#if defined(CONFIG_CMA) && defined(CONFIG_X86_64)
static void destroy_compound_gigantic_page(struct page *page,
- unsigned long order)
+ unsigned int order)
{
int i;
int nr_pages = 1 << order;
struct page *p = page + 1;
for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
- __ClearPageTail(p);
+ clear_compound_head(p);
set_page_refcounted(p);
- p->first_page = NULL;
}
set_compound_order(page, 0);
__ClearPageHead(page);
}
-static void free_gigantic_page(struct page *page, unsigned order)
+static void free_gigantic_page(struct page *page, unsigned int order)
{
free_contig_range(page_to_pfn(page), 1 << order);
}
return zone_spans_pfn(zone, last_pfn);
}
-static struct page *alloc_gigantic_page(int nid, unsigned order)
+static struct page *alloc_gigantic_page(int nid, unsigned int order)
{
unsigned long nr_pages = 1 << order;
unsigned long ret, pfn, flags;
}
static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
-static void prep_compound_gigantic_page(struct page *page, unsigned long order);
+static void prep_compound_gigantic_page(struct page *page, unsigned int order);
static struct page *alloc_fresh_gigantic_page_node(struct hstate *h, int nid)
{
static inline bool gigantic_page_supported(void) { return true; }
#else
static inline bool gigantic_page_supported(void) { return false; }
-static inline void free_gigantic_page(struct page *page, unsigned order) { }
+static inline void free_gigantic_page(struct page *page, unsigned int order) { }
static inline void destroy_compound_gigantic_page(struct page *page,
- unsigned long order) { }
+ unsigned int order) { }
static inline int alloc_fresh_gigantic_page(struct hstate *h,
nodemask_t *nodes_allowed) { return 0; }
#endif
1 << PG_writeback);
}
VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page);
- set_compound_page_dtor(page, NULL);
+ set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
set_page_refcounted(page);
if (hstate_is_gigantic(h)) {
destroy_compound_gigantic_page(page, huge_page_order(h));
static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
INIT_LIST_HEAD(&page->lru);
- set_compound_page_dtor(page, free_huge_page);
+ set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
spin_lock(&hugetlb_lock);
set_hugetlb_cgroup(page, NULL);
h->nr_huge_pages++;
put_page(page); /* free it into the hugepage allocator */
}
-static void prep_compound_gigantic_page(struct page *page, unsigned long order)
+static void prep_compound_gigantic_page(struct page *page, unsigned int order)
{
int i;
int nr_pages = 1 << order;
/* we rely on prep_new_huge_page to set the destructor */
set_compound_order(page, order);
- __SetPageHead(page);
__ClearPageReserved(page);
+ __SetPageHead(page);
for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
/*
* For gigantic hugepages allocated through bootmem at
*/
__ClearPageReserved(p);
set_page_count(p, 0);
- p->first_page = page;
- /* Make sure p->first_page is always valid for PageTail() */
- smp_wmb();
- __SetPageTail(p);
+ set_compound_head(p, page);
}
}
return 0;
page = compound_head(page);
- return get_compound_page_dtor(page) == free_huge_page;
+ return page[1].compound_dtor == HUGETLB_PAGE_DTOR;
}
EXPORT_SYMBOL_GPL(PageHuge);
dissolve_free_huge_page(pfn_to_page(pfn));
}
-static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
+/*
+ * There are 3 ways this can get called:
+ * 1. With vma+addr: we use the VMA's memory policy
+ * 2. With !vma, but nid=NUMA_NO_NODE: We try to allocate a huge
+ * page from any node, and let the buddy allocator itself figure
+ * it out.
+ * 3. With !vma, but nid!=NUMA_NO_NODE. We allocate a huge page
+ * strictly from 'nid'
+ */
+static struct page *__hugetlb_alloc_buddy_huge_page(struct hstate *h,
+ struct vm_area_struct *vma, unsigned long addr, int nid)
+{
+ int order = huge_page_order(h);
+ gfp_t gfp = htlb_alloc_mask(h)|__GFP_COMP|__GFP_REPEAT|__GFP_NOWARN;
+ unsigned int cpuset_mems_cookie;
+
+ /*
+ * We need a VMA to get a memory policy. If we do not
+ * have one, we use the 'nid' argument.
+ *
+ * The mempolicy stuff below has some non-inlined bits
+ * and calls ->vm_ops. That makes it hard to optimize at
+ * compile-time, even when NUMA is off and it does
+ * nothing. This helps the compiler optimize it out.
+ */
+ if (!IS_ENABLED(CONFIG_NUMA) || !vma) {
+ /*
+ * If a specific node is requested, make sure to
+ * get memory from there, but only when a node
+ * is explicitly specified.
+ */
+ if (nid != NUMA_NO_NODE)
+ gfp |= __GFP_THISNODE;
+ /*
+ * Make sure to call something that can handle
+ * nid=NUMA_NO_NODE
+ */
+ return alloc_pages_node(nid, gfp, order);
+ }
+
+ /*
+ * OK, so we have a VMA. Fetch the mempolicy and try to
+ * allocate a huge page with it. We will only reach this
+ * when CONFIG_NUMA=y.
+ */
+ do {
+ struct page *page;
+ struct mempolicy *mpol;
+ struct zonelist *zl;
+ nodemask_t *nodemask;
+
+ cpuset_mems_cookie = read_mems_allowed_begin();
+ zl = huge_zonelist(vma, addr, gfp, &mpol, &nodemask);
+ mpol_cond_put(mpol);
+ page = __alloc_pages_nodemask(gfp, order, zl, nodemask);
+ if (page)
+ return page;
+ } while (read_mems_allowed_retry(cpuset_mems_cookie));
+
+ return NULL;
+}
+
+/*
+ * There are two ways to allocate a huge page:
+ * 1. When you have a VMA and an address (like a fault)
+ * 2. When you have no VMA (like when setting /proc/.../nr_hugepages)
+ *
+ * 'vma' and 'addr' are only for (1). 'nid' is always NUMA_NO_NODE in
+ * this case which signifies that the allocation should be done with
+ * respect for the VMA's memory policy.
+ *
+ * For (2), we ignore 'vma' and 'addr' and use 'nid' exclusively. This
+ * implies that memory policies will not be taken in to account.
+ */
+static struct page *__alloc_buddy_huge_page(struct hstate *h,
+ struct vm_area_struct *vma, unsigned long addr, int nid)
{
struct page *page;
unsigned int r_nid;
if (hstate_is_gigantic(h))
return NULL;
+ if (vma || addr) {
+ VM_WARN_ON_ONCE(!addr || addr == -1);
+ VM_WARN_ON_ONCE(nid != NUMA_NO_NODE);
+ }
/*
* Assume we will successfully allocate the surplus page to
* prevent racing processes from causing the surplus to exceed
}
spin_unlock(&hugetlb_lock);
- if (nid == NUMA_NO_NODE)
- page = alloc_pages(htlb_alloc_mask(h)|__GFP_COMP|
- __GFP_REPEAT|__GFP_NOWARN,
- huge_page_order(h));
- else
- page = __alloc_pages_node(nid,
- htlb_alloc_mask(h)|__GFP_COMP|__GFP_THISNODE|
- __GFP_REPEAT|__GFP_NOWARN, huge_page_order(h));
+ page = __hugetlb_alloc_buddy_huge_page(h, vma, addr, nid);
spin_lock(&hugetlb_lock);
if (page) {
INIT_LIST_HEAD(&page->lru);
r_nid = page_to_nid(page);
- set_compound_page_dtor(page, free_huge_page);
+ set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
set_hugetlb_cgroup(page, NULL);
/*
* We incremented the global counters already
return page;
}
+/*
+ * Allocate a huge page from 'nid'. Note, 'nid' may be
+ * NUMA_NO_NODE, which means that it may be allocated
+ * anywhere.
+ */
+static
+struct page *__alloc_buddy_huge_page_no_mpol(struct hstate *h, int nid)
+{
+ unsigned long addr = -1;
+
+ return __alloc_buddy_huge_page(h, NULL, addr, nid);
+}
+
+/*
+ * Use the VMA's mpolicy to allocate a huge page from the buddy.
+ */
+static
+struct page *__alloc_buddy_huge_page_with_mpol(struct hstate *h,
+ struct vm_area_struct *vma, unsigned long addr)
+{
+ return __alloc_buddy_huge_page(h, vma, addr, NUMA_NO_NODE);
+}
+
/*
* This allocation function is useful in the context where vma is irrelevant.
* E.g. soft-offlining uses this function because it only cares physical
spin_unlock(&hugetlb_lock);
if (!page)
- page = alloc_buddy_huge_page(h, nid);
+ page = __alloc_buddy_huge_page_no_mpol(h, nid);
return page;
}
retry:
spin_unlock(&hugetlb_lock);
for (i = 0; i < needed; i++) {
- page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
+ page = __alloc_buddy_huge_page_no_mpol(h, NUMA_NO_NODE);
if (!page) {
alloc_ok = false;
break;
page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg);
if (!page) {
spin_unlock(&hugetlb_lock);
- page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
+ page = __alloc_buddy_huge_page_with_mpol(h, vma, addr);
if (!page)
goto out_uncharge_cgroup;
return 1;
}
-static void __init prep_compound_huge_page(struct page *page, int order)
+static void __init prep_compound_huge_page(struct page *page,
+ unsigned int order)
{
if (unlikely(order > (MAX_ORDER - 1)))
prep_compound_gigantic_page(page, order);
struct kobject *hugepages_kobj;
struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];
};
-struct node_hstate node_hstates[MAX_NUMNODES];
+static struct node_hstate node_hstates[MAX_NUMNODES];
/*
* A subset of global hstate attributes for node devices
module_init(hugetlb_init);
/* Should be called on processing a hugepagesz=... option */
-void __init hugetlb_add_hstate(unsigned order)
+void __init hugetlb_add_hstate(unsigned int order)
{
struct hstate *h;
unsigned long i;
1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
}
+void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm)
+{
+ seq_printf(m, "HugetlbPages:\t%8lu kB\n",
+ atomic_long_read(&mm->hugetlb_usage) << (PAGE_SHIFT - 10));
+}
+
/* Return the number pages of memory we physically have, in PAGE_SIZE units. */
unsigned long hugetlb_total_pages(void)
{
entry = huge_ptep_get(src_pte);
ptepage = pte_page(entry);
get_page(ptepage);
- page_dup_rmap(ptepage);
+ page_dup_rmap(ptepage, true);
set_huge_pte_at(dst, addr, dst_pte, entry);
+ hugetlb_count_add(pages_per_huge_page(h), dst);
}
spin_unlock(src_ptl);
spin_unlock(dst_ptl);
if (huge_pte_dirty(pte))
set_page_dirty(page);
- page_remove_rmap(page);
+ hugetlb_count_sub(pages_per_huge_page(h), mm);
+ page_remove_rmap(page, true);
force_flush = !__tlb_remove_page(tlb, page);
if (force_flush) {
address += sz;
mmu_notifier_invalidate_range(mm, mmun_start, mmun_end);
set_huge_pte_at(mm, address, ptep,
make_huge_pte(vma, new_page, 1));
- page_remove_rmap(old_page);
+ page_remove_rmap(old_page, true);
hugepage_add_new_anon_rmap(new_page, vma, address);
/* Make the old page be freed below */
new_page = old_page;
ClearPagePrivate(page);
hugepage_add_new_anon_rmap(page, vma, address);
} else
- page_dup_rmap(page);
+ page_dup_rmap(page, true);
new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE)
&& (vma->vm_flags & VM_SHARED)));
set_huge_pte_at(mm, address, ptep, new_pte);
+ hugetlb_count_add(pages_per_huge_page(h), mm);
if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
/* Optimization, do the COW without a second fault */
ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page, ptl);
struct page *pagecache_page = NULL;
struct hstate *h = hstate_vma(vma);
struct address_space *mapping;
+ struct inode *inode = file_inode(vma->vm_file);
int need_wait_lock = 0;
address &= huge_page_mask(h);
mapping = vma->vm_file->f_mapping;
idx = vma_hugecache_offset(h, vma, address);
+ /*
+ * page faults could race with fallocate hole punch. If a page
+ * is faulted between unmap and deallocation, it will still remain
+ * in the punched hole. During hole punch operations, a hugetlb_falloc
+ * structure will be pointed to by i_private. If this fault is for
+ * a page in a hole being punched, wait for the operation to finish
+ * before proceeding.
+ *
+ * Even with this strategy, it is still possible for a page fault to
+ * race with hole punch. In this case, remove_inode_hugepages() will
+ * unmap the page and then remove. Checking i_private as below should
+ * catch most of these races as we want to minimize unmapping a page
+ * multiple times.
+ */
+ if (unlikely(inode->i_private)) {
+ struct hugetlb_falloc *hugetlb_falloc;
+
+ spin_lock(&inode->i_lock);
+ hugetlb_falloc = inode->i_private;
+ if (hugetlb_falloc && hugetlb_falloc->waitq &&
+ idx >= hugetlb_falloc->start &&
+ idx <= hugetlb_falloc->end) {
+ wait_queue_head_t *hugetlb_falloc_waitq;
+ DEFINE_WAIT(hugetlb_fault_wait);
+
+ hugetlb_falloc_waitq = hugetlb_falloc->waitq;
+ prepare_to_wait(hugetlb_falloc_waitq,
+ &hugetlb_fault_wait,
+ TASK_UNINTERRUPTIBLE);
+ spin_unlock(&inode->i_lock);
+ schedule();
+
+ spin_lock(&inode->i_lock);
+ finish_wait(hugetlb_falloc_waitq, &hugetlb_fault_wait);
+ }
+ spin_unlock(&inode->i_lock);
+ }
+
/*
* Serialize hugepage allocation and instantiation, so that we don't
* get spurious allocation failures if two CPUs race to instantiate
same_page:
if (pages) {
pages[i] = mem_map_offset(page, pfn_offset);
- get_page_foll(pages[i]);
+ get_page(pages[i]);
}
if (vmas)
unsigned long s_end = sbase + PUD_SIZE;
/* Allow segments to share if only one is marked locked */
- unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED;
- unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED;
+ unsigned long vm_flags = vma->vm_flags & VM_LOCKED_CLEAR_MASK;
+ unsigned long svm_flags = svma->vm_flags & VM_LOCKED_CLEAR_MASK;
/*
* match the virtual addresses, permission and the alignment of the
projects / karo-tx-linux.git / blobdiff