From 7b78d335ac15b10bbcb0397c635d7f0d569b0270 Mon Sep 17 00:00:00 2001 From: Yasunori Goto Date: Sun, 21 Oct 2007 16:41:36 -0700 Subject: memory hotplug: rearrange memory hotplug notifier Current memory notifier has some defects yet. (Fortunately, nothing uses it.) This patch is to fix and rearrange for them. - Add information of start_pfn, nr_pages, and node id if node status is changes from/to memoryless node for callback functions. Callbacks can't do anything without those information. - Add notification going-online status. It is necessary for creating per node structure before the node's pages are available. - Move GOING_OFFLINE status notification after page isolation. It is good place for return memory like cache for callback, because returned page is not used again. - Make CANCEL events for rollingback when error occurs. - Delete MEM_MAPPING_INVALID notification. It will be not used. - Fix compile error of (un)register_memory_notifier(). Signed-off-by: Yasunori Goto Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 48 +++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 45 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 1833879..3a47871 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -187,7 +187,24 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) unsigned long onlined_pages = 0; struct zone *zone; int need_zonelists_rebuild = 0; + int nid; + int ret; + struct memory_notify arg; + + arg.start_pfn = pfn; + arg.nr_pages = nr_pages; + arg.status_change_nid = -1; + + nid = page_to_nid(pfn_to_page(pfn)); + if (node_present_pages(nid) == 0) + arg.status_change_nid = nid; + ret = memory_notify(MEM_GOING_ONLINE, &arg); + ret = notifier_to_errno(ret); + if (ret) { + memory_notify(MEM_CANCEL_ONLINE, &arg); + return ret; + } /* * This doesn't need a lock to do pfn_to_page(). * The section can't be removed here because of the @@ -222,6 +239,10 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) build_all_zonelists(); vm_total_pages = nr_free_pagecache_pages(); writeback_set_ratelimit(); + + if (onlined_pages) + memory_notify(MEM_ONLINE, &arg); + return 0; } #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ @@ -467,8 +488,9 @@ int offline_pages(unsigned long start_pfn, { unsigned long pfn, nr_pages, expire; long offlined_pages; - int ret, drain, retry_max; + int ret, drain, retry_max, node; struct zone *zone; + struct memory_notify arg; BUG_ON(start_pfn >= end_pfn); /* at least, alignment against pageblock is necessary */ @@ -480,11 +502,27 @@ int offline_pages(unsigned long start_pfn, we assume this for now. .*/ if (!test_pages_in_a_zone(start_pfn, end_pfn)) return -EINVAL; + + zone = page_zone(pfn_to_page(start_pfn)); + node = zone_to_nid(zone); + nr_pages = end_pfn - start_pfn; + /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn); if (ret) return ret; - nr_pages = end_pfn - start_pfn; + + arg.start_pfn = start_pfn; + arg.nr_pages = nr_pages; + arg.status_change_nid = -1; + if (nr_pages >= node_present_pages(node)) + arg.status_change_nid = node; + + ret = memory_notify(MEM_GOING_OFFLINE, &arg); + ret = notifier_to_errno(ret); + if (ret) + goto failed_removal; + pfn = start_pfn; expire = jiffies + timeout; drain = 0; @@ -539,20 +577,24 @@ repeat: /* reset pagetype flags */ start_isolate_page_range(start_pfn, end_pfn); /* removal success */ - zone = page_zone(pfn_to_page(start_pfn)); zone->present_pages -= offlined_pages; zone->zone_pgdat->node_present_pages -= offlined_pages; totalram_pages -= offlined_pages; num_physpages -= offlined_pages; + vm_total_pages = nr_free_pagecache_pages(); writeback_set_ratelimit(); + + memory_notify(MEM_OFFLINE, &arg); return 0; failed_removal: printk(KERN_INFO "memory offlining %lx to %lx failed\n", start_pfn, end_pfn); + memory_notify(MEM_CANCEL_OFFLINE, &arg); /* pushback to free area */ undo_isolate_page_range(start_pfn, end_pfn); + return ret; } #else -- cgit v1.1