From dd6b187ac15a237cefe863c4e5b432cf13b9883a Mon Sep 17 00:00:00 2001
From: bevis_chen <bevis_chen(a)asus.com>
Date: Wed, 3 Jul 2024 15:05:44 +0800
Subject: [PATCH] arm64: Fix bt command show wrong stacktrace on ramdump source
If we use crash to parse ramdump(Qcom phone device) rathen than vmcore.
Start command should be like: crash vmlinux --kaslr=xxx
DDRCS0_0.BIN@0x0000000080000000,... --machdep vabits_actual=39
Then We will see bt command show misleading backtrace information below:
crash> bt 16930
PID: 16930 TASK: ffffff89b3eada00 CPU: 2 COMMAND: "Firebase Backgr"
#0 [ffffffc034c437f0] __switch_to at ffffffe0036832d4
#1 [ffffffc034c43850] __kvm_nvhe_$d.2314 at 6be732e004cf05a0
#2 [ffffffc034c438b0] __kvm_nvhe_$d.2314 at 86c54c6004ceff80
#3 [ffffffc034c43950] __kvm_nvhe_$d.2314 at 55d6f96003a7b120
#4 [ffffffc034c439f0] __kvm_nvhe_$d.2314 at 9ccec46003a80a64
#5 [ffffffc034c43ac0] __kvm_nvhe_$d.2314 at 8cf41e6003a945c4
#6 [ffffffc034c43b10] __kvm_nvhe_$d.2314 at a8f181e00372c818
#7 [ffffffc034c43b40] __kvm_nvhe_$d.2314 at 6dedde600372c0d0
#8 [ffffffc034c43b90] __kvm_nvhe_$d.2314 at 62cc07e00373d0ac
#9 [ffffffc034c43c00] __kvm_nvhe_$d.2314 at 72fb1de00373bedc
...
PC: 00000073f5294840 LR: 00000070d8f39ba4 SP: 00000070d4afd5d0
X29: 00000070d4afd600 X28: b4000071efcda7f0 X27: 00000070d4afe000
X26: 0000000000000000 X25: 00000070d9616000 X24: 0000000000000000
X23: 0000000000000000 X22: 0000000000000000 X21: 0000000000000000
X20: b40000728fd27520 X19: b40000728fd27550 X18: 000000702daba000
X17: 00000073f5294820 X16: 00000070d940f9d8 X15: 00000000000000bf
X14: 0000000000000000 X13: 00000070d8ad2fac X12: b40000718fce5040
X11: 0000000000000000 X10: 0000000000000070 X9: 0000000000000001
X8: 0000000000000062 X7: 0000000000000020 X6: 0000000000000000
X5: 0000000000000000 X4: 0000000000000000 X3: 0000000000000000
X2: 0000000000000002 X1: 0000000000000080 X0: b40000728fd27550
ORIG_X0: b40000728fd27550 SYSCALLNO: ffffffff PSTATE: 40001000
By checking the raw data below, will see the lr (fp+8) data show the pointer which already
been replaced by PAC prefix.
crash> bt -f
PID: 16930 TASK: ffffff89b3eada00 CPU: 2 COMMAND: "Firebase Backgr"
#0 [ffffffc034c437f0] __switch_to at ffffffe0036832d4
ffffffc034c437f0: ffffffc034c43850 6be732e004cf05a4
ffffffc034c43800: ffffffe006186108 a0ed07e004cf09c4
ffffffc034c43810: ffffff8a1a340000 ffffff8a8d343c00
ffffffc034c43820: ffffff89b3eada00 ffffff8b780db540
ffffffc034c43830: ffffff89b3eada00 0000000000000000
ffffffc034c43840: 0000000000000004 712b828118484a00
#1 [ffffffc034c43850] __kvm_nvhe_$d.2314 at 6be732e004cf05a0
ffffffc034c43850: ffffffc034c438b0 86c54c6004ceff84
ffffffc034c43860: 000000708070f000 ffffffc034c43938
ffffffc034c43870: ffffff88bd822878 ffffff89b3eada00
...
So we check the CONFIG_ARM64_PTR_AUTH and CONFIG_ARM64_PTR_AUTH_KERNEL to double check if
pac mechanism been enabled on this ramdump.
Then we use vabits to figure it out.
Fix then show the right backtrace below:
crash> bt 16930
PID: 16930 TASK: ffffff89b3eada00 CPU: 2 COMMAND: "Firebase Backgr"
#0 [ffffffc034c437f0] __switch_to at ffffffe0036832d4
#1 [ffffffc034c43850] __schedule at ffffffe004cf05a0
#2 [ffffffc034c438b0] preempt_schedule_common at ffffffe004ceff80
#3 [ffffffc034c43950] unmap_page_range at ffffffe003a7b120
#4 [ffffffc034c439f0] unmap_vmas at ffffffe003a80a64
#5 [ffffffc034c43ac0] exit_mmap at ffffffe003a945c4
#6 [ffffffc034c43b10] __mmput at ffffffe00372c818
#7 [ffffffc034c43b40] mmput at ffffffe00372c0d0
#8 [ffffffc034c43b90] exit_mm at ffffffe00373d0ac
#9 [ffffffc034c43c00] do_exit at ffffffe00373bedc
PC: 00000073f5294840 LR: 00000070d8f39ba4 SP: 00000070d4afd5d0
X29: 00000070d4afd600 X28: b4000071efcda7f0 X27: 00000070d4afe000
X26: 0000000000000000 X25: 00000070d9616000 X24: 0000000000000000
X23: 0000000000000000 X22: 0000000000000000 X21: 0000000000000000
X20: b40000728fd27520 X19: b40000728fd27550 X18: 000000702daba000
X17: 00000073f5294820 X16: 00000070d940f9d8 X15: 00000000000000bf
X14: 0000000000000000 X13: 00000070d8ad2fac X12: b40000718fce5040
X11: 0000000000000000 X10: 0000000000000070 X9: 0000000000000001
X8: 0000000000000062 X7: 0000000000000020 X6: 0000000000000000
X5: 0000000000000000 X4: 0000000000000000 X3: 0000000000000000
X2: 0000000000000002 X1: 0000000000000080 X0: b40000728fd27550
ORIG_X0: b40000728fd27550 SYSCALLNO: ffffffff PSTATE: 40001000
Let's use GENMASK to replace the pac pointer to fix it.
gki related commit url here:
https://lore.kernel.org/all/20230412160134.306148-4-mark.rutland@arm.com/
Signed-off-by: bevis_chen <bevis_chen(a)asus.com>
---
arm64.c | 33 +++++++++++++++++++++++++++++++++
1 file changed, 33 insertions(+)
diff --git a/arm64.c b/arm64.c
index b3040d7..d8ce98f 100644
--- a/arm64.c
+++ b/arm64.c
@@ -92,6 +92,7 @@ static void arm64_get_crash_notes(void);
static void arm64_calc_VA_BITS(void);
static int arm64_is_uvaddr(ulong, struct task_context *);
static void arm64_calc_KERNELPACMASK(void);
+static void arm64_recalc_KERNELPACMASK(void);
static int arm64_get_vmcoreinfo(unsigned long *vaddr, const char *label, int base);
struct kernel_range {
@@ -581,6 +582,18 @@ arm64_init(int when)
if (!machdep->hz)
machdep->hz = 100;
+ /*
+ * In the case of using ramdump rather than vmcore,
+ * Will fail to parse out KERNELPAC.
+ * So let's try again from kconfig to ensure if PAC enabled.
+ * If yes, then we use vabits to figure it out.
+ * gki related commit url:
+ *
https://lore.kernel.org/all/20230412160134.306148-4-mark.rutland@arm.com/
+ */
+ if(!machdep->machspec->CONFIG_ARM64_KERNELPACMASK)
+ arm64_recalc_KERNELPACMASK();
+
+
arm64_irq_stack_init();
arm64_overflow_stack_init();
arm64_stackframe_init();
@@ -4921,6 +4934,26 @@ static void arm64_calc_KERNELPACMASK(void)
}
}
+
+#define GENMASK_UL(h, l) \
+ (((~0UL) << (l)) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+
+static void arm64_recalc_KERNELPACMASK(void){
+ if (kt->ikconfig_flags & IKCONFIG_AVAIL){
+ /* arm64: check pac already enabled yet.*/
+ if ((get_kernel_config("CONFIG_ARM64_PTR_AUTH", NULL) ==
IKCONFIG_Y)
+ &&
(get_kernel_config("CONFIG_ARM64_PTR_AUTH_KERNEL", NULL) == IKCONFIG_Y)){
+ if (machdep->machspec->VA_BITS_ACTUAL){
+ machdep->machspec->CONFIG_ARM64_KERNELPACMASK =
+ GENMASK_UL(63,
machdep->machspec->VA_BITS_ACTUAL);
+ if (CRASHDEBUG(1))
+ fprintf(fp, "CONFIG_ARM64_KERNELPACMASK:
%lx\n",
+
machdep->machspec->CONFIG_ARM64_KERNELPACMASK);
+ }
+ }
+ }
+}
+
#endif /* ARM64 */
--
2.27.0