From 651910874633a75f4a726d44e449be0a56b4b2e0 Mon Sep 17 00:00:00 2001 From: John Reiser Date: Mon, 21 Jul 2008 14:21:32 -0700 Subject: execve filename: document and export via auxiliary vector The Linux kernel puts the filename argument of execve() into the new address space. Many developers are surprised to learn this. Those who know and could use it, object "But it's not documented." Those who want to use it dislike the expression (char *)(1+ strlen(env[-1+ n_env]) + env[-1+ n_env]) because it requires locating the last original environment variable, and assumes that the filename follows the characters. This patch documents the insertion of the filename, and makes it easier to find by adding a new tag AT_EXECFN in the ElfXX_auxv_t; see . In many cases readlink("/proc/self/exe",) gives the same answer. But if all the original pages get unmapped, then the kernel erases the symlink for /proc/self/exe. This can happen when a program decompressor does a good job of cleaning up after uncompressing directly to memory, so that the address space of the target program looks the same as if compression had never happened. One example is http://upx.sourceforge.net . One notable use of the underlying concept (what path containED the executable) is glibc expanding $ORIGIN in DT_RUNPATH. In practice for the near term, it may be a good idea for user-mode code to use both /proc/self/exe and AT_EXECFN as fall-back methods for each other. /proc/self/exe can fail due to unmapping, AT_EXECFN can fail because it won't be present on non-new systems. The auxvec or {AT_EXECFN}.d_val also can get overwritten, although in nearly all cases this would be the result of a bug. The runtime cost is one NEW_AUX_ENT using two words of stack space. The underlying value is maintained already as bprm->exec; setup_arg_pages() in fs/exec.c slides it for stack_shift, etc. Signed-off-by: John Reiser Cc: Roland McGrath Cc: Jakub Jelinek Cc: Ulrich Drepper Cc: Benjamin Herrenschmidt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/auxvec.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux/auxvec.h') diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h index ad895455ab72..0da17d14fd13 100644 --- a/include/linux/auxvec.h +++ b/include/linux/auxvec.h @@ -26,8 +26,10 @@ #define AT_SECURE 23 /* secure mode boolean */ +#define AT_EXECFN 31 /* filename of program */ #ifdef __KERNEL__ -#define AT_VECTOR_SIZE_BASE (14 + 2) /* NEW_AUX_ENT entries in auxiliary table */ +#define AT_VECTOR_SIZE_BASE 17 /* NEW_AUX_ENT entries in auxiliary table */ + /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */ #endif #endif /* _LINUX_AUXVEC_H */ -- cgit v1.2.3 From 483fad1c3fa1060d7e6710e84a065ad514571739 Mon Sep 17 00:00:00 2001 From: Nathan Lynch Date: Tue, 22 Jul 2008 04:48:46 +1000 Subject: ELF loader support for auxvec base platform string Some IBM POWER-based platforms have the ability to run in a mode which mostly appears to the OS as a different processor from the actual hardware. For example, a Power6 system may appear to be a Power5+, which makes the AT_PLATFORM value "power5+". This means that programs are restricted to the ISA supported by Power5+; Power6-specific instructions are treated as illegal. However, some applications (virtual machines, optimized libraries) can benefit from knowledge of the underlying CPU model. A new aux vector entry, AT_BASE_PLATFORM, will denote the actual hardware. For example, on a Power6 system in Power5+ compatibility mode, AT_PLATFORM will be "power5+" and AT_BASE_PLATFORM will be "power6". The idea is that AT_PLATFORM indicates the instruction set supported, while AT_BASE_PLATFORM indicates the underlying microarchitecture. If the architecture has defined ELF_BASE_PLATFORM, copy that value to the user stack in the same manner as ELF_PLATFORM. Signed-off-by: Nathan Lynch Acked-by: Andrew Morton Signed-off-by: Benjamin Herrenschmidt --- fs/binfmt_elf.c | 28 ++++++++++++++++++++++++++++ include/linux/auxvec.h | 6 +++++- 2 files changed, 33 insertions(+), 1 deletion(-) (limited to 'include/linux/auxvec.h') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 639d2d8b5710..742c8f530481 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -131,6 +131,15 @@ static int padzero(unsigned long elf_bss) #define STACK_ALLOC(sp, len) ({ sp -= len ; sp; }) #endif +#ifndef ELF_BASE_PLATFORM +/* + * AT_BASE_PLATFORM indicates the "real" hardware/microarchitecture. + * If the arch defines ELF_BASE_PLATFORM (in asm/elf.h), the value + * will be copied to the user stack in the same manner as AT_PLATFORM. + */ +#define ELF_BASE_PLATFORM NULL +#endif + static int create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, unsigned long load_addr, unsigned long interp_load_addr) @@ -142,7 +151,9 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, elf_addr_t __user *envp; elf_addr_t __user *sp; elf_addr_t __user *u_platform; + elf_addr_t __user *u_base_platform; const char *k_platform = ELF_PLATFORM; + const char *k_base_platform = ELF_BASE_PLATFORM; int items; elf_addr_t *elf_info; int ei_index = 0; @@ -172,6 +183,19 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, return -EFAULT; } + /* + * If this architecture has a "base" platform capability + * string, copy it to userspace. + */ + u_base_platform = NULL; + if (k_base_platform) { + size_t len = strlen(k_base_platform) + 1; + + u_base_platform = (elf_addr_t __user *)STACK_ALLOC(p, len); + if (__copy_to_user(u_base_platform, k_base_platform, len)) + return -EFAULT; + } + /* Create the ELF interpreter info */ elf_info = (elf_addr_t *)current->mm->saved_auxv; /* update AT_VECTOR_SIZE_BASE if the number of NEW_AUX_ENT() changes */ @@ -209,6 +233,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, NEW_AUX_ENT(AT_PLATFORM, (elf_addr_t)(unsigned long)u_platform); } + if (k_base_platform) { + NEW_AUX_ENT(AT_BASE_PLATFORM, + (elf_addr_t)(unsigned long)u_base_platform); + } if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) { NEW_AUX_ENT(AT_EXECFD, bprm->interp_data); } diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h index 0da17d14fd13..d7afa9dd6635 100644 --- a/include/linux/auxvec.h +++ b/include/linux/auxvec.h @@ -26,9 +26,13 @@ #define AT_SECURE 23 /* secure mode boolean */ +#define AT_BASE_PLATFORM 24 /* string identifying real platform, may + * differ from AT_PLATFORM. */ + #define AT_EXECFN 31 /* filename of program */ + #ifdef __KERNEL__ -#define AT_VECTOR_SIZE_BASE 17 /* NEW_AUX_ENT entries in auxiliary table */ +#define AT_VECTOR_SIZE_BASE 18 /* NEW_AUX_ENT entries in auxiliary table */ /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */ #endif -- cgit v1.2.3