summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/Kconfig1
-rw-r--r--mm/backing-dev.c4
-rw-r--r--mm/compaction.c2
-rw-r--r--mm/early_ioremap.c2
-rw-r--r--mm/filemap.c106
-rw-r--r--mm/memory.c19
-rw-r--r--mm/memory_hotplug.c30
-rw-r--r--mm/migrate.c6
-rw-r--r--mm/mmap.c7
-rw-r--r--mm/nommu.c7
-rw-r--r--mm/page-writeback.c18
-rw-r--r--mm/page_alloc.c8
-rw-r--r--mm/percpu.c1
-rw-r--r--mm/slab.c3
-rw-r--r--mm/util.c40
-rw-r--r--mm/vmscan.c15
-rw-r--r--mm/vmstat.c1
17 files changed, 191 insertions, 79 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index 7077376523ed..dcca76e498df 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -666,6 +666,7 @@ config DEFERRED_STRUCT_PAGE_INIT
default n
depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
depends on MEMORY_HOTPLUG
+ depends on !NEED_PER_CPU_KM
help
Ordinarily all struct pages are initialised during early boot in a
single thread. On very large machines this can take a considerable
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 4c480a20d76c..3081f1234d4e 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -954,7 +954,7 @@ static atomic_t nr_wb_congested[2];
void clear_wb_congested(struct bdi_writeback_congested *congested, int sync)
{
wait_queue_head_t *wqh = &congestion_wqh[sync];
- enum wb_state bit;
+ enum wb_congested_state bit;
bit = sync ? WB_sync_congested : WB_async_congested;
if (test_and_clear_bit(bit, &congested->state))
@@ -967,7 +967,7 @@ EXPORT_SYMBOL(clear_wb_congested);
void set_wb_congested(struct bdi_writeback_congested *congested, int sync)
{
- enum wb_state bit;
+ enum wb_congested_state bit;
bit = sync ? WB_sync_congested : WB_async_congested;
if (!test_and_set_bit(bit, &congested->state))
diff --git a/mm/compaction.c b/mm/compaction.c
index faee4807b1d2..86687ec1d034 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -853,7 +853,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
locked = false;
}
- if (isolate_movable_page(page, isolate_mode))
+ if (!isolate_movable_page(page, isolate_mode))
goto isolate_success;
}
diff --git a/mm/early_ioremap.c b/mm/early_ioremap.c
index 6d5717bd7197..57540de2b44c 100644
--- a/mm/early_ioremap.c
+++ b/mm/early_ioremap.c
@@ -103,7 +103,7 @@ __early_ioremap(resource_size_t phys_addr, unsigned long size, pgprot_t prot)
enum fixed_addresses idx;
int i, slot;
- WARN_ON(system_state != SYSTEM_BOOTING);
+ WARN_ON(system_state >= SYSTEM_RUNNING);
slot = -1;
for (i = 0; i < FIX_BTMAPS_SLOTS; i++) {
diff --git a/mm/filemap.c b/mm/filemap.c
index 8b2cf0f6a529..f3d6d89cfd61 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -573,7 +573,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
VM_BUG_ON_PAGE(!PageLocked(new), new);
VM_BUG_ON_PAGE(new->mapping, new);
- error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
+ error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK);
if (!error) {
struct address_space *mapping = old->mapping;
void (*freepage)(struct page *);
@@ -632,7 +632,7 @@ static int __add_to_page_cache_locked(struct page *page,
return error;
}
- error = radix_tree_maybe_preload(gfp_mask & ~__GFP_HIGHMEM);
+ error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK);
if (error) {
if (!huge)
mem_cgroup_cancel_charge(page, memcg);
@@ -1194,8 +1194,7 @@ no_page:
if (fgp_flags & FGP_ACCESSED)
__SetPageReferenced(page);
- err = add_to_page_cache_lru(page, mapping, offset,
- gfp_mask & GFP_RECLAIM_MASK);
+ err = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
if (unlikely(err)) {
page_cache_release(page);
page = NULL;
@@ -1584,6 +1583,15 @@ find_page:
index, last_index - index);
}
if (!PageUptodate(page)) {
+ /*
+ * See comment in do_read_cache_page on why
+ * wait_on_page_locked is used to avoid unnecessarily
+ * serialisations and why it's safe.
+ */
+ wait_on_page_locked_killable(page);
+ if (PageUptodate(page))
+ goto page_ok;
+
if (inode->i_blkbits == PAGE_CACHE_SHIFT ||
!mapping->a_ops->is_partially_uptodate)
goto page_not_up_to_date;
@@ -1829,19 +1837,18 @@ EXPORT_SYMBOL(generic_file_read_iter);
* This adds the requested page to the page cache if it isn't already there,
* and schedules an I/O to read in its contents from disk.
*/
-static int page_cache_read(struct file *file, pgoff_t offset)
+static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
{
struct address_space *mapping = file->f_mapping;
struct page *page;
int ret;
do {
- page = page_cache_alloc_cold(mapping);
+ page = __page_cache_alloc(gfp_mask|__GFP_COLD);
if (!page)
return -ENOMEM;
- ret = add_to_page_cache_lru(page, mapping, offset,
- mapping_gfp_constraint(mapping, GFP_KERNEL));
+ ret = add_to_page_cache_lru(page, mapping, offset, gfp_mask);
if (ret == 0)
ret = mapping->a_ops->readpage(file, page);
else if (ret == -EEXIST)
@@ -2022,7 +2029,7 @@ no_cached_page:
* We're only likely to ever get here if MADV_RANDOM is in
* effect.
*/
- error = page_cache_read(file, offset);
+ error = page_cache_read(file, offset, vmf->gfp_mask);
/*
* The page we want has now been added to the page cache.
@@ -2219,7 +2226,7 @@ static struct page *wait_on_page_read(struct page *page)
return page;
}
-static struct page *__read_cache_page(struct address_space *mapping,
+static struct page *do_read_cache_page(struct address_space *mapping,
pgoff_t index,
int (*filler)(void *, struct page *),
void *data,
@@ -2241,53 +2248,74 @@ repeat:
/* Presumably ENOMEM for radix tree node */
return ERR_PTR(err);
}
+
+filler:
err = filler(data, page);
if (err < 0) {
page_cache_release(page);
- page = ERR_PTR(err);
- } else {
- page = wait_on_page_read(page);
+ return ERR_PTR(err);
}
- }
- return page;
-}
-static struct page *do_read_cache_page(struct address_space *mapping,
- pgoff_t index,
- int (*filler)(void *, struct page *),
- void *data,
- gfp_t gfp)
-
-{
- struct page *page;
- int err;
+ page = wait_on_page_read(page);
+ if (IS_ERR(page))
+ return page;
+ goto out;
+ }
+ if (PageUptodate(page))
+ goto out;
-retry:
- page = __read_cache_page(mapping, index, filler, data, gfp);
- if (IS_ERR(page))
- return page;
+ /*
+ * Page is not up to date and may be locked due one of the following
+ * case a: Page is being filled and the page lock is held
+ * case b: Read/write error clearing the page uptodate status
+ * case c: Truncation in progress (page locked)
+ * case d: Reclaim in progress
+ *
+ * Case a, the page will be up to date when the page is unlocked.
+ * There is no need to serialise on the page lock here as the page
+ * is pinned so the lock gives no additional protection. Even if the
+ * the page is truncated, the data is still valid if PageUptodate as
+ * it's a race vs truncate race.
+ * Case b, the page will not be up to date
+ * Case c, the page may be truncated but in itself, the data may still
+ * be valid after IO completes as it's a read vs truncate race. The
+ * operation must restart if the page is not uptodate on unlock but
+ * otherwise serialising on page lock to stabilise the mapping gives
+ * no additional guarantees to the caller as the page lock is
+ * released before return.
+ * Case d, similar to truncation. If reclaim holds the page lock, it
+ * will be a race with remove_mapping that determines if the mapping
+ * is valid on unlock but otherwise the data is valid and there is
+ * no need to serialise with page lock.
+ *
+ * As the page lock gives no additional guarantee, we optimistically
+ * wait on the page to be unlocked and check if it's up to date and
+ * use the page if it is. Otherwise, the page lock is required to
+ * distinguish between the different cases. The motivation is that we
+ * avoid spurious serialisations and wakeups when multiple processes
+ * wait on the same page for IO to complete.
+ */
+ wait_on_page_locked(page);
if (PageUptodate(page))
goto out;
+ /* Distinguish between all the cases under the safety of the lock */
lock_page(page);
+
+ /* Case c or d, restart the operation */
if (!page->mapping) {
unlock_page(page);
page_cache_release(page);
- goto retry;
+ goto repeat;
}
+
+ /* Someone else locked and filled the page in a very small window */
if (PageUptodate(page)) {
unlock_page(page);
goto out;
}
- err = filler(data, page);
- if (err < 0) {
- page_cache_release(page);
- return ERR_PTR(err);
- } else {
- page = wait_on_page_read(page);
- if (IS_ERR(page))
- return page;
- }
+ goto filler;
+
out:
mark_page_accessed(page);
return page;
diff --git a/mm/memory.c b/mm/memory.c
index d6e10c888541..78ab57141731 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -72,7 +72,7 @@
#include "internal.h"
-#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+#if defined(LAST_CPUPID_NOT_IN_PAGE_FLAGS) && !defined(CONFIG_COMPILE_TEST)
#warning Unfortunate NUMA and NUMA Balancing config, growing page-frame for last_cpupid.
#endif
@@ -1990,6 +1990,20 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
copy_user_highpage(dst, src, va, vma);
}
+static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
+{
+ struct file *vm_file = vma->vm_file;
+
+ if (vm_file)
+ return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO;
+
+ /*
+ * Special mappings (e.g. VDSO) do not have any file so fake
+ * a default GFP_KERNEL for them.
+ */
+ return GFP_KERNEL;
+}
+
/*
* Notify the address space that the page is about to become writable so that
* it can prohibit this or wait for the page to get into an appropriate state.
@@ -2005,6 +2019,7 @@ static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page,
vmf.virtual_address = (void __user *)(address & PAGE_MASK);
vmf.pgoff = page->index;
vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
+ vmf.gfp_mask = __get_fault_gfp_mask(vma);
vmf.page = page;
vmf.cow_page = NULL;
@@ -2771,6 +2786,7 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
vmf.pgoff = pgoff;
vmf.flags = flags;
vmf.page = NULL;
+ vmf.gfp_mask = __get_fault_gfp_mask(vma);
vmf.cow_page = cow_page;
ret = vma->vm_ops->fault(vma, &vmf);
@@ -2937,6 +2953,7 @@ static void do_fault_around(struct vm_area_struct *vma, unsigned long address,
vmf.pgoff = pgoff;
vmf.max_pgoff = max_pgoff;
vmf.flags = flags;
+ vmf.gfp_mask = __get_fault_gfp_mask(vma);
vma->vm_ops->map_pages(vma, &vmf);
}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 2e80a7bedef3..191b9eff7fc3 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1423,10 +1423,10 @@ int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn,
}
/*
- * Scan pfn range [start,end) to find movable/migratable pages (LRU pages
- * and hugepages). We scan pfn because it's much easier than scanning over
- * linked list. This function returns the pfn of the first found movable
- * page if it's found, otherwise 0.
+ * Scan pfn range [start,end) to find movable/migratable pages (LRU pages,
+ * non-lru movable pages and hugepages). We scan pfn because it's much
+ * easier than scanning over linked list. This function returns the pfn
+ * of the first found movable page if it's found, otherwise 0.
*/
static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
{
@@ -1437,6 +1437,8 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end)
page = pfn_to_page(pfn);
if (PageLRU(page))
return pfn;
+ if (__PageMovable(page))
+ return pfn;
if (PageHuge(page)) {
if (page_huge_active(page))
return pfn;
@@ -1480,22 +1482,24 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
if (!get_page_unless_zero(page))
continue;
/*
- * We can skip free pages. And we can only deal with pages on
- * LRU.
+ * We can skip free pages. And we can deal with pages on
+ * LRU and non-lru movable pages.
*/
- ret = isolate_lru_page(page);
+ if (PageLRU(page))
+ ret = isolate_lru_page(page);
+ else
+ ret = isolate_movable_page(page, ISOLATE_UNEVICTABLE);
if (!ret) { /* Success */
put_page(page);
list_add_tail(&page->lru, &source);
move_pages--;
- inc_zone_page_state(page, NR_ISOLATED_ANON +
- page_is_file_cache(page));
-
+ if (!__PageMovable(page))
+ inc_zone_page_state(page, NR_ISOLATED_ANON +
+ page_is_file_cache(page));
} else {
#ifdef CONFIG_DEBUG_VM
- printk(KERN_ALERT "removing pfn %lx from LRU failed\n",
- pfn);
- dump_page(page, "failed to remove from LRU");
+ pr_alert("failed to isolate pfn %lx\n", pfn);
+ dump_page(page, "isolation failed");
#endif
put_page(page);
/* Because we don't have big zone->lock. we should
diff --git a/mm/migrate.c b/mm/migrate.c
index a021071eceaf..921cf12b03ce 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -75,7 +75,7 @@ int migrate_prep_local(void)
return 0;
}
-bool isolate_movable_page(struct page *page, isolate_mode_t mode)
+int isolate_movable_page(struct page *page, isolate_mode_t mode)
{
struct address_space *mapping;
@@ -126,14 +126,14 @@ bool isolate_movable_page(struct page *page, isolate_mode_t mode)
__SetPageIsolated(page);
unlock_page(page);
- return true;
+ return 0;
out_no_isolated:
unlock_page(page);
out_putpage:
put_page(page);
out:
- return false;
+ return -EBUSY;
}
/* It should be called on page which is PG_movable */
diff --git a/mm/mmap.c b/mm/mmap.c
index 2339b533f4b2..5457c5f4935b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -206,6 +206,13 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
free += global_page_state(NR_SLAB_RECLAIMABLE);
/*
+ * Part of the kernel memory, which can be released
+ * under memory pressure.
+ */
+ free += global_page_state(
+ NR_INDIRECTLY_RECLAIMABLE_BYTES) >> PAGE_SHIFT;
+
+ /*
* Leave reserved pages. The pages are not for anonymous pages.
*/
if (free <= totalreserve_pages)
diff --git a/mm/nommu.c b/mm/nommu.c
index 92be862c859b..8d75e425c21c 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1880,6 +1880,13 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
free += global_page_state(NR_SLAB_RECLAIMABLE);
/*
+ * Part of the kernel memory, which can be released
+ * under memory pressure.
+ */
+ free += global_page_state(
+ NR_INDIRECTLY_RECLAIMABLE_BYTES) >> PAGE_SHIFT;
+
+ /*
* Leave reserved pages. The pages are not for anonymous pages.
*/
if (free <= totalreserve_pages)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index c5bf17598afa..a98dae1bdcff 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2526,13 +2526,13 @@ void account_page_redirty(struct page *page)
if (mapping && mapping_cap_account_dirty(mapping)) {
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
- bool locked;
+ struct wb_lock_cookie cookie = {};
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &cookie);
current->nr_dirtied--;
dec_zone_page_state(page, NR_DIRTIED);
dec_wb_stat(wb, WB_DIRTIED);
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &cookie);
}
}
EXPORT_SYMBOL(account_page_redirty);
@@ -2638,15 +2638,15 @@ void cancel_dirty_page(struct page *page)
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
struct mem_cgroup *memcg;
- bool locked;
+ struct wb_lock_cookie cookie = {};
memcg = mem_cgroup_begin_page_stat(page);
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &cookie);
if (TestClearPageDirty(page))
account_page_cleaned(page, mapping, memcg, wb);
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &cookie);
mem_cgroup_end_page_stat(memcg);
} else {
ClearPageDirty(page);
@@ -2679,7 +2679,7 @@ int clear_page_dirty_for_io(struct page *page)
struct inode *inode = mapping->host;
struct bdi_writeback *wb;
struct mem_cgroup *memcg;
- bool locked;
+ struct wb_lock_cookie cookie = {};
/*
* Yes, Virginia, this is indeed insane.
@@ -2717,14 +2717,14 @@ int clear_page_dirty_for_io(struct page *page)
* exclusion.
*/
memcg = mem_cgroup_begin_page_stat(page);
- wb = unlocked_inode_to_wb_begin(inode, &locked);
+ wb = unlocked_inode_to_wb_begin(inode, &cookie);
if (TestClearPageDirty(page)) {
mem_cgroup_dec_page_stat(memcg, MEM_CGROUP_STAT_DIRTY);
dec_zone_page_state(page, NR_FILE_DIRTY);
dec_wb_stat(wb, WB_RECLAIMABLE);
ret = 1;
}
- unlocked_inode_to_wb_end(inode, locked);
+ unlocked_inode_to_wb_end(inode, &cookie);
mem_cgroup_end_page_stat(memcg);
return ret;
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3c3d8139f594..bad5f32a9765 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6652,8 +6652,9 @@ void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
* If @count is not zero, it is okay to include less @count unmovable pages
*
* PageLRU check without isolation or lru_lock could race so that
- * MIGRATE_MOVABLE block might include unmovable pages. It means you can't
- * expect this function should be exact.
+ * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
+ * check without lock_page also may miss some movable non-lru pages at
+ * race condition. So you can't expect this function should be exact.
*/
bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
bool skip_hwpoisoned_pages)
@@ -6709,6 +6710,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
if (skip_hwpoisoned_pages && PageHWPoison(page))
continue;
+ if (__PageMovable(page))
+ continue;
+
if (!PageLRU(page))
found++;
/*
diff --git a/mm/percpu.c b/mm/percpu.c
index d9f91253953e..c5f2a724101a 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -68,6 +68,7 @@
#include <linux/vmalloc.h>
#include <linux/workqueue.h>
#include <linux/kmemleak.h>
+#include <linux/sched.h>
#include <asm/cacheflush.h>
#include <asm/sections.h>
diff --git a/mm/slab.c b/mm/slab.c
index 8fc762c178bd..80ca19a122f3 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3942,7 +3942,8 @@ next:
next_reap_node();
out:
/* Set up the next iteration */
- schedule_delayed_work(work, round_jiffies_relative(REAPTIMEOUT_AC));
+ schedule_delayed_work_on(smp_processor_id(), work,
+ round_jiffies_relative(REAPTIMEOUT_AC));
}
#ifdef CONFIG_SLABINFO
diff --git a/mm/util.c b/mm/util.c
index d41da54e8d83..f5480eb305c7 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -80,6 +80,8 @@ EXPORT_SYMBOL(kstrdup_const);
* @s: the string to duplicate
* @max: read at most @max chars from @s
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Note: Use kmemdup_nul() instead if the size is known exactly.
*/
char *kstrndup(const char *s, size_t max, gfp_t gfp)
{
@@ -118,6 +120,28 @@ void *kmemdup(const void *src, size_t len, gfp_t gfp)
EXPORT_SYMBOL(kmemdup);
/**
+ * kmemdup_nul - Create a NUL-terminated string from unterminated data
+ * @s: The data to stringify
+ * @len: The size of the data
+ * @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ */
+char *kmemdup_nul(const char *s, size_t len, gfp_t gfp)
+{
+ char *buf;
+
+ if (!s)
+ return NULL;
+
+ buf = kmalloc_track_caller(len + 1, gfp);
+ if (buf) {
+ memcpy(buf, s, len);
+ buf[len] = '\0';
+ }
+ return buf;
+}
+EXPORT_SYMBOL(kmemdup_nul);
+
+/**
* memdup_user - duplicate memory region from user space
*
* @src: source address in user space
@@ -406,17 +430,25 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen)
int res = 0;
unsigned int len;
struct mm_struct *mm = get_task_mm(task);
+ unsigned long arg_start, arg_end, env_start, env_end;
if (!mm)
goto out;
if (!mm->arg_end)
goto out_mm; /* Shh! No looking before we're done */
- len = mm->arg_end - mm->arg_start;
+ down_read(&mm->mmap_sem);
+ arg_start = mm->arg_start;
+ arg_end = mm->arg_end;
+ env_start = mm->env_start;
+ env_end = mm->env_end;
+ up_read(&mm->mmap_sem);
+
+ len = arg_end - arg_start;
if (len > buflen)
len = buflen;
- res = access_process_vm(task, mm->arg_start, buffer, len, 0);
+ res = access_process_vm(task, arg_start, buffer, len, 0);
/*
* If the nul at the end of args has been overwritten, then
@@ -427,10 +459,10 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen)
if (len < res) {
res = len;
} else {
- len = mm->env_end - mm->env_start;
+ len = env_end - env_start;
if (len > buflen - res)
len = buflen - res;
- res += access_process_vm(task, mm->env_start,
+ res += access_process_vm(task, env_start,
buffer+res, len, 0);
res = strnlen(buffer, res);
}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5f6e29f25af9..c7fe805048da 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -267,10 +267,13 @@ EXPORT_SYMBOL(register_shrinker);
*/
void unregister_shrinker(struct shrinker *shrinker)
{
+ if (!shrinker->nr_deferred)
+ return;
down_write(&shrinker_rwsem);
list_del(&shrinker->list);
up_write(&shrinker_rwsem);
kfree(shrinker->nr_deferred);
+ shrinker->nr_deferred = NULL;
}
EXPORT_SYMBOL(unregister_shrinker);
@@ -2191,11 +2194,17 @@ static void get_scan_count(struct lruvec *lruvec, int swappiness,
}
/*
- * There is enough inactive page cache, do not reclaim
- * anything from the anonymous working set right now.
+ * If there is enough inactive page cache, i.e. if the size of the
+ * inactive list is greater than that of the active list *and* the
+ * inactive list actually has some pages to scan on this priority, we
+ * do not reclaim anything from the anonymous working set right now.
+ * Without the second condition we could end up never scanning an
+ * lruvec even if it has plenty of old anonymous pages unless the
+ * system is under heavy pressure.
*/
if (!IS_ENABLED(CONFIG_BALANCE_ANON_FILE_RECLAIM) &&
- !inactive_file_is_low(lruvec)) {
+ !inactive_file_is_low(lruvec) &&
+ get_lru_size(lruvec, LRU_INACTIVE_FILE) >> sc->priority) {
scan_balance = SCAN_FILE;
goto out;
}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6c841595b963..9ab13e3be5df 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -765,6 +765,7 @@ const char * const vmstat_text[] = {
"nr_anon_transparent_hugepages",
"nr_free_cma",
"nr_swapcache",
+ "nr_indirectly_reclaimable",
/* enum writeback_stat_item counters */
"nr_dirty_threshold",
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-27 04:32:46 +0000