From dd942ae331425812930cd01766178b7e28e65f2d Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Fri, 17 Feb 2006 01:39:16 +0100 Subject: [PATCH] [PATCH] Handle all and empty zones when setting up custom zonelists for mbind The memory allocator doesn't like empty zones (which have an uninitialized freelist), so a x86-64 system with a node fully in GFP_DMA32 only would crash on mbind. Fix that up by putting all possible zones as fallback into the zonelist and skipping the empty ones. In fact the code always enough allocated space for all zones, but only used it for the highest. This change just uses all the memory that was allocated before. This should work fine for now, but whoever implements node hot removal needs to fix this somewhere else too (or make sure zone datastructures by itself never go away, only their memory) Signed-off-by: Andi Kleen Acked-by: Christoph Lameter Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 3bd7fb7e4b7..323fdcf128c 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -132,19 +132,29 @@ static int mpol_check_policy(int mode, nodemask_t *nodes) } return nodes_subset(*nodes, node_online_map) ? 0 : -EINVAL; } + /* Generate a custom zonelist for the BIND policy. */ static struct zonelist *bind_zonelist(nodemask_t *nodes) { struct zonelist *zl; - int num, max, nd; + int num, max, nd, k; max = 1 + MAX_NR_ZONES * nodes_weight(*nodes); - zl = kmalloc(sizeof(void *) * max, GFP_KERNEL); + zl = kmalloc(sizeof(struct zone *) * max, GFP_KERNEL); if (!zl) return NULL; num = 0; - for_each_node_mask(nd, *nodes) - zl->zones[num++] = &NODE_DATA(nd)->node_zones[policy_zone]; + /* First put in the highest zones from all nodes, then all the next + lower zones etc. Avoid empty zones because the memory allocator + doesn't like them. If you implement node hot removal you + have to fix that. */ + for (k = policy_zone; k >= 0; k--) { + for_each_node_mask(nd, *nodes) { + struct zone *z = &NODE_DATA(nd)->node_zones[k]; + if (z->present_pages > 0) + zl->zones[num++] = z; + } + } zl->zones[num] = NULL; return zl; } -- 2.41.1