bt: x86_64: filter out idle task stack

When we use crash to troubleshoot softlockup and other problems,
we often use the 'bt -a' command to print the stacks of running
processes on all CPUs. But now some servers have hundreds of CPUs
(such as AMD machines), which causes the 'bt -a' command to output
a lot of process stacks. And many of these stacks are the stacks
of the idle process, which are not needed by us.

Therefore, in order to reduce this part of the interference information,
this patch adds the -n option to the bt command. When we specify
'-n idle' (meaning no idle), the stack of the idle process will be
filtered out, thus speeding up our troubleshooting.

And the option works only for crash dumps captured by kdump.

The command output is as follows:
crash> bt -a -n idle
[...]
PID: 0      TASK: ffff889ff8c34380  CPU: 8   COMMAND: "swapper/8"

PID: 0      TASK: ffff889ff8c32d00  CPU: 9   COMMAND: "swapper/9"

PID: 0      TASK: ffff889ff8c31680  CPU: 10  COMMAND: "swapper/10"

PID: 0      TASK: ffff889ff8c35a00  CPU: 11  COMMAND: "swapper/11"

PID: 0      TASK: ffff889ff8c3c380  CPU: 12  COMMAND: "swapper/12"

PID: 150773  TASK: ffff889fe85a1680  CPU: 13  COMMAND: "bash"
 #0 [ffffc9000d35bcd0] machine_kexec at ffffffff8105a407
 #1 [ffffc9000d35bd28] __crash_kexec at ffffffff8113033d
 #2 [ffffc9000d35bdf0] panic at ffffffff81081930
 #3 [ffffc9000d35be70] sysrq_handle_crash at ffffffff814e38d1
 #4 [ffffc9000d35be78] __handle_sysrq.cold.12 at ffffffff814e4175
 #5 [ffffc9000d35bea8] write_sysrq_trigger at ffffffff814e404b
 #6 [ffffc9000d35beb8] proc_reg_write at ffffffff81330d86
 #7 [ffffc9000d35bed0] vfs_write at ffffffff812a72d5
 #8 [ffffc9000d35bf00] ksys_write at ffffffff812a7579
 #9 [ffffc9000d35bf38] do_syscall_64 at ffffffff81004259
    RIP: 00007fa7abcdc274  RSP: 00007fffa731f678  RFLAGS: 00000246
    RAX: ffffffffffffffda  RBX: 0000000000000002  RCX: 00007fa7abcdc274
    RDX: 0000000000000002  RSI: 0000563ca51ee6d0  RDI: 0000000000000001
    RBP: 0000563ca51ee6d0   R8: 000000000000000a   R9: 00007fa7abd6be80
    R10: 000000000000000a  R11: 0000000000000246  R12: 00007fa7abdad760
    R13: 0000000000000002  R14: 00007fa7abda8760  R15: 0000000000000002
    ORIG_RAX: 0000000000000001  CS: 0033  SS: 002b
[...]

Signed-off-by: Qi Zheng <[email protected]>
Acked-by: Kazuhito Hagio <[email protected]>
Acked-by: Lianbo Jiang <[email protected]>

defs.h

@@ -5832,6 +5832,7 @@ ulong cpu_map_addr(const char *type);
 #define BT_SHOW_ALL_REGS  (0x2000000000000ULL)
 #define BT_REGS_NOT_FOUND (0x4000000000000ULL)
 #define BT_OVERFLOW_STACK (0x8000000000000ULL)
+#define BT_SKIP_IDLE     (0x10000000000000ULL)
 #define BT_SYMBOL_OFFSET   (BT_SYMBOLIC_ARGS)
 
 #define BT_REF_HEXVAL         (0x1)

help.c

@@ -1909,12 +1909,14 @@ char *help_bt[] = {
 "bt",
 "backtrace",
 "[-a|-c cpu(s)|-g|-r|-t|-T|-l|-e|-E|-f|-F|-o|-O|-v|-p] [-R ref] [-s [-x|d]]"
-"\n     [-I ip] [-S sp] [pid | task]",
+"\n     [-I ip] [-S sp] [-n idle] [pid | task]",
 "  Display a kernel stack backtrace.  If no arguments are given, the stack",
 "  trace of the current context will be displayed.\n",
 "       -a  displays the stack traces of the active task on each CPU.",
 "           (only applicable to crash dumps)",
 "       -A  same as -a, but also displays vector registers (S390X only).",
+"  -n idle  filter the stack of idle tasks (x86_64).",
+"           (only applicable to crash dumps)",
 "       -p  display the stack trace of the panic task only.",
 "           (only applicable to crash dumps)",
 "   -c cpu  display the stack trace of the active task on one or more CPUs,",
@@ -2004,6 +2006,35 @@ char *help_bt[] = {
 "       DS:  002b      ESI: bfffc8a0  ES:  002b      EDI: 00000000 ",
 "       SS:  002b      ESP: bfffc82c  EBP: bfffd224 ",
 "       CS:  0023      EIP: 400d032e  ERR: 0000008e  EFLAGS: 00000246  ",
+" ",
+"  Display the stack trace of the active task(s) when the kernel panicked,",
+"  and filter out the stack of the idle tasks:",
+" ",
+"    %s> bt -a -n idle",
+"    ...",
+"    PID: 0      TASK: ffff889ff8c35a00  CPU: 11  COMMAND: \"swapper/11\"",
+" ",
+"    PID: 0      TASK: ffff889ff8c3c380  CPU: 12  COMMAND: \"swapper/12\"",
+" ",
+"    PID: 150773  TASK: ffff889fe85a1680  CPU: 13  COMMAND: \"bash\"",
+"    #0 [ffffc9000d35bcd0] machine_kexec at ffffffff8105a407",
+"    #1 [ffffc9000d35bd28] __crash_kexec at ffffffff8113033d",
+"    #2 [ffffc9000d35bdf0] panic at ffffffff81081930",
+"    #3 [ffffc9000d35be70] sysrq_handle_crash at ffffffff814e38d1",
+"    #4 [ffffc9000d35be78] __handle_sysrq.cold.12 at ffffffff814e4175",
+"    #5 [ffffc9000d35bea8] write_sysrq_trigger at ffffffff814e404b",
+"    #6 [ffffc9000d35beb8] proc_reg_write at ffffffff81330d86",
+"    #7 [ffffc9000d35bed0] vfs_write at ffffffff812a72d5",
+"    #8 [ffffc9000d35bf00] ksys_write at ffffffff812a7579",
+"    #9 [ffffc9000d35bf38] do_syscall_64 at ffffffff81004259",
+"       RIP: 00007fa7abcdc274  RSP: 00007fffa731f678  RFLAGS: 00000246",
+"       RAX: ffffffffffffffda  RBX: 0000000000000002  RCX: 00007fa7abcdc274",
+"       RDX: 0000000000000002  RSI: 0000563ca51ee6d0  RDI: 0000000000000001",
+"       RBP: 0000563ca51ee6d0   R8: 000000000000000a   R9: 00007fa7abd6be80",
+"       R10: 000000000000000a  R11: 0000000000000246  R12: 00007fa7abdad760",
+"       R13: 0000000000000002  R14: 00007fa7abda8760  R15: 0000000000000002",
+"       ORIG_RAX: 0000000000000001  CS: 0033  SS: 002b",
+"    ...",
 "\n  Display the stack trace of the active task on CPU 0 and 1:\n",
 "    %s> bt -c 0,1",
 "    PID: 0      TASK: ffffffff81a8d020  CPU: 0   COMMAND: \"swapper\"",

kernel.c

@@ -2503,7 +2503,7 @@ cmd_bt(void)
 	if (kt->flags & USE_OPT_BT)
 		bt->flags |= BT_OPT_BACK_TRACE;
 
-	while ((c = getopt(argcnt, args, "D:fFI:S:c:aAloreEgstTdxR:Ovp")) != EOF) {
+	while ((c = getopt(argcnt, args, "D:fFI:S:c:n:aAloreEgstTdxR:Ovp")) != EOF) {
                 switch (c)
 		{
 		case 'f':
@@ -2672,6 +2672,13 @@ cmd_bt(void)
 			active++;
 			break;
 
+		case 'n':
+			if (machine_type("X86_64") && STREQ(optarg, "idle"))
+				bt->flags |= BT_SKIP_IDLE;
+			else
+				option_not_supported(c);
+			break;
+
 		case 'r':
 			bt->flags |= BT_RAW;
 			break;
@@ -3092,6 +3099,10 @@ back_trace(struct bt_info *bt)
 	} else
                 machdep->get_stack_frame(bt, &eip, &esp);
 
+	/* skip idle task stack */
+	if (bt->flags & BT_SKIP_IDLE)
+		return;
+
 	if (bt->flags & BT_KSTACKP) {
 		bt->stkptr = esp;
 		return;

x86_64.c

@@ -4918,6 +4918,9 @@ x86_64_get_stack_frame(struct bt_info *bt, ulong *pcp, ulong *spp)
 	if (bt->flags & BT_DUMPFILE_SEARCH)
 		return x86_64_get_dumpfile_stack_frame(bt, pcp, spp);
 
+	if (bt->flags & BT_SKIP_IDLE)
+		bt->flags &= ~BT_SKIP_IDLE;
+
         if (pcp)
                 *pcp = x86_64_get_pc(bt);
         if (spp)
@@ -4960,6 +4963,9 @@ x86_64_get_dumpfile_stack_frame(struct bt_info *bt_in, ulong *rip, ulong *rsp)
 	estack = -1;
 	panic = FALSE;
 
+	if (bt_in->flags & BT_SKIP_IDLE)
+		bt_in->flags &= ~BT_SKIP_IDLE;
+
 	panic_task = tt->panic_task == bt->task ? TRUE : FALSE;
 
 	if (panic_task && bt->machdep) {
@@ -5098,6 +5104,8 @@ x86_64_get_dumpfile_stack_frame(struct bt_info *bt_in, ulong *rip, ulong *rsp)
                 if (!panic_task && STREQ(sym, "crash_nmi_callback")) {
                         *rip = *up;
                         *rsp = bt->stackbase + ((char *)(up) - bt->stackbuf);
+			if ((bt->flags & BT_SKIP_IDLE) && is_idle_thread(bt->task))
+				bt_in->flags |= BT_SKIP_IDLE;
                         return;
                 }