Merge commit 'v2.6.27-rc3' into x86/prototypes

Conflicts:

	include/asm-x86/dma-mapping.h

Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 1289 insertions, 392 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ab171274ef21..67a71191136e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -9,43 +9,357 @@
 #include <linux/mm.h>
 #include <linux/sysctl.h>
 #include <linux/highmem.h>
+#include <linux/mmu_notifier.h>
 #include <linux/nodemask.h>
 #include <linux/pagemap.h>
 #include <linux/mempolicy.h>
 #include <linux/cpuset.h>
 #include <linux/mutex.h>
+#include <linux/bootmem.h>
+#include <linux/sysfs.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
+#include <asm/io.h>
 
 #include <linux/hugetlb.h>
 #include "internal.h"
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
-static unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages;
-static unsigned long surplus_huge_pages;
-static unsigned long nr_overcommit_huge_pages;
-unsigned long max_huge_pages;
-unsigned long sysctl_overcommit_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 unsigned int surplus_huge_pages_node[MAX_NUMNODES];
 static gfp_t htlb_alloc_mask = GFP_HIGHUSER;
 unsigned long hugepages_treat_as_movable;
-static int hugetlb_next_nid;
+
+static int max_hstate;
+unsigned int default_hstate_idx;
+struct hstate hstates[HUGE_MAX_HSTATE];
+
+__initdata LIST_HEAD(huge_boot_pages);
+
+/* for command line parsing */
+static struct hstate * __initdata parsed_hstate;
+static unsigned long __initdata default_hstate_max_huge_pages;
+static unsigned long __initdata default_hstate_size;
+
+#define for_each_hstate(h) \
+        for ((h) = hstates; (h) < &hstates[max_hstate]; (h)++)
 
 /*
  * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
  */
 static DEFINE_SPINLOCK(hugetlb_lock);
 
-static void clear_huge_page(struct page *page, unsigned long addr)
+/*
+ * Region tracking -- allows tracking of reservations and instantiated pages
+ *                    across the pages in a mapping.
+ *
+ * The region data structures are protected by a combination of the mmap_sem
+ * and the hugetlb_instantion_mutex.  To access or modify a region the caller
+ * must either hold the mmap_sem for write, or the mmap_sem for read and
+ * the hugetlb_instantiation mutex:
+ *
+ *      down_write(&mm->mmap_sem);
+ * or
+ *      down_read(&mm->mmap_sem);
+ *      mutex_lock(&hugetlb_instantiation_mutex);
+ */
+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 guarantee to record the reservation. */
+        if (&rg->link == head || t < rg->from) {
+                nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
+                if (!nrg)
+                        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 long region_count(struct list_head *head, long f, long t)
+{
+        struct file_region *rg;
+        long chg = 0;
+
+        /* Locate each segment we overlap with, and count that overlap. */
+        list_for_each_entry(rg, head, link) {
+                int seg_from;
+                int seg_to;
+
+                if (rg->to <= f)
+                        continue;
+                if (rg->from >= t)
+                        break;
+
+                seg_from = max(rg->from, f);
+                seg_to = min(rg->to, t);
+
+                chg += seg_to - seg_from;
+        }
+
+        return chg;
+}
+
+/*
+ * Convert the address within this vma to the page offset within
+ * the mapping, in pagecache page units; huge pages here.
+ */
+static pgoff_t vma_hugecache_offset(struct hstate *h,
+                        struct vm_area_struct *vma, unsigned long address)
+{
+        return ((address - vma->vm_start) >> huge_page_shift(h)) +
+                        (vma->vm_pgoff >> huge_page_order(h));
+}
+
+/*
+ * Flags for MAP_PRIVATE reservations.  These are stored in the bottom
+ * bits of the reservation map pointer, which are always clear due to
+ * alignment.
+ */
+#define HPAGE_RESV_OWNER    (1UL << 0)
+#define HPAGE_RESV_UNMAPPED (1UL << 1)
+#define HPAGE_RESV_MASK (HPAGE_RESV_OWNER | HPAGE_RESV_UNMAPPED)
+
+/*
+ * These helpers are used to track how many pages are reserved for
+ * faults in a MAP_PRIVATE mapping. Only the process that called mmap()
+ * is guaranteed to have their future faults succeed.
+ *
+ * With the exception of reset_vma_resv_huge_pages() which is called at fork(),
+ * the reserve counters are updated with the hugetlb_lock held. It is safe
+ * to reset the VMA at fork() time as it is not in use yet and there is no
+ * chance of the global counters getting corrupted as a result of the values.
+ *
+ * The private mapping reservation is represented in a subtly different
+ * manner to a shared mapping.  A shared mapping has a region map associated
+ * with the underlying file, this region map represents the backing file
+ * pages which have ever had a reservation assigned which this persists even
+ * after the page is instantiated.  A private mapping has a region map
+ * associated with the original mmap which is attached to all VMAs which
+ * reference it, this region map represents those offsets which have consumed
+ * reservation ie. where pages have been instantiated.
+ */
+static unsigned long get_vma_private_data(struct vm_area_struct *vma)
+{
+        return (unsigned long)vma->vm_private_data;
+}
+
+static void set_vma_private_data(struct vm_area_struct *vma,
+                                                        unsigned long value)
+{
+        vma->vm_private_data = (void *)value;
+}
+
+struct resv_map {
+        struct kref refs;
+        struct list_head regions;
+};
+
+struct resv_map *resv_map_alloc(void)
+{
+        struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
+        if (!resv_map)
+                return NULL;
+
+        kref_init(&resv_map->refs);
+        INIT_LIST_HEAD(&resv_map->regions);
+
+        return resv_map;
+}
+
+void resv_map_release(struct kref *ref)
+{
+        struct resv_map *resv_map = container_of(ref, struct resv_map, refs);
+
+        /* Clear out any active regions before we release the map. */
+        region_truncate(&resv_map->regions, 0);
+        kfree(resv_map);
+}
+
+static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
+{
+        VM_BUG_ON(!is_vm_hugetlb_page(vma));
+        if (!(vma->vm_flags & VM_SHARED))
+                return (struct resv_map *)(get_vma_private_data(vma) &
+                                                        ~HPAGE_RESV_MASK);
+        return 0;
+}
+
+static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
+{
+        VM_BUG_ON(!is_vm_hugetlb_page(vma));
+        VM_BUG_ON(vma->vm_flags & VM_SHARED);
+
+        set_vma_private_data(vma, (get_vma_private_data(vma) &
+                                HPAGE_RESV_MASK) | (unsigned long)map);
+}
+
+static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags)
+{
+        VM_BUG_ON(!is_vm_hugetlb_page(vma));
+        VM_BUG_ON(vma->vm_flags & VM_SHARED);
+
+        set_vma_private_data(vma, get_vma_private_data(vma) | flags);
+}
+
+static int is_vma_resv_set(struct vm_area_struct *vma, unsigned long flag)
+{
+        VM_BUG_ON(!is_vm_hugetlb_page(vma));
+
+        return (get_vma_private_data(vma) & flag) != 0;
+}
+
+/* Decrement the reserved pages in the hugepage pool by one */
+static void decrement_hugepage_resv_vma(struct hstate *h,
+                        struct vm_area_struct *vma)
+{
+        if (vma->vm_flags & VM_NORESERVE)
+                return;
+
+        if (vma->vm_flags & VM_SHARED) {
+                /* Shared mappings always use reserves */
+                h->resv_huge_pages--;
+        } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+                /*
+                 * Only the process that called mmap() has reserves for
+                 * private mappings.
+                 */
+                h->resv_huge_pages--;
+        }
+}
+
+/* Reset counters to 0 and clear all HPAGE_RESV_* flags */
+void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
+{
+        VM_BUG_ON(!is_vm_hugetlb_page(vma));
+        if (!(vma->vm_flags & VM_SHARED))
+                vma->vm_private_data = (void *)0;
+}
+
+/* Returns true if the VMA has associated reserve pages */
+static int vma_has_reserves(struct vm_area_struct *vma)
+{
+        if (vma->vm_flags & VM_SHARED)
+                return 1;
+        if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
+                return 1;
+        return 0;
+}
+
+static void clear_huge_page(struct page *page,
+                        unsigned long addr, unsigned long sz)
 {
         int i;
 
         might_sleep();
-        for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); i++) {
+        for (i = 0; i < sz/PAGE_SIZE; i++) {
                 cond_resched();
                 clear_user_highpage(page + i, addr + i * PAGE_SIZE);
         }
@@ -55,42 +369,44 @@ static void copy_huge_page(struct page *dst, struct page *src,
                            unsigned long addr, struct vm_area_struct *vma)
 {
         int i;
+        struct hstate *h = hstate_vma(vma);
 
         might_sleep();
-        for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++) {
+        for (i = 0; i < pages_per_huge_page(h); i++) {
                 cond_resched();
                 copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
         }
 }
 
-static void enqueue_huge_page(struct page *page)
+static void enqueue_huge_page(struct hstate *h, struct page *page)
 {
         int nid = page_to_nid(page);
-        list_add(&page->lru, &hugepage_freelists[nid]);
-        free_huge_pages++;
-        free_huge_pages_node[nid]++;
+        list_add(&page->lru, &h->hugepage_freelists[nid]);
+        h->free_huge_pages++;
+        h->free_huge_pages_node[nid]++;
 }
 
-static struct page *dequeue_huge_page(void)
+static struct page *dequeue_huge_page(struct hstate *h)
 {
         int nid;
         struct page *page = NULL;
 
         for (nid = 0; nid < MAX_NUMNODES; ++nid) {
-                if (!list_empty(&hugepage_freelists[nid])) {
-                        page = list_entry(hugepage_freelists[nid].next,
+                if (!list_empty(&h->hugepage_freelists[nid])) {
+                        page = list_entry(h->hugepage_freelists[nid].next,
                                           struct page, lru);
                         list_del(&page->lru);
-                        free_huge_pages--;
-                        free_huge_pages_node[nid]--;
+                        h->free_huge_pages--;
+                        h->free_huge_pages_node[nid]--;
                         break;
                 }
         }
         return page;
 }
 
-static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
-                                unsigned long address)
+static struct page *dequeue_huge_page_vma(struct hstate *h,
+                                struct vm_area_struct *vma,
+                                unsigned long address, int avoid_reserve)
 {
         int nid;
         struct page *page = NULL;
@@ -101,18 +417,33 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
         struct zone *zone;
         struct zoneref *z;
 
+        /*
+         * A child process with MAP_PRIVATE mappings created by their parent
+         * have no page reserves. This check ensures that reservations are
+         * not "stolen". The child may still get SIGKILLed
+         */
+        if (!vma_has_reserves(vma) &&
+                        h->free_huge_pages - h->resv_huge_pages == 0)
+                return NULL;
+
+        /* If reserves cannot be used, ensure enough pages are in the pool */
+        if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
+                return NULL;
+
         for_each_zone_zonelist_nodemask(zone, z, zonelist,
                                                 MAX_NR_ZONES - 1, nodemask) {
                 nid = zone_to_nid(zone);
                 if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) &&
-                    !list_empty(&hugepage_freelists[nid])) {
-                        page = list_entry(hugepage_freelists[nid].next,
+                    !list_empty(&h->hugepage_freelists[nid])) {
+                        page = list_entry(h->hugepage_freelists[nid].next,
                                           struct page, lru);
                         list_del(&page->lru);
-                        free_huge_pages--;
-                        free_huge_pages_node[nid]--;
-                        if (vma && vma->vm_flags & VM_MAYSHARE)
-                                resv_huge_pages--;
+                        h->free_huge_pages--;
+                        h->free_huge_pages_node[nid]--;
+
+                        if (!avoid_reserve)
+                                decrement_hugepage_resv_vma(h, vma);
+
                         break;
                 }
         }
@@ -120,12 +451,13 @@ static struct page *dequeue_huge_page_vma(struct vm_area_struct *vma,
         return page;
 }
 
-static void update_and_free_page(struct page *page)
+static void update_and_free_page(struct hstate *h, struct page *page)
 {
         int i;
-        nr_huge_pages--;
-        nr_huge_pages_node[page_to_nid(page)]--;
-        for (i = 0; i < (HPAGE_SIZE / PAGE_SIZE); i++) {
+
+        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 | 1 << PG_referenced |
                                 1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
                                 1 << PG_private | 1<< PG_writeback);
@@ -133,11 +465,27 @@ static void update_and_free_page(struct page *page)
         set_compound_page_dtor(page, NULL);
         set_page_refcounted(page);
         arch_release_hugepage(page);
-        __free_pages(page, HUGETLB_PAGE_ORDER);
+        __free_pages(page, huge_page_order(h));
+}
+
+struct hstate *size_to_hstate(unsigned long size)
+{
+        struct hstate *h;
+
+        for_each_hstate(h) {
+                if (huge_page_size(h) == size)
+                        return h;
+        }
+        return NULL;
 }
 
 static void free_huge_page(struct page *page)
 {
+        /*
+         * Can't pass hstate in here because it is called from the
+         * compound page destructor.
+         */
+        struct hstate *h = page_hstate(page);
         int nid = page_to_nid(page);
         struct address_space *mapping;
 
@@ -147,12 +495,12 @@ static void free_huge_page(struct page *page)
         INIT_LIST_HEAD(&page->lru);
 
         spin_lock(&hugetlb_lock);
-        if (surplus_huge_pages_node[nid]) {
-                update_and_free_page(page);
-                surplus_huge_pages--;
-                surplus_huge_pages_node[nid]--;
+        if (h->surplus_huge_pages_node[nid] && huge_page_order(h) < MAX_ORDER) {
+                update_and_free_page(h, page);
+                h->surplus_huge_pages--;
+                h->surplus_huge_pages_node[nid]--;
         } else {
-                enqueue_huge_page(page);
+                enqueue_huge_page(h, page);
         }
         spin_unlock(&hugetlb_lock);
         if (mapping)
@@ -164,7 +512,7 @@ static void free_huge_page(struct page *page)
  * balanced by operating on them in a round-robin fashion.
  * Returns 1 if an adjustment was made.
  */
-static int adjust_pool_surplus(int delta)
+static int adjust_pool_surplus(struct hstate *h, int delta)
 {
         static int prev_nid;
         int nid = prev_nid;
@@ -177,15 +525,15 @@ static int adjust_pool_surplus(int delta)
                         nid = first_node(node_online_map);
 
                 /* To shrink on this node, there must be a surplus page */
-                if (delta < 0 && !surplus_huge_pages_node[nid])
+                if (delta < 0 && !h->surplus_huge_pages_node[nid])
                         continue;
                 /* Surplus cannot exceed the total number of pages */
-                if (delta > 0 && surplus_huge_pages_node[nid] >=
-                                                nr_huge_pages_node[nid])
+                if (delta > 0 && h->surplus_huge_pages_node[nid] >=
+                                                h->nr_huge_pages_node[nid])
                         continue;
 
-                surplus_huge_pages += delta;
-                surplus_huge_pages_node[nid] += delta;
+                h->surplus_huge_pages += delta;
+                h->surplus_huge_pages_node[nid] += delta;
                 ret = 1;
                 break;
         } while (nid != prev_nid);
@@ -194,59 +542,74 @@ static int adjust_pool_surplus(int delta)
         return ret;
 }
 
-static struct page *alloc_fresh_huge_page_node(int nid)
+static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
+{
+        set_compound_page_dtor(page, free_huge_page);
+        spin_lock(&hugetlb_lock);
+        h->nr_huge_pages++;
+        h->nr_huge_pages_node[nid]++;
+        spin_unlock(&hugetlb_lock);
+        put_page(page); /* free it into the hugepage allocator */
+}
+
+static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 {
         struct page *page;
 
+        if (h->order >= MAX_ORDER)
+                return NULL;
+
         page = alloc_pages_node(nid,
                 htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
                                                 __GFP_REPEAT|__GFP_NOWARN,
-                HUGETLB_PAGE_ORDER);
+                huge_page_order(h));
         if (page) {
                 if (arch_prepare_hugepage(page)) {
-                        __free_pages(page, HUGETLB_PAGE_ORDER);
+                        __free_pages(page, huge_page_order(h));
                         return NULL;
                 }
-                set_compound_page_dtor(page, free_huge_page);
-                spin_lock(&hugetlb_lock);
-                nr_huge_pages++;
-                nr_huge_pages_node[nid]++;
-                spin_unlock(&hugetlb_lock);
-                put_page(page); /* free it into the hugepage allocator */
+                prep_new_huge_page(h, page, nid);
         }
 
         return page;
 }
 
-static int alloc_fresh_huge_page(void)
+/*
+ * Use a helper variable to find the next node and then
+ * copy it back to hugetlb_next_nid afterwards:
+ * otherwise there's a window in which a racer might
+ * pass invalid nid MAX_NUMNODES to alloc_pages_node.
+ * But we don't need to use a spin_lock here: it really
+ * doesn't matter if occasionally a racer chooses the
+ * same nid as we do.  Move nid forward in the mask even
+ * if we just successfully allocated a hugepage so that
+ * the next caller gets hugepages on the next node.
+ */
+static int hstate_next_node(struct hstate *h)
+{
+        int next_nid;
+        next_nid = next_node(h->hugetlb_next_nid, node_online_map);
+        if (next_nid == MAX_NUMNODES)
+                next_nid = first_node(node_online_map);
+        h->hugetlb_next_nid = next_nid;
+        return next_nid;
+}
+
+static int alloc_fresh_huge_page(struct hstate *h)
 {
         struct page *page;
         int start_nid;
         int next_nid;
         int ret = 0;
 
-        start_nid = hugetlb_next_nid;
+        start_nid = h->hugetlb_next_nid;
 
         do {
-                page = alloc_fresh_huge_page_node(hugetlb_next_nid);
+                page = alloc_fresh_huge_page_node(h, h->hugetlb_next_nid);
                 if (page)
                         ret = 1;
-                /*
-                 * Use a helper variable to find the next node and then
-                 * copy it back to hugetlb_next_nid afterwards:
-                 * otherwise there's a window in which a racer might
-                 * pass invalid nid MAX_NUMNODES to alloc_pages_node.
-                 * But we don't need to use a spin_lock here: it really
-                 * doesn't matter if occasionally a racer chooses the
-                 * same nid as we do.  Move nid forward in the mask even
-                 * if we just successfully allocated a hugepage so that
-                 * the next caller gets hugepages on the next node.
-                 */
-                next_nid = next_node(hugetlb_next_nid, node_online_map);
-                if (next_nid == MAX_NUMNODES)
-                        next_nid = first_node(node_online_map);
-                hugetlb_next_nid = next_nid;
-        } while (!page && hugetlb_next_nid != start_nid);
+                next_nid = hstate_next_node(h);
+        } while (!page && h->hugetlb_next_nid != start_nid);
 
         if (ret)
                 count_vm_event(HTLB_BUDDY_PGALLOC);
@@ -256,12 +619,15 @@ static int alloc_fresh_huge_page(void)
         return ret;
 }
 
-static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
-                                                unsigned long address)
+static struct page *alloc_buddy_huge_page(struct hstate *h,
+                        struct vm_area_struct *vma, unsigned long address)
 {
         struct page *page;
         unsigned int nid;
 
+        if (h->order >= MAX_ORDER)
+                return NULL;
+
         /*
          * Assume we will successfully allocate the surplus page to
          * prevent racing processes from causing the surplus to exceed
@@ -286,18 +652,23 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
          * per-node value is checked there.
          */
         spin_lock(&hugetlb_lock);
-        if (surplus_huge_pages >= nr_overcommit_huge_pages) {
+        if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
                 spin_unlock(&hugetlb_lock);
                 return NULL;
         } else {
-                nr_huge_pages++;
-                surplus_huge_pages++;
+                h->nr_huge_pages++;
+                h->surplus_huge_pages++;
         }
         spin_unlock(&hugetlb_lock);
 
         page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
                                         __GFP_REPEAT|__GFP_NOWARN,
-                                        HUGETLB_PAGE_ORDER);
+                                        huge_page_order(h));
+
+        if (page && arch_prepare_hugepage(page)) {
+                __free_pages(page, huge_page_order(h));
+                return NULL;
+        }
 
         spin_lock(&hugetlb_lock);
         if (page) {
@@ -312,12 +683,12 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
                 /*
                  * We incremented the global counters already
                  */
-                nr_huge_pages_node[nid]++;
-                surplus_huge_pages_node[nid]++;
+                h->nr_huge_pages_node[nid]++;
+                h->surplus_huge_pages_node[nid]++;
                 __count_vm_event(HTLB_BUDDY_PGALLOC);
         } else {
-                nr_huge_pages--;
-                surplus_huge_pages--;
+                h->nr_huge_pages--;
+                h->surplus_huge_pages--;
                 __count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
         }
         spin_unlock(&hugetlb_lock);
@@ -329,16 +700,16 @@ static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,
  * Increase the hugetlb pool such that it can accomodate a reservation
  * of size 'delta'.
  */
-static int gather_surplus_pages(int delta)
+static int gather_surplus_pages(struct hstate *h, int delta)
 {
         struct list_head surplus_list;
         struct page *page, *tmp;
         int ret, i;
         int needed, allocated;
 
-        needed = (resv_huge_pages + delta) - free_huge_pages;
+        needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
         if (needed <= 0) {
-                resv_huge_pages += delta;
+                h->resv_huge_pages += delta;
                 return 0;
         }
 
@@ -349,7 +720,7 @@ static int gather_surplus_pages(int delta)
 retry:
         spin_unlock(&hugetlb_lock);
         for (i = 0; i < needed; i++) {
-                page = alloc_buddy_huge_page(NULL, 0);
+                page = alloc_buddy_huge_page(h, NULL, 0);
                 if (!page) {
                         /*
                          * We were not able to allocate enough pages to
@@ -370,7 +741,8 @@ retry:
          * because either resv_huge_pages or free_huge_pages may have changed.
          */
         spin_lock(&hugetlb_lock);
-        needed = (resv_huge_pages + delta) - (free_huge_pages + allocated);
+        needed = (h->resv_huge_pages + delta) -
+                        (h->free_huge_pages + allocated);
         if (needed > 0)
                 goto retry;
 
@@ -383,7 +755,7 @@ retry:
          * before they are reserved.
          */
         needed += allocated;
-        resv_huge_pages += delta;
+        h->resv_huge_pages += delta;
         ret = 0;
 free:
         /* Free the needed pages to the hugetlb pool */
@@ -391,7 +763,7 @@ free:
                 if ((--needed) < 0)
                         break;
                 list_del(&page->lru);
-                enqueue_huge_page(page);
+                enqueue_huge_page(h, page);
         }
 
         /* Free unnecessary surplus pages to the buddy allocator */
@@ -419,7 +791,8 @@ free:
  * allocated to satisfy the reservation must be explicitly freed if they were
  * never used.
  */
-static void return_unused_surplus_pages(unsigned long unused_resv_pages)
+static void return_unused_surplus_pages(struct hstate *h,
+                                        unsigned long unused_resv_pages)
 {
         static int nid = -1;
         struct page *page;
@@ -434,157 +807,269 @@ static void return_unused_surplus_pages(unsigned long unused_resv_pages)
         unsigned long remaining_iterations = num_online_nodes();
 
         /* Uncommit the reservation */
-        resv_huge_pages -= unused_resv_pages;
+        h->resv_huge_pages -= unused_resv_pages;
 
-        nr_pages = min(unused_resv_pages, surplus_huge_pages);
+        /* Cannot return gigantic pages currently */
+        if (h->order >= MAX_ORDER)
+                return;
+
+        nr_pages = min(unused_resv_pages, h->surplus_huge_pages);
 
         while (remaining_iterations-- && nr_pages) {
                 nid = next_node(nid, node_online_map);
                 if (nid == MAX_NUMNODES)
                         nid = first_node(node_online_map);
 
-                if (!surplus_huge_pages_node[nid])
+                if (!h->surplus_huge_pages_node[nid])
                         continue;
 
-                if (!list_empty(&hugepage_freelists[nid])) {
-                        page = list_entry(hugepage_freelists[nid].next,
+                if (!list_empty(&h->hugepage_freelists[nid])) {
+                        page = list_entry(h->hugepage_freelists[nid].next,
                                           struct page, lru);
                         list_del(&page->lru);
-                        update_and_free_page(page);
-                        free_huge_pages--;
-                        free_huge_pages_node[nid]--;
-                        surplus_huge_pages--;
-                        surplus_huge_pages_node[nid]--;
+                        update_and_free_page(h, page);
+                        h->free_huge_pages--;
+                        h->free_huge_pages_node[nid]--;
+                        h->surplus_huge_pages--;
+                        h->surplus_huge_pages_node[nid]--;
                         nr_pages--;
                         remaining_iterations = num_online_nodes();
                 }
         }
 }
 
+/*
+ * Determine if the huge page at addr within the vma has an associated
+ * reservation.  Where it does not we will need to logically increase
+ * reservation and actually increase quota before an allocation can occur.
+ * Where any new reservation would be required the reservation change is
+ * prepared, but not committed.  Once the page has been quota'd allocated
+ * an instantiated the change should be committed via vma_commit_reservation.
+ * No action is required on failure.
+ */
+static int vma_needs_reservation(struct hstate *h,
+                        struct vm_area_struct *vma, unsigned long addr)
+{
+        struct address_space *mapping = vma->vm_file->f_mapping;
+        struct inode *inode = mapping->host;
+
+        if (vma->vm_flags & VM_SHARED) {
+                pgoff_t idx = vma_hugecache_offset(h, vma, addr);
+                return region_chg(&inode->i_mapping->private_list,
+                                                        idx, idx + 1);
+
+        } else if (!is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+                return 1;
+
+        } else  {
+                int err;
+                pgoff_t idx = vma_hugecache_offset(h, vma, addr);
+                struct resv_map *reservations = vma_resv_map(vma);
 
-static struct page *alloc_huge_page_shared(struct vm_area_struct *vma,
-                                                unsigned long addr)
+                err = region_chg(&reservations->regions, idx, idx + 1);
+                if (err < 0)
+                        return err;
+                return 0;
+        }
+}
+static void vma_commit_reservation(struct hstate *h,
+                        struct vm_area_struct *vma, unsigned long addr)
 {
-        struct page *page;
+        struct address_space *mapping = vma->vm_file->f_mapping;
+        struct inode *inode = mapping->host;
 
-        spin_lock(&hugetlb_lock);
-        page = dequeue_huge_page_vma(vma, addr);
-        spin_unlock(&hugetlb_lock);
-        return page ? page : ERR_PTR(-VM_FAULT_OOM);
+        if (vma->vm_flags & VM_SHARED) {
+                pgoff_t idx = vma_hugecache_offset(h, vma, addr);
+                region_add(&inode->i_mapping->private_list, idx, idx + 1);
+
+        } else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+                pgoff_t idx = vma_hugecache_offset(h, vma, addr);
+                struct resv_map *reservations = vma_resv_map(vma);
+
+                /* Mark this page used in the map. */
+                region_add(&reservations->regions, idx, idx + 1);
+        }
 }
 
-static struct page *alloc_huge_page_private(struct vm_area_struct *vma,
-                                                unsigned long addr)
+static struct page *alloc_huge_page(struct vm_area_struct *vma,
+                                    unsigned long addr, int avoid_reserve)
 {
-        struct page *page = NULL;
+        struct hstate *h = hstate_vma(vma);
+        struct page *page;
+        struct address_space *mapping = vma->vm_file->f_mapping;
+        struct inode *inode = mapping->host;
+        unsigned int chg;
 
-        if (hugetlb_get_quota(vma->vm_file->f_mapping, 1))
-                return ERR_PTR(-VM_FAULT_SIGBUS);
+        /*
+         * Processes that did not create the mapping will have no reserves and
+         * will not have accounted against quota. Check that the quota can be
+         * made before satisfying the allocation
+         * MAP_NORESERVE mappings may also need pages and quota allocated
+         * if no reserve mapping overlaps.
+         */
+        chg = vma_needs_reservation(h, vma, addr);
+        if (chg < 0)
+                return ERR_PTR(chg);
+        if (chg)
+                if (hugetlb_get_quota(inode->i_mapping, chg))
+                        return ERR_PTR(-ENOSPC);
 
         spin_lock(&hugetlb_lock);
-        if (free_huge_pages > resv_huge_pages)
-                page = dequeue_huge_page_vma(vma, addr);
+        page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
         spin_unlock(&hugetlb_lock);
+
         if (!page) {
-                page = alloc_buddy_huge_page(vma, addr);
+                page = alloc_buddy_huge_page(h, vma, addr);
                 if (!page) {
-                        hugetlb_put_quota(vma->vm_file->f_mapping, 1);
+                        hugetlb_put_quota(inode->i_mapping, chg);
                         return ERR_PTR(-VM_FAULT_OOM);
                 }
         }
+
+        set_page_refcounted(page);
+        set_page_private(page, (unsigned long) mapping);
+
+        vma_commit_reservation(h, vma, addr);
+
         return page;
 }
 
-static struct page *alloc_huge_page(struct vm_area_struct *vma,
-                                    unsigned long addr)
+__attribute__((weak)) int alloc_bootmem_huge_page(struct hstate *h)
 {
-        struct page *page;
-        struct address_space *mapping = vma->vm_file->f_mapping;
+        struct huge_bootmem_page *m;
+        int nr_nodes = nodes_weight(node_online_map);
 
-        if (vma->vm_flags & VM_MAYSHARE)
-                page = alloc_huge_page_shared(vma, addr);
-        else
-                page = alloc_huge_page_private(vma, addr);
+        while (nr_nodes) {
+                void *addr;
+
+                addr = __alloc_bootmem_node_nopanic(
+                                NODE_DATA(h->hugetlb_next_nid),
+                                huge_page_size(h), huge_page_size(h), 0);
 
-        if (!IS_ERR(page)) {
-                set_page_refcounted(page);
-                set_page_private(page, (unsigned long) mapping);
+                if (addr) {
+                        /*
+                         * Use the beginning of the huge page to store the
+                         * huge_bootmem_page struct (until gather_bootmem
+                         * puts them into the mem_map).
+                         */
+                        m = addr;
+                        if (m)
+                                goto found;
+                }
+                hstate_next_node(h);
+                nr_nodes--;
         }
-        return page;
+        return 0;
+
+found:
+        BUG_ON((unsigned long)virt_to_phys(m) & (huge_page_size(h) - 1));
+        /* Put them into a private list first because mem_map is not up yet */
+        list_add(&m->list, &huge_boot_pages);
+        m->hstate = h;
+        return 1;
 }
 
-static int __init hugetlb_init(void)
+/* Put bootmem huge pages into the standard lists after mem_map is up */
+static void __init gather_bootmem_prealloc(void)
 {
-        unsigned long i;
-
-        if (HPAGE_SHIFT == 0)
-                return 0;
-
-        for (i = 0; i < MAX_NUMNODES; ++i)
-                INIT_LIST_HEAD(&hugepage_freelists[i]);
+        struct huge_bootmem_page *m;
+
+        list_for_each_entry(m, &huge_boot_pages, list) {
+                struct page *page = virt_to_page(m);
+                struct hstate *h = m->hstate;
+                __ClearPageReserved(page);
+                WARN_ON(page_count(page) != 1);
+                prep_compound_page(page, h->order);
+                prep_new_huge_page(h, page, page_to_nid(page));
+        }
+}
 
-        hugetlb_next_nid = first_node(node_online_map);
+static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
+{
+        unsigned long i;
 
-        for (i = 0; i < max_huge_pages; ++i) {
-                if (!alloc_fresh_huge_page())
+        for (i = 0; i < h->max_huge_pages; ++i) {
+                if (h->order >= MAX_ORDER) {
+                        if (!alloc_bootmem_huge_page(h))
+                                break;
+                } else if (!alloc_fresh_huge_page(h))
                         break;
         }
-        max_huge_pages = free_huge_pages = nr_huge_pages = i;
-        printk("Total HugeTLB memory allocated, %ld\n", free_huge_pages);
-        return 0;
+        h->max_huge_pages = i;
 }
-module_init(hugetlb_init);
 
-static int __init hugetlb_setup(char *s)
+static void __init hugetlb_init_hstates(void)
 {
-        if (sscanf(s, "%lu", &max_huge_pages) <= 0)
-                max_huge_pages = 0;
-        return 1;
+        struct hstate *h;
+
+        for_each_hstate(h) {
+                /* oversize hugepages were init'ed in early boot */
+                if (h->order < MAX_ORDER)
+                        hugetlb_hstate_alloc_pages(h);
+        }
 }
-__setup("hugepages=", hugetlb_setup);
 
-static unsigned int cpuset_mems_nr(unsigned int *array)
+static char * __init memfmt(char *buf, unsigned long n)
 {
-        int node;
-        unsigned int nr = 0;
-
-        for_each_node_mask(node, cpuset_current_mems_allowed)
-                nr += array[node];
+        if (n >= (1UL << 30))
+                sprintf(buf, "%lu GB", n >> 30);
+        else if (n >= (1UL << 20))
+                sprintf(buf, "%lu MB", n >> 20);
+        else
+                sprintf(buf, "%lu KB", n >> 10);
+        return buf;
+}
 
-        return nr;
+static void __init report_hugepages(void)
+{
+        struct hstate *h;
+
+        for_each_hstate(h) {
+                char buf[32];
+                printk(KERN_INFO "HugeTLB registered %s page size, "
+                                 "pre-allocated %ld pages\n",
+                        memfmt(buf, huge_page_size(h)),
+                        h->free_huge_pages);
+        }
 }
 
-#ifdef CONFIG_SYSCTL
 #ifdef CONFIG_HIGHMEM
-static void try_to_free_low(unsigned long count)
+static void try_to_free_low(struct hstate *h, unsigned long count)
 {
         int i;
 
+        if (h->order >= MAX_ORDER)
+                return;
+
         for (i = 0; i < MAX_NUMNODES; ++i) {
                 struct page *page, *next;
-                list_for_each_entry_safe(page, next, &hugepage_freelists[i], lru) {
-                        if (count >= nr_huge_pages)
+                struct list_head *freel = &h->hugepage_freelists[i];
+                list_for_each_entry_safe(page, next, freel, lru) {
+                        if (count >= h->nr_huge_pages)
                                 return;
                         if (PageHighMem(page))
                                 continue;
                         list_del(&page->lru);
-                        update_and_free_page(page);
-                        free_huge_pages--;
-                        free_huge_pages_node[page_to_nid(page)]--;
+                        update_and_free_page(h, page);
+                        h->free_huge_pages--;
+                        h->free_huge_pages_node[page_to_nid(page)]--;
                 }
         }
 }
 #else
-static inline void try_to_free_low(unsigned long count)
+static inline void try_to_free_low(struct hstate *h, unsigned long count)
 {
 }
 #endif
 
-#define persistent_huge_pages (nr_huge_pages - surplus_huge_pages)
-static unsigned long set_max_huge_pages(unsigned long count)
+#define persistent_huge_pages(h) (h->nr_huge_pages - h->surplus_huge_pages)
+static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count)
 {
         unsigned long min_count, ret;
 
+        if (h->order >= MAX_ORDER)
+                return h->max_huge_pages;
+
         /*
          * Increase the pool size
          * First take pages out of surplus state.  Then make up the
@@ -597,20 +1082,19 @@ static unsigned long set_max_huge_pages(unsigned long count)
          * within all the constraints specified by the sysctls.
          */
         spin_lock(&hugetlb_lock);
-        while (surplus_huge_pages && count > persistent_huge_pages) {
-                if (!adjust_pool_surplus(-1))
+        while (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
+                if (!adjust_pool_surplus(h, -1))
                         break;
         }
 
-        while (count > persistent_huge_pages) {
-                int ret;
+        while (count > persistent_huge_pages(h)) {
                 /*
                  * If this allocation races such that we no longer need the
                  * page, free_huge_page will handle it by freeing the page
                  * and reducing the surplus.
                  */
                 spin_unlock(&hugetlb_lock);
-                ret = alloc_fresh_huge_page();
+                ret = alloc_fresh_huge_page(h);
                 spin_lock(&hugetlb_lock);
                 if (!ret)
                         goto out;
@@ -632,31 +1116,305 @@ static unsigned long set_max_huge_pages(unsigned long count)
          * and won't grow the pool anywhere else. Not until one of the
          * sysctls are changed, or the surplus pages go out of use.
          */
-        min_count = resv_huge_pages + nr_huge_pages - free_huge_pages;
+        min_count = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
         min_count = max(count, min_count);
-        try_to_free_low(min_count);
-        while (min_count < persistent_huge_pages) {
-                struct page *page = dequeue_huge_page();
+        try_to_free_low(h, min_count);
+        while (min_count < persistent_huge_pages(h)) {
+                struct page *page = dequeue_huge_page(h);
                 if (!page)
                         break;
-                update_and_free_page(page);
+                update_and_free_page(h, page);
         }
-        while (count < persistent_huge_pages) {
-                if (!adjust_pool_surplus(1))
+        while (count < persistent_huge_pages(h)) {
+                if (!adjust_pool_surplus(h, 1))
                         break;
         }
 out:
-        ret = persistent_huge_pages;
+        ret = persistent_huge_pages(h);
         spin_unlock(&hugetlb_lock);
         return ret;
 }
 
+#define HSTATE_ATTR_RO(_name) \
+        static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
+
+#define HSTATE_ATTR(_name) \
+        static struct kobj_attribute _name##_attr = \
+                __ATTR(_name, 0644, _name##_show, _name##_store)
+
+static struct kobject *hugepages_kobj;
+static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];
+
+static struct hstate *kobj_to_hstate(struct kobject *kobj)
+{
+        int i;
+        for (i = 0; i < HUGE_MAX_HSTATE; i++)
+                if (hstate_kobjs[i] == kobj)
+                        return &hstates[i];
+        BUG();
+        return NULL;
+}
+
+static ssize_t nr_hugepages_show(struct kobject *kobj,
+                                        struct kobj_attribute *attr, char *buf)
+{
+        struct hstate *h = kobj_to_hstate(kobj);
+        return sprintf(buf, "%lu\n", h->nr_huge_pages);
+}
+static ssize_t nr_hugepages_store(struct kobject *kobj,
+                struct kobj_attribute *attr, const char *buf, size_t count)
+{
+        int err;
+        unsigned long input;
+        struct hstate *h = kobj_to_hstate(kobj);
+
+        err = strict_strtoul(buf, 10, &input);
+        if (err)
+                return 0;
+
+        h->max_huge_pages = set_max_huge_pages(h, input);
+
+        return count;
+}
+HSTATE_ATTR(nr_hugepages);
+
+static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj,
+                                        struct kobj_attribute *attr, char *buf)
+{
+        struct hstate *h = kobj_to_hstate(kobj);
+        return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages);
+}
+static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
+                struct kobj_attribute *attr, const char *buf, size_t count)
+{
+        int err;
+        unsigned long input;
+        struct hstate *h = kobj_to_hstate(kobj);
+
+        err = strict_strtoul(buf, 10, &input);
+        if (err)
+                return 0;
+
+        spin_lock(&hugetlb_lock);
+        h->nr_overcommit_huge_pages = input;
+        spin_unlock(&hugetlb_lock);
+
+        return count;
+}
+HSTATE_ATTR(nr_overcommit_hugepages);
+
+static ssize_t free_hugepages_show(struct kobject *kobj,
+                                        struct kobj_attribute *attr, char *buf)
+{
+        struct hstate *h = kobj_to_hstate(kobj);
+        return sprintf(buf, "%lu\n", h->free_huge_pages);
+}
+HSTATE_ATTR_RO(free_hugepages);
+
+static ssize_t resv_hugepages_show(struct kobject *kobj,
+                                        struct kobj_attribute *attr, char *buf)
+{
+        struct hstate *h = kobj_to_hstate(kobj);
+        return sprintf(buf, "%lu\n", h->resv_huge_pages);
+}
+HSTATE_ATTR_RO(resv_hugepages);
+
+static ssize_t surplus_hugepages_show(struct kobject *kobj,
+                                        struct kobj_attribute *attr, char *buf)
+{
+        struct hstate *h = kobj_to_hstate(kobj);
+        return sprintf(buf, "%lu\n", h->surplus_huge_pages);
+}
+HSTATE_ATTR_RO(surplus_hugepages);
+
+static struct attribute *hstate_attrs[] = {
+        &nr_hugepages_attr.attr,
+        &nr_overcommit_hugepages_attr.attr,
+        &free_hugepages_attr.attr,
+        &resv_hugepages_attr.attr,
+        &surplus_hugepages_attr.attr,
+        NULL,
+};
+
+static struct attribute_group hstate_attr_group = {
+        .attrs = hstate_attrs,
+};
+
+static int __init hugetlb_sysfs_add_hstate(struct hstate *h)
+{
+        int retval;
+
+        hstate_kobjs[h - hstates] = kobject_create_and_add(h->name,
+                                                        hugepages_kobj);
+        if (!hstate_kobjs[h - hstates])
+                return -ENOMEM;
+
+        retval = sysfs_create_group(hstate_kobjs[h - hstates],
+                                                        &hstate_attr_group);
+        if (retval)
+                kobject_put(hstate_kobjs[h - hstates]);
+
+        return retval;
+}
+
+static void __init hugetlb_sysfs_init(void)
+{
+        struct hstate *h;
+        int err;
+
+        hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj);
+        if (!hugepages_kobj)
+                return;
+
+        for_each_hstate(h) {
+                err = hugetlb_sysfs_add_hstate(h);
+                if (err)
+                        printk(KERN_ERR "Hugetlb: Unable to add hstate %s",
+                                                                h->name);
+        }
+}
+
+static void __exit hugetlb_exit(void)
+{
+        struct hstate *h;
+
+        for_each_hstate(h) {
+                kobject_put(hstate_kobjs[h - hstates]);
+        }
+
+        kobject_put(hugepages_kobj);
+}
+module_exit(hugetlb_exit);
+
+static int __init hugetlb_init(void)
+{
+        /* Some platform decide whether they support huge pages at boot
+         * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
+         * there is no such support
+         */
+        if (HPAGE_SHIFT == 0)
+                return 0;
+
+        if (!size_to_hstate(default_hstate_size)) {
+                default_hstate_size = HPAGE_SIZE;
+                if (!size_to_hstate(default_hstate_size))
+                        hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
+        }
+        default_hstate_idx = size_to_hstate(default_hstate_size) - hstates;
+        if (default_hstate_max_huge_pages)
+                default_hstate.max_huge_pages = default_hstate_max_huge_pages;
+
+        hugetlb_init_hstates();
+
+        gather_bootmem_prealloc();
+
+        report_hugepages();
+
+        hugetlb_sysfs_init();
+
+        return 0;
+}
+module_init(hugetlb_init);
+
+/* Should be called on processing a hugepagesz=... option */
+void __init hugetlb_add_hstate(unsigned order)
+{
+        struct hstate *h;
+        unsigned long i;
+
+        if (size_to_hstate(PAGE_SIZE << order)) {
+                printk(KERN_WARNING "hugepagesz= specified twice, ignoring\n");
+                return;
+        }
+        BUG_ON(max_hstate >= HUGE_MAX_HSTATE);
+        BUG_ON(order == 0);
+        h = &hstates[max_hstate++];
+        h->order = order;
+        h->mask = ~((1ULL << (order + PAGE_SHIFT)) - 1);
+        h->nr_huge_pages = 0;
+        h->free_huge_pages = 0;
+        for (i = 0; i < MAX_NUMNODES; ++i)
+                INIT_LIST_HEAD(&h->hugepage_freelists[i]);
+        h->hugetlb_next_nid = first_node(node_online_map);
+        snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
+                                        huge_page_size(h)/1024);
+
+        parsed_hstate = h;
+}
+
+static int __init hugetlb_nrpages_setup(char *s)
+{
+        unsigned long *mhp;
+        static unsigned long *last_mhp;
+
+        /*
+         * !max_hstate means we haven't parsed a hugepagesz= parameter yet,
+         * so this hugepages= parameter goes to the "default hstate".
+         */
+        if (!max_hstate)
+                mhp = &default_hstate_max_huge_pages;
+        else
+                mhp = &parsed_hstate->max_huge_pages;
+
+        if (mhp == last_mhp) {
+                printk(KERN_WARNING "hugepages= specified twice without "
+                        "interleaving hugepagesz=, ignoring\n");
+                return 1;
+        }
+
+        if (sscanf(s, "%lu", mhp) <= 0)
+                *mhp = 0;
+
+        /*
+         * Global state is always initialized later in hugetlb_init.
+         * But we need to allocate >= MAX_ORDER hstates here early to still
+         * use the bootmem allocator.
+         */
+        if (max_hstate && parsed_hstate->order >= MAX_ORDER)
+                hugetlb_hstate_alloc_pages(parsed_hstate);
+
+        last_mhp = mhp;
+
+        return 1;
+}
+__setup("hugepages=", hugetlb_nrpages_setup);
+
+static int __init hugetlb_default_setup(char *s)
+{
+        default_hstate_size = memparse(s, &s);
+        return 1;
+}
+__setup("default_hugepagesz=", hugetlb_default_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
 int hugetlb_sysctl_handler(struct ctl_table *table, int write,
                            struct file *file, void __user *buffer,
                            size_t *length, loff_t *ppos)
 {
+        struct hstate *h = &default_hstate;
+        unsigned long tmp;
+
+        if (!write)
+                tmp = h->max_huge_pages;
+
+        table->data = &tmp;
+        table->maxlen = sizeof(unsigned long);
         proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
-        max_huge_pages = set_max_huge_pages(max_huge_pages);
+
+        if (write)
+                h->max_huge_pages = set_max_huge_pages(h, tmp);
+
         return 0;
 }
 
@@ -676,10 +1434,22 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
                         struct file *file, void __user *buffer,
                         size_t *length, loff_t *ppos)
 {
+        struct hstate *h = &default_hstate;
+        unsigned long tmp;
+
+        if (!write)
+                tmp = h->nr_overcommit_huge_pages;
+
+        table->data = &tmp;
+        table->maxlen = sizeof(unsigned long);
         proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
-        spin_lock(&hugetlb_lock);
-        nr_overcommit_huge_pages = sysctl_overcommit_huge_pages;
-        spin_unlock(&hugetlb_lock);
+
+        if (write) {
+                spin_lock(&hugetlb_lock);
+                h->nr_overcommit_huge_pages = tmp;
+                spin_unlock(&hugetlb_lock);
+        }
+
         return 0;
 }
 
@@ -687,34 +1457,118 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 
 int hugetlb_report_meminfo(char *buf)
 {
+        struct hstate *h = &default_hstate;
         return sprintf(buf,
                         "HugePages_Total: %5lu\n"
                         "HugePages_Free:  %5lu\n"
                         "HugePages_Rsvd:  %5lu\n"
                         "HugePages_Surp:  %5lu\n"
                         "Hugepagesize:    %5lu kB\n",
-                        nr_huge_pages,
-                        free_huge_pages,
-                        resv_huge_pages,
-                        surplus_huge_pages,
-                        HPAGE_SIZE/1024);
+                        h->nr_huge_pages,
+                        h->free_huge_pages,
+                        h->resv_huge_pages,
+                        h->surplus_huge_pages,
+                        1UL << (huge_page_order(h) + PAGE_SHIFT - 10));
 }
 
 int hugetlb_report_node_meminfo(int nid, char *buf)
 {
+        struct hstate *h = &default_hstate;
         return sprintf(buf,
                 "Node %d HugePages_Total: %5u\n"
                 "Node %d HugePages_Free:  %5u\n"
                 "Node %d HugePages_Surp:  %5u\n",
-                nid, nr_huge_pages_node[nid],
-                nid, free_huge_pages_node[nid],
-                nid, surplus_huge_pages_node[nid]);
+                nid, h->nr_huge_pages_node[nid],
+                nid, h->free_huge_pages_node[nid],
+                nid, h->surplus_huge_pages_node[nid]);
 }
 
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
-        return nr_huge_pages * (HPAGE_SIZE / PAGE_SIZE);
+        struct hstate *h = &default_hstate;
+        return h->nr_huge_pages * pages_per_huge_page(h);
+}
+
+static int hugetlb_acct_memory(struct hstate *h, long delta)
+{
+        int ret = -ENOMEM;
+
+        spin_lock(&hugetlb_lock);
+        /*
+         * 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 (delta > 0) {
+                if (gather_surplus_pages(h, delta) < 0)
+                        goto out;
+
+                if (delta > cpuset_mems_nr(h->free_huge_pages_node)) {
+                        return_unused_surplus_pages(h, delta);
+                        goto out;
+                }
+        }
+
+        ret = 0;
+        if (delta < 0)
+                return_unused_surplus_pages(h, (unsigned long) -delta);
+
+out:
+        spin_unlock(&hugetlb_lock);
+        return ret;
+}
+
+static void hugetlb_vm_op_open(struct vm_area_struct *vma)
+{
+        struct resv_map *reservations = vma_resv_map(vma);
+
+        /*
+         * This new VMA should share its siblings reservation map if present.
+         * The VMA will only ever have a valid reservation map pointer where
+         * it is being copied for another still existing VMA.  As that VMA
+         * has a reference to the reservation map it cannot dissappear until
+         * after this open call completes.  It is therefore safe to take a
+         * new reference here without additional locking.
+         */
+        if (reservations)
+                kref_get(&reservations->refs);
+}
+
+static void hugetlb_vm_op_close(struct vm_area_struct *vma)
+{
+        struct hstate *h = hstate_vma(vma);
+        struct resv_map *reservations = vma_resv_map(vma);
+        unsigned long reserve;
+        unsigned long start;
+        unsigned long end;
+
+        if (reservations) {
+                start = vma_hugecache_offset(h, vma, vma->vm_start);
+                end = vma_hugecache_offset(h, vma, vma->vm_end);
+
+                reserve = (end - start) -
+                        region_count(&reservations->regions, start, end);
+
+                kref_put(&reservations->refs, resv_map_release);
+
+                if (reserve) {
+                        hugetlb_acct_memory(h, -reserve);
+                        hugetlb_put_quota(vma->vm_file->f_mapping, reserve);
+                }
+        }
 }
 
 /*
@@ -731,6 +1585,8 @@ static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 struct vm_operations_struct hugetlb_vm_ops = {
         .fault = hugetlb_vm_op_fault,
+        .open = hugetlb_vm_op_open,
+        .close = hugetlb_vm_op_close,
 };
 
 static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,
@@ -769,14 +1625,16 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
         struct page *ptepage;
         unsigned long addr;
         int cow;
+        struct hstate *h = hstate_vma(vma);
+        unsigned long sz = huge_page_size(h);
 
         cow = (vma->vm_flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 
-        for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
+        for (addr = vma->vm_start; addr < vma->vm_end; addr += sz) {
                 src_pte = huge_pte_offset(src, addr);
                 if (!src_pte)
                         continue;
-                dst_pte = huge_pte_alloc(dst, addr);
+                dst_pte = huge_pte_alloc(dst, addr, sz);
                 if (!dst_pte)
                         goto nomem;
 
@@ -804,7 +1662,7 @@ nomem:
 }
 
 void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
-                            unsigned long end)
+                            unsigned long end, struct page *ref_page)
 {
         struct mm_struct *mm = vma->vm_mm;
         unsigned long address;
@@ -812,6 +1670,9 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
         pte_t pte;
         struct page *page;
         struct page *tmp;
+        struct hstate *h = hstate_vma(vma);
+        unsigned long sz = huge_page_size(h);
+
         /*
          * A page gathering list, protected by per file i_mmap_lock. The
          * lock is used to avoid list corruption from multiple unmapping
@@ -820,11 +1681,12 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
         LIST_HEAD(page_list);
 
         WARN_ON(!is_vm_hugetlb_page(vma));
-        BUG_ON(start & ~HPAGE_MASK);
-        BUG_ON(end & ~HPAGE_MASK);
+        BUG_ON(start & ~huge_page_mask(h));
+        BUG_ON(end & ~huge_page_mask(h));
 
+        mmu_notifier_invalidate_range_start(mm, start, end);
         spin_lock(&mm->page_table_lock);
-        for (address = start; address < end; address += HPAGE_SIZE) {
+        for (address = start; address < end; address += sz) {
                 ptep = huge_pte_offset(mm, address);
                 if (!ptep)
                         continue;
@@ -832,6 +1694,27 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
                 if (huge_pmd_unshare(mm, &address, ptep))
                         continue;
 
+                /*
+                 * If a reference page is supplied, it is because a specific
+                 * page is being unmapped, not a range. Ensure the page we
+                 * are about to unmap is the actual page of interest.
+                 */
+                if (ref_page) {
+                        pte = huge_ptep_get(ptep);
+                        if (huge_pte_none(pte))
+                                continue;
+                        page = pte_page(pte);
+                        if (page != ref_page)
+                                continue;
+
+                        /*
+                         * Mark the VMA as having unmapped its page so that
+                         * future faults in this VMA will fail rather than
+                         * looking like data was lost
+                         */
+                        set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED);
+                }
+
                 pte = huge_ptep_get_and_clear(mm, address, ptep);
                 if (huge_pte_none(pte))
                         continue;
@@ -843,6 +1726,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
         }
         spin_unlock(&mm->page_table_lock);
         flush_tlb_range(vma, start, end);
+        mmu_notifier_invalidate_range_end(mm, start, end);
         list_for_each_entry_safe(page, tmp, &page_list, lru) {
                 list_del(&page->lru);
                 put_page(page);
@@ -850,31 +1734,71 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 }
 
 void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
-                          unsigned long end)
+                          unsigned long end, struct page *ref_page)
 {
+        spin_lock(&vma->vm_file->f_mapping->i_mmap_lock);
+        __unmap_hugepage_range(vma, start, end, ref_page);
+        spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock);
+}
+
+/*
+ * This is called when the original mapper is failing to COW a MAP_PRIVATE
+ * mappping it owns the reserve page for. The intention is to unmap the page
+ * from other VMAs and let the children be SIGKILLed if they are faulting the
+ * same region.
+ */
+int unmap_ref_private(struct mm_struct *mm,
+                                        struct vm_area_struct *vma,
+                                        struct page *page,
+                                        unsigned long address)
+{
+        struct vm_area_struct *iter_vma;
+        struct address_space *mapping;
+        struct prio_tree_iter iter;
+        pgoff_t pgoff;
+
         /*
-         * 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.
+         * vm_pgoff is in PAGE_SIZE units, hence the different calculation
+         * from page cache lookup which is in HPAGE_SIZE units.
          */
-        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);
+        address = address & huge_page_mask(hstate_vma(vma));
+        pgoff = ((address - vma->vm_start) >> PAGE_SHIFT)
+                + (vma->vm_pgoff >> PAGE_SHIFT);
+        mapping = (struct address_space *)page_private(page);
+
+        vma_prio_tree_foreach(iter_vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
+                /* Do not unmap the current VMA */
+                if (iter_vma == vma)
+                        continue;
+
+                /*
+                 * Unmap the page from other VMAs without their own reserves.
+                 * They get marked to be SIGKILLed if they fault in these
+                 * areas. This is because a future no-page fault on this VMA
+                 * could insert a zeroed page instead of the data existing
+                 * from the time of fork. This would look like data corruption
+                 */
+                if (!is_vma_resv_set(iter_vma, HPAGE_RESV_OWNER))
+                        unmap_hugepage_range(iter_vma,
+                                address, address + HPAGE_SIZE,
+                                page);
         }
+
+        return 1;
 }
 
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
-                        unsigned long address, pte_t *ptep, pte_t pte)
+                        unsigned long address, pte_t *ptep, pte_t pte,
+                        struct page *pagecache_page)
 {
+        struct hstate *h = hstate_vma(vma);
         struct page *old_page, *new_page;
         int avoidcopy;
+        int outside_reserve = 0;
 
         old_page = pte_page(pte);
 
+retry_avoidcopy:
         /* If no-one else is actually using this page, avoid the copy
          * and just make the page writable */
         avoidcopy = (page_count(old_page) == 1);
@@ -883,11 +1807,43 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
                 return 0;
         }
 
+        /*
+         * If the process that created a MAP_PRIVATE mapping is about to
+         * perform a COW due to a shared page count, attempt to satisfy
+         * the allocation without using the existing reserves. The pagecache
+         * page is used to determine if the reserve at this address was
+         * consumed or not. If reserves were used, a partial faulted mapping
+         * at the time of fork() could consume its reserves on COW instead
+         * of the full address range.
+         */
+        if (!(vma->vm_flags & VM_SHARED) &&
+                        is_vma_resv_set(vma, HPAGE_RESV_OWNER) &&
+                        old_page != pagecache_page)
+                outside_reserve = 1;
+
         page_cache_get(old_page);
-        new_page = alloc_huge_page(vma, address);
+        new_page = alloc_huge_page(vma, address, outside_reserve);
 
         if (IS_ERR(new_page)) {
                 page_cache_release(old_page);
+
+                /*
+                 * If a process owning a MAP_PRIVATE mapping fails to COW,
+                 * it is due to references held by a child and an insufficient
+                 * huge page pool. To guarantee the original mappers
+                 * reliability, unmap the page from child processes. The child
+                 * may get SIGKILLed if it later faults.
+                 */
+                if (outside_reserve) {
+                        BUG_ON(huge_pte_none(pte));
+                        if (unmap_ref_private(mm, vma, old_page, address)) {
+                                BUG_ON(page_count(old_page) != 1);
+                                BUG_ON(huge_pte_none(pte));
+                                goto retry_avoidcopy;
+                        }
+                        WARN_ON_ONCE(1);
+                }
+
                 return -PTR_ERR(new_page);
         }
 
@@ -896,7 +1852,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
         __SetPageUptodate(new_page);
         spin_lock(&mm->page_table_lock);
 
-        ptep = huge_pte_offset(mm, address & HPAGE_MASK);
+        ptep = huge_pte_offset(mm, address & huge_page_mask(h));
         if (likely(pte_same(huge_ptep_get(ptep), pte))) {
                 /* Break COW */
                 huge_ptep_clear_flush(vma, address, ptep);
@@ -910,19 +1866,44 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
         return 0;
 }
 
+/* Return the pagecache page at a given address within a VMA */
+static struct page *hugetlbfs_pagecache_page(struct hstate *h,
+                        struct vm_area_struct *vma, unsigned long address)
+{
+        struct address_space *mapping;
+        pgoff_t idx;
+
+        mapping = vma->vm_file->f_mapping;
+        idx = vma_hugecache_offset(h, vma, address);
+
+        return find_lock_page(mapping, idx);
+}
+
 static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
                         unsigned long address, pte_t *ptep, int write_access)
 {
+        struct hstate *h = hstate_vma(vma);
         int ret = VM_FAULT_SIGBUS;
-        unsigned long idx;
+        pgoff_t idx;
         unsigned long size;
         struct page *page;
         struct address_space *mapping;
         pte_t new_pte;
 
+        /*
+         * Currently, we are forced to kill the process in the event the
+         * original mapper has unmapped pages from the child due to a failed
+         * COW. Warn that such a situation has occured as it may not be obvious
+         */
+        if (is_vma_resv_set(vma, HPAGE_RESV_UNMAPPED)) {
+                printk(KERN_WARNING
+                        "PID %d killed due to inadequate hugepage pool\n",
+                        current->pid);
+                return ret;
+        }
+
         mapping = vma->vm_file->f_mapping;
-        idx = ((address - vma->vm_start) >> HPAGE_SHIFT)
-                + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
+        idx = vma_hugecache_offset(h, vma, address);
 
         /*
          * Use page lock to guard against racing truncation
@@ -931,15 +1912,15 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 retry:
         page = find_lock_page(mapping, idx);
         if (!page) {
-                size = i_size_read(mapping->host) >> HPAGE_SHIFT;
+                size = i_size_read(mapping->host) >> huge_page_shift(h);
                 if (idx >= size)
                         goto out;
-                page = alloc_huge_page(vma, address);
+                page = alloc_huge_page(vma, address, 0);
                 if (IS_ERR(page)) {
                         ret = -PTR_ERR(page);
                         goto out;
                 }
-                clear_huge_page(page, address);
+                clear_huge_page(page, address, huge_page_size(h));
                 __SetPageUptodate(page);
 
                 if (vma->vm_flags & VM_SHARED) {
@@ -955,14 +1936,26 @@ retry:
                         }
 
                         spin_lock(&inode->i_lock);
-                        inode->i_blocks += BLOCKS_PER_HUGEPAGE;
+                        inode->i_blocks += blocks_per_huge_page(h);
                         spin_unlock(&inode->i_lock);
                 } else
                         lock_page(page);
         }
 
+        /*
+         * If we are going to COW a private mapping later, we examine the
+         * pending reservations for this page now. This will ensure that
+         * any allocations necessary to record that reservation occur outside
+         * the spinlock.
+         */
+        if (write_access && !(vma->vm_flags & VM_SHARED))
+                if (vma_needs_reservation(h, vma, address) < 0) {
+                        ret = VM_FAULT_OOM;
+                        goto backout_unlocked;
+                }
+
         spin_lock(&mm->page_table_lock);
-        size = i_size_read(mapping->host) >> HPAGE_SHIFT;
+        size = i_size_read(mapping->host) >> huge_page_shift(h);
         if (idx >= size)
                 goto backout;
 
@@ -976,7 +1969,7 @@ retry:
 
         if (write_access && !(vma->vm_flags & VM_SHARED)) {
                 /* Optimization, do the COW without a second fault */
-                ret = hugetlb_cow(mm, vma, address, ptep, new_pte);
+                ret = hugetlb_cow(mm, vma, address, ptep, new_pte, page);
         }
 
         spin_unlock(&mm->page_table_lock);
@@ -986,6 +1979,7 @@ out:
 
 backout:
         spin_unlock(&mm->page_table_lock);
+backout_unlocked:
         unlock_page(page);
         put_page(page);
         goto out;
@@ -997,9 +1991,11 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         pte_t *ptep;
         pte_t entry;
         int ret;
+        struct page *pagecache_page = NULL;
         static DEFINE_MUTEX(hugetlb_instantiation_mutex);
+        struct hstate *h = hstate_vma(vma);
 
-        ptep = huge_pte_alloc(mm, address);
+        ptep = huge_pte_alloc(mm, address, huge_page_size(h));
         if (!ptep)
                 return VM_FAULT_OOM;
 
@@ -1012,23 +2008,58 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
         entry = huge_ptep_get(ptep);
         if (huge_pte_none(entry)) {
                 ret = hugetlb_no_page(mm, vma, address, ptep, write_access);
-                mutex_unlock(&hugetlb_instantiation_mutex);
-                return ret;
+                goto out_unlock;
         }
 
         ret = 0;
 
+        /*
+         * If we are going to COW the mapping later, we examine the pending
+         * reservations for this page now. This will ensure that any
+         * allocations necessary to record that reservation occur outside the
+         * spinlock. For private mappings, we also lookup the pagecache
+         * page now as it is used to determine if a reservation has been
+         * consumed.
+         */
+        if (write_access && !pte_write(entry)) {
+                if (vma_needs_reservation(h, vma, address) < 0) {
+                        ret = VM_FAULT_OOM;
+                        goto out_unlock;
+                }
+
+                if (!(vma->vm_flags & VM_SHARED))
+                        pagecache_page = hugetlbfs_pagecache_page(h,
+                                                                vma, address);
+        }
+
         spin_lock(&mm->page_table_lock);
         /* Check for a racing update before calling hugetlb_cow */
         if (likely(pte_same(entry, huge_ptep_get(ptep))))
                 if (write_access && !pte_write(entry))
-                        ret = hugetlb_cow(mm, vma, address, ptep, entry);
+                        ret = hugetlb_cow(mm, vma, address, ptep, entry,
+                                                        pagecache_page);
         spin_unlock(&mm->page_table_lock);
+
+        if (pagecache_page) {
+                unlock_page(pagecache_page);
+                put_page(pagecache_page);
+        }
+
+out_unlock:
         mutex_unlock(&hugetlb_instantiation_mutex);
 
         return ret;
 }
 
+/* Can be overriden by architectures */
+__attribute__((weak)) struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+               pud_t *pud, int write)
+{
+        BUG();
+        return NULL;
+}
+
 int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
                         struct page **pages, struct vm_area_struct **vmas,
                         unsigned long *position, int *length, int i,
@@ -1037,6 +2068,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
         unsigned long pfn_offset;
         unsigned long vaddr = *position;
         int remainder = *length;
+        struct hstate *h = hstate_vma(vma);
 
         spin_lock(&mm->page_table_lock);
         while (vaddr < vma->vm_end && remainder) {
@@ -1048,7 +2080,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
                  * each hugepage.  We have to make * sure we get the
                  * first, for the page indexing below to work.
                  */
-                pte = huge_pte_offset(mm, vaddr & HPAGE_MASK);
+                pte = huge_pte_offset(mm, vaddr & huge_page_mask(h));
 
                 if (!pte || huge_pte_none(huge_ptep_get(pte)) ||
                     (write && !pte_write(huge_ptep_get(pte)))) {
@@ -1066,7 +2098,7 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
                         break;
                 }
 
-                pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT;
+                pfn_offset = (vaddr & ~huge_page_mask(h)) >> PAGE_SHIFT;
                 page = pte_page(huge_ptep_get(pte));
 same_page:
                 if (pages) {
@@ -1082,7 +2114,7 @@ same_page:
                 --remainder;
                 ++i;
                 if (vaddr < vma->vm_end && remainder &&
-                                pfn_offset < HPAGE_SIZE/PAGE_SIZE) {
+                                pfn_offset < pages_per_huge_page(h)) {
                         /*
                          * We use pfn_offset to avoid touching the pageframes
                          * of this compound page.
@@ -1104,13 +2136,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
         unsigned long start = address;
         pte_t *ptep;
         pte_t pte;
+        struct hstate *h = hstate_vma(vma);
 
         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) {
+        for (; address < end; address += huge_page_size(h)) {
                 ptep = huge_pte_offset(mm, address);
                 if (!ptep)
                         continue;
@@ -1128,195 +2161,59 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
         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)
+int hugetlb_reserve_pages(struct inode *inode,
+                                        long from, long to,
+                                        struct vm_area_struct *vma)
 {
-        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 guarantee to record the reservation. */
-        if (&rg->link == head || t < rg->from) {
-                nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
-                if (!nrg)
-                        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;
+        long ret, chg;
+        struct hstate *h = hstate_inode(inode);
 
-        /* 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)
+        if (vma && vma->vm_flags & VM_NORESERVE)
                 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);
         /*
-         * 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.
+         * Shared mappings base their reservation on the number of pages that
+         * are already allocated on behalf of the file. Private mappings need
+         * to reserve the full area even if read-only as mprotect() may be
+         * called to make the mapping read-write. Assume !vma is a shm mapping
          */
-        if (delta > 0) {
-                if (gather_surplus_pages(delta) < 0)
-                        goto out;
-
-                if (delta > cpuset_mems_nr(free_huge_pages_node)) {
-                        return_unused_surplus_pages(delta);
-                        goto out;
-                }
-        }
-
-        ret = 0;
-        if (delta < 0)
-                return_unused_surplus_pages((unsigned long) -delta);
+        if (!vma || vma->vm_flags & VM_SHARED)
+                chg = region_chg(&inode->i_mapping->private_list, from, to);
+        else {
+                struct resv_map *resv_map = resv_map_alloc();
+                if (!resv_map)
+                        return -ENOMEM;
 
-out:
-        spin_unlock(&hugetlb_lock);
-        return ret;
-}
+                chg = to - from;
 
-int hugetlb_reserve_pages(struct inode *inode, long from, long to)
-{
-        long ret, chg;
+                set_vma_resv_map(vma, resv_map);
+                set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
+        }
 
-        chg = region_chg(&inode->i_mapping->private_list, from, to);
         if (chg < 0)
                 return chg;
 
         if (hugetlb_get_quota(inode->i_mapping, chg))
                 return -ENOSPC;
-        ret = hugetlb_acct_memory(chg);
+        ret = hugetlb_acct_memory(h, chg);
         if (ret < 0) {
                 hugetlb_put_quota(inode->i_mapping, chg);
                 return ret;
         }
-        region_add(&inode->i_mapping->private_list, from, to);
+        if (!vma || vma->vm_flags & VM_SHARED)
+                region_add(&inode->i_mapping->private_list, from, to);
         return 0;
 }
 
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 {
+        struct hstate *h = hstate_inode(inode);
         long chg = region_truncate(&inode->i_mapping->private_list, offset);
 
         spin_lock(&inode->i_lock);
-        inode->i_blocks -= BLOCKS_PER_HUGEPAGE * freed;
+        inode->i_blocks -= blocks_per_huge_page(h);
         spin_unlock(&inode->i_lock);
 
         hugetlb_put_quota(inode->i_mapping, (chg - freed));
-        hugetlb_acct_memory(-(chg - freed));
+        hugetlb_acct_memory(h, -(chg - freed));
 }