summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2015-09-10 18:19:42 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2015-09-10 18:19:42 -0700
commit33e247c7e58d335d70ecb84fd869091e2e4b8dcb (patch)
treee8561e1993dff03f8e56d10a5795fe9d379a3390 /mm
parentd71fc239b6915a8b750e9a447311029ff45b6580 (diff)
parent452e06af1f0149b01201f94264d452cd7a95db7a (diff)
downloadlinux-33e247c7e58d335d70ecb84fd869091e2e4b8dcb.tar.bz2
Merge branch 'akpm' (patches from Andrew)
Merge third patch-bomb from Andrew Morton: - even more of the rest of MM - lib/ updates - checkpatch updates - small changes to a few scruffy filesystems - kmod fixes/cleanups - kexec updates - a dma-mapping cleanup series from hch * emailed patches from Andrew Morton <akpm@linux-foundation.org>: (81 commits) dma-mapping: consolidate dma_set_mask dma-mapping: consolidate dma_supported dma-mapping: cosolidate dma_mapping_error dma-mapping: consolidate dma_{alloc,free}_noncoherent dma-mapping: consolidate dma_{alloc,free}_{attrs,coherent} mm: use vma_is_anonymous() in create_huge_pmd() and wp_huge_pmd() mm: make sure all file VMAs have ->vm_ops set mm, mpx: add "vm_flags_t vm_flags" arg to do_mmap_pgoff() mm: mark most vm_operations_struct const namei: fix warning while make xmldocs caused by namei.c ipc: convert invalid scenarios to use WARN_ON zlib_deflate/deftree: remove bi_reverse() lib/decompress_unlzma: Do a NULL check for pointer lib/decompressors: use real out buf size for gunzip with kernel fs/affs: make root lookup from blkdev logical size sysctl: fix int -> unsigned long assignments in INT_MIN case kexec: export KERNEL_IMAGE_SIZE to vmcoreinfo kexec: align crash_notes allocation to make it be inside one physical page kexec: remove unnecessary test in kimage_alloc_crash_control_pages() kexec: split kexec_load syscall from kexec core code ...
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig12
-rw-r--r--mm/Makefile1
-rw-r--r--mm/debug.c4
-rw-r--r--mm/huge_memory.c12
-rw-r--r--mm/hwpoison-inject.c5
-rw-r--r--mm/kmemleak.c21
-rw-r--r--mm/memcontrol.c76
-rw-r--r--mm/memory-failure.c16
-rw-r--r--mm/memory.c4
-rw-r--r--mm/migrate.c6
-rw-r--r--mm/mmap.c18
-rw-r--r--mm/mmu_notifier.c17
-rw-r--r--mm/nommu.c19
-rw-r--r--mm/page_ext.c4
-rw-r--r--mm/page_idle.c232
-rw-r--r--mm/rmap.c6
-rw-r--r--mm/swap.c3
-rw-r--r--mm/zpool.c33
-rw-r--r--mm/zswap.c688
19 files changed, 934 insertions, 243 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index 3a4070f5ab79..6413d027c0b2 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -649,6 +649,18 @@ config DEFERRED_STRUCT_PAGE_INIT
processes running early in the lifetime of the systemm until kswapd
finishes the initialisation.
+config IDLE_PAGE_TRACKING
+ bool "Enable idle page tracking"
+ depends on SYSFS && MMU
+ select PAGE_EXTENSION if !64BIT
+ help
+ This feature allows to estimate the amount of user pages that have
+ not been touched during a given period of time. This information can
+ be useful to tune memory cgroup limits and/or for job placement
+ within a compute cluster.
+
+ See Documentation/vm/idle_page_tracking.txt for more details.
+
config ZONE_DEVICE
bool "Device memory (pmem, etc...) hotplug support" if EXPERT
default !ZONE_DMA
diff --git a/mm/Makefile b/mm/Makefile
index b424d5e5b6ff..56f8eed73f1a 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -79,3 +79,4 @@ obj-$(CONFIG_MEMORY_BALLOON) += balloon_compaction.o
obj-$(CONFIG_PAGE_EXTENSION) += page_ext.o
obj-$(CONFIG_CMA_DEBUGFS) += cma_debug.o
obj-$(CONFIG_USERFAULTFD) += userfaultfd.o
+obj-$(CONFIG_IDLE_PAGE_TRACKING) += page_idle.o
diff --git a/mm/debug.c b/mm/debug.c
index 76089ddf99ea..6c1b3ea61bfd 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -48,6 +48,10 @@ static const struct trace_print_flags pageflag_names[] = {
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
{1UL << PG_compound_lock, "compound_lock" },
#endif
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && defined(CONFIG_64BIT)
+ {1UL << PG_young, "young" },
+ {1UL << PG_idle, "idle" },
+#endif
};
static void dump_flags(unsigned long flags,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b16279cbd91d..4b06b8db9df2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -25,6 +25,7 @@
#include <linux/migrate.h>
#include <linux/hashtable.h>
#include <linux/userfaultfd_k.h>
+#include <linux/page_idle.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
@@ -1757,6 +1758,11 @@ static void __split_huge_page_refcount(struct page *page,
/* clear PageTail before overwriting first_page */
smp_wmb();
+ if (page_is_young(page))
+ set_page_young(page_tail);
+ if (page_is_idle(page))
+ set_page_idle(page_tail);
+
/*
* __split_huge_page_splitting() already set the
* splitting bit in all pmd that could map this
@@ -2262,7 +2268,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
VM_BUG_ON_PAGE(PageLRU(page), page);
/* If there is no mapped pte young don't collapse the page */
- if (pte_young(pteval) || PageReferenced(page) ||
+ if (pte_young(pteval) ||
+ page_is_young(page) || PageReferenced(page) ||
mmu_notifier_test_young(vma->vm_mm, address))
referenced = true;
}
@@ -2693,7 +2700,8 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
*/
if (page_count(page) != 1 + !!PageSwapCache(page))
goto out_unmap;
- if (pte_young(pteval) || PageReferenced(page) ||
+ if (pte_young(pteval) ||
+ page_is_young(page) || PageReferenced(page) ||
mmu_notifier_test_young(vma->vm_mm, address))
referenced = true;
}
diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c
index aeba0edd6e44..9d26fd9fefe4 100644
--- a/mm/hwpoison-inject.c
+++ b/mm/hwpoison-inject.c
@@ -45,12 +45,9 @@ static int hwpoison_inject(void *data, u64 val)
/*
* do a racy check with elevated page count, to make sure PG_hwpoison
* will only be set for the targeted owner (or on a free page).
- * We temporarily take page lock for try_get_mem_cgroup_from_page().
* memory_failure() will redo the check reliably inside page lock.
*/
- lock_page(hpage);
err = hwpoison_filter(hpage);
- unlock_page(hpage);
if (err)
goto put_out;
@@ -126,7 +123,7 @@ static int pfn_inject_init(void)
if (!dentry)
goto fail;
-#ifdef CONFIG_MEMCG_SWAP
+#ifdef CONFIG_MEMCG
dentry = debugfs_create_u64("corrupt-filter-memcg", 0600,
hwpoison_dir, &hwpoison_filter_memcg);
if (!dentry)
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index f532f6a37b55..77191eccdc6f 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -302,23 +302,14 @@ static void hex_dump_object(struct seq_file *seq,
struct kmemleak_object *object)
{
const u8 *ptr = (const u8 *)object->pointer;
- int i, len, remaining;
- unsigned char linebuf[HEX_ROW_SIZE * 5];
+ size_t len;
/* limit the number of lines to HEX_MAX_LINES */
- remaining = len =
- min(object->size, (size_t)(HEX_MAX_LINES * HEX_ROW_SIZE));
-
- seq_printf(seq, " hex dump (first %d bytes):\n", len);
- for (i = 0; i < len; i += HEX_ROW_SIZE) {
- int linelen = min(remaining, HEX_ROW_SIZE);
-
- remaining -= HEX_ROW_SIZE;
- hex_dump_to_buffer(ptr + i, linelen, HEX_ROW_SIZE,
- HEX_GROUP_SIZE, linebuf, sizeof(linebuf),
- HEX_ASCII);
- seq_printf(seq, " %s\n", linebuf);
- }
+ len = min_t(size_t, object->size, HEX_MAX_LINES * HEX_ROW_SIZE);
+
+ seq_printf(seq, " hex dump (first %zu bytes):\n", len);
+ seq_hex_dump(seq, " ", DUMP_PREFIX_NONE, HEX_ROW_SIZE,
+ HEX_GROUP_SIZE, ptr, len, HEX_ASCII);
}
/*
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 1742a2db89c7..6ddaeba34e09 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -441,6 +441,34 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page)
return &memcg->css;
}
+/**
+ * page_cgroup_ino - return inode number of the memcg a page is charged to
+ * @page: the page
+ *
+ * Look up the closest online ancestor of the memory cgroup @page is charged to
+ * and return its inode number or 0 if @page is not charged to any cgroup. It
+ * is safe to call this function without holding a reference to @page.
+ *
+ * Note, this function is inherently racy, because there is nothing to prevent
+ * the cgroup inode from getting torn down and potentially reallocated a moment
+ * after page_cgroup_ino() returns, so it only should be used by callers that
+ * do not care (such as procfs interfaces).
+ */
+ino_t page_cgroup_ino(struct page *page)
+{
+ struct mem_cgroup *memcg;
+ unsigned long ino = 0;
+
+ rcu_read_lock();
+ memcg = READ_ONCE(page->mem_cgroup);
+ while (memcg && !(memcg->css.flags & CSS_ONLINE))
+ memcg = parent_mem_cgroup(memcg);
+ if (memcg)
+ ino = cgroup_ino(memcg->css.cgroup);
+ rcu_read_unlock();
+ return ino;
+}
+
static struct mem_cgroup_per_zone *
mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page)
{
@@ -2071,40 +2099,6 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
css_put_many(&memcg->css, nr_pages);
}
-/*
- * try_get_mem_cgroup_from_page - look up page's memcg association
- * @page: the page
- *
- * Look up, get a css reference, and return the memcg that owns @page.
- *
- * The page must be locked to prevent racing with swap-in and page
- * cache charges. If coming from an unlocked page table, the caller
- * must ensure the page is on the LRU or this can race with charging.
- */
-struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
-{
- struct mem_cgroup *memcg;
- unsigned short id;
- swp_entry_t ent;
-
- VM_BUG_ON_PAGE(!PageLocked(page), page);
-
- memcg = page->mem_cgroup;
- if (memcg) {
- if (!css_tryget_online(&memcg->css))
- memcg = NULL;
- } else if (PageSwapCache(page)) {
- ent.val = page_private(page);
- id = lookup_swap_cgroup_id(ent);
- rcu_read_lock();
- memcg = mem_cgroup_from_id(id);
- if (memcg && !css_tryget_online(&memcg->css))
- memcg = NULL;
- rcu_read_unlock();
- }
- return memcg;
-}
-
static void lock_page_lru(struct page *page, int *isolated)
{
struct zone *zone = page_zone(page);
@@ -5301,8 +5295,20 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
* the page lock, which serializes swap cache removal, which
* in turn serializes uncharging.
*/
+ VM_BUG_ON_PAGE(!PageLocked(page), page);
if (page->mem_cgroup)
goto out;
+
+ if (do_swap_account) {
+ swp_entry_t ent = { .val = page_private(page), };
+ unsigned short id = lookup_swap_cgroup_id(ent);
+
+ rcu_read_lock();
+ memcg = mem_cgroup_from_id(id);
+ if (memcg && !css_tryget_online(&memcg->css))
+ memcg = NULL;
+ rcu_read_unlock();
+ }
}
if (PageTransHuge(page)) {
@@ -5310,8 +5316,6 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
VM_BUG_ON_PAGE(!PageTransHuge(page), page);
}
- if (do_swap_account && PageSwapCache(page))
- memcg = try_get_mem_cgroup_from_page(page);
if (!memcg)
memcg = get_mem_cgroup_from_mm(mm);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index eeda6485e76c..95882692e747 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -130,27 +130,15 @@ static int hwpoison_filter_flags(struct page *p)
* can only guarantee that the page either belongs to the memcg tasks, or is
* a freed page.
*/
-#ifdef CONFIG_MEMCG_SWAP
+#ifdef CONFIG_MEMCG
u64 hwpoison_filter_memcg;
EXPORT_SYMBOL_GPL(hwpoison_filter_memcg);
static int hwpoison_filter_task(struct page *p)
{
- struct mem_cgroup *mem;
- struct cgroup_subsys_state *css;
- unsigned long ino;
-
if (!hwpoison_filter_memcg)
return 0;
- mem = try_get_mem_cgroup_from_page(p);
- if (!mem)
- return -EINVAL;
-
- css = &mem->css;
- ino = cgroup_ino(css->cgroup);
- css_put(css);
-
- if (ino != hwpoison_filter_memcg)
+ if (page_cgroup_ino(p) != hwpoison_filter_memcg)
return -EINVAL;
return 0;
diff --git a/mm/memory.c b/mm/memory.c
index 6cd0b2160401..9cb27470fee9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3233,7 +3233,7 @@ out:
static int create_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, unsigned int flags)
{
- if (!vma->vm_ops)
+ if (vma_is_anonymous(vma))
return do_huge_pmd_anonymous_page(mm, vma, address, pmd, flags);
if (vma->vm_ops->pmd_fault)
return vma->vm_ops->pmd_fault(vma, address, pmd, flags);
@@ -3244,7 +3244,7 @@ static int wp_huge_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pmd_t *pmd, pmd_t orig_pmd,
unsigned int flags)
{
- if (!vma->vm_ops)
+ if (vma_is_anonymous(vma))
return do_huge_pmd_wp_page(mm, vma, address, pmd, orig_pmd);
if (vma->vm_ops->pmd_fault)
return vma->vm_ops->pmd_fault(vma, address, pmd, flags);
diff --git a/mm/migrate.c b/mm/migrate.c
index 02ce25df16c2..c3cb566af3e2 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -37,6 +37,7 @@
#include <linux/gfp.h>
#include <linux/balloon_compaction.h>
#include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
#include <asm/tlbflush.h>
@@ -524,6 +525,11 @@ void migrate_page_copy(struct page *newpage, struct page *page)
__set_page_dirty_nobuffers(newpage);
}
+ if (page_is_young(page))
+ set_page_young(newpage);
+ if (page_is_idle(page))
+ set_page_idle(newpage);
+
/*
* Copy NUMA information to the new page, to prevent over-eager
* future migrations of this same page.
diff --git a/mm/mmap.c b/mm/mmap.c
index b6be3249f0a9..971dd2cb77d2 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -612,6 +612,8 @@ static unsigned long count_vma_pages_range(struct mm_struct *mm,
void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
struct rb_node **rb_link, struct rb_node *rb_parent)
{
+ WARN_ONCE(vma->vm_file && !vma->vm_ops, "missing vma->vm_ops");
+
/* Update tracking information for the gap following the new vma. */
if (vma->vm_next)
vma_gap_update(vma->vm_next);
@@ -1260,14 +1262,12 @@ static inline int mlock_future_check(struct mm_struct *mm,
/*
* The caller must hold down_write(&current->mm->mmap_sem).
*/
-
-unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
+unsigned long do_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
- unsigned long flags, unsigned long pgoff,
- unsigned long *populate)
+ unsigned long flags, vm_flags_t vm_flags,
+ unsigned long pgoff, unsigned long *populate)
{
struct mm_struct *mm = current->mm;
- vm_flags_t vm_flags;
*populate = 0;
@@ -1311,7 +1311,7 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
* to. we assume access permissions have been handled by the open
* of the memory object, so we don't do any here.
*/
- vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags) |
+ vm_flags |= calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags) |
mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
if (flags & MAP_LOCKED)
@@ -1638,6 +1638,12 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
*/
WARN_ON_ONCE(addr != vma->vm_start);
+ /* All file mapping must have ->vm_ops set */
+ if (!vma->vm_ops) {
+ static const struct vm_operations_struct dummy_ops = {};
+ vma->vm_ops = &dummy_ops;
+ }
+
addr = vma->vm_start;
vm_flags = vma->vm_flags;
} else if (vm_flags & VM_SHARED) {
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 3b9b3d0741b2..5fbdd367bbed 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -123,6 +123,23 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
return young;
}
+int __mmu_notifier_clear_young(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ struct mmu_notifier *mn;
+ int young = 0, id;
+
+ id = srcu_read_lock(&srcu);
+ hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+ if (mn->ops->clear_young)
+ young |= mn->ops->clear_young(mn, mm, start, end);
+ }
+ srcu_read_unlock(&srcu, id);
+
+ return young;
+}
+
int __mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address)
{
diff --git a/mm/nommu.c b/mm/nommu.c
index 1cc0709fcaa5..ab14a2014dea 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1233,18 +1233,19 @@ enomem:
/*
* handle mapping creation for uClinux
*/
-unsigned long do_mmap_pgoff(struct file *file,
- unsigned long addr,
- unsigned long len,
- unsigned long prot,
- unsigned long flags,
- unsigned long pgoff,
- unsigned long *populate)
+unsigned long do_mmap(struct file *file,
+ unsigned long addr,
+ unsigned long len,
+ unsigned long prot,
+ unsigned long flags,
+ vm_flags_t vm_flags,
+ unsigned long pgoff,
+ unsigned long *populate)
{
struct vm_area_struct *vma;
struct vm_region *region;
struct rb_node *rb;
- unsigned long capabilities, vm_flags, result;
+ unsigned long capabilities, result;
int ret;
*populate = 0;
@@ -1262,7 +1263,7 @@ unsigned long do_mmap_pgoff(struct file *file,
/* we've determined that we can make the mapping, now translate what we
* now know into VMA flags */
- vm_flags = determine_vm_flags(file, prot, flags, capabilities);
+ vm_flags |= determine_vm_flags(file, prot, flags, capabilities);
/* we're going to need to record the mapping */
region = kmem_cache_zalloc(vm_region_jar, GFP_KERNEL);
diff --git a/mm/page_ext.c b/mm/page_ext.c
index d86fd2f5353f..292ca7b8debd 100644
--- a/mm/page_ext.c
+++ b/mm/page_ext.c
@@ -6,6 +6,7 @@
#include <linux/vmalloc.h>
#include <linux/kmemleak.h>
#include <linux/page_owner.h>
+#include <linux/page_idle.h>
/*
* struct page extension
@@ -59,6 +60,9 @@ static struct page_ext_operations *page_ext_ops[] = {
#ifdef CONFIG_PAGE_OWNER
&page_owner_ops,
#endif
+#if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT)
+ &page_idle_ops,
+#endif
};
static unsigned long total_usage;
diff --git a/mm/page_idle.c b/mm/page_idle.c
new file mode 100644
index 000000000000..d5dd79041484
--- /dev/null
+++ b/mm/page_idle.c
@@ -0,0 +1,232 @@
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/fs.h>
+#include <linux/sysfs.h>
+#include <linux/kobject.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/pagemap.h>
+#include <linux/rmap.h>
+#include <linux/mmu_notifier.h>
+#include <linux/page_ext.h>
+#include <linux/page_idle.h>
+
+#define BITMAP_CHUNK_SIZE sizeof(u64)
+#define BITMAP_CHUNK_BITS (BITMAP_CHUNK_SIZE * BITS_PER_BYTE)
+
+/*
+ * Idle page tracking only considers user memory pages, for other types of
+ * pages the idle flag is always unset and an attempt to set it is silently
+ * ignored.
+ *
+ * We treat a page as a user memory page if it is on an LRU list, because it is
+ * always safe to pass such a page to rmap_walk(), which is essential for idle
+ * page tracking. With such an indicator of user pages we can skip isolated
+ * pages, but since there are not usually many of them, it will hardly affect
+ * the overall result.
+ *
+ * This function tries to get a user memory page by pfn as described above.
+ */
+static struct page *page_idle_get_page(unsigned long pfn)
+{
+ struct page *page;
+ struct zone *zone;
+
+ if (!pfn_valid(pfn))
+ return NULL;
+
+ page = pfn_to_page(pfn);
+ if (!page || !PageLRU(page) ||
+ !get_page_unless_zero(page))
+ return NULL;
+
+ zone = page_zone(page);
+ spin_lock_irq(&zone->lru_lock);
+ if (unlikely(!PageLRU(page))) {
+ put_page(page);
+ page = NULL;
+ }
+ spin_unlock_irq(&zone->lru_lock);
+ return page;
+}
+
+static int page_idle_clear_pte_refs_one(struct page *page,
+ struct vm_area_struct *vma,
+ unsigned long addr, void *arg)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ spinlock_t *ptl;
+ pmd_t *pmd;
+ pte_t *pte;
+ bool referenced = false;
+
+ if (unlikely(PageTransHuge(page))) {
+ pmd = page_check_address_pmd(page, mm, addr,
+ PAGE_CHECK_ADDRESS_PMD_FLAG, &ptl);
+ if (pmd) {
+ referenced = pmdp_clear_young_notify(vma, addr, pmd);
+ spin_unlock(ptl);
+ }
+ } else {
+ pte = page_check_address(page, mm, addr, &ptl, 0);
+ if (pte) {
+ referenced = ptep_clear_young_notify(vma, addr, pte);
+ pte_unmap_unlock(pte, ptl);
+ }
+ }
+ if (referenced) {
+ clear_page_idle(page);
+ /*
+ * We cleared the referenced bit in a mapping to this page. To
+ * avoid interference with page reclaim, mark it young so that
+ * page_referenced() will return > 0.
+ */
+ set_page_young(page);
+ }
+ return SWAP_AGAIN;
+}
+
+static void page_idle_clear_pte_refs(struct page *page)
+{
+ /*
+ * Since rwc.arg is unused, rwc is effectively immutable, so we
+ * can make it static const to save some cycles and stack.
+ */
+ static const struct rmap_walk_control rwc = {
+ .rmap_one = page_idle_clear_pte_refs_one,
+ .anon_lock = page_lock_anon_vma_read,
+ };
+ bool need_lock;
+
+ if (!page_mapped(page) ||
+ !page_rmapping(page))
+ return;
+
+ need_lock = !PageAnon(page) || PageKsm(page);
+ if (need_lock && !trylock_page(page))
+ return;
+
+ rmap_walk(page, (struct rmap_walk_control *)&rwc);
+
+ if (need_lock)
+ unlock_page(page);
+}
+
+static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj,
+ struct bin_attribute *attr, char *buf,
+ loff_t pos, size_t count)
+{
+ u64 *out = (u64 *)buf;
+ struct page *page;
+ unsigned long pfn, end_pfn;
+ int bit;
+
+ if (pos % BITMAP_CHUNK_SIZE || count % BITMAP_CHUNK_SIZE)
+ return -EINVAL;
+
+ pfn = pos * BITS_PER_BYTE;
+ if (pfn >= max_pfn)
+ return 0;
+
+ end_pfn = pfn + count * BITS_PER_BYTE;
+ if (end_pfn > max_pfn)
+ end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS);
+
+ for (; pfn < end_pfn; pfn++) {
+ bit = pfn % BITMAP_CHUNK_BITS;
+ if (!bit)
+ *out = 0ULL;
+ page = page_idle_get_page(pfn);
+ if (page) {
+ if (page_is_idle(page)) {
+ /*
+ * The page might have been referenced via a
+ * pte, in which case it is not idle. Clear
+ * refs and recheck.
+ */
+ page_idle_clear_pte_refs(page);
+ if (page_is_idle(page))
+ *out |= 1ULL << bit;
+ }
+ put_page(page);
+ }
+ if (bit == BITMAP_CHUNK_BITS - 1)
+ out++;
+ cond_resched();
+ }
+ return (char *)out - buf;
+}
+
+static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj,
+ struct bin_attribute *attr, char *buf,
+ loff_t pos, size_t count)
+{
+ const u64 *in = (u64 *)buf;
+ struct page *page;
+ unsigned long pfn, end_pfn;
+ int bit;
+
+ if (pos % BITMAP_CHUNK_SIZE || count % BITMAP_CHUNK_SIZE)
+ return -EINVAL;
+
+ pfn = pos * BITS_PER_BYTE;
+ if (pfn >= max_pfn)
+ return -ENXIO;
+
+ end_pfn = pfn + count * BITS_PER_BYTE;
+ if (end_pfn > max_pfn)
+ end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS);
+
+ for (; pfn < end_pfn; pfn++) {
+ bit = pfn % BITMAP_CHUNK_BITS;
+ if ((*in >> bit) & 1) {
+ page = page_idle_get_page(pfn);
+ if (page) {
+ page_idle_clear_pte_refs(page);
+ set_page_idle(page);
+ put_page(page);
+ }
+ }
+ if (bit == BITMAP_CHUNK_BITS - 1)
+ in++;
+ cond_resched();
+ }
+ return (char *)in - buf;
+}
+
+static struct bin_attribute page_idle_bitmap_attr =
+ __BIN_ATTR(bitmap, S_IRUSR | S_IWUSR,
+ page_idle_bitmap_read, page_idle_bitmap_write, 0);
+
+static struct bin_attribute *page_idle_bin_attrs[] = {
+ &page_idle_bitmap_attr,
+ NULL,
+};
+
+static struct attribute_group page_idle_attr_group = {
+ .bin_attrs = page_idle_bin_attrs,
+ .name = "page_idle",
+};
+
+#ifndef CONFIG_64BIT
+static bool need_page_idle(void)
+{
+ return true;
+}
+struct page_ext_operations page_idle_ops = {
+ .need = need_page_idle,
+};
+#endif
+
+static int __init page_idle_init(void)
+{
+ int err;
+
+ err = sysfs_create_group(mm_kobj, &page_idle_attr_group);
+ if (err) {
+ pr_err("page_idle: register sysfs failed\n");
+ return err;
+ }
+ return 0;
+}
+subsys_initcall(page_idle_init);
diff --git a/mm/rmap.c b/mm/rmap.c
index 0db38e7d0a72..f5b5c1f3dcd7 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -59,6 +59,7 @@
#include <linux/migrate.h>
#include <linux/hugetlb.h>
#include <linux/backing-dev.h>
+#include <linux/page_idle.h>
#include <asm/tlbflush.h>
@@ -886,6 +887,11 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
pte_unmap_unlock(pte, ptl);
}
+ if (referenced)
+ clear_page_idle(page);
+ if (test_and_clear_page_young(page))
+ referenced++;
+
if (referenced) {
pra->referenced++;
pra->vm_flags |= vma->vm_flags;
diff --git a/mm/swap.c b/mm/swap.c
index a3a0a2f1f7c3..983f692a47fd 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -32,6 +32,7 @@
#include <linux/gfp.h>
#include <linux/uio.h>
#include <linux/hugetlb.h>
+#include <linux/page_idle.h>
#include "internal.h"
@@ -622,6 +623,8 @@ void mark_page_accessed(struct page *page)
} else if (!PageReferenced(page)) {
SetPageReferenced(page);
}
+ if (page_is_idle(page))
+ clear_page_idle(page);
}
EXPORT_SYMBOL(mark_page_accessed);
diff --git a/mm/zpool.c b/mm/zpool.c
index 68d2dd8ed2d8..8f670d3e8706 100644
--- a/mm/zpool.c
+++ b/mm/zpool.c
@@ -100,6 +100,39 @@ static void zpool_put_driver(struct zpool_driver *driver)
}
/**
+ * zpool_has_pool() - Check if the pool driver is available
+ * @type The type of the zpool to check (e.g. zbud, zsmalloc)
+ *
+ * This checks if the @type pool driver is available. This will try to load
+ * the requested module, if needed, but there is no guarantee the module will
+ * still be loaded and available immediately after calling. If this returns
+ * true, the caller should assume the pool is available, but must be prepared
+ * to handle the @zpool_create_pool() returning failure. However if this
+ * returns false, the caller should assume the requested pool type is not
+ * available; either the requested pool type module does not exist, or could
+ * not be loaded, and calling @zpool_create_pool() with the pool type will
+ * fail.
+ *
+ * Returns: true if @type pool is available, false if not
+ */
+bool zpool_has_pool(char *type)
+{
+ struct zpool_driver *driver = zpool_get_driver(type);
+
+ if (!driver) {
+ request_module("zpool-%s", type);
+ driver = zpool_get_driver(type);
+ }
+
+ if (!driver)
+ return false;
+
+ zpool_put_driver(driver);
+ return true;
+}
+EXPORT_SYMBOL(zpool_has_pool);
+
+/**
* zpool_create_pool() - Create a new zpool
* @type The type of the zpool to create (e.g. zbud, zsmalloc)
* @name The name of the zpool (e.g. zram0, zswap)
diff --git a/mm/zswap.c b/mm/zswap.c
index 48a1d081e2a5..4043df7c672f 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -80,85 +80,54 @@ static u64 zswap_duplicate_entry;
static bool zswap_enabled;
module_param_named(enabled, zswap_enabled, bool, 0644);
-/* Compressor to be used by zswap (fixed at boot for now) */
+/* Crypto compressor to use */
#define ZSWAP_COMPRESSOR_DEFAULT "lzo"
-static char *zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
-module_param_named(compressor, zswap_compressor, charp, 0444);
-
-/* The maximum percentage of memory that the compressed pool can occupy */
-static unsigned int zswap_max_pool_percent = 20;
-module_param_named(max_pool_percent,
- zswap_max_pool_percent, uint, 0644);
+static char zswap_compressor[CRYPTO_MAX_ALG_NAME] = ZSWAP_COMPRESSOR_DEFAULT;
+static struct kparam_string zswap_compressor_kparam = {
+ .string = zswap_compressor,
+ .maxlen = sizeof(zswap_compressor),
+};
+static int zswap_compressor_param_set(const char *,
+ const struct kernel_param *);
+static struct kernel_param_ops zswap_compressor_param_ops = {
+ .set = zswap_compressor_param_set,
+ .get = param_get_string,
+};
+module_param_cb(compressor, &zswap_compressor_param_ops,
+ &zswap_compressor_kparam, 0644);
-/* Compressed storage to use */
+/* Compressed storage zpool to use */
#define ZSWAP_ZPOOL_DEFAULT "zbud"
-static char *zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
-module_param_named(zpool, zswap_zpool_type, charp, 0444);
+static char zswap_zpool_type[32 /* arbitrary */] = ZSWAP_ZPOOL_DEFAULT;
+static struct kparam_string zswap_zpool_kparam = {
+ .string = zswap_zpool_type,
+ .maxlen = sizeof(zswap_zpool_type),
+};
+static int zswap_zpool_param_set(const char *, const struct kernel_param *);
+static struct kernel_param_ops zswap_zpool_param_ops = {
+ .set = zswap_zpool_param_set,
+ .get = param_get_string,
+};
+module_param_cb(zpool, &zswap_zpool_param_ops, &zswap_zpool_kparam, 0644);
-/* zpool is shared by all of zswap backend */
-static struct zpool *zswap_pool;
+/* The maximum percentage of memory that the compressed pool can occupy */
+static unsigned int zswap_max_pool_percent = 20;
+module_param_named(max_pool_percent, zswap_max_pool_percent, uint, 0644);
/*********************************
-* compression functions
+* data structures
**********************************/
-/* per-cpu compression transforms */
-static struct crypto_comp * __percpu *zswap_comp_pcpu_tfms;
-enum comp_op {
- ZSWAP_COMPOP_COMPRESS,
- ZSWAP_COMPOP_DECOMPRESS
+struct zswap_pool {
+ struct zpool *zpool;
+ struct crypto_comp * __percpu *tfm;
+ struct kref kref;
+ struct list_head list;
+ struct rcu_head rcu_head;
+ struct notifier_block notifier;
+ char tfm_name[CRYPTO_MAX_ALG_NAME];
};
-static int zswap_comp_op(enum comp_op op, const u8 *src, unsigned int slen,
- u8 *dst, unsigned int *dlen)
-{
- struct crypto_comp *tfm;
- int ret;
-
- tfm = *per_cpu_ptr(zswap_comp_pcpu_tfms, get_cpu());
- switch (op) {
- case ZSWAP_COMPOP_COMPRESS:
- ret = crypto_comp_compress(tfm, src, slen, dst, dlen);
- break;
- case ZSWAP_COMPOP_DECOMPRESS:
- ret = crypto_comp_decompress(tfm, src, slen, dst, dlen);
- break;
- default:
- ret = -EINVAL;
- }
-
- put_cpu();
- return ret;
-}
-
-static int __init zswap_comp_init(void)
-{
- if (!crypto_has_comp(zswap_compressor, 0, 0)) {
- pr_info("%s compressor not available\n", zswap_compressor);
- /* fall back to default compressor */
- zswap_compressor = ZSWAP_COMPRESSOR_DEFAULT;
- if (!crypto_has_comp(zswap_compressor, 0, 0))
- /* can't even load the default compressor */
- return -ENODEV;
- }
- pr_info("using %s compressor\n", zswap_compressor);
-
- /* alloc percpu transforms */
- zswap_comp_pcpu_tfms = alloc_percpu(struct crypto_comp *);
- if (!zswap_comp_pcpu_tfms)
- return -ENOMEM;
- return 0;
-}
-
-static void __init zswap_comp_exit(void)
-{
- /* free percpu transforms */
- free_percpu(zswap_comp_pcpu_tfms);
-}
-
-/*********************************
-* data structures
-**********************************/
/*
* struct zswap_entry
*
@@ -166,22 +135,24 @@ static void __init zswap_comp_exit(void)
* page within zswap.
*
* rbnode - links the entry into red-black tree for the appropriate swap type
+ * offset - the swap offset for the entry. Index into the red-black tree.
* refcount - the number of outstanding reference to the entry. This is needed
* to protect against premature freeing of the entry by code
* concurrent calls to load, invalidate, and writeback. The lock
* for the zswap_tree structure that contains the entry must
* be held while changing the refcount. Since the lock must
* be held, there is no reason to also make refcount atomic.
- * offset - the swap offset for the entry. Index into the red-black tree.
- * handle - zpool allocation handle that stores the compressed page data
* length - the length in bytes of the compressed page data. Needed during
* decompression
+ * pool - the zswap_pool the entry's data is in
+ * handle - zpool allocation handle that stores the compressed page data
*/
struct zswap_entry {
struct rb_node rbnode;
pgoff_t offset;
int refcount;
unsigned int length;
+ struct zswap_pool *pool;
unsigned long handle;
};
@@ -201,6 +172,51 @@ struct zswap_tree {
static struct zswap_tree *zswap_trees[MAX_SWAPFILES];
+/* RCU-protected iteration */
+static LIST_HEAD(zswap_pools);
+/* protects zswap_pools list modification */
+static DEFINE_SPINLOCK(zswap_pools_lock);
+
+/* used by param callback function */
+static bool zswap_init_started;
+
+/*********************************
+* helpers and fwd declarations
+**********************************/
+
+#define zswap_pool_debug(msg, p) \
+ pr_debug("%s pool %s/%s\n", msg, (p)->tfm_name, \
+ zpool_get_type((p)->zpool))
+
+static int zswap_writeback_entry(struct zpool *pool, unsigned long handle);
+static int zswap_pool_get(struct zswap_pool *pool);
+static void zswap_pool_put(struct zswap_pool *pool);
+
+static const struct zpool_ops zswap_zpool_ops = {
+ .evict = zswap_writeback_entry
+};
+
+static bool zswap_is_full(void)
+{
+ return totalram_pages * zswap_max_pool_percent / 100 <
+ DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
+}
+
+static void zswap_update_total_size(void)
+{
+ struct zswap_pool *pool;
+ u64 total = 0;
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(pool, &zswap_pools, list)
+ total += zpool_get_total_size(pool->zpool);
+
+ rcu_read_unlock();
+
+ zswap_pool_total_size = total;
+}
+
/*********************************
* zswap entry functions
**********************************/
@@ -294,10 +310,11 @@ static void zswap_rb_erase(struct rb_root *root, struct zswap_entry *entry)
*/
static void zswap_free_entry(struct zswap_entry *entry)
{
- zpool_free(zswap_pool, entry->handle);
+ zpool_free(entry->pool->zpool, entry->handle);
+ zswap_pool_put(entry->pool);
zswap_entry_cache_free(entry);
atomic_dec(&zswap_stored_pages);
- zswap_pool_total_size = zpool_get_total_size(zswap_pool);
+ zswap_update_total_size();
}
/* caller must hold the tree lock */
@@ -339,35 +356,21 @@ static struct zswap_entry *zswap_entry_find_get(struct rb_root *root,
**********************************/
static DEFINE_PER_CPU(u8 *, zswap_dstmem);
-static int __zswap_cpu_notifier(unsigned long action, unsigned long cpu)
+static int __zswap_cpu_dstmem_notifier(unsigned long action, unsigned long cpu)
{
- struct crypto_comp *tfm;
u8 *dst;
switch (action) {
case CPU_UP_PREPARE:
- tfm = crypto_alloc_comp(zswap_compressor, 0, 0);
- if (IS_ERR(tfm)) {
- pr_err("can't allocate compressor transform\n");
- return NOTIFY_BAD;
- }
- *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = tfm;
dst = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
if (!dst) {
pr_err("can't allocate compressor buffer\n");
- crypto_free_comp(tfm);
- *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = NULL;
return NOTIFY_BAD;
}
per_cpu(zswap_dstmem, cpu) = dst;
break;
case CPU_DEAD:
case CPU_UP_CANCELED:
- tfm = *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu);
- if (tfm) {
- crypto_free_comp(tfm);
- *per_cpu_ptr(zswap_comp_pcpu_tfms, cpu) = NULL;
- }
dst = per_cpu(zswap_dstmem, cpu);
kfree(dst);
per_cpu(zswap_dstmem, cpu) = NULL;
@@ -378,43 +381,398 @@ static int __zswap_cpu_notifier(unsigned long action, unsigned long cpu)
return NOTIFY_OK;
}
-static int zswap_cpu_notifier(struct notifier_block *nb,
- unsigned long action, void *pcpu)
+static int zswap_cpu_dstmem_notifier(struct notifier_block *nb,
+ unsigned long action, void *pcpu)
{
- unsigned long cpu = (unsigned long)pcpu;
- return __zswap_cpu_notifier(action, cpu);
+ return __zswap_cpu_dstmem_notifier(action, (unsigned long)pcpu);
}
-static struct notifier_block zswap_cpu_notifier_block = {
- .notifier_call = zswap_cpu_notifier
+static struct notifier_block zswap_dstmem_notifier = {
+ .notifier_call = zswap_cpu_dstmem_notifier,
};
-static int __init zswap_cpu_init(void)
+static int __init zswap_cpu_dstmem_init(void)
+{
+ unsigned long cpu;
+
+ cpu_notifier_register_begin();
+ for_each_online_cpu(cpu)
+ if (__zswap_cpu_dstmem_notifier(CPU_UP_PREPARE, cpu) ==
+ NOTIFY_BAD)
+ goto cleanup;
+ __register_cpu_notifier(&zswap_dstmem_notifier);
+ cpu_notifier_register_done();
+ return 0;
+
+cleanup:
+ for_each_online_cpu(cpu)
+ __zswap_cpu_dstmem_notifier(CPU_UP_CANCELED, cpu);
+ cpu_notifier_register_done();
+ return -ENOMEM;
+}
+
+static void zswap_cpu_dstmem_destroy(void)
+{
+ unsigned long cpu;
+
+ cpu_notifier_register_begin();
+ for_each_online_cpu(cpu)
+ __zswap_cpu_dstmem_notifier(CPU_UP_CANCELED, cpu);
+ __unregister_cpu_notifier(&zswap_dstmem_notifier);
+ cpu_notifier_register_done();
+}
+
+static int __zswap_cpu_comp_notifier(struct zswap_pool *pool,
+ unsigned long action, unsigned long cpu)
+{
+ struct crypto_comp *tfm;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ if (WARN_ON(*per_cpu_ptr(pool->tfm, cpu)))
+ break;
+ tfm = crypto_alloc_comp(pool->tfm_name, 0, 0);
+ if (IS_ERR_OR_NULL(tfm)) {
+ pr_err("could not alloc crypto comp %s : %ld\n",
+ pool->tfm_name, PTR_ERR(tfm));
+ return NOTIFY_BAD;
+ }
+ *per_cpu_ptr(pool->tfm, cpu) = tfm;
+ break;
+ case CPU_DEAD:
+ case CPU_UP_CANCELED:
+ tfm = *per_cpu_ptr(pool->tfm, cpu);
+ if (!IS_ERR_OR_NULL(tfm))
+ crypto_free_comp(tfm);
+ *per_cpu_ptr(pool->tfm, cpu) = NULL;
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+static int zswap_cpu_comp_notifier(struct notifier_block *nb,
+ unsigned long action, void *pcpu)
+{
+ unsigned long cpu = (unsigned long)pcpu;
+ struct zswap_pool *pool = container_of(nb, typeof(*pool), notifier);
+
+ return __zswap_cpu_comp_notifier(pool, action, cpu);
+}
+
+static int zswap_cpu_comp_init(struct zswap_pool *pool)
{
unsigned long cpu;
+ memset(&pool->notifier, 0, sizeof(pool->notifier));
+ pool->notifier.notifier_call = zswap_cpu_comp_notifier;
+
cpu_notifier_register_begin();
for_each_online_cpu(cpu)
- if (__zswap_cpu_notifier(CPU_UP_PREPARE, cpu) != NOTIFY_OK)
+ if (__zswap_cpu_comp_notifier(pool, CPU_UP_PREPARE, cpu) ==
+ NOTIFY_BAD)
goto cleanup;
- __register_cpu_notifier(&zswap_cpu_notifier_block);
+ __register_cpu_notifier(&pool->notifier);
cpu_notifier_register_done();
return 0;
cleanup:
for_each_online_cpu(cpu)
- __zswap_cpu_notifier(CPU_UP_CANCELED, cpu);
+ __zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
cpu_notifier_register_done();
return -ENOMEM;
}
+static void zswap_cpu_comp_destroy(struct zswap_pool *pool)
+{
+ unsigned long cpu;
+
+ cpu_notifier_register_begin();
+ for_each_online_cpu(cpu)
+ __zswap_cpu_comp_notifier(pool, CPU_UP_CANCELED, cpu);
+ __unregister_cpu_notifier(&pool->notifier);
+ cpu_notifier_register_done();
+}
+
/*********************************
-* helpers
+* pool functions
**********************************/
-static bool zswap_is_full(void)
+
+static struct zswap_pool *__zswap_pool_current(void)
{
- return totalram_pages * zswap_max_pool_percent / 100 <
- DIV_ROUND_UP(zswap_pool_total_size, PAGE_SIZE);
+ struct zswap_pool *pool;
+
+ pool = list_first_or_null_rcu(&zswap_pools, typeof(*pool), list);
+ WARN_ON(!pool);
+
+ return pool;
+}
+
+static struct zswap_pool *zswap_pool_current(void)
+{
+ assert_spin_locked(&zswap_pools_lock);
+
+ return __zswap_pool_current();
+}
+
+static struct zswap_pool *zswap_pool_current_get(void)
+{
+ struct zswap_pool *pool;
+
+ rcu_read_lock();
+
+ pool = __zswap_pool_current();
+ if (!pool || !zswap_pool_get(pool))
+ pool = NULL;
+
+ rcu_read_unlock();
+
+ return pool;
+}
+
+static struct zswap_pool *zswap_pool_last_get(void)
+{
+ struct zswap_pool *pool, *last = NULL;
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(pool, &zswap_pools, list)
+ last = pool;
+ if (!WARN_ON(!last) && !zswap_pool_get(last))
+ last = NULL;
+
+ rcu_read_unlock();
+
+ return last;
+}
+
+static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor)
+{
+ struct zswap_pool *pool;
+
+ assert_spin_locked(&zswap_pools_lock);
+
+ list_for_each_entry_rcu(pool, &zswap_pools, list) {
+ if (strncmp(pool->tfm_name, compressor, sizeof(pool->tfm_name)))
+ continue;
+ if (strncmp(zpool_get_type(pool->zpool), type,
+ sizeof(zswap_zpool_type)))
+ continue;
+ /* if we can't get it, it's about to be destroyed */
+ if (!zswap_pool_get(pool))
+ continue;
+ return pool;
+ }
+
+ return NULL;
+}
+
+static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
+{
+ struct zswap_pool *pool;
+ gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN;
+
+ pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+ if (!pool) {
+ pr_err("pool alloc failed\n");
+ return NULL;
+ }
+
+ pool->zpool = zpool_create_pool(type, "zswap", gfp, &zswap_zpool_ops);
+ if (!pool->zpool) {
+ pr_err("%s zpool not available\n", type);
+ goto error;
+ }
+ pr_debug("using %s zpool\n", zpool_get_type(pool->zpool));
+
+ strlcpy(pool->tfm_name, compressor, sizeof(pool->tfm_name));
+ pool->tfm = alloc_percpu(struct crypto_comp *);
+ if (!pool->tfm) {
+ pr_err("percpu alloc failed\n");
+ goto error;
+ }
+
+ if (zswap_cpu_comp_init(pool))
+ goto error;
+ pr_debug("using %s compressor\n", pool->tfm_name);
+
+ /* being the current pool takes 1 ref; this func expects the
+ * caller to always add the new pool as the current pool
+ */
+ kref_init(&pool->kref);
+ INIT_LIST_HEAD(&pool->list);
+
+ zswap_pool_debug("created", pool);
+
+ return pool;
+
+error:
+ free_percpu(pool->tfm);
+ if (pool->zpool)
+ zpool_destroy_pool(pool->zpool);
+ kfree(pool);
+ return NULL;
+}
+
+static struct zswap_pool *__zswap_pool_create_fallback(void)
+{
+ if (!crypto_has_comp(zswap_compressor, 0, 0)) {
+ pr_err("compressor %s not available, using default %s\n",
+ zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT);
+ strncpy(zswap_compressor, ZSWAP_COMPRESSOR_DEFAULT,
+ sizeof(zswap_compressor));
+ }
+ if (!zpool_has_pool(zswap_zpool_type)) {
+ pr_err("zpool %s not available, using default %s\n",
+ zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT);
+ strncpy(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT,
+ sizeof(zswap_zpool_type));
+ }
+
+ return zswap_pool_create(zswap_zpool_type, zswap_compressor);
+}
+
+static void zswap_pool_destroy(struct zswap_pool *pool)
+{
+ zswap_pool_debug("destroying", pool);
+
+ zswap_cpu_comp_destroy(pool);
+ free_percpu(pool->tfm);
+ zpool_destroy_pool(pool->zpool);
+ kfree(pool);
+}
+
+static int __must_check zswap_pool_get(struct zswap_pool *pool)
+{
+ return kref_get_unless_zero(&pool->kref);
+}
+
+static void __zswap_pool_release(struct rcu_head *head)
+{
+ struct zswap_pool *pool = container_of(head, typeof(*pool), rcu_head);
+
+ /* nobody should have been able to get a kref... */
+ WARN_ON(kref_get_unless_zero(&pool->kref));
+
+ /* pool is now off zswap_pools list and has no references. */
+ zswap_pool_destroy(pool);
+}
+
+static void __zswap_pool_empty(struct kref *kref)
+{
+ struct zswap_pool *pool;
+
+ pool = container_of(kref, typeof(*pool), kref);
+
+ spin_lock(&zswap_pools_lock);
+
+ WARN_ON(pool == zswap_pool_current());
+
+ list_del_rcu(&pool->list);
+ call_rcu(&pool->rcu_head, __zswap_pool_release);
+
+ spin_unlock(&zswap_pools_lock);
+}
+
+static void zswap_pool_put(struct zswap_pool *pool)
+{
+ kref_put(&pool->kref, __zswap_pool_empty);
+}
+
+/*********************************
+* param callbacks
+**********************************/
+
+static int __zswap_param_set(const char *val, const struct kernel_param *kp,
+ char *type, char *compressor)
+{
+ struct zswap_pool *pool, *put_pool = NULL;
+ char str[kp->str->maxlen], *s;
+ int ret;
+
+ /*
+ * kp is either zswap_zpool_kparam or zswap_compressor_kparam, defined
+ * at the top of this file, so maxlen is CRYPTO_MAX_ALG_NAME (64) or
+ * 32 (arbitrary).
+ */
+ strlcpy(str, val, kp->str->maxlen);
+ s = strim(str);
+
+ /* if this is load-time (pre-init) param setting,
+ * don't create a pool; that's done during init.
+ */
+ if (!zswap_init_started)
+ return param_set_copystring(s, kp);
+
+ /* no change required */
+ if (!strncmp(kp->str->string, s, kp->str->maxlen))
+ return 0;
+
+ if (!type) {
+ type = s;
+ if (!zpool_has_pool(type)) {
+ pr_err("zpool %s not available\n", type);
+ return -ENOENT;
+ }
+ } else if (!compressor) {
+ compressor = s;
+ if (!crypto_has_comp(compressor, 0, 0)) {
+ pr_err("compressor %s not available\n", compressor);
+ return -ENOENT;
+ }
+ }
+
+ spin_lock(&zswap_pools_lock);
+
+ pool = zswap_pool_find_get(type, compressor);
+ if (pool) {
+ zswap_pool_debug("using existing", pool);
+ list_del_rcu(&pool->list);
+ } else {
+ spin_unlock(&zswap_pools_lock);
+ pool = zswap_pool_create(type, compressor);
+ spin_lock(&zswap_pools_lock);
+ }
+
+ if (pool)
+ ret = param_set_copystring(s, kp);
+ else
+ ret = -EINVAL;
+
+ if (!ret) {
+ put_pool = zswap_pool_current();
+ list_add_rcu(&pool->list, &zswap_pools);
+ } else if (pool) {
+ /* add the possibly pre-existing pool to the end of the pools
+ * list; if it's new (and empty) then it'll be removed and
+ * destroyed by the put after we drop the lock
+ */
+ list_add_tail_rcu(&pool->list, &zswap_pools);
+ put_pool = pool;
+ }
+
+ spin_unlock(&zswap_pools_lock);
+
+ /* drop the ref from either the old current pool,
+ * or the new pool we failed to add
+ */
+ if (put_pool)
+ zswap_pool_put(put_pool);
+
+ return ret;
+}
+
+static int zswap_compressor_param_set(const char *val,
+ const struct kernel_param *kp)
+{
+ return __zswap_param_set(val, kp, zswap_zpool_type, NULL);
+}
+
+static int zswap_zpool_param_set(const char *val,
+ const struct kernel_param *kp)
+{
+ return __zswap_param_set(val, kp, NULL, zswap_compressor);
}
/*********************************
@@ -477,6 +835,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
pgoff_t offset;
struct zswap_entry *entry;
struct page *page;
+ struct crypto_comp *tfm;
u8 *src, *dst;
unsigned int dlen;
int ret;
@@ -517,13 +876,15 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
case ZSWAP_SWAPCACHE_NEW: /* page is locked */
/* decompress */
dlen = PAGE_SIZE;
- src = (u8 *)zpool_map_handle(zswap_pool, entry->handle,
+ src = (u8 *)zpool_map_handle(entry->pool->zpool, entry->handle,
ZPOOL_MM_RO) + sizeof(struct zswap_header);
dst = kmap_atomic(page);
- ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src,
- entry->length, dst, &dlen);
+ tfm = *get_cpu_ptr(entry->pool->tfm);
+ ret = crypto_comp_decompress(tfm, src, entry->length,
+ dst, &dlen);
+ put_cpu_ptr(entry->pool->tfm);
kunmap_atomic(dst);
- zpool_unmap_handle(zswap_pool, entry->handle);
+ zpool_unmap_handle(entry->pool->zpool, entry->handle);
BUG_ON(ret);
BUG_ON(dlen != PAGE_SIZE);
@@ -572,6 +933,22 @@ end:
return ret;
}
+static int zswap_shrink(void)
+{
+ struct zswap_pool *pool;
+ int ret;
+
+ pool = zswap_pool_last_get();
+ if (!pool)
+ return -ENOENT;
+
+ ret = zpool_shrink(pool->zpool, 1, NULL);
+
+ zswap_pool_put(pool);
+
+ return ret;
+}
+
/*********************************
* frontswap hooks
**********************************/
@@ -581,6 +958,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
{
struct zswap_tree *tree = zswap_trees[type];
struct zswap_entry *entry, *dupentry;
+ struct crypto_comp *tfm;
int ret;
unsigned int dlen = PAGE_SIZE, len;
unsigned long handle;
@@ -596,7 +974,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
/* reclaim space if needed */
if (zswap_is_full()) {
zswap_pool_limit_hit++;
- if (zpool_shrink(zswap_pool, 1, NULL)) {
+ if (zswap_shrink()) {
zswap_reject_reclaim_fail++;
ret = -ENOMEM;
goto reject;
@@ -611,33 +989,42 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
goto reject;
}
+ /* if entry is successfully added, it keeps the reference */
+ entry->pool = zswap_pool_current_get();
+ if (!entry->pool) {
+ ret = -EINVAL;
+ goto freepage;
+ }
+
/* compress */
dst = get_cpu_var(zswap_dstmem);
+ tfm = *get_cpu_ptr(entry->pool->tfm);
src = kmap_atomic(page);
- ret = zswap_comp_op(ZSWAP_COMPOP_COMPRESS, src, PAGE_SIZE, dst, &dlen);
+ ret = crypto_comp_compress(tfm, src, PAGE_SIZE, dst, &dlen);
kunmap_atomic(src);
+ put_cpu_ptr(entry->pool->tfm);
if (ret) {
ret = -EINVAL;
- goto freepage;
+ goto put_dstmem;
}
/* store */
len = dlen + sizeof(struct zswap_header);
- ret = zpool_malloc(zswap_pool, len, __GFP_NORETRY | __GFP_NOWARN,
- &handle);
+ ret = zpool_malloc(entry->pool->zpool, len,
+ __GFP_NORETRY | __GFP_NOWARN, &handle);
if (ret == -ENOSPC) {
zswap_reject_compress_poor++;
- goto freepage;
+ goto put_dstmem;
}
if (ret) {
zswap_reject_alloc_fail++;
- goto freepage;
+ goto put_dstmem;
}
- zhdr = zpool_map_handle(zswap_pool, handle, ZPOOL_MM_RW);
+ zhdr = zpool_map_handle(entry->pool->zpool, handle, ZPOOL_MM_RW);
zhdr->swpentry = swp_entry(type, offset);
buf = (u8 *)(zhdr + 1);
memcpy(buf, dst, dlen);
- zpool_unmap_handle(zswap_pool, handle);
+ zpool_unmap_handle(entry->pool->zpool, handle);
put_cpu_var(zswap_dstmem);
/* populate entry */
@@ -660,12 +1047,14 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset,
/* update stats */
atomic_inc(&zswap_stored_pages);
- zswap_pool_total_size = zpool_get_total_size(zswap_pool);
+ zswap_update_total_size();
return 0;
-freepage:
+put_dstmem:
put_cpu_var(zswap_dstmem);
+ zswap_pool_put(entry->pool);
+freepage:
zswap_entry_cache_free(entry);
reject:
return ret;
@@ -680,6 +1069,7 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
{
struct zswap_tree *tree = zswap_trees[type];
struct zswap_entry *entry;
+ struct crypto_comp *tfm;
u8 *src, *dst;
unsigned int dlen;
int ret;
@@ -696,13 +1086,14 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
/* decompress */
dlen = PAGE_SIZE;
- src = (u8 *)zpool_map_handle(zswap_pool, entry->handle,
+ src = (u8 *)zpool_map_handle(entry->pool->zpool, entry->handle,
ZPOOL_MM_RO) + sizeof(struct zswap_header);
dst = kmap_atomic(page);
- ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length,
- dst, &dlen);
+ tfm = *get_cpu_ptr(entry->pool->tfm);
+ ret = crypto_comp_decompress(tfm, src, entry->length, dst, &dlen);
+ put_cpu_ptr(entry->pool->tfm);
kunmap_atomic(dst);
- zpool_unmap_handle(zswap_pool, entry->handle);
+ zpool_unmap_handle(entry->pool->zpool, entry->handle);
BUG_ON(ret);
spin_lock(&tree->lock);
@@ -755,10 +1146,6 @@ static void zswap_frontswap_invalidate_area(unsigned type)
zswap_trees[type] = NULL;
}
-static const struct zpool_ops zswap_zpool_ops = {
- .evict = zswap_writeback_entry
-};
-
static void zswap_frontswap_init(unsigned type)
{
struct zswap_tree *tree;
@@ -839,49 +1226,40 @@ static void __exit zswap_debugfs_exit(void) { }
**********************************/
static int __init init_zswap(void)
{
- gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN;
+ struct zswap_pool *pool;
- pr_info("loading zswap\n");
-
- zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp,
- &zswap_zpool_ops);
- if (!zswap_pool && strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) {
- pr_info("%s zpool not available\n", zswap_zpool_type);
- zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT;
- zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp,
- &zswap_zpool_ops);
- }
- if (!zswap_pool) {
- pr_err("%s zpool not available\n", zswap_zpool_type);
- pr_err("zpool creation failed\n");
- goto error;
- }
- pr_info("using %s pool\n", zswap_zpool_type);
+ zswap_init_started = true;
if (zswap_entry_cache_create()) {
pr_err("entry cache creation failed\n");
- goto cachefail;
+ goto cache_fail;
}
- if (zswap_comp_init()) {
- pr_err("compressor initialization failed\n");
- goto compfail;
+
+ if (zswap_cpu_dstmem_init()) {
+ pr_err("dstmem alloc failed\n");
+ goto dstmem_fail;
}
- if (zswap_cpu_init()) {
- pr_err("per-cpu initialization failed\n");
- goto pcpufail;
+
+ pool = __zswap_pool_create_fallback();
+ if (!pool) {
+ pr_err("pool creation failed\n");
+ goto pool_fail;
}
+ pr_info("loaded using pool %s/%s\n", pool->tfm_name,
+ zpool_get_type(pool->zpool));
+
+ list_add(&pool->list, &zswap_pools);
frontswap_register_ops(&zswap_frontswap_ops);
if (zswap_debugfs_init())
pr_warn("debugfs initialization failed\n");
return 0;
-pcpufail:
- zswap_comp_exit();
-compfail:
+
+pool_fail:
+ zswap_cpu_dstmem_destroy();
+dstmem_fail:
zswap_entry_cache_destroy();
-cachefail:
- zpool_destroy_pool(zswap_pool);
-error:
+cache_fail:
return -ENOMEM;
}
/* must be late so crypto has time to come up */