diff options
author | James Bottomley <jejb@mulgrave.il.steeleye.com> | 2006-11-22 12:06:44 -0600 |
---|---|---|
committer | James Bottomley <jejb@mulgrave.il.steeleye.com> | 2006-11-22 12:06:44 -0600 |
commit | 0bd2af46839ad6262d25714a6ec0365db9d6b98f (patch) | |
tree | dcced72d230d69fd0c5816ac6dd03ab84799a93e /mm | |
parent | e138a5d2356729b8752e88520cc1525fae9794ac (diff) | |
parent | f26b90440cd74c78fe10c9bd5160809704a9627c (diff) |
Merge ../scsi-rc-fixes-2.6
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Makefile | 3 | ||||
-rw-r--r-- | mm/backing-dev.c | 69 | ||||
-rw-r--r-- | mm/filemap.c | 109 | ||||
-rw-r--r-- | mm/hugetlb.c | 25 | ||||
-rw-r--r-- | mm/memory.c | 1 | ||||
-rw-r--r-- | mm/mempolicy.c | 2 | ||||
-rw-r--r-- | mm/migrate.c | 3 | ||||
-rw-r--r-- | mm/mmap.c | 26 | ||||
-rw-r--r-- | mm/oom_kill.c | 1 | ||||
-rw-r--r-- | mm/page-writeback.c | 17 | ||||
-rw-r--r-- | mm/page_alloc.c | 60 | ||||
-rw-r--r-- | mm/readahead.c | 2 | ||||
-rw-r--r-- | mm/rmap.c | 41 | ||||
-rw-r--r-- | mm/shmem.c | 84 | ||||
-rw-r--r-- | mm/shmem_acl.c | 2 | ||||
-rw-r--r-- | mm/slab.c | 13 | ||||
-rw-r--r-- | mm/sparse.c | 2 | ||||
-rw-r--r-- | mm/truncate.c | 4 | ||||
-rw-r--r-- | mm/vmalloc.c | 54 | ||||
-rw-r--r-- | mm/vmscan.c | 75 | ||||
-rw-r--r-- | mm/vmstat.c | 2 |
21 files changed, 421 insertions, 174 deletions
diff --git a/mm/Makefile b/mm/Makefile index 12b3a4eee88..f3c077eb0b8 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -10,7 +10,8 @@ mmu-$(CONFIG_MMU) := fremap.o highmem.o madvise.o memory.o mincore.o \ obj-y := bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \ page_alloc.o page-writeback.o pdflush.o \ readahead.o swap.o truncate.o vmscan.o \ - prio_tree.o util.o mmzone.o vmstat.o $(mmu-y) + prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ + $(mmu-y) ifeq ($(CONFIG_MMU)$(CONFIG_BLOCK),yy) obj-y += bounce.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c new file mode 100644 index 00000000000..f50a2811f9d --- /dev/null +++ b/mm/backing-dev.c @@ -0,0 +1,69 @@ + +#include <linux/wait.h> +#include <linux/backing-dev.h> +#include <linux/fs.h> +#include <linux/sched.h> +#include <linux/module.h> + +static wait_queue_head_t congestion_wqh[2] = { + __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]), + __WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1]) + }; + + +void clear_bdi_congested(struct backing_dev_info *bdi, int rw) +{ + enum bdi_state bit; + wait_queue_head_t *wqh = &congestion_wqh[rw]; + + bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested; + clear_bit(bit, &bdi->state); + smp_mb__after_clear_bit(); + if (waitqueue_active(wqh)) + wake_up(wqh); +} +EXPORT_SYMBOL(clear_bdi_congested); + +void set_bdi_congested(struct backing_dev_info *bdi, int rw) +{ + enum bdi_state bit; + + bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested; + set_bit(bit, &bdi->state); +} +EXPORT_SYMBOL(set_bdi_congested); + +/** + * congestion_wait - wait for a backing_dev to become uncongested + * @rw: READ or WRITE + * @timeout: timeout in jiffies + * + * Waits for up to @timeout jiffies for a backing_dev (any backing_dev) to exit + * write congestion. If no backing_devs are congested then just wait for the + * next write to be completed. + */ +long congestion_wait(int rw, long timeout) +{ + long ret; + DEFINE_WAIT(wait); + wait_queue_head_t *wqh = &congestion_wqh[rw]; + + prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); + ret = io_schedule_timeout(timeout); + finish_wait(wqh, &wait); + return ret; +} +EXPORT_SYMBOL(congestion_wait); + +/** + * congestion_end - wake up sleepers on a congested backing_dev_info + * @rw: READ or WRITE + */ +void congestion_end(int rw) +{ + wait_queue_head_t *wqh = &congestion_wqh[rw]; + + if (waitqueue_active(wqh)) + wake_up(wqh); +} +EXPORT_SYMBOL(congestion_end); diff --git a/mm/filemap.c b/mm/filemap.c index 3464b681f84..7b84dc81434 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -75,8 +75,8 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, * ->mmap_sem * ->lock_page (access_process_vm) * - * ->mmap_sem - * ->i_mutex (msync) + * ->i_mutex (generic_file_buffered_write) + * ->mmap_sem (fault_in_pages_readable->do_page_fault) * * ->i_mutex * ->i_alloc_sem (various) @@ -467,25 +467,15 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, } #ifdef CONFIG_NUMA -struct page *page_cache_alloc(struct address_space *x) +struct page *__page_cache_alloc(gfp_t gfp) { if (cpuset_do_page_mem_spread()) { int n = cpuset_mem_spread_node(); - return alloc_pages_node(n, mapping_gfp_mask(x), 0); + return alloc_pages_node(n, gfp, 0); } - return alloc_pages(mapping_gfp_mask(x), 0); + return alloc_pages(gfp, 0); } -EXPORT_SYMBOL(page_cache_alloc); - -struct page *page_cache_alloc_cold(struct address_space *x) -{ - if (cpuset_do_page_mem_spread()) { - int n = cpuset_mem_spread_node(); - return alloc_pages_node(n, mapping_gfp_mask(x)|__GFP_COLD, 0); - } - return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0); -} -EXPORT_SYMBOL(page_cache_alloc_cold); +EXPORT_SYMBOL(__page_cache_alloc); #endif static int __sleep_on_page_lock(void *word) @@ -826,7 +816,6 @@ struct page * grab_cache_page_nowait(struct address_space *mapping, unsigned long index) { struct page *page = find_get_page(mapping, index); - gfp_t gfp_mask; if (page) { if (!TestSetPageLocked(page)) @@ -834,9 +823,8 @@ grab_cache_page_nowait(struct address_space *mapping, unsigned long index) page_cache_release(page); return NULL; } - gfp_mask = mapping_gfp_mask(mapping) & ~__GFP_FS; - page = alloc_pages(gfp_mask, 0); - if (page && add_to_page_cache_lru(page, mapping, index, gfp_mask)) { + page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS); + if (page && add_to_page_cache_lru(page, mapping, index, GFP_KERNEL)) { page_cache_release(page); page = NULL; } @@ -1884,11 +1872,10 @@ repeat: * if suid or (sgid and xgrp) * remove privs */ -int remove_suid(struct dentry *dentry) +int should_remove_suid(struct dentry *dentry) { mode_t mode = dentry->d_inode->i_mode; int kill = 0; - int result = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) @@ -1901,13 +1888,28 @@ int remove_suid(struct dentry *dentry) if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) kill |= ATTR_KILL_SGID; - if (unlikely(kill && !capable(CAP_FSETID))) { - struct iattr newattrs; + if (unlikely(kill && !capable(CAP_FSETID))) + return kill; - newattrs.ia_valid = ATTR_FORCE | kill; - result = notify_change(dentry, &newattrs); - } - return result; + return 0; +} + +int __remove_suid(struct dentry *dentry, int kill) +{ + struct iattr newattrs; + + newattrs.ia_valid = ATTR_FORCE | kill; + return notify_change(dentry, &newattrs); +} + +int remove_suid(struct dentry *dentry) +{ + int kill = should_remove_suid(dentry); + + if (unlikely(kill)) + return __remove_suid(dentry, kill); + + return 0; } EXPORT_SYMBOL(remove_suid); @@ -2222,7 +2224,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t *ppos) { struct file *file = iocb->ki_filp; - const struct address_space * mapping = file->f_mapping; + struct address_space * mapping = file->f_mapping; size_t ocount; /* original count */ size_t count; /* after file limit checks */ struct inode *inode = mapping->host; @@ -2275,8 +2277,11 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (unlikely(file->f_flags & O_DIRECT)) { - written = generic_file_direct_write(iocb, iov, - &nr_segs, pos, ppos, count, ocount); + loff_t endbyte; + ssize_t written_buffered; + + written = generic_file_direct_write(iocb, iov, &nr_segs, pos, + ppos, count, ocount); if (written < 0 || written == count) goto out; /* @@ -2285,10 +2290,46 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, */ pos += written; count -= written; - } + written_buffered = generic_file_buffered_write(iocb, iov, + nr_segs, pos, ppos, count, + written); + /* + * If generic_file_buffered_write() retuned a synchronous error + * then we want to return the number of bytes which were + * direct-written, or the error code if that was zero. Note + * that this differs from normal direct-io semantics, which + * will return -EFOO even if some bytes were written. + */ + if (written_buffered < 0) { + err = written_buffered; + goto out; + } - written = generic_file_buffered_write(iocb, iov, nr_segs, - pos, ppos, count, written); + /* + * We need to ensure that the page cache pages are written to + * disk and invalidated to preserve the expected O_DIRECT + * semantics. + */ + endbyte = pos + written_buffered - written - 1; + err = do_sync_file_range(file, pos, endbyte, + SYNC_FILE_RANGE_WAIT_BEFORE| + SYNC_FILE_RANGE_WRITE| + SYNC_FILE_RANGE_WAIT_AFTER); + if (err == 0) { + written = written_buffered; + invalidate_mapping_pages(mapping, + pos >> PAGE_CACHE_SHIFT, + endbyte >> PAGE_CACHE_SHIFT); + } else { + /* + * We don't know how much we wrote, so just return + * the number of bytes which were direct-written + */ + } + } else { + written = generic_file_buffered_write(iocb, iov, nr_segs, + pos, ppos, count, written); + } out: current->backing_dev_info = NULL; return written ? written : err; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 1d709ff528e..a088f593a80 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -356,8 +356,8 @@ nomem: return -ENOMEM; } -void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, - unsigned long end) +void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -398,6 +398,24 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, } } +void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, + unsigned long end) +{ + /* + * It is undesirable to test vma->vm_file as it should be non-null + * for valid hugetlb area. However, vm_file will be NULL in the error + * cleanup path of do_mmap_pgoff. When hugetlbfs ->mmap method fails, + * do_mmap_pgoff() nullifies vma->vm_file before calling this function + * to clean up. Since no pte has actually been setup, it is safe to + * do nothing in this case. + */ + if (vma->vm_file) { + spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); + __unmap_hugepage_range(vma, start, end); + spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock); + } +} + static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t pte) { @@ -460,6 +478,9 @@ int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma, retry: page = find_lock_page(mapping, idx); if (!page) { + size = i_size_read(mapping->host) >> HPAGE_SHIFT; + if (idx >= size) + goto out; if (hugetlb_get_quota(mapping)) goto out; page = alloc_huge_page(vma, address); diff --git a/mm/memory.c b/mm/memory.c index b5a4aadd961..156861fcac4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1452,6 +1452,7 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) memset(kaddr, 0, PAGE_SIZE); kunmap_atomic(kaddr, KM_USER0); + flush_dcache_page(dst); return; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 25788b1b7fc..617fb31086e 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -727,7 +727,7 @@ int do_migrate_pages(struct mm_struct *mm, return -ENOSYS; } -static struct page *new_vma_page(struct page *page, unsigned long private) +static struct page *new_vma_page(struct page *page, unsigned long private, int **x) { return NULL; } diff --git a/mm/migrate.c b/mm/migrate.c index ba2453f9483..b4979d423d2 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -952,7 +952,8 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, goto out; pm[i].node = node; - } + } else + pm[i].node = 0; /* anything to not match MAX_NUMNODES */ } /* End marker */ pm[nr_pages].node = MAX_NUMNODES; diff --git a/mm/mmap.c b/mm/mmap.c index eea8eefd51a..7b40abd7cba 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -900,17 +900,6 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, int accountable = 1; unsigned long charged = 0, reqprot = prot; - if (file) { - if (is_file_hugepages(file)) - accountable = 0; - - if (!file->f_op || !file->f_op->mmap) - return -ENODEV; - - if ((prot & PROT_EXEC) && - (file->f_vfsmnt->mnt_flags & MNT_NOEXEC)) - return -EPERM; - } /* * Does the application expect PROT_READ to imply PROT_EXEC? * @@ -1000,6 +989,16 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, case MAP_PRIVATE: if (!(file->f_mode & FMODE_READ)) return -EACCES; + if (file->f_vfsmnt->mnt_flags & MNT_NOEXEC) { + if (vm_flags & VM_EXEC) + return -EPERM; + vm_flags &= ~VM_MAYEXEC; + } + if (is_file_hugepages(file)) + accountable = 0; + + if (!file->f_op || !file->f_op->mmap) + return -ENODEV; break; default: @@ -1380,7 +1379,7 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, * Check if the given range is hugepage aligned, and * can be made suitable for hugepages. */ - ret = prepare_hugepage_range(addr, len); + ret = prepare_hugepage_range(addr, len, pgoff); } else { /* * Ensure that a normal request is not falling in a @@ -1881,6 +1880,9 @@ unsigned long do_brk(unsigned long addr, unsigned long len) if ((addr + len) > TASK_SIZE || (addr + len) < addr) return -EINVAL; + if (is_hugepage_only_range(mm, addr, len)) + return -EINVAL; + flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; error = arch_mmap_check(addr, len, flags); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 20f41b082e1..2e3ce3a928b 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -15,6 +15,7 @@ * kernel subsystems and hints as to where to find out what things do. */ +#include <linux/oom.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/swap.h> diff --git a/mm/page-writeback.c b/mm/page-writeback.c index a0f33905744..8d9b19f239c 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -222,7 +222,7 @@ static void balance_dirty_pages(struct address_space *mapping) if (pages_written >= write_chunk) break; /* We've done our duty */ } - blk_congestion_wait(WRITE, HZ/10); + congestion_wait(WRITE, HZ/10); } if (nr_reclaimable + global_page_state(NR_WRITEBACK) @@ -314,7 +314,7 @@ void throttle_vm_writeout(void) if (global_page_state(NR_UNSTABLE_NFS) + global_page_state(NR_WRITEBACK) <= dirty_thresh) break; - blk_congestion_wait(WRITE, HZ/10); + congestion_wait(WRITE, HZ/10); } } @@ -351,7 +351,7 @@ static void background_writeout(unsigned long _min_pages) min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) { /* Wrote less than expected */ - blk_congestion_wait(WRITE, HZ/10); + congestion_wait(WRITE, HZ/10); if (!wbc.encountered_congestion) break; } @@ -422,7 +422,7 @@ static void wb_kupdate(unsigned long arg) writeback_inodes(&wbc); if (wbc.nr_to_write > 0) { if (wbc.encountered_congestion) - blk_congestion_wait(WRITE, HZ/10); + congestion_wait(WRITE, HZ/10); else break; /* All the old data is written */ } @@ -956,15 +956,6 @@ int test_set_page_writeback(struct page *page) EXPORT_SYMBOL(test_set_page_writeback); /* - * Wakes up tasks that are being throttled due to writeback congestion - */ -void writeback_congestion_end(void) -{ - blk_congestion_end(WRITE); -} -EXPORT_SYMBOL(writeback_congestion_end); - -/* * Return true if any of the pages in the mapping are marged with the * passed tag. */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a8c003e7b3d..bf2f6cff1d6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -39,6 +39,7 @@ #include <linux/stop_machine.h> #include <linux/sort.h> #include <linux/pfn.h> +#include <linux/backing-dev.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -495,17 +496,16 @@ static void __free_pages_ok(struct page *page, unsigned int order) int i; int reserved = 0; - arch_free_page(page, order); - if (!PageHighMem(page)) - debug_check_no_locks_freed(page_address(page), - PAGE_SIZE<<order); - for (i = 0 ; i < (1 << order) ; ++i) reserved += free_pages_check(page + i); if (reserved) return; + if (!PageHighMem(page)) + debug_check_no_locks_freed(page_address(page),PAGE_SIZE<<order); + arch_free_page(page, order); kernel_map_pages(page, 1 << order, 0); + local_irq_save(flags); __count_vm_events(PGFREE, 1 << order); free_one_page(page_zone(page), page, order); @@ -781,13 +781,14 @@ static void fastcall free_hot_cold_page(struct page *page, int cold) struct per_cpu_pages *pcp; unsigned long flags; - arch_free_page(page, 0); - if (PageAnon(page)) page->mapping = NULL; if (free_pages_check(page)) return; + if (!PageHighMem(page)) + debug_check_no_locks_freed(page_address(page), PAGE_SIZE); + arch_free_page(page, 0); kernel_map_pages(page, 1, 0); pcp = &zone_pcp(zone, get_cpu())->pcp[cold]; @@ -852,7 +853,7 @@ again: pcp = &zone_pcp(zone, cpu)->pcp[cold]; local_irq_save(flags); if (!pcp->count) { - pcp->count += rmqueue_bulk(zone, 0, + pcp->count = rmqueue_bulk(zone, 0, pcp->batch, &pcp->list); if (unlikely(!pcp->count)) goto failed; @@ -1050,7 +1051,7 @@ nofail_alloc: if (page) goto got_pg; if (gfp_mask & __GFP_NOFAIL) { - blk_congestion_wait(WRITE, HZ/50); + congestion_wait(WRITE, HZ/50); goto nofail_alloc; } } @@ -1113,7 +1114,7 @@ rebalance: do_retry = 1; } if (do_retry) { - blk_congestion_wait(WRITE, HZ/50); + congestion_wait(WRITE, HZ/50); goto rebalance; } @@ -1688,6 +1689,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, for (pfn = start_pfn; pfn < end_pfn; pfn++) { if (!early_pfn_valid(pfn)) continue; + if (!early_pfn_in_nid(pfn, nid)) + continue; page = pfn_to_page(pfn); set_page_links(page, zone, nid, pfn); init_page_count(page); @@ -2258,7 +2261,7 @@ unsigned long __init __absent_pages_in_range(int nid, /* Account for ranges past physical memory on this node */ if (range_end_pfn > prev_end_pfn) - hole_pages = range_end_pfn - + hole_pages += range_end_pfn - max(range_start_pfn, prev_end_pfn); return hole_pages; @@ -2294,19 +2297,6 @@ unsigned long __init zone_absent_pages_in_node(int nid, return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); } -/* Return the zone index a PFN is in */ -int memmap_zone_idx(struct page *lmem_map) -{ - int i; - unsigned long phys_addr = virt_to_phys(lmem_map); - unsigned long pfn = phys_addr >> PAGE_SHIFT; - - for (i = 0; i < MAX_NR_ZONES; i++) - if (pfn < arch_zone_highest_possible_pfn[i]) - break; - - return i; -} #else static inline unsigned long zone_spanned_pages_in_node(int nid, unsigned long zone_type, @@ -2325,10 +2315,6 @@ static inline unsigned long zone_absent_pages_in_node(int nid, return zholes_size[zone_type]; } -static inline int memmap_zone_idx(struct page *lmem_map) -{ - return MAX_NR_ZONES; -} #endif static void __init calculate_node_totalpages(struct pglist_data *pgdat, @@ -2421,7 +2407,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, zone->zone_pgdat = pgdat; zone->free_pages = 0; - zone->temp_priority = zone->prev_priority = DEF_PRIORITY; + zone->prev_priority = DEF_PRIORITY; zone_pcp_init(zone); INIT_LIST_HEAD(&zone->active_list); @@ -3136,3 +3122,19 @@ unsigned long page_to_pfn(struct page *page) EXPORT_SYMBOL(pfn_to_page); EXPORT_SYMBOL(page_to_pfn); #endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */ + +#if MAX_NUMNODES > 1 +/* + * Find the highest possible node id. + */ +int highest_possible_node_id(void) +{ + unsigned int node; + unsigned int highest = 0; + + for_each_node_mask(node, node_possible_map) + highest = node; + return highest; +} +EXPORT_SYMBOL(highest_possible_node_id); +#endif diff --git a/mm/readahead.c b/mm/readahead.c index 1ba736ac036..23cb61a01c6 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -173,6 +173,8 @@ static int read_pages(struct address_space *mapping, struct file *filp, if (mapping->a_ops->readpages) { ret = mapping->a_ops->readpages(filp, mapping, pages, nr_pages); + /* Clean up the remaining pages */ + put_pages_list(pages); goto out; } diff --git a/mm/rmap.c b/mm/rmap.c index e2155d791d9..d8a842a586d 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -21,27 +21,21 @@ * Lock ordering in mm: * * inode->i_mutex (while writing or truncating, not reading or faulting) - * inode->i_alloc_sem - * - * When a page fault occurs in writing from user to file, down_read - * of mmap_sem nests within i_mutex; in sys_msync, i_mutex nests within - * down_read of mmap_sem; i_mutex and down_write of mmap_sem are never - * taken together; in truncation, i_mutex is taken outermost. - * - * mm->mmap_sem - * page->flags PG_locked (lock_page) - * mapping->i_mmap_lock - * anon_vma->lock - * mm->page_table_lock or pte_lock - * zone->lru_lock (in mark_page_accessed, isolate_lru_page) - * swap_lock (in swap_duplicate, swap_info_get) - * mmlist_lock (in mmput, drain_mmlist and others) - * mapping->private_lock (in __set_page_dirty_buffers) - * inode_lock (in set_page_dirty's __mark_inode_dirty) - * sb_lock (within inode_lock in fs/fs-writeback.c) - * mapping->tree_lock (widely used, in set_page_dirty, - * in arch-dependent flush_dcache_mmap_lock, - * within inode_lock in __sync_single_inode) + * inode->i_alloc_sem (vmtruncate_range) + * mm->mmap_sem + * page->flags PG_locked (lock_page) + * mapping->i_mmap_lock + * anon_vma->lock + * mm->page_table_lock or pte_lock + * zone->lru_lock (in mark_page_accessed, isolate_lru_page) + * swap_lock (in swap_duplicate, swap_info_get) + * mmlist_lock (in mmput, drain_mmlist and others) + * mapping->private_lock (in __set_page_dirty_buffers) + * inode_lock (in set_page_dirty's __mark_inode_dirty) + * sb_lock (within inode_lock in fs/fs-writeback.c) + * mapping->tree_lock (widely used, in set_page_dirty, + * in arch-dependent flush_dcache_mmap_lock, + * within inode_lock in __sync_single_inode) */ #include <linux/mm.h> @@ -576,15 +570,14 @@ void page_add_file_rmap(struct page *page) void page_remove_rmap(struct page *page) { if (atomic_add_negative(-1, &page->_mapcount)) { -#ifdef CONFIG_DEBUG_VM if (unlikely(page_mapcount(page) < 0)) { printk (KERN_EMERG "Eeek! page_mapcount(page) went negative! (%d)\n", page_mapcount(page)); printk (KERN_EMERG " page->flags = %lx\n", page->flags); printk (KERN_EMERG " page->count = %x\n", page_count(page)); printk (KERN_EMERG " page->mapping = %p\n", page->mapping); + BUG(); } -#endif - BUG_ON(page_mapcount(page) < 0); + /* * It would be tidy to reset the PageAnon mapping here, * but that might overwrite a racing page_add_anon_rmap diff --git a/mm/shmem.c b/mm/shmem.c index bb8ca7ef709..4959535fc14 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -48,6 +48,7 @@ #include <linux/ctype.h> #include <linux/migrate.h> #include <linux/highmem.h> +#include <linux/backing-dev.h> #include <asm/uaccess.h> #include <asm/div64.h> @@ -1131,7 +1132,7 @@ repeat: page_cache_release(swappage); if (error == -ENOMEM) { /* let kswapd refresh zone for GFP_ATOMICs */ - blk_congestion_wait(WRITE, HZ/50); + congestion_wait(WRITE, HZ/50); } goto repeat; } @@ -1362,6 +1363,7 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) inode->i_mapping->a_ops = &shmem_aops; inode->i_mapping->backing_dev_info = &shmem_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; + inode->i_generation = get_seconds(); info = SHMEM_I(inode); memset(info, 0, (char *)inode - (char *)info); spin_lock_init(&info->lock); @@ -1956,6 +1958,85 @@ static struct xattr_handler *shmem_xattr_handlers[] = { }; #endif +static struct dentry *shmem_get_parent(struct dentry *child) +{ + return ERR_PTR(-ESTALE); +} + +static int shmem_match(struct inode *ino, void *vfh) +{ + __u32 *fh = vfh; + __u64 inum = fh[2]; + inum = (inum << 32) | fh[1]; + return ino->i_ino == inum && fh[0] == ino->i_generation; +} + +static struct dentry *shmem_get_dentry(struct super_block *sb, void *vfh) +{ + struct dentry *de = NULL; + struct inode *inode; + __u32 *fh = vfh; + __u64 inum = fh[2]; + inum = (inum << 32) | fh[1]; + + inode = ilookup5(sb, (unsigned long)(inum+fh[0]), shmem_match, vfh); + if (inode) { + de = d_find_alias(inode); + iput(inode); + } + + return de? de: ERR_PTR(-ESTALE); +} + +static struct dentry *shmem_decode_fh(struct super_block *sb, __u32 *fh, + int len, int type, + int (*acceptable)(void *context, struct dentry *de), + void *context) +{ + if (len < 3) + return ERR_PTR(-ESTALE); + + return sb->s_export_op->find_exported_dentry(sb, fh, NULL, acceptable, + context); +} + +static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len, + int connectable) +{ + struct inode *inode = dentry->d_inode; + + if (*len < 3) + return 255; + + if (hlist_unhashed(&inode->i_hash)) { + /* Unfortunately insert_inode_hash is not idempotent, + * so as we hash inodes here rather than at creation + * time, we need a lock to ensure we only try + * to do it once + */ + static DEFINE_SPINLOCK(lock); + spin_lock(&lock); + if (hlist_unhashed(&inode->i_hash)) + __insert_inode_hash(inode, + inode->i_ino + inode->i_generation); + spin_unlock(&lock); + } + + fh[0] = inode->i_generation; + fh[1] = inode->i_ino; + fh[2] = ((__u64)inode->i_ino) >> 32; + + *len = 3; + return 1; +} + +static struct export_operations shmem_export_ops = { + .get_parent = shmem_get_parent, + .get_dentry = shmem_get_dentry, + .encode_fh = shmem_encode_fh, + .decode_fh = shmem_decode_fh, +}; + static int shmem_parse_options(char *options, int *mode, uid_t *uid, gid_t *gid, unsigned long *blocks, unsigned long *inodes, int *policy, nodemask_t *policy_nodes) @@ -2128,6 +2209,7 @@ static int shmem_fill_super(struct super_block *sb, &inodes, &policy, &policy_nodes)) return -EINVAL; } + sb->s_export_op = &shmem_export_ops; #else sb->s_flags |= MS_NOUSER; #endif diff --git a/mm/shmem_acl.c b/mm/shmem_acl.c index c946bf46871..f5664c5b9eb 100644 --- a/mm/shmem_acl.c +++ b/mm/shmem_acl.c @@ -35,7 +35,7 @@ shmem_get_acl(struct inode *inode, int type) } /** - * shmem_get_acl - generic_acl_operations->setacl() operation + * shmem_set_acl - generic_acl_operations->setacl() operation */ static void shmem_set_acl(struct inode *inode, int type, struct posix_acl *acl) diff --git a/mm/slab.c b/mm/slab.c index 266449d604b..3c4a7e34edd 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -883,7 +883,7 @@ static void init_reap_node(int cpu) if (node == MAX_NUMNODES) node = first_node(node_online_map); - __get_cpu_var(reap_node) = node; + per_cpu(reap_node, cpu) = node; } static void next_reap_node(void) @@ -3152,12 +3152,15 @@ void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) struct zone **z; void *obj = NULL; - for (z = zonelist->zones; *z && !obj; z++) + for (z = zonelist->zones; *z && !obj; z++) { + int nid = zone_to_nid(*z); + if (zone_idx(*z) <= ZONE_NORMAL && - cpuset_zone_allowed(*z, flags)) + cpuset_zone_allowed(*z, flags) && + cache->nodelists[nid]) obj = __cache_alloc_node(cache, - flags | __GFP_THISNODE, - zone_to_nid(*z)); + flags | __GFP_THISNODE, nid); + } return obj; } diff --git a/mm/sparse.c b/mm/sparse.c index 86c52ab8087..b3c82ba3001 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -211,7 +211,7 @@ static struct page *__kmalloc_section_memmap(unsigned long nr_pages) struct page *page, *ret; unsigned long memmap_size = sizeof(struct page) * nr_pages; - page = alloc_pages(GFP_KERNEL, get_order(memmap_size)); + page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size)); if (page) goto got_map_page; diff --git a/mm/truncate.c b/mm/truncate.c index f4edbc179d1..e07b1e682c3 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -96,7 +96,6 @@ invalidate_complete_page(struct address_space *mapping, struct page *page) return 0; ret = remove_mapping(mapping, page); - ClearPageUptodate(page); return ret; } @@ -302,7 +301,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page) if (page->mapping != mapping) return 0; - if (PagePrivate(page) && !try_to_release_page(page, 0)) + if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL)) return 0; write_lock_irq(&mapping->tree_lock); @@ -396,6 +395,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, pagevec_release(&pvec); cond_resched(); } + WARN_ON_ONCE(ret); return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 750ab6ed13f..86897ee792d 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -160,13 +160,15 @@ int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages) return err; } -struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags, - unsigned long start, unsigned long end, int node) +static struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags, + unsigned long start, unsigned long end, + int node, gfp_t gfp_mask) { struct vm_struct **p, *tmp, *area; unsigned long align = 1; unsigned long addr; + BUG_ON(in_interrupt()); if (flags & VM_IOREMAP) { int bit = fls(size); @@ -179,16 +181,13 @@ struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags, } addr = ALIGN(start, align); size = PAGE_ALIGN(size); + if (unlikely(!size)) + return NULL; - area = kmalloc_node(sizeof(*area), GFP_KERNEL, node); + area = kmalloc_node(sizeof(*area), gfp_mask & GFP_LEVEL_MASK, node); if (unlikely(!area)) return NULL; - if (unlikely(!size)) { - kfree (area); - return NULL; - } - /* * We always allocate a guard page. */ @@ -236,7 +235,7 @@ out: struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags, unsigned long start, unsigned long end) { - return __get_vm_area_node(size, flags, start, end, -1); + return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL); } /** @@ -253,9 +252,11 @@ struct vm_struct *get_vm_area(unsigned long size, unsigned long flags) return __get_vm_area(size, flags, VMALLOC_START, VMALLOC_END); } -struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, int node) +struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, + int node, gfp_t gfp_mask) { - return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node); + return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node, + gfp_mask); } /* Caller must hold vmlist_lock */ @@ -428,8 +429,11 @@ void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, if (array_size > PAGE_SIZE) { pages = __vmalloc_node(array_size, gfp_mask, PAGE_KERNEL, node); area->flags |= VM_VPAGES; - } else - pages = kmalloc_node(array_size, (gfp_mask & ~__GFP_HIGHMEM), node); + } else { + pages = kmalloc_node(array_size, + (gfp_mask & ~(__GFP_HIGHMEM | __GFP_ZERO)), + node); + } area->pages = pages; if (!area->pages) { remove_vm_area(area->addr); @@ -484,7 +488,7 @@ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot, if (!size || (size >> PAGE_SHIFT) > num_physpages) return NULL; - area = get_vm_area_node(size, VM_ALLOC, node); + area = get_vm_area_node(size, VM_ALLOC, node, gfp_mask); if (!area) return NULL; @@ -525,11 +529,12 @@ void *vmalloc_user(unsigned long size) 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); - + if (ret) { + write_lock(&vmlist_lock); + area = __find_vm_area(ret); + area->flags |= VM_USERMAP; + write_unlock(&vmlist_lock); + } return ret; } EXPORT_SYMBOL(vmalloc_user); @@ -598,11 +603,12 @@ void *vmalloc_32_user(unsigned long size) 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); - + if (ret) { + write_lock(&vmlist_lock); + area = __find_vm_area(ret); + area->flags |= VM_USERMAP; + write_unlock(&vmlist_lock); + } return ret; } EXPORT_SYMBOL(vmalloc_32_user); diff --git a/mm/vmscan.c b/mm/vmscan.c index eca70310adb..518540a4a2a 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -378,6 +378,12 @@ static pageout_t pageout(struct page *page, struct address_space *mapping) return PAGE_CLEAN; } +/* + * Attempt to detach a locked page from its ->mapping. If it is dirty or if + * someone else has a ref on the page, abort and return 0. If it was + * successfully detached, return 1. Assumes the caller has a single ref on + * this page. + */ int remove_mapping(struct address_space *mapping, struct page *page) { BUG_ON(!PageLocked(page)); @@ -717,6 +723,20 @@ done: return nr_reclaimed; } +/* + * We are about to scan this zone at a certain priority level. If that priority + * level is smaller (ie: more urgent) than the previous priority, then note + * that priority level within the zone. This is done so that when the next + * process comes in to scan this zone, it will immediately start out at this + * priority level rather than having to build up its own scanning priority. + * Here, this priority affects only the reclaim-mapped threshold. + */ +static inline void note_zone_scanning_priority(struct zone *zone, int priority) +{ + if (priority < zone->prev_priority) + zone->prev_priority = priority; +} + static inline int zone_is_near_oom(struct zone *zone) { return zone->pages_scanned >= (zone->nr_active + zone->nr_inactive)*3; @@ -740,7 +760,7 @@ static inline int zone_is_near_oom(struct zone *zone) * But we had to alter page->flags anyway. */ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, - struct scan_control *sc) + struct scan_control *sc, int priority) { unsigned long pgmoved; int pgdeactivate = 0; @@ -764,7 +784,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone, * `distress' is a measure of how much trouble we're having * reclaiming pages. 0 -> no problems. 100 -> great trouble. */ - distress = 100 >> zone->prev_priority; + distress = 100 >> min(zone->prev_priority, priority); /* * The point of this algorithm is to decide when to start @@ -916,7 +936,7 @@ static unsigned long shrink_zone(int priority, struct zone *zone, nr_to_scan = min(nr_active, (unsigned long)sc->swap_cluster_max); nr_active -= nr_to_scan; - shrink_active_list(nr_to_scan, zone, sc); + shrink_active_list(nr_to_scan, zone, sc, priority); } if (nr_inactive) { @@ -966,9 +986,7 @@ static unsigned long shrink_zones(int priority, struct zone **zones, if (!cpuset_zone_allowed(zone, __GFP_HARDWALL)) continue; - zone->temp_priority = priority; - if (zone->prev_priority > priority) - zone->prev_priority = priority; + note_zone_scanning_priority(zone, priority); if (zone->all_unreclaimable && priority != DEF_PRIORITY) continue; /* Let kswapd poll it */ @@ -1018,7 +1036,6 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask) if (!cpuset_zone_allowed(zone, __GFP_HARDWALL)) continue; - zone->temp_priority = DEF_PRIORITY; lru_pages += zone->nr_active + zone->nr_inactive; } @@ -1053,19 +1070,28 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask) /* Take a nap, wait for some writeback to complete */ if (sc.nr_scanned && priority < DEF_PRIORITY - 2) - blk_congestion_wait(WRITE, HZ/10); + congestion_wait(WRITE, HZ/10); } /* top priority shrink_caches still had more to do? don't OOM, then */ if (!sc.all_unreclaimable) ret = 1; out: + /* + * Now that we've scanned all the zones at this priority level, note + * that level within the zone so that the next thread which performs + * scanning of this zone will immediately start out at this priority + * level. This affects only the decision whether or not to bring + * mapped pages onto the inactive list. + */ + if (priority < 0) + priority = 0; for (i = 0; zones[i] != 0; i++) { struct zone *zone = zones[i]; if (!cpuset_zone_allowed(zone, __GFP_HARDWALL)) continue; - zone->prev_priority = zone->temp_priority; + zone->prev_priority = priority; } return ret; } @@ -1105,6 +1131,11 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order) .swap_cluster_max = SWAP_CLUSTER_MAX, .swappiness = vm_swappiness, }; + /* + * temp_priority is used to remember the scanning priority at which + * this zone was successfully refilled to free_pages == pages_high. + */ + int temp_priority[MAX_NR_ZONES]; loop_again: total_scanned = 0; @@ -1112,11 +1143,8 @@ loop_again: sc.may_writepage = !laptop_mode; count_vm_event(PAGEOUTRUN); - for (i = 0; i < pgdat->nr_zones; i++) { - struct zone *zone = pgdat->node_zones + i; - - zone->temp_priority = DEF_PRIORITY; - } + for (i = 0; i < pgdat->nr_zones; i++) + temp_priority[i] = DEF_PRIORITY; for (priority = DEF_PRIORITY; priority >= 0; priority--) { int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ @@ -1177,10 +1205,9 @@ scan: 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; + temp_priority[i] = priority; sc.nr_scanned = 0; + note_zone_scanning_priority(zone, priority); nr_reclaimed += shrink_zone(priority, zone, &sc); reclaim_state->reclaimed_slab = 0; nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL, @@ -1208,7 +1235,7 @@ scan: * another pass across the zones. */ if (total_scanned && priority < DEF_PRIORITY - 2) - blk_congestion_wait(WRITE, HZ/10); + congestion_wait(WRITE, HZ/10); /* * We do this so kswapd doesn't build up large priorities for @@ -1220,10 +1247,15 @@ scan: break; } out: + /* + * Note within each zone the priority level at which this zone was + * brought into a happy state. So that the next thread which scans this + * zone will start out at that priority level. + */ for (i = 0; i < pgdat->nr_zones; i++) { struct zone *zone = pgdat->node_zones + i; - zone->prev_priority = zone->temp_priority; + zone->prev_priority = temp_priority[i]; } if (!all_zones_ok) { cond_resched(); @@ -1352,7 +1384,7 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int pass, 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); + shrink_active_list(nr_to_scan, zone, sc, prio); } } @@ -1452,7 +1484,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages) goto out; if (sc.nr_scanned && prio < DEF_PRIORITY - 2) - blk_congestion_wait(WRITE, HZ / 10); + congestion_wait(WRITE, HZ / 10); } lru_pages = 0; @@ -1608,6 +1640,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) */ priority = ZONE_RECLAIM_PRIORITY; do { + note_zone_scanning_priority(zone, priority); nr_reclaimed += shrink_zone(priority, zone, &sc); priority--; } while (priority >= 0 && nr_reclaimed < nr_pages); diff --git a/mm/vmstat.c b/mm/vmstat.c index 45b124e012f..8614e8f6743 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -587,11 +587,9 @@ static int zoneinfo_show(struct seq_file *m, void *arg) seq_printf(m, "\n all_unreclaimable: %u" "\n prev_priority: %i" - "\n temp_priority: %i" "\n start_pfn: %lu", zone->all_unreclaimable, zone->prev_priority, - zone->temp_priority, zone->zone_start_pfn); spin_unlock_irqrestore(&zone->lock, flags); seq_putc(m, '\n'); |