linux/arch/powerpc/kernel/signal.c
Gustavo Luiz Duarte 2464cc4c34 powerpc/tm: Fix clearing MSR[TS] in current when reclaiming on signal delivery
After a treclaim, we expect to be in non-transactional state. If we
don't clear the current thread's MSR[TS] before we get preempted, then
tm_recheckpoint_new_task() will recheckpoint and we get rescheduled in
suspended transaction state.

When handling a signal caught in transactional state,
handle_rt_signal64() calls get_tm_stackpointer() that treclaims the
transaction using tm_reclaim_current() but without clearing the
thread's MSR[TS]. This can cause the TM Bad Thing exception below if
later we pagefault and get preempted trying to access the user's
sigframe, using __put_user(). Afterwards, when we are rescheduled back
into do_page_fault() (but now in suspended state since the thread's
MSR[TS] was not cleared), upon executing 'rfid' after completion of
the page fault handling, the exception is raised because a transition
from suspended to non-transactional state is invalid.

  Unexpected TM Bad Thing exception at c00000000000de44 (msr 0x8000000302a03031) tm_scratch=800000010280b033
  Oops: Unrecoverable exception, sig: 6 [#1]
  LE PAGE_SIZE=64K MMU=Hash SMP NR_CPUS=2048 NUMA pSeries
  CPU: 25 PID: 15547 Comm: a.out Not tainted 5.4.0-rc2 #32
  NIP:  c00000000000de44 LR: c000000000034728 CTR: 0000000000000000
  REGS: c00000003fe7bd70 TRAP: 0700   Not tainted  (5.4.0-rc2)
  MSR:  8000000302a03031 <SF,VEC,VSX,FP,ME,IR,DR,LE,TM[SE]>  CR: 44000884  XER: 00000000
  CFAR: c00000000000dda4 IRQMASK: 0
  PACATMSCRATCH: 800000010280b033
  GPR00: c000000000034728 c000000f65a17c80 c000000001662800 00007fffacf3fd78
  GPR04: 0000000000001000 0000000000001000 0000000000000000 c000000f611f8af0
  GPR08: 0000000000000000 0000000078006001 0000000000000000 000c000000000000
  GPR12: c000000f611f84b0 c00000003ffcb200 0000000000000000 0000000000000000
  GPR16: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
  GPR20: 0000000000000000 0000000000000000 0000000000000000 c000000f611f8140
  GPR24: 0000000000000000 00007fffacf3fd68 c000000f65a17d90 c000000f611f7800
  GPR28: c000000f65a17e90 c000000f65a17e90 c000000001685e18 00007fffacf3f000
  NIP [c00000000000de44] fast_exception_return+0xf4/0x1b0
  LR [c000000000034728] handle_rt_signal64+0x78/0xc50
  Call Trace:
  [c000000f65a17c80] [c000000000034710] handle_rt_signal64+0x60/0xc50 (unreliable)
  [c000000f65a17d30] [c000000000023640] do_notify_resume+0x330/0x460
  [c000000f65a17e20] [c00000000000dcc4] ret_from_except_lite+0x70/0x74
  Instruction dump:
  7c4ff120 e8410170 7c5a03a6 38400000 f8410060 e8010070 e8410080 e8610088
  60000000 60000000 e8810090 e8210078 <4c000024> 48000000 e8610178 88ed0989
  ---[ end trace 93094aa44b442f87 ]---

The simplified sequence of events that triggers the above exception is:

  ...				# userspace in NON-TRANSACTIONAL state
  tbegin			# userspace in TRANSACTIONAL state
  signal delivery		# kernelspace in SUSPENDED state
  handle_rt_signal64()
    get_tm_stackpointer()
      treclaim			# kernelspace in NON-TRANSACTIONAL state
    __put_user()
      page fault happens. We will never get back here because of the TM Bad Thing exception.

  page fault handling kicks in and we voluntarily preempt ourselves
  do_page_fault()
    __schedule()
      __switch_to(other_task)

  our task is rescheduled and we recheckpoint because the thread's MSR[TS] was not cleared
  __switch_to(our_task)
    switch_to_tm()
      tm_recheckpoint_new_task()
        trechkpt			# kernelspace in SUSPENDED state

  The page fault handling resumes, but now we are in suspended transaction state
  do_page_fault()    completes
  rfid     <----- trying to get back where the page fault happened (we were non-transactional back then)
  TM Bad Thing			# illegal transition from suspended to non-transactional

This patch fixes that issue by clearing the current thread's MSR[TS]
just after treclaim in get_tm_stackpointer() so that we stay in
non-transactional state in case we are preempted. In order to make
treclaim and clearing the thread's MSR[TS] atomic from a preemption
perspective when CONFIG_PREEMPT is set, preempt_disable/enable() is
used. It's also necessary to save the previous value of the thread's
MSR before get_tm_stackpointer() is called so that it can be exposed
to the signal handler later in setup_tm_sigcontexts() to inform the
userspace MSR at the moment of the signal delivery.

Found with tm-signal-context-force-tm kernel selftest.

Fixes: 2b0a576d15 ("powerpc: Add new transactional memory state to the signal context")
Cc: stable@vger.kernel.org # v3.9
Signed-off-by: Gustavo Luiz Duarte <gustavold@linux.ibm.com>
Acked-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20200211033831.11165-1-gustavold@linux.ibm.com
2020-02-18 21:30:42 +11:00

227 lines
6.2 KiB
C

/*
* Common signal handling code for both 32 and 64 bits
*
* Copyright (c) 2007 Benjamin Herrenschmidt, IBM Corporation
* Extracted from signal_32.c and signal_64.c
*
* This file is subject to the terms and conditions of the GNU General
* Public License. See the file README.legal in the main directory of
* this archive for more details.
*/
#include <linux/tracehook.h>
#include <linux/signal.h>
#include <linux/uprobes.h>
#include <linux/key.h>
#include <linux/context_tracking.h>
#include <linux/livepatch.h>
#include <linux/syscalls.h>
#include <asm/hw_breakpoint.h>
#include <linux/uaccess.h>
#include <asm/unistd.h>
#include <asm/debug.h>
#include <asm/tm.h>
#include "signal.h"
/* Log an error when sending an unhandled signal to a process. Controlled
* through debug.exception-trace sysctl.
*/
int show_unhandled_signals = 1;
/*
* Allocate space for the signal frame
*/
void __user *get_sigframe(struct ksignal *ksig, unsigned long sp,
size_t frame_size, int is_32)
{
unsigned long oldsp, newsp;
/* Default to using normal stack */
oldsp = get_clean_sp(sp, is_32);
oldsp = sigsp(oldsp, ksig);
newsp = (oldsp - frame_size) & ~0xFUL;
/* Check access */
if (!access_ok((void __user *)newsp, oldsp - newsp))
return NULL;
return (void __user *)newsp;
}
static void check_syscall_restart(struct pt_regs *regs, struct k_sigaction *ka,
int has_handler)
{
unsigned long ret = regs->gpr[3];
int restart = 1;
/* syscall ? */
if (TRAP(regs) != 0x0C00)
return;
/* error signalled ? */
if (!(regs->ccr & 0x10000000))
return;
switch (ret) {
case ERESTART_RESTARTBLOCK:
case ERESTARTNOHAND:
/* ERESTARTNOHAND means that the syscall should only be
* restarted if there was no handler for the signal, and since
* we only get here if there is a handler, we dont restart.
*/
restart = !has_handler;
break;
case ERESTARTSYS:
/* ERESTARTSYS means to restart the syscall if there is no
* handler or the handler was registered with SA_RESTART
*/
restart = !has_handler || (ka->sa.sa_flags & SA_RESTART) != 0;
break;
case ERESTARTNOINTR:
/* ERESTARTNOINTR means that the syscall should be
* called again after the signal handler returns.
*/
break;
default:
return;
}
if (restart) {
if (ret == ERESTART_RESTARTBLOCK)
regs->gpr[0] = __NR_restart_syscall;
else
regs->gpr[3] = regs->orig_gpr3;
regs->nip -= 4;
regs->result = 0;
} else {
regs->result = -EINTR;
regs->gpr[3] = EINTR;
regs->ccr |= 0x10000000;
}
}
static void do_signal(struct task_struct *tsk)
{
sigset_t *oldset = sigmask_to_save();
struct ksignal ksig = { .sig = 0 };
int ret;
int is32 = is_32bit_task();
BUG_ON(tsk != current);
get_signal(&ksig);
/* Is there any syscall restart business here ? */
check_syscall_restart(tsk->thread.regs, &ksig.ka, ksig.sig > 0);
if (ksig.sig <= 0) {
/* No signal to deliver -- put the saved sigmask back */
restore_saved_sigmask();
tsk->thread.regs->trap = 0;
return; /* no signals delivered */
}
#ifndef CONFIG_PPC_ADV_DEBUG_REGS
/*
* Reenable the DABR before delivering the signal to
* user space. The DABR will have been cleared if it
* triggered inside the kernel.
*/
if (tsk->thread.hw_brk.address && tsk->thread.hw_brk.type)
__set_breakpoint(&tsk->thread.hw_brk);
#endif
/* Re-enable the breakpoints for the signal stack */
thread_change_pc(tsk, tsk->thread.regs);
rseq_signal_deliver(&ksig, tsk->thread.regs);
if (is32) {
if (ksig.ka.sa.sa_flags & SA_SIGINFO)
ret = handle_rt_signal32(&ksig, oldset, tsk);
else
ret = handle_signal32(&ksig, oldset, tsk);
} else {
ret = handle_rt_signal64(&ksig, oldset, tsk);
}
tsk->thread.regs->trap = 0;
signal_setup_done(ret, &ksig, test_thread_flag(TIF_SINGLESTEP));
}
void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
{
user_exit();
/* Check valid addr_limit, TIF check is done there */
addr_limit_user_check();
if (thread_info_flags & _TIF_UPROBE)
uprobe_notify_resume(regs);
if (thread_info_flags & _TIF_PATCH_PENDING)
klp_update_patch_state(current);
if (thread_info_flags & _TIF_SIGPENDING) {
BUG_ON(regs != current->thread.regs);
do_signal(current);
}
if (thread_info_flags & _TIF_NOTIFY_RESUME) {
clear_thread_flag(TIF_NOTIFY_RESUME);
tracehook_notify_resume(regs);
rseq_handle_notify_resume(NULL, regs);
}
user_enter();
}
unsigned long get_tm_stackpointer(struct task_struct *tsk)
{
/* When in an active transaction that takes a signal, we need to be
* careful with the stack. It's possible that the stack has moved back
* up after the tbegin. The obvious case here is when the tbegin is
* called inside a function that returns before a tend. In this case,
* the stack is part of the checkpointed transactional memory state.
* If we write over this non transactionally or in suspend, we are in
* trouble because if we get a tm abort, the program counter and stack
* pointer will be back at the tbegin but our in memory stack won't be
* valid anymore.
*
* To avoid this, when taking a signal in an active transaction, we
* need to use the stack pointer from the checkpointed state, rather
* than the speculated state. This ensures that the signal context
* (written tm suspended) will be written below the stack required for
* the rollback. The transaction is aborted because of the treclaim,
* so any memory written between the tbegin and the signal will be
* rolled back anyway.
*
* For signals taken in non-TM or suspended mode, we use the
* normal/non-checkpointed stack pointer.
*/
unsigned long ret = tsk->thread.regs->gpr[1];
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
BUG_ON(tsk != current);
if (MSR_TM_ACTIVE(tsk->thread.regs->msr)) {
preempt_disable();
tm_reclaim_current(TM_CAUSE_SIGNAL);
if (MSR_TM_TRANSACTIONAL(tsk->thread.regs->msr))
ret = tsk->thread.ckpt_regs.gpr[1];
/*
* If we treclaim, we must clear the current thread's TM bits
* before re-enabling preemption. Otherwise we might be
* preempted and have the live MSR[TS] changed behind our back
* (tm_recheckpoint_new_task() would recheckpoint). Besides, we
* enter the signal handler in non-transactional state.
*/
tsk->thread.regs->msr &= ~MSR_TS_MASK;
preempt_enable();
}
#endif
return ret;
}