From 4e02ed4b4a2fae34aae766a5bb93ae235f60adb8 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Wed, 29 Oct 2008 14:00:55 -0700 Subject: fs: remove prepare_write/commit_write Nothing uses prepare_write or commit_write. Remove them from the tree completely. [akpm@linux-foundation.org: schedule simple_prepare_write() for unexporting] Signed-off-by: Nick Piggin Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 242 +---------------------------------------------------------- 1 file changed, 4 insertions(+), 238 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index ab8553658af3..f3e5f8944d17 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2029,48 +2029,8 @@ int pagecache_write_begin(struct file *file, struct address_space *mapping, { const struct address_space_operations *aops = mapping->a_ops; - if (aops->write_begin) { - return aops->write_begin(file, mapping, pos, len, flags, + return aops->write_begin(file, mapping, pos, len, flags, pagep, fsdata); - } else { - int ret; - pgoff_t index = pos >> PAGE_CACHE_SHIFT; - unsigned offset = pos & (PAGE_CACHE_SIZE - 1); - struct inode *inode = mapping->host; - struct page *page; -again: - page = __grab_cache_page(mapping, index); - *pagep = page; - if (!page) - return -ENOMEM; - - if (flags & AOP_FLAG_UNINTERRUPTIBLE && !PageUptodate(page)) { - /* - * There is no way to resolve a short write situation - * for a !Uptodate page (except by double copying in - * the caller done by generic_perform_write_2copy). - * - * Instead, we have to bring it uptodate here. - */ - ret = aops->readpage(file, page); - page_cache_release(page); - if (ret) { - if (ret == AOP_TRUNCATED_PAGE) - goto again; - return ret; - } - goto again; - } - - ret = aops->prepare_write(file, page, offset, offset+len); - if (ret) { - unlock_page(page); - page_cache_release(page); - if (pos + len > inode->i_size) - vmtruncate(inode, inode->i_size); - } - return ret; - } } EXPORT_SYMBOL(pagecache_write_begin); @@ -2079,32 +2039,9 @@ int pagecache_write_end(struct file *file, struct address_space *mapping, struct page *page, void *fsdata) { const struct address_space_operations *aops = mapping->a_ops; - int ret; - - if (aops->write_end) { - mark_page_accessed(page); - ret = aops->write_end(file, mapping, pos, len, copied, - page, fsdata); - } else { - unsigned offset = pos & (PAGE_CACHE_SIZE - 1); - struct inode *inode = mapping->host; - - flush_dcache_page(page); - ret = aops->commit_write(file, page, offset, offset+len); - unlock_page(page); - mark_page_accessed(page); - page_cache_release(page); - - if (ret < 0) { - if (pos + len > inode->i_size) - vmtruncate(inode, inode->i_size); - } else if (ret > 0) - ret = min_t(size_t, copied, ret); - else - ret = copied; - } - return ret; + mark_page_accessed(page); + return aops->write_end(file, mapping, pos, len, copied, page, fsdata); } EXPORT_SYMBOL(pagecache_write_end); @@ -2226,174 +2163,6 @@ repeat: } EXPORT_SYMBOL(__grab_cache_page); -static ssize_t generic_perform_write_2copy(struct file *file, - struct iov_iter *i, loff_t pos) -{ - struct address_space *mapping = file->f_mapping; - const struct address_space_operations *a_ops = mapping->a_ops; - struct inode *inode = mapping->host; - long status = 0; - ssize_t written = 0; - - do { - struct page *src_page; - struct page *page; - pgoff_t index; /* Pagecache index for current page */ - unsigned long offset; /* Offset into pagecache page */ - unsigned long bytes; /* Bytes to write to page */ - size_t copied; /* Bytes copied from user */ - - offset = (pos & (PAGE_CACHE_SIZE - 1)); - index = pos >> PAGE_CACHE_SHIFT; - bytes = min_t(unsigned long, PAGE_CACHE_SIZE - offset, - iov_iter_count(i)); - - /* - * a non-NULL src_page indicates that we're doing the - * copy via get_user_pages and kmap. - */ - src_page = NULL; - - /* - * Bring in the user page that we will copy from _first_. - * Otherwise there's a nasty deadlock on copying from the - * same page as we're writing to, without it being marked - * up-to-date. - * - * Not only is this an optimisation, but it is also required - * to check that the address is actually valid, when atomic - * usercopies are used, below. - */ - if (unlikely(iov_iter_fault_in_readable(i, bytes))) { - status = -EFAULT; - break; - } - - page = __grab_cache_page(mapping, index); - if (!page) { - status = -ENOMEM; - break; - } - - /* - * non-uptodate pages cannot cope with short copies, and we - * cannot take a pagefault with the destination page locked. - * So pin the source page to copy it. - */ - if (!PageUptodate(page) && !segment_eq(get_fs(), KERNEL_DS)) { - unlock_page(page); - - src_page = alloc_page(GFP_KERNEL); - if (!src_page) { - page_cache_release(page); - status = -ENOMEM; - break; - } - - /* - * Cannot get_user_pages with a page locked for the - * same reason as we can't take a page fault with a - * page locked (as explained below). - */ - copied = iov_iter_copy_from_user(src_page, i, - offset, bytes); - if (unlikely(copied == 0)) { - status = -EFAULT; - page_cache_release(page); - page_cache_release(src_page); - break; - } - bytes = copied; - - lock_page(page); - /* - * Can't handle the page going uptodate here, because - * that means we would use non-atomic usercopies, which - * zero out the tail of the page, which can cause - * zeroes to become transiently visible. We could just - * use a non-zeroing copy, but the APIs aren't too - * consistent. - */ - if (unlikely(!page->mapping || PageUptodate(page))) { - unlock_page(page); - page_cache_release(page); - page_cache_release(src_page); - continue; - } - } - - status = a_ops->prepare_write(file, page, offset, offset+bytes); - if (unlikely(status)) - goto fs_write_aop_error; - - if (!src_page) { - /* - * Must not enter the pagefault handler here, because - * we hold the page lock, so we might recursively - * deadlock on the same lock, or get an ABBA deadlock - * against a different lock, or against the mmap_sem - * (which nests outside the page lock). So increment - * preempt count, and use _atomic usercopies. - * - * The page is uptodate so we are OK to encounter a - * short copy: if unmodified parts of the page are - * marked dirty and written out to disk, it doesn't - * really matter. - */ - pagefault_disable(); - copied = iov_iter_copy_from_user_atomic(page, i, - offset, bytes); - pagefault_enable(); - } else { - void *src, *dst; - src = kmap_atomic(src_page, KM_USER0); - dst = kmap_atomic(page, KM_USER1); - memcpy(dst + offset, src + offset, bytes); - kunmap_atomic(dst, KM_USER1); - kunmap_atomic(src, KM_USER0); - copied = bytes; - } - flush_dcache_page(page); - - status = a_ops->commit_write(file, page, offset, offset+bytes); - if (unlikely(status < 0)) - goto fs_write_aop_error; - if (unlikely(status > 0)) /* filesystem did partial write */ - copied = min_t(size_t, copied, status); - - unlock_page(page); - mark_page_accessed(page); - page_cache_release(page); - if (src_page) - page_cache_release(src_page); - - iov_iter_advance(i, copied); - pos += copied; - written += copied; - - balance_dirty_pages_ratelimited(mapping); - cond_resched(); - continue; - -fs_write_aop_error: - unlock_page(page); - page_cache_release(page); - if (src_page) - page_cache_release(src_page); - - /* - * prepare_write() may have instantiated a few blocks - * outside i_size. Trim these off again. Don't need - * i_size_read because we hold i_mutex. - */ - if (pos + bytes > inode->i_size) - vmtruncate(inode, inode->i_size); - break; - } while (iov_iter_count(i)); - - return written ? written : status; -} - static ssize_t generic_perform_write(struct file *file, struct iov_iter *i, loff_t pos) { @@ -2494,10 +2263,7 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov, struct iov_iter i; iov_iter_init(&i, iov, nr_segs, count, written); - if (a_ops->write_begin) - status = generic_perform_write(file, &i, pos); - else - status = generic_perform_write_2copy(file, &i, pos); + status = generic_perform_write(file, &i, pos); if (likely(status >= 0)) { written += status; -- cgit v1.2.2 From e99c97ade53fb6f5e665f2960eb86c624a532d7b Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Wed, 29 Oct 2008 14:01:09 -0700 Subject: mm: fix kernel-doc function notation Delete excess kernel-doc notation in mm/ subdirectory. Actually this is a kernel-doc notation fix. Warning(/var/linsrc/linux-2.6.27-git10//mm/vmalloc.c:902): Excess function parameter or struct member 'returns' description in 'vm_map_ram' Signed-off-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmalloc.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 036536945dd9..f1cc03bbf6ac 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -897,7 +897,8 @@ EXPORT_SYMBOL(vm_unmap_ram); * @count: number of pages * @node: prefer to allocate data structures on this node * @prot: memory protection to use. PAGE_KERNEL for regular RAM - * @returns: a pointer to the address that has been mapped, or NULL on failure + * + * Returns: a pointer to the address that has been mapped, or %NULL on failure */ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot) { -- cgit v1.2.2 From 731572d39fcd3498702eda4600db4c43d51e0b26 Mon Sep 17 00:00:00 2001 From: Alan Cox Date: Wed, 29 Oct 2008 14:01:20 -0700 Subject: nfsd: fix vm overcommit crash Junjiro R. Okajima reported a problem where knfsd crashes if you are using it to export shmemfs objects and run strict overcommit. In this situation the current->mm based modifier to the overcommit goes through a NULL pointer. We could simply check for NULL and skip the modifier but we've caught other real bugs in the past from mm being NULL here - cases where we did need a valid mm set up (eg the exec bug about a year ago). To preserve the checks and get the logic we want shuffle the checking around and add a new helper to the vm_ security wrappers Also fix a current->mm reference in nommu that should use the passed mm [akpm@linux-foundation.org: coding-style fixes] [akpm@linux-foundation.org: fix build] Reported-by: Junjiro R. Okajima Acked-by: James Morris Signed-off-by: Alan Cox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 3 ++- mm/nommu.c | 3 ++- mm/shmem.c | 8 ++++---- 3 files changed, 8 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/mmap.c b/mm/mmap.c index 74f4d158022e..de14ac21e5b5 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -175,7 +175,8 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) /* Don't let a single process grow too big: leave 3% of the size of this process for other processes */ - allowed -= mm->total_vm / 32; + if (mm) + allowed -= mm->total_vm / 32; /* * cast `allowed' as a signed long because vm_committed_space diff --git a/mm/nommu.c b/mm/nommu.c index 2696b24f2bb3..7695dc850785 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1454,7 +1454,8 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) /* Don't let a single process grow too big: leave 3% of the size of this process for other processes */ - allowed -= current->mm->total_vm / 32; + if (mm) + allowed -= mm->total_vm / 32; /* * cast `allowed' as a signed long because vm_committed_space diff --git a/mm/shmem.c b/mm/shmem.c index d38d7e61fcd0..0ed075215e5f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -161,8 +161,8 @@ static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) */ static inline int shmem_acct_size(unsigned long flags, loff_t size) { - return (flags & VM_ACCOUNT)? - security_vm_enough_memory(VM_ACCT(size)): 0; + return (flags & VM_ACCOUNT) ? + security_vm_enough_memory_kern(VM_ACCT(size)) : 0; } static inline void shmem_unacct_size(unsigned long flags, loff_t size) @@ -179,8 +179,8 @@ static inline void shmem_unacct_size(unsigned long flags, loff_t size) */ static inline int shmem_acct_block(unsigned long flags) { - return (flags & VM_ACCOUNT)? - 0: security_vm_enough_memory(VM_ACCT(PAGE_CACHE_SIZE)); + return (flags & VM_ACCOUNT) ? + 0 : security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)); } static inline void shmem_unacct_blocks(unsigned long flags, long pages) -- cgit v1.2.2 From ab4f2ee130d5ffcf35616e1f5c6ab75af5b463b6 Mon Sep 17 00:00:00 2001 From: Russell King Date: Thu, 6 Nov 2008 17:11:07 +0000 Subject: [ARM] fix naming of MODULE_START / MODULE_END As of 73bdf0a60e607f4b8ecc5aec597105976565a84f, the kernel needs to know where modules are located in the virtual address space. On ARM, we located this region between MODULE_START and MODULE_END. Unfortunately, everyone else calls it MODULES_VADDR and MODULES_END. Update ARM to use the same naming, so is_vmalloc_or_module_addr() can work properly. Also update the comment on mm/vmalloc.c to reflect that ARM also places modules in a separate region from the vmalloc space. Signed-off-by: Russell King --- mm/vmalloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index f1cc03bbf6ac..66fad3fc02b1 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -178,7 +178,7 @@ static int vmap_page_range(unsigned long addr, unsigned long end, static inline int is_vmalloc_or_module_addr(const void *x) { /* - * x86-64 and sparc64 put modules in a special place, + * ARM, x86-64 and sparc64 put modules in a special place, * and fall back on vmalloc() if that fails. Others * just put it in the vmalloc space. */ -- cgit v1.2.2 From 69d177c2fc702d402b17fdca2190d5a7e3ca55c5 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Thu, 6 Nov 2008 12:53:26 -0800 Subject: hugetlbfs: handle pages higher order than MAX_ORDER When working with hugepages, hugetlbfs assumes that those hugepages are smaller than MAX_ORDER. Specifically it assumes that the mem_map is contigious and uses that to optimise access to the elements of the mem_map that represent the hugepage. Gigantic pages (such as 16GB pages on powerpc) by definition are of greater order than MAX_ORDER (larger than MAX_ORDER_NR_PAGES in size). This means that we can no longer make use of the buddy alloctor guarentees for the contiguity of the mem_map, which ensures that the mem_map is at least contigious for maximmally aligned areas of MAX_ORDER_NR_PAGES pages. This patch adds new mem_map accessors and iterator helpers which handle any discontiguity at MAX_ORDER_NR_PAGES boundaries. It then uses these to implement gigantic page versions of copy_huge_page and clear_huge_page, and to allow follow_hugetlb_page handle gigantic pages. Signed-off-by: Andy Whitcroft Cc: Jon Tollefson Cc: Mel Gorman Cc: Nick Piggin Cc: Christoph Lameter Cc: [2.6.27.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 37 ++++++++++++++++++++++++++++++++++++- mm/internal.h | 28 ++++++++++++++++++++++++++++ 2 files changed, 64 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 421aee99b84a..e6afe527bd09 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -354,11 +354,26 @@ static int vma_has_reserves(struct vm_area_struct *vma) return 0; } +static void clear_gigantic_page(struct page *page, + unsigned long addr, unsigned long sz) +{ + int i; + struct page *p = page; + + might_sleep(); + for (i = 0; i < sz/PAGE_SIZE; i++, p = mem_map_next(p, page, i)) { + cond_resched(); + clear_user_highpage(p, addr + i * PAGE_SIZE); + } +} static void clear_huge_page(struct page *page, unsigned long addr, unsigned long sz) { int i; + if (unlikely(sz > MAX_ORDER_NR_PAGES)) + return clear_gigantic_page(page, addr, sz); + might_sleep(); for (i = 0; i < sz/PAGE_SIZE; i++) { cond_resched(); @@ -366,12 +381,32 @@ static void clear_huge_page(struct page *page, } } +static void copy_gigantic_page(struct page *dst, struct page *src, + unsigned long addr, struct vm_area_struct *vma) +{ + int i; + struct hstate *h = hstate_vma(vma); + struct page *dst_base = dst; + struct page *src_base = src; + might_sleep(); + for (i = 0; i < pages_per_huge_page(h); ) { + cond_resched(); + copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma); + + i++; + dst = mem_map_next(dst, dst_base, i); + src = mem_map_next(src, src_base, i); + } +} static void copy_huge_page(struct page *dst, struct page *src, unsigned long addr, struct vm_area_struct *vma) { int i; struct hstate *h = hstate_vma(vma); + if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) + return copy_gigantic_page(dst, src, addr, vma); + might_sleep(); for (i = 0; i < pages_per_huge_page(h); i++) { cond_resched(); @@ -2130,7 +2165,7 @@ same_page: if (zeropage_ok) pages[i] = ZERO_PAGE(0); else - pages[i] = page + pfn_offset; + pages[i] = mem_map_offset(page, pfn_offset); get_page(pages[i]); } diff --git a/mm/internal.h b/mm/internal.h index e4e728bdf324..f482460de3e6 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -175,6 +175,34 @@ static inline void free_page_mlock(struct page *page) { } #endif /* CONFIG_UNEVICTABLE_LRU */ +/* + * Return the mem_map entry representing the 'offset' subpage within + * the maximally aligned gigantic page 'base'. Handle any discontiguity + * in the mem_map at MAX_ORDER_NR_PAGES boundaries. + */ +static inline struct page *mem_map_offset(struct page *base, int offset) +{ + if (unlikely(offset >= MAX_ORDER_NR_PAGES)) + return pfn_to_page(page_to_pfn(base) + offset); + return base + offset; +} + +/* + * Iterator over all subpages withing the maximally aligned gigantic + * page 'base'. Handle any discontiguity in the mem_map. + */ +static inline struct page *mem_map_next(struct page *iter, + struct page *base, int offset) +{ + if (unlikely((offset & (MAX_ORDER_NR_PAGES - 1)) == 0)) { + unsigned long pfn = page_to_pfn(base) + offset; + if (!pfn_valid(pfn)) + return NULL; + return pfn_to_page(pfn); + } + return iter + 1; +} + /* * FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node, * so all functions starting at paging_init should be marked __init -- cgit v1.2.2 From 18229df5b613ed0732a766fc37850de2e7988e43 Mon Sep 17 00:00:00 2001 From: Andy Whitcroft Date: Thu, 6 Nov 2008 12:53:27 -0800 Subject: hugetlb: pull gigantic page initialisation out of the default path As we can determine exactly when a gigantic page is in use we can optimise the common regular page cases by pulling out gigantic page initialisation into its own function. As gigantic pages are never released to buddy we do not need a destructor. This effectivly reverts the previous change to the main buddy allocator. It also adds a paranoid check to ensure we never release gigantic pages from hugetlbfs to the main buddy. Signed-off-by: Andy Whitcroft Cc: Jon Tollefson Cc: Mel Gorman Cc: Nick Piggin Cc: Christoph Lameter Cc: [2.6.27.x] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 12 +++++++++++- mm/internal.h | 1 + mm/page_alloc.c | 28 +++++++++++++++++++++------- 3 files changed, 33 insertions(+), 8 deletions(-) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e6afe527bd09..d143ab67be44 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -491,6 +491,8 @@ static void update_and_free_page(struct hstate *h, struct page *page) { int i; + VM_BUG_ON(h->order >= MAX_ORDER); + h->nr_huge_pages--; h->nr_huge_pages_node[page_to_nid(page)]--; for (i = 0; i < pages_per_huge_page(h); i++) { @@ -1005,6 +1007,14 @@ found: return 1; } +static void prep_compound_huge_page(struct page *page, int order) +{ + if (unlikely(order > (MAX_ORDER - 1))) + prep_compound_gigantic_page(page, order); + else + prep_compound_page(page, order); +} + /* Put bootmem huge pages into the standard lists after mem_map is up */ static void __init gather_bootmem_prealloc(void) { @@ -1015,7 +1025,7 @@ static void __init gather_bootmem_prealloc(void) struct hstate *h = m->hstate; __ClearPageReserved(page); WARN_ON(page_count(page) != 1); - prep_compound_page(page, h->order); + prep_compound_huge_page(page, h->order); prep_new_huge_page(h, page, page_to_nid(page)); } } diff --git a/mm/internal.h b/mm/internal.h index f482460de3e6..13333bc2eb68 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -17,6 +17,7 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling); extern void prep_compound_page(struct page *page, unsigned long order); +extern void prep_compound_gigantic_page(struct page *page, unsigned long order); static inline void set_page_count(struct page *page, int v) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d0a240fbb8bf..54069e64e3a8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -260,6 +260,23 @@ static void free_compound_page(struct page *page) } void prep_compound_page(struct page *page, unsigned long order) +{ + int i; + int nr_pages = 1 << order; + + set_compound_page_dtor(page, free_compound_page); + set_compound_order(page, order); + __SetPageHead(page); + for (i = 1; i < nr_pages; i++) { + struct page *p = page + i; + + __SetPageTail(p); + p->first_page = page; + } +} + +#ifdef CONFIG_HUGETLBFS +void prep_compound_gigantic_page(struct page *page, unsigned long order) { int i; int nr_pages = 1 << order; @@ -268,19 +285,17 @@ void prep_compound_page(struct page *page, unsigned long order) set_compound_page_dtor(page, free_compound_page); set_compound_order(page, order); __SetPageHead(page); - for (i = 1; i < nr_pages; i++, p++) { - if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0)) - p = pfn_to_page(page_to_pfn(page) + i); + for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { __SetPageTail(p); p->first_page = page; } } +#endif static void destroy_compound_page(struct page *page, unsigned long order) { int i; int nr_pages = 1 << order; - struct page *p = page + 1; if (unlikely(compound_order(page) != order)) bad_page(page); @@ -288,9 +303,8 @@ static void destroy_compound_page(struct page *page, unsigned long order) if (unlikely(!PageHead(page))) bad_page(page); __ClearPageHead(page); - for (i = 1; i < nr_pages; i++, p++) { - if (unlikely((i & (MAX_ORDER_NR_PAGES - 1)) == 0)) - p = pfn_to_page(page_to_pfn(page) + i); + for (i = 1; i < nr_pages; i++) { + struct page *p = page + i; if (unlikely(!PageTail(p) | (p->first_page != page))) -- cgit v1.2.2 From b4416d2bea007f07f2e74cdc4cb64042ec996c83 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 6 Nov 2008 12:53:29 -0800 Subject: oom: do not dump task state for non thread group leaders When /proc/sys/vm/oom_dump_tasks is enabled, it's only necessary to dump task state information for thread group leaders. The kernel log gets quickly overwhelmed on machines with a massive number of threads by dumping non-thread group leaders. Reviewed-by: Christoph Lameter Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/oom_kill.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm') diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 64e5b4bcd964..2846a58e5de9 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -295,6 +295,8 @@ static void dump_tasks(const struct mem_cgroup *mem) continue; if (mem && !task_in_mem_cgroup(p, mem)) continue; + if (!thread_group_leader(p)) + continue; task_lock(p); printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n", -- cgit v1.2.2 From 0aedadf91a70a11c4a3e7c7d99b21e5528af8d5d Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 6 Nov 2008 12:53:30 -0800 Subject: mm: move migrate_prep out from under mmap_sem Move the migrate_prep outside the mmap_sem for the following system calls 1. sys_move_pages 2. sys_migrate_pages 3. sys_mbind() It really does not matter when we flush the lru. The system is free to add pages onto the lru even during migration which will make the page migration either skip the page (mbind, migrate_pages) or return a busy state (move_pages). Fixes this lockdep warning (and potential deadlock): Some VM place has mmap_sem -> kevent_wq via lru_add_drain_all() net/core/dev.c::dev_ioctl() has rtnl_lock -> mmap_sem (*) the ioctl has copy_from_user() and it can do page fault. linkwatch_event has kevent_wq -> rtnl_lock Signed-off-by: Christoph Lameter Cc: KOSAKI Motohiro Reported-by: Heiko Carstens Cc: Nick Piggin Cc: Hugh Dickins Cc: Rik van Riel Cc: Lee Schermerhorn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 18 +++++++++++------- mm/migrate.c | 2 +- 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'mm') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 36f42573a335..e9493b1c1117 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -489,12 +489,6 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end, int err; struct vm_area_struct *first, *vma, *prev; - if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { - - err = migrate_prep(); - if (err) - return ERR_PTR(err); - } first = find_vma(mm, start); if (!first) @@ -809,9 +803,13 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags) { int busy = 0; - int err = 0; + int err; nodemask_t tmp; + err = migrate_prep(); + if (err) + return err; + down_read(&mm->mmap_sem); err = migrate_vmas(mm, from_nodes, to_nodes, flags); @@ -974,6 +972,12 @@ static long do_mbind(unsigned long start, unsigned long len, start, start + len, mode, mode_flags, nmask ? nodes_addr(*nmask)[0] : -1); + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) { + + err = migrate_prep(); + if (err) + return err; + } down_write(&mm->mmap_sem); vma = check_range(mm, start, end, nmask, flags | MPOL_MF_INVERT, &pagelist); diff --git a/mm/migrate.c b/mm/migrate.c index 6602941bfab0..385db89f0c33 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -841,12 +841,12 @@ static int do_move_page_to_node_array(struct mm_struct *mm, struct page_to_node *pp; LIST_HEAD(pagelist); + migrate_prep(); down_read(&mm->mmap_sem); /* * Build a list of pages to migrate */ - migrate_prep(); for (pp = pm; pp->node != MAX_NUMNODES; pp++) { struct vm_area_struct *vma; struct page *page; -- cgit v1.2.2 From b41ad14c30acf023d09ac064096a4cf41248ce46 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 6 Nov 2008 12:53:31 -0800 Subject: vmemmap: warn about page_structs with remote distance It's insufficient to simply compare node ids when warning about offnode page_structs since it's possible to still have local affinity. Acked-by: Christoph Lameter Signed-off-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/sparse-vmemmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index a91b5f8fcaf6..a13ea6401ae7 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -64,7 +64,7 @@ void __meminit vmemmap_verify(pte_t *pte, int node, unsigned long pfn = pte_pfn(*pte); int actual_node = early_pfn_to_nid(pfn); - if (actual_node != node) + if (node_distance(actual_node, node) > LOCAL_DISTANCE) printk(KERN_WARNING "[%lx-%lx] potential offnode " "page_structs\n", start, end - 1); } -- cgit v1.2.2 From fbdd12676c83df77480f00ebd32fc98fbe3bf836 Mon Sep 17 00:00:00 2001 From: Qinghuang Feng Date: Thu, 6 Nov 2008 12:53:34 -0800 Subject: mm/oom_kill.c: fix badness() kerneldoc Paramter @mem has been removed since v2.6.26, now delete it's comment. Signed-off-by: Qinghuang Feng Acked-by: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/oom_kill.c | 1 - 1 file changed, 1 deletion(-) (limited to 'mm') diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 2846a58e5de9..a0a01902f551 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -38,7 +38,6 @@ static DEFINE_SPINLOCK(zone_scan_mutex); * badness - calculate a numeric value for how bad this task has been * @p: task struct of which task we should calculate * @uptime: current uptime in seconds - * @mem: target memory controller * * The formula used is relatively simple and documented inline in the * function. The main rationale is that we want to select a good task -- cgit v1.2.2 From a70dcb969f64e2fa98c24f47854f20bf02ff0092 Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Thu, 6 Nov 2008 12:53:36 -0800 Subject: memory hotplug: fix page_zone() calculation in test_pages_isolated() My last bugfix here (adding zone->lock) introduced a new problem: Using page_zone(pfn_to_page(pfn)) to get the zone after the for() loop is wrong. pfn will then be >= end_pfn, which may be in a different zone or not present at all. This may lead to an addressing exception in page_zone() or spin_lock_irqsave(). Now I use __first_valid_page() again after the loop to find a valid page for page_zone(). Signed-off-by: Gerald Schaefer Acked-by: Nathan Fontenot Reviewed-by: KAMEZAWA Hiroyuki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_isolation.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/page_isolation.c b/mm/page_isolation.c index b70a7fec1ff6..5e0ffd967452 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -130,10 +130,11 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn) if (page && get_pageblock_migratetype(page) != MIGRATE_ISOLATE) break; } - if (pfn < end_pfn) + page = __first_valid_page(start_pfn, end_pfn - start_pfn); + if ((pfn < end_pfn) || !page) return -EBUSY; /* Check all pages are free or Marked as ISOLATED */ - zone = page_zone(pfn_to_page(pfn)); + zone = page_zone(page); spin_lock_irqsave(&zone->lock, flags); ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn); spin_unlock_irqrestore(&zone->lock, flags); -- cgit v1.2.2 From 9b46333406b9cb3397ab538485a4d57c316af0ff Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Tue, 28 Oct 2008 19:22:34 +1100 Subject: vmap: cope with vm_unmap_aliases before vmalloc_init() Xen can end up calling vm_unmap_aliases() before vmalloc_init() has been called. In this case its safe to make it a simple no-op. Signed-off-by: Jeremy Fitzhardinge Cc: Linux Memory Management List Cc: Nick Piggin Signed-off-by: Ingo Molnar --- mm/vmalloc.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 66fad3fc02b1..ba6b0f5f7fac 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -592,6 +592,8 @@ static void free_unmap_vmap_area_addr(unsigned long addr) #define VMAP_BLOCK_SIZE (VMAP_BBMAP_BITS * PAGE_SIZE) +static bool vmap_initialized __read_mostly = false; + struct vmap_block_queue { spinlock_t lock; struct list_head free; @@ -828,6 +830,9 @@ void vm_unmap_aliases(void) int cpu; int flush = 0; + if (unlikely(!vmap_initialized)) + return; + for_each_possible_cpu(cpu) { struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu); struct vmap_block *vb; @@ -942,6 +947,8 @@ void __init vmalloc_init(void) INIT_LIST_HEAD(&vbq->dirty); vbq->nr_dirty = 0; } + + vmap_initialized = true; } void unmap_kernel_range(unsigned long addr, unsigned long size) -- cgit v1.2.2