(vcpu); - kvm_synchronize_tsc(vcpu, 0); + kvm_synchronize_tsc(vcpu, NULL); vcpu_put(vcpu); /* poll control enabled by default */ @@ -12315,7 +12448,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) goto out_uninit_mmu; INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list); - INIT_LIST_HEAD(&kvm->arch.assigned_dev_head); atomic_set(&kvm->arch.noncoherent_dma_count, 0); /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */ @@ -12843,6 +12975,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) return true; #endif + if (kvm_test_request(KVM_REQ_PMI, vcpu)) + return true; + if (kvm_arch_interrupt_allowed(vcpu) && (kvm_cpu_has_interrupt(vcpu) || kvm_guest_apic_has_interrupt(vcpu))) @@ -13188,15 +13323,30 @@ bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm) } EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device); +static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm) +{ + /* + * Non-coherent DMA assignment and de-assignment will affect + * whether KVM honors guest MTRRs and cause changes in memtypes + * in TDP. + * So, pass %true unconditionally to indicate non-coherent DMA was, + * or will be involved, and that zapping SPTEs might be necessary. + */ + if (__kvm_mmu_honors_guest_mtrrs(true)) + kvm_zap_gfn_range(kvm, gpa_to_gfn(0), gpa_to_gfn(~0ULL)); +} + void kvm_arch_register_noncoherent_dma(struct kvm *kvm) { - atomic_inc(&kvm->arch.noncoherent_dma_count); + if (atomic_inc_return(&kvm->arch.noncoherent_dma_count) == 1) + kvm_noncoherent_dma_assignment_start_or_stop(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_register_noncoherent_dma); void kvm_arch_unregister_noncoherent_dma(struct kvm *kvm) { - atomic_dec(&kvm->arch.noncoherent_dma_count); + if (!atomic_dec_return(&kvm->arch.noncoherent_dma_count)) + kvm_noncoherent_dma_assignment_start_or_stop(kvm); } EXPORT_SYMBOL_GPL(kvm_arch_unregister_noncoherent_dma); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 1e7be1f6ab29..5184fde1dc54 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -293,6 +293,7 @@ static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk) 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); int kvm_read_guest_virt(struct kvm_vcpu *vcpu, gva_t addr, void *val, unsigned int bytes, diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index 40edf4d1974c..e53fad915a62 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -59,7 +59,7 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) * 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 = ktime_get_real_ns() - get_kvmclock_ns(kvm); + wall_nsec = kvm_get_wall_clock_epoch(kvm); /* It could be invalid again already, so we need to check */ read_lock_irq(&gpc->lock); @@ -98,7 +98,7 @@ static int kvm_xen_shared_info_init(struct kvm *kvm, gfn_t gfn) wc_version = wc->version = (wc->version + 1) | 1; smp_wmb(); - wc->nsec = do_div(wall_nsec, 1000000000); + wc->nsec = do_div(wall_nsec, NSEC_PER_SEC); wc->sec = (u32)wall_nsec; *wc_sec_hi = wall_nsec >> 32; smp_wmb(); @@ -134,9 +134,23 @@ static enum hrtimer_restart xen_timer_callback(struct hrtimer *timer) { struct kvm_vcpu *vcpu = container_of(timer, struct kvm_vcpu, arch.xen.timer); + struct kvm_xen_evtchn e; + int rc; + if (atomic_read(&vcpu->arch.xen.timer_pending)) return HRTIMER_NORESTART; + e.vcpu_id = vcpu->vcpu_id; + e.vcpu_idx = vcpu->vcpu_idx; + e.port = vcpu->arch.xen.timer_virq; + e.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; + + rc = kvm_xen_set_evtchn_fast(&e, vcpu->kvm); + if (rc != -EWOULDBLOCK) { + vcpu->arch.xen.timer_expires = 0; + return HRTIMER_NORESTART; + } + atomic_inc(&vcpu->arch.xen.timer_pending); kvm_make_request(KVM_REQ_UNBLOCK, vcpu); kvm_vcpu_kick(vcpu); @@ -146,6 +160,14 @@ static enum hrtimer_restart xen_timer_callback(struct hrtimer *timer) static void kvm_xen_start_timer(struct kvm_vcpu *vcpu, u64 guest_abs, s64 delta_ns) { + /* + * Avoid races with the old timer firing. Checking timer_expires + * to avoid calling hrtimer_cancel() will only have false positives + * so is fine. + */ + if (vcpu->arch.xen.timer_expires) + hrtimer_cancel(&vcpu->arch.xen.timer); + atomic_set(&vcpu->arch.xen.timer_pending, 0); vcpu->arch.xen.timer_expires = guest_abs; @@ -1019,9 +1041,36 @@ int kvm_xen_vcpu_get_attr(struct kvm_vcpu *vcpu, struct kvm_xen_vcpu_attr *data) break; case KVM_XEN_VCPU_ATTR_TYPE_TIMER: + /* + * Ensure a consistent snapshot of state is captured, with a + * timer either being pending, or the event channel delivered + * to the corresponding bit in the shared_info. Not still + * lurking in the timer_pending flag for deferred delivery. + * Purely as an optimisation, if the timer_expires field is + * zero, that means the timer isn't active (or even in the + * timer_pending flag) and there is no need to cancel it. + */ + if (vcpu->arch.xen.timer_expires) { + hrtimer_cancel(&vcpu->arch.xen.timer); + kvm_xen_inject_timer_irqs(vcpu); + } + data->u.timer.port = vcpu->arch.xen.timer_virq; data->u.timer.priority = KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL; data->u.timer.expires_ns = vcpu->arch.xen.timer_expires; + + /* + * The hrtimer may trigger and raise the IRQ immediately, + * while the returned state causes it to be set up and + * raised again on the destination system after migration. + * That's fine, as the guest won't even have had a chance + * to run and handle the interrupt. Asserting an already + * pending event channel is idempotent. + */ + if (vcpu->arch.xen.timer_expires) + hrtimer_start_expires(&vcpu->arch.xen.timer, + HRTIMER_MODE_ABS_HARD); + r = 0; break; @@ -1374,12 +1423,8 @@ 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); - if ((oneshot.flags & VCPU_SSHOTTMR_future) && delta < 0) { - *r = -ETIME; - return true; - } - kvm_xen_start_timer(vcpu, oneshot.timeout_abs_ns, delta); *r = 0; return true; diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S index 23318c338db0..68f7fa3e1322 100644 --- a/arch/x86/lib/checksum_32.S +++ b/arch/x86/lib/checksum_32.S @@ -21,10 +21,10 @@ * converted to pure assembler */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/errno.h> #include <asm/asm.h> -#include <asm/export.h> #include <asm/nospec-branch.h> /* diff --git a/arch/x86/lib/clear_page_64.S b/arch/x86/lib/clear_page_64.S index f74a3e704a1c..2760a15fbc00 100644 --- a/arch/x86/lib/clear_page_64.S +++ b/arch/x86/lib/clear_page_64.S @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/asm.h> -#include <asm/export.h> /* * Most CPUs support enhanced REP MOVSB/STOSB instructions. It is diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S index 49805257b125..873e4ef23e49 100644 --- a/arch/x86/lib/cmpxchg8b_emu.S +++ b/arch/x86/lib/cmpxchg8b_emu.S @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0-only */ +#include <linux/export.h> #include <linux/linkage.h> -#include <asm/export.h> #include <asm/percpu.h> #include <asm/processor-flags.h> diff --git a/arch/x86/lib/copy_mc.c b/arch/x86/lib/copy_mc.c index 80efd45a7761..6e8b7e600def 100644 --- a/arch/x86/lib/copy_mc.c +++ b/arch/x86/lib/copy_mc.c @@ -70,23 +70,23 @@ unsigned long __must_check copy_mc_to_kernel(void *dst, const void *src, unsigne } EXPORT_SYMBOL_GPL(copy_mc_to_kernel); -unsigned long __must_check copy_mc_to_user(void *dst, const void *src, unsigned len) +unsigned long __must_check copy_mc_to_user(void __user *dst, const void *src, unsigned len) { unsigned long ret; if (copy_mc_fragile_enabled) { __uaccess_begin(); - ret = copy_mc_fragile(dst, src, len); + ret = copy_mc_fragile((__force void *)dst, src, len); __uaccess_end(); return ret; } if (static_cpu_has(X86_FEATURE_ERMS)) { __uaccess_begin(); - ret = copy_mc_enhanced_fast_string(dst, src, len); + ret = copy_mc_enhanced_fast_string((__force void *)dst, src, len); __uaccess_end(); return ret; } - return copy_user_generic(dst, src, len); + return copy_user_generic((__force void *)dst, src, len); } diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S index 30ea644bf446..d6ae793d08fa 100644 --- a/arch/x86/lib/copy_page_64.S +++ b/arch/x86/lib/copy_page_64.S @@ -1,10 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Written 2003 by Andi Kleen, based on a kernel by Evandro Menezes */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> -#include <asm/export.h> /* * Some CPUs run faster using the string copy instructions (sane microcode). diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S index 0a81aafed7f8..fc9fb5d06174 100644 --- a/arch/x86/lib/copy_user_64.S +++ b/arch/x86/lib/copy_user_64.S @@ -6,11 +6,11 @@ * Functions to copy from and to user space. */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> #include <asm/asm.h> -#include <asm/export.h> /* * rep_movs_alternative - memory copy with exception handling. diff --git a/arch/x86/lib/copy_user_uncached_64.S b/arch/x86/lib/copy_user_uncached_64.S index 5c5f38d32672..2918e36eece2 100644 --- a/arch/x86/lib/copy_user_uncached_64.S +++ b/arch/x86/lib/copy_user_uncached_64.S @@ -3,9 +3,9 @@ * Copyright 2023 Linus Torvalds <torvalds@linux-foundation.org> */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/asm.h> -#include <asm/export.h> /* * copy_user_nocache - Uncached memory copy with exception handling diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c index 145f9a0bde29..f4df4d241526 100644 --- a/arch/x86/lib/csum-wrappers_64.c +++ b/arch/x86/lib/csum-wrappers_64.c @@ -14,8 +14,6 @@ * @src: source address (user space) * @dst: destination address * @len: number of bytes to be copied. - * @isum: initial sum that is added into the result (32bit unfolded) - * @errp: set to -EFAULT for an bad source address. * * Returns an 32bit unfolded checksum of the buffer. * src and dst are best aligned to 64bits. @@ -38,8 +36,6 @@ csum_and_copy_from_user(const void __user *src, void *dst, int len) * @src: source address * @dst: destination address (user space) * @len: number of bytes to be copied. - * @isum: initial sum that is added into the result (32bit unfolded) - * @errp: set to -EFAULT for an bad destination address. * * Returns an 32bit unfolded checksum of the buffer. * src and dst are best aligned to 64bits. @@ -62,7 +58,6 @@ csum_and_copy_to_user(const void *src, void __user *dst, int len) * @src: source address * @dst: destination address * @len: number of bytes to be copied. - * @sum: initial sum that is added into the result (32bit unfolded) * * Returns an 32bit unfolded checksum of the buffer. */ diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S index 9c63713477bb..20ef350a60fb 100644 --- a/arch/x86/lib/getuser.S +++ b/arch/x86/lib/getuser.S @@ -26,6 +26,7 @@ * as they get called from within inline assembly. */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/page_types.h> #include <asm/errno.h> @@ -33,7 +34,6 @@ #include <asm/thread_info.h> #include <asm/asm.h> #include <asm/smap.h> -#include <asm/export.h> #define ASM_BARRIER_NOSPEC ALTERNATIVE "", "lfence", X86_FEATURE_LFENCE_RDTSC diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S index 12c16c6aa44a..774bdf3e6f0a 100644 --- a/arch/x86/lib/hweight.S +++ b/arch/x86/lib/hweight.S @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/export.h> #include <linux/linkage.h> -#include <asm/export.h> #include <asm/asm.h> @@ -36,8 +36,12 @@ SYM_FUNC_START(__sw_hweight32) SYM_FUNC_END(__sw_hweight32) EXPORT_SYMBOL(__sw_hweight32) -SYM_FUNC_START(__sw_hweight64) +/* + * No 32-bit variant, because it's implemented as an inline wrapper + * on top of __arch_hweight32(): + */ #ifdef CONFIG_X86_64 +SYM_FUNC_START(__sw_hweight64) pushq %rdi pushq %rdx @@ -66,18 +70,6 @@ SYM_FUNC_START(__sw_hweight64) popq %rdx popq %rdi RET -#else /* CONFIG_X86_32 */ - /* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */ - pushl %ecx - - call __sw_hweight32 - movl %eax, %ecx # stash away result - movl %edx, %eax # second part of input - call __sw_hweight32 - addl %ecx, %eax # result - - popl %ecx - RET -#endif SYM_FUNC_END(__sw_hweight64) EXPORT_SYMBOL(__sw_hweight64) +#endif diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S index 76697df8dfd5..0ae2e1712e2e 100644 --- a/arch/x86/lib/memcpy_64.S +++ b/arch/x86/lib/memcpy_64.S @@ -1,12 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* Copyright 2002 Andi Kleen */ +#include <linux/export.h> #include <linux/linkage.h> #include <linux/cfi_types.h> #include <asm/errno.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> -#include <asm/export.h> .section .noinstr.text, "ax" diff --git a/arch/x86/lib/memmove_32.S b/arch/x86/lib/memmove_32.S index 0588b2c0fc95..35010ba3dd6f 100644 --- a/arch/x86/lib/memmove_32.S +++ b/arch/x86/lib/memmove_32.S @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/export.h> #include <linux/linkage.h> -#include <asm/export.h> SYM_FUNC_START(memmove) /* diff --git a/arch/x86/lib/memmove_64.S b/arch/x86/lib/memmove_64.S index ccdf3a597045..1b60ae81ecd8 100644 --- a/arch/x86/lib/memmove_64.S +++ b/arch/x86/lib/memmove_64.S @@ -6,10 +6,10 @@ * This assembly file is re-written from memmove_64.c file. * - Copyright 2011 Fenghua Yu <fenghua.yu@intel.com> */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> -#include <asm/export.h> #undef memmove diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S index 3d818b849ec6..0199d56cb479 100644 --- a/arch/x86/lib/memset_64.S +++ b/arch/x86/lib/memset_64.S @@ -1,10 +1,10 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright 2002 Andi Kleen, SuSE Labs */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> -#include <asm/export.h> .section .noinstr.text, "ax" diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S index 235bbda6fc82..2877f5934177 100644 --- a/arch/x86/lib/putuser.S +++ b/arch/x86/lib/putuser.S @@ -11,13 +11,12 @@ * return an error value in addition to the "real" * return value. */ +#include <linux/export.h> #include <linux/linkage.h> #include <asm/thread_info.h> #include <asm/errno.h> #include <asm/asm.h> #include <asm/smap.h> -#include <asm/export.h> - /* * __put_user_X diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index cd86aeb5fdd3..7b2589877d06 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -1,12 +1,12 @@ /* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/export.h> #include <linux/stringify.h> #include <linux/linkage.h> #include <asm/dwarf2.h> #include <asm/cpufeatures.h> #include <asm/alternative.h> #include <asm/asm-offsets.h> -#include <asm/export.h> #include <asm/nospec-branch.h> #include <asm/unwind_hints.h> #include <asm/percpu.h> @@ -126,11 +126,19 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) #include <asm/GEN-for-each-reg.h> #undef GEN #endif + +#ifdef CONFIG_RETHUNK + /* - * This function name is magical and is used by -mfunction-return=thunk-extern - * for the compiler to generate JMPs to it. + * Be careful here: that label cannot really be removed because in + * some configurations and toolchains, the JMP __x86_return_thunk the + * compiler issues is either a short one or the compiler doesn't use + * relocations for same-section JMPs and that breaks the returns + * detection logic in apply_returns() and in objtool. */ -#ifdef CONFIG_RETHUNK + .section .text..__x86.return_thunk + +#ifdef CONFIG_CPU_SRSO /* * srso_alias_untrain_ret() and srso_alias_safe_ret() are placed at @@ -147,29 +155,18 @@ SYM_CODE_END(__x86_indirect_jump_thunk_array) * * As a result, srso_alias_safe_ret() becomes a safe return. */ -#ifdef CONFIG_CPU_SRSO - .section .text..__x86.rethunk_untrain - -SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) + .pushsection .text..__x86.rethunk_untrain +SYM_CODE_START_NOALIGN(srso_alias_untrain_ret) UNWIND_HINT_FUNC ANNOTATE_NOENDBR ASM_NOP2 lfence jmp srso_alias_return_thunk SYM_FUNC_END(srso_alias_untrain_ret) -__EXPORT_THUNK(srso_alias_untrain_ret) - - .section .text..__x86.rethunk_safe -#else -/* dummy definition for alternatives */ -SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) - ANNOTATE_UNRET_SAFE - ret - int3 -SYM_FUNC_END(srso_alias_untrain_ret) -#endif + .popsection -SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) + .pushsection .text..__x86.rethunk_safe +SYM_CODE_START_NOALIGN(srso_alias_safe_ret) lea 8(%_ASM_SP), %_ASM_SP UNWIND_HINT_FUNC ANNOTATE_UNRET_SAFE @@ -177,14 +174,63 @@ SYM_START(srso_alias_safe_ret, SYM_L_GLOBAL, SYM_A_NONE) int3 SYM_FUNC_END(srso_alias_safe_ret) - .section .text..__x86.return_thunk - -SYM_CODE_START(srso_alias_return_thunk) +SYM_CODE_START_NOALIGN(srso_alias_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR call srso_alias_safe_ret ud2 SYM_CODE_END(srso_alias_return_thunk) + .popsection + +/* + * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret() + * above. On kernel entry, srso_untrain_ret() is executed which is a + * + * movabs $0xccccc30824648d48,%rax + * + * and when the return thunk executes the inner label srso_safe_ret() + * later, it is a stack manipulation and a RET which is mispredicted and + * thus a "safe" one to use. + */ + .align 64 + .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc +SYM_CODE_START_LOCAL_NOALIGN(srso_untrain_ret) + ANNOTATE_NOENDBR + .byte 0x48, 0xb8 + +/* + * This forces the function return instruction to speculate into a trap + * (UD2 in srso_return_thunk() below). This RET will then mispredict + * and execution will continue at the return site read from the top of + * the stack. + */ +SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) + lea 8(%_ASM_SP), %_ASM_SP + ret + int3 + int3 + /* end of movabs */ + lfence + call srso_safe_ret + ud2 +SYM_CODE_END(srso_safe_ret) +SYM_FUNC_END(srso_untrain_ret) + +SYM_CODE_START(srso_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + call srso_safe_ret + ud2 +SYM_CODE_END(srso_return_thunk) + +#define JMP_SRSO_UNTRAIN_RET "jmp srso_untrain_ret" +#define JMP_SRSO_ALIAS_UNTRAIN_RET "jmp srso_alias_untrain_ret" +#else /* !CONFIG_CPU_SRSO */ +#define JMP_SRSO_UNTRAIN_RET "ud2" +#define JMP_SRSO_ALIAS_UNTRAIN_RET "ud2" +#endif /* CONFIG_CPU_SRSO */ + +#ifdef CONFIG_CPU_UNRET_ENTRY /* * Some generic notes on the untraining sequences: @@ -216,7 +262,7 @@ SYM_CODE_END(srso_alias_return_thunk) */ .align 64 .skip 64 - (retbleed_return_thunk - retbleed_untrain_ret), 0xcc -SYM_START(retbleed_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) +SYM_CODE_START_LOCAL_NOALIGN(retbleed_untrain_ret) ANNOTATE_NOENDBR /* * As executed from retbleed_untrain_ret, this is: @@ -264,72 +310,27 @@ SYM_CODE_END(retbleed_return_thunk) jmp retbleed_return_thunk int3 SYM_FUNC_END(retbleed_untrain_ret) -__EXPORT_THUNK(retbleed_untrain_ret) -/* - * SRSO untraining sequence for Zen1/2, similar to retbleed_untrain_ret() - * above. On kernel entry, srso_untrain_ret() is executed which is a - * - * movabs $0xccccc30824648d48,%rax - * - * and when the return thunk executes the inner label srso_safe_ret() - * later, it is a stack manipulation and a RET which is mispredicted and - * thus a "safe" one to use. - */ - .align 64 - .skip 64 - (srso_safe_ret - srso_untrain_ret), 0xcc -SYM_START(srso_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) - ANNOTATE_NOENDBR - .byte 0x48, 0xb8 +#define JMP_RETBLEED_UNTRAIN_RET "jmp retbleed_untrain_ret" +#else /* !CONFIG_CPU_UNRET_ENTRY */ +#define JMP_RETBLEED_UNTRAIN_RET "ud2" +#endif /* CONFIG_CPU_UNRET_ENTRY */ -/* - * This forces the function return instruction to speculate into a trap - * (UD2 in srso_return_thunk() below). This RET will then mispredict - * and execution will continue at the return site read from the top of - * the stack. - */ -SYM_INNER_LABEL(srso_safe_ret, SYM_L_GLOBAL) - lea 8(%_ASM_SP), %_ASM_SP - ret - int3 - int3 - /* end of movabs */ - lfence - call srso_safe_ret - ud2 -SYM_CODE_END(srso_safe_ret) -SYM_FUNC_END(srso_untrain_ret) -__EXPORT_THUNK(srso_untrain_ret) - -SYM_CODE_START(srso_return_thunk) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - call srso_safe_ret - ud2 -SYM_CODE_END(srso_return_thunk) +#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_SRSO) SYM_FUNC_START(entry_untrain_ret) - ALTERNATIVE_2 "jmp retbleed_untrain_ret", \ - "jmp srso_untrain_ret", X86_FEATURE_SRSO, \ - "jmp srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS + ALTERNATIVE_2 JMP_RETBLEED_UNTRAIN_RET, \ + JMP_SRSO_UNTRAIN_RET, X86_FEATURE_SRSO, \ + JMP_SRSO_ALIAS_UNTRAIN_RET, X86_FEATURE_SRSO_ALIAS SYM_FUNC_END(entry_untrain_ret) __EXPORT_THUNK(entry_untrain_ret) -SYM_CODE_START(__x86_return_thunk) - UNWIND_HINT_FUNC - ANNOTATE_NOENDBR - ANNOTATE_UNRET_SAFE - ret - int3 -SYM_CODE_END(__x86_return_thunk) -EXPORT_SYMBOL(__x86_return_thunk) - -#endif /* CONFIG_RETHUNK */ +#endif /* CONFIG_CPU_UNRET_ENTRY || CONFIG_CPU_SRSO */ #ifdef CONFIG_CALL_DEPTH_TRACKING .align 64 -SYM_FUNC_START(__x86_return_skl) +SYM_FUNC_START(call_depth_return_thunk) ANNOTATE_NOENDBR /* * Keep the hotpath in a 16byte I-fetch for the non-debug @@ -356,6 +357,33 @@ SYM_FUNC_START(__x86_return_skl) ANNOTATE_UNRET_SAFE ret int3 -SYM_FUNC_END(__x86_return_skl) +SYM_FUNC_END(call_depth_return_thunk) #endif /* CONFIG_CALL_DEPTH_TRACKING */ + +/* + * This function name is magical and is used by -mfunction-return=thunk-extern + * for the compiler to generate JMPs to it. + * + * This code is only used during kernel boot or module init. All + * '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. + */ +SYM_CODE_START(__x86_return_thunk) + UNWIND_HINT_FUNC + ANNOTATE_NOENDBR + ANNOTATE_UNRET_SAFE + ret + int3 +SYM_CODE_END(__x86_return_thunk) +EXPORT_SYMBOL(__x86_return_thunk) + +#endif /* CONFIG_RETHUNK */ diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c index 5a53c2cc169c..6993f026adec 100644 --- a/arch/x86/mm/maccess.c +++ b/arch/x86/mm/maccess.c @@ -9,12 +9,21 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) unsigned long vaddr = (unsigned long)unsafe_src; /* - * Range covering the highest possible canonical userspace address - * as well as non-canonical address range. For the canonical range - * we also need to include the userspace guard page. + * Do not allow userspace addresses. This disallows + * normal userspace and the userspace guard page: */ - return vaddr >= TASK_SIZE_MAX + PAGE_SIZE && - __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits); + if (vaddr < TASK_SIZE_MAX + PAGE_SIZE) + return false; + + /* + * Allow everything during early boot before 'x86_virt_bits' + * is initialized. Needed for instruction decoding in early + * exception handlers. + */ + if (!boot_cpu_data.x86_virt_bits) + return true; + + return __is_canonical_address(vaddr, boot_cpu_data.x86_virt_bits); } #else bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 9f27e14e185f..c290c55b632b 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -12,6 +12,7 @@ #include <linux/swiotlb.h> #include <linux/cc_platform.h> #include <linux/mem_encrypt.h> +#include <linux/virtio_anchor.h> /* Override for DMA direct allocation check - ARCH_HAS_FORCE_DMA_UNENCRYPTED */ bool force_dma_unencrypted(struct device *dev) @@ -86,3 +87,36 @@ void __init mem_encrypt_init(void) print_mem_encrypt_feature_info(); } + +void __init mem_encrypt_setup_arch(void) +{ + phys_addr_t total_mem = memblock_phys_mem_size(); + unsigned long size; + + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + return; + + /* + * For SEV and TDX, all DMA has to occur via shared/unencrypted pages. + * Kernel uses SWIOTLB to make this happen without changing device + * drivers. However, depending on the workload being run, the + * default 64MB of SWIOTLB may not be enough and SWIOTLB may + * run out of buffers for DMA, resulting in I/O errors and/or + * performance degradation especially with high I/O workloads. + * + * Adjust the default size of SWIOTLB using a percentage of guest + * memory for SWIOTLB buffers. Also, as the SWIOTLB bounce buffer + * memory is allocated from low memory, ensure that the adjusted size + * is within the limits of low available memory. + * + * The percentage of guest memory used here for SWIOTLB buffers + * is more of an approximation of the static adjustment which + * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6% + */ + size = total_mem * 6 / 100; + size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G); + swiotlb_adjust_size(size); + + /* Set restricted memory access for virtio. */ + virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc); +} diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index 6faea41e99b6..a68f2dda0948 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -19,8 +19,6 @@ #include <linux/kernel.h> #include <linux/bitops.h> #include <linux/dma-mapping.h> -#include <linux/virtio_config.h> -#include <linux/virtio_anchor.h> #include <linux/cc_platform.h> #include <asm/tlbflush.h> @@ -215,40 +213,6 @@ void __init sme_map_bootdata(char *real_mode_data) __sme_early_map_unmap_mem(__va(cmdline_paddr), COMMAND_LINE_SIZE, true); } -void __init sev_setup_arch(void) -{ - phys_addr_t total_mem = memblock_phys_mem_size(); - unsigned long size; - - if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) - return; - - /* - * For SEV, all DMA has to occur via shared/unencrypted pages. - * SEV uses SWIOTLB to make this happen without changing device - * drivers. However, depending on the workload being run, the - * default 64MB of SWIOTLB may not be enough and SWIOTLB may - * run out of buffers for DMA, resulting in I/O errors and/or - * performance degradation especially with high I/O workloads. - * - * Adjust the default size of SWIOTLB for SEV guests using - * a percentage of guest memory for SWIOTLB buffers. - * Also, as the SWIOTLB bounce buffer memory is allocated - * from low memory, ensure that the adjusted size is within - * the limits of low available memory. - * - * The percentage of guest memory used here for SWIOTLB buffers - * is more of an approximation of the static adjustment which - * 64MB for <1G, and ~128M to 256M for 1G-to-4G, i.e., the 6% - */ - size = total_mem * 6 / 100; - size = clamp_val(size, IO_TLB_DEFAULT_SIZE, SZ_1G); - swiotlb_adjust_size(size); - - /* Set restricted memory access for virtio. */ - virtio_set_mem_acc_cb(virtio_require_restricted_mem_acc); -} - static unsigned long pg_level_to_pfn(int level, pte_t *kpte, pgprot_t *ret_prot) { unsigned long pfn = 0; diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 2aadb2019b4f..b29ceb19e46e 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -3,6 +3,7 @@ #include <linux/acpi.h> #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/of.h> #include <linux/string.h> #include <linux/init.h> #include <linux/memblock.h> @@ -11,6 +12,7 @@ #include <linux/nodemask.h> #include <linux/sched.h> #include <linux/topology.h> +#include <linux/sort.h> #include <asm/e820/api.h> #include <asm/proto.h> @@ -56,7 +58,7 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] = { int numa_cpu_node(int cpu) { - int apicid = early_per_cpu(x86_cpu_to_apicid, cpu); + u32 apicid = early_per_cpu(x86_cpu_to_apicid, cpu); if (apicid != BAD_APICID) return __apicid_to_node[apicid]; @@ -601,13 +603,6 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) if (start >= end) continue; - /* - * Don't confuse VM with a node that doesn't have the - * minimum amount of memory: - */ - if (end && (end - start) < NODE_MIN_SIZE) - continue; - alloc_node_data(nid); } @@ -733,6 +728,8 @@ void __init x86_numa_init(void) if (!numa_init(amd_numa_init)) return; #endif + if (acpi_disabled && !numa_init(of_numa_init)) + return; } numa_init(dummy_numa_init); @@ -786,7 +783,7 @@ void __init init_gi_nodes(void) void __init init_cpu_to_node(void) { int cpu; - u16 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid); + u32 *cpu_to_apicid = early_per_cpu_ptr(x86_cpu_to_apicid); BUG_ON(cpu_to_apicid == NULL); @@ -961,4 +958,83 @@ int memory_add_physaddr_to_nid(u64 start) return nid; } EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); + +static int __init cmp_memblk(const void *a, const void *b) +{ + const struct numa_memblk *ma = *(const struct numa_memblk **)a; + const struct numa_memblk *mb = *(const struct numa_memblk **)b; + + return ma->start - mb->start; +} + +static struct numa_memblk *numa_memblk_list[NR_NODE_MEMBLKS] __initdata; + +/** + * numa_fill_memblks - Fill gaps in numa_meminfo memblks + * @start: address to begin fill + * @end: address to end fill + * + * Find and extend numa_meminfo memblks to cover the @start-@end + * physical address range, such that the first memblk includes + * @start, the last memblk includes @end, and any gaps in between + * are filled. + * + * RETURNS: + * 0 : Success + * NUMA_NO_MEMBLK : No memblk exists in @start-@end range + */ + +int __init numa_fill_memblks(u64 start, u64 end) +{ + struct numa_memblk **blk = &numa_memblk_list[0]; + struct numa_meminfo *mi = &numa_meminfo; + int count = 0; + u64 prev_end; + + /* + * Create a list of pointers to numa_meminfo memblks that + * overlap start, end. Exclude (start == bi->end) since + * end addresses in both a CFMWS range and a memblk range + * are exclusive. + * + * This list of pointers is used to make in-place changes + * that fill out the numa_meminfo memblks. + */ + for (int i = 0; i < mi->nr_blks; i++) { + struct numa_memblk *bi = &mi->blk[i]; + + if (start < bi->end && end >= bi->start) { + blk[count] = &mi->blk[i]; + count++; + } + } + if (!count) + return NUMA_NO_MEMBLK; + + /* Sort the list of pointers in memblk->start order */ + sort(&blk[0], count, sizeof(blk[0]), cmp_memblk, NULL); + + /* Make sure the first/last memblks include start/end */ + blk[0]->start = min(blk[0]->start, start); + blk[count - 1]->end = max(blk[count - 1]->end, end); + + /* + * Fill any gaps by tracking the previous memblks + * end address and backfilling to it if needed. + */ + prev_end = blk[0]->end; + for (int i = 1; i < count; i++) { + struct numa_memblk *curr = blk[i]; + + if (prev_end >= curr->start) { + if (prev_end < curr->end) + prev_end = curr->end; + } else { + curr->start = prev_end; + prev_end = curr->end; + } + } + return 0; +} + #endif diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index 9deadf517f14..0cbc1b8e8e3d 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -76,6 +76,9 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd) #if CONFIG_PGTABLE_LEVELS > 3 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud) { + struct ptdesc *ptdesc = virt_to_ptdesc(pud); + + pagetable_pud_dtor(ptdesc); paravirt_release_pud(__pa(pud) >> PAGE_SHIFT); paravirt_tlb_remove_table(tlb, virt_to_page(pud)); } diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 78414c6d1b5e..5dd733944629 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -69,6 +69,7 @@ static void __init pti_print_if_secure(const char *reason) pr_info("%s\n", reason); } +/* Assume mode is auto unless overridden via cmdline below. */ static enum pti_mode { PTI_AUTO = 0, PTI_FORCE_OFF, @@ -77,50 +78,49 @@ static enum pti_mode { void __init pti_check_boottime_disable(void) { - char arg[5]; - int ret; - - /* Assume mode is auto unless overridden. */ - pti_mode = PTI_AUTO; - if (hypervisor_is_type(X86_HYPER_XEN_PV)) { pti_mode = PTI_FORCE_OFF; pti_print_if_insecure("disabled on XEN PV."); return; } - ret = cmdline_find_option(boot_command_line, "pti", arg, sizeof(arg)); - if (ret > 0) { - if (ret == 3 && !strncmp(arg, "off", 3)) { - pti_mode = PTI_FORCE_OFF; - pti_print_if_insecure("disabled on command line."); - return; - } - if (ret == 2 && !strncmp(arg, "on", 2)) { - pti_mode = PTI_FORCE_ON; - pti_print_if_secure("force enabled on command line."); - goto enable; - } - if (ret == 4 && !strncmp(arg, "auto", 4)) { - pti_mode = PTI_AUTO; - goto autosel; - } - } - - if (cmdline_find_option_bool(boot_command_line, "nopti") || - cpu_mitigations_off()) { + if (cpu_mitigations_off()) pti_mode = PTI_FORCE_OFF; + if (pti_mode == PTI_FORCE_OFF) { pti_print_if_insecure("disabled on command line."); return; } -autosel: - if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) + if (pti_mode == PTI_FORCE_ON) + pti_print_if_secure("force enabled on command line."); + + if (pti_mode == PTI_AUTO && !boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN)) return; -enable: + setup_force_cpu_cap(X86_FEATURE_PTI); } +static int __init pti_parse_cmdline(char *arg) +{ + if (!strcmp(arg, "off")) + pti_mode = PTI_FORCE_OFF; + else if (!strcmp(arg, "on")) + pti_mode = PTI_FORCE_ON; + else if (!strcmp(arg, "auto")) + pti_mode = PTI_AUTO; + else + return -EINVAL; + return 0; +} +early_param("pti", pti_parse_cmdline); + +static int __init pti_parse_cmdline_nopti(char *arg) +{ + pti_mode = PTI_FORCE_OFF; + return 0; +} +early_param("nopti", pti_parse_cmdline_nopti); + pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd) { /* diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index a5930042139d..8c10d9abc239 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -16,6 +16,9 @@ #include <asm/set_memory.h> #include <asm/nospec-branch.h> #include <asm/text-patching.h> +#include <asm/unwind.h> + +static bool all_callee_regs_used[4] = {true, true, true, true}; static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) { @@ -255,6 +258,14 @@ struct jit_context { /* Number of bytes that will be skipped on tailcall */ #define X86_TAIL_CALL_OFFSET (11 + ENDBR_INSN_SIZE) +static void push_r12(u8 **pprog) +{ + u8 *prog = *pprog; + + EMIT2(0x41, 0x54); /* push r12 */ + *pprog = prog; +} + static void push_callee_regs(u8 **pprog, bool *callee_regs_used) { u8 *prog = *pprog; @@ -270,6 +281,14 @@ static void push_callee_regs(u8 **pprog, bool *callee_regs_used) *pprog = prog; } +static void pop_r12(u8 **pprog) +{ + u8 *prog = *pprog; + + EMIT2(0x41, 0x5C); /* pop r12 */ + *pprog = prog; +} + static void pop_callee_regs(u8 **pprog, bool *callee_regs_used) { u8 *prog = *pprog; @@ -291,7 +310,8 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used) * while jumping to another program */ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, - bool tail_call_reachable, bool is_subprog) + bool tail_call_reachable, bool is_subprog, + bool is_exception_cb) { u8 *prog = *pprog; @@ -303,12 +323,30 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, prog += X86_PATCH_SIZE; if (!ebpf_from_cbpf) { if (tail_call_reachable && !is_subprog) + /* When it's the entry of the whole tailcall context, + * zeroing rax means initialising tail_call_cnt. + */ EMIT2(0x31, 0xC0); /* xor eax, eax */ else + /* Keep the same instruction layout. */ EMIT2(0x66, 0x90); /* nop2 */ } - EMIT1(0x55); /* push rbp */ - EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ + /* Exception callback receives FP as third parameter */ + if (is_exception_cb) { + EMIT3(0x48, 0x89, 0xF4); /* mov rsp, rsi */ + EMIT3(0x48, 0x89, 0xD5); /* mov rbp, rdx */ + /* The main frame must have exception_boundary as true, so we + * first restore those callee-saved regs from stack, before + * reusing the stack frame. + */ + pop_callee_regs(&prog, all_callee_regs_used); + pop_r12(&prog); + /* Reset the stack frame. */ + EMIT3(0x48, 0x89, 0xEC); /* mov rsp, rbp */ + } else { + EMIT1(0x55); /* push rbp */ + EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ + } /* X86_TAIL_CALL_OFFSET is here */ EMIT_ENDBR(); @@ -467,7 +505,8 @@ static void emit_return(u8 **pprog, u8 *ip) * goto *(prog->bpf_func + prologue_size); * out: */ -static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, +static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog, + u8 **pprog, bool *callee_regs_used, u32 stack_depth, u8 *ip, struct jit_context *ctx) { @@ -517,7 +556,12 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, offset = ctx->tail_call_indirect_label - (prog + 2 - start); EMIT2(X86_JE, offset); /* je out */ - pop_callee_regs(&prog, callee_regs_used); + if (bpf_prog->aux->exception_boundary) { + pop_callee_regs(&prog, all_callee_regs_used); + pop_r12(&prog); + } else { + pop_callee_regs(&prog, callee_regs_used); + } EMIT1(0x58); /* pop rax */ if (stack_depth) @@ -541,7 +585,8 @@ static void emit_bpf_tail_call_indirect(u8 **pprog, bool *callee_regs_used, *pprog = prog; } -static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, +static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog, + struct bpf_jit_poke_descriptor *poke, u8 **pprog, u8 *ip, bool *callee_regs_used, u32 stack_depth, struct jit_context *ctx) @@ -570,7 +615,13 @@ static void emit_bpf_tail_call_direct(struct bpf_jit_poke_descriptor *poke, emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE, poke->tailcall_bypass); - pop_callee_regs(&prog, callee_regs_used); + if (bpf_prog->aux->exception_boundary) { + pop_callee_regs(&prog, all_callee_regs_used); + pop_r12(&prog); + } else { + pop_callee_regs(&prog, callee_regs_used); + } + EMIT1(0x58); /* pop rax */ if (stack_depth) EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8)); @@ -1018,6 +1069,10 @@ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op) #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp))) +/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ +#define RESTORE_TAIL_CALL_CNT(stack) \ + EMIT3_off32(0x48, 0x8B, 0x85, -round_up(stack, 8) - 8) + static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image, int oldproglen, struct jit_context *ctx, bool jmp_padding) { @@ -1041,8 +1096,20 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image emit_prologue(&prog, bpf_prog->aux->stack_depth, bpf_prog_was_classic(bpf_prog), tail_call_reachable, - bpf_prog->aux->func_idx != 0); - push_callee_regs(&prog, callee_regs_used); + bpf_is_subprog(bpf_prog), bpf_prog->aux->exception_cb); + /* Exception callback will clobber callee regs for its own use, and + * restore the original callee regs from main prog's stack frame. + */ + if (bpf_prog->aux->exception_boundary) { + /* We also need to save r12, which is not mapped to any BPF + * register, as we throw after entry into the kernel, which may + * overwrite r12. + */ + push_r12(&prog); + push_callee_regs(&prog, all_callee_regs_used); + } else { + push_callee_regs(&prog, callee_regs_used); + } ilen = prog - temp; if (rw_image) @@ -1623,9 +1690,7 @@ st: if (is_imm8(insn->off)) func = (u8 *) __bpf_call_base + imm32; if (tail_call_reachable) { - /* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */ - EMIT3_off32(0x48, 0x8B, 0x85, - -round_up(bpf_prog->aux->stack_depth, 8) - 8); + RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth); if (!imm32) return -EINVAL; offs = 7 + x86_call_depth_emit_accounting(&prog, func); @@ -1641,13 +1706,15 @@ st: if (is_imm8(insn->off)) case BPF_JMP | BPF_TAIL_CALL: if (imm32) - emit_bpf_tail_call_direct(&bpf_prog->aux->poke_tab[imm32 - 1], + emit_bpf_tail_call_direct(bpf_prog, + &bpf_prog->aux->poke_tab[imm32 - 1], &prog, image + addrs[i - 1], callee_regs_used, bpf_prog->aux->stack_depth, ctx); else - emit_bpf_tail_call_indirect(&prog, + emit_bpf_tail_call_indirect(bpf_prog, + &prog, callee_regs_used, bpf_prog->aux->stack_depth, image + addrs[i - 1], @@ -1900,7 +1967,12 @@ emit_jmp: seen_exit = true; /* Update cleanup_addr */ ctx->cleanup_addr = proglen; - pop_callee_regs(&prog, callee_regs_used); + if (bpf_prog->aux->exception_boundary) { + pop_callee_regs(&prog, all_callee_regs_used); + pop_r12(&prog); + } else { + pop_callee_regs(&prog, callee_regs_used); + } EMIT1(0xC9); /* leave */ emit_return(&prog, image + addrs[i - 1] + (prog - temp)); break; @@ -2400,6 +2472,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i * [ ... ] * [ stack_arg2 ] * RBP - arg_stack_off [ stack_arg1 ] + * RSP [ tail_call_cnt ] BPF_TRAMP_F_TAIL_CALL_CTX */ /* room for return value of orig_call or fentry prog */ @@ -2464,6 +2537,8 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i else /* sub rsp, stack_size */ EMIT4(0x48, 0x83, 0xEC, stack_size); + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + EMIT1(0x50); /* push rax */ /* mov QWORD PTR [rbp - rbx_off], rbx */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_6, -rbx_off); @@ -2516,9 +2591,15 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i restore_regs(m, &prog, regs_off); save_args(m, &prog, arg_stack_off, true); + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + /* Before calling the original function, restore the + * tail_call_cnt from stack to rax. + */ + RESTORE_TAIL_CALL_CNT(stack_size); + if (flags & BPF_TRAMP_F_ORIG_STACK) { - emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8); - EMIT2(0xff, 0xd0); /* call *rax */ + emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, 8); + EMIT2(0xff, 0xd3); /* call *rbx */ } else { /* call original function */ if (emit_rsb_call(&prog, orig_call, prog)) { @@ -2569,7 +2650,12 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i ret = -EINVAL; goto cleanup; } - } + } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + /* Before running the original function, restore the + * tail_call_cnt from stack to rax. + */ + RESTORE_TAIL_CALL_CNT(stack_size); + /* restore return value of orig_call or fentry prog back into RAX */ if (save_ret) emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8); @@ -2913,3 +2999,29 @@ void bpf_jit_free(struct bpf_prog *prog) bpf_prog_unlock_free(prog); } + +bool bpf_jit_supports_exceptions(void) +{ + /* We unwind through both kernel frames (starting from within bpf_throw + * call) and BPF frames. Therefore we require ORC unwinder to be enabled + * to walk kernel frames and reach BPF frames in the stack trace. + */ + return IS_ENABLED(CONFIG_UNWINDER_ORC); +} + +void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie) +{ +#if defined(CONFIG_UNWINDER_ORC) + struct unwind_state state; + unsigned long addr; + + for (unwind_start(&state, current, NULL, NULL); !unwind_done(&state); + unwind_next_frame(&state)) { + addr = unwind_get_return_address(&state); + if (!addr || !consume_fn(cookie, (u64)addr, (u64)state.sp, (u64)state.bp)) + break; + } + return; +#endif + WARN(1, "verification of programs using bpf_throw should have failed\n"); +} diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index e3ec02e6ac9f..f347c20247d3 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -3,9 +3,11 @@ * Exceptions for specific devices. Usually work-arounds for fatal design flaws. */ +#include <linux/bitfield.h> #include <linux/delay.h> #include <linux/dmi.h> #include <linux/pci.h> +#include <linux/suspend.h> #include <linux/vgaarb.h> #include <asm/amd_nb.h> #include <asm/hpet.h> @@ -904,3 +906,60 @@ static void chromeos_fixup_apl_pci_l1ss_capability(struct pci_dev *dev) } DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x5ad6, chromeos_save_apl_pci_l1ss_capability); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, 0x5ad6, chromeos_fixup_apl_pci_l1ss_capability); + +#ifdef CONFIG_SUSPEND +/* + * Root Ports on some AMD SoCs advertise PME_Support for D3hot and D3cold, but + * if the SoC is put into a hardware sleep state by the amd-pmc driver, the + * Root Ports don't generate wakeup interrupts for USB devices. + * + * When suspending, remove D3hot and D3cold from the PME_Support advertised + * by the Root Port so we don't use those states if we're expecting wakeup + * interrupts. Restore the advertised PME_Support when resuming. + */ +static void amd_rp_pme_suspend(struct pci_dev *dev) +{ + struct pci_dev *rp; + + /* + * PM_SUSPEND_ON means we're doing runtime suspend, which means + * amd-pmc will not be involved so PMEs during D3 work as advertised. + * + * The PMEs *do* work if amd-pmc doesn't put the SoC in the hardware + * sleep state, but we assume amd-pmc is always present. + */ + if (pm_suspend_target_state == PM_SUSPEND_ON) + return; + + rp = pcie_find_root_port(dev); + if (!rp->pm_cap) + return; + + rp->pme_support &= ~((PCI_PM_CAP_PME_D3hot|PCI_PM_CAP_PME_D3cold) >> + PCI_PM_CAP_PME_SHIFT); + dev_info_once(&rp->dev, "quirk: disabling D3cold for suspend\n"); +} + +static void amd_rp_pme_resume(struct pci_dev *dev) +{ + struct pci_dev *rp; + u16 pmc; + + rp = pcie_find_root_port(dev); + if (!rp->pm_cap) + return; + + pci_read_config_word(rp, rp->pm_cap + PCI_PM_PMC, &pmc); + rp->pme_support = FIELD_GET(PCI_PM_CAP_PME_MASK, pmc); +} +/* Rembrandt (yellow_carp) */ +DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x162e, amd_rp_pme_suspend); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x162e, amd_rp_pme_resume); +DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x162f, amd_rp_pme_suspend); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x162f, amd_rp_pme_resume); +/* Phoenix (pink_sardine) */ +DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x1668, amd_rp_pme_suspend); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1668, amd_rp_pme_resume); +DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_AMD, 0x1669, amd_rp_pme_suspend); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_AMD, 0x1669, amd_rp_pme_resume); +#endif /* CONFIG_SUSPEND */ diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index 45d0c17ce77c..e03207de2880 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -17,6 +17,7 @@ #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/slab.h> +#include <linux/string.h> #include <linux/clocksource.h> #include <asm/apic.h> @@ -178,49 +179,56 @@ module_param_named(debug, uv_nmi_debug, int, 0644); } while (0) /* Valid NMI Actions */ -#define ACTION_LEN 16 -static struct nmi_action { - char *action; - char *desc; -} valid_acts[] = { - { "kdump", "do kernel crash dump" }, - { "dump", "dump process stack for each cpu" }, - { "ips", "dump Inst Ptr info for each cpu" }, - { "kdb", "enter KDB (needs kgdboc= assignment)" }, - { "kgdb", "enter KGDB (needs gdb target remote)" }, - { "health", "check if CPUs respond to NMI" }, +enum action_t { + nmi_act_kdump, + nmi_act_dump, + nmi_act_ips, + nmi_act_kdb, + nmi_act_kgdb, + nmi_act_health, + nmi_act_max }; -typedef char action_t[ACTION_LEN]; -static action_t uv_nmi_action = { "dump" }; + +static const char * const actions[nmi_act_max] = { + [nmi_act_kdump] = "kdump", + [nmi_act_dump] = "dump", + [nmi_act_ips] = "ips", + [nmi_act_kdb] = "kdb", + [nmi_act_kgdb] = "kgdb", + [nmi_act_health] = "health", +}; + +static const char * const actions_desc[nmi_act_max] = { + [nmi_act_kdump] = "do kernel crash dump", + [nmi_act_dump] = "dump process stack for each cpu", + [nmi_act_ips] = "dump Inst Ptr info for each cpu", + [nmi_act_kdb] = "enter KDB (needs kgdboc= assignment)", + [nmi_act_kgdb] = "enter KGDB (needs gdb target remote)", + [nmi_act_health] = "check if CPUs respond to NMI", +}; + +static enum action_t uv_nmi_action = nmi_act_dump; static int param_get_action(char *buffer, const struct kernel_param *kp) { - return sprintf(buffer, "%s\n", uv_nmi_action); + return sprintf(buffer, "%s\n", actions[uv_nmi_action]); } static int param_set_action(const char *val, const struct kernel_param *kp) { - int i; - int n = ARRAY_SIZE(valid_acts); - char arg[ACTION_LEN]; - - /* (remove possible '\n') */ - strscpy(arg, val, strnchrnul(val, sizeof(arg)-1, '\n') - val + 1); - - for (i = 0; i < n; i++) - if (!strcmp(arg, valid_acts[i].action)) - break; + int i, n = ARRAY_SIZE(actions); - if (i < n) { - strscpy(uv_nmi_action, arg, sizeof(uv_nmi_action)); - pr_info("UV: New NMI action:%s\n", uv_nmi_action); + i = sysfs_match_string(actions, val); + if (i >= 0) { + uv_nmi_action = i; + pr_info("UV: New NMI action:%s\n", actions[i]); return 0; } - pr_err("UV: Invalid NMI action:%s, valid actions are:\n", arg); + pr_err("UV: Invalid NMI action. Valid actions are:\n"); for (i = 0; i < n; i++) - pr_err("UV: %-8s - %s\n", - valid_acts[i].action, valid_acts[i].desc); + pr_err("UV: %-8s - %s\n", actions[i], actions_desc[i]); + return -EINVAL; } @@ -228,15 +236,10 @@ static const struct kernel_param_ops param_ops_action = { .get = param_get_action, .set = param_set_action, }; -#define param_check_action(name, p) __param_check(name, p, action_t) +#define param_check_action(name, p) __param_check(name, p, enum action_t) module_param_named(action, uv_nmi_action, action, 0644); -static inline bool uv_nmi_action_is(const char *action) -{ - return (strncmp(uv_nmi_action, action, strlen(action)) == 0); -} - /* Setup which NMI support is present in system */ static void uv_nmi_setup_mmrs(void) { @@ -727,10 +730,10 @@ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs) if (cpu == 0) uv_nmi_dump_cpu_ip_hdr(); - if (current->pid != 0 || !uv_nmi_action_is("ips")) + if (current->pid != 0 || uv_nmi_action != nmi_act_ips) uv_nmi_dump_cpu_ip(cpu, regs); - if (uv_nmi_action_is("dump")) { + if (uv_nmi_action == nmi_act_dump) { pr_info("UV:%sNMI process trace for CPU %d\n", dots, cpu); show_regs(regs); } @@ -798,7 +801,7 @@ static void uv_nmi_dump_state(int cpu, struct pt_regs *regs, int master) int saved_console_loglevel = console_loglevel; pr_alert("UV: tracing %s for %d CPUs from CPU %d\n", - uv_nmi_action_is("ips") ? "IPs" : "processes", + uv_nmi_action == nmi_act_ips ? "IPs" : "processes", atomic_read(&uv_nmi_cpus_in_nmi), cpu); console_loglevel = uv_nmi_loglevel; @@ -874,7 +877,7 @@ static inline int uv_nmi_kdb_reason(void) static inline int uv_nmi_kdb_reason(void) { /* Ensure user is expecting to attach gdb remote */ - if (uv_nmi_action_is("kgdb")) + if (uv_nmi_action == nmi_act_kgdb) return 0; pr_err("UV: NMI error: KDB is not enabled in this kernel\n"); @@ -950,28 +953,35 @@ static int uv_handle_nmi(unsigned int reason, struct pt_regs *regs) master = (atomic_read(&uv_nmi_cpu) == cpu); /* If NMI action is "kdump", then attempt to do it */ - if (uv_nmi_action_is("kdump")) { + if (uv_nmi_action == nmi_act_kdump) { uv_nmi_kdump(cpu, master, regs); /* Unexpected return, revert action to "dump" */ if (master) - strscpy(uv_nmi_action, "dump", sizeof(uv_nmi_action)); + uv_nmi_action = nmi_act_dump; } /* Pause as all CPU's enter the NMI handler */ uv_nmi_wait(master); /* Process actions other than "kdump": */ - if (uv_nmi_action_is("health")) { + switch (uv_nmi_action) { + case nmi_act_health: uv_nmi_action_health(cpu, regs, master); - } else if (uv_nmi_action_is("ips") || uv_nmi_action_is("dump")) { + break; + case nmi_act_ips: + case nmi_act_dump: uv_nmi_dump_state(cpu, regs, master); - } else if (uv_nmi_action_is("kdb") || uv_nmi_action_is("kgdb")) { + break; + case nmi_act_kdb: + case nmi_act_kgdb: uv_call_kgdb_kdb(cpu, regs, master); - } else { + break; + default: if (master) - pr_alert("UV: unknown NMI action: %s\n", uv_nmi_action); + pr_alert("UV: unknown NMI action: %d\n", uv_nmi_action); uv_nmi_sync_exit(master); + break; } /* Clear per_cpu "in_nmi" flag */ diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c index 54663f3e00cb..ff5afc8a5a41 100644 --- a/arch/x86/platform/uv/uv_time.c +++ b/arch/x86/platform/uv/uv_time.c @@ -53,7 +53,7 @@ struct uv_rtc_timer_head { struct { int lcpu; /* systemwide logical cpu number */ u64 expires; /* next timer expiration for this cpu */ - } cpu[]; + } cpu[] __counted_by(ncpus); }; /* diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile index 6825e146a62f..b86d634730b2 100644 --- a/arch/x86/um/vdso/Makefile +++ b/arch/x86/um/vdso/Makefile @@ -67,15 +67,3 @@ quiet_cmd_vdso = VDSO $@ VDSO_LDFLAGS = -fPIC -shared -Wl,--hash-style=sysv -z noexecstack GCOV_PROFILE := n - -# -# Install the unstripped copy of vdso*.so listed in $(vdso-install-y). -# -quiet_cmd_vdso_install = INSTALL $@ - cmd_vdso_install = cp $(obj)/$@.dbg $(MODLIB)/vdso/$@ -$(vdso-install-y): %.so: $(obj)/%.so.dbg FORCE - @mkdir -p $(MODLIB)/vdso - $(call cmd,vdso_install) - -PHONY += vdso_install $(vdso-install-y) -vdso_install: $(vdso-install-y) diff --git a/arch/x86/video/fbdev.c b/arch/x86/video/fbdev.c index 49a0452402e9..1dd6528cc947 100644 --- a/arch/x86/video/fbdev.c +++ b/arch/x86/video/fbdev.c @@ -13,16 +13,17 @@ #include <linux/vgaarb.h> #include <asm/fb.h> -void fb_pgprotect(struct file *file, struct vm_area_struct *vma, unsigned long off) +pgprot_t pgprot_framebuffer(pgprot_t prot, + unsigned long vm_start, unsigned long vm_end, + unsigned long offset) { - unsigned long prot; - - prot = pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK; + pgprot_val(prot) &= ~_PAGE_CACHE_MASK; if (boot_cpu_data.x86 > 3) - pgprot_val(vma->vm_page_prot) = - prot | cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS); + pgprot_val(prot) |= cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS); + + return prot; } -EXPORT_SYMBOL(fb_pgprotect); +EXPORT_SYMBOL(pgprot_framebuffer); int fb_is_primary_device(struct fb_info *info) { diff --git a/arch/x86/virt/Makefile b/arch/x86/virt/Makefile new file mode 100644 index 000000000000..1e36502cd738 --- /dev/null +++ b/arch/x86/virt/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-y += vmx/ diff --git a/arch/x86/virt/vmx/Makefile b/arch/x86/virt/vmx/Makefile new file mode 100644 index 000000000000..feebda21d793 --- /dev/null +++ b/arch/x86/virt/vmx/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-$(CONFIG_INTEL_TDX_HOST) += tdx/ diff --git a/arch/x86/virt/vmx/tdx/Makefile b/arch/x86/virt/vmx/tdx/Makefile new file mode 100644 index 000000000000..46ef8f73aebb --- /dev/null +++ b/arch/x86/virt/vmx/tdx/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-y += seamcall.o diff --git a/arch/x86/virt/vmx/tdx/seamcall.S b/arch/x86/virt/vmx/tdx/seamcall.S new file mode 100644 index 000000000000..5b1f2286aea9 --- /dev/null +++ b/arch/x86/virt/vmx/tdx/seamcall.S @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/linkage.h> +#include <asm/frame.h> + +#include "tdxcall.S" + +/* + * __seamcall() - Host-side interface functions to SEAM software + * (the P-SEAMLDR or the TDX module). + * + * __seamcall() function ABI: + * + * @fn (RDI) - SEAMCALL Leaf number, moved to RAX + * @args (RSI) - struct tdx_module_args for input + * + * Only RCX/RDX/R8-R11 are used as input registers. + * + * Return (via RAX) TDX_SEAMCALL_VMFAILINVALID if the SEAMCALL itself + * fails, or the completion status of the SEAMCALL leaf function. + */ +SYM_FUNC_START(__seamcall) + TDX_MODULE_CALL host=1 +SYM_FUNC_END(__seamcall) + +/* + * __seamcall_ret() - Host-side interface functions to SEAM software + * (the P-SEAMLDR or the TDX module), with saving output registers to + * the 'struct tdx_module_args' used as input. + * + * __seamcall_ret() function ABI: + * + * @fn (RDI) - SEAMCALL Leaf number, moved to RAX + * @args (RSI) - struct tdx_module_args for input and output + * + * Only RCX/RDX/R8-R11 are used as input/output registers. + * + * Return (via RAX) TDX_SEAMCALL_VMFAILINVALID if the SEAMCALL itself + * fails, or the completion status of the SEAMCALL leaf function. + */ +SYM_FUNC_START(__seamcall_ret) + TDX_MODULE_CALL host=1 ret=1 +SYM_FUNC_END(__seamcall_ret) + +/* + * __seamcall_saved_ret() - Host-side interface functions to SEAM software + * (the P-SEAMLDR or the TDX module), with saving output registers to the + * 'struct tdx_module_args' used as input. + * + * __seamcall_saved_ret() function ABI: + * + * @fn (RDI) - SEAMCALL Leaf number, moved to RAX + * @args (RSI) - struct tdx_module_args for input and output + * + * All registers in @args are used as input/output registers. + * + * Return (via RAX) TDX_SEAMCALL_VMFAILINVALID if the SEAMCALL itself + * fails, or the completion status of the SEAMCALL leaf function. + */ +SYM_FUNC_START(__seamcall_saved_ret) + TDX_MODULE_CALL host=1 ret=1 saved=1 +SYM_FUNC_END(__seamcall_saved_ret) diff --git a/arch/x86/virt/vmx/tdx/tdxcall.S b/arch/x86/virt/vmx/tdx/tdxcall.S index 49a54356ae99..016a2a1ec1d6 100644 --- a/arch/x86/virt/vmx/tdx/tdxcall.S +++ b/arch/x86/virt/vmx/tdx/tdxcall.S @@ -1,5 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <asm/asm-offsets.h> +#include <asm/frame.h> +#include <asm/asm.h> #include <asm/tdx.h> /* @@ -16,35 +18,75 @@ * TDX module and hypercalls to the VMM. * SEAMCALL - used by TDX hosts to make requests to the * TDX module. + * + *------------------------------------------------------------------------- + * TDCALL/SEAMCALL ABI: + *------------------------------------------------------------------------- + * Input Registers: + * + * RAX - TDCALL/SEAMCALL Leaf number. + * RCX,RDX,RDI,RSI,RBX,R8-R15 - TDCALL/SEAMCALL Leaf specific input registers. + * + * Output Registers: + * + * RAX - TDCALL/SEAMCALL instruction error code. + * RCX,RDX,RDI,RSI,RBX,R8-R15 - TDCALL/SEAMCALL Leaf specific output registers. + * + *------------------------------------------------------------------------- + * + * So while the common core (RAX,RCX,RDX,R8-R11) fits nicely in the + * callee-clobbered registers and even leaves RDI,RSI free to act as a + * base pointer, some leafs (e.g., VP.ENTER) make a giant mess of things. + * + * For simplicity, assume that anything that needs the callee-saved regs + * also tramples on RDI,RSI. This isn't strictly true, see for example + * TDH.EXPORT.MEM. */ -.macro TDX_MODULE_CALL host:req - /* - * R12 will be used as temporary storage for struct tdx_module_output - * pointer. Since R12-R15 registers are not used by TDCALL/SEAMCALL - * services supported by this function, it can be reused. - */ +.macro TDX_MODULE_CALL host:req ret=0 saved=0 + FRAME_BEGIN - /* Callee saved, so preserve it */ - push %r12 + /* Move Leaf ID to RAX */ + mov %rdi, %rax + + /* Move other input regs from 'struct tdx_module_args' */ + movq TDX_MODULE_rcx(%rsi), %rcx + movq TDX_MODULE_rdx(%rsi), %rdx + movq TDX_MODULE_r8(%rsi), %r8 + movq TDX_MODULE_r9(%rsi), %r9 + movq TDX_MODULE_r10(%rsi), %r10 + movq TDX_MODULE_r11(%rsi), %r11 +.if \saved /* - * Push output pointer to stack. - * After the operation, it will be fetched into R12 register. + * Move additional input regs from the structure. For simplicity + * assume that anything needs the callee-saved regs also tramples + * on RDI/RSI (see VP.ENTER). */ - push %r9 + /* Save those callee-saved GPRs as mandated by the x86_64 ABI */ + pushq %rbx + pushq %r12 + pushq %r13 + pushq %r14 + pushq %r15 - /* Mangle function call ABI into TDCALL/SEAMCALL ABI: */ - /* Move Leaf ID to RAX */ - mov %rdi, %rax - /* Move input 4 to R9 */ - mov %r8, %r9 - /* Move input 3 to R8 */ - mov %rcx, %r8 - /* Move input 1 to RCX */ - mov %rsi, %rcx - /* Leave input param 2 in RDX */ - - .if \host + movq TDX_MODULE_r12(%rsi), %r12 + movq TDX_MODULE_r13(%rsi), %r13 + movq TDX_MODULE_r14(%rsi), %r14 + movq TDX_MODULE_r15(%rsi), %r15 + movq TDX_MODULE_rbx(%rsi), %rbx + +.if \ret + /* Save the structure pointer as RSI is about to be clobbered */ + pushq %rsi +.endif + + movq TDX_MODULE_rdi(%rsi), %rdi + /* RSI needs to be done at last */ + movq TDX_MODULE_rsi(%rsi), %rsi +.endif /* \saved */ + +.if \host +.Lseamcall\@: seamcall /* * SEAMCALL instruction is essentially a VMExit from VMX root @@ -57,40 +99,122 @@ * This value will never be used as actual SEAMCALL error code as * it is from the Reserved status code class. */ - jnc .Lno_vmfailinvalid - mov $TDX_SEAMCALL_VMFAILINVALID, %rax -.Lno_vmfailinvalid: - - .else + jc .Lseamcall_vmfailinvalid\@ +.else tdcall - .endif +.endif +.if \ret +.if \saved /* - * Fetch output pointer from stack to R12 (It is used - * as temporary storage) + * Restore the structure from stack to save the output registers + * + * In case of VP.ENTER returns due to TDVMCALL, all registers are + * valid thus no register can be used as spare to restore the + * structure from the stack (see "TDH.VP.ENTER Output Operands + * Definition on TDCALL(TDG.VP.VMCALL) Following a TD Entry"). + * For this case, need to make one register as spare by saving it + * to the stack and then manually load the structure pointer to + * the spare register. + * + * Note for other TDCALLs/SEAMCALLs there are spare registers + * thus no need for such hack but just use this for all. */ - pop %r12 + pushq %rax /* save the TDCALL/SEAMCALL return code */ + movq 8(%rsp), %rax /* restore the structure pointer */ + movq %rsi, TDX_MODULE_rsi(%rax) /* save RSI */ + popq %rax /* restore the return code */ + popq %rsi /* pop the structure pointer */ + + /* Copy additional output regs to the structure */ + movq %r12, TDX_MODULE_r12(%rsi) + movq %r13, TDX_MODULE_r13(%rsi) + movq %r14, TDX_MODULE_r14(%rsi) + movq %r15, TDX_MODULE_r15(%rsi) + movq %rbx, TDX_MODULE_rbx(%rsi) + movq %rdi, TDX_MODULE_rdi(%rsi) +.endif /* \saved */ + /* Copy output registers to the structure */ + movq %rcx, TDX_MODULE_rcx(%rsi) + movq %rdx, TDX_MODULE_rdx(%rsi) + movq %r8, TDX_MODULE_r8(%rsi) + movq %r9, TDX_MODULE_r9(%rsi) + movq %r10, TDX_MODULE_r10(%rsi) + movq %r11, TDX_MODULE_r11(%rsi) +.endif /* \ret */ + +.if \saved && \ret /* - * Since this macro can be invoked with NULL as an output pointer, - * check if caller provided an output struct before storing output - * registers. + * Clear registers shared by guest for VP.VMCALL/VP.ENTER to prevent + * speculative use of guest's/VMM's values, including those are + * restored from the stack. + * + * See arch/x86/kvm/vmx/vmenter.S: * - * Update output registers, even if the call failed (RAX != 0). - * Other registers may contain details of the failure. + * In theory, a L1 cache miss when restoring register from stack + * could lead to speculative execution with guest's values. + * + * Note: RBP/RSP are not used as shared register. RSI has been + * restored already. + * + * XOR is cheap, thus unconditionally do for all leafs. */ - test %r12, %r12 - jz .Lno_output_struct - - /* Copy result registers to output struct: */ - movq %rcx, TDX_MODULE_rcx(%r12) - movq %rdx, TDX_MODULE_rdx(%r12) - movq %r8, TDX_MODULE_r8(%r12) - movq %r9, TDX_MODULE_r9(%r12) - movq %r10, TDX_MODULE_r10(%r12) - movq %r11, TDX_MODULE_r11(%r12) - -.Lno_output_struct: - /* Restore the state of R12 register */ - pop %r12 + xorl %ecx, %ecx + xorl %edx, %edx + xorl %r8d, %r8d + xorl %r9d, %r9d + xorl %r10d, %r10d + xorl %r11d, %r11d + xorl %r12d, %r12d + xorl %r13d, %r13d + xorl %r14d, %r14d + xorl %r15d, %r15d + xorl %ebx, %ebx + xorl %edi, %edi +.endif /* \ret && \host */ + +.if \host +.Lout\@: +.endif + +.if \saved + /* Restore callee-saved GPRs as mandated by the x86_64 ABI */ + popq %r15 + popq %r14 + popq %r13 + popq %r12 + popq %rbx +.endif /* \saved */ + + FRAME_END + RET + +.if \host +.Lseamcall_vmfailinvalid\@: + mov $TDX_SEAMCALL_VMFAILINVALID, %rax + jmp .Lseamcall_fail\@ + +.Lseamcall_trap\@: + /* + * SEAMCALL caused #GP or #UD. By reaching here RAX contains + * the trap number. Convert the trap number to the TDX error + * code by setting TDX_SW_ERROR to the high 32-bits of RAX. + * + * Note cannot OR TDX_SW_ERROR directly to RAX as OR instruction + * only accepts 32-bit immediate at most. + */ + movq $TDX_SW_ERROR, %rdi + orq %rdi, %rax + +.Lseamcall_fail\@: +.if \ret && \saved + /* pop the unused structure pointer back to RSI */ + popq %rsi +.endif + jmp .Lout\@ + + _ASM_EXTABLE_FAULT(.Lseamcall\@, .Lseamcall_trap\@) +.endif /* \host */ + .endm diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c index 7ad91225fdf4..9dd5490b3318 100644 --- a/arch/x86/xen/apic.c +++ b/arch/x86/xen/apic.c @@ -33,13 +33,13 @@ static unsigned int xen_io_apic_read(unsigned apic, unsigned reg) return 0xfd; } -static u32 xen_set_apic_id(unsigned int x) +static u32 xen_set_apic_id(u32 x) { WARN_ON(1); return x; } -static unsigned int xen_get_apic_id(unsigned long x) +static u32 xen_get_apic_id(u32 x) { return ((x)>>24) & 0xFFu; } @@ -110,15 +110,15 @@ static int xen_madt_oem_check(char *oem_id, char *oem_table_id) return xen_pv_domain(); } -static int xen_phys_pkg_id(int initial_apic_id, int index_msb) +static u32 xen_phys_pkg_id(u32 initial_apic_id, int index_msb) { return initial_apic_id >> index_msb; } -static int xen_cpu_present_to_apicid(int cpu) +static u32 xen_cpu_present_to_apicid(int cpu) { if (cpu_present(cpu)) - return cpu_data(cpu).apicid; + return cpu_data(cpu).topo.apicid; else return BAD_APICID; } |