[Qemu-devel] [PATCH V5 06/12] NUMA: parse guest numa nodes memory policy

[Wanlong Gao]

The memory policy setting format is like:
    policy={membind|interleave|preferred},host-node=[+|!]{all|N-N}
And we are adding this setting as a suboption of "-numa mem,",
the memory policy then can be set like following:
    -numa node,nodeid=0,cpus=0 \
    -numa node,nodeid=1,cpus=1 \
    -numa mem,nodeid=0,size=1G,policy=membind,host-nodes=0-1 \
    -numa mem,nodeid=1,size=1G,policy=interleave,host-nodes=!1

Reviewed-by: Bandan Das <address@hidden>
Signed-off-by: Andre Przywara <address@hidden>
Signed-off-by: Wanlong Gao <address@hidden>
---
 include/sysemu/sysemu.h |  8 +++++
 numa.c                  | 83 +++++++++++++++++++++++++++++++++++++++++++++++++
 qapi-schema.json        |  8 ++++-
 vl.c                    |  2 ++
 4 files changed, 100 insertions(+), 1 deletion(-)

diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
index 28fe305..af17c02 100644
--- a/include/sysemu/sysemu.h
+++ b/include/sysemu/sysemu.h
@@ -130,10 +130,18 @@ extern QEMUClock *rtc_clock;
 
 #define MAX_NODES 64
 #define MAX_CPUMASK_BITS 255
+#define NODE_HOST_NONE        0x00
+#define NODE_HOST_BIND        0x01
+#define NODE_HOST_INTERLEAVE  0x02
+#define NODE_HOST_PREFERRED   0x03
+#define NODE_HOST_POLICY_MASK 0x03
+#define NODE_HOST_RELATIVE    0x04
 extern int nb_numa_nodes;
 typedef struct node_info {
     uint64_t node_mem;
     DECLARE_BITMAP(node_cpu, MAX_CPUMASK_BITS);
+    DECLARE_BITMAP(host_mem, MAX_CPUMASK_BITS);
+    unsigned int flags;
 } NodeInfo;
 extern NodeInfo numa_info[MAX_NODES];
 extern QemuOptsList qemu_numa_opts;
diff --git a/numa.c b/numa.c
index 766e111..a2eceb1 100644
--- a/numa.c
+++ b/numa.c
@@ -96,6 +96,79 @@ static int numa_node_parse(NumaNodeOptions *opts)
     return numa_node_parse_cpus(nodenr, cpus);
 }
 
+static int numa_mem_parse_policy(int nodenr, const char *policy)
+{
+    if (!strcmp(policy, "interleave")) {
+        numa_info[nodenr].flags |= NODE_HOST_INTERLEAVE;
+    } else if (!strcmp(policy, "preferred")) {
+        numa_info[nodenr].flags |= NODE_HOST_PREFERRED;
+    } else if (!strcmp(policy, "membind")) {
+        numa_info[nodenr].flags |= NODE_HOST_BIND;
+    } else {
+        fprintf(stderr, "qemu: Invalid memory policy: %s\n", policy);
+        return -1;
+    }
+
+    return 0;
+}
+
+static int numa_mem_parse_hostnodes(int nodenr, const char *hostnodes)
+{
+    unsigned long long value, endvalue;
+    char *endptr;
+    bool clear = false;
+    unsigned long *bm = numa_info[nodenr].host_mem;
+
+    if (hostnodes[0] == '!') {
+        clear = true;
+        bitmap_fill(bm, MAX_CPUMASK_BITS);
+        hostnodes++;
+    }
+    if (hostnodes[0] == '+') {
+        numa_info[nodenr].flags |= NODE_HOST_RELATIVE;
+        hostnodes++;
+    }
+
+    if (!strcmp(hostnodes, "all")) {
+        bitmap_fill(bm, MAX_CPUMASK_BITS);
+        return 0;
+    }
+
+    if (parse_uint(hostnodes, &value, &endptr, 10) < 0)
+        goto error;
+    if (*endptr == '-') {
+        if (parse_uint_full(endptr + 1, &endvalue, 10) < 0) {
+            goto error;
+        }
+    } else if (*endptr == '\0') {
+        endvalue = value;
+    } else {
+        goto error;
+    }
+
+    if (endvalue >= MAX_CPUMASK_BITS) {
+        endvalue = MAX_CPUMASK_BITS - 1;
+        fprintf(stderr,
+            "qemu: NUMA: A max of %d host nodes are supported\n",
+             MAX_CPUMASK_BITS);
+    }
+
+    if (endvalue < value) {
+        goto error;
+    }
+
+    if (clear)
+        bitmap_clear(bm, value, endvalue - value + 1);
+    else
+        bitmap_set(bm, value, endvalue - value + 1);
+
+    return 0;
+
+error:
+    fprintf(stderr, "qemu: Invalid host NUMA nodes range: %s\n", hostnodes);
+    return -1;
+}
+
 static int numa_mem_parse(NumaMemOptions *opts)
 {
     uint64_t nodenr, mem_size;
@@ -110,6 +183,16 @@ static int numa_mem_parse(NumaMemOptions *opts)
     mem_size = opts->size;
     numa_info[nodenr].node_mem = mem_size;
 
+    const char *policy = opts->policy;
+    if (numa_mem_parse_policy(nodenr, policy) == -1) {
+        return -1;
+    }
+
+    const char *hostnodes = opts->host_nodes;
+    if (numa_mem_parse_hostnodes(nodenr, hostnodes) == -1) {
+        return -1;
+    }
+
     return 0;
 }
 
diff --git a/qapi-schema.json b/qapi-schema.json
index f753a35..49eac70 100644
--- a/qapi-schema.json
+++ b/qapi-schema.json
@@ -3717,9 +3717,15 @@
 #
 # @size: #optional memory size of this node
 #
+# @policy: #optional memory policy of this node
+#
+# @host-nodes: #optional host nodes for its memory policy
+#
 # Since 1.6
 ##
 { 'type': 'NumaMemOptions',
   'data': {
    '*nodeid':          'int',
-   '*size':            'size' }}
+   '*size':            'size',
+   '*policy':          'str',
+   '*host-nodes':      'str' }}
diff --git a/vl.c b/vl.c
index 5fdba97..dc8131c 100644
--- a/vl.c
+++ b/vl.c
@@ -2887,6 +2887,8 @@ int main(int argc, char **argv, char **envp)
     for (i = 0; i < MAX_NODES; i++) {
         numa_info[i].node_mem = 0;
         bitmap_zero(numa_info[i].node_cpu, MAX_CPUMASK_BITS);
+        bitmap_zero(numa_info[i].host_mem, MAX_CPUMASK_BITS);
+        numa_info[i].flags = NODE_HOST_NONE;
     }
 
     nb_numa_nodes = 0;
-- 
1.8.3.2.634.g7a3187e