From: Feng Tang <feng.tang@intel.com>
To: linux-mm@kvack.org, Andrew Morton <akpm@linux-foundation.org>,
Michal Hocko <mhocko@kernel.org>,
David Rientjes <rientjes@google.com>,
Dave Hansen <dave.hansen@intel.com>,
Ben Widawsky <ben.widawsky@intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>,
Mel Gorman <mgorman@techsingularity.net>,
Mike Kravetz <mike.kravetz@oracle.com>,
Randy Dunlap <rdunlap@infradead.org>,
Vlastimil Babka <vbabka@suse.cz>, Andi Kleen <ak@linux.intel.com>,
Dan Williams <dan.j.williams@intel.com>,
ying.huang@intel.com, Feng Tang <feng.tang@intel.com>
Subject: [v4 PATCH 2/3] mm/mempolicy: don't handle MPOL_LOCAL like a fake MPOL_PREFERRED policy
Date: Tue, 1 Jun 2021 23:14:51 +0800 [thread overview]
Message-ID: <1622560492-1294-3-git-send-email-feng.tang@intel.com> (raw)
In-Reply-To: <1622560492-1294-1-git-send-email-feng.tang@intel.com>
MPOL_LOCAL policy has been setup as a real policy, but it is still handled
like a faked POL_PREFERRED policy with one internal MPOL_F_LOCAL flag bit
set, and there are many places having to judge the real 'prefer' or the
'local' policy, which are quite confusing.
In current code, there are 4 cases that MPOL_LOCAL are used:
1. user specifies 'local' policy
2. user specifies 'prefer' policy, but with empty nodemask
3. system 'default' policy is used
4. 'prefer' policy + valid 'preferred' node with MPOL_F_STATIC_NODES
flag set, and when it is 'rebind' to a nodemask which doesn't
contains the 'preferred' node, it will perform as 'local' policy
So make 'local' a real policy instead of a fake 'prefer' one, and kill
MPOL_F_LOCAL bit, which can greatly reduce the confusion for code reading.
For case 4, the logic of mpol_rebind_preferred() is confusing, as Michal
Hocko pointed out:
: I do believe that rebinding preferred policy is just bogus and it should
: be dropped altogether on the ground that a preference is a mere hint from
: userspace where to start the allocation. Unless I am missing something
: cpusets will be always authoritative for the final placement. The
: preferred node just acts as a starting point and it should be really
: preserved when cpusets changes. Otherwise we have a very subtle behavior
: corner cases.
So dump all the tricky transformation between 'prefer' and 'local',
and just record the new nodemask of rebinding.
Suggested-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Feng Tang <feng.tang@intel.com>
---
include/uapi/linux/mempolicy.h | 1 -
mm/mempolicy.c | 131 +++++++++++++++++------------------------
2 files changed, 53 insertions(+), 79 deletions(-)
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 4832fd0..19a00bc 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -60,7 +60,6 @@ enum {
* are never OR'ed into the mode in mempolicy API arguments.
*/
#define MPOL_F_SHARED (1 << 0) /* identify shared policies */
-#define MPOL_F_LOCAL (1 << 1) /* preferred local allocation */
#define MPOL_F_MOF (1 << 3) /* this policy wants migrate on fault */
#define MPOL_F_MORON (1 << 4) /* Migrate On protnone Reference On Node */
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 6795a6a..9805291 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -121,8 +121,7 @@ enum zone_type policy_zone = 0;
*/
static struct mempolicy default_policy = {
.refcnt = ATOMIC_INIT(1), /* never free it */
- .mode = MPOL_PREFERRED,
- .flags = MPOL_F_LOCAL,
+ .mode = MPOL_LOCAL,
};
static struct mempolicy preferred_node_policy[MAX_NUMNODES];
@@ -200,12 +199,9 @@ static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes)
static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
{
- if (!nodes)
- pol->flags |= MPOL_F_LOCAL; /* local allocation */
- else if (nodes_empty(*nodes))
- return -EINVAL; /* no allowed nodes */
- else
- pol->v.preferred_node = first_node(*nodes);
+ if (nodes_empty(*nodes))
+ return -EINVAL;
+ pol->v.preferred_node = first_node(*nodes);
return 0;
}
@@ -220,8 +216,7 @@ static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
/*
* mpol_set_nodemask is called after mpol_new() to set up the nodemask, if
* any, for the new policy. mpol_new() has already validated the nodes
- * parameter with respect to the policy mode and flags. But, we need to
- * handle an empty nodemask with MPOL_PREFERRED here.
+ * parameter with respect to the policy mode and flags.
*
* Must be called holding task's alloc_lock to protect task's mems_allowed
* and mempolicy. May also be called holding the mmap_lock for write.
@@ -234,30 +229,27 @@ static int mpol_set_nodemask(struct mempolicy *pol,
/* if mode is MPOL_DEFAULT, pol is NULL. This is right. */
if (pol == NULL)
return 0;
+
+ if (pol->mode == MPOL_LOCAL)
+ return 0;
+
/* Check N_MEMORY */
nodes_and(nsc->mask1,
cpuset_current_mems_allowed, node_states[N_MEMORY]);
VM_BUG_ON(!nodes);
- if (pol->mode == MPOL_PREFERRED && nodes_empty(*nodes))
- nodes = NULL; /* explicit local allocation */
- else {
- if (pol->flags & MPOL_F_RELATIVE_NODES)
- mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1);
- else
- nodes_and(nsc->mask2, *nodes, nsc->mask1);
- if (mpol_store_user_nodemask(pol))
- pol->w.user_nodemask = *nodes;
- else
- pol->w.cpuset_mems_allowed =
- cpuset_current_mems_allowed;
- }
+ if (pol->flags & MPOL_F_RELATIVE_NODES)
+ mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1);
+ else
+ nodes_and(nsc->mask2, *nodes, nsc->mask1);
- if (nodes)
- ret = mpol_ops[pol->mode].create(pol, &nsc->mask2);
+ if (mpol_store_user_nodemask(pol))
+ pol->w.user_nodemask = *nodes;
else
- ret = mpol_ops[pol->mode].create(pol, NULL);
+ pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed;
+
+ ret = mpol_ops[pol->mode].create(pol, &nsc->mask2);
return ret;
}
@@ -290,13 +282,14 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
if (((flags & MPOL_F_STATIC_NODES) ||
(flags & MPOL_F_RELATIVE_NODES)))
return ERR_PTR(-EINVAL);
+
+ mode = MPOL_LOCAL;
}
} else if (mode == MPOL_LOCAL) {
if (!nodes_empty(*nodes) ||
(flags & MPOL_F_STATIC_NODES) ||
(flags & MPOL_F_RELATIVE_NODES))
return ERR_PTR(-EINVAL);
- mode = MPOL_PREFERRED;
} else if (nodes_empty(*nodes))
return ERR_PTR(-EINVAL);
policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
@@ -344,25 +337,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes)
static void mpol_rebind_preferred(struct mempolicy *pol,
const nodemask_t *nodes)
{
- nodemask_t tmp;
-
- if (pol->flags & MPOL_F_STATIC_NODES) {
- int node = first_node(pol->w.user_nodemask);
-
- if (node_isset(node, *nodes)) {
- pol->v.preferred_node = node;
- pol->flags &= ~MPOL_F_LOCAL;
- } else
- pol->flags |= MPOL_F_LOCAL;
- } else if (pol->flags & MPOL_F_RELATIVE_NODES) {
- mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
- pol->v.preferred_node = first_node(tmp);
- } else if (!(pol->flags & MPOL_F_LOCAL)) {
- pol->v.preferred_node = node_remap(pol->v.preferred_node,
- pol->w.cpuset_mems_allowed,
- *nodes);
- pol->w.cpuset_mems_allowed = *nodes;
- }
+ pol->w.cpuset_mems_allowed = *nodes;
}
/*
@@ -376,7 +351,7 @@ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask)
{
if (!pol)
return;
- if (!mpol_store_user_nodemask(pol) && !(pol->flags & MPOL_F_LOCAL) &&
+ if (!mpol_store_user_nodemask(pol) &&
nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
return;
@@ -427,6 +402,9 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
.create = mpol_new_bind,
.rebind = mpol_rebind_nodemask,
},
+ [MPOL_LOCAL] = {
+ .rebind = mpol_rebind_default,
+ },
};
static int migrate_page_add(struct page *page, struct list_head *pagelist,
@@ -919,10 +897,12 @@ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
case MPOL_INTERLEAVE:
*nodes = p->v.nodes;
break;
+ case MPOL_LOCAL:
+ /* return empty node mask for local allocation */
+ break;
+
case MPOL_PREFERRED:
- if (!(p->flags & MPOL_F_LOCAL))
- node_set(p->v.preferred_node, *nodes);
- /* else return empty node mask for local allocation */
+ node_set(p->v.preferred_node, *nodes);
break;
default:
BUG();
@@ -1894,9 +1874,9 @@ nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
/* Return the node id preferred by the given mempolicy, or the given id */
static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd)
{
- if (policy->mode == MPOL_PREFERRED && !(policy->flags & MPOL_F_LOCAL))
+ if (policy->mode == MPOL_PREFERRED) {
nd = policy->v.preferred_node;
- else {
+ } else {
/*
* __GFP_THISNODE shouldn't even be used with the bind policy
* because we might easily break the expectation to stay on the
@@ -1933,14 +1913,11 @@ unsigned int mempolicy_slab_node(void)
return node;
policy = current->mempolicy;
- if (!policy || policy->flags & MPOL_F_LOCAL)
+ if (!policy)
return node;
switch (policy->mode) {
case MPOL_PREFERRED:
- /*
- * handled MPOL_F_LOCAL above
- */
return policy->v.preferred_node;
case MPOL_INTERLEAVE:
@@ -1960,6 +1937,8 @@ unsigned int mempolicy_slab_node(void)
&policy->v.nodes);
return z->zone ? zone_to_nid(z->zone) : node;
}
+ case MPOL_LOCAL:
+ return node;
default:
BUG();
@@ -2072,16 +2051,18 @@ bool init_nodemask_of_mempolicy(nodemask_t *mask)
mempolicy = current->mempolicy;
switch (mempolicy->mode) {
case MPOL_PREFERRED:
- if (mempolicy->flags & MPOL_F_LOCAL)
- nid = numa_node_id();
- else
- nid = mempolicy->v.preferred_node;
+ nid = mempolicy->v.preferred_node;
init_nodemask_of_node(mask, nid);
break;
case MPOL_BIND:
case MPOL_INTERLEAVE:
- *mask = mempolicy->v.nodes;
+ *mask = mempolicy->v.nodes;
+ break;
+
+ case MPOL_LOCAL:
+ nid = numa_node_id();
+ init_nodemask_of_node(mask, nid);
break;
default:
@@ -2188,7 +2169,7 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
* If the policy is interleave, or does not allow the current
* node in its nodemask, we allocate the standard way.
*/
- if (pol->mode == MPOL_PREFERRED && !(pol->flags & MPOL_F_LOCAL))
+ if (pol->mode == MPOL_PREFERRED)
hpage_node = pol->v.preferred_node;
nmask = policy_nodemask(gfp, pol);
@@ -2324,10 +2305,9 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
case MPOL_INTERLEAVE:
return !!nodes_equal(a->v.nodes, b->v.nodes);
case MPOL_PREFERRED:
- /* a's ->flags is the same as b's */
- if (a->flags & MPOL_F_LOCAL)
- return true;
return a->v.preferred_node == b->v.preferred_node;
+ case MPOL_LOCAL:
+ return true;
default:
BUG();
return false;
@@ -2465,10 +2445,11 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
break;
case MPOL_PREFERRED:
- if (pol->flags & MPOL_F_LOCAL)
- polnid = numa_node_id();
- else
- polnid = pol->v.preferred_node;
+ polnid = pol->v.preferred_node;
+ break;
+
+ case MPOL_LOCAL:
+ polnid = numa_node_id();
break;
case MPOL_BIND:
@@ -2835,9 +2816,6 @@ void numa_default_policy(void)
* Parse and format mempolicy from/to strings
*/
-/*
- * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag.
- */
static const char * const policy_modes[] =
{
[MPOL_DEFAULT] = "default",
@@ -2915,7 +2893,6 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
*/
if (nodelist)
goto out;
- mode = MPOL_PREFERRED;
break;
case MPOL_DEFAULT:
/*
@@ -2959,7 +2936,7 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
else if (nodelist)
new->v.preferred_node = first_node(nodes);
else
- new->flags |= MPOL_F_LOCAL;
+ new->mode = MPOL_LOCAL;
/*
* Save nodes for contextualization: this will be used to "clone"
@@ -3005,12 +2982,10 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
switch (mode) {
case MPOL_DEFAULT:
+ case MPOL_LOCAL:
break;
case MPOL_PREFERRED:
- if (flags & MPOL_F_LOCAL)
- mode = MPOL_LOCAL;
- else
- node_set(pol->v.preferred_node, nodes);
+ node_set(pol->v.preferred_node, nodes);
break;
case MPOL_BIND:
case MPOL_INTERLEAVE:
--
2.7.4
next prev parent reply other threads:[~2021-06-01 15:15 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-01 15:14 [v4 PATCH 0/3] mm/mempolicy: some fix and semantics cleanup Feng Tang
2021-06-01 15:14 ` [v4 PATCH 1/3] mm/mempolicy: cleanup nodemask intersection check for oom Feng Tang
2021-06-01 15:14 ` Feng Tang [this message]
2021-06-03 7:41 ` [v4 PATCH 2/3] mm/mempolicy: don't handle MPOL_LOCAL like a fake MPOL_PREFERRED policy Michal Hocko
2021-06-03 8:18 ` Feng Tang
2021-06-07 7:48 ` [mm/mempolicy] 7463fff037: ltp.mbind01.fail kernel test robot
2021-06-07 8:10 ` Michal Hocko
2021-06-01 15:14 ` [v4 PATCH 3/3] mm/mempolicy: unify the parameter sanity check for mbind and set_mempolicy Feng Tang
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1622560492-1294-3-git-send-email-feng.tang@intel.com \
--to=feng.tang@intel.com \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=ben.widawsky@intel.com \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@intel.com \
--cc=linux-mm@kvack.org \
--cc=mgorman@techsingularity.net \
--cc=mhocko@kernel.org \
--cc=mike.kravetz@oracle.com \
--cc=rdunlap@infradead.org \
--cc=rientjes@google.com \
--cc=vbabka@suse.cz \
--cc=ying.huang@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).