Linux内核源代码情景分析笔记---对照4.2.5内核 续

/*
* These routines also need to handle stuff like marking pages dirty
* and/or accessed for architectures that don't do it in hardware (most
* RISC architectures).  The early dirtying is also good on the i386.
*
* There is also a hook called "update_mmu_cache()" that architectures
* with external mmu caches can use to update those (ie the Sparc or
* PowerPC hashed page tables that act as extended TLBs).
*
* We enter with non-exclusive mmap_sem (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with pte unmapped and unlocked.
*
* The mmap_sem may have been released depending on flags and our
* return value.  See filemap_fault() and __lock_page_or_retry().
*/
static 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)
{
pte_t entry;
spinlock_t *ptl;

/*
* some architectures can have larger ptes than wordsize,
* e.g.ppc44x-defconfig has CONFIG_PTE_64BIT=y and CONFIG_32BIT=y,
* so READ_ONCE or ACCESS_ONCE cannot guarantee atomic accesses.
* The code below just needs a consistent view for the ifs and
* we later double check anyway with the ptl lock held. So here
* a barrier will do.
*/
entry = *pte;
barrier();
if (!pte_present(entry)) {
if (pte_none(entry)) {
if (vma->vm_ops)
return do_fault(mm, vma, address, pte, pmd,
flags, entry);

return do_anonymous_page(mm, vma, address, pte, pmd,
flags);
}
return do_swap_page(mm, vma, address,
pte, pmd, flags, entry);
}

if (pte_protnone(entry))
return do_numa_page(mm, vma, address, entry, pte, pmd);

ptl = pte_lockptr(mm, pmd);
spin_lock(ptl);
if (unlikely(!pte_same(*pte, entry)))
goto unlock;
if (flags & FAULT_FLAG_WRITE) {
if (!pte_write(entry))
return do_wp_page(mm, vma, address,
pte, pmd, ptl, entry);
entry = pte_mkdirty(entry);
}
entry = pte_mkyoung(entry);
if (ptep_set_access_flags(vma, address, pte, entry, flags & FAULT_FLAG_WRITE)) {
update_mmu_cache(vma, address, pte);
} else {
/*
* This is needed only for protection faults but the arch code
* is not yet telling us if this is a protection fault or not.
* This still avoids useless tlb flushes for .text page faults
* with threads.
*/
if (flags & FAULT_FLAG_WRITE)
flush_tlb_fix_spurious_fault(vma, address);
}
unlock:
pte_unmap_unlock(pte, ptl);
return 0;
}

/*
* We enter with non-exclusive mmap_sem (to exclude vma changes,
* but allow concurrent faults), and pte mapped but not yet locked.
* We return with mmap_sem still held, but pte unmapped and unlocked.
*/
static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
unsigned int flags)
{
struct mem_cgroup *memcg;
struct page *page;
spinlock_t *ptl;
pte_t entry;

pte_unmap(page_table);

/* File mapping without ->vm_ops ? */
if (vma->vm_flags & VM_SHARED)
return VM_FAULT_SIGBUS;

/* Check if we need to add a guard page to the stack */
if (check_stack_guard_page(vma, address) < 0)
return VM_FAULT_SIGSEGV;

/* Use the zero-page for reads */
if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm)) {
entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
vma->vm_page_prot));
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (!pte_none(*page_table))
goto unlock;
goto setpte;
}

/* Allocate our own private page. */
if (unlikely(anon_vma_prepare(vma)))
goto oom;
page = alloc_zeroed_user_highpage_movable(vma, address);
if (!page)
goto oom;

if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg))
goto oom_free_page;

/*
* The memory barrier inside __SetPageUptodate makes sure that
* preceeding stores to the page contents become visible before
* the set_pte_at() write.
*/
__SetPageUptodate(page);

entry = mk_pte(page, vma->vm_page_prot);
if (vma->vm_flags & VM_WRITE)
entry = pte_mkwrite(pte_mkdirty(entry));

page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (!pte_none(*page_table))
goto release;

inc_mm_counter_fast(mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, vma, address);
mem_cgroup_commit_charge(page, memcg, false);
lru_cache_add_active_or_unevictable(page, vma);
setpte:
set_pte_at(mm, address, page_table, entry);

/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, address, page_table);
unlock:
pte_unmap_unlock(page_table, ptl);
return 0;
release:
mem_cgroup_cancel_charge(page, memcg);
page_cache_release(page);
goto unlock;
oom_free_page:
page_cache_release(page);
oom:
return VM_FAULT_OOM;
}

/*
* The in-memory structure used to track swap areas.
*/
struct swap_info_struct {
unsigned long	flags;		/* SWP_USED etc: see above */
signed short	prio;		/* swap priority of this type */
struct plist_node list;		/* entry in swap_active_head */
struct plist_node avail_list;	/* entry in swap_avail_head */
signed char	type;		/* strange name for an index */
unsigned int	max;		/* extent of the swap_map */
unsigned char *swap_map;	/* vmalloc'ed array of usage counts */
struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */
struct swap_cluster_info free_cluster_head; /* free cluster list head */
struct swap_cluster_info free_cluster_tail; /* free cluster list tail */
unsigned int lowest_bit;	/* index of first free in swap_map */
unsigned int highest_bit;	/* index of last free in swap_map */
unsigned int pages;		/* total of usable pages of swap */
unsigned int inuse_pages;	/* number of those currently in use */
unsigned int cluster_next;	/* likely index for next allocation */
unsigned int cluster_nr;	/* countdown to next cluster search */
struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */
struct swap_extent *curr_swap_extent;
struct swap_extent first_swap_extent;
struct block_device *bdev;	/* swap device or bdev of swap file */
struct file *swap_file;		/* seldom referenced */
unsigned int old_block_size;	/* seldom referenced */
#ifdef CONFIG_FRONTSWAP
unsigned long *frontswap_map;	/* frontswap in-use, one bit per page */
atomic_t frontswap_pages;	/* frontswap pages in-use counter */
#endif
spinlock_t lock;		/*
* protect map scan related fields like
* swap_map, lowest_bit, highest_bit,
* inuse_pages, cluster_next,
* cluster_nr, lowest_alloc,
* highest_alloc, free/discard cluster
* list. other fields are only changed
* at swapon/swapoff, so are protected
* by swap_lock. changing flags need
* hold this lock and swap_lock. If
* both locks need hold, hold swap_lock
* first.
*/
struct work_struct discard_work; /* discard worker */
struct swap_cluster_info discard_cluster_head; /* list head of discard clusters */
struct swap_cluster_info discard_cluster_tail; /* list tail of discard clusters */
};

int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
{
int error;

error = radix_tree_maybe_preload(gfp_mask);
if (!error) {
error = __add_to_swap_cache(page, entry);
radix_tree_preload_end();
}
return error;
}

/*
* __add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
* but sets SwapCache flag and private instead of mapping and index.
*/
int __add_to_swap_cache(struct page *page, swp_entry_t entry)
{
int error;
struct address_space *address_space;

VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(PageSwapCache(page), page);
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);

page_cache_get(page);
SetPageSwapCache(page);
set_page_private(page, entry.val);

address_space = swap_address_space(entry);
spin_lock_irq(&address_space->tree_lock);
error = radix_tree_insert(&address_space->page_tree,
entry.val, page);
if (likely(!error)) {
address_space->nrpages++;
__inc_zone_page_state(page, NR_FILE_PAGES);
INC_CACHE_INFO(add_total);
}
spin_unlock_irq(&address_space->tree_lock);

if (unlikely(error)) {
/*
* Only the context which have set SWAP_HAS_CACHE flag
* would call add_to_swap_cache().
* So add_to_swap_cache() doesn't returns -EEXIST.
*/
VM_BUG_ON(error == -EEXIST);
set_page_private(page, 0UL);
ClearPageSwapCache(page);
page_cache_release(page);
}

return error;
}