From mboxrd@z Thu Jan  1 00:00:00 1970
From: Dario Faggioli <dario.faggioli@citrix.com>
Subject: [PATCH 3 of 3] xl: allow for node-wise specification of
	vcpu pinning
Date: Tue, 16 Oct 2012 19:26:28 +0200
Message-ID: <6d7a403305dd057f61bd.1350408388@Solace>
References: <patchbomb.1350408385@Solace>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Return-path: <xen-devel-bounces@lists.xen.org>
In-Reply-To: <patchbomb.1350408385@Solace>
List-Unsubscribe: <http://lists.xen.org/cgi-bin/mailman/options/xen-devel>,
	<mailto:xen-devel-request@lists.xen.org?subject=unsubscribe>
List-Post: <mailto:xen-devel@lists.xen.org>
List-Help: <mailto:xen-devel-request@lists.xen.org?subject=help>
List-Subscribe: <http://lists.xen.org/cgi-bin/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xen.org?subject=subscribe>
Sender: xen-devel-bounces@lists.xen.org
Errors-To: xen-devel-bounces@lists.xen.org
To: xen-devel@lists.xen.org
Cc: Andre Przywara <andre.przywara@amd.com>, Ian Jackson <Ian.Jackson@eu.citrix.com>, Ian Campbell <Ian.Campbell@citrix.com>
List-Id: xen-devel@lists.xenproject.org

Making it possible to use something like the following:
 * "nodes:0-3": all pCPUs of nodes 0,1,2,3;
 * "nodes:0-3,^node:2": all pCPUS of nodes 0,1,3;
 * "1,nodes:1-2,^6": pCPU 1 plus all pCPUs of nodes 1,2 but not pCPU 6;
 * ...

In both domain config file and `xl vcpu-pin'.

Signed-off-by: Dario Faggioli <dario.faggioli@citrix.com>

diff --git a/docs/man/xl.cfg.pod.5 b/docs/man/xl.cfg.pod.5
--- a/docs/man/xl.cfg.pod.5
+++ b/docs/man/xl.cfg.pod.5
@@ -109,7 +109,7 @@ some cpus on its own (see below). A C<CP
 
 =over 4
 
-=item "all"
+=item "all" (or "nodes:all")
 
 To allow all the vcpus of the guest to run on all the cpus on the host.
 
@@ -117,6 +117,14 @@ To allow all the vcpus of the guest to r
 
 To allow all the vcpus of the guest to run on cpus 0,2,3,5.
 
+=item "nodes:0-3,^node:2"
+
+To allow all the vcpus of the guest to run on the cpus belonging to
+the NUMA nodes 0,1,3 of the host. Notice that it is possible to combine
+this syntax with the one above. That means, something like "1,node:2,^6"
+is possible and means all the vcpus of the guest will run on cpus 1 plus
+on all the cpus of node 2, but never on cpu 6.
+
 =item ["2", "3"] (or [2, 3])
 
 To ask for specific vcpu mapping. That means (in this example), vcpu #0
diff --git a/tools/libxl/xl_cmdimpl.c b/tools/libxl/xl_cmdimpl.c
--- a/tools/libxl/xl_cmdimpl.c
+++ b/tools/libxl/xl_cmdimpl.c
@@ -506,31 +506,58 @@ static void split_string_into_string_lis
 
 static int vcpupin_parse(char *cpu, libxl_bitmap *cpumap)
 {
-    libxl_bitmap exclude_cpumap;
-    uint32_t cpuida, cpuidb;
+    libxl_bitmap nodemap, cpu_nodemap;
+    libxl_bitmap exclude_cpumap, exclude_nodemap;
+    uint32_t ida, idb;
     char *endptr, *toka, *tokb, *saveptr = NULL;
-    int i, rc = 0, rmcpu;
-
-    if (!strcmp(cpu, "all")) {
+    int i, rc = 0, isnot, isnode;
+
+    if (!strcmp(cpu, "all") || !strcmp(cpu, "nodes:all")) {
         libxl_bitmap_set_any(cpumap);
         return 0;
     }
 
-    if (libxl_cpu_bitmap_alloc(ctx, &exclude_cpumap, 0)) {
+    libxl_bitmap_init(&cpu_nodemap);
+    libxl_bitmap_init(&nodemap);
+    libxl_bitmap_init(&exclude_nodemap);
+    libxl_bitmap_init(&exclude_nodemap);
+
+    rc = libxl_node_bitmap_alloc(ctx, &cpu_nodemap, 0);
+    if (rc) {
+        fprintf(stderr, "Error: Failed to allocate nodemap.\n");
+        goto vcpp_out;
+    }
+    rc = libxl_node_bitmap_alloc(ctx, &nodemap, 0);
+    if (rc) {
+        fprintf(stderr, "Error: Failed to allocate nodemap.\n");
+        goto vcpp_out;
+    }
+    rc = libxl_node_bitmap_alloc(ctx, &exclude_nodemap, 0);
+    if (rc) {
+        fprintf(stderr, "Error: Failed to allocate nodemap.\n");
+        goto vcpp_out;
+    }
+    rc = libxl_cpu_bitmap_alloc(ctx, &exclude_cpumap, 0);
+    if (rc) {
         fprintf(stderr, "Error: Failed to allocate cpumap.\n");
-        return ENOMEM;
+        goto vcpp_out;
     }
 
     for (toka = strtok_r(cpu, ",", &saveptr); toka;
          toka = strtok_r(NULL, ",", &saveptr)) {
-        rmcpu = 0;
+        isnot = 0; isnode = 0;
         if (*toka == '^') {
-            /* This (These) Cpu(s) will be removed from the map */
+            /* This (These) Cpu(s)/Node(s) will be removed from the map */
             toka++;
-            rmcpu = 1;
-        }
-        /* Extract a valid (range of) cpu(s) */
-        cpuida = cpuidb = strtoul(toka, &endptr, 10);
+            isnot = 1;
+        }
+        /* Check if we're dealing with a full node */
+        if (strstr(toka, "node:") == toka || strstr(toka, "nodes:") == toka) {
+            toka += 5 + (toka[4] == 's');
+            isnode = 1;
+        }
+        /* Extract a valid (range of) cpu(s) or node(s) */
+        ida = idb = strtoul(toka, &endptr, 10);
         if (endptr == toka) {
             fprintf(stderr, "Error: Invalid argument.\n");
             rc = EINVAL;
@@ -538,27 +565,48 @@ static int vcpupin_parse(char *cpu, libx
         }
         if (*endptr == '-') {
             tokb = endptr + 1;
-            cpuidb = strtoul(tokb, &endptr, 10);
-            if (endptr == tokb || cpuida > cpuidb) {
+            idb = strtoul(tokb, &endptr, 10);
+            if (endptr == tokb || ida > idb) {
                 fprintf(stderr, "Error: Invalid argument.\n");
                 rc = EINVAL;
                 goto vcpp_out;
             }
         }
-        while (cpuida <= cpuidb) {
-            rmcpu == 0 ? libxl_bitmap_set(cpumap, cpuida) :
-                         libxl_bitmap_set(&exclude_cpumap, cpuida);
-            cpuida++;
-        }
-    }
-
-    /* Clear all the cpus from the removal list */
+        while (ida <= idb) {
+            if (!isnode)
+                isnot == 0 ? libxl_bitmap_set(cpumap, ida) :
+                             libxl_bitmap_set(&exclude_cpumap, ida);
+            else
+                isnot == 0 ? libxl_bitmap_set(&nodemap, ida) :
+                             libxl_bitmap_set(&exclude_nodemap, ida);
+            ida++;
+        }
+    }
+
+    /* Add the cpus that have been specified via "node:" items */
+    rc = libxl_nodemap_to_cpumap(ctx, &nodemap, &cpu_nodemap);
+    if (rc)
+        goto vcpp_out;
+    libxl_for_each_set_bit(i, cpu_nodemap) {
+        libxl_bitmap_set(cpumap, i);
+    }
+
+    /* Clear all the cpus from the removal cpu and node lists */
     libxl_for_each_set_bit(i, exclude_cpumap) {
         libxl_bitmap_reset(cpumap, i);
     }
+    rc = libxl_nodemap_to_cpumap(ctx, &exclude_nodemap, &cpu_nodemap);
+    if (rc)
+        goto vcpp_out;
+    libxl_for_each_set_bit(i, cpu_nodemap) {
+        libxl_bitmap_reset(cpumap, i);
+    }
 
 vcpp_out:
     libxl_bitmap_dispose(&exclude_cpumap);
+    libxl_bitmap_dispose(&exclude_nodemap);
+    libxl_bitmap_dispose(&nodemap);
+    libxl_bitmap_dispose(&cpu_nodemap);
 
     return rc;
 }