Messages in this thread | | | From | Andrew Randrianasulu <> | Subject | AMD erratum 665 on f15h processor? | Date | Sun, 17 Dec 2017 12:04:28 +0300 |
| |
Hello!
I was trying to investigate why all my old kernels can't be booted on my relatively new machine. Kernels 4.10+ naturally boot - I use 4.14.3 right now - but old kernels die early ...
After some digging I found this https://patchwork.kernel.org/patch/9311567/
Patch talk about family 12h, but my machine has this CPU:
[ 0.056000] smpboot: CPU0: AMD FX(tm)-4300 Quad-Core Processor (family: 0x15, model: 0x2, stepping: 0x0) [ 0.056000] Performance Events: Fam15h core perfctr, AMD PMU driver.
Because fix applied unconditionally it probably helps me, so please don't remove it.
fail log from qemu and kernel 4.2 attached
.text : 0xc0100000 - 0xc046ceb7 (3507 kB) Checking if this processor honours the WP bit even in supervisor mode...Ok. SLUB: HWalign=64, Order=0-3, MinObjects=0, CPUs=1, Nodes=1 Hierarchical RCU implementation. Build-time adjustment of leaf fanout to 32. RCU restricting CPUs from NR_CPUS=16 to nr_cpu_ids=1. RCU: Adjusting geometry for rcu_fanout_leaf=32, nr_cpu_ids=1 NR_IRQS:2304 nr_irqs:256 16 Console: colour VGA+ 80x60 console [tty0] enabled clocksource: hpet: mask: 0xffffffff max_cycles: 0xffffffff, max_idle_ns: 1911260 4467 ns tsc: Fast TSC calibration failed tsc: Unable to calibrate against PIT tsc: HPET/PMTIMER calibration failed tsc: Marking TSC unstable due to could not calculate TSC khz Calibrating delay loop... 1253.37 BogoMIPS (lpj=2506752) pid_max: default: 32768 minimum: 301 ACPI: Core revision 20150619 ACPI: All ACPI Tables successfully acquired Mount-cache hash table entries: 1024 (order: 0, 4096 bytes) Mountpoint-cache hash table entries: 1024 (order: 0, 4096 bytes) Initializing cgroup subsys net_cls general protection fault: 0000 [#1] SMP Modules linked in: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.2.0-i486 #7 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.11.0-0-g63451fca1 3-prebuilt.qemu-project.org 04/01/2014 task: c05dba40 ti: c05d4000 task.ti: c05d4000 EIP: 0060:[<c010ec47>] EFLAGS: 00210202 CPU: 0 EIP is at cpu_has_amd_erratum+0x23/0xb2 EAX: 00210bf7 EBX: 00000001 ECX: c0010140 EDX: c0470b2c ESI: c0630d00 EDI: c0470b30 EBP: c05d5f24 ESP: c05d5f14 DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 CR0: 8005003b CR2: ffc77000 CR3: 006d2000 CR4: 00040690 Stack: 02008140 00000000 c0630d00 00000000 c05d5f70 c010f446 000000d0 c05d5f5c c01e0571 00000010 0000001e 00000000 00000000 00000009 00000010 00000000 c0630d00 00000000 c05d5f70 c010d74d 00000020 c0630d00 c0630d8b c05d5f9c Call Trace: [<c010f446>] init_amd+0x4e8/0x662 [<c01e0571>] ? kmem_cache_alloc_trace+0xbe/0xc8 [<c010d74d>] ? get_cpu_cap+0x127/0x12c [<c010d936>] identify_cpu+0x1e4/0x366 [<c01e044c>] ? kmem_cache_alloc+0x90/0xf7 [<c01c7869>] ? kmem_cache_create+0x118/0x15b [<c063f1ea>] identify_boot_cpu+0x10/0x99 [<c018fb35>] ? __delayacct_tsk_init+0x15/0x28 [<c063f2a6>] check_bugs+0x9/0x39 [<c0638ae3>] start_kernel+0x3a3/0x3b3 [<c063854d>] ? set_init_arg+0x52/0x52 [<c06382b8>] i386_start_kernel+0x82/0x86 Code: e0 eb 5d c0 89 e5 5d c3 55 89 e5 57 56 89 c6 53 51 8b 1a 8d 7a 04 81 fb ff ff 00 00 77 54 8b 40 2c f6 c4 02 74 4c b9 40 01 01 c0 <0f> 32 89 45 f0 89 d8 89 d1 99 39 ca 77 39 72 05 3b 5d f0 73 32 EIP: [<c010ec47>] cpu_has_amd_erratum+0x23/0xb2 SS:ESP 0068:c05d5f14 ---[ end trace 8bfd5e6fa0a4fcb2 ]--- Kernel panic - not syncing: Attempted to kill the idle task! ---[ end Kernel panic - not syncing: Attempted to kill the idle task!
well, because this bug apparently fixed and fix propogated to -stable it shouldn't concern me too much, but may be someone in the future will rearrange those checks and assume only some old AMD CPUs were affected ... so, I leave this message.
qemu cmd line: qemu-system-x86_64 -M q35 -enable-kvm -cdrom /dev/shm/slax_16_12_2017_test.iso -m 512 -soundhw es1370 -cpu host -device sga -curses
-cpu host really important here. I used VGA mode 6 (vga=6) blindly for getting maximized output.
| |