From 48157aa39286b8eddfb81eeaab4d64d0231450e7 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:47 +0100 Subject: arm64: kernel: Manage absolute relocations in code built under pi/ The mini C runtime runs before relocations are processed, and so it cannot rely on statically initialized pointer variables. Add a check to ensure that such code does not get introduced by accident, by going over the relocations in each object, identifying the ones that operate on data sections that are part of the executable image, and raising an error if any relocations of type R_AARCH64_ABS64 exist. Note that such relocations are permitted in other places (e.g., debug sections) and will never occur in compiler generated code sections when using the small code model, so only check sections that have SHF_ALLOC set and SHF_EXECINSTR cleared. To accommodate cases where statically initialized symbol references are unavoidable, introduce a special case for ELF input data sections that have ".rodata.prel64" in their names, and in these cases, instead of rejecting any encountered ABS64 relocations, convert them into PREL64 relocations, which don't require any runtime fixups. Note that the code in question must still be modified to deal with this, as it needs to convert the 64-bit signed offsets into absolute addresses before use. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-46-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/pi/Makefile | 9 ++- arch/arm64/kernel/pi/pi.h | 18 ++++++ arch/arm64/kernel/pi/relacheck.c | 130 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 155 insertions(+), 2 deletions(-) create mode 100644 arch/arm64/kernel/pi/pi.h create mode 100644 arch/arm64/kernel/pi/relacheck.c (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile index c844a0546d7f..bc32a431fe35 100644 --- a/arch/arm64/kernel/pi/Makefile +++ b/arch/arm64/kernel/pi/Makefile @@ -22,11 +22,16 @@ KCSAN_SANITIZE := n UBSAN_SANITIZE := n KCOV_INSTRUMENT := n +hostprogs := relacheck + +quiet_cmd_piobjcopy = $(quiet_cmd_objcopy) + cmd_piobjcopy = $(cmd_objcopy) && $(obj)/relacheck $(@) $(<) + $(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \ --remove-section=.note.gnu.property \ --prefix-alloc-sections=.init -$(obj)/%.pi.o: $(obj)/%.o FORCE - $(call if_changed,objcopy) +$(obj)/%.pi.o: $(obj)/%.o $(obj)/relacheck FORCE + $(call if_changed,piobjcopy) $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE $(call if_changed_rule,cc_o_c) diff --git a/arch/arm64/kernel/pi/pi.h b/arch/arm64/kernel/pi/pi.h new file mode 100644 index 000000000000..7c2d9bbf0ff9 --- /dev/null +++ b/arch/arm64/kernel/pi/pi.h @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2023 Google LLC +// Author: Ard Biesheuvel + +#define __prel64_initconst __section(".init.rodata.prel64") + +#define PREL64(type, name) union { type *name; prel64_t name ## _prel; } + +#define prel64_pointer(__d) (typeof(__d))prel64_to_pointer(&__d##_prel) + +typedef volatile signed long prel64_t; + +static inline void *prel64_to_pointer(const prel64_t *offset) +{ + if (!*offset) + return NULL; + return (void *)offset + *offset; +} diff --git a/arch/arm64/kernel/pi/relacheck.c b/arch/arm64/kernel/pi/relacheck.c new file mode 100644 index 000000000000..b0cd4d0d275b --- /dev/null +++ b/arch/arm64/kernel/pi/relacheck.c @@ -0,0 +1,130 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2023 - Google LLC + * Author: Ard Biesheuvel + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__ +#define HOST_ORDER ELFDATA2LSB +#elif __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ +#define HOST_ORDER ELFDATA2MSB +#endif + +static Elf64_Ehdr *ehdr; +static Elf64_Shdr *shdr; +static const char *strtab; +static bool swap; + +static uint64_t swab_elfxword(uint64_t val) +{ + return swap ? __builtin_bswap64(val) : val; +} + +static uint32_t swab_elfword(uint32_t val) +{ + return swap ? __builtin_bswap32(val) : val; +} + +static uint16_t swab_elfhword(uint16_t val) +{ + return swap ? __builtin_bswap16(val) : val; +} + +int main(int argc, char *argv[]) +{ + struct stat stat; + int fd, ret; + + if (argc < 3) { + fprintf(stderr, "file arguments missing\n"); + exit(EXIT_FAILURE); + } + + fd = open(argv[1], O_RDWR); + if (fd < 0) { + fprintf(stderr, "failed to open %s\n", argv[1]); + exit(EXIT_FAILURE); + } + + ret = fstat(fd, &stat); + if (ret < 0) { + fprintf(stderr, "failed to stat() %s\n", argv[1]); + exit(EXIT_FAILURE); + } + + ehdr = mmap(0, stat.st_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (ehdr == MAP_FAILED) { + fprintf(stderr, "failed to mmap() %s\n", argv[1]); + exit(EXIT_FAILURE); + } + + swap = ehdr->e_ident[EI_DATA] != HOST_ORDER; + shdr = (void *)ehdr + swab_elfxword(ehdr->e_shoff); + strtab = (void *)ehdr + + swab_elfxword(shdr[swab_elfhword(ehdr->e_shstrndx)].sh_offset); + + for (int i = 0; i < swab_elfhword(ehdr->e_shnum); i++) { + unsigned long info, flags; + bool prel64 = false; + Elf64_Rela *rela; + int numrela; + + if (swab_elfword(shdr[i].sh_type) != SHT_RELA) + continue; + + /* only consider RELA sections operating on data */ + info = swab_elfword(shdr[i].sh_info); + flags = swab_elfxword(shdr[info].sh_flags); + if ((flags & (SHF_ALLOC | SHF_EXECINSTR)) != SHF_ALLOC) + continue; + + /* + * We generally don't permit ABS64 relocations in the code that + * runs before relocation processing occurs. If statically + * initialized absolute symbol references are unavoidable, they + * may be emitted into a *.rodata.prel64 section and they will + * be converted to place-relative 64-bit references. This + * requires special handling in the referring code. + */ + if (strstr(strtab + swab_elfword(shdr[info].sh_name), + ".rodata.prel64")) { + prel64 = true; + } + + rela = (void *)ehdr + swab_elfxword(shdr[i].sh_offset); + numrela = swab_elfxword(shdr[i].sh_size) / sizeof(*rela); + + for (int j = 0; j < numrela; j++) { + uint64_t info = swab_elfxword(rela[j].r_info); + + if (ELF64_R_TYPE(info) != R_AARCH64_ABS64) + continue; + + if (prel64) { + /* convert ABS64 into PREL64 */ + info ^= R_AARCH64_ABS64 ^ R_AARCH64_PREL64; + rela[j].r_info = swab_elfxword(info); + } else { + fprintf(stderr, + "Unexpected absolute relocations detected in %s\n", + argv[2]); + close(fd); + unlink(argv[1]); + exit(EXIT_FAILURE); + } + } + } + close(fd); + return 0; +} -- cgit v1.2.3 From a86aa72eb3b075b985473d1d2973c7d00f568f17 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:48 +0100 Subject: arm64: kernel: Don't rely on objcopy to make code under pi/ __init We will add some code under pi/ that contains global variables that should not end up in __initdata, as they will not be writable via the initial ID map. So only rely on objcopy for making the libfdt code __init, and use explicit annotations for the rest. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-47-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/pi/Makefile | 6 ++++-- arch/arm64/kernel/pi/kaslr_early.c | 16 +++++++++------- 2 files changed, 13 insertions(+), 9 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile index bc32a431fe35..2bbe866417d4 100644 --- a/arch/arm64/kernel/pi/Makefile +++ b/arch/arm64/kernel/pi/Makefile @@ -28,11 +28,13 @@ quiet_cmd_piobjcopy = $(quiet_cmd_objcopy) cmd_piobjcopy = $(cmd_objcopy) && $(obj)/relacheck $(@) $(<) $(obj)/%.pi.o: OBJCOPYFLAGS := --prefix-symbols=__pi_ \ - --remove-section=.note.gnu.property \ - --prefix-alloc-sections=.init + --remove-section=.note.gnu.property $(obj)/%.pi.o: $(obj)/%.o $(obj)/relacheck FORCE $(call if_changed,piobjcopy) +# ensure that all the lib- code ends up as __init code and data +$(obj)/lib-%.pi.o: OBJCOPYFLAGS += --prefix-alloc-sections=.init + $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE $(call if_changed_rule,cc_o_c) diff --git a/arch/arm64/kernel/pi/kaslr_early.c b/arch/arm64/kernel/pi/kaslr_early.c index b9e0bb4bc6a9..167081b30a15 100644 --- a/arch/arm64/kernel/pi/kaslr_early.c +++ b/arch/arm64/kernel/pi/kaslr_early.c @@ -17,7 +17,7 @@ #include /* taken from lib/string.c */ -static char *__strstr(const char *s1, const char *s2) +static char *__init __strstr(const char *s1, const char *s2) { size_t l1, l2; @@ -33,7 +33,7 @@ static char *__strstr(const char *s1, const char *s2) } return NULL; } -static bool cmdline_contains_nokaslr(const u8 *cmdline) +static bool __init cmdline_contains_nokaslr(const u8 *cmdline) { const u8 *str; @@ -41,7 +41,7 @@ static bool cmdline_contains_nokaslr(const u8 *cmdline) return str == cmdline || (str > cmdline && *(str - 1) == ' '); } -static bool is_kaslr_disabled_cmdline(void *fdt) +static bool __init is_kaslr_disabled_cmdline(void *fdt) { if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) { int node; @@ -67,17 +67,19 @@ out: return cmdline_contains_nokaslr(CONFIG_CMDLINE); } -static u64 get_kaslr_seed(void *fdt) +static u64 __init get_kaslr_seed(void *fdt) { + static char const chosen_str[] __initconst = "chosen"; + static char const seed_str[] __initconst = "kaslr-seed"; int node, len; fdt64_t *prop; u64 ret; - node = fdt_path_offset(fdt, "/chosen"); + node = fdt_path_offset(fdt, chosen_str); if (node < 0) return 0; - prop = fdt_getprop_w(fdt, node, "kaslr-seed", &len); + prop = fdt_getprop_w(fdt, node, seed_str, &len); if (!prop || len != sizeof(u64)) return 0; @@ -86,7 +88,7 @@ static u64 get_kaslr_seed(void *fdt) return ret; } -asmlinkage u64 kaslr_early_init(void *fdt) +asmlinkage u64 __init kaslr_early_init(void *fdt) { u64 seed, range; -- cgit v1.2.3 From 734958ef0b5497b1b9cb827afb541e7825477bbd Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:49 +0100 Subject: arm64: head: move relocation handling to C code Now that we have a mini C runtime before the kernel mapping is up, we can move the non-trivial relocation processing code out of head.S and reimplement it in C. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-48-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/Makefile | 3 +- arch/arm64/kernel/head.S | 104 +++------------------------------------- arch/arm64/kernel/pi/Makefile | 5 +- arch/arm64/kernel/pi/relocate.c | 62 ++++++++++++++++++++++++ arch/arm64/kernel/vmlinux.lds.S | 12 +++-- 5 files changed, 82 insertions(+), 104 deletions(-) create mode 100644 arch/arm64/kernel/pi/relocate.c (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 467cb7117273..78f14084f6d7 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -57,7 +57,8 @@ obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o obj-$(CONFIG_PARAVIRT) += paravirt.o -obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o pi/ +obj-$(CONFIG_RELOCATABLE) += pi/ +obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o obj-$(CONFIG_ELF_CORE) += elfcore.o obj-$(CONFIG_KEXEC_CORE) += machine_kexec.o relocate_kernel.o \ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index cab7f91949d8..a8fa64fc30d7 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -81,7 +81,7 @@ * x20 primary_entry() .. __primary_switch() CPU boot mode * x21 primary_entry() .. start_kernel() FDT pointer passed at boot in x0 * x22 create_idmap() .. start_kernel() ID map VA of the DT blob - * x23 primary_entry() .. start_kernel() physical misalignment/KASLR offset + * x23 __primary_switch() physical misalignment/KASLR offset * x24 __primary_switch() linear map KASLR seed * x25 primary_entry() .. start_kernel() supported VA size * x28 create_idmap() callee preserved temp register @@ -389,7 +389,7 @@ SYM_FUNC_START_LOCAL(create_idmap) /* Remap the kernel page tables r/w in the ID map */ adrp x1, _text adrp x2, init_pg_dir - adrp x3, init_pg_end + adrp x3, _end bic x4, x2, #SWAPPER_BLOCK_SIZE - 1 mov_q x5, SWAPPER_RW_MMUFLAGS mov x6, #SWAPPER_BLOCK_SHIFT @@ -779,97 +779,6 @@ SYM_FUNC_START_LOCAL(__no_granule_support) b 1b SYM_FUNC_END(__no_granule_support) -#ifdef CONFIG_RELOCATABLE -SYM_FUNC_START_LOCAL(__relocate_kernel) - /* - * Iterate over each entry in the relocation table, and apply the - * relocations in place. - */ - adr_l x9, __rela_start - adr_l x10, __rela_end - mov_q x11, KIMAGE_VADDR // default virtual offset - add x11, x11, x23 // actual virtual offset - -0: cmp x9, x10 - b.hs 1f - ldp x12, x13, [x9], #24 - ldr x14, [x9, #-8] - cmp w13, #R_AARCH64_RELATIVE - b.ne 0b - add x14, x14, x23 // relocate - str x14, [x12, x23] - b 0b - -1: -#ifdef CONFIG_RELR - /* - * Apply RELR relocations. - * - * RELR is a compressed format for storing relative relocations. The - * encoded sequence of entries looks like: - * [ AAAAAAAA BBBBBBB1 BBBBBBB1 ... AAAAAAAA BBBBBB1 ... ] - * - * i.e. start with an address, followed by any number of bitmaps. The - * address entry encodes 1 relocation. The subsequent bitmap entries - * encode up to 63 relocations each, at subsequent offsets following - * the last address entry. - * - * The bitmap entries must have 1 in the least significant bit. The - * assumption here is that an address cannot have 1 in lsb. Odd - * addresses are not supported. Any odd addresses are stored in the RELA - * section, which is handled above. - * - * Excluding the least significant bit in the bitmap, each non-zero - * bit in the bitmap represents a relocation to be applied to - * a corresponding machine word that follows the base address - * word. The second least significant bit represents the machine - * word immediately following the initial address, and each bit - * that follows represents the next word, in linear order. As such, - * a single bitmap can encode up to 63 relocations in a 64-bit object. - * - * In this implementation we store the address of the next RELR table - * entry in x9, the address being relocated by the current address or - * bitmap entry in x13 and the address being relocated by the current - * bit in x14. - */ - adr_l x9, __relr_start - adr_l x10, __relr_end - -2: cmp x9, x10 - b.hs 7f - ldr x11, [x9], #8 - tbnz x11, #0, 3f // branch to handle bitmaps - add x13, x11, x23 - ldr x12, [x13] // relocate address entry - add x12, x12, x23 - str x12, [x13], #8 // adjust to start of bitmap - b 2b - -3: mov x14, x13 -4: lsr x11, x11, #1 - cbz x11, 6f - tbz x11, #0, 5f // skip bit if not set - ldr x12, [x14] // relocate bit - add x12, x12, x23 - str x12, [x14] - -5: add x14, x14, #8 // move to next bit's address - b 4b - -6: /* - * Move to the next bitmap's address. 8 is the word size, and 63 is the - * number of significant bits in a bitmap entry. - */ - add x13, x13, #(8 * 63) - b 2b - -7: -#endif - ret - -SYM_FUNC_END(__relocate_kernel) -#endif - SYM_FUNC_START_LOCAL(__primary_switch) adrp x1, reserved_pg_dir adrp x2, init_idmap_pg_dir @@ -877,11 +786,11 @@ SYM_FUNC_START_LOCAL(__primary_switch) #ifdef CONFIG_RELOCATABLE adrp x23, KERNEL_START and x23, x23, MIN_KIMG_ALIGN - 1 -#ifdef CONFIG_RANDOMIZE_BASE - mov x0, x22 - adrp x1, init_pg_end + adrp x1, early_init_stack mov sp, x1 mov x29, xzr +#ifdef CONFIG_RANDOMIZE_BASE + mov x0, x22 bl __pi_kaslr_early_init and x24, x0, #SZ_2M - 1 // capture memstart offset seed bic x0, x0, #SZ_2M - 1 @@ -894,7 +803,8 @@ SYM_FUNC_START_LOCAL(__primary_switch) adrp x1, init_pg_dir load_ttbr1 x1, x1, x2 #ifdef CONFIG_RELOCATABLE - bl __relocate_kernel + mov x0, x23 + bl __pi_relocate_kernel #endif ldr x8, =__primary_switched adrp x0, KERNEL_START // __pa(KERNEL_START) diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile index 2bbe866417d4..d084c1dcf416 100644 --- a/arch/arm64/kernel/pi/Makefile +++ b/arch/arm64/kernel/pi/Makefile @@ -38,5 +38,6 @@ $(obj)/lib-%.pi.o: OBJCOPYFLAGS += --prefix-alloc-sections=.init $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE $(call if_changed_rule,cc_o_c) -obj-y := kaslr_early.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o -extra-y := $(patsubst %.pi.o,%.o,$(obj-y)) +obj-y := relocate.pi.o +obj-$(CONFIG_RANDOMIZE_BASE) += kaslr_early.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o +extra-y := $(patsubst %.pi.o,%.o,$(obj-y)) diff --git a/arch/arm64/kernel/pi/relocate.c b/arch/arm64/kernel/pi/relocate.c new file mode 100644 index 000000000000..1853408ea76b --- /dev/null +++ b/arch/arm64/kernel/pi/relocate.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2023 Google LLC +// Authors: Ard Biesheuvel +// Peter Collingbourne + +#include +#include +#include + +extern const Elf64_Rela rela_start[], rela_end[]; +extern const u64 relr_start[], relr_end[]; + +void __init relocate_kernel(u64 offset) +{ + u64 *place = NULL; + + for (const Elf64_Rela *rela = rela_start; rela < rela_end; rela++) { + if (ELF64_R_TYPE(rela->r_info) != R_AARCH64_RELATIVE) + continue; + *(u64 *)(rela->r_offset + offset) = rela->r_addend + offset; + } + + if (!IS_ENABLED(CONFIG_RELR) || !offset) + return; + + /* + * Apply RELR relocations. + * + * RELR is a compressed format for storing relative relocations. The + * encoded sequence of entries looks like: + * [ AAAAAAAA BBBBBBB1 BBBBBBB1 ... AAAAAAAA BBBBBB1 ... ] + * + * i.e. start with an address, followed by any number of bitmaps. The + * address entry encodes 1 relocation. The subsequent bitmap entries + * encode up to 63 relocations each, at subsequent offsets following + * the last address entry. + * + * The bitmap entries must have 1 in the least significant bit. The + * assumption here is that an address cannot have 1 in lsb. Odd + * addresses are not supported. Any odd addresses are stored in the + * RELA section, which is handled above. + * + * With the exception of the least significant bit, each bit in the + * bitmap corresponds with a machine word that follows the base address + * word, and the bit value indicates whether or not a relocation needs + * to be applied to it. The second least significant bit represents the + * machine word immediately following the initial address, and each bit + * that follows represents the next word, in linear order. As such, a + * single bitmap can encode up to 63 relocations in a 64-bit object. + */ + for (const u64 *relr = relr_start; relr < relr_end; relr++) { + if ((*relr & 1) == 0) { + place = (u64 *)(*relr + offset); + *place++ += offset; + } else { + for (u64 *p = place, r = *relr >> 1; r; p++, r >>= 1) + if (r & 1) + *p += offset; + place += 63; + } + } +} diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 3cd7e76cc562..8dd5dda66f7c 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -270,15 +270,15 @@ SECTIONS HYPERVISOR_RELOC_SECTION .rela.dyn : ALIGN(8) { - __rela_start = .; + __pi_rela_start = .; *(.rela .rela*) - __rela_end = .; + __pi_rela_end = .; } .relr.dyn : ALIGN(8) { - __relr_start = .; + __pi_relr_start = .; *(.relr.dyn) - __relr_end = .; + __pi_relr_end = .; } . = ALIGN(SEGMENT_ALIGN); @@ -317,6 +317,10 @@ SECTIONS init_pg_dir = .; . += INIT_DIR_SIZE; init_pg_end = .; +#ifdef CONFIG_RELOCATABLE + . += SZ_4K; /* stack for the early relocation code */ + early_init_stack = .; +#endif . = ALIGN(SEGMENT_ALIGN); __pecoff_data_size = ABSOLUTE(. - __initdata_begin); -- cgit v1.2.3 From e223a449125571daa62debd8249fa4fc2da0a961 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:50 +0100 Subject: arm64: idreg-override: Move to early mini C runtime We will want to parse the ID register overrides even earlier, so that we can take them into account before creating the kernel mapping. So migrate the code and make it work in the context of the early C runtime. We will move the invocation to an earlier stage in a subsequent patch. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-49-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/Makefile | 4 +- arch/arm64/kernel/head.S | 5 +- arch/arm64/kernel/idreg-override.c | 375 ---------------------------------- arch/arm64/kernel/image-vars.h | 9 + arch/arm64/kernel/pi/Makefile | 5 +- arch/arm64/kernel/pi/idreg-override.c | 370 +++++++++++++++++++++++++++++++++ 6 files changed, 385 insertions(+), 383 deletions(-) delete mode 100644 arch/arm64/kernel/idreg-override.c create mode 100644 arch/arm64/kernel/pi/idreg-override.c (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 78f14084f6d7..4236f1e0fffa 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -33,8 +33,7 @@ obj-y := debug-monitors.o entry.o irq.o fpsimd.o \ return_address.o cpuinfo.o cpu_errata.o \ cpufeature.o alternative.o cacheinfo.o \ smp.o smp_spin_table.o topology.o smccc-call.o \ - syscall.o proton-pack.o idreg-override.o idle.o \ - patching.o + syscall.o proton-pack.o idle.o patching.o pi/ obj-$(CONFIG_COMPAT) += sys32.o signal32.o \ sys_compat.o @@ -57,7 +56,6 @@ obj-$(CONFIG_ACPI) += acpi.o obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o obj-$(CONFIG_PARAVIRT) += paravirt.o -obj-$(CONFIG_RELOCATABLE) += pi/ obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o obj-$(CONFIG_ELF_CORE) += elfcore.o diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index a8fa64fc30d7..ca5e5fbefcd3 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -510,10 +510,9 @@ SYM_FUNC_START_LOCAL(__primary_switched) #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) bl kasan_early_init #endif - mov x0, x21 // pass FDT address in x0 - bl early_fdt_map // Try mapping the FDT early mov x0, x20 // pass the full boot status - bl init_feature_override // Parse cpu feature overrides + mov x1, x22 // pass the low FDT mapping + bl __pi_init_feature_override // Parse cpu feature overrides #ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS bl scs_patch_vmlinux #endif diff --git a/arch/arm64/kernel/idreg-override.c b/arch/arm64/kernel/idreg-override.c deleted file mode 100644 index e30fd9e32ef3..000000000000 --- a/arch/arm64/kernel/idreg-override.c +++ /dev/null @@ -1,375 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Early cpufeature override framework - * - * Copyright (C) 2020 Google LLC - * Author: Marc Zyngier - */ - -#include -#include -#include - -#include -#include -#include - -#define FTR_DESC_NAME_LEN 20 -#define FTR_DESC_FIELD_LEN 10 -#define FTR_ALIAS_NAME_LEN 30 -#define FTR_ALIAS_OPTION_LEN 116 - -static u64 __boot_status __initdata; - -// temporary __prel64 related definitions -// to be removed when this code is moved under pi/ - -#define __prel64_initconst __initconst - -#define PREL64(type, name) union { type *name; } - -#define prel64_pointer(__d) (__d) - -typedef bool filter_t(u64 val); - -struct ftr_set_desc { - char name[FTR_DESC_NAME_LEN]; - PREL64(struct arm64_ftr_override, override); - struct { - char name[FTR_DESC_FIELD_LEN]; - u8 shift; - u8 width; - PREL64(filter_t, filter); - } fields[]; -}; - -#define FIELD(n, s, f) { .name = n, .shift = s, .width = 4, .filter = f } - -static bool __init mmfr1_vh_filter(u64 val) -{ - /* - * If we ever reach this point while running VHE, we're - * guaranteed to be on one of these funky, VHE-stuck CPUs. If - * the user was trying to force nVHE on us, proceed with - * attitude adjustment. - */ - return !(__boot_status == (BOOT_CPU_FLAG_E2H | BOOT_CPU_MODE_EL2) && - val == 0); -} - -static const struct ftr_set_desc mmfr1 __prel64_initconst = { - .name = "id_aa64mmfr1", - .override = &id_aa64mmfr1_override, - .fields = { - FIELD("vh", ID_AA64MMFR1_EL1_VH_SHIFT, mmfr1_vh_filter), - {} - }, -}; - -static bool __init pfr0_sve_filter(u64 val) -{ - /* - * Disabling SVE also means disabling all the features that - * are associated with it. The easiest way to do it is just to - * override id_aa64zfr0_el1 to be 0. - */ - if (!val) { - id_aa64zfr0_override.val = 0; - id_aa64zfr0_override.mask = GENMASK(63, 0); - } - - return true; -} - -static const struct ftr_set_desc pfr0 __prel64_initconst = { - .name = "id_aa64pfr0", - .override = &id_aa64pfr0_override, - .fields = { - FIELD("sve", ID_AA64PFR0_EL1_SVE_SHIFT, pfr0_sve_filter), - {} - }, -}; - -static bool __init pfr1_sme_filter(u64 val) -{ - /* - * Similarly to SVE, disabling SME also means disabling all - * the features that are associated with it. Just set - * id_aa64smfr0_el1 to 0 and don't look back. - */ - if (!val) { - id_aa64smfr0_override.val = 0; - id_aa64smfr0_override.mask = GENMASK(63, 0); - } - - return true; -} - -static const struct ftr_set_desc pfr1 __prel64_initconst = { - .name = "id_aa64pfr1", - .override = &id_aa64pfr1_override, - .fields = { - FIELD("bt", ID_AA64PFR1_EL1_BT_SHIFT, NULL ), - FIELD("mte", ID_AA64PFR1_EL1_MTE_SHIFT, NULL), - FIELD("sme", ID_AA64PFR1_EL1_SME_SHIFT, pfr1_sme_filter), - {} - }, -}; - -static const struct ftr_set_desc isar1 __prel64_initconst = { - .name = "id_aa64isar1", - .override = &id_aa64isar1_override, - .fields = { - FIELD("gpi", ID_AA64ISAR1_EL1_GPI_SHIFT, NULL), - FIELD("gpa", ID_AA64ISAR1_EL1_GPA_SHIFT, NULL), - FIELD("api", ID_AA64ISAR1_EL1_API_SHIFT, NULL), - FIELD("apa", ID_AA64ISAR1_EL1_APA_SHIFT, NULL), - {} - }, -}; - -static const struct ftr_set_desc isar2 __prel64_initconst = { - .name = "id_aa64isar2", - .override = &id_aa64isar2_override, - .fields = { - FIELD("gpa3", ID_AA64ISAR2_EL1_GPA3_SHIFT, NULL), - FIELD("apa3", ID_AA64ISAR2_EL1_APA3_SHIFT, NULL), - FIELD("mops", ID_AA64ISAR2_EL1_MOPS_SHIFT, NULL), - {} - }, -}; - -static const struct ftr_set_desc smfr0 __prel64_initconst = { - .name = "id_aa64smfr0", - .override = &id_aa64smfr0_override, - .fields = { - FIELD("smever", ID_AA64SMFR0_EL1_SMEver_SHIFT, NULL), - /* FA64 is a one bit field... :-/ */ - { "fa64", ID_AA64SMFR0_EL1_FA64_SHIFT, 1, }, - {} - }, -}; - -static bool __init hvhe_filter(u64 val) -{ - u64 mmfr1 = read_sysreg(id_aa64mmfr1_el1); - - return (val == 1 && - lower_32_bits(__boot_status) == BOOT_CPU_MODE_EL2 && - cpuid_feature_extract_unsigned_field(mmfr1, - ID_AA64MMFR1_EL1_VH_SHIFT)); -} - -static const struct ftr_set_desc sw_features __prel64_initconst = { - .name = "arm64_sw", - .override = &arm64_sw_feature_override, - .fields = { - FIELD("nokaslr", ARM64_SW_FEATURE_OVERRIDE_NOKASLR, NULL), - FIELD("hvhe", ARM64_SW_FEATURE_OVERRIDE_HVHE, hvhe_filter), - {} - }, -}; - -static const -PREL64(const struct ftr_set_desc, reg) regs[] __prel64_initconst = { - { &mmfr1 }, - { &pfr0 }, - { &pfr1 }, - { &isar1 }, - { &isar2 }, - { &smfr0 }, - { &sw_features }, -}; - -static const struct { - char alias[FTR_ALIAS_NAME_LEN]; - char feature[FTR_ALIAS_OPTION_LEN]; -} aliases[] __initconst = { - { "kvm_arm.mode=nvhe", "id_aa64mmfr1.vh=0" }, - { "kvm_arm.mode=protected", "id_aa64mmfr1.vh=0" }, - { "arm64.nosve", "id_aa64pfr0.sve=0" }, - { "arm64.nosme", "id_aa64pfr1.sme=0" }, - { "arm64.nobti", "id_aa64pfr1.bt=0" }, - { "arm64.nopauth", - "id_aa64isar1.gpi=0 id_aa64isar1.gpa=0 " - "id_aa64isar1.api=0 id_aa64isar1.apa=0 " - "id_aa64isar2.gpa3=0 id_aa64isar2.apa3=0" }, - { "arm64.nomops", "id_aa64isar2.mops=0" }, - { "arm64.nomte", "id_aa64pfr1.mte=0" }, - { "nokaslr", "arm64_sw.nokaslr=1" }, -}; - -static int __init parse_hexdigit(const char *p, u64 *v) -{ - // skip "0x" if it comes next - if (p[0] == '0' && tolower(p[1]) == 'x') - p += 2; - - // check whether the RHS is a single hex digit - if (!isxdigit(p[0]) || (p[1] && !isspace(p[1]))) - return -EINVAL; - - *v = tolower(*p) - (isdigit(*p) ? '0' : 'a' - 10); - return 0; -} - -static int __init find_field(const char *cmdline, char *opt, int len, - const struct ftr_set_desc *reg, int f, u64 *v) -{ - int flen = strlen(reg->fields[f].name); - - // append '=' to obtain '.=' - memcpy(opt + len, reg->fields[f].name, flen); - len += flen; - opt[len++] = '='; - - if (memcmp(cmdline, opt, len)) - return -1; - - return parse_hexdigit(cmdline + len, v); -} - -static void __init match_options(const char *cmdline) -{ - char opt[FTR_DESC_NAME_LEN + FTR_DESC_FIELD_LEN + 2]; - int i; - - for (i = 0; i < ARRAY_SIZE(regs); i++) { - const struct ftr_set_desc *reg = prel64_pointer(regs[i].reg); - struct arm64_ftr_override *override; - int len = strlen(reg->name); - int f; - - override = prel64_pointer(reg->override); - - // set opt[] to '.' - memcpy(opt, reg->name, len); - opt[len++] = '.'; - - for (f = 0; reg->fields[f].name[0] != '\0'; f++) { - u64 shift = reg->fields[f].shift; - u64 width = reg->fields[f].width ?: 4; - u64 mask = GENMASK_ULL(shift + width - 1, shift); - bool (*filter)(u64 val); - u64 v; - - if (find_field(cmdline, opt, len, reg, f, &v)) - continue; - - /* - * If an override gets filtered out, advertise - * it by setting the value to the all-ones while - * clearing the mask... Yes, this is fragile. - */ - filter = prel64_pointer(reg->fields[f].filter); - if (filter && !filter(v)) { - override->val |= mask; - override->mask &= ~mask; - continue; - } - - override->val &= ~mask; - override->val |= (v << shift) & mask; - override->mask |= mask; - - return; - } - } -} - -static __init void __parse_cmdline(const char *cmdline, bool parse_aliases) -{ - do { - char buf[256]; - size_t len; - int i; - - cmdline = skip_spaces(cmdline); - - /* terminate on "--" appearing on the command line by itself */ - if (cmdline[0] == '-' && cmdline[1] == '-' && isspace(cmdline[2])) - return; - - for (len = 0; cmdline[len] && !isspace(cmdline[len]); len++) { - if (len >= sizeof(buf) - 1) - break; - if (cmdline[len] == '-') - buf[len] = '_'; - else - buf[len] = cmdline[len]; - } - if (!len) - return; - - buf[len] = 0; - - cmdline += len; - - match_options(buf); - - for (i = 0; parse_aliases && i < ARRAY_SIZE(aliases); i++) - if (!memcmp(buf, aliases[i].alias, len + 1)) - __parse_cmdline(aliases[i].feature, false); - } while (1); -} - -static __init const u8 *get_bootargs_cmdline(void) -{ - const u8 *prop; - void *fdt; - int node; - - fdt = get_early_fdt_ptr(); - if (!fdt) - return NULL; - - node = fdt_path_offset(fdt, "/chosen"); - if (node < 0) - return NULL; - - prop = fdt_getprop(fdt, node, "bootargs", NULL); - if (!prop) - return NULL; - - return strlen(prop) ? prop : NULL; -} - -static __init void parse_cmdline(void) -{ - const u8 *prop = get_bootargs_cmdline(); - - if (IS_ENABLED(CONFIG_CMDLINE_FORCE) || !prop) - __parse_cmdline(CONFIG_CMDLINE, true); - - if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && prop) - __parse_cmdline(prop, true); -} - -/* Keep checkers quiet */ -void init_feature_override(u64 boot_status); - -asmlinkage void __init init_feature_override(u64 boot_status) -{ - struct arm64_ftr_override *override; - const struct ftr_set_desc *reg; - int i; - - for (i = 0; i < ARRAY_SIZE(regs); i++) { - reg = prel64_pointer(regs[i].reg); - override = prel64_pointer(reg->override); - - override->val = 0; - override->mask = 0; - } - - __boot_status = boot_status; - - parse_cmdline(); - - for (i = 0; i < ARRAY_SIZE(regs); i++) { - reg = prel64_pointer(regs[i].reg); - override = prel64_pointer(reg->override); - dcache_clean_inval_poc((unsigned long)override, - (unsigned long)(override + 1)); - } -} diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index e931ce078a00..eacc3d167733 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -37,6 +37,15 @@ PROVIDE(__pi___memmove = __pi_memmove); PROVIDE(__pi___memset = __pi_memset); PROVIDE(__pi_vabits_actual = vabits_actual); +PROVIDE(__pi_id_aa64isar1_override = id_aa64isar1_override); +PROVIDE(__pi_id_aa64isar2_override = id_aa64isar2_override); +PROVIDE(__pi_id_aa64mmfr1_override = id_aa64mmfr1_override); +PROVIDE(__pi_id_aa64pfr0_override = id_aa64pfr0_override); +PROVIDE(__pi_id_aa64pfr1_override = id_aa64pfr1_override); +PROVIDE(__pi_id_aa64smfr0_override = id_aa64smfr0_override); +PROVIDE(__pi_id_aa64zfr0_override = id_aa64zfr0_override); +PROVIDE(__pi_arm64_sw_feature_override = arm64_sw_feature_override); +PROVIDE(__pi__ctype = _ctype); #ifdef CONFIG_KVM diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile index d084c1dcf416..7f6dfce893c3 100644 --- a/arch/arm64/kernel/pi/Makefile +++ b/arch/arm64/kernel/pi/Makefile @@ -38,6 +38,7 @@ $(obj)/lib-%.pi.o: OBJCOPYFLAGS += --prefix-alloc-sections=.init $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE $(call if_changed_rule,cc_o_c) -obj-y := relocate.pi.o -obj-$(CONFIG_RANDOMIZE_BASE) += kaslr_early.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o +obj-y := idreg-override.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o +obj-$(CONFIG_RELOCATABLE) += relocate.pi.o +obj-$(CONFIG_RANDOMIZE_BASE) += kaslr_early.pi.o extra-y := $(patsubst %.pi.o,%.o,$(obj-y)) diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c new file mode 100644 index 000000000000..f9e05c10faab --- /dev/null +++ b/arch/arm64/kernel/pi/idreg-override.c @@ -0,0 +1,370 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Early cpufeature override framework + * + * Copyright (C) 2020 Google LLC + * Author: Marc Zyngier + */ + +#include +#include +#include + +#include +#include +#include + +#include "pi.h" + +#define FTR_DESC_NAME_LEN 20 +#define FTR_DESC_FIELD_LEN 10 +#define FTR_ALIAS_NAME_LEN 30 +#define FTR_ALIAS_OPTION_LEN 116 + +static u64 __boot_status __initdata; + +typedef bool filter_t(u64 val); + +struct ftr_set_desc { + char name[FTR_DESC_NAME_LEN]; + PREL64(struct arm64_ftr_override, override); + struct { + char name[FTR_DESC_FIELD_LEN]; + u8 shift; + u8 width; + PREL64(filter_t, filter); + } fields[]; +}; + +#define FIELD(n, s, f) { .name = n, .shift = s, .width = 4, .filter = f } + +static bool __init mmfr1_vh_filter(u64 val) +{ + /* + * If we ever reach this point while running VHE, we're + * guaranteed to be on one of these funky, VHE-stuck CPUs. If + * the user was trying to force nVHE on us, proceed with + * attitude adjustment. + */ + return !(__boot_status == (BOOT_CPU_FLAG_E2H | BOOT_CPU_MODE_EL2) && + val == 0); +} + +static const struct ftr_set_desc mmfr1 __prel64_initconst = { + .name = "id_aa64mmfr1", + .override = &id_aa64mmfr1_override, + .fields = { + FIELD("vh", ID_AA64MMFR1_EL1_VH_SHIFT, mmfr1_vh_filter), + {} + }, +}; + +static bool __init pfr0_sve_filter(u64 val) +{ + /* + * Disabling SVE also means disabling all the features that + * are associated with it. The easiest way to do it is just to + * override id_aa64zfr0_el1 to be 0. + */ + if (!val) { + id_aa64zfr0_override.val = 0; + id_aa64zfr0_override.mask = GENMASK(63, 0); + } + + return true; +} + +static const struct ftr_set_desc pfr0 __prel64_initconst = { + .name = "id_aa64pfr0", + .override = &id_aa64pfr0_override, + .fields = { + FIELD("sve", ID_AA64PFR0_EL1_SVE_SHIFT, pfr0_sve_filter), + {} + }, +}; + +static bool __init pfr1_sme_filter(u64 val) +{ + /* + * Similarly to SVE, disabling SME also means disabling all + * the features that are associated with it. Just set + * id_aa64smfr0_el1 to 0 and don't look back. + */ + if (!val) { + id_aa64smfr0_override.val = 0; + id_aa64smfr0_override.mask = GENMASK(63, 0); + } + + return true; +} + +static const struct ftr_set_desc pfr1 __prel64_initconst = { + .name = "id_aa64pfr1", + .override = &id_aa64pfr1_override, + .fields = { + FIELD("bt", ID_AA64PFR1_EL1_BT_SHIFT, NULL ), + FIELD("mte", ID_AA64PFR1_EL1_MTE_SHIFT, NULL), + FIELD("sme", ID_AA64PFR1_EL1_SME_SHIFT, pfr1_sme_filter), + {} + }, +}; + +static const struct ftr_set_desc isar1 __prel64_initconst = { + .name = "id_aa64isar1", + .override = &id_aa64isar1_override, + .fields = { + FIELD("gpi", ID_AA64ISAR1_EL1_GPI_SHIFT, NULL), + FIELD("gpa", ID_AA64ISAR1_EL1_GPA_SHIFT, NULL), + FIELD("api", ID_AA64ISAR1_EL1_API_SHIFT, NULL), + FIELD("apa", ID_AA64ISAR1_EL1_APA_SHIFT, NULL), + {} + }, +}; + +static const struct ftr_set_desc isar2 __prel64_initconst = { + .name = "id_aa64isar2", + .override = &id_aa64isar2_override, + .fields = { + FIELD("gpa3", ID_AA64ISAR2_EL1_GPA3_SHIFT, NULL), + FIELD("apa3", ID_AA64ISAR2_EL1_APA3_SHIFT, NULL), + FIELD("mops", ID_AA64ISAR2_EL1_MOPS_SHIFT, NULL), + {} + }, +}; + +static const struct ftr_set_desc smfr0 __prel64_initconst = { + .name = "id_aa64smfr0", + .override = &id_aa64smfr0_override, + .fields = { + FIELD("smever", ID_AA64SMFR0_EL1_SMEver_SHIFT, NULL), + /* FA64 is a one bit field... :-/ */ + { "fa64", ID_AA64SMFR0_EL1_FA64_SHIFT, 1, }, + {} + }, +}; + +static bool __init hvhe_filter(u64 val) +{ + u64 mmfr1 = read_sysreg(id_aa64mmfr1_el1); + + return (val == 1 && + lower_32_bits(__boot_status) == BOOT_CPU_MODE_EL2 && + cpuid_feature_extract_unsigned_field(mmfr1, + ID_AA64MMFR1_EL1_VH_SHIFT)); +} + +static const struct ftr_set_desc sw_features __prel64_initconst = { + .name = "arm64_sw", + .override = &arm64_sw_feature_override, + .fields = { + FIELD("nokaslr", ARM64_SW_FEATURE_OVERRIDE_NOKASLR, NULL), + FIELD("hvhe", ARM64_SW_FEATURE_OVERRIDE_HVHE, hvhe_filter), + {} + }, +}; + +static const +PREL64(const struct ftr_set_desc, reg) regs[] __prel64_initconst = { + { &mmfr1 }, + { &pfr0 }, + { &pfr1 }, + { &isar1 }, + { &isar2 }, + { &smfr0 }, + { &sw_features }, +}; + +static const struct { + char alias[FTR_ALIAS_NAME_LEN]; + char feature[FTR_ALIAS_OPTION_LEN]; +} aliases[] __initconst = { + { "kvm_arm.mode=nvhe", "id_aa64mmfr1.vh=0" }, + { "kvm_arm.mode=protected", "id_aa64mmfr1.vh=0" }, + { "arm64.nosve", "id_aa64pfr0.sve=0" }, + { "arm64.nosme", "id_aa64pfr1.sme=0" }, + { "arm64.nobti", "id_aa64pfr1.bt=0" }, + { "arm64.nopauth", + "id_aa64isar1.gpi=0 id_aa64isar1.gpa=0 " + "id_aa64isar1.api=0 id_aa64isar1.apa=0 " + "id_aa64isar2.gpa3=0 id_aa64isar2.apa3=0" }, + { "arm64.nomops", "id_aa64isar2.mops=0" }, + { "arm64.nomte", "id_aa64pfr1.mte=0" }, + { "nokaslr", "arm64_sw.nokaslr=1" }, +}; + +static int __init parse_hexdigit(const char *p, u64 *v) +{ + // skip "0x" if it comes next + if (p[0] == '0' && tolower(p[1]) == 'x') + p += 2; + + // check whether the RHS is a single hex digit + if (!isxdigit(p[0]) || (p[1] && !isspace(p[1]))) + return -EINVAL; + + *v = tolower(*p) - (isdigit(*p) ? '0' : 'a' - 10); + return 0; +} + +static int __init find_field(const char *cmdline, char *opt, int len, + const struct ftr_set_desc *reg, int f, u64 *v) +{ + int flen = strlen(reg->fields[f].name); + + // append '=' to obtain '.=' + memcpy(opt + len, reg->fields[f].name, flen); + len += flen; + opt[len++] = '='; + + if (memcmp(cmdline, opt, len)) + return -1; + + return parse_hexdigit(cmdline + len, v); +} + +static void __init match_options(const char *cmdline) +{ + char opt[FTR_DESC_NAME_LEN + FTR_DESC_FIELD_LEN + 2]; + int i; + + for (i = 0; i < ARRAY_SIZE(regs); i++) { + const struct ftr_set_desc *reg = prel64_pointer(regs[i].reg); + struct arm64_ftr_override *override; + int len = strlen(reg->name); + int f; + + override = prel64_pointer(reg->override); + + // set opt[] to '.' + memcpy(opt, reg->name, len); + opt[len++] = '.'; + + for (f = 0; reg->fields[f].name[0] != '\0'; f++) { + u64 shift = reg->fields[f].shift; + u64 width = reg->fields[f].width ?: 4; + u64 mask = GENMASK_ULL(shift + width - 1, shift); + bool (*filter)(u64 val); + u64 v; + + if (find_field(cmdline, opt, len, reg, f, &v)) + continue; + + /* + * If an override gets filtered out, advertise + * it by setting the value to the all-ones while + * clearing the mask... Yes, this is fragile. + */ + filter = prel64_pointer(reg->fields[f].filter); + if (filter && !filter(v)) { + override->val |= mask; + override->mask &= ~mask; + continue; + } + + override->val &= ~mask; + override->val |= (v << shift) & mask; + override->mask |= mask; + + return; + } + } +} + +static __init void __parse_cmdline(const char *cmdline, bool parse_aliases) +{ + do { + char buf[256]; + size_t len; + int i; + + cmdline = skip_spaces(cmdline); + + /* terminate on "--" appearing on the command line by itself */ + if (cmdline[0] == '-' && cmdline[1] == '-' && isspace(cmdline[2])) + return; + + for (len = 0; cmdline[len] && !isspace(cmdline[len]); len++) { + if (len >= sizeof(buf) - 1) + break; + if (cmdline[len] == '-') + buf[len] = '_'; + else + buf[len] = cmdline[len]; + } + if (!len) + return; + + buf[len] = 0; + + cmdline += len; + + match_options(buf); + + for (i = 0; parse_aliases && i < ARRAY_SIZE(aliases); i++) + if (!memcmp(buf, aliases[i].alias, len + 1)) + __parse_cmdline(aliases[i].feature, false); + } while (1); +} + +static __init const u8 *get_bootargs_cmdline(const void *fdt) +{ + const u8 *prop; + int node; + + node = fdt_path_offset(fdt, "/chosen"); + if (node < 0) + return NULL; + + prop = fdt_getprop(fdt, node, "bootargs", NULL); + if (!prop) + return NULL; + + return strlen(prop) ? prop : NULL; +} + +static __init void parse_cmdline(const void *fdt) +{ + const u8 *prop = get_bootargs_cmdline(fdt); + + if (IS_ENABLED(CONFIG_CMDLINE_FORCE) || !prop) + __parse_cmdline(CONFIG_CMDLINE, true); + + if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && prop) + __parse_cmdline(prop, true); +} + +/* Keep checkers quiet */ +void init_feature_override(u64 boot_status, const void *fdt); + +asmlinkage void __init init_feature_override(u64 boot_status, const void *fdt) +{ + struct arm64_ftr_override *override; + const struct ftr_set_desc *reg; + int i; + + for (i = 0; i < ARRAY_SIZE(regs); i++) { + reg = prel64_pointer(regs[i].reg); + override = prel64_pointer(reg->override); + + override->val = 0; + override->mask = 0; + } + + __boot_status = boot_status; + + parse_cmdline(fdt); + + for (i = 0; i < ARRAY_SIZE(regs); i++) { + reg = prel64_pointer(regs[i].reg); + override = prel64_pointer(reg->override); + dcache_clean_inval_poc((unsigned long)override, + (unsigned long)(override + 1)); + } +} + +char * __init skip_spaces(const char *str) +{ + while (isspace(*str)) + ++str; + return (char *)str; +} -- cgit v1.2.3 From 9c4cd2a7d12c2c5b11efe7831b54e46c73eb3a8c Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:51 +0100 Subject: arm64: kernel: Remove early fdt remap code The early FDT remap code is no longer used so let's drop it. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-50-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/setup.h | 3 --- arch/arm64/kernel/setup.c | 15 --------------- 2 files changed, 18 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/setup.h b/arch/arm64/include/asm/setup.h index 2e4d7da74fb8..ba269a7a3201 100644 --- a/arch/arm64/include/asm/setup.h +++ b/arch/arm64/include/asm/setup.h @@ -7,9 +7,6 @@ #include -void *get_early_fdt_ptr(void); -void early_fdt_map(u64 dt_phys); - /* * These two variables are used in the head.S file. */ diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 42c690bb2d60..97d2143669cf 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -166,21 +166,6 @@ static void __init smp_build_mpidr_hash(void) pr_warn("Large number of MPIDR hash buckets detected\n"); } -static void *early_fdt_ptr __initdata; - -void __init *get_early_fdt_ptr(void) -{ - return early_fdt_ptr; -} - -asmlinkage void __init early_fdt_map(u64 dt_phys) -{ - int fdt_size; - - early_fixmap_init(); - early_fdt_ptr = fixmap_remap_fdt(dt_phys, &fdt_size, PAGE_KERNEL); -} - static void __init setup_machine_fdt(phys_addr_t dt_phys) { int size; -- cgit v1.2.3 From aa99aad798a8bc6d35ada2af1dc38f75d364e1ce Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:52 +0100 Subject: arm64: head: Clear BSS and the kernel page tables in one go We will move the CPU feature overrides into BSS in a subsequent patch, and this requires that BSS is zeroed before the feature override detection code runs. So let's map BSS read-write in the ID map, and zero it via this mapping. Since the kernel page tables are right next to it, and also zeroed via the ID map, let's drop the separate clear_page_tables() function, and just zero everything in one go. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-51-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/head.S | 33 +++++++++++---------------------- arch/arm64/kernel/vmlinux.lds.S | 3 +++ 2 files changed, 14 insertions(+), 22 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index ca5e5fbefcd3..2af518161f3a 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -177,17 +177,6 @@ SYM_CODE_START_LOCAL(preserve_boot_args) ret SYM_CODE_END(preserve_boot_args) -SYM_FUNC_START_LOCAL(clear_page_tables) - /* - * Clear the init page tables. - */ - adrp x0, init_pg_dir - adrp x1, init_pg_end - sub x2, x1, x0 - mov x1, xzr - b __pi_memset // tail call -SYM_FUNC_END(clear_page_tables) - /* * Macro to populate page table entries, these entries can be pointers to the next level * or last level entries pointing to physical memory. @@ -386,9 +375,9 @@ SYM_FUNC_START_LOCAL(create_idmap) map_memory x0, x1, x3, x6, x7, x3, IDMAP_PGD_ORDER, x10, x11, x12, x13, x14, EXTRA_SHIFT - /* Remap the kernel page tables r/w in the ID map */ + /* Remap BSS and the kernel page tables r/w in the ID map */ adrp x1, _text - adrp x2, init_pg_dir + adrp x2, __bss_start adrp x3, _end bic x4, x2, #SWAPPER_BLOCK_SIZE - 1 mov_q x5, SWAPPER_RW_MMUFLAGS @@ -489,14 +478,6 @@ SYM_FUNC_START_LOCAL(__primary_switched) mov x0, x20 bl set_cpu_boot_mode_flag - // Clear BSS - adr_l x0, __bss_start - mov x1, xzr - adr_l x2, __bss_stop - sub x2, x2, x0 - bl __pi_memset - dsb ishst // Make zero page visible to PTW - #if VA_BITS > 48 adr_l x8, vabits_actual // Set this early so KASAN early init str x25, [x8] // ... observes the correct value @@ -782,6 +763,15 @@ SYM_FUNC_START_LOCAL(__primary_switch) adrp x1, reserved_pg_dir adrp x2, init_idmap_pg_dir bl __enable_mmu + + // Clear BSS + adrp x0, __bss_start + mov x1, xzr + adrp x2, init_pg_end + sub x2, x2, x0 + bl __pi_memset + dsb ishst // Make zero page visible to PTW + #ifdef CONFIG_RELOCATABLE adrp x23, KERNEL_START and x23, x23, MIN_KIMG_ALIGN - 1 @@ -796,7 +786,6 @@ SYM_FUNC_START_LOCAL(__primary_switch) orr x23, x23, x0 // record kernel offset #endif #endif - bl clear_page_tables bl create_kernel_mapping adrp x1, init_pg_dir diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 8dd5dda66f7c..8a3c6aacc355 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -311,12 +311,15 @@ SECTIONS __pecoff_data_rawsize = ABSOLUTE(. - __initdata_begin); _edata = .; + /* start of zero-init region */ BSS_SECTION(SBSS_ALIGN, 0, 0) . = ALIGN(PAGE_SIZE); init_pg_dir = .; . += INIT_DIR_SIZE; init_pg_end = .; + /* end of zero-init region */ + #ifdef CONFIG_RELOCATABLE . += SZ_4K; /* stack for the early relocation code */ early_init_stack = .; -- cgit v1.2.3 From 30687dec5ed5576c743a4cd012a91f93848fe902 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:53 +0100 Subject: arm64: Move feature overrides into the BSS section In order to allow the CPU feature override detection code to run even earlier, move the feature override global variables into BSS, which is the only part of the static kernel image that is mapped read-write in the initial ID map. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-52-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/cpufeature.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 8d1a634a403e..a99ad79adee2 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -655,13 +655,13 @@ static const struct arm64_ftr_bits ftr_raz[] = { #define ARM64_FTR_REG(id, table) \ __ARM64_FTR_REG_OVERRIDE(#id, id, table, &no_override) -struct arm64_ftr_override __ro_after_init id_aa64mmfr1_override; -struct arm64_ftr_override __ro_after_init id_aa64pfr0_override; -struct arm64_ftr_override __ro_after_init id_aa64pfr1_override; -struct arm64_ftr_override __ro_after_init id_aa64zfr0_override; -struct arm64_ftr_override __ro_after_init id_aa64smfr0_override; -struct arm64_ftr_override __ro_after_init id_aa64isar1_override; -struct arm64_ftr_override __ro_after_init id_aa64isar2_override; +struct arm64_ftr_override id_aa64mmfr1_override; +struct arm64_ftr_override id_aa64pfr0_override; +struct arm64_ftr_override id_aa64pfr1_override; +struct arm64_ftr_override id_aa64zfr0_override; +struct arm64_ftr_override id_aa64smfr0_override; +struct arm64_ftr_override id_aa64isar1_override; +struct arm64_ftr_override id_aa64isar2_override; struct arm64_ftr_override arm64_sw_feature_override; -- cgit v1.2.3 From dcfe969a641984fcd2b52aa257e478443612c050 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:54 +0100 Subject: arm64: head: Run feature override detection before mapping the kernel To permit the feature overrides to be taken into account before the KASLR init code runs and the kernel mapping is created, move the detection code to an earlier stage in the boot. In a subsequent patch, this will be taken advantage of by merging the preliminary and permanent mappings of the kernel text and data into a single one that gets created and relocated before start_kernel() is called. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-53-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/head.S | 17 +++++++++-------- arch/arm64/kernel/vmlinux.lds.S | 4 +--- 2 files changed, 10 insertions(+), 11 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 2af518161f3a..865ecc1f8255 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -375,9 +375,9 @@ SYM_FUNC_START_LOCAL(create_idmap) map_memory x0, x1, x3, x6, x7, x3, IDMAP_PGD_ORDER, x10, x11, x12, x13, x14, EXTRA_SHIFT - /* Remap BSS and the kernel page tables r/w in the ID map */ + /* Remap [.init].data, BSS and the kernel page tables r/w in the ID map */ adrp x1, _text - adrp x2, __bss_start + adrp x2, __initdata_begin adrp x3, _end bic x4, x2, #SWAPPER_BLOCK_SIZE - 1 mov_q x5, SWAPPER_RW_MMUFLAGS @@ -491,9 +491,6 @@ SYM_FUNC_START_LOCAL(__primary_switched) #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) bl kasan_early_init #endif - mov x0, x20 // pass the full boot status - mov x1, x22 // pass the low FDT mapping - bl __pi_init_feature_override // Parse cpu feature overrides #ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS bl scs_patch_vmlinux #endif @@ -772,12 +769,16 @@ SYM_FUNC_START_LOCAL(__primary_switch) bl __pi_memset dsb ishst // Make zero page visible to PTW -#ifdef CONFIG_RELOCATABLE - adrp x23, KERNEL_START - and x23, x23, MIN_KIMG_ALIGN - 1 adrp x1, early_init_stack mov sp, x1 mov x29, xzr + mov x0, x20 // pass the full boot status + mov x1, x22 // pass the low FDT mapping + bl __pi_init_feature_override // Parse cpu feature overrides + +#ifdef CONFIG_RELOCATABLE + adrp x23, KERNEL_START + and x23, x23, MIN_KIMG_ALIGN - 1 #ifdef CONFIG_RANDOMIZE_BASE mov x0, x22 bl __pi_kaslr_early_init diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 8a3c6aacc355..3afb4223a5e8 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -320,10 +320,8 @@ SECTIONS init_pg_end = .; /* end of zero-init region */ -#ifdef CONFIG_RELOCATABLE - . += SZ_4K; /* stack for the early relocation code */ + . += SZ_4K; /* stack for the early C runtime */ early_init_stack = .; -#endif . = ALIGN(SEGMENT_ALIGN); __pecoff_data_size = ABSOLUTE(. - __initdata_begin); -- cgit v1.2.3 From 8a6e40e1f68e9fc44497db88e0c0f21bb513c551 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:55 +0100 Subject: arm64: head: move dynamic shadow call stack patching into early C runtime Once we update the early kernel mapping code to only map the kernel once with the right permissions, we can no longer perform code patching via this mapping. So move this code to an earlier stage of the boot, right after applying the relocations. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-54-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/scs.h | 4 +- arch/arm64/kernel/Makefile | 8 -- arch/arm64/kernel/head.S | 8 +- arch/arm64/kernel/module.c | 2 +- arch/arm64/kernel/patch-scs.c | 262 --------------------------------------- arch/arm64/kernel/pi/Makefile | 10 +- arch/arm64/kernel/pi/patch-scs.c | 262 +++++++++++++++++++++++++++++++++++++++ 7 files changed, 276 insertions(+), 280 deletions(-) delete mode 100644 arch/arm64/kernel/patch-scs.c create mode 100644 arch/arm64/kernel/pi/patch-scs.c (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h index 3fdae5fe3142..eca2ba5a6276 100644 --- a/arch/arm64/include/asm/scs.h +++ b/arch/arm64/include/asm/scs.h @@ -72,8 +72,8 @@ static inline void dynamic_scs_init(void) static inline void dynamic_scs_init(void) {} #endif -int scs_patch(const u8 eh_frame[], int size); -asmlinkage void scs_patch_vmlinux(void); +int __pi_scs_patch(const u8 eh_frame[], int size); +asmlinkage void __pi_scs_patch_vmlinux(void); #endif /* __ASSEMBLY __ */ diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 4236f1e0fffa..14b4a179bad3 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -71,14 +71,6 @@ obj-$(CONFIG_ARM64_PTR_AUTH) += pointer_auth.o obj-$(CONFIG_ARM64_MTE) += mte.o obj-y += vdso-wrap.o obj-$(CONFIG_COMPAT_VDSO) += vdso32-wrap.o -obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) += patch-scs.o - -# We need to prevent the SCS patching code from patching itself. Using -# -mbranch-protection=none here to avoid the patchable PAC opcodes from being -# generated triggers an issue with full LTO on Clang, which stops emitting PAC -# instructions altogether. So disable LTO as well for the compilation unit. -CFLAGS_patch-scs.o += -mbranch-protection=none -CFLAGS_REMOVE_patch-scs.o += $(CC_FLAGS_LTO) # Force dependency (vdso*-wrap.S includes vdso.so through incbin) $(obj)/vdso-wrap.o: $(obj)/vdso/vdso.so diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 865ecc1f8255..b320702032a7 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -490,9 +490,6 @@ SYM_FUNC_START_LOCAL(__primary_switched) #endif #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) bl kasan_early_init -#endif -#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS - bl scs_patch_vmlinux #endif mov x0, x20 bl finalise_el2 // Prefer VHE if possible @@ -794,6 +791,11 @@ SYM_FUNC_START_LOCAL(__primary_switch) #ifdef CONFIG_RELOCATABLE mov x0, x23 bl __pi_relocate_kernel +#endif +#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS + ldr x0, =__eh_frame_start + ldr x1, =__eh_frame_end + bl __pi_scs_patch_vmlinux #endif ldr x8, =__primary_switched adrp x0, KERNEL_START // __pa(KERNEL_START) diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c index dd851297596e..47e0be610bb6 100644 --- a/arch/arm64/kernel/module.c +++ b/arch/arm64/kernel/module.c @@ -595,7 +595,7 @@ int module_finalize(const Elf_Ehdr *hdr, if (scs_is_dynamic()) { s = find_section(hdr, sechdrs, ".init.eh_frame"); if (s) - scs_patch((void *)s->sh_addr, s->sh_size); + __pi_scs_patch((void *)s->sh_addr, s->sh_size); } return module_init_ftrace_plt(hdr, sechdrs, me); diff --git a/arch/arm64/kernel/patch-scs.c b/arch/arm64/kernel/patch-scs.c deleted file mode 100644 index a1fe4b4ff591..000000000000 --- a/arch/arm64/kernel/patch-scs.c +++ /dev/null @@ -1,262 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (C) 2022 - Google LLC - * Author: Ard Biesheuvel - */ - -#include -#include -#include -#include -#include -#include - -#include -#include - -// -// This minimal DWARF CFI parser is partially based on the code in -// arch/arc/kernel/unwind.c, and on the document below: -// https://refspecs.linuxbase.org/LSB_4.0.0/LSB-Core-generic/LSB-Core-generic/ehframechpt.html -// - -#define DW_CFA_nop 0x00 -#define DW_CFA_set_loc 0x01 -#define DW_CFA_advance_loc1 0x02 -#define DW_CFA_advance_loc2 0x03 -#define DW_CFA_advance_loc4 0x04 -#define DW_CFA_offset_extended 0x05 -#define DW_CFA_restore_extended 0x06 -#define DW_CFA_undefined 0x07 -#define DW_CFA_same_value 0x08 -#define DW_CFA_register 0x09 -#define DW_CFA_remember_state 0x0a -#define DW_CFA_restore_state 0x0b -#define DW_CFA_def_cfa 0x0c -#define DW_CFA_def_cfa_register 0x0d -#define DW_CFA_def_cfa_offset 0x0e -#define DW_CFA_def_cfa_expression 0x0f -#define DW_CFA_expression 0x10 -#define DW_CFA_offset_extended_sf 0x11 -#define DW_CFA_def_cfa_sf 0x12 -#define DW_CFA_def_cfa_offset_sf 0x13 -#define DW_CFA_val_offset 0x14 -#define DW_CFA_val_offset_sf 0x15 -#define DW_CFA_val_expression 0x16 -#define DW_CFA_lo_user 0x1c -#define DW_CFA_negate_ra_state 0x2d -#define DW_CFA_GNU_args_size 0x2e -#define DW_CFA_GNU_negative_offset_extended 0x2f -#define DW_CFA_hi_user 0x3f - -extern const u8 __eh_frame_start[], __eh_frame_end[]; - -enum { - PACIASP = 0xd503233f, - AUTIASP = 0xd50323bf, - SCS_PUSH = 0xf800865e, - SCS_POP = 0xf85f8e5e, -}; - -static void __always_inline scs_patch_loc(u64 loc) -{ - u32 insn = le32_to_cpup((void *)loc); - - switch (insn) { - case PACIASP: - *(u32 *)loc = cpu_to_le32(SCS_PUSH); - break; - case AUTIASP: - *(u32 *)loc = cpu_to_le32(SCS_POP); - break; - default: - /* - * While the DW_CFA_negate_ra_state directive is guaranteed to - * appear right after a PACIASP/AUTIASP instruction, it may - * also appear after a DW_CFA_restore_state directive that - * restores a state that is only partially accurate, and is - * followed by DW_CFA_negate_ra_state directive to toggle the - * PAC bit again. So we permit other instructions here, and ignore - * them. - */ - return; - } - dcache_clean_pou(loc, loc + sizeof(u32)); -} - -/* - * Skip one uleb128/sleb128 encoded quantity from the opcode stream. All bytes - * except the last one have bit #7 set. - */ -static int __always_inline skip_xleb128(const u8 **opcode, int size) -{ - u8 c; - - do { - c = *(*opcode)++; - size--; - } while (c & BIT(7)); - - return size; -} - -struct eh_frame { - /* - * The size of this frame if 0 < size < U32_MAX, 0 terminates the list. - */ - u32 size; - - /* - * The first frame is a Common Information Entry (CIE) frame, followed - * by one or more Frame Description Entry (FDE) frames. In the former - * case, this field is 0, otherwise it is the negated offset relative - * to the associated CIE frame. - */ - u32 cie_id_or_pointer; - - union { - struct { // CIE - u8 version; - u8 augmentation_string[]; - }; - - struct { // FDE - s32 initial_loc; - s32 range; - u8 opcodes[]; - }; - }; -}; - -static int noinstr scs_handle_fde_frame(const struct eh_frame *frame, - bool fde_has_augmentation_data, - int code_alignment_factor, - bool dry_run) -{ - int size = frame->size - offsetof(struct eh_frame, opcodes) + 4; - u64 loc = (u64)offset_to_ptr(&frame->initial_loc); - const u8 *opcode = frame->opcodes; - - if (fde_has_augmentation_data) { - int l; - - // assume single byte uleb128_t - if (WARN_ON(*opcode & BIT(7))) - return -ENOEXEC; - - l = *opcode++; - opcode += l; - size -= l + 1; - } - - /* - * Starting from 'loc', apply the CFA opcodes that advance the location - * pointer, and identify the locations of the PAC instructions. - */ - while (size-- > 0) { - switch (*opcode++) { - case DW_CFA_nop: - case DW_CFA_remember_state: - case DW_CFA_restore_state: - break; - - case DW_CFA_advance_loc1: - loc += *opcode++ * code_alignment_factor; - size--; - break; - - case DW_CFA_advance_loc2: - loc += *opcode++ * code_alignment_factor; - loc += (*opcode++ << 8) * code_alignment_factor; - size -= 2; - break; - - case DW_CFA_def_cfa: - case DW_CFA_offset_extended: - size = skip_xleb128(&opcode, size); - fallthrough; - case DW_CFA_def_cfa_offset: - case DW_CFA_def_cfa_offset_sf: - case DW_CFA_def_cfa_register: - case DW_CFA_same_value: - case DW_CFA_restore_extended: - case 0x80 ... 0xbf: - size = skip_xleb128(&opcode, size); - break; - - case DW_CFA_negate_ra_state: - if (!dry_run) - scs_patch_loc(loc - 4); - break; - - case 0x40 ... 0x7f: - // advance loc - loc += (opcode[-1] & 0x3f) * code_alignment_factor; - break; - - case 0xc0 ... 0xff: - break; - - default: - pr_err("unhandled opcode: %02x in FDE frame %lx\n", opcode[-1], (uintptr_t)frame); - return -ENOEXEC; - } - } - return 0; -} - -int noinstr scs_patch(const u8 eh_frame[], int size) -{ - const u8 *p = eh_frame; - - while (size > 4) { - const struct eh_frame *frame = (const void *)p; - bool fde_has_augmentation_data = true; - int code_alignment_factor = 1; - int ret; - - if (frame->size == 0 || - frame->size == U32_MAX || - frame->size > size) - break; - - if (frame->cie_id_or_pointer == 0) { - const u8 *p = frame->augmentation_string; - - /* a 'z' in the augmentation string must come first */ - fde_has_augmentation_data = *p == 'z'; - - /* - * The code alignment factor is a uleb128 encoded field - * but given that the only sensible values are 1 or 4, - * there is no point in decoding the whole thing. - */ - p += strlen(p) + 1; - if (!WARN_ON(*p & BIT(7))) - code_alignment_factor = *p; - } else { - ret = scs_handle_fde_frame(frame, - fde_has_augmentation_data, - code_alignment_factor, - true); - if (ret) - return ret; - scs_handle_fde_frame(frame, fde_has_augmentation_data, - code_alignment_factor, false); - } - - p += sizeof(frame->size) + frame->size; - size -= sizeof(frame->size) + frame->size; - } - return 0; -} - -asmlinkage void __init scs_patch_vmlinux(void) -{ - if (!should_patch_pac_into_scs()) - return; - - WARN_ON(scs_patch(__eh_frame_start, __eh_frame_end - __eh_frame_start)); - icache_inval_all_pou(); - isb(); -} diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile index 7f6dfce893c3..a8b302245f15 100644 --- a/arch/arm64/kernel/pi/Makefile +++ b/arch/arm64/kernel/pi/Makefile @@ -38,7 +38,9 @@ $(obj)/lib-%.pi.o: OBJCOPYFLAGS += --prefix-alloc-sections=.init $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE $(call if_changed_rule,cc_o_c) -obj-y := idreg-override.pi.o lib-fdt.pi.o lib-fdt_ro.pi.o -obj-$(CONFIG_RELOCATABLE) += relocate.pi.o -obj-$(CONFIG_RANDOMIZE_BASE) += kaslr_early.pi.o -extra-y := $(patsubst %.pi.o,%.o,$(obj-y)) +obj-y := idreg-override.pi.o \ + lib-fdt.pi.o lib-fdt_ro.pi.o +obj-$(CONFIG_RELOCATABLE) += relocate.pi.o +obj-$(CONFIG_RANDOMIZE_BASE) += kaslr_early.pi.o +obj-$(CONFIG_UNWIND_PATCH_PAC_INTO_SCS) += patch-scs.pi.o +extra-y := $(patsubst %.pi.o,%.o,$(obj-y)) diff --git a/arch/arm64/kernel/pi/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c new file mode 100644 index 000000000000..c65ef40d1e6b --- /dev/null +++ b/arch/arm64/kernel/pi/patch-scs.c @@ -0,0 +1,262 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2022 - Google LLC + * Author: Ard Biesheuvel + */ + +#include +#include +#include +#include + +#include + +// +// This minimal DWARF CFI parser is partially based on the code in +// arch/arc/kernel/unwind.c, and on the document below: +// https://refspecs.linuxbase.org/LSB_4.0.0/LSB-Core-generic/LSB-Core-generic/ehframechpt.html +// + +#define DW_CFA_nop 0x00 +#define DW_CFA_set_loc 0x01 +#define DW_CFA_advance_loc1 0x02 +#define DW_CFA_advance_loc2 0x03 +#define DW_CFA_advance_loc4 0x04 +#define DW_CFA_offset_extended 0x05 +#define DW_CFA_restore_extended 0x06 +#define DW_CFA_undefined 0x07 +#define DW_CFA_same_value 0x08 +#define DW_CFA_register 0x09 +#define DW_CFA_remember_state 0x0a +#define DW_CFA_restore_state 0x0b +#define DW_CFA_def_cfa 0x0c +#define DW_CFA_def_cfa_register 0x0d +#define DW_CFA_def_cfa_offset 0x0e +#define DW_CFA_def_cfa_expression 0x0f +#define DW_CFA_expression 0x10 +#define DW_CFA_offset_extended_sf 0x11 +#define DW_CFA_def_cfa_sf 0x12 +#define DW_CFA_def_cfa_offset_sf 0x13 +#define DW_CFA_val_offset 0x14 +#define DW_CFA_val_offset_sf 0x15 +#define DW_CFA_val_expression 0x16 +#define DW_CFA_lo_user 0x1c +#define DW_CFA_negate_ra_state 0x2d +#define DW_CFA_GNU_args_size 0x2e +#define DW_CFA_GNU_negative_offset_extended 0x2f +#define DW_CFA_hi_user 0x3f + +extern const u8 __eh_frame_start[], __eh_frame_end[]; + +enum { + PACIASP = 0xd503233f, + AUTIASP = 0xd50323bf, + SCS_PUSH = 0xf800865e, + SCS_POP = 0xf85f8e5e, +}; + +static void __always_inline scs_patch_loc(u64 loc) +{ + u32 insn = le32_to_cpup((void *)loc); + + switch (insn) { + case PACIASP: + *(u32 *)loc = cpu_to_le32(SCS_PUSH); + break; + case AUTIASP: + *(u32 *)loc = cpu_to_le32(SCS_POP); + break; + default: + /* + * While the DW_CFA_negate_ra_state directive is guaranteed to + * appear right after a PACIASP/AUTIASP instruction, it may + * also appear after a DW_CFA_restore_state directive that + * restores a state that is only partially accurate, and is + * followed by DW_CFA_negate_ra_state directive to toggle the + * PAC bit again. So we permit other instructions here, and ignore + * them. + */ + return; + } + if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_CLEAN_CACHE)) + asm("dc civac, %0" :: "r"(loc)); + else + asm(ALTERNATIVE("dc cvau, %0", "nop", ARM64_HAS_CACHE_IDC) + :: "r"(loc)); +} + +/* + * Skip one uleb128/sleb128 encoded quantity from the opcode stream. All bytes + * except the last one have bit #7 set. + */ +static int __always_inline skip_xleb128(const u8 **opcode, int size) +{ + u8 c; + + do { + c = *(*opcode)++; + size--; + } while (c & BIT(7)); + + return size; +} + +struct eh_frame { + /* + * The size of this frame if 0 < size < U32_MAX, 0 terminates the list. + */ + u32 size; + + /* + * The first frame is a Common Information Entry (CIE) frame, followed + * by one or more Frame Description Entry (FDE) frames. In the former + * case, this field is 0, otherwise it is the negated offset relative + * to the associated CIE frame. + */ + u32 cie_id_or_pointer; + + union { + struct { // CIE + u8 version; + u8 augmentation_string[]; + }; + + struct { // FDE + s32 initial_loc; + s32 range; + u8 opcodes[]; + }; + }; +}; + +static int scs_handle_fde_frame(const struct eh_frame *frame, + bool fde_has_augmentation_data, + int code_alignment_factor, + bool dry_run) +{ + int size = frame->size - offsetof(struct eh_frame, opcodes) + 4; + u64 loc = (u64)offset_to_ptr(&frame->initial_loc); + const u8 *opcode = frame->opcodes; + + if (fde_has_augmentation_data) { + int l; + + // assume single byte uleb128_t + if (WARN_ON(*opcode & BIT(7))) + return -ENOEXEC; + + l = *opcode++; + opcode += l; + size -= l + 1; + } + + /* + * Starting from 'loc', apply the CFA opcodes that advance the location + * pointer, and identify the locations of the PAC instructions. + */ + while (size-- > 0) { + switch (*opcode++) { + case DW_CFA_nop: + case DW_CFA_remember_state: + case DW_CFA_restore_state: + break; + + case DW_CFA_advance_loc1: + loc += *opcode++ * code_alignment_factor; + size--; + break; + + case DW_CFA_advance_loc2: + loc += *opcode++ * code_alignment_factor; + loc += (*opcode++ << 8) * code_alignment_factor; + size -= 2; + break; + + case DW_CFA_def_cfa: + case DW_CFA_offset_extended: + size = skip_xleb128(&opcode, size); + fallthrough; + case DW_CFA_def_cfa_offset: + case DW_CFA_def_cfa_offset_sf: + case DW_CFA_def_cfa_register: + case DW_CFA_same_value: + case DW_CFA_restore_extended: + case 0x80 ... 0xbf: + size = skip_xleb128(&opcode, size); + break; + + case DW_CFA_negate_ra_state: + if (!dry_run) + scs_patch_loc(loc - 4); + break; + + case 0x40 ... 0x7f: + // advance loc + loc += (opcode[-1] & 0x3f) * code_alignment_factor; + break; + + case 0xc0 ... 0xff: + break; + + default: + return -ENOEXEC; + } + } + return 0; +} + +int scs_patch(const u8 eh_frame[], int size) +{ + const u8 *p = eh_frame; + + while (size > 4) { + const struct eh_frame *frame = (const void *)p; + bool fde_has_augmentation_data = true; + int code_alignment_factor = 1; + int ret; + + if (frame->size == 0 || + frame->size == U32_MAX || + frame->size > size) + break; + + if (frame->cie_id_or_pointer == 0) { + const u8 *p = frame->augmentation_string; + + /* a 'z' in the augmentation string must come first */ + fde_has_augmentation_data = *p == 'z'; + + /* + * The code alignment factor is a uleb128 encoded field + * but given that the only sensible values are 1 or 4, + * there is no point in decoding the whole thing. + */ + p += strlen(p) + 1; + if (!WARN_ON(*p & BIT(7))) + code_alignment_factor = *p; + } else { + ret = scs_handle_fde_frame(frame, + fde_has_augmentation_data, + code_alignment_factor, + true); + if (ret) + return ret; + scs_handle_fde_frame(frame, fde_has_augmentation_data, + code_alignment_factor, false); + } + + p += sizeof(frame->size) + frame->size; + size -= sizeof(frame->size) + frame->size; + } + return 0; +} + +asmlinkage void __init scs_patch_vmlinux(const u8 start[], const u8 end[]) +{ + if (!should_patch_pac_into_scs()) + return; + + scs_patch(start, end - start); + asm("ic ialluis"); + isb(); +} -- cgit v1.2.3 From 35876f35f4821c92fb1bbff7eec5780dba4fffdb Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:56 +0100 Subject: arm64: cpufeature: Add helper to test for CPU feature overrides Add some helpers to extract and apply feature overrides to the bare idreg values. This involves inspecting the value and mask of the specific field that we are interested in, given that an override value/mask pair might be invalid for one field but valid for another. Then, wire up the new helper for the hVHE test - note that we can drop the sysreg test here, as the override will be invalid when trying to enable hVHE on non-VHE capable hardware. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-55-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cpufeature.h | 39 +++++++++++++++++++++++++++++++++++++ arch/arm64/kernel/cpufeature.c | 9 +-------- 2 files changed, 40 insertions(+), 8 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 21c824edf8ce..acd8f4949583 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -915,6 +915,45 @@ extern struct arm64_ftr_override id_aa64isar2_override; extern struct arm64_ftr_override arm64_sw_feature_override; +static inline +u64 arm64_apply_feature_override(u64 val, int feat, int width, + const struct arm64_ftr_override *override) +{ + u64 oval = override->val; + + /* + * When it encounters an invalid override (e.g., an override that + * cannot be honoured due to a missing CPU feature), the early idreg + * override code will set the mask to 0x0 and the value to non-zero for + * the field in question. In order to determine whether the override is + * valid or not for the field we are interested in, we first need to + * disregard bits belonging to other fields. + */ + oval &= GENMASK_ULL(feat + width - 1, feat); + + /* + * The override is valid if all value bits are accounted for in the + * mask. If so, replace the masked bits with the override value. + */ + if (oval == (oval & override->mask)) { + val &= ~override->mask; + val |= oval; + } + + /* Extract the field from the updated value */ + return cpuid_feature_extract_unsigned_field(val, feat); +} + +static inline bool arm64_test_sw_feature_override(int feat) +{ + /* + * Software features are pseudo CPU features that have no underlying + * CPUID system register value to apply the override to. + */ + return arm64_apply_feature_override(0, feat, 4, + &arm64_sw_feature_override); +} + u32 get_kvm_ipa_limit(void); void dump_cpu_features(void); diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index a99ad79adee2..d0ffb872a31a 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2042,14 +2042,7 @@ static bool has_nested_virt_support(const struct arm64_cpu_capabilities *cap, static bool hvhe_possible(const struct arm64_cpu_capabilities *entry, int __unused) { - u64 val; - - val = read_sysreg(id_aa64mmfr1_el1); - if (!cpuid_feature_extract_unsigned_field(val, ID_AA64MMFR1_EL1_VH_SHIFT)) - return false; - - val = arm64_sw_feature_override.val & arm64_sw_feature_override.mask; - return cpuid_feature_extract_unsigned_field(val, ARM64_SW_FEATURE_OVERRIDE_HVHE); + return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_HVHE); } #ifdef CONFIG_ARM64_PAN -- cgit v1.2.3 From af73b9a2dd39fb458627a325dcdc9c76e274eae0 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:57 +0100 Subject: arm64: kaslr: Use feature override instead of parsing the cmdline again The early kaslr code open codes the detection of 'nokaslr' on the kernel command line, and this is no longer necessary now that the feature detection code, which also looks for the same string, executes before this code. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-56-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cpufeature.h | 5 ++++ arch/arm64/kernel/kaslr.c | 4 +-- arch/arm64/kernel/pi/kaslr_early.c | 53 +------------------------------------ 3 files changed, 7 insertions(+), 55 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index acd8f4949583..e309255b7f04 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -954,6 +954,11 @@ static inline bool arm64_test_sw_feature_override(int feat) &arm64_sw_feature_override); } +static inline bool kaslr_disabled_cmdline(void) +{ + return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOKASLR); +} + u32 get_kvm_ipa_limit(void); void dump_cpu_features(void); diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 12c7f3c8ba76..1da3e25f9d9e 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -16,9 +16,7 @@ bool __ro_after_init __kaslr_is_enabled = false; void __init kaslr_init(void) { - if (cpuid_feature_extract_unsigned_field(arm64_sw_feature_override.val & - arm64_sw_feature_override.mask, - ARM64_SW_FEATURE_OVERRIDE_NOKASLR)) { + if (kaslr_disabled_cmdline()) { pr_info("KASLR disabled on command line\n"); return; } diff --git a/arch/arm64/kernel/pi/kaslr_early.c b/arch/arm64/kernel/pi/kaslr_early.c index 167081b30a15..f2305e276ec3 100644 --- a/arch/arm64/kernel/pi/kaslr_early.c +++ b/arch/arm64/kernel/pi/kaslr_early.c @@ -16,57 +16,6 @@ #include #include -/* taken from lib/string.c */ -static char *__init __strstr(const char *s1, const char *s2) -{ - size_t l1, l2; - - l2 = strlen(s2); - if (!l2) - return (char *)s1; - l1 = strlen(s1); - while (l1 >= l2) { - l1--; - if (!memcmp(s1, s2, l2)) - return (char *)s1; - s1++; - } - return NULL; -} -static bool __init cmdline_contains_nokaslr(const u8 *cmdline) -{ - const u8 *str; - - str = __strstr(cmdline, "nokaslr"); - return str == cmdline || (str > cmdline && *(str - 1) == ' '); -} - -static bool __init is_kaslr_disabled_cmdline(void *fdt) -{ - if (!IS_ENABLED(CONFIG_CMDLINE_FORCE)) { - int node; - const u8 *prop; - - node = fdt_path_offset(fdt, "/chosen"); - if (node < 0) - goto out; - - prop = fdt_getprop(fdt, node, "bootargs", NULL); - if (!prop) - goto out; - - if (cmdline_contains_nokaslr(prop)) - return true; - - if (IS_ENABLED(CONFIG_CMDLINE_EXTEND)) - goto out; - - return false; - } -out: - return cmdline_contains_nokaslr(CONFIG_CMDLINE); -} - static u64 __init get_kaslr_seed(void *fdt) { static char const chosen_str[] __initconst = "chosen"; @@ -92,7 +41,7 @@ asmlinkage u64 __init kaslr_early_init(void *fdt) { u64 seed, range; - if (is_kaslr_disabled_cmdline(fdt)) + if (kaslr_disabled_cmdline()) return 0; seed = get_kaslr_seed(fdt); -- cgit v1.2.3 From 9ddd9baa42a01d383d278096a11b200b53ba9470 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:58 +0100 Subject: arm64: idreg-override: Create a pseudo feature for rodata=off Add rodata=off to the set of kernel command line options that is parsed early using the CPU feature override detection code, so we can easily refer to it when creating the kernel mapping. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-57-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cpufeature.h | 1 + arch/arm64/kernel/pi/idreg-override.c | 2 ++ 2 files changed, 3 insertions(+) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index e309255b7f04..03c34242bfc7 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -17,6 +17,7 @@ #define ARM64_SW_FEATURE_OVERRIDE_NOKASLR 0 #define ARM64_SW_FEATURE_OVERRIDE_HVHE 4 +#define ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF 8 #ifndef __ASSEMBLY__ diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c index f9e05c10faab..e4bcabcc6860 100644 --- a/arch/arm64/kernel/pi/idreg-override.c +++ b/arch/arm64/kernel/pi/idreg-override.c @@ -159,6 +159,7 @@ static const struct ftr_set_desc sw_features __prel64_initconst = { .fields = { FIELD("nokaslr", ARM64_SW_FEATURE_OVERRIDE_NOKASLR, NULL), FIELD("hvhe", ARM64_SW_FEATURE_OVERRIDE_HVHE, hvhe_filter), + FIELD("rodataoff", ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF, NULL), {} }, }; @@ -190,6 +191,7 @@ static const struct { { "arm64.nomops", "id_aa64isar2.mops=0" }, { "arm64.nomte", "id_aa64pfr1.mte=0" }, { "nokaslr", "arm64_sw.nokaslr=1" }, + { "rodata=off", "arm64_sw.rodataoff=1" }, }; static int __init parse_hexdigit(const char *p, u64 *v) -- cgit v1.2.3 From a669c6a4935626786e456b25e9cf2bfbba908f15 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:28:59 +0100 Subject: arm64: Add helpers to probe local CPU for PAC and BTI support Add some helpers that will be used by the early kernel mapping code to check feature support on the local CPU. This permits the early kernel mapping to be created with the right attributes, removing the need for tearing it down and recreating it. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-58-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cpufeature.h | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 03c34242bfc7..e3edae1825f3 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -963,6 +963,38 @@ static inline bool kaslr_disabled_cmdline(void) u32 get_kvm_ipa_limit(void); void dump_cpu_features(void); +static inline bool cpu_has_bti(void) +{ + if (!IS_ENABLED(CONFIG_ARM64_BTI)) + return false; + + return arm64_apply_feature_override(read_cpuid(ID_AA64PFR1_EL1), + ID_AA64PFR1_EL1_BT_SHIFT, 4, + &id_aa64pfr1_override); +} + +static inline bool cpu_has_pac(void) +{ + u64 isar1, isar2; + + if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH)) + return false; + + isar1 = read_cpuid(ID_AA64ISAR1_EL1); + isar2 = read_cpuid(ID_AA64ISAR2_EL1); + + if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_APA_SHIFT, 4, + &id_aa64isar1_override)) + return true; + + if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_API_SHIFT, 4, + &id_aa64isar1_override)) + return true; + + return arm64_apply_feature_override(isar2, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, + &id_aa64isar2_override); +} + #endif /* __ASSEMBLY__ */ #endif -- cgit v1.2.3 From 8d47b8e5c74a1be600fd68bbbb4c2ecd8d4cc33c Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:00 +0100 Subject: arm64: head: allocate more pages for the kernel mapping In preparation for switching to an early kernel mapping routine that maps each segment according to its precise boundaries, and with the correct attributes, let's allocate some extra pages for page tables for the 4k page size configuration. This is necessary because the start and end of each segment may not be aligned to the block size, and so we'll need an extra page table at each segment boundary. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-59-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/kernel-pgtable.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 83ddb14b95a5..0631604995ee 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -68,7 +68,7 @@ + EARLY_PGDS((vstart), (vend), add) /* each PGDIR needs a next level page table */ \ + EARLY_PUDS((vstart), (vend), add) /* each PUD needs a next level page table */ \ + EARLY_PMDS((vstart), (vend), add)) /* each PMD needs a next level page table */ -#define INIT_DIR_SIZE (PAGE_SIZE * EARLY_PAGES(KIMAGE_VADDR, _end, EXTRA_PAGE)) +#define INIT_DIR_SIZE (PAGE_SIZE * (EARLY_PAGES(KIMAGE_VADDR, _end, EXTRA_PAGE) + EARLY_SEGMENT_EXTRA_PAGES)) /* the initial ID map may need two extra pages if it needs to be extended */ #if VA_BITS < 48 @@ -89,6 +89,15 @@ #define SWAPPER_TABLE_SHIFT PMD_SHIFT #endif +/* The number of segments in the kernel image (text, rodata, inittext, initdata, data+bss) */ +#define KERNEL_SEGMENT_COUNT 5 + +#if SWAPPER_BLOCK_SIZE > SEGMENT_ALIGN +#define EARLY_SEGMENT_EXTRA_PAGES (KERNEL_SEGMENT_COUNT + 1) +#else +#define EARLY_SEGMENT_EXTRA_PAGES 0 +#endif + /* * Initial memory map attributes. */ -- cgit v1.2.3 From aa6a52b2470c375ecd71b1d81c89d93b11134b56 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:01 +0100 Subject: arm64: head: move memstart_offset_seed handling to C code Now that we can set BSS variables from the early code running from the ID map, we can set memstart_offset_seed directly from the C code that derives the value instead of passing it back and forth between C and asm code. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-60-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/head.S | 7 ------- arch/arm64/kernel/image-vars.h | 1 + arch/arm64/kernel/pi/kaslr_early.c | 4 ++++ 3 files changed, 5 insertions(+), 7 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index b320702032a7..aa7766dc64d9 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -82,7 +82,6 @@ * x21 primary_entry() .. start_kernel() FDT pointer passed at boot in x0 * x22 create_idmap() .. start_kernel() ID map VA of the DT blob * x23 __primary_switch() physical misalignment/KASLR offset - * x24 __primary_switch() linear map KASLR seed * x25 primary_entry() .. start_kernel() supported VA size * x28 create_idmap() callee preserved temp register */ @@ -483,11 +482,6 @@ SYM_FUNC_START_LOCAL(__primary_switched) str x25, [x8] // ... observes the correct value dc civac, x8 // Make visible to booting secondaries #endif - -#ifdef CONFIG_RANDOMIZE_BASE - adrp x5, memstart_offset_seed // Save KASLR linear map seed - strh w24, [x5, :lo12:memstart_offset_seed] -#endif #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) bl kasan_early_init #endif @@ -779,7 +773,6 @@ SYM_FUNC_START_LOCAL(__primary_switch) #ifdef CONFIG_RANDOMIZE_BASE mov x0, x22 bl __pi_kaslr_early_init - and x24, x0, #SZ_2M - 1 // capture memstart offset seed bic x0, x0, #SZ_2M - 1 orr x23, x23, x0 // record kernel offset #endif diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index eacc3d167733..8d96052079e8 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -46,6 +46,7 @@ PROVIDE(__pi_id_aa64smfr0_override = id_aa64smfr0_override); PROVIDE(__pi_id_aa64zfr0_override = id_aa64zfr0_override); PROVIDE(__pi_arm64_sw_feature_override = arm64_sw_feature_override); PROVIDE(__pi__ctype = _ctype); +PROVIDE(__pi_memstart_offset_seed = memstart_offset_seed); #ifdef CONFIG_KVM diff --git a/arch/arm64/kernel/pi/kaslr_early.c b/arch/arm64/kernel/pi/kaslr_early.c index f2305e276ec3..eeecee7ffd6f 100644 --- a/arch/arm64/kernel/pi/kaslr_early.c +++ b/arch/arm64/kernel/pi/kaslr_early.c @@ -16,6 +16,8 @@ #include #include +extern u16 memstart_offset_seed; + static u64 __init get_kaslr_seed(void *fdt) { static char const chosen_str[] __initconst = "chosen"; @@ -51,6 +53,8 @@ asmlinkage u64 __init kaslr_early_init(void *fdt) return 0; } + memstart_offset_seed = seed & U16_MAX; + /* * OK, so we are proceeding with KASLR enabled. Calculate a suitable * kernel image offset from the seed. Let's place the kernel in the -- cgit v1.2.3 From 293d865f0af58e6ff2ff0ba0e890674e00d036b1 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:02 +0100 Subject: arm64: mm: Make kaslr_requires_kpti() a static inline In preparation for moving the first assignment of arm64_use_ng_mappings to an earlier stage in the boot, ensure that kaslr_requires_kpti() is accessible without relying on the core kernel's view on whether or not KASLR is enabled. So make it a static inline, and move the kaslr_enabled() check out of it and into the callers, one of which will disappear in a subsequent patch. Once/when support for the obsolete ThunderX 1 platform is dropped, this check reduces to a E0PD feature check on the local CPU. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-61-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/mmu.h | 38 +++++++++++++++++++++++++++++++++++++- arch/arm64/kernel/cpufeature.c | 42 +----------------------------------------- arch/arm64/kernel/setup.c | 2 +- 3 files changed, 39 insertions(+), 43 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index 2fcf51231d6e..d0b8b4b413b6 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -71,7 +71,43 @@ extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, pgprot_t prot, bool page_mappings_only); extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot); extern void mark_linear_text_alias_ro(void); -extern bool kaslr_requires_kpti(void); + +/* + * This check is triggered during the early boot before the cpufeature + * is initialised. Checking the status on the local CPU allows the boot + * CPU to detect the need for non-global mappings and thus avoiding a + * pagetable re-write after all the CPUs are booted. This check will be + * anyway run on individual CPUs, allowing us to get the consistent + * state once the SMP CPUs are up and thus make the switch to non-global + * mappings if required. + */ +static inline bool kaslr_requires_kpti(void) +{ + /* + * E0PD does a similar job to KPTI so can be used instead + * where available. + */ + if (IS_ENABLED(CONFIG_ARM64_E0PD)) { + u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); + if (cpuid_feature_extract_unsigned_field(mmfr2, + ID_AA64MMFR2_EL1_E0PD_SHIFT)) + return false; + } + + /* + * Systems affected by Cavium erratum 24756 are incompatible + * with KPTI. + */ + if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) { + extern const struct midr_range cavium_erratum_27456_cpus[]; + + if (is_midr_in_range_list(read_cpuid_id(), + cavium_erratum_27456_cpus)) + return false; + } + + return true; +} #define INIT_MM_CONTEXT(name) \ .pgd = init_pg_dir, diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index d0ffb872a31a..7064cf13f226 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1620,46 +1620,6 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope) return has_cpuid_feature(entry, scope); } -/* - * This check is triggered during the early boot before the cpufeature - * is initialised. Checking the status on the local CPU allows the boot - * CPU to detect the need for non-global mappings and thus avoiding a - * pagetable re-write after all the CPUs are booted. This check will be - * anyway run on individual CPUs, allowing us to get the consistent - * state once the SMP CPUs are up and thus make the switch to non-global - * mappings if required. - */ -bool kaslr_requires_kpti(void) -{ - if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) - return false; - - /* - * E0PD does a similar job to KPTI so can be used instead - * where available. - */ - if (IS_ENABLED(CONFIG_ARM64_E0PD)) { - u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); - if (cpuid_feature_extract_unsigned_field(mmfr2, - ID_AA64MMFR2_EL1_E0PD_SHIFT)) - return false; - } - - /* - * Systems affected by Cavium erratum 24756 are incompatible - * with KPTI. - */ - if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) { - extern const struct midr_range cavium_erratum_27456_cpus[]; - - if (is_midr_in_range_list(read_cpuid_id(), - cavium_erratum_27456_cpus)) - return false; - } - - return kaslr_enabled(); -} - static bool __meltdown_safe = true; static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */ @@ -1712,7 +1672,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, } /* Useful for KASLR robustness */ - if (kaslr_requires_kpti()) { + if (kaslr_enabled() && kaslr_requires_kpti()) { if (!__kpti_forced) { str = "KASLR"; __kpti_forced = 1; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 97d2143669cf..0ef45d1927b3 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -288,7 +288,7 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) * mappings from the start, avoiding the cost of rewriting * everything later. */ - arm64_use_ng_mappings = kaslr_requires_kpti(); + arm64_use_ng_mappings = kaslr_enabled() && kaslr_requires_kpti(); early_fixmap_init(); early_ioremap_init(); -- cgit v1.2.3 From 82ca151da7d54d7571c5d511d016b7780d5d559f Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:03 +0100 Subject: arm64: mmu: Make __cpu_replace_ttbr1() out of line __cpu_replace_ttbr1() is a static inline, and so it gets instantiated wherever it is used. This is not really necessary, as it is never called on a hot path. It also has the unfortunate side effect that the symbol idmap_cpu_replace_ttbr1 may never be referenced from kCFI enabled C code, and this means the type id symbol may not exist either. This will result in a build error once we start referring to this symbol from asm code as well. (Note that this problem only occurs when CnP, KAsan and suspend/resume are all disabled in the Kconfig but that is a valid config, if unusual). So let's just move it out of line so all callers will share the same implementation, which will reference idmap_cpu_replace_ttbr1 unconditionally. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-62-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/mmu_context.h | 32 +------------------------------- arch/arm64/mm/mmu.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 33 insertions(+), 31 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 9ce4200508b1..926fbbcecbe0 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -148,37 +148,7 @@ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz) isb(); } -/* - * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, - * avoiding the possibility of conflicting TLB entries being allocated. - */ -static inline void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp) -{ - typedef void (ttbr_replace_func)(phys_addr_t); - extern ttbr_replace_func idmap_cpu_replace_ttbr1; - ttbr_replace_func *replace_phys; - unsigned long daif; - - /* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */ - phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp)); - - if (cnp) - ttbr1 |= TTBR_CNP_BIT; - - replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); - - __cpu_install_idmap(idmap); - - /* - * We really don't want to take *any* exceptions while TTBR1 is - * in the process of being replaced so mask everything. - */ - daif = local_daif_save(); - replace_phys(ttbr1); - local_daif_restore(daif); - - cpu_uninstall_idmap(); -} +void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp); static inline void cpu_enable_swapper_cnp(void) { diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 1ac7467d34c9..f9332eea318f 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1486,3 +1486,35 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte { set_pte_at(vma->vm_mm, addr, ptep, pte); } + +/* + * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, + * avoiding the possibility of conflicting TLB entries being allocated. + */ +void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp) +{ + typedef void (ttbr_replace_func)(phys_addr_t); + extern ttbr_replace_func idmap_cpu_replace_ttbr1; + ttbr_replace_func *replace_phys; + unsigned long daif; + + /* phys_to_ttbr() zeros lower 2 bits of ttbr with 52-bit PA */ + phys_addr_t ttbr1 = phys_to_ttbr(virt_to_phys(pgdp)); + + if (cnp) + ttbr1 |= TTBR_CNP_BIT; + + replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); + + __cpu_install_idmap(idmap); + + /* + * We really don't want to take *any* exceptions while TTBR1 is + * in the process of being replaced so mask everything. + */ + daif = local_daif_save(); + replace_phys(ttbr1); + local_daif_restore(daif); + + cpu_uninstall_idmap(); +} -- cgit v1.2.3 From 97a6f43bb049e64b9913c50c7530e13d78e205d4 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:04 +0100 Subject: arm64: head: Move early kernel mapping routines into C code The asm version of the kernel mapping code works fine for creating a coarse grained identity map, but for mapping the kernel down to its exact boundaries with the right attributes, it is not suitable. This is why we create a preliminary RWX kernel mapping first, and then rebuild it from scratch later on. So let's reimplement this in C, in a way that will make it unnecessary to create the kernel page tables yet another time in paging_init(). Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-63-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/archrandom.h | 2 - arch/arm64/include/asm/scs.h | 32 +------ arch/arm64/kernel/head.S | 52 +---------- arch/arm64/kernel/image-vars.h | 19 ++++ arch/arm64/kernel/pi/Makefile | 1 + arch/arm64/kernel/pi/idreg-override.c | 22 +++-- arch/arm64/kernel/pi/kaslr_early.c | 12 +-- arch/arm64/kernel/pi/map_kernel.c | 164 ++++++++++++++++++++++++++++++++++ arch/arm64/kernel/pi/map_range.c | 88 ++++++++++++++++++ arch/arm64/kernel/pi/patch-scs.c | 16 +--- arch/arm64/kernel/pi/pi.h | 14 +++ arch/arm64/kernel/pi/relocate.c | 2 + arch/arm64/kernel/setup.c | 7 -- arch/arm64/kernel/vmlinux.lds.S | 4 +- arch/arm64/mm/proc.S | 1 + 15 files changed, 315 insertions(+), 121 deletions(-) create mode 100644 arch/arm64/kernel/pi/map_kernel.c create mode 100644 arch/arm64/kernel/pi/map_range.c (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/archrandom.h b/arch/arm64/include/asm/archrandom.h index ecdb3cfcd0f8..8babfbe31f95 100644 --- a/arch/arm64/include/asm/archrandom.h +++ b/arch/arm64/include/asm/archrandom.h @@ -129,6 +129,4 @@ static inline bool __init __early_cpu_has_rndr(void) return (ftr >> ID_AA64ISAR0_EL1_RNDR_SHIFT) & 0xf; } -u64 kaslr_early_init(void *fdt); - #endif /* _ASM_ARCHRANDOM_H */ diff --git a/arch/arm64/include/asm/scs.h b/arch/arm64/include/asm/scs.h index eca2ba5a6276..2e010ea76be2 100644 --- a/arch/arm64/include/asm/scs.h +++ b/arch/arm64/include/asm/scs.h @@ -33,37 +33,11 @@ #include #ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS -static inline bool should_patch_pac_into_scs(void) -{ - u64 reg; - - /* - * We only enable the shadow call stack dynamically if we are running - * on a system that does not implement PAC or BTI. PAC and SCS provide - * roughly the same level of protection, and BTI relies on the PACIASP - * instructions serving as landing pads, preventing us from patching - * those instructions into something else. - */ - reg = read_sysreg_s(SYS_ID_AA64ISAR1_EL1); - if (SYS_FIELD_GET(ID_AA64ISAR1_EL1, APA, reg) | - SYS_FIELD_GET(ID_AA64ISAR1_EL1, API, reg)) - return false; - - reg = read_sysreg_s(SYS_ID_AA64ISAR2_EL1); - if (SYS_FIELD_GET(ID_AA64ISAR2_EL1, APA3, reg)) - return false; - - if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) { - reg = read_sysreg_s(SYS_ID_AA64PFR1_EL1); - if (reg & (0xf << ID_AA64PFR1_EL1_BT_SHIFT)) - return false; - } - return true; -} - static inline void dynamic_scs_init(void) { - if (should_patch_pac_into_scs()) { + extern bool __pi_dynamic_scs_is_enabled; + + if (__pi_dynamic_scs_is_enabled) { pr_info("Enabling dynamic shadow call stack\n"); static_branch_enable(&dynamic_scs_enabled); } diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index aa7766dc64d9..ffacce7b5a02 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -81,7 +81,6 @@ * x20 primary_entry() .. __primary_switch() CPU boot mode * x21 primary_entry() .. start_kernel() FDT pointer passed at boot in x0 * x22 create_idmap() .. start_kernel() ID map VA of the DT blob - * x23 __primary_switch() physical misalignment/KASLR offset * x25 primary_entry() .. start_kernel() supported VA size * x28 create_idmap() callee preserved temp register */ @@ -408,24 +407,6 @@ SYM_FUNC_START_LOCAL(create_idmap) 0: ret x28 SYM_FUNC_END(create_idmap) -SYM_FUNC_START_LOCAL(create_kernel_mapping) - adrp x0, init_pg_dir - mov_q x5, KIMAGE_VADDR // compile time __va(_text) -#ifdef CONFIG_RELOCATABLE - add x5, x5, x23 // add KASLR displacement -#endif - adrp x6, _end // runtime __pa(_end) - adrp x3, _text // runtime __pa(_text) - sub x6, x6, x3 // _end - _text - add x6, x6, x5 // runtime __va(_end) - mov_q x7, SWAPPER_RW_MMUFLAGS - - map_memory x0, x1, x5, x6, x7, x3, (VA_BITS - PGDIR_SHIFT), x10, x11, x12, x13, x14 - - dsb ishst // sync with page table walker - ret -SYM_FUNC_END(create_kernel_mapping) - /* * Initialize CPU registers with task-specific and cpu-specific context. * @@ -752,44 +733,13 @@ SYM_FUNC_START_LOCAL(__primary_switch) adrp x2, init_idmap_pg_dir bl __enable_mmu - // Clear BSS - adrp x0, __bss_start - mov x1, xzr - adrp x2, init_pg_end - sub x2, x2, x0 - bl __pi_memset - dsb ishst // Make zero page visible to PTW - adrp x1, early_init_stack mov sp, x1 mov x29, xzr mov x0, x20 // pass the full boot status mov x1, x22 // pass the low FDT mapping - bl __pi_init_feature_override // Parse cpu feature overrides - -#ifdef CONFIG_RELOCATABLE - adrp x23, KERNEL_START - and x23, x23, MIN_KIMG_ALIGN - 1 -#ifdef CONFIG_RANDOMIZE_BASE - mov x0, x22 - bl __pi_kaslr_early_init - bic x0, x0, #SZ_2M - 1 - orr x23, x23, x0 // record kernel offset -#endif -#endif - bl create_kernel_mapping + bl __pi_early_map_kernel // Map and relocate the kernel - adrp x1, init_pg_dir - load_ttbr1 x1, x1, x2 -#ifdef CONFIG_RELOCATABLE - mov x0, x23 - bl __pi_relocate_kernel -#endif -#ifdef CONFIG_UNWIND_PATCH_PAC_INTO_SCS - ldr x0, =__eh_frame_start - ldr x1, =__eh_frame_end - bl __pi_scs_patch_vmlinux -#endif ldr x8, =__primary_switched adrp x0, KERNEL_START // __pa(KERNEL_START) br x8 diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 8d96052079e8..e566b32f9c22 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -45,9 +45,28 @@ PROVIDE(__pi_id_aa64pfr1_override = id_aa64pfr1_override); PROVIDE(__pi_id_aa64smfr0_override = id_aa64smfr0_override); PROVIDE(__pi_id_aa64zfr0_override = id_aa64zfr0_override); PROVIDE(__pi_arm64_sw_feature_override = arm64_sw_feature_override); +PROVIDE(__pi_arm64_use_ng_mappings = arm64_use_ng_mappings); +#ifdef CONFIG_CAVIUM_ERRATUM_27456 +PROVIDE(__pi_cavium_erratum_27456_cpus = cavium_erratum_27456_cpus); +#endif PROVIDE(__pi__ctype = _ctype); PROVIDE(__pi_memstart_offset_seed = memstart_offset_seed); +PROVIDE(__pi_init_pg_dir = init_pg_dir); +PROVIDE(__pi_init_pg_end = init_pg_end); + +PROVIDE(__pi__text = _text); +PROVIDE(__pi__stext = _stext); +PROVIDE(__pi__etext = _etext); +PROVIDE(__pi___start_rodata = __start_rodata); +PROVIDE(__pi___inittext_begin = __inittext_begin); +PROVIDE(__pi___inittext_end = __inittext_end); +PROVIDE(__pi___initdata_begin = __initdata_begin); +PROVIDE(__pi___initdata_end = __initdata_end); +PROVIDE(__pi__data = _data); +PROVIDE(__pi___bss_start = __bss_start); +PROVIDE(__pi__end = _end); + #ifdef CONFIG_KVM /* diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile index a8b302245f15..8c2f80a46b93 100644 --- a/arch/arm64/kernel/pi/Makefile +++ b/arch/arm64/kernel/pi/Makefile @@ -39,6 +39,7 @@ $(obj)/lib-%.o: $(srctree)/lib/%.c FORCE $(call if_changed_rule,cc_o_c) obj-y := idreg-override.pi.o \ + map_kernel.pi.o map_range.pi.o \ lib-fdt.pi.o lib-fdt_ro.pi.o obj-$(CONFIG_RELOCATABLE) += relocate.pi.o obj-$(CONFIG_RANDOMIZE_BASE) += kaslr_early.pi.o diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c index e4bcabcc6860..1884bd936c0d 100644 --- a/arch/arm64/kernel/pi/idreg-override.c +++ b/arch/arm64/kernel/pi/idreg-override.c @@ -308,37 +308,35 @@ static __init void __parse_cmdline(const char *cmdline, bool parse_aliases) } while (1); } -static __init const u8 *get_bootargs_cmdline(const void *fdt) +static __init const u8 *get_bootargs_cmdline(const void *fdt, int node) { + static char const bootargs[] __initconst = "bootargs"; const u8 *prop; - int node; - node = fdt_path_offset(fdt, "/chosen"); if (node < 0) return NULL; - prop = fdt_getprop(fdt, node, "bootargs", NULL); + prop = fdt_getprop(fdt, node, bootargs, NULL); if (!prop) return NULL; return strlen(prop) ? prop : NULL; } -static __init void parse_cmdline(const void *fdt) +static __init void parse_cmdline(const void *fdt, int chosen) { - const u8 *prop = get_bootargs_cmdline(fdt); + static char const cmdline[] __initconst = CONFIG_CMDLINE; + const u8 *prop = get_bootargs_cmdline(fdt, chosen); if (IS_ENABLED(CONFIG_CMDLINE_FORCE) || !prop) - __parse_cmdline(CONFIG_CMDLINE, true); + __parse_cmdline(cmdline, true); if (!IS_ENABLED(CONFIG_CMDLINE_FORCE) && prop) __parse_cmdline(prop, true); } -/* Keep checkers quiet */ -void init_feature_override(u64 boot_status, const void *fdt); - -asmlinkage void __init init_feature_override(u64 boot_status, const void *fdt) +void __init init_feature_override(u64 boot_status, const void *fdt, + int chosen) { struct arm64_ftr_override *override; const struct ftr_set_desc *reg; @@ -354,7 +352,7 @@ asmlinkage void __init init_feature_override(u64 boot_status, const void *fdt) __boot_status = boot_status; - parse_cmdline(fdt); + parse_cmdline(fdt, chosen); for (i = 0; i < ARRAY_SIZE(regs); i++) { reg = prel64_pointer(regs[i].reg); diff --git a/arch/arm64/kernel/pi/kaslr_early.c b/arch/arm64/kernel/pi/kaslr_early.c index eeecee7ffd6f..0257b43819db 100644 --- a/arch/arm64/kernel/pi/kaslr_early.c +++ b/arch/arm64/kernel/pi/kaslr_early.c @@ -16,17 +16,17 @@ #include #include +#include "pi.h" + extern u16 memstart_offset_seed; -static u64 __init get_kaslr_seed(void *fdt) +static u64 __init get_kaslr_seed(void *fdt, int node) { - static char const chosen_str[] __initconst = "chosen"; static char const seed_str[] __initconst = "kaslr-seed"; - int node, len; fdt64_t *prop; u64 ret; + int len; - node = fdt_path_offset(fdt, chosen_str); if (node < 0) return 0; @@ -39,14 +39,14 @@ static u64 __init get_kaslr_seed(void *fdt) return ret; } -asmlinkage u64 __init kaslr_early_init(void *fdt) +u64 __init kaslr_early_init(void *fdt, int chosen) { u64 seed, range; if (kaslr_disabled_cmdline()) return 0; - seed = get_kaslr_seed(fdt); + seed = get_kaslr_seed(fdt, chosen); if (!seed) { if (!__early_cpu_has_rndr() || !__arm64_rndr((unsigned long *)&seed)) diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c new file mode 100644 index 000000000000..f206373b28b0 --- /dev/null +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -0,0 +1,164 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2023 Google LLC +// Author: Ard Biesheuvel + +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +#include "pi.h" + +extern const u8 __eh_frame_start[], __eh_frame_end[]; + +extern void idmap_cpu_replace_ttbr1(void *pgdir); + +static void __init map_segment(pgd_t *pg_dir, u64 *pgd, u64 va_offset, + void *start, void *end, pgprot_t prot, + bool may_use_cont, int root_level) +{ + map_range(pgd, ((u64)start + va_offset) & ~PAGE_OFFSET, + ((u64)end + va_offset) & ~PAGE_OFFSET, (u64)start, + prot, root_level, (pte_t *)pg_dir, may_use_cont, 0); +} + +static void __init unmap_segment(pgd_t *pg_dir, u64 va_offset, void *start, + void *end, int root_level) +{ + map_segment(pg_dir, NULL, va_offset, start, end, __pgprot(0), + false, root_level); +} + +static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level) +{ + bool enable_scs = IS_ENABLED(CONFIG_UNWIND_PATCH_PAC_INTO_SCS); + bool twopass = IS_ENABLED(CONFIG_RELOCATABLE); + u64 pgdp = (u64)init_pg_dir + PAGE_SIZE; + pgprot_t text_prot = PAGE_KERNEL_ROX; + pgprot_t data_prot = PAGE_KERNEL; + pgprot_t prot; + + /* + * External debuggers may need to write directly to the text mapping to + * install SW breakpoints. Allow this (only) when explicitly requested + * with rodata=off. + */ + if (arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF)) + text_prot = PAGE_KERNEL_EXEC; + + /* + * We only enable the shadow call stack dynamically if we are running + * on a system that does not implement PAC or BTI. PAC and SCS provide + * roughly the same level of protection, and BTI relies on the PACIASP + * instructions serving as landing pads, preventing us from patching + * those instructions into something else. + */ + if (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) && cpu_has_pac()) + enable_scs = false; + + if (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && cpu_has_bti()) { + enable_scs = false; + + /* + * If we have a CPU that supports BTI and a kernel built for + * BTI then mark the kernel executable text as guarded pages + * now so we don't have to rewrite the page tables later. + */ + text_prot = __pgprot_modify(text_prot, PTE_GP, PTE_GP); + } + + /* Map all code read-write on the first pass if needed */ + twopass |= enable_scs; + prot = twopass ? data_prot : text_prot; + + map_segment(init_pg_dir, &pgdp, va_offset, _stext, _etext, prot, + !twopass, root_level); + map_segment(init_pg_dir, &pgdp, va_offset, __start_rodata, + __inittext_begin, data_prot, false, root_level); + map_segment(init_pg_dir, &pgdp, va_offset, __inittext_begin, + __inittext_end, prot, false, root_level); + map_segment(init_pg_dir, &pgdp, va_offset, __initdata_begin, + __initdata_end, data_prot, false, root_level); + map_segment(init_pg_dir, &pgdp, va_offset, _data, _end, data_prot, + true, root_level); + dsb(ishst); + + idmap_cpu_replace_ttbr1(init_pg_dir); + + if (twopass) { + if (IS_ENABLED(CONFIG_RELOCATABLE)) + relocate_kernel(kaslr_offset); + + if (enable_scs) { + scs_patch(__eh_frame_start + va_offset, + __eh_frame_end - __eh_frame_start); + asm("ic ialluis"); + + dynamic_scs_is_enabled = true; + } + + /* + * Unmap the text region before remapping it, to avoid + * potential TLB conflicts when creating the contiguous + * descriptors. + */ + unmap_segment(init_pg_dir, va_offset, _stext, _etext, + root_level); + dsb(ishst); + isb(); + __tlbi(vmalle1); + isb(); + + /* + * Remap these segments with different permissions + * No new page table allocations should be needed + */ + map_segment(init_pg_dir, NULL, va_offset, _stext, _etext, + text_prot, true, root_level); + map_segment(init_pg_dir, NULL, va_offset, __inittext_begin, + __inittext_end, text_prot, false, root_level); + dsb(ishst); + } +} + +asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt) +{ + static char const chosen_str[] __initconst = "/chosen"; + u64 va_base, pa_base = (u64)&_text; + u64 kaslr_offset = pa_base % MIN_KIMG_ALIGN; + int root_level = 4 - CONFIG_PGTABLE_LEVELS; + int chosen; + + /* Clear BSS and the initial page tables */ + memset(__bss_start, 0, (u64)init_pg_end - (u64)__bss_start); + + /* Parse the command line for CPU feature overrides */ + chosen = fdt_path_offset(fdt, chosen_str); + init_feature_override(boot_status, fdt, chosen); + + /* + * The virtual KASLR displacement modulo 2MiB is decided by the + * physical placement of the image, as otherwise, we might not be able + * to create the early kernel mapping using 2 MiB block descriptors. So + * take the low bits of the KASLR offset from the physical address, and + * fill in the high bits from the seed. + */ + if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) { + u64 kaslr_seed = kaslr_early_init(fdt, chosen); + + if (kaslr_seed && kaslr_requires_kpti()) + arm64_use_ng_mappings = true; + + kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1); + } + + va_base = KIMAGE_VADDR + kaslr_offset; + map_kernel(kaslr_offset, va_base - pa_base, root_level); +} diff --git a/arch/arm64/kernel/pi/map_range.c b/arch/arm64/kernel/pi/map_range.c new file mode 100644 index 000000000000..c31feda18f47 --- /dev/null +++ b/arch/arm64/kernel/pi/map_range.c @@ -0,0 +1,88 @@ +// SPDX-License-Identifier: GPL-2.0-only +// Copyright 2023 Google LLC +// Author: Ard Biesheuvel + +#include +#include + +#include +#include +#include + +#include "pi.h" + +/** + * map_range - Map a contiguous range of physical pages into virtual memory + * + * @pte: Address of physical pointer to array of pages to + * allocate page tables from + * @start: Virtual address of the start of the range + * @end: Virtual address of the end of the range (exclusive) + * @pa: Physical address of the start of the range + * @prot: Access permissions of the range + * @level: Translation level for the mapping + * @tbl: The level @level page table to create the mappings in + * @may_use_cont: Whether the use of the contiguous attribute is allowed + * @va_offset: Offset between a physical page and its current mapping + * in the VA space + */ +void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot, + int level, pte_t *tbl, bool may_use_cont, u64 va_offset) +{ + u64 cmask = (level == 3) ? CONT_PTE_SIZE - 1 : U64_MAX; + u64 protval = pgprot_val(prot) & ~PTE_TYPE_MASK; + int lshift = (3 - level) * (PAGE_SHIFT - 3); + u64 lmask = (PAGE_SIZE << lshift) - 1; + + start &= PAGE_MASK; + pa &= PAGE_MASK; + + /* Advance tbl to the entry that covers start */ + tbl += (start >> (lshift + PAGE_SHIFT)) % PTRS_PER_PTE; + + /* + * Set the right block/page bits for this level unless we are + * clearing the mapping + */ + if (protval) + protval |= (level < 3) ? PMD_TYPE_SECT : PTE_TYPE_PAGE; + + while (start < end) { + u64 next = min((start | lmask) + 1, PAGE_ALIGN(end)); + + if (level < 3 && (start | next | pa) & lmask) { + /* + * This chunk needs a finer grained mapping. Create a + * table mapping if necessary and recurse. + */ + if (pte_none(*tbl)) { + *tbl = __pte(__phys_to_pte_val(*pte) | + PMD_TYPE_TABLE | PMD_TABLE_UXN); + *pte += PTRS_PER_PTE * sizeof(pte_t); + } + map_range(pte, start, next, pa, prot, level + 1, + (pte_t *)(__pte_to_phys(*tbl) + va_offset), + may_use_cont, va_offset); + } else { + /* + * Start a contiguous range if start and pa are + * suitably aligned + */ + if (((start | pa) & cmask) == 0 && may_use_cont) + protval |= PTE_CONT; + + /* + * Clear the contiguous attribute if the remaining + * range does not cover a contiguous block + */ + if ((end & ~cmask) <= start) + protval &= ~PTE_CONT; + + /* Put down a block or page mapping */ + *tbl = __pte(__phys_to_pte_val(pa) | protval); + } + pa += next - start; + start = next; + tbl++; + } +} diff --git a/arch/arm64/kernel/pi/patch-scs.c b/arch/arm64/kernel/pi/patch-scs.c index c65ef40d1e6b..49d8b40e61bc 100644 --- a/arch/arm64/kernel/pi/patch-scs.c +++ b/arch/arm64/kernel/pi/patch-scs.c @@ -11,6 +11,10 @@ #include +#include "pi.h" + +bool dynamic_scs_is_enabled; + // // This minimal DWARF CFI parser is partially based on the code in // arch/arc/kernel/unwind.c, and on the document below: @@ -46,8 +50,6 @@ #define DW_CFA_GNU_negative_offset_extended 0x2f #define DW_CFA_hi_user 0x3f -extern const u8 __eh_frame_start[], __eh_frame_end[]; - enum { PACIASP = 0xd503233f, AUTIASP = 0xd50323bf, @@ -250,13 +252,3 @@ int scs_patch(const u8 eh_frame[], int size) } return 0; } - -asmlinkage void __init scs_patch_vmlinux(const u8 start[], const u8 end[]) -{ - if (!should_patch_pac_into_scs()) - return; - - scs_patch(start, end - start); - asm("ic ialluis"); - isb(); -} diff --git a/arch/arm64/kernel/pi/pi.h b/arch/arm64/kernel/pi/pi.h index 7c2d9bbf0ff9..d307c58e9741 100644 --- a/arch/arm64/kernel/pi/pi.h +++ b/arch/arm64/kernel/pi/pi.h @@ -2,6 +2,8 @@ // Copyright 2023 Google LLC // Author: Ard Biesheuvel +#include + #define __prel64_initconst __section(".init.rodata.prel64") #define PREL64(type, name) union { type *name; prel64_t name ## _prel; } @@ -16,3 +18,15 @@ static inline void *prel64_to_pointer(const prel64_t *offset) return NULL; return (void *)offset + *offset; } + +extern bool dynamic_scs_is_enabled; + +void init_feature_override(u64 boot_status, const void *fdt, int chosen); +u64 kaslr_early_init(void *fdt, int chosen); +void relocate_kernel(u64 offset); +int scs_patch(const u8 eh_frame[], int size); + +void map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot, + int level, pte_t *tbl, bool may_use_cont, u64 va_offset); + +asmlinkage void early_map_kernel(u64 boot_status, void *fdt); diff --git a/arch/arm64/kernel/pi/relocate.c b/arch/arm64/kernel/pi/relocate.c index 1853408ea76b..2407d2696398 100644 --- a/arch/arm64/kernel/pi/relocate.c +++ b/arch/arm64/kernel/pi/relocate.c @@ -7,6 +7,8 @@ #include #include +#include "pi.h" + extern const Elf64_Rela rela_start[], rela_end[]; extern const u64 relr_start[], relr_end[]; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 0ef45d1927b3..0ea45b6d0177 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -283,13 +283,6 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) kaslr_init(); - /* - * If know now we are going to need KPTI then use non-global - * mappings from the start, avoiding the cost of rewriting - * everything later. - */ - arm64_use_ng_mappings = kaslr_enabled() && kaslr_requires_kpti(); - early_fixmap_init(); early_ioremap_init(); diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index 3afb4223a5e8..755a22d4f840 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -126,9 +126,9 @@ jiffies = jiffies_64; #ifdef CONFIG_UNWIND_TABLES #define UNWIND_DATA_SECTIONS \ .eh_frame : { \ - __eh_frame_start = .; \ + __pi___eh_frame_start = .; \ *(.eh_frame) \ - __eh_frame_end = .; \ + __pi___eh_frame_end = .; \ } #else #define UNWIND_DATA_SECTIONS diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index f66c37a1610e..7c1bdaf25408 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -195,6 +195,7 @@ SYM_TYPED_FUNC_START(idmap_cpu_replace_ttbr1) ret SYM_FUNC_END(idmap_cpu_replace_ttbr1) +SYM_FUNC_ALIAS(__pi_idmap_cpu_replace_ttbr1, idmap_cpu_replace_ttbr1) .popsection #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -- cgit v1.2.3 From e6128a8e523cfa8f46a1501e6432c37523b47bdf Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:05 +0100 Subject: arm64: mm: Use 48-bit virtual addressing for the permanent ID map Even though we support loading kernels anywhere in 48-bit addressable physical memory, we create the ID maps based on the number of levels that we happened to configure for the kernel VA and user VA spaces. The reason for this is that the PGD/PUD/PMD based classification of translation levels, along with the associated folding when the number of levels is less than 5, does not permit creating a page table hierarchy of a set number of levels. This means that, for instance, on 39-bit VA kernels we need to configure an additional level above PGD level on the fly, and 36-bit VA kernels still only support 47-bit virtual addressing with this trick applied. Now that we have a separate helper to populate page table hierarchies that does not define the levels in terms of PUDS/PMDS/etc at all, let's reuse it to create the permanent ID map with a fixed VA size of 48 bits. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-64-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/kernel-pgtable.h | 3 +++ arch/arm64/kernel/head.S | 5 +++++ arch/arm64/kvm/mmu.c | 15 ++++----------- arch/arm64/mm/mmu.c | 32 +++++++++++++++++--------------- arch/arm64/mm/proc.S | 9 +++------ 5 files changed, 32 insertions(+), 32 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 0631604995ee..742a4b2778f7 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -35,6 +35,9 @@ #define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS) #endif +#define IDMAP_VA_BITS 48 +#define IDMAP_LEVELS ARM64_HW_PGTABLE_LEVELS(IDMAP_VA_BITS) +#define IDMAP_ROOT_LEVEL (4 - IDMAP_LEVELS) /* * A relocatable kernel may execute from an address that differs from the one at diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index ffacce7b5a02..a1c29d64e875 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -729,6 +729,11 @@ SYM_FUNC_START_LOCAL(__no_granule_support) SYM_FUNC_END(__no_granule_support) SYM_FUNC_START_LOCAL(__primary_switch) + mrs x1, tcr_el1 + mov x2, #64 - VA_BITS + tcr_set_t0sz x1, x2 + msr tcr_el1, x1 + adrp x1, reserved_pg_dir adrp x2, init_idmap_pg_dir bl __enable_mmu diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index d14504821b79..6fa9e816df40 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1874,16 +1874,9 @@ int __init kvm_mmu_init(u32 *hyp_va_bits) BUG_ON((hyp_idmap_start ^ (hyp_idmap_end - 1)) & PAGE_MASK); /* - * The ID map may be configured to use an extended virtual address - * range. This is only the case if system RAM is out of range for the - * currently configured page size and VA_BITS_MIN, in which case we will - * also need the extended virtual range for the HYP ID map, or we won't - * be able to enable the EL2 MMU. - * - * However, in some cases the ID map may be configured for fewer than - * the number of VA bits used by the regular kernel stage 1. This - * happens when VA_BITS=52 and the kernel image is placed in PA space - * below 48 bits. + * The ID map is always configured for 48 bits of translation, which + * may be fewer than the number of VA bits used by the regular kernel + * stage 1, when VA_BITS=52. * * At EL2, there is only one TTBR register, and we can't switch between * translation tables *and* update TCR_EL2.T0SZ at the same time. Bottom @@ -1894,7 +1887,7 @@ int __init kvm_mmu_init(u32 *hyp_va_bits) * 1 VA bits to assure that the hypervisor can both ID map its code page * and map any kernel memory. */ - idmap_bits = 64 - ((idmap_t0sz & TCR_T0SZ_MASK) >> TCR_T0SZ_OFFSET); + idmap_bits = IDMAP_VA_BITS; kernel_bits = vabits_actual; *hyp_va_bits = max(idmap_bits, kernel_bits); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index f9332eea318f..a991f195592b 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -757,22 +757,21 @@ static void __init map_kernel(pgd_t *pgdp) kasan_copy_shadow(pgdp); } +void __pi_map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot, + int level, pte_t *tbl, bool may_use_cont, u64 va_offset); + +static u8 idmap_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init, + kpti_ptes[IDMAP_LEVELS - 1][PAGE_SIZE] __aligned(PAGE_SIZE) __ro_after_init; + static void __init create_idmap(void) { u64 start = __pa_symbol(__idmap_text_start); - u64 size = __pa_symbol(__idmap_text_end) - start; - pgd_t *pgd = idmap_pg_dir; - u64 pgd_phys; - - /* check if we need an additional level of translation */ - if (VA_BITS < 48 && idmap_t0sz < (64 - VA_BITS_MIN)) { - pgd_phys = early_pgtable_alloc(PAGE_SHIFT); - set_pgd(&idmap_pg_dir[start >> VA_BITS], - __pgd(pgd_phys | P4D_TYPE_TABLE)); - pgd = __va(pgd_phys); - } - __create_pgd_mapping(pgd, start, start, size, PAGE_KERNEL_ROX, - early_pgtable_alloc, 0); + u64 end = __pa_symbol(__idmap_text_end); + u64 ptep = __pa_symbol(idmap_ptes); + + __pi_map_range(&ptep, start, end, start, PAGE_KERNEL_ROX, + IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false, + __phys_to_virt(ptep) - ptep); if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) { extern u32 __idmap_kpti_flag; @@ -782,8 +781,10 @@ static void __init create_idmap(void) * The KPTI G-to-nG conversion code needs a read-write mapping * of its synchronization flag in the ID map. */ - __create_pgd_mapping(pgd, pa, pa, sizeof(u32), PAGE_KERNEL, - early_pgtable_alloc, 0); + ptep = __pa_symbol(kpti_ptes); + __pi_map_range(&ptep, pa, pa + sizeof(u32), pa, PAGE_KERNEL, + IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false, + __phys_to_virt(ptep) - ptep); } } @@ -808,6 +809,7 @@ void __init paging_init(void) memblock_allow_resize(); create_idmap(); + idmap_t0sz = TCR_T0SZ(IDMAP_VA_BITS); } #ifdef CONFIG_MEMORY_HOTPLUG diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 7c1bdaf25408..47ede52bb900 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -421,9 +421,9 @@ SYM_FUNC_START(__cpu_setup) mair .req x17 tcr .req x16 mov_q mair, MAIR_EL1_SET - mov_q tcr, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \ - TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ - TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS + mov_q tcr, TCR_T0SZ(IDMAP_VA_BITS) | TCR_T1SZ(VA_BITS) | TCR_CACHE_FLAGS | \ + TCR_SMP_FLAGS | TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ + TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS tcr_clear_errata_bits tcr, x9, x5 @@ -431,10 +431,7 @@ SYM_FUNC_START(__cpu_setup) sub x9, xzr, x0 add x9, x9, #64 tcr_set_t1sz tcr, x9 -#else - idmap_get_t0sz x9 #endif - tcr_set_t0sz tcr, x9 /* * Set the IPS bits in TCR_EL1. -- cgit v1.2.3 From 34b98e55f6840cab938d480968c0f600a2ed97d5 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:06 +0100 Subject: arm64: pgtable: Decouple PGDIR size macros from PGD/PUD/PMD levels The mapping from PGD/PUD/PMD to levels and shifts is very confusing, given that, due to folding, the shifts may be equal for different levels, if the macros are even #define'd to begin with. In a subsequent patch, we will modify the ID mapping code to decouple the number of levels from the kernel's view of how these types are folded, so prepare for this by reformulating the macros without the use of these types. Instead, use SWAPPER_BLOCK_SHIFT as the base quantity, and derive it from either PAGE_SHIFT or PMD_SHIFT, which -if defined at all- are defined unambiguously for a given page size, regardless of the number of configured levels. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-65-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/kernel-pgtable.h | 65 ++++++++++----------------------- 1 file changed, 19 insertions(+), 46 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 742a4b2778f7..f1fc98a233d5 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -13,27 +13,22 @@ #include /* - * The linear mapping and the start of memory are both 2M aligned (per - * the arm64 booting.txt requirements). Hence we can use section mapping - * with 4K (section size = 2M) but not with 16K (section size = 32M) or - * 64K (section size = 512M). + * The physical and virtual addresses of the start of the kernel image are + * equal modulo 2 MiB (per the arm64 booting.txt requirements). Hence we can + * use section mapping with 4K (section size = 2M) but not with 16K (section + * size = 32M) or 64K (section size = 512M). */ - -/* - * The idmap and swapper page tables need some space reserved in the kernel - * image. Both require pgd, pud (4 levels only) and pmd tables to (section) - * map the kernel. With the 64K page configuration, swapper and idmap need to - * map to pte level. The swapper also maps the FDT (see __create_page_tables - * for more information). Note that the number of ID map translation levels - * could be increased on the fly if system RAM is out of reach for the default - * VA range, so pages required to map highest possible PA are reserved in all - * cases. - */ -#ifdef CONFIG_ARM64_4K_PAGES -#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - 1) +#if defined(PMD_SIZE) && PMD_SIZE <= MIN_KIMG_ALIGN +#define SWAPPER_BLOCK_SHIFT PMD_SHIFT +#define SWAPPER_SKIP_LEVEL 1 #else -#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS) +#define SWAPPER_BLOCK_SHIFT PAGE_SHIFT +#define SWAPPER_SKIP_LEVEL 0 #endif +#define SWAPPER_BLOCK_SIZE (UL(1) << SWAPPER_BLOCK_SHIFT) +#define SWAPPER_TABLE_SHIFT (SWAPPER_BLOCK_SHIFT + PAGE_SHIFT - 3) + +#define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - SWAPPER_SKIP_LEVEL) #define IDMAP_VA_BITS 48 #define IDMAP_LEVELS ARM64_HW_PGTABLE_LEVELS(IDMAP_VA_BITS) @@ -53,24 +48,13 @@ #define EARLY_ENTRIES(vstart, vend, shift, add) \ (SPAN_NR_ENTRIES(vstart, vend, shift) + (add)) -#define EARLY_PGDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PGDIR_SHIFT, add)) - -#if SWAPPER_PGTABLE_LEVELS > 3 -#define EARLY_PUDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, PUD_SHIFT, add)) -#else -#define EARLY_PUDS(vstart, vend, add) (0) -#endif +#define EARLY_LEVEL(lvl, vstart, vend, add) \ + (SWAPPER_PGTABLE_LEVELS > lvl ? EARLY_ENTRIES(vstart, vend, SWAPPER_BLOCK_SHIFT + lvl * (PAGE_SHIFT - 3), add) : 0) -#if SWAPPER_PGTABLE_LEVELS > 2 -#define EARLY_PMDS(vstart, vend, add) (EARLY_ENTRIES(vstart, vend, SWAPPER_TABLE_SHIFT, add)) -#else -#define EARLY_PMDS(vstart, vend, add) (0) -#endif - -#define EARLY_PAGES(vstart, vend, add) ( 1 /* PGDIR page */ \ - + EARLY_PGDS((vstart), (vend), add) /* each PGDIR needs a next level page table */ \ - + EARLY_PUDS((vstart), (vend), add) /* each PUD needs a next level page table */ \ - + EARLY_PMDS((vstart), (vend), add)) /* each PMD needs a next level page table */ +#define EARLY_PAGES(vstart, vend, add) (1 /* PGDIR page */ \ + + EARLY_LEVEL(3, (vstart), (vend), add) /* each entry needs a next level page table */ \ + + EARLY_LEVEL(2, (vstart), (vend), add) /* each entry needs a next level page table */ \ + + EARLY_LEVEL(1, (vstart), (vend), add))/* each entry needs a next level page table */ #define INIT_DIR_SIZE (PAGE_SIZE * (EARLY_PAGES(KIMAGE_VADDR, _end, EXTRA_PAGE) + EARLY_SEGMENT_EXTRA_PAGES)) /* the initial ID map may need two extra pages if it needs to be extended */ @@ -81,17 +65,6 @@ #endif #define INIT_IDMAP_DIR_PAGES EARLY_PAGES(KIMAGE_VADDR, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE, 1) -/* Initial memory map size */ -#ifdef CONFIG_ARM64_4K_PAGES -#define SWAPPER_BLOCK_SHIFT PMD_SHIFT -#define SWAPPER_BLOCK_SIZE PMD_SIZE -#define SWAPPER_TABLE_SHIFT PUD_SHIFT -#else -#define SWAPPER_BLOCK_SHIFT PAGE_SHIFT -#define SWAPPER_BLOCK_SIZE PAGE_SIZE -#define SWAPPER_TABLE_SHIFT PMD_SHIFT -#endif - /* The number of segments in the kernel image (text, rodata, inittext, initdata, data+bss) */ #define KERNEL_SEGMENT_COUNT 5 -- cgit v1.2.3 From 84b04d3e6bdbc7551e62b75dd97cae4a8bddb1b6 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:07 +0100 Subject: arm64: kernel: Create initial ID map from C code The asm code that creates the initial ID map is rather intricate and hard to follow. This is problematic because it makes adding support for things like LPA2 or WXN more difficult than necessary. Also, it is parameterized like the rest of the MM code to run with a configurable number of levels, which is rather pointless, given that all AArch64 CPUs implement support for 48-bit virtual addressing, and that many systems exist with DRAM located outside of the 39-bit addressable range, which is the only smaller VA size that is widely used, and we need additional tricks to make things work in that combination. So let's bite the bullet, and rip out all the asm macros, and fiddly code, and replace it with a C implementation based on the newly added routines for creating the early kernel VA mappings. And while at it, create the initial ID map based on 48-bit virtual addressing as well, regardless of the number of configured levels for the kernel proper. Note that this code may execute with the MMU and caches disabled, and is therefore not permitted to make unaligned accesses. This shouldn't generally happen in any case for the algorithm as implemented, but to be sure, let's pass -mstrict-align to the compiler just in case. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-66-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/assembler.h | 14 -- arch/arm64/include/asm/kernel-pgtable.h | 50 +++--- arch/arm64/include/asm/mmu_context.h | 6 +- arch/arm64/kernel/head.S | 267 +++----------------------------- arch/arm64/kernel/image-vars.h | 1 + arch/arm64/kernel/pi/Makefile | 3 + arch/arm64/kernel/pi/map_kernel.c | 18 +++ arch/arm64/kernel/pi/map_range.c | 12 ++ arch/arm64/kernel/pi/pi.h | 4 + arch/arm64/mm/mmu.c | 5 - arch/arm64/mm/proc.S | 3 +- 11 files changed, 88 insertions(+), 295 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 513787e43329..6a467c694039 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -345,20 +345,6 @@ alternative_cb_end bfi \valreg, \t1sz, #TCR_T1SZ_OFFSET, #TCR_TxSZ_WIDTH .endm -/* - * idmap_get_t0sz - get the T0SZ value needed to cover the ID map - * - * Calculate the maximum allowed value for TCR_EL1.T0SZ so that the - * entire ID map region can be mapped. As T0SZ == (64 - #bits used), - * this number conveniently equals the number of leading zeroes in - * the physical address of _end. - */ - .macro idmap_get_t0sz, reg - adrp \reg, _end - orr \reg, \reg, #(1 << VA_BITS_MIN) - 1 - clz \reg, \reg - .endm - /* * tcr_compute_pa_size - set TCR.(I)PS to the highest supported * ID_AA64MMFR0_EL1.PARange value diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index f1fc98a233d5..bf05a77873a4 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -29,6 +29,7 @@ #define SWAPPER_TABLE_SHIFT (SWAPPER_BLOCK_SHIFT + PAGE_SHIFT - 3) #define SWAPPER_PGTABLE_LEVELS (CONFIG_PGTABLE_LEVELS - SWAPPER_SKIP_LEVEL) +#define INIT_IDMAP_PGTABLE_LEVELS (IDMAP_LEVELS - SWAPPER_SKIP_LEVEL) #define IDMAP_VA_BITS 48 #define IDMAP_LEVELS ARM64_HW_PGTABLE_LEVELS(IDMAP_VA_BITS) @@ -48,44 +49,39 @@ #define EARLY_ENTRIES(vstart, vend, shift, add) \ (SPAN_NR_ENTRIES(vstart, vend, shift) + (add)) -#define EARLY_LEVEL(lvl, vstart, vend, add) \ - (SWAPPER_PGTABLE_LEVELS > lvl ? EARLY_ENTRIES(vstart, vend, SWAPPER_BLOCK_SHIFT + lvl * (PAGE_SHIFT - 3), add) : 0) +#define EARLY_LEVEL(lvl, lvls, vstart, vend, add) \ + (lvls > lvl ? EARLY_ENTRIES(vstart, vend, SWAPPER_BLOCK_SHIFT + lvl * (PAGE_SHIFT - 3), add) : 0) -#define EARLY_PAGES(vstart, vend, add) (1 /* PGDIR page */ \ - + EARLY_LEVEL(3, (vstart), (vend), add) /* each entry needs a next level page table */ \ - + EARLY_LEVEL(2, (vstart), (vend), add) /* each entry needs a next level page table */ \ - + EARLY_LEVEL(1, (vstart), (vend), add))/* each entry needs a next level page table */ -#define INIT_DIR_SIZE (PAGE_SIZE * (EARLY_PAGES(KIMAGE_VADDR, _end, EXTRA_PAGE) + EARLY_SEGMENT_EXTRA_PAGES)) +#define EARLY_PAGES(lvls, vstart, vend, add) (1 /* PGDIR page */ \ + + EARLY_LEVEL(3, (lvls), (vstart), (vend), add) /* each entry needs a next level page table */ \ + + EARLY_LEVEL(2, (lvls), (vstart), (vend), add) /* each entry needs a next level page table */ \ + + EARLY_LEVEL(1, (lvls), (vstart), (vend), add))/* each entry needs a next level page table */ +#define INIT_DIR_SIZE (PAGE_SIZE * (EARLY_PAGES(SWAPPER_PGTABLE_LEVELS, KIMAGE_VADDR, _end, EXTRA_PAGE) \ + + EARLY_SEGMENT_EXTRA_PAGES)) -/* the initial ID map may need two extra pages if it needs to be extended */ -#if VA_BITS < 48 -#define INIT_IDMAP_DIR_SIZE ((INIT_IDMAP_DIR_PAGES + 2) * PAGE_SIZE) -#else -#define INIT_IDMAP_DIR_SIZE (INIT_IDMAP_DIR_PAGES * PAGE_SIZE) -#endif -#define INIT_IDMAP_DIR_PAGES EARLY_PAGES(KIMAGE_VADDR, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE, 1) +#define INIT_IDMAP_DIR_PAGES (EARLY_PAGES(INIT_IDMAP_PGTABLE_LEVELS, KIMAGE_VADDR, _end, 1)) +#define INIT_IDMAP_DIR_SIZE ((INIT_IDMAP_DIR_PAGES + EARLY_IDMAP_EXTRA_PAGES) * PAGE_SIZE) + +#define INIT_IDMAP_FDT_PAGES (EARLY_PAGES(INIT_IDMAP_PGTABLE_LEVELS, 0UL, UL(MAX_FDT_SIZE), 1) - 1) +#define INIT_IDMAP_FDT_SIZE ((INIT_IDMAP_FDT_PAGES + EARLY_IDMAP_EXTRA_FDT_PAGES) * PAGE_SIZE) /* The number of segments in the kernel image (text, rodata, inittext, initdata, data+bss) */ #define KERNEL_SEGMENT_COUNT 5 #if SWAPPER_BLOCK_SIZE > SEGMENT_ALIGN #define EARLY_SEGMENT_EXTRA_PAGES (KERNEL_SEGMENT_COUNT + 1) -#else -#define EARLY_SEGMENT_EXTRA_PAGES 0 -#endif - /* - * Initial memory map attributes. + * The initial ID map consists of the kernel image, mapped as two separate + * segments, and may appear misaligned wrt the swapper block size. This means + * we need 3 additional pages. The DT could straddle a swapper block boundary, + * so it may need 2. */ -#define SWAPPER_PTE_FLAGS (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED | PTE_UXN) -#define SWAPPER_PMD_FLAGS (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S | PTE_UXN) - -#ifdef CONFIG_ARM64_4K_PAGES -#define SWAPPER_RW_MMUFLAGS (PMD_ATTRINDX(MT_NORMAL) | SWAPPER_PMD_FLAGS | PTE_WRITE) -#define SWAPPER_RX_MMUFLAGS (SWAPPER_RW_MMUFLAGS | PMD_SECT_RDONLY) +#define EARLY_IDMAP_EXTRA_PAGES 3 +#define EARLY_IDMAP_EXTRA_FDT_PAGES 2 #else -#define SWAPPER_RW_MMUFLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS | PTE_WRITE) -#define SWAPPER_RX_MMUFLAGS (SWAPPER_RW_MMUFLAGS | PTE_RDONLY) +#define EARLY_SEGMENT_EXTRA_PAGES 0 +#define EARLY_IDMAP_EXTRA_PAGES 0 +#define EARLY_IDMAP_EXTRA_FDT_PAGES 0 #endif #endif /* __ASM_KERNEL_PGTABLE_H */ diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index 926fbbcecbe0..a8a89a0f2867 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -61,11 +61,9 @@ static inline void cpu_switch_mm(pgd_t *pgd, struct mm_struct *mm) } /* - * TCR.T0SZ value to use when the ID map is active. Usually equals - * TCR_T0SZ(VA_BITS), unless system RAM is positioned very high in - * physical memory, in which case it will be smaller. + * TCR.T0SZ value to use when the ID map is active. */ -extern int idmap_t0sz; +#define idmap_t0sz TCR_T0SZ(IDMAP_VA_BITS) /* * Ensure TCR.T0SZ is set to the provided value. diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index a1c29d64e875..545b5d8976f4 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -80,26 +80,42 @@ * x19 primary_entry() .. start_kernel() whether we entered with the MMU on * x20 primary_entry() .. __primary_switch() CPU boot mode * x21 primary_entry() .. start_kernel() FDT pointer passed at boot in x0 - * x22 create_idmap() .. start_kernel() ID map VA of the DT blob * x25 primary_entry() .. start_kernel() supported VA size - * x28 create_idmap() callee preserved temp register */ SYM_CODE_START(primary_entry) bl record_mmu_state bl preserve_boot_args - bl create_idmap + + adrp x1, early_init_stack + mov sp, x1 + mov x29, xzr + adrp x0, init_idmap_pg_dir + bl __pi_create_init_idmap + + /* + * If the page tables have been populated with non-cacheable + * accesses (MMU disabled), invalidate those tables again to + * remove any speculatively loaded cache lines. + */ + cbnz x19, 0f + dmb sy + mov x1, x0 // end of used region + adrp x0, init_idmap_pg_dir + adr_l x2, dcache_inval_poc + blr x2 + b 1f /* * If we entered with the MMU and caches on, clean the ID mapped part * of the primary boot code to the PoC so we can safely execute it with * the MMU off. */ - cbz x19, 0f - adrp x0, __idmap_text_start +0: adrp x0, __idmap_text_start adr_l x1, __idmap_text_end adr_l x2, dcache_clean_poc blr x2 -0: mov x0, x19 + +1: mov x0, x19 bl init_kernel_el // w0=cpu_boot_mode mov x20, x0 @@ -175,238 +191,6 @@ SYM_CODE_START_LOCAL(preserve_boot_args) ret SYM_CODE_END(preserve_boot_args) -/* - * Macro to populate page table entries, these entries can be pointers to the next level - * or last level entries pointing to physical memory. - * - * tbl: page table address - * rtbl: pointer to page table or physical memory - * index: start index to write - * eindex: end index to write - [index, eindex] written to - * flags: flags for pagetable entry to or in - * inc: increment to rtbl between each entry - * tmp1: temporary variable - * - * Preserves: tbl, eindex, flags, inc - * Corrupts: index, tmp1 - * Returns: rtbl - */ - .macro populate_entries, tbl, rtbl, index, eindex, flags, inc, tmp1 -.Lpe\@: phys_to_pte \tmp1, \rtbl - orr \tmp1, \tmp1, \flags // tmp1 = table entry - str \tmp1, [\tbl, \index, lsl #3] - add \rtbl, \rtbl, \inc // rtbl = pa next level - add \index, \index, #1 - cmp \index, \eindex - b.ls .Lpe\@ - .endm - -/* - * Compute indices of table entries from virtual address range. If multiple entries - * were needed in the previous page table level then the next page table level is assumed - * to be composed of multiple pages. (This effectively scales the end index). - * - * vstart: virtual address of start of range - * vend: virtual address of end of range - we map [vstart, vend] - * shift: shift used to transform virtual address into index - * order: #imm 2log(number of entries in page table) - * istart: index in table corresponding to vstart - * iend: index in table corresponding to vend - * count: On entry: how many extra entries were required in previous level, scales - * our end index. - * On exit: returns how many extra entries required for next page table level - * - * Preserves: vstart, vend - * Returns: istart, iend, count - */ - .macro compute_indices, vstart, vend, shift, order, istart, iend, count - ubfx \istart, \vstart, \shift, \order - ubfx \iend, \vend, \shift, \order - add \iend, \iend, \count, lsl \order - sub \count, \iend, \istart - .endm - -/* - * Map memory for specified virtual address range. Each level of page table needed supports - * multiple entries. If a level requires n entries the next page table level is assumed to be - * formed from n pages. - * - * tbl: location of page table - * rtbl: address to be used for first level page table entry (typically tbl + PAGE_SIZE) - * vstart: virtual address of start of range - * vend: virtual address of end of range - we map [vstart, vend - 1] - * flags: flags to use to map last level entries - * phys: physical address corresponding to vstart - physical memory is contiguous - * order: #imm 2log(number of entries in PGD table) - * - * If extra_shift is set, an extra level will be populated if the end address does - * not fit in 'extra_shift' bits. This assumes vend is in the TTBR0 range. - * - * Temporaries: istart, iend, tmp, count, sv - these need to be different registers - * Preserves: vstart, flags - * Corrupts: tbl, rtbl, vend, istart, iend, tmp, count, sv - */ - .macro map_memory, tbl, rtbl, vstart, vend, flags, phys, order, istart, iend, tmp, count, sv, extra_shift - sub \vend, \vend, #1 - add \rtbl, \tbl, #PAGE_SIZE - mov \count, #0 - - .ifnb \extra_shift - tst \vend, #~((1 << (\extra_shift)) - 1) - b.eq .L_\@ - compute_indices \vstart, \vend, #\extra_shift, #(PAGE_SHIFT - 3), \istart, \iend, \count - mov \sv, \rtbl - populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp - mov \tbl, \sv - .endif -.L_\@: - compute_indices \vstart, \vend, #PGDIR_SHIFT, #\order, \istart, \iend, \count - mov \sv, \rtbl - populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp - mov \tbl, \sv - -#if SWAPPER_PGTABLE_LEVELS > 3 - compute_indices \vstart, \vend, #PUD_SHIFT, #(PAGE_SHIFT - 3), \istart, \iend, \count - mov \sv, \rtbl - populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp - mov \tbl, \sv -#endif - -#if SWAPPER_PGTABLE_LEVELS > 2 - compute_indices \vstart, \vend, #SWAPPER_TABLE_SHIFT, #(PAGE_SHIFT - 3), \istart, \iend, \count - mov \sv, \rtbl - populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp - mov \tbl, \sv -#endif - - compute_indices \vstart, \vend, #SWAPPER_BLOCK_SHIFT, #(PAGE_SHIFT - 3), \istart, \iend, \count - bic \rtbl, \phys, #SWAPPER_BLOCK_SIZE - 1 - populate_entries \tbl, \rtbl, \istart, \iend, \flags, #SWAPPER_BLOCK_SIZE, \tmp - .endm - -/* - * Remap a subregion created with the map_memory macro with modified attributes - * or output address. The entire remapped region must have been covered in the - * invocation of map_memory. - * - * x0: last level table address (returned in first argument to map_memory) - * x1: start VA of the existing mapping - * x2: start VA of the region to update - * x3: end VA of the region to update (exclusive) - * x4: start PA associated with the region to update - * x5: attributes to set on the updated region - * x6: order of the last level mappings - */ -SYM_FUNC_START_LOCAL(remap_region) - sub x3, x3, #1 // make end inclusive - - // Get the index offset for the start of the last level table - lsr x1, x1, x6 - bfi x1, xzr, #0, #PAGE_SHIFT - 3 - - // Derive the start and end indexes into the last level table - // associated with the provided region - lsr x2, x2, x6 - lsr x3, x3, x6 - sub x2, x2, x1 - sub x3, x3, x1 - - mov x1, #1 - lsl x6, x1, x6 // block size at this level - - populate_entries x0, x4, x2, x3, x5, x6, x7 - ret -SYM_FUNC_END(remap_region) - -SYM_FUNC_START_LOCAL(create_idmap) - mov x28, lr - /* - * The ID map carries a 1:1 mapping of the physical address range - * covered by the loaded image, which could be anywhere in DRAM. This - * means that the required size of the VA (== PA) space is decided at - * boot time, and could be more than the configured size of the VA - * space for ordinary kernel and user space mappings. - * - * There are three cases to consider here: - * - 39 <= VA_BITS < 48, and the ID map needs up to 48 VA bits to cover - * the placement of the image. In this case, we configure one extra - * level of translation on the fly for the ID map only. (This case - * also covers 42-bit VA/52-bit PA on 64k pages). - * - * - VA_BITS == 48, and the ID map needs more than 48 VA bits. This can - * only happen when using 64k pages, in which case we need to extend - * the root level table rather than add a level. Note that we can - * treat this case as 'always extended' as long as we take care not - * to program an unsupported T0SZ value into the TCR register. - * - * - Combinations that would require two additional levels of - * translation are not supported, e.g., VA_BITS==36 on 16k pages, or - * VA_BITS==39/4k pages with 5-level paging, where the input address - * requires more than 47 or 48 bits, respectively. - */ -#if (VA_BITS < 48) -#define IDMAP_PGD_ORDER (VA_BITS - PGDIR_SHIFT) -#define EXTRA_SHIFT (PGDIR_SHIFT + PAGE_SHIFT - 3) - - /* - * If VA_BITS < 48, we have to configure an additional table level. - * First, we have to verify our assumption that the current value of - * VA_BITS was chosen such that all translation levels are fully - * utilised, and that lowering T0SZ will always result in an additional - * translation level to be configured. - */ -#if VA_BITS != EXTRA_SHIFT -#error "Mismatch between VA_BITS and page size/number of translation levels" -#endif -#else -#define IDMAP_PGD_ORDER (PHYS_MASK_SHIFT - PGDIR_SHIFT) -#define EXTRA_SHIFT - /* - * If VA_BITS == 48, we don't have to configure an additional - * translation level, but the top-level table has more entries. - */ -#endif - adrp x0, init_idmap_pg_dir - adrp x3, _text - adrp x6, _end + MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE - mov_q x7, SWAPPER_RX_MMUFLAGS - - map_memory x0, x1, x3, x6, x7, x3, IDMAP_PGD_ORDER, x10, x11, x12, x13, x14, EXTRA_SHIFT - - /* Remap [.init].data, BSS and the kernel page tables r/w in the ID map */ - adrp x1, _text - adrp x2, __initdata_begin - adrp x3, _end - bic x4, x2, #SWAPPER_BLOCK_SIZE - 1 - mov_q x5, SWAPPER_RW_MMUFLAGS - mov x6, #SWAPPER_BLOCK_SHIFT - bl remap_region - - /* Remap the FDT after the kernel image */ - adrp x1, _text - adrp x22, _end + SWAPPER_BLOCK_SIZE - bic x2, x22, #SWAPPER_BLOCK_SIZE - 1 - bfi x22, x21, #0, #SWAPPER_BLOCK_SHIFT // remapped FDT address - add x3, x2, #MAX_FDT_SIZE + SWAPPER_BLOCK_SIZE - bic x4, x21, #SWAPPER_BLOCK_SIZE - 1 - mov_q x5, SWAPPER_RW_MMUFLAGS - mov x6, #SWAPPER_BLOCK_SHIFT - bl remap_region - - /* - * Since the page tables have been populated with non-cacheable - * accesses (MMU disabled), invalidate those tables again to - * remove any speculatively loaded cache lines. - */ - cbnz x19, 0f // skip cache invalidation if MMU is on - dmb sy - - adrp x0, init_idmap_pg_dir - adrp x1, init_idmap_pg_end - bl dcache_inval_poc -0: ret x28 -SYM_FUNC_END(create_idmap) - /* * Initialize CPU registers with task-specific and cpu-specific context. * @@ -729,11 +513,6 @@ SYM_FUNC_START_LOCAL(__no_granule_support) SYM_FUNC_END(__no_granule_support) SYM_FUNC_START_LOCAL(__primary_switch) - mrs x1, tcr_el1 - mov x2, #64 - VA_BITS - tcr_set_t0sz x1, x2 - msr tcr_el1, x1 - adrp x1, reserved_pg_dir adrp x2, init_idmap_pg_dir bl __enable_mmu @@ -742,7 +521,7 @@ SYM_FUNC_START_LOCAL(__primary_switch) mov sp, x1 mov x29, xzr mov x0, x20 // pass the full boot status - mov x1, x22 // pass the low FDT mapping + mov x1, x21 // pass the FDT bl __pi_early_map_kernel // Map and relocate the kernel ldr x8, =__primary_switched diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index e566b32f9c22..941a14c05184 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -52,6 +52,7 @@ PROVIDE(__pi_cavium_erratum_27456_cpus = cavium_erratum_27456_cpus); PROVIDE(__pi__ctype = _ctype); PROVIDE(__pi_memstart_offset_seed = memstart_offset_seed); +PROVIDE(__pi_init_idmap_pg_dir = init_idmap_pg_dir); PROVIDE(__pi_init_pg_dir = init_pg_dir); PROVIDE(__pi_init_pg_end = init_pg_end); diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile index 8c2f80a46b93..4393b41f0b71 100644 --- a/arch/arm64/kernel/pi/Makefile +++ b/arch/arm64/kernel/pi/Makefile @@ -11,6 +11,9 @@ KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \ -fno-asynchronous-unwind-tables -fno-unwind-tables \ $(call cc-option,-fno-addrsig) +# this code may run with the MMU off so disable unaligned accesses +CFLAGS_map_range.o += -mstrict-align + # remove SCS flags from all objects in this directory KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_SCS), $(KBUILD_CFLAGS)) # disable LTO diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c index f206373b28b0..f86e878d366d 100644 --- a/arch/arm64/kernel/pi/map_kernel.c +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -128,6 +128,22 @@ static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level) } } +static void __init map_fdt(u64 fdt) +{ + static u8 ptes[INIT_IDMAP_FDT_SIZE] __initdata __aligned(PAGE_SIZE); + u64 efdt = fdt + MAX_FDT_SIZE; + u64 ptep = (u64)ptes; + + /* + * Map up to MAX_FDT_SIZE bytes, but avoid overlap with + * the kernel image. + */ + map_range(&ptep, fdt, (u64)_text > fdt ? min((u64)_text, efdt) : efdt, + fdt, PAGE_KERNEL, IDMAP_ROOT_LEVEL, + (pte_t *)init_idmap_pg_dir, false, 0); + dsb(ishst); +} + asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt) { static char const chosen_str[] __initconst = "/chosen"; @@ -136,6 +152,8 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt) int root_level = 4 - CONFIG_PGTABLE_LEVELS; int chosen; + map_fdt((u64)fdt); + /* Clear BSS and the initial page tables */ memset(__bss_start, 0, (u64)init_pg_end - (u64)__bss_start); diff --git a/arch/arm64/kernel/pi/map_range.c b/arch/arm64/kernel/pi/map_range.c index c31feda18f47..79e4f6a2efe1 100644 --- a/arch/arm64/kernel/pi/map_range.c +++ b/arch/arm64/kernel/pi/map_range.c @@ -86,3 +86,15 @@ void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot, tbl++; } } + +asmlinkage u64 __init create_init_idmap(pgd_t *pg_dir) +{ + u64 ptep = (u64)pg_dir + PAGE_SIZE; + + map_range(&ptep, (u64)_stext, (u64)__initdata_begin, (u64)_stext, + PAGE_KERNEL_ROX, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0); + map_range(&ptep, (u64)__initdata_begin, (u64)_end, (u64)__initdata_begin, + PAGE_KERNEL, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0); + + return ptep; +} diff --git a/arch/arm64/kernel/pi/pi.h b/arch/arm64/kernel/pi/pi.h index d307c58e9741..1ea282a5f96a 100644 --- a/arch/arm64/kernel/pi/pi.h +++ b/arch/arm64/kernel/pi/pi.h @@ -21,6 +21,8 @@ static inline void *prel64_to_pointer(const prel64_t *offset) extern bool dynamic_scs_is_enabled; +extern pgd_t init_idmap_pg_dir[]; + void init_feature_override(u64 boot_status, const void *fdt, int chosen); u64 kaslr_early_init(void *fdt, int chosen); void relocate_kernel(u64 offset); @@ -30,3 +32,5 @@ void map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot, int level, pte_t *tbl, bool may_use_cont, u64 va_offset); asmlinkage void early_map_kernel(u64 boot_status, void *fdt); + +asmlinkage u64 create_init_idmap(pgd_t *pgd); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index a991f195592b..14a62c773201 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -45,8 +45,6 @@ #define NO_CONT_MAPPINGS BIT(1) #define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */ -int idmap_t0sz __ro_after_init; - #if VA_BITS > 48 u64 vabits_actual __ro_after_init = VA_BITS_MIN; EXPORT_SYMBOL(vabits_actual); @@ -793,8 +791,6 @@ void __init paging_init(void) pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir)); extern pgd_t init_idmap_pg_dir[]; - idmap_t0sz = 63UL - __fls(__pa_symbol(_end) | GENMASK(VA_BITS_MIN - 1, 0)); - map_kernel(pgdp); map_mem(pgdp); @@ -809,7 +805,6 @@ void __init paging_init(void) memblock_allow_resize(); create_idmap(); - idmap_t0sz = TCR_T0SZ(IDMAP_VA_BITS); } #ifdef CONFIG_MEMORY_HOTPLUG diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 47ede52bb900..55c366dbda8f 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -200,7 +200,8 @@ SYM_FUNC_ALIAS(__pi_idmap_cpu_replace_ttbr1, idmap_cpu_replace_ttbr1) #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -#define KPTI_NG_PTE_FLAGS (PTE_ATTRINDX(MT_NORMAL) | SWAPPER_PTE_FLAGS | PTE_WRITE) +#define KPTI_NG_PTE_FLAGS (PTE_ATTRINDX(MT_NORMAL) | PTE_TYPE_PAGE | \ + PTE_AF | PTE_SHARED | PTE_UXN | PTE_WRITE) .pushsection ".idmap.text", "a" -- cgit v1.2.3 From 567a70c181df72f3bb42ca825adb5de682713caa Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:08 +0100 Subject: arm64: mm: avoid fixmap for early swapper_pg_dir updates Early in the boot, when .rodata is still writable, we can poke swapper_pg_dir entries directly, and there is no need to go through the fixmap. After a future patch, we will enter the kernel with swapper_pg_dir already active, and early swapper_pg_dir updates for creating the fixmap page table hierarchy itself cannot go through the fixmap for obvious reaons. So let's keep track of whether rodata is writable, and update the descriptor directly in that case. As the same reasoning applies to early KASAN init, make the function noinstr as well. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-67-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/mm/mmu.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'arch/arm64') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 14a62c773201..9758f7e3f4b6 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -55,6 +55,8 @@ EXPORT_SYMBOL(kimage_voffset); u32 __boot_cpu_mode[] = { BOOT_CPU_MODE_EL2, BOOT_CPU_MODE_EL1 }; +static bool rodata_is_rw __ro_after_init = true; + /* * The booting CPU updates the failed status @__early_cpu_boot_status, * with MMU turned off. @@ -71,10 +73,21 @@ EXPORT_SYMBOL(empty_zero_page); static DEFINE_SPINLOCK(swapper_pgdir_lock); static DEFINE_MUTEX(fixmap_lock); -void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd) +void noinstr set_swapper_pgd(pgd_t *pgdp, pgd_t pgd) { pgd_t *fixmap_pgdp; + /* + * Don't bother with the fixmap if swapper_pg_dir is still mapped + * writable in the kernel mapping. + */ + if (rodata_is_rw) { + WRITE_ONCE(*pgdp, pgd); + dsb(ishst); + isb(); + return; + } + spin_lock(&swapper_pgdir_lock); fixmap_pgdp = pgd_set_fixmap(__pa_symbol(pgdp)); WRITE_ONCE(*fixmap_pgdp, pgd); @@ -628,6 +641,7 @@ void mark_rodata_ro(void) * to cover NOTES and EXCEPTION_TABLE. */ section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata; + WRITE_ONCE(rodata_is_rw, false); update_mapping_prot(__pa_symbol(__start_rodata), (unsigned long)__start_rodata, section_size, PAGE_KERNEL_RO); -- cgit v1.2.3 From ba5b0333a847ac026725122e085b2fea9e1674bc Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:09 +0100 Subject: arm64: mm: omit redundant remap of kernel image Now that the early kernel mapping is created with all the right attributes and segment boundaries, there is no longer a need to recreate it and switch to it. This also means we no longer have to copy the kasan shadow or some parts of the fixmap from one set of page tables to the other. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-68-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/fixmap.h | 1 - arch/arm64/include/asm/kasan.h | 2 - arch/arm64/include/asm/mmu.h | 2 +- arch/arm64/kernel/image-vars.h | 1 + arch/arm64/kernel/pi/map_kernel.c | 6 ++- arch/arm64/mm/fixmap.c | 34 ---------------- arch/arm64/mm/kasan_init.c | 15 ------- arch/arm64/mm/mmu.c | 85 +++++++-------------------------------- 8 files changed, 21 insertions(+), 125 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index 58c294a96676..8aabd45e9a13 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -100,7 +100,6 @@ enum fixed_addresses { #define FIXMAP_PAGE_IO __pgprot(PROT_DEVICE_nGnRE) void __init early_fixmap_init(void); -void __init fixmap_copy(pgd_t *pgdir); #define __early_set_fixmap __set_fixmap diff --git a/arch/arm64/include/asm/kasan.h b/arch/arm64/include/asm/kasan.h index 7eefc525a9df..e1b57c13f8a4 100644 --- a/arch/arm64/include/asm/kasan.h +++ b/arch/arm64/include/asm/kasan.h @@ -17,11 +17,9 @@ asmlinkage void kasan_early_init(void); void kasan_init(void); -void kasan_copy_shadow(pgd_t *pgdir); #else static inline void kasan_init(void) { } -static inline void kasan_copy_shadow(pgd_t *pgdir) { } #endif #endif diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index d0b8b4b413b6..65977c7783c5 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -110,7 +110,7 @@ static inline bool kaslr_requires_kpti(void) } #define INIT_MM_CONTEXT(name) \ - .pgd = init_pg_dir, + .pgd = swapper_pg_dir, #endif /* !__ASSEMBLY__ */ #endif diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 941a14c05184..e140c5bda90b 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -55,6 +55,7 @@ PROVIDE(__pi_memstart_offset_seed = memstart_offset_seed); PROVIDE(__pi_init_idmap_pg_dir = init_idmap_pg_dir); PROVIDE(__pi_init_pg_dir = init_pg_dir); PROVIDE(__pi_init_pg_end = init_pg_end); +PROVIDE(__pi_swapper_pg_dir = swapper_pg_dir); PROVIDE(__pi__text = _text); PROVIDE(__pi__stext = _stext); diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c index f86e878d366d..4b76a007a50d 100644 --- a/arch/arm64/kernel/pi/map_kernel.c +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -124,8 +124,12 @@ static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level) text_prot, true, root_level); map_segment(init_pg_dir, NULL, va_offset, __inittext_begin, __inittext_end, text_prot, false, root_level); - dsb(ishst); } + + /* Copy the root page table to its final location */ + memcpy((void *)swapper_pg_dir + va_offset, init_pg_dir, PGD_SIZE); + dsb(ishst); + idmap_cpu_replace_ttbr1(swapper_pg_dir); } static void __init map_fdt(u64 fdt) diff --git a/arch/arm64/mm/fixmap.c b/arch/arm64/mm/fixmap.c index 6fc17b2e1714..9404f282f829 100644 --- a/arch/arm64/mm/fixmap.c +++ b/arch/arm64/mm/fixmap.c @@ -170,37 +170,3 @@ void *__init fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot) return dt_virt; } - -/* - * Copy the fixmap region into a new pgdir. - */ -void __init fixmap_copy(pgd_t *pgdir) -{ - if (!READ_ONCE(pgd_val(*pgd_offset_pgd(pgdir, FIXADDR_TOT_START)))) { - /* - * The fixmap falls in a separate pgd to the kernel, and doesn't - * live in the carveout for the swapper_pg_dir. We can simply - * re-use the existing dir for the fixmap. - */ - set_pgd(pgd_offset_pgd(pgdir, FIXADDR_TOT_START), - READ_ONCE(*pgd_offset_k(FIXADDR_TOT_START))); - } else if (CONFIG_PGTABLE_LEVELS > 3) { - pgd_t *bm_pgdp; - p4d_t *bm_p4dp; - pud_t *bm_pudp; - /* - * The fixmap shares its top level pgd entry with the kernel - * mapping. This can really only occur when we are running - * with 16k/4 levels, so we can simply reuse the pud level - * entry instead. - */ - BUG_ON(!IS_ENABLED(CONFIG_ARM64_16K_PAGES)); - bm_pgdp = pgd_offset_pgd(pgdir, FIXADDR_TOT_START); - bm_p4dp = p4d_offset(bm_pgdp, FIXADDR_TOT_START); - bm_pudp = pud_set_fixmap_offset(bm_p4dp, FIXADDR_TOT_START); - pud_populate(&init_mm, bm_pudp, lm_alias(bm_pmd)); - pud_clear_fixmap(); - } else { - BUG(); - } -} diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 4c7ad574b946..89828ad2bca7 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -189,21 +189,6 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end, kasan_pgd_populate(start & PAGE_MASK, PAGE_ALIGN(end), node, false); } -/* - * Copy the current shadow region into a new pgdir. - */ -void __init kasan_copy_shadow(pgd_t *pgdir) -{ - pgd_t *pgdp, *pgdp_new, *pgdp_end; - - pgdp = pgd_offset_k(KASAN_SHADOW_START); - pgdp_end = pgd_offset_k(KASAN_SHADOW_END); - pgdp_new = pgd_offset_pgd(pgdir, KASAN_SHADOW_START); - do { - set_pgd(pgdp_new, READ_ONCE(*pgdp)); - } while (pgdp++, pgdp_new++, pgdp != pgdp_end); -} - static void __init clear_pgds(unsigned long start, unsigned long end) { diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 9758f7e3f4b6..3db40b517947 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -648,9 +648,9 @@ void mark_rodata_ro(void) debug_checkwx(); } -static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, - pgprot_t prot, struct vm_struct *vma, - int flags, unsigned long vm_flags) +static void __init declare_vma(struct vm_struct *vma, + void *va_start, void *va_end, + unsigned long vm_flags) { phys_addr_t pa_start = __pa_symbol(va_start); unsigned long size = va_end - va_start; @@ -658,9 +658,6 @@ static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, BUG_ON(!PAGE_ALIGNED(pa_start)); BUG_ON(!PAGE_ALIGNED(size)); - __create_pgd_mapping(pgdp, pa_start, (unsigned long)va_start, size, prot, - early_pgtable_alloc, flags); - if (!(vm_flags & VM_NO_GUARD)) size += PAGE_SIZE; @@ -673,12 +670,12 @@ static void __init map_kernel_segment(pgd_t *pgdp, void *va_start, void *va_end, vm_area_add_early(vma); } +#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 static pgprot_t kernel_exec_prot(void) { return rodata_enabled ? PAGE_KERNEL_ROX : PAGE_KERNEL_EXEC; } -#ifdef CONFIG_UNMAP_KERNEL_AT_EL0 static int __init map_entry_trampoline(void) { int i; @@ -713,60 +710,17 @@ core_initcall(map_entry_trampoline); #endif /* - * Open coded check for BTI, only for use to determine configuration - * for early mappings for before the cpufeature code has run. - */ -static bool arm64_early_this_cpu_has_bti(void) -{ - u64 pfr1; - - if (!IS_ENABLED(CONFIG_ARM64_BTI_KERNEL)) - return false; - - pfr1 = __read_sysreg_by_encoding(SYS_ID_AA64PFR1_EL1); - return cpuid_feature_extract_unsigned_field(pfr1, - ID_AA64PFR1_EL1_BT_SHIFT); -} - -/* - * Create fine-grained mappings for the kernel. + * Declare the VMA areas for the kernel */ -static void __init map_kernel(pgd_t *pgdp) +static void __init declare_kernel_vmas(void) { - static struct vm_struct vmlinux_text, vmlinux_rodata, vmlinux_inittext, - vmlinux_initdata, vmlinux_data; - - /* - * External debuggers may need to write directly to the text - * mapping to install SW breakpoints. Allow this (only) when - * explicitly requested with rodata=off. - */ - pgprot_t text_prot = kernel_exec_prot(); - - /* - * If we have a CPU that supports BTI and a kernel built for - * BTI then mark the kernel executable text as guarded pages - * now so we don't have to rewrite the page tables later. - */ - if (arm64_early_this_cpu_has_bti()) - text_prot = __pgprot_modify(text_prot, PTE_GP, PTE_GP); + static struct vm_struct vmlinux_seg[KERNEL_SEGMENT_COUNT]; - /* - * Only rodata will be remapped with different permissions later on, - * all other segments are allowed to use contiguous mappings. - */ - map_kernel_segment(pgdp, _stext, _etext, text_prot, &vmlinux_text, 0, - VM_NO_GUARD); - map_kernel_segment(pgdp, __start_rodata, __inittext_begin, PAGE_KERNEL, - &vmlinux_rodata, NO_CONT_MAPPINGS, VM_NO_GUARD); - map_kernel_segment(pgdp, __inittext_begin, __inittext_end, text_prot, - &vmlinux_inittext, 0, VM_NO_GUARD); - map_kernel_segment(pgdp, __initdata_begin, __initdata_end, PAGE_KERNEL, - &vmlinux_initdata, 0, VM_NO_GUARD); - map_kernel_segment(pgdp, _data, _end, PAGE_KERNEL, &vmlinux_data, 0, 0); - - fixmap_copy(pgdp); - kasan_copy_shadow(pgdp); + declare_vma(&vmlinux_seg[0], _stext, _etext, VM_NO_GUARD); + declare_vma(&vmlinux_seg[1], __start_rodata, __inittext_begin, VM_NO_GUARD); + declare_vma(&vmlinux_seg[2], __inittext_begin, __inittext_end, VM_NO_GUARD); + declare_vma(&vmlinux_seg[3], __initdata_begin, __initdata_end, VM_NO_GUARD); + declare_vma(&vmlinux_seg[4], _data, _end, 0); } void __pi_map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot, @@ -802,23 +756,12 @@ static void __init create_idmap(void) void __init paging_init(void) { - pgd_t *pgdp = pgd_set_fixmap(__pa_symbol(swapper_pg_dir)); - extern pgd_t init_idmap_pg_dir[]; - - map_kernel(pgdp); - map_mem(pgdp); - - pgd_clear_fixmap(); - - cpu_replace_ttbr1(lm_alias(swapper_pg_dir), init_idmap_pg_dir); - init_mm.pgd = swapper_pg_dir; - - memblock_phys_free(__pa_symbol(init_pg_dir), - __pa_symbol(init_pg_end) - __pa_symbol(init_pg_dir)); + map_mem(swapper_pg_dir); memblock_allow_resize(); create_idmap(); + declare_kernel_vmas(); } #ifdef CONFIG_MEMORY_HOTPLUG -- cgit v1.2.3 From e0f92f0d1b512cf11b918c5828e73d5df5b667cc Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:10 +0100 Subject: arm64: Revert "mm: provide idmap pointer to cpu_replace_ttbr1()" This reverts commit 1682c45b920643c, which is no longer needed now that we create the permanent kernel mapping directly during early boot. This is a RINO (revert in name only) given that some of the code has moved around, but the changes are straight-forward. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-69-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/mmu_context.h | 17 ++++++----------- arch/arm64/mm/kasan_init.c | 4 ++-- arch/arm64/mm/mmu.c | 4 ++-- 3 files changed, 10 insertions(+), 15 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index a8a89a0f2867..c768d16b81a4 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -108,18 +108,13 @@ static inline void cpu_uninstall_idmap(void) cpu_switch_mm(mm->pgd, mm); } -static inline void __cpu_install_idmap(pgd_t *idmap) +static inline void cpu_install_idmap(void) { cpu_set_reserved_ttbr0(); local_flush_tlb_all(); cpu_set_idmap_tcr_t0sz(); - cpu_switch_mm(lm_alias(idmap), &init_mm); -} - -static inline void cpu_install_idmap(void) -{ - __cpu_install_idmap(idmap_pg_dir); + cpu_switch_mm(lm_alias(idmap_pg_dir), &init_mm); } /* @@ -146,21 +141,21 @@ static inline void cpu_install_ttbr0(phys_addr_t ttbr0, unsigned long t0sz) isb(); } -void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp); +void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp); static inline void cpu_enable_swapper_cnp(void) { - __cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir, true); + __cpu_replace_ttbr1(lm_alias(swapper_pg_dir), true); } -static inline void cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap) +static inline void cpu_replace_ttbr1(pgd_t *pgdp) { /* * Only for early TTBR1 replacement before cpucaps are finalized and * before we've decided whether to use CNP. */ WARN_ON(system_capabilities_finalized()); - __cpu_replace_ttbr1(pgdp, idmap, false); + __cpu_replace_ttbr1(pgdp, false); } /* diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 89828ad2bca7..a86ab99587c9 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -225,7 +225,7 @@ static void __init kasan_init_shadow(void) */ memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir)); dsb(ishst); - cpu_replace_ttbr1(lm_alias(tmp_pg_dir), idmap_pg_dir); + cpu_replace_ttbr1(lm_alias(tmp_pg_dir)); clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); @@ -261,7 +261,7 @@ static void __init kasan_init_shadow(void) PAGE_KERNEL_RO)); memset(kasan_early_shadow_page, KASAN_SHADOW_INIT, PAGE_SIZE); - cpu_replace_ttbr1(lm_alias(swapper_pg_dir), idmap_pg_dir); + cpu_replace_ttbr1(lm_alias(swapper_pg_dir)); } static void __init kasan_init_depth(void) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 3db40b517947..a3d23da92d87 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1445,7 +1445,7 @@ void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte * Atomically replaces the active TTBR1_EL1 PGD with a new VA-compatible PGD, * avoiding the possibility of conflicting TLB entries being allocated. */ -void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp) +void __cpu_replace_ttbr1(pgd_t *pgdp, bool cnp) { typedef void (ttbr_replace_func)(phys_addr_t); extern ttbr_replace_func idmap_cpu_replace_ttbr1; @@ -1460,7 +1460,7 @@ void __cpu_replace_ttbr1(pgd_t *pgdp, pgd_t *idmap, bool cnp) replace_phys = (void *)__pa_symbol(idmap_cpu_replace_ttbr1); - __cpu_install_idmap(idmap); + cpu_install_idmap(); /* * We really don't want to take *any* exceptions while TTBR1 is -- cgit v1.2.3 From 9cce9c6c2c3b7d46698d9bb693389d37740fec28 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:11 +0100 Subject: arm64: mm: Handle LVA support as a CPU feature Currently, we detect CPU support for 52-bit virtual addressing (LVA) extremely early, before creating the kernel page tables or enabling the MMU. We cannot override the feature this early, and so large virtual addressing is always enabled on CPUs that implement support for it if the software support for it was enabled at build time. It also means we rely on non-trivial code in asm to deal with this feature. Given that both the ID map and the TTBR1 mapping of the kernel image are guaranteed to be 48-bit addressable, it is not actually necessary to enable support this early, and instead, we can model it as a CPU feature. That way, we can rely on code patching to get the correct TCR.T1SZ values programmed on secondary boot and resume from suspend. On the primary boot path, we simply enable the MMU with 48-bit virtual addressing initially, and update TCR.T1SZ if LVA is supported from C code, right before creating the kernel mapping. Given that TTBR1 still points to reserved_pg_dir at this point, updating TCR.T1SZ should be safe without the need for explicit TLB maintenance. Since this gets rid of all accesses to the vabits_actual variable from asm code that occurred before TCR.T1SZ had been programmed, we no longer have a need for this variable, and we can replace it with a C expression that produces the correct value directly, based on the value of TCR.T1SZ. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-70-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/cpufeature.h | 9 +++++++++ arch/arm64/include/asm/memory.h | 13 ++++++++++++- arch/arm64/kernel/cpufeature.c | 13 +++++++++++++ arch/arm64/kernel/head.S | 29 +++++++---------------------- arch/arm64/kernel/image-vars.h | 1 - arch/arm64/kernel/pi/map_kernel.c | 3 +++ arch/arm64/kernel/sleep.S | 3 --- arch/arm64/mm/mmu.c | 5 ----- arch/arm64/mm/proc.S | 9 ++++----- arch/arm64/tools/cpucaps | 1 + 10 files changed, 49 insertions(+), 37 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index e3edae1825f3..4f4dc5496ee3 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -995,6 +995,15 @@ static inline bool cpu_has_pac(void) &id_aa64isar2_override); } +static inline bool cpu_has_lva(void) +{ + u64 mmfr2; + + mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); + return cpuid_feature_extract_unsigned_field(mmfr2, + ID_AA64MMFR2_EL1_VARange_SHIFT); +} + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 60904a6c4b42..9680d7444b3b 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -209,9 +209,20 @@ #include #include #include +#include + +static inline u64 __pure read_tcr(void) +{ + u64 tcr; + + // read_sysreg() uses asm volatile, so avoid it here + asm("mrs %0, tcr_el1" : "=r"(tcr)); + return tcr; +} #if VA_BITS > 48 -extern u64 vabits_actual; +// For reasons of #include hell, we can't use TCR_T1SZ_OFFSET/TCR_T1SZ_MASK here +#define vabits_actual (64 - ((read_tcr() >> 16) & 63)) #else #define vabits_actual ((u64)VA_BITS) #endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 7064cf13f226..8eb8c7f7b317 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2692,6 +2692,19 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .type = ARM64_CPUCAP_SYSTEM_FEATURE, .matches = has_lpa2, }, +#ifdef CONFIG_ARM64_VA_BITS_52 + { + .desc = "52-bit Virtual Addressing (LVA)", + .capability = ARM64_HAS_VA52, + .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, + .sys_reg = SYS_ID_AA64MMFR2_EL1, + .sign = FTR_UNSIGNED, + .field_width = 4, + .field_pos = ID_AA64MMFR2_EL1_VARange_SHIFT, + .matches = has_cpuid_feature, + .min_field_value = ID_AA64MMFR2_EL1_VARange_52, + }, +#endif {}, }; diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 545b5d8976f4..e25351addfd0 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -80,7 +80,6 @@ * x19 primary_entry() .. start_kernel() whether we entered with the MMU on * x20 primary_entry() .. __primary_switch() CPU boot mode * x21 primary_entry() .. start_kernel() FDT pointer passed at boot in x0 - * x25 primary_entry() .. start_kernel() supported VA size */ SYM_CODE_START(primary_entry) bl record_mmu_state @@ -125,14 +124,6 @@ SYM_CODE_START(primary_entry) * On return, the CPU will be ready for the MMU to be turned on and * the TCR will have been set. */ -#if VA_BITS > 48 - mrs_s x0, SYS_ID_AA64MMFR2_EL1 - tst x0, ID_AA64MMFR2_EL1_VARange_MASK - mov x0, #VA_BITS - mov x25, #VA_BITS_MIN - csel x25, x25, x0, eq - mov x0, x25 -#endif bl __cpu_setup // initialise processor b __primary_switch SYM_CODE_END(primary_entry) @@ -242,11 +233,6 @@ SYM_FUNC_START_LOCAL(__primary_switched) mov x0, x20 bl set_cpu_boot_mode_flag -#if VA_BITS > 48 - adr_l x8, vabits_actual // Set this early so KASAN early init - str x25, [x8] // ... observes the correct value - dc civac, x8 // Make visible to booting secondaries -#endif #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) bl kasan_early_init #endif @@ -376,10 +362,13 @@ SYM_FUNC_START_LOCAL(secondary_startup) * Common entry point for secondary CPUs. */ mov x20, x0 // preserve boot mode + +#ifdef CONFIG_ARM64_VA_BITS_52 +alternative_if ARM64_HAS_VA52 bl __cpu_secondary_check52bitva -#if VA_BITS > 48 - ldr_l x0, vabits_actual +alternative_else_nop_endif #endif + bl __cpu_setup // initialise processor adrp x1, swapper_pg_dir adrp x2, idmap_pg_dir @@ -482,12 +471,8 @@ SYM_FUNC_START(__enable_mmu) ret SYM_FUNC_END(__enable_mmu) +#ifdef CONFIG_ARM64_VA_BITS_52 SYM_FUNC_START(__cpu_secondary_check52bitva) -#if VA_BITS > 48 - ldr_l x0, vabits_actual - cmp x0, #52 - b.ne 2f - mrs_s x0, SYS_ID_AA64MMFR2_EL1 and x0, x0, ID_AA64MMFR2_EL1_VARange_MASK cbnz x0, 2f @@ -498,9 +483,9 @@ SYM_FUNC_START(__cpu_secondary_check52bitva) wfi b 1b -#endif 2: ret SYM_FUNC_END(__cpu_secondary_check52bitva) +#endif SYM_FUNC_START_LOCAL(__no_granule_support) /* Indicate that this CPU can't boot and is stuck in the kernel */ diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index e140c5bda90b..2b9d702abe0f 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -36,7 +36,6 @@ PROVIDE(__pi___memcpy = __pi_memcpy); PROVIDE(__pi___memmove = __pi_memmove); PROVIDE(__pi___memset = __pi_memset); -PROVIDE(__pi_vabits_actual = vabits_actual); PROVIDE(__pi_id_aa64isar1_override = id_aa64isar1_override); PROVIDE(__pi_id_aa64isar2_override = id_aa64isar2_override); PROVIDE(__pi_id_aa64mmfr1_override = id_aa64mmfr1_override); diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c index 4b76a007a50d..1853825aa29d 100644 --- a/arch/arm64/kernel/pi/map_kernel.c +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -165,6 +165,9 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt) chosen = fdt_path_offset(fdt, chosen_str); init_feature_override(boot_status, fdt, chosen); + if (VA_BITS > VA_BITS_MIN && cpu_has_lva()) + sysreg_clear_set(tcr_el1, TCR_T1SZ_MASK, TCR_T1SZ(VA_BITS)); + /* * The virtual KASLR displacement modulo 2MiB is decided by the * physical placement of the image, as otherwise, we might not be able diff --git a/arch/arm64/kernel/sleep.S b/arch/arm64/kernel/sleep.S index 2aa5129d8253..f093cdf71be1 100644 --- a/arch/arm64/kernel/sleep.S +++ b/arch/arm64/kernel/sleep.S @@ -102,9 +102,6 @@ SYM_CODE_START(cpu_resume) mov x0, xzr bl init_kernel_el mov x19, x0 // preserve boot mode -#if VA_BITS > 48 - ldr_l x0, vabits_actual -#endif bl __cpu_setup /* enable the MMU early - so we can access sleep_save_stash by va */ adrp x1, swapper_pg_dir diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index a3d23da92d87..ba00d0205447 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -45,11 +45,6 @@ #define NO_CONT_MAPPINGS BIT(1) #define NO_EXEC_MAPPINGS BIT(2) /* assumes FEAT_HPDS is not used */ -#if VA_BITS > 48 -u64 vabits_actual __ro_after_init = VA_BITS_MIN; -EXPORT_SYMBOL(vabits_actual); -#endif - u64 kimage_voffset __ro_after_init; EXPORT_SYMBOL(kimage_voffset); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 55c366dbda8f..d104ddab26a4 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -397,8 +397,6 @@ SYM_FUNC_END(idmap_kpti_install_ng_mappings) * * Initialise the processor for turning the MMU on. * - * Input: - * x0 - actual number of VA bits (ignored unless VA_BITS > 48) * Output: * Return in x0 the value of the SCTLR_EL1 register. */ @@ -422,16 +420,17 @@ SYM_FUNC_START(__cpu_setup) mair .req x17 tcr .req x16 mov_q mair, MAIR_EL1_SET - mov_q tcr, TCR_T0SZ(IDMAP_VA_BITS) | TCR_T1SZ(VA_BITS) | TCR_CACHE_FLAGS | \ + mov_q tcr, TCR_T0SZ(IDMAP_VA_BITS) | TCR_T1SZ(VA_BITS_MIN) | TCR_CACHE_FLAGS | \ TCR_SMP_FLAGS | TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \ TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS tcr_clear_errata_bits tcr, x9, x5 #ifdef CONFIG_ARM64_VA_BITS_52 - sub x9, xzr, x0 - add x9, x9, #64 + mov x9, #64 - VA_BITS +alternative_if ARM64_HAS_VA52 tcr_set_t1sz tcr, x9 +alternative_else_nop_endif #endif /* diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index b912b1409fc0..b370d808b3ec 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -50,6 +50,7 @@ HAS_STAGE2_FWB HAS_TCR2 HAS_TIDCP1 HAS_TLB_RANGE +HAS_VA52 HAS_VIRT_HOST_EXTN HAS_WFXT HW_DBM -- cgit v1.2.3 From 68aec33f8f5a87b0450159e5e141d2d6c9d76850 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:12 +0100 Subject: arm64: mm: Add feature override support for LVA Add support for overriding the VARange field of the MMFR2 CPU ID register. This permits the associated LVA feature to be overridden early enough for the boot code that creates the kernel mapping to take it into account. Given that LPA2 implies LVA, disabling the latter should disable the former as well. So override the ID_AA64MMFR0.TGran field of the current page size as well if it advertises support for 52-bit addressing. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-71-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/assembler.h | 17 ++++++++++------- arch/arm64/include/asm/cpufeature.h | 4 ++++ arch/arm64/kernel/cpufeature.c | 8 ++++++-- arch/arm64/kernel/image-vars.h | 2 ++ arch/arm64/kernel/pi/idreg-override.c | 31 +++++++++++++++++++++++++++++++ 5 files changed, 53 insertions(+), 9 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 6a467c694039..68a99b116256 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -576,18 +576,21 @@ alternative_endif .endm /* - * Offset ttbr1 to allow for 48-bit kernel VAs set with 52-bit PTRS_PER_PGD. + * If the kernel is built for 52-bit virtual addressing but the hardware only + * supports 48 bits, we cannot program the pgdir address into TTBR1 directly, + * but we have to add an offset so that the TTBR1 address corresponds with the + * pgdir entry that covers the lowest 48-bit addressable VA. + * * orr is used as it can cover the immediate value (and is idempotent). - * In future this may be nop'ed out when dealing with 52-bit kernel VAs. * ttbr: Value of ttbr to set, modified. */ .macro offset_ttbr1, ttbr, tmp #ifdef CONFIG_ARM64_VA_BITS_52 - mrs_s \tmp, SYS_ID_AA64MMFR2_EL1 - and \tmp, \tmp, #(0xf << ID_AA64MMFR2_EL1_VARange_SHIFT) - cbnz \tmp, .Lskipoffs_\@ - orr \ttbr, \ttbr, #TTBR1_BADDR_4852_OFFSET -.Lskipoffs_\@ : + mrs \tmp, tcr_el1 + and \tmp, \tmp, #TCR_T1SZ_MASK + cmp \tmp, #TCR_T1SZ(VA_BITS_MIN) + orr \tmp, \ttbr, #TTBR1_BADDR_4852_OFFSET + csel \ttbr, \tmp, \ttbr, eq #endif .endm diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 4f4dc5496ee3..a2ac31aecdd9 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -906,7 +906,9 @@ static inline unsigned int get_vmid_bits(u64 mmfr1) s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, s64 cur); struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id); +extern struct arm64_ftr_override id_aa64mmfr0_override; extern struct arm64_ftr_override id_aa64mmfr1_override; +extern struct arm64_ftr_override id_aa64mmfr2_override; extern struct arm64_ftr_override id_aa64pfr0_override; extern struct arm64_ftr_override id_aa64pfr1_override; extern struct arm64_ftr_override id_aa64zfr0_override; @@ -1000,6 +1002,8 @@ static inline bool cpu_has_lva(void) u64 mmfr2; mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); + mmfr2 &= ~id_aa64mmfr2_override.mask; + mmfr2 |= id_aa64mmfr2_override.val; return cpuid_feature_extract_unsigned_field(mmfr2, ID_AA64MMFR2_EL1_VARange_SHIFT); } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 8eb8c7f7b317..ed9670d8360c 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -655,7 +655,9 @@ static const struct arm64_ftr_bits ftr_raz[] = { #define ARM64_FTR_REG(id, table) \ __ARM64_FTR_REG_OVERRIDE(#id, id, table, &no_override) +struct arm64_ftr_override id_aa64mmfr0_override; struct arm64_ftr_override id_aa64mmfr1_override; +struct arm64_ftr_override id_aa64mmfr2_override; struct arm64_ftr_override id_aa64pfr0_override; struct arm64_ftr_override id_aa64pfr1_override; struct arm64_ftr_override id_aa64zfr0_override; @@ -719,10 +721,12 @@ static const struct __ftr_reg_entry { &id_aa64isar2_override), /* Op1 = 0, CRn = 0, CRm = 7 */ - ARM64_FTR_REG(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0), + ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR0_EL1, ftr_id_aa64mmfr0, + &id_aa64mmfr0_override), ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1, &id_aa64mmfr1_override), - ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2), + ARM64_FTR_REG_OVERRIDE(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2, + &id_aa64mmfr2_override), ARM64_FTR_REG(SYS_ID_AA64MMFR3_EL1, ftr_id_aa64mmfr3), /* Op1 = 1, CRn = 0, CRm = 0 */ diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index 2b9d702abe0f..ff81f809a240 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -38,7 +38,9 @@ PROVIDE(__pi___memset = __pi_memset); PROVIDE(__pi_id_aa64isar1_override = id_aa64isar1_override); PROVIDE(__pi_id_aa64isar2_override = id_aa64isar2_override); +PROVIDE(__pi_id_aa64mmfr0_override = id_aa64mmfr0_override); PROVIDE(__pi_id_aa64mmfr1_override = id_aa64mmfr1_override); +PROVIDE(__pi_id_aa64mmfr2_override = id_aa64mmfr2_override); PROVIDE(__pi_id_aa64pfr0_override = id_aa64pfr0_override); PROVIDE(__pi_id_aa64pfr1_override = id_aa64pfr1_override); PROVIDE(__pi_id_aa64smfr0_override = id_aa64smfr0_override); diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c index 1884bd936c0d..aad399796e81 100644 --- a/arch/arm64/kernel/pi/idreg-override.c +++ b/arch/arm64/kernel/pi/idreg-override.c @@ -59,6 +59,35 @@ static const struct ftr_set_desc mmfr1 __prel64_initconst = { }, }; + +static bool __init mmfr2_varange_filter(u64 val) +{ + int __maybe_unused feat; + + if (val) + return false; + +#ifdef CONFIG_ARM64_LPA2 + feat = cpuid_feature_extract_signed_field(read_sysreg(id_aa64mmfr0_el1), + ID_AA64MMFR0_EL1_TGRAN_SHIFT); + if (feat >= ID_AA64MMFR0_EL1_TGRAN_LPA2) { + id_aa64mmfr0_override.val |= + (ID_AA64MMFR0_EL1_TGRAN_LPA2 - 1) << ID_AA64MMFR0_EL1_TGRAN_SHIFT; + id_aa64mmfr0_override.mask |= 0xfU << ID_AA64MMFR0_EL1_TGRAN_SHIFT; + } +#endif + return true; +} + +static const struct ftr_set_desc mmfr2 __prel64_initconst = { + .name = "id_aa64mmfr2", + .override = &id_aa64mmfr2_override, + .fields = { + FIELD("varange", ID_AA64MMFR2_EL1_VARange_SHIFT, mmfr2_varange_filter), + {} + }, +}; + static bool __init pfr0_sve_filter(u64 val) { /* @@ -167,6 +196,7 @@ static const struct ftr_set_desc sw_features __prel64_initconst = { static const PREL64(const struct ftr_set_desc, reg) regs[] __prel64_initconst = { { &mmfr1 }, + { &mmfr2 }, { &pfr0 }, { &pfr1 }, { &isar1 }, @@ -192,6 +222,7 @@ static const struct { { "arm64.nomte", "id_aa64pfr1.mte=0" }, { "nokaslr", "arm64_sw.nokaslr=1" }, { "rodata=off", "arm64_sw.rodataoff=1" }, + { "arm64.nolva", "id_aa64mmfr2.varange=0" }, }; static int __init parse_hexdigit(const char *p, u64 *v) -- cgit v1.2.3 From 60d043c101769b4fd6f609b4a7b9b8ad1f867860 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:13 +0100 Subject: arm64: Avoid #define'ing PTE_MAYBE_NG to 0x0 for asm use The PROT_* macros resolve to expressions that are only valid in C and not in assembler, and so they are only usable from C code. Currently, we make an exception for the permission indirection init code in proc.S, which doesn't care about the bits that are conditionally set, and so we just #define PTE_MAYBE_NG to 0x0 for any assembler file that includes these definitions. This is dodgy because this means that PROT_NORMAL and friends is generally available in asm code, but defined in a way that deviates from the definition that C code will observe, which might lead to hard to diagnose issues down the road. So instead, #define PTE_MAYBE_NG only in the place where the PIE constants are evaluated, and #undef it again right after. This allows us to drop the #define from pgtable-prot.h, and avoid the risk of deviating definitions between asm and C. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-72-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/pgtable-prot.h | 4 ---- arch/arm64/mm/proc.S | 13 +++++++++++++ 2 files changed, 13 insertions(+), 4 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 483dbfa39c4c..63ced9ccec21 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -57,10 +57,6 @@ #define _PAGE_READONLY_EXEC (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define _PAGE_EXECONLY (_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) -#ifdef __ASSEMBLY__ -#define PTE_MAYBE_NG 0 -#endif - #ifndef __ASSEMBLY__ #include diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index d104ddab26a4..6e1b2bc41a9f 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -456,11 +456,24 @@ alternative_else_nop_endif ubfx x1, x1, #ID_AA64MMFR3_EL1_S1PIE_SHIFT, #4 cbz x1, .Lskip_indirection + /* + * The PROT_* macros describing the various memory types may resolve to + * C expressions if they include the PTE_MAYBE_* macros, and so they + * can only be used from C code. The PIE_E* constants below are also + * defined in terms of those macros, but will mask out those + * PTE_MAYBE_* constants, whether they are set or not. So #define them + * as 0x0 here so we can evaluate the PIE_E* constants in asm context. + */ + +#define PTE_MAYBE_NG 0 + mov_q x0, PIE_E0 msr REG_PIRE0_EL1, x0 mov_q x0, PIE_E1 msr REG_PIR_EL1, x0 +#undef PTE_MAYBE_NG + mov x0, TCR2_EL1x_PIE msr REG_TCR2_EL1, x0 -- cgit v1.2.3 From 7ac8d5b2423cc0112ac2519276610865142a577b Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:14 +0100 Subject: arm64: Add ESR decoding for exceptions involving translation level -1 The LPA2 feature introduces new FSC values to report abort exceptions related to translation level -1. Define these and wire them up. Reuse the new ESR FSC classification helpers that arrived via the KVM arm64 tree, and update the one for translation faults to check specifically for a translation fault at level -1. (Access flag or permission faults cannot occur at level -1 because they alway involve a descriptor at the superior level so changing those helpers is not needed). Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-73-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/esr.h | 13 +++++-------- arch/arm64/include/asm/kvm_emulate.h | 10 ++-------- arch/arm64/mm/fault.c | 30 +++++++++++------------------- 3 files changed, 18 insertions(+), 35 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 353fe08546cf..81606bf7d5ac 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -117,15 +117,9 @@ #define ESR_ELx_FSC_ACCESS (0x08) #define ESR_ELx_FSC_FAULT (0x04) #define ESR_ELx_FSC_PERM (0x0C) -#define ESR_ELx_FSC_SEA_TTW0 (0x14) -#define ESR_ELx_FSC_SEA_TTW1 (0x15) -#define ESR_ELx_FSC_SEA_TTW2 (0x16) -#define ESR_ELx_FSC_SEA_TTW3 (0x17) +#define ESR_ELx_FSC_SEA_TTW(n) (0x14 + (n)) #define ESR_ELx_FSC_SECC (0x18) -#define ESR_ELx_FSC_SECC_TTW0 (0x1c) -#define ESR_ELx_FSC_SECC_TTW1 (0x1d) -#define ESR_ELx_FSC_SECC_TTW2 (0x1e) -#define ESR_ELx_FSC_SECC_TTW3 (0x1f) +#define ESR_ELx_FSC_SECC_TTW(n) (0x1c + (n)) /* ISS field definitions for Data Aborts */ #define ESR_ELx_ISV_SHIFT (24) @@ -394,6 +388,9 @@ static inline bool esr_is_data_abort(unsigned long esr) static inline bool esr_fsc_is_translation_fault(unsigned long esr) { + /* Translation fault, level -1 */ + if ((esr & ESR_ELx_FSC) == 0b101011) + return true; return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT; } diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index b804fe832184..6f5b41c70103 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -425,15 +425,9 @@ static __always_inline bool kvm_vcpu_abt_issea(const struct kvm_vcpu *vcpu) { switch (kvm_vcpu_trap_get_fault(vcpu)) { case ESR_ELx_FSC_EXTABT: - case ESR_ELx_FSC_SEA_TTW0: - case ESR_ELx_FSC_SEA_TTW1: - case ESR_ELx_FSC_SEA_TTW2: - case ESR_ELx_FSC_SEA_TTW3: + case ESR_ELx_FSC_SEA_TTW(-1) ... ESR_ELx_FSC_SEA_TTW(3): case ESR_ELx_FSC_SECC: - case ESR_ELx_FSC_SECC_TTW0: - case ESR_ELx_FSC_SECC_TTW1: - case ESR_ELx_FSC_SECC_TTW2: - case ESR_ELx_FSC_SECC_TTW3: + case ESR_ELx_FSC_SECC_TTW(-1) ... ESR_ELx_FSC_SECC_TTW(3): return true; default: return false; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 55f6455a8284..60265ede48fe 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -257,16 +257,14 @@ static bool is_el1_data_abort(unsigned long esr) static inline bool is_el1_permission_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { - unsigned long fsc_type = esr & ESR_ELx_FSC_TYPE; - if (!is_el1_data_abort(esr) && !is_el1_instruction_abort(esr)) return false; - if (fsc_type == ESR_ELx_FSC_PERM) + if (esr_fsc_is_permission_fault(esr)) return true; if (is_ttbr0_addr(addr) && system_uses_ttbr0_pan()) - return fsc_type == ESR_ELx_FSC_FAULT && + return esr_fsc_is_translation_fault(esr) && (regs->pstate & PSR_PAN_BIT); return false; @@ -279,8 +277,7 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, unsigned long flags; u64 par, dfsc; - if (!is_el1_data_abort(esr) || - (esr & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT) + if (!is_el1_data_abort(esr) || !esr_fsc_is_translation_fault(esr)) return false; local_irq_save(flags); @@ -301,7 +298,7 @@ static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, * treat the translation fault as spurious. */ dfsc = FIELD_GET(SYS_PAR_EL1_FST, par); - return (dfsc & ESR_ELx_FSC_TYPE) != ESR_ELx_FSC_FAULT; + return !esr_fsc_is_translation_fault(dfsc); } static void die_kernel_fault(const char *msg, unsigned long addr, @@ -368,11 +365,6 @@ static bool is_el1_mte_sync_tag_check_fault(unsigned long esr) return false; } -static bool is_translation_fault(unsigned long esr) -{ - return (esr & ESR_ELx_FSC_TYPE) == ESR_ELx_FSC_FAULT; -} - static void __do_kernel_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { @@ -405,7 +397,7 @@ static void __do_kernel_fault(unsigned long addr, unsigned long esr, } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { - if (is_translation_fault(esr) && + if (esr_fsc_is_translation_fault(esr) && kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) return; @@ -782,18 +774,18 @@ static const struct fault_info fault_info[] = { { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, - { do_bad, SIGKILL, SI_KERNEL, "unknown 8" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" }, - { do_bad, SIGKILL, SI_KERNEL, "unknown 12" }, + { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" }, { do_sea, SIGBUS, BUS_OBJERR, "synchronous external abort" }, { do_tag_check_fault, SIGSEGV, SEGV_MTESERR, "synchronous tag check fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 18" }, - { do_bad, SIGKILL, SI_KERNEL, "unknown 19" }, + { do_sea, SIGKILL, SI_KERNEL, "level -1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 0 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 2 (translation table walk)" }, @@ -801,7 +793,7 @@ static const struct fault_info fault_info[] = { { do_sea, SIGBUS, BUS_OBJERR, "synchronous parity or ECC error" }, // Reserved when RAS is implemented { do_bad, SIGKILL, SI_KERNEL, "unknown 25" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 26" }, - { do_bad, SIGKILL, SI_KERNEL, "unknown 27" }, + { do_sea, SIGKILL, SI_KERNEL, "level -1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 0 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 2 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented @@ -815,9 +807,9 @@ static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "unknown 38" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 39" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 40" }, - { do_bad, SIGKILL, SI_KERNEL, "unknown 41" }, + { do_bad, SIGKILL, SI_KERNEL, "level -1 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 42" }, - { do_bad, SIGKILL, SI_KERNEL, "unknown 43" }, + { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level -1 translation fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 44" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 45" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 46" }, -- cgit v1.2.3 From db95ea787bd19be666ba41733259ffea65963bff Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:15 +0100 Subject: arm64: mm: Wire up TCR.DS bit to PTE shareability fields When LPA2 is enabled, bits 8 and 9 of page and block descriptors become part of the output address instead of carrying shareability attributes for the region in question. So avoid setting these bits if TCR.DS == 1, which means LPA2 is enabled. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-74-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 4 ++++ arch/arm64/include/asm/pgtable-hwdef.h | 1 + arch/arm64/include/asm/pgtable-prot.h | 16 ++++++++++++++-- arch/arm64/mm/mmap.c | 4 ++++ arch/arm64/mm/proc.S | 2 ++ 5 files changed, 25 insertions(+), 2 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index aa7c1d435139..8c2c36fffcf5 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1377,6 +1377,10 @@ config ARM64_PA_BITS default 48 if ARM64_PA_BITS_48 default 52 if ARM64_PA_BITS_52 +config ARM64_LPA2 + def_bool y + depends on ARM64_PA_BITS_52 && !ARM64_64K_PAGES + choice prompt "Endianness" default CPU_LITTLE_ENDIAN diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index e4944d517c99..b770f98fc0b5 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -284,6 +284,7 @@ #define TCR_E0PD1 (UL(1) << 56) #define TCR_TCMA0 (UL(1) << 57) #define TCR_TCMA1 (UL(1) << 58) +#define TCR_DS (UL(1) << 59) /* * TTBR. diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h index 63ced9ccec21..dd9ee67d1d87 100644 --- a/arch/arm64/include/asm/pgtable-prot.h +++ b/arch/arm64/include/asm/pgtable-prot.h @@ -30,8 +30,8 @@ #define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) -#define PROT_DEFAULT (_PROT_DEFAULT | PTE_MAYBE_NG) -#define PROT_SECT_DEFAULT (_PROT_SECT_DEFAULT | PMD_MAYBE_NG) +#define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_MAYBE_NG | PTE_MAYBE_SHARED | PTE_AF) +#define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_MAYBE_NG | PMD_MAYBE_SHARED | PMD_SECT_AF) #define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) #define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) @@ -67,7 +67,19 @@ extern bool arm64_use_ng_mappings; #define PTE_MAYBE_NG (arm64_use_ng_mappings ? PTE_NG : 0) #define PMD_MAYBE_NG (arm64_use_ng_mappings ? PMD_SECT_NG : 0) +#ifndef CONFIG_ARM64_LPA2 #define lpa2_is_enabled() false +#define PTE_MAYBE_SHARED PTE_SHARED +#define PMD_MAYBE_SHARED PMD_SECT_S +#else +static inline bool __pure lpa2_is_enabled(void) +{ + return read_tcr() & TCR_DS; +} + +#define PTE_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PTE_SHARED) +#define PMD_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PMD_SECT_S) +#endif /* * If we have userspace only BTI we don't want to mark kernel pages diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c index 645fe60d000f..642bdf908b22 100644 --- a/arch/arm64/mm/mmap.c +++ b/arch/arm64/mm/mmap.c @@ -73,6 +73,10 @@ static int __init adjust_protection_map(void) protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY; } + if (lpa2_is_enabled()) + for (int i = 0; i < ARRAY_SIZE(protection_map); i++) + pgprot_val(protection_map[i]) &= ~PTE_SHARED; + return 0; } arch_initcall(adjust_protection_map); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 6e1b2bc41a9f..7c46f8cfd6ae 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -466,6 +466,7 @@ alternative_else_nop_endif */ #define PTE_MAYBE_NG 0 +#define PTE_MAYBE_SHARED 0 mov_q x0, PIE_E0 msr REG_PIRE0_EL1, x0 @@ -473,6 +474,7 @@ alternative_else_nop_endif msr REG_PIR_EL1, x0 #undef PTE_MAYBE_NG +#undef PTE_MAYBE_SHARED mov x0, TCR2_EL1x_PIE msr REG_TCR2_EL1, x0 -- cgit v1.2.3 From 925a0eb48044bf3d48531703c3b7522e1a8c87fb Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:16 +0100 Subject: arm64: mm: Add LPA2 support to phys<->pte conversion routines In preparation for enabling LPA2 support, introduce the mask values for converting between physical addresses and their representations in a page table descriptor. While at it, move the pte_to_phys asm macro into its only user, so that we can freely modify it to use its input value register as a temp register. For LPA2, the PTE_ADDR_MASK contains two non-adjacent sequences of zero bits, which means it no longer fits into the immediate field of an ordinary ALU instruction. So let's redefine it to include the bits in between as well, and only use it when converting from physical address to PTE representation, where the distinction does not matter. Also update the name accordingly to emphasize this. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-75-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/assembler.h | 16 ++-------------- arch/arm64/include/asm/pgtable-hwdef.h | 10 +++++++--- arch/arm64/include/asm/pgtable.h | 5 +++-- arch/arm64/mm/proc.S | 8 ++++++++ 4 files changed, 20 insertions(+), 19 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 68a99b116256..7eedcb36ebe0 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -612,25 +612,13 @@ alternative_endif .macro phys_to_pte, pte, phys #ifdef CONFIG_ARM64_PA_BITS_52 - /* - * We assume \phys is 64K aligned and this is guaranteed by only - * supporting this configuration with 64K pages. - */ - orr \pte, \phys, \phys, lsr #36 - and \pte, \pte, #PTE_ADDR_MASK + orr \pte, \phys, \phys, lsr #PTE_ADDR_HIGH_SHIFT + and \pte, \pte, #PHYS_TO_PTE_ADDR_MASK #else mov \pte, \phys #endif .endm - .macro pte_to_phys, phys, pte - and \phys, \pte, #PTE_ADDR_MASK -#ifdef CONFIG_ARM64_PA_BITS_52 - orr \phys, \phys, \phys, lsl #PTE_ADDR_HIGH_SHIFT - and \phys, \phys, GENMASK_ULL(PHYS_MASK_SHIFT - 1, PAGE_SHIFT) -#endif - .endm - /* * tcr_clear_errata_bits - Clear TCR bits that trigger an errata on this CPU. */ diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index b770f98fc0b5..4426f48f2ae0 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -155,13 +155,17 @@ #define PTE_PXN (_AT(pteval_t, 1) << 53) /* Privileged XN */ #define PTE_UXN (_AT(pteval_t, 1) << 54) /* User XN */ -#define PTE_ADDR_LOW (((_AT(pteval_t, 1) << (48 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) +#define PTE_ADDR_LOW (((_AT(pteval_t, 1) << (50 - PAGE_SHIFT)) - 1) << PAGE_SHIFT) #ifdef CONFIG_ARM64_PA_BITS_52 +#ifdef CONFIG_ARM64_64K_PAGES #define PTE_ADDR_HIGH (_AT(pteval_t, 0xf) << 12) -#define PTE_ADDR_MASK (PTE_ADDR_LOW | PTE_ADDR_HIGH) #define PTE_ADDR_HIGH_SHIFT 36 +#define PHYS_TO_PTE_ADDR_MASK (PTE_ADDR_LOW | PTE_ADDR_HIGH) #else -#define PTE_ADDR_MASK PTE_ADDR_LOW +#define PTE_ADDR_HIGH (_AT(pteval_t, 0x3) << 8) +#define PTE_ADDR_HIGH_SHIFT 42 +#define PHYS_TO_PTE_ADDR_MASK GENMASK_ULL(49, 8) +#endif #endif /* diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 522c21348ae8..61de7b1516bc 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -80,15 +80,16 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #ifdef CONFIG_ARM64_PA_BITS_52 static inline phys_addr_t __pte_to_phys(pte_t pte) { + pte_val(pte) &= ~PTE_MAYBE_SHARED; return (pte_val(pte) & PTE_ADDR_LOW) | ((pte_val(pte) & PTE_ADDR_HIGH) << PTE_ADDR_HIGH_SHIFT); } static inline pteval_t __phys_to_pte_val(phys_addr_t phys) { - return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PTE_ADDR_MASK; + return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PHYS_TO_PTE_ADDR_MASK; } #else -#define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_MASK) +#define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_LOW) #define __phys_to_pte_val(phys) (phys) #endif diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 7c46f8cfd6ae..d03434b7bca5 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -205,6 +205,14 @@ SYM_FUNC_ALIAS(__pi_idmap_cpu_replace_ttbr1, idmap_cpu_replace_ttbr1) .pushsection ".idmap.text", "a" + .macro pte_to_phys, phys, pte + and \phys, \pte, #PTE_ADDR_LOW +#ifdef CONFIG_ARM64_PA_BITS_52 + and \pte, \pte, #PTE_ADDR_HIGH + orr \phys, \phys, \pte, lsl #PTE_ADDR_HIGH_SHIFT +#endif + .endm + .macro kpti_mk_tbl_ng, type, num_entries add end_\type\()p, cur_\type\()p, #\num_entries * 8 .Ldo_\type: -- cgit v1.2.3 From a6bbf5d4d9d13509fd068de664238c16934962c6 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:17 +0100 Subject: arm64: mm: Add definitions to support 5 levels of paging Add the required types and descriptor accessors to support 5 levels of paging in the common code. This is one of the prerequisites for supporting 52-bit virtual addressing with 4k pages. Note that this does not cover the code that handles kernel mappings or the fixmap. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-76-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/pgalloc.h | 41 +++++++++++++++++ arch/arm64/include/asm/pgtable-hwdef.h | 22 +++++++-- arch/arm64/include/asm/pgtable-types.h | 6 +++ arch/arm64/include/asm/pgtable.h | 82 +++++++++++++++++++++++++++++++++- arch/arm64/mm/mmu.c | 31 ++++++++++++- arch/arm64/mm/pgd.c | 15 +++++-- 6 files changed, 188 insertions(+), 9 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index 237224484d0f..cae8c648f462 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -60,6 +60,47 @@ static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) } #endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#if CONFIG_PGTABLE_LEVELS > 4 + +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot) +{ + if (pgtable_l5_enabled()) + set_pgd(pgdp, __pgd(__phys_to_pgd_val(p4dp) | prot)); +} + +static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgdp, p4d_t *p4dp) +{ + pgdval_t pgdval = PGD_TYPE_TABLE; + + pgdval |= (mm == &init_mm) ? PGD_TABLE_UXN : PGD_TABLE_PXN; + __pgd_populate(pgdp, __pa(p4dp), pgdval); +} + +static inline p4d_t *p4d_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + gfp_t gfp = GFP_PGTABLE_USER; + + if (mm == &init_mm) + gfp = GFP_PGTABLE_KERNEL; + return (p4d_t *)get_zeroed_page(gfp); +} + +static inline void p4d_free(struct mm_struct *mm, p4d_t *p4d) +{ + if (!pgtable_l5_enabled()) + return; + BUG_ON((unsigned long)p4d & (PAGE_SIZE-1)); + free_page((unsigned long)p4d); +} + +#define __p4d_free_tlb(tlb, p4d, addr) p4d_free((tlb)->mm, p4d) +#else +static inline void __pgd_populate(pgd_t *pgdp, phys_addr_t p4dp, pgdval_t prot) +{ + BUILD_BUG(); +} +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ + extern pgd_t *pgd_alloc(struct mm_struct *mm); extern void pgd_free(struct mm_struct *mm, pgd_t *pgdp); diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index 4426f48f2ae0..ef207a0d4f0d 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -26,10 +26,10 @@ #define ARM64_HW_PGTABLE_LEVELS(va_bits) (((va_bits) - 4) / (PAGE_SHIFT - 3)) /* - * Size mapped by an entry at level n ( 0 <= n <= 3) + * Size mapped by an entry at level n ( -1 <= n <= 3) * We map (PAGE_SHIFT - 3) at all translation levels and PAGE_SHIFT bits * in the final page. The maximum number of translation levels supported by - * the architecture is 4. Hence, starting at level n, we have further + * the architecture is 5. Hence, starting at level n, we have further * ((4 - n) - 1) levels of translation excluding the offset within the page. * So, the total number of bits mapped by an entry at level n is : * @@ -62,9 +62,16 @@ #define PTRS_PER_PUD (1 << (PAGE_SHIFT - 3)) #endif +#if CONFIG_PGTABLE_LEVELS > 4 +#define P4D_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(0) +#define P4D_SIZE (_AC(1, UL) << P4D_SHIFT) +#define P4D_MASK (~(P4D_SIZE-1)) +#define PTRS_PER_P4D (1 << (PAGE_SHIFT - 3)) +#endif + /* * PGDIR_SHIFT determines the size a top-level page table entry can map - * (depending on the configuration, this level can be 0, 1 or 2). + * (depending on the configuration, this level can be -1, 0, 1 or 2). */ #define PGDIR_SHIFT ARM64_HW_PGTABLE_LEVEL_SHIFT(4 - CONFIG_PGTABLE_LEVELS) #define PGDIR_SIZE (_AC(1, UL) << PGDIR_SHIFT) @@ -87,6 +94,15 @@ /* * Hardware page table definitions. * + * Level -1 descriptor (PGD). + */ +#define PGD_TYPE_TABLE (_AT(pgdval_t, 3) << 0) +#define PGD_TABLE_BIT (_AT(pgdval_t, 1) << 1) +#define PGD_TYPE_MASK (_AT(pgdval_t, 3) << 0) +#define PGD_TABLE_PXN (_AT(pgdval_t, 1) << 59) +#define PGD_TABLE_UXN (_AT(pgdval_t, 1) << 60) + +/* * Level 0 descriptor (P4D). */ #define P4D_TYPE_TABLE (_AT(p4dval_t, 3) << 0) diff --git a/arch/arm64/include/asm/pgtable-types.h b/arch/arm64/include/asm/pgtable-types.h index b8f158ae2527..6d6d4065b0cb 100644 --- a/arch/arm64/include/asm/pgtable-types.h +++ b/arch/arm64/include/asm/pgtable-types.h @@ -36,6 +36,12 @@ typedef struct { pudval_t pud; } pud_t; #define __pud(x) ((pud_t) { (x) } ) #endif +#if CONFIG_PGTABLE_LEVELS > 4 +typedef struct { p4dval_t p4d; } p4d_t; +#define p4d_val(x) ((x).p4d) +#define __p4d(x) ((p4d_t) { (x) } ) +#endif + typedef struct { pgdval_t pgd; } pgd_t; #define pgd_val(x) ((x).pgd) #define __pgd(x) ((pgd_t) { (x) } ) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 61de7b1516bc..7eb2b933ed3c 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -808,7 +808,6 @@ static inline pud_t *p4d_pgtable(p4d_t p4d) #else #define p4d_page_paddr(p4d) ({ BUILD_BUG(); 0;}) -#define pgd_page_paddr(pgd) ({ BUILD_BUG(); 0;}) /* Match pud_offset folding in */ #define pud_set_fixmap(addr) NULL @@ -819,6 +818,87 @@ static inline pud_t *p4d_pgtable(p4d_t p4d) #endif /* CONFIG_PGTABLE_LEVELS > 3 */ +#if CONFIG_PGTABLE_LEVELS > 4 + +static __always_inline bool pgtable_l5_enabled(void) +{ + if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) + return vabits_actual == VA_BITS; + return alternative_has_cap_unlikely(ARM64_HAS_VA52); +} + +static inline bool mm_p4d_folded(const struct mm_struct *mm) +{ + return !pgtable_l5_enabled(); +} +#define mm_p4d_folded mm_p4d_folded + +#define p4d_ERROR(e) \ + pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e)) + +#define pgd_none(pgd) (pgtable_l5_enabled() && !pgd_val(pgd)) +#define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & 2)) +#define pgd_present(pgd) (!pgd_none(pgd)) + +static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) +{ + if (in_swapper_pgdir(pgdp)) { + set_swapper_pgd(pgdp, __pgd(pgd_val(pgd))); + return; + } + + WRITE_ONCE(*pgdp, pgd); + dsb(ishst); + isb(); +} + +static inline void pgd_clear(pgd_t *pgdp) +{ + if (pgtable_l5_enabled()) + set_pgd(pgdp, __pgd(0)); +} + +static inline phys_addr_t pgd_page_paddr(pgd_t pgd) +{ + return __pgd_to_phys(pgd); +} + +#define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) + +static inline p4d_t *pgd_to_folded_p4d(pgd_t *pgdp, unsigned long addr) +{ + return (p4d_t *)PTR_ALIGN_DOWN(pgdp, PAGE_SIZE) + p4d_index(addr); +} + +static inline phys_addr_t p4d_offset_phys(pgd_t *pgdp, unsigned long addr) +{ + BUG_ON(!pgtable_l5_enabled()); + + return pgd_page_paddr(READ_ONCE(*pgdp)) + p4d_index(addr) * sizeof(p4d_t); +} + +static inline +p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long addr) +{ + if (!pgtable_l5_enabled()) + return pgd_to_folded_p4d(pgdp, addr); + return (p4d_t *)__va(pgd_page_paddr(pgd)) + p4d_index(addr); +} +#define p4d_offset_lockless p4d_offset_lockless + +static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long addr) +{ + return p4d_offset_lockless(pgdp, READ_ONCE(*pgdp), addr); +} + +#define pgd_page(pgd) pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd))) + +#else + +static inline bool pgtable_l5_enabled(void) { return false; } + +#endif /* CONFIG_PGTABLE_LEVELS > 4 */ + #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %016llx.\n", __FILE__, __LINE__, pgd_val(e)) diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index ba00d0205447..d2e9dec38a15 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1025,7 +1025,7 @@ static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr, if (CONFIG_PGTABLE_LEVELS <= 3) return; - if (!pgtable_range_aligned(start, end, floor, ceiling, PGDIR_MASK)) + if (!pgtable_range_aligned(start, end, floor, ceiling, P4D_MASK)) return; /* @@ -1048,8 +1048,8 @@ static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { - unsigned long next; p4d_t *p4dp, p4d; + unsigned long i, next, start = addr; do { next = p4d_addr_end(addr, end); @@ -1061,6 +1061,27 @@ static void free_empty_p4d_table(pgd_t *pgdp, unsigned long addr, WARN_ON(!p4d_present(p4d)); free_empty_pud_table(p4dp, addr, next, floor, ceiling); } while (addr = next, addr < end); + + if (!pgtable_l5_enabled()) + return; + + if (!pgtable_range_aligned(start, end, floor, ceiling, PGDIR_MASK)) + return; + + /* + * Check whether we can free the p4d page if the rest of the + * entries are empty. Overlap with other regions have been + * handled by the floor/ceiling check. + */ + p4dp = p4d_offset(pgdp, 0UL); + for (i = 0; i < PTRS_PER_P4D; i++) { + if (!p4d_none(READ_ONCE(p4dp[i]))) + return; + } + + pgd_clear(pgdp); + __flush_tlb_kernel_pgtable(start); + free_hotplug_pgtable_page(virt_to_page(p4dp)); } static void free_empty_tables(unsigned long addr, unsigned long end, @@ -1145,6 +1166,12 @@ int pmd_set_huge(pmd_t *pmdp, phys_addr_t phys, pgprot_t prot) return 1; } +#ifndef __PAGETABLE_P4D_FOLDED +void p4d_clear_huge(p4d_t *p4dp) +{ +} +#endif + int pud_clear_huge(pud_t *pudp) { if (!pud_sect(READ_ONCE(*pudp))) diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index 4a64089e5771..3c4f8a279d2b 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -17,11 +17,20 @@ static struct kmem_cache *pgd_cache __ro_after_init; +static bool pgdir_is_page_size(void) +{ + if (PGD_SIZE == PAGE_SIZE) + return true; + if (CONFIG_PGTABLE_LEVELS == 5) + return !pgtable_l5_enabled(); + return false; +} + pgd_t *pgd_alloc(struct mm_struct *mm) { gfp_t gfp = GFP_PGTABLE_USER; - if (PGD_SIZE == PAGE_SIZE) + if (pgdir_is_page_size()) return (pgd_t *)__get_free_page(gfp); else return kmem_cache_alloc(pgd_cache, gfp); @@ -29,7 +38,7 @@ pgd_t *pgd_alloc(struct mm_struct *mm) void pgd_free(struct mm_struct *mm, pgd_t *pgd) { - if (PGD_SIZE == PAGE_SIZE) + if (pgdir_is_page_size()) free_page((unsigned long)pgd); else kmem_cache_free(pgd_cache, pgd); @@ -37,7 +46,7 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd) void __init pgtable_cache_init(void) { - if (PGD_SIZE == PAGE_SIZE) + if (pgdir_is_page_size()) return; #ifdef CONFIG_ARM64_PA_BITS_52 -- cgit v1.2.3 From 2b6c8f96cc47eb1b41f7ebf28dfc2459c39f7fa9 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:18 +0100 Subject: arm64: mm: add LPA2 and 5 level paging support to G-to-nG conversion Add support for 5 level paging in the G-to-nG routine that creates its own temporary page tables to traverse the swapper page tables. Also add support for running the 5 level configuration with the top level folded at runtime, to support CPUs that do not implement the LPA2 extension. While at it, wire up the level skipping logic so it will also trigger on 4 level configurations with LPA2 enabled at build time but not active at runtime, as we'll fall back to 3 level paging in that case. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-77-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/kernel/cpufeature.c | 9 ++++-- arch/arm64/mm/proc.S | 70 ++++++++++++++++++++++++++++++++++++------ 2 files changed, 66 insertions(+), 13 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index ed9670d8360c..bc5e4e569864 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1765,6 +1765,9 @@ static int __init __kpti_install_ng_mappings(void *__unused) pgd_t *kpti_ng_temp_pgd; u64 alloc = 0; + if (levels == 5 && !pgtable_l5_enabled()) + levels = 4; + remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); if (!cpu) { @@ -1778,9 +1781,9 @@ static int __init __kpti_install_ng_mappings(void *__unused) // // The physical pages are laid out as follows: // - // +--------+-/-------+-/------ +-\\--------+ - // : PTE[] : | PMD[] : | PUD[] : || PGD[] : - // +--------+-\-------+-\------ +-//--------+ + // +--------+-/-------+-/------ +-/------ +-\\\--------+ + // : PTE[] : | PMD[] : | PUD[] : | P4D[] : ||| PGD[] : + // +--------+-\-------+-\------ +-\------ +-///--------+ // ^ // The first page is mapped into this hierarchy at a PMD_SHIFT // aligned virtual address, so that we can manipulate the PTE diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index d03434b7bca5..fa0d7c63f8d2 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -216,16 +216,15 @@ SYM_FUNC_ALIAS(__pi_idmap_cpu_replace_ttbr1, idmap_cpu_replace_ttbr1) .macro kpti_mk_tbl_ng, type, num_entries add end_\type\()p, cur_\type\()p, #\num_entries * 8 .Ldo_\type: - ldr \type, [cur_\type\()p] // Load the entry + ldr \type, [cur_\type\()p], #8 // Load the entry and advance tbz \type, #0, .Lnext_\type // Skip invalid and tbnz \type, #11, .Lnext_\type // non-global entries orr \type, \type, #PTE_NG // Same bit for blocks and pages - str \type, [cur_\type\()p] // Update the entry + str \type, [cur_\type\()p, #-8] // Update the entry .ifnc \type, pte tbnz \type, #1, .Lderef_\type .endif .Lnext_\type: - add cur_\type\()p, cur_\type\()p, #8 cmp cur_\type\()p, end_\type\()p b.ne .Ldo_\type .endm @@ -235,18 +234,18 @@ SYM_FUNC_ALIAS(__pi_idmap_cpu_replace_ttbr1, idmap_cpu_replace_ttbr1) * fixmap slot associated with the current level. */ .macro kpti_map_pgtbl, type, level - str xzr, [temp_pte, #8 * (\level + 1)] // break before make + str xzr, [temp_pte, #8 * (\level + 2)] // break before make dsb nshst - add pte, temp_pte, #PAGE_SIZE * (\level + 1) + add pte, temp_pte, #PAGE_SIZE * (\level + 2) lsr pte, pte, #12 tlbi vaae1, pte dsb nsh isb phys_to_pte pte, cur_\type\()p - add cur_\type\()p, temp_pte, #PAGE_SIZE * (\level + 1) + add cur_\type\()p, temp_pte, #PAGE_SIZE * (\level + 2) orr pte, pte, pte_flags - str pte, [temp_pte, #8 * (\level + 1)] + str pte, [temp_pte, #8 * (\level + 2)] dsb nshst .endm @@ -279,6 +278,8 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) end_ptep .req x15 pte .req x16 valid .req x17 + cur_p4dp .req x19 + end_p4dp .req x20 mov x5, x3 // preserve temp_pte arg mrs swapper_ttb, ttbr1_el1 @@ -286,6 +287,12 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) cbnz cpu, __idmap_kpti_secondary +#if CONFIG_PGTABLE_LEVELS > 4 + stp x29, x30, [sp, #-32]! + mov x29, sp + stp x19, x20, [sp, #16] +#endif + /* We're the boot CPU. Wait for the others to catch up */ sevl 1: wfe @@ -303,9 +310,32 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) mov_q pte_flags, KPTI_NG_PTE_FLAGS /* Everybody is enjoying the idmap, so we can rewrite swapper. */ + +#ifdef CONFIG_ARM64_LPA2 + /* + * If LPA2 support is configured, but 52-bit virtual addressing is not + * enabled at runtime, we will fall back to one level of paging less, + * and so we have to walk swapper_pg_dir as if we dereferenced its + * address from a PGD level entry, and terminate the PGD level loop + * right after. + */ + adrp pgd, swapper_pg_dir // walk &swapper_pg_dir at the next level + mov cur_pgdp, end_pgdp // must be equal to terminate the PGD loop +alternative_if_not ARM64_HAS_VA52 + b .Lderef_pgd // skip to the next level +alternative_else_nop_endif + /* + * LPA2 based 52-bit virtual addressing requires 52-bit physical + * addressing to be enabled as well. In this case, the shareability + * bits are repurposed as physical address bits, and should not be + * set in pte_flags. + */ + bic pte_flags, pte_flags, #PTE_SHARED +#endif + /* PGD */ adrp cur_pgdp, swapper_pg_dir - kpti_map_pgtbl pgd, 0 + kpti_map_pgtbl pgd, -1 kpti_mk_tbl_ng pgd, PTRS_PER_PGD /* Ensure all the updated entries are visible to secondary CPUs */ @@ -318,16 +348,33 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) /* Set the flag to zero to indicate that we're all done */ str wzr, [flag_ptr] +#if CONFIG_PGTABLE_LEVELS > 4 + ldp x19, x20, [sp, #16] + ldp x29, x30, [sp], #32 +#endif ret .Lderef_pgd: + /* P4D */ + .if CONFIG_PGTABLE_LEVELS > 4 + p4d .req x30 + pte_to_phys cur_p4dp, pgd + kpti_map_pgtbl p4d, 0 + kpti_mk_tbl_ng p4d, PTRS_PER_P4D + b .Lnext_pgd + .else /* CONFIG_PGTABLE_LEVELS <= 4 */ + p4d .req pgd + .set .Lnext_p4d, .Lnext_pgd + .endif + +.Lderef_p4d: /* PUD */ .if CONFIG_PGTABLE_LEVELS > 3 pud .req x10 - pte_to_phys cur_pudp, pgd + pte_to_phys cur_pudp, p4d kpti_map_pgtbl pud, 1 kpti_mk_tbl_ng pud, PTRS_PER_PUD - b .Lnext_pgd + b .Lnext_p4d .else /* CONFIG_PGTABLE_LEVELS <= 3 */ pud .req pgd .set .Lnext_pud, .Lnext_pgd @@ -371,6 +418,9 @@ SYM_TYPED_FUNC_START(idmap_kpti_install_ng_mappings) .unreq end_ptep .unreq pte .unreq valid + .unreq cur_p4dp + .unreq end_p4dp + .unreq p4d /* Secondary CPUs end up here */ __idmap_kpti_secondary: -- cgit v1.2.3 From 9684ec186f8fadde52d6b6eaf64ca508897d0c71 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:19 +0100 Subject: arm64: Enable LPA2 at boot if supported by the system Update the early kernel mapping code to take 52-bit virtual addressing into account based on the LPA2 feature. This is a bit more involved than LVA (which is supported with 64k pages only), given that some page table descriptor bits change meaning in this case. To keep the handling in asm to a minimum, the initial ID map is still created with 48-bit virtual addressing, which implies that the kernel image must be loaded into 48-bit addressable physical memory. This is currently required by the boot protocol, even though we happen to support placement outside of that for LVA/64k based configurations. Enabling LPA2 involves more than setting TCR.T1SZ to a lower value, there is also a DS bit in TCR that needs to be set, and which changes the meaning of bits [9:8] in all page table descriptors. Since we cannot enable DS and every live page table descriptor at the same time, let's pivot through another temporary mapping. This avoids the need to reintroduce manipulations of the page tables with the MMU and caches disabled. To permit the LPA2 feature to be overridden on the kernel command line, which may be necessary to work around silicon errata, or to deal with mismatched features on heterogeneous SoC designs, test for CPU feature overrides first, and only then enable LPA2. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-78-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/assembler.h | 8 ++++- arch/arm64/include/asm/cpufeature.h | 18 ++++++++++ arch/arm64/include/asm/memory.h | 4 +++ arch/arm64/kernel/head.S | 8 +++++ arch/arm64/kernel/image-vars.h | 1 + arch/arm64/kernel/pi/map_kernel.c | 70 +++++++++++++++++++++++++++++++++++-- arch/arm64/kernel/pi/map_range.c | 11 ++++-- arch/arm64/kernel/pi/pi.h | 4 +-- arch/arm64/mm/init.c | 2 +- arch/arm64/mm/mmu.c | 6 +++- arch/arm64/mm/proc.S | 3 ++ 11 files changed, 124 insertions(+), 11 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 7eedcb36ebe0..ce7b95cd6e79 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -581,11 +581,17 @@ alternative_endif * but we have to add an offset so that the TTBR1 address corresponds with the * pgdir entry that covers the lowest 48-bit addressable VA. * + * Note that this trick is only used for LVA/64k pages - LPA2/4k pages uses an + * additional paging level, and on LPA2/16k pages, we would end up with a root + * level table with only 2 entries, which is suboptimal in terms of TLB + * utilization, so there we fall back to 47 bits of translation if LPA2 is not + * supported. + * * orr is used as it can cover the immediate value (and is idempotent). * ttbr: Value of ttbr to set, modified. */ .macro offset_ttbr1, ttbr, tmp -#ifdef CONFIG_ARM64_VA_BITS_52 +#if defined(CONFIG_ARM64_VA_BITS_52) && !defined(CONFIG_ARM64_LPA2) mrs \tmp, tcr_el1 and \tmp, \tmp, #TCR_T1SZ_MASK cmp \tmp, #TCR_T1SZ(VA_BITS_MIN) diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index a2ac31aecdd9..a8f97690ce1f 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -1008,6 +1008,24 @@ static inline bool cpu_has_lva(void) ID_AA64MMFR2_EL1_VARange_SHIFT); } +static inline bool cpu_has_lpa2(void) +{ +#ifdef CONFIG_ARM64_LPA2 + u64 mmfr0; + int feat; + + mmfr0 = read_sysreg(id_aa64mmfr0_el1); + mmfr0 &= ~id_aa64mmfr0_override.mask; + mmfr0 |= id_aa64mmfr0_override.val; + feat = cpuid_feature_extract_signed_field(mmfr0, + ID_AA64MMFR0_EL1_TGRAN_SHIFT); + + return feat >= ID_AA64MMFR0_EL1_TGRAN_LPA2; +#else + return false; +#endif +} + #endif /* __ASSEMBLY__ */ #endif diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 9680d7444b3b..b850b1b91471 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -54,7 +54,11 @@ #define FIXADDR_TOP (-UL(SZ_8M)) #if VA_BITS > 48 +#ifdef CONFIG_ARM64_16K_PAGES +#define VA_BITS_MIN (47) +#else #define VA_BITS_MIN (48) +#endif #else #define VA_BITS_MIN (VA_BITS) #endif diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index e25351addfd0..405e9bce8c73 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -89,6 +89,7 @@ SYM_CODE_START(primary_entry) mov sp, x1 mov x29, xzr adrp x0, init_idmap_pg_dir + mov x1, xzr bl __pi_create_init_idmap /* @@ -473,9 +474,16 @@ SYM_FUNC_END(__enable_mmu) #ifdef CONFIG_ARM64_VA_BITS_52 SYM_FUNC_START(__cpu_secondary_check52bitva) +#ifndef CONFIG_ARM64_LPA2 mrs_s x0, SYS_ID_AA64MMFR2_EL1 and x0, x0, ID_AA64MMFR2_EL1_VARange_MASK cbnz x0, 2f +#else + mrs x0, id_aa64mmfr0_el1 + sbfx x0, x0, #ID_AA64MMFR0_EL1_TGRAN_SHIFT, 4 + cmp x0, #ID_AA64MMFR0_EL1_TGRAN_LPA2 + b.ge 2f +#endif update_early_cpu_boot_status \ CPU_STUCK_IN_KERNEL | CPU_STUCK_REASON_52_BIT_VA, x0, x1 diff --git a/arch/arm64/kernel/image-vars.h b/arch/arm64/kernel/image-vars.h index ff81f809a240..ba4f8f7d6a91 100644 --- a/arch/arm64/kernel/image-vars.h +++ b/arch/arm64/kernel/image-vars.h @@ -54,6 +54,7 @@ PROVIDE(__pi__ctype = _ctype); PROVIDE(__pi_memstart_offset_seed = memstart_offset_seed); PROVIDE(__pi_init_idmap_pg_dir = init_idmap_pg_dir); +PROVIDE(__pi_init_idmap_pg_end = init_idmap_pg_end); PROVIDE(__pi_init_pg_dir = init_pg_dir); PROVIDE(__pi_init_pg_end = init_pg_end); PROVIDE(__pi_swapper_pg_dir = swapper_pg_dir); diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c index 1853825aa29d..5fa08e13e17e 100644 --- a/arch/arm64/kernel/pi/map_kernel.c +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -127,11 +127,64 @@ static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level) } /* Copy the root page table to its final location */ - memcpy((void *)swapper_pg_dir + va_offset, init_pg_dir, PGD_SIZE); + memcpy((void *)swapper_pg_dir + va_offset, init_pg_dir, PAGE_SIZE); dsb(ishst); idmap_cpu_replace_ttbr1(swapper_pg_dir); } +static void noinline __section(".idmap.text") set_ttbr0_for_lpa2(u64 ttbr) +{ + u64 sctlr = read_sysreg(sctlr_el1); + u64 tcr = read_sysreg(tcr_el1) | TCR_DS; + + asm(" msr sctlr_el1, %0 ;" + " isb ;" + " msr ttbr0_el1, %1 ;" + " msr tcr_el1, %2 ;" + " isb ;" + " tlbi vmalle1 ;" + " dsb nsh ;" + " isb ;" + " msr sctlr_el1, %3 ;" + " isb ;" + :: "r"(sctlr & ~SCTLR_ELx_M), "r"(ttbr), "r"(tcr), "r"(sctlr)); +} + +static void __init remap_idmap_for_lpa2(void) +{ + /* clear the bits that change meaning once LPA2 is turned on */ + pteval_t mask = PTE_SHARED; + + /* + * We have to clear bits [9:8] in all block or page descriptors in the + * initial ID map, as otherwise they will be (mis)interpreted as + * physical address bits once we flick the LPA2 switch (TCR.DS). Since + * we cannot manipulate live descriptors in that way without creating + * potential TLB conflicts, let's create another temporary ID map in a + * LPA2 compatible fashion, and update the initial ID map while running + * from that. + */ + create_init_idmap(init_pg_dir, mask); + dsb(ishst); + set_ttbr0_for_lpa2((u64)init_pg_dir); + + /* + * Recreate the initial ID map with the same granularity as before. + * Don't bother with the FDT, we no longer need it after this. + */ + memset(init_idmap_pg_dir, 0, + (u64)init_idmap_pg_dir - (u64)init_idmap_pg_end); + + create_init_idmap(init_idmap_pg_dir, mask); + dsb(ishst); + + /* switch back to the updated initial ID map */ + set_ttbr0_for_lpa2((u64)init_idmap_pg_dir); + + /* wipe the temporary ID map from memory */ + memset(init_pg_dir, 0, (u64)init_pg_end - (u64)init_pg_dir); +} + static void __init map_fdt(u64 fdt) { static u8 ptes[INIT_IDMAP_FDT_SIZE] __initdata __aligned(PAGE_SIZE); @@ -154,6 +207,7 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt) u64 va_base, pa_base = (u64)&_text; u64 kaslr_offset = pa_base % MIN_KIMG_ALIGN; int root_level = 4 - CONFIG_PGTABLE_LEVELS; + int va_bits = VA_BITS; int chosen; map_fdt((u64)fdt); @@ -165,8 +219,15 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt) chosen = fdt_path_offset(fdt, chosen_str); init_feature_override(boot_status, fdt, chosen); - if (VA_BITS > VA_BITS_MIN && cpu_has_lva()) - sysreg_clear_set(tcr_el1, TCR_T1SZ_MASK, TCR_T1SZ(VA_BITS)); + if (IS_ENABLED(CONFIG_ARM64_64K_PAGES) && !cpu_has_lva()) { + va_bits = VA_BITS_MIN; + } else if (IS_ENABLED(CONFIG_ARM64_LPA2) && !cpu_has_lpa2()) { + va_bits = VA_BITS_MIN; + root_level++; + } + + if (va_bits > VA_BITS_MIN) + sysreg_clear_set(tcr_el1, TCR_T1SZ_MASK, TCR_T1SZ(va_bits)); /* * The virtual KASLR displacement modulo 2MiB is decided by the @@ -184,6 +245,9 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt) kaslr_offset |= kaslr_seed & ~(MIN_KIMG_ALIGN - 1); } + if (IS_ENABLED(CONFIG_ARM64_LPA2) && va_bits > VA_BITS_MIN) + remap_idmap_for_lpa2(); + va_base = KIMAGE_VADDR + kaslr_offset; map_kernel(kaslr_offset, va_base - pa_base, root_level); } diff --git a/arch/arm64/kernel/pi/map_range.c b/arch/arm64/kernel/pi/map_range.c index 79e4f6a2efe1..5410b2cac590 100644 --- a/arch/arm64/kernel/pi/map_range.c +++ b/arch/arm64/kernel/pi/map_range.c @@ -87,14 +87,19 @@ void __init map_range(u64 *pte, u64 start, u64 end, u64 pa, pgprot_t prot, } } -asmlinkage u64 __init create_init_idmap(pgd_t *pg_dir) +asmlinkage u64 __init create_init_idmap(pgd_t *pg_dir, pteval_t clrmask) { u64 ptep = (u64)pg_dir + PAGE_SIZE; + pgprot_t text_prot = PAGE_KERNEL_ROX; + pgprot_t data_prot = PAGE_KERNEL; + + pgprot_val(text_prot) &= ~clrmask; + pgprot_val(data_prot) &= ~clrmask; map_range(&ptep, (u64)_stext, (u64)__initdata_begin, (u64)_stext, - PAGE_KERNEL_ROX, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0); + text_prot, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0); map_range(&ptep, (u64)__initdata_begin, (u64)_end, (u64)__initdata_begin, - PAGE_KERNEL, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0); + data_prot, IDMAP_ROOT_LEVEL, (pte_t *)pg_dir, false, 0); return ptep; } diff --git a/arch/arm64/kernel/pi/pi.h b/arch/arm64/kernel/pi/pi.h index 1ea282a5f96a..c91e5e965cd3 100644 --- a/arch/arm64/kernel/pi/pi.h +++ b/arch/arm64/kernel/pi/pi.h @@ -21,7 +21,7 @@ static inline void *prel64_to_pointer(const prel64_t *offset) extern bool dynamic_scs_is_enabled; -extern pgd_t init_idmap_pg_dir[]; +extern pgd_t init_idmap_pg_dir[], init_idmap_pg_end[]; void init_feature_override(u64 boot_status, const void *fdt, int chosen); u64 kaslr_early_init(void *fdt, int chosen); @@ -33,4 +33,4 @@ void map_range(u64 *pgd, u64 start, u64 end, u64 pa, pgprot_t prot, asmlinkage void early_map_kernel(u64 boot_status, void *fdt); -asmlinkage u64 create_init_idmap(pgd_t *pgd); +asmlinkage u64 create_init_idmap(pgd_t *pgd, pteval_t clrmask); diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 74c1db8ce271..0f427b50fdc3 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -238,7 +238,7 @@ void __init arm64_memblock_init(void) * physical address of PAGE_OFFSET, we have to *subtract* from it. */ if (IS_ENABLED(CONFIG_ARM64_VA_BITS_52) && (vabits_actual != 52)) - memstart_addr -= _PAGE_OFFSET(48) - _PAGE_OFFSET(52); + memstart_addr -= _PAGE_OFFSET(vabits_actual) - _PAGE_OFFSET(52); /* * Apply the memory limit if it was set. Since the kernel may be loaded diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index d2e9dec38a15..d30ae4d3fdd9 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -582,8 +582,12 @@ static void __init map_mem(pgd_t *pgdp) * entries at any level are being shared between the linear region and * the vmalloc region. Check whether this is true for the PGD level, in * which case it is guaranteed to be true for all other levels as well. + * (Unless we are running with support for LPA2, in which case the + * entire reduced VA space is covered by a single pgd_t which will have + * been populated without the PXNTable attribute by the time we get here.) */ - BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end)); + BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end) && + pgd_index(_PAGE_OFFSET(VA_BITS_MIN)) != PTRS_PER_PGD - 1); early_kfence_pool = arm64_kfence_alloc_pool(); diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index fa0d7c63f8d2..9d40f3ffd8d2 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -488,6 +488,9 @@ SYM_FUNC_START(__cpu_setup) mov x9, #64 - VA_BITS alternative_if ARM64_HAS_VA52 tcr_set_t1sz tcr, x9 +#ifdef CONFIG_ARM64_LPA2 + orr tcr, tcr, #TCR_DS +#endif alternative_else_nop_endif #endif -- cgit v1.2.3 From 6ed8a3a094b43a27ac35e5c95a8004a1d83d1b79 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:20 +0100 Subject: arm64: mm: Add 5 level paging support to fixmap and swapper handling Add support for using 5 levels of paging in the fixmap, as well as in the kernel page table handling code which uses fixmaps internally. This also handles the case where a 5 level build runs on hardware that only supports 4 levels of paging. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-79-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/fixmap.h | 1 + arch/arm64/include/asm/pgtable.h | 45 +++++++++++++++++++++++++++++++++----- arch/arm64/mm/fixmap.c | 2 +- arch/arm64/mm/mmu.c | 47 ++++++++++++++++++++++++++++++++++++---- 4 files changed, 85 insertions(+), 10 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/fixmap.h b/arch/arm64/include/asm/fixmap.h index 8aabd45e9a13..87e307804b99 100644 --- a/arch/arm64/include/asm/fixmap.h +++ b/arch/arm64/include/asm/fixmap.h @@ -87,6 +87,7 @@ enum fixed_addresses { FIX_PTE, FIX_PMD, FIX_PUD, + FIX_P4D, FIX_PGD, __end_of_fixed_addresses diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 7eb2b933ed3c..3d7fb3cde83d 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -621,12 +621,12 @@ static inline bool pud_table(pud_t pud) { return true; } PUD_TYPE_TABLE) #endif -extern pgd_t init_pg_dir[PTRS_PER_PGD]; +extern pgd_t init_pg_dir[]; extern pgd_t init_pg_end[]; -extern pgd_t swapper_pg_dir[PTRS_PER_PGD]; -extern pgd_t idmap_pg_dir[PTRS_PER_PGD]; -extern pgd_t tramp_pg_dir[PTRS_PER_PGD]; -extern pgd_t reserved_pg_dir[PTRS_PER_PGD]; +extern pgd_t swapper_pg_dir[]; +extern pgd_t idmap_pg_dir[]; +extern pgd_t tramp_pg_dir[]; +extern pgd_t reserved_pg_dir[]; extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd); @@ -891,12 +891,47 @@ static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long addr) return p4d_offset_lockless(pgdp, READ_ONCE(*pgdp), addr); } +static inline p4d_t *p4d_set_fixmap(unsigned long addr) +{ + if (!pgtable_l5_enabled()) + return NULL; + return (p4d_t *)set_fixmap_offset(FIX_P4D, addr); +} + +static inline p4d_t *p4d_set_fixmap_offset(pgd_t *pgdp, unsigned long addr) +{ + if (!pgtable_l5_enabled()) + return pgd_to_folded_p4d(pgdp, addr); + return p4d_set_fixmap(p4d_offset_phys(pgdp, addr)); +} + +static inline void p4d_clear_fixmap(void) +{ + if (pgtable_l5_enabled()) + clear_fixmap(FIX_P4D); +} + +/* use ONLY for statically allocated translation tables */ +static inline p4d_t *p4d_offset_kimg(pgd_t *pgdp, u64 addr) +{ + if (!pgtable_l5_enabled()) + return pgd_to_folded_p4d(pgdp, addr); + return (p4d_t *)__phys_to_kimg(p4d_offset_phys(pgdp, addr)); +} + #define pgd_page(pgd) pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd))) #else static inline bool pgtable_l5_enabled(void) { return false; } +/* Match p4d_offset folding in */ +#define p4d_set_fixmap(addr) NULL +#define p4d_set_fixmap_offset(p4dp, addr) ((p4d_t *)p4dp) +#define p4d_clear_fixmap() + +#define p4d_offset_kimg(dir,addr) ((p4d_t *)dir) + #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #define pgd_ERROR(e) \ diff --git a/arch/arm64/mm/fixmap.c b/arch/arm64/mm/fixmap.c index 9404f282f829..d22506e9c7fd 100644 --- a/arch/arm64/mm/fixmap.c +++ b/arch/arm64/mm/fixmap.c @@ -104,7 +104,7 @@ void __init early_fixmap_init(void) unsigned long end = FIXADDR_TOP; pgd_t *pgdp = pgd_offset_k(addr); - p4d_t *p4dp = p4d_offset(pgdp, addr); + p4d_t *p4dp = p4d_offset_kimg(pgdp, addr); early_fixmap_init_pud(p4dp, addr, end); } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index d30ae4d3fdd9..8e5b3a7c5afd 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -313,15 +313,14 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr, } while (addr = next, addr != end); } -static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end, +static void alloc_init_pud(p4d_t *p4dp, unsigned long addr, unsigned long end, phys_addr_t phys, pgprot_t prot, phys_addr_t (*pgtable_alloc)(int), int flags) { unsigned long next; - pud_t *pudp; - p4d_t *p4dp = p4d_offset(pgdp, addr); p4d_t p4d = READ_ONCE(*p4dp); + pud_t *pudp; if (p4d_none(p4d)) { p4dval_t p4dval = P4D_TYPE_TABLE | P4D_TABLE_UXN; @@ -369,6 +368,46 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end, pud_clear_fixmap(); } +static void alloc_init_p4d(pgd_t *pgdp, unsigned long addr, unsigned long end, + phys_addr_t phys, pgprot_t prot, + phys_addr_t (*pgtable_alloc)(int), + int flags) +{ + unsigned long next; + pgd_t pgd = READ_ONCE(*pgdp); + p4d_t *p4dp; + + if (pgd_none(pgd)) { + pgdval_t pgdval = PGD_TYPE_TABLE | PGD_TABLE_UXN; + phys_addr_t p4d_phys; + + if (flags & NO_EXEC_MAPPINGS) + pgdval |= PGD_TABLE_PXN; + BUG_ON(!pgtable_alloc); + p4d_phys = pgtable_alloc(P4D_SHIFT); + __pgd_populate(pgdp, p4d_phys, pgdval); + pgd = READ_ONCE(*pgdp); + } + BUG_ON(pgd_bad(pgd)); + + p4dp = p4d_set_fixmap_offset(pgdp, addr); + do { + p4d_t old_p4d = READ_ONCE(*p4dp); + + next = p4d_addr_end(addr, end); + + alloc_init_pud(p4dp, addr, next, phys, prot, + pgtable_alloc, flags); + + BUG_ON(p4d_val(old_p4d) != 0 && + p4d_val(old_p4d) != READ_ONCE(p4d_val(*p4dp))); + + phys += next - addr; + } while (p4dp++, addr = next, addr != end); + + p4d_clear_fixmap(); +} + static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, @@ -391,7 +430,7 @@ static void __create_pgd_mapping_locked(pgd_t *pgdir, phys_addr_t phys, do { next = pgd_addr_end(addr, end); - alloc_init_pud(pgdp, addr, next, phys, prot, pgtable_alloc, + alloc_init_p4d(pgdp, addr, next, phys, prot, pgtable_alloc, flags); phys += next - addr; } while (pgdp++, addr = next, addr != end); -- cgit v1.2.3 From 0383808e4d99ac31892655ae9dc93597eb6f1412 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:21 +0100 Subject: arm64: kasan: Reduce minimum shadow alignment and enable 5 level paging Allow the KASAN init code to deal with 5 levels of paging, and relax the requirement that the shadow region is aligned to the top level pgd_t size. This is necessary for LPA2 based 52-bit virtual addressing, where the KASAN shadow will never be aligned to the pgd_t size. Allowing this also enables the 16k/48-bit case for KASAN, which is a nice bonus. This involves some hackery to manipulate the root and next level page tables without having to distinguish all the various configurations, including 16k/48-bits (which has a two entry pgd_t level), and LPA2 configurations running with one translation level less on non-LPA2 hardware. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-80-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 2 +- arch/arm64/mm/kasan_init.c | 148 +++++++++++++++++++++++++++++++++++++++------ 2 files changed, 130 insertions(+), 20 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 8c2c36fffcf5..9ca3316d6379 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -164,7 +164,7 @@ config ARM64 select HAVE_ARCH_HUGE_VMAP select HAVE_ARCH_JUMP_LABEL select HAVE_ARCH_JUMP_LABEL_RELATIVE - select HAVE_ARCH_KASAN if !(ARM64_16K_PAGES && ARM64_VA_BITS_48) + select HAVE_ARCH_KASAN select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN select HAVE_ARCH_KASAN_SW_TAGS if HAVE_ARCH_KASAN select HAVE_ARCH_KASAN_HW_TAGS if (HAVE_ARCH_KASAN && ARM64_MTE) diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index a86ab99587c9..fbddbf9faf19 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -23,7 +23,7 @@ #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) -static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); +static pgd_t tmp_pg_dir[PTRS_PER_PTE] __initdata __aligned(PAGE_SIZE); /* * The p*d_populate functions call virt_to_phys implicitly so they can't be used @@ -99,6 +99,19 @@ static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, return early ? pud_offset_kimg(p4dp, addr) : pud_offset(p4dp, addr); } +static p4d_t *__init kasan_p4d_offset(pgd_t *pgdp, unsigned long addr, int node, + bool early) +{ + if (pgd_none(READ_ONCE(*pgdp))) { + phys_addr_t p4d_phys = early ? + __pa_symbol(kasan_early_shadow_p4d) + : kasan_alloc_zeroed_page(node); + __pgd_populate(pgdp, p4d_phys, PGD_TYPE_TABLE); + } + + return early ? p4d_offset_kimg(pgdp, addr) : p4d_offset(pgdp, addr); +} + static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr, unsigned long end, int node, bool early) { @@ -144,12 +157,12 @@ static void __init kasan_p4d_populate(pgd_t *pgdp, unsigned long addr, unsigned long end, int node, bool early) { unsigned long next; - p4d_t *p4dp = p4d_offset(pgdp, addr); + p4d_t *p4dp = kasan_p4d_offset(pgdp, addr, node, early); do { next = p4d_addr_end(addr, end); kasan_pud_populate(p4dp, addr, next, node, early); - } while (p4dp++, addr = next, addr != end); + } while (p4dp++, addr = next, addr != end && p4d_none(READ_ONCE(*p4dp))); } static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, @@ -165,19 +178,48 @@ static void __init kasan_pgd_populate(unsigned long addr, unsigned long end, } while (pgdp++, addr = next, addr != end); } +#if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS > 4 +#define SHADOW_ALIGN P4D_SIZE +#else +#define SHADOW_ALIGN PUD_SIZE +#endif + +/* + * Return whether 'addr' is aligned to the size covered by a root level + * descriptor. + */ +static bool __init root_level_aligned(u64 addr) +{ + int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 1) * (PAGE_SHIFT - 3); + + return (addr % (PAGE_SIZE << shift)) == 0; +} + /* The early shadow maps everything to a single page of zeroes */ asmlinkage void __init kasan_early_init(void) { BUILD_BUG_ON(KASAN_SHADOW_OFFSET != KASAN_SHADOW_END - (1UL << (64 - KASAN_SHADOW_SCALE_SHIFT))); - /* - * We cannot check the actual value of KASAN_SHADOW_START during build, - * as it depends on vabits_actual. As a best-effort approach, check - * potential values calculated based on VA_BITS and VA_BITS_MIN. - */ - BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS), PGDIR_SIZE)); - BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS_MIN), PGDIR_SIZE)); - BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, PGDIR_SIZE)); + BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS), SHADOW_ALIGN)); + BUILD_BUG_ON(!IS_ALIGNED(_KASAN_SHADOW_START(VA_BITS_MIN), SHADOW_ALIGN)); + BUILD_BUG_ON(!IS_ALIGNED(KASAN_SHADOW_END, SHADOW_ALIGN)); + + if (!root_level_aligned(KASAN_SHADOW_START)) { + /* + * The start address is misaligned, and so the next level table + * will be shared with the linear region. This can happen with + * 4 or 5 level paging, so install a generic pte_t[] as the + * next level. This prevents the kasan_pgd_populate call below + * from inserting an entry that refers to the shared KASAN zero + * shadow pud_t[]/p4d_t[], which could end up getting corrupted + * when the linear region is mapped. + */ + static pte_t tbl[PTRS_PER_PTE] __page_aligned_bss; + pgd_t *pgdp = pgd_offset_k(KASAN_SHADOW_START); + + set_pgd(pgdp, __pgd(__pa_symbol(tbl) | PGD_TYPE_TABLE)); + } + kasan_pgd_populate(KASAN_SHADOW_START, KASAN_SHADOW_END, NUMA_NO_NODE, true); } @@ -189,20 +231,75 @@ static void __init kasan_map_populate(unsigned long start, unsigned long end, kasan_pgd_populate(start & PAGE_MASK, PAGE_ALIGN(end), node, false); } -static void __init clear_pgds(unsigned long start, - unsigned long end) +/* + * Return the descriptor index of 'addr' in the root level table + */ +static int __init root_level_idx(u64 addr) { /* - * Remove references to kasan page tables from - * swapper_pg_dir. pgd_clear() can't be used - * here because it's nop on 2,3-level pagetable setups + * On 64k pages, the TTBR1 range root tables are extended for 52-bit + * virtual addressing, and TTBR1 will simply point to the pgd_t entry + * that covers the start of the 48-bit addressable VA space if LVA is + * not implemented. This means we need to index the table as usual, + * instead of masking off bits based on vabits_actual. */ - for (; start < end; start += PGDIR_SIZE) - set_pgd(pgd_offset_k(start), __pgd(0)); + u64 vabits = IS_ENABLED(CONFIG_ARM64_64K_PAGES) ? VA_BITS + : vabits_actual; + int shift = (ARM64_HW_PGTABLE_LEVELS(vabits) - 1) * (PAGE_SHIFT - 3); + + return (addr & ~_PAGE_OFFSET(vabits)) >> (shift + PAGE_SHIFT); +} + +/* + * Clone a next level table from swapper_pg_dir into tmp_pg_dir + */ +static void __init clone_next_level(u64 addr, pgd_t *tmp_pg_dir, pud_t *pud) +{ + int idx = root_level_idx(addr); + pgd_t pgd = READ_ONCE(swapper_pg_dir[idx]); + pud_t *pudp = (pud_t *)__phys_to_kimg(__pgd_to_phys(pgd)); + + memcpy(pud, pudp, PAGE_SIZE); + tmp_pg_dir[idx] = __pgd(__phys_to_pgd_val(__pa_symbol(pud)) | + PUD_TYPE_TABLE); +} + +/* + * Return the descriptor index of 'addr' in the next level table + */ +static int __init next_level_idx(u64 addr) +{ + int shift = (ARM64_HW_PGTABLE_LEVELS(vabits_actual) - 2) * (PAGE_SHIFT - 3); + + return (addr >> (shift + PAGE_SHIFT)) % PTRS_PER_PTE; +} + +/* + * Dereference the table descriptor at 'pgd_idx' and clear the entries from + * 'start' to 'end' (exclusive) from the table. + */ +static void __init clear_next_level(int pgd_idx, int start, int end) +{ + pgd_t pgd = READ_ONCE(swapper_pg_dir[pgd_idx]); + pud_t *pudp = (pud_t *)__phys_to_kimg(__pgd_to_phys(pgd)); + + memset(&pudp[start], 0, (end - start) * sizeof(pud_t)); +} + +static void __init clear_shadow(u64 start, u64 end) +{ + int l = root_level_idx(start), m = root_level_idx(end); + + if (!root_level_aligned(start)) + clear_next_level(l++, next_level_idx(start), PTRS_PER_PTE); + if (!root_level_aligned(end)) + clear_next_level(m, 0, next_level_idx(end)); + memset(&swapper_pg_dir[l], 0, (m - l) * sizeof(pgd_t)); } static void __init kasan_init_shadow(void) { + static pud_t pud[2][PTRS_PER_PUD] __initdata __aligned(PAGE_SIZE); u64 kimg_shadow_start, kimg_shadow_end; u64 mod_shadow_start; u64 vmalloc_shadow_end; @@ -224,10 +321,23 @@ static void __init kasan_init_shadow(void) * setup will be finished. */ memcpy(tmp_pg_dir, swapper_pg_dir, sizeof(tmp_pg_dir)); + + /* + * If the start or end address of the shadow region is not aligned to + * the root level size, we have to allocate a temporary next-level table + * in each case, clone the next level of descriptors, and install the + * table into tmp_pg_dir. Note that with 5 levels of paging, the next + * level will in fact be p4d_t, but that makes no difference in this + * case. + */ + if (!root_level_aligned(KASAN_SHADOW_START)) + clone_next_level(KASAN_SHADOW_START, tmp_pg_dir, pud[0]); + if (!root_level_aligned(KASAN_SHADOW_END)) + clone_next_level(KASAN_SHADOW_END, tmp_pg_dir, pud[1]); dsb(ishst); cpu_replace_ttbr1(lm_alias(tmp_pg_dir)); - clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END); + clear_shadow(KASAN_SHADOW_START, KASAN_SHADOW_END); kasan_map_populate(kimg_shadow_start, kimg_shadow_end, early_pfn_to_nid(virt_to_pfn(lm_alias(KERNEL_START)))); -- cgit v1.2.3 From 0dd4f60a2c76938c2625f6c630c225699d97608b Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:22 +0100 Subject: arm64: mm: Add support for folding PUDs at runtime In order to support LPA2 on 16k pages in a way that permits non-LPA2 systems to run the same kernel image, we have to be able to fall back to at most 48 bits of virtual addressing. Falling back to 48 bits would result in a level 0 with only 2 entries, which is suboptimal in terms of TLB utilization. So instead, let's fall back to 47 bits in that case. This means we need to be able to fold PUDs dynamically, similar to how we fold P4Ds for 48 bit virtual addressing on LPA2 with 4k pages. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-81-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/pgalloc.h | 12 +++++- arch/arm64/include/asm/pgtable.h | 87 +++++++++++++++++++++++++++++++++++----- arch/arm64/include/asm/tlb.h | 3 ++ arch/arm64/kernel/cpufeature.c | 2 + arch/arm64/mm/mmu.c | 2 +- arch/arm64/mm/pgd.c | 2 + 6 files changed, 95 insertions(+), 13 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index cae8c648f462..aeba2cf15a25 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -14,6 +14,7 @@ #include #define __HAVE_ARCH_PGD_FREE +#define __HAVE_ARCH_PUD_FREE #include #define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t)) @@ -43,7 +44,8 @@ static inline void __pud_populate(pud_t *pudp, phys_addr_t pmdp, pudval_t prot) static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) { - set_p4d(p4dp, __p4d(__phys_to_p4d_val(pudp) | prot)); + if (pgtable_l4_enabled()) + set_p4d(p4dp, __p4d(__phys_to_p4d_val(pudp) | prot)); } static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp) @@ -53,6 +55,14 @@ static inline void p4d_populate(struct mm_struct *mm, p4d_t *p4dp, pud_t *pudp) p4dval |= (mm == &init_mm) ? P4D_TABLE_UXN : P4D_TABLE_PXN; __p4d_populate(p4dp, __pa(pudp), p4dval); } + +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + if (!pgtable_l4_enabled()) + return; + BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); + free_page((unsigned long)pud); +} #else static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) { diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index 3d7fb3cde83d..b3c716fa8121 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -759,12 +759,27 @@ static inline pmd_t *pud_pgtable(pud_t pud) #if CONFIG_PGTABLE_LEVELS > 3 +static __always_inline bool pgtable_l4_enabled(void) +{ + if (CONFIG_PGTABLE_LEVELS > 4 || !IS_ENABLED(CONFIG_ARM64_LPA2)) + return true; + if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) + return vabits_actual == VA_BITS; + return alternative_has_cap_unlikely(ARM64_HAS_VA52); +} + +static inline bool mm_pud_folded(const struct mm_struct *mm) +{ + return !pgtable_l4_enabled(); +} +#define mm_pud_folded mm_pud_folded + #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e)) -#define p4d_none(p4d) (!p4d_val(p4d)) -#define p4d_bad(p4d) (!(p4d_val(p4d) & 2)) -#define p4d_present(p4d) (p4d_val(p4d)) +#define p4d_none(p4d) (pgtable_l4_enabled() && !p4d_val(p4d)) +#define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & 2)) +#define p4d_present(p4d) (!p4d_none(p4d)) static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) { @@ -780,7 +795,8 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) static inline void p4d_clear(p4d_t *p4dp) { - set_p4d(p4dp, __p4d(0)); + if (pgtable_l4_enabled()) + set_p4d(p4dp, __p4d(0)); } static inline phys_addr_t p4d_page_paddr(p4d_t p4d) @@ -788,25 +804,74 @@ static inline phys_addr_t p4d_page_paddr(p4d_t p4d) return __p4d_to_phys(p4d); } +#define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) + +static inline pud_t *p4d_to_folded_pud(p4d_t *p4dp, unsigned long addr) +{ + return (pud_t *)PTR_ALIGN_DOWN(p4dp, PAGE_SIZE) + pud_index(addr); +} + static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_page_paddr(p4d)); } -/* Find an entry in the first-level page table. */ -#define pud_offset_phys(dir, addr) (p4d_page_paddr(READ_ONCE(*(dir))) + pud_index(addr) * sizeof(pud_t)) +static inline phys_addr_t pud_offset_phys(p4d_t *p4dp, unsigned long addr) +{ + BUG_ON(!pgtable_l4_enabled()); -#define pud_set_fixmap(addr) ((pud_t *)set_fixmap_offset(FIX_PUD, addr)) -#define pud_set_fixmap_offset(p4d, addr) pud_set_fixmap(pud_offset_phys(p4d, addr)) -#define pud_clear_fixmap() clear_fixmap(FIX_PUD) + return p4d_page_paddr(READ_ONCE(*p4dp)) + pud_index(addr) * sizeof(pud_t); +} -#define p4d_page(p4d) pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d))) +static inline +pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long addr) +{ + if (!pgtable_l4_enabled()) + return p4d_to_folded_pud(p4dp, addr); + return (pud_t *)__va(p4d_page_paddr(p4d)) + pud_index(addr); +} +#define pud_offset_lockless pud_offset_lockless + +static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long addr) +{ + return pud_offset_lockless(p4dp, READ_ONCE(*p4dp), addr); +} +#define pud_offset pud_offset + +static inline pud_t *pud_set_fixmap(unsigned long addr) +{ + if (!pgtable_l4_enabled()) + return NULL; + return (pud_t *)set_fixmap_offset(FIX_PUD, addr); +} + +static inline pud_t *pud_set_fixmap_offset(p4d_t *p4dp, unsigned long addr) +{ + if (!pgtable_l4_enabled()) + return p4d_to_folded_pud(p4dp, addr); + return pud_set_fixmap(pud_offset_phys(p4dp, addr)); +} + +static inline void pud_clear_fixmap(void) +{ + if (pgtable_l4_enabled()) + clear_fixmap(FIX_PUD); +} /* use ONLY for statically allocated translation tables */ -#define pud_offset_kimg(dir,addr) ((pud_t *)__phys_to_kimg(pud_offset_phys((dir), (addr)))) +static inline pud_t *pud_offset_kimg(p4d_t *p4dp, u64 addr) +{ + if (!pgtable_l4_enabled()) + return p4d_to_folded_pud(p4dp, addr); + return (pud_t *)__phys_to_kimg(pud_offset_phys(p4dp, addr)); +} + +#define p4d_page(p4d) pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d))) #else +static inline bool pgtable_l4_enabled(void) { return false; } + #define p4d_page_paddr(p4d) ({ BUILD_BUG(); 0;}) /* Match pud_offset folding in */ diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h index 0150deb332af..a947c6e784ed 100644 --- a/arch/arm64/include/asm/tlb.h +++ b/arch/arm64/include/asm/tlb.h @@ -103,6 +103,9 @@ static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pudp, { struct ptdesc *ptdesc = virt_to_ptdesc(pudp); + if (!pgtable_l4_enabled()) + return; + pagetable_pud_dtor(ptdesc); tlb_remove_ptdesc(tlb, ptdesc); } diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index bc5e4e569864..94f035f6c421 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1767,6 +1767,8 @@ static int __init __kpti_install_ng_mappings(void *__unused) if (levels == 5 && !pgtable_l5_enabled()) levels = 4; + else if (levels == 4 && !pgtable_l4_enabled()) + levels = 3; remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 8e5b3a7c5afd..b131ed31a6c8 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1065,7 +1065,7 @@ static void free_empty_pud_table(p4d_t *p4dp, unsigned long addr, free_empty_pmd_table(pudp, addr, next, floor, ceiling); } while (addr = next, addr < end); - if (CONFIG_PGTABLE_LEVELS <= 3) + if (!pgtable_l4_enabled()) return; if (!pgtable_range_aligned(start, end, floor, ceiling, P4D_MASK)) diff --git a/arch/arm64/mm/pgd.c b/arch/arm64/mm/pgd.c index 3c4f8a279d2b..0c501cabc238 100644 --- a/arch/arm64/mm/pgd.c +++ b/arch/arm64/mm/pgd.c @@ -21,6 +21,8 @@ static bool pgdir_is_page_size(void) { if (PGD_SIZE == PAGE_SIZE) return true; + if (CONFIG_PGTABLE_LEVELS == 4) + return !pgtable_l4_enabled(); if (CONFIG_PGTABLE_LEVELS == 5) return !pgtable_l5_enabled(); return false; -- cgit v1.2.3 From 16f22981b6d7ea6815d2e4527b82cac5e2f65c89 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:23 +0100 Subject: arm64: ptdump: Disregard unaddressable VA space Configurations built with support for 52-bit virtual addressing can also run on CPUs that only support 48 bits of VA space, in which case only that part of swapper_pg_dir that represents the 48-bit addressable region is relevant, and everything else is ignored by the hardware. Our software pagetable walker has little in the way of input address validation, and so it will happily start a walk from an address that is not representable by the number of paging levels that are actually active, resulting in lots of bogus output from the page table dumper unless we take care to start at a valid address. So define the start address at runtime based on vabits_actual. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-82-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/mm/ptdump.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c index 5f0849528ccf..16d0cf1d85c4 100644 --- a/arch/arm64/mm/ptdump.c +++ b/arch/arm64/mm/ptdump.c @@ -313,7 +313,6 @@ static void __init ptdump_initialize(void) static struct ptdump_info kernel_ptdump_info __ro_after_init = { .mm = &init_mm, - .base_addr = PAGE_OFFSET, }; void ptdump_check_wx(void) @@ -329,7 +328,7 @@ void ptdump_check_wx(void) .ptdump = { .note_page = note_page, .range = (struct ptdump_range[]) { - {PAGE_OFFSET, ~0UL}, + {_PAGE_OFFSET(vabits_actual), ~0UL}, {0, 0} } } @@ -370,6 +369,7 @@ static int __init ptdump_init(void) static struct addr_marker address_markers[ARRAY_SIZE(m)] __ro_after_init; kernel_ptdump_info.markers = memcpy(address_markers, m, sizeof(m)); + kernel_ptdump_info.base_addr = page_offset; ptdump_initialize(); ptdump_debugfs_register(&kernel_ptdump_info, "kernel_page_tables"); -- cgit v1.2.3 From d40900fcb39700207823486ca512a1a87d6331e2 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:24 +0100 Subject: arm64: ptdump: Deal with translation levels folded at runtime Currently, the ptdump code deals with folded PMD or PUD levels at build time, by omitting those levels when invoking note_page. IOW, note_page() is never invoked with level == 1 if P4Ds are folded in the build configuration. With the introduction of LPA2 support, we will defer some of these folding decisions to runtime, so let's take care of this by overriding the 'level' argument when this condition triggers. Substituting the PUD or PMD strings for "PGD" when the level in question is folded at build time is no longer necessary, and so the conditional expressions can be simplified. This also makes the indirection of the 'name' field unnecessary, so change that into a char[] array, and make the whole thing __ro_after_init. Note that the mm_p?d_folded() functions currently ignore their mm pointer arguments, but let's wire them up correctly anyway. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-83-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/mm/ptdump.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c index 16d0cf1d85c4..5b87f8d623f7 100644 --- a/arch/arm64/mm/ptdump.c +++ b/arch/arm64/mm/ptdump.c @@ -48,6 +48,7 @@ struct pg_state { struct ptdump_state ptdump; struct seq_file *seq; const struct addr_marker *marker; + const struct mm_struct *mm; unsigned long start_address; int level; u64 current_prot; @@ -144,12 +145,12 @@ static const struct prot_bits pte_bits[] = { struct pg_level { const struct prot_bits *bits; - const char *name; - size_t num; + char name[4]; + int num; u64 mask; }; -static struct pg_level pg_level[] = { +static struct pg_level pg_level[] __ro_after_init = { { /* pgd */ .name = "PGD", .bits = pte_bits, @@ -159,11 +160,11 @@ static struct pg_level pg_level[] = { .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, { /* pud */ - .name = (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD", + .name = "PUD", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, { /* pmd */ - .name = (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD", + .name = "PMD", .bits = pte_bits, .num = ARRAY_SIZE(pte_bits), }, { /* pte */ @@ -227,6 +228,11 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level, static const char units[] = "KMGTPE"; u64 prot = 0; + /* check if the current level has been folded dynamically */ + if ((level == 1 && mm_p4d_folded(st->mm)) || + (level == 2 && mm_pud_folded(st->mm))) + level = 0; + if (level >= 0) prot = val & pg_level[level].mask; @@ -288,6 +294,7 @@ void ptdump_walk(struct seq_file *s, struct ptdump_info *info) st = (struct pg_state){ .seq = s, .marker = info->markers, + .mm = info->mm, .level = -1, .ptdump = { .note_page = note_page, -- cgit v1.2.3 From 95e059b5db6082e62632f40434059759c7c1f6ed Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:25 +0100 Subject: arm64: kvm: avoid CONFIG_PGTABLE_LEVELS for runtime levels get_user_mapping_size() uses vabits_actual and CONFIG_PGTABLE_LEVELS to provide the starting point for a table walk. This is fine for LVA, as the number of translation levels is the same regardless of whether LVA is enabled. However, with LPA2, this will no longer be the case, so let's derive the number of levels from the number of VA bits directly. Acked-by: Marc Zyngier Acked-by: Oliver Upton Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-84-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/kvm/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/arm64') diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index 6fa9e816df40..cd9456a03e38 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -805,7 +805,7 @@ static int get_user_mapping_size(struct kvm *kvm, u64 addr) .pgd = (kvm_pteref_t)kvm->mm->pgd, .ia_bits = vabits_actual, .start_level = (KVM_PGTABLE_LAST_LEVEL - - CONFIG_PGTABLE_LEVELS + 1), + ARM64_HW_PGTABLE_LEVELS(pgt.ia_bits) + 1), .mm_ops = &kvm_user_mm_ops, }; unsigned long flags; -- cgit v1.2.3 From 352b0395b5053fca01b9dc60294235511f5f3d65 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:26 +0100 Subject: arm64: Enable 52-bit virtual addressing for 4k and 16k granule configs Update Kconfig to permit 4k and 16k granule configurations to be built with 52-bit virtual addressing, now that all the prerequisites are in place. While at it, update the feature description so it matches on the appropriate feature bits depending on the page size. For simplicity, let's just keep ARM64_HAS_VA52 as the feature name. Note that LPA2 based 52-bit virtual addressing requires 52-bit physical addressing support to be enabled as well, as programming TCR.TxSZ to values below 16 is not allowed unless TCR.DS is set, which is what activates the 52-bit physical addressing support. While supporting the converse (52-bit physical addressing without 52-bit virtual addressing) would be possible in principle, let's keep things simple, by only allowing these features to be enabled at the same time. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-85-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 17 ++++++++++------- arch/arm64/kernel/cpufeature.c | 22 ++++++++++++++++++---- 2 files changed, 28 insertions(+), 11 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 9ca3316d6379..eed8fef08a10 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -368,7 +368,9 @@ config PGTABLE_LEVELS default 3 if ARM64_64K_PAGES && (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) default 3 if ARM64_4K_PAGES && ARM64_VA_BITS_39 default 3 if ARM64_16K_PAGES && ARM64_VA_BITS_47 + default 4 if ARM64_16K_PAGES && (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) default 4 if !ARM64_64K_PAGES && ARM64_VA_BITS_48 + default 5 if ARM64_4K_PAGES && ARM64_VA_BITS_52 config ARCH_SUPPORTS_UPROBES def_bool y @@ -396,13 +398,13 @@ config BUILTIN_RETURN_ADDRESS_STRIPS_PAC config KASAN_SHADOW_OFFSET hex depends on KASAN_GENERIC || KASAN_SW_TAGS - default 0xdfff800000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && !KASAN_SW_TAGS - default 0xdfffc00000000000 if ARM64_VA_BITS_47 && !KASAN_SW_TAGS + default 0xdfff800000000000 if (ARM64_VA_BITS_48 || (ARM64_VA_BITS_52 && !ARM64_16K_PAGES)) && !KASAN_SW_TAGS + default 0xdfffc00000000000 if (ARM64_VA_BITS_47 || ARM64_VA_BITS_52) && ARM64_16K_PAGES && !KASAN_SW_TAGS default 0xdffffe0000000000 if ARM64_VA_BITS_42 && !KASAN_SW_TAGS default 0xdfffffc000000000 if ARM64_VA_BITS_39 && !KASAN_SW_TAGS default 0xdffffff800000000 if ARM64_VA_BITS_36 && !KASAN_SW_TAGS - default 0xefff800000000000 if (ARM64_VA_BITS_48 || ARM64_VA_BITS_52) && KASAN_SW_TAGS - default 0xefffc00000000000 if ARM64_VA_BITS_47 && KASAN_SW_TAGS + default 0xefff800000000000 if (ARM64_VA_BITS_48 || (ARM64_VA_BITS_52 && !ARM64_16K_PAGES)) && KASAN_SW_TAGS + default 0xefffc00000000000 if (ARM64_VA_BITS_47 || ARM64_VA_BITS_52) && ARM64_16K_PAGES && KASAN_SW_TAGS default 0xeffffe0000000000 if ARM64_VA_BITS_42 && KASAN_SW_TAGS default 0xefffffc000000000 if ARM64_VA_BITS_39 && KASAN_SW_TAGS default 0xeffffff800000000 if ARM64_VA_BITS_36 && KASAN_SW_TAGS @@ -1310,7 +1312,7 @@ config ARM64_VA_BITS_48 config ARM64_VA_BITS_52 bool "52-bit" - depends on ARM64_64K_PAGES && (ARM64_PAN || !ARM64_SW_TTBR0_PAN) + depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN help Enable 52-bit virtual addressing for userspace when explicitly requested via a hint to mmap(). The kernel will also use 52-bit @@ -1357,10 +1359,11 @@ choice config ARM64_PA_BITS_48 bool "48-bit" + depends on ARM64_64K_PAGES || !ARM64_VA_BITS_52 config ARM64_PA_BITS_52 - bool "52-bit (ARMv8.2)" - depends on ARM64_64K_PAGES + bool "52-bit" + depends on ARM64_64K_PAGES || ARM64_VA_BITS_52 depends on ARM64_PAN || !ARM64_SW_TTBR0_PAN help Enable support for a 52-bit physical address space, introduced as diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 94f035f6c421..0be9296e9253 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2703,15 +2703,29 @@ static const struct arm64_cpu_capabilities arm64_features[] = { }, #ifdef CONFIG_ARM64_VA_BITS_52 { - .desc = "52-bit Virtual Addressing (LVA)", .capability = ARM64_HAS_VA52, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, - .sys_reg = SYS_ID_AA64MMFR2_EL1, - .sign = FTR_UNSIGNED, + .matches = has_cpuid_feature, .field_width = 4, +#ifdef CONFIG_ARM64_64K_PAGES + .desc = "52-bit Virtual Addressing (LVA)", + .sign = FTR_SIGNED, + .sys_reg = SYS_ID_AA64MMFR2_EL1, .field_pos = ID_AA64MMFR2_EL1_VARange_SHIFT, - .matches = has_cpuid_feature, .min_field_value = ID_AA64MMFR2_EL1_VARange_52, +#else + .desc = "52-bit Virtual Addressing (LPA2)", + .sys_reg = SYS_ID_AA64MMFR0_EL1, +#ifdef CONFIG_ARM64_4K_PAGES + .sign = FTR_SIGNED, + .field_pos = ID_AA64MMFR0_EL1_TGRAN4_SHIFT, + .min_field_value = ID_AA64MMFR0_EL1_TGRAN4_52_BIT, +#else + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64MMFR0_EL1_TGRAN16_SHIFT, + .min_field_value = ID_AA64MMFR0_EL1_TGRAN16_52_BIT, +#endif +#endif }, #endif {}, -- cgit v1.2.3 From 5d101654226d64ac0a6928019fbf476b46e9d14b Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:27 +0100 Subject: arm64: defconfig: Enable LPA2 support We typically enable support in defconfig for all architectural features for which we can detect at runtime if the hardware actually supports them. Now that we have implemented support for LPA2 based 52-bit virtual addressing in a way that should not impact 48-bit operation on non-LPA2 CPU, we can do the same, and enable 52-bit virtual addressing by default. Catalin adds: Currently the "Virtual address space size" arch/arm64/Kconfig menu entry sets different defaults for each page size. However, all are overridden by the defconfig to 48 bits. Set the new default in Kconfig and remove the defconfig line. [ardb: squash follow-up fix from Catalin] Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240214122845.2033971-86-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 4 +--- arch/arm64/configs/defconfig | 1 - 2 files changed, 1 insertion(+), 4 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index eed8fef08a10..160856de9bbb 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1283,9 +1283,7 @@ endchoice choice prompt "Virtual address space size" - default ARM64_VA_BITS_39 if ARM64_4K_PAGES - default ARM64_VA_BITS_47 if ARM64_16K_PAGES - default ARM64_VA_BITS_42 if ARM64_64K_PAGES + default ARM64_VA_BITS_52 help Allows choosing one of multiple possible virtual address space sizes. The level of translation table is determined by diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig index e6cf3e5d63c3..f086b0624ec8 100644 --- a/arch/arm64/configs/defconfig +++ b/arch/arm64/configs/defconfig @@ -76,7 +76,6 @@ CONFIG_ARCH_VEXPRESS=y CONFIG_ARCH_VISCONTI=y CONFIG_ARCH_XGENE=y CONFIG_ARCH_ZYNQMP=y -CONFIG_ARM64_VA_BITS_48=y CONFIG_SCHED_MC=y CONFIG_SCHED_SMT=y CONFIG_NUMA=y -- cgit v1.2.3 From 50e3ed0f93f4f62ed2aa83de5db6cb84ecdd5707 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Wed, 14 Feb 2024 13:29:29 +0100 Subject: arm64: mm: add support for WXN memory translation attribute The AArch64 virtual memory system supports a global WXN control, which can be enabled to make all writable mappings implicitly no-exec. This is a useful hardening feature, as it prevents mistakes in managing page table permissions from being exploited to attack the system. When enabled at EL1, the restrictions apply to both EL1 and EL0. EL1 is completely under our control, and has been cleaned up to allow WXN to be enabled from boot onwards. EL0 is not under our control, but given that widely deployed security features such as selinux or PaX already limit the ability of user space to create mappings that are writable and executable at the same time, the impact of enabling this for EL0 is expected to be limited. (For this reason, common user space libraries that have a legitimate need for manipulating executable code already carry fallbacks such as [0].) If enabled at compile time, the feature can still be disabled at boot if needed, by passing arm64.nowxn on the kernel command line. [0] https://github.com/libffi/libffi/blob/master/src/closures.c#L440 Signed-off-by: Ard Biesheuvel Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20240214122845.2033971-88-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/Kconfig | 11 +++++++++++ arch/arm64/include/asm/cpufeature.h | 8 ++++++++ arch/arm64/include/asm/mman.h | 36 +++++++++++++++++++++++++++++++++++ arch/arm64/include/asm/mmu_context.h | 30 ++++++++++++++++++++++++++++- arch/arm64/kernel/pi/idreg-override.c | 4 +++- arch/arm64/kernel/pi/map_kernel.c | 23 ++++++++++++++++++++++ arch/arm64/mm/proc.S | 6 ++++++ 7 files changed, 116 insertions(+), 2 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 160856de9bbb..7761ffc6dbcf 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1608,6 +1608,17 @@ config RODATA_FULL_DEFAULT_ENABLED This requires the linear region to be mapped down to pages, which may adversely affect performance in some cases. +config ARM64_WXN + bool "Enable WXN attribute so all writable mappings are non-exec" + help + Set the WXN bit in the SCTLR system register so that all writable + mappings are treated as if the PXN/UXN bit is set as well. + If this is set to Y, it can still be disabled at runtime by + passing 'arm64.nowxn' on the kernel command line. + + This should only be set if no software needs to be supported that + relies on being able to execute from writable mappings. + config ARM64_SW_TTBR0_PAN bool "Emulate Privileged Access Never using TTBR0_EL1 switching" help diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index a8f97690ce1f..ee33b7e52da7 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -18,6 +18,7 @@ #define ARM64_SW_FEATURE_OVERRIDE_NOKASLR 0 #define ARM64_SW_FEATURE_OVERRIDE_HVHE 4 #define ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF 8 +#define ARM64_SW_FEATURE_OVERRIDE_NOWXN 12 #ifndef __ASSEMBLY__ @@ -962,6 +963,13 @@ static inline bool kaslr_disabled_cmdline(void) return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOKASLR); } +static inline bool arm64_wxn_enabled(void) +{ + if (!IS_ENABLED(CONFIG_ARM64_WXN)) + return false; + return !arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOWXN); +} + u32 get_kvm_ipa_limit(void); void dump_cpu_features(void); diff --git a/arch/arm64/include/asm/mman.h b/arch/arm64/include/asm/mman.h index 5966ee4a6154..6d4940342ba7 100644 --- a/arch/arm64/include/asm/mman.h +++ b/arch/arm64/include/asm/mman.h @@ -35,11 +35,40 @@ static inline unsigned long arch_calc_vm_flag_bits(unsigned long flags) } #define arch_calc_vm_flag_bits(flags) arch_calc_vm_flag_bits(flags) +static inline bool arm64_check_wx_prot(unsigned long prot, + struct task_struct *tsk) +{ + /* + * When we are running with SCTLR_ELx.WXN==1, writable mappings are + * implicitly non-executable. This means we should reject such mappings + * when user space attempts to create them using mmap() or mprotect(). + */ + if (arm64_wxn_enabled() && + ((prot & (PROT_WRITE | PROT_EXEC)) == (PROT_WRITE | PROT_EXEC))) { + /* + * User space libraries such as libffi carry elaborate + * heuristics to decide whether it is worth it to even attempt + * to create writable executable mappings, as PaX or selinux + * enabled systems will outright reject it. They will usually + * fall back to something else (e.g., two separate shared + * mmap()s of a temporary file) on failure. + */ + pr_info_ratelimited( + "process %s (%d) attempted to create PROT_WRITE+PROT_EXEC mapping\n", + tsk->comm, tsk->pid); + return false; + } + return true; +} + static inline bool arch_validate_prot(unsigned long prot, unsigned long addr __always_unused) { unsigned long supported = PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM; + if (!arm64_check_wx_prot(prot, current)) + return false; + if (system_supports_bti()) supported |= PROT_BTI; @@ -50,6 +79,13 @@ static inline bool arch_validate_prot(unsigned long prot, } #define arch_validate_prot(prot, addr) arch_validate_prot(prot, addr) +static inline bool arch_validate_mmap_prot(unsigned long prot, + unsigned long addr) +{ + return arm64_check_wx_prot(prot, current); +} +#define arch_validate_mmap_prot arch_validate_mmap_prot + static inline bool arch_validate_flags(unsigned long vm_flags) { if (!system_supports_mte()) diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h index c768d16b81a4..f0fe2d09d139 100644 --- a/arch/arm64/include/asm/mmu_context.h +++ b/arch/arm64/include/asm/mmu_context.h @@ -20,13 +20,41 @@ #include #include #include -#include #include #include #include extern bool rodata_full; +static inline int arch_dup_mmap(struct mm_struct *oldmm, + struct mm_struct *mm) +{ + return 0; +} + +static inline void arch_exit_mmap(struct mm_struct *mm) +{ +} + +static inline void arch_unmap(struct mm_struct *mm, + unsigned long start, unsigned long end) +{ +} + +static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, + bool write, bool execute, bool foreign) +{ + if (IS_ENABLED(CONFIG_ARM64_WXN) && execute && + (vma->vm_flags & (VM_WRITE | VM_EXEC)) == (VM_WRITE | VM_EXEC)) { + pr_warn_ratelimited( + "process %s (%d) attempted to execute from writable memory\n", + current->comm, current->pid); + /* disallow unless the nowxn override is set */ + return !arm64_wxn_enabled(); + } + return true; +} + static inline void contextidr_thread_switch(struct task_struct *next) { if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR)) diff --git a/arch/arm64/kernel/pi/idreg-override.c b/arch/arm64/kernel/pi/idreg-override.c index aad399796e81..bccfee34f62f 100644 --- a/arch/arm64/kernel/pi/idreg-override.c +++ b/arch/arm64/kernel/pi/idreg-override.c @@ -189,6 +189,7 @@ static const struct ftr_set_desc sw_features __prel64_initconst = { FIELD("nokaslr", ARM64_SW_FEATURE_OVERRIDE_NOKASLR, NULL), FIELD("hvhe", ARM64_SW_FEATURE_OVERRIDE_HVHE, hvhe_filter), FIELD("rodataoff", ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF, NULL), + FIELD("nowxn", ARM64_SW_FEATURE_OVERRIDE_NOWXN, NULL), {} }, }; @@ -221,8 +222,9 @@ static const struct { { "arm64.nomops", "id_aa64isar2.mops=0" }, { "arm64.nomte", "id_aa64pfr1.mte=0" }, { "nokaslr", "arm64_sw.nokaslr=1" }, - { "rodata=off", "arm64_sw.rodataoff=1" }, + { "rodata=off", "arm64_sw.rodataoff=1 arm64_sw.nowxn=1" }, { "arm64.nolva", "id_aa64mmfr2.varange=0" }, + { "arm64.nowxn", "arm64_sw.nowxn=1" }, }; static int __init parse_hexdigit(const char *p, u64 *v) diff --git a/arch/arm64/kernel/pi/map_kernel.c b/arch/arm64/kernel/pi/map_kernel.c index 5fa08e13e17e..cac1e1f63c44 100644 --- a/arch/arm64/kernel/pi/map_kernel.c +++ b/arch/arm64/kernel/pi/map_kernel.c @@ -132,6 +132,25 @@ static void __init map_kernel(u64 kaslr_offset, u64 va_offset, int root_level) idmap_cpu_replace_ttbr1(swapper_pg_dir); } +static void noinline __section(".idmap.text") disable_wxn(void) +{ + u64 sctlr = read_sysreg(sctlr_el1) & ~SCTLR_ELx_WXN; + + /* + * We cannot safely clear the WXN bit while the MMU and caches are on, + * so turn the MMU off, flush the TLBs and turn it on again but with + * the WXN bit cleared this time. + */ + asm(" msr sctlr_el1, %0 ;" + " isb ;" + " tlbi vmalle1 ;" + " dsb nsh ;" + " isb ;" + " msr sctlr_el1, %1 ;" + " isb ;" + :: "r"(sctlr & ~SCTLR_ELx_M), "r"(sctlr)); +} + static void noinline __section(".idmap.text") set_ttbr0_for_lpa2(u64 ttbr) { u64 sctlr = read_sysreg(sctlr_el1); @@ -229,6 +248,10 @@ asmlinkage void __init early_map_kernel(u64 boot_status, void *fdt) if (va_bits > VA_BITS_MIN) sysreg_clear_set(tcr_el1, TCR_T1SZ_MASK, TCR_T1SZ(va_bits)); + if (IS_ENABLED(CONFIG_ARM64_WXN) && + arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOWXN)) + disable_wxn(); + /* * The virtual KASLR displacement modulo 2MiB is decided by the * physical placement of the image, as otherwise, we might not be able diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S index 9d40f3ffd8d2..bfd2ad896108 100644 --- a/arch/arm64/mm/proc.S +++ b/arch/arm64/mm/proc.S @@ -546,6 +546,12 @@ alternative_else_nop_endif * Prepare SCTLR */ mov_q x0, INIT_SCTLR_EL1_MMU_ON +#ifdef CONFIG_ARM64_WXN + ldr_l x1, arm64_sw_feature_override + FTR_OVR_VAL_OFFSET + tst x1, #0xf << ARM64_SW_FEATURE_OVERRIDE_NOWXN + orr x1, x0, #SCTLR_ELx_WXN + csel x0, x0, x1, ne +#endif ret // return to head.S .unreq mair -- cgit v1.2.3 From 90e636f60b76c590aded72964543945084d97c2f Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sat, 17 Feb 2024 00:59:44 +0100 Subject: arm64: mm: Make PUD folding check in set_pud() a runtime check When set_pud() is called on a 4-level paging build config that runs with 3 levels at runtime (which happens with 16k page size builds with support for LPA2), the updated entry is in fact a PGD in swapper_pg_dir[], and this is mapped read-only after boot. So in this case, the existing check needs to be performed as well, even though __PAGETABLE_PUD_FOLDED is not #define'd. So replace the #ifdef with a call to pgtable_l4_enabled(). Cc: Will Deacon Cc: Marc Zyngier Cc: Mark Rutland Cc: Ryan Roberts Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240216235944.3677178-2-ardb+git@google.com Reviewed-by: Itaru Kitayama Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/pgtable.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h index b3c716fa8121..8bec85350865 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -699,14 +699,14 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd) #define pud_user(pud) pte_user(pud_pte(pud)) #define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) +static inline bool pgtable_l4_enabled(void); + static inline void set_pud(pud_t *pudp, pud_t pud) { -#ifdef __PAGETABLE_PUD_FOLDED - if (in_swapper_pgdir(pudp)) { + if (!pgtable_l4_enabled() && in_swapper_pgdir(pudp)) { set_swapper_pgd((pgd_t *)pudp, __pgd(pud_val(pud))); return; } -#endif /* __PAGETABLE_PUD_FOLDED */ WRITE_ONCE(*pudp, pud); -- cgit v1.2.3 From 2aea7b77aabc708a9df769ad5fa63e9912ceb7f7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Mon, 19 Feb 2024 15:13:22 +0000 Subject: arm64: Use Signed/Unsigned enums for TGRAN{4,16,64} and VARange Open-coding the feature matching parameters for LVA/LVA2 leads to issues with upcoming changes to the cpufeature code. By making TGRAN{4,16,64} and VARange signed/unsigned as per the architecture, we can use the existing macros, making the feature match robust against those changes. Signed-off-by: Marc Zyngier Acked-by: Mark Rutland Acked-by: Ard Biesheuvel Tested-by: Ard Biesheuvel Signed-off-by: Catalin Marinas --- arch/arm64/kernel/cpufeature.c | 15 +++------------ arch/arm64/tools/sysreg | 8 ++++---- 2 files changed, 7 insertions(+), 16 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 0be9296e9253..d380ae783b73 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2706,24 +2706,15 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .capability = ARM64_HAS_VA52, .type = ARM64_CPUCAP_BOOT_CPU_FEATURE, .matches = has_cpuid_feature, - .field_width = 4, #ifdef CONFIG_ARM64_64K_PAGES .desc = "52-bit Virtual Addressing (LVA)", - .sign = FTR_SIGNED, - .sys_reg = SYS_ID_AA64MMFR2_EL1, - .field_pos = ID_AA64MMFR2_EL1_VARange_SHIFT, - .min_field_value = ID_AA64MMFR2_EL1_VARange_52, + ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, VARange, 52) #else .desc = "52-bit Virtual Addressing (LPA2)", - .sys_reg = SYS_ID_AA64MMFR0_EL1, #ifdef CONFIG_ARM64_4K_PAGES - .sign = FTR_SIGNED, - .field_pos = ID_AA64MMFR0_EL1_TGRAN4_SHIFT, - .min_field_value = ID_AA64MMFR0_EL1_TGRAN4_52_BIT, + ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, TGRAN4, 52_BIT) #else - .sign = FTR_UNSIGNED, - .field_pos = ID_AA64MMFR0_EL1_TGRAN16_SHIFT, - .min_field_value = ID_AA64MMFR0_EL1_TGRAN16_52_BIT, + ARM64_CPUID_FIELDS(ID_AA64MMFR0_EL1, TGRAN16, 52_BIT) #endif #endif }, diff --git a/arch/arm64/tools/sysreg b/arch/arm64/tools/sysreg index 4c9b67934367..f654e82ef072 100644 --- a/arch/arm64/tools/sysreg +++ b/arch/arm64/tools/sysreg @@ -1540,16 +1540,16 @@ Enum 35:32 TGRAN16_2 0b0010 IMP 0b0011 52_BIT EndEnum -Enum 31:28 TGRAN4 +SignedEnum 31:28 TGRAN4 0b0000 IMP 0b0001 52_BIT 0b1111 NI EndEnum -Enum 27:24 TGRAN64 +SignedEnum 27:24 TGRAN64 0b0000 IMP 0b1111 NI EndEnum -Enum 23:20 TGRAN16 +UnsignedEnum 23:20 TGRAN16 0b0000 NI 0b0001 IMP 0b0010 52_BIT @@ -1697,7 +1697,7 @@ Enum 23:20 CCIDX 0b0000 32 0b0001 64 EndEnum -Enum 19:16 VARange +UnsignedEnum 19:16 VARange 0b0000 48 0b0001 52 EndEnum -- cgit v1.2.3 From 2758269149250e2c28991fb8d216ffa40857ee0a Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Thu, 22 Feb 2024 22:04:41 +0100 Subject: arm64: gitignore: ignore relacheck Add the generated executable for relacheck to the list of ignored files. Signed-off-by: Bartosz Golaszewski Link: https://lore.kernel.org/r/20240222210441.33142-1-brgl@bgdev.pl Signed-off-by: Catalin Marinas --- arch/arm64/kernel/pi/.gitignore | 3 +++ 1 file changed, 3 insertions(+) create mode 100644 arch/arm64/kernel/pi/.gitignore (limited to 'arch/arm64') diff --git a/arch/arm64/kernel/pi/.gitignore b/arch/arm64/kernel/pi/.gitignore new file mode 100644 index 000000000000..efb29b663e85 --- /dev/null +++ b/arch/arm64/kernel/pi/.gitignore @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0-only + +relacheck -- cgit v1.2.3 From 3137db4c66bf70360ee7027af5c50662b3152046 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 1 Mar 2024 11:40:48 +0100 Subject: arm64/mm: Use generic __pud_free() helper in pud_free() implementation Commit 0dd4f60a2c76 ("arm64: mm: Add support for folding PUDs at runtime") implements specialized PUD alloc/free helpers to allow the decision whether or not to fold PUDs to be made at runtime when the number of paging levels is 4 or higher. Its implementation of pud_free() is based on the generic version that existed when the patch was first written, but in the meantime, the freeing of a PUD has become a bit more involved, and so instead of simply freeing the page, we should invoke the generic __pud_free() that encapsulates whatever needs doing at this point. This fixes a reported warning emitted by the page flags self-diagnostics. Reported-by: Ryan Roberts Signed-off-by: Ard Biesheuvel Tested-by: Ryan Roberts Link: https://lore.kernel.org/r/20240301104046.1234309-5-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/include/asm/pgalloc.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/arm64') diff --git a/arch/arm64/include/asm/pgalloc.h b/arch/arm64/include/asm/pgalloc.h index aeba2cf15a25..8ff5f2a2579e 100644 --- a/arch/arm64/include/asm/pgalloc.h +++ b/arch/arm64/include/asm/pgalloc.h @@ -60,8 +60,7 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud) { if (!pgtable_l4_enabled()) return; - BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); - free_page((unsigned long)pud); + __pud_free(mm, pud); } #else static inline void __p4d_populate(p4d_t *p4dp, phys_addr_t pudp, p4dval_t prot) -- cgit v1.2.3 From 27f2b9fcddc76d542ac339febf2af55b67f610ca Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Fri, 1 Mar 2024 11:40:49 +0100 Subject: arm64/mm: Avoid ID mapping of kpti flag if it is no longer needed arm64_use_ng_mappings will be set to 'true' by the early boot code if it decides to use non-global (nG) attributes for all kernel mappings, typically when enabling KASLR on a system that does not implement E0PD. In this case, the G-to-nG update routines are never called, and so there is no reason to create the writable mapping of the associated status flag in the ID map. Signed-off-by: Ard Biesheuvel Link: https://lore.kernel.org/r/20240301104046.1234309-6-ardb+git@google.com Signed-off-by: Catalin Marinas --- arch/arm64/mm/mmu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'arch/arm64') diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index b131ed31a6c8..bf5b1c426ad0 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -777,7 +777,7 @@ static void __init create_idmap(void) IDMAP_ROOT_LEVEL, (pte_t *)idmap_pg_dir, false, __phys_to_virt(ptep) - ptep); - if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0)) { + if (IS_ENABLED(CONFIG_UNMAP_KERNEL_AT_EL0) && !arm64_use_ng_mappings) { extern u32 __idmap_kpti_flag; u64 pa = __pa_symbol(&__idmap_kpti_flag); -- cgit v1.2.3