[Qemu-devel] [PATCH 8/9] spapr: Implement processor compatibility in ibm, client-architecture-support

[Alexey Kardashevskiy <aik@ozlabs.ru>]

Modern Linux kernels support last POWERPC CPUs so when a kernel boots,
in most cases it can find a matching cpu_spec in the kernel's cpu_specs
list. However if the kernel is quite old, it may be missing a definition
of the actual CPU. To provide an ability for old kernels to work on modern
hardware, a Processor Compatibility Mode has been introduced
by the PowerISA specification.

>From the hardware prospective, it is supported by the Processor
Compatibility Register (PCR) which is defined in PowerISA. The register
enables one of the compatibility modes (2.05/2.06/2.07).
Since PCR is a hypervisor privileged register and cannot be
accessed from the guest, the mode selection is done via
ibm,client-architecture-support (CAS) RTAS call using which the guest
specifies what "raw" and "architected" CPU versions it supports.
QEMU works out the best match, changes a "cpu-version" property of
every CPU and notifies the guest about the change by setting these
properties in the buffer passed as a response on a custom H_CAS hypercall.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 hw/ppc/spapr.c       | 40 +++++++++++++++++++++++++
 hw/ppc/spapr_hcall.c | 83 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 trace-events         |  5 ++++
 3 files changed, 128 insertions(+)

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index a2c9106..a0882a1 100644
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -35,6 +35,7 @@
 #include "kvm_ppc.h"
 #include "mmu-hash64.h"
 #include "cpu-models.h"
+#include "qom/cpu.h"
 
 #include "hw/boards.h"
 #include "hw/ppc/ppc.h"
@@ -592,11 +593,50 @@ int spapr_h_cas_compose_response(target_ulong addr, target_ulong size)
 {
     void *fdt;
     sPAPRDeviceTreeUpdateHeader hdr = { .version_id = 1 };
+    CPUState *cs;
+    int smt = kvmppc_smt_threads();
 
     size -= sizeof(hdr);
 
     fdt = g_malloc0(size);
     _FDT((fdt_create(fdt, size)));
+    _FDT((fdt_begin_node(fdt, "cpus")));
+
+    CPU_FOREACH(cs) {
+        PowerPCCPU *cpu = POWERPC_CPU(cs);
+        DeviceClass *dc = DEVICE_GET_CLASS(cpu);
+        int smpt = spapr_get_compat_smp_threads(cpu);
+        int i, index = ppc_get_vcpu_dt_id(cpu);
+        uint32_t servers_prop[smpt];
+        uint32_t gservers_prop[smpt * 2];
+        char tmp[32];
+
+        if ((index % smt) != 0) {
+            continue;
+        }
+
+        snprintf(tmp, 32, "%s@%x", dc->fw_name, index);
+        trace_spapr_cas_add_subnode(tmp);
+
+        _FDT((fdt_begin_node(fdt, tmp)));
+        _FDT((fdt_property_cell(fdt, "cpu-version", cpu->cpu_version)));
+
+        /* Build interrupt servers and gservers properties */
+        for (i = 0; i < smpt; i++) {
+            servers_prop[i] = cpu_to_be32(index + i);
+            /* Hack, direct the group queues back to cpu 0 */
+            gservers_prop[i*2] = cpu_to_be32(index + i);
+            gservers_prop[i*2 + 1] = 0;
+        }
+        _FDT((fdt_property(fdt, "ibm,ppc-interrupt-server#s",
+                           servers_prop, sizeof(servers_prop))));
+        _FDT((fdt_property(fdt, "ibm,ppc-interrupt-gserver#s",
+                           gservers_prop, sizeof(gservers_prop))));
+
+        _FDT((fdt_end_node(fdt)));
+    }
+
+    _FDT((fdt_end_node(fdt)));
 
     _FDT((fdt_finish(fdt)));
 
diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c
index 2f6aa5c..cb815c3 100644
--- a/hw/ppc/spapr_hcall.c
+++ b/hw/ppc/spapr_hcall.c
@@ -3,6 +3,9 @@
 #include "helper_regs.h"
 #include "hw/ppc/spapr.h"
 #include "mmu-hash64.h"
+#include "cpu-models.h"
+#include "trace.h"
+#include "kvm_ppc.h"
 
 struct SPRSyncState {
     CPUState *cs;
@@ -752,12 +755,92 @@ out:
     return ret;
 }
 
+#define get_compat_level(cpuver) ( \
+    ((cpuver) == CPU_POWERPC_LOGICAL_2_05) ? 2050 : \
+    ((cpuver) == CPU_POWERPC_LOGICAL_2_06) ? 2060 : \
+    ((cpuver) == CPU_POWERPC_LOGICAL_2_06_PLUS) ? 2061 : \
+    ((cpuver) == CPU_POWERPC_LOGICAL_2_07) ? 2070 : 0)
+
 static target_ulong h_client_architecture_support(PowerPCCPU *cpu_,
                                                   sPAPREnvironment *spapr,
                                                   target_ulong opcode,
                                                   target_ulong *args)
 {
     target_ulong list = args[0];
+    PowerPCCPUClass *pcc_ = POWERPC_CPU_GET_CLASS(cpu_);
+    CPUState *cs;
+    CPUState *cs_ = CPU(cpu_);
+    bool cpu_match = false;
+    unsigned old_cpu_version = cpu_->cpu_version;
+    unsigned compat_lvl = 0, cpu_version = 0;
+    unsigned max_lvl = get_compat_level(cpu_->max_compat);
+
+    /* Parse PVR list */
+    for ( ; ; ) {
+        uint32_t pvr, pvr_mask;
+
+        pvr_mask = ldl_phys(cs_->as, list);
+        list += 4;
+        pvr = ldl_phys(cs_->as, list);
+        list += 4;
+
+        trace_spapr_cas_pvr_try(pvr);
+        if (!max_lvl &&
+            ((cpu_->env.spr[SPR_PVR] & pvr_mask) == (pvr & pvr_mask))) {
+            cpu_match = true;
+            cpu_version = 0;
+        } else if (pvr == cpu_->cpu_version) {
+            cpu_match = true;
+            cpu_version = cpu_->cpu_version;
+        } else if (!cpu_match) {
+            /* If it is a logical PVR, try to determine the highest level */
+            unsigned lvl = get_compat_level(pvr);
+            if (lvl) {
+                bool is205 = (pcc_->pcr_mask & POWERPC_ISA_COMPAT_2_05) &&
+                     (lvl == get_compat_level(CPU_POWERPC_LOGICAL_2_05));
+                bool is206 = (pcc_->pcr_mask & POWERPC_ISA_COMPAT_2_06) &&
+                    ((lvl == get_compat_level(CPU_POWERPC_LOGICAL_2_06)) ||
+                    (lvl == get_compat_level(CPU_POWERPC_LOGICAL_2_06_PLUS)));
+
+                if (is205 || is206) {
+                    if (!max_lvl) {
+                        /* User did not set the level, choose the highest */
+                        if (compat_lvl <= lvl) {
+                            compat_lvl = lvl;
+                            cpu_version = pvr;
+                        }
+                    } else if (max_lvl >= lvl) {
+                        /* User chose the level, don't set higher than this */
+                        compat_lvl = lvl;
+                        cpu_version = pvr;
+                    }
+                }
+            }
+        }
+        /* Terminator record */
+        if (~pvr_mask & pvr) {
+            break;
+        }
+    }
+
+    /* For the future use: here @list points to the first capability */
+
+    /* Parsing finished */
+    trace_spapr_cas_pvr(cpu_->cpu_version, cpu_match,
+                        cpu_version, pcc_->pcr_mask);
+
+    /* Update CPUs */
+    if (old_cpu_version != cpu_version) {
+        CPU_FOREACH(cs) {
+            PowerPCCPU *cpu = POWERPC_CPU(cs);
+
+            ppc_set_compat(cpu, cpu_version);
+        }
+    }
+
+    if (!cpu_version) {
+        return H_SUCCESS;
+    }
 
     if (!list) {
         return H_SUCCESS;
diff --git a/trace-events b/trace-events
index 03565dc..c2db909 100644
--- a/trace-events
+++ b/trace-events
@@ -1182,6 +1182,11 @@ xics_ics_eoi(int nr) "ics_eoi: irq %#x"
 # hw/ppc/spapr.c
 spapr_cas_failed(unsigned long n) "DT diff buffer is too small: %ld bytes"
 spapr_cas_continue(unsigned long n) "Copy changes to the guest: %ld bytes"
+spapr_cas_add_subnode(const char *s) "%s"
+
+# hw/ppc/spapr_hcall.c
+spapr_cas_pvr_try(uint32_t pvr) "%x"
+spapr_cas_pvr(uint32_t cur_pvr, bool cpu_match, uint32_t new_pvr, uint64_t pcr) "current=%x, cpu_match=%u, new=%x, compat flags=%"PRIx64
 
 # hw/ppc/spapr_iommu.c
 spapr_iommu_put(uint64_t liobn, uint64_t ioba, uint64_t tce, uint64_t ret) "liobn=%"PRIx64" ioba=0x%"PRIx64" tce=0x%"PRIx64" ret=%"PRId64
-- 
1.9.rc0