On Mon, Apr 28, 2025 at 09:41:51PM +0000, Ashish Kalra wrote:
> From: Ashish Kalra <[email protected]>
>
> When kdump is running makedumpfile to generate vmcore and dumping SNP
> guest memory it touches the VMSA page of the vCPU executing kdump which
> then results in unrecoverable #NPF/RMP faults as the VMSA page is
> marked busy/in-use when the vCPU is running and subsequently causes
> guest softlockup/hang.
>
> Additionally other APs may be halted in guest mode and their VMSA pages
> are marked busy and touching these VMSA pages during guest memory dump
> will also cause #NPF.
>
> Issue AP_DESTROY GHCB calls on other APs to ensure they are kicked out
> of guest mode and then clear the VMSA bit on their VMSA pages.
>
> If the vCPU running kdump is an AP, mark it's VMSA page as offline to
> ensure that makedumpfile excludes that page while dumping guest memory.
>
> Cc: [email protected]
> Fixes: 3074152e56c9 ("x86/sev: Convert shared memory back to private on
> kexec")
> Signed-off-by: Ashish Kalra <[email protected]>
> ---
> arch/x86/coco/sev/core.c | 241 +++++++++++++++++++++++++--------------
> 1 file changed, 155 insertions(+), 86 deletions(-)
Some minor cleanups ontop:
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index b031cabb2ccf..9ac902d022bf 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -961,6 +961,7 @@ void snp_accept_memory(phys_addr_t start, phys_addr_t end)
static int vmgexit_ap_control(u64 event, struct sev_es_save_area *vmsa, u32
apic_id)
{
+ bool create = event == SVM_VMGEXIT_AP_CREATE;
struct ghcb_state state;
unsigned long flags;
struct ghcb *ghcb;
@@ -971,8 +972,10 @@ static int vmgexit_ap_control(u64 event, struct
sev_es_save_area *vmsa, u32 apic
ghcb = __sev_get_ghcb(&state);
vc_ghcb_invalidate(ghcb);
- if (event == SVM_VMGEXIT_AP_CREATE)
+
+ if (create)
ghcb_set_rax(ghcb, vmsa->sev_features);
+
ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_CREATION);
ghcb_set_sw_exit_info_1(ghcb,
((u64)apic_id << 32) |
@@ -985,7 +988,7 @@ static int vmgexit_ap_control(u64 event, struct
sev_es_save_area *vmsa, u32 apic
if (!ghcb_sw_exit_info_1_is_valid(ghcb) ||
lower_32_bits(ghcb->save.sw_exit_info_1)) {
- pr_err("SNP AP %s error\n", (event == SVM_VMGEXIT_AP_CREATE ?
"CREATE" : "DESTROY"));
+ pr_err("SNP AP %s error\n", (create ? "CREATE" : "DESTROY"));
ret = -EINVAL;
}
@@ -1168,8 +1171,8 @@ static void shutdown_all_aps(void)
vmsa = per_cpu(sev_vmsa, cpu);
/*
- * BSP does not have guest allocated VMSA and there is no need
- * to clear the VMSA tag for this page.
+ * The BSP or offlined APs do not have guest allocated VMSA
+ * and there is no need to clear the VMSA tag for this page.
*/
if (!vmsa)
continue;
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
