spapr: Add ibm, client-architecture-support call

The PAPR+ specification defines a ibm,client-architecture-support (CAS)
RTAS call which purpose is to provide a negotiation mechanism for
the guest and the hypervisor to work out the best compatibility parameters.
During the negotiation process, the guest provides an array of various
options and capabilities which it supports, the hypervisor adjusts
the device tree and (optionally) reboots the guest.

At the moment the Linux guest calls CAS method at early boot so SLOF
gets called. SLOF allocates a memory buffer for the device tree changes
and calls a custom KVMPPC_H_CAS hypercall. QEMU parses the options,
composes a diff for the device tree, copies it to the buffer provided
by SLOF and returns to SLOF. SLOF updates the device tree and returns
control to the guest kernel. Only then the Linux guest parses the device
tree so it is possible to avoid unnecessary reboot in most cases.

The device tree diff is a header with an update format version
(defined as 1 in this patch) followed by a device tree with the properties
which require update.

If QEMU detects that it has to reboot the guest, it silently does so
as the guest expects reboot to happen because this is usual pHyp firmware
behavior.

This defines custom KVMPPC_H_CAS hypercall. The current SLOF already
has support for it.

This implements stub which returns very basic tree (root node,
no properties) to the guest.

As the return buffer does not contain any change, no change in behavior is
expected.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Signed-off-by: Alexander Graf <agraf@suse.de>

hw/ppc/spapr.c

@@ -53,6 +53,7 @@
 #include "hw/usb.h"
 #include "qemu/config-file.h"
 #include "qemu/error-report.h"
+#include "trace.h"
 
 #include <libfdt.h>
 
@@ -559,6 +560,41 @@ static void *spapr_create_fdt_skel(hwaddr initrd_base,
     return fdt;
 }
 
+int spapr_h_cas_compose_response(target_ulong addr, target_ulong size)
+{
+    void *fdt, *fdt_skel;
+    sPAPRDeviceTreeUpdateHeader hdr = { .version_id = 1 };
+
+    size -= sizeof(hdr);
+
+    /* Create sceleton */
+    fdt_skel = g_malloc0(size);
+    _FDT((fdt_create(fdt_skel, size)));
+    _FDT((fdt_begin_node(fdt_skel, "")));
+    _FDT((fdt_end_node(fdt_skel)));
+    _FDT((fdt_finish(fdt_skel)));
+    fdt = g_malloc0(size);
+    _FDT((fdt_open_into(fdt_skel, fdt, size)));
+    g_free(fdt_skel);
+
+    /* Place to make changes to the tree */
+
+    /* Pack resulting tree */
+    _FDT((fdt_pack(fdt)));
+
+    if (fdt_totalsize(fdt) + sizeof(hdr) > size) {
+        trace_spapr_cas_failed(size);
+        return -1;
+    }
+
+    cpu_physical_memory_write(addr, &hdr, sizeof(hdr));
+    cpu_physical_memory_write(addr + sizeof(hdr), fdt, fdt_totalsize(fdt));
+    trace_spapr_cas_continue(fdt_totalsize(fdt) + sizeof(hdr));
+    g_free(fdt);
+
+    return 0;
+}
+
 static int spapr_populate_memory(sPAPREnvironment *spapr, void *fdt)
 {
     uint32_t associativity[] = {cpu_to_be32(0x4), cpu_to_be32(0x0),

hw/ppc/spapr_hcall.c

@@ -752,6 +752,24 @@ out:
     return ret;
 }
 
+static target_ulong h_client_architecture_support(PowerPCCPU *cpu_,
+                                                  sPAPREnvironment *spapr,
+                                                  target_ulong opcode,
+                                                  target_ulong *args)
+{
+    target_ulong list = args[0];
+
+    if (!list) {
+        return H_SUCCESS;
+    }
+
+    if (spapr_h_cas_compose_response(args[1], args[2])) {
+        qemu_system_reset_request();
+    }
+
+    return H_SUCCESS;
+}
+
 static spapr_hcall_fn papr_hypercall_table[(MAX_HCALL_OPCODE / 4) + 1];
 static spapr_hcall_fn kvmppc_hypercall_table[KVMPPC_HCALL_MAX - KVMPPC_HCALL_BASE + 1];
 
@@ -831,6 +849,9 @@ static void hypercall_register_types(void)
     spapr_register_hypercall(KVMPPC_H_RTAS, h_rtas);
 
     spapr_register_hypercall(H_SET_MODE, h_set_mode);
+
+    /* ibm,client-architecture-support support */
+    spapr_register_hypercall(KVMPPC_H_CAS, h_client_architecture_support);
 }
 
 type_init(hypercall_register_types)

include/hw/ppc/spapr.h

@@ -303,10 +303,16 @@ typedef struct sPAPREnvironment {
 #define KVMPPC_HCALL_BASE       0xf000
 #define KVMPPC_H_RTAS           (KVMPPC_HCALL_BASE + 0x0)
 #define KVMPPC_H_LOGICAL_MEMOP  (KVMPPC_HCALL_BASE + 0x1)
-#define KVMPPC_HCALL_MAX        KVMPPC_H_LOGICAL_MEMOP
+/* Client Architecture support */
+#define KVMPPC_H_CAS            (KVMPPC_HCALL_BASE + 0x2)
+#define KVMPPC_HCALL_MAX        KVMPPC_H_CAS
 
 extern sPAPREnvironment *spapr;
 
+typedef struct sPAPRDeviceTreeUpdateHeader {
+    uint32_t version_id;
+} sPAPRDeviceTreeUpdateHeader;
+
 /*#define DEBUG_SPAPR_HCALLS*/
 
 #ifdef DEBUG_SPAPR_HCALLS
@@ -402,6 +408,7 @@ struct sPAPRTCETable {
 
 void spapr_events_init(sPAPREnvironment *spapr);
 void spapr_events_fdt_skel(void *fdt, uint32_t epow_irq);
+int spapr_h_cas_compose_response(target_ulong addr, target_ulong size);
 sPAPRTCETable *spapr_tce_new_table(DeviceState *owner, uint32_t liobn,
                                    size_t window_size);
 MemoryRegion *spapr_tce_get_iommu(sPAPRTCETable *tcet);

trace-events

@@ -1189,6 +1189,10 @@ xics_ics_write_xive(int nr, int srcno, int server, uint8_t priority) "ics_write_
 xics_ics_reject(int nr, int srcno) "reject irq %#x [src %d]"
 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"
+
 # 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
 spapr_iommu_get(uint64_t liobn, uint64_t ioba, uint64_t ret, uint64_t tce) "liobn=%"PRIx64" ioba=0x%"PRIx64" ret=%"PRId64" tce=0x%"PRIx64