summaryrefslogtreecommitdiff
path: root/mm/memcontrol.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/memcontrol.c')
-rw-r--r--mm/memcontrol.c128
1 files changed, 98 insertions, 30 deletions
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a1a35c12635e..ab457f0394ab 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -63,6 +63,7 @@
#include <linux/resume_user_mode.h>
#include <linux/psi.h>
#include <linux/seq_buf.h>
+#include <linux/parser.h>
#include "internal.h"
#include <net/sock.h>
#include <net/ip.h>
@@ -661,8 +662,10 @@ static const unsigned int memcg_vm_event_stat[] = {
PGPGOUT,
PGSCAN_KSWAPD,
PGSCAN_DIRECT,
+ PGSCAN_KHUGEPAGED,
PGSTEAL_KSWAPD,
PGSTEAL_DIRECT,
+ PGSTEAL_KHUGEPAGED,
PGFAULT,
PGMAJFAULT,
PGREFILL,
@@ -1219,7 +1222,7 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
* cgroup root (root_mem_cgroup). So we have to handle
* dead_memcg from cgroup root separately.
*/
- if (last != root_mem_cgroup)
+ if (!mem_cgroup_is_root(last))
__invalidate_reclaim_iterators(root_mem_cgroup,
dead_memcg);
}
@@ -1243,7 +1246,7 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
struct mem_cgroup *iter;
int ret = 0;
- BUG_ON(memcg == root_mem_cgroup);
+ BUG_ON(mem_cgroup_is_root(memcg));
for_each_mem_cgroup_tree(iter, memcg) {
struct css_task_iter it;
@@ -1272,7 +1275,7 @@ void lruvec_memcg_debug(struct lruvec *lruvec, struct folio *folio)
memcg = folio_memcg(folio);
if (!memcg)
- VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != root_mem_cgroup, folio);
+ VM_BUG_ON_FOLIO(!mem_cgroup_is_root(lruvec_memcg(lruvec)), folio);
else
VM_BUG_ON_FOLIO(lruvec_memcg(lruvec) != memcg, folio);
}
@@ -1574,10 +1577,12 @@ static void memory_stat_format(struct mem_cgroup *memcg, char *buf, int bufsize)
/* Accumulated memory events */
seq_buf_printf(&s, "pgscan %lu\n",
memcg_events(memcg, PGSCAN_KSWAPD) +
- memcg_events(memcg, PGSCAN_DIRECT));
+ memcg_events(memcg, PGSCAN_DIRECT) +
+ memcg_events(memcg, PGSCAN_KHUGEPAGED));
seq_buf_printf(&s, "pgsteal %lu\n",
memcg_events(memcg, PGSTEAL_KSWAPD) +
- memcg_events(memcg, PGSTEAL_DIRECT));
+ memcg_events(memcg, PGSTEAL_DIRECT) +
+ memcg_events(memcg, PGSTEAL_KHUGEPAGED));
for (i = 0; i < ARRAY_SIZE(memcg_vm_event_stat); i++) {
if (memcg_vm_event_stat[i] == PGPGIN ||
@@ -2036,7 +2041,7 @@ struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
rcu_read_lock();
memcg = mem_cgroup_from_task(victim);
- if (memcg == root_mem_cgroup)
+ if (mem_cgroup_is_root(memcg))
goto out;
/*
@@ -2388,7 +2393,8 @@ static unsigned long reclaim_high(struct mem_cgroup *memcg,
psi_memstall_enter(&pflags);
nr_reclaimed += try_to_free_mem_cgroup_pages(memcg, nr_pages,
gfp_mask,
- MEMCG_RECLAIM_MAY_SWAP);
+ MEMCG_RECLAIM_MAY_SWAP,
+ NULL);
psi_memstall_leave(&pflags);
} while ((memcg = parent_mem_cgroup(memcg)) &&
!mem_cgroup_is_root(memcg));
@@ -2679,7 +2685,8 @@ retry:
psi_memstall_enter(&pflags);
nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
- gfp_mask, reclaim_options);
+ gfp_mask, reclaim_options,
+ NULL);
psi_memstall_leave(&pflags);
if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
@@ -2995,7 +3002,7 @@ static struct obj_cgroup *__get_obj_cgroup_from_memcg(struct mem_cgroup *memcg)
{
struct obj_cgroup *objcg = NULL;
- for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) {
+ for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
objcg = rcu_dereference(memcg->objcg);
if (objcg && obj_cgroup_tryget(objcg))
break;
@@ -3499,7 +3506,8 @@ static int mem_cgroup_resize_max(struct mem_cgroup *memcg,
}
if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
- memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) {
+ memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP,
+ NULL)) {
ret = -EBUSY;
break;
}
@@ -3610,7 +3618,8 @@ static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
return -EINTR;
if (!try_to_free_mem_cgroup_pages(memcg, 1, GFP_KERNEL,
- MEMCG_RECLAIM_MAY_SWAP))
+ MEMCG_RECLAIM_MAY_SWAP,
+ NULL))
nr_retries--;
}
@@ -4832,6 +4841,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
unsigned int efd, cfd;
struct fd efile;
struct fd cfile;
+ struct dentry *cdentry;
const char *name;
char *endp;
int ret;
@@ -4886,6 +4896,16 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
goto out_put_cfile;
/*
+ * The control file must be a regular cgroup1 file. As a regular cgroup
+ * file can't be renamed, it's safe to access its name afterwards.
+ */
+ cdentry = cfile.file->f_path.dentry;
+ if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) {
+ ret = -EINVAL;
+ goto out_put_cfile;
+ }
+
+ /*
* Determine the event callbacks and set them in @event. This used
* to be done via struct cftype but cgroup core no longer knows
* about these events. The following is crude but the whole thing
@@ -4893,7 +4913,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
*
* DO NOT ADD NEW FILES.
*/
- name = cfile.file->f_path.dentry->d_name.name;
+ name = cdentry->d_name.name;
if (!strcmp(name, "memory.usage_in_bytes")) {
event->register_event = mem_cgroup_usage_register_event;
@@ -4917,7 +4937,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
* automatically removed on cgroup destruction but the removal is
* asynchronous, so take an extra ref on @css.
*/
- cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent,
+ cfile_css = css_tryget_online_from_dir(cdentry->d_parent,
&memory_cgrp_subsys);
ret = -EINVAL;
if (IS_ERR(cfile_css))
@@ -5648,15 +5668,21 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
unsigned long addr, pte_t ptent)
{
+ unsigned long index;
+ struct folio *folio;
+
if (!vma->vm_file) /* anonymous vma */
return NULL;
if (!(mc.flags & MOVE_FILE))
return NULL;
- /* page is moved even if it's not RSS of this task(page-faulted). */
+ /* folio is moved even if it's not RSS of this task(page-faulted). */
/* shmem/tmpfs may report page out on swap: account for that too. */
- return find_get_incore_page(vma->vm_file->f_mapping,
- linear_page_index(vma, addr));
+ index = linear_page_index(vma, addr);
+ folio = filemap_get_incore_folio(vma->vm_file->f_mapping, index);
+ if (!folio)
+ return NULL;
+ return folio_file_page(folio, index);
}
/**
@@ -5741,6 +5767,12 @@ static int mem_cgroup_move_account(struct page *page,
}
}
+#ifdef CONFIG_SWAP
+ if (folio_test_swapcache(folio)) {
+ __mod_lruvec_state(from_vec, NR_SWAPCACHE, -nr_pages);
+ __mod_lruvec_state(to_vec, NR_SWAPCACHE, nr_pages);
+ }
+#endif
if (folio_test_writeback(folio)) {
__mod_lruvec_state(from_vec, NR_WRITEBACK, -nr_pages);
__mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages);
@@ -6397,7 +6429,8 @@ static ssize_t memory_high_write(struct kernfs_open_file *of,
}
reclaimed = try_to_free_mem_cgroup_pages(memcg, nr_pages - high,
- GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP);
+ GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP,
+ NULL);
if (!reclaimed && !nr_retries--)
break;
@@ -6446,7 +6479,8 @@ static ssize_t memory_max_write(struct kernfs_open_file *of,
if (nr_reclaims) {
if (!try_to_free_mem_cgroup_pages(memcg, nr_pages - max,
- GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP))
+ GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP,
+ NULL))
nr_reclaims--;
continue;
}
@@ -6569,21 +6603,54 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of,
return nbytes;
}
+enum {
+ MEMORY_RECLAIM_NODES = 0,
+ MEMORY_RECLAIM_NULL,
+};
+
+static const match_table_t if_tokens = {
+ { MEMORY_RECLAIM_NODES, "nodes=%s" },
+ { MEMORY_RECLAIM_NULL, NULL },
+};
+
static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
size_t nbytes, loff_t off)
{
struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
unsigned int nr_retries = MAX_RECLAIM_RETRIES;
unsigned long nr_to_reclaim, nr_reclaimed = 0;
- unsigned int reclaim_options;
- int err;
+ unsigned int reclaim_options = MEMCG_RECLAIM_MAY_SWAP |
+ MEMCG_RECLAIM_PROACTIVE;
+ char *old_buf, *start;
+ substring_t args[MAX_OPT_ARGS];
+ int token;
+ char value[256];
+ nodemask_t nodemask = NODE_MASK_ALL;
buf = strstrip(buf);
- err = page_counter_memparse(buf, "", &nr_to_reclaim);
- if (err)
- return err;
- reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE;
+ old_buf = buf;
+ nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE;
+ if (buf == old_buf)
+ return -EINVAL;
+
+ buf = strstrip(buf);
+
+ while ((start = strsep(&buf, " ")) != NULL) {
+ if (!strlen(start))
+ continue;
+ token = match_token(start, if_tokens, args);
+ match_strlcpy(value, args, sizeof(value));
+ switch (token) {
+ case MEMORY_RECLAIM_NODES:
+ if (nodelist_parse(value, nodemask) < 0)
+ return -EINVAL;
+ break;
+ default:
+ return -EINVAL;
+ }
+ }
+
while (nr_reclaimed < nr_to_reclaim) {
unsigned long reclaimed;
@@ -6600,7 +6667,8 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
reclaimed = try_to_free_mem_cgroup_pages(memcg,
nr_to_reclaim - nr_reclaimed,
- GFP_KERNEL, reclaim_options);
+ GFP_KERNEL, reclaim_options,
+ &nodemask);
if (!reclaimed && !nr_retries--)
return -EAGAIN;
@@ -7163,7 +7231,7 @@ void mem_cgroup_sk_alloc(struct sock *sk)
rcu_read_lock();
memcg = mem_cgroup_from_task(current);
- if (memcg == root_mem_cgroup)
+ if (mem_cgroup_is_root(memcg))
goto out;
if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg->tcpmem_active)
goto out;
@@ -7298,7 +7366,7 @@ static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg)
* The root cgroup cannot be destroyed, so it's refcount must
* always be >= 1.
*/
- if (WARN_ON_ONCE(memcg == root_mem_cgroup)) {
+ if (WARN_ON_ONCE(mem_cgroup_is_root(memcg))) {
VM_BUG_ON(1);
break;
}
@@ -7462,7 +7530,7 @@ long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg)
if (mem_cgroup_disabled() || do_memsw_account())
return nr_swap_pages;
- for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg))
+ for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg))
nr_swap_pages = min_t(long, nr_swap_pages,
READ_ONCE(memcg->swap.max) -
page_counter_read(&memcg->swap));
@@ -7484,7 +7552,7 @@ bool mem_cgroup_swap_full(struct folio *folio)
if (!memcg)
return false;
- for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) {
+ for (; !mem_cgroup_is_root(memcg); memcg = parent_mem_cgroup(memcg)) {
unsigned long usage = page_counter_read(&memcg->swap);
if (usage * 2 >= READ_ONCE(memcg->swap.high) ||
@@ -7648,7 +7716,7 @@ bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
return true;
original_memcg = get_mem_cgroup_from_objcg(objcg);
- for (memcg = original_memcg; memcg != root_mem_cgroup;
+ for (memcg = original_memcg; !mem_cgroup_is_root(memcg);
memcg = parent_mem_cgroup(memcg)) {
unsigned long max = READ_ONCE(memcg->zswap_max);
unsigned long pages;
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-26 06:36:24 +0300