Linus Torvalds 35ce8ae9ae Merge branch 'signal-for-v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace
Pull signal/exit/ptrace updates from Eric Biederman:
 "This set of changes deletes some dead code, makes a lot of cleanups
  which hopefully make the code easier to follow, and fixes bugs found
  along the way.

  The end-game which I have not yet reached yet is for fatal signals
  that generate coredumps to be short-circuit deliverable from
  complete_signal, for force_siginfo_to_task not to require changing
  userspace configured signal delivery state, and for the ptrace stops
  to always happen in locations where we can guarantee on all
  architectures that the all of the registers are saved and available on
  the stack.

  Removal of profile_task_ext, profile_munmap, and profile_handoff_task
  are the big successes for dead code removal this round.

  A bunch of small bug fixes are included, as most of the issues
  reported were small enough that they would not affect bisection so I
  simply added the fixes and did not fold the fixes into the changes
  they were fixing.

  There was a bug that broke coredumps piped to systemd-coredump. I
  dropped the change that caused that bug and replaced it entirely with
  something much more restrained. Unfortunately that required some
  rebasing.

  Some successes after this set of changes: There are few enough calls
  to do_exit to audit in a reasonable amount of time. The lifetime of
  struct kthread now matches the lifetime of struct task, and the
  pointer to struct kthread is no longer stored in set_child_tid. The
  flag SIGNAL_GROUP_COREDUMP is removed. The field group_exit_task is
  removed. Issues where task->exit_code was examined with
  signal->group_exit_code should been examined were fixed.

  There are several loosely related changes included because I am
  cleaning up and if I don't include them they will probably get lost.

  The original postings of these changes can be found at:
     https://lkml.kernel.org/r/87a6ha4zsd.fsf@email.froward.int.ebiederm.org
     https://lkml.kernel.org/r/87bl1kunjj.fsf@email.froward.int.ebiederm.org
     https://lkml.kernel.org/r/87r19opkx1.fsf_-_@email.froward.int.ebiederm.org

  I trimmed back the last set of changes to only the obviously correct
  once. Simply because there was less time for review than I had hoped"

* 'signal-for-v5.17' of git://git.kernel.org/pub/scm/linux/kernel/git/ebiederm/user-namespace: (44 commits)
  ptrace/m68k: Stop open coding ptrace_report_syscall
  ptrace: Remove unused regs argument from ptrace_report_syscall
  ptrace: Remove second setting of PT_SEIZED in ptrace_attach
  taskstats: Cleanup the use of task->exit_code
  exit: Use the correct exit_code in /proc/<pid>/stat
  exit: Fix the exit_code for wait_task_zombie
  exit: Coredumps reach do_group_exit
  exit: Remove profile_handoff_task
  exit: Remove profile_task_exit & profile_munmap
  signal: clean up kernel-doc comments
  signal: Remove the helper signal_group_exit
  signal: Rename group_exit_task group_exec_task
  coredump: Stop setting signal->group_exit_task
  signal: Remove SIGNAL_GROUP_COREDUMP
  signal: During coredumps set SIGNAL_GROUP_EXIT in zap_process
  signal: Make coredump handling explicit in complete_signal
  signal: Have prepare_signal detect coredumps using signal->core_state
  signal: Have the oom killer detect coredumps using signal->core_state
  exit: Move force_uaccess back into do_exit
  exit: Guarantee make_task_dead leaks the tsk when calling do_task_exit
  ...
2022-01-17 05:49:30 +02:00

208 lines
4.8 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* linux/arch/m68k/mm/fault.c
*
* Copyright (C) 1995 Hamish Macdonald
*/
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/kernel.h>
#include <linux/ptrace.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/perf_event.h>
#include <asm/setup.h>
#include <asm/traps.h>
extern void die_if_kernel(char *, struct pt_regs *, long);
int send_fault_sig(struct pt_regs *regs)
{
int signo, si_code;
void __user *addr;
signo = current->thread.signo;
si_code = current->thread.code;
addr = (void __user *)current->thread.faddr;
pr_debug("send_fault_sig: %p,%d,%d\n", addr, signo, si_code);
if (user_mode(regs)) {
force_sig_fault(signo, si_code, addr);
} else {
if (fixup_exception(regs))
return -1;
//if (signo == SIGBUS)
// force_sig_fault(si_signo, si_code, addr);
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
if ((unsigned long)addr < PAGE_SIZE)
pr_alert("Unable to handle kernel NULL pointer dereference");
else
pr_alert("Unable to handle kernel access");
pr_cont(" at virtual address %p\n", addr);
die_if_kernel("Oops", regs, 0 /*error_code*/);
make_task_dead(SIGKILL);
}
return 1;
}
/*
* This routine handles page faults. It determines the problem, and
* then passes it off to one of the appropriate routines.
*
* error_code:
* bit 0 == 0 means no page found, 1 means protection fault
* bit 1 == 0 means read, 1 means write
*
* If this routine detects a bad access, it returns 1, otherwise it
* returns 0.
*/
int do_page_fault(struct pt_regs *regs, unsigned long address,
unsigned long error_code)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct * vma;
vm_fault_t fault;
unsigned int flags = FAULT_FLAG_DEFAULT;
pr_debug("do page fault:\nregs->sr=%#x, regs->pc=%#lx, address=%#lx, %ld, %p\n",
regs->sr, regs->pc, address, error_code, mm ? mm->pgd : NULL);
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (faulthandler_disabled() || !mm)
goto no_context;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
retry:
mmap_read_lock(mm);
vma = find_vma(mm, address);
if (!vma)
goto map_err;
if (vma->vm_flags & VM_IO)
goto acc_err;
if (vma->vm_start <= address)
goto good_area;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto map_err;
if (user_mode(regs)) {
/* Accessing the stack below usp is always a bug. The
"+ 256" is there due to some instructions doing
pre-decrement on the stack and that doesn't show up
until later. */
if (address + 256 < rdusp())
goto map_err;
}
if (expand_stack(vma, address))
goto map_err;
/*
* Ok, we have a good vm_area for this memory access, so
* we can handle it..
*/
good_area:
pr_debug("do_page_fault: good_area\n");
switch (error_code & 3) {
default: /* 3: write, present */
fallthrough;
case 2: /* write, not present */
if (!(vma->vm_flags & VM_WRITE))
goto acc_err;
flags |= FAULT_FLAG_WRITE;
break;
case 1: /* read, present */
goto acc_err;
case 0: /* read, not present */
if (unlikely(!vma_is_accessible(vma)))
goto acc_err;
}
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
fault = handle_mm_fault(vma, address, flags, regs);
pr_debug("handle_mm_fault returns %x\n", fault);
if (fault_signal_pending(fault, regs))
return 0;
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGSEGV)
goto map_err;
else if (fault & VM_FAULT_SIGBUS)
goto bus_err;
BUG();
}
if (fault & VM_FAULT_RETRY) {
flags |= FAULT_FLAG_TRIED;
/*
* No need to mmap_read_unlock(mm) as we would
* have already released it in __lock_page_or_retry
* in mm/filemap.c.
*/
goto retry;
}
mmap_read_unlock(mm);
return 0;
/*
* We ran out of memory, or some other thing happened to us that made
* us unable to handle the page fault gracefully.
*/
out_of_memory:
mmap_read_unlock(mm);
if (!user_mode(regs))
goto no_context;
pagefault_out_of_memory();
return 0;
no_context:
current->thread.signo = SIGBUS;
current->thread.faddr = address;
return send_fault_sig(regs);
bus_err:
current->thread.signo = SIGBUS;
current->thread.code = BUS_ADRERR;
current->thread.faddr = address;
goto send_sig;
map_err:
current->thread.signo = SIGSEGV;
current->thread.code = SEGV_MAPERR;
current->thread.faddr = address;
goto send_sig;
acc_err:
current->thread.signo = SIGSEGV;
current->thread.code = SEGV_ACCERR;
current->thread.faddr = address;
send_sig:
mmap_read_unlock(mm);
return send_fault_sig(regs);
}