#include <linux/syscalls.h>
#include <linux/hugetlb.h>
#include <linux/gfp.h>
+#include <linux/ptrace.h>
#include <asm/tlbflush.h>
get_page(new);
pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
+
+ /* Recheck VMA as permissions can change since migration started */
if (is_write_migration_entry(entry))
- pte = pte_mkwrite(pte);
+ pte = maybe_mkwrite(pte, vma);
+
#ifdef CONFIG_HUGETLB_PAGE
if (PageHuge(new))
pte = pte_mkhuge(pte);
#endif
- flush_cache_page(vma, addr, pte_pfn(pte));
+ flush_dcache_page(new);
set_pte_at(mm, addr, ptep, pte);
if (PageHuge(new)) {
*
* This function is called from do_swap_page().
*/
-void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
- unsigned long address)
+static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
+ spinlock_t *ptl)
{
- pte_t *ptep, pte;
- spinlock_t *ptl;
+ pte_t pte;
swp_entry_t entry;
struct page *page;
- ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
+ spin_lock(ptl);
pte = *ptep;
if (!is_swap_pte(pte))
goto out;
pte_unmap_unlock(ptep, ptl);
}
+void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
+ unsigned long address)
+{
+ spinlock_t *ptl = pte_lockptr(mm, pmd);
+ pte_t *ptep = pte_offset_map(pmd, address);
+ __migration_entry_wait(mm, ptep, ptl);
+}
+
+void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte)
+{
+ spinlock_t *ptl = &(mm)->page_table_lock;
+ __migration_entry_wait(mm, pte, ptl);
+}
+
#ifdef CONFIG_BLOCK
/* Returns true if all buffers are successfully locked */
-static bool buffer_migrate_lock_buffers(struct buffer_head *head, bool sync)
+static bool buffer_migrate_lock_buffers(struct buffer_head *head,
+ enum migrate_mode mode)
{
struct buffer_head *bh = head;
/* Simple case, sync compaction */
- if (sync) {
+ if (mode != MIGRATE_ASYNC) {
do {
get_bh(bh);
lock_buffer(bh);
}
#else
static inline bool buffer_migrate_lock_buffers(struct buffer_head *head,
- bool sync)
+ enum migrate_mode mode)
{
return true;
}
* 2 for pages with a mapping
* 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
*/
-static int migrate_page_move_mapping(struct address_space *mapping,
+int migrate_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page,
- struct buffer_head *head, bool sync)
+ struct buffer_head *head, enum migrate_mode mode)
{
int expected_count;
void **pslot;
* the mapping back due to an elevated page count, we would have to
* block waiting on other references to be dropped.
*/
- if (!sync && head && !buffer_migrate_lock_buffers(head, sync)) {
+ if (mode == MIGRATE_ASYNC && head &&
+ !buffer_migrate_lock_buffers(head, mode)) {
page_unfreeze_refs(page, expected_count);
spin_unlock_irq(&mapping->tree_lock);
return -EAGAIN;
return 0;
}
+EXPORT_SYMBOL(migrate_page_move_mapping);
/*
* The expected number of remaining references is the same as that
if (PageWriteback(newpage))
end_page_writeback(newpage);
}
+EXPORT_SYMBOL(migrate_page_copy);
/************************************************************
* Migration functions
* Pages are locked upon entry and exit.
*/
int migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page, bool sync)
+ struct page *newpage, struct page *page,
+ enum migrate_mode mode)
{
int rc;
BUG_ON(PageWriteback(page)); /* Writeback must be complete */
- rc = migrate_page_move_mapping(mapping, newpage, page, NULL, sync);
+ rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode);
if (rc)
return rc;
* exist.
*/
int buffer_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page, bool sync)
+ struct page *newpage, struct page *page, enum migrate_mode mode)
{
struct buffer_head *bh, *head;
int rc;
if (!page_has_buffers(page))
- return migrate_page(mapping, newpage, page, sync);
+ return migrate_page(mapping, newpage, page, mode);
head = page_buffers(page);
- rc = migrate_page_move_mapping(mapping, newpage, page, head, sync);
+ rc = migrate_page_move_mapping(mapping, newpage, page, head, mode);
if (rc)
return rc;
* with an IRQ-safe spinlock held. In the sync case, the buffers
* need to be locked now
*/
- if (sync)
- BUG_ON(!buffer_migrate_lock_buffers(head, sync));
+ if (mode != MIGRATE_ASYNC)
+ BUG_ON(!buffer_migrate_lock_buffers(head, mode));
ClearPagePrivate(page);
set_page_private(newpage, page_private(page));
* Default handling if a filesystem does not provide a migration function.
*/
static int fallback_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page, bool sync)
+ struct page *newpage, struct page *page, enum migrate_mode mode)
{
if (PageDirty(page)) {
- if (!sync)
+ /* Only writeback pages in full synchronous migration */
+ if (mode != MIGRATE_SYNC)
return -EBUSY;
return writeout(mapping, page);
}
!try_to_release_page(page, GFP_KERNEL))
return -EAGAIN;
- return migrate_page(mapping, newpage, page, sync);
+ return migrate_page(mapping, newpage, page, mode);
}
/*
* == 0 - success
*/
static int move_to_new_page(struct page *newpage, struct page *page,
- int remap_swapcache, bool sync)
+ int remap_swapcache, enum migrate_mode mode)
{
struct address_space *mapping;
int rc;
mapping = page_mapping(page);
if (!mapping)
- rc = migrate_page(mapping, newpage, page, sync);
+ rc = migrate_page(mapping, newpage, page, mode);
else if (mapping->a_ops->migratepage)
/*
* Most pages have a mapping and most filesystems provide a
* is the most common path for page migration.
*/
rc = mapping->a_ops->migratepage(mapping,
- newpage, page, sync);
+ newpage, page, mode);
else
- rc = fallback_migrate_page(mapping, newpage, page, sync);
+ rc = fallback_migrate_page(mapping, newpage, page, mode);
if (rc) {
newpage->mapping = NULL;
}
static int __unmap_and_move(struct page *page, struct page *newpage,
- int force, bool offlining, bool sync)
+ int force, bool offlining, enum migrate_mode mode)
{
int rc = -EAGAIN;
int remap_swapcache = 1;
struct anon_vma *anon_vma = NULL;
if (!trylock_page(page)) {
- if (!force || !sync)
+ if (!force || mode == MIGRATE_ASYNC)
goto out;
/*
if (PageWriteback(page)) {
/*
- * For !sync, there is no point retrying as the retry loop
- * is expected to be too short for PageWriteback to be cleared
+ * Only in the case of a full syncronous migration is it
+ * necessary to wait for PageWriteback. In the async case,
+ * the retry loop is too short and in the sync-light case,
+ * the overhead of stalling is too much
*/
- if (!sync) {
+ if (mode != MIGRATE_SYNC) {
rc = -EBUSY;
goto uncharge;
}
skip_unmap:
if (!page_mapped(page))
- rc = move_to_new_page(newpage, page, remap_swapcache, sync);
+ rc = move_to_new_page(newpage, page, remap_swapcache, mode);
if (rc && remap_swapcache)
remove_migration_ptes(page, page);
* to the newly allocated page in newpage.
*/
static int unmap_and_move(new_page_t get_new_page, unsigned long private,
- struct page *page, int force, bool offlining, bool sync)
+ struct page *page, int force, bool offlining,
+ enum migrate_mode mode)
{
int rc = 0;
int *result = NULL;
if (unlikely(split_huge_page(page)))
goto out;
- rc = __unmap_and_move(page, newpage, force, offlining, sync);
+ rc = __unmap_and_move(page, newpage, force, offlining, mode);
out:
if (rc != -EAGAIN) {
/*
*/
static int unmap_and_move_huge_page(new_page_t get_new_page,
unsigned long private, struct page *hpage,
- int force, bool offlining, bool sync)
+ int force, bool offlining,
+ enum migrate_mode mode)
{
int rc = 0;
int *result = NULL;
rc = -EAGAIN;
if (!trylock_page(hpage)) {
- if (!force || !sync)
+ if (!force || mode != MIGRATE_SYNC)
goto out;
lock_page(hpage);
}
try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
if (!page_mapped(hpage))
- rc = move_to_new_page(new_hpage, hpage, 1, sync);
+ rc = move_to_new_page(new_hpage, hpage, 1, mode);
if (rc)
remove_migration_ptes(hpage, hpage);
*/
int migrate_pages(struct list_head *from,
new_page_t get_new_page, unsigned long private, bool offlining,
- bool sync)
+ enum migrate_mode mode)
{
int retry = 1;
int nr_failed = 0;
rc = unmap_and_move(get_new_page, private,
page, pass > 2, offlining,
- sync);
+ mode);
switch(rc) {
case -ENOMEM:
int migrate_huge_pages(struct list_head *from,
new_page_t get_new_page, unsigned long private, bool offlining,
- bool sync)
+ enum migrate_mode mode)
{
int retry = 1;
int nr_failed = 0;
rc = unmap_and_move_huge_page(get_new_page,
private, page, pass > 2, offlining,
- sync);
+ mode);
switch(rc) {
case -ENOMEM:
err = 0;
if (!list_empty(&pagelist)) {
err = migrate_pages(&pagelist, new_page_node,
- (unsigned long)pm, 0, true);
+ (unsigned long)pm, 0, MIGRATE_SYNC);
if (err)
putback_lru_pages(&pagelist);
}
* Migrate an array of page address onto an array of nodes and fill
* the corresponding array of status.
*/
-static int do_pages_move(struct mm_struct *mm, struct task_struct *task,
+static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
unsigned long nr_pages,
const void __user * __user *pages,
const int __user *nodes,
int __user *status, int flags)
{
struct page_to_node *pm;
- nodemask_t task_nodes;
unsigned long chunk_nr_pages;
unsigned long chunk_start;
int err;
- task_nodes = cpuset_mems_allowed(task);
-
err = -ENOMEM;
pm = (struct page_to_node *)__get_free_page(GFP_KERNEL);
if (!pm)
const int __user *, nodes,
int __user *, status, int, flags)
{
- const struct cred *cred = current_cred(), *tcred;
struct task_struct *task;
struct mm_struct *mm;
int err;
+ nodemask_t task_nodes;
/* Check flags */
if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL))
rcu_read_unlock();
return -ESRCH;
}
- mm = get_task_mm(task);
- rcu_read_unlock();
-
- if (!mm)
- return -EINVAL;
+ get_task_struct(task);
/*
* Check if this process has the right to modify the specified
- * process. The right exists if the process has administrative
- * capabilities, superuser privileges or the same
- * userid as the target process.
+ * process. Use the regular "ptrace_may_access()" checks.
*/
- rcu_read_lock();
- tcred = __task_cred(task);
- if (cred->euid != tcred->suid && cred->euid != tcred->uid &&
- cred->uid != tcred->suid && cred->uid != tcred->uid &&
- !capable(CAP_SYS_NICE)) {
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) {
rcu_read_unlock();
err = -EPERM;
goto out;
if (err)
goto out;
- if (nodes) {
- err = do_pages_move(mm, task, nr_pages, pages, nodes, status,
- flags);
- } else {
+ task_nodes = cpuset_mems_allowed(task);
+ mm = get_task_mm(task);
+ put_task_struct(task);
+
+ if (!mm)
+ return -EINVAL;
+
+ if (nodes)
+ err = do_pages_move(mm, task_nodes, nr_pages, pages,
+ nodes, status, flags);
+ else
err = do_pages_stat(mm, nr_pages, pages, status);
- }
-out:
mmput(mm);
return err;
+
+out:
+ put_task_struct(task);
+ return err;
}
/*
git.openpandora.org / pandora-kernel.git / blobdiff