From: Maynard J. <may...@us...> - 2013-04-30 13:30:22
|
On 04/29/2013 08:13 PM, Langley, Scott E wrote: > Hi Folks, > > I've trying to build OProfile from the latest source on a machine running SUSE Enterprise Desktop Linux 11 SP2 with a recent Intel core7 CPU and I'm encountering the following error: > > Making all in libperf_events > make[2]: Entering directory `/local_static/git/oprofile/libperf_events' > g++ -DHAVE_CONFIG_H -I. -I.. -I ../libabi -I ../libutil -I ../libutil++ -I ../libop -I ../libdb -I ../libperf_events -g -O2 -MT operf_utils.o -MD -MP -MF .deps/operf_utils.Tpo -c -o operf_utils.o operf_utils.cpp > mv -f .deps/operf_utils.Tpo .deps/operf_utils.Po > g++ -DHAVE_CONFIG_H -I. -I.. -I ../libabi -I ../libutil -I ../libutil++ -I ../libop -I ../libdb -I ../libperf_events -g -O2 -MT operf_counter.o -MD -MP -MF .deps/operf_counter.Tpo -c -o operf_counter.o operf_counter.cpp > operf_counter.cpp: In constructor 'operf_counter::operf_counter(operf_event_t&, bool, bool, bool, bool, int)': > operf_counter.cpp:211: error: 'struct perf_event_attr' has no member named 'precise_ip' > make[2]: *** [operf_counter.o] Error 1 *Andi*, the code that's failing to compile above was added in a patch you contributed (and which I accepted) on Oct 31, 2012. We did not take into consideration that the precise_ip field did not exist in earlier versions of perf_event.h. Below is a partial patch to fix this problem. It defines a new macro, HAVE_PERF_PRECISE_IP, which will be set to '1' if the field exists or '0' otherwise. What's missing in the patch is what to do -- if anything -- if HAVE_PERF_PRECISE_IP is '0'. Can you help with that part of the patch, please. Thanks! -Maynard Index: op-master/configure.ac =================================================================== --- op-master.orig/configure.ac +++ op-master/configure.ac @@ -156,6 +156,25 @@ if test "$kernel_has_perf_events_support fi AC_DEFINE_UNQUOTED(HAVE_PERF_GUEST_MACROS, $HAVE_PERF_GUEST_MACROS, [PERF_RECORD_MISC_GUEST_KERNEL is defined in perf_event.h]) rm -f test-for-PERF_GUEST* + + AC_MSG_CHECKING([whether precise_ip is defined in perf_event.h]) + rm -f test-for-precise-ip + AC_LANG_CONFTEST( + [AC_LANG_PROGRAM([[#include <linux/perf_event.h>]], + [[struct perf_event_attr attr; + attr.precise_ip = 2;]]) + ]) + $CC conftest.$ac_ext $CFLAGS $LDFLAGS $LIBS $PERF_EVENT_FLAGS -o test-for-precise-ip > /dev/null 2>&1 + if test -f test-for-precise-ip; then + echo "yes" + HAVE_PERF_PRECISE_IP='1' + else + echo "no" + HAVE_PERF_PRECISE_IP='0' + fi + AC_DEFINE_UNQUOTED(HAVE_PERF_PRECISE_IP, $HAVE_PERF_PRECISE_IP, [precise_ip is defined in perf_event.h]) + rm -f test-for-precise-ip* + else HAVE_PERF_EVENTS='0' AC_MSG_RESULT([No perf_events support available; falling back to legacy oprofile]) Index: op-master/libperf_events/operf_counter.cpp =================================================================== --- op-master.orig/libperf_events/operf_counter.cpp +++ op-master/libperf_events/operf_counter.cpp @@ -206,7 +206,7 @@ operf_counter::operf_counter(operf_event if (separate_cpu) attr.sample_type |= PERF_SAMPLE_CPU; attr.type = PERF_TYPE_RAW; -#if defined(__i386__) || defined(__x86_64__) +#if ((defined(__i386__) || defined(__x86_64__)) && (HAVE_PERF_PRECISE_IP)) if (evt.evt_code & EXTRA_PEBS) { attr.precise_ip = 2; evt.evt_code ^= EXTRA_PEBS; -------------------------------------------- > > > Here are my machine specs: > > uname -a > Linux hyena 3.0.38-0.5-default #1 SMP Fri Aug 3 09:02:17 UTC 2012 (358029e) x86_64 x86_64 x86_64 GNU/Linux > > cat /etc/SuSE-release > SUSE Linux Enterprise Desktop 11 (x86_64) > VERSION = 11 > PATCHLEVEL = 2 > > cat /proc/cpuinfo > processor : 0 > vendor_id : GenuineIntel > cpu family : 6 > model : 58 > model name : Intel(R) Core(TM) i7-3770 CPU @ 3.40GHz > stepping : 9 > cpu MHz : 1600.000 > cache size : 8192 KB > physical id : 0 > siblings : 8 > core id : 0 > cpu cores : 4 > apicid : 0 > initial apicid : 0 > fpu : yes > fpu_exception : yes > cpuid level : 13 > wp : yes > flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm sse4_1 sse4_2 x2apic popcnt aes xsave avx f16c rdrand lahf_lm ida arat epb xsaveopt pln pts dtherm tpr_shadow vnmi flexpriority ept vpid fsgsbase smep erms > bogomips : 6785.06 > clflush size : 64 > cache_alignment : 64 > address sizes : 36 bits physical, 48 bits virtual > power management: > ... > > Any help or suggestions would be appreciated. > > Thanks. > |