[Linux-ia64] Re: kernel update (relative to 2.4.18)

[Xavier Bru <Xavier.Bru@bull.net>]

David, Ken

Thanks for the patch that fixed this one :-)
unfortunately, we have other problems with the Itanium-2 based new memcopy
routines, and new Ooops running the ltp test suite (test system calls
with wrong arguments :-).
I identified problems due to missing static exception handler
definitions. A potential patch could be:

--- l.ref/arch/ia64/lib/memcpy_mck.S	Tue Jun 25 11:52:22 2002
+++ l/arch/ia64/lib/memcpy_mck.S	Wed Jul  3 09:21:15 2002
@@ -178,7 +178,7 @@
 	and	r21=-8,tmp
 	;;
 EX(.ex_handler, (p8)	ld8	t3=[src1])
-EK(.ex_handler, (p6)	st8	[dst0]=t1)	// store byte 1
+EX(.ex_handler, (p6)	st8	[dst0]=t1)	// store byte 1 
 	and	in2=7,tmp	// remaining length
 EX(.ex_handler, (p7)	st8	[dst1]=t2,8)	// store byte 2
 	add	src0=src0,r21	// setting up src pointer
@@ -215,7 +215,7 @@
 	// same as .line_copy loop, but with all predicated-off instructions removed:
 .prefetch_loop:
 EX(.ex_handler_lcpy, (p[A])	ld8 v[A] = [src_pre_mem], 128)		// M0
-EK(.ex_handler_lcpy, (p[B])	st8 [dst_pre_mem] = v[B], 128)		// M2
+EX(.ex_handler_lcpy, (p[B])	st8 [dst_pre_mem] = v[B], 128)		// M2 
 	br.ctop.sptk .prefetch_loop
 	;;
 	cmp.eq p16, p0 = r0, r0			// reset p16 to 1

But this seems not sufficient: we also are facing recursive calls to
__copy_user due to exeception management when running the
ex_handler_short path.

Herafter some traces:

Problem 1 (missing EX handler, fixed by patch).
-----------------------------------------------
Entering kdb (current=0xe000000012df8000, pid 2742) on processor 0 Oops: <NULL>
due to oops @ 0xe00000000489d1a1
 psr: 0x0000121008026018   ifs: 0x800000000000cc18    ip: 0xe00000000489d1a0  
unat: 0x0000000000000000   pfs: 0x000000000000038a   rsc: 0x0000000000000003  
rnat: 0x0000000000000000  bsps: 0x0000000000000000    pr: 0x00000000000105e9  
ldrs: 0x0000000000000000   ccv: 0x0000000000000000  fpsr: 0x0009804c0270033f  
  b0: 0xe000000004425a40    b6: 0xe000000004401370    b7: 0x0000000000000000  
  r1: 0xe000000004e50450    r2: 0xe000000012dffec8    r3: 0xe000000012dffed8  
  r8: 0x0000000000000000    r9: 0xffffffffffffffff   r10: 0x0000000000000000  
 r11: 0x00000000000005e9   r12: 0xe000000012dffd50   r13: 0xe000000012df8000  
 r14: 0x60000fffff7fb510   r15: 0xe000000012dffec8   r16: 0x0000000000000018  
 r17: 0x60000fffff7fb510   r18: 0x60000fffff7fb518   r19: 0xe000000012dfff48  
 r20: 0x60000fffff7fb590   r21: 0x0000000000000018   r22: 0x60000fffff7fb4a8  
 r23: 0x600000000000f458   r24: 0xc000000000000692   r25: 0x60000fffff7fdb50  
 r26: 0xfffffffffffffff2   r27: 0x60000fffff7fb500   r28: 0x0000000000000000  
 r29: 0x0000000000000000   r30: 0x0000000000000018   r31: 0x000000000000038a  
&regs = e000000012dffbc0
[0]kdb> bt
0xe00000000489d1a0 __copy_user+0x160
        args (0x60000fffff7fb510, 0xe000000012dffec8, 0x18, 0x80000000f, 0x80200000000)
        kernel .text 0xe000000004400000 0xe00000000489d040 0xe00000000489d940
0xe000000004425a40 setup_sigcontext+0x320
        args (0x60000fffff7fb440, 0x60000fffff7fb4a0, 0xe000000012dffe60, 0xfffffffffffffff2, 0xe000000012dffe70)
        kernel .text 0xe000000004400000 0xe000000004425720 0xe000000004425b00
0xe000000004425e10 setup_frame+0x310
        args (0xb, 0xe00000001219b878, 0xfffffffffffffff2, 0xe000000012df8f00, 0xe000000012dffe60)
        kernel .text 0xe000000004400000 0xe000000004425b00 0xe000000004425f40
0xe000000004426170 handle_signal+0x230
        args (0xb, 0xe00000001219b878, 0xe000000012dffde0, 0xe000000012df8f00, 0xe000000012dffe60)
        kernel .text 0xe000000004400000 0xe000000004425f40 0xe000000004426180
0xe000000004426560 ia64_do_signal+0x3e0
        args (0xe000000012df8f00, 0xe000000012dffe60, 0x0, 0xb, 0xe00000001219b878)
        kernel .text 0xe000000004400000 0xe000000004426180 0xe000000004426a40
0xe00000000440a350 handle_signal_delivery+0x30
        args (0x80000000f, 0xa0200000000, 0xe000000012dffde4, 0x800000004, 0xe000000012dffdfc)
        kernel .text 0xe000000004400000 0xe00000000440a320 0xe00000000440a380
0xe000000004409f90 ia64_leave_kernel+0x70
        args (0x80000000f, 0xa0200000000, 0xe000000012dffde4)
        kernel .text 0xe000000004400000 0xe000000004409f20
0xe00000000440a1b0

Problem 2(recursive call to __copy_user)
---------
[0]kdb> bt
0xe00000000489d840 __copy_user+0x800
        args (0xffffffff, 0xe0000000143f7c10, 0x14, 0xe0000000045dfec0)
        kernel .text 0xe000000004400000 0xe00000000489d040 0xe00000000489d940
0xe0000000045e06e0 semctl_main+0x9c0
        args (0xe00000001bdf6ad8, 0xfffffffbfff, 0xe000000004c839a0, 0xe000000004c83970, 0xffffffff)
        kernel .text 0xe000000004400000 0xe0000000045dfd20 0xe0000000045e0780
0xe0000000045e0f00 sys_semctl+0x1c0
        args (0x8001, 0x0, 0xd, 0xffffffff, 0x80100)
				XXXXXXXXXXX 
        kernel .text 0xe000000004400000 0xe0000000045e0d40 0xe0000000045e0f20
0xe000000004409f00 ia64_ret_from_syscall
        args (0x8001, 0x0, 0xd, 0xffffffff)
        kernel .text 0xe000000004400000 0xe000000004409f00 0xe000000004409f20
[0]kdb> go
...

[0]kdb> bt
0xe00000000489d840 __copy_user+0x800
        args (0xffffffff, 0xe0000000143f7c10, 0x1)
        kernel .text 0xe000000004400000 0xe00000000489d040 0xe00000000489d940
0xe00000000489d900 __copy_user+0x8c0
        args (0x100000000, 0x0, 0x1, 0x0, 0xe00000000489d900)
        kernel .text 0xe000000004400000 0xe00000000489d040 0xe00000000489d940
0xe00000000489d900 __copy_user+0x8c0
        args (0x100000000, 0x0, 0x14, 0x13, 0xe0000000045e06e0)
        kernel .text 0xe000000004400000 0xe00000000489d040 0xe00000000489d940
0xe00000000489d900 __copy_user+0x8c0
        args (0xa, 0xa, 0xe0000000143f7c10, 0xe0000000045e0f00, 0x794)
        kernel .text 0xe000000004400000 0xe00000000489d040 0xe00000000489d940
0xe00000000489d900 __copy_user+0x8c0
        args (0xfffffffbfff, 0xe000000004c839a0, 0xe000000004c83970, 0xffffffff, 0x0)
        kernel .text 0xe000000004400000 0xe00000000489d040 0xe00000000489d940
0xe00000000489d900 __copy_user+0x8c0
        args (0x0, 0xffffffff, 0x1, 0xe000000004409f00, 0x4)
        kernel .text 0xe000000004400000 0xe00000000489d040 0xe00000000489d940
0xe00000000489d900 __copy_user+0x8c0
        args (0x80100, 0xe0000000143f7cd0, 0xe000000004409f20, 0x2, 0x8001)
        kernel .text 0xe000000004400000 0xe00000000489d040 0xe00000000489d940
0xe00000000489d900 __copy_user+0x8c0
[0]more> 
        args (0xc00000000000050d, 0x60000fffffffb9c0, 0x8001, 0x0, 0xd)
        kernel .text 0xe000000004400000 0xe00000000489d040 0xe00000000489d940
[0]kdb> 

Thanks for your help...
Xavier

David Mosberger writes:
 > >>>>> On Wed, 26 Jun 2002 19:30:48 +0200 (DFT), Xavier Bru  <Xavier.Bru@bull.net> said:
 > 
 >   Xavier> It seems that null pointers passed as argument to syscalls
 >   Xavier> by wrong user code now generate a Oops, and enter kdb if
 >   Xavier> enabled.
 > 
 > I haven't seen a fix from Ken yet, so the patch below comes live from OLS...
 > Please test heavily and let me know how it goes.
 > 
 > Thanks,
 > 
 > 	--david
 > 
 > --- lia64-2.4/arch/ia64/kernel/traps.c~	Thu Jun 20 18:56:08 2002
 > +++ lia64-2.4/arch/ia64/kernel/traps.c	Fri Jun 28 12:15:58 2002
 > @@ -497,7 +497,8 @@
 >  			siginfo.si_isr = isr;
 >  			force_sig_info(sig, &siginfo, current);
 >  			return;
 > -		}
 > +		} else if (done_with_exception(regs))
 > +			return;
 >  		sprintf(buf, "NaT consumption");
 >  		break;
 >