summaryrefslogtreecommitdiffstats
path: root/mm/hugetlb.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r--mm/hugetlb.c133
1 files changed, 82 insertions, 51 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a80832487981..e37efd5d8318 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3238,24 +3238,35 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
struct page *ptepage;
unsigned long addr;
int cow;
+ struct address_space *mapping = vma->vm_file->f_mapping;
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
- unsigned long mmun_start; /* For mmu_notifiers */
- unsigned long mmun_end; /* For mmu_notifiers */
+ struct mmu_notifier_range range;
int ret = 0;
cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
- mmun_start = vma->vm_start;
- mmun_end = vma->vm_end;
- if (cow)
- mmu_notifier_invalidate_range_start(src, mmun_start, mmun_end);
+ if (cow) {
+ mmu_notifier_range_init(&range, src, vma->vm_start,
+ vma->vm_end);
+ mmu_notifier_invalidate_range_start(&range);
+ } else {
+ /*
+ * For shared mappings i_mmap_rwsem must be held to call
+ * huge_pte_alloc, otherwise the returned ptep could go
+ * away if part of a shared pmd and another thread calls
+ * huge_pmd_unshare.
+ */
+ i_mmap_lock_read(mapping);
+ }
for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
spinlock_t *src_ptl, *dst_ptl;
+
src_pte = huge_pte_offset(src, addr, sz);
if (!src_pte)
continue;
+
dst_pte = huge_pte_alloc(dst, addr, sz);
if (!dst_pte) {
ret = -ENOMEM;
@@ -3325,7 +3336,9 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
}
if (cow)
- mmu_notifier_invalidate_range_end(src, mmun_start, mmun_end);
+ mmu_notifier_invalidate_range_end(&range);
+ else
+ i_mmap_unlock_read(mapping);
return ret;
}
@@ -3342,8 +3355,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
struct page *page;
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
- unsigned long mmun_start = start; /* For mmu_notifiers */
- unsigned long mmun_end = end; /* For mmu_notifiers */
+ struct mmu_notifier_range range;
WARN_ON(!is_vm_hugetlb_page(vma));
BUG_ON(start & ~huge_page_mask(h));
@@ -3359,8 +3371,9 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
/*
* If sharing possible, alert mmu notifiers of worst case.
*/
- adjust_range_if_pmd_sharing_possible(vma, &mmun_start, &mmun_end);
- mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+ mmu_notifier_range_init(&range, mm, start, end);
+ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
+ mmu_notifier_invalidate_range_start(&range);
address = start;
for (; address < end; address += sz) {
ptep = huge_pte_offset(mm, address, sz);
@@ -3428,7 +3441,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
if (ref_page)
break;
}
- mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
+ mmu_notifier_invalidate_range_end(&range);
tlb_end_vma(tlb, vma);
}
@@ -3546,9 +3559,8 @@ static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
struct page *old_page, *new_page;
int outside_reserve = 0;
vm_fault_t ret = 0;
- unsigned long mmun_start; /* For mmu_notifiers */
- unsigned long mmun_end; /* For mmu_notifiers */
unsigned long haddr = address & huge_page_mask(h);
+ struct mmu_notifier_range range;
pte = huge_ptep_get(ptep);
old_page = pte_page(pte);
@@ -3627,9 +3639,8 @@ retry_avoidcopy:
__SetPageUptodate(new_page);
set_page_huge_active(new_page);
- mmun_start = haddr;
- mmun_end = mmun_start + huge_page_size(h);
- mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
+ mmu_notifier_range_init(&range, mm, haddr, haddr + huge_page_size(h));
+ mmu_notifier_invalidate_range_start(&range);
/*
* Retake the page table lock to check for racing updates
@@ -3642,7 +3653,7 @@ retry_avoidcopy:
/* Break COW */
huge_ptep_clear_flush(vma, haddr, ptep);
- mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
+ mmu_notifier_invalidate_range(mm, range.start, range.end);
set_huge_pte_at(mm, haddr, ptep,
make_huge_pte(vma, new_page, 1));
page_remove_rmap(old_page, true);
@@ -3651,7 +3662,7 @@ retry_avoidcopy:
new_page = old_page;
}
spin_unlock(ptl);
- mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
+ mmu_notifier_invalidate_range_end(&range);
out_release_all:
restore_reserve_on_error(h, vma, haddr, new_page);
put_page(new_page);
@@ -3744,16 +3755,16 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
}
/*
- * Use page lock to guard against racing truncation
- * before we get page_table_lock.
+ * We can not race with truncation due to holding i_mmap_rwsem.
+ * Check once here for faults beyond end of file.
*/
+ size = i_size_read(mapping->host) >> huge_page_shift(h);
+ if (idx >= size)
+ goto out;
+
retry:
page = find_lock_page(mapping, idx);
if (!page) {
- size = i_size_read(mapping->host) >> huge_page_shift(h);
- if (idx >= size)
- goto out;
-
/*
* Check for page in userfault range
*/
@@ -3773,14 +3784,18 @@ retry:
};
/*
- * hugetlb_fault_mutex must be dropped before
- * handling userfault. Reacquire after handling
- * fault to make calling code simpler.
+ * hugetlb_fault_mutex and i_mmap_rwsem must be
+ * dropped before handling userfault. Reacquire
+ * after handling fault to make calling code simpler.
*/
hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping,
idx, haddr);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+ i_mmap_unlock_read(mapping);
+
ret = handle_userfault(&vmf, VM_UFFD_MISSING);
+
+ i_mmap_lock_read(mapping);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
goto out;
}
@@ -3839,9 +3854,6 @@ retry:
}
ptl = huge_pte_lock(h, mm, ptep);
- size = i_size_read(mapping->host) >> huge_page_shift(h);
- if (idx >= size)
- goto backout;
ret = 0;
if (!huge_pte_none(huge_ptep_get(ptep)))
@@ -3928,6 +3940,11 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
ptep = huge_pte_offset(mm, haddr, huge_page_size(h));
if (ptep) {
+ /*
+ * Since we hold no locks, ptep could be stale. That is
+ * OK as we are only making decisions based on content and
+ * not actually modifying content here.
+ */
entry = huge_ptep_get(ptep);
if (unlikely(is_hugetlb_entry_migration(entry))) {
migration_entry_wait_huge(vma, mm, ptep);
@@ -3935,20 +3952,33 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
return VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(hstate_index(h));
- } else {
- ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
- if (!ptep)
- return VM_FAULT_OOM;
}
+ /*
+ * Acquire i_mmap_rwsem before calling huge_pte_alloc and hold
+ * until finished with ptep. This serves two purposes:
+ * 1) It prevents huge_pmd_unshare from being called elsewhere
+ * and making the ptep no longer valid.
+ * 2) It synchronizes us with file truncation.
+ *
+ * ptep could have already be assigned via huge_pte_offset. That
+ * is OK, as huge_pte_alloc will return the same value unless
+ * something changed.
+ */
mapping = vma->vm_file->f_mapping;
- idx = vma_hugecache_offset(h, vma, haddr);
+ i_mmap_lock_read(mapping);
+ ptep = huge_pte_alloc(mm, haddr, huge_page_size(h));
+ if (!ptep) {
+ i_mmap_unlock_read(mapping);
+ return VM_FAULT_OOM;
+ }
/*
* Serialize hugepage allocation and instantiation, so that we don't
* get spurious allocation failures if two CPUs race to instantiate
* the same page in the page cache.
*/
+ idx = vma_hugecache_offset(h, vma, haddr);
hash = hugetlb_fault_mutex_hash(h, mm, vma, mapping, idx, haddr);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
@@ -4036,6 +4066,7 @@ out_ptl:
}
out_mutex:
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+ i_mmap_unlock_read(mapping);
/*
* Generally it's safe to hold refcount during waiting page lock. But
* here we just wait to defer the next page fault to avoid busy loop and
@@ -4340,21 +4371,21 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
pte_t pte;
struct hstate *h = hstate_vma(vma);
unsigned long pages = 0;
- unsigned long f_start = start;
- unsigned long f_end = end;
bool shared_pmd = false;
+ struct mmu_notifier_range range;
/*
* In the case of shared PMDs, the area to flush could be beyond
- * start/end. Set f_start/f_end to cover the maximum possible
+ * start/end. Set range.start/range.end to cover the maximum possible
* range if PMD sharing is possible.
*/
- adjust_range_if_pmd_sharing_possible(vma, &f_start, &f_end);
+ mmu_notifier_range_init(&range, mm, start, end);
+ adjust_range_if_pmd_sharing_possible(vma, &range.start, &range.end);
BUG_ON(address >= end);
- flush_cache_range(vma, f_start, f_end);
+ flush_cache_range(vma, range.start, range.end);
- mmu_notifier_invalidate_range_start(mm, f_start, f_end);
+ mmu_notifier_invalidate_range_start(&range);
i_mmap_lock_write(vma->vm_file->f_mapping);
for (; address < end; address += huge_page_size(h)) {
spinlock_t *ptl;
@@ -4405,7 +4436,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
* did unshare a page of pmds, flush the range corresponding to the pud.
*/
if (shared_pmd)
- flush_hugetlb_tlb_range(vma, f_start, f_end);
+ flush_hugetlb_tlb_range(vma, range.start, range.end);
else
flush_hugetlb_tlb_range(vma, start, end);
/*
@@ -4415,7 +4446,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
* See Documentation/vm/mmu_notifier.rst
*/
i_mmap_unlock_write(vma->vm_file->f_mapping);
- mmu_notifier_invalidate_range_end(mm, f_start, f_end);
+ mmu_notifier_invalidate_range_end(&range);
return pages << h->order;
}
@@ -4640,10 +4671,12 @@ void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
* Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
* and returns the corresponding pte. While this is not necessary for the
* !shared pmd case because we can allocate the pmd later as well, it makes the
- * code much cleaner. pmd allocation is essential for the shared case because
- * pud has to be populated inside the same i_mmap_rwsem section - otherwise
- * racing tasks could either miss the sharing (see huge_pte_offset) or select a
- * bad pmd for sharing.
+ * code much cleaner.
+ *
+ * This routine must be called with i_mmap_rwsem held in at least read mode.
+ * For hugetlbfs, this prevents removal of any page table entries associated
+ * with the address space. This is important as we are setting up sharing
+ * based on existing page table entries (mappings).
*/
pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
{
@@ -4660,7 +4693,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
if (!vma_shareable(vma, addr))
return (pte_t *)pmd_alloc(mm, pud, addr);
- i_mmap_lock_write(mapping);
vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) {
if (svma == vma)
continue;
@@ -4690,7 +4722,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
spin_unlock(ptl);
out:
pte = (pte_t *)pmd_alloc(mm, pud, addr);
- i_mmap_unlock_write(mapping);
return pte;
}
@@ -4701,7 +4732,7 @@ out:
* indicated by page_count > 1, unmap is achieved by clearing pud and
* decrementing the ref count. If count == 1, the pte page is not shared.
*
- * called with page table lock held.
+ * Called with page table lock held and i_mmap_rwsem held in write mode.
*
* returns: 1 successfully unmapped a shared pte page
* 0 the underlying pte page is not shared, or it is the last user