diff options
author | Trond Myklebust <Trond.Myklebust@netapp.com> | 2006-06-24 08:41:41 -0400 |
---|---|---|
committer | Trond Myklebust <Trond.Myklebust@netapp.com> | 2006-06-24 13:07:53 -0400 |
commit | 816724e65c72a90a44fbad0ef0b59b186c85fa90 (patch) | |
tree | 421fa29aedff988e392f92780637553e275d37a0 /mm | |
parent | 70ac4385a13f78bc478f26d317511893741b05bd (diff) | |
parent | d384ea691fe4ea8c2dd5b9b8d9042eb181776f18 (diff) | |
download | linux-3.10-816724e65c72a90a44fbad0ef0b59b186c85fa90.tar.gz linux-3.10-816724e65c72a90a44fbad0ef0b59b186c85fa90.tar.bz2 linux-3.10-816724e65c72a90a44fbad0ef0b59b186c85fa90.zip |
Merge branch 'master' of /home/trondmy/kernel/linux-2.6/
Conflicts:
fs/nfs/inode.c
fs/super.c
Fix conflicts between patch 'NFS: Split fs/nfs/inode.c' and patch
'VFS: Permit filesystem to override root dentry on mount'
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 4 | ||||
-rw-r--r-- | mm/filemap.c | 183 | ||||
-rw-r--r-- | mm/filemap.h | 6 | ||||
-rw-r--r-- | mm/fremap.c | 9 | ||||
-rw-r--r-- | mm/hugetlb.c | 282 | ||||
-rw-r--r-- | mm/memory.c | 125 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 27 | ||||
-rw-r--r-- | mm/mempolicy.c | 36 | ||||
-rw-r--r-- | mm/migrate.c | 1058 | ||||
-rw-r--r-- | mm/mmap.c | 12 | ||||
-rw-r--r-- | mm/mprotect.c | 37 | ||||
-rw-r--r-- | mm/msync.c | 3 | ||||
-rw-r--r-- | mm/oom_kill.c | 9 | ||||
-rw-r--r-- | mm/page-writeback.c | 3 | ||||
-rw-r--r-- | mm/page_alloc.c | 184 | ||||
-rw-r--r-- | mm/pdflush.c | 3 | ||||
-rw-r--r-- | mm/rmap.c | 107 | ||||
-rw-r--r-- | mm/shmem.c | 18 | ||||
-rw-r--r-- | mm/slab.c | 249 | ||||
-rw-r--r-- | mm/sparse.c | 22 | ||||
-rw-r--r-- | mm/swap.c | 42 | ||||
-rw-r--r-- | mm/swapfile.c | 43 | ||||
-rw-r--r-- | mm/truncate.c | 22 | ||||
-rw-r--r-- | mm/vmalloc.c | 122 | ||||
-rw-r--r-- | mm/vmscan.c | 240 |
25 files changed, 1816 insertions, 1030 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 332f5c29b53..66e65ab3942 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -138,8 +138,8 @@ config SPLIT_PTLOCK_CPUS # config MIGRATION bool "Page migration" - def_bool y if NUMA - depends on SWAP && NUMA + def_bool y + depends on NUMA help Allows the migration of the physical location of pages of processes while the virtual addresses are not changed. This is useful for diff --git a/mm/filemap.c b/mm/filemap.c index fd57442186c..807a463fd5e 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <linux/compiler.h> #include <linux/fs.h> +#include <linux/uaccess.h> #include <linux/aio.h> #include <linux/capability.h> #include <linux/kernel_stat.h> @@ -38,7 +39,6 @@ */ #include <linux/buffer_head.h> /* for generic_osync_inode */ -#include <asm/uaccess.h> #include <asm/mman.h> static ssize_t @@ -171,15 +171,17 @@ static int sync_page(void *word) } /** - * filemap_fdatawrite_range - start writeback against all of a mapping's - * dirty pages that lie within the byte offsets <start, end> + * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write * @start: offset in bytes where the range starts * @end: offset in bytes where the range ends (inclusive) * @sync_mode: enable synchronous operation * + * Start writeback against all of a mapping's dirty pages that lie + * within the byte offsets <start, end> inclusive. + * * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as - * opposed to a regular memory * cleansing writeback. The difference between + * opposed to a regular memory cleansing writeback. The difference between * these two operations is that if a dirty page/buffer is encountered, it must * be waited upon, and not just skipped over. */ @@ -190,8 +192,8 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, struct writeback_control wbc = { .sync_mode = sync_mode, .nr_to_write = mapping->nrpages * 2, - .start = start, - .end = end, + .range_start = start, + .range_end = end, }; if (!mapping_cap_writeback_dirty(mapping)) @@ -204,7 +206,7 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start, static inline int __filemap_fdatawrite(struct address_space *mapping, int sync_mode) { - return __filemap_fdatawrite_range(mapping, 0, 0, sync_mode); + return __filemap_fdatawrite_range(mapping, 0, LLONG_MAX, sync_mode); } int filemap_fdatawrite(struct address_space *mapping) @@ -219,7 +221,10 @@ static int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL); } -/* +/** + * filemap_flush - mostly a non-blocking flush + * @mapping: target address_space + * * This is a mostly non-blocking flush. Not suitable for data-integrity * purposes - I/O may not be started against all dirty pages. */ @@ -229,7 +234,12 @@ int filemap_flush(struct address_space *mapping) } EXPORT_SYMBOL(filemap_flush); -/* +/** + * wait_on_page_writeback_range - wait for writeback to complete + * @mapping: target address_space + * @start: beginning page index + * @end: ending page index + * * Wait for writeback to complete against pages indexed by start->end * inclusive */ @@ -276,7 +286,13 @@ int wait_on_page_writeback_range(struct address_space *mapping, return ret; } -/* +/** + * sync_page_range - write and wait on all pages in the passed range + * @inode: target inode + * @mapping: target address_space + * @pos: beginning offset in pages to write + * @count: number of bytes to write + * * Write and wait upon all the pages in the passed range. This is a "data * integrity" operation. It waits upon in-flight writeout before starting and * waiting upon new writeout. If there was an IO error, return it. @@ -305,7 +321,13 @@ int sync_page_range(struct inode *inode, struct address_space *mapping, } EXPORT_SYMBOL(sync_page_range); -/* +/** + * sync_page_range_nolock + * @inode: target inode + * @mapping: target address_space + * @pos: beginning offset in pages to write + * @count: number of bytes to write + * * Note: Holding i_mutex across sync_page_range_nolock is not a good idea * as it forces O_SYNC writers to different parts of the same file * to be serialised right until io completion. @@ -329,10 +351,11 @@ int sync_page_range_nolock(struct inode *inode, struct address_space *mapping, EXPORT_SYMBOL(sync_page_range_nolock); /** - * filemap_fdatawait - walk the list of under-writeback pages of the given - * address space and wait for all of them. - * + * filemap_fdatawait - wait for all under-writeback pages to complete * @mapping: address space structure to wait for + * + * Walk the list of under-writeback pages of the given address space + * and wait for all of them. */ int filemap_fdatawait(struct address_space *mapping) { @@ -368,7 +391,12 @@ int filemap_write_and_wait(struct address_space *mapping) } EXPORT_SYMBOL(filemap_write_and_wait); -/* +/** + * filemap_write_and_wait_range - write out & wait on a file range + * @mapping: the address_space for the pages + * @lstart: offset in bytes where the range starts + * @lend: offset in bytes where the range ends (inclusive) + * * Write out and wait upon file offsets lstart->lend, inclusive. * * Note that `lend' is inclusive (describes the last byte to be written) so @@ -394,8 +422,14 @@ int filemap_write_and_wait_range(struct address_space *mapping, return err; } -/* - * This function is used to add newly allocated pagecache pages: +/** + * add_to_page_cache - add newly allocated pagecache pages + * @page: page to add + * @mapping: the page's address_space + * @offset: page index + * @gfp_mask: page allocation mode + * + * This function is used to add newly allocated pagecache pages; * the page is new, so we can just run SetPageLocked() against it. * The other page state flags were set by rmqueue(). * @@ -422,7 +456,6 @@ int add_to_page_cache(struct page *page, struct address_space *mapping, } return error; } - EXPORT_SYMBOL(add_to_page_cache); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, @@ -489,8 +522,7 @@ void fastcall wait_on_page_bit(struct page *page, int bit_nr) EXPORT_SYMBOL(wait_on_page_bit); /** - * unlock_page() - unlock a locked page - * + * unlock_page - unlock a locked page * @page: the page * * Unlocks the page and wakes up sleepers in ___wait_on_page_locked(). @@ -513,8 +545,9 @@ void fastcall unlock_page(struct page *page) } EXPORT_SYMBOL(unlock_page); -/* - * End writeback against a page. +/** + * end_page_writeback - end writeback against a page + * @page: the page */ void end_page_writeback(struct page *page) { @@ -527,10 +560,11 @@ void end_page_writeback(struct page *page) } EXPORT_SYMBOL(end_page_writeback); -/* - * Get a lock on the page, assuming we need to sleep to get it. +/** + * __lock_page - get a lock on the page, assuming we need to sleep to get it + * @page: the page to lock * - * Ugly: running sync_page() in state TASK_UNINTERRUPTIBLE is scary. If some + * Ugly. Running sync_page() in state TASK_UNINTERRUPTIBLE is scary. If some * random driver's requestfn sets TASK_RUNNING, we could busywait. However * chances are that on the second loop, the block layer's plug list is empty, * so sync_page() will then return in state TASK_UNINTERRUPTIBLE. @@ -544,8 +578,12 @@ void fastcall __lock_page(struct page *page) } EXPORT_SYMBOL(__lock_page); -/* - * a rather lightweight function, finding and getting a reference to a +/** + * find_get_page - find and get a page reference + * @mapping: the address_space to search + * @offset: the page index + * + * A rather lightweight function, finding and getting a reference to a * hashed page atomically. */ struct page * find_get_page(struct address_space *mapping, unsigned long offset) @@ -559,11 +597,14 @@ struct page * find_get_page(struct address_space *mapping, unsigned long offset) read_unlock_irq(&mapping->tree_lock); return page; } - EXPORT_SYMBOL(find_get_page); -/* - * Same as above, but trylock it instead of incrementing the count. +/** + * find_trylock_page - find and lock a page + * @mapping: the address_space to search + * @offset: the page index + * + * Same as find_get_page(), but trylock it instead of incrementing the count. */ struct page *find_trylock_page(struct address_space *mapping, unsigned long offset) { @@ -576,12 +617,10 @@ struct page *find_trylock_page(struct address_space *mapping, unsigned long offs read_unlock_irq(&mapping->tree_lock); return page; } - EXPORT_SYMBOL(find_trylock_page); /** * find_lock_page - locate, pin and lock a pagecache page - * * @mapping: the address_space to search * @offset: the page index * @@ -617,12 +656,10 @@ repeat: read_unlock_irq(&mapping->tree_lock); return page; } - EXPORT_SYMBOL(find_lock_page); /** * find_or_create_page - locate or add a pagecache page - * * @mapping: the page's address_space * @index: the page's index into the mapping * @gfp_mask: page allocation mode @@ -663,7 +700,6 @@ repeat: page_cache_release(cached_page); return page; } - EXPORT_SYMBOL(find_or_create_page); /** @@ -729,9 +765,16 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, return i; } -/* +/** + * find_get_pages_tag - find and return pages that match @tag + * @mapping: the address_space to search + * @index: the starting page index + * @tag: the tag index + * @nr_pages: the maximum number of pages + * @pages: where the resulting pages are placed + * * Like find_get_pages, except we only return pages which are tagged with - * `tag'. We update *index to index the next page for the traversal. + * @tag. We update @index to index the next page for the traversal. */ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, int tag, unsigned int nr_pages, struct page **pages) @@ -750,7 +793,11 @@ unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, return ret; } -/* +/** + * grab_cache_page_nowait - returns locked page at given index in given cache + * @mapping: target address_space + * @index: the page index + * * Same as grab_cache_page, but do not wait if the page is unavailable. * This is intended for speculative data generators, where the data can * be regenerated if the page couldn't be grabbed. This routine should @@ -779,19 +826,25 @@ grab_cache_page_nowait(struct address_space *mapping, unsigned long index) } return page; } - EXPORT_SYMBOL(grab_cache_page_nowait); -/* +/** + * do_generic_mapping_read - generic file read routine + * @mapping: address_space to be read + * @_ra: file's readahead state + * @filp: the file to read + * @ppos: current file position + * @desc: read_descriptor + * @actor: read method + * * This is a generic file read routine, and uses the - * mapping->a_ops->readpage() function for the actual low-level - * stuff. + * mapping->a_ops->readpage() function for the actual low-level stuff. * * This is really ugly. But the goto's actually try to clarify some * of the logic when it comes to error handling etc. * - * Note the struct file* is only passed for the use of readpage. It may be - * NULL. + * Note the struct file* is only passed for the use of readpage. + * It may be NULL. */ void do_generic_mapping_read(struct address_space *mapping, struct file_ra_state *_ra, @@ -1004,7 +1057,6 @@ out: if (filp) file_accessed(filp); } - EXPORT_SYMBOL(do_generic_mapping_read); int file_read_actor(read_descriptor_t *desc, struct page *page, @@ -1045,7 +1097,13 @@ success: return size; } -/* +/** + * __generic_file_aio_read - generic filesystem read routine + * @iocb: kernel I/O control block + * @iov: io vector request + * @nr_segs: number of segments in the iovec + * @ppos: current file position + * * This is the "read()" routine for all filesystems * that can use the page cache directly. */ @@ -1124,7 +1182,6 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, out: return retval; } - EXPORT_SYMBOL(__generic_file_aio_read); ssize_t @@ -1135,7 +1192,6 @@ generic_file_aio_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t BUG_ON(iocb->ki_pos != pos); return __generic_file_aio_read(iocb, &local_iov, 1, &iocb->ki_pos); } - EXPORT_SYMBOL(generic_file_aio_read); ssize_t @@ -1151,7 +1207,6 @@ generic_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppo ret = wait_on_sync_kiocb(&kiocb); return ret; } - EXPORT_SYMBOL(generic_file_read); int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size) @@ -1192,7 +1247,6 @@ ssize_t generic_file_sendfile(struct file *in_file, loff_t *ppos, return desc.written; return desc.error; } - EXPORT_SYMBOL(generic_file_sendfile); static ssize_t @@ -1228,11 +1282,15 @@ asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count) } #ifdef CONFIG_MMU -/* +static int FASTCALL(page_cache_read(struct file * file, unsigned long offset)); +/** + * page_cache_read - adds requested page to the page cache if not already there + * @file: file to read + * @offset: page index + * * This adds the requested page to the page cache if it isn't already there, * and schedules an I/O to read in its contents from disk. */ -static int FASTCALL(page_cache_read(struct file * file, unsigned long offset)); static int fastcall page_cache_read(struct file * file, unsigned long offset) { struct address_space *mapping = file->f_mapping; @@ -1259,7 +1317,12 @@ static int fastcall page_cache_read(struct file * file, unsigned long offset) #define MMAP_LOTSAMISS (100) -/* +/** + * filemap_nopage - read in file data for page fault handling + * @area: the applicable vm_area + * @address: target address to read in + * @type: returned with VM_FAULT_{MINOR,MAJOR} if not %NULL + * * filemap_nopage() is invoked via the vma operations vector for a * mapped memory region to read in file data during a page fault. * @@ -1462,7 +1525,6 @@ page_not_uptodate: page_cache_release(page); return NULL; } - EXPORT_SYMBOL(filemap_nopage); static struct page * filemap_getpage(struct file *file, unsigned long pgoff, @@ -1716,7 +1778,13 @@ repeat: return page; } -/* +/** + * read_cache_page - read into page cache, fill it if needed + * @mapping: the page's address_space + * @index: the page index + * @filler: function to perform the read + * @data: destination for read data + * * Read into the page cache. If a page already exists, * and PageUptodate() is not set, try to fill the page. */ @@ -1754,7 +1822,6 @@ retry: out: return page; } - EXPORT_SYMBOL(read_cache_page); /* @@ -1835,7 +1902,7 @@ __filemap_copy_from_user_iovec(char *vaddr, int copy = min(bytes, iov->iov_len - base); base = 0; - left = __copy_from_user_inatomic(vaddr, buf, copy); + left = __copy_from_user_inatomic_nocache(vaddr, buf, copy); copied += copy; bytes -= copy; vaddr += copy; @@ -1854,7 +1921,7 @@ __filemap_copy_from_user_iovec(char *vaddr, /* * Performs necessary checks before doing a write * - * Can adjust writing position aor amount of bytes to write. + * Can adjust writing position or amount of bytes to write. * Returns appropriate error code that caller should return or * zero in case that write should be allowed. */ diff --git a/mm/filemap.h b/mm/filemap.h index 13793ba0ce1..5683cde2205 100644 --- a/mm/filemap.h +++ b/mm/filemap.h @@ -13,7 +13,7 @@ #include <linux/highmem.h> #include <linux/uio.h> #include <linux/config.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> size_t __filemap_copy_from_user_iovec(char *vaddr, @@ -34,13 +34,13 @@ filemap_copy_from_user(struct page *page, unsigned long offset, int left; kaddr = kmap_atomic(page, KM_USER0); - left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); + left = __copy_from_user_inatomic_nocache(kaddr + offset, buf, bytes); kunmap_atomic(kaddr, KM_USER0); if (left != 0) { /* Do it the slow way */ kaddr = kmap(page); - left = __copy_from_user(kaddr + offset, buf, bytes); + left = __copy_from_user_nocache(kaddr + offset, buf, bytes); kunmap(page); } return bytes - left; diff --git a/mm/fremap.c b/mm/fremap.c index 9f381e58bf4..21b7d0cbc98 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -83,6 +83,7 @@ int install_page(struct mm_struct *mm, struct vm_area_struct *vma, page_add_file_rmap(page); pte_val = *pte; update_mmu_cache(vma, addr, pte_val); + lazy_mmu_prot_update(pte_val); err = 0; unlock: pte_unmap_unlock(pte, ptl); @@ -114,7 +115,13 @@ int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, set_pte_at(mm, addr, pte, pgoff_to_pte(pgoff)); pte_val = *pte; - update_mmu_cache(vma, addr, pte_val); + /* + * We don't need to run update_mmu_cache() here because the "file pte" + * being installed by install_file_pte() is not a real pte - it's a + * non-present entry (like a swap entry), noting what file offset should + * be mapped there when there's a fault (in a non-linear vma where + * that's not obvious). + */ pte_unmap_unlock(pte, ptl); err = 0; out: diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 832f676ca03..df499973255 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -22,7 +22,7 @@ #include "internal.h" const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL; -static unsigned long nr_huge_pages, free_huge_pages, reserved_huge_pages; +static unsigned long nr_huge_pages, free_huge_pages, resv_huge_pages; unsigned long max_huge_pages; static struct list_head hugepage_freelists[MAX_NUMNODES]; static unsigned int nr_huge_pages_node[MAX_NUMNODES]; @@ -123,39 +123,13 @@ static int alloc_fresh_huge_page(void) static struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr) { - struct inode *inode = vma->vm_file->f_dentry->d_inode; struct page *page; - int use_reserve = 0; - unsigned long idx; spin_lock(&hugetlb_lock); - - if (vma->vm_flags & VM_MAYSHARE) { - - /* idx = radix tree index, i.e. offset into file in - * HPAGE_SIZE units */ - idx = ((addr - vma->vm_start) >> HPAGE_SHIFT) - + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT)); - - /* The hugetlbfs specific inode info stores the number - * of "guaranteed available" (huge) pages. That is, - * the first 'prereserved_hpages' pages of the inode - * are either already instantiated, or have been - * pre-reserved (by hugetlb_reserve_for_inode()). Here - * we're in the process of instantiating the page, so - * we use this to determine whether to draw from the - * pre-reserved pool or the truly free pool. */ - if (idx < HUGETLBFS_I(inode)->prereserved_hpages) - use_reserve = 1; - } - - if (!use_reserve) { - if (free_huge_pages <= reserved_huge_pages) - goto fail; - } else { - BUG_ON(reserved_huge_pages == 0); - reserved_huge_pages--; - } + if (vma->vm_flags & VM_MAYSHARE) + resv_huge_pages--; + else if (free_huge_pages <= resv_huge_pages) + goto fail; page = dequeue_huge_page(vma, addr); if (!page) @@ -165,96 +139,11 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, set_page_refcounted(page); return page; - fail: - WARN_ON(use_reserve); /* reserved allocations shouldn't fail */ +fail: spin_unlock(&hugetlb_lock); return NULL; } -/* hugetlb_extend_reservation() - * - * Ensure that at least 'atleast' hugepages are, and will remain, - * available to instantiate the first 'atleast' pages of the given - * inode. If the inode doesn't already have this many pages reserved - * or instantiated, set aside some hugepages in the reserved pool to - * satisfy later faults (or fail now if there aren't enough, rather - * than getting the SIGBUS later). - */ -int hugetlb_extend_reservation(struct hugetlbfs_inode_info *info, - unsigned long atleast) -{ - struct inode *inode = &info->vfs_inode; - unsigned long change_in_reserve = 0; - int ret = 0; - - spin_lock(&hugetlb_lock); - read_lock_irq(&inode->i_mapping->tree_lock); - - if (info->prereserved_hpages >= atleast) - goto out; - - /* Because we always call this on shared mappings, none of the - * pages beyond info->prereserved_hpages can have been - * instantiated, so we need to reserve all of them now. */ - change_in_reserve = atleast - info->prereserved_hpages; - - if ((reserved_huge_pages + change_in_reserve) > free_huge_pages) { - ret = -ENOMEM; - goto out; - } - - reserved_huge_pages += change_in_reserve; - info->prereserved_hpages = atleast; - - out: - read_unlock_irq(&inode->i_mapping->tree_lock); - spin_unlock(&hugetlb_lock); - - return ret; -} - -/* hugetlb_truncate_reservation() - * - * This returns pages reserved for the given inode to the general free - * hugepage pool. If the inode has any pages prereserved, but not - * instantiated, beyond offset (atmost << HPAGE_SIZE), then release - * them. - */ -void hugetlb_truncate_reservation(struct hugetlbfs_inode_info *info, - unsigned long atmost) -{ - struct inode *inode = &info->vfs_inode; - struct address_space *mapping = inode->i_mapping; - unsigned long idx; - unsigned long change_in_reserve = 0; - struct page *page; - - spin_lock(&hugetlb_lock); - read_lock_irq(&inode->i_mapping->tree_lock); - - if (info->prereserved_hpages <= atmost) - goto out; - - /* Count pages which were reserved, but not instantiated, and - * which we can now release. */ - for (idx = atmost; idx < info->prereserved_hpages; idx++) { - page = radix_tree_lookup(&mapping->page_tree, idx); - if (!page) - /* Pages which are already instantiated can't - * be unreserved (and in fact have already - * been removed from the reserved pool) */ - change_in_reserve++; - } - - BUG_ON(reserved_huge_pages < change_in_reserve); - reserved_huge_pages -= change_in_reserve; - info->prereserved_hpages = atmost; - - out: - read_unlock_irq(&inode->i_mapping->tree_lock); - spin_unlock(&hugetlb_lock); -} - static int __init hugetlb_init(void) { unsigned long i; @@ -334,7 +223,7 @@ static unsigned long set_max_huge_pages(unsigned long count) return nr_huge_pages; spin_lock(&hugetlb_lock); - count = max(count, reserved_huge_pages); + count = max(count, resv_huge_pages); try_to_free_low(count); while (count < nr_huge_pages) { struct page *page = dequeue_huge_page(NULL, 0); @@ -361,11 +250,11 @@ int hugetlb_report_meminfo(char *buf) return sprintf(buf, "HugePages_Total: %5lu\n" "HugePages_Free: %5lu\n" - "HugePages_Rsvd: %5lu\n" + "HugePages_Rsvd: %5lu\n" "Hugepagesize: %5lu kB\n", nr_huge_pages, free_huge_pages, - reserved_huge_pages, + resv_huge_pages, HPAGE_SIZE/1024); } @@ -754,3 +643,156 @@ void hugetlb_change_protection(struct vm_area_struct *vma, flush_tlb_range(vma, start, end); } +struct file_region { + struct list_head link; + long from; + long to; +}; + +static long region_add(struct list_head *head, long f, long t) +{ + struct file_region *rg, *nrg, *trg; + + /* Locate the region we are either in or before. */ + list_for_each_entry(rg, head, link) + if (f <= rg->to) + break; + + /* Round our left edge to the current segment if it encloses us. */ + if (f > rg->from) + f = rg->from; + + /* Check for and consume any regions we now overlap with. */ + nrg = rg; + list_for_each_entry_safe(rg, trg, rg->link.prev, link) { + if (&rg->link == head) + break; + if (rg->from > t) + break; + + /* If this area reaches higher then extend our area to + * include it completely. If this is not the first area + * which we intend to reuse, free it. */ + if (rg->to > t) + t = rg->to; + if (rg != nrg) { + list_del(&rg->link); + kfree(rg); + } + } + nrg->from = f; + nrg->to = t; + return 0; +} + +static long region_chg(struct list_head *head, long f, long t) +{ + struct file_region *rg, *nrg; + long chg = 0; + + /* Locate the region we are before or in. */ + list_for_each_entry(rg, head, link) + if (f <= rg->to) + break; + + /* If we are below the current region then a new region is required. + * Subtle, allocate a new region at the position but make it zero + * size such that we can guarentee to record the reservation. */ + if (&rg->link == head || t < rg->from) { + nrg = kmalloc(sizeof(*nrg), GFP_KERNEL); + if (nrg == 0) + return -ENOMEM; + nrg->from = f; + nrg->to = f; + INIT_LIST_HEAD(&nrg->link); + list_add(&nrg->link, rg->link.prev); + + return t - f; + } + + /* Round our left edge to the current segment if it encloses us. */ + if (f > rg->from) + f = rg->from; + chg = t - f; + + /* Check for and consume any regions we now overlap with. */ + list_for_each_entry(rg, rg->link.prev, link) { + if (&rg->link == head) + break; + if (rg->from > t) + return chg; + + /* We overlap with this area, if it extends futher than + * us then we must extend ourselves. Account for its + * existing reservation. */ + if (rg->to > t) { + chg += rg->to - t; + t = rg->to; + } + chg -= rg->to - rg->from; + } + return chg; +} + +static long region_truncate(struct list_head *head, long end) +{ + struct file_region *rg, *trg; + long chg = 0; + + /* Locate the region we are either in or before. */ + list_for_each_entry(rg, head, link) + if (end <= rg->to) + break; + if (&rg->link == head) + return 0; + + /* If we are in the middle of a region then adjust it. */ + if (end > rg->from) { + chg = rg->to - end; + rg->to = end; + rg = list_entry(rg->link.next, typeof(*rg), link); + } + + /* Drop any remaining regions. */ + list_for_each_entry_safe(rg, trg, rg->link.prev, link) { + if (&rg->link == head) + break; + chg += rg->to - rg->from; + list_del(&rg->link); + kfree(rg); + } + return chg; +} + +static int hugetlb_acct_memory(long delta) +{ + int ret = -ENOMEM; + + spin_lock(&hugetlb_lock); + if ((delta + resv_huge_pages) <= free_huge_pages) { + resv_huge_pages += delta; + ret = 0; + } + spin_unlock(&hugetlb_lock); + return ret; +} + +int hugetlb_reserve_pages(struct inode *inode, long from, long to) +{ + long ret, chg; + + chg = region_chg(&inode->i_mapping->private_list, from, to); + if (chg < 0) + return chg; + ret = hugetlb_acct_memory(chg); + if (ret < 0) + return ret; + region_add(&inode->i_mapping->private_list, from, to); + return 0; +} + +void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) +{ + long chg = region_truncate(&inode->i_mapping->private_list, offset); + hugetlb_acct_memory(freed - chg); +} diff --git a/mm/memory.c b/mm/memory.c index 0ec7bc64427..247b5c312b9 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -434,7 +434,9 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, /* pte contains position in swap or file, so copy. */ if (unlikely(!pte_present(pte))) { if (!pte_file(pte)) { - swap_duplicate(pte_to_swp_entry(pte)); + swp_entry_t entry = pte_to_swp_entry(pte); + + swap_duplicate(entry); /* make sure dst_mm is on swapoff's mmlist. */ if (unlikely(list_empty(&dst_mm->mmlist))) { spin_lock(&mmlist_lock); @@ -443,6 +445,16 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, &src_mm->mmlist); spin_unlock(&mmlist_lock); } + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { + /* + * COW mappings require pages in both parent + * and child to be set to read. + */ + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + set_pte_at(src_mm, addr, src_pte, pte); + } } goto out_set_pte; } @@ -1445,25 +1457,60 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, { struct page *old_page, *new_page; pte_t entry; - int ret = VM_FAULT_MINOR; + int reuse, ret = VM_FAULT_MINOR; old_page = vm_normal_page(vma, address, orig_pte); if (!old_page) goto gotten; - if (PageAnon(old_page) && !TestSetPageLocked(old_page)) { - int reuse = can_share_swap_page(old_page); - unlock_page(old_page); - if (reuse) { - flush_cache_page(vma, address, pte_pfn(orig_pte)); - entry = pte_mkyoung(orig_pte); - entry = maybe_mkwrite(pte_mkdirty(entry), vma); - ptep_set_access_flags(vma, address, page_table, entry, 1); - update_mmu_cache(vma, address, entry); - lazy_mmu_prot_update(entry); - ret |= VM_FAULT_WRITE; - goto unlock; + if (unlikely((vma->vm_flags & (VM_SHARED|VM_WRITE)) == + (VM_SHARED|VM_WRITE))) { + if (vma->vm_ops && vma->vm_ops->page_mkwrite) { + /* + * Notify the address space that the page is about to + * become writable so that it can prohibit this or wait + * for the page to get into an appropriate state. + * + * We do this without the lock held, so that it can + * sleep if it needs to. + */ + page_cache_get(old_page); + pte_unmap_unlock(page_table, ptl); + + if (vma->vm_ops->page_mkwrite(vma, old_page) < 0) + goto unwritable_page; + + page_cache_release(old_page); + + /* + * Since we dropped the lock we need to revalidate + * the PTE as someone else may have changed it. If + * they did, we just return, as we can count on the + * MMU to tell us if they didn't also make it writable. + */ + page_table = pte_offset_map_lock(mm, pmd, address, + &ptl); + if (!pte_same(*page_table, orig_pte)) + goto unlock; } + + reuse = 1; + } else if (PageAnon(old_page) && !TestSetPageLocked(old_page)) { + reuse = can_share_swap_page(old_page); + unlock_page(old_page); + } else { + reuse = 0; + } + + if (reuse) { + flush_cache_page(vma, address, pte_pfn(orig_pte)); + entry = pte_mkyoung(orig_pte); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + ptep_set_access_flags(vma, address, page_table, entry, 1); + update_mmu_cache(vma, address, entry); + lazy_mmu_prot_update(entry); + ret |= VM_FAULT_WRITE; + goto unlock; } /* @@ -1523,6 +1570,10 @@ oom: if (old_page) page_cache_release(old_page); return VM_FAULT_OOM; + +unwritable_page: + page_cache_release(old_page); + return VM_FAULT_SIGBUS; } /* @@ -1879,7 +1930,10 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out; entry = pte_to_swp_entry(orig_pte); -again: + if (is_migration_entry(entry)) { + migration_entry_wait(mm, pmd, address); + goto out; + } page = lookup_swap_cache(entry); if (!page) { swapin_readahead(entry, address, vma); @@ -1903,12 +1957,6 @@ again: mark_page_accessed(page); lock_page(page); - if (!PageSwapCache(page)) { - /* Page migration has occured */ - unlock_page(page); - page_cache_release(page); - goto again; - } /* * Back out if somebody else already faulted in this pte. @@ -2074,18 +2122,31 @@ retry: /* * Should we do an early C-O-W break? */ - if (write_access && !(vma->vm_flags & VM_SHARED)) { - struct page *page; + if (write_access) { + if (!(vma->vm_flags & VM_SHARED)) { + struct page *page; - if (unlikely(anon_vma_prepare(vma))) - goto oom; - page = alloc_page_vma(GFP_HIGHUSER, vma, address); - if (!page) - goto oom; - copy_user_highpage(page, new_page, address); - page_cache_release(new_page); - new_page = page; - anon = 1; + if (unlikely(anon_vma_prepare(vma))) + goto oom; + page = alloc_page_vma(GFP_HIGHUSER, vma, address); + if (!page) + goto oom; + copy_user_highpage(page, new_page, address); + page_cache_release(new_page); + new_page = page; + anon = 1; + + } else { + /* if the page will be shareable, see if the backing + * address space wants to know that the page is about + * to become writable */ + if (vma->vm_ops->page_mkwrite && + vma->vm_ops->page_mkwrite(vma, new_page) < 0 + ) { + page_cache_release(new_page); + return VM_FAULT_SIGBUS; + } + } } page_table = pte_offset_map_lock(mm, pmd, address, &ptl); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 70df5c0d957..841a077d5ae 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -26,7 +26,7 @@ extern void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn, unsigned long size); -static void __add_zone(struct zone *zone, unsigned long phys_start_pfn) +static int __add_zone(struct zone *zone, unsigned long phys_start_pfn) { struct pglist_data *pgdat = zone->zone_pgdat; int nr_pages = PAGES_PER_SECTION; @@ -34,8 +34,15 @@ static void __add_zone(struct zone *zone, unsigned long phys_start_pfn) int zone_type; zone_type = zone - pgdat->node_zones; + if (!populated_zone(zone)) { + int ret = 0; + ret = init_currently_empty_zone(zone, phys_start_pfn, nr_pages); + if (ret < 0) + return ret; + } memmap_init_zone(nr_pages, nid, zone_type, phys_start_pfn); zonetable_add(zone, nid, zone_type, phys_start_pfn, nr_pages); + return 0; } extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn, @@ -50,7 +57,11 @@ static int __add_section(struct zone *zone, unsigned long phys_start_pfn) if (ret < 0) return ret; - __add_zone(zone, phys_start_pfn); + ret = __add_zone(zone, phys_start_pfn); + + if (ret < 0) + return ret; + return register_new_memory(__pfn_to_section(phys_start_pfn)); } @@ -116,6 +127,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) unsigned long flags; unsigned long onlined_pages = 0; struct zone *zone; + int need_zonelists_rebuild = 0; /* * This doesn't need a lock to do pfn_to_page(). @@ -128,6 +140,14 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) grow_pgdat_span(zone->zone_pgdat, pfn, pfn + nr_pages); pgdat_resize_unlock(zone->zone_pgdat, &flags); + /* + * If this zone is not populated, then it is not in zonelist. + * This means the page allocator ignores this zone. + * So, zonelist must be updated after online. + */ + if (!populated_zone(zone)) + need_zonelists_rebuild = 1; + for (i = 0; i < nr_pages; i++) { struct page *page = pfn_to_page(pfn + i); online_page(page); @@ -138,5 +158,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) setup_per_zone_pages_min(); + if (need_zonelists_rebuild) + build_all_zonelists(); + vm_total_pages = nr_free_pagecache_pages(); return 0; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 8778f58880c..ec4a1a950df 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -87,6 +87,8 @@ #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/migrate.h> +#include <linux/rmap.h> +#include <linux/security.h> #include <asm/tlbflush.h> #include <asm/uaccess.h> @@ -587,6 +589,11 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, isolate_lru_page(page, pagelist); } +static struct page *new_node_page(struct page *page, unsigned long node, int **x) +{ + return alloc_pages_node(node, GFP_HIGHUSER, 0); +} + /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. @@ -603,11 +610,9 @@ int migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) check_range(mm, mm->mmap->vm_start, TASK_SIZE, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); - if (!list_empty(&pagelist)) { - err = migrate_pages_to(&pagelist, NULL, dest); - if (!list_empty(&pagelist)) - putback_lru_pages(&pagelist); - } + if (!list_empty(&pagelist)) + err = migrate_pages(&pagelist, new_node_page, dest); + return err; } @@ -694,6 +699,12 @@ int do_migrate_pages(struct mm_struct *mm, } +static struct page *new_vma_page(struct page *page, unsigned long private, int **x) +{ + struct vm_area_struct *vma = (struct vm_area_struct *)private; + + return alloc_page_vma(GFP_HIGHUSER, vma, page_address_in_vma(page, vma)); +} #else static void migrate_page_add(struct page *page, struct list_head *pagelist, @@ -706,6 +717,11 @@ int do_migrate_pages(struct mm_struct *mm, { return -ENOSYS; } + +static struct page *new_vma_page(struct page *page, unsigned long private) +{ + return NULL; +} #endif long do_mbind(unsigned long start, unsigned long len, @@ -767,15 +783,13 @@ long do_mbind(unsigned long start, unsigned long len, err = mbind_range(vma, start, end, new); if (!list_empty(&pagelist)) - nr_failed = migrate_pages_to(&pagelist, vma, -1); + nr_failed = migrate_pages(&pagelist, new_vma_page, + (unsigned long)vma); if (!err && nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; } - if (!list_empty(&pagelist)) - putback_lru_pages(&pagelist); - up_write(&mm->mmap_sem); mpol_free(new); return err; @@ -929,6 +943,10 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, goto out; } + err = security_task_movememory(task); + if (err) + goto out; + err = do_migrate_pages(mm, &old, &new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); out: diff --git a/mm/migrate.c b/mm/migrate.c index 1c25040693d..1c2a71aa05c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -15,6 +15,7 @@ #include <linux/migrate.h> #include <linux/module.h> #include <linux/swap.h> +#include <linux/swapops.h> #include <linux/pagemap.h> #include <linux/buffer_head.h> #include <linux/mm_inline.h> @@ -23,13 +24,13 @@ #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> -#include <linux/swapops.h> +#include <linux/writeback.h> +#include <linux/mempolicy.h> +#include <linux/vmalloc.h> +#include <linux/security.h> #include "internal.h" -/* The maximum number of pages to take off the LRU for migration */ -#define MIGRATE_CHUNK_SIZE 256 - #define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru)) /* @@ -64,16 +65,11 @@ int isolate_lru_page(struct page *page, struct list_head *pagelist) } /* - * migrate_prep() needs to be called after we have compiled the list of pages - * to be migrated using isolate_lru_page() but before we begin a series of calls - * to migrate_pages(). + * migrate_prep() needs to be called before we start compiling a list of pages + * to be migrated using isolate_lru_page(). */ int migrate_prep(void) { - /* Must have swap device for migration */ - if (nr_swap_pages <= 0) - return -ENODEV; - /* * Clear the LRU lists so pages can be isolated. * Note that pages may be moved off the LRU after we have @@ -87,7 +83,6 @@ int migrate_prep(void) static inline void move_to_lru(struct page *page) { - list_del(&page->lru); if (PageActive(page)) { /* * lru_cache_add_active checks that @@ -113,113 +108,200 @@ int putback_lru_pages(struct list_head *l) int count = 0; list_for_each_entry_safe(page, page2, l, lru) { + list_del(&page->lru); move_to_lru(page); count++; } return count; } -/* - * Non migratable page - */ -int fail_migrate_page(struct page *newpage, struct page *page) +static inline int is_swap_pte(pte_t pte) { - return -EIO; + return !pte_none(pte) && !pte_present(pte) && !pte_file(pte); } -EXPORT_SYMBOL(fail_migrate_page); /* - * swapout a single page - * page is locked upon entry, unlocked on exit + * Restore a potential migration pte to a working pte entry */ -static int swap_page(struct page *page) +static void remove_migration_pte(struct vm_area_struct *vma, + struct page *old, struct page *new) { - struct address_space *mapping = page_mapping(page); + struct mm_struct *mm = vma->vm_mm; + swp_entry_t entry; + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep, pte; + spinlock_t *ptl; + unsigned long addr = page_address_in_vma(new, vma); + + if (addr == -EFAULT) + return; + + pgd = pgd_offset(mm, addr); + if (!pgd_present(*pgd)) + return; + + pud = pud_offset(pgd, addr); + if (!pud_present(*pud)) + return; + + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) + return; + + ptep = pte_offset_map(pmd, addr); + + if (!is_swap_pte(*ptep)) { + pte_unmap(ptep); + return; + } - if (page_mapped(page) && mapping) - if (try_to_unmap(page, 1) != SWAP_SUCCESS) - goto unlock_retry; + ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + pte = *ptep; + if (!is_swap_pte(pte)) + goto out; - if (PageDirty(page)) { - /* Page is dirty, try to write it out here */ - switch(pageout(page, mapping)) { - case PAGE_KEEP: - case PAGE_ACTIVATE: - goto unlock_retry; + entry = pte_to_swp_entry(pte); - case PAGE_SUCCESS: - goto retry; + if (!is_migration_entry(entry) || migration_entry_to_page(entry) != old) + goto out; - case PAGE_CLEAN: - ; /* try to free the page below */ - } - } + get_page(new); + pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); + if (is_write_migration_entry(entry)) + pte = pte_mkwrite(pte); + set_pte_at(mm, addr, ptep, pte); - if (PagePrivate(page)) { - if (!try_to_release_page(page, GFP_KERNEL) || - (!mapping && page_count(page) == 1)) - goto unlock_retry; - } + if (PageAnon(new)) + page_add_anon_rmap(new, vma, addr); + else + page_add_file_rmap(new); - if (remove_mapping(mapping, page)) { - /* Success */ - unlock_page(page); - return 0; - } + /* No need to invalidate - it was non-present before */ + update_mmu_cache(vma, addr, pte); + lazy_mmu_prot_update(pte); -unlock_retry: - unlock_page(page); +out: + pte_unmap_unlock(ptep, ptl); +} -retry: - return -EAGAIN; +/* + * Note that remove_file_migration_ptes will only work on regular mappings, + * Nonlinear mappings do not use migration entries. + */ +static void remove_file_migration_ptes(struct page *old, struct page *new) +{ + struct vm_area_struct *vma; + struct address_space *mapping = page_mapping(new); + struct prio_tree_iter iter; + pgoff_t pgoff = new->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); + + if (!mapping) + return; + + spin_lock(&mapping->i_mmap_lock); + + vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) + remove_migration_pte(vma, old, new); + + spin_unlock(&mapping->i_mmap_lock); } /* - * Remove references for a page and establish the new page with the correct - * basic settings to be able to stop accesses to the page. + * Must hold mmap_sem lock on at least one of the vmas containing + * the page so that the anon_vma cannot vanish. */ -int migrate_page_remove_references(struct page *newpage, - struct page *page, int nr_refs) +static void remove_anon_migration_ptes(struct page *old, struct page *new) { - struct address_space *mapping = page_mapping(page); - struct page **radix_pointer; + struct anon_vma *anon_vma; + struct vm_area_struct *vma; + unsigned long mapping; - /* - * Avoid doing any of the following work if the page count - * indicates that the page is in use or truncate has removed - * the page. - */ - if (!mapping || page_mapcount(page) + nr_refs != page_count(page)) - return -EAGAIN; + mapping = (unsigned long)new->mapping; - /* - * Establish swap ptes for anonymous pages or destroy pte - * maps for files. - * - * In order to reestablish file backed mappings the fault handlers - * will take the radix tree_lock which may then be used to stop - * processses from accessing this page until the new page is ready. - * - * A process accessing via a swap pte (an anonymous page) will take a - * page_lock on the old page which will block the process until the - * migration attempt is complete. At that time the PageSwapCache bit - * will be examined. If the page was migrated then the PageSwapCache - * bit will be clear and the operation to retrieve the page will be - * retried which will find the new page in the radix tree. Then a new - * direct mapping may be generated based on the radix tree contents. - * - * If the page was not migrated then the PageSwapCache bit - * is still set and the operation may continue. - */ - if (try_to_unmap(page, 1) == SWAP_FAIL) - /* A vma has VM_LOCKED set -> permanent failure */ - return -EPERM; + if (!mapping || (mapping & PAGE_MAPPING_ANON) == 0) + return; /* - * Give up if we were unable to remove all mappings. + * We hold the mmap_sem lock. So no need to call page_lock_anon_vma. */ - if (page_mapcount(page)) - return -EAGAIN; + anon_vma = (struct anon_vma *) (mapping - PAGE_MAPPING_ANON); + spin_lock(&anon_vma->lock); + + list_for_each_entry(vma, &anon_vma->head, anon_vma_node) + remove_migration_pte(vma, old, new); + + spin_unlock(&anon_vma->lock); +} + +/* + * Get rid of all migration entries and replace them by + * references to the indicated page. + */ +static void remove_migration_ptes(struct page *old, struct page *new) +{ + if (PageAnon(new)) + remove_anon_migration_ptes(old, new); + else + remove_file_migration_ptes(old, new); +} + +/* + * Something used the pte of a page under migration. We need to + * get to the page and wait until migration is finished. + * When we return from this function the fault will be retried. + * + * This function is called from do_swap_page(). + */ +void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, + unsigned long address) +{ + pte_t *ptep, pte; + spinlock_t *ptl; + swp_entry_t entry; + struct page *page; + + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + pte = *ptep; + if (!is_swap_pte(pte)) + goto out; + + entry = pte_to_swp_entry(pte); + if (!is_migration_entry(entry)) + goto out; + + page = migration_entry_to_page(entry); + + get_page(page); + pte_unmap_unlock(ptep, ptl); + wait_on_page_locked(page); + put_page(page); + return; +out: + pte_unmap_unlock(ptep, ptl); +} + +/* + * Replace the page in the mapping. + * + * The number of remaining references must be: + * 1 for anonymous pages without a mapping + * 2 for pages with a mapping + * 3 for pages with a mapping and PagePrivate set. + */ +static int migrate_page_move_mapping(struct address_space *mapping, + struct page *newpage, struct page *page) +{ + struct page **radix_pointer; + + if (!mapping) { + /* Anonymous page */ + if (page_count(page) != 1) + return -EAGAIN; + return 0; + } write_lock_irq(&mapping->tree_lock); @@ -227,7 +309,7 @@ int migrate_page_remove_references(struct page *newpage, &mapping->page_tree, page_index(page)); - if (!page_mapping(page) || page_count(page) != nr_refs || + if (page_count(page) != 2 + !!PagePrivate(page) || *radix_pointer != page) { write_unlock_irq(&mapping->tree_lock); return -EAGAIN; @@ -235,19 +317,14 @@ int migrate_page_remove_references(struct page *newpage, /* * Now we know that no one else is looking at the page. - * - * Certain minimal information about a page must be available - * in order for other subsystems to properly handle the page if they - * find it through the radix tree update before we are finished - * copying the page. */ get_page(newpage); - newpage->index = page->index; - newpage->mapping = page->mapping; +#ifdef CONFIG_SWAP if (PageSwapCache(page)) { SetPageSwapCache(newpage); set_page_private(newpage, page_private(page)); } +#endif *radix_pointer = newpage; __put_page(page); @@ -255,12 +332,11 @@ int migrate_page_remove_references(struct page *newpage, return 0; } -EXPORT_SYMBOL(migrate_page_remove_references); /* * Copy the page to its new location */ -void migrate_page_copy(struct page *newpage, struct page *page) +static void migrate_page_copy(struct page *newpage, struct page *page) { copy_highpage(newpage, page); @@ -282,7 +358,9 @@ void migrate_page_copy(struct page *newpage, struct page *page) set_page_dirty(newpage); } +#ifdef CONFIG_SWAP ClearPageSwapCache(page); +#endif ClearPageActive(page); ClearPagePrivate(page); set_page_private(page, 0); @@ -295,7 +373,18 @@ void migrate_page_copy(struct page *newpage, struct page *page) if (PageWriteback(newpage)) end_page_writeback(newpage); } -EXPORT_SYMBOL(migrate_page_copy); + +/************************************************************ + * Migration functions + ***********************************************************/ + +/* Always fail migration. Used for mappings that are not movable */ +int fail_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page) +{ + return -EIO; +} +EXPORT_SYMBOL(fail_migrate_page); /* * Common logic to directly migrate a single page suitable for @@ -303,51 +392,286 @@ EXPORT_SYMBOL(migrate_page_copy); * * Pages are locked upon entry and exit. */ -int migrate_page(struct page *newpage, struct page *page) +int migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page) { int rc; BUG_ON(PageWriteback(page)); /* Writeback must be complete */ - rc = migrate_page_remove_references(newpage, page, 2); + rc = migrate_page_move_mapping(mapping, newpage, page); + + if (rc) + return rc; + + migrate_page_copy(newpage, page); + return 0; +} +EXPORT_SYMBOL(migrate_page); + +/* + * Migration function for pages with buffers. This function can only be used + * if the underlying filesystem guarantees that no other references to "page" + * exist. + */ +int buffer_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page) +{ + struct buffer_head *bh, *head; + int rc; + + if (!page_has_buffers(page)) + return migrate_page(mapping, newpage, page); + + head = page_buffers(page); + + rc = migrate_page_move_mapping(mapping, newpage, page); if (rc) return rc; + bh = head; + do { + get_bh(bh); + lock_buffer(bh); + bh = bh->b_this_page; + + } while (bh != head); + + ClearPagePrivate(page); + set_page_private(newpage, page_private(page)); + set_page_private(page, 0); + put_page(page); + get_page(newpage); + + bh = head; + do { + set_bh_page(bh, newpage, bh_offset(bh)); + bh = bh->b_this_page; + + } while (bh != head); + + SetPagePrivate(newpage); + migrate_page_copy(newpage, page); + bh = head; + do { + unlock_buffer(bh); + put_bh(bh); + bh = bh->b_this_page; + + } while (bh != head); + + return 0; +} +EXPORT_SYMBOL(buffer_migrate_page); + +/* + * Writeback a page to clean the dirty state + */ +static int writeout(struct address_space *mapping, struct page *page) +{ + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + .nr_to_write = 1, + .range_start = 0, + .range_end = LLONG_MAX, + .nonblocking = 1, + .for_reclaim = 1 + }; + int rc; + + if (!mapping->a_ops->writepage) + /* No write method for the address space */ + return -EINVAL; + + if (!clear_page_dirty_for_io(page)) + /* Someone else already triggered a write */ + return -EAGAIN; + /* - * Remove auxiliary swap entries and replace - * them with real ptes. - * - * Note that a real pte entry will allow processes that are not - * waiting on the page lock to use the new page via the page tables - * before the new page is unlocked. + * A dirty page may imply that the underlying filesystem has + * the page on some queue. So the page must be clean for + * migration. Writeout may mean we loose the lock and the + * page state is no longer what we checked for earlier. + * At this point we know that the migration attempt cannot + * be successful. */ - remove_from_swap(newpage); - return 0; + remove_migration_ptes(page, page); + + rc = mapping->a_ops->writepage(page, &wbc); + if (rc < 0) + /* I/O Error writing */ + return -EIO; + + if (rc != AOP_WRITEPAGE_ACTIVATE) + /* unlocked. Relock */ + lock_page(page); + + return -EAGAIN; +} + +/* + * Default handling if a filesystem does not provide a migration function. + */ +static int fallback_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page) +{ + if (PageDirty(page)) + return writeout(mapping, page); + + /* + * Buffers may be managed in a filesystem specific way. + * We must have no buffers or drop them. + */ + if (page_has_buffers(page) && + !try_to_release_page(page, GFP_KERNEL)) + return -EAGAIN; + + return migrate_page(mapping, newpage, page); +} + +/* + * Move a page to a newly allocated page + * The page is locked and all ptes have been successfully removed. + * + * The new page will have replaced the old page if this function + * is successful. + */ +static int move_to_new_page(struct page *newpage, struct page *page) +{ + struct address_space *mapping; + int rc; + + /* + * Block others from accessing the page when we get around to + * establishing additional references. We are the only one + * holding a reference to the new page at this point. + */ + if (TestSetPageLocked(newpage)) + BUG(); + + /* Prepare mapping for the new page.*/ + newpage->index = page->index; + newpage->mapping = page->mapping; + + mapping = page_mapping(page); + if (!mapping) + rc = migrate_page(mapping, newpage, page); + else if (mapping->a_ops->migratepage) + /* + * Most pages have a mapping and most filesystems + * should provide a migration function. Anonymous + * pages are part of swap space which also has its + * own migration function. This is the most common + * path for page migration. + */ + rc = mapping->a_ops->migratepage(mapping, + newpage, page); + else + rc = fallback_migrate_page(mapping, newpage, page); + + if (!rc) + remove_migration_ptes(page, newpage); + else + newpage->mapping = NULL; + + unlock_page(newpage); + + return rc; +} + +/* + * Obtain the lock on page, remove all ptes and migrate the page + * to the newly allocated page in newpage. + */ +static int unmap_and_move(new_page_t get_new_page, unsigned long private, + struct page *page, int force) +{ + int rc = 0; + int *result = NULL; + struct page *newpage = get_new_page(page, private, &result); + + if (!newpage) + return -ENOMEM; + + if (page_count(page) == 1) + /* page was freed from under us. So we are done. */ + goto move_newpage; + + rc = -EAGAIN; + if (TestSetPageLocked(page)) { + if (!force) + goto move_newpage; + lock_page(page); + } + + if (PageWriteback(page)) { + if (!force) + goto unlock; + wait_on_page_writeback(page); + } + + /* + * Establish migration ptes or remove ptes + */ + if (try_to_unmap(page, 1) != SWAP_FAIL) { + if (!page_mapped(page)) + rc = move_to_new_page(newpage, page); + } else + /* A vma has VM_LOCKED set -> permanent failure */ + rc = -EPERM; + + if (rc) + remove_migration_ptes(page, page); +unlock: + unlock_page(page); + + if (rc != -EAGAIN) { + /* + * A page that has been migrated has all references + * removed and will be freed. A page that has not been + * migrated will have kepts its references and be + * restored. + */ + list_del(&page->lru); + move_to_lru(page); + } + +move_newpage: + /* + * Move the new page to the LRU. If migration was not successful + * then this will free the page. + */ + move_to_lru(newpage); + if (result) { + if (rc) + *result = rc; + else + *result = page_to_nid(newpage); + } + return rc; } -EXPORT_SYMBOL(migrate_page); /* * migrate_pages * - * Two lists are passed to this function. The first list - * contains the pages isolated from the LRU to be migrated. - * The second list contains new pages that the pages isolated - * can be moved to. If the second list is NULL then all - * pages are swapped out. + * The function takes one list of pages to migrate and a function + * that determines from the page to be migrated and the private data + * the target of the move and allocates the page. * * The function returns after 10 attempts or if no pages * are movable anymore because to has become empty - * or no retryable pages exist anymore. + * or no retryable pages exist anymore. All pages will be + * retruned to the LRU or freed. * - * Return: Number of pages not migrated when "to" ran empty. + * Return: Number of pages not migrated or error code. */ -int migrate_pages(struct list_head *from, struct list_head *to, - struct list_head *moved, struct list_head *failed) +int migrate_pages(struct list_head *from, + new_page_t get_new_page, unsigned long private) { - int retry; + int retry = 1; int nr_failed = 0; int pass = 0; struct page *page; @@ -358,305 +682,297 @@ int migrate_pages(struct list_head *from, struct list_head *to, if (!swapwrite) current->flags |= PF_SWAPWRITE; -redo: - retry = 0; + for(pass = 0; pass < 10 && retry; pass++) { + retry = 0; + + list_for_each_entry_safe(page, page2, from, lru) { + cond_resched(); + + rc = unmap_and_move(get_new_page, private, + page, pass > 2); + + switch(rc) { + case -ENOMEM: + goto out; + case -EAGAIN: + retry++; + break; + case 0: + break; + default: + /* Permanent failure */ + nr_failed++; + break; + } + } + } + rc = 0; +out: + if (!swapwrite) + current->flags &= ~PF_SWAPWRITE; - list_for_each_entry_safe(page, page2, from, lru) { - struct page *newpage = NULL; - struct address_space *mapping; + putback_lru_pages(from); - cond_resched(); + if (rc) + return rc; - rc = 0; - if (page_count(page) == 1) - /* page was freed from under us. So we are done. */ - goto next; + return nr_failed + retry; +} - if (to && list_empty(to)) - break; +#ifdef CONFIG_NUMA +/* + * Move a list of individual pages + */ +struct page_to_node { + unsigned long addr; + struct page *page; + int node; + int status; +}; - /* - * Skip locked pages during the first two passes to give the - * functions holding the lock time to release the page. Later we - * use lock_page() to have a higher chance of acquiring the - * lock. - */ - rc = -EAGAIN; - if (pass > 2) - lock_page(page); - else - if (TestSetPageLocked(page)) - goto next; +static struct page *new_page_node(struct page *p, unsigned long private, + int **result) +{ + struct page_to_node *pm = (struct page_to_node *)private; - /* - * Only wait on writeback if we have already done a pass where - * we we may have triggered writeouts for lots of pages. - */ - if (pass > 0) { - wait_on_page_writeback(page); - } else { - if (PageWriteback(page)) - goto unlock_page; - } + while (pm->node != MAX_NUMNODES && pm->page != p) + pm++; - /* - * Anonymous pages must have swap cache references otherwise - * the information contained in the page maps cannot be - * preserved. - */ - if (PageAnon(page) && !PageSwapCache(page)) { - if (!add_to_swap(page, GFP_KERNEL)) { - rc = -ENOMEM; - goto unlock_page; - } - } + if (pm->node == MAX_NUMNODES) + return NULL; - if (!to) { - rc = swap_page(page); - goto next; - } + *result = &pm->status; - newpage = lru_to_page(to); - lock_page(newpage); + return alloc_pages_node(pm->node, GFP_HIGHUSER, 0); +} - /* - * Pages are properly locked and writeback is complete. - * Try to migrate the page. - */ - mapping = page_mapping(page); - if (!mapping) - goto unlock_both; +/* + * Move a set of pages as indicated in the pm array. The addr + * field must be set to the virtual address of the page to be moved + * and the node number must contain a valid target node. + */ +static int do_move_pages(struct mm_struct *mm, struct page_to_node *pm, + int migrate_all) +{ + int err; + struct page_to_node *pp; + LIST_HEAD(pagelist); - if (mapping->a_ops->migratepage) { - /* - * Most pages have a mapping and most filesystems - * should provide a migration function. Anonymous - * pages are part of swap space which also has its - * own migration function. This is the most common - * path for page migration. - */ - rc = mapping->a_ops->migratepage(newpage, page); - goto unlock_both; - } - - /* Make sure the dirty bit is up to date */ - if (try_to_unmap(page, 1) == SWAP_FAIL) { - rc = -EPERM; - goto unlock_both; - } + down_read(&mm->mmap_sem); - if (page_mapcount(page)) { - rc = -EAGAIN; - goto unlock_both; - } + /* + * 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; /* - * Default handling if a filesystem does not provide - * a migration function. We can only migrate clean - * pages so try to write out any dirty pages first. + * A valid page pointer that will not match any of the + * pages that will be moved. */ - if (PageDirty(page)) { - switch (pageout(page, mapping)) { - case PAGE_KEEP: - case PAGE_ACTIVATE: - goto unlock_both; - - case PAGE_SUCCESS: - unlock_page(newpage); - goto next; - - case PAGE_CLEAN: - ; /* try to migrate the page below */ - } - } + pp->page = ZERO_PAGE(0); - /* - * Buffers are managed in a filesystem specific way. - * We must have no buffers or drop them. - */ - if (!page_has_buffers(page) || - try_to_release_page(page, GFP_KERNEL)) { - rc = migrate_page(newpage, page); - goto unlock_both; - } + err = -EFAULT; + vma = find_vma(mm, pp->addr); + if (!vma) + goto set_status; - /* - * On early passes with mapped pages simply - * retry. There may be a lock held for some - * buffers that may go away. Later - * swap them out. - */ - if (pass > 4) { + page = follow_page(vma, pp->addr, FOLL_GET); + err = -ENOENT; + if (!page) + goto set_status; + + if (PageReserved(page)) /* Check for zero page */ + goto put_and_set; + + pp->page = page; + err = page_to_nid(page); + + if (err == pp->node) /* - * Persistently unable to drop buffers..... As a - * measure of last resort we fall back to - * swap_page(). + * Node already in the right place */ - unlock_page(newpage); - newpage = NULL; - rc = swap_page(page); - goto next; - } + goto put_and_set; -unlock_both: - unlock_page(newpage); - -unlock_page: - unlock_page(page); - -next: - if (rc == -EAGAIN) { - retry++; - } else if (rc) { - /* Permanent failure */ - list_move(&page->lru, failed); - nr_failed++; - } else { - if (newpage) { - /* Successful migration. Return page to LRU */ - move_to_lru(newpage); - } - list_move(&page->lru, moved); - } + err = -EACCES; + if (page_mapcount(page) > 1 && + !migrate_all) + goto put_and_set; + + err = isolate_lru_page(page, &pagelist); +put_and_set: + /* + * Either remove the duplicate refcount from + * isolate_lru_page() or drop the page ref if it was + * not isolated. + */ + put_page(page); +set_status: + pp->status = err; } - if (retry && pass++ < 10) - goto redo; - if (!swapwrite) - current->flags &= ~PF_SWAPWRITE; + if (!list_empty(&pagelist)) + err = migrate_pages(&pagelist, new_page_node, + (unsigned long)pm); + else + err = -ENOENT; - return nr_failed + retry; + up_read(&mm->mmap_sem); + return err; } /* - * Migration function for pages with buffers. This function can only be used - * if the underlying filesystem guarantees that no other references to "page" - * exist. + * Determine the nodes of a list of pages. The addr in the pm array + * must have been set to the virtual address of which we want to determine + * the node number. */ -int buffer_migrate_page(struct page *newpage, struct page *page) +static int do_pages_stat(struct mm_struct *mm, struct page_to_node *pm) { - struct address_space *mapping = page->mapping; - struct buffer_head *bh, *head; - int rc; + down_read(&mm->mmap_sem); + + for ( ; pm->node != MAX_NUMNODES; pm++) { + struct vm_area_struct *vma; + struct page *page; + int err; + + err = -EFAULT; + vma = find_vma(mm, pm->addr); + if (!vma) + goto set_status; + + page = follow_page(vma, pm->addr, 0); + err = -ENOENT; + /* Use PageReserved to check for zero page */ + if (!page || PageReserved(page)) + goto set_status; + + err = page_to_nid(page); +set_status: + pm->status = err; + } - if (!mapping) - return -EAGAIN; + up_read(&mm->mmap_sem); + return 0; +} - if (!page_has_buffers(page)) - return migrate_page(newpage, page); +/* + * Move a list of pages in the address space of the currently executing + * process. + */ +asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, + const void __user * __user *pages, + const int __user *nodes, + int __user *status, int flags) +{ + int err = 0; + int i; + struct task_struct *task; + nodemask_t task_nodes; + struct mm_struct *mm; + struct page_to_node *pm = NULL; - head = page_buffers(page); + /* Check flags */ + if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL)) + return -EINVAL; - rc = migrate_page_remove_references(newpage, page, 3); + if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) + return -EPERM; - if (rc) - return rc; + /* Find the mm_struct */ + read_lock(&tasklist_lock); + task = pid ? find_task_by_pid(pid) : current; + if (!task) { + read_unlock(&tasklist_lock); + return -ESRCH; + } + mm = get_task_mm(task); + read_unlock(&tasklist_lock); - bh = head; - do { - get_bh(bh); - lock_buffer(bh); - bh = bh->b_this_page; + if (!mm) + return -EINVAL; - } while (bh != head); + /* + * Check if this process has the right to modify the specified + * process. The right exists if the process has administrative + * capabilities, superuser privileges or the same + * userid as the target process. + */ + if ((current->euid != task->suid) && (current->euid != task->uid) && + (current->uid != task->suid) && (current->uid != task->uid) && + !capable(CAP_SYS_NICE)) { + err = -EPERM; + goto out2; + } - ClearPagePrivate(page); - set_page_private(newpage, page_private(page)); - set_page_private(page, 0); - put_page(page); - get_page(newpage); + err = security_task_movememory(task); + if (err) + goto out2; - bh = head; - do { - set_bh_page(bh, newpage, bh_offset(bh)); - bh = bh->b_this_page; - } while (bh != head); + task_nodes = cpuset_mems_allowed(task); - SetPagePrivate(newpage); + /* Limit nr_pages so that the multiplication may not overflow */ + if (nr_pages >= ULONG_MAX / sizeof(struct page_to_node) - 1) { + err = -E2BIG; + goto out2; + } - migrate_page_copy(newpage, page); + pm = vmalloc((nr_pages + 1) * sizeof(struct page_to_node)); + if (!pm) { + err = -ENOMEM; + goto out2; + } - bh = head; - do { - unlock_buffer(bh); - put_bh(bh); - bh = bh->b_this_page; + /* + * Get parameters from user space and initialize the pm + * array. Return various errors if the user did something wrong. + */ + for (i = 0; i < nr_pages; i++) { + const void *p; - } while (bh != head); + err = -EFAULT; + if (get_user(p, pages + i)) + goto out; - return 0; -} -EXPORT_SYMBOL(buffer_migrate_page); + pm[i].addr = (unsigned long)p; + if (nodes) { + int node; -/* - * Migrate the list 'pagelist' of pages to a certain destination. - * - * Specify destination with either non-NULL vma or dest_node >= 0 - * Return the number of pages not migrated or error code - */ -int migrate_pages_to(struct list_head *pagelist, - struct vm_area_struct *vma, int dest) -{ - LIST_HEAD(newlist); - LIST_HEAD(moved); - LIST_HEAD(failed); - int err = 0; - unsigned long offset = 0; - int nr_pages; - struct page *page; - struct list_head *p; + if (get_user(node, nodes + i)) + goto out; -redo: - nr_pages = 0; - list_for_each(p, pagelist) { - if (vma) { - /* - * The address passed to alloc_page_vma is used to - * generate the proper interleave behavior. We fake - * the address here by an increasing offset in order - * to get the proper distribution of pages. - * - * No decision has been made as to which page - * a certain old page is moved to so we cannot - * specify the correct address. - */ - page = alloc_page_vma(GFP_HIGHUSER, vma, - offset + vma->vm_start); - offset += PAGE_SIZE; - } - else - page = alloc_pages_node(dest, GFP_HIGHUSER, 0); + err = -ENODEV; + if (!node_online(node)) + goto out; - if (!page) { - err = -ENOMEM; - goto out; + err = -EACCES; + if (!node_isset(node, task_nodes)) + goto out; + + pm[i].node = node; } - list_add_tail(&page->lru, &newlist); - nr_pages++; - if (nr_pages > MIGRATE_CHUNK_SIZE) - break; } - err = migrate_pages(pagelist, &newlist, &moved, &failed); + /* End marker */ + pm[nr_pages].node = MAX_NUMNODES; + + if (nodes) + err = do_move_pages(mm, pm, flags & MPOL_MF_MOVE_ALL); + else + err = do_pages_stat(mm, pm); - putback_lru_pages(&moved); /* Call release pages instead ?? */ + if (err >= 0) + /* Return status information */ + for (i = 0; i < nr_pages; i++) + if (put_user(pm[i].status, status + i)) + err = -EFAULT; - if (err >= 0 && list_empty(&newlist) && !list_empty(pagelist)) - goto redo; out: - /* Return leftover allocated pages */ - while (!list_empty(&newlist)) { - page = list_entry(newlist.next, struct page, lru); - list_del(&page->lru); - __free_page(page); - } - list_splice(&failed, pagelist); - if (err < 0) - return err; - - /* Calculate number of leftover pages */ - nr_pages = 0; - list_for_each(p, pagelist) - nr_pages++; - return nr_pages; + vfree(pm); +out2: + mmput(mm); + return err; } +#endif + diff --git a/mm/mmap.c b/mm/mmap.c index e6ee12344b1..6446c6134b0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1065,7 +1065,8 @@ munmap_back: vma->vm_start = addr; vma->vm_end = addr + len; vma->vm_flags = vm_flags; - vma->vm_page_prot = protection_map[vm_flags & 0x0f]; + vma->vm_page_prot = protection_map[vm_flags & + (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]; vma->vm_pgoff = pgoff; if (file) { @@ -1089,6 +1090,12 @@ munmap_back: goto free_vma; } + /* Don't make the VMA automatically writable if it's shared, but the + * backer wishes to know when pages are first written to */ + if (vma->vm_ops && vma->vm_ops->page_mkwrite) + vma->vm_page_prot = + protection_map[vm_flags & (VM_READ|VM_WRITE|VM_EXEC)]; + /* We set VM_ACCOUNT in a shared mapping's vm_flags, to inform * shmem_zero_setup (perhaps called through /dev/zero's ->mmap) * that memory reservation must be checked; but that reservation @@ -1921,7 +1928,8 @@ unsigned long do_brk(unsigned long addr, unsigned long len) vma->vm_end = addr + len; vma->vm_pgoff = pgoff; vma->vm_flags = flags; - vma->vm_page_prot = protection_map[flags & 0x0f]; + vma->vm_page_prot = protection_map[flags & + (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]; vma_link(mm, vma, prev, rb_link, rb_parent); out: mm->total_vm += len >> PAGE_SHIFT; diff --git a/mm/mprotect.c b/mm/mprotect.c index 4c14d4289b6..638edabaff7 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -19,7 +19,8 @@ #include <linux/mempolicy.h> #include <linux/personality.h> #include <linux/syscalls.h> - +#include <linux/swap.h> +#include <linux/swapops.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm/cacheflush.h> @@ -28,12 +29,13 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pgprot_t newprot) { - pte_t *pte; + pte_t *pte, oldpte; spinlock_t *ptl; pte = pte_offset_map_lock(mm, pmd, addr, &ptl); do { - if (pte_present(*pte)) { + oldpte = *pte; + if (pte_present(oldpte)) { pte_t ptent; /* Avoid an SMP race with hardware updated dirty/clean @@ -43,7 +45,22 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, ptent = pte_modify(ptep_get_and_clear(mm, addr, pte), newprot); set_pte_at(mm, addr, pte, ptent); lazy_mmu_prot_update(ptent); +#ifdef CONFIG_MIGRATION + } else if (!pte_file(oldpte)) { + swp_entry_t entry = pte_to_swp_entry(oldpte); + + if (is_write_migration_entry(entry)) { + /* + * A protection check is difficult so + * just be safe and disable write + */ + make_migration_entry_read(&entry); + set_pte_at(mm, addr, pte, + swp_entry_to_pte(entry)); + } +#endif } + } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap_unlock(pte - 1, ptl); } @@ -106,6 +123,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, unsigned long oldflags = vma->vm_flags; long nrpages = (end - start) >> PAGE_SHIFT; unsigned long charged = 0; + unsigned int mask; pgprot_t newprot; pgoff_t pgoff; int error; @@ -132,8 +150,6 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, } } - newprot = protection_map[newflags & 0xf]; - /* * First try to merge with previous and/or next vma. */ @@ -160,6 +176,14 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, } success: + /* Don't make the VMA automatically writable if it's shared, but the + * backer wishes to know when pages are first written to */ + mask = VM_READ|VM_WRITE|VM_EXEC|VM_SHARED; + if (vma->vm_ops && vma->vm_ops->page_mkwrite) + mask &= ~VM_SHARED; + + newprot = protection_map[newflags & mask]; + /* * vm_flags and vm_page_prot are protected by the mmap_sem * held in write mode. @@ -205,8 +229,7 @@ sys_mprotect(unsigned long start, size_t len, unsigned long prot) /* * Does the application expect PROT_READ to imply PROT_EXEC: */ - if (unlikely((prot & PROT_READ) && - (current->personality & READ_IMPLIES_EXEC))) + if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) prot |= PROT_EXEC; vm_flags = calc_vm_prot_bits(prot); diff --git a/mm/msync.c b/mm/msync.c index bc6c9537636..d083544df21 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -170,8 +170,6 @@ asmlinkage long sys_msync(unsigned long start, size_t len, int flags) * just ignore them, but return -ENOMEM at the end. */ down_read(¤t->mm->mmap_sem); - if (flags & MS_SYNC) - current->flags |= PF_SYNCWRITE; vma = find_vma(current->mm, start); if (!vma) { error = -ENOMEM; @@ -228,7 +226,6 @@ asmlinkage long sys_msync(unsigned long start, size_t len, int flags) } } while (vma && !done); out_unlock: - current->flags &= ~PF_SYNCWRITE; up_read(¤t->mm->mmap_sem); out: return error; diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 042e6436c3e..d46ed0f1dc0 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -22,10 +22,11 @@ #include <linux/jiffies.h> #include <linux/cpuset.h> +int sysctl_panic_on_oom; /* #define DEBUG */ /** - * oom_badness - calculate a numeric value for how bad this task has been + * 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 * @@ -200,7 +201,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints) continue; /* - * This is in the process of releasing memory so for wait it + * This is in the process of releasing memory so wait for it * to finish before killing some other task by mistake. */ releasing = test_tsk_thread_flag(p, TIF_MEMDIE) || @@ -306,7 +307,7 @@ static int oom_kill_process(struct task_struct *p, unsigned long points, } /** - * oom_kill - kill the "best" process when we run out of memory + * out_of_memory - kill the "best" process when we run out of memory * * If we run out of memory, we have the choice between either * killing a random task (bad), letting the system crash (worse) @@ -344,6 +345,8 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order) break; case CONSTRAINT_NONE: + if (sysctl_panic_on_oom) + panic("out of memory. panic_on_oom is selected\n"); retry: /* * Rambo mode: Shoot down a process and hope it solves whatever diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 75d7f48b79b..8ccf6f1b147 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -204,6 +204,7 @@ static void balance_dirty_pages(struct address_space *mapping) .sync_mode = WB_SYNC_NONE, .older_than_this = NULL, .nr_to_write = write_chunk, + .range_cyclic = 1, }; get_dirty_limits(&wbs, &background_thresh, @@ -331,6 +332,7 @@ static void background_writeout(unsigned long _min_pages) .older_than_this = NULL, .nr_to_write = 0, .nonblocking = 1, + .range_cyclic = 1, }; for ( ; ; ) { @@ -407,6 +409,7 @@ static void wb_kupdate(unsigned long arg) .nr_to_write = 0, .nonblocking = 1, .for_kupdate = 1, + .range_cyclic = 1, }; sync_supers(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 253a450c400..423db0db7c0 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -37,6 +37,7 @@ #include <linux/nodemask.h> #include <linux/vmalloc.h> #include <linux/mempolicy.h> +#include <linux/stop_machine.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -83,8 +84,8 @@ EXPORT_SYMBOL(zone_table); static char *zone_names[MAX_NR_ZONES] = { "DMA", "DMA32", "Normal", "HighMem" }; int min_free_kbytes = 1024; -unsigned long __initdata nr_kernel_pages; -unsigned long __initdata nr_all_pages; +unsigned long __meminitdata nr_kernel_pages; +unsigned long __meminitdata nr_all_pages; #ifdef CONFIG_DEBUG_VM static int page_outside_zone_boundaries(struct zone *zone, struct page *page) @@ -286,22 +287,27 @@ __find_combined_index(unsigned long page_idx, unsigned int order) * we can do coalesce a page and its buddy if * (a) the buddy is not in a hole && * (b) the buddy is in the buddy system && - * (c) a page and its buddy have the same order. + * (c) a page and its buddy have the same order && + * (d) a page and its buddy are in the same zone. * * For recording whether a page is in the buddy system, we use PG_buddy. * Setting, clearing, and testing PG_buddy is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ -static inline int page_is_buddy(struct page *page, int order) +static inline int page_is_buddy(struct page *page, struct page *buddy, + int order) { #ifdef CONFIG_HOLES_IN_ZONE - if (!pfn_valid(page_to_pfn(page))) + if (!pfn_valid(page_to_pfn(buddy))) return 0; #endif - if (PageBuddy(page) && page_order(page) == order) { - BUG_ON(page_count(page) != 0); + if (page_zone_id(page) != page_zone_id(buddy)) + return 0; + + if (PageBuddy(buddy) && page_order(buddy) == order) { + BUG_ON(page_count(buddy) != 0); return 1; } return 0; @@ -352,7 +358,7 @@ static inline void __free_one_page(struct page *page, struct page *buddy; buddy = __page_find_buddy(page, page_idx, order); - if (!page_is_buddy(buddy, order)) + if (!page_is_buddy(page, buddy, order)) break; /* Move the buddy up one level. */ list_del(&buddy->lru); @@ -1485,7 +1491,7 @@ void show_free_areas(void) } for_each_zone(zone) { - unsigned long nr, flags, order, total = 0; + unsigned long nr[MAX_ORDER], flags, order, total = 0; show_node(zone); printk("%s: ", zone->name); @@ -1496,11 +1502,12 @@ void show_free_areas(void) spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { - nr = zone->free_area[order].nr_free; - total += nr << order; - printk("%lu*%lukB ", nr, K(1UL) << order); + nr[order] = zone->free_area[order].nr_free; + total += nr[order] << order; } spin_unlock_irqrestore(&zone->lock, flags); + for (order = 0; order < MAX_ORDER; order++) + printk("%lu*%lukB ", nr[order], K(1UL) << order); printk("= %lukB\n", K(total)); } @@ -1512,7 +1519,7 @@ void show_free_areas(void) * * Add all populated zones of a node to the zonelist. */ -static int __init build_zonelists_node(pg_data_t *pgdat, +static int __meminit build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, int nr_zones, int zone_type) { struct zone *zone; @@ -1548,7 +1555,7 @@ static inline int highest_zone(int zone_bits) #ifdef CONFIG_NUMA #define MAX_NODE_LOAD (num_online_nodes()) -static int __initdata node_load[MAX_NUMNODES]; +static int __meminitdata node_load[MAX_NUMNODES]; /** * find_next_best_node - find the next node that should appear in a given node's fallback list * @node: node whose fallback list we're appending @@ -1563,7 +1570,7 @@ static int __initdata node_load[MAX_NUMNODES]; * on them otherwise. * It returns -1 if no node is found. */ -static int __init find_next_best_node(int node, nodemask_t *used_node_mask) +static int __meminit find_next_best_node(int node, nodemask_t *used_node_mask) { int n, val; int min_val = INT_MAX; @@ -1609,7 +1616,7 @@ static int __init find_next_best_node(int node, nodemask_t *used_node_mask) return best_node; } -static void __init build_zonelists(pg_data_t *pgdat) +static void __meminit build_zonelists(pg_data_t *pgdat) { int i, j, k, node, local_node; int prev_node, load; @@ -1661,7 +1668,7 @@ static void __init build_zonelists(pg_data_t *pgdat) #else /* CONFIG_NUMA */ -static void __init build_zonelists(pg_data_t *pgdat) +static void __meminit build_zonelists(pg_data_t *pgdat) { int i, j, k, node, local_node; @@ -1699,14 +1706,29 @@ static void __init build_zonelists(pg_data_t *pgdat) #endif /* CONFIG_NUMA */ -void __init build_all_zonelists(void) +/* return values int ....just for stop_machine_run() */ +static int __meminit __build_all_zonelists(void *dummy) { - int i; + int nid; + for_each_online_node(nid) + build_zonelists(NODE_DATA(nid)); + return 0; +} - for_each_online_node(i) - build_zonelists(NODE_DATA(i)); - printk("Built %i zonelists\n", num_online_nodes()); - cpuset_init_current_mems_allowed(); +void __meminit build_all_zonelists(void) +{ + if (system_state == SYSTEM_BOOTING) { + __build_all_zonelists(0); + cpuset_init_current_mems_allowed(); + } else { + /* we have to stop all cpus to guaranntee there is no user + of zonelist */ + stop_machine_run(__build_all_zonelists, NULL, NR_CPUS); + /* cpuset refresh routine should be here */ + } + vm_total_pages = nr_free_pagecache_pages(); + printk("Built %i zonelists. Total pages: %ld\n", + num_online_nodes(), vm_total_pages); } /* @@ -1722,7 +1744,8 @@ void __init build_all_zonelists(void) */ #define PAGES_PER_WAITQUEUE 256 -static inline unsigned long wait_table_size(unsigned long pages) +#ifndef CONFIG_MEMORY_HOTPLUG +static inline unsigned long wait_table_hash_nr_entries(unsigned long pages) { unsigned long size = 1; @@ -1740,6 +1763,29 @@ static inline unsigned long wait_table_size(unsigned long pages) return max(size, 4UL); } +#else +/* + * A zone's size might be changed by hot-add, so it is not possible to determine + * a suitable size for its wait_table. So we use the maximum size now. + * + * The max wait table size = 4096 x sizeof(wait_queue_head_t). ie: + * + * i386 (preemption config) : 4096 x 16 = 64Kbyte. + * ia64, x86-64 (no preemption): 4096 x 20 = 80Kbyte. + * ia64, x86-64 (preemption) : 4096 x 24 = 96Kbyte. + * + * The maximum entries are prepared when a zone's memory is (512K + 256) pages + * or more by the traditional way. (See above). It equals: + * + * i386, x86-64, powerpc(4K page size) : = ( 2G + 1M)byte. + * ia64(16K page size) : = ( 8G + 4M)byte. + * powerpc (64K page size) : = (32G +16M)byte. + */ +static inline unsigned long wait_table_hash_nr_entries(unsigned long pages) +{ + return 4096UL; +} +#endif /* * This is an integer logarithm so that shifts can be used later @@ -2005,23 +2051,46 @@ void __init setup_per_cpu_pageset(void) #endif static __meminit -void zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) +int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) { int i; struct pglist_data *pgdat = zone->zone_pgdat; + size_t alloc_size; /* * The per-page waitqueue mechanism uses hashed waitqueues * per zone. */ - zone->wait_table_size = wait_table_size(zone_size_pages); - zone->wait_table_bits = wait_table_bits(zone->wait_table_size); - zone->wait_table = (wait_queue_head_t *) - alloc_bootmem_node(pgdat, zone->wait_table_size - * sizeof(wait_queue_head_t)); + zone->wait_table_hash_nr_entries = + wait_table_hash_nr_entries(zone_size_pages); + zone->wait_table_bits = + wait_table_bits(zone->wait_table_hash_nr_entries); + alloc_size = zone->wait_table_hash_nr_entries + * sizeof(wait_queue_head_t); + + if (system_state == SYSTEM_BOOTING) { + zone->wait_table = (wait_queue_head_t *) + alloc_bootmem_node(pgdat, alloc_size); + } else { + /* + * This case means that a zone whose size was 0 gets new memory + * via memory hot-add. + * But it may be the case that a new node was hot-added. In + * this case vmalloc() will not be able to use this new node's + * memory - this wait_table must be initialized to use this new + * node itself as well. + * To use this new node's memory, further consideration will be + * necessary. + */ + zone->wait_table = (wait_queue_head_t *)vmalloc(alloc_size); + } + if (!zone->wait_table) + return -ENOMEM; - for(i = 0; i < zone->wait_table_size; ++i) + for(i = 0; i < zone->wait_table_hash_nr_entries; ++i) init_waitqueue_head(zone->wait_table + i); + + return 0; } static __meminit void zone_pcp_init(struct zone *zone) @@ -2043,12 +2112,15 @@ static __meminit void zone_pcp_init(struct zone *zone) zone->name, zone->present_pages, batch); } -static __meminit void init_currently_empty_zone(struct zone *zone, - unsigned long zone_start_pfn, unsigned long size) +__meminit int init_currently_empty_zone(struct zone *zone, + unsigned long zone_start_pfn, + unsigned long size) { struct pglist_data *pgdat = zone->zone_pgdat; - - zone_wait_table_init(zone, size); + int ret; + ret = zone_wait_table_init(zone, size); + if (ret) + return ret; pgdat->nr_zones = zone_idx(zone) + 1; zone->zone_start_pfn = zone_start_pfn; @@ -2056,6 +2128,8 @@ static __meminit void init_currently_empty_zone(struct zone *zone, memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn); zone_init_free_lists(pgdat, zone, zone->spanned_pages); + + return 0; } /* @@ -2064,12 +2138,13 @@ static __meminit void init_currently_empty_zone(struct zone *zone, * - mark all memory queues empty * - clear the memory bitmaps */ -static void __init free_area_init_core(struct pglist_data *pgdat, +static void __meminit free_area_init_core(struct pglist_data *pgdat, unsigned long *zones_size, unsigned long *zholes_size) { unsigned long j; int nid = pgdat->node_id; unsigned long zone_start_pfn = pgdat->node_start_pfn; + int ret; pgdat_resize_init(pgdat); pgdat->nr_zones = 0; @@ -2111,7 +2186,8 @@ static void __init free_area_init_core(struct pglist_data *pgdat, continue; zonetable_add(zone, nid, j, zone_start_pfn, size); - init_currently_empty_zone(zone, zone_start_pfn, size); + ret = init_currently_empty_zone(zone, zone_start_pfn, size); + BUG_ON(ret); zone_start_pfn += size; } } @@ -2152,7 +2228,7 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat) #endif /* CONFIG_FLAT_NODE_MEM_MAP */ } -void __init free_area_init_node(int nid, struct pglist_data *pgdat, +void __meminit free_area_init_node(int nid, struct pglist_data *pgdat, unsigned long *zones_size, unsigned long node_start_pfn, unsigned long *zholes_size) { @@ -2804,42 +2880,14 @@ void *__init alloc_large_system_hash(const char *tablename, } #ifdef CONFIG_OUT_OF_LINE_PFN_TO_PAGE -/* - * pfn <-> page translation. out-of-line version. - * (see asm-generic/memory_model.h) - */ -#if defined(CONFIG_FLATMEM) struct page *pfn_to_page(unsigned long pfn) { - return mem_map + (pfn - ARCH_PFN_OFFSET); + return __pfn_to_page(pfn); } unsigned long page_to_pfn(struct page *page) { - return (page - mem_map) + ARCH_PFN_OFFSET; -} -#elif defined(CONFIG_DISCONTIGMEM) -struct page *pfn_to_page(unsigned long pfn) -{ - int nid = arch_pfn_to_nid(pfn); - return NODE_DATA(nid)->node_mem_map + arch_local_page_offset(pfn,nid); -} -unsigned long page_to_pfn(struct page *page) -{ - struct pglist_data *pgdat = NODE_DATA(page_to_nid(page)); - return (page - pgdat->node_mem_map) + pgdat->node_start_pfn; -} -#elif defined(CONFIG_SPARSEMEM) -struct page *pfn_to_page(unsigned long pfn) -{ - return __section_mem_map_addr(__pfn_to_section(pfn)) + pfn; -} - -unsigned long page_to_pfn(struct page *page) -{ - long section_id = page_to_section(page); - return page - __section_mem_map_addr(__nr_to_section(section_id)); + return __page_to_pfn(page); } -#endif /* CONFIG_FLATMEM/DISCONTIGMME/SPARSEMEM */ EXPORT_SYMBOL(pfn_to_page); EXPORT_SYMBOL(page_to_pfn); #endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */ diff --git a/mm/pdflush.c b/mm/pdflush.c index c4b6d0afd73..df7e50b8f70 100644 --- a/mm/pdflush.c +++ b/mm/pdflush.c @@ -202,8 +202,7 @@ int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0) unsigned long flags; int ret = 0; - if (fn == NULL) - BUG(); /* Hard to diagnose if it's deferred */ + BUG_ON(fn == NULL); /* Hard to diagnose if it's deferred */ spin_lock_irqsave(&pdflush_lock, flags); if (list_empty(&pdflush_list)) { diff --git a/mm/rmap.c b/mm/rmap.c index 1963e269314..882a85826bb 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -103,7 +103,7 @@ int anon_vma_prepare(struct vm_area_struct *vma) spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; - list_add(&vma->anon_vma_node, &anon_vma->head); + list_add_tail(&vma->anon_vma_node, &anon_vma->head); allocated = NULL; } spin_unlock(&mm->page_table_lock); @@ -127,7 +127,7 @@ void __anon_vma_link(struct vm_area_struct *vma) struct anon_vma *anon_vma = vma->anon_vma; if (anon_vma) { - list_add(&vma->anon_vma_node, &anon_vma->head); + list_add_tail(&vma->anon_vma_node, &anon_vma->head); validate_anon_vma(vma); } } @@ -138,7 +138,7 @@ void anon_vma_link(struct vm_area_struct *vma) if (anon_vma) { spin_lock(&anon_vma->lock); - list_add(&vma->anon_vma_node, &anon_vma->head); + list_add_tail(&vma->anon_vma_node, &anon_vma->head); validate_anon_vma(vma); spin_unlock(&anon_vma->lock); } @@ -205,44 +205,6 @@ out: return anon_vma; } -#ifdef CONFIG_MIGRATION -/* - * Remove an anonymous page from swap replacing the swap pte's - * through real pte's pointing to valid pages and then releasing - * the page from the swap cache. - * - * Must hold page lock on page and mmap_sem of one vma that contains - * the page. - */ -void remove_from_swap(struct page *page) -{ - struct anon_vma *anon_vma; - struct vm_area_struct *vma; - unsigned long mapping; - - if (!PageSwapCache(page)) - return; - - mapping = (unsigned long)page->mapping; - - if (!mapping || (mapping & PAGE_MAPPING_ANON) == 0) - return; - - /* - * We hold the mmap_sem lock. So no need to call page_lock_anon_vma. - */ - anon_vma = (struct anon_vma *) (mapping - PAGE_MAPPING_ANON); - spin_lock(&anon_vma->lock); - - list_for_each_entry(vma, &anon_vma->head, anon_vma_node) - remove_vma_swap(vma, page); - - spin_unlock(&anon_vma->lock); - delete_from_swap_cache(page); -} -EXPORT_SYMBOL(remove_from_swap); -#endif - /* * At what user virtual address is page expected in vma? */ @@ -578,7 +540,7 @@ void page_remove_rmap(struct page *page) * repeatedly from either try_to_unmap_anon or try_to_unmap_file. */ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, - int ignore_refs) + int migration) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -602,7 +564,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, */ if ((vma->vm_flags & VM_LOCKED) || (ptep_clear_flush_young(vma, address, pte) - && !ignore_refs)) { + && !migration)) { ret = SWAP_FAIL; goto out_unmap; } @@ -620,24 +582,45 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (PageAnon(page)) { swp_entry_t entry = { .val = page_private(page) }; - /* - * Store the swap location in the pte. - * See handle_pte_fault() ... - */ - BUG_ON(!PageSwapCache(page)); - swap_duplicate(entry); - if (list_empty(&mm->mmlist)) { - spin_lock(&mmlist_lock); - if (list_empty(&mm->mmlist)) - list_add(&mm->mmlist, &init_mm.mmlist); - spin_unlock(&mmlist_lock); + + if (PageSwapCache(page)) { + /* + * Store the swap location in the pte. + * See handle_pte_fault() ... + */ + swap_duplicate(entry); + if (list_empty(&mm->mmlist)) { + spin_lock(&mmlist_lock); + if (list_empty(&mm->mmlist)) + list_add(&mm->mmlist, &init_mm.mmlist); + spin_unlock(&mmlist_lock); + } + dec_mm_counter(mm, anon_rss); +#ifdef CONFIG_MIGRATION + } else { + /* + * Store the pfn of the page in a special migration + * pte. do_swap_page() will wait until the migration + * pte is removed and then restart fault handling. + */ + BUG_ON(!migration); + entry = make_migration_entry(page, pte_write(pteval)); +#endif } set_pte_at(mm, address, pte, swp_entry_to_pte(entry)); BUG_ON(pte_file(*pte)); - dec_mm_counter(mm, anon_rss); } else +#ifdef CONFIG_MIGRATION + if (migration) { + /* Establish migration entry for a file page */ + swp_entry_t entry; + entry = make_migration_entry(page, pte_write(pteval)); + set_pte_at(mm, address, pte, swp_entry_to_pte(entry)); + } else +#endif dec_mm_counter(mm, file_rss); + page_remove_rmap(page); page_cache_release(page); @@ -736,7 +719,7 @@ static void try_to_unmap_cluster(unsigned long cursor, pte_unmap_unlock(pte - 1, ptl); } -static int try_to_unmap_anon(struct page *page, int ignore_refs) +static int try_to_unmap_anon(struct page *page, int migration) { struct anon_vma *anon_vma; struct vm_area_struct *vma; @@ -747,7 +730,7 @@ static int try_to_unmap_anon(struct page *page, int ignore_refs) return ret; list_for_each_entry(vma, &anon_vma->head, anon_vma_node) { - ret = try_to_unmap_one(page, vma, ignore_refs); + ret = try_to_unmap_one(page, vma, migration); if (ret == SWAP_FAIL || !page_mapped(page)) break; } @@ -764,7 +747,7 @@ static int try_to_unmap_anon(struct page *page, int ignore_refs) * * This function is only called from try_to_unmap for object-based pages. */ -static int try_to_unmap_file(struct page *page, int ignore_refs) +static int try_to_unmap_file(struct page *page, int migration) { struct address_space *mapping = page->mapping; pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); @@ -778,7 +761,7 @@ static int try_to_unmap_file(struct page *page, int ignore_refs) spin_lock(&mapping->i_mmap_lock); vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { - ret = try_to_unmap_one(page, vma, ignore_refs); + ret = try_to_unmap_one(page, vma, migration); if (ret == SWAP_FAIL || !page_mapped(page)) goto out; } @@ -863,16 +846,16 @@ out: * SWAP_AGAIN - we missed a mapping, try again later * SWAP_FAIL - the page is unswappable */ -int try_to_unmap(struct page *page, int ignore_refs) +int try_to_unmap(struct page *page, int migration) { int ret; BUG_ON(!PageLocked(page)); if (PageAnon(page)) - ret = try_to_unmap_anon(page, ignore_refs); + ret = try_to_unmap_anon(page, migration); else - ret = try_to_unmap_file(page, ignore_refs); + ret = try_to_unmap_file(page, migration); if (!page_mapped(page)) ret = SWAP_SUCCESS; diff --git a/mm/shmem.c b/mm/shmem.c index 797eef3805c..38bc3334f26 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1081,14 +1081,6 @@ repeat: page_cache_release(swappage); goto repeat; } - if (!PageSwapCache(swappage)) { - /* Page migration has occured */ - shmem_swp_unmap(entry); - spin_unlock(&info->lock); - unlock_page(swappage); - page_cache_release(swappage); - goto repeat; - } if (PageWriteback(swappage)) { shmem_swp_unmap(entry); spin_unlock(&info->lock); @@ -1654,9 +1646,9 @@ static ssize_t shmem_file_sendfile(struct file *in_file, loff_t *ppos, return desc.error; } -static int shmem_statfs(struct super_block *sb, struct kstatfs *buf) +static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf) { - struct shmem_sb_info *sbinfo = SHMEM_SB(sb); + struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb); buf->f_type = TMPFS_MAGIC; buf->f_bsize = PAGE_CACHE_SIZE; @@ -2233,10 +2225,10 @@ static struct vm_operations_struct shmem_vm_ops = { }; -static struct super_block *shmem_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +static int shmem_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *data, struct vfsmount *mnt) { - return get_sb_nodev(fs_type, flags, data, shmem_fill_super); + return get_sb_nodev(fs_type, flags, data, shmem_fill_super, mnt); } static struct file_system_type tmpfs_fs_type = { diff --git a/mm/slab.c b/mm/slab.c index f1b644eb39d..98ac20bc0de 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -331,6 +331,8 @@ static __always_inline int index_of(const size_t size) return 0; } +static int slab_early_init = 1; + #define INDEX_AC index_of(sizeof(struct arraycache_init)) #define INDEX_L3 index_of(sizeof(struct kmem_list3)) @@ -592,6 +594,7 @@ static inline struct kmem_cache *page_get_cache(struct page *page) { if (unlikely(PageCompound(page))) page = (struct page *)page_private(page); + BUG_ON(!PageSlab(page)); return (struct kmem_cache *)page->lru.next; } @@ -604,6 +607,7 @@ static inline struct slab *page_get_slab(struct page *page) { if (unlikely(PageCompound(page))) page = (struct page *)page_private(page); + BUG_ON(!PageSlab(page)); return (struct slab *)page->lru.prev; } @@ -1024,6 +1028,40 @@ static void drain_alien_cache(struct kmem_cache *cachep, } } } + +static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) +{ + struct slab *slabp = virt_to_slab(objp); + int nodeid = slabp->nodeid; + struct kmem_list3 *l3; + struct array_cache *alien = NULL; + + /* + * Make sure we are not freeing a object from another node to the array + * cache on this cpu. + */ + if (likely(slabp->nodeid == numa_node_id())) + return 0; + + l3 = cachep->nodelists[numa_node_id()]; + STATS_INC_NODEFREES(cachep); + if (l3->alien && l3->alien[nodeid]) { + alien = l3->alien[nodeid]; + spin_lock(&alien->lock); + if (unlikely(alien->avail == alien->limit)) { + STATS_INC_ACOVERFLOW(cachep); + __drain_alien_cache(cachep, alien, nodeid); + } + alien->entry[alien->avail++] = objp; + spin_unlock(&alien->lock); + } else { + spin_lock(&(cachep->nodelists[nodeid])->list_lock); + free_block(cachep, &objp, 1, nodeid); + spin_unlock(&(cachep->nodelists[nodeid])->list_lock); + } + return 1; +} + #else #define drain_alien_cache(cachep, alien) do { } while (0) @@ -1038,6 +1076,11 @@ static inline void free_alien_cache(struct array_cache **ac_ptr) { } +static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) +{ + return 0; +} + #endif static int cpuup_callback(struct notifier_block *nfb, @@ -1335,6 +1378,8 @@ void __init kmem_cache_init(void) NULL, NULL); } + slab_early_init = 0; + while (sizes->cs_size != ULONG_MAX) { /* * For performance, all the general caches are L1 aligned. @@ -1450,31 +1495,29 @@ __initcall(cpucache_init); static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) { struct page *page; - void *addr; + int nr_pages; int i; - flags |= cachep->gfpflags; #ifndef CONFIG_MMU - /* nommu uses slab's for process anonymous memory allocations, so - * requires __GFP_COMP to properly refcount higher order allocations" + /* + * Nommu uses slab's for process anonymous memory allocations, and thus + * requires __GFP_COMP to properly refcount higher order allocations */ - page = alloc_pages_node(nodeid, (flags | __GFP_COMP), cachep->gfporder); -#else - page = alloc_pages_node(nodeid, flags, cachep->gfporder); + flags |= __GFP_COMP; #endif + flags |= cachep->gfpflags; + + page = alloc_pages_node(nodeid, flags, cachep->gfporder); if (!page) return NULL; - addr = page_address(page); - i = (1 << cachep->gfporder); + nr_pages = (1 << cachep->gfporder); if (cachep->flags & SLAB_RECLAIM_ACCOUNT) - atomic_add(i, &slab_reclaim_pages); - add_page_state(nr_slab, i); - while (i--) { - __SetPageSlab(page); - page++; - } - return addr; + atomic_add(nr_pages, &slab_reclaim_pages); + add_page_state(nr_slab, nr_pages); + for (i = 0; i < nr_pages; i++) + __SetPageSlab(page + i); + return page_address(page); } /* @@ -1913,8 +1956,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, void (*dtor)(void*, struct kmem_cache *, unsigned long)) { size_t left_over, slab_size, ralign; - struct kmem_cache *cachep = NULL; - struct list_head *p; + struct kmem_cache *cachep = NULL, *pc; /* * Sanity checks... these are all serious usage bugs. @@ -1934,8 +1976,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, mutex_lock(&cache_chain_mutex); - list_for_each(p, &cache_chain) { - struct kmem_cache *pc = list_entry(p, struct kmem_cache, next); + list_for_each_entry(pc, &cache_chain, next) { mm_segment_t old_fs = get_fs(); char tmp; int res; @@ -2069,8 +2110,12 @@ kmem_cache_create (const char *name, size_t size, size_t align, #endif #endif - /* Determine if the slab management is 'on' or 'off' slab. */ - if (size >= (PAGE_SIZE >> 3)) + /* + * Determine if the slab management is 'on' or 'off' slab. + * (bootstrapping cannot cope with offslab caches so don't do + * it too early on.) + */ + if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init) /* * Size is large, assume best to place the slab management obj * off-slab (should allow better packing of objs). @@ -2460,23 +2505,28 @@ static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp, slabp->inuse--; } -static void set_slab_attr(struct kmem_cache *cachep, struct slab *slabp, - void *objp) +/* + * Map pages beginning at addr to the given cache and slab. This is required + * for the slab allocator to be able to lookup the cache and slab of a + * virtual address for kfree, ksize, kmem_ptr_validate, and slab debugging. + */ +static void slab_map_pages(struct kmem_cache *cache, struct slab *slab, + void *addr) { - int i; + int nr_pages; struct page *page; - /* Nasty!!!!!! I hope this is OK. */ - page = virt_to_page(objp); + page = virt_to_page(addr); - i = 1; + nr_pages = 1; if (likely(!PageCompound(page))) - i <<= cachep->gfporder; + nr_pages <<= cache->gfporder; + do { - page_set_cache(page, cachep); - page_set_slab(page, slabp); + page_set_cache(page, cache); + page_set_slab(page, slab); page++; - } while (--i); + } while (--nr_pages); } /* @@ -2548,7 +2598,7 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid) goto opps1; slabp->nodeid = nodeid; - set_slab_attr(cachep, slabp, objp); + slab_map_pages(cachep, slabp, objp); cache_init_objs(cachep, slabp, ctor_flags); @@ -2596,6 +2646,28 @@ static void kfree_debugcheck(const void *objp) } } +static inline void verify_redzone_free(struct kmem_cache *cache, void *obj) +{ + unsigned long redzone1, redzone2; + + redzone1 = *dbg_redzone1(cache, obj); + redzone2 = *dbg_redzone2(cache, obj); + + /* + * Redzone is ok. + */ + if (redzone1 == RED_ACTIVE && redzone2 == RED_ACTIVE) + return; + + if (redzone1 == RED_INACTIVE && redzone2 == RED_INACTIVE) + slab_error(cache, "double free detected"); + else + slab_error(cache, "memory outside object was overwritten"); + + printk(KERN_ERR "%p: redzone 1:0x%lx, redzone 2:0x%lx.\n", + obj, redzone1, redzone2); +} + static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, void *caller) { @@ -2607,27 +2679,10 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp, kfree_debugcheck(objp); page = virt_to_page(objp); - if (page_get_cache(page) != cachep) { - printk(KERN_ERR "mismatch in kmem_cache_free: expected " - "cache %p, got %p\n", - page_get_cache(page), cachep); - printk(KERN_ERR "%p is %s.\n", cachep, cachep->name); - printk(KERN_ERR "%p is %s.\n", page_get_cache(page), - page_get_cache(page)->name); - WARN_ON(1); - } slabp = page_get_slab(page); if (cachep->flags & SLAB_RED_ZONE) { - if (*dbg_redzone1(cachep, objp) != RED_ACTIVE || - *dbg_redzone2(cachep, objp) != RED_ACTIVE) { - slab_error(cachep, "double free, or memory outside" - " object was overwritten"); - printk(KERN_ERR "%p: redzone 1:0x%lx, " - "redzone 2:0x%lx.\n", - objp, *dbg_redzone1(cachep, objp), - *dbg_redzone2(cachep, objp)); - } + verify_redzone_free(cachep, objp); *dbg_redzone1(cachep, objp) = RED_INACTIVE; *dbg_redzone2(cachep, objp) = RED_INACTIVE; } @@ -3087,41 +3142,9 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp) check_irq_off(); objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0)); - /* Make sure we are not freeing a object from another - * node to the array cache on this cpu. - */ -#ifdef CONFIG_NUMA - { - struct slab *slabp; - slabp = virt_to_slab(objp); - if (unlikely(slabp->nodeid != numa_node_id())) { - struct array_cache *alien = NULL; - int nodeid = slabp->nodeid; - struct kmem_list3 *l3; - - l3 = cachep->nodelists[numa_node_id()]; - STATS_INC_NODEFREES(cachep); - if (l3->alien && l3->alien[nodeid]) { - alien = l3->alien[nodeid]; - spin_lock(&alien->lock); - if (unlikely(alien->avail == alien->limit)) { - STATS_INC_ACOVERFLOW(cachep); - __drain_alien_cache(cachep, - alien, nodeid); - } - alien->entry[alien->avail++] = objp; - spin_unlock(&alien->lock); - } else { - spin_lock(&(cachep->nodelists[nodeid])-> - list_lock); - free_block(cachep, &objp, 1, nodeid); - spin_unlock(&(cachep->nodelists[nodeid])-> - list_lock); - } - return; - } - } -#endif + if (cache_free_alien(cachep, objp)) + return; + if (likely(ac->avail < ac->limit)) { STATS_INC_FREEHIT(cachep); ac->entry[ac->avail++] = objp; @@ -3254,26 +3277,10 @@ EXPORT_SYMBOL(kmalloc_node); #endif /** - * kmalloc - allocate memory + * __do_kmalloc - allocate memory * @size: how many bytes of memory are required. - * @flags: the type of memory to allocate. + * @flags: the type of memory to allocate (see kmalloc). * @caller: function caller for debug tracking of the caller - * - * kmalloc is the normal method of allocating memory - * in the kernel. - * - * The @flags argument may be one of: - * - * %GFP_USER - Allocate memory on behalf of user. May sleep. - * - * %GFP_KERNEL - Allocate normal kernel ram. May sleep. - * - * %GFP_ATOMIC - Allocation will not sleep. Use inside interrupt handlers. - * - * Additionally, the %GFP_DMA flag may be set to indicate the memory - * must be suitable for DMA. This can mean different things on different - * platforms. For example, on i386, it means that the memory must come - * from the first 16MB. */ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, void *caller) @@ -3371,6 +3378,8 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp) { unsigned long flags; + BUG_ON(virt_to_cache(objp) != cachep); + local_irq_save(flags); __cache_free(cachep, objp); local_irq_restore(flags); @@ -3680,7 +3689,7 @@ void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, */ static void cache_reap(void *unused) { - struct list_head *walk; + struct kmem_cache *searchp; struct kmem_list3 *l3; int node = numa_node_id(); @@ -3691,13 +3700,11 @@ static void cache_reap(void *unused) return; } - list_for_each(walk, &cache_chain) { - struct kmem_cache *searchp; + list_for_each_entry(searchp, &cache_chain, next) { struct list_head *p; int tofree; struct slab *slabp; - searchp = list_entry(walk, struct kmem_cache, next); check_irq_on(); /* @@ -3825,7 +3832,6 @@ static void s_stop(struct seq_file *m, void *p) static int s_show(struct seq_file *m, void *p) { struct kmem_cache *cachep = p; - struct list_head *q; struct slab *slabp; unsigned long active_objs; unsigned long num_objs; @@ -3846,15 +3852,13 @@ static int s_show(struct seq_file *m, void *p) check_irq_on(); spin_lock_irq(&l3->list_lock); - list_for_each(q, &l3->slabs_full) { - slabp = list_entry(q, struct slab, list); + list_for_each_entry(slabp, &l3->slabs_full, list) { if (slabp->inuse != cachep->num && !error) error = "slabs_full accounting error"; active_objs += cachep->num; active_slabs++; } - list_for_each(q, &l3->slabs_partial) { - slabp = list_entry(q, struct slab, list); + list_for_each_entry(slabp, &l3->slabs_partial, list) { if (slabp->inuse == cachep->num && !error) error = "slabs_partial inuse accounting error"; if (!slabp->inuse && !error) @@ -3862,8 +3866,7 @@ static int s_show(struct seq_file *m, void *p) active_objs += slabp->inuse; active_slabs++; } - list_for_each(q, &l3->slabs_free) { - slabp = list_entry(q, struct slab, list); + list_for_each_entry(slabp, &l3->slabs_free, list) { if (slabp->inuse && !error) error = "slabs_free/inuse accounting error"; num_slabs++; @@ -3956,7 +3959,7 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer, { char kbuf[MAX_SLABINFO_WRITE + 1], *tmp; int limit, batchcount, shared, res; - struct list_head *p; + struct kmem_cache *cachep; if (count > MAX_SLABINFO_WRITE) return -EINVAL; @@ -3975,10 +3978,7 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer, /* Find the cache in the chain of caches. */ mutex_lock(&cache_chain_mutex); res = -EINVAL; - list_for_each(p, &cache_chain) { - struct kmem_cache *cachep; - - cachep = list_entry(p, struct kmem_cache, next); + list_for_each_entry(cachep, &cache_chain, next) { if (!strcmp(cachep->name, kbuf)) { if (limit < 1 || batchcount < 1 || batchcount > limit || shared < 0) { @@ -4080,7 +4080,6 @@ static void show_symbol(struct seq_file *m, unsigned long address) static int leaks_show(struct seq_file *m, void *p) { struct kmem_cache *cachep = p; - struct list_head *q; struct slab *slabp; struct kmem_list3 *l3; const char *name; @@ -4105,14 +4104,10 @@ static int leaks_show(struct seq_file *m, void *p) check_irq_on(); spin_lock_irq(&l3->list_lock); - list_for_each(q, &l3->slabs_full) { - slabp = list_entry(q, struct slab, list); + list_for_each_entry(slabp, &l3->slabs_full, list) handle_slab(n, cachep, slabp); - } - list_for_each(q, &l3->slabs_partial) { - slabp = list_entry(q, struct slab, list); + list_for_each_entry(slabp, &l3->slabs_partial, list) handle_slab(n, cachep, slabp); - } spin_unlock_irq(&l3->list_lock); } name = cachep->name; diff --git a/mm/sparse.c b/mm/sparse.c index 100040c0dfb..e0a3fe48aa3 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -99,6 +99,22 @@ int __section_nr(struct mem_section* ms) return (root_nr * SECTIONS_PER_ROOT) + (ms - root); } +/* + * During early boot, before section_mem_map is used for an actual + * mem_map, we use section_mem_map to store the section's NUMA + * node. This keeps us from having to use another data structure. The + * node information is cleared just before we store the real mem_map. + */ +static inline unsigned long sparse_encode_early_nid(int nid) +{ + return (nid << SECTION_NID_SHIFT); +} + +static inline int sparse_early_nid(struct mem_section *section) +{ + return (section->section_mem_map >> SECTION_NID_SHIFT); +} + /* Record a memory area against a node. */ void memory_present(int nid, unsigned long start, unsigned long end) { @@ -113,7 +129,8 @@ void memory_present(int nid, unsigned long start, unsigned long end) ms = __nr_to_section(section); if (!ms->section_mem_map) - ms->section_mem_map = SECTION_MARKED_PRESENT; + ms->section_mem_map = sparse_encode_early_nid(nid) | + SECTION_MARKED_PRESENT; } } @@ -164,6 +181,7 @@ static int sparse_init_one_section(struct mem_section *ms, if (!valid_section(ms)) return -EINVAL; + ms->section_mem_map &= ~SECTION_MAP_MASK; ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum); return 1; @@ -172,8 +190,8 @@ static int sparse_init_one_section(struct mem_section *ms, static struct page *sparse_early_mem_map_alloc(unsigned long pnum) { struct page *map; - int nid = early_pfn_to_nid(section_nr_to_pfn(pnum)); struct mem_section *ms = __nr_to_section(pnum); + int nid = sparse_early_nid(ms); map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION); if (map) diff --git a/mm/swap.c b/mm/swap.c index 88895c249bc..03ae2076f92 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -480,48 +480,6 @@ static int cpu_swap_callback(struct notifier_block *nfb, #endif /* CONFIG_HOTPLUG_CPU */ #endif /* CONFIG_SMP */ -#ifdef CONFIG_SMP -void percpu_counter_mod(struct percpu_counter *fbc, long amount) -{ - long count; - long *pcount; - int cpu = get_cpu(); - - pcount = per_cpu_ptr(fbc->counters, cpu); - count = *pcount + amount; - if (count >= FBC_BATCH || count <= -FBC_BATCH) { - spin_lock(&fbc->lock); - fbc->count += count; - *pcount = 0; - spin_unlock(&fbc->lock); - } else { - *pcount = count; - } - put_cpu(); -} -EXPORT_SYMBOL(percpu_counter_mod); - -/* - * Add up all the per-cpu counts, return the result. This is a more accurate - * but much slower version of percpu_counter_read_positive() - */ -long percpu_counter_sum(struct percpu_counter *fbc) -{ - long ret; - int cpu; - - spin_lock(&fbc->lock); - ret = fbc->count; - for_each_possible_cpu(cpu) { - long *pcount = per_cpu_ptr(fbc->counters, cpu); - ret += *pcount; - } - spin_unlock(&fbc->lock); - return ret < 0 ? 0 : ret; -} -EXPORT_SYMBOL(percpu_counter_sum); -#endif - /* * Perform any setup for the swap system */ diff --git a/mm/swapfile.c b/mm/swapfile.c index e5fd5385f0c..cc367f7e75d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -395,6 +395,9 @@ void free_swap_and_cache(swp_entry_t entry) struct swap_info_struct * p; struct page *page = NULL; + if (is_migration_entry(entry)) + return; + p = swap_info_get(entry); if (p) { if (swap_entry_free(p, swp_offset(entry)) == 1) { @@ -615,15 +618,6 @@ static int unuse_mm(struct mm_struct *mm, return 0; } -#ifdef CONFIG_MIGRATION -int remove_vma_swap(struct vm_area_struct *vma, struct page *page) -{ - swp_entry_t entry = { .val = page_private(page) }; - - return unuse_vma(vma, entry, page); -} -#endif - /* * Scan swap_map from current position to next entry still in use. * Recycle to start on reaching the end, returning 0 when empty. @@ -716,7 +710,6 @@ static int try_to_unuse(unsigned int type) */ swap_map = &si->swap_map[i]; entry = swp_entry(type, i); -again: page = read_swap_cache_async(entry, NULL, 0); if (!page) { /* @@ -751,12 +744,6 @@ again: wait_on_page_locked(page); wait_on_page_writeback(page); lock_page(page); - if (!PageSwapCache(page)) { - /* Page migration has occured */ - unlock_page(page); - page_cache_release(page); - goto again; - } wait_on_page_writeback(page); /* @@ -785,10 +772,8 @@ again: while (*swap_map > 1 && !retval && (p = p->next) != &start_mm->mmlist) { mm = list_entry(p, struct mm_struct, mmlist); - if (atomic_inc_return(&mm->mm_users) == 1) { - atomic_dec(&mm->mm_users); + if (!atomic_inc_not_zero(&mm->mm_users)) continue; - } spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; @@ -1407,19 +1392,7 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) if (!(p->flags & SWP_USED)) break; error = -EPERM; - /* - * Test if adding another swap device is possible. There are - * two limiting factors: 1) the number of bits for the swap - * type swp_entry_t definition and 2) the number of bits for - * the swap type in the swap ptes as defined by the different - * architectures. To honor both limitations a swap entry - * with swap offset 0 and swap type ~0UL is created, encoded - * to a swap pte, decoded to a swp_entry_t again and finally - * the swap type part is extracted. This will mask all bits - * from the initial ~0UL that can't be encoded in either the - * swp_entry_t or the architecture definition of a swap pte. - */ - if (type > swp_type(pte_to_swp_entry(swp_entry_to_pte(swp_entry(~0UL,0))))) { + if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); goto out; } @@ -1504,8 +1477,7 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) error = -EINVAL; goto bad_swap; } - page = read_cache_page(mapping, 0, - (filler_t *)mapping->a_ops->readpage, swap_file); + page = read_mapping_page(mapping, 0, swap_file); if (IS_ERR(page)) { error = PTR_ERR(page); goto bad_swap; @@ -1709,6 +1681,9 @@ int swap_duplicate(swp_entry_t entry) unsigned long offset, type; int result = 0; + if (is_migration_entry(entry)) + return 1; + type = swp_type(entry); if (type >= nr_swapfiles) goto bad_file; diff --git a/mm/truncate.c b/mm/truncate.c index 6cb3fff25f6..cf1b015df4a 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -230,14 +230,24 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; + pgoff_t index; + int lock_failed; - if (TestSetPageLocked(page)) { - next++; - continue; - } - if (page->index > next) - next = page->index; + lock_failed = TestSetPageLocked(page); + + /* + * We really shouldn't be looking at the ->index of an + * unlocked page. But we're not allowed to lock these + * pages. So we rely upon nobody altering the ->index + * of this (pinned-by-us) page. + */ + index = page->index; + if (index > next) + next = index; next++; + if (lock_failed) + continue; + if (PageDirty(page) || PageWriteback(page)) goto unlock; if (page_mapped(page)) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index c0504f1e34e..35f8553f893 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -257,6 +257,19 @@ struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, int } /* Caller must hold vmlist_lock */ +static struct vm_struct *__find_vm_area(void *addr) +{ + struct vm_struct *tmp; + + for (tmp = vmlist; tmp != NULL; tmp = tmp->next) { + if (tmp->addr == addr) + break; + } + + return tmp; +} + +/* Caller must hold vmlist_lock */ struct vm_struct *__remove_vm_area(void *addr) { struct vm_struct **p, *tmp; @@ -498,11 +511,33 @@ EXPORT_SYMBOL(__vmalloc); */ void *vmalloc(unsigned long size) { - return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL); + return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL); } EXPORT_SYMBOL(vmalloc); /** + * vmalloc_user - allocate virtually contiguous memory which has + * been zeroed so it can be mapped to userspace without + * leaking data. + * + * @size: allocation size + */ +void *vmalloc_user(unsigned long size) +{ + struct vm_struct *area; + void *ret; + + ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); + write_lock(&vmlist_lock); + area = __find_vm_area(ret); + area->flags |= VM_USERMAP; + write_unlock(&vmlist_lock); + + return ret; +} +EXPORT_SYMBOL(vmalloc_user); + +/** * vmalloc_node - allocate memory on a specific node * * @size: allocation size @@ -516,7 +551,7 @@ EXPORT_SYMBOL(vmalloc); */ void *vmalloc_node(unsigned long size, int node) { - return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, node); + return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL, node); } EXPORT_SYMBOL(vmalloc_node); @@ -556,6 +591,28 @@ void *vmalloc_32(unsigned long size) } EXPORT_SYMBOL(vmalloc_32); +/** + * vmalloc_32_user - allocate virtually contiguous memory (32bit + * addressable) which is zeroed so it can be + * mapped to userspace without leaking data. + * + * @size: allocation size + */ +void *vmalloc_32_user(unsigned long size) +{ + struct vm_struct *area; + void *ret; + + ret = __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL); + write_lock(&vmlist_lock); + area = __find_vm_area(ret); + area->flags |= VM_USERMAP; + write_unlock(&vmlist_lock); + + return ret; +} +EXPORT_SYMBOL(vmalloc_32_user); + long vread(char *buf, char *addr, unsigned long count) { struct vm_struct *tmp; @@ -630,3 +687,64 @@ finished: read_unlock(&vmlist_lock); return buf - buf_start; } + +/** + * remap_vmalloc_range - map vmalloc pages to userspace + * + * @vma: vma to cover (map full range of vma) + * @addr: vmalloc memory + * @pgoff: number of pages into addr before first page to map + * @returns: 0 for success, -Exxx on failure + * + * This function checks that addr is a valid vmalloc'ed area, and + * that it is big enough to cover the vma. Will return failure if + * that criteria isn't met. + * + * Similar to remap_pfn_range (see mm/memory.c) + */ +int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, + unsigned long pgoff) +{ + struct vm_struct *area; + unsigned long uaddr = vma->vm_start; + unsigned long usize = vma->vm_end - vma->vm_start; + int ret; + + if ((PAGE_SIZE-1) & (unsigned long)addr) + return -EINVAL; + + read_lock(&vmlist_lock); + area = __find_vm_area(addr); + if (!area) + goto out_einval_locked; + + if (!(area->flags & VM_USERMAP)) + goto out_einval_locked; + + if (usize + (pgoff << PAGE_SHIFT) > area->size - PAGE_SIZE) + goto out_einval_locked; + read_unlock(&vmlist_lock); + + addr += pgoff << PAGE_SHIFT; + do { + struct page *page = vmalloc_to_page(addr); + ret = vm_insert_page(vma, uaddr, page); + if (ret) + return ret; + + uaddr += PAGE_SIZE; + addr += PAGE_SIZE; + usize -= PAGE_SIZE; + } while (usize > 0); + + /* Prevent "things" like memory migration? VM_flags need a cleanup... */ + vma->vm_flags |= VM_RESERVED; + + return ret; + +out_einval_locked: + read_unlock(&vmlist_lock); + return -EINVAL; +} +EXPORT_SYMBOL(remap_vmalloc_range); + diff --git a/mm/vmscan.c b/mm/vmscan.c index 440a733fe2e..72babac71de 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -61,6 +61,8 @@ struct scan_control { * In this context, it doesn't matter that we scan the * whole list at once. */ int swap_cluster_max; + + int swappiness; }; /* @@ -108,7 +110,7 @@ struct shrinker { * From 0 .. 100. Higher means more swappy. */ int vm_swappiness = 60; -static long total_memory; +long vm_total_pages; /* The total number of pages which the VM controls */ static LIST_HEAD(shrinker_list); static DECLARE_RWSEM(shrinker_rwsem); @@ -288,11 +290,23 @@ static void handle_write_error(struct address_space *mapping, unlock_page(page); } +/* possible outcome of pageout() */ +typedef enum { + /* failed to write page out, page is locked */ + PAGE_KEEP, + /* move page to the active list, page is locked */ + PAGE_ACTIVATE, + /* page has been sent to the disk successfully, page is unlocked */ + PAGE_SUCCESS, + /* page is clean and locked */ + PAGE_CLEAN, +} pageout_t; + /* * pageout is called by shrink_page_list() for each dirty page. * Calls ->writepage(). */ -pageout_t pageout(struct page *page, struct address_space *mapping) +static pageout_t pageout(struct page *page, struct address_space *mapping) { /* * If the page is dirty, only perform writeback if that write @@ -337,6 +351,8 @@ pageout_t pageout(struct page *page, struct address_space *mapping) struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .nr_to_write = SWAP_CLUSTER_MAX, + .range_start = 0, + .range_end = LLONG_MAX, .nonblocking = 1, .for_reclaim = 1, }; @@ -727,7 +743,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, * how much memory * is mapped. */ - mapped_ratio = (sc->nr_mapped * 100) / total_memory; + mapped_ratio = (sc->nr_mapped * 100) / vm_total_pages; /* * Now decide how much we really want to unmap some pages. The @@ -741,7 +757,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, * A 100% value of vm_swappiness overrides this algorithm * altogether. */ - swap_tendency = mapped_ratio / 2 + distress + vm_swappiness; + swap_tendency = mapped_ratio / 2 + distress + sc->swappiness; /* * Now use this metric to decide whether to start moving mapped @@ -957,6 +973,7 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask) .may_writepage = !laptop_mode, .swap_cluster_max = SWAP_CLUSTER_MAX, .may_swap = 1, + .swappiness = vm_swappiness, }; inc_page_state(allocstall); @@ -1021,10 +1038,6 @@ out: * For kswapd, balance_pgdat() will work across all this node's zones until * they are all at pages_high. * - * If `nr_pages' is non-zero then it is the number of pages which are to be - * reclaimed, regardless of the zone occupancies. This is a software suspend - * special. - * * Returns the number of pages which were actually freed. * * There is special handling here for zones which are full of pinned pages. @@ -1042,10 +1055,8 @@ out: * the page allocator fallback scheme to ensure that aging of pages is balanced * across the zones. */ -static unsigned long balance_pgdat(pg_data_t *pgdat, unsigned long nr_pages, - int order) +static unsigned long balance_pgdat(pg_data_t *pgdat, int order) { - unsigned long to_free = nr_pages; int all_zones_ok; int priority; int i; @@ -1055,7 +1066,8 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, unsigned long nr_pages, struct scan_control sc = { .gfp_mask = GFP_KERNEL, .may_swap = 1, - .swap_cluster_max = nr_pages ? nr_pages : SWAP_CLUSTER_MAX, + .swap_cluster_max = SWAP_CLUSTER_MAX, + .swappiness = vm_swappiness, }; loop_again: @@ -1082,31 +1094,26 @@ loop_again: all_zones_ok = 1; - if (nr_pages == 0) { - /* - * Scan in the highmem->dma direction for the highest - * zone which needs scanning - */ - for (i = pgdat->nr_zones - 1; i >= 0; i--) { - struct zone *zone = pgdat->node_zones + i; + /* + * Scan in the highmem->dma direction for the highest + * zone which needs scanning + */ + for (i = pgdat->nr_zones - 1; i >= 0; i--) { + struct zone *zone = pgdat->node_zones + i; - if (!populated_zone(zone)) - continue; + if (!populated_zone(zone)) + continue; - if (zone->all_unreclaimable && - priority != DEF_PRIORITY) - continue; + if (zone->all_unreclaimable && priority != DEF_PRIORITY) + continue; - if (!zone_watermark_ok(zone, order, - zone->pages_high, 0, 0)) { - end_zone = i; - goto scan; - } + if (!zone_watermark_ok(zone, order, zone->pages_high, + 0, 0)) { + end_zone = i; + goto scan; } - goto out; - } else { - end_zone = pgdat->nr_zones - 1; } + goto out; scan: for (i = 0; i <= end_zone; i++) { struct zone *zone = pgdat->node_zones + i; @@ -1133,11 +1140,9 @@ scan: if (zone->all_unreclaimable && priority != DEF_PRIORITY) continue; - if (nr_pages == 0) { /* Not software suspend */ - if (!zone_watermark_ok(zone, order, - zone->pages_high, end_zone, 0)) - all_zones_ok = 0; - } + if (!zone_watermark_ok(zone, order, zone->pages_high, + end_zone, 0)) + all_zones_ok = 0; zone->temp_priority = priority; if (zone->prev_priority > priority) zone->prev_priority = priority; @@ -1162,8 +1167,6 @@ scan: total_scanned > nr_reclaimed + nr_reclaimed / 2) sc.may_writepage = 1; } - if (nr_pages && to_free > nr_reclaimed) - continue; /* swsusp: need to do more work */ if (all_zones_ok) break; /* kswapd: all done */ /* @@ -1179,7 +1182,7 @@ scan: * matches the direct reclaim path behaviour in terms of impact * on zone->*_priority. */ - if ((nr_reclaimed >= SWAP_CLUSTER_MAX) && !nr_pages) + if (nr_reclaimed >= SWAP_CLUSTER_MAX) break; } out: @@ -1261,7 +1264,7 @@ static int kswapd(void *p) } finish_wait(&pgdat->kswapd_wait, &wait); - balance_pgdat(pgdat, 0, order); + balance_pgdat(pgdat, order); } return 0; } @@ -1290,35 +1293,154 @@ void wakeup_kswapd(struct zone *zone, int order) #ifdef CONFIG_PM /* - * Try to free `nr_pages' of memory, system-wide. Returns the number of freed - * pages. + * Helper function for shrink_all_memory(). Tries to reclaim 'nr_pages' pages + * from LRU lists system-wide, for given pass and priority, and returns the + * number of reclaimed pages + * + * For pass > 3 we also try to shrink the LRU lists that contain a few pages + */ +static unsigned long shrink_all_zones(unsigned long nr_pages, int pass, + int prio, struct scan_control *sc) +{ + struct zone *zone; + unsigned long nr_to_scan, ret = 0; + + for_each_zone(zone) { + + if (!populated_zone(zone)) + continue; + + if (zone->all_unreclaimable && prio != DEF_PRIORITY) + continue; + + /* For pass = 0 we don't shrink the active list */ + if (pass > 0) { + zone->nr_scan_active += (zone->nr_active >> prio) + 1; + if (zone->nr_scan_active >= nr_pages || pass > 3) { + zone->nr_scan_active = 0; + nr_to_scan = min(nr_pages, zone->nr_active); + shrink_active_list(nr_to_scan, zone, sc); + } + } + + zone->nr_scan_inactive += (zone->nr_inactive >> prio) + 1; + if (zone->nr_scan_inactive >= nr_pages || pass > 3) { + zone->nr_scan_inactive = 0; + nr_to_scan = min(nr_pages, zone->nr_inactive); + ret += shrink_inactive_list(nr_to_scan, zone, sc); + if (ret >= nr_pages) + return ret; + } + } + + return ret; +} + +/* + * Try to free `nr_pages' of memory, system-wide, and return the number of + * freed pages. + * + * Rather than trying to age LRUs the aim is to preserve the overall + * LRU order by reclaiming preferentially + * inactive > active > active referenced > active mapped */ unsigned long shrink_all_memory(unsigned long nr_pages) { - pg_data_t *pgdat; - unsigned long nr_to_free = nr_pages; + unsigned long lru_pages, nr_slab; unsigned long ret = 0; - unsigned retry = 2; - struct reclaim_state reclaim_state = { - .reclaimed_slab = 0, + int pass; + struct reclaim_state reclaim_state; + struct zone *zone; + struct scan_control sc = { + .gfp_mask = GFP_KERNEL, + .may_swap = 0, + .swap_cluster_max = nr_pages, + .may_writepage = 1, + .swappiness = vm_swappiness, }; current->reclaim_state = &reclaim_state; -repeat: - for_each_online_pgdat(pgdat) { - unsigned long freed; - freed = balance_pgdat(pgdat, nr_to_free, 0); - ret += freed; - nr_to_free -= freed; - if ((long)nr_to_free <= 0) + lru_pages = 0; + for_each_zone(zone) + lru_pages += zone->nr_active + zone->nr_inactive; + + nr_slab = read_page_state(nr_slab); + /* If slab caches are huge, it's better to hit them first */ + while (nr_slab >= lru_pages) { + reclaim_state.reclaimed_slab = 0; + shrink_slab(nr_pages, sc.gfp_mask, lru_pages); + if (!reclaim_state.reclaimed_slab) break; + + ret += reclaim_state.reclaimed_slab; + if (ret >= nr_pages) + goto out; + + nr_slab -= reclaim_state.reclaimed_slab; } - if (retry-- && ret < nr_pages) { - blk_congestion_wait(WRITE, HZ/5); - goto repeat; + + /* + * We try to shrink LRUs in 5 passes: + * 0 = Reclaim from inactive_list only + * 1 = Reclaim from active list but don't reclaim mapped + * 2 = 2nd pass of type 1 + * 3 = Reclaim mapped (normal reclaim) + * 4 = 2nd pass of type 3 + */ + for (pass = 0; pass < 5; pass++) { + int prio; + + /* Needed for shrinking slab caches later on */ + if (!lru_pages) + for_each_zone(zone) { + lru_pages += zone->nr_active; + lru_pages += zone->nr_inactive; + } + + /* Force reclaiming mapped pages in the passes #3 and #4 */ + if (pass > 2) { + sc.may_swap = 1; + sc.swappiness = 100; + } + + for (prio = DEF_PRIORITY; prio >= 0; prio--) { + unsigned long nr_to_scan = nr_pages - ret; + + sc.nr_mapped = read_page_state(nr_mapped); + sc.nr_scanned = 0; + + ret += shrink_all_zones(nr_to_scan, prio, pass, &sc); + if (ret >= nr_pages) + goto out; + + reclaim_state.reclaimed_slab = 0; + shrink_slab(sc.nr_scanned, sc.gfp_mask, lru_pages); + ret += reclaim_state.reclaimed_slab; + if (ret >= nr_pages) + goto out; + + if (sc.nr_scanned && prio < DEF_PRIORITY - 2) + blk_congestion_wait(WRITE, HZ / 10); + } + + lru_pages = 0; } + + /* + * If ret = 0, we could not shrink LRUs, but there may be something + * in slab caches + */ + if (!ret) + do { + reclaim_state.reclaimed_slab = 0; + shrink_slab(nr_pages, sc.gfp_mask, lru_pages); + ret += reclaim_state.reclaimed_slab; + } while (ret < nr_pages && reclaim_state.reclaimed_slab > 0); + +out: current->reclaim_state = NULL; + return ret; } #endif @@ -1360,7 +1482,6 @@ static int __init kswapd_init(void) pgdat->kswapd = find_task_by_pid(pid); read_unlock(&tasklist_lock); } - total_memory = nr_free_pagecache_pages(); hotcpu_notifier(cpu_callback, 0); return 0; } @@ -1416,6 +1537,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) .swap_cluster_max = max_t(unsigned long, nr_pages, SWAP_CLUSTER_MAX), .gfp_mask = gfp_mask, + .swappiness = vm_swappiness, }; disable_swap_token(); |