Subversion Repositories or1k_soc_on_altera_embedded_dev_kit

/*

 * Generic hugetlb support.

 * (C) William Irwin, April 2004

 */

#include <linux/gfp.h>

#include <linux/list.h>

#include <linux/init.h>

#include <linux/module.h>

#include <linux/mm.h>

#include <linux/sysctl.h>

#include <linux/highmem.h>

#include <linux/nodemask.h>

#include <linux/pagemap.h>

#include <linux/mempolicy.h>

#include <linux/cpuset.h>

#include <linux/mutex.h>

#include <asm/page.h>

#include <asm/pgtable.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;

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 unsigned int surplus_huge_pages_node[MAX_NUMNODES];

static gfp_t htlb_alloc_mask = GFP_HIGHUSER;

unsigned long hugepages_treat_as_movable;

unsigned long nr_overcommit_huge_pages;

static int hugetlb_next_nid;

/*

 * 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)

{

        int i;

        might_sleep();

        for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); i++) {

                cond_resched();

                clear_user_highpage(page + i, addr + i * PAGE_SIZE);

        }

}

static void copy_huge_page(struct page *dst, struct page *src,

                           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, vma);

        }

}

static void enqueue_huge_page(struct page *page)

{

        int nid = page_to_nid(page);

        list_add(&page->lru, &hugepage_freelists[nid]);

        free_huge_pages++;

        free_huge_pages_node[nid]++;

}

static struct page *dequeue_huge_page(struct vm_area_struct *vma,

                                unsigned long address)

{

        int nid;

        struct page *page = NULL;

        struct mempolicy *mpol;

        struct zonelist *zonelist = huge_zonelist(vma, address,

                                        htlb_alloc_mask, &mpol);

        struct zone **z;

        for (z = zonelist->zones; *z; z++) {

                nid = zone_to_nid(*z);

                if (cpuset_zone_allowed_softwall(*z, htlb_alloc_mask) &&

                    !list_empty(&hugepage_freelists[nid])) {

                        page = list_entry(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--;

                        break;

                }

        }

        mpol_free(mpol);        /* unref if mpol !NULL */

        return page;

}

static void update_and_free_page(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++) {

                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);

        }

        set_compound_page_dtor(page, NULL);

        set_page_refcounted(page);

        __free_pages(page, HUGETLB_PAGE_ORDER);

}

static void free_huge_page(struct page *page)

{

        int nid = page_to_nid(page);

        struct address_space *mapping;

        mapping = (struct address_space *) page_private(page);

        BUG_ON(page_count(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]--;

        } else {

                enqueue_huge_page(page);

        }

        spin_unlock(&hugetlb_lock);

        if (mapping)

                hugetlb_put_quota(mapping, 1);

        set_page_private(page, 0);

}

/*

 * Increment or decrement surplus_huge_pages.  Keep node-specific counters

 * 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 prev_nid;

        int nid = prev_nid;

        int ret = 0;

        VM_BUG_ON(delta != -1 && delta != 1);

        do {

                nid = next_node(nid, node_online_map);

                if (nid == MAX_NUMNODES)

                        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])

                        continue;

                /* Surplus cannot exceed the total number of pages */

                if (delta > 0 && surplus_huge_pages_node[nid] >=

                                                nr_huge_pages_node[nid])

                        continue;

                surplus_huge_pages += delta;

                surplus_huge_pages_node[nid] += delta;

                ret = 1;

                break;

        } while (nid != prev_nid);

        prev_nid = nid;

        return ret;

}

static struct page *alloc_fresh_huge_page_node(int nid)

{

        struct page *page;

        page = alloc_pages_node(nid,

                htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|__GFP_NOWARN,

                HUGETLB_PAGE_ORDER);

        if (page) {

                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 */

        }

        return page;

}

static int alloc_fresh_huge_page(void)

{

        struct page *page;

        int start_nid;

        int next_nid;

        int ret = 0;

        start_nid = hugetlb_next_nid;

        do {

                page = alloc_fresh_huge_page_node(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);

        return ret;

}

static struct page *alloc_buddy_huge_page(struct vm_area_struct *vma,

                                                unsigned long address)

{

        struct page *page;

        unsigned int nid;

        /*

         * Assume we will successfully allocate the surplus page to

         * prevent racing processes from causing the surplus to exceed

         * overcommit

         *

         * This however introduces a different race, where a process B

         * tries to grow the static hugepage pool while alloc_pages() is

         * called by process A. B will only examine the per-node

         * counters in determining if surplus huge pages can be

         * converted to normal huge pages in adjust_pool_surplus(). A

         * won't be able to increment the per-node counter, until the

         * lock is dropped by B, but B doesn't drop hugetlb_lock until

         * no more huge pages can be converted from surplus to normal

         * state (and doesn't try to convert again). Thus, we have a

         * case where a surplus huge page exists, the pool is grown, and

         * the surplus huge page still exists after, even though it

         * should just have been converted to a normal huge page. This

         * does not leak memory, though, as the hugepage will be freed

         * once it is out of use. It also does not allow the counters to

         * go out of whack in adjust_pool_surplus() as we don't modify

         * the node values until we've gotten the hugepage and only the

         * per-node value is checked there.

         */

        spin_lock(&hugetlb_lock);

        if (surplus_huge_pages >= nr_overcommit_huge_pages) {

                spin_unlock(&hugetlb_lock);

                return NULL;

        } else {

                nr_huge_pages++;

                surplus_huge_pages++;

        }

        spin_unlock(&hugetlb_lock);

        page = alloc_pages(htlb_alloc_mask|__GFP_COMP|__GFP_NOWARN,

                                        HUGETLB_PAGE_ORDER);

        spin_lock(&hugetlb_lock);

        if (page) {

                nid = page_to_nid(page);

                set_compound_page_dtor(page, free_huge_page);

                /*

                 * We incremented the global counters already

                 */

                nr_huge_pages_node[nid]++;

                surplus_huge_pages_node[nid]++;

        } else {

                nr_huge_pages--;

                surplus_huge_pages--;

        }

        spin_unlock(&hugetlb_lock);

        return page;

}

/*

 * Increase the hugetlb pool such that it can accomodate a reservation

 * of size 'delta'.

 */

static int gather_surplus_pages(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;

        if (needed <= 0)

                return 0;

        allocated = 0;

        INIT_LIST_HEAD(&surplus_list);

        ret = -ENOMEM;

retry:

        spin_unlock(&hugetlb_lock);

        for (i = 0; i < needed; i++) {

                page = alloc_buddy_huge_page(NULL, 0);

                if (!page) {

                        /*

                         * We were not able to allocate enough pages to

                         * satisfy the entire reservation so we free what

                         * we've allocated so far.

                         */

                        spin_lock(&hugetlb_lock);

                        needed = 0;

                        goto free;

                }

                list_add(&page->lru, &surplus_list);

        }

        allocated += needed;

        /*

         * After retaking hugetlb_lock, we need to recalculate 'needed'

         * 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);

        if (needed > 0)

                goto retry;

        /*

         * The surplus_list now contains _at_least_ the number of extra pages

         * needed to accomodate the reservation.  Add the appropriate number

         * of pages to the hugetlb pool and free the extras back to the buddy

         * allocator.

         */

        needed += allocated;

        ret = 0;

free:

        list_for_each_entry_safe(page, tmp, &surplus_list, lru) {

                list_del(&page->lru);

                if ((--needed) >= 0)

                        enqueue_huge_page(page);

                else {

                        /*

                         * Decrement the refcount and free the page using its

                         * destructor.  This must be done with hugetlb_lock

                         * unlocked which is safe because free_huge_page takes

                         * hugetlb_lock before deciding how to free the page.

                         */

                        spin_unlock(&hugetlb_lock);

                        put_page(page);

                        spin_lock(&hugetlb_lock);

                }

        }

        return ret;

}

/*

 * When releasing a hugetlb pool reservation, any surplus pages that were

 * 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 int nid = -1;

        struct page *page;

        unsigned long nr_pages;

        nr_pages = min(unused_resv_pages, surplus_huge_pages);

        while (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])

                        continue;

                if (!list_empty(&hugepage_freelists[nid])) {

                        page = list_entry(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]--;

                        nr_pages--;

                }

        }

}

static struct page *alloc_huge_page_shared(struct vm_area_struct *vma,

                                                unsigned long addr)

{

        struct page *page;

        spin_lock(&hugetlb_lock);

        page = dequeue_huge_page(vma, addr);

        spin_unlock(&hugetlb_lock);

        return page ? page : ERR_PTR(-VM_FAULT_OOM);

}

static struct page *alloc_huge_page_private(struct vm_area_struct *vma,

                                                unsigned long addr)

{

        struct page *page = NULL;

        if (hugetlb_get_quota(vma->vm_file->f_mapping, 1))

                return ERR_PTR(-VM_FAULT_SIGBUS);

        spin_lock(&hugetlb_lock);

        if (free_huge_pages > resv_huge_pages)

                page = dequeue_huge_page(vma, addr);

        spin_unlock(&hugetlb_lock);

        if (!page) {

                page = alloc_buddy_huge_page(vma, addr);

                if (!page) {

                        hugetlb_put_quota(vma->vm_file->f_mapping, 1);

                        return ERR_PTR(-VM_FAULT_OOM);

                }

        }

        return page;

}

static struct page *alloc_huge_page(struct vm_area_struct *vma,

                                    unsigned long addr)

{

        struct page *page;

        struct address_space *mapping = vma->vm_file->f_mapping;

        if (vma->vm_flags & VM_MAYSHARE)

                page = alloc_huge_page_shared(vma, addr);

        else

                page = alloc_huge_page_private(vma, addr);

        if (!IS_ERR(page)) {

                set_page_refcounted(page);

                set_page_private(page, (unsigned long) mapping);

        }

        return page;

}

static int __init hugetlb_init(void)

{

        unsigned long i;

        if (HPAGE_SHIFT == 0)

                return 0;

        for (i = 0; i < MAX_NUMNODES; ++i)

                INIT_LIST_HEAD(&hugepage_freelists[i]);

        hugetlb_next_nid = first_node(node_online_map);

        for (i = 0; i < max_huge_pages; ++i) {

                if (!alloc_fresh_huge_page())

                        break;

        }

        max_huge_pages = free_huge_pages = nr_huge_pages = i;

        printk("Total HugeTLB memory allocated, %ld\n", free_huge_pages);

        return 0;

}

module_init(hugetlb_init);

static int __init hugetlb_setup(char *s)

{

        if (sscanf(s, "%lu", &max_huge_pages) <= 0)

                max_huge_pages = 0;

        return 1;

}

__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

#ifdef CONFIG_HIGHMEM

static void try_to_free_low(unsigned long count)

{

        int i;

        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)

                                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)]--;

                }

        }

}

#else

static inline void try_to_free_low(unsigned long count)

{

}

#endif

#define persistent_huge_pages (nr_huge_pages - surplus_huge_pages)

static unsigned long set_max_huge_pages(unsigned long count)

{

        unsigned long min_count, ret;

        /*

         * Increase the pool size

         * First take pages out of surplus state.  Then make up the

         * remaining difference by allocating fresh huge pages.

         *

         * We might race with alloc_buddy_huge_page() here and be unable

         * to convert a surplus huge page to a normal huge page. That is

         * not critical, though, it just means the overall size of the

         * pool might be one hugepage larger than it needs to be, but

         * 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))

                        break;

        }

        while (count > persistent_huge_pages) {

                int ret;

                /*

                 * 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();

                spin_lock(&hugetlb_lock);

                if (!ret)

                        goto out;

        }

        /*

         * Decrease the pool size

         * First return free pages to the buddy allocator (being careful

         * to keep enough around to satisfy reservations).  Then place

         * pages into surplus state as needed so the pool will shrink

         * to the desired size as pages become free.

         *

         * By placing pages into the surplus state independent of the

         * overcommit value, we are allowing the surplus pool size to

         * exceed overcommit. There are few sane options here. Since

         * alloc_buddy_huge_page() is checking the global counter,

         * though, we'll note that we're not allowed to exceed surplus

         * 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 = max(count, min_count);

        try_to_free_low(min_count);

        while (min_count < persistent_huge_pages) {

                struct page *page = dequeue_huge_page(NULL, 0);

                if (!page)

                        break;

                update_and_free_page(page);

        }

        while (count < persistent_huge_pages) {

                if (!adjust_pool_surplus(1))

                        break;

        }

out:

        ret = persistent_huge_pages;

        spin_unlock(&hugetlb_lock);

        return ret;

}

int hugetlb_sysctl_handler(struct ctl_table *table, int write,

                           struct file *file, void __user *buffer,

                           size_t *length, loff_t *ppos)

{

        proc_doulongvec_minmax(table, write, file, buffer, length, ppos);

        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_Surp:  %5lu\n"

                        "Hugepagesize:    %5lu kB\n",

                        nr_huge_pages,

                        free_huge_pages,

                        resv_huge_pages,

                        surplus_huge_pages,

                        HPAGE_SIZE/1024);

}

int hugetlb_report_node_meminfo(int nid, char *buf)

{

        return sprintf(buf,

                "Node %d HugePages_Total: %5u\n"

                "Node %d HugePages_Free:  %5u\n",

                nid, nr_huge_pages_node[nid],

                nid, free_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);

}

/*

 * We cannot handle pagefaults against hugetlb pages at all.  They cause

 * handle_mm_fault() to try to instantiate regular-sized pages in the

 * hugegpage VMA.  do_page_fault() is supposed to trap this, so BUG is we get

 * this far.

 */

static int hugetlb_vm_op_fault(struct vm_area_struct *vma, struct vm_fault *vmf)

{

        BUG();

        return 0;

}

struct vm_operations_struct hugetlb_vm_ops = {

        .fault = hugetlb_vm_op_fault,

};

static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page,

                                int writable)

{

        pte_t entry;

        if (writable) {

                entry =

                    pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));

        } else {

                entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot));

        }

        entry = pte_mkyoung(entry);

        entry = pte_mkhuge(entry);

        return entry;

}

static void set_huge_ptep_writable(struct vm_area_struct *vma,

                                   unsigned long address, pte_t *ptep)

{

        pte_t entry;

        entry = pte_mkwrite(pte_mkdirty(*ptep));

        if (ptep_set_access_flags(vma, address, ptep, entry, 1)) {

                update_mmu_cache(vma, address, entry);

        }

}

int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,

                            struct vm_area_struct *vma)

{

        pte_t *src_pte, *dst_pte, entry;

        struct page *ptepage;

        unsigned long addr;