Newer
Older
ret |= VM_FAULT_WRITE;
goto unlock;
}
/*
* Ok, we need to copy. Oh, well..
*/
pte_unmap_unlock(page_table, ptl);
VM_BUG_ON(old_page == ZERO_PAGE(0));
new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
if (!new_page)
goto oom;
/*
* Don't let another task, with possibly unlocked vma,
* keep the mlocked page.
*/
if ((vma->vm_flags & VM_LOCKED) && old_page) {
lock_page(old_page); /* for LRU manipulation */
clear_page_mlock(old_page);
unlock_page(old_page);
}
if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
/*
* Re-check the pte - we dropped the lock
*/
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (likely(pte_same(*page_table, orig_pte))) {
if (old_page) {
if (!PageAnon(old_page)) {
dec_mm_counter(mm, file_rss);
inc_mm_counter(mm, anon_rss);
}
} else
flush_cache_page(vma, address, pte_pfn(orig_pte));
entry = mk_pte(new_page, vma->vm_page_prot);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
/*
* Clear the pte entry and flush it first, before updating the
* pte with the new entry. This will avoid a race condition
* seen in the presence of one thread doing SMC and another
* thread doing COW.
*/
ptep_clear_flush_notify(vma, address, page_table);
page_add_new_anon_rmap(new_page, vma, address);
set_pte_at(mm, address, page_table, entry);
update_mmu_cache(vma, address, entry);
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
if (old_page) {
/*
* Only after switching the pte to the new page may
* we remove the mapcount here. Otherwise another
* process may come and find the rmap count decremented
* before the pte is switched to the new page, and
* "reuse" the old page writing into it while our pte
* here still points into it and can be read by other
* threads.
*
* The critical issue is to order this
* page_remove_rmap with the ptp_clear_flush above.
* Those stores are ordered by (if nothing else,)
* the barrier present in the atomic_add_negative
* in page_remove_rmap.
*
* Then the TLB flush in ptep_clear_flush ensures that
* no process can access the old page before the
* decremented mapcount is visible. And the old page
* cannot be reused until after the decremented
* mapcount is visible. So transitively, TLBs to
* old page will be flushed before it can be reused.
*/
} else
mem_cgroup_uncharge_page(new_page);
if (new_page)
page_cache_release(new_page);
if (old_page)
page_cache_release(old_page);
pte_unmap_unlock(page_table, ptl);
if (vma->vm_file)
file_update_time(vma->vm_file);
/*
* Yes, Virginia, this is actually required to prevent a race
* with clear_page_dirty_for_io() from clearing the page dirty
* bit after it clear all dirty ptes, but before a racing
* do_wp_page installs a dirty pte.
*
* do_no_page is protected similarly.
*/
wait_on_page_locked(dirty_page);
set_page_dirty_balance(dirty_page, page_mkwrite);
if (old_page)
page_cache_release(old_page);
unwritable_page:
page_cache_release(old_page);
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
}
/*
* Helper functions for unmap_mapping_range().
*
* __ Notes on dropping i_mmap_lock to reduce latency while unmapping __
*
* We have to restart searching the prio_tree whenever we drop the lock,
* since the iterator is only valid while the lock is held, and anyway
* a later vma might be split and reinserted earlier while lock dropped.
*
* The list of nonlinear vmas could be handled more efficiently, using
* a placeholder, but handle it in the same way until a need is shown.
* It is important to search the prio_tree before nonlinear list: a vma
* may become nonlinear and be shifted from prio_tree to nonlinear list
* while the lock is dropped; but never shifted from list to prio_tree.
*
* In order to make forward progress despite restarting the search,
* vm_truncate_count is used to mark a vma as now dealt with, so we can
* quickly skip it next time around. Since the prio_tree search only
* shows us those vmas affected by unmapping the range in question, we
* can't efficiently keep all vmas in step with mapping->truncate_count:
* so instead reset them all whenever it wraps back to 0 (then go to 1).
* mapping->truncate_count and vma->vm_truncate_count are protected by
* i_mmap_lock.
*
* In order to make forward progress despite repeatedly restarting some
* large vma, note the restart_addr from unmap_vmas when it breaks out:
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
* and restart from that address when we reach that vma again. It might
* have been split or merged, shrunk or extended, but never shifted: so
* restart_addr remains valid so long as it remains in the vma's range.
* unmap_mapping_range forces truncate_count to leap over page-aligned
* values so we can save vma's restart_addr in its truncate_count field.
*/
#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK))
static void reset_vma_truncate_counts(struct address_space *mapping)
{
struct vm_area_struct *vma;
struct prio_tree_iter iter;
vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
vma->vm_truncate_count = 0;
list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
vma->vm_truncate_count = 0;
}
static int unmap_mapping_range_vma(struct vm_area_struct *vma,
unsigned long start_addr, unsigned long end_addr,
struct zap_details *details)
{
unsigned long restart_addr;
int need_break;
/*
* files that support invalidating or truncating portions of the
* file from under mmaped areas must have their ->fault function
* return a locked page (and set VM_FAULT_LOCKED in the return).
* This provides synchronisation against concurrent unmapping here.
again:
restart_addr = vma->vm_truncate_count;
if (is_restart_addr(restart_addr) && start_addr < restart_addr) {
start_addr = restart_addr;
if (start_addr >= end_addr) {
/* Top of vma has been split off since last time */
vma->vm_truncate_count = details->truncate_count;
return 0;
}
}
restart_addr = zap_page_range(vma, start_addr,
end_addr - start_addr, details);
need_break = need_resched() || spin_needbreak(details->i_mmap_lock);
/* We have now completed this vma: mark it so */
vma->vm_truncate_count = details->truncate_count;
if (!need_break)
return 0;
} else {
/* Note restart_addr in vma's truncate_count field */
vma->vm_truncate_count = restart_addr;
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
if (!need_break)
goto again;
}
spin_unlock(details->i_mmap_lock);
cond_resched();
spin_lock(details->i_mmap_lock);
return -EINTR;
}
static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
struct zap_details *details)
{
struct vm_area_struct *vma;
struct prio_tree_iter iter;
pgoff_t vba, vea, zba, zea;
restart:
vma_prio_tree_foreach(vma, &iter, root,
details->first_index, details->last_index) {
/* Skip quickly over those we have already dealt with */
if (vma->vm_truncate_count == details->truncate_count)
continue;
vba = vma->vm_pgoff;
vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1;
/* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */
zba = details->first_index;
if (zba < vba)
zba = vba;
zea = details->last_index;
if (zea > vea)
zea = vea;
if (unmap_mapping_range_vma(vma,
((zba - vba) << PAGE_SHIFT) + vma->vm_start,
((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start,
details) < 0)
goto restart;
}
}
static inline void unmap_mapping_range_list(struct list_head *head,
struct zap_details *details)
{
struct vm_area_struct *vma;
/*
* In nonlinear VMAs there is no correspondence between virtual address
* offset and file offset. So we must perform an exhaustive search
* across *all* the pages in each nonlinear VMA, not just the pages
* whose virtual address lies outside the file truncation point.
*/
restart:
list_for_each_entry(vma, head, shared.vm_set.list) {
/* Skip quickly over those we have already dealt with */
if (vma->vm_truncate_count == details->truncate_count)
continue;
details->nonlinear_vma = vma;
if (unmap_mapping_range_vma(vma, vma->vm_start,
vma->vm_end, details) < 0)
goto restart;
}
}
/**
* unmap_mapping_range - unmap the portion of all mmaps in the specified address_space corresponding to the specified page range in the underlying file.
* @mapping: the address space containing mmaps to be unmapped.
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
* @holebegin: byte in first page to unmap, relative to the start of
* the underlying file. This will be rounded down to a PAGE_SIZE
* boundary. Note that this is different from vmtruncate(), which
* must keep the partial page. In contrast, we must get rid of
* partial pages.
* @holelen: size of prospective hole in bytes. This will be rounded
* up to a PAGE_SIZE boundary. A holelen of zero truncates to the
* end of the file.
* @even_cows: 1 when truncating a file, unmap even private COWed pages;
* but 0 when invalidating pagecache, don't throw away private data.
*/
void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows)
{
struct zap_details details;
pgoff_t hba = holebegin >> PAGE_SHIFT;
pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
/* Check for overflow. */
if (sizeof(holelen) > sizeof(hlen)) {
long long holeend =
(holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT;
if (holeend & ~(long long)ULONG_MAX)
hlen = ULONG_MAX - hba + 1;
}
details.check_mapping = even_cows? NULL: mapping;
details.nonlinear_vma = NULL;
details.first_index = hba;
details.last_index = hba + hlen - 1;
if (details.last_index < details.first_index)
details.last_index = ULONG_MAX;
details.i_mmap_lock = &mapping->i_mmap_lock;
spin_lock(&mapping->i_mmap_lock);
/* Protect against endless unmapping loops */
mapping->truncate_count++;
if (unlikely(is_restart_addr(mapping->truncate_count))) {
if (mapping->truncate_count == 0)
reset_vma_truncate_counts(mapping);
mapping->truncate_count++;
}
details.truncate_count = mapping->truncate_count;
if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
unmap_mapping_range_tree(&mapping->i_mmap, &details);
if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
spin_unlock(&mapping->i_mmap_lock);
}
EXPORT_SYMBOL(unmap_mapping_range);
/**
* vmtruncate - unmap mappings "freed" by truncate() syscall
* @inode: inode of the file used
* @offset: file offset to start truncating
*
* NOTE! We have to be ready to update the memory sharing
* between the file and the memory map for a potential last
* incomplete page. Ugly, but necessary.
*/
int vmtruncate(struct inode * inode, loff_t offset)
{
if (inode->i_size < offset) {
unsigned long limit;
limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
if (limit != RLIM_INFINITY && offset > limit)
goto out_sig;
if (offset > inode->i_sb->s_maxbytes)
goto out_big;
i_size_write(inode, offset);
} else {
struct address_space *mapping = inode->i_mapping;
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
/*
* truncation of in-use swapfiles is disallowed - it would
* cause subsequent swapout to scribble on the now-freed
* blocks.
*/
if (IS_SWAPFILE(inode))
return -ETXTBSY;
i_size_write(inode, offset);
/*
* unmap_mapping_range is called twice, first simply for
* efficiency so that truncate_inode_pages does fewer
* single-page unmaps. However after this first call, and
* before truncate_inode_pages finishes, it is possible for
* private pages to be COWed, which remain after
* truncate_inode_pages finishes, hence the second
* unmap_mapping_range call must be made for correctness.
*/
unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
truncate_inode_pages(mapping, offset);
unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
}
out_sig:
send_sig(SIGXFSZ, current, 0);
out_big:
return -EFBIG;
}
EXPORT_SYMBOL(vmtruncate);
int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
{
struct address_space *mapping = inode->i_mapping;
/*
* If the underlying filesystem is not going to provide
* a way to truncate a range of blocks (punch a hole) -
* we should return failure right now.
*/
return -ENOSYS;
mutex_lock(&inode->i_mutex);
down_write(&inode->i_alloc_sem);
unmap_mapping_range(mapping, offset, (end - offset), 1);
truncate_inode_pages_range(mapping, offset, end);
unmap_mapping_range(mapping, offset, (end - offset), 1);
inode->i_op->truncate_range(inode, offset, end);
up_write(&inode->i_alloc_sem);
mutex_unlock(&inode->i_mutex);
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_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
int write_access, pte_t orig_pte)
struct mem_cgroup *ptr = NULL;
if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
entry = pte_to_swp_entry(orig_pte);
if (is_migration_entry(entry)) {
migration_entry_wait(mm, pmd, address);
goto out;
}
Shailabh Nagar
committed
delayacct_set_flag(DELAYACCT_PF_SWAPIN);
grab_swap_token(); /* Contend for token _before_ read-in */
page = swapin_readahead(entry,
GFP_HIGHUSER_MOVABLE, vma, address);
* Back out if somebody else faulted in this pte
* while we released the pte lock.
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (likely(pte_same(*page_table, orig_pte)))
ret = VM_FAULT_OOM;
Shailabh Nagar
committed
delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
}
/* Had to read the page from swap area: Major fault */
ret = VM_FAULT_MAJOR;
lock_page(page);
delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) {
* Back out if somebody else already faulted in this pte.
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (unlikely(!pte_same(*page_table, orig_pte)))
goto out_nomap;
if (unlikely(!PageUptodate(page))) {
ret = VM_FAULT_SIGBUS;
goto out_nomap;
/*
* The page isn't present yet, go ahead with the fault.
*
* Be careful about the sequence of operations here.
* To get its accounting right, reuse_swap_page() must be called
* while the page is counted on swap but not yet in mapcount i.e.
* before page_add_anon_rmap() and swap_free(); try_to_free_swap()
* must be called after the swap_free(), or it will never succeed.
* Because delete_from_swap_page() may be called by reuse_swap_page(),
* mem_cgroup_commit_charge_swapin() may not be able to find swp_entry
* in page->private. In this case, a record in swap_cgroup is silently
* discarded at swap_free().
if (write_access && reuse_swap_page(page)) {
pte = maybe_mkwrite(pte_mkdirty(pte), vma);
write_access = 0;
}
flush_icache_page(vma, page);
set_pte_at(mm, address, page_table, pte);
page_add_anon_rmap(page, vma, address);
/* It's better to call commit-charge after rmap is established */
mem_cgroup_commit_charge_swapin(page, ptr);
if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
try_to_free_swap(page);
ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte);
if (ret & VM_FAULT_ERROR)
ret &= VM_FAULT_ERROR;
goto out;
}
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, address, pte);
pte_unmap_unlock(page_table, ptl);
out_nomap:
mem_cgroup_cancel_charge_swapin(ptr);
pte_unmap_unlock(page_table, ptl);
unlock_page(page);
page_cache_release(page);
* 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,
int write_access)
struct page *page;
spinlock_t *ptl;
/* Allocate our own private page. */
pte_unmap(page_table);
if (unlikely(anon_vma_prepare(vma)))
goto oom;
page = alloc_zeroed_user_highpage_movable(vma, address);
if (!page)
goto oom;
if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))
entry = mk_pte(page, vma->vm_page_prot);
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (!pte_none(*page_table))
goto release;
inc_mm_counter(mm, anon_rss);
page_add_new_anon_rmap(page, vma, address);
set_pte_at(mm, address, page_table, entry);
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, address, entry);
unlock:
pte_unmap_unlock(page_table, ptl);
page_cache_release(page);
goto unlock;
* __do_fault() tries to create a new page mapping. It aggressively
* tries to share with existing pages, but makes a separate copy if
* the FAULT_FLAG_WRITE is set in the flags parameter in order to avoid
* the next page fault.
*
* As this is called only for pages that do not currently exist, we
* do not need to flush old virtual caches or the TLB.
*
* We enter with non-exclusive mmap_sem (to exclude vma changes,
* but allow concurrent faults), and pte neither mapped nor locked.
* We return with mmap_sem still held, but pte unmapped and unlocked.
static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd,
pgoff_t pgoff, unsigned int flags, pte_t orig_pte)
struct page *dirty_page = NULL;
int page_mkwrite = 0;
vmf.virtual_address = (void __user *)(address & PAGE_MASK);
vmf.pgoff = pgoff;
vmf.flags = flags;
vmf.page = NULL;
ret = vma->vm_ops->fault(vma, &vmf);
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
return ret;
* For consistency in subsequent calls, make the faulted page always
if (flags & FAULT_FLAG_WRITE) {
if (!(vma->vm_flags & VM_SHARED)) {
if (unlikely(anon_vma_prepare(vma))) {
page = alloc_page_vma(GFP_HIGHUSER_MOVABLE,
vma, address);
if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) {
ret = VM_FAULT_OOM;
page_cache_release(page);
goto out;
}
charged = 1;
/*
* Don't let another task, with possibly unlocked vma,
* keep the mlocked page.
*/
if (vma->vm_flags & VM_LOCKED)
clear_page_mlock(vmf.page);
/*
* If the page will be shareable, see if the backing
* address space wants to know that the page is about
* to become writable
*/
if (vma->vm_ops->page_mkwrite) {
unlock_page(page);
vmf.flags |= FAULT_FLAG_MKWRITE;
tmp = vma->vm_ops->page_mkwrite(vma, &vmf);
if (unlikely(tmp &
(VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
ret = tmp;
goto out_unlocked;
}
lock_page(page);
/*
* XXX: this is not quite right (racy vs
* invalidate) to unlock and relock the page
* like this, however a better fix requires
* reworking page_mkwrite locking API, which
* is better done later.
*/
if (!page->mapping) {
anon = 1; /* no anon but release vmf.page */
goto out;
}
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
/*
* This silly early PAGE_DIRTY setting removes a race
* due to the bad i386 page protection. But it's valid
* for other architectures too.
*
* Note that if write_access is true, we either now have
* an exclusive copy of the page, or this is a shared mapping,
* so we can make it writable and dirty to avoid having to
* handle that later.
*/
/* Only go through if we didn't race with anybody else... */
if (likely(pte_same(*page_table, orig_pte))) {
flush_icache_page(vma, page);
entry = mk_pte(page, vma->vm_page_prot);
if (flags & FAULT_FLAG_WRITE)
entry = maybe_mkwrite(pte_mkdirty(entry), vma);
if (anon) {
inc_mm_counter(mm, anon_rss);
page_add_new_anon_rmap(page, vma, address);
page_add_file_rmap(page);
if (flags & FAULT_FLAG_WRITE) {
set_pte_at(mm, address, page_table, entry);
/* no need to invalidate: a not-present page won't be cached */
update_mmu_cache(vma, address, entry);
if (charged)
mem_cgroup_uncharge_page(page);
if (anon)
page_cache_release(page);
else
anon = 1; /* no anon but release faulted_page */
pte_unmap_unlock(page_table, ptl);
else if (dirty_page) {
if (vma->vm_file)
file_update_time(vma->vm_file);
set_page_dirty_balance(dirty_page, page_mkwrite);
static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
int write_access, pte_t orig_pte)
{
pgoff_t pgoff = (((address & PAGE_MASK)
- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
unsigned int flags = (write_access ? FAULT_FLAG_WRITE : 0);
pte_unmap(page_table);
return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
/*
* Fault of a previously existing named mapping. Repopulate the pte
* from the encoded file_pte if possible. This enables swappable
* nonlinear vmas.
*
* 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_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *page_table, pmd_t *pmd,
int write_access, pte_t orig_pte)
unsigned int flags = FAULT_FLAG_NONLINEAR |
(write_access ? FAULT_FLAG_WRITE : 0);
if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) {
/*
* Page table corrupted: show pte and kill process.
*/
print_bad_pte(vma, address, orig_pte, NULL);
return VM_FAULT_OOM;
}
pgoff = pte_to_pgoff(orig_pte);
return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte);
}
/*
* 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 mmap_sem still held, but pte unmapped and unlocked.
*/
static inline int handle_pte_fault(struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long address,
pte_t *pte, pmd_t *pmd, int write_access)
return do_linear_fault(mm, vma, address,
pte, pmd, write_access, entry);
}
return do_anonymous_page(mm, vma, address,
pte, pmd, write_access);
pte, pmd, write_access, entry);
return do_swap_page(mm, vma, address,
pte, pmd, write_access, entry);
spin_lock(ptl);
if (unlikely(!pte_same(*pte, entry)))
goto unlock;
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, write_access)) {
update_mmu_cache(vma, address, entry);
} 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 (write_access)
flush_tlb_page(vma, address);
}
unlock:
pte_unmap_unlock(pte, ptl);
}
/*
* By the time we get here, we already hold the mm semaphore
*/
int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, int write_access)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
__set_current_state(TASK_RUNNING);
if (unlikely(is_vm_hugetlb_page(vma)))
return hugetlb_fault(mm, vma, address, write_access);
pgd = pgd_offset(mm, address);
pud = pud_alloc(mm, pgd, address);
if (!pud)
pte = pte_alloc_map(mm, pmd, address);
if (!pte)
return handle_pte_fault(mm, vma, address, pte, pmd, write_access);
}
#ifndef __PAGETABLE_PUD_FOLDED
/*
* Allocate page upper directory.
* We've already handled the fast-path in-line.
int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
pud_t *new = pud_alloc_one(mm, address);
if (!new)
smp_wmb(); /* See comment in __pte_alloc */
if (pgd_present(*pgd)) /* Another has populated it */
else
pgd_populate(mm, pgd, new);
}
#endif /* __PAGETABLE_PUD_FOLDED */
#ifndef __PAGETABLE_PMD_FOLDED
/*
* Allocate page middle directory.
* We've already handled the fast-path in-line.
int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
pmd_t *new = pmd_alloc_one(mm, address);
if (!new)
smp_wmb(); /* See comment in __pte_alloc */
if (pud_present(*pud)) /* Another has populated it */
else
pud_populate(mm, pud, new);
if (pgd_present(*pud)) /* Another has populated it */
else
pgd_populate(mm, pud, new);
#endif /* __PAGETABLE_PMD_FOLDED */
int make_pages_present(unsigned long addr, unsigned long end)
{
int ret, len, write;
struct vm_area_struct * vma;
vma = find_vma(current->mm, addr);
if (!vma)
BUG_ON(addr >= end);
BUG_ON(end > vma->vm_end);
len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE;
ret = get_user_pages(current, current->mm, addr,
len, write, 0, NULL, NULL);
return ret == len ? 0 : -EFAULT;
}
#if !defined(__HAVE_ARCH_GATE_AREA)
#if defined(AT_SYSINFO_EHDR)
static struct vm_area_struct gate_vma;
static int __init gate_vma_init(void)
{
gate_vma.vm_mm = NULL;
gate_vma.vm_start = FIXADDR_USER_START;
gate_vma.vm_end = FIXADDR_USER_END;
gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC;
gate_vma.vm_page_prot = __P101;
/*
* Make sure the vDSO gets into every core dump.
* Dumping its contents makes post-mortem fully interpretable later
* without matching up the same kernel and hardware config to see
* what PC values meant.
*/
gate_vma.vm_flags |= VM_ALWAYSDUMP;