spapr: Workaround for broken radix guests

For a little while around 4.9, Linux kernels that saw the radix bit in
ibm,pa-features would attempt to set up the MMU as if they were a
hypervisor, even if they were a guest, which would cause them to
crash.

Work around this by detecting pre-ISA 3.0 guests by their lack of that
bit in option vector 1, and then removing the radix bit from
ibm,pa-features. Note: This now requires regeneration of that node
after CAS negotiation.

Signed-off-by: Sam Bobroff <sam.bobroff@au1.ibm.com>
[dwg: Fix style nits]
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

2 files changed, 17 insertions, 4 deletions

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index d967ec30b4..a355512849 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -228,7 +228,8 @@ static int spapr_fixup_cpu_numa_dt(void *fdt, int offset, CPUState *cs)
 }
 
 /* Populate the "ibm,pa-features" property */
-static void spapr_populate_pa_features(CPUPPCState *env, void *fdt, int offset)
+static void spapr_populate_pa_features(CPUPPCState *env, void *fdt, int offset,
+                                      bool legacy_guest)
 {
     uint8_t pa_features_206[] = { 6, 0,
         0xf6, 0x1f, 0xc7, 0x00, 0x80, 0xc0 };
@@ -295,6 +296,12 @@ static void spapr_populate_pa_features(CPUPPCState *env, void *fdt, int offset)
     if (kvmppc_has_cap_htm() && pa_size > 24) {
         pa_features[24] |= 0x80;    /* Transactional memory support */
     }
+    if (legacy_guest && pa_size > 40) {
+        /* Workaround for broken kernels that attempt (guest) radix
+         * mode when they can't handle it, if they see the radix bit set
+         * in pa-features. So hide it from them. */
+        pa_features[40 + 2] &= ~0x80; /* Radix MMU */
+    }
 
     _FDT((fdt_setprop(fdt, offset, "ibm,pa-features", pa_features, pa_size)));
 }
@@ -309,6 +316,7 @@ static int spapr_fixup_cpu_dt(void *fdt, sPAPRMachineState *spapr)
 
     CPU_FOREACH(cs) {
         PowerPCCPU *cpu = POWERPC_CPU(cs);
+        CPUPPCState *env = &cpu->env;
         DeviceClass *dc = DEVICE_GET_CLASS(cs);
         int index = ppc_get_vcpu_dt_id(cpu);
         int compat_smt = MIN(smp_threads, ppc_compat_max_threads(cpu));
@@ -350,6 +358,9 @@ static int spapr_fixup_cpu_dt(void *fdt, sPAPRMachineState *spapr)
         if (ret < 0) {
             return ret;
         }
+
+        spapr_populate_pa_features(env, fdt, offset,
+                                         spapr->cas_legacy_guest_workaround);
     }
     return ret;
 }
@@ -547,7 +558,7 @@ static void spapr_populate_cpu_dt(CPUState *cs, void *fdt, int offset,
                           page_sizes_prop, page_sizes_prop_size)));
     }
 
-    spapr_populate_pa_features(env, fdt, offset);
+    spapr_populate_pa_features(env, fdt, offset, false);
 
     _FDT((fdt_setprop_cell(fdt, offset, "ibm,chip-id",
                            cs->cpu_index / vcpus_per_socket)));
diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c
index cbd1f296d6..9f18f75b88 100644
--- a/hw/ppc/spapr_hcall.c
+++ b/hw/ppc/spapr_hcall.c
@@ -1062,7 +1062,7 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu,
     uint32_t max_compat = cpu->max_compat;
     uint32_t best_compat = 0;
     int i;
-    sPAPROptionVector *ov5_guest, *ov5_cas_old, *ov5_updates;
+    sPAPROptionVector *ov1_guest, *ov5_guest, *ov5_cas_old, *ov5_updates;
     bool guest_radix;
 
     /*
@@ -1114,6 +1114,7 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu,
     /* For the future use: here @ov_table points to the first option vector */
     ov_table = list;
 
+    ov1_guest = spapr_ovec_parse_vector(ov_table, 1);
     ov5_guest = spapr_ovec_parse_vector(ov_table, 5);
     if (spapr_ovec_test(ov5_guest, OV5_MMU_BOTH)) {
         error_report("guest requested hash and radix MMU, which is invalid.");
@@ -1155,7 +1156,8 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu,
             exit(EXIT_FAILURE);
         }
     }
-
+    spapr->cas_legacy_guest_workaround = !spapr_ovec_test(ov1_guest,
+                                                          OV1_PPC_3_00);
     if (!spapr->cas_reboot) {
         spapr->cas_reboot =
             (spapr_h_cas_compose_response(spapr, args[1], args[2],