x86/hyperv: fix kexec crash due to VP assist page corruption

commit b9af6418279c4cf73ca073f8ea024992b38be8ab upstream.

commit 9636be85cc5b ("x86/hyperv: Fix hyperv_pcpu_input_arg handling when
CPUs go online/offline") introduces a new cpuhp state for hyperv
initialization.

cpuhp_setup_state() returns the state number if state is
CPUHP_AP_ONLINE_DYN or CPUHP_BP_PREPARE_DYN and 0 for all other states.
For the hyperv case, since a new cpuhp state was introduced it would
return 0. However, in hv_machine_shutdown(), the cpuhp_remove_state() call
is conditioned upon "hyperv_init_cpuhp > 0". This will never be true and
so hv_cpu_die() won't be called on all CPUs. This means the VP assist page
won't be reset. When the kexec kernel tries to setup the VP assist page
again, the hypervisor corrupts the memory region of the old VP assist page
causing a panic in case the kexec kernel is using that memory elsewhere.
This was originally fixed in commit dfe94d4086e4 ("x86/hyperv: Fix kexec
panic/hang issues").

Get rid of hyperv_init_cpuhp entirely since we are no longer using a
dynamic cpuhp state and use CPUHP_AP_HYPERV_ONLINE directly with
cpuhp_remove_state().

Cc: stable@vger.kernel.org
Fixes: 9636be85cc5b ("x86/hyperv: Fix hyperv_pcpu_input_arg handling when CPUs go online/offline")
Signed-off-by: Anirudh Rayabharam (Microsoft) <anirudh@anirudhrb.com>
Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Link: https://lore.kernel.org/r/20240828112158.3538342-1-anirudh@anirudhrb.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Message-ID: <20240828112158.3538342-1-anirudh@anirudhrb.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 8f3a4d16bb791f37ac924858668d37eb49446f91..d1e2d12279e26866184a0aa3ecef97d5bc860ccf 100644 (file)
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -35,7 +35,6 @@
 #include <clocksource/hyperv_timer.h>
 #include <linux/highmem.h>
 
-int hyperv_init_cpuhp;
 u64 hv_current_partition_id = ~0ull;
 EXPORT_SYMBOL_GPL(hv_current_partition_id);
 
@@ -607,8 +606,6 @@ skip_hypercall_pg_init:
 
        register_syscore_ops(&hv_syscore_ops);
 
-       hyperv_init_cpuhp = cpuhp;
-
        if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID)
                hv_get_partition_id();
 
@@ -637,7 +634,7 @@ skip_hypercall_pg_init:
 clean_guest_os_id:
        wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
        hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
-       cpuhp_remove_state(cpuhp);
+       cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE);
 free_ghcb_page:
        free_percpu(hv_ghcb_pg);
 free_vp_assist_page:

diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 896445edc6a8e924910bd2b04e43e7fee248ee52..ec95d6e9f1682c7c30ac8a32db2261d3eb4a6eeb 100644 (file)
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -40,7 +40,6 @@ static inline unsigned char hv_get_nmi_reason(void)
 }
 
 #if IS_ENABLED(CONFIG_HYPERV)
-extern int hyperv_init_cpuhp;
 extern bool hyperv_paravisor_present;
 
 extern void *hv_hypercall_pg;

diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index e6bba12c759cb793a2a3eb0ff367bb51a6b502f0..fac4b4116efe102612f6eae1a2437685d18be329 100644 (file)
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -199,8 +199,8 @@ static void hv_machine_shutdown(void)
         * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor
         * corrupts the old VP Assist Pages and can crash the kexec kernel.
         */
-       if (kexec_in_progress && hyperv_init_cpuhp > 0)
-               cpuhp_remove_state(hyperv_init_cpuhp);
+       if (kexec_in_progress)
+               cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE);
 
        /* The function calls stop_other_cpus(). */
        native_machine_shutdown();