Re: [Qemu-devel] [PATCH V4 02/10] NUMA: Add numa_info structure to contain numa nodes info

["Andreas Färber" <afaerber@suse.de>]

Am 05.07.2013 21:32, schrieb Eduardo Habkost:
> On Thu, Jul 04, 2013 at 05:53:09PM +0800, Wanlong Gao wrote:
>> Add the numa_info structure to contain the numa nodes memory,
>> VCPUs information and the future added numa nodes host memory
>> policies.
>>
>> Signed-off-by: Andre Przywara <andre.przywara@amd.com>
>> Signed-off-by: Wanlong Gao <gaowanlong@cn.fujitsu.com>
> 
> Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
> 
>> ---
>>  cpus.c                  |  2 +-
>>  hw/i386/pc.c            |  4 ++--
>>  hw/net/eepro100.c       |  1 -
>>  include/sysemu/sysemu.h |  8 ++++++--
>>  monitor.c               |  2 +-
>>  vl.c                    | 24 ++++++++++++------------
>>  6 files changed, 22 insertions(+), 19 deletions(-)
>>
>> diff --git a/cpus.c b/cpus.c
>> index 20958e5..496d5ce 100644
>> --- a/cpus.c
>> +++ b/cpus.c
>> @@ -1180,7 +1180,7 @@ void set_numa_modes(void)
>>      for (env = first_cpu; env != NULL; env = env->next_cpu) {
>>          cpu = ENV_GET_CPU(env);
>>          for (i = 0; i < nb_numa_nodes; i++) {
>> -            if (test_bit(cpu->cpu_index, node_cpumask[i])) {
>> +            if (test_bit(cpu->cpu_index, numa_info[i].node_cpu)) {
>>                  cpu->numa_node = i;
>>              }
>>          }
>> diff --git a/hw/i386/pc.c b/hw/i386/pc.c
>> index 78f92e2..78b5a72 100644
>> --- a/hw/i386/pc.c
>> +++ b/hw/i386/pc.c
>> @@ -650,14 +650,14 @@ static FWCfgState *bochs_bios_init(void)
>>          unsigned int apic_id = x86_cpu_apic_id_from_index(i);
>>          assert(apic_id < apic_id_limit);
>>          for (j = 0; j < nb_numa_nodes; j++) {
>> -            if (test_bit(i, node_cpumask[j])) {
>> +            if (test_bit(i, numa_info[j].node_cpu)) {
>>                  numa_fw_cfg[apic_id + 1] = cpu_to_le64(j);
>>                  break;
>>              }
>>          }
>>      }
>>      for (i = 0; i < nb_numa_nodes; i++) {
>> -        numa_fw_cfg[apic_id_limit + 1 + i] = cpu_to_le64(node_mem[i]);
>> +        numa_fw_cfg[apic_id_limit + 1 + i] = cpu_to_le64(numa_info[i].node_mem);
>>      }
>>      fw_cfg_add_bytes(fw_cfg, FW_CFG_NUMA, numa_fw_cfg,
>>                       (1 + apic_id_limit + nb_numa_nodes) *
>> diff --git a/hw/net/eepro100.c b/hw/net/eepro100.c
>> index dc99ea6..478c688 100644
>> --- a/hw/net/eepro100.c
>> +++ b/hw/net/eepro100.c
>> @@ -105,7 +105,6 @@
>>  #define PCI_IO_SIZE             64
>>  #define PCI_FLASH_SIZE          (128 * KiB)
>>  
>> -#define BIT(n) (1 << (n))
>>  #define BITS(n, m) (((0xffffffffU << (31 - n)) >> (31 - n + m)) << m)
>>  
>>  /* The SCB accepts the following controls for the Tx and Rx units: */
>> diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
>> index 2fb71af..70fd2ed 100644
>> --- a/include/sysemu/sysemu.h
>> +++ b/include/sysemu/sysemu.h
>> @@ -9,6 +9,7 @@
>>  #include "qapi-types.h"
>>  #include "qemu/notify.h"
>>  #include "qemu/main-loop.h"
>> +#include "qemu/bitmap.h"
>>  
>>  /* vl.c */
>>  
>> @@ -130,8 +131,11 @@ extern QEMUClock *rtc_clock;
>>  #define MAX_NODES 64
>>  #define MAX_CPUMASK_BITS 255
>>  extern int nb_numa_nodes;
>> -extern uint64_t node_mem[MAX_NODES];
>> -extern unsigned long *node_cpumask[MAX_NODES];
>> +struct node_info {

NodeInfo

>> +    uint64_t node_mem;
>> +    DECLARE_BITMAP(node_cpu, MAX_CPUMASK_BITS);
>> +};

Please add a typedef and use that everywhere below.

>> +extern struct node_info numa_info[MAX_NODES];

I wonder if those structs should be QOM Objects instead, so that we can
use link<> properties from CPUState. I think Paolo suggested something
in that direction?

Regards,
Andreas

>>  
>>  #define MAX_OPTION_ROMS 16
>>  typedef struct QEMUOptionRom {
>> diff --git a/monitor.c b/monitor.c
>> index 9be515c..93ac045 100644
>> --- a/monitor.c
>> +++ b/monitor.c
>> @@ -1820,7 +1820,7 @@ static void do_info_numa(Monitor *mon, const QDict *qdict)
>>          }
>>          monitor_printf(mon, "\n");
>>          monitor_printf(mon, "node %d size: %" PRId64 " MB\n", i,
>> -            node_mem[i] >> 20);
>> +            numa_info[i].node_mem >> 20);
>>      }
>>  }
>>  
>> diff --git a/vl.c b/vl.c
>> index 6f2e17a..5207b8e 100644
>> --- a/vl.c
>> +++ b/vl.c
>> @@ -250,8 +250,7 @@ static QTAILQ_HEAD(, FWBootEntry) fw_boot_order =
>>      QTAILQ_HEAD_INITIALIZER(fw_boot_order);
>>  
>>  int nb_numa_nodes;
>> -uint64_t node_mem[MAX_NODES];
>> -unsigned long *node_cpumask[MAX_NODES];
>> +struct node_info numa_info[MAX_NODES];
>>  
>>  uint8_t qemu_uuid[16];
>>  
>> @@ -1367,7 +1366,7 @@ static void numa_node_parse_cpus(int nodenr, const char *cpus)
>>          goto error;
>>      }
>>  
>> -    bitmap_set(node_cpumask[nodenr], value, endvalue-value+1);
>> +    bitmap_set(numa_info[nodenr].node_cpu, value, endvalue-value+1);
>>      return;
>>  
>>  error:
>> @@ -1399,7 +1398,7 @@ static int numa_init_func(QemuOpts *opts, void *opaque)
>>      }
>>  
>>      mem_size = qemu_opt_get_size(opts, "mem", 0);
>> -    node_mem[nodenr] = mem_size;
>> +    numa_info[nodenr].node_mem = mem_size;
>>  
>>      if (qemu_opt_foreach(opts, numa_add_cpus, &nodenr, 1) < 0) {
>>          return -1;
>> @@ -2961,8 +2960,8 @@ int main(int argc, char **argv, char **envp)
>>      translation = BIOS_ATA_TRANSLATION_AUTO;
>>  
>>      for (i = 0; i < MAX_NODES; i++) {
>> -        node_mem[i] = 0;
>> -        node_cpumask[i] = bitmap_new(MAX_CPUMASK_BITS);
>> +        numa_info[i].node_mem = 0;
>> +        bitmap_zero(numa_info[i].node_cpu, MAX_CPUMASK_BITS);
>>      }
>>  
>>      nb_numa_nodes = 0;
>> @@ -4228,7 +4227,7 @@ int main(int argc, char **argv, char **envp)
>>           * and distribute the available memory equally across all nodes
>>           */
>>          for (i = 0; i < nb_numa_nodes; i++) {
>> -            if (node_mem[i] != 0)
>> +            if (numa_info[i].node_mem != 0)
>>                  break;
>>          }
>>          if (i == nb_numa_nodes) {
>> @@ -4238,14 +4237,15 @@ int main(int argc, char **argv, char **envp)
>>               * the final node gets the rest.
>>               */
>>              for (i = 0; i < nb_numa_nodes - 1; i++) {
>> -                node_mem[i] = (ram_size / nb_numa_nodes) & ~((1 << 23UL) - 1);
>> -                usedmem += node_mem[i];
>> +                numa_info[i].node_mem = (ram_size / nb_numa_nodes) &
>> +                                        ~((1 << 23UL) - 1);
>> +                usedmem += numa_info[i].node_mem;
>>              }
>> -            node_mem[i] = ram_size - usedmem;
>> +            numa_info[i].node_mem = ram_size - usedmem;
>>          }
>>  
>>          for (i = 0; i < nb_numa_nodes; i++) {
>> -            if (!bitmap_empty(node_cpumask[i], MAX_CPUMASK_BITS)) {
>> +            if (!bitmap_empty(numa_info[i].node_cpu, MAX_CPUMASK_BITS)) {
>>                  break;
>>              }
>>          }
>> @@ -4255,7 +4255,7 @@ int main(int argc, char **argv, char **envp)
>>           */
>>          if (i == nb_numa_nodes) {
>>              for (i = 0; i < max_cpus; i++) {
>> -                set_bit(i, node_cpumask[i % nb_numa_nodes]);
>> +                set_bit(i, numa_info[i % nb_numa_nodes].node_cpu);
>>              }
>>          }
>>      }
>> -- 
>> 1.8.3.2.634.g7a3187e
>>
>>
> 


-- 
SUSE LINUX Products GmbH, Maxfeldstr. 5, 90409 Nürnberg, Germany
GF: Jeff Hawn, Jennifer Guild, Felix Imendörffer; HRB 16746 AG Nürnberg