[PATCH] Add sysfs removable attribute for hotplug memory remove
From: Badari Pulavarty
Date: Fri May 02 2008 - 12:56:20 EST
Hi Andrew,
Here is the updated/commented version of the sysfs "removability"
attribute patch for hotplug memory remove (against 2.6.25-git18).
Could you please consider this for inclusion ?
Thanks,
Badari
Memory may be hot-removed on a per-memory-block basis, particularly on POWER
where the SPARSEMEM section size often matches the memory-block size. A
user-level agent must be able to identify which sections of memory are likely
to be removable before attempting the potentially expensive operation. This
patch adds a file called "removable" to the memory directory in sysfs to
help such an agent. In this patch, a memory block is considered removable if;
o It contains only MOVABLE pageblocks
o It contains only pageblocks with free pages regardless of pageblock type
On the other hand, a memory block starting with a PageReserved() page will
never be considered removable. Without this patch, the user-agent is
forced to choose a memory block to remove randomly.
Sample output of the sysfs files:
./memory/memory0/removable: 0
./memory/memory1/removable: 0
./memory/memory2/removable: 0
./memory/memory3/removable: 0
./memory/memory4/removable: 0
./memory/memory5/removable: 0
./memory/memory6/removable: 0
./memory/memory7/removable: 1
./memory/memory8/removable: 0
./memory/memory9/removable: 0
./memory/memory10/removable: 0
./memory/memory11/removable: 0
./memory/memory12/removable: 0
./memory/memory13/removable: 0
./memory/memory14/removable: 0
./memory/memory15/removable: 0
./memory/memory16/removable: 0
./memory/memory17/removable: 1
./memory/memory18/removable: 1
./memory/memory19/removable: 1
./memory/memory20/removable: 1
./memory/memory21/removable: 1
./memory/memory22/removable: 1
Signed-off-by: Badari Pulavarty <pbadari@xxxxxxxxxx>
Signed-off-by: Mel Gorman <mel@xxxxxxxxx>
Acked-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
drivers/base/memory.c | 19 +++++++++++++
include/linux/memory_hotplug.h | 12 ++++++++
mm/memory_hotplug.c | 58 +++++++++++++++++++++++++++++++++++++++++
3 files changed, 89 insertions(+)
Index: linux-2.6.25/drivers/base/memory.c
===================================================================
--- linux-2.6.25.orig/drivers/base/memory.c 2008-05-02 07:53:06.000000000 -0700
+++ linux-2.6.25/drivers/base/memory.c 2008-05-02 07:53:39.000000000 -0700
@@ -98,6 +98,21 @@ static ssize_t show_mem_phys_index(struc
}
/*
+ * Show whether the section of memory is likely to be hot-removable
+ */
+static ssize_t show_mem_removable(struct sys_device *dev, char *buf)
+{
+ unsigned long start_pfn;
+ int ret;
+ struct memory_block *mem =
+ container_of(dev, struct memory_block, sysdev);
+
+ start_pfn = section_nr_to_pfn(mem->phys_index);
+ ret = is_mem_section_removable(start_pfn, PAGES_PER_SECTION);
+ return sprintf(buf, "%d\n", ret);
+}
+
+/*
* online, offline, going offline, etc.
*/
static ssize_t show_mem_state(struct sys_device *dev, char *buf)
@@ -256,6 +271,7 @@ static ssize_t show_phys_device(struct s
static SYSDEV_ATTR(phys_index, 0444, show_mem_phys_index, NULL);
static SYSDEV_ATTR(state, 0644, show_mem_state, store_mem_state);
static SYSDEV_ATTR(phys_device, 0444, show_phys_device, NULL);
+static SYSDEV_ATTR(removable, 0444, show_mem_removable, NULL);
#define mem_create_simple_file(mem, attr_name) \
sysdev_create_file(&mem->sysdev, &attr_##attr_name)
@@ -344,6 +360,8 @@ static int add_memory_block(unsigned lon
ret = mem_create_simple_file(mem, state);
if (!ret)
ret = mem_create_simple_file(mem, phys_device);
+ if (!ret)
+ ret = mem_create_simple_file(mem, removable);
return ret;
}
@@ -388,6 +406,7 @@ int remove_memory_block(unsigned long no
mem_remove_simple_file(mem, phys_index);
mem_remove_simple_file(mem, state);
mem_remove_simple_file(mem, phys_device);
+ mem_remove_simple_file(mem, removable);
unregister_memory(mem, section);
return 0;
Index: linux-2.6.25/include/linux/memory_hotplug.h
===================================================================
--- linux-2.6.25.orig/include/linux/memory_hotplug.h 2008-05-02 07:53:13.000000000 -0700
+++ linux-2.6.25/include/linux/memory_hotplug.h 2008-05-02 07:53:39.000000000 -0700
@@ -199,6 +199,18 @@ static inline void register_page_bootmem
#endif /* ! CONFIG_MEMORY_HOTPLUG */
+#ifdef CONFIG_MEMORY_HOTREMOVE
+
+extern int is_mem_section_removable(unsigned long pfn, unsigned long nr_pages);
+
+#else
+static inline int is_mem_section_removable(unsigned long pfn,
+ unsigned long nr_pages)
+{
+ return 0;
+}
+#endif /* CONFIG_MEMORY_HOTREMOVE */
+
extern int add_memory(int nid, u64 start, u64 size);
extern int arch_add_memory(int nid, u64 start, u64 size);
extern int remove_memory(u64 start, u64 size);
Index: linux-2.6.25/mm/memory_hotplug.c
===================================================================
--- linux-2.6.25.orig/mm/memory_hotplug.c 2008-05-02 07:53:13.000000000 -0700
+++ linux-2.6.25/mm/memory_hotplug.c 2008-05-02 07:54:31.000000000 -0700
@@ -513,6 +513,64 @@ EXPORT_SYMBOL_GPL(add_memory);
#ifdef CONFIG_MEMORY_HOTREMOVE
/*
+ * A free page on the buddy free lists (not the per-cpu lists) has PageBuddy
+ * set and the size of the free page is given by page_order(). Using this,
+ * the function determines if the pageblock contains only free pages.
+ * Due to buddy contraints, a free page at least the size of a pageblock will
+ * be located at the start of the pageblock
+ */
+static inline int pageblock_free(struct page *page)
+{
+ return PageBuddy(page) && page_order(page) >= pageblock_order;
+}
+
+/* Return the start of the next active pageblock after a given page */
+static struct page *next_active_pageblock(struct page *page)
+{
+ /* Ensure the starting page is pageblock-aligned */
+ BUG_ON(page_to_pfn(page) & (pageblock_nr_pages - 1));
+
+ /* Move forward by at least 1 * pageblock_nr_pages */
+ int pageblocks_stride = 1;
+
+ /* If the entire pageblock is free, move to the end of free page */
+ if (pageblock_free(page))
+ pageblocks_stride += page_order(page) - pageblock_order;
+
+ return page + (pageblocks_stride * pageblock_nr_pages);
+}
+
+/* Checks if this range of memory is likely to be hot-removable. */
+int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
+{
+ int type;
+ struct page *page = pfn_to_page(start_pfn);
+ struct page *end_page = page + nr_pages;
+
+ /* Check the starting page of each pageblock within the range */
+ for (; page < end_page; page = next_active_pageblock(page)) {
+ type = get_pageblock_migratetype(page);
+
+ /*
+ * A pageblock containing MOVABLE or free pages is considered
+ * removable
+ */
+ if (type != MIGRATE_MOVABLE && !pageblock_free(page))
+ return 0;
+
+ /*
+ * A pageblock starting with a PageReserved page is not
+ * considered removable.
+ */
+ if (PageReserved(page))
+ return 0;
+ }
+
+ /* All pageblocks in the memory block are likely to be hot-removable */
+ return 1;
+}
+
+/*
* Confirm all pages in a range [start, end) is belongs to the same zone.
*/
static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/