Commit-ID: e975d6ac08f3447d7e44851d37f7791ace6da73b Gitweb: http://git.kernel.org/tip/e975d6ac08f3447d7e44851d37f7791ace6da73b Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx> AuthorDate: Thu, 12 Jan 2012 16:07:00 +0100 Committer: Ingo Molnar <mingo@xxxxxxxxxx> CommitDate: Thu, 17 May 2012 14:06:12 +0200 mm/mpol: Remove NUMA_INTERLEAVE_HIT Since the NUMA_INTERLEAVE_HIT statistic is useless on its own; it wants to be compared to either a total of interleave allocations or to a miss count, remove it. Fixing it would be possible, but since we've gone years without these statistics I figure we can continue that way. Also NUMA_HIT fully includes NUMA_INTERLEAVE_HIT so users might switch to using that. This cleans up some of the weird MPOL_INTERLEAVE allocation exceptions. Signed-off-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> Cc: Suresh Siddha <suresh.b.siddha@xxxxxxxxx> Cc: Paul Turner <pjt@xxxxxxxxxx> Cc: Dan Smith <danms@xxxxxxxxxx> Cc: Bharata B Rao <bharata.rao@xxxxxxxxx> Cc: Lee Schermerhorn <Lee.Schermerhorn@xxxxxx> Cc: Christoph Lameter <cl@xxxxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Link: http://lkml.kernel.org/r/1326380820.2442.186.camel@twins Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx> --- drivers/base/node.c | 2 +- include/linux/mmzone.h | 1 - mm/mempolicy.c | 68 +++++++++++++++--------------------------------- 3 files changed, 22 insertions(+), 49 deletions(-) diff --git a/drivers/base/node.c b/drivers/base/node.c index 90aa2a1..e7c61f3 100644 --- a/drivers/base/node.c +++ b/drivers/base/node.c @@ -169,7 +169,7 @@ static ssize_t node_read_numastat(struct device *dev, node_page_state(dev->id, NUMA_HIT), node_page_state(dev->id, NUMA_MISS), node_page_state(dev->id, NUMA_FOREIGN), - node_page_state(dev->id, NUMA_INTERLEAVE_HIT), + 0UL, node_page_state(dev->id, NUMA_LOCAL), node_page_state(dev->id, NUMA_OTHER)); } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index dff7115..0440e51 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -111,7 +111,6 @@ enum zone_stat_item { NUMA_HIT, /* allocated in intended node */ NUMA_MISS, /* allocated in non intended node */ NUMA_FOREIGN, /* was intended here, hit elsewhere */ - NUMA_INTERLEAVE_HIT, /* interleaver preferred this zone */ NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ #endif diff --git a/mm/mempolicy.c b/mm/mempolicy.c index cdb3b9d..82d209b 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1489,11 +1489,29 @@ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy) return NULL; } +/* Do dynamic interleaving for a process */ +static unsigned interleave_nodes(struct mempolicy *policy) +{ + unsigned nid, next; + struct task_struct *me = current; + + nid = me->il_next; + next = next_node(nid, policy->v.nodes); + if (next >= MAX_NUMNODES) + next = first_node(policy->v.nodes); + if (next < MAX_NUMNODES) + me->il_next = next; + return nid; +} + /* Return a zonelist indicated by gfp for node representing a mempolicy */ static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy, int nd) { switch (policy->mode) { + case MPOL_INTERLEAVE: + nd = interleave_nodes(policy); + break; case MPOL_PREFERRED: if (!(policy->flags & MPOL_F_LOCAL)) nd = policy->v.preferred_node; @@ -1515,21 +1533,6 @@ static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy, return node_zonelist(nd, gfp); } -/* Do dynamic interleaving for a process */ -static unsigned interleave_nodes(struct mempolicy *policy) -{ - unsigned nid, next; - struct task_struct *me = current; - - nid = me->il_next; - next = next_node(nid, policy->v.nodes); - if (next >= MAX_NUMNODES) - next = first_node(policy->v.nodes); - if (next < MAX_NUMNODES) - me->il_next = next; - return nid; -} - /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. @@ -1760,21 +1763,6 @@ out: return ret; } -/* Allocate a page in interleaved policy. - Own path because it needs to do special accounting. */ -static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, - unsigned nid) -{ - struct zonelist *zl; - struct page *page; - - zl = node_zonelist(nid, gfp); - page = __alloc_pages(gfp, order, zl); - if (page && page_zone(page) == zonelist_zone(&zl->_zonerefs[0])) - inc_zone_page_state(page, NUMA_INTERLEAVE_HIT); - return page; -} - /** * alloc_pages_vma - Allocate a page for a VMA. * @@ -1811,17 +1799,6 @@ retry_cpuset: pol = get_vma_policy(current, vma, addr); cpuset_mems_cookie = read_mems_allowed_begin(); - if (unlikely(pol->mode == MPOL_INTERLEAVE)) { - unsigned nid; - - nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); - mpol_cond_put(pol); - page = alloc_page_interleave(gfp, order, nid); - if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) - goto retry_cpuset; - - return page; - } zl = policy_zonelist(gfp, pol, node); if (unlikely(mpol_needs_cond_ref(pol))) { /* @@ -1879,12 +1856,9 @@ retry_cpuset: * No reference counting needed for current->mempolicy * nor system default_policy */ - if (pol->mode == MPOL_INTERLEAVE) - page = alloc_page_interleave(gfp, order, interleave_nodes(pol)); - else - page = __alloc_pages_nodemask(gfp, order, - policy_zonelist(gfp, pol, numa_node_id()), - policy_nodemask(gfp, pol)); + page = __alloc_pages_nodemask(gfp, order, + policy_zonelist(gfp, pol, numa_node_id()), + policy_nodemask(gfp, pol)); if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; -- To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html