From 778d3b0ff0654ad7092bf823fd32010066b12365 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Tue, 26 Jul 2011 16:08:30 -0700 Subject: cpusets: randomize node rotor used in cpuset_mem_spread_node() [ This patch has already been accepted as commit 0ac0c0d0f837 but later reverted (commit 35926ff5fba8) because it itroduced arch specific __node_random which was defined only for x86 code so it broke other archs. This is a followup without any arch specific code. Other than that there are no functional changes.] Some workloads that create a large number of small files tend to assign too many pages to node 0 (multi-node systems). Part of the reason is that the rotor (in cpuset_mem_spread_node()) used to assign nodes starts at node 0 for newly created tasks. This patch changes the rotor to be initialized to a random node number of the cpuset. [akpm@linux-foundation.org: fix layout] [Lee.Schermerhorn@hp.com: Define stub numa_random() for !NUMA configuration] [mhocko@suse.cz: Make it arch independent] [akpm@linux-foundation.org: fix CONFIG_NUMA=y, MAX_NUMNODES>1 build] Signed-off-by: Jack Steiner Signed-off-by: Lee Schermerhorn Signed-off-by: Michal Hocko Reviewed-by: KOSAKI Motohiro Cc: Christoph Lameter Cc: Pekka Enberg Cc: Paul Menage Cc: Jack Steiner Cc: Robin Holt Cc: David Rientjes Cc: Christoph Lameter Cc: David Rientjes Cc: Jack Steiner Cc: KOSAKI Motohiro Cc: Lee Schermerhorn Cc: Michal Hocko Cc: Paul Menage Cc: Pekka Enberg Cc: Robin Holt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e7fb9d25c54e..8b57173c1dd5 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -93,6 +93,7 @@ #include #include +#include #include "internal.h" @@ -1645,6 +1646,21 @@ static inline unsigned interleave_nid(struct mempolicy *pol, return interleave_nodes(pol); } +/* + * Return the bit number of a random bit set in the nodemask. + * (returns -1 if nodemask is empty) + */ +int node_random(const nodemask_t *maskp) +{ + int w, bit = -1; + + w = nodes_weight(*maskp); + if (w) + bit = bitmap_ord_to_pos(maskp->bits, + get_random_int() % w, MAX_NUMNODES); + return bit; +} + #ifdef CONFIG_HUGETLBFS /* * huge_zonelist(@vma, @addr, @gfp_flags, @mpol) -- cgit v1.2.3 From 8aacc9f550feb09c8b26470498345c192996a68e Mon Sep 17 00:00:00 2001 From: Caspar Zhang Date: Wed, 14 Sep 2011 16:20:58 -0700 Subject: mm/mempolicy.c: fix pgoff in mbind vma merge commit 9d8cebd4bcd7 ("mm: fix mbind vma merge problem") didn't really fix the mbind vma merge problem due to wrong pgoff value passing to vma_merge(), which made vma_merge() always return NULL. Before the patch applied, we are getting a result like: addr = 0x7fa58f00c000 [snip] 7fa58f00c000-7fa58f00d000 rw-p 00000000 00:00 0 7fa58f00d000-7fa58f00e000 rw-p 00000000 00:00 0 7fa58f00e000-7fa58f00f000 rw-p 00000000 00:00 0 here 7fa58f00c000->7fa58f00f000 we get 3 VMAs which are expected to be merged described as described in commit 9d8cebd. Re-testing the patched kernel with the reproducer provided in commit 9d8cebd, we get the correct result: addr = 0x7ffa5aaa2000 [snip] 7ffa5aaa2000-7ffa5aaa6000 rw-p 00000000 00:00 0 7fffd556f000-7fffd5584000 rw-p 00000000 00:00 0 [stack] Signed-off-by: Caspar Zhang Cc: KOSAKI Motohiro Cc: Christoph Lameter Cc: Hugh Dickins Cc: Mel Gorman Cc: Lee Schermerhorn Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 8b57173c1dd5..b1f70d6eec35 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -636,7 +636,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, struct vm_area_struct *prev; struct vm_area_struct *vma; int err = 0; - pgoff_t pgoff; unsigned long vmstart; unsigned long vmend; @@ -649,9 +648,9 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, vmstart = max(start, vma->vm_start); vmend = min(end, vma->vm_end); - pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, - vma->anon_vma, vma->vm_file, pgoff, new_pol); + vma->anon_vma, vma->vm_file, vma->vm_pgoff, + new_pol); if (prev) { vma = prev; next = vma->vm_next; -- cgit v1.2.3 From 2bbff6c761e31b4642d297513cd3e0e89bc68ff7 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 14 Sep 2011 16:21:02 -0700 Subject: mm/mempolicy.c: make copy_from_user() provably correct When compiling mm/mempolicy.c with struct user copy checks the following warning is shown: In file included from arch/x86/include/asm/uaccess.h:572, from include/linux/uaccess.h:5, from include/linux/highmem.h:7, from include/linux/pagemap.h:10, from include/linux/mempolicy.h:70, from mm/mempolicy.c:68: In function `copy_from_user', inlined from `compat_sys_get_mempolicy' at mm/mempolicy.c:1415: arch/x86/include/asm/uaccess_64.h:64: warning: call to `copy_from_user_overflow' declared with attribute warning: copy_from_user() buffer size is not provably correct LD mm/built-in.o Fix this by passing correct buffer size value. Signed-off-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'mm/mempolicy.c') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index b1f70d6eec35..9c51f9f58cac 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1411,7 +1411,9 @@ asmlinkage long compat_sys_get_mempolicy(int __user *policy, err = sys_get_mempolicy(policy, nm, nr_bits+1, addr, flags); if (!err && nmask) { - err = copy_from_user(bm, nm, alloc_size); + unsigned long copy_size; + copy_size = min_t(unsigned long, sizeof(bm), alloc_size); + err = copy_from_user(bm, nm, copy_size); /* ensure entire bitmap is zeroed */ err |= clear_user(nmask, ALIGN(maxnode-1, 8) / 8); err |= compat_put_bitmap(nmask, bm, nr_bits); -- cgit v1.2.3