pseries: fix kvmppc_set_fwnmi()

QEMU issues the ioctl(KVM_CAP_PPC_FWNMI) on the first vCPU.

If the first vCPU is currently running, the vCPU mutex is held
and the ioctl() cannot be done and waits until the mutex is released.
This never happens and the VM is stuck.

To avoid this deadlock, issue the ioctl on the same vCPU doing the
RTAS call.

The problem can be reproduced by booting a guest with several vCPUs
(the probability to have the problem is (n - 1) / n,  n = # of CPUs),
and then by triggering a kernel crash with "echo c >/proc/sysrq-trigger".

On the reboot, the kernel hangs after:

...
[    0.000000] -----------------------------------------------------
[    0.000000] ppc64_pft_size    = 0x0
[    0.000000] phys_mem_size     = 0x48000000
[    0.000000] dcache_bsize      = 0x80
[    0.000000] icache_bsize      = 0x80
[    0.000000] cpu_features      = 0x0001c06f8f4f91a7
[    0.000000]   possible        = 0x0003fbffcf5fb1a7
[    0.000000]   always          = 0x00000003800081a1
[    0.000000] cpu_user_features = 0xdc0065c2 0xaee00000
[    0.000000] mmu_features      = 0x3c006041
[    0.000000] firmware_features = 0x00000085455a445f
[    0.000000] physical_start    = 0x8000000
[    0.000000] -----------------------------------------------------
[    0.000000] numa:   NODE_DATA [mem 0x47f33c80-0x47f3ffff]

Fixes: ec010c00665b ("ppc/spapr: KVM FWNMI should not be enabled until guest requests it")
Cc: [email protected]
Signed-off-by: Laurent Vivier <[email protected]>
Message-Id: <20200724083533[email protected]>
Signed-off-by: David Gibson <[email protected]>

diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c
index bcac0d00e7b6b5cf639c65b82cca9bc631824b1b..513c7a84351bcfb31638c7b655e91edc4a6ebb6f 100644 (file)
--- a/hw/ppc/spapr_rtas.c
+++ b/hw/ppc/spapr_rtas.c
@@ -438,7 +438,7 @@ static void rtas_ibm_nmi_register(PowerPCCPU *cpu,
     }
 
     if (kvm_enabled()) {
-        if (kvmppc_set_fwnmi() < 0) {
+        if (kvmppc_set_fwnmi(cpu) < 0) {
             rtas_st(rets, 0, RTAS_OUT_NOT_SUPPORTED);
             return;
         }

diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c
index 2692f76130aae94e0ff4367e3f5efc21afb14d09..d85ba8ffe00b8fac65cddc618b540282e7d4bd63 100644 (file)
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -2071,9 +2071,8 @@ bool kvmppc_get_fwnmi(void)
     return cap_fwnmi;
 }
 
-int kvmppc_set_fwnmi(void)
+int kvmppc_set_fwnmi(PowerPCCPU *cpu)
 {
-    PowerPCCPU *cpu = POWERPC_CPU(first_cpu);
     CPUState *cs = CPU(cpu);
 
     return kvm_vcpu_enable_cap(cs, KVM_CAP_PPC_FWNMI, 0);

diff --git a/target/ppc/kvm_ppc.h b/target/ppc/kvm_ppc.h
index 701c0c262be2a65cf36ee98c13c1c56c622a109c..72e05f1cd2fcb9d3aac0da4f17a835830e3019c2 100644 (file)
--- a/target/ppc/kvm_ppc.h
+++ b/target/ppc/kvm_ppc.h
@@ -28,7 +28,7 @@ void kvmppc_set_papr(PowerPCCPU *cpu);
 int kvmppc_set_compat(PowerPCCPU *cpu, uint32_t compat_pvr);
 void kvmppc_set_mpic_proxy(PowerPCCPU *cpu, int mpic_proxy);
 bool kvmppc_get_fwnmi(void);
-int kvmppc_set_fwnmi(void);
+int kvmppc_set_fwnmi(PowerPCCPU *cpu);
 int kvmppc_smt_threads(void);
 void kvmppc_error_append_smt_possible_hint(Error *const *errp);
 int kvmppc_set_smt_threads(int smt);
@@ -169,7 +169,7 @@ static inline bool kvmppc_get_fwnmi(void)
     return false;
 }
 
-static inline int kvmppc_set_fwnmi(void)
+static inline int kvmppc_set_fwnmi(PowerPCCPU *cpu)
 {
     return -1;
 }