Revert "mm: add nodes= arg to memory.reclaim"

This reverts commit 12a5d3955227b0d7e04fb793ccceeb2a1dd275c5.

Although it is recognized that a finer grained pro-active reclaim is
something we need and want the semantic of this implementation is really
ambiguous.

In a follow up discussion it became clear that there are two essential
usecases here.  One is to use memory.reclaim to pro-actively reclaim
memory and expectation is that the requested and reported amount of memory
is uncharged from the memcg.  Another usecase focuses on pro-active
demotion when the memory is merely shuffled around to demotion targets
while the overall charged memory stays unchanged.

The current implementation considers demoted pages as reclaimed and that
break both usecases.  [1] has tried to address the reporting part but
there are more issues with that summarized in [2] and follow up emails.

Let's revert the nodemask based extension of the memcg pro-active
reclaim for now until we settle with a more robust semantic.

[1] http://lkml.kernel.org/r/http://lkml.kernel.org/r/20221206023406.3182800-1-almasrymina@google.com
[2] http://lkml.kernel.org/r/Y5bsmpCyeryu3Zz1@dhcp22.suse.cz

Link: https://lkml.kernel.org/r/Y5xASNe1x8cusiTx@dhcp22.suse.cz
Fixes: 12a5d3955227b0d ("mm: add nodes= arg to memory.reclaim")
Signed-off-by: Michal Hocko <mhocko@suse.com>
Cc: Bagas Sanjaya <bagasdotme@gmail.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Wei Xu <weixugc@google.com>
Cc: Yang Shi <yang.shi@linux.alibaba.com>
Cc: Yosry Ahmed <yosryahmed@google.com>
Cc: zefan li <lizefan.x@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index c8ae7c897f142a329e9f3ac6c496435460ef1c8b..74cec76be9f2c0a336a89756327e43742bd24528 100644 (file)
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1245,13 +1245,17 @@ PAGE_SIZE multiple when read back.
        This is a simple interface to trigger memory reclaim in the
        target cgroup.
 
-       This file accepts a string which contains the number of bytes to
-       reclaim.
+       This file accepts a single key, the number of bytes to reclaim.
+       No nested keys are currently supported.
 
        Example::
 
          echo "1G" > memory.reclaim
 
+       The interface can be later extended with nested keys to
+       configure the reclaim behavior. For example, specify the
+       type of memory to reclaim from (anon, file, ..).
+
        Please note that the kernel can over or under reclaim from
        the target cgroup. If less bytes are reclaimed than the
        specified amount, -EAGAIN is returned.
@@ -1263,13 +1267,6 @@ PAGE_SIZE multiple when read back.
        This means that the networking layer will not adapt based on
        reclaim induced by memory.reclaim.
 
-       This file also allows the user to specify the nodes to reclaim from,
-       via the 'nodes=' key, for example::
-
-         echo "1G nodes=0,1" > memory.reclaim
-
-       The above instructs the kernel to reclaim memory from nodes 0,1.
-
   memory.peak
        A read-only single value file which exists on non-root
        cgroups.

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 2787b84eaf12f76b9b16059300d7b84d41ddab00..0ceed49516adcc7797d316f550183c8fd9aa8c25 100644 (file)
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -418,8 +418,7 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
                                                  unsigned long nr_pages,
                                                  gfp_t gfp_mask,
-                                                 unsigned int reclaim_options,
-                                                 nodemask_t *nodemask);
+                                                 unsigned int reclaim_options);
 extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
                                                gfp_t gfp_mask, bool noswap,
                                                pg_data_t *pgdat,

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ab457f0394ab6eeed8bf33c84ee9943586844178..73afff8062f9bf96b17dfae12fbe18091e215cda 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -63,7 +63,6 @@
 #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>
@@ -2393,8 +2392,7 @@ 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,
-                                                       NULL);
+                                                       MEMCG_RECLAIM_MAY_SWAP);
                psi_memstall_leave(&pflags);
        } while ((memcg = parent_mem_cgroup(memcg)) &&
                 !mem_cgroup_is_root(memcg));
@@ -2685,8 +2683,7 @@ retry:
 
        psi_memstall_enter(&pflags);
        nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages,
-                                                   gfp_mask, reclaim_options,
-                                                   NULL);
+                                                   gfp_mask, reclaim_options);
        psi_memstall_leave(&pflags);
 
        if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
@@ -3506,8 +3503,7 @@ 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,
-                                       NULL)) {
+                                       memsw ? 0 : MEMCG_RECLAIM_MAY_SWAP)) {
                        ret = -EBUSY;
                        break;
                }
@@ -3618,8 +3614,7 @@ 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,
-                                                 NULL))
+                                                 MEMCG_RECLAIM_MAY_SWAP))
                        nr_retries--;
        }
 
@@ -6429,8 +6424,7 @@ 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,
-                                       NULL);
+                                       GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP);
 
                if (!reclaimed && !nr_retries--)
                        break;
@@ -6479,8 +6473,7 @@ 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,
-                                       NULL))
+                                       GFP_KERNEL, MEMCG_RECLAIM_MAY_SWAP))
                                nr_reclaims--;
                        continue;
                }
@@ -6603,54 +6596,21 @@ 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 = 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);
-
-       old_buf = buf;
-       nr_to_reclaim = memparse(buf, &buf) / PAGE_SIZE;
-       if (buf == old_buf)
-               return -EINVAL;
+       unsigned int reclaim_options;
+       int err;
 
        buf = strstrip(buf);
+       err = page_counter_memparse(buf, "", &nr_to_reclaim);
+       if (err)
+               return err;
 
-       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;
-               }
-       }
-
+       reclaim_options = MEMCG_RECLAIM_MAY_SWAP | MEMCG_RECLAIM_PROACTIVE;
        while (nr_reclaimed < nr_to_reclaim) {
                unsigned long reclaimed;
 
@@ -6667,8 +6627,7 @@ 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,
-                                               &nodemask);
+                                               GFP_KERNEL, reclaim_options);
 
                if (!reclaimed && !nr_retries--)
                        return -EAGAIN;

diff --git a/mm/vmscan.c b/mm/vmscan.c
index bd6637fcd8f9b19a69045e79e73d6b0c44d9f15b..e83d2a74e9422b7bd032e6d3b31f804842576208 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -6754,8 +6754,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
                                           unsigned long nr_pages,
                                           gfp_t gfp_mask,
-                                          unsigned int reclaim_options,
-                                          nodemask_t *nodemask)
+                                          unsigned int reclaim_options)
 {
        unsigned long nr_reclaimed;
        unsigned int noreclaim_flag;
@@ -6770,7 +6769,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
                .may_unmap = 1,
                .may_swap = !!(reclaim_options & MEMCG_RECLAIM_MAY_SWAP),
                .proactive = !!(reclaim_options & MEMCG_RECLAIM_PROACTIVE),
-               .nodemask = nodemask,
        };
        /*
         * Traverse the ZONELIST_FALLBACK zonelist of the current node to put