PATCH 09/15 Mempolicy: Use MPOL_PREFERRED for system-wide default policy
Against: 2.6.25-rc8-mm1
V2 -> V3:
+ mpol_to_str(): show "default" policy when &default_policy is
passed in, rather than the details of the default_policy, in
/proc/<pid>/numa_maps.
V1 -> V2:
+ restore BUG()s in switch(policy) default cases -- per
Christoph
+ eliminate unneeded re-init of struct mempolicy policy member
before freeing
Currently, when one specifies MPOL_DEFAULT via a NUMA memory
policy API [set_mempolicy(), mbind() and internal versions],
the kernel simply installs a NULL struct mempolicy pointer in
the appropriate context: task policy, vma policy, or shared
policy. This causes any use of that policy to "fall back" to
the next most specific policy scope.
The only use of MPOL_DEFAULT to mean "local allocation" is in
the system default policy. This requires extra checks/cases
for MPOL_DEFAULT in many mempolicy.c functions.
There is another, "preferred" way to specify local allocation via
the APIs. That is using the MPOL_PREFERRED policy mode with an
empty nodemask. Internally, the empty nodemask gets converted to
a preferred_node id of '-1'. All internal usage of MPOL_PREFERRED
will convert the '-1' to the id of the node local to the cpu
where the allocation occurs.
System default policy, except during boot, is hard-coded to
"local allocation". By using the MPOL_PREFERRED mode with a
negative value of preferred node for system default policy,
MPOL_DEFAULT will never occur in the 'policy' member of a
struct mempolicy. Thus, we can remove all checks for
MPOL_DEFAULT when converting policy to a node id/zonelist in
the allocation paths.
In slab_node() return local node id when policy pointer is NULL.
No need to set a pol value to take the switch default. Replace
switch default with BUG()--i.e., shouldn't happen.
With this patch MPOL_DEFAULT is only used in the APIs, including
internal calls to do_set_mempolicy() and in the display of policy
in /proc/<pid>/numa_maps. It always means "fall back" to the the
next most specific policy scope. This simplifies the description
of memory policies quite a bit, with no visible change in behavior.
get_mempolicy() continues to return MPOL_DEFAULT and an empty
nodemask when the requested policy [task or vma/shared] is
NULL. These are the values one would supply via set_mempolicy()
or mbind() to achieve that condition--default behavior.
This patch updates Documentation to reflect this change.
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@xxxxxx>
Documentation/vm/numa_memory_policy.txt | 52 ++++++++----------------
mm/mempolicy.c | 68 +++++++++++++++++++-------------
2 files changed, 59 insertions(+), 61 deletions(-)
Index: linux-2.6.25-rc8-mm1/mm/mempolicy.c
===================================================================
--- linux-2.6.25-rc8-mm1.orig/mm/mempolicy.c 2008-04-02 17:47:26.000000000 -0400
+++ linux-2.6.25-rc8-mm1/mm/mempolicy.c 2008-04-02 17:47:37.000000000 -0400
@@ -104,9 +104,13 @@ static struct kmem_cache *sn_cache;
policied. */
enum zone_type policy_zone = 0;
+/*
+ * run-time system-wide default policy => local allocation
+ */
struct mempolicy default_policy = {
.refcnt = ATOMIC_INIT(1), /* never free it */
- .mode = MPOL_DEFAULT,
+ .mode = MPOL_PREFERRED,
+ .v = { .preferred_node = -1 },
};
static const struct mempolicy_operations {
@@ -189,7 +193,7 @@ static struct mempolicy *mpol_new(unsign
if (mode == MPOL_DEFAULT) {
if (nodes && !nodes_empty(*nodes))
return ERR_PTR(-EINVAL);
- return NULL;
+ return NULL; /* simply delete any existing policy */
}
VM_BUG_ON(!nodes);
@@ -246,7 +250,6 @@ void __mpol_put(struct mempolicy *p)
{
if (!atomic_dec_and_test(&p->refcnt))
return;
- p->mode = MPOL_DEFAULT;
kmem_cache_free(policy_cache, p);
}
@@ -626,13 +629,16 @@ static long do_set_mempolicy(unsigned sh
return 0;
}
-/* Fill a zone bitmap for a policy */
-static void get_zonemask(struct mempolicy *p, nodemask_t *nodes)
+/*
+ * Return nodemask for policy for get_mempolicy() query
+ */
+static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
{
nodes_clear(*nodes);
+ if (p == &default_policy)
+ return;
+
switch (p->mode) {
- case MPOL_DEFAULT:
- break;
case MPOL_BIND:
/* Fall through */
case MPOL_INTERLEAVE:
@@ -686,6 +692,11 @@ static long do_get_mempolicy(int *policy
}
if (flags & MPOL_F_ADDR) {
+ /*
+ * Do NOT fall back to task policy if the
+ * vma/shared policy at addr is NULL. We
+ * want to return MPOL_DEFAULT in this case.
+ */
down_read(&mm->mmap_sem);
vma = find_vma_intersection(mm, addr, addr+1);
if (!vma) {
@@ -700,7 +711,7 @@ static long do_get_mempolicy(int *policy
return -EINVAL;
if (!pol)
- pol = &default_policy;
+ pol = &default_policy; /* indicates default behavior */
if (flags & MPOL_F_NODE) {
if (flags & MPOL_F_ADDR) {
@@ -715,8 +726,11 @@ static long do_get_mempolicy(int *policy
err = -EINVAL;
goto out;
}
- } else
- *policy = pol->mode | pol->flags;
+ } else {
+ *policy = pol == &default_policy ? MPOL_DEFAULT :
+ pol->mode;
+ *policy |= pol->flags;
+ }
if (vma) {
up_read(¤t->mm->mmap_sem);
@@ -725,7 +739,7 @@ static long do_get_mempolicy(int *policy
err = 0;
if (nmask)
- get_zonemask(pol, nmask);
+ get_policy_nodemask(pol, nmask);
out:
mpol_cond_put(pol);
@@ -1286,8 +1300,7 @@ static struct mempolicy *get_vma_policy(
addr);
if (vpol)
pol = vpol;
- } else if (vma->vm_policy &&
- vma->vm_policy->mode != MPOL_DEFAULT)
+ } else if (vma->vm_policy)
pol = vma->vm_policy;
}
if (!pol)
@@ -1334,7 +1347,6 @@ static struct zonelist *policy_zonelist(
nd = first_node(policy->v.nodes);
break;
case MPOL_INTERLEAVE: /* should not happen */
- case MPOL_DEFAULT:
nd = numa_node_id();
break;
default:
@@ -1369,9 +1381,15 @@ static unsigned interleave_nodes(struct
*/
unsigned slab_node(struct mempolicy *policy)
{
- unsigned short pol = policy ? policy->mode : MPOL_DEFAULT;
+ if (!policy)
+ return numa_node_id();
+
+ switch (policy->mode) {
+ case MPOL_PREFERRED:
+ if (unlikely(policy->v.preferred_node >= 0))
+ return policy->v.preferred_node;
+ return numa_node_id();
- switch (pol) {
case MPOL_INTERLEAVE:
return interleave_nodes(policy);
@@ -1391,13 +1409,8 @@ unsigned slab_node(struct mempolicy *pol
return zonelist_node_idx(z);
}
- case MPOL_PREFERRED:
- if (policy->v.preferred_node >= 0)
- return policy->v.preferred_node;
- /* Fall through */
-
default:
- return numa_node_id();
+ BUG();
}
}
@@ -1651,8 +1664,6 @@ int __mpol_equal(struct mempolicy *a, st
if (a->mode != MPOL_DEFAULT && !mpol_match_intent(a, b))
return 0;
switch (a->mode) {
- case MPOL_DEFAULT:
- return 1;
case MPOL_BIND:
/* Fall through */
case MPOL_INTERLEAVE:
@@ -1829,7 +1840,7 @@ void mpol_shared_policy_init(struct shar
if (policy != MPOL_DEFAULT) {
struct mempolicy *newpol;
- /* Falls back to MPOL_DEFAULT on any error */
+ /* Falls back to NULL policy [MPOL_DEFAULT] on any error */
newpol = mpol_new(policy, flags, policy_nodes);
if (!IS_ERR(newpol)) {
/* Create pseudo-vma that contains just the policy */
@@ -1953,9 +1964,14 @@ static inline int mpol_to_str(char *buff
char *p = buffer;
int l;
nodemask_t nodes;
- unsigned short mode = pol ? pol->mode : MPOL_DEFAULT;
+ unsigned short mode;
unsigned short flags = pol ? pol->flags : 0;
+ if (!pol || pol == &default_policy)
+ mode = MPOL_DEFAULT;
+ else
+ mode = pol->mode;
+
switch (mode) {
case MPOL_DEFAULT:
nodes_clear(nodes);
Index: linux-2.6.25-rc8-mm1/Documentation/vm/numa_memory_policy.txt
===================================================================
--- linux-2.6.25-rc8-mm1.orig/Documentation/vm/numa_memory_policy.txt 2008-04-02 17:47:26.000000000 -0400
+++ linux-2.6.25-rc8-mm1/Documentation/vm/numa_memory_policy.txt 2008-04-02 17:47:37.000000000 -0400
@@ -147,35 +147,18 @@ Components of Memory Policies
Linux memory policy supports the following 4 behavioral modes:
- Default Mode--MPOL_DEFAULT: The behavior specified by this mode is
- context or scope dependent.
+ Default Mode--MPOL_DEFAULT: This mode is only used in the memory
+ policy APIs. Internally, MPOL_DEFAULT is converted to the NULL
+ memory policy in all policy scopes. Any existing non-default policy
+ will simply be removed when MPOL_DEFAULT is specified. As a result,
+ MPOL_DEFAULT means "fall back to the next most specific policy scope."
+
+ For example, a NULL or default task policy will fall back to the
+ system default policy. A NULL or default vma policy will fall
+ back to the task policy.
- As mentioned in the Policy Scope section above, during normal
- system operation, the System Default Policy is hard coded to
- contain the Default mode.
-
- In this context, default mode means "local" allocation--that is
- attempt to allocate the page from the node associated with the cpu
- where the fault occurs. If the "local" node has no memory, or the
- node's memory can be exhausted [no free pages available], local
- allocation will "fallback to"--attempt to allocate pages from--
- "nearby" nodes, in order of increasing "distance".
-
- Implementation detail -- subject to change: "Fallback" uses
- a per node list of sibling nodes--called zonelists--built at
- boot time, or when nodes or memory are added or removed from
- the system [memory hotplug]. These per node zonelist are
- constructed with nodes in order of increasing distance based
- on information provided by the platform firmware.
-
- When a task/process policy or a shared policy contains the Default
- mode, this also means "local allocation", as described above.
-
- In the context of a VMA, Default mode means "fall back to task
- policy"--which may or may not specify Default mode. Thus, Default
- mode can not be counted on to mean local allocation when used
- on a non-shared region of the address space. However, see
- MPOL_PREFERRED below.
+ When specified in one of the memory policy APIs, the Default mode
+ does not use the optional set of nodes.
It is an error for the set of nodes specified for this policy to
be non-empty.
@@ -187,19 +170,18 @@ Components of Memory Policies
MPOL_PREFERRED: This mode specifies that the allocation should be
attempted from the single node specified in the policy. If that
- allocation fails, the kernel will search other nodes, exactly as
- it would for a local allocation that started at the preferred node
- in increasing distance from the preferred node. "Local" allocation
- policy can be viewed as a Preferred policy that starts at the node
+ allocation fails, the kernel will search other nodes, in order of
+ increasing distance from the preferred node based on information
+ provided by the platform firmware.
containing the cpu where the allocation takes place.
Internally, the Preferred policy uses a single node--the
preferred_node member of struct mempolicy. A "distinguished
value of this preferred_node, currently '-1', is interpreted
as "the node containing the cpu where the allocation takes
- place"--local allocation. This is the way to specify
- local allocation for a specific range of addresses--i.e. for
- VMA policies.
+ place"--local allocation. "Local" allocation policy can be
+ viewed as a Preferred policy that starts at the node containing
+ the cpu where the allocation takes place.
It is possible for the user to specify that local allocation is
always preferred by passing an empty nodemask with this mode.
--
To unsubscribe from this list: send the line "unsubscribe linux-numa" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
