#include <linux/capability.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/sched/user.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/pagewalk.h>
#include <linux/mempolicy.h>
#include <linux/syscalls.h>
#include <linux/sched.h>
#include <linux/export.h>
#include <linux/rmap.h>
#include <linux/mmzone.h>
#include <linux/hugetlb.h>
#include <linux/memcontrol.h>
#include <linux/mm_inline.h>
#include <linux/secretmem.h>
#include "internal.h"
struct mlock_fbatch {
local_lock_t lock;
struct folio_batch fbatch;
};
static DEFINE_PER_CPU(struct mlock_fbatch, mlock_fbatch) = {
.lock = INIT_LOCAL_LOCK(lock),
};
bool can_do_mlock(void)
{
if (rlimit(RLIMIT_MEMLOCK) != 0)
return true;
if (capable(CAP_IPC_LOCK))
return true;
return false;
}
EXPORT_SYMBOL(can_do_mlock);
static struct lruvec *__mlock_folio(struct folio *folio, struct lruvec *lruvec)
{
if (!folio_test_clear_lru(folio))
return lruvec;
lruvec = folio_lruvec_relock_irq(folio, lruvec);
if (unlikely(folio_evictable(folio))) {
if (folio_test_unevictable(folio)) {
lruvec_del_folio(lruvec, folio);
folio_clear_unevictable(folio);
lruvec_add_folio(lruvec, folio);
__count_vm_events(UNEVICTABLE_PGRESCUED,
folio_nr_pages(folio));
}
goto out;
}
if (folio_test_unevictable(folio)) {
if (folio_test_mlocked(folio))
folio->mlock_count++;
goto out;
}
lruvec_del_folio(lruvec, folio);
folio_clear_active(folio);
folio_set_unevictable(folio);
folio->mlock_count = !!folio_test_mlocked(folio);
lruvec_add_folio(lruvec, folio);
__count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio));
out:
folio_set_lru(folio);
return lruvec;
}
static struct lruvec *__mlock_new_folio(struct folio *folio, struct lruvec *lruvec)
{
VM_BUG_ON_FOLIO(folio_test_lru(folio), folio);
lruvec = folio_lruvec_relock_irq(folio, lruvec);
if (unlikely(folio_evictable(folio)))
goto out;
folio_set_unevictable(folio);
folio->mlock_count = !!folio_test_mlocked(folio);
__count_vm_events(UNEVICTABLE_PGCULLED, folio_nr_pages(folio));
out:
lruvec_add_folio(lruvec, folio);
folio_set_lru(folio);
return lruvec;
}
static struct lruvec *__munlock_folio(struct folio *folio, struct lruvec *lruvec)
{
int nr_pages = folio_nr_pages(folio);
bool isolated = false;
if (!folio_test_clear_lru(folio))
goto munlock;
isolated = true;
lruvec = folio_lruvec_relock_irq(folio, lruvec);
if (folio_test_unevictable(folio)) {
if (folio->mlock_count)
folio->mlock_count--;
if (folio->mlock_count)
goto out;
}
munlock:
if (folio_test_clear_mlocked(folio)) {
__zone_stat_mod_folio(folio, NR_MLOCK, -nr_pages);
if (isolated || !folio_test_unevictable(folio))
__count_vm_events(UNEVICTABLE_PGMUNLOCKED, nr_pages);
else
__count_vm_events(UNEVICTABLE_PGSTRANDED, nr_pages);
}
if (isolated && folio_test_unevictable(folio) && folio_evictable(folio)) {
lruvec_del_folio(lruvec, folio);
folio_clear_unevictable(folio);
lruvec_add_folio(lruvec, folio);
__count_vm_events(UNEVICTABLE_PGRESCUED, nr_pages);
}
out:
if (isolated)
folio_set_lru(folio);
return lruvec;
}
#define LRU_FOLIO 0x1
#define NEW_FOLIO 0x2
static inline struct folio *mlock_lru(struct folio *folio)
{
return (struct folio *)((unsigned long)folio + LRU_FOLIO);
}
static inline struct folio *mlock_new(struct folio *folio)
{
return (struct folio *)((unsigned long)folio + NEW_FOLIO);
}
static void mlock_folio_batch(struct folio_batch *fbatch)
{
struct lruvec *lruvec = NULL;
unsigned long mlock;
struct folio *folio;
int i;
for (i = 0; i < folio_batch_count(fbatch); i++) {
folio = fbatch->folios[i];
mlock = (unsigned long)folio & (LRU_FOLIO | NEW_FOLIO);
folio = (struct folio *)((unsigned long)folio - mlock);
fbatch->folios[i] = folio;
if (mlock & LRU_FOLIO)
lruvec = __mlock_folio(folio, lruvec);
else if (mlock & NEW_FOLIO)
lruvec = __mlock_new_folio(folio, lruvec);
else
lruvec = __munlock_folio(folio, lruvec);
}
if (lruvec)
unlock_page_lruvec_irq(lruvec);
folios_put(fbatch->folios, folio_batch_count(fbatch));
folio_batch_reinit(fbatch);
}
void mlock_drain_local(void)
{
struct folio_batch *fbatch;
local_lock(&mlock_fbatch.lock);
fbatch = this_cpu_ptr(&mlock_fbatch.fbatch);
if (folio_batch_count(fbatch))
mlock_folio_batch(fbatch);
local_unlock(&mlock_fbatch.lock);
}
void mlock_drain_remote(int cpu)
{
struct folio_batch *fbatch;
WARN_ON_ONCE(cpu_online(cpu));
fbatch = &per_cpu(mlock_fbatch.fbatch, cpu);
if (folio_batch_count(fbatch))
mlock_folio_batch(fbatch);
}
bool need_mlock_drain(int cpu)
{
return folio_batch_count(&per_cpu(mlock_fbatch.fbatch, cpu));
}
void mlock_folio(struct folio *folio)
{
struct folio_batch *fbatch;
local_lock(&mlock_fbatch.lock);
fbatch = this_cpu_ptr(&mlock_fbatch.fbatch);
if (!folio_test_set_mlocked(folio)) {
int nr_pages = folio_nr_pages(folio);
zone_stat_mod_folio(folio, NR_MLOCK, nr_pages);
__count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
}
folio_get(folio);
if (!folio_batch_add(fbatch, mlock_lru(folio)) ||
folio_test_large(folio) || lru_cache_disabled())
mlock_folio_batch(fbatch);
local_unlock(&mlock_fbatch.lock);
}
void mlock_new_folio(struct folio *folio)
{
struct folio_batch *fbatch;
int nr_pages = folio_nr_pages(folio);
local_lock(&mlock_fbatch.lock);
fbatch = this_cpu_ptr(&mlock_fbatch.fbatch);
folio_set_mlocked(folio);
zone_stat_mod_folio(folio, NR_MLOCK, nr_pages);
__count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
folio_get(folio);
if (!folio_batch_add(fbatch, mlock_new(folio)) ||
folio_test_large(folio) || lru_cache_disabled())
mlock_folio_batch(fbatch);
local_unlock(&mlock_fbatch.lock);
}
void munlock_folio(struct folio *folio)
{
struct folio_batch *fbatch;
local_lock(&mlock_fbatch.lock);
fbatch = this_cpu_ptr(&mlock_fbatch.fbatch);
folio_get(folio);
if (!folio_batch_add(fbatch, folio) ||
folio_test_large(folio) || lru_cache_disabled())
mlock_folio_batch(fbatch);
local_unlock(&mlock_fbatch.lock);
}
static int mlock_pte_range(pmd_t *pmd, unsigned long addr,
unsigned long end, struct mm_walk *walk)
{
struct vm_area_struct *vma = walk->vma;
spinlock_t *ptl;
pte_t *start_pte, *pte;
pte_t ptent;
struct folio *folio;
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
if (!pmd_present(*pmd))
goto out;
if (is_huge_zero_pmd(*pmd))
goto out;
folio = page_folio(pmd_page(*pmd));
if (vma->vm_flags & VM_LOCKED)
mlock_folio(folio);
else
munlock_folio(folio);
goto out;
}
start_pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
if (!start_pte) {
walk->action = ACTION_AGAIN;
return 0;
}
for (pte = start_pte; addr != end; pte++, addr += PAGE_SIZE) {
ptent = ptep_get(pte);
if (!pte_present(ptent))
continue;
folio = vm_normal_folio(vma, addr, ptent);
if (!folio || folio_is_zone_device(folio))
continue;
if (folio_test_large(folio))
continue;
if (vma->vm_flags & VM_LOCKED)
mlock_folio(folio);
else
munlock_folio(folio);
}
pte_unmap(start_pte);
out:
spin_unlock(ptl);
cond_resched();
return 0;
}
static void mlock_vma_pages_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end, vm_flags_t newflags)
{
static const struct mm_walk_ops mlock_walk_ops = {
.pmd_entry = mlock_pte_range,
.walk_lock = PGWALK_WRLOCK_VERIFY,
};
if (newflags & VM_LOCKED)
newflags |= VM_IO;
vma_start_write(vma);
vm_flags_reset_once(vma, newflags);
lru_add_drain();
walk_page_range(vma->vm_mm, start, end, &mlock_walk_ops, NULL);
lru_add_drain();
if (newflags & VM_IO) {
newflags &= ~VM_IO;
vm_flags_reset_once(vma, newflags);
}
}
static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
struct vm_area_struct **prev, unsigned long start,
unsigned long end, vm_flags_t newflags)
{
struct mm_struct *mm = vma->vm_mm;
pgoff_t pgoff;
int nr_pages;
int ret = 0;
vm_flags_t oldflags = vma->vm_flags;
if (newflags == oldflags || (oldflags & VM_SPECIAL) ||
is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm) ||
vma_is_dax(vma) || vma_is_secretmem(vma))
goto out;
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(vmi, mm, *prev, start, end, newflags,
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
vma->vm_userfaultfd_ctx, anon_vma_name(vma));
if (*prev) {
vma = *prev;
goto success;
}
if (start != vma->vm_start) {
ret = split_vma(vmi, vma, start, 1);
if (ret)
goto out;
}
if (end != vma->vm_end) {
ret = split_vma(vmi, vma, end, 0);
if (ret)
goto out;
}
success:
nr_pages = (end - start) >> PAGE_SHIFT;
if (!(newflags & VM_LOCKED))
nr_pages = -nr_pages;
else if (oldflags & VM_LOCKED)
nr_pages = 0;
mm->locked_vm += nr_pages;
if ((newflags & VM_LOCKED) && (oldflags & VM_LOCKED)) {
vma_start_write(vma);
vm_flags_reset(vma, newflags);
} else {
mlock_vma_pages_range(vma, start, end, newflags);
}
out:
*prev = vma;
return ret;
}
static int apply_vma_lock_flags(unsigned long start, size_t len,
vm_flags_t flags)
{
unsigned long nstart, end, tmp;
struct vm_area_struct *vma, *prev;
VMA_ITERATOR(vmi, current->mm, start);
VM_BUG_ON(offset_in_page(start));
VM_BUG_ON(len != PAGE_ALIGN(len));
end = start + len;
if (end < start)
return -EINVAL;
if (end == start)
return 0;
vma = vma_iter_load(&vmi);
if (!vma)
return -ENOMEM;
prev = vma_prev(&vmi);
if (start > vma->vm_start)
prev = vma;
nstart = start;
tmp = vma->vm_start;
for_each_vma_range(vmi, vma, end) {
int error;
vm_flags_t newflags;
if (vma->vm_start != tmp)
return -ENOMEM;
newflags = vma->vm_flags & ~VM_LOCKED_MASK;
newflags |= flags;
tmp = vma->vm_end;
if (tmp > end)
tmp = end;
error = mlock_fixup(&vmi, vma, &prev, nstart, tmp, newflags);
if (error)
return error;
tmp = vma_iter_end(&vmi);
nstart = tmp;
}
if (tmp < end)
return -ENOMEM;
return 0;
}
static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm,
unsigned long start, size_t len)
{
struct vm_area_struct *vma;
unsigned long count = 0;
unsigned long end;
VMA_ITERATOR(vmi, mm, start);
if (unlikely(ULONG_MAX - len < start))
end = ULONG_MAX;
else
end = start + len;
for_each_vma_range(vmi, vma, end) {
if (vma->vm_flags & VM_LOCKED) {
if (start > vma->vm_start)
count -= (start - vma->vm_start);
if (end < vma->vm_end) {
count += end - vma->vm_start;
break;
}
count += vma->vm_end - vma->vm_start;
}
}
return count >> PAGE_SHIFT;
}
static int __mlock_posix_error_return(long retval)
{
if (retval == -EFAULT)
retval = -ENOMEM;
else if (retval == -ENOMEM)
retval = -EAGAIN;
return retval;
}
static __must_check int do_mlock(unsigned long start, size_t len, vm_flags_t flags)
{
unsigned long locked;
unsigned long lock_limit;
int error = -ENOMEM;
start = untagged_addr(start);
if (!can_do_mlock())
return -EPERM;
len = PAGE_ALIGN(len + (offset_in_page(start)));
start &= PAGE_MASK;
lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
locked = len >> PAGE_SHIFT;
if (mmap_write_lock_killable(current->mm))
return -EINTR;
locked += current->mm->locked_vm;
if ((locked > lock_limit) && (!capable(CAP_IPC_LOCK))) {
locked -= count_mm_mlocked_page_nr(current->mm,
start, len);
}
if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
error = apply_vma_lock_flags(start, len, flags);
mmap_write_unlock(current->mm);
if (error)
return error;
error = __mm_populate(start, len, 0);
if (error)
return __mlock_posix_error_return(error);
return 0;
}
SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
{
return do_mlock(start, len, VM_LOCKED);
}
SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags)
{
vm_flags_t vm_flags = VM_LOCKED;
if (flags & ~MLOCK_ONFAULT)
return -EINVAL;
if (flags & MLOCK_ONFAULT)
vm_flags |= VM_LOCKONFAULT;
return do_mlock(start, len, vm_flags);
}
SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
{
int ret;
start = untagged_addr(start);
len = PAGE_ALIGN(len + (offset_in_page(start)));
start &= PAGE_MASK;
if (mmap_write_lock_killable(current->mm))
return -EINTR;
ret = apply_vma_lock_flags(start, len, 0);
mmap_write_unlock(current->mm);
return ret;
}
static int apply_mlockall_flags(int flags)
{
VMA_ITERATOR(vmi, current->mm, 0);
struct vm_area_struct *vma, *prev = NULL;
vm_flags_t to_add = 0;
current->mm->def_flags &= ~VM_LOCKED_MASK;
if (flags & MCL_FUTURE) {
current->mm->def_flags |= VM_LOCKED;
if (flags & MCL_ONFAULT)
current->mm->def_flags |= VM_LOCKONFAULT;
if (!(flags & MCL_CURRENT))
goto out;
}
if (flags & MCL_CURRENT) {
to_add |= VM_LOCKED;
if (flags & MCL_ONFAULT)
to_add |= VM_LOCKONFAULT;
}
for_each_vma(vmi, vma) {
vm_flags_t newflags;
newflags = vma->vm_flags & ~VM_LOCKED_MASK;
newflags |= to_add;
mlock_fixup(&vmi, vma, &prev, vma->vm_start, vma->vm_end,
newflags);
cond_resched();
}
out:
return 0;
}
SYSCALL_DEFINE1(mlockall, int, flags)
{
unsigned long lock_limit;
int ret;
if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) ||
flags == MCL_ONFAULT)
return -EINVAL;
if (!can_do_mlock())
return -EPERM;
lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
if (mmap_write_lock_killable(current->mm))
return -EINTR;
ret = -ENOMEM;
if (!(flags & MCL_CURRENT) || (current->mm->total_vm <= lock_limit) ||
capable(CAP_IPC_LOCK))
ret = apply_mlockall_flags(flags);
mmap_write_unlock(current->mm);
if (!ret && (flags & MCL_CURRENT))
mm_populate(0, TASK_SIZE);
return ret;
}
SYSCALL_DEFINE0(munlockall)
{
int ret;
if (mmap_write_lock_killable(current->mm))
return -EINTR;
ret = apply_mlockall_flags(0);
mmap_write_unlock(current->mm);
return ret;
}
static DEFINE_SPINLOCK(shmlock_user_lock);
int user_shm_lock(size_t size, struct ucounts *ucounts)
{
unsigned long lock_limit, locked;
long memlock;
int allowed = 0;
locked = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
lock_limit = rlimit(RLIMIT_MEMLOCK);
if (lock_limit != RLIM_INFINITY)
lock_limit >>= PAGE_SHIFT;
spin_lock(&shmlock_user_lock);
memlock = inc_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked);
if ((memlock == LONG_MAX || memlock > lock_limit) && !capable(CAP_IPC_LOCK)) {
dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked);
goto out;
}
if (!get_ucounts(ucounts)) {
dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, locked);
allowed = 0;
goto out;
}
allowed = 1;
out:
spin_unlock(&shmlock_user_lock);
return allowed;
}
void user_shm_unlock(size_t size, struct ucounts *ucounts)
{
spin_lock(&shmlock_user_lock);
dec_rlimit_ucounts(ucounts, UCOUNT_RLIMIT_MEMLOCK, (size + PAGE_SIZE - 1) >> PAGE_SHIFT);
spin_unlock(&shmlock_user_lock);
put_ucounts(ucounts);
}