在书中P18对应的struct结构体 list_head在4.2.5内核里面是这样写的 /linux/list.h 20
page.h 在include/asm-generic/目录下
zone:
#define LIST_HEAD_INIT(name) { &(name), &(name) }
#define LIST_HEAD(name) \
struct list_head name = LIST_HEAD_INIT(name)// LIST_HEAD(name) struct list_head name = { &(name), &(name) }
static inline void INIT_LIST_HEAD(struct list_head *list)
{
list->next = list;
list->prev = list;
}
可以看到,最上面是对struct list_head的初始化,至于为什么要加括号,可以看之前的define定义,&(a+b)与&a+b的区别;
这个文件里还有关于指针的操作,增加,减少,在尾部增加等等各种的链表操作,有兴趣的应该好好看看
list_head 的声明在/linux/types.h 185
struct list_head {
struct list_head *next, *prev;
};
page.h 在include/asm-generic/目录下
struct_page 在include/linux/Mm_types.h里面
/*
* Each physical page in the system has a struct page associated with
* it to keep track of whatever it is we are using the page for at the
* moment. Note that we have no way to track which tasks are using
* a page, though if it is a pagecache page, rmap structures can tell us
* who is mapping it.
*
* The objects in struct page are organized in double word blocks in
* order to allows us to use atomic double word operations on portions
* of struct page. That is currently only used by slub but the arrangement
* allows the use of atomic double word operations on the flags/mapping
* and lru list pointers also.
*/
struct page {
/* First double word block */
unsigned long flags; /* Atomic flags, some possibly
* updated asynchronously */
union {
struct address_space *mapping; /* If low bit clear, points to
* inode address_space, or NULL.
* If page mapped as anonymous
* memory, low bit is set, and
* it points to anon_vma object:
* see PAGE_MAPPING_ANON below.
*/
void *s_mem; /* slab first object */
};
/* Second double word */
struct {
union {
pgoff_t index; /* Our offset within mapping. */
void *freelist; /* sl[aou]b first free object */
};
union {
#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE) && \
defined(CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
/* Used for cmpxchg_double in slub */
unsigned long counters;
#else
/*
* Keep _count separate from slub cmpxchg_double data.
* As the rest of the double word is protected by
* slab_lock but _count is not.
*/
unsigned counters;
#endif
struct {
union {
/*
* Count of ptes mapped in
* mms, to show when page is
* mapped & limit reverse map
* searches.
*
* Used also for tail pages
* refcounting instead of
* _count. Tail pages cannot
* be mapped and keeping the
* tail page _count zero at
* all times guarantees
* get_page_unless_zero() will
* never succeed on tail
* pages.
*/
atomic_t _mapcount;
struct { /* SLUB */
unsigned inuse:16;
unsigned objects:15;
unsigned frozen:1;
};
int units; /* SLOB */
};
atomic_t _count; /* Usage count, see below. */
};
unsigned int active; /* SLAB */
};
};
/* Third double word block */
union {
struct list_head lru; /* Pageout list, eg. active_list
* protected by zone->lru_lock !
* Can be used as a generic list
* by the page owner.
*/
struct { /* slub per cpu partial pages */
struct page *next; /* Next partial slab */
#ifdef CONFIG_64BIT
int pages; /* Nr of partial slabs left */
int pobjects; /* Approximate # of objects */
#else
short int pages;
short int pobjects;
#endif
};
struct slab *slab_page; /* slab fields */
struct rcu_head rcu_head; /* Used by SLAB
* when destroying via RCU
*/
/* First tail page of compound page */
struct {
compound_page_dtor *compound_dtor;
unsigned long compound_order;
};
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
pgtable_t pmd_huge_pte; /* protected by page->ptl */
#endif
};
/* Remainder is not double word aligned */
union {
unsigned long private; /* Mapping-private opaque data:
* usually used for buffer_heads
* if PagePrivate set; used for
* swp_entry_t if PageSwapCache;
* indicates order in the buddy
* system if PG_buddy is set.
*/
#if USE_SPLIT_PTE_PTLOCKS
#if ALLOC_SPLIT_PTLOCKS
spinlock_t *ptl;
#else
spinlock_t ptl;
#endif
#endif
struct kmem_cache *slab_cache; /* SL[AU]B: Pointer to slab */
struct page *first_page; /* Compound tail pages */
};
#ifdef CONFIG_MEMCG
struct mem_cgroup *mem_cgroup;
#endif
/*
* On machines where all RAM is mapped into kernel address space,
* we can simply calculate the virtual address. On machines with
* highmem some memory is mapped into kernel virtual memory
* dynamically, so we need a place to store that address.
* Note that this field could be 16 bits on x86 ... ;)
*
* Architectures with slow multiplication can define
* WANT_PAGE_VIRTUAL in asm/page.h
*/
#if defined(WANT_PAGE_VIRTUAL)
void *virtual; /* Kernel virtual address (NULL if
not kmapped, ie. highmem) */
#endif /* WANT_PAGE_VIRTUAL */
#ifdef CONFIG_KMEMCHECK
/*
* kmemcheck wants to track the status of each byte in a page; this
* is a pointer to such a status block. NULL if not tracked.
*/
void *shadow;
#endif
#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
int _last_cpupid;
#endif
}
跟2.4差了不是一点半点。我的天
free_area:/linux/mmzone.h
struct free_area {
struct list_head free_list[MIGRATE_TYPES];
unsigned long nr_free;
};
zone:
struct zone {
/* Read-mostly fields */
/* zone watermarks, access with *_wmark_pages(zone) macros */
unsigned long watermark[NR_WMARK];
/*
* We don't know if the memory that we're going to allocate will be freeable
* or/and it will be released eventually, so to avoid totally wasting several
* GB of ram we must reserve some of the lower zone memory (otherwise we risk
* to run OOM on the lower zones despite there's tons of freeable ram
* on the higher zones). This array is recalculated at runtime if the
* sysctl_lowmem_reserve_ratio sysctl changes.
*/
long lowmem_reserve[MAX_NR_ZONES];
#ifdef CONFIG_NUMA
int node;
#endif
/*
* The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
* this zone's LRU. Maintained by the pageout code.
*/
unsigned int inactive_ratio;
struct pglist_data *zone_pgdat;
struct per_cpu_pageset __percpu *pageset;
/*
* This is a per-zone reserve of pages that should not be
* considered dirtyable memory.
*/
unsigned long dirty_balance_reserve;
#ifndef CONFIG_SPARSEMEM
/*
* Flags for a pageblock_nr_pages block. See pageblock-flags.h.
* In SPARSEMEM, this map is stored in struct mem_section
*/
unsigned long *pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
#ifdef CONFIG_NUMA
/*
* zone reclaim becomes active if more unmapped pages exist.
*/
unsigned long min_unmapped_pages;
unsigned long min_slab_pages;
#endif /* CONFIG_NUMA */
/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
unsigned long zone_start_pfn;
/*
* spanned_pages is the total pages spanned by the zone, including
* holes, which is calculated as:
* spanned_pages = zone_end_pfn - zone_start_pfn;
*
* present_pages is physical pages existing within the zone, which
* is calculated as:
* present_pages = spanned_pages - absent_pages(pages 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
* frequently read in proximity to zone->lock. It's good to
* give them a chance of being in the same cacheline.
*
* Write access to present_pages at runtime should be protected by
* mem_hotplug_begin/end(). Any reader who can't tolerant drift of
* present_pages should get_online_mems() to get a stable value.
*
* Read access to managed_pages should be safe because it's unsigned
* long. Write access to zone->managed_pages and totalram_pages are
* protected by managed_page_count_lock at runtime. Idealy only
* adjust_managed_page_count() should be used instead of directly
* touching zone->managed_pages and totalram_pages.
*/
unsigned long managed_pages;
unsigned long spanned_pages;
unsigned long present_pages;
const char *name;
/*
* Number of MIGRATE_RESERVE page block. To maintain for just
* optimization. Protected by zone->lock.
*/
int nr_migrate_reserve_block;
#ifdef CONFIG_MEMORY_ISOLATION
/*
* Number of isolated pageblock. It is used to solve incorrect
* freepage counting problem due to racy retrieving migratetype
* of pageblock. Protected by zone->lock.
*/
unsigned long nr_isolate_pageblock;
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
/* see spanned/present_pages for more description */
seqlock_t span_seqlock;
#endif
/*
* wait_table -- the array holding the hash table
* wait_table_hash_nr_entries -- the size of the hash table array
* wait_table_bits -- wait_table_size == (1 << wait_table_bits)
*
* The purpose of all these is to keep track of the people
* waiting for a page to become available and make them
* runnable again when possible. The trouble is that this
* consumes a lot of space, especially when so few things
* wait on pages at a given time. So instead of using
* per-page waitqueues, we use a waitqueue hash table.
*
* The bucket discipline is to sleep on the same queue when
* colliding and wake all in that wait queue when removing.
* When something wakes, it must check to be sure its page is
* truly available, a la thundering herd. The cost of a
* collision is great, but given the expected load of the
* table, they should be so rare as to be outweighed by the
* benefits from the saved space.
*
* __wait_on_page_locked() and unlock_page() in mm/filemap.c, are the
* primary users of these fields, and in mm/page_alloc.c
* free_area_init_core() performs the initialization of them.
*/
wait_queue_head_t *wait_table;
unsigned long wait_table_hash_nr_entries;
unsigned long wait_table_bits;
ZONE_PADDING(_pad1_)
/* free areas of different sizes */
struct free_area free_area[MAX_ORDER];
/* zone flags, see below */
unsigned long flags;
/* Write-intensive fields used from the page allocator */
spinlock_t lock;
ZONE_PADDING(_pad2_)
/* Write-intensive fields used by page reclaim */
/* Fields commonly accessed by the page reclaim scanner */
spinlock_t lru_lock;
struct lruvec lruvec;
/* Evictions & activations on the inactive file list */
atomic_long_t inactive_age;
/*
* When free pages are below this point, additional steps are taken
* when reading the number of free pages to avoid per-cpu counter
* drift allowing watermarks to be breached
*/
unsigned long percpu_drift_mark;
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* pfn where compaction free scanner should start */
unsigned long compact_cached_free_pfn;
/* pfn where async and sync compaction migration scanner should start */
unsigned long compact_cached_migrate_pfn[2];
#endif
#ifdef CONFIG_COMPACTION
/*
* On compaction failure, 1<<compact_defer_shift compactions
* are skipped before trying again. The number attempted since
* last failure is tracked with compact_considered.
*/
unsigned int compact_considered;
unsigned int compact_defer_shift;
int compact_order_failed;
#endif
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/* Set to true when the PG_migrate_skip bits should be cleared */
bool compact_blockskip_flush;
#endif
ZONE_PADDING(_pad3_)
/* Zone statistics */
atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
} ____cacheline_internodealigned_in_smp;
再来看看现在的do_page_fault /arch/x86/mm/fault.c
dotraplinkage void notrace
do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
unsigned long address = read_cr2(); /* Get the faulting address */
enum ctx_state prev_state;
/*
* We must have this function tagged with __kprobes, notrace and call
* read_cr2() before calling anything else. To avoid calling any kind
* of tracing machinery before we've observed the CR2 value.
*
* exception_{enter,exit}() contain all sorts of tracepoints.
*/
prev_state = exception_enter();
__do_page_fault(regs, error_code, address);
exception_exit(prev_state);
}
里面有个__do_page_fault
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
*
* This function must have noinline because both callers
* {,trace_}do_page_fault() have notrace on. Having this an actual function
* guarantees there's a function trace entry.
*/
static noinline void
__do_page_fault(struct pt_regs *regs, unsigned long error_code,
unsigned long address)
{
struct vm_area_struct *vma;
struct task_struct *tsk;
struct mm_struct *mm;
int fault, major = 0;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
tsk = current;
mm = tsk->mm;
/*
* Detect and handle instructions that would cause a page fault for
* both a tracked kernel page and a userspace page.
*/
if (kmemcheck_active(regs))
kmemcheck_hide(regs);
prefetchw(&mm->mmap_sem);
if (unlikely(kmmio_fault(regs, address)))
return;
/*
* We fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
*
* NOTE! We MUST NOT take any locks for this case. We may
* be in an interrupt or a critical region, and should
* only copy the information from the master page table,
* nothing more.
*
* This verifies that the fault happens in kernel space
* (error_code & 4) == 0, and that the fault was not a
* protection error (error_code & 9) == 0.
*/
if (unlikely(fault_in_kernel_space(address))) {
if (!(error_code & (PF_RSVD | PF_USER | PF_PROT))) {
if (vmalloc_fault(address) >= 0)
return;
if (kmemcheck_fault(regs, address, error_code))
return;
}
/* Can handle a stale RO->RW TLB: */
if (spurious_fault(error_code, address))
return;
/* kprobes don't want to hook the spurious faults: */
if (kprobes_fault(regs))
return;
/*
* Don't take the mm semaphore here. If we fixup a prefetch
* fault we could otherwise deadlock:
*/
bad_area_nosemaphore(regs, error_code, address);
return;
}
/* kprobes don't want to hook the spurious faults: */
if (unlikely(kprobes_fault(regs)))
return;
if (unlikely(error_code & PF_RSVD))
pgtable_bad(regs, error_code, address);
if (unlikely(smap_violation(error_code, regs))) {
bad_area_nosemaphore(regs, error_code, address);
return;
}
/*
* If we're in an interrupt, have no user context or are running
* in a region with pagefaults disabled then we must not take the fault
*/
if (unlikely(faulthandler_disabled() || !mm)) {
bad_area_nosemaphore(regs, error_code, address);
return;
}
/*
* It's safe to allow irq's after cr2 has been saved and the
* vmalloc fault has been handled.
*
* User-mode registers count as a user access even for any
* potential system fault or CPU buglet:
*/
if (user_mode(regs)) {
local_irq_enable();
error_code |= PF_USER;
flags |= FAULT_FLAG_USER;
} else {
if (regs->flags & X86_EFLAGS_IF)
local_irq_enable();
}
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
if (error_code & PF_WRITE)
flags |= FAULT_FLAG_WRITE;
/*
* When running in the kernel we expect faults to occur only to
* addresses in user space. All other faults represent errors in
* the kernel and should generate an OOPS. Unfortunately, in the
* case of an erroneous fault occurring in a code path which already
* holds mmap_sem we will deadlock attempting to validate the fault
* against the address space. Luckily the kernel only validly
* references user space from well defined areas of code, which are
* listed in the exceptions table.
*
* As the vast majority of faults will be valid we will only perform
* the source reference check when there is a possibility of a
* deadlock. Attempt to lock the address space, if we cannot we then
* validate the source. If this is invalid we can skip the address
* space check, thus avoiding the deadlock:
*/
if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
if ((error_code & PF_USER) == 0 &&
!search_exception_tables(regs->ip)) {
bad_area_nosemaphore(regs, error_code, address);
return;
}
retry:
down_read(&mm->mmap_sem);
} else {
/*
* The above down_read_trylock() might have succeeded in
* which case we'll have missed the might_sleep() from
* down_read():
*/
might_sleep();
}
vma = find_vma(mm, address);
if (unlikely(!vma)) {
bad_area(regs, error_code, address);
return;
}
if (likely(vma->vm_start <= address))
goto good_area;
if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
bad_area(regs, error_code, address);
return;
}
if (error_code & PF_USER) {
/*
* Accessing the stack below %sp is always a bug.
* The large cushion allows instructions like enter
* and pusha to work. ("enter $65535, $31" pushes
* 32 pointers and then decrements %sp by 65535.)
*/
if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) {
bad_area(regs, error_code, address);
return;
}
}
if (unlikely(expand_stack(vma, address))) {
bad_area(regs, error_code, address);
return;
}
/*
* Ok, we have a good vm_area for this memory access, so
* we can handle it..
*/
good_area:
if (unlikely(access_error(error_code, vma))) {
bad_area_access_error(regs, error_code, address);
return;
}
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault. Since we never set FAULT_FLAG_RETRY_NOWAIT, if
* we get VM_FAULT_RETRY back, the mmap_sem has been unlocked.
*/
fault = handle_mm_fault(mm, vma, address, flags);
major |= fault & VM_FAULT_MAJOR;
/*
* If we need to retry the mmap_sem has already been released,
* and if there is a fatal signal pending there is no guarantee
* that we made any progress. Handle this case first.
*/
if (unlikely(fault & VM_FAULT_RETRY)) {
/* Retry at most once */
if (flags & FAULT_FLAG_ALLOW_RETRY) {
flags &= ~FAULT_FLAG_ALLOW_RETRY;
flags |= FAULT_FLAG_TRIED;
if (!fatal_signal_pending(tsk))
goto retry;
}
/* User mode? Just return to handle the fatal exception */
if (flags & FAULT_FLAG_USER)
return;
/* Not returning to user mode? Handle exceptions or die: */
no_context(regs, error_code, address, SIGBUS, BUS_ADRERR);
return;
}
up_read(&mm->mmap_sem);
if (unlikely(fault & VM_FAULT_ERROR)) {
mm_fault_error(regs, error_code, address, fault);
return;
}
/*
* Major/minor page fault accounting. If any of the events
* returned VM_FAULT_MAJOR, we account it as a major fault.
*/
if (major) {
tsk->maj_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs, address);
} else {
tsk->min_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs, address);
}
check_v8086_mode(regs, address, tsk);
}
之后的expand_stack在/mm/mmap.c文件中
int expand_stack(struct vm_area_struct *vma, unsigned long address)
{
struct vm_area_struct *prev;
address &= PAGE_MASK;
prev = vma->vm_prev;
if (prev && prev->vm_end == address) {
if (!(prev->vm_flags & VM_GROWSDOWN))
return -ENOMEM;
}
return expand_downwards(vma, address);
}