From eafd296e0cc0cc03b4ae01c2b3b07273514d757c Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Fri, 23 Sep 2022 11:33:46 +0800 Subject: memory: remove unused register_hotmemory_notifier() Remove unused register_hotmemory_notifier(). Link: https://lkml.kernel.org/r/20220923033347.3935160-8-liushixin2@huawei.com Signed-off-by: Liu Shixin Reviewed-by: David Hildenbrand Cc: Christoph Lameter Cc: Kefeng Wang Cc: Waiman Long Cc: zefan li Signed-off-by: Andrew Morton --- include/linux/memory.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux/memory.h') diff --git a/include/linux/memory.h b/include/linux/memory.h index aa619464a1df..98d2a2ebcc10 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -19,7 +19,6 @@ #include #include #include -#include #define MIN_MEMORY_BLOCK_SIZE (1UL << SECTION_SIZE_BITS) @@ -136,9 +135,6 @@ 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); @@ -166,8 +162,6 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, { .notifier_call = fn, .priority = pri };\ register_memory_notifier(&fn##_mem_nb); \ }) -#define register_hotmemory_notifier(nb) register_memory_notifier(nb) -#define unregister_hotmemory_notifier(nb) unregister_memory_notifier(nb) #ifdef CONFIG_NUMA void memory_block_add_nid(struct memory_block *mem, int nid, -- cgit v1.2.3 From 1eeaa4fd39b0b1b3e986f8eab6978e69b01e3c5e Mon Sep 17 00:00:00 2001 From: Liu Shixin Date: Fri, 23 Sep 2022 11:33:47 +0800 Subject: memory: move hotplug memory notifier priority to same file for easy sorting The priority of hotplug memory callback is defined in a different file. And there are some callers using numbers directly. Collect them together into include/linux/memory.h for easy reading. This allows us to sort their priorities more intuitively without additional comments. Link: https://lkml.kernel.org/r/20220923033347.3935160-9-liushixin2@huawei.com Signed-off-by: Liu Shixin Cc: Christoph Lameter Cc: David Hildenbrand Cc: Kefeng Wang Cc: Waiman Long Cc: zefan li Signed-off-by: Andrew Morton --- drivers/acpi/numa/hmat.c | 2 +- fs/proc/kcore.c | 2 +- include/linux/memory-tiers.h | 1 - include/linux/memory.h | 9 +++++++-- kernel/cgroup/cpuset.c | 2 +- mm/kasan/shadow.c | 2 +- mm/ksm.c | 2 +- mm/memory-tiers.c | 2 +- mm/mm_init.c | 2 +- mm/mmap.c | 2 +- mm/page_ext.c | 2 +- 11 files changed, 16 insertions(+), 12 deletions(-) (limited to 'include/linux/memory.h') diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c index 0ecefb604734..139e3b41653e 100644 --- a/drivers/acpi/numa/hmat.c +++ b/drivers/acpi/numa/hmat.c @@ -849,7 +849,7 @@ static __init int hmat_init(void) hmat_register_targets(); /* Keep the table and structures if the notifier may use them */ - if (!hotplug_memory_notifier(hmat_callback, 2)) + if (!hotplug_memory_notifier(hmat_callback, HMAT_CALLBACK_PRI)) return 0; out_put: hmat_free_structures(); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 7692a360972d..98f3289556e4 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -689,7 +689,7 @@ static int __init proc_kcore_init(void) add_modules_range(); /* Store direct-map area from physical memory map */ kcore_update_ram(); - hotplug_memory_notifier(kcore_callback, 0); + hotplug_memory_notifier(kcore_callback, DEFAULT_CALLBACK_PRI); return 0; } diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h index 965009aa01d7..fc9647b1b4f9 100644 --- a/include/linux/memory-tiers.h +++ b/include/linux/memory-tiers.h @@ -18,7 +18,6 @@ * the same memory tier. */ #define MEMTIER_ADISTANCE_DRAM ((4 * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1)) -#define MEMTIER_HOTPLUG_PRIO 100 struct memory_tier; struct memory_dev_type { diff --git a/include/linux/memory.h b/include/linux/memory.h index 98d2a2ebcc10..463662ef7614 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -112,8 +112,13 @@ struct mem_section; * Priorities for the hotplug memory callback routines (stored in decreasing * order in the callback chain) */ -#define SLAB_CALLBACK_PRI 1 -#define IPC_CALLBACK_PRI 10 +#define DEFAULT_CALLBACK_PRI 0 +#define SLAB_CALLBACK_PRI 1 +#define HMAT_CALLBACK_PRI 2 +#define MM_COMPUTE_BATCH_PRI 10 +#define CPUSET_CALLBACK_PRI 10 +#define MEMTIER_HOTPLUG_PRI 100 +#define KSM_CALLBACK_PRI 100 #ifndef CONFIG_MEMORY_HOTPLUG static inline void memory_dev_init(void) diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 0c6db6a4f427..3ea2e836e93e 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -3647,7 +3647,7 @@ void __init cpuset_init_smp(void) cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); top_cpuset.effective_mems = node_states[N_MEMORY]; - hotplug_memory_notifier(cpuset_track_online_nodes, 10); + hotplug_memory_notifier(cpuset_track_online_nodes, CPUSET_CALLBACK_PRI); cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); BUG_ON(!cpuset_migrate_mm_wq); diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c index 0e3648b603a6..2fba1f51f042 100644 --- a/mm/kasan/shadow.c +++ b/mm/kasan/shadow.c @@ -244,7 +244,7 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb, static int __init kasan_memhotplug_init(void) { - hotplug_memory_notifier(kasan_mem_notifier, 0); + hotplug_memory_notifier(kasan_mem_notifier, DEFAULT_CALLBACK_PRI); return 0; } diff --git a/mm/ksm.c b/mm/ksm.c index c19fcca9bc03..7ba97f86d831 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -3211,7 +3211,7 @@ static int __init ksm_init(void) #ifdef CONFIG_MEMORY_HOTREMOVE /* There is no significance to this priority 100 */ - hotplug_memory_notifier(ksm_memory_callback, 100); + hotplug_memory_notifier(ksm_memory_callback, KSM_CALLBACK_PRI); #endif return 0; diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c index fa8c9d07f9ce..939e200c283b 100644 --- a/mm/memory-tiers.c +++ b/mm/memory-tiers.c @@ -664,7 +664,7 @@ static int __init memory_tier_init(void) establish_demotion_targets(); mutex_unlock(&memory_tier_lock); - hotplug_memory_notifier(memtier_hotplug_callback, MEMTIER_HOTPLUG_PRIO); + hotplug_memory_notifier(memtier_hotplug_callback, MEMTIER_HOTPLUG_PRI); return 0; } subsys_initcall(memory_tier_init); diff --git a/mm/mm_init.c b/mm/mm_init.c index 44aadc162d1f..c1883362e71d 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -181,7 +181,7 @@ static int __meminit mm_compute_batch_notifier(struct notifier_block *self, static int __init mm_compute_batch_init(void) { mm_compute_batch(sysctl_overcommit_memory); - hotplug_memory_notifier(mm_compute_batch_notifier, IPC_CALLBACK_PRI); + hotplug_memory_notifier(mm_compute_batch_notifier, MM_COMPUTE_BATCH_PRI); return 0; } diff --git a/mm/mmap.c b/mm/mmap.c index 3f47fd57d165..c697771d406b 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -3751,7 +3751,7 @@ static int reserve_mem_notifier(struct notifier_block *nb, static int __meminit init_reserve_notifier(void) { - if (hotplug_memory_notifier(reserve_mem_notifier, 0)) + if (hotplug_memory_notifier(reserve_mem_notifier, DEFAULT_CALLBACK_PRI)) pr_err("Failed registering memory add/remove notifier for admin reserve\n"); return 0; diff --git a/mm/page_ext.c b/mm/page_ext.c index affe80243b6d..b2ff5c9129f4 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -513,7 +513,7 @@ void __init page_ext_init(void) cond_resched(); } } - hotplug_memory_notifier(page_ext_callback, 0); + hotplug_memory_notifier(page_ext_callback, DEFAULT_CALLBACK_PRI); pr_info("allocated %ld bytes of page_ext\n", total_usage); invoke_init_callbacks(); return; -- cgit v1.2.3 From 5033091de814ab4b5623faed2755f3064e19e2d2 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Mon, 24 Oct 2022 15:20:12 +0900 Subject: mm/hwpoison: introduce per-memory_block hwpoison counter Currently PageHWPoison flag does not behave well when experiencing memory hotremove/hotplug. Any data field in struct page is unreliable when the associated memory is offlined, and the current mechanism can't tell whether a memory block is onlined because a new memory devices is installed or because previous failed offline operations are undone. Especially if there's a hwpoisoned memory, it's unclear what the best option is. So introduce a new mechanism to make struct memory_block remember that a memory block has hwpoisoned memory inside it. And make any online event fail if the onlining memory block contains hwpoison. struct memory_block is freed and reallocated over ACPI-based hotremove/hotplug, but not over sysfs-based hotremove/hotplug. So the new counter can distinguish these cases. Link: https://lkml.kernel.org/r/20221024062012.1520887-5-naoya.horiguchi@linux.dev Signed-off-by: Naoya Horiguchi Reported-by: kernel test robot Reviewed-by: Miaohe Lin Cc: David Hildenbrand Cc: Jane Chu Cc: Mike Kravetz Cc: Muchun Song Cc: Oscar Salvador Cc: Yang Shi Signed-off-by: Andrew Morton --- drivers/base/memory.c | 38 ++++++++++++++++++++++++++++++++++++++ include/linux/memory.h | 3 +++ include/linux/mm.h | 20 +++++++++++++++++++- mm/internal.h | 8 -------- mm/memory-failure.c | 36 +++++++++++------------------------- mm/sparse.c | 2 -- 6 files changed, 71 insertions(+), 36 deletions(-) (limited to 'include/linux/memory.h') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 9aa0da991cfb..fe98fb8d94e5 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -175,6 +175,15 @@ int memory_notify(unsigned long val, void *v) return blocking_notifier_call_chain(&memory_chain, val, v); } +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) +static unsigned long memblk_nr_poison(struct memory_block *mem); +#else +static inline unsigned long memblk_nr_poison(struct memory_block *mem) +{ + return 0; +} +#endif + static int memory_block_online(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -183,6 +192,9 @@ static int memory_block_online(struct memory_block *mem) struct zone *zone; int ret; + if (memblk_nr_poison(mem)) + return -EHWPOISON; + zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group, start_pfn, nr_pages); @@ -864,6 +876,7 @@ void remove_memory_block_devices(unsigned long start, unsigned long size) mem = find_memory_block_by_id(block_id); if (WARN_ON_ONCE(!mem)) continue; + num_poisoned_pages_sub(-1UL, memblk_nr_poison(mem)); unregister_memory_block_under_nodes(mem); remove_memory_block(mem); } @@ -1164,3 +1177,28 @@ int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func, } return ret; } + +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) +void memblk_nr_poison_inc(unsigned long pfn) +{ + const unsigned long block_id = pfn_to_block_id(pfn); + struct memory_block *mem = find_memory_block_by_id(block_id); + + if (mem) + atomic_long_inc(&mem->nr_hwpoison); +} + +void memblk_nr_poison_sub(unsigned long pfn, long i) +{ + const unsigned long block_id = pfn_to_block_id(pfn); + struct memory_block *mem = find_memory_block_by_id(block_id); + + if (mem) + atomic_long_sub(i, &mem->nr_hwpoison); +} + +static unsigned long memblk_nr_poison(struct memory_block *mem) +{ + return atomic_long_read(&mem->nr_hwpoison); +} +#endif diff --git a/include/linux/memory.h b/include/linux/memory.h index 463662ef7614..31343566c221 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -84,6 +84,9 @@ struct memory_block { unsigned long nr_vmemmap_pages; struct memory_group *group; /* group (if any) for this block */ struct list_head group_next; /* next block inside memory group */ +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) + atomic_long_t nr_hwpoison; +#endif }; int arch_get_memory_phys_device(unsigned long start_pfn); diff --git a/include/linux/mm.h b/include/linux/mm.h index 78ae2ee09a24..429ff89bfe06 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -3279,7 +3279,8 @@ extern int soft_offline_page(unsigned long pfn, int flags); #ifdef CONFIG_MEMORY_FAILURE extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared); -extern void num_poisoned_pages_inc(unsigned long pfn); +void num_poisoned_pages_inc(unsigned long pfn); +void num_poisoned_pages_sub(unsigned long pfn, long i); #else static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared) @@ -3290,6 +3291,23 @@ static inline int __get_huge_page_for_hwpoison(unsigned long pfn, int flags, static inline void num_poisoned_pages_inc(unsigned long pfn) { } + +static inline void num_poisoned_pages_sub(unsigned long pfn, long i) +{ +} +#endif + +#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG) +extern void memblk_nr_poison_inc(unsigned long pfn); +extern void memblk_nr_poison_sub(unsigned long pfn, long i); +#else +static inline void memblk_nr_poison_inc(unsigned long pfn) +{ +} + +static inline void memblk_nr_poison_sub(unsigned long pfn, long i) +{ +} #endif #ifndef arch_memory_failure diff --git a/mm/internal.h b/mm/internal.h index 68afdbe7106e..bcf75a8b032d 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -708,14 +708,6 @@ extern u64 hwpoison_filter_flags_value; extern u64 hwpoison_filter_memcg; extern u32 hwpoison_filter_enable; -#ifdef CONFIG_MEMORY_FAILURE -void clear_hwpoisoned_pages(struct page *memmap, int nr_pages); -#else -static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) -{ -} -#endif - extern unsigned long __must_check vm_mmap_pgoff(struct file *, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long); diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 757a46e172de..9b82402ec242 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -77,11 +77,14 @@ static bool hw_memory_failure __read_mostly = false; inline void num_poisoned_pages_inc(unsigned long pfn) { atomic_long_inc(&num_poisoned_pages); + memblk_nr_poison_inc(pfn); } -static inline void num_poisoned_pages_sub(unsigned long pfn, long i) +inline void num_poisoned_pages_sub(unsigned long pfn, long i) { atomic_long_sub(i, &num_poisoned_pages); + if (pfn != -1UL) + memblk_nr_poison_sub(pfn, i); } /* @@ -1706,6 +1709,8 @@ static unsigned long __free_raw_hwp_pages(struct page *hpage, bool move_flag) if (move_flag) SetPageHWPoison(p->page); + else + num_poisoned_pages_sub(page_to_pfn(p->page), 1); kfree(p); count++; } @@ -2332,6 +2337,7 @@ int unpoison_memory(unsigned long pfn) int ret = -EBUSY; int freeit = 0; unsigned long count = 1; + bool huge = false; static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); @@ -2380,6 +2386,7 @@ int unpoison_memory(unsigned long pfn) ret = get_hwpoison_page(p, MF_UNPOISON); if (!ret) { if (PageHuge(p)) { + huge = true; count = free_raw_hwp_pages(page, false); if (count == 0) { ret = -EBUSY; @@ -2395,6 +2402,7 @@ int unpoison_memory(unsigned long pfn) pfn, &unpoison_rs); } else { if (PageHuge(p)) { + huge = true; count = free_raw_hwp_pages(page, false); if (count == 0) { ret = -EBUSY; @@ -2414,7 +2422,8 @@ int unpoison_memory(unsigned long pfn) unlock_mutex: mutex_unlock(&mf_mutex); if (!ret || freeit) { - num_poisoned_pages_sub(pfn, count); + if (!huge) + num_poisoned_pages_sub(pfn, 1); unpoison_pr_info("Unpoison: Software-unpoisoned page %#lx\n", page_to_pfn(p), &unpoison_rs); } @@ -2609,26 +2618,3 @@ retry: return ret; } - -void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) -{ - int i, total = 0; - - /* - * A further optimization is to have per section refcounted - * num_poisoned_pages. But that would need more space per memmap, so - * for now just do a quick global check to speed up this routine in the - * absence of bad pages. - */ - if (atomic_long_read(&num_poisoned_pages) == 0) - return; - - for (i = 0; i < nr_pages; i++) { - if (PageHWPoison(&memmap[i])) { - total++; - ClearPageHWPoison(&memmap[i]); - } - } - if (total) - num_poisoned_pages_sub(0, total); -} diff --git a/mm/sparse.c b/mm/sparse.c index e5a8a3a0edd7..2779b419ef2a 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -926,8 +926,6 @@ void sparse_remove_section(struct mem_section *ms, unsigned long pfn, unsigned long nr_pages, unsigned long map_offset, struct vmem_altmap *altmap) { - clear_hwpoisoned_pages(pfn_to_page(pfn) + map_offset, - nr_pages - map_offset); section_deactivate(pfn, nr_pages, altmap); } #endif /* CONFIG_MEMORY_HOTPLUG */ -- cgit v1.2.3