blob: 7c204e3d132b808364fc1e87e3dace180f9ba173 [file] [log] [blame]
/*
* Generic hugetlb support.
* (C) Nadia Yvette Chambers, April 2004
*/
#include <linux/list.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/seq_file.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/compiler.h>
#include <linux/cpuset.h>
#include <linux/mutex.h>
#include <linux/bootmem.h>
#include <linux/sysfs.h>
#include <linux/slab.h>
#include <linux/sched/signal.h>
#include <linux/rmap.h>
#include <linux/string_helpers.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/jhash.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/tlb.h>
#include <linux/io.h>
#include <linux/hugetlb.h>
#include <linux/hugetlb_cgroup.h>
#include <linux/node.h>
#include <linux/userfaultfd_k.h>
#include <linux/page_owner.h>
#include "internal.h"
int hugetlb_max_hstate __read_mostly;
unsigned int default_hstate_idx;
struct hstate hstates[HUGE_MAX_HSTATE];
/*
* Minimum page order among possible hugepage sizes, set to a proper value
* at boot time.
*/
static unsigned int minimum_order __read_mostly = UINT_MAX;
__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;
static bool __initdata parsed_valid_hugepagesz = true;
/*
* Protects updates to hugepage_freelists, hugepage_activelist, nr_huge_pages,
* free_huge_pages, and surplus_huge_pages.
*/
DEFINE_SPINLOCK(hugetlb_lock);
/*
* Serializes faults on the same logical page. This is used to
* prevent spurious OOMs when the hugepage pool is fully utilized.
*/
static int num_fault_mutexes;
struct mutex *hugetlb_fault_mutex_table ____cacheline_aligned_in_smp;
/* Forward declaration */
static int hugetlb_acct_memory(struct hstate *h, long delta);
static inline void unlock_or_release_subpool(struct hugepage_subpool *spool)
{
bool free = (spool->count == 0) && (spool->used_hpages == 0);
spin_unlock(&spool->lock);
/* If no pages are used, and no other handles to the subpool
* remain, give up any reservations mased on minimum size and
* free the subpool */
if (free) {
if (spool->min_hpages != -1)
hugetlb_acct_memory(spool->hstate,
-spool->min_hpages);
kfree(spool);
}
}
struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages,
long min_hpages)
{
struct hugepage_subpool *spool;
spool = kzalloc(sizeof(*spool), GFP_KERNEL);
if (!spool)
return NULL;
spin_lock_init(&spool->lock);
spool->count = 1;
spool->max_hpages = max_hpages;
spool->hstate = h;
spool->min_hpages = min_hpages;
if (min_hpages != -1 && hugetlb_acct_memory(h, min_hpages)) {
kfree(spool);
return NULL;
}
spool->rsv_hpages = min_hpages;
return spool;
}
void hugepage_put_subpool(struct hugepage_subpool *spool)
{
spin_lock(&spool->lock);
BUG_ON(!spool->count);
spool->count--;
unlock_or_release_subpool(spool);
}
/*
* Subpool accounting for allocating and reserving pages.
* Return -ENOMEM if there are not enough resources to satisfy the
* the request. Otherwise, return the number of pages by which the
* global pools must be adjusted (upward). The returned value may
* only be different than the passed value (delta) in the case where
* a subpool minimum size must be manitained.
*/
static long hugepage_subpool_get_pages(struct hugepage_subpool *spool,
long delta)
{
long ret = delta;
if (!spool)
return ret;
spin_lock(&spool->lock);
if (spool->max_hpages != -1) { /* maximum size accounting */
if ((spool->used_hpages + delta) <= spool->max_hpages)
spool->used_hpages += delta;
else {
ret = -ENOMEM;
goto unlock_ret;
}
}
/* minimum size accounting */
if (spool->min_hpages != -1 && spool->rsv_hpages) {
if (delta > spool->rsv_hpages) {
/*
* Asking for more reserves than those already taken on
* behalf of subpool. Return difference.
*/
ret = delta - spool->rsv_hpages;
spool->rsv_hpages = 0;
} else {
ret = 0; /* reserves already accounted for */
spool->rsv_hpages -= delta;
}
}
unlock_ret:
spin_unlock(&spool->lock);
return ret;
}
/*
* Subpool accounting for freeing and unreserving pages.
* Return the number of global page reservations that must be dropped.
* The return value may only be different than the passed value (delta)
* in the case where a subpool minimum size must be maintained.
*/
static long hugepage_subpool_put_pages(struct hugepage_subpool *spool,
long delta)
{
long ret = delta;
if (!spool)
return delta;
spin_lock(&spool->lock);
if (spool->max_hpages != -1) /* maximum size accounting */
spool->used_hpages -= delta;
/* minimum size accounting */
if (spool->min_hpages != -1 && spool->used_hpages < spool->min_hpages) {
if (spool->rsv_hpages + delta <= spool->min_hpages)
ret = 0;
else
ret = spool->rsv_hpages + delta - spool->min_hpages;
spool->rsv_hpages += delta;
if (spool->rsv_hpages > spool->min_hpages)
spool->rsv_hpages = spool->min_hpages;
}
/*
* If hugetlbfs_put_super couldn't free spool due to an outstanding
* quota reference, free it now.
*/
unlock_or_release_subpool(spool);
return ret;
}
static inline struct hugepage_subpool *subpool_inode(struct inode *inode)
{
return HUGETLBFS_SB(inode->i_sb)->spool;
}
static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
{
return subpool_inode(file_inode(vma->vm_file));
}
/*
* Region tracking -- allows tracking of reservations and instantiated pages
* across the pages in a mapping.
*
* The region data structures are embedded into a resv_map and protected
* by a resv_map's lock. The set of regions within the resv_map represent
* reservations for huge pages, or huge pages that have already been
* instantiated within the map. The from and to elements are huge page
* indicies into the associated mapping. from indicates the starting index
* of the region. to represents the first index past the end of the region.
*
* For example, a file region structure with from == 0 and to == 4 represents
* four huge pages in a mapping. It is important to note that the to element
* represents the first element past the end of the region. This is used in
* arithmetic as 4(to) - 0(from) = 4 huge pages in the region.
*
* Interval notation of the form [from, to) will be used to indicate that
* the endpoint from is inclusive and to is exclusive.
*/
struct file_region {
struct list_head link;
long from;
long to;
};
/*
* Add the huge page range represented by [f, t) to the reserve
* map. In the normal case, existing regions will be expanded
* to accommodate the specified range. Sufficient regions should
* exist for expansion due to the previous call to region_chg
* with the same range. However, it is possible that region_del
* could have been called after region_chg and modifed the map
* in such a way that no region exists to be expanded. In this
* case, pull a region descriptor from the cache associated with
* the map and use that for the new range.
*
* Return the number of new huge pages added to the map. This
* number is greater than or equal to zero.
*/
static long region_add(struct resv_map *resv, long f, long t)
{
struct list_head *head = &resv->regions;
struct file_region *rg, *nrg, *trg;
long add = 0;
spin_lock(&resv->lock);
/* Locate the region we are either in or before. */
list_for_each_entry(rg, head, link)
if (f <= rg->to)
break;
/*
* If no region exists which can be expanded to include the
* specified range, the list must have been modified by an
* interleving call to region_del(). Pull a region descriptor
* from the cache and use it for this range.
*/
if (&rg->link == head || t < rg->from) {
VM_BUG_ON(resv->region_cache_count <= 0);
resv->region_cache_count--;
nrg = list_first_entry(&resv->region_cache, struct file_region,
link);
list_del(&nrg->link);
nrg->from = f;
nrg->to = t;
list_add(&nrg->link, rg->link.prev);
add += t - f;
goto out_locked;
}
/* 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) {
/* Decrement return value by the deleted range.
* Another range will span this area so that by
* end of routine add will be >= zero
*/
add -= (rg->to - rg->from);
list_del(&rg->link);
kfree(rg);
}
}
add += (nrg->from - f); /* Added to beginning of region */
nrg->from = f;
add += t - nrg->to; /* Added to end of region */
nrg->to = t;
out_locked:
resv->adds_in_progress--;
spin_unlock(&resv->lock);
VM_BUG_ON(add < 0);
return add;
}
/*
* Examine the existing reserve map and determine how many
* huge pages in the specified range [f, t) are NOT currently
* represented. This routine is called before a subsequent
* call to region_add that will actually modify the reserve
* map to add the specified range [f, t). region_chg does
* not change the number of huge pages represented by the
* map. However, if the existing regions in the map can not
* be expanded to represent the new range, a new file_region
* structure is added to the map as a placeholder. This is
* so that the subsequent region_add call will have all the
* regions it needs and will not fail.
*
* Upon entry, region_chg will also examine the cache of region descriptors
* associated with the map. If there are not enough descriptors cached, one
* will be allocated for the in progress add operation.
*
* Returns the number of huge pages that need to be added to the existing
* reservation map for the range [f, t). This number is greater or equal to
* zero. -ENOMEM is returned if a new file_region structure or cache entry
* is needed and can not be allocated.
*/
static long region_chg(struct resv_map *resv, long f, long t)
{
struct list_head *head = &resv->regions;
struct file_region *rg, *nrg = NULL;
long chg = 0;
retry:
spin_lock(&resv->lock);
retry_locked:
resv->adds_in_progress++;
/*
* Check for sufficient descriptors in the cache to accommodate
* the number of in progress add operations.
*/
if (resv->adds_in_progress > resv->region_cache_count) {
struct file_region *trg;
VM_BUG_ON(resv->adds_in_progress - resv->region_cache_count > 1);
/* Must drop lock to allocate a new descriptor. */
resv->adds_in_progress--;
spin_unlock(&resv->lock);
trg = kmalloc(sizeof(*trg), GFP_KERNEL);
if (!trg) {
kfree(nrg);
return -ENOMEM;
}
spin_lock(&resv->lock);
list_add(&trg->link, &resv->region_cache);
resv->region_cache_count++;
goto retry_locked;
}
/* 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) {
if (!nrg) {
resv->adds_in_progress--;
spin_unlock(&resv->lock);
nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
if (!nrg)
return -ENOMEM;
nrg->from = f;
nrg->to = f;
INIT_LIST_HEAD(&nrg->link);
goto retry;
}
list_add(&nrg->link, rg->link.prev);
chg = t - f;
goto out_nrg;
}
/* 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)
goto out;
/* We overlap with this area, if it extends further 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;
}
out:
spin_unlock(&resv->lock);
/* We already know we raced and no longer need the new region */
kfree(nrg);
return chg;
out_nrg:
spin_unlock(&resv->lock);
return chg;
}
/*
* Abort the in progress add operation. The adds_in_progress field
* of the resv_map keeps track of the operations in progress between
* calls to region_chg and region_add. Operations are sometimes
* aborted after the call to region_chg. In such cases, region_abort
* is called to decrement the adds_in_progress counter.
*
* NOTE: The range arguments [f, t) are not needed or used in this
* routine. They are kept to make reading the calling code easier as
* arguments will match the associated region_chg call.
*/
static void region_abort(struct resv_map *resv, long f, long t)
{
spin_lock(&resv->lock);
VM_BUG_ON(!resv->region_cache_count);
resv->adds_in_progress--;
spin_unlock(&resv->lock);
}
/*
* Delete the specified range [f, t) from the reserve map. If the
* t parameter is LONG_MAX, this indicates that ALL regions after f
* should be deleted. Locate the regions which intersect [f, t)
* and either trim, delete or split the existing regions.
*
* Returns the number of huge pages deleted from the reserve map.
* In the normal case, the return value is zero or more. In the
* case where a region must be split, a new region descriptor must
* be allocated. If the allocation fails, -ENOMEM will be returned.
* NOTE: If the parameter t == LONG_MAX, then we will never split
* a region and possibly return -ENOMEM. Callers specifying
* t == LONG_MAX do not need to check for -ENOMEM error.
*/
static long region_del(struct resv_map *resv, long f, long t)
{
struct list_head *head = &resv->regions;
struct file_region *rg, *trg;
struct file_region *nrg = NULL;
long del = 0;
retry:
spin_lock(&resv->lock);
list_for_each_entry_safe(rg, trg, head, link) {
/*
* Skip regions before the range to be deleted. file_region
* ranges are normally of the form [from, to). However, there
* may be a "placeholder" entry in the map which is of the form
* (from, to) with from == to. Check for placeholder entries
* at the beginning of the range to be deleted.
*/
if (rg->to <= f && (rg->to != rg->from || rg->to != f))
continue;
if (rg->from >= t)
break;
if (f > rg->from && t < rg->to) { /* Must split region */
/*
* Check for an entry in the cache before dropping
* lock and attempting allocation.
*/
if (!nrg &&
resv->region_cache_count > resv->adds_in_progress) {
nrg = list_first_entry(&resv->region_cache,
struct file_region,
link);
list_del(&nrg->link);
resv->region_cache_count--;
}
if (!nrg) {
spin_unlock(&resv->lock);
nrg = kmalloc(sizeof(*nrg), GFP_KERNEL);
if (!nrg)
return -ENOMEM;
goto retry;
}
del += t - f;
/* New entry for end of split region */
nrg->from = t;
nrg->to = rg->to;
INIT_LIST_HEAD(&nrg->link);
/* Original entry is trimmed */
rg->to = f;
list_add(&nrg->link, &rg->link);
nrg = NULL;
break;
}
if (f <= rg->from && t >= rg->to) { /* Remove entire region */
del += rg->to - rg->from;
list_del(&rg->link);
kfree(rg);
continue;
}
if (f <= rg->from) { /* Trim beginning of region */
del += t - rg->from;
rg->from = t;
} else { /* Trim end of region */
del += rg->to - f;
rg->to = f;
}
}
spin_unlock(&resv->lock);
kfree(nrg);
return del;
}
/*
* A rare out of memory error was encountered which prevented removal of
* the reserve map region for a page. The huge page itself was free'ed
* and removed from the page cache. This routine will adjust the subpool
* usage count, and the global reserve count if needed. By incrementing
* these counts, the reserve map entry which could not be deleted will
* appear as a "reserved" entry instead of simply dangling with incorrect
* counts.
*/
void hugetlb_fix_reserve_counts(struct inode *inode)
{
struct hugepage_subpool *spool = subpool_inode(inode);
long rsv_adjust;
rsv_adjust = hugepage_subpool_get_pages(spool, 1);
if (rsv_adjust) {
struct hstate *h = hstate_inode(inode);
hugetlb_acct_memory(h, 1);
}
}
/*
* Count and return the number of huge pages in the reserve map
* that intersect with the range [f, t).
*/
static long region_count(struct resv_map *resv, long f, long t)
{
struct list_head *head = &resv->regions;
struct file_region *rg;
long chg = 0;
spin_lock(&resv->lock);
/* Locate each segment we overlap with, and count that overlap. */
list_for_each_entry(rg, head, link) {
long seg_from;
long 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;
}
spin_unlock(&resv->lock);
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));
}
pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
unsigned long address)
{
return vma_hugecache_offset(hstate_vma(vma), vma, address);
}
EXPORT_SYMBOL_GPL(linear_hugepage_index);
/*
* Return the size of the pages allocated when backing a VMA. In the majority
* cases this will be same size as used by the page table entries.
*/
unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
{
struct hstate *hstate;
if (!is_vm_hugetlb_page(vma))
return PAGE_SIZE;
hstate = hstate_vma(vma);
return 1UL << huge_page_shift(hstate);
}
EXPORT_SYMBOL_GPL(vma_kernel_pagesize);
/*
* Return the page size being used by the MMU to back a VMA. In the majority
* of cases, the page size used by the kernel matches the MMU size. On
* architectures where it differs, an architecture-specific version of this
* function is required.
*/
#ifndef vma_mmu_pagesize
unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
{
return vma_kernel_pagesize(vma);
}
#endif
/*
* 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 *resv_map_alloc(void)
{
struct resv_map *resv_map = kmalloc(sizeof(*resv_map), GFP_KERNEL);
struct file_region *rg = kmalloc(sizeof(*rg), GFP_KERNEL);
if (!resv_map || !rg) {
kfree(resv_map);
kfree(rg);
return NULL;
}
kref_init(&resv_map->refs);
spin_lock_init(&resv_map->lock);
INIT_LIST_HEAD(&resv_map->regions);
resv_map->adds_in_progress = 0;
INIT_LIST_HEAD(&resv_map->region_cache);
list_add(&rg->link, &resv_map->region_cache);
resv_map->region_cache_count = 1;
return resv_map;
}
void resv_map_release(struct kref *ref)
{
struct resv_map *resv_map = container_of(ref, struct resv_map, refs);
struct list_head *head = &resv_map->region_cache;
struct file_region *rg, *trg;
/* Clear out any active regions before we release the map. */
region_del(resv_map, 0, LONG_MAX);
/* ... and any entries left in the cache */
list_for_each_entry_safe(rg, trg, head, link) {
list_del(&rg->link);
kfree(rg);
}
VM_BUG_ON(resv_map->adds_in_progress);
kfree(resv_map);
}
static inline struct resv_map *inode_resv_map(struct inode *inode)
{
return inode->i_mapping->private_data;
}
static struct resv_map *vma_resv_map(struct vm_area_struct *vma)
{
VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
if (vma->vm_flags & VM_MAYSHARE) {
struct address_space *mapping = vma->vm_file->f_mapping;
struct inode *inode = mapping->host;
return inode_resv_map(inode);
} else {
return (struct resv_map *)(get_vma_private_data(vma) &
~HPAGE_RESV_MASK);
}
}
static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map)
{
VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma);
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_VMA(!is_vm_hugetlb_page(vma), vma);
VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma);
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_VMA(!is_vm_hugetlb_page(vma), vma);
return (get_vma_private_data(vma) & flag) != 0;
}
/* Reset counters to 0 and clear all HPAGE_RESV_* flags */
void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma);
if (!(vma->vm_flags & VM_MAYSHARE))
vma->vm_private_data = (void *)0;
}
/* Returns true if the VMA has associated reserve pages */
static bool vma_has_reserves(struct vm_area_struct *vma, long chg)
{
if (vma->vm_flags & VM_NORESERVE) {
/*
* This address is already reserved by other process(chg == 0),
* so, we should decrement reserved count. Without decrementing,
* reserve count remains after releasing inode, because this
* allocated page will go into page cache and is regarded as
* coming from reserved pool in releasing step. Currently, we
* don't have any other solution to deal with this situation
* properly, so add work-around here.
*/
if (vma->vm_flags & VM_MAYSHARE && chg == 0)
return true;
else
return false;
}
/* Shared mappings always use reserves */
if (vma->vm_flags & VM_MAYSHARE) {
/*
* We know VM_NORESERVE is not set. Therefore, there SHOULD
* be a region map for all pages. The only situation where
* there is no region map is if a hole was punched via
* fallocate. In this case, there really are no reverves to
* use. This situation is indicated if chg != 0.
*/
if (chg)
return false;
else
return true;
}
/*
* Only the process that called mmap() has reserves for
* private mappings.
*/
if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
/*
* Like the shared case above, a hole punch or truncate
* could have been performed on the private mapping.
* Examine the value of chg to determine if reserves
* actually exist or were previously consumed.
* Very Subtle - The value of chg comes from a previous
* call to vma_needs_reserves(). The reserve map for
* private mappings has different (opposite) semantics
* than that of shared mappings. vma_needs_reserves()
* has already taken this difference in semantics into
* account. Therefore, the meaning of chg is the same
* as in the shared case above. Code could easily be
* combined, but keeping it separate draws attention to
* subtle differences.
*/
if (chg)
return false;
else
return true;
}
return false;
}
static void enqueue_huge_page(struct hstate *h, struct page *page)
{
int nid = page_to_nid(page);
list_move(&page->lru, &h->hugepage_freelists[nid]);
h->free_huge_pages++;
h->free_huge_pages_node[nid]++;
}
static struct page *dequeue_huge_page_node_exact(struct hstate *h, int nid)
{
struct page *page;
list_for_each_entry(page, &h->hugepage_freelists[nid], lru)
if (!PageHWPoison(page))
break;
/*
* if 'non-isolated free hugepage' not found on the list,
* the allocation fails.
*/
if (&h->hugepage_freelists[nid] == &page->lru)
return NULL;
list_move(&page->lru, &h->hugepage_activelist);
set_page_refcounted(page);
h->free_huge_pages--;
h->free_huge_pages_node[nid]--;
return page;
}
static struct page *dequeue_huge_page_nodemask(struct hstate *h, gfp_t gfp_mask, int nid,
nodemask_t *nmask)
{
unsigned int cpuset_mems_cookie;
struct zonelist *zonelist;
struct zone *zone;
struct zoneref *z;
int node = -1;
zonelist = node_zonelist(nid, gfp_mask);
retry_cpuset:
cpuset_mems_cookie = read_mems_allowed_begin();
for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nmask) {
struct page *page;
if (!cpuset_zone_allowed(zone, gfp_mask))
continue;
/*
* no need to ask again on the same node. Pool is node rather than
* zone aware
*/
if (zone_to_nid(zone) == node)
continue;
node = zone_to_nid(zone);
page = dequeue_huge_page_node_exact(h, node);
if (page)
return page;
}
if (unlikely(read_mems_allowed_retry(cpuset_mems_cookie)))
goto retry_cpuset;
return NULL;
}
/* Movability of hugepages depends on migration support. */
static inline gfp_t htlb_alloc_mask(struct hstate *h)
{
if (hugepage_migration_supported(h))
return GFP_HIGHUSER_MOVABLE;
else
return GFP_HIGHUSER;
}
static struct page *dequeue_huge_page_vma(struct hstate *h,
struct vm_area_struct *vma,
unsigned long address, int avoid_reserve,
long chg)
{
struct page *page;
struct mempolicy *mpol;
gfp_t gfp_mask;
nodemask_t *nodemask;
int nid;
/*
* 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, chg) &&
h->free_huge_pages - h->resv_huge_pages == 0)
goto err;
/* If reserves cannot be used, ensure enough pages are in the pool */
if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
goto err;
gfp_mask = htlb_alloc_mask(h);
nid = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
page = dequeue_huge_page_nodemask(h, gfp_mask, nid, nodemask);
if (page && !avoid_reserve && vma_has_reserves(vma, chg)) {
SetPagePrivate(page);
h->resv_huge_pages--;
}
mpol_cond_put(mpol);
return page;
err:
return NULL;
}
/*
* common helper functions for hstate_next_node_to_{alloc|free}.
* We may have allocated or freed a huge page based on a different
* nodes_allowed previously, so h->next_node_to_{alloc|free} might
* be outside of *nodes_allowed. Ensure that we use an allowed
* node for alloc or free.
*/
static int next_node_allowed(int nid, nodemask_t *nodes_allowed)
{
nid = next_node_in(nid, *nodes_allowed);
VM_BUG_ON(nid >= MAX_NUMNODES);
return nid;
}
static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed)
{
if (!node_isset(nid, *nodes_allowed))
nid = next_node_allowed(nid, nodes_allowed);
return nid;
}
/*
* returns the previously saved node ["this node"] from which to
* allocate a persistent huge page for the pool and advance the
* next node from which to allocate, handling wrap at end of node
* mask.
*/
static int hstate_next_node_to_alloc(struct hstate *h,
nodemask_t *nodes_allowed)
{
int nid;
VM_BUG_ON(!nodes_allowed);
nid = get_valid_node_allowed(h->next_nid_to_alloc, nodes_allowed);
h->next_nid_to_alloc = next_node_allowed(nid, nodes_allowed);
return nid;
}
/*
* helper for free_pool_huge_page() - return the previously saved
* node ["this node"] from which to free a huge page. Advance the
* next node id whether or not we find a free huge page to free so
* that the next attempt to free addresses the next node.
*/
static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
{
int nid;
VM_BUG_ON(!nodes_allowed);
nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed);
h->next_nid_to_free = next_node_allowed(nid, nodes_allowed);
return nid;
}
#define for_each_node_mask_to_alloc(hs, nr_nodes, node, mask) \
for (nr_nodes = nodes_weight(*mask); \
nr_nodes > 0 && \
((node = hstate_next_node_to_alloc(hs, mask)) || 1); \
nr_nodes--)
#define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \
for (nr_nodes = nodes_weight(*mask); \
nr_nodes > 0 && \
((node = hstate_next_node_to_free(hs, mask)) || 1); \
nr_nodes--)
#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
static void destroy_compound_gigantic_page(struct page *page,
unsigned int order)
{
int i;
int nr_pages = 1 << order;
struct page *p = page + 1;
atomic_set(compound_mapcount_ptr(page), 0);
for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
clear_compound_head(p);
set_page_refcounted(p);
}
set_compound_order(page, 0);
__ClearPageHead(page);
}
static void free_gigantic_page(struct page *page, unsigned int order)
{
free_contig_range(page_to_pfn(page), 1 << order);
}
static int __alloc_gigantic_page(unsigned long start_pfn,
unsigned long nr_pages, gfp_t gfp_mask)
{
unsigned long end_pfn = start_pfn + nr_pages;
return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE,
gfp_mask);
}
static bool pfn_range_valid_gigantic(struct zone *z,
unsigned long start_pfn, unsigned long nr_pages)
{
unsigned long i, end_pfn = start_pfn + nr_pages;
struct page *page;
for (i = start_pfn; i < end_pfn; i++) {
if (!pfn_valid(i))
return false;
page = pfn_to_page(i);
if (page_zone(page) != z)
return false;
if (PageReserved(page))
return false;
if (page_count(page) > 0)
return false;
if (PageHuge(page))
return false;
}
return true;
}
static bool zone_spans_last_pfn(const struct zone *zone,
unsigned long start_pfn, unsigned long nr_pages)
{
unsigned long last_pfn = start_pfn + nr_pages - 1;
return zone_spans_pfn(zone, last_pfn);
}
static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nodemask)
{
unsigned int order = huge_page_order(h);
unsigned long nr_pages = 1 << order;
unsigned long ret, pfn, flags;
struct zonelist *zonelist;
struct zone *zone;
struct zoneref *z;
zonelist = node_zonelist(nid, gfp_mask);
for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(gfp_mask), nodemask) {
spin_lock_irqsave(&zone->lock, flags);
pfn = ALIGN(zone->zone_start_pfn, nr_pages);
while (zone_spans_last_pfn(zone, pfn, nr_pages)) {
if (pfn_range_valid_gigantic(zone, pfn, nr_pages)) {
/*
* We release the zone lock here because
* alloc_contig_range() will also lock the zone
* at some point. If there's an allocation
* spinning on this lock, it may win the race
* and cause alloc_contig_range() to fail...
*/
spin_unlock_irqrestore(&zone->lock, flags);
ret = __alloc_gigantic_page(pfn, nr_pages, gfp_mask);
if (!ret)
return pfn_to_page(pfn);
spin_lock_irqsave(&zone->lock, flags);
}
pfn += nr_pages;
}
spin_unlock_irqrestore(&zone->lock, flags);
}
return NULL;
}
static void prep_new_huge_page(struct hstate *h, struct page *page, int nid);
static void prep_compound_gigantic_page(struct page *page, unsigned int order);
#else /* !CONFIG_ARCH_HAS_GIGANTIC_PAGE */
static inline bool gigantic_page_supported(void) { return false; }
static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nodemask) { return NULL; }
static inline void free_gigantic_page(struct page *page, unsigned int order) { }
static inline void destroy_compound_gigantic_page(struct page *page,
unsigned int order) { }
#endif
static void update_and_free_page(struct hstate *h, struct page *page)
{
int i;
if (hstate_is_gigantic(h) && !gigantic_page_supported())
return;
h->nr_huge_pages--;
h->nr_huge_pages_node[page_to_nid(page)]--;
for (i = 0; i < pages_per_huge_page(h); i++) {
page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
1 << PG_referenced | 1 << PG_dirty |
1 << PG_active | 1 << PG_private |
1 << PG_writeback);
}
VM_BUG_ON_PAGE(hugetlb_cgroup_from_page(page), page);
set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
set_page_refcounted(page);
if (hstate_is_gigantic(h)) {
destroy_compound_gigantic_page(page, huge_page_order(h));
free_gigantic_page(page, huge_page_order(h));
} else {
__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;
}
/*
* Test to determine whether the hugepage is "active/in-use" (i.e. being linked
* to hstate->hugepage_activelist.)
*
* This function can be called for tail pages, but never returns true for them.
*/
bool page_huge_active(struct page *page)
{
VM_BUG_ON_PAGE(!PageHuge(page), page);
return PageHead(page) && PagePrivate(&page[1]);
}
/* never called for tail page */
static void set_page_huge_active(struct page *page)
{
VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
SetPagePrivate(&page[1]);
}
static void clear_page_huge_active(struct page *page)
{
VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
ClearPagePrivate(&page[1]);
}
/*
* Internal hugetlb specific page flag. Do not use outside of the hugetlb
* code
*/
static inline bool PageHugeTemporary(struct page *page)
{
if (!PageHuge(page))
return false;
return (unsigned long)page[2].mapping == -1U;
}
static inline void SetPageHugeTemporary(struct page *page)
{
page[2].mapping = (void *)-1U;
}
static inline void ClearPageHugeTemporary(struct page *page)
{
page[2].mapping = NULL;
}
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 hugepage_subpool *spool =
(struct hugepage_subpool *)page_private(page);
bool restore_reserve;
set_page_private(page, 0);
page->mapping = NULL;
VM_BUG_ON_PAGE(page_count(page), page);
VM_BUG_ON_PAGE(page_mapcount(page), page);
restore_reserve = PagePrivate(page);
ClearPagePrivate(page);
/*
* A return code of zero implies that the subpool will be under its
* minimum size if the reservation is not restored after page is free.
* Therefore, force restore_reserve operation.
*/
if (hugepage_subpool_put_pages(spool, 1) == 0)
restore_reserve = true;
spin_lock(&hugetlb_lock);
clear_page_huge_active(page);
hugetlb_cgroup_uncharge_page(hstate_index(h),
pages_per_huge_page(h), page);
if (restore_reserve)
h->resv_huge_pages++;
if (PageHugeTemporary(page)) {
list_del(&page->lru);
ClearPageHugeTemporary(page);
update_and_free_page(h, page);
} else if (h->surplus_huge_pages_node[nid]) {
/* remove the page from active list */
list_del(&page->lru);
update_and_free_page(h, page);
h->surplus_huge_pages--;
h->surplus_huge_pages_node[nid]--;
} else {
arch_clear_hugepage_flags(page);
enqueue_huge_page(h, page);
}
spin_unlock(&hugetlb_lock);
}
static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
INIT_LIST_HEAD(&page->lru);
set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
spin_lock(&hugetlb_lock);
set_hugetlb_cgroup(page, NULL);
h->nr_huge_pages++;
h->nr_huge_pages_node[nid]++;
spin_unlock(&hugetlb_lock);
}
static void prep_compound_gigantic_page(struct page *page, unsigned int order)
{
int i;
int nr_pages = 1 << order;
struct page *p = page + 1;
/* we rely on prep_new_huge_page to set the destructor */
set_compound_order(page, order);
__ClearPageReserved(page);
__SetPageHead(page);
for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
/*
* For gigantic hugepages allocated through bootmem at
* boot, it's safer to be consistent with the not-gigantic
* hugepages and clear the PG_reserved bit from all tail pages
* too. Otherwse drivers using get_user_pages() to access tail
* pages may get the reference counting wrong if they see
* PG_reserved set on a tail page (despite the head page not
* having PG_reserved set). Enforcing this consistency between
* head and tail pages allows drivers to optimize away a check
* on the head page when they need know if put_page() is needed
* after get_user_pages().
*/
__ClearPageReserved(p);
set_page_count(p, 0);
set_compound_head(p, page);
}
atomic_set(compound_mapcount_ptr(page), -1);
}
/*
* PageHuge() only returns true for hugetlbfs pages, but not for normal or
* transparent huge pages. See the PageTransHuge() documentation for more
* details.
*/
int PageHuge(struct page *page)
{
if (!PageCompound(page))
return 0;
page = compound_head(page);
return page[1].compound_dtor == HUGETLB_PAGE_DTOR;
}
EXPORT_SYMBOL_GPL(PageHuge);
/*
* PageHeadHuge() only returns true for hugetlbfs head page, but not for
* normal or transparent huge pages.
*/
int PageHeadHuge(struct page *page_head)
{
if (!PageHead(page_head))
return 0;
return get_compound_page_dtor(page_head) == free_huge_page;
}
pgoff_t __basepage_index(struct page *page)
{
struct page *page_head = compound_head(page);
pgoff_t index = page_index(page_head);
unsigned long compound_idx;
if (!PageHuge(page_head))
return page_index(page);
if (compound_order(page_head) >= MAX_ORDER)
compound_idx = page_to_pfn(page) - page_to_pfn(page_head);
else
compound_idx = page - page_head;
return (index << compound_order(page_head)) + compound_idx;
}
static struct page *alloc_buddy_huge_page(struct hstate *h,
gfp_t gfp_mask, int nid, nodemask_t *nmask)
{
int order = huge_page_order(h);
struct page *page;
gfp_mask |= __GFP_COMP|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
if (nid == NUMA_NO_NODE)
nid = numa_mem_id();
page = __alloc_pages_nodemask(gfp_mask, order, nid, nmask);
if (page)
__count_vm_event(HTLB_BUDDY_PGALLOC);
else
__count_vm_event(HTLB_BUDDY_PGALLOC_FAIL);
return page;
}
/*
* Common helper to allocate a fresh hugetlb page. All specific allocators
* should use this function to get new hugetlb pages
*/
static struct page *alloc_fresh_huge_page(struct hstate *h,
gfp_t gfp_mask, int nid, nodemask_t *nmask)
{
struct page *page;
if (hstate_is_gigantic(h))
page = alloc_gigantic_page(h, gfp_mask, nid, nmask);
else
page = alloc_buddy_huge_page(h, gfp_mask,
nid, nmask);
if (!page)
return NULL;
if (hstate_is_gigantic(h))
prep_compound_gigantic_page(page, huge_page_order(h));
prep_new_huge_page(h, page, page_to_nid(page));
return page;
}
/*
* Allocates a fresh page to the hugetlb allocator pool in the node interleaved
* manner.
*/
static int alloc_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
{
struct page *page;
int nr_nodes, node;
gfp_t gfp_mask = htlb_alloc_mask(h) | __GFP_THISNODE;
for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
page = alloc_fresh_huge_page(h, gfp_mask, node, nodes_allowed);
if (page)
break;
}
if (!page)
return 0;
put_page(page); /* free it into the hugepage allocator */
return 1;
}
/*
* Free huge page from pool from next node to free.
* Attempt to keep persistent huge pages more or less
* balanced over allowed nodes.
* Called with hugetlb_lock locked.
*/
static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
bool acct_surplus)
{
int nr_nodes, node;
int ret = 0;
for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
/*
* If we're returning unused surplus pages, only examine
* nodes with surplus pages.
*/
if ((!acct_surplus || h->surplus_huge_pages_node[node]) &&
!list_empty(&h->hugepage_freelists[node])) {
struct page *page =
list_entry(h->hugepage_freelists[node].next,
struct page, lru);
list_del(&page->lru);
h->free_huge_pages--;
h->free_huge_pages_node[node]--;
if (acct_surplus) {
h->surplus_huge_pages--;
h->surplus_huge_pages_node[node]--;
}
update_and_free_page(h, page);
ret = 1;
break;
}
}
return ret;
}
/*
* Dissolve a given free hugepage into free buddy pages. This function does
* nothing for in-use (including surplus) hugepages. Returns -EBUSY if the
* number of free hugepages would be reduced below the number of reserved
* hugepages.
*/
int dissolve_free_huge_page(struct page *page)
{
int rc = 0;
spin_lock(&hugetlb_lock);
if (PageHuge(page) && !page_count(page)) {
struct page *head = compound_head(page);
struct hstate *h = page_hstate(head);
int nid = page_to_nid(head);
if (h->free_huge_pages - h->resv_huge_pages == 0) {
rc = -EBUSY;
goto out;
}
/*
* Move PageHWPoison flag from head page to the raw error page,
* which makes any subpages rather than the error page reusable.
*/
if (PageHWPoison(head) && page != head) {
SetPageHWPoison(page);
ClearPageHWPoison(head);
}
list_del(&head->lru);
h->free_huge_pages--;
h->free_huge_pages_node[nid]--;
h->max_huge_pages--;
update_and_free_page(h, head);
}
out:
spin_unlock(&hugetlb_lock);
return rc;
}
/*
* Dissolve free hugepages in a given pfn range. Used by memory hotplug to
* make specified memory blocks removable from the system.
* Note that this will dissolve a free gigantic hugepage completely, if any
* part of it lies within the given range.
* Also note that if dissolve_free_huge_page() returns with an error, all
* free hugepages that were dissolved before that error are lost.
*/
int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn)
{
unsigned long pfn;
struct page *page;
int rc = 0;
if (!hugepages_supported())
return rc;
for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) {
page = pfn_to_page(pfn);
if (PageHuge(page) && !page_count(page)) {
rc = dissolve_free_huge_page(page);
if (rc)
break;
}
}
return rc;
}
/*
* Allocates a fresh surplus page from the page allocator.
*/
static struct page *alloc_surplus_huge_page(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nmask)
{
struct page *page = NULL;
if (hstate_is_gigantic(h))
return NULL;
spin_lock(&hugetlb_lock);
if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages)
goto out_unlock;
spin_unlock(&hugetlb_lock);
page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask);
if (!page)
return NULL;
spin_lock(&hugetlb_lock);
/*
* We could have raced with the pool size change.
* Double check that and simply deallocate the new page
* if we would end up overcommiting the surpluses. Abuse
* temporary page to workaround the nasty free_huge_page
* codeflow
*/
if (h->surplus_huge_pages >= h->nr_overcommit_huge_pages) {
SetPageHugeTemporary(page);
put_page(page);
page = NULL;
} else {
h->surplus_huge_pages++;
h->nr_huge_pages_node[page_to_nid(page)]++;
}
out_unlock:
spin_unlock(&hugetlb_lock);
return page;
}
static struct page *alloc_migrate_huge_page(struct hstate *h, gfp_t gfp_mask,
int nid, nodemask_t *nmask)
{
struct page *page;
if (hstate_is_gigantic(h))
return NULL;
page = alloc_fresh_huge_page(h, gfp_mask, nid, nmask);
if (!page)
return NULL;
/*
* We do not account these pages as surplus because they are only
* temporary and will be released properly on the last reference
*/
SetPageHugeTemporary(page);
return page;
}
/*
* Use the VMA's mpolicy to allocate a huge page from the buddy.
*/
static
struct page *alloc_buddy_huge_page_with_mpol(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
struct page *page;
struct mempolicy *mpol;
gfp_t gfp_mask = htlb_alloc_mask(h);
int nid;
nodemask_t *nodemask;
nid = huge_node(vma, addr, gfp_mask, &mpol, &nodemask);
page = alloc_surplus_huge_page(h, gfp_mask, nid, nodemask);
mpol_cond_put(mpol);
return page;
}
/* page migration callback function */
struct page *alloc_huge_page_node(struct hstate *h, int nid)
{
gfp_t gfp_mask = htlb_alloc_mask(h);
struct page *page = NULL;
if (nid != NUMA_NO_NODE)
gfp_mask |= __GFP_THISNODE;
spin_lock(&hugetlb_lock);
if (h->free_huge_pages - h->resv_huge_pages > 0)
page = dequeue_huge_page_nodemask(h, gfp_mask, nid, NULL);
spin_unlock(&hugetlb_lock);
if (!page)
page = alloc_migrate_huge_page(h, gfp_mask, nid, NULL);
return page;
}
/* page migration callback function */
struct page *alloc_huge_page_nodemask(struct hstate *h, int preferred_nid,
nodemask_t *nmask)
{
gfp_t gfp_mask = htlb_alloc_mask(h);
spin_lock(&hugetlb_lock);
if (h->free_huge_pages - h->resv_huge_pages > 0) {
struct page *page;
page = dequeue_huge_page_nodemask(h, gfp_mask, preferred_nid, nmask);
if (page) {
spin_unlock(&hugetlb_lock);
return page;
}
}
spin_unlock(&hugetlb_lock);
return alloc_migrate_huge_page(h, gfp_mask, preferred_nid, nmask);
}
/* mempolicy aware migration callback */
struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
unsigned long address)
{
struct mempolicy *mpol;
nodemask_t *nodemask;
struct page *page;
gfp_t gfp_mask;
int node;
gfp_mask = htlb_alloc_mask(h);
node = huge_node(vma, address, gfp_mask, &mpol, &nodemask);
page = alloc_huge_page_nodemask(h, node, nodemask);
mpol_cond_put(mpol);
return page;
}
/*
* Increase the hugetlb pool such that it can accommodate a reservation
* of size '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;
bool alloc_ok = true;
needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
if (needed <= 0) {
h->resv_huge_pages += delta;
return 0;
}
allocated = 0;
INIT_LIST_HEAD(&surplus_list);
ret = -ENOMEM;
retry:
spin_unlock(&hugetlb_lock);
for (i = 0; i < needed; i++) {
page = alloc_surplus_huge_page(h, htlb_alloc_mask(h),
NUMA_NO_NODE, NULL);
if (!page) {
alloc_ok = false;
break;
}
list_add(&page->lru, &surplus_list);
cond_resched();
}
allocated += i;
/*
* 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 = (h->resv_huge_pages + delta) -
(h->free_huge_pages + allocated);
if (needed > 0) {
if (alloc_ok)
goto retry;
/*
* We were not able to allocate enough pages to
* satisfy the entire reservation so we free what
* we've allocated so far.
*/
goto free;
}
/*
* The surplus_list now contains _at_least_ the number of extra pages
* needed to accommodate the reservation. Add the appropriate number
* of pages to the hugetlb pool and free the extras back to the buddy
* allocator. Commit the entire reservation here to prevent another
* process from stealing the pages as they are added to the pool but
* before they are reserved.
*/
needed += allocated;
h->resv_huge_pages += delta;
ret = 0;
/* Free the needed pages to the hugetlb pool */
list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
if ((--needed) < 0)
break;
/*
* This page is now managed by the hugetlb allocator and has
* no users -- drop the buddy allocator's reference.
*/
put_page_testzero(page);
VM_BUG_ON_PAGE(page_count(page), page);
enqueue_huge_page(h, page);
}
free:
spin_unlock(&hugetlb_lock);
/* Free unnecessary surplus pages to the buddy allocator */
list_for_each_entry_safe(page, tmp, &surplus_list, lru)
put_page(page);
spin_lock(&hugetlb_lock);
return ret;
}
/*
* This routine has two main purposes:
* 1) Decrement the reservation count (resv_huge_pages) by the value passed
* in unused_resv_pages. This corresponds to the prior adjustments made
* to the associated reservation map.
* 2) Free any unused surplus pages that may have been allocated to satisfy
* the reservation. As many as unused_resv_pages may be freed.
*
* Called with hugetlb_lock held. However, the lock could be dropped (and
* reacquired) during calls to cond_resched_lock. Whenever dropping the lock,
* we must make sure nobody else can claim pages we are in the process of
* freeing. Do this by ensuring resv_huge_page always is greater than the
* number of huge pages we plan to free when dropping the lock.
*/
static void return_unused_surplus_pages(struct hstate *h,
unsigned long unused_resv_pages)
{
unsigned long nr_pages;
/* Cannot return gigantic pages currently */
if (hstate_is_gigantic(h))
goto out;
/*
* Part (or even all) of the reservation could have been backed
* by pre-allocated pages. Only free surplus pages.
*/
nr_pages = min(unused_resv_pages, h->surplus_huge_pages);
/*
* We want to release as many surplus pages as possible, spread
* evenly across all nodes with memory. Iterate across these nodes
* until we can no longer free unreserved surplus pages. This occurs
* when the nodes with surplus pages have no free pages.
* free_pool_huge_page() will balance the the freed pages across the
* on-line nodes with memory and will handle the hstate accounting.
*
* Note that we decrement resv_huge_pages as we free the pages. If
* we drop the lock, resv_huge_pages will still be sufficiently large
* to cover subsequent pages we may free.
*/
while (nr_pages--) {
h->resv_huge_pages--;
unused_resv_pages--;
if (!free_pool_huge_page(h, &node_states[N_MEMORY], 1))
goto out;
cond_resched_lock(&hugetlb_lock);
}
out:
/* Fully uncommit the reservation */
h->resv_huge_pages -= unused_resv_pages;
}
/*
* vma_needs_reservation, vma_commit_reservation and vma_end_reservation
* are used by the huge page allocation routines to manage reservations.
*
* vma_needs_reservation is called to determine if the huge page at addr
* within the vma has an associated reservation. If a reservation is
* needed, the value 1 is returned. The caller is then responsible for
* managing the global reservation and subpool usage counts. After
* the huge page has been allocated, vma_commit_reservation is called
* to add the page to the reservation map. If the page allocation fails,
* the reservation must be ended instead of committed. vma_end_reservation
* is called in such cases.
*
* In the normal case, vma_commit_reservation returns the same value
* as the preceding vma_needs_reservation call. The only time this
* is not the case is if a reserve map was changed between calls. It
* is the responsibility of the caller to notice the difference and
* take appropriate action.
*
* vma_add_reservation is used in error paths where a reservation must
* be restored when a newly allocated huge page must be freed. It is
* to be called after calling vma_needs_reservation to determine if a
* reservation exists.
*/
enum vma_resv_mode {
VMA_NEEDS_RESV,
VMA_COMMIT_RESV,
VMA_END_RESV,
VMA_ADD_RESV,
};
static long __vma_reservation_common(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr,
enum vma_resv_mode mode)
{
struct resv_map *resv;
pgoff_t idx;
long ret;
resv = vma_resv_map(vma);
if (!resv)
return 1;
idx = vma_hugecache_offset(h, vma, addr);
switch (mode) {
case VMA_NEEDS_RESV:
ret = region_chg(resv, idx, idx + 1);
break;
case VMA_COMMIT_RESV:
ret = region_add(resv, idx, idx + 1);
break;
case VMA_END_RESV:
region_abort(resv, idx, idx + 1);
ret = 0;
break;
case VMA_ADD_RESV:
if (vma->vm_flags & VM_MAYSHARE)
ret = region_add(resv, idx, idx + 1);
else {
region_abort(resv, idx, idx + 1);
ret = region_del(resv, idx, idx + 1);
}
break;
default:
BUG();
}
if (vma->vm_flags & VM_MAYSHARE)
return ret;
else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && ret >= 0) {
/*
* In most cases, reserves always exist for private mappings.
* However, a file associated with mapping could have been
* hole punched or truncated after reserves were consumed.
* As subsequent fault on such a range will not use reserves.
* Subtle - The reserve map for private mappings has the
* opposite meaning than that of shared mappings. If NO
* entry is in the reserve map, it means a reservation exists.
* If an entry exists in the reserve map, it means the
* reservation has already been consumed. As a result, the
* return value of this routine is the opposite of the
* value returned from reserve map manipulation routines above.
*/
if (ret)
return 0;
else
return 1;
}
else
return ret < 0 ? ret : 0;
}
static long vma_needs_reservation(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
return __vma_reservation_common(h, vma, addr, VMA_NEEDS_RESV);
}
static long vma_commit_reservation(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
return __vma_reservation_common(h, vma, addr, VMA_COMMIT_RESV);
}
static void vma_end_reservation(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
(void)__vma_reservation_common(h, vma, addr, VMA_END_RESV);
}
static long vma_add_reservation(struct hstate *h,
struct vm_area_struct *vma, unsigned long addr)
{
return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV);
}
/*
* This routine is called to restore a reservation on error paths. In the
* specific error paths, a huge page was allocated (via alloc_huge_page)
* and is about to be freed. If a reservation for the page existed,
* alloc_huge_page would have consumed the reservation and set PagePrivate
* in the newly allocated page. When the page is freed via free_huge_page,
* the global reservation count will be incremented if PagePrivate is set.
* However, free_huge_page can not adjust the reserve map. Adjust the
* reserve map here to be consistent with global reserve count adjustments
* to be made by free_huge_page.
*/
static void restore_reserve_on_error(struct hstate *h,
struct vm_area_struct *vma, unsigned long address,
struct page *page)
{
if (unlikely(PagePrivate(page))) {
long rc = vma_needs_reservation(h, vma, address);
if (unlikely(rc < 0)) {
/*
* Rare out of memory condition in reserve map
* manipulation. Clear PagePrivate so that
* global reserve count will not be incremented
* by free_huge_page. This will make it appear
* as though the reservation for this page was
* consumed. This may prevent the task from
* faulting in the page at a later time. This
* is better than inconsistent global huge page
* accounting of reserve counts.
*/
ClearPagePrivate(page);
} else if (rc) {
rc = vma_add_reservation(h, vma, address);
if (unlikely(rc < 0))
/*
* See above comment about rare out of
* memory condition.
*/
ClearPagePrivate(page);
} else
vma_end_reservation(h, vma, address);
}
}
struct page *alloc_huge_page(struct vm_area_struct *vma,
unsigned long addr, int avoid_reserve)
{
struct hugepage_subpool *spool = subpool_vma(vma);
struct hstate *h = hstate_vma(vma);
struct page *page;
long map_chg, map_commit;
long gbl_chg;
int ret, idx;
struct hugetlb_cgroup *h_cg;
idx = hstate_index(h);
/*
* Examine the region/reserve map to determine if the process
* has a reservation for the page to be allocated. A return
* code of zero indicates a reservation exists (no change).
*/
map_chg = gbl_chg = vma_needs_reservation(h, vma, addr);
if (map_chg < 0)
return ERR_PTR(-ENOMEM);
/*
* Processes that did not create the mapping will have no
* reserves as indicated by the region/reserve map. Check
* that the allocation will not exceed the subpool limit.
* Allocations for MAP_NORESERVE mappings also need to be
* checked against any subpool limit.
*/
if (map_chg || avoid_reserve) {
gbl_chg = hugepage_subpool_get_pages(spool, 1);
if (gbl_chg < 0) {
vma_end_reservation(h, vma, addr);
return ERR_PTR(-ENOSPC);
}
/*
* Even though there was no reservation in the region/reserve
* map, there could be reservations associated with the
* subpool that can be used. This would be indicated if the
* return value of hugepage_subpool_get_pages() is zero.
* However, if avoid_reserve is specified we still avoid even
* the subpool reservations.
*/
if (avoid_reserve)
gbl_chg = 1;
}
ret = hugetlb_cgroup_charge_cgroup(idx, pages_per_huge_page(h), &h_cg);
if (ret)
goto out_subpool_put;
spin_lock(&hugetlb_lock);
/*
* glb_chg is passed to indicate whether or not a page must be taken
* from the global free pool (global change). gbl_chg == 0 indicates
* a reservation exists for the allocation.
*/
page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve, gbl_chg);
if (!page) {
spin_unlock(&hugetlb_lock);
page = alloc_buddy_huge_page_with_mpol(h, vma, addr);
if (!page)
goto out_uncharge_cgroup;
if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) {
SetPagePrivate(page);
h->resv_huge_pages--;
}
spin_lock(&hugetlb_lock);
list_move(&page->lru, &h->hugepage_activelist);
/* Fall through */
}
hugetlb_cgroup_commit_charge(idx, pages_per_huge_page(h), h_cg, page);
spin_unlock(&hugetlb_lock);
set_page_private(page, (unsigned long)spool);
map_commit = vma_commit_reservation(h, vma, addr);
if (unlikely(map_chg > map_commit)) {
/*
* The page was added to the reservation map between
* vma_needs_reservation and vma_commit_reservation.
* This indicates a race with hugetlb_reserve_pages.
* Adjust for the subpool count incremented above AND
* in hugetlb_reserve_pages for the same page. Also,
* the reservation count added in hugetlb_reserve_pages
* no longer applies.
*/
long rsv_adjust;
rsv_adjust = hugepage_subpool_put_pages(spool, 1);
hugetlb_acct_memory(h, -rsv_adjust);
}
return page;
out_uncharge_cgroup:
hugetlb_cgroup_uncharge_cgroup(idx, pages_per_huge_page(h), h_cg);
out_subpool_put:
if (map_chg || avoid_reserve)
hugepage_subpool_put_pages(spool, 1);
vma_end_reservation(h, vma, addr);
return ERR_PTR(-ENOSPC);
}
int alloc_bootmem_huge_page(struct hstate *h)
__attribute__ ((weak, alias("__alloc_bootmem_huge_page")));
int __alloc_bootmem_huge_page(struct hstate *h)
{
struct huge_bootmem_page *m;
int nr_nodes, node;
for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) {
void *addr;
addr = memblock_virt_alloc_try_nid_nopanic(
huge_page_size(h), huge_page_size(h),
0, BOOTMEM_ALLOC_ACCESSIBLE, node);
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;
goto found;
}
}
return 0;
found:
BUG_ON(!IS_ALIGNED(virt_to_phys(m), huge_page_size(h)));
/* 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 void __init prep_compound_huge_page(struct page *page,
unsigned int order)
{
if (unlikely(order > (MAX_ORDER - 1)))
prep_compound_gigantic_page(page, order);
else
prep_compound_page(page, order);
}
/* Put bootmem huge pages into the standard lists after mem_map is up */
static void __init gather_bootmem_prealloc(void)
{
struct huge_bootmem_page *m;
list_for_each_entry(m, &huge_boot_pages, list) {
struct hstate *h = m->hstate;
struct page *page;
#ifdef CONFIG_HIGHMEM
page = pfn_to_page(m->phys >> PAGE_SHIFT);
memblock_free_late(__pa(m),
sizeof(struct huge_bootmem_page));
#else
page = virt_to_page(m);
#endif
WARN_ON(page_count(page) != 1);
prep_compound_huge_page(page, h->order);
WARN_ON(PageReserved(page));
prep_new_huge_page(h, page, page_to_nid(page));
put_page(page); /* free it into the hugepage allocator */
/*
* If we had gigantic hugepages allocated at boot time, we need
* to restore the 'stolen' pages to totalram_pages in order to
* fix confusing memory reports from free(1) and another
* side-effects, like CommitLimit going negative.
*/
if (hstate_is_gigantic(h))
adjust_managed_page_count(page, 1 << h->order);
}
}
static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
{
unsigned long i;
for (i = 0; i < h->max_huge_pages; ++i) {
if (hstate_is_gigantic(h)) {
if (!alloc_bootmem_huge_page(h))
break;
} else if (!alloc_pool_huge_page(h,
&node_states[N_MEMORY]))
break;
cond_resched();
}
if (i < h->max_huge_pages) {
char buf[32];
string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
pr_warn("HugeTLB: allocating %lu of page size %s failed. Only allocated %lu hugepages.\n",
h->max_huge_pages, buf, i);
h->max_huge_pages = i;
}
}
static void __init hugetlb_init_hstates(void)
{
struct hstate *h;
for_each_hstate(h) {
if (minimum_order > huge_page_order(h))
minimum_order = huge_page_order(h);
/* oversize hugepages were init'ed in early boot */
if (!hstate_is_gigantic(h))
hugetlb_hstate_alloc_pages(h);
}
VM_BUG_ON(minimum_order == UINT_MAX);
}
static void __init report_hugepages(void)
{
struct hstate *h;
for_each_hstate(h) {
char buf[32];
string_get_size(huge_page_size(h), 1, STRING_UNITS_2, buf, 32);
pr_info("HugeTLB registered %s page size, pre-allocated %ld pages\n",
buf, h->free_huge_pages);
}
}
#ifdef CONFIG_HIGHMEM
static void try_to_free_low(struct hstate *h, unsigned long count,
nodemask_t *nodes_allowed)
{
int i;
if (hstate_is_gigantic(h))
return;
for_each_node_mask(i, *nodes_allowed) {
struct page *page, *next;
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(h, page);
h->free_huge_pages--;
h->free_huge_pages_node[page_to_nid(page)]--;
}
}
}
#else
static inline void try_to_free_low(struct hstate *h, unsigned long count,
nodemask_t *nodes_allowed)
{
}
#endif
/*
* 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(struct hstate *h, nodemask_t *nodes_allowed,
int delta)
{
int nr_nodes, node;
VM_BUG_ON(delta != -1 && delta != 1);
if (delta < 0) {
for_each_node_mask_to_alloc(h, nr_nodes, node, nodes_allowed) {
if (h->surplus_huge_pages_node[node])
goto found;
}
} else {
for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
if (h->surplus_huge_pages_node[node] <
h->nr_huge_pages_node[node])
goto found;
}
}
return 0;
found:
h->surplus_huge_pages += delta;
h->surplus_huge_pages_node[node] += delta;
return 1;
}
#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,
nodemask_t *nodes_allowed)
{
unsigned long min_count, ret;
if (hstate_is_gigantic(h) && !gigantic_page_supported())
return h->max_huge_pages;
/*
* 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_surplus_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 (h->surplus_huge_pages && count > persistent_huge_pages(h)) {
if (!adjust_pool_surplus(h, nodes_allowed, -1))
break;
}
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);
/* yield cpu to avoid soft lockup */
cond_resched();
ret = alloc_pool_huge_page(h, nodes_allowed);
spin_lock(&hugetlb_lock);
if (!ret)
goto out;
/* Bail for signals. Probably ctrl-c from user */
if (signal_pending(current))
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_surplus_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 = h->resv_huge_pages + h->nr_huge_pages - h->free_huge_pages;
min_count = max(count, min_count);
try_to_free_low(h, min_count, nodes_allowed);
while (min_count < persistent_huge_pages(h)) {
if (!free_pool_huge_page(h, nodes_allowed, 0))
break;
cond_resched_lock(&hugetlb_lock);
}
while (count < persistent_huge_pages(h)) {
if (!adjust_pool_surplus(h, nodes_allowed, 1))
break;
}
out:
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_node_hstate(struct kobject *kobj, int *nidp);
static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp)
{
int i;
for (i = 0; i < HUGE_MAX_HSTATE; i++)
if (hstate_kobjs[i] == kobj) {
if (nidp)
*nidp = NUMA_NO_NODE;
return &hstates[i];
}
return kobj_to_node_hstate(kobj, nidp);
}
static ssize_t nr_hugepages_show_common(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct hstate *h;
unsigned long nr_huge_pages;
int nid;
h = kobj_to_hstate(kobj, &nid);
if (nid == NUMA_NO_NODE)
nr_huge_pages = h->nr_huge_pages;
else
nr_huge_pages = h->nr_huge_pages_node[nid];
return sprintf(buf, "%lu\n", nr_huge_pages);
}
static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
struct hstate *h, int nid,
unsigned long count, size_t len)
{
int err;
NODEMASK_ALLOC(nodemask_t, nodes_allowed, GFP_KERNEL | __GFP_NORETRY);
if (hstate_is_gigantic(h) && !gigantic_page_supported()) {
err = -EINVAL;
goto out;
}
if (nid == NUMA_NO_NODE) {
/*
* global hstate attribute
*/
if (!(obey_mempolicy &&
init_nodemask_of_mempolicy(nodes_allowed))) {
NODEMASK_FREE(nodes_allowed);
nodes_allowed = &node_states[N_MEMORY];
}
} else if (nodes_allowed) {
/*
* per node hstate attribute: adjust count to global,
* but restrict alloc/free to the specified node.
*/
count += h->nr_huge_pages - h->nr_huge_pages_node[nid];
init_nodemask_of_node(nodes_allowed, nid);
} else
nodes_allowed = &node_states[N_MEMORY];
h->max_huge_pages = set_max_huge_pages(h, count, nodes_allowed);
if (nodes_allowed != &node_states[N_MEMORY])
NODEMASK_FREE(nodes_allowed);
return len;
out:
NODEMASK_FREE(nodes_allowed);
return err;
}
static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
struct kobject *kobj, const char *buf,
size_t len)
{
struct hstate *h;
unsigned long count;
int nid;
int err;
err = kstrtoul(buf, 10, &count);
if (err)
return err;
h = kobj_to_hstate(kobj, &nid);
return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len);
}
static ssize_t nr_hugepages_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return nr_hugepages_show_common(kobj, attr, buf);
}
static ssize_t nr_hugepages_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf, size_t len)
{
return nr_hugepages_store_common(false, kobj, buf, len);
}
HSTATE_ATTR(nr_hugepages);
#ifdef CONFIG_NUMA
/*
* hstate attribute for optionally mempolicy-based constraint on persistent
* huge page alloc/free.
*/
static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
return nr_hugepages_show_common(kobj, attr, buf);
}
static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj,
struct kobj_attribute *attr, const char *buf, size_t len)
{
return nr_hugepages_store_common(true, kobj, buf, len);
}
HSTATE_ATTR(nr_hugepages_mempolicy);
#endif
static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
struct hstate *h = kobj_to_hstate(kobj, NULL);
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, NULL);
if (hstate_is_gigantic(h))
return -EINVAL;
err = kstrtoul(buf, 10, &input);
if (err)
return err;
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;
unsigned long free_huge_pages;
int nid;
h = kobj_to_hstate(kobj, &nid);
if (nid == NUMA_NO_NODE)
free_huge_pages = h->free_huge_pages;
else
free_huge_pages = h->free_huge_pages_node[nid];
return sprintf(buf, "%lu\n", 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, NULL);
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;
unsigned long surplus_huge_pages;
int nid;
h = kobj_to_hstate(kobj, &nid);
if (nid == NUMA_NO_NODE)
surplus_huge_pages = h->surplus_huge_pages;
else
surplus_huge_pages = h->surplus_huge_pages_node[nid];
return sprintf(buf, "%lu\n", 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,
#ifdef CONFIG_NUMA
&nr_hugepages_mempolicy_attr.attr,
#endif
NULL,
};
static const struct attribute_group hstate_attr_group = {
.attrs = hstate_attrs,
};
static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
struct kobject **hstate_kobjs,
const struct attribute_group *hstate_attr_group)
{
int retval;
int hi = hstate_index(h);
hstate_kobjs[hi] = kobject_create_and_add(h->name, parent);
if (!hstate_kobjs[hi])
return -ENOMEM;
retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group);
if (retval)
kobject_put(hstate_kobjs[hi]);
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, hugepages_kobj,
hstate_kobjs, &hstate_attr_group);
if (err)
pr_err("Hugetlb: Unable to add hstate %s", h->name);
}
}
#ifdef CONFIG_NUMA
/*
* node_hstate/s - associate per node hstate attributes, via their kobjects,
* with node devices in node_devices[] using a parallel array. The array
* index of a node device or _hstate == node id.
* This is here to avoid any static dependency of the node device driver, in
* the base kernel, on the hugetlb module.
*/
struct node_hstate {
struct kobject *hugepages_kobj;
struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];
};
static struct node_hstate node_hstates[MAX_NUMNODES];
/*
* A subset of global hstate attributes for node devices
*/
static struct attribute *per_node_hstate_attrs[] = {
&nr_hugepages_attr.attr,
&free_hugepages_attr.attr,
&surplus_hugepages_attr.attr,
NULL,
};
static const struct attribute_group per_node_hstate_attr_group = {
.attrs = per_node_hstate_attrs,
};
/*
* kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj.
* Returns node id via non-NULL nidp.
*/
static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
{
int nid;
for (nid = 0; nid < nr_node_ids; nid++) {
struct node_hstate *nhs = &node_hstates[nid];
int i;
for (i = 0; i < HUGE_MAX_HSTATE; i++)
if (nhs->hstate_kobjs[i] == kobj) {
if (nidp)
*nidp = nid;
return &hstates[i];
}
}
BUG();
return NULL;
}
/*
* Unregister hstate attributes from a single node device.
* No-op if no hstate attributes attached.
*/
static void hugetlb_unregister_node(struct node *node)
{
struct hstate *h;
struct node_hstate *nhs = &node_hstates[node->dev.id];
if (!nhs->hugepages_kobj)
return; /* no hstate attributes */
for_each_hstate(h) {
int idx = hstate_index(h);
if (nhs->hstate_kobjs[idx]) {
kobject_put(nhs->hstate_kobjs[idx]);
nhs->hstate_kobjs[idx] = NULL;
}
}
kobject_put(nhs->hugepages_kobj);
nhs->hugepages_kobj = NULL;
}
/*
* Register hstate attributes for a single node device.
* No-op if attributes already registered.
*/
static void hugetlb_register_node(struct node *node)
{
struct hstate *h;
struct node_hstate *nhs = &node_hstates[node->dev.id];
int err;
if (nhs->hugepages_kobj)
return; /* already allocated */
nhs->hugepages_kobj = kobject_create_and_add("hugepages",
&node->dev.kobj);
if (!nhs->hugepages_kobj)
return;
for_each_hstate(h) {
err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj,
nhs->hstate_kobjs,
&per_node_hstate_attr_group);
if (err) {
pr_err("Hugetlb: Unable to add hstate %s for node %d\n",
h->name, node->dev.id);
hugetlb_unregister_node(node);
break;
}
}
}
/*
* hugetlb init time: register hstate attributes for all registered node
* devices of nodes that have memory. All on-line nodes should have
* registered their associated device by this time.
*/
static void __init hugetlb_register_all_nodes(void)
{
int nid;
for_each_node_state(nid, N_MEMORY) {
struct node *node = node_devices[nid];
if (node->dev.id == nid)
hugetlb_register_node(node);
}
/*
* Let the node device driver know we're here so it can
* [un]register hstate attributes on node hotplug.
*/
register_hugetlbfs_with_node(hugetlb_register_node,
hugetlb_unregister_node);
}
#else /* !CONFIG_NUMA */
static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
{
BUG();
if (nidp)
*nidp = -1;
return NULL;
}
static void hugetlb_register_all_nodes(void) { }
#endif
static int __init hugetlb_init(void)
{
int i;
if (!hugepages_supported())
return 0;
if (!size_to_hstate(default_hstate_size)) {
if (default_hstate_size != 0) {
pr_err("HugeTLB: unsupported default_hugepagesz %lu. Reverting to %lu\n",
default_hstate_size, HPAGE_SIZE);
}
default_hstate_size = HPAGE_SIZE;
if (!size_to_hstate(default_hstate_size))
hugetlb_add_hstate(HUGETLB_PAGE_ORDER);
}
default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size));
if (default_hstate_max_huge_pages) {
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();
hugetlb_register_all_nodes();
hugetlb_cgroup_file_init();
#ifdef CONFIG_SMP
num_fault_mutexes = roundup_pow_of_two(8 * num_possible_cpus());
#else
num_fault_mutexes = 1;
#endif
hugetlb_fault_mutex_table =
kmalloc(sizeof(struct mutex) * num_fault_mutexes, GFP_KERNEL);
BUG_ON(!hugetlb_fault_mutex_table);
for (i = 0; i < num_fault_mutexes; i++)
mutex_init(&hugetlb_fault_mutex_table[i]);
return 0;
}
subsys_initcall(hugetlb_init);
/* Should be called on processing a hugepagesz=... option */
void __init hugetlb_bad_size(void)
{
parsed_valid_hugepagesz = false;
}
void __init hugetlb_add_hstate(unsigned int order)
{
struct hstate *h;
unsigned long i;
if (size_to_hstate(PAGE_SIZE << order)) {
pr_warn("hugepagesz= specified twice, ignoring\n");
return;
}
BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE);
BUG_ON(order == 0);
h = &hstates[hugetlb_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]);
INIT_LIST_HEAD(&h->hugepage_activelist);
h->next_nid_to_alloc = first_memory_node;
h->next_nid_to_free = first_memory_node;
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;
if (!parsed_valid_hugepagesz) {
pr_warn("hugepages = %s preceded by "
"an unsupported hugepagesz, ignoring\n", s);
parsed_valid_hugepagesz = true;
return 1;
}
/*
* !hugetlb_max_hstate means we haven't parsed a hugepagesz= parameter yet,
* so this hugepages= parameter goes to the "default hstate".
*/
else if (!hugetlb_max_hstate)
mhp = &default_hstate_max_huge_pages;
else
mhp = &parsed_hstate->max_huge_pages;
if (mhp == last_mhp) {
pr_warn("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.