#include <linux/numa.h>
#include <linux/perf_event.h>
#include <linux/ptrace.h>
+#include <linux/vmalloc.h>
#include <trace/events/kmem.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
+#include "pgalloc-track.h"
#include "internal.h"
#if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
* covered by this vma.
*/
-static inline unsigned long
-copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+static unsigned long
+copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
unsigned long addr, int *rss)
{
unsigned long vm_flags = vma->vm_flags;
pte_t pte = *src_pte;
struct page *page;
+ swp_entry_t entry = pte_to_swp_entry(pte);
+
+ if (likely(!non_swap_entry(entry))) {
+ if (swap_duplicate(entry) < 0)
+ return entry.val;
+
+ /* make sure dst_mm is on swapoff's mmlist. */
+ if (unlikely(list_empty(&dst_mm->mmlist))) {
+ spin_lock(&mmlist_lock);
+ if (list_empty(&dst_mm->mmlist))
+ list_add(&dst_mm->mmlist,
+ &src_mm->mmlist);
+ spin_unlock(&mmlist_lock);
+ }
+ rss[MM_SWAPENTS]++;
+ } else if (is_migration_entry(entry)) {
+ page = migration_entry_to_page(entry);
- /* pte contains position in swap or file, so copy. */
- if (unlikely(!pte_present(pte))) {
- swp_entry_t entry = pte_to_swp_entry(pte);
-
- if (likely(!non_swap_entry(entry))) {
- if (swap_duplicate(entry) < 0)
- return entry.val;
-
- /* make sure dst_mm is on swapoff's mmlist. */
- if (unlikely(list_empty(&dst_mm->mmlist))) {
- spin_lock(&mmlist_lock);
- if (list_empty(&dst_mm->mmlist))
- list_add(&dst_mm->mmlist,
- &src_mm->mmlist);
- spin_unlock(&mmlist_lock);
- }
- rss[MM_SWAPENTS]++;
- } else if (is_migration_entry(entry)) {
- page = migration_entry_to_page(entry);
-
- rss[mm_counter(page)]++;
-
- if (is_write_migration_entry(entry) &&
- is_cow_mapping(vm_flags)) {
- /*
- * COW mappings require pages in both
- * parent and child to be set to read.
- */
- make_migration_entry_read(&entry);
- pte = swp_entry_to_pte(entry);
- if (pte_swp_soft_dirty(*src_pte))
- pte = pte_swp_mksoft_dirty(pte);
- if (pte_swp_uffd_wp(*src_pte))
- pte = pte_swp_mkuffd_wp(pte);
- set_pte_at(src_mm, addr, src_pte, pte);
- }
- } else if (is_device_private_entry(entry)) {
- page = device_private_entry_to_page(entry);
+ rss[mm_counter(page)]++;
+ if (is_write_migration_entry(entry) &&
+ is_cow_mapping(vm_flags)) {
/*
- * Update rss count even for unaddressable pages, as
- * they should treated just like normal pages in this
- * respect.
- *
- * We will likely want to have some new rss counters
- * for unaddressable pages, at some point. But for now
- * keep things as they are.
+ * COW mappings require pages in both
+ * parent and child to be set to read.
*/
- get_page(page);
- rss[mm_counter(page)]++;
- page_dup_rmap(page, false);
+ make_migration_entry_read(&entry);
+ pte = swp_entry_to_pte(entry);
+ if (pte_swp_soft_dirty(*src_pte))
+ pte = pte_swp_mksoft_dirty(pte);
+ if (pte_swp_uffd_wp(*src_pte))
+ pte = pte_swp_mkuffd_wp(pte);
+ set_pte_at(src_mm, addr, src_pte, pte);
+ }
+ } else if (is_device_private_entry(entry)) {
+ page = device_private_entry_to_page(entry);
- /*
- * We do not preserve soft-dirty information, because so
- * far, checkpoint/restore is the only feature that
- * requires that. And checkpoint/restore does not work
- * when a device driver is involved (you cannot easily
- * save and restore device driver state).
- */
- if (is_write_device_private_entry(entry) &&
- is_cow_mapping(vm_flags)) {
- make_device_private_entry_read(&entry);
- pte = swp_entry_to_pte(entry);
- if (pte_swp_uffd_wp(*src_pte))
- pte = pte_swp_mkuffd_wp(pte);
- set_pte_at(src_mm, addr, src_pte, pte);
- }
+ /*
+ * Update rss count even for unaddressable pages, as
+ * they should treated just like normal pages in this
+ * respect.
+ *
+ * We will likely want to have some new rss counters
+ * for unaddressable pages, at some point. But for now
+ * keep things as they are.
+ */
+ get_page(page);
+ rss[mm_counter(page)]++;
+ page_dup_rmap(page, false);
+
+ /*
+ * We do not preserve soft-dirty information, because so
+ * far, checkpoint/restore is the only feature that
+ * requires that. And checkpoint/restore does not work
+ * when a device driver is involved (you cannot easily
+ * save and restore device driver state).
+ */
+ if (is_write_device_private_entry(entry) &&
+ is_cow_mapping(vm_flags)) {
+ make_device_private_entry_read(&entry);
+ pte = swp_entry_to_pte(entry);
+ if (pte_swp_uffd_wp(*src_pte))
+ pte = pte_swp_mkuffd_wp(pte);
+ set_pte_at(src_mm, addr, src_pte, pte);
}
- goto out_set_pte;
}
+ set_pte_at(dst_mm, addr, dst_pte, pte);
+ return 0;
+}
+
+static inline void
+copy_present_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+ pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma,
+ unsigned long addr, int *rss)
+{
+ unsigned long vm_flags = vma->vm_flags;
+ pte_t pte = *src_pte;
+ struct page *page;
/*
* If it's a COW mapping, write protect it both
rss[mm_counter(page)]++;
}
-out_set_pte:
set_pte_at(dst_mm, addr, dst_pte, pte);
- return 0;
}
static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
progress++;
continue;
}
- entry.val = copy_one_pte(dst_mm, src_mm, dst_pte, src_pte,
+ if (unlikely(!pte_present(*src_pte))) {
+ entry.val = copy_nonpresent_pte(dst_mm, src_mm,
+ dst_pte, src_pte,
vma, addr, rss);
- if (entry.val)
- break;
+ if (entry.val)
+ break;
+ progress += 8;
+ continue;
+ }
+ copy_present_pte(dst_mm, src_mm, dst_pte, src_pte,
+ vma, addr, rss);
progress += 8;
} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
unsigned long addr, unsigned long end,
- pte_fn_t fn, void *data, bool create)
+ pte_fn_t fn, void *data, bool create,
+ pgtbl_mod_mask *mask)
{
pte_t *pte;
int err = 0;
if (create) {
pte = (mm == &init_mm) ?
- pte_alloc_kernel(pmd, addr) :
+ pte_alloc_kernel_track(pmd, addr, mask) :
pte_alloc_map_lock(mm, pmd, addr, &ptl);
if (!pte)
return -ENOMEM;
break;
}
} while (addr += PAGE_SIZE, addr != end);
+ *mask |= PGTBL_PTE_MODIFIED;
arch_leave_lazy_mmu_mode();
static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
unsigned long addr, unsigned long end,
- pte_fn_t fn, void *data, bool create)
+ pte_fn_t fn, void *data, bool create,
+ pgtbl_mod_mask *mask)
{
pmd_t *pmd;
unsigned long next;
BUG_ON(pud_huge(*pud));
if (create) {
- pmd = pmd_alloc(mm, pud, addr);
+ pmd = pmd_alloc_track(mm, pud, addr, mask);
if (!pmd)
return -ENOMEM;
} else {
next = pmd_addr_end(addr, end);
if (create || !pmd_none_or_clear_bad(pmd)) {
err = apply_to_pte_range(mm, pmd, addr, next, fn, data,
- create);
+ create, mask);
if (err)
break;
}
static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
unsigned long addr, unsigned long end,
- pte_fn_t fn, void *data, bool create)
+ pte_fn_t fn, void *data, bool create,
+ pgtbl_mod_mask *mask)
{
pud_t *pud;
unsigned long next;
int err = 0;
if (create) {
- pud = pud_alloc(mm, p4d, addr);
+ pud = pud_alloc_track(mm, p4d, addr, mask);
if (!pud)
return -ENOMEM;
} else {
next = pud_addr_end(addr, end);
if (create || !pud_none_or_clear_bad(pud)) {
err = apply_to_pmd_range(mm, pud, addr, next, fn, data,
- create);
+ create, mask);
if (err)
break;
}
static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
unsigned long addr, unsigned long end,
- pte_fn_t fn, void *data, bool create)
+ pte_fn_t fn, void *data, bool create,
+ pgtbl_mod_mask *mask)
{
p4d_t *p4d;
unsigned long next;
int err = 0;
if (create) {
- p4d = p4d_alloc(mm, pgd, addr);
+ p4d = p4d_alloc_track(mm, pgd, addr, mask);
if (!p4d)
return -ENOMEM;
} else {
next = p4d_addr_end(addr, end);
if (create || !p4d_none_or_clear_bad(p4d)) {
err = apply_to_pud_range(mm, p4d, addr, next, fn, data,
- create);
+ create, mask);
if (err)
break;
}
void *data, bool create)
{
pgd_t *pgd;
- unsigned long next;
+ unsigned long start = addr, next;
unsigned long end = addr + size;
+ pgtbl_mod_mask mask = 0;
int err = 0;
if (WARN_ON(addr >= end))
next = pgd_addr_end(addr, end);
if (!create && pgd_none_or_clear_bad(pgd))
continue;
- err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create);
+ err = apply_to_p4d_range(mm, pgd, addr, next, fn, data, create, &mask);
if (err)
break;
} while (pgd++, addr = next, addr != end);
+ if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
+ arch_sync_kernel_mappings(start, start + size);
+
return err;
}
* page count reference, and the page is locked,
* it's dark out, and we're wearing sunglasses. Hit it.
*/
- wp_page_reuse(vmf);
unlock_page(page);
+ wp_page_reuse(vmf);
return VM_FAULT_WRITE;
} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
(VM_WRITE|VM_SHARED))) {