/*
* copy_user_page
* @to: P1 address
* @from: P1 address
* @address: U0 address to be mapped
* @page: page (virt_to_page(to))
*/
void copy_user_page(void *to, void *from, unsigned long address,
struct page *page)
{
__set_bit(PG_mapped, &page->flags);
if (((address ^ (unsigned long)to) & CACHE_ALIAS) == 0)
copy_page(to, from);
else {
unsigned long phys_addr = PHYSADDR(to);
unsigned long p3_addr = P3SEG + (address & CACHE_ALIAS);
pgd_t *pgd = pgd_offset_k(p3_addr);
pud_t *pud = pud_offset(pgd, p3_addr);
pmd_t *pmd = pmd_offset(pud, p3_addr);
pte_t *pte = pte_offset_kernel(pmd, p3_addr);
pte_t entry;
unsigned long flags;
entry = pfn_pte(phys_addr >> PAGE_SHIFT, PAGE_KERNEL);
mutex_lock(&p3map_mutex[(address & CACHE_ALIAS)>>12]);
set_pte(pte, entry);
local_irq_save(flags);
__flush_tlb_page(get_asid(), p3_addr);
local_irq_restore(flags);
update_mmu_cache(NULL, p3_addr, entry);
__copy_user_page((void *)p3_addr, from, to);
pte_clear(&init_mm, p3_addr, pte);
mutex_unlock(&p3map_mutex[(address & CACHE_ALIAS)>>12]);
}
}
/*
* copy_user_page
* @to: kernel logical address
* @from: kernel logical address
* @address: U0 address to be mapped
* @page: page (virt_to_page(to))
*/
void copy_user_page(void *to, void *from, unsigned long address,
struct page *page)
{
extern void __copy_page_wb(void *to, void *from);
if (((address ^ (unsigned long)to) & CACHE_ALIAS) == 0)
__copy_page_wb(to, from);
else {
pgprot_t pgprot = __pgprot(_PAGE_PRESENT |
_PAGE_RW | _PAGE_CACHABLE |
_PAGE_DIRTY | _PAGE_ACCESSED |
_PAGE_HW_SHARED | _PAGE_FLAGS_HARD);
unsigned long phys_addr = virt_to_phys(to);
unsigned long p3_addr = P3SEG + (address & CACHE_ALIAS);
pgd_t *pgd = pgd_offset_k(p3_addr);
pud_t *pud = pud_offset(pgd, p3_addr);
pmd_t *pmd = pmd_offset(pud, p3_addr);
pte_t *pte = pte_offset_kernel(pmd, p3_addr);
pte_t entry;
unsigned long flags;
entry = pfn_pte(phys_addr >> PAGE_SHIFT, pgprot);
inc_preempt_count();
BUG_ON(atomic_inc_return(&concurreny_check[(address & CACHE_ALIAS)>>12]) != 1);
set_pte(pte, entry);
local_irq_save(flags);
flush_tlb_one(get_asid(), p3_addr);
local_irq_restore(flags);
update_mmu_cache(NULL, p3_addr, entry);
__copy_user_page((void *)p3_addr, from, to);
pte_clear(&init_mm, p3_addr, pte);
atomic_dec(&concurreny_check[(address & CACHE_ALIAS)>>12]);
dec_preempt_count();
}
}
/*
* copy_user_page
* @to: P1 address
* @from: P1 address
* @address: U0 address to be mapped
* @page: page (virt_to_page(to))
*/
void copy_user_page(void *to, void *from, unsigned long address,
struct page *page)
{
__set_bit(PG_mapped, &page->flags);
if (((address ^ (unsigned long)to) & CACHE_ALIAS) == 0)
copy_page(to, from);
else {
pgprot_t pgprot = __pgprot(_PAGE_PRESENT |
_PAGE_RW | _PAGE_CACHABLE |
_PAGE_DIRTY | _PAGE_ACCESSED |
_PAGE_HW_SHARED | _PAGE_FLAGS_HARD);
unsigned long phys_addr = PHYSADDR(to);
unsigned long p3_addr = P3SEG + (address & CACHE_ALIAS);
pgd_t *dir = pgd_offset_k(p3_addr);
pmd_t *pmd = pmd_offset(dir, p3_addr);
pte_t *pte = pte_offset_kernel(pmd, p3_addr);
pte_t entry;
unsigned long flags;
entry = pfn_pte(phys_addr >> PAGE_SHIFT, pgprot);
down(&p3map_sem[(address & CACHE_ALIAS)>>12]);
set_pte(pte, entry);
local_irq_save(flags);
__flush_tlb_page(get_asid(), p3_addr);
local_irq_restore(flags);
update_mmu_cache(NULL, p3_addr, entry);
__copy_user_page((void *)p3_addr, from, to);
pte_clear(&init_mm, p3_addr, pte);
up(&p3map_sem[(address & CACHE_ALIAS)>>12]);
}
}
static int mfill_zeropage_pte(struct mm_struct *dst_mm,
pmd_t *dst_pmd,
struct vm_area_struct *dst_vma,
unsigned long dst_addr)
{
pte_t _dst_pte, *dst_pte;
spinlock_t *ptl;
int ret;
pgoff_t offset, max_off;
struct inode *inode;
_dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr),
dst_vma->vm_page_prot));
dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
if (dst_vma->vm_file) {
/* the shmem MAP_PRIVATE case requires checking the i_size */
inode = dst_vma->vm_file->f_inode;
offset = linear_page_index(dst_vma, dst_addr);
max_off = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
ret = -EFAULT;
if (unlikely(offset >= max_off))
goto out_unlock;
}
ret = -EEXIST;
if (!pte_none(*dst_pte))
goto out_unlock;
set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
/* No need to invalidate - it was non-present before */
update_mmu_cache(dst_vma, dst_addr, dst_pte);
ret = 0;
out_unlock:
pte_unmap_unlock(dst_pte, ptl);
return ret;
}
/*
* This only needs the MM semaphore
*/
static int do_anonymous_page(struct mm_struct * mm, struct vm_area_struct * vma, pte_t *page_table, int write_access, unsigned long addr)
{
struct page *page = NULL;
pte_t entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot));
if (write_access) {
page = alloc_page(GFP_HIGHUSER);
if (!page)
return -1;
clear_user_highpage(page, addr);
entry = pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
mm->rss++;
flush_page_to_ram(page);
}
set_pte(page_table, entry);
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, addr, entry);
return 1; /* Minor fault */
}
/*
* do_no_page() tries to create a new page mapping. It aggressively
* tries to share with existing pages, but makes a separate copy if
* the "write_access" parameter is true 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.
*
* This is called with the MM semaphore held.
*/
static int do_no_page(struct mm_struct * mm, struct vm_area_struct * vma,
unsigned long address, int write_access, pte_t *page_table)
{
struct page * new_page;
pte_t entry;
if (!vma->vm_ops || !vma->vm_ops->nopage)
return do_anonymous_page(mm, vma, page_table, write_access, address);
/*
* The third argument is "no_share", which tells the low-level code
* to copy, not share the page even if sharing is possible. It's
* essentially an early COW detection.
*/
new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, (vma->vm_flags & VM_SHARED)?0:write_access);
if (new_page == NULL) /* no page was available -- SIGBUS */
return 0;
if (new_page == NOPAGE_OOM)
return -1;
++mm->rss;
/*
* 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.
*/
flush_page_to_ram(new_page);
flush_icache_page(vma, new_page);
entry = mk_pte(new_page, vma->vm_page_prot);
if (write_access) {
entry = pte_mkwrite(pte_mkdirty(entry));
} else if (page_count(new_page) > 1 &&
!(vma->vm_flags & VM_SHARED))
entry = pte_wrprotect(entry);
set_pte(page_table, entry);
/* no need to invalidate: a not-present page shouldn't be cached */
update_mmu_cache(vma, address, entry);
return 2; /* Major fault */
}
/*
* We are called with the MM semaphore and page_table_lock
* spinlock held to protect against concurrent faults in
* multithreaded programs.
*/
static int do_anonymous_page(struct mm_struct * mm, struct vm_area_struct * vma, pte_t *page_table, int write_access, unsigned long addr)
{
pte_t entry;
/* Read-only mapping of ZERO_PAGE. */
entry = pte_wrprotect(mk_pte(ZERO_PAGE(addr), vma->vm_page_prot));
/* ..except if it's a write access */
if (write_access) {
struct page *page;
/* Allocate our own private page. */
spin_unlock(&mm->page_table_lock);
page = alloc_page(GFP_HIGHUSER);
if (!page)
goto no_mem;
clear_user_highpage(page, addr);
spin_lock(&mm->page_table_lock);
if (!pte_none(*page_table)) {
page_cache_release(page);
spin_unlock(&mm->page_table_lock);
return 1;
}
mm->rss++;
flush_page_to_ram(page);
entry = pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
lru_cache_add(page);
mark_page_accessed(page);
}
set_pte(page_table, entry);
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, addr, entry);
spin_unlock(&mm->page_table_lock);
return 1; /* Minor fault */
no_mem:
return -1;
}
void handle_mm_fault(struct vm_area_struct * vma, unsigned long address,
int write_access)
{
pgd_t *pgd;
pmd_t *pmd;
pte_t *pte;
pgd = pgd_offset(vma->vm_mm, address);
pmd = pmd_alloc(pgd, address);
if (!pmd)
goto no_memory;
pte = pte_alloc(pmd, address);
if (!pte)
goto no_memory;
handle_pte_fault(vma, address, write_access, pte);
update_mmu_cache(vma, address, *pte);
return;
no_memory:
oom(current);
}
static int do_swap_page(struct mm_struct * mm,
struct vm_area_struct * vma, unsigned long address,
pte_t * page_table, swp_entry_t entry, int write_access)
{
struct page *page = lookup_swap_cache(entry);
pte_t pte;
if (!page) {
lock_kernel();
swapin_readahead(entry);
page = read_swap_cache(entry);
unlock_kernel();
if (!page)
return -1;
flush_page_to_ram(page);
flush_icache_page(vma, page);
}
mm->rss++;
pte = mk_pte(page, vma->vm_page_prot);
/*
* Freeze the "shared"ness of the page, ie page_count + swap_count.
* Must lock page before transferring our swap count to already
* obtained page count.
*/
lock_page(page);
swap_free(entry);
if (write_access && !is_page_shared(page))
pte = pte_mkwrite(pte_mkdirty(pte));
UnlockPage(page);
set_pte(page_table, pte);
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, address, pte);
return 1; /* Minor fault */
}
static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address,
pte_t *pte, unsigned int flags)
{
/* No page to get reference */
if (flags & FOLL_GET)
return -EFAULT;
if (flags & FOLL_TOUCH) {
pte_t entry = *pte;
if (flags & FOLL_WRITE)
entry = pte_mkdirty(entry);
entry = pte_mkyoung(entry);
if (!pte_same(*pte, entry)) {
set_pte_at(vma->vm_mm, address, pte, entry);
update_mmu_cache(vma, address, pte);
}
}
/* Proper page table entry exists, but no corresponding struct page */
return -EEXIST;
}
static int mfill_zeropage_pte(struct mm_struct *dst_mm,
pmd_t *dst_pmd,
struct vm_area_struct *dst_vma,
unsigned long dst_addr)
{
pte_t _dst_pte, *dst_pte;
spinlock_t *ptl;
int ret;
_dst_pte = pte_mkspecial(pfn_pte(my_zero_pfn(dst_addr),
dst_vma->vm_page_prot));
ret = -EEXIST;
dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
if (!pte_none(*dst_pte))
goto out_unlock;
set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
/* No need to invalidate - it was non-present before */
update_mmu_cache(dst_vma, dst_addr, dst_pte);
ret = 0;
out_unlock:
pte_unmap_unlock(dst_pte, ptl);
return ret;
}
/*
* Establish a new mapping:
* - flush the old one
* - update the page tables
* - inform the TLB about the new one
*/
static inline void establish_pte(struct vm_area_struct * vma, unsigned long address, pte_t *page_table, pte_t entry)
{
set_pte(page_table, entry);
flush_tlb_page(vma, address);
update_mmu_cache(vma, address, entry);
}
static int mcopy_atomic_pte(struct mm_struct *dst_mm,
pmd_t *dst_pmd,
struct vm_area_struct *dst_vma,
unsigned long dst_addr,
unsigned long src_addr,
struct page **pagep)
{
struct mem_cgroup *memcg;
pte_t _dst_pte, *dst_pte;
spinlock_t *ptl;
void *page_kaddr;
int ret;
struct page *page;
if (!*pagep) {
ret = -ENOMEM;
page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, dst_vma, dst_addr);
if (!page)
goto out;
page_kaddr = kmap_atomic(page);
ret = copy_from_user(page_kaddr,
(const void __user *) src_addr,
PAGE_SIZE);
kunmap_atomic(page_kaddr);
/* fallback to copy_from_user outside mmap_sem */
if (unlikely(ret)) {
ret = -EFAULT;
*pagep = page;
/* don't free the page */
goto out;
}
} else {
page = *pagep;
*pagep = NULL;
}
/*
* The memory barrier inside __SetPageUptodate makes sure that
* preceeding stores to the page contents become visible before
* the set_pte_at() write.
*/
__SetPageUptodate(page);
ret = -ENOMEM;
if (mem_cgroup_try_charge(page, dst_mm, GFP_KERNEL, &memcg, false))
goto out_release;
_dst_pte = mk_pte(page, dst_vma->vm_page_prot);
if (dst_vma->vm_flags & VM_WRITE)
_dst_pte = pte_mkwrite(pte_mkdirty(_dst_pte));
ret = -EEXIST;
dst_pte = pte_offset_map_lock(dst_mm, dst_pmd, dst_addr, &ptl);
if (!pte_none(*dst_pte))
goto out_release_uncharge_unlock;
inc_mm_counter(dst_mm, MM_ANONPAGES);
page_add_new_anon_rmap(page, dst_vma, dst_addr, false);
mem_cgroup_commit_charge(page, memcg, false, false);
lru_cache_add_active_or_unevictable(page, dst_vma);
set_pte_at(dst_mm, dst_addr, dst_pte, _dst_pte);
/* No need to invalidate - it was non-present before */
update_mmu_cache(dst_vma, dst_addr, dst_pte);
pte_unmap_unlock(dst_pte, ptl);
ret = 0;
out:
return ret;
out_release_uncharge_unlock:
pte_unmap_unlock(dst_pte, ptl);
mem_cgroup_cancel_charge(page, memcg, false);
out_release:
page_cache_release(page);
goto out;
}
/*
* do_no_page() tries to create a new page mapping. It aggressively
* tries to share with existing pages, but makes a separate copy if
* the "write_access" parameter is true 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.
*
* This is called with the MM semaphore held and the page table
* spinlock held. Exit with the spinlock released.
*/
static int do_no_page(struct mm_struct * mm, struct vm_area_struct * vma,
unsigned long address, int write_access, pte_t *page_table)
{
struct page * new_page;
pte_t entry;
if (!vma->vm_ops || !vma->vm_ops->nopage)
return do_anonymous_page(mm, vma, page_table, write_access, address);
spin_unlock(&mm->page_table_lock);
new_page = vma->vm_ops->nopage(vma, address & PAGE_MASK, 0);
if (new_page == NULL) /* no page was available -- SIGBUS */
return 0;
if (new_page == NOPAGE_OOM)
return -1;
/*
* Should we do an early C-O-W break?
*/
if (write_access && !(vma->vm_flags & VM_SHARED)) {
struct page * page = alloc_page(GFP_HIGHUSER);
if (!page) {
page_cache_release(new_page);
return -1;
}
copy_highpage(page, new_page);
page_cache_release(new_page);
lru_cache_add(page);
new_page = page;
}
spin_lock(&mm->page_table_lock);
/*
* 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 (pte_none(*page_table)) {
++mm->rss;
flush_page_to_ram(new_page);
flush_icache_page(vma, new_page);
entry = mk_pte(new_page, vma->vm_page_prot);
if (write_access)
entry = pte_mkwrite(pte_mkdirty(entry));
set_pte(page_table, entry);
} else {
/* One of our sibling threads was faster, back out. */
page_cache_release(new_page);
spin_unlock(&mm->page_table_lock);
return 1;
}
/* no need to invalidate: a not-present page shouldn't be cached */
update_mmu_cache(vma, address, entry);
spin_unlock(&mm->page_table_lock);
return 2; /* Major fault */
}
/*
* We hold the mm semaphore and the page_table_lock on entry and
* should release the pagetable lock on exit..
*/
static int do_swap_page(struct mm_struct * mm,
struct vm_area_struct * vma, unsigned long address,
pte_t * page_table, pte_t orig_pte, int write_access)
{
struct page *page;
swp_entry_t entry = pte_to_swp_entry(orig_pte);
pte_t pte;
int ret = 1;
spin_unlock(&mm->page_table_lock);
page = lookup_swap_cache(entry);
if (!page) {
swapin_readahead(entry);
page = read_swap_cache_async(entry);
if (!page) {
/*
* Back out if somebody else faulted in this pte while
* we released the page table lock.
*/
int retval;
spin_lock(&mm->page_table_lock);
retval = pte_same(*page_table, orig_pte) ? -1 : 1;
spin_unlock(&mm->page_table_lock);
return retval;
}
/* Had to read the page from swap area: Major fault */
ret = 2;
}
lock_page(page);
/*
* Back out if somebody else faulted in this pte while we
* released the page table lock.
*/
spin_lock(&mm->page_table_lock);
if (!pte_same(*page_table, orig_pte)) {
spin_unlock(&mm->page_table_lock);
unlock_page(page);
page_cache_release(page);
return 1;
}
/* The page isn't present yet, go ahead with the fault. */
swap_free(entry);
if (vm_swap_full())
remove_exclusive_swap_page(page);
mm->rss++;
pte = mk_pte(page, vma->vm_page_prot);
if (write_access && can_share_swap_page(page))
pte = pte_mkdirty(pte_mkwrite(pte));
unlock_page(page);
flush_page_to_ram(page);
flush_icache_page(vma, page);
set_pte(page_table, pte);
/* No need to invalidate - it was non-present before */
update_mmu_cache(vma, address, pte);
spin_unlock(&mm->page_table_lock);
return ret;
}
