From 41d54d3bf83f62d3ff5948cb788fe6007e66a0d0 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 3 Jul 2008 09:14:26 -0500 Subject: slub: Do not use 192 byte sized cache if minimum alignment is 128 byte The 192 byte cache is not necessary if we have a basic alignment of 128 byte. If it would be used then the 192 would be aligned to the next 128 byte boundary which would result in another 256 byte cache. Two 256 kmalloc caches cause sysfs to complain about a duplicate entry. MIPS needs 128 byte aligned kmalloc caches and spits out warnings on boot without this patch. Signed-off-by: Christoph Lameter Signed-off-by: Pekka Enberg --- mm/slub.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 0987d1cd943c..2c9a62d1f429 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2995,8 +2995,6 @@ void __init kmem_cache_init(void) create_kmalloc_cache(&kmalloc_caches[1], "kmalloc-96", 96, GFP_KERNEL); caches++; - } - if (KMALLOC_MIN_SIZE <= 128) { create_kmalloc_cache(&kmalloc_caches[2], "kmalloc-192", 192, GFP_KERNEL); caches++; @@ -3026,6 +3024,16 @@ void __init kmem_cache_init(void) for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) size_index[(i - 1) / 8] = KMALLOC_SHIFT_LOW; + if (KMALLOC_MIN_SIZE == 128) { + /* + * The 192 byte sized cache is not used if the alignment + * is 128 byte. Redirect kmalloc to use the 256 byte cache + * instead. + */ + for (i = 128 + 8; i <= 192; i += 8) + size_index[(i - 1) / 8] = 8; + } + slab_state = UP; /* Provide the correct kmalloc names now that the caches are up */ -- cgit v1.2.3 From 494de90098784b8e2797598cefdd34188884ec2e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 3 Jul 2008 05:27:51 +0100 Subject: Do not overwrite nr_zones on !NUMA when initialising zlcache_ptr The non-NUMA case of build_zonelist_cache() would initialize the zlcache_ptr for both node_zonelists[] to NULL. Which is problematic, since non-NUMA only has a single node_zonelists[] entry, and trying to zero the non-existent second one just overwrote the nr_zones field instead. As kswapd uses this value to determine what reclaim work is necessary, the result is that kswapd never reclaims. This causes processes to stall frequently in low-memory situations as they always direct reclaim. This patch initialises zlcache_ptr correctly. Signed-off-by: Mel Gorman Tested-by: Dan Williams [ Simplified patch a bit ] Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 1 - 1 file changed, 1 deletion(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2f552955a02f..f32fae3121f0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2328,7 +2328,6 @@ static void build_zonelists(pg_data_t *pgdat) static void build_zonelist_cache(pg_data_t *pgdat) { pgdat->node_zonelists[0].zlcache_ptr = NULL; - pgdat->node_zonelists[1].zlcache_ptr = NULL; } #endif /* CONFIG_NUMA */ -- cgit v1.2.3 From cde53535991fbb5c34a1566f25955297c1487b8d Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 4 Jul 2008 09:59:22 -0700 Subject: Christoph has moved Remove all clameter@sgi.com addresses from the kernel tree since they will become invalid on June 27th. Change my maintainer email address for the slab allocators to cl@linux-foundation.org (which will be the new email address for the future). Signed-off-by: Christoph Lameter Signed-off-by: Christoph Lameter Cc: Pekka Enberg Cc: Stephen Rothwell Cc: Matt Mackall Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/slabinfo.c | 4 ++-- Documentation/vm/slub.txt | 2 +- MAINTAINERS | 2 +- include/asm-generic/atomic.h | 2 +- include/linux/slab.h | 2 +- include/linux/slub_def.h | 2 +- kernel/workqueue.c | 2 +- lib/radix-tree.c | 2 +- mm/allocpercpu.c | 2 +- mm/migrate.c | 2 +- mm/slub.c | 2 +- mm/sparse-vmemmap.c | 2 +- 12 files changed, 13 insertions(+), 13 deletions(-) (limited to 'mm') diff --git a/Documentation/vm/slabinfo.c b/Documentation/vm/slabinfo.c index e4230ed16ee7..df3227605d59 100644 --- a/Documentation/vm/slabinfo.c +++ b/Documentation/vm/slabinfo.c @@ -1,7 +1,7 @@ /* * Slabinfo: Tool to get reports about slabs * - * (C) 2007 sgi, Christoph Lameter + * (C) 2007 sgi, Christoph Lameter * * Compile by: * @@ -99,7 +99,7 @@ void fatal(const char *x, ...) void usage(void) { - printf("slabinfo 5/7/2007. (c) 2007 sgi. clameter@sgi.com\n\n" + printf("slabinfo 5/7/2007. (c) 2007 sgi.\n\n" "slabinfo [-ahnpvtsz] [-d debugopts] [slab-regexp]\n" "-a|--aliases Show aliases\n" "-A|--activity Most active slabs first\n" diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt index 7c13f22a0c9e..bb1f5c6e28b3 100644 --- a/Documentation/vm/slub.txt +++ b/Documentation/vm/slub.txt @@ -266,4 +266,4 @@ of other objects. slub_debug=FZ,dentry -Christoph Lameter, , May 30, 2007 +Christoph Lameter, May 30, 2007 diff --git a/MAINTAINERS b/MAINTAINERS index 460e699fd280..13b7b19692e6 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3672,7 +3672,7 @@ S: Maintained SLAB ALLOCATOR P: Christoph Lameter -M: clameter@sgi.com +M: cl@linux-foundation.org P: Pekka Enberg M: penberg@cs.helsinki.fi P: Matt Mackall diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h index 85fd0aa27a8c..4ec0a296bdec 100644 --- a/include/asm-generic/atomic.h +++ b/include/asm-generic/atomic.h @@ -2,7 +2,7 @@ #define _ASM_GENERIC_ATOMIC_H /* * Copyright (C) 2005 Silicon Graphics, Inc. - * Christoph Lameter + * Christoph Lameter * * Allows to provide arch independent atomic definitions without the need to * edit all arch specific atomic.h files. diff --git a/include/linux/slab.h b/include/linux/slab.h index c2ad35016599..9aa90a6f20e0 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -1,7 +1,7 @@ /* * Written by Mark Hemment, 1996 (markhe@nextd.demon.co.uk). * - * (C) SGI 2006, Christoph Lameter + * (C) SGI 2006, Christoph Lameter * Cleaned up and restructured to ease the addition of alternative * implementations of SLAB allocators. */ diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h index cef6f8fddd7d..d117ea2825a9 100644 --- a/include/linux/slub_def.h +++ b/include/linux/slub_def.h @@ -4,7 +4,7 @@ /* * SLUB : A Slab allocator without object queues. * - * (C) 2007 SGI, Christoph Lameter + * (C) 2007 SGI, Christoph Lameter */ #include #include diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 29fc39f1029c..ce7799540c91 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -13,7 +13,7 @@ * Kai Petzke * Theodore Ts'o * - * Made to use alloc_percpu by Christoph Lameter . + * Made to use alloc_percpu by Christoph Lameter. */ #include diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 169a2f8dabcc..56ec21a7f73d 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1,7 +1,7 @@ /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig - * Copyright (C) 2005 SGI, Christoph Lameter + * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * * This program is free software; you can redistribute it and/or diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c index f4026bae6eed..05f2b4009ccc 100644 --- a/mm/allocpercpu.c +++ b/mm/allocpercpu.c @@ -1,7 +1,7 @@ /* * linux/mm/allocpercpu.c * - * Separated from slab.c August 11, 2006 Christoph Lameter + * Separated from slab.c August 11, 2006 Christoph Lameter */ #include #include diff --git a/mm/migrate.c b/mm/migrate.c index 112bcaeaa104..55bd355d170d 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -9,7 +9,7 @@ * IWAMOTO Toshihiro * Hirokazu Takahashi * Dave Hansen - * Christoph Lameter + * Christoph Lameter */ #include diff --git a/mm/slub.c b/mm/slub.c index 2c9a62d1f429..1a427c0ae83b 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -5,7 +5,7 @@ * The allocator synchronizes using per slab locks and only * uses a centralized lock to manage a pool of partial slabs. * - * (C) 2007 SGI, Christoph Lameter + * (C) 2007 SGI, Christoph Lameter */ #include diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 99c4f36eb8a3..a91b5f8fcaf6 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -1,7 +1,7 @@ /* * Virtual Memory Map support * - * (C) 2007 sgi. Christoph Lameter . + * (C) 2007 sgi. Christoph Lameter. * * Virtual memory maps allow VM primitives pfn_to_page, page_to_pfn, * virt_to_page, page_address() to be implemented as a base offset -- cgit v1.2.3 From 251b97f552b1ad414cc5a9ccc8e4e94503edd5fc Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 4 Jul 2008 09:59:24 -0700 Subject: mm: dirty page accounting vs VM_MIXEDMAP Dirty page accounting accurately measures the amound of dirty pages in writable shared mappings by mapping the pages RO (as indicated by vma_wants_writenotify). We then trap on first write and call set_page_dirty() on the page, after which we map the page RW and continue execution. When we launder dirty pages, we call clear_page_dirty_for_io() which clears both the dirty flag, and maps the page RO again before we start writeout so that the story can repeat itself. vma_wants_writenotify() excludes VM_PFNMAP on the basis that we cannot do the regular dirty page stuff on raw PFNs and the memory isn't going anywhere anyway. The recently introduced VM_MIXEDMAP mixes both !pfn_valid() and pfn_valid() pages in a single mapping. We can't do dirty page accounting on !pfn_valid() pages as stated above, and mapping them RO causes them to be COW'ed on write, which breaks VM_SHARED semantics. Excluding VM_MIXEDMAP in vma_wants_writenotify() would mean we don't do the regular dirty page accounting for the pfn_valid() pages, which would bring back all the head-aches from inaccurate dirty page accounting. So instead, we let the !pfn_valid() pages get mapped RO, but fix them up unconditionally in the fault path. Signed-off-by: Peter Zijlstra Cc: Nick Piggin Acked-by: Hugh Dickins Cc: "Jared Hulbert" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index d14b251a25a6..350e646032f5 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1697,8 +1697,19 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page *dirty_page = NULL; old_page = vm_normal_page(vma, address, orig_pte); - if (!old_page) + if (!old_page) { + /* + * VM_MIXEDMAP !pfn_valid() case + * + * We should not cow pages in a shared writeable mapping. + * Just mark the pages writable as we can't do any dirty + * accounting on raw pfn maps. + */ + if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + (VM_WRITE|VM_SHARED)) + goto reuse; goto gotten; + } /* * Take out anonymous pages first, anonymous shared vmas are @@ -1751,6 +1762,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, } if (reuse) { +reuse: flush_cache_page(vma, address, pte_pfn(orig_pte)); entry = pte_mkyoung(orig_pte); entry = maybe_mkwrite(pte_mkdirty(entry), vma); -- cgit v1.2.3 From 7a36a752d006f6874049da510297eeb7f09d92a7 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 4 Jul 2008 09:59:28 -0700 Subject: get_user_pages(): fix possible page leak on oom get_user_pages() must not return the error when i != 0. When pages != NULL we have i get_page()'ed pages. Signed-off-by: Oleg Nesterov Acked-by: Nick Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index 350e646032f5..2302d228fe04 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1151,7 +1151,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, * be processed until returning to user space. */ if (unlikely(test_tsk_thread_flag(tsk, TIF_MEMDIE))) - return -ENOMEM; + return i ? i : -ENOMEM; if (write) foll_flags |= FOLL_WRITE; -- cgit v1.2.3 From d79df630f622806c4d0e116fbaf6ebf6baf53461 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Fri, 4 Jul 2008 12:24:13 -0700 Subject: mempolicy: mask off internal flags for userspace API Flags considered internal to the mempolicy kernel code are stored as part of the "flags" member of struct mempolicy. Before exposing a policy type to userspace via get_mempolicy(), these internal flags must be masked. Flags exposed to userspace, however, should still be returned to the user. Signed-off-by: David Rientjes Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index a37a5034f63d..c94e58b192c3 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -729,7 +729,11 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; - *policy |= pol->flags; + /* + * Internal mempolicy flags must be masked off before exposing + * the policy to userspace. + */ + *policy |= (pol->flags & MPOL_MODE_FLAGS); } if (vma) { -- cgit v1.2.3