From 22823ab419d8ed884195cfa75483fd3a99bb1462 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 11 Jan 2016 10:54:54 -0500 Subject: EXPORT_SYMBOL() for asm Add asm-usable variants of EXPORT_SYMBOL/EXPORT_SYMBOL_GPL. This commit just adds the default implementation; most of the architectures can simply add export.h to asm/Kbuild and start using from assembler. The rest needs to have their define everal macros and then explicitly include One area where the things might diverge from default is the alignment; normally it's 8 bytes on 64bit targets and 4 on 32bit ones, both for unsigned long and for struct kernel_symbol. Unfortunately, amd64 and m68k are unusual - m68k aligns to 2 bytes (for both) and amd64 aligns struct kernel_symbol to 16 bytes. For those we'll need asm/export.h to override the constants used by generic version - KSYM_ALIGN and KCRC_ALIGN for kernel_symbol and unsigned long resp. And no, __alignof__ would not do the trick - on amd64 __alignof__ of struct kernel_symbol is 8, not 16. More serious source of unpleasantness is treatment of function descriptors on architectures that have those. Things like ppc64, parisc, ia64, etc. need more than the address of the first insn to call an arbitrary function. As the result, their representation of pointers to functions is not the typical "address of the entry point" - it's an address of a small static structure containing all the required information (including the entry point, of course). Sadly, the asm-side conventions differ in what the function name refers to - entry point or the function descriptor. On ppc64 we do the latter; bar: .quad foo is what void (*bar)(void) = foo; turns into and the rare places where we need to explicitly work with the label of entry point are dealt with as DOTSYM(foo). For our purposes it's ideal - generic macros are usable. However, parisc would have foo and P%foo used for label of entry point and address of the function descriptor and bar: .long P%foo woudl be used instead. ia64 goes similar to parisc in that respect, except that there it's @fptr(foo) rather than P%foo. Such architectures need to define KSYM_FUNC that would turn a function name into whatever is needed to refer to function descriptor. What's more, on such architectures we need to know whether we are exporting a function or an object - in assembler we have to tell that explicitly, to decide whether we want EXPORT_SYMBOL(foo) produce e.g. __ksymtab_foo: .quad foo or __ksymtab_foo: .quad @fptr(foo) For that reason we introduce EXPORT_DATA_SYMBOL{,_GPL}(), to be used for exports of data objects. On normal architectures it's the same thing as EXPORT_SYMBOL{,_GPL}(), but on parisc-like ones they differ and the right one needs to be used. Most of the exports are functions, so we keep EXPORT_SYMBOL for those... Signed-off-by: Al Viro --- include/asm-generic/export.h | 94 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 94 insertions(+) create mode 100644 include/asm-generic/export.h (limited to 'include') diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h new file mode 100644 index 0000000..43199a0 --- /dev/null +++ b/include/asm-generic/export.h @@ -0,0 +1,94 @@ +#ifndef __ASM_GENERIC_EXPORT_H +#define __ASM_GENERIC_EXPORT_H + +#ifndef KSYM_FUNC +#define KSYM_FUNC(x) x +#endif +#ifdef CONFIG_64BIT +#define __put .quad +#ifndef KSYM_ALIGN +#define KSYM_ALIGN 8 +#endif +#ifndef KCRC_ALIGN +#define KCRC_ALIGN 8 +#endif +#else +#define __put .long +#ifndef KSYM_ALIGN +#define KSYM_ALIGN 4 +#endif +#ifndef KCRC_ALIGN +#define KCRC_ALIGN 4 +#endif +#endif + +#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX +#define KSYM(name) _##name +#else +#define KSYM(name) name +#endif + +/* + * note on .section use: @progbits vs %progbits nastiness doesn't matter, + * since we immediately emit into those sections anyway. + */ +.macro ___EXPORT_SYMBOL name,val,sec +#ifdef CONFIG_MODULES + .globl KSYM(__ksymtab_\name) + .section ___ksymtab\sec+\name,"a" + .balign KSYM_ALIGN +KSYM(__ksymtab_\name): + __put \val, KSYM(__kstrtab_\name) + .previous + .section __ksymtab_strings,"a" +KSYM(__kstrtab_\name): +#ifdef CONFIG_HAVE_UNDERSCORE_SYMBOL_PREFIX + .asciz "_\name" +#else + .asciz "\name" +#endif + .previous +#ifdef CONFIG_MODVERSIONS + .section ___kcrctab\sec+\name,"a" + .balign KCRC_ALIGN +KSYM(__kcrctab_\name): + __put KSYM(__crc_\name) + .weak KSYM(__crc_\name) + .previous +#endif +#endif +.endm +#undef __put + +#if defined(__KSYM_DEPS__) + +#define __EXPORT_SYMBOL(sym, val, sec) === __KSYM_##sym === + +#elif defined(CONFIG_TRIM_UNUSED_KSYMS) + +#include +#include + +#define __EXPORT_SYMBOL(sym, val, sec) \ + __cond_export_sym(sym, val, sec, config_enabled(__KSYM_##sym)) +#define __cond_export_sym(sym, val, sec, conf) \ + ___cond_export_sym(sym, val, sec, conf) +#define ___cond_export_sym(sym, val, sec, enabled) \ + __cond_export_sym_##enabled(sym, val, sec) +#define __cond_export_sym_1(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec +#define __cond_export_sym_0(sym, val, sec) /* nothing */ + +#else +#define __EXPORT_SYMBOL(sym, val, sec) ___EXPORT_SYMBOL sym, val, sec +#endif + +#define EXPORT_SYMBOL(name) \ + __EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)),) +#define EXPORT_SYMBOL_GPL(name) \ + __EXPORT_SYMBOL(name, KSYM_FUNC(KSYM(name)), _gpl) +#define EXPORT_DATA_SYMBOL(name) \ + __EXPORT_SYMBOL(name, KSYM(name),) +#define EXPORT_DATA_SYMBOL_GPL(name) \ + __EXPORT_SYMBOL(name, KSYM(name),_gpl) + +#endif -- cgit v1.1 From b67067f1176df6ee727450546b58704e4b588563 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 24 Aug 2016 22:29:20 +1000 Subject: kbuild: allow archs to select link dead code/data elimination Introduce LD_DEAD_CODE_DATA_ELIMINATION option for architectures to select to build with -ffunction-sections, -fdata-sections, and link with --gc-sections. It requires some work (documented) to ensure all unreferenced entrypoints are live, and requires toolchain and build verification, so it is made a per-arch option for now. On a random powerpc64le build, this yelds a significant size saving, it boots and runs fine, but there is a lot I haven't tested as yet, so these savings may be reduced if there are bugs in the link. text data bss dec filename 11169741 1180744 1923176 14273661 vmlinux 10445269 1004127 1919707 13369103 vmlinux.dce ~700K text, ~170K data, 6% removed from kernel image size. Signed-off-by: Nicholas Piggin Signed-off-by: Michal Marek --- include/asm-generic/vmlinux.lds.h | 52 ++++++++++++++++++++++----------------- include/linux/compiler.h | 23 +++++++++++++++++ include/linux/export.h | 30 +++++++++++----------- include/linux/init.h | 38 ++++++++++------------------ 4 files changed, 80 insertions(+), 63 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 2456397..ad9d8f9 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -196,9 +196,14 @@ *(.dtb.init.rodata) \ VMLINUX_SYMBOL(__dtb_end) = .; -/* .data section */ +/* + * .data section + * -fdata-sections generates .data.identifier which needs to be pulled in + * with .data, but don't want to pull in .data..stuff which has its own + * requirements. Same for bss. + */ #define DATA_DATA \ - *(.data) \ + *(.data .data.[0-9a-zA-Z_]*) \ *(.ref.data) \ *(.data..shared_aligned) /* percpu related */ \ MEM_KEEP(init.data) \ @@ -320,76 +325,76 @@ /* Kernel symbol table: Normal symbols */ \ __ksymtab : AT(ADDR(__ksymtab) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab) = .; \ - *(SORT(___ksymtab+*)) \ + KEEP(*(SORT(___ksymtab+*))) \ VMLINUX_SYMBOL(__stop___ksymtab) = .; \ } \ \ /* Kernel symbol table: GPL-only symbols */ \ __ksymtab_gpl : AT(ADDR(__ksymtab_gpl) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab_gpl) = .; \ - *(SORT(___ksymtab_gpl+*)) \ + KEEP(*(SORT(___ksymtab_gpl+*))) \ VMLINUX_SYMBOL(__stop___ksymtab_gpl) = .; \ } \ \ /* Kernel symbol table: Normal unused symbols */ \ __ksymtab_unused : AT(ADDR(__ksymtab_unused) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab_unused) = .; \ - *(SORT(___ksymtab_unused+*)) \ + KEEP(*(SORT(___ksymtab_unused+*))) \ VMLINUX_SYMBOL(__stop___ksymtab_unused) = .; \ } \ \ /* Kernel symbol table: GPL-only unused symbols */ \ __ksymtab_unused_gpl : AT(ADDR(__ksymtab_unused_gpl) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab_unused_gpl) = .; \ - *(SORT(___ksymtab_unused_gpl+*)) \ + KEEP(*(SORT(___ksymtab_unused_gpl+*))) \ VMLINUX_SYMBOL(__stop___ksymtab_unused_gpl) = .; \ } \ \ /* Kernel symbol table: GPL-future-only symbols */ \ __ksymtab_gpl_future : AT(ADDR(__ksymtab_gpl_future) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___ksymtab_gpl_future) = .; \ - *(SORT(___ksymtab_gpl_future+*)) \ + KEEP(*(SORT(___ksymtab_gpl_future+*))) \ VMLINUX_SYMBOL(__stop___ksymtab_gpl_future) = .; \ } \ \ /* Kernel symbol table: Normal symbols */ \ __kcrctab : AT(ADDR(__kcrctab) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab) = .; \ - *(SORT(___kcrctab+*)) \ + KEEP(*(SORT(___kcrctab+*))) \ VMLINUX_SYMBOL(__stop___kcrctab) = .; \ } \ \ /* Kernel symbol table: GPL-only symbols */ \ __kcrctab_gpl : AT(ADDR(__kcrctab_gpl) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab_gpl) = .; \ - *(SORT(___kcrctab_gpl+*)) \ + KEEP(*(SORT(___kcrctab_gpl+*))) \ VMLINUX_SYMBOL(__stop___kcrctab_gpl) = .; \ } \ \ /* Kernel symbol table: Normal unused symbols */ \ __kcrctab_unused : AT(ADDR(__kcrctab_unused) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab_unused) = .; \ - *(SORT(___kcrctab_unused+*)) \ + KEEP(*(SORT(___kcrctab_unused+*))) \ VMLINUX_SYMBOL(__stop___kcrctab_unused) = .; \ } \ \ /* Kernel symbol table: GPL-only unused symbols */ \ __kcrctab_unused_gpl : AT(ADDR(__kcrctab_unused_gpl) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab_unused_gpl) = .; \ - *(SORT(___kcrctab_unused_gpl+*)) \ + KEEP(*(SORT(___kcrctab_unused_gpl+*))) \ VMLINUX_SYMBOL(__stop___kcrctab_unused_gpl) = .; \ } \ \ /* Kernel symbol table: GPL-future-only symbols */ \ __kcrctab_gpl_future : AT(ADDR(__kcrctab_gpl_future) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__start___kcrctab_gpl_future) = .; \ - *(SORT(___kcrctab_gpl_future+*)) \ + KEEP(*(SORT(___kcrctab_gpl_future+*))) \ VMLINUX_SYMBOL(__stop___kcrctab_gpl_future) = .; \ } \ \ /* Kernel symbol table: strings */ \ __ksymtab_strings : AT(ADDR(__ksymtab_strings) - LOAD_OFFSET) { \ - *(__ksymtab_strings) \ + KEEP(*(__ksymtab_strings)) \ } \ \ /* __*init sections */ \ @@ -424,7 +429,7 @@ #define SECURITY_INIT \ .security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \ VMLINUX_SYMBOL(__security_initcall_start) = .; \ - *(.security_initcall.init) \ + KEEP(*(.security_initcall.init)) \ VMLINUX_SYMBOL(__security_initcall_end) = .; \ } @@ -432,7 +437,7 @@ * during second ld run in second ld pass when generating System.map */ #define TEXT_TEXT \ ALIGN_FUNCTION(); \ - *(.text.hot .text .text.fixup .text.unlikely) \ + *(.text.hot .text .text.fixup .text.unlikely .text.*) \ *(.ref.text) \ MEM_KEEP(init.text) \ MEM_KEEP(exit.text) \ @@ -527,6 +532,7 @@ /* init and exit section handling */ #define INIT_DATA \ + KEEP(*(SORT(___kentry+*))) \ *(.init.data) \ MEM_DISCARD(init.data) \ KERNEL_CTORS() \ @@ -593,7 +599,7 @@ BSS_FIRST_SECTIONS \ *(.bss..page_aligned) \ *(.dynbss) \ - *(.bss) \ + *(.bss .bss.[0-9a-zA-Z_]*) \ *(COMMON) \ } @@ -676,12 +682,12 @@ #define INIT_CALLS_LEVEL(level) \ VMLINUX_SYMBOL(__initcall##level##_start) = .; \ - *(.initcall##level##.init) \ - *(.initcall##level##s.init) \ + KEEP(*(.initcall##level##.init)) \ + KEEP(*(.initcall##level##s.init)) \ #define INIT_CALLS \ VMLINUX_SYMBOL(__initcall_start) = .; \ - *(.initcallearly.init) \ + KEEP(*(.initcallearly.init)) \ INIT_CALLS_LEVEL(0) \ INIT_CALLS_LEVEL(1) \ INIT_CALLS_LEVEL(2) \ @@ -695,21 +701,21 @@ #define CON_INITCALL \ VMLINUX_SYMBOL(__con_initcall_start) = .; \ - *(.con_initcall.init) \ + KEEP(*(.con_initcall.init)) \ VMLINUX_SYMBOL(__con_initcall_end) = .; #define SECURITY_INITCALL \ VMLINUX_SYMBOL(__security_initcall_start) = .; \ - *(.security_initcall.init) \ + KEEP(*(.security_initcall.init)) \ VMLINUX_SYMBOL(__security_initcall_end) = .; #ifdef CONFIG_BLK_DEV_INITRD #define INIT_RAM_FS \ . = ALIGN(4); \ VMLINUX_SYMBOL(__initramfs_start) = .; \ - *(.init.ramfs) \ + KEEP(*(.init.ramfs)) \ . = ALIGN(8); \ - *(.init.ramfs.info) + KEEP(*(.init.ramfs.info)) #else #define INIT_RAM_FS #endif diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 1bb9548..86130cd 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -182,6 +182,29 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect); # define unreachable() do { } while (1) #endif +/* + * KENTRY - kernel entry point + * This can be used to annotate symbols (functions or data) that are used + * without their linker symbol being referenced explicitly. For example, + * interrupt vector handlers, or functions in the kernel image that are found + * programatically. + * + * Not required for symbols exported with EXPORT_SYMBOL, or initcalls. Those + * are handled in their own way (with KEEP() in linker scripts). + * + * KENTRY can be avoided if the symbols in question are marked as KEEP() in the + * linker script. For example an architecture could KEEP() its entire + * boot/exception vector code rather than annotate each function and data. + */ +#ifndef KENTRY +# define KENTRY(sym) \ + extern typeof(sym) sym; \ + static const unsigned long __kentry_##sym \ + __used \ + __attribute__((section("___kentry" "+" #sym ), used)) \ + = (unsigned long)&sym; +#endif + #ifndef RELOC_HIDE # define RELOC_HIDE(ptr, off) \ ({ unsigned long __ptr; \ diff --git a/include/linux/export.h b/include/linux/export.h index c565f87..337cb90 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -1,5 +1,6 @@ #ifndef _LINUX_EXPORT_H #define _LINUX_EXPORT_H + /* * Export symbols from the kernel to modules. Forked from module.h * to reduce the amount of pointless cruft we feed to gcc when only @@ -42,27 +43,26 @@ extern struct module __this_module; #ifdef CONFIG_MODVERSIONS /* Mark the CRC weak since genksyms apparently decides not to * generate a checksums for some symbols */ -#define __CRC_SYMBOL(sym, sec) \ - extern __visible void *__crc_##sym __attribute__((weak)); \ - static const unsigned long __kcrctab_##sym \ - __used \ - __attribute__((section("___kcrctab" sec "+" #sym), unused)) \ +#define __CRC_SYMBOL(sym, sec) \ + extern __visible void *__crc_##sym __attribute__((weak)); \ + static const unsigned long __kcrctab_##sym \ + __used \ + __attribute__((section("___kcrctab" sec "+" #sym), used)) \ = (unsigned long) &__crc_##sym; #else #define __CRC_SYMBOL(sym, sec) #endif /* For every exported symbol, place a struct in the __ksymtab section */ -#define ___EXPORT_SYMBOL(sym, sec) \ - extern typeof(sym) sym; \ - __CRC_SYMBOL(sym, sec) \ - static const char __kstrtab_##sym[] \ - __attribute__((section("__ksymtab_strings"), aligned(1))) \ - = VMLINUX_SYMBOL_STR(sym); \ - extern const struct kernel_symbol __ksymtab_##sym; \ - __visible const struct kernel_symbol __ksymtab_##sym \ - __used \ - __attribute__((section("___ksymtab" sec "+" #sym), unused)) \ +#define ___EXPORT_SYMBOL(sym, sec) \ + extern typeof(sym) sym; \ + __CRC_SYMBOL(sym, sec) \ + static const char __kstrtab_##sym[] \ + __attribute__((section("__ksymtab_strings"), aligned(1))) \ + = VMLINUX_SYMBOL_STR(sym); \ + static const struct kernel_symbol __ksymtab_##sym \ + __used \ + __attribute__((section("___ksymtab" sec "+" #sym), used)) \ = { (unsigned long)&sym, __kstrtab_##sym } #if defined(__KSYM_DEPS__) diff --git a/include/linux/init.h b/include/linux/init.h index 6935d02..e571fec 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -150,24 +150,8 @@ extern bool initcall_debug; #ifndef __ASSEMBLY__ -#ifdef CONFIG_LTO -/* Work around a LTO gcc problem: when there is no reference to a variable - * in a module it will be moved to the end of the program. This causes - * reordering of initcalls which the kernel does not like. - * Add a dummy reference function to avoid this. The function is - * deleted by the linker. - */ -#define LTO_REFERENCE_INITCALL(x) \ - ; /* yes this is needed */ \ - static __used __exit void *reference_##x(void) \ - { \ - return &x; \ - } -#else -#define LTO_REFERENCE_INITCALL(x) -#endif - -/* initcalls are now grouped by functionality into separate +/* + * initcalls are now grouped by functionality into separate * subsections. Ordering inside the subsections is determined * by link order. * For backwards compatibility, initcall() puts the call in @@ -175,12 +159,16 @@ extern bool initcall_debug; * * The `id' arg to __define_initcall() is needed so that multiple initcalls * can point at the same handler without causing duplicate-symbol build errors. + * + * Initcalls are run by placing pointers in initcall sections that the + * kernel iterates at runtime. The linker can do dead code / data elimination + * and remove that completely, so the initcall sections have to be marked + * as KEEP() in the linker script. */ #define __define_initcall(fn, id) \ static initcall_t __initcall_##fn##id __used \ - __attribute__((__section__(".initcall" #id ".init"))) = fn; \ - LTO_REFERENCE_INITCALL(__initcall_##fn##id) + __attribute__((__section__(".initcall" #id ".init"))) = fn; /* * Early initcalls run before initializing SMP. @@ -216,15 +204,15 @@ extern bool initcall_debug; #define __initcall(fn) device_initcall(fn) -#define __exitcall(fn) \ +#define __exitcall(fn) \ static exitcall_t __exitcall_##fn __exit_call = fn -#define console_initcall(fn) \ - static initcall_t __initcall_##fn \ +#define console_initcall(fn) \ + static initcall_t __initcall_##fn \ __used __section(.con_initcall.init) = fn -#define security_initcall(fn) \ - static initcall_t __initcall_##fn \ +#define security_initcall(fn) \ + static initcall_t __initcall_##fn \ __used __section(.security_initcall.init) = fn struct obs_kernel_param { -- cgit v1.1 From 0f4c4af06eec5717041d6fe568b80ee4cf3c1475 Mon Sep 17 00:00:00 2001 From: Nicholas Piggin Date: Wed, 14 Sep 2016 12:24:03 +1000 Subject: kbuild: -ffunction-sections fix for archs with conflicting sections Enabling -ffunction-sections modified the generic linker script to pull .text.* sections into regular TEXT_TEXT section, conflicting with some architectures. Revert that change and require archs that enable the option to ensure they have no conflicting section names, and do the appropriate merging. Reported-by: Guenter Roeck Tested-by: Guenter Roeck Fixes: b67067f1176d ("kbuild: allow archs to select link dead code/data elimination") Signed-off-by: Nicholas Piggin Signed-off-by: Michal Marek --- include/asm-generic/vmlinux.lds.h | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index ad9d8f9..48dd44f3 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -198,9 +198,9 @@ /* * .data section - * -fdata-sections generates .data.identifier which needs to be pulled in - * with .data, but don't want to pull in .data..stuff which has its own - * requirements. Same for bss. + * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections generates + * .data.identifier which needs to be pulled in with .data, but don't want to + * pull in .data..stuff which has its own requirements. Same for bss. */ #define DATA_DATA \ *(.data .data.[0-9a-zA-Z_]*) \ @@ -434,10 +434,15 @@ } /* .text section. Map to function alignment to avoid address changes - * during second ld run in second ld pass when generating System.map */ + * during second ld run in second ld pass when generating System.map + * LD_DEAD_CODE_DATA_ELIMINATION option enables -ffunction-sections generates + * .text.identifier which needs to be pulled in with .text , but some + * architectures define .text.foo which is not intended to be pulled in here. + * Those enabling LD_DEAD_CODE_DATA_ELIMINATION must ensure they don't have + * conflicting section names, and must pull in .text.[0-9a-zA-Z_]* */ #define TEXT_TEXT \ ALIGN_FUNCTION(); \ - *(.text.hot .text .text.fixup .text.unlikely .text.*) \ + *(.text.hot .text .text.fixup .text.unlikely) \ *(.ref.text) \ MEM_KEEP(init.text) \ MEM_KEEP(exit.text) \ -- cgit v1.1