From c98940f6fa3d06fa8fec75aa2362b25227573d06 Mon Sep 17 00:00:00 2001 From: Yaowei Bai Date: Thu, 19 May 2016 17:11:26 -0700 Subject: mm/memory_hotplug: is_mem_section_removable() can return bool Make is_mem_section_removable() return bool to improve readability due to this particular function only using either one or zero as its return value. Signed-off-by: Yaowei Bai Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index aa34431c3f31..b21d8895ea41 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1410,7 +1410,7 @@ static struct page *next_active_pageblock(struct page *page) } /* 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) +bool is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) { struct page *page = pfn_to_page(start_pfn); struct page *end_page = page + nr_pages; @@ -1418,12 +1418,12 @@ int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages) /* Check the starting page of each pageblock within the range */ for (; page < end_page; page = next_active_pageblock(page)) { if (!is_pageblock_removable_nolock(page)) - return 0; + return false; cond_resched(); } /* All pageblocks in the memory block are likely to be hot-removable */ - return 1; + return true; } /* -- cgit v1.3-8-gc7d7 From 8604d9e534a3e662600e288bcfd1a5acd2763d28 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Thu, 19 May 2016 17:13:03 -0700 Subject: memory_hotplug: introduce CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE This patchset continues the work I started with commit 31bc3858ea3e ("memory-hotplug: add automatic onlining policy for the newly added memory"). Initially I was going to stop there and bring the policy setting logic to userspace. I met two issues on this way: 1) It is possible to have memory hotplugged at boot (e.g. with QEMU). These blocks stay offlined if we turn the onlining policy on by userspace. 2) My attempt to bring this policy setting to systemd failed, systemd maintainers suggest to change the default in kernel or ... to use tmpfiles.d to alter the policy (which looks like a hack to me): https://github.com/systemd/systemd/pull/2938 Here I suggest to add a config option to set the default value for the policy and a kernel command line parameter to make the override. This patch (of 2): Introduce config option to set the default value for memory hotplug onlining policy (/sys/devices/system/memory/auto_online_blocks). The reason one would want to turn this option on are to have early onlining for hotpluggable memory available at boot and to not require any userspace actions to make memory hotplug work. [akpm@linux-foundation.org: tweak Kconfig text] Signed-off-by: Vitaly Kuznetsov Cc: Jonathan Corbet Cc: Dan Williams Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: David Vrabel Cc: David Rientjes Cc: Igor Mammedov Cc: Lennart Poettering Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/memory-hotplug.txt | 9 +++++---- mm/Kconfig | 16 ++++++++++++++++ mm/memory_hotplug.c | 4 ++++ 3 files changed, 25 insertions(+), 4 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt index 443f4b44ad97..0d7cb955aa01 100644 --- a/Documentation/memory-hotplug.txt +++ b/Documentation/memory-hotplug.txt @@ -261,10 +261,11 @@ it according to the policy which can be read from "auto_online_blocks" file: % cat /sys/devices/system/memory/auto_online_blocks -The default is "offline" which means the newly added memory is not in a -ready-to-use state and you have to "online" the newly added memory blocks -manually. Automatic onlining can be requested by writing "online" to -"auto_online_blocks" file: +The default depends on the CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config +option. If it is disabled the default is "offline" which means the newly added +memory is not in a ready-to-use state and you have to "online" the newly added +memory blocks manually. Automatic onlining can be requested by writing "online" +to "auto_online_blocks" file: % echo online > /sys/devices/system/memory/auto_online_blocks diff --git a/mm/Kconfig b/mm/Kconfig index d6e9042b99e0..b0432b71137d 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -192,6 +192,22 @@ config MEMORY_HOTPLUG_SPARSE def_bool y depends on SPARSEMEM && MEMORY_HOTPLUG +config MEMORY_HOTPLUG_DEFAULT_ONLINE + bool "Online the newly added memory blocks by default" + default n + depends on MEMORY_HOTPLUG + help + This option sets the default policy setting for memory hotplug + onlining policy (/sys/devices/system/memory/auto_online_blocks) which + determines what happens to newly added memory regions. Policy setting + can always be changed at runtime. + See Documentation/memory-hotplug.txt for more information. + + Say Y here if you want all hot-plugged memory blocks to appear in + 'online' state by default. + Say N here if you want the default policy to keep all hot-plugged + memory blocks in 'offline' state. + config MEMORY_HOTREMOVE bool "Allow for memory hot remove" select MEMORY_ISOLATION diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b21d8895ea41..fcafbfcff044 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -78,7 +78,11 @@ static struct { #define memhp_lock_acquire() lock_map_acquire(&mem_hotplug.dep_map) #define memhp_lock_release() lock_map_release(&mem_hotplug.dep_map) +#ifndef CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE bool memhp_auto_online; +#else +bool memhp_auto_online = true; +#endif EXPORT_SYMBOL_GPL(memhp_auto_online); void get_online_mems(void) -- cgit v1.3-8-gc7d7 From 86dd995d63241039e0ad9123f9b424013c611510 Mon Sep 17 00:00:00 2001 From: Vitaly Kuznetsov Date: Thu, 19 May 2016 17:13:06 -0700 Subject: memory_hotplug: introduce memhp_default_state= command line parameter CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE specifies the default value for the memory hotplug onlining policy. Add a command line parameter to make it possible to override the default. It may come handy for debug and testing purposes. Signed-off-by: Vitaly Kuznetsov Cc: Jonathan Corbet Cc: Dan Williams Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: David Vrabel Cc: David Rientjes Cc: Igor Mammedov Cc: Lennart Poettering Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/kernel-parameters.txt | 8 ++++++++ mm/memory_hotplug.c | 11 +++++++++++ 2 files changed, 19 insertions(+) (limited to 'mm/memory_hotplug.c') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 794403166a8f..2edb27bdc680 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -2161,6 +2161,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted. [KNL,SH] Allow user to override the default size for per-device physically contiguous DMA buffers. + memhp_default_state=online/offline + [KNL] Set the initial state for the memory hotplug + onlining policy. If not specified, the default value is + set according to the + CONFIG_MEMORY_HOTPLUG_DEFAULT_ONLINE kernel config + option. + See Documentation/memory-hotplug.txt. + memmap=exactmap [KNL,X86] Enable setting of an exact E820 memory map, as specified by the user. Such memmap=exactmap lines can be constructed based on diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fcafbfcff044..caf2a14c37ad 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -85,6 +85,17 @@ bool memhp_auto_online = true; #endif EXPORT_SYMBOL_GPL(memhp_auto_online); +static int __init setup_memhp_default_state(char *str) +{ + if (!strcmp(str, "online")) + memhp_auto_online = true; + else if (!strcmp(str, "offline")) + memhp_auto_online = false; + + return 1; +} +__setup("memhp_default_state=", setup_memhp_default_state); + void get_online_mems(void) { might_sleep(); -- cgit v1.3-8-gc7d7 From f65e91df25aa426289cbcb580ca3183e24979fb1 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 27 May 2016 14:27:32 -0700 Subject: mm: use early_pfn_to_nid in register_page_bootmem_info_node register_page_bootmem_info_node() is invoked in mem_init(), so it will be called before page_alloc_init_late() if DEFERRED_STRUCT_PAGE_INIT is enabled. But, pfn_to_nid() depends on memmap which won't be fully setup until page_alloc_init_late() is done, so replace pfn_to_nid() by early_pfn_to_nid(). Link: http://lkml.kernel.org/r/1464210007-30930-1-git-send-email-yang.shi@linaro.org Signed-off-by: Yang Shi Cc: Mel Gorman Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/memory_hotplug.c') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index caf2a14c37ad..b8ee0806415f 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -300,7 +300,7 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat) * multiple nodes we check that this pfn does not already * reside in some other nodes. */ - if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node)) + if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node)) register_page_bootmem_info_section(pfn); } } -- cgit v1.3-8-gc7d7 From 7ded384a12688c2a86b618da16bc87713404dfcc Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 27 May 2016 15:23:32 -0700 Subject: mm: fix section mismatch warning The register_page_bootmem_info_node() function needs to be marked __init in order to avoid a new warning introduced by commit f65e91df25aa ("mm: use early_pfn_to_nid in register_page_bootmem_info_node"). Otherwise you'll get a warning about how a non-init function calls early_pfn_to_nid (which is __meminit) Cc: Yang Shi Cc: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memory_hotplug.h | 2 +- mm/memory_hotplug.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 20d8a5d4d133..5145620ba48a 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -182,7 +182,7 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat) #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */ #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE -extern void register_page_bootmem_info_node(struct pglist_data *pgdat); +extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat); #else static inline void register_page_bootmem_info_node(struct pglist_data *pgdat) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b8ee0806415f..e3cbdcaff2a5 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -263,7 +263,7 @@ static void register_page_bootmem_info_section(unsigned long start_pfn) } #endif /* !CONFIG_SPARSEMEM_VMEMMAP */ -void register_page_bootmem_info_node(struct pglist_data *pgdat) +void __init register_page_bootmem_info_node(struct pglist_data *pgdat) { unsigned long i, pfn, end_pfn, nr_pages; int node = pgdat->node_id; -- cgit v1.3-8-gc7d7