diff options
Diffstat (limited to 'arch/x86/kernel/vmlinux.lds.S')
| -rw-r--r-- | arch/x86/kernel/vmlinux.lds.S | 256 |
1 files changed, 153 insertions, 103 deletions
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index efd9e9ea17f2..d7af4a64c211 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -15,11 +15,7 @@ * put it inside the section definition. */ -#ifdef CONFIG_X86_32 -#define LOAD_OFFSET __PAGE_OFFSET -#else #define LOAD_OFFSET __START_KERNEL_map -#endif #define RUNTIME_DISCARD_EXIT #define EMITS_PT_NOTE @@ -32,6 +28,7 @@ #include <asm/orc_lookup.h> #include <asm/cache.h> #include <asm/boot.h> +#include <asm/kexec.h> #undef i386 /* in case the preprocessor is a 32bit one */ @@ -46,6 +43,8 @@ ENTRY(phys_startup_64) #endif jiffies = jiffies_64; +const_current_task = current_task; +const_cpu_current_top_of_stack = cpu_current_top_of_stack; #if defined(CONFIG_X86_64) /* @@ -80,11 +79,13 @@ jiffies = jiffies_64; #define BSS_DECRYPTED \ . = ALIGN(PMD_SIZE); \ __start_bss_decrypted = .; \ + __pi___start_bss_decrypted = .; \ *(.bss..decrypted); \ . = ALIGN(PAGE_SIZE); \ __start_bss_decrypted_unused = .; \ . = ALIGN(PMD_SIZE); \ __end_bss_decrypted = .; \ + __pi___end_bss_decrypted = .; \ #else @@ -98,54 +99,66 @@ jiffies = jiffies_64; #define BSS_DECRYPTED #endif - +#if defined(CONFIG_X86_64) && defined(CONFIG_KEXEC_CORE) +#define KEXEC_RELOCATE_KERNEL \ + . = ALIGN(0x100); \ + __relocate_kernel_start = .; \ + *(.text..relocate_kernel); \ + *(.data..relocate_kernel); \ + __relocate_kernel_end = .; + +ASSERT(__relocate_kernel_end - __relocate_kernel_start <= KEXEC_CONTROL_CODE_MAX_SIZE, + "relocate_kernel code too large!") +#else +#define KEXEC_RELOCATE_KERNEL +#endif PHDRS { text PT_LOAD FLAGS(5); /* R_E */ data PT_LOAD FLAGS(6); /* RW_ */ -#ifdef CONFIG_X86_64 -#ifdef CONFIG_SMP - percpu PT_LOAD FLAGS(6); /* RW_ */ -#endif - init PT_LOAD FLAGS(7); /* RWE */ -#endif note PT_NOTE FLAGS(0); /* ___ */ } SECTIONS { + . = __START_KERNEL; #ifdef CONFIG_X86_32 - . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR; phys_startup_32 = ABSOLUTE(startup_32 - LOAD_OFFSET); #else - . = __START_KERNEL; phys_startup_64 = ABSOLUTE(startup_64 - LOAD_OFFSET); #endif /* Text and read-only data */ .text : AT(ADDR(.text) - LOAD_OFFSET) { _text = .; + __pi__text = .; _stext = .; - /* bootstrapping code */ - HEAD_TEXT + ALIGN_ENTRY_TEXT_BEGIN + *(.text..__x86.rethunk_untrain) + ENTRY_TEXT + +#ifdef CONFIG_MITIGATION_SRSO + /* + * See the comment above srso_alias_untrain_ret()'s + * definition. + */ + . = srso_alias_untrain_ret | (1 << 2) | (1 << 8) | (1 << 14) | (1 << 20); + *(.text..__x86.rethunk_safe) +#endif + ALIGN_ENTRY_TEXT_END + TEXT_TEXT SCHED_TEXT - CPUIDLE_TEXT LOCK_TEXT KPROBES_TEXT - ALIGN_ENTRY_TEXT_BEGIN - ENTRY_TEXT - ALIGN_ENTRY_TEXT_END SOFTIRQENTRY_TEXT +#ifdef CONFIG_MITIGATION_RETPOLINE + *(.text..__x86.indirect_thunk) + *(.text..__x86.return_thunk) +#endif STATIC_CALL_TEXT - *(.fixup) *(.gnu.warning) -#ifdef CONFIG_RETPOLINE - __indirect_thunk_start = .; - *(.text.__x86.indirect_thunk) - __indirect_thunk_end = .; -#endif - } :text =0xcccc + } :text = 0xcccccccc /* End of text section, which should occupy whole number of pages */ _etext = .; @@ -163,6 +176,9 @@ SECTIONS /* init_task */ INIT_TASK_DATA(THREAD_SIZE) + /* equivalent to task_pt_regs(&init_task) */ + __top_init_kernel_stack = __end_init_stack - TOP_OF_KERNEL_STACK_PADDING - PTREGS_SIZE; + #ifdef CONFIG_X86_32 /* 32 bit has nosave before _edata */ NOSAVE_DATA @@ -170,10 +186,13 @@ SECTIONS PAGE_ALIGNED_DATA(PAGE_SIZE) + CACHE_HOT_DATA(L1_CACHE_BYTES) + CACHELINE_ALIGNED_DATA(L1_CACHE_BYTES) DATA_DATA CONSTRUCTORS + KEXEC_RELOCATE_KERNEL /* rarely changed data like cpu maps */ READ_MOSTLY_DATA(INTERNODE_CACHE_BYTES) @@ -186,50 +205,13 @@ SECTIONS ORC_UNWIND_TABLE - . = ALIGN(PAGE_SIZE); - __vvar_page = .; - - .vvar : AT(ADDR(.vvar) - LOAD_OFFSET) { - /* work around gold bug 13023 */ - __vvar_beginning_hack = .; - - /* Place all vvars at the offsets in asm/vvar.h. */ -#define EMIT_VVAR(name, offset) \ - . = __vvar_beginning_hack + offset; \ - *(.vvar_ ## name) -#include <asm/vvar.h> -#undef EMIT_VVAR - - /* - * Pad the rest of the page with zeros. Otherwise the loader - * can leave garbage here. - */ - . = __vvar_beginning_hack + PAGE_SIZE; - } :data - - . = ALIGN(__vvar_page + PAGE_SIZE, PAGE_SIZE); - /* Init code and data - will be freed after init */ . = ALIGN(PAGE_SIZE); .init.begin : AT(ADDR(.init.begin) - LOAD_OFFSET) { __init_begin = .; /* paired with __init_end */ } -#if defined(CONFIG_X86_64) && defined(CONFIG_SMP) - /* - * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the - * output PHDR, so the next output section - .init.text - should - * start another segment - init. - */ - PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu) - ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START, - "per-CPU data too large - increase CONFIG_PHYSICAL_START") -#endif - INIT_TEXT_SECTION(PAGE_SIZE) -#ifdef CONFIG_X86_64 - :init -#endif /* * Section for code used exclusively before alternatives are run. All @@ -240,6 +222,8 @@ SECTIONS */ .altinstr_aux : AT(ADDR(.altinstr_aux) - LOAD_OFFSET) { *(.altinstr_aux) + . = ALIGN(PAGE_SIZE); + __inittext_end = .; } INIT_DATA_SECTION(16) @@ -259,19 +243,52 @@ SECTIONS } #endif +#ifdef CONFIG_MITIGATION_RETPOLINE /* - * start address and size of operations which during runtime - * can be patched with virtualization friendly instructions or - * baremetal native ones. Think page table operations. - * Details in paravirt_types.h + * List of instructions that call/jmp/jcc to retpoline thunks + * __x86_indirect_thunk_*(). These instructions can be patched along + * with alternatives, after which the section can be freed. */ . = ALIGN(8); - .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) { - __parainstructions = .; - *(.parainstructions) - __parainstructions_end = .; + .retpoline_sites : AT(ADDR(.retpoline_sites) - LOAD_OFFSET) { + __retpoline_sites = .; + *(.retpoline_sites) + __retpoline_sites_end = .; + } + + . = ALIGN(8); + .return_sites : AT(ADDR(.return_sites) - LOAD_OFFSET) { + __return_sites = .; + *(.return_sites) + __return_sites_end = .; } + . = ALIGN(8); + .call_sites : AT(ADDR(.call_sites) - LOAD_OFFSET) { + __call_sites = .; + *(.call_sites) + __call_sites_end = .; + } +#endif + +#ifdef CONFIG_X86_KERNEL_IBT + . = ALIGN(8); + .ibt_endbr_seal : AT(ADDR(.ibt_endbr_seal) - LOAD_OFFSET) { + __ibt_endbr_seal = .; + *(.ibt_endbr_seal) + __ibt_endbr_seal_end = .; + } +#endif + +#ifdef CONFIG_FINEIBT + . = ALIGN(8); + .cfi_sites : AT(ADDR(.cfi_sites) - LOAD_OFFSET) { + __cfi_sites = .; + *(.cfi_sites) + __cfi_sites_end = .; + } +#endif + /* * struct alt_inst entries. From the header (alternative.h): * "Alternative instructions for different CPU types or capabilities" @@ -293,18 +310,6 @@ SECTIONS *(.altinstr_replacement) } - /* - * struct iommu_table_entry entries are injected in this section. - * It is an array of IOMMUs which during run time gets sorted depending - * on its dependency order. After rootfs_initcall is complete - * this section can be safely removed. - */ - .iommu_table : AT(ADDR(.iommu_table) - LOAD_OFFSET) { - __iommu_table = .; - *(.iommu_table) - __iommu_table_end = .; - } - . = ALIGN(8); .apicdrivers : AT(ADDR(.apicdrivers) - LOAD_OFFSET) { __apicdrivers = .; @@ -325,9 +330,11 @@ SECTIONS EXIT_DATA } -#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP) - PERCPU_SECTION(INTERNODE_CACHE_BYTES) -#endif + PERCPU_SECTION(L1_CACHE_BYTES) + ASSERT(__per_cpu_hot_end - __per_cpu_hot_start <= 64, "percpu cache hot data too large") + + RUNTIME_CONST_VARIABLES + RUNTIME_CONST(ptr, USER_PTR_MAX) . = ALIGN(PAGE_SIZE); @@ -378,12 +385,13 @@ SECTIONS .brk : AT(ADDR(.brk) - LOAD_OFFSET) { __brk_base = .; . += 64 * 1024; /* 64k alignment slop space */ - *(.brk_reservation) /* areas brk users have reserved */ + *(.bss..brk) /* areas brk users have reserved */ __brk_limit = .; } . = ALIGN(PAGE_SIZE); /* keep VO_INIT_SIZE page aligned */ _end = .; + __pi__end = .; #ifdef CONFIG_AMD_MEM_ENCRYPT /* @@ -412,6 +420,10 @@ SECTIONS STABS_DEBUG DWARF_DEBUG +#ifdef CONFIG_PROPELLER_CLANG + .llvm_bb_addr_map : { *(.llvm_bb_addr_map) } +#endif + ELF_DETAILS DISCARDS @@ -455,32 +467,70 @@ SECTIONS } /* - * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility: + * COMPILE_TEST kernels can be large - CONFIG_KASAN, for example, can cause + * this. Let's assume that nobody will be running a COMPILE_TEST kernel and + * let's assert that fuller build coverage is more valuable than being able to + * run a COMPILE_TEST kernel. + */ +#ifndef CONFIG_COMPILE_TEST +/* + * The ASSERT() sync to . is intentional, for binutils 2.14 compatibility: */ . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE), "kernel image bigger than KERNEL_IMAGE_SIZE"); +#endif + +/* needed for Clang - see arch/x86/entry/entry.S */ +PROVIDE(__ref_stack_chk_guard = __stack_chk_guard); #ifdef CONFIG_X86_64 + +#ifdef CONFIG_MITIGATION_UNRET_ENTRY +. = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned"); +#endif + +#ifdef CONFIG_MITIGATION_SRSO +. = ASSERT((srso_safe_ret & 0x3f) == 0, "srso_safe_ret not cacheline-aligned"); /* - * Per-cpu symbols which need to be offset from __per_cpu_load - * for the boot processor. + * GNU ld cannot do XOR until 2.41. + * https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h=f6f78318fca803c4907fb8d7f6ded8295f1947b1 + * + * LLVM lld cannot do XOR until lld-17. + * https://github.com/llvm/llvm-project/commit/fae96104d4378166cbe5c875ef8ed808a356f3fb + * + * Instead do: (A | B) - (A & B) in order to compute the XOR + * of the two function addresses: */ -#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load -INIT_PER_CPU(gdt_page); -INIT_PER_CPU(fixed_percpu_data); -INIT_PER_CPU(irq_stack_backing_store); - -#ifdef CONFIG_SMP -. = ASSERT((fixed_percpu_data == 0), - "fixed_percpu_data is not at start of per-cpu area"); +. = ASSERT(((ABSOLUTE(srso_alias_untrain_ret) | srso_alias_safe_ret) - + (ABSOLUTE(srso_alias_untrain_ret) & srso_alias_safe_ret)) == ((1 << 2) | (1 << 8) | (1 << 14) | (1 << 20)), + "SRSO function pair won't alias"); #endif -#endif /* CONFIG_X86_64 */ +#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B) +. = ASSERT(__x86_indirect_its_thunk_rax & 0x20, "__x86_indirect_thunk_rax not in second half of cacheline"); +. = ASSERT(((__x86_indirect_its_thunk_rcx - __x86_indirect_its_thunk_rax) % 64) == 0, "Indirect thunks are not cacheline apart"); +. = ASSERT(__x86_indirect_its_thunk_array == __x86_indirect_its_thunk_rax, "Gap in ITS thunk array"); +#endif -#ifdef CONFIG_KEXEC_CORE -#include <asm/kexec.h> +#if defined(CONFIG_MITIGATION_ITS) && !defined(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B) +. = ASSERT(its_return_thunk & 0x20, "its_return_thunk not in second half of cacheline"); +#endif -. = ASSERT(kexec_control_code_size <= KEXEC_CONTROL_CODE_MAX_SIZE, - "kexec control code size is too big"); +#endif /* CONFIG_X86_64 */ + +/* + * The symbols below are referenced using relative relocations in the + * respective ELF notes. This produces build time constants that the + * linker will never mark as relocatable. (Using just ABSOLUTE() is not + * sufficient for that). + */ +#ifdef CONFIG_XEN_PV +xen_elfnote_entry_value = + ABSOLUTE(xen_elfnote_entry) + ABSOLUTE(startup_xen); +#endif +#ifdef CONFIG_PVH +xen_elfnote_phys32_entry_value = + ABSOLUTE(xen_elfnote_phys32_entry) + ABSOLUTE(pvh_start_xen - LOAD_OFFSET); #endif +#include "../boot/startup/exports.h" |