Re: [Qemu-devel] [PATCH RFC 2/2] numa: make -numa parser dynamically allocate CPUs masks

[Igor Mammedov]

On Wed, 16 Nov 2016 15:08:26 -0200
Eduardo Habkost <address@hidden> wrote:

> On Wed, Nov 16, 2016 at 05:02:56PM +0100, Igor Mammedov wrote:
> > so it won't impose an additional limits on max_cpus limits
> > supported by different targets.
> > 
> > It removes global MAX_CPUMASK_BITS constant and need to
> > bump it up whenever max_cpus is being increased for
> > a target above MAX_CPUMASK_BITS value.
> > 
> > Use runtime max_cpus value instead to allocate sufficiently
> > sized node_cpu bitmasks in numa parser.
> > 
> > Signed-off-by: Igor Mammedov <address@hidden>
> > ---
> >  include/sysemu/numa.h   |  2 +-
> >  include/sysemu/sysemu.h |  7 -------
> >  numa.c                  | 19 ++++++++++++-------
> >  vl.c                    |  5 -----
> >  4 files changed, 13 insertions(+), 20 deletions(-)
> > 
> > diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h
> > index 4da808a..8f09dcf 100644
> > --- a/include/sysemu/numa.h
> > +++ b/include/sysemu/numa.h
> > @@ -17,7 +17,7 @@ struct numa_addr_range {
> >  
> >  typedef struct node_info {
> >      uint64_t node_mem;
> > -    DECLARE_BITMAP(node_cpu, MAX_CPUMASK_BITS);
> > +    unsigned long *node_cpu;
> >      struct HostMemoryBackend *node_memdev;
> >      bool present;
> >      QLIST_HEAD(, numa_addr_range) addr; /* List to store address ranges */
> > diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
> > index 66c6f15..cccde56 100644
> > --- a/include/sysemu/sysemu.h
> > +++ b/include/sysemu/sysemu.h
> > @@ -168,13 +168,6 @@ extern int mem_prealloc;
> >  #define MAX_NODES 128
> >  #define NUMA_NODE_UNASSIGNED MAX_NODES
> >  
> > -/* The following shall be true for all CPUs:
> > - *   cpu->cpu_index < max_cpus <= MAX_CPUMASK_BITS
> > - *
> > - * Note that cpu->get_arch_id() may be larger than MAX_CPUMASK_BITS.
> > - */
> > -#define MAX_CPUMASK_BITS 288
> > -  
> 
> Nice!
> 
> >  #define MAX_OPTION_ROMS 16
> >  typedef struct QEMUOptionRom {
> >      const char *name;
> > diff --git a/numa.c b/numa.c
> > index 9c09e45..5542e40 100644
> > --- a/numa.c
> > +++ b/numa.c
> > @@ -266,20 +266,20 @@ static char *enumerate_cpus(unsigned long *cpus, int 
> > max_cpus)
> >  static void validate_numa_cpus(void)
> >  {
> >      int i;
> > -    DECLARE_BITMAP(seen_cpus, MAX_CPUMASK_BITS);
> > +    unsigned long *seen_cpus = bitmap_new(max_cpus);
> >  
> > -    bitmap_zero(seen_cpus, MAX_CPUMASK_BITS);
> > +    bitmap_zero(seen_cpus, max_cpus);  
> 
> bitmap_new() already returns a zeroed bitmap.
> 
> >      for (i = 0; i < nb_numa_nodes; i++) {
> > -        if (bitmap_intersects(seen_cpus, numa_info[i].node_cpu,
> > -                              MAX_CPUMASK_BITS)) {
> > +        if (bitmap_intersects(seen_cpus, numa_info[i].node_cpu, max_cpus)) 
> > {
> >              bitmap_and(seen_cpus, seen_cpus,
> > -                       numa_info[i].node_cpu, MAX_CPUMASK_BITS);
> > +                       numa_info[i].node_cpu, max_cpus);
> >              error_report("CPU(s) present in multiple NUMA nodes: %s",
> >                           enumerate_cpus(seen_cpus, max_cpus));
> > +            bitmap_free(seen_cpus);
> >              exit(EXIT_FAILURE);
> >          }
> >          bitmap_or(seen_cpus, seen_cpus,
> > -                  numa_info[i].node_cpu, MAX_CPUMASK_BITS);
> > +                  numa_info[i].node_cpu, max_cpus);
> >      }
> >  
> >      if (!bitmap_full(seen_cpus, max_cpus)) {
> > @@ -291,12 +291,17 @@ static void validate_numa_cpus(void)
> >                       "in NUMA config");
> >          g_free(msg);
> >      }
> > +    bitmap_free(seen_cpus);  
> 
> See comment about bitmap_free() on patch 1/2. I think g_free() is
> good enough (unless you really want to review all callers of
> bitmap_[try_]new()).
ok, I'll replace bitmap_free() with g_free() and respin.

> 
> >  }
> >  
> >  void parse_numa_opts(MachineClass *mc)
> >  {
> >      int i;
> >  
> > +    for (i = 0; i < MAX_NODES; i++) {
> > +        numa_info[i].node_cpu = bitmap_new(max_cpus);
> > +    }
> > +
> >      if (qemu_opts_foreach(qemu_find_opts("numa"), parse_numa, NULL, NULL)) 
> > {
> >          exit(1);
> >      }
> > @@ -362,7 +367,7 @@ void parse_numa_opts(MachineClass *mc)
> >          numa_set_mem_ranges();
> >  
> >          for (i = 0; i < nb_numa_nodes; i++) {
> > -            if (!bitmap_empty(numa_info[i].node_cpu, MAX_CPUMASK_BITS)) {
> > +            if (!bitmap_empty(numa_info[i].node_cpu, max_cpus)) {
> >                  break;
> >              }
> >          }
> > diff --git a/vl.c b/vl.c
> > index d77dd86..37790e5 100644
> > --- a/vl.c
> > +++ b/vl.c
> > @@ -1277,11 +1277,6 @@ static void smp_parse(QemuOpts *opts)
> >  
> >          max_cpus = qemu_opt_get_number(opts, "maxcpus", cpus);
> >  
> > -        if (max_cpus > MAX_CPUMASK_BITS) {
> > -            error_report("unsupported number of maxcpus");
> > -            exit(1);
> > -        }
> > -
> >          if (max_cpus < cpus) {
> >              error_report("maxcpus must be equal to or greater than smp");
> >              exit(1);
> > -- 
> > 2.7.4
> >   
>