From 383c464e74b19af5a4e1e18bb56df969e9d61c2a Mon Sep 17 00:00:00 2001
Message-Id: <383c464e74b19af5a4e1e18bb56df969e9d61c2a.1351776104.git.minovotn@redhat.com>
From: Eduardo Habkost <ehabkost@redhat.com>
Date: Mon, 29 Oct 2012 18:52:27 +0100
Subject: [PATCH 01/11] Fixes related to processing of qemu's -numa option

RH-Author: Eduardo Habkost <ehabkost@redhat.com>
Message-id: <1351536756-16475-2-git-send-email-ehabkost@redhat.com>
Patchwork-id: 43759
O-Subject: [RHEL6.4 qemu-kvm PATCH 01/10] Fixes related to processing of qemu's -numa option
Bugzilla: 733720
RH-Acked-by: Laszlo Ersek <lersek@redhat.com>
RH-Acked-by: Igor Mammedov <imammedo@redhat.com>
RH-Acked-by: Gleb Natapov <gleb@redhat.com>

From: Chegu Vinod <chegu_vinod@hp.com>

Bugzilla: 733720
Related TestOnly BZs: 816804, 815958, 782648
Upstream status: commit ee785fed5dd035d4b12142cacec6d3c344426dec

The -numa option to qemu is used to create [fake] numa nodes
and expose them to the guest OS instance.

There are a couple of issues with the -numa option:

a) Max VCPU's that can be specified for a guest while using
   the qemu's -numa option is 64. Due to a typecasting issue
   when the number of VCPUs is > 32 the VCPUs don't show up
   under the specified [fake] numa nodes.

b) KVM currently has support for 160VCPUs per guest. The
   qemu's -numa option has only support for upto 64VCPUs
   per guest.
This patch addresses these two issues.

Below are examples of (a) and (b)

a) >32 VCPUs are specified with the -numa option:

/usr/local/bin/qemu-system-x86_64 \
-enable-kvm \
71:01:01 \
-net tap,ifname=tap0,script=no,downscript=no \
-vnc :4

...
Upstream qemu :
--------------

QEMU 1.1.50 monitor - type 'help' for more information
(qemu) info numa
6 nodes
node 0 cpus: 0 1 2 3 4 5 6 7 8 9 32 33 34 35 36 37 38 39 40 41
node 0 size: 131072 MB
node 1 cpus: 10 11 12 13 14 15 16 17 18 19 42 43 44 45 46 47 48 49 50 51
node 1 size: 131072 MB
node 2 cpus: 20 21 22 23 24 25 26 27 28 29 52 53 54 55 56 57 58 59
node 2 size: 131072 MB
node 3 cpus: 30
node 3 size: 131072 MB
node 4 cpus:
node 4 size: 131072 MB
node 5 cpus: 31
node 5 size: 131072 MB

With the patch applied :
-----------------------

QEMU 1.1.50 monitor - type 'help' for more information
(qemu) info numa
6 nodes
node 0 cpus: 0 1 2 3 4 5 6 7 8 9
node 0 size: 131072 MB
node 1 cpus: 10 11 12 13 14 15 16 17 18 19
node 1 size: 131072 MB
node 2 cpus: 20 21 22 23 24 25 26 27 28 29
node 2 size: 131072 MB
node 3 cpus: 30 31 32 33 34 35 36 37 38 39
node 3 size: 131072 MB
node 4 cpus: 40 41 42 43 44 45 46 47 48 49
node 4 size: 131072 MB
node 5 cpus: 50 51 52 53 54 55 56 57 58 59
node 5 size: 131072 MB

b) >64 VCPUs specified with -numa option:

/usr/local/bin/qemu-system-x86_64 \
-enable-kvm \
-cpu Westmere,+rdtscp,+pdpe1gb,+dca,+pdcm,+xtpr,+tm2,+est,+smx,+vmx,+ds_cpl,+monitor,+dtes64,+pclmuldq,+pbe,+tm,+ht,+ss,+acpi,+d-vnc :4

...

Upstream qemu :
--------------

only 63 CPUs in NUMA mode supported.
only 64 CPUs in NUMA mode supported.
QEMU 1.1.50 monitor - type 'help' for more information
(qemu) info numa
8 nodes
node 0 cpus: 6 7 8 9 38 39 40 41 70 71 72 73
node 0 size: 65536 MB
node 1 cpus: 10 11 12 13 14 15 16 17 18 19 42 43 44 45 46 47 48 49 50 51 74 75 76 77 78 79
node 1 size: 65536 MB
node 2 cpus: 20 21 22 23 24 25 26 27 28 29 52 53 54 55 56 57 58 59 60 61
node 2 size: 65536 MB
node 3 cpus: 30 62
node 3 size: 65536 MB
node 4 cpus:
node 4 size: 65536 MB
node 5 cpus:
node 5 size: 65536 MB
node 6 cpus: 31 63
node 6 size: 65536 MB
node 7 cpus: 0 1 2 3 4 5 32 33 34 35 36 37 64 65 66 67 68 69
node 7 size: 65536 MB

With the patch applied :
-----------------------

QEMU 1.1.50 monitor - type 'help' for more information
(qemu) info numa
8 nodes
node 0 cpus: 0 1 2 3 4 5 6 7 8 9
node 0 size: 65536 MB
node 1 cpus: 10 11 12 13 14 15 16 17 18 19
node 1 size: 65536 MB
node 2 cpus: 20 21 22 23 24 25 26 27 28 29
node 2 size: 65536 MB
node 3 cpus: 30 31 32 33 34 35 36 37 38 39
node 3 size: 65536 MB
node 4 cpus: 40 41 42 43 44 45 46 47 48 49
node 4 size: 65536 MB
node 5 cpus: 50 51 52 53 54 55 56 57 58 59
node 5 size: 65536 MB
node 6 cpus: 60 61 62 63 64 65 66 67 68 69
node 6 size: 65536 MB
node 7 cpus: 70 71 72 73 74 75 76 77 78 79

Signed-off-by: Chegu Vinod <chegu_vinod@hp.com>, Jim Hull <jim.hull@hp.com>, Craig Hada <craig.hada@hp.com>
Tested-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
(cherry picked from commit ee785fed5dd035d4b12142cacec6d3c344426dec)

Conflicts:
	cpus.c
	hw/pc.c
	vl.c

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
---
 hw/pc.c  |  3 ++-
 sysemu.h |  3 ++-
 vl.c     | 42 +++++++++++++++++++-----------------------
 3 files changed, 23 insertions(+), 25 deletions(-)

Signed-off-by: Michal Novotny <minovotn@redhat.com>
---
 hw/pc.c  |  3 ++-
 sysemu.h |  3 ++-
 vl.c     | 42 +++++++++++++++++++-----------------------
 3 files changed, 23 insertions(+), 25 deletions(-)

diff --git a/hw/pc.c b/hw/pc.c
index 279f525..fcc760d 100644
--- a/hw/pc.c
+++ b/hw/pc.c
@@ -48,6 +48,7 @@
 #include "qemu-kvm.h"
 #include "ui/qemu-spice.h"
 #include "kvmclock.h"
+#include "bitmap.h"
 
 /* output Bochs bios info messages */
 //#define DEBUG_BIOS
@@ -494,7 +495,7 @@ static void *bochs_bios_init(void)
     numa_fw_cfg[0] = cpu_to_le64(nb_numa_nodes);
     for (i = 0; i < smp_cpus; i++) {
         for (j = 0; j < nb_numa_nodes; j++) {
-            if (node_cpumask[j] & (1 << i)) {
+            if (test_bit(i, node_cpumask[j])) {
                 numa_fw_cfg[i + 1] = cpu_to_le64(j);
                 break;
             }
diff --git a/sysemu.h b/sysemu.h
index 411a82a..8223113 100644
--- a/sysemu.h
+++ b/sysemu.h
@@ -175,9 +175,10 @@ extern QEMUClock *rtc_clock;
 extern long hpagesize;
 
 #define MAX_NODES 64
+#define MAX_CPUMASK_BITS 255
 extern int nb_numa_nodes;
 extern uint64_t node_mem[MAX_NODES];
-extern uint64_t node_cpumask[MAX_NODES];
+extern unsigned long *node_cpumask[MAX_NODES];
 
 #define MAX_OPTION_ROMS 16
 typedef struct QEMUOptionRom {
diff --git a/vl.c b/vl.c
index 5d94e02..73fe5da 100644
--- a/vl.c
+++ b/vl.c
@@ -29,6 +29,7 @@
 #include <sys/time.h>
 #include <grp.h>
 #include <zlib.h>
+#include "bitmap.h"
 
 /* Needed early for CONFIG_BSD etc. */
 #include "config-host.h"
@@ -281,7 +282,7 @@ QTAILQ_HEAD(, FWBootEntry) fw_boot_order = QTAILQ_HEAD_INITIALIZER(fw_boot_order
 
 int nb_numa_nodes;
 uint64_t node_mem[MAX_NODES];
-uint64_t node_cpumask[MAX_NODES];
+unsigned long *node_cpumask[MAX_NODES];
 
 static CPUState *cur_cpu;
 static CPUState *next_cpu;
@@ -2395,27 +2396,21 @@ static void numa_add(const char *optarg)
             }
             node_mem[nodenr] = sval;
         }
-        if (get_param_value(option, 128, "cpus", optarg) == 0) {
-            node_cpumask[nodenr] = 0;
-        } else {
+        if (get_param_value(option, 128, "cpus", optarg) != 0) {
             value = strtoull(option, &endptr, 10);
-            if (value >= 64) {
-                value = 63;
-                fprintf(stderr, "only 64 CPUs in NUMA mode supported.\n");
+            if (*endptr == '-') {
+                endvalue = strtoull(endptr+1, &endptr, 10);
             } else {
-                if (*endptr == '-') {
-                    endvalue = strtoull(endptr+1, &endptr, 10);
-                    if (endvalue >= 63) {
-                        endvalue = 62;
-                        fprintf(stderr,
-                            "only 63 CPUs in NUMA mode supported.\n");
-                    }
-                    value = (2ULL << endvalue) - (1ULL << value);
-                } else {
-                    value = 1ULL << value;
-                }
+                endvalue = value;
+            }
+            if (!(endvalue < MAX_CPUMASK_BITS)) {
+                endvalue = MAX_CPUMASK_BITS - 1;
+                fprintf(stderr,
+                    "A max of %d CPUs are supported in a guest\n",
+                     MAX_CPUMASK_BITS);
             }
-            node_cpumask[nodenr] = value;
+
+            bitmap_set(node_cpumask[nodenr], value, endvalue-value+1);
         }
         nb_numa_nodes++;
     }
@@ -5163,7 +5158,7 @@ int main(int argc, char **argv, char **envp)
 
     for (i = 0; i < MAX_NODES; i++) {
         node_mem[i] = 0;
-        node_cpumask[i] = 0;
+        node_cpumask[i] = bitmap_new(MAX_CPUMASK_BITS);
     }
 
     assigned_devices_index = 0;
@@ -6271,8 +6266,9 @@ int main(int argc, char **argv, char **envp)
         }
 
         for (i = 0; i < nb_numa_nodes; i++) {
-            if (node_cpumask[i] != 0)
+            if (!bitmap_empty(node_cpumask[i], MAX_CPUMASK_BITS)) {
                 break;
+            }
         }
         /* assigning the VCPUs round-robin is easier to implement, guest OSes
          * must cope with this anyway, because there are BIOSes out there in
@@ -6280,7 +6276,7 @@ int main(int argc, char **argv, char **envp)
          */
         if (i == nb_numa_nodes) {
             for (i = 0; i < smp_cpus; i++) {
-                node_cpumask[i % nb_numa_nodes] |= 1 << i;
+                set_bit(i, node_cpumask[i % nb_numa_nodes]);
             }
         }
     }
@@ -6316,7 +6312,7 @@ int main(int argc, char **argv, char **envp)
 
     for (env = first_cpu; env != NULL; env = env->next_cpu) {
         for (i = 0; i < nb_numa_nodes; i++) {
-            if (node_cpumask[i] & (1 << env->cpu_index)) {
+            if (test_bit(env->cpu_index, node_cpumask[i])) {
                 env->numa_node = i;
             }
         }
-- 
1.7.11.7