litmus-rt.git - The LITMUS^RT kernel.

diff options

author	Michael Holzheu <holzheu@linux.vnet.ibm.com>	2012-03-11 11:59:34 -0400
committer	Martin Schwidefsky <schwidefsky@de.ibm.com>	2012-03-11 11:59:29 -0400
commit	4857d4bbe9821c8d732cb84455e18e12b3d79add (patch)
tree	54583e3ef5c84c04f92b7b15ea6aad8224781d9b /tools/perf/scripts/python/net_dropmonitor.py
parent	ad252ffa2a0fbb1f37e81688322034b3af037cee (diff)

[S390] kernel: Add OS info memory interface

In order to allow kdump based stand-alone dump, some information has to be passed from the old kernel to the new dump kernel. This is done via a the struct "os_info" that contains the following fields: * crashkernel base and size * reipl block * vmcoreinfo * init function A pointer to os_info is stored at a well known storage location and the whole structure as well as all fields are secured with checksums. Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

Diffstat (limited to 'tools/perf/scripts/python/net_dropmonitor.py')

0 files changed, 0 insertions, 0 deletions

#ifndef _LINUX_MM_H #define _LINUX_MM_H #include <linux/errno.h> #ifdef __KERNEL__ #include <linux/gfp.h> #include <linux/bug.h> #include <linux/list.h> #include <linux/mmzone.h> #include <linux/rbtree.h> #include <linux/atomic.h> #include <linux/debug_locks.h> #include <linux/mm_types.h> #include <linux/range.h> #include <linux/pfn.h> #include <linux/bit_spinlock.h> #include <linux/shrinker.h> struct mempolicy; struct anon_vma; struct anon_vma_chain; struct file_ra_state; struct user_struct; struct writeback_control; #ifndef CONFIG_DISCONTIGMEM /* Don't use mapnrs, do it properly */ extern unsigned long max_mapnr; #endif extern unsigned long num_physpages; extern unsigned long totalram_pages; extern void * high_memory; extern int page_cluster; #ifdef CONFIG_SYSCTL extern int sysctl_legacy_va_layout; #else #define sysctl_legacy_va_layout 0 #endif #include <asm/page.h> #include <asm/pgtable.h> #include <asm/processor.h> extern unsigned long sysctl_user_reserve_kbytes; extern unsigned long sysctl_admin_reserve_kbytes; #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n)) /* to align the pointer to the (next) page boundary */ #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE) /* * Linux kernel virtual memory manager primitives. * The idea being to have a "virtual" mm in the same way * we have a virtual fs - giving a cleaner interface to the * mm details, and allowing different kinds of memory mappings * (from shared memory to executable loading to arbitrary * mmap() functions). */ extern struct kmem_cache *vm_area_cachep; #ifndef CONFIG_MMU extern struct rb_root nommu_region_tree; extern struct rw_semaphore nommu_region_sem; extern unsigned int kobjsize(const void *objp); #endif /* * vm_flags in vm_area_struct, see mm_types.h. */ #define VM_NONE 0x00000000 #define VM_READ 0x00000001 /* currently active flags */ #define VM_WRITE 0x00000002 #define VM_EXEC 0x00000004 #define VM_SHARED 0x00000008 /* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */ #define VM_MAYREAD 0x00000010 /* limits for mprotect() etc */ #define VM_MAYWRITE 0x00000020 #define VM_MAYEXEC 0x00000040 #define VM_MAYSHARE 0x00000080 #define VM_GROWSDOWN 0x00000100 /* general info on the segment */ #define VM_PFNMAP 0x00000400 /* Page-ranges managed without "struct page", just pure PFN */ #define VM_DENYWRITE 0x00000800 /* ETXTBSY on write attempts.. */ #define VM_LOCKED 0x00002000 #define VM_IO 0x00004000 /* Memory mapped I/O or similar */ /* Used by sys_madvise() */ #define VM_SEQ_READ 0x00008000 /* App will access data sequentially */ #define VM_RAND_READ 0x00010000 /* App will not benefit from clustered reads */ #define VM_DONTCOPY 0x00020000 /* Do not copy this vma on fork */ #define VM_DONTEXPAND 0x00040000 /* Cannot expand with mremap() */ #define VM_ACCOUNT 0x00100000 /* Is a VM accounted object */ #define VM_NORESERVE 0x00200000 /* should the VM suppress accounting */ #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_ARCH_1 0x01000000 /* Architecture-specific flag */ #define VM_DONTDUMP 0x04000000 /* Do not include in the core dump */ #define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */ #define VM_HUGEPAGE 0x20000000 /* MADV_HUGEPAGE marked this vma */ #define VM_NOHUGEPAGE 0x40000000 /* MADV_NOHUGEPAGE marked this vma */ #define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */ #if defined(CONFIG_X86) # define VM_PAT VM_ARCH_1 /* PAT reserves whole VMA at once (x86) */ #elif defined(CONFIG_PPC) # define VM_SAO VM_ARCH_1 /* Strong Access Ordering (powerpc) */ #elif defined(CONFIG_PARISC) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_METAG) # define VM_GROWSUP VM_ARCH_1 #elif defined(CONFIG_IA64) # define VM_GROWSUP VM_ARCH_1 #elif !defined(CONFIG_MMU) # define VM_MAPPED_COPY VM_ARCH_1 /* T if mapped copy of data (nommu mmap) */ #endif #ifndef VM_GROWSUP # define VM_GROWSUP VM_NONE #endif /* Bits set in the VMA until the stack is in its final location */ #define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ) #ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */ #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS #endif #ifdef CONFIG_STACK_GROWSUP #define VM_STACK_FLAGS (VM_GROWSUP | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) #else #define VM_STACK_FLAGS (VM_GROWSDOWN | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT) #endif #define VM_READHINTMASK (VM_SEQ_READ | VM_RAND_READ) #define VM_ClearReadHint(v) (v)->vm_flags &= ~VM_READHINTMASK #define VM_NormalReadHint(v) (!((v)->vm_flags & VM_READHINTMASK)) #define VM_SequentialReadHint(v) ((v)->vm_flags & VM_SEQ_READ) #define VM_RandomReadHint(v) ((v)->vm_flags & VM_RAND_READ) /* * Special vmas that are non-mergable, non-mlock()able. * Note: mm/huge_memory.c VM_NO_THP depends on this definition. */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP) /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. */ extern pgprot_t protection_map[16]; #define FAULT_FLAG_WRITE 0x01 /* Fault was a write access */ #define FAULT_FLAG_NONLINEAR 0x02 /* Fault was via a nonlinear mapping */ #define FAULT_FLAG_MKWRITE 0x04 /* Fault was mkwrite of existing pte */ #define FAULT_FLAG_ALLOW_RETRY 0x08 /* Retry fault if blocking */ #define FAULT_FLAG_RETRY_NOWAIT 0x10 /* Don't drop mmap_sem and wait when retrying */ #define FAULT_FLAG_KILLABLE 0x20 /* The fault task is in SIGKILL killable region */ #define FAULT_FLAG_TRIED 0x40 /* second try */ /* * vm_fault is filled by the the pagefault handler and passed to the vma's * ->fault function. The vma's ->fault is responsible for returning a bitmask * of VM_FAULT_xxx flags that give details about how the fault was handled. * * pgoff should be used in favour of virtual_address, if possible. If pgoff * is used, one may implement ->remap_pages to get nonlinear mapping support. */ struct vm_fault { unsigned int flags; /* FAULT_FLAG_xxx flags */ pgoff_t pgoff; /* Logical page offset based on vma */ void __user *virtual_address; /* Faulting virtual address */ struct page *page; /* ->fault handlers should return a * page here, unless VM_FAULT_NOPAGE * is set (which is also implied by * VM_FAULT_ERROR). */ }; /* * These are the virtual MM functions - opening of an area, closing and * unmapping it (needed to keep files on disk up-to-date etc), pointer * to the functions called when a no-page or a wp-page exception occurs. */ struct vm_operations_struct { void (*open)(struct vm_area_struct * area); void (*close)(struct vm_area_struct * area); int (*fault)(struct vm_area_struct *vma, struct vm_fault *vmf); /* notification that a previously read-only page is about to become * writable, if an error is returned it will cause a SIGBUS */ int (*page_mkwrite)(struct vm_area_struct *vma, struct vm_fault *vmf); /* called by access_process_vm when get_user_pages() fails, typically * for use by special VMAs that can switch between memory and hardware */ int (*access)(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write); #ifdef CONFIG_NUMA /* * set_policy() op must add a reference to any non-NULL @new mempolicy * to hold the policy upon return. Caller should pass NULL @new to * remove a policy and fall back to surrounding context--i.e. do not * install a MPOL_DEFAULT policy, nor the task or system default * mempolicy. */ int (*set_policy)(struct vm_area_struct *vma, struct mempolicy *new); /* * get_policy() op must add reference [mpol_get()] to any policy at * (vma,addr) marked as MPOL_SHARED. The shared policy infrastructure * in mm/mempolicy.c will do this automatically. * get_policy() must NOT add a ref if the policy at (vma,addr) is not * marked as MPOL_SHARED. vma policies are protected by the mmap_sem. * If no [shared/vma] mempolicy exists at the addr, get_policy() op * must return NULL--i.e., do not "fallback" to task or system default * policy. */ struct mempolicy *(*get_policy)(struct vm_area_struct *vma, unsigned long addr); int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from, const nodemask_t *to, unsigned long flags); #endif /* called by sys_remap_file_pages() to populate non-linear mapping */ int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr, unsigned long size, pgoff_t pgoff); }; struct mmu_gather; struct inode; #define page_private(page) ((page)->private) #define set_page_private(page, v) ((page)->private = (v)) /* It's valid only if the page is free path or free_list */ static inline void set_freepage_migratetype(struct page *page, int migratetype) { page->index = migratetype; } /* It's valid only if the page is free path or free_list */ static inline int get_freepage_migratetype(struct page *page) { return page->index; } /* * FIXME: take this include out, include page-flags.h in * files which need it (119 of them) */ #include <linux/page-flags.h> #include <linux/huge_mm.h> /* * Methods to modify the page usage count. * * What counts for a page usage: * - cache mapping (page->mapping) * - private data (page->private) * - page mapped in a task's page tables, each mapping * is counted separately * * Also, many kernel routines increase the page count before a critical * routine so they can be sure the page doesn't go away from under them. */ /* * Drop a ref, return true if the refcount fell to zero (the page has no users) */ static inline int put_page_testzero(struct page *page) { VM_BUG_ON(atomic_read(&page->_count) == 0); return atomic_dec_and_test(&page->_count); } /* * Try to grab a ref unless the page has a refcount of zero, return false if * that is the case. */ static inline int get_page_unless_zero(struct page *page) { return atomic_inc_not_zero(&page->_count); } extern int page_is_ram(unsigned long pfn); /* Support for virtually mapped pages */ struct page *vmalloc_to_page(const void *addr); unsigned long vmalloc_to_pfn(const void *addr); /* * Determine if an address is within the vmalloc range * * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there * is no special casing required. */ static inline int is_vmalloc_addr(const void *x) { #ifdef CONFIG_MMU unsigned long addr = (unsigned long)x; return addr >= VMALLOC_START && addr < VMALLOC_END; #else return 0; #endif } #ifdef CONFIG_MMU extern int is_vmalloc_or_module_addr(const void *x); #else static inline int is_vmalloc_or_module_addr(const void *x) { return 0; } #endif static inline void compound_lock(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE VM_BUG_ON(PageSlab(page)); bit_spin_lock(PG_compound_lock, &page->flags); #endif } static inline void compound_unlock(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE VM_BUG_ON(PageSlab(page)); bit_spin_unlock(PG_compound_lock, &page->flags); #endif } static inline unsigned long compound_lock_irqsave(struct page *page) { unsigned long uninitialized_var(flags); #ifdef CONFIG_TRANSPARENT_HUGEPAGE local_irq_save(flags); compound_lock(page); #endif return flags; } static inline void compound_unlock_irqrestore(struct page *page, unsigned long flags) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE compound_unlock(page); local_irq_restore(flags); #endif } static inline struct page *compound_head(struct page *page) { if (unlikely(PageTail(page))) return page->first_page; return page; } /* * The atomic page->_mapcount, starts from -1: so that transitions * both from it and to it can be tracked, using atomic_inc_and_test * and atomic_add_negative(-1). */ static inline void page_mapcount_reset(struct page *page) { atomic_set(&(page)->_mapcount, -1); } static inline int page_mapcount(struct page *page) { return atomic_read(&(page)->_mapcount) + 1; } static inline int page_count(struct page *page) { return atomic_read(&compound_head(page)->_count); } static inline void get_huge_page_tail(struct page *page) { /* * __split_huge_page_refcount() cannot run * from under us. */ VM_BUG_ON(page_mapcount(page) < 0); VM_BUG_ON(atomic_read(&page->_count) != 0); atomic_inc(&page->_mapcount); } extern bool __get_page_tail(struct page *page); static inline void get_page(struct page *page) { if (unlikely(PageTail(page))) if (likely(__get_page_tail(page))) return; /* * Getting a normal page or the head of a compound page * requires to already have an elevated page->_count. */ VM_BUG_ON(atomic_read(&page->_count) <= 0); atomic_inc(&page->_count); } static inline struct page *virt_to_head_page(const void *x) { struct page *page = virt_to_page(x); return compound_head(page); } /* * Setup the page count before being freed into the page allocator for * the first time (boot or memory hotplug) */ static inline void init_page_count(struct page *page) { atomic_set(&page->_count, 1); } /* * PageBuddy() indicate that the page is free and in the buddy system * (see mm/page_alloc.c). * * PAGE_BUDDY_MAPCOUNT_VALUE must be <= -2 but better not too close to * -2 so that an underflow of the page_mapcount() won't be mistaken * for a genuine PAGE_BUDDY_MAPCOUNT_VALUE. -128 can be created very * efficiently by most CPU architectures. */ #define PAGE_BUDDY_MAPCOUNT_VALUE (-128) static inline int PageBuddy(struct page *page) { return atomic_read(&page->_mapcount) == PAGE_BUDDY_MAPCOUNT_VALUE; } static inline void __SetPageBuddy(struct page *page) { VM_BUG_ON(atomic_read(&page->_mapcount) != -1); atomic_set(&page->_mapcount, PAGE_BUDDY_MAPCOUNT_VALUE); } static inline void __ClearPageBuddy(struct page *page) { VM_BUG_ON(!PageBuddy(page)); atomic_set(&page->_mapcount, -1); } void put_page(struct page *page); void put_pages_list(struct list_head *pages); void split_page(struct page *page, unsigned int order); int split_free_page(struct page *page); /* * Compound pages have a destructor function. Provide a * prototype for that function and accessor functions. * These are _only_ valid on the head of a PG_compound page. */ typedef void compound_page_dtor(struct page *); static inline void set_compound_page_dtor(struct page *page, compound_page_dtor *dtor) { page[1].lru.next = (void *)dtor; } static inline compound_page_dtor *get_compound_page_dtor(struct page *page) { return (compound_page_dtor *)page[1].lru.next; } static inline int compound_order(struct page *page) { if (!PageHead(page)) return 0; return (unsigned long)page[1].lru.prev; } static inline int compound_trans_order(struct page *page) { int order; unsigned long flags; if (!PageHead(page)) return 0; flags = compound_lock_irqsave(page); order = compound_order(page); compound_unlock_irqrestore(page, flags); return order; } static inline void set_compound_order(struct page *page, unsigned long order) { page[1].lru.prev = (void *)order; } #ifdef CONFIG_MMU /* * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when * servicing faults for write access. In the normal case, do always want * pte_mkwrite. But get_user_pages can cause write faults for mappings * that do not have writing enabled, when used by access_process_vm. */ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pte = pte_mkwrite(pte); return pte; } #endif /* * Multiple processes may "see" the same page. E.g. for untouched * mappings of /dev/null, all processes see the same page full of * zeroes, and text pages of executables and shared libraries have * only one copy in memory, at most, normally. * * For the non-reserved pages, page_count(page) denotes a reference count. * page_count() == 0 means the page is free. page->lru is then used for * freelist management in the buddy allocator. * page_count() > 0 means the page has been allocated. * * Pages are allocated by the slab allocator in order to provide memory * to kmalloc and kmem_cache_alloc. In this case, the management of the * page, and the fields in 'struct page' are the responsibility of mm/slab.c * unless a particular usage is carefully commented. (the responsibility of * freeing the kmalloc memory is the caller's, of course). * * A page may be used by anyone else who does a __get_free_page(). * In this case, page_count still tracks the references, and should only * be used through the normal accessor functions. The top bits of page->flags * and page->virtual store page management information, but all other fields * are unused and could be used privately, carefully. The management of this * page is the responsibility of the one who allocated it, and those who have * subsequently been given references to it. * * The other pages (we may call them "pagecache pages") are completely * managed by the Linux memory manager: I/O, buffers, swapping etc. * The following discussion applies only to them. * * A pagecache page contains an opaque `private' member, which belongs to the * page's address_space. Usually, this is the address of a circular list of * the page's disk buffers. PG_private must be set to tell the VM to call * into the filesystem to release these pages. * * A page may belong to an inode's memory mapping. In this case, page->mapping * is the pointer to the inode, and page->index is the file offset of the page, * in units of PAGE_CACHE_SIZE. * * If pagecache pages are not associated with an inode, they are said to be * anonymous pages. These may become associated with the swapcache, and in that * case PG_swapcache is set, and page->private is an offset into the swapcache. * * In either case (swapcache or inode backed), the pagecache itself holds one * reference to the page. Setting PG_private should also increment the * refcount. The each user mapping also has a reference to the page. * * The pagecache pages are stored in a per-mapping radix tree, which is * rooted at mapping->page_tree, and indexed by offset. * Where 2.4 and early 2.6 kernels kept dirty/clean pages in per-address_space * lists, we instead now tag pages as dirty/writeback in the radix tree. * * All pagecache pages may be subject to I/O: * - inode pages may need to be read from disk, * - inode pages which have been modified and are MAP_SHARED may need * to be written back to the inode on disk, * - anonymous pages (including MAP_PRIVATE file mappings) which have been * modified may need to be swapped out to swap space and (later) to be read * back into memory. */ /* * The zone field is never updated after free_area_init_core() * sets it, so none of the operations on it need to be atomic. */ /* Page flags: | [SECTION] | [NODE] | ZONE | [LAST_NID] | ... | FLAGS | */ #define SECTIONS_PGOFF ((sizeof(unsigned long)*8) - SECTIONS_WIDTH) #define NODES_PGOFF (SECTIONS_PGOFF - NODES_WIDTH) #define ZONES_PGOFF (NODES_PGOFF - ZONES_WIDTH) #define LAST_NID_PGOFF (ZONES_PGOFF - LAST_NID_WIDTH) /* * Define the bit shifts to access each section. For non-existent * sections we define the shift as 0; that plus a 0 mask ensures * the compiler will optimise away reference to them. */ #define SECTIONS_PGSHIFT (SECTIONS_PGOFF * (SECTIONS_WIDTH != 0)) #define NODES_PGSHIFT (NODES_PGOFF * (NODES_WIDTH != 0)) #define ZONES_PGSHIFT (ZONES_PGOFF * (ZONES_WIDTH != 0)) #define LAST_NID_PGSHIFT (LAST_NID_PGOFF * (LAST_NID_WIDTH != 0)) /* NODE:ZONE or SECTION:ZONE is used to ID a zone for the buddy allocator */ #ifdef NODE_NOT_IN_PAGE_FLAGS #define ZONEID_SHIFT (SECTIONS_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((SECTIONS_PGOFF < ZONES_PGOFF)? \ SECTIONS_PGOFF : ZONES_PGOFF) #else #define ZONEID_SHIFT (NODES_SHIFT + ZONES_SHIFT) #define ZONEID_PGOFF ((NODES_PGOFF < ZONES_PGOFF)? \ NODES_PGOFF : ZONES_PGOFF) #endif #define ZONEID_PGSHIFT (ZONEID_PGOFF * (ZONEID_SHIFT != 0)) #if SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS #error SECTIONS_WIDTH+NODES_WIDTH+ZONES_WIDTH > BITS_PER_LONG - NR_PAGEFLAGS #endif #define ZONES_MASK ((1UL << ZONES_WIDTH) - 1) #define NODES_MASK ((1UL << NODES_WIDTH) - 1) #define SECTIONS_MASK ((1UL << SECTIONS_WIDTH) - 1) #define LAST_NID_MASK ((1UL << LAST_NID_WIDTH) - 1) #define ZONEID_MASK ((1UL << ZONEID_SHIFT) - 1) static inline enum zone_type page_zonenum(const struct page *page) { return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK; } #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP) #define SECTION_IN_PAGE_FLAGS #endif /* * The identification function is only used by the buddy allocator for * determining if two pages could be buddies. We are not really * identifying a zone since we could be using a the section number * id if we have not node id available in page flags. * We guarantee only that it will return the same value for two * combinable pages in a zone. */ static inline int page_zone_id(struct page *page) { return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK; } static inline int zone_to_nid(struct zone *zone) { #ifdef CONFIG_NUMA return zone->node; #else return 0; #endif } #ifdef NODE_NOT_IN_PAGE_FLAGS extern int page_to_nid(const struct page *page); #else static inline int page_to_nid(const struct page *page) { return (page->flags >> NODES_PGSHIFT) & NODES_MASK; } #endif #ifdef CONFIG_NUMA_BALANCING #ifdef LAST_NID_NOT_IN_PAGE_FLAGS static inline int page_nid_xchg_last(struct page *page, int nid) { return xchg(&page->_last_nid, nid); } static inline int page_nid_last(struct page *page) { return page->_last_nid; } static inline void page_nid_reset_last(struct page *page) { page->_last_nid = -1; } #else static inline int page_nid_last(struct page *page) { return (page->flags >> LAST_NID_PGSHIFT) & LAST_NID_MASK; } extern int page_nid_xchg_last(struct page *page, int nid); static inline void page_nid_reset_last(struct page *page) { int nid = (1 << LAST_NID_SHIFT) - 1; page->flags &= ~(LAST_NID_MASK << LAST_NID_PGSHIFT); page->flags |= (nid & LAST_NID_MASK) << LAST_NID_PGSHIFT; } #endif /* LAST_NID_NOT_IN_PAGE_FLAGS */ #else static inline int page_nid_xchg_last(struct page *page, int nid) { return page_to_nid(page); } static inline int page_nid_last(struct page *page) { return page_to_nid(page); } static inline void page_nid_reset_last(struct page *page) { } #endif static inline struct zone *page_zone(const struct page *page) { return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)]; } #ifdef SECTION_IN_PAGE_FLAGS static inline void set_page_section(struct page *page, unsigned long section) { page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT); page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } static inline unsigned long page_to_section(const struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } #endif static inline void set_page_zone(struct page *page, enum zone_type zone) { page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT); page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT; } static inline void set_page_node(struct page *page, unsigned long node) { page->flags &= ~(NODES_MASK << NODES_PGSHIFT); page->flags |= (node & NODES_MASK) << NODES_PGSHIFT; } static inline void set_page_links(struct page *page, enum zone_type zone, unsigned long node, unsigned long pfn) { set_page_zone(page, zone); set_page_node(page, node); #ifdef SECTION_IN_PAGE_FLAGS set_page_section(page, pfn_to_section_nr(pfn)); #endif } /* * Some inline functions in vmstat.h depend on page_zone() */ #include <linux/vmstat.h> static __always_inline void *lowmem_page_address(const struct page *page) { return __va(PFN_PHYS(page_to_pfn(page))); } #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) #define HASHED_PAGE_VIRTUAL #endif #if defined(WANT_PAGE_VIRTUAL) #define page_address(page) ((page)->virtual) #define set_page_address(page, address) \ do { \ (page)->virtual = (address); \ } while(0) #define page_address_init() do { } while(0) #endif #if defined(HASHED_PAGE_VIRTUAL) void *page_address(const struct page *page); void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL) #define page_address(page) lowmem_page_address(page) #define set_page_address(page, address) do { } while(0) #define page_address_init() do { } while(0) #endif /* * On an anonymous page mapped into a user virtual memory area, * page->mapping points to its anon_vma, not to a struct address_space; * with the PAGE_MAPPING_ANON bit set to distinguish it. See rmap.h. * * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled, * the PAGE_MAPPING_KSM bit may be set along with the PAGE_MAPPING_ANON bit; * and then page->mapping points, not to an anon_vma, but to a private * structure which KSM associates with that merged page. See ksm.h. * * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is currently never used. * * Please note that, confusingly, "page_mapping" refers to the inode * address_space which maps the page from disk; whereas "page_mapped" * refers to user virtual address space into which the page is mapped. */ #define PAGE_MAPPING_ANON 1 #define PAGE_MAPPING_KSM 2 #define PAGE_MAPPING_FLAGS (PAGE_MAPPING_ANON | PAGE_MAPPING_KSM) extern struct address_space *page_mapping(struct page *page); /* Neutral page->mapping pointer to address_space or anon_vma or other */ static inline void *page_rmapping(struct page *page) { return (void *)((unsigned long)page->mapping & ~PAGE_MAPPING_FLAGS); } extern struct address_space *__page_file_mapping(struct page *); static inline struct address_space *page_file_mapping(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_mapping(page); return page->mapping; } static inline int PageAnon(struct page *page) { return ((unsigned long)page->mapping & PAGE_MAPPING_ANON) != 0; } /* * Return the pagecache index of the passed page. Regular pagecache pages * use ->index whereas swapcache pages use ->private */ static inline pgoff_t page_index(struct page *page) { if (unlikely(PageSwapCache(page))) return page_private(page); return page->index; } extern pgoff_t __page_file_index(struct page *page); /* * Return the file index of the page. Regular pagecache pages use ->index * whereas swapcache pages use swp_offset(->private) */ static inline pgoff_t page_file_index(struct page *page) { if (unlikely(PageSwapCache(page))) return __page_file_index(page); return page->index; } /* * Return true if this page is mapped into pagetables. */ static inline int page_mapped(struct page *page) { return atomic_read(&(page)->_mapcount) >= 0; } /* * Different kinds of faults, as returned by handle_mm_fault(). * Used to decide whether a process gets delivered SIGBUS or * just gets major/minor fault counters bumped up. */ #define VM_FAULT_MINOR 0 /* For backwards compat. Remove me quickly. */ #define VM_FAULT_OOM 0x0001 #define VM_FAULT_SIGBUS 0x0002 #define VM_FAULT_MAJOR 0x0004 #define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */ #define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned small page */ #define VM_FAULT_HWPOISON_LARGE 0x0020 /* Hit poisoned large page. Index encoded in upper bits */ #define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */ #define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */ #define VM_FAULT_RETRY 0x0400 /* ->fault blocked, must retry */ #define VM_FAULT_HWPOISON_LARGE_MASK 0xf000 /* encodes hpage index for large hwpoison */ #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | \ VM_FAULT_HWPOISON_LARGE) /* Encode hstate index for a hwpoisoned large page */ #define VM_FAULT_SET_HINDEX(x) ((x) << 12) #define VM_FAULT_GET_HINDEX(x) (((x) >> 12) & 0xf) /* * Can be called by the pagefault handler when it gets a VM_FAULT_OOM. */ extern void pagefault_out_of_memory(void); #define offset_in_page(p) ((unsigned long)(p) & ~PAGE_MASK) /* * Flags passed to show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ #define SHOW_MEM_FILTER_PAGE_COUNT (0x0002u) /* page type count */ extern void show_free_areas(unsigned int flags); extern bool skip_free_areas_node(unsigned int flags, int nid); int shmem_zero_setup(struct vm_area_struct *); extern int can_do_mlock(void); extern int user_shm_lock(size_t, struct user_struct *); extern void user_shm_unlock(size_t, struct user_struct *); /* * Parameter block passed down to zap_pte_range in exceptional cases. */ struct zap_details { struct vm_area_struct *nonlinear_vma; /* Check page->index if set */ struct address_space *check_mapping; /* Check page->mapping if set */ pgoff_t first_index; /* Lowest page->index to unmap */ pgoff_t last_index; /* Highest page->index to unmap */ }; struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); void zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *); void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long start, unsigned long end); /** * mm_walk - callbacks for walk_page_range * @pgd_entry: if set, called for each non-empty PGD (top-level) entry * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry * this handler is required to be able to handle * pmd_trans_huge() pmds. They may simply choose to * split_huge_page() instead of handling it explicitly. * @pte_entry: if set, called for each non-empty PTE (4th-level) entry * @pte_hole: if set, called for each hole at all levels * @hugetlb_entry: if set, called for each hugetlb entry * *Caution*: The caller must hold mmap_sem() if @hugetlb_entry * is used. * * (see walk_page_range for more details) */ struct mm_walk { int (*pgd_entry)(pgd_t *pgd, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pud_entry)(pud_t *pud, unsigned long addr, unsigned long next, struct mm_walk *walk); int (*pmd_entry)(pmd_t *pmd, unsigned long addr,


context:
space:
mode: