X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fbinfmt_elf_fdpic.c;h=63039ed9576f75c396ed0dae71bec1e4abf53058;hb=3be2264be3c00865116f997dc53ebcc90fe7fc4b;hp=a4ff87389823dedacb6c1cc7abc16862148eb238;hpb=8a2ab7f5df76b920d62b908919d987d3b8a82856;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index a4ff873..63039ed 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -24,23 +24,23 @@ #include #include #include +#include +#include #include +#include #include #include #include -#include #include #include #include +#include #include #include #include typedef char *elf_caddr_t; -#ifndef elf_addr_t -#define elf_addr_t unsigned long -#endif #if 0 #define kdebug(fmt, ...) printk("FDPIC "fmt"\n" ,##__VA_ARGS__ ) @@ -48,6 +48,12 @@ typedef char *elf_caddr_t; #define kdebug(fmt, ...) do {} while(0) #endif +#if 0 +#define kdcore(fmt, ...) printk("FDPIC "fmt"\n" ,##__VA_ARGS__ ) +#else +#define kdcore(fmt, ...) do {} while(0) +#endif + MODULE_LICENSE("GPL"); static int load_elf_fdpic_binary(struct linux_binprm *, struct pt_regs *); @@ -70,10 +76,16 @@ static int elf_fdpic_map_file_constdisp_on_uclinux(struct elf_fdpic_params *, static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *, struct file *, struct mm_struct *); +#ifdef CONFIG_ELF_CORE +static int elf_fdpic_core_dump(struct coredump_params *cprm); +#endif + static struct linux_binfmt elf_fdpic_format = { .module = THIS_MODULE, .load_binary = load_elf_fdpic_binary, -// .core_dump = elf_fdpic_core_dump, +#ifdef CONFIG_ELF_CORE + .core_dump = elf_fdpic_core_dump, +#endif .min_coredump = ELF_EXEC_PAGESIZE, }; @@ -87,7 +99,7 @@ static void __exit exit_elf_fdpic_binfmt(void) unregister_binfmt(&elf_fdpic_format); } -module_init(init_elf_fdpic_binfmt); +core_initcall(init_elf_fdpic_binfmt); module_exit(exit_elf_fdpic_binfmt); static int is_elf_fdpic(struct elfhdr *hdr, struct file *file) @@ -126,8 +138,8 @@ static int elf_fdpic_fetch_phdrs(struct elf_fdpic_params *params, retval = kernel_read(file, params->hdr.e_phoff, (char *) params->phdrs, size); - if (retval < 0) - return retval; + if (unlikely(retval != size)) + return retval < 0 ? retval : -ENOEXEC; /* determine stack size for this binary */ phdr = params->phdrs; @@ -157,17 +169,19 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, struct elf_fdpic_params exec_params, interp_params; struct elf_phdr *phdr; unsigned long stack_size, entryaddr; -#ifndef CONFIG_MMU - unsigned long fullsize; -#endif #ifdef ELF_FDPIC_PLAT_INIT unsigned long dynaddr; #endif +#ifndef CONFIG_MMU + unsigned long stack_prot; +#endif struct file *interpreter = NULL; /* to shut gcc up */ char *interpreter_name = NULL; int executable_stack; int retval, i; + kdebug("____ LOAD %d ____", current->pid); + memset(&exec_params, 0, sizeof(exec_params)); memset(&interp_params, 0, sizeof(interp_params)); @@ -206,8 +220,11 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, phdr->p_offset, interpreter_name, phdr->p_filesz); - if (retval < 0) + if (unlikely(retval != phdr->p_filesz)) { + if (retval >= 0) + retval = -ENOEXEC; goto error; + } retval = -ENOENT; if (interpreter_name[phdr->p_filesz - 1] != '\0') @@ -223,10 +240,21 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, goto error; } + /* + * If the binary is not readable then enforce + * mm->dumpable = 0 regardless of the interpreter's + * permissions. + */ + if (file_permission(interpreter, MAY_READ) < 0) + bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; + retval = kernel_read(interpreter, 0, bprm->buf, BINPRM_BUF_SIZE); - if (retval < 0) + if (unlikely(retval != BINPRM_BUF_SIZE)) { + if (retval >= 0) + retval = -ENOEXEC; goto error; + } interp_params.hdr = *((struct elfhdr *) bprm->buf); break; @@ -259,20 +287,23 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, } stack_size = exec_params.stack_size; - if (stack_size < interp_params.stack_size) - stack_size = interp_params.stack_size; - if (exec_params.flags & ELF_FDPIC_FLAG_EXEC_STACK) executable_stack = EXSTACK_ENABLE_X; else if (exec_params.flags & ELF_FDPIC_FLAG_NOEXEC_STACK) executable_stack = EXSTACK_DISABLE_X; - else if (interp_params.flags & ELF_FDPIC_FLAG_EXEC_STACK) - executable_stack = EXSTACK_ENABLE_X; - else if (interp_params.flags & ELF_FDPIC_FLAG_NOEXEC_STACK) - executable_stack = EXSTACK_DISABLE_X; else executable_stack = EXSTACK_DEFAULT; + if (stack_size == 0) { + stack_size = interp_params.stack_size; + if (interp_params.flags & ELF_FDPIC_FLAG_EXEC_STACK) + executable_stack = EXSTACK_ENABLE_X; + else if (interp_params.flags & ELF_FDPIC_FLAG_NOEXEC_STACK) + executable_stack = EXSTACK_DISABLE_X; + else + executable_stack = EXSTACK_DEFAULT; + } + retval = -ENOEXEC; if (stack_size == 0) goto error; @@ -289,6 +320,11 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, * defunct, deceased, etc. after this point we have to exit via * error_kill */ set_personality(PER_LINUX_FDPIC); + if (elf_read_implies_exec(&exec_params.hdr, executable_stack)) + current->personality |= READ_IMPLIES_EXEC; + + setup_new_exec(bprm); + set_binfmt(&elf_fdpic_format); current->mm->start_code = 0; @@ -350,10 +386,15 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, if (stack_size < PAGE_SIZE * 2) stack_size = PAGE_SIZE * 2; + stack_prot = PROT_READ | PROT_WRITE; + if (executable_stack == EXSTACK_ENABLE_X || + (executable_stack == EXSTACK_DEFAULT && VM_STACK_FLAGS & VM_EXEC)) + stack_prot |= PROT_EXEC; + down_write(¤t->mm->mmap_sem); - current->mm->start_brk = do_mmap(NULL, 0, stack_size, - PROT_READ | PROT_WRITE | PROT_EXEC, - MAP_PRIVATE | MAP_ANON | MAP_GROWSDOWN, + current->mm->start_brk = do_mmap(NULL, 0, stack_size, stack_prot, + MAP_PRIVATE | MAP_ANONYMOUS | + MAP_UNINITIALIZED | MAP_GROWSDOWN, 0); if (IS_ERR_VALUE(current->mm->start_brk)) { @@ -363,11 +404,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, goto error_kill; } - /* expand the stack mapping to use up the entire allocation granule */ - fullsize = ksize((char *) current->mm->start_brk); - if (!IS_ERR_VALUE(do_mremap(current->mm->start_brk, stack_size, - fullsize, 0, 0))) - stack_size = fullsize; up_write(¤t->mm->mmap_sem); current->mm->brk = current->mm->start_brk; @@ -377,7 +413,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, current->mm->start_stack = current->mm->start_brk + stack_size; #endif - compute_creds(bprm); + install_exec_creds(bprm); current->flags &= ~PF_FORKNOEXEC; if (create_elf_fdpic_tables(bprm, current->mm, &exec_params, &interp_params) < 0) @@ -407,13 +443,6 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, entryaddr = interp_params.entry_addr ?: exec_params.entry_addr; start_thread(regs, entryaddr, current->mm->start_stack); - if (unlikely(current->ptrace & PT_PTRACED)) { - if (current->ptrace & PT_TRACE_EXEC) - ptrace_notify((PTRACE_EVENT_EXEC << 8) | SIGTRAP); - else - send_sig(SIGTRAP, current, 0); - } - retval = 0; error: @@ -436,25 +465,42 @@ error_kill: } /*****************************************************************************/ + +#ifndef ELF_BASE_PLATFORM /* - * present useful information to the program + * 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 + +/* + * present useful information to the program by shovelling it onto the new + * process's stack */ static int create_elf_fdpic_tables(struct linux_binprm *bprm, struct mm_struct *mm, struct elf_fdpic_params *exec_params, struct elf_fdpic_params *interp_params) { + const struct cred *cred = current_cred(); unsigned long sp, csp, nitems; elf_caddr_t __user *argv, *envp; size_t platform_len = 0, len; - char *k_platform; - char __user *u_platform, *p; + char *k_platform, *k_base_platform; + char __user *u_platform, *u_base_platform, *p; long hwcap; int loop; + int nr; /* reset for each csp adjustment */ - /* we're going to shovel a whole load of stuff onto the stack */ #ifdef CONFIG_MMU - sp = bprm->p; + /* In some cases (e.g. Hyper-Threading), we want to avoid L1 evictions + * by the processes running on the same package. One thing we can do is + * to shuffle the initial stack for them, so we give the architecture + * an opportunity to do so here. + */ + sp = arch_align_stack(bprm->p); #else sp = mm->start_stack; @@ -463,11 +509,14 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, return -EFAULT; #endif - /* get hold of platform and hardware capabilities masks for the machine - * we are running on. In some cases (Sparc), this info is impossible - * to get, in others (i386) it is merely difficult. - */ hwcap = ELF_HWCAP; + + /* + * If this architecture has a platform capability string, copy it + * to userspace. In some cases (Sparc), this info is impossible + * for userspace to get any other way, in others (i386) it is + * merely difficult. + */ k_platform = ELF_PLATFORM; u_platform = NULL; @@ -479,19 +528,20 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, return -EFAULT; } -#if defined(__i386__) && defined(CONFIG_SMP) - /* in some cases (e.g. Hyper-Threading), we want to avoid L1 evictions - * by the processes running on the same package. One thing we can do is - * to shuffle the initial stack for them. - * - * the conditionals here are unneeded, but kept in to make the code - * behaviour the same as pre change unless we have hyperthreaded - * processors. This keeps Mr Marcelo Person happier but should be - * removed for 2.5 + /* + * If this architecture has a "base" platform capability + * string, copy it to userspace. */ - if (smp_num_siblings > 1) - sp = sp - ((current->pid % 64) << 7); -#endif + k_base_platform = ELF_BASE_PLATFORM; + u_base_platform = NULL; + + if (k_base_platform) { + platform_len = strlen(k_base_platform) + 1; + sp -= platform_len; + u_base_platform = (char __user *) sp; + if (__copy_to_user(u_base_platform, k_base_platform, platform_len) != 0) + return -EFAULT; + } sp &= ~7UL; @@ -521,12 +571,13 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, } /* force 16 byte _final_ alignment here for generality */ -#define DLINFO_ITEMS 13 +#define DLINFO_ITEMS 15 - nitems = 1 + DLINFO_ITEMS + (k_platform ? 1 : 0); -#ifdef DLINFO_ARCH_ITEMS - nitems += DLINFO_ARCH_ITEMS; -#endif + nitems = 1 + DLINFO_ITEMS + (k_platform ? 1 : 0) + + (k_base_platform ? 1 : 0) + AT_VECTOR_SIZE_ARCH; + + if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) + nitems++; csp = sp; sp -= nitems * 2 * sizeof(unsigned long); @@ -538,39 +589,61 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, sp -= sp & 15UL; /* put the ELF interpreter info on the stack */ -#define NEW_AUX_ENT(nr, id, val) \ +#define NEW_AUX_ENT(id, val) \ do { \ struct { unsigned long _id, _val; } __user *ent; \ \ ent = (void __user *) csp; \ __put_user((id), &ent[nr]._id); \ __put_user((val), &ent[nr]._val); \ + nr++; \ } while (0) + nr = 0; csp -= 2 * sizeof(unsigned long); - NEW_AUX_ENT(0, AT_NULL, 0); + NEW_AUX_ENT(AT_NULL, 0); if (k_platform) { + nr = 0; csp -= 2 * sizeof(unsigned long); - NEW_AUX_ENT(0, AT_PLATFORM, + NEW_AUX_ENT(AT_PLATFORM, (elf_addr_t) (unsigned long) u_platform); } + if (k_base_platform) { + nr = 0; + csp -= 2 * sizeof(unsigned long); + NEW_AUX_ENT(AT_BASE_PLATFORM, + (elf_addr_t) (unsigned long) u_base_platform); + } + + if (bprm->interp_flags & BINPRM_FLAGS_EXECFD) { + nr = 0; + csp -= 2 * sizeof(unsigned long); + NEW_AUX_ENT(AT_EXECFD, bprm->interp_data); + } + + nr = 0; csp -= DLINFO_ITEMS * 2 * sizeof(unsigned long); - NEW_AUX_ENT( 0, AT_HWCAP, hwcap); - NEW_AUX_ENT( 1, AT_PAGESZ, PAGE_SIZE); - NEW_AUX_ENT( 2, AT_CLKTCK, CLOCKS_PER_SEC); - NEW_AUX_ENT( 3, AT_PHDR, exec_params->ph_addr); - NEW_AUX_ENT( 4, AT_PHENT, sizeof(struct elf_phdr)); - NEW_AUX_ENT( 5, AT_PHNUM, exec_params->hdr.e_phnum); - NEW_AUX_ENT( 6, AT_BASE, interp_params->elfhdr_addr); - NEW_AUX_ENT( 7, AT_FLAGS, 0); - NEW_AUX_ENT( 8, AT_ENTRY, exec_params->entry_addr); - NEW_AUX_ENT( 9, AT_UID, (elf_addr_t) current->uid); - NEW_AUX_ENT(10, AT_EUID, (elf_addr_t) current->euid); - NEW_AUX_ENT(11, AT_GID, (elf_addr_t) current->gid); - NEW_AUX_ENT(12, AT_EGID, (elf_addr_t) current->egid); + NEW_AUX_ENT(AT_HWCAP, hwcap); + NEW_AUX_ENT(AT_PAGESZ, PAGE_SIZE); + NEW_AUX_ENT(AT_CLKTCK, CLOCKS_PER_SEC); + NEW_AUX_ENT(AT_PHDR, exec_params->ph_addr); + NEW_AUX_ENT(AT_PHENT, sizeof(struct elf_phdr)); + NEW_AUX_ENT(AT_PHNUM, exec_params->hdr.e_phnum); + NEW_AUX_ENT(AT_BASE, interp_params->elfhdr_addr); + NEW_AUX_ENT(AT_FLAGS, 0); + NEW_AUX_ENT(AT_ENTRY, exec_params->entry_addr); + NEW_AUX_ENT(AT_UID, (elf_addr_t) cred->uid); + NEW_AUX_ENT(AT_EUID, (elf_addr_t) cred->euid); + NEW_AUX_ENT(AT_GID, (elf_addr_t) cred->gid); + NEW_AUX_ENT(AT_EGID, (elf_addr_t) cred->egid); + NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm)); + NEW_AUX_ENT(AT_EXECFN, bprm->exec); #ifdef ARCH_DLINFO + nr = 0; + csp -= AT_VECTOR_SIZE_ARCH * 2 * sizeof(unsigned long); + /* ARCH_DLINFO must come last so platform specific code can enforce * special alignment requirements on the AUXV if necessary (eg. PPC). */ @@ -601,8 +674,8 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, p = (char __user *) current->mm->arg_start; for (loop = bprm->argc; loop > 0; loop--) { __put_user((elf_caddr_t) p, argv++); - len = strnlen_user(p, PAGE_SIZE * MAX_ARG_PAGES); - if (!len || len > PAGE_SIZE * MAX_ARG_PAGES) + len = strnlen_user(p, MAX_ARG_STRLEN); + if (!len || len > MAX_ARG_STRLEN) return -EINVAL; p += len; } @@ -613,8 +686,8 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, current->mm->env_start = (unsigned long) p; for (loop = bprm->envc; loop > 0; loop--) { __put_user((elf_caddr_t)(unsigned long) p, envp++); - len = strnlen_user(p, PAGE_SIZE * MAX_ARG_PAGES); - if (!len || len > PAGE_SIZE * MAX_ARG_PAGES) + len = strnlen_user(p, MAX_ARG_STRLEN); + if (!len || len > MAX_ARG_STRLEN) return -EINVAL; p += len; } @@ -695,12 +768,11 @@ static int elf_fdpic_map_file(struct elf_fdpic_params *params, return -ELIBBAD; size = sizeof(*loadmap) + nloads * sizeof(*seg); - loadmap = kmalloc(size, GFP_KERNEL); + loadmap = kzalloc(size, GFP_KERNEL); if (!loadmap) return -ENOMEM; params->loadmap = loadmap; - memset(loadmap, 0, size); loadmap->version = ELF32_FDPIC_LOADMAP_VERSION; loadmap->nsegs = nloads; @@ -844,7 +916,7 @@ static int elf_fdpic_map_file(struct elf_fdpic_params *params, dynamic_error: printk("ELF FDPIC %s with invalid DYNAMIC section (inode=%lu)\n", - what, file->f_dentry->d_inode->i_ino); + what, file->f_path.dentry->d_inode->i_ino); return -ELIBBAD; } @@ -917,25 +989,23 @@ static int elf_fdpic_map_file_constdisp_on_uclinux( params->elfhdr_addr = seg->addr; /* clear any space allocated but not loaded */ - if (phdr->p_filesz < phdr->p_memsz) - clear_user((void *) (seg->addr + phdr->p_filesz), - phdr->p_memsz - phdr->p_filesz); + if (phdr->p_filesz < phdr->p_memsz) { + if (clear_user((void *) (seg->addr + phdr->p_filesz), + phdr->p_memsz - phdr->p_filesz)) + return -EFAULT; + } if (mm) { if (phdr->p_flags & PF_X) { - mm->start_code = seg->addr; - mm->end_code = seg->addr + phdr->p_memsz; + if (!mm->start_code) { + mm->start_code = seg->addr; + mm->end_code = seg->addr + + phdr->p_memsz; + } } else if (!mm->start_data) { mm->start_data = seg->addr; -#ifndef CONFIG_MMU mm->end_data = seg->addr + phdr->p_memsz; -#endif } - -#ifdef CONFIG_MMU - if (seg->addr + phdr->p_memsz > mm->end_data) - mm->end_data = seg->addr + phdr->p_memsz; -#endif } seg++; @@ -1056,7 +1126,8 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, * PT_LOAD */ if (prot & PROT_WRITE && disp > 0) { kdebug("clear[%d] ad=%lx sz=%lx", loop, maddr, disp); - clear_user((void __user *) maddr, disp); + if (clear_user((void __user *) maddr, disp)) + return -EFAULT; maddr += disp; } @@ -1091,22 +1162,26 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, if (prot & PROT_WRITE && excess1 > 0) { kdebug("clear[%d] ad=%lx sz=%lx", loop, maddr + phdr->p_filesz, excess1); - clear_user((void __user *) maddr + phdr->p_filesz, - excess1); + if (clear_user((void __user *) maddr + phdr->p_filesz, + excess1)) + return -EFAULT; } #else if (excess > 0) { kdebug("clear[%d] ad=%lx sz=%lx", loop, maddr + phdr->p_filesz, excess); - clear_user((void *) maddr + phdr->p_filesz, excess); + if (clear_user((void *) maddr + phdr->p_filesz, excess)) + return -EFAULT; } #endif if (mm) { if (phdr->p_flags & PF_X) { - mm->start_code = maddr; - mm->end_code = maddr + phdr->p_memsz; + if (!mm->start_code) { + mm->start_code = maddr; + mm->end_code = maddr + phdr->p_memsz; + } } else if (!mm->start_data) { mm->start_data = maddr; mm->end_data = maddr + phdr->p_memsz; @@ -1118,3 +1193,682 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params, return 0; } + +/*****************************************************************************/ +/* + * ELF-FDPIC core dumper + * + * Modelled on fs/exec.c:aout_core_dump() + * Jeremy Fitzhardinge + * + * Modelled on fs/binfmt_elf.c core dumper + */ +#ifdef CONFIG_ELF_CORE + +/* + * Decide whether a segment is worth dumping; default is yes to be + * sure (missing info is worse than too much; etc). + * Personally I'd include everything, and use the coredump limit... + * + * I think we should skip something. But I am not sure how. H.J. + */ +static int maydump(struct vm_area_struct *vma, unsigned long mm_flags) +{ + int dump_ok; + + /* Do not dump I/O mapped devices or special mappings */ + if (vma->vm_flags & (VM_IO | VM_RESERVED)) { + kdcore("%08lx: %08lx: no (IO)", vma->vm_start, vma->vm_flags); + return 0; + } + + /* If we may not read the contents, don't allow us to dump + * them either. "dump_write()" can't handle it anyway. + */ + if (!(vma->vm_flags & VM_READ)) { + kdcore("%08lx: %08lx: no (!read)", vma->vm_start, vma->vm_flags); + return 0; + } + + /* By default, dump shared memory if mapped from an anonymous file. */ + if (vma->vm_flags & VM_SHARED) { + if (vma->vm_file->f_path.dentry->d_inode->i_nlink == 0) { + dump_ok = test_bit(MMF_DUMP_ANON_SHARED, &mm_flags); + kdcore("%08lx: %08lx: %s (share)", vma->vm_start, + vma->vm_flags, dump_ok ? "yes" : "no"); + return dump_ok; + } + + dump_ok = test_bit(MMF_DUMP_MAPPED_SHARED, &mm_flags); + kdcore("%08lx: %08lx: %s (share)", vma->vm_start, + vma->vm_flags, dump_ok ? "yes" : "no"); + return dump_ok; + } + +#ifdef CONFIG_MMU + /* By default, if it hasn't been written to, don't write it out */ + if (!vma->anon_vma) { + dump_ok = test_bit(MMF_DUMP_MAPPED_PRIVATE, &mm_flags); + kdcore("%08lx: %08lx: %s (!anon)", vma->vm_start, + vma->vm_flags, dump_ok ? "yes" : "no"); + return dump_ok; + } +#endif + + dump_ok = test_bit(MMF_DUMP_ANON_PRIVATE, &mm_flags); + kdcore("%08lx: %08lx: %s", vma->vm_start, vma->vm_flags, + dump_ok ? "yes" : "no"); + return dump_ok; +} + +/* An ELF note in memory */ +struct memelfnote +{ + const char *name; + int type; + unsigned int datasz; + void *data; +}; + +static int notesize(struct memelfnote *en) +{ + int sz; + + sz = sizeof(struct elf_note); + sz += roundup(strlen(en->name) + 1, 4); + sz += roundup(en->datasz, 4); + + return sz; +} + +/* #define DEBUG */ + +#define DUMP_WRITE(addr, nr, foffset) \ + do { if (!dump_write(file, (addr), (nr))) return 0; *foffset += (nr); } while(0) + +static int alignfile(struct file *file, loff_t *foffset) +{ + static const char buf[4] = { 0, }; + DUMP_WRITE(buf, roundup(*foffset, 4) - *foffset, foffset); + return 1; +} + +static int writenote(struct memelfnote *men, struct file *file, + loff_t *foffset) +{ + struct elf_note en; + en.n_namesz = strlen(men->name) + 1; + en.n_descsz = men->datasz; + en.n_type = men->type; + + DUMP_WRITE(&en, sizeof(en), foffset); + DUMP_WRITE(men->name, en.n_namesz, foffset); + if (!alignfile(file, foffset)) + return 0; + DUMP_WRITE(men->data, men->datasz, foffset); + if (!alignfile(file, foffset)) + return 0; + + return 1; +} +#undef DUMP_WRITE + +static inline void fill_elf_fdpic_header(struct elfhdr *elf, int segs) +{ + memcpy(elf->e_ident, ELFMAG, SELFMAG); + elf->e_ident[EI_CLASS] = ELF_CLASS; + elf->e_ident[EI_DATA] = ELF_DATA; + elf->e_ident[EI_VERSION] = EV_CURRENT; + elf->e_ident[EI_OSABI] = ELF_OSABI; + memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD); + + elf->e_type = ET_CORE; + elf->e_machine = ELF_ARCH; + elf->e_version = EV_CURRENT; + elf->e_entry = 0; + elf->e_phoff = sizeof(struct elfhdr); + elf->e_shoff = 0; + elf->e_flags = ELF_FDPIC_CORE_EFLAGS; + elf->e_ehsize = sizeof(struct elfhdr); + elf->e_phentsize = sizeof(struct elf_phdr); + elf->e_phnum = segs; + elf->e_shentsize = 0; + elf->e_shnum = 0; + elf->e_shstrndx = 0; + return; +} + +static inline void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offset) +{ + phdr->p_type = PT_NOTE; + phdr->p_offset = offset; + phdr->p_vaddr = 0; + phdr->p_paddr = 0; + phdr->p_filesz = sz; + phdr->p_memsz = 0; + phdr->p_flags = 0; + phdr->p_align = 0; + return; +} + +static inline void fill_note(struct memelfnote *note, const char *name, int type, + unsigned int sz, void *data) +{ + note->name = name; + note->type = type; + note->datasz = sz; + note->data = data; + return; +} + +/* + * fill up all the fields in prstatus from the given task struct, except + * registers which need to be filled up separately. + */ +static void fill_prstatus(struct elf_prstatus *prstatus, + struct task_struct *p, long signr) +{ + prstatus->pr_info.si_signo = prstatus->pr_cursig = signr; + prstatus->pr_sigpend = p->pending.signal.sig[0]; + prstatus->pr_sighold = p->blocked.sig[0]; + rcu_read_lock(); + prstatus->pr_ppid = task_pid_vnr(rcu_dereference(p->real_parent)); + rcu_read_unlock(); + prstatus->pr_pid = task_pid_vnr(p); + prstatus->pr_pgrp = task_pgrp_vnr(p); + prstatus->pr_sid = task_session_vnr(p); + if (thread_group_leader(p)) { + struct task_cputime cputime; + + /* + * This is the record for the group leader. It shows the + * group-wide total, not its individual thread total. + */ + thread_group_cputime(p, &cputime); + cputime_to_timeval(cputime.utime, &prstatus->pr_utime); + cputime_to_timeval(cputime.stime, &prstatus->pr_stime); + } else { + cputime_to_timeval(p->utime, &prstatus->pr_utime); + cputime_to_timeval(p->stime, &prstatus->pr_stime); + } + cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime); + cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime); + + prstatus->pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap; + prstatus->pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap; +} + +static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, + struct mm_struct *mm) +{ + const struct cred *cred; + unsigned int i, len; + + /* first copy the parameters from user space */ + memset(psinfo, 0, sizeof(struct elf_prpsinfo)); + + len = mm->arg_end - mm->arg_start; + if (len >= ELF_PRARGSZ) + len = ELF_PRARGSZ - 1; + if (copy_from_user(&psinfo->pr_psargs, + (const char __user *) mm->arg_start, len)) + return -EFAULT; + for (i = 0; i < len; i++) + if (psinfo->pr_psargs[i] == 0) + psinfo->pr_psargs[i] = ' '; + psinfo->pr_psargs[len] = 0; + + rcu_read_lock(); + psinfo->pr_ppid = task_pid_vnr(rcu_dereference(p->real_parent)); + rcu_read_unlock(); + psinfo->pr_pid = task_pid_vnr(p); + psinfo->pr_pgrp = task_pgrp_vnr(p); + psinfo->pr_sid = task_session_vnr(p); + + i = p->state ? ffz(~p->state) + 1 : 0; + psinfo->pr_state = i; + psinfo->pr_sname = (i > 5) ? '.' : "RSDTZW"[i]; + psinfo->pr_zomb = psinfo->pr_sname == 'Z'; + psinfo->pr_nice = task_nice(p); + psinfo->pr_flag = p->flags; + rcu_read_lock(); + cred = __task_cred(p); + SET_UID(psinfo->pr_uid, cred->uid); + SET_GID(psinfo->pr_gid, cred->gid); + rcu_read_unlock(); + strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname)); + + return 0; +} + +/* Here is the structure in which status of each thread is captured. */ +struct elf_thread_status +{ + struct list_head list; + struct elf_prstatus prstatus; /* NT_PRSTATUS */ + elf_fpregset_t fpu; /* NT_PRFPREG */ + struct task_struct *thread; +#ifdef ELF_CORE_COPY_XFPREGS + elf_fpxregset_t xfpu; /* ELF_CORE_XFPREG_TYPE */ +#endif + struct memelfnote notes[3]; + int num_notes; +}; + +/* + * In order to add the specific thread information for the elf file format, + * we need to keep a linked list of every thread's pr_status and then create + * a single section for them in the final core file. + */ +static int elf_dump_thread_status(long signr, struct elf_thread_status *t) +{ + struct task_struct *p = t->thread; + int sz = 0; + + t->num_notes = 0; + + fill_prstatus(&t->prstatus, p, signr); + elf_core_copy_task_regs(p, &t->prstatus.pr_reg); + + fill_note(&t->notes[0], "CORE", NT_PRSTATUS, sizeof(t->prstatus), + &t->prstatus); + t->num_notes++; + sz += notesize(&t->notes[0]); + + t->prstatus.pr_fpvalid = elf_core_copy_task_fpregs(p, NULL, &t->fpu); + if (t->prstatus.pr_fpvalid) { + fill_note(&t->notes[1], "CORE", NT_PRFPREG, sizeof(t->fpu), + &t->fpu); + t->num_notes++; + sz += notesize(&t->notes[1]); + } + +#ifdef ELF_CORE_COPY_XFPREGS + if (elf_core_copy_task_xfpregs(p, &t->xfpu)) { + fill_note(&t->notes[2], "LINUX", ELF_CORE_XFPREG_TYPE, + sizeof(t->xfpu), &t->xfpu); + t->num_notes++; + sz += notesize(&t->notes[2]); + } +#endif + return sz; +} + +static void fill_extnum_info(struct elfhdr *elf, struct elf_shdr *shdr4extnum, + elf_addr_t e_shoff, int segs) +{ + elf->e_shoff = e_shoff; + elf->e_shentsize = sizeof(*shdr4extnum); + elf->e_shnum = 1; + elf->e_shstrndx = SHN_UNDEF; + + memset(shdr4extnum, 0, sizeof(*shdr4extnum)); + + shdr4extnum->sh_type = SHT_NULL; + shdr4extnum->sh_size = elf->e_shnum; + shdr4extnum->sh_link = elf->e_shstrndx; + shdr4extnum->sh_info = segs; +} + +/* + * dump the segments for an MMU process + */ +#ifdef CONFIG_MMU +static int elf_fdpic_dump_segments(struct file *file, size_t *size, + unsigned long *limit, unsigned long mm_flags) +{ + struct vm_area_struct *vma; + int err = 0; + + for (vma = current->mm->mmap; vma; vma = vma->vm_next) { + unsigned long addr; + + if (!maydump(vma, mm_flags)) + continue; + + for (addr = vma->vm_start; addr < vma->vm_end; + addr += PAGE_SIZE) { + struct page *page = get_dump_page(addr); + if (page) { + void *kaddr = kmap(page); + *size += PAGE_SIZE; + if (*size > *limit) + err = -EFBIG; + else if (!dump_write(file, kaddr, PAGE_SIZE)) + err = -EIO; + kunmap(page); + page_cache_release(page); + } else if (!dump_seek(file, PAGE_SIZE)) + err = -EFBIG; + if (err) + goto out; + } + } +out: + return err; +} +#endif + +/* + * dump the segments for a NOMMU process + */ +#ifndef CONFIG_MMU +static int elf_fdpic_dump_segments(struct file *file, size_t *size, + unsigned long *limit, unsigned long mm_flags) +{ + struct vm_area_struct *vma; + + for (vma = current->mm->mmap; vma; vma = vma->vm_next) { + if (!maydump(vma, mm_flags)) + continue; + + if ((*size += PAGE_SIZE) > *limit) + return -EFBIG; + + if (!dump_write(file, (void *) vma->vm_start, + vma->vm_end - vma->vm_start)) + return -EIO; + } + + return 0; +} +#endif + +static size_t elf_core_vma_data_size(unsigned long mm_flags) +{ + struct vm_area_struct *vma; + size_t size = 0; + + for (vma = current->mm->mmap; vma; vma = vma->vm_next) + if (maydump(vma, mm_flags)) + size += vma->vm_end - vma->vm_start; + return size; +} + +/* + * Actual dumper + * + * This is a two-pass process; first we find the offsets of the bits, + * and then they are actually written out. If we run out of core limit + * we just truncate. + */ +static int elf_fdpic_core_dump(struct coredump_params *cprm) +{ +#define NUM_NOTES 6 + int has_dumped = 0; + mm_segment_t fs; + int segs; + size_t size = 0; + int i; + struct vm_area_struct *vma; + struct elfhdr *elf = NULL; + loff_t offset = 0, dataoff, foffset; + int numnote; + struct memelfnote *notes = NULL; + struct elf_prstatus *prstatus = NULL; /* NT_PRSTATUS */ + struct elf_prpsinfo *psinfo = NULL; /* NT_PRPSINFO */ + LIST_HEAD(thread_list); + struct list_head *t; + elf_fpregset_t *fpu = NULL; +#ifdef ELF_CORE_COPY_XFPREGS + elf_fpxregset_t *xfpu = NULL; +#endif + int thread_status_size = 0; + elf_addr_t *auxv; + struct elf_phdr *phdr4note = NULL; + struct elf_shdr *shdr4extnum = NULL; + Elf_Half e_phnum; + elf_addr_t e_shoff; + + /* + * We no longer stop all VM operations. + * + * This is because those proceses that could possibly change map_count + * or the mmap / vma pages are now blocked in do_exit on current + * finishing this core dump. + * + * Only ptrace can touch these memory addresses, but it doesn't change + * the map_count or the pages allocated. So no possibility of crashing + * exists while dumping the mm->vm_next areas to the core file. + */ + + /* alloc memory for large data structures: too large to be on stack */ + elf = kmalloc(sizeof(*elf), GFP_KERNEL); + if (!elf) + goto cleanup; + prstatus = kzalloc(sizeof(*prstatus), GFP_KERNEL); + if (!prstatus) + goto cleanup; + psinfo = kmalloc(sizeof(*psinfo), GFP_KERNEL); + if (!psinfo) + goto cleanup; + notes = kmalloc(NUM_NOTES * sizeof(struct memelfnote), GFP_KERNEL); + if (!notes) + goto cleanup; + fpu = kmalloc(sizeof(*fpu), GFP_KERNEL); + if (!fpu) + goto cleanup; +#ifdef ELF_CORE_COPY_XFPREGS + xfpu = kmalloc(sizeof(*xfpu), GFP_KERNEL); + if (!xfpu) + goto cleanup; +#endif + + if (cprm->signr) { + struct core_thread *ct; + struct elf_thread_status *tmp; + + for (ct = current->mm->core_state->dumper.next; + ct; ct = ct->next) { + tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + if (!tmp) + goto cleanup; + + tmp->thread = ct->task; + list_add(&tmp->list, &thread_list); + } + + list_for_each(t, &thread_list) { + struct elf_thread_status *tmp; + int sz; + + tmp = list_entry(t, struct elf_thread_status, list); + sz = elf_dump_thread_status(cprm->signr, tmp); + thread_status_size += sz; + } + } + + /* now collect the dump for the current */ + fill_prstatus(prstatus, current, cprm->signr); + elf_core_copy_regs(&prstatus->pr_reg, cprm->regs); + + segs = current->mm->map_count; + segs += elf_core_extra_phdrs(); + + /* for notes section */ + segs++; + + /* If segs > PN_XNUM(0xffff), then e_phnum overflows. To avoid + * this, kernel supports extended numbering. Have a look at + * include/linux/elf.h for further information. */ + e_phnum = segs > PN_XNUM ? PN_XNUM : segs; + + /* Set up header */ + fill_elf_fdpic_header(elf, e_phnum); + + has_dumped = 1; + current->flags |= PF_DUMPCORE; + + /* + * Set up the notes in similar form to SVR4 core dumps made + * with info from their /proc. + */ + + fill_note(notes + 0, "CORE", NT_PRSTATUS, sizeof(*prstatus), prstatus); + fill_psinfo(psinfo, current->group_leader, current->mm); + fill_note(notes + 1, "CORE", NT_PRPSINFO, sizeof(*psinfo), psinfo); + + numnote = 2; + + auxv = (elf_addr_t *) current->mm->saved_auxv; + + i = 0; + do + i += 2; + while (auxv[i - 2] != AT_NULL); + fill_note(¬es[numnote++], "CORE", NT_AUXV, + i * sizeof(elf_addr_t), auxv); + + /* Try to dump the FPU. */ + if ((prstatus->pr_fpvalid = + elf_core_copy_task_fpregs(current, cprm->regs, fpu))) + fill_note(notes + numnote++, + "CORE", NT_PRFPREG, sizeof(*fpu), fpu); +#ifdef ELF_CORE_COPY_XFPREGS + if (elf_core_copy_task_xfpregs(current, xfpu)) + fill_note(notes + numnote++, + "LINUX", ELF_CORE_XFPREG_TYPE, sizeof(*xfpu), xfpu); +#endif + + fs = get_fs(); + set_fs(KERNEL_DS); + + offset += sizeof(*elf); /* Elf header */ + offset += segs * sizeof(struct elf_phdr); /* Program headers */ + foffset = offset; + + /* Write notes phdr entry */ + { + int sz = 0; + + for (i = 0; i < numnote; i++) + sz += notesize(notes + i); + + sz += thread_status_size; + + phdr4note = kmalloc(sizeof(*phdr4note), GFP_KERNEL); + if (!phdr4note) + goto end_coredump; + + fill_elf_note_phdr(phdr4note, sz, offset); + offset += sz; + } + + /* Page-align dumped data */ + dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE); + + offset += elf_core_vma_data_size(cprm->mm_flags); + offset += elf_core_extra_data_size(); + e_shoff = offset; + + if (e_phnum == PN_XNUM) { + shdr4extnum = kmalloc(sizeof(*shdr4extnum), GFP_KERNEL); + if (!shdr4extnum) + goto end_coredump; + fill_extnum_info(elf, shdr4extnum, e_shoff, segs); + } + + offset = dataoff; + + size += sizeof(*elf); + if (size > cprm->limit || !dump_write(cprm->file, elf, sizeof(*elf))) + goto end_coredump; + + size += sizeof(*phdr4note); + if (size > cprm->limit + || !dump_write(cprm->file, phdr4note, sizeof(*phdr4note))) + goto end_coredump; + + /* write program headers for segments dump */ + for (vma = current->mm->mmap; vma; vma = vma->vm_next) { + struct elf_phdr phdr; + size_t sz; + + sz = vma->vm_end - vma->vm_start; + + phdr.p_type = PT_LOAD; + phdr.p_offset = offset; + phdr.p_vaddr = vma->vm_start; + phdr.p_paddr = 0; + phdr.p_filesz = maydump(vma, cprm->mm_flags) ? sz : 0; + phdr.p_memsz = sz; + offset += phdr.p_filesz; + phdr.p_flags = vma->vm_flags & VM_READ ? PF_R : 0; + if (vma->vm_flags & VM_WRITE) + phdr.p_flags |= PF_W; + if (vma->vm_flags & VM_EXEC) + phdr.p_flags |= PF_X; + phdr.p_align = ELF_EXEC_PAGESIZE; + + size += sizeof(phdr); + if (size > cprm->limit + || !dump_write(cprm->file, &phdr, sizeof(phdr))) + goto end_coredump; + } + + if (!elf_core_write_extra_phdrs(cprm->file, offset, &size, cprm->limit)) + goto end_coredump; + + /* write out the notes section */ + for (i = 0; i < numnote; i++) + if (!writenote(notes + i, cprm->file, &foffset)) + goto end_coredump; + + /* write out the thread status notes section */ + list_for_each(t, &thread_list) { + struct elf_thread_status *tmp = + list_entry(t, struct elf_thread_status, list); + + for (i = 0; i < tmp->num_notes; i++) + if (!writenote(&tmp->notes[i], cprm->file, &foffset)) + goto end_coredump; + } + + if (!dump_seek(cprm->file, dataoff - foffset)) + goto end_coredump; + + if (elf_fdpic_dump_segments(cprm->file, &size, &cprm->limit, + cprm->mm_flags) < 0) + goto end_coredump; + + if (!elf_core_write_extra_data(cprm->file, &size, cprm->limit)) + goto end_coredump; + + if (e_phnum == PN_XNUM) { + size += sizeof(*shdr4extnum); + if (size > cprm->limit + || !dump_write(cprm->file, shdr4extnum, + sizeof(*shdr4extnum))) + goto end_coredump; + } + + if (cprm->file->f_pos != offset) { + /* Sanity check */ + printk(KERN_WARNING + "elf_core_dump: file->f_pos (%lld) != offset (%lld)\n", + cprm->file->f_pos, offset); + } + +end_coredump: + set_fs(fs); + +cleanup: + while (!list_empty(&thread_list)) { + struct list_head *tmp = thread_list.next; + list_del(tmp); + kfree(list_entry(tmp, struct elf_thread_status, list)); + } + kfree(phdr4note); + kfree(elf); + kfree(prstatus); + kfree(psinfo); + kfree(notes); + kfree(fpu); +#ifdef ELF_CORE_COPY_XFPREGS + kfree(xfpu); +#endif + return has_dumped; +#undef NUM_NOTES +} + +#endif /* CONFIG_ELF_CORE */