[permalink] [raw]

Subject: [V5 PATCH 04/26] node: cleanup node_state_attr

use [index] = init_value
use N_xxxxx instead of hardcode.

Make it more readability and easy to add new state.

Signed-off-by: Lai Jiangshan <[email protected]>
---
drivers/base/node.c | 20 ++++++++++----------
1 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/base/node.c b/drivers/base/node.c
index af1a177..5d7731e 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -614,23 +614,23 @@ static ssize_t show_node_state(struct device *dev,
{ __ATTR(name, 0444, show_node_state, NULL), state }

static struct node_attr node_state_attr[] = {
- _NODE_ATTR(possible, N_POSSIBLE),
- _NODE_ATTR(online, N_ONLINE),
- _NODE_ATTR(has_normal_memory, N_NORMAL_MEMORY),
- _NODE_ATTR(has_cpu, N_CPU),
+ [N_POSSIBLE] = _NODE_ATTR(possible, N_POSSIBLE),
+ [N_ONLINE] = _NODE_ATTR(online, N_ONLINE),
+ [N_NORMAL_MEMORY] = _NODE_ATTR(has_normal_memory, N_NORMAL_MEMORY),
#ifdef CONFIG_HIGHMEM
- _NODE_ATTR(has_high_memory, N_HIGH_MEMORY),
+ [N_HIGH_MEMORY] = _NODE_ATTR(has_high_memory, N_HIGH_MEMORY),
#endif
+ [N_CPU] = _NODE_ATTR(has_cpu, N_CPU),
};

static struct attribute *node_state_attrs[] = {
- &node_state_attr[0].attr.attr,
- &node_state_attr[1].attr.attr,
- &node_state_attr[2].attr.attr,
- &node_state_attr[3].attr.attr,
+ &node_state_attr[N_POSSIBLE].attr.attr,
+ &node_state_attr[N_ONLINE].attr.attr,
+ &node_state_attr[N_NORMAL_MEMORY].attr.attr,
#ifdef CONFIG_HIGHMEM
- &node_state_attr[4].attr.attr,
+ &node_state_attr[N_HIGH_MEMORY].attr.attr,
#endif
+ &node_state_attr[N_CPU].attr.attr,
NULL
};

--
1.7.4.4

2012-10-29 15:48:28

by Lai Jiangshan

[permalink] [raw]

Subject: [V5 PATCH 20/26] memory_hotplug: allow online/offline memory to result movable node

Now, memory management can handle movable node or nodes which don't have
any normal memory, so we can dynamic configure and add movable node by:
online a ZONE_MOVABLE memory from a previous offline node
offline the last normal memory which result a non-normal-memory-node

movable-node is very important for power-saving,
hardware partitioning and high-available-system(hardware fault management).

Signed-off-by: Lai Jiangshan <[email protected]>
---
mm/memory_hotplug.c | 16 ++++++++++++++++
1 files changed, 16 insertions(+), 0 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a55b547..756744c 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -589,11 +589,19 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
return 0;
}

+#ifdef CONFIG_MOVABLE_NODE
+/* when CONFIG_MOVABLE_NODE, we allow online node don't have normal memory */
+static bool can_online_high_movable(struct zone *zone)
+{
+ return true;
+}
+#else /* #ifdef CONFIG_MOVABLE_NODE */
/* ensure every online node has NORMAL memory */
static bool can_online_high_movable(struct zone *zone)
{
return node_state(zone_to_nid(zone), N_NORMAL_MEMORY);
}
+#endif /* #ifdef CONFIG_MOVABLE_NODE */

/* check which state of node_states will be changed when online memory */
static void node_states_check_changes_online(unsigned long nr_pages,
@@ -1097,6 +1105,13 @@ check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
return offlined;
}

+#ifdef CONFIG_MOVABLE_NODE
+/* when CONFIG_MOVABLE_NODE, we allow online node don't have normal memory */
+static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
+{
+ return true;
+}
+#else /* #ifdef CONFIG_MOVABLE_NODE */
/* ensure the node has NORMAL memory if it is still online */
static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
{
@@ -1120,6 +1135,7 @@ static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
*/
return present_pages == 0;
}
+#endif /* #ifdef CONFIG_MOVABLE_NODE */

/* check which state of node_states will be changed when offline memory */
static void node_states_check_changes_offline(unsigned long nr_pages,
--
1.7.4.4

2012-10-29 15:49:44

by Lai Jiangshan

[permalink] [raw]

Subject: [V5 PATCH 19/26] numa: add CONFIG_MOVABLE_NODE for movable-dedicated node

All are prepared, we can actually introduce N_MEMORY.
add CONFIG_MOVABLE_NODE make we can use it for movable-dedicated node

Signed-off-by: Lai Jiangshan <[email protected]>
---
drivers/base/node.c | 6 ++++++
include/linux/nodemask.h | 4 ++++
mm/Kconfig | 8 ++++++++
mm/page_alloc.c | 3 +++
4 files changed, 21 insertions(+), 0 deletions(-)

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 4c3aa7c..9cdd66f 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -620,6 +620,9 @@ static struct node_attr node_state_attr[] = {
#ifdef CONFIG_HIGHMEM
[N_HIGH_MEMORY] = _NODE_ATTR(has_high_memory, N_HIGH_MEMORY),
#endif
+#ifdef CONFIG_MOVABLE_NODE
+ [N_MEMORY] = _NODE_ATTR(has_memory, N_MEMORY),
+#endif
[N_CPU] = _NODE_ATTR(has_cpu, N_CPU),
};

@@ -630,6 +633,9 @@ static struct attribute *node_state_attrs[] = {
#ifdef CONFIG_HIGHMEM
&node_state_attr[N_HIGH_MEMORY].attr.attr,
#endif
+#ifdef CONFIG_MOVABLE_NODE
+ &node_state_attr[N_MEMORY].attr.attr,
+#endif
&node_state_attr[N_CPU].attr.attr,
NULL
};
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index c6ebdc9..4e2cbfa 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -380,7 +380,11 @@ enum node_states {
#else
N_HIGH_MEMORY = N_NORMAL_MEMORY,
#endif
+#ifdef CONFIG_MOVABLE_NODE
+ N_MEMORY, /* The node has memory(regular, high, movable) */
+#else
N_MEMORY = N_HIGH_MEMORY,
+#endif
N_CPU, /* The node has one or more cpus */
NR_NODE_STATES
};
diff --git a/mm/Kconfig b/mm/Kconfig
index a3f8ddd..957ebd5 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -143,6 +143,14 @@ config NO_BOOTMEM
config MEMORY_ISOLATION
boolean

+config MOVABLE_NODE
+ boolean "Enable to assign a node has only movable memory"
+ depends on HAVE_MEMBLOCK
+ depends on NO_BOOTMEM
+ depends on X86_64
+ depends on NUMA
+ default y
+
# eventually, we can have this option just 'select SPARSEMEM'
config MEMORY_HOTPLUG
bool "Allow for memory hot-add"
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b70c929..a42337f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -90,6 +90,9 @@ nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
#ifdef CONFIG_HIGHMEM
[N_HIGH_MEMORY] = { { [0] = 1UL } },
#endif
+#ifdef CONFIG_MOVABLE_NODE
+ [N_MEMORY] = { { [0] = 1UL } },
+#endif
[N_CPU] = { { [0] = 1UL } },
#endif /* NUMA */
};
--
1.7.4.4

2012-10-29 15:49:42

by Lai Jiangshan

[permalink] [raw]

Subject: [V5 PATCH 08/26] memcontrol: use N_MEMORY instead N_HIGH_MEMORY

2012-10-29 15:48:25

by Lai Jiangshan

[permalink] [raw]

2012-10-29 15:51:17

by Lai Jiangshan

[permalink] [raw]

2012-10-29 15:48:20

by Lai Jiangshan

[permalink] [raw]

Subject: [V5 PATCH 05/26] node_states: introduce N_MEMORY

We have N_NORMAL_MEMORY for standing for the nodes that have normal memory with
zone_type <= ZONE_NORMAL.

And we have N_HIGH_MEMORY for standing for the nodes that have normal or high
memory.

But we don't have any word to stand for the nodes that have *any* memory.

And we have N_CPU but without N_MEMORY.

Current code reuse the N_HIGH_MEMORY for this purpose because any node which
has memory must have high memory or normal memory currently.

A) But this reusing is bad for *readability*. Because the name
N_HIGH_MEMORY just stands for high or normal:

A.example 1)
mem_cgroup_nr_lru_pages():
for_each_node_state(nid, N_HIGH_MEMORY)

The user will be confused(why this function just counts for high or
normal memory node? does it counts for ZONE_MOVABLE's lru pages?)
until someone else tell them N_HIGH_MEMORY is reused to stand for
nodes that have any memory.

A.cont) If we introduce N_MEMORY, we can reduce this confusing
AND make the code more clearly:

A.example 2) mm/page_cgroup.c use N_HIGH_MEMORY twice:

One is in page_cgroup_init(void):
for_each_node_state(nid, N_HIGH_MEMORY) {

It means if the node have memory, we will allocate page_cgroup map for
the node. We should use N_MEMORY instead here to gaim more clearly.

The second using is in alloc_page_cgroup():
if (node_state(nid, N_HIGH_MEMORY))
addr = vzalloc_node(size, nid);

It means if the node has high or normal memory that can be allocated
from kernel. We should keep N_HIGH_MEMORY here, and it will be better
if the "any memory" semantic of N_HIGH_MEMORY is removed.

B) This reusing is out-dated if we introduce MOVABLE-dedicated node.
The MOVABLE-dedicated node should not appear in
node_stats[N_HIGH_MEMORY] nor node_stats[N_NORMAL_MEMORY],
because MOVABLE-dedicated node has no high or normal memory.

In x86_64, N_HIGH_MEMORY=N_NORMAL_MEMORY, if a MOVABLE-dedicated node
is in node_stats[N_HIGH_MEMORY], it is also means it is in
node_stats[N_NORMAL_MEMORY], it causes SLUB wrong.

The slub uses
for_each_node_state(nid, N_NORMAL_MEMORY)
and creates kmem_cache_node for MOVABLE-dedicated node and cause problem.

In one word, we need a N_MEMORY. We just intrude it as an alias to
N_HIGH_MEMORY and fix all im-proper usages of N_HIGH_MEMORY in late patches.

Signed-off-by: Lai Jiangshan <[email protected]>
Acked-by: Christoph Lameter <[email protected]>
Acked-by: Hillf Danton <[email protected]>
---
include/linux/nodemask.h | 1 +
1 files changed, 1 insertions(+), 0 deletions(-)

diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 7afc363..c6ebdc9 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -380,6 +380,7 @@ enum node_states {
#else
N_HIGH_MEMORY = N_NORMAL_MEMORY,
#endif
+ N_MEMORY = N_HIGH_MEMORY,
N_CPU, /* The node has one or more cpus */
NR_NODE_STATES
};
--
1.7.4.4

2012-10-29 15:52:34

by Lai Jiangshan

[permalink] [raw]

Subject: [V5 PATCH 22/26] x86: get pg_data_t's memory from other node

From: Yasuaki Ishimatsu <[email protected]>

If system can create movable node which all memory of the
node is allocated as ZONE_MOVABLE, setup_node_data() cannot
allocate memory for the node's pg_data_t.
So when memblock_alloc_nid() fails, setup_node_data() retries
memblock_alloc().

Signed-off-by: Yasuaki Ishimatsu <[email protected]>
Signed-off-by: Lai Jiangshan <[email protected]>
---
arch/x86/mm/numa.c | 8 ++++++--
1 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 2d125be..a86e315 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -223,9 +223,13 @@ static void __init setup_node_data(int nid, u64 start, u64 end)
remapped = true;
} else {
nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid);
- if (!nd_pa) {
- pr_err("Cannot find %zu bytes in node %d\n",
+ if (!nd_pa)
+ printk(KERN_WARNING "Cannot find %zu bytes in node %d\n",
nd_size, nid);
+ nd_pa = memblock_alloc(nd_size, SMP_CACHE_BYTES);
+ if (!nd_pa) {
+ pr_err("Cannot find %zu bytes in other node\n",
+ nd_size);
return;
}
nd = __va(nd_pa);
--
1.7.4.4

2012-10-29 15:52:31

by Lai Jiangshan

[permalink] [raw]

Subject: [V5 PATCH 25/26] memblock: compare current_limit with end variable at memblock_find_in_range_node()

From: Yasuaki Ishimatsu <[email protected]>

memblock_find_in_range_node() does not compare memblock.current_limit
with end variable. Thus even if memblock.current_limit is smaller than
end variable, the function allocates memory address that is bigger than
memblock.current_limit.

The patch adds the check to "memblock_find_in_range_node()"

Signed-off-by: Yasuaki Ishimatsu <[email protected]>
Signed-off-by: Lai Jiangshan <[email protected]>
---
mm/memblock.c | 5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/mm/memblock.c b/mm/memblock.c
index ee2e307..50ab53c 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -100,11 +100,12 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start,
phys_addr_t align, int nid)
{
phys_addr_t this_start, this_end, cand;
+ phys_addr_t current_limit = memblock.current_limit;
u64 i;

/* pump up @end */
- if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
- end = memblock.current_limit;
+ if ((end == MEMBLOCK_ALLOC_ACCESSIBLE) || (end > current_limit))
+ end = current_limit;

/* avoid allocating the first page */
start = max_t(phys_addr_t, start, PAGE_SIZE);
--
1.7.4.4

2012-10-29 15:53:32

by Lai Jiangshan

[permalink] [raw]

Subject: [V5 PATCH 10/26] mm,migrate: use N_MEMORY instead N_HIGH_MEMORY

2012-10-29 15:53:49

by Lai Jiangshan

[permalink] [raw]

2012-10-29 16:03:24

by Lai Jiangshan

[permalink] [raw]

Subject: [V5 PATCH 21/26] page_alloc: add kernelcore_max_addr

Current ZONE_MOVABLE (kernelcore=) setting policy with boot option doesn't meet
our requirement. We need something like kernelcore_max_addr=XX boot option
to limit the kernelcore upper address.

The memory with higher address will be migratable(movable) and they
are easier to be offline(always ready to be offline when the system don't require
so much memory).

It makes things easy when we dynamic hot-add/remove memory, make better
utilities of memories, and helps for THP.

All kernelcore_max_addr=, kernelcore= and movablecore= can be safely specified
at the same time(or any 2 of them).

Signed-off-by: Lai Jiangshan <[email protected]>
---
Documentation/kernel-parameters.txt | 9 +++++++++
mm/page_alloc.c | 29 ++++++++++++++++++++++++++++-
2 files changed, 37 insertions(+), 1 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 9776f06..2b72ffb 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1223,6 +1223,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
use the HighMem zone if it exists, and the Normal
zone if it does not.

+ kernelcore_max_addr=nn[KMG] [KNL,X86,IA-64,PPC] This parameter
+ is the same effect as kernelcore parameter, except it
+ specifies the up physical address of memory range
+ usable by the kernel for non-movable allocations.
+ If both kernelcore and kernelcore_max_addr are
+ specified, this requested's priority is higher than
+ kernelcore's.
+ See the kernelcore parameter.
+
kgdbdbgp= [KGDB,HW] kgdb over EHCI usb debug port.
Format: <Controller#>[,poll interval]
The controller # is the number of the ehci usb debug
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a42337f..11df8b5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -203,6 +203,7 @@ static unsigned long __meminitdata dma_reserve;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
+static unsigned long __initdata required_kernelcore_max_pfn;
static unsigned long __initdata required_kernelcore;
static unsigned long __initdata required_movablecore;
static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
@@ -4700,6 +4701,7 @@ static void __init find_zone_movable_pfns_for_nodes(void)
{
int i, nid;
unsigned long usable_startpfn;
+ unsigned long kernelcore_max_pfn;
unsigned long kernelcore_node, kernelcore_remaining;
/* save the state before borrow the nodemask */
nodemask_t saved_node_state = node_states[N_MEMORY];
@@ -4728,6 +4730,9 @@ static void __init find_zone_movable_pfns_for_nodes(void)
required_kernelcore = max(required_kernelcore, corepages);
}

+ if (required_kernelcore_max_pfn && !required_kernelcore)
+ required_kernelcore = totalpages;
+
/* If kernelcore was not specified, there is no ZONE_MOVABLE */
if (!required_kernelcore)
goto out;
@@ -4736,6 +4741,12 @@ static void __init find_zone_movable_pfns_for_nodes(void)
find_usable_zone_for_movable();
usable_startpfn = arch_zone_lowest_possible_pfn[movable_zone];

+ if (required_kernelcore_max_pfn)
+ kernelcore_max_pfn = required_kernelcore_max_pfn;
+ else
+ kernelcore_max_pfn = ULONG_MAX >> PAGE_SHIFT;
+ kernelcore_max_pfn = max(kernelcore_max_pfn, usable_startpfn);
+
restart:
/* Spread kernelcore memory as evenly as possible throughout nodes */
kernelcore_node = required_kernelcore / usable_nodes;
@@ -4762,8 +4773,12 @@ restart:
unsigned long size_pages;

start_pfn = max(start_pfn, zone_movable_pfn[nid]);
- if (start_pfn >= end_pfn)
+ end_pfn = min(kernelcore_max_pfn, end_pfn);
+ if (start_pfn >= end_pfn) {
+ if (!zone_movable_pfn[nid])
+ zone_movable_pfn[nid] = start_pfn;
continue;
+ }

/* Account for what is only usable for kernelcore */
if (start_pfn < usable_startpfn) {
@@ -4954,6 +4969,18 @@ static int __init cmdline_parse_core(char *p, unsigned long *core)
return 0;
}

+#ifdef CONFIG_MOVABLE_NODE
+/*
+ * kernelcore_max_addr=addr sets the up physical address of memory range
+ * for use for allocations that cannot be reclaimed or migrated.
+ */
+static int __init cmdline_parse_kernelcore_max_addr(char *p)
+{
+ return cmdline_parse_core(p, &required_kernelcore_max_pfn);
+}
+early_param("kernelcore_max_addr", cmdline_parse_kernelcore_max_addr);
+#endif
+
/*
* kernelcore=size sets the amount of memory for use for allocations that
* cannot be reclaimed or migrated.
--
1.7.4.4

2012-10-29 16:03:18

by Lai Jiangshan

[permalink] [raw]

On Wed 31-10-12 15:03:36, Wen Congyang wrote:
> At 10/30/2012 04:46 AM, David Rientjes Wrote:
> > On Mon, 29 Oct 2012, Lai Jiangshan wrote:
[...]
> >> In one word, we need a N_MEMORY. We just intrude it as an alias to
> >> N_HIGH_MEMORY and fix all im-proper usages of N_HIGH_MEMORY in late patches.
> >>
> >
> > If this is really that problematic (and it appears it's not given that
> > there are many use cases of it and people tend to get it right), then why
> > not simply rename N_HIGH_MEMORY instead of introducing yet another
> > nodemask to the equation?
>
> The reason is that we need a node which only contains movable memory. This
> feature is very important for node hotplug. So we will add a new nodemask
> for movable memory. N_MEMORY contains movable memory but N_HIGH_MEMORY
> doesn't contain it.

OK, so the N_MOVABLE_MEMORY (or how you will call it) requires that all
the allocations will be migrateable?
How do you want to achieve that with the page_cgroup descriptors? (see
bellow)

On Mon 29-10-12 23:20:58, Lai Jiangshan wrote:
[...]
> diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
> index 5ddad0c..c1054ad 100644
> --- a/mm/page_cgroup.c
> +++ b/mm/page_cgroup.c
> @@ -271,7 +271,7 @@ void __init page_cgroup_init(void)
> if (mem_cgroup_disabled())
> return;
>
> - for_each_node_state(nid, N_HIGH_MEMORY) {
> + for_each_node_state(nid, N_MEMORY) {
> unsigned long start_pfn, end_pfn;
>
> start_pfn = node_start_pfn(nid);

This will call init_section_page_cgroup(pfn, nid) later which allocates
page_cgroup descriptors which are not movable. Or is there any code in
your patchset that handles this?
--
Michal Hocko
SUSE Labs