#include "internal.h"
const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
-static unsigned long nr_huge_pages, free_huge_pages, reserved_huge_pages;
+static unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages;
unsigned long max_huge_pages;
static struct list_head hugepage_freelists[MAX_NUMNODES];
static unsigned int nr_huge_pages_node[MAX_NUMNODES];
static unsigned int free_huge_pages_node[MAX_NUMNODES];
+static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
+unsigned long hugepages_treat_as_movable;
+
/*
* Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
*/
}
static void copy_huge_page(struct page *dst, struct page *src,
- unsigned long addr)
+ unsigned long addr, struct vm_area_struct *vma)
{
int i;
might_sleep();
for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++) {
cond_resched();
- copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE);
+ copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
}
}
static struct page *dequeue_huge_page(struct vm_area_struct *vma,
unsigned long address)
{
- int nid = numa_node_id();
+ int nid;
struct page *page = NULL;
- struct zonelist *zonelist = huge_zonelist(vma, address);
+ struct zonelist *zonelist = huge_zonelist(vma, address,
+ htlb_alloc_mask);
struct zone **z;
for (z = zonelist->zones; *z; z++) {
- nid = (*z)->zone_pgdat->node_id;
- if (cpuset_zone_allowed(*z, GFP_HIGHUSER) &&
+ nid = zone_to_nid(*z);
+ if (cpuset_zone_allowed_softwall(*z, htlb_alloc_mask) &&
!list_empty(&hugepage_freelists[nid]))
break;
}
return page;
}
+static void free_huge_page(struct page *page)
+{
+ BUG_ON(page_count(page));
+
+ INIT_LIST_HEAD(&page->lru);
+
+ spin_lock(&hugetlb_lock);
+ enqueue_huge_page(page);
+ spin_unlock(&hugetlb_lock);
+}
+
static int alloc_fresh_huge_page(void)
{
- static int nid = 0;
+ static int prev_nid;
struct page *page;
- page = alloc_pages_node(nid, GFP_HIGHUSER|__GFP_COMP|__GFP_NOWARN,
+ static DEFINE_SPINLOCK(nid_lock);
+ int nid;
+
+ spin_lock(&nid_lock);
+ nid = next_node(prev_nid, node_online_map);
+ if (nid == MAX_NUMNODES)
+ nid = first_node(node_online_map);
+ prev_nid = nid;
+ spin_unlock(&nid_lock);
+
+ page = alloc_pages_node(nid, htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN,
HUGETLB_PAGE_ORDER);
- nid = (nid + 1) % num_online_nodes();
if (page) {
- page[1].lru.next = (void *)free_huge_page; /* dtor */
+ set_compound_page_dtor(page, free_huge_page);
spin_lock(&hugetlb_lock);
nr_huge_pages++;
nr_huge_pages_node[page_to_nid(page)]++;
return 0;
}
-void free_huge_page(struct page *page)
+static struct page *alloc_huge_page(struct vm_area_struct *vma,
+ unsigned long addr)
{
- BUG_ON(page_count(page));
-
- INIT_LIST_HEAD(&page->lru);
-
- spin_lock(&hugetlb_lock);
- enqueue_huge_page(page);
- spin_unlock(&hugetlb_lock);
-}
-
-struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr)
-{
- struct inode *inode = vma->vm_file->f_dentry->d_inode;
struct page *page;
- int use_reserve = 0;
- unsigned long idx;
spin_lock(&hugetlb_lock);
-
- if (vma->vm_flags & VM_MAYSHARE) {
-
- /* idx = radix tree index, i.e. offset into file in
- * HPAGE_SIZE units */
- idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
- + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
-
- /* The hugetlbfs specific inode info stores the number
- * of "guaranteed available" (huge) pages. That is,
- * the first 'prereserved_hpages' pages of the inode
- * are either already instantiated, or have been
- * pre-reserved (by hugetlb_reserve_for_inode()). Here
- * we're in the process of instantiating the page, so
- * we use this to determine whether to draw from the
- * pre-reserved pool or the truly free pool. */
- if (idx < HUGETLBFS_I(inode)->prereserved_hpages)
- use_reserve = 1;
- }
-
- if (!use_reserve) {
- if (free_huge_pages <= reserved_huge_pages)
- goto fail;
- } else {
- BUG_ON(reserved_huge_pages == 0);
- reserved_huge_pages--;
- }
+ if (vma->vm_flags & VM_MAYSHARE)
+ resv_huge_pages--;
+ else if (free_huge_pages <= resv_huge_pages)
+ goto fail;
page = dequeue_huge_page(vma, addr);
if (!page)
set_page_refcounted(page);
return page;
- fail:
- WARN_ON(use_reserve); /* reserved allocations shouldn't fail */
+fail:
+ if (vma->vm_flags & VM_MAYSHARE)
+ resv_huge_pages++;
spin_unlock(&hugetlb_lock);
return NULL;
}
-/* hugetlb_extend_reservation()
- *
- * Ensure that at least 'atleast' hugepages are, and will remain,
- * available to instantiate the first 'atleast' pages of the given
- * inode. If the inode doesn't already have this many pages reserved
- * or instantiated, set aside some hugepages in the reserved pool to
- * satisfy later faults (or fail now if there aren't enough, rather
- * than getting the SIGBUS later).
- */
-int hugetlb_extend_reservation(struct hugetlbfs_inode_info *info,
- unsigned long atleast)
-{
- struct inode *inode = &info->vfs_inode;
- unsigned long change_in_reserve = 0;
- int ret = 0;
-
- spin_lock(&hugetlb_lock);
- read_lock_irq(&inode->i_mapping->tree_lock);
-
- if (info->prereserved_hpages >= atleast)
- goto out;
-
- /* Because we always call this on shared mappings, none of the
- * pages beyond info->prereserved_hpages can have been
- * instantiated, so we need to reserve all of them now. */
- change_in_reserve = atleast - info->prereserved_hpages;
-
- if ((reserved_huge_pages + change_in_reserve) > free_huge_pages) {
- ret = -ENOMEM;
- goto out;
- }
-
- reserved_huge_pages += change_in_reserve;
- info->prereserved_hpages = atleast;
-
- out:
- read_unlock_irq(&inode->i_mapping->tree_lock);
- spin_unlock(&hugetlb_lock);
-
- return ret;
-}
-
-/* hugetlb_truncate_reservation()
- *
- * This returns pages reserved for the given inode to the general free
- * hugepage pool. If the inode has any pages prereserved, but not
- * instantiated, beyond offset (atmost << HPAGE_SIZE), then release
- * them.
- */
-void hugetlb_truncate_reservation(struct hugetlbfs_inode_info *info,
- unsigned long atmost)
-{
- struct inode *inode = &info->vfs_inode;
- struct address_space *mapping = inode->i_mapping;
- unsigned long idx;
- unsigned long change_in_reserve = 0;
- struct page *page;
-
- spin_lock(&hugetlb_lock);
- read_lock_irq(&inode->i_mapping->tree_lock);
-
- if (info->prereserved_hpages <= atmost)
- goto out;
-
- /* Count pages which were reserved, but not instantiated, and
- * which we can now release. */
- for (idx = atmost; idx < info->prereserved_hpages; idx++) {
- page = radix_tree_lookup(&mapping->page_tree, idx);
- if (!page)
- /* Pages which are already instantiated can't
- * be unreserved (and in fact have already
- * been removed from the reserved pool) */
- change_in_reserve++;
- }
-
- BUG_ON(reserved_huge_pages < change_in_reserve);
- reserved_huge_pages -= change_in_reserve;
- info->prereserved_hpages = atmost;
-
- out:
- read_unlock_irq(&inode->i_mapping->tree_lock);
- spin_unlock(&hugetlb_lock);
-}
-
static int __init hugetlb_init(void)
{
unsigned long i;
}
__setup("hugepages=", hugetlb_setup);
+static unsigned int cpuset_mems_nr(unsigned int *array)
+{
+ int node;
+ unsigned int nr = 0;
+
+ for_each_node_mask(node, cpuset_current_mems_allowed)
+ nr += array[node];
+
+ return nr;
+}
+
#ifdef CONFIG_SYSCTL
static void update_and_free_page(struct page *page)
{
int i;
nr_huge_pages--;
- nr_huge_pages_node[page_zone(page)->zone_pgdat->node_id]--;
+ nr_huge_pages_node[page_to_nid(page)]--;
for (i = 0; i < (HPAGE_SIZE / PAGE_SIZE); i++) {
page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
#ifdef CONFIG_HIGHMEM
static void try_to_free_low(unsigned long count)
{
- int i, nid;
+ int i;
+
for (i = 0; i < MAX_NUMNODES; ++i) {
struct page *page, *next;
list_for_each_entry_safe(page, next, &hugepage_freelists[i], lru) {
continue;
list_del(&page->lru);
update_and_free_page(page);
- nid = page_zone(page)->zone_pgdat->node_id;
free_huge_pages--;
- free_huge_pages_node[nid]--;
+ free_huge_pages_node[page_to_nid(page)]--;
if (count >= nr_huge_pages)
return;
}
return nr_huge_pages;
spin_lock(&hugetlb_lock);
+ count = max(count, resv_huge_pages);
try_to_free_low(count);
while (count < nr_huge_pages) {
struct page *page = dequeue_huge_page(NULL, 0);
max_huge_pages = set_max_huge_pages(max_huge_pages);
return 0;
}
+
+int hugetlb_treat_movable_handler(struct ctl_table *table, int write,
+ struct file *file, void __user *buffer,
+ size_t *length, loff_t *ppos)
+{
+ proc_dointvec(table, write, file, buffer, length, ppos);
+ if (hugepages_treat_as_movable)
+ htlb_alloc_mask = GFP_HIGHUSER_MOVABLE;
+ else
+ htlb_alloc_mask = GFP_HIGHUSER;
+ return 0;
+}
+
#endif /* CONFIG_SYSCTL */
int hugetlb_report_meminfo(char *buf)
return sprintf(buf,
"HugePages_Total: %5lu\n"
"HugePages_Free: %5lu\n"
- "HugePages_Rsvd: %5lu\n"
+ "HugePages_Rsvd: %5lu\n"
"Hugepagesize: %5lu kB\n",
nr_huge_pages,
free_huge_pages,
- reserved_huge_pages,
+ resv_huge_pages,
HPAGE_SIZE/1024);
}
* hugegpage VMA. do_page_fault() is supposed to trap this, so BUG is we get
* this far.
*/
-static struct page *hugetlb_nopage(struct vm_area_struct *vma,
- unsigned long address, int *unused)
+static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
BUG();
- return NULL;
+ return 0;
}
struct vm_operations_struct hugetlb_vm_ops = {
- .nopage = hugetlb_nopage,
+ .fault = hugetlb_vm_op_fault,
};
static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
pte_t entry;
entry = pte_mkwrite(pte_mkdirty(*ptep));
- ptep_set_access_flags(vma, address, ptep, entry, 1);
- update_mmu_cache(vma, address, entry);
- lazy_mmu_prot_update(entry);
+ if (ptep_set_access_flags(vma, address, ptep, entry, 1)) {
+ update_mmu_cache(vma, address, entry);
+ lazy_mmu_prot_update(entry);
+ }
}
entry = *src_pte;
ptepage = pte_page(entry);
get_page(ptepage);
- add_mm_counter(dst, file_rss, HPAGE_SIZE / PAGE_SIZE);
set_huge_pte_at(dst, addr, dst_pte, entry);
}
spin_unlock(&src->page_table_lock);
return -ENOMEM;
}
-void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
- unsigned long end)
+void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
pte_t *ptep;
pte_t pte;
struct page *page;
+ struct page *tmp;
+ /*
+ * A page gathering list, protected by per file i_mmap_lock. The
+ * lock is used to avoid list corruption from multiple unmapping
+ * of the same page since we are using page->lru.
+ */
+ LIST_HEAD(page_list);
WARN_ON(!is_vm_hugetlb_page(vma));
BUG_ON(start & ~HPAGE_MASK);
BUG_ON(end & ~HPAGE_MASK);
spin_lock(&mm->page_table_lock);
-
- /* Update high watermark before we lower rss */
- update_hiwater_rss(mm);
-
for (address = start; address < end; address += HPAGE_SIZE) {
ptep = huge_pte_offset(mm, address);
if (!ptep)
continue;
+ if (huge_pmd_unshare(mm, &address, ptep))
+ continue;
+
pte = huge_ptep_get_and_clear(mm, address, ptep);
if (pte_none(pte))
continue;
page = pte_page(pte);
- put_page(page);
- add_mm_counter(mm, file_rss, (int) -(HPAGE_SIZE / PAGE_SIZE));
+ if (pte_dirty(pte))
+ set_page_dirty(page);
+ list_add(&page->lru, &page_list);
}
-
spin_unlock(&mm->page_table_lock);
flush_tlb_range(vma, start, end);
+ list_for_each_entry_safe(page, tmp, &page_list, lru) {
+ list_del(&page->lru);
+ put_page(page);
+ }
+}
+
+void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
+ unsigned long end)
+{
+ /*
+ * It is undesirable to test vma->vm_file as it should be non-null
+ * for valid hugetlb area. However, vm_file will be NULL in the error
+ * cleanup path of do_mmap_pgoff. When hugetlbfs ->mmap method fails,
+ * do_mmap_pgoff() nullifies vma->vm_file before calling this function
+ * to clean up. Since no pte has actually been setup, it is safe to
+ * do nothing in this case.
+ */
+ if (vma->vm_file) {
+ spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+ __unmap_hugepage_range(vma, start, end);
+ spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+ }
}
static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
}
spin_unlock(&mm->page_table_lock);
- copy_huge_page(new_page, old_page, address);
+ copy_huge_page(new_page, old_page, address, vma);
spin_lock(&mm->page_table_lock);
ptep = huge_pte_offset(mm, address & HPAGE_MASK);
return VM_FAULT_MINOR;
}
-int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
+static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *ptep, int write_access)
{
int ret = VM_FAULT_SIGBUS;
retry:
page = find_lock_page(mapping, idx);
if (!page) {
+ size = i_size_read(mapping->host) >> HPAGE_SHIFT;
+ if (idx >= size)
+ goto out;
if (hugetlb_get_quota(mapping))
goto out;
page = alloc_huge_page(vma, address);
if (!pte_none(*ptep))
goto backout;
- add_mm_counter(mm, file_rss, HPAGE_SIZE / PAGE_SIZE);
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);
struct page **pages, struct vm_area_struct **vmas,
unsigned long *position, int *length, int i)
{
- unsigned long vpfn, vaddr = *position;
+ unsigned long pfn_offset;
+ unsigned long vaddr = *position;
int remainder = *length;
- vpfn = vaddr/PAGE_SIZE;
spin_lock(&mm->page_table_lock);
while (vaddr < vma->vm_end && remainder) {
pte_t *pte;
break;
}
+ pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT;
+ page = pte_page(*pte);
+same_page:
if (pages) {
- page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
get_page(page);
- pages[i] = page;
+ pages[i] = page + pfn_offset;
}
if (vmas)
vmas[i] = vma;
vaddr += PAGE_SIZE;
- ++vpfn;
+ ++pfn_offset;
--remainder;
++i;
+ if (vaddr < vma->vm_end && remainder &&
+ pfn_offset < HPAGE_SIZE/PAGE_SIZE) {
+ /*
+ * We use pfn_offset to avoid touching the pageframes
+ * of this compound page.
+ */
+ goto same_page;
+ }
}
spin_unlock(&mm->page_table_lock);
*length = remainder;
BUG_ON(address >= end);
flush_cache_range(vma, address, end);
+ spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
spin_lock(&mm->page_table_lock);
for (; address < end; address += HPAGE_SIZE) {
ptep = huge_pte_offset(mm, address);
if (!ptep)
continue;
+ if (huge_pmd_unshare(mm, &address, ptep))
+ continue;
if (!pte_none(*ptep)) {
pte = huge_ptep_get_and_clear(mm, address, ptep);
pte = pte_mkhuge(pte_modify(pte, newprot));
}
}
spin_unlock(&mm->page_table_lock);
+ spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
flush_tlb_range(vma, start, end);
}
+struct file_region {
+ struct list_head link;
+ long from;
+ long to;
+};
+
+static long region_add(struct list_head *head, long f, long t)
+{
+ struct file_region *rg, *nrg, *trg;
+
+ /* Locate the region we are either in or before. */
+ list_for_each_entry(rg, head, link)
+ if (f <= rg->to)
+ break;
+
+ /* Round our left edge to the current segment if it encloses us. */
+ if (f > rg->from)
+ f = rg->from;
+
+ /* Check for and consume any regions we now overlap with. */
+ nrg = rg;
+ list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
+ if (&rg->link == head)
+ break;
+ if (rg->from > t)
+ break;
+
+ /* If this area reaches higher then extend our area to
+ * include it completely. If this is not the first area
+ * which we intend to reuse, free it. */
+ if (rg->to > t)
+ t = rg->to;
+ if (rg != nrg) {
+ list_del(&rg->link);
+ kfree(rg);
+ }
+ }
+ nrg->from = f;
+ nrg->to = t;
+ return 0;
+}
+
+static long region_chg(struct list_head *head, long f, long t)
+{
+ struct file_region *rg, *nrg;
+ long chg = 0;
+
+ /* Locate the region we are before or in. */
+ list_for_each_entry(rg, head, link)
+ if (f <= rg->to)
+ break;
+
+ /* If we are below the current region then a new region is required.
+ * Subtle, allocate a new region at the position but make it zero
+ * size such that we can guarentee to record the reservation. */
+ if (&rg->link == head || t < rg->from) {
+ nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
+ if (nrg == 0)
+ return -ENOMEM;
+ nrg->from = f;
+ nrg->to = f;
+ INIT_LIST_HEAD(&nrg->link);
+ list_add(&nrg->link, rg->link.prev);
+
+ return t - f;
+ }
+
+ /* Round our left edge to the current segment if it encloses us. */
+ if (f > rg->from)
+ f = rg->from;
+ chg = t - f;
+
+ /* Check for and consume any regions we now overlap with. */
+ list_for_each_entry(rg, rg->link.prev, link) {
+ if (&rg->link == head)
+ break;
+ if (rg->from > t)
+ return chg;
+
+ /* We overlap with this area, if it extends futher than
+ * us then we must extend ourselves. Account for its
+ * existing reservation. */
+ if (rg->to > t) {
+ chg += rg->to - t;
+ t = rg->to;
+ }
+ chg -= rg->to - rg->from;
+ }
+ return chg;
+}
+
+static long region_truncate(struct list_head *head, long end)
+{
+ struct file_region *rg, *trg;
+ long chg = 0;
+
+ /* Locate the region we are either in or before. */
+ list_for_each_entry(rg, head, link)
+ if (end <= rg->to)
+ break;
+ if (&rg->link == head)
+ return 0;
+
+ /* If we are in the middle of a region then adjust it. */
+ if (end > rg->from) {
+ chg = rg->to - end;
+ rg->to = end;
+ rg = list_entry(rg->link.next, typeof(*rg), link);
+ }
+
+ /* Drop any remaining regions. */
+ list_for_each_entry_safe(rg, trg, rg->link.prev, link) {
+ if (&rg->link == head)
+ break;
+ chg += rg->to - rg->from;
+ list_del(&rg->link);
+ kfree(rg);
+ }
+ return chg;
+}
+
+static int hugetlb_acct_memory(long delta)
+{
+ int ret = -ENOMEM;
+
+ spin_lock(&hugetlb_lock);
+ if ((delta + resv_huge_pages) <= free_huge_pages) {
+ resv_huge_pages += delta;
+ ret = 0;
+ }
+ spin_unlock(&hugetlb_lock);
+ return ret;
+}
+
+int hugetlb_reserve_pages(struct inode *inode, long from, long to)
+{
+ long ret, chg;
+
+ chg = region_chg(&inode->i_mapping->private_list, from, to);
+ if (chg < 0)
+ return chg;
+ /*
+ * When cpuset is configured, it breaks the strict hugetlb page
+ * reservation as the accounting is done on a global variable. Such
+ * reservation is completely rubbish in the presence of cpuset because
+ * the reservation is not checked against page availability for the
+ * current cpuset. Application can still potentially OOM'ed by kernel
+ * with lack of free htlb page in cpuset that the task is in.
+ * Attempt to enforce strict accounting with cpuset is almost
+ * impossible (or too ugly) because cpuset is too fluid that
+ * task or memory node can be dynamically moved between cpusets.
+ *
+ * The change of semantics for shared hugetlb mapping with cpuset is
+ * undesirable. However, in order to preserve some of the semantics,
+ * we fall back to check against current free page availability as
+ * a best attempt and hopefully to minimize the impact of changing
+ * semantics that cpuset has.
+ */
+ if (chg > cpuset_mems_nr(free_huge_pages_node))
+ return -ENOMEM;
+
+ ret = hugetlb_acct_memory(chg);
+ if (ret < 0)
+ return ret;
+ region_add(&inode->i_mapping->private_list, from, to);
+ return 0;
+}
+
+void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
+{
+ long chg = region_truncate(&inode->i_mapping->private_list, offset);
+ hugetlb_acct_memory(freed - chg);
+}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff