summaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/backing-dev.c8
-rw-r--r--mm/filemap.c13
-rw-r--r--mm/huge_memory.c16
-rw-r--r--mm/hugetlb.c5
-rw-r--r--mm/memcontrol.c103
-rw-r--r--mm/mempolicy.c11
-rw-r--r--mm/migrate.c2
-rw-r--r--mm/nommu.c2
-rw-r--r--mm/oom_kill.c7
-rw-r--r--mm/page-writeback.c55
-rw-r--r--mm/page_alloc.c10
-rw-r--r--mm/percpu-vm.c17
-rw-r--r--mm/percpu.c68
-rw-r--r--mm/slab.c5
-rw-r--r--mm/slub.c42
-rw-r--r--mm/vmalloc.c31
-rw-r--r--mm/vmscan.c26
17 files changed, 292 insertions, 129 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index a0860640378..71034f41a2b 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -724,6 +724,14 @@ void bdi_destroy(struct backing_dev_info *bdi)
bdi_unregister(bdi);
+ /*
+ * If bdi_unregister() had already been called earlier, the
+ * wakeup_timer could still be armed because bdi_prune_sb()
+ * can race with the bdi_wakeup_thread_delayed() calls from
+ * __mark_inode_dirty().
+ */
+ del_timer_sync(&bdi->wb.wakeup_timer);
+
for (i = 0; i < NR_BDI_STAT_ITEMS; i++)
percpu_counter_destroy(&bdi->bdi_stat[i]);
diff --git a/mm/filemap.c b/mm/filemap.c
index c0018f2d50e..5f0a3c91fda 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1828,7 +1828,7 @@ repeat:
page = __page_cache_alloc(gfp | __GFP_COLD);
if (!page)
return ERR_PTR(-ENOMEM);
- err = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL);
+ err = add_to_page_cache_lru(page, mapping, index, gfp);
if (unlikely(err)) {
page_cache_release(page);
if (err == -EEXIST)
@@ -1925,10 +1925,7 @@ static struct page *wait_on_page_read(struct page *page)
* @gfp: the page allocator flags to use if allocating
*
* This is the same as "read_mapping_page(mapping, index, NULL)", but with
- * any new page allocations done using the specified allocation flags. Note
- * that the Radix tree operations will still use GFP_KERNEL, so you can't
- * expect to do this atomically or anything like that - but you can pass in
- * other page requirements.
+ * any new page allocations done using the specified allocation flags.
*
* If the page does not get brought uptodate, return -EIO.
*/
@@ -2407,7 +2404,6 @@ static ssize_t generic_perform_write(struct file *file,
iov_iter_count(i));
again:
-
/*
* Bring in the user page that we will copy from _first_.
* Otherwise there's a nasty deadlock on copying from the
@@ -2463,7 +2459,10 @@ again:
written += copied;
balance_dirty_pages_ratelimited(mapping);
-
+ if (fatal_signal_pending(current)) {
+ status = -EINTR;
+ break;
+ }
} while (iov_iter_count(i));
return written ? written : status;
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 4298abaae15..36b3d988b4e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2259,12 +2259,8 @@ static void khugepaged_do_scan(struct page **hpage)
static void khugepaged_alloc_sleep(void)
{
- DEFINE_WAIT(wait);
- add_wait_queue(&khugepaged_wait, &wait);
- schedule_timeout_interruptible(
- msecs_to_jiffies(
- khugepaged_alloc_sleep_millisecs));
- remove_wait_queue(&khugepaged_wait, &wait);
+ wait_event_freezable_timeout(khugepaged_wait, false,
+ msecs_to_jiffies(khugepaged_alloc_sleep_millisecs));
}
#ifndef CONFIG_NUMA
@@ -2313,14 +2309,10 @@ static void khugepaged_loop(void)
if (unlikely(kthread_should_stop()))
break;
if (khugepaged_has_work()) {
- DEFINE_WAIT(wait);
if (!khugepaged_scan_sleep_millisecs)
continue;
- add_wait_queue(&khugepaged_wait, &wait);
- schedule_timeout_interruptible(
- msecs_to_jiffies(
- khugepaged_scan_sleep_millisecs));
- remove_wait_queue(&khugepaged_wait, &wait);
+ wait_event_freezable_timeout(khugepaged_wait, false,
+ msecs_to_jiffies(khugepaged_scan_sleep_millisecs));
} else if (khugepaged_enabled())
wait_event_freezable(khugepaged_wait,
khugepaged_wait_event());
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index dae27ba3be2..2316840b337 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -576,6 +576,7 @@ static void prep_compound_gigantic_page(struct page *page, unsigned long order)
__SetPageHead(page);
for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
__SetPageTail(p);
+ set_page_count(p, 0);
p->first_page = page;
}
}
@@ -900,7 +901,6 @@ retry:
h->resv_huge_pages += delta;
ret = 0;
- spin_unlock(&hugetlb_lock);
/* Free the needed pages to the hugetlb pool */
list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
if ((--needed) < 0)
@@ -914,6 +914,7 @@ retry:
VM_BUG_ON(page_count(page));
enqueue_huge_page(h, page);
}
+ spin_unlock(&hugetlb_lock);
/* Free unnecessary surplus pages to the buddy allocator */
free:
@@ -2422,6 +2423,8 @@ retry_avoidcopy:
* anon_vma prepared.
*/
if (unlikely(anon_vma_prepare(vma))) {
+ page_cache_release(new_page);
+ page_cache_release(old_page);
/* Caller expects lock to be held */
spin_lock(&mm->page_table_lock);
return VM_FAULT_OOM;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6aff93c98ac..94da8ee9e2c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -50,6 +50,8 @@
#include <linux/cpu.h>
#include <linux/oom.h>
#include "internal.h"
+#include <net/sock.h>
+#include <net/tcp_memcontrol.h>
#include <asm/uaccess.h>
@@ -286,6 +288,10 @@ struct mem_cgroup {
*/
struct mem_cgroup_stat_cpu nocpu_base;
spinlock_t pcp_counter_lock;
+
+#ifdef CONFIG_INET
+ struct tcp_memcontrol tcp_mem;
+#endif
};
/* Stuffs for move charges at task migration. */
@@ -365,7 +371,58 @@ enum charge_type {
static void mem_cgroup_get(struct mem_cgroup *memcg);
static void mem_cgroup_put(struct mem_cgroup *memcg);
-static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
+
+/* Writing them here to avoid exposing memcg's inner layout */
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_INET
+#include <net/sock.h>
+#include <net/ip.h>
+
+static bool mem_cgroup_is_root(struct mem_cgroup *memcg);
+void sock_update_memcg(struct sock *sk)
+{
+ /* A socket spends its whole life in the same cgroup */
+ if (sk->sk_cgrp) {
+ WARN_ON(1);
+ return;
+ }
+ if (static_branch(&memcg_socket_limit_enabled)) {
+ struct mem_cgroup *memcg;
+
+ BUG_ON(!sk->sk_prot->proto_cgroup);
+
+ rcu_read_lock();
+ memcg = mem_cgroup_from_task(current);
+ if (!mem_cgroup_is_root(memcg)) {
+ mem_cgroup_get(memcg);
+ sk->sk_cgrp = sk->sk_prot->proto_cgroup(memcg);
+ }
+ rcu_read_unlock();
+ }
+}
+EXPORT_SYMBOL(sock_update_memcg);
+
+void sock_release_memcg(struct sock *sk)
+{
+ if (static_branch(&memcg_socket_limit_enabled) && sk->sk_cgrp) {
+ struct mem_cgroup *memcg;
+ WARN_ON(!sk->sk_cgrp->memcg);
+ memcg = sk->sk_cgrp->memcg;
+ mem_cgroup_put(memcg);
+ }
+}
+
+struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
+{
+ if (!memcg || mem_cgroup_is_root(memcg))
+ return NULL;
+
+ return &memcg->tcp_mem.cg_proto;
+}
+EXPORT_SYMBOL(tcp_proto_cgroup);
+#endif /* CONFIG_INET */
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+
static void drain_all_stock_async(struct mem_cgroup *memcg);
static struct mem_cgroup_per_zone *
@@ -745,7 +802,7 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
preempt_enable();
}
-static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
+struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
{
return container_of(cgroup_subsys_state(cont,
mem_cgroup_subsys_id), struct mem_cgroup,
@@ -4612,6 +4669,36 @@ static int mem_control_numa_stat_open(struct inode *unused, struct file *file)
}
#endif /* CONFIG_NUMA */
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+ /*
+ * Part of this would be better living in a separate allocation
+ * function, leaving us with just the cgroup tree population work.
+ * We, however, depend on state such as network's proto_list that
+ * is only initialized after cgroup creation. I found the less
+ * cumbersome way to deal with it to defer it all to populate time
+ */
+ return mem_cgroup_sockets_init(cont, ss);
+};
+
+static void kmem_cgroup_destroy(struct cgroup_subsys *ss,
+ struct cgroup *cont)
+{
+ mem_cgroup_sockets_destroy(cont, ss);
+}
+#else
+static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+ return 0;
+}
+
+static void kmem_cgroup_destroy(struct cgroup_subsys *ss,
+ struct cgroup *cont)
+{
+}
+#endif
+
static struct cftype mem_cgroup_files[] = {
{
.name = "usage_in_bytes",
@@ -4843,12 +4930,13 @@ static void mem_cgroup_put(struct mem_cgroup *memcg)
/*
* Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
*/
-static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
+struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
{
if (!memcg->res.parent)
return NULL;
return mem_cgroup_from_res_counter(memcg->res.parent, res);
}
+EXPORT_SYMBOL(parent_mem_cgroup);
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
static void __init enable_swap_cgroup(void)
@@ -4907,9 +4995,9 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
int cpu;
enable_swap_cgroup();
parent = NULL;
- root_mem_cgroup = memcg;
if (mem_cgroup_soft_limit_tree_init())
goto free_out;
+ root_mem_cgroup = memcg;
for_each_possible_cpu(cpu) {
struct memcg_stock_pcp *stock =
&per_cpu(memcg_stock, cpu);
@@ -4948,7 +5036,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
return &memcg->css;
free_out:
__mem_cgroup_free(memcg);
- root_mem_cgroup = NULL;
return ERR_PTR(error);
}
@@ -4965,6 +5052,8 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss,
{
struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ kmem_cgroup_destroy(ss, cont);
+
mem_cgroup_put(memcg);
}
@@ -4978,6 +5067,10 @@ static int mem_cgroup_populate(struct cgroup_subsys *ss,
if (!ret)
ret = register_memsw_files(cont, ss);
+
+ if (!ret)
+ ret = register_kmem_files(cont, ss);
+
return ret;
}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index adc39548181..c3fdbcb1765 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -636,6 +636,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
struct vm_area_struct *prev;
struct vm_area_struct *vma;
int err = 0;
+ pgoff_t pgoff;
unsigned long vmstart;
unsigned long vmend;
@@ -643,13 +644,21 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
if (!vma || vma->vm_start > start)
return -EFAULT;
+ if (start > vma->vm_start)
+ prev = vma;
+
for (; vma && vma->vm_start < end; prev = vma, vma = next) {
next = vma->vm_next;
vmstart = max(start, vma->vm_start);
vmend = min(end, vma->vm_end);
+ if (mpol_equal(vma_policy(vma), new_pol))
+ continue;
+
+ pgoff = vma->vm_pgoff +
+ ((vmstart - vma->vm_start) >> PAGE_SHIFT);
prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
- vma->anon_vma, vma->vm_file, vma->vm_pgoff,
+ vma->anon_vma, vma->vm_file, pgoff,
new_pol);
if (prev) {
vma = prev;
diff --git a/mm/migrate.c b/mm/migrate.c
index 578e29174fa..177aca424a0 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -871,9 +871,9 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
if (anon_vma)
put_anon_vma(anon_vma);
-out:
unlock_page(hpage);
+out:
if (rc != -EAGAIN) {
list_del(&hpage->lru);
put_page(hpage);
diff --git a/mm/nommu.c b/mm/nommu.c
index 73419c55eda..b982290fd96 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -454,7 +454,7 @@ void __attribute__((weak)) vmalloc_sync_all(void)
* between processes, it syncs the pagetable across all
* processes.
*/
-struct vm_struct *alloc_vm_area(size_t size)
+struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
{
BUG();
return NULL;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 471dedb463a..069b64e521f 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -176,7 +176,7 @@ static bool oom_unkillable_task(struct task_struct *p,
unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
const nodemask_t *nodemask, unsigned long totalpages)
{
- int points;
+ long points;
if (oom_unkillable_task(p, mem, nodemask))
return 0;
@@ -185,6 +185,11 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
if (!p)
return 0;
+ if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+ task_unlock(p);
+ return 0;
+ }
+
/*
* The memory controller may have a limit of 0 bytes, so avoid a divide
* by zero, if necessary.
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index a3278f00523..50f08241f98 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -128,7 +128,6 @@ unsigned long global_dirty_limit;
*
*/
static struct prop_descriptor vm_completions;
-static struct prop_descriptor vm_dirties;
/*
* couple the period to the dirty_ratio:
@@ -154,7 +153,6 @@ static void update_completion_period(void)
{
int shift = calc_period_shift();
prop_change_shift(&vm_completions, shift);
- prop_change_shift(&vm_dirties, shift);
writeback_set_ratelimit();
}
@@ -235,11 +233,6 @@ void bdi_writeout_inc(struct backing_dev_info *bdi)
}
EXPORT_SYMBOL_GPL(bdi_writeout_inc);
-void task_dirty_inc(struct task_struct *tsk)
-{
- prop_inc_single(&vm_dirties, &tsk->dirties);
-}
-
/*
* Obtain an accurate fraction of the BDI's portion.
*/
@@ -418,8 +411,13 @@ void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
*
* Returns @bdi's dirty limit in pages. The term "dirty" in the context of
* dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages.
- * And the "limit" in the name is not seriously taken as hard limit in
- * balance_dirty_pages().
+ *
+ * Note that balance_dirty_pages() will only seriously take it as a hard limit
+ * when sleeping max_pause per page is not enough to keep the dirty pages under
+ * control. For example, when the device is completely stalled due to some error
+ * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key.
+ * In the other normal situations, it acts more gently by throttling the tasks
+ * more (rather than completely block them) when the bdi dirty pages go high.
*
* It allocates high/low dirty limits to fast/slow devices, in order to prevent
* - starving fast devices
@@ -601,6 +599,13 @@ static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
*/
if (unlikely(bdi_thresh > thresh))
bdi_thresh = thresh;
+ /*
+ * It's very possible that bdi_thresh is close to 0 not because the
+ * device is slow, but that it has remained inactive for long time.
+ * Honour such devices a reasonable good (hopefully IO efficient)
+ * threshold, so that the occasional writes won't be blocked and active
+ * writes can rampup the threshold quickly.
+ */
bdi_thresh = max(bdi_thresh, (limit - dirty) / 8);
/*
* scale global setpoint to bdi's:
@@ -984,8 +989,7 @@ static unsigned long bdi_max_pause(struct backing_dev_info *bdi,
*
* 8 serves as the safety ratio.
*/
- if (bdi_dirty)
- t = min(t, bdi_dirty * HZ / (8 * bw + 1));
+ t = min(t, bdi_dirty * HZ / (8 * bw + 1));
/*
* The pause time will be settled within range (max_pause/4, max_pause).
@@ -1133,17 +1137,30 @@ pause:
pages_dirtied,
pause,
start_time);
- __set_current_state(TASK_UNINTERRUPTIBLE);
+ __set_current_state(TASK_KILLABLE);
io_schedule_timeout(pause);
- dirty_thresh = hard_dirty_limit(dirty_thresh);
/*
- * max-pause area. If dirty exceeded but still within this
- * area, no need to sleep for more than 200ms: (a) 8 pages per
- * 200ms is typically more than enough to curb heavy dirtiers;
- * (b) the pause time limit makes the dirtiers more responsive.
+ * This is typically equal to (nr_dirty < dirty_thresh) and can
+ * also keep "1000+ dd on a slow USB stick" under control.
*/
- if (nr_dirty < dirty_thresh)
+ if (task_ratelimit)
+ break;
+
+ /*
+ * In the case of an unresponding NFS server and the NFS dirty
+ * pages exceeds dirty_thresh, give the other good bdi's a pipe
+ * to go through, so that tasks on them still remain responsive.
+ *
+ * In theory 1 page is enough to keep the comsumer-producer
+ * pipe going: the flusher cleans 1 page => the task dirties 1
+ * more page. However bdi_dirty has accounting errors. So use
+ * the larger and more IO friendly bdi_stat_error.
+ */
+ if (bdi_dirty <= bdi_stat_error(bdi))
+ break;
+
+ if (fatal_signal_pending(current))
break;
}
@@ -1395,7 +1412,6 @@ void __init page_writeback_init(void)
shift = calc_period_shift();
prop_descriptor_init(&vm_completions, shift);
- prop_descriptor_init(&vm_dirties, shift);
}
/**
@@ -1724,7 +1740,6 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
__inc_zone_page_state(page, NR_DIRTIED);
__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
__inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED);
- task_dirty_inc(current);
task_io_account_write(PAGE_CACHE_SIZE);
}
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9dd443d89d8..2b8ba3aebf6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -356,8 +356,8 @@ void prep_compound_page(struct page *page, unsigned long order)
__SetPageHead(page);
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
-
__SetPageTail(p);
+ set_page_count(p, 0);
p->first_page = page;
}
}
@@ -3377,9 +3377,15 @@ static void setup_zone_migrate_reserve(struct zone *zone)
unsigned long block_migratetype;
int reserve;
- /* Get the start pfn, end pfn and the number of blocks to reserve */
+ /*
+ * Get the start pfn, end pfn and the number of blocks to reserve
+ * We have to be careful to be aligned to pageblock_nr_pages to
+ * make sure that we always check pfn_valid for the first page in
+ * the block.
+ */
start_pfn = zone->zone_start_pfn;
end_pfn = start_pfn + zone->spanned_pages;
+ start_pfn = roundup(start_pfn, pageblock_nr_pages);
reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
pageblock_order;
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index ea534960a04..12a48a88c0d 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -50,14 +50,13 @@ static struct page **pcpu_get_pages_and_bitmap(struct pcpu_chunk *chunk,
if (!pages || !bitmap) {
if (may_alloc && !pages)
- pages = pcpu_mem_alloc(pages_size);
+ pages = pcpu_mem_zalloc(pages_size);
if (may_alloc && !bitmap)
- bitmap = pcpu_mem_alloc(bitmap_size);
+ bitmap = pcpu_mem_zalloc(bitmap_size);
if (!pages || !bitmap)
return NULL;
}
- memset(pages, 0, pages_size);
bitmap_copy(bitmap, chunk->populated, pcpu_unit_pages);
*bitmapp = bitmap;
@@ -143,8 +142,8 @@ static void pcpu_pre_unmap_flush(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
flush_cache_vunmap(
- pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
- pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+ pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+ pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}
static void __pcpu_unmap_pages(unsigned long addr, int nr_pages)
@@ -206,8 +205,8 @@ static void pcpu_post_unmap_tlb_flush(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
flush_tlb_kernel_range(
- pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
- pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+ pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+ pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}
static int __pcpu_map_pages(unsigned long addr, struct page **pages,
@@ -284,8 +283,8 @@ static void pcpu_post_map_flush(struct pcpu_chunk *chunk,
int page_start, int page_end)
{
flush_cache_vmap(
- pcpu_chunk_addr(chunk, pcpu_first_unit_cpu, page_start),
- pcpu_chunk_addr(chunk, pcpu_last_unit_cpu, page_end));
+ pcpu_chunk_addr(chunk, pcpu_low_unit_cpu, page_start),
+ pcpu_chunk_addr(chunk, pcpu_high_unit_cpu, page_end));
}
/**
diff --git a/mm/percpu.c b/mm/percpu.c
index bf80e55dbed..716eb4acf2f 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -116,9 +116,9 @@ static int pcpu_atom_size __read_mostly;
static int pcpu_nr_slots __read_mostly;
static size_t pcpu_chunk_struct_size __read_mostly;
-/* cpus with the lowest and highest unit numbers */
-static unsigned int pcpu_first_unit_cpu __read_mostly;
-static unsigned int pcpu_last_unit_cpu __read_mostly;
+/* cpus with the lowest and highest unit addresses */
+static unsigned int pcpu_low_unit_cpu __read_mostly;
+static unsigned int pcpu_high_unit_cpu __read_mostly;
/* the address of the first chunk which starts with the kernel static area */
void *pcpu_base_addr __read_mostly;
@@ -273,11 +273,11 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk,
(rs) = (re) + 1, pcpu_next_pop((chunk), &(rs), &(re), (end)))
/**
- * pcpu_mem_alloc - allocate memory
+ * pcpu_mem_zalloc - allocate memory
* @size: bytes to allocate
*
* Allocate @size bytes. If @size is smaller than PAGE_SIZE,
- * kzalloc() is used; otherwise, vmalloc() is used. The returned
+ * kzalloc() is used; otherwise, vzalloc() is used. The returned
* memory is always zeroed.
*
* CONTEXT:
@@ -286,7 +286,7 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk,
* RETURNS:
* Pointer to the allocated area on success, NULL on failure.
*/
-static void *pcpu_mem_alloc(size_t size)
+static void *pcpu_mem_zalloc(size_t size)
{
if (WARN_ON_ONCE(!slab_is_available()))
return NULL;
@@ -302,7 +302,7 @@ static void *pcpu_mem_alloc(size_t size)
* @ptr: memory to free
* @size: size of the area
*
- * Free @ptr. @ptr should have been allocated using pcpu_mem_alloc().
+ * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc().
*/
static void pcpu_mem_free(void *ptr, size_t size)
{
@@ -384,7 +384,7 @@ static int pcpu_extend_area_map(struct pcpu_chunk *chunk, int new_alloc)
size_t old_size = 0, new_size = new_alloc * sizeof(new[0]);
unsigned long flags;
- new = pcpu_mem_alloc(new_size);
+ new = pcpu_mem_zalloc(new_size);
if (!new)
return -ENOMEM;
@@ -604,11 +604,12 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void)
{
struct pcpu_chunk *chunk;
- chunk = pcpu_mem_alloc(pcpu_chunk_struct_size);
+ chunk = pcpu_mem_zalloc(pcpu_chunk_struct_size);
if (!chunk)
return NULL;
- chunk->map = pcpu_mem_alloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0]));
+ chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC *
+ sizeof(chunk->map[0]));
if (!chunk->map) {
kfree(chunk);
return NULL;
@@ -977,6 +978,17 @@ bool is_kernel_percpu_address(unsigned long addr)
* address. The caller is responsible for ensuring @addr stays valid
* until this function finishes.
*
+ * percpu allocator has special setup for the first chunk, which currently
+ * supports either embedding in linear address space or vmalloc mapping,
+ * and, from the second one, the backing allocator (currently either vm or
+ * km) provides translation.
+ *
+ * The addr can be tranlated simply without checking if it falls into the
+ * first chunk. But the current code reflects better how percpu allocator
+ * actually works, and the verification can discover both bugs in percpu
+ * allocator itself and per_cpu_ptr_to_phys() callers. So we keep current
+ * code.
+ *
* RETURNS:
* The physical address for @addr.
*/
@@ -984,19 +996,19 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr)
{
void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
bool in_first_chunk = false;
- unsigned long first_start, first_end;
+ unsigned long first_low, first_high;
unsigned int cpu;
/*
- * The following test on first_start/end isn't strictly
+ * The following test on unit_low/high isn't strictly
* necessary but will speed up lookups of addresses which
* aren't in the first chunk.
*/
- first_start = pcpu_chunk_addr(pcpu_first_chunk, pcpu_first_unit_cpu, 0);
- first_end = pcpu_chunk_addr(pcpu_first_chunk, pcpu_last_unit_cpu,
- pcpu_unit_pages);
- if ((unsigned long)addr >= first_start &&
- (unsigned long)addr < first_end) {
+ first_low = pcpu_chunk_addr(pcpu_first_chunk, pcpu_low_unit_cpu, 0);
+ first_high = pcpu_chunk_addr(pcpu_first_chunk, pcpu_high_unit_cpu,
+ pcpu_unit_pages);
+ if ((unsigned long)addr >= first_low &&
+ (unsigned long)addr < first_high) {
for_each_possible_cpu(cpu) {
void *start = per_cpu_ptr(base, cpu);
@@ -1011,9 +1023,11 @@ phys_addr_t per_cpu_ptr_to_phys(void *addr)
if (!is_vmalloc_addr(addr))
return __pa(addr);
else
- return page_to_phys(vmalloc_to_page(addr));
+ return page_to_phys(vmalloc_to_page(addr)) +
+ offset_in_page(addr);
} else
- return page_to_phys(pcpu_addr_to_page(addr));
+ return page_to_phys(pcpu_addr_to_page(addr)) +
+ offset_in_page(addr);
}
/**
@@ -1233,7 +1247,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
for (cpu = 0; cpu < nr_cpu_ids; cpu++)
unit_map[cpu] = UINT_MAX;
- pcpu_first_unit_cpu = NR_CPUS;
+
+ pcpu_low_unit_cpu = NR_CPUS;
+ pcpu_high_unit_cpu = NR_CPUS;
for (group = 0, unit = 0; group < ai->nr_groups; group++, unit += i) {
const struct pcpu_group_info *gi = &ai->groups[group];
@@ -1253,9 +1269,13 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
unit_map[cpu] = unit + i;
unit_off[cpu] = gi->base_offset + i * ai->unit_size;
- if (pcpu_first_unit_cpu == NR_CPUS)
- pcpu_first_unit_cpu = cpu;
- pcpu_last_unit_cpu = cpu;
+ /* determine low/high unit_cpu */
+ if (pcpu_low_unit_cpu == NR_CPUS ||
+ unit_off[cpu] < unit_off[pcpu_low_unit_cpu])
+ pcpu_low_unit_cpu = cpu;
+ if (pcpu_high_unit_cpu == NR_CPUS ||
+ unit_off[cpu] > unit_off[pcpu_high_unit_cpu])
+ pcpu_high_unit_cpu = cpu;
}
}
pcpu_nr_units = unit;
@@ -1889,7 +1909,7 @@ void __init percpu_init_late(void)
BUILD_BUG_ON(size > PAGE_SIZE);
- map = pcpu_mem_alloc(size);
+ map = pcpu_mem_zalloc(size);
BUG_ON(!map);
spin_lock_irqsave(&pcpu_lock, flags);
diff --git a/mm/slab.c b/mm/slab.c
index 708efe88615..83311c9aaf9 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -595,6 +595,7 @@ static enum {
PARTIAL_AC,
PARTIAL_L3,
EARLY,
+ LATE,
FULL
} g_cpucache_up;
@@ -671,7 +672,7 @@ static void init_node_lock_keys(int q)
{
struct cache_sizes *s = malloc_sizes;
- if (g_cpucache_up != FULL)
+ if (g_cpucache_up < LATE)
return;
for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
@@ -1666,6 +1667,8 @@ void __init kmem_cache_init_late(void)
{
struct kmem_cache *cachep;
+ g_cpucache_up = LATE;
+
/* Annotate slab for lockdep -- annotate the malloc caches */
init_lock_keys();
diff --git a/mm/slub.c b/mm/slub.c
index 7d2a996c307..ed3334d9b6d 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1862,7 +1862,7 @@ static void unfreeze_partials(struct kmem_cache *s)
{
struct kmem_cache_node *n = NULL;
struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
- struct page *page;
+ struct page *page, *discard_page = NULL;
while ((page = c->partial)) {
enum slab_modes { M_PARTIAL, M_FREE };
@@ -1904,7 +1904,8 @@ static void unfreeze_partials(struct kmem_cache *s)
if (l == M_PARTIAL)
remove_partial(n, page);
else
- add_partial(n, page, 1);
+ add_partial(n, page,
+ DEACTIVATE_TO_TAIL);
l = m;
}
@@ -1915,14 +1916,22 @@ static void unfreeze_partials(struct kmem_cache *s)
"unfreezing slab"));
if (m == M_FREE) {
- stat(s, DEACTIVATE_EMPTY);
- discard_slab(s, page);
- stat(s, FREE_SLAB);
+ page->next = discard_page;
+ discard_page = page;
}
}
if (n)
spin_unlock(&n->list_lock);
+
+ while (discard_page) {
+ page = discard_page;
+ discard_page = discard_page->next;
+
+ stat(s, DEACTIVATE_EMPTY);
+ discard_slab(s, page);
+ stat(s, FREE_SLAB);
+ }
}
/*
@@ -1969,7 +1978,7 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
page->pobjects = pobjects;
page->next = oldpage;
- } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
+ } while (irqsafe_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
stat(s, CPU_PARTIAL_FREE);
return pobjects;
}
@@ -4435,30 +4444,31 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
for_each_possible_cpu(cpu) {
struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
+ int node = ACCESS_ONCE(c->node);
struct page *page;
- if (!c || c->node < 0)
+ if (node < 0)
continue;
-
- if (c->page) {
- if (flags & SO_TOTAL)
- x = c->page->objects;
+ page = ACCESS_ONCE(c->page);
+ if (page) {
+ if (flags & SO_TOTAL)
+ x = page->objects;
else if (flags & SO_OBJECTS)
- x = c->page->inuse;
+ x = page->inuse;
else
x = 1;
total += x;
- nodes[c->node] += x;
+ nodes[node] += x;
}
page = c->partial;
if (page) {
x = page->pobjects;
- total += x;
- nodes[c->node] += x;
+ total += x;
+ nodes[node] += x;
}
- per_cpu[c->node]++;
+ per_cpu[node]++;
}
}
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index b669aa6f6ca..27be2f0d4cb 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1290,7 +1290,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
unsigned long align, unsigned long flags, unsigned long start,
unsigned long end, int node, gfp_t gfp_mask, void *caller)
{
- static struct vmap_area *va;
+ struct vmap_area *va;
struct vm_struct *area;
BUG_ON(in_interrupt());
@@ -1633,6 +1633,8 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align,
goto fail;
addr = __vmalloc_area_node(area, gfp_mask, prot, node, caller);
+ if (!addr)
+ return NULL;
/*
* In this function, newly allocated vm_struct is not added
@@ -2141,23 +2143,30 @@ void __attribute__((weak)) vmalloc_sync_all(void)
static int f(pte_t *pte, pgtable_t table, unsigned long addr, void *data)
{
- /* apply_to_page_range() does all the hard work. */
+ pte_t ***p = data;
+
+ if (p) {
+ *(*p) = pte;
+ (*p)++;
+ }
return 0;
}
/**
* alloc_vm_area - allocate a range of kernel address space
* @size: size of the area
+ * @ptes: returns the PTEs for the address space
*
* Returns: NULL on failure, vm_struct on success
*
* This function reserves a range of kernel address space, and
* allocates pagetables to map that range. No actual mappings
- * are created. If the kernel address space is not shared
- * between processes, it syncs the pagetable across all
- * processes.
+ * are created.
+ *
+ * If @ptes is non-NULL, pointers to the PTEs (in init_mm)
+ * allocated for the VM area are returned.
*/
-struct vm_struct *alloc_vm_area(size_t size)
+struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes)
{
struct vm_struct *area;
@@ -2171,19 +2180,11 @@ struct vm_struct *alloc_vm_area(size_t size)
* of kernel virtual address space and mapped into init_mm.
*/
if (apply_to_page_range(&init_mm, (unsigned long)area->addr,
- area->size, f, NULL)) {
+ size, f, ptes ? &ptes : NULL)) {
free_vm_area(area);
return NULL;
}
- /*
- * If the allocated address space is passed to a hypercall
- * before being used then we cannot rely on a page fault to
- * trigger an update of the page tables. So sync all the page
- * tables here.
- */
- vmalloc_sync_all();
-
return area;
}
EXPORT_SYMBOL_GPL(alloc_vm_area);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a1893c05079..f54a05b7a61 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -183,7 +183,7 @@ static unsigned long zone_nr_lru_pages(struct zone *zone,
*/
void register_shrinker(struct shrinker *shrinker)
{
- shrinker->nr = 0;
+ atomic_long_set(&shrinker->nr_in_batch, 0);
down_write(&shrinker_rwsem);
list_add_tail(&shrinker->list, &shrinker_list);
up_write(&shrinker_rwsem);
@@ -247,25 +247,26 @@ unsigned long shrink_slab(struct shrink_control *shrink,
list_for_each_entry(shrinker, &shrinker_list, list) {
unsigned long long delta;
- unsigned long total_scan;
- unsigned long max_pass;
+ long total_scan;
+ long max_pass;
int shrink_ret = 0;
long nr;
long new_nr;
long batch_size = shrinker->batch ? shrinker->batch
: SHRINK_BATCH;
+ max_pass = do_shrinker_shrink(shrinker, shrink, 0);
+ if (max_pass <= 0)
+ continue;
+
/*
* copy the current shrinker scan count into a local variable
* and zero it so that other concurrent shrinker invocations
* don't also do this scanning work.
*/
- do {
- nr = shrinker->nr;
- } while (cmpxchg(&shrinker->nr, nr, 0) != nr);
+ nr = atomic_long_xchg(&shrinker->nr_in_batch, 0);
total_scan = nr;
- max_pass = do_shrinker_shrink(shrinker, shrink, 0);
delta = (4 * nr_pages_scanned) / shrinker->seeks;
delta *= max_pass;
do_div(delta, lru_pages + 1);
@@ -325,12 +326,11 @@ unsigned long shrink_slab(struct shrink_control *shrink,
* manner that handles concurrent updates. If we exhausted the
* scan, there is no need to do an update.
*/
- do {
- nr = shrinker->nr;
- new_nr = total_scan + nr;
- if (total_scan <= 0)
- break;
- } while (cmpxchg(&shrinker->nr, nr, new_nr) != nr);
+ if (total_scan > 0)
+ new_nr = atomic_long_add_return(total_scan,
+ &shrinker->nr_in_batch);
+ else
+ new_nr = atomic_long_read(&shrinker->nr_in_batch);
trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-12-15 01:17:13 +0000