selftests: rtnetlink: correct xfrm policy rule in kci_test_ipsec_offload

[platform/kernel/linux-rpi.git] / mm / hugetlb.c

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 405793b..e7bd42f 100644 (file)
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2813,11 +2813,11 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
                page = alloc_buddy_huge_page_with_mpol(h, vma, addr);
                if (!page)
                        goto out_uncharge_cgroup;
+               spin_lock_irq(&hugetlb_lock);
                if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) {
                        SetHPageRestoreReserve(page);
                        h->resv_huge_pages--;
                }
-               spin_lock_irq(&hugetlb_lock);
                list_add(&page->lru, &h->hugepage_activelist);
                /* Fall through */
        }
@@ -4844,7 +4844,6 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma,
                                                  unsigned long haddr,
                                                  unsigned long reason)
 {
-       vm_fault_t ret;
        u32 hash;
        struct vm_fault vmf = {
                .vma = vma,
@@ -4861,18 +4860,14 @@ static inline vm_fault_t hugetlb_handle_userfault(struct vm_area_struct *vma,
        };
 
        /*
-        * hugetlb_fault_mutex and i_mmap_rwsem must be
-        * dropped before handling userfault.  Reacquire
-        * after handling fault to make calling code simpler.
+        * vma_lock and hugetlb_fault_mutex must be dropped before handling
+        * userfault. Also mmap_lock will be dropped during handling
+        * userfault, any vma operation should be careful from here.
         */
        hash = hugetlb_fault_mutex_hash(mapping, idx);
        mutex_unlock(&hugetlb_fault_mutex_table[hash]);
        i_mmap_unlock_read(mapping);
-       ret = handle_userfault(&vmf, reason);
-       i_mmap_lock_read(mapping);
-       mutex_lock(&hugetlb_fault_mutex_table[hash]);
-
-       return ret;
+       return handle_userfault(&vmf, reason);
 }
 
 static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
@@ -4889,6 +4884,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
        spinlock_t *ptl;
        unsigned long haddr = address & huge_page_mask(h);
        bool new_page, new_pagecache_page = false;
+       u32 hash = hugetlb_fault_mutex_hash(mapping, idx);
 
        /*
         * Currently, we are forced to kill the process in the event the
@@ -4898,7 +4894,7 @@ static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
        if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) {
                pr_warn_ratelimited("PID %d killed due to inadequate hugepage pool\n",
                           current->pid);
-               return ret;
+               goto out;
        }
 
        /*
@@ -4915,12 +4911,10 @@ retry:
        page = find_lock_page(mapping, idx);
        if (!page) {
                /* Check for page in userfault range */
-               if (userfaultfd_missing(vma)) {
-                       ret = hugetlb_handle_userfault(vma, mapping, idx,
+               if (userfaultfd_missing(vma))
+                       return hugetlb_handle_userfault(vma, mapping, idx,
                                                       flags, haddr,
                                                       VM_UFFD_MISSING);
-                       goto out;
-               }
 
                page = alloc_huge_page(vma, haddr, 0);
                if (IS_ERR(page)) {
@@ -4980,10 +4974,9 @@ retry:
                if (userfaultfd_minor(vma)) {
                        unlock_page(page);
                        put_page(page);
-                       ret = hugetlb_handle_userfault(vma, mapping, idx,
+                       return hugetlb_handle_userfault(vma, mapping, idx,
                                                       flags, haddr,
                                                       VM_UFFD_MINOR);
-                       goto out;
                }
        }
 
@@ -5034,6 +5027,8 @@ retry:
 
        unlock_page(page);
 out:
+       mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+       i_mmap_unlock_read(mapping);
        return ret;
 
 backout:
@@ -5131,10 +5126,12 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
        mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
        entry = huge_ptep_get(ptep);
-       if (huge_pte_none(entry)) {
-               ret = hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags);
-               goto out_mutex;
-       }
+       if (huge_pte_none(entry))
+               /*
+                * hugetlb_no_page will drop vma lock and hugetlb fault
+                * mutex internally, which make us return immediately.
+                */
+               return hugetlb_no_page(mm, vma, mapping, idx, address, ptep, flags);
 
        ret = 0;
 
@@ -5353,6 +5350,10 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
        ptl = huge_pte_lockptr(h, dst_mm, dst_pte);
        spin_lock(ptl);
 
+       ret = -EIO;
+       if (PageHWPoison(page))
+               goto out_release_unlock;
+
        /*
         * Recheck the i_size after holding PT lock to make sure not
         * to leave any page mapped (as page_mapped()) beyond the end
@@ -5371,7 +5372,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
        if (!huge_pte_none(huge_ptep_get(dst_pte)))
                goto out_release_unlock;
 
-       if (vm_shared) {
+       if (page_in_pagecache) {
                page_dup_rmap(page, true);
        } else {
                ClearHPageRestoreReserve(page);
@@ -6185,12 +6186,13 @@ follow_huge_pd(struct vm_area_struct *vma,
 }
 
 struct page * __weak
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-               pmd_t *pmd, int flags)
+follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, int flags)
 {
+       struct hstate *h = hstate_vma(vma);
+       struct mm_struct *mm = vma->vm_mm;
        struct page *page = NULL;
        spinlock_t *ptl;
-       pte_t pte;
+       pte_t *ptep, pte;
 
        /* FOLL_GET and FOLL_PIN are mutually exclusive. */
        if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) ==
@@ -6198,17 +6200,15 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
                return NULL;
 
 retry:
-       ptl = pmd_lockptr(mm, pmd);
-       spin_lock(ptl);
-       /*
-        * make sure that the address range covered by this pmd is not
-        * unmapped from other threads.
-        */
-       if (!pmd_huge(*pmd))
-               goto out;
-       pte = huge_ptep_get((pte_t *)pmd);
+       ptep = huge_pte_offset(mm, address, huge_page_size(h));
+       if (!ptep)
+               return NULL;
+
+       ptl = huge_pte_lock(h, mm, ptep);
+       pte = huge_ptep_get(ptep);
        if (pte_present(pte)) {
-               page = pmd_page(*pmd) + ((address & ~PMD_MASK) >> PAGE_SHIFT);
+               page = pte_page(pte) +
+                       ((address & ~huge_page_mask(h)) >> PAGE_SHIFT);
                /*
                 * try_grab_page() should always succeed here, because: a) we
                 * hold the pmd (ptl) lock, and b) we've just checked that the
@@ -6224,7 +6224,7 @@ retry:
        } else {
                if (is_hugetlb_entry_migration(pte)) {
                        spin_unlock(ptl);
-                       __migration_entry_wait(mm, (pte_t *)pmd, ptl);
+                       __migration_entry_wait(mm, ptep, ptl);
                        goto retry;
                }
                /*