#include <linux/userfaultfd_k.h>
#include <linux/dax.h>
#include <linux/oom.h>
+#include <linux/numa.h>
#include <asm/io.h>
#include <asm/mmu_context.h>
spinlock_t *ptl;
retval = -EINVAL;
- if (PageAnon(page))
+ if (PageAnon(page) || PageSlab(page) || page_has_type(page))
goto out;
retval = -ENOMEM;
flush_dcache_page(page);
* under mm->mmap_sem write-lock, so it can change vma->vm_flags.
* Caller must set VM_MIXEDMAP on vma if it wants to call this
* function from other places, for example from page-fault handler.
+ *
+ * Return: %0 on success, negative error code otherwise.
*/
int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
struct page *page)
* @size: size of map area
* @prot: page protection flags for this mapping
*
- * Note: this is only safe if the mm semaphore is held when called.
+ * Note: this is only safe if the mm semaphore is held when called.
+ *
+ * Return: %0 on success, negative error code otherwise.
*/
int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
unsigned long pfn, unsigned long size, pgprot_t prot)
*
* NOTE! Some drivers might want to tweak vma->vm_page_prot first to get
* whatever write-combining details or similar.
+ *
+ * Return: %0 on success, negative error code otherwise.
*/
int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len)
{
*
* This function handles all that is needed to finish a write page fault in a
* shared mapping due to PTE being read-only once the mapped page is prepared.
- * It handles locking of PTE and modifying it. The function returns
- * VM_FAULT_WRITE on success, 0 when PTE got changed before we acquired PTE
- * lock.
+ * It handles locking of PTE and modifying it.
*
* The function expects the page to be locked or other protection against
* concurrent faults / writeback (such as DAX radix tree locks).
+ *
+ * Return: %VM_FAULT_WRITE on success, %0 when PTE got changed before
+ * we acquired PTE lock.
*/
vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf)
{
* Take out anonymous pages first, anonymous shared vmas are
* not dirty accountable.
*/
- if (PageAnon(vmf->page) && !PageKsm(vmf->page)) {
+ if (PageAnon(vmf->page)) {
int total_map_swapcount;
+ if (PageKsm(vmf->page) && (PageSwapCache(vmf->page) ||
+ page_count(vmf->page) != 1))
+ goto copy;
if (!trylock_page(vmf->page)) {
get_page(vmf->page);
pte_unmap_unlock(vmf->pte, vmf->ptl);
}
put_page(vmf->page);
}
+ if (PageKsm(vmf->page)) {
+ bool reused = reuse_ksm_page(vmf->page, vmf->vma,
+ vmf->address);
+ unlock_page(vmf->page);
+ if (!reused)
+ goto copy;
+ wp_page_reuse(vmf);
+ return VM_FAULT_WRITE;
+ }
if (reuse_swap_page(vmf->page, &total_map_swapcount)) {
if (total_map_swapcount == 1) {
/*
(VM_WRITE|VM_SHARED))) {
return wp_page_shared(vmf);
}
-
+copy:
/*
* Ok, we need to copy. Oh, well..
*/
*
* Target users are page handler itself and implementations of
* vm_ops->map_pages.
+ *
+ * Return: %0 on success, %VM_FAULT_ code in case of error.
*/
vm_fault_t alloc_set_pte(struct vm_fault *vmf, struct mem_cgroup *memcg,
struct page *page)
* This function handles all that is needed to finish a page fault once the
* page to fault in is prepared. It handles locking of PTEs, inserts PTE for
* given page, adds reverse page mapping, handles memcg charges and LRU
- * addition. The function returns 0 on success, VM_FAULT_ code in case of
- * error.
+ * addition.
*
* The function expects the page to be locked and on success it consumes a
* reference of a page being mapped (for the PTE which maps it).
+ *
+ * Return: %0 on success, %VM_FAULT_ code in case of error.
*/
vm_fault_t finish_fault(struct vm_fault *vmf)
{
static int __init fault_around_debugfs(void)
{
- void *ret;
-
- ret = debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL,
- &fault_around_bytes_fops);
- if (!ret)
- pr_warn("Failed to create fault_around_bytes in debugfs");
+ debugfs_create_file_unsafe("fault_around_bytes", 0644, NULL, NULL,
+ &fault_around_bytes_fops);
return 0;
}
late_initcall(fault_around_debugfs);
* but allow concurrent faults).
* The mmap_sem may have been released depending on flags and our
* return value. See filemap_fault() and __lock_page_or_retry().
+ * If mmap_sem is released, vma may become invalid (for example
+ * by other thread calling munmap()).
*/
static vm_fault_t do_fault(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
+ struct mm_struct *vm_mm = vma->vm_mm;
vm_fault_t ret;
/*
/* preallocated pagetable is unused: free it */
if (vmf->prealloc_pte) {
- pte_free(vma->vm_mm, vmf->prealloc_pte);
+ pte_free(vm_mm, vmf->prealloc_pte);
vmf->prealloc_pte = NULL;
}
return ret;
{
struct vm_area_struct *vma = vmf->vma;
struct page *page = NULL;
- int page_nid = -1;
+ int page_nid = NUMA_NO_NODE;
int last_cpupid;
int target_nid;
bool migrated = false;
- pte_t pte;
+ pte_t pte, old_pte;
bool was_writable = pte_savedwrite(vmf->orig_pte);
int flags = 0;
* Make it present again, Depending on how arch implementes non
* accessible ptes, some can allow access by kernel mode.
*/
- pte = ptep_modify_prot_start(vma->vm_mm, vmf->address, vmf->pte);
- pte = pte_modify(pte, vma->vm_page_prot);
+ old_pte = ptep_modify_prot_start(vma, vmf->address, vmf->pte);
+ pte = pte_modify(old_pte, vma->vm_page_prot);
pte = pte_mkyoung(pte);
if (was_writable)
pte = pte_mkwrite(pte);
- ptep_modify_prot_commit(vma->vm_mm, vmf->address, vmf->pte, pte);
+ ptep_modify_prot_commit(vma, vmf->address, vmf->pte, old_pte, pte);
update_mmu_cache(vma, vmf->address, vmf->pte);
page = vm_normal_page(vma, vmf->address, pte);
target_nid = numa_migrate_prep(page, vma, vmf->address, page_nid,
&flags);
pte_unmap_unlock(vmf->pte, vmf->ptl);
- if (target_nid == -1) {
+ if (target_nid == NUMA_NO_NODE) {
put_page(page);
goto out;
}
flags |= TNF_MIGRATE_FAIL;
out:
- if (page_nid != -1)
+ if (page_nid != NUMA_NO_NODE)
task_numa_fault(last_cpupid, page_nid, 1, flags);
return 0;
}
*
* Only IO mappings and raw PFN mappings are allowed.
*
- * Returns zero and the pfn at @pfn on success, -ve otherwise.
+ * Return: zero and the pfn at @pfn on success, -ve otherwise.
*/
int follow_pfn(struct vm_area_struct *vma, unsigned long address,
unsigned long *pfn)
* @gup_flags: flags modifying lookup behaviour
*
* The caller must hold a reference on @mm.
+ *
+ * Return: number of bytes copied from source to destination.
*/
int access_remote_vm(struct mm_struct *mm, unsigned long addr,
void *buf, int len, unsigned int gup_flags)