2010-12-02 06:37:33

by Zheng, Shaohui

[permalink] [raw]
Subject: [patch 7/7, v7] NUMA Hotplug Emulator: Implement mem_hotplug/add_memory debugfs interface

From: Shaohui Zheng <[email protected]>

Add mem_hotplug/add_memory interface to support to memory hotplug emulation.
the reserved memory can be added into desired node with this interface.

Add a memory section(128M) to node 3(boots with mem=1024m)

echo 0x40000000,3 > mem_hotplug/add_memory

And more we make it friendly, it is possible to add memory to do

echo 3g > mem_hotplug/add_memory
echo 1024m,3 > mem_hotplug/add_memory

Another format suggested by Dave Hansen:

echo physical_address=0x40000000 numa_node=3 > mem_hotplug/add_memory

it is more explicit to show meaning of the parameters.

CC: David Rientjes <[email protected]>
CC: Dave Hansen <[email protected]>
Signed-off-by: Shaohui Zheng <[email protected]>
Signed-off-by: Haicheng Li <[email protected]>
Signed-off-by: Shaohui Zheng <[email protected]>
---
Index: linux-hpe4/mm/memory_hotplug.c
===================================================================
--- linux-hpe4.orig/mm/memory_hotplug.c 2010-12-02 12:17:58.267622002 +0800
+++ linux-hpe4/mm/memory_hotplug.c 2010-12-02 12:18:02.507622002 +0800
@@ -983,4 +983,87 @@
}

module_init(node_debug_init);
+
+#ifdef CONFIG_ARCH_MEMORY_PROBE
+
+static ssize_t add_memory_store(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ u64 phys_addr = 0;
+ int nid = 0;
+ int ret;
+ char *p = NULL, *q = NULL;
+ /* format: physical_address=0x40000000 numa_node=3 */
+ p = strchr(buf, '=');
+ if (p != NULL) {
+ *p = '\0';
+ q = strchr(buf, ' ');
+ if (q == NULL) {
+ if (strcmp(buf, "physical_address") != 0)
+ ret = -EPERM;
+ else
+ phys_addr = memparse(p+1, NULL);
+ } else {
+ *q++ = '\0';
+ p = strchr(q, '=');
+ if (strcmp(buf, "physical_address") == 0)
+ phys_addr = memparse(p+1, NULL);
+ if (strcmp(buf, "numa_node") == 0)
+ nid = simple_strtoul(p+1, NULL, 0);
+ if (strcmp(q, "physical_address") == 0)
+ phys_addr = memparse(p+1, NULL);
+ if (strcmp(q, "numa_node") == 0)
+ nid = simple_strtoul(p+1, NULL, 0);
+ }
+ } else { /* physical_address,numa_node */
+ p = strchr(buf, ',');
+ if (p != NULL && strlen(p+1) > 0) {
+ /* nid specified */
+ *p++ = '\0';
+ nid = simple_strtoul(p, NULL, 0);
+ phys_addr = memparse(buf, NULL);
+ } else {
+ phys_addr = memparse(buf, NULL);
+ nid = memory_add_physaddr_to_nid(phys_addr);
+ }
+ }
+
+ if (nid < 0 || nid > nr_node_ids - 1) {
+ printk(KERN_ERR "Invalid node id %d(0<=nid<%d).\n", nid, nr_node_ids);
+ ret = -EPERM;
+ } else {
+ printk(KERN_INFO "Add a memory section to node: %d.\n", nid);
+ ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT);
+ if (ret)
+ count = ret;
+ }
+
+ if (ret)
+ count = ret;
+
+ return count;
+}
+
+static const struct file_operations add_memory_file_ops = {
+ .write = add_memory_store,
+ .llseek = generic_file_llseek,
+};
+
+static int __init memory_debug_init(void)
+{
+ if (!memhp_debug_root)
+ memhp_debug_root = debugfs_create_dir("mem_hotplug", NULL);
+ if (!memhp_debug_root)
+ return -ENOMEM;
+
+ if (!debugfs_create_file("add_memory", S_IWUSR, memhp_debug_root,
+ NULL, &add_memory_file_ops))
+ return -ENOMEM;
+
+ return 0;
+}
+
+module_init(memory_debug_init);
+
+#endif /* CONFIG_ARCH_MEMORY_PROBE */
#endif /* CONFIG_DEBUG_FS */
Index: linux-hpe4/Documentation/memory-hotplug.txt
===================================================================
--- linux-hpe4.orig/Documentation/memory-hotplug.txt 2010-12-02 12:18:17.387622002 +0800
+++ linux-hpe4/Documentation/memory-hotplug.txt 2010-12-02 12:30:51.717622000 +0800
@@ -19,6 +19,7 @@
4.1 Hardware(Firmware) Support
4.2 Notify memory hot-add event by hand
4.3 Node hotplug emulation
+ 4.4 Memory hotplug emulation
5. Logical Memory hot-add phase
5.1. State of memory
5.2. How to online memory
@@ -239,6 +240,30 @@
Once the new node has been added, it is possible to online the memory by
toggling the "state" of its memory section(s) as described in section 5.1.

+4.4 Memory hotplug emulation
+------------
+With debugfs, it is possible to test memory hotplug with software method, we
+can add memory section to desired node with add_memory interface. It is a much
+more powerful interface than "probe" described in section 4.2.
+
+The add_memory interface is located at "mem_hotplug/add_memory" at the debugfs
+mount point.
+
+Add a memory section(128M) to node 3(boots with mem=1024m)
+
+ echo 0x40000000,3 > mem_hotplug/add_memory
+
+And more we make it friendly, it is possible to add memory to do
+
+ echo 3g > mem_hotplug/add_memory
+ echo 1024m,3 > mem_hotplug/add_memory
+
+Another format suggested by Dave Hansen:
+
+ echo physical_address=0x40000000 numa_node=3 > mem_hotplug/add_memory
+
+Once the new memory section has been added, it is possible to online the memory
+by toggling the "state" described in section 5.1.

------------------------------
5. Logical Memory hot-add phase

--
Thanks & Regards,
Shaohui


2010-12-02 23:37:12

by David Rientjes

[permalink] [raw]
Subject: Re: [patch 7/7, v7] NUMA Hotplug Emulator: Implement mem_hotplug/add_memory debugfs interface

On Thu, 2 Dec 2010, [email protected] wrote:

> From: Shaohui Zheng <[email protected]>
>
> Add mem_hotplug/add_memory interface to support to memory hotplug emulation.
> the reserved memory can be added into desired node with this interface.
>
> Add a memory section(128M) to node 3(boots with mem=1024m)
>
> echo 0x40000000,3 > mem_hotplug/add_memory
>
> And more we make it friendly, it is possible to add memory to do
>
> echo 3g > mem_hotplug/add_memory
> echo 1024m,3 > mem_hotplug/add_memory
>
> Another format suggested by Dave Hansen:
>
> echo physical_address=0x40000000 numa_node=3 > mem_hotplug/add_memory
>
> it is more explicit to show meaning of the parameters.
>

NACK, we don't need such convoluted definitions if debugfs were extended
with per-node triggers to add_memory as I suggested in v6 of your
proposal:

/sys/kernel/debug/mem_hotplug/add_node (already exists)
/sys/kernel/debug/mem_hotplug/node0/add_memory
/sys/kernel/debug/mem_hotplug/node1/add_memory
...

You can then write a physical starting address to the add_memory files to
hotadd memory to a node other than the one to which it has physical
affinity. This is much more extendable if we add additional per-node
triggers later.

It would also be helpful if you were to reach consensus on the matters
under discussion before posting a new version of your patchset everyday.

2010-12-06 01:15:33

by Shaohui Zheng

[permalink] [raw]
Subject: Re: [patch 7/7, v7] NUMA Hotplug Emulator: Implement mem_hotplug/add_memory debugfs interface

On Thu, Dec 02, 2010 at 03:37:03PM -0800, David Rientjes wrote:
> On Thu, 2 Dec 2010, [email protected] wrote:
>
> > From: Shaohui Zheng <[email protected]>
> >
> > Add mem_hotplug/add_memory interface to support to memory hotplug emulation.
> > the reserved memory can be added into desired node with this interface.
> >
> > Add a memory section(128M) to node 3(boots with mem=1024m)
> >
> > echo 0x40000000,3 > mem_hotplug/add_memory
> >
> > And more we make it friendly, it is possible to add memory to do
> >
> > echo 3g > mem_hotplug/add_memory
> > echo 1024m,3 > mem_hotplug/add_memory
> >
> > Another format suggested by Dave Hansen:
> >
> > echo physical_address=0x40000000 numa_node=3 > mem_hotplug/add_memory
> >
> > it is more explicit to show meaning of the parameters.
> >
>
> NACK, we don't need such convoluted definitions if debugfs were extended
> with per-node triggers to add_memory as I suggested in v6 of your
> proposal:
>
> /sys/kernel/debug/mem_hotplug/add_node (already exists)
> /sys/kernel/debug/mem_hotplug/node0/add_memory
> /sys/kernel/debug/mem_hotplug/node1/add_memory
> ...
>
> You can then write a physical starting address to the add_memory files to
> hotadd memory to a node other than the one to which it has physical
> affinity. This is much more extendable if we add additional per-node
> triggers later.
>
> It would also be helpful if you were to reach consensus on the matters
> under discussion before posting a new version of your patchset everyday.

After consider your proposal again, the new add_memory interface under each
nodes follow the rule "one file one parameter" better. it make the parser
much simpler.

I work out a patch for this proposal, and it works on my side.
Any more comments?

Subject: NUMA Hotplug Emulator: Implement add_memory debugfs interface

From: Shaohui Zheng <[email protected]>

Add add_memory interface to support to memory hotplug emulation for each online
node under debugfs. The reserved memory can be added into desired node with
this interface.

The layout on debufs:
mem_hotplug/node0/add_memory
mem_hotplug/node1/add_memory
mem_hotplug/node2/add_memory
...

Add a memory section(128M) to node 3(boots with mem=1024m)

echo 0x40000000 > mem_hotplug/node3/add_memory

And more we make it friendly, it is possible to add memory to do

echo 1024m > mem_hotplug/node3/add_memory

CC: David Rientjes <[email protected]>
CC: Dave Hansen <[email protected]>
Signed-off-by: Shaohui Zheng <[email protected]>
Signed-off-by: Haicheng Li <[email protected]>
Signed-off-by: Shaohui Zheng <[email protected]>
---
Index: linux-hpe4/mm/memory_hotplug.c
===================================================================
--- linux-hpe4.orig/mm/memory_hotplug.c 2010-12-02 12:35:31.557622002 +0800
+++ linux-hpe4/mm/memory_hotplug.c 2010-12-06 07:30:36.067622001 +0800
@@ -930,6 +930,80 @@

static struct dentry *memhp_debug_root;

+#ifdef CONFIG_ARCH_MEMORY_PROBE
+
+static ssize_t add_memory_store(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ u64 phys_addr = 0;
+ int nid = file->private_data - NULL;
+ int ret;
+
+ phys_addr = simple_strtoull(buf, NULL, 0);
+ printk(KERN_INFO "Add a memory section to node: %d.\n", nid);
+ phys_addr = memparse(buf, NULL);
+ ret = add_memory(nid, phys_addr, PAGES_PER_SECTION << PAGE_SHIFT);
+
+ if (ret)
+ count = ret;
+
+ return count;
+}
+
+static int add_memory_open(struct inode *inode, struct file *file)
+{
+ file->private_data = inode->i_private;
+ return 0;
+}
+
+static const struct file_operations add_memory_file_ops = {
+ .open = add_memory_open,
+ .write = add_memory_store,
+ .llseek = generic_file_llseek,
+};
+
+/*
+ * Create add_memory debugfs entry under specified node
+ */
+static int debugfs_create_add_memory_entry(int nid)
+{
+ char buf[32];
+ static struct dentry *node_debug_root;
+
+ snprintf(buf, sizeof(buf), "node%d", nid);
+ node_debug_root = debugfs_create_dir(buf, memhp_debug_root);
+
+ /* the nid information was represented by the offset of pointer(NULL+nid) */
+ if (!debugfs_create_file("add_memory", S_IWUSR, node_debug_root,
+ NULL + nid, &add_memory_file_ops))
+ return -ENOMEM;
+
+ return 0;
+}
+
+static int __init memory_debug_init(void)
+{
+ int nid;
+
+ if (!memhp_debug_root)
+ memhp_debug_root = debugfs_create_dir("mem_hotplug", NULL);
+ if (!memhp_debug_root)
+ return -ENOMEM;
+
+ for_each_online_node(nid)
+ debugfs_create_add_memory_entry(nid);
+
+ return 0;
+}
+
+module_init(memory_debug_init);
+#else
+static debugfs_create_add_memory_entry(int nid)
+{
+ return 0;
+}
+#endif /* CONFIG_ARCH_MEMORY_PROBE */
+
static ssize_t add_node_store(struct file *file, const char __user *buf,
size_t count, loff_t *ppos)
{
@@ -960,6 +1034,8 @@
return -ENOMEM;

ret = add_memory(nid, start, size);
+
+ debugfs_create_add_memory_entry(nid);
return ret ? ret : count;
}

Index: linux-hpe4/Documentation/memory-hotplug.txt
===================================================================
--- linux-hpe4.orig/Documentation/memory-hotplug.txt 2010-12-02 12:35:31.557622002 +0800
+++ linux-hpe4/Documentation/memory-hotplug.txt 2010-12-06 07:39:36.007622000 +0800
@@ -19,6 +19,7 @@
4.1 Hardware(Firmware) Support
4.2 Notify memory hot-add event by hand
4.3 Node hotplug emulation
+ 4.4 Memory hotplug emulation
5. Logical Memory hot-add phase
5.1. State of memory
5.2. How to online memory
@@ -239,6 +240,29 @@
Once the new node has been added, it is possible to online the memory by
toggling the "state" of its memory section(s) as described in section 5.1.

+4.4 Memory hotplug emulation
+------------
+With debugfs, it is possible to test memory hotplug with software method, we
+can add memory section to desired node with add_memory interface. It is a much
+more powerful interface than "probe" described in section 4.2.
+
+There is an add_memory interface for each online node at the debugfs mount
+point.
+ mem_hotplug/node0/add_memory
+ mem_hotplug/node1/add_memory
+ mem_hotplug/node2/add_memory
+ ...
+
+Add a memory section(128M) to node 3(boots with mem=1024m)
+
+ echo 0x40000000 > mem_hotplug/node3/add_memory
+
+And more we make it friendly, it is possible to add memory to do
+
+ echo 1024m > mem_hotplug/node3/add_memory
+
+Once the new memory section has been added, it is possible to online the memory
+by toggling the "state" described in section 5.1.

------------------------------
5. Logical Memory hot-add phase


--
Thanks & Regards,
Shaohui