qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Tao Xu <tao3.xu@intel.com>
To: imammedo@redhat.com, eblake@redhat.com, ehabkost@redhat.com
Cc: jingqi.liu@intel.com, tao3.xu@intel.com, fan.du@intel.com,
	qemu-devel@nongnu.org, jonathan.cameron@huawei.com,
	dan.j.williams@intel.com
Subject: [Qemu-devel] [PATCH v6 10/14] numa: Extend the CLI to provide memory side cache information
Date: Sun,  7 Jul 2019 22:29:54 +0800	[thread overview]
Message-ID: <20190707142958.31316-11-tao3.xu@intel.com> (raw)
In-Reply-To: <20190707142958.31316-1-tao3.xu@intel.com>

From: Liu Jingqi <jingqi.liu@intel.com>

Add -numa hmat-cache option to provide Memory Side Cache Information.
These memory attributes help to build Memory Side Cache Information
Structure(s) in ACPI Heterogeneous Memory Attribute Table (HMAT).

Signed-off-by: Liu Jingqi <jingqi.liu@intel.com>
Signed-off-by: Tao Xu <tao3.xu@intel.com>
---

Changes in v6:
    - Add add reference to ACPI 6.3 spec (Igor)
---
 numa.c          | 68 +++++++++++++++++++++++++++++++++++++++++
 qapi/misc.json  | 81 +++++++++++++++++++++++++++++++++++++++++++++++--
 qemu-options.hx | 16 ++++++++--
 3 files changed, 161 insertions(+), 4 deletions(-)

diff --git a/numa.c b/numa.c
index db5fe8c12f..1cbfb8ab4e 100644
--- a/numa.c
+++ b/numa.c
@@ -307,6 +307,68 @@ static void parse_numa_hmat_lb(MachineState *ms, NumaHmatLBOptions *node,
     }
 }
 
+static
+void parse_numa_hmat_cache(MachineState *ms, NumaHmatCacheOptions *node,
+                            Error **errp)
+{
+    int nb_numa_nodes = ms->numa_state->num_nodes;
+    HMAT_Cache_Info *hmat_cache = NULL;
+
+    if (node->node_id >= nb_numa_nodes) {
+        error_setg(errp, "Invalid node-id=%" PRIu32
+                   ", it should be less than %d.",
+                   node->node_id, nb_numa_nodes);
+        return;
+    }
+
+    if (node->total > MAX_HMAT_CACHE_LEVEL) {
+        error_setg(errp, "Invalid total=%" PRIu8
+                   ", it should be less than or equal to %d.",
+                   node->total, MAX_HMAT_CACHE_LEVEL);
+        return;
+    }
+    if (node->level > node->total) {
+        error_setg(errp, "Invalid level=%" PRIu8
+                   ", it should be less than or equal to"
+                   " total=%" PRIu8 ".",
+                   node->level, node->total);
+        return;
+    }
+    if (ms->numa_state->hmat_cache[node->node_id][node->level]) {
+        error_setg(errp, "Duplicate configuration of the side cache for "
+                   "node-id=%" PRIu32 " and level=%" PRIu8 ".",
+                   node->node_id, node->level);
+        return;
+    }
+
+    if ((node->level > 1) &&
+        ms->numa_state->hmat_cache[node->node_id][node->level - 1] &&
+        (node->size >=
+            ms->numa_state->hmat_cache[node->node_id][node->level - 1]->size)) {
+        error_setg(errp, "Invalid size=0x%" PRIx64
+                   ", the size of level=%" PRIu8
+                   " should be less than the size(0x%" PRIx64
+                   ") of level=%" PRIu8 ".",
+                   node->size, node->level,
+                   ms->numa_state->hmat_cache[node->node_id]
+                                             [node->level - 1]->size,
+                   node->level - 1);
+        return;
+    }
+
+    hmat_cache = g_malloc0(sizeof(*hmat_cache));
+
+    hmat_cache->mem_proximity = node->node_id;
+    hmat_cache->size = node->size;
+    hmat_cache->total_levels = node->total;
+    hmat_cache->level = node->level;
+    hmat_cache->associativity = node->assoc;
+    hmat_cache->write_policy = node->policy;
+    hmat_cache->line_size = node->line;
+
+    ms->numa_state->hmat_cache[node->node_id][node->level] = hmat_cache;
+}
+
 static
 void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp)
 {
@@ -352,6 +414,12 @@ void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp)
             goto end;
         }
         break;
+    case NUMA_OPTIONS_TYPE_HMAT_CACHE:
+        parse_numa_hmat_cache(ms, &object->u.hmat_cache, &err);
+        if (err) {
+            goto end;
+        }
+        break;
     default:
         abort();
     }
diff --git a/qapi/misc.json b/qapi/misc.json
index 6c7a356fa8..00d5ffabe8 100644
--- a/qapi/misc.json
+++ b/qapi/misc.json
@@ -2537,10 +2537,12 @@
 #
 # @hmat-lb: memory latency and bandwidth information (Since: 4.1)
 #
+# @hmat-cache: memory side cache information (Since: 4.1)
+#
 # Since: 2.1
 ##
 { 'enum': 'NumaOptionsType',
-  'data': [ 'node', 'dist', 'cpu', 'hmat-lb' ] }
+  'data': [ 'node', 'dist', 'cpu', 'hmat-lb', 'hmat-cache' ] }
 
 ##
 # @NumaOptions:
@@ -2556,7 +2558,8 @@
     'node': 'NumaNodeOptions',
     'dist': 'NumaDistOptions',
     'cpu': 'NumaCpuOptions',
-    'hmat-lb': 'NumaHmatLBOptions' }}
+    'hmat-lb': 'NumaHmatLBOptions',
+    'hmat-cache': 'NumaHmatCacheOptions' }}
 
 ##
 # @NumaNodeOptions:
@@ -2719,6 +2722,80 @@
     '*latency': 'uint16',
     '*bandwidth': 'uint16' }}
 
+##
+# @HmatCacheAssociativity:
+#
+# Cache associativity in the Memory Side Cache
+# Information Structure of HMAT
+#
+# For more information of @HmatCacheAssociativity see
+# the chapter 5.2.27.5: Table 5-143 of ACPI 6.3 spec.
+#
+# @none: None
+#
+# @direct: Direct Mapped
+#
+# @complex: Complex Cache Indexing (implementation specific)
+#
+# Since: 4.1
+##
+{ 'enum': 'HmatCacheAssociativity',
+  'data': [ 'none', 'direct', 'complex' ] }
+
+##
+# @HmatCacheWritePolicy:
+#
+# Cache write policy in the Memory Side Cache
+# Information Structure of HMAT
+#
+# For more information of @HmatCacheWritePolicy see
+# the chapter 5.2.27.5: Table 5-143: Field "Cache Attributes" of ACPI 6.3 spec.
+#
+# @none: None
+#
+# @write-back: Write Back (WB)
+#
+# @write-through: Write Through (WT)
+#
+# Since: 4.1
+##
+{ 'enum': 'HmatCacheWritePolicy',
+  'data': [ 'none', 'write-back', 'write-through' ] }
+
+##
+# @NumaHmatCacheOptions:
+#
+# Set the memory side cache information for a given memory domain.
+#
+# For more information of @NumaHmatCacheOptions see
+# the chapter 5.2.27.5: Table 5-143: Field "Cache Attributes" of ACPI 6.3 spec.
+#
+# @node-id: the memory proximity domain to which the memory belongs.
+#
+# @size: the size of memory side cache in bytes.
+#
+# @total: the total cache levels for this memory proximity domain.
+#
+# @level: the cache level described in this structure.
+#
+# @assoc: the cache associativity, none/direct-mapped/complex(complex cache indexing).
+#
+# @policy: the write policy, none/write-back/write-through.
+#
+# @line: the cache Line size in bytes.
+#
+# Since: 4.1
+##
+{ 'struct': 'NumaHmatCacheOptions',
+  'data': {
+   'node-id': 'uint32',
+   'size': 'size',
+   'total': 'uint8',
+   'level': 'uint8',
+   'assoc': 'HmatCacheAssociativity',
+   'policy': 'HmatCacheWritePolicy',
+   'line': 'uint16' }}
+
 ##
 # @HostMemPolicy:
 #
diff --git a/qemu-options.hx b/qemu-options.hx
index 8dfbeb2941..d47a7db69e 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -164,7 +164,8 @@ DEF("numa", HAS_ARG, QEMU_OPTION_numa,
     "-numa node[,memdev=id][,cpus=firstcpu[-lastcpu]][,nodeid=node][,initiator=node]\n"
     "-numa dist,src=source,dst=destination,val=distance\n"
     "-numa cpu,node-id=node[,socket-id=x][,core-id=y][,thread-id=z]\n"
-    "-numa hmat-lb,initiator=node,target=node,hierarchy=memory|last-level|first-level|second-level|third-level,data-type=access-latency|read-latency|write-latency[,base-lat=blat][,base-bw=bbw][,latency=lat][,bandwidth=bw]\n",
+    "-numa hmat-lb,initiator=node,target=node,hierarchy=memory|last-level|first-level|second-level|third-level,data-type=access-latency|read-latency|write-latency[,base-lat=blat][,base-bw=bbw][,latency=lat][,bandwidth=bw]\n"
+    "-numa hmat-cache,node-id=node,size=size,total=total,level=level[,assoc=none|direct|complex][,policy=none|write-back|write-through][,line=size]\n",
     QEMU_ARCH_ALL)
 STEXI
 @item -numa node[,mem=@var{size}][,cpus=@var{firstcpu}[-@var{lastcpu}]][,nodeid=@var{node}][,initiator=@var{initiator}]
@@ -172,6 +173,7 @@ STEXI
 @itemx -numa dist,src=@var{source},dst=@var{destination},val=@var{distance}
 @itemx -numa cpu,node-id=@var{node}[,socket-id=@var{x}][,core-id=@var{y}][,thread-id=@var{z}]
 @itemx -numa hmat-lb,initiator=@var{node},target=@var{node},hierarchy=@var{str},data-type=@var{str}[,base-lat=@var{blat}][,base-bw=@var{bbw}][,latency=@var{lat}][,bandwidth=@var{bw}]
+@itemx -numa hmat-cache,node-id=@var{node},size=@var{size},total=@var{total},level=@var{level}[,assoc=@var{str}][,policy=@var{str}][,line=@var{size}]
 @findex -numa
 Define a NUMA node and assign RAM and VCPUs to it.
 Set the NUMA distance from a source node to a destination node.
@@ -274,11 +276,19 @@ Note: Due to the minimum matrix value entry value being 10, the base unit corres
 to a value of 10. And @var{blat} or @var{bbw} should be an integer. @var{lat} or
 @var{bw} is the latency/bandwidth value.
 
+In @samp{hmat-cache} option, @var{node-id} is the NUMA-id of the memory belongs.
+@var{size} is the size of memory side cache in bytes. @var{total} is the total cache levels.
+@var{level} is the cache level described in this structure. @var{assoc} is the cache associativity.
+"none/direct-mapped/complex(complex cache indexing). @var{policy} is the write policy.
+@var{line} is the cache Line size in bytes.
+
 For example, the following option assigns NUMA node 0 and 1. Node 0 has 2 cpus and
 a ram, node 1 has only a ram. The processors in node 0 access memory in node
 0 with access-latency 5 picoseconds(base latency is 10), access-bandwidth 5 MB/s(base latency is 20);
 The processors in NUMA node 0 access memory in NUMA node 1 with access-latency 10
-picoseconds(base latency is 10), access-bandwidth 10 MB/s(base latency is 20):
+picoseconds(base latency is 10), access-bandwidth 10 MB/s(base latency is 20).
+And for memory side cache information, NUMA node 0 and 1 both have 1 level memory
+cache, size is 0x20000 bytes, policy is write-back, the cache Line size is 8 bytes:
 @example
 -m 2G \
 -object memory-backend-ram,size=1024M,policy=bind,host-nodes=0,id=ram-node0 -numa node,nodeid=0,memdev=ram-node0 \
@@ -290,6 +300,8 @@ picoseconds(base latency is 10), access-bandwidth 10 MB/s(base latency is 20):
 -numa hmat-lb,initiator=0,target=0,hierarchy=memory,data-type=access-bandwidth,base-bw=20,bandwidth=5 \
 -numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-latency,base-lat=10,latency=10 \
 -numa hmat-lb,initiator=0,target=1,hierarchy=memory,data-type=access-bandwidth,base-bw=20,bandwidth=10 \
+-numa hmat-cache,node-id=0,size=0x20000,total=1,level=1,assoc=direct,policy=write-back,line=8 \
+-numa hmat-cache,node-id=1,size=0x20000,total=1,level=1,assoc=direct,policy=write-back,line=8 \
 @end example
 
 ETEXI
-- 
2.20.1



  parent reply	other threads:[~2019-07-07 14:37 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-07 14:29 [Qemu-devel] [PATCH v6 00/14] Build ACPI Heterogeneous Memory Attribute Table (HMAT) Tao Xu
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 01/14] hw/arm: simplify arm_load_dtb Tao Xu
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 02/14] numa: move numa global variable nb_numa_nodes into MachineState Tao Xu
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 03/14] numa: move numa global variable have_numa_distance " Tao Xu
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 04/14] numa: move numa global variable numa_info " Tao Xu
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 05/14] numa: Extend CLI to provide initiator information for numa nodes Tao Xu
2019-07-08 13:20   ` Eric Blake
2019-07-09  0:46     ` Tao Xu
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 06/14] hmat acpi: Build Memory Proximity Domain Attributes Structure(s) Tao Xu
2019-07-09  8:25   ` Jonathan Cameron
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 07/14] hmat acpi: Build System Locality Latency and Bandwidth Information Structure(s) Tao Xu
2019-07-09  8:50   ` Jonathan Cameron
2019-07-09 15:48     ` Tao Xu
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 08/14] hmat acpi: Build Memory Side Cache " Tao Xu
2019-07-09  8:24   ` Jonathan Cameron
2019-07-09 14:48     ` Tao Xu
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 09/14] numa: Extend the CLI to provide memory latency and bandwidth information Tao Xu
2019-07-07 14:29 ` Tao Xu [this message]
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 11/14] acpi: introduce aml_build_runtime_buf for NFIT generalizations Tao Xu
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 12/14] hmat acpi: Implement _HMA method to update HMAT at runtime Tao Xu
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 13/14] QMP: Add QMP interface " Tao Xu
2019-07-07 14:29 ` [Qemu-devel] [PATCH v6 14/14] tests/bios-tables-test: add test cases for ACPI HMAT Tao Xu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190707142958.31316-11-tao3.xu@intel.com \
    --to=tao3.xu@intel.com \
    --cc=dan.j.williams@intel.com \
    --cc=eblake@redhat.com \
    --cc=ehabkost@redhat.com \
    --cc=fan.du@intel.com \
    --cc=imammedo@redhat.com \
    --cc=jingqi.liu@intel.com \
    --cc=jonathan.cameron@huawei.com \
    --cc=qemu-devel@nongnu.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).