Hello Pingfan,
With this patch series applied, the kdump kernel fails to boot on
powerpc with nr_cpus=1.
Console logs:
-------------------
[root]# echo c > /proc/sysrq-trigger
[ 74.783235] sysrq: Trigger a crash
[ 74.783244] Kernel panic - not syncing: sysrq triggered crash
[ 74.783252] CPU: 58 PID: 3838 Comm: bash Kdump: loaded Not tainted
6.6.0-rc5pf-nr-cpus+ #3
[ 74.783259] Hardware name: POWER10 (raw) phyp pSeries
[ 74.783275] Call Trace:
[ 74.783280] [c00000020f4ebac0] [c000000000ed9f38]
dump_stack_lvl+0x6c/0x9c (unreliable)
[ 74.783291] [c00000020f4ebaf0] [c000000000150300] panic+0x178/0x438
[ 74.783298] [c00000020f4ebb90] [c000000000936d48]
sysrq_handle_crash+0x28/0x30
[ 74.783304] [c00000020f4ebbf0] [c00000000093773c]
__handle_sysrq+0x10c/0x250
[ 74.783309] [c00000020f4ebc90] [c000000000937fa8]
write_sysrq_trigger+0xc8/0x168
[ 74.783314] [c00000020f4ebcd0] [c000000000665d8c]
proc_reg_write+0x10c/0x1b0
[ 74.783321] [c00000020f4ebd00] [c00000000058da54] vfs_write+0x104/0x4b0
[ 74.783326] [c00000020f4ebdc0] [c00000000058dfdc] ksys_write+0x7c/0x140
[ 74.783331] [c00000020f4ebe10] [c000000000033a64]
system_call_exception+0x144/0x3a0
[ 74.783337] [c00000020f4ebe50] [c00000000000c554]
system_call_common+0xf4/0x258
[ 74.783343] --- interrupt: c00 at 0x7fffa0721594
[ 74.783352] NIP: 00007fffa0721594 LR: 00007fffa0697bf4 CTR:
0000000000000000
[ 74.783364] REGS: c00000020f4ebe80 TRAP: 0c00 Not tainted
(6.6.0-rc5pf-nr-cpus+)
[ 74.783376] MSR: 800000000280f033
<SF,VEC,VSX,EE,PR,FP,ME,IR,DR,RI,LE> CR: 28222202 XER: 00000000
[ 74.783394] IRQMASK: 0
[ 74.783394] GPR00: 0000000000000004 00007ffffc4b6800 00007fffa0807300
0000000000000001
[ 74.783394] GPR04: 000000013549ea60 0000000000000002 0000000000000010
0000000000000000
[ 74.783394] GPR08: 0000000000000000 0000000000000000 0000000000000000
0000000000000000
[ 74.783394] GPR12: 0000000000000000 00007fffa0abaf70 0000000040000000
000000011a0f9798
[ 74.783394] GPR16: 000000011a0f9724 000000011a097688 000000011a02ff70
000000011a0fd568
[ 74.783394] GPR20: 0000000135554bf0 0000000000000001 000000011a0aa478
00007ffffc4b6a24
[ 74.783394] GPR24: 00007ffffc4b6a20 000000011a0faf94 0000000000000002
000000013549ea60
[ 74.783394] GPR28: 0000000000000002 00007fffa08017a0 000000013549ea60
0000000000000002
[ 74.783440] NIP [00007fffa0721594] 0x7fffa0721594
[ 74.783443] LR [00007fffa0697bf4] 0x7fffa0697bf4
[ 74.783447] --- interrupt: c00
I'm in purgatory
[ 0.000000] radix-mmu: Page sizes from device-tree:
[ 0.000000] radix-mmu: Page size shift = 12 AP=0x0
[ 0.000000] radix-mmu: Page size shift = 16 AP=0x5
[ 0.000000] radix-mmu: Page size shift = 21 AP=0x1
[ 0.000000] radix-mmu: Page size shift = 30 AP=0x2
[ 0.000000] Activating Kernel Userspace Access Prevention
[ 0.000000] Activating Kernel Userspace Execution Prevention
[ 0.000000] radix-mmu: Mapped 0x0000000000000000-0x0000000000010000
with 64.0 KiB pages (exec)
[ 0.000000] radix-mmu: Mapped 0x0000000000010000-0x0000000000200000
with 64.0 KiB pages
[ 0.000000] radix-mmu: Mapped 0x0000000000200000-0x0000000020000000
with 2.00 MiB pages
[ 0.000000] radix-mmu: Mapped 0x0000000020000000-0x0000000022600000
with 2.00 MiB pages (exec)
[ 0.000000] radix-mmu: Mapped 0x0000000022600000-0x0000000040000000
with 2.00 MiB pages
[ 0.000000] radix-mmu: Mapped 0x0000000040000000-0x0000000180000000
with 1.00 GiB pages
[ 0.000000] radix-mmu: Mapped 0x0000000180000000-0x00000001a0000000
with 2.00 MiB pages
[ 0.000000] lpar: Using radix MMU under hypervisor
[ 0.000000] Linux version 6.6.0-rc5pf-nr-cpus+
(root@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx) (gcc (GCC) 8.5.0 20210514 (Red
Hat 8.5.0-20), GNU ld version 2.30-123.el8) #3 SMP Mon Oct 9 11:07:
41 CDT 2023
[ 0.000000] Found initrd at 0xc000000022e60000:0xc0000000248f08d8
[ 0.000000] Hardware name: IBM,9043-MRX POWER10 (raw) 0x800200
0xf000006 of:IBM,FW1060.00 (NM1060_016) hv:phyp pSeries
[ 0.000000] printk: bootconsole [udbg0] enabled
[ 0.000000] the round shift between dt seq and the cpu logic number: 56
[ 0.000000] BUG: Unable to handle kernel data access on write at
0xc0000001a0000000
[ 0.000000] Faulting instruction address: 0xc000000022009c64
[ 0.000000] Oops: Kernel access of bad area, sig: 11 [#1]
[ 0.000000] LE PAGE_SIZE=64K MMU=Radix SMP NR_CPUS=2048 NUMA pSeries
[ 0.000000] Modules linked in:
[ 0.000000] CPU: 2 PID: 0 Comm: swapper Not tainted
6.6.0-rc5pf-nr-cpus+ #3
[ 0.000000] Hardware name: POWER10 (raw) hv:phyp pSeries
[ 0.000000] NIP: c000000022009c64 LR: c000000022009c54 CTR:
c0000000201ff348
[ 0.000000] REGS: c000000022aebb00 TRAP: 0300 Not tainted
(6.6.0-rc5pf-nr-cpus+)
[ 0.000000] MSR: 8000000000001033 <SF,ME,IR,DR,RI,LE> CR: 28222824
XER: 00000001
[ 0.000000] CFAR: c000000020031574 DAR: c0000001a0000000 DSISR:
42000000 IRQMASK: 1
[ 0.000000] GPR00: c000000022009ba0 c000000022aebda0 c0000000213d1300
0000000000000004
[ 0.000000] GPR04: 0000000000000001 c000000022aebbc0 c000000022aebbb8
0000000000000000
[ 0.000000] GPR08: 0000000000000001 c00000019ffffff8 000000000000003a
c0000000229c8a78
[ 0.000000] GPR12: 0000000000002000 c000000022e4a800 c0000000211d34b8
c0000000211d3aa8
[ 0.000000] GPR16: c0000000211d75a0 c0000000211d75b0 c0000000225f3b98
0000000000000000
[ 0.000000] GPR20: 0000000000000001 0000000000000001 0000000000000001
0000000000000001
[ 0.000000] GPR24: 0000000000000008 0000000000000000 0000000000000001
c00000019ffffdc0
[ 0.000000] GPR28: 0000000000000002 c000000022b368e0 c000000022aebe08
0000000000000008
[ 0.000000] NIP [c000000022009c64] smp_setup_cpu_maps+0x420/0x724
[ 0.000000] LR [c000000022009c54] smp_setup_cpu_maps+0x410/0x724
[ 0.000000] Call Trace:
[ 0.000000] [c000000022aebda0] [c000000022009ba0]
smp_setup_cpu_maps+0x35c/0x724 (unreliable)
[ 0.000000] [c000000022aebeb0] [c00000002200a19c] setup_arch+0x1b8/0x54c
[ 0.000000] [c000000022aebf30] [c000000022003f88] start_kernel+0xb0/0x768
[ 0.000000] [c000000022aebfe0] [c00000002000d888]
start_here_common+0x1c/0x20
[ 0.000000] Code: 3929ffff 7f89e040 409c002c 7ec4b378 7f83e378
4a027939 7f83e378 4a0278e5 e95b0018 3d22017d e929f028 7d4ac42c
<7d49c12e> eb7b0000 7e99a378 4bffff3c
[ 0.000000] ---[ end trace 0000000000000000 ]---
[ 0.000000]
[ 0.000000] Kernel panic - not syncing: Fatal exception
[ 0.000000] Rebooting in 180 seconds..
However, the kdump kernel boots fine if the kernel crashes on CPU 0.
Thanks,
Sourabh Jain
On 09/10/23 17:00, Pingfan Liu wrote:
In order to identify the boot cpu, its intserv[] should be recorded and
checked in smp_setup_cpu_maps().
smp_setup_cpu_maps() is shared between PPC64 and PPC32. Since PPC64 has
already used boot_cpu_hwid to carry that information, enabling this
variable on PPC32 so later it can also be used to carry that information
for PPC32 in the coming patch.
Signed-off-by: Pingfan Liu <piliu@xxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Nicholas Piggin <npiggin@xxxxxxxxx>
Cc: Christophe Leroy <christophe.leroy@xxxxxxxxxx>
Cc: Mahesh Salgaonkar <mahesh@xxxxxxxxxxxxx>
Cc: Wen Xiong <wenxiong@xxxxxxxxxx>
Cc: Baoquan He <bhe@xxxxxxxxxx>
Cc: Ming Lei <ming.lei@xxxxxxxxxx>
Cc: kexec@xxxxxxxxxxxxxxxxxxx
To: linuxppc-dev@xxxxxxxxxxxxxxxx
---
arch/powerpc/include/asm/smp.h | 2 +-
arch/powerpc/kernel/prom.c | 3 +--
arch/powerpc/kernel/setup-common.c | 2 --
3 files changed, 2 insertions(+), 5 deletions(-)
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index aaaa576d0e15..5db9178cc800 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -26,7 +26,7 @@
#include <asm/percpu.h>
extern int boot_cpuid;
-extern int boot_cpu_hwid; /* PPC64 only */
+extern int boot_cpu_hwid;
extern int spinning_secondaries;
extern u32 *cpu_to_phys_id;
extern bool coregroup_enabled;
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 0b5878c3125b..ec82f5bda908 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -372,8 +372,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
be32_to_cpu(intserv[found_thread]));
boot_cpuid = found;
- if (IS_ENABLED(CONFIG_PPC64))
- boot_cpu_hwid = be32_to_cpu(intserv[found_thread]);
+ boot_cpu_hwid = be32_to_cpu(intserv[found_thread]);
/*
* PAPR defines "logical" PVR values for cpus that
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index d2a446216444..1b19a9815672 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -87,9 +87,7 @@ EXPORT_SYMBOL(machine_id);
int boot_cpuid = -1;
EXPORT_SYMBOL_GPL(boot_cpuid);
-#ifdef CONFIG_PPC64
int boot_cpu_hwid = -1;
-#endif
/*
* These are used in binfmt_elf.c to put aux entries on the stack
_______________________________________________
kexec mailing list
kexec@xxxxxxxxxxxxxxxxxxx
http://lists.infradead.org/mailman/listinfo/kexec
