libpfm4 faults on P4 machine
On P4 machine, intel_x86_arch_support.get_event_info(...) faults because intel_x86_arch_support.pe is NULL.
intel_x86_arch_support.pe is set at run time, but P4 does not have arch event support, so intel_x86_arch_support.pe is always NULL.
#gdb libpfm4/examples/check_events
Program received signal SIGSEGV, Segmentation fault.
[Switching to Thread 0xb785caf0 (LWP 3950)]0x0804d74b in pfm_intel_x86_get_event_info (this=0x81c5f80, idx=0, info=0xbff45f14)
at pfmlib_intel_x86.c:667
667 info->desc = pe[idx].desc;
(gdb) bt
#0 0x0804d74b in pfm_intel_x86_get_event_info (this=0x81c5f80, idx=0, info=0xbff45f14)
at pfmlib_intel_x86.c:667
#1 0x08049cd3 in pfmlib_parse_event (event=0x804fb7b "PERF_COUNT_HW_CPU_CYCLES", d=0xbff45f7c)
at pfmlib_common.c:676
#2 0x08049f3f in pfm_get_event_encoding (str=0x804fb7b "PERF_COUNT_HW_CPU_CYCLES", dfl_plm=8,
fstr=0xbff464d4, idx=0xbff464c8, codes=0xbff464d0, count=0xbff464cc) at pfmlib_common.c:877#3 0x08048dc1 in main (argc=<value optimized out>, argv=0xbff46584) at check_events.c:118 (gdb) list
662
663 /*
664 * pmu and idx filled out by caller
665 */
666 info->name = pe[idx].name; 667 info->desc = pe[idx].desc; 668 info->code = pe[idx].code;
669 info->equiv = pe[idx].equiv;
670
671 /* unit masks + modifiers */
(gdb)
Any fix?
Lin Ming
Lin,
It should not have chosen intel_x86_arch to begin with. That's where the bug is. Let me fix this.
Quoted 39 lines · Lin Ming
On P4 machine,
intel_x86_arch_support.get_event_info(...)faults because intel_x86_arch_support.pe is NULL.intel_x86_arch_support.pe is set at run time, but P4 does not have arch event support, so intel_x86_arch_support.pe is always NULL.
#gdb libpfm4/examples/check_events
Program received signal SIGSEGV, Segmentation fault.
[Switching to Thread0xb785caf0(LWP 3950)]0x0804d74binpfm_intel_x86_get_event_info(this=0x81c5f80, idx=0, info=0xbff45f14) at pfmlib_intel_x86.c:667
667info->desc= pe[idx].desc;
(gdb) bt
#0 0x0804d74b inpfm_intel_x86_get_event_info(this=0x81c5f80, idx=0, info=0xbff45f14) at pfmlib_intel_x86.c:667
#1 0x08049cd3 inpfmlib_parse_event(event=0x804fb7b "PERF_COUNT_HW_CPU_CYCLES", d=0xbff45f7c) at pfmlib_common.c:676
#2 0x08049f3f inpfm_get_event_encoding(str=0x804fb7b "PERF_COUNT_HW_CPU_CYCLES", dfl_plm=8, fstr=0xbff464d4, idx=0xbff464c8, codes=0xbff464d0, count=0xbff464cc) at pfmlib_common.c:877 #3 0x08048dc1 in main (argc=<value optimized out>, argv=0xbff46584) at check_events.c:118 (gdb) list
662
663 /*
664 * pmu and idx filled out by caller
665 */
666info->name= pe[idx].name;
667info->desc= pe[idx].desc;
668info->code= pe[idx].code;
669info->equiv= pe[idx].equiv;
670
671 /* unit masks + modifiers */
(gdb)Any fix?
Lin Ming
Quoted 6 lines · stephane eranian
Lin,
It should not have chosen intel_x86_arch to begin with. That's where the bug is. Let me fix this.
Fixed in the git tree, just pull again.
Thanks for reporting this issue.
Quoted 41 lines · Lin Ming
Quoted 39 lines
On P4 machine,
intel_x86_arch_support.get_event_info(...)faults because intel_x86_arch_support.pe is NULL.intel_x86_arch_support.pe is set at run time, but P4 does not have arch event support, so intel_x86_arch_support.pe is always NULL.
#gdb libpfm4/examples/check_events
Program received signal SIGSEGV, Segmentation fault.
[Switching to Thread0xb785caf0(LWP 3950)]0x0804d74binpfm_intel_x86_get_event_info(this=0x81c5f80, idx=0, info=0xbff45f14) at pfmlib_intel_x86.c:667
667info->desc= pe[idx].desc;
(gdb) bt
#0 0x0804d74b inpfm_intel_x86_get_event_info(this=0x81c5f80, idx=0, info=0xbff45f14) at pfmlib_intel_x86.c:667
#1 0x08049cd3 inpfmlib_parse_event(event=0x804fb7b "PERF_COUNT_HW_CPU_CYCLES", d=0xbff45f7c) at pfmlib_common.c:676
#2 0x08049f3f inpfm_get_event_encoding(str=0x804fb7b "PERF_COUNT_HW_CPU_CYCLES", dfl_plm=8, fstr=0xbff464d4, idx=0xbff464c8, codes=0xbff464d0, count=0xbff464cc) at pfmlib_common.c:877 #3 0x08048dc1 in main (argc=<value optimized out>, argv=0xbff46584) at check_events.c:118 (gdb) list
662
663 /*
664 * pmu and idx filled out by caller
665 */
666info->name= pe[idx].name;
667info->desc= pe[idx].desc;
668info->code= pe[idx].code;
669info->equiv= pe[idx].equiv;
670
671 /* unit masks + modifiers */
(gdb)Any fix?
Lin Ming