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

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>

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index 17a71e92a343e128dc457e0db61f7185a59c3868..95eada2994e150a5c952bb0f773d3d9f6d814aae 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 390c4d13956d0c051494b3898ab13080a74e7494..5f0bc6a6d02556bd9a6c8173915c468ce8340518 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 6a9aa057f9ca099193519e950d72fb6aa97b6e21..ead967479fa6340efcb7565915294e4415807d62 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();