[Qemu-devel] [PATCH 28/28] Implement PAPR VPA functions for pSeries shared processor partitions

[qemu@gibson.dropbear.id.au]

From: David Gibson <david@gibson.dropbear.id.au>

Shared-processor partitions are those where a CPU is time-sliced between
partitions, rather than being permanently dedicated to a single
partition.  qemu emulated partitions, since they are just scheduled with
the qemu user process, behave mostly like shared processor partitions.

In order to better support shared processor partitions (splpar), PAPR
defines the "VPA" (Virtual Processor Area), a shared memory communication
channel between the hypervisor and partitions.  There are also two
additional shared memory communication areas for specialized purposes
associated with the VPA.

A VPA is not essential for operating an splpar, though it can be necessary
for obtaining accurate performance measurements in the presence of
runtime partition switching.

Most importantly, however, the VPA is a prerequisite for PAPR's H_CEDE,
hypercall, which allows a partition OS to give up it's shared processor
timeslices to other partitions when idle.

This patch implements the VPA and H_CEDE hypercalls in qemu.  We don't
implement any of the more advanced statistics which can be communicated
through the VPA.  However, this is enough to make normal pSeries kernels
do an effective power-save idle on an emulated pSeries, significantly
reducing the host load of a qemu emulated pSeries running an idle guest OS.

Signed-off-by: David Gibson <dwg@au1.ibm.com>
---
 hw/spapr.c       |    2 +-
 hw/spapr_hcall.c |  192 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 target-ppc/cpu.h |    4 +
 3 files changed, 197 insertions(+), 1 deletions(-)

diff --git a/hw/spapr.c b/hw/spapr.c
index 80ea512..2e04554 100644
--- a/hw/spapr.c
+++ b/hw/spapr.c
@@ -68,7 +68,7 @@ static void *spapr_create_fdt(int *fdt_size, ram_addr_t ramsize,
     uint32_t end_prop = cpu_to_be32(initrd_base + initrd_size);
     uint32_t pft_size_prop[] = {0, cpu_to_be32(hash_shift)};
     char hypertas_prop[] = "hcall-pft\0hcall-term\0hcall-dabr\0hcall-interrupt"
-        "\0hcall-tce\0hcall-vio";
+        "\0hcall-tce\0hcall-vio\0hcall-splpar";
     uint32_t interrupt_server_ranges_prop[] = {0, cpu_to_be32(smp_cpus)};
     int i;
     char *modelname;
diff --git a/hw/spapr_hcall.c b/hw/spapr_hcall.c
index 0ff83c9..6f65655 100644
--- a/hw/spapr_hcall.c
+++ b/hw/spapr_hcall.c
@@ -4,6 +4,8 @@
 #include "sysemu.h"
 #include "qemu-char.h"
 #include "exec-all.h"
+#include "exec.h"
+#include "helper_regs.h"
 #include "hw/spapr.h"
 
 #define HPTES_PER_GROUP 8
@@ -248,6 +250,192 @@ static target_ulong h_set_dabr(CPUState *env, sPAPREnvironment *spapr,
     return H_HARDWARE;
 }
 
+#define FLAGS_REGISTER_VPA         0x0000200000000000ULL
+#define FLAGS_REGISTER_DTL         0x0000400000000000ULL
+#define FLAGS_REGISTER_SLBSHADOW   0x0000600000000000ULL
+#define FLAGS_DEREGISTER_VPA       0x0000a00000000000ULL
+#define FLAGS_DEREGISTER_DTL       0x0000c00000000000ULL
+#define FLAGS_DEREGISTER_SLBSHADOW 0x0000e00000000000ULL
+
+#define VPA_MIN_SIZE           640
+#define VPA_SIZE_OFFSET        0x4
+#define VPA_SHARED_PROC_OFFSET 0x9
+#define VPA_SHARED_PROC_VAL    0x2
+
+static target_ulong register_vpa(CPUState *env, target_ulong vpa)
+{
+    uint16_t size;
+    uint8_t tmp;
+
+    if (vpa == 0) {
+        fprintf(stderr, "Can't cope with registering a VPA at logical 0\n");
+        return H_HARDWARE;
+    }
+
+    if (vpa % env->dcache_line_size) {
+        return H_PARAMETER;
+    }
+    /* FIXME: bounds check the address */
+
+    size = lduw_phys(vpa + 0x4);
+
+    if (size < VPA_MIN_SIZE) {
+        return H_PARAMETER;
+    }
+
+    /* VPA is not allowed to cross a page boundary */
+    if ((vpa / 4096) != ((vpa + size - 1) / 4096)) {
+        return H_PARAMETER;
+    }
+
+    env->vpa = vpa;
+
+    tmp = ldub_phys(env->vpa + VPA_SHARED_PROC_OFFSET);
+    tmp |= VPA_SHARED_PROC_VAL;
+    stb_phys(env->vpa + VPA_SHARED_PROC_OFFSET, tmp);
+
+    return H_SUCCESS;
+}
+
+static target_ulong deregister_vpa(CPUState *env, target_ulong vpa)
+{
+    if (env->slb_shadow) {
+        return H_RESOURCE;
+    }
+
+    if (env->dispatch_trace_log) {
+        return H_RESOURCE;
+    }
+
+    env->vpa = 0;
+    return H_SUCCESS;
+}
+
+static target_ulong register_slb_shadow(CPUState *env, target_ulong addr)
+{
+    uint32_t size;
+
+    if (addr == 0) {
+        fprintf(stderr, "Can't cope with SLB shadow at logical 0\n");
+        return H_HARDWARE;
+    }
+
+    size = ldl_phys(addr + 0x4);
+    if (size < 0x8) {
+        return H_PARAMETER;
+    }
+
+    if ((addr / 4096) != ((addr + size - 1) / 4096)) {
+        return H_PARAMETER;
+    }
+
+    if (!env->vpa) {
+        return H_RESOURCE;
+    }
+
+    env->slb_shadow = addr;
+
+    return H_SUCCESS;
+}
+
+static target_ulong deregister_slb_shadow(CPUState *env, target_ulong addr)
+{
+    env->slb_shadow = 0;
+    return H_SUCCESS;
+}
+
+static target_ulong register_dtl(CPUState *env, target_ulong addr)
+{
+    uint32_t size;
+
+    if (addr == 0) {
+        fprintf(stderr, "Can't cope with DTL at logical 0\n");
+        return H_HARDWARE;
+    }
+
+    size = ldl_phys(addr + 0x4);
+
+    if (size < 48) {
+        return H_PARAMETER;
+    }
+
+    if (!env->vpa) {
+        return H_RESOURCE;
+    }
+
+    env->dispatch_trace_log = addr;
+    env->dtl_size = size;
+
+    return H_SUCCESS;
+}
+
+static target_ulong deregister_dtl(CPUState *emv, target_ulong addr)
+{
+    env->dispatch_trace_log = 0;
+    env->dtl_size = 0;
+
+    return H_SUCCESS;
+}
+
+static target_ulong h_register_vpa(CPUState *env, sPAPREnvironment *spapr,
+                                   target_ulong opcode, target_ulong *args)
+{
+    target_ulong flags = args[0];
+    target_ulong procno = args[1];
+    target_ulong vpa = args[2];
+    target_ulong ret = H_PARAMETER;
+    CPUState *tenv;
+
+    for (tenv = first_cpu; tenv; tenv = tenv->next_cpu) {
+        if (tenv->cpu_index == procno) {
+            break;
+        }
+    }
+
+    if (!tenv) {
+        return H_PARAMETER;
+    }
+
+    switch (flags) {
+    case FLAGS_REGISTER_VPA:
+        ret = register_vpa(tenv, vpa);
+        break;
+
+    case FLAGS_DEREGISTER_VPA:
+        ret = deregister_vpa(tenv, vpa);
+        break;
+
+    case FLAGS_REGISTER_SLBSHADOW:
+        ret = register_slb_shadow(tenv, vpa);
+        break;
+
+    case FLAGS_DEREGISTER_SLBSHADOW:
+        ret = deregister_slb_shadow(tenv, vpa);
+        break;
+
+    case FLAGS_REGISTER_DTL:
+        ret = register_dtl(tenv, vpa);
+        break;
+
+    case FLAGS_DEREGISTER_DTL:
+        ret = deregister_dtl(tenv, vpa);
+        break;
+    }
+
+    return ret;
+}
+
+static target_ulong h_cede(CPUState *env, sPAPREnvironment *spapr,
+                           target_ulong opcode, target_ulong *args)
+{
+    env->msr |= (1ULL << MSR_EE);
+    hreg_compute_hflags(env);
+    if (!cpu_has_work(env)) {
+        env->halted = 1;
+    }
+    return H_SUCCESS;
+}
+
 static target_ulong h_rtas(sPAPREnvironment *spapr, target_ulong rtas_r3)
 {
     uint32_t token = ldl_phys(rtas_r3);
@@ -311,5 +499,9 @@ static void hypercall_init(void)
 
     /* hcall-dabr */
     spapr_register_hypercall(H_SET_DABR, h_set_dabr);
+
+    /* hcall-splpar */
+    spapr_register_hypercall(H_REGISTER_VPA, h_register_vpa);
+    spapr_register_hypercall(H_CEDE, h_cede);
 }
 device_init(hypercall_init);
diff --git a/target-ppc/cpu.h b/target-ppc/cpu.h
index 29d6b49..867a2d8 100644
--- a/target-ppc/cpu.h
+++ b/target-ppc/cpu.h
@@ -722,6 +722,10 @@ struct CPUPPCState {
     uint64_t insns_flags;
     void (*emulate_hypercall)(CPUState *, void *);
     void *hcall_opaque;
+    target_phys_addr_t vpa;
+    target_phys_addr_t slb_shadow;
+    target_phys_addr_t dispatch_trace_log;
+    uint32_t dtl_size;
 
     int error_code;
     uint32_t pending_interrupts;
-- 
1.7.1