Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b45a953..95a3274 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -27,6 +27,7 @@
#include <linux/swapops.h>
#include <linux/jhash.h>
#include <linux/numa.h>
+#include <linux/llist.h>
#include <asm/page.h>
#include <asm/pgtable.h>
@@ -70,6 +71,21 @@
static int num_fault_mutexes;
struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
+static inline bool PageHugeFreed(struct page *head)
+{
+ return page_private(head + 4) == -1UL;
+}
+
+static inline void SetPageHugeFreed(struct page *head)
+{
+ set_page_private(head + 4, -1UL);
+}
+
+static inline void ClearPageHugeFreed(struct page *head)
+{
+ set_page_private(head + 4, 0);
+}
+
/* Forward declaration */
static int hugetlb_acct_memory(struct hstate *h, long delta);
@@ -575,13 +591,20 @@
{
struct hugepage_subpool *spool = subpool_inode(inode);
long rsv_adjust;
+ bool reserved = false;
rsv_adjust = hugepage_subpool_get_pages(spool, 1);
- if (rsv_adjust) {
+ if (rsv_adjust > 0) {
struct hstate *h = hstate_inode(inode);
- hugetlb_acct_memory(h, 1);
+ if (!hugetlb_acct_memory(h, 1))
+ reserved = true;
+ } else if (!rsv_adjust) {
+ reserved = true;
}
+
+ if (!reserved)
+ pr_warn("hugetlb: Huge Page Reserved count may go negative.\n");
}
/*
@@ -868,6 +891,7 @@
list_move(&page->lru, &h->hugepage_freelists[nid]);
h->free_huge_pages++;
h->free_huge_pages_node[nid]++;
+ SetPageHugeFreed(page);
}
static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
@@ -885,6 +909,7 @@
return NULL;
list_move(&page->lru, &h->hugepage_activelist);
set_page_refcounted(page);
+ ClearPageHugeFreed(page);
h->free_huge_pages--;
h->free_huge_pages_node[nid]--;
return page;
@@ -1174,14 +1199,16 @@
static void update_and_free_page(struct hstate *h, struct page *page)
{
int i;
+ struct page *subpage = page;
if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
return;
h->nr_huge_pages--;
h->nr_huge_pages_node[page_to_nid(page)]--;
- for (i = 0; i < pages_per_huge_page(h); i++) {
- page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
+ for (i = 0; i < pages_per_huge_page(h);
+ i++, subpage = mem_map_next(subpage, page, i)) {
+ subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
1 << PG_referenced | 1 << PG_dirty |
1 << PG_active | 1 << PG_private |
1 << PG_writeback);
@@ -1216,12 +1243,11 @@
*/
bool page_huge_active(struct page *page)
{
- VM_BUG_ON_PAGE(!PageHuge(page), page);
- return PageHead(page) && PagePrivate(&page[1]);
+ return PageHeadHuge(page) && PagePrivate(&page[1]);
}
/* never called for tail page */
-static void set_page_huge_active(struct page *page)
+void set_page_huge_active(struct page *page)
{
VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
SetPagePrivate(&page[1]);
@@ -1255,7 +1281,7 @@
page[2].mapping = NULL;
}
-void free_huge_page(struct page *page)
+static void __free_huge_page(struct page *page)
{
/*
* Can't pass hstate in here because it is called from the
@@ -1318,6 +1344,54 @@
spin_unlock(&hugetlb_lock);
}
+/*
+ * As free_huge_page() can be called from a non-task context, we have
+ * to defer the actual freeing in a workqueue to prevent potential
+ * hugetlb_lock deadlock.
+ *
+ * free_hpage_workfn() locklessly retrieves the linked list of pages to
+ * be freed and frees them one-by-one. As the page->mapping pointer is
+ * going to be cleared in __free_huge_page() anyway, it is reused as the
+ * llist_node structure of a lockless linked list of huge pages to be freed.
+ */
+static LLIST_HEAD(hpage_freelist);
+
+static void free_hpage_workfn(struct work_struct *work)
+{
+ struct llist_node *node;
+ struct page *page;
+
+ node = llist_del_all(&hpage_freelist);
+
+ while (node) {
+ page = container_of((struct address_space **)node,
+ struct page, mapping);
+ node = node->next;
+ __free_huge_page(page);
+ }
+}
+static DECLARE_WORK(free_hpage_work, free_hpage_workfn);
+
+void free_huge_page(struct page *page)
+{
+ /*
+ * Defer freeing if in non-task context to avoid hugetlb_lock deadlock.
+ */
+ if (!in_task()) {
+ /*
+ * Only call schedule_work() if hpage_freelist is previously
+ * empty. Otherwise, schedule_work() had been called but the
+ * workfn hasn't retrieved the list yet.
+ */
+ if (llist_add((struct llist_node *)&page->mapping,
+ &hpage_freelist))
+ schedule_work(&free_hpage_work);
+ return;
+ }
+
+ __free_huge_page(page);
+}
+
static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
INIT_LIST_HEAD(&page->lru);
@@ -1326,6 +1400,7 @@
set_hugetlb_cgroup(page, NULL);
h->nr_huge_pages++;
h->nr_huge_pages_node[nid]++;
+ ClearPageHugeFreed(page);
spin_unlock(&hugetlb_lock);
}
@@ -1386,15 +1461,12 @@
return get_compound_page_dtor(page_head) == free_huge_page;
}
-pgoff_t __basepage_index(struct page *page)
+pgoff_t hugetlb_basepage_index(struct page *page)
{
struct page *page_head = compound_head(page);
pgoff_t index = page_index(page_head);
unsigned long compound_idx;
- if (!PageHuge(page_head))
- return page_index(page);
-
if (compound_order(page_head) >= MAX_ORDER)
compound_idx = page_to_pfn(page) - page_to_pfn(page_head);
else
@@ -1553,6 +1625,7 @@
{
int rc = -EBUSY;
+retry:
/* Not to disrupt normal path by vainly holding hugetlb_lock */
if (!PageHuge(page))
return 0;
@@ -1569,6 +1642,26 @@
int nid = page_to_nid(head);
if (h->free_huge_pages - h->resv_huge_pages == 0)
goto out;
+
+ /*
+ * We should make sure that the page is already on the free list
+ * when it is dissolved.
+ */
+ if (unlikely(!PageHugeFreed(head))) {
+ spin_unlock(&hugetlb_lock);
+ cond_resched();
+
+ /*
+ * Theoretically, we should return -EBUSY when we
+ * encounter this race. In fact, we have a chance
+ * to successfully dissolve the page if we do a
+ * retry. Because the race window is quite small.
+ * If we seize this opportunity, it is an optimization
+ * for increasing the success rate of dissolving page.
+ */
+ goto retry;
+ }
+
/*
* Move PageHWPoison flag from head page to the raw error page,
* which makes any subpages rather than the error page reusable.
@@ -2725,8 +2818,10 @@
return -ENOMEM;
retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group);
- if (retval)
+ if (retval) {
kobject_put(hstate_kobjs[hi]);
+ hstate_kobjs[hi] = NULL;
+ }
return retval;
}
@@ -3033,6 +3128,22 @@
}
#ifdef CONFIG_SYSCTL
+static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write,
+ void *buffer, size_t *length,
+ loff_t *ppos, unsigned long *out)
+{
+ struct ctl_table dup_table;
+
+ /*
+ * In order to avoid races with __do_proc_doulongvec_minmax(), we
+ * can duplicate the @table and alter the duplicate of it.
+ */
+ dup_table = *table;
+ dup_table.data = out;
+
+ return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos);
+}
+
static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
@@ -3044,9 +3155,8 @@
if (!hugepages_supported())
return -EOPNOTSUPP;
- table->data = &tmp;
- table->maxlen = sizeof(unsigned long);
- ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+ ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+ &tmp);
if (ret)
goto out;
@@ -3090,9 +3200,8 @@
if (write && hstate_is_gigantic(h))
return -EINVAL;
- table->data = &tmp;
- table->maxlen = sizeof(unsigned long);
- ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+ ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+ &tmp);
if (ret)
goto out;
@@ -3915,7 +4024,7 @@
* handling userfault. Reacquire after handling
* fault to make calling code simpler.
*/
- hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr);
+ hash = hugetlb_fault_mutex_hash(h, mapping, idx);
mutex_unlock(&hugetlb_fault_mutex_table[hash]);
ret = handle_userfault(&vmf, VM_UFFD_MISSING);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
@@ -3973,7 +4082,7 @@
* So we need to block hugepage fault by PG_hwpoison bit check.
*/
if (unlikely(PageHWPoison(page))) {
- ret = VM_FAULT_HWPOISON |
+ ret = VM_FAULT_HWPOISON_LARGE |
VM_FAULT_SET_HINDEX(hstate_index(h));
goto backout_unlocked;
}
@@ -4043,7 +4152,7 @@
#ifdef CONFIG_SMP
u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
- pgoff_t idx, unsigned long address)
+ pgoff_t idx)
{
unsigned long key[2];
u32 hash;
@@ -4051,7 +4160,7 @@
key[0] = (unsigned long) mapping;
key[1] = idx;
- hash = jhash2((u32 *)&key, sizeof(key)/sizeof(u32), 0);
+ hash = jhash2((u32 *)&key, sizeof(key)/(sizeof(u32)), 0);
return hash & (num_fault_mutexes - 1);
}
@@ -4061,7 +4170,7 @@
* return 0 and avoid the hashing overhead.
*/
u32 hugetlb_fault_mutex_hash(struct hstate *h, struct address_space *mapping,
- pgoff_t idx, unsigned long address)
+ pgoff_t idx)
{
return 0;
}
@@ -4105,7 +4214,7 @@
* get spurious allocation failures if two CPUs race to instantiate
* the same page in the page cache.
*/
- hash = hugetlb_fault_mutex_hash(h, mapping, idx, haddr);
+ hash = hugetlb_fault_mutex_hash(h, mapping, idx);
mutex_lock(&hugetlb_fault_mutex_table[hash]);
entry = huge_ptep_get(ptep);
@@ -4226,10 +4335,20 @@
struct page *page;
if (!*pagep) {
- ret = -ENOMEM;
- page = alloc_huge_page(dst_vma, dst_addr, 0);
- if (IS_ERR(page))
+ /* If a page already exists, then it's UFFDIO_COPY for
+ * a non-missing case. Return -EEXIST.
+ */
+ if (vm_shared &&
+ hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) {
+ ret = -EEXIST;
goto out;
+ }
+
+ page = alloc_huge_page(dst_vma, dst_addr, 0);
+ if (IS_ERR(page)) {
+ ret = -ENOMEM;
+ goto out;
+ }
ret = copy_huge_page_from_user(page,
(const void __user *) src_addr,
@@ -4797,25 +4916,23 @@
void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
unsigned long *start, unsigned long *end)
{
- unsigned long check_addr = *start;
+ unsigned long v_start = ALIGN(vma->vm_start, PUD_SIZE),
+ v_end = ALIGN_DOWN(vma->vm_end, PUD_SIZE);
- if (!(vma->vm_flags & VM_MAYSHARE))
+ /*
+ * vma need span at least one aligned PUD size and the start,end range
+ * must at least partialy within it.
+ */
+ if (!(vma->vm_flags & VM_MAYSHARE) || !(v_end > v_start) ||
+ (*end <= v_start) || (*start >= v_end))
return;
- for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) {
- unsigned long a_start = check_addr & PUD_MASK;
- unsigned long a_end = a_start + PUD_SIZE;
+ /* Extend the range to be PUD aligned for a worst case scenario */
+ if (*start > v_start)
+ *start = ALIGN_DOWN(*start, PUD_SIZE);
- /*
- * If sharing is possible, adjust start/end if necessary.
- */
- if (range_in_vma(vma, a_start, a_end)) {
- if (a_start < *start)
- *start = a_start;
- if (a_end > *end)
- *end = a_end;
- }
- }
+ if (*end < v_end)
+ *end = ALIGN(*end, PUD_SIZE);
}
/*
@@ -4967,8 +5084,8 @@
{
pgd_t *pgd;
p4d_t *p4d;
- pud_t *pud;
- pmd_t *pmd;
+ pud_t *pud, pud_entry;
+ pmd_t *pmd, pmd_entry;
pgd = pgd_offset(mm, addr);
if (!pgd_present(*pgd))
@@ -4978,17 +5095,19 @@
return NULL;
pud = pud_offset(p4d, addr);
- if (sz != PUD_SIZE && pud_none(*pud))
+ pud_entry = READ_ONCE(*pud);
+ if (sz != PUD_SIZE && pud_none(pud_entry))
return NULL;
/* hugepage or swap? */
- if (pud_huge(*pud) || !pud_present(*pud))
+ if (pud_huge(pud_entry) || !pud_present(pud_entry))
return (pte_t *)pud;
pmd = pmd_offset(pud, addr);
- if (sz != PMD_SIZE && pmd_none(*pmd))
+ pmd_entry = READ_ONCE(*pmd);
+ if (sz != PMD_SIZE && pmd_none(pmd_entry))
return NULL;
/* hugepage or swap? */
- if (pmd_huge(*pmd) || !pmd_present(*pmd))
+ if (pmd_huge(pmd_entry) || !pmd_present(pmd_entry))
return (pte_t *)pmd;
return NULL;
@@ -5075,9 +5194,9 @@
{
bool ret = true;
- VM_BUG_ON_PAGE(!PageHead(page), page);
spin_lock(&hugetlb_lock);
- if (!page_huge_active(page) || !get_page_unless_zero(page)) {
+ if (!PageHeadHuge(page) || !page_huge_active(page) ||
+ !get_page_unless_zero(page)) {
ret = false;
goto unlock;
}