summaryrefslogtreecommitdiff
path: root/mm/hugetlb.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2021-03-14 12:23:34 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-03-14 12:23:34 -0700
commit50eb842fe517b2765b7748c3016082b484a6dbb8 (patch)
tree043787bcebc48b58698469d5699f9e034b92a391 /mm/hugetlb.c
parent88fe49249c99de14e543c632a46248d85411ab9e (diff)
parent2766f1821600cc7562bae2128ad0b163f744c5d9 (diff)
Merge branch 'akpm' (patches from Andrew)
Merge misc fixes from Andrew Morton: "28 patches. Subsystems affected by this series: mm (memblock, pagealloc, hugetlb, highmem, kfence, oom-kill, madvise, kasan, userfaultfd, memcg, and zram), core-kernel, kconfig, fork, binfmt, MAINTAINERS, kbuild, and ia64" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (28 commits) zram: fix broken page writeback zram: fix return value on writeback_store mm/memcg: set memcg when splitting page mm/memcg: rename mem_cgroup_split_huge_fixup to split_page_memcg and add nr_pages argument ia64: fix ptrace(PTRACE_SYSCALL_INFO_EXIT) sign ia64: fix ia64_syscall_get_set_arguments() for break-based syscalls mm/userfaultfd: fix memory corruption due to writeprotect kasan: fix KASAN_STACK dependency for HW_TAGS kasan, mm: fix crash with HW_TAGS and DEBUG_PAGEALLOC mm/madvise: replace ptrace attach requirement for process_madvise include/linux/sched/mm.h: use rcu_dereference in in_vfork() kfence: fix reports if constant function prefixes exist kfence, slab: fix cache_alloc_debugcheck_after() for bulk allocations kfence: fix printk format for ptrdiff_t linux/compiler-clang.h: define HAVE_BUILTIN_BSWAP* MAINTAINERS: exclude uapi directories in API/ABI section binfmt_misc: fix possible deadlock in bm_register_write mm/highmem.c: fix zero_user_segments() with start > end hugetlb: do early cow when page pinned on src mm mm: use is_cow_mapping() across tree where proper ...
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r--mm/hugetlb.c123
1 files changed, 91 insertions, 32 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 8fb42c6dd74b..5b1ab1f427c5 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -331,6 +331,24 @@ static void coalesce_file_region(struct resv_map *resv, struct file_region *rg)
}
}
+static inline long
+hugetlb_resv_map_add(struct resv_map *map, struct file_region *rg, long from,
+ long to, struct hstate *h, struct hugetlb_cgroup *cg,
+ long *regions_needed)
+{
+ struct file_region *nrg;
+
+ if (!regions_needed) {
+ nrg = get_file_region_entry_from_cache(map, from, to);
+ record_hugetlb_cgroup_uncharge_info(cg, h, map, nrg);
+ list_add(&nrg->link, rg->link.prev);
+ coalesce_file_region(map, nrg);
+ } else
+ *regions_needed += 1;
+
+ return to - from;
+}
+
/*
* Must be called with resv->lock held.
*
@@ -346,7 +364,7 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
long add = 0;
struct list_head *head = &resv->regions;
long last_accounted_offset = f;
- struct file_region *rg = NULL, *trg = NULL, *nrg = NULL;
+ struct file_region *rg = NULL, *trg = NULL;
if (regions_needed)
*regions_needed = 0;
@@ -369,24 +387,17 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
/* When we find a region that starts beyond our range, we've
* finished.
*/
- if (rg->from > t)
+ if (rg->from >= t)
break;
/* Add an entry for last_accounted_offset -> rg->from, and
* update last_accounted_offset.
*/
- if (rg->from > last_accounted_offset) {
- add += rg->from - last_accounted_offset;
- if (!regions_needed) {
- nrg = get_file_region_entry_from_cache(
- resv, last_accounted_offset, rg->from);
- record_hugetlb_cgroup_uncharge_info(h_cg, h,
- resv, nrg);
- list_add(&nrg->link, rg->link.prev);
- coalesce_file_region(resv, nrg);
- } else
- *regions_needed += 1;
- }
+ if (rg->from > last_accounted_offset)
+ add += hugetlb_resv_map_add(resv, rg,
+ last_accounted_offset,
+ rg->from, h, h_cg,
+ regions_needed);
last_accounted_offset = rg->to;
}
@@ -394,17 +405,9 @@ static long add_reservation_in_range(struct resv_map *resv, long f, long t,
/* Handle the case where our range extends beyond
* last_accounted_offset.
*/
- if (last_accounted_offset < t) {
- add += t - last_accounted_offset;
- if (!regions_needed) {
- nrg = get_file_region_entry_from_cache(
- resv, last_accounted_offset, t);
- record_hugetlb_cgroup_uncharge_info(h_cg, h, resv, nrg);
- list_add(&nrg->link, rg->link.prev);
- coalesce_file_region(resv, nrg);
- } else
- *regions_needed += 1;
- }
+ if (last_accounted_offset < t)
+ add += hugetlb_resv_map_add(resv, rg, last_accounted_offset,
+ t, h, h_cg, regions_needed);
VM_BUG_ON(add < 0);
return add;
@@ -3725,21 +3728,32 @@ static bool is_hugetlb_entry_hwpoisoned(pte_t pte)
return false;
}
+static void
+hugetlb_install_page(struct vm_area_struct *vma, pte_t *ptep, unsigned long addr,
+ struct page *new_page)
+{
+ __SetPageUptodate(new_page);
+ set_huge_pte_at(vma->vm_mm, addr, ptep, make_huge_pte(vma, new_page, 1));
+ hugepage_add_new_anon_rmap(new_page, vma, addr);
+ hugetlb_count_add(pages_per_huge_page(hstate_vma(vma)), vma->vm_mm);
+ ClearHPageRestoreReserve(new_page);
+ SetHPageMigratable(new_page);
+}
+
int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
struct vm_area_struct *vma)
{
pte_t *src_pte, *dst_pte, entry, dst_entry;
struct page *ptepage;
unsigned long addr;
- int cow;
+ bool cow = is_cow_mapping(vma->vm_flags);
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
+ unsigned long npages = pages_per_huge_page(h);
struct address_space *mapping = vma->vm_file->f_mapping;
struct mmu_notifier_range range;
int ret = 0;
- cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
-
if (cow) {
mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, src,
vma->vm_start,
@@ -3784,6 +3798,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
entry = huge_ptep_get(src_pte);
dst_entry = huge_ptep_get(dst_pte);
+again:
if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) {
/*
* Skip if src entry none. Also, skip in the
@@ -3807,6 +3822,52 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
}
set_huge_swap_pte_at(dst, addr, dst_pte, entry, sz);
} else {
+ entry = huge_ptep_get(src_pte);
+ ptepage = pte_page(entry);
+ get_page(ptepage);
+
+ /*
+ * This is a rare case where we see pinned hugetlb
+ * pages while they're prone to COW. We need to do the
+ * COW earlier during fork.
+ *
+ * When pre-allocating the page or copying data, we
+ * need to be without the pgtable locks since we could
+ * sleep during the process.
+ */
+ if (unlikely(page_needs_cow_for_dma(vma, ptepage))) {
+ pte_t src_pte_old = entry;
+ struct page *new;
+
+ spin_unlock(src_ptl);
+ spin_unlock(dst_ptl);
+ /* Do not use reserve as it's private owned */
+ new = alloc_huge_page(vma, addr, 1);
+ if (IS_ERR(new)) {
+ put_page(ptepage);
+ ret = PTR_ERR(new);
+ break;
+ }
+ copy_user_huge_page(new, ptepage, addr, vma,
+ npages);
+ put_page(ptepage);
+
+ /* Install the new huge page if src pte stable */
+ dst_ptl = huge_pte_lock(h, dst, dst_pte);
+ src_ptl = huge_pte_lockptr(h, src, src_pte);
+ spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+ entry = huge_ptep_get(src_pte);
+ if (!pte_same(src_pte_old, entry)) {
+ put_page(new);
+ /* dst_entry won't change as in child */
+ goto again;
+ }
+ hugetlb_install_page(vma, dst_pte, addr, new);
+ spin_unlock(src_ptl);
+ spin_unlock(dst_ptl);
+ continue;
+ }
+
if (cow) {
/*
* No need to notify as we are downgrading page
@@ -3817,12 +3878,10 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
*/
huge_ptep_set_wrprotect(src, addr, src_pte);
}
- entry = huge_ptep_get(src_pte);
- ptepage = pte_page(entry);
- get_page(ptepage);
+
page_dup_rmap(ptepage, true);
set_huge_pte_at(dst, addr, dst_pte, entry);
- hugetlb_count_add(pages_per_huge_page(h), dst);
+ hugetlb_count_add(npages, dst);
}
spin_unlock(src_ptl);
spin_unlock(dst_ptl);