[Qemu-devel] [PATCH 3/7] NUMA: parse guest numa nodes memory policy

[Wanlong Gao]

The memory policy setting format is like:
{membind|interleave|preferred}=[+|!]{all|N-N}
And we are adding this setting as a suboption of "-numa",
the memory policy then can be set like following:
 -numa node,nodeid=0,mem=1024,cpus=0,membind=0-1
 -numa node,nodeid=1,mem=1024,cpus=1,interleave=1

Signed-off-by: Andre Przywara <address@hidden>
Signed-off-by: Wanlong Gao <address@hidden>
---
 include/sysemu/sysemu.h |  8 ++++++
 vl.c                    | 76 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 84 insertions(+)

diff --git a/include/sysemu/sysemu.h b/include/sysemu/sysemu.h
index 70fd2ed..993b8e0 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;
 struct node_info {
     uint64_t node_mem;
     DECLARE_BITMAP(node_cpu, MAX_CPUMASK_BITS);
+    DECLARE_BITMAP(host_mem, MAX_CPUMASK_BITS);
+    unsigned int flags;
 };
 extern struct node_info numa_info[MAX_NODES];
 
diff --git a/vl.c b/vl.c
index 42dec5e..ada9fb2 100644
--- a/vl.c
+++ b/vl.c
@@ -1348,11 +1348,68 @@ error:
     exit(1);
 }
 
+static unsigned int numa_node_parse_mpol(const char *str, unsigned long *bm)
+{
+    unsigned long long value, endvalue;
+    char *endptr;
+    unsigned int flags = 0;
+
+    if (str[0] == '!') {
+        flags |= 2;
+        bitmap_fill(bm, MAX_CPUMASK_BITS);
+        str++;
+    }
+    if (str[0] == '+') {
+        flags |= 1;
+        str++;
+    }
+
+    if (!strcmp(str, "all")) {
+        bitmap_fill(bm, MAX_CPUMASK_BITS);
+        return flags;
+    }
+
+    if (parse_uint(str, &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 (flags & 2)
+        bitmap_clear(bm, value, endvalue - value + 1);
+    else
+        bitmap_set(bm, value, endvalue - value + 1);
+
+    return flags;
+
+error:
+    fprintf(stderr, "qemu: Invalid host NUMA nodes range: %s\n", str);
+    return 4;
+}
+
 static void numa_add(const char *optarg)
 {
     char option[128];
     char *endptr;
     unsigned long long nodenr;
+    unsigned int ret;
 
     optarg = get_opt_name(option, 128, optarg, ',');
     if (*optarg == ',') {
@@ -1393,6 +1450,23 @@ static void numa_add(const char *optarg)
         if (get_param_value(option, 128, "cpus", optarg) != 0) {
             numa_node_parse_cpus(nodenr, option);
         }
+
+        option[0] = 0;
+        if (get_param_value(option, 128, "interleave", optarg) != 0)
+            numa_info[nodenr].flags |= NODE_HOST_INTERLEAVE;
+        else if (get_param_value(option, 128, "preferred", optarg) != 0)
+            numa_info[nodenr].flags |= NODE_HOST_PREFERRED;
+        else if (get_param_value(option, 128, "membind", optarg) != 0)
+            numa_info[nodenr].flags |= NODE_HOST_BIND;
+        if (option[0] != 0) {
+            ret = numa_node_parse_mpol(option, numa_info[nodenr].host_mem);
+            if (ret == 4) {
+                exit(1);
+            } else if (ret & 1) {
+                numa_info[nodenr].flags |= NODE_HOST_RELATIVE;
+            }
+        }
+
         nb_numa_nodes++;
     } else {
         fprintf(stderr, "Invalid -numa option: %s\n", option);
@@ -2922,6 +2996,8 @@ 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.rc2.10.g0c2b1cf