From 4e4785bcf0c8503224fa6c17d8e0228de781bff6 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Mon, 25 Sep 2006 23:31:17 -0700 Subject: [PATCH] [PATCH] mempolicies: fix policy_zone check There is a check in zonelist_policy that compares pieces of the bitmap obtained from a gfp mask via GFP_ZONETYPES with a zone number in function zonelist_policy(). The bitmap is an ORed mask of __GFP_DMA, __GFP_DMA32 and __GFP_HIGHMEM. The policy_zone is a zone number with the possible values of ZONE_DMA, ZONE_DMA32, ZONE_HIGHMEM and ZONE_NORMAL. These are two different domains of values. For some reason seemed to work before the zone reduction patchset (It definitely works on SGI boxes since we just have one zone and the check cannot fail). With the zone reduction patchset this check definitely fails on systems with two zones if the system actually has memory in both zones. This is because ZONE_NORMAL is selected using no __GFP flag at all and thus gfp_zone(gfpmask) == 0. ZONE_DMA is selected when __GFP_DMA is set. __GFP_DMA is 0x01. So gfp_zone(gfpmask) == 1. policy_zone is set to ZONE_NORMAL (==1) if ZONE_NORMAL and ZONE_DMA are populated. For ZONE_NORMAL gfp_zone() yields 0 which is < policy_zone(ZONE_NORMAL) and so policy is not applied to regular memory allocations! Instead gfp_zone(__GFP_DMA) == 1 which results in policy being applied to DMA allocations! What we realy want in that place is to establish the highest allowable zone for a given gfp_mask. If the highest zone is higher or equal to the policy_zone then memory policies need to be applied. We have such a highest_zone() function in page_alloc.c. So move the highest_zone() function from mm/page_alloc.c into include/linux/gfp.h. On the way we simplify the function and use the new zone_type that was also introduced with the zone reduction patchset plus we also specify the right type for the gfp flags parameter. Signed-off-by: Christoph Lameter Signed-off-by: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 15 +++++++++++++++ mm/mempolicy.c | 2 +- mm/page_alloc.c | 16 ---------------- 3 files changed, 16 insertions(+), 17 deletions(-) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 2a2153ebfe..a0992d392d 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -85,6 +85,21 @@ static inline int gfp_zone(gfp_t gfp) return zone; } +static inline enum zone_type highest_zone(gfp_t flags) +{ + if (flags & __GFP_DMA) + return ZONE_DMA; +#ifdef CONFIG_ZONE_DMA32 + if (flags & __GFP_DMA32) + return ZONE_DMA32; +#endif +#ifdef CONFIG_HIGHMEM + if (flags & __GFP_HIGHMEM) + return ZONE_HIGHMEM; +#endif + return ZONE_NORMAL; +} + /* * There is only one page-allocator function, and two main namespaces to * it. The alloc_page*() variants return 'struct page *' and as such diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a9963ceddd..9870624d72 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1096,7 +1096,7 @@ static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy) case MPOL_BIND: /* Lower zones don't get a policy applied */ /* Careful: current->mems_allowed might have moved */ - if (gfp_zone(gfp) >= policy_zone) + if (highest_zone(gfp) >= policy_zone) if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist)) return policy->v.zonelist; /*FALL THROUGH*/ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6c7c2dd1b3..25f39865e3 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1376,22 +1376,6 @@ static int __meminit build_zonelists_node(pg_data_t *pgdat, return nr_zones; } -static inline int highest_zone(int zone_bits) -{ - int res = ZONE_NORMAL; -#ifdef CONFIG_HIGHMEM - if (zone_bits & (__force int)__GFP_HIGHMEM) - res = ZONE_HIGHMEM; -#endif -#ifdef CONFIG_ZONE_DMA32 - if (zone_bits & (__force int)__GFP_DMA32) - res = ZONE_DMA32; -#endif - if (zone_bits & (__force int)__GFP_DMA) - res = ZONE_DMA; - return res; -} - #ifdef CONFIG_NUMA #define MAX_NODE_LOAD (num_online_nodes()) static int __meminitdata node_load[MAX_NUMNODES]; -- 2.39.5