adulau/aha
1
0
Fork 0
mirror of https://github.com/adulau/aha.git synced 2024-12-28 03:36:19 +00:00
Code Issues Projects Releases Packages Wiki Activity
aha/fs/binfmt_elf.c
Frank Mayhar f06febc96b timers: fix itimer/many thread hang 
Overview

This patch reworks the handling of POSIX CPU timers, including the
ITIMER_PROF, ITIMER_VIRT timers and rlimit handling.  It was put together
with the help of Roland McGrath, the owner and original writer of this code.

The problem we ran into, and the reason for this rework, has to do with using
a profiling timer in a process with a large number of threads.  It appears
that the performance of the old implementation of run_posix_cpu_timers() was
at least O(n*3) (where "n" is the number of threads in a process) or worse.
Everything is fine with an increasing number of threads until the time taken
for that routine to run becomes the same as or greater than the tick time, at
which point things degrade rather quickly.

This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF."

Code Changes

This rework corrects the implementation of run_posix_cpu_timers() to make it
run in constant time for a particular machine.  (Performance may vary between
one machine and another depending upon whether the kernel is built as single-
or multiprocessor and, in the latter case, depending upon the number of
running processors.)  To do this, at each tick we now update fields in
signal_struct as well as task_struct.  The run_posix_cpu_timers() function
uses those fields to make its decisions.

We define a new structure, "task_cputime," to contain user, system and
scheduler times and use these in appropriate places:

struct task_cputime {
	cputime_t utime;
	cputime_t stime;
	unsigned long long sum_exec_runtime;
};

This is included in the structure "thread_group_cputime," which is a new
substructure of signal_struct and which varies for uniprocessor versus
multiprocessor kernels.  For uniprocessor kernels, it uses "task_cputime" as
a simple substructure, while for multiprocessor kernels it is a pointer:

struct thread_group_cputime {
	struct task_cputime totals;
};

struct thread_group_cputime {
	struct task_cputime *totals;
};

We also add a new task_cputime substructure directly to signal_struct, to
cache the earliest expiration of process-wide timers, and task_cputime also
replaces the it_*_expires fields of task_struct (used for earliest expiration
of thread timers).  The "thread_group_cputime" structure contains process-wide
timers that are updated via account_user_time() and friends.  In the non-SMP
case the structure is a simple aggregator; unfortunately in the SMP case that
simplicity was not achievable due to cache-line contention between CPUs (in
one measured case performance was actually _worse_ on a 16-cpu system than
the same test on a 4-cpu system, due to this contention).  For SMP, the
thread_group_cputime counters are maintained as a per-cpu structure allocated
using alloc_percpu().  The timer functions update only the timer field in
the structure corresponding to the running CPU, obtained using per_cpu_ptr().

We define a set of inline functions in sched.h that we use to maintain the
thread_group_cputime structure and hide the differences between UP and SMP
implementations from the rest of the kernel.  The thread_group_cputime_init()
function initializes the thread_group_cputime structure for the given task.
The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the
out-of-line function thread_group_cputime_alloc_smp() to allocate and fill
in the per-cpu structures and fields.  The thread_group_cputime_free()
function, also a no-op for UP, in SMP frees the per-cpu structures.  The
thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls
thread_group_cputime_alloc() if the per-cpu structures haven't yet been
allocated.  The thread_group_cputime() function fills the task_cputime
structure it is passed with the contents of the thread_group_cputime fields;
in UP it's that simple but in SMP it must also safely check that tsk->signal
is non-NULL (if it is it just uses the appropriate fields of task_struct) and,
if so, sums the per-cpu values for each online CPU.  Finally, the three
functions account_group_user_time(), account_group_system_time() and
account_group_exec_runtime() are used by timer functions to update the
respective fields of the thread_group_cputime structure.

Non-SMP operation is trivial and will not be mentioned further.

The per-cpu structure is always allocated when a task creates its first new
thread, via a call to thread_group_cputime_clone_thread() from copy_signal().
It is freed at process exit via a call to thread_group_cputime_free() from
cleanup_signal().

All functions that formerly summed utime/stime/sum_sched_runtime values from
from all threads in the thread group now use thread_group_cputime() to
snapshot the values in the thread_group_cputime structure or the values in
the task structure itself if the per-cpu structure hasn't been allocated.

Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit.
The run_posix_cpu_timers() function has been split into a fast path and a
slow path; the former safely checks whether there are any expired thread
timers and, if not, just returns, while the slow path does the heavy lifting.
With the dedicated thread group fields, timers are no longer "rebalanced" and
the process_timer_rebalance() function and related code has gone away.  All
summing loops are gone and all code that used them now uses the
thread_group_cputime() inline.  When process-wide timers are set, the new
task_cputime structure in signal_struct is used to cache the earliest
expiration; this is checked in the fast path.

Performance

The fix appears not to add significant overhead to existing operations.  It
generally performs the same as the current code except in two cases, one in
which it performs slightly worse (Case 5 below) and one in which it performs
very significantly better (Case 2 below).  Overall it's a wash except in those
two cases.

I've since done somewhat more involved testing on a dual-core Opteron system.

Case 1: With no itimer running, for a test with 100,000 threads, the fixed
	kernel took 1428.5 seconds, 513 seconds more than the unfixed system,
	all of which was spent in the system.  There were twice as many
	voluntary context switches with the fix as without it.

Case 2: With an itimer running at .01 second ticks and 4000 threads (the most
	an unmodified kernel can handle), the fixed kernel ran the test in
	eight percent of the time (5.8 seconds as opposed to 70 seconds) and
	had better tick accuracy (.012 seconds per tick as opposed to .023
	seconds per tick).

Case 3: A 4000-thread test with an initial timer tick of .01 second and an
	interval of 10,000 seconds (i.e. a timer that ticks only once) had
	very nearly the same performance in both cases:  6.3 seconds elapsed
	for the fixed kernel versus 5.5 seconds for the unfixed kernel.

With fewer threads (eight in these tests), the Case 1 test ran in essentially
the same time on both the modified and unmodified kernels (5.2 seconds versus
5.8 seconds).  The Case 2 test ran in about the same time as well, 5.9 seconds
versus 5.4 seconds but again with much better tick accuracy, .013 seconds per
tick versus .025 seconds per tick for the unmodified kernel.

Since the fix affected the rlimit code, I also tested soft and hard CPU limits.

Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer
	running), the modified kernel was very slightly favored in that while
	it killed the process in 19.997 seconds of CPU time (5.002 seconds of
	wall time), only .003 seconds of that was system time, the rest was
	user time.  The unmodified kernel killed the process in 20.001 seconds
	of CPU (5.014 seconds of wall time) of which .016 seconds was system
	time.  Really, though, the results were too close to call.  The results
	were essentially the same with no itimer running.

Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds
	(where the hard limit would never be reached) and an itimer running,
	the modified kernel exhibited worse tick accuracy than the unmodified
	kernel: .050 seconds/tick versus .028 seconds/tick.  Otherwise,
	performance was almost indistinguishable.  With no itimer running this
	test exhibited virtually identical behavior and times in both cases.

In times past I did some limited performance testing.  those results are below.

On a four-cpu Opteron system without this fix, a sixteen-thread test executed
in 3569.991 seconds, of which user was 3568.435s and system was 1.556s.  On
the same system with the fix, user and elapsed time were about the same, but
system time dropped to 0.007 seconds.  Performance with eight, four and one
thread were comparable.  Interestingly, the timer ticks with the fix seemed
more accurate:  The sixteen-thread test with the fix received 149543 ticks
for 0.024 seconds per tick, while the same test without the fix received 58720
for 0.061 seconds per tick.  Both cases were configured for an interval of
0.01 seconds.  Again, the other tests were comparable.  Each thread in this
test computed the primes up to 25,000,000.

I also did a test with a large number of threads, 100,000 threads, which is
impossible without the fix.  In this case each thread computed the primes only
up to 10,000 (to make the runtime manageable).  System time dominated, at
1546.968 seconds out of a total 2176.906 seconds (giving a user time of
629.938s).  It received 147651 ticks for 0.015 seconds per tick, still quite
accurate.  There is obviously no comparable test without the fix.

Signed-off-by: Frank Mayhar <fmayhar@google.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-14 16:25:35 +02:00

2066 lines
53 KiB
C
Raw Blame History

/*
* linux/fs/binfmt_elf.c
*
* These are the functions used to load ELF format executables as used
* on SVr4 machines. Information on the format may be found in the book
* "UNIX SYSTEM V RELEASE 4 Programmers Guide: Ansi C and Programming Support
* Tools".
*
* Copyright 1993, 1994: Eric Youngdale (ericy@cais.com).
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/stat.h>
#include <linux/time.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/errno.h>
#include <linux/signal.h>
#include <linux/binfmts.h>
#include <linux/string.h>
#include <linux/file.h>
#include <linux/fcntl.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/shm.h>
#include <linux/personality.h>
#include <linux/elfcore.h>
#include <linux/init.h>
#include <linux/highuid.h>
#include <linux/smp.h>
#include <linux/compiler.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/security.h>
#include <linux/syscalls.h>
#include <linux/random.h>
#include <linux/elf.h>
#include <linux/utsname.h>
#include <asm/uaccess.h>
#include <asm/param.h>
#include <asm/page.h>
static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs);
static int load_elf_library(struct file *);
static unsigned long elf_map(struct file *, unsigned long, struct elf_phdr *,
int, int, unsigned long);
/*
* If we don't support core dumping, then supply a NULL so we
* don't even try.
*/
#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, unsigned long limit);
#else
#define elf_core_dump NULL
#endif
#if ELF_EXEC_PAGESIZE > PAGE_SIZE
#define ELF_MIN_ALIGN ELF_EXEC_PAGESIZE
#else
#define ELF_MIN_ALIGN PAGE_SIZE
#endif
#ifndef ELF_CORE_EFLAGS
#define ELF_CORE_EFLAGS 0
#endif
#define ELF_PAGESTART(_v) ((_v) & ~(unsigned long)(ELF_MIN_ALIGN-1))
#define ELF_PAGEOFFSET(_v) ((_v) & (ELF_MIN_ALIGN-1))
#define ELF_PAGEALIGN(_v) (((_v) + ELF_MIN_ALIGN - 1) & ~(ELF_MIN_ALIGN - 1))
static struct linux_binfmt elf_format = {
.module = THIS_MODULE,
.load_binary = load_elf_binary,
.load_shlib = load_elf_library,
.core_dump = elf_core_dump,
.min_coredump = ELF_EXEC_PAGESIZE,
.hasvdso = 1
};
#define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE)
static int set_brk(unsigned long start, unsigned long end)
{
start = ELF_PAGEALIGN(start);
end = ELF_PAGEALIGN(end);
if (end > start) {
unsigned long addr;
down_write(&current->mm->mmap_sem);
addr = do_brk(start, end - start);
up_write(&current->mm->mmap_sem);
if (BAD_ADDR(addr))
return addr;
}
current->mm->start_brk = current->mm->brk = end;
return 0;
}
/* We need to explicitly zero any fractional pages
after the data section (i.e. bss). This would
contain the junk from the file that should not
be in memory
*/
static int padzero(unsigned long elf_bss)
{
unsigned long nbyte;
nbyte = ELF_PAGEOFFSET(elf_bss);
if (nbyte) {
nbyte = ELF_MIN_ALIGN - nbyte;
if (clear_user((void __user *) elf_bss, nbyte))
return -EFAULT;
}
return 0;
}
/* Let's use some macros to make this stack manipulation a little clearer */
#ifdef CONFIG_STACK_GROWSUP
#define STACK_ADD(sp, items) ((elf_addr_t __user *)(sp) + (items))
#define STACK_ROUND(sp, items) \
((15 + (unsigned long) ((sp) + (items))) &~ 15UL)
#define STACK_ALLOC(sp, len) ({ \
elf_addr_t __user *old_sp = (elf_addr_t __user *)sp; sp += len; \
old_sp; })
#else
#define STACK_ADD(sp, items) ((elf_addr_t __user *)(sp) - (items))
#define STACK_ROUND(sp, items) \
(((unsigned long) (sp - items)) &~ 15UL)
#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)
{
unsigned long p = bprm->p;
int argc = bprm->argc;
int envc = bprm->envc;
elf_addr_t __user *argv;
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;
struct task_struct *tsk = current;
struct vm_area_struct *vma;
/*
* 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.
*/
p = arch_align_stack(p);
/*
* 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.
*/
u_platform = NULL;
if (k_platform) {
size_t len = strlen(k_platform) + 1;
u_platform = (elf_addr_t __user *)STACK_ALLOC(p, len);
if (__copy_to_user(u_platform, k_platform, len))
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 */
#define NEW_AUX_ENT(id, val) \
do { \
elf_info[ei_index++] = id; \
elf_info[ei_index++] = val; \
} while (0)
#ifdef ARCH_DLINFO
/*
* ARCH_DLINFO must come first so PPC can do its special alignment of
* AUXV.
* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT() in
* ARCH_DLINFO changes
*/
ARCH_DLINFO;
#endif
NEW_AUX_ENT(AT_HWCAP, ELF_HWCAP);
NEW_AUX_ENT(AT_PAGESZ, ELF_EXEC_PAGESIZE);
NEW_AUX_ENT(AT_CLKTCK, CLOCKS_PER_SEC);
NEW_AUX_ENT(AT_PHDR, load_addr + exec->e_phoff);
NEW_AUX_ENT(AT_PHENT, sizeof(struct elf_phdr));
NEW_AUX_ENT(AT_PHNUM, exec->e_phnum);
NEW_AUX_ENT(AT_BASE, interp_load_addr);
NEW_AUX_ENT(AT_FLAGS, 0);
NEW_AUX_ENT(AT_ENTRY, exec->e_entry);
NEW_AUX_ENT(AT_UID, tsk->uid);
NEW_AUX_ENT(AT_EUID, tsk->euid);
NEW_AUX_ENT(AT_GID, tsk->gid);
NEW_AUX_ENT(AT_EGID, tsk->egid);
NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm));
NEW_AUX_ENT(AT_EXECFN, bprm->exec);
if (k_platform) {
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);
}
#undef NEW_AUX_ENT
/* AT_NULL is zero; clear the rest too */
memset(&elf_info[ei_index], 0,
sizeof current->mm->saved_auxv - ei_index * sizeof elf_info[0]);
/* And advance past the AT_NULL entry. */
ei_index += 2;
sp = STACK_ADD(p, ei_index);
items = (argc + 1) + (envc + 1) + 1;
bprm->p = STACK_ROUND(sp, items);
/* Point sp at the lowest address on the stack */
#ifdef CONFIG_STACK_GROWSUP
sp = (elf_addr_t __user *)bprm->p - items - ei_index;
bprm->exec = (unsigned long)sp; /* XXX: PARISC HACK */
#else
sp = (elf_addr_t __user *)bprm->p;
#endif
/*
* Grow the stack manually; some architectures have a limit on how
* far ahead a user-space access may be in order to grow the stack.
*/
vma = find_extend_vma(current->mm, bprm->p);
if (!vma)
return -EFAULT;
/* Now, let's put argc (and argv, envp if appropriate) on the stack */
if (__put_user(argc, sp++))
return -EFAULT;
argv = sp;
envp = argv + argc + 1;
/* Populate argv and envp */
p = current->mm->arg_end = current->mm->arg_start;
while (argc-- > 0) {
size_t len;
if (__put_user((elf_addr_t)p, argv++))
return -EFAULT;
len = strnlen_user((void __user *)p, MAX_ARG_STRLEN);
if (!len || len > MAX_ARG_STRLEN)
return -EINVAL;
p += len;
}
if (__put_user(0, argv))
return -EFAULT;
current->mm->arg_end = current->mm->env_start = p;
while (envc-- > 0) {
size_t len;
if (__put_user((elf_addr_t)p, envp++))
return -EFAULT;
len = strnlen_user((void __user *)p, MAX_ARG_STRLEN);
if (!len || len > MAX_ARG_STRLEN)
return -EINVAL;
p += len;
}
if (__put_user(0, envp))
return -EFAULT;
current->mm->env_end = p;
/* Put the elf_info on the stack in the right place. */
sp = (elf_addr_t __user *)envp + 1;
if (copy_to_user(sp, elf_info, ei_index * sizeof(elf_addr_t)))
return -EFAULT;
return 0;
}
#ifndef elf_map
static unsigned long elf_map(struct file *filep, unsigned long addr,
struct elf_phdr *eppnt, int prot, int type,
unsigned long total_size)
{
unsigned long map_addr;
unsigned long size = eppnt->p_filesz + ELF_PAGEOFFSET(eppnt->p_vaddr);
unsigned long off = eppnt->p_offset - ELF_PAGEOFFSET(eppnt->p_vaddr);
addr = ELF_PAGESTART(addr);
size = ELF_PAGEALIGN(size);
/* mmap() will return -EINVAL if given a zero size, but a
* segment with zero filesize is perfectly valid */
if (!size)
return addr;
down_write(&current->mm->mmap_sem);
/*
* total_size is the size of the ELF (interpreter) image.
* The _first_ mmap needs to know the full size, otherwise
* randomization might put this image into an overlapping
* position with the ELF binary image. (since size < total_size)
* So we first map the 'big' image - and unmap the remainder at
* the end. (which unmap is needed for ELF images with holes.)
*/
if (total_size) {
total_size = ELF_PAGEALIGN(total_size);
map_addr = do_mmap(filep, addr, total_size, prot, type, off);
if (!BAD_ADDR(map_addr))
do_munmap(current->mm, map_addr+size, total_size-size);
} else
map_addr = do_mmap(filep, addr, size, prot, type, off);
up_write(&current->mm->mmap_sem);
return(map_addr);
}
#endif /* !elf_map */
static unsigned long total_mapping_size(struct elf_phdr *cmds, int nr)
{
int i, first_idx = -1, last_idx = -1;
for (i = 0; i < nr; i++) {
if (cmds[i].p_type == PT_LOAD) {
last_idx = i;
if (first_idx == -1)
first_idx = i;
}
}
if (first_idx == -1)
return 0;
return cmds[last_idx].p_vaddr + cmds[last_idx].p_memsz -
ELF_PAGESTART(cmds[first_idx].p_vaddr);
}
/* This is much more generalized than the library routine read function,
so we keep this separate. Technically the library read function
is only provided so that we can read a.out libraries that have
an ELF header */
static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
struct file *interpreter, unsigned long *interp_map_addr,
unsigned long no_base)
{
struct elf_phdr *elf_phdata;
struct elf_phdr *eppnt;
unsigned long load_addr = 0;
int load_addr_set = 0;
unsigned long last_bss = 0, elf_bss = 0;
unsigned long error = ~0UL;
unsigned long total_size;
int retval, i, size;
/* First of all, some simple consistency checks */
if (interp_elf_ex->e_type != ET_EXEC &&
interp_elf_ex->e_type != ET_DYN)
goto out;
if (!elf_check_arch(interp_elf_ex))
goto out;
if (!interpreter->f_op || !interpreter->f_op->mmap)
goto out;
/*
* If the size of this structure has changed, then punt, since
* we will be doing the wrong thing.
*/
if (interp_elf_ex->e_phentsize != sizeof(struct elf_phdr))
goto out;
if (interp_elf_ex->e_phnum < 1 ||
interp_elf_ex->e_phnum > 65536U / sizeof(struct elf_phdr))
goto out;
/* Now read in all of the header information */
size = sizeof(struct elf_phdr) * interp_elf_ex->e_phnum;
if (size > ELF_MIN_ALIGN)
goto out;
elf_phdata = kmalloc(size, GFP_KERNEL);
if (!elf_phdata)
goto out;
retval = kernel_read(interpreter, interp_elf_ex->e_phoff,
(char *)elf_phdata,size);
error = -EIO;
if (retval != size) {
if (retval < 0)
error = retval;
goto out_close;
}
total_size = total_mapping_size(elf_phdata, interp_elf_ex->e_phnum);
if (!total_size) {
error = -EINVAL;
goto out_close;
}
eppnt = elf_phdata;
for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) {
if (eppnt->p_type == PT_LOAD) {
int elf_type = MAP_PRIVATE | MAP_DENYWRITE;
int elf_prot = 0;
unsigned long vaddr = 0;
unsigned long k, map_addr;
if (eppnt->p_flags & PF_R)
elf_prot = PROT_READ;
if (eppnt->p_flags & PF_W)
elf_prot |= PROT_WRITE;
if (eppnt->p_flags & PF_X)
elf_prot |= PROT_EXEC;
vaddr = eppnt->p_vaddr;
if (interp_elf_ex->e_type == ET_EXEC || load_addr_set)
elf_type |= MAP_FIXED;
else if (no_base && interp_elf_ex->e_type == ET_DYN)
load_addr = -vaddr;
map_addr = elf_map(interpreter, load_addr + vaddr,
eppnt, elf_prot, elf_type, total_size);
total_size = 0;
if (!*interp_map_addr)
*interp_map_addr = map_addr;
error = map_addr;
if (BAD_ADDR(map_addr))
goto out_close;
if (!load_addr_set &&
interp_elf_ex->e_type == ET_DYN) {
load_addr = map_addr - ELF_PAGESTART(vaddr);
load_addr_set = 1;
}
/*
* Check to see if the section's size will overflow the
* allowed task size. Note that p_filesz must always be
* <= p_memsize so it's only necessary to check p_memsz.
*/
k = load_addr + eppnt->p_vaddr;
if (BAD_ADDR(k) ||
eppnt->p_filesz > eppnt->p_memsz ||
eppnt->p_memsz > TASK_SIZE ||
TASK_SIZE - eppnt->p_memsz < k) {
error = -ENOMEM;
goto out_close;
}
/*
* Find the end of the file mapping for this phdr, and
* keep track of the largest address we see for this.
*/
k = load_addr + eppnt->p_vaddr + eppnt->p_filesz;
if (k > elf_bss)
elf_bss = k;
/*
* Do the same thing for the memory mapping - between
* elf_bss and last_bss is the bss section.
*/
k = load_addr + eppnt->p_memsz + eppnt->p_vaddr;
if (k > last_bss)
last_bss = k;
}
}
/*
* Now fill out the bss section. First pad the last page up
* to the page boundary, and then perform a mmap to make sure
* that there are zero-mapped pages up to and including the
* last bss page.
*/
if (padzero(elf_bss)) {
error = -EFAULT;
goto out_close;
}
/* What we have mapped so far */
elf_bss = ELF_PAGESTART(elf_bss + ELF_MIN_ALIGN - 1);
/* Map the last of the bss segment */
if (last_bss > elf_bss) {
down_write(&current->mm->mmap_sem);
error = do_brk(elf_bss, last_bss - elf_bss);
up_write(&current->mm->mmap_sem);
if (BAD_ADDR(error))
goto out_close;
}
error = load_addr;
out_close:
kfree(elf_phdata);
out:
return error;
}
/*
* These are the functions used to load ELF style executables and shared
* libraries. There is no binary dependent code anywhere else.
*/
#define INTERPRETER_NONE 0
#define INTERPRETER_ELF 2
#ifndef STACK_RND_MASK
#define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */
#endif
static unsigned long randomize_stack_top(unsigned long stack_top)
{
unsigned int random_variable = 0;
if ((current->flags & PF_RANDOMIZE) &&
!(current->personality & ADDR_NO_RANDOMIZE)) {
random_variable = get_random_int() & STACK_RND_MASK;
random_variable <<= PAGE_SHIFT;
}
#ifdef CONFIG_STACK_GROWSUP
return PAGE_ALIGN(stack_top) + random_variable;
#else
return PAGE_ALIGN(stack_top) - random_variable;
#endif
}
static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
{
struct file *interpreter = NULL; /* to shut gcc up */
unsigned long load_addr = 0, load_bias = 0;
int load_addr_set = 0;
char * elf_interpreter = NULL;
unsigned long error;
struct elf_phdr *elf_ppnt, *elf_phdata;
unsigned long elf_bss, elf_brk;
int elf_exec_fileno;
int retval, i;
unsigned int size;
unsigned long elf_entry;
unsigned long interp_load_addr = 0;
unsigned long start_code, end_code, start_data, end_data;
unsigned long reloc_func_desc = 0;
int executable_stack = EXSTACK_DEFAULT;
unsigned long def_flags = 0;
struct {
struct elfhdr elf_ex;
struct elfhdr interp_elf_ex;
} *loc;
loc = kmalloc(sizeof(*loc), GFP_KERNEL);
if (!loc) {
retval = -ENOMEM;
goto out_ret;
}
/* Get the exec-header */
loc->elf_ex = *((struct elfhdr *)bprm->buf);
retval = -ENOEXEC;
/* First of all, some simple consistency checks */
if (memcmp(loc->elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
goto out;
if (loc->elf_ex.e_type != ET_EXEC && loc->elf_ex.e_type != ET_DYN)
goto out;
if (!elf_check_arch(&loc->elf_ex))
goto out;
if (!bprm->file->f_op||!bprm->file->f_op->mmap)
goto out;
/* Now read in all of the header information */
if (loc->elf_ex.e_phentsize != sizeof(struct elf_phdr))
goto out;
if (loc->elf_ex.e_phnum < 1 ||
loc->elf_ex.e_phnum > 65536U / sizeof(struct elf_phdr))
goto out;
size = loc->elf_ex.e_phnum * sizeof(struct elf_phdr);
retval = -ENOMEM;
elf_phdata = kmalloc(size, GFP_KERNEL);
if (!elf_phdata)
goto out;
retval = kernel_read(bprm->file, loc->elf_ex.e_phoff,
(char *)elf_phdata, size);
if (retval != size) {
if (retval >= 0)
retval = -EIO;
goto out_free_ph;
}
retval = get_unused_fd();
if (retval < 0)
goto out_free_ph;
get_file(bprm->file);
fd_install(elf_exec_fileno = retval, bprm->file);
elf_ppnt = elf_phdata;
elf_bss = 0;
elf_brk = 0;
start_code = ~0UL;
end_code = 0;
start_data = 0;
end_data = 0;
for (i = 0; i < loc->elf_ex.e_phnum; i++) {
if (elf_ppnt->p_type == PT_INTERP) {
/* This is the program interpreter used for
* shared libraries - for now assume that this
* is an a.out format binary
*/
retval = -ENOEXEC;
if (elf_ppnt->p_filesz > PATH_MAX ||
elf_ppnt->p_filesz < 2)
goto out_free_file;
retval = -ENOMEM;
elf_interpreter = kmalloc(elf_ppnt->p_filesz,
GFP_KERNEL);
if (!elf_interpreter)
goto out_free_file;
retval = kernel_read(bprm->file, elf_ppnt->p_offset,
elf_interpreter,
elf_ppnt->p_filesz);
if (retval != elf_ppnt->p_filesz) {
if (retval >= 0)
retval = -EIO;
goto out_free_interp;
}
/* make sure path is NULL terminated */
retval = -ENOEXEC;
if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0')
goto out_free_interp;
/*
* The early SET_PERSONALITY here is so that the lookup
* for the interpreter happens in the namespace of the
* to-be-execed image. SET_PERSONALITY can select an
* alternate root.
*
* However, SET_PERSONALITY is NOT allowed to switch
* this task into the new images's memory mapping
* policy - that is, TASK_SIZE must still evaluate to
* that which is appropriate to the execing application.
* This is because exit_mmap() needs to have TASK_SIZE
* evaluate to the size of the old image.
*
* So if (say) a 64-bit application is execing a 32-bit
* application it is the architecture's responsibility
* to defer changing the value of TASK_SIZE until the
* switch really is going to happen - do this in
* flush_thread(). - akpm
*/
SET_PERSONALITY(loc->elf_ex, 0);
interpreter = open_exec(elf_interpreter);
retval = PTR_ERR(interpreter);
if (IS_ERR(interpreter))
goto out_free_interp;
/*
* 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 != BINPRM_BUF_SIZE) {
if (retval >= 0)
retval = -EIO;
goto out_free_dentry;
}
/* Get the exec headers */
loc->interp_elf_ex = *((struct elfhdr *)bprm->buf);
break;
}
elf_ppnt++;
}
elf_ppnt = elf_phdata;
for (i = 0; i < loc->elf_ex.e_phnum; i++, elf_ppnt++)
if (elf_ppnt->p_type == PT_GNU_STACK) {
if (elf_ppnt->p_flags & PF_X)
executable_stack = EXSTACK_ENABLE_X;
else
executable_stack = EXSTACK_DISABLE_X;
break;
}
/* Some simple consistency checks for the interpreter */
if (elf_interpreter) {
retval = -ELIBBAD;
/* Not an ELF interpreter */
if (memcmp(loc->interp_elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
goto out_free_dentry;
/* Verify the interpreter has a valid arch */
if (!elf_check_arch(&loc->interp_elf_ex))
goto out_free_dentry;
} else {
/* Executables without an interpreter also need a personality */
SET_PERSONALITY(loc->elf_ex, 0);
}
/* Flush all traces of the currently running executable */
retval = flush_old_exec(bprm);
if (retval)
goto out_free_dentry;
/* OK, This is the point of no return */
current->flags &= ~PF_FORKNOEXEC;
current->mm->def_flags = def_flags;
/* Do this immediately, since STACK_TOP as used in setup_arg_pages
may depend on the personality. */
SET_PERSONALITY(loc->elf_ex, 0);
if (elf_read_implies_exec(loc->elf_ex, executable_stack))
current->personality |= READ_IMPLIES_EXEC;
if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
current->flags |= PF_RANDOMIZE;
arch_pick_mmap_layout(current->mm);
/* Do this so that we can load the interpreter, if need be. We will
change some of these later */
current->mm->free_area_cache = current->mm->mmap_base;
current->mm->cached_hole_size = 0;
retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP),
executable_stack);
if (retval < 0) {
send_sig(SIGKILL, current, 0);
goto out_free_dentry;
}
current->mm->start_stack = bprm->p;
/* Now we do a little grungy work by mmaping the ELF image into
the correct location in memory. */
for(i = 0, elf_ppnt = elf_phdata;
i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
int elf_prot = 0, elf_flags;
unsigned long k, vaddr;
if (elf_ppnt->p_type != PT_LOAD)
continue;
if (unlikely (elf_brk > elf_bss)) {
unsigned long nbyte;
/* There was a PT_LOAD segment with p_memsz > p_filesz
before this one. Map anonymous pages, if needed,
and clear the area. */
retval = set_brk (elf_bss + load_bias,
elf_brk + load_bias);
if (retval) {
send_sig(SIGKILL, current, 0);
goto out_free_dentry;
}
nbyte = ELF_PAGEOFFSET(elf_bss);
if (nbyte) {
nbyte = ELF_MIN_ALIGN - nbyte;
if (nbyte > elf_brk - elf_bss)
nbyte = elf_brk - elf_bss;
if (clear_user((void __user *)elf_bss +
load_bias, nbyte)) {
/*
* This bss-zeroing can fail if the ELF
* file specifies odd protections. So
* we don't check the return value
*/
}
}
}
if (elf_ppnt->p_flags & PF_R)
elf_prot |= PROT_READ;
if (elf_ppnt->p_flags & PF_W)
elf_prot |= PROT_WRITE;
if (elf_ppnt->p_flags & PF_X)
elf_prot |= PROT_EXEC;
elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE;
vaddr = elf_ppnt->p_vaddr;
if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
elf_flags |= MAP_FIXED;
} else if (loc->elf_ex.e_type == ET_DYN) {
/* Try and get dynamic programs out of the way of the
* default mmap base, as well as whatever program they
* might try to exec. This is because the brk will
* follow the loader, and is not movable. */
#ifdef CONFIG_X86
load_bias = 0;
#else
load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
#endif
}
error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt,
elf_prot, elf_flags, 0);
if (BAD_ADDR(error)) {
send_sig(SIGKILL, current, 0);
retval = IS_ERR((void *)error) ?
PTR_ERR((void*)error) : -EINVAL;
goto out_free_dentry;
}
if (!load_addr_set) {
load_addr_set = 1;
load_addr = (elf_ppnt->p_vaddr - elf_ppnt->p_offset);
if (loc->elf_ex.e_type == ET_DYN) {
load_bias += error -
ELF_PAGESTART(load_bias + vaddr);
load_addr += load_bias;
reloc_func_desc = load_bias;
}
}
k = elf_ppnt->p_vaddr;
if (k < start_code)
start_code = k;
if (start_data < k)
start_data = k;
/*
* Check to see if the section's size will overflow the
* allowed task size. Note that p_filesz must always be
* <= p_memsz so it is only necessary to check p_memsz.
*/
if (BAD_ADDR(k) || elf_ppnt->p_filesz > elf_ppnt->p_memsz ||
elf_ppnt->p_memsz > TASK_SIZE ||
TASK_SIZE - elf_ppnt->p_memsz < k) {
/* set_brk can never work. Avoid overflows. */
send_sig(SIGKILL, current, 0);
retval = -EINVAL;
goto out_free_dentry;
}
k = elf_ppnt->p_vaddr + elf_ppnt->p_filesz;
if (k > elf_bss)
elf_bss = k;
if ((elf_ppnt->p_flags & PF_X) && end_code < k)
end_code = k;
if (end_data < k)
end_data = k;
k = elf_ppnt->p_vaddr + elf_ppnt->p_memsz;
if (k > elf_brk)
elf_brk = k;
}
loc->elf_ex.e_entry += load_bias;
elf_bss += load_bias;
elf_brk += load_bias;
start_code += load_bias;
end_code += load_bias;
start_data += load_bias;
end_data += load_bias;
/* Calling set_brk effectively mmaps the pages that we need
* for the bss and break sections. We must do this before
* mapping in the interpreter, to make sure it doesn't wind
* up getting placed where the bss needs to go.
*/
retval = set_brk(elf_bss, elf_brk);
if (retval) {
send_sig(SIGKILL, current, 0);
goto out_free_dentry;
}
if (likely(elf_bss != elf_brk) && unlikely(padzero(elf_bss))) {
send_sig(SIGSEGV, current, 0);
retval = -EFAULT; /* Nobody gets to see this, but.. */
goto out_free_dentry;
}
if (elf_interpreter) {
unsigned long uninitialized_var(interp_map_addr);
elf_entry = load_elf_interp(&loc->interp_elf_ex,
interpreter,
&interp_map_addr,
load_bias);
if (!IS_ERR((void *)elf_entry)) {
/*
* load_elf_interp() returns relocation
* adjustment
*/
interp_load_addr = elf_entry;
elf_entry += loc->interp_elf_ex.e_entry;
}
if (BAD_ADDR(elf_entry)) {
force_sig(SIGSEGV, current);
retval = IS_ERR((void *)elf_entry) ?
(int)elf_entry : -EINVAL;
goto out_free_dentry;
}
reloc_func_desc = interp_load_addr;
allow_write_access(interpreter);
fput(interpreter);
kfree(elf_interpreter);
} else {
elf_entry = loc->elf_ex.e_entry;
if (BAD_ADDR(elf_entry)) {
force_sig(SIGSEGV, current);
retval = -EINVAL;
goto out_free_dentry;
}
}
kfree(elf_phdata);
sys_close(elf_exec_fileno);
set_binfmt(&elf_format);
#ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
retval = arch_setup_additional_pages(bprm, executable_stack);
if (retval < 0) {
send_sig(SIGKILL, current, 0);
goto out;
}
#endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */
compute_creds(bprm);
current->flags &= ~PF_FORKNOEXEC;
retval = create_elf_tables(bprm, &loc->elf_ex,
load_addr, interp_load_addr);
if (retval < 0) {
send_sig(SIGKILL, current, 0);
goto out;
}
/* N.B. passed_fileno might not be initialized? */
current->mm->end_code = end_code;
current->mm->start_code = start_code;
current->mm->start_data = start_data;
current->mm->end_data = end_data;
current->mm->start_stack = bprm->p;
#ifdef arch_randomize_brk
if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1))
current->mm->brk = current->mm->start_brk =
arch_randomize_brk(current->mm);
#endif
if (current->personality & MMAP_PAGE_ZERO) {
/* Why this, you ask??? Well SVr4 maps page 0 as read-only,
and some applications "depend" upon this behavior.
Since we do not have the power to recompile these, we
emulate the SVr4 behavior. Sigh. */
down_write(&current->mm->mmap_sem);
error = do_mmap(NULL, 0, PAGE_SIZE, PROT_READ | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE, 0);
up_write(&current->mm->mmap_sem);
}
#ifdef ELF_PLAT_INIT
/*
* The ABI may specify that certain registers be set up in special
* ways (on i386 %edx is the address of a DT_FINI function, for
* example. In addition, it may also specify (eg, PowerPC64 ELF)
* that the e_entry field is the address of the function descriptor
* for the startup routine, rather than the address of the startup
* routine itself. This macro performs whatever initialization to
* the regs structure is required as well as any relocations to the
* function descriptor entries when executing dynamically links apps.
*/
ELF_PLAT_INIT(regs, reloc_func_desc);
#endif
start_thread(regs, elf_entry, bprm->p);
retval = 0;
out:
kfree(loc);
out_ret:
return retval;
/* error cleanup */
out_free_dentry:
allow_write_access(interpreter);
if (interpreter)
fput(interpreter);
out_free_interp:
kfree(elf_interpreter);
out_free_file:
sys_close(elf_exec_fileno);
out_free_ph:
kfree(elf_phdata);
goto out;
}
/* This is really simpleminded and specialized - we are loading an
a.out library that is given an ELF header. */
static int load_elf_library(struct file *file)
{
struct elf_phdr *elf_phdata;
struct elf_phdr *eppnt;
unsigned long elf_bss, bss, len;
int retval, error, i, j;
struct elfhdr elf_ex;
error = -ENOEXEC;
retval = kernel_read(file, 0, (char *)&elf_ex, sizeof(elf_ex));
if (retval != sizeof(elf_ex))
goto out;
if (memcmp(elf_ex.e_ident, ELFMAG, SELFMAG) != 0)
goto out;
/* First of all, some simple consistency checks */
if (elf_ex.e_type != ET_EXEC || elf_ex.e_phnum > 2 ||
!elf_check_arch(&elf_ex) || !file->f_op || !file->f_op->mmap)
goto out;
/* Now read in all of the header information */
j = sizeof(struct elf_phdr) * elf_ex.e_phnum;
/* j < ELF_MIN_ALIGN because elf_ex.e_phnum <= 2 */
error = -ENOMEM;
elf_phdata = kmalloc(j, GFP_KERNEL);
if (!elf_phdata)
goto out;
eppnt = elf_phdata;
error = -ENOEXEC;
retval = kernel_read(file, elf_ex.e_phoff, (char *)eppnt, j);
if (retval != j)
goto out_free_ph;
for (j = 0, i = 0; i<elf_ex.e_phnum; i++)
if ((eppnt + i)->p_type == PT_LOAD)
j++;
if (j != 1)
goto out_free_ph;
while (eppnt->p_type != PT_LOAD)
eppnt++;
/* Now use mmap to map the library into memory. */
down_write(&current->mm->mmap_sem);
error = do_mmap(file,
ELF_PAGESTART(eppnt->p_vaddr),
(eppnt->p_filesz +
ELF_PAGEOFFSET(eppnt->p_vaddr)),
PROT_READ | PROT_WRITE | PROT_EXEC,
MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE,
(eppnt->p_offset -
ELF_PAGEOFFSET(eppnt->p_vaddr)));
up_write(&current->mm->mmap_sem);
if (error != ELF_PAGESTART(eppnt->p_vaddr))
goto out_free_ph;
elf_bss = eppnt->p_vaddr + eppnt->p_filesz;
if (padzero(elf_bss)) {
error = -EFAULT;
goto out_free_ph;
}
len = ELF_PAGESTART(eppnt->p_filesz + eppnt->p_vaddr +
ELF_MIN_ALIGN - 1);
bss = eppnt->p_memsz + eppnt->p_vaddr;
if (bss > len) {
down_write(&current->mm->mmap_sem);
do_brk(len, bss - len);
up_write(&current->mm->mmap_sem);
}
error = 0;
out_free_ph:
kfree(elf_phdata);
out:
return error;
}
/*
* Note that some platforms still use traditional core dumps and not
* the ELF core dump. Each platform can select it as appropriate.
*/
#if defined(USE_ELF_CORE_DUMP) && defined(CONFIG_ELF_CORE)
/*
* ELF core dumper
*
* Modelled on fs/exec.c:aout_core_dump()
* Jeremy Fitzhardinge <jeremy@sw.oz.au>
*/
/*
* These are the only things you should do on a core-file: use only these
* functions to write out all the necessary info.
*/
static int dump_write(struct file *file, const void *addr, int nr)
{
return file->f_op->write(file, addr, nr, &file->f_pos) == nr;
}
static int dump_seek(struct file *file, loff_t off)
{
if (file->f_op->llseek && file->f_op->llseek != no_llseek) {
if (file->f_op->llseek(file, off, SEEK_CUR) < 0)
return 0;
} else {
char *buf = (char *)get_zeroed_page(GFP_KERNEL);
if (!buf)
return 0;
while (off > 0) {
unsigned long n = off;
if (n > PAGE_SIZE)
n = PAGE_SIZE;
if (!dump_write(file, buf, n))
return 0;
off -= n;
}
free_page((unsigned long)buf);
}
return 1;
}
/*
* Decide what to dump of a segment, part, all or none.
*/
static unsigned long vma_dump_size(struct vm_area_struct *vma,
unsigned long mm_flags)
{
/* The vma can be set up to tell us the answer directly. */
if (vma->vm_flags & VM_ALWAYSDUMP)
goto whole;
/* Do not dump I/O mapped devices or special mappings */
if (vma->vm_flags & (VM_IO | VM_RESERVED))
return 0;
#define FILTER(type) (mm_flags & (1UL << MMF_DUMP_##type))
/* 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 ?
FILTER(ANON_SHARED) : FILTER(MAPPED_SHARED))
goto whole;
return 0;
}
/* Dump segments that have been written to. */
if (vma->anon_vma && FILTER(ANON_PRIVATE))
goto whole;
if (vma->vm_file == NULL)
return 0;
if (FILTER(MAPPED_PRIVATE))
goto whole;
/*
* If this looks like the beginning of a DSO or executable mapping,
* check for an ELF header. If we find one, dump the first page to
* aid in determining what was mapped here.
*/
if (FILTER(ELF_HEADERS) && vma->vm_file != NULL && vma->vm_pgoff == 0) {
u32 __user *header = (u32 __user *) vma->vm_start;
u32 word;
/*
* Doing it this way gets the constant folded by GCC.
*/
union {
u32 cmp;
char elfmag[SELFMAG];
} magic;
BUILD_BUG_ON(SELFMAG != sizeof word);
magic.elfmag[EI_MAG0] = ELFMAG0;
magic.elfmag[EI_MAG1] = ELFMAG1;
magic.elfmag[EI_MAG2] = ELFMAG2;
magic.elfmag[EI_MAG3] = ELFMAG3;
if (get_user(word, header) == 0 && word == magic.cmp)
return PAGE_SIZE;
}
#undef FILTER
return 0;
whole:
return vma->vm_end - vma->vm_start;
}
/* 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 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
#define DUMP_WRITE(addr, nr) \
if ((size += (nr)) > limit || !dump_write(file, (addr), (nr))) \
goto end_coredump;
#define DUMP_SEEK(off) \
if (!dump_seek(file, (off))) \
goto end_coredump;
static void fill_elf_header(struct elfhdr *elf, int segs,
u16 machine, u32 flags, u8 osabi)
{
memset(elf, 0, sizeof(*elf));
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;
elf->e_type = ET_CORE;
elf->e_machine = machine;
elf->e_version = EV_CURRENT;
elf->e_phoff = sizeof(struct elfhdr);
elf->e_flags = flags;
elf->e_ehsize = sizeof(struct elfhdr);
elf->e_phentsize = sizeof(struct elf_phdr);
elf->e_phnum = segs;
return;
}
static 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 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];
prstatus->pr_pid = task_pid_vnr(p);
prstatus->pr_ppid = task_pid_vnr(p->real_parent);
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);
}
static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
struct mm_struct *mm)
{
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;
psinfo->pr_pid = task_pid_vnr(p);
psinfo->pr_ppid = task_pid_vnr(p->real_parent);
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;
SET_UID(psinfo->pr_uid, p->uid);
SET_GID(psinfo->pr_gid, p->gid);
strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname));
return 0;
}
static void fill_auxv_note(struct memelfnote *note, struct mm_struct *mm)
{
elf_addr_t *auxv = (elf_addr_t *) mm->saved_auxv;
int i = 0;
do
i += 2;
while (auxv[i - 2] != AT_NULL);
fill_note(note, "CORE", NT_AUXV, i * sizeof(elf_addr_t), auxv);
}
#ifdef CORE_DUMP_USE_REGSET
#include <linux/regset.h>
struct elf_thread_core_info {
struct elf_thread_core_info *next;
struct task_struct *task;
struct elf_prstatus prstatus;
struct memelfnote notes[0];
};
struct elf_note_info {
struct elf_thread_core_info *thread;
struct memelfnote psinfo;
struct memelfnote auxv;
size_t size;
int thread_notes;
};
/*
* When a regset has a writeback hook, we call it on each thread before
* dumping user memory. On register window machines, this makes sure the
* user memory backing the register data is up to date before we read it.
*/
static void do_thread_regset_writeback(struct task_struct *task,
const struct user_regset *regset)
{
if (regset->writeback)
regset->writeback(task, regset, 1);
}
static int fill_thread_core_info(struct elf_thread_core_info *t,
const struct user_regset_view *view,
long signr, size_t *total)
{
unsigned int i;
/*
* NT_PRSTATUS is the one special case, because the regset data
* goes into the pr_reg field inside the note contents, rather
* than being the whole note contents. We fill the reset in here.
* We assume that regset 0 is NT_PRSTATUS.
*/
fill_prstatus(&t->prstatus, t->task, signr);
(void) view->regsets[0].get(t->task, &view->regsets[0],
0, sizeof(t->prstatus.pr_reg),
&t->prstatus.pr_reg, NULL);
fill_note(&t->notes[0], "CORE", NT_PRSTATUS,
sizeof(t->prstatus), &t->prstatus);
*total += notesize(&t->notes[0]);
do_thread_regset_writeback(t->task, &view->regsets[0]);
/*
* Each other regset might generate a note too. For each regset
* that has no core_note_type or is inactive, we leave t->notes[i]
* all zero and we'll know to skip writing it later.
*/
for (i = 1; i < view->n; ++i) {
const struct user_regset *regset = &view->regsets[i];
do_thread_regset_writeback(t->task, regset);
if (regset->core_note_type &&
(!regset->active || regset->active(t->task, regset))) {
int ret;
size_t size = regset->n * regset->size;
void *data = kmalloc(size, GFP_KERNEL);
if (unlikely(!data))
return 0;
ret = regset->get(t->task, regset,
0, size, data, NULL);
if (unlikely(ret))
kfree(data);
else {
if (regset->core_note_type != NT_PRFPREG)
fill_note(&t->notes[i], "LINUX",
regset->core_note_type,
size, data);
else {
t->prstatus.pr_fpvalid = 1;
fill_note(&t->notes[i], "CORE",
NT_PRFPREG, size, data);
}
*total += notesize(&t->notes[i]);
}
}
}
return 1;
}
static int fill_note_info(struct elfhdr *elf, int phdrs,
struct elf_note_info *info,
long signr, struct pt_regs *regs)
{
struct task_struct *dump_task = current;
const struct user_regset_view *view = task_user_regset_view(dump_task);
struct elf_thread_core_info *t;
struct elf_prpsinfo *psinfo;
struct core_thread *ct;
unsigned int i;
info->size = 0;
info->thread = NULL;
psinfo = kmalloc(sizeof(*psinfo), GFP_KERNEL);
fill_note(&info->psinfo, "CORE", NT_PRPSINFO, sizeof(*psinfo), psinfo);
if (psinfo == NULL)
return 0;
/*
* Figure out how many notes we're going to need for each thread.
*/
info->thread_notes = 0;
for (i = 0; i < view->n; ++i)
if (view->regsets[i].core_note_type != 0)
++info->thread_notes;
/*
* Sanity check. We rely on regset 0 being in NT_PRSTATUS,
* since it is our one special case.
*/
if (unlikely(info->thread_notes == 0) ||
unlikely(view->regsets[0].core_note_type != NT_PRSTATUS)) {
WARN_ON(1);
return 0;
}
/*
* Initialize the ELF file header.
*/
fill_elf_header(elf, phdrs,
view->e_machine, view->e_flags, view->ei_osabi);
/*
* Allocate a structure for each thread.
*/
for (ct = &dump_task->mm->core_state->dumper; ct; ct = ct->next) {
t = kzalloc(offsetof(struct elf_thread_core_info,
notes[info->thread_notes]),
GFP_KERNEL);
if (unlikely(!t))
return 0;
t->task = ct->task;
if (ct->task == dump_task || !info->thread) {
t->next = info->thread;
info->thread = t;
} else {
/*
* Make sure to keep the original task at
* the head of the list.
*/
t->next = info->thread->next;
info->thread->next = t;
}
}
/*
* Now fill in each thread's information.
*/
for (t = info->thread; t != NULL; t = t->next)
if (!fill_thread_core_info(t, view, signr, &info->size))
return 0;
/*
* Fill in the two process-wide notes.
*/
fill_psinfo(psinfo, dump_task->group_leader, dump_task->mm);
info->size += notesize(&info->psinfo);
fill_auxv_note(&info->auxv, current->mm);
info->size += notesize(&info->auxv);
return 1;
}
static size_t get_note_info_size(struct elf_note_info *info)
{
return info->size;
}
/*
* Write all the notes for each thread. When writing the first thread, the
* process-wide notes are interleaved after the first thread-specific note.
*/
static int write_note_info(struct elf_note_info *info,
struct file *file, loff_t *foffset)
{
bool first = 1;
struct elf_thread_core_info *t = info->thread;
do {
int i;
if (!writenote(&t->notes[0], file, foffset))
return 0;
if (first && !writenote(&info->psinfo, file, foffset))
return 0;
if (first && !writenote(&info->auxv, file, foffset))
return 0;
for (i = 1; i < info->thread_notes; ++i)
if (t->notes[i].data &&
!writenote(&t->notes[i], file, foffset))
return 0;
first = 0;
t = t->next;
} while (t);
return 1;
}
static void free_note_info(struct elf_note_info *info)
{
struct elf_thread_core_info *threads = info->thread;
while (threads) {
unsigned int i;
struct elf_thread_core_info *t = threads;
threads = t->next;
WARN_ON(t->notes[0].data && t->notes[0].data != &t->prstatus);
for (i = 1; i < info->thread_notes; ++i)
kfree(t->notes[i].data);
kfree(t);
}
kfree(info->psinfo.data);
}
#else
/* 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 threads 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)
{
int sz = 0;
struct task_struct *p = t->thread;
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]);
if ((t->prstatus.pr_fpvalid = elf_core_copy_task_fpregs(p, NULL,
&t->fpu))) {
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;
}
struct elf_note_info {
struct memelfnote *notes;
struct elf_prstatus *prstatus; /* NT_PRSTATUS */
struct elf_prpsinfo *psinfo; /* NT_PRPSINFO */
struct list_head thread_list;
elf_fpregset_t *fpu;
#ifdef ELF_CORE_COPY_XFPREGS
elf_fpxregset_t *xfpu;
#endif
int thread_status_size;
int numnote;
};
static int fill_note_info(struct elfhdr *elf, int phdrs,
struct elf_note_info *info,
long signr, struct pt_regs *regs)
{
#define NUM_NOTES 6
struct list_head *t;
info->notes = NULL;
info->prstatus = NULL;
info->psinfo = NULL;
info->fpu = NULL;
#ifdef ELF_CORE_COPY_XFPREGS
info->xfpu = NULL;
#endif
INIT_LIST_HEAD(&info->thread_list);
info->notes = kmalloc(NUM_NOTES * sizeof(struct memelfnote),
GFP_KERNEL);
if (!info->notes)
return 0;
info->psinfo = kmalloc(sizeof(*info->psinfo), GFP_KERNEL);
if (!info->psinfo)
return 0;
info->prstatus = kmalloc(sizeof(*info->prstatus), GFP_KERNEL);
if (!info->prstatus)
return 0;
info->fpu = kmalloc(sizeof(*info->fpu), GFP_KERNEL);
if (!info->fpu)
return 0;
#ifdef ELF_CORE_COPY_XFPREGS
info->xfpu = kmalloc(sizeof(*info->xfpu), GFP_KERNEL);
if (!info->xfpu)
return 0;
#endif
info->thread_status_size = 0;
if (signr) {
struct core_thread *ct;
struct elf_thread_status *ets;
for (ct = current->mm->core_state->dumper.next;
ct; ct = ct->next) {
ets = kzalloc(sizeof(*ets), GFP_KERNEL);
if (!ets)
return 0;
ets->thread = ct->task;
list_add(&ets->list, &info->thread_list);
}
list_for_each(t, &info->thread_list) {
int sz;
ets = list_entry(t, struct elf_thread_status, list);
sz = elf_dump_thread_status(signr, ets);
info->thread_status_size += sz;
}
}
/* now collect the dump for the current */
memset(info->prstatus, 0, sizeof(*info->prstatus));
fill_prstatus(info->prstatus, current, signr);
elf_core_copy_regs(&info->prstatus->pr_reg, regs);
/* Set up header */
fill_elf_header(elf, phdrs, ELF_ARCH, ELF_CORE_EFLAGS, ELF_OSABI);
/*
* Set up the notes in similar form to SVR4 core dumps made
* with info from their /proc.
*/
fill_note(info->notes + 0, "CORE", NT_PRSTATUS,
sizeof(*info->prstatus), info->prstatus);
fill_psinfo(info->psinfo, current->group_leader, current->mm);
fill_note(info->notes + 1, "CORE", NT_PRPSINFO,
sizeof(*info->psinfo), info->psinfo);
info->numnote = 2;
fill_auxv_note(&info->notes[info->numnote++], current->mm);
/* Try to dump the FPU. */
info->prstatus->pr_fpvalid = elf_core_copy_task_fpregs(current, regs,
info->fpu);
if (info->prstatus->pr_fpvalid)
fill_note(info->notes + info->numnote++,
"CORE", NT_PRFPREG, sizeof(*info->fpu), info->fpu);
#ifdef ELF_CORE_COPY_XFPREGS
if (elf_core_copy_task_xfpregs(current, info->xfpu))
fill_note(info->notes + info->numnote++,
"LINUX", ELF_CORE_XFPREG_TYPE,
sizeof(*info->xfpu), info->xfpu);
#endif
return 1;
#undef NUM_NOTES
}
static size_t get_note_info_size(struct elf_note_info *info)
{
int sz = 0;
int i;
for (i = 0; i < info->numnote; i++)
sz += notesize(info->notes + i);
sz += info->thread_status_size;
return sz;
}
static int write_note_info(struct elf_note_info *info,
struct file *file, loff_t *foffset)
{
int i;
struct list_head *t;
for (i = 0; i < info->numnote; i++)
if (!writenote(info->notes + i, file, foffset))
return 0;
/* write out the thread status notes section */
list_for_each(t, &info->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], file, foffset))
return 0;
}
return 1;
}
static void free_note_info(struct elf_note_info *info)
{
while (!list_empty(&info->thread_list)) {
struct list_head *tmp = info->thread_list.next;
list_del(tmp);
kfree(list_entry(tmp, struct elf_thread_status, list));
}
kfree(info->prstatus);
kfree(info->psinfo);
kfree(info->notes);
kfree(info->fpu);
#ifdef ELF_CORE_COPY_XFPREGS
kfree(info->xfpu);
#endif
}
#endif
static struct vm_area_struct *first_vma(struct task_struct *tsk,
struct vm_area_struct *gate_vma)
{
struct vm_area_struct *ret = tsk->mm->mmap;
if (ret)
return ret;
return gate_vma;
}
/*
* Helper function for iterating across a vma list. It ensures that the caller
* will visit `gate_vma' prior to terminating the search.
*/
static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma,
struct vm_area_struct *gate_vma)
{
struct vm_area_struct *ret;
ret = this_vma->vm_next;
if (ret)
return ret;
if (this_vma == gate_vma)
return NULL;
return gate_vma;
}
/*
* 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_core_dump(long signr, struct pt_regs *regs, struct file *file, unsigned long limit)
{
int has_dumped = 0;
mm_segment_t fs;
int segs;
size_t size = 0;
struct vm_area_struct *vma, *gate_vma;
struct elfhdr *elf = NULL;
loff_t offset = 0, dataoff, foffset;
unsigned long mm_flags;
struct elf_note_info info;
/*
* 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 out;
segs = current->mm->map_count;
#ifdef ELF_CORE_EXTRA_PHDRS
segs += ELF_CORE_EXTRA_PHDRS;
#endif
gate_vma = get_gate_vma(current);
if (gate_vma != NULL)
segs++;
/*
* Collect all the non-memory information about the process for the
* notes. This also sets up the file header.
*/
if (!fill_note_info(elf, segs + 1, /* including notes section */
&info, signr, regs))
goto cleanup;
has_dumped = 1;
current->flags |= PF_DUMPCORE;
fs = get_fs();
set_fs(KERNEL_DS);
DUMP_WRITE(elf, sizeof(*elf));
offset += sizeof(*elf); /* Elf header */
offset += (segs + 1) * sizeof(struct elf_phdr); /* Program headers */
foffset = offset;
/* Write notes phdr entry */
{
struct elf_phdr phdr;
size_t sz = get_note_info_size(&info);
sz += elf_coredump_extra_notes_size();
fill_elf_note_phdr(&phdr, sz, offset);
offset += sz;
DUMP_WRITE(&phdr, sizeof(phdr));
}
dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE);
/*
* We must use the same mm->flags while dumping core to avoid
* inconsistency between the program headers and bodies, otherwise an
* unusable core file can be generated.
*/
mm_flags = current->mm->flags;
/* Write program headers for segments dump */
for (vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma)) {
struct elf_phdr phdr;
phdr.p_type = PT_LOAD;
phdr.p_offset = offset;
phdr.p_vaddr = vma->vm_start;
phdr.p_paddr = 0;
phdr.p_filesz = vma_dump_size(vma, mm_flags);
phdr.p_memsz = vma->vm_end - vma->vm_start;
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;
DUMP_WRITE(&phdr, sizeof(phdr));
}
#ifdef ELF_CORE_WRITE_EXTRA_PHDRS
ELF_CORE_WRITE_EXTRA_PHDRS;
#endif
/* write out the notes section */
if (!write_note_info(&info, file, &foffset))
goto end_coredump;
if (elf_coredump_extra_notes_write(file, &foffset))
goto end_coredump;
/* Align to page */
DUMP_SEEK(dataoff - foffset);
for (vma = first_vma(current, gate_vma); vma != NULL;
vma = next_vma(vma, gate_vma)) {
unsigned long addr;
unsigned long end;
end = vma->vm_start + vma_dump_size(vma, mm_flags);
for (addr = vma->vm_start; addr < end; addr += PAGE_SIZE) {
struct page *page;
struct vm_area_struct *tmp_vma;
if (get_user_pages(current, current->mm, addr, 1, 0, 1,
&page, &tmp_vma) <= 0) {
DUMP_SEEK(PAGE_SIZE);
} else {
if (page == ZERO_PAGE(0)) {
if (!dump_seek(file, PAGE_SIZE)) {
page_cache_release(page);
goto end_coredump;
}
} else {
void *kaddr;
flush_cache_page(tmp_vma, addr,
page_to_pfn(page));
kaddr = kmap(page);
if ((size += PAGE_SIZE) > limit ||
!dump_write(file, kaddr,
PAGE_SIZE)) {
kunmap(page);
page_cache_release(page);
goto end_coredump;
}
kunmap(page);
}
page_cache_release(page);
}
}
}
#ifdef ELF_CORE_WRITE_EXTRA_DATA
ELF_CORE_WRITE_EXTRA_DATA;
#endif
end_coredump:
set_fs(fs);
cleanup:
free_note_info(&info);
kfree(elf);
out:
return has_dumped;
}
#endif /* USE_ELF_CORE_DUMP */
static int __init init_elf_binfmt(void)
{
return register_binfmt(&elf_format);
}
static void __exit exit_elf_binfmt(void)
{
/* Remove the COFF and ELF loaders. */
unregister_binfmt(&elf_format);
}
core_initcall(init_elf_binfmt);
module_exit(exit_elf_binfmt);
MODULE_LICENSE("GPL");
Reference in a new issue View git blame Copy permalink