diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 11 | ||||
-rw-r--r-- | mm/Makefile | 7 | ||||
-rw-r--r-- | mm/allocpercpu.c | 9 | ||||
-rw-r--r-- | mm/backing-dev.c | 69 | ||||
-rw-r--r-- | mm/bootmem.c | 6 | ||||
-rw-r--r-- | mm/bounce.c | 302 | ||||
-rw-r--r-- | mm/fadvise.c | 2 | ||||
-rw-r--r-- | mm/filemap.c | 318 | ||||
-rw-r--r-- | mm/filemap.h | 1 | ||||
-rw-r--r-- | mm/filemap_xip.c | 2 | ||||
-rw-r--r-- | mm/fremap.c | 4 | ||||
-rw-r--r-- | mm/highmem.c | 281 | ||||
-rw-r--r-- | mm/hugetlb.c | 55 | ||||
-rw-r--r-- | mm/memory.c | 183 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 72 | ||||
-rw-r--r-- | mm/mempolicy.c | 19 | ||||
-rw-r--r-- | mm/migrate.c | 26 | ||||
-rw-r--r-- | mm/mlock.c | 2 | ||||
-rw-r--r-- | mm/mmap.c | 38 | ||||
-rw-r--r-- | mm/mmzone.c | 5 | ||||
-rw-r--r-- | mm/mprotect.c | 2 | ||||
-rw-r--r-- | mm/mremap.c | 2 | ||||
-rw-r--r-- | mm/nommu.c | 280 | ||||
-rw-r--r-- | mm/oom_kill.c | 95 | ||||
-rw-r--r-- | mm/page-writeback.c | 268 | ||||
-rw-r--r-- | mm/page_alloc.c | 1156 | ||||
-rw-r--r-- | mm/page_io.c | 45 | ||||
-rw-r--r-- | mm/pdflush.c | 1 | ||||
-rw-r--r-- | mm/readahead.c | 15 | ||||
-rw-r--r-- | mm/rmap.c | 41 | ||||
-rw-r--r-- | mm/shmem.c | 231 | ||||
-rw-r--r-- | mm/shmem_acl.c | 197 | ||||
-rw-r--r-- | mm/slab.c | 546 | ||||
-rw-r--r-- | mm/slob.c | 3 | ||||
-rw-r--r-- | mm/sparse.c | 25 | ||||
-rw-r--r-- | mm/swap.c | 10 | ||||
-rw-r--r-- | mm/swapfile.c | 103 | ||||
-rw-r--r-- | mm/thrash.c | 116 | ||||
-rw-r--r-- | mm/tiny-shmem.c | 4 | ||||
-rw-r--r-- | mm/truncate.c | 89 | ||||
-rw-r--r-- | mm/util.c | 22 | ||||
-rw-r--r-- | mm/vmalloc.c | 90 | ||||
-rw-r--r-- | mm/vmscan.c | 118 | ||||
-rw-r--r-- | mm/vmstat.c | 28 |
44 files changed, 3533 insertions, 1366 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 8f5b45615f7..db7c55de92c 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -92,7 +92,7 @@ config HAVE_MEMORY_PRESENT # # SPARSEMEM_EXTREME (which is the default) does some bootmem -# allocations when memory_present() is called. If this can not +# allocations when memory_present() is called. If this cannot # be done on your architecture, select this option. However, # statically allocating the mem_section[] array can potentially # consume vast quantities of .bss, so be careful. @@ -104,7 +104,7 @@ config SPARSEMEM_STATIC def_bool n # -# Architectecture platforms which require a two level mem_section in SPARSEMEM +# Architecture platforms which require a two level mem_section in SPARSEMEM # must select this option. This is usually for architecture platforms with # an extremely sparse physical address space. # @@ -115,12 +115,17 @@ config SPARSEMEM_EXTREME # eventually, we can have this option just 'select SPARSEMEM' config MEMORY_HOTPLUG bool "Allow for memory hot-add" - depends on SPARSEMEM && HOTPLUG && !SOFTWARE_SUSPEND && ARCH_ENABLE_MEMORY_HOTPLUG + depends on SPARSEMEM || X86_64_ACPI_NUMA + depends on HOTPLUG && !SOFTWARE_SUSPEND && ARCH_ENABLE_MEMORY_HOTPLUG depends on (IA64 || X86 || PPC64) comment "Memory hotplug is currently incompatible with Software Suspend" depends on SPARSEMEM && HOTPLUG && SOFTWARE_SUSPEND +config MEMORY_HOTPLUG_SPARSE + def_bool y + depends on SPARSEMEM && MEMORY_HOTPLUG + # Heavily threaded applications may benefit from splitting the mm-wide # page_table_lock, so that faults on different parts of the user address # space can be handled with less contention: split it at this NR_CPUS. diff --git a/mm/Makefile b/mm/Makefile index 60c56c0b5e1..f3c077eb0b8 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -10,13 +10,18 @@ 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)$(CONFIG_BLOCK),yy) +obj-y += bounce.o +endif obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o thrash.o obj-$(CONFIG_HUGETLBFS) += hugetlb.o obj-$(CONFIG_NUMA) += mempolicy.o obj-$(CONFIG_SPARSEMEM) += sparse.o obj-$(CONFIG_SHMEM) += shmem.o +obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o obj-$(CONFIG_SLOB) += slob.o obj-$(CONFIG_SLAB) += slab.o diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c index eaa9abeea53..b2486cf887a 100644 --- a/mm/allocpercpu.c +++ b/mm/allocpercpu.c @@ -17,10 +17,9 @@ void percpu_depopulate(void *__pdata, int cpu) { struct percpu_data *pdata = __percpu_disguise(__pdata); - if (pdata->ptrs[cpu]) { - kfree(pdata->ptrs[cpu]); - pdata->ptrs[cpu] = NULL; - } + + kfree(pdata->ptrs[cpu]); + pdata->ptrs[cpu] = NULL; } EXPORT_SYMBOL_GPL(percpu_depopulate); @@ -123,6 +122,8 @@ EXPORT_SYMBOL_GPL(__percpu_alloc_mask); */ void percpu_free(void *__pdata) { + if (unlikely(!__pdata)) + return; __percpu_depopulate_mask(__pdata, &cpu_possible_map); kfree(__percpu_disguise(__pdata)); } 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/bootmem.c b/mm/bootmem.c index d53112fcb40..00a96970b23 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -27,8 +27,6 @@ unsigned long max_low_pfn; unsigned long min_low_pfn; unsigned long max_pfn; -EXPORT_UNUSED_SYMBOL(max_pfn); /* June 2006 */ - static LIST_HEAD(bdata_list); #ifdef CONFIG_CRASH_DUMP /* @@ -196,6 +194,10 @@ __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size, if (limit && bdata->node_boot_start >= limit) return NULL; + /* on nodes without memory - bootmem_map is NULL */ + if (!bdata->node_bootmem_map) + return NULL; + end_pfn = bdata->node_low_pfn; limit = PFN_DOWN(limit); if (limit && end_pfn > limit) diff --git a/mm/bounce.c b/mm/bounce.c new file mode 100644 index 00000000000..e4b62d2a402 --- /dev/null +++ b/mm/bounce.c @@ -0,0 +1,302 @@ +/* bounce buffer handling for block devices + * + * - Split from highmem.c + */ + +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/swap.h> +#include <linux/bio.h> +#include <linux/pagemap.h> +#include <linux/mempool.h> +#include <linux/blkdev.h> +#include <linux/init.h> +#include <linux/hash.h> +#include <linux/highmem.h> +#include <linux/blktrace_api.h> +#include <asm/tlbflush.h> + +#define POOL_SIZE 64 +#define ISA_POOL_SIZE 16 + +static mempool_t *page_pool, *isa_page_pool; + +#ifdef CONFIG_HIGHMEM +static __init int init_emergency_pool(void) +{ + struct sysinfo i; + si_meminfo(&i); + si_swapinfo(&i); + + if (!i.totalhigh) + return 0; + + page_pool = mempool_create_page_pool(POOL_SIZE, 0); + BUG_ON(!page_pool); + printk("highmem bounce pool size: %d pages\n", POOL_SIZE); + + return 0; +} + +__initcall(init_emergency_pool); + +/* + * highmem version, map in to vec + */ +static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom) +{ + unsigned long flags; + unsigned char *vto; + + local_irq_save(flags); + vto = kmap_atomic(to->bv_page, KM_BOUNCE_READ); + memcpy(vto + to->bv_offset, vfrom, to->bv_len); + kunmap_atomic(vto, KM_BOUNCE_READ); + local_irq_restore(flags); +} + +#else /* CONFIG_HIGHMEM */ + +#define bounce_copy_vec(to, vfrom) \ + memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len) + +#endif /* CONFIG_HIGHMEM */ + +/* + * allocate pages in the DMA region for the ISA pool + */ +static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data) +{ + return mempool_alloc_pages(gfp_mask | GFP_DMA, data); +} + +/* + * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA + * as the max address, so check if the pool has already been created. + */ +int init_emergency_isa_pool(void) +{ + if (isa_page_pool) + return 0; + + isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa, + mempool_free_pages, (void *) 0); + BUG_ON(!isa_page_pool); + + printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE); + return 0; +} + +/* + * Simple bounce buffer support for highmem pages. Depending on the + * queue gfp mask set, *to may or may not be a highmem page. kmap it + * always, it will do the Right Thing + */ +static void copy_to_high_bio_irq(struct bio *to, struct bio *from) +{ + unsigned char *vfrom; + struct bio_vec *tovec, *fromvec; + int i; + + __bio_for_each_segment(tovec, to, i, 0) { + fromvec = from->bi_io_vec + i; + + /* + * not bounced + */ + if (tovec->bv_page == fromvec->bv_page) + continue; + + /* + * fromvec->bv_offset and fromvec->bv_len might have been + * modified by the block layer, so use the original copy, + * bounce_copy_vec already uses tovec->bv_len + */ + vfrom = page_address(fromvec->bv_page) + tovec->bv_offset; + + flush_dcache_page(tovec->bv_page); + bounce_copy_vec(tovec, vfrom); + } +} + +static void bounce_end_io(struct bio *bio, mempool_t *pool, int err) +{ + struct bio *bio_orig = bio->bi_private; + struct bio_vec *bvec, *org_vec; + int i; + + if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags)) + set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags); + + /* + * free up bounce indirect pages used + */ + __bio_for_each_segment(bvec, bio, i, 0) { + org_vec = bio_orig->bi_io_vec + i; + if (bvec->bv_page == org_vec->bv_page) + continue; + + dec_zone_page_state(bvec->bv_page, NR_BOUNCE); + mempool_free(bvec->bv_page, pool); + } + + bio_endio(bio_orig, bio_orig->bi_size, err); + bio_put(bio); +} + +static int bounce_end_io_write(struct bio *bio, unsigned int bytes_done, int err) +{ + if (bio->bi_size) + return 1; + + bounce_end_io(bio, page_pool, err); + return 0; +} + +static int bounce_end_io_write_isa(struct bio *bio, unsigned int bytes_done, int err) +{ + if (bio->bi_size) + return 1; + + bounce_end_io(bio, isa_page_pool, err); + return 0; +} + +static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err) +{ + struct bio *bio_orig = bio->bi_private; + + if (test_bit(BIO_UPTODATE, &bio->bi_flags)) + copy_to_high_bio_irq(bio_orig, bio); + + bounce_end_io(bio, pool, err); +} + +static int bounce_end_io_read(struct bio *bio, unsigned int bytes_done, int err) +{ + if (bio->bi_size) + return 1; + + __bounce_end_io_read(bio, page_pool, err); + return 0; +} + +static int bounce_end_io_read_isa(struct bio *bio, unsigned int bytes_done, int err) +{ + if (bio->bi_size) + return 1; + + __bounce_end_io_read(bio, isa_page_pool, err); + return 0; +} + +static void __blk_queue_bounce(request_queue_t *q, struct bio **bio_orig, + mempool_t *pool) +{ + struct page *page; + struct bio *bio = NULL; + int i, rw = bio_data_dir(*bio_orig); + struct bio_vec *to, *from; + + bio_for_each_segment(from, *bio_orig, i) { + page = from->bv_page; + + /* + * is destination page below bounce pfn? + */ + if (page_to_pfn(page) < q->bounce_pfn) + continue; + + /* + * irk, bounce it + */ + if (!bio) + bio = bio_alloc(GFP_NOIO, (*bio_orig)->bi_vcnt); + + to = bio->bi_io_vec + i; + + to->bv_page = mempool_alloc(pool, q->bounce_gfp); + to->bv_len = from->bv_len; + to->bv_offset = from->bv_offset; + inc_zone_page_state(to->bv_page, NR_BOUNCE); + + if (rw == WRITE) { + char *vto, *vfrom; + + flush_dcache_page(from->bv_page); + vto = page_address(to->bv_page) + to->bv_offset; + vfrom = kmap(from->bv_page) + from->bv_offset; + memcpy(vto, vfrom, to->bv_len); + kunmap(from->bv_page); + } + } + + /* + * no pages bounced + */ + if (!bio) + return; + + /* + * at least one page was bounced, fill in possible non-highmem + * pages + */ + __bio_for_each_segment(from, *bio_orig, i, 0) { + to = bio_iovec_idx(bio, i); + if (!to->bv_page) { + to->bv_page = from->bv_page; + to->bv_len = from->bv_len; + to->bv_offset = from->bv_offset; + } + } + + bio->bi_bdev = (*bio_orig)->bi_bdev; + bio->bi_flags |= (1 << BIO_BOUNCED); + bio->bi_sector = (*bio_orig)->bi_sector; + bio->bi_rw = (*bio_orig)->bi_rw; + + bio->bi_vcnt = (*bio_orig)->bi_vcnt; + bio->bi_idx = (*bio_orig)->bi_idx; + bio->bi_size = (*bio_orig)->bi_size; + + if (pool == page_pool) { + bio->bi_end_io = bounce_end_io_write; + if (rw == READ) + bio->bi_end_io = bounce_end_io_read; + } else { + bio->bi_end_io = bounce_end_io_write_isa; + if (rw == READ) + bio->bi_end_io = bounce_end_io_read_isa; + } + + bio->bi_private = *bio_orig; + *bio_orig = bio; +} + +void blk_queue_bounce(request_queue_t *q, struct bio **bio_orig) +{ + mempool_t *pool; + + /* + * for non-isa bounce case, just check if the bounce pfn is equal + * to or bigger than the highest pfn in the system -- in that case, + * don't waste time iterating over bio segments + */ + if (!(q->bounce_gfp & GFP_DMA)) { + if (q->bounce_pfn >= blk_max_pfn) + return; + pool = page_pool; + } else { + BUG_ON(!isa_page_pool); + pool = isa_page_pool; + } + + blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE); + + /* + * slow path + */ + __blk_queue_bounce(q, bio_orig, pool); +} + +EXPORT_SYMBOL(blk_queue_bounce); diff --git a/mm/fadvise.c b/mm/fadvise.c index 168c78a121b..0df4c899e97 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -38,7 +38,7 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice) if (!file) return -EBADF; - if (S_ISFIFO(file->f_dentry->d_inode->i_mode)) { + if (S_ISFIFO(file->f_path.dentry->d_inode->i_mode)) { ret = -ESPIPE; goto out; } diff --git a/mm/filemap.c b/mm/filemap.c index afcdc72b5e9..8332c77b1bd 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; } @@ -1139,23 +1127,24 @@ success: } /** - * __generic_file_aio_read - generic filesystem read routine + * 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 + * @pos: current file position * * This is the "read()" routine for all filesystems * that can use the page cache directly. */ ssize_t -__generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *filp = iocb->ki_filp; ssize_t retval; unsigned long seg; size_t count; + loff_t *ppos = &iocb->ki_pos; count = 0; for (seg = 0; seg < nr_segs; seg++) { @@ -1179,7 +1168,7 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (filp->f_flags & O_DIRECT) { - loff_t pos = *ppos, size; + loff_t size; struct address_space *mapping; struct inode *inode; @@ -1192,13 +1181,13 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, if (pos < size) { retval = generic_file_direct_IO(READ, iocb, iov, pos, nr_segs); - if (retval > 0 && !is_sync_kiocb(iocb)) - retval = -EIOCBQUEUED; if (retval > 0) *ppos = pos + retval; } - file_accessed(filp); - goto out; + if (likely(retval != 0)) { + file_accessed(filp); + goto out; + } } retval = 0; @@ -1223,33 +1212,8 @@ __generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, out: return retval; } -EXPORT_SYMBOL(__generic_file_aio_read); - -ssize_t -generic_file_aio_read(struct kiocb *iocb, char __user *buf, size_t count, loff_t pos) -{ - struct iovec local_iov = { .iov_base = buf, .iov_len = count }; - - 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 -generic_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos) -{ - struct iovec local_iov = { .iov_base = buf, .iov_len = count }; - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, filp); - ret = __generic_file_aio_read(&kiocb, &local_iov, 1, ppos); - if (-EIOCBQUEUED == ret) - 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) { ssize_t written; @@ -1471,7 +1435,7 @@ outside_data_content: * accessible.. */ if (area->vm_mm == current->mm) - return NULL; + return NOPAGE_SIGBUS; /* Fall through to the non-read-ahead case */ no_cached_page: /* @@ -1479,7 +1443,6 @@ no_cached_page: * effect. */ error = page_cache_read(file, pgoff); - grab_swap_token(); /* * The page we want has now been added to the page cache. @@ -1496,7 +1459,7 @@ no_cached_page: */ if (error == -ENOMEM) return NOPAGE_OOM; - return NULL; + return NOPAGE_SIGBUS; page_not_uptodate: if (!did_readaround) { @@ -1565,7 +1528,7 @@ page_not_uptodate: */ shrink_readahead_size_eio(file, ra); page_cache_release(page); - return NULL; + return NOPAGE_SIGBUS; } EXPORT_SYMBOL(filemap_nopage); @@ -1906,11 +1869,10 @@ 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)) @@ -1923,13 +1885,29 @@ 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; +} +EXPORT_SYMBOL(should_remove_suid); + +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); @@ -2020,6 +1998,7 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i if (unlikely(*pos + *count > inode->i_sb->s_maxbytes)) *count = inode->i_sb->s_maxbytes - *pos; } else { +#ifdef CONFIG_BLOCK loff_t isize; if (bdev_read_only(I_BDEV(inode))) return -EPERM; @@ -2031,6 +2010,9 @@ inline int generic_write_checks(struct file *file, loff_t *pos, size_t *count, i if (*pos + *count > isize) *count = isize - *pos; +#else + return -EPERM; +#endif } return 0; } @@ -2063,15 +2045,14 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov, * Sync the fs metadata but not the minor inode changes and * of course not the data as we did direct DMA for the IO. * i_mutex is held, which protects generic_osync_inode() from - * livelocking. + * livelocking. AIO O_DIRECT ops attempt to sync metadata here. */ - if (written >= 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { + if ((written >= 0 || written == -EIOCBQUEUED) && + ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { int err = generic_osync_inode(inode, mapping, OSYNC_METADATA); if (err < 0) written = err; } - if (written == count && !is_sync_kiocb(iocb)) - written = -EIOCBQUEUED; return written; } EXPORT_SYMBOL(generic_file_direct_write); @@ -2240,7 +2221,7 @@ __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; @@ -2285,7 +2266,7 @@ __generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, if (count == 0) goto out; - err = remove_suid(file->f_dentry); + err = remove_suid(file->f_path.dentry); if (err) goto out; @@ -2293,8 +2274,11 @@ __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; /* @@ -2303,30 +2287,66 @@ __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; } -EXPORT_SYMBOL(generic_file_aio_write_nolock); -ssize_t -generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) +ssize_t generic_file_aio_write_nolock(struct kiocb *iocb, + const struct iovec *iov, unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - loff_t pos = *ppos; - ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, ppos); + BUG_ON(iocb->ki_pos != pos); + + ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, + &iocb->ki_pos); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err; + ssize_t err; err = sync_page_range_nolock(inode, mapping, pos, ret); if (err < 0) @@ -2334,51 +2354,21 @@ generic_file_aio_write_nolock(struct kiocb *iocb, const struct iovec *iov, } return ret; } +EXPORT_SYMBOL(generic_file_aio_write_nolock); -static ssize_t -__generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, file); - ret = __generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); - if (ret == -EIOCBQUEUED) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} - -ssize_t -generic_file_write_nolock(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, file); - ret = generic_file_aio_write_nolock(&kiocb, iov, nr_segs, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} -EXPORT_SYMBOL(generic_file_write_nolock); - -ssize_t generic_file_aio_write(struct kiocb *iocb, const char __user *buf, - size_t count, loff_t pos) +ssize_t generic_file_aio_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct file *file = iocb->ki_filp; struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; BUG_ON(iocb->ki_pos != pos); mutex_lock(&inode->i_mutex); - ret = __generic_file_aio_write_nolock(iocb, &local_iov, 1, - &iocb->ki_pos); + ret = __generic_file_aio_write_nolock(iocb, iov, nr_segs, + &iocb->ki_pos); mutex_unlock(&inode->i_mutex); if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { @@ -2392,66 +2382,6 @@ ssize_t generic_file_aio_write(struct kiocb *iocb, const char __user *buf, } EXPORT_SYMBOL(generic_file_aio_write); -ssize_t generic_file_write(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) -{ - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; - struct iovec local_iov = { .iov_base = (void __user *)buf, - .iov_len = count }; - - mutex_lock(&inode->i_mutex); - ret = __generic_file_write_nolock(file, &local_iov, 1, ppos); - mutex_unlock(&inode->i_mutex); - - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - ssize_t err; - - err = sync_page_range(inode, mapping, *ppos - ret, ret); - if (err < 0) - ret = err; - } - return ret; -} -EXPORT_SYMBOL(generic_file_write); - -ssize_t generic_file_readv(struct file *filp, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct kiocb kiocb; - ssize_t ret; - - init_sync_kiocb(&kiocb, filp); - ret = __generic_file_aio_read(&kiocb, iov, nr_segs, ppos); - if (-EIOCBQUEUED == ret) - ret = wait_on_sync_kiocb(&kiocb); - return ret; -} -EXPORT_SYMBOL(generic_file_readv); - -ssize_t generic_file_writev(struct file *file, const struct iovec *iov, - unsigned long nr_segs, loff_t *ppos) -{ - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - ssize_t ret; - - mutex_lock(&inode->i_mutex); - ret = __generic_file_write_nolock(file, iov, nr_segs, ppos); - mutex_unlock(&inode->i_mutex); - - if (ret > 0 && ((file->f_flags & O_SYNC) || IS_SYNC(inode))) { - int err; - - err = sync_page_range(inode, mapping, *ppos - ret, ret); - if (err < 0) - ret = err; - } - return ret; -} -EXPORT_SYMBOL(generic_file_writev); - /* * Called under i_mutex for writes to S_ISREG files. Returns -EIO if something * went wrong during pagecache shootdown. @@ -2491,3 +2421,33 @@ generic_file_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, } return retval; } + +/** + * try_to_release_page() - release old fs-specific metadata on a page + * + * @page: the page which the kernel is trying to free + * @gfp_mask: memory allocation flags (and I/O mode) + * + * The address_space is to try to release any data against the page + * (presumably at page->private). If the release was successful, return `1'. + * Otherwise return zero. + * + * The @gfp_mask argument specifies whether I/O may be performed to release + * this page (__GFP_IO), and whether the call may block (__GFP_WAIT). + * + * NOTE: @gfp_mask may go away, and this function may become non-blocking. + */ +int try_to_release_page(struct page *page, gfp_t gfp_mask) +{ + struct address_space * const mapping = page->mapping; + + BUG_ON(!PageLocked(page)); + if (PageWriteback(page)) + return 0; + + if (mapping && mapping->a_ops->releasepage) + return mapping->a_ops->releasepage(page, gfp_mask); + return try_to_free_buffers(page); +} + +EXPORT_SYMBOL(try_to_release_page); diff --git a/mm/filemap.h b/mm/filemap.h index 3f2a343c601..c2bff04c84e 100644 --- a/mm/filemap.h +++ b/mm/filemap.h @@ -12,7 +12,6 @@ #include <linux/mm.h> #include <linux/highmem.h> #include <linux/uio.h> -#include <linux/config.h> #include <linux/uaccess.h> size_t diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index b4fd0d7c9bf..8d667617f55 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -379,7 +379,7 @@ xip_file_write(struct file *filp, const char __user *buf, size_t len, if (count == 0) goto out_backing; - ret = remove_suid(filp->f_dentry); + ret = remove_suid(filp->f_path.dentry); if (ret) goto out_backing; diff --git a/mm/fremap.c b/mm/fremap.c index aa30618ec6b..b77a002c335 100644 --- a/mm/fremap.c +++ b/mm/fremap.c @@ -39,7 +39,7 @@ static int zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, } else { if (!pte_file(pte)) free_swap_and_cache(pte_to_swp_entry(pte)); - pte_clear(mm, addr, ptep); + pte_clear_not_present_full(mm, addr, ptep, 0); } return !!page; } @@ -101,7 +101,6 @@ int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, { int err = -ENOMEM; pte_t *pte; - pte_t pte_val; spinlock_t *ptl; pte = get_locked_pte(mm, addr, &ptl); @@ -114,7 +113,6 @@ 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; /* * 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 diff --git a/mm/highmem.c b/mm/highmem.c index ee5519b176e..0206e7e5018 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -29,13 +29,6 @@ #include <linux/blktrace_api.h> #include <asm/tlbflush.h> -static mempool_t *page_pool, *isa_page_pool; - -static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data) -{ - return mempool_alloc_pages(gfp_mask | GFP_DMA, data); -} - /* * Virtual_count is not a pure "count". * 0 means that it is not mapped, and has not been mapped @@ -217,282 +210,8 @@ void fastcall kunmap_high(struct page *page) } EXPORT_SYMBOL(kunmap_high); - -#define POOL_SIZE 64 - -static __init int init_emergency_pool(void) -{ - struct sysinfo i; - si_meminfo(&i); - si_swapinfo(&i); - - if (!i.totalhigh) - return 0; - - page_pool = mempool_create_page_pool(POOL_SIZE, 0); - BUG_ON(!page_pool); - printk("highmem bounce pool size: %d pages\n", POOL_SIZE); - - return 0; -} - -__initcall(init_emergency_pool); - -/* - * highmem version, map in to vec - */ -static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom) -{ - unsigned long flags; - unsigned char *vto; - - local_irq_save(flags); - vto = kmap_atomic(to->bv_page, KM_BOUNCE_READ); - memcpy(vto + to->bv_offset, vfrom, to->bv_len); - kunmap_atomic(vto, KM_BOUNCE_READ); - local_irq_restore(flags); -} - -#else /* CONFIG_HIGHMEM */ - -#define bounce_copy_vec(to, vfrom) \ - memcpy(page_address((to)->bv_page) + (to)->bv_offset, vfrom, (to)->bv_len) - #endif -#define ISA_POOL_SIZE 16 - -/* - * gets called "every" time someone init's a queue with BLK_BOUNCE_ISA - * as the max address, so check if the pool has already been created. - */ -int init_emergency_isa_pool(void) -{ - if (isa_page_pool) - return 0; - - isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa, - mempool_free_pages, (void *) 0); - BUG_ON(!isa_page_pool); - - printk("isa bounce pool size: %d pages\n", ISA_POOL_SIZE); - return 0; -} - -/* - * Simple bounce buffer support for highmem pages. Depending on the - * queue gfp mask set, *to may or may not be a highmem page. kmap it - * always, it will do the Right Thing - */ -static void copy_to_high_bio_irq(struct bio *to, struct bio *from) -{ - unsigned char *vfrom; - struct bio_vec *tovec, *fromvec; - int i; - - __bio_for_each_segment(tovec, to, i, 0) { - fromvec = from->bi_io_vec + i; - - /* - * not bounced - */ - if (tovec->bv_page == fromvec->bv_page) - continue; - - /* - * fromvec->bv_offset and fromvec->bv_len might have been - * modified by the block layer, so use the original copy, - * bounce_copy_vec already uses tovec->bv_len - */ - vfrom = page_address(fromvec->bv_page) + tovec->bv_offset; - - flush_dcache_page(tovec->bv_page); - bounce_copy_vec(tovec, vfrom); - } -} - -static void bounce_end_io(struct bio *bio, mempool_t *pool, int err) -{ - struct bio *bio_orig = bio->bi_private; - struct bio_vec *bvec, *org_vec; - int i; - - if (test_bit(BIO_EOPNOTSUPP, &bio->bi_flags)) - set_bit(BIO_EOPNOTSUPP, &bio_orig->bi_flags); - - /* - * free up bounce indirect pages used - */ - __bio_for_each_segment(bvec, bio, i, 0) { - org_vec = bio_orig->bi_io_vec + i; - if (bvec->bv_page == org_vec->bv_page) - continue; - - dec_zone_page_state(bvec->bv_page, NR_BOUNCE); - mempool_free(bvec->bv_page, pool); - } - - bio_endio(bio_orig, bio_orig->bi_size, err); - bio_put(bio); -} - -static int bounce_end_io_write(struct bio *bio, unsigned int bytes_done, int err) -{ - if (bio->bi_size) - return 1; - - bounce_end_io(bio, page_pool, err); - return 0; -} - -static int bounce_end_io_write_isa(struct bio *bio, unsigned int bytes_done, int err) -{ - if (bio->bi_size) - return 1; - - bounce_end_io(bio, isa_page_pool, err); - return 0; -} - -static void __bounce_end_io_read(struct bio *bio, mempool_t *pool, int err) -{ - struct bio *bio_orig = bio->bi_private; - - if (test_bit(BIO_UPTODATE, &bio->bi_flags)) - copy_to_high_bio_irq(bio_orig, bio); - - bounce_end_io(bio, pool, err); -} - -static int bounce_end_io_read(struct bio *bio, unsigned int bytes_done, int err) -{ - if (bio->bi_size) - return 1; - - __bounce_end_io_read(bio, page_pool, err); - return 0; -} - -static int bounce_end_io_read_isa(struct bio *bio, unsigned int bytes_done, int err) -{ - if (bio->bi_size) - return 1; - - __bounce_end_io_read(bio, isa_page_pool, err); - return 0; -} - -static void __blk_queue_bounce(request_queue_t *q, struct bio **bio_orig, - mempool_t *pool) -{ - struct page *page; - struct bio *bio = NULL; - int i, rw = bio_data_dir(*bio_orig); - struct bio_vec *to, *from; - - bio_for_each_segment(from, *bio_orig, i) { - page = from->bv_page; - - /* - * is destination page below bounce pfn? - */ - if (page_to_pfn(page) < q->bounce_pfn) - continue; - - /* - * irk, bounce it - */ - if (!bio) - bio = bio_alloc(GFP_NOIO, (*bio_orig)->bi_vcnt); - - to = bio->bi_io_vec + i; - - to->bv_page = mempool_alloc(pool, q->bounce_gfp); - to->bv_len = from->bv_len; - to->bv_offset = from->bv_offset; - inc_zone_page_state(to->bv_page, NR_BOUNCE); - - if (rw == WRITE) { - char *vto, *vfrom; - - flush_dcache_page(from->bv_page); - vto = page_address(to->bv_page) + to->bv_offset; - vfrom = kmap(from->bv_page) + from->bv_offset; - memcpy(vto, vfrom, to->bv_len); - kunmap(from->bv_page); - } - } - - /* - * no pages bounced - */ - if (!bio) - return; - - /* - * at least one page was bounced, fill in possible non-highmem - * pages - */ - __bio_for_each_segment(from, *bio_orig, i, 0) { - to = bio_iovec_idx(bio, i); - if (!to->bv_page) { - to->bv_page = from->bv_page; - to->bv_len = from->bv_len; - to->bv_offset = from->bv_offset; - } - } - - bio->bi_bdev = (*bio_orig)->bi_bdev; - bio->bi_flags |= (1 << BIO_BOUNCED); - bio->bi_sector = (*bio_orig)->bi_sector; - bio->bi_rw = (*bio_orig)->bi_rw; - - bio->bi_vcnt = (*bio_orig)->bi_vcnt; - bio->bi_idx = (*bio_orig)->bi_idx; - bio->bi_size = (*bio_orig)->bi_size; - - if (pool == page_pool) { - bio->bi_end_io = bounce_end_io_write; - if (rw == READ) - bio->bi_end_io = bounce_end_io_read; - } else { - bio->bi_end_io = bounce_end_io_write_isa; - if (rw == READ) - bio->bi_end_io = bounce_end_io_read_isa; - } - - bio->bi_private = *bio_orig; - *bio_orig = bio; -} - -void blk_queue_bounce(request_queue_t *q, struct bio **bio_orig) -{ - mempool_t *pool; - - /* - * for non-isa bounce case, just check if the bounce pfn is equal - * to or bigger than the highest pfn in the system -- in that case, - * don't waste time iterating over bio segments - */ - if (!(q->bounce_gfp & GFP_DMA)) { - if (q->bounce_pfn >= blk_max_pfn) - return; - pool = page_pool; - } else { - BUG_ON(!isa_page_pool); - pool = isa_page_pool; - } - - blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE); - - /* - * slow path - */ - __blk_queue_bounce(q, bio_orig, pool); -} - -EXPORT_SYMBOL(blk_queue_bounce); - #if defined(HASHED_PAGE_VIRTUAL) #define PA_HASH_ORDER 7 diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7c7d03dbf73..0ccc7f23025 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -109,7 +109,7 @@ static int alloc_fresh_huge_page(void) if (nid == MAX_NUMNODES) nid = first_node(node_online_map); if (page) { - page[1].lru.next = (void *)free_huge_page; /* dtor */ + set_compound_page_dtor(page, free_huge_page); spin_lock(&hugetlb_lock); nr_huge_pages++; nr_huge_pages_node[page_to_nid(page)]++; @@ -344,7 +344,6 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, entry = *src_pte; ptepage = pte_page(entry); get_page(ptepage); - add_mm_counter(dst, file_rss, HPAGE_SIZE / PAGE_SIZE); set_huge_pte_at(dst, addr, dst_pte, entry); } spin_unlock(&src->page_table_lock); @@ -356,40 +355,66 @@ 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; pte_t *ptep; pte_t pte; struct page *page; + struct page *tmp; + /* + * A page gathering list, protected by per file i_mmap_lock. The + * lock is used to avoid list corruption from multiple unmapping + * of the same page since we are using page->lru. + */ + LIST_HEAD(page_list); WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~HPAGE_MASK); BUG_ON(end & ~HPAGE_MASK); spin_lock(&mm->page_table_lock); - - /* Update high watermark before we lower rss */ - update_hiwater_rss(mm); - for (address = start; address < end; address += HPAGE_SIZE) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; + if (huge_pmd_unshare(mm, &address, ptep)) + continue; + pte = huge_ptep_get_and_clear(mm, address, ptep); if (pte_none(pte)) continue; page = pte_page(pte); - put_page(page); - add_mm_counter(mm, file_rss, (int) -(HPAGE_SIZE / PAGE_SIZE)); + list_add(&page->lru, &page_list); } - spin_unlock(&mm->page_table_lock); flush_tlb_range(vma, start, end); + list_for_each_entry_safe(page, tmp, &page_list, lru) { + list_del(&page->lru); + put_page(page); + } +} + +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, @@ -454,6 +479,9 @@ 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); @@ -488,7 +516,6 @@ retry: if (!pte_none(*ptep)) goto backout; - add_mm_counter(mm, file_rss, HPAGE_SIZE / PAGE_SIZE); new_pte = make_huge_pte(vma, page, ((vma->vm_flags & VM_WRITE) && (vma->vm_flags & VM_SHARED))); set_huge_pte_at(mm, address, ptep, new_pte); @@ -626,11 +653,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma, BUG_ON(address >= end); flush_cache_range(vma, address, end); + spin_lock(&vma->vm_file->f_mapping->i_mmap_lock); spin_lock(&mm->page_table_lock); for (; address < end; address += HPAGE_SIZE) { ptep = huge_pte_offset(mm, address); if (!ptep) continue; + if (huge_pmd_unshare(mm, &address, ptep)) + continue; if (!pte_none(*ptep)) { pte = huge_ptep_get_and_clear(mm, address, ptep); pte = pte_mkhuge(pte_modify(pte, newprot)); @@ -639,6 +669,7 @@ void hugetlb_change_protection(struct vm_area_struct *vma, } } spin_unlock(&mm->page_table_lock); + spin_unlock(&vma->vm_file->f_mapping->i_mmap_lock); flush_tlb_range(vma, start, end); } diff --git a/mm/memory.c b/mm/memory.c index 92a3ebd8d79..bf6100236e6 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -467,7 +467,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, */ if (is_cow_mapping(vm_flags)) { ptep_set_wrprotect(src_mm, addr, src_pte); - pte = *src_pte; + pte = pte_wrprotect(pte); } /* @@ -506,6 +506,7 @@ again: src_pte = pte_offset_map_nested(src_pmd, addr); src_ptl = pte_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + arch_enter_lazy_mmu_mode(); do { /* @@ -527,6 +528,7 @@ again: progress += 8; } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); spin_unlock(src_ptl); pte_unmap_nested(src_pte - 1); add_mm_rss(dst_mm, rss[0], rss[1]); @@ -628,6 +630,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, int anon_rss = 0; pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + arch_enter_lazy_mmu_mode(); do { pte_t ptent = *pte; if (pte_none(ptent)) { @@ -690,10 +693,11 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, continue; if (!pte_file(ptent)) free_swap_and_cache(pte_to_swp_entry(ptent)); - pte_clear_full(mm, addr, pte, tlb->fullmm); + pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0)); add_mm_rss(mm, file_rss, anon_rss); + arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); return addr; @@ -1082,6 +1086,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, default: BUG(); } + cond_resched(); } if (pages) { pages[i] = page; @@ -1105,21 +1110,29 @@ static int zeromap_pte_range(struct mm_struct *mm, pmd_t *pmd, { pte_t *pte; spinlock_t *ptl; + int err = 0; pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) - return -ENOMEM; + return -EAGAIN; + arch_enter_lazy_mmu_mode(); do { struct page *page = ZERO_PAGE(addr); pte_t zero_pte = pte_wrprotect(mk_pte(page, prot)); + + if (unlikely(!pte_none(*pte))) { + err = -EEXIST; + pte++; + break; + } page_cache_get(page); page_add_file_rmap(page); inc_mm_counter(mm, file_rss); - BUG_ON(!pte_none(*pte)); set_pte_at(mm, addr, pte, zero_pte); } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); - return 0; + return err; } static inline int zeromap_pmd_range(struct mm_struct *mm, pud_t *pud, @@ -1127,16 +1140,18 @@ static inline int zeromap_pmd_range(struct mm_struct *mm, pud_t *pud, { pmd_t *pmd; unsigned long next; + int err; pmd = pmd_alloc(mm, pud, addr); if (!pmd) - return -ENOMEM; + return -EAGAIN; do { next = pmd_addr_end(addr, end); - if (zeromap_pte_range(mm, pmd, addr, next, prot)) - return -ENOMEM; + err = zeromap_pte_range(mm, pmd, addr, next, prot); + if (err) + break; } while (pmd++, addr = next, addr != end); - return 0; + return err; } static inline int zeromap_pud_range(struct mm_struct *mm, pgd_t *pgd, @@ -1144,16 +1159,18 @@ static inline int zeromap_pud_range(struct mm_struct *mm, pgd_t *pgd, { pud_t *pud; unsigned long next; + int err; pud = pud_alloc(mm, pgd, addr); if (!pud) - return -ENOMEM; + return -EAGAIN; do { next = pud_addr_end(addr, end); - if (zeromap_pmd_range(mm, pud, addr, next, prot)) - return -ENOMEM; + err = zeromap_pmd_range(mm, pud, addr, next, prot); + if (err) + break; } while (pud++, addr = next, addr != end); - return 0; + return err; } int zeromap_page_range(struct vm_area_struct *vma, @@ -1275,11 +1292,13 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); if (!pte) return -ENOMEM; + arch_enter_lazy_mmu_mode(); do { BUG_ON(!pte_none(*pte)); set_pte_at(mm, addr, pte, pfn_pte(pfn, prot)); pfn++; } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); return 0; } @@ -1443,6 +1462,7 @@ 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; } @@ -1577,7 +1597,14 @@ gotten: entry = mk_pte(new_page, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); lazy_mmu_prot_update(entry); - ptep_establish(vma, address, page_table, entry); + /* + * Clear the pte entry and flush it first, before updating the + * pte with the new entry. This will avoid a race condition + * seen in the presence of one thread doing SMC and another + * thread doing COW. + */ + ptep_clear_flush(vma, address, page_table); + set_pte_at(mm, address, page_table, entry); update_mmu_cache(vma, address, entry); lru_cache_add_active(new_page); page_add_new_anon_rmap(new_page, vma, address); @@ -1885,7 +1912,6 @@ int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end) return 0; } -EXPORT_UNUSED_SYMBOL(vmtruncate_range); /* June 2006 */ /** * swapin_readahead - swap in pages in hope we need them soon @@ -1974,6 +2000,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, delayacct_set_flag(DELAYACCT_PF_SWAPIN); page = lookup_swap_cache(entry); if (!page) { + grab_swap_token(); /* Contend for token _before_ read-in */ swapin_readahead(entry, address, vma); page = read_swap_cache_async(entry, vma, address); if (!page) { @@ -1991,7 +2018,6 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Had to read the page from swap area: Major fault */ ret = VM_FAULT_MAJOR; count_vm_event(PGMAJFAULT); - grab_swap_token(); } delayacct_clear_flag(DELAYACCT_PF_SWAPIN); @@ -2154,11 +2180,13 @@ retry: * after the next truncate_count read. */ - /* no page was available -- either SIGBUS or OOM */ - if (new_page == NOPAGE_SIGBUS) + /* no page was available -- either SIGBUS, OOM or REFAULT */ + if (unlikely(new_page == NOPAGE_SIGBUS)) return VM_FAULT_SIGBUS; - if (new_page == NOPAGE_OOM) + else if (unlikely(new_page == NOPAGE_OOM)) return VM_FAULT_OOM; + else if (unlikely(new_page == NOPAGE_REFAULT)) + return VM_FAULT_MINOR; /* * Should we do an early C-O-W break? @@ -2256,6 +2284,54 @@ oom: } /* + * do_no_pfn() tries to create a new page mapping for a page without + * a struct_page backing it + * + * As this is called only for pages that do not currently exist, we + * do not need to flush old virtual caches or the TLB. + * + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), and pte mapped but not yet locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. + * + * It is expected that the ->nopfn handler always returns the same pfn + * for a given virtual mapping. + * + * Mark this `noinline' to prevent it from bloating the main pagefault code. + */ +static noinline int do_no_pfn(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + int write_access) +{ + spinlock_t *ptl; + pte_t entry; + unsigned long pfn; + int ret = VM_FAULT_MINOR; + + pte_unmap(page_table); + BUG_ON(!(vma->vm_flags & VM_PFNMAP)); + BUG_ON(is_cow_mapping(vma->vm_flags)); + + pfn = vma->vm_ops->nopfn(vma, address & PAGE_MASK); + if (pfn == NOPFN_OOM) + return VM_FAULT_OOM; + if (pfn == NOPFN_SIGBUS) + return VM_FAULT_SIGBUS; + + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + + /* Only go through if we didn't race with anybody else... */ + if (pte_none(*page_table)) { + entry = pfn_pte(pfn, vma->vm_page_prot); + if (write_access) + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + set_pte_at(mm, address, page_table, entry); + } + pte_unmap_unlock(page_table, ptl); + return ret; +} + +/* * Fault of a previously existing named mapping. Repopulate the pte * from the encoded file_pte if possible. This enables swappable * nonlinear vmas. @@ -2317,11 +2393,17 @@ static inline int handle_pte_fault(struct mm_struct *mm, old_entry = entry = *pte; if (!pte_present(entry)) { if (pte_none(entry)) { - if (!vma->vm_ops || !vma->vm_ops->nopage) - return do_anonymous_page(mm, vma, address, - pte, pmd, write_access); - return do_no_page(mm, vma, address, - pte, pmd, write_access); + if (vma->vm_ops) { + if (vma->vm_ops->nopage) + return do_no_page(mm, vma, address, + pte, pmd, + write_access); + if (unlikely(vma->vm_ops->nopfn)) + return do_no_pfn(mm, vma, address, pte, + pmd, write_access); + } + return do_anonymous_page(mm, vma, address, + pte, pmd, write_access); } if (pte_file(entry)) return do_file_page(mm, vma, address, @@ -2550,3 +2632,56 @@ int in_gate_area_no_task(unsigned long addr) } #endif /* __HAVE_ARCH_GATE_AREA */ + +/* + * Access another process' address space. + * Source/target buffer must be kernel space, + * Do not walk the page table directly, use get_user_pages + */ +int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write) +{ + struct mm_struct *mm; + struct vm_area_struct *vma; + struct page *page; + void *old_buf = buf; + + mm = get_task_mm(tsk); + if (!mm) + return 0; + + down_read(&mm->mmap_sem); + /* ignore errors, just check how much was sucessfully transfered */ + while (len) { + int bytes, ret, offset; + void *maddr; + + ret = get_user_pages(tsk, mm, addr, 1, + write, 1, &page, &vma); + if (ret <= 0) + break; + + bytes = len; + offset = addr & (PAGE_SIZE-1); + if (bytes > PAGE_SIZE-offset) + bytes = PAGE_SIZE-offset; + + maddr = kmap(page); + if (write) { + copy_to_user_page(vma, page, addr, + maddr + offset, buf, bytes); + set_page_dirty_lock(page); + } else { + copy_from_user_page(vma, page, addr, + buf, maddr + offset, bytes); + } + kunmap(page); + page_cache_release(page); + len -= bytes; + buf += bytes; + addr += bytes; + } + up_read(&mm->mmap_sem); + mmput(mm); + + return buf - old_buf; +} diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c37319542b7..0c055a090f4 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -13,6 +13,7 @@ #include <linux/compiler.h> #include <linux/module.h> #include <linux/pagevec.h> +#include <linux/writeback.h> #include <linux/slab.h> #include <linux/sysctl.h> #include <linux/cpu.h> @@ -21,11 +22,41 @@ #include <linux/highmem.h> #include <linux/vmalloc.h> #include <linux/ioport.h> +#include <linux/cpuset.h> #include <asm/tlbflush.h> -extern void zonetable_add(struct zone *zone, int nid, int zid, unsigned long pfn, - unsigned long size); +/* add this memory to iomem resource */ +static struct resource *register_memory_resource(u64 start, u64 size) +{ + struct resource *res; + res = kzalloc(sizeof(struct resource), GFP_KERNEL); + BUG_ON(!res); + + res->name = "System RAM"; + res->start = start; + res->end = start + size - 1; + res->flags = IORESOURCE_MEM; + if (request_resource(&iomem_resource, res) < 0) { + printk("System RAM resource %llx - %llx cannot be added\n", + (unsigned long long)res->start, (unsigned long long)res->end); + kfree(res); + res = NULL; + } + return res; +} + +static void release_memory_resource(struct resource *res) +{ + if (!res) + return; + release_resource(res); + kfree(res); + return; +} + + +#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE static int __add_zone(struct zone *zone, unsigned long phys_start_pfn) { struct pglist_data *pgdat = zone->zone_pgdat; @@ -41,12 +72,9 @@ static int __add_zone(struct zone *zone, unsigned long phys_start_pfn) 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, - int nr_pages); static int __add_section(struct zone *zone, unsigned long phys_start_pfn) { int nr_pages = PAGES_PER_SECTION; @@ -191,8 +219,10 @@ int online_pages(unsigned long pfn, unsigned long nr_pages) if (need_zonelists_rebuild) build_all_zonelists(); vm_total_pages = nr_free_pagecache_pages(); + writeback_set_ratelimit(); return 0; } +#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ static pg_data_t *hotadd_new_pgdat(int nid, u64 start) { @@ -222,36 +252,6 @@ static void rollback_node_hotadd(int nid, pg_data_t *pgdat) return; } -/* add this memory to iomem resource */ -static struct resource *register_memory_resource(u64 start, u64 size) -{ - struct resource *res; - res = kzalloc(sizeof(struct resource), GFP_KERNEL); - BUG_ON(!res); - - res->name = "System RAM"; - res->start = start; - res->end = start + size - 1; - res->flags = IORESOURCE_MEM; - if (request_resource(&iomem_resource, res) < 0) { - printk("System RAM resource %llx - %llx cannot be added\n", - (unsigned long long)res->start, (unsigned long long)res->end); - kfree(res); - res = NULL; - } - return res; -} - -static void release_memory_resource(struct resource *res) -{ - if (!res) - return; - release_resource(res); - kfree(res); - return; -} - - int add_memory(int nid, u64 start, u64 size) { @@ -283,6 +283,8 @@ int add_memory(int nid, u64 start, u64 size) /* we online node here. we can't roll back from here. */ node_set_online(nid); + cpuset_track_online_nodes(); + if (new_pgdat) { ret = register_one_node(nid); /* diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 38f89650bc8..da946394655 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -141,9 +141,11 @@ static struct zonelist *bind_zonelist(nodemask_t *nodes) enum zone_type k; max = 1 + MAX_NR_ZONES * nodes_weight(*nodes); + max++; /* space for zlcache_ptr (see mmzone.h) */ zl = kmalloc(sizeof(struct zone *) * max, GFP_KERNEL); if (!zl) return NULL; + zl->zlcache_ptr = NULL; num = 0; /* First put in the highest zones from all nodes, then all the next lower zones etc. Avoid empty zones because the memory allocator @@ -219,7 +221,7 @@ static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd, orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); do { struct page *page; - unsigned int nid; + int nid; if (!pte_present(*pte)) continue; @@ -727,7 +729,7 @@ 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; } @@ -1136,7 +1138,9 @@ static unsigned interleave_nodes(struct mempolicy *policy) */ unsigned slab_node(struct mempolicy *policy) { - switch (policy->policy) { + int pol = policy ? policy->policy : MPOL_DEFAULT; + + switch (pol) { case MPOL_INTERLEAVE: return interleave_nodes(policy); @@ -1322,12 +1326,11 @@ struct mempolicy *__mpol_copy(struct mempolicy *old) atomic_set(&new->refcnt, 1); if (new->policy == MPOL_BIND) { int sz = ksize(old->v.zonelist); - new->v.zonelist = kmalloc(sz, SLAB_KERNEL); + new->v.zonelist = kmemdup(old->v.zonelist, sz, GFP_KERNEL); if (!new->v.zonelist) { kmem_cache_free(policy_cache, new); return ERR_PTR(-ENOMEM); } - memcpy(new->v.zonelist, old->v.zonelist, sz); } return new; } @@ -1704,8 +1707,8 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) * Display pages allocated per node and memory policy via /proc. */ -static const char *policy_types[] = { "default", "prefer", "bind", - "interleave" }; +static const char * const policy_types[] = + { "default", "prefer", "bind", "interleave" }; /* * Convert a mempolicy into a string. @@ -1854,7 +1857,7 @@ int show_numa_map(struct seq_file *m, void *v) if (file) { seq_printf(m, " file="); - seq_path(m, file->f_vfsmnt, file->f_dentry, "\n\t= "); + seq_path(m, file->f_path.mnt, file->f_path.dentry, "\n\t= "); } else if (vma->vm_start <= mm->brk && vma->vm_end >= mm->start_brk) { seq_printf(m, " heap"); } else if (vma->vm_start <= mm->start_stack && diff --git a/mm/migrate.c b/mm/migrate.c index 20a8c2687b1..e9b161bde95 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -294,7 +294,7 @@ out: static int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page) { - struct page **radix_pointer; + void **pslot; if (!mapping) { /* Anonymous page */ @@ -305,12 +305,11 @@ static int migrate_page_move_mapping(struct address_space *mapping, write_lock_irq(&mapping->tree_lock); - radix_pointer = (struct page **)radix_tree_lookup_slot( - &mapping->page_tree, - page_index(page)); + pslot = radix_tree_lookup_slot(&mapping->page_tree, + page_index(page)); if (page_count(page) != 2 + !!PagePrivate(page) || - *radix_pointer != page) { + (struct page *)radix_tree_deref_slot(pslot) != page) { write_unlock_irq(&mapping->tree_lock); return -EAGAIN; } @@ -318,7 +317,7 @@ static int migrate_page_move_mapping(struct address_space *mapping, /* * Now we know that no one else is looking at the page. */ - get_page(newpage); + get_page(newpage); /* add cache reference */ #ifdef CONFIG_SWAP if (PageSwapCache(page)) { SetPageSwapCache(newpage); @@ -326,8 +325,14 @@ static int migrate_page_move_mapping(struct address_space *mapping, } #endif - *radix_pointer = newpage; + radix_tree_replace_slot(pslot, newpage); + + /* + * Drop cache reference from old page. + * We know this isn't the last reference. + */ __put_page(page); + write_unlock_irq(&mapping->tree_lock); return 0; @@ -409,6 +414,7 @@ int migrate_page(struct address_space *mapping, } EXPORT_SYMBOL(migrate_page); +#ifdef CONFIG_BLOCK /* * Migration function for pages with buffers. This function can only be used * if the underlying filesystem guarantees that no other references to "page" @@ -466,6 +472,7 @@ int buffer_migrate_page(struct address_space *mapping, return 0; } EXPORT_SYMBOL(buffer_migrate_page); +#endif /* * Writeback a page to clean the dirty state @@ -525,7 +532,7 @@ static int fallback_migrate_page(struct address_space *mapping, * Buffers may be managed in a filesystem specific way. * We must have no buffers or drop them. */ - if (page_has_buffers(page) && + if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL)) return -EAGAIN; @@ -950,7 +957,8 @@ 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/mlock.c b/mm/mlock.c index b90c59573ab..3446b7ef731 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -65,7 +65,7 @@ success: ret = make_pages_present(start, end); } - vma->vm_mm->locked_vm -= pages; + mm->locked_vm -= pages; out: if (ret == -ENOMEM) ret = -EAGAIN; diff --git a/mm/mmap.c b/mm/mmap.c index eea8eefd51a..9717337293c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -188,7 +188,7 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma, struct file *file, struct address_space *mapping) { if (vma->vm_flags & VM_DENYWRITE) - atomic_inc(&file->f_dentry->d_inode->i_writecount); + atomic_inc(&file->f_path.dentry->d_inode->i_writecount); if (vma->vm_flags & VM_SHARED) mapping->i_mmap_writable--; @@ -399,7 +399,7 @@ static inline void __vma_link_file(struct vm_area_struct *vma) struct address_space *mapping = file->f_mapping; if (vma->vm_flags & VM_DENYWRITE) - atomic_dec(&file->f_dentry->d_inode->i_writecount); + atomic_dec(&file->f_path.dentry->d_inode->i_writecount); if (vma->vm_flags & VM_SHARED) mapping->i_mmap_writable++; @@ -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? * @@ -918,7 +907,7 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, * mounted, in which case we dont add PROT_EXEC.) */ if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC)) - if (!(file && (file->f_vfsmnt->mnt_flags & MNT_NOEXEC))) + if (!(file && (file->f_path.mnt->mnt_flags & MNT_NOEXEC))) prot |= PROT_EXEC; if (!len) @@ -971,7 +960,7 @@ unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, return -EAGAIN; } - inode = file ? file->f_dentry->d_inode : NULL; + inode = file ? file->f_path.dentry->d_inode : NULL; if (file) { switch (flags & MAP_TYPE) { @@ -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_path.mnt->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 @@ -1737,7 +1736,7 @@ int split_vma(struct mm_struct * mm, struct vm_area_struct * vma, if (mm->map_count >= sysctl_max_map_count) return -ENOMEM; - new = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL); + new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (!new) return -ENOMEM; @@ -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); @@ -2055,7 +2057,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, vma_start < new_vma->vm_end) *vmap = new_vma; } else { - new_vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL); + new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL); if (new_vma) { *new_vma = *vma; pol = mpol_copy(vma_policy(vma)); diff --git a/mm/mmzone.c b/mm/mmzone.c index febea1c9816..eb5838634f1 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -14,8 +14,6 @@ struct pglist_data *first_online_pgdat(void) return NODE_DATA(first_online_node); } -EXPORT_UNUSED_SYMBOL(first_online_pgdat); /* June 2006 */ - struct pglist_data *next_online_pgdat(struct pglist_data *pgdat) { int nid = next_online_node(pgdat->node_id); @@ -24,8 +22,6 @@ struct pglist_data *next_online_pgdat(struct pglist_data *pgdat) return NULL; return NODE_DATA(nid); } -EXPORT_UNUSED_SYMBOL(next_online_pgdat); /* June 2006 */ - /* * next_zone - helper magic for for_each_zone() @@ -45,5 +41,4 @@ struct zone *next_zone(struct zone *zone) } return zone; } -EXPORT_UNUSED_SYMBOL(next_zone); /* June 2006 */ diff --git a/mm/mprotect.c b/mm/mprotect.c index 955f9d0e38a..3b8f3c0c63f 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -34,6 +34,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, spinlock_t *ptl; pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + arch_enter_lazy_mmu_mode(); do { oldpte = *pte; if (pte_present(oldpte)) { @@ -70,6 +71,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, } } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); pte_unmap_unlock(pte - 1, ptl); } diff --git a/mm/mremap.c b/mm/mremap.c index 7c15cf3373a..9c769fa29f3 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -98,6 +98,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, new_ptl = pte_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); + arch_enter_lazy_mmu_mode(); for (; old_addr < old_end; old_pte++, old_addr += PAGE_SIZE, new_pte++, new_addr += PAGE_SIZE) { @@ -109,6 +110,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, set_pte_at(mm, new_addr, new_pte, pte); } + arch_leave_lazy_mmu_mode(); if (new_ptl != old_ptl) spin_unlock(new_ptl); pte_unmap_nested(new_pte - 1); diff --git a/mm/nommu.c b/mm/nommu.c index d99dea31e44..23fb033e596 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -122,26 +122,50 @@ unsigned int kobjsize(const void *objp) } /* - * The nommu dodgy version :-) + * get a list of pages in an address range belonging to the specified process + * and indicate the VMA that covers each page + * - this is potentially dodgy as we may end incrementing the page count of a + * slab page or a secondary page from a compound page + * - don't permit access to VMAs that don't support it, such as I/O mappings */ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int len, int write, int force, struct page **pages, struct vm_area_struct **vmas) { + struct vm_area_struct *vma; + unsigned long vm_flags; int i; - static struct vm_area_struct dummy_vma; + + /* calculate required read or write permissions. + * - if 'force' is set, we only require the "MAY" flags. + */ + vm_flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); + vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); for (i = 0; i < len; i++) { + vma = find_vma(mm, start); + if (!vma) + goto finish_or_fault; + + /* protect what we can, including chardevs */ + if (vma->vm_flags & (VM_IO | VM_PFNMAP) || + !(vm_flags & vma->vm_flags)) + goto finish_or_fault; + if (pages) { pages[i] = virt_to_page(start); if (pages[i]) page_cache_get(pages[i]); } if (vmas) - vmas[i] = &dummy_vma; + vmas[i] = vma; start += PAGE_SIZE; } - return(i); + + return i; + +finish_or_fault: + return i ? : -EFAULT; } EXPORT_SYMBOL(get_user_pages); @@ -197,7 +221,7 @@ long vwrite(char *buf, char *addr, unsigned long count) * Allocate enough pages to cover @size from the page level * allocator and map them into continguos kernel virtual space. * - * For tight cotrol over page level allocator and protection flags + * For tight control over page level allocator and protection flags * use __vmalloc() instead. */ void *vmalloc(unsigned long size) @@ -286,6 +310,77 @@ static void show_process_blocks(void) } #endif /* DEBUG */ +/* + * add a VMA into a process's mm_struct in the appropriate place in the list + * - should be called with mm->mmap_sem held writelocked + */ +static void add_vma_to_mm(struct mm_struct *mm, struct vm_list_struct *vml) +{ + struct vm_list_struct **ppv; + + for (ppv = ¤t->mm->context.vmlist; *ppv; ppv = &(*ppv)->next) + if ((*ppv)->vma->vm_start > vml->vma->vm_start) + break; + + vml->next = *ppv; + *ppv = vml; +} + +/* + * look up the first VMA in which addr resides, NULL if none + * - should be called with mm->mmap_sem at least held readlocked + */ +struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) +{ + struct vm_list_struct *loop, *vml; + + /* search the vm_start ordered list */ + vml = NULL; + for (loop = mm->context.vmlist; loop; loop = loop->next) { + if (loop->vma->vm_start > addr) + break; + vml = loop; + } + + if (vml && vml->vma->vm_end > addr) + return vml->vma; + + return NULL; +} +EXPORT_SYMBOL(find_vma); + +/* + * find a VMA + * - we don't extend stack VMAs under NOMMU conditions + */ +struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr) +{ + return find_vma(mm, addr); +} + +/* + * look up the first VMA exactly that exactly matches addr + * - should be called with mm->mmap_sem at least held readlocked + */ +static inline struct vm_area_struct *find_vma_exact(struct mm_struct *mm, + unsigned long addr) +{ + struct vm_list_struct *vml; + + /* search the vm_start ordered list */ + for (vml = mm->context.vmlist; vml; vml = vml->next) { + if (vml->vma->vm_start == addr) + return vml->vma; + if (vml->vma->vm_start > addr) + break; + } + + return NULL; +} + +/* + * find a VMA in the global tree + */ static inline struct vm_area_struct *find_nommu_vma(unsigned long start) { struct vm_area_struct *vma; @@ -305,6 +400,9 @@ static inline struct vm_area_struct *find_nommu_vma(unsigned long start) return NULL; } +/* + * add a VMA in the global tree + */ static void add_nommu_vma(struct vm_area_struct *vma) { struct vm_area_struct *pvma; @@ -351,6 +449,9 @@ static void add_nommu_vma(struct vm_area_struct *vma) rb_insert_color(&vma->vm_rb, &nommu_vma_tree); } +/* + * delete a VMA from the global list + */ static void delete_nommu_vma(struct vm_area_struct *vma) { struct address_space *mapping; @@ -396,15 +497,17 @@ static int validate_mmap_request(struct file *file, (flags & MAP_TYPE) != MAP_SHARED) return -EINVAL; - if (PAGE_ALIGN(len) == 0) - return addr; - - if (len > TASK_SIZE) + if (!len) return -EINVAL; + /* Careful about overflows.. */ + len = PAGE_ALIGN(len); + if (!len || len > TASK_SIZE) + return -ENOMEM; + /* offset overflow? */ if ((pgoff + (len >> PAGE_SHIFT)) < pgoff) - return -EINVAL; + return -EOVERFLOW; if (file) { /* validate file mapping requests */ @@ -420,7 +523,7 @@ static int validate_mmap_request(struct file *file, */ mapping = file->f_mapping; if (!mapping) - mapping = file->f_dentry->d_inode->i_mapping; + mapping = file->f_path.dentry->d_inode->i_mapping; capabilities = 0; if (mapping && mapping->backing_dev_info) @@ -429,7 +532,7 @@ static int validate_mmap_request(struct file *file, if (!capabilities) { /* no explicit capabilities set, so assume some * defaults */ - switch (file->f_dentry->d_inode->i_mode & S_IFMT) { + switch (file->f_path.dentry->d_inode->i_mode & S_IFMT) { case S_IFREG: case S_IFBLK: capabilities = BDI_CAP_MAP_COPY; @@ -460,11 +563,11 @@ static int validate_mmap_request(struct file *file, !(file->f_mode & FMODE_WRITE)) return -EACCES; - if (IS_APPEND(file->f_dentry->d_inode) && + if (IS_APPEND(file->f_path.dentry->d_inode) && (file->f_mode & FMODE_WRITE)) return -EACCES; - if (locks_verify_locked(file->f_dentry->d_inode)) + if (locks_verify_locked(file->f_path.dentry->d_inode)) return -EAGAIN; if (!(capabilities & BDI_CAP_MAP_DIRECT)) @@ -495,7 +598,7 @@ static int validate_mmap_request(struct file *file, /* handle executable mappings and implied executable * mappings */ - if (file->f_vfsmnt->mnt_flags & MNT_NOEXEC) { + if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) { if (prot & PROT_EXEC) return -EPERM; } @@ -705,10 +808,9 @@ unsigned long do_mmap_pgoff(struct file *file, vm_flags = determine_vm_flags(file, prot, flags, capabilities); /* we're going to need to record the mapping if it works */ - vml = kmalloc(sizeof(struct vm_list_struct), GFP_KERNEL); + vml = kzalloc(sizeof(struct vm_list_struct), GFP_KERNEL); if (!vml) goto error_getting_vml; - memset(vml, 0, sizeof(*vml)); down_write(&nommu_vma_sem); @@ -731,7 +833,7 @@ unsigned long do_mmap_pgoff(struct file *file, continue; /* search for overlapping mappings on the same file */ - if (vma->vm_file->f_dentry->d_inode != file->f_dentry->d_inode) + if (vma->vm_file->f_path.dentry->d_inode != file->f_path.dentry->d_inode) continue; if (vma->vm_pgoff >= pgoff + pglen) @@ -784,11 +886,10 @@ unsigned long do_mmap_pgoff(struct file *file, } /* we're going to need a VMA struct as well */ - vma = kmalloc(sizeof(struct vm_area_struct), GFP_KERNEL); + vma = kzalloc(sizeof(struct vm_area_struct), GFP_KERNEL); if (!vma) goto error_getting_vma; - memset(vma, 0, sizeof(*vma)); INIT_LIST_HEAD(&vma->anon_vma_node); atomic_set(&vma->vm_usage, 1); if (file) @@ -828,8 +929,7 @@ unsigned long do_mmap_pgoff(struct file *file, realalloc += kobjsize(vml); askedalloc += sizeof(*vml); - vml->next = current->mm->context.vmlist; - current->mm->context.vmlist = vml; + add_vma_to_mm(current->mm, vml); up_write(&nommu_vma_sem); @@ -848,7 +948,8 @@ unsigned long do_mmap_pgoff(struct file *file, up_write(&nommu_vma_sem); kfree(vml); if (vma) { - fput(vma->vm_file); + if (vma->vm_file) + fput(vma->vm_file); kfree(vma); } return ret; @@ -908,6 +1009,11 @@ static void put_vma(struct vm_area_struct *vma) } } +/* + * release a mapping + * - under NOMMU conditions the parameters must match exactly to the mapping to + * be removed + */ int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len) { struct vm_list_struct *vml, **parent; @@ -917,10 +1023,13 @@ int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len) printk("do_munmap:\n"); #endif - for (parent = &mm->context.vmlist; *parent; parent = &(*parent)->next) + for (parent = &mm->context.vmlist; *parent; parent = &(*parent)->next) { + if ((*parent)->vma->vm_start > addr) + break; if ((*parent)->vma->vm_start == addr && ((len == 0) || ((*parent)->vma->vm_end == end))) goto found; + } printk("munmap of non-mmaped memory by process %d (%s): %p\n", current->pid, current->comm, (void *) addr); @@ -946,7 +1055,20 @@ int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len) return 0; } -/* Release all mmaps. */ +asmlinkage long sys_munmap(unsigned long addr, size_t len) +{ + int ret; + struct mm_struct *mm = current->mm; + + down_write(&mm->mmap_sem); + ret = do_munmap(mm, addr, len); + up_write(&mm->mmap_sem); + return ret; +} + +/* + * Release all mappings + */ void exit_mmap(struct mm_struct * mm) { struct vm_list_struct *tmp; @@ -973,37 +1095,26 @@ void exit_mmap(struct mm_struct * mm) } } -asmlinkage long sys_munmap(unsigned long addr, size_t len) -{ - int ret; - struct mm_struct *mm = current->mm; - - down_write(&mm->mmap_sem); - ret = do_munmap(mm, addr, len); - up_write(&mm->mmap_sem); - return ret; -} - unsigned long do_brk(unsigned long addr, unsigned long len) { return -ENOMEM; } /* - * Expand (or shrink) an existing mapping, potentially moving it at the - * same time (controlled by the MREMAP_MAYMOVE flag and available VM space) + * expand (or shrink) an existing mapping, potentially moving it at the same + * time (controlled by the MREMAP_MAYMOVE flag and available VM space) * - * MREMAP_FIXED option added 5-Dec-1999 by Benjamin LaHaise - * This option implies MREMAP_MAYMOVE. + * under NOMMU conditions, we only permit changing a mapping's size, and only + * as long as it stays within the hole allocated by the kmalloc() call in + * do_mmap_pgoff() and the block is not shareable * - * on uClinux, we only permit changing a mapping's size, and only as long as it stays within the - * hole allocated by the kmalloc() call in do_mmap_pgoff() and the block is not shareable + * MREMAP_FIXED is not supported under NOMMU conditions */ unsigned long do_mremap(unsigned long addr, unsigned long old_len, unsigned long new_len, unsigned long flags, unsigned long new_addr) { - struct vm_list_struct *vml = NULL; + struct vm_area_struct *vma; /* insanity checks first */ if (new_len == 0) @@ -1012,58 +1123,46 @@ unsigned long do_mremap(unsigned long addr, if (flags & MREMAP_FIXED && new_addr != addr) return (unsigned long) -EINVAL; - for (vml = current->mm->context.vmlist; vml; vml = vml->next) - if (vml->vma->vm_start == addr) - goto found; - - return (unsigned long) -EINVAL; + vma = find_vma_exact(current->mm, addr); + if (!vma) + return (unsigned long) -EINVAL; - found: - if (vml->vma->vm_end != vml->vma->vm_start + old_len) + if (vma->vm_end != vma->vm_start + old_len) return (unsigned long) -EFAULT; - if (vml->vma->vm_flags & VM_MAYSHARE) + if (vma->vm_flags & VM_MAYSHARE) return (unsigned long) -EPERM; if (new_len > kobjsize((void *) addr)) return (unsigned long) -ENOMEM; /* all checks complete - do it */ - vml->vma->vm_end = vml->vma->vm_start + new_len; + vma->vm_end = vma->vm_start + new_len; askedalloc -= old_len; askedalloc += new_len; - return vml->vma->vm_start; + return vma->vm_start; } -/* - * Look up the first VMA which satisfies addr < vm_end, NULL if none - */ -struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) +asmlinkage unsigned long sys_mremap(unsigned long addr, + unsigned long old_len, unsigned long new_len, + unsigned long flags, unsigned long new_addr) { - struct vm_list_struct *vml; - - for (vml = mm->context.vmlist; vml; vml = vml->next) - if (addr >= vml->vma->vm_start && addr < vml->vma->vm_end) - return vml->vma; + unsigned long ret; - return NULL; + down_write(¤t->mm->mmap_sem); + ret = do_mremap(addr, old_len, new_len, flags, new_addr); + up_write(¤t->mm->mmap_sem); + return ret; } -EXPORT_SYMBOL(find_vma); - struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags) { return NULL; } -struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr) -{ - return NULL; -} - int remap_pfn_range(struct vm_area_struct *vma, unsigned long from, unsigned long to, unsigned long size, pgprot_t prot) { @@ -1206,3 +1305,44 @@ struct page *filemap_nopage(struct vm_area_struct *area, BUG(); return NULL; } + +/* + * Access another process' address space. + * - source/target buffer must be kernel space + */ +int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write) +{ + struct vm_area_struct *vma; + struct mm_struct *mm; + + if (addr + len < addr) + return 0; + + mm = get_task_mm(tsk); + if (!mm) + return 0; + + down_read(&mm->mmap_sem); + + /* the access must start within one of the target process's mappings */ + vma = find_vma(mm, addr); + if (vma) { + /* don't overrun this mapping */ + if (addr + len >= vma->vm_end) + len = vma->vm_end - addr; + + /* only read or write mappings where it is permitted */ + if (write && vma->vm_flags & VM_MAYWRITE) + len -= copy_to_user((void *) addr, buf, len); + else if (!write && vma->vm_flags & VM_MAYREAD) + len -= copy_from_user(buf, (void *) addr, len); + else + len = 0; + } else { + len = 0; + } + + up_read(&mm->mmap_sem); + mmput(mm); + return len; +} diff --git a/mm/oom_kill.c b/mm/oom_kill.c index bada3d03119..223d9ccb7d6 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> @@ -204,16 +205,30 @@ static struct task_struct *select_bad_process(unsigned long *ppoints) do_posix_clock_monotonic_gettime(&uptime); do_each_thread(g, p) { unsigned long points; - int releasing; - /* skip kernel threads */ + /* + * skip kernel threads and tasks which have already released + * their mm. + */ if (!p->mm) continue; - /* skip the init task with pid == 1 */ - if (p->pid == 1) + /* skip the init task */ + if (is_init(p)) continue; /* + * This task already has access to memory reserves and is + * being killed. Don't allow any other task access to the + * memory reserve. + * + * Note: this may have a chance of deadlock if it gets + * blocked waiting for another task which itself is waiting + * for memory. Is there a better alternative? + */ + if (test_tsk_thread_flag(p, TIF_MEMDIE)) + return ERR_PTR(-1UL); + + /* * This is in the process of releasing memory so wait for it * to finish before killing some other task by mistake. * @@ -221,21 +236,16 @@ static struct task_struct *select_bad_process(unsigned long *ppoints) * go ahead if it is exiting: this will simply set TIF_MEMDIE, * which will allow it to gain access to memory reserves in * the process of exiting and releasing its resources. - * Otherwise we could get an OOM deadlock. + * Otherwise we could get an easy OOM deadlock. */ - releasing = test_tsk_thread_flag(p, TIF_MEMDIE) || - p->flags & PF_EXITING; - if (releasing) { - /* PF_DEAD tasks have already released their mm */ - if (p->flags & PF_DEAD) - continue; - if (p->flags & PF_EXITING && p == current) { - chosen = p; - *ppoints = ULONG_MAX; - break; - } - return ERR_PTR(-1UL); + if (p->flags & PF_EXITING) { + if (p != current) + return ERR_PTR(-1UL); + + chosen = p; + *ppoints = ULONG_MAX; } + if (p->oomkilladj == OOM_DISABLE) continue; @@ -245,6 +255,7 @@ static struct task_struct *select_bad_process(unsigned long *ppoints) *ppoints = points; } } while_each_thread(g, p); + return chosen; } @@ -253,27 +264,22 @@ static struct task_struct *select_bad_process(unsigned long *ppoints) * flag though it's unlikely that we select a process with CAP_SYS_RAW_IO * set. */ -static void __oom_kill_task(struct task_struct *p, const char *message) +static void __oom_kill_task(struct task_struct *p, int verbose) { - if (p->pid == 1) { + if (is_init(p)) { WARN_ON(1); printk(KERN_WARNING "tried to kill init!\n"); return; } - task_lock(p); - if (!p->mm || p->mm == &init_mm) { + if (!p->mm) { WARN_ON(1); printk(KERN_WARNING "tried to kill an mm-less task!\n"); - task_unlock(p); return; } - task_unlock(p); - if (message) { - printk(KERN_ERR "%s: Killed process %d (%s).\n", - message, p->pid, p->comm); - } + if (verbose) + printk(KERN_ERR "Killed process %d (%s)\n", p->pid, p->comm); /* * We give our sacrificial lamb high priority and access to @@ -286,7 +292,7 @@ static void __oom_kill_task(struct task_struct *p, const char *message) force_sig(SIGKILL, p); } -static int oom_kill_task(struct task_struct *p, const char *message) +static int oom_kill_task(struct task_struct *p) { struct mm_struct *mm; struct task_struct *g, *q; @@ -302,18 +308,28 @@ static int oom_kill_task(struct task_struct *p, const char *message) * However, this is of no concern to us. */ - if (mm == NULL || mm == &init_mm) + if (mm == NULL) return 1; - __oom_kill_task(p, message); + /* + * Don't kill the process if any threads are set to OOM_DISABLE + */ + do_each_thread(g, q) { + if (q->mm == mm && p->oomkilladj == OOM_DISABLE) + return 1; + } while_each_thread(g, q); + + __oom_kill_task(p, 1); + /* * kill all processes that share the ->mm (i.e. all threads), - * but are in a different thread group + * but are in a different thread group. Don't let them have access + * to memory reserves though, otherwise we might deplete all memory. */ - do_each_thread(g, q) + do_each_thread(g, q) { if (q->mm == mm && q->tgid != p->tgid) - __oom_kill_task(q, message); - while_each_thread(g, q); + force_sig(SIGKILL, p); + } while_each_thread(g, q); return 0; } @@ -329,21 +345,22 @@ static int oom_kill_process(struct task_struct *p, unsigned long points, * its children or threads, just set TIF_MEMDIE so it can die quickly */ if (p->flags & PF_EXITING) { - __oom_kill_task(p, NULL); + __oom_kill_task(p, 0); return 0; } - printk(KERN_ERR "Out of Memory: Kill process %d (%s) score %li" - " and children.\n", p->pid, p->comm, points); + printk(KERN_ERR "%s: kill process %d (%s) score %li or a child\n", + message, p->pid, p->comm, points); + /* Try to kill a child first */ list_for_each(tsk, &p->children) { c = list_entry(tsk, struct task_struct, sibling); if (c->mm == p->mm) continue; - if (!oom_kill_task(c, message)) + if (!oom_kill_task(c)) return 0; } - return oom_kill_task(p, message); + return oom_kill_task(p); } static BLOCKING_NOTIFIER_HEAD(oom_notify_list); diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 555752907dc..237107c1b08 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1,5 +1,5 @@ /* - * mm/page-writeback.c. + * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. * @@ -21,6 +21,7 @@ #include <linux/writeback.h> #include <linux/init.h> #include <linux/backing-dev.h> +#include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/mpage.h> #include <linux/rmap.h> @@ -30,6 +31,8 @@ #include <linux/sysctl.h> #include <linux/cpu.h> #include <linux/syscalls.h> +#include <linux/buffer_head.h> +#include <linux/pagevec.h> /* * The maximum number of pages to writeout in a single bdflush/kupdate @@ -46,7 +49,6 @@ */ static long ratelimit_pages = 32; -static long total_pages; /* The total number of pages in the machine. */ static int dirty_exceeded __cacheline_aligned_in_smp; /* Dirty mem may be over limit */ /* @@ -126,7 +128,7 @@ get_dirty_limits(long *pbackground, long *pdirty, int unmapped_ratio; long background; long dirty; - unsigned long available_memory = total_pages; + unsigned long available_memory = vm_total_pages; struct task_struct *tsk; #ifdef CONFIG_HIGHMEM @@ -141,7 +143,7 @@ get_dirty_limits(long *pbackground, long *pdirty, unmapped_ratio = 100 - ((global_page_state(NR_FILE_MAPPED) + global_page_state(NR_ANON_PAGES)) * 100) / - total_pages; + vm_total_pages; dirty_ratio = vm_dirty_ratio; if (dirty_ratio > unmapped_ratio / 2) @@ -221,7 +223,7 @@ 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) @@ -313,7 +315,7 @@ 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); } } @@ -350,7 +352,7 @@ 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; } @@ -421,7 +423,7 @@ 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 */ } @@ -502,9 +504,9 @@ void laptop_sync_completion(void) * will write six megabyte chunks, max. */ -static void set_ratelimit(void) +void writeback_set_ratelimit(void) { - ratelimit_pages = total_pages / (num_online_cpus() * 32); + ratelimit_pages = vm_total_pages / (num_online_cpus() * 32); if (ratelimit_pages < 16) ratelimit_pages = 16; if (ratelimit_pages * PAGE_CACHE_SIZE > 4096 * 1024) @@ -514,7 +516,7 @@ static void set_ratelimit(void) static int __cpuinit ratelimit_handler(struct notifier_block *self, unsigned long u, void *v) { - set_ratelimit(); + writeback_set_ratelimit(); return 0; } @@ -533,9 +535,7 @@ void __init page_writeback_init(void) long buffer_pages = nr_free_buffer_pages(); long correction; - total_pages = nr_free_pagecache_pages(); - - correction = (100 * 4 * buffer_pages) / total_pages; + correction = (100 * 4 * buffer_pages) / vm_total_pages; if (correction < 100) { dirty_background_ratio *= correction; @@ -549,10 +549,143 @@ void __init page_writeback_init(void) vm_dirty_ratio = 1; } mod_timer(&wb_timer, jiffies + dirty_writeback_interval); - set_ratelimit(); + writeback_set_ratelimit(); register_cpu_notifier(&ratelimit_nb); } +/** + * generic_writepages - walk the list of dirty pages of the given + * address space and writepage() all of them. + * + * @mapping: address space structure to write + * @wbc: subtract the number of written pages from *@wbc->nr_to_write + * + * This is a library function, which implements the writepages() + * address_space_operation. + * + * If a page is already under I/O, generic_writepages() skips it, even + * if it's dirty. This is desirable behaviour for memory-cleaning writeback, + * but it is INCORRECT for data-integrity system calls such as fsync(). fsync() + * and msync() need to guarantee that all the data which was dirty at the time + * the call was made get new I/O started against them. If wbc->sync_mode is + * WB_SYNC_ALL then we were called for data integrity and we must wait for + * existing IO to complete. + * + * Derived from mpage_writepages() - if you fix this you should check that + * also! + */ +int generic_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + struct backing_dev_info *bdi = mapping->backing_dev_info; + int ret = 0; + int done = 0; + int (*writepage)(struct page *page, struct writeback_control *wbc); + struct pagevec pvec; + int nr_pages; + pgoff_t index; + pgoff_t end; /* Inclusive */ + int scanned = 0; + int range_whole = 0; + + if (wbc->nonblocking && bdi_write_congested(bdi)) { + wbc->encountered_congestion = 1; + return 0; + } + + writepage = mapping->a_ops->writepage; + + /* deal with chardevs and other special file */ + if (!writepage) + return 0; + + pagevec_init(&pvec, 0); + if (wbc->range_cyclic) { + index = mapping->writeback_index; /* Start from prev offset */ + end = -1; + } else { + index = wbc->range_start >> PAGE_CACHE_SHIFT; + end = wbc->range_end >> PAGE_CACHE_SHIFT; + if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) + range_whole = 1; + scanned = 1; + } +retry: + while (!done && (index <= end) && + (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, + PAGECACHE_TAG_DIRTY, + min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) { + unsigned i; + + scanned = 1; + for (i = 0; i < nr_pages; i++) { + struct page *page = pvec.pages[i]; + + /* + * At this point we hold neither mapping->tree_lock nor + * lock on the page itself: the page may be truncated or + * invalidated (changing page->mapping to NULL), or even + * swizzled back from swapper_space to tmpfs file + * mapping + */ + lock_page(page); + + if (unlikely(page->mapping != mapping)) { + unlock_page(page); + continue; + } + + if (!wbc->range_cyclic && page->index > end) { + done = 1; + unlock_page(page); + continue; + } + + if (wbc->sync_mode != WB_SYNC_NONE) + wait_on_page_writeback(page); + + if (PageWriteback(page) || + !clear_page_dirty_for_io(page)) { + unlock_page(page); + continue; + } + + ret = (*writepage)(page, wbc); + if (ret) { + if (ret == -ENOSPC) + set_bit(AS_ENOSPC, &mapping->flags); + else + set_bit(AS_EIO, &mapping->flags); + } + + if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE)) + unlock_page(page); + if (ret || (--(wbc->nr_to_write) <= 0)) + done = 1; + if (wbc->nonblocking && bdi_write_congested(bdi)) { + wbc->encountered_congestion = 1; + done = 1; + } + } + pagevec_release(&pvec); + cond_resched(); + } + if (!scanned && !done) { + /* + * We hit the last page and there is more work to be done: wrap + * back to the start of the file + */ + scanned = 1; + index = 0; + goto retry; + } + if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) + mapping->writeback_index = index; + return ret; +} + +EXPORT_SYMBOL(generic_writepages); + int do_writepages(struct address_space *mapping, struct writeback_control *wbc) { int ret; @@ -629,23 +762,24 @@ int __set_page_dirty_nobuffers(struct page *page) struct address_space *mapping = page_mapping(page); struct address_space *mapping2; - if (mapping) { - write_lock_irq(&mapping->tree_lock); - mapping2 = page_mapping(page); - if (mapping2) { /* Race with truncate? */ - BUG_ON(mapping2 != mapping); - if (mapping_cap_account_dirty(mapping)) - __inc_zone_page_state(page, - NR_FILE_DIRTY); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), PAGECACHE_TAG_DIRTY); - } - write_unlock_irq(&mapping->tree_lock); - if (mapping->host) { - /* !PageAnon && !swapper_space */ - __mark_inode_dirty(mapping->host, - I_DIRTY_PAGES); + if (!mapping) + return 1; + + write_lock_irq(&mapping->tree_lock); + mapping2 = page_mapping(page); + if (mapping2) { /* Race with truncate? */ + BUG_ON(mapping2 != mapping); + if (mapping_cap_account_dirty(mapping)) { + __inc_zone_page_state(page, NR_FILE_DIRTY); + task_io_account_write(PAGE_CACHE_SIZE); } + radix_tree_tag_set(&mapping->page_tree, + page_index(page), PAGECACHE_TAG_DIRTY); + } + write_unlock_irq(&mapping->tree_lock); + if (mapping->host) { + /* !PageAnon && !swapper_space */ + __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); } return 1; } @@ -675,9 +809,11 @@ int fastcall set_page_dirty(struct page *page) if (likely(mapping)) { int (*spd)(struct page *) = mapping->a_ops->set_page_dirty; - if (spd) - return (*spd)(page); - return __set_page_dirty_buffers(page); +#ifdef CONFIG_BLOCK + if (!spd) + spd = __set_page_dirty_buffers; +#endif + return (*spd)(page); } if (!PageDirty(page)) { if (!TestSetPageDirty(page)) @@ -717,27 +853,26 @@ int test_clear_page_dirty(struct page *page) struct address_space *mapping = page_mapping(page); unsigned long flags; - if (mapping) { - write_lock_irqsave(&mapping->tree_lock, flags); - if (TestClearPageDirty(page)) { - radix_tree_tag_clear(&mapping->page_tree, - page_index(page), - PAGECACHE_TAG_DIRTY); - write_unlock_irqrestore(&mapping->tree_lock, flags); - /* - * We can continue to use `mapping' here because the - * page is locked, which pins the address_space - */ - if (mapping_cap_account_dirty(mapping)) { - page_mkclean(page); - dec_zone_page_state(page, NR_FILE_DIRTY); - } - return 1; - } + if (!mapping) + return TestClearPageDirty(page); + + write_lock_irqsave(&mapping->tree_lock, flags); + if (TestClearPageDirty(page)) { + radix_tree_tag_clear(&mapping->page_tree, + page_index(page), PAGECACHE_TAG_DIRTY); write_unlock_irqrestore(&mapping->tree_lock, flags); - return 0; + /* + * We can continue to use `mapping' here because the + * page is locked, which pins the address_space + */ + if (mapping_cap_account_dirty(mapping)) { + page_mkclean(page); + dec_zone_page_state(page, NR_FILE_DIRTY); + } + return 1; } - return TestClearPageDirty(page); + write_unlock_irqrestore(&mapping->tree_lock, flags); + return 0; } EXPORT_SYMBOL(test_clear_page_dirty); @@ -759,17 +894,17 @@ int clear_page_dirty_for_io(struct page *page) { struct address_space *mapping = page_mapping(page); - if (mapping) { - if (TestClearPageDirty(page)) { - if (mapping_cap_account_dirty(mapping)) { - page_mkclean(page); - dec_zone_page_state(page, NR_FILE_DIRTY); - } - return 1; + if (!mapping) + return TestClearPageDirty(page); + + if (TestClearPageDirty(page)) { + if (mapping_cap_account_dirty(mapping)) { + page_mkclean(page); + dec_zone_page_state(page, NR_FILE_DIRTY); } - return 0; + return 1; } - return TestClearPageDirty(page); + return 0; } EXPORT_SYMBOL(clear_page_dirty_for_io); @@ -822,15 +957,6 @@ 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 9810f0a60db..e6b17b2989e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -37,6 +37,10 @@ #include <linux/vmalloc.h> #include <linux/mempolicy.h> #include <linux/stop_machine.h> +#include <linux/sort.h> +#include <linux/pfn.h> +#include <linux/backing-dev.h> +#include <linux/fault-inject.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -80,14 +84,7 @@ int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES-1] = { EXPORT_SYMBOL(totalram_pages); -/* - * Used by page_zone() to look up the address of the struct zone whose - * id is encoded in the upper bits of page->flags - */ -struct zone *zone_table[1 << ZONETABLE_SHIFT] __read_mostly; -EXPORT_SYMBOL(zone_table); - -static char *zone_names[MAX_NR_ZONES] = { +static char * const zone_names[MAX_NR_ZONES] = { "DMA", #ifdef CONFIG_ZONE_DMA32 "DMA32", @@ -102,6 +99,38 @@ int min_free_kbytes = 1024; unsigned long __meminitdata nr_kernel_pages; unsigned long __meminitdata nr_all_pages; +static unsigned long __initdata dma_reserve; + +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP + /* + * MAX_ACTIVE_REGIONS determines the maxmimum number of distinct + * ranges of memory (RAM) that may be registered with add_active_range(). + * Ranges passed to add_active_range() will be merged if possible + * so the number of times add_active_range() can be called is + * related to the number of nodes and the number of holes + */ + #ifdef CONFIG_MAX_ACTIVE_REGIONS + /* Allow an architecture to set MAX_ACTIVE_REGIONS to save memory */ + #define MAX_ACTIVE_REGIONS CONFIG_MAX_ACTIVE_REGIONS + #else + #if MAX_NUMNODES >= 32 + /* If there can be many nodes, allow up to 50 holes per node */ + #define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50) + #else + /* By default, allow up to 256 distinct regions */ + #define MAX_ACTIVE_REGIONS 256 + #endif + #endif + + struct node_active_region __initdata early_node_map[MAX_ACTIVE_REGIONS]; + int __initdata nr_nodemap_entries; + unsigned long __initdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES]; + unsigned long __initdata arch_zone_highest_possible_pfn[MAX_NR_ZONES]; +#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE + unsigned long __initdata node_boundary_start_pfn[MAX_NUMNODES]; + unsigned long __initdata node_boundary_end_pfn[MAX_NUMNODES]; +#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */ +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ #ifdef CONFIG_DEBUG_VM static int page_outside_zone_boundaries(struct zone *zone, struct page *page) @@ -202,7 +231,7 @@ static void prep_compound_page(struct page *page, unsigned long order) int i; int nr_pages = 1 << order; - page[1].lru.next = (void *)free_compound_page; /* set dtor */ + set_compound_page_dtor(page, free_compound_page); page[1].lru.prev = (void *)order; for (i = 0; i < nr_pages; i++) { struct page *p = page + i; @@ -451,7 +480,7 @@ static void free_one_page(struct zone *zone, struct page *page, int order) spin_lock(&zone->lock); zone->all_unreclaimable = 0; zone->pages_scanned = 0; - __free_one_page(page, zone ,order); + __free_one_page(page, zone, order); spin_unlock(&zone->lock); } @@ -461,17 +490,16 @@ 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); @@ -571,6 +599,8 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) 1 << PG_checked | 1 << PG_mappedtodisk); set_page_private(page, 0); set_page_refcounted(page); + + arch_alloc_page(page, order); kernel_map_pages(page, 1 << order, 1); if (gfp_flags & __GFP_ZERO) @@ -656,9 +686,15 @@ void drain_node_pages(int nodeid) pcp = &pset->pcp[i]; if (pcp->count) { + int to_drain; + local_irq_save(flags); - free_pages_bulk(zone, pcp->count, &pcp->list, 0); - pcp->count = 0; + if (pcp->count >= pcp->batch) + to_drain = pcp->batch; + else + to_drain = pcp->count; + free_pages_bulk(zone, to_drain, &pcp->list, 0); + pcp->count -= to_drain; local_irq_restore(flags); } } @@ -666,7 +702,6 @@ void drain_node_pages(int nodeid) } #endif -#if defined(CONFIG_PM) || defined(CONFIG_HOTPLUG_CPU) static void __drain_pages(unsigned int cpu) { unsigned long flags; @@ -688,7 +723,6 @@ static void __drain_pages(unsigned int cpu) } } } -#endif /* CONFIG_PM || CONFIG_HOTPLUG_CPU */ #ifdef CONFIG_PM @@ -747,13 +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]; @@ -818,7 +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; @@ -858,6 +893,91 @@ failed: #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ +#ifdef CONFIG_FAIL_PAGE_ALLOC + +static struct fail_page_alloc_attr { + struct fault_attr attr; + + u32 ignore_gfp_highmem; + u32 ignore_gfp_wait; + +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + + struct dentry *ignore_gfp_highmem_file; + struct dentry *ignore_gfp_wait_file; + +#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ + +} fail_page_alloc = { + .attr = FAULT_ATTR_INITIALIZER, + .ignore_gfp_wait = 1, + .ignore_gfp_highmem = 1, +}; + +static int __init setup_fail_page_alloc(char *str) +{ + return setup_fault_attr(&fail_page_alloc.attr, str); +} +__setup("fail_page_alloc=", setup_fail_page_alloc); + +static int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +{ + if (gfp_mask & __GFP_NOFAIL) + return 0; + if (fail_page_alloc.ignore_gfp_highmem && (gfp_mask & __GFP_HIGHMEM)) + return 0; + if (fail_page_alloc.ignore_gfp_wait && (gfp_mask & __GFP_WAIT)) + return 0; + + return should_fail(&fail_page_alloc.attr, 1 << order); +} + +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + +static int __init fail_page_alloc_debugfs(void) +{ + mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; + struct dentry *dir; + int err; + + err = init_fault_attr_dentries(&fail_page_alloc.attr, + "fail_page_alloc"); + if (err) + return err; + dir = fail_page_alloc.attr.dentries.dir; + + fail_page_alloc.ignore_gfp_wait_file = + debugfs_create_bool("ignore-gfp-wait", mode, dir, + &fail_page_alloc.ignore_gfp_wait); + + fail_page_alloc.ignore_gfp_highmem_file = + debugfs_create_bool("ignore-gfp-highmem", mode, dir, + &fail_page_alloc.ignore_gfp_highmem); + + if (!fail_page_alloc.ignore_gfp_wait_file || + !fail_page_alloc.ignore_gfp_highmem_file) { + err = -ENOMEM; + debugfs_remove(fail_page_alloc.ignore_gfp_wait_file); + debugfs_remove(fail_page_alloc.ignore_gfp_highmem_file); + cleanup_fault_attr_dentries(&fail_page_alloc.attr); + } + + return err; +} + +late_initcall(fail_page_alloc_debugfs); + +#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ + +#else /* CONFIG_FAIL_PAGE_ALLOC */ + +static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +{ + return 0; +} + +#endif /* CONFIG_FAIL_PAGE_ALLOC */ + /* * Return 1 if free pages are above 'mark'. This takes into account the order * of the allocation. @@ -866,7 +986,8 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark, int classzone_idx, int alloc_flags) { /* free_pages my go negative - that's OK */ - long min = mark, free_pages = z->free_pages - (1 << order) + 1; + unsigned long min = mark; + long free_pages = z->free_pages - (1 << order) + 1; int o; if (alloc_flags & ALLOC_HIGH) @@ -889,31 +1010,160 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark, return 1; } +#ifdef CONFIG_NUMA /* - * get_page_from_freeliest goes through the zonelist trying to allocate + * zlc_setup - Setup for "zonelist cache". Uses cached zone data to + * skip over zones that are not allowed by the cpuset, or that have + * been recently (in last second) found to be nearly full. See further + * comments in mmzone.h. Reduces cache footprint of zonelist scans + * that have to skip over alot of full or unallowed zones. + * + * If the zonelist cache is present in the passed in zonelist, then + * returns a pointer to the allowed node mask (either the current + * tasks mems_allowed, or node_online_map.) + * + * If the zonelist cache is not available for this zonelist, does + * nothing and returns NULL. + * + * If the fullzones BITMAP in the zonelist cache is stale (more than + * a second since last zap'd) then we zap it out (clear its bits.) + * + * We hold off even calling zlc_setup, until after we've checked the + * first zone in the zonelist, on the theory that most allocations will + * be satisfied from that first zone, so best to examine that zone as + * quickly as we can. + */ +static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags) +{ + struct zonelist_cache *zlc; /* cached zonelist speedup info */ + nodemask_t *allowednodes; /* zonelist_cache approximation */ + + zlc = zonelist->zlcache_ptr; + if (!zlc) + return NULL; + + if (jiffies - zlc->last_full_zap > 1 * HZ) { + bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); + zlc->last_full_zap = jiffies; + } + + allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ? + &cpuset_current_mems_allowed : + &node_online_map; + return allowednodes; +} + +/* + * Given 'z' scanning a zonelist, run a couple of quick checks to see + * if it is worth looking at further for free memory: + * 1) Check that the zone isn't thought to be full (doesn't have its + * bit set in the zonelist_cache fullzones BITMAP). + * 2) Check that the zones node (obtained from the zonelist_cache + * z_to_n[] mapping) is allowed in the passed in allowednodes mask. + * Return true (non-zero) if zone is worth looking at further, or + * else return false (zero) if it is not. + * + * This check -ignores- the distinction between various watermarks, + * such as GFP_HIGH, GFP_ATOMIC, PF_MEMALLOC, ... If a zone is + * found to be full for any variation of these watermarks, it will + * be considered full for up to one second by all requests, unless + * we are so low on memory on all allowed nodes that we are forced + * into the second scan of the zonelist. + * + * In the second scan we ignore this zonelist cache and exactly + * apply the watermarks to all zones, even it is slower to do so. + * We are low on memory in the second scan, and should leave no stone + * unturned looking for a free page. + */ +static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z, + nodemask_t *allowednodes) +{ + struct zonelist_cache *zlc; /* cached zonelist speedup info */ + int i; /* index of *z in zonelist zones */ + int n; /* node that zone *z is on */ + + zlc = zonelist->zlcache_ptr; + if (!zlc) + return 1; + + i = z - zonelist->zones; + n = zlc->z_to_n[i]; + + /* This zone is worth trying if it is allowed but not full */ + return node_isset(n, *allowednodes) && !test_bit(i, zlc->fullzones); +} + +/* + * Given 'z' scanning a zonelist, set the corresponding bit in + * zlc->fullzones, so that subsequent attempts to allocate a page + * from that zone don't waste time re-examining it. + */ +static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z) +{ + struct zonelist_cache *zlc; /* cached zonelist speedup info */ + int i; /* index of *z in zonelist zones */ + + zlc = zonelist->zlcache_ptr; + if (!zlc) + return; + + i = z - zonelist->zones; + + set_bit(i, zlc->fullzones); +} + +#else /* CONFIG_NUMA */ + +static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags) +{ + return NULL; +} + +static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zone **z, + nodemask_t *allowednodes) +{ + return 1; +} + +static void zlc_mark_zone_full(struct zonelist *zonelist, struct zone **z) +{ +} +#endif /* CONFIG_NUMA */ + +/* + * get_page_from_freelist goes through the zonelist trying to allocate * a page. */ static struct page * get_page_from_freelist(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, int alloc_flags) { - struct zone **z = zonelist->zones; + struct zone **z; struct page *page = NULL; - int classzone_idx = zone_idx(*z); + int classzone_idx = zone_idx(zonelist->zones[0]); struct zone *zone; + nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */ + int zlc_active = 0; /* set if using zonelist_cache */ + int did_zlc_setup = 0; /* just call zlc_setup() one time */ +zonelist_scan: /* - * Go through the zonelist once, looking for a zone with enough free. + * Scan zonelist, looking for a zone with enough free. * See also cpuset_zone_allowed() comment in kernel/cpuset.c. */ + z = zonelist->zones; + do { + if (NUMA_BUILD && zlc_active && + !zlc_zone_worth_trying(zonelist, z, allowednodes)) + continue; zone = *z; - if (unlikely((gfp_mask & __GFP_THISNODE) && + if (unlikely(NUMA_BUILD && (gfp_mask & __GFP_THISNODE) && zone->zone_pgdat != zonelist->zones[0]->zone_pgdat)) break; if ((alloc_flags & ALLOC_CPUSET) && - !cpuset_zone_allowed(zone, gfp_mask)) - continue; + !cpuset_zone_allowed(zone, gfp_mask)) + goto try_next_zone; if (!(alloc_flags & ALLOC_NO_WATERMARKS)) { unsigned long mark; @@ -923,18 +1173,34 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, mark = zone->pages_low; else mark = zone->pages_high; - if (!zone_watermark_ok(zone , order, mark, - classzone_idx, alloc_flags)) + if (!zone_watermark_ok(zone, order, mark, + classzone_idx, alloc_flags)) { if (!zone_reclaim_mode || !zone_reclaim(zone, gfp_mask, order)) - continue; + goto this_zone_full; + } } page = buffered_rmqueue(zonelist, zone, order, gfp_mask); - if (page) { + if (page) break; +this_zone_full: + if (NUMA_BUILD) + zlc_mark_zone_full(zonelist, z); +try_next_zone: + if (NUMA_BUILD && !did_zlc_setup) { + /* we do zlc_setup after the first zone is tried */ + allowednodes = zlc_setup(zonelist, alloc_flags); + zlc_active = 1; + did_zlc_setup = 1; } } while (*(++z) != NULL); + + if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) { + /* Disable zlc cache for second zonelist scan */ + zlc_active = 0; + goto zonelist_scan; + } return page; } @@ -956,6 +1222,9 @@ __alloc_pages(gfp_t gfp_mask, unsigned int order, might_sleep_if(wait); + if (should_fail_alloc_page(gfp_mask, order)) + return NULL; + restart: z = zonelist->zones; /* the list of zones suitable for gfp_mask */ @@ -969,9 +1238,19 @@ restart: if (page) goto got_pg; - do { + /* + * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and + * __GFP_NOWARN set) should not cause reclaim since the subsystem + * (f.e. slab) using GFP_THISNODE may choose to trigger reclaim + * using a larger set of nodes after it has established that the + * allowed per node queues are empty and that nodes are + * over allocated. + */ + if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE) + goto nopage; + + for (z = zonelist->zones; *z; z++) wakeup_kswapd(*z, order); - } while (*(++z)); /* * OK, we're below the kswapd watermark and have kicked background @@ -1005,6 +1284,7 @@ restart: /* This allocation should allow future memory freeing. */ +rebalance: if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE))) && !in_interrupt()) { if (!(gfp_mask & __GFP_NOMEMALLOC)) { @@ -1015,7 +1295,7 @@ 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; } } @@ -1026,7 +1306,6 @@ nofail_alloc: if (!wait) goto nopage; -rebalance: cond_resched(); /* We now go into synchronous reclaim */ @@ -1078,7 +1357,7 @@ rebalance: do_retry = 1; } if (do_retry) { - blk_congestion_wait(WRITE, HZ/50); + congestion_wait(WRITE, HZ/50); goto rebalance; } @@ -1222,14 +1501,12 @@ unsigned int nr_free_pagecache_pages(void) { return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER)); } -#ifdef CONFIG_NUMA -static void show_node(struct zone *zone) + +static inline void show_node(struct zone *zone) { - printk("Node %ld ", zone_to_nid(zone)); + if (NUMA_BUILD) + printk("Node %d ", zone_to_nid(zone)); } -#else -#define show_node(zone) do { } while (0) -#endif void si_meminfo(struct sysinfo *val) { @@ -1271,34 +1548,30 @@ void si_meminfo_node(struct sysinfo *val, int nid) */ void show_free_areas(void) { - int cpu, temperature; + int cpu; unsigned long active; unsigned long inactive; unsigned long free; struct zone *zone; for_each_zone(zone) { - show_node(zone); - printk("%s per-cpu:", zone->name); - - if (!populated_zone(zone)) { - printk(" empty\n"); + if (!populated_zone(zone)) continue; - } else - printk("\n"); + + show_node(zone); + printk("%s per-cpu:\n", zone->name); for_each_online_cpu(cpu) { struct per_cpu_pageset *pageset; pageset = zone_pcp(zone, cpu); - for (temperature = 0; temperature < 2; temperature++) - printk("cpu %d %s: high %d, batch %d used:%d\n", - cpu, - temperature ? "cold" : "hot", - pageset->pcp[temperature].high, - pageset->pcp[temperature].batch, - pageset->pcp[temperature].count); + printk("CPU %4d: Hot: hi:%5d, btch:%4d usd:%4d " + "Cold: hi:%5d, btch:%4d usd:%4d\n", + cpu, pageset->pcp[0].high, + pageset->pcp[0].batch, pageset->pcp[0].count, + pageset->pcp[1].high, pageset->pcp[1].batch, + pageset->pcp[1].count); } } @@ -1320,6 +1593,9 @@ void show_free_areas(void) for_each_zone(zone) { int i; + if (!populated_zone(zone)) + continue; + show_node(zone); printk("%s" " free:%lukB" @@ -1352,12 +1628,11 @@ void show_free_areas(void) for_each_zone(zone) { unsigned long nr[MAX_ORDER], flags, order, total = 0; + if (!populated_zone(zone)) + continue; + show_node(zone); printk("%s: ", zone->name); - if (!populated_zone(zone)) { - printk("empty\n"); - continue; - } spin_lock_irqsave(&zone->lock, flags); for (order = 0; order < MAX_ORDER; order++) { @@ -1510,6 +1785,24 @@ static void __meminit build_zonelists(pg_data_t *pgdat) } } +/* Construct the zonelist performance cache - see further mmzone.h */ +static void __meminit build_zonelist_cache(pg_data_t *pgdat) +{ + int i; + + for (i = 0; i < MAX_NR_ZONES; i++) { + struct zonelist *zonelist; + struct zonelist_cache *zlc; + struct zone **z; + + zonelist = pgdat->node_zonelists + i; + zonelist->zlcache_ptr = zlc = &zonelist->zlcache; + bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST); + for (z = zonelist->zones; *z; z++) + zlc->z_to_n[z - zonelist->zones] = zone_to_nid(*z); + } +} + #else /* CONFIG_NUMA */ static void __meminit build_zonelists(pg_data_t *pgdat) @@ -1547,21 +1840,33 @@ static void __meminit build_zonelists(pg_data_t *pgdat) } } +/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */ +static void __meminit build_zonelist_cache(pg_data_t *pgdat) +{ + int i; + + for (i = 0; i < MAX_NR_ZONES; i++) + pgdat->node_zonelists[i].zlcache_ptr = NULL; +} + #endif /* CONFIG_NUMA */ /* return values int ....just for stop_machine_run() */ static int __meminit __build_all_zonelists(void *dummy) { int nid; - for_each_online_node(nid) + + for_each_online_node(nid) { build_zonelists(NODE_DATA(nid)); + build_zonelist_cache(NODE_DATA(nid)); + } return 0; } void __meminit build_all_zonelists(void) { if (system_state == SYSTEM_BOOTING) { - __build_all_zonelists(0); + __build_all_zonelists(NULL); cpuset_init_current_mems_allowed(); } else { /* we have to stop all cpus to guaranntee there is no user @@ -1642,25 +1947,6 @@ static inline unsigned long wait_table_bits(unsigned long size) #define LONG_ALIGN(x) (((x)+(sizeof(long))-1)&~((sizeof(long))-1)) -static void __init calculate_zone_totalpages(struct pglist_data *pgdat, - unsigned long *zones_size, unsigned long *zholes_size) -{ - unsigned long realtotalpages, totalpages = 0; - enum zone_type i; - - for (i = 0; i < MAX_NR_ZONES; i++) - totalpages += zones_size[i]; - pgdat->node_spanned_pages = totalpages; - - realtotalpages = totalpages; - if (zholes_size) - for (i = 0; i < MAX_NR_ZONES; i++) - realtotalpages -= zholes_size[i]; - pgdat->node_present_pages = realtotalpages; - printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, realtotalpages); -} - - /* * Initially all pages are reserved - free ones are freed * up by free_all_bootmem() once the early boot process is @@ -1676,6 +1962,8 @@ 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); @@ -1700,20 +1988,6 @@ void zone_init_free_lists(struct pglist_data *pgdat, struct zone *zone, } } -#define ZONETABLE_INDEX(x, zone_nr) ((x << ZONES_SHIFT) | zone_nr) -void zonetable_add(struct zone *zone, int nid, enum zone_type zid, - unsigned long pfn, unsigned long size) -{ - unsigned long snum = pfn_to_section_nr(pfn); - unsigned long end = pfn_to_section_nr(pfn + size); - - if (FLAGS_HAS_NODE) - zone_table[ZONETABLE_INDEX(nid, zid)] = zone; - else - for (; snum <= end; snum++) - zone_table[ZONETABLE_INDEX(snum, zid)] = zone; -} - #ifndef __HAVE_ARCH_MEMMAP_INIT #define memmap_init(size, nid, zone, start_pfn) \ memmap_init_zone((size), (nid), (zone), (start_pfn)) @@ -1818,6 +2092,9 @@ static int __cpuinit process_zones(int cpu) for_each_zone(zone) { + if (!populated_zone(zone)) + continue; + zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset), GFP_KERNEL, cpu_to_node(cpu)); if (!zone_pcp(zone, cpu)) @@ -1863,16 +2140,16 @@ static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb, int ret = NOTIFY_OK; switch (action) { - case CPU_UP_PREPARE: - if (process_zones(cpu)) - ret = NOTIFY_BAD; - break; - case CPU_UP_CANCELED: - case CPU_DEAD: - free_zone_pagesets(cpu); - break; - default: - break; + case CPU_UP_PREPARE: + if (process_zones(cpu)) + ret = NOTIFY_BAD; + break; + case CPU_UP_CANCELED: + case CPU_DEAD: + free_zone_pagesets(cpu); + break; + default: + break; } return ret; } @@ -1977,6 +2254,349 @@ __meminit int init_currently_empty_zone(struct zone *zone, return 0; } +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +/* + * Basic iterator support. Return the first range of PFNs for a node + * Note: nid == MAX_NUMNODES returns first region regardless of node + */ +static int __init first_active_region_index_in_nid(int nid) +{ + int i; + + for (i = 0; i < nr_nodemap_entries; i++) + if (nid == MAX_NUMNODES || early_node_map[i].nid == nid) + return i; + + return -1; +} + +/* + * Basic iterator support. Return the next active range of PFNs for a node + * Note: nid == MAX_NUMNODES returns next region regardles of node + */ +static int __init next_active_region_index_in_nid(int index, int nid) +{ + for (index = index + 1; index < nr_nodemap_entries; index++) + if (nid == MAX_NUMNODES || early_node_map[index].nid == nid) + return index; + + return -1; +} + +#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID +/* + * Required by SPARSEMEM. Given a PFN, return what node the PFN is on. + * Architectures may implement their own version but if add_active_range() + * was used and there are no special requirements, this is a convenient + * alternative + */ +int __init early_pfn_to_nid(unsigned long pfn) +{ + int i; + + for (i = 0; i < nr_nodemap_entries; i++) { + unsigned long start_pfn = early_node_map[i].start_pfn; + unsigned long end_pfn = early_node_map[i].end_pfn; + + if (start_pfn <= pfn && pfn < end_pfn) + return early_node_map[i].nid; + } + + return 0; +} +#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */ + +/* Basic iterator support to walk early_node_map[] */ +#define for_each_active_range_index_in_nid(i, nid) \ + for (i = first_active_region_index_in_nid(nid); i != -1; \ + i = next_active_region_index_in_nid(i, nid)) + +/** + * free_bootmem_with_active_regions - Call free_bootmem_node for each active range + * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed. + * @max_low_pfn: The highest PFN that will be passed to free_bootmem_node + * + * If an architecture guarantees that all ranges registered with + * add_active_ranges() contain no holes and may be freed, this + * this function may be used instead of calling free_bootmem() manually. + */ +void __init free_bootmem_with_active_regions(int nid, + unsigned long max_low_pfn) +{ + int i; + + for_each_active_range_index_in_nid(i, nid) { + unsigned long size_pages = 0; + unsigned long end_pfn = early_node_map[i].end_pfn; + + if (early_node_map[i].start_pfn >= max_low_pfn) + continue; + + if (end_pfn > max_low_pfn) + end_pfn = max_low_pfn; + + size_pages = end_pfn - early_node_map[i].start_pfn; + free_bootmem_node(NODE_DATA(early_node_map[i].nid), + PFN_PHYS(early_node_map[i].start_pfn), + size_pages << PAGE_SHIFT); + } +} + +/** + * sparse_memory_present_with_active_regions - Call memory_present for each active range + * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used. + * + * If an architecture guarantees that all ranges registered with + * add_active_ranges() contain no holes and may be freed, this + * function may be used instead of calling memory_present() manually. + */ +void __init sparse_memory_present_with_active_regions(int nid) +{ + int i; + + for_each_active_range_index_in_nid(i, nid) + memory_present(early_node_map[i].nid, + early_node_map[i].start_pfn, + early_node_map[i].end_pfn); +} + +/** + * push_node_boundaries - Push node boundaries to at least the requested boundary + * @nid: The nid of the node to push the boundary for + * @start_pfn: The start pfn of the node + * @end_pfn: The end pfn of the node + * + * In reserve-based hot-add, mem_map is allocated that is unused until hotadd + * time. Specifically, on x86_64, SRAT will report ranges that can potentially + * be hotplugged even though no physical memory exists. This function allows + * an arch to push out the node boundaries so mem_map is allocated that can + * be used later. + */ +#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE +void __init push_node_boundaries(unsigned int nid, + unsigned long start_pfn, unsigned long end_pfn) +{ + printk(KERN_DEBUG "Entering push_node_boundaries(%u, %lu, %lu)\n", + nid, start_pfn, end_pfn); + + /* Initialise the boundary for this node if necessary */ + if (node_boundary_end_pfn[nid] == 0) + node_boundary_start_pfn[nid] = -1UL; + + /* Update the boundaries */ + if (node_boundary_start_pfn[nid] > start_pfn) + node_boundary_start_pfn[nid] = start_pfn; + if (node_boundary_end_pfn[nid] < end_pfn) + node_boundary_end_pfn[nid] = end_pfn; +} + +/* If necessary, push the node boundary out for reserve hotadd */ +static void __init account_node_boundary(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn) +{ + printk(KERN_DEBUG "Entering account_node_boundary(%u, %lu, %lu)\n", + nid, *start_pfn, *end_pfn); + + /* Return if boundary information has not been provided */ + if (node_boundary_end_pfn[nid] == 0) + return; + + /* Check the boundaries and update if necessary */ + if (node_boundary_start_pfn[nid] < *start_pfn) + *start_pfn = node_boundary_start_pfn[nid]; + if (node_boundary_end_pfn[nid] > *end_pfn) + *end_pfn = node_boundary_end_pfn[nid]; +} +#else +void __init push_node_boundaries(unsigned int nid, + unsigned long start_pfn, unsigned long end_pfn) {} + +static void __init account_node_boundary(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn) {} +#endif + + +/** + * get_pfn_range_for_nid - Return the start and end page frames for a node + * @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned. + * @start_pfn: Passed by reference. On return, it will have the node start_pfn. + * @end_pfn: Passed by reference. On return, it will have the node end_pfn. + * + * It returns the start and end page frame of a node based on information + * provided by an arch calling add_active_range(). If called for a node + * with no available memory, a warning is printed and the start and end + * PFNs will be 0. + */ +void __init get_pfn_range_for_nid(unsigned int nid, + unsigned long *start_pfn, unsigned long *end_pfn) +{ + int i; + *start_pfn = -1UL; + *end_pfn = 0; + + for_each_active_range_index_in_nid(i, nid) { + *start_pfn = min(*start_pfn, early_node_map[i].start_pfn); + *end_pfn = max(*end_pfn, early_node_map[i].end_pfn); + } + + if (*start_pfn == -1UL) { + printk(KERN_WARNING "Node %u active with no memory\n", nid); + *start_pfn = 0; + } + + /* Push the node boundaries out if requested */ + account_node_boundary(nid, start_pfn, end_pfn); +} + +/* + * Return the number of pages a zone spans in a node, including holes + * present_pages = zone_spanned_pages_in_node() - zone_absent_pages_in_node() + */ +unsigned long __init zone_spanned_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *ignored) +{ + unsigned long node_start_pfn, node_end_pfn; + unsigned long zone_start_pfn, zone_end_pfn; + + /* Get the start and end of the node and zone */ + get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn); + zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type]; + zone_end_pfn = arch_zone_highest_possible_pfn[zone_type]; + + /* Check that this node has pages within the zone's required range */ + if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn) + return 0; + + /* Move the zone boundaries inside the node if necessary */ + zone_end_pfn = min(zone_end_pfn, node_end_pfn); + zone_start_pfn = max(zone_start_pfn, node_start_pfn); + + /* Return the spanned pages */ + return zone_end_pfn - zone_start_pfn; +} + +/* + * Return the number of holes in a range on a node. If nid is MAX_NUMNODES, + * then all holes in the requested range will be accounted for. + */ +unsigned long __init __absent_pages_in_range(int nid, + unsigned long range_start_pfn, + unsigned long range_end_pfn) +{ + int i = 0; + unsigned long prev_end_pfn = 0, hole_pages = 0; + unsigned long start_pfn; + + /* Find the end_pfn of the first active range of pfns in the node */ + i = first_active_region_index_in_nid(nid); + if (i == -1) + return 0; + + /* Account for ranges before physical memory on this node */ + if (early_node_map[i].start_pfn > range_start_pfn) + hole_pages = early_node_map[i].start_pfn - range_start_pfn; + + prev_end_pfn = early_node_map[i].start_pfn; + + /* Find all holes for the zone within the node */ + for (; i != -1; i = next_active_region_index_in_nid(i, nid)) { + + /* No need to continue if prev_end_pfn is outside the zone */ + if (prev_end_pfn >= range_end_pfn) + break; + + /* Make sure the end of the zone is not within the hole */ + start_pfn = min(early_node_map[i].start_pfn, range_end_pfn); + prev_end_pfn = max(prev_end_pfn, range_start_pfn); + + /* Update the hole size cound and move on */ + if (start_pfn > range_start_pfn) { + BUG_ON(prev_end_pfn > start_pfn); + hole_pages += start_pfn - prev_end_pfn; + } + prev_end_pfn = early_node_map[i].end_pfn; + } + + /* Account for ranges past physical memory on this node */ + if (range_end_pfn > prev_end_pfn) + hole_pages += range_end_pfn - + max(range_start_pfn, prev_end_pfn); + + return hole_pages; +} + +/** + * absent_pages_in_range - Return number of page frames in holes within a range + * @start_pfn: The start PFN to start searching for holes + * @end_pfn: The end PFN to stop searching for holes + * + * It returns the number of pages frames in memory holes within a range. + */ +unsigned long __init absent_pages_in_range(unsigned long start_pfn, + unsigned long end_pfn) +{ + return __absent_pages_in_range(MAX_NUMNODES, start_pfn, end_pfn); +} + +/* Return the number of page frames in holes in a zone on a node */ +unsigned long __init zone_absent_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *ignored) +{ + unsigned long node_start_pfn, node_end_pfn; + unsigned long zone_start_pfn, zone_end_pfn; + + get_pfn_range_for_nid(nid, &node_start_pfn, &node_end_pfn); + zone_start_pfn = max(arch_zone_lowest_possible_pfn[zone_type], + node_start_pfn); + zone_end_pfn = min(arch_zone_highest_possible_pfn[zone_type], + node_end_pfn); + + return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn); +} + +#else +static inline unsigned long zone_spanned_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *zones_size) +{ + return zones_size[zone_type]; +} + +static inline unsigned long zone_absent_pages_in_node(int nid, + unsigned long zone_type, + unsigned long *zholes_size) +{ + if (!zholes_size) + return 0; + + return zholes_size[zone_type]; +} + +#endif + +static void __init calculate_node_totalpages(struct pglist_data *pgdat, + unsigned long *zones_size, unsigned long *zholes_size) +{ + unsigned long realtotalpages, totalpages = 0; + enum zone_type i; + + for (i = 0; i < MAX_NR_ZONES; i++) + totalpages += zone_spanned_pages_in_node(pgdat->node_id, i, + zones_size); + pgdat->node_spanned_pages = totalpages; + + realtotalpages = totalpages; + for (i = 0; i < MAX_NR_ZONES; i++) + realtotalpages -= + zone_absent_pages_in_node(pgdat->node_id, i, + zholes_size); + pgdat->node_present_pages = realtotalpages; + printk(KERN_DEBUG "On node %d totalpages: %lu\n", pgdat->node_id, + realtotalpages); +} + /* * Set up the zone data structures: * - mark all pages reserved @@ -1998,11 +2618,34 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, for (j = 0; j < MAX_NR_ZONES; j++) { struct zone *zone = pgdat->node_zones + j; - unsigned long size, realsize; + unsigned long size, realsize, memmap_pages; - realsize = size = zones_size[j]; - if (zholes_size) - realsize -= zholes_size[j]; + size = zone_spanned_pages_in_node(nid, j, zones_size); + realsize = size - zone_absent_pages_in_node(nid, j, + zholes_size); + + /* + * Adjust realsize so that it accounts for how much memory + * is used by this zone for memmap. This affects the watermark + * and per-cpu initialisations + */ + memmap_pages = (size * sizeof(struct page)) >> PAGE_SHIFT; + if (realsize >= memmap_pages) { + realsize -= memmap_pages; + printk(KERN_DEBUG + " %s zone: %lu pages used for memmap\n", + zone_names[j], memmap_pages); + } else + printk(KERN_WARNING + " %s zone: %lu pages exceeds realsize %lu\n", + zone_names[j], memmap_pages, realsize); + + /* Account for reserved DMA pages */ + if (j == ZONE_DMA && realsize > dma_reserve) { + realsize -= dma_reserve; + printk(KERN_DEBUG " DMA zone: %lu pages reserved\n", + dma_reserve); + } if (!is_highmem_idx(j)) nr_kernel_pages += realsize; @@ -2011,6 +2654,7 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, zone->spanned_pages = size; zone->present_pages = realsize; #ifdef CONFIG_NUMA + zone->node = nid; zone->min_unmapped_pages = (realsize*sysctl_min_unmapped_ratio) / 100; zone->min_slab_pages = (realsize * sysctl_min_slab_ratio) / 100; @@ -2022,7 +2666,7 @@ 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); @@ -2036,7 +2680,6 @@ static void __meminit free_area_init_core(struct pglist_data *pgdat, if (!size) continue; - zonetable_add(zone, nid, j, zone_start_pfn, size); ret = init_currently_empty_zone(zone, zone_start_pfn, size); BUG_ON(ret); zone_start_pfn += size; @@ -2073,8 +2716,13 @@ static void __init alloc_node_mem_map(struct pglist_data *pgdat) /* * With no DISCONTIG, the global mem_map is just set as node 0's */ - if (pgdat == NODE_DATA(0)) + if (pgdat == NODE_DATA(0)) { mem_map = NODE_DATA(0)->node_mem_map; +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP + if (page_to_pfn(mem_map) != pgdat->node_start_pfn) + mem_map -= pgdat->node_start_pfn; +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ + } #endif #endif /* CONFIG_FLAT_NODE_MEM_MAP */ } @@ -2085,13 +2733,254 @@ void __meminit free_area_init_node(int nid, struct pglist_data *pgdat, { pgdat->node_id = nid; pgdat->node_start_pfn = node_start_pfn; - calculate_zone_totalpages(pgdat, zones_size, zholes_size); + calculate_node_totalpages(pgdat, zones_size, zholes_size); alloc_node_mem_map(pgdat); free_area_init_core(pgdat, zones_size, zholes_size); } +#ifdef CONFIG_ARCH_POPULATES_NODE_MAP +/** + * add_active_range - Register a range of PFNs backed by physical memory + * @nid: The node ID the range resides on + * @start_pfn: The start PFN of the available physical memory + * @end_pfn: The end PFN of the available physical memory + * + * These ranges are stored in an early_node_map[] and later used by + * free_area_init_nodes() to calculate zone sizes and holes. If the + * range spans a memory hole, it is up to the architecture to ensure + * the memory is not freed by the bootmem allocator. If possible + * the range being registered will be merged with existing ranges. + */ +void __init add_active_range(unsigned int nid, unsigned long start_pfn, + unsigned long end_pfn) +{ + int i; + + printk(KERN_DEBUG "Entering add_active_range(%d, %lu, %lu) " + "%d entries of %d used\n", + nid, start_pfn, end_pfn, + nr_nodemap_entries, MAX_ACTIVE_REGIONS); + + /* Merge with existing active regions if possible */ + for (i = 0; i < nr_nodemap_entries; i++) { + if (early_node_map[i].nid != nid) + continue; + + /* Skip if an existing region covers this new one */ + if (start_pfn >= early_node_map[i].start_pfn && + end_pfn <= early_node_map[i].end_pfn) + return; + + /* Merge forward if suitable */ + if (start_pfn <= early_node_map[i].end_pfn && + end_pfn > early_node_map[i].end_pfn) { + early_node_map[i].end_pfn = end_pfn; + return; + } + + /* Merge backward if suitable */ + if (start_pfn < early_node_map[i].end_pfn && + end_pfn >= early_node_map[i].start_pfn) { + early_node_map[i].start_pfn = start_pfn; + return; + } + } + + /* Check that early_node_map is large enough */ + if (i >= MAX_ACTIVE_REGIONS) { + printk(KERN_CRIT "More than %d memory regions, truncating\n", + MAX_ACTIVE_REGIONS); + return; + } + + early_node_map[i].nid = nid; + early_node_map[i].start_pfn = start_pfn; + early_node_map[i].end_pfn = end_pfn; + nr_nodemap_entries = i + 1; +} + +/** + * shrink_active_range - Shrink an existing registered range of PFNs + * @nid: The node id the range is on that should be shrunk + * @old_end_pfn: The old end PFN of the range + * @new_end_pfn: The new PFN of the range + * + * i386 with NUMA use alloc_remap() to store a node_mem_map on a local node. + * The map is kept at the end physical page range that has already been + * registered with add_active_range(). This function allows an arch to shrink + * an existing registered range. + */ +void __init shrink_active_range(unsigned int nid, unsigned long old_end_pfn, + unsigned long new_end_pfn) +{ + int i; + + /* Find the old active region end and shrink */ + for_each_active_range_index_in_nid(i, nid) + if (early_node_map[i].end_pfn == old_end_pfn) { + early_node_map[i].end_pfn = new_end_pfn; + break; + } +} + +/** + * remove_all_active_ranges - Remove all currently registered regions + * + * During discovery, it may be found that a table like SRAT is invalid + * and an alternative discovery method must be used. This function removes + * all currently registered regions. + */ +void __init remove_all_active_ranges(void) +{ + memset(early_node_map, 0, sizeof(early_node_map)); + nr_nodemap_entries = 0; +#ifdef CONFIG_MEMORY_HOTPLUG_RESERVE + memset(node_boundary_start_pfn, 0, sizeof(node_boundary_start_pfn)); + memset(node_boundary_end_pfn, 0, sizeof(node_boundary_end_pfn)); +#endif /* CONFIG_MEMORY_HOTPLUG_RESERVE */ +} + +/* Compare two active node_active_regions */ +static int __init cmp_node_active_region(const void *a, const void *b) +{ + struct node_active_region *arange = (struct node_active_region *)a; + struct node_active_region *brange = (struct node_active_region *)b; + + /* Done this way to avoid overflows */ + if (arange->start_pfn > brange->start_pfn) + return 1; + if (arange->start_pfn < brange->start_pfn) + return -1; + + return 0; +} + +/* sort the node_map by start_pfn */ +static void __init sort_node_map(void) +{ + sort(early_node_map, (size_t)nr_nodemap_entries, + sizeof(struct node_active_region), + cmp_node_active_region, NULL); +} + +/* Find the lowest pfn for a node. This depends on a sorted early_node_map */ +unsigned long __init find_min_pfn_for_node(unsigned long nid) +{ + int i; + + /* Regions in the early_node_map can be in any order */ + sort_node_map(); + + /* Assuming a sorted map, the first range found has the starting pfn */ + for_each_active_range_index_in_nid(i, nid) + return early_node_map[i].start_pfn; + + printk(KERN_WARNING "Could not find start_pfn for node %lu\n", nid); + return 0; +} + +/** + * find_min_pfn_with_active_regions - Find the minimum PFN registered + * + * It returns the minimum PFN based on information provided via + * add_active_range(). + */ +unsigned long __init find_min_pfn_with_active_regions(void) +{ + return find_min_pfn_for_node(MAX_NUMNODES); +} + +/** + * find_max_pfn_with_active_regions - Find the maximum PFN registered + * + * It returns the maximum PFN based on information provided via + * add_active_range(). + */ +unsigned long __init find_max_pfn_with_active_regions(void) +{ + int i; + unsigned long max_pfn = 0; + + for (i = 0; i < nr_nodemap_entries; i++) + max_pfn = max(max_pfn, early_node_map[i].end_pfn); + + return max_pfn; +} + +/** + * free_area_init_nodes - Initialise all pg_data_t and zone data + * @max_zone_pfn: an array of max PFNs for each zone + * + * This will call free_area_init_node() for each active node in the system. + * Using the page ranges provided by add_active_range(), the size of each + * zone in each node and their holes is calculated. If the maximum PFN + * between two adjacent zones match, it is assumed that the zone is empty. + * For example, if arch_max_dma_pfn == arch_max_dma32_pfn, it is assumed + * that arch_max_dma32_pfn has no pages. It is also assumed that a zone + * starts where the previous one ended. For example, ZONE_DMA32 starts + * at arch_max_dma_pfn. + */ +void __init free_area_init_nodes(unsigned long *max_zone_pfn) +{ + unsigned long nid; + enum zone_type i; + + /* Record where the zone boundaries are */ + memset(arch_zone_lowest_possible_pfn, 0, + sizeof(arch_zone_lowest_possible_pfn)); + memset(arch_zone_highest_possible_pfn, 0, + sizeof(arch_zone_highest_possible_pfn)); + arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions(); + arch_zone_highest_possible_pfn[0] = max_zone_pfn[0]; + for (i = 1; i < MAX_NR_ZONES; i++) { + arch_zone_lowest_possible_pfn[i] = + arch_zone_highest_possible_pfn[i-1]; + arch_zone_highest_possible_pfn[i] = + max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]); + } + + /* Print out the zone ranges */ + printk("Zone PFN ranges:\n"); + for (i = 0; i < MAX_NR_ZONES; i++) + printk(" %-8s %8lu -> %8lu\n", + zone_names[i], + arch_zone_lowest_possible_pfn[i], + arch_zone_highest_possible_pfn[i]); + + /* Print out the early_node_map[] */ + printk("early_node_map[%d] active PFN ranges\n", nr_nodemap_entries); + for (i = 0; i < nr_nodemap_entries; i++) + printk(" %3d: %8lu -> %8lu\n", early_node_map[i].nid, + early_node_map[i].start_pfn, + early_node_map[i].end_pfn); + + /* Initialise every node */ + for_each_online_node(nid) { + pg_data_t *pgdat = NODE_DATA(nid); + free_area_init_node(nid, pgdat, NULL, + find_min_pfn_for_node(nid), NULL); + } +} +#endif /* CONFIG_ARCH_POPULATES_NODE_MAP */ + +/** + * set_dma_reserve - set the specified number of pages reserved in the first zone + * @new_dma_reserve: The number of pages to mark reserved + * + * The per-cpu batchsize and zone watermarks are determined by present_pages. + * In the DMA zone, a significant percentage may be consumed by kernel image + * and other unfreeable allocations which can skew the watermarks badly. This + * function may optionally be used to account for unfreeable pages in the + * first zone (e.g., ZONE_DMA). The effect will be lower watermarks and + * smaller per-cpu batchsize. + */ +void __init set_dma_reserve(unsigned long new_dma_reserve) +{ + dma_reserve = new_dma_reserve; +} + #ifndef CONFIG_NEED_MULTIPLE_NODES static bootmem_data_t contig_bootmem_data; struct pglist_data contig_page_data = { .bdata = &contig_bootmem_data }; @@ -2105,7 +2994,6 @@ void __init free_area_init(unsigned long *zones_size) __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL); } -#ifdef CONFIG_HOTPLUG_CPU static int page_alloc_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) { @@ -2120,7 +3008,6 @@ static int page_alloc_cpu_notify(struct notifier_block *self, } return NOTIFY_OK; } -#endif /* CONFIG_HOTPLUG_CPU */ void __init page_alloc_init(void) { @@ -2198,10 +3085,11 @@ static void setup_per_zone_lowmem_reserve(void) calculate_totalreserve_pages(); } -/* - * setup_per_zone_pages_min - called when min_free_kbytes changes. Ensures - * that the pages_{min,low,high} values for each zone are set correctly - * with respect to min_free_kbytes. +/** + * setup_per_zone_pages_min - called when min_free_kbytes changes. + * + * Ensures that the pages_{min,low,high} values for each zone are set correctly + * with respect to min_free_kbytes. */ void setup_per_zone_pages_min(void) { @@ -2423,7 +3311,7 @@ void *__init alloc_large_system_hash(const char *tablename, /* allow the kernel cmdline to have a say */ if (!numentries) { /* round applicable memory size up to nearest megabyte */ - numentries = (flags & HASH_HIGHMEM) ? nr_all_pages : nr_kernel_pages; + numentries = nr_kernel_pages; numentries += (1UL << (20 - PAGE_SHIFT)) - 1; numentries >>= 20 - PAGE_SHIFT; numentries <<= 20 - PAGE_SHIFT; @@ -2445,7 +3333,7 @@ void *__init alloc_large_system_hash(const char *tablename, if (numentries > max) numentries = max; - log2qty = long_log2(numentries); + log2qty = ilog2(numentries); do { size = bucketsize << log2qty; @@ -2467,7 +3355,7 @@ void *__init alloc_large_system_hash(const char *tablename, printk("%s hash table entries: %d (order: %d, %lu bytes)\n", tablename, (1U << log2qty), - long_log2(size) - PAGE_SHIFT, + ilog2(size) - PAGE_SHIFT, size); if (_hash_shift) @@ -2490,3 +3378,19 @@ 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/page_io.c b/mm/page_io.c index d4840ecbf8f..dbffec0d78c 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -147,48 +147,3 @@ int swap_readpage(struct file *file, struct page *page) out: return ret; } - -#ifdef CONFIG_SOFTWARE_SUSPEND -/* - * A scruffy utility function to read or write an arbitrary swap page - * and wait on the I/O. The caller must have a ref on the page. - * - * We use end_swap_bio_read() even for writes, because it happens to do what - * we want. - */ -int rw_swap_page_sync(int rw, swp_entry_t entry, struct page *page, - struct bio **bio_chain) -{ - struct bio *bio; - int ret = 0; - int bio_rw; - - lock_page(page); - - bio = get_swap_bio(GFP_KERNEL, entry.val, page, end_swap_bio_read); - if (bio == NULL) { - unlock_page(page); - ret = -ENOMEM; - goto out; - } - - bio_rw = rw; - if (!bio_chain) - bio_rw |= (1 << BIO_RW_SYNC); - if (bio_chain) - bio_get(bio); - submit_bio(bio_rw, bio); - if (bio_chain == NULL) { - wait_on_page_locked(page); - - if (!PageUptodate(page) || PageError(page)) - ret = -EIO; - } - if (bio_chain) { - bio->bi_private = *bio_chain; - *bio_chain = bio; - } -out: - return ret; -} -#endif diff --git a/mm/pdflush.c b/mm/pdflush.c index b02102feeb4..8ce0900dc95 100644 --- a/mm/pdflush.c +++ b/mm/pdflush.c @@ -21,6 +21,7 @@ #include <linux/writeback.h> // Prototypes pdflush_operation() #include <linux/kthread.h> #include <linux/cpuset.h> +#include <linux/freezer.h> /* diff --git a/mm/readahead.c b/mm/readahead.c index aa7ec424656..0f539e8e827 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -13,6 +13,7 @@ #include <linux/module.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> +#include <linux/task_io_accounting_ops.h> #include <linux/pagevec.h> void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page) @@ -38,6 +39,7 @@ file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) ra->ra_pages = mapping->backing_dev_info->ra_pages; ra->prev_page = -1; } +EXPORT_SYMBOL_GPL(file_ra_state_init); /* * Return max readahead size for this inode in number-of-pages. @@ -147,15 +149,10 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages, if (!pagevec_add(&lru_pvec, page)) __pagevec_lru_add(&lru_pvec); if (ret) { - while (!list_empty(pages)) { - struct page *victim; - - victim = list_to_page(pages); - list_del(&victim->lru); - page_cache_release(victim); - } + put_pages_list(pages); break; } + task_io_account_read(PAGE_CACHE_SIZE); } pagevec_lru_add(&lru_pvec); return ret; @@ -172,6 +169,8 @@ 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; } @@ -453,7 +452,7 @@ static int make_ahead_window(struct address_space *mapping, struct file *filp, * * Note that @filp is purely used for passing on to the ->readpage[s]() * handler: it may refer to a different file from @mapping (so we may not use - * @filp->f_mapping or @filp->f_dentry->d_inode here). + * @filp->f_mapping or @filp->f_path.dentry->d_inode here). * Also, @ra may not be equal to &@filp->f_ra. * */ 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 8631be45b40..4bb28d218eb 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -26,6 +26,8 @@ #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> +#include <linux/xattr.h> +#include <linux/generic_acl.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/file.h> @@ -46,6 +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> @@ -174,9 +177,10 @@ static inline void shmem_unacct_blocks(unsigned long flags, long pages) static struct super_operations shmem_ops; static const struct address_space_operations shmem_aops; -static struct file_operations shmem_file_operations; +static const struct file_operations shmem_file_operations; static struct inode_operations shmem_inode_operations; static struct inode_operations shmem_dir_inode_operations; +static struct inode_operations shmem_special_inode_operations; static struct vm_operations_struct shmem_vm_ops; static struct backing_dev_info shmem_backing_dev_info __read_mostly = { @@ -637,7 +641,7 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) struct page *page = NULL; int error; - if (attr->ia_valid & ATTR_SIZE) { + if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { if (attr->ia_size < inode->i_size) { /* * If truncating down to a partial page, then @@ -670,6 +674,10 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) error = inode_change_ok(inode, attr); if (!error) error = inode_setattr(inode, attr); +#ifdef CONFIG_TMPFS_POSIX_ACL + if (!error && (attr->ia_valid & ATTR_MODE)) + error = generic_acl_chmod(inode, &shmem_acl_ops); +#endif if (page) page_cache_release(page); return error; @@ -1124,7 +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; } @@ -1217,7 +1225,7 @@ failed: struct page *shmem_nopage(struct vm_area_struct *vma, unsigned long address, int *type) { - struct inode *inode = vma->vm_file->f_dentry->d_inode; + struct inode *inode = vma->vm_file->f_path.dentry->d_inode; struct page *page = NULL; unsigned long idx; int error; @@ -1240,7 +1248,7 @@ static int shmem_populate(struct vm_area_struct *vma, unsigned long addr, unsigned long len, pgprot_t prot, unsigned long pgoff, int nonblock) { - struct inode *inode = vma->vm_file->f_dentry->d_inode; + struct inode *inode = vma->vm_file->f_path.dentry->d_inode; struct mm_struct *mm = vma->vm_mm; enum sgp_type sgp = nonblock? SGP_QUICK: SGP_CACHE; unsigned long size; @@ -1285,14 +1293,14 @@ static int shmem_populate(struct vm_area_struct *vma, #ifdef CONFIG_NUMA int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new) { - struct inode *i = vma->vm_file->f_dentry->d_inode; + struct inode *i = vma->vm_file->f_path.dentry->d_inode; return mpol_set_shared_policy(&SHMEM_I(i)->policy, vma, new); } struct mempolicy * shmem_get_policy(struct vm_area_struct *vma, unsigned long addr) { - struct inode *i = vma->vm_file->f_dentry->d_inode; + struct inode *i = vma->vm_file->f_path.dentry->d_inode; unsigned long idx; idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; @@ -1302,7 +1310,7 @@ shmem_get_policy(struct vm_area_struct *vma, unsigned long addr) int shmem_lock(struct file *file, int lock, struct user_struct *user) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; struct shmem_inode_info *info = SHMEM_I(inode); int retval = -ENOMEM; @@ -1351,11 +1359,11 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) inode->i_mode = mode; inode->i_uid = current->fsuid; inode->i_gid = current->fsgid; - inode->i_blksize = PAGE_CACHE_SIZE; inode->i_blocks = 0; 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); @@ -1363,6 +1371,7 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) switch (mode & S_IFMT) { default: + inode->i_op = &shmem_special_inode_operations; init_special_inode(inode, mode, dev); break; case S_IFREG: @@ -1372,7 +1381,7 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) &sbinfo->policy_nodes); break; case S_IFDIR: - inode->i_nlink++; + inc_nlink(inode); /* Some things misbehave if size == 0 on a directory */ inode->i_size = 2 * BOGO_DIRENT_SIZE; inode->i_op = &shmem_dir_inode_operations; @@ -1413,7 +1422,7 @@ shmem_prepare_write(struct file *file, struct page *page, unsigned offset, unsig static ssize_t shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; loff_t pos; unsigned long written; ssize_t err; @@ -1433,7 +1442,7 @@ shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t if (err || !count) goto out; - err = remove_suid(file->f_dentry); + err = remove_suid(file->f_path.dentry); if (err) goto out; @@ -1515,7 +1524,7 @@ out: static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor) { - struct inode *inode = filp->f_dentry->d_inode; + struct inode *inode = filp->f_path.dentry->d_inode; struct address_space *mapping = inode->i_mapping; unsigned long index, offset; @@ -1683,7 +1692,11 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) iput(inode); return error; } - error = 0; + } + error = shmem_acl_init(inode, dir); + if (error) { + iput(inode); + return error; } if (dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; @@ -1704,7 +1717,7 @@ static int shmem_mkdir(struct inode *dir, struct dentry *dentry, int mode) if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0))) return error; - dir->i_nlink++; + inc_nlink(dir); return 0; } @@ -1739,7 +1752,7 @@ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentr dir->i_size += BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - inode->i_nlink++; + inc_nlink(inode); atomic_inc(&inode->i_count); /* New dentry reference */ dget(dentry); /* Extra pinning count for the created dentry */ d_instantiate(dentry, inode); @@ -1761,7 +1774,7 @@ static int shmem_unlink(struct inode *dir, struct dentry *dentry) dir->i_size -= BOGO_DIRENT_SIZE; inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME; - inode->i_nlink--; + drop_nlink(inode); dput(dentry); /* Undo the count from "create" - this does all the work */ return 0; } @@ -1771,8 +1784,8 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry) if (!simple_empty(dentry)) return -ENOTEMPTY; - dentry->d_inode->i_nlink--; - dir->i_nlink--; + drop_nlink(dentry->d_inode); + drop_nlink(dir); return shmem_unlink(dir, dentry); } @@ -1793,10 +1806,10 @@ static int shmem_rename(struct inode *old_dir, struct dentry *old_dentry, struct if (new_dentry->d_inode) { (void) shmem_unlink(new_dir, new_dentry); if (they_are_dirs) - old_dir->i_nlink--; + drop_nlink(old_dir); } else if (they_are_dirs) { - old_dir->i_nlink--; - new_dir->i_nlink++; + drop_nlink(old_dir); + inc_nlink(new_dir); } old_dir->i_size -= BOGO_DIRENT_SIZE; @@ -1898,6 +1911,132 @@ static struct inode_operations shmem_symlink_inode_operations = { .put_link = shmem_put_link, }; +#ifdef CONFIG_TMPFS_POSIX_ACL +/** + * Superblocks without xattr inode operations will get security.* xattr + * support from the VFS "for free". As soon as we have any other xattrs + * like ACLs, we also need to implement the security.* handlers at + * filesystem level, though. + */ + +static size_t shmem_xattr_security_list(struct inode *inode, char *list, + size_t list_len, const char *name, + size_t name_len) +{ + return security_inode_listsecurity(inode, list, list_len); +} + +static int shmem_xattr_security_get(struct inode *inode, const char *name, + void *buffer, size_t size) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return security_inode_getsecurity(inode, name, buffer, size, + -EOPNOTSUPP); +} + +static int shmem_xattr_security_set(struct inode *inode, const char *name, + const void *value, size_t size, int flags) +{ + if (strcmp(name, "") == 0) + return -EINVAL; + return security_inode_setsecurity(inode, name, value, size, flags); +} + +static struct xattr_handler shmem_xattr_security_handler = { + .prefix = XATTR_SECURITY_PREFIX, + .list = shmem_xattr_security_list, + .get = shmem_xattr_security_get, + .set = shmem_xattr_security_set, +}; + +static struct xattr_handler *shmem_xattr_handlers[] = { + &shmem_xattr_acl_access_handler, + &shmem_xattr_acl_default_handler, + &shmem_xattr_security_handler, + NULL +}; +#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) @@ -2070,6 +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 @@ -2095,6 +2235,10 @@ static int shmem_fill_super(struct super_block *sb, sb->s_magic = TMPFS_MAGIC; sb->s_op = &shmem_ops; sb->s_time_gran = 1; +#ifdef CONFIG_TMPFS_POSIX_ACL + sb->s_xattr = shmem_xattr_handlers; + sb->s_flags |= MS_POSIXACL; +#endif inode = shmem_get_inode(sb, S_IFDIR | mode, 0); if (!inode) @@ -2119,7 +2263,7 @@ static struct kmem_cache *shmem_inode_cachep; static struct inode *shmem_alloc_inode(struct super_block *sb) { struct shmem_inode_info *p; - p = (struct shmem_inode_info *)kmem_cache_alloc(shmem_inode_cachep, SLAB_KERNEL); + p = (struct shmem_inode_info *)kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL); if (!p) return NULL; return &p->vfs_inode; @@ -2131,6 +2275,7 @@ static void shmem_destroy_inode(struct inode *inode) /* only struct inode is valid if it's an inline symlink */ mpol_free_shared_policy(&SHMEM_I(inode)->policy); } + shmem_acl_destroy_inode(inode); kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); } @@ -2142,6 +2287,10 @@ static void init_once(void *foo, struct kmem_cache *cachep, if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) == SLAB_CTOR_CONSTRUCTOR) { inode_init_once(&p->vfs_inode); +#ifdef CONFIG_TMPFS_POSIX_ACL + p->i_acl = NULL; + p->i_default_acl = NULL; +#endif } } @@ -2157,8 +2306,7 @@ static int init_inodecache(void) static void destroy_inodecache(void) { - if (kmem_cache_destroy(shmem_inode_cachep)) - printk(KERN_INFO "shmem_inode_cache: not all structures were freed\n"); + kmem_cache_destroy(shmem_inode_cachep); } static const struct address_space_operations shmem_aops = { @@ -2171,7 +2319,7 @@ static const struct address_space_operations shmem_aops = { .migratepage = migrate_page, }; -static struct file_operations shmem_file_operations = { +static const struct file_operations shmem_file_operations = { .mmap = shmem_mmap, #ifdef CONFIG_TMPFS .llseek = generic_file_llseek, @@ -2186,6 +2334,14 @@ static struct inode_operations shmem_inode_operations = { .truncate = shmem_truncate, .setattr = shmem_notify_change, .truncate_range = shmem_truncate_range, +#ifdef CONFIG_TMPFS_POSIX_ACL + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = generic_listxattr, + .removexattr = generic_removexattr, + .permission = shmem_permission, +#endif + }; static struct inode_operations shmem_dir_inode_operations = { @@ -2200,6 +2356,25 @@ static struct inode_operations shmem_dir_inode_operations = { .mknod = shmem_mknod, .rename = shmem_rename, #endif +#ifdef CONFIG_TMPFS_POSIX_ACL + .setattr = shmem_notify_change, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = generic_listxattr, + .removexattr = generic_removexattr, + .permission = shmem_permission, +#endif +}; + +static struct inode_operations shmem_special_inode_operations = { +#ifdef CONFIG_TMPFS_POSIX_ACL + .setattr = shmem_notify_change, + .setxattr = generic_setxattr, + .getxattr = generic_getxattr, + .listxattr = generic_listxattr, + .removexattr = generic_removexattr, + .permission = shmem_permission, +#endif }; static struct super_operations shmem_ops = { @@ -2318,8 +2493,8 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) d_instantiate(dentry, inode); inode->i_size = size; inode->i_nlink = 0; /* It is unlinked */ - file->f_vfsmnt = mntget(shm_mnt); - file->f_dentry = dentry; + file->f_path.mnt = mntget(shm_mnt); + file->f_path.dentry = dentry; file->f_mapping = inode->i_mapping; file->f_op = &shmem_file_operations; file->f_mode = FMODE_WRITE | FMODE_READ; diff --git a/mm/shmem_acl.c b/mm/shmem_acl.c new file mode 100644 index 00000000000..f5664c5b9eb --- /dev/null +++ b/mm/shmem_acl.c @@ -0,0 +1,197 @@ +/* + * mm/shmem_acl.c + * + * (C) 2005 Andreas Gruenbacher <agruen@suse.de> + * + * This file is released under the GPL. + */ + +#include <linux/fs.h> +#include <linux/shmem_fs.h> +#include <linux/xattr.h> +#include <linux/generic_acl.h> + +/** + * shmem_get_acl - generic_acl_operations->getacl() operation + */ +static struct posix_acl * +shmem_get_acl(struct inode *inode, int type) +{ + struct posix_acl *acl = NULL; + + spin_lock(&inode->i_lock); + switch(type) { + case ACL_TYPE_ACCESS: + acl = posix_acl_dup(SHMEM_I(inode)->i_acl); + break; + + case ACL_TYPE_DEFAULT: + acl = posix_acl_dup(SHMEM_I(inode)->i_default_acl); + break; + } + spin_unlock(&inode->i_lock); + + return acl; +} + +/** + * shmem_set_acl - generic_acl_operations->setacl() operation + */ +static void +shmem_set_acl(struct inode *inode, int type, struct posix_acl *acl) +{ + struct posix_acl *free = NULL; + + spin_lock(&inode->i_lock); + switch(type) { + case ACL_TYPE_ACCESS: + free = SHMEM_I(inode)->i_acl; + SHMEM_I(inode)->i_acl = posix_acl_dup(acl); + break; + + case ACL_TYPE_DEFAULT: + free = SHMEM_I(inode)->i_default_acl; + SHMEM_I(inode)->i_default_acl = posix_acl_dup(acl); + break; + } + spin_unlock(&inode->i_lock); + posix_acl_release(free); +} + +struct generic_acl_operations shmem_acl_ops = { + .getacl = shmem_get_acl, + .setacl = shmem_set_acl, +}; + +/** + * shmem_list_acl_access, shmem_get_acl_access, shmem_set_acl_access, + * shmem_xattr_acl_access_handler - plumbing code to implement the + * system.posix_acl_access xattr using the generic acl functions. + */ + +static size_t +shmem_list_acl_access(struct inode *inode, char *list, size_t list_size, + const char *name, size_t name_len) +{ + return generic_acl_list(inode, &shmem_acl_ops, ACL_TYPE_ACCESS, + list, list_size); +} + +static int +shmem_get_acl_access(struct inode *inode, const char *name, void *buffer, + size_t size) +{ + if (strcmp(name, "") != 0) + return -EINVAL; + return generic_acl_get(inode, &shmem_acl_ops, ACL_TYPE_ACCESS, buffer, + size); +} + +static int +shmem_set_acl_access(struct inode *inode, const char *name, const void *value, + size_t size, int flags) +{ + if (strcmp(name, "") != 0) + return -EINVAL; + return generic_acl_set(inode, &shmem_acl_ops, ACL_TYPE_ACCESS, value, + size); +} + +struct xattr_handler shmem_xattr_acl_access_handler = { + .prefix = POSIX_ACL_XATTR_ACCESS, + .list = shmem_list_acl_access, + .get = shmem_get_acl_access, + .set = shmem_set_acl_access, +}; + +/** + * shmem_list_acl_default, shmem_get_acl_default, shmem_set_acl_default, + * shmem_xattr_acl_default_handler - plumbing code to implement the + * system.posix_acl_default xattr using the generic acl functions. + */ + +static size_t +shmem_list_acl_default(struct inode *inode, char *list, size_t list_size, + const char *name, size_t name_len) +{ + return generic_acl_list(inode, &shmem_acl_ops, ACL_TYPE_DEFAULT, + list, list_size); +} + +static int +shmem_get_acl_default(struct inode *inode, const char *name, void *buffer, + size_t size) +{ + if (strcmp(name, "") != 0) + return -EINVAL; + return generic_acl_get(inode, &shmem_acl_ops, ACL_TYPE_DEFAULT, buffer, + size); +} + +static int +shmem_set_acl_default(struct inode *inode, const char *name, const void *value, + size_t size, int flags) +{ + if (strcmp(name, "") != 0) + return -EINVAL; + return generic_acl_set(inode, &shmem_acl_ops, ACL_TYPE_DEFAULT, value, + size); +} + +struct xattr_handler shmem_xattr_acl_default_handler = { + .prefix = POSIX_ACL_XATTR_DEFAULT, + .list = shmem_list_acl_default, + .get = shmem_get_acl_default, + .set = shmem_set_acl_default, +}; + +/** + * shmem_acl_init - Inizialize the acl(s) of a new inode + */ +int +shmem_acl_init(struct inode *inode, struct inode *dir) +{ + return generic_acl_init(inode, dir, &shmem_acl_ops); +} + +/** + * shmem_acl_destroy_inode - destroy acls hanging off the in-memory inode + * + * This is done before destroying the actual inode. + */ + +void +shmem_acl_destroy_inode(struct inode *inode) +{ + if (SHMEM_I(inode)->i_acl) + posix_acl_release(SHMEM_I(inode)->i_acl); + SHMEM_I(inode)->i_acl = NULL; + if (SHMEM_I(inode)->i_default_acl) + posix_acl_release(SHMEM_I(inode)->i_default_acl); + SHMEM_I(inode)->i_default_acl = NULL; +} + +/** + * shmem_check_acl - check_acl() callback for generic_permission() + */ +static int +shmem_check_acl(struct inode *inode, int mask) +{ + struct posix_acl *acl = shmem_get_acl(inode, ACL_TYPE_ACCESS); + + if (acl) { + int error = posix_acl_permission(inode, acl, mask); + posix_acl_release(acl); + return error; + } + return -EAGAIN; +} + +/** + * shmem_permission - permission() inode operation + */ +int +shmem_permission(struct inode *inode, int mask, struct nameidata *nd) +{ + return generic_permission(inode, mask, shmem_check_acl); +} diff --git a/mm/slab.c b/mm/slab.c index 7a48eb1a60c..2c655532f5e 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -86,7 +86,6 @@ * All object allocations for a node occur from node specific slab lists. */ -#include <linux/config.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/poison.h> @@ -104,12 +103,13 @@ #include <linux/module.h> #include <linux/rcupdate.h> #include <linux/string.h> +#include <linux/uaccess.h> #include <linux/nodemask.h> #include <linux/mempolicy.h> #include <linux/mutex.h> +#include <linux/fault-inject.h> #include <linux/rtmutex.h> -#include <asm/uaccess.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/page.h> @@ -314,7 +314,7 @@ static int drain_freelist(struct kmem_cache *cache, static void free_block(struct kmem_cache *cachep, void **objpp, int len, int node); static int enable_cpucache(struct kmem_cache *cachep); -static void cache_reap(void *unused); +static void cache_reap(struct work_struct *unused); /* * This function must be completely optimized away if a constant is passed to @@ -731,7 +731,10 @@ static inline void init_lock_keys(void) } #endif -/* Guard access to the cache-chain. */ +/* + * 1. Guard access to the cache-chain. + * 2. Protect sanity of cpu_online_map against cpu hotplug events + */ static DEFINE_MUTEX(cache_chain_mutex); static struct list_head cache_chain; @@ -754,7 +757,7 @@ int slab_is_available(void) return g_cpucache_up == FULL; } -static DEFINE_PER_CPU(struct work_struct, reap_work); +static DEFINE_PER_CPU(struct delayed_work, reap_work); static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep) { @@ -867,6 +870,22 @@ static void __slab_error(const char *function, struct kmem_cache *cachep, dump_stack(); } +/* + * By default on NUMA we use alien caches to stage the freeing of + * objects allocated from other nodes. This causes massive memory + * inefficiencies when using fake NUMA setup to split memory into a + * large number of small nodes, so it can be disabled on the command + * line + */ + +static int use_alien_caches __read_mostly = 1; +static int __init noaliencache_setup(char *s) +{ + use_alien_caches = 0; + return 1; +} +__setup("noaliencache", noaliencache_setup); + #ifdef CONFIG_NUMA /* * Special reaping functions for NUMA systems called from cache_reap(). @@ -884,7 +903,7 @@ 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) @@ -917,17 +936,18 @@ static void next_reap_node(void) */ static void __devinit start_cpu_timer(int cpu) { - struct work_struct *reap_work = &per_cpu(reap_work, cpu); + struct delayed_work *reap_work = &per_cpu(reap_work, cpu); /* * When this gets called from do_initcalls via cpucache_init(), * init_workqueues() has already run, so keventd will be setup * at that time. */ - if (keventd_up() && reap_work->func == NULL) { + if (keventd_up() && reap_work->work.func == NULL) { init_reap_node(cpu); - INIT_WORK(reap_work, cache_reap, NULL); - schedule_delayed_work_on(cpu, reap_work, HZ + 3 * cpu); + INIT_DELAYED_WORK(reap_work, cache_reap); + schedule_delayed_work_on(cpu, reap_work, + __round_jiffies_relative(HZ, cpu)); } } @@ -972,8 +992,40 @@ static int transfer_objects(struct array_cache *to, return nr; } -#ifdef CONFIG_NUMA -static void *__cache_alloc_node(struct kmem_cache *, gfp_t, int); +#ifndef CONFIG_NUMA + +#define drain_alien_cache(cachep, alien) do { } while (0) +#define reap_alien(cachep, l3) do { } while (0) + +static inline struct array_cache **alloc_alien_cache(int node, int limit) +{ + return (struct array_cache **)BAD_ALIEN_MAGIC; +} + +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; +} + +static inline void *alternate_node_alloc(struct kmem_cache *cachep, + gfp_t flags) +{ + return NULL; +} + +static inline void *____cache_alloc_node(struct kmem_cache *cachep, + gfp_t flags, int nodeid) +{ + return NULL; +} + +#else /* CONFIG_NUMA */ + +static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int); static void *alternate_node_alloc(struct kmem_cache *, gfp_t); static struct array_cache **alloc_alien_cache(int node, int limit) @@ -1075,15 +1127,18 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) int nodeid = slabp->nodeid; struct kmem_list3 *l3; struct array_cache *alien = NULL; + int node; + + node = numa_node_id(); /* * 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())) + if (likely(slabp->nodeid == node) || unlikely(!use_alien_caches)) return 0; - l3 = cachep->nodelists[numa_node_id()]; + l3 = cachep->nodelists[node]; STATS_INC_NODEFREES(cachep); if (l3->alien && l3->alien[nodeid]) { alien = l3->alien[nodeid]; @@ -1101,26 +1156,6 @@ static inline int cache_free_alien(struct kmem_cache *cachep, void *objp) } return 1; } - -#else - -#define drain_alien_cache(cachep, alien) do { } while (0) -#define reap_alien(cachep, l3) do { } while (0) - -static inline struct array_cache **alloc_alien_cache(int node, int limit) -{ - return (struct array_cache **)BAD_ALIEN_MAGIC; -} - -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 __cpuinit cpuup_callback(struct notifier_block *nfb, @@ -1178,7 +1213,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, list_for_each_entry(cachep, &cache_chain, next) { struct array_cache *nc; struct array_cache *shared; - struct array_cache **alien; + struct array_cache **alien = NULL; nc = alloc_arraycache(node, cachep->limit, cachep->batchcount); @@ -1190,9 +1225,11 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, if (!shared) goto bad; - alien = alloc_alien_cache(node, cachep->limit); - if (!alien) - goto bad; + if (use_alien_caches) { + alien = alloc_alien_cache(node, cachep->limit); + if (!alien) + goto bad; + } cachep->array[cpu] = nc; l3 = cachep->nodelists[node]; BUG_ON(!l3); @@ -1216,12 +1253,18 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, kfree(shared); free_alien_cache(alien); } - mutex_unlock(&cache_chain_mutex); break; case CPU_ONLINE: + mutex_unlock(&cache_chain_mutex); start_cpu_timer(cpu); break; #ifdef CONFIG_HOTPLUG_CPU + case CPU_DOWN_PREPARE: + mutex_lock(&cache_chain_mutex); + break; + case CPU_DOWN_FAILED: + mutex_unlock(&cache_chain_mutex); + break; case CPU_DEAD: /* * Even if all the cpus of a node are down, we don't free the @@ -1232,8 +1275,8 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb, * gets destroyed at kmem_cache_destroy(). */ /* fall thru */ +#endif case CPU_UP_CANCELED: - mutex_lock(&cache_chain_mutex); list_for_each_entry(cachep, &cache_chain, next) { struct array_cache *nc; struct array_cache *shared; @@ -1294,11 +1337,9 @@ free_array_cache: } mutex_unlock(&cache_chain_mutex); break; -#endif } return NOTIFY_OK; bad: - mutex_unlock(&cache_chain_mutex); return NOTIFY_BAD; } @@ -1314,7 +1355,6 @@ static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list, { struct kmem_list3 *ptr; - BUG_ON(cachep->nodelists[nodeid] != list); ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, nodeid); BUG_ON(!ptr); @@ -1341,6 +1381,7 @@ void __init kmem_cache_init(void) struct cache_names *names; int i; int order; + int node; for (i = 0; i < NUM_INIT_LISTS; i++) { kmem_list3_init(&initkmem_list3[i]); @@ -1375,12 +1416,14 @@ void __init kmem_cache_init(void) * 6) Resize the head arrays of the kmalloc caches to their final sizes. */ + node = numa_node_id(); + /* 1) create the cache_cache */ INIT_LIST_HEAD(&cache_chain); list_add(&cache_cache.next, &cache_chain); cache_cache.colour_off = cache_line_size(); cache_cache.array[smp_processor_id()] = &initarray_cache.cache; - cache_cache.nodelists[numa_node_id()] = &initkmem_list3[CACHE_CACHE]; + cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE]; cache_cache.buffer_size = ALIGN(cache_cache.buffer_size, cache_line_size()); @@ -1485,19 +1528,18 @@ void __init kmem_cache_init(void) } /* 5) Replace the bootstrap kmem_list3's */ { - int node; + int nid; + /* Replace the static kmem_list3 structures for the boot cpu */ - init_list(&cache_cache, &initkmem_list3[CACHE_CACHE], - numa_node_id()); + init_list(&cache_cache, &initkmem_list3[CACHE_CACHE], node); - for_each_online_node(node) { + for_each_online_node(nid) { init_list(malloc_sizes[INDEX_AC].cs_cachep, - &initkmem_list3[SIZE_AC + node], node); + &initkmem_list3[SIZE_AC + nid], nid); if (INDEX_AC != INDEX_L3) { init_list(malloc_sizes[INDEX_L3].cs_cachep, - &initkmem_list3[SIZE_L3 + node], - node); + &initkmem_list3[SIZE_L3 + nid], nid); } } } @@ -1564,6 +1606,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) */ flags |= __GFP_COMP; #endif + flags |= cachep->gfpflags; page = alloc_pages_node(nodeid, flags, cachep->gfporder); @@ -1665,10 +1708,32 @@ static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val) static void dump_line(char *data, int offset, int limit) { int i; + unsigned char error = 0; + int bad_count = 0; + printk(KERN_ERR "%03x:", offset); - for (i = 0; i < limit; i++) + for (i = 0; i < limit; i++) { + if (data[offset + i] != POISON_FREE) { + error = data[offset + i]; + bad_count++; + } printk(" %02x", (unsigned char)data[offset + i]); + } printk("\n"); + + if (bad_count == 1) { + error ^= POISON_FREE; + if (!(error & (error - 1))) { + printk(KERN_ERR "Single bit error detected. Probably " + "bad RAM.\n"); +#ifdef CONFIG_X86 + printk(KERN_ERR "Run memtest86+ or a similar memory " + "test tool.\n"); +#else + printk(KERN_ERR "Run a memory test tool.\n"); +#endif + } + } } #endif @@ -2055,15 +2120,12 @@ kmem_cache_create (const char *name, size_t size, size_t align, } /* - * Prevent CPUs from coming and going. - * lock_cpu_hotplug() nests outside cache_chain_mutex + * We use cache_chain_mutex to ensure a consistent view of + * cpu_online_map as well. Please see cpuup_callback */ - lock_cpu_hotplug(); - mutex_lock(&cache_chain_mutex); list_for_each_entry(pc, &cache_chain, next) { - mm_segment_t old_fs = get_fs(); char tmp; int res; @@ -2072,9 +2134,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, * destroy its slab cache and no-one else reuses the vmalloc * area of the module. Print a warning. */ - set_fs(KERNEL_DS); - res = __get_user(tmp, pc->name); - set_fs(old_fs); + res = probe_kernel_address(pc->name, tmp); if (res) { printk("SLAB: cache with size %d has lost its name\n", pc->buffer_size); @@ -2154,25 +2214,24 @@ kmem_cache_create (const char *name, size_t size, size_t align, if (flags & SLAB_RED_ZONE || flags & SLAB_STORE_USER) ralign = BYTES_PER_WORD; - /* 2) arch mandated alignment: disables debug if necessary */ + /* 2) arch mandated alignment */ if (ralign < ARCH_SLAB_MINALIGN) { ralign = ARCH_SLAB_MINALIGN; - if (ralign > BYTES_PER_WORD) - flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); } - /* 3) caller mandated alignment: disables debug if necessary */ + /* 3) caller mandated alignment */ if (ralign < align) { ralign = align; - if (ralign > BYTES_PER_WORD) - flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); } + /* disable debug if necessary */ + if (ralign > BYTES_PER_WORD) + flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER); /* * 4) Store it. */ align = ralign; /* Get cache's description obj. */ - cachep = kmem_cache_zalloc(&cache_cache, SLAB_KERNEL); + cachep = kmem_cache_zalloc(&cache_cache, GFP_KERNEL); if (!cachep) goto oops; @@ -2283,7 +2342,6 @@ oops: panic("kmem_cache_create(): failed to create slab `%s'\n", name); mutex_unlock(&cache_chain_mutex); - unlock_cpu_hotplug(); return cachep; } EXPORT_SYMBOL(kmem_cache_create); @@ -2401,6 +2459,7 @@ out: return nr_freed; } +/* Called with cache_chain_mutex held to protect against cpu hotplug */ static int __cache_shrink(struct kmem_cache *cachep) { int ret = 0, i = 0; @@ -2431,9 +2490,13 @@ static int __cache_shrink(struct kmem_cache *cachep) */ int kmem_cache_shrink(struct kmem_cache *cachep) { + int ret; BUG_ON(!cachep || in_interrupt()); - return __cache_shrink(cachep); + mutex_lock(&cache_chain_mutex); + ret = __cache_shrink(cachep); + mutex_unlock(&cache_chain_mutex); + return ret; } EXPORT_SYMBOL(kmem_cache_shrink); @@ -2442,7 +2505,6 @@ EXPORT_SYMBOL(kmem_cache_shrink); * @cachep: the cache to destroy * * Remove a struct kmem_cache object from the slab cache. - * Returns 0 on success. * * It is expected this function will be called by a module when it is * unloaded. This will remove the cache completely, and avoid a duplicate @@ -2454,36 +2516,28 @@ EXPORT_SYMBOL(kmem_cache_shrink); * The caller must guarantee that noone will allocate memory from the cache * during the kmem_cache_destroy(). */ -int kmem_cache_destroy(struct kmem_cache *cachep) +void kmem_cache_destroy(struct kmem_cache *cachep) { BUG_ON(!cachep || in_interrupt()); - /* Don't let CPUs to come and go */ - lock_cpu_hotplug(); - /* Find the cache in the chain of caches. */ mutex_lock(&cache_chain_mutex); /* * the chain is never empty, cache_cache is never destroyed */ list_del(&cachep->next); - mutex_unlock(&cache_chain_mutex); - if (__cache_shrink(cachep)) { slab_error(cachep, "Can't free all objects"); - mutex_lock(&cache_chain_mutex); list_add(&cachep->next, &cache_chain); mutex_unlock(&cache_chain_mutex); - unlock_cpu_hotplug(); - return 1; + return; } if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) synchronize_rcu(); __kmem_cache_destroy(cachep); - unlock_cpu_hotplug(); - return 0; + mutex_unlock(&cache_chain_mutex); } EXPORT_SYMBOL(kmem_cache_destroy); @@ -2507,7 +2561,7 @@ static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp, if (OFF_SLAB(cachep)) { /* Slab management obj is off-slab. */ slabp = kmem_cache_alloc_node(cachep->slabp_cache, - local_flags, nodeid); + local_flags & ~GFP_THISNODE, nodeid); if (!slabp) return NULL; } else { @@ -2577,7 +2631,7 @@ static void cache_init_objs(struct kmem_cache *cachep, static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags) { - if (flags & SLAB_DMA) + if (flags & GFP_DMA) BUG_ON(!(cachep->gfpflags & GFP_DMA)); else BUG_ON(cachep->gfpflags & GFP_DMA); @@ -2648,10 +2702,10 @@ static void slab_map_pages(struct kmem_cache *cache, struct slab *slab, * Grow (by 1) the number of slabs within a cache. This is called by * kmem_cache_alloc() when there are no active objs left in a cache. */ -static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid) +static int cache_grow(struct kmem_cache *cachep, + gfp_t flags, int nodeid, void *objp) { struct slab *slabp; - void *objp; size_t offset; gfp_t local_flags; unsigned long ctor_flags; @@ -2661,12 +2715,12 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid) * Be lazy and only check for valid flags here, keeping it out of the * critical path in kmem_cache_alloc(). */ - BUG_ON(flags & ~(SLAB_DMA | SLAB_LEVEL_MASK | SLAB_NO_GROW)); - if (flags & SLAB_NO_GROW) + BUG_ON(flags & ~(GFP_DMA | GFP_LEVEL_MASK | __GFP_NO_GROW)); + if (flags & __GFP_NO_GROW) return 0; ctor_flags = SLAB_CTOR_CONSTRUCTOR; - local_flags = (flags & SLAB_LEVEL_MASK); + local_flags = (flags & GFP_LEVEL_MASK); if (!(local_flags & __GFP_WAIT)) /* * Not allowed to sleep. Need to tell a constructor about @@ -2703,12 +2757,14 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid) * Get mem for the objs. Attempt to allocate a physical page from * 'nodeid'. */ - objp = kmem_getpages(cachep, flags, nodeid); + if (!objp) + objp = kmem_getpages(cachep, flags, nodeid); if (!objp) goto failed; /* Get slab management. */ - slabp = alloc_slabmgmt(cachep, objp, offset, local_flags, nodeid); + slabp = alloc_slabmgmt(cachep, objp, offset, + local_flags & ~GFP_THISNODE, nodeid); if (!slabp) goto opps1; @@ -2881,6 +2937,9 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags) int batchcount; struct kmem_list3 *l3; struct array_cache *ac; + int node; + + node = numa_node_id(); check_irq_off(); ac = cpu_cache_get(cachep); @@ -2894,7 +2953,7 @@ retry: */ batchcount = BATCHREFILL_LIMIT; } - l3 = cachep->nodelists[numa_node_id()]; + l3 = cachep->nodelists[node]; BUG_ON(ac->avail > 0 || !l3); spin_lock(&l3->list_lock); @@ -2924,7 +2983,7 @@ retry: STATS_SET_HIGH(cachep); ac->entry[ac->avail++] = slab_get_obj(cachep, slabp, - numa_node_id()); + node); } check_slabp(cachep, slabp); @@ -2943,7 +3002,7 @@ alloc_done: if (unlikely(!ac->avail)) { int x; - x = cache_grow(cachep, flags, numa_node_id()); + x = cache_grow(cachep, flags | GFP_THISNODE, node, NULL); /* cache_grow can reenable interrupts, then ac could change. */ ac = cpu_cache_get(cachep); @@ -3019,26 +3078,101 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, cachep->ctor(objp, cachep, ctor_flags); } +#if ARCH_SLAB_MINALIGN + if ((u32)objp & (ARCH_SLAB_MINALIGN-1)) { + printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n", + objp, ARCH_SLAB_MINALIGN); + } +#endif return objp; } #else #define cache_alloc_debugcheck_after(a,b,objp,d) (objp) #endif +#ifdef CONFIG_FAILSLAB + +static struct failslab_attr { + + struct fault_attr attr; + + u32 ignore_gfp_wait; +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + struct dentry *ignore_gfp_wait_file; +#endif + +} failslab = { + .attr = FAULT_ATTR_INITIALIZER, + .ignore_gfp_wait = 1, +}; + +static int __init setup_failslab(char *str) +{ + return setup_fault_attr(&failslab.attr, str); +} +__setup("failslab=", setup_failslab); + +static int should_failslab(struct kmem_cache *cachep, gfp_t flags) +{ + if (cachep == &cache_cache) + return 0; + if (flags & __GFP_NOFAIL) + return 0; + if (failslab.ignore_gfp_wait && (flags & __GFP_WAIT)) + return 0; + + return should_fail(&failslab.attr, obj_size(cachep)); +} + +#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS + +static int __init failslab_debugfs(void) +{ + mode_t mode = S_IFREG | S_IRUSR | S_IWUSR; + struct dentry *dir; + int err; + + err = init_fault_attr_dentries(&failslab.attr, "failslab"); + if (err) + return err; + dir = failslab.attr.dentries.dir; + + failslab.ignore_gfp_wait_file = + debugfs_create_bool("ignore-gfp-wait", mode, dir, + &failslab.ignore_gfp_wait); + + if (!failslab.ignore_gfp_wait_file) { + err = -ENOMEM; + debugfs_remove(failslab.ignore_gfp_wait_file); + cleanup_fault_attr_dentries(&failslab.attr); + } + + return err; +} + +late_initcall(failslab_debugfs); + +#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */ + +#else /* CONFIG_FAILSLAB */ + +static inline int should_failslab(struct kmem_cache *cachep, gfp_t flags) +{ + return 0; +} + +#endif /* CONFIG_FAILSLAB */ + static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags) { void *objp; struct array_cache *ac; -#ifdef CONFIG_NUMA - if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) { - objp = alternate_node_alloc(cachep, flags); - if (objp != NULL) - return objp; - } -#endif - check_irq_off(); + + if (should_failslab(cachep, flags)) + return NULL; + ac = cpu_cache_get(cachep); if (likely(ac->avail)) { STATS_INC_ALLOCHIT(cachep); @@ -3055,12 +3189,24 @@ static __always_inline void *__cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller) { unsigned long save_flags; - void *objp; + void *objp = NULL; cache_alloc_debugcheck_before(cachep, flags); local_irq_save(save_flags); - objp = ____cache_alloc(cachep, flags); + + if (unlikely(NUMA_BUILD && + current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) + objp = alternate_node_alloc(cachep, flags); + + if (!objp) + objp = ____cache_alloc(cachep, flags); + /* + * We may just have run out of memory on the local node. + * ____cache_alloc_node() knows how to locate memory on other nodes + */ + if (NUMA_BUILD && !objp) + objp = ____cache_alloc_node(cachep, flags, numa_node_id()); local_irq_restore(save_flags); objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller); @@ -3079,7 +3225,7 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) { int nid_alloc, nid_here; - if (in_interrupt()) + if (in_interrupt() || (flags & __GFP_THISNODE)) return NULL; nid_alloc = nid_here = numa_node_id(); if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD)) @@ -3087,14 +3233,77 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) else if (current->mempolicy) nid_alloc = slab_node(current->mempolicy); if (nid_alloc != nid_here) - return __cache_alloc_node(cachep, flags, nid_alloc); + return ____cache_alloc_node(cachep, flags, nid_alloc); return NULL; } /* + * Fallback function if there was no memory available and no objects on a + * certain node and fall back is permitted. First we scan all the + * available nodelists for available objects. If that fails then we + * perform an allocation without specifying a node. This allows the page + * allocator to do its reclaim / fallback magic. We then insert the + * slab into the proper nodelist and then allocate from it. + */ +void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) +{ + struct zonelist *zonelist = &NODE_DATA(slab_node(current->mempolicy)) + ->node_zonelists[gfp_zone(flags)]; + struct zone **z; + void *obj = NULL; + int nid; + +retry: + /* + * Look through allowed nodes for objects available + * from existing per node queues. + */ + for (z = zonelist->zones; *z && !obj; z++) { + nid = zone_to_nid(*z); + + if (cpuset_zone_allowed(*z, flags | __GFP_HARDWALL) && + cache->nodelists[nid] && + cache->nodelists[nid]->free_objects) + obj = ____cache_alloc_node(cache, + flags | GFP_THISNODE, nid); + } + + if (!obj) { + /* + * This allocation will be performed within the constraints + * of the current cpuset / memory policy requirements. + * We may trigger various forms of reclaim on the allowed + * set and go into memory reserves if necessary. + */ + obj = kmem_getpages(cache, flags, -1); + if (obj) { + /* + * Insert into the appropriate per node queues + */ + nid = page_to_nid(virt_to_page(obj)); + if (cache_grow(cache, flags, nid, obj)) { + obj = ____cache_alloc_node(cache, + flags | GFP_THISNODE, nid); + if (!obj) + /* + * Another processor may allocate the + * objects in the slab since we are + * not holding any locks. + */ + goto retry; + } else { + kmem_freepages(cache, obj); + obj = NULL; + } + } + } + return obj; +} + +/* * A interface to enable slab creation on nodeid */ -static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, +static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) { struct list_head *entry; @@ -3143,12 +3352,16 @@ retry: must_grow: spin_unlock(&l3->list_lock); - x = cache_grow(cachep, flags, nodeid); + x = cache_grow(cachep, flags | GFP_THISNODE, nodeid, NULL); + if (x) + goto retry; - if (!x) - return NULL; + if (!(flags & __GFP_THISNODE)) + /* Unable to grow the cache. Fall back to other nodes. */ + return fallback_alloc(cachep, flags); + + return NULL; - goto retry; done: return obj; } @@ -3357,35 +3570,59 @@ out: * @flags: See kmalloc(). * @nodeid: node number of the target node. * - * Identical to kmem_cache_alloc, except that this function is slow - * and can sleep. And it will allocate memory on the given node, which - * can improve the performance for cpu bound structures. - * New and improved: it will now make sure that the object gets - * put on the correct node list so that there is no false sharing. + * Identical to kmem_cache_alloc but it will allocate memory on the given + * node, which can improve the performance for cpu bound structures. + * + * Fallback to other node is possible if __GFP_THISNODE is not set. */ -void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) +static __always_inline void * +__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, + int nodeid, void *caller) { unsigned long save_flags; - void *ptr; + void *ptr = NULL; cache_alloc_debugcheck_before(cachep, flags); local_irq_save(save_flags); - if (nodeid == -1 || nodeid == numa_node_id() || - !cachep->nodelists[nodeid]) - ptr = ____cache_alloc(cachep, flags); - else - ptr = __cache_alloc_node(cachep, flags, nodeid); - local_irq_restore(save_flags); + if (unlikely(nodeid == -1)) + nodeid = numa_node_id(); + + if (likely(cachep->nodelists[nodeid])) { + if (nodeid == numa_node_id()) { + /* + * Use the locally cached objects if possible. + * However ____cache_alloc does not allow fallback + * to other nodes. It may fail while we still have + * objects on other nodes available. + */ + ptr = ____cache_alloc(cachep, flags); + } + if (!ptr) { + /* ___cache_alloc_node can fall back to other nodes */ + ptr = ____cache_alloc_node(cachep, flags, nodeid); + } + } else { + /* Node not bootstrapped yet */ + if (!(flags & __GFP_THISNODE)) + ptr = fallback_alloc(cachep, flags); + } - ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, - __builtin_return_address(0)); + local_irq_restore(save_flags); + ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller); return ptr; } + +void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid) +{ + return __cache_alloc_node(cachep, flags, nodeid, + __builtin_return_address(0)); +} EXPORT_SYMBOL(kmem_cache_alloc_node); -void *__kmalloc_node(size_t size, gfp_t flags, int node) +static __always_inline void * +__do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller) { struct kmem_cache *cachep; @@ -3394,8 +3631,29 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) return NULL; return kmem_cache_alloc_node(cachep, flags, node); } + +#ifdef CONFIG_DEBUG_SLAB +void *__kmalloc_node(size_t size, gfp_t flags, int node) +{ + return __do_kmalloc_node(size, flags, node, + __builtin_return_address(0)); +} EXPORT_SYMBOL(__kmalloc_node); -#endif + +void *__kmalloc_node_track_caller(size_t size, gfp_t flags, + int node, void *caller) +{ + return __do_kmalloc_node(size, flags, node, caller); +} +EXPORT_SYMBOL(__kmalloc_node_track_caller); +#else +void *__kmalloc_node(size_t size, gfp_t flags, int node) +{ + return __do_kmalloc_node(size, flags, node, NULL); +} +EXPORT_SYMBOL(__kmalloc_node); +#endif /* CONFIG_DEBUG_SLAB */ +#endif /* CONFIG_NUMA */ /** * __do_kmalloc - allocate memory @@ -3420,22 +3678,25 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, } +#ifdef CONFIG_DEBUG_SLAB void *__kmalloc(size_t size, gfp_t flags) { -#ifndef CONFIG_DEBUG_SLAB - return __do_kmalloc(size, flags, NULL); -#else return __do_kmalloc(size, flags, __builtin_return_address(0)); -#endif } EXPORT_SYMBOL(__kmalloc); -#ifdef CONFIG_DEBUG_SLAB void *__kmalloc_track_caller(size_t size, gfp_t flags, void *caller) { return __do_kmalloc(size, flags, caller); } EXPORT_SYMBOL(__kmalloc_track_caller); + +#else +void *__kmalloc(size_t size, gfp_t flags) +{ + return __do_kmalloc(size, flags, NULL); +} +EXPORT_SYMBOL(__kmalloc); #endif /** @@ -3503,13 +3764,15 @@ static int alloc_kmemlist(struct kmem_cache *cachep) int node; struct kmem_list3 *l3; struct array_cache *new_shared; - struct array_cache **new_alien; + struct array_cache **new_alien = NULL; for_each_online_node(node) { - new_alien = alloc_alien_cache(node, cachep->limit); - if (!new_alien) - goto fail; + if (use_alien_caches) { + new_alien = alloc_alien_cache(node, cachep->limit); + if (!new_alien) + goto fail; + } new_shared = alloc_arraycache(node, cachep->shared*cachep->batchcount, @@ -3735,7 +3998,7 @@ void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3, * If we cannot acquire the cache chain mutex then just give up - we'll try * again on the next iteration. */ -static void cache_reap(void *unused) +static void cache_reap(struct work_struct *unused) { struct kmem_cache *searchp; struct kmem_list3 *l3; @@ -3744,7 +4007,7 @@ static void cache_reap(void *unused) if (!mutex_trylock(&cache_chain_mutex)) { /* Give up. Setup the next iteration. */ schedule_delayed_work(&__get_cpu_var(reap_work), - REAPTIMEOUT_CPUC); + round_jiffies_relative(REAPTIMEOUT_CPUC)); return; } @@ -3790,7 +4053,8 @@ next: next_reap_node(); refresh_cpu_vm_stats(smp_processor_id()); /* Set up the next iteration */ - schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC); + schedule_delayed_work(&__get_cpu_var(reap_work), + round_jiffies_relative(REAPTIMEOUT_CPUC)); } #ifdef CONFIG_PROC_FS @@ -3958,7 +4222,7 @@ static int s_show(struct seq_file *m, void *p) * + further values on SMP and with statistics enabled */ -struct seq_operations slabinfo_op = { +const struct seq_operations slabinfo_op = { .start = s_start, .next = s_next, .stop = s_stop, @@ -4156,7 +4420,7 @@ static int leaks_show(struct seq_file *m, void *p) return 0; } -struct seq_operations slabstats_op = { +const struct seq_operations slabstats_op = { .start = leaks_start, .next = s_next, .stop = s_stop, diff --git a/mm/slob.c b/mm/slob.c index 20188627347..542394184a5 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -270,10 +270,9 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, } EXPORT_SYMBOL(kmem_cache_create); -int kmem_cache_destroy(struct kmem_cache *c) +void kmem_cache_destroy(struct kmem_cache *c) { slob_free(c, sizeof(struct kmem_cache)); - return 0; } EXPORT_SYMBOL(kmem_cache_destroy); diff --git a/mm/sparse.c b/mm/sparse.c index 86c52ab8087..ac26eb0d73c 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -24,6 +24,25 @@ struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT] #endif EXPORT_SYMBOL(mem_section); +#ifdef NODE_NOT_IN_PAGE_FLAGS +/* + * If we did not store the node number in the page then we have to + * do a lookup in the section_to_node_table in order to find which + * node the page belongs to. + */ +#if MAX_NUMNODES <= 256 +static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned; +#else +static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned; +#endif + +int page_to_nid(struct page *page) +{ + return section_to_node_table[page_to_section(page)]; +} +EXPORT_SYMBOL(page_to_nid); +#endif + #ifdef CONFIG_SPARSEMEM_EXTREME static struct mem_section *sparse_index_alloc(int nid) { @@ -49,6 +68,10 @@ static int sparse_index_init(unsigned long section_nr, int nid) struct mem_section *section; int ret = 0; +#ifdef NODE_NOT_IN_PAGE_FLAGS + section_to_node_table[section_nr] = nid; +#endif + if (mem_section[root]) return -EEXIST; @@ -211,7 +234,7 @@ 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/swap.c b/mm/swap.c index 2e0e871f542..2ed7be39795 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -57,9 +57,9 @@ static void put_compound_page(struct page *page) { page = (struct page *)page_private(page); if (put_page_testzero(page)) { - void (*dtor)(struct page *page); + compound_page_dtor *dtor; - dtor = (void (*)(struct page *))page[1].lru.next; + dtor = get_compound_page_dtor(page); (*dtor)(page); } } @@ -216,7 +216,7 @@ void lru_add_drain(void) } #ifdef CONFIG_NUMA -static void lru_add_drain_per_cpu(void *dummy) +static void lru_add_drain_per_cpu(struct work_struct *dummy) { lru_add_drain(); } @@ -226,7 +226,7 @@ static void lru_add_drain_per_cpu(void *dummy) */ int lru_add_drain_all(void) { - return schedule_on_each_cpu(lru_add_drain_per_cpu, NULL); + return schedule_on_each_cpu(lru_add_drain_per_cpu); } #else @@ -514,5 +514,7 @@ void __init swap_setup(void) * Right now other parts of the system means that we * _really_ don't want to cluster much more */ +#ifdef CONFIG_HOTPLUG_CPU hotcpu_notifier(cpu_swap_callback, 0); +#endif } diff --git a/mm/swapfile.c b/mm/swapfile.c index f1f5ec78378..b9fc0e5de6d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -427,34 +427,48 @@ void free_swap_and_cache(swp_entry_t entry) #ifdef CONFIG_SOFTWARE_SUSPEND /* - * Find the swap type that corresponds to given device (if any) + * Find the swap type that corresponds to given device (if any). * - * This is needed for software suspend and is done in such a way that inode - * aliasing is allowed. + * @offset - number of the PAGE_SIZE-sized block of the device, starting + * from 0, in which the swap header is expected to be located. + * + * This is needed for the suspend to disk (aka swsusp). */ -int swap_type_of(dev_t device) +int swap_type_of(dev_t device, sector_t offset) { + struct block_device *bdev = NULL; int i; + if (device) + bdev = bdget(device); + spin_lock(&swap_lock); for (i = 0; i < nr_swapfiles; i++) { - struct inode *inode; + struct swap_info_struct *sis = swap_info + i; - if (!(swap_info[i].flags & SWP_WRITEOK)) + if (!(sis->flags & SWP_WRITEOK)) continue; - if (!device) { + if (!bdev) { spin_unlock(&swap_lock); return i; } - inode = swap_info[i].swap_file->f_dentry->d_inode; - if (S_ISBLK(inode->i_mode) && - device == MKDEV(imajor(inode), iminor(inode))) { - spin_unlock(&swap_lock); - return i; + if (bdev == sis->bdev) { + struct swap_extent *se; + + se = list_entry(sis->extent_list.next, + struct swap_extent, list); + if (se->start_block == offset) { + spin_unlock(&swap_lock); + bdput(bdev); + return i; + } } } spin_unlock(&swap_lock); + if (bdev) + bdput(bdev); + return -ENODEV; } @@ -931,6 +945,23 @@ sector_t map_swap_page(struct swap_info_struct *sis, pgoff_t offset) } } +#ifdef CONFIG_SOFTWARE_SUSPEND +/* + * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev + * corresponding to given index in swap_info (swap type). + */ +sector_t swapdev_block(int swap_type, pgoff_t offset) +{ + struct swap_info_struct *sis; + + if (swap_type >= nr_swapfiles) + return 0; + + sis = swap_info + swap_type; + return (sis->flags & SWP_WRITEOK) ? map_swap_page(sis, offset) : 0; +} +#endif /* CONFIG_SOFTWARE_SUSPEND */ + /* * Free all of a swapdev's extent information */ @@ -1274,10 +1305,13 @@ static void *swap_start(struct seq_file *swap, loff_t *pos) mutex_lock(&swapon_mutex); + if (!l) + return SEQ_START_TOKEN; + for (i = 0; i < nr_swapfiles; i++, ptr++) { if (!(ptr->flags & SWP_USED) || !ptr->swap_map) continue; - if (!l--) + if (!--l) return ptr; } @@ -1286,10 +1320,17 @@ static void *swap_start(struct seq_file *swap, loff_t *pos) static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { - struct swap_info_struct *ptr = v; + struct swap_info_struct *ptr; struct swap_info_struct *endptr = swap_info + nr_swapfiles; - for (++ptr; ptr < endptr; ptr++) { + if (v == SEQ_START_TOKEN) + ptr = swap_info; + else { + ptr = v; + ptr++; + } + + for (; ptr < endptr; ptr++) { if (!(ptr->flags & SWP_USED) || !ptr->swap_map) continue; ++*pos; @@ -1310,14 +1351,16 @@ static int swap_show(struct seq_file *swap, void *v) struct file *file; int len; - if (v == swap_info) - seq_puts(swap, "Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n"); + if (ptr == SEQ_START_TOKEN) { + seq_puts(swap,"Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n"); + return 0; + } file = ptr->swap_file; - len = seq_path(swap, file->f_vfsmnt, file->f_dentry, " \t\n\\"); + len = seq_path(swap, file->f_path.mnt, file->f_path.dentry, " \t\n\\"); seq_printf(swap, "%*s%s\t%u\t%u\t%d\n", len < 40 ? 40 - len : 1, " ", - S_ISBLK(file->f_dentry->d_inode->i_mode) ? + S_ISBLK(file->f_path.dentry->d_inode->i_mode) ? "partition" : "file\t", ptr->pages << (PAGE_SHIFT - 10), ptr->inuse_pages << (PAGE_SHIFT - 10), @@ -1325,7 +1368,7 @@ static int swap_show(struct seq_file *swap, void *v) return 0; } -static struct seq_operations swaps_op = { +static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, @@ -1337,7 +1380,7 @@ static int swaps_open(struct inode *inode, struct file *file) return seq_open(file, &swaps_op); } -static struct file_operations proc_swaps_operations = { +static const struct file_operations proc_swaps_operations = { .open = swaps_open, .read = seq_read, .llseek = seq_lseek, @@ -1540,6 +1583,11 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) error = -EINVAL; if (!maxpages) goto bad_swap; + if (swapfilesize && maxpages > swapfilesize) { + printk(KERN_WARNING + "Swap area shorter than signature indicates\n"); + goto bad_swap; + } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) goto bad_swap; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) @@ -1567,12 +1615,6 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags) goto bad_swap; } - if (swapfilesize && maxpages > swapfilesize) { - printk(KERN_WARNING - "Swap area shorter than signature indicates\n"); - error = -EINVAL; - goto bad_swap; - } if (nr_good_pages) { p->swap_map[0] = SWAP_MAP_BAD; p->max = maxpages; @@ -1723,13 +1765,14 @@ get_swap_info_struct(unsigned type) */ int valid_swaphandles(swp_entry_t entry, unsigned long *offset) { - int ret = 0, i = 1 << page_cluster; + int our_page_cluster = page_cluster; + int ret = 0, i = 1 << our_page_cluster; unsigned long toff; struct swap_info_struct *swapdev = swp_type(entry) + swap_info; - if (!page_cluster) /* no readahead */ + if (!our_page_cluster) /* no readahead */ return 0; - toff = (swp_offset(entry) >> page_cluster) << page_cluster; + toff = (swp_offset(entry) >> our_page_cluster) << our_page_cluster; if (!toff) /* first page is swap header */ toff++, i--; *offset = toff; diff --git a/mm/thrash.c b/mm/thrash.c index f4c560b4a2b..9ef9071f99b 100644 --- a/mm/thrash.c +++ b/mm/thrash.c @@ -7,100 +7,74 @@ * * Simple token based thrashing protection, using the algorithm * described in: http://www.cs.wm.edu/~sjiang/token.pdf + * + * Sep 2006, Ashwin Chaugule <ashwin.chaugule@celunite.com> + * Improved algorithm to pass token: + * Each task has a priority which is incremented if it contended + * for the token in an interval less than its previous attempt. + * If the token is acquired, that task's priority is boosted to prevent + * the token from bouncing around too often and to let the task make + * some progress in its execution. */ + #include <linux/jiffies.h> #include <linux/mm.h> #include <linux/sched.h> #include <linux/swap.h> static DEFINE_SPINLOCK(swap_token_lock); -static unsigned long swap_token_timeout; -static unsigned long swap_token_check; -struct mm_struct * swap_token_mm = &init_mm; - -#define SWAP_TOKEN_CHECK_INTERVAL (HZ * 2) -#define SWAP_TOKEN_TIMEOUT (300 * HZ) -/* - * Currently disabled; Needs further code to work at HZ * 300. - */ -unsigned long swap_token_default_timeout = SWAP_TOKEN_TIMEOUT; - -/* - * Take the token away if the process had no page faults - * in the last interval, or if it has held the token for - * too long. - */ -#define SWAP_TOKEN_ENOUGH_RSS 1 -#define SWAP_TOKEN_TIMED_OUT 2 -static int should_release_swap_token(struct mm_struct *mm) -{ - int ret = 0; - if (!mm->recent_pagein) - ret = SWAP_TOKEN_ENOUGH_RSS; - else if (time_after(jiffies, swap_token_timeout)) - ret = SWAP_TOKEN_TIMED_OUT; - mm->recent_pagein = 0; - return ret; -} +struct mm_struct *swap_token_mm; +static unsigned int global_faults; -/* - * Try to grab the swapout protection token. We only try to - * grab it once every TOKEN_CHECK_INTERVAL, both to prevent - * SMP lock contention and to check that the process that held - * the token before is no longer thrashing. - */ void grab_swap_token(void) { - struct mm_struct *mm; - int reason; + int current_interval; - /* We have the token. Let others know we still need it. */ - if (has_swap_token(current->mm)) { - current->mm->recent_pagein = 1; - if (unlikely(!swap_token_default_timeout)) - disable_swap_token(); - return; - } - - if (time_after(jiffies, swap_token_check)) { + global_faults++; - if (!swap_token_default_timeout) { - swap_token_check = jiffies + SWAP_TOKEN_CHECK_INTERVAL; - return; - } - - /* ... or if we recently held the token. */ - if (time_before(jiffies, current->mm->swap_token_time)) - return; + current_interval = global_faults - current->mm->faultstamp; - if (!spin_trylock(&swap_token_lock)) - return; + if (!spin_trylock(&swap_token_lock)) + return; - swap_token_check = jiffies + SWAP_TOKEN_CHECK_INTERVAL; + /* First come first served */ + if (swap_token_mm == NULL) { + current->mm->token_priority = current->mm->token_priority + 2; + swap_token_mm = current->mm; + goto out; + } - mm = swap_token_mm; - if ((reason = should_release_swap_token(mm))) { - unsigned long eligible = jiffies; - if (reason == SWAP_TOKEN_TIMED_OUT) { - eligible += swap_token_default_timeout; - } - mm->swap_token_time = eligible; - swap_token_timeout = jiffies + swap_token_default_timeout; + if (current->mm != swap_token_mm) { + if (current_interval < current->mm->last_interval) + current->mm->token_priority++; + else { + current->mm->token_priority--; + if (unlikely(current->mm->token_priority < 0)) + current->mm->token_priority = 0; + } + /* Check if we deserve the token */ + if (current->mm->token_priority > + swap_token_mm->token_priority) { + current->mm->token_priority += 2; swap_token_mm = current->mm; } - spin_unlock(&swap_token_lock); + } else { + /* Token holder came in again! */ + current->mm->token_priority += 2; } - return; + +out: + current->mm->faultstamp = global_faults; + current->mm->last_interval = current_interval; + spin_unlock(&swap_token_lock); +return; } /* Called on process exit. */ void __put_swap_token(struct mm_struct *mm) { spin_lock(&swap_token_lock); - if (likely(mm == swap_token_mm)) { - mm->swap_token_time = jiffies + SWAP_TOKEN_CHECK_INTERVAL; - swap_token_mm = &init_mm; - swap_token_check = jiffies; - } + if (likely(mm == swap_token_mm)) + swap_token_mm = NULL; spin_unlock(&swap_token_lock); } diff --git a/mm/tiny-shmem.c b/mm/tiny-shmem.c index 5f2cbf0f153..c7f6e1914bc 100644 --- a/mm/tiny-shmem.c +++ b/mm/tiny-shmem.c @@ -79,8 +79,8 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags) d_instantiate(dentry, inode); inode->i_nlink = 0; /* It is unlinked */ - file->f_vfsmnt = mntget(shm_mnt); - file->f_dentry = dentry; + file->f_path.mnt = mntget(shm_mnt); + file->f_path.dentry = dentry; file->f_mapping = inode->i_mapping; file->f_op = &ramfs_file_operations; file->f_mode = FMODE_WRITE | FMODE_READ; diff --git a/mm/truncate.c b/mm/truncate.c index c6ab55ec688..9bfb8e85386 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -9,13 +9,41 @@ #include <linux/kernel.h> #include <linux/mm.h> +#include <linux/swap.h> #include <linux/module.h> #include <linux/pagemap.h> #include <linux/pagevec.h> +#include <linux/task_io_accounting_ops.h> #include <linux/buffer_head.h> /* grr. try_to_release_page, do_invalidatepage */ +/** + * do_invalidatepage - invalidate part of all of a page + * @page: the page which is affected + * @offset: the index of the truncation point + * + * do_invalidatepage() is called when all or part of the page has become + * invalidated by a truncate operation. + * + * do_invalidatepage() does not have to release all buffers, but it must + * ensure that no dirty buffer is left outside @offset and that no I/O + * is underway against any of the blocks which are outside the truncation + * point. Because the caller is about to free (and possibly reuse) those + * blocks on-disk. + */ +void do_invalidatepage(struct page *page, unsigned long offset) +{ + void (*invalidatepage)(struct page *, unsigned long); + invalidatepage = page->mapping->a_ops->invalidatepage; +#ifdef CONFIG_BLOCK + if (!invalidatepage) + invalidatepage = block_invalidatepage; +#endif + if (invalidatepage) + (*invalidatepage)(page, offset); +} + static inline void truncate_partial_page(struct page *page, unsigned partial) { memclear_highpage_flush(page, partial, PAGE_CACHE_SIZE-partial); @@ -42,7 +70,8 @@ truncate_complete_page(struct address_space *mapping, struct page *page) if (PagePrivate(page)) do_invalidatepage(page, 0); - clear_page_dirty(page); + if (test_clear_page_dirty(page)) + task_io_account_cancelled_write(PAGE_CACHE_SIZE); ClearPageUptodate(page); ClearPageMappedToDisk(page); remove_from_page_cache(page); @@ -52,36 +81,25 @@ truncate_complete_page(struct address_space *mapping, struct page *page) /* * This is for invalidate_inode_pages(). That function can be called at * any time, and is not supposed to throw away dirty pages. But pages can - * be marked dirty at any time too. So we re-check the dirtiness inside - * ->tree_lock. That provides exclusion against the __set_page_dirty - * functions. + * be marked dirty at any time too, so use remove_mapping which safely + * discards clean, unused pages. * * Returns non-zero if the page was successfully invalidated. */ static int invalidate_complete_page(struct address_space *mapping, struct page *page) { + int ret; + if (page->mapping != mapping) return 0; if (PagePrivate(page) && !try_to_release_page(page, 0)) return 0; - write_lock_irq(&mapping->tree_lock); - if (PageDirty(page)) - goto failed; - if (page_count(page) != 2) /* caller's ref + pagecache ref */ - goto failed; + ret = remove_mapping(mapping, page); - BUG_ON(PagePrivate(page)); - __remove_from_page_cache(page); - write_unlock_irq(&mapping->tree_lock); - ClearPageUptodate(page); - page_cache_release(page); /* pagecache ref */ - return 1; -failed: - write_unlock_irq(&mapping->tree_lock); - return 0; + return ret; } /** @@ -270,9 +288,39 @@ unsigned long invalidate_inode_pages(struct address_space *mapping) { return invalidate_mapping_pages(mapping, 0, ~0UL); } - EXPORT_SYMBOL(invalidate_inode_pages); +/* + * This is like invalidate_complete_page(), except it ignores the page's + * refcount. We do this because invalidate_inode_pages2() needs stronger + * invalidation guarantees, and cannot afford to leave pages behind because + * shrink_list() has a temp ref on them, or because they're transiently sitting + * in the lru_cache_add() pagevecs. + */ +static int +invalidate_complete_page2(struct address_space *mapping, struct page *page) +{ + if (page->mapping != mapping) + return 0; + + if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL)) + return 0; + + write_lock_irq(&mapping->tree_lock); + if (PageDirty(page)) + goto failed; + + BUG_ON(PagePrivate(page)); + __remove_from_page_cache(page); + write_unlock_irq(&mapping->tree_lock); + ClearPageUptodate(page); + page_cache_release(page); /* pagecache ref */ + return 1; +failed: + write_unlock_irq(&mapping->tree_lock); + return 0; +} + /** * invalidate_inode_pages2_range - remove range of pages from an address_space * @mapping: the address_space @@ -339,7 +387,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, } } was_dirty = test_clear_page_dirty(page); - if (!invalidate_complete_page(mapping, page)) { + if (!invalidate_complete_page2(mapping, page)) { if (was_dirty) set_page_dirty(page); ret = -EIO; @@ -349,6 +397,7 @@ 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/util.c b/mm/util.c index 7368479220b..ace2aea69f1 100644 --- a/mm/util.c +++ b/mm/util.c @@ -11,7 +11,7 @@ */ void *__kzalloc(size_t size, gfp_t flags) { - void *ret = ____kmalloc(size, flags); + void *ret = kmalloc_track_caller(size, flags); if (ret) memset(ret, 0, size); return ret; @@ -33,13 +33,31 @@ char *kstrdup(const char *s, gfp_t gfp) return NULL; len = strlen(s) + 1; - buf = ____kmalloc(len, gfp); + buf = kmalloc_track_caller(len, gfp); if (buf) memcpy(buf, s, len); return buf; } EXPORT_SYMBOL(kstrdup); +/** + * kmemdup - duplicate region of memory + * + * @src: memory region to duplicate + * @len: memory region length + * @gfp: GFP mask to use + */ +void *kmemdup(const void *src, size_t len, gfp_t gfp) +{ + void *p; + + p = kmalloc_track_caller(len, gfp); + if (p) + memcpy(p, src, len); + return p; +} +EXPORT_SYMBOL(kmemdup); + /* * strndup_user - duplicate an existing string from user space * diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 9aad8b0cc6e..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); @@ -179,15 +181,12 @@ struct vm_struct *__get_vm_area_node(unsigned long size, unsigned long flags, } addr = ALIGN(start, align); size = PAGE_ALIGN(size); - - area = kmalloc_node(sizeof(*area), GFP_KERNEL, node); - if (unlikely(!area)) + if (unlikely(!size)) return NULL; - if (unlikely(!size)) { - kfree (area); + area = kmalloc_node(sizeof(*area), gfp_mask & GFP_LEVEL_MASK, node); + if (unlikely(!area)) return NULL; - } /* * We always allocate a guard page. @@ -236,12 +235,11 @@ 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); } /** * get_vm_area - reserve a contingous kernel virtual area - * * @size: size of the area * @flags: %VM_IOREMAP for I/O mappings or VM_ALLOC * @@ -254,9 +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 */ @@ -273,7 +273,7 @@ static struct vm_struct *__find_vm_area(void *addr) } /* Caller must hold vmlist_lock */ -struct vm_struct *__remove_vm_area(void *addr) +static struct vm_struct *__remove_vm_area(void *addr) { struct vm_struct **p, *tmp; @@ -296,7 +296,6 @@ found: /** * remove_vm_area - find and remove a contingous kernel virtual area - * * @addr: base address * * Search for the kernel VM area starting at @addr, and remove it. @@ -355,7 +354,6 @@ void __vunmap(void *addr, int deallocate_pages) /** * vfree - release memory allocated by vmalloc() - * * @addr: memory base address * * Free the virtually contiguous memory area starting at @addr, as @@ -373,7 +371,6 @@ EXPORT_SYMBOL(vfree); /** * vunmap - release virtual mapping obtained by vmap() - * * @addr: memory base address * * Free the virtually contiguous memory area starting at @addr, @@ -390,7 +387,6 @@ EXPORT_SYMBOL(vunmap); /** * vmap - map an array of pages into virtually contiguous space - * * @pages: array of page pointers * @count: number of pages to map * @flags: vm_area->flags @@ -433,8 +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); @@ -471,7 +470,6 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) /** * __vmalloc_node - allocate virtually contiguous memory - * * @size: allocation size * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages @@ -490,7 +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; @@ -505,13 +503,11 @@ EXPORT_SYMBOL(__vmalloc); /** * vmalloc - allocate virtually contiguous memory - * * @size: allocation size - * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * - * For tight cotrol over page level allocator and protection flags + * For tight control over page level allocator and protection flags * use __vmalloc() instead. */ void *vmalloc(unsigned long size) @@ -521,11 +517,11 @@ void *vmalloc(unsigned long size) EXPORT_SYMBOL(vmalloc); /** - * vmalloc_user - allocate virtually contiguous memory which has - * been zeroed so it can be mapped to userspace without - * leaking data. + * vmalloc_user - allocate zeroed virtually contiguous memory for userspace + * @size: allocation size * - * @size: allocation size + * The resulting memory area is zeroed so it can be mapped to userspace + * without leaking data. */ void *vmalloc_user(unsigned long size) { @@ -533,25 +529,25 @@ 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); /** * vmalloc_node - allocate memory on a specific node - * * @size: allocation size * @node: numa node * * Allocate enough pages to cover @size from the page level * allocator and map them into contiguous kernel virtual space. * - * For tight cotrol over page level allocator and protection flags + * For tight control over page level allocator and protection flags * use __vmalloc() instead. */ void *vmalloc_node(unsigned long size, int node) @@ -566,14 +562,13 @@ EXPORT_SYMBOL(vmalloc_node); /** * vmalloc_exec - allocate virtually contiguous, executable memory - * * @size: allocation size * * Kernel-internal function to allocate enough pages to cover @size * the page level allocator and map them into contiguous and * executable kernel virtual space. * - * For tight cotrol over page level allocator and protection flags + * For tight control over page level allocator and protection flags * use __vmalloc() instead. */ @@ -584,7 +579,6 @@ void *vmalloc_exec(unsigned long size) /** * vmalloc_32 - allocate virtually contiguous memory (32bit addressable) - * * @size: allocation size * * Allocate enough 32bit PA addressable pages to cover @size from the @@ -597,11 +591,11 @@ 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. - * + * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory * @size: allocation size + * + * The resulting memory area is 32bit addressable and zeroed so it can be + * mapped to userspace without leaking data. */ void *vmalloc_32_user(unsigned long size) { @@ -609,11 +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); @@ -695,7 +690,6 @@ finished: /** * 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 diff --git a/mm/vmscan.c b/mm/vmscan.c index 87779dda4ec..093f5fe6dd7 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -19,6 +19,7 @@ #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> +#include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> #include <linux/blkdev.h> @@ -35,6 +36,7 @@ #include <linux/rwsem.h> #include <linux/delay.h> #include <linux/kthread.h> +#include <linux/freezer.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -370,24 +372,49 @@ static pageout_t pageout(struct page *page, struct address_space *mapping) /* synchronous write or broken a_ops? */ ClearPageReclaim(page); } - + inc_zone_page_state(page, NR_VMSCAN_WRITE); return PAGE_SUCCESS; } 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)); BUG_ON(mapping != page_mapping(page)); write_lock_irq(&mapping->tree_lock); - /* - * The non-racy check for busy page. It is critical to check - * PageDirty _after_ making sure that the page is freeable and - * not in use by anybody. (pagecache + us == 2) + * The non racy check for a busy page. + * + * Must be careful with the order of the tests. When someone has + * a ref to the page, it may be possible that they dirty it then + * drop the reference. So if PageDirty is tested before page_count + * here, then the following race may occur: + * + * get_user_pages(&page); + * [user mapping goes away] + * write_to(page); + * !PageDirty(page) [good] + * SetPageDirty(page); + * put_page(page); + * !page_count(page) [good, discard it] + * + * [oops, our write_to data is lost] + * + * Reversing the order of the tests ensures such a situation cannot + * escape unnoticed. The smp_rmb is needed to ensure the page->flags + * load is not satisfied before that of page->_count. + * + * Note that if SetPageDirty is always performed via set_page_dirty, + * and thus under tree_lock, then this ordering is not required. */ if (unlikely(page_count(page) != 2)) goto cannot_free; @@ -697,6 +724,20 @@ 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; @@ -720,7 +761,7 @@ 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; @@ -744,7 +785,7 @@ 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 @@ -896,7 +937,7 @@ 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) { @@ -946,9 +987,7 @@ 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 */ @@ -998,7 +1037,6 @@ 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; } @@ -1033,19 +1071,28 @@ 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; } @@ -1085,6 +1132,11 @@ 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; @@ -1092,11 +1144,8 @@ 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 */ @@ -1124,11 +1173,12 @@ loop_again: if (!zone_watermark_ok(zone, order, zone->pages_high, 0, 0)) { end_zone = i; - goto scan; + break; } } - goto out; -scan: + if (i < 0) + goto out; + for (i = 0; i <= end_zone; i++) { struct zone *zone = pgdat->node_zones + i; @@ -1157,10 +1207,9 @@ 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, @@ -1188,7 +1237,7 @@ 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 @@ -1200,13 +1249,21 @@ 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(); + + try_to_freeze(); + goto loop_again; } @@ -1332,7 +1389,7 @@ 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); } } @@ -1432,7 +1489,7 @@ 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; @@ -1456,7 +1513,6 @@ out: } #endif -#ifdef CONFIG_HOTPLUG_CPU /* It's optimal to keep kswapds on the same CPUs as their memory, but not required for correctness. So if the last cpu in a node goes away, we get changed to run anywhere: as the first one comes back, @@ -1477,7 +1533,6 @@ static int __devinit cpu_callback(struct notifier_block *nfb, } return NOTIFY_OK; } -#endif /* CONFIG_HOTPLUG_CPU */ /* * This kswapd start function will be called by init and node-hot-add. @@ -1588,6 +1643,7 @@ 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 490d8c1a0de..dc005a0c96a 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -9,7 +9,6 @@ * Christoph Lameter <christoph@lameter.com> */ -#include <linux/config.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/cpu.h> @@ -371,7 +370,7 @@ void zone_statistics(struct zonelist *zonelist, struct zone *z) __inc_zone_state(z, NUMA_MISS); __inc_zone_state(zonelist->zones[0], NUMA_FOREIGN); } - if (z->zone_pgdat == NODE_DATA(numa_node_id())) + if (z->node == numa_node_id()) __inc_zone_state(z, NUMA_LOCAL); else __inc_zone_state(z, NUMA_OTHER); @@ -431,7 +430,7 @@ static int frag_show(struct seq_file *m, void *arg) return 0; } -struct seq_operations fragmentation_op = { +const struct seq_operations fragmentation_op = { .start = frag_start, .next = frag_next, .stop = frag_stop, @@ -453,7 +452,7 @@ struct seq_operations fragmentation_op = { #define TEXTS_FOR_ZONES(xx) xx "_dma", TEXT_FOR_DMA32(xx) xx "_normal", \ TEXT_FOR_HIGHMEM(xx) -static char *vmstat_text[] = { +static const char * const vmstat_text[] = { /* Zoned VM counters */ "nr_anon_pages", "nr_mapped", @@ -465,6 +464,7 @@ static char *vmstat_text[] = { "nr_writeback", "nr_unstable", "nr_bounce", + "nr_vmscan_write", #ifdef CONFIG_NUMA "numa_hit", @@ -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'); @@ -599,7 +597,7 @@ static int zoneinfo_show(struct seq_file *m, void *arg) return 0; } -struct seq_operations zoneinfo_op = { +const struct seq_operations zoneinfo_op = { .start = frag_start, /* iterate over all zones. The same as in * fragmentation. */ .next = frag_next, @@ -662,7 +660,7 @@ static void vmstat_stop(struct seq_file *m, void *arg) m->private = NULL; } -struct seq_operations vmstat_op = { +const struct seq_operations vmstat_op = { .start = vmstat_start, .next = vmstat_next, .stop = vmstat_stop, @@ -681,13 +679,13 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb, void *hcpu) { switch (action) { - case CPU_UP_PREPARE: - case CPU_UP_CANCELED: - case CPU_DEAD: - refresh_zone_stat_thresholds(); - break; - default: - break; + case CPU_UP_PREPARE: + case CPU_UP_CANCELED: + case CPU_DEAD: + refresh_zone_stat_thresholds(); + break; + default: + break; } return NOTIFY_OK; } |