diff options
author | Bharata B Rao <bharata@linux.vnet.ibm.com> | 2015-07-13 10:34:00 +1000 |
---|---|---|
committer | David Gibson <david@gibson.dropbear.id.au> | 2015-09-23 10:51:10 +1000 |
commit | 03d196b7c57f22f796197f221f9d95336debee9e (patch) | |
tree | ac6905e9877a652e4488a6ed4cc661514ec421e0 /hw/ppc | |
parent | 224245bf524189789d231f38434c9f8fd57a249c (diff) | |
download | qemu-03d196b7c57f22f796197f221f9d95336debee9e.zip |
spapr: Support ibm,dynamic-reconfiguration-memory
Parse ibm,architecture.vec table obtained from the guest and enable
memory node configuration via ibm,dynamic-reconfiguration-memory if guest
supports it. This is in preparation to support memory hotplug for
sPAPR guests.
This changes the way memory node configuration is done. Currently all
memory nodes are built upfront. But after this patch, only memory@0 node
for RMA is built upfront. Guest kernel boots with just that and rest of
the memory nodes (via memory@XXX or ibm,dynamic-reconfiguration-memory)
are built when guest does ibm,client-architecture-support call.
Note: This patch needs a SLOF enhancement which is already part of
SLOF binary in QEMU.
Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Diffstat (limited to 'hw/ppc')
-rw-r--r-- | hw/ppc/spapr.c | 210 | ||||
-rw-r--r-- | hw/ppc/spapr_hcall.c | 51 |
2 files changed, 212 insertions, 49 deletions
diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index 940a82fc71..2f49f97924 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -504,44 +504,7 @@ static void *spapr_create_fdt_skel(hwaddr initrd_base, return fdt; } -int spapr_h_cas_compose_response(sPAPRMachineState *spapr, - 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); - - /* Fix skeleton up */ - _FDT((spapr_fixup_cpu_dt(fdt, spapr))); - - /* 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 void spapr_populate_memory_node(void *fdt, int nodeid, hwaddr start, +static int spapr_populate_memory_node(void *fdt, int nodeid, hwaddr start, hwaddr size) { uint32_t associativity[] = { @@ -564,6 +527,7 @@ static void spapr_populate_memory_node(void *fdt, int nodeid, hwaddr start, sizeof(mem_reg_property)))); _FDT((fdt_setprop(fdt, off, "ibm,associativity", associativity, sizeof(associativity)))); + return off; } static int spapr_populate_memory(sPAPRMachineState *spapr, void *fdt) @@ -595,7 +559,6 @@ static int spapr_populate_memory(sPAPRMachineState *spapr, void *fdt) } if (!mem_start) { /* ppc_spapr_init() checks for rma_size <= node0_size already */ - spapr_populate_memory_node(fdt, i, 0, spapr->rma_size); mem_start += spapr->rma_size; node_size -= spapr->rma_size; } @@ -745,6 +708,154 @@ static void spapr_populate_cpus_dt_node(void *fdt, sPAPRMachineState *spapr) } +/* + * Adds ibm,dynamic-reconfiguration-memory node. + * Refer to docs/specs/ppc-spapr-hotplug.txt for the documentation + * of this device tree node. + */ +static int spapr_populate_drconf_memory(sPAPRMachineState *spapr, void *fdt) +{ + MachineState *machine = MACHINE(spapr); + int ret, i, offset; + uint64_t lmb_size = SPAPR_MEMORY_BLOCK_SIZE; + uint32_t prop_lmb_size[] = {0, cpu_to_be32(lmb_size)}; + uint32_t nr_rma_lmbs = spapr->rma_size/lmb_size; + uint32_t nr_lmbs = machine->maxram_size/lmb_size - nr_rma_lmbs; + uint32_t nr_assigned_lmbs = machine->ram_size/lmb_size - nr_rma_lmbs; + uint32_t *int_buf, *cur_index, buf_len; + + /* Allocate enough buffer size to fit in ibm,dynamic-memory */ + buf_len = nr_lmbs * SPAPR_DR_LMB_LIST_ENTRY_SIZE * sizeof(uint32_t) + + sizeof(uint32_t); + cur_index = int_buf = g_malloc0(buf_len); + + offset = fdt_add_subnode(fdt, 0, "ibm,dynamic-reconfiguration-memory"); + + ret = fdt_setprop(fdt, offset, "ibm,lmb-size", prop_lmb_size, + sizeof(prop_lmb_size)); + if (ret < 0) { + goto out; + } + + ret = fdt_setprop_cell(fdt, offset, "ibm,memory-flags-mask", 0xff); + if (ret < 0) { + goto out; + } + + ret = fdt_setprop_cell(fdt, offset, "ibm,memory-preservation-time", 0x0); + if (ret < 0) { + goto out; + } + + /* ibm,dynamic-memory */ + int_buf[0] = cpu_to_be32(nr_lmbs); + cur_index++; + for (i = 0; i < nr_lmbs; i++) { + sPAPRDRConnector *drc; + sPAPRDRConnectorClass *drck; + uint64_t addr; + uint32_t *dynamic_memory = cur_index; + + if (i < nr_assigned_lmbs) { + addr = (i + nr_rma_lmbs) * lmb_size; + } else { + addr = (i - nr_assigned_lmbs) * lmb_size + + spapr->hotplug_memory.base; + } + drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB, + addr/lmb_size); + g_assert(drc); + drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + + dynamic_memory[0] = cpu_to_be32(addr >> 32); + dynamic_memory[1] = cpu_to_be32(addr & 0xffffffff); + dynamic_memory[2] = cpu_to_be32(drck->get_index(drc)); + dynamic_memory[3] = cpu_to_be32(0); /* reserved */ + dynamic_memory[4] = cpu_to_be32(numa_get_node(addr, NULL)); + if (addr < machine->ram_size || + memory_region_present(get_system_memory(), addr)) { + dynamic_memory[5] = cpu_to_be32(SPAPR_LMB_FLAGS_ASSIGNED); + } else { + dynamic_memory[5] = cpu_to_be32(0); + } + + cur_index += SPAPR_DR_LMB_LIST_ENTRY_SIZE; + } + ret = fdt_setprop(fdt, offset, "ibm,dynamic-memory", int_buf, buf_len); + if (ret < 0) { + goto out; + } + + /* ibm,associativity-lookup-arrays */ + cur_index = int_buf; + int_buf[0] = cpu_to_be32(nb_numa_nodes); + int_buf[1] = cpu_to_be32(4); /* Number of entries per associativity list */ + cur_index += 2; + for (i = 0; i < nb_numa_nodes; i++) { + uint32_t associativity[] = { + cpu_to_be32(0x0), + cpu_to_be32(0x0), + cpu_to_be32(0x0), + cpu_to_be32(i) + }; + memcpy(cur_index, associativity, sizeof(associativity)); + cur_index += 4; + } + ret = fdt_setprop(fdt, offset, "ibm,associativity-lookup-arrays", int_buf, + (cur_index - int_buf) * sizeof(uint32_t)); +out: + g_free(int_buf); + return ret; +} + +int spapr_h_cas_compose_response(sPAPRMachineState *spapr, + target_ulong addr, target_ulong size, + bool cpu_update, bool memory_update) +{ + void *fdt, *fdt_skel; + sPAPRDeviceTreeUpdateHeader hdr = { .version_id = 1 }; + sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(qdev_get_machine()); + + 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); + + /* Fixup cpu nodes */ + if (cpu_update) { + _FDT((spapr_fixup_cpu_dt(fdt, spapr))); + } + + /* Generate memory nodes or ibm,dynamic-reconfiguration-memory node */ + if (memory_update && smc->dr_lmb_enabled) { + _FDT((spapr_populate_drconf_memory(spapr, fdt))); + } else { + _FDT((spapr_populate_memory(spapr, fdt))); + } + + /* 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 void spapr_finalize_fdt(sPAPRMachineState *spapr, hwaddr fdt_addr, hwaddr rtas_addr, @@ -763,10 +874,23 @@ static void spapr_finalize_fdt(sPAPRMachineState *spapr, /* open out the base tree into a temp buffer for the final tweaks */ _FDT((fdt_open_into(spapr->fdt_skel, fdt, FDT_MAX_SIZE))); - ret = spapr_populate_memory(spapr, fdt); - if (ret < 0) { - fprintf(stderr, "couldn't setup memory nodes in fdt\n"); - exit(1); + /* + * Add memory@0 node to represent RMA. Rest of the memory is either + * represented by memory nodes or ibm,dynamic-reconfiguration-memory + * node later during ibm,client-architecture-support call. + * + * If NUMA is configured, ensure that memory@0 ends up in the + * first memory-less node. + */ + if (nb_numa_nodes) { + for (i = 0; i < nb_numa_nodes; ++i) { + if (numa_info[i].node_mem) { + spapr_populate_memory_node(fdt, i, 0, spapr->rma_size); + break; + } + } + } else { + spapr_populate_memory_node(fdt, 0, 0, spapr->rma_size); } ret = spapr_populate_vdevice(spapr->vio_bus, fdt); diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c index 71fc9f23a1..cebceea69b 100644 --- a/hw/ppc/spapr_hcall.c +++ b/hw/ppc/spapr_hcall.c @@ -808,6 +808,32 @@ static target_ulong h_set_mode(PowerPCCPU *cpu, sPAPRMachineState *spapr, return ret; } +/* + * Return the offset to the requested option vector @vector in the + * option vector table @table. + */ +static target_ulong cas_get_option_vector(int vector, target_ulong table) +{ + int i; + char nr_vectors, nr_entries; + + if (!table) { + return 0; + } + + nr_vectors = (ldl_phys(&address_space_memory, table) >> 24) + 1; + if (!vector || vector > nr_vectors) { + return 0; + } + table++; /* skip nr option vectors */ + + for (i = 0; i < vector - 1; i++) { + nr_entries = ldl_phys(&address_space_memory, table) >> 24; + table += nr_entries + 2; + } + return table; +} + typedef struct { PowerPCCPU *cpu; uint32_t cpu_version; @@ -828,19 +854,22 @@ static void do_set_compat(void *arg) ((cpuver) == CPU_POWERPC_LOGICAL_2_06_PLUS) ? 2061 : \ ((cpuver) == CPU_POWERPC_LOGICAL_2_07) ? 2070 : 0) +#define OV5_DRCONF_MEMORY 0x20 + static target_ulong h_client_architecture_support(PowerPCCPU *cpu_, sPAPRMachineState *spapr, target_ulong opcode, target_ulong *args) { - target_ulong list = args[0]; + target_ulong list = args[0], ov_table; PowerPCCPUClass *pcc_ = POWERPC_CPU_GET_CLASS(cpu_); CPUState *cs; - bool cpu_match = false; + bool cpu_match = false, cpu_update = true, memory_update = false; unsigned old_cpu_version = cpu_->cpu_version; unsigned compat_lvl = 0, cpu_version = 0; unsigned max_lvl = get_compat_level(cpu_->max_compat); int counter; + char ov5_byte2; /* Parse PVR list */ for (counter = 0; counter < 512; ++counter) { @@ -890,8 +919,6 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu_, } } - /* 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); @@ -915,14 +942,26 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu_, } if (!cpu_version) { - return H_SUCCESS; + cpu_update = false; } + /* For the future use: here @ov_table points to the first option vector */ + ov_table = list; + + list = cas_get_option_vector(5, ov_table); if (!list) { return H_SUCCESS; } - if (spapr_h_cas_compose_response(spapr, args[1], args[2])) { + /* @list now points to OV 5 */ + list += 2; + ov5_byte2 = rtas_ld(list, 0) >> 24; + if (ov5_byte2 & OV5_DRCONF_MEMORY) { + memory_update = true; + } + + if (spapr_h_cas_compose_response(spapr, args[1], args[2], + cpu_update, memory_update)) { qemu_system_reset_request(); } |