<html><body><div style="font-family: arial,helvetica,sans-serif; font-size: 12pt; color: #000000"><div><br></div><div><br></div><div><span id="zwchr" data-marker="__DIVIDER__">----- On Aug 19, 2015, at 8:44 PM, Jason Evans <jasone@canonware.com> wrote:<br></span></div><div data-marker="__QUOTED_TEXT__"><blockquote style="border-left: 2px solid #1010FF; margin-left: 5px; padding-left: 5px; color: #000; font-weight: normal; font-style: normal; text-decoration: none; font-family: Helvetica,Arial,sans-serif; font-size: 12pt;" data-mce-style="border-left: 2px solid #1010FF; margin-left: 5px; padding-left: 5px; color: #000; font-weight: normal; font-style: normal; text-decoration: none; font-family: Helvetica,Arial,sans-serif; font-size: 12pt;">On Aug 19, 2015, at 3:02 AM, Ingvar Hagelund <ingvar@redpill-linpro.com> wrote:<br>> I've started wrapping jemalloc-4.0.0 for fedora. aarch64 is now a target<br>> arch for fedora. When sent to the arm builders, the unit/bitmap test<br>> segfaults. Full log here:<br>> <br>> http://arm.koji.fedoraproject.org//work/tasks/6832/3126832/build.log<br>> <br>> Also note the vast amounts of "warning: left shift count is negative".<br><br>This happens with page sizes larger than 8 KiB.</blockquote><div><div>That's the case here, yes. Fedora 22 on aarch64. </div><div><br></div><div><div>$ uname -a<br>Linux arm64 4.0.4-301.fc22.aarch64 #1 SMP Thu May 21 15:21:42 UTC 2015 aarch64 aarch64 aarch64 GNU/Linux</div><div><br></div>$ getconf PAGESIZE<br>65536</div></div><blockquote style="border-left: 2px solid #1010FF; margin-left: 5px; padding-left: 5px; color: #000; font-weight: normal; font-style: normal; text-decoration: none; font-family: Helvetica,Arial,sans-serif; font-size: 12pt;" data-mce-style="border-left: 2px solid #1010FF; margin-left: 5px; padding-left: 5px; color: #000; font-weight: normal; font-style: normal; text-decoration: none; font-family: Helvetica,Arial,sans-serif; font-size: 12pt;"> I can test a patch locally by specifying --with-lg-page=16 during configuration. The segfault is hopefully a side effect of the bit shifting issue (I certainly get test crashes when specifying --with-lg-page=16).</blockquote><div>I have got a qemu aarch64 instance running now, so I would happily test patches.</div><div><br data-mce-bogus="1"></div><div>I throw in a gdb backtrace for good measure</div><div><br data-mce-bogus="1"></div><div>[ingvar@arm64 jemalloc-4.0.0]$ gdb test/unit/bitmap<br>GNU gdb (GDB) Fedora 7.9-11.fc22<br></div><div>(...snip...)</div><div>This GDB was configured as "aarch64-redhat-linux-gnu".<br>(...snip....)<br></div><div><br data-mce-bogus="1"></div><div>Reading symbols from test/unit/bitmap...done.<br>(gdb) run<br>Starting program: /home/ingvar/rpmbuild/BUILD/jemalloc-4.0.0/test/unit/bitmap <br>[Thread debugging using libthread_db enabled]<br>Using host libthread_db library "/lib64/libthread_db.so.1".<br>test_bitmap_size: pass<br><br>Program received signal SIGSEGV, Segmentation fault.<br>__GI___pthread_mutex_lock (mutex=mutex@entry=0x840) at pthread_mutex_lock.c:67<br>67 unsigned int type = PTHREAD_MUTEX_TYPE_ELISION (mutex);<br>(gdb) bt<br>#0 __GI___pthread_mutex_lock (mutex=mutex@entry=0x840) at pthread_mutex_lock.c:67<br>#1 0x000000000042f704 in jet_malloc_mutex_lock (mutex=0x14ae70840) at include/jemalloc/internal/mutex.h:85<br>#2 jet_tcache_bin_flush_small (tsd=tsd@entry=0x3ffb7810008, tcache=tcache@entry=0x3ffb7820000, tbin=tbin@entry=0x3ffb7820020, binind=binind@entry=0, rem=1768846639) at src/tcache.c:115<br>#3 0x0000000000408574 in jet_tcache_dalloc_small (binind=0, ptr=0x3ffb7a78f00, tcache=0x3ffb7820000, tsd=0x3ffb7810008) at include/jemalloc/internal/tcache.h:376<br>#4 jet_arena_dalloc (tcache=0x3ffb7820000, ptr=0x3ffb7a78f00, tsd=0x3ffb7810008) at include/jemalloc/internal/arena.h:1195<br>#5 jet_idalloctm (is_metadata=false, tcache=0x3ffb7820000, ptr=0x3ffb7a78f00, tsd=0x3ffb7810008) at include/jemalloc/internal/jemalloc_internal.h:1005<br>#6 jet_iqalloc (tcache=0x3ffb7820000, ptr=0x3ffb7a78f00, tsd=0x3ffb7810008) at include/jemalloc/internal/jemalloc_internal.h:1029<br>#7 ifree (tcache=0x3ffb7820000, ptr=0x3ffb7a78f00, tsd=0x3ffb7810008) at src/jemalloc.c:1723<br>#8 jet_free (ptr=ptr@entry=0x3ffb7a78f00) at src/jemalloc.c:1817<br>#9 0x0000000000401a84 in test_bitmap_init () at test/unit/bitmap.c:34<br>#10 0x0000000000434a20 in p_test (t=0x401970 <test_bitmap_init>) at test/src/test.c:84<br>#11 0x000003ffb7d1f964 in __libc_start_main (main=0x0, argc=0, argv=0x0, init=<optimized out>, fini=<optimized out>, rtld_fini=<optimized out>, stack_end=<optimized out>) at libc-start.c:289<br>#12 0x00000000004016f0 in _start ()<br>Backtrace stopped: previous frame identical to this frame (corrupt stack?)</div><div><br data-mce-bogus="1"></div><div><br data-mce-bogus="1"></div></div></div></body></html>