Hi Dave,
I've reworked patch about ppc "bt" problem discussed in
https://www.redhat.com/archives/crash-utility/2012-June/msg00029.html
A patch is now getting to work only for ppc targets,
and notes are relocatecd in first ppc's "bt", not in initialization-time.
And I've tested both "bt" diskdump by makedumpfile and netdump by
/proc/vmcore with patched kernel like
void crash_save_cpu(struct pt_regs *regs, int cpu)
if ((cpu % 2))
return;
I was worried about beeing able to catch all of non-contiguous NT_PRSTATUS
notes, alternate with invalid odd notes in every process well,
so I modified test case this time (that's no problem, everything OK).
[After initialization: notes are not relocated yet]
crash> help -D | grep notes
num_prstatus_notes: 4
notes_buf: 107a3518
notes[0]: 107a3518
notes[1]: 107a3638
notes[2]: 107a3758
notes[3]: 107a3878
[Relocate in first bt(only once) and display correctly]
crash> bt
PID: 1000 TASK: eb0cf800 CPU: 4 COMMAND: "bash"
bt: WARNING: cpu#1: not saved crash_notes
bt: WARNING: cpu#3: not saved crash_notes
bt: WARNING: cpu#5: not saved crash_notes
bt: WARNING: cpu#7: not saved crash_notes
R0: 00000001 R1: ea11be60 R2: eb0cf800 R3: 00000063
R4: 00000000 R5: ffffffff R6: c043ba2c R7: 00000000
R8: 00008000 R9: 00000000 R10: 00000000 R11: ea11be70
R12: 28242444 R13: 100b8448 R14: 100b07b8 R15: 100b0894
R16: 00000000 R17: 00000000 R18: 00000000 R19: 1006d270
R20: 00000000 R21: 100f02e0 R22: 00000000 R23: 00000001
R24: c08f1ac8 R25: 00029002 R26: c08f1bac R27: c08d0000
R28: 00000000 R29: c09ada48 R30: 00000063 R31: ea11be60
NIP: c0423378 MSR: 00021002 OR3: c09ada48 CTR: c0423344
LR: c0423d8c XER: 00000000 CCR: 28242444 MQ: 00008000
DAR: 00000000 DSISR: 00800000 Syscall Result: ea11be60
NIP [00000000c0423378] sysrq_handle_crash
LR [00000000c0423d8c] __handle_sysrq
=> PC: c0423378 (sysrq_handle_crash+52) FP: ea11be60
#0 [ea11be60] sysrq_handle_crash at c0423378
#1 [ea11be70] __handle_sysrq at c0423d8c
#2 [ea11bea0] write_sysrq_trigger at c0423ed0
#3 [ea11beb0] proc_reg_write at c01a79a4
#4 [ea11bee0] vfs_write at c014ba44
#5 [ea11bf00] sys_write at c014bcd8
#6 [ea11bf40] ret_from_syscall at c0013834
syscall [c00] exception frame:
R0: 00000004 R1: bfe54e00 R2: 48027f80 R3: 00000001
R4: 4811d000 R5: 00000002 R6: 00000000 R7: 00000001
R8: 00000000 R9: 00000000 R10: 00000000 R11: 00000200
R12: 28242442 R13: 100b8448 R14: 100b07b8 R15: 100b0894
R16: 00000000 R17: 00000000 R18: 00000000 R19: 1006d270
R20: 00000000 R21: 100f02e0 R22: 1006b4d0 R23: 00000001
R24: 100b0000 R25: 1009b474 R26: bfe54ec8 R27: 00000002
R28: 0fefa400 R29: 4811d000 R30: 0fef9ff4 R31: 00000002
NIP: 0fe61494 MSR: 0002f902 OR3: 00000001 CTR: 0fe06fec
LR: 0fe07050 XER: 00000000 CCR: 28242444 MQ: 00000000
DAR: 4811d000 DSISR: 00800000 Syscall Result: 00000000
[notes has been relocated: Counts num_prstatus_notes even if NULL]
crash> help -D | grep notes
num_prstatus_notes: 8
notes_buf: 107a3518
notes[0]: 107a3518
notes[1]: 0
notes[2]: 107a3638
notes[3]: 0
notes[4]: 107a3758
notes[5]: 0
notes[6]: 107a3878
notes[7]: 0
Thanks,
Toshi
Date: Thu, 21 Jun 2012 10:39:45 +0900
Subject: [PATCH] ppc: fix up back trace for panic or active tasks problem
When dump file is not contained enough NT_PRSTATUS notes for all online cpus,
ppc diskdump and netdump can not do correct "bt".
Relocate NT_PRSTATUS instances into corresponding cpu maps.
This can do only once when first "bt" command is required.
I couldn't found out good entry point for this while initialization time.
Signed-off-by: Toshikazu Nakayama <[email protected]>
---
diskdump.c | 81 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
netdump.c | 3 ++
ppc.c | 2 +
3 files changed, 85 insertions(+), 1 deletions(-)
diff --git a/diskdump.c b/diskdump.c
index e3f04e8..4781659 100644
--- a/diskdump.c
+++ b/diskdump.c
@@ -1012,12 +1012,91 @@ get_diskdump_panic_task(void)
extern void get_netdump_regs_x86(struct bt_info *, ulong *, ulong *);
extern void get_netdump_regs_x86_64(struct bt_info *, ulong *, ulong *);
+/*
+ * Try to relocate NT_PRSTATUS notes according by in kernel crash_notes.
+ * Function is only called from ppc's get_regs.
+ */
+
+static int
+verify_crash_note_in_kernel_ppc(int cpu)
+{
+ int ret;
+ Elf32_Nhdr *note32;
+ ulong crash_notes_ptr;
+ char *buf, *name;
+
+ ret = TRUE;
+ if (!readmem(symbol_value("crash_notes"), KVADDR, &crash_notes_ptr,
+ sizeof(ulong), "crash_notes", QUIET|RETURN_ON_ERROR) ||
+ !crash_notes_ptr)
+ goto out;
+
+ buf = GETBUF(SIZE(note_buf));
+ if ((kt->flags & SMP) && (kt->flags & PER_CPU_OFF))
+ crash_notes_ptr += kt->__per_cpu_offset[cpu];
+ if (!readmem(crash_notes_ptr, KVADDR, buf, SIZE(note_buf),
+ "cpu crash_notes", QUIET|RETURN_ON_ERROR))
+ goto freebuf;
+
+ note32 = (Elf32_Nhdr *)buf;
+ name = (char *)(note32 + 1);
+ if (note32->n_type != NT_PRSTATUS ||
+ note32->n_namesz != strlen("CORE") + 1 ||
+ strncmp(name, "CORE", note32->n_namesz) ||
+ note32->n_descsz != SIZE(elf_prstatus))
+ ret = FALSE;
+freebuf:
+ FREEBUF(buf);
+out:
+ return ret;
+}
+
+void
+relocate_nt_prstatus_percpu_ppc(void **nt_prstatus_percpu,
+ int *num_prstatus_notes)
+{
+ static int relocated = FALSE;
+ void **nt_ptr;
+ int i, j, nrcpus;
+ size_t size;
+
+ /* relocation is possible only once */
+ if (relocated == TRUE)
+ return;
+ relocated = TRUE;
+ if (!symbol_exists("crash_notes") ||
+ !VALID_STRUCT(note_buf) || !VALID_STRUCT(elf_prstatus))
+ return;
+
+ size = NR_CPUS * sizeof(void *);
+ nt_ptr = (void **)GETBUF(size);
+ BCOPY(nt_prstatus_percpu, nt_ptr, size);
+ BZERO(nt_prstatus_percpu, size);
+
+ *num_prstatus_notes = 0;
+ nrcpus = (kt->kernel_NR_CPUS ? kt->kernel_NR_CPUS : NR_CPUS);
+ for (i = 0, j = 0; i < nrcpus; i++) {
+ if (!in_cpu_map(ONLINE, i))
+ continue;
+ if (verify_crash_note_in_kernel_ppc(i))
+ nt_prstatus_percpu[i] = nt_ptr[j++];
+ else if (CRASHDEBUG(1))
+ error(WARNING, "cpu#%d: not saved crash_notes\n", i);
+ /* num_prstatus_notes is always equal to online cpus in ppc */
+ (*num_prstatus_notes)++;
+ }
+ FREEBUF(nt_ptr);
+}
+
static void
get_diskdump_regs_ppc(struct bt_info *bt, ulong *eip, ulong *esp)
{
Elf32_Nhdr *note;
int len;
+ if (KDUMP_CMPRS_VALID())
+ relocate_nt_prstatus_percpu_ppc(dd->nt_prstatus_percpu,
+ &dd->num_prstatus_notes);
if (KDUMP_CMPRS_VALID() &&
(bt->task == tt->panic_task ||
(is_task_active(bt->task) && dd->num_prstatus_notes > 1))) {
@@ -1030,7 +1109,7 @@ get_diskdump_regs_ppc(struct bt_info *bt, ulong *eip, ulong *esp)
"panic" : "active", bt->task);
len = sizeof(Elf32_Nhdr);
len = roundup(len + note->n_namesz, 4);
- bt->machdep = (void *)((char *)note + len +
+ bt->machdep = (void *)((char *)note + len +
MEMBER_OFFSET("elf_prstatus", "pr_reg"));
}
diff --git a/netdump.c b/netdump.c
index 51bbc35..6cfc1e9 100644
--- a/netdump.c
+++ b/netdump.c
@@ -2589,12 +2589,15 @@ next_sysrq:
machdep->get_stack_frame(bt, eip, esp);
}
+extern void relocate_nt_prstatus_percpu_ppc(void **, int *);
static void
get_netdump_regs_ppc(struct bt_info *bt, ulong *eip, ulong *esp)
{
Elf32_Nhdr *note;
size_t len;
+ relocate_nt_prstatus_percpu_ppc(nd->nt_prstatus_percpu,
+ &nd->num_prstatus_notes);
if ((bt->task == tt->panic_task) ||
(is_task_active(bt->task) && nd->num_prstatus_notes > 1)) {
/*
diff --git a/ppc.c b/ppc.c
index bc5f201..7c5f3be 100755
--- a/ppc.c
+++ b/ppc.c
@@ -414,6 +414,8 @@ ppc_init(int when)
symbol_exists("hardirq_ctx"))
STRUCT_SIZE_INIT(irq_ctx, "hardirq_ctx");
+ STRUCT_SIZE_INIT(note_buf, "note_buf_t");
+ STRUCT_SIZE_INIT(elf_prstatus, "elf_prstatus");
break;
case POST_INIT:
--
1.7.0.4
--
Crash-utility mailing list
[email protected]
https://www.redhat.com/mailman/listinfo/crash-utility
