Hi,
back again with some more info. Here are parts of the dump of the
assembler code for tm_log_unroll
0x0001aedc <tm_log_unroll+0>: save %sp, -136, %sp
0x0001aee0 <tm_log_unroll+4>: mov %i0, %g5
0x0001aee4 <tm_log_unroll+8>: st %g5, [ %fp + 0x44 ]
0x0001aee8 <tm_log_unroll+12>: b 0x1aef0 <tm_log_unroll+20>
0x0001aeec <tm_log_unroll+16>: nop
0x0001aef0 <tm_log_unroll+20>: sethi %hi(0x30400), %g5
0x0001aef4 <tm_log_unroll+24>: add %g5, 0xa8, %o2 ! 0x304a8
<threadTransContext>
0x0001aef8 <tm_log_unroll+28>: ld [ %o2 ], %o3
0x0001aefc <tm_log_unroll+32>: ld [ %fp + 0x44 ], %o4
0x0001af00 <tm_log_unroll+36>: sll %o4, 2, %o5
0x0001af04 <tm_log_unroll+40>: ld [ %o3 + %o5 ], %o4
0x0001af08 <tm_log_unroll+44>: sethi %hi(0x1000), %o5
0x0001af0c <tm_log_unroll+48>: add %o5, 0x20, %o7 ! 0x1020
0x0001af10 <tm_log_unroll+52>: add %o4, %o7, %l0
0x0001af14 <tm_log_unroll+56>: st %l0, [ %sp + 0x7c ]
0x0001af18 <tm_log_unroll+60>: sethi %hi(0x30400), %l1
0x0001af1c <tm_log_unroll+64>: add %l1, 0xa8, %l2 ! 0x304a8
<threadTransContext>
0x0001af20 <tm_log_unroll+68>: ld [ %l2 ], %l3
0x0001af24 <tm_log_unroll+72>: ld [ %fp + 0x44 ], %l4
0x0001af28 <tm_log_unroll+76>: sll %l4, 2, %l5
0x0001af2c <tm_log_unroll+80>: ld [ %l3 + %l5 ], %l4
0x0001af30 <tm_log_unroll+84>: sethi %hi(0x1000), %l5
0x0001af34 <tm_log_unroll+88>: add %l5, 0x10, %l6 ! 0x1010
0x0001af38 <tm_log_unroll+92>: ld [ %l4 + %l6 ], %l5
0x0001af3c <tm_log_unroll+96>: st %l5, [ %sp + 0x78 ]
0x0001af40 <tm_log_unroll+100>: ld [ %sp + 0x78 ], %l6
0x0001af44 <tm_log_unroll+104>: srl %l6, 2, %l7
0x0001af48 <tm_log_unroll+108>: sll %l7, 2, %g5
0x0001af4c <tm_log_unroll+112>: ld [ %sp + 0x7c ], %o2
0x0001af50 <tm_log_unroll+116>: add %o2, %g5, %o3
0x0001af54 <tm_log_unroll+120>: st %o3, [ %sp + 0x74 ]
0x0001af58 <tm_log_unroll+124>: sethi %hi(0x30400), %o4
0x0001af5c <tm_log_unroll+128>: add %o4, 0xa8, %o5 ! 0x304a8
<threadTransContext>
0x0001af60 <tm_log_unroll+132>: ld [ %o5 ], %o7
0x0001af64 <tm_log_unroll+136>: ld [ %fp + 0x44 ], %l0
0x0001af68 <tm_log_unroll+140>: sll %l0, 2, %l1
0x0001af6c <tm_log_unroll+144>: ld [ %o7 + %l1 ], %l0
0x0001af70 <tm_log_unroll+148>: sethi %hi(0x1000), %l1
0x0001af74 <tm_log_unroll+152>: add %l1, 0x14, %l2 ! 0x1014
0x0001af78 <tm_log_unroll+156>: ld [ %l0 + %l2 ], %l1
0x0001af7c <tm_log_unroll+160>: st %l1, [ %sp + 0x70 ]
0x0001af80 <tm_log_unroll+164>: sethi %hi(0x30400), %l2
0x0001af84 <tm_log_unroll+168>: add %l2, 0xa8, %l3 ! 0x304a8
<threadTransContext>
0x0001af88 <tm_log_unroll+172>: ld [ %l3 ], %l4
0x0001af8c <tm_log_unroll+176>: ld [ %fp + 0x44 ], %l5
0x0001af90 <tm_log_unroll+180>: sll %l5, 2, %l6
0x0001af94 <tm_log_unroll+184>: ld [ %l4 + %l6 ], %l5
0x0001af98 <tm_log_unroll+188>: sethi %hi(0x1000), %l6
0x0001af9c <tm_log_unroll+192>: add %l6, 8, %l7 ! 0x1008
0x0001afa0 <tm_log_unroll+196>: ld [ %l5 + %l7 ], %l6
0x0001afa4 <tm_log_unroll+200>: st %l6, [ %sp + 0x6c ]
0x0001afa8 <tm_log_unroll+204>: sethi %hi(0x30400), %l7
0x0001afac <tm_log_unroll+208>: add %l7, 0xa8, %g5 ! 0x304a8
<threadTransContext>
0x0001afb0 <tm_log_unroll+212>: ld [ %g5 ], %o2
0x0001afb4 <tm_log_unroll+216>: ld [ %fp + 0x44 ], %o3
0x0001afb8 <tm_log_unroll+220>: sll %o3, 2, %o4
0x0001afbc <tm_log_unroll+224>: ld [ %o2 + %o4 ], %o3
0x0001afc0 <tm_log_unroll+228>: sethi %hi(0x1000), %o4
0x0001afc4 <tm_log_unroll+232>: ld [ %o3 + %o4 ], %o5
0x0001afc8 <tm_log_unroll+236>: st %o5, [ %sp + 0x80 ]
0x0001afcc <tm_log_unroll+240>: clr [ %sp + 0x68 ]
......................................
**** code for while loop (omitted) *****
.......................................
0x0001b1bc <tm_log_unroll+736>: nop
0x0001b1c0 <tm_log_unroll+740>: b 0x1b1c8 <tm_log_unroll+748>
0x0001b1c4 <tm_log_unroll+744>: nop
0x0001b1c8 <tm_log_unroll+748>: ld [ %sp + 0x70 ], %g5
0x0001b1cc <tm_log_unroll+752>: cmp %g5, 0
0x0001b1d0 <tm_log_unroll+756>: bgu,pn %icc, 0x1b1e0
<tm_log_unroll+772>
0x0001b1d4 <tm_log_unroll+760>: nop
0x0001b1d8 <tm_log_unroll+764>: b 0x1b200 <tm_log_unroll+804>
0x0001b1dc <tm_log_unroll+768>: nop
0x0001b1e0 <tm_log_unroll+772>: ld [ %sp + 0x70 ], %g5
0x0001b1e4 <tm_log_unroll+776>: ld [ %fp + 0x44 ], %o2
0x0001b1e8 <tm_log_unroll+780>: mov %g5, %o0
0x0001b1ec <tm_log_unroll+784>: mov %o2, %o1
0x0001b1f0 <tm_log_unroll+788>: call 0x1a960 <randomized_backoff>
0x0001b1f4 <tm_log_unroll+792>: nop
0x0001b1f8 <tm_log_unroll+796>: b 0x1b200 <tm_log_unroll+804>
0x0001b1fc <tm_log_unroll+800>: nop
0x0001b200 <tm_log_unroll+804>: sethi %hi(0x8ae000), %g00
0x0001b204 <tm_log_unroll+808>: sethi %hi(0x30400), %g5
0x0001b208 <tm_log_unroll+812>: add %g5, 0xa8, %o2 ! 0x304a8
<threadTransContext>
0x0001b20c <tm_log_unroll+816>: ld [ %o2 ], %o3
0x0001b210 <tm_log_unroll+820>: ld [ %fp + 0x44 ], %o4
0x0001b214 <tm_log_unroll+824>: sll %o4, 2, %o5
0x0001b218 <tm_log_unroll+828>: ld [ %o3 + %o5 ], %o4
0x0001b21c <tm_log_unroll+832>: ld [ %sp + 0x68 ], %o5
0x0001b220 <tm_log_unroll+836>: sethi %hi(0x1000), %o7
0x0001b224 <tm_log_unroll+840>: add %o7, 4, %l0 ! 0x1004
0x0001b228 <tm_log_unroll+844>: st %o5, [ %o4 + %l0 ]
0x0001b22c <tm_log_unroll+848>: sethi %hi(0x30400), %l1
0x0001b230 <tm_log_unroll+852>: add %l1, 0xa8, %l2 ! 0x304a8
<threadTransContext>
0x0001b234 <tm_log_unroll+856>: ld [ %l2 ], %l3
0x0001b238 <tm_log_unroll+860>: ld [ %fp + 0x44 ], %l4
0x0001b23c <tm_log_unroll+864>: sll %l4, 2, %l5
0x0001b240 <tm_log_unroll+868>: ld [ %l3 + %l5 ], %l4
0x0001b244 <tm_log_unroll+872>: ld [ %sp + 0x6c ], %l5
0x0001b248 <tm_log_unroll+876>: sethi %hi(0x1000), %l6
0x0001b24c <tm_log_unroll+880>: add %l6, 8, %l7 ! 0x1008
0x0001b250 <tm_log_unroll+884>: st %l5, [ %l4 + %l7 ]
0x0001b254 <tm_log_unroll+888>: sethi %hi(0x30400), %g5
0x0001b258 <tm_log_unroll+892>: add %g5, 0xa8, %o2 ! 0x304a8
<threadTransContext>
0x0001b25c <tm_log_unroll+896>: ld [ %o2 ], %o3
0x0001b260 <tm_log_unroll+900>: ld [ %fp + 0x44 ], %o4
0x0001b264 <tm_log_unroll+904>: sll %o4, 2, %o5
0x0001b268 <tm_log_unroll+908>: ld [ %o3 + %o5 ], %o4
0x0001b26c <tm_log_unroll+912>: ld [ %sp + 0x78 ], %o5
0x0001b270 <tm_log_unroll+916>: sethi %hi(0x1000), %o7
0x0001b274 <tm_log_unroll+920>: add %o7, 0x10, %l0 ! 0x1010
0x0001b278 <tm_log_unroll+924>: st %o5, [ %o4 + %l0 ]
0x0001b27c <tm_log_unroll+928>: sethi %hi(0x8ae000), %g0
0x0001b280 <tm_log_unroll+932>: b 0x1b288 <tm_log_unroll+940>
0x0001b284 <tm_log_unroll+936>: nop
0x0001b288 <tm_log_unroll+940>: ret
0x0001b28c <tm_log_unroll+944>: restore
End of assembler dump.
As you can see the handler uses mem [%fp + 0x44] to access the
threadTransContext and at the start it stores at this location register
%g5 which at the moment of execution is 0. Now, the first two times the
handler is called everything works fine and the transaction is restarted
correctly. However the third time it is called something goes wrong. So
I added a breakpoint to monitor read and writes to that address (as I
thought that there is a memory race and a stray write from some other
cpu destroys the correct values). However, the write happens from the
cpu that runs the software hanlder and it happens inside
tm_unroll_log_entry (which is called inside the while loop). The dump of
tm_unroll_log_entry is the following :
Dump of assembler code for function tm_unroll_log_entry:
0x0001ab6c <tm_unroll_log_entry+0>: ld [ %o0 + 0x40 ], %o5
0x0001ab70 <tm_unroll_log_entry+4>: mov %o0, %o4
0x0001ab74 <tm_unroll_log_entry+8>: and %o5, -64, %o5
0x0001ab78 <tm_unroll_log_entry+12>: sub %o5, %o0, %o3
0x0001ab7c <tm_unroll_log_entry+16>: sra %o3, 0x1f, %o1
0x0001ab80 <tm_unroll_log_entry+20>: xor %o3, %o1, %o2
0x0001ab84 <tm_unroll_log_entry+24>: sub %o2, %o1, %o0
0x0001ab88 <tm_unroll_log_entry+28>: cmp %o0, 0x40
0x0001ab8c <tm_unroll_log_entry+32>: bl,a,pn %icc, 0x1ac1c
<tm_unroll_log_entry+176>
0x0001ab90 <tm_unroll_log_entry+36>: ld [ %o4 ], %g5
0x0001ab94 <tm_unroll_log_entry+40>: ld [ %o4 ], %o2
0x0001ab98 <tm_unroll_log_entry+44>: ld [ %o4 + 4 ], %o1
0x0001ab9c <tm_unroll_log_entry+48>: ld [ %o4 + 8 ], %o0
0x0001aba0 <tm_unroll_log_entry+52>: st %o2, [ %o5 ]
0x0001aba4 <tm_unroll_log_entry+56>: st %o1, [ %o5 + 4 ]
0x0001aba8 <tm_unroll_log_entry+60>: st %o0, [ %o5 + 8 ]
0x0001abac <tm_unroll_log_entry+64>: ld [ %o4 + 0xc ], %g5
0x0001abb0 <tm_unroll_log_entry+68>: ld [ %o4 + 0x10 ], %g1
0x0001abb4 <tm_unroll_log_entry+72>: ld [ %o4 + 0x14 ], %o3
0x0001abb8 <tm_unroll_log_entry+76>: ld [ %o4 + 0x18 ], %o2
0x0001abbc <tm_unroll_log_entry+80>: ld [ %o4 + 0x1c ], %o1
0x0001abc0 <tm_unroll_log_entry+84>: ld [ %o4 + 0x20 ], %o0
0x0001abc4 <tm_unroll_log_entry+88>: st %g5, [ %o5 + 0xc ]
0x0001abc8 <tm_unroll_log_entry+92>: st %g1, [ %o5 + 0x10 ]
0x0001abcc <tm_unroll_log_entry+96>: st %o3, [ %o5 + 0x14 ]
0x0001abd0 <tm_unroll_log_entry+100>: st %o2, [ %o5 + 0x18 ]
0x0001abd4 <tm_unroll_log_entry+104>: st %o1, [ %o5 + 0x1c ]
0x0001abd8 <tm_unroll_log_entry+108>: st %o0, [ %o5 + 0x20 ]
0x0001abdc <tm_unroll_log_entry+112>: ld [ %o4 + 0x24 ], %g5
0x0001abe0 <tm_unroll_log_entry+116>: ld [ %o4 + 0x28 ], %g1
0x0001abe4 <tm_unroll_log_entry+120>: ld [ %o4 + 0x2c ], %o3
0x0001abe8 <tm_unroll_log_entry+124>: ld [ %o4 + 0x30 ], %o2
0x0001abec <tm_unroll_log_entry+128>: ld [ %o4 + 0x34 ], %o1
0x0001abf0 <tm_unroll_log_entry+132>: ld [ %o4 + 0x38 ], %o0
0x0001abf4 <tm_unroll_log_entry+136>: ld [ %o4 + 0x3c ], %o4
0x0001abf8 <tm_unroll_log_entry+140>: st %g5, [ %o5 + 0x24 ]
0x0001abfc <tm_unroll_log_entry+144>: st %g1, [ %o5 + 0x28 ]
0x0001ac00 <tm_unroll_log_entry+148>: st %o3, [ %o5 + 0x2c ]
0x0001ac04 <tm_unroll_log_entry+152>: st %o2, [ %o5 + 0x30 ]
0x0001ac08 <tm_unroll_log_entry+156>: st %o1, [ %o5 + 0x34 ]
0x0001ac0c <tm_unroll_log_entry+160>: st %o0, [ %o5 + 0x38 ]
0x0001ac10 <tm_unroll_log_entry+164>: st %o4, [ %o5 + 0x3c ]
0x0001ac14 <tm_unroll_log_entry+168>: retl
0x0001ac18 <tm_unroll_log_entry+172>: nop
0x0001ac1c <tm_unroll_log_entry+176>: st %g5, [ %o5 ]
0x0001ac20 <tm_unroll_log_entry+180>: ld [ %o4 + 4 ], %g1
0x0001ac24 <tm_unroll_log_entry+184>: st %g1, [ %o5 + 4 ]
0x0001ac28 <tm_unroll_log_entry+188>: ld [ %o4 + 8 ], %o3
0x0001ac2c <tm_unroll_log_entry+192>: st %o3, [ %o5 + 8 ]
0x0001ac30 <tm_unroll_log_entry+196>: ld [ %o4 + 0xc ], %o2
0x0001ac34 <tm_unroll_log_entry+200>: st %o2, [ %o5 + 0xc ]
0x0001ac38 <tm_unroll_log_entry+204>: ld [ %o4 + 0x10 ], %o1
0x0001ac3c <tm_unroll_log_entry+208>: st %o1, [ %o5 + 0x10 ]
0x0001ac40 <tm_unroll_log_entry+212>: ld [ %o4 + 0x14 ], %o0
0x0001ac44 <tm_unroll_log_entry+216>: st %o0, [ %o5 + 0x14 ]
0x0001ac48 <tm_unroll_log_entry+220>: ld [ %o4 + 0x18 ], %g5
0x0001ac4c <tm_unroll_log_entry+224>: st %g5, [ %o5 + 0x18 ]
0x0001ac50 <tm_unroll_log_entry+228>: ld [ %o4 + 0x1c ], %g1
0x0001ac54 <tm_unroll_log_entry+232>: st %g1, [ %o5 + 0x1c ]
0x0001ac58 <tm_unroll_log_entry+236>: ld [ %o4 + 0x20 ], %o3
0x0001ac5c <tm_unroll_log_entry+240>: st %o3, [ %o5 + 0x20 ]
0x0001ac60 <tm_unroll_log_entry+244>: ld [ %o4 + 0x24 ], %o2
0x0001ac64 <tm_unroll_log_entry+248>: st %o2, [ %o5 + 0x24 ]
0x0001ac68 <tm_unroll_log_entry+252>: ld [ %o4 + 0x28 ], %o1
0x0001ac6c <tm_unroll_log_entry+256>: st %o1, [ %o5 + 0x28 ]
0x0001ac70 <tm_unroll_log_entry+260>: ld [ %o4 + 0x2c ], %o0
0x0001ac74 <tm_unroll_log_entry+264>: st %o0, [ %o5 + 0x2c ]
0x0001ac78 <tm_unroll_log_entry+268>: ld [ %o4 + 0x30 ], %g5
0x0001ac7c <tm_unroll_log_entry+272>: st %g5, [ %o5 + 0x30 ]
0x0001ac80 <tm_unroll_log_entry+276>: ld [ %o4 + 0x34 ], %g1
0x0001ac84 <tm_unroll_log_entry+280>: st %g1, [ %o5 + 0x34 ]
0x0001ac88 <tm_unroll_log_entry+284>: ld [ %o4 + 0x38 ], %o3
0x0001ac8c <tm_unroll_log_entry+288>: st %o3, [ %o5 + 0x38 ]
0x0001ac90 <tm_unroll_log_entry+292>: ld [ %o4 + 0x3c ], %o4
0x0001ac94 <tm_unroll_log_entry+296>: retl
0x0001ac98 <tm_unroll_log_entry+300>: st %o4, [ %o5 + 0x3c ]
End of assembler dump.
The offending instruction is @ 0x1abc4 : st %g5, [ %o5 + 0xc ] which
goes and writes to the memory location the value of 4. So when the
handler returns to tm_log_unroll and tries to access [%fp+0x44] in order
to save the new xact_level and xact_log_size values it reads the wrong
values!
Any suggestions?????
Kind regards,
Kostis
I agree that a race should not occur. Could you try moving the
randomized_backoff call to the end of
the function so that the threadTransContext structures get updated right
after the while loop.
You might want to look and see if the simulator is passing the right
threadID to the software handlers
and if there are any stray simulator log writes from processor 2 to the
log of the first thread.
Jayaram
_______________________________________________
Gems-users mailing list
Gems-users@xxxxxxxxxxx
https://lists.cs.wisc.edu/mailman/listinfo/gems-users
Use Google to search the GEMS Users mailing list by adding "site:https://lists.cs.wisc.edu/archive/gems-users/"; to your search.
|
![[Computer Systems Lab]](http://www.cs.wisc.edu/pics/csl_logo.gif){kind=logo}