return pmd;
}
-static inline struct list_head *page_deferred_list(struct page *page)
+#ifdef CONFIG_MEMCG
+static inline struct deferred_split *get_deferred_split_queue(struct page *page)
{
- /* ->lru in the tail pages is occupied by compound_head. */
- return &page[2].deferred_list;
+ struct mem_cgroup *memcg = compound_head(page)->mem_cgroup;
+ struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
+
+ if (memcg)
+ return &memcg->deferred_split_queue;
+ else
+ return &pgdat->deferred_split_queue;
+}
+#else
+static inline struct deferred_split *get_deferred_split_queue(struct page *page)
+{
+ struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
+
+ return &pgdat->deferred_split_queue;
}
+#endif
void prep_transhuge_page(struct page *page)
{
* available
* never: never stall for any thp allocation
*/
- static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr)
+ static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
{
const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
- gfp_t this_node = 0;
-
- #ifdef CONFIG_NUMA
- struct mempolicy *pol;
- /*
- * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not
- * specified, to express a general desire to stay on the current
- * node for optimistic allocation attempts. If the defrag mode
- * and/or madvise hint requires the direct reclaim then we prefer
- * to fallback to other node rather than node reclaim because that
- * can lead to excessive reclaim even though there is free memory
- * on other nodes. We expect that NUMA preferences are specified
- * by memory policies.
- */
- pol = get_vma_policy(vma, addr);
- if (pol->mode != MPOL_BIND)
- this_node = __GFP_THISNODE;
- mpol_cond_put(pol);
- #endif
+ /* Always do synchronous compaction */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
+
+ /* Kick kcompactd and fail quickly */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
- return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node;
+ return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+
+ /* Synchronous compaction if madvised, otherwise kick kcompactd */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
- return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
- __GFP_KSWAPD_RECLAIM | this_node);
+ return GFP_TRANSHUGE_LIGHT |
+ (vma_madvised ? __GFP_DIRECT_RECLAIM :
+ __GFP_KSWAPD_RECLAIM);
+
+ /* Only do synchronous compaction if madvised */
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
- return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
- this_node);
- return GFP_TRANSHUGE_LIGHT | this_node;
+ return GFP_TRANSHUGE_LIGHT |
+ (vma_madvised ? __GFP_DIRECT_RECLAIM : 0);
+
+ return GFP_TRANSHUGE_LIGHT;
}
/* Caller must hold page table lock. */
pte_free(vma->vm_mm, pgtable);
return ret;
}
- gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
- page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id());
+ gfp = alloc_hugepage_direct_gfpmask(vma);
+ page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
if (unlikely(!page)) {
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
alloc:
if (__transparent_hugepage_enabled(vma) &&
!transparent_hugepage_debug_cow()) {
- huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
- new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma,
- haddr, numa_node_id());
+ huge_gfp = alloc_hugepage_direct_gfpmask(vma);
+ new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
} else
new_page = NULL;
struct page *head = compound_head(page);
pg_data_t *pgdat = page_pgdat(head);
struct lruvec *lruvec;
+ struct address_space *swap_cache = NULL;
+ unsigned long offset = 0;
int i;
lruvec = mem_cgroup_page_lruvec(head, pgdat);
/* complete memcg works before add pages to LRU */
mem_cgroup_split_huge_fixup(head);
+ if (PageAnon(head) && PageSwapCache(head)) {
+ swp_entry_t entry = { .val = page_private(head) };
+
+ offset = swp_offset(entry);
+ swap_cache = swap_address_space(entry);
+ xa_lock(&swap_cache->i_pages);
+ }
+
for (i = HPAGE_PMD_NR - 1; i >= 1; i--) {
__split_huge_page_tail(head, i, lruvec, list);
/* Some pages can be beyond i_size: drop them from page cache */
if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head))
shmem_uncharge(head->mapping->host, 1);
put_page(head + i);
+ } else if (!PageAnon(page)) {
+ __xa_store(&head->mapping->i_pages, head[i].index,
+ head + i, 0);
+ } else if (swap_cache) {
+ __xa_store(&swap_cache->i_pages, offset + i,
+ head + i, 0);
}
}
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
/* Additional pin to swap cache */
- if (PageSwapCache(head))
+ if (PageSwapCache(head)) {
page_ref_add(head, 2);
- else
+ xa_unlock(&swap_cache->i_pages);
+ } else {
page_ref_inc(head);
+ }
} else {
/* Additional pin to page cache */
page_ref_add(head, 2);
{
struct page *head = compound_head(page);
struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
+ struct deferred_split *ds_queue = get_deferred_split_queue(page);
struct anon_vma *anon_vma = NULL;
struct address_space *mapping = NULL;
int count, mapcount, extra_pins, ret;
}
/* Prevent deferred_split_scan() touching ->_refcount */
- spin_lock(&pgdata->split_queue_lock);
+ spin_lock(&ds_queue->split_queue_lock);
count = page_count(head);
mapcount = total_mapcount(head);
if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
if (!list_empty(page_deferred_list(head))) {
- pgdata->split_queue_len--;
+ ds_queue->split_queue_len--;
list_del(page_deferred_list(head));
}
if (mapping)
__dec_node_page_state(page, NR_SHMEM_THPS);
- spin_unlock(&pgdata->split_queue_lock);
+ spin_unlock(&ds_queue->split_queue_lock);
__split_huge_page(page, list, end, flags);
if (PageSwapCache(head)) {
swp_entry_t entry = { .val = page_private(head) };
dump_page(page, "total_mapcount(head) > 0");
BUG();
}
- spin_unlock(&pgdata->split_queue_lock);
+ spin_unlock(&ds_queue->split_queue_lock);
fail: if (mapping)
xa_unlock(&mapping->i_pages);
spin_unlock_irqrestore(&pgdata->lru_lock, flags);
void free_transhuge_page(struct page *page)
{
- struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
+ struct deferred_split *ds_queue = get_deferred_split_queue(page);
unsigned long flags;
- spin_lock_irqsave(&pgdata->split_queue_lock, flags);
+ spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
if (!list_empty(page_deferred_list(page))) {
- pgdata->split_queue_len--;
+ ds_queue->split_queue_len--;
list_del(page_deferred_list(page));
}
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
+ spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
free_compound_page(page);
}
void deferred_split_huge_page(struct page *page)
{
- struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
+ struct deferred_split *ds_queue = get_deferred_split_queue(page);
+#ifdef CONFIG_MEMCG
+ struct mem_cgroup *memcg = compound_head(page)->mem_cgroup;
+#endif
unsigned long flags;
VM_BUG_ON_PAGE(!PageTransHuge(page), page);
- spin_lock_irqsave(&pgdata->split_queue_lock, flags);
+ /*
+ * The try_to_unmap() in page reclaim path might reach here too,
+ * this may cause a race condition to corrupt deferred split queue.
+ * And, if page reclaim is already handling the same page, it is
+ * unnecessary to handle it again in shrinker.
+ *
+ * Check PageSwapCache to determine if the page is being
+ * handled by page reclaim since THP swap would add the page into
+ * swap cache before calling try_to_unmap().
+ */
+ if (PageSwapCache(page))
+ return;
+
+ spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
if (list_empty(page_deferred_list(page))) {
count_vm_event(THP_DEFERRED_SPLIT_PAGE);
- list_add_tail(page_deferred_list(page), &pgdata->split_queue);
- pgdata->split_queue_len++;
+ list_add_tail(page_deferred_list(page), &ds_queue->split_queue);
+ ds_queue->split_queue_len++;
+#ifdef CONFIG_MEMCG
+ if (memcg)
+ memcg_set_shrinker_bit(memcg, page_to_nid(page),
+ deferred_split_shrinker.id);
+#endif
}
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
+ spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
}
static unsigned long deferred_split_count(struct shrinker *shrink,
struct shrink_control *sc)
{
struct pglist_data *pgdata = NODE_DATA(sc->nid);
- return READ_ONCE(pgdata->split_queue_len);
+ struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
+
+#ifdef CONFIG_MEMCG
+ if (sc->memcg)
+ ds_queue = &sc->memcg->deferred_split_queue;
+#endif
+ return READ_ONCE(ds_queue->split_queue_len);
}
static unsigned long deferred_split_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
struct pglist_data *pgdata = NODE_DATA(sc->nid);
+ struct deferred_split *ds_queue = &pgdata->deferred_split_queue;
unsigned long flags;
LIST_HEAD(list), *pos, *next;
struct page *page;
int split = 0;
- spin_lock_irqsave(&pgdata->split_queue_lock, flags);
+#ifdef CONFIG_MEMCG
+ if (sc->memcg)
+ ds_queue = &sc->memcg->deferred_split_queue;
+#endif
+
+ spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
/* Take pin on all head pages to avoid freeing them under us */
- list_for_each_safe(pos, next, &pgdata->split_queue) {
+ list_for_each_safe(pos, next, &ds_queue->split_queue) {
page = list_entry((void *)pos, struct page, mapping);
page = compound_head(page);
if (get_page_unless_zero(page)) {
} else {
/* We lost race with put_compound_page() */
list_del_init(page_deferred_list(page));
- pgdata->split_queue_len--;
+ ds_queue->split_queue_len--;
}
if (!--sc->nr_to_scan)
break;
}
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
+ spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
list_for_each_safe(pos, next, &list) {
page = list_entry((void *)pos, struct page, mapping);
put_page(page);
}
- spin_lock_irqsave(&pgdata->split_queue_lock, flags);
- list_splice_tail(&list, &pgdata->split_queue);
- spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
+ spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
+ list_splice_tail(&list, &ds_queue->split_queue);
+ spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
/*
* Stop shrinker if we didn't split any page, but the queue is empty.
* This can happen if pages were freed under us.
*/
- if (!split && list_empty(&pgdata->split_queue))
+ if (!split && list_empty(&ds_queue->split_queue))
return SHRINK_STOP;
return split;
}
.count_objects = deferred_split_count,
.scan_objects = deferred_split_scan,
.seeks = DEFAULT_SEEKS,
- .flags = SHRINKER_NUMA_AWARE,
+ .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE |
+ SHRINKER_NONSLAB,
};
#ifdef CONFIG_DEBUG_FS
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/mempolicy.h>
-#include <linux/mm.h>
+#include <linux/pagewalk.h>
#include <linux/highmem.h>
#include <linux/hugetlb.h>
#include <linux/kernel.h>
return 1;
}
+static const struct mm_walk_ops queue_pages_walk_ops = {
+ .hugetlb_entry = queue_pages_hugetlb,
+ .pmd_entry = queue_pages_pte_range,
+ .test_walk = queue_pages_test_walk,
+};
+
/*
* Walk through page tables and collect pages to be migrated.
*
.nmask = nodes,
.prev = NULL,
};
- struct mm_walk queue_pages_walk = {
- .hugetlb_entry = queue_pages_hugetlb,
- .pmd_entry = queue_pages_pte_range,
- .test_walk = queue_pages_test_walk,
- .mm = mm,
- .private = &qp,
- };
- return walk_page_range(start, end, &queue_pages_walk);
+ return walk_page_range(mm, start, end, &queue_pages_walk_ops, &qp);
}
/*
} else if (PageTransHuge(page)) {
struct page *thp;
- thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma,
- address, numa_node_id());
+ thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address,
+ HPAGE_PMD_ORDER);
if (!thp)
return NULL;
prep_transhuge_page(thp);
int err;
unsigned short mode_flags;
+ start = untagged_addr(start);
mode_flags = mode & MPOL_MODE_FLAGS;
mode &= ~MPOL_MODE_FLAGS;
if (mode >= MPOL_MAX)
if (nodes_empty(*new))
goto out_put;
- nodes_and(*new, *new, node_states[N_MEMORY]);
- if (nodes_empty(*new))
- goto out_put;
-
err = security_task_movememory(task);
if (err)
goto out_put;
int uninitialized_var(pval);
nodemask_t nodes;
+ addr = untagged_addr(addr);
+
if (nmask != NULL && maxnode < nr_node_ids)
return -EINVAL;
* freeing by another task. It is the caller's responsibility to free the
* extra reference for shared policies.
*/
- struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+ static struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
unsigned long addr)
{
struct mempolicy *pol = __get_vma_policy(vma, addr);
* @vma: Pointer to VMA or NULL if not available.
* @addr: Virtual Address of the allocation. Must be inside the VMA.
* @node: Which node to prefer for allocation (modulo policy).
+ * @hugepage: for hugepages try only the preferred node if possible
*
* This function allocates a page from the kernel page pool and applies
* a NUMA policy associated with the VMA or the current process.
*/
struct page *
alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
- unsigned long addr, int node)
+ unsigned long addr, int node, bool hugepage)
{
struct mempolicy *pol;
struct page *page;
mpol_cond_put(pol);
page = alloc_page_interleave(gfp, order, nid);
goto out;
+ }
+
+ if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) {
+ int hpage_node = node;
+
+ /*
+ * For hugepage allocation and non-interleave policy which
+ * allows the current node (or other explicitly preferred
+ * node) we only try to allocate from the current/preferred
+ * node and don't fall back to other nodes, as the cost of
+ * remote accesses would likely offset THP benefits.
+ *
+ * If the policy is interleave, or does not allow the current
+ * node in its nodemask, we allocate the standard way.
+ */
+ if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL))
+ hpage_node = pol->v.preferred_node;
+
+ nmask = policy_nodemask(gfp, pol);
+ if (!nmask || node_isset(hpage_node, *nmask)) {
+ mpol_cond_put(pol);
+ page = __alloc_pages_node(hpage_node,
+ gfp | __GFP_THISNODE, order);
+
+ /*
+ * If hugepage allocations are configured to always
+ * synchronous compact or the vma has been madvised
+ * to prefer hugepage backing, retry allowing remote
+ * memory as well.
+ */
+ if (!page && (gfp & __GFP_DIRECT_RECLAIM))
+ page = __alloc_pages_node(hpage_node,
+ gfp | __GFP_NORETRY, order);
+
+ goto out;
+ }
}
nmask = policy_nodemask(gfp, pol);
void free_compound_page(struct page *page)
{
+ mem_cgroup_uncharge(page);
__free_pages_ok(page, compound_order(page));
}
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <=
- RECLAIM_DISTANCE;
+ node_reclaim_distance;
}
#else /* CONFIG_NUMA */
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
if (compaction_failed(compact_result))
goto check_priority;
+ /*
+ * compaction was skipped because there are not enough order-0 pages
+ * to work with, so we retry only if it looks like reclaim can help.
+ */
+ if (compaction_needs_reclaim(compact_result)) {
+ ret = compaction_zonelist_suitable(ac, order, alloc_flags);
+ goto out;
+ }
+
/*
* make sure the compaction wasn't deferred or didn't bail out early
* due to locks contention before we declare that we should give up.
- * But do not retry if the given zonelist is not suitable for
- * compaction.
+ * But the next retry should use a higher priority if allowed, so
+ * we don't just keep bailing out endlessly.
*/
if (compaction_withdrawn(compact_result)) {
- ret = compaction_zonelist_suitable(ac, order, alloc_flags);
- goto out;
+ goto check_priority;
}
/*
if (page)
goto got_pg;
+ if (order >= pageblock_order && (gfp_mask & __GFP_IO)) {
+ /*
+ * If allocating entire pageblock(s) and compaction
+ * failed because all zones are below low watermarks
+ * or is prohibited because it recently failed at this
+ * order, fail immediately.
+ *
+ * Reclaim is
+ * - potentially very expensive because zones are far
+ * below their low watermarks or this is part of very
+ * bursty high order allocations,
+ * - not guaranteed to help because isolate_freepages()
+ * may not iterate over freed pages as part of its
+ * linear scan, and
+ * - unlikely to make entire pageblocks free on its
+ * own.
+ */
+ if (compact_result == COMPACT_SKIPPED ||
+ compact_result == COMPACT_DEFERRED)
+ goto nopage;
+ }
+
/*
* Checks for costly allocations with __GFP_NORETRY, which
* includes THP page fault allocations
}
}
- pr_info("%s initialised, %lu pages in %ums\n", dev_name(pgmap->dev),
+ pr_info("%s initialised %lu pages in %ums\n", __func__,
size, jiffies_to_msecs(jiffies - start));
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static void pgdat_init_split_queue(struct pglist_data *pgdat)
{
- spin_lock_init(&pgdat->split_queue_lock);
- INIT_LIST_HEAD(&pgdat->split_queue);
- pgdat->split_queue_len = 0;
+ struct deferred_split *ds_queue = &pgdat->deferred_split_queue;
+
+ spin_lock_init(&ds_queue->split_queue_lock);
+ INIT_LIST_HEAD(&ds_queue->split_queue);
+ ds_queue->split_queue_len = 0;
}
#else
static void pgdat_init_split_queue(struct pglist_data *pgdat) {}
if (!hugepage_migration_supported(page_hstate(head)))
goto unmovable;
- skip_pages = (1 << compound_order(head)) - (page - head);
+ skip_pages = compound_nr(head) - (page - head);
iter += skip_pages - 1;
continue;
}
#include <linux/khugepaged.h>
#include <linux/hugetlb.h>
#include <linux/frontswap.h>
+#include <linux/fs_parser.h>
#include <asm/tlbflush.h> /* for arch/microblaze update_mmu_cache() */
pgoff_t nr_unswapped; /* how often writepage refused to swap out */
};
+struct shmem_options {
+ unsigned long long blocks;
+ unsigned long long inodes;
+ struct mempolicy *mpol;
+ kuid_t uid;
+ kgid_t gid;
+ umode_t mode;
+ int huge;
+ int seen;
+#define SHMEM_SEEN_BLOCKS 1
+#define SHMEM_SEEN_INODES 2
+#define SHMEM_SEEN_HUGE 4
+};
+
#ifdef CONFIG_TMPFS
static unsigned long shmem_default_max_blocks(void)
{
{
XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page));
unsigned long i = 0;
- unsigned long nr = 1UL << compound_order(page);
+ unsigned long nr = compound_nr(page);
VM_BUG_ON_PAGE(PageTail(page), page);
VM_BUG_ON_PAGE(index != round_down(index, nr), page);
if (xas_error(&xas))
goto unlock;
next:
- xas_store(&xas, page + i);
+ xas_store(&xas, page);
if (++i < nr) {
xas_next(&xas);
goto next;
shmem_pseudo_vma_init(&pvma, info, hindex);
page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN,
- HPAGE_PMD_ORDER, &pvma, 0, numa_node_id());
+ HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true);
shmem_pseudo_vma_destroy(&pvma);
if (page)
prep_transhuge_page(page);
* vm. If we swap it in we mark it dirty since we also free the swap
* entry since a page cannot live in both the swap and page cache.
*
- * fault_mm and fault_type are only supplied by shmem_fault:
+ * vmf and fault_type are only supplied by shmem_fault:
* otherwise they are NULL.
*/
static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
lru_cache_add_anon(page);
spin_lock_irq(&info->lock);
- info->alloced += 1 << compound_order(page);
+ info->alloced += compound_nr(page);
inode->i_blocks += BLOCKS_PER_PAGE << compound_order(page);
shmem_recalc_inode(inode);
spin_unlock_irq(&info->lock);
struct page *head = compound_head(page);
int i;
- for (i = 0; i < (1 << compound_order(head)); i++) {
+ for (i = 0; i < compound_nr(head); i++) {
clear_highpage(head + i);
flush_dcache_page(head + i);
}
* Error recovery.
*/
unacct:
- shmem_inode_unacct_blocks(inode, 1 << compound_order(page));
+ shmem_inode_unacct_blocks(inode, compound_nr(page));
if (PageTransHuge(page)) {
unlock_page(page);
.fh_to_dentry = shmem_fh_to_dentry,
};
-static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
- bool remount)
+enum shmem_param {
+ Opt_gid,
+ Opt_huge,
+ Opt_mode,
+ Opt_mpol,
+ Opt_nr_blocks,
+ Opt_nr_inodes,
+ Opt_size,
+ Opt_uid,
+};
+
+static const struct fs_parameter_spec shmem_param_specs[] = {
+ fsparam_u32 ("gid", Opt_gid),
+ fsparam_enum ("huge", Opt_huge),
+ fsparam_u32oct("mode", Opt_mode),
+ fsparam_string("mpol", Opt_mpol),
+ fsparam_string("nr_blocks", Opt_nr_blocks),
+ fsparam_string("nr_inodes", Opt_nr_inodes),
+ fsparam_string("size", Opt_size),
+ fsparam_u32 ("uid", Opt_uid),
+ {}
+};
+
+static const struct fs_parameter_enum shmem_param_enums[] = {
+ { Opt_huge, "never", SHMEM_HUGE_NEVER },
+ { Opt_huge, "always", SHMEM_HUGE_ALWAYS },
+ { Opt_huge, "within_size", SHMEM_HUGE_WITHIN_SIZE },
+ { Opt_huge, "advise", SHMEM_HUGE_ADVISE },
+ {}
+};
+
+const struct fs_parameter_description shmem_fs_parameters = {
+ .name = "tmpfs",
+ .specs = shmem_param_specs,
+ .enums = shmem_param_enums,
+};
+
+static int shmem_parse_one(struct fs_context *fc, struct fs_parameter *param)
+{
+ struct shmem_options *ctx = fc->fs_private;
+ struct fs_parse_result result;
+ unsigned long long size;
+ char *rest;
+ int opt;
+
+ opt = fs_parse(fc, &shmem_fs_parameters, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case Opt_size:
+ size = memparse(param->string, &rest);
+ if (*rest == '%') {
+ size <<= PAGE_SHIFT;
+ size *= totalram_pages();
+ do_div(size, 100);
+ rest++;
+ }
+ if (*rest)
+ goto bad_value;
+ ctx->blocks = DIV_ROUND_UP(size, PAGE_SIZE);
+ ctx->seen |= SHMEM_SEEN_BLOCKS;
+ break;
+ case Opt_nr_blocks:
+ ctx->blocks = memparse(param->string, &rest);
+ if (*rest)
+ goto bad_value;
+ ctx->seen |= SHMEM_SEEN_BLOCKS;
+ break;
+ case Opt_nr_inodes:
+ ctx->inodes = memparse(param->string, &rest);
+ if (*rest)
+ goto bad_value;
+ ctx->seen |= SHMEM_SEEN_INODES;
+ break;
+ case Opt_mode:
+ ctx->mode = result.uint_32 & 07777;
+ break;
+ case Opt_uid:
+ ctx->uid = make_kuid(current_user_ns(), result.uint_32);
+ if (!uid_valid(ctx->uid))
+ goto bad_value;
+ break;
+ case Opt_gid:
+ ctx->gid = make_kgid(current_user_ns(), result.uint_32);
+ if (!gid_valid(ctx->gid))
+ goto bad_value;
+ break;
+ case Opt_huge:
+ ctx->huge = result.uint_32;
+ if (ctx->huge != SHMEM_HUGE_NEVER &&
+ !(IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE) &&
+ has_transparent_hugepage()))
+ goto unsupported_parameter;
+ ctx->seen |= SHMEM_SEEN_HUGE;
+ break;
+ case Opt_mpol:
+ if (IS_ENABLED(CONFIG_NUMA)) {
+ mpol_put(ctx->mpol);
+ ctx->mpol = NULL;
+ if (mpol_parse_str(param->string, &ctx->mpol))
+ goto bad_value;
+ break;
+ }
+ goto unsupported_parameter;
+ }
+ return 0;
+
+unsupported_parameter:
+ return invalf(fc, "tmpfs: Unsupported parameter '%s'", param->key);
+bad_value:
+ return invalf(fc, "tmpfs: Bad value for '%s'", param->key);
+}
+
+static int shmem_parse_options(struct fs_context *fc, void *data)
{
- char *this_char, *value, *rest;
- struct mempolicy *mpol = NULL;
- uid_t uid;
- gid_t gid;
+ char *options = data;
while (options != NULL) {
- this_char = options;
+ char *this_char = options;
for (;;) {
/*
* NUL-terminate this option: unfortunately,
break;
}
}
- if (!*this_char)
- continue;
- if ((value = strchr(this_char,'=')) != NULL) {
- *value++ = 0;
- } else {
- pr_err("tmpfs: No value for mount option '%s'\n",
- this_char);
- goto error;
- }
-
- if (!strcmp(this_char,"size")) {
- unsigned long long size;
- size = memparse(value,&rest);
- if (*rest == '%') {
- size <<= PAGE_SHIFT;
- size *= totalram_pages();
- do_div(size, 100);
- rest++;
+ if (*this_char) {
+ char *value = strchr(this_char,'=');
+ size_t len = 0;
+ int err;
+
+ if (value) {
+ *value++ = '\0';
+ len = strlen(value);
}
- if (*rest)
- goto bad_val;
- sbinfo->max_blocks =
- DIV_ROUND_UP(size, PAGE_SIZE);
- } else if (!strcmp(this_char,"nr_blocks")) {
- sbinfo->max_blocks = memparse(value, &rest);
- if (*rest)
- goto bad_val;
- } else if (!strcmp(this_char,"nr_inodes")) {
- sbinfo->max_inodes = memparse(value, &rest);
- if (*rest)
- goto bad_val;
- } else if (!strcmp(this_char,"mode")) {
- if (remount)
- continue;
- sbinfo->mode = simple_strtoul(value, &rest, 8) & 07777;
- if (*rest)
- goto bad_val;
- } else if (!strcmp(this_char,"uid")) {
- if (remount)
- continue;
- uid = simple_strtoul(value, &rest, 0);
- if (*rest)
- goto bad_val;
- sbinfo->uid = make_kuid(current_user_ns(), uid);
- if (!uid_valid(sbinfo->uid))
- goto bad_val;
- } else if (!strcmp(this_char,"gid")) {
- if (remount)
- continue;
- gid = simple_strtoul(value, &rest, 0);
- if (*rest)
- goto bad_val;
- sbinfo->gid = make_kgid(current_user_ns(), gid);
- if (!gid_valid(sbinfo->gid))
- goto bad_val;
-#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
- } else if (!strcmp(this_char, "huge")) {
- int huge;
- huge = shmem_parse_huge(value);
- if (huge < 0)
- goto bad_val;
- if (!has_transparent_hugepage() &&
- huge != SHMEM_HUGE_NEVER)
- goto bad_val;
- sbinfo->huge = huge;
-#endif
-#ifdef CONFIG_NUMA
- } else if (!strcmp(this_char,"mpol")) {
- mpol_put(mpol);
- mpol = NULL;
- if (mpol_parse_str(value, &mpol))
- goto bad_val;
-#endif
- } else {
- pr_err("tmpfs: Bad mount option %s\n", this_char);
- goto error;
+ err = vfs_parse_fs_string(fc, this_char, value, len);
+ if (err < 0)
+ return err;
}
}
- sbinfo->mpol = mpol;
return 0;
-
-bad_val:
- pr_err("tmpfs: Bad value '%s' for mount option '%s'\n",
- value, this_char);
-error:
- mpol_put(mpol);
- return 1;
-
}
-static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
+/*
+ * Reconfigure a shmem filesystem.
+ *
+ * Note that we disallow change from limited->unlimited blocks/inodes while any
+ * are in use; but we must separately disallow unlimited->limited, because in
+ * that case we have no record of how much is already in use.
+ */
+static int shmem_reconfigure(struct fs_context *fc)
{
- struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
- struct shmem_sb_info config = *sbinfo;
+ struct shmem_options *ctx = fc->fs_private;
+ struct shmem_sb_info *sbinfo = SHMEM_SB(fc->root->d_sb);
unsigned long inodes;
- int error = -EINVAL;
-
- config.mpol = NULL;
- if (shmem_parse_options(data, &config, true))
- return error;
+ const char *err;
spin_lock(&sbinfo->stat_lock);
inodes = sbinfo->max_inodes - sbinfo->free_inodes;
- if (percpu_counter_compare(&sbinfo->used_blocks, config.max_blocks) > 0)
- goto out;
- if (config.max_inodes < inodes)
- goto out;
- /*
- * Those tests disallow limited->unlimited while any are in use;
- * but we must separately disallow unlimited->limited, because
- * in that case we have no record of how much is already in use.
- */
- if (config.max_blocks && !sbinfo->max_blocks)
- goto out;
- if (config.max_inodes && !sbinfo->max_inodes)
- goto out;
+ if ((ctx->seen & SHMEM_SEEN_BLOCKS) && ctx->blocks) {
+ if (!sbinfo->max_blocks) {
+ err = "Cannot retroactively limit size";
+ goto out;
+ }
+ if (percpu_counter_compare(&sbinfo->used_blocks,
+ ctx->blocks) > 0) {
+ err = "Too small a size for current use";
+ goto out;
+ }
+ }
+ if ((ctx->seen & SHMEM_SEEN_INODES) && ctx->inodes) {
+ if (!sbinfo->max_inodes) {
+ err = "Cannot retroactively limit inodes";
+ goto out;
+ }
+ if (ctx->inodes < inodes) {
+ err = "Too few inodes for current use";
+ goto out;
+ }
+ }
- error = 0;
- sbinfo->huge = config.huge;
- sbinfo->max_blocks = config.max_blocks;
- sbinfo->max_inodes = config.max_inodes;
- sbinfo->free_inodes = config.max_inodes - inodes;
+ if (ctx->seen & SHMEM_SEEN_HUGE)
+ sbinfo->huge = ctx->huge;
+ if (ctx->seen & SHMEM_SEEN_BLOCKS)
+ sbinfo->max_blocks = ctx->blocks;
+ if (ctx->seen & SHMEM_SEEN_INODES) {
+ sbinfo->max_inodes = ctx->inodes;
+ sbinfo->free_inodes = ctx->inodes - inodes;
+ }
/*
* Preserve previous mempolicy unless mpol remount option was specified.
*/
- if (config.mpol) {
+ if (ctx->mpol) {
mpol_put(sbinfo->mpol);
- sbinfo->mpol = config.mpol; /* transfers initial ref */
+ sbinfo->mpol = ctx->mpol; /* transfers initial ref */
+ ctx->mpol = NULL;
}
+ spin_unlock(&sbinfo->stat_lock);
+ return 0;
out:
spin_unlock(&sbinfo->stat_lock);
- return error;
+ return invalf(fc, "tmpfs: %s", err);
}
static int shmem_show_options(struct seq_file *seq, struct dentry *root)
sb->s_fs_info = NULL;
}
-int shmem_fill_super(struct super_block *sb, void *data, int silent)
+static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
{
+ struct shmem_options *ctx = fc->fs_private;
struct inode *inode;
struct shmem_sb_info *sbinfo;
int err = -ENOMEM;
if (!sbinfo)
return -ENOMEM;
- sbinfo->mode = 0777 | S_ISVTX;
- sbinfo->uid = current_fsuid();
- sbinfo->gid = current_fsgid();
sb->s_fs_info = sbinfo;
#ifdef CONFIG_TMPFS
* but the internal instance is left unlimited.
*/
if (!(sb->s_flags & SB_KERNMOUNT)) {
- sbinfo->max_blocks = shmem_default_max_blocks();
- sbinfo->max_inodes = shmem_default_max_inodes();
- if (shmem_parse_options(data, sbinfo, false)) {
- err = -EINVAL;
- goto failed;
- }
+ if (!(ctx->seen & SHMEM_SEEN_BLOCKS))
+ ctx->blocks = shmem_default_max_blocks();
+ if (!(ctx->seen & SHMEM_SEEN_INODES))
+ ctx->inodes = shmem_default_max_inodes();
} else {
sb->s_flags |= SB_NOUSER;
}
#else
sb->s_flags |= SB_NOUSER;
#endif
+ sbinfo->max_blocks = ctx->blocks;
+ sbinfo->free_inodes = sbinfo->max_inodes = ctx->inodes;
+ sbinfo->uid = ctx->uid;
+ sbinfo->gid = ctx->gid;
+ sbinfo->mode = ctx->mode;
+ sbinfo->huge = ctx->huge;
+ sbinfo->mpol = ctx->mpol;
+ ctx->mpol = NULL;
spin_lock_init(&sbinfo->stat_lock);
if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL))
goto failed;
- sbinfo->free_inodes = sbinfo->max_inodes;
spin_lock_init(&sbinfo->shrinklist_lock);
INIT_LIST_HEAD(&sbinfo->shrinklist);
return err;
}
+static int shmem_get_tree(struct fs_context *fc)
+{
+ return get_tree_nodev(fc, shmem_fill_super);
+}
+
+static void shmem_free_fc(struct fs_context *fc)
+{
+ struct shmem_options *ctx = fc->fs_private;
+
+ if (ctx) {
+ mpol_put(ctx->mpol);
+ kfree(ctx);
+ }
+}
+
+static const struct fs_context_operations shmem_fs_context_ops = {
+ .free = shmem_free_fc,
+ .get_tree = shmem_get_tree,
+#ifdef CONFIG_TMPFS
+ .parse_monolithic = shmem_parse_options,
+ .parse_param = shmem_parse_one,
+ .reconfigure = shmem_reconfigure,
+#endif
+};
+
static struct kmem_cache *shmem_inode_cachep;
static struct inode *shmem_alloc_inode(struct super_block *sb)
.destroy_inode = shmem_destroy_inode,
#ifdef CONFIG_TMPFS
.statfs = shmem_statfs,
- .remount_fs = shmem_remount_fs,
.show_options = shmem_show_options,
#endif
.evict_inode = shmem_evict_inode,
#endif
};
-static struct dentry *shmem_mount(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data)
+int shmem_init_fs_context(struct fs_context *fc)
{
- return mount_nodev(fs_type, flags, data, shmem_fill_super);
+ struct shmem_options *ctx;
+
+ ctx = kzalloc(sizeof(struct shmem_options), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ ctx->mode = 0777 | S_ISVTX;
+ ctx->uid = current_fsuid();
+ ctx->gid = current_fsgid();
+
+ fc->fs_private = ctx;
+ fc->ops = &shmem_fs_context_ops;
+ return 0;
}
static struct file_system_type shmem_fs_type = {
.owner = THIS_MODULE,
.name = "tmpfs",
- .mount = shmem_mount,
+ .init_fs_context = shmem_init_fs_context,
+#ifdef CONFIG_TMPFS
+ .parameters = &shmem_fs_parameters,
+#endif
.kill_sb = kill_litter_super,
.fs_flags = FS_USERNS_MOUNT,
};
static struct file_system_type shmem_fs_type = {
.name = "tmpfs",
- .mount = ramfs_mount,
+ .init_fs_context = ramfs_init_fs_context,
+ .parameters = &ramfs_fs_parameters,
.kill_sb = kill_litter_super,
.fs_flags = FS_USERNS_MOUNT,
};
projects / linux-2.6-block.git / commitdiff