#12928 NORM 14.1.0: display hang, extreme load

Zarro Boogs per Child bugtracker at laptop.org
Tue Jan 26 18:30:47 EST 2016


#12928: display hang, extreme load
-------------------------------------+-------------------------------------
     Reporter:  Quozl                |                 Owner:
         Type:  defect               |                Status:  new
     Priority:  normal               |             Milestone:  14.1.0
    Component:  not assigned         |               Version:  Development
     Keywords:                       |  build as of this date
     Blocking:                       |            Blocked By:
Action Needed:  reproduce            |  Deployments affected:
                                     |              Verified:  0
-------------------------------------+-------------------------------------
 Context: Fedora 20, XO-4, local build 11, test of extreme load web site in
 combination with frame show and hide using f6 key at 10Hz.

 Problem: display hang, no response to keyboard, mouse, touchscreen.
 Normal response to power button.  Normal response to SSH.

 Analysis: /usr/bin/Xorg process looping with 100% CPU usage, attached gdb,
 captured PC samples, always
 pixman_scaled_bilinear_scanline_8888_0565_SRC_asm_neon+1324, captured core
 dump, captured backtraces;

 {{{
 (gdb) thread apply all bt

 Thread 3 (Thread 0xb68fa000 (LWP 397)):
 #0  0xb6db1710 in pixman_scaled_bilinear_scanline_8888_0565_SRC_asm_neon
 () at pixman-arm-neon-asm.S:3627
 #1  0xb6d9a700 in scaled_bilinear_scanline_neon_8888_0565_SRC
 (mask=<synthetic pointer>, max_vx=2147483647, zero_src=0, unit_x=0,
     vx=<optimized out>, wb=<optimized out>, wt=<optimized out>, w=0,
 src_bottom=<optimized out>, src_top=<optimized out>,
     dst=<optimized out>) at pixman-arm-neon.c:140
 #2  fast_composite_scaled_bilinear_neon_8888_0565_cover_SRC
 (imp=<optimized out>, info=<optimized out>) at pixman-arm-neon.c:140
 #3  0xb6ffec88 in dyn_temp () from /lib/ld-linux-armhf.so.3
 Backtrace stopped: previous frame identical to this frame (corrupt stack?)

 Thread 2 (Thread 0xac56d2b0 (LWP 456)):
 #0  0xb6dd3e8c in pthread_cond_wait@@GLIBC_2.4 () from
 /lib/libpthread.so.0
 #1  0xaea3f678 in cnd_wait (mtx=0x2c4088, cond=<optimized out>) at
 ../../../../include/c11/threads_posix.h:154
 #2  pipe_semaphore_wait (sema=0x2c4088) at
 ../../../../src/gallium/auxiliary/os/os_thread.h:248
 #3  thread_function (init_data=init_data at entry=0x2c4020) at lp_rast.c:761
 #4  0xaea3ef44 in impl_thrd_routine (p=<optimized out>) at
 ../../../../include/c11/threads_posix.h:87
 #5  0xb6dcd1bc in start_thread () from /lib/libpthread.so.0
 #6  0xb6b98e40 in ?? () from /lib/libc.so.6
 Backtrace stopped: previous frame identical to this frame (corrupt stack?)

 Thread 1 (Thread 0xacd6d2b0 (LWP 455)):
 #0  0xb6dd3e8c in pthread_cond_wait@@GLIBC_2.4 () from
 /lib/libpthread.so.0
 #1  0xaea3f678 in cnd_wait (mtx=0x2c3f80, cond=<optimized out>) at
 ../../../../include/c11/threads_posix.h:154
 #2  pipe_semaphore_wait (sema=0x2c3f80) at
 ../../../../src/gallium/auxiliary/os/os_thread.h:248
 #3  thread_function (init_data=init_data at entry=0x2c3f18) at lp_rast.c:761
 #4  0xaea3ef44 in impl_thrd_routine (p=<optimized out>) at
 ../../../../include/c11/threads_posix.h:87
 #5  0xb6dcd1bc in start_thread () from /lib/libpthread.so.0
 #6  0xb6b98e40 in ?? () from /lib/libc.so.6
 Backtrace stopped: previous frame identical to this frame (corrupt stack?)
 }}}

 Captured instruction stream disassembly:
 {{{
 (gdb) disassemble 0xb6db1700,+32
 Dump of assembler code from 0xb6db1700 to 0xb6db1720:
    0xb6db1700 <+1308>:    vshrn.i32       d4, q2, #14
    0xb6db1704 <+1312>:    vld1.32 {d22}, [r4], r2
    0xb6db1708 <+1316>:    vshrn.i32       d5, q3, #14
    0xb6db170c <+1320>:    vadd.i16        q12, q12, q13
 => 0xb6db1710 <+1324>:    vld1.32 {d23}, [r4]
    0xb6db1714 <+1328>:    vmull.u8        q9, d22, d28
    0xb6db1718 <+1332>:    asr     r8, r5, #16
    0xb6db171c <+1336>:    add     r5, r5, r6
 End of assembler dump.
 (gdb)
 }}}

 Register dump:
 {{{
 (gdb) i r
 r0             0x2c3f9c 2899868
 r1             0x80     128
 r2             0x1      1
 r3             0x0      0
 r4             0x2c3f98 2899864
 r5             0x0      0
 r6             0x1      1
 r7             0xf0     240
 r8             0x0      0
 r9             0x80     128
 r10            0x1      1
 r11            0x2c3f9c 2899868
 r12            0xacd6cc04       2899758084
 sp             0xacd6cc18       0xacd6cc18
 lr             0xacd6d770       -1395206288
 pc             0xb6dd3e8c       0xb6dd3e8c
 <pthread_cond_wait@@GLIBC_2.4+312>
 cpsr           0x800b0010       -2146762736
 (gdb)
 }}}

 Neon registers were not captured by the core dump.

 Relevant package versions:
 {{{
 glibc-2.22.90-29.fc24.armv7hl
 glibc-common-2.22.90-29.fc24.armv7hl
 pixman-0.30.0-5.fc20.armv7hl
 xorg-x11-drv-vivante-M5.3.12.5.6-5.olpc.1.armv7hl
 xorg-x11-server-Xorg-1.11.4-3.olpc.1.armv7hl
 }}}

--
Ticket URL: <http://dev.laptop.org/ticket/12928>
One Laptop per Child <http://one.laptop.org/>
One Laptop per Child bug tracking system


More information about the Bugs mailing list