diff options
Diffstat (limited to 'include/asm-generic/vmlinux.lds.h')
| -rw-r--r-- | include/asm-generic/vmlinux.lds.h | 112 |
1 files changed, 57 insertions, 55 deletions
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index eeadbaeccf88..fa5f19b8d53a 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -95,19 +95,26 @@ * With LTO_CLANG, the linker also splits sections by default, so we need * these macros to combine the sections during the final link. * + * With AUTOFDO_CLANG and PROPELLER_CLANG, by default, the linker splits + * text sections and regroups functions into subsections. + * * RODATA_MAIN is not used because existing code already defines .rodata.x * sections to be brought in with rodata. */ -#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) +#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) || \ +defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) #define TEXT_MAIN .text .text.[0-9a-zA-Z_]* -#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$L* +#else +#define TEXT_MAIN .text +#endif +#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) +#define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data.rel.* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$L* #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]* #define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* .rodata..L* #define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..L* .bss..compoundliteral* #define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]* #else -#define TEXT_MAIN .text -#define DATA_MAIN .data +#define DATA_MAIN .data .data.rel .data.rel.local #define SDATA_MAIN .sdata #define RODATA_MAIN .rodata #define BSS_MAIN .bss @@ -350,9 +357,9 @@ *(.data..decrypted) \ *(.ref.data) \ *(.data..shared_aligned) /* percpu related */ \ - *(.data.unlikely) \ + *(.data..unlikely) \ __start_once = .; \ - *(.data.once) \ + *(.data..once) \ __end_once = .; \ STRUCT_ALIGN(); \ *(__tracepoints) \ @@ -378,6 +385,11 @@ . = ALIGN(PAGE_SIZE); \ __nosave_end = .; +#define CACHE_HOT_DATA(align) \ + . = ALIGN(align); \ + *(SORT_BY_ALIGNMENT(.data..hot.*)) \ + . = ALIGN(align); + #define PAGE_ALIGNED_DATA(page_align) \ . = ALIGN(page_align); \ *(.data..page_aligned) \ @@ -397,7 +409,6 @@ __start_init_stack = .; \ init_thread_union = .; \ init_stack = .; \ - KEEP(*(.data..init_task)) \ KEEP(*(.data..init_thread_info)) \ . = __start_init_stack + THREAD_SIZE; \ __end_init_stack = .; @@ -450,7 +461,7 @@ . = ALIGN((align)); \ .rodata : AT(ADDR(.rodata) - LOAD_OFFSET) { \ __start_rodata = .; \ - *(.rodata) *(.rodata.*) \ + *(.rodata) *(.rodata.*) *(.data.rel.ro*) \ SCHED_DATA \ RO_AFTER_INIT_DATA /* Read only after init */ \ . = ALIGN(8); \ @@ -549,24 +560,44 @@ __cpuidle_text_end = .; \ __noinstr_text_end = .; +#define TEXT_SPLIT \ + __split_text_start = .; \ + *(.text.split .text.split.[0-9a-zA-Z_]*) \ + __split_text_end = .; + +#define TEXT_UNLIKELY \ + __unlikely_text_start = .; \ + *(.text.unlikely .text.unlikely.*) \ + __unlikely_text_end = .; + +#define TEXT_HOT \ + __hot_text_start = .; \ + *(.text.hot .text.hot.*) \ + __hot_text_end = .; + /* * .text section. Map to function alignment to avoid address changes * during second ld run in second ld pass when generating System.map * - * TEXT_MAIN here will match .text.fixup and .text.unlikely if dead - * code elimination is enabled, so these sections should be converted - * to use ".." first. + * TEXT_MAIN here will match symbols with a fixed pattern (for example, + * .text.hot or .text.unlikely) if dead code elimination or + * function-section is enabled. Match these symbols first before + * TEXT_MAIN to ensure they are grouped together. + * + * Also placing .text.hot section at the beginning of a page, this + * would help the TLB performance. */ #define TEXT_TEXT \ ALIGN_FUNCTION(); \ - *(.text.hot .text.hot.*) \ - *(TEXT_MAIN .text.fixup) \ - *(.text.unlikely .text.unlikely.*) \ + *(.text.asan.* .text.tsan.*) \ *(.text.unknown .text.unknown.*) \ + TEXT_SPLIT \ + TEXT_UNLIKELY \ + . = ALIGN(PAGE_SIZE); \ + TEXT_HOT \ + *(TEXT_MAIN .text.fixup) \ NOINSTR_TEXT \ - *(.ref.text) \ - *(.text.asan.* .text.tsan.*) - + *(.ref.text) /* sched.text is aling to function alignment to secure we have same * address even at second ld pass when generating System.map */ @@ -636,10 +667,11 @@ */ #ifdef CONFIG_DEBUG_INFO_BTF #define BTF \ + . = ALIGN(PAGE_SIZE); \ .BTF : AT(ADDR(.BTF) - LOAD_OFFSET) { \ BOUNDED_SECTION_BY(.BTF, _BTF) \ } \ - . = ALIGN(4); \ + . = ALIGN(PAGE_SIZE); \ .BTF_ids : AT(ADDR(.BTF_ids) - LOAD_OFFSET) { \ *(.BTF_ids) \ } @@ -1011,6 +1043,7 @@ *(.discard) \ *(.discard.*) \ *(.export_symbol) \ + *(.no_trim_symbol) \ *(.modinfo) \ /* ld.bfd warns about .gnu.version* even when not emitted */ \ *(.gnu.version*) \ @@ -1034,10 +1067,13 @@ */ #define PERCPU_INPUT(cacheline) \ __per_cpu_start = .; \ - *(.data..percpu..first) \ . = ALIGN(PAGE_SIZE); \ *(.data..percpu..page_aligned) \ . = ALIGN(cacheline); \ + __per_cpu_hot_start = .; \ + *(SORT_BY_ALIGNMENT(.data..percpu..hot.*)) \ + __per_cpu_hot_end = .; \ + . = ALIGN(cacheline); \ *(.data..percpu..read_mostly) \ . = ALIGN(cacheline); \ *(.data..percpu) \ @@ -1046,52 +1082,17 @@ __per_cpu_end = .; /** - * PERCPU_VADDR - define output section for percpu area + * PERCPU_SECTION - define output section for percpu area * @cacheline: cacheline size - * @vaddr: explicit base address (optional) - * @phdr: destination PHDR (optional) * * Macro which expands to output section for percpu area. * * @cacheline is used to align subsections to avoid false cacheline * sharing between subsections for different purposes. - * - * If @vaddr is not blank, it specifies explicit base address and all - * percpu symbols will be offset from the given address. If blank, - * @vaddr always equals @laddr + LOAD_OFFSET. - * - * @phdr defines the output PHDR to use if not blank. Be warned that - * output PHDR is sticky. If @phdr is specified, the next output - * section in the linker script will go there too. @phdr should have - * a leading colon. - * - * Note that this macros defines __per_cpu_load as an absolute symbol. - * If there is no need to put the percpu section at a predetermined - * address, use PERCPU_SECTION. - */ -#define PERCPU_VADDR(cacheline, vaddr, phdr) \ - __per_cpu_load = .; \ - .data..percpu vaddr : AT(__per_cpu_load - LOAD_OFFSET) { \ - PERCPU_INPUT(cacheline) \ - } phdr \ - . = __per_cpu_load + SIZEOF(.data..percpu); - -/** - * PERCPU_SECTION - define output section for percpu area, simple version - * @cacheline: cacheline size - * - * Align to PAGE_SIZE and outputs output section for percpu area. This - * macro doesn't manipulate @vaddr or @phdr and __per_cpu_load and - * __per_cpu_start will be identical. - * - * This macro is equivalent to ALIGN(PAGE_SIZE); PERCPU_VADDR(@cacheline,,) - * except that __per_cpu_load is defined as a relative symbol against - * .data..percpu which is required for relocatable x86_32 configuration. */ #define PERCPU_SECTION(cacheline) \ . = ALIGN(PAGE_SIZE); \ .data..percpu : AT(ADDR(.data..percpu) - LOAD_OFFSET) { \ - __per_cpu_load = .; \ PERCPU_INPUT(cacheline) \ } @@ -1120,6 +1121,7 @@ INIT_TASK_DATA(inittask) \ NOSAVE_DATA \ PAGE_ALIGNED_DATA(pagealigned) \ + CACHE_HOT_DATA(cacheline) \ CACHELINE_ALIGNED_DATA(cacheline) \ READ_MOSTLY_DATA(cacheline) \ DATA_DATA \ |