From 3ecc68349bbab6bff1d12cbc7951ca6019b2faf6 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 5 Nov 2021 13:43:19 -0700 Subject: memblock: rename memblock_free to memblock_phys_free Since memblock_free() operates on a physical range, make its name reflect it and rename it to memblock_phys_free(), so it will be a logical counterpart to memblock_phys_alloc(). The callers are updated with the below semantic patch: @@ expression addr; expression size; @@ - memblock_free(addr, size); + memblock_phys_free(addr, size); Link: https://lkml.kernel.org/r/20210930185031.18648-6-rppt@kernel.org Signed-off-by: Mike Rapoport Cc: Christophe Leroy Cc: Juergen Gross Cc: Shahab Vahedi 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 9fd0be32a281..feffaa9423fe 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -2204,7 +2204,7 @@ static int __ref try_remove_memory(u64 start, u64 size) arch_remove_memory(start, size, altmap); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { - memblock_free(start, size); + memblock_phys_free(start, size); memblock_remove(start, size); } -- cgit v1.2.3 From ac62554ba7060c8824d7821c1342673f1e13c31d Mon Sep 17 00:00:00 2001 From: Tang Yizhou Date: Fri, 5 Nov 2021 13:44:08 -0700 Subject: mm/memory_hotplug: add static qualifier for online_policy_to_str() online_policy_to_str is only used in memory_hotplug.c and should be defined as static. Link: https://lkml.kernel.org/r/20210913024534.26161-1-tangyizhou@huawei.com Signed-off-by: Tang Yizhou Reviewed-by: Muchun Song Reviewed-by: David Hildenbrand 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 feffaa9423fe..afaae370b8cd 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -57,7 +57,7 @@ enum { ONLINE_POLICY_AUTO_MOVABLE, }; -const char *online_policy_to_str[] = { +static const char * const online_policy_to_str[] = { [ONLINE_POLICY_CONTIG_ZONES] = "contig-zones", [ONLINE_POLICY_AUTO_MOVABLE] = "auto-movable", }; -- cgit v1.2.3 From 50f9481ed9fb8a2d2a06a155634c7f9eeff9fa61 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:24 -0700 Subject: mm/memory_hotplug: remove CONFIG_MEMORY_HOTPLUG_SPARSE CONFIG_MEMORY_HOTPLUG depends on CONFIG_SPARSEMEM, so there is no need for CONFIG_MEMORY_HOTPLUG_SPARSE anymore; adjust all instances to use CONFIG_MEMORY_HOTPLUG and remove CONFIG_MEMORY_HOTPLUG_SPARSE. Link: https://lkml.kernel.org/r/20210929143600.49379-3-david@redhat.com Signed-off-by: David Hildenbrand Acked-by: Shuah Khan [kselftest] Acked-by: Greg Kroah-Hartman Acked-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/include/asm/machdep.h | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/powerpc/platforms/powernv/setup.c | 4 ++-- arch/powerpc/platforms/pseries/setup.c | 2 +- drivers/base/Makefile | 2 +- drivers/base/node.c | 9 ++++----- drivers/virtio/Kconfig | 2 +- include/linux/memory.h | 24 ++++++++++-------------- include/linux/node.h | 4 ++-- lib/Kconfig.debug | 2 +- mm/Kconfig | 4 ---- mm/memory_hotplug.c | 2 -- tools/testing/selftests/memory-hotplug/config | 1 - 13 files changed, 24 insertions(+), 36 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h index 764f2732a821..d8a2ca007082 100644 --- a/arch/powerpc/include/asm/machdep.h +++ b/arch/powerpc/include/asm/machdep.h @@ -32,7 +32,7 @@ struct machdep_calls { void (*iommu_save)(void); void (*iommu_restore)(void); #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG unsigned long (*memory_block_size)(void); #endif #endif /* CONFIG_PPC64 */ diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 1777e992b20b..6052f5d5ded3 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -912,7 +912,7 @@ void __init setup_per_cpu_areas(void) } #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG unsigned long memory_block_size_bytes(void) { if (ppc_md.memory_block_size) diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c index a8db3f153063..ad56a54ac9c5 100644 --- a/arch/powerpc/platforms/powernv/setup.c +++ b/arch/powerpc/platforms/powernv/setup.c @@ -440,7 +440,7 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary) } #endif /* CONFIG_KEXEC_CORE */ -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG static unsigned long pnv_memory_block_size(void) { /* @@ -553,7 +553,7 @@ define_machine(powernv) { #ifdef CONFIG_KEXEC_CORE .kexec_cpu_down = pnv_kexec_cpu_down, #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG .memory_block_size = pnv_memory_block_size, #endif }; diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index f79126f16258..d29f6f1f7f37 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -1089,7 +1089,7 @@ define_machine(pseries) { .machine_kexec = pSeries_machine_kexec, .kexec_cpu_down = pseries_kexec_cpu_down, #endif -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG .memory_block_size = pseries_memory_block_size, #endif }; diff --git a/drivers/base/Makefile b/drivers/base/Makefile index ef8e44a7d288..02f7f1358e86 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -13,7 +13,7 @@ obj-y += power/ obj-$(CONFIG_ISA_BUS_API) += isa.o obj-y += firmware_loader/ obj-$(CONFIG_NUMA) += node.o -obj-$(CONFIG_MEMORY_HOTPLUG_SPARSE) += memory.o +obj-$(CONFIG_MEMORY_HOTPLUG) += memory.o ifeq ($(CONFIG_SYSFS),y) obj-$(CONFIG_MODULES) += module.o endif diff --git a/drivers/base/node.c b/drivers/base/node.c index c56d34f8158f..b5a4ba18f9f9 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -629,7 +629,7 @@ static void node_device_release(struct device *dev) { struct node *node = to_node(dev); -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS) /* * We schedule the work only when a memory section is * onlined/offlined on this node. When we come here, @@ -782,7 +782,7 @@ int unregister_cpu_under_node(unsigned int cpu, unsigned int nid) return 0; } -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG static int __ref get_nid_for_pfn(unsigned long pfn) { #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT @@ -958,10 +958,9 @@ static int node_memory_callback(struct notifier_block *self, return NOTIFY_OK; } #endif /* CONFIG_HUGETLBFS */ -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ +#endif /* CONFIG_MEMORY_HOTPLUG */ -#if !defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || \ - !defined(CONFIG_HUGETLBFS) +#if !defined(CONFIG_MEMORY_HOTPLUG) || !defined(CONFIG_HUGETLBFS) static inline int node_memory_callback(struct notifier_block *self, unsigned long action, void *arg) { diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig index ce1b3f6ec325..3654def9915c 100644 --- a/drivers/virtio/Kconfig +++ b/drivers/virtio/Kconfig @@ -98,7 +98,7 @@ config VIRTIO_MEM default m depends on X86_64 depends on VIRTIO - depends on MEMORY_HOTPLUG_SPARSE + depends on MEMORY_HOTPLUG depends on MEMORY_HOTREMOVE depends on CONTIG_ALLOC help diff --git a/include/linux/memory.h b/include/linux/memory.h index 053a530c7bdd..0328ec039c38 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -110,7 +110,7 @@ struct mem_section; #define SLAB_CALLBACK_PRI 1 #define IPC_CALLBACK_PRI 10 -#ifndef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifndef CONFIG_MEMORY_HOTPLUG static inline void memory_dev_init(void) { return; @@ -126,7 +126,14 @@ static inline int memory_notify(unsigned long val, void *v) { return 0; } -#else +static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) +{ + return 0; +} +/* These aren't inline functions due to a GCC bug. */ +#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) +#define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) +#else /* CONFIG_MEMORY_HOTPLUG */ extern int register_memory_notifier(struct notifier_block *nb); extern void unregister_memory_notifier(struct notifier_block *nb); int create_memory_block_devices(unsigned long start, unsigned long size, @@ -148,9 +155,6 @@ struct memory_group *memory_group_find_by_id(int mgid); typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *); int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, struct memory_group *excluded, void *arg); -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ - -#ifdef CONFIG_MEMORY_HOTPLUG #define hotplug_memory_notifier(fn, pri) ({ \ static __meminitdata struct notifier_block fn##_mem_nb =\ { .notifier_call = fn, .priority = pri };\ @@ -158,15 +162,7 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, }) #define register_hotmemory_notifier(nb) register_memory_notifier(nb) #define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) -#else -static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri) -{ - return 0; -} -/* These aren't inline functions due to a GCC bug. */ -#define register_hotmemory_notifier(nb) ({ (void)(nb); 0; }) -#define unregister_hotmemory_notifier(nb) ({ (void)(nb); }) -#endif +#endif /* CONFIG_MEMORY_HOTPLUG */ /* * Kernel text modification mutex, used for code patching. Users of this lock diff --git a/include/linux/node.h b/include/linux/node.h index 8e5a29897936..bb21fd631b16 100644 --- a/include/linux/node.h +++ b/include/linux/node.h @@ -85,7 +85,7 @@ struct node { struct device dev; struct list_head access_list; -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HUGETLBFS) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_HUGETLBFS) struct work_struct node_work; #endif #ifdef CONFIG_HMEM_REPORTING @@ -98,7 +98,7 @@ struct memory_block; extern struct node *node_devices[]; typedef void (*node_registration_func_t)(struct node *); -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA) +#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA) void link_mem_sections(int nid, unsigned long start_pfn, unsigned long end_pfn, enum meminit_context context); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2a9b6dcdac4f..669fee1d26b8 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -877,7 +877,7 @@ config DEBUG_MEMORY_INIT config MEMORY_NOTIFIER_ERROR_INJECT tristate "Memory hotplug notifier error injection module" - depends on MEMORY_HOTPLUG_SPARSE && NOTIFIER_ERROR_INJECTION + depends on MEMORY_HOTPLUG && NOTIFIER_ERROR_INJECTION help This option provides the ability to inject artificial errors to memory hotplug notifier chain callbacks. It is controlled through diff --git a/mm/Kconfig b/mm/Kconfig index b2bf73c90a38..0148a9c4fa2a 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -128,10 +128,6 @@ config MEMORY_HOTPLUG depends on 64BIT || BROKEN select NUMA_KEEP_MEMINFO if NUMA -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" depends on MEMORY_HOTPLUG diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index afaae370b8cd..fc07ce7b5842 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -220,7 +220,6 @@ static void release_memory_resource(struct resource *res) kfree(res); } -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static int check_pfn_span(unsigned long pfn, unsigned long nr_pages, const char *reason) { @@ -1163,7 +1162,6 @@ failed_addition: mem_hotplug_done(); return ret; } -#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ static void reset_node_present_pages(pg_data_t *pgdat) { diff --git a/tools/testing/selftests/memory-hotplug/config b/tools/testing/selftests/memory-hotplug/config index a7e8cd5bb265..1eef042a31e1 100644 --- a/tools/testing/selftests/memory-hotplug/config +++ b/tools/testing/selftests/memory-hotplug/config @@ -1,5 +1,4 @@ CONFIG_MEMORY_HOTPLUG=y -CONFIG_MEMORY_HOTPLUG_SPARSE=y CONFIG_NOTIFIER_ERROR_INJECTION=y CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m CONFIG_MEMORY_HOTREMOVE=y -- cgit v1.2.3 From 6b740c6c3aa371cd70ac07f8d071f2a8af28c51c Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:31 -0700 Subject: mm/memory_hotplug: remove HIGHMEM leftovers We don't support CONFIG_MEMORY_HOTPLUG on 32 bit and consequently not HIGHMEM. Let's remove any leftover code -- including the unused "status_change_nid_high" field part of the memory notifier. Link: https://lkml.kernel.org/r/20210929143600.49379-5-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Oscar Salvador Cc: Alex Shi Cc: Andy Lutomirski Cc: Benjamin Herrenschmidt Cc: Borislav Petkov Cc: Dave Hansen Cc: Greg Kroah-Hartman Cc: "H. Peter Anvin" Cc: Ingo Molnar Cc: Jason Wang Cc: Jonathan Corbet Cc: Michael Ellerman Cc: "Michael S. Tsirkin" Cc: Michal Hocko Cc: Mike Rapoport Cc: Paul Mackerras Cc: Peter Zijlstra Cc: "Rafael J. Wysocki" Cc: Shuah Khan Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/core-api/memory-hotplug.rst | 3 -- .../translations/zh_CN/core-api/memory-hotplug.rst | 4 --- include/linux/memory.h | 1 - mm/memory_hotplug.c | 36 ++-------------------- 4 files changed, 2 insertions(+), 42 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/Documentation/core-api/memory-hotplug.rst b/Documentation/core-api/memory-hotplug.rst index de7467e48067..682259ee633a 100644 --- a/Documentation/core-api/memory-hotplug.rst +++ b/Documentation/core-api/memory-hotplug.rst @@ -57,7 +57,6 @@ The third argument (arg) passes a pointer of struct memory_notify:: unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; - int status_change_nid_high; int status_change_nid; } @@ -65,8 +64,6 @@ The third argument (arg) passes a pointer of struct memory_notify:: - nr_pages is # of pages of online/offline memory. - status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask is (will be) set/clear, if this is -1, then nodemask status is not changed. -- status_change_nid_high is set node id when N_HIGH_MEMORY of nodemask - is (will be) set/clear, if this is -1, then nodemask status is not changed. - status_change_nid is set node id when N_MEMORY of nodemask is (will be) set/clear. It means a new(memoryless) node gets new memory by online and a node loses all memory. If this is -1, then nodemask status is not changed. diff --git a/Documentation/translations/zh_CN/core-api/memory-hotplug.rst b/Documentation/translations/zh_CN/core-api/memory-hotplug.rst index 161f4d2c18cc..9a204eb196f2 100644 --- a/Documentation/translations/zh_CN/core-api/memory-hotplug.rst +++ b/Documentation/translations/zh_CN/core-api/memory-hotplug.rst @@ -63,7 +63,6 @@ memory_notify结构体的指针:: unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; - int status_change_nid_high; int status_change_nid; } @@ -74,9 +73,6 @@ memory_notify结构体的指针:: - status_change_nid_normal是当nodemask的N_NORMAL_MEMORY被设置/清除时设置节 点id，如果是-1，则nodemask状态不改变。 -- status_change_nid_high是当nodemask的N_HIGH_MEMORY被设置/清除时设置的节点 - id，如果这个值为-1，那么nodemask状态不会改变。 - - status_change_nid是当nodemask的N_MEMORY被（将）设置/清除时设置的节点id。这 意味着一个新的（没上线的）节点通过联机获得新的内存，而一个节点失去了所有的内 存。如果这个值为-1，那么nodemask的状态就不会改变。 diff --git a/include/linux/memory.h b/include/linux/memory.h index 0328ec039c38..88eb587b5143 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -96,7 +96,6 @@ struct memory_notify { unsigned long start_pfn; unsigned long nr_pages; int status_change_nid_normal; - int status_change_nid_high; int status_change_nid; }; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index fc07ce7b5842..0aa7ca3dfbc9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -21,7 +21,6 @@ #include #include #include -#include #include #include #include @@ -585,10 +584,6 @@ void generic_online_page(struct page *page, unsigned int order) debug_pagealloc_map_pages(page, 1 << order); __free_pages_core(page, order); totalram_pages_add(1UL << order); -#ifdef CONFIG_HIGHMEM - if (PageHighMem(page)) - totalhigh_pages_add(1UL << order); -#endif } EXPORT_SYMBOL_GPL(generic_online_page); @@ -625,16 +620,11 @@ static void node_states_check_changes_online(unsigned long nr_pages, arg->status_change_nid = NUMA_NO_NODE; arg->status_change_nid_normal = NUMA_NO_NODE; - arg->status_change_nid_high = NUMA_NO_NODE; if (!node_state(nid, N_MEMORY)) arg->status_change_nid = nid; if (zone_idx(zone) <= ZONE_NORMAL && !node_state(nid, N_NORMAL_MEMORY)) arg->status_change_nid_normal = nid; -#ifdef CONFIG_HIGHMEM - if (zone_idx(zone) <= ZONE_HIGHMEM && !node_state(nid, N_HIGH_MEMORY)) - arg->status_change_nid_high = nid; -#endif } static void node_states_set_node(int node, struct memory_notify *arg) @@ -642,9 +632,6 @@ static void node_states_set_node(int node, struct memory_notify *arg) if (arg->status_change_nid_normal >= 0) node_set_state(node, N_NORMAL_MEMORY); - if (arg->status_change_nid_high >= 0) - node_set_state(node, N_HIGH_MEMORY); - if (arg->status_change_nid >= 0) node_set_state(node, N_MEMORY); } @@ -1801,7 +1788,6 @@ static void node_states_check_changes_offline(unsigned long nr_pages, arg->status_change_nid = NUMA_NO_NODE; arg->status_change_nid_normal = NUMA_NO_NODE; - arg->status_change_nid_high = NUMA_NO_NODE; /* * Check whether node_states[N_NORMAL_MEMORY] will be changed. @@ -1816,24 +1802,9 @@ static void node_states_check_changes_offline(unsigned long nr_pages, if (zone_idx(zone) <= ZONE_NORMAL && nr_pages >= present_pages) arg->status_change_nid_normal = zone_to_nid(zone); -#ifdef CONFIG_HIGHMEM - /* - * node_states[N_HIGH_MEMORY] contains nodes which - * have normal memory or high memory. - * Here we add the present_pages belonging to ZONE_HIGHMEM. - * If the zone is within the range of [0..ZONE_HIGHMEM), and - * we determine that the zones in that range become empty, - * we need to clear the node for N_HIGH_MEMORY. - */ - present_pages += pgdat->node_zones[ZONE_HIGHMEM].present_pages; - if (zone_idx(zone) <= ZONE_HIGHMEM && nr_pages >= present_pages) - arg->status_change_nid_high = zone_to_nid(zone); -#endif - /* - * We have accounted the pages from [0..ZONE_NORMAL), and - * in case of CONFIG_HIGHMEM the pages from ZONE_HIGHMEM - * as well. + * We have accounted the pages from [0..ZONE_NORMAL); ZONE_HIGHMEM + * does not apply as we don't support 32bit. * Here we count the possible pages from ZONE_MOVABLE. * If after having accounted all the pages, we see that the nr_pages * to be offlined is over or equal to the accounted pages, @@ -1851,9 +1822,6 @@ static void node_states_clear_node(int node, struct memory_notify *arg) if (arg->status_change_nid_normal >= 0) node_clear_state(node, N_NORMAL_MEMORY); - if (arg->status_change_nid_high >= 0) - node_clear_state(node, N_HIGH_MEMORY); - if (arg->status_change_nid >= 0) node_clear_state(node, N_MEMORY); } -- cgit v1.2.3 From 53d38316ab2017a7c0d733765b521700aa357ec9 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:42 -0700 Subject: mm/memory_hotplug: handle memblock_add_node() failures in add_memory_resource() Patch series "mm/memory_hotplug: full support for add_memory_driver_managed() with CONFIG_ARCH_KEEP_MEMBLOCK", v2. Architectures that require CONFIG_ARCH_KEEP_MEMBLOCK=y, such as arm64, don't cleanly support add_memory_driver_managed() yet. Most prominently, kexec_file can still end up placing kexec images on such driver-managed memory, resulting in undesired behavior, for example, having kexec images located on memory not part of the firmware-provided memory map. Teaching kexec to not place images on driver-managed memory is especially relevant for virtio-mem. Details can be found in commit 7b7b27214bba ("mm/memory_hotplug: introduce add_memory_driver_managed()"). Extend memblock with a new flag and set it from memory hotplug code when applicable. This is required to fully support virtio-mem on arm64, making also kexec_file behave like on x86-64. This patch (of 2): If memblock_add_node() fails, we're most probably running out of memory. While this is unlikely to happen, it can happen and having memory added without a memblock can be problematic for architectures that use memblock to detect valid memory. Let's fail in a nice way instead of silently ignoring the error. Link: https://lkml.kernel.org/r/20211004093605.5830-1-david@redhat.com Link: https://lkml.kernel.org/r/20211004093605.5830-2-david@redhat.com Signed-off-by: David Hildenbrand Cc: Mike Rapoport Cc: Michal Hocko Cc: Oscar Salvador Cc: Jianyong Wu Cc: "Aneesh Kumar K . V" Cc: Vineet Gupta Cc: Geert Uytterhoeven Cc: Huacai Chen Cc: Jiaxun Yang Cc: Thomas Bogendoerfer Cc: Heiko Carstens Cc: Vasily Gorbik Cc: Christian Borntraeger Cc: Eric Biederman Cc: Arnd Bergmann Cc: Shahab Vahedi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 0aa7ca3dfbc9..9d254e88221e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1369,8 +1369,11 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) mem_hotplug_begin(); - if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) - memblock_add_node(start, size, nid); + if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { + ret = memblock_add_node(start, size, nid); + if (ret) + goto error_mem_hotplug_end; + } ret = __try_online_node(nid, false); if (ret < 0) @@ -1443,6 +1446,7 @@ error: rollback_node_hotadd(nid); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) memblock_remove(start, size); +error_mem_hotplug_end: mem_hotplug_done(); return ret; } -- cgit v1.2.3 From 952eea9b01e4bbb7011329f1b7240844e61e5128 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:49 -0700 Subject: memblock: allow to specify flags with memblock_add_node() We want to specify flags when hotplugging memory. Let's prepare to pass flags to memblock_add_node() by adjusting all existing users. Note that when hotplugging memory the system is already up and running and we might have concurrent memblock users: for example, while we're hotplugging memory, kexec_file code might search for suitable memory regions to place kexec images. It's important to add the memory directly to memblock via a single call with the right flags, instead of adding the memory first and apply flags later: otherwise, concurrent memblock users might temporarily stumble over memblocks with wrong flags, which will be important in a follow-up patch that introduces a new flag to properly handle add_memory_driver_managed(). Link: https://lkml.kernel.org/r/20211004093605.5830-4-david@redhat.com Acked-by: Geert Uytterhoeven Acked-by: Heiko Carstens Signed-off-by: David Hildenbrand Acked-by: Shahab Vahedi [arch/arc] Reviewed-by: Mike Rapoport Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Oscar Salvador Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arc/mm/init.c | 4 ++-- arch/ia64/mm/contig.c | 2 +- arch/ia64/mm/init.c | 2 +- arch/m68k/mm/mcfmmu.c | 3 ++- arch/m68k/mm/motorola.c | 6 ++++-- arch/mips/loongson64/init.c | 4 +++- arch/mips/sgi-ip27/ip27-memory.c | 3 ++- arch/s390/kernel/setup.c | 3 ++- include/linux/memblock.h | 3 ++- include/linux/mm.h | 2 +- mm/memblock.c | 9 +++++---- mm/memory_hotplug.c | 2 +- 12 files changed, 26 insertions(+), 17 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 59408f6a02d4..ce4e939a7f07 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -59,13 +59,13 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size) low_mem_sz = size; in_use = 1; - memblock_add_node(base, size, 0); + memblock_add_node(base, size, 0, MEMBLOCK_NONE); } else { #ifdef CONFIG_HIGHMEM high_mem_start = base; high_mem_sz = size; in_use = 1; - memblock_add_node(base, size, 1); + memblock_add_node(base, size, 1, MEMBLOCK_NONE); memblock_reserve(base, size); #endif } diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 42e025cfbd08..24901d809301 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -153,7 +153,7 @@ find_memory (void) efi_memmap_walk(find_max_min_low_pfn, NULL); max_pfn = max_low_pfn; - memblock_add_node(0, PFN_PHYS(max_low_pfn), 0); + memblock_add_node(0, PFN_PHYS(max_low_pfn), 0, MEMBLOCK_NONE); find_initrd(); diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 5c6da8d83c1a..5d165607bf35 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -378,7 +378,7 @@ int __init register_active_ranges(u64 start, u64 len, int nid) #endif if (start < end) - memblock_add_node(__pa(start), end - start, nid); + memblock_add_node(__pa(start), end - start, nid, MEMBLOCK_NONE); return 0; } diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index eac9dde65193..6f1f25125294 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -174,7 +174,8 @@ void __init cf_bootmem_alloc(void) m68k_memory[0].addr = _rambase; m68k_memory[0].size = _ramend - _rambase; - memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0, + MEMBLOCK_NONE); /* compute total pages in system */ num_pages = PFN_DOWN(_ramend - _rambase); diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 9f3f77785aa7..2b05bb2bac00 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -410,7 +410,8 @@ void __init paging_init(void) min_addr = m68k_memory[0].addr; max_addr = min_addr + m68k_memory[0].size; - memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0); + memblock_add_node(m68k_memory[0].addr, m68k_memory[0].size, 0, + MEMBLOCK_NONE); for (i = 1; i < m68k_num_memory;) { if (m68k_memory[i].addr < min_addr) { printk("Ignoring memory chunk at 0x%lx:0x%lx before the first chunk\n", @@ -421,7 +422,8 @@ void __init paging_init(void) (m68k_num_memory - i) * sizeof(struct m68k_mem_info)); continue; } - memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i); + memblock_add_node(m68k_memory[i].addr, m68k_memory[i].size, i, + MEMBLOCK_NONE); addr = m68k_memory[i].addr + m68k_memory[i].size; if (addr > max_addr) max_addr = addr; diff --git a/arch/mips/loongson64/init.c b/arch/mips/loongson64/init.c index 76e0a9636a0e..4ac5ba80bbf6 100644 --- a/arch/mips/loongson64/init.c +++ b/arch/mips/loongson64/init.c @@ -77,7 +77,9 @@ void __init szmem(unsigned int node) (u32)node_id, mem_type, mem_start, mem_size); pr_info(" start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n", start_pfn, end_pfn, num_physpages); - memblock_add_node(PFN_PHYS(start_pfn), PFN_PHYS(node_psize), node); + memblock_add_node(PFN_PHYS(start_pfn), + PFN_PHYS(node_psize), node, + MEMBLOCK_NONE); break; case SYSTEM_RAM_RESERVED: pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n", diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index 6173684b5aaa..adc2faeecf7c 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -341,7 +341,8 @@ static void __init szmem(void) continue; } memblock_add_node(PFN_PHYS(slot_getbasepfn(node, slot)), - PFN_PHYS(slot_psize), node); + PFN_PHYS(slot_psize), node, + MEMBLOCK_NONE); } } } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 7fc836e9e194..8a378d426239 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -593,7 +593,8 @@ static void __init setup_resources(void) * part of the System RAM resource. */ if (crashk_res.end) { - memblock_add_node(crashk_res.start, resource_size(&crashk_res), 0); + memblock_add_node(crashk_res.start, resource_size(&crashk_res), + 0, MEMBLOCK_NONE); memblock_reserve(crashk_res.start, resource_size(&crashk_res)); insert_resource(&iomem_resource, &crashk_res); } diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 1d2b3e902a84..8b6560dc7a9e 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -104,7 +104,8 @@ static inline void memblock_discard(void) {} #endif void memblock_allow_resize(void); -int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid); +int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid, + enum memblock_flags flags); int memblock_add(phys_addr_t base, phys_addr_t size); int memblock_remove(phys_addr_t base, phys_addr_t size); int memblock_phys_free(phys_addr_t base, phys_addr_t size); diff --git a/include/linux/mm.h b/include/linux/mm.h index 7e37c726b9db..15058d9cec99 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2425,7 +2425,7 @@ static inline unsigned long get_num_physpages(void) * unsigned long max_zone_pfns[MAX_NR_ZONES] = {max_dma, max_normal_pfn, * max_highmem_pfn}; * for_each_valid_physical_page_range() - * memblock_add_node(base, size, nid) + * memblock_add_node(base, size, nid, MEMBLOCK_NONE) * free_area_init(max_zone_pfns); */ void free_area_init(unsigned long *max_zone_pfn); diff --git a/mm/memblock.c b/mm/memblock.c index fb0c7f48e627..1b0cd8a52a13 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -655,6 +655,7 @@ repeat: * @base: base address of the new region * @size: size of the new region * @nid: nid of the new region + * @flags: flags of the new region * * Add new memblock region [@base, @base + @size) to the "memory" * type. See memblock_add_range() description for mode details @@ -663,14 +664,14 @@ repeat: * 0 on success, -errno on failure. */ int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size, - int nid) + int nid, enum memblock_flags flags) { phys_addr_t end = base + size - 1; - memblock_dbg("%s: [%pa-%pa] nid=%d %pS\n", __func__, - &base, &end, nid, (void *)_RET_IP_); + memblock_dbg("%s: [%pa-%pa] nid=%d flags=%x %pS\n", __func__, + &base, &end, nid, flags, (void *)_RET_IP_); - return memblock_add_range(&memblock.memory, base, size, nid, 0); + return memblock_add_range(&memblock.memory, base, size, nid, flags); } /** diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 9d254e88221e..cedeaa4d6f0e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1370,7 +1370,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) mem_hotplug_begin(); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { - ret = memblock_add_node(start, size, nid); + ret = memblock_add_node(start, size, nid, MEMBLOCK_NONE); if (ret) goto error_mem_hotplug_end; } -- cgit v1.2.3 From 32befe9e27859b87e70e0aba9b60bfb8000d9a66 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Fri, 5 Nov 2021 13:44:56 -0700 Subject: mm/memory_hotplug: indicate MEMBLOCK_DRIVER_MANAGED with IORESOURCE_SYSRAM_DRIVER_MANAGED Let's communicate driver-managed regions to memblock, to properly teach kexec_file with CONFIG_ARCH_KEEP_MEMBLOCK to not place images on these memory regions. Link: https://lkml.kernel.org/r/20211004093605.5830-6-david@redhat.com Signed-off-by: David Hildenbrand Cc: "Aneesh Kumar K . V" Cc: Arnd Bergmann Cc: Christian Borntraeger Cc: Eric Biederman Cc: Geert Uytterhoeven Cc: Heiko Carstens Cc: Huacai Chen Cc: Jianyong Wu Cc: Jiaxun Yang Cc: Michal Hocko Cc: Mike Rapoport Cc: Oscar Salvador Cc: Shahab Vahedi Cc: Thomas Bogendoerfer Cc: Vasily Gorbik Cc: Vineet Gupta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'mm/memory_hotplug.c') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index cedeaa4d6f0e..852041f6be41 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1342,6 +1342,7 @@ bool mhp_supports_memmap_on_memory(unsigned long size) int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) { struct mhp_params params = { .pgprot = pgprot_mhp(PAGE_KERNEL) }; + enum memblock_flags memblock_flags = MEMBLOCK_NONE; struct vmem_altmap mhp_altmap = {}; struct memory_group *group = NULL; u64 start, size; @@ -1370,7 +1371,9 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) mem_hotplug_begin(); if (IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK)) { - ret = memblock_add_node(start, size, nid, MEMBLOCK_NONE); + if (res->flags & IORESOURCE_SYSRAM_DRIVER_MANAGED) + memblock_flags = MEMBLOCK_DRIVER_MANAGED; + ret = memblock_add_node(start, size, nid, memblock_flags); if (ret) goto error_mem_hotplug_end; } -- cgit v1.2.3