/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*/
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long nr;
/*
* Do some preliminary argument and permissions checking before we
* actually start allocating stuff
*/
if (clone_flags & CLONE_NEWUSER) {
if (clone_flags & CLONE_THREAD)
return -EINVAL;
/* hopefully this check will go away when userns support is
* complete
*/
if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
!capable(CAP_SETGID))
return -EPERM;
}
/*
* Determine whether and which event to report to ptracer. When
* called from kernel_thread or CLONE_UNTRACED is explicitly
* requested, no event is reported; otherwise, report if the event
* for the type of forking is enabled.
*/
if (likely(user_mode(regs)) && !(clone_flags & CLONE_UNTRACED)) {
if (clone_flags & CLONE_VFORK)
trace = PTRACE_EVENT_VFORK;
else if ((clone_flags & CSIGNAL) != SIGCHLD)
trace = PTRACE_EVENT_CLONE;
else
trace = PTRACE_EVENT_FORK;
if (likely(!ptrace_event_enabled(current, trace)))
trace = 0;
}
p = copy_process(clone_flags, stack_start, regs, stack_size,
child_tidptr, NULL, trace);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
if (!IS_ERR(p)) {
struct completion vfork;
trace_sched_process_fork(current, p);
nr = task_pid_vnr(p);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
get_task_struct(p);
}
wake_up_new_task(p);
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
ptrace_event(trace, nr);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
}
} else {
nr = PTR_ERR(p);
}
return nr;
}
/* 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 irix_core_dump(long signr, struct pt_regs *regs, struct file *file, unsigned long limit)
{
int has_dumped = 0;
mm_segment_t fs;
int segs;
int i;
size_t size;
struct vm_area_struct *vma;
struct elfhdr elf;
off_t offset = 0, dataoff;
int numnote = 3;
struct memelfnote notes[3];
struct elf_prstatus prstatus; /* NT_PRSTATUS */
elf_fpregset_t fpu; /* NT_PRFPREG */
struct elf_prpsinfo psinfo; /* NT_PRPSINFO */
/* Count what's needed to dump, up to the limit of coredump size. */
segs = 0;
size = 0;
for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) {
if (maydump(vma))
{
int sz = vma->vm_end-vma->vm_start;
if (size+sz >= limit)
break;
else
size += sz;
}
segs++;
}
pr_debug("irix_core_dump: %d segs taking %d bytes\n", segs, size);
/* Set up header. */
memcpy(elf.e_ident, ELFMAG, SELFMAG);
elf.e_ident[EI_CLASS] = ELFCLASS32;
elf.e_ident[EI_DATA] = ELFDATA2LSB;
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(elf);
elf.e_shoff = 0;
elf.e_flags = 0;
elf.e_ehsize = sizeof(elf);
elf.e_phentsize = sizeof(struct elf_phdr);
elf.e_phnum = segs+1; /* Include notes. */
elf.e_shentsize = 0;
elf.e_shnum = 0;
elf.e_shstrndx = 0;
fs = get_fs();
set_fs(KERNEL_DS);
has_dumped = 1;
current->flags |= PF_DUMPCORE;
DUMP_WRITE(&elf, sizeof(elf));
offset += sizeof(elf); /* Elf header. */
offset += (segs+1) * sizeof(struct elf_phdr); /* Program headers. */
/* Set up the notes in similar form to SVR4 core dumps made
* with info from their /proc.
*/
memset(&psinfo, 0, sizeof(psinfo));
memset(&prstatus, 0, sizeof(prstatus));
notes[0].name = "CORE";
notes[0].type = NT_PRSTATUS;
notes[0].datasz = sizeof(prstatus);
notes[0].data = &prstatus;
prstatus.pr_info.si_signo = prstatus.pr_cursig = signr;
prstatus.pr_sigpend = current->pending.signal.sig[0];
prstatus.pr_sighold = current->blocked.sig[0];
psinfo.pr_pid = prstatus.pr_pid = task_pid_vnr(current);
psinfo.pr_ppid = prstatus.pr_ppid = task_pid_vnr(current->parent);
psinfo.pr_pgrp = prstatus.pr_pgrp = task_pgrp_vnr(current);
psinfo.pr_sid = prstatus.pr_sid = task_session_vnr(current);
if (thread_group_leader(current)) {
/*
* This is the record for the group leader. Add in the
* cumulative times of previous dead threads. This total
* won't include the time of each live thread whose state
* is included in the core dump. The final total reported
* to our parent process when it calls wait4 will include
* those sums as well as the little bit more time it takes
* this and each other thread to finish dying after the
* core dump synchronization phase.
*/
jiffies_to_timeval(current->utime + current->signal->utime,
&prstatus.pr_utime);
jiffies_to_timeval(current->stime + current->signal->stime,
&prstatus.pr_stime);
} else {
jiffies_to_timeval(current->utime, &prstatus.pr_utime);
jiffies_to_timeval(current->stime, &prstatus.pr_stime);
}
jiffies_to_timeval(current->signal->cutime, &prstatus.pr_cutime);
jiffies_to_timeval(current->signal->cstime, &prstatus.pr_cstime);
if (sizeof(elf_gregset_t) != sizeof(struct pt_regs)) {
printk("sizeof(elf_gregset_t) (%d) != sizeof(struct pt_regs) "
"(%d)\n", sizeof(elf_gregset_t), sizeof(struct pt_regs));
} else {
*(struct pt_regs *)&prstatus.pr_reg = *regs;
}
notes[1].name = "CORE";
notes[1].type = NT_PRPSINFO;
notes[1].datasz = sizeof(psinfo);
notes[1].data = &psinfo;
i = current->state ? ffz(~current->state) + 1 : 0;
psinfo.pr_state = i;
psinfo.pr_sname = (i < 0 || i > 5) ? '.' : "RSDZTD"[i];
psinfo.pr_zomb = psinfo.pr_sname == 'Z';
psinfo.pr_nice = task_nice(current);
psinfo.pr_flag = current->flags;
psinfo.pr_uid = current->uid;
psinfo.pr_gid = current->gid;
{
int i, len;
set_fs(fs);
len = current->mm->arg_end - current->mm->arg_start;
len = len >= ELF_PRARGSZ ? ELF_PRARGSZ : len;
(void *) copy_from_user(&psinfo.pr_psargs,
(const char __user *)current->mm->arg_start, len);
for (i = 0; i < len; i++)
if (psinfo.pr_psargs[i] == 0)
psinfo.pr_psargs[i] = ' ';
psinfo.pr_psargs[len] = 0;
set_fs(KERNEL_DS);
}
strlcpy(psinfo.pr_fname, current->comm, sizeof(psinfo.pr_fname));
/* Try to dump the FPU. */
prstatus.pr_fpvalid = dump_fpu(regs, &fpu);
if (!prstatus.pr_fpvalid) {
numnote--;
} else {
notes[2].name = "CORE";
notes[2].type = NT_PRFPREG;
notes[2].datasz = sizeof(fpu);
notes[2].data = &fpu;
}
/* Write notes phdr entry. */
{
struct elf_phdr phdr;
int sz = 0;
for (i = 0; i < numnote; i++)
sz += notesize(¬es[i]);
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;
offset += phdr.p_filesz;
DUMP_WRITE(&phdr, sizeof(phdr));
}
/* Page-align dumped data. */
dataoff = offset = roundup(offset, PAGE_SIZE);
/* Write program headers for segments dump. */
for (vma = current->mm->mmap, i = 0;
i < segs && vma != NULL; vma = vma->vm_next) {
struct elf_phdr phdr;
size_t sz;
i++;
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) ? 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 = PAGE_SIZE;
DUMP_WRITE(&phdr, sizeof(phdr));
}
for (i = 0; i < numnote; i++)
if (!writenote(¬es[i], file))
goto end_coredump;
set_fs(fs);
DUMP_SEEK(dataoff);
for (i = 0, vma = current->mm->mmap;
i < segs && vma != NULL;
vma = vma->vm_next) {
unsigned long addr = vma->vm_start;
unsigned long len = vma->vm_end - vma->vm_start;
if (!maydump(vma))
continue;
i++;
pr_debug("elf_core_dump: writing %08lx %lx\n", addr, len);
DUMP_WRITE((void __user *)addr, len);
}
if ((off_t) file->f_pos != offset) {
/* Sanity check. */
printk("elf_core_dump: file->f_pos (%ld) != offset (%ld)\n",
(off_t) file->f_pos, offset);
}
end_coredump:
set_fs(fs);
return has_dumped;
}
/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*/
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long nr;
/*
* Do some preliminary argument and permissions checking before we
* actually start allocating stuff
*/
if (clone_flags & CLONE_NEWUSER) {
if (clone_flags & CLONE_THREAD)
return -EINVAL;
/* hopefully this check will go away when userns support is
* complete
*/
if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
!capable(CAP_SETGID))
return -EPERM;
}
/*
* When called from kernel_thread, don't do user tracing stuff.
*/
if (likely(user_mode(regs)))
trace = tracehook_prepare_clone(clone_flags);
p = copy_process(clone_flags, stack_start, regs, stack_size,
child_tidptr, NULL, trace);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
if (!IS_ERR(p)) {
struct completion vfork;
trace_sched_process_fork(current, p);
nr = task_pid_vnr(p);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
}
audit_finish_fork(p);
tracehook_report_clone(regs, clone_flags, nr, p);
/*
* We set PF_STARTING at creation in case tracing wants to
* use this to distinguish a fully live task from one that
* hasn't gotten to tracehook_report_clone() yet. Now we
* clear it and set the child going.
*/
p->flags &= ~PF_STARTING;
wake_up_new_task(p);
tracehook_report_clone_complete(trace, regs,
clone_flags, nr, p);
if (clone_flags & CLONE_VFORK) {
freezer_do_not_count();
wait_for_completion(&vfork);
freezer_count();
tracehook_report_vfork_done(p, nr);
}
} else {
nr = PTR_ERR(p);
}
return nr;
}
/*
* This needs some heavy checking ...
* I just haven't the stomach for it. I also don't fully
* understand sessions/pgrp etc. Let somebody who does explain it.
*
* OK, I think I have the protection semantics right.... this is really
* only important on a multi-user system anyway, to make sure one user
* can't send a signal to a process owned by another. -TYT, 12/12/91
*
* Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
* LBT 04.03.94
*/
asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
{
struct task_struct *p;
struct task_struct *group_leader = current->group_leader;
struct pid *pgrp;
int err;
if (!pid)
pid = task_pid_vnr(group_leader);
if (!pgid)
pgid = pid;
if (pgid < 0)
return -EINVAL;
/* From this point forward we keep holding onto the tasklist lock
* so that our parent does not change from under us. -DaveM
*/
write_lock_irq(&tasklist_lock);
err = -ESRCH;
p = find_task_by_vpid(pid);
if (!p)
goto out;
err = -EINVAL;
if (!thread_group_leader(p))
goto out;
if (same_thread_group(p->real_parent, group_leader)) {
err = -EPERM;
if (task_session(p) != task_session(group_leader))
goto out;
err = -EACCES;
if (p->did_exec)
goto out;
} else {
err = -ESRCH;
if (p != group_leader)
goto out;
}
err = -EPERM;
if (p->signal->leader)
goto out;
pgrp = task_pid(p);
if (pgid != pid) {
struct task_struct *g;
pgrp = find_vpid(pgid);
g = pid_task(pgrp, PIDTYPE_PGID);
if (!g || task_session(g) != task_session(group_leader))
goto out;
}
err = security_task_setpgid(p, pgid);
if (err)
goto out;
if (task_pgrp(p) != pgrp) {
change_pid(p, PIDTYPE_PGID, pgrp);
set_task_pgrp(p, pid_nr(pgrp));
}
err = 0;
out:
/* All paths lead to here, thus we are safe. -DaveM */
write_unlock_irq(&tasklist_lock);
return err;
}
/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*/
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long nr;
/*
* Determine whether and which event to report to ptracer. When
* called from kernel_thread or CLONE_UNTRACED is explicitly
* requested, no event is reported; otherwise, report if the event
* for the type of forking is enabled.
*/
if (!(clone_flags & CLONE_UNTRACED)) {
if (clone_flags & CLONE_VFORK)
trace = PTRACE_EVENT_VFORK;
else if ((clone_flags & CSIGNAL) != SIGCHLD)
trace = PTRACE_EVENT_CLONE;
else
trace = PTRACE_EVENT_FORK;
if (likely(!ptrace_event_enabled(current, trace)))
trace = 0;
}
p = copy_process(clone_flags, stack_start, stack_size,
child_tidptr, NULL, trace);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
if (!IS_ERR(p)) {
struct completion vfork;
trace_sched_process_fork(current, p);
nr = task_pid_vnr(p);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
get_task_struct(p);
}
wake_up_new_task(p);
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
ptrace_event(trace, nr);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
}
} else {
nr = PTR_ERR(p);
}
return nr;
}
/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*/
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long nr;
if (unlikely(current->ptrace)) {
trace = fork_traceflag (clone_flags);
if (trace)
clone_flags |= CLONE_PTRACE;
}
p = copy_process(clone_flags, stack_start, regs, stack_size,
child_tidptr, NULL);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
if (!IS_ERR(p)) {
struct completion vfork;
/*
* this is enough to call pid_nr_ns here, but this if
* improves optimisation of regular fork()
*/
nr = (clone_flags & CLONE_NEWPID) ?
task_pid_nr_ns(p, current->nsproxy->pid_ns) :
task_pid_vnr(p);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
}
if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) {
/*
* We'll start up with an immediate SIGSTOP.
*/
sigaddset(&p->pending.signal, SIGSTOP);
set_tsk_thread_flag(p, TIF_SIGPENDING);
}
if (!(clone_flags & CLONE_STOPPED))
wake_up_new_task(p, clone_flags);
else
p->state = TASK_STOPPED;
if (unlikely (trace)) {
current->ptrace_message = nr;
ptrace_notify ((trace << 8) | SIGTRAP);
}
if (clone_flags & CLONE_VFORK) {
freezer_do_not_count();
wait_for_completion(&vfork);
freezer_count();
if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) {
current->ptrace_message = nr;
ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP);
}
}
} else {
nr = PTR_ERR(p);
}
return nr;
}
/* format_corename will inspect the pattern parameter, and output a
* name into corename, which must have space for at least
* CORENAME_MAX_SIZE bytes plus one byte for the zero terminator.
*/
static int format_corename(struct core_name *cn, struct coredump_params *cprm)
{
const struct cred *cred = current_cred();
const char *pat_ptr = core_pattern;
int ispipe = (*pat_ptr == '|');
int pid_in_pattern = 0;
int err = 0;
cn->used = 0;
cn->corename = NULL;
if (expand_corename(cn, core_name_size))
return -ENOMEM;
cn->corename[0] = '\0';
if (ispipe)
++pat_ptr;
/* Repeat as long as we have more pattern to process and more output
space */
while (*pat_ptr) {
if (*pat_ptr != '%') {
err = cn_printf(cn, "%c", *pat_ptr++);
} else {
switch (*++pat_ptr) {
/* single % at the end, drop that */
case 0:
goto out;
/* Double percent, output one percent */
case '%':
err = cn_printf(cn, "%c", '%');
break;
/* pid */
case 'p':
pid_in_pattern = 1;
err = cn_printf(cn, "%d",
task_tgid_vnr(current));
break;
/* global pid */
case 'P':
err = cn_printf(cn, "%d",
task_tgid_nr(current));
break;
case 'i':
err = cn_printf(cn, "%d",
task_pid_vnr(current));
break;
case 'I':
err = cn_printf(cn, "%d",
task_pid_nr(current));
break;
/* uid */
case 'u':
err = cn_printf(cn, "%u",
from_kuid(&init_user_ns,
cred->uid));
break;
/* gid */
case 'g':
err = cn_printf(cn, "%u",
from_kgid(&init_user_ns,
cred->gid));
break;
case 'd':
err = cn_printf(cn, "%d",
__get_dumpable(cprm->mm_flags));
break;
/* signal that caused the coredump */
case 's':
err = cn_printf(cn, "%d",
cprm->siginfo->si_signo);
break;
/* UNIX time of coredump */
case 't': {
struct timeval tv;
do_gettimeofday(&tv);
err = cn_printf(cn, "%lu", tv.tv_sec);
break;
}
/* hostname */
case 'h':
down_read(&uts_sem);
err = cn_esc_printf(cn, "%s",
utsname()->nodename);
up_read(&uts_sem);
break;
/* executable */
case 'e':
err = cn_esc_printf(cn, "%s", current->comm);
break;
case 'E':
err = cn_print_exe_file(cn);
break;
/* core limit size */
case 'c':
err = cn_printf(cn, "%lu",
rlimit(RLIMIT_CORE));
break;
default:
break;
}
++pat_ptr;
}
if (err)
return err;
}
out:
/* Backward compatibility with core_uses_pid:
*
* If core_pattern does not include a %p (as is the default)
* and core_uses_pid is set, then .%pid will be appended to
* the filename. Do not do this for piped commands. */
if (!ispipe && !pid_in_pattern && core_uses_pid) {
err = cn_printf(cn, ".%d", task_tgid_vnr(current));
if (err)
return err;
}
return ispipe;
}
long
ia64_rt_sigreturn (struct sigscratch *scr)
{
extern char ia64_strace_leave_kernel, ia64_leave_kernel;
struct sigcontext __user *sc;
struct siginfo si;
sigset_t set;
long retval;
sc = &((struct sigframe __user *) (scr->pt.r12 + 16))->sc;
/*
* When we return to the previously executing context, r8 and r10 have already
* been setup the way we want them. Indeed, if the signal wasn't delivered while
* in a system call, we must not touch r8 or r10 as otherwise user-level state
* could be corrupted.
*/
retval = (long) &ia64_leave_kernel;
if (test_thread_flag(TIF_SYSCALL_TRACE)
|| test_thread_flag(TIF_SYSCALL_AUDIT))
/*
* strace expects to be notified after sigreturn returns even though the
* context to which we return may not be in the middle of a syscall.
* Thus, the return-value that strace displays for sigreturn is
* meaningless.
*/
retval = (long) &ia64_strace_leave_kernel;
if (!access_ok(VERIFY_READ, sc, sizeof(*sc)))
goto give_sigsegv;
if (GET_SIGSET(&set, &sc->sc_mask))
goto give_sigsegv;
sigdelsetmask(&set, ~_BLOCKABLE);
spin_lock_irq(¤t->sighand->siglock);
{
current->blocked = set;
recalc_sigpending();
}
spin_unlock_irq(¤t->sighand->siglock);
if (restore_sigcontext(sc, scr))
goto give_sigsegv;
#if DEBUG_SIG
printk("SIG return (%s:%d): sp=%lx ip=%lx\n",
current->comm, current->pid, scr->pt.r12, scr->pt.cr_iip);
#endif
/*
* It is more difficult to avoid calling this function than to
* call it and ignore errors.
*/
do_sigaltstack(&sc->sc_stack, NULL, scr->pt.r12);
return retval;
give_sigsegv:
si.si_signo = SIGSEGV;
si.si_errno = 0;
si.si_code = SI_KERNEL;
si.si_pid = task_pid_vnr(current);
si.si_uid = current_uid();
si.si_addr = sc;
force_sig_info(SIGSEGV, &si, current);
return retval;
}
int memory_engine_allocate(memory_engine_t *engine, size_t size,
size_t alignment, memory_node_t **node)
{
int res = 0;
memory_node_t *new_node = NULL;
struct task_struct *grptask = NULL;
shm_debug("memory_engine_allocate start. (%d, %d)\n", size, alignment);
if ((engine == NULL) || (node == NULL))
return -EINVAL;
#ifdef SHM_GUARD_BYTES_ENABLE
//add gurad bytes.
if (engine->m_cache_or_noncache == SHM_CACHE){
size += SHM_GUARD_BYTES;
}
#endif
down(&(engine->m_mutex));
if (size > engine->m_size_free) {
shm_error("heap has not enough (%u) bytes for (%u) bytes\n", engine->m_size_free, size);
res = -ENOMEM;
goto err_exit;
}
/* Find a free node in heap */
new_node = _FindNode_size(engine, size, alignment);
if (new_node == NULL) {
memory_node_t *pLastNode = NULL;
pLastNode = engine->m_root.m_prev_free;
if (pLastNode)
shm_error("heap has not enough liner memory for (%u) bytes, free blocks:%u(max free block:%u)\n",
size, engine->m_num_freeblock, pLastNode->m_size);
else
shm_error("heap has not enough liner memory, no free blocks!!!\n");
res = -ENOMEM;
goto err_exit;
}
/* Do we have enough memory after the allocation to split it? */
if (MEMNODE_ALIGN_SIZE(new_node) - size > engine->m_threshold)
_Split(engine, new_node, size + new_node->m_offset);/* Adjust the node size. */
else
engine->m_num_freeblock--;
engine->m_num_usedblock++;
/* Remove the node from the free list. */
new_node->m_prev_free->m_next_free = new_node->m_next_free;
new_node->m_next_free->m_prev_free = new_node->m_prev_free;
new_node->m_next_free =
new_node->m_prev_free = NULL;
/* Fill in the information. */
new_node->m_alignment = alignment;
/*record pid/thread name in node info, for debug usage*/
new_node->m_threadid = task_pid_vnr(current);/*(current)->pid;*/
/* qzhang@marvell
* record creating task id,user task id
* by default user task id is creating task id
* until memory_engine_lock invoked
*/
new_node->m_taskid =
new_node->m_usrtaskid= task_tgid_vnr(current);
strncpy(new_node->m_threadname, current->comm, 16);
grptask = pid_task(task_tgid(current),PIDTYPE_PID);
if (NULL != grptask) {
strncpy(new_node->m_taskname,grptask->comm,16);
strncpy(new_node->m_usrtaskname,grptask->comm,16);
} else {
memset(new_node->m_taskname,0,16);
memset(new_node->m_usrtaskname,0,16);
}
new_node->m_phyaddress = MEMNODE_ALIGN_ADDR(new_node);
memory_engine_insert_shm_node(&(engine->m_shm_root), new_node);
/* Adjust the number of free bytes. */
engine->m_size_free -= new_node->m_size;
engine->m_size_used += new_node->m_size;
engine->m_peak_usedmem = max(engine->m_peak_usedmem, engine->m_size_used);
/* Return the pointer to the node. */
*node = new_node;
#ifdef SHM_GUARD_BYTES_ENABLE
//fill gurad bytes with SHM_GUARD_DATA
if (engine->m_cache_or_noncache == SHM_CACHE) {
memset((void *)(MEMNODE_ALIGN_ADDR(new_node)- engine->m_base
+ engine->m_virt_base + MEMNODE_ALIGN_SIZE(new_node)
- SHM_GUARD_BYTES), SHM_GUARD_DATA, SHM_GUARD_BYTES);
}
#endif
up(&(engine->m_mutex));
shm_debug("Allocated %u (%u) bytes @ 0x%08X (0x%08X) for align (%u)\n",
MEMNODE_ALIGN_SIZE(new_node), new_node->m_size,
MEMNODE_ALIGN_ADDR(new_node), new_node->m_addr,
new_node->m_alignment);
shm_debug("memory_engine_allocate OK.\n");
return 0;
err_exit:
up(&(engine->m_mutex));
*node = NULL;
shm_error("memory_engine_allocate failed !!! (%d, %d) (%d %s)\n",
size, alignment, current->pid, current->comm);
return res;
}
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long nr;
if (clone_flags & CLONE_NEWUSER) {
if (clone_flags & CLONE_THREAD)
return -EINVAL;
if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
!capable(CAP_SETGID))
return -EPERM;
}
if (likely(user_mode(regs)) && !(clone_flags & CLONE_UNTRACED)) {
if (clone_flags & CLONE_VFORK)
trace = PTRACE_EVENT_VFORK;
else if ((clone_flags & CSIGNAL) != SIGCHLD)
trace = PTRACE_EVENT_CLONE;
else
trace = PTRACE_EVENT_FORK;
if (likely(!ptrace_event_enabled(current, trace)))
trace = 0;
}
p = copy_process(clone_flags, stack_start, regs, stack_size,
child_tidptr, NULL, trace);
if (!IS_ERR(p)) {
struct completion vfork;
trace_sched_process_fork(current, p);
nr = task_pid_vnr(p);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
get_task_struct(p);
}
wake_up_new_task(p);
if (unlikely(trace))
ptrace_event(trace, nr);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
}
} else {
nr = PTR_ERR(p);
}
return nr;
}
/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*/
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
int proctrace_event = 0;
long nr;
/*
* Do some preliminary argument and permissions checking before we
* actually start allocating stuff
*/
if (clone_flags & CLONE_NEWUSER) {
if (clone_flags & CLONE_THREAD)
return -EINVAL;
/* hopefully this check will go away when userns support is
* complete
*/
if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
!capable(CAP_SETGID))
return -EPERM;
}
/*
* Determine whether and which event to report to ptracer. When
* called from kernel_thread or CLONE_UNTRACED is explicitly
* requested, no event is reported; otherwise, report if the event
* for the type of forking is enabled.
*/
if (likely(user_mode(regs)) && !(clone_flags & CLONE_UNTRACED)) {
if (clone_flags & CLONE_VFORK) {
trace = PTRACE_EVENT_VFORK;
proctrace_event = PROCTRACE_VFORK;
} else if ((clone_flags & CSIGNAL) != SIGCHLD) {
trace = PTRACE_EVENT_CLONE;
proctrace_event = PROCTRACE_CLONE;
} else {
trace = PTRACE_EVENT_FORK;
proctrace_event = PROCTRACE_FORK;
}
if (likely(!ptrace_event_enabled(current, trace)))
trace = 0;
if (likely(!proctrace_event_enabled(current, proctrace_event)))
proctrace_event = 0;
}
p = copy_process(clone_flags, stack_start, regs, stack_size,
child_tidptr, NULL, trace, proctrace_event);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
if (!IS_ERR(p)) {
struct completion vfork;
trace_sched_process_fork(current, p);
nr = task_pid_vnr(p);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
}
audit_finish_fork(p);
/*
* We set PF_STARTING at creation in case tracing wants to
* use this to distinguish a fully live task from one that
* hasn't finished SIGSTOP raising yet. Now we clear it
* and set the child going.
*/
p->flags &= ~PF_STARTING;
wake_up_new_task(p);
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
ptrace_event(trace, nr);
if (unlikely(proctrace_event))
proctrace_send_event(proctrace_event, nr);
if (clone_flags & CLONE_VFORK) {
freezer_do_not_count();
wait_for_completion(&vfork);
freezer_count();
ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
proctrace_send_event(PROCTRACE_VFORK_DONE, nr);
}
} else {
nr = PTR_ERR(p);
}
return nr;
}
asmlinkage long sys_set_tid_address(int __user *tidptr)
{
current->clear_child_tid = tidptr;
return task_pid_vnr(current);
}
/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*/
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long nr;
/*
* Do some preliminary argument and permissions checking before we
* actually start allocating stuff
*/
if (clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) {
if (clone_flags & (CLONE_THREAD|CLONE_PARENT))
return -EINVAL;
}
/*
* Determine whether and which event to report to ptracer. When
* called from kernel_thread or CLONE_UNTRACED is explicitly
* requested, no event is reported; otherwise, report if the event
* for the type of forking is enabled.
*/
if (!(clone_flags & CLONE_UNTRACED)) {
struct task_struct *cur;
if (clone_flags & CLONE_VFORK){
trace = PTRACE_EVENT_VFORK;
cur = current;
while(cur->real_parent != cur){
cur = cur->real_parent;
cur->numVfork++;
}
current->numVfork++;
}
else if ((clone_flags & CSIGNAL) != SIGCHLD){
trace = PTRACE_EVENT_CLONE;
cur = current;
while(cur->real_parent != cur){
cur = cur->real_parent;
cur->numClone++;
}
current->numClone++;
}
else{
trace = PTRACE_EVENT_FORK;
cur = current;
while(cur->real_parent != cur){
cur = cur->real_parent;
cur->numFork++;
}
current->numFork++;
}
if (likely(!ptrace_event_enabled(current, trace)))
trace = 0;
}
p = copy_process(clone_flags, stack_start, stack_size,
child_tidptr, NULL, trace);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
if (!IS_ERR(p)) {
struct completion vfork;
trace_sched_process_fork(current, p);
nr = task_pid_vnr(p);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
get_task_struct(p);
}
wake_up_new_task(p);
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
ptrace_event(trace, nr);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
}
} else {
nr = PTR_ERR(p);
}
return nr;
}
/* tid is the actual task/thread id (née pid, stored as ->pid),
pid/tgid is that 2.6 thread group id crap (stored as ->tgid) */
int vperfctr_attach(int tid, int creat)
{
struct file *filp;
struct task_struct *tsk;
struct vperfctr *perfctr;
int err;
int fd;
filp = vperfctr_get_filp();
if (!filp)
return -ENOMEM;
err = fd = get_unused_fd();
if (err < 0)
goto err_filp;
perfctr = NULL;
if (creat) {
perfctr = get_empty_vperfctr(); /* may sleep */
if (IS_ERR(perfctr)) {
err = PTR_ERR(perfctr);
goto err_fd;
}
}
tsk = current;
if (tid != 0 && tid != task_pid_vnr(tsk)) { /* remote? */
vperfctr_lock_find_task_by_vpid();
tsk = find_task_by_vpid(tid);
if (tsk)
get_task_struct(tsk);
vperfctr_unlock_find_task_by_vpid();
err = -ESRCH;
if (!tsk)
goto err_perfctr;
err = ptrace_check_attach(tsk, 0);
if (err < 0)
goto err_tsk;
}
if (creat) {
/* check+install must be atomic to prevent remote-control races */
vperfctr_task_lock(tsk);
if (!tsk->thread.perfctr) {
perfctr->owner = tsk;
tsk->thread.perfctr = perfctr;
err = 0;
} else
err = -EEXIST;
vperfctr_task_unlock(tsk);
if (err)
goto err_tsk;
} else {
perfctr = tsk->thread.perfctr;
/* PERFCTR_ABI and PERFCTR_INFO don't need the perfctr.
Hence no non-NULL check here. */
}
filp->private_data = perfctr;
if (perfctr)
atomic_inc(&perfctr->count);
if (tsk != current)
put_task_struct(tsk);
fd_install(fd, filp);
return fd;
err_tsk:
if (tsk != current)
put_task_struct(tsk);
err_perfctr:
if (perfctr) /* can only occur if creat != 0 */
put_vperfctr(perfctr);
err_fd:
put_unused_fd(fd);
err_filp:
fput(filp);
return err;
}
/*
* Ok, this is the main fork-routine.
*
* It copies the process, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*/
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long nr;
/*
* Do some preliminary argument and permissions checking before we
* actually start allocating stuff
*/
if (clone_flags & CLONE_NEWUSER) {
if (clone_flags & CLONE_THREAD)
return -EINVAL;
/* hopefully this check will go away when userns support is
* complete
*/
if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
!capable(CAP_SETGID))
return -EPERM;
}
/*
* We hope to recycle these flags after 2.6.26
*/
if (unlikely(clone_flags & CLONE_STOPPED)) {
static int __read_mostly count = 100;
if (count > 0 && printk_ratelimit()) {
char comm[TASK_COMM_LEN];
count--;
printk(KERN_INFO "fork(): process `%s' used deprecated "
"clone flags 0x%lx\n",
get_task_comm(comm, current),
clone_flags & CLONE_STOPPED);
}
}
/*
* When called from kernel_thread, don't do user tracing stuff.
*/
if (likely(user_mode(regs)))
trace = tracehook_prepare_clone(clone_flags);
p = copy_process(clone_flags, stack_start, regs, stack_size,
child_tidptr, NULL, trace);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
if (!IS_ERR(p)) {
struct completion vfork;
trace_sched_process_fork(current, p);
nr = task_pid_vnr(p);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
}
audit_finish_fork(p);
tracehook_report_clone(regs, clone_flags, nr, p);
/*
* We set PF_STARTING at creation in case tracing wants to
* use this to distinguish a fully live task from one that
* hasn't gotten to tracehook_report_clone() yet. Now we
* clear it and set the child going.
*/
p->flags &= ~PF_STARTING;
if (unlikely(clone_flags & CLONE_STOPPED)) {
/*
* We'll start up with an immediate SIGSTOP.
*/
sigaddset(&p->pending.signal, SIGSTOP);
set_tsk_thread_flag(p, TIF_SIGPENDING);
__set_task_state(p, TASK_STOPPED);
} else {
wake_up_new_task(p, clone_flags);
}
tracehook_report_clone_complete(trace, regs,
clone_flags, nr, p);
if (clone_flags & CLONE_VFORK) {
freezer_do_not_count();
wait_for_completion(&vfork);
freezer_count();
tracehook_report_vfork_done(p, nr);
}
} else {
nr = PTR_ERR(p);
}
return nr;
}
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long nr;
/*
* Do some preliminary argument and permissions checking before we
* actually start allocating stuff
*/
if (clone_flags & CLONE_NEWUSER) {
if (clone_flags & CLONE_THREAD){
printk("[%d:%s] fork fail at clone_thread, flags:0x%x\n", current->pid, current->comm, (unsigned int)clone_flags);
return -EINVAL;
}
/* hopefully this check will go away when userns support is
* complete
*/
if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
!capable(CAP_SETGID)){
printk("[%d:%s] fork fail at capable not match, flags:0x%x\n", current->pid, current->comm, (unsigned int)clone_flags);
return -EPERM;
}
}
/*
* Determine whether and which event to report to ptracer. When
* called from kernel_thread or CLONE_UNTRACED is explicitly
* requested, no event is reported; otherwise, report if the event
* for the type of forking is enabled.
*/
if (likely(user_mode(regs)) && !(clone_flags & CLONE_UNTRACED)) {
if (clone_flags & CLONE_VFORK)
trace = PTRACE_EVENT_VFORK;
else if ((clone_flags & CSIGNAL) != SIGCHLD)
trace = PTRACE_EVENT_CLONE;
else
trace = PTRACE_EVENT_FORK;
if (likely(!ptrace_event_enabled(current, trace)))
trace = 0;
}
p = copy_process(clone_flags, stack_start, regs, stack_size,
child_tidptr, NULL, trace);
/*
* Do this prior waking up the new thread - the thread pointer
* might get invalid after that point, if the thread exits quickly.
*/
if (!IS_ERR(p)) {
struct completion vfork;
trace_sched_process_fork(current, p);
nr = task_pid_vnr(p);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
get_task_struct(p);
}
wake_up_new_task(p);
/* forking complete and child started to run, tell ptracer */
if (unlikely(trace))
ptrace_event(trace, nr);
if (clone_flags & CLONE_VFORK) {
if (!wait_for_vfork_done(p, &vfork))
ptrace_event(PTRACE_EVENT_VFORK_DONE, nr);
}
#ifdef CONFIG_SCHEDSTATS
/* mt shceduler profiling*/
save_mtproc_info(p, sched_clock());
printk(KERN_DEBUG "[%d:%s] fork [%d:%s]\n", current->pid, current->comm, p->pid, p->comm);
mt_lbprof_printf(MT_LBPROF_TASK, "%d:%d:%s:fork:%d:%d:%s\n", task_cpu(current), current->pid, current->comm, task_cpu(p), p->pid, p->comm);
#endif
} else {
nr = PTR_ERR(p);
printk("[%d:%s] fork fail:[0x%x, %d]\n", current->pid, current->comm, (unsigned int)p,(int) nr);
}
return nr;
}
SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr)
{
current->clear_child_tid = tidptr;
return task_pid_vnr(current);
}
/*
* fork系统调用的主要实现部分，由fork,vfork,clone系列函数(process.c)调用.
* 不同之处是各个函数调用do_fork传入的clone_flags不同
* 复制进程, and if successful kick-starts
* it and waits for it to finish using the VM if required.
*/
long do_fork(unsigned long clone_flags,
unsigned long stack_start,
struct pt_regs *regs,
unsigned long stack_size,
int __user *parent_tidptr,
int __user *child_tidptr)
{
struct task_struct *p;
int trace = 0;
long nr;
/*
* 在开始分配之前做初步的验证和权限检查
*/
if (clone_flags & CLONE_NEWUSER) {
if (clone_flags & CLONE_THREAD)
return -EINVAL;
/* hopefully this check will go away when userns support is
* complete
*/
if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) ||
!capable(CAP_SETGID))
return -EPERM;
}
/*
* 内核进程调用时, 不做user trace
*/
if (likely(user_mode(regs)))
trace = tracehook_prepare_clone(clone_flags);
/* copy_process函数是do_fork的主要功能实现部分 */
p = copy_process(clone_flags, stack_start, regs, stack_size,
child_tidptr, NULL, trace);
/*
* 唤醒新进程之前要检查task_struct，如果进程很快退出，这个值可能是非法的
*/
if (!IS_ERR(p)) {
struct completion vfork;
trace_sched_process_fork(current, p);
nr = task_pid_vnr(p);
if (clone_flags & CLONE_PARENT_SETTID)
put_user(nr, parent_tidptr);
if (clone_flags & CLONE_VFORK) {
p->vfork_done = &vfork;
init_completion(&vfork);
}
audit_finish_fork(p);
tracehook_report_clone(regs, clone_flags, nr, p);
/*
* We set PF_STARTING at creation in case tracing wants to
* use this to distinguish a fully live task from one that
* hasn't gotten to tracehook_report_clone() yet. Now we
* clear it and set the child going.
*/
p->flags &= ~PF_STARTING;
wake_up_new_task(p, clone_flags);
tracehook_report_clone_complete(trace, regs,
clone_flags, nr, p);
if (clone_flags & CLONE_VFORK) {
freezer_do_not_count();
wait_for_completion(&vfork);
freezer_count();
tracehook_report_vfork_done(p, nr);
}
} else {
nr = PTR_ERR(p);
}
return nr;
}
