#include <linux/pagewalk.h>
#include <linux/hmm.h>
#include <linux/init.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/mmzone.h>
#include <linux/pagemap.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
#include <linux/memremap.h>
#include <linux/sched/mm.h>
#include <linux/jump_label.h>
#include <linux/dma-mapping.h>
#include <linux/mmu_notifier.h>
#include <linux/memory_hotplug.h>
#include "internal.h"
struct hmm_vma_walk {
struct hmm_range *range;
unsigned long last;
};
enum {
HMM_NEED_FAULT = 1 << 0,
HMM_NEED_WRITE_FAULT = 1 << 1,
HMM_NEED_ALL_BITS = HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT,
};
static int hmm_pfns_fill(unsigned long addr, unsigned long end,
struct hmm_range *range, unsigned long cpu_flags)
{
unsigned long i = (addr - range->start) >> PAGE_SHIFT;
for (; addr < end; addr += PAGE_SIZE, i++)
range->hmm_pfns[i] = cpu_flags;
return 0;
}
static int hmm_vma_fault(unsigned long addr, unsigned long end,
unsigned int required_fault, struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct vm_area_struct *vma = walk->vma;
unsigned int fault_flags = FAULT_FLAG_REMOTE;
WARN_ON_ONCE(!required_fault);
hmm_vma_walk->last = addr;
if (required_fault & HMM_NEED_WRITE_FAULT) {
if (!(vma->vm_flags & VM_WRITE))
return -EPERM;
fault_flags |= FAULT_FLAG_WRITE;
}
for (; addr < end; addr += PAGE_SIZE)
if (handle_mm_fault(vma, addr, fault_flags, NULL) &
VM_FAULT_ERROR)
return -EFAULT;
return -EBUSY;
}
static unsigned int hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
unsigned long pfn_req_flags,
unsigned long cpu_flags)
{
struct hmm_range *range = hmm_vma_walk->range;
pfn_req_flags &= range->pfn_flags_mask;
pfn_req_flags |= range->default_flags;
if (!(pfn_req_flags & HMM_PFN_REQ_FAULT))
return 0;
if ((pfn_req_flags & HMM_PFN_REQ_WRITE) &&
!(cpu_flags & HMM_PFN_WRITE))
return HMM_NEED_FAULT | HMM_NEED_WRITE_FAULT;
if (!(cpu_flags & HMM_PFN_VALID))
return HMM_NEED_FAULT;
return 0;
}
static unsigned int
hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
const unsigned long hmm_pfns[], unsigned long npages,
unsigned long cpu_flags)
{
struct hmm_range *range = hmm_vma_walk->range;
unsigned int required_fault = 0;
unsigned long i;
if (!((range->default_flags | range->pfn_flags_mask) &
HMM_PFN_REQ_FAULT))
return 0;
for (i = 0; i < npages; ++i) {
required_fault |= hmm_pte_need_fault(hmm_vma_walk, hmm_pfns[i],
cpu_flags);
if (required_fault == HMM_NEED_ALL_BITS)
return required_fault;
}
return required_fault;
}
static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
__always_unused int depth, struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned int required_fault;
unsigned long i, npages;
unsigned long *hmm_pfns;
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
hmm_pfns = &range->hmm_pfns[i];
required_fault =
hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0);
if (!walk->vma) {
if (required_fault)
return -EFAULT;
return hmm_pfns_fill(addr, end, range, HMM_PFN_ERROR);
}
if (required_fault)
return hmm_vma_fault(addr, end, required_fault, walk);
return hmm_pfns_fill(addr, end, range, 0);
}
static inline unsigned long hmm_pfn_flags_order(unsigned long order)
{
return order << HMM_PFN_ORDER_SHIFT;
}
static inline unsigned long pmd_to_hmm_pfn_flags(struct hmm_range *range,
pmd_t pmd)
{
if (pmd_protnone(pmd))
return 0;
return (pmd_write(pmd) ? (HMM_PFN_VALID | HMM_PFN_WRITE) :
HMM_PFN_VALID) |
hmm_pfn_flags_order(PMD_SHIFT - PAGE_SHIFT);
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
unsigned long end, unsigned long hmm_pfns[],
pmd_t pmd)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned long pfn, npages, i;
unsigned int required_fault;
unsigned long cpu_flags;
npages = (end - addr) >> PAGE_SHIFT;
cpu_flags = pmd_to_hmm_pfn_flags(range, pmd);
required_fault =
hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, cpu_flags);
if (required_fault)
return hmm_vma_fault(addr, end, required_fault, walk);
pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++)
hmm_pfns[i] = pfn | cpu_flags;
return 0;
}
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
unsigned long end, unsigned long hmm_pfns[], pmd_t pmd);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range,
pte_t pte)
{
if (pte_none(pte) || !pte_present(pte) || pte_protnone(pte))
return 0;
return pte_write(pte) ? (HMM_PFN_VALID | HMM_PFN_WRITE) : HMM_PFN_VALID;
}
static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
unsigned long end, pmd_t *pmdp, pte_t *ptep,
unsigned long *hmm_pfn)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned int required_fault;
unsigned long cpu_flags;
pte_t pte = ptep_get(ptep);
uint64_t pfn_req_flags = *hmm_pfn;
if (pte_none_mostly(pte)) {
required_fault =
hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
if (required_fault)
goto fault;
*hmm_pfn = 0;
return 0;
}
if (!pte_present(pte)) {
swp_entry_t entry = pte_to_swp_entry(pte);
if (is_device_private_entry(entry) &&
pfn_swap_entry_to_page(entry)->pgmap->owner ==
range->dev_private_owner) {
cpu_flags = HMM_PFN_VALID;
if (is_writable_device_private_entry(entry))
cpu_flags |= HMM_PFN_WRITE;
*hmm_pfn = swp_offset_pfn(entry) | cpu_flags;
return 0;
}
required_fault =
hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0);
if (!required_fault) {
*hmm_pfn = 0;
return 0;
}
if (!non_swap_entry(entry))
goto fault;
if (is_device_private_entry(entry))
goto fault;
if (is_device_exclusive_entry(entry))
goto fault;
if (is_migration_entry(entry)) {
pte_unmap(ptep);
hmm_vma_walk->last = addr;
migration_entry_wait(walk->mm, pmdp, addr);
return -EBUSY;
}
pte_unmap(ptep);
return -EFAULT;
}
cpu_flags = pte_to_hmm_pfn_flags(range, pte);
required_fault =
hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags);
if (required_fault)
goto fault;
if (!vm_normal_page(walk->vma, addr, pte) &&
!pte_devmap(pte) &&
!is_zero_pfn(pte_pfn(pte))) {
if (hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, 0)) {
pte_unmap(ptep);
return -EFAULT;
}
*hmm_pfn = HMM_PFN_ERROR;
return 0;
}
*hmm_pfn = pte_pfn(pte) | cpu_flags;
return 0;
fault:
pte_unmap(ptep);
return hmm_vma_fault(addr, end, required_fault, walk);
}
static int hmm_vma_walk_pmd(pmd_t *pmdp,
unsigned long start,
unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned long *hmm_pfns =
&range->hmm_pfns[(start - range->start) >> PAGE_SHIFT];
unsigned long npages = (end - start) >> PAGE_SHIFT;
unsigned long addr = start;
pte_t *ptep;
pmd_t pmd;
again:
pmd = pmdp_get_lockless(pmdp);
if (pmd_none(pmd))
return hmm_vma_walk_hole(start, end, -1, walk);
if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0)) {
hmm_vma_walk->last = addr;
pmd_migration_entry_wait(walk->mm, pmdp);
return -EBUSY;
}
return hmm_pfns_fill(start, end, range, 0);
}
if (!pmd_present(pmd)) {
if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0))
return -EFAULT;
return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
}
if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) {
pmd = pmdp_get_lockless(pmdp);
if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd))
goto again;
return hmm_vma_handle_pmd(walk, addr, end, hmm_pfns, pmd);
}
if (pmd_bad(pmd)) {
if (hmm_range_need_fault(hmm_vma_walk, hmm_pfns, npages, 0))
return -EFAULT;
return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
}
ptep = pte_offset_map(pmdp, addr);
if (!ptep)
goto again;
for (; addr < end; addr += PAGE_SIZE, ptep++, hmm_pfns++) {
int r;
r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, hmm_pfns);
if (r) {
return r;
}
}
pte_unmap(ptep - 1);
return 0;
}
#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && \
defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
static inline unsigned long pud_to_hmm_pfn_flags(struct hmm_range *range,
pud_t pud)
{
if (!pud_present(pud))
return 0;
return (pud_write(pud) ? (HMM_PFN_VALID | HMM_PFN_WRITE) :
HMM_PFN_VALID) |
hmm_pfn_flags_order(PUD_SHIFT - PAGE_SHIFT);
}
static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned long addr = start;
pud_t pud;
spinlock_t *ptl = pud_trans_huge_lock(pudp, walk->vma);
if (!ptl)
return 0;
walk->action = ACTION_CONTINUE;
pud = READ_ONCE(*pudp);
if (pud_none(pud)) {
spin_unlock(ptl);
return hmm_vma_walk_hole(start, end, -1, walk);
}
if (pud_huge(pud) && pud_devmap(pud)) {
unsigned long i, npages, pfn;
unsigned int required_fault;
unsigned long *hmm_pfns;
unsigned long cpu_flags;
if (!pud_present(pud)) {
spin_unlock(ptl);
return hmm_vma_walk_hole(start, end, -1, walk);
}
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
hmm_pfns = &range->hmm_pfns[i];
cpu_flags = pud_to_hmm_pfn_flags(range, pud);
required_fault = hmm_range_need_fault(hmm_vma_walk, hmm_pfns,
npages, cpu_flags);
if (required_fault) {
spin_unlock(ptl);
return hmm_vma_fault(addr, end, required_fault, walk);
}
pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
for (i = 0; i < npages; ++i, ++pfn)
hmm_pfns[i] = pfn | cpu_flags;
goto out_unlock;
}
walk->action = ACTION_SUBTREE;
out_unlock:
spin_unlock(ptl);
return 0;
}
#else
#define hmm_vma_walk_pud NULL
#endif
#ifdef CONFIG_HUGETLB_PAGE
static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
unsigned long start, unsigned long end,
struct mm_walk *walk)
{
unsigned long addr = start, i, pfn;
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
unsigned int required_fault;
unsigned long pfn_req_flags;
unsigned long cpu_flags;
spinlock_t *ptl;
pte_t entry;
ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
entry = huge_ptep_get(pte);
i = (start - range->start) >> PAGE_SHIFT;
pfn_req_flags = range->hmm_pfns[i];
cpu_flags = pte_to_hmm_pfn_flags(range, entry) |
hmm_pfn_flags_order(huge_page_order(hstate_vma(vma)));
required_fault =
hmm_pte_need_fault(hmm_vma_walk, pfn_req_flags, cpu_flags);
if (required_fault) {
int ret;
spin_unlock(ptl);
hugetlb_vma_unlock_read(vma);
ret = hmm_vma_fault(addr, end, required_fault, walk);
hugetlb_vma_lock_read(vma);
return ret;
}
pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT);
for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
range->hmm_pfns[i] = pfn | cpu_flags;
spin_unlock(ptl);
return 0;
}
#else
#define hmm_vma_walk_hugetlb_entry NULL
#endif /* CONFIG_HUGETLB_PAGE */
static int hmm_vma_walk_test(unsigned long start, unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
if (!(vma->vm_flags & (VM_IO | VM_PFNMAP)) &&
vma->vm_flags & VM_READ)
return 0;
if (hmm_range_need_fault(hmm_vma_walk,
range->hmm_pfns +
((start - range->start) >> PAGE_SHIFT),
(end - start) >> PAGE_SHIFT, 0))
return -EFAULT;
hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
return 1;
}
static const struct mm_walk_ops hmm_walk_ops = {
.pud_entry = hmm_vma_walk_pud,
.pmd_entry = hmm_vma_walk_pmd,
.pte_hole = hmm_vma_walk_hole,
.hugetlb_entry = hmm_vma_walk_hugetlb_entry,
.test_walk = hmm_vma_walk_test,
.walk_lock = PGWALK_RDLOCK,
};
int hmm_range_fault(struct hmm_range *range)
{
struct hmm_vma_walk hmm_vma_walk = {
.range = range,
.last = range->start,
};
struct mm_struct *mm = range->notifier->mm;
int ret;
mmap_assert_locked(mm);
do {
if (mmu_interval_check_retry(range->notifier,
range->notifier_seq))
return -EBUSY;
ret = walk_page_range(mm, hmm_vma_walk.last, range->end,
&hmm_walk_ops, &hmm_vma_walk);
} while (ret == -EBUSY);
return ret;
}
EXPORT_SYMBOL