diff options
52 files changed, 996 insertions, 422 deletions
diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt index cefd3d8bbd1..12e01d432bf 100644 --- a/Documentation/cgroups/cpusets.txt +++ b/Documentation/cgroups/cpusets.txt @@ -218,7 +218,7 @@ and name space for cpusets, with a minimum of additional kernel code. The cpus and mems files in the root (top_cpuset) cpuset are read-only. The cpus file automatically tracks the value of cpu_online_mask using a CPU hotplug notifier, and the mems file -automatically tracks the value of node_states[N_HIGH_MEMORY]--i.e., +automatically tracks the value of node_states[N_MEMORY]--i.e., nodes with memory--using the cpuset_track_online_nodes() hook. diff --git a/Documentation/memory-hotplug.txt b/Documentation/memory-hotplug.txt index c6f993d491b..8e5eacbdcfa 100644 --- a/Documentation/memory-hotplug.txt +++ b/Documentation/memory-hotplug.txt @@ -390,6 +390,7 @@ 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; } @@ -397,7 +398,9 @@ start_pfn is start_pfn of online/offline memory. 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 is set node id when N_HIGH_MEMORY of nodemask is (will be) +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. If status_changed_nid* >= 0, callback should create/discard structures for the diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt index f734bb2a78d..8785fb87d9c 100644 --- a/Documentation/vm/transhuge.txt +++ b/Documentation/vm/transhuge.txt @@ -116,6 +116,13 @@ echo always >/sys/kernel/mm/transparent_hugepage/defrag echo madvise >/sys/kernel/mm/transparent_hugepage/defrag echo never >/sys/kernel/mm/transparent_hugepage/defrag +By default kernel tries to use huge zero page on read page fault. +It's possible to disable huge zero page by writing 0 or enable it +back by writing 1: + +echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page +echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/use_zero_page + khugepaged will be automatically started when transparent_hugepage/enabled is set to "always" or "madvise, and it'll be automatically shutdown if it's set to "never". @@ -197,6 +204,14 @@ thp_split is incremented every time a huge page is split into base pages. This can happen for a variety of reasons but a common reason is that a huge page is old and is being reclaimed. +thp_zero_page_alloc is incremented every time a huge zero page is + successfully allocated. It includes allocations which where + dropped due race with other allocation. Note, it doesn't count + every map of the huge zero page, only its allocation. + +thp_zero_page_alloc_failed is incremented if kernel fails to allocate + huge zero page and falls back to using small pages. + As the system ages, allocating huge pages may be expensive as the system uses memory compaction to copy data around memory to free a huge page for use. There are some counters in /proc/vmstat to help @@ -276,7 +291,7 @@ unaffected. libhugetlbfs will also work fine as usual. == Graceful fallback == Code walking pagetables but unware about huge pmds can simply call -split_huge_page_pmd(mm, pmd) where the pmd is the one returned by +split_huge_page_pmd(vma, addr, pmd) where the pmd is the one returned by pmd_offset. It's trivial to make the code transparent hugepage aware by just grepping for "pmd_offset" and adding split_huge_page_pmd where missing after pmd_offset returns the pmd. Thanks to the graceful @@ -299,7 +314,7 @@ diff --git a/mm/mremap.c b/mm/mremap.c return NULL; pmd = pmd_offset(pud, addr); -+ split_huge_page_pmd(mm, pmd); ++ split_huge_page_pmd(vma, addr, pmd); if (pmd_none_or_clear_bad(pmd)) return NULL; diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h index c02158be836..14490e9443a 100644 --- a/arch/mips/include/asm/pgtable.h +++ b/arch/mips/include/asm/pgtable.h @@ -76,16 +76,7 @@ extern unsigned long zero_page_mask; #define ZERO_PAGE(vaddr) \ (virt_to_page((void *)(empty_zero_page + (((unsigned long)(vaddr)) & zero_page_mask)))) - -#define is_zero_pfn is_zero_pfn -static inline int is_zero_pfn(unsigned long pfn) -{ - extern unsigned long zero_pfn; - unsigned long offset_from_zero_pfn = pfn - zero_pfn; - return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT); -} - -#define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) +#define __HAVE_COLOR_ZERO_PAGE extern void paging_init(void); diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 0a6b28336eb..3a8489a354e 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -113,19 +113,6 @@ static int store_updates_sp(struct pt_regs *regs) #define MM_FAULT_CONTINUE -1 #define MM_FAULT_ERR(sig) (sig) -static int out_of_memory(struct pt_regs *regs) -{ - /* - * We ran out of memory, or some other thing happened to us that made - * us unable to handle the page fault gracefully. - */ - up_read(¤t->mm->mmap_sem); - if (!user_mode(regs)) - return MM_FAULT_ERR(SIGKILL); - pagefault_out_of_memory(); - return MM_FAULT_RETURN; -} - static int do_sigbus(struct pt_regs *regs, unsigned long address) { siginfo_t info; @@ -169,8 +156,18 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault) return MM_FAULT_CONTINUE; /* Out of memory */ - if (fault & VM_FAULT_OOM) - return out_of_memory(regs); + if (fault & VM_FAULT_OOM) { + up_read(¤t->mm->mmap_sem); + + /* + * We ran out of memory, or some other thing happened to us that + * made us unable to handle the page fault gracefully. + */ + if (!user_mode(regs)) + return MM_FAULT_ERR(SIGKILL); + pagefault_out_of_memory(); + return MM_FAULT_RETURN; + } /* Bus error. x86 handles HWPOISON here, we'll add this if/when * we support the feature in HW diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h index 2d3b7cb2600..c814e6f5b57 100644 --- a/arch/s390/include/asm/pgtable.h +++ b/arch/s390/include/asm/pgtable.h @@ -55,16 +55,7 @@ extern unsigned long zero_page_mask; #define ZERO_PAGE(vaddr) \ (virt_to_page((void *)(empty_zero_page + \ (((unsigned long)(vaddr)) &zero_page_mask)))) - -#define is_zero_pfn is_zero_pfn -static inline int is_zero_pfn(unsigned long pfn) -{ - extern unsigned long zero_pfn; - unsigned long offset_from_zero_pfn = pfn - zero_pfn; - return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT); -} - -#define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) +#define __HAVE_COLOR_ZERO_PAGE #endif /* !__ASSEMBLY__ */ diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index cbbdcad8fcb..1f49c28affa 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -301,17 +301,6 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code, __bad_area(regs, error_code, address, SEGV_ACCERR); } -static void out_of_memory(void) -{ - /* - * We ran out of memory, call the OOM killer, and return the userspace - * (which will retry the fault, or kill us if we got oom-killed): - */ - up_read(¤t->mm->mmap_sem); - - pagefault_out_of_memory(); -} - static void do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address) { @@ -353,8 +342,14 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, no_context(regs, error_code, address); return 1; } + up_read(¤t->mm->mmap_sem); - out_of_memory(); + /* + * We ran out of memory, call the OOM killer, and return the + * userspace (which will retry the fault, or kill us if we got + * oom-killed): + */ + pagefault_out_of_memory(); } else { if (fault & VM_FAULT_SIGBUS) do_sigbus(regs, error_code, address); diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 5c9687b1bde..1dfe69cc78a 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -182,7 +182,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) if (pud_none_or_clear_bad(pud)) goto out; pmd = pmd_offset(pud, 0xA0000); - split_huge_page_pmd(mm, pmd); + split_huge_page_pmd_mm(mm, 0xA0000, pmd); if (pmd_none_or_clear_bad(pmd)) goto out; pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 7a529cbab7a..027088f2f7d 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -803,20 +803,6 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code, __bad_area(regs, error_code, address, SEGV_ACCERR); } -/* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */ -static void -out_of_memory(struct pt_regs *regs, unsigned long error_code, - unsigned long address) -{ - /* - * We ran out of memory, call the OOM killer, and return the userspace - * (which will retry the fault, or kill us if we got oom-killed): - */ - up_read(¤t->mm->mmap_sem); - - pagefault_out_of_memory(); -} - static void do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address, unsigned int fault) @@ -879,7 +865,14 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code, return 1; } - out_of_memory(regs, error_code, address); + up_read(¤t->mm->mmap_sem); + + /* + * We ran out of memory, call the OOM killer, and return the + * userspace (which will retry the fault, or kill us if we got + * oom-killed): + */ + pagefault_out_of_memory(); } else { if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON| VM_FAULT_HWPOISON_LARGE)) diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 3baff255ada..2ead3c8a4c8 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -630,7 +630,9 @@ void __init paging_init(void) * numa support is not compiled in, and later node_set_state * will not set it back. */ - node_clear_state(0, N_NORMAL_MEMORY); + node_clear_state(0, N_MEMORY); + if (N_MEMORY != N_NORMAL_MEMORY) + node_clear_state(0, N_NORMAL_MEMORY); zone_sizes_init(); } diff --git a/drivers/base/node.c b/drivers/base/node.c index 294e3162621..fac124a7e1c 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -227,7 +227,7 @@ static node_registration_func_t __hugetlb_unregister_node; static inline bool hugetlb_register_node(struct node *node) { if (__hugetlb_register_node && - node_state(node->dev.id, N_HIGH_MEMORY)) { + node_state(node->dev.id, N_MEMORY)) { __hugetlb_register_node(node); return true; } @@ -644,6 +644,9 @@ static struct node_attr node_state_attr[] = { #ifdef CONFIG_HIGHMEM [N_HIGH_MEMORY] = _NODE_ATTR(has_high_memory, N_HIGH_MEMORY), #endif +#ifdef CONFIG_MOVABLE_NODE + [N_MEMORY] = _NODE_ATTR(has_memory, N_MEMORY), +#endif [N_CPU] = _NODE_ATTR(has_cpu, N_CPU), }; @@ -654,6 +657,9 @@ static struct attribute *node_state_attrs[] = { #ifdef CONFIG_HIGHMEM &node_state_attr[N_HIGH_MEMORY].attr.attr, #endif +#ifdef CONFIG_MOVABLE_NODE + &node_state_attr[N_MEMORY].attr.attr, +#endif &node_state_attr[N_CPU].attr.attr, NULL }; diff --git a/fs/buffer.c b/fs/buffer.c index 6e9ed48064f..c017a2dfb90 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -46,8 +46,7 @@ static int fsync_buffers_list(spinlock_t *lock, struct list_head *list); #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers) -inline void -init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *private) +void init_buffer(struct buffer_head *bh, bh_end_io_t *handler, void *private) { bh->b_end_io = handler; bh->b_private = private; @@ -850,13 +849,10 @@ try_again: if (!bh) goto no_grow; - bh->b_bdev = NULL; bh->b_this_page = head; bh->b_blocknr = -1; head = bh; - bh->b_state = 0; - atomic_set(&bh->b_count, 0); bh->b_size = size; /* Link the buffer to its page */ diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 3e3422f7f0a..310972b72a6 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -1034,7 +1034,7 @@ int bdi_writeback_thread(void *data) while (!kthread_freezable_should_stop(NULL)) { /* * Remove own delayed wake-up timer, since we are already awake - * and we'll take care of the preriodic write-back. + * and we'll take care of the periodic write-back. */ del_timer(&wb->wakeup_timer); diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index 86c67eee439..e96d4f18ca3 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -249,7 +249,7 @@ static int kcore_update_ram(void) /* Not inialized....update now */ /* find out "max pfn" */ end_pfn = 0; - for_each_node_state(nid, N_HIGH_MEMORY) { + for_each_node_state(nid, N_MEMORY) { unsigned long node_end; node_end = NODE_DATA(nid)->node_start_pfn + NODE_DATA(nid)->node_spanned_pages; diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 90c63f9392a..48775628abb 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -643,7 +643,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr, spinlock_t *ptl; struct page *page; - split_huge_page_pmd(walk->mm, pmd); + split_huge_page_pmd(vma, addr, pmd); if (pmd_trans_unstable(pmd)) return 0; @@ -1126,7 +1126,7 @@ static struct page *can_gather_numa_stats(pte_t pte, struct vm_area_struct *vma, return NULL; nid = page_to_nid(page); - if (!node_isset(nid, node_states[N_HIGH_MEMORY])) + if (!node_isset(nid, node_states[N_MEMORY])) return NULL; return page; @@ -1279,7 +1279,7 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid) if (md->writeback) seq_printf(m, " writeback=%lu", md->writeback); - for_each_node_state(n, N_HIGH_MEMORY) + for_each_node_state(n, N_MEMORY) if (md->node[n]) seq_printf(m, " N%d=%lu", n, md->node[n]); out: diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h index b36ce40bd1c..284e80831d2 100644 --- a/include/asm-generic/pgtable.h +++ b/include/asm-generic/pgtable.h @@ -449,6 +449,32 @@ extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size); #endif +#ifdef __HAVE_COLOR_ZERO_PAGE +static inline int is_zero_pfn(unsigned long pfn) +{ + extern unsigned long zero_pfn; + unsigned long offset_from_zero_pfn = pfn - zero_pfn; + return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT); +} + +static inline unsigned long my_zero_pfn(unsigned long addr) +{ + return page_to_pfn(ZERO_PAGE(addr)); +} +#else +static inline int is_zero_pfn(unsigned long pfn) +{ + extern unsigned long zero_pfn; + return pfn == zero_pfn; +} + +static inline unsigned long my_zero_pfn(unsigned long addr) +{ + extern unsigned long zero_pfn; + return zero_pfn; +} +#endif + #ifdef CONFIG_MMU #ifndef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 7b74452c531..3f778c27f82 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -137,9 +137,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #define alloc_bootmem_low_pages_node(pgdat, x) \ __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) -extern int reserve_bootmem_generic(unsigned long addr, unsigned long size, - int flags); - #ifdef CONFIG_HAVE_ARCH_ALLOC_REMAP extern void *alloc_remap(int nid, unsigned long size); #else diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 838320fc3d1..8c8a60d2940 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -144,7 +144,7 @@ static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) return node_possible_map; } -#define cpuset_current_mems_allowed (node_states[N_HIGH_MEMORY]) +#define cpuset_current_mems_allowed (node_states[N_MEMORY]) static inline void cpuset_init_current_mems_allowed(void) {} static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 31e8041274f..f74856e17e4 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -34,6 +34,7 @@ struct vm_area_struct; #define ___GFP_NO_KSWAPD 0x400000u #define ___GFP_OTHER_NODE 0x800000u #define ___GFP_WRITE 0x1000000u +/* If the above are modified, __GFP_BITS_SHIFT may need updating */ /* * GFP bitmasks.. diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 1af47755245..092dc5305a3 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -39,6 +39,7 @@ enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_DEFRAG_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, + TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG, #ifdef CONFIG_DEBUG_VM TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG, #endif @@ -78,6 +79,9 @@ extern bool is_vma_temporary_stack(struct vm_area_struct *vma); (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG) && \ (__vma)->vm_flags & VM_HUGEPAGE)) +#define transparent_hugepage_use_zero_page() \ + (transparent_hugepage_flags & \ + (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) #ifdef CONFIG_DEBUG_VM #define transparent_hugepage_debug_cow() \ (transparent_hugepage_flags & \ @@ -95,12 +99,14 @@ extern int handle_pte_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *pte, pmd_t *pmd, unsigned int flags); extern int split_huge_page(struct page *page); -extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd); -#define split_huge_page_pmd(__mm, __pmd) \ +extern void __split_huge_page_pmd(struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd); +#define split_huge_page_pmd(__vma, __address, __pmd) \ do { \ pmd_t *____pmd = (__pmd); \ if (unlikely(pmd_trans_huge(*____pmd))) \ - __split_huge_page_pmd(__mm, ____pmd); \ + __split_huge_page_pmd(__vma, __address, \ + ____pmd); \ } while (0) #define wait_split_huge_page(__anon_vma, __pmd) \ do { \ @@ -110,6 +116,8 @@ extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd); BUG_ON(pmd_trans_splitting(*____pmd) || \ pmd_trans_huge(*____pmd)); \ } while (0) +extern void split_huge_page_pmd_mm(struct mm_struct *mm, unsigned long address, + pmd_t *pmd); #if HPAGE_PMD_ORDER > MAX_ORDER #error "hugepages can't be allocated by the buddy allocator" #endif @@ -177,10 +185,12 @@ static inline int split_huge_page(struct page *page) { return 0; } -#define split_huge_page_pmd(__mm, __pmd) \ +#define split_huge_page_pmd(__vma, __address, __pmd) \ do { } while (0) #define wait_split_huge_page(__anon_vma, __pmd) \ do { } while (0) +#define split_huge_page_pmd_mm(__mm, __address, __pmd) \ + do { } while (0) #define compound_trans_head(page) compound_head(page) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 11ddc7ffeba..e98a74c0c9c 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -181,7 +181,14 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, gfp_t gfp_mask, unsigned long *total_scanned); -void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); +void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx); +static inline void mem_cgroup_count_vm_event(struct mm_struct *mm, + enum vm_event_item idx) +{ + if (mem_cgroup_disabled()) + return; + __mem_cgroup_count_vm_event(mm, idx); +} #ifdef CONFIG_TRANSPARENT_HUGEPAGE void mem_cgroup_split_huge_fixup(struct page *head); #endif diff --git a/include/linux/memory.h b/include/linux/memory.h index a09216d0dcc..45e93b46887 100644 --- a/include/linux/memory.h +++ b/include/linux/memory.h @@ -54,6 +54,7 @@ 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/include/linux/mmzone.h b/include/linux/mmzone.h index 0c0b1d608a6..cd55dad56aa 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -460,17 +460,44 @@ struct zone { unsigned long zone_start_pfn; /* - * zone_start_pfn, spanned_pages and present_pages are all - * protected by span_seqlock. It is a seqlock because it has - * to be read outside of zone->lock, and it is done in the main - * allocator path. But, it is written quite infrequently. + * spanned_pages is the total pages spanned by the zone, including + * holes, which is calculated as: + * spanned_pages = zone_end_pfn - zone_start_pfn; * - * The lock is declared along with zone->lock because it is + * present_pages is physical pages existing within the zone, which + * is calculated as: + * present_pages = spanned_pages - absent_pages(pags in holes); + * + * managed_pages is present pages managed by the buddy system, which + * is calculated as (reserved_pages includes pages allocated by the + * bootmem allocator): + * managed_pages = present_pages - reserved_pages; + * + * So present_pages may be used by memory hotplug or memory power + * management logic to figure out unmanaged pages by checking + * (present_pages - managed_pages). And managed_pages should be used + * by page allocator and vm scanner to calculate all kinds of watermarks + * and thresholds. + * + * Locking rules: + * + * zone_start_pfn and spanned_pages are protected by span_seqlock. + * It is a seqlock because it has to be read outside of zone->lock, + * and it is done in the main allocator path. But, it is written + * quite infrequently. + * + * The span_seq lock is declared along with zone->lock because it is |