linux_dsm_epyc7002/fs/binfmt_aout.c

344 lines
8.3 KiB
C
Raw Normal View History

/*
* linux/fs/binfmt_aout.c
*
* Copyright (C) 1991, 1992, 1996 Linus Torvalds
*/
#include <linux/module.h>
#include <linux/time.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/a.out.h>
#include <linux/errno.h>
#include <linux/signal.h>
#include <linux/string.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/ptrace.h>
#include <linux/user.h>
#include <linux/binfmts.h>
#include <linux/personality.h>
#include <linux/init.h>
#include <linux/coredump.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/sched/task_stack.h>
#include <linux/uaccess.h>
#include <asm/cacheflush.h>
static int load_aout_binary(struct linux_binprm *);
static int load_aout_library(struct file*);
static struct linux_binfmt aout_format = {
.module = THIS_MODULE,
.load_binary = load_aout_binary,
.load_shlib = load_aout_library,
};
#define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE)
static int set_brk(unsigned long start, unsigned long end)
{
start = PAGE_ALIGN(start);
end = PAGE_ALIGN(end);
if (end > start)
return vm_brk(start, end - start);
return 0;
}
/*
* create_aout_tables() parses the env- and arg-strings in new user
* memory and creates the pointer tables from them, and puts their
* addresses on the "stack", returning the new stack pointer value.
*/
static unsigned long __user *create_aout_tables(char __user *p, struct linux_binprm * bprm)
{
char __user * __user *argv;
char __user * __user *envp;
unsigned long __user *sp;
int argc = bprm->argc;
int envc = bprm->envc;
sp = (void __user *)((-(unsigned long)sizeof(char *)) & (unsigned long) p);
#ifdef __alpha__
/* whee.. test-programs are so much fun. */
put_user(0, --sp);
put_user(0, --sp);
if (bprm->loader) {
put_user(0, --sp);
put_user(1003, --sp);
put_user(bprm->loader, --sp);
put_user(1002, --sp);
}
put_user(bprm->exec, --sp);
put_user(1001, --sp);
#endif
sp -= envc+1;
envp = (char __user * __user *) sp;
sp -= argc+1;
argv = (char __user * __user *) sp;
#ifndef __alpha__
put_user((unsigned long) envp,--sp);
put_user((unsigned long) argv,--sp);
#endif
put_user(argc,--sp);
current->mm->arg_start = (unsigned long) p;
while (argc-->0) {
char c;
put_user(p,argv++);
do {
get_user(c,p++);
} while (c);
}
put_user(NULL,argv);
current->mm->arg_end = current->mm->env_start = (unsigned long) p;
while (envc-->0) {
char c;
put_user(p,envp++);
do {
get_user(c,p++);
} while (c);
}
put_user(NULL,envp);
current->mm->env_end = (unsigned long) p;
return sp;
}
/*
* These are the functions used to load a.out style executables and shared
* libraries. There is no binary dependent code anywhere else.
*/
static int load_aout_binary(struct linux_binprm * bprm)
{
struct pt_regs *regs = current_pt_regs();
struct exec ex;
unsigned long error;
unsigned long fd_offset;
unsigned long rlim;
int retval;
ex = *((struct exec *) bprm->buf); /* exec-header */
if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != OMAGIC &&
N_MAGIC(ex) != QMAGIC && N_MAGIC(ex) != NMAGIC) ||
N_TRSIZE(ex) || N_DRSIZE(ex) ||
i_size_read(file_inode(bprm->file)) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
return -ENOEXEC;
}
/*
* Requires a mmap handler. This prevents people from using a.out
* as part of an exploit attack against /proc-related vulnerabilities.
*/
if (!bprm->file->f_op->mmap)
return -ENOEXEC;
fd_offset = N_TXTOFF(ex);
/* Check initial limits. This avoids letting people circumvent
* size limits imposed on them by creating programs with large
* arrays in the data or bss.
*/
rlim = rlimit(RLIMIT_DATA);
if (rlim >= RLIM_INFINITY)
rlim = ~0;
if (ex.a_data + ex.a_bss > rlim)
return -ENOMEM;
/* Flush all traces of the currently running executable */
retval = flush_old_exec(bprm);
if (retval)
return retval;
/* OK, This is the point of no return */
#ifdef __alpha__
SET_AOUT_PERSONALITY(bprm, ex);
#else
set_personality(PER_LINUX);
#endif
setup_new_exec(bprm);
current->mm->end_code = ex.a_text +
(current->mm->start_code = N_TXTADDR(ex));
current->mm->end_data = ex.a_data +
(current->mm->start_data = N_DATADDR(ex));
current->mm->brk = ex.a_bss +
(current->mm->start_brk = N_BSSADDR(ex));
retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT);
if (retval < 0)
return retval;
CRED: Make execve() take advantage of copy-on-write credentials Make execve() take advantage of copy-on-write credentials, allowing it to set up the credentials in advance, and then commit the whole lot after the point of no return. This patch and the preceding patches have been tested with the LTP SELinux testsuite. This patch makes several logical sets of alteration: (1) execve(). The credential bits from struct linux_binprm are, for the most part, replaced with a single credentials pointer (bprm->cred). This means that all the creds can be calculated in advance and then applied at the point of no return with no possibility of failure. I would like to replace bprm->cap_effective with: cap_isclear(bprm->cap_effective) but this seems impossible due to special behaviour for processes of pid 1 (they always retain their parent's capability masks where normally they'd be changed - see cap_bprm_set_creds()). The following sequence of events now happens: (a) At the start of do_execve, the current task's cred_exec_mutex is locked to prevent PTRACE_ATTACH from obsoleting the calculation of creds that we make. (a) prepare_exec_creds() is then called to make a copy of the current task's credentials and prepare it. This copy is then assigned to bprm->cred. This renders security_bprm_alloc() and security_bprm_free() unnecessary, and so they've been removed. (b) The determination of unsafe execution is now performed immediately after (a) rather than later on in the code. The result is stored in bprm->unsafe for future reference. (c) prepare_binprm() is called, possibly multiple times. (i) This applies the result of set[ug]id binaries to the new creds attached to bprm->cred. Personality bit clearance is recorded, but now deferred on the basis that the exec procedure may yet fail. (ii) This then calls the new security_bprm_set_creds(). This should calculate the new LSM and capability credentials into *bprm->cred. This folds together security_bprm_set() and parts of security_bprm_apply_creds() (these two have been removed). Anything that might fail must be done at this point. (iii) bprm->cred_prepared is set to 1. bprm->cred_prepared is 0 on the first pass of the security calculations, and 1 on all subsequent passes. This allows SELinux in (ii) to base its calculations only on the initial script and not on the interpreter. (d) flush_old_exec() is called to commit the task to execution. This performs the following steps with regard to credentials: (i) Clear pdeath_signal and set dumpable on certain circumstances that may not be covered by commit_creds(). (ii) Clear any bits in current->personality that were deferred from (c.i). (e) install_exec_creds() [compute_creds() as was] is called to install the new credentials. This performs the following steps with regard to credentials: (i) Calls security_bprm_committing_creds() to apply any security requirements, such as flushing unauthorised files in SELinux, that must be done before the credentials are changed. This is made up of bits of security_bprm_apply_creds() and security_bprm_post_apply_creds(), both of which have been removed. This function is not allowed to fail; anything that might fail must have been done in (c.ii). (ii) Calls commit_creds() to apply the new credentials in a single assignment (more or less). Possibly pdeath_signal and dumpable should be part of struct creds. (iii) Unlocks the task's cred_replace_mutex, thus allowing PTRACE_ATTACH to take place. (iv) Clears The bprm->cred pointer as the credentials it was holding are now immutable. (v) Calls security_bprm_committed_creds() to apply any security alterations that must be done after the creds have been changed. SELinux uses this to flush signals and signal handlers. (f) If an error occurs before (d.i), bprm_free() will call abort_creds() to destroy the proposed new credentials and will then unlock cred_replace_mutex. No changes to the credentials will have been made. (2) LSM interface. A number of functions have been changed, added or removed: (*) security_bprm_alloc(), ->bprm_alloc_security() (*) security_bprm_free(), ->bprm_free_security() Removed in favour of preparing new credentials and modifying those. (*) security_bprm_apply_creds(), ->bprm_apply_creds() (*) security_bprm_post_apply_creds(), ->bprm_post_apply_creds() Removed; split between security_bprm_set_creds(), security_bprm_committing_creds() and security_bprm_committed_creds(). (*) security_bprm_set(), ->bprm_set_security() Removed; folded into security_bprm_set_creds(). (*) security_bprm_set_creds(), ->bprm_set_creds() New. The new credentials in bprm->creds should be checked and set up as appropriate. bprm->cred_prepared is 0 on the first call, 1 on the second and subsequent calls. (*) security_bprm_committing_creds(), ->bprm_committing_creds() (*) security_bprm_committed_creds(), ->bprm_committed_creds() New. Apply the security effects of the new credentials. This includes closing unauthorised files in SELinux. This function may not fail. When the former is called, the creds haven't yet been applied to the process; when the latter is called, they have. The former may access bprm->cred, the latter may not. (3) SELinux. SELinux has a number of changes, in addition to those to support the LSM interface changes mentioned above: (a) The bprm_security_struct struct has been removed in favour of using the credentials-under-construction approach. (c) flush_unauthorized_files() now takes a cred pointer and passes it on to inode_has_perm(), file_has_perm() and dentry_open(). Signed-off-by: David Howells <dhowells@redhat.com> Acked-by: James Morris <jmorris@namei.org> Acked-by: Serge Hallyn <serue@us.ibm.com> Signed-off-by: James Morris <jmorris@namei.org>
2008-11-14 06:39:24 +07:00
install_exec_creds(bprm);
if (N_MAGIC(ex) == OMAGIC) {
unsigned long text_addr, map_size;
loff_t pos;
text_addr = N_TXTADDR(ex);
#ifdef __alpha__
pos = fd_offset;
map_size = ex.a_text+ex.a_data + PAGE_SIZE - 1;
#else
pos = 32;
map_size = ex.a_text+ex.a_data;
#endif
error = vm_brk(text_addr & PAGE_MASK, map_size);
if (error)
return error;
error = read_code(bprm->file, text_addr, pos,
ex.a_text+ex.a_data);
if ((signed long)error < 0)
return error;
} else {
if ((ex.a_text & 0xfff || ex.a_data & 0xfff) &&
(N_MAGIC(ex) != NMAGIC) && printk_ratelimit())
{
printk(KERN_NOTICE "executable not page aligned\n");
}
if ((fd_offset & ~PAGE_MASK) != 0 && printk_ratelimit())
{
printk(KERN_WARNING
"fd_offset is not page aligned. Please convert program: %pD\n",
bprm->file);
}
if (!bprm->file->f_op->mmap||((fd_offset & ~PAGE_MASK) != 0)) {
error = vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
if (error)
return error;
read_code(bprm->file, N_TXTADDR(ex), fd_offset,
ex.a_text + ex.a_data);
goto beyond_if;
}
error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
PROT_READ | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE,
fd_offset);
if (error != N_TXTADDR(ex))
return error;
error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
PROT_READ | PROT_WRITE | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE,
fd_offset + ex.a_text);
if (error != N_DATADDR(ex))
return error;
}
beyond_if:
set_binfmt(&aout_format);
retval = set_brk(current->mm->start_brk, current->mm->brk);
if (retval < 0)
return retval;
current->mm->start_stack =
(unsigned long) create_aout_tables((char __user *) bprm->p, bprm);
#ifdef __alpha__
regs->gp = ex.a_gpvalue;
#endif
finalize_exec(bprm);
start_thread(regs, ex.a_entry, current->mm->start_stack);
return 0;
}
static int load_aout_library(struct file *file)
{
struct inode * inode;
unsigned long bss, start_addr, len;
unsigned long error;
int retval;
struct exec ex;
loff_t pos = 0;
inode = file_inode(file);
retval = -ENOEXEC;
error = kernel_read(file, &ex, sizeof(ex), &pos);
if (error != sizeof(ex))
goto out;
/* We come in here for the regular a.out style of shared libraries */
if ((N_MAGIC(ex) != ZMAGIC && N_MAGIC(ex) != QMAGIC) || N_TRSIZE(ex) ||
N_DRSIZE(ex) || ((ex.a_entry & 0xfff) && N_MAGIC(ex) == ZMAGIC) ||
i_size_read(inode) < ex.a_text+ex.a_data+N_SYMSIZE(ex)+N_TXTOFF(ex)) {
goto out;
}
/*
* Requires a mmap handler. This prevents people from using a.out
* as part of an exploit attack against /proc-related vulnerabilities.
*/
if (!file->f_op->mmap)
goto out;
if (N_FLAGS(ex))
goto out;
/* For QMAGIC, the starting address is 0x20 into the page. We mask
this off to get the starting address for the page */
start_addr = ex.a_entry & 0xfffff000;
if ((N_TXTOFF(ex) & ~PAGE_MASK) != 0) {
if (printk_ratelimit())
{
printk(KERN_WARNING
"N_TXTOFF is not page aligned. Please convert library: %pD\n",
file);
}
retval = vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
if (retval)
goto out;
read_code(file, start_addr, N_TXTOFF(ex),
ex.a_text + ex.a_data);
retval = 0;
goto out;
}
/* Now use mmap to map the library into memory. */
error = vm_mmap(file, start_addr, ex.a_text + ex.a_data,
PROT_READ | PROT_WRITE | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
N_TXTOFF(ex));
retval = error;
if (error != start_addr)
goto out;
len = PAGE_ALIGN(ex.a_text + ex.a_data);
bss = ex.a_text + ex.a_data + ex.a_bss;
if (bss > len) {
retval = vm_brk(start_addr + len, bss - len);
if (retval)
goto out;
}
retval = 0;
out:
return retval;
}
static int __init init_aout_binfmt(void)
{
register_binfmt(&aout_format);
return 0;
}
static void __exit exit_aout_binfmt(void)
{
unregister_binfmt(&aout_format);
}
core_initcall(init_aout_binfmt);
module_exit(exit_aout_binfmt);
MODULE_LICENSE("GPL");