xen: delay xen_hvm_init_time_ops() if kdump is boot on vcpu>=32

The sched_clock() can be used very early since commit 857baa87b642
("sched/clock: Enable sched clock early"). In addition, with commit
38669ba205d1 ("x86/xen/time: Output xen sched_clock time from 0"), kdump
kernel in Xen HVM guest may panic at very early stage when accessing
&__this_cpu_read(xen_vcpu)->time as in below:

setup_arch()
 -> init_hypervisor_platform()
     -> x86_init.hyper.init_platform = xen_hvm_guest_init()
         -> xen_hvm_init_time_ops()
             -> xen_clocksource_read()
                 -> src = &__this_cpu_read(xen_vcpu)->time;

This is because Xen HVM supports at most MAX_VIRT_CPUS=32 'vcpu_info'
embedded inside 'shared_info' during early stage until xen_vcpu_setup() is
used to allocate/relocate 'vcpu_info' for boot cpu at arbitrary address.

However, when Xen HVM guest panic on vcpu >= 32, since
xen_vcpu_info_reset(0) would set per_cpu(xen_vcpu, cpu) = NULL when
vcpu >= 32, xen_clocksource_read() on vcpu >= 32 would panic.

This patch calls xen_hvm_init_time_ops() again later in
xen_hvm_smp_prepare_boot_cpu() after the 'vcpu_info' for boot vcpu is
registered when the boot vcpu is >= 32.

This issue can be reproduced on purpose via below command at the guest
side when kdump/kexec is enabled:

"taskset -c 33 echo c > /proc/sysrq-trigger"

The bugfix for PVM is not implemented due to the lack of testing
environment.

[boris: xen_hvm_init_time_ops() returns on errors instead of jumping to end]

Cc: Joe Jin <joe.jin@oracle.com>
Signed-off-by: Dongli Zhang <dongli.zhang@oracle.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Link: https://lore.kernel.org/r/20220302164032.14569-3-dongli.zhang@oracle.com
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>

2 files changed, 29 insertions, 1 deletions

diff --git a/arch/x86/xen/smp_hvm.c b/arch/x86/xen/smp_hvm.c
index 6ff3c887e0b9..b70afdff419c 100644
--- a/arch/x86/xen/smp_hvm.c
+++ b/arch/x86/xen/smp_hvm.c
@@ -20,6 +20,12 @@ static void __init xen_hvm_smp_prepare_boot_cpu(void)
 	xen_vcpu_setup(0);
 
 	/*
+	 * Called again in case the kernel boots on vcpu >= MAX_VIRT_CPUS.
+	 * Refer to comments in xen_hvm_init_time_ops().
+	 */
+	xen_hvm_init_time_ops();
+
+	/*
 	 * The alternative logic (which patches the unlock/lock) runs before
 	 * the smp bootup up code is activated. Hence we need to set this up
 	 * the core kernel is being patched. Otherwise we will have only
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index d9c945ee1100..9ef0a5cca96e 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -558,6 +558,11 @@ static void xen_hvm_setup_cpu_clockevents(void)
 
 void __init xen_hvm_init_time_ops(void)
 {
+	static bool hvm_time_initialized;
+
+	if (hvm_time_initialized)
+		return;
+
 	/*
 	 * vector callback is needed otherwise we cannot receive interrupts
 	 * on cpu > 0 and at this point we don't know how many cpus are
@@ -567,7 +572,22 @@ void __init xen_hvm_init_time_ops(void)
 		return;
 
 	if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
-		pr_info("Xen doesn't support pvclock on HVM, disable pv timer");
+		pr_info_once("Xen doesn't support pvclock on HVM, disable pv timer");
+		return;
+	}
+
+	/*
+	 * Only MAX_VIRT_CPUS 'vcpu_info' are embedded inside 'shared_info'.
+	 * The __this_cpu_read(xen_vcpu) is still NULL when Xen HVM guest
+	 * boots on vcpu >= MAX_VIRT_CPUS (e.g., kexec), To access
+	 * __this_cpu_read(xen_vcpu) via xen_clocksource_read() will panic.
+	 *
+	 * The xen_hvm_init_time_ops() should be called again later after
+	 * __this_cpu_read(xen_vcpu) is available.
+	 */
+	if (!__this_cpu_read(xen_vcpu)) {
+		pr_info("Delay xen_init_time_common() as kernel is running on vcpu=%d\n",
+			xen_vcpu_nr(0));
 		return;
 	}
 
@@ -577,6 +597,8 @@ void __init xen_hvm_init_time_ops(void)
 	x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
 
 	x86_platform.set_wallclock = xen_set_wallclock;
+
+	hvm_time_initialized = true;
 }
 #endif